From 9e738ea6ba24264a559368fd0408f73736b7c339 Mon Sep 17 00:00:00 2001 From: Minh Vu Date: Thu, 16 Jul 2026 14:57:56 +0200 Subject: [PATCH] fix(compute): handle comparison output offsets --- .../kernels/_lib/scalar_comparison.cc | 33 +- .../_lib/scalar_comparison_avx2_amd64.s | 96529 +++++++-------- .../_lib/scalar_comparison_sse4_amd64.s | 93385 ++++++++------- .../kernels/scalar_comparison_avx2_amd64.s | 98603 ++++++++-------- .../kernels/scalar_comparison_sse4_amd64.s | 85191 ++++++------- .../internal/kernels/scalar_comparisons.go | 26 +- .../kernels/scalar_comparisons_test.go | 119 + 7 files changed, 190517 insertions(+), 183369 deletions(-) create mode 100644 arrow/compute/internal/kernels/scalar_comparisons_test.go diff --git a/arrow/compute/internal/kernels/_lib/scalar_comparison.cc b/arrow/compute/internal/kernels/_lib/scalar_comparison.cc index 09540f367..794970a55 100644 --- a/arrow/compute/internal/kernels/_lib/scalar_comparison.cc +++ b/arrow/compute/internal/kernels/_lib/scalar_comparison.cc @@ -67,16 +67,21 @@ struct compare_primitive_arr_arr { const T* right = reinterpret_cast(right_void); uint8_t* out_bitmap = reinterpret_cast(out_void); static constexpr int kBatchSize = 32; - int64_t num_batches = length / kBatchSize; uint32_t temp_output[kBatchSize]; if (int prefix = offset % 8) { - for (int i = prefix; i < 8; ++i) { - set_bit_to(out_bitmap, i, Op::template Call(*left++, *right++)); + const int64_t prefix_length = length < 8 - prefix ? length : 8 - prefix; + for (int64_t i = 0; i < prefix_length; ++i) { + set_bit_to(out_bitmap, prefix + i, Op::template Call(*left++, *right++)); + } + length -= prefix_length; + if (length == 0) { + return; } out_bitmap++; } + int64_t num_batches = length / kBatchSize; for (int64_t j = 0; j < num_batches; ++j) { for (int i = 0; i < kBatchSize; ++i) { temp_output[i] = Op::template Call(*left++, *right++); @@ -98,16 +103,21 @@ struct compare_primitive_arr_scalar { const T right = *reinterpret_cast(right_void); uint8_t* out_bitmap = reinterpret_cast(out_void); static constexpr int kBatchSize = 32; - int64_t num_batches = length / kBatchSize; uint32_t temp_output[kBatchSize]; if (int prefix = offset % 8) { - for (int i = prefix; i < 8; ++i) { - set_bit_to(out_bitmap, i, Op::template Call(*left++, right)); + const int64_t prefix_length = length < 8 - prefix ? length : 8 - prefix; + for (int64_t i = 0; i < prefix_length; ++i) { + set_bit_to(out_bitmap, prefix + i, Op::template Call(*left++, right)); + } + length -= prefix_length; + if (length == 0) { + return; } out_bitmap++; } + int64_t num_batches = length / kBatchSize; for (int64_t j = 0; j < num_batches; ++j) { for (int i = 0; i < kBatchSize; ++i) { temp_output[i] = Op::template Call(*left++, right); @@ -129,16 +139,21 @@ struct compare_primitive_scalar_arr { const T* right = reinterpret_cast(right_void); uint8_t* out_bitmap = reinterpret_cast(out_void); static constexpr int kBatchSize = 32; - int64_t num_batches = length / kBatchSize; uint32_t temp_output[kBatchSize]; if (int prefix = offset % 8) { - for (int i = prefix; i < 8; ++i) { - set_bit_to(out_bitmap, i, Op::template Call(left, *right++)); + const int64_t prefix_length = length < 8 - prefix ? length : 8 - prefix; + for (int64_t i = 0; i < prefix_length; ++i) { + set_bit_to(out_bitmap, prefix + i, Op::template Call(left, *right++)); + } + length -= prefix_length; + if (length == 0) { + return; } out_bitmap++; } + int64_t num_batches = length / kBatchSize; for (int64_t j = 0; j < num_batches; ++j) { for (int i = 0; i < kBatchSize; ++i) { temp_output[i] = Op::template Call(left, *right++); diff --git a/arrow/compute/internal/kernels/_lib/scalar_comparison_avx2_amd64.s b/arrow/compute/internal/kernels/_lib/scalar_comparison_avx2_amd64.s index 593d4c45a..1c28cad72 100644 --- a/arrow/compute/internal/kernels/_lib/scalar_comparison_avx2_amd64.s +++ b/arrow/compute/internal/kernels/_lib/scalar_comparison_avx2_amd64.s @@ -15,104 +15,120 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 push rbx and rsp, -8 sub rsp, 72 - mov eax, r9d - mov r14, r8 - mov r12, rcx + # kill: def $r9d killed $r9d def $r9 + mov r12, r8 + mov r15, rcx cmp edi, 6 - jg .LBB0_29 + jg .LBB0_35 # %bb.1: cmp edi, 3 jle .LBB0_2 -# %bb.15: +# %bb.18: cmp edi, 4 - je .LBB0_68 -# %bb.16: + je .LBB0_83 +# %bb.19: cmp edi, 5 - je .LBB0_79 -# %bb.17: + je .LBB0_97 +# %bb.20: cmp edi, 6 - jne .LBB0_123 -# %bb.18: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_22 -# %bb.19: - cdqe + jne .LBB0_153 +# %bb.21: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_26 +# %bb.23: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_24: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_20 -# %bb.21: - add r12, 1 -.LBB0_22: - sar r15, 5 - cmp r14, 32 - jl .LBB0_26 -# %bb.23: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB0_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB0_26: + sub r12, r8 + je .LBB0_153 +# %bb.27: + add r15, 1 +.LBB0_28: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_32 +# %bb.29: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov eax, dword ptr [rsi + 12] cmp eax, dword ptr [rdx + 12] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov eax, dword ptr [rsi + 16] cmp eax, dword ptr [rdx + 16] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov eax, dword ptr [rsi + 20] cmp eax, dword ptr [rdx + 20] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov eax, dword ptr [rsi + 24] cmp eax, dword ptr [rdx + 24] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] sete r13b mov eax, dword ptr [rsi + 32] cmp eax, dword ptr [rdx + 32] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - sete r8b + sete dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] sete r11b @@ -121,21 +137,21 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r15b mov eax, dword ptr [rsi + 48] cmp eax, dword ptr [rdx + 48] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov eax, dword ptr [rsi + 56] cmp eax, dword ptr [rdx + 56] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov eax, dword ptr [rsi + 60] cmp eax, dword ptr [rdx + 60] - sete dil + sete r8b mov eax, dword ptr [rsi + 64] mov ebx, dword ptr [rsi + 68] cmp eax, dword ptr [rdx + 64] mov eax, dword ptr [rsi + 72] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 68] mov ebx, dword ptr [rsi + 76] sete r10b @@ -146,144 +162,144 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 mov ebx, dword ptr [rsi + 84] sete r12b cmp eax, dword ptr [rdx + 80] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 84] mov eax, dword ptr [rsi + 88] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] sete r9b cmp eax, dword ptr [rdx + 96] mov eax, dword ptr [rsi + 100] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 112] mov eax, dword ptr [rsi + 116] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 116] mov eax, dword ptr [rsi + 120] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 120] mov eax, dword ptr [rsi + 124] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_24 -# %bb.25: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_26: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.27: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_30 +# %bb.31: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_32: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB0_28: # =>This Inner Loop Header: Depth=1 +.LBB0_34: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -291,7 +307,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -299,106 +316,122 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_28 - jmp .LBB0_123 -.LBB0_29: + cmp r12, r8 + jne .LBB0_34 + jmp .LBB0_153 +.LBB0_35: cmp edi, 8 - jle .LBB0_30 -# %bb.43: + jle .LBB0_36 +# %bb.52: cmp edi, 9 - je .LBB0_101 -# %bb.44: + je .LBB0_125 +# %bb.53: cmp edi, 11 - je .LBB0_112 -# %bb.45: + je .LBB0_139 +# %bb.54: cmp edi, 12 - jne .LBB0_123 -# %bb.46: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_50 -# %bb.47: - movsxd r10, eax + jne .LBB0_153 +# %bb.55: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_60 +# %bb.57: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB0_48: # =>This Inner Loop Header: Depth=1 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - vucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - setnp cl +.LBB0_58: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + vmovsd xmm0, qword ptr [rsi + 8*r14] # xmm0 = mem[0],zero + vucomisd xmm0, qword ptr [rdx + 8*r14] + setnp r10b sete bl - and bl, cl + and bl, r10b neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d + lea eax, [8*rdi] + sub ecx, eax mov eax, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB0_48 -# %bb.49: - add r12, 1 -.LBB0_50: - sar r15, 5 - cmp r14, 32 - jl .LBB0_54 -# %bb.51: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -8 + cmp r8, r14 + jne .LBB0_58 +# %bb.59: + sub rsi, r11 + sub rdx, r11 +.LBB0_60: + sub r12, r8 + je .LBB0_153 +# %bb.61: + add r15, 1 +.LBB0_62: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_66 +# %bb.63: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx] vmovsd xmm0, qword ptr [rsi + 8] # xmm0 = mem[0],zero setnp al sete cl and cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill + mov byte ptr [rsp + 29], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 8] setnp al sete cl and cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill + mov byte ptr [rsp + 22], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 16] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 16] setnp al sete cl and cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill + mov byte ptr [rsp + 28], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 24] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 24] setnp al sete cl and cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill + mov byte ptr [rsp + 31], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 32] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 32] setnp al sete cl and cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill + mov byte ptr [rsp + 30], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 40] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 40] setnp al @@ -414,13 +447,13 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill + mov byte ptr [rsp + 12], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill + mov byte ptr [rsp + 27], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 72] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 72] setnp al @@ -431,117 +464,116 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill + mov byte ptr [rsp + 26], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 88] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 88] setnp al sete cl and cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill + mov byte ptr [rsp + 25], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 96] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 96] setnp al sete cl and cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 11], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 104] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 104] setnp al sete cl and cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 112] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 112] setnp al sete cl and cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill + mov byte ptr [rsp + 21], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 120] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 120] setnp al sete cl and cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill + mov byte ptr [rsp + 20], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 128] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 128] setnp al sete cl and cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill + mov byte ptr [rsp + 23], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 136] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 136] setnp al sete cl and cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill + mov byte ptr [rsp + 19], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 144] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 144] setnp al sete cl and cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill + mov byte ptr [rsp + 18], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 152] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 152] setnp al - sete r14b - and r14b, al + sete r15b + and r15b, al vmovsd xmm0, qword ptr [rsi + 160] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 160] setnp al sete cl and cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 17], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 168] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 168] setnp al sete cl and cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 176] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 176] setnp al sete cl and cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill + mov byte ptr [rsp + 14], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 184] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 184] setnp al - sete r15b - and r15b, al + sete r10b + and r10b, al vmovsd xmm0, qword ptr [rsi + 192] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 192] setnp al sete cl and cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill + mov byte ptr [rsp + 15], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 200] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 200] setnp al - sete cl - and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + sete r12b + and r12b, al vmovsd xmm0, qword ptr [rsi + 208] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 208] setnp al - sete r11b - and r11b, al + sete r14b + and r14b, al vmovsd xmm0, qword ptr [rsi + 216] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 216] setnp al - sete r10b - and r10b, al + sete r11b + and r11b, al vmovsd xmm0, qword ptr [rsi + 224] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 224] setnp al sete cl and cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 13], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 232] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 232] setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 240] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 240] setnp al @@ -553,110 +585,108 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 setnp al sete r8b and r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload shl dil, 5 shl r13b, 6 or r13b, dil mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload shl cl, 2 or cl, al mov eax, ebx add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload + add al, byte ptr [rsp + 27] # 1-byte Folded Reload mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 or al, r13b mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload shl bl, 3 or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 6 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload shl cl, 2 or cl, bl - shl r14b, 3 - or r14b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload shl bl, 4 - or bl, r14b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r14d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r14b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 or cl, r13b - or al, dil - shl r15b, 7 - or r15b, cl - or r15b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r11b, 2 - or r11b, cl - shl r10b, 3 - or r10b, r11b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload + shl r10b, 7 + or r10b, cl + or r10b, bl + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload shl cl, 4 - or cl, r10b - mov byte ptr [r12], r14b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 shl r9b, 6 or r9b, bl - mov byte ptr [r12 + 1], al + mov byte ptr [r15 + 1], dil shl r8b, 7 or r8b, r9b or r8b, cl - mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], r8b + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB0_52 -# %bb.53: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB0_54: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.55: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_64 +# %bb.65: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_66: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB0_56: # =>This Inner Loop Header: Depth=1 +.LBB0_68: # =>This Inner Loop Header: Depth=1 lea r9, [rcx + 1] vmovsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 8*rcx] @@ -666,7 +696,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg al mov rdi, rcx shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] xor al, r8b and cl, 7 mov bl, 1 @@ -674,95 +705,119 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl bl, cl and bl, al xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r15 + rdi], bl mov rcx, r9 - cmp r14, r9 - jne .LBB0_56 - jmp .LBB0_123 + cmp r12, r9 + jne .LBB0_68 + jmp .LBB0_153 .LBB0_2: cmp edi, 2 - je .LBB0_57 + mov r13, r15 + je .LBB0_69 # %bb.3: cmp edi, 3 - jne .LBB0_123 + jne .LBB0_153 # %bb.4: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_8 + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_11 # %bb.5: - cdqe - .p2align 4, 0x90 -.LBB0_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - sete r10b - neg r10b - lea rdi, [rax + 7] + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB0_9 +# %bb.6: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB0_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + sete r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB0_6 -# %bb.7: - add r12, 1 -.LBB0_8: - sar r15, 5 - cmp r14, 32 - jl .LBB0_12 -# %bb.9: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB0_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB0_9: + sub r12, rax + je .LBB0_153 +# %bb.10: + add r15, 1 +.LBB0_11: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_15 +# %bb.12: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] sete bl movzx eax, byte ptr [rsi + 2] cmp al, byte ptr [rdx + 2] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 3] cmp al, byte ptr [rdx + 3] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 4] cmp al, byte ptr [rdx + 4] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 5] cmp al, byte ptr [rdx + 5] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 6] cmp al, byte ptr [rdx + 6] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - sete r15b + sete r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 9] cmp al, byte ptr [rdx + 9] sete dil @@ -774,19 +829,19 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - sete r14b + sete r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 14] cmp al, byte ptr [rdx + 14] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 15] cmp al, byte ptr [rdx + 15] sete r8b movzx eax, byte ptr [rsi + 16] cmp al, byte ptr [rdx + 16] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 17] cmp al, byte ptr [rdx + 17] sete r12b @@ -795,148 +850,147 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r13b movzx eax, byte ptr [rsi + 19] cmp al, byte ptr [rdx + 19] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 20] cmp al, byte ptr [rdx + 20] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 21] cmp al, byte ptr [rdx + 21] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 22] cmp al, byte ptr [rdx + 22] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 23] cmp al, byte ptr [rdx + 23] sete r9b movzx eax, byte ptr [rsi + 24] cmp al, byte ptr [rdx + 24] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 25] cmp al, byte ptr [rdx + 25] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 26] cmp al, byte ptr [rdx + 26] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 27] cmp al, byte ptr [rdx + 27] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 28] cmp al, byte ptr [rdx + 28] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 29] cmp al, byte ptr [rdx + 29] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 30] cmp al, byte ptr [rdx + 30] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 31] add rsi, 32 cmp al, byte ptr [rdx + 31] sete cl add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload shl bl, 2 or bl, al mov eax, ebx add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r10b, 2 or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al mov edi, ebx shl r11b, 3 or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload shl dil, 6 shl r8b, 7 or r8b, dil - or r15b, bl + or r14b, bl or r8b, al add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 3 or al, r13b mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], r8b + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB0_10 -# %bb.11: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB0_12: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.13: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB0_13 +# %bb.14: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB0_15: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB0_14: # =>This Inner Loop Header: Depth=1 +.LBB0_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -944,7 +998,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -952,98 +1007,114 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_14 - jmp .LBB0_123 -.LBB0_30: + cmp r12, r8 + jne .LBB0_17 + jmp .LBB0_153 +.LBB0_36: cmp edi, 7 - je .LBB0_90 -# %bb.31: + je .LBB0_111 +# %bb.37: cmp edi, 8 - jne .LBB0_123 -# %bb.32: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_36 -# %bb.33: - cdqe + jne .LBB0_153 +# %bb.38: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_41: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_34 -# %bb.35: - add r12, 1 -.LBB0_36: - sar r15, 5 - cmp r14, 32 - jl .LBB0_40 -# %bb.37: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB0_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB0_43: + sub r12, r8 + je .LBB0_153 +# %bb.44: + add r15, 1 +.LBB0_45: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_49 +# %bb.46: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov rax, qword ptr [rsi + 24] cmp rax, qword ptr [rdx + 24] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov rax, qword ptr [rsi + 32] cmp rax, qword ptr [rdx + 32] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov rax, qword ptr [rsi + 40] cmp rax, qword ptr [rdx + 40] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov rax, qword ptr [rsi + 48] cmp rax, qword ptr [rdx + 48] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] sete r13b mov rax, qword ptr [rsi + 64] cmp rax, qword ptr [rdx + 64] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - sete r8b + sete dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] sete r11b @@ -1052,21 +1123,21 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r15b mov rax, qword ptr [rsi + 96] cmp rax, qword ptr [rdx + 96] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov rax, qword ptr [rsi + 112] cmp rax, qword ptr [rdx + 112] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov rax, qword ptr [rsi + 120] cmp rax, qword ptr [rdx + 120] - sete dil + sete r8b mov rax, qword ptr [rsi + 128] mov rbx, qword ptr [rsi + 136] cmp rax, qword ptr [rdx + 128] mov rax, qword ptr [rsi + 144] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 136] mov rbx, qword ptr [rsi + 152] sete r10b @@ -1077,144 +1148,144 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 mov rbx, qword ptr [rsi + 168] sete r12b cmp rax, qword ptr [rdx + 160] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 168] mov rax, qword ptr [rsi + 176] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] sete r9b cmp rax, qword ptr [rdx + 192] mov rax, qword ptr [rsi + 200] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 224] mov rax, qword ptr [rsi + 232] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 232] mov rax, qword ptr [rsi + 240] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 240] mov rax, qword ptr [rsi + 248] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_38 -# %bb.39: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_40: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.41: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_47 +# %bb.48: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_49: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB0_42: # =>This Inner Loop Header: Depth=1 +.LBB0_51: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -1222,7 +1293,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -1230,92 +1302,108 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_42 - jmp .LBB0_123 -.LBB0_68: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_72 -# %bb.69: - cdqe + cmp r12, r8 + jne .LBB0_51 + jmp .LBB0_153 +.LBB0_83: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_86: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_70 -# %bb.71: - add r12, 1 -.LBB0_72: - sar r15, 5 - cmp r14, 32 - jl .LBB0_76 -# %bb.73: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB0_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB0_88: + sub r12, r8 + je .LBB0_153 +# %bb.89: + add r15, 1 +.LBB0_90: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_94 +# %bb.91: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, word ptr [rsi + 6] cmp ax, word ptr [rdx + 6] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, word ptr [rsi + 8] cmp ax, word ptr [rdx + 8] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, word ptr [rsi + 10] cmp ax, word ptr [rdx + 10] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, word ptr [rsi + 12] cmp ax, word ptr [rdx + 12] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] sete r13b movzx eax, word ptr [rsi + 16] cmp ax, word ptr [rdx + 16] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - sete r8b + sete dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] sete r11b @@ -1324,21 +1412,21 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r15b movzx eax, word ptr [rsi + 24] cmp ax, word ptr [rdx + 24] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, word ptr [rsi + 28] cmp ax, word ptr [rdx + 28] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, word ptr [rsi + 30] cmp ax, word ptr [rdx + 30] - sete dil + sete r8b movzx eax, word ptr [rsi + 32] movzx ebx, word ptr [rsi + 34] cmp ax, word ptr [rdx + 32] movzx eax, word ptr [rsi + 36] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp bx, word ptr [rdx + 34] movzx ebx, word ptr [rsi + 38] sete r10b @@ -1349,144 +1437,144 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 movzx ebx, word ptr [rsi + 42] sete r12b cmp ax, word ptr [rdx + 40] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp bx, word ptr [rdx + 42] movzx eax, word ptr [rsi + 44] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] sete r9b cmp ax, word ptr [rdx + 48] movzx eax, word ptr [rsi + 50] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp ax, word ptr [rdx + 56] movzx eax, word ptr [rsi + 58] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp ax, word ptr [rdx + 58] movzx eax, word ptr [rsi + 60] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp ax, word ptr [rdx + 60] movzx eax, word ptr [rsi + 62] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_74 -# %bb.75: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_76: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.77: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_92 +# %bb.93: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_94: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB0_78: # =>This Inner Loop Header: Depth=1 +.LBB0_96: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -1494,7 +1582,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -1502,92 +1591,108 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_78 - jmp .LBB0_123 -.LBB0_79: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_83 -# %bb.80: - cdqe + cmp r12, r8 + jne .LBB0_96 + jmp .LBB0_153 +.LBB0_97: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_81 -# %bb.82: - add r12, 1 -.LBB0_83: - sar r15, 5 - cmp r14, 32 - jl .LBB0_87 -# %bb.84: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB0_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB0_102: + sub r12, r8 + je .LBB0_153 +# %bb.103: + add r15, 1 +.LBB0_104: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_108 +# %bb.105: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, word ptr [rsi + 6] cmp ax, word ptr [rdx + 6] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, word ptr [rsi + 8] cmp ax, word ptr [rdx + 8] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, word ptr [rsi + 10] cmp ax, word ptr [rdx + 10] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, word ptr [rsi + 12] cmp ax, word ptr [rdx + 12] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] sete r13b movzx eax, word ptr [rsi + 16] cmp ax, word ptr [rdx + 16] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - sete r8b + sete dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] sete r11b @@ -1596,21 +1701,21 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r15b movzx eax, word ptr [rsi + 24] cmp ax, word ptr [rdx + 24] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, word ptr [rsi + 28] cmp ax, word ptr [rdx + 28] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, word ptr [rsi + 30] cmp ax, word ptr [rdx + 30] - sete dil + sete r8b movzx eax, word ptr [rsi + 32] movzx ebx, word ptr [rsi + 34] cmp ax, word ptr [rdx + 32] movzx eax, word ptr [rsi + 36] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp bx, word ptr [rdx + 34] movzx ebx, word ptr [rsi + 38] sete r10b @@ -1621,144 +1726,144 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 movzx ebx, word ptr [rsi + 42] sete r12b cmp ax, word ptr [rdx + 40] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp bx, word ptr [rdx + 42] movzx eax, word ptr [rsi + 44] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] sete r9b cmp ax, word ptr [rdx + 48] movzx eax, word ptr [rsi + 50] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp ax, word ptr [rdx + 56] movzx eax, word ptr [rsi + 58] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp ax, word ptr [rdx + 58] movzx eax, word ptr [rsi + 60] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp ax, word ptr [rdx + 60] movzx eax, word ptr [rsi + 62] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_85 -# %bb.86: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_87: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.88: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_106 +# %bb.107: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_108: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB0_89: # =>This Inner Loop Header: Depth=1 +.LBB0_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -1766,7 +1871,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -1774,92 +1880,108 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_89 - jmp .LBB0_123 -.LBB0_101: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_105 -# %bb.102: - cdqe + cmp r12, r8 + jne .LBB0_110 + jmp .LBB0_153 +.LBB0_125: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_103 -# %bb.104: - add r12, 1 -.LBB0_105: - sar r15, 5 - cmp r14, 32 - jl .LBB0_109 -# %bb.106: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB0_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB0_130: + sub r12, r8 + je .LBB0_153 +# %bb.131: + add r15, 1 +.LBB0_132: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_136 +# %bb.133: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov rax, qword ptr [rsi + 24] cmp rax, qword ptr [rdx + 24] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov rax, qword ptr [rsi + 32] cmp rax, qword ptr [rdx + 32] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov rax, qword ptr [rsi + 40] cmp rax, qword ptr [rdx + 40] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov rax, qword ptr [rsi + 48] cmp rax, qword ptr [rdx + 48] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] sete r13b mov rax, qword ptr [rsi + 64] cmp rax, qword ptr [rdx + 64] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - sete r8b + sete dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] sete r11b @@ -1868,21 +1990,21 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r15b mov rax, qword ptr [rsi + 96] cmp rax, qword ptr [rdx + 96] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov rax, qword ptr [rsi + 112] cmp rax, qword ptr [rdx + 112] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov rax, qword ptr [rsi + 120] cmp rax, qword ptr [rdx + 120] - sete dil + sete r8b mov rax, qword ptr [rsi + 128] mov rbx, qword ptr [rsi + 136] cmp rax, qword ptr [rdx + 128] mov rax, qword ptr [rsi + 144] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 136] mov rbx, qword ptr [rsi + 152] sete r10b @@ -1893,144 +2015,144 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 mov rbx, qword ptr [rsi + 168] sete r12b cmp rax, qword ptr [rdx + 160] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 168] mov rax, qword ptr [rsi + 176] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] sete r9b cmp rax, qword ptr [rdx + 192] mov rax, qword ptr [rsi + 200] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 224] mov rax, qword ptr [rsi + 232] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 232] mov rax, qword ptr [rsi + 240] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 240] mov rax, qword ptr [rsi + 248] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_107 -# %bb.108: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_109: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.110: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_134 +# %bb.135: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_136: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.137: xor ecx, ecx .p2align 4, 0x90 -.LBB0_111: # =>This Inner Loop Header: Depth=1 +.LBB0_138: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -2038,7 +2160,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -2046,94 +2169,110 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_111 - jmp .LBB0_123 -.LBB0_112: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_116 -# %bb.113: - movsxd r10, eax + cmp r12, r8 + jne .LBB0_138 + jmp .LBB0_153 +.LBB0_139: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_144 +# %bb.141: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB0_114: # =>This Inner Loop Header: Depth=1 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - vucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - setnp cl +.LBB0_142: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + vmovss xmm0, dword ptr [rsi + 4*r14] # xmm0 = mem[0],zero,zero,zero + vucomiss xmm0, dword ptr [rdx + 4*r14] + setnp r10b sete bl - and bl, cl + and bl, r10b neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d + lea eax, [8*rdi] + sub ecx, eax mov eax, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB0_114 -# %bb.115: - add r12, 1 -.LBB0_116: - sar r15, 5 - cmp r14, 32 - jl .LBB0_120 -# %bb.117: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -4 + cmp r8, r14 + jne .LBB0_142 +# %bb.143: + sub rsi, r11 + sub rdx, r11 +.LBB0_144: + sub r12, r8 + je .LBB0_153 +# %bb.145: + add r15, 1 +.LBB0_146: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_150 +# %bb.147: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx] vmovss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero setnp al sete cl and cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill + mov byte ptr [rsp + 29], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 4] setnp al sete cl and cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill + mov byte ptr [rsp + 22], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 8] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 8] setnp al sete cl and cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill + mov byte ptr [rsp + 28], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 12] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 12] setnp al sete cl and cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill + mov byte ptr [rsp + 31], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 16] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 16] setnp al sete cl and cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill + mov byte ptr [rsp + 30], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 20] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 20] setnp al @@ -2149,13 +2288,13 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill + mov byte ptr [rsp + 12], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 32] setnp al sete cl and cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill + mov byte ptr [rsp + 27], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 36] setnp al @@ -2166,78 +2305,78 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill + mov byte ptr [rsp + 26], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 44] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 44] setnp al sete cl and cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill + mov byte ptr [rsp + 25], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 48] setnp al sete cl and cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 11], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 52] setnp al sete cl and cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 56] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 56] setnp al sete cl and cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill + mov byte ptr [rsp + 21], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 60] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 60] setnp al sete cl and cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill + mov byte ptr [rsp + 20], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 64] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill + mov byte ptr [rsp + 23], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 68] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 68] setnp al sete cl and cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill + mov byte ptr [rsp + 19], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 72] setnp al sete cl and cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill + mov byte ptr [rsp + 18], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 76] setnp al - sete r11b - and r11b, al + sete r15b + and r15b, al vmovss xmm0, dword ptr [rsi + 80] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 80] setnp al sete cl and cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 17], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 84] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 84] setnp al sete cl and cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 88] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 88] setnp al sete cl and cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill + mov byte ptr [rsp + 14], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 92] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 92] setnp al @@ -2248,35 +2387,34 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill + mov byte ptr [rsp + 15], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 100] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 100] setnp al - sete cl - and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + sete r12b + and r12b, al vmovss xmm0, dword ptr [rsi + 104] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 104] setnp al - sete r15b - and r15b, al + sete r14b + and r14b, al vmovss xmm0, dword ptr [rsi + 108] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 108] setnp al - sete r14b - and r14b, al + sete r11b + and r11b, al vmovss xmm0, dword ptr [rsi + 112] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 112] setnp al sete cl and cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 13], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 116] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 116] setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 120] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 120] setnp al @@ -2288,110 +2426,108 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 setnp al sete r8b and r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload shl dil, 5 shl r13b, 6 or r13b, dil mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload shl cl, 2 or cl, al mov eax, ebx add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload + add al, byte ptr [rsp + 27] # 1-byte Folded Reload mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 or al, r13b mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload shl bl, 3 or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 6 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload shl cl, 2 or cl, bl - shl r11b, 3 - or r11b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload shl bl, 4 - or bl, r11b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r11d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r11b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 or cl, r13b - or al, dil + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload shl r10b, 7 or r10b, cl or r10b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r15b, 2 - or r15b, cl - shl r14b, 3 - or r14b, r15b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload shl cl, 4 - or cl, r14b - mov byte ptr [r12], r11b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 shl r9b, 6 or r9b, bl - mov byte ptr [r12 + 1], al + mov byte ptr [r15 + 1], dil shl r8b, 7 or r8b, r9b or r8b, cl - mov byte ptr [r12 + 2], r10b - mov byte ptr [r12 + 3], r8b + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB0_118 -# %bb.119: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB0_120: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.121: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_148 +# %bb.149: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_150: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.151: xor ecx, ecx .p2align 4, 0x90 -.LBB0_122: # =>This Inner Loop Header: Depth=1 +.LBB0_152: # =>This Inner Loop Header: Depth=1 lea r9, [rcx + 1] vmovss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 4*rcx] @@ -2401,7 +2537,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg al mov rdi, rcx shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] xor al, r8b and cl, 7 mov bl, 1 @@ -2409,89 +2546,112 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl bl, cl and bl, al xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r15 + rdi], bl mov rcx, r9 - cmp r14, r9 - jne .LBB0_122 - jmp .LBB0_123 -.LBB0_57: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_61 -# %bb.58: - cdqe - .p2align 4, 0x90 -.LBB0_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - sete r10b - neg r10b - lea rdi, [rax + 7] + cmp r12, r9 + jne .LBB0_152 + jmp .LBB0_153 +.LBB0_69: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB0_74 +# %bb.71: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB0_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + sete r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB0_59 -# %bb.60: - add r12, 1 -.LBB0_61: - sar r15, 5 - cmp r14, 32 - jl .LBB0_65 -# %bb.62: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB0_72 +# %bb.73: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB0_74: + sub r12, rax + je .LBB0_153 +# %bb.75: + add r15, 1 +.LBB0_76: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_80 +# %bb.77: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] sete bl movzx eax, byte ptr [rsi + 2] cmp al, byte ptr [rdx + 2] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 3] cmp al, byte ptr [rdx + 3] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 4] cmp al, byte ptr [rdx + 4] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 5] cmp al, byte ptr [rdx + 5] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 6] cmp al, byte ptr [rdx + 6] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - sete r15b + sete r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 9] cmp al, byte ptr [rdx + 9] sete dil @@ -2503,19 +2663,19 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - sete r14b + sete r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 14] cmp al, byte ptr [rdx + 14] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 15] cmp al, byte ptr [rdx + 15] sete r8b movzx eax, byte ptr [rsi + 16] cmp al, byte ptr [rdx + 16] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 17] cmp al, byte ptr [rdx + 17] sete r12b @@ -2524,148 +2684,147 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r13b movzx eax, byte ptr [rsi + 19] cmp al, byte ptr [rdx + 19] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 20] cmp al, byte ptr [rdx + 20] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 21] cmp al, byte ptr [rdx + 21] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 22] cmp al, byte ptr [rdx + 22] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 23] cmp al, byte ptr [rdx + 23] sete r9b movzx eax, byte ptr [rsi + 24] cmp al, byte ptr [rdx + 24] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 25] cmp al, byte ptr [rdx + 25] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 26] cmp al, byte ptr [rdx + 26] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 27] cmp al, byte ptr [rdx + 27] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 28] cmp al, byte ptr [rdx + 28] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 29] cmp al, byte ptr [rdx + 29] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 30] cmp al, byte ptr [rdx + 30] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 31] add rsi, 32 cmp al, byte ptr [rdx + 31] sete cl add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload shl bl, 2 or bl, al mov eax, ebx add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r10b, 2 or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al mov edi, ebx shl r11b, 3 or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload shl dil, 6 shl r8b, 7 or r8b, dil - or r15b, bl + or r14b, bl or r8b, al add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 3 or al, r13b mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], r8b + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB0_63 -# %bb.64: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB0_65: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.66: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB0_78 +# %bb.79: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB0_80: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.81: xor ecx, ecx .p2align 4, 0x90 -.LBB0_67: # =>This Inner Loop Header: Depth=1 +.LBB0_82: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -2673,7 +2832,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -2681,92 +2841,108 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_67 - jmp .LBB0_123 -.LBB0_90: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_94 -# %bb.91: - cdqe + cmp r12, r8 + jne .LBB0_82 + jmp .LBB0_153 +.LBB0_111: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_92 -# %bb.93: - add r12, 1 -.LBB0_94: - sar r15, 5 - cmp r14, 32 - jl .LBB0_98 -# %bb.95: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB0_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB0_116: + sub r12, r8 + je .LBB0_153 +# %bb.117: + add r15, 1 +.LBB0_118: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_122 +# %bb.119: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov eax, dword ptr [rsi + 12] cmp eax, dword ptr [rdx + 12] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov eax, dword ptr [rsi + 16] cmp eax, dword ptr [rdx + 16] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov eax, dword ptr [rsi + 20] cmp eax, dword ptr [rdx + 20] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov eax, dword ptr [rsi + 24] cmp eax, dword ptr [rdx + 24] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] sete r13b mov eax, dword ptr [rsi + 32] cmp eax, dword ptr [rdx + 32] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - sete r8b + sete dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] sete r11b @@ -2775,21 +2951,21 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 sete r15b mov eax, dword ptr [rsi + 48] cmp eax, dword ptr [rdx + 48] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov eax, dword ptr [rsi + 56] cmp eax, dword ptr [rdx + 56] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov eax, dword ptr [rsi + 60] cmp eax, dword ptr [rdx + 60] - sete dil + sete r8b mov eax, dword ptr [rsi + 64] mov ebx, dword ptr [rsi + 68] cmp eax, dword ptr [rdx + 64] mov eax, dword ptr [rsi + 72] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 68] mov ebx, dword ptr [rsi + 76] sete r10b @@ -2800,144 +2976,144 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 mov ebx, dword ptr [rsi + 84] sete r12b cmp eax, dword ptr [rdx + 80] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 84] mov eax, dword ptr [rsi + 88] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] sete r9b cmp eax, dword ptr [rdx + 96] mov eax, dword ptr [rsi + 100] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 112] mov eax, dword ptr [rsi + 116] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 116] mov eax, dword ptr [rsi + 120] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 120] mov eax, dword ptr [rsi + 124] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_96 -# %bb.97: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_98: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.99: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_120 +# %bb.121: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_122: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.123: xor ecx, ecx .p2align 4, 0x90 -.LBB0_100: # =>This Inner Loop Header: Depth=1 +.LBB0_124: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -2945,7 +3121,8 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -2953,11 +3130,11 @@ comparison_equal_arr_arr_avx2: # @comparison_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_100 -.LBB0_123: + cmp r12, r8 + jne .LBB0_124 +.LBB0_153: lea rsp, [rbp - 40] pop rbx pop r12 @@ -3001,90 +3178,104 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 and rsp, -32 sub rsp, 1280 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov r11, rcx + mov r15, r8 + mov r14, rcx cmp edi, 6 - jg .LBB1_13 + jg .LBB1_19 # %bb.1: cmp edi, 3 - jle .LBB1_25 + jle .LBB1_36 # %bb.2: cmp edi, 4 - je .LBB1_49 + je .LBB1_59 # %bb.3: cmp edi, 5 - je .LBB1_57 + je .LBB1_73 # %bb.4: cmp edi, 6 - jne .LBB1_165 + jne .LBB1_189 # %bb.5: mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_9 + je .LBB1_11 # %bb.6: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_9 +# %bb.7: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_7: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB1_8: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + sete bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_7 -# %bb.8: - add r11, 1 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_8 .LBB1_9: - sar r15, 5 - cmp r10, 32 - jl .LBB1_101 + sub r15, r8 + je .LBB1_189 # %bb.10: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + add r14, 1 +.LBB1_11: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_15 +# %bb.12: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_11: # =>This Inner Loop Header: Depth=1 +.LBB1_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp dword ptr [rsi], r13d - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 168] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d sete r10b cmp dword ptr [rsi + 8], r13d sete r14b cmp dword ptr [rsi + 12], r13d - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - sete byte ptr [rsp + 88] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d sete al cmp dword ptr [rsi + 28], r13d sete bl cmp dword ptr [rsi + 32], r13d - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d sete dil cmp dword ptr [rsi + 40], r13d @@ -3096,33 +3287,33 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp dword ptr [rsi + 52], r13d sete r12b cmp dword ptr [rsi + 56], r13d - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - sete cl + sete dl cmp dword ptr [rsi + 64], r13d - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 68], r13d - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp dword ptr [rsi + 72], r13d - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp dword ptr [rsi + 88], r13d - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d sete r15b cmp dword ptr [rsi + 96], r13d - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp dword ptr [rsi + 104], r13d sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp dword ptr [rsi + 108], r13d - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp dword ptr [rsi + 112], r13d sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp dword ptr [rsi + 116], r13d @@ -3130,185 +3321,241 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp dword ptr [rsi + 120], r13d sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp dword ptr [rsi + 124], r13d - sete dl + sete cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 152] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 40] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 128 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_11 -# %bb.12: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_102 - jmp .LBB1_165 -.LBB1_13: - cmp edi, 8 - jle .LBB1_39 + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_13 # %bb.14: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB1_15: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_189 +# %bb.16: + or rax, 1 + cmp r15, rax + je .LBB1_129 +# %bb.17: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB1_18: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d + sete al + neg al + mov rdi, r11 + shr rdi, 3 + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + sete al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r10, r11 + jne .LBB1_18 + jmp .LBB1_179 +.LBB1_19: + cmp edi, 8 + jle .LBB1_43 +# %bb.20: cmp edi, 9 - je .LBB1_65 -# %bb.15: + je .LBB1_86 +# %bb.21: cmp edi, 11 - je .LBB1_73 -# %bb.16: + je .LBB1_99 +# %bb.22: cmp edi, 12 - jne .LBB1_165 -# %bb.17: - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jne .LBB1_189 +# %bb.23: + mov r12, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero sub r9d, eax - je .LBB1_21 -# %bb.18: - movsxd rax, r9d + je .LBB1_29 +# %bb.24: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_27 +# %bb.25: + movsxd rdx, r9d + vmovq xmm0, r12 + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_19: # =>This Inner Loop Header: Depth=1 - vucomisd xmm0, qword ptr [rsi] - lea rsi, [rsi + 8] +.LBB1_26: # =>This Inner Loop Header: Depth=1 + vucomisd xmm0, qword ptr [rcx] + lea rsi, [rcx + 8] setnp cl - sete dl - and dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + sete bl + and bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_19 -# %bb.20: - add r11, 1 -.LBB1_21: - sar r15, 5 - cmp r10, 32 - jl .LBB1_105 -# %bb.22: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_26 +.LBB1_27: + sub r15, r8 + je .LBB1_189 +# %bb.28: + add r14, 1 +.LBB1_29: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_33 +# %bb.30: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 184], r12 # 8-byte Spill + vmovq xmm0, r12 + mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_23: # =>This Inner Loop Header: Depth=1 +.LBB1_31: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill vucomisd xmm0, qword ptr [rsi] setnp al sete cl and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 8] setnp al - sete bl - and bl, al - vucomisd xmm0, qword ptr [rsi + 16] - setnp al sete r13b and r13b, al + vucomisd xmm0, qword ptr [rsi + 16] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 32], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 24] setnp al sete cl @@ -3318,16 +3565,16 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 288], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 40] setnp al - sete dil - and dil, al + sete r12b + and r12b, al vucomisd xmm0, qword ptr [rsi + 48] setnp al sete cl and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 56] setnp al sete cl @@ -3337,529 +3584,366 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 72] setnp al sete cl and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 80] setnp al sete cl and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 88] setnp al - sete cl - and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + sete bl + and bl, al vucomisd xmm0, qword ptr [rsi + 96] setnp al sete cl and cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 288], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 104] setnp al sete cl and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 112] setnp al - sete dl - and dl, al + sete cl + and cl, al + mov byte ptr [rsp + 88], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 120] setnp al sete cl and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 128] setnp al sete cl and cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 136] setnp al sete cl and cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 144] setnp al sete cl and cl, al + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 152] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 128], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 160] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 120], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 168] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 104], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 136], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 176] setnp al - sete r12b - and r12b, al + sete r15b + and r15b, al vucomisd xmm0, qword ptr [rsi + 184] setnp al sete r10b and r10b, al vucomisd xmm0, qword ptr [rsi + 192] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 112], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 168], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 200] setnp al - sete r15b - and r15b, al + sete r11b + and r11b, al vucomisd xmm0, qword ptr [rsi + 208] setnp al - sete r14b - and r14b, al + sete r9b + and r9b, al vucomisd xmm0, qword ptr [rsi + 216] setnp al - sete r11b - and r11b, al + sete r8b + and r8b, al vucomisd xmm0, qword ptr [rsi + 224] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 160], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 176], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 232] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 152], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 240] setnp al - sete r9b - and r9b, al + sete dil + and dil, al vucomisd xmm0, qword ptr [rsi + 248] setnp al - sete r8b - and r8b, al - add bl, bl - add bl, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 5 - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 6 - or al, dil - mov edi, eax - shl r13b, 2 - or r13b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax + sete dl + and dl, al + add r13b, r13b + add r13b, byte ptr [rsp + 56] # 1-byte Folded Reload + mov eax, r13d + shl r12b, 5 + movzx r13d, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r13b, 6 + or r13b, r12b + movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 - or al, dil + or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 - or al, bl - mov ebx, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 3 - or al, r13b - mov r13d, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov edi, eax + or al, r12b + shl bl, 3 + or bl, cl + movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 + or al, bl + mov byte ptr [rsp + 288], al # 1-byte Spill + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 5 + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 6 + or al, cl + mov ecx, eax + movzx r14d, byte ptr [rsp + 80] # 1-byte Folded Reload + shl r14b, 7 + or r14b, al + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 2 + or bl, cl + movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov r12d, ecx + mov rcx, qword ptr [rsp + 272] # 8-byte Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload or al, r13b - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 4 - or bl, dil - movzx edi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dil, 5 - shl dl, 6 - or dl, dil - movzx r13d, byte ptr [rsp + 72] # 1-byte Folded Reload - shl r13b, 7 - or r13b, dl - movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 144] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 3 - or dl, cl - mov ecx, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 4 - or dl, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - or cl, al - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 5 - shl r12b, 6 - or r12b, al - or r13b, bl + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl bl, 5 + shl r15b, 6 + or r15b, bl + or r14b, byte ptr [rsp + 288] # 1-byte Folded Reload shl r10b, 7 + or r10b, r15b or r10b, r12b - or r10b, dl - add r15b, r15b - add r15b, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r15b - shl r11b, 3 - or r11b, r14b - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 4 - or al, r11b - mov ebx, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], cl - movzx edx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl dl, 5 - shl r9b, 6 - or r9b, dl - mov byte ptr [rax + 1], r13b - shl r8b, 7 + add r11b, r11b + add r11b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 or r8b, r9b - or r8b, bl - mov byte ptr [rax + 2], r10b - mov byte ptr [rax + 3], r8b + movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload + shl bl, 4 + or bl, r8b + mov r8d, ebx + mov byte ptr [rcx], al + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl bl, 5 + shl dil, 6 + or dil, bl + mov byte ptr [rcx + 1], r14b + shl dl, 7 + or dl, dil + or dl, r8b + mov byte ptr [rcx + 2], r10b + mov byte ptr [rcx + 3], dl add rsi, 256 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_23 -# %bb.24: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_106 - jmp .LBB1_165 -.LBB1_25: + add rcx, 4 + mov r14, rcx + add qword ptr [rsp + 192], -1 # 8-byte Folded Spill + jne .LBB1_31 +# %bb.32: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12, qword ptr [rsp + 184] # 8-byte Reload + mov rax, qword ptr [rsp + 200] # 8-byte Reload +.LBB1_33: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_189 +# %bb.34: + vmovq xmm0, r12 + or rax, 1 + cmp r15, rax + jne .LBB1_160 +# %bb.35: + xor r11d, r11d + jmp .LBB1_162 +.LBB1_36: cmp edi, 2 - je .LBB1_81 -# %bb.26: + je .LBB1_112 +# %bb.37: cmp edi, 3 - jne .LBB1_165 -# %bb.27: - mov r14b, byte ptr [rdx] - lea r13, [r10 + 31] - test r10, r10 - mov r15, r10 - cmovns r13, r10 + jne .LBB1_189 +# %bb.38: + mov r12b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_31 -# %bb.28: - movsxd rax, r9d + je .LBB1_130 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_132 +# %bb.40: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB1_29: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r14b - lea rsi, [rsi + 1] - sete dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 +.LBB1_41: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r12b + sete bl + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB1_41 +# %bb.42: + sub r15, r8 + jne .LBB1_133 + jmp .LBB1_189 +.LBB1_43: + cmp edi, 7 + je .LBB1_117 +# %bb.44: + cmp edi, 8 + jne .LBB1_189 +# %bb.45: + mov r13, qword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB1_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_49 +# %bb.47: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB1_48: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + sete bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_29 -# %bb.30: - add r11, 1 -.LBB1_31: - sar r13, 5 + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_48 +.LBB1_49: + sub r15, r8 + je .LBB1_189 +# %bb.50: + add r14, 1 +.LBB1_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - jl .LBB1_108 -# %bb.32: - cmp r13, 32 - mov dword ptr [rsp + 28], r14d # 4-byte Spill + jl .LBB1_55 +# %bb.52: mov qword ptr [rsp + 280], r15 # 8-byte Spill - mov qword ptr [rsp + 392], r13 # 8-byte Spill - jb .LBB1_35 -# %bb.33: - mov rax, r13 - shl rax, 5 - add rax, rsi - cmp r11, rax - jae .LBB1_166 -# %bb.34: - lea rax, [r11 + 4*r13] - cmp rsi, rax - jae .LBB1_166 -.LBB1_35: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 376], r11 # 8-byte Spill -.LBB1_36: - sub r13, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r13 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_37: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b - sete byte ptr [rsp + 48] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b - sete r8b - cmp byte ptr [r12 + 2], r14b - sete r15b - cmp byte ptr [r12 + 3], r14b - sete r13b - cmp byte ptr [r12 + 4], r14b - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b +.LBB1_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill + cmp qword ptr [rsi], r13 + sete byte ptr [rsp + 168] # 1-byte Folded Spill + cmp qword ptr [rsi + 8], r13 + sete r10b + cmp qword ptr [rsi + 16], r13 + sete r14b + cmp qword ptr [rsi + 24], r13 + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp qword ptr [rsi + 40], r13 sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b - sete al - cmp byte ptr [r12 + 7], r14b - sete r11b - cmp byte ptr [r12 + 8], r14b - sete byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b - sete dl - cmp byte ptr [r12 + 10], r14b - sete sil - cmp byte ptr [r12 + 11], r14b - sete dil - cmp byte ptr [r12 + 12], r14b - sete r10b - cmp byte ptr [r12 + 13], r14b - sete r12b - cmp byte ptr [rcx + 14], r14b - sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b - sete r9b - cmp byte ptr [rcx + 16], r14b - sete byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b - sete byte ptr [rsp + 136] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b - sete byte ptr [rsp + 144] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - sete r14b - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 24], bl - sete byte ptr [rsp + 272] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 25], bl - sete byte ptr [rsp + 80] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 26], bl - sete byte ptr [rsp + 96] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 27], bl - sete byte ptr [rsp + 64] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 28], bl - sete byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 29], bl - sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 30], bl - sete byte ptr [rsp + 32] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 31], bl - sete bl - add r8b, r8b - add r8b, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, r8b - add dl, dl - add dl, byte ptr [rsp + 320] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b - shl sil, 2 - or sil, dl - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - shl dil, 3 - or dil, sil - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, dil - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload - shl sil, 6 - shl r9b, 7 - or r9b, sil - or r11b, dl - or r9b, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 288] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov rsi, qword ptr [rsp + 376] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 272] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dl, 6 - shl bl, 7 - or bl, dl - or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 376], rsi # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB1_37 -# %bb.38: - mov r15, qword ptr [rsp + 280] # 8-byte Reload - mov r13, qword ptr [rsp + 392] # 8-byte Reload - jmp .LBB1_109 -.LBB1_39: - cmp edi, 7 - je .LBB1_93 -# %bb.40: - cmp edi, 8 - jne .LBB1_165 -# %bb.41: - mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB1_45 -# %bb.42: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB1_43: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_43 -# %bb.44: - add r11, 1 -.LBB1_45: - sar r15, 5 - cmp r10, 32 - jl .LBB1_112 -# %bb.46: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB1_47: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r11 # 8-byte Spill - cmp qword ptr [rsi], r13 - sete byte ptr [rsp + 152] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 - sete r10b - cmp qword ptr [rsi + 16], r13 - sete r14b - cmp qword ptr [rsi + 24], r13 - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - sete byte ptr [rsp + 136] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 + cmp qword ptr [rsi + 48], r13 sete al cmp qword ptr [rsi + 56], r13 sete bl cmp qword ptr [rsi + 64], r13 - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 sete dil cmp qword ptr [rsi + 80], r13 @@ -3871,33 +3955,33 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp qword ptr [rsi + 104], r13 sete r12b cmp qword ptr [rsi + 112], r13 - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - sete cl + sete dl cmp qword ptr [rsi + 128], r13 - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 sete r15b cmp qword ptr [rsi + 192], r13 - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp qword ptr [rsi + 232], r13 @@ -3905,156 +3989,210 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp qword ptr [rsi + 240], r13 sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - sete dl + sete cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - mov r11, qword ptr [rsp + 272] # 8-byte Reload - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 152] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r11 + 1], cl + mov byte ptr [r14 + 1], dl or r15b, al movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ecx, eax + add al, byte ptr [rsp + 40] # 1-byte Folded Reload + mov edx, eax movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], dl + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 256 - add r11, 4 - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_47 -# %bb.48: - mov r14, r11 - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_113 - jmp .LBB1_165 -.LBB1_49: + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_53 +# %bb.54: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB1_55: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_189 +# %bb.56: + or rax, 1 + cmp r15, rax + je .LBB1_98 +# %bb.57: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB1_58: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + sete al + neg al + mov rdi, r11 + shr rdi, 3 + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + sete al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r10, r11 + jne .LBB1_58 + jmp .LBB1_170 +.LBB1_59: movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_53 -# %bb.50: - movsxd rax, r9d + je .LBB1_65 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_63 +# %bb.61: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_51: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB1_62: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + sete bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_51 -# %bb.52: - add r11, 1 -.LBB1_53: - sar r15, 5 - cmp r10, 32 - jl .LBB1_116 -# %bb.54: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_62 +.LBB1_63: + sub r15, r8 + je .LBB1_189 +# %bb.64: + add r14, 1 +.LBB1_65: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_69 +# %bb.66: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_55: # =>This Inner Loop Header: Depth=1 +.LBB1_67: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp word ptr [rsi], r13w sete al cmp word ptr [rsi + 2], r13w @@ -4062,17 +4200,17 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp word ptr [rsi + 4], r13w sete r14b cmp word ptr [rsi + 6], r13w - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp word ptr [rsi + 8], r13w sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp word ptr [rsi + 8], r13w + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - sete byte ptr [rsp + 88] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 168] # 1-byte Folded Spill cmp word ptr [rsi + 14], r13w sete bl cmp word ptr [rsi + 16], r13w - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w sete dil cmp word ptr [rsi + 20], r13w @@ -4084,33 +4222,33 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp word ptr [rsi + 26], r13w sete r12b cmp word ptr [rsi + 28], r13w - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - sete cl + sete dl cmp word ptr [rsi + 32], r13w - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp word ptr [rsi + 36], r13w - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 44], r13w - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w sete r15b cmp word ptr [rsi + 48], r13w - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [rsi + 52], r13w sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 56], r13w sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp word ptr [rsi + 58], r13w @@ -4118,177 +4256,229 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp word ptr [rsi + 60], r13w sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp word ptr [rsi + 62], r13w - sete dl + sete cl add r10b, r10b or r10b, al - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 40] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 64 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_55 -# %bb.56: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_117 - jmp .LBB1_165 -.LBB1_57: + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_67 +# %bb.68: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB1_69: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_189 +# %bb.70: + or rax, 1 + cmp r15, rax + je .LBB1_85 +# %bb.71: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB1_72: # =>This Inner Loop Header: Depth=1 + cmp word ptr [rsi], r13w + sete al + neg al + mov rdi, r11 + shr rdi, 3 + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add r11, 2 + cmp word ptr [rsi + 2], r13w + lea rsi, [rsi + 4] + sete al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r10, r11 + jne .LBB1_72 + jmp .LBB1_166 +.LBB1_73: movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_61 -# %bb.58: - movsxd rax, r9d + je .LBB1_79 +# %bb.74: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_77 +# %bb.75: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_59: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB1_76: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + sete bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_59 -# %bb.60: - add r11, 1 -.LBB1_61: - sar r15, 5 - cmp r10, 32 - jl .LBB1_120 -# %bb.62: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_76 +.LBB1_77: + sub r15, r8 + je .LBB1_189 +# %bb.78: + add r14, 1 +.LBB1_79: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_83 +# %bb.80: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_63: # =>This Inner Loop Header: Depth=1 +.LBB1_81: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp word ptr [rsi], r13w - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 168] # 1-byte Folded Spill cmp word ptr [rsi + 2], r13w sete r10b cmp word ptr [rsi + 4], r13w sete r14b cmp word ptr [rsi + 6], r13w - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp word ptr [rsi + 8], r13w sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp word ptr [rsi + 8], r13w + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - sete byte ptr [rsp + 88] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w sete al cmp word ptr [rsi + 14], r13w sete bl cmp word ptr [rsi + 16], r13w - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w sete dil cmp word ptr [rsi + 20], r13w @@ -4300,33 +4490,33 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp word ptr [rsi + 26], r13w sete r12b cmp word ptr [rsi + 28], r13w - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - sete cl + sete dl cmp word ptr [rsi + 32], r13w - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp word ptr [rsi + 36], r13w - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 44], r13w - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w sete r15b cmp word ptr [rsi + 48], r13w - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [rsi + 52], r13w sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 56], r13w sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp word ptr [rsi + 58], r13w @@ -4334,176 +4524,195 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp word ptr [rsi + 60], r13w sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp word ptr [rsi + 62], r13w - sete dl + sete cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 152] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 40] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 64 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_63 -# %bb.64: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_121 - jmp .LBB1_165 -.LBB1_65: + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_81 +# %bb.82: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB1_83: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_189 +# %bb.84: + or rax, 1 + cmp r15, rax + jne .LBB1_164 +.LBB1_85: + xor r11d, r11d + jmp .LBB1_166 +.LBB1_86: mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_69 -# %bb.66: - movsxd rax, r9d + je .LBB1_92 +# %bb.87: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_90 +# %bb.88: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_67: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB1_89: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + sete bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_67 -# %bb.68: - add r11, 1 -.LBB1_69: - sar r15, 5 - cmp r10, 32 - jl .LBB1_123 -# %bb.70: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_89 +.LBB1_90: + sub r15, r8 + je .LBB1_189 +# %bb.91: + add r14, 1 +.LBB1_92: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_96 +# %bb.93: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_71: # =>This Inner Loop Header: Depth=1 +.LBB1_94: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp qword ptr [rsi], r13 - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 168] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 sete r10b cmp qword ptr [rsi + 16], r13 sete r14b cmp qword ptr [rsi + 24], r13 - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 40], r13 - sete byte ptr [rsp + 88] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp qword ptr [rsi + 48], r13 sete al cmp qword ptr [rsi + 56], r13 sete bl cmp qword ptr [rsi + 64], r13 - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 sete dil cmp qword ptr [rsi + 80], r13 @@ -4515,33 +4724,33 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp qword ptr [rsi + 104], r13 sete r12b cmp qword ptr [rsi + 112], r13 - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - sete cl + sete dl cmp qword ptr [rsi + 128], r13 - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 sete r15b cmp qword ptr [rsi + 192], r13 - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp qword ptr [rsi + 232], r13 @@ -4549,173 +4758,196 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp qword ptr [rsi + 240], r13 sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - sete dl + sete cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 152] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 40] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 256 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_71 -# %bb.72: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_124 - jmp .LBB1_165 -.LBB1_73: - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_94 +# %bb.95: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB1_96: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_189 +# %bb.97: + or rax, 1 + cmp r15, rax + jne .LBB1_168 +.LBB1_98: + xor r11d, r11d + jmp .LBB1_170 +.LBB1_99: + mov r12d, dword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB1_77 -# %bb.74: - movsxd rax, r9d + je .LBB1_105 +# %bb.100: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_103 +# %bb.101: + movsxd rdx, r9d + vmovd xmm0, r12d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_75: # =>This Inner Loop Header: Depth=1 - vucomiss xmm0, dword ptr [rsi] - lea rsi, [rsi + 4] +.LBB1_102: # =>This Inner Loop Header: Depth=1 + vucomiss xmm0, dword ptr [rcx] + lea rsi, [rcx + 4] setnp cl - sete dl - and dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + sete bl + and bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_75 -# %bb.76: - add r11, 1 -.LBB1_77: - sar r15, 5 - cmp r10, 32 - jl .LBB1_126 -# %bb.78: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_102 +.LBB1_103: + sub r15, r8 + je .LBB1_189 +# %bb.104: + add r14, 1 +.LBB1_105: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_109 +# %bb.106: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov dword ptr [rsp + 192], r12d # 4-byte Spill + vmovd xmm0, r12d + mov qword ptr [rsp + 184], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_79: # =>This Inner Loop Header: Depth=1 +.LBB1_107: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill vucomiss xmm0, dword ptr [rsi] setnp al sete cl and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 4] setnp al - sete bl - and bl, al - vucomiss xmm0, dword ptr [rsi + 8] - setnp al sete r13b and r13b, al + vucomiss xmm0, dword ptr [rsi + 8] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 32], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 12] setnp al sete cl @@ -4725,16 +4957,16 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 288], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 20] setnp al - sete dil - and dil, al + sete r12b + and r12b, al vucomiss xmm0, dword ptr [rsi + 24] setnp al sete cl and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 28] setnp al sete cl @@ -4744,516 +4976,348 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 36] setnp al sete cl and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 40] setnp al sete cl and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 44] setnp al - sete cl - and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + sete bl + and bl, al vucomiss xmm0, dword ptr [rsi + 48] setnp al sete cl and cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 288], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 52] setnp al sete cl and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 56] setnp al - sete dl - and dl, al + sete cl + and cl, al + mov byte ptr [rsp + 88], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 60] setnp al sete cl and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 68] setnp al sete cl and cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 72] setnp al sete cl and cl, al + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 76] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 128], al # 1-byte Spill + setnp al + sete r14b + and r14b, al vucomiss xmm0, dword ptr [rsi + 80] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 120], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 84] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 104], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 88] setnp al - sete r12b - and r12b, al + sete r15b + and r15b, al vucomiss xmm0, dword ptr [rsi + 92] setnp al sete r10b and r10b, al vucomiss xmm0, dword ptr [rsi + 96] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 112], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 136], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 100] setnp al - sete r15b - and r15b, al + sete r11b + and r11b, al vucomiss xmm0, dword ptr [rsi + 104] setnp al - sete r14b - and r14b, al + sete r9b + and r9b, al vucomiss xmm0, dword ptr [rsi + 108] setnp al - sete r11b - and r11b, al + sete r8b + and r8b, al vucomiss xmm0, dword ptr [rsi + 112] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 160], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 168], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 116] - setnp r8b - sete al - and al, r8b - mov byte ptr [rsp + 152], al # 1-byte Spill + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 120] setnp al - sete r9b - and r9b, al + sete dil + and dil, al vucomiss xmm0, dword ptr [rsi + 124] setnp al - sete r8b - and r8b, al - add bl, bl - add bl, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 5 - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 6 - or al, dil - mov edi, eax - shl r13b, 2 - or r13b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax + sete dl + and dl, al + add r13b, r13b + add r13b, byte ptr [rsp + 56] # 1-byte Folded Reload + mov eax, r13d + shl r12b, 5 + movzx r13d, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r13b, 6 + or r13b, r12b + movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 - or al, dil + or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 3 - or al, r13b - mov r13d, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 3 - or al, bl - mov edi, eax + or al, r12b + shl bl, 3 + or bl, cl + movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 - or al, r13b - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 4 - or bl, dil - movzx edi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dil, 5 - shl dl, 6 - or dl, dil - movzx r13d, byte ptr [rsp + 72] # 1-byte Folded Reload - shl r13b, 7 - or r13b, dl - movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 144] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 3 - or dl, cl - mov ecx, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 4 - or dl, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - or cl, al - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 5 - shl r12b, 6 - or r12b, al - or r13b, bl + or al, bl + mov byte ptr [rsp + 288], al # 1-byte Spill + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 5 + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 6 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 7 + or al, cl + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 2 + or bl, cl + shl r14b, 3 + or r14b, bl + movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload + shl cl, 4 + or cl, r14b + mov r14, qword ptr [rsp + 272] # 8-byte Reload + movzx r12d, byte ptr [rsp + 28] # 1-byte Folded Reload + or r12b, r13b + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl bl, 5 + shl r15b, 6 + or r15b, bl + or al, byte ptr [rsp + 288] # 1-byte Folded Reload shl r10b, 7 - or r10b, r12b - or r10b, dl - add r15b, r15b - add r15b, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r15b - shl r11b, 3 - or r11b, r14b - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 4 - or al, r11b - mov ebx, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], cl - movzx edx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl dl, 5 - shl r9b, 6 - or r9b, dl - mov byte ptr [rax + 1], r13b - shl r8b, 7 + or r10b, r15b + or r10b, cl + add r11b, r11b + add r11b, byte ptr [rsp + 136] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 or r8b, r9b - or r8b, bl - mov byte ptr [rax + 2], r10b - mov byte ptr [rax + 3], r8b + movzx ecx, byte ptr [rsp + 168] # 1-byte Folded Reload + shl cl, 4 + or cl, r8b + mov byte ptr [r14], r12b + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl bl, 5 + shl dil, 6 + or dil, bl + mov byte ptr [r14 + 1], al + shl dl, 7 + or dl, dil + or dl, cl + mov byte ptr [r14 + 2], r10b + mov byte ptr [r14 + 3], dl add rsi, 128 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill + add r14, 4 add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_79 -# %bb.80: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_127 - jmp .LBB1_165 -.LBB1_81: - mov r14b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jne .LBB1_107 +# %bb.108: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 192] # 4-byte Reload + mov rax, qword ptr [rsp + 184] # 8-byte Reload +.LBB1_109: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_189 +# %bb.110: + vmovd xmm0, r12d + or rax, 1 + cmp r15, rax + jne .LBB1_172 +# %bb.111: + xor r11d, r11d + jmp .LBB1_174 +.LBB1_112: + mov r12b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_85 -# %bb.82: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB1_83: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r14b - lea rsi, [rsi + 1] - sete dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_83 -# %bb.84: - add r11, 1 -.LBB1_85: - sar r15, 5 - cmp r10, 32 - jl .LBB1_129 -# %bb.86: - cmp r15, 32 - mov dword ptr [rsp + 28], r14d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 392], r15 # 8-byte Spill - jb .LBB1_89 -# %bb.87: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp r11, rax - jae .LBB1_169 -# %bb.88: - lea rax, [r11 + 4*r15] - cmp rsi, rax - jae .LBB1_169 -.LBB1_89: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 376], r11 # 8-byte Spill -.LBB1_90: - sub r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r15 # 8-byte Spill + je .LBB1_131 +# %bb.113: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_146 +# %bb.114: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB1_91: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b - sete byte ptr [rsp + 32] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b - sete r8b - cmp byte ptr [r12 + 2], r14b - sete r15b - cmp byte ptr [r12 + 3], r14b - sete r13b - cmp byte ptr [r12 + 4], r14b - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b - sete al - cmp byte ptr [r12 + 7], r14b - sete r11b - cmp byte ptr [r12 + 8], r14b - sete byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b - sete dl - cmp byte ptr [r12 + 10], r14b - sete sil - cmp byte ptr [r12 + 11], r14b - sete dil - cmp byte ptr [r12 + 12], r14b - sete r10b - cmp byte ptr [r12 + 13], r14b - sete r12b - cmp byte ptr [rcx + 14], r14b - sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b - sete r9b - cmp byte ptr [rcx + 16], r14b - sete byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b - sete byte ptr [rsp + 136] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b - sete byte ptr [rsp + 144] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - sete r14b - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 24], bl - sete byte ptr [rsp + 272] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 25], bl - sete byte ptr [rsp + 88] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 26], bl - sete byte ptr [rsp + 96] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 27], bl - sete byte ptr [rsp + 64] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 28], bl - sete byte ptr [rsp + 48] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 29], bl - sete byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 30], bl - sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 31], bl +.LBB1_115: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r12b sete bl - add r8b, r8b - add r8b, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, r8b - add dl, dl - add dl, byte ptr [rsp + 320] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b - shl sil, 2 - or sil, dl - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - shl dil, 3 - or dil, sil - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, dil - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload - shl sil, 6 - shl r9b, 7 - or r9b, sil - or r11b, dl - or r9b, r12b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 288] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov rsi, qword ptr [rsp + 376] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 272] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl dl, 6 - shl bl, 7 - or bl, dl - or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 376], rsi # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB1_91 -# %bb.92: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 392] # 8-byte Reload - jmp .LBB1_130 -.LBB1_93: + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB1_115 +# %bb.116: + sub r15, r8 + jne .LBB1_147 + jmp .LBB1_189 +.LBB1_117: mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_97 -# %bb.94: - movsxd rax, r9d + je .LBB1_123 +# %bb.118: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_121 +# %bb.119: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_95: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB1_120: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + sete bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_95 -# %bb.96: - add r11, 1 -.LBB1_97: - sar r15, 5 - cmp r10, 32 - jl .LBB1_133 -# %bb.98: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_120 +.LBB1_121: + sub r15, r8 + je .LBB1_189 +# %bb.122: + add r14, 1 +.LBB1_123: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_127 +# %bb.124: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_99: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r11 # 8-byte Spill +.LBB1_125: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp dword ptr [rsi], r13d - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 168] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d sete r10b cmp dword ptr [rsi + 8], r13d sete r14b cmp dword ptr [rsi + 12], r13d - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - sete byte ptr [rsp + 88] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d sete al cmp dword ptr [rsi + 28], r13d sete bl cmp dword ptr [rsi + 32], r13d - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d sete dil cmp dword ptr [rsi + 40], r13d @@ -5265,33 +5329,33 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp dword ptr [rsi + 52], r13d sete r12b cmp dword ptr [rsi + 56], r13d - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - sete cl + sete dl cmp dword ptr [rsi + 64], r13d - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 68], r13d - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp dword ptr [rsi + 72], r13d - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp dword ptr [rsi + 88], r13d - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d sete r15b cmp dword ptr [rsi + 96], r13d - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp dword ptr [rsi + 104], r13d sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp dword ptr [rsi + 108], r13d - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp dword ptr [rsi + 112], r13d sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp dword ptr [rsi + 116], r13d @@ -5299,388 +5363,644 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 cmp dword ptr [rsi + 120], r13d sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp dword ptr [rsi + 124], r13d - sete dl + sete cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - mov r11, qword ptr [rsp + 272] # 8-byte Reload - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 152] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r11 + 1], cl + mov byte ptr [r14 + 1], dl or r15b, al movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ecx, eax + add al, byte ptr [rsp + 40] # 1-byte Folded Reload + mov edx, eax movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], dl + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 128 - add r11, 4 - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB1_99 -# %bb.100: - mov r14, r11 - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB1_134 - jmp .LBB1_165 -.LBB1_101: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_102: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB1_135 -# %bb.103: - mov r10, r8 - and r10, -2 - xor r11d, r11d - mov r15, r14 - .p2align 4, 0x90 -.LBB1_104: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - sete al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r15 + rdi], bl - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - sete al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r15 + rdi], dl - cmp r10, r11 - jne .LBB1_104 - jmp .LBB1_162 -.LBB1_105: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_106: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_136 -# %bb.107: - xor r11d, r11d - jmp .LBB1_138 -.LBB1_108: - mov qword ptr [rsp + 376], r11 # 8-byte Spill - mov r12, rsi -.LBB1_109: - shl r13, 5 - cmp r13, r15 - jge .LBB1_165 -# %bb.110: + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_125 +# %bb.126: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB1_127: + shl rax, 5 mov r8, r15 - sub r8, r13 - not r13 - add r13, r15 - je .LBB1_132 -# %bb.140: - mov r10, r8 - and r10, -2 - xor esi, esi - mov r11, qword ptr [rsp + 376] # 8-byte Reload - .p2align 4, 0x90 -.LBB1_141: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rsi], r14b - sete bl - neg bl + sub r8, rax + jle .LBB1_189 +# %bb.128: + or rax, 1 + cmp r15, rax + jne .LBB1_177 +.LBB1_129: + xor r11d, r11d + jmp .LBB1_179 +.LBB1_130: mov rdi, rsi - shr rdi, 3 - mov ecx, esi - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r11 + rdi] - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp byte ptr [r12 + rsi + 1], r14b - lea rsi, [rsi + 2] - sete bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB1_141 - jmp .LBB1_157 -.LBB1_112: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_113: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB1_125 -# %bb.114: + jmp .LBB1_134 +.LBB1_131: + mov rdi, rsi + jmp .LBB1_148 +.LBB1_132: + mov rdi, rsi + sub r15, r8 + je .LBB1_189 +.LBB1_133: + add r14, 1 +.LBB1_134: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB1_142 +# %bb.135: + cmp rcx, 32 + mov dword ptr [rsp + 28], r12d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 392], rcx # 8-byte Spill + jb .LBB1_138 +# %bb.136: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB1_190 +# %bb.137: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB1_190 +.LBB1_138: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 376], r14 # 8-byte Spill +.LBB1_139: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 160], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB1_140: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r12b + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r12b + sete r8b + cmp byte ptr [rsi + 2], r12b + sete r14b + cmp byte ptr [rsi + 3], r12b + sete r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 4], al + sete byte ptr [rsp + 112] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 5], al + sete byte ptr [rsp + 32] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 6], al + sete byte ptr [rsp + 168] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 7], al + sete r11b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 8], al + sete byte ptr [rsp + 320] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 9], al + sete dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 10], al + sete sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 11], al + sete dil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 12], al + sete r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 13], al + sete r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 14], al + sete byte ptr [rsp + 136] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 15], al + sete r9b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 16], bl + sete byte ptr [rsp + 288] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + sete byte ptr [rsp + 80] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 18], bl + sete byte ptr [rsp + 144] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 19], bl + sete byte ptr [rsp + 152] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + sete byte ptr [rsp + 64] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + sete byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + sete byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + sete r15b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 24], bl + sete byte ptr [rsp + 272] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 25], bl + sete byte ptr [rsp + 96] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 26], bl + sete byte ptr [rsp + 88] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 27], bl + sete byte ptr [rsp + 104] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 28], bl + sete byte ptr [rsp + 128] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 29], bl + sete byte ptr [rsp + 48] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 30], bl + sete byte ptr [rsp + 56] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 31], bl + sete bl + add r8b, r8b + add r8b, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r8b + add dl, dl + add dl, byte ptr [rsp + 320] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, dl + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, r13b + mov r8d, edx + mov eax, dword ptr [rsp + 28] # 4-byte Reload + shl dil, 3 + or dil, sil + movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl dl, 5 + or dl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 136] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, dl + or r9b, r12b + mov r12d, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 288] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dl, 2 + or dl, al + mov esi, edx + movzx edx, byte ptr [rsp + 152] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov rdi, qword ptr [rsp + 376] # 8-byte Reload + mov byte ptr [rdi], r11b + movzx esi, byte ptr [rsp + 120] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [rdi + 1], r9b + or r15b, dl + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 272] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r15b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 376], rdi # 8-byte Spill + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_140 +# %bb.141: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + jmp .LBB1_143 +.LBB1_142: + mov qword ptr [rsp + 376], r14 # 8-byte Spill + mov rsi, rdi +.LBB1_143: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB1_189 +# %bb.144: + or rcx, 1 + cmp r15, rcx + je .LBB1_159 +# %bb.182: mov r10, r8 and r10, -2 - xor r11d, r11d - mov r15, r14 + xor r9d, r9d + mov r11, qword ptr [rsp + 376] # 8-byte Reload .p2align 4, 0x90 -.LBB1_115: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - sete al - neg al - mov rdi, r11 +.LBB1_183: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r12b + sete bl + neg bl + mov rdi, r9 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - mov ecx, r11d + mov ecx, eax and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r15 + rdi], bl - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] - sete al - neg al - xor al, bl - or cl, 1 mov dl, 1 shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r15 + rdi], dl - cmp r10, r11 - jne .LBB1_115 - jmp .LBB1_148 -.LBB1_116: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_117: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB1_122 -# %bb.118: - mov r10, r8 - and r10, -2 - xor r11d, r11d - mov r15, r14 - .p2align 4, 0x90 -.LBB1_119: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - sete al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al + movzx r9d, byte ptr [r11 + rdi] xor bl, r9b - mov byte ptr [r15 + rdi], bl - add r11, 2 - cmp word ptr [rsi + 2], r13w - lea rsi, [rsi + 4] - sete al - neg al - xor al, bl + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r12b + lea r9, [rax + 2] + sete bl + neg bl + xor bl, dl or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r15 + rdi], dl - cmp r10, r11 - jne .LBB1_119 - jmp .LBB1_144 -.LBB1_120: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_121: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_142 -.LBB1_122: - xor r11d, r11d - jmp .LBB1_144 -.LBB1_123: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_124: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_146 -.LBB1_125: - xor r11d, r11d - jmp .LBB1_148 -.LBB1_126: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_127: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_150 -# %bb.128: - xor r11d, r11d - jmp .LBB1_152 -.LBB1_129: - mov qword ptr [rsp + 376], r11 # 8-byte Spill - mov r12, rsi -.LBB1_130: - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -# %bb.131: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_155 -.LBB1_132: - xor esi, esi - jmp .LBB1_158 -.LBB1_133: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB1_165 -.LBB1_134: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_160 -.LBB1_135: - xor r11d, r11d - jmp .LBB1_162 -.LBB1_136: + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB1_183 + jmp .LBB1_186 +.LBB1_146: + mov rdi, rsi + sub r15, r8 + je .LBB1_189 +.LBB1_147: + add r14, 1 +.LBB1_148: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB1_156 +# %bb.149: + cmp rcx, 32 + mov dword ptr [rsp + 28], r12d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 392], rcx # 8-byte Spill + jb .LBB1_152 +# %bb.150: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB1_193 +# %bb.151: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB1_193 +.LBB1_152: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 376], r14 # 8-byte Spill +.LBB1_153: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 160], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB1_154: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r12b + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r12b + sete r8b + cmp byte ptr [rsi + 2], r12b + sete r14b + cmp byte ptr [rsi + 3], r12b + sete r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 4], al + sete byte ptr [rsp + 112] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 5], al + sete byte ptr [rsp + 32] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 6], al + sete byte ptr [rsp + 168] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 7], al + sete r11b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 8], al + sete byte ptr [rsp + 320] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 9], al + sete dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 10], al + sete sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 11], al + sete dil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 12], al + sete r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 13], al + sete r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 14], al + sete byte ptr [rsp + 136] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 15], al + sete r9b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 16], bl + sete byte ptr [rsp + 288] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + sete byte ptr [rsp + 80] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 18], bl + sete byte ptr [rsp + 144] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 19], bl + sete byte ptr [rsp + 152] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + sete byte ptr [rsp + 64] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + sete byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + sete byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + sete r15b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 24], bl + sete byte ptr [rsp + 272] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 25], bl + sete byte ptr [rsp + 96] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 26], bl + sete byte ptr [rsp + 88] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 27], bl + sete byte ptr [rsp + 104] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 28], bl + sete byte ptr [rsp + 128] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 29], bl + sete byte ptr [rsp + 48] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 30], bl + sete byte ptr [rsp + 56] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 31], bl + sete bl + add r8b, r8b + add r8b, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r8b + add dl, dl + add dl, byte ptr [rsp + 320] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, dl + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, r13b + mov r8d, edx + mov eax, dword ptr [rsp + 28] # 4-byte Reload + shl dil, 3 + or dil, sil + movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl dl, 5 + or dl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 136] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, dl + or r9b, r12b + mov r12d, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 288] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dl, 2 + or dl, al + mov esi, edx + movzx edx, byte ptr [rsp + 152] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov rdi, qword ptr [rsp + 376] # 8-byte Reload + mov byte ptr [rdi], r11b + movzx esi, byte ptr [rsp + 120] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [rdi + 1], r9b + or r15b, dl + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 272] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r15b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 376], rdi # 8-byte Spill + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB1_154 +# %bb.155: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + jmp .LBB1_157 +.LBB1_156: + mov qword ptr [rsp + 376], r14 # 8-byte Spill + mov rsi, rdi +.LBB1_157: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB1_189 +# %bb.158: + or rcx, 1 + cmp r15, rcx + jne .LBB1_184 +.LBB1_159: + xor r9d, r9d + jmp .LBB1_187 +.LBB1_160: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB1_137: # =>This Inner Loop Header: Depth=1 +.LBB1_161: # =>This Inner Loop Header: Depth=1 vucomisd xmm0, qword ptr [rsi] setnp cl sete al @@ -5688,7 +6008,8 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 neg al mov rdi, r11 shr rdi, 3 - movzx r10d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r10d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -5696,7 +6017,7 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 xor al, r10b and bl, al xor bl, r10b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 vucomisd xmm0, qword ptr [rsi + 8] lea rsi, [rsi + 16] @@ -5710,28 +6031,28 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r9, r11 - jne .LBB1_137 -.LBB1_138: + jne .LBB1_161 +.LBB1_162: test r8b, 1 - je .LBB1_165 -# %bb.139: + je .LBB1_189 +# %bb.163: vucomisd xmm0, qword ptr [rsi] - jmp .LBB1_154 -.LBB1_142: + jmp .LBB1_176 +.LBB1_164: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB1_143: # =>This Inner Loop Header: Depth=1 +.LBB1_165: # =>This Inner Loop Header: Depth=1 cmp word ptr [rsi], r13w sete al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -5739,7 +6060,7 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp word ptr [rsi + 2], r13w lea rsi, [rsi + 4] @@ -5751,28 +6072,28 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB1_143 -.LBB1_144: + jne .LBB1_165 +.LBB1_166: test r8b, 1 - je .LBB1_165 -# %bb.145: + je .LBB1_189 +# %bb.167: cmp word ptr [rsi], r13w - jmp .LBB1_164 -.LBB1_146: + jmp .LBB1_181 +.LBB1_168: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB1_147: # =>This Inner Loop Header: Depth=1 +.LBB1_169: # =>This Inner Loop Header: Depth=1 cmp qword ptr [rsi], r13 sete al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -5780,7 +6101,7 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp qword ptr [rsi + 8], r13 lea rsi, [rsi + 16] @@ -5792,22 +6113,21 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB1_147 -.LBB1_148: + jne .LBB1_169 +.LBB1_170: test r8b, 1 - je .LBB1_165 -# %bb.149: + je .LBB1_189 +# %bb.171: cmp qword ptr [rsi], r13 - jmp .LBB1_164 -.LBB1_150: + jmp .LBB1_181 +.LBB1_172: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB1_151: # =>This Inner Loop Header: Depth=1 +.LBB1_173: # =>This Inner Loop Header: Depth=1 vucomiss xmm0, dword ptr [rsi] setnp cl sete al @@ -5815,7 +6135,8 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 neg al mov rdi, r11 shr rdi, 3 - movzx r10d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r10d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -5823,7 +6144,7 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 xor al, r10b and bl, al xor bl, r10b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 vucomiss xmm0, dword ptr [rsi + 4] lea rsi, [rsi + 8] @@ -5837,15 +6158,15 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r9, r11 - jne .LBB1_151 -.LBB1_152: + jne .LBB1_173 +.LBB1_174: test r8b, 1 - je .LBB1_165 -# %bb.153: + je .LBB1_189 +# %bb.175: vucomiss xmm0, dword ptr [rsi] -.LBB1_154: +.LBB1_176: setnp al sete dl and dl, al @@ -5861,76 +6182,20 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 and bl, dl xor bl, sil mov byte ptr [r14 + rax], bl - jmp .LBB1_165 -.LBB1_155: + jmp .LBB1_189 +.LBB1_177: mov r10, r8 and r10, -2 - xor esi, esi - mov r11, qword ptr [rsp + 376] # 8-byte Reload + xor r11d, r11d .p2align 4, 0x90 -.LBB1_156: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rsi], r14b - sete bl - neg bl - mov rdi, rsi - shr rdi, 3 - mov ecx, esi - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r11 + rdi] - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp byte ptr [r12 + rsi + 1], r14b - lea rsi, [rsi + 2] - sete bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB1_156 -.LBB1_157: - add r12, rsi -.LBB1_158: - test r8b, 1 - je .LBB1_165 -# %bb.159: - cmp byte ptr [r12], r14b - sete al - neg al - mov rdx, rsi - shr rdx, 3 - mov r8, qword ptr [rsp + 376] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r8 + rdx], bl - jmp .LBB1_165 -.LBB1_160: - mov r10, r8 - and r10, -2 - xor r11d, r11d - mov r15, r14 - .p2align 4, 0x90 -.LBB1_161: # =>This Inner Loop Header: Depth=1 +.LBB1_178: # =>This Inner Loop Header: Depth=1 cmp dword ptr [rsi], r13d sete al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -5938,7 +6203,7 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp dword ptr [rsi + 4], r13d lea rsi, [rsi + 8] @@ -5950,15 +6215,15 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB1_161 -.LBB1_162: + jne .LBB1_178 +.LBB1_179: test r8b, 1 - je .LBB1_165 -# %bb.163: + je .LBB1_189 +# %bb.180: cmp dword ptr [rsi], r13d -.LBB1_164: +.LBB1_181: sete al neg al mov rdx, r11 @@ -5972,7 +6237,64 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 and bl, al xor bl, sil mov byte ptr [r14 + rdx], bl -.LBB1_165: + jmp .LBB1_189 +.LBB1_184: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 376] # 8-byte Reload + .p2align 4, 0x90 +.LBB1_185: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r12b + sete bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r12b + lea r9, [rax + 2] + sete bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB1_185 +.LBB1_186: + add rsi, r9 +.LBB1_187: + test r8b, 1 + je .LBB1_189 +# %bb.188: + cmp byte ptr [rsi], r12b + sete al + neg al + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 376] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r8 + rdx], bl +.LBB1_189: lea rsp, [rbp - 40] pop rbx pop r12 @@ -5982,102 +6304,102 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 pop rbp vzeroupper ret -.LBB1_166: - and r13, -32 - mov rax, r13 +.LBB1_190: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - mov qword ptr [rsp + 384], r13 # 8-byte Spill - lea rax, [r11 + 4*r13] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 376], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r12d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 272], r11 # 8-byte Spill + mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB1_167: # =>This Inner Loop Header: Depth=1 +.LBB1_191: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 408], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 88], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 160], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 248], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 264], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] - mov rdx, rcx + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - mov rcx, rbx - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rdx + 1] + movzx eax, byte ptr [rdi + rcx + 1] + mov rdx, rcx vmovd xmm4, eax - movzx eax, byte ptr [rsi + rbx + 1] + mov rcx, rbx + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rsi + rdx + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm13, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rsi + rdx + 6] + movzx eax, byte ptr [rdi + rdx + 6] mov qword ptr [rsp + 240], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 416 mov qword ptr [rsp + 32], rax # 8-byte Spill @@ -6086,1881 +6408,1882 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov qword ptr [rsp + 152], rax # 8-byte Spill - mov rax, rbx - or rax, 576 - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov rax, rbx - or rax, 608 mov qword ptr [rsp + 104], rax # 8-byte Spill - mov r15, rbx - or r15, 640 - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov r11, rbx - or r11, 672 - mov qword ptr [rsp + 200], r11 # 8-byte Spill - mov r8, rbx - or r8, 704 - mov qword ptr [rsp + 176], r8 # 8-byte Spill - mov rdx, rbx - or rdx, 736 - mov qword ptr [rsp + 192], rdx # 8-byte Spill - mov r12, rbx - or r12, 768 - mov qword ptr [rsp + 216], r12 # 8-byte Spill - mov r14, rbx - or r14, 800 - mov qword ptr [rsp + 184], r14 # 8-byte Spill - mov r10, rbx + or rbx, 576 + mov qword ptr [rsp + 264], rbx # 8-byte Spill + mov rax, rcx + or rax, 608 + mov qword ptr [rsp + 200], rax # 8-byte Spill + mov r14, rcx + or r14, 640 + mov qword ptr [rsp + 112], r14 # 8-byte Spill + mov rax, rcx + or rax, 672 + mov qword ptr [rsp + 192], rax # 8-byte Spill + mov r12, rcx + or r12, 704 + mov qword ptr [rsp + 144], r12 # 8-byte Spill + mov rsi, rcx + or rsi, 736 + mov qword ptr [rsp + 208], rsi # 8-byte Spill + mov r15, rcx + or r15, 768 + mov qword ptr [rsp + 224], r15 # 8-byte Spill + mov r11, rcx + or r11, 800 + mov qword ptr [rsp + 232], r11 # 8-byte Spill + mov r10, rcx or r10, 832 - mov qword ptr [rsp + 80], r10 # 8-byte Spill - mov r9, rbx + mov qword ptr [rsp + 88], r10 # 8-byte Spill + mov r9, rcx or r9, 864 - mov qword ptr [rsp + 72], r9 # 8-byte Spill - mov rax, rbx - or rax, 896 - mov qword ptr [rsp + 248], rax # 8-byte Spill - mov rdi, rbx - or rdi, 928 - mov qword ptr [rsp + 112], rdi # 8-byte Spill - mov rax, rbx - mov qword ptr [rsp + 256], rbx # 8-byte Spill + mov qword ptr [rsp + 216], r9 # 8-byte Spill + mov r8, rcx + or r8, 896 + mov qword ptr [rsp + 80], r8 # 8-byte Spill + mov rdx, rcx + or rdx, 928 + mov qword ptr [rsp + 72], rdx # 8-byte Spill + mov rax, rcx + mov qword ptr [rsp + 256], rcx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 56], rcx # 8-byte Spill - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm9, xmm0, byte ptr [rsi + r13], 1 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + rbx], 2 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 11 - mov r13, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 1 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12], 2 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 3 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11], 4 - mov r8, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 5 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 6 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 7 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 12 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 13 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 14 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 15 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 1 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 2 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 3 + mov qword ptr [rsp + 96], rcx # 8-byte Spill + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + r13], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 4 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 1 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 2 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 3 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 4 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 6 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 7 mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 4 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 5 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 7 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 8 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 9 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 10 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 12 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 13 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 14 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rsi + r14 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 6 - mov r8, r9 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 15 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 1 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 3 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 4 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 5 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 7 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 2 + mov rsi, r12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 vinserti128 ymm15, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 1], 15 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm9, edx vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm10, edi - mov rdx, qword ptr [rsp + 152] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm10, edx + mov r8, qword ptr [rsp + 104] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 2], 1 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 2], 2 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 2], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 4 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 1 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 2 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 7 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 2], 8 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 9 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 2], 10 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 11 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 2], 12 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 2 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 4 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 2], 6 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 7 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 8 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 9 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 10 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 2], 11 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 12 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + rdx + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 4 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 5 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 6 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 13 - mov r14, r15 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 2 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 3], 3 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 3], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 7 - mov r11, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 3], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 7 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 2], 8 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 9 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 10 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 11 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 12 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 7 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 8 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 10 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 13 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 14 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r8 + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 5 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 6 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 11 + mov r12, r11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 13 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rax + 3], 1 + mov r13, rax + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 4 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 14 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm8, edi - mov r9, rbx - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 3], 15 + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 14 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm8, edx + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm11, edi + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm11, edx + mov r14, qword ptr [rsp + 104] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 1 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 2 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 3 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 4 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 4], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 4], 8 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 9 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 11 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 14 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 4], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm13, byte ptr [rsi + rax + 4], 1 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 4], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 4 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 4], 6 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 4], 8 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 1 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 3 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 4 + mov rcx, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 5 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 7 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 8 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 14 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 15 + vpinsrb xmm3, xmm13, byte ptr [rdi + r13 + 4], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 4 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 6 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 10 mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 4], 11 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 4], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 11 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 13 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 4], 15 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm14, byte ptr [rsi + r9 + 5], 1 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 2 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 5 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 6 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 7 - mov r13, rcx - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 8 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 14 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r14 + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 2 + mov r14, r15 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 5 + mov r10, rcx + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 5], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 9 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 11 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 11 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 14 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 5], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + rax + 5], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 13 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 3 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 6 - mov r10, rdi - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 7 - mov r14, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 5], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r13 + 5], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 4 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 5], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 5], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 6 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 5], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 12 + mov r12, r11 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 vinserti128 ymm14, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 5], 15 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 5], 15 mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm3, edi + movzx edx, byte ptr [rdi + rax + 10] + vmovd xmm3, edx vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm4, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rsi + rax + 6], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 2 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 6], 3 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 6], 4 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 6], 5 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 7 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 8 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 9 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 11 - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 6], 12 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 6], 13 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 15 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rcx + 6], 1 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 2 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 4 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 6], 6 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 7 - mov r10, r14 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 8 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 10 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 12 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 13 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 14 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 4 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 7 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 7], 9 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 10 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 10] + vmovd xmm4, edx + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rsi + 6], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 5 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 8 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 11 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 12 mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 7], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 7], 13 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 14 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 15 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 1 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 13 mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 3 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 5 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 6 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 7], 8 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 10 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 14 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 15 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rcx + 6], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 5 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 7 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 6], 8 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 10 + mov r15, r13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 6], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 13 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 14 + mov r13, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 1 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 4 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 7 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 10 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 13 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 15 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 1 mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 2 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 3 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 6 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 7], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 7], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 12 mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rcx + 7], 14 + vpinsrb xmm0, xmm1, byte ptr [rdi + rcx + 7], 14 mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 11] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 7], 15 + movzx edx, byte ptr [rdi + rcx + 11] + vmovd xmm1, edx + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 11] - vmovd xmm2, edi - vpinsrb xmm0, xmm9, byte ptr [rsi + rax + 8], 1 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 8], 2 + movzx edx, byte ptr [rdi + rcx + 11] + vmovd xmm2, edx mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 8], 4 - mov rbx, r14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 8], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 8], 8 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 8], 9 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 8], 11 - mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 8], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 13 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 14 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 15 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rsi + rdx + 8], 1 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 8], 2 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 4 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 5 + vpinsrb xmm0, xmm9, byte ptr [rdi + rcx + 8], 1 + mov r15, r13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 8], 2 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 4 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 8], 5 mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 8], 8 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 8], 9 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 8], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 12 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 13 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 14 - mov r13, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 15 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rsi + r13 + 9], 1 - vpinsrb xmm6, xmm6, byte ptr [rsi + r12 + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 7 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 8 - vpinsrb xmm6, xmm6, byte ptr [rsi + r8 + 9], 9 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 11 - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rsi + rax + 9], 1 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 9], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 6 + mov r8, rax + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 7 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 8], 8 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 8], 9 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 10 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 11 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 13 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 4 - mov r14, rdi + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 8], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 6 + mov r14, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 14 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm8, byte ptr [rdi + rax + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 9], 5 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 9], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 9], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 7 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 9], 9 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 12 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rax + 9], 1 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 9], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 4 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 8 + mov r14, r11 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 10 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 12 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 9], 15 mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm0, edi + movzx edx, byte ptr [rdi + rax + 12] + vmovd xmm0, edx vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1088], ymm5 # 32-byte Spill mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 10], 1 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 10], 2 + movzx edx, byte ptr [rdi + rax + 12] + vmovd xmm5, edx mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 3 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 4 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 10], 7 - mov r8, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 8 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 3 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 4 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 7 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 10], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 11 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 10], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 10], 14 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 10], 15 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 1 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 2 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 5 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 9 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 11 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 10], 13 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 10], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 3 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 5 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 10], 6 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 8 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 9 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 10 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 11 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 12 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 13 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 14 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 15 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 11], 4 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 5 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 11], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 7 - mov r9, rdx - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 11], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 5 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 11], 8 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 11 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 11 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 14 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 11], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 11], 1 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 4 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 6 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 7 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 11], 8 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 11], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 11], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 13 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 1 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 11], 6 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 14 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 13] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 15 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 14 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 13] + vmovd xmm3, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1024], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 13] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 1 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 3 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 5 - mov rbx, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 12], 8 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 9 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 11 - mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 12], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 13 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 12], 14 - mov r10, r15 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 12], 15 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rsi + r13 + 12], 1 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 12], 2 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 4 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 13] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 1 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 4 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 8 + mov r9, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 9 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 10 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 12], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 15 + vpinsrb xmm2, xmm5, byte ptr [rdi + rax + 12], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 4 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 8 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 9 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 12 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 14 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 6 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 12], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 12], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 10 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 12], 11 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 13 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 14 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 15 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 4 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 5 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 7 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 13], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 11 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 15 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 2 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 3 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 5 mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 1 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 4 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 6 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 13], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 9 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 12 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 13], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 2 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 4 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 13], 7 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 13], 11 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 13], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 13], 13 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rax + 13], 15 - mov r13, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 14] - vmovd xmm1, edi + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 14] + vmovd xmm1, edx vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - mov r14, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r14 + 14] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 1 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 14], 2 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 14], 3 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 14], 4 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 14] + vmovd xmm0, edx + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov r10, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 2 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 5 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 6 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 4 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 14], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 14], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 8 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 15 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 14], 10 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 4 + mov r9, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 14], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 6 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 7 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 8 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 12 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 14 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 15 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + r14 + 15] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 3 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 9 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 15] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 15], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 15 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 14], 1 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 3 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 14], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 5 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 14], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 7 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 8 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 10 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 14], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 15 - movzx edi, byte ptr [rsi + r13 + 15] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 4 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 15], 7 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 8 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 9 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 11 - mov r13, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 15], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 13 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 15 - movzx edi, byte ptr [rsi + r14 + 15] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 15], 1 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 2 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 15], 4 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 6 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 15], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 10 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 14 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 15], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 16] - vmovd xmm0, edi - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 16], 1 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 2 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 16], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 5 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 7 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 8 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 9 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 16], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 16] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 1 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 2 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 16], 7 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 8 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 11 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 12 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 13 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 16], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 16], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 17] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 17], 1 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 17], 3 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 4 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 17], 6 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 8 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 17], 10 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 17], 11 - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 12 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 13 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 17] - vmovd xmm3, edi - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 17], 1 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 17], 2 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 17], 3 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 5 + movzx edx, byte ptr [rdi + r14 + 16] + vmovd xmm0, edx + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 1 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 4 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 5 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 6 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 8 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 7 + mov r11, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 16], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 16], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 13 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 14 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 15 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rbx + 16] + vmovd xmm1, edx + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 16], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 2 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 4 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 6 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 7 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 8 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 10 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 13 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 17] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 1 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 2 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 5 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 15 + movzx edx, byte ptr [rdi + rbx + 17] + vmovd xmm3, edx + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 1 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 17], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 17], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 3 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 5 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 17], 8 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 11 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rax + 17], 15 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 18] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 18], 2 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rbx + 18] + vmovd xmm0, edx mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 4 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 5 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 18], 6 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 2 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 4 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 5 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 7 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 8 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 10 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 8 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 9 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 11 - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 18], 12 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 14 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 18] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 18], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 18], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 4 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 5 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 18], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 18], 7 - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 10 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 18], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 13 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 14 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 18] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 1 mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 18], 14 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 18], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 19] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 1 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 3 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 4 - mov r13, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 19], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 19], 6 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 19], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 19], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 13 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 19], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 6 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 13 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 14 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 15 + movzx edx, byte ptr [rdi + rbx + 19] + vmovd xmm2, edx + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 3 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 19], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 5 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 6 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 7 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 8 + mov r10, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 19] + vmovd xmm3, edx + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 15 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r10 + 19] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 1 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 8 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 19], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 7 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 19], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 19], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 19], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 20] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 1 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 3 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 6 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 7 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 20], 8 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 9 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 11 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 20], 14 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 20], 15 - movzx edi, byte ptr [rsi + r10 + 20] - vmovd xmm1, edi - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 20], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 20], 2 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 20], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 4 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 6 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 20], 7 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 8 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 10 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 11 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 14 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 15 - movzx edi, byte ptr [rsi + r11 + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 2 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 4 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 20] + vmovd xmm0, edx + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 1 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 21], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 21], 8 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 11 - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 21], 15 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 21] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 21], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 20], 4 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 9 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 21], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 7 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 21], 8 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 9 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 11 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 13 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 15 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + r9 + 20] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 1 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 2 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 3 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 4 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 8 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 9 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 13 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 14 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 20], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 21] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 2 + mov r11, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 21], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 4 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 8 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 14 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 15 + movzx edx, byte ptr [rdi + r9 + 21] + vmovd xmm3, edx + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 3 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 21], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 10 mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 21], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 21], 12 - mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 21], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 13 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + r10 + 21], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + r14 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 1 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 3 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 4 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 5 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 7 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 8 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 9 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 22], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 22], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 13 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 22], 14 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 15 - movzx edi, byte ptr [rsi + r11 + 22] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 1 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 2 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 22], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 22], 4 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 22], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 6 - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 22], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 22], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 22], 11 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 22], 13 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 22], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 23] - vmovd xmm2, edi - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 23], 1 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 23], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 3 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 4 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 5 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 6 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 10 + mov r10, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + r10 + 22] + vmovd xmm0, edx + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 1 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 3 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 4 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 5 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 6 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 7 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 12 mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 11 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 12 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 23], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 22] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 2 mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 23] - vmovd xmm3, edi - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 23], 1 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 4 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 7 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 9 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 23], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 4 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 6 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 11 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 14 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 14 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 15 + movzx edx, byte ptr [rdi + r10 + 23] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 23], 2 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 4 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 8 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 13 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 15 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + r15 + 23] + vmovd xmm3, edx + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 5 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 8 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 13 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 24] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 24], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 24], 2 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 24], 3 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 4 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 6 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 24], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 8 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 9 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 24], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 24], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 24], 15 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 24] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 1 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 2 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 4 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 6 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 8 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 10 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 14 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 15 - movzx edi, byte ptr [rsi + rcx + 25] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 1 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 25], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 25], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 4 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 25], 7 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 25], 9 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 25], 10 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 25], 11 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 14 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 24] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 4 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 10 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 24], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 15 + movzx edx, byte ptr [rdi + r15 + 24] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 15 - movzx edi, byte ptr [rsi + rdx + 25] - vmovd xmm3, edi - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 5 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 25], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 7 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 8 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 25], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 3 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 4 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 7 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 10 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 12 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 13 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 14 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 25] + vmovd xmm2, edx + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 4 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 8 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 25] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 1 mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 12 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 13 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 8 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 9 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 14 vinserti128 ymm9, ymm1, xmm0, 1 - vpinsrb xmm0, xmm3, byte ptr [rsi + r11 + 25], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + rbx + 25], 15 vinserti128 ymm8, ymm0, xmm2, 1 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 26] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 2 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 3 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 5 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 26], 6 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 8 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 26], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 11 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 12 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 26], 13 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 26] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 1 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 2 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 4 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 6 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 7 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 26], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 12 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 26], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 14 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 15 - movzx edi, byte ptr [rsi + r11 + 27] - vmovd xmm2, edi - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 27], 1 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 27], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 4 - mov r8, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 27], 6 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 7 + movzx edx, byte ptr [rdi + rax + 26] + vmovd xmm0, edx + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 1 + mov r10, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 5 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 7 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 10 mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 8 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 27], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 11 mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 12 mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 27], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 27], 13 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 14 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 15 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 27] - vmovd xmm3, edi - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 1 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 27], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 13 mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 3 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 27], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 5 - mov r15, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 6 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 8 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 11 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 27], 13 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 14 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rsi + 26] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 1 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 2 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 6 + mov r12, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 13 + mov r9, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 27] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 2 + mov r13, r10 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 4 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 10 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 11 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 14 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 15 + movzx edx, byte ptr [rdi + rsi + 27] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 3 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 4 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 5 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 8 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 1 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 3 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 7 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 9 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 11 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 14 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 15 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r12 + 28] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 28], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 4 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 28], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 6 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 7 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 28], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 9 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 10 - mov r10, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 28], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 14 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 29] - vmovd xmm2, edi - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 29], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 4 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 6 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 8 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 9 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 14 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 15 - movzx edi, byte ptr [rsi + r12 + 29] - vmovd xmm3, edi - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 29], 1 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 2 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 3 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 29], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 29], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 29], 8 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 29], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 29], 12 - mov r14, rdx - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 13 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 28] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 3 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 6 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 7 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 8 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 12 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 15 + mov r11, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + r11 + 28] + vmovd xmm1, edx + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 6 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 7 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 8 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 13 mov r10, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rsi + r10 + 29], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 29] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 4 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 10 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 11 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 14 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 15 + movzx edx, byte ptr [rdi + r11 + 29] + vmovd xmm3, edx + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 3 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 29], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 9 + mov r15, rbx + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 10 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + r10 + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rsi + rdx + 29], 15 + mov r10, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + r10 + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill - mov r8, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + r8 + 30] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 30], 1 - movzx edi, byte ptr [rsi + r8 + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 31], 1 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 30] + vmovd xmm0, edx + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 30], 1 + movzx edx, byte ptr [rdi + rax + 31] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 31], 1 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + mov rax, r9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 31], 5 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rbx, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 31], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 31], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 6 - mov r11, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 31], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 11 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + rax + 31], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx eax, byte ptr [rsi + rcx + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + r14 + 31], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 30] vmovd xmm1, eax - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 30], 1 - movzx eax, byte ptr [rsi + rcx + 31] + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 1 + movzx eax, byte ptr [rdi + rdx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 31], 1 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + r12 + 31], 4 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 31], 7 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 8 - mov rax, r9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 31], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 4 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 11 - mov rax, r14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 31], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 31], 14 - mov rax, rdx - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 31], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + mov rax, rcx + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 31], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -8089,1993 +8412,2002 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [r11 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r11 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r11 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r11 + 4*rcx], ymm1 + vmovdqu ymmword ptr [rbx + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rbx + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rbx + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rbx + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB1_167 -# %bb.168: - mov r13, qword ptr [rsp + 392] # 8-byte Reload - cmp r13, qword ptr [rsp + 384] # 8-byte Folded Reload + jne .LBB1_191 +# %bb.192: + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload mov r15, qword ptr [rsp + 280] # 8-byte Reload - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 400] # 8-byte Reload - jne .LBB1_36 - jmp .LBB1_109 -.LBB1_169: - and r15, -32 - mov rax, r15 + mov r12d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB1_139 + jmp .LBB1_143 +.LBB1_193: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - mov qword ptr [rsp + 384], r15 # 8-byte Spill - lea rax, [r11 + 4*r15] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 376], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r12d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 272], r11 # 8-byte Spill + mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB1_170: # =>This Inner Loop Header: Depth=1 +.LBB1_194: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 408], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 232], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 216], rax # 8-byte Spill + mov qword ptr [rsp + 248], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill mov rax, rbx or rax, 320 mov qword ptr [rsp + 40], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rcx + 1] + movzx eax, byte ptr [rdi + rcx + 1] + mov rdx, rcx vmovd xmm4, eax - movzx eax, byte ptr [rsi + rbx + 1] + mov rcx, rbx + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rsi + rcx + 2] - mov rdx, rcx + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - mov rcx, rbx - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm13, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rsi + rdx + 6] - mov qword ptr [rsp + 248], rdx # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 240], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 416 mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill or rbx, 576 - mov qword ptr [rsp + 256], rbx # 8-byte Spill + mov qword ptr [rsp + 264], rbx # 8-byte Spill mov rax, rcx or rax, 608 - mov qword ptr [rsp + 48], rax # 8-byte Spill - mov r12, rcx - or r12, 640 - mov qword ptr [rsp + 208], r12 # 8-byte Spill + mov qword ptr [rsp + 200], rax # 8-byte Spill mov r14, rcx - or r14, 672 - mov qword ptr [rsp + 144], r14 # 8-byte Spill + or r14, 640 + mov qword ptr [rsp + 112], r14 # 8-byte Spill mov rax, rcx - or rax, 704 - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov rdi, rcx - or rdi, 736 - mov r9, rcx - or r9, 768 - mov qword ptr [rsp + 224], r9 # 8-byte Spill + or rax, 672 + mov qword ptr [rsp + 192], rax # 8-byte Spill + mov r12, rcx + or r12, 704 + mov qword ptr [rsp + 144], r12 # 8-byte Spill + mov rsi, rcx + or rsi, 736 + mov qword ptr [rsp + 208], rsi # 8-byte Spill mov r15, rcx - or r15, 800 - mov qword ptr [rsp + 112], r15 # 8-byte Spill + or r15, 768 + mov qword ptr [rsp + 224], r15 # 8-byte Spill mov r11, rcx - or r11, 832 - mov qword ptr [rsp + 192], r11 # 8-byte Spill + or r11, 800 + mov qword ptr [rsp + 232], r11 # 8-byte Spill mov r10, rcx - or r10, 864 + or r10, 832 mov qword ptr [rsp + 88], r10 # 8-byte Spill + mov r9, rcx + or r9, 864 + mov qword ptr [rsp + 216], r9 # 8-byte Spill mov r8, rcx or r8, 896 - mov qword ptr [rsp + 128], r8 # 8-byte Spill + mov qword ptr [rsp + 80], r8 # 8-byte Spill mov rdx, rcx or rdx, 928 - mov qword ptr [rsp + 240], rdx # 8-byte Spill + mov qword ptr [rsp + 72], rdx # 8-byte Spill mov rax, rcx - mov qword ptr [rsp + 264], rcx # 8-byte Spill + mov qword ptr [rsp + 256], rcx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 80], rcx # 8-byte Spill - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm9, xmm0, byte ptr [rsi + r13], 1 - vpinsrb xmm0, xmm9, byte ptr [rsi + rbx], 2 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 5 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 7 - mov r13, rdi - mov qword ptr [rsp + 160], rdi # 8-byte Spill - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 1 + mov qword ptr [rsp + 96], rcx # 8-byte Spill + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + r13], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 4 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 1 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 2 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 3 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 4 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 2 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12], 3 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 4 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11], 5 - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 6 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 7 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 6 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 10 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 12 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 13 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 14 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 15 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 1 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 2 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 3 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 4 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 5 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 7 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 15 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 1 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 3 mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 9 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 10 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 12 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 13 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 14 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rsi + r14 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 4 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 5 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 7 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 2 + mov rsi, r12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 14 - vinserti128 ymm15, ymm3, xmm0, 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 1], 15 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 + vinserti128 ymm15, ymm3, xmm0, 1 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm9, edx vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm10, edi - mov r8, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm10, edx + mov r8, qword ptr [rsp + 104] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 2], 1 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 2], 2 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 2], 3 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 1 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 2 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 5 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 2], 6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 2], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 8 - mov r12, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 9 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 10 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 11 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 2], 12 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 15 - mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 7 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 2], 8 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 9 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 10 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 11 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 12 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 6 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 7 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 10 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 12 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + r8 + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 3 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 4 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 7 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 13 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 14 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 3], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 7 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 8 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 10 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 13 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 14 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r8 + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 5 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 6 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 11 + mov r12, r11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 13 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rax + 3], 1 + mov r13, rax mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 4 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 3], 5 - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 2 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 8 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 3], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 14 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm8, edi - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 3], 15 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 14 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm8, edx + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm11, edi + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm11, edx + mov r14, qword ptr [rsp + 104] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 1 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 3 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 4], 5 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 6 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 1 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 3 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 4 + mov rcx, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 5 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 7 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 8 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 9 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 12 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 4], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 4], 15 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm13, byte ptr [rsi + rax + 4], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 4], 2 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 4], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 5 - mov rdi, r14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 6 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 7 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 4], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 4], 10 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 4], 12 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 4], 13 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 4], 15 - vpinsrb xmm4, xmm14, byte ptr [rsi + r8 + 5], 1 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 2 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 5 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 6 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 5], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 9 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 10 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 5], 11 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 12 - mov r8, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 5], 13 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 14 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 15 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + r12 + 5], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 14 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 15 + vpinsrb xmm3, xmm13, byte ptr [rdi + r13 + 4], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 5 mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 5], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 5], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 5], 8 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 5], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 6 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 10 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 11 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 14 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r14 + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 2 + mov r14, r15 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 5 + mov r10, rcx + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 5], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 9 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r13 + 5], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 6 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 5], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 12 + mov r12, r11 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 14 - vinserti128 ymm14, ymm3, xmm0, 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 5], 15 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm3, edi + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 + vinserti128 ymm14, ymm3, xmm0, 1 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 5], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 10] + vmovd xmm3, edx vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm4, edi - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rsi + r11 + 6], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 6], 3 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 4 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 10] + vmovd xmm4, edx + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rsi + 6], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 5 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 6], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 9 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 6], 10 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 6], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 6], 13 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 15 - vpinsrb xmm5, xmm7, byte ptr [rsi + r12 + 6], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 8 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 11 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 12 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 14 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 15 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rcx + 6], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 5 mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 3 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 5 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 6 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 7 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 6], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 6], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 7 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 6], 8 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 9 mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 10 - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 6], 11 - mov r8, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 6], 12 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 6], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 10 + mov r15, r13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 6], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 13 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 3 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 4 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 5 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 7 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 12 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 13 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 14 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 15 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 14 + mov r13, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 1 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 4 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 7 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 10 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 13 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 15 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 1 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 2 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 3 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 3 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 7], 6 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 7], 8 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 6 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 7], 9 mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 7], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 12 mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rcx + 7], 14 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 11] - vmovd xmm1, edi mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 7], 15 + vpinsrb xmm0, xmm1, byte ptr [rdi + rcx + 7], 14 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 11] + vmovd xmm1, edx + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 11] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + rcx + 8], 1 - mov r8, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 8], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 8], 4 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 5 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 7 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 8], 8 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 8], 9 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 8], 10 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 11 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 8], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 8], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 15 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rsi + rax + 8], 1 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 8], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 5 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 8], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 7 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 8 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 11] + vmovd xmm2, edx + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + rcx + 8], 1 + mov r15, r13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 8], 2 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 4 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 8], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 6 + mov r8, rax + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 7 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 8], 8 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 8], 9 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 10 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 11 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 13 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 8], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 6 + mov r14, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 10 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 12 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 13 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 14 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 15 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rsi + r13 + 9], 1 - vpinsrb xmm6, xmm6, byte ptr [rsi + r8 + 9], 2 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 3 - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 4 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 6 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 7 - vpinsrb xmm6, xmm6, byte ptr [rsi + r14 + 9], 8 - vpinsrb xmm6, xmm6, byte ptr [rsi + r10 + 9], 9 - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 10 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 11 - vpinsrb xmm6, xmm6, byte ptr [rsi + r12 + 9], 12 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 13 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 14 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r13 + 9], 15 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rsi + rcx + 9], 1 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 9], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 4 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r11 + 9], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 9], 6 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 9], 7 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 9], 8 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 9], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 9], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 14 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm8, byte ptr [rdi + rax + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 9], 5 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 7 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 9], 9 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 12 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rax + 9], 1 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 9], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 4 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 8 + mov r14, r11 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm0, edi + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 9], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 12] + vmovd xmm0, edx vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1088], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 10], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 3 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 4 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 10], 5 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 6 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 10], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 10], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 12 - mov r10, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 10], 13 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 10], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 10], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 12] + vmovd xmm5, edx mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 1 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 4 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 5 - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 7 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 3 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 4 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 7 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 10], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 13 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 10 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 3 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 5 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 10], 6 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 8 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 9 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 10 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 12 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 13 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 14 mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 12 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 14 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 3 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 11], 5 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 11], 7 - mov r12, r9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 11], 8 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 9 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 10 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 5 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 11], 8 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 13 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 1 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 11], 6 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 10 mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 11], 13 - mov r13, r10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 11], 14 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 15 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 11], 1 - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 11], 6 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 11], 7 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 10 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm3 # 32-byte Spill - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 11], 14 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 13] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 15 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 14 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 13] + vmovd xmm3, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1024], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 13] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 1 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 2 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 12], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 4 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 12], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 12], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 12], 7 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 12], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 11 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 13 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 15 - vpinsrb xmm2, xmm5, byte ptr [rsi + rdx + 12], 1 - mov rdi, r14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 12], 2 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 12], 3 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 13] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 1 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 4 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 8 + mov r9, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 9 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 10 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 12], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 15 + vpinsrb xmm2, xmm5, byte ptr [rdi + rax + 12], 1 mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 4 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 12], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 12], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 2 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 12], 9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 12], 10 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 12], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 12], 12 - mov r9, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 12], 13 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 12], 14 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 12], 15 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 1 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 13], 3 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 13], 5 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 13], 6 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 13], 8 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 13], 9 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 12 - mov r10, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 13], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 13], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 4 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 8 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 9 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 12 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 14 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 15 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 4 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 5 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 7 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 13], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 11 mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 15 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 13], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 13], 5 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 6 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 13 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 10 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 13], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 15 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 2 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 3 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 5 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 13], 13 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rax + 13], 15 - mov r13, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 14] - vmovd xmm1, edi + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 14] + vmovd xmm1, edx vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 14] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 1 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 3 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 14], 4 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 14], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 6 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 14] + vmovd xmm0, edx + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov r10, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 4 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 14], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 14], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 8 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 3 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 4 + mov r9, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 14], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 6 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 7 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 8 mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 14], 9 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 10 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 14], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 14], 13 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 14], 14 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 14], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 12 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 14 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 15 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + r14 + 15] + vmovd xmm2, edx mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 14], 1 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 2 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 14], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 14], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 6 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 14], 7 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 8 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 14], 9 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 10 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 15 - movzx edi, byte ptr [rsi + r13 + 15] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 15], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 6 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 7 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 9 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 12 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 13 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 15], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 15], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 15] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 1 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 3 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 9 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 15] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 3 mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 15], 7 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 15], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 15], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 10 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 15], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 13 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 15], 14 - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 15 - vinserti128 ymm0, ymm0, xmm1, 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 15 + vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + r10 + 16] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 16], 1 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 16], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 16], 3 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 16], 4 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 16], 5 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 16], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 16], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 10 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 12 - mov r8, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 16], 14 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 15 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rbx + 16] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 1 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 3 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 5 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 6 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 7 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 8 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 9 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 16], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 12 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 16], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 16], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 15 - movzx edi, byte ptr [rsi + r10 + 17] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 1 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 2 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 17], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 5 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 17], 6 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 7 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 17], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 9 + movzx edx, byte ptr [rdi + r14 + 16] + vmovd xmm0, edx + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 1 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 4 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 5 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 7 + mov r11, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 16], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 16], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 13 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 14 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 15 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rbx + 16] + vmovd xmm1, edx + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 16], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 2 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 4 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 6 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 7 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 8 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 10 mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 17], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 13 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 14 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 15 - movzx edi, byte ptr [rsi + rbx + 17] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 1 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 2 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 17], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 17], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 6 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 7 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 9 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 17], 10 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 17], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 13 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 17] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 1 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 2 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 5 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 15 + movzx edx, byte ptr [rdi + rbx + 17] + vmovd xmm3, edx + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 3 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 5 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 17], 8 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 11 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rdi + 17], 15 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 18] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 3 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 4 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 18], 8 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 9 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 18], 12 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 15 - movzx edi, byte ptr [rsi + rbx + 18] - vmovd xmm1, edi - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 18], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 18], 3 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 18], 4 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 18], 5 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rbx + 18] + vmovd xmm0, edx + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 2 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 4 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 5 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 7 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 8 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 6 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 18], 7 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 18], 10 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 15 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 19] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 1 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 19], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 19], 4 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 5 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 6 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 19], 10 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 12 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 13 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 19], 14 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 19], 15 - movzx edi, byte ptr [rsi + rbx + 19] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 19], 1 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 13 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 14 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 18] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 6 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 7 mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 19], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 19], 5 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 19], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 19], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 19], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 9 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 19], 10 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 11 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 19], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 13 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 14 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 15 + movzx edx, byte ptr [rdi + rbx + 19] + vmovd xmm2, edx + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 3 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 19], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 5 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 6 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 7 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 8 + mov r10, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 19] + vmovd xmm3, edx + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 8 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 14 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 19], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov r15, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + r15 + 20] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 3 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 4 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 20], 5 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 6 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 12 mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 20], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 20], 15 + movzx edx, byte ptr [rdi + rax + 20] + vmovd xmm0, edx + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 1 mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 20] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 20], 1 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 20], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 20], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 20], 4 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 20], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 20], 6 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 20], 7 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 20], 8 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 20], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 20], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 20], 4 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 11 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 13 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 15 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + r9 + 20] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 1 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 2 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 3 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 4 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 6 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 8 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 9 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 13 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 14 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 20], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 21] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 2 mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 20], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 20], 12 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 20], 13 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 20], 15 - movzx edi, byte ptr [rsi + r15 + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 1 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 21], 5 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 21], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 4 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 8 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 14 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 15 + movzx edx, byte ptr [rdi + r9 + 21] + vmovd xmm3, edx + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 3 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 8 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 21], 9 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 10 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 21], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 12 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 21], 13 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 14 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 15 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 21] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 21], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 5 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 21], 6 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 7 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 21], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 21], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 21], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 21], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 10 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 13 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rax + 21], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + r14 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 1 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 3 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 4 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 22], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 22], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 22], 9 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 22], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 22], 11 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 22], 13 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 14 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 15 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rbx + 22] - vmovd xmm1, edi - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 1 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 22], 2 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 3 + mov r10, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + r10 + 22] + vmovd xmm0, edx + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 1 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 3 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 4 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 5 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 6 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 7 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 10 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 22] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 1 mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 4 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 22], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 2 mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 8 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 4 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 6 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 11 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 14 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 15 + movzx edx, byte ptr [rdi + r10 + 23] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 23], 2 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 4 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 8 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 13 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 15 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + r15 + 23] + vmovd xmm3, edx + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 5 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 8 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 9 mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 10 - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 22], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 12 mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 13 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 13 mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 22], 15 - movzx edi, byte ptr [rsi + rax + 23] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 1 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 2 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 3 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 5 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 6 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 23], 10 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 23], 12 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 13 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 14 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 15 - movzx edi, byte ptr [rsi + rbx + 23] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 23], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 3 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 23], 4 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 23], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 23], 6 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 7 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 23], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 23], 9 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 23], 11 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 12 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 23], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 23], 14 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 23], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 24] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 1 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 24], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 24], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 5 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 24], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 12 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 24] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 1 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 24], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 24], 5 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 24], 6 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 24], 8 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 10 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 24], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 15 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + r8 + 25] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 25], 2 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 24] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 3 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 4 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 10 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 24], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 15 + movzx edx, byte ptr [rdi + r15 + 24] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 3 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 7 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 10 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 11 mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 3 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 25], 4 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 5 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 7 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 25], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 12 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 13 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 14 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 25] + vmovd xmm2, edx + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 3 mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 4 mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 25], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 25], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 12 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 13 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 7 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 8 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 11 mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 15 - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 25] - vmovd xmm3, edi - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 1 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 25], 6 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 7 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 25], 9 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 12 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 25] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 2 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 8 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 9 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 14 vinserti128 ymm9, ymm1, xmm0, 1 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rdi + 25], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + rbx + 25], 15 vinserti128 ymm8, ymm0, xmm2, 1 - movzx edi, byte ptr [rsi + r8 + 26] - vmovd xmm0, edi - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 1 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 26], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 6 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 26], 8 + movzx edx, byte ptr [rdi + rax + 26] + vmovd xmm0, edx + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 1 + mov r10, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 3 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 26], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 11 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 13 - mov rcx, r14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 5 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 7 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 8 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 10 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx edx, byte ptr [rdi + rsi + 26] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 1 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 2 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 4 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 5 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 6 + mov r12, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 13 + mov r9, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 27] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 2 + mov r13, r10 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 4 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 10 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 11 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 15 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + r12 + 26] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 1 - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 26], 2 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 26], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 6 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 7 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 13 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 10 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 26], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 26], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 14 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 15 - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 27] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 1 - mov r8, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 14 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 15 + movzx edx, byte ptr [rdi + rsi + 27] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 3 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 4 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 5 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 8 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 10 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 11 mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 3 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 4 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 27], 5 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 27], 6 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 9 - mov r10, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 27], 10 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 27], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 13 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 14 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 15 - movzx edi, byte ptr [rsi + r12 + 27] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 27], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 5 - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 27], 6 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 7 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 9 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 27], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 27], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 27], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 28] - vmovd xmm0, edi - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 3 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 28], 6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 8 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 10 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 12 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 14 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 28] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 1 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 2 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 4 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 28], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 6 - mov r14, r15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 7 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 28], 10 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 28], 11 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 15 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 29] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 1 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 28] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 3 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 6 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 7 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 8 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 12 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 15 mov r11, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 3 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 4 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 5 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 29], 7 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 29], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 9 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 29], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 29], 13 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 15 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + r8 + 29] - vmovd xmm3, edi - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 29], 3 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 29], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 29], 5 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 29], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 7 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 29], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 29], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 13 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rsi + r15 + 29], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rsi + rax + 29], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 30] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 30], 1 - movzx edi, byte ptr [rsi + rax + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 31], 1 - mov rax, r11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 31], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 3 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 5 + movzx edx, byte ptr [rdi + r11 + 28] + vmovd xmm1, edx mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 6 - mov r11, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 31], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 31], 12 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + rax + 31], 15 - mov rdx, r8 - movzx eax, byte ptr [rsi + r8 + 30] - vmovd xmm1, eax - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 30], 1 - movzx eax, byte ptr [rsi + r8 + 31] - vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 31], 1 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + r13 + 31], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 31], 6 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 6 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 7 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 8 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 13 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 14 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 29] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 4 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 10 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 11 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 13 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 14 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 15 + movzx edx, byte ptr [rdi + r11 + 29] + vmovd xmm3, edx + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 1 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 3 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 29], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 9 + mov r15, rbx + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 10 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + r10 + 29], 14 + vinserti128 ymm0, ymm1, xmm0, 1 + vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill + mov r10, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + r10 + 29], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 240] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 30] + vmovd xmm0, edx + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 30], 1 + movzx edx, byte ptr [rdi + rax + 31] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 31], 1 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + mov rax, r9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 31], 5 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rbx, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 31], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + r14 + 31], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 30] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 1 + movzx eax, byte ptr [rdi + rdx + 31] + vmovd xmm7, eax + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 1 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 31], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 - mov rax, r12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + r12 + 31], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 31], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + mov rax, rcx + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 31], 13 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -10204,22 +10536,22 @@ comparison_equal_arr_scalar_avx2: # @comparison_equal_arr_scalar_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [r11 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r11 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r11 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r11 + 4*rcx], ymm1 + vmovdqu ymmword ptr [rbx + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rbx + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rbx + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rbx + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB1_170 -# %bb.171: - mov r15, qword ptr [rsp + 392] # 8-byte Reload - cmp r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 400] # 8-byte Reload - jne .LBB1_90 - jmp .LBB1_130 + jne .LBB1_194 +# %bb.195: + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB1_153 + jmp .LBB1_157 .Lfunc_end1: .size comparison_equal_arr_scalar_avx2, .Lfunc_end1-comparison_equal_arr_scalar_avx2 # -- End function @@ -10255,91 +10587,104 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 and rsp, -32 sub rsp, 1280 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 + mov r15, r8 mov r14, rcx cmp edi, 6 - jg .LBB2_17 + jg .LBB2_19 # %bb.1: cmp edi, 3 - jle .LBB2_32 + jle .LBB2_36 # %bb.2: cmp edi, 4 - je .LBB2_60 + je .LBB2_59 # %bb.3: cmp edi, 5 - je .LBB2_72 + je .LBB2_73 # %bb.4: cmp edi, 6 - jne .LBB2_165 + jne .LBB2_189 # %bb.5: mov r13d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_9 + je .LBB2_11 # %bb.6: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_9 +# %bb.7: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_7: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - lea rdx, [rdx + 4] +.LBB2_8: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r13d, dword ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_7 -# %bb.8: - add r14, 1 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_8 .LBB2_9: - sar r11, 5 - cmp r10, 32 - jl .LBB2_13 + sub r15, r8 + je .LBB2_189 # %bb.10: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill + add r14, 1 +.LBB2_11: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_15 +# %bb.12: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_11: # =>This Inner Loop Header: Depth=1 +.LBB2_13: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp r13d, dword ptr [rdx] - sete byte ptr [rsp + 160] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 4] sete r10b cmp r13d, dword ptr [rdx + 8] sete r14b cmp r13d, dword ptr [rdx + 12] - sete byte ptr [rsp + 136] # 1-byte Folded Spill + sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 16] - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 20] - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 24] sete bl cmp r13d, dword ptr [rdx + 28] sete dil cmp r13d, dword ptr [rdx + 32] - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 36] sete sil cmp r13d, dword ptr [rdx + 40] @@ -10351,33 +10696,33 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13d, dword ptr [rdx + 52] sete r12b cmp r13d, dword ptr [rdx + 56] - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 60] - sete al + sete cl cmp r13d, dword ptr [rdx + 64] - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 68] - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 136] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 72] - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 76] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 80] sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 80] + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 84] - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 88] - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 92] sete r15b cmp r13d, dword ptr [rdx + 96] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 100] - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 104] - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 108] - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 112] sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 116] @@ -10385,117 +10730,116 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13d, dword ptr [rdx + 120] sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 124] - sete cl + sete al add r10b, r10b - add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload shl bl, 6 shl dil, 7 or dil, bl shl r14b, 2 or r14b, r10b add sil, sil - add sil, byte ptr [rsp + 144] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 3 or bl, r14b mov r10d, ebx mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, sil - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload shl bl, 4 or bl, r10b mov esi, ebx shl r9b, 3 or r9b, r8b - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 5 or bl, sil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx esi, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload shl sil, 6 - shl al, 7 - or al, sil + shl cl, 7 + or cl, sil or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + or cl, r12b + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 96] # 1-byte Folded Reload + add bl, byte ptr [rsp + 112] # 1-byte Folded Reload mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 2 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 5 or bl, sil mov byte ptr [r14], dil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], al + mov byte ptr [r14 + 1], cl or r15b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 5 - or al, bl + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov ebx, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 2 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 5 + or cl, bl movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al + shl al, 7 + or al, bl + or al, cl mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], cl + mov byte ptr [r14 + 3], al add rdx, 128 add r14, 4 add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB2_11 -# %bb.12: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 168] # 8-byte Reload -.LBB2_13: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 + jne .LBB2_13 # %bb.14: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB2_127 -# %bb.15: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 168] # 8-byte Reload +.LBB2_15: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 +# %bb.16: + or rax, 1 + cmp r15, rax + je .LBB2_129 +# %bb.17: mov r10, r8 and r10, -2 xor edi, edi .p2align 4, 0x90 -.LBB2_16: # =>This Inner Loop Header: Depth=1 +.LBB2_18: # =>This Inner Loop Header: Depth=1 cmp r13d, dword ptr [rdx] sete al neg al @@ -10524,78 +10868,94 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor al, bl mov byte ptr [r14 + rsi], al cmp r10, rdi - jne .LBB2_16 - jmp .LBB2_155 -.LBB2_17: + jne .LBB2_18 + jmp .LBB2_179 +.LBB2_19: cmp edi, 8 - jle .LBB2_46 -# %bb.18: + jle .LBB2_43 +# %bb.20: cmp edi, 9 - je .LBB2_83 -# %bb.19: + je .LBB2_86 +# %bb.21: cmp edi, 11 - je .LBB2_94 -# %bb.20: + je .LBB2_99 +# %bb.22: cmp edi, 12 - jne .LBB2_165 -# %bb.21: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jne .LBB2_189 +# %bb.23: + mov r12, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero sub r9d, eax - je .LBB2_25 -# %bb.22: - movsxd rax, r9d + je .LBB2_29 +# %bb.24: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_27 +# %bb.25: + movsxd rsi, r9d + vmovq xmm0, r12 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_23: # =>This Inner Loop Header: Depth=1 - vucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] +.LBB2_26: # =>This Inner Loop Header: Depth=1 + vucomisd xmm0, qword ptr [rcx] + lea rdx, [rcx + 8] setnp cl sete bl and bl, cl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_23 -# %bb.24: + mov byte ptr [r14 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_26 +.LBB2_27: + sub r15, r8 + je .LBB2_189 +# %bb.28: add r14, 1 -.LBB2_25: - sar r11, 5 - cmp r10, 32 - jl .LBB2_29 -# %bb.26: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 192], r11 # 8-byte Spill - mov qword ptr [rsp + 184], r11 # 8-byte Spill +.LBB2_29: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_33 +# %bb.30: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 184], r12 # 8-byte Spill + vmovq xmm0, r12 + mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_27: # =>This Inner Loop Header: Depth=1 +.LBB2_31: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r14 # 8-byte Spill vucomisd xmm0, qword ptr [rdx] setnp al sete cl and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 8] setnp al sete r13b @@ -10604,7 +10964,7 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 24] setnp al sete cl @@ -10614,7 +10974,7 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 88], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 40] setnp al sete r12b @@ -10623,7 +10983,7 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 56] setnp al sete cl @@ -10633,17 +10993,17 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 72] setnp al sete cl and cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 80] setnp al sete cl and cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 88] setnp al sete bl @@ -10657,72 +11017,72 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 112] setnp al sete cl and cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 120] setnp al sete cl and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 128] setnp al sete cl and cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 136] setnp al sete cl and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 144] setnp al sete cl and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 136], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 152] setnp al sete cl and cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 160] setnp al sete cl and cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 168] setnp al sete cl and cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 176] setnp al sete r15b and r15b, al vucomisd xmm0, qword ptr [rdx + 184] setnp al - sete r8b - and r8b, al + sete r10b + and r10b, al vucomisd xmm0, qword ptr [rdx + 192] setnp al sete cl and cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 200] setnp al sete r11b and r11b, al vucomisd xmm0, qword ptr [rdx + 208] setnp al - sete r10b - and r10b, al - vucomisd xmm0, qword ptr [rdx + 216] - setnp al sete r9b and r9b, al + vucomisd xmm0, qword ptr [rdx + 216] + setnp al + sete r8b + and r8b, al vucomisd xmm0, qword ptr [rdx + 224] setnp al sete cl @@ -10742,23 +11102,23 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 sete sil and sil, al add r13b, r13b - add r13b, byte ptr [rsp + 56] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 72] # 1-byte Folded Reload mov eax, r13d shl r12b, 5 - movzx r13d, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload shl r13b, 6 or r13b, r12b - movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 80] # 1-byte Folded Reload shl r12b, 2 or r12b, al - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -10767,57 +11127,57 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 or al, r12b shl bl, 3 or bl, cl - movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 88] # 1-byte Folded Reload shl r13b, 4 or r13b, al movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, bl mov byte ptr [rsp + 288], al # 1-byte Spill - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload shl cl, 5 - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 6 or al, cl mov ecx, eax - movzx r14d, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx r14d, byte ptr [rsp + 96] # 1-byte Folded Reload shl r14b, 7 or r14b, al - movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload shl bl, 2 or bl, cl - movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload shl cl, 3 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 4 or cl, bl mov r12d, ecx mov rcx, qword ptr [rsp + 272] # 8-byte Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload or al, r13b - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 5 shl r15b, 6 or r15b, bl or r14b, byte ptr [rsp + 288] # 1-byte Folded Reload - shl r8b, 7 - or r8b, r15b - or r8b, r12b + shl r10b, 7 + or r10b, r15b + or r10b, r12b add r11b, r11b - add r11b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r10b, 2 - or r10b, r11b - shl r9b, 3 - or r9b, r10b + add r11b, byte ptr [rsp + 152] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 + or r8b, r9b movzx ebx, byte ptr [rsp + 168] # 1-byte Folded Reload shl bl, 4 - or bl, r9b - mov r9d, ebx + or bl, r8b + mov r8d, ebx mov byte ptr [rcx], al movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload shl bl, 5 @@ -10826,408 +11186,211 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 mov byte ptr [rcx + 1], r14b shl sil, 7 or sil, dil - or sil, r9b - mov byte ptr [rcx + 2], r8b + or sil, r8b + mov byte ptr [rcx + 2], r10b mov byte ptr [rcx + 3], sil add rdx, 256 add rcx, 4 mov r14, rcx - add qword ptr [rsp + 184], -1 # 8-byte Folded Spill - jne .LBB2_27 -# %bb.28: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 192] # 8-byte Reload -.LBB2_29: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 -# %bb.30: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB2_136 -# %bb.31: + add qword ptr [rsp + 192], -1 # 8-byte Folded Spill + jne .LBB2_31 +# %bb.32: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12, qword ptr [rsp + 184] # 8-byte Reload + mov rax, qword ptr [rsp + 200] # 8-byte Reload +.LBB2_33: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 +# %bb.34: + vmovq xmm0, r12 + or rax, 1 + cmp r15, rax + jne .LBB2_160 +# %bb.35: xor edi, edi - jmp .LBB2_138 -.LBB2_32: + jmp .LBB2_162 +.LBB2_36: cmp edi, 2 - je .LBB2_105 -# %bb.33: + je .LBB2_112 +# %bb.37: cmp edi, 3 - jne .LBB2_165 -# %bb.34: - mov r11b, byte ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jne .LBB2_189 +# %bb.38: + mov r12b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_38 -# %bb.35: - movsxd rax, r9d + je .LBB2_130 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_132 +# %bb.40: + movsxd rsi, r9d + mov r11, r8 + .p2align 4, 0x90 +.LBB2_41: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r12b, byte ptr [rdx] + sete dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r14 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB2_41 +# %bb.42: + sub r15, r8 + jne .LBB2_133 + jmp .LBB2_189 +.LBB2_43: + cmp edi, 7 + je .LBB2_117 +# %bb.44: + cmp edi, 8 + jne .LBB2_189 +# %bb.45: + mov r13, qword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB2_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_49 +# %bb.47: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_36: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx] - lea rdx, [rdx + 1] +.LBB2_48: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r13, qword ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 mov r12, r14 - movzx r9d, byte ptr [r14 + rsi] + movzx r9d, byte ptr [r14 + rdi] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_36 -# %bb.37: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_48 +.LBB2_49: + sub r15, r8 + je .LBB2_189 +# %bb.50: add r14, 1 -.LBB2_38: - sar r15, 5 - cmp r10, 32 - jl .LBB2_128 -# %bb.39: +.LBB2_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - mov dword ptr [rsp + 28], r11d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 392], r15 # 8-byte Spill - jb .LBB2_42 -# %bb.40: - mov rax, r15 - shl rax, 5 - add rax, rdx - cmp r14, rax - jae .LBB2_166 -# %bb.41: - lea rax, [r14 + 4*r15] - cmp rdx, rax - jae .LBB2_166 -.LBB2_42: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rdx - mov qword ptr [rsp + 376], r14 # 8-byte Spill -.LBB2_43: - sub r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 160], r15 # 8-byte Spill + jl .LBB2_55 +# %bb.52: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_44: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp r11b, byte ptr [r12] - sete byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r11b, byte ptr [r12 + 1] - sete r9b - cmp r11b, byte ptr [r12 + 2] - sete r11b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 3] - sete r13b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 4] - sete byte ptr [rsp + 48] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 5] +.LBB2_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill + cmp r13, qword ptr [rdx] + sete byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 8] + sete r10b + cmp r13, qword ptr [rdx + 16] + sete r14b + cmp r13, qword ptr [rdx + 24] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 32] + sete byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 40] sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 6] + cmp r13, qword ptr [rdx + 48] sete bl - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 7] - sete r12b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 8] - sete byte ptr [rsp + 136] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 9] - sete sil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 10] + cmp r13, qword ptr [rdx + 56] sete dil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 11] + cmp r13, qword ptr [rdx + 64] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 72] + sete sil + cmp r13, qword ptr [rdx + 80] sete r8b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 12] - sete r10b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 13] - sete r15b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 14] + cmp r13, qword ptr [rdx + 88] + sete r9b + cmp r13, qword ptr [rdx + 96] + sete r11b + cmp r13, qword ptr [rdx + 104] + sete r12b + cmp r13, qword ptr [rdx + 112] + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 120] + sete cl + cmp r13, qword ptr [rdx + 128] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 136] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 144] sete byte ptr [rsp + 144] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 15] - sete al - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 16] - sete byte ptr [rsp + 288] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 17] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 18] - sete byte ptr [rsp + 152] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 19] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 20] - sete byte ptr [rsp + 72] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 21] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 22] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 23] - sete r14b - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 24] - sete byte ptr [rsp + 272] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 25] - sete byte ptr [rsp + 104] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 26] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 27] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 28] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 29] - sete byte ptr [rsp + 56] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 30] - sete byte ptr [rsp + 32] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 28] # 4-byte Reload - cmp dl, byte ptr [rcx + 31] - sete dl - add r9b, r9b - add r9b, byte ptr [rsp + 320] # 1-byte Folded Reload - shl bl, 6 - shl r12b, 7 - or r12b, bl - shl r11b, 2 - or r11b, r9b - add sil, sil - add sil, byte ptr [rsp + 136] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r11b - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - shl dil, 2 - or dil, sil - movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl bl, 4 - or bl, r13b - mov esi, ebx - shl r8b, 3 - or r8b, dil - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r10b, 4 - or r10b, r8b - shl r15b, 5 - or r15b, r10b - movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload - shl sil, 6 - shl al, 7 - or al, sil - or r12b, bl - or al, r15b - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 288] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl bl, 2 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - mov rsi, qword ptr [rsp + 376] # 8-byte Reload - mov byte ptr [rsi], r12b - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], al - or r14b, bl - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 272] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, al - mov byte ptr [rsi + 2], r14b - mov byte ptr [rsi + 3], dl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 376], rsi # 8-byte Spill - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB2_44 -# %bb.45: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 392] # 8-byte Reload - jmp .LBB2_129 -.LBB2_46: - cmp edi, 7 - je .LBB2_117 -# %bb.47: - cmp edi, 8 - jne .LBB2_165 -# %bb.48: - mov r13, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB2_52 -# %bb.49: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB2_50: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] - lea rdx, [rdx + 8] - sete bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_50 -# %bb.51: - add r14, 1 -.LBB2_52: - sar r11, 5 - cmp r10, 32 - jl .LBB2_56 -# %bb.53: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB2_54: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r14 # 8-byte Spill - cmp r13, qword ptr [rdx] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 8] - sete r10b - cmp r13, qword ptr [rdx + 16] - sete r14b - cmp r13, qword ptr [rdx + 24] - sete byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 32] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 40] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 48] - sete bl - cmp r13, qword ptr [rdx + 56] - sete dil - cmp r13, qword ptr [rdx + 64] - sete byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 72] - sete sil - cmp r13, qword ptr [rdx + 80] - sete r8b - cmp r13, qword ptr [rdx + 88] - sete r9b - cmp r13, qword ptr [rdx + 96] - sete r11b - cmp r13, qword ptr [rdx + 104] - sete r12b - cmp r13, qword ptr [rdx + 112] - sete byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 120] - sete al - cmp r13, qword ptr [rdx + 128] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 136] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 144] - sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 152] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 160] sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 160] + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 168] - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 176] - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 184] sete r15b cmp r13, qword ptr [rdx + 192] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 200] - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 208] - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 216] - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 224] sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 232] @@ -11235,117 +11398,116 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13, qword ptr [rdx + 240] sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 248] - sete cl + sete al add r10b, r10b - add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload shl bl, 6 shl dil, 7 or dil, bl shl r14b, 2 or r14b, r10b add sil, sil - add sil, byte ptr [rsp + 144] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 3 or bl, r14b mov r10d, ebx mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, sil - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload shl bl, 4 or bl, r10b mov esi, ebx shl r9b, 3 or r9b, r8b - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 5 or bl, sil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx esi, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload shl sil, 6 - shl al, 7 - or al, sil + shl cl, 7 + or cl, sil or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + or cl, r12b + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 96] # 1-byte Folded Reload + add bl, byte ptr [rsp + 112] # 1-byte Folded Reload mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 2 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 5 or bl, sil mov byte ptr [r14], dil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], al + mov byte ptr [r14 + 1], cl or r15b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 5 - or al, bl + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov ebx, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 2 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 5 + or cl, bl movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al + shl al, 7 + or al, bl + or al, cl mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], cl + mov byte ptr [r14 + 3], al add rdx, 256 add r14, 4 add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB2_54 -# %bb.55: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 168] # 8-byte Reload -.LBB2_56: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 + jne .LBB2_53 +# %bb.54: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 168] # 8-byte Reload +.LBB2_55: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 +# %bb.56: + or rax, 1 + cmp r15, rax + je .LBB2_98 # %bb.57: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB2_93 -# %bb.58: mov r10, r8 and r10, -2 xor edi, edi .p2align 4, 0x90 -.LBB2_59: # =>This Inner Loop Header: Depth=1 +.LBB2_58: # =>This Inner Loop Header: Depth=1 cmp r13, qword ptr [rdx] sete al neg al @@ -11374,61 +11536,74 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor al, bl mov byte ptr [r14 + rsi], al cmp r10, rdi - jne .LBB2_59 - jmp .LBB2_146 -.LBB2_60: + jne .LBB2_58 + jmp .LBB2_170 +.LBB2_59: movzx r13d, word ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_64 + je .LBB2_65 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_63 # %bb.61: - movsxd rax, r9d + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 .LBB2_62: # =>This Inner Loop Header: Depth=1 - cmp r13w, word ptr [rdx] - lea rdx, [rdx + 2] + lea rdx, [rcx + 2] + cmp r13w, word ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 jne .LBB2_62 -# %bb.63: +.LBB2_63: + sub r15, r8 + je .LBB2_189 +# %bb.64: add r14, 1 -.LBB2_64: - sar r11, 5 - cmp r10, 32 - jl .LBB2_68 -# %bb.65: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill +.LBB2_65: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_69 +# %bb.66: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_66: # =>This Inner Loop Header: Depth=1 +.LBB2_67: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp r13w, word ptr [rdx] - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 2] sete r10b cmp r13w, word ptr [rdx + 4] @@ -11436,15 +11611,15 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13w, word ptr [rdx + 6] sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 8] - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 10] - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 12] sete bl cmp r13w, word ptr [rdx + 14] sete dil cmp r13w, word ptr [rdx + 16] - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 18] sete sil cmp r13w, word ptr [rdx + 20] @@ -11456,33 +11631,33 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13w, word ptr [rdx + 26] sete r12b cmp r13w, word ptr [rdx + 28] - sete byte ptr [rsp + 136] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 30] - sete al + sete cl cmp r13w, word ptr [rdx + 32] - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 34] - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 136] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 36] - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 38] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 40] sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 40] + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 42] - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 44] - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 46] sete r15b cmp r13w, word ptr [rdx + 48] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 50] - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 52] - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 54] - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 56] sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 58] @@ -11490,16 +11665,16 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13w, word ptr [rdx + 60] sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 62] - sete cl + sete al add r10b, r10b - add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload shl bl, 6 shl dil, 7 or dil, bl shl r14b, 2 or r14b, r10b add sil, sil - add sil, byte ptr [rsp + 152] # 1-byte Folded Reload + add sil, byte ptr [rsp + 128] # 1-byte Folded Reload movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 3 or bl, r14b @@ -11507,100 +11682,99 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, sil - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload shl bl, 4 or bl, r10b mov esi, ebx shl r9b, 3 or r9b, r8b - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 5 or bl, sil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx esi, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 120] # 1-byte Folded Reload shl sil, 6 - shl al, 7 - or al, sil + shl cl, 7 + or cl, sil or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + or cl, r12b + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 96] # 1-byte Folded Reload + add bl, byte ptr [rsp + 112] # 1-byte Folded Reload mov esi, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 2 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 5 or bl, sil mov byte ptr [r14], dil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], al + mov byte ptr [r14 + 1], cl or r15b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 5 - or al, bl + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov ebx, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 2 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 5 + or cl, bl movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al + shl al, 7 + or al, bl + or al, cl mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], cl + mov byte ptr [r14 + 3], al add rdx, 64 add r14, 4 add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB2_66 -# %bb.67: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 168] # 8-byte Reload -.LBB2_68: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 -# %bb.69: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB2_82 + jne .LBB2_67 +# %bb.68: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 168] # 8-byte Reload +.LBB2_69: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 # %bb.70: + or rax, 1 + cmp r15, rax + je .LBB2_85 +# %bb.71: mov r10, r8 and r10, -2 xor edi, edi .p2align 4, 0x90 -.LBB2_71: # =>This Inner Loop Header: Depth=1 +.LBB2_72: # =>This Inner Loop Header: Depth=1 cmp r13w, word ptr [rdx] sete al neg al @@ -11629,77 +11803,90 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor al, bl mov byte ptr [r14 + rsi], al cmp r10, rdi - jne .LBB2_71 - jmp .LBB2_142 -.LBB2_72: + jne .LBB2_72 + jmp .LBB2_166 +.LBB2_73: movzx r13d, word ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_76 -# %bb.73: - movsxd rax, r9d + je .LBB2_79 +# %bb.74: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_77 +# %bb.75: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_74: # =>This Inner Loop Header: Depth=1 - cmp r13w, word ptr [rdx] - lea rdx, [rdx + 2] +.LBB2_76: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r13w, word ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_74 -# %bb.75: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_76 +.LBB2_77: + sub r15, r8 + je .LBB2_189 +# %bb.78: add r14, 1 -.LBB2_76: - sar r11, 5 - cmp r10, 32 - jl .LBB2_80 -# %bb.77: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill +.LBB2_79: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_83 +# %bb.80: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_78: # =>This Inner Loop Header: Depth=1 +.LBB2_81: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp r13w, word ptr [rdx] - sete byte ptr [rsp + 160] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 2] sete r10b cmp r13w, word ptr [rdx + 4] sete r14b cmp r13w, word ptr [rdx + 6] - sete byte ptr [rsp + 136] # 1-byte Folded Spill + sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 8] - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 10] - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 12] sete bl cmp r13w, word ptr [rdx + 14] sete dil cmp r13w, word ptr [rdx + 16] - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 18] sete sil cmp r13w, word ptr [rdx + 20] @@ -11711,33 +11898,33 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13w, word ptr [rdx + 26] sete r12b cmp r13w, word ptr [rdx + 28] - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 30] - sete al + sete cl cmp r13w, word ptr [rdx + 32] - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 34] - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 136] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 36] - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 38] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 40] sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 42] - sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 40] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 42] + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 44] - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 46] sete r15b cmp r13w, word ptr [rdx + 48] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 50] - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 52] - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 54] - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 56] sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 58] @@ -11745,183 +11932,195 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13w, word ptr [rdx + 60] sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 62] - sete cl + sete al add r10b, r10b - add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload shl bl, 6 shl dil, 7 or dil, bl shl r14b, 2 or r14b, r10b add sil, sil - add sil, byte ptr [rsp + 144] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 3 or bl, r14b mov r10d, ebx mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, sil - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload shl bl, 4 or bl, r10b mov esi, ebx shl r9b, 3 or r9b, r8b - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 5 or bl, sil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx esi, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload shl sil, 6 - shl al, 7 - or al, sil + shl cl, 7 + or cl, sil or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + or cl, r12b + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 96] # 1-byte Folded Reload + add bl, byte ptr [rsp + 112] # 1-byte Folded Reload mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 2 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 5 or bl, sil mov byte ptr [r14], dil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], al + mov byte ptr [r14 + 1], cl or r15b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 5 - or al, bl + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov ebx, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 2 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 5 + or cl, bl movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al + shl al, 7 + or al, bl + or al, cl mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], cl + mov byte ptr [r14 + 3], al add rdx, 64 add r14, 4 add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB2_78 -# %bb.79: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 168] # 8-byte Reload -.LBB2_80: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 -# %bb.81: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB2_140 -.LBB2_82: - xor edi, edi - jmp .LBB2_142 + jne .LBB2_81 +# %bb.82: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 168] # 8-byte Reload .LBB2_83: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 +# %bb.84: + or rax, 1 + cmp r15, rax + jne .LBB2_164 +.LBB2_85: + xor edi, edi + jmp .LBB2_166 +.LBB2_86: mov r13, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_87 -# %bb.84: - movsxd rax, r9d + je .LBB2_92 +# %bb.87: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_90 +# %bb.88: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_85: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] - lea rdx, [rdx + 8] +.LBB2_89: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r13, qword ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_85 -# %bb.86: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_89 +.LBB2_90: + sub r15, r8 + je .LBB2_189 +# %bb.91: add r14, 1 -.LBB2_87: - sar r11, 5 - cmp r10, 32 - jl .LBB2_91 -# %bb.88: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill +.LBB2_92: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_96 +# %bb.93: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_89: # =>This Inner Loop Header: Depth=1 +.LBB2_94: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp r13, qword ptr [rdx] - sete byte ptr [rsp + 160] # 1-byte Folded Spill + sete byte ptr [rsp + 152] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 8] sete r10b cmp r13, qword ptr [rdx + 16] sete r14b cmp r13, qword ptr [rdx + 24] - sete byte ptr [rsp + 136] # 1-byte Folded Spill + sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 32] - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 40] - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 48] sete bl cmp r13, qword ptr [rdx + 56] sete dil cmp r13, qword ptr [rdx + 64] - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 72] sete sil cmp r13, qword ptr [rdx + 80] @@ -11933,33 +12132,33 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13, qword ptr [rdx + 104] sete r12b cmp r13, qword ptr [rdx + 112] - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 120] - sete al + sete cl cmp r13, qword ptr [rdx + 128] - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 136] - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 136] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 144] - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 152] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 160] sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 160] + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 168] - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 176] - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 184] sete r15b cmp r13, qword ptr [rdx + 192] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 200] - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 208] - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 216] - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 224] sete byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 232] @@ -11967,172 +12166,187 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 cmp r13, qword ptr [rdx + 240] sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 248] - sete cl + sete al add r10b, r10b - add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload shl bl, 6 shl dil, 7 or dil, bl shl r14b, 2 or r14b, r10b add sil, sil - add sil, byte ptr [rsp + 144] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 3 or bl, r14b mov r10d, ebx mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, sil - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload shl bl, 4 or bl, r10b mov esi, ebx shl r9b, 3 or r9b, r8b - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 5 or bl, sil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx esi, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload shl sil, 6 - shl al, 7 - or al, sil + shl cl, 7 + or cl, sil or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + or cl, r12b + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 96] # 1-byte Folded Reload + add bl, byte ptr [rsp + 112] # 1-byte Folded Reload mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 2 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 5 or bl, sil mov byte ptr [r14], dil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], al + mov byte ptr [r14 + 1], cl or r15b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 5 - or al, bl + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov ebx, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 2 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 5 + or cl, bl movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al + shl al, 7 + or al, bl + or al, cl mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], cl + mov byte ptr [r14 + 3], al add rdx, 256 add r14, 4 add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB2_89 -# %bb.90: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 168] # 8-byte Reload -.LBB2_91: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 -# %bb.92: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB2_144 -.LBB2_93: + jne .LBB2_94 +# %bb.95: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 168] # 8-byte Reload +.LBB2_96: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 +# %bb.97: + or rax, 1 + cmp r15, rax + jne .LBB2_168 +.LBB2_98: xor edi, edi - jmp .LBB2_146 -.LBB2_94: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jmp .LBB2_170 +.LBB2_99: + mov r12d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB2_98 -# %bb.95: - movsxd rax, r9d + je .LBB2_105 +# %bb.100: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_103 +# %bb.101: + movsxd rsi, r9d + vmovd xmm0, r12d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_96: # =>This Inner Loop Header: Depth=1 - vucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] +.LBB2_102: # =>This Inner Loop Header: Depth=1 + vucomiss xmm0, dword ptr [rcx] + lea rdx, [rcx + 4] setnp cl sete bl and bl, cl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_96 -# %bb.97: + mov byte ptr [r14 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_102 +.LBB2_103: + sub r15, r8 + je .LBB2_189 +# %bb.104: add r14, 1 -.LBB2_98: - sar r11, 5 - cmp r10, 32 - jl .LBB2_102 -# %bb.99: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 184], r11 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill +.LBB2_105: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_109 +# %bb.106: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov dword ptr [rsp + 192], r12d # 4-byte Spill + vmovd xmm0, r12d + mov qword ptr [rsp + 184], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_100: # =>This Inner Loop Header: Depth=1 +.LBB2_107: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r14 # 8-byte Spill vucomiss xmm0, dword ptr [rdx] setnp al sete cl and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 4] setnp al sete r13b @@ -12141,7 +12355,7 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 12] setnp al sete cl @@ -12151,7 +12365,7 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 88], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 20] setnp al sete r12b @@ -12160,7 +12374,7 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 28] setnp al sete cl @@ -12170,17 +12384,17 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 36] setnp al sete cl and cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 40] setnp al sete cl and cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 44] setnp al sete bl @@ -12194,32 +12408,32 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 56] setnp al sete cl and cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 60] setnp al sete cl and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 68] setnp al sete cl and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 72] setnp al sete cl and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 136], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 76] setnp al sete r14b @@ -12228,42 +12442,42 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 setnp al sete cl and cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 84] setnp al sete cl and cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 88] setnp al sete r15b and r15b, al vucomiss xmm0, dword ptr [rdx + 92] setnp al - sete r8b - and r8b, al + sete r10b + and r10b, al vucomiss xmm0, dword ptr [rdx + 96] setnp al sete cl and cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 100] setnp al sete r11b and r11b, al vucomiss xmm0, dword ptr [rdx + 104] setnp al - sete r10b - and r10b, al - vucomiss xmm0, dword ptr [rdx + 108] - setnp al sete r9b and r9b, al + vucomiss xmm0, dword ptr [rdx + 108] + setnp al + sete r8b + and r8b, al vucomiss xmm0, dword ptr [rdx + 112] setnp al sete cl and cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 116] setnp al sete cl @@ -12278,23 +12492,23 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 sete sil and sil, al add r13b, r13b - add r13b, byte ptr [rsp + 56] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 72] # 1-byte Folded Reload mov eax, r13d shl r12b, 5 - movzx r13d, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload shl r13b, 6 or r13b, r12b - movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 80] # 1-byte Folded Reload shl r12b, 2 or r12b, al - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -12303,53 +12517,53 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 or al, r12b shl bl, 3 or bl, cl - movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 88] # 1-byte Folded Reload shl r13b, 4 or r13b, al movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, bl mov byte ptr [rsp + 288], al # 1-byte Spill - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload shl cl, 5 - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 6 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 7 or al, cl - movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload shl bl, 2 or bl, cl shl r14b, 3 or r14b, bl - movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload shl cl, 4 or cl, r14b mov r14, qword ptr [rsp + 272] # 8-byte Reload movzx r12d, byte ptr [rsp + 28] # 1-byte Folded Reload or r12b, r13b - movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload shl bl, 5 shl r15b, 6 or r15b, bl or al, byte ptr [rsp + 288] # 1-byte Folded Reload - shl r8b, 7 - or r8b, r15b - or r8b, cl + shl r10b, 7 + or r10b, r15b + or r10b, cl add r11b, r11b - add r11b, byte ptr [rsp + 136] # 1-byte Folded Reload - shl r10b, 2 - or r10b, r11b - shl r9b, 3 - or r9b, r10b - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 + or r8b, r9b + movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload shl cl, 4 - or cl, r9b + or cl, r8b mov byte ptr [r14], r12b movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload shl bl, 5 @@ -12359,141 +12573,398 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 shl sil, 7 or sil, dil or sil, cl - mov byte ptr [r14 + 2], r8b + mov byte ptr [r14 + 2], r10b mov byte ptr [r14 + 3], sil add rdx, 128 add r14, 4 add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB2_100 -# %bb.101: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 184] # 8-byte Reload -.LBB2_102: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 -# %bb.103: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB2_148 -# %bb.104: + jne .LBB2_107 +# %bb.108: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 192] # 4-byte Reload + mov rax, qword ptr [rsp + 184] # 8-byte Reload +.LBB2_109: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 +# %bb.110: + vmovd xmm0, r12d + or rax, 1 + cmp r15, rax + jne .LBB2_172 +# %bb.111: xor edi, edi - jmp .LBB2_150 -.LBB2_105: - mov r11b, byte ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jmp .LBB2_174 +.LBB2_112: + mov r12b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_109 -# %bb.106: - movsxd rax, r9d + je .LBB2_131 +# %bb.113: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_146 +# %bb.114: + movsxd rsi, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB2_107: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx] - lea rdx, [rdx + 1] +.LBB2_115: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r12b, byte ptr [rdx] + sete dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r14 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB2_115 +# %bb.116: + sub r15, r8 + jne .LBB2_147 + jmp .LBB2_189 +.LBB2_117: + mov r13d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB2_123 +# %bb.118: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_121 +# %bb.119: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx + .p2align 4, 0x90 +.LBB2_120: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r13d, dword ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 mov r12, r14 - movzx r9d, byte ptr [r14 + rsi] + movzx r9d, byte ptr [r14 + rdi] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_107 -# %bb.108: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_120 +.LBB2_121: + sub r15, r8 + je .LBB2_189 +# %bb.122: add r14, 1 -.LBB2_109: - sar r15, 5 - cmp r10, 32 - jl .LBB2_132 -# %bb.110: +.LBB2_123: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - mov dword ptr [rsp + 28], r11d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 392], r15 # 8-byte Spill - jb .LBB2_113 -# %bb.111: - mov rax, r15 - shl rax, 5 - add rax, rdx - cmp r14, rax - jae .LBB2_169 -# %bb.112: - lea rax, [r14 + 4*r15] - cmp rdx, rax - jae .LBB2_169 -.LBB2_113: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rdx - mov qword ptr [rsp + 376], r14 # 8-byte Spill -.LBB2_114: - sub r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 160], r15 # 8-byte Spill + jl .LBB2_127 +# %bb.124: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_115: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp r11b, byte ptr [r12] - sete byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r11b, byte ptr [r12 + 1] - sete r9b - cmp r11b, byte ptr [r12 + 2] - sete r11b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 3] - sete r13b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 4] - sete byte ptr [rsp + 48] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 5] +.LBB2_125: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill + cmp r13d, dword ptr [rdx] + sete byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 4] + sete r10b + cmp r13d, dword ptr [rdx + 8] + sete r14b + cmp r13d, dword ptr [rdx + 12] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 16] + sete byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 20] sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 6] + cmp r13d, dword ptr [rdx + 24] sete bl - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [r12 + 7] - sete r12b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 8] - sete byte ptr [rsp + 136] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 9] - sete sil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 10] + cmp r13d, dword ptr [rdx + 28] sete dil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 11] + cmp r13d, dword ptr [rdx + 32] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 36] + sete sil + cmp r13d, dword ptr [rdx + 40] sete r8b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 12] - sete r10b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rcx + 13] + cmp r13d, dword ptr [rdx + 44] + sete r9b + cmp r13d, dword ptr [rdx + 48] + sete r11b + cmp r13d, dword ptr [rdx + 52] + sete r12b + cmp r13d, dword ptr [rdx + 56] + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 60] + sete cl + cmp r13d, dword ptr [rdx + 64] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 68] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 72] + sete byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 76] + sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 80] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 84] + sete byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 88] + sete byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 92] + sete r15b + cmp r13d, dword ptr [rdx + 96] + sete byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 100] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 104] + sete byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 108] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 112] + sete byte ptr [rsp + 320] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 116] + sete byte ptr [rsp + 288] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 120] + sete byte ptr [rsp + 28] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 124] + sete al + add r10b, r10b + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + shl bl, 6 + shl dil, 7 + or dil, bl + shl r14b, 2 + or r14b, r10b + add sil, sil + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl bl, 3 + or bl, r14b + mov r10d, ebx + mov r14, qword ptr [rsp + 272] # 8-byte Reload + shl r8b, 2 + or r8b, sil + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl bl, 4 + or bl, r10b + mov esi, ebx + shl r9b, 3 + or r9b, r8b + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl bl, 5 + or bl, sil + shl r11b, 4 + or r11b, r9b + shl r12b, 5 + or r12b, r11b + movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + shl sil, 6 + shl cl, 7 + or cl, sil + or dil, bl + or cl, r12b + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 112] # 1-byte Folded Reload + mov esi, ebx + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl bl, 2 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl bl, 3 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl bl, 4 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl bl, 5 + or bl, sil + mov byte ptr [r14], dil + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [r14 + 1], cl + or r15b, bl + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov ebx, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 2 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 5 + or cl, bl + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl bl, 6 + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], al + add rdx, 128 + add r14, 4 + add qword ptr [rsp + 176], -1 # 8-byte Folded Spill + jne .LBB2_125 +# %bb.126: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 168] # 8-byte Reload +.LBB2_127: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_189 +# %bb.128: + or rax, 1 + cmp r15, rax + jne .LBB2_177 +.LBB2_129: + xor edi, edi + jmp .LBB2_179 +.LBB2_130: + mov rdi, rdx + jmp .LBB2_134 +.LBB2_131: + mov rdi, rdx + jmp .LBB2_148 +.LBB2_132: + mov rdi, rdx + sub r15, r8 + je .LBB2_189 +.LBB2_133: + add r14, 1 +.LBB2_134: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB2_142 +# %bb.135: + cmp rcx, 32 + mov dword ptr [rsp + 28], r12d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 392], rcx # 8-byte Spill + jb .LBB2_138 +# %bb.136: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB2_190 +# %bb.137: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB2_190 +.LBB2_138: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 376], r14 # 8-byte Spill +.LBB2_139: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 152], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB2_140: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp r12b, byte ptr [rsi] + sete byte ptr [rsp + 320] # 1-byte Folded Spill + cmp r12b, byte ptr [rsi + 1] + sete r9b + cmp r12b, byte ptr [rsi + 2] + sete r11b + cmp r12b, byte ptr [rsi + 3] + sete r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 4] + sete byte ptr [rsp + 48] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 5] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 6] + sete bl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 7] + sete r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 8] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 9] + sete sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 10] + sete dil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 11] + sete r8b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 12] + sete r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 13] sete r15b mov eax, dword ptr [rsp + 28] # 4-byte Reload cmp al, byte ptr [rcx + 14] - sete byte ptr [rsp + 144] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill mov eax, dword ptr [rsp + 28] # 4-byte Reload cmp al, byte ptr [rcx + 15] sete al @@ -12502,22 +12973,22 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 sete byte ptr [rsp + 288] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 17] - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 18] - sete byte ptr [rsp + 152] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 19] - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 136] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 20] - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 21] - sete byte ptr [rsp + 88] # 1-byte Folded Spill + sete byte ptr [rsp + 144] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 22] - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 23] sete r14b @@ -12526,22 +12997,22 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 sete byte ptr [rsp + 272] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 25] - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 26] - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 27] - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 28] - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 29] - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 30] - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill mov edx, dword ptr [rsp + 28] # 4-byte Reload cmp dl, byte ptr [rcx + 31] sete dl @@ -12553,351 +13024,130 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 shl r11b, 2 or r11b, r9b add sil, sil - add sil, byte ptr [rsp + 136] # 1-byte Folded Reload + add sil, byte ptr [rsp + 160] # 1-byte Folded Reload shl r13b, 3 or r13b, r11b - mov r11d, dword ptr [rsp + 28] # 4-byte Reload shl dil, 2 or dil, sil movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 4 or bl, r13b - mov esi, ebx + mov r9d, ebx + mov esi, dword ptr [rsp + 28] # 4-byte Reload shl r8b, 3 or r8b, dil - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 5 - or bl, sil + or bl, r9b shl r10b, 4 or r10b, r8b shl r15b, 5 or r15b, r10b - movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload - shl sil, 6 + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 6 shl al, 7 - or al, sil + or al, dil or r12b, bl or al, r15b - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload add bl, bl add bl, byte ptr [rsp + 288] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 152] # 1-byte Folded Reload + mov edi, ebx + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 2 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + or bl, dil + mov edi, ebx + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + or bl, dil + mov edi, ebx + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + or bl, dil + mov edi, ebx + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 5 - or bl, sil - mov rsi, qword ptr [rsp + 376] # 8-byte Reload - mov byte ptr [rsi], r12b - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dil, 6 + or bl, dil + mov rdi, qword ptr [rsp + 376] # 8-byte Reload + mov byte ptr [rdi], r12b + mov r12d, esi + movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + shl sil, 6 shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], al + or r14b, sil + mov byte ptr [rdi + 1], al or r14b, bl - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 272] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload shl bl, 6 shl dl, 7 or dl, bl or dl, al - mov byte ptr [rsi + 2], r14b - mov byte ptr [rsi + 3], dl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 376], rsi # 8-byte Spill - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB2_115 -# %bb.116: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 392] # 8-byte Reload - jmp .LBB2_133 -.LBB2_117: - mov r13d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB2_121 -# %bb.118: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB2_119: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - lea rdx, [rdx + 4] - sete bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_119 -# %bb.120: - add r14, 1 -.LBB2_121: - sar r11, 5 - cmp r10, 32 - jl .LBB2_125 -# %bb.122: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB2_123: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r14 # 8-byte Spill - cmp r13d, dword ptr [rdx] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 4] - sete r10b - cmp r13d, dword ptr [rdx + 8] - sete r14b - cmp r13d, dword ptr [rdx + 12] - sete byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 16] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 20] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 24] - sete bl - cmp r13d, dword ptr [rdx + 28] - sete dil - cmp r13d, dword ptr [rdx + 32] - sete byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 36] - sete sil - cmp r13d, dword ptr [rdx + 40] - sete r8b - cmp r13d, dword ptr [rdx + 44] - sete r9b - cmp r13d, dword ptr [rdx + 48] - sete r11b - cmp r13d, dword ptr [rdx + 52] - sete r12b - cmp r13d, dword ptr [rdx + 56] - sete byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 60] - sete al - cmp r13d, dword ptr [rdx + 64] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 68] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 72] - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 76] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 80] - sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 84] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 88] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 92] - sete r15b - cmp r13d, dword ptr [rdx + 96] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 100] - sete byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 104] - sete byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 108] - sete byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 112] - sete byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 116] - sete byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 120] - sete byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 124] - sete cl - add r10b, r10b - add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 6 - shl dil, 7 - or dil, bl - shl r14b, 2 - or r14b, r10b - add sil, sil - add sil, byte ptr [rsp + 144] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl bl, 3 - or bl, r14b - mov r10d, ebx - mov r14, qword ptr [rsp + 272] # 8-byte Reload - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, r10b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r11b, 4 - or r11b, r9b - shl r12b, 5 - or r12b, r11b - movzx esi, byte ptr [rsp + 152] # 1-byte Folded Reload - shl sil, 6 - shl al, 7 - or al, sil - or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 96] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 2 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - mov byte ptr [r14], dil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload - shl sil, 6 - shl r15b, 7 - or r15b, sil - mov byte ptr [r14 + 1], al - or r15b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], cl - add rdx, 128 - add r14, 4 - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB2_123 -# %bb.124: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 168] # 8-byte Reload -.LBB2_125: - shl r11, 5 - cmp r11, r10 - jge .LBB2_165 -# %bb.126: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB2_153 -.LBB2_127: - xor edi, edi - jmp .LBB2_155 -.LBB2_128: + mov byte ptr [rdi + 2], r14b + mov byte ptr [rdi + 3], dl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 376], rdi # 8-byte Spill + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB2_140 +# %bb.141: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + jmp .LBB2_143 +.LBB2_142: mov qword ptr [rsp + 376], r14 # 8-byte Spill - mov r12, rdx -.LBB2_129: - shl r15, 5 - cmp r15, r10 - jge .LBB2_165 -# %bb.130: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB2_135 -# %bb.158: + mov rsi, rdi +.LBB2_143: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB2_189 +# %bb.144: + or rcx, 1 + cmp r15, rcx + je .LBB2_159 +# %bb.182: mov r10, r8 and r10, -2 - xor esi, esi - mov r14, qword ptr [rsp + 376] # 8-byte Reload + xor r9d, r9d + mov r11, qword ptr [rsp + 376] # 8-byte Reload .p2align 4, 0x90 -.LBB2_159: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [r12 + rsi] +.LBB2_183: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r12b, byte ptr [rsi + r9] sete bl neg bl - mov rdi, rsi + mov rdi, r9 shr rdi, 3 - mov ecx, esi + mov ecx, eax and cl, 6 mov dl, 1 shl dl, cl - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r11 + rdi] xor bl, r9b and dl, bl xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp r11b, byte ptr [r12 + rsi + 1] - lea rsi, [rsi + 2] + mov byte ptr [r11 + rdi], dl + cmp r12b, byte ptr [rsi + rax + 1] + lea r9, [rax + 2] sete bl neg bl xor bl, dl @@ -12906,32 +13156,259 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 shl al, cl and al, bl xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, rsi - jne .LBB2_159 - jmp .LBB2_162 -.LBB2_132: + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB2_183 + jmp .LBB2_186 +.LBB2_146: + mov rdi, rdx + sub r15, r8 + je .LBB2_189 +.LBB2_147: + add r14, 1 +.LBB2_148: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB2_156 +# %bb.149: + cmp rcx, 32 + mov dword ptr [rsp + 28], r12d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 392], rcx # 8-byte Spill + jb .LBB2_152 +# %bb.150: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB2_193 +# %bb.151: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB2_193 +.LBB2_152: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi mov qword ptr [rsp + 376], r14 # 8-byte Spill - mov r12, rdx -.LBB2_133: - shl r15, 5 - cmp r15, r10 - jge .LBB2_165 -# %bb.134: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB2_160 -.LBB2_135: - xor esi, esi - jmp .LBB2_163 -.LBB2_136: - mov r9, r8 - and r9, -2 - xor edi, edi +.LBB2_153: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 152], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB2_154: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp r12b, byte ptr [rsi] + sete byte ptr [rsp + 320] # 1-byte Folded Spill + cmp r12b, byte ptr [rsi + 1] + sete r9b + cmp r12b, byte ptr [rsi + 2] + sete r11b + cmp r12b, byte ptr [rsi + 3] + sete r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 4] + sete byte ptr [rsp + 48] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 5] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 6] + sete bl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 7] + sete r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 8] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rsi + 9] + sete sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 10] + sete dil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 11] + sete r8b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 12] + sete r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 13] + sete r15b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 14] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rcx + 15] + sete al + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 16] + sete byte ptr [rsp + 288] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 17] + sete byte ptr [rsp + 104] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 18] + sete byte ptr [rsp + 128] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 19] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 20] + sete byte ptr [rsp + 96] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 21] + sete byte ptr [rsp + 144] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 22] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 23] + sete r14b + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 24] + sete byte ptr [rsp + 272] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 25] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 26] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 27] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 28] + sete byte ptr [rsp + 56] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 29] + sete byte ptr [rsp + 72] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 30] + sete byte ptr [rsp + 88] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 28] # 4-byte Reload + cmp dl, byte ptr [rcx + 31] + sete dl + add r9b, r9b + add r9b, byte ptr [rsp + 320] # 1-byte Folded Reload + shl bl, 6 + shl r12b, 7 + or r12b, bl + shl r11b, 2 + or r11b, r9b + add sil, sil + add sil, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r11b + shl dil, 2 + or dil, sil + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl bl, 4 + or bl, r13b + mov r9d, ebx + mov esi, dword ptr [rsp + 28] # 4-byte Reload + shl r8b, 3 + or r8b, dil + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl bl, 5 + or bl, r9b + shl r10b, 4 + or r10b, r8b + shl r15b, 5 + or r15b, r10b + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 6 + shl al, 7 + or al, dil + or r12b, bl + or al, r15b + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 288] # 1-byte Folded Reload + mov edi, ebx + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 2 + or bl, dil + mov edi, ebx + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl bl, 3 + or bl, dil + mov edi, ebx + movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl bl, 4 + or bl, dil + mov edi, ebx + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl bl, 5 + or bl, dil + mov rdi, qword ptr [rsp + 376] # 8-byte Reload + mov byte ptr [rdi], r12b + mov r12d, esi + movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + shl sil, 6 + shl r14b, 7 + or r14b, sil + mov byte ptr [rdi + 1], al + or r14b, bl + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 272] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rdi + 2], r14b + mov byte ptr [rdi + 3], dl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 376], rdi # 8-byte Spill + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB2_154 +# %bb.155: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + jmp .LBB2_157 +.LBB2_156: + mov qword ptr [rsp + 376], r14 # 8-byte Spill + mov rsi, rdi +.LBB2_157: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB2_189 +# %bb.158: + or rcx, 1 + cmp r15, rcx + jne .LBB2_184 +.LBB2_159: + xor r9d, r9d + jmp .LBB2_187 +.LBB2_160: + mov r9, r8 + and r9, -2 + xor edi, edi .p2align 4, 0x90 -.LBB2_137: # =>This Inner Loop Header: Depth=1 +.LBB2_161: # =>This Inner Loop Header: Depth=1 vucomisd xmm0, qword ptr [rdx] setnp cl sete al @@ -12964,19 +13441,19 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor bl, r11b mov byte ptr [r14 + rsi], bl cmp r9, rdi - jne .LBB2_137 -.LBB2_138: + jne .LBB2_161 +.LBB2_162: test r8b, 1 - je .LBB2_165 -# %bb.139: + je .LBB2_189 +# %bb.163: vucomisd xmm0, qword ptr [rdx] - jmp .LBB2_152 -.LBB2_140: + jmp .LBB2_176 +.LBB2_164: mov r10, r8 and r10, -2 xor edi, edi .p2align 4, 0x90 -.LBB2_141: # =>This Inner Loop Header: Depth=1 +.LBB2_165: # =>This Inner Loop Header: Depth=1 cmp r13w, word ptr [rdx] sete al neg al @@ -13005,19 +13482,19 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor al, bl mov byte ptr [r14 + rsi], al cmp r10, rdi - jne .LBB2_141 -.LBB2_142: + jne .LBB2_165 +.LBB2_166: test r8b, 1 - je .LBB2_165 -# %bb.143: + je .LBB2_189 +# %bb.167: cmp r13w, word ptr [rdx] - jmp .LBB2_157 -.LBB2_144: + jmp .LBB2_181 +.LBB2_168: mov r10, r8 and r10, -2 xor edi, edi .p2align 4, 0x90 -.LBB2_145: # =>This Inner Loop Header: Depth=1 +.LBB2_169: # =>This Inner Loop Header: Depth=1 cmp r13, qword ptr [rdx] sete al neg al @@ -13046,19 +13523,19 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor al, bl mov byte ptr [r14 + rsi], al cmp r10, rdi - jne .LBB2_145 -.LBB2_146: + jne .LBB2_169 +.LBB2_170: test r8b, 1 - je .LBB2_165 -# %bb.147: + je .LBB2_189 +# %bb.171: cmp r13, qword ptr [rdx] - jmp .LBB2_157 -.LBB2_148: + jmp .LBB2_181 +.LBB2_172: mov r9, r8 and r9, -2 xor edi, edi .p2align 4, 0x90 -.LBB2_149: # =>This Inner Loop Header: Depth=1 +.LBB2_173: # =>This Inner Loop Header: Depth=1 vucomiss xmm0, dword ptr [rdx] setnp cl sete al @@ -13091,13 +13568,13 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor bl, r11b mov byte ptr [r14 + rsi], bl cmp r9, rdi - jne .LBB2_149 -.LBB2_150: + jne .LBB2_173 +.LBB2_174: test r8b, 1 - je .LBB2_165 -# %bb.151: + je .LBB2_189 +# %bb.175: vucomiss xmm0, dword ptr [rdx] -.LBB2_152: +.LBB2_176: setnp al sete dl and dl, al @@ -13113,13 +13590,13 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 and bl, dl xor bl, sil mov byte ptr [r14 + rax], bl - jmp .LBB2_165 -.LBB2_153: + jmp .LBB2_189 +.LBB2_177: mov r10, r8 and r10, -2 xor edi, edi .p2align 4, 0x90 -.LBB2_154: # =>This Inner Loop Header: Depth=1 +.LBB2_178: # =>This Inner Loop Header: Depth=1 cmp r13d, dword ptr [rdx] sete al neg al @@ -13148,13 +13625,13 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 xor al, bl mov byte ptr [r14 + rsi], al cmp r10, rdi - jne .LBB2_154 -.LBB2_155: + jne .LBB2_178 +.LBB2_179: test r8b, 1 - je .LBB2_165 -# %bb.156: + je .LBB2_189 +# %bb.180: cmp r13d, dword ptr [rdx] -.LBB2_157: +.LBB2_181: sete al neg al mov rdx, rdi @@ -13168,30 +13645,31 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 and bl, al xor bl, sil mov byte ptr [r14 + rdx], bl - jmp .LBB2_165 -.LBB2_160: + jmp .LBB2_189 +.LBB2_184: mov r10, r8 and r10, -2 - xor esi, esi - mov r14, qword ptr [rsp + 376] # 8-byte Reload + xor r9d, r9d + mov r11, qword ptr [rsp + 376] # 8-byte Reload .p2align 4, 0x90 -.LBB2_161: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [r12 + rsi] +.LBB2_185: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r12b, byte ptr [rsi + r9] sete bl neg bl - mov rdi, rsi + mov rdi, r9 shr rdi, 3 - mov ecx, esi + mov ecx, eax and cl, 6 mov dl, 1 shl dl, cl - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r11 + rdi] xor bl, r9b and dl, bl xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp r11b, byte ptr [r12 + rsi + 1] - lea rsi, [rsi + 2] + mov byte ptr [r11 + rdi], dl + cmp r12b, byte ptr [rsi + rax + 1] + lea r9, [rax + 2] sete bl neg bl xor bl, dl @@ -13200,31 +13678,31 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 shl al, cl and al, bl xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, rsi - jne .LBB2_161 -.LBB2_162: - add r12, rsi -.LBB2_163: + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB2_185 +.LBB2_186: + add rsi, r9 +.LBB2_187: test r8b, 1 - je .LBB2_165 -# %bb.164: - cmp r11b, byte ptr [r12] + je .LBB2_189 +# %bb.188: + cmp r12b, byte ptr [rsi] sete al neg al - mov rdx, rsi + mov rdx, r9 shr rdx, 3 mov r8, qword ptr [rsp + 376] # 8-byte Reload mov dil, byte ptr [r8 + rdx] - and sil, 7 + and r9b, 7 mov bl, 1 - mov ecx, esi + mov ecx, r9d shl bl, cl xor al, dil and bl, al xor bl, dil mov byte ptr [r8 + rdx], bl -.LBB2_165: +.LBB2_189: lea rsp, [rbp - 40] pop rbx pop r12 @@ -13234,1988 +13712,1985 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 pop rbp vzeroupper ret -.LBB2_166: - and r15, -32 - mov rax, r15 +.LBB2_190: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - mov qword ptr [rsp + 384], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 376], rax # 8-byte Spill - vmovd xmm0, r11d + vmovd xmm0, r12d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill xor eax, eax mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB2_167: # =>This Inner Loop Header: Depth=1 +.LBB2_191: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 408], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 96], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 160], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 112], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rdx + rax] + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rdx + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rdx + rcx + 1] - mov rsi, rcx + movzx eax, byte ptr [rdi + rcx + 1] + mov rdx, rcx vmovd xmm4, eax mov rcx, rbx - movzx eax, byte ptr [rdx + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rsi + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rsi + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rsi + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm13, eax - movzx eax, byte ptr [rdx + rsi + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rdx + rsi + 6] - mov qword ptr [rsp + 240], rsi # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 256], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rdx + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rsi + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 128], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 248], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov qword ptr [rsp + 104], rax # 8-byte Spill - mov rax, rbx - or rax, 576 mov qword ptr [rsp + 264], rax # 8-byte Spill - mov rax, rbx + or rbx, 576 + mov qword ptr [rsp + 240], rbx # 8-byte Spill + mov rax, rcx or rax, 608 - mov qword ptr [rsp + 200], rax # 8-byte Spill - mov r11, rbx - or r11, 640 - mov qword ptr [rsp + 112], r11 # 8-byte Spill - mov rax, rbx + mov qword ptr [rsp + 80], rax # 8-byte Spill + mov r14, rcx + or r14, 640 + mov qword ptr [rsp + 160], r14 # 8-byte Spill + mov rax, rcx or rax, 672 - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov r12, rbx - or r12, 704 - mov qword ptr [rsp + 144], r12 # 8-byte Spill - mov rsi, rbx + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov r13, rcx + or r13, 704 + mov qword ptr [rsp + 232], r13 # 8-byte Spill + mov rsi, rcx or rsi, 736 - mov qword ptr [rsp + 208], rsi # 8-byte Spill - mov r15, rbx + mov qword ptr [rsp + 192], rsi # 8-byte Spill + mov r15, rcx or r15, 768 - mov qword ptr [rsp + 224], r15 # 8-byte Spill - mov r9, rbx - or r9, 800 - mov qword ptr [rsp + 232], r9 # 8-byte Spill - mov r8, rbx - or r8, 832 - mov qword ptr [rsp + 88], r8 # 8-byte Spill - mov rdi, rbx - or rdi, 864 - mov qword ptr [rsp + 216], rdi # 8-byte Spill - mov r14, rbx - or r14, 896 - mov qword ptr [rsp + 80], r14 # 8-byte Spill - mov r10, rbx - or r10, 928 - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov rax, rbx - mov qword ptr [rsp + 256], rbx # 8-byte Spill + mov qword ptr [rsp + 120], r15 # 8-byte Spill + mov r11, rcx + or r11, 800 + mov qword ptr [rsp + 168], r11 # 8-byte Spill + mov r10, rcx + or r10, 832 + mov qword ptr [rsp + 288], r10 # 8-byte Spill + mov r9, rcx + or r9, 864 + mov qword ptr [rsp + 136], r9 # 8-byte Spill + mov r8, rcx + or r8, 896 + mov qword ptr [rsp + 208], r8 # 8-byte Spill + mov rdx, rcx + or rdx, 928 + mov qword ptr [rsp + 216], rdx # 8-byte Spill + mov rax, rcx + mov qword ptr [rsp + 200], rcx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 96], rcx # 8-byte Spill - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm9, xmm0, byte ptr [rdx + r13], 1 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rdx + rbx], 2 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11], 4 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx], 15 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 1 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12], 2 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 3 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 4 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 5 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10], 6 - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 11 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 15 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 1 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 3 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 5 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 6 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 8 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 10 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 11 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 12 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 13 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 14 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r14 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 1], 2 - mov rdi, r12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 14 + mov qword ptr [rsp + 56], rcx # 8-byte Spill + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + r12], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 4 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 2 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 3 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 4 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 6 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 7 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 12 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 13 + mov r12, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 15 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 1 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 3 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 5 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 8 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 10 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 11 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 12 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + rbx + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 6 + mov rdx, r15 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + mov r10, rax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 14 vinserti128 ymm15, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 1], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm9, esi vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm10, esi - mov r8, qword ptr [rsp + 104] # 8-byte Reload + mov r8, qword ptr [rsp + 264] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 2], 1 - mov r9, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 2], 2 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 2], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 2], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 2], 8 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 2], 9 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 2], 10 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 2], 11 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 2], 12 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 2], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 7 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 8 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 9 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 10 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 11 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rdx + r8 + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 3], 3 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 3], 4 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 3], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 3], 6 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 11 - mov r12, r11 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 3], 13 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 14 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rdx + rax + 3], 1 - mov r13, rax + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 1 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 2], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 7 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 3], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 8 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 9 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 10 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 11 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 12 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 13 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 14 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 15 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 7 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 13 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r8 + 3], 1 + mov rdx, r8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 6 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 13 + mov r14, r15 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rax + 3], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 2 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 3], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 3], 14 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 9] + vpinsrb xmm0, xmm5, byte ptr [rdi + r10 + 3], 14 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 9] vmovd xmm8, esi - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 3], 15 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 9] + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 9] vmovd xmm11, esi - mov r14, qword ptr [rsp + 104] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 4], 1 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 4], 3 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 4], 4 - mov rcx, r8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 5 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 7 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 8 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 4], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 4], 14 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 15 - vpinsrb xmm3, xmm13, byte ptr [rdx + r13 + 4], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 9 + mov r10, rdx + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 5 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 11 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 13 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 10 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 4], 11 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 4], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 15 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm13, byte ptr [rdi + rax + 4], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 5 + mov rsi, r15 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 4], 6 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 15 - vpinsrb xmm4, xmm14, byte ptr [rdx + r14 + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 2 - mov r14, r15 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 5], 5 - mov r10, rcx - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 6 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 5], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 9 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 5], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 4], 8 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 10 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 5], 15 - vpinsrb xmm5, xmm6, byte ptr [rdx + r13 + 5], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 11 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 12 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 4], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r10 + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 2 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 8 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 10 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 12 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 14 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 5], 6 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 10 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 5], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 5], 12 - mov r12, r11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 15 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm6, byte ptr [rdi + rdx + 5], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 4 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 6 + mov r13, rsi + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 5], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 vinserti128 ymm14, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 10] + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 5], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 10] vmovd xmm3, esi vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 10] - vmovd xmm4, esi - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rdx + rdi + 6], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 6], 2 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 3 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 6], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 6], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 6], 8 - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 6], 11 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 12 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 6], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 14 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 6], 15 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + rcx + 6], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 7 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 6], 8 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 10 - mov r15, r13 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 13 + movzx esi, byte ptr [rdi + rax + 10] + vmovd xmm4, esi + vpinsrb xmm0, xmm12, byte ptr [rdi + r10 + 6], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 6], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 5 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 6 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 8 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 9 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 14 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 1 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 7], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 7], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 10 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 7], 13 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 7], 15 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 7], 1 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 11 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 12 + mov r9, r15 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 13 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 14 mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 6 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 7], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 7], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 15 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + r15 + 6], 1 mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 2 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 3 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 6 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 8 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 9 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 6], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 12 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 13 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 2 + mov r10, rbx + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 10 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 11 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 7], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 11 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rcx + 7], 14 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 11] + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rcx + 7], 14 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 11] vmovd xmm1, esi - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 7], 15 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 11] - vmovd xmm2, esi - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rdx + rcx + 8], 1 - mov r15, r13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 8], 2 mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 4 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 8], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 6 - mov r8, rax - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 8 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 8], 9 + movzx esi, byte ptr [rdi + rcx + 11] + vmovd xmm2, esi + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r14 + 8], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 3 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 4 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 8], 6 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 8], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 8 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 11 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 12 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 14 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 15 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + rdx + 8], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 4 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 5 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 6 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 9 mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 8], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 10 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 13 + mov r13, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r14 + 9], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 2 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 5 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 9], 7 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 9 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 12 mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 8], 11 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 12 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 13 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 15 + vpinsrb xmm7, xmm11, byte ptr [rdi + rdx + 9], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 2 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 4 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 10 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r14 + 8], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 6 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 15 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rdx + rax + 9], 1 - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 9], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + r13 + 9], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 7 - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 9], 8 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 9], 9 - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 9], 11 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 12 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rdx + rax + 9], 1 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 9], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 9], 4 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 9], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 9], 8 - mov r14, r11 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 12 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 9], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 12] vmovd xmm0, esi vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1088], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 12] vmovd xmm5, esi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 10], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 3 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 4 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 7 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 10], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 10], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 11 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 10], 1 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 2 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 10], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 10], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 10], 3 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 5 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 10], 6 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 8 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 10], 9 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 10 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 3 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 4 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 12 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 10], 13 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 14 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 5 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 11 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 15 + mov r14, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 10], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 3 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 8 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 8 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 11 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 10], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 13 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 14 + mov r15, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 11], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 4 + mov r15, r10 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 6 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 8 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 9 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 12 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 4 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 5 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 10 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 13 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 1 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 11], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 11], 6 - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 11], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 11], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 11], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm3 # 32-byte Spill - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 14 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 13] + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 14 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] vmovd xmm3, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 15 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1024], ymm1 # 32-byte Spill - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 13] + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] vmovd xmm1, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 1 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 12], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 12], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 4 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 8 - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 12], 9 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 12], 10 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 12], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 12], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 15 - vpinsrb xmm2, xmm5, byte ptr [rdx + rax + 12], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 2 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 1 + mov r8, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 5 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 6 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 9 + mov r15, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 11 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 12 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 14 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 4 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 12], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 8 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 12], 9 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 12], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 12 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 15 - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 13], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 13], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 13], 5 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 7 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 13], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 13], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 11 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 15 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + rsi + 12], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 2 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 4 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 6 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 7 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 8 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 10 mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 14 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 15 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 2 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 13], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 13], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 11 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 12 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 13 + mov r11, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 14 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 15 + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 8 + mov r8, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 10 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 11 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 13 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 7 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 13 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rax + 13], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 14] + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 13], 15 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + r15 + 14] vmovd xmm1, esi vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 14] - vmovd xmm0, esi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 1 - mov r10, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 2 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 4 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 14], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 8 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 14], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 1 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 14], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 4 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 14], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 7 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 14], 8 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 12 + movzx esi, byte ptr [rdi + rax + 14] + vmovd xmm0, esi + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 6 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 9 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 12 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 14], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 15 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 14], 1 mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 14], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 14], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 15 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + r14 + 15] - vmovd xmm2, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 3 mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 15], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 3 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 15], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 15], 6 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 15], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 5 mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 15], 9 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 15], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 15] - vmovd xmm3, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 15], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 8 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 10 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 11 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 12 mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 15], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 14 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 15 + movzx esi, byte ptr [rdi + r15 + 15] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 3 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 4 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 15], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 7 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 9 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 11 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 13 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 14 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 15 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 15] + vmovd xmm3, esi + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 2 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 4 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 5 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 7 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 15], 12 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - movzx esi, byte ptr [rdx + r14 + 16] + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 16] vmovd xmm0, esi - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 16], 1 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 16], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 16], 7 - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 16], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 16], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 16], 10 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 1 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 5 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 8 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 12 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 13 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 16], 14 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 16], 15 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rbx + 16] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 15 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + r10 + 16] vmovd xmm1, esi - mov r10, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 16], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 2 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 4 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 16], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 6 - mov r9, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 16], 7 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 8 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 9 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 10 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 16], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 13 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 14 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 17] - vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 1 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 2 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 3 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 8 mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 4 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 17], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 9 mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 17], 15 - movzx esi, byte ptr [rdx + rbx + 17] - vmovd xmm3, esi - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 17], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 5 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 17], 8 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 17], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 17], 11 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 12 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 13 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 17] + vmovd xmm2, esi + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 1 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 6 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 7 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 17], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 10 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 12 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 17], 13 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 14 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 15 + movzx esi, byte ptr [rdi + r10 + 17] + vmovd xmm3, esi + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 12 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 13 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rax + 17], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + r13 + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rbx + 18] + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 18] vmovd xmm0, esi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 1 - mov r14, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 18], 2 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 4 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 18], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 8 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 13 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 18], 14 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 18], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 18] - vmovd xmm1, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 6 - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 13 + mov r11, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 6 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 8 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 9 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 14 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 15 - movzx esi, byte ptr [rdx + rbx + 19] - vmovd xmm2, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 11 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 18], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 18], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 15 + mov r9, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + r9 + 18] + vmovd xmm1, esi + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 2 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 3 mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 19], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 19], 3 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 19], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 19], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 4 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 5 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 7 mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 6 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 19], 7 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 19], 8 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 19], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 19], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 12 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 19], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 19] - vmovd xmm3, esi - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 19], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 19], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 11 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 13 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 15 + movzx esi, byte ptr [rdi + rdx + 19] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 5 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 19], 9 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 11 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 15 + movzx esi, byte ptr [rdi + r9 + 19] + vmovd xmm3, esi + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 3 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 5 + mov r8, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 7 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 19], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 12 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 14 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 20] + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 20] vmovd xmm0, esi - mov r12, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 20], 1 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 2 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 1 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 7 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 11 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 12 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 15 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 20], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 20], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 20], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 20], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 20], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 20], 11 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 20], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 13 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 14 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 20], 15 - mov r9, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + r9 + 20] + movzx esi, byte ptr [rdi + rax + 20] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 1 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 20], 2 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 20], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 4 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 6 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 11 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 20], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 21] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 1 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 3 mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 8 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 9 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 4 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 5 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 6 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 8 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 9 mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 14 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 20], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 21] - vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 21], 1 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 2 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 21], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 4 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 8 - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 21], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 21], 14 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 21], 15 - movzx esi, byte ptr [rdx + r9 + 21] + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 12 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 15 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 21] vmovd xmm3, esi - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 21], 3 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 21], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 8 - mov r12, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 21], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 10 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 11 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 13 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 14 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 7 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 21], 12 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rdx + r14 + 21], 15 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + r10 + 22] + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 22] vmovd xmm0, esi - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 1 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 22], 3 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 4 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 5 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 22], 6 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 22], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 12 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 1 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 2 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 22], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 22], 6 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 13 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 14 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 22] + vmovd xmm1, esi + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 1 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 6 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 10 mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 22], 13 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 14 mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 22], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 22] - vmovd xmm1, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 22], 4 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 22], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 6 - mov r9, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 22], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 22], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 11 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 22], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 15 - movzx esi, byte ptr [rdx + r10 + 23] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 15 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + r14 + 23] vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 23], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 23], 2 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 23], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 23], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 23], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 8 - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 23], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 12 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 23], 13 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 23], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 15 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 23] - vmovd xmm3, esi - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 23], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 1 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 2 + mov rcx, r9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 3 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 5 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 8 mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 23], 5 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 23], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 8 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 23], 9 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 23], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 9 mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 14 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 11 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 23] + vmovd xmm3, esi + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 3 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 23], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 12 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 23], 13 + mov r13, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 14 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 24] + movzx esi, byte ptr [rdi + r14 + 24] vmovd xmm0, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 1 mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 24], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 4 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 10 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 24], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 24], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 15 - movzx esi, byte ptr [rdx + r15 + 24] - vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 24], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 3 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 24], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 24], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 7 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 24], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 10 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 1 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 4 mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 24], 12 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 14 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 24], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 25] - vmovd xmm2, esi - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 25], 1 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 4 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 25], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 5 mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 25], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 25] - vmovd xmm3, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 6 mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 7 mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 25], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 25], 8 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 25], 9 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 14 - vinserti128 ymm9, ymm1, xmm0, 1 - vpinsrb xmm0, xmm3, byte ptr [rdx + rbx + 25], 15 - vinserti128 ymm8, ymm0, xmm2, 1 - movzx esi, byte ptr [rdx + rax + 26] - vmovd xmm0, esi - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 26], 1 - mov r10, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 26], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 26], 5 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 26], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 7 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 26], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 9 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 10 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 11 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 12 mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rdi + 26] + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 14 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 24] vmovd xmm1, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 1 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 26], 2 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 26], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 26], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 6 - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 26], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 26], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 12 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 1 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 13 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 4 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 5 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 27] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 7 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 12 + mov r14, r10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 25] vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 27], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 27], 2 - mov r13, r10 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 4 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 27], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 27], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 27], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 10 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 27], 11 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 14 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 27], 15 - movzx esi, byte ptr [rdx + rdi + 27] + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 25], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 2 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 5 + mov r10, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 12 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 15 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 25] vmovd xmm3, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 27], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 3 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 4 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 5 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 27], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 8 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 9 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 9 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 10 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 11 mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 25], 13 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 14 + vinserti128 ymm9, ymm1, xmm0, 1 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r14 + 25], 15 + vinserti128 ymm8, ymm0, xmm2, 1 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 26] + vmovd xmm0, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 1 + mov r8, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 4 mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 27], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 6 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 7 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 9 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 11 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 15 + movzx esi, byte ptr [rdi + rdx + 26] + vmovd xmm1, esi + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 3 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 5 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 10 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 26], 15 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 27] + vmovd xmm2, esi + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 27], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 5 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 8 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 11 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 27] + vmovd xmm3, esi + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 4 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 7 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 8 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 9 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 28] + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 28] vmovd xmm0, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 3 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 28], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 6 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 7 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 28], 8 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 28], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 12 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 28], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 28], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 28], 15 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + r11 + 28] - vmovd xmm1, esi - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 28], 6 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 7 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 8 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 1 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 3 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 6 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 7 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 9 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 12 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 13 mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 11 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 13 - mov r10, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 14 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 15 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 28] + vmovd xmm1, esi + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 2 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 3 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 5 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 29] - vmovd xmm2, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 1 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 4 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 7 mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 10 - mov r8, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 11 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 10 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 11 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 12 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 13 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 14 mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 14 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 15 - movzx esi, byte ptr [rdx + r11 + 29] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 15 + movzx esi, byte ptr [rdi + rax + 29] + vmovd xmm2, esi + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 5 + mov r9, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 10 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 11 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 29], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 13 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 29] vmovd xmm3, esi - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 3 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 29], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 29], 9 - mov r15, rbx - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 10 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 13 - vpinsrb xmm4, xmm3, byte ptr [rdx + r10 + 29], 14 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 29], 4 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 5 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 8 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + rbx + 29], 14 + mov r12, rbx vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rdx + r10 + 29], 15 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rbx + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 30] + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 30] vmovd xmm0, esi - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 30], 1 - movzx esi, byte ptr [rdx + rax + 31] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 1 + movzx esi, byte ptr [rdi + rcx + 31] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 31], 1 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 4 - mov rax, r9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 31], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 7 - mov rbx, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 10 - mov rax, r8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 31], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 31], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rdx + r14 + 31], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx eax, byte ptr [rdx + rsi + 30] - vmovd xmm1, eax - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 30], 1 - movzx eax, byte ptr [rdx + rsi + 31] - vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 31], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 31], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 1 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + r15 + 31], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rdx + rdi + 31], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 12 - mov rax, rcx - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 31], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 31], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rsi, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rdx + r10 + 31], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, r11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 31], 12 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 31], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + rax + 31], 15 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] + vmovd xmm1, eax + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] + vmovd xmm7, eax + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 31], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + mov rax, r15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 31], 13 + mov rax, r12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 14 + mov rax, rbx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -15344,2002 +15819,2001 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [rbx + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [rbx + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [rbx + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [rbx + 4*rcx], ymm1 + vmovdqu ymmword ptr [rsi + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rsi + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rsi + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rsi + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB2_167 -# %bb.168: - mov r15, qword ptr [rsp + 392] # 8-byte Reload - cmp r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 400] # 8-byte Reload - jne .LBB2_43 - jmp .LBB2_129 -.LBB2_169: - and r15, -32 - mov rax, r15 + jne .LBB2_191 +# %bb.192: + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB2_139 + jmp .LBB2_143 +.LBB2_193: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - mov qword ptr [rsp + 384], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 376], rax # 8-byte Spill - vmovd xmm0, r11d + vmovd xmm0, r12d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill xor eax, eax mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB2_170: # =>This Inner Loop Header: Depth=1 +.LBB2_194: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 408], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 96], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 160], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 112], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rdx + rax] + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rdx + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rdx + rcx + 1] - mov rsi, rcx + movzx eax, byte ptr [rdi + rcx + 1] + mov rdx, rcx vmovd xmm4, eax mov rcx, rbx - movzx eax, byte ptr [rdx + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rsi + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rsi + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rsi + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm13, eax - movzx eax, byte ptr [rdx + rsi + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rdx + rsi + 6] - mov qword ptr [rsp + 240], rsi # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 256], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rdx + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rsi + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 128], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 248], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 264], rax # 8-byte Spill or rbx, 576 - mov qword ptr [rsp + 264], rbx # 8-byte Spill + mov qword ptr [rsp + 240], rbx # 8-byte Spill mov rax, rcx or rax, 608 - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov r14, rcx or r14, 640 - mov qword ptr [rsp + 112], r14 # 8-byte Spill + mov qword ptr [rsp + 160], r14 # 8-byte Spill mov rax, rcx or rax, 672 - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov r12, rcx - or r12, 704 - mov qword ptr [rsp + 144], r12 # 8-byte Spill - mov rdi, rcx - or rdi, 736 - mov qword ptr [rsp + 208], rdi # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov r13, rcx + or r13, 704 + mov qword ptr [rsp + 232], r13 # 8-byte Spill + mov rsi, rcx + or rsi, 736 + mov qword ptr [rsp + 192], rsi # 8-byte Spill mov r15, rcx or r15, 768 - mov qword ptr [rsp + 224], r15 # 8-byte Spill + mov qword ptr [rsp + 120], r15 # 8-byte Spill mov r11, rcx or r11, 800 - mov qword ptr [rsp + 232], r11 # 8-byte Spill + mov qword ptr [rsp + 168], r11 # 8-byte Spill mov r10, rcx or r10, 832 - mov qword ptr [rsp + 88], r10 # 8-byte Spill + mov qword ptr [rsp + 288], r10 # 8-byte Spill mov r9, rcx or r9, 864 - mov qword ptr [rsp + 216], r9 # 8-byte Spill + mov qword ptr [rsp + 136], r9 # 8-byte Spill mov r8, rcx or r8, 896 - mov qword ptr [rsp + 80], r8 # 8-byte Spill - mov rsi, rcx - or rsi, 928 - mov qword ptr [rsp + 72], rsi # 8-byte Spill + mov qword ptr [rsp + 208], r8 # 8-byte Spill + mov rdx, rcx + or rdx, 928 + mov qword ptr [rsp + 216], rdx # 8-byte Spill mov rax, rcx - mov qword ptr [rsp + 256], rcx # 8-byte Spill + mov qword ptr [rsp + 200], rcx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 96], rcx # 8-byte Spill - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm9, xmm0, byte ptr [rdx + r13], 1 - vpinsrb xmm0, xmm9, byte ptr [rdx + rbx], 2 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14], 4 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx], 15 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 1 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12], 2 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 3 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 4 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 5 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10], 6 - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 11 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 15 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 1 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 3 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 5 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 6 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 8 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 10 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 11 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 12 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 13 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 14 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r14 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 1], 2 - mov rdi, r12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 14 + mov qword ptr [rsp + 56], rcx # 8-byte Spill + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + r12], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 4 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 2 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 3 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 4 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 6 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 7 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 12 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 13 + mov r12, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 15 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 1 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 3 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 5 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 8 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 10 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 11 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 12 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + rbx + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 6 + mov rdx, r15 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + mov r10, rax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 14 vinserti128 ymm15, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 1], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm9, esi vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm10, esi - mov r8, qword ptr [rsp + 104] # 8-byte Reload + mov r8, qword ptr [rsp + 264] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 2], 1 - mov r9, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 2], 2 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 2], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 2], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 2], 8 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 2], 9 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 2], 10 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 2], 11 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 2], 12 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 2], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 7 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 8 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 9 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 10 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 11 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rdx + r8 + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 3], 3 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 3], 4 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 3], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 3], 6 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 11 - mov r12, r11 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 3], 13 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 14 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rdx + rax + 3], 1 - mov r13, rax + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 1 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 2], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 7 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 3], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 8 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 9 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 10 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 11 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 12 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 13 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 14 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 15 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 7 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 13 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r8 + 3], 1 + mov rdx, r8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 6 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 13 + mov r14, r15 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rax + 3], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 2 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 3], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 3], 14 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 9] + vpinsrb xmm0, xmm5, byte ptr [rdi + r10 + 3], 14 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 9] vmovd xmm8, esi - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 3], 15 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 9] + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 9] vmovd xmm11, esi - mov r14, qword ptr [rsp + 104] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 4], 1 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 4], 3 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 4], 4 - mov rcx, r8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 5 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 7 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 8 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 4], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 4], 14 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 15 - vpinsrb xmm3, xmm13, byte ptr [rdx + r13 + 4], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 9 + mov r10, rdx + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 5 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 11 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 13 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 10 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 4], 11 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 4], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 15 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm13, byte ptr [rdi + rax + 4], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 5 + mov rsi, r15 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 4], 6 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 15 - vpinsrb xmm4, xmm14, byte ptr [rdx + r14 + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 2 - mov r14, r15 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 5], 5 - mov r10, rcx - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 6 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 5], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 9 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 5], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 4], 8 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 10 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 5], 15 - vpinsrb xmm5, xmm6, byte ptr [rdx + r13 + 5], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 11 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 12 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 4], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r10 + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 2 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 8 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 10 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 12 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 14 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 5], 6 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 10 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 5], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 5], 12 - mov r12, r11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 15 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm6, byte ptr [rdi + rdx + 5], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 4 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 6 + mov r13, rsi + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 5], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 vinserti128 ymm14, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 10] + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 5], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 10] vmovd xmm3, esi vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 10] - vmovd xmm4, esi - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rdx + rdi + 6], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 6], 2 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 3 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 6], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 6], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 6], 8 - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 6], 11 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 12 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 6], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 14 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 6], 15 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + rcx + 6], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 7 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 6], 8 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 10 - mov r15, r13 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 13 + movzx esi, byte ptr [rdi + rax + 10] + vmovd xmm4, esi + vpinsrb xmm0, xmm12, byte ptr [rdi + r10 + 6], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 6], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 5 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 6 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 8 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 9 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 14 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 1 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 7], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 7], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 10 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 7], 13 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 7], 15 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 7], 1 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 11 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 12 + mov r9, r15 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 13 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 14 mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 6 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 7], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 7], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 15 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + r15 + 6], 1 mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 2 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 3 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 6 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 8 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 9 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 6], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 12 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 13 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 2 + mov r10, rbx + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 10 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 11 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 7], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 11 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rcx + 7], 14 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 11] + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rcx + 7], 14 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 11] vmovd xmm1, esi - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 7], 15 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 11] - vmovd xmm2, esi - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rdx + rcx + 8], 1 - mov r15, r13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 8], 2 mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 4 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 8], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 6 - mov r8, rax - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 8 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 8], 9 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 8], 10 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 8], 11 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r14 + 8], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 6 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 15 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rdx + rax + 9], 1 - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 9], 3 + movzx esi, byte ptr [rdi + rcx + 11] + vmovd xmm2, esi + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r14 + 8], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 3 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 4 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 8], 6 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 8], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 8 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 11 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 12 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 14 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 15 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + rdx + 8], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 4 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 5 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 6 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 8 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + r13 + 9], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 7 - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 9], 8 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 9], 9 - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 9], 11 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 12 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rdx + rax + 9], 1 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 9], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 9], 4 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 9], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 9], 8 - mov r14, r11 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 9 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 10 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 13 + mov r13, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r14 + 9], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 2 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 5 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 9], 7 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 9 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 12 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 13 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 15 + vpinsrb xmm7, xmm11, byte ptr [rdi + rdx + 9], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 2 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 4 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 12 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 9], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 12] vmovd xmm0, esi vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1088], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 12] vmovd xmm5, esi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 10], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 3 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 4 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 7 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 10], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 10], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 11 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 10], 1 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 2 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 10], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 10], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 10], 3 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 5 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 10], 6 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 8 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 10], 9 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 10 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 3 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 4 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 12 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 10], 13 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 14 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 5 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 11 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 15 + mov r14, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 10], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 3 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 8 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 8 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 11 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 10], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 13 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 14 + mov r15, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 11], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 4 + mov r15, r10 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 6 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 8 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 9 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 12 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 4 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 5 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 10 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 13 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 1 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 11], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 11], 6 - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 11], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 11], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 11], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm3 # 32-byte Spill - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 14 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 13] + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 14 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] vmovd xmm3, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 15 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1024], ymm1 # 32-byte Spill - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 13] + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] vmovd xmm1, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 1 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 12], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 12], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 4 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 8 - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 12], 9 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 12], 10 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 12], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 12], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 15 - vpinsrb xmm2, xmm5, byte ptr [rdx + rax + 12], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 2 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 1 + mov r8, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 5 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 6 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 9 + mov r15, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 11 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 12 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 14 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 4 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 12], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 8 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 12], 9 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 12], 10 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 12 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 15 - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 13], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 13], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 13], 5 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 7 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 13], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 13], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 11 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 15 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + rsi + 12], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 2 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 4 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 6 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 7 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 8 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 10 mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 14 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 15 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 2 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 13], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 13], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 11 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 12 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 13 + mov r11, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 14 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 15 + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 8 + mov r8, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 10 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 11 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 13 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 7 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 13 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rax + 13], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 14] + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 13], 15 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + r15 + 14] vmovd xmm1, esi vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 14] - vmovd xmm0, esi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 1 - mov r10, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 2 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 4 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 14], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 8 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 14], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 1 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 14], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 4 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 14], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 7 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 14], 8 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 12 + movzx esi, byte ptr [rdi + rax + 14] + vmovd xmm0, esi + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 6 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 9 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 12 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 14], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 15 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 14], 1 mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 14], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 14], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 15 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + r14 + 15] - vmovd xmm2, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 3 mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 15], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 3 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 15], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 15], 6 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 15], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 5 mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 15], 9 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 15], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 15] - vmovd xmm3, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 15], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 8 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 10 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 11 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 12 mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 15], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 14 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 15 + movzx esi, byte ptr [rdi + r15 + 15] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 3 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 4 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 15], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 7 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 9 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 11 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 13 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 14 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 15 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 15] + vmovd xmm3, esi + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 2 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 4 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 5 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 7 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 15], 12 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - movzx esi, byte ptr [rdx + r14 + 16] + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 16] vmovd xmm0, esi - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 16], 1 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 16], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 16], 7 - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 16], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 16], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 16], 10 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 1 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 5 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 8 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 12 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 13 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 16], 14 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 16], 15 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rbx + 16] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 15 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + r10 + 16] vmovd xmm1, esi - mov r10, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 16], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 2 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 3 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 4 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 16], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 6 - mov r9, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 16], 7 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 8 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 9 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 10 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 16], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 13 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 14 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 17] - vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 1 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 2 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 3 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 8 mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 4 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 17], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 9 mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 17], 15 - movzx esi, byte ptr [rdx + rbx + 17] + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 12 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 13 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 17] + vmovd xmm2, esi + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 1 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 6 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 7 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 17], 9 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 10 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 12 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 17], 13 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 14 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 15 + movzx esi, byte ptr [rdi + r10 + 17] vmovd xmm3, esi - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 17], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 12 mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 17], 8 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 17], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 17], 11 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 13 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rax + 17], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + r13 + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rbx + 18] + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 18] vmovd xmm0, esi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 1 - mov r14, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 18], 2 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 4 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 18], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 8 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 13 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 18], 14 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 18], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 18] - vmovd xmm1, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 6 - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 13 + mov r11, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 1 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 6 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 8 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 9 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 14 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 15 - movzx esi, byte ptr [rdx + rbx + 19] - vmovd xmm2, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 11 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 18], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 18], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 15 + mov r9, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + r9 + 18] + vmovd xmm1, esi + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 2 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 3 mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 19], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 19], 3 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 19], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 19], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 4 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 5 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 7 mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 6 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 19], 7 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 19], 8 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 19], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 19], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 12 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 19], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 19] - vmovd xmm3, esi - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 19], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 19], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 8 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 11 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 13 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 15 + movzx esi, byte ptr [rdi + rdx + 19] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 5 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 19], 9 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 11 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 15 + movzx esi, byte ptr [rdi + r9 + 19] + vmovd xmm3, esi + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 3 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 5 + mov r8, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 7 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 19], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 12 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 14 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 20] + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 20] vmovd xmm0, esi - mov r12, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 20], 1 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 2 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 1 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 7 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 11 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 12 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 15 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 20], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 20], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 20], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 20], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 20], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 20], 11 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 20], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 13 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 14 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 20], 15 - mov r9, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + r9 + 20] + movzx esi, byte ptr [rdi + rax + 20] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 1 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 20], 2 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 20], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 4 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 6 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 6 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 11 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 20], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 21] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 1 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 3 mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 8 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 9 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 12 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 4 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 5 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 6 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 8 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 9 mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 14 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 20], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 21] - vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 21], 1 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 2 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 21], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 4 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 8 - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 21], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 21], 14 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 21], 15 - movzx esi, byte ptr [rdx + r9 + 21] + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 12 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 15 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 21] vmovd xmm3, esi - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 21], 3 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 21], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 8 - mov r12, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 21], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 10 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 11 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 13 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 14 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 7 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 21], 12 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rdx + r14 + 21], 15 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + r10 + 22] + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 22] vmovd xmm0, esi - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 1 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 22], 3 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 4 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 5 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 22], 6 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 22], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 12 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 1 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 2 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 22], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 22], 6 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 13 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 14 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 22] + vmovd xmm1, esi + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 1 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 6 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 9 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 10 mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 22], 13 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 14 mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 22], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 22] - vmovd xmm1, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 22], 4 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 22], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 6 - mov r9, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 22], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 22], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 11 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 22], 12 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 13 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 15 - movzx esi, byte ptr [rdx + r10 + 23] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 15 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + r14 + 23] vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 23], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 23], 2 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 23], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 23], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 23], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 8 - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 23], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 11 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 12 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 23], 13 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 23], 14 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 15 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 23] - vmovd xmm3, esi - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 23], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 1 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 2 + mov rcx, r9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 3 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 5 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 8 mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 23], 5 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 23], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 8 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 23], 9 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 23], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 9 mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 14 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 11 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 23] + vmovd xmm3, esi + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 3 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 23], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 9 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 12 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 23], 13 + mov r13, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 14 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 24] + movzx esi, byte ptr [rdi + r14 + 24] vmovd xmm0, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 1 mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 24], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 4 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 10 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 24], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 24], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 15 - movzx esi, byte ptr [rdx + r15 + 24] - vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 24], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 3 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 24], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 24], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 7 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 24], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 10 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 1 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 4 mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 24], 12 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 13 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 14 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 24], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 25] - vmovd xmm2, esi - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 25], 1 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 4 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 25], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 7 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 5 mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 25], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 25] - vmovd xmm3, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 6 mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 7 mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 25], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 25], 8 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 25], 9 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 14 - vinserti128 ymm9, ymm1, xmm0, 1 - vpinsrb xmm0, xmm3, byte ptr [rdx + rbx + 25], 15 - vinserti128 ymm8, ymm0, xmm2, 1 - movzx esi, byte ptr [rdx + rax + 26] - vmovd xmm0, esi - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 26], 1 - mov r10, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 26], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 26], 5 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 26], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 7 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 26], 8 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 9 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 10 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 11 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 12 mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 11 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 13 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 14 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + rdi + 26] + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 14 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 24] vmovd xmm1, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 1 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 26], 2 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 26], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 26], 4 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 6 - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 26], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 26], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 10 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 11 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 12 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 1 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 13 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 4 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 5 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 27] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 7 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 12 + mov r14, r10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 25] vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 27], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 27], 2 - mov r13, r10 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 4 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 27], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 27], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 27], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 10 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 27], 11 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 14 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 27], 15 - movzx esi, byte ptr [rdx + rdi + 27] + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 25], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 2 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 5 + mov r10, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 12 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 15 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 25] vmovd xmm3, esi - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 27], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 3 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 4 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 5 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 27], 7 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 8 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 9 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 9 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 10 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 11 mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 25], 13 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 14 + vinserti128 ymm9, ymm1, xmm0, 1 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r14 + 25], 15 + vinserti128 ymm8, ymm0, xmm2, 1 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 26] + vmovd xmm0, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 1 + mov r8, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 4 mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 27], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 6 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 7 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 9 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 11 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 15 + movzx esi, byte ptr [rdi + rdx + 26] + vmovd xmm1, esi + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 3 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 5 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 10 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 26], 15 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 27] + vmovd xmm2, esi + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 27], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 4 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 5 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 8 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 10 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 11 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 27] + vmovd xmm3, esi + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 4 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 7 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 8 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 9 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 28] + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 28] vmovd xmm0, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 3 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 28], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 6 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 7 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 28], 8 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 28], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 12 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 28], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 28], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 28], 15 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx esi, byte ptr [rdx + r11 + 28] - vmovd xmm1, esi - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 28], 6 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 7 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 8 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 1 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 3 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 4 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 6 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 7 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 9 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 10 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 12 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 13 mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 11 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 12 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 13 - mov r10, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 14 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 15 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 28] + vmovd xmm1, esi + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 2 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 3 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 4 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 5 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 29] - vmovd xmm2, esi - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 1 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 4 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 7 mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 10 - mov r8, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 11 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 10 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 11 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 12 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 13 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 14 mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 14 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 15 - movzx esi, byte ptr [rdx + r11 + 29] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 15 + movzx esi, byte ptr [rdi + rax + 29] + vmovd xmm2, esi + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 5 + mov r9, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 10 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 11 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 29], 12 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 13 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 14 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 29] vmovd xmm3, esi - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 1 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 3 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 29], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 29], 9 - mov r15, rbx - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 10 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 12 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 13 - vpinsrb xmm4, xmm3, byte ptr [rdx + r10 + 29], 14 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 29], 4 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 5 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 7 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 8 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 9 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + rbx + 29], 14 + mov r12, rbx vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rdx + r10 + 29], 15 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rbx + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 30] + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 30] vmovd xmm0, esi - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 30], 1 - movzx esi, byte ptr [rdx + rax + 31] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 1 + movzx esi, byte ptr [rdi + rcx + 31] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 31], 1 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 4 - mov rax, r9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 31], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 7 - mov rbx, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 10 - mov rax, r8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 31], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 31], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rdx + r14 + 31], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx eax, byte ptr [rdx + rsi + 30] - vmovd xmm1, eax - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 30], 1 - movzx eax, byte ptr [rdx + rsi + 31] - vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 31], 1 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 31], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 6 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 1 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + r15 + 31], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rdx + rdi + 31], 11 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 12 - mov rax, rcx - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 31], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 31], 6 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rsi, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rdx + r10 + 31], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, r11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 31], 12 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 31], 14 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + rax + 31], 15 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] + vmovd xmm1, eax + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] + vmovd xmm7, eax + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 31], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + mov rax, r15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 31], 13 + mov rax, r12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 14 + mov rax, rbx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -17468,22 +17942,22 @@ comparison_equal_scalar_arr_avx2: # @comparison_equal_scalar_arr_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [rbx + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [rbx + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [rbx + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [rbx + 4*rcx], ymm1 + vmovdqu ymmword ptr [rsi + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rsi + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rsi + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rsi + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB2_170 -# %bb.171: - mov r15, qword ptr [rsp + 392] # 8-byte Reload - cmp r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 400] # 8-byte Reload - jne .LBB2_114 - jmp .LBB2_133 + jne .LBB2_194 +# %bb.195: + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB2_153 + jmp .LBB2_157 .Lfunc_end2: .size comparison_equal_scalar_arr_avx2, .Lfunc_end2-comparison_equal_scalar_arr_avx2 # -- End function @@ -17501,104 +17975,120 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 push rbx and rsp, -8 sub rsp, 72 - mov eax, r9d - mov r14, r8 - mov r12, rcx + # kill: def $r9d killed $r9d def $r9 + mov r12, r8 + mov r15, rcx cmp edi, 6 - jg .LBB3_29 + jg .LBB3_35 # %bb.1: cmp edi, 3 jle .LBB3_2 -# %bb.15: +# %bb.18: cmp edi, 4 - je .LBB3_68 -# %bb.16: + je .LBB3_83 +# %bb.19: cmp edi, 5 - je .LBB3_79 -# %bb.17: + je .LBB3_97 +# %bb.20: cmp edi, 6 - jne .LBB3_123 -# %bb.18: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_22 -# %bb.19: - cdqe + jne .LBB3_153 +# %bb.21: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_26 +# %bb.23: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_24: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_20 -# %bb.21: - add r12, 1 -.LBB3_22: - sar r15, 5 - cmp r14, 32 - jl .LBB3_26 -# %bb.23: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB3_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB3_26: + sub r12, r8 + je .LBB3_153 +# %bb.27: + add r15, 1 +.LBB3_28: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_32 +# %bb.29: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill mov eax, dword ptr [rsi + 12] cmp eax, dword ptr [rdx + 12] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill mov eax, dword ptr [rsi + 16] cmp eax, dword ptr [rdx + 16] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill mov eax, dword ptr [rsi + 20] cmp eax, dword ptr [rdx + 20] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill mov eax, dword ptr [rsi + 24] cmp eax, dword ptr [rdx + 24] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] setne r13b mov eax, dword ptr [rsi + 32] cmp eax, dword ptr [rdx + 32] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - setne r8b + setne dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] setne r11b @@ -17607,21 +18097,21 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r15b mov eax, dword ptr [rsi + 48] cmp eax, dword ptr [rdx + 48] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill mov eax, dword ptr [rsi + 56] cmp eax, dword ptr [rdx + 56] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill mov eax, dword ptr [rsi + 60] cmp eax, dword ptr [rdx + 60] - setne dil + setne r8b mov eax, dword ptr [rsi + 64] mov ebx, dword ptr [rsi + 68] cmp eax, dword ptr [rdx + 64] mov eax, dword ptr [rsi + 72] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 68] mov ebx, dword ptr [rsi + 76] setne r10b @@ -17632,144 +18122,144 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 mov ebx, dword ptr [rsi + 84] setne r12b cmp eax, dword ptr [rdx + 80] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 84] mov eax, dword ptr [rsi + 88] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] setne r9b cmp eax, dword ptr [rdx + 96] mov eax, dword ptr [rsi + 100] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 112] mov eax, dword ptr [rsi + 116] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 116] mov eax, dword ptr [rsi + 120] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 120] mov eax, dword ptr [rsi + 124] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_24 -# %bb.25: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_26: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.27: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_30 +# %bb.31: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_32: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB3_28: # =>This Inner Loop Header: Depth=1 +.LBB3_34: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -17777,7 +18267,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -17785,106 +18276,122 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_28 - jmp .LBB3_123 -.LBB3_29: + cmp r12, r8 + jne .LBB3_34 + jmp .LBB3_153 +.LBB3_35: cmp edi, 8 - jle .LBB3_30 -# %bb.43: + jle .LBB3_36 +# %bb.52: cmp edi, 9 - je .LBB3_101 -# %bb.44: + je .LBB3_125 +# %bb.53: cmp edi, 11 - je .LBB3_112 -# %bb.45: + je .LBB3_139 +# %bb.54: cmp edi, 12 - jne .LBB3_123 -# %bb.46: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_50 -# %bb.47: - movsxd r10, eax + jne .LBB3_153 +# %bb.55: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_60 +# %bb.57: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB3_48: # =>This Inner Loop Header: Depth=1 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - vucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - setp cl +.LBB3_58: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + vmovsd xmm0, qword ptr [rsi + 8*r14] # xmm0 = mem[0],zero + vucomisd xmm0, qword ptr [rdx + 8*r14] + setp r10b setne bl - or bl, cl + or bl, r10b neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d + lea eax, [8*rdi] + sub ecx, eax mov eax, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB3_48 -# %bb.49: - add r12, 1 -.LBB3_50: - sar r15, 5 - cmp r14, 32 - jl .LBB3_54 -# %bb.51: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -8 + cmp r8, r14 + jne .LBB3_58 +# %bb.59: + sub rsi, r11 + sub rdx, r11 +.LBB3_60: + sub r12, r8 + je .LBB3_153 +# %bb.61: + add r15, 1 +.LBB3_62: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_66 +# %bb.63: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx] vmovsd xmm0, qword ptr [rsi + 8] # xmm0 = mem[0],zero setp al setne cl or cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill + mov byte ptr [rsp + 29], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 8] setp al setne cl or cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill + mov byte ptr [rsp + 22], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 16] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 16] setp al setne cl or cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill + mov byte ptr [rsp + 28], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 24] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 24] setp al setne cl or cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill + mov byte ptr [rsp + 31], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 32] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 32] setp al setne cl or cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill + mov byte ptr [rsp + 30], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 40] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 40] setp al @@ -17900,13 +18407,13 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill + mov byte ptr [rsp + 12], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 64] setp al setne cl or cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill + mov byte ptr [rsp + 27], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 72] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 72] setp al @@ -17917,117 +18424,116 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill + mov byte ptr [rsp + 26], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 88] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 88] setp al setne cl or cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill + mov byte ptr [rsp + 25], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 96] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 96] setp al setne cl or cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 11], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 104] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 104] setp al setne cl or cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 112] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 112] setp al setne cl or cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill + mov byte ptr [rsp + 21], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 120] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 120] setp al setne cl or cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill + mov byte ptr [rsp + 20], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 128] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 128] setp al setne cl or cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill + mov byte ptr [rsp + 23], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 136] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 136] setp al setne cl or cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill + mov byte ptr [rsp + 19], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 144] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 144] setp al setne cl or cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill + mov byte ptr [rsp + 18], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 152] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 152] setp al - setne r14b - or r14b, al + setne r15b + or r15b, al vmovsd xmm0, qword ptr [rsi + 160] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 160] setp al setne cl or cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 17], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 168] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 168] setp al setne cl or cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 176] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 176] setp al setne cl or cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill + mov byte ptr [rsp + 14], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 184] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 184] setp al - setne r15b - or r15b, al + setne r10b + or r10b, al vmovsd xmm0, qword ptr [rsi + 192] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 192] setp al setne cl or cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill + mov byte ptr [rsp + 15], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 200] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 200] setp al - setne cl - or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + setne r12b + or r12b, al vmovsd xmm0, qword ptr [rsi + 208] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 208] setp al - setne r11b - or r11b, al + setne r14b + or r14b, al vmovsd xmm0, qword ptr [rsi + 216] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 216] setp al - setne r10b - or r10b, al + setne r11b + or r11b, al vmovsd xmm0, qword ptr [rsi + 224] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 224] setp al setne cl or cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 13], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 232] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 232] setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vmovsd xmm0, qword ptr [rsi + 240] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 240] setp al @@ -18039,110 +18545,108 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setp al setne r8b or r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload shl dil, 5 shl r13b, 6 or r13b, dil mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload shl cl, 2 or cl, al mov eax, ebx add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload + add al, byte ptr [rsp + 27] # 1-byte Folded Reload mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 or al, r13b mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload shl bl, 3 or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 6 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload shl cl, 2 or cl, bl - shl r14b, 3 - or r14b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload shl bl, 4 - or bl, r14b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r14d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r14b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 or cl, r13b - or al, dil - shl r15b, 7 - or r15b, cl - or r15b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r11b, 2 - or r11b, cl - shl r10b, 3 - or r10b, r11b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload + shl r10b, 7 + or r10b, cl + or r10b, bl + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload shl cl, 4 - or cl, r10b - mov byte ptr [r12], r14b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 shl r9b, 6 or r9b, bl - mov byte ptr [r12 + 1], al + mov byte ptr [r15 + 1], dil shl r8b, 7 or r8b, r9b or r8b, cl - mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], r8b + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB3_52 -# %bb.53: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB3_54: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.55: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_64 +# %bb.65: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_66: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB3_56: # =>This Inner Loop Header: Depth=1 +.LBB3_68: # =>This Inner Loop Header: Depth=1 lea r9, [rcx + 1] vmovsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 8*rcx] @@ -18152,7 +18656,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg al mov rdi, rcx shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] xor al, r8b and cl, 7 mov bl, 1 @@ -18160,95 +18665,119 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl bl, cl and bl, al xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r15 + rdi], bl mov rcx, r9 - cmp r14, r9 - jne .LBB3_56 - jmp .LBB3_123 + cmp r12, r9 + jne .LBB3_68 + jmp .LBB3_153 .LBB3_2: cmp edi, 2 - je .LBB3_57 + mov r13, r15 + je .LBB3_69 # %bb.3: cmp edi, 3 - jne .LBB3_123 + jne .LBB3_153 # %bb.4: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_8 + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_11 # %bb.5: - cdqe - .p2align 4, 0x90 -.LBB3_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setne r10b - neg r10b - lea rdi, [rax + 7] + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB3_9 +# %bb.6: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB3_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setne r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB3_6 -# %bb.7: - add r12, 1 -.LBB3_8: - sar r15, 5 - cmp r14, 32 - jl .LBB3_12 -# %bb.9: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB3_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB3_9: + sub r12, rax + je .LBB3_153 +# %bb.10: + add r15, 1 +.LBB3_11: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_15 +# %bb.12: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setne bl movzx eax, byte ptr [rsi + 2] cmp al, byte ptr [rdx + 2] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 3] cmp al, byte ptr [rdx + 3] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 4] cmp al, byte ptr [rdx + 4] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 5] cmp al, byte ptr [rdx + 5] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 6] cmp al, byte ptr [rdx + 6] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setne r15b + setne r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 9] cmp al, byte ptr [rdx + 9] setne dil @@ -18260,19 +18789,19 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setne r14b + setne r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 14] cmp al, byte ptr [rdx + 14] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 15] cmp al, byte ptr [rdx + 15] setne r8b movzx eax, byte ptr [rsi + 16] cmp al, byte ptr [rdx + 16] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 17] cmp al, byte ptr [rdx + 17] setne r12b @@ -18281,148 +18810,147 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r13b movzx eax, byte ptr [rsi + 19] cmp al, byte ptr [rdx + 19] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 20] cmp al, byte ptr [rdx + 20] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 21] cmp al, byte ptr [rdx + 21] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 22] cmp al, byte ptr [rdx + 22] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 23] cmp al, byte ptr [rdx + 23] setne r9b movzx eax, byte ptr [rsi + 24] cmp al, byte ptr [rdx + 24] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 25] cmp al, byte ptr [rdx + 25] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 26] cmp al, byte ptr [rdx + 26] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 27] cmp al, byte ptr [rdx + 27] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 28] cmp al, byte ptr [rdx + 28] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 29] cmp al, byte ptr [rdx + 29] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 30] cmp al, byte ptr [rdx + 30] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 31] add rsi, 32 cmp al, byte ptr [rdx + 31] setne cl add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload shl bl, 2 or bl, al mov eax, ebx add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r10b, 2 or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al mov edi, ebx shl r11b, 3 or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload shl dil, 6 shl r8b, 7 or r8b, dil - or r15b, bl + or r14b, bl or r8b, al add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 3 or al, r13b mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], r8b + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB3_10 -# %bb.11: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB3_12: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.13: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB3_13 +# %bb.14: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB3_15: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB3_14: # =>This Inner Loop Header: Depth=1 +.LBB3_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -18430,7 +18958,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -18438,98 +18967,114 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_14 - jmp .LBB3_123 -.LBB3_30: + cmp r12, r8 + jne .LBB3_17 + jmp .LBB3_153 +.LBB3_36: cmp edi, 7 - je .LBB3_90 -# %bb.31: + je .LBB3_111 +# %bb.37: cmp edi, 8 - jne .LBB3_123 -# %bb.32: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_36 -# %bb.33: - cdqe + jne .LBB3_153 +# %bb.38: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_41: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_34 -# %bb.35: - add r12, 1 -.LBB3_36: - sar r15, 5 - cmp r14, 32 - jl .LBB3_40 -# %bb.37: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB3_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB3_43: + sub r12, r8 + je .LBB3_153 +# %bb.44: + add r15, 1 +.LBB3_45: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_49 +# %bb.46: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill mov rax, qword ptr [rsi + 24] cmp rax, qword ptr [rdx + 24] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill mov rax, qword ptr [rsi + 32] cmp rax, qword ptr [rdx + 32] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill mov rax, qword ptr [rsi + 40] cmp rax, qword ptr [rdx + 40] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill mov rax, qword ptr [rsi + 48] cmp rax, qword ptr [rdx + 48] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] setne r13b mov rax, qword ptr [rsi + 64] cmp rax, qword ptr [rdx + 64] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setne r8b + setne dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setne r11b @@ -18538,21 +19083,21 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r15b mov rax, qword ptr [rsi + 96] cmp rax, qword ptr [rdx + 96] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill mov rax, qword ptr [rsi + 112] cmp rax, qword ptr [rdx + 112] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill mov rax, qword ptr [rsi + 120] cmp rax, qword ptr [rdx + 120] - setne dil + setne r8b mov rax, qword ptr [rsi + 128] mov rbx, qword ptr [rsi + 136] cmp rax, qword ptr [rdx + 128] mov rax, qword ptr [rsi + 144] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 136] mov rbx, qword ptr [rsi + 152] setne r10b @@ -18563,144 +19108,144 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 mov rbx, qword ptr [rsi + 168] setne r12b cmp rax, qword ptr [rdx + 160] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 168] mov rax, qword ptr [rsi + 176] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setne r9b cmp rax, qword ptr [rdx + 192] mov rax, qword ptr [rsi + 200] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 224] mov rax, qword ptr [rsi + 232] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 232] mov rax, qword ptr [rsi + 240] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 240] mov rax, qword ptr [rsi + 248] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload - shl al, 4 + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_38 -# %bb.39: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_40: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.41: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_47 +# %bb.48: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_49: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB3_42: # =>This Inner Loop Header: Depth=1 +.LBB3_51: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -18708,7 +19253,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -18716,92 +19262,108 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_42 - jmp .LBB3_123 -.LBB3_68: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_72 -# %bb.69: - cdqe + cmp r12, r8 + jne .LBB3_51 + jmp .LBB3_153 +.LBB3_83: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_86: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_70 -# %bb.71: - add r12, 1 -.LBB3_72: - sar r15, 5 - cmp r14, 32 - jl .LBB3_76 -# %bb.73: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB3_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB3_88: + sub r12, r8 + je .LBB3_153 +# %bb.89: + add r15, 1 +.LBB3_90: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_94 +# %bb.91: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, word ptr [rsi + 6] cmp ax, word ptr [rdx + 6] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, word ptr [rsi + 8] cmp ax, word ptr [rdx + 8] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, word ptr [rsi + 10] cmp ax, word ptr [rdx + 10] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, word ptr [rsi + 12] cmp ax, word ptr [rdx + 12] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] setne r13b movzx eax, word ptr [rsi + 16] cmp ax, word ptr [rdx + 16] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setne r8b + setne dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setne r11b @@ -18810,21 +19372,21 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r15b movzx eax, word ptr [rsi + 24] cmp ax, word ptr [rdx + 24] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, word ptr [rsi + 28] cmp ax, word ptr [rdx + 28] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, word ptr [rsi + 30] cmp ax, word ptr [rdx + 30] - setne dil + setne r8b movzx eax, word ptr [rsi + 32] movzx ebx, word ptr [rsi + 34] cmp ax, word ptr [rdx + 32] movzx eax, word ptr [rsi + 36] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill cmp bx, word ptr [rdx + 34] movzx ebx, word ptr [rsi + 38] setne r10b @@ -18835,144 +19397,144 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 movzx ebx, word ptr [rsi + 42] setne r12b cmp ax, word ptr [rdx + 40] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill cmp bx, word ptr [rdx + 42] movzx eax, word ptr [rsi + 44] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setne r9b cmp ax, word ptr [rdx + 48] movzx eax, word ptr [rsi + 50] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill cmp ax, word ptr [rdx + 56] movzx eax, word ptr [rsi + 58] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill cmp ax, word ptr [rdx + 58] movzx eax, word ptr [rsi + 60] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp ax, word ptr [rdx + 60] movzx eax, word ptr [rsi + 62] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_74 -# %bb.75: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_76: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.77: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_92 +# %bb.93: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_94: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB3_78: # =>This Inner Loop Header: Depth=1 +.LBB3_96: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -18980,7 +19542,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -18988,92 +19551,108 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_78 - jmp .LBB3_123 -.LBB3_79: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_83 -# %bb.80: - cdqe + cmp r12, r8 + jne .LBB3_96 + jmp .LBB3_153 +.LBB3_97: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_81 -# %bb.82: - add r12, 1 -.LBB3_83: - sar r15, 5 - cmp r14, 32 - jl .LBB3_87 -# %bb.84: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB3_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB3_102: + sub r12, r8 + je .LBB3_153 +# %bb.103: + add r15, 1 +.LBB3_104: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_108 +# %bb.105: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, word ptr [rsi + 6] cmp ax, word ptr [rdx + 6] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, word ptr [rsi + 8] cmp ax, word ptr [rdx + 8] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, word ptr [rsi + 10] cmp ax, word ptr [rdx + 10] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, word ptr [rsi + 12] cmp ax, word ptr [rdx + 12] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] setne r13b movzx eax, word ptr [rsi + 16] cmp ax, word ptr [rdx + 16] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setne r8b + setne dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setne r11b @@ -19082,21 +19661,21 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r15b movzx eax, word ptr [rsi + 24] cmp ax, word ptr [rdx + 24] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, word ptr [rsi + 28] cmp ax, word ptr [rdx + 28] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, word ptr [rsi + 30] cmp ax, word ptr [rdx + 30] - setne dil + setne r8b movzx eax, word ptr [rsi + 32] movzx ebx, word ptr [rsi + 34] cmp ax, word ptr [rdx + 32] movzx eax, word ptr [rsi + 36] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill cmp bx, word ptr [rdx + 34] movzx ebx, word ptr [rsi + 38] setne r10b @@ -19107,144 +19686,144 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 movzx ebx, word ptr [rsi + 42] setne r12b cmp ax, word ptr [rdx + 40] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill cmp bx, word ptr [rdx + 42] movzx eax, word ptr [rsi + 44] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setne r9b cmp ax, word ptr [rdx + 48] movzx eax, word ptr [rsi + 50] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill cmp ax, word ptr [rdx + 56] movzx eax, word ptr [rsi + 58] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill cmp ax, word ptr [rdx + 58] movzx eax, word ptr [rsi + 60] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp ax, word ptr [rdx + 60] movzx eax, word ptr [rsi + 62] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_85 -# %bb.86: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_87: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.88: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_106 +# %bb.107: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_108: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB3_89: # =>This Inner Loop Header: Depth=1 +.LBB3_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -19252,7 +19831,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -19260,92 +19840,108 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_89 - jmp .LBB3_123 -.LBB3_101: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_105 -# %bb.102: - cdqe + cmp r12, r8 + jne .LBB3_110 + jmp .LBB3_153 +.LBB3_125: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_103 -# %bb.104: - add r12, 1 -.LBB3_105: - sar r15, 5 - cmp r14, 32 - jl .LBB3_109 -# %bb.106: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB3_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB3_130: + sub r12, r8 + je .LBB3_153 +# %bb.131: + add r15, 1 +.LBB3_132: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_136 +# %bb.133: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill mov rax, qword ptr [rsi + 24] cmp rax, qword ptr [rdx + 24] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill mov rax, qword ptr [rsi + 32] cmp rax, qword ptr [rdx + 32] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill mov rax, qword ptr [rsi + 40] cmp rax, qword ptr [rdx + 40] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill mov rax, qword ptr [rsi + 48] cmp rax, qword ptr [rdx + 48] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] setne r13b mov rax, qword ptr [rsi + 64] cmp rax, qword ptr [rdx + 64] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setne r8b + setne dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setne r11b @@ -19354,21 +19950,21 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r15b mov rax, qword ptr [rsi + 96] cmp rax, qword ptr [rdx + 96] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill mov rax, qword ptr [rsi + 112] cmp rax, qword ptr [rdx + 112] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill mov rax, qword ptr [rsi + 120] cmp rax, qword ptr [rdx + 120] - setne dil + setne r8b mov rax, qword ptr [rsi + 128] mov rbx, qword ptr [rsi + 136] cmp rax, qword ptr [rdx + 128] mov rax, qword ptr [rsi + 144] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 136] mov rbx, qword ptr [rsi + 152] setne r10b @@ -19379,144 +19975,144 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 mov rbx, qword ptr [rsi + 168] setne r12b cmp rax, qword ptr [rdx + 160] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 168] mov rax, qword ptr [rsi + 176] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setne r9b cmp rax, qword ptr [rdx + 192] mov rax, qword ptr [rsi + 200] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 224] mov rax, qword ptr [rsi + 232] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 232] mov rax, qword ptr [rsi + 240] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 240] mov rax, qword ptr [rsi + 248] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_107 -# %bb.108: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_109: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.110: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_134 +# %bb.135: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_136: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.137: xor ecx, ecx .p2align 4, 0x90 -.LBB3_111: # =>This Inner Loop Header: Depth=1 +.LBB3_138: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -19524,7 +20120,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -19532,94 +20129,110 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_111 - jmp .LBB3_123 -.LBB3_112: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_116 -# %bb.113: - movsxd r10, eax + cmp r12, r8 + jne .LBB3_138 + jmp .LBB3_153 +.LBB3_139: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_144 +# %bb.141: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB3_114: # =>This Inner Loop Header: Depth=1 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - vucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - setp cl +.LBB3_142: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + vmovss xmm0, dword ptr [rsi + 4*r14] # xmm0 = mem[0],zero,zero,zero + vucomiss xmm0, dword ptr [rdx + 4*r14] + setp r10b setne bl - or bl, cl + or bl, r10b neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d + lea eax, [8*rdi] + sub ecx, eax mov eax, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB3_114 -# %bb.115: - add r12, 1 -.LBB3_116: - sar r15, 5 - cmp r14, 32 - jl .LBB3_120 -# %bb.117: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -4 + cmp r8, r14 + jne .LBB3_142 +# %bb.143: + sub rsi, r11 + sub rdx, r11 +.LBB3_144: + sub r12, r8 + je .LBB3_153 +# %bb.145: + add r15, 1 +.LBB3_146: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_150 +# %bb.147: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx] vmovss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero setp al setne cl or cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill + mov byte ptr [rsp + 29], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 4] setp al setne cl or cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill + mov byte ptr [rsp + 22], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 8] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 8] setp al setne cl or cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill + mov byte ptr [rsp + 28], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 12] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 12] setp al setne cl or cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill + mov byte ptr [rsp + 31], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 16] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 16] setp al setne cl or cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill + mov byte ptr [rsp + 30], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 20] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 20] setp al @@ -19635,13 +20248,13 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill + mov byte ptr [rsp + 12], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 32] setp al setne cl or cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill + mov byte ptr [rsp + 27], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 36] setp al @@ -19652,78 +20265,78 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill + mov byte ptr [rsp + 26], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 44] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 44] setp al setne cl or cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill + mov byte ptr [rsp + 25], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 48] setp al setne cl or cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 11], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 52] setp al setne cl or cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 56] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 56] setp al setne cl or cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill + mov byte ptr [rsp + 21], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 60] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 60] setp al setne cl or cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill + mov byte ptr [rsp + 20], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 64] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 64] setp al setne cl or cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill + mov byte ptr [rsp + 23], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 68] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 68] setp al setne cl or cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill + mov byte ptr [rsp + 19], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 72] setp al setne cl or cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill + mov byte ptr [rsp + 18], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 76] setp al - setne r11b - or r11b, al + setne r15b + or r15b, al vmovss xmm0, dword ptr [rsi + 80] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 80] setp al setne cl or cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 17], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 84] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 84] setp al setne cl or cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 88] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 88] setp al setne cl or cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill + mov byte ptr [rsp + 14], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 92] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 92] setp al @@ -19734,35 +20347,34 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill + mov byte ptr [rsp + 15], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 100] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 100] setp al - setne cl - or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + setne r12b + or r12b, al vmovss xmm0, dword ptr [rsi + 104] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 104] setp al - setne r15b - or r15b, al + setne r14b + or r14b, al vmovss xmm0, dword ptr [rsi + 108] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 108] setp al - setne r14b - or r14b, al + setne r11b + or r11b, al vmovss xmm0, dword ptr [rsi + 112] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 112] setp al setne cl or cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 13], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 116] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 116] setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vmovss xmm0, dword ptr [rsi + 120] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 120] setp al @@ -19774,110 +20386,108 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setp al setne r8b or r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload shl dil, 5 shl r13b, 6 or r13b, dil mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload shl cl, 2 or cl, al mov eax, ebx add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload + add al, byte ptr [rsp + 27] # 1-byte Folded Reload mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 or al, r13b mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload shl bl, 3 or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 6 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload shl cl, 2 or cl, bl - shl r11b, 3 - or r11b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload shl bl, 4 - or bl, r11b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r11d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r11b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 or cl, r13b - or al, dil + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload shl r10b, 7 or r10b, cl or r10b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r15b, 2 - or r15b, cl - shl r14b, 3 - or r14b, r15b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload shl cl, 4 - or cl, r14b - mov byte ptr [r12], r11b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 shl r9b, 6 or r9b, bl - mov byte ptr [r12 + 1], al + mov byte ptr [r15 + 1], dil shl r8b, 7 or r8b, r9b or r8b, cl - mov byte ptr [r12 + 2], r10b - mov byte ptr [r12 + 3], r8b + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB3_118 -# %bb.119: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB3_120: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.121: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_148 +# %bb.149: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_150: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.151: xor ecx, ecx .p2align 4, 0x90 -.LBB3_122: # =>This Inner Loop Header: Depth=1 +.LBB3_152: # =>This Inner Loop Header: Depth=1 lea r9, [rcx + 1] vmovss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 4*rcx] @@ -19887,7 +20497,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg al mov rdi, rcx shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] xor al, r8b and cl, 7 mov bl, 1 @@ -19895,89 +20506,112 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl bl, cl and bl, al xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r15 + rdi], bl mov rcx, r9 - cmp r14, r9 - jne .LBB3_122 - jmp .LBB3_123 -.LBB3_57: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_61 -# %bb.58: - cdqe - .p2align 4, 0x90 -.LBB3_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setne r10b - neg r10b - lea rdi, [rax + 7] + cmp r12, r9 + jne .LBB3_152 + jmp .LBB3_153 +.LBB3_69: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB3_74 +# %bb.71: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB3_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setne r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB3_59 -# %bb.60: - add r12, 1 -.LBB3_61: - sar r15, 5 - cmp r14, 32 - jl .LBB3_65 -# %bb.62: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB3_72 +# %bb.73: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB3_74: + sub r12, rax + je .LBB3_153 +# %bb.75: + add r15, 1 +.LBB3_76: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_80 +# %bb.77: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setne bl movzx eax, byte ptr [rsi + 2] cmp al, byte ptr [rdx + 2] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 3] cmp al, byte ptr [rdx + 3] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 4] cmp al, byte ptr [rdx + 4] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 5] cmp al, byte ptr [rdx + 5] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 6] cmp al, byte ptr [rdx + 6] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setne r15b + setne r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 9] cmp al, byte ptr [rdx + 9] setne dil @@ -19989,19 +20623,19 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setne r14b + setne r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 14] cmp al, byte ptr [rdx + 14] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 15] cmp al, byte ptr [rdx + 15] setne r8b movzx eax, byte ptr [rsi + 16] cmp al, byte ptr [rdx + 16] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 17] cmp al, byte ptr [rdx + 17] setne r12b @@ -20010,148 +20644,147 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r13b movzx eax, byte ptr [rsi + 19] cmp al, byte ptr [rdx + 19] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 20] cmp al, byte ptr [rdx + 20] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 21] cmp al, byte ptr [rdx + 21] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 22] cmp al, byte ptr [rdx + 22] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 23] cmp al, byte ptr [rdx + 23] setne r9b movzx eax, byte ptr [rsi + 24] cmp al, byte ptr [rdx + 24] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 25] cmp al, byte ptr [rdx + 25] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 26] cmp al, byte ptr [rdx + 26] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 27] cmp al, byte ptr [rdx + 27] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 28] cmp al, byte ptr [rdx + 28] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 29] cmp al, byte ptr [rdx + 29] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 30] cmp al, byte ptr [rdx + 30] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 31] add rsi, 32 cmp al, byte ptr [rdx + 31] setne cl add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload shl bl, 2 or bl, al mov eax, ebx add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r10b, 2 or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al mov edi, ebx shl r11b, 3 or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload shl dil, 6 shl r8b, 7 or r8b, dil - or r15b, bl + or r14b, bl or r8b, al add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 3 or al, r13b mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], r8b + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB3_63 -# %bb.64: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB3_65: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.66: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB3_78 +# %bb.79: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB3_80: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.81: xor ecx, ecx .p2align 4, 0x90 -.LBB3_67: # =>This Inner Loop Header: Depth=1 +.LBB3_82: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -20159,7 +20792,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -20167,92 +20801,108 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_67 - jmp .LBB3_123 -.LBB3_90: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_94 -# %bb.91: - cdqe + cmp r12, r8 + jne .LBB3_82 + jmp .LBB3_153 +.LBB3_111: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_92 -# %bb.93: - add r12, 1 -.LBB3_94: - sar r15, 5 - cmp r14, 32 - jl .LBB3_98 -# %bb.95: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB3_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB3_116: + sub r12, r8 + je .LBB3_153 +# %bb.117: + add r15, 1 +.LBB3_118: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_122 +# %bb.119: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill mov eax, dword ptr [rsi + 12] cmp eax, dword ptr [rdx + 12] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill mov eax, dword ptr [rsi + 16] cmp eax, dword ptr [rdx + 16] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill mov eax, dword ptr [rsi + 20] cmp eax, dword ptr [rdx + 20] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill mov eax, dword ptr [rsi + 24] cmp eax, dword ptr [rdx + 24] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] setne r13b mov eax, dword ptr [rsi + 32] cmp eax, dword ptr [rdx + 32] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - setne r8b + setne dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] setne r11b @@ -20261,21 +20911,21 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 setne r15b mov eax, dword ptr [rsi + 48] cmp eax, dword ptr [rdx + 48] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill mov eax, dword ptr [rsi + 56] cmp eax, dword ptr [rdx + 56] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill mov eax, dword ptr [rsi + 60] cmp eax, dword ptr [rdx + 60] - setne dil + setne r8b mov eax, dword ptr [rsi + 64] mov ebx, dword ptr [rsi + 68] cmp eax, dword ptr [rdx + 64] mov eax, dword ptr [rsi + 72] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 68] mov ebx, dword ptr [rsi + 76] setne r10b @@ -20286,144 +20936,144 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 mov ebx, dword ptr [rsi + 84] setne r12b cmp eax, dword ptr [rdx + 80] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 84] mov eax, dword ptr [rsi + 88] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] setne r9b cmp eax, dword ptr [rdx + 96] mov eax, dword ptr [rsi + 100] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 112] mov eax, dword ptr [rsi + 116] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 116] mov eax, dword ptr [rsi + 120] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 120] mov eax, dword ptr [rsi + 124] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_96 -# %bb.97: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_98: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.99: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_120 +# %bb.121: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_122: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.123: xor ecx, ecx .p2align 4, 0x90 -.LBB3_100: # =>This Inner Loop Header: Depth=1 +.LBB3_124: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -20431,7 +21081,8 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -20439,11 +21090,11 @@ comparison_not_equal_arr_arr_avx2: # @comparison_not_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_100 -.LBB3_123: + cmp r12, r8 + jne .LBB3_124 +.LBB3_153: lea rsp, [rbp - 40] pop rbx pop r12 @@ -20487,90 +21138,104 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 and rsp, -32 sub rsp, 1280 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov r11, rcx + mov r15, r8 + mov r14, rcx cmp edi, 6 - jg .LBB4_13 + jg .LBB4_19 # %bb.1: cmp edi, 3 - jle .LBB4_25 + jle .LBB4_36 # %bb.2: cmp edi, 4 - je .LBB4_48 + je .LBB4_59 # %bb.3: cmp edi, 5 - je .LBB4_56 + je .LBB4_73 # %bb.4: cmp edi, 6 - jne .LBB4_165 + jne .LBB4_189 # %bb.5: mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_9 + je .LBB4_11 # %bb.6: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_9 +# %bb.7: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_7: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB4_8: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_7 -# %bb.8: - add r11, 1 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_8 .LBB4_9: - sar r15, 5 - cmp r10, 32 - jl .LBB4_100 + sub r15, r8 + je .LBB4_189 # %bb.10: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + add r14, 1 +.LBB4_11: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB4_15 +# %bb.12: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_11: # =>This Inner Loop Header: Depth=1 +.LBB4_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp dword ptr [rsi], r13d - setne byte ptr [rsp + 144] # 1-byte Folded Spill + setne byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d setne r10b cmp dword ptr [rsi + 8], r13d setne r14b cmp dword ptr [rsi + 12], r13d - setne byte ptr [rsp + 152] # 1-byte Folded Spill + setne byte ptr [rsp + 104] # 1-byte Folded Spill cmp dword ptr [rsi + 16], r13d - setne byte ptr [rsp + 136] # 1-byte Folded Spill + setne byte ptr [rsp + 144] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - setne byte ptr [rsp + 96] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d setne al cmp dword ptr [rsi + 28], r13d setne bl cmp dword ptr [rsi + 32], r13d - setne byte ptr [rsp + 160] # 1-byte Folded Spill + setne byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d setne dil cmp dword ptr [rsi + 40], r13d @@ -20582,206 +21247,261 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 cmp dword ptr [rsi + 52], r13d setne r12b cmp dword ptr [rsi + 56], r13d - setne byte ptr [rsp + 112] # 1-byte Folded Spill + setne byte ptr [rsp + 120] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - setne cl + setne dl cmp dword ptr [rsi + 64], r13d - setne byte ptr [rsp + 80] # 1-byte Folded Spill + setne byte ptr [rsp + 160] # 1-byte Folded Spill cmp dword ptr [rsi + 68], r13d - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setne byte ptr [rsp + 136] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - setne byte ptr [rsp + 72] # 1-byte Folded Spill + setne byte ptr [rsp + 152] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d - setne byte ptr [rsp + 88] # 1-byte Folded Spill + setne byte ptr [rsp + 168] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + setne byte ptr [rsp + 72] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d setne r15b cmp dword ptr [rsi + 96], r13d - setne byte ptr [rsp + 32] # 1-byte Folded Spill + setne byte ptr [rsp + 48] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 80] # 1-byte Folded Spill cmp dword ptr [rsi + 104], r13d - setne byte ptr [rsp + 48] # 1-byte Folded Spill + setne byte ptr [rsp + 32] # 1-byte Folded Spill cmp dword ptr [rsi + 108], r13d - setne byte ptr [rsp + 56] # 1-byte Folded Spill + setne byte ptr [rsp + 40] # 1-byte Folded Spill cmp dword ptr [rsi + 112], r13d - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d setne byte ptr [rsp + 320] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d + setne byte ptr [rsp + 288] # 1-byte Folded Spill cmp dword ptr [rsi + 120], r13d setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp dword ptr [rsi + 124], r13d - setne dl + setne cl add r10b, r10b - add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add dil, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 128 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_11 -# %bb.12: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_101 - jmp .LBB4_165 -.LBB4_13: - cmp edi, 8 - jle .LBB4_38 + add r14, 4 + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill + jne .LBB4_13 # %bb.14: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_15: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.16: + or rax, 1 + cmp r15, rax + je .LBB4_129 +# %bb.17: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB4_18: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d + setne al + neg al + mov rdi, r11 + shr rdi, 3 + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + setne al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r10, r11 + jne .LBB4_18 + jmp .LBB4_179 +.LBB4_19: + cmp edi, 8 + jle .LBB4_43 +# %bb.20: cmp edi, 9 - je .LBB4_64 -# %bb.15: + je .LBB4_86 +# %bb.21: cmp edi, 11 - je .LBB4_72 -# %bb.16: + je .LBB4_99 +# %bb.22: cmp edi, 12 - jne .LBB4_165 -# %bb.17: - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jne .LBB4_189 +# %bb.23: + mov r12, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero sub r9d, eax - je .LBB4_21 -# %bb.18: - movsxd rax, r9d + je .LBB4_29 +# %bb.24: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_27 +# %bb.25: + movsxd rdx, r9d + vmovq xmm0, r12 + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_19: # =>This Inner Loop Header: Depth=1 - vucomisd xmm0, qword ptr [rsi] - lea rsi, [rsi + 8] +.LBB4_26: # =>This Inner Loop Header: Depth=1 + vucomisd xmm0, qword ptr [rcx] + lea rsi, [rcx + 8] setp cl - setne dl - or dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + setne bl + or bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_19 -# %bb.20: - add r11, 1 -.LBB4_21: - sar r15, 5 - cmp r10, 32 - jl .LBB4_104 -# %bb.22: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_26 +.LBB4_27: + sub r15, r8 + je .LBB4_189 +# %bb.28: + add r14, 1 +.LBB4_29: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB4_33 +# %bb.30: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 184], r12 # 8-byte Spill + vmovq xmm0, r12 + mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_23: # =>This Inner Loop Header: Depth=1 +.LBB4_31: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill vucomisd xmm0, qword ptr [rsi] setp al setne cl @@ -20789,31 +21509,32 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 mov byte ptr [rsp + 32], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 8] setp al - setne bl - or bl, al - vucomisd xmm0, qword ptr [rsi + 16] - setp al setne r13b or r13b, al + vucomisd xmm0, qword ptr [rsi + 16] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 24] setp al setne cl or cl, al - mov byte ptr [rsp + 288], cl # 1-byte Spill + mov byte ptr [rsp + 320], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 32] setp al setne cl or cl, al - mov byte ptr [rsp + 320], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 40] setp al - setne dil - or dil, al + setne r12b + or r12b, al vucomisd xmm0, qword ptr [rsi + 48] setp al setne cl or cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 56] setp al setne cl @@ -20823,46 +21544,46 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 72] setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 80] setp al setne cl or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 88] setp al - setne cl - or cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + setne bl + or bl, al vucomisd xmm0, qword ptr [rsi + 96] setp al setne cl or cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 288], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 104] setp al setne cl or cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 112] setp al - setne dl - or dl, al + setne cl + or cl, al + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 120] setp al setne cl or cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 128] setp al setne cl or cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 168], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 136] setp al setne cl @@ -20872,676 +21593,566 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 setp al setne cl or cl, al + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 152] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 128], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 160] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 120], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 168] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 160], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 104], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 176] setp al - setne r12b - or r12b, al + setne r15b + or r15b, al vucomisd xmm0, qword ptr [rsi + 184] setp al setne r10b or r10b, al vucomisd xmm0, qword ptr [rsi + 192] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 112], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 96], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 200] setp al - setne r15b - or r15b, al + setne r11b + or r11b, al vucomisd xmm0, qword ptr [rsi + 208] setp al - setne r14b - or r14b, al + setne r9b + or r9b, al vucomisd xmm0, qword ptr [rsi + 216] setp al - setne r11b - or r11b, al + setne r8b + or r8b, al vucomisd xmm0, qword ptr [rsi + 224] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 152], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 176], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 232] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 144], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 88], cl # 1-byte Spill vucomisd xmm0, qword ptr [rsi + 240] setp al - setne r9b - or r9b, al + setne dil + or dil, al vucomisd xmm0, qword ptr [rsi + 248] setp al - setne r8b - or r8b, al - add bl, bl - add bl, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 5 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 6 - or al, dil - mov edi, eax - shl r13b, 2 - or r13b, bl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 56] # 1-byte Folded Reload - mov ebx, eax + setne dl + or dl, al + add r13b, r13b + add r13b, byte ptr [rsp + 32] # 1-byte Folded Reload + mov eax, r13d + shl r12b, 5 + movzx r13d, byte ptr [rsp + 72] # 1-byte Folded Reload + shl r13b, 6 + or r13b, r12b + movzx r12d, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 80] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 - or al, dil + or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 3 - or al, r13b - mov r13d, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov edi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 3 + or al, r12b + shl bl, 3 + or bl, cl + movzx r13d, byte ptr [rsp + 48] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 + or al, bl + mov byte ptr [rsp + 288], al # 1-byte Spill + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 5 + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 6 + or al, cl + mov ecx, eax + movzx r14d, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r14b, 7 + or r14b, al + movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 168] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 2 + or bl, cl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + mov r12d, ecx + mov rcx, qword ptr [rsp + 272] # 8-byte Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload or al, r13b - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 4 - or bl, dil - movzx edi, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dil, 5 - shl dl, 6 - or dl, dil - movzx r13d, byte ptr [rsp + 80] # 1-byte Folded Reload - shl r13b, 7 - or r13b, dl - movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 72] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 3 - or dl, cl - mov ecx, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 4 - or dl, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - or cl, al - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 5 - shl r12b, 6 - or r12b, al - or r13b, bl + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl bl, 5 + shl r15b, 6 + or r15b, bl + or r14b, byte ptr [rsp + 288] # 1-byte Folded Reload shl r10b, 7 + or r10b, r15b or r10b, r12b - or r10b, dl - add r15b, r15b - add r15b, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r15b - shl r11b, 3 - or r11b, r14b - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload - shl al, 4 - or al, r11b - mov ebx, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], cl - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 5 - shl r9b, 6 - or r9b, dl - mov byte ptr [rax + 1], r13b - shl r8b, 7 + add r11b, r11b + add r11b, byte ptr [rsp + 96] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 or r8b, r9b - or r8b, bl - mov byte ptr [rax + 2], r10b - mov byte ptr [rax + 3], r8b + movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload + shl bl, 4 + or bl, r8b + mov r8d, ebx + mov byte ptr [rcx], al + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl bl, 5 + shl dil, 6 + or dil, bl + mov byte ptr [rcx + 1], r14b + shl dl, 7 + or dl, dil + or dl, r8b + mov byte ptr [rcx + 2], r10b + mov byte ptr [rcx + 3], dl add rsi, 256 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_23 -# %bb.24: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_105 - jmp .LBB4_165 -.LBB4_25: + add rcx, 4 + mov r14, rcx + add qword ptr [rsp + 192], -1 # 8-byte Folded Spill + jne .LBB4_31 +# %bb.32: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12, qword ptr [rsp + 184] # 8-byte Reload + mov rax, qword ptr [rsp + 200] # 8-byte Reload +.LBB4_33: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.34: + vmovq xmm0, r12 + or rax, 1 + cmp r15, rax + jne .LBB4_160 +# %bb.35: + xor r11d, r11d + jmp .LBB4_162 +.LBB4_36: cmp edi, 2 - je .LBB4_80 -# %bb.26: + je .LBB4_112 +# %bb.37: cmp edi, 3 - jne .LBB4_165 -# %bb.27: - mov r14b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jne .LBB4_189 +# %bb.38: + mov r12b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_131 -# %bb.28: - movsxd rax, r9d - mov r13, r11 + je .LBB4_130 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_132 +# %bb.40: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB4_29: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r14b - lea rsi, [rsi + 1] - setne dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r13 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 +.LBB4_41: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r12b + setne bl + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB4_41 +# %bb.42: + sub r15, r8 + jne .LBB4_133 + jmp .LBB4_189 +.LBB4_43: + cmp edi, 7 + je .LBB4_117 +# %bb.44: + cmp edi, 8 + jne .LBB4_189 +# %bb.45: + mov r13, qword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB4_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_49 +# %bb.47: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB4_48: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] xor bl, r9b - mov byte ptr [r13 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_29 -# %bb.30: - add r13, 1 - sar r15, 5 - cmp r10, 32 - jl .LBB4_132 -.LBB4_31: + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_48 +.LBB4_49: + sub r15, r8 + je .LBB4_189 +# %bb.50: + add r14, 1 +.LBB4_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - mov dword ptr [rsp + 28], r14d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 392], r15 # 8-byte Spill - jb .LBB4_34 -# %bb.32: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp r13, rax - jae .LBB4_166 -# %bb.33: - lea rax, [4*r15] - add rax, r13 - cmp rsi, rax - jae .LBB4_166 -.LBB4_34: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 376], r13 # 8-byte Spill -.LBB4_35: - mov r13, r15 - sub r13, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 144], r13 # 8-byte Spill + jl .LBB4_55 +# %bb.52: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_36: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b - setne r8b - cmp byte ptr [r12 + 2], r14b - setne r15b - cmp byte ptr [r12 + 3], r14b - setne r13b - cmp byte ptr [r12 + 4], r14b - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b +.LBB4_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill + cmp qword ptr [rsi], r13 + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp qword ptr [rsi + 8], r13 + setne r10b + cmp qword ptr [rsi + 16], r13 + setne r14b + cmp qword ptr [rsi + 24], r13 + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + setne byte ptr [rsp + 144] # 1-byte Folded Spill + cmp qword ptr [rsi + 40], r13 + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp qword ptr [rsi + 48], r13 setne al - cmp byte ptr [r12 + 7], r14b - setne r11b - cmp byte ptr [r12 + 8], r14b - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b - setne dl - cmp byte ptr [r12 + 10], r14b - setne sil - cmp byte ptr [r12 + 11], r14b + cmp qword ptr [rsi + 56], r13 + setne bl + cmp qword ptr [rsi + 64], r13 + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp qword ptr [rsi + 72], r13 setne dil - cmp byte ptr [r12 + 12], r14b - setne r10b - cmp byte ptr [r12 + 13], r14b - setne r12b - cmp byte ptr [rcx + 14], r14b - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b + cmp qword ptr [rsi + 80], r13 + setne r8b + cmp qword ptr [rsi + 88], r13 setne r9b - cmp byte ptr [rcx + 16], r14b - setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b + cmp qword ptr [rsi + 96], r13 + setne r11b + cmp qword ptr [rsi + 104], r13 + setne r12b + cmp qword ptr [rsi + 112], r13 setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b + cmp qword ptr [rsi + 120], r13 + setne dl + cmp qword ptr [rsi + 128], r13 + setne byte ptr [rsp + 160] # 1-byte Folded Spill + cmp qword ptr [rsi + 136], r13 + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp qword ptr [rsi + 144], r13 setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b + cmp qword ptr [rsi + 152], r13 + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp qword ptr [rsi + 160], r13 + setne byte ptr [rsp + 168] # 1-byte Folded Spill + cmp qword ptr [rsi + 168], r13 setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - setne r14b - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 24], bl - setne byte ptr [rsp + 272] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 25], bl - setne byte ptr [rsp + 88] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 26], bl - setne byte ptr [rsp + 96] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 27], bl - setne byte ptr [rsp + 104] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 28], bl - setne byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 29], bl - setne byte ptr [rsp + 48] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 30], bl - setne byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 31], bl - setne bl - add r8b, r8b - add r8b, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, r8b - add dl, dl - add dl, byte ptr [rsp + 288] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b - shl sil, 2 - or sil, dl - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - shl dil, 3 - or dil, sil - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, dil - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 152] # 1-byte Folded Reload - shl sil, 6 - shl r9b, 7 - or r9b, sil - or r11b, dl - or r9b, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 320] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov rsi, qword ptr [rsp + 376] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 272] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 6 - shl bl, 7 - or bl, dl - or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 376], rsi # 8-byte Spill - add qword ptr [rsp + 144], -1 # 8-byte Folded Spill - jne .LBB4_36 -# %bb.37: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 392] # 8-byte Reload - jmp .LBB4_133 -.LBB4_38: - cmp edi, 7 - je .LBB4_92 -# %bb.39: - cmp edi, 8 - jne .LBB4_165 -# %bb.40: - mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB4_44 -# %bb.41: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB4_42: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_42 -# %bb.43: - add r11, 1 -.LBB4_44: - sar r15, 5 - cmp r10, 32 - jl .LBB4_107 -# %bb.45: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB4_46: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r11 # 8-byte Spill - cmp qword ptr [rsi], r13 - setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 - setne r10b - cmp qword ptr [rsi + 16], r13 - setne r14b - cmp qword ptr [rsi + 24], r13 - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 - setne al - cmp qword ptr [rsi + 56], r13 - setne bl - cmp qword ptr [rsi + 64], r13 - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 72], r13 - setne dil - cmp qword ptr [rsi + 80], r13 - setne r8b - cmp qword ptr [rsi + 88], r13 - setne r9b - cmp qword ptr [rsi + 96], r13 - setne r11b - cmp qword ptr [rsi + 104], r13 - setne r12b - cmp qword ptr [rsi + 112], r13 - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp qword ptr [rsi + 120], r13 - setne cl - cmp qword ptr [rsi + 128], r13 - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 136], r13 - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp qword ptr [rsi + 152], r13 - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp qword ptr [rsi + 160], r13 - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp qword ptr [rsi + 168], r13 - setne byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - setne byte ptr [rsp + 64] # 1-byte Folded Spill + setne byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 setne r15b cmp qword ptr [rsi + 192], r13 - setne byte ptr [rsp + 32] # 1-byte Folded Spill + setne byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 - setne byte ptr [rsp + 48] # 1-byte Folded Spill + setne byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - setne byte ptr [rsp + 56] # 1-byte Folded Spill + setne byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp qword ptr [rsi + 232], r13 setne byte ptr [rsp + 320] # 1-byte Folded Spill + cmp qword ptr [rsi + 232], r13 + setne byte ptr [rsp + 288] # 1-byte Folded Spill cmp qword ptr [rsi + 240], r13 setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - setne dl + setne cl add r10b, r10b - add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add dil, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - mov r11, qword ptr [rsp + 272] # 8-byte Reload - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r11 + 1], cl + mov byte ptr [r14 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], dl + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 256 - add r11, 4 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_46 -# %bb.47: - mov r14, r11 - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_108 - jmp .LBB4_165 -.LBB4_48: + add r14, 4 + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill + jne .LBB4_53 +# %bb.54: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_55: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.56: + or rax, 1 + cmp r15, rax + je .LBB4_98 +# %bb.57: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB4_58: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + setne al + neg al + mov rdi, r11 + shr rdi, 3 + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + setne al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r10, r11 + jne .LBB4_58 + jmp .LBB4_170 +.LBB4_59: movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_52 -# %bb.49: - movsxd rax, r9d + je .LBB4_65 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_63 +# %bb.61: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_50: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB4_62: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_50 -# %bb.51: - add r11, 1 -.LBB4_52: - sar r15, 5 - cmp r10, 32 - jl .LBB4_111 -# %bb.53: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_62 +.LBB4_63: + sub r15, r8 + je .LBB4_189 +# %bb.64: + add r14, 1 +.LBB4_65: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB4_69 +# %bb.66: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_54: # =>This Inner Loop Header: Depth=1 +.LBB4_67: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp word ptr [rsi], r13w setne al cmp word ptr [rsi + 2], r13w @@ -21549,17 +22160,17 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 cmp word ptr [rsi + 4], r13w setne r14b cmp word ptr [rsi + 6], r13w - setne byte ptr [rsp + 152] # 1-byte Folded Spill + setne byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - setne byte ptr [rsp + 136] # 1-byte Folded Spill + setne byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - setne byte ptr [rsp + 96] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w - setne byte ptr [rsp + 144] # 1-byte Folded Spill + setne byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 14], r13w setne bl cmp word ptr [rsi + 16], r13w - setne byte ptr [rsp + 160] # 1-byte Folded Spill + setne byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w setne dil cmp word ptr [rsi + 20], r13w @@ -21571,211 +22182,263 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 cmp word ptr [rsi + 26], r13w setne r12b cmp word ptr [rsi + 28], r13w - setne byte ptr [rsp + 112] # 1-byte Folded Spill + setne byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - setne cl + setne dl cmp word ptr [rsi + 32], r13w - setne byte ptr [rsp + 80] # 1-byte Folded Spill + setne byte ptr [rsp + 160] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp word ptr [rsi + 36], r13w setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [rsi + 36], r13w + setne byte ptr [rsp + 136] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - setne byte ptr [rsp + 72] # 1-byte Folded Spill + setne byte ptr [rsp + 152] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - setne byte ptr [rsp + 88] # 1-byte Folded Spill + setne byte ptr [rsp + 168] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp word ptr [rsi + 44], r13w setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp word ptr [rsi + 44], r13w + setne byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w setne r15b cmp word ptr [rsi + 48], r13w - setne byte ptr [rsp + 32] # 1-byte Folded Spill + setne byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 52], r13w - setne byte ptr [rsp + 48] # 1-byte Folded Spill + setne byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w - setne byte ptr [rsp + 56] # 1-byte Folded Spill + setne byte ptr [rsp + 40] # 1-byte Folded Spill cmp word ptr [rsi + 56], r13w - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp word ptr [rsi + 58], r13w setne byte ptr [rsp + 320] # 1-byte Folded Spill + cmp word ptr [rsi + 58], r13w + setne byte ptr [rsp + 288] # 1-byte Folded Spill cmp word ptr [rsi + 60], r13w setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp word ptr [rsi + 62], r13w - setne dl + setne cl add r10b, r10b or r10b, al - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add dil, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 64 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_54 -# %bb.55: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_112 - jmp .LBB4_165 -.LBB4_56: - movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB4_60 -# %bb.57: - movsxd rax, r9d + add r14, 4 + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill + jne .LBB4_67 +# %bb.68: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_69: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.70: + or rax, 1 + cmp r15, rax + je .LBB4_85 +# %bb.71: + mov r10, r8 + and r10, -2 + xor r11d, r11d .p2align 4, 0x90 -.LBB4_58: # =>This Inner Loop Header: Depth=1 +.LBB4_72: # =>This Inner Loop Header: Depth=1 cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_58 -# %bb.59: - add r11, 1 -.LBB4_60: - sar r15, 5 - cmp r10, 32 - jl .LBB4_115 -# %bb.61: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB4_62: # =>This Inner Loop Header: Depth=1 + setne al + neg al + mov rdi, r11 + shr rdi, 3 + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add r11, 2 + cmp word ptr [rsi + 2], r13w + lea rsi, [rsi + 4] + setne al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r10, r11 + jne .LBB4_72 + jmp .LBB4_166 +.LBB4_73: + movzx r13d, word ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB4_79 +# %bb.74: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_77 +# %bb.75: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB4_76: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_76 +.LBB4_77: + sub r15, r8 + je .LBB4_189 +# %bb.78: + add r14, 1 +.LBB4_79: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB4_83 +# %bb.80: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB4_81: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp word ptr [rsi], r13w - setne byte ptr [rsp + 144] # 1-byte Folded Spill + setne byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 2], r13w setne r10b cmp word ptr [rsi + 4], r13w setne r14b cmp word ptr [rsi + 6], r13w - setne byte ptr [rsp + 152] # 1-byte Folded Spill + setne byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - setne byte ptr [rsp + 136] # 1-byte Folded Spill + setne byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - setne byte ptr [rsp + 96] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w setne al cmp word ptr [rsi + 14], r13w setne bl cmp word ptr [rsi + 16], r13w - setne byte ptr [rsp + 160] # 1-byte Folded Spill + setne byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w setne dil cmp word ptr [rsi + 20], r13w @@ -21787,210 +22450,229 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 cmp word ptr [rsi + 26], r13w setne r12b cmp word ptr [rsi + 28], r13w - setne byte ptr [rsp + 112] # 1-byte Folded Spill + setne byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - setne cl + setne dl cmp word ptr [rsi + 32], r13w - setne byte ptr [rsp + 80] # 1-byte Folded Spill + setne byte ptr [rsp + 160] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp word ptr [rsi + 36], r13w setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [rsi + 36], r13w + setne byte ptr [rsp + 136] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - setne byte ptr [rsp + 72] # 1-byte Folded Spill + setne byte ptr [rsp + 152] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - setne byte ptr [rsp + 88] # 1-byte Folded Spill + setne byte ptr [rsp + 168] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp word ptr [rsi + 44], r13w setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp word ptr [rsi + 44], r13w + setne byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w setne r15b cmp word ptr [rsi + 48], r13w - setne byte ptr [rsp + 32] # 1-byte Folded Spill + setne byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 52], r13w - setne byte ptr [rsp + 48] # 1-byte Folded Spill + setne byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w - setne byte ptr [rsp + 56] # 1-byte Folded Spill + setne byte ptr [rsp + 40] # 1-byte Folded Spill cmp word ptr [rsi + 56], r13w - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp word ptr [rsi + 58], r13w setne byte ptr [rsp + 320] # 1-byte Folded Spill + cmp word ptr [rsi + 58], r13w + setne byte ptr [rsp + 288] # 1-byte Folded Spill cmp word ptr [rsi + 60], r13w setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp word ptr [rsi + 62], r13w - setne dl + setne cl add r10b, r10b - add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add dil, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 64 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_62 -# %bb.63: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_116 - jmp .LBB4_165 -.LBB4_64: + add r14, 4 + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill + jne .LBB4_81 +# %bb.82: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_83: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.84: + or rax, 1 + cmp r15, rax + jne .LBB4_164 +.LBB4_85: + xor r11d, r11d + jmp .LBB4_166 +.LBB4_86: mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_68 -# %bb.65: - movsxd rax, r9d + je .LBB4_92 +# %bb.87: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_90 +# %bb.88: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_66: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB4_89: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_66 -# %bb.67: - add r11, 1 -.LBB4_68: - sar r15, 5 - cmp r10, 32 - jl .LBB4_118 -# %bb.69: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_89 +.LBB4_90: + sub r15, r8 + je .LBB4_189 +# %bb.91: + add r14, 1 +.LBB4_92: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB4_96 +# %bb.93: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_70: # =>This Inner Loop Header: Depth=1 +.LBB4_94: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp qword ptr [rsi], r13 - setne byte ptr [rsp + 144] # 1-byte Folded Spill + setne byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 setne r10b cmp qword ptr [rsi + 16], r13 setne r14b cmp qword ptr [rsi + 24], r13 - setne byte ptr [rsp + 152] # 1-byte Folded Spill + setne byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 32], r13 - setne byte ptr [rsp + 136] # 1-byte Folded Spill + setne byte ptr [rsp + 144] # 1-byte Folded Spill cmp qword ptr [rsi + 40], r13 - setne byte ptr [rsp + 96] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 48], r13 setne al cmp qword ptr [rsi + 56], r13 setne bl cmp qword ptr [rsi + 64], r13 - setne byte ptr [rsp + 160] # 1-byte Folded Spill + setne byte ptr [rsp + 112] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 setne dil cmp qword ptr [rsi + 80], r13 @@ -22002,194 +22684,216 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 cmp qword ptr [rsi + 104], r13 setne r12b cmp qword ptr [rsi + 112], r13 - setne byte ptr [rsp + 112] # 1-byte Folded Spill + setne byte ptr [rsp + 120] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - setne cl + setne dl cmp qword ptr [rsi + 128], r13 - setne byte ptr [rsp + 80] # 1-byte Folded Spill + setne byte ptr [rsp + 160] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp qword ptr [rsi + 144], r13 + setne byte ptr [rsp + 136] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - setne byte ptr [rsp + 72] # 1-byte Folded Spill + setne byte ptr [rsp + 152] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - setne byte ptr [rsp + 88] # 1-byte Folded Spill + setne byte ptr [rsp + 168] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp qword ptr [rsi + 176], r13 setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp qword ptr [rsi + 176], r13 + setne byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 setne r15b cmp qword ptr [rsi + 192], r13 - setne byte ptr [rsp + 32] # 1-byte Folded Spill + setne byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 - setne byte ptr [rsp + 48] # 1-byte Folded Spill + setne byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - setne byte ptr [rsp + 56] # 1-byte Folded Spill + setne byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp qword ptr [rsi + 232], r13 setne byte ptr [rsp + 320] # 1-byte Folded Spill + cmp qword ptr [rsi + 232], r13 + setne byte ptr [rsp + 288] # 1-byte Folded Spill cmp qword ptr [rsi + 240], r13 setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - setne dl + setne cl add r10b, r10b - add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add dil, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 256 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_70 -# %bb.71: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_119 - jmp .LBB4_165 -.LBB4_72: - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + add r14, 4 + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill + jne .LBB4_94 +# %bb.95: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_96: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.97: + or rax, 1 + cmp r15, rax + jne .LBB4_168 +.LBB4_98: + xor r11d, r11d + jmp .LBB4_170 +.LBB4_99: + mov r12d, dword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB4_76 -# %bb.73: - movsxd rax, r9d + je .LBB4_105 +# %bb.100: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_103 +# %bb.101: + movsxd rdx, r9d + vmovd xmm0, r12d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_74: # =>This Inner Loop Header: Depth=1 - vucomiss xmm0, dword ptr [rsi] - lea rsi, [rsi + 4] +.LBB4_102: # =>This Inner Loop Header: Depth=1 + vucomiss xmm0, dword ptr [rcx] + lea rsi, [rcx + 4] setp cl - setne dl - or dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + setne bl + or bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_74 -# %bb.75: - add r11, 1 -.LBB4_76: - sar r15, 5 - cmp r10, 32 - jl .LBB4_121 -# %bb.77: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_102 +.LBB4_103: + sub r15, r8 + je .LBB4_189 +# %bb.104: + add r14, 1 +.LBB4_105: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB4_109 +# %bb.106: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov dword ptr [rsp + 192], r12d # 4-byte Spill + vmovd xmm0, r12d + mov qword ptr [rsp + 184], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_78: # =>This Inner Loop Header: Depth=1 +.LBB4_107: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill vucomiss xmm0, dword ptr [rsi] setp al setne cl @@ -22197,31 +22901,32 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 mov byte ptr [rsp + 32], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 4] setp al - setne bl - or bl, al - vucomiss xmm0, dword ptr [rsi + 8] - setp al setne r13b or r13b, al + vucomiss xmm0, dword ptr [rsi + 8] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 12] setp al setne cl or cl, al - mov byte ptr [rsp + 288], cl # 1-byte Spill + mov byte ptr [rsp + 320], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 16] setp al setne cl or cl, al - mov byte ptr [rsp + 320], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 20] setp al - setne dil - or dil, al + setne r12b + or r12b, al vucomiss xmm0, dword ptr [rsi + 24] setp al setne cl or cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 28] setp al setne cl @@ -22231,46 +22936,46 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 36] setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 40] setp al setne cl or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 44] setp al - setne cl - or cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + setne bl + or bl, al vucomiss xmm0, dword ptr [rsi + 48] setp al setne cl or cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 288], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 52] setp al setne cl or cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 56] setp al - setne dl - or dl, al + setne cl + or cl, al + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 60] setp al setne cl or cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 64] setp al setne cl or cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 168], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 68] setp al setne cl @@ -22280,467 +22985,299 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 setp al setne cl or cl, al + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 76] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 128], al # 1-byte Spill + setp al + setne r14b + or r14b, al vucomiss xmm0, dword ptr [rsi + 80] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 120], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 84] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 160], al # 1-byte Spill + setp al + setne cl + or cl, al + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomiss xmm0, dword ptr [rsi + 88] setp al - setne r12b - or r12b, al + setne r15b + or r15b, al vucomiss xmm0, dword ptr [rsi + 92] setp al setne r10b or r10b, al vucomiss xmm0, dword ptr [rsi + 96] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 112], al # 1-byte Spill - vucomiss xmm0, dword ptr [rsi + 100] - setp al - setne r15b - or r15b, al - vucomiss xmm0, dword ptr [rsi + 104] setp al - setne r14b - or r14b, al - vucomiss xmm0, dword ptr [rsi + 108] + setne cl + or cl, al + mov byte ptr [rsp + 104], cl # 1-byte Spill + vucomiss xmm0, dword ptr [rsi + 100] setp al setne r11b or r11b, al - vucomiss xmm0, dword ptr [rsi + 112] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 152], al # 1-byte Spill - vucomiss xmm0, dword ptr [rsi + 116] - setp r8b - setne al - or al, r8b - mov byte ptr [rsp + 144], al # 1-byte Spill - vucomiss xmm0, dword ptr [rsi + 120] + vucomiss xmm0, dword ptr [rsi + 104] setp al setne r9b or r9b, al - vucomiss xmm0, dword ptr [rsi + 124] + vucomiss xmm0, dword ptr [rsi + 108] setp al setne r8b or r8b, al - add bl, bl - add bl, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 5 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 6 - or al, dil - mov edi, eax - shl r13b, 2 - or r13b, bl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 56] # 1-byte Folded Reload - mov ebx, eax + vucomiss xmm0, dword ptr [rsi + 112] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 96], cl # 1-byte Spill + vucomiss xmm0, dword ptr [rsi + 116] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 88], cl # 1-byte Spill + vucomiss xmm0, dword ptr [rsi + 120] + setp al + setne dil + or dil, al + vucomiss xmm0, dword ptr [rsi + 124] + setp al + setne dl + or dl, al + add r13b, r13b + add r13b, byte ptr [rsp + 32] # 1-byte Folded Reload + mov eax, r13d + shl r12b, 5 + movzx r13d, byte ptr [rsp + 72] # 1-byte Folded Reload + shl r13b, 6 + or r13b, r12b + movzx r12d, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 80] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 - or al, dil + or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 3 - or al, r13b - mov r13d, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov edi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 3 + or al, r12b + shl bl, 3 + or bl, cl + movzx r13d, byte ptr [rsp + 48] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 - or al, r13b - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 4 - or bl, dil - movzx edi, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dil, 5 - shl dl, 6 - or dl, dil - movzx r13d, byte ptr [rsp + 80] # 1-byte Folded Reload - shl r13b, 7 - or r13b, dl - movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 72] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 3 - or dl, cl - mov ecx, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 4 - or dl, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - or cl, al - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 5 - shl r12b, 6 - or r12b, al - or r13b, bl - shl r10b, 7 - or r10b, r12b - or r10b, dl - add r15b, r15b - add r15b, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r15b - shl r11b, 3 - or r11b, r14b + or al, bl + mov byte ptr [rsp + 288], al # 1-byte Spill + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 5 movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload - shl al, 4 - or al, r11b - mov ebx, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], cl - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 5 - shl r9b, 6 - or r9b, dl - mov byte ptr [rax + 1], r13b - shl r8b, 7 + shl al, 6 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + shl al, 7 + or al, cl + movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 168] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 2 + or bl, cl + shl r14b, 3 + or r14b, bl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, r14b + mov r14, qword ptr [rsp + 272] # 8-byte Reload + movzx r12d, byte ptr [rsp + 28] # 1-byte Folded Reload + or r12b, r13b + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl bl, 5 + shl r15b, 6 + or r15b, bl + or al, byte ptr [rsp + 288] # 1-byte Folded Reload + shl r10b, 7 + or r10b, r15b + or r10b, cl + add r11b, r11b + add r11b, byte ptr [rsp + 104] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 or r8b, r9b - or r8b, bl - mov byte ptr [rax + 2], r10b - mov byte ptr [rax + 3], r8b + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 4 + or cl, r8b + mov byte ptr [r14], r12b + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl bl, 5 + shl dil, 6 + or dil, bl + mov byte ptr [r14 + 1], al + shl dl, 7 + or dl, dil + or dl, cl + mov byte ptr [r14 + 2], r10b + mov byte ptr [r14 + 3], dl add rsi, 128 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_78 -# %bb.79: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_122 - jmp .LBB4_165 -.LBB4_80: - mov r14b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + add r14, 4 + add qword ptr [rsp + 176], -1 # 8-byte Folded Spill + jne .LBB4_107 +# %bb.108: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 192] # 4-byte Reload + mov rax, qword ptr [rsp + 184] # 8-byte Reload +.LBB4_109: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.110: + vmovd xmm0, r12d + or rax, 1 + cmp r15, rax + jne .LBB4_172 +# %bb.111: + xor r11d, r11d + jmp .LBB4_174 +.LBB4_112: + mov r12b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_84 -# %bb.81: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB4_82: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r14b - lea rsi, [rsi + 1] - setne dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_82 -# %bb.83: - add r11, 1 -.LBB4_84: - sar r15, 5 - cmp r10, 32 - jl .LBB4_124 -# %bb.85: - cmp r15, 32 - mov dword ptr [rsp + 28], r14d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 392], r15 # 8-byte Spill - jb .LBB4_88 -# %bb.86: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp r11, rax - jae .LBB4_169 -# %bb.87: - lea rax, [r11 + 4*r15] - cmp rsi, rax - jae .LBB4_169 -.LBB4_88: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 376], r11 # 8-byte Spill -.LBB4_89: - sub r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 144], r15 # 8-byte Spill + je .LBB4_131 +# %bb.113: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_146 +# %bb.114: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB4_90: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b - setne r8b - cmp byte ptr [r12 + 2], r14b - setne r15b - cmp byte ptr [r12 + 3], r14b - setne r13b - cmp byte ptr [r12 + 4], r14b - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b - setne al - cmp byte ptr [r12 + 7], r14b - setne r11b - cmp byte ptr [r12 + 8], r14b - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b - setne dl - cmp byte ptr [r12 + 10], r14b - setne sil - cmp byte ptr [r12 + 11], r14b - setne dil - cmp byte ptr [r12 + 12], r14b - setne r10b - cmp byte ptr [r12 + 13], r14b - setne r12b - cmp byte ptr [rcx + 14], r14b - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b - setne r9b - cmp byte ptr [rcx + 16], r14b - setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - setne r14b - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 24], bl - setne byte ptr [rsp + 272] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 25], bl - setne byte ptr [rsp + 96] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 26], bl - setne byte ptr [rsp + 88] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 27], bl - setne byte ptr [rsp + 104] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 28], bl - setne byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 29], bl - setne byte ptr [rsp + 48] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 30], bl - setne byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 31], bl +.LBB4_115: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r12b setne bl - add r8b, r8b - add r8b, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, r8b - add dl, dl - add dl, byte ptr [rsp + 288] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b - shl sil, 2 - or sil, dl - movzx edx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - shl dil, 3 - or dil, sil - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, dil - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl r9b, 7 - or r9b, sil - or r11b, dl - or r9b, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 320] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov rsi, qword ptr [rsp + 376] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 272] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 6 - shl bl, 7 - or bl, dl - or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 376], rsi # 8-byte Spill - add qword ptr [rsp + 144], -1 # 8-byte Folded Spill - jne .LBB4_90 -# %bb.91: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 392] # 8-byte Reload - jmp .LBB4_125 -.LBB4_92: + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov r13, r14 + movzx r9d, byte ptr [r14 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB4_115 +# %bb.116: + sub r15, r8 + jne .LBB4_147 + jmp .LBB4_189 +.LBB4_117: mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_96 -# %bb.93: - movsxd rax, r9d + je .LBB4_123 +# %bb.118: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB4_121 +# %bb.119: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_94: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB4_120: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r12, r14 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_94 -# %bb.95: - add r11, 1 -.LBB4_96: - sar r15, 5 - cmp r10, 32 - jl .LBB4_128 -# %bb.97: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_120 +.LBB4_121: + sub r15, r8 + je .LBB4_189 +# %bb.122: + add r14, 1 +.LBB4_123: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB4_127 +# %bb.124: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_98: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r11 # 8-byte Spill +.LBB4_125: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp dword ptr [rsi], r13d - setne byte ptr [rsp + 144] # 1-byte Folded Spill + setne byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d setne r10b cmp dword ptr [rsi + 8], r13d setne r14b cmp dword ptr [rsi + 12], r13d - setne byte ptr [rsp + 152] # 1-byte Folded Spill + setne byte ptr [rsp + 104] # 1-byte Folded Spill cmp dword ptr [rsi + 16], r13d - setne byte ptr [rsp + 136] # 1-byte Folded Spill + setne byte ptr [rsp + 144] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - setne byte ptr [rsp + 96] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d setne al cmp dword ptr [rsi + 28], r13d setne bl cmp dword ptr [rsi + 32], r13d - setne byte ptr [rsp + 160] # 1-byte Folded Spill + setne byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d setne dil cmp dword ptr [rsi + 40], r13d @@ -22752,363 +23289,407 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 cmp dword ptr [rsi + 52], r13d setne r12b cmp dword ptr [rsi + 56], r13d - setne byte ptr [rsp + 112] # 1-byte Folded Spill + setne byte ptr [rsp + 120] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - setne cl + setne dl cmp dword ptr [rsi + 64], r13d - setne byte ptr [rsp + 80] # 1-byte Folded Spill + setne byte ptr [rsp + 160] # 1-byte Folded Spill cmp dword ptr [rsi + 68], r13d - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setne byte ptr [rsp + 136] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - setne byte ptr [rsp + 72] # 1-byte Folded Spill + setne byte ptr [rsp + 152] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d - setne byte ptr [rsp + 88] # 1-byte Folded Spill + setne byte ptr [rsp + 168] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + setne byte ptr [rsp + 72] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d setne r15b cmp dword ptr [rsi + 96], r13d - setne byte ptr [rsp + 32] # 1-byte Folded Spill + setne byte ptr [rsp + 48] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 80] # 1-byte Folded Spill cmp dword ptr [rsi + 104], r13d - setne byte ptr [rsp + 48] # 1-byte Folded Spill + setne byte ptr [rsp + 32] # 1-byte Folded Spill cmp dword ptr [rsi + 108], r13d - setne byte ptr [rsp + 56] # 1-byte Folded Spill + setne byte ptr [rsp + 40] # 1-byte Folded Spill cmp dword ptr [rsi + 112], r13d - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d setne byte ptr [rsp + 320] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d + setne byte ptr [rsp + 288] # 1-byte Folded Spill cmp dword ptr [rsi + 120], r13d setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp dword ptr [rsi + 124], r13d - setne dl + setne cl add r10b, r10b - add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add dil, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - mov r11, qword ptr [rsp + 272] # 8-byte Reload - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r11 + 1], cl + mov byte ptr [r14 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], dl + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 128 - add r11, 4 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB4_98 -# %bb.99: - mov r14, r11 - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB4_129 - jmp .LBB4_165 -.LBB4_100: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_101: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB4_130 -# %bb.102: - mov r10, r8 - and r10, -2 + add r14, 4 + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill + jne .LBB4_125 +# %bb.126: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_127: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB4_189 +# %bb.128: + or rax, 1 + cmp r15, rax + jne .LBB4_177 +.LBB4_129: xor r11d, r11d - mov r15, r14 - .p2align 4, 0x90 -.LBB4_103: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - setne al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r15 + rdi], bl - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - setne al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r15 + rdi], dl - cmp r10, r11 - jne .LBB4_103 - jmp .LBB4_157 -.LBB4_104: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_105: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB4_136 -# %bb.106: - xor r11d, r11d - jmp .LBB4_138 -.LBB4_107: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_108: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB4_120 -# %bb.109: - mov r10, r8 - and r10, -2 - xor r11d, r11d - mov r15, r14 - .p2align 4, 0x90 -.LBB4_110: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - setne al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r15 + rdi], bl - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] - setne al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r15 + rdi], dl - cmp r10, r11 - jne .LBB4_110 - jmp .LBB4_146 -.LBB4_111: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_112: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB4_117 -# %bb.113: - mov r10, r8 - and r10, -2 - xor r11d, r11d - mov r15, r14 + jmp .LBB4_179 +.LBB4_130: + mov rdi, rsi + jmp .LBB4_134 +.LBB4_131: + mov rdi, rsi + jmp .LBB4_148 +.LBB4_132: + mov rdi, rsi + sub r15, r8 + je .LBB4_189 +.LBB4_133: + add r14, 1 +.LBB4_134: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB4_142 +# %bb.135: + cmp rcx, 32 + mov dword ptr [rsp + 28], r12d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 392], rcx # 8-byte Spill + jb .LBB4_138 +# %bb.136: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB4_190 +# %bb.137: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB4_190 +.LBB4_138: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 376], r14 # 8-byte Spill +.LBB4_139: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 88], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB4_114: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - setne al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r15 + rdi], bl - add r11, 2 - cmp word ptr [rsi + 2], r13w - lea rsi, [rsi + 4] - setne al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r15 + rdi], dl - cmp r10, r11 - jne .LBB4_114 - jmp .LBB4_142 -.LBB4_115: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_116: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 +.LBB4_140: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r12b + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r12b + setne r8b + cmp byte ptr [rsi + 2], r12b + setne r14b + cmp byte ptr [rsi + 3], r12b + setne r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 4], al + setne byte ptr [rsp + 56] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 5], al + setne byte ptr [rsp + 40] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 6], al + setne byte ptr [rsp + 96] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 7], al + setne r11b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 8], al + setne byte ptr [rsp + 320] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 9], al + setne dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 10], al + setne sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 11], al + setne dil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 12], al + setne r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 13], al + setne r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 14], al + setne byte ptr [rsp + 104] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 15], al + setne r9b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 16], bl + setne byte ptr [rsp + 288] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + setne byte ptr [rsp + 144] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 18], bl + setne byte ptr [rsp + 112] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 19], bl + setne byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + setne byte ptr [rsp + 128] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + setne byte ptr [rsp + 136] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + setne byte ptr [rsp + 64] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + setne r15b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 24], bl + setne byte ptr [rsp + 272] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 25], bl + setne byte ptr [rsp + 152] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 26], bl + setne byte ptr [rsp + 160] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 27], bl + setne byte ptr [rsp + 168] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 28], bl + setne byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 29], bl + setne byte ptr [rsp + 80] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 30], bl + setne byte ptr [rsp + 32] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 31], bl + setne bl + add r8b, r8b + add r8b, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r8b + add dl, dl + add dl, byte ptr [rsp + 320] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, dl + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 4 + or dl, r13b + mov r8d, edx + mov eax, dword ptr [rsp + 28] # 4-byte Reload + shl dil, 3 + or dil, sil + movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl dl, 5 + or dl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, dl + or r9b, r12b + mov r12d, eax + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 288] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 2 + or dl, al + mov esi, edx + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov rdi, qword ptr [rsp + 376] # 8-byte Reload + mov byte ptr [rdi], r11b + movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [rdi + 1], r9b + or r15b, dl + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 272] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r15b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 376], rdi # 8-byte Spill + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill jne .LBB4_140 -.LBB4_117: - xor r11d, r11d - jmp .LBB4_142 -.LBB4_118: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_119: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB4_144 -.LBB4_120: - xor r11d, r11d - jmp .LBB4_146 -.LBB4_121: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_122: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB4_148 -# %bb.123: - xor r11d, r11d - jmp .LBB4_150 -.LBB4_124: - mov qword ptr [rsp + 376], r11 # 8-byte Spill - mov r12, rsi -.LBB4_125: - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -# %bb.126: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB4_127 -# %bb.153: +# %bb.141: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + jmp .LBB4_143 +.LBB4_142: + mov qword ptr [rsp + 376], r14 # 8-byte Spill + mov rsi, rdi +.LBB4_143: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB4_189 +# %bb.144: + or rcx, 1 + cmp r15, rcx + je .LBB4_159 +# %bb.182: mov r10, r8 and r10, -2 - xor esi, esi + xor r9d, r9d mov r11, qword ptr [rsp + 376] # 8-byte Reload .p2align 4, 0x90 -.LBB4_154: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rsi], r14b +.LBB4_183: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r12b setne bl neg bl - mov rdi, rsi + mov rdi, r9 shr rdi, 3 - mov ecx, esi + mov ecx, eax and cl, 6 mov dl, 1 shl dl, cl @@ -23117,8 +23698,8 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 and dl, bl xor dl, r9b mov byte ptr [r11 + rdi], dl - cmp byte ptr [r12 + rsi + 1], r14b - lea rsi, [rsi + 2] + cmp byte ptr [rsi + rax + 1], r12b + lea r9, [rax + 2] setne bl neg bl xor bl, dl @@ -23128,51 +23709,258 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 and al, bl xor al, dl mov byte ptr [r11 + rdi], al - cmp r10, rsi + cmp r10, r9 + jne .LBB4_183 + jmp .LBB4_186 +.LBB4_146: + mov rdi, rsi + sub r15, r8 + je .LBB4_189 +.LBB4_147: + add r14, 1 +.LBB4_148: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB4_156 +# %bb.149: + cmp rcx, 32 + mov dword ptr [rsp + 28], r12d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 392], rcx # 8-byte Spill + jb .LBB4_152 +# %bb.150: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB4_193 +# %bb.151: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB4_193 +.LBB4_152: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 376], r14 # 8-byte Spill +.LBB4_153: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 88], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB4_154: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r12b + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r12b + setne r8b + cmp byte ptr [rsi + 2], r12b + setne r14b + cmp byte ptr [rsi + 3], r12b + setne r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 4], al + setne byte ptr [rsp + 56] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 5], al + setne byte ptr [rsp + 40] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 6], al + setne byte ptr [rsp + 96] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 7], al + setne r11b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 8], al + setne byte ptr [rsp + 320] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 9], al + setne dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 10], al + setne sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 11], al + setne dil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 12], al + setne r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 13], al + setne r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 14], al + setne byte ptr [rsp + 104] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 15], al + setne r9b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 16], bl + setne byte ptr [rsp + 288] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + setne byte ptr [rsp + 144] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 18], bl + setne byte ptr [rsp + 112] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 19], bl + setne byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + setne byte ptr [rsp + 128] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + setne byte ptr [rsp + 136] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + setne byte ptr [rsp + 64] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + setne r15b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 24], bl + setne byte ptr [rsp + 272] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 25], bl + setne byte ptr [rsp + 152] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 26], bl + setne byte ptr [rsp + 160] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 27], bl + setne byte ptr [rsp + 168] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 28], bl + setne byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 29], bl + setne byte ptr [rsp + 80] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 30], bl + setne byte ptr [rsp + 32] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 31], bl + setne bl + add r8b, r8b + add r8b, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r8b + add dl, dl + add dl, byte ptr [rsp + 320] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, dl + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 4 + or dl, r13b + mov r8d, edx + mov eax, dword ptr [rsp + 28] # 4-byte Reload + shl dil, 3 + or dil, sil + movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl dl, 5 + or dl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, dl + or r9b, r12b + mov r12d, eax + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 288] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 2 + or dl, al + mov esi, edx + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov rdi, qword ptr [rsp + 376] # 8-byte Reload + mov byte ptr [rdi], r11b + movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [rdi + 1], r9b + or r15b, dl + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 272] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r15b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 376], rdi # 8-byte Spill + add qword ptr [rsp + 88], -1 # 8-byte Folded Spill jne .LBB4_154 - jmp .LBB4_162 -.LBB4_128: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -.LBB4_129: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB4_155 -.LBB4_130: - xor r11d, r11d +# %bb.155: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 392] # 8-byte Reload jmp .LBB4_157 -.LBB4_131: - mov r13, r11 - sar r15, 5 - cmp r10, 32 - jge .LBB4_31 -.LBB4_132: - mov qword ptr [rsp + 376], r13 # 8-byte Spill - mov r12, rsi -.LBB4_133: - shl r15, 5 - cmp r15, r10 - jge .LBB4_165 -# %bb.134: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB4_160 -.LBB4_127: - xor esi, esi - jmp .LBB4_163 -.LBB4_136: +.LBB4_156: + mov qword ptr [rsp + 376], r14 # 8-byte Spill + mov rsi, rdi +.LBB4_157: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB4_189 +# %bb.158: + or rcx, 1 + cmp r15, rcx + jne .LBB4_184 +.LBB4_159: + xor r9d, r9d + jmp .LBB4_187 +.LBB4_160: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB4_137: # =>This Inner Loop Header: Depth=1 +.LBB4_161: # =>This Inner Loop Header: Depth=1 vucomisd xmm0, qword ptr [rsi] setp cl setne al @@ -23180,7 +23968,8 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 neg al mov rdi, r11 shr rdi, 3 - movzx r10d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r10d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -23188,7 +23977,7 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 xor al, r10b and bl, al xor bl, r10b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 vucomisd xmm0, qword ptr [rsi + 8] lea rsi, [rsi + 16] @@ -23202,28 +23991,28 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r9, r11 - jne .LBB4_137 -.LBB4_138: + jne .LBB4_161 +.LBB4_162: test r8b, 1 - je .LBB4_165 -# %bb.139: + je .LBB4_189 +# %bb.163: vucomisd xmm0, qword ptr [rsi] - jmp .LBB4_152 -.LBB4_140: + jmp .LBB4_176 +.LBB4_164: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB4_141: # =>This Inner Loop Header: Depth=1 +.LBB4_165: # =>This Inner Loop Header: Depth=1 cmp word ptr [rsi], r13w setne al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -23231,7 +24020,7 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp word ptr [rsi + 2], r13w lea rsi, [rsi + 4] @@ -23243,28 +24032,28 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB4_141 -.LBB4_142: + jne .LBB4_165 +.LBB4_166: test r8b, 1 - je .LBB4_165 -# %bb.143: + je .LBB4_189 +# %bb.167: cmp word ptr [rsi], r13w - jmp .LBB4_159 -.LBB4_144: + jmp .LBB4_181 +.LBB4_168: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB4_145: # =>This Inner Loop Header: Depth=1 +.LBB4_169: # =>This Inner Loop Header: Depth=1 cmp qword ptr [rsi], r13 setne al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -23272,7 +24061,7 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp qword ptr [rsi + 8], r13 lea rsi, [rsi + 16] @@ -23284,22 +24073,21 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB4_145 -.LBB4_146: + jne .LBB4_169 +.LBB4_170: test r8b, 1 - je .LBB4_165 -# %bb.147: + je .LBB4_189 +# %bb.171: cmp qword ptr [rsi], r13 - jmp .LBB4_159 -.LBB4_148: + jmp .LBB4_181 +.LBB4_172: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB4_149: # =>This Inner Loop Header: Depth=1 +.LBB4_173: # =>This Inner Loop Header: Depth=1 vucomiss xmm0, dword ptr [rsi] setp cl setne al @@ -23307,7 +24095,8 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 neg al mov rdi, r11 shr rdi, 3 - movzx r10d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r10d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -23315,7 +24104,7 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 xor al, r10b and bl, al xor bl, r10b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 vucomiss xmm0, dword ptr [rsi + 4] lea rsi, [rsi + 8] @@ -23329,15 +24118,15 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r9, r11 - jne .LBB4_149 -.LBB4_150: + jne .LBB4_173 +.LBB4_174: test r8b, 1 - je .LBB4_165 -# %bb.151: + je .LBB4_189 +# %bb.175: vucomiss xmm0, dword ptr [rsi] -.LBB4_152: +.LBB4_176: setp al setne dl or dl, al @@ -23353,20 +24142,20 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 and bl, dl xor bl, sil mov byte ptr [r14 + rax], bl - jmp .LBB4_165 -.LBB4_155: + jmp .LBB4_189 +.LBB4_177: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB4_156: # =>This Inner Loop Header: Depth=1 +.LBB4_178: # =>This Inner Loop Header: Depth=1 cmp dword ptr [rsi], r13d setne al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + mov r15, r14 + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -23374,7 +24163,7 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp dword ptr [rsi + 4], r13d lea rsi, [rsi + 8] @@ -23386,15 +24175,15 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB4_156 -.LBB4_157: + jne .LBB4_178 +.LBB4_179: test r8b, 1 - je .LBB4_165 -# %bb.158: + je .LBB4_189 +# %bb.180: cmp dword ptr [rsi], r13d -.LBB4_159: +.LBB4_181: setne al neg al mov rdx, r11 @@ -23408,20 +24197,21 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 and bl, al xor bl, sil mov byte ptr [r14 + rdx], bl - jmp .LBB4_165 -.LBB4_160: + jmp .LBB4_189 +.LBB4_184: mov r10, r8 and r10, -2 - xor esi, esi + xor r9d, r9d mov r11, qword ptr [rsp + 376] # 8-byte Reload .p2align 4, 0x90 -.LBB4_161: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rsi], r14b +.LBB4_185: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r12b setne bl neg bl - mov rdi, rsi + mov rdi, r9 shr rdi, 3 - mov ecx, esi + mov ecx, eax and cl, 6 mov dl, 1 shl dl, cl @@ -23430,8 +24220,8 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 and dl, bl xor dl, r9b mov byte ptr [r11 + rdi], dl - cmp byte ptr [r12 + rsi + 1], r14b - lea rsi, [rsi + 2] + cmp byte ptr [rsi + rax + 1], r12b + lea r9, [rax + 2] setne bl neg bl xor bl, dl @@ -23441,30 +24231,30 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 and al, bl xor al, dl mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB4_161 -.LBB4_162: - add r12, rsi -.LBB4_163: + cmp r10, r9 + jne .LBB4_185 +.LBB4_186: + add rsi, r9 +.LBB4_187: test r8b, 1 - je .LBB4_165 -# %bb.164: - cmp byte ptr [r12], r14b + je .LBB4_189 +# %bb.188: + cmp byte ptr [rsi], r12b setne al neg al - mov rdx, rsi + mov rdx, r9 shr rdx, 3 mov r8, qword ptr [rsp + 376] # 8-byte Reload mov dil, byte ptr [r8 + rdx] - and sil, 7 + and r9b, 7 mov bl, 1 - mov ecx, esi + mov ecx, r9d shl bl, cl xor al, dil and bl, al xor bl, dil mov byte ptr [r8 + rdx], bl -.LBB4_165: +.LBB4_189: lea rsp, [rbp - 40] pop rbx pop r12 @@ -23474,1991 +24264,1982 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 pop rbp vzeroupper ret -.LBB4_166: - and r15, -32 - mov rax, r15 +.LBB4_190: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - mov qword ptr [rsp + 384], r15 # 8-byte Spill - lea rax, [4*r15] - add rax, r13 + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 376], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r12d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 272], r13 # 8-byte Spill + mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB4_167: # =>This Inner Loop Header: Depth=1 +.LBB4_191: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 408], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 184], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 112], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 192 mov qword ptr [rsp + 192], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 256 mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rcx + 1] + movzx eax, byte ptr [rdi + rcx + 1] mov rdx, rcx vmovd xmm4, eax mov rcx, rbx - movzx eax, byte ptr [rsi + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rsi + rdx + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rsi + rdx + 6] - mov qword ptr [rsp + 256], rdx # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 264], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 320], rax # 8-byte Spill - mov r13, rbx - or r13, 544 - mov qword ptr [rsp + 248], r13 # 8-byte Spill - mov rax, rbx - or rax, 576 - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx + or rax, 544 + mov qword ptr [rsp + 96], rax # 8-byte Spill + or rbx, 576 + mov qword ptr [rsp + 200], rbx # 8-byte Spill + mov rax, rcx or rax, 608 - mov qword ptr [rsp + 80], rax # 8-byte Spill - mov r10, rbx - or r10, 640 - mov qword ptr [rsp + 128], r10 # 8-byte Spill - mov rax, rbx + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov r14, rcx + or r14, 640 + mov qword ptr [rsp + 144], r14 # 8-byte Spill + mov rax, rcx or rax, 672 - mov r12, rax - mov qword ptr [rsp + 176], rax # 8-byte Spill - mov rdi, rbx - or rdi, 704 - mov qword ptr [rsp + 216], rdi # 8-byte Spill - mov rdx, rbx - or rdx, 736 - mov qword ptr [rsp + 224], rdx # 8-byte Spill - mov rax, rbx - or rax, 768 - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov r15, rbx - or r15, 800 - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov r11, rbx - or r11, 832 - mov qword ptr [rsp + 208], r11 # 8-byte Spill - mov r8, rbx - or r8, 864 - mov qword ptr [rsp + 264], r8 # 8-byte Spill - mov r14, rbx - or r14, 896 - mov qword ptr [rsp + 120], r14 # 8-byte Spill - mov r9, rbx - or r9, 928 - mov qword ptr [rsp + 88], r9 # 8-byte Spill - mov rax, rbx - mov qword ptr [rsp + 240], rbx # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill + mov r12, rcx + or r12, 704 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov rsi, rcx + or rsi, 736 + mov qword ptr [rsp + 208], rsi # 8-byte Spill + mov r15, rcx + or r15, 768 + mov qword ptr [rsp + 256], r15 # 8-byte Spill + mov r11, rcx + or r11, 800 + mov qword ptr [rsp + 248], r11 # 8-byte Spill + mov r10, rcx + or r10, 832 + mov qword ptr [rsp + 128], r10 # 8-byte Spill + mov r9, rcx + or r9, 864 + mov qword ptr [rsp + 112], r9 # 8-byte Spill + mov r8, rcx + or r8, 896 + mov qword ptr [rsp + 216], r8 # 8-byte Spill + mov rdx, rcx + or rdx, 928 + mov qword ptr [rsp + 176], rdx # 8-byte Spill + mov rax, rcx + mov qword ptr [rsp + 232], rcx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 32], rcx # 8-byte Spill - vpinsrb xmm9, xmm0, byte ptr [rsi + r13], 1 - mov r13, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + r13], 2 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 7 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 1 + mov qword ptr [rsp + 48], rcx # 8-byte Spill + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + r13], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 1 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 2 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 3 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 4 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 6 mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 2 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 3 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 4 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11], 5 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 6 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 12 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 13 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12], 14 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 15 - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 1 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 2 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 3 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 4 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 5 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 6 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 7 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 8 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 9 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 10 - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 12 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 13 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rsi + rbx + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 6 - mov rbx, r8 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 15 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 1 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 2 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 3 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 5 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 7 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 2 + mov rsi, r12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 1], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 vinserti128 ymm13, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 1], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm9, edx vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm10, edi - mov rcx, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm10, edx + mov rcx, qword ptr [rsp + 96] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 2], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 2], 1 mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 2], 2 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 2], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 2 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 7 + mov r8, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 8 + mov r12, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 9 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 10 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 11 mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 2], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 7 - mov r12, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 8 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 9 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 2], 10 - mov r11, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 2], 12 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 12 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 14 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 15 - mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 3 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 4 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 7 mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 9 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 12 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + rcx + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 3 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 4 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 3], 6 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 13 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 3 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 4 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 5 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 8 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 9 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 10 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 13 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + rcx + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 5 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 6 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 10 + mov r8, r13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 13 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rax + 3], 1 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 4 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 7 + mov rax, rdx + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 8 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 11 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm8, edi - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 3], 15 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rcx + 3], 14 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm8, edx + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 9] - vmovd xmm11, edi + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm11, edx + mov r14, qword ptr [rsp + 96] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 1 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 4], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 3 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 4 - mov rax, r10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 4], 5 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 4], 7 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 4], 8 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 9 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 4], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 12 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 4], 15 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm15, byte ptr [rsi + rcx + 4], 1 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 4], 2 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 1 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 4 mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 4 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 5 - mov rdi, r14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 7 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 4], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 9 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 11 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 12 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 13 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 4], 15 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm14, byte ptr [rsi + r14 + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 2 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 7 - mov r15, rax - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 5], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 5 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 7 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 10 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 11 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 12 + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 15 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm15, byte ptr [rdi + rdx + 4], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 9 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 5], 11 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 13 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 5], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 15 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + rcx + 5], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 3 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 4 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 10 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 11 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 13 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 5], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r14 + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 5], 8 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 14 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 15 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm6, byte ptr [rdi + rbx + 5], 1 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 4 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 6 + mov r8, rdx + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 7 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 8 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 5], 14 vinserti128 ymm14, ymm3, xmm0, 1 - vpinsrb xmm0, xmm5, byte ptr [rsi + r12 + 5], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm3, edi - vinserti128 ymm15, ymm0, xmm4, 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm4, edi - mov r11, r14 - vpinsrb xmm0, xmm12, byte ptr [rsi + r14 + 6], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 6], 3 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 6], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 5 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 8 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 9 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 6], 10 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 6], 11 - mov rax, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 15 - vpinsrb xmm5, xmm7, byte ptr [rsi + rcx + 6], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 2 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 3 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 4 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 5 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 6], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 7 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 12 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 14 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 1 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 2 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 4 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 7], 6 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 7 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 14 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 15 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 1 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 7], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 3 + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 5], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 10] + vmovd xmm3, edx + vinserti128 ymm15, ymm0, xmm4, 1 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 10] + vmovd xmm4, edx + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rcx + 6], 1 + mov r12, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 4 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 6 - mov r8, r13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 7 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 7], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 10 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 13 - vinserti128 ymm0, ymm5, xmm0, 1 - vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rax + 7], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 5 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 7 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 7], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm2, edi - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + r15 + 8], 1 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 8], 2 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 9 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 8], 5 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 6 - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 8], 8 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 9 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 10 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 10 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 13 mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 12 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 13 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 15 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rsi + rdx + 8], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 8], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 3 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 4 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 8], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 8], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 15 + vpinsrb xmm5, xmm7, byte ptr [rdi + rbx + 6], 1 mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 9 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 8], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 11 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 8], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 4 mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 13 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 14 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 15 - vpinsrb xmm6, xmm8, byte ptr [rsi + r15 + 9], 1 - mov r13, r15 - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 3 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rsi + r14 + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 6 - mov r9, rax - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 7 - vpinsrb xmm6, xmm6, byte ptr [rsi + r10 + 9], 8 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 9 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r15 + 9], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 11 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 6 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 8 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 11 + mov r14, r11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 6], 12 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 6], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 6], 14 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 3 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 6 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 7 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 8 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 12 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 14 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rsi + rax + 9], 1 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 9], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 4 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 5 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 1 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 9], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + r12 + 9], 12 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 9], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 9], 14 - vinserti128 ymm0, ymm5, xmm0, 1 - vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm0, edi - vinserti128 ymm5, ymm5, xmm6, 1 - vmovdqa ymmword ptr [rsp + 1120], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 10], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 2 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 10], 4 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 3 mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 7 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 10], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 10], 10 - mov r9, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 10], 12 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 10], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 15 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 4 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 7], 7 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 10], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 13 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 11], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 4 - mov r13, rbx - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 5 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 8 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 11], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 7], 9 + mov r8, r9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 13 + vinserti128 ymm0, ymm5, xmm0, 1 + vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill + vpinsrb xmm0, xmm1, byte ptr [rdi + r15 + 7], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 11] + vmovd xmm1, edx + mov r13, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 7], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 11] + vmovd xmm2, edx + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + rsi + 8], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 5 + mov r9, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 8], 8 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 9 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 15 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + rdx + 8], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 4 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 6 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 7 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 10 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 11 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 13 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + rsi + 9], 1 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 4 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 5 + mov rbx, r15 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 9 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 12 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 13 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 15 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rcx + 9], 1 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 6 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 8 + mov r12, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 11 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 14 + vinserti128 ymm0, ymm5, xmm0, 1 + vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 12] + vmovd xmm0, edx + vinserti128 ymm5, ymm5, xmm6, 1 + vmovdqa ymmword ptr [rsp + 1120], ymm5 # 32-byte Spill + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 12] + vmovd xmm5, edx + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 2 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 3 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 5 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 7 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 8 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 10 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 12 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 14 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 15 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 1 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 6 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 8 + mov r11, r12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 9 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 12 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 13 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 14 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 5 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 6 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 11 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 12 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 3 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 4 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 5 + mov r14, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 6 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 11], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 11], 5 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 11], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1088], ymm3 # 32-byte Spill - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 11], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 13] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 13] + vmovd xmm3, edx + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1056], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 13] - vmovd xmm1, edi - mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 12], 1 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 12], 2 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 12], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 4 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 5 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 6 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 7 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 12], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 9 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 10 - mov r14, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 12], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 12], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 15 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rsi + rax + 12], 1 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 12], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 13] + vmovd xmm1, edx + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 1 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 4 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 5 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 12], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 7 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 8 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 10 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 5 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 13 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + rax + 12], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 6 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 7 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 9 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 12], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 12], 12 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 14 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 1 - mov r15, r11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 13], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 9 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 10 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 13 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 15 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 8 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 9 mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 10 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 11 mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 13], 8 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 11 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 13], 14 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 13], 15 mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 13 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 15 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 3 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 4 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 13], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 5 mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 13], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 13], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 13], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rax + 13], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 14] - vmovd xmm1, edi + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rsi + 13], 15 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r15 + 14] + vmovd xmm1, edx vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill - mov r13, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 14] - vmovd xmm0, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 1 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 14] + vmovd xmm0, edx + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 2 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 14], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 4 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 9 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 5 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 14], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 11 + mov r13, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 12 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 3 mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 8 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 14], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 15 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 14], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 6 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 3 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 14], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 14], 5 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 14], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 7 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 14], 9 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 14], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 14], 12 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 14], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 15] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 1 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 15], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 15], 6 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 15], 7 - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 15], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 9 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 10 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 11 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 15 - movzx edi, byte ptr [rsi + r13 + 15] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 1 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 8 + mov r8, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 10 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 15], 4 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 15], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 15], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 15], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 15], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 12 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 15 + movzx edx, byte ptr [rdi + r15 + 15] + vmovd xmm2, edx + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 15], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 5 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 15], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 7 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 10 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 15] + vmovd xmm3, edx + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 4 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 9 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 11 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 15], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 16] - vmovd xmm0, edi - mov r10, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 16], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 3 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 4 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 5 + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rbx + 16] + vmovd xmm0, edx + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 16], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 8 + mov r14, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 16], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 16], 8 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 16], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 15 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 16] - vmovd xmm1, edi - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 16], 1 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 16], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 3 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 16], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 12 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 14 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 16] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 3 + mov r11, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 5 mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 6 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 7 mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 8 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 16], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 12 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 14 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 15 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 17] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 2 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 17], 5 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 17], 7 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 8 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 9 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 17], 11 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 17] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 17], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 17], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 3 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 17], 4 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 5 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 6 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 17], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 10 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 17], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 8 + mov r15, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 10 + mov r12, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 14 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 15 + movzx edx, byte ptr [rdi + rbx + 17] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 1 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 5 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 7 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 9 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 17] + vmovd xmm3, edx + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 17], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 4 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 11 + mov r10, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 12 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 13 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rax + 17], 15 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r8 + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r13 + 18] - vmovd xmm0, edi + mov r9, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r9 + 18] + vmovd xmm0, edx + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 7 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 8 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 5 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 18], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 18], 8 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 18], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 11 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 18], 12 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 18], 14 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 15 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 18] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 1 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 14 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 18] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 3 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 10 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 18], 4 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 5 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 18], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 8 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 18], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 13 + mov r14, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 15 + movzx edx, byte ptr [rdi + r9 + 19] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 1 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 2 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 3 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 5 mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 18], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 12 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 18], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 18], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 15 - movzx edi, byte ptr [rsi + r13 + 19] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 2 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 3 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 19], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 5 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 6 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 7 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 19], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 19], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 19], 8 + mov r8, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 15 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + r11 + 19] + vmovd xmm3, edx + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 6 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 8 mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 19] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 1 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 19], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 10 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 3 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 4 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 19], 5 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 19], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 19], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 19], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 19], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 11 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 20] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 1 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 2 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 4 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 5 - mov r8, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 20], 6 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 7 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 8 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 10 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 20], 11 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 20] - vmovd xmm1, edi - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 20], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 20], 2 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 20], 3 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 20], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 20], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 8 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 20], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 12 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 13 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 15 - movzx edi, byte ptr [rsi + r11 + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 2 - mov r11, rdx - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 3 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 20] + vmovd xmm0, edx + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 4 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 9 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 11 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 13 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 14 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 15 + movzx edx, byte ptr [rdi + r11 + 20] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 1 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 20], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 3 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 4 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 9 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 10 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 14 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 15 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 21] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 3 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 5 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 7 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 12 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 21], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 15 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 8 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 21], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 12 + movzx edx, byte ptr [rdi + rax + 21] + vmovd xmm3, edx mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 21] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 21], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 21], 4 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 21], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 6 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 7 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 9 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 21], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 12 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 21], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rbx + 21], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + r11 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 4 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 5 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 22], 6 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 7 + mov r10, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r10 + 22] + vmovd xmm0, edx + mov r11, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 2 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 22], 3 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 4 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 5 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 22], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 7 + mov r15, r12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 9 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 10 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 12 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 15 mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 8 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 9 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 10 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 11 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 22], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 22] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 1 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 22], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 3 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 22], 5 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 7 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 22], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 12 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 22], 15 - movzx edi, byte ptr [rsi + rcx + 23] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 6 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 23], 10 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 23], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 23], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 23] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 23], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 23], 3 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 23], 4 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 23], 5 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 23], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 23], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 9 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 23], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 23], 13 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 23], 14 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 15 - vinserti128 ymm10, ymm1, xmm0, 1 - vinserti128 ymm11, ymm3, xmm2, 1 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 24] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 2 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 4 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 5 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 24], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 24], 7 + movzx edx, byte ptr [rdi + rdx + 22] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 11 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 13 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 14 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 15 + movzx edx, byte ptr [rdi + r10 + 23] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 1 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 6 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 8 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 11 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 23], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 13 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 15 mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 8 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 24], 11 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 12 + movzx edx, byte ptr [rdi + rcx + 23] + vmovd xmm3, edx mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 15 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 24] - vmovd xmm1, edi - mov r9, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 1 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 24], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 24], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 7 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 1 mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 24], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 12 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 24], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 3 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 4 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 5 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 6 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 10 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 12 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 14 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 15 + vinserti128 ymm10, ymm1, xmm0, 1 + vinserti128 ymm11, ymm3, xmm2, 1 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 24] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 3 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 5 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 8 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 10 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 12 + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 24], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 24] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 3 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 7 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 8 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 10 + mov r12, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 15 + mov r11, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r11 + 25] + vmovd xmm2, edx + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 1 + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 6 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 7 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 25] - vmovd xmm2, edi - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 1 - mov r8, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 25], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 4 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 25], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 6 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 8 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 25], 9 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 10 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 11 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 25], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 25], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 25] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 2 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 3 - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 4 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 5 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 25], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 10 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 25], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 9 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 13 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 25], 14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 15 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 25] + vmovd xmm3, edx + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 25], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 5 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 9 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rcx + 25], 15 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r10 + 25], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 26] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 2 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 3 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 5 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 6 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 26], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 26], 12 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 13 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 26], 15 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 26] - vmovd xmm1, edi + movzx edx, byte ptr [rdi + r11 + 26] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 3 mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 1 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 26], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 4 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 5 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 6 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 7 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 26], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 4 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 5 mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 26], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 12 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 14 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 15 - movzx edi, byte ptr [rsi + rcx + 27] - vmovd xmm2, edi - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 27], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 2 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 27], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 4 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 27], 5 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 7 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 10 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 12 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 15 + movzx edx, byte ptr [rdi + rcx + 26] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 3 mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 7 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 8 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 9 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 27], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 27], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 27] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 1 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 2 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 3 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 4 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 27], 5 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 27], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 10 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 11 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 13 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 6 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 7 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 26], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 9 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 10 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 11 mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 12 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 26], 15 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r14 + 27] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 5 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 7 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 8 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 13 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 27] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 2 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 27], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 10 + mov rsi, r8 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 28], 1 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 28], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 3 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 5 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 6 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 7 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 28], 8 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 10 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 11 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 12 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 13 + movzx edx, byte ptr [rdi + r14 + 28] + vmovd xmm0, edx + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 4 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 6 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 7 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 11 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 14 mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 15 - movzx edi, byte ptr [rsi + rax + 28] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 15 + mov r10, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + r10 + 28] + vmovd xmm1, edx + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 4 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 5 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 6 mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 7 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 10 mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 3 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 5 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 10 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 28], 12 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 28], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 14 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 29] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 29], 2 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 29], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 5 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 29], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 29], 8 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 9 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 29], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 11 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 13 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 29], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 15 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsi + r15 + 29] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 3 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 29], 4 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 29], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 13 mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 29], 7 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 29], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 11 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 29], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rsi + rax + 29], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 14 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 15 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 29] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 3 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 5 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 8 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 12 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 13 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 14 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 15 + movzx edx, byte ptr [rdi + r10 + 29] + vmovd xmm3, edx + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 1 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 29], 2 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 3 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 6 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 8 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm3, byte ptr [rdi + rbx + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm4, byte ptr [rsi + r13 + 29], 15 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rax + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 30] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 30], 1 - movzx edi, byte ptr [rsi + rax + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 31], 1 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 30] + vmovd xmm0, edx + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 30], 1 + movzx edx, byte ptr [rdi + rax + 31] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 31], 1 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rdx, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 31], 9 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 31], 6 - mov r13, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 31], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 11 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 31], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + rax + 31], 15 - movzx eax, byte ptr [rsi + r15 + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + r8 + 31], 15 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 30], 1 - movzx eax, byte ptr [rsi + r15 + 31] + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 31], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + r11 + 31], 4 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 31], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 31], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 31], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 31], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 31], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 4 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 14 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r9 + 31], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, rsi + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 13 + mov rax, rbx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill - vinserti128 ymm0, ymm7, xmm2, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill + vinserti128 ymm0, ymm7, xmm2, 1 + vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill vmovdqa ymm2, ymmword ptr [rsp + 512] # 32-byte Reload vpcmpeqb ymm0, ymm13, ymm2 vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1216] # 32-byte Folded Reload @@ -25555,10 +26336,10 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 vpor ymm3, ymm5, ymm3 vpcmpeqb ymm4, ymm2, ymmword ptr [rsp + 704] # 32-byte Folded Reload vpandn ymm4, ymm4, ymm1 - vpcmpeqb ymm1, ymm2, ymmword ptr [rsp + 288] # 32-byte Folded Reload + vpcmpeqb ymm1, ymm2, ymmword ptr [rsp + 320] # 32-byte Folded Reload vpandn ymm1, ymm1, ymm13 vpor ymm1, ymm4, ymm1 - vpcmpeqb ymm2, ymm2, ymmword ptr [rsp + 320] # 32-byte Folded Reload + vpcmpeqb ymm2, ymm2, ymmword ptr [rsp + 288] # 32-byte Folded Reload vpandn ymm2, ymm2, ymm14 vpor ymm1, ymm1, ymm2 vpor ymm1, ymm3, ymm1 @@ -25575,2011 +26356,1998 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [r13 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r13 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r13 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r13 + 4*rcx], ymm1 + vmovdqu ymmword ptr [rdx + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rdx + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rdx + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rdx + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB4_167 -# %bb.168: - mov r15, qword ptr [rsp + 392] # 8-byte Reload - cmp r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 400] # 8-byte Reload - jne .LBB4_35 - jmp .LBB4_133 -.LBB4_169: - and r15, -32 - mov rax, r15 + jne .LBB4_191 +# %bb.192: + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB4_139 + jmp .LBB4_143 +.LBB4_193: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - mov qword ptr [rsp + 384], r15 # 8-byte Spill - lea rax, [r11 + 4*r15] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 376], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r12d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 272], r11 # 8-byte Spill + mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB4_170: # =>This Inner Loop Header: Depth=1 +.LBB4_194: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 408], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 128], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill mov rax, rbx or rax, 320 mov qword ptr [rsp + 160], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rcx + 1] + movzx eax, byte ptr [rdi + rcx + 1] + mov rdx, rcx vmovd xmm4, eax - movzx eax, byte ptr [rsi + rbx + 1] + mov rcx, rbx + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rsi + rcx + 2] - mov rdx, rcx + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - mov rcx, rbx - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rsi + rdx + 6] - mov qword ptr [rsp + 256], rdx # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 264], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 384 mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 88], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov rbx, rax - mov qword ptr [rsp + 240], rax # 8-byte Spill + mov qword ptr [rsp + 96], rax # 8-byte Spill + or rbx, 576 + mov qword ptr [rsp + 200], rbx # 8-byte Spill mov rax, rcx - or rax, 576 - mov qword ptr [rsp + 136], rax # 8-byte Spill - mov r12, rcx - or r12, 608 - mov qword ptr [rsp + 184], r12 # 8-byte Spill + or rax, 608 + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov r14, rcx + or r14, 640 + mov qword ptr [rsp + 144], r14 # 8-byte Spill mov rax, rcx - or rax, 640 - mov r13, rax - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov r9, rcx - or r9, 672 - mov qword ptr [rsp + 224], r9 # 8-byte Spill + or rax, 672 + mov qword ptr [rsp + 152], rax # 8-byte Spill + mov r12, rcx + or r12, 704 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov rsi, rcx + or rsi, 736 + mov qword ptr [rsp + 208], rsi # 8-byte Spill mov r15, rcx - or r15, 704 - mov qword ptr [rsp + 248], r15 # 8-byte Spill - mov rdi, rcx - or rdi, 736 - mov qword ptr [rsp + 152], rdi # 8-byte Spill - mov r14, rcx - or r14, 768 - mov qword ptr [rsp + 112], r14 # 8-byte Spill + or r15, 768 + mov qword ptr [rsp + 256], r15 # 8-byte Spill mov r11, rcx or r11, 800 - mov qword ptr [rsp + 216], r11 # 8-byte Spill + mov qword ptr [rsp + 248], r11 # 8-byte Spill mov r10, rcx or r10, 832 - mov qword ptr [rsp + 176], r10 # 8-byte Spill - mov rax, rcx - or rax, 864 - mov qword ptr [rsp + 80], rax # 8-byte Spill + mov qword ptr [rsp + 128], r10 # 8-byte Spill + mov r9, rcx + or r9, 864 + mov qword ptr [rsp + 112], r9 # 8-byte Spill mov r8, rcx or r8, 896 - mov qword ptr [rsp + 200], r8 # 8-byte Spill + mov qword ptr [rsp + 216], r8 # 8-byte Spill mov rdx, rcx or rdx, 928 - mov qword ptr [rsp + 168], rdx # 8-byte Spill + mov qword ptr [rsp + 176], rdx # 8-byte Spill mov rax, rcx - mov qword ptr [rsp + 208], rcx # 8-byte Spill + mov qword ptr [rsp + 232], rcx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 232], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 40], rcx # 8-byte Spill - vpinsrb xmm9, xmm0, byte ptr [rsi + rbx], 1 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + rbx], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 10 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 1 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 2 - mov r10, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 3 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11], 4 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12], 5 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 6 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 12 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 13 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 14 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 15 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 1 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 2 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 3 - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 4 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 5 - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 6 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 7 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 8 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 9 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 11 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 12 + mov qword ptr [rsp + 48], rcx # 8-byte Spill + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + r13], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 1 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 2 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 3 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 4 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 6 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 7 mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 13 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 14 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rsi + r14 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - mov r9, rdi - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 15 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 1 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 2 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 3 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 5 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 7 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 2 + mov rsi, r12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 11 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 12 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 vinserti128 ymm13, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 1], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm9, edx vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm10, edi - mov r8, qword ptr [rsp + 240] # 8-byte Reload + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 8] + vmovd xmm10, edx + mov rcx, qword ptr [rsp + 96] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 2], 1 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 2], 2 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 2], 3 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 4 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 5 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 2], 1 + mov r9, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 2 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 8 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 2], 9 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 10 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 11 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 2], 12 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 13 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 4 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 5 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 2], 8 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 2], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 10 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 12 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + r8 + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 3 - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 4 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 6 - mov r10, rcx - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 7 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 13 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 14 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 7 + mov r8, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 8 + mov r12, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 9 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 10 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 11 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 12 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 14 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 2 - mov r12, rax - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 4 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 7 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 8 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 9 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 10 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 13 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + rcx + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 5 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 6 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 10 + mov r8, r13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 13 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rax + 3], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 4 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 7 - mov r11, rdi - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 3], 9 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 12 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 7 + mov rax, rdx + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 8 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 11 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 14 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 9] - vmovd xmm8, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 3], 15 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rcx + 3], 14 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm8, edx + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm11, edi + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 9] + vmovd xmm11, edx + mov r14, qword ptr [rsp + 96] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 4], 1 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 2 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 4], 3 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 4 - mov rcx, r8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 4], 6 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 4], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 8 - mov r8, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 9 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 11 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 4], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 1 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 5 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 7 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 10 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 11 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 12 + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 15 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm15, byte ptr [rdi + rdx + 4], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 4], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm15, byte ptr [rsi + rax + 4], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 4], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 4 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 5 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 4], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 4], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 8 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 4], 9 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 10 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 11 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 11 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 12 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 4], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 14 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 15 - vpinsrb xmm4, xmm14, byte ptr [rsi + r9 + 5], 1 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 5], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 4 - mov r14, r13 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 5 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 5], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 5], 9 - mov r10, r8 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 10 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 12 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 13 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 15 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + r12 + 5], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 3 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 5], 4 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 13 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 5], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r14 + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 5], 8 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 14 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 15 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm6, byte ptr [rdi + rbx + 5], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 6 + mov r8, rdx + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 7 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 8 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 9 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 5], 12 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 5], 14 vinserti128 ymm14, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 5], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm3, edi + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 5], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 10] + vmovd xmm3, edx vinserti128 ymm15, ymm0, xmm4, 1 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm4, edi - mov r8, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rsi + r8 + 6], 1 - mov rcx, r9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 6], 2 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 6], 4 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 6], 5 - mov r9, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 6], 6 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 6], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 6], 9 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 6], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 11 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 6], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 13 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 14 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 15 - vpinsrb xmm5, xmm7, byte ptr [rsi + r12 + 6], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 4 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 5 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 6 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 7 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 9 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 6], 10 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 12 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 6], 13 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 14 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 7], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 2 - mov rbx, rcx - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 3 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 6 - mov r13, r9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 8 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 7], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 13 mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 14 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 7], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 1 + movzx edx, byte ptr [rdi + rcx + 10] + vmovd xmm4, edx + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rcx + 6], 1 + mov r12, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 5 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 10 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 15 + vpinsrb xmm5, xmm7, byte ptr [rdi + rbx + 6], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 6 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 8 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 11 + mov r14, r11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 6], 12 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 6], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 6], 14 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 3 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 6 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 7 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 8 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 12 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 14 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 7], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 7], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 7], 9 + mov r8, r9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 3 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 5 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 7], 10 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 7], 11 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 7], 12 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rdx + 7], 14 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 11] - vmovd xmm1, edi - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 7], 15 + vpinsrb xmm0, xmm1, byte ptr [rdi + r15 + 7], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 11] + vmovd xmm1, edx + mov r13, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 11] - vmovd xmm2, edi - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + rdx + 8], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 8], 2 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 3 - mov rdx, r15 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 8], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 8], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 8], 6 - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 8], 7 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 8], 9 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 8], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 11 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 8], 12 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 8], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 8], 15 - mov r10, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rsi + r10 + 8], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 3 - mov rdi, r8 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 8], 4 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 11] + vmovd xmm2, edx + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + rsi + 8], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 5 + mov r9, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 8], 8 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 8], 9 mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 8], 5 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 8], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 9 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 8], 10 - mov r8, r12 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 8], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 8], 12 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 8], 13 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 8], 14 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 8], 15 - mov r12, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rsi + r12 + 9], 1 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 2 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 3 - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 4 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rsi + r13 + 9], 6 - mov rcx, r13 - vpinsrb xmm6, xmm6, byte ptr [rsi + r14 + 9], 7 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 11 mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 9 - vpinsrb xmm6, xmm6, byte ptr [rsi + r15 + 9], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 15 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + rdx + 8], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 2 mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 11 - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 12 - vpinsrb xmm6, xmm6, byte ptr [rsi + r9 + 9], 13 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r12 + 9], 14 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r14 + 9], 15 - vpinsrb xmm7, xmm11, byte ptr [rsi + r10 + 9], 1 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 9], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 4 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 9], 5 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 9], 6 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 9], 7 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 9 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 9], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + r11 + 9], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 14 - vinserti128 ymm0, ymm5, xmm0, 1 - vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm0, edi - vinserti128 ymm5, ymm5, xmm6, 1 - vmovdqa ymmword ptr [rsp + 1120], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - mov r13, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 10], 1 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 4 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 6 mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 10], 3 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 4 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 5 - mov rdx, rcx - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 6 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 7 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 10 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 11 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 13 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + rsi + 9], 1 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 4 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 5 + mov rbx, r15 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 9 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 11 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 9 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 12 mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 11 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 12 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 10], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 10], 15 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 13 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 14 mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 4 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 10], 7 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 10], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 15 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rcx + 9], 1 mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 9 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 10], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 6 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 8 + mov r12, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 11 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 12 mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 11 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 14 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 11], 1 - mov rcx, r13 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 3 - mov r13, rbx - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 11], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 6 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 14 + vinserti128 ymm0, ymm5, xmm0, 1 + vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 12] + vmovd xmm0, edx + vinserti128 ymm5, ymm5, xmm6, 1 + vmovdqa ymmword ptr [rsp + 1120], ymm5 # 32-byte Spill + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 12] + vmovd xmm5, edx + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 2 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 3 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 5 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 7 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 8 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 10 mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 9 - mov rbx, rax + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 12 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 11 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 13 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 15 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 14 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 11], 4 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 15 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 1 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 11], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 11], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 11], 12 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 6 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 8 + mov r11, r12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 9 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 12 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 13 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 5 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 6 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 11 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 12 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 3 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 4 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 5 + mov r14, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 6 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1088], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 13] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 13] + vmovd xmm3, edx + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1056], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 13] - vmovd xmm1, edi - mov rax, rcx - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 12], 2 - mov rcx, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 3 - mov r13, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 13] + vmovd xmm1, edx + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 1 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 5 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 12], 6 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 7 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 8 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 13 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + rax + 12], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 6 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 9 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 10 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 13 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 15 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 8 mov r9, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 6 - mov r11, r8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 12], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 9 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 10 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 12], 11 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 12 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 12], 13 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 14 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 15 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rsi + r14 + 12], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 12], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 3 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 4 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 5 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 6 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 12], 7 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 8 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 12], 9 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 10 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 12 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 13 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 14 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 1 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 13], 4 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 8 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 13], 11 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 13], 13 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 14 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 2 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 3 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 9 mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 5 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 13], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 13], 9 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 13], 10 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 13], 11 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 13], 12 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 13], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 10 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 11 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 13], 14 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 13], 15 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 13], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + r12 + 13], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 14] - vmovd xmm1, edi + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rsi + 13], 15 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r15 + 14] + vmovd xmm1, edx vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 14] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 1 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 14], 2 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 3 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 14], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 5 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 6 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 14], 9 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 10 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 14], 11 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 14], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 14], 14 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 14], 15 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 1 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 14], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 4 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 5 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 14], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 14], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 14], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 14], 13 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 14], 15 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 15] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 3 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 4 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 5 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 6 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 7 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 15], 8 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 15], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 12 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 13 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 15], 15 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r14 + 15] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 15], 2 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 3 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 15], 4 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 15], 5 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 15], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 9 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 10 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 15], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 12 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 13 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 14 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 15 - vinserti128 ymm0, ymm0, xmm1, 1 - vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - vinserti128 ymm0, ymm3, xmm2, 1 - vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r11 + 16] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 1 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 2 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 3 - mov r11, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 16], 4 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 6 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 16], 8 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 9 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 11 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 15 - movzx edi, byte ptr [rsi + r14 + 16] - vmovd xmm1, edi - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 16], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 16], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 7 + movzx edx, byte ptr [rdi + rax + 14] + vmovd xmm0, edx mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 16], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 12 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 16], 13 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 16], 14 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 15 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rbx + 17] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 4 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 5 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 2 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 17], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 17], 4 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 17], 5 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 7 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 17], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 9 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 11 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 12 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 17], 13 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 11 + mov r13, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 12 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 6 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 8 + mov r8, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 12 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 15 + movzx edx, byte ptr [rdi + r15 + 15] + vmovd xmm2, edx + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 15], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 5 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 15], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 7 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 10 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 15] + vmovd xmm3, edx + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 4 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 9 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 15], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 15 + vinserti128 ymm0, ymm0, xmm1, 1 + vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill + vinserti128 ymm0, ymm3, xmm2, 1 + vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rbx + 16] + vmovd xmm0, edx + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 16], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 8 + mov r14, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 12 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 14 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 16] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 3 + mov r11, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 6 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 8 + mov r15, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 10 + mov r12, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 14 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 15 + movzx edx, byte ptr [rdi + rbx + 17] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 1 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 5 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 6 mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 17] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 17], 1 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 3 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 4 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 5 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 9 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 17], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 7 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 9 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 17] + vmovd xmm3, edx + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 17], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 9 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 11 + mov r10, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 12 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 13 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + r13 + 17], 15 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r8 + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + rbx + 18] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 1 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 18], 3 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 5 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 6 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 18], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 11 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 18], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 18], 14 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 18], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 18] - vmovd xmm1, edi - mov r8, r12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 18], 1 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r9 + 18] + vmovd xmm0, edx + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 7 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 8 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 14 mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 18], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 3 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 18], 4 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 18], 5 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 18], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 9 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 12 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 13 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 18], 15 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 19] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 1 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 2 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 3 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 19], 4 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 5 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 18] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 3 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 13 + mov r14, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 15 + movzx edx, byte ptr [rdi + r9 + 19] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 1 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 2 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 3 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 4 mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 8 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 9 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 19], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 13 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 19], 15 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 19] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 19], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 19], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 19], 6 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 19], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 9 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 19], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 5 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 19], 8 + mov r8, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 15 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + r11 + 19] + vmovd xmm3, edx + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 6 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 11 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 19], 12 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 14 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r13 + 20] - vmovd xmm0, edi - mov r13, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 1 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 2 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 20], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 20], 4 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 20], 5 - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 6 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 7 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 9 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 10 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 20], 11 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 12 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 13 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 14 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 15 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 20] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 1 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 2 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 3 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 4 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 20], 5 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 20], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 20], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 20], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 20], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 20], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 20] + vmovd xmm0, edx + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 4 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 7 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 21], 1 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 21], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 21], 3 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 21], 5 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 6 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 7 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 9 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 21], 11 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 21], 12 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 21], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 14 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 15 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 21] - vmovd xmm3, edi - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 21], 1 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 21], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 21], 5 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 21], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 11 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 13 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 14 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 15 + movzx edx, byte ptr [rdi + r11 + 20] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 1 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 20], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 3 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 4 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 9 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 10 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 13 mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 21], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 14 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 15 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 21] + vmovd xmm2, edx mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 21], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 21], 9 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 21], 10 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 21], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 21], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 3 mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 21], 13 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 5 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 6 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 7 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 12 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 21] + vmovd xmm3, edx + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rdx + 21], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + r11 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 22] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 2 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 22], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 22], 6 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 22], 7 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 8 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 9 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 22], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 22], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 22], 13 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 22], 14 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 22], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 22] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 22], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 22], 2 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 22], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 4 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 5 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 6 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 22], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 22], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 12 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 22], 14 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 15 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 23] - vmovd xmm2, edi - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 1 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 2 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 3 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 23], 4 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 5 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 23], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 23], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 11 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 23], 12 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 13 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 23], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 23], 15 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 23] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 1 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 23], 3 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 4 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 23], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 23], 7 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 23], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 9 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 11 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 23], 12 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 13 + mov r10, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r10 + 22] + vmovd xmm0, edx + mov r11, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 2 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 22], 3 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 4 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 5 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 22], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 7 + mov r15, r12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 9 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 10 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 12 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 22] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 3 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 10 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 11 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 13 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 14 mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 15 + movzx edx, byte ptr [rdi + r10 + 23] + vmovd xmm2, edx + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 1 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 6 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 8 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 10 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 11 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 23], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 13 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 15 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 23] + vmovd xmm3, edx mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 1 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 3 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 4 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 5 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 6 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 10 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 12 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 14 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm11, ymm3, xmm2, 1 - movzx edi, byte ptr [rsi + r13 + 24] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 24], 1 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 2 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 24], 4 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 5 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 6 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 7 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 24] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 3 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 5 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 8 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 10 mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 24], 8 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 24], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 12 mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 24], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 24], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 24], 14 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 15 - movzx edi, byte ptr [rsi + r11 + 24] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 24], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 24] + vmovd xmm1, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 3 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 7 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 8 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 10 mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 3 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 24], 5 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 24], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 24], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 9 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 24], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 13 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 24], 14 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 25] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 25], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 25], 2 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 3 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 25], 4 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 5 - mov r13, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 25], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 25], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 11 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 13 - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 25], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 15 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r14 + 25] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 1 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 25], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 4 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 25], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 7 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 25], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 25], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 11 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 15 + mov r11, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r11 + 25] + vmovd xmm2, edx + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 1 + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 3 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 6 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 9 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 13 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 25], 14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 15 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 25] + vmovd xmm3, edx + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 25], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 5 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 7 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 9 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + r11 + 25], 15 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r10 + 25], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 26] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 1 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 2 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 26], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 26], 4 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 26], 6 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 7 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 9 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 10 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 26], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 12 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 26], 14 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 26], 15 - movzx edi, byte ptr [rsi + r14 + 26] - vmovd xmm1, edi - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 26], 2 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 3 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 26], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 5 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 26], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 9 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 10 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 12 - mov r15, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 26], 13 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 26], 15 - movzx edi, byte ptr [rsi + rax + 27] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 1 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 27], 3 - mov r10, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 27], 4 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 5 - mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 27], 6 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 7 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 27], 8 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 9 + movzx edx, byte ptr [rdi + r11 + 26] + vmovd xmm0, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 3 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 4 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 5 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 7 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 8 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 10 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 12 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 27], 11 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 13 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 27], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 27], 15 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r9 + 27] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 1 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 2 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 27], 4 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 27], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 15 + movzx edx, byte ptr [rdi + rcx + 26] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 3 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 4 mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 7 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 9 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 6 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 7 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 26], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 9 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 10 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 11 mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 13 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 14 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 12 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 26], 15 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + r14 + 27] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 5 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 6 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 7 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 8 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 13 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 27] + vmovd xmm3, edx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 2 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 27], 8 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 10 + mov rsi, r8 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 28] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 1 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 2 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 6 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 28], 8 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 9 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 12 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 28], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 28], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 15 - movzx edi, byte ptr [rsi + r9 + 28] - vmovd xmm1, edi - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 28], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 2 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 28], 5 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 6 - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 7 + movzx edx, byte ptr [rdi + r14 + 28] + vmovd xmm0, edx mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 28], 9 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 10 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 28], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 12 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 28], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 28], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 29] - vmovd xmm2, edi - mov r12, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 29], 1 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 2 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 3 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 4 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 5 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 6 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 8 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 29], 10 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 29], 11 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 29], 13 - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 29], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 2 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 29] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 29], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 29], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 4 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 29], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 29], 7 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 29], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 29], 9 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 29], 13 - mov r9, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rsi + r9 + 29], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 4 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 6 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 7 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 10 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 11 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 12 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 15 + mov r10, qword ptr [rsp + 232] # 8-byte Reload + movzx edx, byte ptr [rdi + r10 + 28] + vmovd xmm1, edx + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 4 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 5 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 6 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 7 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 8 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 10 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 11 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 13 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 14 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 15 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 29] + vmovd xmm2, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 3 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 5 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 8 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 9 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 29], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 12 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 13 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 29], 14 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 15 + movzx edx, byte ptr [rdi + r10 + 29] + vmovd xmm3, edx + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 1 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 29], 2 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 3 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 6 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 8 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 11 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 13 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm3, byte ptr [rdi + rbx + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm4, byte ptr [rsi + r15 + 29], 15 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rax + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rbx + 30] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 30], 1 - movzx edi, byte ptr [rsi + rbx + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 31], 1 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 3 mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 6 - mov r11, qword ptr [rsp + 272] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 30] + vmovd xmm0, edx + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 30], 1 + movzx edx, byte ptr [rdi + rax + 31] + vmovd xmm1, edx + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 31], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rdx, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 31], 9 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 11 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 31], 11 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 31], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + rax + 31], 15 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx eax, byte ptr [rsi + rcx + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + r8 + 31], 15 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 30], 1 - movzx eax, byte ptr [rsi + rcx + 31] + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 31], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 4 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 31], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 31], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 4 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + r13 + 31], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 7 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r9 + 31], 9 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, rsi + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 31], 13 - mov rax, r9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 31], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 13 + mov rax, rbx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 14 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill - vinserti128 ymm0, ymm7, xmm2, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill + vinserti128 ymm0, ymm7, xmm2, 1 + vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill vmovdqa ymm2, ymmword ptr [rsp + 512] # 32-byte Reload vpcmpeqb ymm0, ymm13, ymm2 vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1216] # 32-byte Folded Reload @@ -27676,10 +28444,10 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 vpor ymm3, ymm5, ymm3 vpcmpeqb ymm4, ymm2, ymmword ptr [rsp + 704] # 32-byte Folded Reload vpandn ymm4, ymm4, ymm1 - vpcmpeqb ymm1, ymm2, ymmword ptr [rsp + 288] # 32-byte Folded Reload + vpcmpeqb ymm1, ymm2, ymmword ptr [rsp + 320] # 32-byte Folded Reload vpandn ymm1, ymm1, ymm13 vpor ymm1, ymm4, ymm1 - vpcmpeqb ymm2, ymm2, ymmword ptr [rsp + 320] # 32-byte Folded Reload + vpcmpeqb ymm2, ymm2, ymmword ptr [rsp + 288] # 32-byte Folded Reload vpandn ymm2, ymm2, ymm14 vpor ymm1, ymm1, ymm2 vpor ymm1, ymm3, ymm1 @@ -27696,22 +28464,22 @@ comparison_not_equal_arr_scalar_avx2: # @comparison_not_equal_arr_scalar_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [r11 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r11 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r11 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r11 + 4*rcx], ymm1 + vmovdqu ymmword ptr [rdx + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rdx + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rdx + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rdx + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB4_170 -# %bb.171: - mov r15, qword ptr [rsp + 392] # 8-byte Reload - cmp r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 400] # 8-byte Reload - jne .LBB4_89 - jmp .LBB4_125 + jne .LBB4_194 +# %bb.195: + mov rcx, qword ptr [rsp + 392] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB4_153 + jmp .LBB4_157 .Lfunc_end4: .size comparison_not_equal_arr_scalar_avx2, .Lfunc_end4-comparison_not_equal_arr_scalar_avx2 # -- End function @@ -27745,212 +28513,225 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 push r12 push rbx and rsp, -32 - sub rsp, 1280 + sub rsp, 1248 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 + mov r12, r8 mov r13, rcx cmp edi, 6 - jg .LBB5_17 + jg .LBB5_19 # %bb.1: cmp edi, 3 - jle .LBB5_32 + jle .LBB5_36 # %bb.2: cmp edi, 4 - je .LBB5_63 + je .LBB5_59 # %bb.3: cmp edi, 5 - je .LBB5_75 + je .LBB5_73 # %bb.4: cmp edi, 6 - jne .LBB5_164 + jne .LBB5_188 # %bb.5: - mov r14d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + mov r8d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_9 + je .LBB5_11 # %bb.6: - movsxd rax, r9d + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB5_9 +# %bb.7: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_7: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] - lea rdx, [rdx + 4] +.LBB5_8: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r13 - movzx r8d, byte ptr [r13 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_7 -# %bb.8: - add r13, 1 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r13 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_8 .LBB5_9: - sar r11, 5 - cmp r10, 32 - jl .LBB5_13 + sub r12, r14 + je .LBB5_188 # %bb.10: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill + add r13, 1 +.LBB5_11: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_15 +# %bb.12: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_11: # =>This Inner Loop Header: Depth=1 +.LBB5_13: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r13 # 8-byte Spill - cmp r14d, dword ptr [rdx + 124] + cmp r8d, dword ptr [rdx + 124] setne byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 120] + cmp r8d, dword ptr [rdx + 120] setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 116] + cmp r8d, dword ptr [rdx + 116] setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 112] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 108] + cmp r8d, dword ptr [rdx + 112] setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 104] + cmp r8d, dword ptr [rdx + 108] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 100] + cmp r8d, dword ptr [rdx + 104] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 92] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 88] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 84] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 80] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 76] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 72] + cmp r8d, dword ptr [rdx + 100] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 92] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 88] setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 68] + cmp r8d, dword ptr [rdx + 84] setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 60] - setne r8b - cmp r14d, dword ptr [rdx + 56] + cmp r8d, dword ptr [rdx + 80] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 76] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 52] + cmp r8d, dword ptr [rdx + 72] setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 48] + cmp r8d, dword ptr [rdx + 68] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 60] + setne dil + cmp r8d, dword ptr [rdx + 56] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] setne r11b - cmp r14d, dword ptr [rdx + 44] + cmp r8d, dword ptr [rdx + 44] setne r10b - cmp r14d, dword ptr [rdx + 40] + cmp r8d, dword ptr [rdx + 40] setne r9b - cmp r14d, dword ptr [rdx + 36] - setne dil - cmp r14d, dword ptr [rdx + 28] + cmp r8d, dword ptr [rdx + 36] + setne sil + cmp r8d, dword ptr [rdx + 28] setne al - cmp r14d, dword ptr [rdx + 24] + cmp r8d, dword ptr [rdx + 24] setne bl - cmp r14d, dword ptr [rdx + 20] - setne sil - cmp r14d, dword ptr [rdx + 16] + cmp r8d, dword ptr [rdx + 20] setne cl - cmp r14d, dword ptr [rdx + 12] + cmp r8d, dword ptr [rdx + 16] setne r12b - cmp r14d, dword ptr [rdx + 8] + cmp r8d, dword ptr [rdx + 12] setne r13b - cmp r14d, dword ptr [rdx] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 4] + cmp r8d, dword ptr [rdx + 8] setne r15b - cmp r14d, dword ptr [rdx + 32] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 64] - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 96] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r13b, 2 + cmp r8d, dword ptr [rdx] + setne byte ptr [rsp + 168] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 4] + setne r14b + cmp r8d, dword ptr [rdx + 32] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 64] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 or r13b, r15b - mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r12b, 3 + mov r14, qword ptr [rsp + 272] # 8-byte Reload + shl r12b, 4 or r12b, r13b - shl cl, 4 + shl cl, 5 or cl, r12b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 152] # 1-byte Folded Reload + or al, cl + mov byte ptr [r14], al + add sil, sil + add sil, byte ptr [rsp + 64] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r14 + 1], dil + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, byte ptr [rsp + 72] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -27964,131 +28745,146 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al + mov byte ptr [r14 + 3], al sub rdx, -128 - add r15, 4 - mov r13, r15 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_11 -# %bb.12: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 160] # 8-byte Reload -.LBB5_13: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 + add r14, 4 + mov r13, r14 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB5_13 # %bb.14: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB5_133 -# %bb.15: - mov r10, r8 - and r10, -2 + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB5_15: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB5_188 +# %bb.16: + or rax, 1 + cmp r12, rax + je .LBB5_129 +# %bb.17: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB5_16: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] +.LBB5_18: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] setne al neg al mov rsi, rdi shr rsi, 3 - mov r11, r13 - movzx r9d, byte ptr [r13 + rsi] + mov r14, r13 + movzx r10d, byte ptr [r13 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b + xor bl, r10b mov byte ptr [r13 + rsi], bl add rdi, 2 - cmp r14d, dword ptr [rdx + 4] + cmp r8d, dword ptr [rdx + 4] lea rdx, [rdx + 8] - setne r9b - neg r9b - xor r9b, bl + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl mov byte ptr [r13 + rsi], al - cmp r10, rdi - jne .LBB5_16 - jmp .LBB5_160 -.LBB5_17: + cmp r11, rdi + jne .LBB5_18 + jmp .LBB5_177 +.LBB5_19: cmp edi, 8 - jle .LBB5_49 -# %bb.18: + jle .LBB5_43 +# %bb.20: cmp edi, 9 je .LBB5_86 -# %bb.19: +# %bb.21: cmp edi, 11 - je .LBB5_97 -# %bb.20: + je .LBB5_99 +# %bb.22: cmp edi, 12 - jne .LBB5_164 -# %bb.21: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jne .LBB5_188 +# %bb.23: + mov r14, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero sub r9d, eax - je .LBB5_25 -# %bb.22: - movsxd rax, r9d + je .LBB5_29 +# %bb.24: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB5_27 +# %bb.25: + movsxd rsi, r9d + vmovq xmm0, r14 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_23: # =>This Inner Loop Header: Depth=1 - vucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] +.LBB5_26: # =>This Inner Loop Header: Depth=1 + vucomisd xmm0, qword ptr [rcx] + lea rdx, [rcx + 8] setp cl setne bl or bl, cl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r14, r13 - movzx r9d, byte ptr [r13 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_23 -# %bb.24: + mov byte ptr [r13 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_26 +.LBB5_27: + sub r12, r8 + je .LBB5_188 +# %bb.28: add r13, 1 -.LBB5_25: - sar r11, 5 - cmp r10, 32 - jl .LBB5_29 -# %bb.26: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 192], r11 # 8-byte Spill - mov qword ptr [rsp + 184], r11 # 8-byte Spill +.LBB5_29: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_33 +# %bb.30: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 184], r14 # 8-byte Spill + vmovq xmm0, r14 + mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_27: # =>This Inner Loop Header: Depth=1 +.LBB5_31: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r13 # 8-byte Spill vucomisd xmm0, qword ptr [rdx] setp al setne cl or cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 8] setp al setne r13b @@ -28097,7 +28893,7 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 24] setp al setne cl @@ -28107,7 +28903,7 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 40] setp al setne r12b @@ -28116,7 +28912,7 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 56] setp al setne cl @@ -28126,17 +28922,17 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 72] setp al setne cl or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 80] setp al setne cl or cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 136], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 88] setp al setne bl @@ -28150,82 +28946,82 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 112] setp al setne cl or cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 120] setp al setne cl or cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 128] setp al setne cl or cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 136] setp al setne cl or cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 144] setp al setne cl or cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 88], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 152] setp al setne cl or cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 160] setp al setne cl or cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 168] setp al setne cl or cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill + mov byte ptr [rsp + 168], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 176] setp al setne r15b or r15b, al vucomisd xmm0, qword ptr [rdx + 184] setp al - setne r8b - or r8b, al + setne r10b + or r10b, al vucomisd xmm0, qword ptr [rdx + 192] setp al setne cl or cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 200] setp al setne r11b or r11b, al vucomisd xmm0, qword ptr [rdx + 208] setp al - setne r10b - or r10b, al - vucomisd xmm0, qword ptr [rdx + 216] - setp al setne r9b or r9b, al + vucomisd xmm0, qword ptr [rdx + 216] + setp al + setne r8b + or r8b, al vucomisd xmm0, qword ptr [rdx + 224] setp al setne cl or cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill + mov byte ptr [rsp + 176], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 232] setp al setne cl or cl, al - mov byte ptr [rsp + 168], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomisd xmm0, qword ptr [rdx + 240] setp al setne dil @@ -28235,23 +29031,23 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setne sil or sil, al add r13b, r13b - add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload mov eax, r13d shl r12b, 5 - movzx r13d, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 152] # 1-byte Folded Reload shl r13b, 6 or r13b, r12b - movzx r12d, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 48] # 1-byte Folded Reload shl r12b, 2 or r12b, al - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 32] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -28260,315 +29056,350 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 or al, r12b shl bl, 3 or bl, cl - movzx r13d, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload shl r13b, 4 or r13b, al movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, bl mov byte ptr [rsp + 288], al # 1-byte Spill - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 5 - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 6 or al, cl mov ecx, eax - movzx r14d, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx r14d, byte ptr [rsp + 104] # 1-byte Folded Reload shl r14b, 7 or r14b, al - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 88] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload shl bl, 2 or bl, cl - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 3 or cl, bl mov r12d, ecx mov rcx, qword ptr [rsp + 272] # 8-byte Reload - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 4 or bl, r12b movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload or al, r13b - movzx r12d, byte ptr [rsp + 176] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 168] # 1-byte Folded Reload shl r12b, 5 shl r15b, 6 or r15b, r12b or r14b, byte ptr [rsp + 288] # 1-byte Folded Reload - shl r8b, 7 - or r8b, r15b - or r8b, bl + shl r10b, 7 + or r10b, r15b + or r10b, bl add r11b, r11b - add r11b, byte ptr [rsp + 152] # 1-byte Folded Reload - shl r10b, 2 - or r10b, r11b - shl r9b, 3 - or r9b, r10b - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 64] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 + or r8b, r9b + movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload shl bl, 4 - or bl, r9b - mov r9d, ebx + or bl, r8b + mov r8d, ebx mov byte ptr [rcx], al - movzx ebx, byte ptr [rsp + 168] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 5 shl dil, 6 or dil, bl mov byte ptr [rcx + 1], r14b shl sil, 7 or sil, dil - or sil, r9b - mov byte ptr [rcx + 2], r8b + or sil, r8b + mov byte ptr [rcx + 2], r10b mov byte ptr [rcx + 3], sil add rdx, 256 add rcx, 4 mov r13, rcx - add qword ptr [rsp + 184], -1 # 8-byte Folded Spill - jne .LBB5_27 -# %bb.28: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 192] # 8-byte Reload -.LBB5_29: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 -# %bb.30: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB5_134 -# %bb.31: + add qword ptr [rsp + 192], -1 # 8-byte Folded Spill + jne .LBB5_31 +# %bb.32: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14, qword ptr [rsp + 184] # 8-byte Reload + mov rax, qword ptr [rsp + 200] # 8-byte Reload +.LBB5_33: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB5_188 +# %bb.34: + vmovq xmm0, r14 + or rax, 1 + cmp r12, rax + jne .LBB5_158 +# %bb.35: xor edi, edi - jmp .LBB5_136 -.LBB5_32: + jmp .LBB5_160 +.LBB5_36: cmp edi, 2 - je .LBB5_108 -# %bb.33: + je .LBB5_112 +# %bb.37: cmp edi, 3 - jne .LBB5_164 -# %bb.34: - mov r11b, byte ptr [rsi] - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + jne .LBB5_188 +# %bb.38: + mov r14b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_38 -# %bb.35: - movsxd rax, r9d + je .LBB5_130 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB5_132 +# %bb.40: + movsxd rsi, r9d + mov r11, r8 + .p2align 4, 0x90 +.LBB5_41: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r14b, byte ptr [rdx] + setne dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r13 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB5_41 +# %bb.42: + sub r12, r8 + jne .LBB5_133 + jmp .LBB5_188 +.LBB5_43: + cmp edi, 7 + je .LBB5_117 +# %bb.44: + cmp edi, 8 + jne .LBB5_188 +# %bb.45: + mov r8, qword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB5_51 +# %bb.46: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB5_49 +# %bb.47: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_36: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx] - lea rdx, [rdx + 1] +.LBB5_48: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 mov r15, r13 - movzx r9d, byte ptr [r13 + rsi] + movzx r9d, byte ptr [r13 + rdi] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_36 -# %bb.37: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r13 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_48 +.LBB5_49: + sub r12, r14 + je .LBB5_188 +# %bb.50: add r13, 1 -.LBB5_38: - sar r14, 5 - cmp r10, 32 - jl .LBB5_46 -# %bb.39: - cmp r14, 32 - mov dword ptr [rsp + 28], r11d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 384], r14 # 8-byte Spill - jb .LBB5_42 -# %bb.40: - mov rax, r14 - shl rax, 5 - add rax, rdx - cmp r13, rax - jae .LBB5_165 -# %bb.41: - lea rax, [4*r14] - add rax, r13 - cmp rdx, rax - jae .LBB5_165 -.LBB5_42: - xor eax, eax - mov qword ptr [rsp + 376], rax # 8-byte Spill -.LBB5_43: - sub r14, qword ptr [rsp + 376] # 8-byte Folded Reload - mov qword ptr [rsp + 160], r14 # 8-byte Spill +.LBB5_51: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_55 +# %bb.52: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_44: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx + 31] - setne byte ptr [rsp + 272] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 30] +.LBB5_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r13 # 8-byte Spill + cmp r8, qword ptr [rdx + 248] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 240] setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 29] + cmp r8, qword ptr [rdx + 232] setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 28] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 27] + cmp r8, qword ptr [rdx + 224] setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 26] + cmp r8, qword ptr [rdx + 216] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 25] + cmp r8, qword ptr [rdx + 208] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 23] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 22] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 21] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 20] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 19] + cmp r8, qword ptr [rdx + 200] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 184] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 176] + setne byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 168] setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 18] + cmp r8, qword ptr [rdx + 160] setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 17] + cmp r8, qword ptr [rdx + 152] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 15] - setne r14b - cmp r11b, byte ptr [rdx + 14] + cmp r8, qword ptr [rdx + 144] setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 13] + cmp r8, qword ptr [rdx + 136] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 12] - setne r12b - cmp r11b, byte ptr [rdx + 11] - setne r15b - cmp r11b, byte ptr [rdx + 10] + cmp r8, qword ptr [rdx + 120] + setne dil + cmp r8, qword ptr [rdx + 112] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 104] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 96] setne r11b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 9] + cmp r8, qword ptr [rdx + 88] setne r10b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 7] - setne dil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 6] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 5] + cmp r8, qword ptr [rdx + 80] setne r9b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 4] - setne r8b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 3] + cmp r8, qword ptr [rdx + 72] setne sil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 2] + cmp r8, qword ptr [rdx + 56] + setne al + cmp r8, qword ptr [rdx + 48] + setne bl + cmp r8, qword ptr [rdx + 40] setne cl - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx] + cmp r8, qword ptr [rdx + 32] + setne r12b + cmp r8, qword ptr [rdx + 24] + setne r13b + cmp r8, qword ptr [rdx + 16] + setne r15b + cmp r8, qword ptr [rdx] setne byte ptr [rsp + 168] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 1] - setne al - mov rbx, r13 - mov r13d, dword ptr [rsp + 28] # 4-byte Reload - cmp r13b, byte ptr [rdx + 8] - mov r13, rbx - setne byte ptr [rsp + 152] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp bl, byte ptr [rdx + 16] - setne byte ptr [rsp + 144] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp bl, byte ptr [rdx + 24] + cmp r8, qword ptr [rdx + 8] + setne r14b + cmp r8, qword ptr [rdx + 64] setne byte ptr [rsp + 64] # 1-byte Folded Spill - add al, al - add al, byte ptr [rsp + 168] # 1-byte Folded Reload - shl cl, 2 - or cl, al - shl sil, 3 - or sil, cl - shl r8b, 4 - or r8b, sil - shl r9b, 5 - or r9b, r8b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 6 - shl dil, 7 - or dil, al - or dil, r9b - mov byte ptr [r13], dil - add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r10b - shl r15b, 3 - or r15b, r11b - mov r11d, dword ptr [rsp + 28] # 4-byte Reload + cmp r8, qword ptr [rdx + 128] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 + or r13b, r15b + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r12b, 4 - or r12b, r15b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or r12b, r13b + shl cl, 5 + or cl, r12b + shl bl, 6 + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r14], al + add sil, sil + add sil, byte ptr [rsp + 64] # 1-byte Folded Reload + shl r9b, 2 + or r9b, sil + shl r10b, 3 + or r10b, r9b + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 - or al, r12b - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + or al, r11b + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r14b, 7 - or r14b, cl - or r14b, al - mov byte ptr [r13 + 1], r14b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r14 + 1], dil + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 72] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r13 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 64] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -28578,256 +29409,265 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 mov ecx, eax movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r13 + 3], al - add rdx, 32 - add r13, 4 + mov byte ptr [r14 + 3], al + add rdx, 256 + add r14, 4 + mov r13, r14 add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB5_44 -# %bb.45: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14, qword ptr [rsp + 384] # 8-byte Reload -.LBB5_46: - shl r14, 5 - cmp r14, r10 - jge .LBB5_164 -# %bb.47: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - je .LBB5_122 -# %bb.138: - mov r10, r8 - and r10, -2 - xor esi, esi + jne .LBB5_53 +# %bb.54: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB5_55: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB5_188 +# %bb.56: + or rax, 1 + cmp r12, rax + je .LBB5_98 +# %bb.57: + mov r11, r9 + and r11, -2 + xor edi, edi .p2align 4, 0x90 -.LBB5_139: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx + rsi] +.LBB5_58: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] setne al neg al - mov rdi, rsi - shr rdi, 3 - mov ecx, esi + mov rsi, rdi + shr rsi, 3 + mov r14, r13 + movzx r10d, byte ptr [r13 + rsi] + mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - movzx r9d, byte ptr [r13 + rdi] - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b - mov byte ptr [r13 + rdi], bl - cmp r11b, byte ptr [rdx + rsi + 1] - lea rsi, [rsi + 2] - setne r9b - neg r9b - xor r9b, bl + xor bl, r10b + mov byte ptr [r13 + rsi], bl + add rdi, 2 + cmp r8, qword ptr [rdx + 8] + lea rdx, [rdx + 16] + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl - mov byte ptr [r13 + rdi], al - cmp r10, rsi - jne .LBB5_139 - jmp .LBB5_155 -.LBB5_49: - cmp edi, 7 - je .LBB5_123 -# %bb.50: - cmp edi, 8 - jne .LBB5_164 -# %bb.51: - mov r14, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + mov byte ptr [r13 + rsi], al + cmp r11, rdi + jne .LBB5_58 + jmp .LBB5_168 +.LBB5_59: + movzx r8d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_55 -# %bb.52: - movsxd rax, r9d + je .LBB5_65 +# %bb.60: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB5_63 +# %bb.61: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_53: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] - lea rdx, [rdx + 8] +.LBB5_62: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r8w, word ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r13 - movzx r8d, byte ptr [r13 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_53 -# %bb.54: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r13 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_62 +.LBB5_63: + sub r12, r14 + je .LBB5_188 +# %bb.64: add r13, 1 -.LBB5_55: - sar r11, 5 - cmp r10, 32 - jl .LBB5_59 -# %bb.56: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill +.LBB5_65: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_69 +# %bb.66: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_57: # =>This Inner Loop Header: Depth=1 +.LBB5_67: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r13 # 8-byte Spill - cmp r14, qword ptr [rdx + 248] + cmp r8w, word ptr [rdx + 62] setne byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 240] + cmp r8w, word ptr [rdx + 60] setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 232] + cmp r8w, word ptr [rdx + 58] setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 224] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 216] + cmp r8w, word ptr [rdx + 56] setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 208] + cmp r8w, word ptr [rdx + 54] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 200] + cmp r8w, word ptr [rdx + 52] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 184] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 176] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 168] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 160] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 152] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 144] + cmp r8w, word ptr [rdx + 50] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 46] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 44] setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 136] + cmp r8w, word ptr [rdx + 42] setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 120] - setne r8b - cmp r14, qword ptr [rdx + 112] + cmp r8w, word ptr [rdx + 40] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 38] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 104] + cmp r8w, word ptr [rdx + 36] setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 96] + cmp r8w, word ptr [rdx + 34] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 30] + setne dil + cmp r8w, word ptr [rdx + 28] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 26] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 24] setne r11b - cmp r14, qword ptr [rdx + 88] + cmp r8w, word ptr [rdx + 22] setne r10b - cmp r14, qword ptr [rdx + 80] + cmp r8w, word ptr [rdx + 20] setne r9b - cmp r14, qword ptr [rdx + 72] - setne dil - cmp r14, qword ptr [rdx + 56] + cmp r8w, word ptr [rdx + 18] + setne sil + cmp r8w, word ptr [rdx + 14] setne al - cmp r14, qword ptr [rdx + 48] + cmp r8w, word ptr [rdx + 12] setne bl - cmp r14, qword ptr [rdx + 40] - setne sil - cmp r14, qword ptr [rdx + 32] + cmp r8w, word ptr [rdx + 10] setne cl - cmp r14, qword ptr [rdx + 24] + cmp r8w, word ptr [rdx + 8] setne r12b - cmp r14, qword ptr [rdx + 16] + cmp r8w, word ptr [rdx + 6] setne r13b - cmp r14, qword ptr [rdx] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 8] + cmp r8w, word ptr [rdx + 4] setne r15b - cmp r14, qword ptr [rdx + 64] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 128] - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 192] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r13b, 2 + cmp r8w, word ptr [rdx] + setne byte ptr [rsp + 168] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 2] + setne r14b + cmp r8w, word ptr [rdx + 16] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 32] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 48] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 or r13b, r15b - mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r12b, 3 + mov r14, qword ptr [rsp + 272] # 8-byte Reload + shl r12b, 4 or r12b, r13b - shl cl, 4 + shl cl, 5 or cl, r12b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 152] # 1-byte Folded Reload + or al, cl + mov byte ptr [r14], al + add sil, sil + add sil, byte ptr [rsp + 64] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r14 + 1], dil + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, byte ptr [rsp + 72] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -28841,249 +29681,261 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al - add rdx, 256 - add r15, 4 - mov r13, r15 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_57 -# %bb.58: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 160] # 8-byte Reload -.LBB5_59: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 -# %bb.60: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB5_96 -# %bb.61: - mov r10, r8 - and r10, -2 + mov byte ptr [r14 + 3], al + add rdx, 64 + add r14, 4 + mov r13, r14 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB5_67 +# %bb.68: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB5_69: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB5_188 +# %bb.70: + or rax, 1 + cmp r12, rax + je .LBB5_85 +# %bb.71: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB5_62: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] +.LBB5_72: # =>This Inner Loop Header: Depth=1 + cmp r8w, word ptr [rdx] setne al neg al mov rsi, rdi shr rsi, 3 - mov r11, r13 - movzx r9d, byte ptr [r13 + rsi] + mov r14, r13 + movzx r10d, byte ptr [r13 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b + xor bl, r10b mov byte ptr [r13 + rsi], bl add rdi, 2 - cmp r14, qword ptr [rdx + 8] - lea rdx, [rdx + 16] - setne r9b - neg r9b - xor r9b, bl + cmp r8w, word ptr [rdx + 2] + lea rdx, [rdx + 4] + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl mov byte ptr [r13 + rsi], al - cmp r10, rdi - jne .LBB5_62 - jmp .LBB5_146 -.LBB5_63: - movzx r14d, word ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + cmp r11, rdi + jne .LBB5_72 + jmp .LBB5_164 +.LBB5_73: + movzx r8d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_67 -# %bb.64: - movsxd rax, r9d + je .LBB5_79 +# %bb.74: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB5_77 +# %bb.75: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_65: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] +.LBB5_76: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r8w, word ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r13 - movzx r8d, byte ptr [r13 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_65 -# %bb.66: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r13 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_76 +.LBB5_77: + sub r12, r14 + je .LBB5_188 +# %bb.78: add r13, 1 -.LBB5_67: - sar r11, 5 - cmp r10, 32 - jl .LBB5_71 -# %bb.68: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill +.LBB5_79: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_83 +# %bb.80: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_69: # =>This Inner Loop Header: Depth=1 +.LBB5_81: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r13 # 8-byte Spill - cmp r14w, word ptr [rdx + 62] + cmp r8w, word ptr [rdx + 62] setne byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 60] + cmp r8w, word ptr [rdx + 60] setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 58] + cmp r8w, word ptr [rdx + 58] setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 56] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 54] + cmp r8w, word ptr [rdx + 56] setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 52] + cmp r8w, word ptr [rdx + 54] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 50] + cmp r8w, word ptr [rdx + 52] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 46] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 44] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 42] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 40] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 38] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 36] + cmp r8w, word ptr [rdx + 50] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 46] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 44] setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 34] + cmp r8w, word ptr [rdx + 42] setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 30] - setne r8b - cmp r14w, word ptr [rdx + 28] + cmp r8w, word ptr [rdx + 40] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 38] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 26] + cmp r8w, word ptr [rdx + 36] setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 24] + cmp r8w, word ptr [rdx + 34] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 30] + setne dil + cmp r8w, word ptr [rdx + 28] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 26] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 24] setne r11b - cmp r14w, word ptr [rdx + 22] + cmp r8w, word ptr [rdx + 22] setne r10b - cmp r14w, word ptr [rdx + 20] + cmp r8w, word ptr [rdx + 20] setne r9b - cmp r14w, word ptr [rdx + 18] - setne dil - cmp r14w, word ptr [rdx + 14] + cmp r8w, word ptr [rdx + 18] + setne sil + cmp r8w, word ptr [rdx + 14] setne al - cmp r14w, word ptr [rdx + 12] + cmp r8w, word ptr [rdx + 12] setne bl - cmp r14w, word ptr [rdx + 10] - setne sil - cmp r14w, word ptr [rdx + 8] + cmp r8w, word ptr [rdx + 10] setne cl - cmp r14w, word ptr [rdx + 6] + cmp r8w, word ptr [rdx + 8] setne r12b - cmp r14w, word ptr [rdx + 4] + cmp r8w, word ptr [rdx + 6] setne r13b - cmp r14w, word ptr [rdx] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 2] + cmp r8w, word ptr [rdx + 4] setne r15b - cmp r14w, word ptr [rdx + 16] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 32] - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 48] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r13b, 2 + cmp r8w, word ptr [rdx] + setne byte ptr [rsp + 168] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 2] + setne r14b + cmp r8w, word ptr [rdx + 16] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 32] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 48] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 or r13b, r15b - mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r12b, 3 + mov r14, qword ptr [rsp + 272] # 8-byte Reload + shl r12b, 4 or r12b, r13b - shl cl, 4 + shl cl, 5 or cl, r12b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 152] # 1-byte Folded Reload + or al, cl + mov byte ptr [r14], al + add sil, sil + add sil, byte ptr [rsp + 64] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r14 + 1], dil + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, byte ptr [rsp + 72] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -29097,472 +29949,228 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al + mov byte ptr [r14 + 3], al add rdx, 64 - add r15, 4 - mov r13, r15 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_69 -# %bb.70: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 160] # 8-byte Reload -.LBB5_71: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 -# %bb.72: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB5_85 -# %bb.73: - mov r10, r8 - and r10, -2 + add r14, 4 + mov r13, r14 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB5_81 +# %bb.82: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB5_83: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB5_188 +# %bb.84: + or rax, 1 + cmp r12, rax + jne .LBB5_162 +.LBB5_85: xor edi, edi - .p2align 4, 0x90 -.LBB5_74: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - setne al - neg al - mov rsi, rdi - shr rsi, 3 - mov r11, r13 - movzx r9d, byte ptr [r13 + rsi] - mov ecx, edi - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r13 + rsi], bl - add rdi, 2 - cmp r14w, word ptr [rdx + 2] - lea rdx, [rdx + 4] - setne r9b - neg r9b - xor r9b, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, r9b - xor al, bl - mov byte ptr [r13 + rsi], al - cmp r10, rdi - jne .LBB5_74 - jmp .LBB5_142 -.LBB5_75: - movzx r14d, word ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jmp .LBB5_164 +.LBB5_86: + mov r8, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_79 -# %bb.76: - movsxd rax, r9d + je .LBB5_92 +# %bb.87: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB5_90 +# %bb.88: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_77: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] +.LBB5_89: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r13 - movzx r8d, byte ptr [r13 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_77 -# %bb.78: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r13 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_89 +.LBB5_90: + sub r12, r14 + je .LBB5_188 +# %bb.91: add r13, 1 -.LBB5_79: - sar r11, 5 - cmp r10, 32 - jl .LBB5_83 -# %bb.80: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill +.LBB5_92: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_96 +# %bb.93: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_81: # =>This Inner Loop Header: Depth=1 +.LBB5_94: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r13 # 8-byte Spill - cmp r14w, word ptr [rdx + 62] + cmp r8, qword ptr [rdx + 248] setne byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 60] + cmp r8, qword ptr [rdx + 240] setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 58] + cmp r8, qword ptr [rdx + 232] setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 56] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 54] + cmp r8, qword ptr [rdx + 224] setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 52] + cmp r8, qword ptr [rdx + 216] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 50] + cmp r8, qword ptr [rdx + 208] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 46] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 44] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 42] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 40] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 38] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 36] + cmp r8, qword ptr [rdx + 200] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 184] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 176] setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 34] + cmp r8, qword ptr [rdx + 168] setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 30] - setne r8b - cmp r14w, word ptr [rdx + 28] + cmp r8, qword ptr [rdx + 160] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 152] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 26] + cmp r8, qword ptr [rdx + 144] setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 24] - setne r11b - cmp r14w, word ptr [rdx + 22] - setne r10b - cmp r14w, word ptr [rdx + 20] - setne r9b - cmp r14w, word ptr [rdx + 18] - setne dil - cmp r14w, word ptr [rdx + 14] - setne al - cmp r14w, word ptr [rdx + 12] - setne bl - cmp r14w, word ptr [rdx + 10] - setne sil - cmp r14w, word ptr [rdx + 8] - setne cl - cmp r14w, word ptr [rdx + 6] - setne r12b - cmp r14w, word ptr [rdx + 4] - setne r13b - cmp r14w, word ptr [rdx] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 2] - setne r15b - cmp r14w, word ptr [rdx + 16] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 32] + cmp r8, qword ptr [rdx + 136] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 48] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r13b, 2 - or r13b, r15b - mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r12b, 3 - or r12b, r13b - shl cl, 4 - or cl, r12b - shl sil, 5 - or sil, cl - shl bl, 6 - shl al, 7 - or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 152] # 1-byte Folded Reload - shl r9b, 2 - or r9b, dil - shl r10b, 3 - or r10b, r9b - shl r11b, 4 - or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 5 - or al, r11b - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r15 + 3], al - add rdx, 64 - add r15, 4 - mov r13, r15 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_81 -# %bb.82: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 160] # 8-byte Reload -.LBB5_83: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 -# %bb.84: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB5_140 -.LBB5_85: - xor edi, edi - jmp .LBB5_142 -.LBB5_86: - mov r14, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB5_90 -# %bb.87: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB5_88: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] - lea rdx, [rdx + 8] - setne bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r13 - movzx r8d, byte ptr [r13 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_88 -# %bb.89: - add r13, 1 -.LBB5_90: - sar r11, 5 - cmp r10, 32 - jl .LBB5_94 -# %bb.91: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB5_92: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r13 # 8-byte Spill - cmp r14, qword ptr [rdx + 248] - setne byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 240] - setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 232] - setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 224] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 216] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 208] - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 200] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 184] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 176] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 168] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 160] + cmp r8, qword ptr [rdx + 120] + setne dil + cmp r8, qword ptr [rdx + 112] setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 152] + cmp r8, qword ptr [rdx + 104] setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 144] - setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 136] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 120] - setne r8b - cmp r14, qword ptr [rdx + 112] - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 104] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 96] + cmp r8, qword ptr [rdx + 96] setne r11b - cmp r14, qword ptr [rdx + 88] + cmp r8, qword ptr [rdx + 88] setne r10b - cmp r14, qword ptr [rdx + 80] + cmp r8, qword ptr [rdx + 80] setne r9b - cmp r14, qword ptr [rdx + 72] - setne dil - cmp r14, qword ptr [rdx + 56] + cmp r8, qword ptr [rdx + 72] + setne sil + cmp r8, qword ptr [rdx + 56] setne al - cmp r14, qword ptr [rdx + 48] + cmp r8, qword ptr [rdx + 48] setne bl - cmp r14, qword ptr [rdx + 40] - setne sil - cmp r14, qword ptr [rdx + 32] + cmp r8, qword ptr [rdx + 40] setne cl - cmp r14, qword ptr [rdx + 24] + cmp r8, qword ptr [rdx + 32] setne r12b - cmp r14, qword ptr [rdx + 16] + cmp r8, qword ptr [rdx + 24] setne r13b - cmp r14, qword ptr [rdx] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 8] + cmp r8, qword ptr [rdx + 16] setne r15b - cmp r14, qword ptr [rdx + 64] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 128] - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 192] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r13b, 2 + cmp r8, qword ptr [rdx] + setne byte ptr [rsp + 168] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 8] + setne r14b + cmp r8, qword ptr [rdx + 64] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 128] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 or r13b, r15b - mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r12b, 3 + mov r14, qword ptr [rsp + 272] # 8-byte Reload + shl r12b, 4 or r12b, r13b - shl cl, 4 + shl cl, 5 or cl, r12b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 152] # 1-byte Folded Reload + or al, cl + mov byte ptr [r14], al + add sil, sil + add sil, byte ptr [rsp + 64] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r14 + 1], dil + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, byte ptr [rsp + 72] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -29576,86 +30184,101 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al + mov byte ptr [r14 + 3], al add rdx, 256 - add r15, 4 - mov r13, r15 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_92 -# %bb.93: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 160] # 8-byte Reload -.LBB5_94: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 + add r14, 4 + mov r13, r14 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB5_94 # %bb.95: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB5_144 + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload .LBB5_96: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB5_188 +# %bb.97: + or rax, 1 + cmp r12, rax + jne .LBB5_166 +.LBB5_98: xor edi, edi - jmp .LBB5_146 -.LBB5_97: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jmp .LBB5_168 +.LBB5_99: + mov r14d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB5_101 -# %bb.98: - movsxd rax, r9d + je .LBB5_105 +# %bb.100: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB5_103 +# %bb.101: + movsxd rsi, r9d + vmovd xmm0, r14d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_99: # =>This Inner Loop Header: Depth=1 - vucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] +.LBB5_102: # =>This Inner Loop Header: Depth=1 + vucomiss xmm0, dword ptr [rcx] + lea rdx, [rcx + 4] setp cl setne bl or bl, cl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r14, r13 - movzx r9d, byte ptr [r13 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_99 -# %bb.100: + mov byte ptr [r13 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_102 +.LBB5_103: + sub r12, r8 + je .LBB5_188 +# %bb.104: add r13, 1 -.LBB5_101: - sar r11, 5 - cmp r10, 32 - jl .LBB5_105 -# %bb.102: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 184], r11 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill +.LBB5_105: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_109 +# %bb.106: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov dword ptr [rsp + 192], r14d # 4-byte Spill + vmovd xmm0, r14d + mov qword ptr [rsp + 184], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_103: # =>This Inner Loop Header: Depth=1 +.LBB5_107: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r13 # 8-byte Spill vucomiss xmm0, dword ptr [rdx] setp al setne cl or cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 4] setp al setne r13b @@ -29664,7 +30287,7 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 12] setp al setne cl @@ -29674,7 +30297,7 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 20] setp al setne r12b @@ -29683,7 +30306,7 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 152], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 28] setp al setne cl @@ -29693,17 +30316,17 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 36] setp al setne cl or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 40] setp al setne cl or cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 136], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 44] setp al setne bl @@ -29717,27 +30340,27 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 56] setp al setne cl or cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 60] setp al setne cl or cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 64] setp al setne cl or cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 68] setp al setne cl or cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 72] setp al setne r15b @@ -29746,52 +30369,52 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setp al setne cl or cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 88], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 80] setp al setne cl or cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 84] setp al setne cl or cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 88] setp al setne r14b or r14b, al vucomiss xmm0, dword ptr [rdx + 92] setp al - setne r8b - or r8b, al + setne r10b + or r10b, al vucomiss xmm0, dword ptr [rdx + 96] setp al setne cl or cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 100] setp al setne r11b or r11b, al vucomiss xmm0, dword ptr [rdx + 104] setp al - setne r10b - or r10b, al - vucomiss xmm0, dword ptr [rdx + 108] - setp al setne r9b or r9b, al + vucomiss xmm0, dword ptr [rdx + 108] + setp al + setne r8b + or r8b, al vucomiss xmm0, dword ptr [rdx + 112] setp al setne cl or cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill + mov byte ptr [rsp + 168], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 116] setp al setne cl or cl, al - mov byte ptr [rsp + 168], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill vucomiss xmm0, dword ptr [rdx + 120] setp al setne dil @@ -29801,23 +30424,23 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 setne sil or sil, al add r13b, r13b - add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload mov eax, r13d shl r12b, 5 - movzx r13d, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 152] # 1-byte Folded Reload shl r13b, 6 or r13b, r12b - movzx r12d, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 48] # 1-byte Folded Reload shl r12b, 2 or r12b, al - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 32] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 or al, r13b mov byte ptr [rsp + 28], al # 1-byte Spill - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -29826,56 +30449,56 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 or al, r12b shl bl, 3 or bl, cl - movzx r13d, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload shl r13b, 4 or r13b, al movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, bl mov byte ptr [rsp + 288], al # 1-byte Spill - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 5 - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 6 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 7 or al, cl - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + add cl, byte ptr [rsp + 128] # 1-byte Folded Reload shl r15b, 2 or r15b, cl - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 3 or cl, r15b mov ebx, ecx mov r15, qword ptr [rsp + 272] # 8-byte Reload - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 4 or cl, bl movzx r12d, byte ptr [rsp + 28] # 1-byte Folded Reload or r12b, r13b - movzx ebx, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload shl bl, 5 shl r14b, 6 or r14b, bl or al, byte ptr [rsp + 288] # 1-byte Folded Reload - shl r8b, 7 - or r8b, r14b - or r8b, cl + shl r10b, 7 + or r10b, r14b + or r10b, cl add r11b, r11b - add r11b, byte ptr [rsp + 104] # 1-byte Folded Reload - shl r10b, 2 - or r10b, r11b - shl r9b, 3 - or r9b, r10b - movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 72] # 1-byte Folded Reload + shl r9b, 2 + or r9b, r11b + shl r8b, 3 + or r8b, r9b + movzx ecx, byte ptr [rsp + 168] # 1-byte Folded Reload shl cl, 4 - or cl, r9b + or cl, r8b mov byte ptr [r15], r12b - movzx ebx, byte ptr [rsp + 168] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 5 shl dil, 6 or dil, bl @@ -29883,250 +30506,279 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 shl sil, 7 or sil, dil or sil, cl - mov byte ptr [r15 + 2], r8b + mov byte ptr [r15 + 2], r10b mov byte ptr [r15 + 3], sil add rdx, 128 add r15, 4 mov r13, r15 - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB5_103 -# %bb.104: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 184] # 8-byte Reload -.LBB5_105: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 -# %bb.106: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB5_148 -# %bb.107: + add qword ptr [rsp + 176], -1 # 8-byte Folded Spill + jne .LBB5_107 +# %bb.108: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14d, dword ptr [rsp + 192] # 4-byte Reload + mov rax, qword ptr [rsp + 184] # 8-byte Reload +.LBB5_109: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB5_188 +# %bb.110: + vmovd xmm0, r14d + or rax, 1 + cmp r12, rax + jne .LBB5_170 +# %bb.111: xor edi, edi - jmp .LBB5_150 -.LBB5_108: - mov r11b, byte ptr [rsi] - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + jmp .LBB5_172 +.LBB5_112: + mov r14b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_112 -# %bb.109: - movsxd rax, r9d + je .LBB5_131 +# %bb.113: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB5_145 +# %bb.114: + movsxd rsi, r9d + mov r11, r8 + .p2align 4, 0x90 +.LBB5_115: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r14b, byte ptr [rdx] + setne dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r15, r13 + movzx r9d, byte ptr [r13 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r13 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB5_115 +# %bb.116: + sub r12, r8 + jne .LBB5_146 + jmp .LBB5_188 +.LBB5_117: + mov r8d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB5_123 +# %bb.118: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB5_121 +# %bb.119: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_110: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx] - lea rdx, [rdx + 1] +.LBB5_120: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 mov r15, r13 - movzx r9d, byte ptr [r13 + rsi] + movzx r9d, byte ptr [r13 + rdi] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_110 -# %bb.111: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r13 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_120 +.LBB5_121: + sub r12, r14 + je .LBB5_188 +# %bb.122: add r13, 1 -.LBB5_112: - sar r14, 5 - cmp r10, 32 - jl .LBB5_120 -# %bb.113: - cmp r14, 32 - mov dword ptr [rsp + 28], r11d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 384], r14 # 8-byte Spill - jb .LBB5_116 -# %bb.114: - mov rax, r14 - shl rax, 5 - add rax, rdx - cmp r13, rax - jae .LBB5_168 -# %bb.115: - lea rax, [4*r14] - add rax, r13 - cmp rdx, rax - jae .LBB5_168 -.LBB5_116: - xor eax, eax - mov qword ptr [rsp + 376], rax # 8-byte Spill -.LBB5_117: - sub r14, qword ptr [rsp + 376] # 8-byte Folded Reload - mov qword ptr [rsp + 160], r14 # 8-byte Spill +.LBB5_123: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB5_127 +# %bb.124: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_118: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx + 31] - setne byte ptr [rsp + 272] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 30] +.LBB5_125: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r13 # 8-byte Spill + cmp r8d, dword ptr [rdx + 124] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 120] setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 29] + cmp r8d, dword ptr [rdx + 116] setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 28] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 27] + cmp r8d, dword ptr [rdx + 112] setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 26] + cmp r8d, dword ptr [rdx + 108] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 25] + cmp r8d, dword ptr [rdx + 104] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 23] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 22] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 21] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 20] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 19] + cmp r8d, dword ptr [rdx + 100] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 92] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 88] + setne byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 84] setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 18] + cmp r8d, dword ptr [rdx + 80] setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 17] + cmp r8d, dword ptr [rdx + 76] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 15] - setne r14b - cmp r11b, byte ptr [rdx + 14] + cmp r8d, dword ptr [rdx + 72] setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 13] + cmp r8d, dword ptr [rdx + 68] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 12] - setne r12b - cmp r11b, byte ptr [rdx + 11] - setne r15b - cmp r11b, byte ptr [rdx + 10] + cmp r8d, dword ptr [rdx + 60] + setne dil + cmp r8d, dword ptr [rdx + 56] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] setne r11b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 9] + cmp r8d, dword ptr [rdx + 44] setne r10b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 7] - setne dil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 6] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 5] + cmp r8d, dword ptr [rdx + 40] setne r9b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 4] - setne r8b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 3] + cmp r8d, dword ptr [rdx + 36] setne sil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 2] + cmp r8d, dword ptr [rdx + 28] + setne al + cmp r8d, dword ptr [rdx + 24] + setne bl + cmp r8d, dword ptr [rdx + 20] setne cl - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx] + cmp r8d, dword ptr [rdx + 16] + setne r12b + cmp r8d, dword ptr [rdx + 12] + setne r13b + cmp r8d, dword ptr [rdx + 8] + setne r15b + cmp r8d, dword ptr [rdx] setne byte ptr [rsp + 168] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 1] - setne al - mov rbx, r13 - mov r13d, dword ptr [rsp + 28] # 4-byte Reload - cmp r13b, byte ptr [rdx + 8] - mov r13, rbx - setne byte ptr [rsp + 152] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp bl, byte ptr [rdx + 16] - setne byte ptr [rsp + 144] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp bl, byte ptr [rdx + 24] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - add al, al - add al, byte ptr [rsp + 168] # 1-byte Folded Reload - shl cl, 2 - or cl, al - shl sil, 3 - or sil, cl - shl r8b, 4 - or r8b, sil - shl r9b, 5 - or r9b, r8b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 6 - shl dil, 7 - or dil, al - or dil, r9b - mov byte ptr [r13], dil - add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r10b - shl r15b, 3 - or r15b, r11b - mov r11d, dword ptr [rsp + 28] # 4-byte Reload + cmp r8d, dword ptr [rdx + 4] + setne r14b + cmp r8d, dword ptr [rdx + 32] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 64] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 + or r13b, r15b + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r12b, 4 - or r12b, r15b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or r12b, r13b + shl cl, 5 + or cl, r12b + shl bl, 6 + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r14], al + add sil, sil + add sil, byte ptr [rsp + 64] # 1-byte Folded Reload + shl r9b, 2 + or r9b, sil + shl r10b, 3 + or r10b, r9b + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 - or al, r12b - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + or al, r11b + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r14b, 7 - or r14b, cl - or r14b, al - mov byte ptr [r13 + 1], r14b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r14 + 1], dil + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 72] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r13 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 88] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -30136,219 +30788,486 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 mov ecx, eax movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r13 + 3], al - add rdx, 32 - add r13, 4 + mov byte ptr [r14 + 3], al + sub rdx, -128 + add r14, 4 + mov r13, r14 add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB5_118 -# %bb.119: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14, qword ptr [rsp + 384] # 8-byte Reload -.LBB5_120: - shl r14, 5 - cmp r14, r10 - jge .LBB5_164 -# %bb.121: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB5_153 -.LBB5_122: - xor esi, esi - jmp .LBB5_156 -.LBB5_123: - mov r14d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB5_127 -# %bb.124: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB5_125: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] - lea rdx, [rdx + 4] - setne bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - mov r9, r13 - movzx r8d, byte ptr [r13 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r13 + rsi], dil - add rax, 1 - cmp rax, 8 jne .LBB5_125 # %bb.126: - add r13, 1 + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload .LBB5_127: - sar r11, 5 - cmp r10, 32 - jl .LBB5_131 + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB5_188 # %bb.128: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - mov qword ptr [rsp + 168], r11 # 8-byte Spill + or rax, 1 + cmp r12, rax + jne .LBB5_175 +.LBB5_129: + xor edi, edi + jmp .LBB5_177 +.LBB5_130: + mov rdi, rdx + jmp .LBB5_134 +.LBB5_131: + mov rdi, rdx + jmp .LBB5_147 +.LBB5_132: + mov rdi, rdx + sub r12, r8 + je .LBB5_188 +.LBB5_133: + add r13, 1 +.LBB5_134: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB5_142 +# %bb.135: + cmp rcx, 32 + mov dword ptr [rsp + 28], r14d # 4-byte Spill + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 384], rcx # 8-byte Spill + jb .LBB5_138 +# %bb.136: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r13, rax + jae .LBB5_189 +# %bb.137: + lea rax, [4*rcx] + add rax, r13 + cmp rdi, rax + jae .LBB5_189 +.LBB5_138: + xor eax, eax + mov qword ptr [rsp + 376], rax # 8-byte Spill +.LBB5_139: + sub rcx, qword ptr [rsp + 376] # 8-byte Folded Reload + mov qword ptr [rsp + 160], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB5_129: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r13 # 8-byte Spill - cmp r14d, dword ptr [rdx + 124] - setne byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 120] +.LBB5_140: # =>This Inner Loop Header: Depth=1 + cmp r14b, byte ptr [rdi + 31] + setne byte ptr [rsp + 272] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 30] setne byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 116] + cmp r14b, byte ptr [rdi + 29] setne byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 112] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 108] + cmp r14b, byte ptr [rdi + 28] setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 104] + cmp r14b, byte ptr [rdi + 27] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 100] + cmp r14b, byte ptr [rdi + 26] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 92] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 88] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 84] + cmp r14b, byte ptr [rdi + 25] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 23] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 22] + setne byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 21] + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 20] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 19] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 18] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 17] setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 80] + cmp r14b, byte ptr [rdi + 15] + setne r11b + cmp r14b, byte ptr [rdi + 14] setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 76] + cmp r14b, byte ptr [rdi + 13] setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 72] - setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 68] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 60] + cmp r14b, byte ptr [rdi + 12] + setne r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 11] + setne r15b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 10] + setne r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 9] + setne r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 7] + setne sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 6] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 5] + setne r9b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 4] setne r8b - cmp r14d, dword ptr [rdx + 56] + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 3] + setne dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 2] + setne cl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi] + setne byte ptr [rsp + 168] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 1] + setne al + mov rbx, r13 + mov r13d, dword ptr [rsp + 28] # 4-byte Reload + cmp r13b, byte ptr [rdi + 8] + mov r13, rbx + setne byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp bl, byte ptr [rdi + 16] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 52] + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp bl, byte ptr [rdi + 24] + setne bl + add al, al + add al, byte ptr [rsp + 168] # 1-byte Folded Reload + shl cl, 2 + or cl, al + shl dl, 3 + or dl, cl + shl r8b, 4 + or r8b, dl + shl r9b, 5 + or r9b, r8b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 6 + shl sil, 7 + or sil, al + or sil, r9b + mov byte ptr [r13], sil + add r10b, r10b + add r10b, byte ptr [rsp + 72] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r15b, 3 + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, r12b + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 6 + shl r11b, 7 + or r11b, cl + or r11b, al + mov byte ptr [r13 + 1], r11b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 120] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, al + or al, bl + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 3], al + add rdi, 32 + add r13, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB5_140 +# %bb.141: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 384] # 8-byte Reload +.LBB5_142: + shl rcx, 5 + mov r8, r12 + sub r8, rcx + jle .LBB5_188 +# %bb.143: + or rcx, 1 + cmp r12, rcx + je .LBB5_157 +# %bb.180: + mov r10, r8 + and r10, -2 + xor r9d, r9d + .p2align 4, 0x90 +.LBB5_181: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r14b, byte ptr [rdi + r9] + setne bl + neg bl + mov rsi, r9 + shr rsi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r13 + rsi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r13 + rsi], dl + cmp r14b, byte ptr [rdi + rax + 1] + lea r9, [rax + 2] + setne bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r13 + rsi], al + cmp r10, r9 + jne .LBB5_181 + jmp .LBB5_184 +.LBB5_145: + mov rdi, rdx + sub r12, r8 + je .LBB5_188 +.LBB5_146: + add r13, 1 +.LBB5_147: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB5_155 +# %bb.148: + cmp rcx, 32 + mov dword ptr [rsp + 28], r14d # 4-byte Spill + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 384], rcx # 8-byte Spill + jb .LBB5_151 +# %bb.149: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r13, rax + jae .LBB5_192 +# %bb.150: + lea rax, [4*rcx] + add rax, r13 + cmp rdi, rax + jae .LBB5_192 +.LBB5_151: + xor eax, eax + mov qword ptr [rsp + 376], rax # 8-byte Spill +.LBB5_152: + sub rcx, qword ptr [rsp + 376] # 8-byte Folded Reload + mov qword ptr [rsp + 160], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB5_153: # =>This Inner Loop Header: Depth=1 + cmp r14b, byte ptr [rdi + 31] + setne byte ptr [rsp + 272] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 30] + setne byte ptr [rsp + 288] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 29] + setne byte ptr [rsp + 320] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 28] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 27] + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 26] + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 25] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 23] + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 22] + setne byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 21] + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 20] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 19] setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 48] + cmp r14b, byte ptr [rdi + 18] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 17] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 15] setne r11b - cmp r14d, dword ptr [rdx + 44] + cmp r14b, byte ptr [rdi + 14] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 13] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 12] + setne r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 11] + setne r15b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 10] + setne r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 9] setne r10b - cmp r14d, dword ptr [rdx + 40] + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 7] + setne sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 6] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 5] setne r9b - cmp r14d, dword ptr [rdx + 36] - setne dil - cmp r14d, dword ptr [rdx + 28] + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 4] + setne r8b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 3] + setne dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 2] + setne cl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi] + setne byte ptr [rsp + 168] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 1] setne al - cmp r14d, dword ptr [rdx + 24] + mov rbx, r13 + mov r13d, dword ptr [rsp + 28] # 4-byte Reload + cmp r13b, byte ptr [rdi + 8] + mov r13, rbx + setne byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp bl, byte ptr [rdi + 16] + setne byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp bl, byte ptr [rdi + 24] setne bl - cmp r14d, dword ptr [rdx + 20] - setne sil - cmp r14d, dword ptr [rdx + 16] - setne cl - cmp r14d, dword ptr [rdx + 12] - setne r12b - cmp r14d, dword ptr [rdx + 8] - setne r13b - cmp r14d, dword ptr [rdx] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 4] - setne r15b - cmp r14d, dword ptr [rdx + 32] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 64] - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 96] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r13b, 2 - or r13b, r15b - mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r12b, 3 - or r12b, r13b - shl cl, 4 - or cl, r12b - shl sil, 5 - or sil, cl - shl bl, 6 - shl al, 7 - or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 152] # 1-byte Folded Reload - shl r9b, 2 - or r9b, dil - shl r10b, 3 - or r10b, r9b - shl r11b, 4 - or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 168] # 1-byte Folded Reload + shl cl, 2 + or cl, al + shl dl, 3 + or dl, cl + shl r8b, 4 + or r8b, dl + shl r9b, 5 + or r9b, r8b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 6 + shl sil, 7 + or sil, al + or sil, r9b + mov byte ptr [r13], sil + add r10b, r10b + add r10b, byte ptr [rsp + 72] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r15b, 3 + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 - or al, r11b - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + or al, r12b + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl r11b, 7 + or r11b, cl + or r11b, al + mov byte ptr [r13 + 1], r11b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, byte ptr [rsp + 120] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 7 - or al, bl + or al, dl or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r13 + 2], al + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + or al, bl mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -30356,40 +31275,38 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload shl al, 7 - or al, bl + or al, dl or al, cl - mov byte ptr [r15 + 3], al - sub rdx, -128 - add r15, 4 - mov r13, r15 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_129 -# %bb.130: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 160] # 8-byte Reload -.LBB5_131: - shl r11, 5 - cmp r11, r10 - jge .LBB5_164 -# %bb.132: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB5_158 -.LBB5_133: - xor edi, edi - jmp .LBB5_160 -.LBB5_134: + mov byte ptr [r13 + 3], al + add rdi, 32 + add r13, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB5_153 +# %bb.154: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 384] # 8-byte Reload +.LBB5_155: + shl rcx, 5 + mov r8, r12 + sub r8, rcx + jle .LBB5_188 +# %bb.156: + or rcx, 1 + cmp r12, rcx + jne .LBB5_182 +.LBB5_157: + xor r9d, r9d + jmp .LBB5_185 +.LBB5_158: mov r9, r8 and r9, -2 xor edi, edi .p2align 4, 0x90 -.LBB5_135: # =>This Inner Loop Header: Depth=1 +.LBB5_159: # =>This Inner Loop Header: Depth=1 vucomisd xmm0, qword ptr [rdx] setp cl setne al @@ -30422,101 +31339,101 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 xor bl, r11b mov byte ptr [r13 + rsi], bl cmp r9, rdi - jne .LBB5_135 -.LBB5_136: + jne .LBB5_159 +.LBB5_160: test r8b, 1 - je .LBB5_164 -# %bb.137: + je .LBB5_188 +# %bb.161: vucomisd xmm0, qword ptr [rdx] - jmp .LBB5_152 -.LBB5_140: - mov r10, r8 - and r10, -2 + jmp .LBB5_174 +.LBB5_162: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB5_141: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] +.LBB5_163: # =>This Inner Loop Header: Depth=1 + cmp r8w, word ptr [rdx] setne al neg al mov rsi, rdi shr rsi, 3 - mov r11, r13 - movzx r9d, byte ptr [r13 + rsi] + mov r14, r13 + movzx r10d, byte ptr [r13 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b + xor bl, r10b mov byte ptr [r13 + rsi], bl add rdi, 2 - cmp r14w, word ptr [rdx + 2] + cmp r8w, word ptr [rdx + 2] lea rdx, [rdx + 4] - setne r9b - neg r9b - xor r9b, bl + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl mov byte ptr [r13 + rsi], al - cmp r10, rdi - jne .LBB5_141 -.LBB5_142: - test r8b, 1 - je .LBB5_164 -# %bb.143: - cmp r14w, word ptr [rdx] - jmp .LBB5_162 -.LBB5_144: - mov r10, r8 - and r10, -2 + cmp r11, rdi + jne .LBB5_163 +.LBB5_164: + test r9b, 1 + je .LBB5_188 +# %bb.165: + cmp r8w, word ptr [rdx] + jmp .LBB5_179 +.LBB5_166: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB5_145: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] +.LBB5_167: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] setne al neg al mov rsi, rdi shr rsi, 3 - mov r11, r13 - movzx r9d, byte ptr [r13 + rsi] + mov r14, r13 + movzx r10d, byte ptr [r13 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b + xor bl, r10b mov byte ptr [r13 + rsi], bl add rdi, 2 - cmp r14, qword ptr [rdx + 8] + cmp r8, qword ptr [rdx + 8] lea rdx, [rdx + 16] - setne r9b - neg r9b - xor r9b, bl + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl mov byte ptr [r13 + rsi], al - cmp r10, rdi - jne .LBB5_145 -.LBB5_146: - test r8b, 1 - je .LBB5_164 -# %bb.147: - cmp r14, qword ptr [rdx] - jmp .LBB5_162 -.LBB5_148: + cmp r11, rdi + jne .LBB5_167 +.LBB5_168: + test r9b, 1 + je .LBB5_188 +# %bb.169: + cmp r8, qword ptr [rdx] + jmp .LBB5_179 +.LBB5_170: mov r9, r8 and r9, -2 xor edi, edi .p2align 4, 0x90 -.LBB5_149: # =>This Inner Loop Header: Depth=1 +.LBB5_171: # =>This Inner Loop Header: Depth=1 vucomiss xmm0, dword ptr [rdx] setp cl setne al @@ -30549,13 +31466,13 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 xor bl, r11b mov byte ptr [r13 + rsi], bl cmp r9, rdi - jne .LBB5_149 -.LBB5_150: + jne .LBB5_171 +.LBB5_172: test r8b, 1 - je .LBB5_164 -# %bb.151: + je .LBB5_188 +# %bb.173: vucomiss xmm0, dword ptr [rdx] -.LBB5_152: +.LBB5_174: setp al setne dl or dl, al @@ -30571,116 +31488,117 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 and bl, dl xor bl, sil mov byte ptr [r13 + rax], bl - jmp .LBB5_164 -.LBB5_153: - mov r10, r8 - and r10, -2 - xor esi, esi + jmp .LBB5_188 +.LBB5_175: + mov r11, r9 + and r11, -2 + xor edi, edi .p2align 4, 0x90 -.LBB5_154: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx + rsi] +.LBB5_176: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] setne al neg al - mov rdi, rsi - shr rdi, 3 - mov ecx, esi + mov rsi, rdi + shr rsi, 3 + mov r14, r13 + movzx r10d, byte ptr [r13 + rsi] + mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - movzx r9d, byte ptr [r13 + rdi] - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b - mov byte ptr [r13 + rdi], bl - cmp r11b, byte ptr [rdx + rsi + 1] - lea rsi, [rsi + 2] - setne r9b - neg r9b - xor r9b, bl + xor bl, r10b + mov byte ptr [r13 + rsi], bl + add rdi, 2 + cmp r8d, dword ptr [rdx + 4] + lea rdx, [rdx + 8] + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl - mov byte ptr [r13 + rdi], al - cmp r10, rsi - jne .LBB5_154 -.LBB5_155: - add rdx, rsi -.LBB5_156: - test r8b, 1 - je .LBB5_164 -# %bb.157: - cmp r11b, byte ptr [rdx] + mov byte ptr [r13 + rsi], al + cmp r11, rdi + jne .LBB5_176 +.LBB5_177: + test r9b, 1 + je .LBB5_188 +# %bb.178: + cmp r8d, dword ptr [rdx] +.LBB5_179: setne al neg al - mov rdx, rsi + mov rdx, rdi shr rdx, 3 - mov dil, byte ptr [r13 + rdx] - and sil, 7 + mov sil, byte ptr [r13 + rdx] + and dil, 7 mov bl, 1 - mov ecx, esi + mov ecx, edi shl bl, cl - xor al, dil + xor al, sil and bl, al - xor bl, dil - jmp .LBB5_163 -.LBB5_158: + xor bl, sil + jmp .LBB5_187 +.LBB5_182: mov r10, r8 and r10, -2 - xor edi, edi + xor r9d, r9d .p2align 4, 0x90 -.LBB5_159: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] - setne al - neg al - mov rsi, rdi +.LBB5_183: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r14b, byte ptr [rdi + r9] + setne bl + neg bl + mov rsi, r9 shr rsi, 3 - mov r11, r13 - movzx r9d, byte ptr [r13 + rsi] - mov ecx, edi + mov ecx, eax and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r13 + rsi] xor bl, r9b - mov byte ptr [r13 + rsi], bl - add rdi, 2 - cmp r14d, dword ptr [rdx + 4] - lea rdx, [rdx + 8] - setne r9b - neg r9b - xor r9b, bl + and dl, bl + xor dl, r9b + mov byte ptr [r13 + rsi], dl + cmp r14b, byte ptr [rdi + rax + 1] + lea r9, [rax + 2] + setne bl + neg bl + xor bl, dl or cl, 1 mov al, 1 shl al, cl - and al, r9b - xor al, bl + and al, bl + xor al, dl mov byte ptr [r13 + rsi], al - cmp r10, rdi - jne .LBB5_159 -.LBB5_160: + cmp r10, r9 + jne .LBB5_183 +.LBB5_184: + add rdi, r9 +.LBB5_185: test r8b, 1 - je .LBB5_164 -# %bb.161: - cmp r14d, dword ptr [rdx] -.LBB5_162: + je .LBB5_188 +# %bb.186: + cmp r14b, byte ptr [rdi] setne al neg al - mov rdx, rdi + mov rdx, r9 shr rdx, 3 - mov sil, byte ptr [r13 + rdx] - and dil, 7 + mov dil, byte ptr [r13 + rdx] + and r9b, 7 mov bl, 1 - mov ecx, edi + mov ecx, r9d shl bl, cl - xor al, sil + xor al, dil and bl, al - xor bl, sil -.LBB5_163: + xor bl, dil +.LBB5_187: mov byte ptr [r13 + rdx], bl -.LBB5_164: +.LBB5_188: lea rsp, [rbp - 40] pop rbx pop r12 @@ -30690,1985 +31608,1987 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 pop rbp vzeroupper ret -.LBB5_165: - and r14, -32 - mov rax, r14 +.LBB5_189: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 392], rax # 8-byte Spill - mov qword ptr [rsp + 376], r14 # 8-byte Spill - lea rax, [4*r14] - add rax, r13 + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - vmovd xmm0, r11d + mov qword ptr [rsp + 376], rcx # 8-byte Spill + lea rax, [4*rcx] + add rax, r13 + mov qword ptr [rsp + 392], rax # 8-byte Spill + vmovd xmm0, r14d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill - xor esi, esi + xor eax, eax mov qword ptr [rsp + 272], r13 # 8-byte Spill .p2align 4, 0x90 -.LBB5_166: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 408], rsi # 8-byte Spill - shl rsi, 5 - mov rax, rsi +.LBB5_190: # =>This Inner Loop Header: Depth=1 + mov rbx, rax + mov qword ptr [rsp + 408], rax # 8-byte Spill + shl rbx, 5 + mov rax, rbx or rax, 32 - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 240], rax # 8-byte Spill + mov rax, rbx or rax, 64 - mov qword ptr [rsp + 216], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov rax, rbx or rax, 96 - mov qword ptr [rsp + 160], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov rax, rbx or rax, 128 - mov qword ptr [rsp + 32], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 128], rax # 8-byte Spill + mov rax, rbx or rax, 160 - mov qword ptr [rsp + 72], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 120], rax # 8-byte Spill + mov rax, rbx or rax, 192 - mov qword ptr [rsp + 176], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 112], rax # 8-byte Spill + mov rax, rbx or rax, 224 - mov qword ptr [rsp + 168], rax # 8-byte Spill - mov rax, rsi - or rax, 256 mov qword ptr [rsp + 288], rax # 8-byte Spill - mov rax, rsi + mov rax, rbx + or rax, 256 + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov rax, rbx or rax, 288 - mov qword ptr [rsp + 64], rax # 8-byte Spill - mov rax, rsi - mov qword ptr [rsp + 264], rsi # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill + mov rax, rbx or rax, 320 - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov rax, rbx or rax, 512 - mov rcx, rax - movzx eax, byte ptr [rdx + rax] + mov rdx, rax + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rdx + rsi] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rdx + rcx + 1] + movzx eax, byte ptr [rdi + rdx + 1] vmovd xmm4, eax - movzx eax, byte ptr [rdx + rsi + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rcx + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rsi + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rcx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rsi + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rcx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rsi + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rdx + rcx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rsi + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rdx + rcx + 6] - mov qword ptr [rsp + 240], rcx # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 232], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rdx + rsi + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rcx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rsi + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax - mov rax, rsi + mov rax, rbx or rax, 352 - mov qword ptr [rsp + 48], rax # 8-byte Spill - mov rax, rsi - or rax, 384 mov qword ptr [rsp + 320], rax # 8-byte Spill - mov rax, rsi + mov rax, rbx + or rax, 384 + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov rax, rbx or rax, 416 - mov qword ptr [rsp + 40], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov rax, rbx or rax, 448 - mov qword ptr [rsp + 88], rax # 8-byte Spill - mov rax, rsi + mov qword ptr [rsp + 80], rax # 8-byte Spill + mov rax, rbx or rax, 480 - mov qword ptr [rsp + 144], rax # 8-byte Spill - mov rax, rsi - or rax, 544 - mov r13, rax - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov r12, rsi - or r12, 576 + mov qword ptr [rsp + 88], rax # 8-byte Spill + mov r12, rbx + or r12, 544 mov qword ptr [rsp + 224], r12 # 8-byte Spill - mov rax, rsi - or rax, 608 - mov r14, rax - mov qword ptr [rsp + 248], rax # 8-byte Spill - mov r15, rsi - or r15, 640 - mov qword ptr [rsp + 256], r15 # 8-byte Spill - mov r10, rsi - or r10, 672 - mov qword ptr [rsp + 104], r10 # 8-byte Spill - mov rax, rsi - or rax, 704 - mov qword ptr [rsp + 128], rax # 8-byte Spill - mov r8, rsi - or r8, 736 - mov qword ptr [rsp + 112], r8 # 8-byte Spill - mov rax, rsi - or rax, 768 - mov qword ptr [rsp + 200], rax # 8-byte Spill - mov rax, rsi + mov r15, rbx + or r15, 576 + mov qword ptr [rsp + 64], r15 # 8-byte Spill + mov r11, rbx + or r11, 608 + mov qword ptr [rsp + 216], r11 # 8-byte Spill + mov r10, rbx + or r10, 640 + mov qword ptr [rsp + 200], r10 # 8-byte Spill + mov rax, rbx + or rax, 672 + mov qword ptr [rsp + 96], rax # 8-byte Spill + mov r14, rbx + or r14, 704 + mov qword ptr [rsp + 192], r14 # 8-byte Spill + mov rax, rbx + or rax, 736 + mov qword ptr [rsp + 104], rax # 8-byte Spill + mov r13, rbx + or r13, 768 + mov qword ptr [rsp + 40], r13 # 8-byte Spill + mov rax, rbx or rax, 800 - mov qword ptr [rsp + 152], rax # 8-byte Spill - mov r9, rsi + mov qword ptr [rsp + 72], rax # 8-byte Spill + mov r9, rbx or r9, 832 mov qword ptr [rsp + 208], r9 # 8-byte Spill - mov rdi, rsi - or rdi, 864 - mov qword ptr [rsp + 96], rdi # 8-byte Spill - mov rcx, rsi - or rcx, 896 - mov qword ptr [rsp + 136], rcx # 8-byte Spill - mov r11, rsi - or r11, 928 - mov qword ptr [rsp + 192], r11 # 8-byte Spill - mov rax, rsi + mov rcx, rbx + or rcx, 864 + mov qword ptr [rsp + 184], rcx # 8-byte Spill + mov r8, rbx + or r8, 896 + mov qword ptr [rsp + 176], r8 # 8-byte Spill + mov rsi, rbx + or rsi, 928 + mov qword ptr [rsp + 256], rsi # 8-byte Spill + mov rax, rbx + mov rdx, rbx + mov qword ptr [rsp + 248], rbx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 120], rax # 8-byte Spill - or rsi, 992 - mov qword ptr [rsp + 80], rsi # 8-byte Spill - vpinsrb xmm9, xmm0, byte ptr [rdx + r13], 1 - vpinsrb xmm0, xmm9, byte ptr [rdx + r12], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 5 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8], 7 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 8 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi], 15 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12], 1 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 2 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 3 - mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 4 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 5 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 6 + mov qword ptr [rsp + 160], rax # 8-byte Spill + or rdx, 992 + mov qword ptr [rsp + 264], rdx # 8-byte Spill + vpinsrb xmm9, xmm0, byte ptr [rdi + r12], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + r15], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 6 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 15 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 1 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 2 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 3 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 4 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 5 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 6 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 7 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 10 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 11 mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 7 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 9 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 10 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 13 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 14 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13], 15 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 2 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 3 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 4 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 5 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 6 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 7 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 8 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 10 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 11 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 12 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 14 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r12 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 1], 2 - mov rcx, r14 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 10 - mov r11, rax - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 1], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 13 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 15 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 2 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 4 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 5 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 7 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 vinserti128 ymm13, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 1], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm9, edi + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax vinserti128 ymm0, ymm0, xmm4, 1 - vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm10, edi - mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm10, eax vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 2], 1 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 2], 2 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 2], 3 - mov r9, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 2], 4 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 2], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 2 + mov r10, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 2], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 6 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 7 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 8 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 12 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 13 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rcx, r14 + vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 2], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 3 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 4 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 2], 5 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 7 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 8 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 9 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 2], 10 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 2], 11 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 2], 12 - mov r10, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 2], 13 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 15 - vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 1 - mov rax, rcx - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 3 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 5 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 6 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 8 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 2], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 8 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 9 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 10 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 13 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 14 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 15 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm11, byte ptr [rdi + r13 + 3], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 5 + mov r10, rbx + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 9 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 10 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 11 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 14 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rcx + 3], 1 mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 13 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 14 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rdx + rsi + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 3], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 3], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 2 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 3 mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 6 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 3], 7 - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 8 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 3], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 14 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 3], 15 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm8, byte ptr [rdx + rcx + 3], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 3 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 5 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 6 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 8 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 9 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 3], 5 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 3], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rdi + 3], 14 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 9] - vmovd xmm8, edi - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 3], 15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 9] - vmovd xmm11, edi + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 1 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 2 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 4], 3 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 4], 4 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 4], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 4], 9 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 10 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 4], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 4], 12 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 13 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 4], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 4], 15 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm15, byte ptr [rdx + r10 + 4], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 3 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 6 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 7 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 9 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 10 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 5 + mov r15, r13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 13 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 14 + mov rcx, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 15 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm15, byte ptr [rdi + r14 + 4], 1 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 13 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 4], 15 - vpinsrb xmm4, xmm14, byte ptr [rdx + r12 + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 3 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 5], 4 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 5 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 6 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 7 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 8 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 5], 11 - mov r15, r11 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 5], 13 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 5], 14 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 5], 15 - vpinsrb xmm5, xmm6, byte ptr [rdx + r10 + 5], 1 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 2 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + mov r9, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 3 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 4 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 8 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 9 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 10 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 11 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 12 mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 4 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 5], 5 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 5], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 5], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 5], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 13 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 14 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + rsi + 5], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 2 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 4 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 6 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 7 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 8 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 9 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 10 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 12 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r14 + 5], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 5 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 7 + mov rsi, rax + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 5], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 13 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 + mov r8, rax vinserti128 ymm14, ymm3, xmm0, 1 - vpinsrb xmm0, xmm5, byte ptr [rdx + r13 + 5], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm3, edi - vinserti128 ymm15, ymm0, xmm4, 1 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm4, edi - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rdx + r11 + 6], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 2 + vpinsrb xmm0, xmm5, byte ptr [rdi + rbx + 5], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm3, eax + vinserti128 ymm15, ymm0, xmm4, 1 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 6], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 5 + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rcx + 6], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 2 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 3 + mov r11, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 5 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 9 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 10 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 6], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 12 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 6], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 3 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 6 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 6], 7 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 8 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 11 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 12 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 6], 13 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 6], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 15 - vpinsrb xmm5, xmm7, byte ptr [rdx + r10 + 6], 1 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 2 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 6], 3 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 6], 6 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 7 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 5 + mov rax, r10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 7 mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 10 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 11 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 12 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 13 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 14 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 7], 1 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 2 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 3 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 4 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 5 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 7 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 7], 8 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 8 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 10 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 11 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 14 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 3 + mov r8, r14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 4 mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 7], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 7], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 7], 14 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 7], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 7], 1 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 7], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 7], 3 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 6 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 7 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 8 mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 6 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 7], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 9 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 11 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 14 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 15 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 2 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 4 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rax + 7], 14 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 11] - vmovd xmm1, edi - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 7], 15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 7], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 11] - vmovd xmm2, edi + vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm2, eax + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r14 + 8], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 6 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 8 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 10 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rdx + rax + 8], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 2 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 3 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 4 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 5 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 6 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 8], 8 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 9 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 8], 10 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 11 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 12 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 8], 15 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rdx + r15 + 8], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 8], 3 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 8], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 8], 5 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 8], 6 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 8], 7 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 10 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 12 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 13 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 14 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 15 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rdx + r11 + 9], 1 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 9], 3 - mov rbx, rcx - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 4 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 9], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 7 - mov r8, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 8 - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 9 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 9], 10 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 11 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 12 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 9], 13 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 15 - vpinsrb xmm7, xmm11, byte ptr [rdx + r15 + 9], 1 - mov r12, r15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 13 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 3 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rdi + 9], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + r9 + 9], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 9], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r11 + 8], 1 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 5 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 7 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 9 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 10 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 11 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 8], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 13 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r14 + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 2 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 3 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 7 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 9 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 10 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 11 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 12 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 13 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rdx + 9], 1 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 2 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 6 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 8 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r15 + 9], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 10 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 9], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 10 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 9], 12 + mov r15, r10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 - vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm0, edi + vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm0, eax vinserti128 ymm5, ymm5, xmm6, 1 - vmovdqa ymmword ptr [rsp + 1120], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm5, edi - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 10], 1 + vmovdqa ymmword ptr [rsp + 1088], ymm5 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 10], 3 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 10], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 10], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 8 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 10], 9 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 10 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 11 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 10], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 14 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 15 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 10], 1 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 10], 3 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 10], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 5 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 6 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 10], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 3 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 4 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 5 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 10 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 11 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 13 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 15 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 1 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 5 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 6 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 7 mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 10 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 13 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 9 mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 11], 3 - mov rax, rbx - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 11], 4 - mov r11, r13 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 11], 6 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 7 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 11], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 10 + mov rcx, r11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 12 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 13 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 14 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 15 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 1 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 2 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 6 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 7 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 9 mov r10, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 11], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 12 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 14 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 15 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 11], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 11], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 5 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 11], 7 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 8 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 9 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 12 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 14 + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 2 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 4 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 11], 11 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 - vmovdqa ymmword ptr [rsp + 1088], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 14 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 13] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 15 + vmovdqa ymmword ptr [rsp + 1056], ymm3 # 32-byte Spill + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 - vmovdqa ymmword ptr [rsp + 1056], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 13] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 1 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 12], 4 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 12], 5 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 12], 6 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 12], 7 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 8 - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 12], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 12], 10 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 12], 11 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 12], 12 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 12], 13 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 12], 14 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 12], 15 - vpinsrb xmm2, xmm5, byte ptr [rdx + rbx + 12], 1 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 3 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 4 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 6 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 7 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 9 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 10 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 12 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 13 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 14 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 13], 2 - mov r13, rsi - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 13], 3 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 13], 9 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 10 + vmovdqa ymmword ptr [rsp + 1024], ymm1 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm1, eax + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 2 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 11 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 12 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 13], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 15 - mov r14, r12 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 3 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 6 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 7 - mov r10, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 13], 8 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 13], 9 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 13 - mov r15, rbx - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 13], 14 - vinserti128 ymm0, ymm2, xmm0, 1 - vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rdi + 13], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 14] - vmovd xmm1, edi - vinserti128 ymm0, ymm0, xmm3, 1 - vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 14] - vmovd xmm0, edi - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 14], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 3 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 4 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 14], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 14], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 14], 7 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 14], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 14], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 14], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 11 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 14], 12 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 14], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 14], 15 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 14], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 2 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 14], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 5 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 6 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 14], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 14], 9 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 10 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 14], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 14], 14 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 15] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 15], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 15], 2 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 15], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 4 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 5 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 15], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 15], 8 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 15], 9 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 15], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 15], 13 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 15 - mov r10, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + r10 + 15] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 15], 1 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 15], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 15], 3 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 6 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 8 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 11 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 6 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 9 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 15], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 12], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 15 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + r11 + 12], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 5 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 7 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 9 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 10 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 14 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 4 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 5 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 8 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 9 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 10 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 11 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 13 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 1 mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 15], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 13 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 14 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 15], 15 - vinserti128 ymm0, ymm0, xmm1, 1 - vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - vinserti128 ymm0, ymm3, xmm2, 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 6 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 7 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 14 + vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - mov r9, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + r9 + 16] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 16], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 16], 2 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 16], 3 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 4 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 16], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 7 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 16], 9 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 16], 10 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 11 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 12 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 14 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 15 - movzx edi, byte ptr [rdx + r10 + 16] - vmovd xmm1, edi - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 3 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 4 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 5 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 16], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 7 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 13], 15 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r13 + 14] + vmovd xmm1, eax + vinserti128 ymm0, ymm0, xmm3, 1 + vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill + mov r15, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r15 + 14] + vmovd xmm0, eax + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 1 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 16], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 16], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 9 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 11 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 12 + mov r11, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 5 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 12 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 16], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 12 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 14 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 16], 15 - movzx edi, byte ptr [rdx + r9 + 17] - vmovd xmm2, edi + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 15 + movzx eax, byte ptr [rdi + r13 + 15] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 3 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 15], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 10 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 17], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 15], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 15 + movzx eax, byte ptr [rdi + r15 + 15] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 8 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 9 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 13 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 14 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 15 + vinserti128 ymm0, ymm0, xmm1, 1 + vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill + vinserti128 ymm0, ymm3, xmm2, 1 + vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm0, eax + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 4 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 6 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 10 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 12 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 4 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 17], 5 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 17], 6 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 7 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 17], 8 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 17], 10 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 13 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 12 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 17], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 10 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 15 + mov r9, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r9 + 17] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 1 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 7 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 17], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 14 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 17], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 17] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 1 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 2 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 4 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 6 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 11 + mov r14, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 17], 15 - movzx edi, byte ptr [rdx + r10 + 17] - vmovd xmm3, edi - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 17], 1 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 2 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 17], 3 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 17], 6 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 7 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 8 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 9 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 12 - mov r11, rbx - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 17], 13 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rbx + 17], 15 - vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 18] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 2 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 3 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 18], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 6 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 17], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill + movzx eax, byte ptr [rdi + r9 + 18] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 2 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 18], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm1, eax + mov r12, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 5 mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 18], 8 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 9 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 10 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 11 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 18], 13 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 15 - movzx edi, byte ptr [rdx + r10 + 18] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 18], 1 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 18], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 3 - mov r12, r8 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 4 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 18], 5 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 6 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 18], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 7 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 8 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 9 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 10 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 11 + mov rcx, r14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 12 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 13 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 14 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 1 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 10 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 18], 13 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 18], 15 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + r15 + 19] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 1 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 19], 2 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 3 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 4 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 5 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 6 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 7 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 8 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 19], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 10 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 11 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 12 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 14 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 15 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 19] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 19], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 19], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 19], 6 - mov r14, r8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 19], 7 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 9 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 10 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 11 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 19], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 5 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 6 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 7 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 13 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 19], 14 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill + vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 - vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - movzx edi, byte ptr [rdx + r15 + 20] - vmovd xmm0, edi - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 20], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 20], 2 - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 20], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 4 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 5 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 6 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 20], 7 + vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill + mov r9, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r9 + 20] + vmovd xmm0, eax + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 20], 3 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 20], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 9 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 10 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 11 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 12 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 13 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 14 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 15 + mov r13, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r13 + 20] + vmovd xmm1, eax + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 12 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 4 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 14 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 20], 15 - movzx edi, byte ptr [rdx + rcx + 20] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 1 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 20], 3 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 4 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 20], 6 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 20], 9 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 20], 14 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 20], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 21], 1 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 21], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 21], 3 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 21], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 5 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 21], 7 - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 21], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 21], 9 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 21], 10 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 21], 11 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 21], 12 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 21], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 21] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 3 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 21], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 21], 6 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 6 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 10 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 11 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 21], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 15 + movzx eax, byte ptr [rdi + r9 + 21] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 1 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 21], 3 + mov r12, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 7 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 13 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 15 + movzx eax, byte ptr [rdi + r13 + 21] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 4 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov r9, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 13 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rdx + r12 + 21], 15 + vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r11 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 22] - vmovd xmm0, edi + vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 4 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 5 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 8 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 10 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 22], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 22], 2 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 22], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 4 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 22], 8 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 9 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 22], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 22], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 22], 12 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 22], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 14 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 22], 15 - mov r11, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 22] - vmovd xmm1, edi - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 22], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 3 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 6 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 22], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 9 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 22], 12 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 22], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 14 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 15 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rbx + 23] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 12 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 4 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 5 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 23], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 8 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 10 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 11 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 23], 13 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 23], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 23], 15 - movzx edi, byte ptr [rdx + r11 + 23] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 23], 1 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 3 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 23], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 23], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 9 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 11 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 23], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 23], 13 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 15 - vinserti128 ymm10, ymm1, xmm0, 1 - vinserti128 ymm11, ymm3, xmm2, 1 - movzx edi, byte ptr [rdx + rbx + 24] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 24], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 24], 2 - mov r10, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 24], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 4 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 6 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 24], 7 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 24], 9 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 24], 10 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 24], 11 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 12 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 24], 14 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 15 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 24] - vmovd xmm1, edi - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 24], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 2 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 11 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm2, eax + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 2 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 6 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 10 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 11 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 12 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 13 mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 24], 4 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 5 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 6 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 7 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 8 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 9 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 10 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 24], 12 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 13 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 24], 14 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rsi + 25] - vmovd xmm2, edi - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 25], 1 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 25], 3 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 14 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm3, eax + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 3 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 25], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 25], 8 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 25], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 25], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 25], 11 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 25], 12 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 25], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 25], 14 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 25], 15 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 25] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 25], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 25], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 5 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 9 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 25], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 25], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 25], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rdi + 25], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 15 + vinserti128 ymm10, ymm1, xmm0, 1 + vinserti128 ymm11, ymm3, xmm2, 1 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 24], 1 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 3 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 24], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 8 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 3 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 7 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 11 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 13 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm2, eax + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 2 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 4 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 5 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 6 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 12 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 14 + vinserti128 ymm9, ymm1, xmm0, 1 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rdx + 25], 15 vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 26] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 26], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 2 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 3 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 26], 4 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 6 + vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 26] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 1 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 7 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 11 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 26], 15 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 26] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 1 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 3 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 4 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 5 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 13 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 27] + vmovd xmm2, eax + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 3 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 26], 9 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 26], 10 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 26], 12 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 26], 13 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 26], 15 - movzx edi, byte ptr [rdx + rcx + 26] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 26], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 2 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 26], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 26], 4 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 26], 5 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 26], 6 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 26], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 26], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 26], 12 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 26], 13 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 14 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 27] - vmovd xmm2, edi - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 27], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 2 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 27], 4 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 8 - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 27], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 9 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 10 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 15 + movzx eax, byte ptr [rdi + r10 + 27] + vmovd xmm3, eax + mov r10, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 27], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 27], 15 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rsi + 27] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 1 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 27], 3 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 27], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 27], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 9 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 10 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 11 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 27], 13 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 27], 14 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill + vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 - vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 28], 1 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 28], 2 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 28], 3 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 28], 4 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 28], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 28], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 28], 7 + vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill + movzx eax, byte ptr [rdi + rdx + 28] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 2 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 3 mov r8, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 28], 9 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 28], 10 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 28], 11 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 28], 12 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 28], 14 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 28], 15 - movzx edi, byte ptr [rdx + rsi + 28] - vmovd xmm1, edi - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 1 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 3 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 5 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 6 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 4 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 28], 11 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 15 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 28] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 5 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 28], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 28], 14 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 28], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 29] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 2 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 29], 4 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 29], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 6 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 10 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 29], 13 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 14 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 15 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 29] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 1 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 8 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 10 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 11 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 29] + vmovd xmm2, eax + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 29], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 9 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 29], 10 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 12 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 14 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 15 + movzx eax, byte ptr [rdi + rdx + 29] + vmovd xmm3, eax + mov r13, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 8 + mov r11, r14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 29], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 12 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 4 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 29], 6 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 7 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 9 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 29], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 13 - vpinsrb xmm4, xmm3, byte ptr [rdx + r15 + 29], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 13 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm3, byte ptr [rdi + r14 + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm4, byte ptr [rdx + r11 + 29], 15 + vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rax + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - movzx edi, byte ptr [rdx + rax + 30] - vmovd xmm0, edi - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 30], 1 - movzx edi, byte ptr [rdx + rax + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 31], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 3 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 4 - mov rax, r10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 31], 5 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 31], 7 - mov r9, qword ptr [rsp + 272] # 8-byte Reload + vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 30] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 1 + movzx eax, byte ptr [rdi + rbx + 31] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 31], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 11 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 31], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rdx + r8 + 31], 15 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - movzx eax, byte ptr [rdx + rdi + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rbx, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 31], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 31], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + r12 + 31], 15 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - mov r10, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 30], 1 - movzx eax, byte ptr [rdx + rdi + 31] + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rdx + r10 + 31], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 31], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 3 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + r12 + 31], 5 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 31], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 1 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 10 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 11 - mov rax, rbx - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 31], 12 - mov rax, rcx - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 31], 14 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill vmovdqa ymm2, ymmword ptr [rsp + 512] # 32-byte Reload vpcmpeqb ymm0, ymm13, ymm2 - vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1216] # 32-byte Folded Reload + vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1184] # 32-byte Folded Reload vmovdqa ymm5, ymmword ptr [rip + .LCPI5_0] # ymm5 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] vpandn ymm7, ymm7, ymm5 vpaddb ymm0, ymm7, ymm0 @@ -32680,12 +33600,12 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 vpandn ymm12, ymm12, ymm3 vpor ymm7, ymm12, ymm7 vpcmpeqb ymm12, ymm14, ymm2 - vmovdqa ymm8, ymmword ptr [rip + .LCPI5_3] # ymm8 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - vpandn ymm12, ymm12, ymm8 + vmovdqa ymm4, ymmword ptr [rip + .LCPI5_3] # ymm4 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + vpandn ymm12, ymm12, ymm4 vpor ymm7, ymm12, ymm7 vpcmpeqd ymm1, ymm1, ymm1 vpsubb ymm0, ymm0, ymm1 - vpcmpeqd ymm4, ymm4, ymm4 + vpcmpeqd ymm8, ymm8, ymm8 vpor ymm0, ymm0, ymm7 vpcmpeqb ymm7, ymm15, ymm2 vmovdqa ymm1, ymmword ptr [rip + .LCPI5_4] # ymm1 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] @@ -32694,73 +33614,75 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 vmovdqa ymm13, ymmword ptr [rip + .LCPI5_5] # ymm13 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] vpandn ymm12, ymm12, ymm13 vpor ymm7, ymm12, ymm7 - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1184] # 32-byte Folded Reload - vmovdqa ymm9, ymmword ptr [rip + .LCPI5_6] # ymm9 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - vpandn ymm12, ymm12, ymm9 + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1152] # 32-byte Folded Reload + vmovdqa ymm14, ymmword ptr [rip + .LCPI5_6] # ymm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + vpandn ymm12, ymm12, ymm14 vpor ymm7, ymm12, ymm7 vpor ymm0, ymm0, ymm7 - vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1152] # 32-byte Folded Reload - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1120] # 32-byte Folded Reload + vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1120] # 32-byte Folded Reload + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1088] # 32-byte Folded Reload vpandn ymm12, ymm12, ymm5 vpaddb ymm7, ymm12, ymm7 - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1088] # 32-byte Folded Reload + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1056] # 32-byte Folded Reload vpandn ymm12, ymm12, ymm6 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 1056] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 1024] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm3 vpor ymm12, ymm12, ymm15 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 992] # 32-byte Folded Reload - vpandn ymm15, ymm15, ymm8 + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 960] # 32-byte Folded Reload + vpandn ymm15, ymm15, ymm4 vpor ymm12, ymm12, ymm15 - vpsubb ymm7, ymm7, ymm4 + vpsubb ymm7, ymm7, ymm8 vpor ymm7, ymm12, ymm7 - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1024] # 32-byte Folded Reload + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 992] # 32-byte Folded Reload vpandn ymm12, ymm12, ymm1 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 928] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 896] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm13 vpor ymm12, ymm12, ymm15 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 960] # 32-byte Folded Reload - vpandn ymm15, ymm15, ymm9 + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 928] # 32-byte Folded Reload + vpandn ymm15, ymm15, ymm14 + vmovdqa ymm8, ymm14 vpor ymm12, ymm12, ymm15 vpor ymm12, ymm12, ymm7 - vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 896] # 32-byte Folded Reload - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 864] # 32-byte Folded Reload + vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 864] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 832] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm5 vpaddb ymm7, ymm15, ymm7 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 800] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 768] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm6 - vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 832] # 32-byte Folded Reload + vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 800] # 32-byte Folded Reload vpandn ymm14, ymm14, ymm3 vpor ymm14, ymm15, ymm14 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 736] # 32-byte Folded Reload - vpandn ymm15, ymm15, ymm8 + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 704] # 32-byte Folded Reload + vpandn ymm15, ymm15, ymm4 vpor ymm14, ymm14, ymm15 - vpsubb ymm7, ymm7, ymm4 + vpcmpeqd ymm15, ymm15, ymm15 + vpsubb ymm7, ymm7, ymm15 vpor ymm7, ymm14, ymm7 - vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 768] # 32-byte Folded Reload + vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 736] # 32-byte Folded Reload vpandn ymm14, ymm14, ymm1 vpcmpeqb ymm10, ymm10, ymm2 vpandn ymm10, ymm10, ymm13 vpor ymm10, ymm14, ymm10 vpcmpeqb ymm11, ymm11, ymm2 - vmovdqa ymm14, ymm9 - vpandn ymm11, ymm11, ymm9 + vpandn ymm11, ymm11, ymm8 + vmovdqa ymm14, ymm8 vpor ymm10, ymm10, ymm11 vpor ymm7, ymm10, ymm7 - vpcmpeqb ymm9, ymm2, ymmword ptr [rsp + 544] # 32-byte Folded Reload - vpcmpeqb ymm8, ymm2, ymmword ptr [rsp + 576] # 32-byte Folded Reload + vpcmpeqb ymm9, ymm9, ymm2 + vpcmpeqb ymm8, ymm2, ymmword ptr [rsp + 544] # 32-byte Folded Reload vpandn ymm8, ymm8, ymm5 vpaddb ymm8, ymm8, ymm9 - vpcmpeqb ymm5, ymm2, ymmword ptr [rsp + 608] # 32-byte Folded Reload + vpcmpeqb ymm5, ymm2, ymmword ptr [rsp + 576] # 32-byte Folded Reload vpandn ymm5, ymm5, ymm6 - vpcmpeqb ymm6, ymm2, ymmword ptr [rsp + 640] # 32-byte Folded Reload + vpcmpeqb ymm6, ymm2, ymmword ptr [rsp + 608] # 32-byte Folded Reload vpandn ymm6, ymm6, ymm3 vpor ymm5, ymm5, ymm6 - vpcmpeqb ymm3, ymm2, ymmword ptr [rsp + 672] # 32-byte Folded Reload - vpandn ymm3, ymm3, ymmword ptr [rip + .LCPI5_3] + vpcmpeqb ymm3, ymm2, ymmword ptr [rsp + 640] # 32-byte Folded Reload + vpandn ymm3, ymm3, ymm4 vpor ymm3, ymm5, ymm3 - vpsubb ymm5, ymm8, ymm4 + vpsubb ymm5, ymm8, ymm15 vpor ymm3, ymm5, ymm3 - vpcmpeqb ymm4, ymm2, ymmword ptr [rsp + 704] # 32-byte Folded Reload + vpcmpeqb ymm4, ymm2, ymmword ptr [rsp + 672] # 32-byte Folded Reload vpandn ymm4, ymm4, ymm1 vpcmpeqb ymm1, ymm2, ymmword ptr [rsp + 320] # 32-byte Folded Reload vpandn ymm1, ymm1, ymm13 @@ -32782,2002 +33704,2004 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [r9 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r9 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r9 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r9 + 4*rcx], ymm1 + vmovdqu ymmword ptr [rbx + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rbx + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rbx + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rbx + 4*rcx], ymm1 add rcx, 32 - mov rsi, rcx + mov rax, rcx cmp rcx, qword ptr [rsp + 376] # 8-byte Folded Reload - jne .LBB5_166 -# %bb.167: - mov r14, qword ptr [rsp + 384] # 8-byte Reload - cmp r14, qword ptr [rsp + 376] # 8-byte Folded Reload - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - mov r13, qword ptr [rsp + 400] # 8-byte Reload - mov rdx, qword ptr [rsp + 392] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - jne .LBB5_43 - jmp .LBB5_46 -.LBB5_168: - and r14, -32 - mov rax, r14 + jne .LBB5_190 +# %bb.191: + mov rcx, qword ptr [rsp + 384] # 8-byte Reload + cmp rcx, qword ptr [rsp + 376] # 8-byte Folded Reload + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + mov r13, qword ptr [rsp + 392] # 8-byte Reload + mov rdi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB5_139 + jmp .LBB5_142 +.LBB5_192: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 392], rax # 8-byte Spill - mov qword ptr [rsp + 376], r14 # 8-byte Spill - lea rax, [4*r14] - add rax, r13 + add rax, rdi mov qword ptr [rsp + 400], rax # 8-byte Spill - vmovd xmm0, r11d + mov qword ptr [rsp + 376], rcx # 8-byte Spill + lea rax, [4*rcx] + add rax, r13 + mov qword ptr [rsp + 392], rax # 8-byte Spill + vmovd xmm0, r14d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill - xor ebx, ebx + xor eax, eax mov qword ptr [rsp + 272], r13 # 8-byte Spill .p2align 4, 0x90 -.LBB5_169: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 408], rbx # 8-byte Spill +.LBB5_193: # =>This Inner Loop Header: Depth=1 + mov rbx, rax + mov qword ptr [rsp + 408], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 96 mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 112], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 264], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill mov rax, rbx or rax, 512 - mov rcx, rax - movzx eax, byte ptr [rdx + rax] + mov rdx, rax + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rdx + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rdx + rcx + 1] + movzx eax, byte ptr [rdi + rdx + 1] vmovd xmm4, eax - movzx eax, byte ptr [rdx + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rcx + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rcx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rcx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - mov qword ptr [rsp + 256], rbx # 8-byte Spill - movzx eax, byte ptr [rdx + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rdx + rcx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rdx + rcx + 6] - mov qword ptr [rsp + 216], rcx # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 232], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rdx + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rcx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 288], rax # 8-byte Spill - mov r14, rbx - or r14, 544 - mov qword ptr [rsp + 128], r14 # 8-byte Spill - mov rcx, rbx - or rcx, 576 - mov qword ptr [rsp + 184], rcx # 8-byte Spill - mov rax, rbx - or rax, 608 - mov r13, rax - mov qword ptr [rsp + 240], rax # 8-byte Spill - mov rax, rbx - or rax, 640 - mov qword ptr [rsp + 160], rax # 8-byte Spill - mov r10, rbx - or r10, 672 - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov r9, rbx - or r9, 704 - mov qword ptr [rsp + 232], r9 # 8-byte Spill - mov r11, rbx - or r11, 736 - mov qword ptr [rsp + 104], r11 # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov r12, rbx - or r12, 768 - mov qword ptr [rsp + 112], r12 # 8-byte Spill - mov r8, rbx - or r8, 800 - mov qword ptr [rsp + 48], r8 # 8-byte Spill + or r12, 544 + mov qword ptr [rsp + 224], r12 # 8-byte Spill mov r15, rbx - or r15, 832 - mov qword ptr [rsp + 120], r15 # 8-byte Spill - mov rax, rbx - or rax, 864 - mov qword ptr [rsp + 88], rax # 8-byte Spill + or r15, 576 + mov qword ptr [rsp + 64], r15 # 8-byte Spill + mov r11, rbx + or r11, 608 + mov qword ptr [rsp + 216], r11 # 8-byte Spill + mov r10, rbx + or r10, 640 + mov qword ptr [rsp + 200], r10 # 8-byte Spill mov rax, rbx - or rax, 896 - mov rdi, rax + or rax, 672 mov qword ptr [rsp + 96], rax # 8-byte Spill + mov r14, rbx + or r14, 704 + mov qword ptr [rsp + 192], r14 # 8-byte Spill mov rax, rbx - or rax, 928 - mov rsi, rax - mov qword ptr [rsp + 168], rax # 8-byte Spill + or rax, 736 + mov qword ptr [rsp + 104], rax # 8-byte Spill + mov r13, rbx + or r13, 768 + mov qword ptr [rsp + 40], r13 # 8-byte Spill + mov rax, rbx + or rax, 800 + mov qword ptr [rsp + 72], rax # 8-byte Spill + mov r9, rbx + or r9, 832 + mov qword ptr [rsp + 208], r9 # 8-byte Spill + mov rcx, rbx + or rcx, 864 + mov qword ptr [rsp + 184], rcx # 8-byte Spill + mov r8, rbx + or r8, 896 + mov qword ptr [rsp + 176], r8 # 8-byte Spill + mov rsi, rbx + or rsi, 928 + mov qword ptr [rsp + 256], rsi # 8-byte Spill mov rax, rbx + mov rdx, rbx + mov qword ptr [rsp + 248], rbx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 80], rax # 8-byte Spill - or rbx, 992 - vpinsrb xmm9, xmm0, byte ptr [rdx + r14], 1 - vpinsrb xmm0, xmm9, byte ptr [rdx + rcx], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15], 10 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 15 - mov r12, rbx - mov qword ptr [rsp + 176], rbx # 8-byte Spill - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 2 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 3 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 4 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 6 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 7 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 10 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 13 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 14 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 15 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 1], 1 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 1], 2 - mov r13, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 4 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 5 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 8 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 9 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 1], 11 + mov qword ptr [rsp + 160], rax # 8-byte Spill + or rdx, 992 + mov qword ptr [rsp + 264], rdx # 8-byte Spill + vpinsrb xmm9, xmm0, byte ptr [rdi + r12], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + r15], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 4 mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 1], 12 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 1], 13 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r11 + 1], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 6 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 15 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 1 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 2 mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 1], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 9 - mov r13, rdi - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 3 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 4 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 5 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 6 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 7 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 10 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 11 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 15 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 2 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 4 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 5 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 7 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 vinserti128 ymm13, ymm3, xmm0, 1 - vpinsrb xmm0, xmm5, byte ptr [rdx + r14 + 1], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm9, edi + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax vinserti128 ymm0, ymm0, xmm4, 1 - vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm10, edi + vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm10, eax vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 2], 1 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 2 + mov r10, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 2], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 6 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 7 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 8 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 10 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 2 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 4 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 5 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 2], 6 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 2], 7 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 2], 8 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 9 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 2], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 2], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 11 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 15 - mov r10, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 12 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 13 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rcx, r14 vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 2], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 2], 3 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 2], 4 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 2], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 7 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 8 - mov rcx, r13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 9 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 10 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 13 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 14 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rdx + r15 + 3], 1 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 2 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 3 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 4 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 3], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 8 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 9 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 11 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 12 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 3], 13 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 14 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rdx + r10 + 3], 1 - mov rbx, r10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 2], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 3], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 3], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 4 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 2], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 8 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 9 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 10 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 13 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 14 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 15 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm11, byte ptr [rdi + r13 + 3], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 5 + mov r10, rbx + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 9 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 10 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 11 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 14 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rcx + 3], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 2 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 3], 5 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 3], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 3], 14 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 9] - vmovd xmm8, edi - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 3], 15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 9] - vmovd xmm11, edi + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 1 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 2 - mov r12, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 4], 4 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 4], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 9 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 10 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 11 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 4], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 14 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 4], 15 - vpinsrb xmm3, xmm15, byte ptr [rdx + rbx + 4], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 2 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 4], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 4], 4 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 6 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 7 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 9 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 1 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 10 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 15 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm14, byte ptr [rdx + rax + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 6 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 5], 8 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 9 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 5], 11 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 5], 12 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 5], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 5], 15 - vpinsrb xmm5, xmm6, byte ptr [rdx + rbx + 5], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 3 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 2 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 5], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 5], 4 - mov r9, r14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 5 + mov r15, r13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 5], 7 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 5], 8 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 5], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 5], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 13 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 14 + mov rcx, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 15 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm15, byte ptr [rdi + r14 + 4], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + mov r9, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 3 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 4 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 8 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 9 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 10 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 11 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 12 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 13 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 14 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + rsi + 5], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 2 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 4 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 6 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 7 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 8 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 9 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 10 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 12 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r14 + 5], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 5 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 7 + mov rsi, rax + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 5], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 + mov r8, rax vinserti128 ymm14, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm3, edi - vinserti128 ymm15, ymm0, xmm4, 1 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm4, edi - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rdx + rax + 6], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 2 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 6], 3 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 4 - mov r10, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 6], 5 + vpinsrb xmm0, xmm5, byte ptr [rdi + rbx + 5], 15 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 8 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 9 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 10 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 6], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 6], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 13 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 14 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 6], 15 - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + r11 + 6], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 2 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 6], 6 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 6], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 9 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 10 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 6], 11 - mov r9, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 13 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 14 - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 15 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 1 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 7], 5 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 7 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 7], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 11 + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm3, eax + vinserti128 ymm15, ymm0, xmm4, 1 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rcx + 6], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 2 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 3 + mov r11, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 12 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 7], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 7], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 1 - mov r13, r11 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 5 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 9 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 10 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 6], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 12 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 6], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 3 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 4 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 6 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 7 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 8 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 9 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 7], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 13 - vinserti128 ymm0, ymm5, xmm0, 1 - vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rdi + 7], 14 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 11] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 7], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 11] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rdx + rdi + 8], 1 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 2 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 8], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 4 - mov r9, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 8], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 8], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 8 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 9 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 10 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 5 + mov rax, r10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 7 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 8 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 10 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 11 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 14 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 3 + mov r8, r14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 4 mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 8], 13 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 14 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r13 + 8], 1 - mov r14, rsi - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 2 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 3 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 8], 4 - mov rdi, r12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 8], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 6 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 9 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 10 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 13 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 14 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 15 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rdx + rbx + 9], 1 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 9], 3 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 6 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 9], 7 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 8 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 9 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 11 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 12 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 13 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 14 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 15 - vpinsrb xmm7, xmm11, byte ptr [rdx + r13 + 9], 1 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 9], 2 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rdi + 9], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 9], 6 - mov r14, rsi - vpinsrb xmm7, xmm7, byte ptr [rdx + r12 + 9], 7 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 9], 10 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 9], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 6 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 7 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 8 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 11 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 14 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 15 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 2 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 4 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 + vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 7], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 7], 15 + vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1152], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm0, edi - vinserti128 ymm5, ymm5, xmm6, 1 - vmovdqa ymmword ptr [rsp + 1120], ymm5 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm2, eax + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r14 + 8], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 6 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 8 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 12 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm5, edi - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 10], 1 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 10], 2 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 3 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 10], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 10], 5 - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 10], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 10], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r11 + 8], 1 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 5 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 7 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 9 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 10 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 11 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 8], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 13 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r14 + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 2 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 3 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 7 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 9 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 10 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 11 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 12 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 13 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 15 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rdx + 9], 1 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 2 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 5 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 8 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 9 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 11 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 14 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 10 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 9], 12 + mov r15, r10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 14 + vinserti128 ymm0, ymm5, xmm0, 1 + vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm0, eax + vinserti128 ymm5, ymm5, xmm6, 1 + vmovdqa ymmword ptr [rsp + 1088], ymm5 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 10], 4 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 6 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 7 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 10], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 1 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 12 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 13 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 11], 2 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 11], 4 - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 11], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 3 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 4 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 5 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 6 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 8 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 11], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 11 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 13 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 11], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 10 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 11 mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 11], 15 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 11], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 13 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 15 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 1 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 11], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 11], 8 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 5 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 7 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 9 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 10 + mov rcx, r11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 12 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 13 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 14 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 15 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 1 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 2 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 6 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 7 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 9 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 12 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 14 + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 2 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 4 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 11], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 11], 11 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 - vmovdqa ymmword ptr [rsp + 1088], ymm3 # 32-byte Spill - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 11], 14 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 13] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 15 - vinserti128 ymm1, ymm2, xmm1, 1 - vmovdqa ymmword ptr [rsp + 1056], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 13] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 1 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 12], 2 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 12], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 12], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 12], 5 + vmovdqa ymmword ptr [rsp + 1056], ymm3 # 32-byte Spill + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 8 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 9 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 11 + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 15 + vinserti128 ymm1, ymm2, xmm1, 1 + vmovdqa ymmword ptr [rsp + 1024], ymm1 # 32-byte Spill + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm1, eax + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 2 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 12], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 15 - vpinsrb xmm2, xmm5, byte ptr [rdx + r9 + 12], 1 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 2 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 4 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 5 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 12], 6 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 7 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 12], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 10 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 12], 14 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 5 - mov r10, r12 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 6 mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 7 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 12], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 15 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + r11 + 12], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 5 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 7 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 9 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 10 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 14 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 3 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 4 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 5 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 8 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 9 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 10 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 11 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 13 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 1 mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 9 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 11 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 13], 12 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 13 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 14 - mov r12, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 15 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 3 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 13], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 13], 6 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 13], 8 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 6 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 7 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 + vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 13], 15 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r13 + 14] + vmovd xmm1, eax + vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rax + 13], 15 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r15 + 14] + vmovd xmm0, eax + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 2 mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 14] - vmovd xmm1, edi - vinserti128 ymm0, ymm0, xmm3, 1 - vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 14] - vmovd xmm0, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 1 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 14], 2 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 9 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 11 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 12 + mov r11, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 13 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 5 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 14], 7 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 14], 8 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 9 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 10 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 14], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 12 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 13 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 14], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 14], 15 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 2 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 6 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 7 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 9 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 10 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 11 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 14], 12 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 15 - mov r8, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + r8 + 15] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 4 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 15], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 15], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 15], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 15 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 5 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 12 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 15 + movzx eax, byte ptr [rdi + r13 + 15] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 3 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 15], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 15], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 15], 14 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 15], 15 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rbx + 15] - vmovd xmm3, edi - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 2 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 15], 3 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 6 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 15], 7 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 9 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 13 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 14 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 15], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 15], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 15 + movzx eax, byte ptr [rdi + r15 + 15] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 8 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 9 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 13 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 14 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 - vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill + vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 - vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - movzx edi, byte ptr [rdx + r8 + 16] - vmovd xmm0, edi - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 1 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 2 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 4 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 16], 6 - mov r12, r13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 7 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 8 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 9 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 10 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 13 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 16], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 16], 15 - movzx edi, byte ptr [rdx + rbx + 16] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 16], 1 - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 16], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 16], 3 + vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm0, eax + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 4 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 4 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 16], 7 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 9 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 13 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 16], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 16], 15 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 17] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 1 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 2 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 4 - mov r10, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 17], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 17], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 6 mov r12, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 17], 7 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 8 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 9 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 17], 10 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 11 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 12 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 17], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 17], 14 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 17] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 2 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 5 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 6 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 17], 10 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 11 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 17], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rax + 17], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 18] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 2 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 3 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 18], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 5 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 18], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 8 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 18], 10 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 11 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 18], 13 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 14 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 15 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 18] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 1 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 18], 2 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 18], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 7 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 9 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 12 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 14 - mov r8, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 15 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 19] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 2 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 19], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 10 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 13 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 15 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 19], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 11 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 12 + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 10 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 11 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 14 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 15 - movzx edi, byte ptr [rdx + r11 + 19] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 19], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 19], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 15 + mov r9, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r9 + 17] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 1 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 4 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 19], 6 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 7 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 9 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 19], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 7 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 17], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 14 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 17], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 17] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 1 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 2 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 6 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 19], 13 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 19], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 19], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 11 + mov r14, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - vinserti128 ymm0, ymm3, xmm2, 1 + vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 17], 15 + vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 20] - vmovd xmm0, edi - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 1 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 20], 2 + movzx eax, byte ptr [rdi + r9 + 18] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 2 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 18], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm1, eax mov r12, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 20], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 4 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 20], 5 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 20], 6 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 7 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 8 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 9 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 20], 12 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 20], 13 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 14 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 20] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 2 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 20], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 6 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 8 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 10 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 11 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 20], 14 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 20], 15 - movzx edi, byte ptr [rdx + rax + 21] - vmovd xmm2, edi + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 3 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 21], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 21], 3 - mov r13, r12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 5 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 7 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 8 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 9 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 10 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 11 + mov rcx, r14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 12 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 13 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 14 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 5 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 6 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 13 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 21], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 21], 6 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 21], 7 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 21], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 1 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 9 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 21], 10 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 11 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 21], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 15 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 21] - vmovd xmm3, edi - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 21], 1 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 3 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 6 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 7 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 8 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 9 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rdx + r9 + 21], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 1 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 22], 3 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 22], 4 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 22], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 8 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 22], 10 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 11 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 22], 14 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 15 - movzx edi, byte ptr [rdx + r11 + 22] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 22], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 22], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 5 - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 22], 6 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 7 - mov r10, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 22], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 19], 15 + vinserti128 ymm0, ymm1, xmm0, 1 + vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill + vinserti128 ymm0, ymm3, xmm2, 1 + vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill + mov r9, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r9 + 20] + vmovd xmm0, eax + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 1 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 10 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 22], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 20], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 7 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 23] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 2 - mov r14, r13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 23], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 9 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 10 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 11 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 12 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 13 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 14 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 15 mov r13, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 23], 5 - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 6 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 7 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 8 + movzx eax, byte ptr [rdi + r13 + 20] + vmovd xmm1, eax + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 1 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 9 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 10 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 11 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 12 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 23], 13 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 23], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 23] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 2 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 23], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 23], 8 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 23], 9 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 23], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 15 - vinserti128 ymm10, ymm1, xmm0, 1 - vinserti128 ymm11, ymm3, xmm2, 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 24] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 1 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 24], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 24], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 24], 7 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 4 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 10 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 24], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 24], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 24], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 13 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 14 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 15 - mov r14, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + r14 + 24] - vmovd xmm1, edi - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 15 + movzx eax, byte ptr [rdi + r9 + 21] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 1 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 21], 3 + mov r12, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 15 + movzx eax, byte ptr [rdi + r13 + 21] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 3 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 24], 4 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 4 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 6 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 8 - mov r10, rbx - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 24], 9 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 24], 10 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 24], 11 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov r9, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 13 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 24], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 25] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 25], 2 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 4 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 7 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 8 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 9 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 25], 11 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 13 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 14 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 25], 15 - movzx edi, byte ptr [rdx + r14 + 25] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 1 - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 2 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 25], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 6 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 7 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 25], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 12 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 25], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 13 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rcx + 25], 15 + vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r11 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 26] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 1 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 26], 2 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 4 - mov rsi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 5 + vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 6 + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 4 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 5 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 6 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 8 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 2 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 5 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 11 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm2, eax + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 2 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 6 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 10 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 11 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 12 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 13 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 14 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm3, eax + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 1 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 9 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 26], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 12 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 14 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 15 + vinserti128 ymm10, ymm1, xmm0, 1 + vinserti128 ymm11, ymm3, xmm2, 1 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 24], 1 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 3 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 13 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 26], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 26], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 26] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 1 - mov rax, r9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 2 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 6 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 7 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 26], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 26], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 24], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 8 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 3 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 7 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 11 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 13 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm2, eax + mov r13, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 2 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 4 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 5 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 6 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 12 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 14 + vinserti128 ymm9, ymm1, xmm0, 1 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rdx + 25], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 26] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 1 mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 26], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 26], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 15 - movzx edi, byte ptr [rdx + r11 + 27] - vmovd xmm2, edi - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 27], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 27], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 5 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 27], 6 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 27], 7 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 8 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 27], 10 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 11 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 27], 14 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 27], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 27] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 2 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 3 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 27], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 7 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 8 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 27], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 27], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 10 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 11 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 26], 15 + mov r10, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 26] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 1 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 3 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 4 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 13 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 27] + vmovd xmm2, eax + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 9 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 10 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 15 + movzx eax, byte ptr [rdi + r10 + 27] + vmovd xmm3, eax + mov r10, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill + vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 - vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov r9, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + r9 + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 28], 1 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 28], 2 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 28], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 4 - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 28], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 7 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 8 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 28], 9 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 11 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 28], 12 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 13 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 14 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 15 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rsi + 28] - vmovd xmm1, edi - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 1 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 2 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 28], 4 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 5 + vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill + movzx eax, byte ptr [rdi + rdx + 28] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 2 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 3 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 4 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 28], 11 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 15 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 28] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 5 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 8 mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 28], 6 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 7 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 9 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 10 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 28], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 10 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 11 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 29] + vmovd xmm2, eax + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 29], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 7 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 15 - movzx edi, byte ptr [rdx + r9 + 29] - vmovd xmm2, edi - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 29], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 29], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 5 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 29], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 29], 9 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 29], 10 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 29], 12 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 29], 14 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 29], 15 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rbx + 29] - vmovd xmm3, edi - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 29], 1 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 3 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 29], 6 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 9 mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 8 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 9 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 11 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 13 - vpinsrb xmm4, xmm3, byte ptr [rdx + rax + 29], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rdx + rax + 29], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 30] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 30], 1 - movzx edi, byte ptr [rdx + rcx + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 31], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 29], 10 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 12 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 13 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 4 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 31], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 7 - mov rdi, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 14 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 15 + movzx eax, byte ptr [rdi + rdx + 29] + vmovd xmm3, eax + mov r13, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 1 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 31], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 31], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 8 + mov r11, r14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 29], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 13 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm3, byte ptr [rdi + r14 + 29], 14 + vinserti128 ymm0, ymm1, xmm0, 1 + vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rax + 29], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 30] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 1 + movzx eax, byte ptr [rdi + rbx + 31] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 31], 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 12 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov rbx, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 31], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 11 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rdx + rax + 31], 15 - movzx eax, byte ptr [rdx + rbx + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 31], 13 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + r12 + 31], 15 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 30], 1 - movzx eax, byte ptr [rdx + rbx + 31] + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rdx + r12 + 31], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rdx + r10 + 31], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 1 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 2 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 31], 4 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 6 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 7 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 31], 14 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill vmovdqa ymm2, ymmword ptr [rsp + 512] # 32-byte Reload vpcmpeqb ymm0, ymm13, ymm2 - vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1216] # 32-byte Folded Reload + vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1184] # 32-byte Folded Reload vmovdqa ymm5, ymmword ptr [rip + .LCPI5_0] # ymm5 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] vpandn ymm7, ymm7, ymm5 vpaddb ymm0, ymm7, ymm0 @@ -34789,12 +35713,12 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 vpandn ymm12, ymm12, ymm3 vpor ymm7, ymm12, ymm7 vpcmpeqb ymm12, ymm14, ymm2 - vmovdqa ymm8, ymmword ptr [rip + .LCPI5_3] # ymm8 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - vpandn ymm12, ymm12, ymm8 + vmovdqa ymm4, ymmword ptr [rip + .LCPI5_3] # ymm4 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + vpandn ymm12, ymm12, ymm4 vpor ymm7, ymm12, ymm7 vpcmpeqd ymm1, ymm1, ymm1 vpsubb ymm0, ymm0, ymm1 - vpcmpeqd ymm4, ymm4, ymm4 + vpcmpeqd ymm8, ymm8, ymm8 vpor ymm0, ymm0, ymm7 vpcmpeqb ymm7, ymm15, ymm2 vmovdqa ymm1, ymmword ptr [rip + .LCPI5_4] # ymm1 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] @@ -34803,73 +35727,75 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 vmovdqa ymm13, ymmword ptr [rip + .LCPI5_5] # ymm13 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] vpandn ymm12, ymm12, ymm13 vpor ymm7, ymm12, ymm7 - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1184] # 32-byte Folded Reload - vmovdqa ymm9, ymmword ptr [rip + .LCPI5_6] # ymm9 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - vpandn ymm12, ymm12, ymm9 + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1152] # 32-byte Folded Reload + vmovdqa ymm14, ymmword ptr [rip + .LCPI5_6] # ymm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + vpandn ymm12, ymm12, ymm14 vpor ymm7, ymm12, ymm7 vpor ymm0, ymm0, ymm7 - vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1152] # 32-byte Folded Reload - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1120] # 32-byte Folded Reload + vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 1120] # 32-byte Folded Reload + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1088] # 32-byte Folded Reload vpandn ymm12, ymm12, ymm5 vpaddb ymm7, ymm12, ymm7 - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1088] # 32-byte Folded Reload + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1056] # 32-byte Folded Reload vpandn ymm12, ymm12, ymm6 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 1056] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 1024] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm3 vpor ymm12, ymm12, ymm15 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 992] # 32-byte Folded Reload - vpandn ymm15, ymm15, ymm8 + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 960] # 32-byte Folded Reload + vpandn ymm15, ymm15, ymm4 vpor ymm12, ymm12, ymm15 - vpsubb ymm7, ymm7, ymm4 + vpsubb ymm7, ymm7, ymm8 vpor ymm7, ymm12, ymm7 - vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 1024] # 32-byte Folded Reload + vpcmpeqb ymm12, ymm2, ymmword ptr [rsp + 992] # 32-byte Folded Reload vpandn ymm12, ymm12, ymm1 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 928] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 896] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm13 vpor ymm12, ymm12, ymm15 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 960] # 32-byte Folded Reload - vpandn ymm15, ymm15, ymm9 + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 928] # 32-byte Folded Reload + vpandn ymm15, ymm15, ymm14 + vmovdqa ymm8, ymm14 vpor ymm12, ymm12, ymm15 vpor ymm12, ymm12, ymm7 - vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 896] # 32-byte Folded Reload - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 864] # 32-byte Folded Reload + vpcmpeqb ymm7, ymm2, ymmword ptr [rsp + 864] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 832] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm5 vpaddb ymm7, ymm15, ymm7 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 800] # 32-byte Folded Reload + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 768] # 32-byte Folded Reload vpandn ymm15, ymm15, ymm6 - vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 832] # 32-byte Folded Reload + vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 800] # 32-byte Folded Reload vpandn ymm14, ymm14, ymm3 vpor ymm14, ymm15, ymm14 - vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 736] # 32-byte Folded Reload - vpandn ymm15, ymm15, ymm8 + vpcmpeqb ymm15, ymm2, ymmword ptr [rsp + 704] # 32-byte Folded Reload + vpandn ymm15, ymm15, ymm4 vpor ymm14, ymm14, ymm15 - vpsubb ymm7, ymm7, ymm4 + vpcmpeqd ymm15, ymm15, ymm15 + vpsubb ymm7, ymm7, ymm15 vpor ymm7, ymm14, ymm7 - vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 768] # 32-byte Folded Reload + vpcmpeqb ymm14, ymm2, ymmword ptr [rsp + 736] # 32-byte Folded Reload vpandn ymm14, ymm14, ymm1 vpcmpeqb ymm10, ymm10, ymm2 vpandn ymm10, ymm10, ymm13 vpor ymm10, ymm14, ymm10 vpcmpeqb ymm11, ymm11, ymm2 - vmovdqa ymm14, ymm9 - vpandn ymm11, ymm11, ymm9 + vpandn ymm11, ymm11, ymm8 + vmovdqa ymm14, ymm8 vpor ymm10, ymm10, ymm11 vpor ymm7, ymm10, ymm7 - vpcmpeqb ymm9, ymm2, ymmword ptr [rsp + 544] # 32-byte Folded Reload - vpcmpeqb ymm8, ymm2, ymmword ptr [rsp + 576] # 32-byte Folded Reload + vpcmpeqb ymm9, ymm9, ymm2 + vpcmpeqb ymm8, ymm2, ymmword ptr [rsp + 544] # 32-byte Folded Reload vpandn ymm8, ymm8, ymm5 vpaddb ymm8, ymm8, ymm9 - vpcmpeqb ymm5, ymm2, ymmword ptr [rsp + 608] # 32-byte Folded Reload + vpcmpeqb ymm5, ymm2, ymmword ptr [rsp + 576] # 32-byte Folded Reload vpandn ymm5, ymm5, ymm6 - vpcmpeqb ymm6, ymm2, ymmword ptr [rsp + 640] # 32-byte Folded Reload + vpcmpeqb ymm6, ymm2, ymmword ptr [rsp + 608] # 32-byte Folded Reload vpandn ymm6, ymm6, ymm3 vpor ymm5, ymm5, ymm6 - vpcmpeqb ymm3, ymm2, ymmword ptr [rsp + 672] # 32-byte Folded Reload - vpandn ymm3, ymm3, ymmword ptr [rip + .LCPI5_3] + vpcmpeqb ymm3, ymm2, ymmword ptr [rsp + 640] # 32-byte Folded Reload + vpandn ymm3, ymm3, ymm4 vpor ymm3, ymm5, ymm3 - vpsubb ymm5, ymm8, ymm4 + vpsubb ymm5, ymm8, ymm15 vpor ymm3, ymm5, ymm3 - vpcmpeqb ymm4, ymm2, ymmword ptr [rsp + 704] # 32-byte Folded Reload + vpcmpeqb ymm4, ymm2, ymmword ptr [rsp + 672] # 32-byte Folded Reload vpandn ymm4, ymm4, ymm1 vpcmpeqb ymm1, ymm2, ymmword ptr [rsp + 320] # 32-byte Folded Reload vpandn ymm1, ymm1, ymm13 @@ -34891,23 +35817,23 @@ comparison_not_equal_scalar_arr_avx2: # @comparison_not_equal_scalar_arr_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 408] # 8-byte Reload - vmovdqu ymmword ptr [rdi + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [rdi + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [rdi + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [rdi + 4*rcx], ymm1 + vmovdqu ymmword ptr [rbx + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rbx + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rbx + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rbx + 4*rcx], ymm1 add rcx, 32 - mov rbx, rcx + mov rax, rcx cmp rcx, qword ptr [rsp + 376] # 8-byte Folded Reload - jne .LBB5_169 -# %bb.170: - mov r14, qword ptr [rsp + 384] # 8-byte Reload - cmp r14, qword ptr [rsp + 376] # 8-byte Folded Reload - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - mov r13, qword ptr [rsp + 400] # 8-byte Reload - mov rdx, qword ptr [rsp + 392] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - jne .LBB5_117 - jmp .LBB5_120 + jne .LBB5_193 +# %bb.194: + mov rcx, qword ptr [rsp + 384] # 8-byte Reload + cmp rcx, qword ptr [rsp + 376] # 8-byte Folded Reload + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + mov r13, qword ptr [rsp + 392] # 8-byte Reload + mov rdi, qword ptr [rsp + 400] # 8-byte Reload + jne .LBB5_152 + jmp .LBB5_155 .Lfunc_end5: .size comparison_not_equal_scalar_arr_avx2, .Lfunc_end5-comparison_not_equal_scalar_arr_avx2 # -- End function @@ -34926,76 +35852,91 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 and rsp, -8 sub rsp, 72 # kill: def $r9d killed $r9d def $r9 - mov r11, r8 - mov r14, rcx + mov r13, r8 + mov r15, rcx cmp edi, 6 - jg .LBB6_29 + jg .LBB6_35 # %bb.1: cmp edi, 3 jle .LBB6_2 -# %bb.15: +# %bb.18: cmp edi, 4 - je .LBB6_68 -# %bb.16: + je .LBB6_83 +# %bb.19: cmp edi, 5 - je .LBB6_79 -# %bb.17: + je .LBB6_97 +# %bb.20: cmp edi, 6 - jne .LBB6_123 -# %bb.18: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB6_153 +# %bb.21: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_22 -# %bb.19: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rdx] - add rdx, 4 - cmp ecx, dword ptr [rsi] - lea rsi, [rsi + 4] - sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB6_20 -# %bb.21: - add r14, 1 -.LBB6_22: - sar r15, 5 - cmp r11, 32 - jl .LBB6_26 + je .LBB6_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_26 # %bb.23: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 .LBB6_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill + lea rcx, [r9 + rax] + mov ebx, dword ptr [rdx + 4*rax] + cmp ebx, dword ptr [rsi + 4*rax] + sbb r11d, r11d + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl + add rax, 1 + add r10, -4 + cmp r8, rax + jne .LBB6_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB6_26: + sub r13, r8 + je .LBB6_153 +# %bb.27: + add r15, 1 +.LBB6_28: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_32 +# %bb.29: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB6_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] mov eax, dword ptr [rsi + 8] seta r13b @@ -35016,7 +35957,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] mov eax, dword ptr [rsi + 32] - seta r15b + seta r14b cmp eax, dword ptr [rdx + 32] seta byte ptr [rsp + 9] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] @@ -35030,7 +35971,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 mov eax, dword ptr [rsi + 48] seta r9b cmp eax, dword ptr [rdx + 48] - seta r12b + seta r15b mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] mov eax, dword ptr [rsi + 56] @@ -35046,7 +35987,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 cmp r11d, dword ptr [rdx + 64] seta byte ptr [rsp + 10] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 68] - seta r14b + seta r12b cmp eax, dword ptr [rdx + 72] mov eax, dword ptr [rsi + 76] seta byte ptr [rsp + 6] # 1-byte Folded Spill @@ -35090,11 +36031,11 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 cmp eax, dword ptr [rdx + 124] seta al add r13b, r13b - add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, r13b @@ -35114,23 +36055,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r12b, 4 - or r12b, r9b + shl r15b, 4 + or r15b, r9b movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload shl bl, 5 - or bl, r12b + or bl, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload shl r8b, 6 shl r10b, 7 or r10b, r8b - or r15b, cl + or r14b, cl or r10b, bl - add r14b, r14b - add r14b, byte ptr [rsp + 10] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 10] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 6] # 1-byte Folded Reload shl cl, 2 - or cl, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or cl, r12b shl r11b, 3 or r11b, cl movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload @@ -35140,12 +36081,12 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 5 or cl, bl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx r8d, byte ptr [rsp + 13] # 1-byte Folded Reload shl r8b, 6 shl dil, 7 or dil, r8b - mov byte ptr [r14 + 1], r10b + mov byte ptr [r15 + 1], r10b or dil, cl movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload add cl, cl @@ -35169,31 +36110,30 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, 7 or al, bl or al, cl - mov byte ptr [r14 + 2], dil - mov byte ptr [r14 + 3], al + mov byte ptr [r15 + 2], dil + mov byte ptr [r15 + 3], al add rdx, 128 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_24 -# %bb.25: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_26: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.27: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_30 +# %bb.31: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_32: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB6_28: # =>This Inner Loop Header: Depth=1 +.LBB6_34: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rdx + 4*rcx] cmp edi, dword ptr [rsi + 4*rcx] sbb edi, edi mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -35201,74 +36141,89 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_28 - jmp .LBB6_123 -.LBB6_29: + cmp r13, r8 + jne .LBB6_34 + jmp .LBB6_153 +.LBB6_35: cmp edi, 8 - jle .LBB6_30 -# %bb.43: + jle .LBB6_36 +# %bb.52: cmp edi, 9 - je .LBB6_101 -# %bb.44: + je .LBB6_125 +# %bb.53: cmp edi, 11 - je .LBB6_112 -# %bb.45: + je .LBB6_139 +# %bb.54: cmp edi, 12 - jne .LBB6_123 -# %bb.46: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB6_153 +# %bb.55: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_50 -# %bb.47: - movsxd rax, r9d + je .LBB6_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_60 +# %bb.57: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_48: # =>This Inner Loop Header: Depth=1 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - vucomisd xmm0, qword ptr [rdx] - seta r10b - add rdx, 8 - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_58: # =>This Inner Loop Header: Depth=1 + vmovsd xmm0, qword ptr [rsi + 8*rax] # xmm0 = mem[0],zero + vucomisd xmm0, qword ptr [rdx + 8*rax] + lea rcx, [r9 + rax] + seta r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_48 -# %bb.49: - add r14, 1 -.LBB6_50: - sar r15, 5 - cmp r11, 32 - jl .LBB6_54 -# %bb.51: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB6_58 +# %bb.59: + sub rsi, r10 + sub rdx, r10 +.LBB6_60: + sub r13, r8 + je .LBB6_153 +# %bb.61: + add r15, 1 +.LBB6_62: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_66 +# %bb.63: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx] seta byte ptr [rsp + 4] # 1-byte Folded Spill @@ -35292,7 +36247,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 seta al vmovsd xmm0, qword ptr [rsi + 56] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 56] - seta r15b + seta r14b vmovsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 64] seta byte ptr [rsp + 8] # 1-byte Folded Spill @@ -35307,7 +36262,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 seta r11b vmovsd xmm0, qword ptr [rsi + 96] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 96] - seta r14b + seta r15b vmovsd xmm0, qword ptr [rsi + 104] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 104] seta byte ptr [rsp + 5] # 1-byte Folded Spill @@ -35369,8 +36324,8 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 add cl, cl add cl, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 - shl r15b, 7 - or r15b, al + shl r14b, 7 + or r14b, al movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 2 or al, cl @@ -35391,26 +36346,26 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 or al, cl @@ -35418,12 +36373,12 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al @@ -35449,24 +36404,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB6_52 -# %bb.53: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB6_54: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.55: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB6_64 +# %bb.65: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB6_66: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB6_56: # =>This Inner Loop Header: Depth=1 +.LBB6_68: # =>This Inner Loop Header: Depth=1 vmovsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 8*rcx] lea r8, [rcx + 1] @@ -35474,7 +36428,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -35482,72 +36436,93 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_56 - jmp .LBB6_123 + cmp r13, r8 + jne .LBB6_68 + jmp .LBB6_153 .LBB6_2: cmp edi, 2 - je .LBB6_57 + mov r8, r15 + je .LBB6_69 # %bb.3: cmp edi, 3 - jne .LBB6_123 + jne .LBB6_153 # %bb.4: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_8 + je .LBB6_11 # %bb.5: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setg r10b - neg r10b - lea rdi, [rax + 7] + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 test rax, rax - cmovns rdi, rax + jle .LBB6_9 +# %bb.6: + movsxd rbx, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB6_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setg r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r15, r8 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB6_6 -# %bb.7: - add r14, 1 -.LBB6_8: - sar r15, 5 - cmp r11, 32 - jl .LBB6_12 -# %bb.9: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov byte ptr [r8 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB6_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB6_9: + sub r13, rax + je .LBB6_153 +# %bb.10: + add r15, 1 +.LBB6_11: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_15 +# %bb.12: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setg cl movzx eax, byte ptr [rsi + 2] @@ -35567,7 +36542,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 4] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setg r15b + setg r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] setg byte ptr [rsp + 7] # 1-byte Folded Spill @@ -35582,7 +36557,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setg r14b + setg r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] setg byte ptr [rsp + 5] # 1-byte Folded Spill @@ -35642,12 +36617,12 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 cmp al, byte ptr [rdx + 31] setg r8b add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload mov eax, ecx movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, al @@ -35669,26 +36644,26 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 6] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 13] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 4 or al, cl @@ -35696,12 +36671,12 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al @@ -35727,24 +36702,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_10 -# %bb.11: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_12: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.13: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_13 +# %bb.14: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_15: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB6_14: # =>This Inner Loop Header: Depth=1 +.LBB6_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -35752,7 +36726,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -35760,71 +36734,86 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_14 - jmp .LBB6_123 -.LBB6_30: + cmp r13, r8 + jne .LBB6_17 + jmp .LBB6_153 +.LBB6_36: cmp edi, 7 - je .LBB6_90 -# %bb.31: + je .LBB6_111 +# %bb.37: cmp edi, 8 - jne .LBB6_123 -# %bb.32: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB6_153 +# %bb.38: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_36 -# %bb.33: - movsxd rax, r9d + je .LBB6_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rdx] - add rdx, 8 - cmp rcx, qword ptr [rsi] - lea rsi, [rsi + 8] - sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB6_41: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rdx + 8*rax] + cmp rbx, qword ptr [rsi + 8*rax] + sbb r11d, r11d + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_34 -# %bb.35: - add r14, 1 -.LBB6_36: - sar r15, 5 - cmp r11, 32 - jl .LBB6_40 -# %bb.37: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB6_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB6_43: + sub r13, r8 + je .LBB6_153 +# %bb.44: + add r15, 1 +.LBB6_45: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_49 +# %bb.46: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] mov rax, qword ptr [rsi + 16] seta r13b @@ -35845,7 +36834,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] mov rax, qword ptr [rsi + 64] - seta r15b + seta r14b cmp rax, qword ptr [rdx + 64] seta byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] @@ -35859,7 +36848,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 mov rax, qword ptr [rsi + 96] seta r9b cmp rax, qword ptr [rdx + 96] - seta r12b + seta r15b mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] mov rax, qword ptr [rsi + 112] @@ -35875,7 +36864,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 cmp r11, qword ptr [rdx + 128] seta byte ptr [rsp + 10] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 136] - seta r14b + seta r12b cmp rax, qword ptr [rdx + 144] mov rax, qword ptr [rsi + 152] seta byte ptr [rsp + 6] # 1-byte Folded Spill @@ -35919,11 +36908,11 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 cmp rax, qword ptr [rdx + 248] seta al add r13b, r13b - add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, r13b @@ -35943,23 +36932,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r12b, 4 - or r12b, r9b + shl r15b, 4 + or r15b, r9b movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload shl bl, 5 - or bl, r12b + or bl, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload shl r8b, 6 shl r10b, 7 or r10b, r8b - or r15b, cl + or r14b, cl or r10b, bl - add r14b, r14b - add r14b, byte ptr [rsp + 10] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 10] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 6] # 1-byte Folded Reload shl cl, 2 - or cl, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or cl, r12b shl r11b, 3 or r11b, cl movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload @@ -35969,12 +36958,12 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 5 or cl, bl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx r8d, byte ptr [rsp + 13] # 1-byte Folded Reload shl r8b, 6 shl dil, 7 or dil, r8b - mov byte ptr [r14 + 1], r10b + mov byte ptr [r15 + 1], r10b or dil, cl movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload add cl, cl @@ -35998,31 +36987,30 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, 7 or al, bl or al, cl - mov byte ptr [r14 + 2], dil - mov byte ptr [r14 + 3], al + mov byte ptr [r15 + 2], dil + mov byte ptr [r15 + 3], al add rdx, 256 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_38 -# %bb.39: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_40: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.41: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_47 +# %bb.48: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_49: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB6_42: # =>This Inner Loop Header: Depth=1 +.LBB6_51: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rdx + 8*rcx] cmp rdi, qword ptr [rsi + 8*rcx] sbb edi, edi mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -36030,65 +37018,80 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_42 - jmp .LBB6_123 -.LBB6_68: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_51 + jmp .LBB6_153 +.LBB6_83: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_72 -# %bb.69: - movsxd rax, r9d + je .LBB6_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rdx] - add rdx, 2 - cmp cx, word ptr [rsi] - lea rsi, [rsi + 2] - sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB6_86: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rdx + 2*rax] + cmp bx, word ptr [rsi + 2*rax] + sbb r11d, r11d + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_70 -# %bb.71: - add r14, 1 -.LBB6_72: - sar r15, 5 - cmp r11, 32 - jl .LBB6_76 -# %bb.73: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB6_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB6_88: + sub r13, r8 + je .LBB6_153 +# %bb.89: + add r15, 1 +.LBB6_90: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_94 +# %bb.91: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] movzx eax, word ptr [rsi + 4] seta r13b @@ -36109,7 +37112,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] movzx eax, word ptr [rsi + 16] - seta r15b + seta r14b cmp ax, word ptr [rdx + 16] seta byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] @@ -36123,7 +37126,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, word ptr [rsi + 24] seta r9b cmp ax, word ptr [rdx + 24] - seta r12b + seta r15b movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] movzx eax, word ptr [rsi + 28] @@ -36139,7 +37142,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 cmp r11w, word ptr [rdx + 32] seta byte ptr [rsp + 10] # 1-byte Folded Spill cmp cx, word ptr [rdx + 34] - seta r14b + seta r12b cmp ax, word ptr [rdx + 36] movzx eax, word ptr [rsi + 38] seta byte ptr [rsp + 6] # 1-byte Folded Spill @@ -36183,11 +37186,11 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 cmp ax, word ptr [rdx + 62] seta al add r13b, r13b - add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, r13b @@ -36207,23 +37210,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r12b, 4 - or r12b, r9b + shl r15b, 4 + or r15b, r9b movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload shl bl, 5 - or bl, r12b + or bl, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload shl r8b, 6 shl r10b, 7 or r10b, r8b - or r15b, cl + or r14b, cl or r10b, bl - add r14b, r14b - add r14b, byte ptr [rsp + 10] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 10] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 6] # 1-byte Folded Reload shl cl, 2 - or cl, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or cl, r12b shl r11b, 3 or r11b, cl movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload @@ -36233,12 +37236,12 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 5 or cl, bl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx r8d, byte ptr [rsp + 13] # 1-byte Folded Reload shl r8b, 6 shl dil, 7 or dil, r8b - mov byte ptr [r14 + 1], r10b + mov byte ptr [r15 + 1], r10b or dil, cl movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload add cl, cl @@ -36262,31 +37265,30 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, 7 or al, bl or al, cl - mov byte ptr [r14 + 2], dil - mov byte ptr [r14 + 3], al + mov byte ptr [r15 + 2], dil + mov byte ptr [r15 + 3], al add rdx, 64 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_74 -# %bb.75: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_76: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.77: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_92 +# %bb.93: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_94: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB6_78: # =>This Inner Loop Header: Depth=1 +.LBB6_96: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rdx + 2*rcx] cmp di, word ptr [rsi + 2*rcx] sbb edi, edi mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -36294,68 +37296,83 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_78 - jmp .LBB6_123 -.LBB6_79: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_96 + jmp .LBB6_153 +.LBB6_97: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_83 -# %bb.80: - movsxd rax, r9d + je .LBB6_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setg r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setg r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_81 -# %bb.82: - add r14, 1 -.LBB6_83: - sar r15, 5 - cmp r11, 32 - jl .LBB6_87 -# %bb.84: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB6_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB6_102: + sub r13, r8 + je .LBB6_153 +# %bb.103: + add r15, 1 +.LBB6_104: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_108 +# %bb.105: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] setg byte ptr [rsp + 20] # 1-byte Folded Spill @@ -36379,7 +37396,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setg r8b + setg dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setg r11b @@ -36419,7 +37436,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 11] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setg byte ptr [rsp + 12] # 1-byte Folded Spill + setg byte ptr [rsp + 14] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setg r9b @@ -36428,10 +37445,10 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 19] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setg byte ptr [rsp + 13] # 1-byte Folded Spill + setg byte ptr [rsp + 12] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setg byte ptr [rsp + 14] # 1-byte Folded Spill + setg byte ptr [rsp + 13] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] setg byte ptr [rsp + 15] # 1-byte Folded Spill @@ -36446,10 +37463,10 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] - setg dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setg r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -36458,34 +37475,34 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -36498,22 +37515,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -36530,27 +37548,26 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 64 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB6_85 -# %bb.86: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB6_87: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.88: - sub r11, r15 + jne .LBB6_106 +# %bb.107: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB6_108: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB6_89: # =>This Inner Loop Header: Depth=1 +.LBB6_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -36558,7 +37575,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -36566,68 +37583,83 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_89 - jmp .LBB6_123 -.LBB6_101: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_110 + jmp .LBB6_153 +.LBB6_125: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_105 -# %bb.102: - movsxd rax, r9d + je .LBB6_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setg r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setg r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_103 -# %bb.104: - add r14, 1 -.LBB6_105: - sar r15, 5 - cmp r11, 32 - jl .LBB6_109 -# %bb.106: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB6_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB6_130: + sub r13, r8 + je .LBB6_153 +# %bb.131: + add r15, 1 +.LBB6_132: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_136 +# %bb.133: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] setg byte ptr [rsp + 20] # 1-byte Folded Spill @@ -36651,7 +37683,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setg r8b + setg dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setg r11b @@ -36691,7 +37723,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 11] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setg byte ptr [rsp + 12] # 1-byte Folded Spill + setg byte ptr [rsp + 14] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setg r9b @@ -36700,10 +37732,10 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 19] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setg byte ptr [rsp + 13] # 1-byte Folded Spill + setg byte ptr [rsp + 12] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setg byte ptr [rsp + 14] # 1-byte Folded Spill + setg byte ptr [rsp + 13] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] setg byte ptr [rsp + 15] # 1-byte Folded Spill @@ -36718,10 +37750,10 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] - setg dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setg r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -36730,34 +37762,34 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -36770,22 +37802,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -36802,27 +37835,26 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB6_107 -# %bb.108: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB6_109: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.110: - sub r11, r15 + jne .LBB6_134 +# %bb.135: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB6_136: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.137: xor ecx, ecx .p2align 4, 0x90 -.LBB6_111: # =>This Inner Loop Header: Depth=1 +.LBB6_138: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -36830,7 +37862,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -36838,62 +37870,77 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_111 - jmp .LBB6_123 -.LBB6_112: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_138 + jmp .LBB6_153 +.LBB6_139: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_116 -# %bb.113: - movsxd rax, r9d + je .LBB6_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_144 +# %bb.141: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_114: # =>This Inner Loop Header: Depth=1 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - vucomiss xmm0, dword ptr [rdx] - seta r10b - add rdx, 4 - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_142: # =>This Inner Loop Header: Depth=1 + vmovss xmm0, dword ptr [rsi + 4*rax] # xmm0 = mem[0],zero,zero,zero + vucomiss xmm0, dword ptr [rdx + 4*rax] + lea rcx, [r9 + rax] + seta r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_114 -# %bb.115: - add r14, 1 -.LBB6_116: - sar r15, 5 - cmp r11, 32 - jl .LBB6_120 -# %bb.117: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB6_142 +# %bb.143: + sub rsi, r10 + sub rdx, r10 +.LBB6_144: + sub r13, r8 + je .LBB6_153 +# %bb.145: + add r15, 1 +.LBB6_146: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_150 +# %bb.147: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx] seta byte ptr [rsp + 4] # 1-byte Folded Spill @@ -36917,7 +37964,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 seta al vmovss xmm0, dword ptr [rsi + 28] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 28] - seta r15b + seta r14b vmovss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 32] seta byte ptr [rsp + 8] # 1-byte Folded Spill @@ -36932,7 +37979,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 seta r11b vmovss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 48] - seta r14b + seta r15b vmovss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 52] seta byte ptr [rsp + 5] # 1-byte Folded Spill @@ -36994,8 +38041,8 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 add cl, cl add cl, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 - shl r15b, 7 - or r15b, al + shl r14b, 7 + or r14b, al movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 2 or al, cl @@ -37016,26 +38063,26 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 or al, cl @@ -37043,12 +38090,12 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al @@ -37074,24 +38121,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB6_118 -# %bb.119: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB6_120: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.121: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB6_148 +# %bb.149: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB6_150: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.151: xor ecx, ecx .p2align 4, 0x90 -.LBB6_122: # =>This Inner Loop Header: Depth=1 +.LBB6_152: # =>This Inner Loop Header: Depth=1 vmovss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 4*rcx] lea r8, [rcx + 1] @@ -37099,7 +38145,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -37107,61 +38153,81 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_122 - jmp .LBB6_123 -.LBB6_57: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_152 + jmp .LBB6_153 +.LBB6_69: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_61 -# %bb.58: - movsxd rax, r9d + je .LBB6_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 + test rax, rax + jle .LBB6_74 +# %bb.71: + movsxd rbx, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r11d, r11d + xor r12d, r12d .p2align 4, 0x90 -.LBB6_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rdx] - add rdx, 1 - cmp cl, byte ptr [rsi] - lea rsi, [rsi + 1] +.LBB6_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rdx + r12] + cmp cl, byte ptr [rsi + r12] sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx + sar rdi, 3 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r15, r8 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB6_59 -# %bb.60: - add r14, 1 -.LBB6_61: - sar r15, 5 - cmp r11, 32 - jl .LBB6_65 -# %bb.62: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl eax, cl + xor r10b, r14b + and al, r10b + xor al, r14b + mov byte ptr [r8 + rdi], al + add r12, 1 + add rbx, 1 + add r11, -1 + cmp r9, r11 + jne .LBB6_72 +# %bb.73: + sub rsi, r11 + sub rdx, r11 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB6_74: + sub r13, rax + je .LBB6_153 +# %bb.75: + add r15, 1 +.LBB6_76: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_80 +# %bb.77: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] @@ -37183,9 +38249,9 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsi + 6] cmp al, byte ptr [rdx + 6] movzx eax, byte ptr [rsi + 7] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp al, byte ptr [rdx + 7] - seta r15b + seta r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] movzx eax, byte ptr [rsi + 9] @@ -37215,11 +38281,11 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsi + 17] seta byte ptr [rsp + 12] # 1-byte Folded Spill cmp al, byte ptr [rdx + 17] - seta r12b + seta r15b movzx eax, byte ptr [rsi + 18] cmp al, byte ptr [rdx + 18] movzx eax, byte ptr [rsi + 19] - seta r14b + seta r12b cmp al, byte ptr [rdx + 19] seta byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 20] @@ -37262,10 +38328,10 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 add r13b, r13b add r13b, byte ptr [rsp + 4] # 1-byte Folded Reload mov eax, r13d - movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 48] # 1-byte Folded Reload shl r13b, 6 - shl r15b, 7 - or r15b, r13b + shl r14b, 7 + or r14b, r13b movzx r13d, byte ptr [rsp + 20] # 1-byte Folded Reload shl r13b, 2 or r13b, al @@ -37295,28 +38361,28 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl r9b, 6 shl bl, 7 or bl, r9b - or r15b, cl + or r14b, cl or bl, al - add r12b, r12b - add r12b, byte ptr [rsp + 12] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r12b + add r15b, r15b + add r15b, byte ptr [rsp + 12] # 1-byte Folded Reload + shl r12b, 2 + or r12b, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 - or al, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or al, r12b movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload shl cl, 4 or cl, al movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 10] # 1-byte Folded Reload shl cl, 6 shl r8b, 7 or r8b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r8b, al movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload add al, al @@ -37339,31 +38405,30 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl dil, 7 or dil, al or dil, cl - mov byte ptr [r14 + 2], r8b - mov byte ptr [r14 + 3], dil + mov byte ptr [r15 + 2], r8b + mov byte ptr [r15 + 3], dil add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_63 -# %bb.64: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_65: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.66: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_78 +# %bb.79: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_80: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.81: xor ecx, ecx .p2align 4, 0x90 -.LBB6_67: # =>This Inner Loop Header: Depth=1 +.LBB6_82: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rdx + rcx] cmp bl, byte ptr [rsi + rcx] sbb edi, edi mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -37371,68 +38436,83 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_67 - jmp .LBB6_123 -.LBB6_90: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_82 + jmp .LBB6_153 +.LBB6_111: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_94 -# %bb.91: - movsxd rax, r9d + je .LBB6_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setg r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setg r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_92 -# %bb.93: - add r14, 1 -.LBB6_94: - sar r15, 5 - cmp r11, 32 - jl .LBB6_98 -# %bb.95: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB6_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB6_116: + sub r13, r8 + je .LBB6_153 +# %bb.117: + add r15, 1 +.LBB6_118: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_122 +# %bb.119: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] setg byte ptr [rsp + 20] # 1-byte Folded Spill @@ -37456,7 +38536,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 9] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - setg r8b + setg dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] setg r11b @@ -37496,7 +38576,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 11] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - setg byte ptr [rsp + 12] # 1-byte Folded Spill + setg byte ptr [rsp + 14] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] setg r9b @@ -37505,10 +38585,10 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 19] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - setg byte ptr [rsp + 13] # 1-byte Folded Spill + setg byte ptr [rsp + 12] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - setg byte ptr [rsp + 14] # 1-byte Folded Spill + setg byte ptr [rsp + 13] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] setg byte ptr [rsp + 15] # 1-byte Folded Spill @@ -37523,10 +38603,10 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 setg byte ptr [rsp + 17] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] - setg dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setg r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -37535,34 +38615,34 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -37575,22 +38655,23 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -37607,27 +38688,26 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB6_96 -# %bb.97: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB6_98: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.99: - sub r11, r15 + jne .LBB6_120 +# %bb.121: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB6_122: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.123: xor ecx, ecx .p2align 4, 0x90 -.LBB6_100: # =>This Inner Loop Header: Depth=1 +.LBB6_124: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -37635,7 +38715,7 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -37643,11 +38723,11 @@ comparison_greater_arr_arr_avx2: # @comparison_greater_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_100 -.LBB6_123: + cmp r13, r8 + jne .LBB6_124 +.LBB6_153: lea rsp, [rbp - 40] pop rbx pop r12 @@ -37691,91 +38771,104 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 and rsp, -32 sub rsp, 1344 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov r11, rcx + mov r15, r8 + mov r14, rcx cmp edi, 6 - jg .LBB7_19 + jg .LBB7_24 # %bb.1: cmp edi, 3 jle .LBB7_2 -# %bb.10: +# %bb.6: cmp edi, 4 - je .LBB7_84 -# %bb.11: + je .LBB7_112 +# %bb.7: cmp edi, 5 - je .LBB7_102 -# %bb.12: + je .LBB7_130 +# %bb.8: cmp edi, 6 - jne .LBB7_191 -# %bb.13: + jne .LBB7_210 +# %bb.9: mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_17 -# %bb.14: - movsxd rax, r9d + je .LBB7_15 +# %bb.10: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_13 +# %bb.11: + movsxd rdx, r9d + mov rax, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_15: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rsi] - lea rsi, [rsi + 4] - sbb edx, edx - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB7_12: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp r13d, dword ptr [rcx] + sbb r11d, r11d + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_15 + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add rdx, 1 + mov rcx, rsi + add rax, -1 + jne .LBB7_12 +.LBB7_13: + sub r15, r8 + je .LBB7_210 +# %bb.14: + add r14, 1 +.LBB7_15: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_19 # %bb.16: - add r11, 1 -.LBB7_17: - sar r15, 5 - cmp r10, 32 - jl .LBB7_18 -# %bb.119: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_120: # =>This Inner Loop Header: Depth=1 +.LBB7_17: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill cmp dword ptr [rsi], r13d - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta byte ptr [rsp + 136] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d seta dil cmp dword ptr [rsi + 8], r13d seta r14b cmp dword ptr [rsi + 12], r13d - seta byte ptr [rsp + 128] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp dword ptr [rsi + 16], r13d - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d seta al cmp dword ptr [rsi + 28], r13d seta bl cmp dword ptr [rsi + 32], r13d - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d - seta dl + seta cl cmp dword ptr [rsi + 40], r13d seta r9b cmp dword ptr [rsi + 44], r13d @@ -37785,33 +38878,33 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp dword ptr [rsi + 52], r13d seta r12b cmp dword ptr [rsi + 56], r13d - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - seta cl + seta dl cmp dword ptr [rsi + 64], r13d seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp dword ptr [rsi + 68], r13d - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp dword ptr [rsi + 72], r13d - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp dword ptr [rsi + 88], r13d - seta byte ptr [rsp + 24] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d seta r15b cmp dword ptr [rsi + 96], r13d seta byte ptr [rsp + 320] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp dword ptr [rsi + 104], r13d seta byte ptr [rsp + 16] # 1-byte Folded Spill cmp dword ptr [rsi + 108], r13d - seta byte ptr [rsp + 8] # 1-byte Folded Spill + seta byte ptr [rsp + 24] # 1-byte Folded Spill cmp dword ptr [rsi + 112], r13d seta byte ptr [rsp + 288] # 1-byte Folded Spill cmp dword ptr [rsi + 116], r13d @@ -37821,174 +38914,193 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp dword ptr [rsi + 124], r13d seta r8b add dil, dil - add dil, byte ptr [rsp + 120] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, dil - add dl, dl - add dl, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 or al, r14b + mov r14, qword ptr [rsp + 240] # 8-byte Reload shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx + or r9b, cl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r10b, 3 or r10b, r9b - movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl dl, 5 - or dl, dil + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r11b, 4 or r11b, r10b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 96] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or bl, dl - or cl, r12b - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 64] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov edi, edx - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - mov byte ptr [rdx], bl - movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + or bl, cl + or dl, r12b + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rdx + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + mov byte ptr [r14 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 320] # 1-byte Folded Reload - mov ebx, ecx + mov edx, ecx movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload shl cl, 3 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload shl cl, 4 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl bl, 6 + or cl, dl + movzx edx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl dl, 6 shl r8b, 7 - or r8b, bl + or r8b, dl or r8b, cl - mov byte ptr [rdx + 2], r15b - mov byte ptr [rdx + 3], r8b + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], r8b add rsi, 128 - add rdx, 4 - mov qword ptr [rsp + 240], rdx # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB7_120 -# %bb.121: - mov r14, qword ptr [rsp + 240] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB7_123 - jmp .LBB7_191 + add r14, 4 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_17 +# %bb.18: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload .LBB7_19: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.20: + or rax, 1 + cmp r15, rax + jne .LBB7_148 +# %bb.21: + xor r11d, r11d + jmp .LBB7_22 +.LBB7_24: cmp edi, 8 - jle .LBB7_20 -# %bb.28: + jle .LBB7_25 +# %bb.42: cmp edi, 9 - je .LBB7_155 -# %bb.29: + je .LBB7_169 +# %bb.43: cmp edi, 11 - je .LBB7_171 -# %bb.30: + je .LBB7_186 +# %bb.44: cmp edi, 12 - jne .LBB7_191 -# %bb.31: - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + jne .LBB7_210 +# %bb.45: + mov r12, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero sub r9d, eax - je .LBB7_35 -# %bb.32: - movsxd rax, r9d + je .LBB7_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_49 +# %bb.47: + movsxd rdx, r9d + vmovq xmm0, r12 + mov r11, r8 .p2align 4, 0x90 -.LBB7_33: # =>This Inner Loop Header: Depth=1 +.LBB7_48: # =>This Inner Loop Header: Depth=1 vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero add rsi, 8 vucomisd xmm1, xmm0 - seta dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + seta bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_33 -# %bb.34: - add r11, 1 -.LBB7_35: - sar r14, 5 - cmp r10, 32 - jl .LBB7_39 -# %bb.36: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 136], r14 # 8-byte Spill - mov qword ptr [rsp + 120], r14 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + add r11, -1 + jne .LBB7_48 +.LBB7_49: + sub r15, r8 + je .LBB7_210 +# %bb.50: + add r14, 1 +.LBB7_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_55 +# %bb.52: + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 128], r12 # 8-byte Spill + vmovq xmm0, r12 + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_37: # =>This Inner Loop Header: Depth=1 +.LBB7_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero vmovsd xmm2, qword ptr [rsi + 8] # xmm2 = mem[0],zero vucomisd xmm1, xmm0 seta byte ptr [rsp + 288] # 1-byte Folded Spill vucomisd xmm2, xmm0 - seta bl + seta dl vmovsd xmm1, qword ptr [rsi + 16] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 24] # xmm1 = mem[0],zero @@ -37998,15 +39110,15 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vmovsd xmm1, qword ptr [rsi + 32] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 40] # xmm1 = mem[0],zero - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill vucomisd xmm1, xmm0 - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 48] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 56] # xmm1 = mem[0],zero - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 32] # 1-byte Folded Spill vucomisd xmm1, xmm0 - seta byte ptr [rsp + 24] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 64] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 72] # xmm1 = mem[0],zero @@ -38016,7 +39128,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vmovsd xmm1, qword ptr [rsi + 80] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 88] # xmm1 = mem[0],zero - seta byte ptr [rsp + 16] # 1-byte Folded Spill + seta byte ptr [rsp + 8] # 1-byte Folded Spill vucomisd xmm1, xmm0 seta byte ptr [rsp + 320] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 96] # xmm1 = mem[0],zero @@ -38024,19 +39136,19 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vucomisd xmm1, xmm0 vmovsd xmm5, qword ptr [rsi + 112] # xmm5 = mem[0],zero vmovsd xmm6, qword ptr [rsi + 120] # xmm6 = mem[0],zero - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill vmovsd xmm8, qword ptr [rsi + 128] # xmm8 = mem[0],zero vmovsd xmm9, qword ptr [rsi + 136] # xmm9 = mem[0],zero vucomisd xmm3, xmm0 vmovsd xmm10, qword ptr [rsi + 144] # xmm10 = mem[0],zero vmovsd xmm11, qword ptr [rsi + 152] # xmm11 = mem[0],zero - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill vmovsd xmm12, qword ptr [rsi + 160] # xmm12 = mem[0],zero vmovsd xmm13, qword ptr [rsi + 168] # xmm13 = mem[0],zero vucomisd xmm5, xmm0 vmovsd xmm14, qword ptr [rsi + 176] # xmm14 = mem[0],zero vmovsd xmm2, qword ptr [rsi + 184] # xmm2 = mem[0],zero - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill vmovsd xmm3, qword ptr [rsi + 192] # xmm3 = mem[0],zero vmovsd xmm4, qword ptr [rsi + 200] # xmm4 = mem[0],zero vucomisd xmm6, xmm0 @@ -38046,7 +39158,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vmovsd xmm1, qword ptr [rsi + 224] # xmm1 = mem[0],zero vmovsd xmm5, qword ptr [rsi + 232] # xmm5 = mem[0],zero vucomisd xmm8, xmm0 - seta byte ptr [rsp + 128] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill vucomisd xmm9, xmm0 seta cl vucomisd xmm10, xmm0 @@ -38058,68 +39170,68 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vucomisd xmm13, xmm0 seta r14b vucomisd xmm14, xmm0 - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill vucomisd xmm2, xmm0 seta r9b vucomisd xmm3, xmm0 - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill vucomisd xmm4, xmm0 seta r15b vucomisd xmm6, xmm0 - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill vucomisd xmm7, xmm0 seta byte ptr [rsp + 64] # 1-byte Folded Spill vucomisd xmm1, xmm0 - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill vucomisd xmm5, xmm0 vmovsd xmm1, qword ptr [rsi + 240] # xmm1 = mem[0],zero - seta byte ptr [rsp + 8] # 1-byte Folded Spill + seta byte ptr [rsp + 24] # 1-byte Folded Spill vucomisd xmm1, xmm0 seta byte ptr [rsp + 4] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 248] # xmm1 = mem[0],zero add rsi, 256 vucomisd xmm1, xmm0 - seta dl - add bl, bl - add bl, byte ptr [rsp + 288] # 1-byte Folded Reload + seta bl + add dl, dl + add dl, byte ptr [rsp + 288] # 1-byte Folded Reload shl r13b, 2 - or r13b, bl + or r13b, dl shl r12b, 3 or r12b, r13b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl bl, 4 - or bl, r12b - mov r12d, ebx - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 5 - or bl, r12b - movzx r12d, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 4 + or dl, r12b + mov r12d, edx + movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl dl, 5 + or dl, r12b + movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload shl r12b, 6 - movzx r13d, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 48] # 1-byte Folded Reload shl r13b, 7 or r13b, r12b add al, al add al, byte ptr [rsp + 256] # 1-byte Folded Reload - movzx r12d, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 8] # 1-byte Folded Reload shl r12b, 2 or r12b, al mov eax, r12d movzx r12d, byte ptr [rsp + 320] # 1-byte Folded Reload shl r12b, 3 or r12b, al - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, r12b - or r13b, bl - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 5 - or bl, al - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or r13b, dl + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dl, 5 + or dl, al + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al add cl, cl - add cl, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, byte ptr [rsp + 80] # 1-byte Folded Reload shl dil, 2 or dil, cl shl r8b, 3 @@ -38128,8 +39240,8 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 or r10b, r8b shl r14b, 5 or r14b, r10b - or r11b, bl - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + or r11b, dl + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl r9b, 7 or r9b, al @@ -38137,369 +39249,192 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 mov byte ptr [rax], r13b or r9b, r14b add r15b, r15b - add r15b, byte ptr [rsp + 88] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl cl, 2 - or cl, r15b - mov ebx, ecx - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - mov byte ptr [rax + 1], r11b - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - mov byte ptr [rax + 2], r9b - or dl, cl - mov byte ptr [rax + 3], dl - add rax, 4 - mov qword ptr [rsp + 240], rax # 8-byte Spill - add qword ptr [rsp + 120], -1 # 8-byte Folded Spill - jne .LBB7_37 -# %bb.38: - mov r11, qword ptr [rsp + 240] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14, qword ptr [rsp + 136] # 8-byte Reload -.LBB7_39: - shl r14, 5 - cmp r14, r10 - jge .LBB7_191 -# %bb.40: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB7_186 -# %bb.41: + add r15b, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, r15b + mov ecx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + mov r14, qword ptr [rsp + 240] # 8-byte Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov byte ptr [r14 + 1], r11b + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + mov byte ptr [r14 + 2], r9b + or bl, al + mov byte ptr [r14 + 3], bl + add r14, 4 + add qword ptr [rsp + 136], -1 # 8-byte Folded Spill + jne .LBB7_53 +# %bb.54: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov r12, qword ptr [rsp + 128] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB7_55: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.56: + vmovq xmm0, r12 + or rax, 1 + cmp r15, rax + jne .LBB7_203 +# %bb.57: xor r10d, r10d - jmp .LBB7_188 + jmp .LBB7_205 .LBB7_2: cmp edi, 2 - je .LBB7_42 + je .LBB7_58 # %bb.3: cmp edi, 3 - jne .LBB7_191 + jne .LBB7_210 # %bb.4: - mov r14b, byte ptr [rdx] - lea r13, [r10 + 31] - test r10, r10 - mov r15, r10 - cmovns r13, r10 + mov r13b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_8 -# %bb.5: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB7_6: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r14b - lea rsi, [rsi + 1] - setg dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_6 -# %bb.7: - add r11, 1 -.LBB7_8: - sar r13, 5 - cmp r15, 32 - jl .LBB7_9 -# %bb.66: - cmp r13, 32 - mov dword ptr [rsp + 4], r14d # 4-byte Spill - mov qword ptr [rsp + 248], r15 # 8-byte Spill - mov qword ptr [rsp + 360], r13 # 8-byte Spill - jb .LBB7_67 -# %bb.68: - mov rax, r13 - shl rax, 5 - add rax, rsi - cmp r11, rax - jae .LBB7_70 -# %bb.69: - lea rax, [r11 + 4*r13] - cmp rsi, rax - jae .LBB7_70 -.LBB7_67: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 352], r11 # 8-byte Spill -.LBB7_73: - sub r13, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 120], r13 # 8-byte Spill + je .LBB7_5 +# %bb.86: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_87 +# %bb.92: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB7_74: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b - setg byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b - setg r8b - cmp byte ptr [r12 + 2], r14b - setg r15b - cmp byte ptr [r12 + 3], r14b - setg r13b - cmp byte ptr [r12 + 4], r14b - setg byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b - setg al - cmp byte ptr [r12 + 7], r14b - setg r11b - cmp byte ptr [r12 + 8], r14b - setg byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b - setg dl - cmp byte ptr [r12 + 10], r14b - setg sil - cmp byte ptr [r12 + 11], r14b - setg dil - cmp byte ptr [r12 + 12], r14b - setg r10b - cmp byte ptr [r12 + 13], r14b - setg r12b - cmp byte ptr [rcx + 14], r14b - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b - setg r9b - cmp byte ptr [rcx + 16], r14b - setg byte ptr [rsp + 256] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - setg r14b - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 24], bl - setg byte ptr [rsp + 240] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 25], bl - setg byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 26], bl - setg byte ptr [rsp + 48] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 27], bl - setg byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 28], bl - setg byte ptr [rsp + 32] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 29], bl - setg byte ptr [rsp + 16] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 30], bl - setg byte ptr [rsp + 8] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 4] # 4-byte Reload - cmp byte ptr [rcx + 31], bl +.LBB7_93: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r13b setg bl - add r8b, r8b - add r8b, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, r8b - add dl, dl - add dl, byte ptr [rsp + 288] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b - shl sil, 2 - or sil, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - shl dil, 3 - or dil, sil - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, dil - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload - shl sil, 6 - shl r9b, 7 - or r9b, sil - or r11b, dl - or r9b, r12b - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 256] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov rsi, qword ptr [rsp + 352] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 24] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 240] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl dl, 6 - shl bl, 7 - or bl, dl - or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 4] # 4-byte Reload - mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 352], rsi # 8-byte Spill - add qword ptr [rsp + 120], -1 # 8-byte Folded Spill - jne .LBB7_74 -# %bb.75: - mov r15, qword ptr [rsp + 248] # 8-byte Reload - mov r13, qword ptr [rsp + 360] # 8-byte Reload - jmp .LBB7_76 -.LBB7_20: + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + movzx r9d, byte ptr [r14 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB7_93 +# %bb.88: + sub r15, r8 + jne .LBB7_89 + jmp .LBB7_210 +.LBB7_25: cmp edi, 7 - je .LBB7_129 -# %bb.21: + je .LBB7_150 +# %bb.26: cmp edi, 8 - jne .LBB7_191 -# %bb.22: + jne .LBB7_210 +# %bb.27: mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_26 -# %bb.23: - movsxd rax, r9d + je .LBB7_33 +# %bb.28: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_31 +# %bb.29: + movsxd rdx, r9d + mov rax, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_24: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rsi] - lea rsi, [rsi + 8] - sbb edx, edx - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB7_30: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp r13, qword ptr [rcx] + sbb r11d, r11d + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_24 -# %bb.25: - add r11, 1 -.LBB7_26: - sar r15, 5 - cmp r10, 32 - jl .LBB7_27 -# %bb.145: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add rdx, 1 + mov rcx, rsi + add rax, -1 + jne .LBB7_30 +.LBB7_31: + sub r15, r8 + je .LBB7_210 +# %bb.32: + add r14, 1 +.LBB7_33: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_37 +# %bb.34: + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_146: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 240], r11 # 8-byte Spill +.LBB7_35: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill cmp qword ptr [rsi], r13 - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta byte ptr [rsp + 136] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 seta dil cmp qword ptr [rsi + 16], r13 seta r14b cmp qword ptr [rsi + 24], r13 - seta byte ptr [rsp + 128] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 32], r13 - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp qword ptr [rsi + 40], r13 - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 48], r13 seta al cmp qword ptr [rsi + 56], r13 seta bl cmp qword ptr [rsi + 64], r13 - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 - seta dl + seta cl cmp qword ptr [rsi + 80], r13 seta r9b cmp qword ptr [rsi + 88], r13 @@ -38509,33 +39444,33 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp qword ptr [rsi + 104], r13 seta r12b cmp qword ptr [rsi + 112], r13 - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - seta cl + seta dl cmp qword ptr [rsi + 128], r13 seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - seta byte ptr [rsp + 24] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 seta r15b cmp qword ptr [rsi + 192], r13 seta byte ptr [rsp + 320] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 seta byte ptr [rsp + 16] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - seta byte ptr [rsp + 8] # 1-byte Folded Spill + seta byte ptr [rsp + 24] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 seta byte ptr [rsp + 288] # 1-byte Folded Spill cmp qword ptr [rsi + 232], r13 @@ -38545,66 +39480,66 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp qword ptr [rsi + 248], r13 seta r8b add dil, dil - add dil, byte ptr [rsp + 120] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, dil - add dl, dl - add dl, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 or al, r14b + mov r14, qword ptr [rsp + 240] # 8-byte Reload shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx + or r9b, cl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r10b, 3 or r10b, r9b - movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl dl, 5 - or dl, dil + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r11b, 4 or r11b, r10b shl r12b, 5 or r12b, r11b - mov r11, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 96] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or bl, dl - or cl, r12b - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 64] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + or bl, cl + or dl, r12b + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r11 + 1], cl - or r15b, dl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + mov byte ptr [r14 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 320] # 1-byte Folded Reload mov edx, ecx @@ -38612,7 +39547,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl cl, 2 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload shl cl, 3 or cl, dl mov edx, ecx @@ -38628,89 +39563,109 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl r8b, 7 or r8b, dl or r8b, cl - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], r8b + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], r8b add rsi, 256 - add r11, 4 - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB7_146 -# %bb.147: - mov r14, r11 - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB7_149 - jmp .LBB7_191 -.LBB7_84: + add r14, 4 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_35 +# %bb.36: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB7_37: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.38: + or rax, 1 + cmp r15, rax + jne .LBB7_167 +# %bb.39: + xor r11d, r11d + jmp .LBB7_40 +.LBB7_112: movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_88 -# %bb.85: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB7_86: # =>This Inner Loop Header: Depth=1 - cmp r13w, word ptr [rsi] - lea rsi, [rsi + 2] - sbb edx, edx - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 + je .LBB7_118 +# %bb.113: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_116 +# %bb.114: + movsxd rdx, r9d + mov rax, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB7_115: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp r13w, word ptr [rcx] + sbb r11d, r11d + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_86 -# %bb.87: - add r11, 1 -.LBB7_88: - sar r15, 5 - cmp r10, 32 - jl .LBB7_89 -# %bb.90: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add rdx, 1 + mov rcx, rsi + add rax, -1 + jne .LBB7_115 +.LBB7_116: + sub r15, r8 + je .LBB7_210 +# %bb.117: + add r14, 1 +.LBB7_118: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_122 +# %bb.119: + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_91: # =>This Inner Loop Header: Depth=1 +.LBB7_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill cmp word ptr [rsi], r13w - seta al + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 2], r13w seta dil cmp word ptr [rsi + 4], r13w seta r14b cmp word ptr [rsi + 6], r13w - seta byte ptr [rsp + 128] # 1-byte Folded Spill + seta byte ptr [rsp + 136] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta al cmp word ptr [rsi + 14], r13w seta bl cmp word ptr [rsi + 16], r13w - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w - seta dl + seta cl cmp word ptr [rsi + 20], r13w seta r9b cmp word ptr [rsi + 22], r13w @@ -38720,33 +39675,33 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp word ptr [rsi + 26], r13w seta r12b cmp word ptr [rsi + 28], r13w - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - seta cl + seta dl cmp word ptr [rsi + 32], r13w seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [rsi + 36], r13w - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp word ptr [rsi + 44], r13w - seta byte ptr [rsp + 24] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w seta r15b cmp word ptr [rsi + 48], r13w seta byte ptr [rsp + 320] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp word ptr [rsi + 52], r13w seta byte ptr [rsp + 16] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w - seta byte ptr [rsp + 8] # 1-byte Folded Spill + seta byte ptr [rsp + 24] # 1-byte Folded Spill cmp word ptr [rsi + 56], r13w seta byte ptr [rsp + 288] # 1-byte Folded Spill cmp word ptr [rsi + 58], r13w @@ -38756,176 +39711,193 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp word ptr [rsi + 62], r13w seta r8b add dil, dil - or dil, al - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + add dil, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, dil - add dl, dl - add dl, byte ptr [rsp + 72] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b + mov r14, qword ptr [rsp + 240] # 8-byte Reload shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx + or r9b, cl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r10b, 3 or r10b, r9b - movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl dl, 5 - or dl, dil + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r11b, 4 or r11b, r10b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 96] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or bl, dl - or cl, r12b - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 64] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov edi, edx - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - mov byte ptr [rdx], bl - movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + or bl, cl + or dl, r12b + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rdx + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + mov byte ptr [r14 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 320] # 1-byte Folded Reload - mov ebx, ecx + mov edx, ecx movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload shl cl, 3 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload shl cl, 4 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl bl, 6 + or cl, dl + movzx edx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl dl, 6 shl r8b, 7 - or r8b, bl + or r8b, dl or r8b, cl - mov byte ptr [rdx + 2], r15b - mov byte ptr [rdx + 3], r8b + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], r8b add rsi, 64 - add rdx, 4 - mov qword ptr [rsp + 240], rdx # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB7_91 -# %bb.92: - mov r14, qword ptr [rsp + 240] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB7_94 - jmp .LBB7_191 -.LBB7_102: + add r14, 4 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_120 +# %bb.121: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB7_122: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.123: + or rax, 1 + cmp r15, rax + jne .LBB7_128 +# %bb.124: + xor r11d, r11d + jmp .LBB7_125 +.LBB7_130: movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_106 -# %bb.103: - movsxd rax, r9d + je .LBB7_136 +# %bb.131: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_134 +# %bb.132: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_104: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - setg dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB7_133: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + setg bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_104 -# %bb.105: - add r11, 1 -.LBB7_106: - sar r15, 5 - cmp r10, 32 - jl .LBB7_107 -# %bb.108: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB7_133 +.LBB7_134: + sub r15, r8 + je .LBB7_210 +# %bb.135: + add r14, 1 +.LBB7_136: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_140 +# %bb.137: + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_109: # =>This Inner Loop Header: Depth=1 +.LBB7_138: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill cmp word ptr [rsi], r13w - setg byte ptr [rsp + 120] # 1-byte Folded Spill + setg byte ptr [rsp + 136] # 1-byte Folded Spill cmp word ptr [rsi + 2], r13w setg dil cmp word ptr [rsi + 4], r13w setg r14b cmp word ptr [rsi + 6], r13w - setg byte ptr [rsp + 128] # 1-byte Folded Spill + setg byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - setg byte ptr [rsp + 88] # 1-byte Folded Spill + setg byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - setg byte ptr [rsp + 48] # 1-byte Folded Spill + setg byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w setg al cmp word ptr [rsi + 14], r13w setg bl cmp word ptr [rsi + 16], r13w - setg byte ptr [rsp + 104] # 1-byte Folded Spill + setg byte ptr [rsp + 88] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w - setg dl + setg cl cmp word ptr [rsi + 20], r13w setg r9b cmp word ptr [rsi + 22], r13w @@ -38935,33 +39907,33 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp word ptr [rsi + 26], r13w setg r12b cmp word ptr [rsi + 28], r13w - setg byte ptr [rsp + 112] # 1-byte Folded Spill + setg byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - setg cl + setg dl cmp word ptr [rsi + 32], r13w setg byte ptr [rsp + 64] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w - setg byte ptr [rsp + 72] # 1-byte Folded Spill + setg byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [rsi + 36], r13w - setg byte ptr [rsp + 80] # 1-byte Folded Spill + setg byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - setg byte ptr [rsp + 96] # 1-byte Folded Spill + setg byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - setg byte ptr [rsp + 56] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill cmp word ptr [rsi + 44], r13w - setg byte ptr [rsp + 24] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w setg r15b cmp word ptr [rsi + 48], r13w setg byte ptr [rsp + 320] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 8] # 1-byte Folded Spill cmp word ptr [rsi + 52], r13w setg byte ptr [rsp + 16] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w - setg byte ptr [rsp + 8] # 1-byte Folded Spill + setg byte ptr [rsp + 24] # 1-byte Folded Spill cmp word ptr [rsi + 56], r13w setg byte ptr [rsp + 288] # 1-byte Folded Spill cmp word ptr [rsi + 58], r13w @@ -38971,175 +39943,193 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp word ptr [rsi + 62], r13w setg r8b add dil, dil - add dil, byte ptr [rsp + 120] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, dil - add dl, dl - add dl, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 or al, r14b + mov r14, qword ptr [rsp + 240] # 8-byte Reload shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx + or r9b, cl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r10b, 3 or r10b, r9b - movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl dl, 5 - or dl, dil + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r11b, 4 or r11b, r10b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 96] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or bl, dl - or cl, r12b - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 64] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov edi, edx - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - mov byte ptr [rdx], bl - movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + or bl, cl + or dl, r12b + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rdx + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + mov byte ptr [r14 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 320] # 1-byte Folded Reload - mov ebx, ecx + mov edx, ecx movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload shl cl, 3 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload shl cl, 4 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl bl, 6 + or cl, dl + movzx edx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl dl, 6 shl r8b, 7 - or r8b, bl + or r8b, dl or r8b, cl - mov byte ptr [rdx + 2], r15b - mov byte ptr [rdx + 3], r8b + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], r8b add rsi, 64 - add rdx, 4 - mov qword ptr [rsp + 240], rdx # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB7_109 -# %bb.110: - mov r14, qword ptr [rsp + 240] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB7_112 - jmp .LBB7_191 -.LBB7_155: + add r14, 4 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_138 +# %bb.139: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB7_140: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.141: + or rax, 1 + cmp r15, rax + jne .LBB7_146 +# %bb.142: + xor r11d, r11d + jmp .LBB7_143 +.LBB7_169: mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_159 -# %bb.156: - movsxd rax, r9d + je .LBB7_175 +# %bb.170: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_173 +# %bb.171: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_157: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setg dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB7_172: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + setg bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_157 -# %bb.158: - add r11, 1 -.LBB7_159: - sar r15, 5 - cmp r10, 32 - jl .LBB7_160 -# %bb.161: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB7_172 +.LBB7_173: + sub r15, r8 + je .LBB7_210 +# %bb.174: + add r14, 1 +.LBB7_175: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_179 +# %bb.176: + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_162: # =>This Inner Loop Header: Depth=1 +.LBB7_177: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill cmp qword ptr [rsi], r13 - setg byte ptr [rsp + 120] # 1-byte Folded Spill + setg byte ptr [rsp + 136] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 setg dil cmp qword ptr [rsi + 16], r13 setg r14b cmp qword ptr [rsi + 24], r13 - setg byte ptr [rsp + 128] # 1-byte Folded Spill + setg byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 32], r13 - setg byte ptr [rsp + 88] # 1-byte Folded Spill + setg byte ptr [rsp + 120] # 1-byte Folded Spill cmp qword ptr [rsi + 40], r13 - setg byte ptr [rsp + 48] # 1-byte Folded Spill + setg byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 48], r13 setg al cmp qword ptr [rsi + 56], r13 setg bl cmp qword ptr [rsi + 64], r13 - setg byte ptr [rsp + 104] # 1-byte Folded Spill + setg byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 - setg dl + setg cl cmp qword ptr [rsi + 80], r13 setg r9b cmp qword ptr [rsi + 88], r13 @@ -39149,33 +40139,33 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp qword ptr [rsi + 104], r13 setg r12b cmp qword ptr [rsi + 112], r13 - setg byte ptr [rsp + 112] # 1-byte Folded Spill + setg byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - setg cl + setg dl cmp qword ptr [rsi + 128], r13 setg byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - setg byte ptr [rsp + 72] # 1-byte Folded Spill + setg byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - setg byte ptr [rsp + 80] # 1-byte Folded Spill + setg byte ptr [rsp + 112] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - setg byte ptr [rsp + 96] # 1-byte Folded Spill + setg byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - setg byte ptr [rsp + 56] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - setg byte ptr [rsp + 24] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 setg r15b cmp qword ptr [rsi + 192], r13 setg byte ptr [rsp + 320] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 8] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 setg byte ptr [rsp + 16] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - setg byte ptr [rsp + 8] # 1-byte Folded Spill + setg byte ptr [rsp + 24] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 setg byte ptr [rsp + 288] # 1-byte Folded Spill cmp qword ptr [rsi + 232], r13 @@ -39185,162 +40175,181 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 cmp qword ptr [rsi + 248], r13 setg r8b add dil, dil - add dil, byte ptr [rsp + 120] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, dil - add dl, dl - add dl, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 or al, r14b + mov r14, qword ptr [rsp + 240] # 8-byte Reload shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx + or r9b, cl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r10b, 3 or r10b, r9b - movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl dl, 5 - or dl, dil + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r11b, 4 or r11b, r10b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 96] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or bl, dl - or cl, r12b - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 64] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov edi, edx - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - mov byte ptr [rdx], bl - movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + or bl, cl + or dl, r12b + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rdx + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + mov byte ptr [r14 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 320] # 1-byte Folded Reload - mov ebx, ecx + mov edx, ecx movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload shl cl, 3 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload shl cl, 4 - or cl, bl - mov ebx, ecx + or cl, dl + mov edx, ecx movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl bl, 6 + or cl, dl + movzx edx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl dl, 6 shl r8b, 7 - or r8b, bl + or r8b, dl or r8b, cl - mov byte ptr [rdx + 2], r15b - mov byte ptr [rdx + 3], r8b + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], r8b add rsi, 256 - add rdx, 4 - mov qword ptr [rsp + 240], rdx # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB7_162 -# %bb.163: - mov r14, qword ptr [rsp + 240] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB7_165 - jmp .LBB7_191 -.LBB7_171: - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + add r14, 4 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_177 +# %bb.178: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB7_179: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.180: + or rax, 1 + cmp r15, rax + jne .LBB7_184 +# %bb.181: + xor r11d, r11d + jmp .LBB7_182 +.LBB7_186: + mov r12d, dword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB7_175 -# %bb.172: - movsxd rax, r9d + je .LBB7_192 +# %bb.187: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_190 +# %bb.188: + movsxd rdx, r9d + vmovd xmm0, r12d + mov r11, r8 .p2align 4, 0x90 -.LBB7_173: # =>This Inner Loop Header: Depth=1 +.LBB7_189: # =>This Inner Loop Header: Depth=1 vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero add rsi, 4 vucomiss xmm1, xmm0 - seta dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + seta bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_173 -# %bb.174: - add r11, 1 -.LBB7_175: - sar r14, 5 - cmp r10, 32 - jl .LBB7_179 -# %bb.176: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 136], r14 # 8-byte Spill - mov qword ptr [rsp + 120], r14 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + add r11, -1 + jne .LBB7_189 +.LBB7_190: + sub r15, r8 + je .LBB7_210 +# %bb.191: + add r14, 1 +.LBB7_192: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_196 +# %bb.193: + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov dword ptr [rsp + 128], r12d # 4-byte Spill + vmovd xmm0, r12d + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_177: # =>This Inner Loop Header: Depth=1 +.LBB7_194: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero vmovss xmm2, dword ptr [rsi + 4] # xmm2 = mem[0],zero,zero,zero vucomiss xmm1, xmm0 seta byte ptr [rsp + 288] # 1-byte Folded Spill vucomiss xmm2, xmm0 - seta bl + seta dl vmovss xmm1, dword ptr [rsi + 8] # xmm1 = mem[0],zero,zero,zero vucomiss xmm1, xmm0 vmovss xmm1, dword ptr [rsi + 12] # xmm1 = mem[0],zero,zero,zero @@ -39350,15 +40359,15 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vmovss xmm1, dword ptr [rsi + 16] # xmm1 = mem[0],zero,zero,zero vucomiss xmm1, xmm0 vmovss xmm1, dword ptr [rsi + 20] # xmm1 = mem[0],zero,zero,zero - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill vucomiss xmm1, xmm0 - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill vmovss xmm1, dword ptr [rsi + 24] # xmm1 = mem[0],zero,zero,zero vucomiss xmm1, xmm0 vmovss xmm1, dword ptr [rsi + 28] # xmm1 = mem[0],zero,zero,zero - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 32] # 1-byte Folded Spill vucomiss xmm1, xmm0 - seta byte ptr [rsp + 24] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill vmovss xmm1, dword ptr [rsi + 32] # xmm1 = mem[0],zero,zero,zero vucomiss xmm1, xmm0 vmovss xmm1, dword ptr [rsi + 36] # xmm1 = mem[0],zero,zero,zero @@ -39368,7 +40377,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vmovss xmm1, dword ptr [rsi + 40] # xmm1 = mem[0],zero,zero,zero vucomiss xmm1, xmm0 vmovss xmm1, dword ptr [rsi + 44] # xmm1 = mem[0],zero,zero,zero - seta byte ptr [rsp + 16] # 1-byte Folded Spill + seta byte ptr [rsp + 8] # 1-byte Folded Spill vucomiss xmm1, xmm0 seta byte ptr [rsp + 320] # 1-byte Folded Spill vmovss xmm1, dword ptr [rsi + 48] # xmm1 = mem[0],zero,zero,zero @@ -39376,19 +40385,19 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vucomiss xmm1, xmm0 vmovss xmm5, dword ptr [rsi + 56] # xmm5 = mem[0],zero,zero,zero vmovss xmm6, dword ptr [rsi + 60] # xmm6 = mem[0],zero,zero,zero - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill vmovss xmm8, dword ptr [rsi + 64] # xmm8 = mem[0],zero,zero,zero vmovss xmm9, dword ptr [rsi + 68] # xmm9 = mem[0],zero,zero,zero vucomiss xmm3, xmm0 vmovss xmm10, dword ptr [rsi + 72] # xmm10 = mem[0],zero,zero,zero vmovss xmm11, dword ptr [rsi + 76] # xmm11 = mem[0],zero,zero,zero - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill vmovss xmm12, dword ptr [rsi + 80] # xmm12 = mem[0],zero,zero,zero vmovss xmm13, dword ptr [rsi + 84] # xmm13 = mem[0],zero,zero,zero vucomiss xmm5, xmm0 vmovss xmm14, dword ptr [rsi + 88] # xmm14 = mem[0],zero,zero,zero vmovss xmm2, dword ptr [rsi + 92] # xmm2 = mem[0],zero,zero,zero - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill vmovss xmm3, dword ptr [rsi + 96] # xmm3 = mem[0],zero,zero,zero vmovss xmm4, dword ptr [rsi + 100] # xmm4 = mem[0],zero,zero,zero vucomiss xmm6, xmm0 @@ -39398,7 +40407,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vmovss xmm1, dword ptr [rsi + 112] # xmm1 = mem[0],zero,zero,zero vmovss xmm5, dword ptr [rsi + 116] # xmm5 = mem[0],zero,zero,zero vucomiss xmm8, xmm0 - seta byte ptr [rsp + 128] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill vucomiss xmm9, xmm0 seta cl vucomiss xmm10, xmm0 @@ -39410,68 +40419,68 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vucomiss xmm13, xmm0 seta r14b vucomiss xmm14, xmm0 - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill vucomiss xmm2, xmm0 seta r9b vucomiss xmm3, xmm0 - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill vucomiss xmm4, xmm0 seta r15b vucomiss xmm6, xmm0 - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill vucomiss xmm7, xmm0 seta byte ptr [rsp + 64] # 1-byte Folded Spill vucomiss xmm1, xmm0 - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill vucomiss xmm5, xmm0 vmovss xmm1, dword ptr [rsi + 120] # xmm1 = mem[0],zero,zero,zero - seta byte ptr [rsp + 8] # 1-byte Folded Spill + seta byte ptr [rsp + 24] # 1-byte Folded Spill vucomiss xmm1, xmm0 seta byte ptr [rsp + 4] # 1-byte Folded Spill vmovss xmm1, dword ptr [rsi + 124] # xmm1 = mem[0],zero,zero,zero sub rsi, -128 vucomiss xmm1, xmm0 - seta dl - add bl, bl - add bl, byte ptr [rsp + 288] # 1-byte Folded Reload + seta bl + add dl, dl + add dl, byte ptr [rsp + 288] # 1-byte Folded Reload shl r13b, 2 - or r13b, bl + or r13b, dl shl r12b, 3 or r12b, r13b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl bl, 4 - or bl, r12b - mov r12d, ebx - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 5 - or bl, r12b - movzx r12d, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 4 + or dl, r12b + mov r12d, edx + movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl dl, 5 + or dl, r12b + movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload shl r12b, 6 - movzx r13d, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 48] # 1-byte Folded Reload shl r13b, 7 or r13b, r12b add al, al add al, byte ptr [rsp + 256] # 1-byte Folded Reload - movzx r12d, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 8] # 1-byte Folded Reload shl r12b, 2 or r12b, al mov eax, r12d movzx r12d, byte ptr [rsp + 320] # 1-byte Folded Reload shl r12b, 3 or r12b, al - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 or al, r12b - or r13b, bl - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 5 - or bl, al - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or r13b, dl + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dl, 5 + or dl, al + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al add cl, cl - add cl, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, byte ptr [rsp + 80] # 1-byte Folded Reload shl dil, 2 or dil, cl shl r8b, 3 @@ -39480,8 +40489,8 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 or r10b, r8b shl r14b, 5 or r14b, r10b - or r11b, bl - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + or r11b, dl + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl r9b, 7 or r9b, al @@ -39489,728 +40498,830 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 mov byte ptr [rax], r13b or r9b, r14b add r15b, r15b - add r15b, byte ptr [rsp + 88] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl cl, 2 - or cl, r15b - mov ebx, ecx - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - mov byte ptr [rax + 1], r11b - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - mov byte ptr [rax + 2], r9b - or dl, cl - mov byte ptr [rax + 3], dl - add rax, 4 - mov qword ptr [rsp + 240], rax # 8-byte Spill - add qword ptr [rsp + 120], -1 # 8-byte Folded Spill - jne .LBB7_177 -# %bb.178: - mov r11, qword ptr [rsp + 240] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14, qword ptr [rsp + 136] # 8-byte Reload -.LBB7_179: - shl r14, 5 - cmp r14, r10 - jge .LBB7_191 -# %bb.180: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB7_184 -# %bb.181: + add r15b, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, r15b + mov ecx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + mov r14, qword ptr [rsp + 240] # 8-byte Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov byte ptr [r14 + 1], r11b + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + mov byte ptr [r14 + 2], r9b + or bl, al + mov byte ptr [r14 + 3], bl + add r14, 4 + add qword ptr [rsp + 136], -1 # 8-byte Folded Spill + jne .LBB7_194 +# %bb.195: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov r12d, dword ptr [rsp + 128] # 4-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB7_196: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.197: + vmovd xmm0, r12d + or rax, 1 + cmp r15, rax + jne .LBB7_201 +# %bb.198: xor r10d, r10d - jmp .LBB7_182 -.LBB7_42: - mov r14b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jmp .LBB7_199 +.LBB7_58: + mov r13b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_46 -# %bb.43: - movsxd rax, r9d + je .LBB7_59 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_61 +# %bb.66: + movsxd rdx, r9d + mov rax, r8 .p2align 4, 0x90 -.LBB7_44: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rsi] - lea rsi, [rsi + 1] - sbb edx, edx - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 +.LBB7_67: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp r13b, byte ptr [rsi] + sbb r11d, r11d + lea rbx, [rdx + 7] + test rdx, rdx + cmovns rbx, rdx + sar rbx, 3 + movzx r9d, byte ptr [r14 + rbx] + xor r11b, r9b + lea r10d, [8*rbx] + mov ecx, edx + sub ecx, r10d + mov esi, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + shl esi, cl + and sil, r11b + xor sil, r9b + mov byte ptr [r14 + rbx], sil + add rdx, 1 + mov rsi, rdi + add rax, -1 + jne .LBB7_67 +# %bb.62: + sub r15, r8 + jne .LBB7_63 + jmp .LBB7_210 +.LBB7_150: + mov r13d, dword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB7_156 +# %bb.151: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_154 +# %bb.152: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB7_153: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + setg bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_44 -# %bb.45: - add r11, 1 -.LBB7_46: - sar r15, 5 - cmp r10, 32 - jl .LBB7_47 -# %bb.48: + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB7_153 +.LBB7_154: + sub r15, r8 + je .LBB7_210 +# %bb.155: + add r14, 1 +.LBB7_156: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_160 +# %bb.157: + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB7_158: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r14 # 8-byte Spill + cmp dword ptr [rsi], r13d + setg byte ptr [rsp + 136] # 1-byte Folded Spill + cmp dword ptr [rsi + 4], r13d + setg dil + cmp dword ptr [rsi + 8], r13d + setg r14b + cmp dword ptr [rsi + 12], r13d + setg byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + setg byte ptr [rsp + 120] # 1-byte Folded Spill + cmp dword ptr [rsi + 20], r13d + setg byte ptr [rsp + 32] # 1-byte Folded Spill + cmp dword ptr [rsi + 24], r13d + setg al + cmp dword ptr [rsi + 28], r13d + setg bl + cmp dword ptr [rsi + 32], r13d + setg byte ptr [rsp + 88] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d + setg cl + cmp dword ptr [rsi + 40], r13d + setg r9b + cmp dword ptr [rsi + 44], r13d + setg r10b + cmp dword ptr [rsi + 48], r13d + setg r11b + cmp dword ptr [rsi + 52], r13d + setg r12b + cmp dword ptr [rsi + 56], r13d + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp dword ptr [rsi + 60], r13d + setg dl + cmp dword ptr [rsi + 64], r13d + setg byte ptr [rsp + 64] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + setg byte ptr [rsp + 104] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp dword ptr [rsi + 80], r13d + setg byte ptr [rsp + 72] # 1-byte Folded Spill + cmp dword ptr [rsi + 84], r13d + setg byte ptr [rsp + 40] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp dword ptr [rsi + 92], r13d + setg r15b + cmp dword ptr [rsi + 96], r13d + setg byte ptr [rsp + 320] # 1-byte Folded Spill + cmp dword ptr [rsi + 100], r13d + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp dword ptr [rsi + 104], r13d + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp dword ptr [rsi + 108], r13d + setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp dword ptr [rsi + 112], r13d + setg byte ptr [rsp + 288] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d + setg byte ptr [rsp + 256] # 1-byte Folded Spill + cmp dword ptr [rsi + 120], r13d + setg byte ptr [rsp + 4] # 1-byte Folded Spill + cmp dword ptr [rsi + 124], r13d + setg r8b + add dil, dil + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r14, qword ptr [rsp + 240] # 8-byte Reload + shl r9b, 2 + or r9b, cl + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r10b, 3 + or r10b, r9b + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r11b, 4 + or r11b, r10b + shl r12b, 5 + or r12b, r11b + movzx edi, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dil, 6 + shl dl, 7 + or dl, dil + or bl, cl + or dl, r12b + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl bl, 6 + shl r15b, 7 + or r15b, bl + mov byte ptr [r14 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 320] # 1-byte Folded Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl cl, 3 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 4 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload + shl cl, 5 + or cl, dl + movzx edx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl dl, 6 + shl r8b, 7 + or r8b, dl + or r8b, cl + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], r8b + add rsi, 128 + add r14, 4 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_158 +# %bb.159: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB7_160: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_210 +# %bb.161: + or rax, 1 + cmp r15, rax + jne .LBB7_165 +# %bb.162: + xor r11d, r11d + jmp .LBB7_163 +.LBB7_5: + mov rdi, rsi + jmp .LBB7_90 +.LBB7_59: + mov rdi, rsi + jmp .LBB7_64 +.LBB7_87: + mov rdi, rsi + sub r15, r8 + je .LBB7_210 +.LBB7_89: + add r14, 1 +.LBB7_90: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB7_91 +# %bb.94: + cmp rcx, 32 + mov dword ptr [rsp + 4], r13d # 4-byte Spill + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 360], rcx # 8-byte Spill + jb .LBB7_95 +# %bb.96: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB7_98 +# %bb.97: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB7_98 +.LBB7_95: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 352], r14 # 8-byte Spill +.LBB7_101: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 128], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB7_102: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r13b + setg byte ptr [rsp + 320] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r13b + setg r8b + cmp byte ptr [rsi + 2], r13b + setg r14b + cmp byte ptr [rsi + 3], r13b + setg r13b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rsi + 4], al + setg byte ptr [rsp + 32] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rsi + 5], al + setg byte ptr [rsp + 24] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rsi + 6], al + setg byte ptr [rsp + 136] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rsi + 7], al + setg r11b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rsi + 8], al + setg byte ptr [rsp + 288] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rsi + 9], al + setg dl + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rsi + 10], al + setg sil + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 11], al + setg dil + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 12], al + setg r10b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 13], al + setg r12b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 14], al + setg byte ptr [rsp + 80] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 15], al + setg r9b + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 16], bl + setg byte ptr [rsp + 256] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + setg byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 18], bl + setg byte ptr [rsp + 88] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 19], bl + setg byte ptr [rsp + 96] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + setg byte ptr [rsp + 112] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + setg byte ptr [rsp + 104] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + setg byte ptr [rsp + 40] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + setg r15b + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 24], bl + setg byte ptr [rsp + 240] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 25], bl + setg byte ptr [rsp + 56] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 26], bl + setg byte ptr [rsp + 64] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 27], bl + setg byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 28], bl + setg byte ptr [rsp + 48] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 29], bl + setg byte ptr [rsp + 8] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 30], bl + setg byte ptr [rsp + 16] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 31], bl + setg bl + add r8b, r8b + add r8b, byte ptr [rsp + 320] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r8b + add dl, dl + add dl, byte ptr [rsp + 288] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, dl + movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl dl, 4 + or dl, r13b + mov r8d, edx + mov r13d, dword ptr [rsp + 4] # 4-byte Reload + shl dil, 3 + or dil, sil + movzx edx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl dl, 5 + or dl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, dl + or r9b, r12b + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 256] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 2 + or dl, al + mov esi, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov rdi, qword ptr [rsp + 352] # 8-byte Reload + mov byte ptr [rdi], r11b + movzx esi, byte ptr [rsp + 40] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [rdi + 1], r9b + or r15b, dl + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 240] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 16] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r15b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 352], rdi # 8-byte Spill + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_102 +# %bb.103: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rcx, qword ptr [rsp + 360] # 8-byte Reload + jmp .LBB7_104 +.LBB7_91: + mov qword ptr [rsp + 352], r14 # 8-byte Spill + mov rsi, rdi +.LBB7_104: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB7_210 +# %bb.105: + or rcx, 1 + cmp r15, rcx + jne .LBB7_107 +# %bb.106: + xor r9d, r9d + jmp .LBB7_110 +.LBB7_61: + mov rdi, rsi + sub r15, r8 + je .LBB7_210 +.LBB7_63: + add r14, 1 +.LBB7_64: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 cmp r15, 32 - mov dword ptr [rsp + 4], r14d # 4-byte Spill - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 376], r15 # 8-byte Spill - jb .LBB7_49 -# %bb.50: - mov rax, r15 + jl .LBB7_65 +# %bb.68: + cmp rcx, 32 + mov dword ptr [rsp + 4], r13d # 4-byte Spill + mov qword ptr [rsp + 248], r15 # 8-byte Spill + mov qword ptr [rsp + 376], rcx # 8-byte Spill + jb .LBB7_69 +# %bb.70: + mov rax, rcx shl rax, 5 - add rax, rsi - cmp r11, rax - jae .LBB7_52 -# %bb.51: - lea rax, [r11 + 4*r15] - cmp rsi, rax - jae .LBB7_52 -.LBB7_49: + add rax, rdi + cmp r14, rax + jae .LBB7_72 +# %bb.71: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB7_72 +.LBB7_69: xor eax, eax mov qword ptr [rsp + 360], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 352], r11 # 8-byte Spill -.LBB7_55: - sub r15, qword ptr [rsp + 360] # 8-byte Folded Reload - mov qword ptr [rsp + 120], r15 # 8-byte Spill + mov r11, rdi + mov qword ptr [rsp + 352], r14 # 8-byte Spill +.LBB7_75: + sub rcx, qword ptr [rsp + 360] # 8-byte Folded Reload + mov qword ptr [rsp + 128], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB7_56: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b +.LBB7_76: # =>This Inner Loop Header: Depth=1 + mov rcx, r11 + cmp byte ptr [r11], r13b seta byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b + cmp byte ptr [r11 + 1], r13b seta r8b - cmp byte ptr [r12 + 2], r14b - seta r15b - cmp byte ptr [r12 + 3], r14b + cmp byte ptr [r11 + 2], r13b + seta r14b + cmp byte ptr [r11 + 3], r13b seta r13b - cmp byte ptr [r12 + 4], r14b - seta byte ptr [rsp + 104] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b - seta byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b - seta al - cmp byte ptr [r12 + 7], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [r11 + 4], al + seta byte ptr [rsp + 32] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [r11 + 5], al + seta byte ptr [rsp + 16] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [r11 + 6], al + seta byte ptr [rsp + 136] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [r11 + 7], al seta r11b - cmp byte ptr [r12 + 8], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 8], al seta byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 9], al seta dl - cmp byte ptr [r12 + 10], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 10], al seta sil - cmp byte ptr [r12 + 11], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 11], al seta dil - cmp byte ptr [r12 + 12], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 12], al seta r10b - cmp byte ptr [r12 + 13], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 13], al seta r12b - cmp byte ptr [rcx + 14], r14b - seta byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 14], al + seta byte ptr [rsp + 80] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 15], al seta r9b - cmp byte ptr [rcx + 16], r14b + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 16], bl seta byte ptr [rsp + 256] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b - seta byte ptr [rsp + 80] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b - seta byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + seta byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 18], bl seta byte ptr [rsp + 88] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 19], bl seta byte ptr [rsp + 96] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - seta byte ptr [rsp + 64] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b - seta byte ptr [rsp + 24] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - seta r14b + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + seta byte ptr [rsp + 112] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + seta byte ptr [rsp + 104] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + seta byte ptr [rsp + 40] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 4] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + seta r15b mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 24], bl seta byte ptr [rsp + 240] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 25], bl - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 26], bl - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 27], bl - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 28], bl - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 29], bl seta byte ptr [rsp + 8] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 30], bl - seta byte ptr [rsp + 16] # 1-byte Folded Spill + seta byte ptr [rsp + 24] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 4] # 4-byte Reload cmp byte ptr [rcx + 31], bl seta bl add r8b, r8b add r8b, byte ptr [rsp + 320] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al - shl r15b, 2 - or r15b, r8b + shl r14b, 2 + or r14b, r8b add dl, dl add dl, byte ptr [rsp + 288] # 1-byte Folded Reload shl r13b, 3 - or r13b, r15b + or r13b, r14b shl sil, 2 or sil, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload shl dl, 4 or dl, r13b mov r8d, edx + mov r13d, dword ptr [rsp + 4] # 4-byte Reload shl dil, 3 or dil, sil - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 16] # 1-byte Folded Reload shl dl, 5 or dl, r8b shl r10b, 4 or r10b, dil shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload shl sil, 6 shl r9b, 7 or r9b, sil or r11b, dl or r9b, r12b - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 256] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload shl dl, 2 or dl, al mov esi, edx - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload shl dl, 3 or dl, sil mov esi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload shl dl, 4 or dl, sil mov esi, edx - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload shl dl, 5 or dl, sil mov rsi, qword ptr [rsp + 352] # 8-byte Reload mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 40] # 1-byte Folded Reload shl dil, 6 - shl r14b, 7 - or r14b, dil + shl r15b, 7 + or r15b, dil mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + or r15b, dl + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 240] # 1-byte Folded Reload mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 2 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 3 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 4 or al, dl mov edx, eax movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 5 or al, dl - movzx edx, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 24] # 1-byte Folded Reload shl dl, 6 shl bl, 7 or bl, dl or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 4] # 4-byte Reload + mov byte ptr [rsi + 2], r15b mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] + lea r11, [rcx + 32] add rsi, 4 mov qword ptr [rsp + 352], rsi # 8-byte Spill - add qword ptr [rsp + 120], -1 # 8-byte Folded Spill - jne .LBB7_56 -# %bb.57: - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 376] # 8-byte Reload - jmp .LBB7_58 -.LBB7_129: - mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB7_133 -# %bb.130: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB7_131: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setg dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_131 -# %bb.132: - add r11, 1 -.LBB7_133: - sar r15, 5 - cmp r10, 32 - jl .LBB7_134 -# %bb.135: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB7_136: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 240], r11 # 8-byte Spill - cmp dword ptr [rsi], r13d - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - setg dil - cmp dword ptr [rsi + 8], r13d - setg r14b - cmp dword ptr [rsi + 12], r13d - setg byte ptr [rsp + 128] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - setg al - cmp dword ptr [rsi + 28], r13d - setg bl - cmp dword ptr [rsi + 32], r13d - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d - setg dl - cmp dword ptr [rsi + 40], r13d - setg r9b - cmp dword ptr [rsi + 44], r13d - setg r10b - cmp dword ptr [rsi + 48], r13d - setg r11b - cmp dword ptr [rsi + 52], r13d - setg r12b - cmp dword ptr [rsi + 56], r13d - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - setg cl - cmp dword ptr [rsi + 64], r13d - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - setg byte ptr [rsp + 56] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d - setg r15b - cmp dword ptr [rsi + 96], r13d - setg byte ptr [rsp + 320] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - setg byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d - setg byte ptr [rsp + 288] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d - setg byte ptr [rsp + 256] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - setg byte ptr [rsp + 4] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - setg r8b - add dil, dil - add dil, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al - shl r14b, 2 - or r14b, dil - add dl, dl - add dl, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 3 - or al, r14b - shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx - shl r10b, 3 - or r10b, r9b - movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - shl r11b, 4 - or r11b, r10b - shl r12b, 5 - or r12b, r11b - mov r11, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, dl - or cl, r12b - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 64] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r11 + 1], cl - or r15b, dl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 320] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload - shl cl, 5 - or cl, dl - movzx edx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl dl, 6 - shl r8b, 7 - or r8b, dl - or r8b, cl - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], r8b - add rsi, 128 - add r11, 4 - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB7_136 -# %bb.137: - mov r14, r11 - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB7_139 - jmp .LBB7_191 -.LBB7_18: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB7_191 -.LBB7_123: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB7_127 -# %bb.124: - xor r11d, r11d - jmp .LBB7_125 -.LBB7_9: - mov qword ptr [rsp + 352], r11 # 8-byte Spill - mov r12, rsi -.LBB7_76: - shl r13, 5 - cmp r13, r15 - jge .LBB7_191 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB7_76 # %bb.77: + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov rcx, qword ptr [rsp + 376] # 8-byte Reload + jmp .LBB7_78 +.LBB7_65: + mov qword ptr [rsp + 352], r14 # 8-byte Spill + mov r11, rdi +.LBB7_78: + shl rcx, 5 mov r8, r15 - sub r8, r13 - not r13 - add r13, r15 - jne .LBB7_79 -# %bb.78: - xor esi, esi - jmp .LBB7_82 -.LBB7_27: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB7_191 -.LBB7_149: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB7_153 -# %bb.150: - xor r11d, r11d - jmp .LBB7_151 -.LBB7_89: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB7_191 -.LBB7_94: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB7_100 -# %bb.95: - xor r11d, r11d - jmp .LBB7_96 -.LBB7_107: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB7_191 -.LBB7_112: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB7_117 -# %bb.113: - xor r11d, r11d - jmp .LBB7_114 -.LBB7_160: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB7_191 -.LBB7_165: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB7_169 -# %bb.166: - xor r11d, r11d - jmp .LBB7_167 -.LBB7_47: - mov qword ptr [rsp + 352], r11 # 8-byte Spill - mov r12, rsi -.LBB7_58: - shl r15, 5 - cmp r15, r10 - jge .LBB7_191 -# %bb.59: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB7_61 -# %bb.60: + sub r8, rcx + jle .LBB7_210 +# %bb.79: + or rcx, 1 + cmp r15, rcx + jne .LBB7_81 +# %bb.80: xor eax, eax - jmp .LBB7_64 -.LBB7_134: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB7_191 -.LBB7_139: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB7_143 -# %bb.140: - xor r11d, r11d - jmp .LBB7_141 -.LBB7_186: - mov r9, r8 - and r9, -2 - xor r10d, r10d - mov r14, r11 - .p2align 4, 0x90 -.LBB7_187: # =>This Inner Loop Header: Depth=1 - vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - vucomisd xmm1, xmm0 - seta al - neg al - mov rdi, r10 - shr rdi, 3 - mov ecx, r10d - and cl, 6 - mov bl, 1 - shl bl, cl - movzx edx, byte ptr [r14 + rdi] - xor al, dl - and bl, al - xor bl, dl - mov byte ptr [r14 + rdi], bl - add r10, 2 - vmovsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero - add rsi, 16 - vucomisd xmm1, xmm0 - seta al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r9, r10 - jne .LBB7_187 -.LBB7_188: - test r8b, 1 - je .LBB7_191 -# %bb.189: - vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - vucomisd xmm1, xmm0 - jmp .LBB7_190 -.LBB7_184: - mov r9, r8 - and r9, -2 - xor r10d, r10d - mov r14, r11 - .p2align 4, 0x90 -.LBB7_185: # =>This Inner Loop Header: Depth=1 - vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - seta al - neg al - mov rdi, r10 - shr rdi, 3 - mov ecx, r10d - and cl, 6 - mov bl, 1 - shl bl, cl - movzx edx, byte ptr [r14 + rdi] - xor al, dl - and bl, al - xor bl, dl - mov byte ptr [r14 + rdi], bl - add r10, 2 - vmovss xmm1, dword ptr [rsi + 4] # xmm1 = mem[0],zero,zero,zero - add rsi, 8 - vucomiss xmm1, xmm0 - seta al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r9, r10 - jne .LBB7_185 -.LBB7_182: - test r8b, 1 - je .LBB7_191 -# %bb.183: - vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 -.LBB7_190: - seta al - neg al - mov rdx, r10 - shr rdx, 3 - mov sil, byte ptr [r11 + rdx] - and r10b, 7 - mov bl, 1 - mov ecx, r10d - shl bl, cl - xor al, sil - and bl, al - xor bl, sil - mov byte ptr [r11 + rdx], bl - jmp .LBB7_191 -.LBB7_127: + jmp .LBB7_84 +.LBB7_148: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB7_128: # =>This Inner Loop Header: Depth=1 +.LBB7_149: # =>This Inner Loop Header: Depth=1 cmp r13d, dword ptr [rsi] sbb edi, edi mov rdx, r11 shr rdx, 3 - movzx r10d, byte ptr [r15 + rdx] + movzx r10d, byte ptr [r14 + rdx] mov ecx, r11d and cl, 6 mov al, 1 @@ -40218,7 +41329,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 xor dil, r10b and al, dil xor al, r10b - mov byte ptr [r15 + rdx], al + mov byte ptr [r14 + rdx], al add r11, 2 cmp r13d, dword ptr [rsi + 4] lea rsi, [rsi + 8] @@ -40229,83 +41340,69 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rdx], bl + mov byte ptr [r14 + rdx], bl cmp r9, r11 - jne .LBB7_128 -.LBB7_125: + jne .LBB7_149 +.LBB7_22: test r8b, 1 - je .LBB7_191 -# %bb.126: + je .LBB7_210 +# %bb.23: cmp r13d, dword ptr [rsi] - jmp .LBB7_98 -.LBB7_79: - mov r10, r8 - and r10, -2 - xor esi, esi - mov r11, qword ptr [rsp + 352] # 8-byte Reload + jmp .LBB7_127 +.LBB7_203: + mov r9, r8 + and r9, -2 + xor r10d, r10d .p2align 4, 0x90 -.LBB7_80: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rsi], r14b - setg bl - neg bl - mov rdi, rsi +.LBB7_204: # =>This Inner Loop Header: Depth=1 + vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + vucomisd xmm1, xmm0 + seta al + neg al + mov rdi, r10 shr rdi, 3 - mov ecx, esi + mov ecx, r10d and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r11 + rdi] - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp byte ptr [r12 + rsi + 1], r14b - lea rsi, [rsi + 2] - setg bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB7_80 -# %bb.81: - add r12, rsi -.LBB7_82: - test r8b, 1 - je .LBB7_191 -# %bb.83: - cmp byte ptr [r12], r14b - setg al - neg al - mov rdx, rsi - shr rdx, 3 - mov r8, qword ptr [rsp + 352] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and sil, 7 mov bl, 1 - mov ecx, esi shl bl, cl - xor al, dil + movzx edx, byte ptr [r14 + rdi] + xor al, dl and bl, al - xor bl, dil - mov byte ptr [r8 + rdx], bl - jmp .LBB7_191 -.LBB7_153: + xor bl, dl + mov byte ptr [r14 + rdi], bl + add r10, 2 + vmovsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero + add rsi, 16 + vucomisd xmm1, xmm0 + seta al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r9, r10 + jne .LBB7_204 +.LBB7_205: + test r8b, 1 + je .LBB7_210 +# %bb.206: + vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + vucomisd xmm1, xmm0 + jmp .LBB7_207 +.LBB7_167: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB7_154: # =>This Inner Loop Header: Depth=1 +.LBB7_168: # =>This Inner Loop Header: Depth=1 cmp r13, qword ptr [rsi] sbb edi, edi mov rdx, r11 shr rdx, 3 - movzx r10d, byte ptr [r15 + rdx] + movzx r10d, byte ptr [r14 + rdx] mov ecx, r11d and cl, 6 mov al, 1 @@ -40313,7 +41410,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 xor dil, r10b and al, dil xor al, r10b - mov byte ptr [r15 + rdx], al + mov byte ptr [r14 + rdx], al add r11, 2 cmp r13, qword ptr [rsi + 8] lea rsi, [rsi + 16] @@ -40324,27 +41421,26 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rdx], bl + mov byte ptr [r14 + rdx], bl cmp r9, r11 - jne .LBB7_154 -.LBB7_151: + jne .LBB7_168 +.LBB7_40: test r8b, 1 - je .LBB7_191 -# %bb.152: + je .LBB7_210 +# %bb.41: cmp r13, qword ptr [rsi] - jmp .LBB7_98 -.LBB7_100: + jmp .LBB7_127 +.LBB7_128: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB7_101: # =>This Inner Loop Header: Depth=1 +.LBB7_129: # =>This Inner Loop Header: Depth=1 cmp r13w, word ptr [rsi] sbb edi, edi mov rdx, r11 shr rdx, 3 - movzx r10d, byte ptr [r15 + rdx] + movzx r10d, byte ptr [r14 + rdx] mov ecx, r11d and cl, 6 mov al, 1 @@ -40352,7 +41448,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 xor dil, r10b and al, dil xor al, r10b - mov byte ptr [r15 + rdx], al + mov byte ptr [r14 + rdx], al add r11, 2 cmp r13w, word ptr [rsi + 2] lea rsi, [rsi + 4] @@ -40363,15 +41459,15 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rdx], bl + mov byte ptr [r14 + rdx], bl cmp r9, r11 - jne .LBB7_101 -.LBB7_96: + jne .LBB7_129 +.LBB7_125: test r8b, 1 - je .LBB7_191 -# %bb.97: + je .LBB7_210 +# %bb.126: cmp r13w, word ptr [rsi] -.LBB7_98: +.LBB7_127: sbb eax, eax mov rdx, r11 shr rdx, 3 @@ -40382,20 +41478,19 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl bl, cl xor al, sil and bl, al - jmp .LBB7_99 -.LBB7_117: + jmp .LBB7_209 +.LBB7_146: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB7_118: # =>This Inner Loop Header: Depth=1 +.LBB7_147: # =>This Inner Loop Header: Depth=1 cmp word ptr [rsi], r13w setg al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -40403,7 +41498,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp word ptr [rsi + 2], r13w lea rsi, [rsi + 4] @@ -40415,28 +41510,27 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB7_118 -.LBB7_114: + jne .LBB7_147 +.LBB7_143: test r8b, 1 - je .LBB7_191 -# %bb.115: + je .LBB7_210 +# %bb.144: cmp word ptr [rsi], r13w - jmp .LBB7_116 -.LBB7_169: + jmp .LBB7_145 +.LBB7_184: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB7_170: # =>This Inner Loop Header: Depth=1 +.LBB7_185: # =>This Inner Loop Header: Depth=1 cmp qword ptr [rsi], r13 setg al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -40444,7 +41538,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp qword ptr [rsi + 8], r13 lea rsi, [rsi + 16] @@ -40456,81 +41550,79 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB7_170 -.LBB7_167: + jne .LBB7_185 +.LBB7_182: test r8b, 1 - je .LBB7_191 -# %bb.168: + je .LBB7_210 +# %bb.183: cmp qword ptr [rsi], r13 - jmp .LBB7_116 -.LBB7_61: + jmp .LBB7_145 +.LBB7_201: mov r9, r8 and r9, -2 - xor eax, eax - mov r10, qword ptr [rsp + 352] # 8-byte Reload + xor r10d, r10d .p2align 4, 0x90 -.LBB7_62: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [r12 + rax] - sbb esi, esi - mov rdi, rax +.LBB7_202: # =>This Inner Loop Header: Depth=1 + vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + seta al + neg al + mov rdi, r10 shr rdi, 3 - mov ecx, eax + mov ecx, r10d and cl, 6 - mov dl, 1 - shl dl, cl - movzx ebx, byte ptr [r10 + rdi] - xor sil, bl - and dl, sil - xor dl, bl - mov byte ptr [r10 + rdi], dl - cmp r14b, byte ptr [r12 + rax + 1] - lea rax, [rax + 2] - sbb esi, esi - xor sil, dl - or cl, 1 mov bl, 1 shl bl, cl - and bl, sil + movzx edx, byte ptr [r14 + rdi] + xor al, dl + and bl, al xor bl, dl - mov byte ptr [r10 + rdi], bl - cmp r9, rax - jne .LBB7_62 -# %bb.63: - add r12, rax -.LBB7_64: + mov byte ptr [r14 + rdi], bl + add r10, 2 + vmovss xmm1, dword ptr [rsi + 4] # xmm1 = mem[0],zero,zero,zero + add rsi, 8 + vucomiss xmm1, xmm0 + seta al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r14 + rdi], dl + cmp r9, r10 + jne .LBB7_202 +.LBB7_199: test r8b, 1 - je .LBB7_191 -# %bb.65: - cmp r14b, byte ptr [r12] - sbb edx, edx - mov rsi, rax - shr rsi, 3 - mov r8, qword ptr [rsp + 352] # 8-byte Reload - mov dil, byte ptr [r8 + rsi] - and al, 7 + je .LBB7_210 +# %bb.200: + vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 +.LBB7_207: + seta al + neg al + mov rdx, r10 + shr rdx, 3 + mov sil, byte ptr [r14 + rdx] + and r10b, 7 mov bl, 1 - mov ecx, eax - shl bl, cl - xor dl, dil - and bl, dl - xor bl, dil - mov byte ptr [r8 + rsi], bl - jmp .LBB7_191 -.LBB7_143: + mov ecx, r10d + jmp .LBB7_208 +.LBB7_165: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB7_144: # =>This Inner Loop Header: Depth=1 +.LBB7_166: # =>This Inner Loop Header: Depth=1 cmp dword ptr [rsi], r13d setg al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -40538,7 +41630,7 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp dword ptr [rsi + 4], r13d lea rsi, [rsi + 8] @@ -40550,15 +41642,15 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB7_144 -.LBB7_141: + jne .LBB7_166 +.LBB7_163: test r8b, 1 - je .LBB7_191 -# %bb.142: + je .LBB7_210 +# %bb.164: cmp dword ptr [rsi], r13d -.LBB7_116: +.LBB7_145: setg al neg al mov rdx, r11 @@ -40567,13 +41659,14 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 and r11b, 7 mov bl, 1 mov ecx, r11d +.LBB7_208: shl bl, cl xor al, sil and bl, al -.LBB7_99: +.LBB7_209: xor bl, sil mov byte ptr [r14 + rdx], bl -.LBB7_191: +.LBB7_210: lea rsp, [rbp - 40] pop rbx pop r12 @@ -40583,1985 +41676,2091 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 pop rbp vzeroupper ret -.LBB7_70: - and r13, -32 - mov rax, r13 +.LBB7_107: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 352] # 8-byte Reload + .p2align 4, 0x90 +.LBB7_108: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r13b + setg bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r13b + lea r9, [rax + 2] + setg bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB7_108 +# %bb.109: + add rsi, r9 +.LBB7_110: + test r8b, 1 + je .LBB7_210 +# %bb.111: + cmp byte ptr [rsi], r13b + setg al + neg al + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 352] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r8 + rdx], bl + jmp .LBB7_210 +.LBB7_81: + mov r9, r8 + and r9, -2 + xor eax, eax + mov r10, qword ptr [rsp + 352] # 8-byte Reload + .p2align 4, 0x90 +.LBB7_82: # =>This Inner Loop Header: Depth=1 + cmp r13b, byte ptr [r11 + rax] + sbb esi, esi + mov rdi, rax + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx ebx, byte ptr [r10 + rdi] + xor sil, bl + and dl, sil + xor dl, bl + mov byte ptr [r10 + rdi], dl + cmp r13b, byte ptr [r11 + rax + 1] + lea rax, [rax + 2] + sbb esi, esi + xor sil, dl + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, sil + xor bl, dl + mov byte ptr [r10 + rdi], bl + cmp r9, rax + jne .LBB7_82 +# %bb.83: + add r11, rax +.LBB7_84: + test r8b, 1 + je .LBB7_210 +# %bb.85: + cmp r13b, byte ptr [r11] + sbb edx, edx + mov rsi, rax + shr rsi, 3 + mov r8, qword ptr [rsp + 352] # 8-byte Reload + mov dil, byte ptr [r8 + rsi] + and al, 7 + mov bl, 1 + mov ecx, eax + shl bl, cl + xor dl, dil + and bl, dl + xor bl, dil + mov byte ptr [r8 + rsi], bl + jmp .LBB7_210 +.LBB7_98: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 576], rax # 8-byte Spill - mov qword ptr [rsp + 384], r13 # 8-byte Spill - lea rax, [r11 + 4*r13] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 352], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r13d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 240], r11 # 8-byte Spill + mov qword ptr [rsp + 240], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB7_71: # =>This Inner Loop Header: Depth=1 +.LBB7_99: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 368], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 112], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 200], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 24], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 128], rax # 8-byte Spill + mov qword ptr [rsp + 232], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 232], rax # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 88], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] - mov rdx, rcx + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - mov rcx, rbx - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rdx + 1] + movzx eax, byte ptr [rdi + rcx + 1] vmovd xmm4, eax - movzx eax, byte ptr [rsi + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rsi + rdx + 2] + movzx eax, byte ptr [rdi + rcx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 544], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rcx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rcx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm13, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rcx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rsi + rdx + 6] - mov qword ptr [rsp + 208], rdx # 8-byte Spill + movzx eax, byte ptr [rdi + rcx + 6] + mov qword ptr [rsp + 192], rcx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rcx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 80], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 8], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 16], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov qword ptr [rsp + 120], rax # 8-byte Spill - mov rax, rbx - or rax, 576 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov r12, rbx + or r12, 576 mov rax, rbx or rax, 608 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov rax, rbx + or rax, 640 + mov qword ptr [rsp + 144], rax # 8-byte Spill mov r15, rbx - or r15, 640 - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov r11, rbx - or r11, 672 - mov qword ptr [rsp + 184], r11 # 8-byte Spill - mov r8, rbx - or r8, 704 - mov qword ptr [rsp + 136], r8 # 8-byte Spill - mov rdx, rbx - or rdx, 736 - mov qword ptr [rsp + 176], rdx # 8-byte Spill - mov r12, rbx - or r12, 768 - mov qword ptr [rsp + 160], r12 # 8-byte Spill + or r15, 672 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov r14, rbx - or r14, 800 - mov qword ptr [rsp + 168], r14 # 8-byte Spill + or r14, 704 + mov qword ptr [rsp + 96], r14 # 8-byte Spill + mov rax, rbx + or rax, 736 + mov r13, rax + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov r11, rbx + or r11, 768 + mov qword ptr [rsp + 216], r11 # 8-byte Spill mov r10, rbx - or r10, 832 - mov qword ptr [rsp + 40], r10 # 8-byte Spill + or r10, 800 + mov qword ptr [rsp + 88], r10 # 8-byte Spill mov r9, rbx - or r9, 864 - mov qword ptr [rsp + 64], r9 # 8-byte Spill - mov rax, rbx - or rax, 896 - mov qword ptr [rsp + 216], rax # 8-byte Spill - mov rdi, rbx - or rdi, 928 - mov qword ptr [rsp + 112], rdi # 8-byte Spill - mov rax, rbx + or r9, 832 + mov qword ptr [rsp + 56], r9 # 8-byte Spill + mov rdx, rbx + or rdx, 864 + mov qword ptr [rsp + 64], rdx # 8-byte Spill + mov rsi, rbx + mov rcx, rbx mov qword ptr [rsp + 224], rbx # 8-byte Spill + or rsi, 896 + mov qword ptr [rsp + 80], rsi # 8-byte Spill + mov r8, rbx + or r8, 928 + mov qword ptr [rsp + 72], r8 # 8-byte Spill + mov rax, rbx or rax, 960 - mov qword ptr [rsp + 8], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 16], rcx # 8-byte Spill - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm9, xmm0, byte ptr [rsi + r13], 1 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + rbx], 2 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 11 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 1 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12], 2 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 3 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11], 4 - mov r8, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 5 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 6 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 7 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 12 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 13 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 15 + mov qword ptr [rsp + 160], rcx # 8-byte Spill + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + rbx], 1 + mov qword ptr [rsp + 184], r12 # 8-byte Spill + vpinsrb xmm0, xmm9, byte ptr [rdi + r12], 2 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 1 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 2 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 3 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 4 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 7 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 8 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 9 mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 1 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 2 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 3 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 4 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 5 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 6 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 7 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 8 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 9 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 10 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 12 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 10 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 12 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 13 mov r13, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rsi + r14 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 6 - mov r8, r9 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13], 14 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 15 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 1], 2 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 1], 3 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 4 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 1], 5 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 6 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 7 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 8 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 9 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 10 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 1], 11 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 13 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 14 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r15 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 6 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 1], 14 vinserti128 ymm15, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 1], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1280], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm10, edi - mov rdx, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm10, eax + mov r10, qword ptr [rsp + 176] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 544] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 2], 1 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 2], 2 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 2], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 1 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 3 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 5 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 7 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 2], 8 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 9 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 2], 10 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 11 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 2], 12 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 13 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 15 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 2 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 2], 6 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 7 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 9 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 10 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 2], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + rdx + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 3 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 4 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 5 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 6 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 13 - mov r14, r15 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 14 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 2 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 3], 3 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 3], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 7 - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 3], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 7 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 8 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 9 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 11 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 13 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 2], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 3 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 2], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 5 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 7 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 8 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 9 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 11 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 12 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 13 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 14 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r10 + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 2 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 5 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 7 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 10 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 12 + mov r12, r9 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 14 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rcx + 3], 1 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 2 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 3], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 3], 4 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 5 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 7 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 3], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 14 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm8, edi - mov r9, rbx - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 3], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 14 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm11, edi + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 1 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 2 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 3 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 4 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 4], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 1 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 5 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 6 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 4], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 10 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 11 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 14 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 4], 15 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm13, byte ptr [rsi + rax + 4], 1 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 4], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 4 - mov r10, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 5 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 4], 6 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 4], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 7 + mov rcx, r14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 8 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 10 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 4], 11 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 4], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 13 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 15 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm13, byte ptr [rdi + rbx + 4], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 5 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 13 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 4], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 4], 15 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm14, byte ptr [rsi + r9 + 5], 1 - mov r15, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 2 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 5 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 6 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 7 - mov r13, rcx - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 10 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 11 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 13 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 14 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 5], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 6 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 7 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 8 + mov r14, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 4], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 4], 10 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 11 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 4], 12 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 13 + mov r12, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 14 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r10 + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 2 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 3 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 4 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 6 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 8 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 9 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 10 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 11 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 14 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + rbx + 5], 1 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 5], 2 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 3 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 4 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 5], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + rax + 5], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 2 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 3 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 6 - mov r10, rdi - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 7 - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 5], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 5], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 5], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 5], 12 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 vinserti128 ymm14, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 5], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm3, edi + vpinsrb xmm0, xmm5, byte ptr [rdi + r12 + 5], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm3, eax vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm4, edi - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rsi + rax + 6], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 2 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 6], 3 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 6], 4 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 6], 5 + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + r9 + 6], 1 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 6 mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 7 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 8 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 10 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 7 mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 6], 12 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 6], 13 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 14 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 15 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rcx + 6], 1 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 2 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 6], 6 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 7 - mov r10, r14 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 10 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 12 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 13 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 14 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 4 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 6 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 7 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 7], 9 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 10 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 7], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 7], 13 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 15 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 1 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 2 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 3 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 5 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 6 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 7], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 8 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 6], 9 mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 11 mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 11 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 12 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 15 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rcx + 6], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 6], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 5 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 6 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 7 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 9 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 10 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 11 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 12 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 13 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 14 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 2 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 3 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 4 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 5 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 7 + mov rsi, r11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 8 + mov r15, r12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 10 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 13 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 14 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 1 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 7], 2 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 3 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 7 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rcx + 7], 14 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 11] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 7], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 7], 14 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1248], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 11] - vmovd xmm2, edi - vpinsrb xmm0, xmm9, byte ptr [rsi + rax + 8], 1 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 8], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 8], 4 - mov rbx, r14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 8], 5 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 6 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 8], 8 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 8], 9 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 8], 11 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 8], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 13 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 15 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rsi + rdx + 8], 1 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 8], 2 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 4 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 5 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 8], 8 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 8], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 8], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 12 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 13 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 15 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rsi + r13 + 9], 1 - vpinsrb xmm6, xmm6, byte ptr [rsi + r12 + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 3 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 6 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 8 - vpinsrb xmm6, xmm6, byte ptr [rsi + r8 + 9], 9 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm2, eax + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r10 + 8], 1 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 2 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 3 + mov r11, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 4 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 5 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 8], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 8], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 14 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 15 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + rax + 8], 1 + mov r15, r13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 2 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 3 + mov rax, rbx + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 4 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 5 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 6 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 8 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 9 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 10 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 12 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 13 + mov r12, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 14 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r10 + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 5 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 7 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 8 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 9 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 10 mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 11 - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 13 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 15 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 11 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 12 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 13 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 15 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rsi + 9], 1 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 9], 2 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 4 + mov rsi, rax + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 9], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 6 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 7 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 10 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rsi + rax + 9], 1 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 9], 2 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 4 - mov r14, rdi + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 6 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 9], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 9], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 12 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 12 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm0, edi + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 9], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm0, eax vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1184], ymm5 # 32-byte Spill mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 10], 1 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 10], 2 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 3 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 5 + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 1 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 2 + mov r9, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 5 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 6 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 10], 7 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 8 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 10], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 10], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 13 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 10], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 10], 15 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 2 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 5 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 6 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 9 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 9 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 11 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 11 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 10], 13 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 10], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 2 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 11], 4 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 5 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 11], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 7 - mov r9, rdx - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 11], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 13 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 14 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 15 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 1 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 10], 2 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 10 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 11 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 13 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 14 - mov r15, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 11], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 11], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 4 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 5 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 8 + mov r14, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 9 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 10 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 12 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 14 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 11], 4 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 6 + mov r9, r13 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 7 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 11], 8 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 9 + mov r13, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 10 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 11 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 13 + mov r15, rbx + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 15 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 3 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 6 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 6 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 7 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 11], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 11], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 11], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1152], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 14 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 13] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1120], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 13] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 1 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 3 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 5 - mov rbx, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 12], 8 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 10 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 11 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 12], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 12], 13 - mov r14, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 12], 14 - mov r10, r15 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 12], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 6 + mov r9, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 12], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 12], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 11 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 13 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 14 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 15 + vpinsrb xmm2, xmm5, byte ptr [rdi + rdx + 12], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 2 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 4 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 5 + mov r15, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 6 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 7 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 9 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 10 mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rsi + r13 + 12], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 12], 2 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 6 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 12], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 12], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 10 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 12], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 12 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 13 + mov rbx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 14 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 15 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 1 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 2 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 4 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 5 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 7 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 8 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 9 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 10 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 13 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 15 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 1 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 4 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 6 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 13], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 9 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 10 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 12 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 13], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 2 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 13], 7 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 13], 11 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 13], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 13 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 13], 15 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 3 + mov r9, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 13], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 13], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 9 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 11 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 12 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 13 + mov rbx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 1088], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rax + 13], 15 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 14] - vmovd xmm1, edi + mov r11, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + r11 + 13], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm1, eax vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm0 # 32-byte Spill - mov r14, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + r14 + 14] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 1 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 14], 2 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 14], 3 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 14], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 5 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 7 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm0, eax + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 1 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 2 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 12 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 14], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 15 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 14], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 10 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 14], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 15] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 15], 3 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 4 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 6 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 9 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 15], 10 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 14 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 15] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 1 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 5 + mov r8, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 6 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 15], 7 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 8 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 14], 10 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 11 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 9 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 11 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 13 mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 14 mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 15 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 14], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 2 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 3 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 14], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 5 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 14], 6 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 14], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 13 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 15 - movzx edi, byte ptr [rsi + r13 + 15] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 4 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 6 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 15], 7 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 8 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 9 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 11 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 15], 12 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 13 - mov r8, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 14 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 15 - movzx edi, byte ptr [rsi + r14 + 15] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 15], 1 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 2 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 15], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 6 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 15], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 10 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 13 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 14 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 15], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 16] - vmovd xmm0, edi - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 16], 1 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 2 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 16], 3 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 5 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 7 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 10 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 16], 12 + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 16], 7 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 16], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 11 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 13 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 15 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 16] + vmovd xmm1, eax mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 16], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 3 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 14 mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 15 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 16] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 2 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 16], 7 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 12 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 13 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 16], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 16], 15 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 17] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 17], 1 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 17], 3 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 17], 6 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 8 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 17], 10 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 17], 11 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 12 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 13 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 17] - vmovd xmm3, edi - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 17], 1 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 17], 2 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 17], 3 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 15 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 17] + vmovd xmm2, eax + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 17], 1 + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 5 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 6 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 6 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 7 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 8 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 17], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 17], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 15 + movzx eax, byte ptr [rdi + rbx + 17] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 1 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 17], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 4 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 5 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 7 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rax + 17], 15 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill + movzx eax, byte ptr [rdi + rdx + 18] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 3 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 18], 7 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 18], 8 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 18], 9 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 18], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 14 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm1, eax + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 3 + mov r15, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 7 mov rax, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 18] - vmovd xmm0, edi + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 8 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 9 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 18], 2 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 5 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 18], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 9 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 11 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 18], 12 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 13 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 18], 15 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 18] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 18], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 18], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 4 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 5 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 18], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 18], 7 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 10 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 18], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 18], 14 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 18], 15 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 19] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 1 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 3 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 4 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 19], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 19], 6 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 7 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 19], 10 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 19], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 13 - mov r9, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 19], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 15 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + r10 + 19] - vmovd xmm3, edi + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 10 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 1 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 14 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 2 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 19], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 10 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 12 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 13 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 19], 1 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + mov r15, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 9 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 10 + mov r9, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 19], 6 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 19], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 19], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 19], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 20] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 1 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 3 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 5 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 6 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 7 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 20], 8 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 9 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 10 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 11 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 20], 14 - mov r14, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 20], 15 - movzx edi, byte ptr [rsi + r10 + 20] - vmovd xmm1, edi - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 20], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 20], 2 - mov r8, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 20], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 5 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 6 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 20], 7 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 11 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 13 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 15 - movzx edi, byte ptr [rsi + r11 + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 2 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 20] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 1 + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 3 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 4 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 5 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 21], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 21], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 11 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 4 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 6 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 7 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 20], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 15 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 20] + vmovd xmm1, eax mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 13 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 21], 15 - mov r11, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 21] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 21], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 1 + mov rsi, r8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 4 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 6 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 21], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 8 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 20], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 11 + mov r9, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 13 + mov r15, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 14 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 15 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + r12 + 21] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 5 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 7 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 21], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 10 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 21], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 21], 12 - mov r8, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 21], 13 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 7 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 14 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 15 + movzx eax, byte ptr [rdi + rbx + 21] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 2 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 5 + mov rsi, rcx + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 21], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + r10 + 21], 15 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 1 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 3 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 4 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 5 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 6 + movzx eax, byte ptr [rdi + r12 + 22] + vmovd xmm0, eax mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 7 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 8 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 9 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 22], 10 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 22], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 13 - mov r9, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 22], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 15 - movzx edi, byte ptr [rsi + r11 + 22] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 2 - mov r12, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 22], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 22], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 22], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 6 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 22], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 22], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 2 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 3 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 5 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 7 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 9 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 22], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 22], 13 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 22], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 15 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 23] - vmovd xmm2, edi - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 23], 1 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 23], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 3 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 5 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 6 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 7 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 10 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 11 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 12 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 23], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 15 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 23] - vmovd xmm3, edi - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 23], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 5 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 7 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 22], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 13 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 5 + mov rbx, rsi + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 22], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 14 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 1 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 23], 8 mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 23], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 9 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 14 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 15 + mov r10, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 23] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 1 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 2 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 7 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 10 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 14 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 24] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 24], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 24], 2 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 24], 3 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 4 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 6 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 24], 7 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 8 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 9 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 10 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 24], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 24], 13 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 24], 15 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 24] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 1 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 2 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 5 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 6 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 13 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 14 - mov r11, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 15 - movzx edi, byte ptr [rsi + rcx + 25] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 1 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 25], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 25], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 3 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 4 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 6 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 25], 7 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 25], 9 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 25], 10 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 25], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 7 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 10 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 15 + movzx eax, byte ptr [rdi + r10 + 24] + vmovd xmm1, eax + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 3 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 6 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 8 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 11 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 13 mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 15 - movzx edi, byte ptr [rsi + rdx + 25] - vmovd xmm3, edi - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 15 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 2 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 5 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 25], 6 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 7 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 8 - mov r10, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 25], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 3 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 4 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 5 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 6 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 7 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 11 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 12 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 13 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 7 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 25], 12 + mov r8, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 25], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 14 vinserti128 ymm9, ymm1, xmm0, 1 - vpinsrb xmm0, xmm3, byte ptr [rsi + r11 + 25], 15 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r12 + 25], 15 vinserti128 ymm8, ymm0, xmm2, 1 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 26] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 2 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 3 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 5 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 26], 6 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 8 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 26], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 11 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 12 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 26], 13 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 14 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 26], 15 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 26] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 1 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 2 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 4 - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 6 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 7 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 26], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 11 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 26] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 2 + mov r14, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 26], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 7 + mov r13, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 8 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 9 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 10 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 12 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 26], 13 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 13 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 15 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rsi + 26] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 1 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 26], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 7 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 8 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 15 + movzx eax, byte ptr [rdi + rdx + 27] + vmovd xmm2, eax + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 27], 1 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 4 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 15 - movzx edi, byte ptr [rsi + r11 + 27] - vmovd xmm2, edi - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 27], 1 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 27], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 4 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 27], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 7 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 8 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 27], 9 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 10 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 27], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 27], 13 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 15 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 27] - vmovd xmm3, edi - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 1 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 27], 2 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 3 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 27], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 5 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 6 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 12 mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 27], 13 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 14 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 15 + movzx eax, byte ptr [rdi + rsi + 27] + vmovd xmm3, eax + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 2 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 3 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 8 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 13 + mov rbx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 14 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 1 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 3 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 5 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 10 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 28] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 4 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 8 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 10 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 11 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 13 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 15 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rsi + r12 + 28] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 28], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 4 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 28], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 6 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 7 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 28], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 11 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 15 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 28] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 5 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 6 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 7 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 9 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 10 + mov r11, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 14 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 15 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 29] + vmovd xmm2, eax + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 3 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 5 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 9 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 9 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 10 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 28], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 10 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 11 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 15 + movzx eax, byte ptr [rdi + rcx + 29] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 15 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 29] - vmovd xmm2, edi - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 29], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 4 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 5 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 6 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 7 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 8 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 9 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 10 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 12 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 13 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 15 - movzx edi, byte ptr [rsi + r12 + 29] - vmovd xmm3, edi - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 29], 1 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 2 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 3 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 29], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 5 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 29], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 29], 8 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 29], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 29], 12 - mov r14, rdx - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 13 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rsi + r10 + 29], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 8 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 11 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 12 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 13 + mov r9, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm4, xmm3, byte ptr [rdi + r9 + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rsi + rdx + 29], 15 + vpinsrb xmm0, xmm4, byte ptr [rdi + rbx + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov r8, qword ptr [rsp + 208] # 8-byte Reload - movzx edi, byte ptr [rsi + r8 + 30] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 30], 1 - movzx edi, byte ptr [rsi + r8 + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 31], 1 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 31], 3 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 31], 5 + mov rcx, r10 + movzx eax, byte ptr [rdi + r10 + 30] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 30], 1 + movzx eax, byte ptr [rdi + r10 + 31] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 31], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 31], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 31], 6 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 6 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 10 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov r14, qword ptr [rsp + 240] # 8-byte Reload mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 12 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 13 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + rax + 31], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + rax + 31], 15 mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx eax, byte ptr [rsi + rcx + 30] + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 30], 1 - movzx eax, byte ptr [rsi + rcx + 31] + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 31], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + r12 + 31], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 31], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 8 - mov rax, r9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 31], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 11 - mov rax, r14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 31], 14 - mov rax, rdx - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + mov rax, rsi + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, r11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r9 + 31], 14 + mov rax, rbx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -42715,2011 +43914,2001 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 368] # 8-byte Reload - vmovdqu ymmword ptr [r11 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r11 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r11 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r11 + 4*rcx], ymm1 + vmovdqu ymmword ptr [r14 + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [r14 + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [r14 + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [r14 + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB7_71 -# %bb.72: - mov r13, qword ptr [rsp + 360] # 8-byte Reload - cmp r13, qword ptr [rsp + 384] # 8-byte Folded Reload + jne .LBB7_99 +# %bb.100: + mov rcx, qword ptr [rsp + 360] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload mov r15, qword ptr [rsp + 248] # 8-byte Reload - mov r14d, dword ptr [rsp + 4] # 4-byte Reload - mov r12, qword ptr [rsp + 576] # 8-byte Reload - jne .LBB7_73 - jmp .LBB7_76 -.LBB7_52: - and r15, -32 - mov rax, r15 + mov r13d, dword ptr [rsp + 4] # 4-byte Reload + mov rsi, qword ptr [rsp + 576] # 8-byte Reload + jne .LBB7_101 + jmp .LBB7_104 +.LBB7_72: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 504], rax # 8-byte Spill - mov qword ptr [rsp + 360], r15 # 8-byte Spill - lea rax, [r11 + 4*r15] + mov qword ptr [rsp + 360], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 352], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r13d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 240], r11 # 8-byte Spill + mov qword ptr [rsp + 240], r14 # 8-byte Spill vmovdqa ymm14, ymmword ptr [rsp + 576] # 32-byte Reload .p2align 4, 0x90 -.LBB7_53: # =>This Inner Loop Header: Depth=1 +.LBB7_73: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 368], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 24], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 128], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 216], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 112], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 216], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rcx + 1] + movzx eax, byte ptr [rdi + rcx + 1] vmovd xmm4, eax - movzx eax, byte ptr [rsi + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rsi + rcx + 2] - mov rdx, rcx + movzx eax, byte ptr [rdi + rcx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - mov rcx, rbx - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rcx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rcx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 512], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm13, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rcx + 5] vmovd xmm15, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rsi + rdx + 6] - mov qword ptr [rsp + 184], rdx # 8-byte Spill + movzx eax, byte ptr [rdi + rcx + 6] + mov qword ptr [rsp + 232], rcx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rcx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 8], rax # 8-byte Spill + mov qword ptr [rsp + 24], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 8], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 16], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 48], rax # 8-byte Spill - mov r13, rbx - or r13, 544 - mov qword ptr [rsp + 56], r13 # 8-byte Spill - mov r11, rbx - or r11, 576 - mov r14, rbx - or r14, 608 - mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov rax, rbx + or rax, 544 + mov qword ptr [rsp + 16], rax # 8-byte Spill + mov rax, rbx + or rax, 576 + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r12, rbx + or r12, 608 + mov qword ptr [rsp + 48], r12 # 8-byte Spill mov r15, rbx or r15, 640 - mov qword ptr [rsp + 168], r15 # 8-byte Spill - or rbx, 672 - mov qword ptr [rsp + 144], rbx # 8-byte Spill - mov r12, rcx - or r12, 704 - mov qword ptr [rsp + 200], r12 # 8-byte Spill - mov rax, rcx + mov qword ptr [rsp + 184], r15 # 8-byte Spill + mov rax, rbx + or rax, 672 + mov r13, rax + mov qword ptr [rsp + 112], rax # 8-byte Spill + mov r14, rbx + or r14, 704 + mov qword ptr [rsp + 192], r14 # 8-byte Spill + mov rax, rbx or rax, 736 - mov qword ptr [rsp + 192], rax # 8-byte Spill - mov r8, rcx - or r8, 768 - mov qword ptr [rsp + 120], r8 # 8-byte Spill - mov rax, rcx - or rax, 800 - mov qword ptr [rsp + 152], rax # 8-byte Spill - mov r9, rcx + mov qword ptr [rsp + 80], rax # 8-byte Spill + mov r11, rbx + or r11, 768 + mov qword ptr [rsp + 160], r11 # 8-byte Spill + mov r10, rbx + or r10, 800 + mov qword ptr [rsp + 256], r10 # 8-byte Spill + mov r9, rbx or r9, 832 - mov qword ptr [rsp + 88], r9 # 8-byte Spill - mov rdi, rcx - or rdi, 864 - mov qword ptr [rsp + 176], rdi # 8-byte Spill - mov rdx, rcx - or rdx, 896 - mov qword ptr [rsp + 160], rdx # 8-byte Spill - mov r10, rcx - or r10, 928 - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov rax, rcx - mov qword ptr [rsp + 232], rcx # 8-byte Spill + mov qword ptr [rsp + 40], r9 # 8-byte Spill + mov rdx, rbx + or rdx, 864 + mov qword ptr [rsp + 208], rdx # 8-byte Spill + mov rsi, rbx + mov rcx, rbx + mov qword ptr [rsp + 224], rbx # 8-byte Spill + or rsi, 896 + mov qword ptr [rsp + 200], rsi # 8-byte Spill + mov r8, rbx + or r8, 928 + mov qword ptr [rsp + 88], r8 # 8-byte Spill + mov rax, rbx or rax, 960 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 208], rcx # 8-byte Spill - vpinsrb xmm9, xmm0, byte ptr [rsi + r13], 1 - mov qword ptr [rsp + 80], r11 # 8-byte Spill - vpinsrb xmm0, xmm9, byte ptr [rsi + r11], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 6 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 8 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 1 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 2 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 3 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 5 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 6 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 10 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 12 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 13 + mov qword ptr [rsp + 96], rcx # 8-byte Spill mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 14 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 15 + vpinsrb xmm9, xmm0, byte ptr [rdi + rbx], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 6 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 1 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 2 + mov r10, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 3 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 4 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 6 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 8 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 9 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 10 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 11 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 13 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 14 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 15 vinserti128 ymm0, ymm3, xmm0, 1 vpminub ymm3, ymm14, ymm0 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 1], 2 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 3 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 4 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 1], 5 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 1], 7 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 9 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 10 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 11 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 2 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 3 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 4 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 5 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 6 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 7 mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 12 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 13 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 8 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 9 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 10 mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rsi + r10 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 3 - mov r10, r15 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 4 - mov r13, r8 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 10 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 11 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 12 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 13 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 14 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r15 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 4 + mov r10, r8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 5 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 vpcmpeqb ymm0, ymm0, ymm3 vmovdqa ymmword ptr [rsp + 1280], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 1], 14 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 1], 15 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 1], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm10, edi + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm10, eax + mov r14, qword ptr [rsp + 16] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 448] # 16-byte Reload - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 2], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 2 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 3 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 2], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 5 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 2], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 1 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 2 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 2], 7 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 8 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 10 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 11 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 12 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 6 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 7 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 10 mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 15 - mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 14 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 15 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload vmovdqa xmm3, xmmword ptr [rsp + 416] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 2], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 2], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 2], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 2], 5 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 6 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 2], 7 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 2], 8 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 2], 9 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 10 - mov rbx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 11 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 2], 12 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + r8 + 3], 1 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 2 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 3], 4 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 7 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 9 - mov r9, r15 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 2], 1 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 4 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 5 + mov rax, rbx + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 6 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 2], 7 mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 12 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 13 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 14 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 3], 2 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 3], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 3], 7 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 3], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 3], 9 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 8 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 9 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 2], 11 + mov r12, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 2], 12 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 13 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 14 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r14 + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 2 + mov r14, r15 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 3 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 4 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 7 + mov r11, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 8 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 9 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 10 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 11 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 12 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 13 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rcx + 3], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 2 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 3 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 4 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 8 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 9 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 3], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 14 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 15 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm8, edi + vpinsrb xmm0, xmm5, byte ptr [rdi + r12 + 3], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm11, edi + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm0, xmmword ptr [rsp + 512] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 1 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 4], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 4], 3 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 4], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 5 - mov r8, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 6 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 4], 7 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 4], 9 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 4], 10 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 4], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 4], 12 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 4], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 14 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 4 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 5 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 8 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 10 mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 12 + mov r10, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 15 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm13, byte ptr [rdi + r9 + 4], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 4 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 5 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 6 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 7 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 4], 10 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm13, byte ptr [rsi + rax + 4], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 4], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 4], 5 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 4], 6 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 7 - mov rcx, r10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 11 + mov r13, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 4], 12 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 13 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 14 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 15 + vpinsrb xmm4, xmm15, byte ptr [rdi + r12 + 5], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 9 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 10 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 11 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 2 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 3 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 6 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 7 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 5], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 13 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 4], 14 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 15 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm15, byte ptr [rsi + rax + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 5], 2 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 4 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 5], 6 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 8 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 11 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 5], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 14 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 15 - mov r11, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + r11 + 5], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 2 - mov r9, r14 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 6 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 5], 8 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 5], 9 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 5], 10 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 10 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r9 + 5], 1 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 2 mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 5], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 6 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 5], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 5], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 5], 13 vinserti128 ymm13, ymm3, xmm0, 1 - vpinsrb xmm0, xmm5, byte ptr [rsi + r10 + 5], 14 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 10] - vmovd xmm3, edi - mov r13, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 5], 15 + vpinsrb xmm0, xmm5, byte ptr [rdi + rdx + 5], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 5], 15 vinserti128 ymm15, ymm0, xmm4, 1 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 10] - vmovd xmm4, edi - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rsi + rax + 6], 1 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 6], 2 - mov r8, r12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 6], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 6], 5 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 6 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 6], 7 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 8 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 6], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 10 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 12 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 14 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 6], 15 - vpinsrb xmm5, xmm7, byte ptr [rsi + r11 + 6], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 6], 2 - mov r11, r14 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 5 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 6], 6 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 7 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 6], 8 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 9 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 10 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 13 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 14 - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 6], 15 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 7], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 5 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 7], 7 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 9 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 10 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 11 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 13 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 7], 15 - mov r15, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 7], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 7], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 4 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 7], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 7], 8 - mov r14, r10 + vpinsrb xmm0, xmm12, byte ptr [rdi + rax + 6], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 9 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 10 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 2 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 3 + mov r11, r12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 5 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 7 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 8 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 10 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 11 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 14 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 15 + vpinsrb xmm5, xmm7, byte ptr [rdi + r9 + 6], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 2 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 4 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 5 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 7 + mov r14, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 8 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 9 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 10 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 11 + mov rbx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 12 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 13 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 14 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 15 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 4 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 7], 10 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 12 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 13 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 7], 1 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 2 + mov r8, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 7], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 4 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov r11, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 15 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm0, edi + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm0, eax vinserti128 ymm1, ymm1, xmm2, 1 vmovdqa ymmword ptr [rsp + 1248], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm1, edi - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm9, byte ptr [rsi + r8 + 8], 1 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 8], 2 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 5 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 8], 6 - mov r11, r12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 8], 7 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 8], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 8], 9 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 8], 10 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 8], 11 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov r10, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm9, byte ptr [rdi + r10 + 8], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 8], 2 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 8], 3 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 8], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 8], 5 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 8], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 7 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 12 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 10 + mov r9, r15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 8], 11 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 8], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 14 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 8], 15 - mov rcx, r15 - vpinsrb xmm5, xmm10, byte ptr [rsi + r15 + 8], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 2 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 5 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 6 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 8], 8 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 8], 9 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 10 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 11 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 8], 12 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 13 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 14 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 8], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + rax + 8], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 3 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 8 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 9 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 10 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 12 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 13 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 14 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 15 vinserti128 ymm2, ymm5, xmm2, 1 vpminub ymm5, ymm14, ymm2 - vpinsrb xmm6, xmm8, byte ptr [rsi + r8 + 9], 1 - vpinsrb xmm6, xmm6, byte ptr [rsi + r9 + 9], 2 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 3 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r15 + 9], 4 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rsi + r10 + 9], 6 - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 7 - vpinsrb xmm6, xmm6, byte ptr [rsi + r12 + 9], 8 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 9 - vpinsrb xmm6, xmm6, byte ptr [rsi + r13 + 9], 10 - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 11 + vpinsrb xmm6, xmm8, byte ptr [rdi + r10 + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 4 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 5 + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 9], 6 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 7 mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 12 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r9 + 9], 13 - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 14 - mov r12, rax - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 15 - vpinsrb xmm7, xmm11, byte ptr [rsi + rcx + 9], 1 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 9], 2 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 5 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 9], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 7 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 9], 9 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 8 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 10 + mov r10, rdx + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 12 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 13 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 14 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 15 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rsi + 9], 1 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 2 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 4 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 5 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 9 + mov rsi, r12 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 11 mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 12 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 14 + mov r12, rcx vpcmpeqb ymm2, ymm2, ymm5 vmovdqa ymmword ptr [rsp + 1216], ymm2 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm2, edi + vpinsrb xmm5, xmm7, byte ptr [rdi + r11 + 9], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm2, eax vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1184], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 1 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax + mov r11, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 2 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 4 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 6 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 2 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 3 - mov r13, r15 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 10], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 5 - mov r14, r10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 10], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 10], 7 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 10], 8 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 10], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 10], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 10], 11 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 10], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 13 - mov r9, r12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 10], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 10], 15 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 10], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 10], 2 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 10], 4 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 10], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 6 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 7 - mov r8, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 10], 8 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 9 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 10 - mov rbx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 11 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 12 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 10], 13 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 10], 14 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 10], 15 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 11], 1 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 11], 2 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 11], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 11], 4 - mov rbx, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 11], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 11], 6 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 11], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 11], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 11], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 11], 10 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 11], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 11], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 10 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 4 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 5 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 6 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 7 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 8 + mov r15, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 10 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 11 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 10], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 14 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 11], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 11], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 11], 3 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 11], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 5 + mov r9, rbx + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 11], 6 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 7 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 11], 8 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 9 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 11], 11 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 12 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 13 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 11], 14 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 15 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 1 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 6 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 11], 9 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 11], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 11], 14 - mov r10, r9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 11], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 10 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 11], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 5 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 6 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 11], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 8 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 11], 9 - mov r8, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 10 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 11], 11 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 11], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1152], ymm3 # 32-byte Spill - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 11], 14 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 13] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 11], 15 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 13] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm2, byte ptr [rsi + rdi + 12], 1 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 12], 2 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 12], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 12], 4 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 12], 5 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 12], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 12], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 12], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 12], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 12], 10 - mov r9, r13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 12], 11 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 12], 12 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 12], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 12], 14 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 12], 15 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rsi + rcx + 12], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 12], 2 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 6 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 7 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 8 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm0, eax + mov r15, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm2, byte ptr [rdi + r15 + 12], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 12], 10 - mov r10, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 12], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 12], 12 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 12], 13 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 12], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 2 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 15 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 5 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 13], 6 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 8 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 12], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 12], 5 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 12], 6 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 12], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 12], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 10 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 12], 11 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 12], 12 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 13], 12 - mov rbx, r13 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 12], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 15 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + rax + 12], 1 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 2 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 3 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 13], 5 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 13], 7 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 13], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 4 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 7 + mov r14, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 8 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 9 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 10 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 12 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 13 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 14 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 13], 8 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 13], 11 - mov r9, r10 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 13], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 13], 12 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 14 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 13], 2 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 13], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 13], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 13], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 13], 8 + mov r11, r14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 13], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 10 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 13], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 13], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1088], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 15 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 14] - vmovd xmm1, edi + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 13], 15 + mov r15, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r15 + 14] + vmovd xmm1, eax vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 14] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 2 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 14], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 4 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 14], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 6 - mov r15, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 7 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 9 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 10 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 14], 12 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 14], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 14], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 14], 15 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 2 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 3 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 14], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 5 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 6 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 14], 8 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 14], 9 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 14], 11 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 14], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 14], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 14], 15 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 15] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 1 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 15], 3 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 15], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 15], 5 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 7 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 8 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 11 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 7 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 12 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 9 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 10 mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 15], 15 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 15] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 2 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 15], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 15], 4 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 15], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 13 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 4 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 5 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 9 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 14], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 15 + movzx eax, byte ptr [rdi + r15 + 15] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 4 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 6 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 7 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 9 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 15], 10 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 15], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 15], 12 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 15], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 15], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 15], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 7 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 8 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 10 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 15], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 12 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 14 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 15] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 14 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 16] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 16], 2 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 16], 4 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 5 - mov r13, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 16], 7 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 16], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 11 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 12 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 14 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 15 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 16] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 16], 3 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 16], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 6 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 16], 7 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rsi + 16] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 1 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 16], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 3 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 9 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 11 + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 15 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r9 + 16] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 1 + mov r15, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 8 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 16], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 5 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 6 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 16], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 9 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 11 mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 16], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 14 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 15 + movzx eax, byte ptr [rdi + rsi + 17] + vmovd xmm2, eax mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 14 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 16], 15 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + r15 + 17] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 1 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 2 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 4 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 17], 6 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 8 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 17], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 10 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 17], 11 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 12 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 13 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 15 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + r12 + 17] - vmovd xmm3, edi - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 1 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 2 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 3 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 4 - mov r8, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 17], 5 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 17], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 17], 9 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 10 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 6 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 7 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 10 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 12 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 15 + movzx eax, byte ptr [rdi + r9 + 17] + vmovd xmm3, eax + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 4 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 17], 7 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 11 + mov r12, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 13 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vpinsrb xmm1, xmm3, byte ptr [rsi + r11 + 17], 15 + vpinsrb xmm1, xmm3, byte ptr [rdi + r13 + 17], 15 vpminub ymm3, ymm14, ymm0 vpcmpeqb ymm0, ymm0, ymm3 vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill vinserti128 ymm0, ymm1, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r15 + 18] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 1 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 2 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 18], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 4 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 18], 5 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 6 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 18] + vmovd xmm0, eax + mov r15, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 18], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 2 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 18], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 10 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 12 + mov rdx, r14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 13 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 14 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 18], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 2 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 5 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 6 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 18], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 18], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 18], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 8 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 9 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 14 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 15 - movzx edi, byte ptr [rsi + r12 + 18] - vmovd xmm1, edi + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 10 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 1 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 18], 2 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 18], 5 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 18], 6 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 7 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 14 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 15 + movzx eax, byte ptr [rdi + rcx + 19] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 3 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 5 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 19], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 7 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 8 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 10 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 11 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 18], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 18], 13 - mov r15, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 18], 14 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 15 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 19] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 2 - mov r13, r14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 19], 3 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 19], 5 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 19], 6 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 7 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 11 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 19], 12 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 14 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 15 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 19] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 19], 2 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 6 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 19], 8 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 9 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 19], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 15 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r15 + 19] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 4 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 19], 6 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 19], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 8 + mov rbx, r9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 11 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 12 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rsi + rcx + 19], 15 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rcx + 19], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 20] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 1 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 20] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 6 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 20], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 20], 6 - mov r15, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 20], 7 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 20], 8 - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 7 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 8 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 9 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 10 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 11 + mov r11, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 20], 12 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 10 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 20], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 20], 12 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 20], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 13 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 14 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 15 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + r8 + 20] - vmovd xmm1, edi - mov r10, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 20], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 2 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 20], 3 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 5 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 6 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 8 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 9 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 10 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 14 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 15 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 1 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 21], 2 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 3 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 4 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 5 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 21], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 21], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 21], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 21], 11 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 21], 13 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 21], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 15 - mov r9, rax - movzx edi, byte ptr [rsi + r8 + 21] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 21], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 15 + movzx eax, byte ptr [rdi + r15 + 20] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 20], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 13 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 21] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 1 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 3 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 21], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 6 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 7 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 21], 12 + mov r14, r11 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 14 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 15 + mov r11, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r11 + 21] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 1 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 4 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 12 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 5 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 7 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 21], 8 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 9 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 21], 10 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 14 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 14 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 15 vinserti128 ymm11, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 22], 2 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 3 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 5 - mov r13, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 22], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 7 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 22], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 22], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 11 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 22], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 22], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 22], 15 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 22] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 1 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 2 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 22], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 5 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 6 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 22], 8 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 22], 10 - mov r12, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 22], 11 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 12 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 2 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 22], 4 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 22], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 7 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 14 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 15 - movzx edi, byte ptr [rsi + rcx + 23] - vmovd xmm2, edi - mov r11, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 23], 1 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 2 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 4 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 23], 8 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 10 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 23], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 14 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 15 - mov r10, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + r10 + 23] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 23], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 23], 3 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 23], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 5 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 23], 6 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 23], 7 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 23], 8 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 9 - mov r9, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 23], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 11 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 23], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 13 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rax + 23], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 24] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 24], 1 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 2 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 3 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 4 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 5 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 6 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 24], 7 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 8 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 11 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 12 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 24], 15 - movzx edi, byte ptr [rsi + r10 + 24] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 1 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 24], 2 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 4 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 24], 8 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 10 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 12 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 15 + movzx eax, byte ptr [rdi + r11 + 22] + vmovd xmm1, eax + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 2 mov r8, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 24], 12 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 15 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + r9 + 25] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 5 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 7 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 22], 10 + mov r10, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 22], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + mov r11, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 14 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 15 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rsi + 23] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 5 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 9 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 10 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 14 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 4 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 5 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 6 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 23], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 12 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 14 + vinserti128 ymm0, ymm1, xmm0, 1 + vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 4 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 25], 5 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 25], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 25], 7 + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 23], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill + movzx eax, byte ptr [rdi + rsi + 24] + vmovd xmm0, eax + mov r11, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 3 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 6 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 7 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 8 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 10 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 11 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 24], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm1, eax + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 5 + mov rbx, r14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 7 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 9 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 10 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 13 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 14 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 7 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 10 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 11 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 15 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r12 + 25] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 1 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 3 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 5 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 6 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 9 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 25], 10 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 11 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 12 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 25], 14 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 15 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 25] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 25], 2 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 5 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 25], 6 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 7 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 25], 8 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 9 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 25], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 25], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 8 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 11 + mov r15, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 13 vinserti128 ymm0, ymm1, xmm0, 1 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm3, byte ptr [rsi + rcx + 25], 14 + vpinsrb xmm1, xmm3, byte ptr [rdi + r14 + 25], 14 vpminub ymm3, ymm14, ymm0 vpcmpeqb ymm0, ymm0, ymm3 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rcx + 25], 15 + mov rdx, r9 + vpinsrb xmm0, xmm1, byte ptr [rdi + r9 + 25], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 384], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r9 + 26] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 1 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 2 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 3 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 26], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 7 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 8 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 26], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 11 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 26], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 14 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 15 mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 26] - vmovd xmm1, edi + movzx eax, byte ptr [rdi + rax + 26] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 1 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 2 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 13 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 15 + movzx eax, byte ptr [rdi + r12 + 26] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 26], 4 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 26], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 10 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 1 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 26], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 12 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 15 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r12 + 27] + vmovd xmm2, eax + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 3 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 4 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 5 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 6 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 11 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 12 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 27], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 15 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 27] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 1 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 2 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 3 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 6 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 26], 8 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 26], 9 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 10 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 11 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 15 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + r12 + 27] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 1 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 27], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 3 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 4 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 27], 5 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 6 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 7 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 8 - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 27], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 10 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 27], 12 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 15 - mov r9, rdx - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 27] - vmovd xmm3, edi - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 27], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 27], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 27], 4 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 5 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 6 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 27], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 9 - mov r15, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 10 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 11 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 12 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 13 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 14 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 4 + mov r13, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 9 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 14 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r12 + 28] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 2 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 28], 5 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 6 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 7 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 28], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 28], 9 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 10 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 11 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 28], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 13 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 28], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 15 - mov r8, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + r8 + 28] - vmovd xmm1, edi - mov r9, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 28], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 2 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 5 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 6 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 28], 8 - mov r11, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 28], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 10 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 11 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 28], 12 + movzx eax, byte ptr [rdi + r12 + 28] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 28], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 7 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 8 + mov r8, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 9 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 10 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 14 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 15 + movzx eax, byte ptr [rdi + rcx + 28] + vmovd xmm1, eax + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 1 + mov r12, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 2 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 6 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 9 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 10 + mov r10, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 11 + mov r13, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 12 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 13 + mov r9, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 14 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 29] + vmovd xmm2, eax mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 14 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 28], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 3 mov rax, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 29] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 1 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 5 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 7 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 11 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 13 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 29] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 3 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 4 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 5 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 4 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 6 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 29], 8 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 9 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 29], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 29], 12 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 29], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 29], 14 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 29], 15 - movzx edi, byte ptr [rsi + r8 + 29] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 1 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 29], 2 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 3 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 29], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 5 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 6 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 29], 7 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 29], 9 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 29], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 29], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 29], 13 - mov r15, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rsi + r15 + 29], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 8 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 12 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + r9 + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm4, byte ptr [rsi + r10 + 29], 15 + vpinsrb xmm0, xmm4, byte ptr [rdi + r15 + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 184] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 30] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 1 - movzx edi, byte ptr [rsi + r11 + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 3 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 6 - mov r11, qword ptr [rsp + 240] # 8-byte Reload + mov r10, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 30] + vmovd xmm0, eax + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 30], 1 + movzx eax, byte ptr [rdi + r10 + 31] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 31], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 - mov rax, rbx - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 31], 10 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov r14, qword ptr [rsp + 240] # 8-byte Reload mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 31], 12 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + r14 + 31], 15 - mov rdx, r8 - movzx eax, byte ptr [rsi + r8 + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + rax + 31], 15 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - mov r8, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 30], 1 - movzx eax, byte ptr [rsi + rdx + 31] + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 31], 1 - mov rax, r13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + r13 + 31], 2 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 31], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 1 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + r12 + 31], 7 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 9 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 31], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 31], 14 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 5 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + mov rax, r13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r9 + 31], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -44912,22 +46101,22 @@ comparison_greater_arr_scalar_avx2: # @comparison_greater_arr_scalar_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 368] # 8-byte Reload - vmovdqu ymmword ptr [r11 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r11 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r11 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r11 + 4*rcx], ymm1 + vmovdqu ymmword ptr [r14 + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [r14 + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [r14 + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [r14 + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 360] # 8-byte Folded Reload - jne .LBB7_53 -# %bb.54: - mov r15, qword ptr [rsp + 376] # 8-byte Reload - cmp r15, qword ptr [rsp + 360] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14d, dword ptr [rsp + 4] # 4-byte Reload - mov r12, qword ptr [rsp + 504] # 8-byte Reload - jne .LBB7_55 - jmp .LBB7_58 + jne .LBB7_73 +# %bb.74: + mov rcx, qword ptr [rsp + 376] # 8-byte Reload + cmp rcx, qword ptr [rsp + 360] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 248] # 8-byte Reload + mov r13d, dword ptr [rsp + 4] # 4-byte Reload + mov r11, qword ptr [rsp + 504] # 8-byte Reload + jne .LBB7_75 + jmp .LBB7_78 .Lfunc_end7: .size comparison_greater_arr_scalar_avx2, .Lfunc_end7-comparison_greater_arr_scalar_avx2 # -- End function @@ -44963,71 +46152,85 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 and rsp, -32 sub rsp, 1312 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov r11, rcx + mov r14, r8 + mov r12, rcx cmp edi, 6 - jg .LBB8_13 + jg .LBB8_18 # %bb.1: cmp edi, 3 - jle .LBB8_28 + jle .LBB8_35 # %bb.2: cmp edi, 4 - je .LBB8_51 + je .LBB8_57 # %bb.3: cmp edi, 5 - je .LBB8_59 + je .LBB8_70 # %bb.4: cmp edi, 6 - jne .LBB8_179 + jne .LBB8_194 # %bb.5: mov r13d, dword ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_9 + je .LBB8_11 # %bb.6: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_9 +# %bb.7: + movsxd rsi, r9d + mov rax, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_7: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rdx], r13d - lea rdx, [rdx + 4] - sbb esi, esi - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB8_8: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp dword ptr [rcx], r13d + sbb r11d, r11d + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r12 + movzx r9d, byte ptr [r12 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_7 -# %bb.8: - add r11, 1 + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add rsi, 1 + mov rcx, rdx + add rax, -1 + jne .LBB8_8 .LBB8_9: - sar r15, 5 - cmp r10, 32 - jl .LBB8_115 + sub r14, r8 + je .LBB8_194 # %bb.10: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill - mov qword ptr [rsp + 232], r11 # 8-byte Spill + add r12, 1 +.LBB8_11: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_15 +# %bb.12: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_11: # =>This Inner Loop Header: Depth=1 +.LBB8_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill cmp r13d, dword ptr [rdx] seta byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 4] @@ -45035,21 +46238,21 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13d, dword ptr [rdx + 8] seta r14b cmp r13d, dword ptr [rdx + 12] - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 16] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 20] - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 24] seta al cmp r13d, dword ptr [rdx + 28] seta r11b cmp r13d, dword ptr [rdx + 32] - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 36] - seta sil + seta cl cmp r13d, dword ptr [rdx + 40] - seta r8b + seta sil cmp r13d, dword ptr [rdx + 44] seta r9b cmp r13d, dword ptr [rdx + 48] @@ -45057,31 +46260,31 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13d, dword ptr [rdx + 52] seta r12b cmp r13d, dword ptr [rdx + 56] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 60] - seta cl + seta r8b cmp r13d, dword ptr [rdx + 64] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 68] - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 72] - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 76] - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 80] - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 84] - seta byte ptr [rsp + 64] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 88] - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 92] seta r15b cmp r13d, dword ptr [rdx + 96] seta byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 100] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 104] seta byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 104] + seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 108] seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 112] @@ -45099,65 +46302,64 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 72] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b + mov r12, qword ptr [rsp + 240] # 8-byte Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 6 + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 320] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -45168,93 +46370,117 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, cl - movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - shl al, 6 + mov ecx, eax + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 shl bl, 7 - or bl, al or bl, cl - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], bl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rdx, 128 - add rsi, 4 - mov qword ptr [rsp + 232], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB8_11 -# %bb.12: - mov r14, qword ptr [rsp + 232] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB8_116 - jmp .LBB8_179 -.LBB8_13: - cmp edi, 8 - jle .LBB8_41 + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB8_13 # %bb.14: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_15: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.16: + or rax, 1 + cmp r14, rax + jne .LBB8_157 +# %bb.17: + xor r11d, r11d + jmp .LBB8_159 +.LBB8_18: + cmp edi, 8 + jle .LBB8_42 +# %bb.19: cmp edi, 9 - je .LBB8_70 -# %bb.15: + je .LBB8_83 +# %bb.20: cmp edi, 11 - je .LBB8_81 -# %bb.16: + je .LBB8_96 +# %bb.21: cmp edi, 12 - jne .LBB8_179 -# %bb.17: - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + jne .LBB8_194 +# %bb.22: + mov r15, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero sub r9d, eax - je .LBB8_21 -# %bb.18: - movsxd rax, r9d + je .LBB8_28 +# %bb.23: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_26 +# %bb.24: + movsxd rsi, r9d + vmovq xmm0, r15 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_19: # =>This Inner Loop Header: Depth=1 - vucomisd xmm0, qword ptr [rdx] +.LBB8_25: # =>This Inner Loop Header: Depth=1 + vucomisd xmm0, qword ptr [rcx] seta bl - add rdx, 8 + lea rdx, [rcx + 8] neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_19 -# %bb.20: - add r11, 1 -.LBB8_21: - sar r14, 5 - cmp r10, 32 - jl .LBB8_25 -# %bb.22: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 136], r14 # 8-byte Spill - mov qword ptr [rsp + 128], r14 # 8-byte Spill - mov qword ptr [rsp + 232], r11 # 8-byte Spill + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_25 +.LBB8_26: + sub r14, r8 + je .LBB8_194 +# %bb.27: + add r12, 1 +.LBB8_28: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_32 +# %bb.29: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 144], r15 # 8-byte Spill + vmovq xmm0, r15 + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_23: # =>This Inner Loop Header: Depth=1 +.LBB8_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill vucomisd xmm0, qword ptr [rdx] - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 8] seta r8b vucomisd xmm0, qword ptr [rdx + 16] @@ -45262,19 +46488,19 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 vucomisd xmm0, qword ptr [rdx + 24] seta r13b vucomisd xmm0, qword ptr [rdx + 32] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 40] - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 48] seta al vucomisd xmm0, qword ptr [rdx + 56] seta r11b vucomisd xmm0, qword ptr [rdx + 64] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 72] - seta sil + seta cl vucomisd xmm0, qword ptr [rdx + 80] - seta dil + seta sil vucomisd xmm0, qword ptr [rdx + 88] seta r9b vucomisd xmm0, qword ptr [rdx + 96] @@ -45282,31 +46508,31 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 vucomisd xmm0, qword ptr [rdx + 104] seta r12b vucomisd xmm0, qword ptr [rdx + 112] - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 120] - seta cl + seta dil vucomisd xmm0, qword ptr [rdx + 128] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 136] - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 144] - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 152] - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 160] - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 168] - seta byte ptr [rsp + 64] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 176] - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 184] seta r15b vucomisd xmm0, qword ptr [rdx + 192] seta byte ptr [rsp + 320] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 200] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - vucomisd xmm0, qword ptr [rdx + 208] seta byte ptr [rsp + 24] # 1-byte Folded Spill + vucomisd xmm0, qword ptr [rdx + 208] + seta byte ptr [rsp + 32] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 216] seta byte ptr [rsp + 8] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 224] @@ -45318,69 +46544,68 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 vucomisd xmm0, qword ptr [rdx + 248] seta bl add r8b, r8b - add r8b, byte ptr [rsp + 120] # 1-byte Folded Reload + add r8b, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al shl r14b, 2 or r14b, r8b - add sil, sil - add sil, byte ptr [rsp + 80] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 112] # 1-byte Folded Reload shl r13b, 3 or r13b, r14b - shl dil, 2 - or dil, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, r13b - mov r8d, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, r13b + mov r8d, ecx + mov r14, qword ptr [rsp + 240] # 8-byte Reload shl r9b, 3 - or r9b, dil - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, r8b + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, r8b shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 120] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dil, 7 + or dil, sil + or r11b, cl + or dil, r12b + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 6 + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 + or cl, al + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r14], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r14 + 1], dil + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 320] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -45391,335 +46616,162 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, cl - movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - shl al, 6 + mov ecx, eax + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 shl bl, 7 - or bl, al or bl, cl - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], bl + or bl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], bl add rdx, 256 - add rsi, 4 - mov qword ptr [rsp + 232], rsi # 8-byte Spill + add r14, 4 + mov r12, r14 add qword ptr [rsp + 128], -1 # 8-byte Folded Spill - jne .LBB8_23 -# %bb.24: - mov r11, qword ptr [rsp + 232] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14, qword ptr [rsp + 136] # 8-byte Reload -.LBB8_25: - shl r14, 5 - cmp r14, r10 - jge .LBB8_179 -# %bb.26: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB8_133 -# %bb.27: + jne .LBB8_30 +# %bb.31: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov r15, qword ptr [rsp + 144] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_32: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.33: + vmovq xmm0, r15 + or rax, 1 + cmp r14, rax + jne .LBB8_161 +# %bb.34: xor edi, edi - jmp .LBB8_135 -.LBB8_28: + jmp .LBB8_163 +.LBB8_35: cmp edi, 2 - je .LBB8_92 -# %bb.29: + je .LBB8_109 +# %bb.36: cmp edi, 3 - jne .LBB8_179 -# %bb.30: - mov r14b, byte ptr [rsi] - lea r13, [r10 + 31] - test r10, r10 - cmovns r13, r10 + jne .LBB8_194 +# %bb.37: + mov r15b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_128 -# %bb.31: - movsxd rax, r9d - mov r15, r11 - .p2align 4, 0x90 -.LBB8_32: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rdx] - lea rdx, [rdx + 1] - setg bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r15 + rsi] - xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_32 -# %bb.33: - add r15, 1 - sar r13, 5 - cmp r10, 32 - jl .LBB8_129 -.LBB8_34: - cmp r13, 32 - mov dword ptr [rsp + 4], r14d # 4-byte Spill - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 360], r13 # 8-byte Spill - jb .LBB8_37 -# %bb.35: - mov rax, r13 - shl rax, 5 - add rax, rdx - cmp r15, rax - jae .LBB8_180 -# %bb.36: - lea rax, [r15 + 4*r13] - cmp rdx, rax - jae .LBB8_180 -.LBB8_37: - xor eax, eax - mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rdx - mov qword ptr [rsp + 352], r15 # 8-byte Spill -.LBB8_38: - sub r13, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 128], r13 # 8-byte Spill + je .LBB8_127 +# %bb.38: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_129 +# %bb.39: + movsxd rsi, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB8_39: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp r14b, byte ptr [r12] - setg byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14b, byte ptr [r12 + 1] - setg r10b - cmp r14b, byte ptr [r12 + 2] - setg bl - cmp r14b, byte ptr [r12 + 3] - setg r13b - cmp r14b, byte ptr [r12 + 4] - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14b, byte ptr [r12 + 5] - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14b, byte ptr [r12 + 6] - setg al - cmp r14b, byte ptr [r12 + 7] - setg r12b - cmp r14b, byte ptr [rcx + 8] - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 9] - setg sil - cmp r14b, byte ptr [rcx + 10] - setg dil - cmp r14b, byte ptr [rcx + 11] - setg r9b - cmp r14b, byte ptr [rcx + 12] - setg r11b - cmp r14b, byte ptr [rcx + 13] - setg r15b - cmp r14b, byte ptr [rcx + 14] - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 15] - setg r8b - cmp r14b, byte ptr [rcx + 16] - setg byte ptr [rsp + 256] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 17] - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 18] - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 19] - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 20] - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 21] - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 22] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 23] - setg r14b - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 24] - setg byte ptr [rsp + 232] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 25] - setg byte ptr [rsp + 56] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 26] - setg byte ptr [rsp + 64] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 27] - setg byte ptr [rsp + 32] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 28] - setg byte ptr [rsp + 24] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 29] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 30] - setg byte ptr [rsp + 320] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp dl, byte ptr [rcx + 31] +.LBB8_40: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r15b, byte ptr [rdx] setg dl - add r10b, r10b - add r10b, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 6 - shl r12b, 7 - or r12b, al - shl bl, 2 - or bl, r10b - add sil, sil - add sil, byte ptr [rsp + 120] # 1-byte Folded Reload - shl r13b, 3 - or r13b, bl - shl dil, 2 - or dil, sil - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 4 - or bl, r13b - mov esi, ebx - shl r9b, 3 - or r9b, dil - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r11b, 4 - or r11b, r9b - shl r15b, 5 - or r15b, r11b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r12b, bl - or r8b, r15b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 256] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 2 - or bl, al - mov esi, ebx - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - mov rsi, qword ptr [rsp + 352] # 8-byte Reload - mov byte ptr [rsi], r12b - movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r8b - or r14b, bl - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 232] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 4] # 4-byte Reload - mov byte ptr [rsi + 3], dl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 352], rsi # 8-byte Spill - add qword ptr [rsp + 128], -1 # 8-byte Folded Spill - jne .LBB8_39 -# %bb.40: - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r13, qword ptr [rsp + 360] # 8-byte Reload - jmp .LBB8_130 -.LBB8_41: + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r12 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB8_40 +# %bb.41: + sub r14, r8 + jne .LBB8_130 + jmp .LBB8_194 +.LBB8_42: cmp edi, 7 - je .LBB8_104 -# %bb.42: - cmp edi, 8 - jne .LBB8_179 + je .LBB8_114 # %bb.43: + cmp edi, 8 + jne .LBB8_194 +# %bb.44: mov r13, qword ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_47 -# %bb.44: - movsxd rax, r9d + je .LBB8_50 +# %bb.45: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_48 +# %bb.46: + movsxd rsi, r9d + mov rax, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_45: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rdx], r13 - lea rdx, [rdx + 8] - sbb r9d, r9d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor r9b, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB8_47: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp qword ptr [rcx], r13 + sbb r11d, r11d + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r12 + movzx r9d, byte ptr [r12 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r9b - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_45 -# %bb.46: - add r11, 1 -.LBB8_47: - sar r15, 5 - cmp r10, 32 - jl .LBB8_118 -# %bb.48: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add rsi, 1 + mov rcx, rdx + add rax, -1 + jne .LBB8_47 +.LBB8_48: + sub r14, r8 + je .LBB8_194 +# %bb.49: + add r12, 1 +.LBB8_50: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_54 +# %bb.51: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_49: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 232], r11 # 8-byte Spill +.LBB8_52: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill cmp r13, qword ptr [rdx] seta byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 8] @@ -45727,21 +46779,21 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13, qword ptr [rdx + 16] seta r14b cmp r13, qword ptr [rdx + 24] - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 32] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 40] - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 48] seta al cmp r13, qword ptr [rdx + 56] seta r11b cmp r13, qword ptr [rdx + 64] - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 72] - seta sil + seta cl cmp r13, qword ptr [rdx + 80] - seta r8b + seta sil cmp r13, qword ptr [rdx + 88] seta r9b cmp r13, qword ptr [rdx + 96] @@ -45749,31 +46801,31 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13, qword ptr [rdx + 104] seta r12b cmp r13, qword ptr [rdx + 112] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 120] - seta cl + seta r8b cmp r13, qword ptr [rdx + 128] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 136] - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 144] - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 152] - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 160] - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 168] - seta byte ptr [rsp + 64] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 176] - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 184] seta r15b cmp r13, qword ptr [rdx + 192] seta byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 200] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 208] seta byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 208] + seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 216] seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 224] @@ -45791,67 +46843,64 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 72] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b + mov r12, qword ptr [rsp + 240] # 8-byte Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov edi, eax - mov rax, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rax], r11b - mov r11, qword ptr [rsp + 232] # 8-byte Reload - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 6 + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, al - mov byte ptr [r11 + 1], cl - or r15b, dil - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 320] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -45871,69 +46920,90 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 shl bl, 7 or bl, cl or bl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], bl + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rdx, 256 - add r11, 4 - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB8_49 -# %bb.50: - mov r14, r11 - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB8_119 - jmp .LBB8_179 -.LBB8_51: + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB8_52 +# %bb.53: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_54: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.55: + or rax, 1 + cmp r14, rax + jne .LBB8_165 +# %bb.56: + xor r11d, r11d + jmp .LBB8_167 +.LBB8_57: movzx r13d, word ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_55 -# %bb.52: - movsxd rax, r9d + je .LBB8_63 +# %bb.58: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_61 +# %bb.59: + movsxd rsi, r9d + mov r15, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_53: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rdx], r13w - lea rdx, [rdx + 2] - sbb esi, esi - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB8_60: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp word ptr [rcx], r13w + sbb r11d, r11d + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov rax, r12 + movzx r9d, byte ptr [r12 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_53 -# %bb.54: - add r11, 1 -.LBB8_55: - sar r15, 5 - cmp r10, 32 - jl .LBB8_121 -# %bb.56: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r15 # 8-byte Spill - mov qword ptr [rsp + 232], r11 # 8-byte Spill + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add rsi, 1 + mov rcx, rdx + add r15, -1 + jne .LBB8_60 +.LBB8_61: + sub r14, r8 + je .LBB8_194 +# %bb.62: + add r12, 1 +.LBB8_63: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_67 +# %bb.64: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_57: # =>This Inner Loop Header: Depth=1 +.LBB8_65: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill cmp r13w, word ptr [rdx] seta al cmp r13w, word ptr [rdx + 2] @@ -45941,21 +47011,21 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13w, word ptr [rdx + 4] seta r14b cmp r13w, word ptr [rdx + 6] - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 8] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 10] - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 12] - seta byte ptr [rsp + 128] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 14] seta r11b cmp r13w, word ptr [rdx + 16] - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 18] - seta sil + seta cl cmp r13w, word ptr [rdx + 20] - seta r8b + seta sil cmp r13w, word ptr [rdx + 22] seta r9b cmp r13w, word ptr [rdx + 24] @@ -45963,31 +47033,31 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13w, word ptr [rdx + 26] seta r12b cmp r13w, word ptr [rdx + 28] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 30] - seta cl + seta r8b cmp r13w, word ptr [rdx + 32] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 34] - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 36] - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 38] - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 40] - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 42] - seta byte ptr [rsp + 64] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 44] - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 46] seta r15b cmp r13w, word ptr [rdx + 48] seta byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 50] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 52] seta byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 52] + seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 54] seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 56] @@ -46000,71 +47070,70 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 seta bl add dil, dil or dil, al - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 72] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b + mov r12, qword ptr [rsp + 240] # 8-byte Reload + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 6 + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 320] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -46075,79 +47144,100 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, cl - movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - shl al, 6 + mov ecx, eax + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 shl bl, 7 - or bl, al or bl, cl - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], bl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rdx, 64 - add rsi, 4 - mov qword ptr [rsp + 232], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB8_57 -# %bb.58: - mov r14, qword ptr [rsp + 232] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB8_122 - jmp .LBB8_179 -.LBB8_59: + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB8_65 +# %bb.66: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_67: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.68: + or rax, 1 + cmp r14, rax + jne .LBB8_169 +# %bb.69: + xor r11d, r11d + jmp .LBB8_171 +.LBB8_70: movzx r13d, word ptr [rsi] - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_63 -# %bb.60: - movsxd rax, r9d + je .LBB8_76 +# %bb.71: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_74 +# %bb.72: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_61: # =>This Inner Loop Header: Depth=1 - cmp r13w, word ptr [rdx] - lea rdx, [rdx + 2] +.LBB8_73: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r13w, word ptr [rcx] setg bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r11 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_61 -# %bb.62: - add r11, 1 -.LBB8_63: - sar r14, 5 - cmp r10, 32 - jl .LBB8_67 -# %bb.64: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 136], r14 # 8-byte Spill - mov qword ptr [rsp + 232], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_73 +.LBB8_74: + sub r14, r8 + je .LBB8_194 +# %bb.75: + add r12, 1 +.LBB8_76: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_80 +# %bb.77: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_65: # =>This Inner Loop Header: Depth=1 +.LBB8_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill cmp r13w, word ptr [rdx] setg byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 2] @@ -46155,21 +47245,21 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13w, word ptr [rdx + 4] setg r14b cmp r13w, word ptr [rdx + 6] - setg byte ptr [rsp + 120] # 1-byte Folded Spill + setg byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 8] - setg byte ptr [rsp + 104] # 1-byte Folded Spill + setg byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 10] - setg byte ptr [rsp + 56] # 1-byte Folded Spill + setg byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 12] setg al cmp r13w, word ptr [rdx + 14] setg r11b cmp r13w, word ptr [rdx + 16] - setg byte ptr [rsp + 72] # 1-byte Folded Spill + setg byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 18] - setg sil + setg cl cmp r13w, word ptr [rdx + 20] - setg r8b + setg sil cmp r13w, word ptr [rdx + 22] setg r9b cmp r13w, word ptr [rdx + 24] @@ -46177,31 +47267,31 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13w, word ptr [rdx + 26] setg r12b cmp r13w, word ptr [rdx + 28] - setg byte ptr [rsp + 80] # 1-byte Folded Spill + setg byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 30] - setg cl + setg r8b cmp r13w, word ptr [rdx + 32] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 34] - setg byte ptr [rsp + 88] # 1-byte Folded Spill + setg byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 36] - setg byte ptr [rsp + 96] # 1-byte Folded Spill + setg byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 38] - setg byte ptr [rsp + 112] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 40] - setg byte ptr [rsp + 48] # 1-byte Folded Spill + setg byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 42] - setg byte ptr [rsp + 64] # 1-byte Folded Spill + setg byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 44] - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 16] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 46] setg r15b cmp r13w, word ptr [rdx + 48] setg byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 50] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 52] setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 52] + setg byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 54] setg byte ptr [rsp + 8] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 56] @@ -46219,65 +47309,64 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 72] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b + mov r12, qword ptr [rsp + 240] # 8-byte Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 6 + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 320] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -46288,88 +47377,100 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, cl - movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - shl al, 6 + mov ecx, eax + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 shl bl, 7 - or bl, al or bl, cl - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], bl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rdx, 64 - add rsi, 4 - mov qword ptr [rsp + 232], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB8_65 -# %bb.66: - mov r11, qword ptr [rsp + 232] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14, qword ptr [rsp + 144] # 8-byte Reload -.LBB8_67: - shl r14, 5 - cmp r14, r10 - jge .LBB8_179 -# %bb.68: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB8_137 -# %bb.69: + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB8_78 +# %bb.79: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_80: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.81: + or rax, 1 + cmp r14, rax + jne .LBB8_174 +# %bb.82: xor edi, edi - jmp .LBB8_139 -.LBB8_70: + jmp .LBB8_176 +.LBB8_83: mov r13, qword ptr [rsi] - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_74 -# %bb.71: - movsxd rax, r9d + je .LBB8_89 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_87 +# %bb.85: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_72: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] - lea rdx, [rdx + 8] +.LBB8_86: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r13, qword ptr [rcx] setg bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r11 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_72 -# %bb.73: - add r11, 1 -.LBB8_74: - sar r14, 5 - cmp r10, 32 - jl .LBB8_78 -# %bb.75: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 136], r14 # 8-byte Spill - mov qword ptr [rsp + 232], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_86 +.LBB8_87: + sub r14, r8 + je .LBB8_194 +# %bb.88: + add r12, 1 +.LBB8_89: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_93 +# %bb.90: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_76: # =>This Inner Loop Header: Depth=1 +.LBB8_91: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill cmp r13, qword ptr [rdx] setg byte ptr [rsp + 128] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 8] @@ -46377,21 +47478,21 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13, qword ptr [rdx + 16] setg r14b cmp r13, qword ptr [rdx + 24] - setg byte ptr [rsp + 120] # 1-byte Folded Spill + setg byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 32] - setg byte ptr [rsp + 104] # 1-byte Folded Spill + setg byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 40] - setg byte ptr [rsp + 56] # 1-byte Folded Spill + setg byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 48] setg al cmp r13, qword ptr [rdx + 56] setg r11b cmp r13, qword ptr [rdx + 64] - setg byte ptr [rsp + 72] # 1-byte Folded Spill + setg byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 72] - setg sil + setg cl cmp r13, qword ptr [rdx + 80] - setg r8b + setg sil cmp r13, qword ptr [rdx + 88] setg r9b cmp r13, qword ptr [rdx + 96] @@ -46399,31 +47500,31 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 cmp r13, qword ptr [rdx + 104] setg r12b cmp r13, qword ptr [rdx + 112] - setg byte ptr [rsp + 80] # 1-byte Folded Spill + setg byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 120] - setg cl + setg r8b cmp r13, qword ptr [rdx + 128] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 136] - setg byte ptr [rsp + 88] # 1-byte Folded Spill + setg byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 144] - setg byte ptr [rsp + 96] # 1-byte Folded Spill + setg byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 152] - setg byte ptr [rsp + 112] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 160] - setg byte ptr [rsp + 48] # 1-byte Folded Spill + setg byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 168] - setg byte ptr [rsp + 64] # 1-byte Folded Spill + setg byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 176] - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 16] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 184] setg r15b cmp r13, qword ptr [rdx + 192] setg byte ptr [rsp + 320] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 200] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 208] setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 208] + setg byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 216] setg byte ptr [rsp + 8] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 224] @@ -46441,65 +47542,64 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 72] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b + mov r12, qword ptr [rsp + 240] # 8-byte Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 6 + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 320] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -46510,142 +47610,157 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, cl - movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - shl al, 6 + mov ecx, eax + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 shl bl, 7 - or bl, al or bl, cl - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], bl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rdx, 256 - add rsi, 4 - mov qword ptr [rsp + 232], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB8_76 -# %bb.77: - mov r11, qword ptr [rsp + 232] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14, qword ptr [rsp + 144] # 8-byte Reload -.LBB8_78: - shl r14, 5 - cmp r14, r10 - jge .LBB8_179 -# %bb.79: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB8_141 -# %bb.80: + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB8_91 +# %bb.92: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_93: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.94: + or rax, 1 + cmp r14, rax + jne .LBB8_178 +# %bb.95: xor edi, edi - jmp .LBB8_143 -.LBB8_81: - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + jmp .LBB8_180 +.LBB8_96: + mov r15d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB8_85 -# %bb.82: - movsxd rax, r9d + je .LBB8_102 +# %bb.97: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_100 +# %bb.98: + movsxd rsi, r9d + vmovd xmm0, r15d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_83: # =>This Inner Loop Header: Depth=1 - vucomiss xmm0, dword ptr [rdx] +.LBB8_99: # =>This Inner Loop Header: Depth=1 + vucomiss xmm0, dword ptr [rcx] seta bl - add rdx, 4 + lea rdx, [rcx + 4] neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_83 -# %bb.84: - add r11, 1 -.LBB8_85: - sar r14, 5 - cmp r10, 32 - jl .LBB8_89 -# %bb.86: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 136], r14 # 8-byte Spill - mov qword ptr [rsp + 128], r14 # 8-byte Spill - mov qword ptr [rsp + 232], r11 # 8-byte Spill + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_99 +.LBB8_100: + sub r14, r8 + je .LBB8_194 +# %bb.101: + add r12, 1 +.LBB8_102: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_106 +# %bb.103: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov dword ptr [rsp + 144], r15d # 4-byte Spill + vmovd xmm0, r15d + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_87: # =>This Inner Loop Header: Depth=1 +.LBB8_104: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill vucomiss xmm0, dword ptr [rdx] - seta byte ptr [rsp + 120] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 4] seta r8b vucomiss xmm0, dword ptr [rdx + 8] seta r14b vucomiss xmm0, dword ptr [rdx + 12] - seta r13b + seta r12b vucomiss xmm0, dword ptr [rdx + 16] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 20] - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 24] seta al vucomiss xmm0, dword ptr [rdx + 28] seta r11b vucomiss xmm0, dword ptr [rdx + 32] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 112] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 36] - seta sil + seta cl vucomiss xmm0, dword ptr [rdx + 40] - seta dil + seta sil vucomiss xmm0, dword ptr [rdx + 44] seta r9b vucomiss xmm0, dword ptr [rdx + 48] seta r10b vucomiss xmm0, dword ptr [rdx + 52] - seta r12b + seta r13b vucomiss xmm0, dword ptr [rdx + 56] - seta byte ptr [rsp + 88] # 1-byte Folded Spill + seta byte ptr [rsp + 120] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 60] - seta cl + seta dil vucomiss xmm0, dword ptr [rdx + 64] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 68] - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 72] - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 76] - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 40] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 80] - seta byte ptr [rsp + 48] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 84] - seta byte ptr [rsp + 64] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 88] - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 92] seta r15b vucomiss xmm0, dword ptr [rdx + 96] seta byte ptr [rsp + 320] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 100] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - vucomiss xmm0, dword ptr [rdx + 104] seta byte ptr [rsp + 24] # 1-byte Folded Spill + vucomiss xmm0, dword ptr [rdx + 104] + seta byte ptr [rsp + 32] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 108] seta byte ptr [rsp + 8] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 112] @@ -46657,69 +47772,350 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 vucomiss xmm0, dword ptr [rdx + 124] seta bl add r8b, r8b - add r8b, byte ptr [rsp + 120] # 1-byte Folded Reload + add r8b, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al shl r14b, 2 or r14b, r8b - add sil, sil - add sil, byte ptr [rsp + 80] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r14b - shl dil, 2 - or dil, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, r13b - mov r8d, eax + add cl, cl + add cl, byte ptr [rsp + 112] # 1-byte Folded Reload + shl r12b, 3 + or r12b, r14b + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, r12b + mov r8d, ecx + mov r12, qword ptr [rsp + 240] # 8-byte Reload shl r9b, 3 - or r9b, dil - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, r8b + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, r8b shl r10b, 4 or r10b, r9b - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 88] # 1-byte Folded Reload + shl r13b, 5 + or r13b, r10b + movzx esi, byte ptr [rsp + 120] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 + shl dil, 7 + or dil, sil + or r11b, cl + or dil, r13b + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 + or cl, al + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [r12 + 1], dil + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, byte ptr [rsp + 320] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload shl al, 5 - or al, sil - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dil, 6 + or al, cl + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl + add rdx, 128 + add r12, 4 + add qword ptr [rsp + 128], -1 # 8-byte Folded Spill + jne .LBB8_104 +# %bb.105: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov r15d, dword ptr [rsp + 144] # 4-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_106: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.107: + vmovd xmm0, r15d + or rax, 1 + cmp r14, rax + jne .LBB8_182 +# %bb.108: + xor edi, edi + jmp .LBB8_184 +.LBB8_109: + mov r15b, byte ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB8_128 +# %bb.110: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_143 +# %bb.111: + movsxd rsi, r9d + mov rax, r8 + .p2align 4, 0x90 +.LBB8_112: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp byte ptr [rdx], r15b + sbb r11d, r11d + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rbx] + xor r11b, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov edx, 1 + # kill: def $cl killed $cl killed $ecx + shl edx, cl + and dl, r11b + xor dl, r9b + mov byte ptr [r12 + rbx], dl + add rsi, 1 + mov rdx, rdi + add rax, -1 + jne .LBB8_112 +# %bb.113: + sub r14, r8 + jne .LBB8_144 + jmp .LBB8_194 +.LBB8_114: + mov r13d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB8_120 +# %bb.115: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB8_118 +# %bb.116: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx + .p2align 4, 0x90 +.LBB8_117: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r13d, dword ptr [rcx] + setg bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r15, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_117 +.LBB8_118: + sub r14, r8 + je .LBB8_194 +# %bb.119: + add r12, 1 +.LBB8_120: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB8_124 +# %bb.121: + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB8_122: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 240], r12 # 8-byte Spill + cmp r13d, dword ptr [rdx] + setg byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 4] + setg dil + cmp r13d, dword ptr [rdx + 8] + setg r14b + cmp r13d, dword ptr [rdx + 12] + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 16] + setg byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 20] + setg byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 24] + setg al + cmp r13d, dword ptr [rdx + 28] + setg r11b + cmp r13d, dword ptr [rdx + 32] + setg byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 36] + setg cl + cmp r13d, dword ptr [rdx + 40] + setg sil + cmp r13d, dword ptr [rdx + 44] + setg r9b + cmp r13d, dword ptr [rdx + 48] + setg r10b + cmp r13d, dword ptr [rdx + 52] + setg r12b + cmp r13d, dword ptr [rdx + 56] + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 60] + setg r8b + cmp r13d, dword ptr [rdx + 64] + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 68] + setg byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 72] + setg byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 76] + setg byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 80] + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 84] + setg byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 88] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 92] + setg r15b + cmp r13d, dword ptr [rdx + 96] + setg byte ptr [rsp + 320] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 100] + setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 104] + setg byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 108] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 112] + setg byte ptr [rsp + 288] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 116] + setg byte ptr [rsp + 256] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 120] + setg byte ptr [rsp + 4] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 124] + setg bl + add dil, dil + add dil, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r9b, 3 + or r9b, sil + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r10b, 4 + or r10b, r9b + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload + shl sil, 6 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b + mov r12, qword ptr [rsp + 240] # 8-byte Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 320] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -46730,219 +48126,438 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 4 or al, cl - movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - shl al, 6 + mov ecx, eax + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + shl cl, 6 shl bl, 7 - or bl, al or bl, cl - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], bl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rdx, 128 - add rsi, 4 - mov qword ptr [rsp + 232], rsi # 8-byte Spill + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB8_122 +# %bb.123: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload +.LBB8_124: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB8_194 +# %bb.125: + or rax, 1 + cmp r14, rax + jne .LBB8_187 +# %bb.126: + xor edi, edi + jmp .LBB8_189 +.LBB8_127: + mov rdi, rdx + jmp .LBB8_131 +.LBB8_128: + mov rdi, rdx + jmp .LBB8_145 +.LBB8_129: + mov rdi, rdx + sub r14, r8 + je .LBB8_194 +.LBB8_130: + add r12, 1 +.LBB8_131: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB8_139 +# %bb.132: + cmp rcx, 32 + mov dword ptr [rsp + 4], r15d # 4-byte Spill + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 360], rcx # 8-byte Spill + jb .LBB8_135 +# %bb.133: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r12, rax + jae .LBB8_205 +# %bb.134: + lea rax, [r12 + 4*rcx] + cmp rdi, rax + jae .LBB8_205 +.LBB8_135: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 352], r12 # 8-byte Spill +.LBB8_136: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 128], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB8_137: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp r15b, byte ptr [rsi] + setg byte ptr [rsp + 288] # 1-byte Folded Spill + cmp r15b, byte ptr [rsi + 1] + setg r9b + cmp r15b, byte ptr [rsi + 2] + setg r11b + cmp r15b, byte ptr [rsi + 3] + setg r13b + cmp r15b, byte ptr [rsi + 4] + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r15b, byte ptr [rsi + 5] + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r15b, byte ptr [rsi + 6] + setg bl + cmp r15b, byte ptr [rsi + 7] + setg r12b + cmp r15b, byte ptr [rsi + 8] + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r15b, byte ptr [rsi + 9] + setg sil + cmp r15b, byte ptr [rcx + 10] + setg dil + cmp r15b, byte ptr [rcx + 11] + setg r8b + cmp r15b, byte ptr [rcx + 12] + setg r10b + cmp r15b, byte ptr [rcx + 13] + setg r15b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp al, byte ptr [rcx + 14] + setg byte ptr [rsp + 104] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp al, byte ptr [rcx + 15] + setg al + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 16] + setg byte ptr [rsp + 256] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 17] + setg byte ptr [rsp + 40] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 18] + setg byte ptr [rsp + 120] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 19] + setg byte ptr [rsp + 80] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 20] + setg byte ptr [rsp + 88] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 21] + setg byte ptr [rsp + 48] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 22] + setg byte ptr [rsp + 24] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 23] + setg r14b + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 24] + setg byte ptr [rsp + 240] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 25] + setg byte ptr [rsp + 72] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 26] + setg byte ptr [rsp + 64] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 27] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 28] + setg byte ptr [rsp + 32] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 29] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 30] + setg byte ptr [rsp + 320] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 31] + setg dl + add r9b, r9b + add r9b, byte ptr [rsp + 288] # 1-byte Folded Reload + shl bl, 6 + shl r12b, 7 + or r12b, bl + shl r11b, 2 + or r11b, r9b + add sil, sil + add sil, byte ptr [rsp + 96] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r11b + shl dil, 2 + or dil, sil + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl bl, 4 + or bl, r13b + mov esi, ebx + shl r8b, 3 + or r8b, dil + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl bl, 5 + or bl, sil + shl r10b, 4 + or r10b, r8b + shl r15b, 5 + or r15b, r10b + movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload + shl sil, 6 + shl al, 7 + or al, sil + or r12b, bl + or al, r15b + mov r15d, dword ptr [rsp + 4] # 4-byte Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 256] # 1-byte Folded Reload + mov esi, ebx + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl bl, 2 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl bl, 3 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl bl, 4 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl bl, 5 + or bl, sil + mov rdi, qword ptr [rsp + 352] # 8-byte Reload + mov byte ptr [rdi], r12b + movzx esi, byte ptr [rsp + 24] # 1-byte Folded Reload + shl sil, 6 + shl r14b, 7 + or r14b, sil + mov byte ptr [rdi + 1], al + or r14b, bl + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 240] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rdi + 2], r14b + mov byte ptr [rdi + 3], dl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 352], rdi # 8-byte Spill add qword ptr [rsp + 128], -1 # 8-byte Folded Spill - jne .LBB8_87 -# %bb.88: - mov r11, qword ptr [rsp + 232] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14, qword ptr [rsp + 136] # 8-byte Reload -.LBB8_89: - shl r14, 5 - cmp r14, r10 - jge .LBB8_179 -# %bb.90: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB8_145 -# %bb.91: - xor edi, edi - jmp .LBB8_147 -.LBB8_92: - mov r14b, byte ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB8_96 -# %bb.93: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB8_94: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rdx], r14b - lea rdx, [rdx + 1] - sbb esi, esi - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, sil - xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB8_94 -# %bb.95: - add r11, 1 -.LBB8_96: - sar r15, 5 - cmp r10, 32 - jl .LBB8_124 -# %bb.97: - cmp r15, 32 - mov dword ptr [rsp + 4], r14d # 4-byte Spill - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 368], r15 # 8-byte Spill - jb .LBB8_100 -# %bb.98: - mov rax, r15 + jne .LBB8_137 +# %bb.138: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rcx, qword ptr [rsp + 360] # 8-byte Reload + jmp .LBB8_140 +.LBB8_139: + mov qword ptr [rsp + 352], r12 # 8-byte Spill + mov rsi, rdi +.LBB8_140: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB8_194 +# %bb.141: + or rcx, 1 + cmp r14, rcx + jne .LBB8_195 +# %bb.142: + xor r9d, r9d + jmp .LBB8_198 +.LBB8_143: + mov rdi, rdx + sub r14, r8 + je .LBB8_194 +.LBB8_144: + add r12, 1 +.LBB8_145: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB8_153 +# %bb.146: + cmp rcx, 32 + mov dword ptr [rsp + 4], r15d # 4-byte Spill + mov qword ptr [rsp + 248], r14 # 8-byte Spill + mov qword ptr [rsp + 368], rcx # 8-byte Spill + jb .LBB8_149 +# %bb.147: + mov rax, rcx shl rax, 5 - add rax, rdx - cmp r11, rax - jae .LBB8_183 -# %bb.99: - lea rax, [r11 + 4*r15] - cmp rdx, rax - jae .LBB8_183 -.LBB8_100: + add rax, rdi + cmp r12, rax + jae .LBB8_208 +# %bb.148: + lea rax, [r12 + 4*rcx] + cmp rdi, rax + jae .LBB8_208 +.LBB8_149: xor eax, eax mov qword ptr [rsp + 360], rax # 8-byte Spill - mov r12, rdx - mov qword ptr [rsp + 352], r11 # 8-byte Spill -.LBB8_101: - sub r15, qword ptr [rsp + 360] # 8-byte Folded Reload - mov qword ptr [rsp + 128], r15 # 8-byte Spill + mov r11, rdi + mov qword ptr [rsp + 352], r12 # 8-byte Spill +.LBB8_150: + sub rcx, qword ptr [rsp + 360] # 8-byte Folded Reload + mov qword ptr [rsp + 128], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB8_102: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp r14b, byte ptr [r12] - seta byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14b, byte ptr [r12 + 1] - seta r10b - cmp r14b, byte ptr [r12 + 2] - seta bl - cmp r14b, byte ptr [r12 + 3] +.LBB8_151: # =>This Inner Loop Header: Depth=1 + mov rcx, r11 + cmp r15b, byte ptr [r11] + seta byte ptr [rsp + 288] # 1-byte Folded Spill + cmp r15b, byte ptr [r11 + 1] + seta r9b + cmp r15b, byte ptr [r11 + 2] + seta r11b + cmp r15b, byte ptr [rcx + 3] seta r13b - cmp r14b, byte ptr [r12 + 4] - seta byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14b, byte ptr [r12 + 5] - seta byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14b, byte ptr [r12 + 6] - seta al - cmp r14b, byte ptr [r12 + 7] + cmp r15b, byte ptr [rcx + 4] + seta byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r15b, byte ptr [rcx + 5] + seta byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r15b, byte ptr [rcx + 6] + seta bl + cmp r15b, byte ptr [rcx + 7] seta r12b - cmp r14b, byte ptr [rcx + 8] - seta byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 9] + cmp r15b, byte ptr [rcx + 8] + seta byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r15b, byte ptr [rcx + 9] seta sil - cmp r14b, byte ptr [rcx + 10] + cmp r15b, byte ptr [rcx + 10] seta dil - cmp r14b, byte ptr [rcx + 11] - seta r9b - cmp r14b, byte ptr [rcx + 12] - seta r11b - cmp r14b, byte ptr [rcx + 13] - seta r15b - cmp r14b, byte ptr [rcx + 14] - seta byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 15] + cmp r15b, byte ptr [rcx + 11] seta r8b - cmp r14b, byte ptr [rcx + 16] - seta byte ptr [rsp + 256] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 17] + cmp r15b, byte ptr [rcx + 12] + seta r10b + cmp r15b, byte ptr [rcx + 13] + seta r15b + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp al, byte ptr [rcx + 14] seta byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 18] - seta byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 19] - seta byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 20] - seta byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 21] + mov eax, dword ptr [rsp + 4] # 4-byte Reload + cmp al, byte ptr [rcx + 15] + seta al + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 16] + seta byte ptr [rsp + 256] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 17] seta byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 22] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14b, byte ptr [rcx + 23] + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 18] + seta byte ptr [rsp + 120] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 19] + seta byte ptr [rsp + 80] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 20] + seta byte ptr [rsp + 40] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 21] + seta byte ptr [rsp + 88] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 22] + seta byte ptr [rsp + 24] # 1-byte Folded Spill + mov edx, dword ptr [rsp + 4] # 4-byte Reload + cmp dl, byte ptr [rcx + 23] seta r14b mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 24] - seta byte ptr [rsp + 232] # 1-byte Folded Spill + seta byte ptr [rsp + 240] # 1-byte Folded Spill mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 25] - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 26] - seta byte ptr [rsp + 64] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 27] - seta byte ptr [rsp + 32] # 1-byte Folded Spill + seta byte ptr [rsp + 16] # 1-byte Folded Spill mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 28] - seta byte ptr [rsp + 24] # 1-byte Folded Spill + seta byte ptr [rsp + 32] # 1-byte Folded Spill mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 29] seta byte ptr [rsp + 8] # 1-byte Folded Spill mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 30] - seta byte ptr [rsp + 288] # 1-byte Folded Spill + seta byte ptr [rsp + 320] # 1-byte Folded Spill mov edx, dword ptr [rsp + 4] # 4-byte Reload cmp dl, byte ptr [rcx + 31] seta dl - add r10b, r10b - add r10b, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 6 + add r9b, r9b + add r9b, byte ptr [rsp + 288] # 1-byte Folded Reload + shl bl, 6 shl r12b, 7 - or r12b, al - shl bl, 2 - or bl, r10b + or r12b, bl + shl r11b, 2 + or r11b, r9b add sil, sil - add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + add sil, byte ptr [rsp + 96] # 1-byte Folded Reload shl r13b, 3 - or r13b, bl + or r13b, r11b shl dil, 2 or dil, sil - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload shl bl, 4 or bl, r13b mov esi, ebx - shl r9b, 3 - or r9b, dil - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl r8b, 3 + or r8b, dil + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 or bl, sil - shl r11b, 4 - or r11b, r9b + shl r10b, 4 + or r10b, r8b shl r15b, 5 - or r15b, r11b - movzx esi, byte ptr [rsp + 72] # 1-byte Folded Reload + or r15b, r10b + movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload shl sil, 6 - shl r8b, 7 - or r8b, sil + shl al, 7 + or al, sil or r12b, bl - or r8b, r15b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 256] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + or al, r15b + mov r15d, dword ptr [rsp + 4] # 4-byte Reload + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 256] # 1-byte Folded Reload + mov esi, ebx + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload shl bl, 2 - or bl, al + or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx @@ -46950,368 +48565,119 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload shl bl, 5 or bl, sil mov rsi, qword ptr [rsp + 352] # 8-byte Reload mov byte ptr [rsi], r12b - movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 24] # 1-byte Folded Reload shl dil, 6 shl r14b, 7 or r14b, dil - mov byte ptr [rsi + 1], r8b + mov byte ptr [rsi + 1], al or r14b, bl - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 232] # 1-byte Folded Reload + add al, byte ptr [rsp + 240] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 320] # 1-byte Folded Reload shl bl, 6 shl dl, 7 or dl, bl or dl, al mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 4] # 4-byte Reload mov byte ptr [rsi + 3], dl - lea r12, [rcx + 32] + lea r11, [rcx + 32] add rsi, 4 mov qword ptr [rsp + 352], rsi # 8-byte Spill add qword ptr [rsp + 128], -1 # 8-byte Folded Spill - jne .LBB8_102 -# %bb.103: - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r15, qword ptr [rsp + 368] # 8-byte Reload - jmp .LBB8_125 -.LBB8_104: - mov r13d, dword ptr [rsi] - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB8_108 -# %bb.105: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB8_106: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - lea rdx, [rdx + 4] - setg bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r11 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_106 -# %bb.107: - add r11, 1 -.LBB8_108: - sar r14, 5 - cmp r10, 32 - jl .LBB8_112 -# %bb.109: - mov qword ptr [rsp + 248], r10 # 8-byte Spill - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 136], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_110: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 232], r11 # 8-byte Spill - cmp r13d, dword ptr [rdx] - setg byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 4] - setg dil - cmp r13d, dword ptr [rdx + 8] - setg r14b - cmp r13d, dword ptr [rdx + 12] - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 16] - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 20] - setg byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 24] - setg al - cmp r13d, dword ptr [rdx + 28] - setg r11b - cmp r13d, dword ptr [rdx + 32] - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 36] - setg sil - cmp r13d, dword ptr [rdx + 40] - setg r8b - cmp r13d, dword ptr [rdx + 44] - setg r9b - cmp r13d, dword ptr [rdx + 48] - setg r10b - cmp r13d, dword ptr [rdx + 52] - setg r12b - cmp r13d, dword ptr [rdx + 56] - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 60] - setg cl - cmp r13d, dword ptr [rdx + 64] - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 68] - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 72] - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 76] - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 80] - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 84] - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 88] - setg byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 92] - setg r15b - cmp r13d, dword ptr [rdx + 96] - setg byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 100] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 104] - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 108] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 112] - setg byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 116] - setg byte ptr [rsp + 256] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 120] - setg byte ptr [rsp + 4] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 124] - setg bl - add dil, dil - add dil, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r14b, 2 - or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 72] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, dil - shl r10b, 4 - or r10b, r9b - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov esi, eax - mov rax, qword ptr [rsp + 232] # 8-byte Reload - mov byte ptr [rax], r11b - mov r11, qword ptr [rsp + 232] # 8-byte Reload - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 6 - shl r15b, 7 - or r15b, al - mov byte ptr [r11 + 1], cl - or r15b, sil - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 320] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload - shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl cl, 6 - shl bl, 7 - or bl, cl - or bl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], bl - add rdx, 128 - add r11, 4 - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB8_110 -# %bb.111: - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14, qword ptr [rsp + 144] # 8-byte Reload -.LBB8_112: - shl r14, 5 - cmp r14, r10 - jge .LBB8_179 -# %bb.113: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB8_150 -# %bb.114: - xor edi, edi - jmp .LBB8_152 -.LBB8_115: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB8_179 -.LBB8_116: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB8_156 -# %bb.117: - xor r11d, r11d - jmp .LBB8_158 -.LBB8_118: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB8_179 -.LBB8_119: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB8_160 -# %bb.120: - xor r11d, r11d - jmp .LBB8_162 -.LBB8_121: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB8_179 -.LBB8_122: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB8_164 -# %bb.123: - xor r11d, r11d - jmp .LBB8_166 -.LBB8_124: - mov qword ptr [rsp + 352], r11 # 8-byte Spill - mov r12, rdx -.LBB8_125: - shl r15, 5 - cmp r15, r10 - jge .LBB8_179 -# %bb.126: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB8_169 -# %bb.127: + jne .LBB8_151 +# %bb.152: + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov rcx, qword ptr [rsp + 368] # 8-byte Reload + jmp .LBB8_154 +.LBB8_153: + mov qword ptr [rsp + 352], r12 # 8-byte Spill + mov r11, rdi +.LBB8_154: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB8_194 +# %bb.155: + or rcx, 1 + cmp r14, rcx + jne .LBB8_200 +# %bb.156: xor eax, eax - jmp .LBB8_172 -.LBB8_128: - mov r15, r11 - sar r13, 5 - cmp r10, 32 - jge .LBB8_34 -.LBB8_129: - mov qword ptr [rsp + 352], r15 # 8-byte Spill - mov r12, rdx -.LBB8_130: - shl r13, 5 - cmp r13, r10 - jge .LBB8_179 -# %bb.131: - mov r8, r10 - sub r8, r13 - not r13 - add r13, r10 - jne .LBB8_174 -# %bb.132: - xor esi, esi - jmp .LBB8_177 -.LBB8_133: + jmp .LBB8_203 +.LBB8_157: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB8_158: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rdx], r13d + sbb edi, edi + mov rsi, r11 + shr rsi, 3 + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r12 + rsi], al + add r11, 2 + cmp dword ptr [rdx + 4], r13d + lea rdx, [rdx + 8] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r12 + rsi], bl + cmp r9, r11 + jne .LBB8_158 +.LBB8_159: + test r8b, 1 + je .LBB8_194 +# %bb.160: + cmp dword ptr [rdx], r13d + jmp .LBB8_173 +.LBB8_161: mov r10, r8 and r10, -2 xor edi, edi - mov r14, r11 .p2align 4, 0x90 -.LBB8_134: # =>This Inner Loop Header: Depth=1 +.LBB8_162: # =>This Inner Loop Header: Depth=1 vucomisd xmm0, qword ptr [rdx] seta al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -47319,7 +48685,7 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r14 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 vucomisd xmm0, qword ptr [rdx + 8] seta r9b @@ -47331,28 +48697,117 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 shl al, cl and al, r9b xor al, bl - mov byte ptr [r14 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB8_134 -.LBB8_135: + jne .LBB8_162 +.LBB8_163: test r8b, 1 - je .LBB8_179 -# %bb.136: + je .LBB8_194 +# %bb.164: vucomisd xmm0, qword ptr [rdx] - jmp .LBB8_149 -.LBB8_137: + jmp .LBB8_186 +.LBB8_165: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB8_166: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rdx], r13 + sbb edi, edi + mov rsi, r11 + shr rsi, 3 + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r12 + rsi], al + add r11, 2 + cmp qword ptr [rdx + 8], r13 + lea rdx, [rdx + 16] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r12 + rsi], bl + cmp r9, r11 + jne .LBB8_166 +.LBB8_167: + test r8b, 1 + je .LBB8_194 +# %bb.168: + cmp qword ptr [rdx], r13 + jmp .LBB8_173 +.LBB8_169: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB8_170: # =>This Inner Loop Header: Depth=1 + cmp word ptr [rdx], r13w + sbb edi, edi + mov rsi, r11 + shr rsi, 3 + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r12 + rsi], al + add r11, 2 + cmp word ptr [rdx + 2], r13w + lea rdx, [rdx + 4] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r12 + rsi], bl + cmp r9, r11 + jne .LBB8_170 +.LBB8_171: + test r8b, 1 + je .LBB8_194 +# %bb.172: + cmp word ptr [rdx], r13w +.LBB8_173: + sbb eax, eax + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al + jmp .LBB8_193 +.LBB8_174: mov r10, r8 and r10, -2 xor edi, edi - mov r14, r11 .p2align 4, 0x90 -.LBB8_138: # =>This Inner Loop Header: Depth=1 +.LBB8_175: # =>This Inner Loop Header: Depth=1 cmp r13w, word ptr [rdx] setg al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -47360,7 +48815,7 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r14 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 cmp r13w, word ptr [rdx + 2] lea rdx, [rdx + 4] @@ -47372,28 +48827,28 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 shl al, cl and al, r9b xor al, bl - mov byte ptr [r14 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB8_138 -.LBB8_139: + jne .LBB8_175 +.LBB8_176: test r8b, 1 - je .LBB8_179 -# %bb.140: + je .LBB8_194 +# %bb.177: cmp r13w, word ptr [rdx] - jmp .LBB8_154 -.LBB8_141: + jmp .LBB8_191 +.LBB8_178: mov r10, r8 and r10, -2 xor edi, edi - mov r14, r11 .p2align 4, 0x90 -.LBB8_142: # =>This Inner Loop Header: Depth=1 +.LBB8_179: # =>This Inner Loop Header: Depth=1 cmp r13, qword ptr [rdx] setg al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -47401,7 +48856,7 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r14 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 cmp r13, qword ptr [rdx + 8] lea rdx, [rdx + 16] @@ -47413,28 +48868,28 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 shl al, cl and al, r9b xor al, bl - mov byte ptr [r14 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB8_142 -.LBB8_143: + jne .LBB8_179 +.LBB8_180: test r8b, 1 - je .LBB8_179 -# %bb.144: + je .LBB8_194 +# %bb.181: cmp r13, qword ptr [rdx] - jmp .LBB8_154 -.LBB8_145: + jmp .LBB8_191 +.LBB8_182: mov r10, r8 and r10, -2 xor edi, edi - mov r14, r11 .p2align 4, 0x90 -.LBB8_146: # =>This Inner Loop Header: Depth=1 +.LBB8_183: # =>This Inner Loop Header: Depth=1 vucomiss xmm0, dword ptr [rdx] seta al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -47442,7 +48897,7 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r14 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 vucomiss xmm0, dword ptr [rdx + 4] seta r9b @@ -47454,30 +48909,30 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 shl al, cl and al, r9b xor al, bl - mov byte ptr [r14 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB8_146 -.LBB8_147: + jne .LBB8_183 +.LBB8_184: test r8b, 1 - je .LBB8_179 -# %bb.148: + je .LBB8_194 +# %bb.185: vucomiss xmm0, dword ptr [rdx] -.LBB8_149: +.LBB8_186: seta al - jmp .LBB8_155 -.LBB8_150: + jmp .LBB8_192 +.LBB8_187: mov r10, r8 and r10, -2 xor edi, edi - mov r14, r11 .p2align 4, 0x90 -.LBB8_151: # =>This Inner Loop Header: Depth=1 +.LBB8_188: # =>This Inner Loop Header: Depth=1 cmp r13d, dword ptr [rdx] setg al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -47485,7 +48940,7 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r14 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 cmp r13d, dword ptr [rdx + 4] lea rdx, [rdx + 8] @@ -47497,168 +48952,105 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 shl al, cl and al, r9b xor al, bl - mov byte ptr [r14 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB8_151 -.LBB8_152: + jne .LBB8_188 +.LBB8_189: test r8b, 1 - je .LBB8_179 -# %bb.153: + je .LBB8_194 +# %bb.190: cmp r13d, dword ptr [rdx] -.LBB8_154: +.LBB8_191: setg al -.LBB8_155: +.LBB8_192: neg al mov rdx, rdi shr rdx, 3 - mov sil, byte ptr [r11 + rdx] + mov sil, byte ptr [r12 + rdx] and dil, 7 mov bl, 1 mov ecx, edi shl bl, cl xor al, sil and bl, al +.LBB8_193: xor bl, sil - mov byte ptr [r11 + rdx], bl - jmp .LBB8_179 -.LBB8_156: - mov r9, r8 - and r9, -2 - xor r11d, r11d - mov r15, r14 - .p2align 4, 0x90 -.LBB8_157: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rdx], r13d - sbb edi, edi - mov rsi, r11 - shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r15 + rsi], al - add r11, 2 - cmp dword ptr [rdx + 4], r13d - lea rdx, [rdx + 8] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB8_157 -.LBB8_158: - test r8b, 1 - je .LBB8_179 -# %bb.159: - cmp dword ptr [rdx], r13d - jmp .LBB8_168 -.LBB8_160: - mov r9, r8 - and r9, -2 - xor r11d, r11d - mov r15, r14 + mov byte ptr [r12 + rdx], bl +.LBB8_194: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + vzeroupper + ret +.LBB8_195: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 352] # 8-byte Reload .p2align 4, 0x90 -.LBB8_161: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rdx], r13 - sbb edi, edi - mov rsi, r11 - shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - mov ecx, r11d +.LBB8_196: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r15b, byte ptr [rsi + r9] + setg bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r15 + rsi], al - add r11, 2 - cmp qword ptr [rdx + 8], r13 - lea rdx, [rdx + 16] - sbb edi, edi - xor dil, al + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp r15b, byte ptr [rsi + rax + 1] + lea r9, [rax + 2] + setg bl + neg bl + xor bl, dl or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB8_161 -.LBB8_162: - test r8b, 1 - je .LBB8_179 -# %bb.163: - cmp qword ptr [rdx], r13 - jmp .LBB8_168 -.LBB8_164: - mov r9, r8 - and r9, -2 - xor r11d, r11d - mov r15, r14 - .p2align 4, 0x90 -.LBB8_165: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rdx], r13w - sbb edi, edi - mov rsi, r11 - shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - mov ecx, r11d - and cl, 6 mov al, 1 shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r15 + rsi], al - add r11, 2 - cmp word ptr [rdx + 2], r13w - lea rdx, [rdx + 4] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB8_165 -.LBB8_166: + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB8_196 +# %bb.197: + add rsi, r9 +.LBB8_198: test r8b, 1 - je .LBB8_179 -# %bb.167: - cmp word ptr [rdx], r13w -.LBB8_168: - sbb eax, eax - mov rdx, r11 + je .LBB8_194 +# %bb.199: + cmp r15b, byte ptr [rsi] + setg al + neg al + mov rdx, r9 shr rdx, 3 - mov sil, byte ptr [r14 + rdx] - and r11b, 7 + mov r8, qword ptr [rsp + 352] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 mov bl, 1 - mov ecx, r11d + mov ecx, r9d shl bl, cl - xor al, sil + xor al, dil and bl, al - xor bl, sil - mov byte ptr [r14 + rdx], bl - jmp .LBB8_179 -.LBB8_169: + xor bl, dil + mov byte ptr [r8 + rdx], bl + jmp .LBB8_194 +.LBB8_200: mov r9, r8 and r9, -2 xor eax, eax mov r10, qword ptr [rsp + 352] # 8-byte Reload .p2align 4, 0x90 -.LBB8_170: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rax], r14b +.LBB8_201: # =>This Inner Loop Header: Depth=1 + cmp byte ptr [r11 + rax], r15b sbb esi, esi mov rdi, rax shr rdi, 3 @@ -47671,7 +49063,7 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 and dl, sil xor dl, bl mov byte ptr [r10 + rdi], dl - cmp byte ptr [r12 + rax + 1], r14b + cmp byte ptr [r11 + rax + 1], r15b lea rax, [rax + 2] sbb esi, esi xor sil, dl @@ -47682,14 +49074,14 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 xor bl, dl mov byte ptr [r10 + rdi], bl cmp r9, rax - jne .LBB8_170 -# %bb.171: - add r12, rax -.LBB8_172: + jne .LBB8_201 +# %bb.202: + add r11, rax +.LBB8_203: test r8b, 1 - je .LBB8_179 -# %bb.173: - cmp byte ptr [r12], r14b + je .LBB8_194 +# %bb.204: + cmp byte ptr [r11], r15b sbb edx, edx mov rsi, rax shr rsi, 3 @@ -47703,2047 +49095,1986 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 and bl, dl xor bl, dil mov byte ptr [r8 + rsi], bl - jmp .LBB8_179 -.LBB8_174: - mov r10, r8 - and r10, -2 - xor esi, esi - mov r11, qword ptr [rsp + 352] # 8-byte Reload - .p2align 4, 0x90 -.LBB8_175: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [r12 + rsi] - setg bl - neg bl - mov rdi, rsi - shr rdi, 3 - mov ecx, esi - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r11 + rdi] - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp r14b, byte ptr [r12 + rsi + 1] - lea rsi, [rsi + 2] - setg bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB8_175 -# %bb.176: - add r12, rsi -.LBB8_177: - test r8b, 1 - je .LBB8_179 -# %bb.178: - cmp r14b, byte ptr [r12] - setg al - neg al - mov rdx, rsi - shr rdx, 3 - mov r8, qword ptr [rsp + 352] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r8 + rdx], bl -.LBB8_179: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - vzeroupper - ret -.LBB8_180: - and r13, -32 - mov rax, r13 + jmp .LBB8_194 +.LBB8_205: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx + add rax, rdi mov qword ptr [rsp + 368], rax # 8-byte Spill - mov qword ptr [rsp + 384], r13 # 8-byte Spill - lea rax, [r15 + 4*r13] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] mov qword ptr [rsp + 352], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r15d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 232], r15 # 8-byte Spill + mov qword ptr [rsp + 240], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB8_181: # =>This Inner Loop Header: Depth=1 +.LBB8_206: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 376], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 240], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 128], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 88], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 80], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 112], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rdx + rax] + movzx eax, byte ptr [rdi + rax] + mov rdx, rcx vmovd xmm0, eax - movzx eax, byte ptr [rdx + rbx] + mov rcx, rbx + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rdx + rcx + 1] - mov rsi, rcx + movzx eax, byte ptr [rdi + rdx + 1] vmovd xmm4, eax - mov rcx, rbx - movzx eax, byte ptr [rdx + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rsi + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 544], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rsi + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rsi + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm13, eax - movzx eax, byte ptr [rdx + rsi + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rdx + rsi + 6] - mov qword ptr [rsp + 216], rsi # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 208], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rdx + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rsi + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 8], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov qword ptr [rsp + 16], rax # 8-byte Spill - or rbx, 576 - mov qword ptr [rsp + 144], rbx # 8-byte Spill - mov rax, rcx + mov qword ptr [rsp + 8], rax # 8-byte Spill + mov rax, rbx + or rax, 576 + mov qword ptr [rsp + 200], rax # 8-byte Spill + mov rax, rbx or rax, 608 - mov qword ptr [rsp + 32], rax # 8-byte Spill - mov r12, rcx - or r12, 640 - mov r14, rcx - or r14, 672 - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov r10, rcx - or r10, 704 - mov qword ptr [rsp + 104], r10 # 8-byte Spill - mov rdi, rcx - or rdi, 736 - mov qword ptr [rsp + 176], rdi # 8-byte Spill - mov rax, rcx - or rax, 768 - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov r15, rcx - or r15, 800 - mov qword ptr [rsp + 112], r15 # 8-byte Spill - mov r11, rcx - or r11, 832 - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov r9, rcx - or r9, 864 - mov qword ptr [rsp + 72], r9 # 8-byte Spill - mov r8, rcx - or r8, 896 - mov qword ptr [rsp + 168], r8 # 8-byte Spill - mov rsi, rcx - or rsi, 928 - mov qword ptr [rsp + 200], rsi # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill + mov r11, rbx + or r11, 640 + mov qword ptr [rsp + 168], r11 # 8-byte Spill + mov r12, rbx + or r12, 672 + mov qword ptr [rsp + 152], r12 # 8-byte Spill + mov r15, rbx + or r15, 704 + mov qword ptr [rsp + 232], r15 # 8-byte Spill + mov r14, rbx + or r14, 736 + mov qword ptr [rsp + 224], r14 # 8-byte Spill + mov r8, rbx + or r8, 768 + mov qword ptr [rsp + 16], r8 # 8-byte Spill + mov rax, rbx + or rax, 800 + mov rsi, rax + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov rax, rbx + or rax, 832 + mov qword ptr [rsp + 96], rax # 8-byte Spill + mov r10, rbx + or r10, 864 + mov qword ptr [rsp + 192], r10 # 8-byte Spill + mov r9, rbx + or r9, 896 + mov qword ptr [rsp + 128], r9 # 8-byte Spill + or rbx, 928 + mov qword ptr [rsp + 160], rbx # 8-byte Spill mov rax, rcx - mov qword ptr [rsp + 224], rcx # 8-byte Spill + mov qword ptr [rsp + 216], rcx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 24], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 152], rcx # 8-byte Spill - mov r13, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm9, xmm0, byte ptr [rdx + r13], 1 - vpinsrb xmm0, xmm9, byte ptr [rdx + rbx], 2 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12], 4 - mov r13, r12 - mov qword ptr [rsp + 160], r12 # 8-byte Spill - vpinsrb xmm0, xmm0, byte ptr [rdx + r14], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx], 15 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 1 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 2 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12], 3 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 4 + mov qword ptr [rsp + 288], rcx # 8-byte Spill + mov r13, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + r13], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + rdx], 2 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 9 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 2 mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 5 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10], 6 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 7 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 9 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 10 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 11 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 13 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 14 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 15 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 2 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 4 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 5 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 6 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 11 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 12 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 1], 14 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r14 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 1], 2 - mov rdi, r11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 11 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 3 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 4 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 6 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 8 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 14 - vinserti128 ymm15, ymm3, xmm0, 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 10 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13], 15 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 2 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 3 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 4 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 5 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 6 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 8 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 1], 10 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 12 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 13 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 1], 14 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + rbx + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 2 + mov rdx, r8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 1], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 + vinserti128 ymm15, ymm3, xmm0, 1 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm9, esi vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1248], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + mov rax, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm10, esi - mov r8, qword ptr [rsp + 16] # 8-byte Reload + mov rcx, qword ptr [rsp + 8] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 544] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 2], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 2], 2 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 2], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 2], 1 + mov r9, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 2 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 5 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 6 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 9 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 10 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 11 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 12 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 13 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 5 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 7 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 2], 8 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 2], 9 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 2], 10 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 2], 11 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 2], 12 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 2], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 14 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 15 - mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov r8, qword ptr [rsp + 144] # 8-byte Reload vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 2 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 3 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 4 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 5 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 7 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 9 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 10 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 11 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 13 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 14 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rdx + r8 + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 3], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 4 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 3], 5 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 3], 6 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 10 - mov r8, r9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 3], 13 - mov r12, r15 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 14 - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rdx + rax + 3], 1 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 3], 2 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 3 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 4 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 3], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 2], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 3 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 4 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 5 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 8 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 9 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 10 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + rcx + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 7 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 8 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 9 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 10 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 11 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 3], 9 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 13 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 3], 14 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + r8 + 3], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 2 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 3], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 5 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 3], 14 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 9] + vpinsrb xmm0, xmm5, byte ptr [rdi + rdx + 3], 14 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 9] vmovd xmm8, esi - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 3], 15 + mov r15, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 9] + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 9] vmovd xmm11, esi vmovdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload + mov r8, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 2 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 3 + mov rdx, r10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 5 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 6 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 7 mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 1 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 4], 3 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 4], 4 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 5 - mov r15, rdi - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 4], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 4], 8 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 4], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 10 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 11 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 4], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 4], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 4], 15 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm13, byte ptr [rdx + rsi + 4], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 4], 2 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 4], 3 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 4], 4 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 4], 5 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 6 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 4], 7 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 9 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 10 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 4], 11 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 13 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 4], 14 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 15 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm14, byte ptr [rdx + r10 + 5], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 10 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 12 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 13 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 14 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 15 mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 5], 2 + vpinsrb xmm3, xmm13, byte ptr [rdi + rcx + 4], 1 mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 3 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 4 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 5 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 7 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 8 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 9 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 10 mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 5], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 9 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 11 - mov r8, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 12 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 14 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rdx + rax + 5], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 2 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 5], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 5], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 5], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 7 - mov r12, rbx - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 5], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 11 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 12 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 4], 13 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 4], 15 + mov rcx, r15 + vpinsrb xmm4, xmm14, byte ptr [rdi + r8 + 5], 1 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 4 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 5], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 9 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 10 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 12 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 13 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 14 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 5], 11 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 5], 15 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm6, byte ptr [rdi + rax + 5], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 5], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 6 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 5], 8 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 14 - vinserti128 ymm14, ymm3, xmm0, 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 9 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 10] + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 + vinserti128 ymm14, ymm3, xmm0, 1 + vpinsrb xmm0, xmm5, byte ptr [rdi + rcx + 5], 15 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 10] vmovd xmm3, esi vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 10] + mov rax, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 10] vmovd xmm4, esi - vpinsrb xmm0, xmm12, byte ptr [rdx + r10 + 6], 1 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 6], 2 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 4 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 6], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 6], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 6], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 6], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 12 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 14 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 15 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + r10 + 6], 1 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 6], 2 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 3 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rax + 6], 1 + mov r9, r13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 2 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 6], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 5 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 6 + mov r11, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 8 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 10 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 11 + mov r10, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 6], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 13 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 15 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 6], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 6], 4 mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 4 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 5 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 8 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 6], 9 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 10 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 11 - mov r12, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 12 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 13 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 14 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 15 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 5 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 8 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 9 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 10 + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 15 + mov r15, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 2 + mov r15, r9 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 7 mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 7], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 7], 2 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 4 - mov r14, rax - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 5 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 7], 12 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 13 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 14 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 3 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 7], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 9 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 7], 11 + mov r13, r8 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 12 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 12 - mov rbx, r8 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 14 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 7], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 2 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 3 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 7 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 7], 9 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 7], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rcx + 7], 14 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 11] + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 7], 14 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 11] vmovd xmm1, esi - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 7], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 11] + mov rax, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 11] vmovd xmm2, esi - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rdx + rcx + 8], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 2 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 8], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 8], 4 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 5 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 6 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 8 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 8], 9 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 8], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 8], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 8], 14 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 8], 15 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rdx + r11 + 8], 1 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 2 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 3 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 4 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 5 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 8], 6 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 8], 7 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 9 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 10 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 11 - mov rbx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 12 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 13 - mov r14, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 14 + mov r10, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r10 + 8], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 3 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 4 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 8], 6 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 8 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 8], 9 + mov rax, r11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 8], 10 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 11 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 8], 14 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 15 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + rdx + 8], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 3 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 4 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 5 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 6 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 8 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 9 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 11 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 13 mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 15 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r10 + 9], 1 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 2 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 5 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 6 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 7 mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rdx + rbx + 9], 1 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + r13 + 9], 3 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 9], 5 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 9], 6 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 7 - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 9], 8 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 9 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 10 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 11 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 9], 12 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 9], 13 - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 9], 14 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 9], 15 - vpinsrb xmm7, xmm11, byte ptr [rdx + r11 + 9], 1 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r9 + 9], 2 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 9], 4 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + r15 + 9], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + r12 + 9], 7 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r15 + 9], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 9 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 10 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r12 + 9], 11 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 9 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 9], 10 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 9], 12 + mov r11, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 9], 13 + mov r10, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 9], 14 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 9], 15 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rax + 9], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 8 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 9 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 10 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 12 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 13 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + r14 + 9], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 12] vmovd xmm0, esi vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1152], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 12] vmovd xmm5, esi - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 1 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 10], 2 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 3 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 4 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 7 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 10], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 10 - mov rcx, rbx - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 10], 11 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 10], 12 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 14 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 15 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 10], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 10], 2 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 10], 3 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 4 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 5 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 10], 6 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 8 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 9 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 10], 11 - mov rbx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 13 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 10], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 15 - mov r12, r14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 11], 2 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 4 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 5 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 11], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 11], 12 - mov r8, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 14 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 15 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 1 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 3 - mov r14, rsi - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 4 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 11], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 7 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 9 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 10 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 11 mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 1 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 2 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 10], 3 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 5 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 6 + mov r8, r14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 8 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 9 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 11 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 14 + mov r15, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 15 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 3 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 5 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 8 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 9 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 12 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 10], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 7 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 9 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 10 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 11], 12 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 13 + mov r14, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 11], 15 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 10 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1120], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 14 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 13] + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] vmovd xmm3, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 11], 15 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1088], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 13] + mov rax, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] vmovd xmm1, esi - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 12], 3 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 12], 4 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 5 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 6 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 12], 7 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 12], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 12], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 11 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 12], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 12], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 14 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 15 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rdx + r8 + 12], 1 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 12], 3 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 12], 4 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 5 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 6 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 7 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 1 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 2 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 3 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 4 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 6 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 12], 8 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 9 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 10 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 12 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 12], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 14 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 15 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + r14 + 12], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 4 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 5 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 8 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 9 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 11 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 12 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 13 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 14 mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 10 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 11 - mov r13, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 13 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 12], 15 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 2 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 4 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 5 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 13], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 13], 12 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 13], 14 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 13], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 2 - mov r8, rsi - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 4 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 13], 5 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 6 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 7 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 8 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 10 - mov r15, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 11 - mov r14, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 12 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 13], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 2 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 13], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 7 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 8 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 9 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 13], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 13], 13 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 14 + mov r9, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 3 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 5 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 6 + mov r15, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 13], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 8 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 10 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 11 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 13], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 1056], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm1, byte ptr [rdx + r12 + 13], 15 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 14] + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rdx + 13], 15 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 14] vmovd xmm1, esi vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 14] + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 14] vmovd xmm0, esi - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 1 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 2 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 3 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 1 + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 3 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 4 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 10 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 11 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 12 mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 14], 5 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 7 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 10 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 14], 11 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 12 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 14 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 14], 15 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 14], 2 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 14], 3 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 14], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 14], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 7 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 14], 8 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 14], 9 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 14], 11 - mov rdi, r14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 14], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 14], 13 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 14 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 14], 15 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 15] - vmovd xmm2, esi - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 1 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 15 + mov r9, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 14], 1 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 4 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 4 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 5 + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 14], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 8 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 14], 9 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 14], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 13 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 14 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 15 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rbx + 15] + vmovd xmm2, esi + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 15], 2 mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 15], 7 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 8 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 9 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 15], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 3 mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 15], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 15], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 15], 5 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 6 mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 15] - vmovd xmm3, esi - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 1 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 15], 3 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 15], 4 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 15], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 15], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 9 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 10 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 12 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 13 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 14 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 15], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 15], 13 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 15], 15 - mov r12, r14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 15 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + r8 + 15] + vmovd xmm3, esi + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 1 + mov r9, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 2 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 7 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 15], 10 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 12 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov r15, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 16] + movzx esi, byte ptr [rdi + rbx + 16] + vmovd xmm0, esi + mov rbx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 1 + mov r11, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 16], 2 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 3 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 6 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 7 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 16], 8 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 9 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 10 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 12 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 16], 14 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 16], 15 + movzx esi, byte ptr [rdi + r8 + 16] + vmovd xmm1, esi + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 3 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 4 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 5 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 8 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 9 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 10 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 16], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 15 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 17] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 2 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 3 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 4 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 6 + mov r8, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 17], 8 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 9 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 10 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 17], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 13 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 14 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 15 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 17] + vmovd xmm3, esi + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 2 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 3 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 5 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 + vinserti128 ymm0, ymm1, xmm0, 1 + vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r14 + 17], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill + mov r13, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + r13 + 18] vmovd xmm0, esi + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 2 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 4 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 18], 7 mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 1 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 16], 2 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 12 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 13 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 5 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 7 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 11 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 12 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 16], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 16], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 16], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 16] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 15 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rbx + 18] vmovd xmm1, esi - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 1 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 2 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 16], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 7 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 9 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 16], 10 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 11 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 16], 14 - mov r13, r12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 16], 15 - mov rcx, r15 - movzx esi, byte ptr [rdx + r15 + 17] - vmovd xmm2, esi - mov r15, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 17], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 17], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 4 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 17], 5 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 17], 6 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 17], 7 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 17], 8 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 17], 9 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 17], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 17], 11 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 17], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 17], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 17], 14 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 17], 15 - movzx esi, byte ptr [rdx + rax + 17] - vmovd xmm3, esi - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 17], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 2 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 3 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 4 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 4 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 7 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 8 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 10 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 11 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 5 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 7 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 8 mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rdx + r13 + 17], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - movzx esi, byte ptr [rdx + rcx + 18] - vmovd xmm0, esi - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 18], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 2 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 18], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 4 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 6 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 18], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 18], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 18], 10 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 18], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 9 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 10 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 12 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 15 + movzx esi, byte ptr [rdi + r13 + 19] + vmovd xmm2, esi + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 1 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 2 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 3 mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 18], 12 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 18], 14 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 18], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 19], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 5 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 6 mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 18] - vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 18], 1 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 18], 2 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 18], 3 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 4 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 5 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 9 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 7 + mov r10, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 8 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 9 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 19], 10 mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 18], 11 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 12 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 13 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 14 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 19], 15 + movzx esi, byte ptr [rdi + rbx + 19] + vmovd xmm3, esi + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 3 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + mov r13, rax + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 19], 6 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 8 mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 9 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 19], 13 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 19] - vmovd xmm2, esi - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 1 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 19], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 19], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 5 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 6 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 7 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 19], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 19], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 19], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 14 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 15 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 19] - vmovd xmm3, esi - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 19], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 19], 2 - mov r8, r12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 19], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 4 - mov r11, rdi - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 19], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 7 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 8 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 19], 9 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 19], 11 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 12 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 13 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 14 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov r15, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 20] + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 20] vmovd xmm0, esi - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 1 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 2 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 4 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 5 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 20], 7 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 11 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 12 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 20], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 15 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rbx + 20] + mov rcx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 1 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 20], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 5 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 6 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 9 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 20], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 20], 12 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 13 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 14 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 20], 15 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + r9 + 20] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 1 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 20], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 20], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 20], 5 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 20], 9 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 10 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 20], 11 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 20], 13 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 14 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 20], 15 - movzx esi, byte ptr [rdx + r15 + 21] - vmovd xmm2, esi - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 1 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 21], 2 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 21], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 4 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 5 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 21], 6 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 7 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 8 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 1 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 20], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 3 mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 11 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 12 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 5 + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 7 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 8 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 11 mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 14 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 15 - movzx esi, byte ptr [rdx + rbx + 21] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 15 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 21] + vmovd xmm2, esi + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 2 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 5 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 21], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 9 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 14 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 15 + movzx esi, byte ptr [rdi + r9 + 21] vmovd xmm3, esi - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 21], 2 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 3 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 4 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 6 - mov r10, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 7 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 8 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 21], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 21], 14 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 6 + mov r12, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 21], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 8 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 9 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 21], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 12 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 13 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rdx + r9 + 21], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + rbx + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 22] + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 22] vmovd xmm0, esi - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 22], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 22], 3 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 22], 4 - mov r12, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 22], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 6 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 22], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 22], 9 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 22], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 11 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 12 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 22], 14 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 22], 15 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 22] - vmovd xmm1, esi - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 22], 2 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 3 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 4 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 22], 7 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 9 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 10 - mov r15, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 22], 11 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 12 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 13 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 14 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 22], 15 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 23] - vmovd xmm2, esi + mov r11, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 2 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 3 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 22], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 22], 5 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 6 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 7 mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 1 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 8 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 9 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 10 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 12 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 15 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 22] + vmovd xmm1, esi + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 1 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 23], 5 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 23], 7 - mov r12, rbx - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 23], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 11 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 2 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 3 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 4 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 5 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 7 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 22], 10 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 22], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 15 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 23] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 1 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 23], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 23], 15 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + r8 + 23] + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 2 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 23], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 6 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 9 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 10 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 23], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 12 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 13 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 15 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 23] vmovd xmm3, esi - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 23], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 23], 2 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 23], 3 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 23], 4 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 5 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 23], 7 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 8 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 9 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 23], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 4 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 5 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 6 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 8 mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 23], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 23], 10 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 12 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 13 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 23], 14 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 24] + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 24] vmovd xmm0, esi - mov r13, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 24], 1 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 2 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 4 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 24], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 24], 7 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 8 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 24], 9 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 11 + mov r13, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 24], 1 + mov r12, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 3 mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 12 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 24], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 4 mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 15 - movzx esi, byte ptr [rdx + r8 + 24] + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 5 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 7 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 8 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 9 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 12 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 13 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 14 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 15 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 24] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 1 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 24], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 24], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 7 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 8 - mov r10, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 9 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 24], 10 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 11 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 12 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 13 - mov r8, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 14 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 15 - movzx esi, byte ptr [rdx + rcx + 25] + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 3 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 4 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 5 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 9 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 15 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 25] vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 25], 1 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 25], 2 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 25], 3 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 25], 4 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 25], 5 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 25], 6 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 7 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 25], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 25], 9 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 10 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 25], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 2 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 3 mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 12 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 4 mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 25], 15 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 25] + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 6 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 7 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 25], 8 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 9 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 10 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 11 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 14 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 15 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + r12 + 25] vmovd xmm3, esi - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 2 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 3 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 4 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 5 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 25], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 25], 10 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 11 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 14 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 25], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 5 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 + mov r8, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 25], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 9 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 12 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 14 vinserti128 ymm9, ymm1, xmm0, 1 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rax + 25], 15 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 25], 15 vinserti128 ymm8, ymm0, xmm2, 1 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 26] + movzx esi, byte ptr [rdi + rcx + 26] vmovd xmm0, esi - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 26], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 26], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 26], 4 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 6 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 26], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 26], 11 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 26], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 26], 13 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 26], 14 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 26], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 26] - vmovd xmm1, esi - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 26], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 2 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 26], 3 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 4 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 5 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 26], 6 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 7 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 8 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 26], 9 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 2 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 3 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 5 + mov r15, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 8 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 10 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 12 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 14 mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 11 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 12 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 13 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 14 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 15 - movzx esi, byte ptr [rdx + r15 + 27] - vmovd xmm2, esi - mov r15, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 27], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 27], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 15 + movzx esi, byte ptr [rdi + r12 + 26] + vmovd xmm1, esi + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 26], 1 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 3 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 4 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 5 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 6 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 7 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 8 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 2 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 3 mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 27], 12 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 27], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 27], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 27], 15 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + r12 + 27] - vmovd xmm3, esi - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 27], 1 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 27], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 3 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 7 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 27], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 4 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 5 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 7 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 8 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 26], 10 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 12 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 26], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 26], 15 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + r11 + 27] + vmovd xmm2, esi + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 1 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 27], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 3 + mov r8, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 27], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 6 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 9 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 13 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 14 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 10 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 11 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 27], 13 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 14 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 15 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 27] + vmovd xmm3, esi + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 3 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 27], 4 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 5 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 8 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 9 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 10 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 13 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 28] + movzx esi, byte ptr [rdi + r11 + 28] vmovd xmm0, esi - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 28], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 2 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 4 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 5 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 6 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 28], 7 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 9 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 28], 10 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 28], 11 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 28], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 28], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 15 - movzx esi, byte ptr [rdx + r12 + 28] - vmovd xmm1, esi - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 28], 1 - mov rdi, r11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 28], 2 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 3 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 28], 4 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 28], 5 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 9 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 10 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 11 mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 12 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 13 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 14 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 15 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 29] - vmovd xmm2, esi + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 1 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 2 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 4 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 5 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 7 mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 1 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 29], 2 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 29], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 8 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 10 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 12 mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 29], 5 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 29], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 7 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 29], 8 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 29], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 29], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 29], 11 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 29], 12 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 29], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 29], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 15 + movzx esi, byte ptr [rdi + rax + 28] + vmovd xmm1, esi + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 28], 4 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 7 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 9 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 10 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 11 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 28], 12 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 13 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 14 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 15 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 29] + vmovd xmm2, esi + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 29], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 3 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 5 + mov r10, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 29], 6 mov r13, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + r13 + 29] + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 7 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 8 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 9 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 10 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 11 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 12 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 14 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 15 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 29] vmovd xmm3, esi - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 29], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 2 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 29], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 29], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 5 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 29], 6 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 7 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 9 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 29], 11 - mov rbx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 29], 12 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 3 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 5 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 6 mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 13 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rdx + rax + 29], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 29], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 8 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 29], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + r12 + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rdx + rax + 29], 15 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rdx + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov r15, qword ptr [rsp + 216] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 30] + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 30] vmovd xmm0, esi - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 1 - movzx esi, byte ptr [rdx + r15 + 31] + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 1 + movzx esi, byte ptr [rdi + rcx + 31] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 1 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 4 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 6 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 7 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 31], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 31], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rdx + rax + 31], 15 - movzx eax, byte ptr [rdx + r13 + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 + mov rax, r10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 31], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 31], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + rax + 31], 15 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 30], 1 - movzx eax, byte ptr [rdx + r13 + 31] + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rdx + r8 + 31], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + r12 + 31], 3 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + r9 + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 31], 7 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 10 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 31], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 31], 13 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r9 + 31], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 288], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -49872,2007 +51203,2001 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 376] # 8-byte Reload - vmovdqu ymmword ptr [r15 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r15 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r15 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r15 + 4*rcx], ymm1 + vmovdqu ymmword ptr [rsi + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [rsi + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rsi + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [rsi + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB8_181 -# %bb.182: - mov r13, qword ptr [rsp + 360] # 8-byte Reload - cmp r13, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14d, dword ptr [rsp + 4] # 4-byte Reload - mov r12, qword ptr [rsp + 368] # 8-byte Reload - jne .LBB8_38 - jmp .LBB8_130 -.LBB8_183: - and r15, -32 - mov rax, r15 + jne .LBB8_206 +# %bb.207: + mov rcx, qword ptr [rsp + 360] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov r15d, dword ptr [rsp + 4] # 4-byte Reload + mov rsi, qword ptr [rsp + 368] # 8-byte Reload + jne .LBB8_136 + jmp .LBB8_140 +.LBB8_208: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx + add rax, rdi mov qword ptr [rsp + 504], rax # 8-byte Spill - mov qword ptr [rsp + 360], r15 # 8-byte Spill - lea rax, [r11 + 4*r15] + mov qword ptr [rsp + 360], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] mov qword ptr [rsp + 352], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r15d vpbroadcastb ymm0, xmm0 xor eax, eax - mov qword ptr [rsp + 232], r11 # 8-byte Spill + mov qword ptr [rsp + 240], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB8_184: # =>This Inner Loop Header: Depth=1 +.LBB8_209: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 376], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 80], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 8], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 24], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 16], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rdx + rax] + movzx eax, byte ptr [rdi + rax] + mov rdx, rcx vmovd xmm3, eax - movzx eax, byte ptr [rdx + rbx] + mov rcx, rbx + movzx eax, byte ptr [rdi + rbx] vmovd xmm4, eax - movzx eax, byte ptr [rdx + rcx + 1] - mov rdi, rcx + movzx eax, byte ptr [rdi + rdx + 1] vmovd xmm5, eax - mov rcx, rbx - movzx eax, byte ptr [rdx + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rdi + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rdi + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rdi + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 512], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rdx + rdi + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm12, eax - movzx eax, byte ptr [rdx + rdi + 6] - mov qword ptr [rsp + 200], rdi # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 224], rdx # 8-byte Spill vmovd xmm13, eax - movzx eax, byte ptr [rdx + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rdi + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 112], rax # 8-byte Spill mov rax, rbx or rax, 416 mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 128], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 544 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 576 - mov rbx, rax - mov qword ptr [rsp + 240], rax # 8-byte Spill - mov rax, rcx + mov qword ptr [rsp + 8], rax # 8-byte Spill + mov rax, rbx or rax, 608 - mov qword ptr [rsp + 160], rax # 8-byte Spill - mov rax, rcx + mov qword ptr [rsp + 200], rax # 8-byte Spill + mov rax, rbx or rax, 640 - mov r14, rax - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov r9, rcx - or r9, 672 - mov qword ptr [rsp + 40], r9 # 8-byte Spill - mov rax, rcx - or rax, 704 - mov qword ptr [rsp + 64], rax # 8-byte Spill - mov rax, rcx - or rax, 736 - mov rdi, rax - mov qword ptr [rsp + 112], rax # 8-byte Spill - mov rax, rcx - or rax, 768 - mov r13, rax - mov qword ptr [rsp + 256], rax # 8-byte Spill - mov r11, rcx - or r11, 800 - mov qword ptr [rsp + 120], r11 # 8-byte Spill - mov r10, rcx - or r10, 832 - mov qword ptr [rsp + 208], r10 # 8-byte Spill - mov r8, rcx - or r8, 864 - mov qword ptr [rsp + 216], r8 # 8-byte Spill - mov r15, rcx - or r15, 896 - mov qword ptr [rsp + 88], r15 # 8-byte Spill - mov rsi, rcx - or rsi, 928 - mov qword ptr [rsp + 136], rsi # 8-byte Spill - mov rax, rcx - mov qword ptr [rsp + 224], rcx # 8-byte Spill + mov r10, rax + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r12, rbx + or r12, 672 + mov qword ptr [rsp + 120], r12 # 8-byte Spill + mov r15, rbx + or r15, 704 + mov qword ptr [rsp + 168], r15 # 8-byte Spill + mov r14, rbx + or r14, 736 + mov qword ptr [rsp + 320], r14 # 8-byte Spill + mov rdx, rbx + or rdx, 768 + mov qword ptr [rsp + 16], rdx # 8-byte Spill + mov r8, rbx + or r8, 800 + mov qword ptr [rsp + 176], r8 # 8-byte Spill + mov rax, rbx + or rax, 832 + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov r9, rbx + or r9, 864 + mov qword ptr [rsp + 80], r9 # 8-byte Spill + mov rsi, rbx + or rsi, 896 + mov qword ptr [rsp + 216], rsi # 8-byte Spill + mov r11, rbx + or r11, 928 + mov qword ptr [rsp + 136], r11 # 8-byte Spill + mov rax, rbx + mov qword ptr [rsp + 232], rbx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 96], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 56], rcx # 8-byte Spill - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm9, xmm3, byte ptr [rdx + r12], 1 - vpinsrb xmm3, xmm9, byte ptr [rdx + rbx], 2 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 5 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 15 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14], 1 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10], 2 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11], 3 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12], 4 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8], 5 - mov r9, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9], 6 - mov r15, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15], 7 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax], 9 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx], 10 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi], 13 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi], 14 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi], 15 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 1 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 3 + mov qword ptr [rsp + 64], rcx # 8-byte Spill mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 1], 4 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 5 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 7 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 8 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 1], 9 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 1], 10 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 11 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 12 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 13 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 14 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 15 - vpinsrb xmm6, xmm10, byte ptr [rdx + r14 + 1], 1 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 1], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + r11 + 1], 3 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 1], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 1], 5 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 1], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 1], 7 - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 1], 8 - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 9 - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 1], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 1], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 12 + vpinsrb xmm9, xmm3, byte ptr [rdi + r13], 1 + mov rbx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm9, byte ptr [rdi + rbx], 2 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 9 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 15 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9], 1 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx], 2 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax], 3 + mov r11, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11], 4 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8], 5 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15], 6 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14], 7 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi], 8 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax], 9 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10], 10 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx], 11 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx], 12 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx], 13 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx], 14 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx], 15 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 1 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 1], 3 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 1], 4 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 5 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 1], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 8 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 10 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 12 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 13 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 15 + vpinsrb xmm6, xmm10, byte ptr [rdi + r9 + 1], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 1], 2 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 1], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 1], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 1], 5 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 1], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 1], 7 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 1], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 1], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 1], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 1], 12 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 1], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 1], 14 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1248], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm6, byte ptr [rdx + rax + 1], 15 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm6, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm9, esi vinserti128 ymm3, ymm3, xmm5, 1 vmovdqa ymmword ptr [rsp + 544], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 8] + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 8] vmovd xmm10, esi - mov rbx, qword ptr [rsp + 152] # 8-byte Reload + mov r8, qword ptr [rsp + 184] # 8-byte Reload vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 1 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 2], 2 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 2], 3 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 5 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 6 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 2], 1 + mov rcx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 2], 2 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 4 mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 2], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 10 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 2], 11 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 2], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 2], 5 + mov r10, r13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 6 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 2], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 8 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 10 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 2], 11 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 2], 12 mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 2], 13 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 2], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 2], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload vmovdqa xmm4, xmmword ptr [rsp + 416] # 16-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 2], 1 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 2 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 3 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 4 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 5 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 6 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 7 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 8 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 9 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 10 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 13 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 14 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 15 - vpinsrb xmm5, xmm11, byte ptr [rdx + rbx + 3], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 3], 2 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 3], 3 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 4 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 3], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 7 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 3], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 3], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 3], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 3], 12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 3], 13 - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 3], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 15 - vpinsrb xmm6, xmm8, byte ptr [rdx + rax + 3], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 2 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 3], 3 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 4 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 5 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 3], 7 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r14 + 3], 8 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 9 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 10 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 11 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 12 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 2], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 3 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 2], 4 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 6 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 7 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 8 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 9 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 10 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 12 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 13 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 14 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 15 + vpinsrb xmm5, xmm11, byte ptr [rdi + r8 + 3], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 3 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 3], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 3], 7 + mov rcx, r9 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 8 + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 3], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 3], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 3], 12 + mov r10, r14 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 3], 13 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 3], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + rax + 3], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 2 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 3], 4 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 3], 5 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 3], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 8 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 3], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 10 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 3], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 448], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm6, byte ptr [rdx + rcx + 3], 14 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 9] + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm6, byte ptr [rdi + rax + 3], 14 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 9] vmovd xmm8, esi - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 3], 15 + mov r14, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 3], 15 vinserti128 ymm3, ymm3, xmm5, 1 vmovdqa ymmword ptr [rsp + 416], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 9] + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 9] vmovd xmm11, esi - mov rbx, qword ptr [rsp + 152] # 8-byte Reload + mov r9, qword ptr [rsp + 184] # 8-byte Reload vmovdqa xmm3, xmmword ptr [rsp + 512] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 4], 1 - mov r11, r9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 4], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 3 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 4], 4 - mov rcx, r8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 4], 5 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 7 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 8 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 9 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 4], 10 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 11 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 4], 13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 14 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 4], 15 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm15, byte ptr [rdx + rsi + 4], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 4], 3 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 4], 4 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 4], 5 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 4], 6 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 4], 8 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 4], 9 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 10 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 4], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 13 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 4], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 4], 15 - mov r14, r12 - vpinsrb xmm5, xmm14, byte ptr [rdx + rbx + 5], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 5], 2 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 5], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 5], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 5], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 1 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 3 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 11 + mov r13, r10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 12 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 14 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 6 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 5], 8 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 5], 10 - mov r13, r9 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 12 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 5], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm15, byte ptr [rdi + rsi + 4], 1 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm12, byte ptr [rdx + rax + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 4], 2 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 4], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 4], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 4], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 4], 6 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 4], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 4], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 4], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 4], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 4], 11 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 4], 12 + mov r12, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 4], 13 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 4], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 4], 15 + vpinsrb xmm5, xmm14, byte ptr [rdi + r9 + 5], 1 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 9 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 10 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 5], 2 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 5], 3 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 5], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 5], 5 - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 5], 6 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 5], 7 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 5], 8 - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 5], 9 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 5], 10 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 5], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 5], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 5], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 13 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 15 + mov r8, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm12, byte ptr [rdi + r8 + 5], 1 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 5], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 5], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 4 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 5], 5 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 5], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 5], 7 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 5], 8 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 10 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 5], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 5], 12 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 5], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 13 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 5], 14 vinserti128 ymm15, ymm4, xmm3, 1 - vpinsrb xmm4, xmm6, byte ptr [rdx + r14 + 5], 15 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 10] + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm6, byte ptr [rdi + rax + 5], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 10] vmovd xmm12, esi vinserti128 ymm3, ymm4, xmm5, 1 vmovdqa ymmword ptr [rsp + 512], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 10] + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 10] vmovd xmm4, esi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm13, byte ptr [rdx + rax + 6], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 2 - mov r14, r11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 6], 3 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 5 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 6], 6 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 6], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 6], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 12 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 6], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 14 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 6], 15 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm7, byte ptr [rdx + r13 + 6], 1 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 6], 2 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 6], 3 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 6], 4 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 6], 5 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm13, byte ptr [rdi + rax + 6], 1 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 8 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 11 + mov r12, r13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 12 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 15 + vpinsrb xmm6, xmm7, byte ptr [rdi + r8 + 6], 1 + mov r13, r10 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 6], 2 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 6], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 6], 4 + mov rsi, rbx + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 6], 5 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 6], 6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 6], 7 + mov r10, r15 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 6], 8 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 6], 9 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 6], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 6], 11 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 6], 12 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 6], 13 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 6], 14 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 6], 15 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 1 mov rbx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 6], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 6], 7 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 6], 8 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 6], 9 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 6], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 6], 11 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r11 + 6], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 6], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 2 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 3 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 4 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 5 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 6 mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 6], 14 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 6], 15 - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 7], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 4 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 8 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 11 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 12 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 7], 13 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 7], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 7], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 7], 1 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 2 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 7], 3 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 5 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 6 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 7 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 7], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 7], 10 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 12 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 7 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 8 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 9 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 10 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 12 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 13 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 15 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 7], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 7], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 7], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 8 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 10 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 7], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 13 vinserti128 ymm3, ymm6, xmm5, 1 vmovdqa ymmword ptr [rsp + 1216], ymm3 # 32-byte Spill - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm1, byte ptr [rdx + rsi + 7], 14 - mov r13, rsi - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 11] + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm1, byte ptr [rdi + rax + 7], 14 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 11] vmovd xmm1, esi - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 7], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 7], 15 vinserti128 ymm2, ymm5, xmm2, 1 vmovdqa ymmword ptr [rsp + 1184], ymm2 # 32-byte Spill - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 11] + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 11] vmovd xmm2, esi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm9, byte ptr [rdx + rdi + 8], 1 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 3 mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 8], 4 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 5 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 8 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 8], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 8], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 12 - mov r10, r12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 8], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 8], 15 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm10, byte ptr [rdx + rcx + 8], 1 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 8], 2 - mov r12, r8 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 8], 3 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 4 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 8], 5 + vpinsrb xmm5, xmm9, byte ptr [rdi + r15 + 8], 1 mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 8], 6 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 8], 7 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 8], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 2 + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 3 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 4 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 5 mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r11 + 8], 9 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 8], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + r14 + 8], 11 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r14 + 8], 12 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rcx + 8], 13 - vpinsrb xmm6, xmm6, byte ptr [rdx + r13 + 8], 14 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r13 + 8], 15 - vpinsrb xmm7, xmm8, byte ptr [rdx + rdi + 9], 1 - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + r15 + 9], 4 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rdi + 9], 5 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 6 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 7 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + r9 + 9], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 8 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 10 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 11 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 12 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 13 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 8], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm10, byte ptr [rdi + rdx + 8], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 8], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 8], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 8], 4 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 8], 5 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 8], 6 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 8], 7 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 8], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 8], 9 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 8], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 8], 11 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 8], 12 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 8], 13 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 8], 14 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 8], 15 + vpinsrb xmm7, xmm8, byte ptr [rdi + r15 + 9], 1 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 4 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 9], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 9 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 12 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 9], 14 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 9], 15 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm11, byte ptr [rdi + rcx + 9], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 2 mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 11 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 12 - vpinsrb xmm7, xmm7, byte ptr [rdx + r10 + 9], 13 - mov rcx, r10 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 14 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 9], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 9], 4 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 9], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 9], 6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 8 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm11, byte ptr [rdx + rax + 9], 1 - mov r10, rax - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 9], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 9], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 5 - mov r15, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 9], 6 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 9], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 9], 9 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 10 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 9], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 9], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 9], 10 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 12 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 9], 14 vinserti128 ymm5, ymm6, xmm5, 1 vmovdqa ymmword ptr [rsp + 1152], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 12] vmovd xmm5, esi vinserti128 ymm3, ymm3, xmm7, 1 vmovdqa ymmword ptr [rsp + 1120], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 12] + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 12] vmovd xmm6, esi - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm12, byte ptr [rdx + r9 + 10], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 2 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 10], 3 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 5 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 6 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 10], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 8 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm12, byte ptr [rdi + rax + 10], 1 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 2 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 3 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 5 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 7 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 8 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 10 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 11 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 13 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 2 mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 10 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 10], 11 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 13 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 10], 15 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 10], 1 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 10], 2 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 10], 3 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 4 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 6 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 7 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 8 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 10], 9 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 10], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 12 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 13 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 14 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 1 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 4 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 11], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 11], 7 - mov r8, r11 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 11], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 11], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 3 + mov r11, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 5 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 6 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 8 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 10 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 11 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 10], 12 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 13 + mov rdx, r13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 14 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 15 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 1 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 4 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 11], 8 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 9 + mov r15, rax + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 11], 12 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 11], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 15 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 1 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 11], 6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 8 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 10 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 5 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 6 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 7 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 11], 9 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 11], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 11 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 12 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 11], 12 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1088], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 14 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 13] + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 11], 14 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] vmovd xmm3, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1056], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 13] + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 13] vmovd xmm1, esi - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rdx + r11 + 12], 1 - mov r10, r9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 12], 2 - mov rcx, r14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 12], 3 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 12], 4 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 5 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 12], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 8 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 9 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 10 - mov r8, r12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 12], 11 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 12], 12 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 12], 13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 14 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 15 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm6, byte ptr [rdx + rsi + 12], 1 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 12], 2 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 12], 3 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 12], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 12], 5 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + rbx + 12], 1 mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 12], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 2 + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 3 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 12], 7 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 12], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 12], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 12], 10 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 12], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 12], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 12], 13 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 12], 14 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 13], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 13], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 5 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 6 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 12], 7 + mov r11, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 9 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 10 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 11 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 12 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 13 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 14 mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 6 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 13], 7 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 8 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm6, byte ptr [rdi + rsi + 12], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 12], 2 mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 13 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 15 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 2 - mov r9, rsi + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 4 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 5 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 6 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 12], 8 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 12], 9 mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 3 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 4 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 10 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 11 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 12], 12 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 13 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 12], 14 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 1 mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 6 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 13], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 9 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 10 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 4 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 13], 8 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 10 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 13], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 2 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 5 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 7 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 9 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 10 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 12 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 14 vinserti128 ymm2, ymm4, xmm2, 1 vmovdqa ymmword ptr [rsp + 1024], ymm2 # 32-byte Spill - mov r12, r13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 13], 15 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + r14 + 14] + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 14] vmovd xmm2, esi vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 992], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 14] + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rbx + 14] vmovd xmm1, esi - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 14], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 14], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 14], 3 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 14], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 5 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 14], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 8 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 10 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 14], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 12 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 13 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 14], 14 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 14], 15 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 14], 2 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 14], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 5 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 6 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 14], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 14], 2 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 14], 3 mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 7 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 8 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 9 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 10 - mov r15, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 11 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 12 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 14], 4 + mov rcx, r14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 14], 5 + mov r14, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 14], 6 mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 14], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 14], 15 - movzx esi, byte ptr [rdx + r14 + 15] - vmovd xmm3, esi - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 15], 1 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 15], 4 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 5 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 15], 6 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 7 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 8 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 9 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 15], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 11 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 7 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 8 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 14], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 12 mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 15], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 14 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 14], 15 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 4 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 6 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 14], 8 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 11 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 14], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 13 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 14 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 15 mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 15] + movzx esi, byte ptr [rdi + rsi + 15] + vmovd xmm3, esi + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 1 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 7 + mov r14, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 8 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 10 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 13 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 15 + movzx esi, byte ptr [rdi + rbx + 15] vmovd xmm4, esi - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 15], 1 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 15], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 15], 3 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 15], 4 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 15], 5 - mov r13, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 15], 6 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 15], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 8 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 15], 9 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 15], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 15], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 15], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 13 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 15], 14 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 2 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 15], 4 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 15], 5 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 15], 6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 8 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 15], 10 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 15], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 15], 12 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 15], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 15], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 15], 15 vinserti128 ymm1, ymm1, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm1 # 32-byte Spill vinserti128 ymm1, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 960], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 16] + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 16] vmovd xmm1, esi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 1 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 16], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 3 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 16], 6 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 8 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 16], 10 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 16], 11 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 12 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 14 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 15 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 16] + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 1 + mov r9, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 2 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 3 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 4 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 5 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 16], 11 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 12 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 15 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + r14 + 16] vmovd xmm2, esi - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 16], 1 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 16], 2 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 16], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 16], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 16], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 16], 6 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 16], 7 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 16], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 16], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 16], 10 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 16], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 16], 12 - mov r11, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 16], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 16], 14 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 16], 15 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rdi + 17] - vmovd xmm3, esi - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 17], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 3 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 17], 4 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 5 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 17], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 8 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 9 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 17], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 17], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 17] - vmovd xmm4, esi - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 1 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 17], 2 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 17], 3 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 16], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 16], 2 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 16], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 16], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 16], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 16], 6 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 16], 7 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 16], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 10 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 5 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 17], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 17], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 11 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 16], 12 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 14 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 15 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + r12 + 17] + vmovd xmm3, esi + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 2 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 4 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 5 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 7 mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 10 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 12 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 17], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 15 + movzx esi, byte ptr [rdi + r14 + 17] + vmovd xmm4, esi + mov r15, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 17], 1 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 17], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 17], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 5 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 6 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 17], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 17], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 8 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 17], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 17], 10 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 17], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 17], 12 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 17], 13 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 17], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 896], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm4, byte ptr [rdx + rax + 17], 15 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm4, byte ptr [rdi + rsi + 17], 15 vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 864], ymm1 # 32-byte Spill - movzx esi, byte ptr [rdx + rdi + 18] + movzx esi, byte ptr [rdi + r12 + 18] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 2 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 18], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 18], 6 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 18], 7 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 8 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 9 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 18], 10 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 18], 11 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 12 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 13 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 18], 14 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 15 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + r9 + 18] - vmovd xmm2, esi - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 18], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 18], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 18], 3 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 4 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 18], 5 + mov r12, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 1 mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 6 - mov r12, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 18], 7 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 8 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 3 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 6 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 7 mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 10 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 11 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 12 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 13 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 18], 14 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 18], 15 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 19] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 8 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 10 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 11 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 13 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 15 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 18] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 18], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 18], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 18], 3 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 18], 4 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 18], 5 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 18], 6 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 18], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 18], 8 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 18], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 18], 10 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 18], 11 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 18], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 18], 13 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 18], 14 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 18], 15 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 19] vmovd xmm3, esi - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 19], 3 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 5 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 19], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 8 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 19], 11 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 19], 12 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 19], 14 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 15 - movzx esi, byte ptr [rdx + r9 + 19] - vmovd xmm4, esi - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 1 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 19], 2 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 3 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 19], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 19], 5 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 19], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 19], 7 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 19], 8 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 19], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 1 + mov r8, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 2 + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 3 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 4 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 7 mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 19], 10 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 19], 11 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 19], 12 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 19], 13 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 19], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 19], 15 - vinserti128 ymm1, ymm2, xmm1, 1 - vmovdqa ymmword ptr [rsp + 800], ymm1 # 32-byte Spill - vinserti128 ymm1, ymm4, xmm3, 1 - vmovdqa ymmword ptr [rsp + 832], ymm1 # 32-byte Spill - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 20] - vmovd xmm1, esi - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 1 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 3 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 4 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 20], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 8 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 9 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 10 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 12 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 14 mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 15 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + r12 + 19] + vmovd xmm4, esi mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 20], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 20], 10 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 20], 12 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 13 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 15 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 20] + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 19], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 19], 2 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 19], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 19], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 19], 5 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 19], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 19], 7 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 19], 8 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 19], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 11 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 19], 12 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 19], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 19], 15 + vinserti128 ymm1, ymm2, xmm1, 1 + vmovdqa ymmword ptr [rsp + 800], ymm1 # 32-byte Spill + vinserti128 ymm1, ymm4, xmm3, 1 + vmovdqa ymmword ptr [rsp + 832], ymm1 # 32-byte Spill + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 20] + vmovd xmm1, esi + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 20], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 5 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 8 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 15 + movzx esi, byte ptr [rdi + r12 + 20] vmovd xmm2, esi - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 20], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 20], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 20], 4 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 20], 5 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 6 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 20], 8 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 9 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 10 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 20], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 20], 12 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 1 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 20], 2 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 20], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 6 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 20], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 20], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 20], 9 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 20], 10 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 20], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 20], 12 mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 13 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 14 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 15 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 21] + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 20], 13 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 20], 14 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 20], 15 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + r15 + 21] vmovd xmm3, esi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 1 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 2 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 21], 3 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 21], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 1 + mov rcx, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 2 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 3 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 4 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 6 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 7 + mov r10, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 21], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 10 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 12 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 14 mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 8 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 10 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 21], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 15 - movzx esi, byte ptr [rdx + r15 + 21] - mov rbx, r15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 15 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 21] vmovd xmm4, esi + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 21], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 21], 2 + mov r9, r12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 21], 3 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 21], 4 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 21], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 8 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 1 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 21], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 9 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 10 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 21], 5 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 6 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 21], 7 - mov r12, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 21], 8 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 21], 9 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 21], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 21], 11 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 21], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 12 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 21], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 736], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm4, byte ptr [rdx + rax + 21], 15 + vpinsrb xmm1, xmm4, byte ptr [rdi + r8 + 21], 15 vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 768], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 22] + movzx esi, byte ptr [rdi + r15 + 22] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 22], 3 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 4 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 5 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 6 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 8 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 22], 9 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 10 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 11 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 22], 12 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 13 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 22], 14 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 15 - movzx esi, byte ptr [rdx + rbx + 22] + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 22], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 4 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 22], 8 + mov rbx, r11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 9 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 11 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 12 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 13 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 22], 14 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 22] vmovd xmm2, esi + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 22], 1 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 22], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 22], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 22], 4 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 22], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 22], 6 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 22], 7 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 22], 8 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 22], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 22], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 22], 9 mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 22], 3 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 22], 4 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 22], 5 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 22], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 22], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 22], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 22], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 22], 10 - mov r12, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 22], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 22], 12 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 22], 13 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 22], 14 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 22], 15 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 23] + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 22], 10 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 22], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 22], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 22], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 22], 15 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + r13 + 23] vmovd xmm3, esi - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 23], 1 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 23], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 23], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 23], 5 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 23], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 9 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 10 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 23], 12 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 23], 14 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 15 - movzx esi, byte ptr [rdx + rbx + 23] + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 1 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 4 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 10 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 12 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 23], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 23] vmovd xmm4, esi + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 23], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 23], 2 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 23], 3 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 23], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 23], 5 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 23], 6 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 23], 7 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 23], 8 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 1 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 2 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 23], 3 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 4 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 5 - mov rbx, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 23], 6 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 7 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 8 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 9 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 23], 11 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 23], 13 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 23], 14 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 23], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 23], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 23], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 23], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 23], 12 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 23], 13 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 23], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 23], 15 vinserti128 ymm11, ymm2, xmm1, 1 vinserti128 ymm12, ymm4, xmm3, 1 - movzx esi, byte ptr [rdx + r15 + 24] + movzx esi, byte ptr [rdi + r13 + 24] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 24], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 3 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 4 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 5 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 24], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 8 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 24], 11 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 12 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 13 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 14 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 24], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 24] + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 1 + mov r9, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 3 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 5 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 7 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 8 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 9 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 11 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 15 + movzx esi, byte ptr [rdi + rax + 24] vmovd xmm2, esi - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 24], 3 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 4 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 24], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 24], 6 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 7 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 9 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 24], 10 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 24], 11 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 2 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 24], 4 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 24], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 24], 6 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 24], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 24], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 24], 15 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 25] + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 24], 8 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 24], 9 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 24], 10 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 24], 11 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 24], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 24], 13 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 24], 14 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 24], 15 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 25] vmovd xmm3, esi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 25], 6 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 25], 9 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 10 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 12 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 25], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 25], 15 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + r10 + 25] - vmovd xmm4, esi - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 25], 1 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 25], 2 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 25], 3 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 25], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 25], 5 - mov r11, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 25], 6 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 25], 7 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 2 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 4 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 5 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 7 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 8 mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 25], 8 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 25], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 25], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 25], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 25], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 25], 13 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 25], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 10 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 12 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 14 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 25], 15 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + r11 + 25] + vmovd xmm4, esi + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 25], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 25], 2 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 25], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 25], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 25], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 25], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 7 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 25], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 25], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 25], 10 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 25], 11 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 25], 12 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 13 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 384], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm4, byte ptr [rdx + rcx + 25], 15 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm4, byte ptr [rdi + r13 + 25], 15 vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 576], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 26] + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rbx + 26] vmovd xmm1, esi - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 26], 1 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 26], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 26], 3 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 4 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 5 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 26], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 8 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 26], 10 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 12 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 26], 13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 14 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 15 - movzx esi, byte ptr [rdx + r10 + 26] + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 1 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 3 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 4 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 6 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 7 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 8 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 10 + mov rdx, r12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 11 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 26], 15 + movzx esi, byte ptr [rdi + r11 + 26] vmovd xmm2, esi + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 1 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 26], 2 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 4 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 6 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 26], 8 mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 26], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 9 mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 26], 4 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 26], 6 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 7 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 26], 9 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 10 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 26], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 26], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 26], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 26], 12 mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 26], 14 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 26], 15 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + r15 + 27] + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 13 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 26], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 26], 15 + movzx esi, byte ptr [rdi + rbx + 27] vmovd xmm3, esi - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 1 - mov r10, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 27], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 1 + mov r9, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 2 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 4 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 5 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 27], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 7 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 9 mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 27], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 7 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 27], 8 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 9 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 27], 10 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 27], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 27], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 27] + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 12 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 13 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 15 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 27] vmovd xmm4, esi - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 1 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 27], 2 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 3 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 4 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 27], 5 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 6 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 27], 7 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 8 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 9 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 27], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 27], 13 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 27], 14 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 27], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 27], 2 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 27], 3 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 4 mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 27], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 6 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 7 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 8 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 10 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 12 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 13 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 14 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 27], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 608], ymm1 # 32-byte Spill vinserti128 ymm1, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 640], ymm1 # 32-byte Spill - movzx esi, byte ptr [rdx + r15 + 28] + movzx esi, byte ptr [rdi + rbx + 28] vmovd xmm1, esi - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 28], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 3 mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 5 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 28], 6 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 28], 8 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 28], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 28], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 28], 11 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 12 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 13 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 14 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 28], 15 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 28] + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 28], 8 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 13 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 15 + movzx esi, byte ptr [rdi + rdx + 28] vmovd xmm2, esi - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 28], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 28], 2 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 28], 3 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 28], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 28], 5 - mov r8, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 28], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 28], 7 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 28], 8 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 28], 9 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 28], 10 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 28], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 28], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 13 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 28], 14 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 15 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 29] + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 28], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 28], 3 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 28], 4 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 28], 5 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 7 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 28], 8 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 28], 9 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 28], 10 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 28], 11 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 28], 12 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 28], 13 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 28], 14 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 28], 15 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rsi + 29] vmovd xmm3, esi - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 1 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 2 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 3 mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 1 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 2 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 3 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 4 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 5 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 6 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 7 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 8 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 9 mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 29], 6 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 7 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 9 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 10 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 29], 11 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 10 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 11 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 12 mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 29], 15 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 29] + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 14 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 15 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + movzx esi, byte ptr [rdi + r12 + 29] vmovd xmm4, esi - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 29], 1 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 29], 2 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 29], 3 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 29], 4 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 29], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 29], 6 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 29], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 29], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 29], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 29], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 29], 11 - mov r13, rdi - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 29], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 29], 13 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 29], 14 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 29], 1 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 29], 2 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 29], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 29], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 29], 5 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 29], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 29], 7 + mov r9, rax + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 29], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 29], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 29], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 29], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 29], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 29], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 29], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 672], ymm1 # 32-byte Spill - vpinsrb xmm1, xmm4, byte ptr [rdx + rax + 29], 15 - mov r12, rax + vpinsrb xmm1, xmm4, byte ptr [rdi + r15 + 29], 15 vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 704], ymm1 # 32-byte Spill - mov r8, qword ptr [rsp + 200] # 8-byte Reload - movzx esi, byte ptr [rdx + r8 + 30] + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 30] vmovd xmm1, esi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 1 - movzx esi, byte ptr [rdx + r8 + 31] - vmovd xmm2, esi - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 1 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 3 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 5 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 6 - mov r11, qword ptr [rsp + 232] # 8-byte Reload - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 7 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 1 + movzx esi, byte ptr [rdi + rcx + 31] + vmovd xmm2, esi + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 1 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 4 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 30], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 31], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 9 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 11 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 12 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 15 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - movzx eax, byte ptr [rdx + rsi + 30] + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 15 + mov rcx, r12 + movzx eax, byte ptr [rdi + r12 + 30] vmovd xmm3, eax - mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 30], 1 - movzx eax, byte ptr [rdx + rsi + 31] + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 30], 1 + movzx eax, byte ptr [rdi + r12 + 31] vmovd xmm4, eax - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 31], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 30], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 31], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 30], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 31], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 5 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 6 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 30], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 31], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 30], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 31], 9 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 30], 11 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 31], 11 - mov rax, rbx - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 30], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 31], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 30], 13 - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 31], 13 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 30], 15 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 31], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 31], 1 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 30], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 31], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 30], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 31], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 30], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 31], 8 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 30], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 31], 10 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 30], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 31], 12 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 30], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 31], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 30], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 31], 15 vinserti128 ymm1, ymm3, xmm1, 1 vmovdqa ymmword ptr [rsp + 288], ymm1 # 32-byte Spill vinserti128 ymm1, ymm4, xmm2, 1 @@ -52045,22 +53370,22 @@ comparison_greater_scalar_arr_avx2: # @comparison_greater_scalar_arr_avx2 vinserti128 ymm5, ymm4, xmm1, 1 vperm2i128 ymm1, ymm4, ymm1, 49 # ymm1 = ymm4[2,3],ymm1[2,3] mov rcx, qword ptr [rsp + 376] # 8-byte Reload - vmovdqu ymmword ptr [r11 + 4*rcx + 96], ymm1 - vmovdqu ymmword ptr [r11 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r11 + 4*rcx + 32], ymm5 - vmovdqu ymmword ptr [r11 + 4*rcx], ymm3 + vmovdqu ymmword ptr [rsi + 4*rcx + 96], ymm1 + vmovdqu ymmword ptr [rsi + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [rsi + 4*rcx + 32], ymm5 + vmovdqu ymmword ptr [rsi + 4*rcx], ymm3 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 360] # 8-byte Folded Reload - jne .LBB8_184 -# %bb.185: - mov r15, qword ptr [rsp + 368] # 8-byte Reload - cmp r15, qword ptr [rsp + 360] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - mov r14d, dword ptr [rsp + 4] # 4-byte Reload - mov r12, qword ptr [rsp + 504] # 8-byte Reload - jne .LBB8_101 - jmp .LBB8_125 + jne .LBB8_209 +# %bb.210: + mov rcx, qword ptr [rsp + 368] # 8-byte Reload + cmp rcx, qword ptr [rsp + 360] # 8-byte Folded Reload + mov r14, qword ptr [rsp + 248] # 8-byte Reload + mov r15d, dword ptr [rsp + 4] # 4-byte Reload + mov r11, qword ptr [rsp + 504] # 8-byte Reload + jne .LBB8_150 + jmp .LBB8_154 .Lfunc_end8: .size comparison_greater_scalar_arr_avx2, .Lfunc_end8-comparison_greater_scalar_arr_avx2 # -- End function @@ -52079,79 +53404,94 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 and rsp, -8 sub rsp, 72 # kill: def $r9d killed $r9d def $r9 - mov r11, r8 - mov r14, rcx + mov r13, r8 + mov r15, rcx cmp edi, 6 - jg .LBB9_29 + jg .LBB9_35 # %bb.1: cmp edi, 3 jle .LBB9_2 -# %bb.15: +# %bb.18: cmp edi, 4 - je .LBB9_68 -# %bb.16: + je .LBB9_83 +# %bb.19: cmp edi, 5 - je .LBB9_79 -# %bb.17: + je .LBB9_97 +# %bb.20: cmp edi, 6 - jne .LBB9_123 -# %bb.18: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB9_153 +# %bb.21: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_22 -# %bb.19: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB9_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB9_20 -# %bb.21: - add r14, 1 -.LBB9_22: - sar r15, 5 - cmp r11, 32 - jl .LBB9_26 + je .LBB9_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_26 # %bb.23: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 .LBB9_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill + mov ecx, dword ptr [rsi + 4*rax] + cmp ecx, dword ptr [rdx + 4*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl + add rax, 1 + add r10, -4 + cmp r8, rax + jne .LBB9_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB9_26: + sub r13, r8 + je .LBB9_153 +# %bb.27: + add r15, 1 +.LBB9_28: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_32 +# %bb.29: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB9_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - setae byte ptr [rsp + 32] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] setae byte ptr [rsp + 20] # 1-byte Folded Spill @@ -52175,7 +53515,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 9] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - setae r8b + setae dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] setae r11b @@ -52215,7 +53555,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 11] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - setae byte ptr [rsp + 12] # 1-byte Folded Spill + setae byte ptr [rsp + 14] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] setae r9b @@ -52224,10 +53564,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 19] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - setae byte ptr [rsp + 13] # 1-byte Folded Spill + setae byte ptr [rsp + 12] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - setae byte ptr [rsp + 14] # 1-byte Folded Spill + setae byte ptr [rsp + 13] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] setae byte ptr [rsp + 15] # 1-byte Folded Spill @@ -52242,10 +53582,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 17] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] - setae dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setae r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -52254,34 +53594,34 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -52294,22 +53634,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -52326,27 +53667,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_24 -# %bb.25: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_26: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.27: - sub r11, r15 + jne .LBB9_30 +# %bb.31: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_32: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB9_28: # =>This Inner Loop Header: Depth=1 +.LBB9_34: # =>This Inner Loop Header: Depth=1 mov eax, dword ptr [rsi + 4*rcx] cmp eax, dword ptr [rdx + 4*rcx] lea r8, [rcx + 1] @@ -52354,7 +53694,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -52362,74 +53702,89 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_28 - jmp .LBB9_123 -.LBB9_29: + cmp r13, r8 + jne .LBB9_34 + jmp .LBB9_153 +.LBB9_35: cmp edi, 8 - jle .LBB9_30 -# %bb.43: + jle .LBB9_36 +# %bb.52: cmp edi, 9 - je .LBB9_101 -# %bb.44: + je .LBB9_125 +# %bb.53: cmp edi, 11 - je .LBB9_112 -# %bb.45: + je .LBB9_139 +# %bb.54: cmp edi, 12 - jne .LBB9_123 -# %bb.46: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB9_153 +# %bb.55: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_50 -# %bb.47: - movsxd rax, r9d + je .LBB9_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_60 +# %bb.57: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_48: # =>This Inner Loop Header: Depth=1 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - vucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_58: # =>This Inner Loop Header: Depth=1 + vmovsd xmm0, qword ptr [rsi + 8*rax] # xmm0 = mem[0],zero + vucomisd xmm0, qword ptr [rdx + 8*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_48 -# %bb.49: - add r14, 1 -.LBB9_50: - sar r15, 5 - cmp r11, 32 - jl .LBB9_54 -# %bb.51: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB9_58 +# %bb.59: + sub rsi, r10 + sub rdx, r10 +.LBB9_60: + sub r13, r8 + je .LBB9_153 +# %bb.61: + add r15, 1 +.LBB9_62: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_66 +# %bb.63: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero vmovsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero vucomisd xmm0, qword ptr [rdx] @@ -52453,7 +53808,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 vmovsd xmm0, qword ptr [rsi + 56] # xmm0 = mem[0],zero setae r13b vucomisd xmm0, qword ptr [rdx + 56] - setae r15b + setae r14b vmovsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 64] vmovsd xmm0, qword ptr [rsi + 72] # xmm0 = mem[0],zero @@ -52484,7 +53839,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 14] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 136] vmovsd xmm0, qword ptr [rsi + 144] # xmm0 = mem[0],zero - setae r14b + setae r15b vucomisd xmm0, qword ptr [rdx + 144] vmovsd xmm0, qword ptr [rsi + 152] # xmm0 = mem[0],zero setae r12b @@ -52530,8 +53885,8 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 add al, al add al, byte ptr [rsp + 4] # 1-byte Folded Reload shl r13b, 6 - shl r15b, 7 - or r15b, r13b + shl r14b, 7 + or r14b, r13b movzx r13d, byte ptr [rsp + 5] # 1-byte Folded Reload shl r13b, 2 or r13b, al @@ -52561,17 +53916,17 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl r9b, 6 shl bl, 7 or bl, r9b - or r15b, cl + or r14b, cl or bl, al - add r14b, r14b - add r14b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r15b, r15b + add r15b, byte ptr [rsp + 14] # 1-byte Folded Reload shl r12b, 2 - or r12b, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or r12b, r15b movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 or al, r12b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 or al, cl @@ -52579,12 +53934,12 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r8b, 7 or r8b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r8b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al @@ -52609,24 +53964,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl dil, 7 or dil, al or dil, cl - mov byte ptr [r14 + 2], r8b - mov byte ptr [r14 + 3], dil + mov byte ptr [r15 + 2], r8b + mov byte ptr [r15 + 3], dil add rdx, 256 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB9_52 -# %bb.53: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB9_54: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.55: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB9_64 +# %bb.65: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB9_66: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB9_56: # =>This Inner Loop Header: Depth=1 +.LBB9_68: # =>This Inner Loop Header: Depth=1 vmovsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero vucomisd xmm0, qword ptr [rdx + 8*rcx] lea r8, [rcx + 1] @@ -52634,7 +53988,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -52642,72 +53996,93 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_56 - jmp .LBB9_123 + cmp r13, r8 + jne .LBB9_68 + jmp .LBB9_153 .LBB9_2: cmp edi, 2 - je .LBB9_57 + mov r8, r15 + je .LBB9_69 # %bb.3: cmp edi, 3 - jne .LBB9_123 + jne .LBB9_153 # %bb.4: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_8 + je .LBB9_11 # %bb.5: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB9_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setge r10b - neg r10b - lea rdi, [rax + 7] + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 test rax, rax - cmovns rdi, rax + jle .LBB9_9 +# %bb.6: + movsxd rbx, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB9_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setge r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r15, r8 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB9_6 -# %bb.7: - add r14, 1 -.LBB9_8: - sar r15, 5 - cmp r11, 32 - jl .LBB9_12 -# %bb.9: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov byte ptr [r8 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB9_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB9_9: + sub r13, rax + je .LBB9_153 +# %bb.10: + add r15, 1 +.LBB9_11: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_15 +# %bb.12: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setge cl movzx eax, byte ptr [rsi + 2] @@ -52727,7 +54102,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 4] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setge r15b + setge r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] setge byte ptr [rsp + 7] # 1-byte Folded Spill @@ -52742,7 +54117,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setge r14b + setge r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] setge byte ptr [rsp + 5] # 1-byte Folded Spill @@ -52802,12 +54177,12 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 cmp al, byte ptr [rdx + 31] setge r8b add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload mov eax, ecx movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, al @@ -52829,26 +54204,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 6] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 13] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 4 or al, cl @@ -52856,12 +54231,12 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al @@ -52887,24 +54262,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB9_10 -# %bb.11: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB9_12: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.13: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB9_13 +# %bb.14: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB9_15: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB9_14: # =>This Inner Loop Header: Depth=1 +.LBB9_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -52912,7 +54286,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -52920,74 +54294,89 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_14 - jmp .LBB9_123 -.LBB9_30: + cmp r13, r8 + jne .LBB9_17 + jmp .LBB9_153 +.LBB9_36: cmp edi, 7 - je .LBB9_90 -# %bb.31: + je .LBB9_111 +# %bb.37: cmp edi, 8 - jne .LBB9_123 -# %bb.32: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB9_153 +# %bb.38: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_36 -# %bb.33: - movsxd rax, r9d + je .LBB9_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_41: # =>This Inner Loop Header: Depth=1 + mov rcx, qword ptr [rsi + 8*rax] + cmp rcx, qword ptr [rdx + 8*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_34 -# %bb.35: - add r14, 1 -.LBB9_36: - sar r15, 5 - cmp r11, 32 - jl .LBB9_40 -# %bb.37: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB9_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB9_43: + sub r13, r8 + je .LBB9_153 +# %bb.44: + add r15, 1 +.LBB9_45: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_49 +# %bb.46: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setae byte ptr [rsp + 32] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] setae byte ptr [rsp + 20] # 1-byte Folded Spill @@ -53011,7 +54400,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setae r8b + setae dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setae r11b @@ -53051,7 +54440,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 11] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setae byte ptr [rsp + 12] # 1-byte Folded Spill + setae byte ptr [rsp + 14] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setae r9b @@ -53060,10 +54449,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 19] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setae byte ptr [rsp + 13] # 1-byte Folded Spill + setae byte ptr [rsp + 12] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setae byte ptr [rsp + 14] # 1-byte Folded Spill + setae byte ptr [rsp + 13] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] setae byte ptr [rsp + 15] # 1-byte Folded Spill @@ -53078,10 +54467,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] - setae dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setae r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -53090,34 +54479,34 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -53130,22 +54519,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -53162,27 +54552,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_38 -# %bb.39: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_40: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.41: - sub r11, r15 + jne .LBB9_47 +# %bb.48: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_49: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB9_42: # =>This Inner Loop Header: Depth=1 +.LBB9_51: # =>This Inner Loop Header: Depth=1 mov rax, qword ptr [rsi + 8*rcx] cmp rax, qword ptr [rdx + 8*rcx] lea r8, [rcx + 1] @@ -53190,7 +54579,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -53198,68 +54587,83 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_42 - jmp .LBB9_123 -.LBB9_68: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_51 + jmp .LBB9_153 +.LBB9_83: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_72 -# %bb.69: - movsxd rax, r9d + je .LBB9_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_86: # =>This Inner Loop Header: Depth=1 + movzx ecx, word ptr [rsi + 2*rax] + cmp cx, word ptr [rdx + 2*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_70 -# %bb.71: - add r14, 1 -.LBB9_72: - sar r15, 5 - cmp r11, 32 - jl .LBB9_76 -# %bb.73: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB9_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB9_88: + sub r13, r8 + je .LBB9_153 +# %bb.89: + add r15, 1 +.LBB9_90: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_94 +# %bb.91: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setae byte ptr [rsp + 32] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] setae byte ptr [rsp + 20] # 1-byte Folded Spill @@ -53283,7 +54687,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setae r8b + setae dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setae r11b @@ -53323,7 +54727,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 11] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setae byte ptr [rsp + 12] # 1-byte Folded Spill + setae byte ptr [rsp + 14] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setae r9b @@ -53332,10 +54736,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 19] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setae byte ptr [rsp + 13] # 1-byte Folded Spill + setae byte ptr [rsp + 12] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setae byte ptr [rsp + 14] # 1-byte Folded Spill + setae byte ptr [rsp + 13] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] setae byte ptr [rsp + 15] # 1-byte Folded Spill @@ -53350,10 +54754,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] - setae dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setae r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -53362,34 +54766,34 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -53402,22 +54806,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -53434,27 +54839,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 64 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_74 -# %bb.75: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_76: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.77: - sub r11, r15 + jne .LBB9_92 +# %bb.93: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_94: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB9_78: # =>This Inner Loop Header: Depth=1 +.LBB9_96: # =>This Inner Loop Header: Depth=1 movzx eax, word ptr [rsi + 2*rcx] cmp ax, word ptr [rdx + 2*rcx] lea r8, [rcx + 1] @@ -53462,7 +54866,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -53470,68 +54874,83 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_78 - jmp .LBB9_123 -.LBB9_79: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_96 + jmp .LBB9_153 +.LBB9_97: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_83 -# %bb.80: - movsxd rax, r9d + je .LBB9_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setge r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB9_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setge r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_81 -# %bb.82: - add r14, 1 -.LBB9_83: - sar r15, 5 - cmp r11, 32 - jl .LBB9_87 -# %bb.84: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB9_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB9_102: + sub r13, r8 + je .LBB9_153 +# %bb.103: + add r15, 1 +.LBB9_104: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_108 +# %bb.105: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setge byte ptr [rsp + 32] # 1-byte Folded Spill + setge byte ptr [rsp + 40] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] setge byte ptr [rsp + 20] # 1-byte Folded Spill @@ -53555,7 +54974,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setge r8b + setge dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setge r11b @@ -53595,7 +55014,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 11] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setge byte ptr [rsp + 12] # 1-byte Folded Spill + setge byte ptr [rsp + 14] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setge r9b @@ -53604,10 +55023,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 19] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setge byte ptr [rsp + 13] # 1-byte Folded Spill + setge byte ptr [rsp + 12] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setge byte ptr [rsp + 14] # 1-byte Folded Spill + setge byte ptr [rsp + 13] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] setge byte ptr [rsp + 15] # 1-byte Folded Spill @@ -53622,10 +55041,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] - setge dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setge r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -53634,34 +55053,34 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -53674,22 +55093,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -53706,27 +55126,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 64 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_85 -# %bb.86: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_87: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.88: - sub r11, r15 + jne .LBB9_106 +# %bb.107: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_108: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB9_89: # =>This Inner Loop Header: Depth=1 +.LBB9_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -53734,7 +55153,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -53742,68 +55161,83 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_89 - jmp .LBB9_123 -.LBB9_101: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_110 + jmp .LBB9_153 +.LBB9_125: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_105 -# %bb.102: - movsxd rax, r9d + je .LBB9_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setge r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB9_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setge r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_103 -# %bb.104: - add r14, 1 -.LBB9_105: - sar r15, 5 - cmp r11, 32 - jl .LBB9_109 -# %bb.106: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB9_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB9_130: + sub r13, r8 + je .LBB9_153 +# %bb.131: + add r15, 1 +.LBB9_132: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_136 +# %bb.133: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setge byte ptr [rsp + 32] # 1-byte Folded Spill + setge byte ptr [rsp + 40] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] setge byte ptr [rsp + 20] # 1-byte Folded Spill @@ -53827,7 +55261,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setge r8b + setge dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setge r11b @@ -53867,7 +55301,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 11] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setge byte ptr [rsp + 12] # 1-byte Folded Spill + setge byte ptr [rsp + 14] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setge r9b @@ -53876,10 +55310,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 19] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setge byte ptr [rsp + 13] # 1-byte Folded Spill + setge byte ptr [rsp + 12] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setge byte ptr [rsp + 14] # 1-byte Folded Spill + setge byte ptr [rsp + 13] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] setge byte ptr [rsp + 15] # 1-byte Folded Spill @@ -53894,10 +55328,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] - setge dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setge r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -53906,34 +55340,34 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -53946,22 +55380,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -53978,27 +55413,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_107 -# %bb.108: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_109: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.110: - sub r11, r15 + jne .LBB9_134 +# %bb.135: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_136: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.137: xor ecx, ecx .p2align 4, 0x90 -.LBB9_111: # =>This Inner Loop Header: Depth=1 +.LBB9_138: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -54006,7 +55440,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -54014,62 +55448,77 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_111 - jmp .LBB9_123 -.LBB9_112: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_138 + jmp .LBB9_153 +.LBB9_139: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_116 -# %bb.113: - movsxd rax, r9d + je .LBB9_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_144 +# %bb.141: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_114: # =>This Inner Loop Header: Depth=1 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - vucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_142: # =>This Inner Loop Header: Depth=1 + vmovss xmm0, dword ptr [rsi + 4*rax] # xmm0 = mem[0],zero,zero,zero + vucomiss xmm0, dword ptr [rdx + 4*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_114 -# %bb.115: - add r14, 1 -.LBB9_116: - sar r15, 5 - cmp r11, 32 - jl .LBB9_120 -# %bb.117: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB9_142 +# %bb.143: + sub rsi, r10 + sub rdx, r10 +.LBB9_144: + sub r13, r8 + je .LBB9_153 +# %bb.145: + add r15, 1 +.LBB9_146: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_150 +# %bb.147: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero vmovss xmm1, dword ptr [rsi + 4] # xmm1 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx] @@ -54093,7 +55542,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 vmovss xmm0, dword ptr [rsi + 28] # xmm0 = mem[0],zero,zero,zero setae r13b vucomiss xmm0, dword ptr [rdx + 28] - setae r15b + setae r14b vmovss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 32] vmovss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero @@ -54124,7 +55573,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 14] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 68] vmovss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero - setae r14b + setae r15b vucomiss xmm0, dword ptr [rdx + 72] vmovss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero setae r12b @@ -54170,8 +55619,8 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 add al, al add al, byte ptr [rsp + 4] # 1-byte Folded Reload shl r13b, 6 - shl r15b, 7 - or r15b, r13b + shl r14b, 7 + or r14b, r13b movzx r13d, byte ptr [rsp + 5] # 1-byte Folded Reload shl r13b, 2 or r13b, al @@ -54201,17 +55650,17 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl r9b, 6 shl bl, 7 or bl, r9b - or r15b, cl + or r14b, cl or bl, al - add r14b, r14b - add r14b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r15b, r15b + add r15b, byte ptr [rsp + 14] # 1-byte Folded Reload shl r12b, 2 - or r12b, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or r12b, r15b movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 or al, r12b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 or al, cl @@ -54219,12 +55668,12 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r8b, 7 or r8b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r8b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al @@ -54249,24 +55698,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl dil, 7 or dil, al or dil, cl - mov byte ptr [r14 + 2], r8b - mov byte ptr [r14 + 3], dil + mov byte ptr [r15 + 2], r8b + mov byte ptr [r15 + 3], dil add rdx, 128 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB9_118 -# %bb.119: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB9_120: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.121: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB9_148 +# %bb.149: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB9_150: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.151: xor ecx, ecx .p2align 4, 0x90 -.LBB9_122: # =>This Inner Loop Header: Depth=1 +.LBB9_152: # =>This Inner Loop Header: Depth=1 vmovss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero vucomiss xmm0, dword ptr [rdx + 4*rcx] lea r8, [rcx + 1] @@ -54274,7 +55722,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -54282,66 +55730,86 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_122 - jmp .LBB9_123 -.LBB9_57: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_152 + jmp .LBB9_153 +.LBB9_69: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_61 -# %bb.58: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB9_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] + je .LBB9_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 + jle .LBB9_74 +# %bb.71: + movsxd r12, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB9_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + mov edi, 0 + adc dil, -1 + lea rax, [r12 + 7] + test r12, r12 + cmovns rax, r12 + sar rax, 3 + movzx r14d, byte ptr [r15 + rax] + lea r15d, [8*rax] + mov ecx, r12d + sub ecx, r15d + mov r15, r8 + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB9_59 -# %bb.60: - add r14, 1 -.LBB9_61: - sar r15, 5 - cmp r11, 32 - jl .LBB9_65 -# %bb.62: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl ebx, cl + xor dil, r14b + and bl, dil + xor bl, r14b + mov byte ptr [r8 + rax], bl + add r11, 1 + add r12, 1 + add r10, -1 + cmp r9, r10 + jne .LBB9_72 +# %bb.73: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB9_74: + sub r13, rax + je .LBB9_153 +# %bb.75: + add r15, 1 +.LBB9_76: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_80 +# %bb.77: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setae cl movzx eax, byte ptr [rsi + 2] @@ -54361,7 +55829,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae byte ptr [rsp + 4] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setae r15b + setae r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] setae byte ptr [rsp + 7] # 1-byte Folded Spill @@ -54376,7 +55844,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setae r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setae r14b + setae r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] setae byte ptr [rsp + 5] # 1-byte Folded Spill @@ -54436,12 +55904,12 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 cmp al, byte ptr [rdx + 31] setae r8b add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload mov eax, ecx movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, al @@ -54463,26 +55931,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 6] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 13] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 4 or al, cl @@ -54490,12 +55958,12 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al @@ -54521,24 +55989,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB9_63 -# %bb.64: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB9_65: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.66: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB9_78 +# %bb.79: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB9_80: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.81: xor ecx, ecx .p2align 4, 0x90 -.LBB9_67: # =>This Inner Loop Header: Depth=1 +.LBB9_82: # =>This Inner Loop Header: Depth=1 movzx eax, byte ptr [rsi + rcx] cmp al, byte ptr [rdx + rcx] lea r8, [rcx + 1] @@ -54546,7 +56013,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -54554,68 +56021,83 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_67 - jmp .LBB9_123 -.LBB9_90: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_82 + jmp .LBB9_153 +.LBB9_111: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_94 -# %bb.91: - movsxd rax, r9d + je .LBB9_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setge r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB9_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setge r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_92 -# %bb.93: - add r14, 1 -.LBB9_94: - sar r15, 5 - cmp r11, 32 - jl .LBB9_98 -# %bb.95: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB9_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB9_116: + sub r13, r8 + je .LBB9_153 +# %bb.117: + add r15, 1 +.LBB9_118: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_122 +# %bb.119: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - setge byte ptr [rsp + 32] # 1-byte Folded Spill + setge byte ptr [rsp + 40] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] setge byte ptr [rsp + 20] # 1-byte Folded Spill @@ -54639,7 +56121,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 9] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - setge r8b + setge dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] setge r11b @@ -54679,7 +56161,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 11] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - setge byte ptr [rsp + 12] # 1-byte Folded Spill + setge byte ptr [rsp + 14] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] setge r9b @@ -54688,10 +56170,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 19] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - setge byte ptr [rsp + 13] # 1-byte Folded Spill + setge byte ptr [rsp + 12] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - setge byte ptr [rsp + 14] # 1-byte Folded Spill + setge byte ptr [rsp + 13] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] setge byte ptr [rsp + 15] # 1-byte Folded Spill @@ -54706,10 +56188,10 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 setge byte ptr [rsp + 17] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] - setge dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setge r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -54718,34 +56200,34 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -54758,22 +56240,23 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -54790,27 +56273,26 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_96 -# %bb.97: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_98: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.99: - sub r11, r15 + jne .LBB9_120 +# %bb.121: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_122: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.123: xor ecx, ecx .p2align 4, 0x90 -.LBB9_100: # =>This Inner Loop Header: Depth=1 +.LBB9_124: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -54818,7 +56300,7 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -54826,11 +56308,11 @@ comparison_greater_equal_arr_arr_avx2: # @comparison_greater_equal_arr_arr_avx2 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_100 -.LBB9_123: + cmp r13, r8 + jne .LBB9_124 +.LBB9_153: lea rsp, [rbp - 40] pop rbx pop r12 @@ -54874,90 +56356,103 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar and rsp, -32 sub rsp, 1344 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov r11, rcx + mov r15, r8 + mov r14, rcx cmp edi, 6 - jg .LBB10_15 + jg .LBB10_24 # %bb.1: cmp edi, 3 jle .LBB10_2 # %bb.6: cmp edi, 4 - je .LBB10_81 + je .LBB10_113 # %bb.7: cmp edi, 5 - je .LBB10_97 + je .LBB10_130 # %bb.8: cmp edi, 6 - jne .LBB10_194 + jne .LBB10_209 # %bb.9: mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_13 + je .LBB10_15 # %bb.10: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_13 +# %bb.11: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_11: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - mov edx, 0 - adc dl, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_12: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + mov ebx, 0 + adc bl, -1 + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_11 -# %bb.12: - add r11, 1 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_12 .LBB10_13: - sar r15, 5 - cmp r10, 32 - jl .LBB10_14 -# %bb.114: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + sub r15, r8 + je .LBB10_209 +# %bb.14: + add r14, 1 +.LBB10_15: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_19 +# %bb.16: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_115: # =>This Inner Loop Header: Depth=1 +.LBB10_17: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp dword ptr [rsi], r13d - setae byte ptr [rsp + 152] # 1-byte Folded Spill + setae byte ptr [rsp + 160] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d setae r10b cmp dword ptr [rsi + 8], r13d setae r14b cmp dword ptr [rsi + 12], r13d - setae byte ptr [rsp + 160] # 1-byte Folded Spill + setae byte ptr [rsp + 168] # 1-byte Folded Spill cmp dword ptr [rsi + 16], r13d - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - setae byte ptr [rsp + 96] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d setae al cmp dword ptr [rsi + 28], r13d setae bl cmp dword ptr [rsi + 32], r13d - setae byte ptr [rsp + 112] # 1-byte Folded Spill + setae byte ptr [rsp + 136] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d setae dil cmp dword ptr [rsi + 40], r13d @@ -54969,33 +56464,33 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar cmp dword ptr [rsi + 52], r13d setae r12b cmp dword ptr [rsi + 56], r13d - setae byte ptr [rsp + 120] # 1-byte Folded Spill + setae byte ptr [rsp + 144] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - setae cl + setae dl cmp dword ptr [rsi + 64], r13d - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + setae byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 72], r13d - setae byte ptr [rsp + 136] # 1-byte Folded Spill + setae byte ptr [rsp + 104] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - setae byte ptr [rsp + 72] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d - setae byte ptr [rsp + 88] # 1-byte Folded Spill + setae byte ptr [rsp + 72] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 88] # 1-byte Folded Spill cmp dword ptr [rsi + 88], r13d - setae byte ptr [rsp + 64] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d setae r15b cmp dword ptr [rsi + 96], r13d setae byte ptr [rsp + 32] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d + cmp dword ptr [rsi + 104], r13d setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp dword ptr [rsi + 108], r13d + setae byte ptr [rsp + 64] # 1-byte Folded Spill cmp dword ptr [rsi + 112], r13d setae byte ptr [rsp + 320] # 1-byte Folded Spill cmp dword ptr [rsi + 116], r13d @@ -55003,175 +56498,194 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar cmp dword ptr [rsi + 120], r13d setae byte ptr [rsp + 28] # 1-byte Folded Spill cmp dword ptr [rsi + 124], r13d - setae dl + setae cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 3 + or al, dil + mov edi, eax movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 5 + or al, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl bl, 6 + shl r15b, 7 + or r15b, bl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 5 - or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 128 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB10_115 -# %bb.116: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_118 - jmp .LBB10_194 -.LBB10_15: + add r14, 4 + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB10_17 +# %bb.18: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_19: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.20: + or rax, 1 + cmp r15, rax + jne .LBB10_148 +# %bb.21: + xor r11d, r11d + jmp .LBB10_22 +.LBB10_24: cmp edi, 8 - jle .LBB10_16 -# %bb.24: + jle .LBB10_25 +# %bb.42: cmp edi, 9 - je .LBB10_150 -# %bb.25: + je .LBB10_169 +# %bb.43: cmp edi, 11 - je .LBB10_166 -# %bb.26: + je .LBB10_186 +# %bb.44: cmp edi, 12 - jne .LBB10_194 -# %bb.27: - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jne .LBB10_209 +# %bb.45: + mov r12, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero sub r9d, eax - je .LBB10_31 -# %bb.28: - movsxd rax, r9d + je .LBB10_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_49 +# %bb.47: + movsxd rdx, r9d + vmovq xmm0, r12 + mov r11, r8 .p2align 4, 0x90 -.LBB10_29: # =>This Inner Loop Header: Depth=1 +.LBB10_48: # =>This Inner Loop Header: Depth=1 vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero add rsi, 8 vucomisd xmm1, xmm0 - mov edx, 0 - adc dl, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + mov ebx, 0 + adc bl, -1 + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_29 -# %bb.30: - add r11, 1 -.LBB10_31: - sar r15, 5 - cmp r10, 32 - jl .LBB10_32 -# %bb.182: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 152], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + add r11, -1 + jne .LBB10_48 +.LBB10_49: + sub r15, r8 + je .LBB10_209 +# %bb.50: + add r14, 1 +.LBB10_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_55 +# %bb.52: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 152], r12 # 8-byte Spill + vmovq xmm0, r12 + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_183: # =>This Inner Loop Header: Depth=1 +.LBB10_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero vmovsd xmm2, qword ptr [rsi + 8] # xmm2 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 120] # 1-byte Folded Spill + setae byte ptr [rsp + 144] # 1-byte Folded Spill vucomisd xmm2, xmm0 setae dl vmovsd xmm1, qword ptr [rsi + 16] # xmm1 = mem[0],zero @@ -55185,16 +56699,16 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar setae r9b vmovsd xmm1, qword ptr [rsi + 40] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 160] # 1-byte Folded Spill + setae byte ptr [rsp + 168] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 48] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 128] # 1-byte Folded Spill + setae byte ptr [rsp + 96] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 56] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 112] # 1-byte Folded Spill + setae byte ptr [rsp + 136] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 64] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 96] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 72] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 setae r10b @@ -55206,21 +56720,21 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar setae r15b vmovsd xmm1, qword ptr [rsi + 96] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae al + setae cl vmovsd xmm1, qword ptr [rsi + 104] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 112] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 88] # 1-byte Folded Spill + setae byte ptr [rsp + 72] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 120] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 - setae byte ptr [rsp + 72] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill vmovsd xmm1, qword ptr [rsi + 128] # xmm1 = mem[0],zero vmovsd xmm2, qword ptr [rsi + 136] # xmm2 = mem[0],zero vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 144] # xmm1 = mem[0],zero - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill vucomisd xmm2, xmm0 vmovsd xmm2, qword ptr [rsi + 152] # xmm2 = mem[0],zero setae r11b @@ -55232,13 +56746,13 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar setae r12b vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 176] # xmm1 = mem[0],zero - setae byte ptr [rsp + 136] # 1-byte Folded Spill + setae byte ptr [rsp + 104] # 1-byte Folded Spill vucomisd xmm2, xmm0 vmovsd xmm2, qword ptr [rsi + 184] # xmm2 = mem[0],zero - setae byte ptr [rsp + 80] # 1-byte Folded Spill + setae byte ptr [rsp + 128] # 1-byte Folded Spill vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 192] # xmm1 = mem[0],zero - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 88] # 1-byte Folded Spill vucomisd xmm2, xmm0 vmovsd xmm2, qword ptr [rsi + 200] # xmm2 = mem[0],zero setae r13b @@ -55247,13 +56761,13 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar setae byte ptr [rsp + 288] # 1-byte Folded Spill vucomisd xmm2, xmm0 vmovsd xmm2, qword ptr [rsi + 216] # xmm2 = mem[0],zero - setae byte ptr [rsp + 64] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 224] # xmm1 = mem[0],zero - setae byte ptr [rsp + 48] # 1-byte Folded Spill + setae byte ptr [rsp + 56] # 1-byte Folded Spill vucomisd xmm2, xmm0 vmovsd xmm2, qword ptr [rsi + 232] # xmm2 = mem[0],zero - setae byte ptr [rsp + 56] # 1-byte Folded Spill + setae byte ptr [rsp + 64] # 1-byte Folded Spill vucomisd xmm1, xmm0 vmovsd xmm1, qword ptr [rsi + 240] # xmm1 = mem[0],zero setae byte ptr [rsp + 32] # 1-byte Folded Spill @@ -55264,418 +56778,249 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar setae byte ptr [rsp + 28] # 1-byte Folded Spill add rsi, 256 vucomisd xmm2, xmm0 - setae cl + setae al add dl, dl - add dl, byte ptr [rsp + 120] # 1-byte Folded Reload + add dl, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 2 or dil, dl shl r8b, 3 or r8b, dil shl r9b, 4 or r9b, r8b - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 168] # 1-byte Folded Reload shl dl, 5 or dl, r9b - movzx r8d, byte ptr [rsp + 128] # 1-byte Folded Reload + mov edi, edx + movzx r8d, byte ptr [rsp + 96] # 1-byte Folded Reload shl r8b, 6 - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 7 - or dil, r8b + movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dl, 7 + or dl, r8b add r10b, r10b - add r10b, byte ptr [rsp + 96] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 2 or bl, r10b shl r15b, 3 or r15b, bl - shl al, 4 - or al, r15b - or dil, dl - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 5 - or dl, al - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 6 - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, r15b + or dl, dil + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl bl, 5 + or bl, cl + mov edi, ebx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 6 + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload shl bl, 7 - or bl, al + or bl, cl add r11b, r11b - add r11b, byte ptr [rsp + 40] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 48] # 1-byte Folded Reload shl r14b, 2 or r14b, r11b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 4 - or al, r12b - mov r8d, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 5 - or al, r8b - or bl, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 6 + mov r14, qword ptr [rsp + 272] # 8-byte Reload + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, r12b + mov r8d, ecx + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl cl, 5 + or cl, r8b + or bl, dil + movzx edi, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dil, 6 shl r13b, 7 - or r13b, dl - mov rdx, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rdx], dil - or r13b, al - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 288] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 5 - or al, dil - mov byte ptr [rdx + 1], bl + or r13b, dil + mov byte ptr [r14], dl + or r13b, cl + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 288] # 1-byte Folded Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 3 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 4 + or cl, dl + movzx edx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl dl, 5 + or dl, cl + mov byte ptr [r14 + 1], bl movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - shl cl, 7 - or cl, bl - mov byte ptr [rdx + 2], r13b - or cl, al - mov byte ptr [rdx + 3], cl - add rdx, 4 - mov qword ptr [rsp + 272], rdx # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB10_183 -# %bb.184: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_186 - jmp .LBB10_194 + shl al, 7 + or al, bl + mov byte ptr [r14 + 2], r13b + or al, dl + mov byte ptr [r14 + 3], al + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB10_53 +# %bb.54: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_55: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.56: + vmovq xmm0, r12 + or rax, 1 + cmp r15, rax + jne .LBB10_203 +# %bb.57: + xor r11d, r11d + jmp .LBB10_205 .LBB10_2: cmp edi, 2 - je .LBB10_33 + je .LBB10_58 # %bb.3: cmp edi, 3 - jne .LBB10_194 + jne .LBB10_209 # %bb.4: - mov r14b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + mov r13b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax je .LBB10_5 -# %bb.58: - movsxd rax, r9d - mov r13, r11 - .p2align 4, 0x90 -.LBB10_59: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r14b - lea rsi, [rsi + 1] - setge dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r13 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r13 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_59 -# %bb.60: - add r13, 1 - sar r15, 5 - cmp r10, 32 - jl .LBB10_62 -.LBB10_63: - cmp r15, 32 - mov dword ptr [rsp + 28], r14d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 608], r15 # 8-byte Spill - jb .LBB10_64 -# %bb.65: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp r13, rax - jae .LBB10_67 -# %bb.66: - lea rax, [4*r15] - add rax, r13 - cmp rsi, rax - jae .LBB10_67 -.LBB10_64: - xor eax, eax - mov qword ptr [rsp + 416], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 360], r13 # 8-byte Spill -.LBB10_70: - mov r13, r15 - sub r13, qword ptr [rsp + 416] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r13 # 8-byte Spill +# %bb.87: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_88 +# %bb.93: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB10_71: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b - setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b - setge r8b - cmp byte ptr [r12 + 2], r14b - setge r15b - cmp byte ptr [r12 + 3], r14b - setge r13b - cmp byte ptr [r12 + 4], r14b - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b - setge al - cmp byte ptr [r12 + 7], r14b - setge r11b - cmp byte ptr [r12 + 8], r14b - setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b - setge dl - cmp byte ptr [r12 + 10], r14b - setge sil - cmp byte ptr [r12 + 11], r14b - setge dil - cmp byte ptr [r12 + 12], r14b - setge r10b - cmp byte ptr [r12 + 13], r14b - setge r12b - cmp byte ptr [rcx + 14], r14b - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b - setge r9b - cmp byte ptr [rcx + 16], r14b - setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b - setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - setge r14b - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 24], bl - setge byte ptr [rsp + 272] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 25], bl - setge byte ptr [rsp + 88] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 26], bl - setge byte ptr [rsp + 96] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 27], bl - setge byte ptr [rsp + 104] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 28], bl - setge byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 29], bl - setge byte ptr [rsp + 48] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 30], bl - setge byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp byte ptr [rcx + 31], bl +.LBB10_94: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r13b setge bl - add r8b, r8b - add r8b, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, r8b - add dl, dl - add dl, byte ptr [rsp + 320] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b - shl sil, 2 - or sil, dl - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - shl dil, 3 - or dil, sil - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, dil - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl r9b, 7 - or r9b, sil - or r11b, dl - or r9b, r12b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 288] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov rsi, qword ptr [rsp + 360] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 272] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 6 - shl bl, 7 - or bl, dl - or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 360], rsi # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB10_71 -# %bb.72: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 608] # 8-byte Reload - jmp .LBB10_73 -.LBB10_16: + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + movzx r9d, byte ptr [r14 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB10_94 +# %bb.89: + sub r15, r8 + jne .LBB10_90 + jmp .LBB10_209 +.LBB10_25: cmp edi, 7 - je .LBB10_124 -# %bb.17: + je .LBB10_150 +# %bb.26: cmp edi, 8 - jne .LBB10_194 -# %bb.18: + jne .LBB10_209 +# %bb.27: mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_22 -# %bb.19: - movsxd rax, r9d + je .LBB10_33 +# %bb.28: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_31 +# %bb.29: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_20: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - mov edx, 0 - adc dl, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_30: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + mov ebx, 0 + adc bl, -1 + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_20 -# %bb.21: - add r11, 1 -.LBB10_22: - sar r15, 5 - cmp r10, 32 - jl .LBB10_23 -# %bb.140: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_30 +.LBB10_31: + sub r15, r8 + je .LBB10_209 +# %bb.32: + add r14, 1 +.LBB10_33: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_37 +# %bb.34: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_141: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r11 # 8-byte Spill +.LBB10_35: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp qword ptr [rsi], r13 - setae byte ptr [rsp + 152] # 1-byte Folded Spill + setae byte ptr [rsp + 160] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 setae r10b cmp qword ptr [rsi + 16], r13 setae r14b cmp qword ptr [rsi + 24], r13 - setae byte ptr [rsp + 160] # 1-byte Folded Spill + setae byte ptr [rsp + 168] # 1-byte Folded Spill cmp qword ptr [rsi + 32], r13 - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill cmp qword ptr [rsi + 40], r13 - setae byte ptr [rsp + 96] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 48], r13 setae al cmp qword ptr [rsi + 56], r13 setae bl cmp qword ptr [rsi + 64], r13 - setae byte ptr [rsp + 112] # 1-byte Folded Spill + setae byte ptr [rsp + 136] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 setae dil cmp qword ptr [rsi + 80], r13 @@ -55687,33 +57032,33 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar cmp qword ptr [rsi + 104], r13 setae r12b cmp qword ptr [rsi + 112], r13 - setae byte ptr [rsp + 120] # 1-byte Folded Spill + setae byte ptr [rsp + 144] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - setae cl + setae dl cmp qword ptr [rsi + 128], r13 - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 136], r13 setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp qword ptr [rsi + 136], r13 + setae byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - setae byte ptr [rsp + 136] # 1-byte Folded Spill + setae byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - setae byte ptr [rsp + 72] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - setae byte ptr [rsp + 88] # 1-byte Folded Spill + setae byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - setae byte ptr [rsp + 64] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 setae r15b cmp qword ptr [rsi + 192], r13 setae byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp qword ptr [rsi + 208], r13 setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp qword ptr [rsi + 216], r13 + cmp qword ptr [rsi + 208], r13 setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp qword ptr [rsi + 216], r13 + setae byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 setae byte ptr [rsp + 320] # 1-byte Folded Spill cmp qword ptr [rsi + 232], r13 @@ -55721,156 +57066,176 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar cmp qword ptr [rsi + 240], r13 setae byte ptr [rsp + 28] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - setae dl + setae cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - mov r11, qword ptr [rsp + 272] # 8-byte Reload - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r11 + 1], cl + mov byte ptr [r14 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax + mov edx, eax movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], dl + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 256 - add r11, 4 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB10_141 -# %bb.142: - mov r14, r11 - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_144 - jmp .LBB10_194 -.LBB10_81: + add r14, 4 + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB10_35 +# %bb.36: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_37: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.38: + or rax, 1 + cmp r15, rax + jne .LBB10_167 +# %bb.39: + xor r11d, r11d + jmp .LBB10_40 +.LBB10_113: movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_85 -# %bb.82: - movsxd rax, r9d + je .LBB10_119 +# %bb.114: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_117 +# %bb.115: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_83: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - mov edx, 0 - adc dl, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_116: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + mov ebx, 0 + adc bl, -1 + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_83 -# %bb.84: - add r11, 1 -.LBB10_85: - sar r15, 5 - cmp r10, 32 - jl .LBB10_86 -# %bb.87: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_116 +.LBB10_117: + sub r15, r8 + je .LBB10_209 +# %bb.118: + add r14, 1 +.LBB10_119: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_123 +# %bb.120: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_88: # =>This Inner Loop Header: Depth=1 +.LBB10_121: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp word ptr [rsi], r13w setae al cmp word ptr [rsi + 2], r13w @@ -55878,17 +57243,17 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar cmp word ptr [rsi + 4], r13w setae r14b cmp word ptr [rsi + 6], r13w - setae byte ptr [rsp + 160] # 1-byte Folded Spill + setae byte ptr [rsp + 168] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - setae byte ptr [rsp + 96] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w - setae byte ptr [rsp + 152] # 1-byte Folded Spill + setae byte ptr [rsp + 160] # 1-byte Folded Spill cmp word ptr [rsi + 14], r13w setae bl cmp word ptr [rsi + 16], r13w - setae byte ptr [rsp + 112] # 1-byte Folded Spill + setae byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w setae dil cmp word ptr [rsi + 20], r13w @@ -55900,33 +57265,33 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar cmp word ptr [rsi + 26], r13w setae r12b cmp word ptr [rsi + 28], r13w - setae byte ptr [rsp + 120] # 1-byte Folded Spill + setae byte ptr [rsp + 136] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - setae cl + setae dl cmp word ptr [rsi + 32], r13w - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp word ptr [rsi + 34], r13w setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [rsi + 34], r13w + setae byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 36], r13w - setae byte ptr [rsp + 136] # 1-byte Folded Spill + setae byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - setae byte ptr [rsp + 72] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - setae byte ptr [rsp + 88] # 1-byte Folded Spill + setae byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 88] # 1-byte Folded Spill cmp word ptr [rsi + 44], r13w - setae byte ptr [rsp + 64] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w setae r15b cmp word ptr [rsi + 48], r13w setae byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp word ptr [rsi + 52], r13w setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp word ptr [rsi + 54], r13w + cmp word ptr [rsi + 52], r13w setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp word ptr [rsi + 54], r13w + setae byte ptr [rsp + 64] # 1-byte Folded Spill cmp word ptr [rsi + 56], r13w setae byte ptr [rsp + 320] # 1-byte Folded Spill cmp word ptr [rsi + 58], r13w @@ -55934,910 +57299,1492 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar cmp word ptr [rsi + 60], r13w setae byte ptr [rsp + 28] # 1-byte Folded Spill cmp word ptr [rsi + 62], r13w - setae dl + setae cl add r10b, r10b or r10b, al - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 136] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl add rsi, 64 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB10_88 -# %bb.89: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_91 - jmp .LBB10_194 -.LBB10_97: + add r14, 4 + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB10_121 +# %bb.122: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_123: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.124: + or rax, 1 + cmp r15, rax + jne .LBB10_128 +# %bb.125: + xor r11d, r11d + jmp .LBB10_126 +.LBB10_130: movzx r13d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_101 -# %bb.98: - movsxd rax, r9d + je .LBB10_136 +# %bb.131: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_134 +# %bb.132: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_99: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - setge dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_133: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + setge bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_99 -# %bb.100: - add r11, 1 -.LBB10_101: - sar r15, 5 - cmp r10, 32 - jl .LBB10_102 -# %bb.103: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_133 +.LBB10_134: + sub r15, r8 + je .LBB10_209 +# %bb.135: + add r14, 1 +.LBB10_136: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_140 +# %bb.137: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_104: # =>This Inner Loop Header: Depth=1 +.LBB10_138: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill cmp word ptr [rsi], r13w - setge byte ptr [rsp + 152] # 1-byte Folded Spill + setge byte ptr [rsp + 160] # 1-byte Folded Spill cmp word ptr [rsi + 2], r13w setge r10b cmp word ptr [rsi + 4], r13w setge r14b cmp word ptr [rsi + 6], r13w - setge byte ptr [rsp + 160] # 1-byte Folded Spill + setge byte ptr [rsp + 168] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - setge byte ptr [rsp + 144] # 1-byte Folded Spill + setge byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - setge byte ptr [rsp + 96] # 1-byte Folded Spill + setge byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w setge al cmp word ptr [rsi + 14], r13w setge bl cmp word ptr [rsi + 16], r13w - setge byte ptr [rsp + 112] # 1-byte Folded Spill + setge byte ptr [rsp + 136] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w setge dil - cmp word ptr [rsi + 20], r13w + cmp word ptr [rsi + 20], r13w + setge r8b + cmp word ptr [rsi + 22], r13w + setge r9b + cmp word ptr [rsi + 24], r13w + setge r11b + cmp word ptr [rsi + 26], r13w + setge r12b + cmp word ptr [rsi + 28], r13w + setge byte ptr [rsp + 144] # 1-byte Folded Spill + cmp word ptr [rsi + 30], r13w + setge dl + cmp word ptr [rsi + 32], r13w + setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [rsi + 34], r13w + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp word ptr [rsi + 36], r13w + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp word ptr [rsi + 38], r13w + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp word ptr [rsi + 40], r13w + setge byte ptr [rsp + 72] # 1-byte Folded Spill + cmp word ptr [rsi + 42], r13w + setge byte ptr [rsp + 88] # 1-byte Folded Spill + cmp word ptr [rsi + 44], r13w + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp word ptr [rsi + 46], r13w + setge r15b + cmp word ptr [rsi + 48], r13w + setge byte ptr [rsp + 32] # 1-byte Folded Spill + cmp word ptr [rsi + 50], r13w + setge byte ptr [rsp + 48] # 1-byte Folded Spill + cmp word ptr [rsi + 52], r13w + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp word ptr [rsi + 54], r13w + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp word ptr [rsi + 56], r13w + setge byte ptr [rsp + 320] # 1-byte Folded Spill + cmp word ptr [rsi + 58], r13w + setge byte ptr [rsp + 288] # 1-byte Folded Spill + cmp word ptr [rsi + 60], r13w + setge byte ptr [rsp + 28] # 1-byte Folded Spill + cmp word ptr [rsi + 62], r13w + setge cl + add r10b, r10b + add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, r10b + add dil, dil + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload + shl r8b, 2 + or r8b, dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 4 + or al, r10b + mov edi, eax + shl r9b, 3 + or r9b, r8b + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, dil + shl r11b, 4 + or r11b, r9b + shl r12b, 5 + or r12b, r11b + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dil, 6 + shl dl, 7 + or dl, dil + or bl, al + or dl, r12b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 128] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 2 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 3 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 5 + or al, dil + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl bl, 6 + shl r15b, 7 + or r15b, bl + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl + add rsi, 64 + add r14, 4 + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB10_138 +# %bb.139: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_140: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.141: + or rax, 1 + cmp r15, rax + jne .LBB10_146 +# %bb.142: + xor r11d, r11d + jmp .LBB10_143 +.LBB10_169: + mov r13, qword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB10_175 +# %bb.170: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_173 +# %bb.171: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB10_172: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + setge bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_172 +.LBB10_173: + sub r15, r8 + je .LBB10_209 +# %bb.174: + add r14, 1 +.LBB10_175: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_179 +# %bb.176: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB10_177: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill + cmp qword ptr [rsi], r13 + setge byte ptr [rsp + 160] # 1-byte Folded Spill + cmp qword ptr [rsi + 8], r13 + setge r10b + cmp qword ptr [rsi + 16], r13 + setge r14b + cmp qword ptr [rsi + 24], r13 + setge byte ptr [rsp + 168] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp qword ptr [rsi + 40], r13 + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp qword ptr [rsi + 48], r13 + setge al + cmp qword ptr [rsi + 56], r13 + setge bl + cmp qword ptr [rsi + 64], r13 + setge byte ptr [rsp + 136] # 1-byte Folded Spill + cmp qword ptr [rsi + 72], r13 + setge dil + cmp qword ptr [rsi + 80], r13 setge r8b - cmp word ptr [rsi + 22], r13w + cmp qword ptr [rsi + 88], r13 setge r9b - cmp word ptr [rsi + 24], r13w + cmp qword ptr [rsi + 96], r13 setge r11b - cmp word ptr [rsi + 26], r13w + cmp qword ptr [rsi + 104], r13 setge r12b - cmp word ptr [rsi + 28], r13w - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp word ptr [rsi + 30], r13w - setge cl - cmp word ptr [rsi + 32], r13w - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp word ptr [rsi + 34], r13w + cmp qword ptr [rsi + 112], r13 + setge byte ptr [rsp + 144] # 1-byte Folded Spill + cmp qword ptr [rsi + 120], r13 + setge dl + cmp qword ptr [rsi + 128], r13 setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp word ptr [rsi + 36], r13w - setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp word ptr [rsi + 38], r13w + cmp qword ptr [rsi + 136], r13 + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp qword ptr [rsi + 144], r13 + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp qword ptr [rsi + 152], r13 + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp qword ptr [rsi + 160], r13 setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp word ptr [rsi + 40], r13w + cmp qword ptr [rsi + 168], r13 setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp word ptr [rsi + 42], r13w - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp word ptr [rsi + 44], r13w - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp word ptr [rsi + 46], r13w + cmp qword ptr [rsi + 176], r13 + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp qword ptr [rsi + 184], r13 setge r15b - cmp word ptr [rsi + 48], r13w + cmp qword ptr [rsi + 192], r13 setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp word ptr [rsi + 50], r13w - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp word ptr [rsi + 52], r13w + cmp qword ptr [rsi + 200], r13 setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp word ptr [rsi + 54], r13w + cmp qword ptr [rsi + 208], r13 setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp word ptr [rsi + 56], r13w + cmp qword ptr [rsi + 216], r13 + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp qword ptr [rsi + 224], r13 setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp word ptr [rsi + 58], r13w + cmp qword ptr [rsi + 232], r13 setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp word ptr [rsi + 60], r13w + cmp qword ptr [rsi + 240], r13 setge byte ptr [rsp + 28] # 1-byte Folded Spill - cmp word ptr [rsi + 62], r13w - setge dl + cmp qword ptr [rsi + 248], r13 + setge cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl + add rsi, 256 + add r14, 4 + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB10_177 +# %bb.178: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_179: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.180: + or rax, 1 + cmp r15, rax + jne .LBB10_184 +# %bb.181: + xor r11d, r11d + jmp .LBB10_182 +.LBB10_186: + mov r12d, dword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB10_192 +# %bb.187: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_190 +# %bb.188: + movsxd rdx, r9d + vmovd xmm0, r12d + mov r11, r8 + .p2align 4, 0x90 +.LBB10_189: # =>This Inner Loop Header: Depth=1 + vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + add rsi, 4 + vucomiss xmm1, xmm0 + mov ebx, 0 + adc bl, -1 + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r14 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rdx, 1 + add r11, -1 + jne .LBB10_189 +.LBB10_190: + sub r15, r8 + je .LBB10_209 +# %bb.191: + add r14, 1 +.LBB10_192: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_196 +# %bb.193: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov dword ptr [rsp + 152], r12d # 4-byte Spill + vmovd xmm0, r12d + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB10_194: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill + vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + vmovss xmm2, dword ptr [rsi + 4] # xmm2 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 144] # 1-byte Folded Spill + vucomiss xmm2, xmm0 + setae dl + vmovss xmm1, dword ptr [rsi + 8] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae dil + vmovss xmm1, dword ptr [rsi + 12] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae r8b + vmovss xmm1, dword ptr [rsi + 16] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae r9b + vmovss xmm1, dword ptr [rsi + 20] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 168] # 1-byte Folded Spill + vmovss xmm1, dword ptr [rsi + 24] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 96] # 1-byte Folded Spill + vmovss xmm1, dword ptr [rsi + 28] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 136] # 1-byte Folded Spill + vmovss xmm1, dword ptr [rsi + 32] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 80] # 1-byte Folded Spill + vmovss xmm1, dword ptr [rsi + 36] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae r10b + vmovss xmm1, dword ptr [rsi + 40] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae bl + vmovss xmm1, dword ptr [rsi + 44] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae r15b + vmovss xmm1, dword ptr [rsi + 48] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae cl + vmovss xmm1, dword ptr [rsi + 52] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 112] # 1-byte Folded Spill + vmovss xmm1, dword ptr [rsi + 56] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 72] # 1-byte Folded Spill + vmovss xmm1, dword ptr [rsi + 60] # xmm1 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 120] # 1-byte Folded Spill + vmovss xmm1, dword ptr [rsi + 64] # xmm1 = mem[0],zero,zero,zero + vmovss xmm2, dword ptr [rsi + 68] # xmm2 = mem[0],zero,zero,zero + vucomiss xmm1, xmm0 + vmovss xmm1, dword ptr [rsi + 72] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 48] # 1-byte Folded Spill + vucomiss xmm2, xmm0 + vmovss xmm2, dword ptr [rsi + 76] # xmm2 = mem[0],zero,zero,zero + setae r11b + vucomiss xmm1, xmm0 + vmovss xmm1, dword ptr [rsi + 80] # xmm1 = mem[0],zero,zero,zero + setae r14b + vucomiss xmm2, xmm0 + vmovss xmm2, dword ptr [rsi + 84] # xmm2 = mem[0],zero,zero,zero + setae r12b + vucomiss xmm1, xmm0 + vmovss xmm1, dword ptr [rsi + 88] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 104] # 1-byte Folded Spill + vucomiss xmm2, xmm0 + vmovss xmm2, dword ptr [rsi + 92] # xmm2 = mem[0],zero,zero,zero + setae byte ptr [rsp + 128] # 1-byte Folded Spill + vucomiss xmm1, xmm0 + vmovss xmm1, dword ptr [rsi + 96] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 88] # 1-byte Folded Spill + vucomiss xmm2, xmm0 + vmovss xmm2, dword ptr [rsi + 100] # xmm2 = mem[0],zero,zero,zero + setae r13b + vucomiss xmm1, xmm0 + vmovss xmm1, dword ptr [rsi + 104] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 288] # 1-byte Folded Spill + vucomiss xmm2, xmm0 + vmovss xmm2, dword ptr [rsi + 108] # xmm2 = mem[0],zero,zero,zero + setae byte ptr [rsp + 40] # 1-byte Folded Spill + vucomiss xmm1, xmm0 + vmovss xmm1, dword ptr [rsi + 112] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 56] # 1-byte Folded Spill + vucomiss xmm2, xmm0 + vmovss xmm2, dword ptr [rsi + 116] # xmm2 = mem[0],zero,zero,zero + setae byte ptr [rsp + 64] # 1-byte Folded Spill + vucomiss xmm1, xmm0 + vmovss xmm1, dword ptr [rsi + 120] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 32] # 1-byte Folded Spill + vucomiss xmm2, xmm0 + vmovss xmm2, dword ptr [rsi + 124] # xmm2 = mem[0],zero,zero,zero + setae byte ptr [rsp + 320] # 1-byte Folded Spill + vucomiss xmm1, xmm0 + setae byte ptr [rsp + 28] # 1-byte Folded Spill + sub rsi, -128 + vucomiss xmm2, xmm0 + setae al + add dl, dl + add dl, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dil, 2 + or dil, dl + shl r8b, 3 + or r8b, dil + shl r9b, 4 + or r9b, r8b + movzx edx, byte ptr [rsp + 168] # 1-byte Folded Reload + shl dl, 5 + or dl, r9b + mov edi, edx + movzx r8d, byte ptr [rsp + 96] # 1-byte Folded Reload + shl r8b, 6 + movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dl, 7 + or dl, r8b + add r10b, r10b + add r10b, byte ptr [rsp + 80] # 1-byte Folded Reload + shl bl, 2 + or bl, r10b + shl r15b, 3 + or r15b, bl + shl cl, 4 + or cl, r15b + or dl, dil + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl bl, 5 + or bl, cl + mov edi, ebx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 6 + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl bl, 7 + or bl, cl + add r11b, r11b + add r11b, byte ptr [rsp + 48] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r11b + shl r12b, 3 + or r12b, r14b + mov r14, qword ptr [rsp + 272] # 8-byte Reload + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, r12b + mov r8d, ecx + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl cl, 5 + or cl, r8b + or bl, dil + movzx edi, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dil, 6 + shl r13b, 7 + or r13b, dil + mov byte ptr [r14], dl + or r13b, cl movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx + add cl, byte ptr [rsp + 288] # 1-byte Folded Reload + mov edx, ecx movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl + or cl, dl + movzx edx, byte ptr [rsp + 320] # 1-byte Folded Reload + shl dl, 5 + or dl, cl + mov byte ptr [r14 + 1], bl movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl - add rsi, 64 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB10_104 -# %bb.105: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_107 - jmp .LBB10_194 + shl al, 7 + or al, bl + mov byte ptr [r14 + 2], r13b + or al, dl + mov byte ptr [r14 + 3], al + add r14, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB10_194 +# %bb.195: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r12d, dword ptr [rsp + 152] # 4-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_196: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.197: + vmovd xmm0, r12d + or rax, 1 + cmp r15, rax + jne .LBB10_201 +# %bb.198: + xor r11d, r11d + jmp .LBB10_199 +.LBB10_58: + mov r13b, byte ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB10_59 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_61 +# %bb.66: + movsxd rdx, r9d + mov r11, r8 + .p2align 4, 0x90 +.LBB10_67: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r13b + mov esi, 0 + adc sil, -1 + lea rbx, [rdx + 7] + test rdx, rdx + cmovns rbx, rdx + sar rbx, 3 + movzx r9d, byte ptr [r14 + rbx] + xor sil, r9b + lea r10d, [8*rbx] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, sil + xor al, r9b + mov byte ptr [r14 + rbx], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB10_67 +# %bb.62: + sub r15, r8 + jne .LBB10_63 + jmp .LBB10_209 .LBB10_150: - mov r13, qword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + mov r13d, dword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_154 + je .LBB10_156 # %bb.151: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB10_154 +# %bb.152: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_152: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setge dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_153: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + setge bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_152 -# %bb.153: - add r11, 1 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_153 .LBB10_154: - sar r15, 5 - cmp r10, 32 - jl .LBB10_155 -# %bb.156: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + sub r15, r8 + je .LBB10_209 +# %bb.155: + add r14, 1 +.LBB10_156: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB10_160 +# %bb.157: + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 152], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_157: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - setge byte ptr [rsp + 152] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 +.LBB10_158: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r14 # 8-byte Spill + cmp dword ptr [rsi], r13d + setge byte ptr [rsp + 160] # 1-byte Folded Spill + cmp dword ptr [rsi + 4], r13d setge r10b - cmp qword ptr [rsi + 16], r13 + cmp dword ptr [rsi + 8], r13d setge r14b - cmp qword ptr [rsi + 24], r13 - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 + cmp dword ptr [rsi + 12], r13d + setge byte ptr [rsp + 168] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp dword ptr [rsi + 20], r13d + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 24], r13d setge al - cmp qword ptr [rsi + 56], r13 + cmp dword ptr [rsi + 28], r13d setge bl - cmp qword ptr [rsi + 64], r13 - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp qword ptr [rsi + 72], r13 + cmp dword ptr [rsi + 32], r13d + setge byte ptr [rsp + 136] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d setge dil - cmp qword ptr [rsi + 80], r13 + cmp dword ptr [rsi + 40], r13d setge r8b - cmp qword ptr [rsi + 88], r13 + cmp dword ptr [rsi + 44], r13d setge r9b - cmp qword ptr [rsi + 96], r13 + cmp dword ptr [rsi + 48], r13d setge r11b - cmp qword ptr [rsi + 104], r13 + cmp dword ptr [rsi + 52], r13d setge r12b - cmp qword ptr [rsi + 112], r13 - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp qword ptr [rsi + 120], r13 - setge cl - cmp qword ptr [rsi + 128], r13 - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 136], r13 + cmp dword ptr [rsi + 56], r13d + setge byte ptr [rsp + 144] # 1-byte Folded Spill + cmp dword ptr [rsi + 60], r13d + setge dl + cmp dword ptr [rsi + 64], r13d setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 - setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp qword ptr [rsi + 152], r13 + cmp dword ptr [rsi + 68], r13d + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp dword ptr [rsi + 80], r13d setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp qword ptr [rsi + 160], r13 + cmp dword ptr [rsi + 84], r13d setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp qword ptr [rsi + 168], r13 - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp qword ptr [rsi + 176], r13 - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp qword ptr [rsi + 184], r13 + cmp dword ptr [rsi + 88], r13d + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp dword ptr [rsi + 92], r13d setge r15b - cmp qword ptr [rsi + 192], r13 + cmp dword ptr [rsi + 96], r13d setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp qword ptr [rsi + 200], r13 - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp qword ptr [rsi + 208], r13 + cmp dword ptr [rsi + 100], r13d setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp qword ptr [rsi + 216], r13 + cmp dword ptr [rsi + 104], r13d setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp qword ptr [rsi + 224], r13 + cmp dword ptr [rsi + 108], r13d + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp dword ptr [rsi + 112], r13d setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp qword ptr [rsi + 232], r13 + cmp dword ptr [rsi + 116], r13d setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp qword ptr [rsi + 240], r13 + cmp dword ptr [rsi + 120], r13d setge byte ptr [rsp + 28] # 1-byte Folded Spill - cmp qword ptr [rsi + 248], r13 - setge dl + cmp dword ptr [rsi + 124], r13d + setge cl add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload shl al, 3 or al, r14b mov r10d, eax + mov r14, qword ptr [rsp + 272] # 8-byte Reload shl r8b, 2 or r8b, dil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax shl r9b, 3 or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, dil shl r11b, 4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + or dl, r12b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, dil - mov edi, eax - mov rax, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rax], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [r14], bl + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [rax + 1], cl - or r15b, dil - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 320] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, cl - mov byte ptr [rax + 2], r15b - mov byte ptr [rax + 3], dl - add rsi, 256 - add rax, 4 - mov qword ptr [rsp + 272], rax # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB10_157 -# %bb.158: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_160 - jmp .LBB10_194 -.LBB10_166: - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - vmovss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero - sub r9d, eax - je .LBB10_170 -# %bb.167: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB10_168: # =>This Inner Loop Header: Depth=1 - vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero - add rsi, 4 - vucomiss xmm1, xmm0 - mov edx, 0 - adc dl, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_168 -# %bb.169: - add r11, 1 -.LBB10_170: - sar r15, 5 - cmp r10, 32 - jl .LBB10_171 -# %bb.172: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - mov qword ptr [rsp + 152], r15 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill + mov byte ptr [r14 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], cl + add rsi, 128 + add r14, 4 + add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + jne .LBB10_158 +# %bb.159: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB10_160: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB10_209 +# %bb.161: + or rax, 1 + cmp r15, rax + jne .LBB10_165 +# %bb.162: + xor r11d, r11d + jmp .LBB10_163 +.LBB10_5: + mov rdi, rsi + jmp .LBB10_91 +.LBB10_59: + mov rdi, rsi + jmp .LBB10_64 +.LBB10_88: + mov rdi, rsi + sub r15, r8 + je .LBB10_209 +.LBB10_90: + add r14, 1 +.LBB10_91: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB10_92 +# %bb.95: + cmp rcx, 32 + mov dword ptr [rsp + 28], r13d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 608], rcx # 8-byte Spill + jb .LBB10_96 +# %bb.97: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB10_99 +# %bb.98: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB10_99 +.LBB10_96: + xor eax, eax + mov qword ptr [rsp + 416], rax # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 360], r14 # 8-byte Spill +.LBB10_102: + sub rcx, qword ptr [rsp + 416] # 8-byte Folded Reload + mov qword ptr [rsp + 152], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB10_173: # =>This Inner Loop Header: Depth=1 - vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero - vmovss xmm2, dword ptr [rsi + 4] # xmm2 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 120] # 1-byte Folded Spill - vucomiss xmm2, xmm0 - setae dl - vmovss xmm1, dword ptr [rsi + 8] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae dil - vmovss xmm1, dword ptr [rsi + 12] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae r8b - vmovss xmm1, dword ptr [rsi + 16] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae r9b - vmovss xmm1, dword ptr [rsi + 20] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 160] # 1-byte Folded Spill - vmovss xmm1, dword ptr [rsi + 24] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 128] # 1-byte Folded Spill - vmovss xmm1, dword ptr [rsi + 28] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 112] # 1-byte Folded Spill - vmovss xmm1, dword ptr [rsi + 32] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 96] # 1-byte Folded Spill - vmovss xmm1, dword ptr [rsi + 36] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae r10b - vmovss xmm1, dword ptr [rsi + 40] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae bl - vmovss xmm1, dword ptr [rsi + 44] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae r15b - vmovss xmm1, dword ptr [rsi + 48] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae al - vmovss xmm1, dword ptr [rsi + 52] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 144] # 1-byte Folded Spill - vmovss xmm1, dword ptr [rsi + 56] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 88] # 1-byte Folded Spill - vmovss xmm1, dword ptr [rsi + 60] # xmm1 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 72] # 1-byte Folded Spill - vmovss xmm1, dword ptr [rsi + 64] # xmm1 = mem[0],zero,zero,zero - vmovss xmm2, dword ptr [rsi + 68] # xmm2 = mem[0],zero,zero,zero - vucomiss xmm1, xmm0 - vmovss xmm1, dword ptr [rsi + 72] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 40] # 1-byte Folded Spill - vucomiss xmm2, xmm0 - vmovss xmm2, dword ptr [rsi + 76] # xmm2 = mem[0],zero,zero,zero - setae r11b - vucomiss xmm1, xmm0 - vmovss xmm1, dword ptr [rsi + 80] # xmm1 = mem[0],zero,zero,zero - setae r14b - vucomiss xmm2, xmm0 - vmovss xmm2, dword ptr [rsi + 84] # xmm2 = mem[0],zero,zero,zero - setae r12b - vucomiss xmm1, xmm0 - vmovss xmm1, dword ptr [rsi + 88] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 136] # 1-byte Folded Spill - vucomiss xmm2, xmm0 - vmovss xmm2, dword ptr [rsi + 92] # xmm2 = mem[0],zero,zero,zero - setae byte ptr [rsp + 80] # 1-byte Folded Spill - vucomiss xmm1, xmm0 - vmovss xmm1, dword ptr [rsi + 96] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 104] # 1-byte Folded Spill - vucomiss xmm2, xmm0 - vmovss xmm2, dword ptr [rsi + 100] # xmm2 = mem[0],zero,zero,zero - setae r13b - vucomiss xmm1, xmm0 - vmovss xmm1, dword ptr [rsi + 104] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 288] # 1-byte Folded Spill - vucomiss xmm2, xmm0 - vmovss xmm2, dword ptr [rsi + 108] # xmm2 = mem[0],zero,zero,zero - setae byte ptr [rsp + 64] # 1-byte Folded Spill - vucomiss xmm1, xmm0 - vmovss xmm1, dword ptr [rsi + 112] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 48] # 1-byte Folded Spill - vucomiss xmm2, xmm0 - vmovss xmm2, dword ptr [rsi + 116] # xmm2 = mem[0],zero,zero,zero - setae byte ptr [rsp + 56] # 1-byte Folded Spill - vucomiss xmm1, xmm0 - vmovss xmm1, dword ptr [rsi + 120] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 32] # 1-byte Folded Spill - vucomiss xmm2, xmm0 - vmovss xmm2, dword ptr [rsi + 124] # xmm2 = mem[0],zero,zero,zero - setae byte ptr [rsp + 320] # 1-byte Folded Spill - vucomiss xmm1, xmm0 - setae byte ptr [rsp + 28] # 1-byte Folded Spill - sub rsi, -128 - vucomiss xmm2, xmm0 - setae cl +.LBB10_103: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r13b + setge byte ptr [rsp + 32] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r13b + setge r8b + cmp byte ptr [rsi + 2], r13b + setge r14b + cmp byte ptr [rsi + 3], r13b + setge r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 4], al + setge byte ptr [rsp + 88] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 5], al + setge byte ptr [rsp + 56] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 6], al + setge byte ptr [rsp + 160] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 7], al + setge r11b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 8], al + setge byte ptr [rsp + 320] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 9], al + setge dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 10], al + setge sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 11], al + setge dil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 12], al + setge r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 13], al + setge r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 14], al + setge byte ptr [rsp + 168] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 15], al + setge r9b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 16], bl + setge byte ptr [rsp + 288] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + setge byte ptr [rsp + 104] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 18], bl + setge byte ptr [rsp + 136] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 19], bl + setge byte ptr [rsp + 144] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + setge byte ptr [rsp + 96] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + setge byte ptr [rsp + 112] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + setge byte ptr [rsp + 128] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + setge r15b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 24], bl + setge byte ptr [rsp + 272] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 25], bl + setge byte ptr [rsp + 120] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 26], bl + setge byte ptr [rsp + 72] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 27], bl + setge byte ptr [rsp + 80] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 28], bl + setge byte ptr [rsp + 40] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 29], bl + setge byte ptr [rsp + 48] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 30], bl + setge byte ptr [rsp + 64] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 31], bl + setge bl + add r8b, r8b + add r8b, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r8b add dl, dl - add dl, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dil, 2 - or dil, dl - shl r8b, 3 - or r8b, dil - shl r9b, 4 - or r9b, r8b - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload + add dl, byte ptr [rsp + 320] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, dl + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 4 + or dl, r13b + mov r8d, edx + mov r13d, dword ptr [rsp + 28] # 4-byte Reload + shl dil, 3 + or dil, sil + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload shl dl, 5 - or dl, r9b - movzx r8d, byte ptr [rsp + 128] # 1-byte Folded Reload - shl r8b, 6 - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 7 - or dil, r8b - add r10b, r10b - add r10b, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 2 - or bl, r10b - shl r15b, 3 - or r15b, bl - shl al, 4 - or al, r15b - or dil, dl + or dl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 168] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, dl + or r9b, r12b + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 288] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl dl, 2 + or dl, al + mov esi, edx movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload shl dl, 5 - or dl, al - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 6 - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 7 - or bl, al - add r11b, r11b - add r11b, byte ptr [rsp + 40] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r11b - shl r12b, 3 - or r12b, r14b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 4 - or al, r12b - mov r8d, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 5 - or al, r8b - or bl, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 6 - shl r13b, 7 - or r13b, dl - mov rdx, qword ptr [rsp + 272] # 8-byte Reload - mov byte ptr [rdx], dil - or r13b, al - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + or dl, sil + mov rdi, qword ptr [rsp + 360] # 8-byte Reload + mov byte ptr [rdi], r11b + movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [rdi + 1], r9b + or r15b, dl + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 288] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 272] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [rdx + 1], bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl cl, 7 - or cl, bl - mov byte ptr [rdx + 2], r13b - or cl, al - mov byte ptr [rdx + 3], cl - add rdx, 4 - mov qword ptr [rsp + 272], rdx # 8-byte Spill + or al, dl + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r15b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 360], rdi # 8-byte Spill add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB10_173 -# %bb.174: - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 168] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_176 - jmp .LBB10_194 -.LBB10_33: - mov r14b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB10_37 -# %bb.34: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB10_35: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r14b - lea rsi, [rsi + 1] - mov edx, 0 - adc dl, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r11 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_35 -# %bb.36: - add r11, 1 -.LBB10_37: - sar r15, 5 - cmp r10, 32 - jl .LBB10_38 -# %bb.39: + jne .LBB10_103 +# %bb.104: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 608] # 8-byte Reload + jmp .LBB10_105 +.LBB10_92: + mov qword ptr [rsp + 360], r14 # 8-byte Spill + mov rsi, rdi +.LBB10_105: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB10_209 +# %bb.106: + or rcx, 1 + cmp r15, rcx + jne .LBB10_108 +# %bb.107: + xor r9d, r9d + jmp .LBB10_111 +.LBB10_61: + mov rdi, rsi + sub r15, r8 + je .LBB10_209 +.LBB10_63: + add r14, 1 +.LBB10_64: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 cmp r15, 32 - mov dword ptr [rsp + 28], r14d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 368], r15 # 8-byte Spill - jb .LBB10_40 -# %bb.41: - mov rax, r15 + jl .LBB10_65 +# %bb.68: + cmp rcx, 32 + mov dword ptr [rsp + 28], r13d # 4-byte Spill + mov qword ptr [rsp + 280], r15 # 8-byte Spill + mov qword ptr [rsp + 368], rcx # 8-byte Spill + jb .LBB10_69 +# %bb.70: + mov rax, rcx shl rax, 5 - add rax, rsi - cmp r11, rax - jae .LBB10_43 -# %bb.42: - lea rax, [r11 + 4*r15] - cmp rsi, rax - jae .LBB10_43 -.LBB10_40: + add rax, rdi + cmp r14, rax + jae .LBB10_72 +# %bb.71: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB10_72 +.LBB10_69: xor eax, eax mov qword ptr [rsp + 384], rax # 8-byte Spill - mov r12, rsi - mov qword ptr [rsp + 360], r11 # 8-byte Spill -.LBB10_46: - sub r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov rsi, rdi + mov qword ptr [rsp + 360], r14 # 8-byte Spill +.LBB10_75: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 152], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB10_47: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r14b +.LBB10_76: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r13b setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r14b + cmp byte ptr [rsi + 1], r13b setae r8b - cmp byte ptr [r12 + 2], r14b - setae r15b - cmp byte ptr [r12 + 3], r14b - setae r13b - cmp byte ptr [r12 + 4], r14b - setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r14b - setae byte ptr [rsp + 120] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r14b - setae al - cmp byte ptr [r12 + 7], r14b + cmp byte ptr [rsi + 2], r13b + setae r14b + cmp byte ptr [rsi + 3], r13b + setae r13b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 4], al + setae byte ptr [rsp + 88] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 5], al + setae byte ptr [rsp + 64] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 6], al + setae byte ptr [rsp + 160] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 7], al setae r11b - cmp byte ptr [r12 + 8], r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 8], al setae byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 9], al setae dl - cmp byte ptr [r12 + 10], r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rsi + 10], al setae sil - cmp byte ptr [r12 + 11], r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 11], al setae dil - cmp byte ptr [r12 + 12], r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 12], al setae r10b - cmp byte ptr [r12 + 13], r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 13], al setae r12b - cmp byte ptr [rcx + 14], r14b - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [rcx + 15], r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 14], al + setae byte ptr [rsp + 168] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 15], al setae r9b - cmp byte ptr [rcx + 16], r14b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 16], bl setae byte ptr [rsp + 288] # 1-byte Folded Spill - cmp byte ptr [rcx + 17], r14b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 17], bl + setae byte ptr [rsp + 104] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 18], bl setae byte ptr [rsp + 136] # 1-byte Folded Spill - cmp byte ptr [rcx + 18], r14b - setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [rcx + 19], r14b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 19], bl setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp byte ptr [rcx + 20], r14b - setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp byte ptr [rcx + 21], r14b - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp byte ptr [rcx + 22], r14b - setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp byte ptr [rcx + 23], r14b - setae r14b + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 20], bl + setae byte ptr [rsp + 96] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 21], bl + setae byte ptr [rsp + 112] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 22], bl + setae byte ptr [rsp + 128] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp byte ptr [rcx + 23], bl + setae r15b mov ebx, dword ptr [rsp + 28] # 4-byte Reload cmp byte ptr [rcx + 24], bl setae byte ptr [rsp + 272] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 28] # 4-byte Reload cmp byte ptr [rcx + 25], bl - setae byte ptr [rsp + 88] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 28] # 4-byte Reload cmp byte ptr [rcx + 26], bl - setae byte ptr [rsp + 96] # 1-byte Folded Spill + setae byte ptr [rsp + 72] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 28] # 4-byte Reload cmp byte ptr [rcx + 27], bl - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 28] # 4-byte Reload cmp byte ptr [rcx + 28], bl setae byte ptr [rsp + 40] # 1-byte Folded Spill @@ -56852,40 +58799,42 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar setae bl add r8b, r8b add r8b, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al - shl r15b, 2 - or r15b, r8b + shl r14b, 2 + or r14b, r8b add dl, dl add dl, byte ptr [rsp + 320] # 1-byte Folded Reload shl r13b, 3 - or r13b, r15b + or r13b, r14b shl sil, 2 or sil, dl - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload shl dl, 4 or dl, r13b mov r8d, edx + mov r13d, dword ptr [rsp + 28] # 4-byte Reload shl dil, 3 or dil, sil - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload shl dl, 5 or dl, r8b shl r10b, 4 or r10b, dil shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 168] # 1-byte Folded Reload shl sil, 6 shl r9b, 7 or r9b, sil or r11b, dl or r9b, r12b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 288] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 136] # 1-byte Folded Reload shl dl, 2 or dl, al mov esi, edx @@ -56893,30 +58842,30 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl dl, 3 or dl, sil mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload shl dl, 4 or dl, sil mov esi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload shl dl, 5 or dl, sil - mov rsi, qword ptr [rsp + 360] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 - shl r14b, 7 - or r14b, dil - mov byte ptr [rsi + 1], r9b - or r14b, dl - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 360] # 8-byte Reload + mov byte ptr [rdi], r11b + movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [rdi + 1], r9b + or r15b, dl + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 272] # 1-byte Folded Reload mov edx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 or al, dl mov edx, eax @@ -56932,393 +58881,44 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, 7 or bl, dl or bl, al - mov byte ptr [rsi + 2], r14b - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov byte ptr [rsi + 3], bl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 360], rsi # 8-byte Spill + mov byte ptr [rdi + 2], r15b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 360], rdi # 8-byte Spill add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB10_47 -# %bb.48: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 368] # 8-byte Reload - jmp .LBB10_49 -.LBB10_124: - mov r13d, dword ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB10_128 -# %bb.125: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB10_126: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setge dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r11 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r11 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_126 -# %bb.127: - add r11, 1 -.LBB10_128: - sar r15, 5 - cmp r10, 32 - jl .LBB10_129 -# %bb.130: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r15 # 8-byte Spill - mov qword ptr [rsp + 168], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB10_131: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r11 # 8-byte Spill - cmp dword ptr [rsi], r13d - setge byte ptr [rsp + 152] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - setge r10b - cmp dword ptr [rsi + 8], r13d - setge r14b - cmp dword ptr [rsi + 12], r13d - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - setge al - cmp dword ptr [rsi + 28], r13d - setge bl - cmp dword ptr [rsi + 32], r13d - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d - setge dil - cmp dword ptr [rsi + 40], r13d - setge r8b - cmp dword ptr [rsi + 44], r13d - setge r9b - cmp dword ptr [rsi + 48], r13d - setge r11b - cmp dword ptr [rsi + 52], r13d - setge r12b - cmp dword ptr [rsi + 56], r13d - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - setge cl - cmp dword ptr [rsi + 64], r13d - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d - setge r15b - cmp dword ptr [rsi + 96], r13d - setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d - setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d - setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - setge byte ptr [rsp + 28] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - setge dl - add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al - shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov r10d, eax - shl r8b, 2 - or r8b, dil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b - shl r12b, 5 - or r12b, r11b - mov r11, qword ptr [rsp + 272] # 8-byte Reload - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 5 - or al, dil - mov byte ptr [r11], bl - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r11 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 288] # 1-byte Folded Reload - shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r11 + 2], r15b - mov byte ptr [r11 + 3], dl - add rsi, 128 - add r11, 4 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB10_131 -# %bb.132: - mov r14, r11 - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r15, qword ptr [rsp + 176] # 8-byte Reload - shl r15, 5 - cmp r15, r10 - jl .LBB10_134 - jmp .LBB10_194 -.LBB10_14: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_118: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_122 -# %bb.119: - xor r11d, r11d - jmp .LBB10_120 -.LBB10_32: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_186: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_188 -# %bb.187: - xor r11d, r11d - jmp .LBB10_190 -.LBB10_23: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_144: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_148 -# %bb.145: - xor r11d, r11d - jmp .LBB10_146 -.LBB10_86: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_91: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_95 -# %bb.92: - xor r11d, r11d - jmp .LBB10_93 -.LBB10_102: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_107: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_112 -# %bb.108: - xor r11d, r11d - jmp .LBB10_109 -.LBB10_155: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_160: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_164 -# %bb.161: - xor r11d, r11d - jmp .LBB10_162 -.LBB10_171: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_176: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_180 -# %bb.177: - xor r11d, r11d - jmp .LBB10_178 -.LBB10_38: - mov qword ptr [rsp + 360], r11 # 8-byte Spill - mov r12, rsi -.LBB10_49: - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -# %bb.50: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_52 -# %bb.51: - xor esi, esi - jmp .LBB10_55 -.LBB10_129: - mov r14, r11 - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -.LBB10_134: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_138 -# %bb.135: - xor r11d, r11d - jmp .LBB10_136 -.LBB10_5: - mov r13, r11 - sar r15, 5 - cmp r10, 32 - jge .LBB10_63 -.LBB10_62: - mov qword ptr [rsp + 360], r13 # 8-byte Spill - mov r12, rsi -.LBB10_73: - shl r15, 5 - cmp r15, r10 - jge .LBB10_194 -# %bb.74: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 jne .LBB10_76 -# %bb.75: - xor esi, esi - jmp .LBB10_79 -.LBB10_122: +# %bb.77: + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 368] # 8-byte Reload + jmp .LBB10_78 +.LBB10_65: + mov qword ptr [rsp + 360], r14 # 8-byte Spill + mov rsi, rdi +.LBB10_78: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB10_209 +# %bb.79: + or rcx, 1 + cmp r15, rcx + jne .LBB10_81 +# %bb.80: + xor r9d, r9d + jmp .LBB10_84 +.LBB10_148: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_123: # =>This Inner Loop Header: Depth=1 +.LBB10_149: # =>This Inner Loop Header: Depth=1 cmp dword ptr [rsi], r13d mov edi, 0 adc dil, -1 mov rdx, r11 shr rdx, 3 - movzx r10d, byte ptr [r15 + rdx] + movzx r10d, byte ptr [r14 + rdx] xor dil, r10b mov ecx, r11d and cl, 6 @@ -57326,7 +58926,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl al, cl and al, dil xor al, r10b - mov byte ptr [r15 + rdx], al + mov byte ptr [r14 + rdx], al add r11, 2 cmp dword ptr [rsi + 4], r13d lea rsi, [rsi + 8] @@ -57338,30 +58938,29 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rdx], bl + mov byte ptr [r14 + rdx], bl cmp r9, r11 - jne .LBB10_123 -.LBB10_120: + jne .LBB10_149 +.LBB10_22: test r8b, 1 - je .LBB10_194 -# %bb.121: + je .LBB10_209 +# %bb.23: xor eax, eax cmp dword ptr [rsi], r13d - jmp .LBB10_192 -.LBB10_188: + jmp .LBB10_207 +.LBB10_203: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_189: # =>This Inner Loop Header: Depth=1 +.LBB10_204: # =>This Inner Loop Header: Depth=1 vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero vucomisd xmm1, xmm0 mov eax, 0 adc al, -1 mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] xor al, r9b mov ecx, r11d and cl, 6 @@ -57369,7 +58968,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, cl and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 vmovsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero add rsi, 16 @@ -57382,30 +58981,29 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB10_189 -.LBB10_190: + jne .LBB10_204 +.LBB10_205: test r8b, 1 - je .LBB10_194 -# %bb.191: + je .LBB10_209 +# %bb.206: vmovsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero xor eax, eax vucomisd xmm1, xmm0 - jmp .LBB10_192 -.LBB10_148: + jmp .LBB10_207 +.LBB10_167: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_149: # =>This Inner Loop Header: Depth=1 +.LBB10_168: # =>This Inner Loop Header: Depth=1 cmp qword ptr [rsi], r13 mov edi, 0 adc dil, -1 mov rdx, r11 shr rdx, 3 - movzx r10d, byte ptr [r15 + rdx] + movzx r10d, byte ptr [r14 + rdx] xor dil, r10b mov ecx, r11d and cl, 6 @@ -57413,7 +59011,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl al, cl and al, dil xor al, r10b - mov byte ptr [r15 + rdx], al + mov byte ptr [r14 + rdx], al add r11, 2 cmp qword ptr [rsi + 8], r13 lea rsi, [rsi + 16] @@ -57425,29 +59023,28 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rdx], bl + mov byte ptr [r14 + rdx], bl cmp r9, r11 - jne .LBB10_149 -.LBB10_146: + jne .LBB10_168 +.LBB10_40: test r8b, 1 - je .LBB10_194 -# %bb.147: + je .LBB10_209 +# %bb.41: xor eax, eax cmp qword ptr [rsi], r13 - jmp .LBB10_192 -.LBB10_95: + jmp .LBB10_207 +.LBB10_128: mov r9, r8 and r9, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_96: # =>This Inner Loop Header: Depth=1 +.LBB10_129: # =>This Inner Loop Header: Depth=1 cmp word ptr [rsi], r13w mov edi, 0 adc dil, -1 mov rdx, r11 shr rdx, 3 - movzx r10d, byte ptr [r15 + rdx] + movzx r10d, byte ptr [r14 + rdx] xor dil, r10b mov ecx, r11d and cl, 6 @@ -57455,7 +59052,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl al, cl and al, dil xor al, r10b - mov byte ptr [r15 + rdx], al + mov byte ptr [r14 + rdx], al add r11, 2 cmp word ptr [rsi + 2], r13w lea rsi, [rsi + 4] @@ -57467,29 +59064,28 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rdx], bl + mov byte ptr [r14 + rdx], bl cmp r9, r11 - jne .LBB10_96 -.LBB10_93: + jne .LBB10_129 +.LBB10_126: test r8b, 1 - je .LBB10_194 -# %bb.94: + je .LBB10_209 +# %bb.127: xor eax, eax cmp word ptr [rsi], r13w - jmp .LBB10_192 -.LBB10_112: + jmp .LBB10_207 +.LBB10_146: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_113: # =>This Inner Loop Header: Depth=1 +.LBB10_147: # =>This Inner Loop Header: Depth=1 cmp word ptr [rsi], r13w setge al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -57497,7 +59093,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp word ptr [rsi + 2], r13w lea rsi, [rsi + 4] @@ -57509,28 +59105,27 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB10_113 -.LBB10_109: + jne .LBB10_147 +.LBB10_143: test r8b, 1 - je .LBB10_194 -# %bb.110: + je .LBB10_209 +# %bb.144: cmp word ptr [rsi], r13w - jmp .LBB10_111 -.LBB10_164: + jmp .LBB10_145 +.LBB10_184: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_165: # =>This Inner Loop Header: Depth=1 +.LBB10_185: # =>This Inner Loop Header: Depth=1 cmp qword ptr [rsi], r13 setge al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -57538,7 +59133,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp qword ptr [rsi + 8], r13 lea rsi, [rsi + 16] @@ -57550,29 +59145,28 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB10_165 -.LBB10_162: + jne .LBB10_185 +.LBB10_182: test r8b, 1 - je .LBB10_194 -# %bb.163: + je .LBB10_209 +# %bb.183: cmp qword ptr [rsi], r13 - jmp .LBB10_111 -.LBB10_180: + jmp .LBB10_145 +.LBB10_201: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_181: # =>This Inner Loop Header: Depth=1 +.LBB10_202: # =>This Inner Loop Header: Depth=1 vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero vucomiss xmm1, xmm0 mov eax, 0 adc al, -1 mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] xor al, r9b mov ecx, r11d and cl, 6 @@ -57580,7 +59174,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, cl and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 vmovss xmm1, dword ptr [rsi + 4] # xmm1 = mem[0],zero,zero,zero add rsi, 8 @@ -57593,17 +59187,17 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB10_181 -.LBB10_178: + jne .LBB10_202 +.LBB10_199: test r8b, 1 - je .LBB10_194 -# %bb.179: + je .LBB10_209 +# %bb.200: vmovss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero xor eax, eax vucomiss xmm1, xmm0 -.LBB10_192: +.LBB10_207: adc al, -1 mov rdx, r11 shr rdx, 3 @@ -57614,74 +59208,19 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, cl xor al, sil and bl, al - jmp .LBB10_193 -.LBB10_52: - mov r10, r8 - and r10, -2 - xor esi, esi - mov r11, qword ptr [rsp + 360] # 8-byte Reload - .p2align 4, 0x90 -.LBB10_53: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rsi], r14b - mov ebx, 0 - adc bl, -1 - mov rdi, rsi - shr rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - mov ecx, esi - and cl, 6 - mov dl, 1 - shl dl, cl - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp byte ptr [r12 + rsi + 1], r14b - lea rsi, [rsi + 2] - mov ebx, 0 - adc bl, -1 - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB10_53 -# %bb.54: - add r12, rsi -.LBB10_55: - test r8b, 1 - je .LBB10_194 -# %bb.56: - xor eax, eax - cmp byte ptr [r12], r14b - adc al, -1 - mov rdx, rsi - shr rdx, 3 - mov r8, qword ptr [rsp + 360] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - jmp .LBB10_57 -.LBB10_138: + jmp .LBB10_208 +.LBB10_165: mov r10, r8 and r10, -2 xor r11d, r11d - mov r15, r14 .p2align 4, 0x90 -.LBB10_139: # =>This Inner Loop Header: Depth=1 +.LBB10_166: # =>This Inner Loop Header: Depth=1 cmp dword ptr [rsi], r13d setge al neg al mov rdi, r11 shr rdi, 3 - movzx r9d, byte ptr [r15 + rdi] + movzx r9d, byte ptr [r14 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -57689,7 +59228,7 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rdi], bl + mov byte ptr [r14 + rdi], bl add r11, 2 cmp dword ptr [rsi + 4], r13d lea rsi, [rsi + 8] @@ -57701,15 +59240,15 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl dl, cl and dl, al xor dl, bl - mov byte ptr [r15 + rdi], dl + mov byte ptr [r14 + rdi], dl cmp r10, r11 - jne .LBB10_139 -.LBB10_136: + jne .LBB10_166 +.LBB10_163: test r8b, 1 - je .LBB10_194 -# %bb.137: + je .LBB10_209 +# %bb.164: cmp dword ptr [rsi], r13d -.LBB10_111: +.LBB10_145: setge al neg al mov rdx, r11 @@ -57721,10 +59260,10 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar shl bl, cl xor al, sil and bl, al -.LBB10_193: +.LBB10_208: xor bl, sil mov byte ptr [r14 + rdx], bl -.LBB10_194: +.LBB10_209: lea rsp, [rbp - 40] pop rbx pop r12 @@ -57734,19 +59273,20 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar pop rbp vzeroupper ret -.LBB10_76: +.LBB10_108: mov r10, r8 and r10, -2 - xor esi, esi + xor r9d, r9d mov r11, qword ptr [rsp + 360] # 8-byte Reload .p2align 4, 0x90 -.LBB10_77: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [r12 + rsi], r14b +.LBB10_109: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r13b setge bl neg bl - mov rdi, rsi + mov rdi, r9 shr rdi, 3 - mov ecx, esi + mov ecx, eax and cl, 6 mov dl, 1 shl dl, cl @@ -57755,8 +59295,8 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar and dl, bl xor dl, r9b mov byte ptr [r11 + rdi], dl - cmp byte ptr [r12 + rsi + 1], r14b - lea rsi, [rsi + 2] + cmp byte ptr [rsi + rax + 1], r13b + lea r9, [rax + 2] setge bl neg bl xor bl, dl @@ -57766,2011 +59306,2065 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar and al, bl xor al, dl mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB10_77 -# %bb.78: - add r12, rsi -.LBB10_79: + cmp r10, r9 + jne .LBB10_109 +# %bb.110: + add rsi, r9 +.LBB10_111: test r8b, 1 - je .LBB10_194 -# %bb.80: - cmp byte ptr [r12], r14b + je .LBB10_209 +# %bb.112: + cmp byte ptr [rsi], r13b setge al neg al - mov rdx, rsi + mov rdx, r9 shr rdx, 3 mov r8, qword ptr [rsp + 360] # 8-byte Reload mov dil, byte ptr [r8 + rdx] - and sil, 7 + and r9b, 7 mov bl, 1 - mov ecx, esi + mov ecx, r9d + shl bl, cl + xor al, dil + and bl, al + jmp .LBB10_86 +.LBB10_81: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 360] # 8-byte Reload + .p2align 4, 0x90 +.LBB10_82: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r13b + mov ebx, 0 + adc bl, -1 + mov rdi, r9 + shr rdi, 3 + movzx r9d, byte ptr [r11 + rdi] + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r13b + lea r9, [rax + 2] + mov ebx, 0 + adc bl, -1 + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB10_82 +# %bb.83: + add rsi, r9 +.LBB10_84: + test r8b, 1 + je .LBB10_209 +# %bb.85: + xor eax, eax + cmp byte ptr [rsi], r13b + adc al, -1 + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 360] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d shl bl, cl xor al, dil and bl, al -.LBB10_57: +.LBB10_86: xor bl, dil mov byte ptr [r8 + rdx], bl - jmp .LBB10_194 -.LBB10_67: - and r15, -32 - mov rax, r15 + jmp .LBB10_209 +.LBB10_99: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 368], rax # 8-byte Spill - mov qword ptr [rsp + 416], r15 # 8-byte Spill - lea rax, [4*r15] - add rax, r13 + mov qword ptr [rsp + 416], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 360], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r13d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 384], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 272], r13 # 8-byte Spill + mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB10_68: # =>This Inner Loop Header: Depth=1 +.LBB10_100: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 376], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 216], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 160], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rcx + 1] - mov rdx, rcx + movzx eax, byte ptr [rdi + rcx + 1] vmovd xmm4, eax - mov rcx, rbx - movzx eax, byte ptr [rsi + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rsi + rdx + 2] + movzx eax, byte ptr [rdi + rcx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 576], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rcx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rcx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rcx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rsi + rdx + 6] - mov qword ptr [rsp + 256], rdx # 8-byte Spill + movzx eax, byte ptr [rdi + rcx + 6] + mov qword ptr [rsp + 200], rcx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rcx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 mov qword ptr [rsp + 40], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 288], rax # 8-byte Spill - or rbx, 544 - mov qword ptr [rsp + 248], rbx # 8-byte Spill - mov rax, rcx + mov qword ptr [rsp + 128], rax # 8-byte Spill + mov rax, rbx + or rax, 544 + mov qword ptr [rsp + 192], rax # 8-byte Spill + mov rax, rbx or rax, 576 - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov rax, rcx - or rax, 608 - mov qword ptr [rsp + 80], rax # 8-byte Spill - mov r11, rcx - or r11, 640 - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov rax, rcx + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov r13, rbx + or r13, 608 + mov qword ptr [rsp + 152], r13 # 8-byte Spill + mov rax, rbx + or rax, 640 + mov qword ptr [rsp + 104], rax # 8-byte Spill + mov rax, rbx or rax, 672 + mov r15, rax + mov qword ptr [rsp + 96], rax # 8-byte Spill + mov rax, rbx + or rax, 704 + mov r14, rax + mov qword ptr [rsp + 240], rax # 8-byte Spill + mov rax, rbx + or rax, 736 mov r12, rax - mov qword ptr [rsp + 176], rax # 8-byte Spill - mov rdi, rcx - or rdi, 704 - mov qword ptr [rsp + 240], rdi # 8-byte Spill - mov rdx, rcx - or rdx, 736 - mov qword ptr [rsp + 216], rdx # 8-byte Spill - mov rax, rcx - or rax, 768 - mov qword ptr [rsp + 224], rax # 8-byte Spill - mov r15, rcx - or r15, 800 - mov qword ptr [rsp + 112], r15 # 8-byte Spill - mov r14, rcx - or r14, 832 - mov qword ptr [rsp + 192], r14 # 8-byte Spill - mov r9, rcx - or r9, 864 - mov qword ptr [rsp + 264], r9 # 8-byte Spill - mov r8, rcx - or r8, 896 - mov qword ptr [rsp + 128], r8 # 8-byte Spill - mov r10, rcx - or r10, 928 - mov qword ptr [rsp + 88], r10 # 8-byte Spill - mov rax, rcx - mov qword ptr [rsp + 232], rcx # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill + mov r8, rbx + or r8, 768 + mov qword ptr [rsp + 248], r8 # 8-byte Spill + mov r10, rbx + or r10, 800 + mov qword ptr [rsp + 72], r10 # 8-byte Spill + mov r9, rbx + or r9, 832 + mov qword ptr [rsp + 144], r9 # 8-byte Spill + mov rdx, rbx + or rdx, 864 + mov qword ptr [rsp + 264], rdx # 8-byte Spill + mov rsi, rbx + mov rcx, rbx + mov qword ptr [rsp + 256], rbx # 8-byte Spill + or rsi, 896 + mov qword ptr [rsp + 112], rsi # 8-byte Spill + mov r11, rbx + or r11, 928 + mov qword ptr [rsp + 184], r11 # 8-byte Spill + mov rax, rbx or rax, 960 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 32], rcx # 8-byte Spill - vpinsrb xmm9, xmm0, byte ptr [rsi + rbx], 1 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + r13], 2 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 7 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 1 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 2 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 3 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 4 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11], 5 - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 6 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 12 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 13 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12], 14 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 15 - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 1 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 2 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 3 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 4 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 5 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 6 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 7 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 8 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 9 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 10 - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 12 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 13 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rsi + rbx + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 6 - mov rbx, r8 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 1], 14 - vinserti128 ymm13, ymm3, xmm0, 1 + mov qword ptr [rsp + 232], rcx # 8-byte Spill + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + rbx], 1 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + rbx], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 3 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 1 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 2 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 3 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 4 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13], 5 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 6 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 8 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 9 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 10 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 12 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 13 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 14 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 15 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 1 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 2 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 1], 3 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 5 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 6 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 7 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 8 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 1], 9 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 10 + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 11 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 12 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 13 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 14 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r12 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 1], 7 + mov r9, r14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 8 + mov r11, rax + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 1], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 + vinserti128 ymm13, ymm3, xmm0, 1 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1280], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm10, edi - mov rcx, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm10, eax + mov r10, qword ptr [rsp + 192] # 8-byte Reload vmovdqa xmm0, xmmword ptr [rsp + 576] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 2], 1 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 2], 2 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 2], 3 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 5 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 2], 6 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 7 - mov r12, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 8 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 9 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 2], 10 - mov r11, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 2], 12 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 1 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 2], 2 mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 5 + mov r15, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 7 + mov r14, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 13 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 15 + mov rcx, r12 vmovdqa xmm3, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 2 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 4 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 7 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 9 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 2], 1 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 2], 2 mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + rcx + 3], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 3 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 4 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 3], 6 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 3], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 3], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 3], 13 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 4 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 5 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 3], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 3 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 9 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 6 + mov rax, r9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 2], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 2], 8 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 2], 9 + mov r9, rdx + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 10 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 13 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 14 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r10 + 3], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 2 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 3 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 6 + mov rsi, r15 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 8 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 9 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 10 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 11 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 12 + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 14 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rcx + 3], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 3], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 3 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 4 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 3], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 3], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm8, edi - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 3], 15 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 14 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 9] - vmovd xmm11, edi + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm0, xmmword ptr [rsp + 448] # 16-byte Reload + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 2 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 5 + mov r11, rsi + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 7 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 1 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 4], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 3 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 4 - mov rax, r10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 4], 5 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 4], 7 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 4], 8 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 9 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 4], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 12 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 4], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 4], 15 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm15, byte ptr [rsi + rcx + 4], 1 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 4], 2 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 14 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 15 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm15, byte ptr [rdi + r15 + 4], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 6 mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 4 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 5 - mov rdi, r14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 7 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 4], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 9 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 7 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 8 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 9 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 10 mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 11 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 11 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 12 + mov r12, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 13 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 4], 15 + mov r12, r13 + vpinsrb xmm4, xmm14, byte ptr [rdi + r9 + 5], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 3 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 4 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 6 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 7 + mov r11, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 5], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 5], 11 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 5], 12 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 13 + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r15 + 5], 1 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 2 mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 4], 13 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 4], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 4], 15 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm4, xmm14, byte ptr [rsi + r14 + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 2 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 6 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 7 - mov r15, rax - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 5], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 5], 11 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 13 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 5], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 15 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + rcx + 5], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 3 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 4 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 6 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 4 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 5], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 9 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 vinserti128 ymm14, ymm3, xmm0, 1 - vpinsrb xmm0, xmm5, byte ptr [rsi + r12 + 5], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm3, edi + vpinsrb xmm0, xmm5, byte ptr [rdi + r12 + 5], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm3, eax vinserti128 ymm15, ymm0, xmm4, 1 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 10] - vmovd xmm4, edi - mov r11, r14 - vpinsrb xmm0, xmm12, byte ptr [rsi + r14 + 6], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 6], 3 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 6], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 5 - mov r10, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rax + 6], 1 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 2 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 6 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 6], 7 + mov r15, r11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 9 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 12 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 13 + mov rdx, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 14 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 6], 15 mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 6], 8 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 6], 9 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 6], 10 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 6], 11 - mov rax, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 15 - vpinsrb xmm5, xmm7, byte ptr [rsi + rcx + 6], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 2 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 4 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 5 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 6], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 6], 7 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 9 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 11 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 12 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 13 + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 6], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 5 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 6 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 7 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 8 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 9 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 10 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 12 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 13 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 14 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 6], 15 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 2 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 3 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 4 mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 14 - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 1 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 2 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 4 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 7], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 7], 6 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 7], 7 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 7], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 7], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 5 + mov r12, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 10 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 11 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 15 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 1 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 2 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 3 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 6 + mov rbx, rsi + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 7], 15 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 1 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 7], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 7], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 10 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 12 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 6 - mov r8, r13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 7 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 7], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 10 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 7], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rax + 7], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 7], 15 + vpinsrb xmm0, xmm1, byte ptr [rdi + r13 + 7], 14 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm2, edi - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rsi + r15 + 8], 1 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 8], 2 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 8], 3 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 8], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 8], 6 - mov r11, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 8], 8 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 9 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 10 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 8], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 12 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 13 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 8], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm2, eax + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r8 + 8], 1 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 8], 2 mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm10, byte ptr [rsi + rdx + 8], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 8], 2 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 5 + mov r14, r12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 8], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 8 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 8], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 11 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 15 + mov r10, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm10, byte ptr [rdi + r10 + 8], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 4 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 6 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 7 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 8 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 9 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 10 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 12 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 13 + mov rbx, r13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 14 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r8 + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 9], 4 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 5 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 6 mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 8], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 7 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 9], 9 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 10 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 12 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 13 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 9], 14 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 15 + vpinsrb xmm7, xmm11, byte ptr [rdi + r10 + 9], 1 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 9], 2 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 5 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 9], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 14 + vinserti128 ymm0, ymm5, xmm0, 1 + vmovdqa ymmword ptr [rsp + 1248], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 9], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm0, eax + vinserti128 ymm5, ymm5, xmm6, 1 + vmovdqa ymmword ptr [rsp + 1216], ymm5 # 32-byte Spill + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 2 + mov r11, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 5 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 8 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 10 + mov rcx, r14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 12 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 10], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 4 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 6 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 7 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 8 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 9 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 10 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 11 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 12 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 13 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 14 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 10], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 1 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 11], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 11], 6 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 8 + mov rsi, rdx + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 9 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 11 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 13 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 14 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 15 + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 1 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 11], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 11], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 11 + mov r15, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 12 + mov r13, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 13 + vinserti128 ymm3, ymm4, xmm3, 1 + vmovdqa ymmword ptr [rsp + 1184], ymm3 # 32-byte Spill + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 15 + vinserti128 ymm1, ymm2, xmm1, 1 + vmovdqa ymmword ptr [rsp + 1152], ymm1 # 32-byte Spill + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 12], 3 mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 8], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 9 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 8], 10 - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 11 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 8], 12 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 12], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 6 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 8 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 9 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 12], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 12 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 12], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 15 + vpinsrb xmm2, xmm5, byte ptr [rdi + r9 + 12], 1 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 2 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 3 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 4 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 5 + mov r8, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 6 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 7 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 12], 8 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 10 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 12], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 13 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 14 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 15 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 1 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 2 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 4 mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 8], 14 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r13 + 8], 15 - vpinsrb xmm6, xmm8, byte ptr [rsi + r15 + 9], 1 - mov r13, r15 - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 3 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rsi + r14 + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 6 - mov r9, rax - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 7 - vpinsrb xmm6, xmm6, byte ptr [rsi + r10 + 9], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 5 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 7 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 10 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 11 mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 9 - mov r15, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r15 + 9], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 11 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r11 + 9], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 13], 13 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 14 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 15 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 13], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 3 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 13], 4 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rsi + rax + 9], 1 - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 9], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 4 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 13], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 9 mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 9], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + r12 + 9], 12 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 9], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 9], 14 - vinserti128 ymm0, ymm5, xmm0, 1 - vmovdqa ymmword ptr [rsp + 1248], ymm0 # 32-byte Spill + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 13], 14 + vinserti128 ymm0, ymm2, xmm0, 1 + vmovdqa ymmword ptr [rsp + 1088], ymm0 # 32-byte Spill + vpinsrb xmm0, xmm1, byte ptr [rdi + r13 + 13], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm1, eax + vinserti128 ymm0, ymm0, xmm3, 1 + vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm0, edi - vinserti128 ymm5, ymm5, xmm6, 1 - vmovdqa ymmword ptr [rsp + 1216], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 10], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 10], 4 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 6 + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm0, eax + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 1 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 2 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 3 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 7 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 + mov r10, r12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 14], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 12 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 13 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 14], 14 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 14], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 7 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 10], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 10], 10 - mov r9, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 10], 12 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 10], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 14], 4 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 15 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 10], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 2 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 10], 4 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 5 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 9 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 6 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 9 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 14], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 10], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 13 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 11], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 4 - mov r13, rbx - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 11], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 6 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 8 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 11], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 11], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 13 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 14 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 11], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 11], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 15 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 11], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 11], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 8 + movzx eax, byte ptr [rdi + rax + 15] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 4 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 5 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 15], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 9 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 15], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 15], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 15], 15 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 15] + vmovd xmm3, eax + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 1 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 3 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 9 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 8 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 15], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 11], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 13 - vinserti128 ymm3, ymm4, xmm3, 1 - vmovdqa ymmword ptr [rsp + 1184], ymm3 # 32-byte Spill - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 11], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 13] - vmovd xmm3, edi + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 11], 15 - vinserti128 ymm1, ymm2, xmm1, 1 - vmovdqa ymmword ptr [rsp + 1152], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 13] - vmovd xmm1, edi - mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 12], 1 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 12], 2 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 12], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 12], 4 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 12], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 6 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 12], 7 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 12], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 9 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 12], 10 - mov r14, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 12], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 13 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 14 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 12], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 15 + vinserti128 ymm0, ymm0, xmm1, 1 + vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill + vinserti128 ymm0, ymm3, xmm2, 1 + vmovdqa ymmword ptr [rsp + 1056], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 1 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 2 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rsi + rax + 12], 1 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 12], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 4 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 3 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 12], 9 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 12], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 12], 12 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 12], 14 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 1 - mov r15, r11 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 13], 3 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 13], 5 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 13], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 11 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 13], 12 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 13 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 15 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 2 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 3 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 4 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 13], 5 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 13], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 13], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 13], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 7 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 8 mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 13], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 16], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 16], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 15 + movzx eax, byte ptr [rdi + r10 + 16] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 2 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 13], 14 - vinserti128 ymm0, ymm2, xmm0, 1 - vmovdqa ymmword ptr [rsp + 1088], ymm0 # 32-byte Spill + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 5 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 7 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 10 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rax + 13], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 14] - vmovd xmm1, edi - vinserti128 ymm0, ymm0, xmm3, 1 - vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill - mov r13, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 14] - vmovd xmm0, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 2 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 14], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 13 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 14 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 15 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rsi + 17] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 2 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 3 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 17], 4 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 6 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 7 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 13 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 5 - mov r12, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 14], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 15 + movzx eax, byte ptr [rdi + r10 + 17] + vmovd xmm3, eax + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 17], 1 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 8 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 14], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 2 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 3 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 17], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 14 + vinserti128 ymm0, ymm1, xmm0, 1 + vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r15 + 17], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill + movzx eax, byte ptr [rdi + rsi + 18] + vmovd xmm0, eax mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 2 + mov r9, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 18], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 5 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 7 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 10 mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 14], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 15 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 14], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 12 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 18], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 1 + mov r13, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 6 mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 14], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 14], 5 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 14], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 14], 7 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 14], 9 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 14], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 14], 12 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 14], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 15] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 1 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 15], 3 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 15], 6 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 15], 7 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 15], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 9 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 10 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 15], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 15 - movzx edi, byte ptr [rsi + r13 + 15] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 2 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 15], 4 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 15], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 15], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 15], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 8 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 11 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 18], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm2, eax + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 19], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 19], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 7 + mov r11, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 19], 8 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 15], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 15 - vinserti128 ymm0, ymm0, xmm1, 1 - vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 10 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 13 + mov r14, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 19], 14 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm3, eax + mov r9, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 19], 7 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 10 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 13 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 15 + vinserti128 ymm0, ymm1, xmm0, 1 + vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 - vmovdqa ymmword ptr [rsp + 1056], ymm0 # 32-byte Spill + vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 20] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 3 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + mov r13, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 20], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 20], 8 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 20], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 11 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 15 + mov r14, r8 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 16] - vmovd xmm0, edi - mov r10, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 16], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 2 + movzx eax, byte ptr [rdi + rax + 20] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 1 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 4 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 8 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 3 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 4 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 16], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 16], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 16], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 11 + mov r15, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 12 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 13 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 20], 14 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 21] + vmovd xmm2, eax mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 16], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 1 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 16], 15 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 16] - vmovd xmm1, edi - mov r14, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 16], 1 - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 16], 2 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 3 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 16], 5 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 7 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 8 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 16], 9 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 12 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 14 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 15 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r13 + 17] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 1 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 2 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 17], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 17], 5 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 17], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 17], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 9 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 17], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 17], 15 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 17] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 17], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 17], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 3 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 17], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 6 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 6 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 17], 9 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 10 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 17], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 21], 10 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 12 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 15 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + r14 + 21] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 1 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 2 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 17], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 21], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 10 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rax + 17], 15 + vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill + vpinsrb xmm0, xmm3, byte ptr [rdi + r9 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r13 + 18] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 1 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 3 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 5 + vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill + mov r10, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 22] + vmovd xmm0, eax + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 22], 1 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 2 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 4 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 22], 5 mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 18], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 18], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 6 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 7 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 11 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 18], 9 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 18], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 11 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 18], 12 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 18], 14 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 15 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 18] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 2 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 18], 4 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 5 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 18], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 8 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 18], 9 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 18], 11 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 12 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 18], 13 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 18], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 15 - movzx edi, byte ptr [rsi + r13 + 19] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 1 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 2 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 3 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 19], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 5 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 6 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 9 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 19], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 19], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 13 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 22], 14 mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 19] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 1 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 19], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 3 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 4 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 19], 5 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 19], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 15 + movzx eax, byte ptr [rdi + r14 + 22] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 3 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 22], 4 + mov r9, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 5 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 19], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 11 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 19], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 19], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 19], 15 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - vinserti128 ymm0, ymm3, xmm2, 1 - vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 20] - vmovd xmm0, edi + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 14 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 15 + movzx eax, byte ptr [rdi + r10 + 23] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 2 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 23], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 5 + mov r15, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 7 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 1 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 2 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 20], 4 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 5 - mov r8, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 20], 6 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 7 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 9 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 10 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 20], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 15 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 20] - vmovd xmm1, edi - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 20], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 20], 2 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 20], 3 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 20], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 20], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 8 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 20], 9 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 12 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 13 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 15 - movzx edi, byte ptr [rsi + r11 + 21] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 2 - mov r11, rdx + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 9 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 14 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 15 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 23] + vmovd xmm3, eax + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 1 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 8 mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 9 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 10 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 23], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 13 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 21], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 21], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 15 + vinserti128 ymm10, ymm1, xmm0, 1 + vinserti128 ymm11, ymm3, xmm2, 1 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm0, eax + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 6 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 7 + mov r8, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 8 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 10 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 11 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 21], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 21], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 15 + movzx eax, byte ptr [rdi + rbx + 24] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 1 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 4 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 7 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 12 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 13 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 14 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 15 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 21] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 15 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 21], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 21], 4 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 21], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 6 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 7 + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 2 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 3 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 9 + mov r9, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 11 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 12 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 13 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 3 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 5 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 9 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 21], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 12 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 21], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rbx + 21], 15 + vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r11 + 25], 15 vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 3 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 4 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 5 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 22], 6 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 7 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 8 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 9 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 10 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 11 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 22], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 15 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 22] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 1 + vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill mov r13, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 22], 2 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 3 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 22], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 7 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 22], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 22], 12 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 13 + movzx eax, byte ptr [rdi + r13 + 26] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 2 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 26], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 22], 15 - movzx edi, byte ptr [rsi + rcx + 23] - vmovd xmm2, edi + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 5 + mov r15, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 26], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 7 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 1 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 3 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 4 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 6 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 13 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 26] + vmovd xmm1, eax mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 23], 10 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 23], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 23], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 3 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 4 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 7 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 23], 15 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 23] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 23], 2 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 23], 3 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 23], 4 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 23], 5 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 23], 6 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 23], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 9 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 23], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 8 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 9 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 10 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 23], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 23], 13 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 23], 14 - mov r11, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 15 - vinserti128 ymm10, ymm1, xmm0, 1 - vinserti128 ymm11, ymm3, xmm2, 1 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 24] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 2 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 3 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 4 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 5 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 24], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 24], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 9 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 24], 11 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 12 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 14 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 24], 15 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 24] - vmovd xmm1, edi - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 1 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 24], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 24], 6 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 7 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 24], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 11 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 24], 12 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 24], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 25] - vmovd xmm2, edi - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 1 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 25], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 13 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 4 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 25], 5 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 6 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 26], 15 + movzx eax, byte ptr [rdi + r13 + 27] + vmovd xmm2, eax + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 27], 1 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 2 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 3 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + mov r11, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 9 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 12 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 27], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 15 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 27] + vmovd xmm3, eax mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 8 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 25], 9 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 10 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 11 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 25], 12 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 25], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 25], 15 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 25] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 2 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 3 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 4 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 25], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 9 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 10 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 25], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 13 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 14 - vinserti128 ymm0, ymm1, xmm0, 1 - vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rcx + 25], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 26] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 2 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 3 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 5 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 6 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 26], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 26], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 26], 12 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 13 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 26], 15 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 26] - vmovd xmm1, edi - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 1 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 26], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 4 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 5 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 6 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 7 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 26], 8 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 9 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 26], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 26], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 12 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 26], 13 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 15 - movzx edi, byte ptr [rsi + rcx + 27] - vmovd xmm2, edi - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 27], 1 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 2 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 27], 3 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 4 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 27], 5 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 6 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 7 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 8 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 27], 9 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 27], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 1 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 10 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov r8, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 13 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 14 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 27], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 27], 15 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 27] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 1 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 2 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 3 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 4 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 27], 5 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 27], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 10 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 11 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 13 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 27], 14 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 28], 1 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 28], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 3 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 5 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 6 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 7 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 28], 8 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 10 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 28], 11 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 12 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 28], 13 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 15 - movzx edi, byte ptr [rsi + rax + 28] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 1 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 2 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 3 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 5 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 28], 6 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 7 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 9 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 28], 10 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 28], 12 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 28], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 14 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 29] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 29], 2 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 29], 4 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 5 - mov r12, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 29], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 29], 8 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 9 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 29], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 29], 11 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 29], 13 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 29], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 15 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - movzx edi, byte ptr [rsi + r15 + 29] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 1 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 3 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 29], 4 + movzx eax, byte ptr [rdi + rax + 28] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 28], 2 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 6 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 29], 6 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 29], 7 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 29], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 12 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 13 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 14 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 15 + movzx eax, byte ptr [rdi + r10 + 28] + vmovd xmm1, eax + mov r10, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 1 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 28], 3 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 11 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 29], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 5 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 6 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 7 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 8 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 9 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 10 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 11 + mov r9, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 13 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 14 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 15 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 29] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 4 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm3, byte ptr [rsi + rax + 29], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 7 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 10 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 29], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 15 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 29] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 1 + mov r13, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 3 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 7 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 9 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 10 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 12 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + r8 + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm4, byte ptr [rsi + r13 + 29], 15 + vpinsrb xmm0, xmm4, byte ptr [rdi + rsi + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 30] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 30], 1 - movzx edi, byte ptr [rsi + rax + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 31], 1 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + movzx eax, byte ptr [rdi + rsi + 30] + vmovd xmm0, eax + mov r14, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 30], 1 + movzx eax, byte ptr [rdi + rsi + 31] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 31], 1 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 + mov r14, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 31], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 3 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 31], 6 - mov r13, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 31], 10 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 11 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 31], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + rax + 31], 15 - movzx eax, byte ptr [rsi + r15 + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + rax + 31], 15 + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 30], 1 - movzx eax, byte ptr [rsi + r15 + 31] + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 31], 1 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + r11 + 31], 4 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 31], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 31], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 9 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 31], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 31], 2 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 13 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 4 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 8 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 9 + mov rax, rbx + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r9 + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 31], 14 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -59891,2004 +61485,2007 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 376] # 8-byte Reload - vmovdqu ymmword ptr [r13 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r13 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r13 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r13 + 4*rcx], ymm1 + vmovdqu ymmword ptr [r14 + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [r14 + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [r14 + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [r14 + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 416] # 8-byte Folded Reload - jne .LBB10_68 -# %bb.69: - mov r15, qword ptr [rsp + 608] # 8-byte Reload - cmp r15, qword ptr [rsp + 416] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 368] # 8-byte Reload - jne .LBB10_70 - jmp .LBB10_73 -.LBB10_43: - and r15, -32 - mov rax, r15 + jne .LBB10_100 +# %bb.101: + mov rcx, qword ptr [rsp + 608] # 8-byte Reload + cmp rcx, qword ptr [rsp + 416] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r13d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 368] # 8-byte Reload + jne .LBB10_102 + jmp .LBB10_105 +.LBB10_72: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rsi + add rax, rdi mov qword ptr [rsp + 536], rax # 8-byte Spill - mov qword ptr [rsp + 384], r15 # 8-byte Spill - lea rax, [r11 + 4*r15] + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp + 360], rax # 8-byte Spill - vmovd xmm0, r14d + vmovd xmm0, r13d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill xor eax, eax - mov qword ptr [rsp + 272], r11 # 8-byte Spill + mov qword ptr [rsp + 272], r14 # 8-byte Spill .p2align 4, 0x90 -.LBB10_44: # =>This Inner Loop Header: Depth=1 +.LBB10_73: # =>This Inner Loop Header: Depth=1 mov rbx, rax mov qword ptr [rsp + 376], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 248], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 160], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 104], rax # 8-byte Spill + mov qword ptr [rsp + 216], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 232], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 512 mov rcx, rax - movzx eax, byte ptr [rsi + rax] - mov rdx, rcx + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - mov rcx, rbx - movzx eax, byte ptr [rsi + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rsi + rdx + 1] + movzx eax, byte ptr [rdi + rcx + 1] vmovd xmm4, eax - movzx eax, byte ptr [rsi + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm5, eax - movzx eax, byte ptr [rsi + rdx + 2] + movzx eax, byte ptr [rdi + rcx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rdx + 3] + movzx eax, byte ptr [rdi + rcx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rsi + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rsi + rdx + 4] + movzx eax, byte ptr [rdi + rcx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 544], xmm1 # 16-byte Spill - movzx eax, byte ptr [rsi + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rsi + rdx + 5] + movzx eax, byte ptr [rdi + rcx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rsi + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm13, eax - movzx eax, byte ptr [rsi + rdx + 6] - mov qword ptr [rsp + 264], rdx # 8-byte Spill + movzx eax, byte ptr [rdi + rcx + 6] + mov qword ptr [rsp + 232], rcx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rsi + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rsi + rdx + 7] + movzx eax, byte ptr [rdi + rcx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rsi + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 96], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 80], rax # 8-byte Spill + mov qword ptr [rsp + 88], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 64], rax # 8-byte Spill - mov r13, rbx - or r13, 544 + mov qword ptr [rsp + 288], rax # 8-byte Spill + mov rax, rbx + or rax, 544 + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 576 - mov r12, rax - mov qword ptr [rsp + 72], rax # 8-byte Spill - mov r14, rbx - or r14, 608 - mov qword ptr [rsp + 192], r14 # 8-byte Spill - or rbx, 640 - mov qword ptr [rsp + 240], rbx # 8-byte Spill - mov r9, rcx + mov r13, rax + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov rax, rbx + or rax, 608 + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r11, rbx + or r11, 640 + mov qword ptr [rsp + 168], r11 # 8-byte Spill + mov r9, rbx or r9, 672 - mov qword ptr [rsp + 136], r9 # 8-byte Spill - mov rax, rcx - or rax, 704 - mov qword ptr [rsp + 128], rax # 8-byte Spill - mov rax, rcx + mov qword ptr [rsp + 40], r9 # 8-byte Spill + mov r10, rbx + or r10, 704 + mov qword ptr [rsp + 224], r10 # 8-byte Spill + mov rax, rbx or rax, 736 - mov qword ptr [rsp + 184], rax # 8-byte Spill - mov r11, rcx - or r11, 768 - mov qword ptr [rsp + 176], r11 # 8-byte Spill - mov rdi, rcx - or rdi, 800 - mov qword ptr [rsp + 88], rdi # 8-byte Spill - mov r10, rcx - or r10, 832 - mov qword ptr [rsp + 112], r10 # 8-byte Spill - mov r8, rcx - or r8, 864 - mov qword ptr [rsp + 168], r8 # 8-byte Spill - mov rax, rcx - or rax, 896 + mov qword ptr [rsp + 152], rax # 8-byte Spill + mov r14, rbx + or r14, 768 + mov qword ptr [rsp + 120], r14 # 8-byte Spill + mov rax, rbx + or rax, 800 + mov r12, rax + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov rax, rbx + or rax, 832 mov r15, rax - mov qword ptr [rsp + 224], rax # 8-byte Spill - mov rdx, rcx - or rdx, 928 - mov qword ptr [rsp + 40], rdx # 8-byte Spill - mov rax, rcx - mov qword ptr [rsp + 256], rcx # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill + mov rdx, rbx + or rdx, 864 + mov qword ptr [rsp + 200], rdx # 8-byte Spill + mov rsi, rbx + mov rcx, rbx + mov qword ptr [rsp + 264], rbx # 8-byte Spill + or rsi, 896 + mov qword ptr [rsp + 136], rsi # 8-byte Spill + mov r8, rbx + or r8, 928 + mov qword ptr [rsp + 112], r8 # 8-byte Spill + mov rax, rbx or rax, 960 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill or rcx, 992 - mov qword ptr [rsp + 216], rcx # 8-byte Spill - mov qword ptr [rsp + 248], r13 # 8-byte Spill - vpinsrb xmm9, xmm0, byte ptr [rsi + r13], 1 - vpinsrb xmm0, xmm9, byte ptr [rsi + r12], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9], 5 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 6 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx], 15 - mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8], 1 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10], 2 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 4 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9], 5 - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14], 6 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15], 7 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi], 8 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax], 9 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11], 10 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 11 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx], 12 + mov qword ptr [rsp + 160], rcx # 8-byte Spill + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm9, xmm0, byte ptr [rdi + rbx], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + r13], 2 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 6 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 15 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 1 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 2 + mov r8, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 3 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 4 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 5 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 8 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 9 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 10 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 11 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 13 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 14 mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 13 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12], 14 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 15 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymm10, ymmword ptr [rsp + 608] # 32-byte Reload vpmaxub ymm3, ymm10, ymm0 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 1 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 2 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 3 - mov r13, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 1], 4 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 5 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 6 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 7 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 8 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 9 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 10 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 1 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 2 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 3 mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 11 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 4 mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 5 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 7 mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 14 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 1], 15 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 1], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + r10 + 1], 2 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 1], 3 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 1], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 1], 7 - mov r14, r15 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 9 - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 1], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 1], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 1], 13 - mov rbx, rax + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 8 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 9 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 10 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 11 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 12 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 13 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 14 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 1], 15 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 1], 6 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 11 + mov rdx, r12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 vpcmpeqb ymm0, ymm0, ymm3 vmovdqa ymmword ptr [rsp + 1280], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm5, byte ptr [rsi + r12 + 1], 14 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm9, edi - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 1], 15 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + r13 + 1], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 1], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 8] - vmovd xmm6, edi + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm6, eax vmovdqa xmm0, xmmword ptr [rsp + 480] # 16-byte Reload - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 2], 1 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 2 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 2], 4 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 2], 5 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 2], 6 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 2], 7 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 8 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 9 + mov r10, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 1 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 2 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 6 + mov r9, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 7 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 11 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 12 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 10 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 11 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 2], 13 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 2], 14 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 2], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 13 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 2], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload vmovdqa xmm3, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 2], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 2], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 2], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 2 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 3 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 2], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 6 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 7 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 2], 8 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 9 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 2], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 2], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 2], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 2], 7 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 2], 8 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 2], 9 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 2], 10 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 2], 11 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 2], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rsi + r15 + 3], 1 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 2 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 3 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 4 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 3], 6 - vpinsrb xmm4, xmm4, byte ptr [rsi + r8 + 3], 7 - mov r15, r8 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 3], 8 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 9 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 3], 10 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 11 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 12 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 3], 13 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 3], 14 - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rsi + rax + 3], 1 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 3], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 14 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 15 + vpinsrb xmm4, xmm11, byte ptr [rdi + r10 + 3], 1 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 3 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 4 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 8 + mov r13, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 9 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 10 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 12 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 3], 14 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rcx + 3], 1 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 2 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 3], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 3], 4 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 3], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 3], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 7 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 3], 8 - vpinsrb xmm5, xmm5, byte ptr [rsi + r12 + 3], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 3], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 3], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 14 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rax + 3], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm8, edi + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 9] - vmovd xmm11, edi - mov rcx, qword ptr [rsp + 248] # 8-byte Reload + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm0, xmmword ptr [rsp + 544] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 4], 1 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 4], 2 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 4], 3 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 5 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 4], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 4], 7 - mov r12, r13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 8 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 4], 9 - mov r10, r11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 4], 10 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 4], 11 - mov rbx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 4], 12 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 4], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 1 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 4], 2 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 3 + mov r14, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 4], 4 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 5 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 4], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 7 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 9 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 11 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 4], 12 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm15, byte ptr [rdi + rax + 4], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 3 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 4], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm15, byte ptr [rsi + rax + 4], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 4], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 4 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 4], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 7 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 8 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 10 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 4], 11 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 4], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 14 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 4], 15 - vpinsrb xmm4, xmm14, byte ptr [rsi + rcx + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 5], 2 - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 5], 3 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 4 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rcx + 5], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 5], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 5 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 6 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 7 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 8 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 9 mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r9 + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rsi + r12 + 5], 8 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 5], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 5], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + rbx + 5], 12 - vpinsrb xmm4, xmm4, byte ptr [rsi + r15 + 5], 13 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 5], 14 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r10 + 5], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm13, byte ptr [rsi + rax + 5], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 11 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 12 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 13 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 14 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 15 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm14, byte ptr [rdi + rbx + 5], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 5], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 6 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 5], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 5], 10 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 5], 13 mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 5], 2 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 5], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 4 - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 5], 5 - mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 5], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 5], 7 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 8 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 9 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 10 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 11 - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 5], 12 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdx + 5], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 14 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 15 + mov r14, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm5, xmm13, byte ptr [rdi + r14 + 5], 1 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 2 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 5], 3 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 5], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 6 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 11 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 vinserti128 ymm14, ymm3, xmm0, 1 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rsi + rdx + 5], 14 - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 10] - vmovd xmm3, edi - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 5], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 5], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 5], 15 vinserti128 ymm15, ymm0, xmm4, 1 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 10] - vmovd xmm4, edi - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rsi + r12 + 6], 1 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 6], 2 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 6], 3 - mov rdx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 6], 4 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 6], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 6], 7 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 8 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 9 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 10 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 11 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 6], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 6], 15 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rdi + 6], 1 - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 2 - mov r10, r14 - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 6], 4 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 5 - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 6 - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 7 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r8 + 6], 8 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r14 + 6], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 6], 11 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 6], 12 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 6], 13 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rcx + 6], 14 - vpinsrb xmm5, xmm5, byte ptr [rsi + r15 + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 7], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 7], 2 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 5 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 6 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 7 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 8 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 7], 9 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 10 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 11 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 12 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 13 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 14 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 7], 15 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 1 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rbx + 6], 1 + mov r11, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 8 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 6], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 13 mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 7], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 7], 4 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 5 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 6 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 7], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 7], 9 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 7], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 7], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 7], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 15 + vpinsrb xmm5, xmm7, byte ptr [rdi + r14 + 6], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 2 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 3 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 4 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 5 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 7 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 8 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 9 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 12 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 13 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 14 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 2 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 3 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 4 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 6 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 7 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 9 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 10 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 11 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 12 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 14 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 15 + mov r15, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 7], 1 + mov r11, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 5 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 7], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 7], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 7], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm0, edi + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm0, eax vinserti128 ymm1, ymm1, xmm2, 1 vmovdqa ymmword ptr [rsp + 1248], ymm1 # 32-byte Spill + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm9, byte ptr [rdi + rax + 8], 1 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 11] - vmovd xmm1, edi - vpinsrb xmm2, xmm9, byte ptr [rsi + r12 + 8], 1 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 2 - mov r8, r13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 8], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 3 + mov r8, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 8], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 8], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 8], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 8], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 8], 12 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 8], 13 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 8], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 8], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r15 + 8], 1 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 8], 2 mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 4 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 8], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 3 + mov r10, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 8], 4 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 6 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 8], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 6 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 8], 9 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 10 - mov rdx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 8], 11 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 8], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 8], 13 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 8], 14 - mov r15, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 8], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm6, byte ptr [rsi + rax + 8], 1 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 4 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r9 + 8], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 6 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rdi + 8], 7 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 8 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rax + 8], 9 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 8], 10 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 8], 11 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 8], 12 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 8], 13 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + rbx + 8], 14 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rsi + r11 + 8], 15 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 7 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 8 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 9 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 10 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 13 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 14 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 8], 15 vinserti128 ymm2, ymm5, xmm2, 1 vpmaxub ymm5, ymm10, ymm2 - vpinsrb xmm6, xmm8, byte ptr [rsi + r12 + 9], 1 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rsi + r8 + 9], 3 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm6, xmm8, byte ptr [rdi + rbx + 9], 1 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 2 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 4 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 5 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 6 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 7 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 8 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 9 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 10 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 11 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 12 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 9], 13 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 9], 14 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 15 + vpinsrb xmm7, xmm11, byte ptr [rdi + r15 + 9], 1 + vpinsrb xmm7, xmm7, byte ptr [rdi + r9 + 9], 2 mov rbx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rsi + r13 + 9], 5 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 6 - vpinsrb xmm6, xmm6, byte ptr [rsi + r10 + 9], 7 - mov r12, r10 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 8 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + r10 + 9], 9 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rbx + 9], 10 - vpinsrb xmm6, xmm6, byte ptr [rsi + rdx + 9], 11 - vpinsrb xmm6, xmm6, byte ptr [rsi + r14 + 9], 12 - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rsi + rcx + 9], 14 - vpinsrb xmm6, xmm6, byte ptr [rsi + r15 + 9], 15 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm11, byte ptr [rsi + rcx + 9], 1 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r11 + 9], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 9], 3 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 9], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + r9 + 9], 5 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rdx + 9], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rdi + 9], 7 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rcx + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 9 - mov r14, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 9], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 11 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + r13 + 9], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 9], 4 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 5 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 12 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 9], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r13 + 9], 14 vpcmpeqb ymm2, ymm2, ymm5 vmovdqa ymmword ptr [rsp + 1216], ymm2 # 32-byte Spill - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rsi + rax + 9], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm2, edi + vpinsrb xmm5, xmm7, byte ptr [rdi + r14 + 9], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm2, eax vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1184], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 12] - vmovd xmm5, edi - mov r15, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 10], 1 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 10], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 3 - mov r8, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 10], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 5 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 10], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 10], 7 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 10], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 10], 9 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 10], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax + mov r13, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 1 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 2 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 3 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 11 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 13 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 10], 14 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 10], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 1 - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdi + 10], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 5 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 6 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 7 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 9 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 5 - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 10], 6 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r11 + 10], 7 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rax + 10], 8 - mov rdx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 10], 9 - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 10 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r14 + 10], 11 - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 10], 12 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 10], 13 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + rdx + 10], 14 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rsi + r13 + 10], 15 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 11], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 11], 2 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 11], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 11], 4 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 11], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 11], 6 - mov rbx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 11], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 11], 8 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 11], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 11], 10 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 11], 11 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 11], 12 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 11], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 11], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 11], 15 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 11], 3 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 4 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 5 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 11], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 11], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 10 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 11], 11 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 11 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 2 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 5 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 6 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 7 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 8 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 9 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 10 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 11 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 12 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 13 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 10], 14 + mov r14, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 10], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 11], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 11], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 11], 3 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 11], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 11], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 11], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 11], 8 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 11], 9 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 11], 10 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 11], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 11], 12 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 11], 13 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 11], 14 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 11], 15 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 1 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 3 + mov r11, rax + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 5 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 6 + mov r14, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 11], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1152], ymm3 # 32-byte Spill - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 11], 14 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 13] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 11], 15 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 11], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 1120], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 13] - vmovd xmm0, edi - mov r12, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm2, byte ptr [rsi + r12 + 12], 1 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 12], 2 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 12], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 12], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 12], 5 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 12], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 12], 7 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 12], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 12], 9 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 12], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 12], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 12], 12 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm2, byte ptr [rdi + rax + 12], 1 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 12], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 12], 4 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 12], 13 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 12], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 12], 15 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm5, byte ptr [rsi + r10 + 12], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 12], 2 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 3 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 12], 4 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 5 - mov r15, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 12], 6 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 7 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 8 - mov r13, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 12], 9 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 10 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 11 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 12 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 13 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 12], 14 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 13], 1 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 13], 4 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 5 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 13], 6 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 13], 8 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 9 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 13], 10 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 11 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 13], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 13 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 13], 14 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 13], 15 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 13], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 12], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 7 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 12], 8 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 12], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 12], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 12], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 12 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 12], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 12], 14 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 13], 4 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 13], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 13], 6 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 13], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 12], 15 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + rdx + 12], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 3 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 12], 4 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 7 + mov r14, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 12], 8 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 9 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 10 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 11 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 12 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 13 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 14 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 15 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 2 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 3 + mov rbx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 4 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 5 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 6 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 13], 8 + mov r15, r12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 13], 10 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 11 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 13 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 14 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 13], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 2 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 13], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 13], 5 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 13], 9 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 13], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 11 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 13 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 13], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 13], 8 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 13], 9 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 13], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 13], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 13], 13 + mov r10, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 13], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1088], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 13], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 14] - vmovd xmm1, edi + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 13], 15 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r8 + 14] + vmovd xmm1, eax vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 14] - vmovd xmm0, edi - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 14], 1 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 14], 2 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 14], 3 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 4 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 14], 6 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 14], 8 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 14], 10 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov r13, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 14], 13 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 14], 14 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 14], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 4 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 14], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 2 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 14], 3 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 14], 4 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 14], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 14], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 12 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 14], 15 + movzx eax, byte ptr [rdi + r8 + 15] + vmovd xmm2, eax + mov r9, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 2 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 15], 6 + mov r13, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 15], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 11 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 15], 12 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 15], 13 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 14 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 14], 5 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 14], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 14], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 15] + vmovd xmm3, eax + mov r11, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 15], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 15], 5 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 8 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 14], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 14], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 11 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 13 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 14 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 14], 15 - mov r15, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + r15 + 15] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 15], 3 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 4 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 15], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 6 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 15], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 15], 8 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 15], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 15], 10 - mov r14, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 15], 11 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 15], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 15], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 15], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 15], 15 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rbx + 15] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 15], 2 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 15], 3 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 15], 4 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 15], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 6 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 15], 7 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 15], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 11 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 15], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 15], 13 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 15], 14 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 15], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 6 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 10 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 11 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r15 + 16] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 1 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 3 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 16], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 16], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 7 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 16], 9 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 16], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 16], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 16], 13 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 16], 14 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 16], 15 - movzx edi, byte ptr [rsi + rbx + 16] - vmovd xmm1, edi - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 16], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 16], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 16], 4 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 16], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 16], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 7 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 16], 8 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 16], 9 - mov r10, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 16], 10 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 16], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 12 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 1 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 3 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 5 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 16], 7 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 16], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 9 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 16], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 13 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 2 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 3 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 7 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 16], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 13 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 14 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 17] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 1 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 2 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 17], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 17], 6 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 17], 8 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 17], 10 + mov r9, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 17], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 14 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 15 + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 17] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 3 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 6 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 17], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 8 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 12 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 16], 14 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 16], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 17] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 1 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 17], 4 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 5 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 17], 6 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 7 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 8 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 9 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 17], 11 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 17], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 17], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 17], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 17] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 17], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 17], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 5 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 17], 6 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 17], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 17], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 17], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 17], 11 - mov r12, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 17], 12 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 13 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 17], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 - vpinsrb xmm1, xmm3, byte ptr [rsi + r9 + 17], 15 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm3, byte ptr [rdi + rax + 17], 15 vpmaxub ymm3, ymm10, ymm0 vpcmpeqb ymm0, ymm0, ymm3 vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill vinserti128 ymm0, ymm1, xmm2, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + rax + 18] - vmovd xmm0, edi - mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 18], 1 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 2 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 18], 3 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 18], 4 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 6 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 18], 7 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 18], 8 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 9 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 18], 10 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 18], 11 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 12 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 13 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 14 - mov rdx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 18], 15 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 18] - vmovd xmm1, edi - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 1 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 2 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 3 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + mov r15, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 18], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 18], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 7 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 18], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 18], 9 mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 18], 4 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 18], 6 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 7 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 8 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 9 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 18], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 18], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 14 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 18], 15 - movzx edi, byte ptr [rsi + rax + 19] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 18], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 15 + movzx eax, byte ptr [rdi + rbx + 18] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 1 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 2 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 4 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 9 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 10 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 19], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 19], 4 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 19], 5 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 19], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 19], 7 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 19], 8 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 19], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 19], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 19], 11 - mov r11, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 19], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 12 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 14 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 4 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 19], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 14 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 19], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 19] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 19], 2 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 19], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 4 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 19], 6 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 19], 7 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 8 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 19], 9 - mov rdx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 10 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 11 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 12 - mov rdx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 13 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 19], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 19], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 19], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 15 + movzx eax, byte ptr [rdi + rbx + 19] + vmovd xmm3, eax + mov r13, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 19], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 8 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 10 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + r9 + 19], 15 + vpinsrb xmm0, xmm3, byte ptr [rdi + rsi + 19], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov rdx, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 20] - vmovd xmm0, edi - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 1 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 20], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 3 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 20], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 20], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 6 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 7 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 20], 9 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 10 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 20], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 20], 12 - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 13 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 20], 14 - mov rbx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 20], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 20] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 20], 3 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 20], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 20], 6 - mov r10, r13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 20], 7 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 20], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 20], 9 - mov r15, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 20], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 11 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 12 - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 20], 13 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 20], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 20], 15 - mov r14, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + r14 + 21] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 2 - mov rdx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 21], 3 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 4 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 5 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 21], 6 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 21], 7 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 21], 8 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 9 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 10 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 11 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 21], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 21], 14 - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 21], 15 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rbx + 21] - vmovd xmm3, edi + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 20] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 1 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 2 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 21], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 2 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 4 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 6 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 21], 7 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 8 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 21], 10 - mov r10, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 21], 11 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 12 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 21], 13 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 21], 14 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 21], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 3 + mov r11, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 20], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 7 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 20], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 10 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 12 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 20] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 + mov r13, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 3 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 11 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 12 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 15 + mov r15, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r15 + 21] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 21], 4 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 6 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 21], 8 + mov r11, r9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 13 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 21], 14 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 21] + vmovd xmm3, eax + mov r9, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 3 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 13 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 15 vinserti128 ymm11, ymm1, xmm0, 1 vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r14 + 22] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 1 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 2 - mov r15, rdx - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 3 - mov r14, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 22], 4 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 22], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 22], 6 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 22], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 22], 8 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 9 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 10 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 11 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r12 + 22], 12 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 22], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 22], 14 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 22], 15 - movzx edi, byte ptr [rsi + rbx + 22] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 1 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 22], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 22], 3 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 22], 4 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 6 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 7 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 8 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 9 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 22], 11 - mov rbx, r10 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 22], 14 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 22], 15 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 23] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 1 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 23], 2 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 23], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 5 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 6 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 23], 7 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 23], 8 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 23], 9 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 23], 10 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 23], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r12 + 23], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 23], 14 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 23], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rcx + 23] - vmovd xmm3, edi - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 23], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 23], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 4 + movzx eax, byte ptr [rdi + r15 + 22] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 1 + mov rdx, r10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 2 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 8 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 22], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 12 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 22], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 15 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 22] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 1 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 22], 2 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 3 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 22], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 5 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 11 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 15 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 6 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 23], 7 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 8 - mov r11, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 23], 9 - mov r12, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 23], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 23], 11 + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 3 + mov r10, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 5 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 6 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 12 - mov r8, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r8 + 23], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 10 + mov r11, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 15 + movzx eax, byte ptr [rdi + rcx + 23] + vmovd xmm3, eax + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 23], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 23], 4 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 6 + mov rsi, r13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 7 + mov r13, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 9 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 10 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 23], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 12 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 23], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 14 vinserti128 ymm9, ymm1, xmm0, 1 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rsi + rbx + 23], 15 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 23], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 24] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 1 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 24], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 3 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 4 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 6 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 7 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 24], 8 - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 24], 9 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 24], 10 - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 24], 11 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 24], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 24], 15 - movzx edi, byte ptr [rsi + rcx + 24] - vmovd xmm1, edi - mov r10, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 24], 1 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 24], 2 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 24], 3 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 4 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 24], 5 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 24], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 7 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 10 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 24], 11 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 24], 13 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdx + 24], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 24], 15 - mov r8, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + r8 + 25] - vmovd xmm2, edi - mov rdx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 1 - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 2 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r14 + 25], 3 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 25], 4 - mov rdx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 25], 5 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rbx + 25], 6 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 7 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 8 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 9 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 10 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 11 - mov r13, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 25], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 13 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r12 + 24] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 1 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 4 + mov r14, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 24], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 7 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 9 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 24], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 11 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 2 + mov r15, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 24], 3 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 25], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 5 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 11 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 24], 12 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 13 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 24], 14 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 15 + movzx eax, byte ptr [rdi + r12 + 25] + vmovd xmm2, eax + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 25], 1 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 25] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 25], 1 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 25], 3 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 25], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 2 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 6 + mov r10, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 25], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 25], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 12 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 25], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 15 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 7 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 25], 8 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 9 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 25], 11 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 25], 12 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdi + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 25], 3 + mov rdx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 5 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 25], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 9 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 25], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 13 vinserti128 ymm0, ymm1, xmm0, 1 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm3, byte ptr [rsi + r10 + 25], 14 + vpinsrb xmm1, xmm3, byte ptr [rdi + r8 + 25], 14 vpmaxub ymm3, ymm10, ymm0 vpcmpeqb ymm0, ymm0, ymm3 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rsi + rdi + 25], 15 + vpinsrb xmm0, xmm1, byte ptr [rdi + rbx + 25], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 416], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + r8 + 26] - vmovd xmm0, edi - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 26], 1 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 2 - vpinsrb xmm0, xmm0, byte ptr [rsi + r14 + 26], 3 - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 26], 4 - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + rbx + 26], 6 - mov rdx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 7 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 8 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 9 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 10 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r11 + 26], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 26], 12 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 13 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 26], 14 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 26], 15 - mov r14, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + r14 + 26] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 26], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 26], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 4 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 26], 5 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 6 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 26], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 8 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 26], 9 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 26], 10 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 26] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 26], 1 + mov r8, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 5 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 26], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 8 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 10 + mov r12, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 13 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 26], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 15 + mov r11, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + r11 + 26] + vmovd xmm1, eax + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 1 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 2 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 4 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 26], 6 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 26], 7 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 9 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 26], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 14 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 26], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 26], 14 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 26], 15 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 27] - vmovd xmm2, edi - mov r10, r8 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 1 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 27], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 3 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 4 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 5 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 6 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 7 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 8 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 9 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r11 + 27], 11 - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 27], 12 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 27], 13 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 27], 14 - mov r13, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r13 + 27], 15 - movzx edi, byte ptr [rsi + r14 + 27] - vmovd xmm3, edi - mov r14, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 27], 1 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 2 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 3 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 4 - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 27], 5 - mov rdx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 27], 7 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rdx + 27], 8 - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 10 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 11 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r11 + 27], 12 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rbx + 27], 13 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rcx + 27], 14 - vpinsrb xmm3, xmm3, byte ptr [rsi + r9 + 27], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 15 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + r14 + 27] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 27], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 8 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 27], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 27], 11 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 12 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 14 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 27], 15 + movzx eax, byte ptr [rdi + r11 + 27] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 2 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 27], 3 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 27], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 5 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 10 + mov rdx, r13 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - movzx edi, byte ptr [rsi + rax + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 1 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 2 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 3 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 28], 4 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 28], 5 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 6 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 28], 7 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 8 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 28], 9 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdx + 28], 10 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r10 + 28], 11 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 12 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + r15 + 28], 13 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rdi + 28], 14 - vpinsrb xmm0, xmm0, byte ptr [rsi + r13 + 28], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdi + 28] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 1 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 2 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 28], 3 - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 28], 4 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 5 - mov r12, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 28], 6 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 7 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 8 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 28], 10 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rdi + 28], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 28], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 28], 13 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 28], 14 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r11 + 28], 15 + movzx eax, byte ptr [rdi + r14 + 28] + vmovd xmm0, eax + mov r13, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 1 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 3 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 5 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 6 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 9 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 28], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 11 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 28], 12 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 28], 13 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 15 mov rax, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + rax + 29] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 1 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rdi + 29], 3 - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 29], 4 - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 29], 5 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r8 + 29], 6 - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 7 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 8 + movzx eax, byte ptr [rdi + rax + 28] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 6 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 8 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 10 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 28], 11 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 13 mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 9 - vpinsrb xmm2, xmm2, byte ptr [rsi + rdx + 29], 10 - vpinsrb xmm2, xmm2, byte ptr [rsi + r10 + 29], 11 - mov r9, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + r9 + 29], 12 - vpinsrb xmm2, xmm2, byte ptr [rsi + r15 + 29], 13 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rcx + 29], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 14 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 15 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 29] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 2 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 29], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 4 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 6 + mov r9, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 7 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 29], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 29], 13 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 29], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 15 + mov r10, qword ptr [rsp + 264] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 29] + vmovd xmm3, eax + mov r12, qword ptr [rsp + 248] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 29], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 2 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 3 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rsi + rax + 29], 15 - mov rdx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rsi + rdx + 29] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 1 - mov r15, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r15 + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 3 - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 29], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 29], 6 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r12 + 29], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 8 - mov r14, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r14 + 29], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 10 - mov r10, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r10 + 29], 11 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + r13 + 29], 12 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rsi + rax + 29], 13 - vpinsrb xmm4, xmm3, byte ptr [rsi + rbx + 29], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 7 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 9 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 12 + mov r15, rdx + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 13 + vpinsrb xmm4, xmm3, byte ptr [rdi + rcx + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm4, byte ptr [rsi + r11 + 29], 15 - mov rbx, r11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rax + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 264] # 8-byte Reload - movzx edi, byte ptr [rsi + r11 + 30] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 1 - movzx edi, byte ptr [rsi + r11 + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 1 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 2 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 3 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 4 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] + vmovd xmm0, eax + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 31], 1 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, r14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 31], 3 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 31], 5 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 31], 7 + mov r14, qword ptr [rsp + 272] # 8-byte Reload + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 11 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 5 - vpinsrb xmm0, xmm0, byte ptr [rsi + r8 + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 31], 6 - mov r11, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 7 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 8 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 10 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 11 - vpinsrb xmm0, xmm0, byte ptr [rsi + r9 + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rsi + r9 + 31], 12 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 31], 13 - mov rax, rcx - vpinsrb xmm0, xmm0, byte ptr [rsi + rcx + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rsi + rcx + 31], 14 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rsi + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rsi + rax + 31], 15 - movzx eax, byte ptr [rsi + rdx + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 31], 14 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + rax + 31], 15 + mov rcx, r10 + movzx eax, byte ptr [rdi + r10 + 30] vmovd xmm1, eax - mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + r8 + 30], 1 - movzx eax, byte ptr [rsi + rdx + 31] + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 30], 1 + movzx eax, byte ptr [rdi + r10 + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rsi + r8 + 31], 1 - vpinsrb xmm1, xmm1, byte ptr [rsi + r15 + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rsi + r15 + 31], 2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 3 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 4 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 5 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rsi + r12 + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rsi + r12 + 31], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 31], 1 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 8 - vpinsrb xmm1, xmm1, byte ptr [rsi + r14 + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rsi + r14 + 31], 9 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 10 - vpinsrb xmm1, xmm1, byte ptr [rsi + r10 + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rsi + r10 + 31], 11 - vpinsrb xmm1, xmm1, byte ptr [rsi + r13 + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rsi + r13 + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, r11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 31], 10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, r15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 31], 12 + mov rax, rdx + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 13 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 14 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 13 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rsi + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rsi + rax + 31], 14 - mov rax, rbx - vpinsrb xmm1, xmm1, byte ptr [rsi + rbx + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rsi + rbx + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -62052,22 +63649,22 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar vinserti128 ymm4, ymm3, xmm0, 1 vperm2i128 ymm0, ymm3, ymm0, 49 # ymm0 = ymm3[2,3],ymm0[2,3] mov rcx, qword ptr [rsp + 376] # 8-byte Reload - vmovdqu ymmword ptr [r11 + 4*rcx + 96], ymm0 - vmovdqu ymmword ptr [r11 + 4*rcx + 64], ymm2 - vmovdqu ymmword ptr [r11 + 4*rcx + 32], ymm4 - vmovdqu ymmword ptr [r11 + 4*rcx], ymm1 + vmovdqu ymmword ptr [r14 + 4*rcx + 96], ymm0 + vmovdqu ymmword ptr [r14 + 4*rcx + 64], ymm2 + vmovdqu ymmword ptr [r14 + 4*rcx + 32], ymm4 + vmovdqu ymmword ptr [r14 + 4*rcx], ymm1 add rcx, 32 mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB10_44 -# %bb.45: - mov r15, qword ptr [rsp + 368] # 8-byte Reload - cmp r15, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14d, dword ptr [rsp + 28] # 4-byte Reload - mov r12, qword ptr [rsp + 536] # 8-byte Reload - jne .LBB10_46 - jmp .LBB10_49 + jne .LBB10_73 +# %bb.74: + mov rcx, qword ptr [rsp + 368] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 280] # 8-byte Reload + mov r13d, dword ptr [rsp + 28] # 4-byte Reload + mov rsi, qword ptr [rsp + 536] # 8-byte Reload + jne .LBB10_75 + jmp .LBB10_78 .Lfunc_end10: .size comparison_greater_equal_arr_scalar_avx2, .Lfunc_end10-comparison_greater_equal_arr_scalar_avx2 # -- End function @@ -62087,8 +63684,6 @@ comparison_greater_equal_arr_scalar_avx2: # @comparison_greater_equal_arr_scalar .zero 32,64 .LCPI11_6: .zero 32,128 -.LCPI11_7: - .zero 32,255 .text .globl comparison_greater_equal_scalar_arr_avx2 .p2align 4, 0x90 @@ -62105,205 +63700,218 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr and rsp, -32 sub rsp, 1280 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 + mov r12, r8 mov r15, rcx cmp edi, 6 - jg .LBB11_26 + jg .LBB11_24 # %bb.1: cmp edi, 3 jle .LBB11_2 -# %bb.10: +# %bb.6: cmp edi, 4 - je .LBB11_99 -# %bb.11: + je .LBB11_113 +# %bb.7: cmp edi, 5 - je .LBB11_114 -# %bb.12: + je .LBB11_131 +# %bb.8: cmp edi, 6 - jne .LBB11_185 -# %bb.13: - mov r14d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jne .LBB11_211 +# %bb.9: + mov r8d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_17 -# %bb.14: - movsxd rax, r9d + je .LBB11_15 +# %bb.10: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB11_13 +# %bb.11: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_15: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] - lea rdx, [rdx + 4] - mov esi, 0 - adc sil, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r15 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB11_12: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r15 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r15 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_15 -# %bb.16: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_12 +.LBB11_13: + sub r12, r14 + je .LBB11_211 +# %bb.14: add r15, 1 -.LBB11_17: - sar r11, 5 - cmp r10, 32 - jl .LBB11_21 -# %bb.18: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill +.LBB11_15: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB11_19 +# %bb.16: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_19: # =>This Inner Loop Header: Depth=1 +.LBB11_17: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r15 # 8-byte Spill - cmp r14d, dword ptr [rdx + 124] + cmp r8d, dword ptr [rdx + 124] setae byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 120] + cmp r8d, dword ptr [rdx + 120] setae byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 116] + cmp r8d, dword ptr [rdx + 116] setae byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 112] + cmp r8d, dword ptr [rdx + 112] setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 108] - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 104] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 100] + cmp r8d, dword ptr [rdx + 108] setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 92] - setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 88] - setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 84] - setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 80] - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 76] + cmp r8d, dword ptr [rdx + 104] + setae byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 100] setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 72] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 68] - setae byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 60] - setae r8b - cmp r14d, dword ptr [rdx + 56] + cmp r8d, dword ptr [rdx + 92] + setae byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 88] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 84] setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 52] + cmp r8d, dword ptr [rdx + 80] setae byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 48] + cmp r8d, dword ptr [rdx + 76] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 72] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 68] + setae byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 60] + setae dil + cmp r8d, dword ptr [rdx + 56] + setae byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setae byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] setae r11b - cmp r14d, dword ptr [rdx + 44] + cmp r8d, dword ptr [rdx + 44] setae r10b - cmp r14d, dword ptr [rdx + 40] + cmp r8d, dword ptr [rdx + 40] setae r9b - cmp r14d, dword ptr [rdx + 36] - setae dil - cmp r14d, dword ptr [rdx + 28] + cmp r8d, dword ptr [rdx + 36] + setae sil + cmp r8d, dword ptr [rdx + 28] setae al - cmp r14d, dword ptr [rdx + 24] + cmp r8d, dword ptr [rdx + 24] setae bl - cmp r14d, dword ptr [rdx + 20] - setae sil - cmp r14d, dword ptr [rdx + 16] + cmp r8d, dword ptr [rdx + 20] setae cl - cmp r14d, dword ptr [rdx + 12] + cmp r8d, dword ptr [rdx + 16] setae r13b - cmp r14d, dword ptr [rdx + 8] + cmp r8d, dword ptr [rdx + 12] setae r12b - cmp r14d, dword ptr [rdx] - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 4] + cmp r8d, dword ptr [rdx + 8] setae r15b - cmp r14d, dword ptr [rdx + 32] + cmp r8d, dword ptr [rdx] setae byte ptr [rsp + 168] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 64] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 96] - setae byte ptr [rsp + 112] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r12b, 2 + cmp r8d, dword ptr [rdx + 4] + setae r14b + cmp r8d, dword ptr [rdx + 32] + setae byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 64] + setae byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil + or al, cl mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 168] # 1-byte Folded Reload + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r15 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 80] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 6 movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax @@ -62324,88 +63932,103 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov byte ptr [r15 + 3], al sub rdx, -128 add r15, 4 - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB11_19 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB11_17 +# %bb.18: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB11_19: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB11_211 # %bb.20: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 176] # 8-byte Reload -.LBB11_21: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 -# %bb.22: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_130 -# %bb.23: - xor r11d, r11d - jmp .LBB11_24 -.LBB11_26: + or rax, 1 + cmp r12, rax + jne .LBB11_149 +# %bb.21: + xor r14d, r14d + jmp .LBB11_22 +.LBB11_24: cmp edi, 8 - jle .LBB11_27 + jle .LBB11_25 # %bb.42: cmp edi, 9 - je .LBB11_149 + je .LBB11_170 # %bb.43: cmp edi, 11 - je .LBB11_164 + je .LBB11_187 # %bb.44: cmp edi, 12 - jne .LBB11_185 + jne .LBB11_211 # %bb.45: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + mov r14, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero sub r9d, eax - je .LBB11_49 + je .LBB11_51 # %bb.46: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB11_49 +# %bb.47: + movsxd rsi, r9d + vmovq xmm0, r14 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_47: # =>This Inner Loop Header: Depth=1 - vucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - mov esi, 0 - adc sil, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, sil +.LBB11_48: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + vucomisd xmm0, qword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + movzx r9d, byte ptr [r15 + rax] xor bl, r9b - mov byte ptr [r15 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB11_47 -# %bb.48: - add r15, 1 + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r15 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_48 .LBB11_49: - sar r11, 5 - cmp r10, 32 - jl .LBB11_53 + sub r12, r8 + je .LBB11_211 # %bb.50: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill + add r15, 1 +.LBB11_51: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB11_55 +# %bb.52: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 160], r14 # 8-byte Spill + vmovq xmm0, r14 + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_51: # =>This Inner Loop Header: Depth=1 +.LBB11_53: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r15 # 8-byte Spill vucomisd xmm0, qword ptr [rdx] - setae byte ptr [rsp + 168] # 1-byte Folded Spill + setae byte ptr [rsp + 152] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 8] setae r9b vucomisd xmm0, qword ptr [rdx + 16] @@ -62413,15 +64036,15 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomisd xmm0, qword ptr [rdx + 24] setae r13b vucomisd xmm0, qword ptr [rdx + 32] - setae byte ptr [rsp + 128] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 40] - setae byte ptr [rsp + 88] # 1-byte Folded Spill + setae byte ptr [rsp + 144] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 48] setae bl vucomisd xmm0, qword ptr [rdx + 56] setae r12b vucomisd xmm0, qword ptr [rdx + 64] - setae byte ptr [rsp + 136] # 1-byte Folded Spill + setae byte ptr [rsp + 88] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 72] setae sil vucomisd xmm0, qword ptr [rdx + 80] @@ -62433,21 +64056,21 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomisd xmm0, qword ptr [rdx + 104] setae r15b vucomisd xmm0, qword ptr [rdx + 112] - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 96] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 120] setae cl vucomisd xmm0, qword ptr [rdx + 128] - setae byte ptr [rsp + 72] # 1-byte Folded Spill + setae byte ptr [rsp + 128] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 136] - setae byte ptr [rsp + 112] # 1-byte Folded Spill + setae byte ptr [rsp + 104] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 144] - setae byte ptr [rsp + 120] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 152] - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 160] - setae byte ptr [rsp + 80] # 1-byte Folded Spill + setae byte ptr [rsp + 136] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 168] - setae byte ptr [rsp + 96] # 1-byte Folded Spill + setae byte ptr [rsp + 56] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 176] setae byte ptr [rsp + 64] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 184] @@ -62455,11 +64078,11 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomisd xmm0, qword ptr [rdx + 192] setae byte ptr [rsp + 32] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 200] - setae byte ptr [rsp + 48] # 1-byte Folded Spill + setae byte ptr [rsp + 72] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 208] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - vucomisd xmm0, qword ptr [rdx + 216] setae byte ptr [rsp + 40] # 1-byte Folded Spill + vucomisd xmm0, qword ptr [rdx + 216] + setae byte ptr [rsp + 48] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 224] setae byte ptr [rsp + 320] # 1-byte Folded Spill vucomisd xmm0, qword ptr [rdx + 232] @@ -62469,55 +64092,55 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomisd xmm0, qword ptr [rdx + 248] setae al add r9b, r9b - add r9b, byte ptr [rsp + 168] # 1-byte Folded Reload + add r9b, byte ptr [rsp + 152] # 1-byte Folded Reload shl bl, 6 shl r12b, 7 or r12b, bl shl r11b, 2 or r11b, r9b add sil, sil - add sil, byte ptr [rsp + 136] # 1-byte Folded Reload + add sil, byte ptr [rsp + 88] # 1-byte Folded Reload shl r13b, 3 or r13b, r11b shl dil, 2 or dil, sil - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 4 or bl, r13b mov esi, ebx shl r8b, 3 or r8b, dil - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 5 or bl, sil shl r10b, 4 or r10b, r8b shl r15b, 5 or r15b, r10b - movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 96] # 1-byte Folded Reload shl sil, 6 shl cl, 7 or cl, sil or r12b, bl or cl, r15b mov r15, qword ptr [rsp + 272] # 8-byte Reload - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 72] # 1-byte Folded Reload + add bl, byte ptr [rsp + 128] # 1-byte Folded Reload mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload shl bl, 2 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 or bl, sil mov byte ptr [r15], r12b @@ -62527,15 +64150,15 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr or r14b, sil mov byte ptr [r15 + 1], cl or r14b, bl - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 32] # 1-byte Folded Reload mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload shl cl, 2 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload shl cl, 3 or cl, bl mov ebx, ecx @@ -62543,473 +64166,292 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr shl cl, 4 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl cl, 5 - or cl, bl - movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload - shl bl, 6 - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r15 + 2], r14b - mov byte ptr [r15 + 3], al - add rdx, 256 - add r15, 4 - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB11_51 -# %bb.52: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB11_53: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 -# %bb.54: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_179 -# %bb.55: - xor r11d, r11d - jmp .LBB11_181 -.LBB11_2: - cmp edi, 2 - je .LBB11_56 -# %bb.3: - cmp edi, 3 - jne .LBB11_185 -# %bb.4: - mov r11b, byte ptr [rsi] - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB11_8 -# %bb.5: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB11_6: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx] - lea rdx, [rdx + 1] - setge bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r15 + rsi] - xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_6 -# %bb.7: - add r15, 1 -.LBB11_8: - sar r14, 5 - cmp r10, 32 - jl .LBB11_9 -# %bb.81: - cmp r14, 32 - mov dword ptr [rsp + 28], r11d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 352], r14 # 8-byte Spill - jb .LBB11_82 -# %bb.83: - mov rax, r14 - shl rax, 5 - add rax, rdx - cmp r15, rax - jae .LBB11_85 -# %bb.84: - lea rax, [r15 + 4*r14] - cmp rdx, rax - jae .LBB11_85 -.LBB11_82: - xor eax, eax - mov qword ptr [rsp + 416], rax # 8-byte Spill - mov r13, r15 -.LBB11_88: - sub r14, qword ptr [rsp + 416] # 8-byte Folded Reload - mov qword ptr [rsp + 176], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB11_89: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx + 31] - setge byte ptr [rsp + 272] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 30] - setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 29] - setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 28] - setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 27] - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 26] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 25] - setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 23] - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 22] - setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 21] - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 20] - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 19] - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 18] - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 17] - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 15] - setge r14b - cmp r11b, byte ptr [rdx + 14] - setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 13] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11b, byte ptr [rdx + 12] - setge r12b - cmp r11b, byte ptr [rdx + 11] - setge r15b - cmp r11b, byte ptr [rdx + 10] - setge r11b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 9] - setge r10b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 7] - setge dil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 6] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 5] - setge r9b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 4] - setge r8b - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 3] - setge sil - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 2] - setge cl - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx] - setge byte ptr [rsp + 152] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 28] # 4-byte Reload - cmp al, byte ptr [rdx + 1] - setge al - mov rbx, r13 - mov r13d, dword ptr [rsp + 28] # 4-byte Reload - cmp r13b, byte ptr [rdx + 8] - mov r13, rbx - setge byte ptr [rsp + 168] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp bl, byte ptr [rdx + 16] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 28] # 4-byte Reload - cmp bl, byte ptr [rdx + 24] - setge byte ptr [rsp + 96] # 1-byte Folded Spill - add al, al - add al, byte ptr [rsp + 152] # 1-byte Folded Reload - shl cl, 2 - or cl, al - shl sil, 3 - or sil, cl - shl r8b, 4 - or r8b, sil - shl r9b, 5 - or r9b, r8b - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 6 - shl dil, 7 - or dil, al - or dil, r9b - mov byte ptr [r13], dil - add r10b, r10b - add r10b, byte ptr [rsp + 168] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r10b - shl r15b, 3 - or r15b, r11b - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - shl r12b, 4 - or r12b, r15b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 5 - or al, r12b - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl cl, 6 - shl r14b, 7 - or r14b, cl - or r14b, al - mov byte ptr [r13 + 1], r14b - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r13 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 96] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 5 + or cl, bl + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r13 + 3], al - add rdx, 32 - add r13, 4 - add qword ptr [rsp + 176], -1 # 8-byte Folded Spill - jne .LBB11_89 -# %bb.90: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14, qword ptr [rsp + 352] # 8-byte Reload - jmp .LBB11_91 -.LBB11_27: + mov byte ptr [r15 + 2], r14b + mov byte ptr [r15 + 3], al + add rdx, 256 + add r15, 4 + add qword ptr [rsp + 168], -1 # 8-byte Folded Spill + jne .LBB11_53 +# %bb.54: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14, qword ptr [rsp + 160] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB11_55: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB11_211 +# %bb.56: + vmovq xmm0, r14 + or rax, 1 + cmp r12, rax + jne .LBB11_204 +# %bb.57: + xor r11d, r11d + jmp .LBB11_206 +.LBB11_2: + cmp edi, 2 + je .LBB11_58 +# %bb.3: + cmp edi, 3 + jne .LBB11_211 +# %bb.4: + mov r14b, byte ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB11_5 +# %bb.87: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB11_88 +# %bb.93: + movsxd rsi, r9d + mov r11, r8 + .p2align 4, 0x90 +.LBB11_94: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r14b, byte ptr [rdx] + setge dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + movzx r9d, byte ptr [r15 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r15 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB11_94 +# %bb.89: + sub r12, r8 + jne .LBB11_90 + jmp .LBB11_211 +.LBB11_25: cmp edi, 7 - je .LBB11_132 -# %bb.28: + je .LBB11_151 +# %bb.26: cmp edi, 8 - jne .LBB11_185 -# %bb.29: - mov r14, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jne .LBB11_211 +# %bb.27: + mov r8, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax je .LBB11_33 -# %bb.30: - movsxd rax, r9d +# %bb.28: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB11_31 +# %bb.29: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_31: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] - lea rdx, [rdx + 8] - mov esi, 0 - adc sil, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r15 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB11_30: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r15 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r15 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_31 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_30 +.LBB11_31: + sub r12, r14 + je .LBB11_211 # %bb.32: add r15, 1 .LBB11_33: - sar r11, 5 - cmp r10, 32 + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 jl .LBB11_37 # %bb.34: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 .LBB11_35: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r15 # 8-byte Spill - cmp r14, qword ptr [rdx + 248] + cmp r8, qword ptr [rdx + 248] setae byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 240] + cmp r8, qword ptr [rdx + 240] setae byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 232] + cmp r8, qword ptr [rdx + 232] setae byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 224] + cmp r8, qword ptr [rdx + 224] setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 216] - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 208] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 200] + cmp r8, qword ptr [rdx + 216] setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 184] - setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 176] - setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 168] - setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 160] - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 152] + cmp r8, qword ptr [rdx + 208] + setae byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 200] setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 144] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 136] - setae byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 120] - setae r8b - cmp r14, qword ptr [rdx + 112] + cmp r8, qword ptr [rdx + 184] + setae byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 176] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 168] setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 104] + cmp r8, qword ptr [rdx + 160] setae byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 96] + cmp r8, qword ptr [rdx + 152] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 144] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 136] + setae byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 120] + setae dil + cmp r8, qword ptr [rdx + 112] + setae byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 104] + setae byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 96] setae r11b - cmp r14, qword ptr [rdx + 88] + cmp r8, qword ptr [rdx + 88] setae r10b - cmp r14, qword ptr [rdx + 80] + cmp r8, qword ptr [rdx + 80] setae r9b - cmp r14, qword ptr [rdx + 72] - setae dil - cmp r14, qword ptr [rdx + 56] + cmp r8, qword ptr [rdx + 72] + setae sil + cmp r8, qword ptr [rdx + 56] setae al - cmp r14, qword ptr [rdx + 48] + cmp r8, qword ptr [rdx + 48] setae bl - cmp r14, qword ptr [rdx + 40] - setae sil - cmp r14, qword ptr [rdx + 32] + cmp r8, qword ptr [rdx + 40] setae cl - cmp r14, qword ptr [rdx + 24] + cmp r8, qword ptr [rdx + 32] setae r13b - cmp r14, qword ptr [rdx + 16] + cmp r8, qword ptr [rdx + 24] setae r12b - cmp r14, qword ptr [rdx] - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 8] + cmp r8, qword ptr [rdx + 16] setae r15b - cmp r14, qword ptr [rdx + 64] + cmp r8, qword ptr [rdx] setae byte ptr [rsp + 168] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 128] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 192] - setae byte ptr [rsp + 112] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r12b, 2 + cmp r8, qword ptr [rdx + 8] + setae r14b + cmp r8, qword ptr [rdx + 64] + setae byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 128] + setae byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil + or al, cl mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 168] # 1-byte Folded Reload + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r15 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 80] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 6 movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax @@ -63030,207 +64472,219 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov byte ptr [r15 + 3], al add rdx, 256 add r15, 4 - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill jne .LBB11_35 # %bb.36: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 176] # 8-byte Reload + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload .LBB11_37: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB11_211 # %bb.38: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_147 + or rax, 1 + cmp r12, rax + jne .LBB11_168 # %bb.39: - xor r11d, r11d + xor r14d, r14d jmp .LBB11_40 -.LBB11_99: - movzx r14d, word ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 +.LBB11_113: + movzx r8d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_103 -# %bb.100: - movsxd rax, r9d + je .LBB11_119 +# %bb.114: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB11_117 +# %bb.115: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_101: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] - mov esi, 0 - adc sil, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r15 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB11_116: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r8w, word ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r15 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r15 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_101 -# %bb.102: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_116 +.LBB11_117: + sub r12, r14 + je .LBB11_211 +# %bb.118: add r15, 1 -.LBB11_103: - sar r11, 5 - cmp r10, 32 - jl .LBB11_107 -# %bb.104: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill +.LBB11_119: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB11_123 +# %bb.120: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_105: # =>This Inner Loop Header: Depth=1 +.LBB11_121: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r15 # 8-byte Spill - cmp r14w, word ptr [rdx + 62] + cmp r8w, word ptr [rdx + 62] setae byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 60] + cmp r8w, word ptr [rdx + 60] setae byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 58] + cmp r8w, word ptr [rdx + 58] setae byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 56] + cmp r8w, word ptr [rdx + 56] setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 54] - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 52] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 50] + cmp r8w, word ptr [rdx + 54] setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 46] - setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 44] - setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 42] - setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 40] - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 38] + cmp r8w, word ptr [rdx + 52] + setae byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 50] setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 36] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 34] - setae byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 30] - setae r8b - cmp r14w, word ptr [rdx + 28] + cmp r8w, word ptr [rdx + 46] + setae byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 44] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 42] setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 26] + cmp r8w, word ptr [rdx + 40] setae byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 24] + cmp r8w, word ptr [rdx + 38] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 36] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 34] + setae byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 30] + setae dil + cmp r8w, word ptr [rdx + 28] + setae byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 26] + setae byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 24] setae r11b - cmp r14w, word ptr [rdx + 22] + cmp r8w, word ptr [rdx + 22] setae r10b - cmp r14w, word ptr [rdx + 20] + cmp r8w, word ptr [rdx + 20] setae r9b - cmp r14w, word ptr [rdx + 18] - setae dil - cmp r14w, word ptr [rdx + 14] + cmp r8w, word ptr [rdx + 18] + setae sil + cmp r8w, word ptr [rdx + 14] setae al - cmp r14w, word ptr [rdx + 12] + cmp r8w, word ptr [rdx + 12] setae bl - cmp r14w, word ptr [rdx + 10] - setae sil - cmp r14w, word ptr [rdx + 8] + cmp r8w, word ptr [rdx + 10] setae cl - cmp r14w, word ptr [rdx + 6] + cmp r8w, word ptr [rdx + 8] setae r13b - cmp r14w, word ptr [rdx + 4] + cmp r8w, word ptr [rdx + 6] setae r12b - cmp r14w, word ptr [rdx] - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 2] + cmp r8w, word ptr [rdx + 4] setae r15b - cmp r14w, word ptr [rdx + 16] + cmp r8w, word ptr [rdx] setae byte ptr [rsp + 168] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 32] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 48] - setae byte ptr [rsp + 112] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r12b, 2 + cmp r8w, word ptr [rdx + 2] + setae r14b + cmp r8w, word ptr [rdx + 16] + setae byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 32] + setae byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 48] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil + or al, cl mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 168] # 1-byte Folded Reload + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r15 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 6 movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax @@ -63251,207 +64705,219 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov byte ptr [r15 + 3], al add rdx, 64 add r15, 4 - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB11_105 -# %bb.106: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 176] # 8-byte Reload -.LBB11_107: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 -# %bb.108: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_112 -# %bb.109: - xor r11d, r11d - jmp .LBB11_110 -.LBB11_114: - movzx r14d, word ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB11_121 +# %bb.122: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB11_123: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB11_211 +# %bb.124: + or rax, 1 + cmp r12, rax + jne .LBB11_129 +# %bb.125: + xor r14d, r14d + jmp .LBB11_126 +.LBB11_131: + movzx r8d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_118 -# %bb.115: - movsxd rax, r9d + je .LBB11_137 +# %bb.132: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB11_135 +# %bb.133: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_116: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] +.LBB11_134: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r8w, word ptr [rcx] setge bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r15 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r15 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_116 -# %bb.117: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_134 +.LBB11_135: + sub r12, r14 + je .LBB11_211 +# %bb.136: add r15, 1 -.LBB11_118: - sar r11, 5 - cmp r10, 32 - jl .LBB11_122 -# %bb.119: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill +.LBB11_137: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB11_141 +# %bb.138: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_120: # =>This Inner Loop Header: Depth=1 +.LBB11_139: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r15 # 8-byte Spill - cmp r14w, word ptr [rdx + 62] + cmp r8w, word ptr [rdx + 62] setge byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 60] + cmp r8w, word ptr [rdx + 60] setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 58] + cmp r8w, word ptr [rdx + 58] setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 56] + cmp r8w, word ptr [rdx + 56] setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 54] - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 52] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 50] + cmp r8w, word ptr [rdx + 54] setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 46] - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 44] - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 42] - setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 40] - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 38] + cmp r8w, word ptr [rdx + 52] + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 50] setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 36] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 34] - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 30] - setge r8b - cmp r14w, word ptr [rdx + 28] + cmp r8w, word ptr [rdx + 46] + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 44] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 42] setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 26] + cmp r8w, word ptr [rdx + 40] setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 24] + cmp r8w, word ptr [rdx + 38] + setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 36] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 34] + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 30] + setge dil + cmp r8w, word ptr [rdx + 28] + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 26] + setge byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 24] setge r11b - cmp r14w, word ptr [rdx + 22] + cmp r8w, word ptr [rdx + 22] setge r10b - cmp r14w, word ptr [rdx + 20] + cmp r8w, word ptr [rdx + 20] setge r9b - cmp r14w, word ptr [rdx + 18] - setge dil - cmp r14w, word ptr [rdx + 14] + cmp r8w, word ptr [rdx + 18] + setge sil + cmp r8w, word ptr [rdx + 14] setge al - cmp r14w, word ptr [rdx + 12] + cmp r8w, word ptr [rdx + 12] setge bl - cmp r14w, word ptr [rdx + 10] - setge sil - cmp r14w, word ptr [rdx + 8] + cmp r8w, word ptr [rdx + 10] setge cl - cmp r14w, word ptr [rdx + 6] + cmp r8w, word ptr [rdx + 8] setge r13b - cmp r14w, word ptr [rdx + 4] + cmp r8w, word ptr [rdx + 6] setge r12b - cmp r14w, word ptr [rdx] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 2] + cmp r8w, word ptr [rdx + 4] setge r15b - cmp r14w, word ptr [rdx + 16] + cmp r8w, word ptr [rdx] setge byte ptr [rsp + 168] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 32] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 48] - setge byte ptr [rsp + 112] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r12b, 2 + cmp r8w, word ptr [rdx + 2] + setge r14b + cmp r8w, word ptr [rdx + 16] + setge byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 32] + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 48] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil + or al, cl mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 168] # 1-byte Folded Reload + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r15 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 80] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 6 movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax @@ -63472,207 +64938,219 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov byte ptr [r15 + 3], al add rdx, 64 add r15, 4 - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB11_120 -# %bb.121: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 176] # 8-byte Reload -.LBB11_122: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 -# %bb.123: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_128 -# %bb.124: + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB11_139 +# %bb.140: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB11_141: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB11_211 +# %bb.142: + or rax, 1 + cmp r12, rax + jne .LBB11_147 +# %bb.143: xor edi, edi - jmp .LBB11_125 -.LBB11_149: - mov r14, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jmp .LBB11_144 +.LBB11_170: + mov r8, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_153 -# %bb.150: - movsxd rax, r9d + je .LBB11_176 +# %bb.171: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB11_174 +# %bb.172: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_151: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] - lea rdx, [rdx + 8] +.LBB11_173: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] setge bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r15 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r15 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_151 -# %bb.152: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_173 +.LBB11_174: + sub r12, r14 + je .LBB11_211 +# %bb.175: add r15, 1 -.LBB11_153: - sar r11, 5 - cmp r10, 32 - jl .LBB11_157 -# %bb.154: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill +.LBB11_176: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB11_180 +# %bb.177: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_155: # =>This Inner Loop Header: Depth=1 +.LBB11_178: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r15 # 8-byte Spill - cmp r14, qword ptr [rdx + 248] + cmp r8, qword ptr [rdx + 248] setge byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 240] + cmp r8, qword ptr [rdx + 240] setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 232] + cmp r8, qword ptr [rdx + 232] setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 224] + cmp r8, qword ptr [rdx + 224] setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 216] - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 208] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 200] + cmp r8, qword ptr [rdx + 216] setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 184] - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 176] - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 168] - setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 160] - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 152] + cmp r8, qword ptr [rdx + 208] + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 200] setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 144] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 136] - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 120] - setge r8b - cmp r14, qword ptr [rdx + 112] + cmp r8, qword ptr [rdx + 184] + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 176] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 168] setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 104] + cmp r8, qword ptr [rdx + 160] setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 96] + cmp r8, qword ptr [rdx + 152] + setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 144] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 136] + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 120] + setge dil + cmp r8, qword ptr [rdx + 112] + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 104] + setge byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 96] setge r11b - cmp r14, qword ptr [rdx + 88] + cmp r8, qword ptr [rdx + 88] setge r10b - cmp r14, qword ptr [rdx + 80] + cmp r8, qword ptr [rdx + 80] setge r9b - cmp r14, qword ptr [rdx + 72] - setge dil - cmp r14, qword ptr [rdx + 56] + cmp r8, qword ptr [rdx + 72] + setge sil + cmp r8, qword ptr [rdx + 56] setge al - cmp r14, qword ptr [rdx + 48] + cmp r8, qword ptr [rdx + 48] setge bl - cmp r14, qword ptr [rdx + 40] - setge sil - cmp r14, qword ptr [rdx + 32] + cmp r8, qword ptr [rdx + 40] setge cl - cmp r14, qword ptr [rdx + 24] + cmp r8, qword ptr [rdx + 32] setge r13b - cmp r14, qword ptr [rdx + 16] + cmp r8, qword ptr [rdx + 24] setge r12b - cmp r14, qword ptr [rdx] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 8] + cmp r8, qword ptr [rdx + 16] setge r15b - cmp r14, qword ptr [rdx + 64] + cmp r8, qword ptr [rdx] setge byte ptr [rsp + 168] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 128] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 192] - setge byte ptr [rsp + 112] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r12b, 2 + cmp r8, qword ptr [rdx + 8] + setge r14b + cmp r8, qword ptr [rdx + 64] + setge byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 128] + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil + or al, cl mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 168] # 1-byte Folded Reload + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r15 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 80] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 6 movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax @@ -63693,76 +65171,91 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov byte ptr [r15 + 3], al add rdx, 256 add r15, 4 - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB11_155 -# %bb.156: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 176] # 8-byte Reload -.LBB11_157: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 -# %bb.158: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_162 -# %bb.159: + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB11_178 +# %bb.179: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB11_180: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB11_211 +# %bb.181: + or rax, 1 + cmp r12, rax + jne .LBB11_185 +# %bb.182: xor edi, edi - jmp .LBB11_160 -.LBB11_164: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jmp .LBB11_183 +.LBB11_187: + mov r14d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - vmovss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB11_168 -# %bb.165: - movsxd rax, r9d + je .LBB11_193 +# %bb.188: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB11_191 +# %bb.189: + movsxd rsi, r9d + vmovd xmm0, r14d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_166: # =>This Inner Loop Header: Depth=1 - vucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - mov esi, 0 - adc sil, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, sil +.LBB11_190: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + vucomiss xmm0, dword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + movzx r9d, byte ptr [r15 + rax] xor bl, r9b - mov byte ptr [r15 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB11_166 -# %bb.167: + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r15 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_190 +.LBB11_191: + sub r12, r8 + je .LBB11_211 +# %bb.192: add r15, 1 -.LBB11_168: - sar r11, 5 - cmp r10, 32 - jl .LBB11_172 -# %bb.169: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill +.LBB11_193: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB11_197 +# %bb.194: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov dword ptr [rsp + 160], r14d # 4-byte Spill + vmovd xmm0, r14d + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_170: # =>This Inner Loop Header: Depth=1 +.LBB11_195: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 272], r15 # 8-byte Spill vucomiss xmm0, dword ptr [rdx] - setae byte ptr [rsp + 168] # 1-byte Folded Spill + setae byte ptr [rsp + 152] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 4] setae r9b vucomiss xmm0, dword ptr [rdx + 8] @@ -63770,15 +65263,15 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomiss xmm0, dword ptr [rdx + 12] setae r13b vucomiss xmm0, dword ptr [rdx + 16] - setae byte ptr [rsp + 128] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 20] - setae byte ptr [rsp + 88] # 1-byte Folded Spill + setae byte ptr [rsp + 144] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 24] setae bl vucomiss xmm0, dword ptr [rdx + 28] setae r12b vucomiss xmm0, dword ptr [rdx + 32] - setae byte ptr [rsp + 136] # 1-byte Folded Spill + setae byte ptr [rsp + 88] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 36] setae sil vucomiss xmm0, dword ptr [rdx + 40] @@ -63790,21 +65283,21 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomiss xmm0, dword ptr [rdx + 52] setae r15b vucomiss xmm0, dword ptr [rdx + 56] - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 96] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 60] setae cl vucomiss xmm0, dword ptr [rdx + 64] - setae byte ptr [rsp + 72] # 1-byte Folded Spill + setae byte ptr [rsp + 128] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 68] - setae byte ptr [rsp + 112] # 1-byte Folded Spill + setae byte ptr [rsp + 104] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 72] - setae byte ptr [rsp + 120] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 76] - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 80] - setae byte ptr [rsp + 80] # 1-byte Folded Spill + setae byte ptr [rsp + 136] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 84] - setae byte ptr [rsp + 96] # 1-byte Folded Spill + setae byte ptr [rsp + 56] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 88] setae byte ptr [rsp + 64] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 92] @@ -63812,11 +65305,11 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomiss xmm0, dword ptr [rdx + 96] setae byte ptr [rsp + 32] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 100] - setae byte ptr [rsp + 48] # 1-byte Folded Spill + setae byte ptr [rsp + 72] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 104] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - vucomiss xmm0, dword ptr [rdx + 108] setae byte ptr [rsp + 40] # 1-byte Folded Spill + vucomiss xmm0, dword ptr [rdx + 108] + setae byte ptr [rsp + 48] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 112] setae byte ptr [rsp + 320] # 1-byte Folded Spill vucomiss xmm0, dword ptr [rdx + 116] @@ -63826,55 +65319,55 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vucomiss xmm0, dword ptr [rdx + 124] setae al add r9b, r9b - add r9b, byte ptr [rsp + 168] # 1-byte Folded Reload + add r9b, byte ptr [rsp + 152] # 1-byte Folded Reload shl bl, 6 shl r12b, 7 or r12b, bl shl r11b, 2 or r11b, r9b add sil, sil - add sil, byte ptr [rsp + 136] # 1-byte Folded Reload + add sil, byte ptr [rsp + 88] # 1-byte Folded Reload shl r13b, 3 or r13b, r11b shl dil, 2 or dil, sil - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 4 or bl, r13b mov esi, ebx shl r8b, 3 or r8b, dil - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload shl bl, 5 or bl, sil shl r10b, 4 or r10b, r8b shl r15b, 5 or r15b, r10b - movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 96] # 1-byte Folded Reload shl sil, 6 shl cl, 7 or cl, sil or r12b, bl or cl, r15b mov r15, qword ptr [rsp + 272] # 8-byte Reload - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 72] # 1-byte Folded Reload + add bl, byte ptr [rsp + 128] # 1-byte Folded Reload mov esi, ebx - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload shl bl, 2 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload shl bl, 3 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload shl bl, 4 or bl, sil mov esi, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 or bl, sil mov byte ptr [r15], r12b @@ -63884,15 +65377,15 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr or r14b, sil mov byte ptr [r15 + 1], cl or r14b, bl - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 32] # 1-byte Folded Reload mov ebx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload shl cl, 2 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload shl cl, 3 or cl, bl mov ebx, ecx @@ -63912,133 +65405,619 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov byte ptr [r15 + 3], al add rdx, 128 add r15, 4 - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB11_170 -# %bb.171: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB11_172: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 -# %bb.173: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_177 -# %bb.174: + add qword ptr [rsp + 168], -1 # 8-byte Folded Spill + jne .LBB11_195 +# %bb.196: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14d, dword ptr [rsp + 160] # 4-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB11_197: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB11_211 +# %bb.198: + vmovd xmm0, r14d + or rax, 1 + cmp r12, rax + jne .LBB11_202 +# %bb.199: xor r11d, r11d - jmp .LBB11_175 -.LBB11_56: - mov r11b, byte ptr [rsi] - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + jmp .LBB11_200 +.LBB11_58: + mov r14b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_60 -# %bb.57: - movsxd rax, r9d + je .LBB11_59 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB11_61 +# %bb.66: + movsxd rsi, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB11_58: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx] - lea rdx, [rdx + 1] - mov esi, 0 - adc sil, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB11_67: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r14b, byte ptr [rdx] + mov edx, 0 + adc dl, -1 + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + movzx r9d, byte ptr [r15 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r15 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB11_67 +# %bb.62: + sub r12, r8 + jne .LBB11_63 + jmp .LBB11_211 +.LBB11_151: + mov r8d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB11_157 +# %bb.152: + mov r14d, 8 + sub r14d, r9d + cmp r14, r12 + cmovg r14, r12 + test r14, r14 + jle .LBB11_155 +# %bb.153: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx + .p2align 4, 0x90 +.LBB11_154: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] + setge bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi sar rdi, 3 movzx r9d, byte ptr [r15 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, sil xor bl, r9b - mov byte ptr [r15 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB11_58 -# %bb.59: + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_154 +.LBB11_155: + sub r12, r14 + je .LBB11_211 +# %bb.156: add r15, 1 -.LBB11_60: - sar r14, 5 - cmp r10, 32 - jl .LBB11_61 -# %bb.62: - cmp r14, 32 - mov dword ptr [rsp + 28], r11d # 4-byte Spill - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 352], r14 # 8-byte Spill - jb .LBB11_63 -# %bb.64: - mov rax, r14 +.LBB11_157: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB11_161 +# %bb.158: + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB11_159: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 272], r15 # 8-byte Spill + cmp r8d, dword ptr [rdx + 124] + setge byte ptr [rsp + 28] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 120] + setge byte ptr [rsp + 288] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 116] + setge byte ptr [rsp + 320] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 112] + setge byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 108] + setge byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 104] + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 100] + setge byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 92] + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 88] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 84] + setge byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 80] + setge byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 76] + setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 72] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 68] + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 60] + setge dil + cmp r8d, dword ptr [rdx + 56] + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setge byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] + setge r11b + cmp r8d, dword ptr [rdx + 44] + setge r10b + cmp r8d, dword ptr [rdx + 40] + setge r9b + cmp r8d, dword ptr [rdx + 36] + setge sil + cmp r8d, dword ptr [rdx + 28] + setge al + cmp r8d, dword ptr [rdx + 24] + setge bl + cmp r8d, dword ptr [rdx + 20] + setge cl + cmp r8d, dword ptr [rdx + 16] + setge r13b + cmp r8d, dword ptr [rdx + 12] + setge r12b + cmp r8d, dword ptr [rdx + 8] + setge r15b + cmp r8d, dword ptr [rdx] + setge byte ptr [rsp + 168] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 4] + setge r14b + cmp r8d, dword ptr [rdx + 32] + setge byte ptr [rsp + 152] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 64] + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 168] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 + or r12b, r15b + mov r15, qword ptr [rsp + 272] # 8-byte Reload + shl r13b, 4 + or r13b, r12b + shl cl, 5 + or cl, r13b + shl bl, 6 + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r15], al + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload + shl r9b, 2 + or r9b, sil + shl r10b, 3 + or r10b, r9b + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 5 + or al, r11b + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 6 + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r15 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 80] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r15 + 2], al + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 104] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r15 + 3], al + sub rdx, -128 + add r15, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB11_159 +# %bb.160: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB11_161: + shl rax, 5 + mov r9, r12 + sub r9, rax + jle .LBB11_211 +# %bb.162: + or rax, 1 + cmp r12, rax + jne .LBB11_166 +# %bb.163: + xor edi, edi + jmp .LBB11_164 +.LBB11_5: + mov rdi, rdx + jmp .LBB11_91 +.LBB11_59: + mov rdi, rdx + jmp .LBB11_64 +.LBB11_88: + mov rdi, rdx + sub r12, r8 + je .LBB11_211 +.LBB11_90: + add r15, 1 +.LBB11_91: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB11_92 +# %bb.95: + cmp rcx, 32 + mov dword ptr [rsp + 28], r14d # 4-byte Spill + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 352], rcx # 8-byte Spill + jb .LBB11_96 +# %bb.97: + mov rax, rcx shl rax, 5 - add rax, rdx + add rax, rdi cmp r15, rax - jae .LBB11_66 -# %bb.65: - lea rax, [r15 + 4*r14] - cmp rdx, rax - jae .LBB11_66 + jae .LBB11_99 +# %bb.98: + lea rax, [r15 + 4*rcx] + cmp rdi, rax + jae .LBB11_99 +.LBB11_96: + xor eax, eax + mov qword ptr [rsp + 416], rax # 8-byte Spill + mov r13, r15 +.LBB11_102: + sub rcx, qword ptr [rsp + 416] # 8-byte Folded Reload + mov qword ptr [rsp + 160], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB11_103: # =>This Inner Loop Header: Depth=1 + cmp r14b, byte ptr [rdi + 31] + setge byte ptr [rsp + 272] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 30] + setge byte ptr [rsp + 288] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 29] + setge byte ptr [rsp + 320] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 28] + setge byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 27] + setge byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 26] + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 25] + setge byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 23] + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 22] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 21] + setge byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 20] + setge byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 19] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 18] + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 17] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 15] + setge r11b + cmp r14b, byte ptr [rdi + 14] + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 13] + setge byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 12] + setge r12b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 11] + setge r15b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 10] + setge r14b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 9] + setge r10b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 7] + setge sil + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 6] + setge byte ptr [rsp + 152] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 5] + setge r9b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 4] + setge r8b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 3] + setge dl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 2] + setge cl + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi] + setge byte ptr [rsp + 168] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 1] + setge al + mov rbx, r13 + mov r13d, dword ptr [rsp + 28] # 4-byte Reload + cmp r13b, byte ptr [rdi + 8] + mov r13, rbx + setge byte ptr [rsp + 80] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp bl, byte ptr [rdi + 16] + setge byte ptr [rsp + 128] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 28] # 4-byte Reload + cmp bl, byte ptr [rdi + 24] + setge bl + add al, al + add al, byte ptr [rsp + 168] # 1-byte Folded Reload + shl cl, 2 + or cl, al + shl dl, 3 + or dl, cl + shl r8b, 4 + or r8b, dl + shl r9b, 5 + or r9b, r8b + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 6 + shl sil, 7 + or sil, al + or sil, r9b + mov byte ptr [r13], sil + add r10b, r10b + add r10b, byte ptr [rsp + 80] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r15b, 3 + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 5 + or al, r12b + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 6 + shl r11b, 7 + or r11b, cl + or r11b, al + mov byte ptr [r13 + 1], r11b + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 128] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 2], al + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, al + or al, bl + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 3], al + add rdi, 32 + add r13, 4 + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB11_103 +# %bb.104: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 352] # 8-byte Reload + jmp .LBB11_105 +.LBB11_92: + mov r13, r15 +.LBB11_105: + shl rcx, 5 + mov r8, r12 + sub r8, rcx + jle .LBB11_211 +# %bb.106: + or rcx, 1 + cmp r12, rcx + jne .LBB11_108 +# %bb.107: + xor r9d, r9d + jmp .LBB11_111 +.LBB11_61: + mov rdi, rdx + sub r12, r8 + je .LBB11_211 .LBB11_63: + add r15, 1 +.LBB11_64: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB11_65 +# %bb.68: + cmp rcx, 32 + mov dword ptr [rsp + 28], r14d # 4-byte Spill + mov qword ptr [rsp + 280], r12 # 8-byte Spill + mov qword ptr [rsp + 352], rcx # 8-byte Spill + jb .LBB11_69 +# %bb.70: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r15, rax + jae .LBB11_72 +# %bb.71: + lea rax, [r15 + 4*rcx] + cmp rdi, rax + jae .LBB11_72 +.LBB11_69: xor eax, eax mov qword ptr [rsp + 384], rax # 8-byte Spill - mov rdi, rdx mov r13, r15 -.LBB11_69: - sub r14, qword ptr [rsp + 384] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r14 # 8-byte Spill +.LBB11_75: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 160], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB11_70: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdi + 31] +.LBB11_76: # =>This Inner Loop Header: Depth=1 + cmp r14b, byte ptr [rdi + 31] setae byte ptr [rsp + 272] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 30] + cmp r14b, byte ptr [rdi + 30] setae byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 29] + cmp r14b, byte ptr [rdi + 29] setae byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 28] + cmp r14b, byte ptr [rdi + 28] setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 27] - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 26] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 25] + cmp r14b, byte ptr [rdi + 27] setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 23] + cmp r14b, byte ptr [rdi + 26] + setae byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 25] + setae byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 23] setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 22] - setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 21] - setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 20] - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 19] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 18] - setae byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 17] - setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 15] - setae r14b - cmp r11b, byte ptr [rdi + 14] + cmp r14b, byte ptr [rdi + 22] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 21] setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 13] + cmp r14b, byte ptr [rdi + 20] setae byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11b, byte ptr [rdi + 12] + cmp r14b, byte ptr [rdi + 19] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 18] + setae byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 17] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 15] + setae r11b + cmp r14b, byte ptr [rdi + 14] + setae byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 13] + setae byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 12] setae r12b - cmp r11b, byte ptr [rdi + 11] + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 11] setae r15b - cmp r11b, byte ptr [rdi + 10] - setae r11b + mov eax, dword ptr [rsp + 28] # 4-byte Reload + cmp al, byte ptr [rdi + 10] + setae r14b mov eax, dword ptr [rsp + 28] # 4-byte Reload cmp al, byte ptr [rdi + 9] setae r10b @@ -64047,7 +66026,7 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr setae sil mov eax, dword ptr [rsp + 28] # 4-byte Reload cmp al, byte ptr [rdi + 6] - setae byte ptr [rsp + 168] # 1-byte Folded Spill + setae byte ptr [rsp + 152] # 1-byte Folded Spill mov eax, dword ptr [rsp + 28] # 4-byte Reload cmp al, byte ptr [rdi + 5] setae r9b @@ -64062,7 +66041,7 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr setae cl mov eax, dword ptr [rsp + 28] # 4-byte Reload cmp al, byte ptr [rdi] - setae byte ptr [rsp + 160] # 1-byte Folded Spill + setae byte ptr [rsp + 168] # 1-byte Folded Spill mov eax, dword ptr [rsp + 28] # 4-byte Reload cmp al, byte ptr [rdi + 1] setae al @@ -64070,15 +66049,15 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov r13d, dword ptr [rsp + 28] # 4-byte Reload cmp r13b, byte ptr [rdi + 8] mov r13, rbx - setae byte ptr [rsp + 128] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 28] # 4-byte Reload cmp bl, byte ptr [rdi + 16] - setae byte ptr [rsp + 72] # 1-byte Folded Spill + setae byte ptr [rsp + 128] # 1-byte Folded Spill mov ebx, dword ptr [rsp + 28] # 4-byte Reload cmp bl, byte ptr [rdi + 24] setae bl add al, al - add al, byte ptr [rsp + 160] # 1-byte Folded Reload + add al, byte ptr [rsp + 168] # 1-byte Folded Reload shl cl, 2 or cl, al shl dl, 3 @@ -64087,66 +66066,66 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr or r8b, dl shl r9b, 5 or r9b, r8b - movzx eax, byte ptr [rsp + 168] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 6 shl sil, 7 or sil, al or sil, r9b mov byte ptr [r13], sil add r10b, r10b - add r10b, byte ptr [rsp + 128] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r10b + add r10b, byte ptr [rsp + 80] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b shl r15b, 3 - or r15b, r11b - mov r11d, dword ptr [rsp + 28] # 4-byte Reload + or r15b, r14b shl r12b, 4 or r12b, r15b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, r12b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 6 - shl r14b, 7 - or r14b, cl - or r14b, al - mov byte ptr [r13 + 1], r14b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl r11b, 7 + or r11b, cl + or r11b, al + mov byte ptr [r13 + 1], r11b + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 72] # 1-byte Folded Reload + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload shl dl, 6 movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, dl or al, cl mov byte ptr [r13 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload add al, al or al, bl mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax @@ -64167,286 +66146,48 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr mov byte ptr [r13 + 3], al add rdi, 32 add r13, 4 - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB11_70 -# %bb.71: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r14, qword ptr [rsp + 352] # 8-byte Reload - jmp .LBB11_72 -.LBB11_132: - mov r14d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB11_136 -# %bb.133: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB11_134: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] - lea rdx, [rdx + 4] - setge bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r15 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_134 -# %bb.135: - add r15, 1 -.LBB11_136: - sar r11, 5 - cmp r10, 32 - jl .LBB11_140 -# %bb.137: - mov qword ptr [rsp + 280], r10 # 8-byte Spill - mov qword ptr [rsp + 176], r11 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB11_138: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 272], r15 # 8-byte Spill - cmp r14d, dword ptr [rdx + 124] - setge byte ptr [rsp + 28] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 120] - setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 116] - setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 112] - setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 108] - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 104] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 100] - setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 92] - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 88] - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 84] - setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 80] - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 76] - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 72] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 68] - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 60] - setge r8b - cmp r14d, dword ptr [rdx + 56] - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 52] - setge byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 48] - setge r11b - cmp r14d, dword ptr [rdx + 44] - setge r10b - cmp r14d, dword ptr [rdx + 40] - setge r9b - cmp r14d, dword ptr [rdx + 36] - setge dil - cmp r14d, dword ptr [rdx + 28] - setge al - cmp r14d, dword ptr [rdx + 24] - setge bl - cmp r14d, dword ptr [rdx + 20] - setge sil - cmp r14d, dword ptr [rdx + 16] - setge cl - cmp r14d, dword ptr [rdx + 12] - setge r13b - cmp r14d, dword ptr [rdx + 8] - setge r12b - cmp r14d, dword ptr [rdx] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 4] - setge r15b - cmp r14d, dword ptr [rdx + 32] - setge byte ptr [rsp + 168] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 64] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 96] - setge byte ptr [rsp + 112] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r12b, 2 - or r12b, r15b - mov r15, qword ptr [rsp + 272] # 8-byte Reload - shl r13b, 3 - or r13b, r12b - shl cl, 4 - or cl, r13b - shl sil, 5 - or sil, cl - shl bl, 6 - shl al, 7 - or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 168] # 1-byte Folded Reload - shl r9b, 2 - or r9b, dil - shl r10b, 3 - or r10b, r9b - shl r11b, 4 - or r11b, r10b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 5 - or al, r11b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 288] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r15 + 3], al - sub rdx, -128 - add r15, 4 - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB11_138 -# %bb.139: - mov r10, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 176] # 8-byte Reload -.LBB11_140: - shl r11, 5 - cmp r11, r10 - jge .LBB11_185 -# %bb.141: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB11_145 -# %bb.142: - xor edi, edi - jmp .LBB11_143 -.LBB11_9: - mov r13, r15 -.LBB11_91: - shl r14, 5 - cmp r14, r10 - jge .LBB11_185 -# %bb.92: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB11_94 -# %bb.93: - xor esi, esi - jmp .LBB11_97 -.LBB11_61: + add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + jne .LBB11_76 +# %bb.77: + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov rcx, qword ptr [rsp + 352] # 8-byte Reload + jmp .LBB11_78 +.LBB11_65: mov r13, r15 - mov rdi, rdx -.LBB11_72: - shl r14, 5 - cmp r14, r10 - jge .LBB11_185 -# %bb.73: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB11_75 -# %bb.74: +.LBB11_78: + shl rcx, 5 + mov r8, r12 + sub r8, rcx + jle .LBB11_211 +# %bb.79: + or rcx, 1 + cmp r12, rcx + jne .LBB11_81 +# %bb.80: xor r9d, r9d - jmp .LBB11_78 -.LBB11_130: - mov r9, r8 - and r9, -2 - xor r11d, r11d + jmp .LBB11_84 +.LBB11_149: + mov r10, r9 + and r10, -2 + xor r14d, r14d .p2align 4, 0x90 -.LBB11_131: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] +.LBB11_150: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] mov edi, 0 adc dil, -1 - mov rsi, r11 + mov rsi, r14 shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - xor dil, r10b - mov ecx, r11d + movzx r11d, byte ptr [r15 + rsi] + xor dil, r11b + mov ecx, r14d and cl, 6 mov al, 1 shl al, cl and al, dil - xor al, r10b + xor al, r11b mov byte ptr [r15 + rsi], al - add r11, 2 - cmp r14d, dword ptr [rdx + 4] + add r14, 2 + cmp r8d, dword ptr [rdx + 4] lea rdx, [rdx + 8] mov edi, 0 adc dil, -1 @@ -64457,21 +66198,21 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr and bl, dil xor bl, al mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB11_131 -.LBB11_24: - test r8b, 1 - je .LBB11_185 -# %bb.25: + cmp r10, r14 + jne .LBB11_150 +.LBB11_22: + test r9b, 1 + je .LBB11_211 +# %bb.23: xor eax, eax - cmp r14d, dword ptr [rdx] - jmp .LBB11_183 -.LBB11_179: + cmp r8d, dword ptr [rdx] + jmp .LBB11_128 +.LBB11_204: mov r10, r8 and r10, -2 xor r11d, r11d .p2align 4, 0x90 -.LBB11_180: # =>This Inner Loop Header: Depth=1 +.LBB11_205: # =>This Inner Loop Header: Depth=1 vucomisd xmm0, qword ptr [rdx] mov eax, 0 adc al, -1 @@ -64499,36 +66240,36 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr xor al, bl mov byte ptr [r15 + rsi], al cmp r10, r11 - jne .LBB11_180 -.LBB11_181: + jne .LBB11_205 +.LBB11_206: test r8b, 1 - je .LBB11_185 -# %bb.182: + je .LBB11_211 +# %bb.207: xor eax, eax vucomisd xmm0, qword ptr [rdx] - jmp .LBB11_183 -.LBB11_147: - mov r9, r8 - and r9, -2 - xor r11d, r11d + jmp .LBB11_208 +.LBB11_168: + mov r10, r9 + and r10, -2 + xor r14d, r14d .p2align 4, 0x90 -.LBB11_148: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] +.LBB11_169: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] mov edi, 0 adc dil, -1 - mov rsi, r11 + mov rsi, r14 shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - xor dil, r10b - mov ecx, r11d + movzx r11d, byte ptr [r15 + rsi] + xor dil, r11b + mov ecx, r14d and cl, 6 mov al, 1 shl al, cl and al, dil - xor al, r10b + xor al, r11b mov byte ptr [r15 + rsi], al - add r11, 2 - cmp r14, qword ptr [rdx + 8] + add r14, 2 + cmp r8, qword ptr [rdx + 8] lea rdx, [rdx + 16] mov edi, 0 adc dil, -1 @@ -64539,37 +66280,37 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr and bl, dil xor bl, al mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB11_148 + cmp r10, r14 + jne .LBB11_169 .LBB11_40: - test r8b, 1 - je .LBB11_185 + test r9b, 1 + je .LBB11_211 # %bb.41: xor eax, eax - cmp r14, qword ptr [rdx] - jmp .LBB11_183 -.LBB11_112: - mov r9, r8 - and r9, -2 - xor r11d, r11d + cmp r8, qword ptr [rdx] + jmp .LBB11_128 +.LBB11_129: + mov r10, r9 + and r10, -2 + xor r14d, r14d .p2align 4, 0x90 -.LBB11_113: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] +.LBB11_130: # =>This Inner Loop Header: Depth=1 + cmp r8w, word ptr [rdx] mov edi, 0 adc dil, -1 - mov rsi, r11 + mov rsi, r14 shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - xor dil, r10b - mov ecx, r11d + movzx r11d, byte ptr [r15 + rsi] + xor dil, r11b + mov ecx, r14d and cl, 6 mov al, 1 shl al, cl and al, dil - xor al, r10b + xor al, r11b mov byte ptr [r15 + rsi], al - add r11, 2 - cmp r14w, word ptr [rdx + 2] + add r14, 2 + cmp r8w, word ptr [rdx + 2] lea rdx, [rdx + 4] mov edi, 0 adc dil, -1 @@ -64580,101 +66321,109 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr and bl, dil xor bl, al mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB11_113 -.LBB11_110: - test r8b, 1 - je .LBB11_185 -# %bb.111: + cmp r10, r14 + jne .LBB11_130 +.LBB11_126: + test r9b, 1 + je .LBB11_211 +# %bb.127: xor eax, eax - cmp r14w, word ptr [rdx] - jmp .LBB11_183 + cmp r8w, word ptr [rdx] .LBB11_128: - mov r10, r8 - and r10, -2 + adc al, -1 + mov rdx, r14 + shr rdx, 3 + mov sil, byte ptr [r15 + rdx] + and r14b, 7 + mov bl, 1 + mov ecx, r14d + jmp .LBB11_209 +.LBB11_147: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB11_129: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] +.LBB11_148: # =>This Inner Loop Header: Depth=1 + cmp r8w, word ptr [rdx] setge al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r15 + rsi] + movzx r10d, byte ptr [r15 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b + xor bl, r10b mov byte ptr [r15 + rsi], bl add rdi, 2 - cmp r14w, word ptr [rdx + 2] + cmp r8w, word ptr [rdx + 2] lea rdx, [rdx + 4] - setge r9b - neg r9b - xor r9b, bl + setge r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl mov byte ptr [r15 + rsi], al - cmp r10, rdi - jne .LBB11_129 -.LBB11_125: - test r8b, 1 - je .LBB11_185 -# %bb.126: - cmp r14w, word ptr [rdx] - jmp .LBB11_127 -.LBB11_162: - mov r10, r8 - and r10, -2 + cmp r11, rdi + jne .LBB11_148 +.LBB11_144: + test r9b, 1 + je .LBB11_211 +# %bb.145: + cmp r8w, word ptr [rdx] + jmp .LBB11_146 +.LBB11_185: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB11_163: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] +.LBB11_186: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] setge al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r15 + rsi] + movzx r10d, byte ptr [r15 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b + xor bl, r10b mov byte ptr [r15 + rsi], bl add rdi, 2 - cmp r14, qword ptr [rdx + 8] + cmp r8, qword ptr [rdx + 8] lea rdx, [rdx + 16] - setge r9b - neg r9b - xor r9b, bl + setge r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl mov byte ptr [r15 + rsi], al - cmp r10, rdi - jne .LBB11_163 -.LBB11_160: - test r8b, 1 - je .LBB11_185 -# %bb.161: - cmp r14, qword ptr [rdx] - jmp .LBB11_127 -.LBB11_177: + cmp r11, rdi + jne .LBB11_186 +.LBB11_183: + test r9b, 1 + je .LBB11_211 +# %bb.184: + cmp r8, qword ptr [rdx] + jmp .LBB11_146 +.LBB11_202: mov r10, r8 and r10, -2 xor r11d, r11d .p2align 4, 0x90 -.LBB11_178: # =>This Inner Loop Header: Depth=1 +.LBB11_203: # =>This Inner Loop Header: Depth=1 vucomiss xmm0, dword ptr [rdx] mov eax, 0 adc al, -1 @@ -64702,14 +66451,14 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr xor al, bl mov byte ptr [r15 + rsi], al cmp r10, r11 - jne .LBB11_178 -.LBB11_175: + jne .LBB11_203 +.LBB11_200: test r8b, 1 - je .LBB11_185 -# %bb.176: + je .LBB11_211 +# %bb.201: xor eax, eax vucomiss xmm0, dword ptr [rdx] -.LBB11_183: +.LBB11_208: adc al, -1 mov rdx, r11 shr rdx, 3 @@ -64717,50 +66466,51 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr and r11b, 7 mov bl, 1 mov ecx, r11d +.LBB11_209: shl bl, cl xor al, sil and bl, al - jmp .LBB11_184 -.LBB11_145: - mov r10, r8 - and r10, -2 + jmp .LBB11_210 +.LBB11_166: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB11_146: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] +.LBB11_167: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] setge al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r15 + rsi] + movzx r10d, byte ptr [r15 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b + xor bl, r10b mov byte ptr [r15 + rsi], bl add rdi, 2 - cmp r14d, dword ptr [rdx + 4] + cmp r8d, dword ptr [rdx + 4] lea rdx, [rdx + 8] - setge r9b - neg r9b - xor r9b, bl + setge r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl mov byte ptr [r15 + rsi], al - cmp r10, rdi - jne .LBB11_146 -.LBB11_143: - test r8b, 1 - je .LBB11_185 -# %bb.144: - cmp r14d, dword ptr [rdx] -.LBB11_127: + cmp r11, rdi + jne .LBB11_167 +.LBB11_164: + test r9b, 1 + je .LBB11_211 +# %bb.165: + cmp r8d, dword ptr [rdx] +.LBB11_146: setge al neg al mov rdx, rdi @@ -64772,10 +66522,10 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr shl bl, cl xor al, sil and bl, al -.LBB11_184: +.LBB11_210: xor bl, sil mov byte ptr [r15 + rdx], bl -.LBB11_185: +.LBB11_211: lea rsp, [rbp - 40] pop rbx pop r12 @@ -64785,66 +66535,67 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr pop rbp vzeroupper ret -.LBB11_94: +.LBB11_108: mov r10, r8 and r10, -2 - xor esi, esi + xor r9d, r9d .p2align 4, 0x90 -.LBB11_95: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx + rsi] - setge al - neg al - mov rdi, rsi - shr rdi, 3 - mov ecx, esi +.LBB11_109: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r14b, byte ptr [rdi + r9] + setge bl + neg bl + mov rsi, r9 + shr rsi, 3 + mov ecx, eax and cl, 6 - mov bl, 1 - shl bl, cl - movzx r9d, byte ptr [r13 + rdi] - xor al, r9b - and bl, al + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r13 + rsi] xor bl, r9b - mov byte ptr [r13 + rdi], bl - cmp r11b, byte ptr [rdx + rsi + 1] - lea rsi, [rsi + 2] - setge r9b - neg r9b - xor r9b, bl + and dl, bl + xor dl, r9b + mov byte ptr [r13 + rsi], dl + cmp r14b, byte ptr [rdi + rax + 1] + lea r9, [rax + 2] + setge bl + neg bl + xor bl, dl or cl, 1 mov al, 1 shl al, cl - and al, r9b - xor al, bl - mov byte ptr [r13 + rdi], al - cmp r10, rsi - jne .LBB11_95 -# %bb.96: - add rdx, rsi -.LBB11_97: + and al, bl + xor al, dl + mov byte ptr [r13 + rsi], al + cmp r10, r9 + jne .LBB11_109 +# %bb.110: + add rdi, r9 +.LBB11_111: test r8b, 1 - je .LBB11_185 -# %bb.98: - cmp r11b, byte ptr [rdx] + je .LBB11_211 +# %bb.112: + cmp r14b, byte ptr [rdi] setge al neg al - mov rdx, rsi + mov rdx, r9 shr rdx, 3 mov dil, byte ptr [r13 + rdx] - and sil, 7 + and r9b, 7 mov bl, 1 - mov ecx, esi + mov ecx, r9d shl bl, cl xor al, dil and bl, al - jmp .LBB11_80 -.LBB11_75: + jmp .LBB11_86 +.LBB11_81: mov r10, r8 and r10, -2 xor r9d, r9d .p2align 4, 0x90 -.LBB11_76: # =>This Inner Loop Header: Depth=1 +.LBB11_82: # =>This Inner Loop Header: Depth=1 mov rax, r9 - cmp r11b, byte ptr [rdi + r9] + cmp r14b, byte ptr [rdi + r9] mov ebx, 0 adc bl, -1 mov rsi, r9 @@ -64858,7 +66609,7 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr and dl, bl xor dl, r9b mov byte ptr [r13 + rsi], dl - cmp r11b, byte ptr [rdi + rax + 1] + cmp r14b, byte ptr [rdi + rax + 1] lea r9, [rax + 2] mov ebx, 0 adc bl, -1 @@ -64870,15 +66621,15 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr xor al, dl mov byte ptr [r13 + rsi], al cmp r10, r9 - jne .LBB11_76 -# %bb.77: + jne .LBB11_82 +# %bb.83: add rdi, r9 -.LBB11_78: +.LBB11_84: test r8b, 1 - je .LBB11_185 -# %bb.79: + je .LBB11_211 +# %bb.85: xor eax, eax - cmp r11b, byte ptr [rdi] + cmp r14b, byte ptr [rdi] adc al, -1 mov rdx, r9 shr rdx, 3 @@ -64889,1983 +66640,1984 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr shl bl, cl xor al, dil and bl, al -.LBB11_80: +.LBB11_86: xor bl, dil mov byte ptr [r13 + rdx], bl - jmp .LBB11_185 -.LBB11_85: - and r14, -32 - mov rax, r14 + jmp .LBB11_211 +.LBB11_99: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 360], rax # 8-byte Spill - mov qword ptr [rsp + 416], r14 # 8-byte Spill - lea rax, [r15 + 4*r14] + add rax, rdi mov qword ptr [rsp + 368], rax # 8-byte Spill - vmovd xmm0, r11d + mov qword ptr [rsp + 416], rcx # 8-byte Spill + lea rax, [r15 + 4*rcx] + mov qword ptr [rsp + 360], rax # 8-byte Spill + vmovd xmm0, r14d vpbroadcastb ymm0, xmm0 vmovdqa ymmword ptr [rsp + 384], ymm0 # 32-byte Spill - xor ebx, ebx + xor eax, eax mov qword ptr [rsp + 272], r15 # 8-byte Spill .p2align 4, 0x90 -.LBB11_86: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 376], rbx # 8-byte Spill +.LBB11_100: # =>This Inner Loop Header: Depth=1 + mov rbx, rax + mov qword ptr [rsp + 376], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 232], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 216], rax # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill mov rax, rbx or rax, 96 - mov qword ptr [rsp + 112], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 192], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 120], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 184], rax # 8-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill mov rax, rbx or rax, 288 - mov qword ptr [rsp + 264], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 320 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill mov rax, rbx or rax, 512 - mov rcx, rax - movzx eax, byte ptr [rdx + rax] + mov rdx, rax + movzx eax, byte ptr [rdi + rax] vmovd xmm0, eax - movzx eax, byte ptr [rdx + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm3, eax - movzx eax, byte ptr [rdx + rcx + 1] + movzx eax, byte ptr [rdi + rdx + 1] vmovd xmm4, eax - movzx eax, byte ptr [rdx + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rcx + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 544], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rcx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rcx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - mov qword ptr [rsp + 248], rbx # 8-byte Spill - movzx eax, byte ptr [rdx + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rdx + rcx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm6, eax - movzx eax, byte ptr [rdx + rcx + 6] - mov qword ptr [rsp + 224], rcx # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 248], rdx # 8-byte Spill vmovd xmm12, eax - movzx eax, byte ptr [rdx + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rcx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 184], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 320], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 96], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 288], rax # 8-byte Spill - mov r14, rbx - or r14, 544 - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov rcx, rbx - or rcx, 576 - mov qword ptr [rsp + 176], rcx # 8-byte Spill - mov rax, rbx - or rax, 608 - mov r13, rax - mov qword ptr [rsp + 200], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill + mov r12, rbx + or r12, 544 + mov qword ptr [rsp + 200], r12 # 8-byte Spill + mov r15, rbx + or r15, 576 + mov qword ptr [rsp + 80], r15 # 8-byte Spill + mov r11, rbx + or r11, 608 + mov qword ptr [rsp + 232], r11 # 8-byte Spill + mov r10, rbx + or r10, 640 + mov qword ptr [rsp + 192], r10 # 8-byte Spill mov rax, rbx - or rax, 640 + or rax, 672 mov qword ptr [rsp + 152], rax # 8-byte Spill - mov r10, rbx - or r10, 672 - mov qword ptr [rsp + 256], r10 # 8-byte Spill - mov r9, rbx - or r9, 704 - mov qword ptr [rsp + 240], r9 # 8-byte Spill - mov r11, rbx - or r11, 736 - mov qword ptr [rsp + 80], r11 # 8-byte Spill - mov r15, rbx - or r15, 768 - mov qword ptr [rsp + 128], r15 # 8-byte Spill - mov r8, rbx - or r8, 800 - mov qword ptr [rsp + 56], r8 # 8-byte Spill - mov r12, rbx - or r12, 832 - mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov r14, rbx + or r14, 704 + mov qword ptr [rsp + 160], r14 # 8-byte Spill mov rax, rbx - or rax, 864 - mov qword ptr [rsp + 72], rax # 8-byte Spill + or rax, 736 + mov qword ptr [rsp + 112], rax # 8-byte Spill + mov r13, rbx + or r13, 768 + mov qword ptr [rsp + 48], r13 # 8-byte Spill mov rax, rbx - or rax, 896 - mov rdi, rax + or rax, 800 mov qword ptr [rsp + 88], rax # 8-byte Spill - mov rax, rbx - or rax, 928 - mov rsi, rax - mov qword ptr [rsp + 160], rax # 8-byte Spill - mov rax, rbx - or rax, 960 - mov qword ptr [rsp + 104], rax # 8-byte Spill - or rbx, 992 - vpinsrb xmm9, xmm0, byte ptr [rdx + r14], 1 - vpinsrb xmm0, xmm9, byte ptr [rdx + rcx], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13], 3 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12], 10 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx], 15 - mov r12, rbx - mov qword ptr [rsp + 168], rbx # 8-byte Spill - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 1 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 2 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 3 - mov r8, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 4 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 6 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 7 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 11 + mov r9, rbx + or r9, 832 + mov qword ptr [rsp + 216], r9 # 8-byte Spill + mov rcx, rbx + or rcx, 864 + mov qword ptr [rsp + 176], rcx # 8-byte Spill + mov r8, rbx + or r8, 896 + mov qword ptr [rsp + 168], r8 # 8-byte Spill + mov rsi, rbx + or rsi, 928 + mov qword ptr [rsp + 240], rsi # 8-byte Spill + mov rax, rbx + mov rdx, rbx + mov qword ptr [rsp + 224], rbx # 8-byte Spill + or rax, 960 + mov qword ptr [rsp + 208], rax # 8-byte Spill + or rdx, 992 + mov qword ptr [rsp + 264], rdx # 8-byte Spill + vpinsrb xmm9, xmm0, byte ptr [rdi + r12], 1 + vpinsrb xmm0, xmm9, byte ptr [rdi + r15], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14], 6 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13], 8 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx], 15 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14], 1 mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 14 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 15 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 1], 1 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 1], 2 - mov r13, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 1], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 4 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 5 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 6 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 7 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 2 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 3 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 4 + mov r10, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 5 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 6 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 7 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 9 mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 1], 11 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 1], 12 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 1], 13 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 1], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 1], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r11 + 1], 1 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 2 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 1], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 1], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 1], 5 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 1], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 1], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 1], 9 - mov r13, rdi - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 10 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 11 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 12 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 15 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 1 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 2 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 3 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 5 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 1], 6 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 7 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 1], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 1], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 1], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 1], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 1], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 1], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 1], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 1], 10 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 1], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 12 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 1], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 1], 14 vinserti128 ymm13, ymm3, xmm0, 1 - vpinsrb xmm0, xmm5, byte ptr [rdx + r14 + 1], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm9, edi + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 1216], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm10, edi + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm10, eax vmovdqa xmm0, xmmword ptr [rsp + 544] # 16-byte Reload - mov r15, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 2], 1 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 2 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 3 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 4 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 5 - mov r8, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 2], 6 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 2], 7 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 2], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 2], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 2], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 14 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 2], 15 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 2 mov r10, qword ptr [rsp + 232] # 8-byte Reload - vmovdqa xmm3, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 2], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 2], 3 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 2], 4 + mov rbx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 2], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 2], 6 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 2], 7 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 2], 8 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 2], 9 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 2], 3 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 2], 4 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 2], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 2], 8 - mov rcx, r13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 9 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 2], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 12 + mov r12, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 2], 13 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 2], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 2], 15 + mov rcx, r14 + vmovdqa xmm3, xmmword ptr [rsp + 480] # 16-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 2], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 4 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 2], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 8 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 9 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 10 + mov rdx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 11 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 12 mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 14 - mov r13, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 15 - vpinsrb xmm4, xmm11, byte ptr [rdx + r15 + 3], 1 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 2 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 3 - mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 4 - mov rbx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 3], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 3], 8 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 3], 9 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 10 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 11 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 13 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 14 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 2], 15 + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm4, xmm11, byte ptr [rdi + r13 + 3], 1 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 3], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 3], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 5 + mov r10, rbx mov r13, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 3], 13 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 14 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 3], 15 - vpinsrb xmm5, xmm8, byte ptr [rdx + r10 + 3], 1 - mov rbx, r10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 2 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 3], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 3], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 6 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 3], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 3], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 3], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 9 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 3], 10 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 3], 11 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 3], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 3], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 3], 14 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 3], 15 + vpinsrb xmm5, xmm8, byte ptr [rdi + rcx + 3], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 2 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 3 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 3], 5 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 3], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 3], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 3], 13 vinserti128 ymm0, ymm3, xmm0, 1 vmovdqa ymmword ptr [rsp + 544], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 3], 14 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 9] - vmovd xmm8, edi - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 3], 15 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm5, byte ptr [rdi + rax + 3], 14 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 3], 15 vinserti128 ymm0, ymm0, xmm4, 1 vmovdqa ymmword ptr [rsp + 480], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 9] - vmovd xmm11, edi + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm0, xmmword ptr [rsp + 448] # 16-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 1 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 4], 2 - mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 4], 3 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 4], 4 - mov r8, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 4], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 6 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 4], 1 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 4], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 10 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 4], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 2 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 4], 5 + mov r15, r13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 4], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 8 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 4], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 4], 14 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 4], 15 - vpinsrb xmm3, xmm15, byte ptr [rdx + rbx + 4], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 2 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 4], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 4], 4 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 4], 7 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 4], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 4], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 4], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 4], 12 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 4], 13 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 4], 14 + mov rcx, r8 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 4], 15 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm15, byte ptr [rdi + r14 + 4], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + mov r9, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 3 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 4 + mov r10, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 6 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 15 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm14, byte ptr [rdx + rax + 5], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 5], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 5], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 5], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 6 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 5], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 5], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 7 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 4], 8 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 4], 9 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 10 + mov rbx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 11 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 12 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 13 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 14 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 15 + vpinsrb xmm4, xmm14, byte ptr [rdi + rsi + 5], 1 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 2 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 3 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 4 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 6 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 7 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 5], 8 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 9 + mov rsi, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 10 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 5], 12 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 5], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 5], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 5], 15 + vpinsrb xmm5, xmm6, byte ptr [rdi + r14 + 5], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 5 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 7 + mov rsi, rax + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 5], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 5], 9 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 5], 11 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 5], 12 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 5], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 5], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 5], 15 - vpinsrb xmm5, xmm6, byte ptr [rdx + rbx + 5], 1 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 2 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 5], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 5], 4 - mov r9, r14 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 5], 7 - mov r14, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 5], 8 - mov r12, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 5], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 5], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 5], 14 + mov r8, rax vinserti128 ymm14, ymm3, xmm0, 1 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm5, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm3, edi - vinserti128 ymm15, ymm0, xmm4, 1 + vpinsrb xmm0, xmm5, byte ptr [rdi + rbx + 5], 15 mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm4, edi + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm3, eax + vinserti128 ymm15, ymm0, xmm4, 1 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm12, byte ptr [rdi + rcx + 6], 1 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 6], 2 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 6], 3 + mov r11, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 6], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 5 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 6], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 9 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 6], 10 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 6], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 12 + mov r12, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 6], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 6], 14 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 6], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm5, xmm7, byte ptr [rdi + rax + 6], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 2 mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm12, byte ptr [rdx + rax + 6], 1 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 2 - mov rbx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 6], 3 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 6], 4 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 6], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 7 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 8 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 6], 9 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 3 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 6], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 6], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 6], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 6], 14 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 6], 15 - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + r11 + 6], 1 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 5 + mov rax, r10 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 7 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 8 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 6], 9 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 10 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 11 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 12 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 13 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 14 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 3 + mov r8, r14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 6 mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 4 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rdi + 6], 6 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 6], 8 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 9 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 10 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 6], 11 - mov r9, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 6], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 7 mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 14 - mov r12, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 6], 15 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 1 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 7], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 7], 5 - mov r8, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 6 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 7 - mov r10, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 7], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 7], 12 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 7], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 7], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 1 - mov r13, r11 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 7], 2 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 3 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 4 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 7 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 8 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 7], 11 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 14 mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 9 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 7], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 7], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 15 + mov r11, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 2 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 7], 3 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 4 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 13 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 448], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rdi + 7], 14 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 11] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 7], 15 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 7], 14 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 7], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 512], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 11] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm9, byte ptr [rdx + rdi + 8], 1 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 8], 2 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 8], 3 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 4 - mov r9, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 8], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 8], 6 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 10 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 8], 11 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 8], 13 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 14 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 8], 15 - vpinsrb xmm5, xmm10, byte ptr [rdx + r13 + 8], 1 - mov r14, rsi - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 2 - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 3 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 8], 4 - mov rdi, r12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 8], 5 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 6 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 8], 7 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 9 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 14 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 15 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rdx + rbx + 9], 1 - mov rbx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 9], 3 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm2, eax + mov r14, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm9, byte ptr [rdi + r14 + 8], 1 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 8], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 4 mov rbx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 9], 5 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 6 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 9], 7 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 9 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 9], 11 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 12 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 9], 13 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 14 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 9], 15 - vpinsrb xmm7, xmm11, byte ptr [rdx + r13 + 9], 1 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 9], 2 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rdi + 9], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 9], 6 - mov r14, rsi - vpinsrb xmm7, xmm7, byte ptr [rdx + r12 + 9], 7 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 9], 10 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 9], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 8], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 6 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 8], 7 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 8 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 8], 9 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 12 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 8], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 8], 15 + vpinsrb xmm5, xmm10, byte ptr [rdi + r11 + 8], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 8], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 5 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 7 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 8 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 9 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 8], 10 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 11 + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 8], 12 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 8], 13 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + r14 + 9], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 2 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 9], 3 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 5 + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 9], 7 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 9], 9 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 9], 10 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 11 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 12 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 13 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 9], 15 + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm7, xmm11, byte ptr [rdi + rdx + 9], 1 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 9], 2 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 3 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 9], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 10 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 9], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 9], 12 + mov r15, r10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rcx + 9], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 14 vinserti128 ymm0, ymm5, xmm0, 1 vmovdqa ymmword ptr [rsp + 1184], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm5, xmm7, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm0, edi + vpinsrb xmm5, xmm7, byte ptr [rdi + r13 + 9], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm0, eax vinserti128 ymm5, ymm5, xmm6, 1 vmovdqa ymmword ptr [rsp + 1152], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm5, edi - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 10], 1 - mov r12, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 10], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 3 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 10], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 10], 5 - mov r9, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 10], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 10], 7 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 9 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 14 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 15 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 1 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 10], 4 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 10], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 6 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 10], 7 - mov r8, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 10], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 12 - mov r11, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 13 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 10], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 11], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 11], 4 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 11], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 1 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 7 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 11], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 3 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 4 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 5 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 8 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 12 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 13 - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 11], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 10 + mov r14, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 11 mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 11], 15 - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 11], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 2 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 11], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 11], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 11], 8 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 11], 13 - vinserti128 ymm3, ymm4, xmm3, 1 - vmovdqa ymmword ptr [rsp + 1120], ymm3 # 32-byte Spill - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 11], 14 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 13] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 15 - vinserti128 ymm1, ymm2, xmm1, 1 - vmovdqa ymmword ptr [rsp + 1088], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 13] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 12], 1 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 12], 2 - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 12], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 12], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 12], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 12 mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 6 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 7 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 13 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 10], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 15 + mov r9, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 10], 1 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 12 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 12], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 12], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 12], 15 - vpinsrb xmm2, xmm5, byte ptr [rdx + r9 + 12], 1 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 2 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 3 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 4 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 12], 5 - mov r9, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 12], 6 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 7 - mov r11, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 12], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 12], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 12 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 12], 14 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 5 - mov r10, r12 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 6 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 7 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 8 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 9 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 10 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 11 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 13], 12 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 13 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 14 - mov r12, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 13], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 5 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 7 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 8 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 9 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 10 + mov rcx, r11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 12 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 10], 13 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 14 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 10], 15 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 1 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 2 mov rbx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 3 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 13], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 13], 6 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 13], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 6 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 7 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 8 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 9 + mov r10, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 12 + mov rbx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 14 mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 2 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 4 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 11], 11 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 11], 13 + vinserti128 ymm3, ymm4, xmm3, 1 + vmovdqa ymmword ptr [rsp + 1120], ymm3 # 32-byte Spill + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 11], 15 + vinserti128 ymm1, ymm2, xmm1, 1 + vmovdqa ymmword ptr [rsp + 1088], ymm1 # 32-byte Spill + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm1, eax + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 12], 1 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 12], 2 + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 12], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 6 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 12], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 12], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 12], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 12], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 12], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 12], 15 + mov r11, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + r11 + 12], 1 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 5 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 12], 6 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 7 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 8 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 9 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 12], 10 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 12 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 13 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 14 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 3 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 4 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 5 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 8 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 9 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 10 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 11 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 13 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 13], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 6 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 13], 7 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 11 + mov r10, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 14 vinserti128 ymm0, ymm2, xmm0, 1 vmovdqa ymmword ptr [rsp + 1024], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm1, byte ptr [rdx + rax + 13], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 14] - vmovd xmm1, edi + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm1, byte ptr [rdi + rax + 13], 15 + mov r13, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r13 + 14] + vmovd xmm1, eax vinserti128 ymm0, ymm0, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 14] - vmovd xmm0, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 1 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 14], 2 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 3 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r15 + 14] + vmovd xmm0, eax + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 2 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 4 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 5 - mov r13, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 14], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 14], 7 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 9 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 11 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 14], 12 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 14], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 1 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 14], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 5 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 14], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 14], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 14], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 9 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 14], 9 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 10 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 14], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 12 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 13 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 14], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 14], 15 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 2 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 4 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 12 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 14], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 14 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 14], 15 + movzx eax, byte ptr [rdi + r13 + 15] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 2 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 3 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 15], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 8 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 15], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 15], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 15], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 15], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 15], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 15], 15 + movzx eax, byte ptr [rdi + r15 + 15] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 15], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 8 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 15], 9 + mov r13, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 15], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 13 mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 10 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 11 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 14], 12 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 14], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 14], 15 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + r8 + 15] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 15], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 15], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 3 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 4 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 15], 6 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 15], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 15], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 15], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 15], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 15], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 15], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 15], 14 - mov r9, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 15], 15 - mov rbx, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rbx + 15] - vmovd xmm3, edi - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 1 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 2 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 15], 3 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 4 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 5 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 15], 6 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 15], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 9 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 14 - mov r15, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 15], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 14 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 15 vinserti128 ymm0, ymm0, xmm1, 1 vmovdqa ymmword ptr [rsp + 960], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 992], ymm0 # 32-byte Spill - movzx edi, byte ptr [rdx + r8 + 16] - vmovd xmm0, edi - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 1 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 2 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 3 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 4 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 16], 6 - mov r12, r13 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 7 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 8 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 9 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 16], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 12 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm0, eax + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 16], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 2 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 16], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 4 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 16], 5 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 16], 13 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 16], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 16], 15 - movzx edi, byte ptr [rdx + rbx + 16] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 16], 1 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 16], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 16], 3 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 4 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 16], 7 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 16], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 6 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 16], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 16], 9 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 10 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 16], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 12 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 13 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 16], 14 mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 16], 9 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 16], 13 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 16], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 16], 15 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 17] - vmovd xmm2, edi - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 1 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 17], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 4 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 17], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 17], 6 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 17], 7 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 9 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 17], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 11 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 12 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 17], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 17], 14 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 17], 15 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 17] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 2 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 4 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 17], 5 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 17], 6 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 17], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 17], 10 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 11 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 17], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 17], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 16], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 16], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 10 + mov r14, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 16], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 16], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 15 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r9 + 17] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 1 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 17], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 17], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 17], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 7 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 17], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 17], 9 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 17], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 17], 12 + mov r12, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 17], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 17], 14 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 17], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 17] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 2 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 17], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 6 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 11 + mov r14, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 17], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 928], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rax + 17], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rax + 17], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 896], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 18] - vmovd xmm0, edi - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 18], 1 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 2 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 3 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 18], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 5 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 18], 7 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 18], 8 - mov r10, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 18], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 18], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 11 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 18], 13 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 14 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 18], 15 - mov r11, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 18] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 1 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 18], 2 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 18], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 4 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 18], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 9 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 18], 12 - mov r9, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 14 - mov r8, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 18], 15 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 19] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 1 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 19], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 4 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 6 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 19], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 19], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 10 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 19], 11 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 19], 12 + movzx eax, byte ptr [rdi + r9 + 18] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 18], 2 + mov r15, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 18], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 18], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 5 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 18], 8 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 18], 9 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 11 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 19], 15 - movzx edi, byte ptr [rdx + r11 + 19] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 19], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 19], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 18], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 18], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 18], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm1, eax + mov r12, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 5 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 18], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 7 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 18], 8 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 9 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 18], 10 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 11 + mov rcx, r14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 12 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 13 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 14 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 3 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 4 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 19], 6 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 7 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 19], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 5 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 19], 6 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 19], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 9 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 12 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 14 mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 9 - mov r10, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 19], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 19], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 19], 13 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 19], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 19], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 19], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 19], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 19], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 19], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 19], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 19], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 19], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 832], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 864], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 20] - vmovd xmm0, edi - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 1 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 20], 2 + mov r9, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + r9 + 20] + vmovd xmm0, eax mov r12, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 20], 3 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 4 - mov r8, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 20], 5 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 20], 6 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 7 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 8 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 9 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 20], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 20], 12 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 20], 13 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 14 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 20], 15 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 20] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 2 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 20], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 4 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 20], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 8 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 11 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 20], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 20], 14 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 20], 15 - movzx edi, byte ptr [rdx + rax + 21] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 21], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 21], 3 - mov r13, r12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 20], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 2 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 20], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 4 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 21], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 21], 6 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 21], 7 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 21], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 9 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 21], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 20], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 8 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 21], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 20], 9 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 20], 10 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 20], 11 + mov r15, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 20], 12 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 20], 13 + mov rbx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 20], 14 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 20], 15 + mov r13, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r13 + 20] + vmovd xmm1, eax + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 14 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 21], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 21], 15 - mov r11, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 21] - vmovd xmm3, edi - mov r14, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 21], 1 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 3 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 4 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 21], 5 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 6 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 7 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 8 - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 9 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 15 + movzx eax, byte ptr [rdi + r9 + 21] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 1 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 21], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 21], 3 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 21], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 21], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 21], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 21], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 21], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 21], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 21], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 21], 15 + movzx eax, byte ptr [rdi + r13 + 21] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 3 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 4 + mov rbx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 21], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 9 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 768], ymm0 # 32-byte Spill - vpinsrb xmm0, xmm3, byte ptr [rdx + r9 + 21], 15 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + r11 + 21], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 800], ymm0 # 32-byte Spill - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 22] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 1 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 22], 3 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 22], 4 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 5 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 22], 7 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 22], 10 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 11 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 12 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 22], 13 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 22], 14 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 22], 15 - movzx edi, byte ptr [rdx + r11 + 22] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 22], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 22], 2 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm0, eax + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 2 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 3 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 4 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rdx + 22], 5 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 22], 6 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 5 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 22], 6 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 7 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 22], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 10 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 22], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 8 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 22], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 22], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 12 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 22], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 22], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 22], 2 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 22], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 10 mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 11 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 22], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 22], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 22], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm2, eax + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 23], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 2 + mov r15, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 23], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 23], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 6 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 23], 7 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 22], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 23], 10 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 23], 11 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 23], 12 + mov r10, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 23], 13 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 23], 14 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 23], 15 mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 23] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 1 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 2 - mov r14, r13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 23], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 4 - mov r13, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 23], 5 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 23], 6 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 23], 7 + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm3, eax + mov r14, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 4 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 23], 9 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 11 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 23], 12 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 23], 13 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 23], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 23], 15 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 23] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 1 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 2 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 4 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 23], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 23], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 23], 8 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 23], 9 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 23], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 12 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 12 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 14 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 15 vinserti128 ymm10, ymm1, xmm0, 1 vinserti128 ymm11, ymm3, xmm2, 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 24] - vmovd xmm0, edi - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 1 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 24], 2 - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 24], 3 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rdi + 24], 4 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 24], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 6 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 24], 7 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 24], 8 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 10 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 24], 11 - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 24], 12 - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 24], 13 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 24], 1 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 24], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 3 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 24], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 24], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 8 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 24], 9 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 24], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 24], 11 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 24], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 24], 13 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 24], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 24], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 2 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 3 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 7 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 24], 8 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 11 + mov r11, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 13 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 14 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 14 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 24], 15 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + r14 + 24] - vmovd xmm1, edi - mov r9, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm2, eax + mov r13, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 25], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 2 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 25], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 4 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 25], 5 + mov rsi, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 25], 6 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 25], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 9 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 2 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 3 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 24], 4 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 12 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 25], 13 mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 25], 14 + mov r15, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 25], 15 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 25], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 5 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 8 - mov r10, rbx - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 24], 9 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 24], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 24], 11 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 24], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 13 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 24], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 6 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 15 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 25] - vmovd xmm2, edi - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 25], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 3 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 25], 4 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 5 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 6 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 7 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 8 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 9 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 25], 11 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 12 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 13 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 25], 14 - mov r15, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 25], 15 - movzx edi, byte ptr [rdx + r14 + 25] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 1 - mov r9, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 2 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 25], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 25], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 25], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 12 - mov r13, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 25], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 25], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 8 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 25], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 25], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 576], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm3, byte ptr [rdx + rcx + 25], 15 - vinserti128 ymm0, ymm0, xmm2, 1 - vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill - mov r11, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 26] - vmovd xmm0, edi - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 1 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 26], 2 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rcx + 26], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 4 - mov rsi, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 26], 5 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 6 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 7 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 9 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 26], 10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 11 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 12 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 26], 13 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r14 + 26], 14 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 26], 15 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm3, byte ptr [rdi + rdx + 25], 15 + vinserti128 ymm0, ymm0, xmm2, 1 + vmovdqa ymmword ptr [rsp + 608], ymm0 # 32-byte Spill mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 26] - vmovd xmm1, edi + movzx eax, byte ptr [rdi + rax + 26] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 26], 1 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 26], 2 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 26], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r8 + 26], 5 + vpinsrb xmm0, xmm0, byte ptr [rdi + rsi + 26], 6 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 7 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 26], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 9 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 26], 11 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 26], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 13 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 26], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 26], 15 + mov r10, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 26] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 26], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 3 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 26], 4 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 26], 9 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 13 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 15 + mov rdx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 27] + vmovd xmm2, eax + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 27], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 2 mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 1 - mov rax, r9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 2 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 3 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 4 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 5 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 6 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 7 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 26], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 26], 9 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 26], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 26], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 15 - movzx edi, byte ptr [rdx + r11 + 27] - vmovd xmm2, edi - mov r11, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 27], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 27], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 3 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 27], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 5 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 27], 6 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 7 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 8 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 27], 10 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 27], 11 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 12 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 27], 14 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 27], 15 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 27] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 4 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 6 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 3 - mov r14, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 27], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 27], 9 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 27], 10 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 27], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 12 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 27], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 14 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 27], 15 + movzx eax, byte ptr [rdi + r10 + 27] + vmovd xmm3, eax + mov r10, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 27], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 27], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 7 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 8 mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 5 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 27], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 27], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 11 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 11 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 12 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 27], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 14 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 27], 14 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 640], ymm0 # 32-byte Spill vinserti128 ymm0, ymm3, xmm2, 1 vmovdqa ymmword ptr [rsp + 672], ymm0 # 32-byte Spill - mov r10, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + r10 + 28] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 28], 1 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 28], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 28], 3 - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 4 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 28], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + rsi + 28], 6 + movzx eax, byte ptr [rdi + rdx + 28] + vmovd xmm0, eax + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 1 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 28], 7 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 28], 8 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r8 + 28], 9 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 28], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r13 + 28], 11 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + r11 + 28], 12 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 28], 13 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rbx + 28], 14 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 28], 15 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 28] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 1 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 2 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 28], 4 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 5 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 28], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 7 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 8 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 9 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 10 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 28], 11 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 13 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 14 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 15 - movzx edi, byte ptr [rdx + r10 + 29] - vmovd xmm2, edi - mov r10, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 29], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 29], 2 - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 3 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 5 - mov r15, qword ptr [rsp + 240] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 29], 6 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 29], 9 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 29], 10 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 29], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 29], 12 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 29], 14 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 29], 15 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - movzx edi, byte ptr [rdx + r8 + 29] - vmovd xmm3, edi - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 3 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 4 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 29], 6 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 7 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 2 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 28], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 4 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 28], 5 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 28], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 28], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + r11 + 28], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + rbx + 28], 11 + mov r13, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 28], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 13 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 28], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r14 + 28], 15 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rdx + 28] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 2 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 28], 3 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 5 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 28], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 8 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 10 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 11 + mov r8, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 13 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 11 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 29], 13 - vpinsrb xmm4, xmm3, byte ptr [rdx + rcx + 29], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 14 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 29] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 29], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 29], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 7 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 29], 9 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 29], 10 + mov r12, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 29], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 12 + mov r13, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 29], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 14 + mov r9, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 29], 15 + movzx eax, byte ptr [rdi + rdx + 29] + vmovd xmm3, eax + mov rdx, qword ptr [rsp + 256] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 29], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 29], 6 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 8 + mov r11, r14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 29], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 29], 12 + mov r14, r8 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 29], 13 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm4, xmm3, byte ptr [rdi + r8 + 29], 14 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 704], ymm0 # 32-byte Spill - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm0, xmm4, byte ptr [rdx + rax + 29], 15 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm0, xmm4, byte ptr [rdi + rax + 29], 15 vinserti128 ymm0, ymm0, xmm2, 1 vmovdqa ymmword ptr [rsp + 736], ymm0 # 32-byte Spill - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 30] - vmovd xmm0, edi - vpinsrb xmm0, xmm0, byte ptr [rdx + r10 + 30], 1 - movzx edi, byte ptr [rdx + rcx + 31] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 31], 1 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 2 - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 3 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 4 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 5 - vpinsrb xmm0, xmm0, byte ptr [rdx + r15 + 30], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 31], 6 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 30] + vmovd xmm0, eax + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + r10 + 30], 1 + movzx eax, byte ptr [rdi + rbx + 31] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 31], 1 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 7 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 4 + vpinsrb xmm0, xmm0, byte ptr [rdi + r15 + 30], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 31], 5 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 7 mov r15, qword ptr [rsp + 272] # 8-byte Reload - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 9 - vpinsrb xmm0, xmm0, byte ptr [rdx + r12 + 30], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 31], 10 - vpinsrb xmm0, xmm0, byte ptr [rdx + r9 + 30], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 31], 11 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 8 mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 12 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 9 + vpinsrb xmm0, xmm0, byte ptr [rdi + rcx + 30], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 31], 10 + vpinsrb xmm0, xmm0, byte ptr [rdi + r12 + 30], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 31], 11 mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm0, xmm0, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm2, xmm1, byte ptr [rdx + rax + 31], 15 - mov rcx, r8 - movzx eax, byte ptr [rdx + r8 + 30] + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 12 + vpinsrb xmm0, xmm0, byte ptr [rdi + r13 + 30], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 31], 13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm0, xmm0, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 31], 14 + vpinsrb xmm0, xmm0, byte ptr [rdi + r9 + 30], 15 + vpinsrb xmm2, xmm1, byte ptr [rdi + r9 + 31], 15 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm1, eax - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 30], 1 - movzx eax, byte ptr [rdx + r8 + 31] + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm7, eax - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 31], 1 - mov r10, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 30], 2 - vpinsrb xmm7, xmm7, byte ptr [rdx + r10 + 31], 2 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 30], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 31], 4 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 30], 6 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 31], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 31], 1 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 2 + vpinsrb xmm7, xmm7, byte ptr [rdi + r10 + 31], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 5 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 7 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 11 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 30], 12 - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 31], 12 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 6 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 31], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 7 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 30], 9 + vpinsrb xmm7, xmm7, byte ptr [rdi + r11 + 31], 9 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 11 + mov rax, r14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 30], 12 + vpinsrb xmm7, xmm7, byte ptr [rdi + r14 + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 30], 13 + vpinsrb xmm7, xmm7, byte ptr [rdi + rsi + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 30], 14 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 31], 14 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm7, xmm7, byte ptr [rdi + rax + 31], 15 vinserti128 ymm0, ymm1, xmm0, 1 vmovdqa ymmword ptr [rsp + 320], ymm0 # 32-byte Spill vinserti128 ymm0, ymm7, xmm2, 1 @@ -66883,20 +68635,20 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vpandn ymm7, ymm7, ymm13 vmovdqa ymm3, ymmword ptr [rsp + 480] # 32-byte Reload vpcmpgtb ymm12, ymm3, ymm2 - vmovdqa ymm9, ymmword ptr [rip + .LCPI11_2] # ymm9 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - vpandn ymm12, ymm12, ymm9 + vmovdqa ymm8, ymmword ptr [rip + .LCPI11_2] # ymm8 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + vpandn ymm12, ymm12, ymm8 vpor ymm7, ymm12, ymm7 vpcmpgtb ymm12, ymm14, ymm2 - vmovdqa ymm4, ymmword ptr [rip + .LCPI11_3] # ymm4 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - vpandn ymm12, ymm12, ymm4 + vmovdqa ymm9, ymmword ptr [rip + .LCPI11_3] # ymm9 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + vpandn ymm12, ymm12, ymm9 vpor ymm7, ymm12, ymm7 vpcmpeqd ymm12, ymm12, ymm12 vpsubb ymm0, ymm0, ymm12 - vpcmpeqd ymm8, ymm8, ymm8 + vpcmpeqd ymm6, ymm6, ymm6 vpor ymm0, ymm0, ymm7 vpcmpgtb ymm7, ymm15, ymm2 - vmovdqa ymm6, ymmword ptr [rip + .LCPI11_4] # ymm6 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - vpandn ymm7, ymm7, ymm6 + vmovdqa ymm4, ymmword ptr [rip + .LCPI11_4] # ymm4 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + vpandn ymm7, ymm7, ymm4 vmovdqa ymm12, ymmword ptr [rsp + 448] # 32-byte Reload vpcmpgtb ymm12, ymm12, ymm2 vmovdqa ymm3, ymmword ptr [rip + .LCPI11_5] # ymm3 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] @@ -66919,17 +68671,17 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vpandn ymm12, ymm12, ymm13 vmovdqa ymm14, ymmword ptr [rsp + 1088] # 32-byte Reload vpcmpgtb ymm15, ymm14, ymm2 - vpandn ymm15, ymm15, ymm9 + vpandn ymm15, ymm15, ymm8 vpor ymm12, ymm12, ymm15 vmovdqa ymm14, ymmword ptr [rsp + 1024] # 32-byte Reload vpcmpgtb ymm15, ymm14, ymm2 - vpandn ymm15, ymm15, ymm4 + vpandn ymm15, ymm15, ymm9 vpor ymm12, ymm12, ymm15 - vpsubb ymm7, ymm7, ymm8 + vpsubb ymm7, ymm7, ymm6 vpor ymm7, ymm12, ymm7 vmovdqa ymm12, ymmword ptr [rsp + 1056] # 32-byte Reload vpcmpgtb ymm12, ymm12, ymm2 - vpandn ymm12, ymm12, ymm6 + vpandn ymm12, ymm12, ymm4 vmovdqa ymm14, ymmword ptr [rsp + 960] # 32-byte Reload vpcmpgtb ymm15, ymm14, ymm2 vpandn ymm15, ymm15, ymm3 @@ -66950,18 +68702,18 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vpandn ymm15, ymm15, ymm13 vmovdqa ymm14, ymmword ptr [rsp + 864] # 32-byte Reload vpcmpgtb ymm14, ymm14, ymm2 - vpandn ymm14, ymm14, ymm9 + vpandn ymm14, ymm14, ymm8 vpor ymm14, ymm15, ymm14 vmovdqa ymm15, ymmword ptr [rsp + 768] # 32-byte Reload vpcmpgtb ymm15, ymm15, ymm2 - vpandn ymm15, ymm15, ymm4 + vpandn ymm15, ymm15, ymm9 vpor ymm14, ymm14, ymm15 - vpsubb ymm7, ymm7, ymm8 + vpcmpeqd ymm15, ymm15, ymm15 + vpsubb ymm7, ymm7, ymm15 vpor ymm7, ymm14, ymm7 vmovdqa ymm14, ymmword ptr [rsp + 800] # 32-byte Reload vpcmpgtb ymm14, ymm14, ymm2 - vmovdqa ymm15, ymm6 - vpandn ymm14, ymm14, ymm6 + vpandn ymm14, ymm14, ymm4 vpcmpgtb ymm10, ymm10, ymm2 vpandn ymm10, ymm10, ymm3 vpor ymm10, ymm14, ymm10 @@ -66985,13 +68737,13 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vpor ymm5, ymm5, ymm6 vmovdqa ymm1, ymmword ptr [rsp + 704] # 32-byte Reload vpcmpgtb ymm3, ymm1, ymm2 - vpandn ymm3, ymm3, ymm4 + vpandn ymm3, ymm3, ymmword ptr [rip + .LCPI11_3] vpor ymm3, ymm5, ymm3 - vpsubb ymm5, ymm8, ymmword ptr [rip + .LCPI11_7] + vpsubb ymm5, ymm8, ymm15 vpor ymm3, ymm5, ymm3 vmovdqa ymm1, ymmword ptr [rsp + 736] # 32-byte Reload vpcmpgtb ymm4, ymm1, ymm2 - vpandn ymm4, ymm4, ymm15 + vpandn ymm4, ymm4, ymmword ptr [rip + .LCPI11_4] vmovdqa ymm1, ymmword ptr [rsp + 320] # 32-byte Reload vpcmpgtb ymm1, ymm1, ymm2 vpandn ymm1, ymm1, ymmword ptr [rip + .LCPI11_5] @@ -67019,1988 +68771,1989 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vmovdqu ymmword ptr [r15 + 4*rcx + 32], ymm4 vmovdqu ymmword ptr [r15 + 4*rcx], ymm1 add rcx, 32 - mov rbx, rcx + mov rax, rcx cmp rcx, qword ptr [rsp + 416] # 8-byte Folded Reload - jne .LBB11_86 -# %bb.87: - mov r14, qword ptr [rsp + 352] # 8-byte Reload - cmp r14, qword ptr [rsp + 416] # 8-byte Folded Reload - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - mov r13, qword ptr [rsp + 368] # 8-byte Reload - mov rdx, qword ptr [rsp + 360] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - jne .LBB11_88 - jmp .LBB11_91 -.LBB11_66: - and r14, -32 - mov rax, r14 + jne .LBB11_100 +# %bb.101: + mov rcx, qword ptr [rsp + 352] # 8-byte Reload + cmp rcx, qword ptr [rsp + 416] # 8-byte Folded Reload + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + mov r13, qword ptr [rsp + 360] # 8-byte Reload + mov rdi, qword ptr [rsp + 368] # 8-byte Reload + jne .LBB11_102 + jmp .LBB11_105 +.LBB11_72: + and rcx, -32 + mov rax, rcx shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 360], rax # 8-byte Spill - mov qword ptr [rsp + 384], r14 # 8-byte Spill - lea rax, [r15 + 4*r14] + add rax, rdi mov qword ptr [rsp + 368], rax # 8-byte Spill - vmovd xmm0, r11d + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r15 + 4*rcx] + mov qword ptr [rsp + 360], rax # 8-byte Spill + vmovd xmm0, r14d vpbroadcastb ymm0, xmm0 - xor ebx, ebx + xor eax, eax mov qword ptr [rsp + 272], r15 # 8-byte Spill .p2align 4, 0x90 -.LBB11_67: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 376], rbx # 8-byte Spill +.LBB11_73: # =>This Inner Loop Header: Depth=1 + mov rbx, rax + mov qword ptr [rsp + 376], rax # 8-byte Spill shl rbx, 5 mov rax, rbx or rax, 32 - mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 160], rax # 8-byte Spill mov rax, rbx or rax, 64 - mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill mov rax, rbx or rax, 96 mov qword ptr [rsp + 48], rax # 8-byte Spill mov rax, rbx or rax, 128 - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 264], rax # 8-byte Spill mov rax, rbx or rax, 160 - mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill mov rax, rbx or rax, 192 - mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill mov rax, rbx or rax, 224 - mov qword ptr [rsp + 136], rax # 8-byte Spill + mov qword ptr [rsp + 128], rax # 8-byte Spill mov rax, rbx or rax, 256 - mov qword ptr [rsp + 96], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill mov rax, rbx or rax, 288 mov qword ptr [rsp + 216], rax # 8-byte Spill mov rax, rbx - mov qword ptr [rsp + 240], rbx # 8-byte Spill or rax, 320 - mov qword ptr [rsp + 88], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill mov rax, rbx or rax, 512 - mov rcx, rax - movzx eax, byte ptr [rdx + rax] + mov rdx, rax + movzx eax, byte ptr [rdi + rax] vmovd xmm3, eax - movzx eax, byte ptr [rdx + rbx] + movzx eax, byte ptr [rdi + rbx] vmovd xmm4, eax - movzx eax, byte ptr [rdx + rcx + 1] + movzx eax, byte ptr [rdi + rdx + 1] vmovd xmm5, eax - movzx eax, byte ptr [rdx + rbx + 1] + movzx eax, byte ptr [rdi + rbx + 1] vmovd xmm10, eax - movzx eax, byte ptr [rdx + rcx + 2] + movzx eax, byte ptr [rdi + rdx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 480], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 2] + movzx eax, byte ptr [rdi + rbx + 2] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 448], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rcx + 3] + movzx eax, byte ptr [rdi + rdx + 3] vmovd xmm11, eax - movzx eax, byte ptr [rdx + rbx + 3] + movzx eax, byte ptr [rdi + rbx + 3] vmovd xmm8, eax - movzx eax, byte ptr [rdx + rcx + 4] + movzx eax, byte ptr [rdi + rdx + 4] vmovd xmm1, eax vmovdqa xmmword ptr [rsp + 512], xmm1 # 16-byte Spill - movzx eax, byte ptr [rdx + rbx + 4] + movzx eax, byte ptr [rdi + rbx + 4] vmovd xmm15, eax - movzx eax, byte ptr [rdx + rcx + 5] + movzx eax, byte ptr [rdi + rdx + 5] vmovd xmm14, eax - movzx eax, byte ptr [rdx + rbx + 5] + movzx eax, byte ptr [rdi + rbx + 5] vmovd xmm12, eax - movzx eax, byte ptr [rdx + rcx + 6] - mov qword ptr [rsp + 256], rcx # 8-byte Spill + movzx eax, byte ptr [rdi + rdx + 6] + mov qword ptr [rsp + 248], rdx # 8-byte Spill vmovd xmm13, eax - movzx eax, byte ptr [rdx + rbx + 6] + movzx eax, byte ptr [rdi + rbx + 6] vmovd xmm7, eax - movzx eax, byte ptr [rdx + rcx + 7] + movzx eax, byte ptr [rdi + rdx + 7] vmovd xmm2, eax - movzx eax, byte ptr [rdx + rbx + 7] + movzx eax, byte ptr [rdi + rbx + 7] vmovd xmm1, eax mov rax, rbx or rax, 352 - mov qword ptr [rsp + 80], rax # 8-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill mov rax, rbx or rax, 384 - mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill mov rax, rbx or rax, 416 - mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill mov rax, rbx or rax, 448 - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 80], rax # 8-byte Spill mov rax, rbx or rax, 480 - mov qword ptr [rsp + 104], rax # 8-byte Spill - mov rdi, rbx - or rdi, 544 - mov qword ptr [rsp + 200], rdi # 8-byte Spill - mov rax, rbx - or rax, 576 - mov r13, rax - mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 232], rax # 8-byte Spill + mov r15, rbx + or r15, 544 + mov qword ptr [rsp + 88], r15 # 8-byte Spill + mov r14, rbx + or r14, 576 + mov qword ptr [rsp + 184], r14 # 8-byte Spill mov r11, rbx or r11, 608 - mov qword ptr [rsp + 168], r11 # 8-byte Spill - mov r14, rbx - or r14, 640 - mov qword ptr [rsp + 128], r14 # 8-byte Spill + mov qword ptr [rsp + 224], r11 # 8-byte Spill mov r10, rbx - or r10, 672 - mov qword ptr [rsp + 160], r10 # 8-byte Spill + or r10, 640 + mov qword ptr [rsp + 72], r10 # 8-byte Spill mov rax, rbx - or rax, 704 + or rax, 672 + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov r9, rbx + or r9, 704 + mov qword ptr [rsp + 56], r9 # 8-byte Spill + mov rax, rbx + or rax, 736 + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov rax, rbx + or rax, 768 + mov r13, rax + mov qword ptr [rsp + 192], rax # 8-byte Spill + mov rax, rbx + or rax, 800 + mov r12, rax mov qword ptr [rsp + 152], rax # 8-byte Spill mov r8, rbx - or r8, 736 - mov qword ptr [rsp + 120], r8 # 8-byte Spill - mov r15, rbx - or r15, 768 - mov qword ptr [rsp + 192], r15 # 8-byte Spill + or r8, 832 + mov qword ptr [rsp + 240], r8 # 8-byte Spill + mov rcx, rbx + or rcx, 864 + mov qword ptr [rsp + 200], rcx # 8-byte Spill mov rax, rbx - or rax, 800 - mov qword ptr [rsp + 320], rax # 8-byte Spill - mov r9, rbx - or r9, 832 - mov qword ptr [rsp + 184], r9 # 8-byte Spill - mov r12, rbx - or r12, 864 - mov qword ptr [rsp + 176], r12 # 8-byte Spill + or rax, 896 + mov qword ptr [rsp + 112], rax # 8-byte Spill mov rsi, rbx - or rsi, 896 - mov qword ptr [rsp + 264], rsi # 8-byte Spill - mov rcx, rbx - or rcx, 928 - mov qword ptr [rsp + 232], rcx # 8-byte Spill + or rsi, 928 + mov qword ptr [rsp + 208], rsi # 8-byte Spill mov rax, rbx + mov rdx, rbx + mov qword ptr [rsp + 256], rbx # 8-byte Spill or rax, 960 - mov qword ptr [rsp + 112], rax # 8-byte Spill - or rbx, 992 - mov qword ptr [rsp + 248], rbx # 8-byte Spill - vpinsrb xmm9, xmm3, byte ptr [rdx + rdi], 1 - vpinsrb xmm3, xmm9, byte ptr [rdx + r13], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx], 15 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12], 1 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14], 2 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11], 3 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8], 4 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9], 5 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx], 6 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi], 7 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax], 10 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10], 11 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx], 12 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx], 14 - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13], 15 - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 4 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 6 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 7 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 1], 8 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 9 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 10 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 11 - mov rcx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 12 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 13 + mov qword ptr [rsp + 120], rax # 8-byte Spill + or rdx, 992 + mov qword ptr [rsp + 96], rdx # 8-byte Spill + vpinsrb xmm9, xmm3, byte ptr [rdi + r15], 1 + vpinsrb xmm3, xmm9, byte ptr [rdi + r14], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10], 4 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9], 6 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 11 mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 14 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 1], 15 - vpinsrb xmm6, xmm10, byte ptr [rdx + r12 + 1], 1 - vpinsrb xmm6, xmm6, byte ptr [rdx + r14 + 1], 2 - vpinsrb xmm6, xmm6, byte ptr [rdx + r11 + 1], 3 - vpinsrb xmm6, xmm6, byte ptr [rdx + r8 + 1], 4 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 1], 5 - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 1], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 1], 7 - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 1], 8 - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 1], 9 - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + r10 + 1], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 13 - mov r11, rax - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 1], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx], 15 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14], 1 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10], 2 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12], 3 + mov r8, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8], 4 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx], 5 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9], 6 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11], 7 + mov r15, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15], 8 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax], 9 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx], 10 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx], 11 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi], 12 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13], 13 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi], 14 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi], 15 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 1 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 2 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 3 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 4 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 5 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 6 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 7 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 8 + mov rsi, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 9 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 10 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 13 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 14 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 1], 15 + vpinsrb xmm6, xmm10, byte ptr [rdi + r14 + 1], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 1], 2 + mov r14, r10 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 1], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + r8 + 1], 4 + mov rsi, r8 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 1], 5 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 1], 6 + mov r10, r9 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 1], 7 + vpinsrb xmm6, xmm6, byte ptr [rdi + r15 + 1], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 1], 9 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 1], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 1], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 1], 12 + vpinsrb xmm6, xmm6, byte ptr [rdi + r13 + 1], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 1], 14 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1216], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm6, byte ptr [rdx + rax + 1], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm9, edi + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm6, byte ptr [rdi + rax + 1], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm9, eax vinserti128 ymm3, ymm3, xmm5, 1 vmovdqa ymmword ptr [rsp + 544], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 8] - vmovd xmm10, edi - mov r9, qword ptr [rsp + 200] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 8] + vmovd xmm10, eax vmovdqa xmm3, xmmword ptr [rsp + 480] # 16-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 2], 1 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 2], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 3 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 2], 4 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 5 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 2], 6 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 2 + mov r15, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 2], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 4 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 2], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 6 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 2], 7 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 2], 8 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 2], 9 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 12 + mov r13, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 2], 13 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 8 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 9 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 2], 10 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 2], 11 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 2], 12 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 2], 13 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 2], 14 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 2], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 2], 15 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload vmovdqa xmm4, xmmword ptr [rsp + 448] # 16-byte Reload - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 2], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 2], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 3 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 2], 8 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 2], 1 + mov r12, r14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 2], 2 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 2], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 4 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 2], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 2], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 2], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 2], 8 + mov r10, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 2], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 10 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 11 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 12 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 13 mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 11 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 2], 13 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 2], 14 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 2], 15 - vpinsrb xmm5, xmm11, byte ptr [rdx + r9 + 3], 1 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 3], 2 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 3 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 3], 4 - mov r11, r15 - mov r14, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 3], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 3], 6 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 7 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 3], 8 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 3], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + r12 + 3], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 3], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 3], 12 - mov r13, rbx - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 3], 13 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 3], 14 - mov r10, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 3], 15 - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm6, xmm8, byte ptr [rdx + rcx + 3], 1 - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 3 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 14 + mov rsi, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 2], 15 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm11, byte ptr [rdi + rsi + 3], 1 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 3], 3 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 5 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 3], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + r11 + 3], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 3], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 3], 9 + mov r9, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 3], 10 + mov rbx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 3], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 12 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 3], 13 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 3], 14 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 3], 15 + vpinsrb xmm6, xmm8, byte ptr [rdi + rcx + 3], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 3], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 3], 3 + mov r11, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 3], 4 + vpinsrb xmm6, xmm6, byte ptr [rdi + rdx + 3], 5 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r12 + 3], 6 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 3], 7 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 8 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 3], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 5 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 3], 6 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 7 - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 3], 8 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 3], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 3], 13 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 3], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 480], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm6, byte ptr [rdx + rax + 3], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 9] - vmovd xmm8, edi - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 3], 15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm3, xmm6, byte ptr [rdi + rax + 3], 14 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm8, eax + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 3], 15 vinserti128 ymm3, ymm3, xmm5, 1 vmovdqa ymmword ptr [rsp + 448], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 9] - vmovd xmm11, edi + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 9] + vmovd xmm11, eax vmovdqa xmm3, xmmword ptr [rsp + 512] # 16-byte Reload - mov r8, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 4], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 2 - mov rbx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 4], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 4], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 4], 5 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 2 + mov r10, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 4], 3 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 4], 4 + mov r8, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 4], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 4], 6 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 4], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 8 mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 6 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 4], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 4], 8 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 9 - mov r15, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 4], 10 - mov r14, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 4], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 4], 12 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 13 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 4], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 4], 15 - mov r10, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm15, byte ptr [rdx + r10 + 4], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 4], 11 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 4], 12 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 4], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 4], 14 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 4], 15 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm15, byte ptr [rdi + r13 + 4], 1 + mov r14, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 4], 2 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 3 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 4], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 4], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 4], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 4], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 4], 7 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 4], 8 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 4], 9 + mov r12, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 4], 10 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 4], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 4], 12 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 4], 13 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 4], 14 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 4], 15 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm14, byte ptr [rdi + rbx + 5], 1 + mov rbx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 5], 2 + vpinsrb xmm5, xmm5, byte ptr [rdi + r10 + 5], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 4 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 5], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 5], 6 + mov r8, r15 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 7 + mov rsi, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 5], 8 + mov r15, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 5], 9 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 10 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 5], 12 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 5], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 5], 15 + vpinsrb xmm6, xmm12, byte ptr [rdi + r13 + 5], 1 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 5], 2 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 5], 3 + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 5], 4 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 5], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 5], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 7 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 5], 8 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 4], 6 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 4], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 4], 9 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 4], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 13 mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 4], 11 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 4], 12 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 4], 13 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 4], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 4], 15 - vpinsrb xmm5, xmm14, byte ptr [rdx + r8 + 5], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 5], 2 - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 3 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 4 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 5], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 5], 6 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 5], 7 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 8 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 5], 10 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 5], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 5], 12 - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 5], 13 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 5], 14 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 5], 15 - vpinsrb xmm6, xmm12, byte ptr [rdx + r10 + 5], 1 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 5], 2 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 5], 3 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 5], 4 - mov rbx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 5], 5 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 5], 6 - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 5], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 5], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 5], 9 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 5], 10 - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 5], 11 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 5], 12 - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 5], 13 - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 5], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 5], 14 vinserti128 ymm14, ymm4, xmm3, 1 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm6, byte ptr [rdx + rax + 5], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm12, edi + vpinsrb xmm4, xmm6, byte ptr [rdi + r12 + 5], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm12, eax vinserti128 ymm3, ymm4, xmm5, 1 vmovdqa ymmword ptr [rsp + 512], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 10] - vmovd xmm4, edi - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm13, byte ptr [rdx + r15 + 6], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 4 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 6], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 6 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 6], 7 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 8 - mov r8, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 6], 9 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 10 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 10] + vmovd xmm4, eax + mov r11, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm5, xmm13, byte ptr [rdi + r11 + 6], 1 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rcx + 6], 2 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 6], 3 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 6], 4 mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 6], 11 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 6], 12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 6], 13 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 6], 14 - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 6], 15 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm6, xmm7, byte ptr [rdx + r11 + 6], 1 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r14 + 6], 2 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rbx + 6], 3 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 6], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 6], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 6], 6 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 6], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 5 + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 7 + vpinsrb xmm5, xmm5, byte ptr [rdi + rsi + 6], 8 + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 6], 9 + mov r15, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r15 + 6], 10 + mov r8, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 6], 11 + vpinsrb xmm5, xmm5, byte ptr [rdi + r9 + 6], 12 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 6], 13 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 6], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 6], 8 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rax + 6], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 6], 10 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r9 + 6], 11 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 6], 12 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 6], 13 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 6], 14 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 6], 15 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 7], 1 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 2 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 3 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 6], 15 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm7, byte ptr [rdi + rax + 6], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 6], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 6], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 6], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 6], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 6], 6 mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 4 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 5 - mov r15, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 7], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 7 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 7], 9 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 7], 10 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 6], 7 + mov rsi, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 6], 8 + mov r10, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 6], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 6], 10 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 6], 11 + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 6], 12 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 6], 13 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 6], 14 + mov rbx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rbx + 6], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 7], 1 + mov rbx, r11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 7], 4 mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 7], 12 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 7], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 7], 14 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 7], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 7], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 7], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 7], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 5 mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 7], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 6 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 7 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 8 + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 7], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 7], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 7], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 7], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 7], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 14 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 7], 15 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 1 mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 7], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 7], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 7], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 7], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 2 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 7], 3 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 7], 4 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 7], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 6 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 7], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 9 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 7], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 7], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 7], 13 vinserti128 ymm3, ymm6, xmm5, 1 vmovdqa ymmword ptr [rsp + 1184], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm5, xmm1, byte ptr [rdx + rax + 7], 14 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 11] - vmovd xmm1, edi - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 7], 15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm5, xmm1, byte ptr [rdi + rax + 7], 14 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm1, eax + mov r14, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r14 + 7], 15 vinserti128 ymm2, ymm5, xmm2, 1 vmovdqa ymmword ptr [rsp + 1152], ymm2 # 32-byte Spill + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 11] + vmovd xmm2, eax + mov r15, rbx + vpinsrb xmm5, xmm9, byte ptr [rdi + rbx + 8], 1 + mov rdx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rdx + 8], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 3 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r8 + 8], 4 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rbx + 8], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 8 + mov r12, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + r12 + 8], 9 mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 11] - vmovd xmm2, edi + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 10 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm5, xmm9, byte ptr [rdx + rax + 8], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rcx + 8], 3 - mov r10, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r10 + 8], 4 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rbx + 8], 5 - vpinsrb xmm5, xmm5, byte ptr [rdx + r15 + 8], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 12 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 13 mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + rax + 8], 7 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r9 + 8], 8 - mov rax, r8 - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 8], 9 - vpinsrb xmm5, xmm5, byte ptr [rdx + rsi + 8], 10 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r8 + 8], 11 - mov r11, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r11 + 8], 12 - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 8], 13 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r13 + 8], 14 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm5, xmm5, byte ptr [rdx + r14 + 8], 15 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm6, xmm10, byte ptr [rdx + rsi + 8], 1 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 2 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 3 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r15 + 8], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rdi + 8], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 6 + vpinsrb xmm5, xmm5, byte ptr [rdi + rax + 8], 14 + vpinsrb xmm5, xmm5, byte ptr [rdi + r13 + 8], 15 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm6, xmm10, byte ptr [rdi + r13 + 8], 1 mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 7 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 8 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 10 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 11 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 12 - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 8], 13 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + r12 + 8], 14 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm6, xmm6, byte ptr [rdx + rsi + 8], 15 - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm7, xmm8, byte ptr [rdx + rsi + 9], 1 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 9], 2 - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 3 - mov r12, rcx - vpinsrb xmm7, xmm7, byte ptr [rdx + r10 + 9], 4 - vpinsrb xmm7, xmm7, byte ptr [rdx + rbx + 9], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rsi + 9], 6 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 7 - vpinsrb xmm7, xmm7, byte ptr [rdx + r9 + 9], 8 - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 9 - mov rcx, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rcx + 9], 10 - vpinsrb xmm7, xmm7, byte ptr [rdx + r8 + 9], 11 - vpinsrb xmm7, xmm7, byte ptr [rdx + r11 + 9], 12 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm7, xmm7, byte ptr [rdx + rax + 9], 13 - vpinsrb xmm7, xmm7, byte ptr [rdx + r13 + 9], 14 - vpinsrb xmm7, xmm7, byte ptr [rdx + r14 + 9], 15 - mov r13, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm3, xmm11, byte ptr [rdx + r13 + 9], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 9], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 9], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 6 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 9], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 8 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 11 + vpinsrb xmm6, xmm6, byte ptr [rdi + rsi + 8], 2 + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 8], 3 + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 8], 4 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + rax + 8], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 8], 6 + vpinsrb xmm6, xmm6, byte ptr [rdi + r9 + 8], 7 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 8], 8 + mov rcx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 8], 9 + mov r9, r10 + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 8], 10 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r11 + 8], 11 + mov r10, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + r10 + 8], 12 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 8], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm6, xmm6, byte ptr [rdi + rcx + 8], 14 + vpinsrb xmm6, xmm6, byte ptr [rdi + r14 + 8], 15 + vpinsrb xmm7, xmm8, byte ptr [rdi + r15 + 9], 1 + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 2 + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 3 + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 4 + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 5 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 6 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rbx + 9], 7 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r8 + 9], 8 + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 9 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 10 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r15 + 9], 11 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 12 + mov rdx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + rdx + 9], 14 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm7, xmm7, byte ptr [rdi + r12 + 9], 15 + vpinsrb xmm3, xmm11, byte ptr [rdi + r13 + 9], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 9], 2 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 9], 3 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 9], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 8 + mov r13, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 9], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 9], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 9], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 9], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 9], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 9], 14 vinserti128 ymm5, ymm6, xmm5, 1 vmovdqa ymmword ptr [rsp + 1120], ymm5 # 32-byte Spill - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 9], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm5, edi + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 9], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm5, eax vinserti128 ymm3, ymm3, xmm7, 1 vmovdqa ymmword ptr [rsp + 1088], ymm3 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 12] - vmovd xmm6, edi - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm12, byte ptr [rdx + r10 + 10], 1 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 10], 2 - mov r9, r12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 10], 3 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 10], 4 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 10], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 10], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 7 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 10], 10 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 10], 11 - mov r14, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 10], 12 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 13 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 10], 14 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 10], 15 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 10], 1 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 10], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 10], 3 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 10], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 5 - mov r13, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 10], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 8 - mov rcx, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 10], 9 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 12] + vmovd xmm6, eax mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 10 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 10], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 14 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 10], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 11], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 11], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 11], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 11], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 11], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 11], 6 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 7 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 8 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 9 + vpinsrb xmm3, xmm12, byte ptr [rdi + rax + 10], 1 mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 11], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 11], 12 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 11], 13 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 11], 14 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 11], 15 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 11], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 10], 4 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 10], 5 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 10], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 10], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 10], 8 + mov r14, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 10], 9 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 10], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 10], 12 + mov r15, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 10], 13 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 10], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 10], 15 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 10], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 2 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 11], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 11], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 11], 6 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 7 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 11], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 9 - mov r13, rcx - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 11], 11 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 3 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 10], 4 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 10], 5 + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 6 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 7 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 9 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 10 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 10], 11 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 12 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 10], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 14 + mov rcx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 10], 15 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 11], 1 + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 2 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 3 mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 11], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 11], 6 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 7 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 11], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 11], 10 + mov rcx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 11], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 11], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 11], 14 + mov r11, r9 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 11], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 11], 1 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 11], 2 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 11], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 5 + mov r12, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 11], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 7 + mov r15, rax + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 8 + mov r9, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 11], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 11], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 12 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 11], 13 vinserti128 ymm3, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 1056], ymm3 # 32-byte Spill - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 14 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 13] - vmovd xmm3, edi - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 11], 15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 14 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 11], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 1024], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 13] - vmovd xmm1, edi - mov rcx, r10 - vpinsrb xmm2, xmm5, byte ptr [rdx + r10 + 12], 1 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 12], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 12], 3 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 12], 4 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 12], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 6 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 7 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 12], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 9 - mov r10, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 12], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 11 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 12 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 12], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 12], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 12], 15 - vpinsrb xmm4, xmm6, byte ptr [rdx + rbx + 12], 1 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 12], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 12], 3 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 12], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 12], 5 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 12], 6 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 12], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 12], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 12], 9 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r11 + 12], 10 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 12], 11 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 12], 12 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 12], 13 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 12], 14 - mov r13, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 12], 15 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 6 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 13], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 13], 8 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 13] + vmovd xmm1, eax + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm5, byte ptr [rdi + r14 + 12], 1 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 12], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 6 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 12], 7 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 12], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 9 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 12], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 12 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 12], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 12], 14 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 12], 15 + mov r11, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm6, byte ptr [rdi + r11 + 12], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 12], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 12], 3 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 4 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 12], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 12], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 12], 7 mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 13], 10 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 11 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 13], 12 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 13 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 13], 14 - mov r8, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 13], 15 - mov r10, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 13], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 13], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 12], 9 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 12], 10 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 12], 11 + mov r15, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 12], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 12], 13 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 12], 14 + mov r13, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 12], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 2 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 13], 3 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 4 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 5 mov rsi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 4 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 13], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 13], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 8 - mov r14, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 13], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 13], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 13], 13 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 8 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 13], 9 + mov rdx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 10 + mov rdx, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 13], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 12 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 13 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 13], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 13], 15 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 1 + mov rsi, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 13], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 3 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 13], 5 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 13], 6 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 13], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 8 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 13], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 13], 11 + mov rbx, r9 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 13], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 13], 14 vinserti128 ymm2, ymm4, xmm2, 1 vmovdqa ymmword ptr [rsp + 992], ymm2 # 32-byte Spill - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 13], 15 - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 14] - vmovd xmm2, edi + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 13], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm2, eax vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 960], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 14] - vmovd xmm1, edi - mov rsi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 14], 1 - mov rax, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 4 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 14] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 14], 1 + mov r15, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 14], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 14], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 14], 4 + mov r9, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 14], 5 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 14], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 14], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 14], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 14], 9 + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 14], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 14], 11 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 14], 12 + mov r12, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 14], 13 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 14], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 14], 15 mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 5 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 14], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 14], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 3 + mov r14, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 14], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 5 + mov rdx, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 14], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 7 + mov r11, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 14], 8 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 11 + mov rbx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 14], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 14], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 14], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 15] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 15], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 15], 6 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 15], 7 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 8 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 9 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 10 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 14], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 14], 12 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 14], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 14], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 14], 15 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 14], 1 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 3 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 5 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 14], 6 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 14], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 11 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 14], 12 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 14], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 14], 14 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 14], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 15] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 1 - mov r10, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 15], 2 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 3 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 15], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 15], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 15], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 15], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 15], 14 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 15], 15 + mov r10, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + r10 + 15] + vmovd xmm4, eax mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 6 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 15], 7 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 15], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 15], 9 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 15], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 11 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 15], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 15], 13 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 14 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 15], 15 - mov rsi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rsi + 15] - vmovd xmm4, edi - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 2 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 3 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 15], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 15], 1 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 15], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 15], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 15], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 15], 10 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 15], 11 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 15], 12 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 15], 13 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 15], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 15], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 15], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 15], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 15], 8 + mov r14, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 15], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 15], 10 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 15], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 15], 12 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 15], 13 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 15], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 15], 15 vinserti128 ymm1, ymm1, xmm2, 1 vmovdqa ymmword ptr [rsp + 896], ymm1 # 32-byte Spill vinserti128 ymm1, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 928], ymm1 # 32-byte Spill - movzx edi, byte ptr [rdx + rcx + 16] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 16], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 4 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 6 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 16], 8 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 9 - mov r12, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r12 + 16], 10 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 16], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 13 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 16], 14 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 16], 15 - movzx edi, byte ptr [rdx + rsi + 16] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 16], 1 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 16], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 16], 3 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 16], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 16], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 16], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 16], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 16], 8 - mov rsi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 16], 9 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 16] + vmovd xmm1, eax + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 16], 1 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 16], 2 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 16], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 7 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 16], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 9 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 12 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 16], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 16], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 16], 15 + movzx eax, byte ptr [rdi + r10 + 16] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 16], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 2 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 16], 3 + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 16], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 16], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 16], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 16], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 16], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 16], 15 + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 17] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 1 + mov r14, r13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 17], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 3 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 17], 4 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 17], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 7 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 17], 8 + mov rdx, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 17], 9 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 10 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 17], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 17], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 17], 13 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 17], 14 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 17], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 17] + vmovd xmm4, eax + mov r15, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 17], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 17], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 17], 4 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 17], 5 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 17], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 8 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 17], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 17], 14 + vinserti128 ymm1, ymm2, xmm1, 1 + vmovdqa ymmword ptr [rsp + 864], ymm1 # 32-byte Spill + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm4, byte ptr [rdi + rax + 17], 15 + vinserti128 ymm1, ymm1, xmm3, 1 + vmovdqa ymmword ptr [rsp + 832], ymm1 # 32-byte Spill + movzx eax, byte ptr [rdi + rbx + 18] + vmovd xmm1, eax mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 16], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 16], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 16], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 16], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 2 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 18], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 18], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 18], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 6 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 16], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 16], 15 - mov r8, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + r8 + 17] - vmovd xmm3, edi - mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 1 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 17], 2 - mov r11, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 17], 3 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 17], 4 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 6 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 7 mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 8 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 17], 10 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 8 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 18], 9 + mov r14, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 18], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 18], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 12 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 18], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 18], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 18], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 18] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 18], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 18], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 18], 3 mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 12 - mov rax, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 17], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 18], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 18], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 18], 6 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 18], 7 + mov r10, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 18], 8 + mov r11, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 18], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 18], 10 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 18], 11 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 18], 12 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 18], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 18], 14 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 18], 15 mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 17], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 17] - vmovd xmm4, edi - mov r15, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 17], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 17], 2 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 17], 3 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 17], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 17], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 17], 6 - mov r14, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 17], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 17], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 17], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 17], 10 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 17], 11 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 17], 12 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 17], 13 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 17], 14 - vinserti128 ymm1, ymm2, xmm1, 1 - vmovdqa ymmword ptr [rsp + 864], ymm1 # 32-byte Spill - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm4, byte ptr [rdx + rsi + 17], 15 - vinserti128 ymm1, ymm1, xmm3, 1 - vmovdqa ymmword ptr [rsp + 832], ymm1 # 32-byte Spill - movzx edi, byte ptr [rdx + r8 + 18] - vmovd xmm1, edi - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 18], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 18], 3 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 4 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 18], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 7 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 18], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 9 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 11 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 12 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 13 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 18], 14 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 18], 15 - mov rax, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 18] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 18], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 18], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 18], 3 + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 1 + mov r13, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 19], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 3 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 19], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 5 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 18], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 18], 5 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 18], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 18], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 18], 8 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 18], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 18], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 18], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 18], 12 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 18], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 6 mov r8, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 18], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 18], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 19] - vmovd xmm3, edi - mov r10, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 19], 1 - mov rsi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 19], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 19], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 6 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 19], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 19], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 9 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 10 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 19], 11 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 12 - mov r13, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 19], 13 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 14 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 19], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 19] - vmovd xmm4, edi - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 1 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 3 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 19], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 19], 6 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 19], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 19], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 19], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 19], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 19], 7 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 19], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 19], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 12 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 19], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 19] + vmovd xmm4, eax + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 3 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 4 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 19], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 19], 13 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 19], 14 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 19], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 19], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 19], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 19], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 19], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 19], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 19], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 19], 13 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 19], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 19], 15 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 768], ymm1 # 32-byte Spill vinserti128 ymm1, ymm4, xmm3, 1 vmovdqa ymmword ptr [rsp + 800], ymm1 # 32-byte Spill - movzx edi, byte ptr [rdx + rcx + 20] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 2 - mov r10, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 20], 3 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 20], 4 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 20], 5 - mov r8, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 20], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 7 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 20], 8 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 20], 9 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 20], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 20], 11 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 20], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 20], 13 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 20], 14 mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 20], 15 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 20] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 1 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 20], 2 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 20], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 20], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 6 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 7 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 20], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 11 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 12 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 13 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 14 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 20], 15 - mov r12, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + r12 + 21] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 21], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 21], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 21], 6 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 21], 7 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 8 - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 9 - mov rsi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 21], 10 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r15 + 21], 11 - mov rbx, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 21], 12 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 21], 13 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 21], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 21], 15 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 21] - vmovd xmm4, edi - mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 21], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 21], 3 + movzx eax, byte ptr [rdi + r11 + 20] + vmovd xmm1, eax + mov r14, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 20], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 4 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 20], 5 mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 4 - mov r10, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 21], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 20], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 20], 8 + mov r8, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 20], 9 + mov r10, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 20], 10 + mov rsi, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 20], 11 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 20], 12 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 20], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 20], 14 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 20], 15 + mov rbx, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 20] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 1 mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 21], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 3 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 8 mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 9 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 21], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 11 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 21], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 20], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 20], 15 + movzx eax, byte ptr [rdi + r11 + 21] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 2 + mov r14, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 21], 3 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 4 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 21], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 6 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 21], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 21], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 21], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 21], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 21], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 21], 12 + mov r8, r9 + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 21], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 21], 14 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 21], 15 + movzx eax, byte ptr [rdi + rbx + 21] + vmovd xmm4, eax + mov r10, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 21], 1 + mov rcx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 21], 2 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 21], 3 + mov rdx, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 21], 4 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 21], 5 + mov r9, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 21], 6 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 21], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 8 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 9 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 21], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 13 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 21], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 704], ymm1 # 32-byte Spill - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm1, xmm4, byte ptr [rdx + rcx + 21], 15 + mov r11, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm4, byte ptr [rdi + r11 + 21], 15 vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 736], ymm1 # 32-byte Spill - movzx edi, byte ptr [rdx + r12 + 22] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 2 - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 4 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 5 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 22], 7 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 22], 8 - mov rcx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 22], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 22], 12 - mov rsi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 22], 13 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 14 - mov rcx, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 22], 15 - movzx edi, byte ptr [rdx + r11 + 22] - vmovd xmm2, edi - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 22], 1 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 22], 2 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 22], 3 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 22], 3 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 22], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 5 mov r13, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 22], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 22], 5 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 22], 6 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 22], 7 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 22], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 22], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 22], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 22], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 22], 12 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 22], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 22], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r13 + 22], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 9 + mov rax, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 12 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 22], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 22], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 22] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 22], 1 + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 22], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 22], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 22], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 22], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 22], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 22], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 22], 8 + mov rbx, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 22], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 22], 10 mov rax, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 22], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 23] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 1 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 23], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 4 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 23], 5 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 23], 6 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 23], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 23], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 9 - mov r9, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 23], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 11 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 23], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 13 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 23], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 23], 15 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 23] - vmovd xmm4, edi - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 23], 1 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 23], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 23], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 23], 4 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 23], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 23], 6 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 23], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 23], 8 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 23], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 23], 10 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r13 + 23], 11 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 23], 12 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 23], 13 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 23], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 23], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 22], 11 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 22], 12 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 22], 13 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 22], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 22], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 1 + mov rsi, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 23], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 23], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 23], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 7 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 23], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 9 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 23], 10 + mov r10, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 23], 11 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 23], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 23], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 23], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 23] + vmovd xmm4, eax + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 2 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 23], 3 + mov r13, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 23], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 23], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 23], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 23], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 23], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 23], 14 + mov r12, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 23], 15 vinserti128 ymm11, ymm2, xmm1, 1 vinserti128 ymm12, ymm4, xmm3, 1 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 1 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 24], 2 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 24], 3 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 5 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 24], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 24], 10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 24], 11 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 24], 12 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 24], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 24], 15 mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 24] - vmovd xmm1, edi + movzx eax, byte ptr [rdi + rax + 24] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 1 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 24], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 24], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 24], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 5 + mov rsi, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 24], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 7 + mov rcx, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rcx + 24], 8 + mov r8, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 24], 9 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 24], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 24], 13 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 24], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 24], 15 + mov rax, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm3, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 5 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 25], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 7 + mov rbx, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 25], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 9 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 25], 10 mov rax, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r8 + 24], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 3 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 25], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 25], 14 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 25], 15 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rax + 25] + vmovd xmm4, eax + mov r14, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 25], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 25], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 25], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 25], 6 mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 4 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 24], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 24], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 24], 7 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 24], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 9 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 24], 10 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 24], 11 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 12 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 13 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 14 - mov rdi, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 24], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 24] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 24], 1 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 24], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 24], 3 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 24], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 24], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 24], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 24], 7 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 24], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 24], 9 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 24], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 24], 11 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 24], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 24], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 24], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + rcx + 25], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + r8 + 25], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 25], 10 mov r10, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 24], 15 - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rcx + 25] - vmovd xmm3, edi - mov r9, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 25], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 2 - mov r13, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 25], 3 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 4 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 5 - mov rsi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 25], 6 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 8 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 9 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 10 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 25], 11 - mov rax, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 25], 12 - mov rcx, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 25], 13 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 25], 14 - mov r11, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 25], 15 - mov rdi, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 25] - vmovd xmm4, edi - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 25], 1 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 25], 2 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 25], 3 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 25], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 25], 5 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 25], 6 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 25], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 25], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 25], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 25], 10 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 25], 11 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 25], 12 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 25], 13 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 25], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 25], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 25], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 25], 14 vinserti128 ymm10, ymm2, xmm1, 1 - vpinsrb xmm1, xmm4, byte ptr [rdx + r10 + 25], 15 + mov r8, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm1, xmm4, byte ptr [rdi + r8 + 25], 15 vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 416], ymm1 # 32-byte Spill - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 26] - vmovd xmm1, edi - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 1 - mov rdi, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 2 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 26], 3 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 26], 4 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 26], 5 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 6 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 7 - mov rsi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 8 - mov rsi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 9 - mov r13, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 26], 10 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 26], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 26], 12 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 26], 13 - mov rax, rcx - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 26], 14 - mov rsi, r11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 26], 15 - mov r11, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + r11 + 26] - vmovd xmm2, edi - mov rcx, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 26], 1 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r8 + 26], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 26], 3 - mov r10, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 26], 4 - mov rcx, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 26], 5 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 26], 6 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 26], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 26], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 26], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 26], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 26], 11 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 26], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r14 + 26], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + rbx + 26], 14 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 26], 15 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rdi + 27] - vmovd xmm3, edi - mov rdi, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 1 - mov r14, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 27], 2 - mov rdi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 27], 4 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 5 - mov rdi, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 7 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 27], 8 - mov rbx, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 27], 9 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 27], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 11 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 27], 12 - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 13 + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 26] + vmovd xmm1, eax + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 26], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 2 + mov rsi, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 26], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 26], 8 + mov r9, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 26], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + r11 + 26], 10 + mov r15, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r15 + 26], 11 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 27], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 27], 15 - movzx edi, byte ptr [rdx + r11 + 27] - vmovd xmm4, edi - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 27], 1 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 27], 2 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 27], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + r10 + 27], 4 - mov rsi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 27], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rsi + 27], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 27], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 27], 8 - mov r12, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 27], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 27], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 27], 11 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 27], 12 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 27], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 27], 14 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rcx + 27], 15 - vinserti128 ymm1, ymm2, xmm1, 1 - vmovdqa ymmword ptr [rsp + 576], ymm1 # 32-byte Spill - vinserti128 ymm1, ymm4, xmm3, 1 - vmovdqa ymmword ptr [rsp + 608], ymm1 # 32-byte Spill - mov r8, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + r8 + 28] - vmovd xmm1, edi - mov rcx, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 28], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 28], 2 - mov rsi, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 28], 3 - mov r10, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 28], 4 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 28], 5 - mov r13, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 28], 6 - mov rdi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 7 - vpinsrb xmm1, xmm1, byte ptr [rdx + r9 + 28], 8 - vpinsrb xmm1, xmm1, byte ptr [rdx + rbx + 28], 9 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 10 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 11 - mov rdi, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 12 - mov rdi, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rdi + 28], 13 - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 28], 14 - mov r14, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r14 + 28], 15 - mov rbx, qword ptr [rsp + 240] # 8-byte Reload - movzx edi, byte ptr [rdx + rbx + 28] - vmovd xmm2, edi + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 12 mov rax, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 2 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 26], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + r12 + 26], 15 + mov r12, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + r12 + 26] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 26], 1 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 26], 2 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 3 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 26], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 26], 4 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 26], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 26], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 26], 7 + mov r13, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 26], 8 + mov rax, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 26], 9 + mov r11, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 26], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 26], 11 mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 6 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r9 + 28], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 26], 12 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 26], 13 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 26], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 26], 15 + movzx eax, byte ptr [rdi + rcx + 27] + vmovd xmm3, eax + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 4 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rcx + 27], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 7 + mov r8, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 27], 8 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 27], 9 + mov rsi, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rsi + 27], 10 + vpinsrb xmm3, xmm3, byte ptr [rdi + r15 + 27], 11 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 12 + mov r14, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 27], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 27], 14 mov rax, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 28], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 28], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 27], 15 + movzx eax, byte ptr [rdi + r12 + 27] + vmovd xmm4, eax + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 27], 1 + vpinsrb xmm4, xmm4, byte ptr [rdi + rbx + 27], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 27], 3 + mov r12, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 27], 4 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 28], 12 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 28], 13 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + rdi + 28], 14 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - vpinsrb xmm2, xmm2, byte ptr [rdx + r12 + 28], 15 - movzx edi, byte ptr [rdx + r8 + 29] - vmovd xmm3, edi - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 1 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rcx + 29], 2 - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 29], 4 - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 5 - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 6 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rsi + 29], 7 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 8 - mov rdi, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 9 - mov rdi, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 10 - mov r13, qword ptr [rsp + 176] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r13 + 29], 11 - mov r10, qword ptr [rsp + 264] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r10 + 29], 12 - mov r11, qword ptr [rsp + 232] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r11 + 29], 13 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rdi + 29], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 29], 15 - movzx edi, byte ptr [rdx + rbx + 29] - vmovd xmm4, edi - mov r8, qword ptr [rsp + 208] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 29], 1 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 29], 2 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 29], 3 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 29], 4 - mov rdi, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 29], 5 - mov rbx, qword ptr [rsp + 144] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 29], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 29], 7 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 29], 8 - mov rdi, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 29], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + r15 + 29], 10 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rdi + 29], 11 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 29], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 27], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 27], 6 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 27], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 27], 8 + mov r15, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 27], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 27], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 27], 11 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 27], 12 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 27], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 27], 14 + mov rax, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 27], 15 + vinserti128 ymm1, ymm2, xmm1, 1 + vmovdqa ymmword ptr [rsp + 576], ymm1 # 32-byte Spill + vinserti128 ymm1, ymm4, xmm3, 1 + vmovdqa ymmword ptr [rsp + 608], ymm1 # 32-byte Spill + mov rbx, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rbx + 28] + vmovd xmm1, eax + mov rax, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 1 + mov r9, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 28], 2 + mov r10, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 28], 3 mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 29], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 4 + vpinsrb xmm1, xmm1, byte ptr [rdi + rcx + 28], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 6 mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 29], 14 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 7 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 9 + vpinsrb xmm1, xmm1, byte ptr [rdi + rsi + 28], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 11 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 28], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r14 + 28], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rdx + 28], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 28], 15 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 28] + vmovd xmm2, eax + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 28], 4 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r12 + 28], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 6 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r14 + 28], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 28], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 28], 9 + mov r15, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r15 + 28], 10 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rsi + 28], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + r13 + 28], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 28], 13 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + r11 + 28], 14 + mov rdx, qword ptr [rsp + 232] # 8-byte Reload + vpinsrb xmm2, xmm2, byte ptr [rdi + rdx + 28], 15 + movzx eax, byte ptr [rdi + rbx + 29] + vmovd xmm3, eax + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rbx + 29], 1 + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 2 + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 6 + mov r9, qword ptr [rsp + 32] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 29], 7 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 9 + mov r10, qword ptr [rsp + 240] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 29], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 29], 12 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r8 + 29], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 29], 15 + movzx eax, byte ptr [rdi + rcx + 29] + vmovd xmm4, eax + mov rax, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 29], 1 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 29], 2 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 29], 3 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 29], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 29], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 29], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 29], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 29], 8 + mov r12, qword ptr [rsp + 216] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 29], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r15 + 29], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + rsi + 29], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 29], 12 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 29], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 29], 14 vinserti128 ymm1, ymm2, xmm1, 1 vmovdqa ymmword ptr [rsp + 640], ymm1 # 32-byte Spill - vpinsrb xmm1, xmm4, byte ptr [rdx + r12 + 29], 15 + vpinsrb xmm1, xmm4, byte ptr [rdi + rdx + 29], 15 vinserti128 ymm1, ymm1, xmm3, 1 vmovdqa ymmword ptr [rsp + 672], ymm1 # 32-byte Spill - mov rax, qword ptr [rsp + 256] # 8-byte Reload - movzx edi, byte ptr [rdx + rax + 30] - vmovd xmm1, edi - mov r15, qword ptr [rsp + 200] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + r15 + 30], 1 - movzx edi, byte ptr [rdx + rax + 31] - vmovd xmm2, edi - vpinsrb xmm2, xmm2, byte ptr [rdx + r15 + 31], 1 - vpinsrb xmm1, xmm1, byte ptr [rdx + rcx + 30], 2 - vpinsrb xmm2, xmm2, byte ptr [rdx + rcx + 31], 2 - mov rax, qword ptr [rsp + 168] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 4 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 4 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 5 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 6 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 6 - vpinsrb xmm1, xmm1, byte ptr [rdx + rsi + 30], 7 - vpinsrb xmm2, xmm2, byte ptr [rdx + rsi + 31], 7 + mov rsi, qword ptr [rsp + 248] # 8-byte Reload + movzx eax, byte ptr [rdi + rsi + 30] + vmovd xmm1, eax + vpinsrb xmm1, xmm1, byte ptr [rdi + rbx + 30], 1 + movzx eax, byte ptr [rdi + rsi + 31] + vmovd xmm2, eax + vpinsrb xmm2, xmm2, byte ptr [rdi + rbx + 31], 1 + mov rax, qword ptr [rsp + 184] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 2 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 2 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 4 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 6 + vpinsrb xmm1, xmm1, byte ptr [rdi + r9 + 30], 7 + vpinsrb xmm2, xmm2, byte ptr [rdi + r9 + 31], 7 mov r15, qword ptr [rsp + 272] # 8-byte Reload mov rax, qword ptr [rsp + 192] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 8 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 8 - mov rax, qword ptr [rsp + 320] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 184] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 10 - vpinsrb xmm1, xmm1, byte ptr [rdx + r13 + 30], 11 - vpinsrb xmm2, xmm2, byte ptr [rdx + r13 + 31], 11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r10 + 30], 12 - vpinsrb xmm2, xmm2, byte ptr [rdx + r10 + 31], 12 - mov rax, r11 - vpinsrb xmm1, xmm1, byte ptr [rdx + r11 + 30], 13 - vpinsrb xmm2, xmm2, byte ptr [rdx + r11 + 31], 13 + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 8 + mov rax, qword ptr [rsp + 152] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 9 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 9 + mov rax, r10 + vpinsrb xmm1, xmm1, byte ptr [rdi + r10 + 30], 10 + vpinsrb xmm2, xmm2, byte ptr [rdi + r10 + 31], 10 + mov rax, qword ptr [rsp + 200] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 11 mov rax, qword ptr [rsp + 112] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 14 - mov rax, qword ptr [rsp + 248] # 8-byte Reload - vpinsrb xmm1, xmm1, byte ptr [rdx + rax + 30], 15 - vpinsrb xmm2, xmm2, byte ptr [rdx + rax + 31], 15 - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movzx eax, byte ptr [rdx + rcx + 30] + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 12 + vpinsrb xmm1, xmm1, byte ptr [rdi + r8 + 30], 13 + vpinsrb xmm2, xmm2, byte ptr [rdi + r8 + 31], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 14 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 14 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + vpinsrb xmm1, xmm1, byte ptr [rdi + rax + 30], 15 + vpinsrb xmm2, xmm2, byte ptr [rdi + rax + 31], 15 + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movzx eax, byte ptr [rdi + rcx + 30] vmovd xmm3, eax - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 30], 1 - movzx eax, byte ptr [rdx + rcx + 31] + mov r9, qword ptr [rsp + 160] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r9 + 30], 1 + movzx eax, byte ptr [rdi + rcx + 31] vmovd xmm4, eax - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 31], 1 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + r8 + 30], 2 - vpinsrb xmm4, xmm4, byte ptr [rdx + r8 + 31], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r9 + 31], 1 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + r10 + 30], 2 + vpinsrb xmm4, xmm4, byte ptr [rdi + r10 + 31], 2 mov rax, qword ptr [rsp + 48] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 3 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 3 - vpinsrb xmm3, xmm3, byte ptr [rdx + r14 + 30], 4 - vpinsrb xmm4, xmm4, byte ptr [rdx + r14 + 31], 4 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 5 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 5 - mov rax, rbx - vpinsrb xmm3, xmm3, byte ptr [rdx + rbx + 30], 6 - vpinsrb xmm4, xmm4, byte ptr [rdx + rbx + 31], 6 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 7 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 7 - vpinsrb xmm3, xmm3, byte ptr [rdx + r9 + 30], 8 - vpinsrb xmm4, xmm4, byte ptr [rdx + r9 + 31], 8 - mov rax, qword ptr [rsp + 216] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 9 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 10 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 11 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 11 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 3 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 3 + mov rax, qword ptr [rsp + 264] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 4 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 4 mov rax, qword ptr [rsp + 40] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 12 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 12 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 13 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - vpinsrb xmm3, xmm3, byte ptr [rdx + rax + 30], 14 - vpinsrb xmm4, xmm4, byte ptr [rdx + rax + 31], 14 - vpinsrb xmm3, xmm3, byte ptr [rdx + r12 + 30], 15 - vpinsrb xmm4, xmm4, byte ptr [rdx + r12 + 31], 15 + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 5 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 5 + mov rax, qword ptr [rsp + 168] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 6 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 6 + vpinsrb xmm3, xmm3, byte ptr [rdi + r14 + 30], 7 + vpinsrb xmm4, xmm4, byte ptr [rdi + r14 + 31], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 8 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 8 + mov rax, r12 + vpinsrb xmm3, xmm3, byte ptr [rdi + r12 + 30], 9 + vpinsrb xmm4, xmm4, byte ptr [rdi + r12 + 31], 9 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 10 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 11 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 11 + mov rax, qword ptr [rsp + 288] # 8-byte Reload + vpinsrb xmm3, xmm3, byte ptr [rdi + rax + 30], 12 + vpinsrb xmm4, xmm4, byte ptr [rdi + rax + 31], 12 + mov rax, r13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r13 + 30], 13 + vpinsrb xmm4, xmm4, byte ptr [rdi + r13 + 31], 13 + vpinsrb xmm3, xmm3, byte ptr [rdi + r11 + 30], 14 + vpinsrb xmm4, xmm4, byte ptr [rdi + r11 + 31], 14 + mov rax, rdx + vpinsrb xmm3, xmm3, byte ptr [rdi + rdx + 30], 15 + vpinsrb xmm4, xmm4, byte ptr [rdi + rdx + 31], 15 vinserti128 ymm1, ymm3, xmm1, 1 vmovdqa ymmword ptr [rsp + 320], ymm1 # 32-byte Spill vinserti128 ymm1, ymm4, xmm2, 1 @@ -69151,18 +70904,18 @@ comparison_greater_equal_scalar_arr_avx2: # @comparison_greater_equal_scalar_arr vmovdqu ymmword ptr [r15 + 4*rcx + 32], ymm5 vmovdqu ymmword ptr [r15 + 4*rcx], ymm3 add rcx, 32 - mov rbx, rcx + mov rax, rcx cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload - jne .LBB11_67 -# %bb.68: - mov r14, qword ptr [rsp + 352] # 8-byte Reload - cmp r14, qword ptr [rsp + 384] # 8-byte Folded Reload - mov r11d, dword ptr [rsp + 28] # 4-byte Reload - mov r13, qword ptr [rsp + 368] # 8-byte Reload - mov rdi, qword ptr [rsp + 360] # 8-byte Reload - mov r10, qword ptr [rsp + 280] # 8-byte Reload - jne .LBB11_69 - jmp .LBB11_72 + jne .LBB11_73 +# %bb.74: + mov rcx, qword ptr [rsp + 352] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r12, qword ptr [rsp + 280] # 8-byte Reload + mov r14d, dword ptr [rsp + 28] # 4-byte Reload + mov r13, qword ptr [rsp + 360] # 8-byte Reload + mov rdi, qword ptr [rsp + 368] # 8-byte Reload + jne .LBB11_75 + jmp .LBB11_78 .Lfunc_end11: .size comparison_greater_equal_scalar_arr_avx2, .Lfunc_end11-comparison_greater_equal_scalar_arr_avx2 # -- End function diff --git a/arrow/compute/internal/kernels/_lib/scalar_comparison_sse4_amd64.s b/arrow/compute/internal/kernels/_lib/scalar_comparison_sse4_amd64.s index 851ea35f8..5da802f5f 100644 --- a/arrow/compute/internal/kernels/_lib/scalar_comparison_sse4_amd64.s +++ b/arrow/compute/internal/kernels/_lib/scalar_comparison_sse4_amd64.s @@ -15,104 +15,120 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 push rbx and rsp, -8 sub rsp, 72 - mov eax, r9d - mov r14, r8 - mov r12, rcx + # kill: def $r9d killed $r9d def $r9 + mov r12, r8 + mov r15, rcx cmp edi, 6 - jg .LBB0_29 + jg .LBB0_35 # %bb.1: cmp edi, 3 jle .LBB0_2 -# %bb.15: +# %bb.18: cmp edi, 4 - je .LBB0_68 -# %bb.16: + je .LBB0_83 +# %bb.19: cmp edi, 5 - je .LBB0_79 -# %bb.17: + je .LBB0_97 +# %bb.20: cmp edi, 6 - jne .LBB0_123 -# %bb.18: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_22 -# %bb.19: - cdqe + jne .LBB0_153 +# %bb.21: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_26 +# %bb.23: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_24: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_20 -# %bb.21: - add r12, 1 -.LBB0_22: - sar r15, 5 - cmp r14, 32 - jl .LBB0_26 -# %bb.23: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB0_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB0_26: + sub r12, r8 + je .LBB0_153 +# %bb.27: + add r15, 1 +.LBB0_28: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_32 +# %bb.29: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov eax, dword ptr [rsi + 12] cmp eax, dword ptr [rdx + 12] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov eax, dword ptr [rsi + 16] cmp eax, dword ptr [rdx + 16] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov eax, dword ptr [rsi + 20] cmp eax, dword ptr [rdx + 20] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov eax, dword ptr [rsi + 24] cmp eax, dword ptr [rdx + 24] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] sete r13b mov eax, dword ptr [rsi + 32] cmp eax, dword ptr [rdx + 32] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - sete r8b + sete dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] sete r11b @@ -121,21 +137,21 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r15b mov eax, dword ptr [rsi + 48] cmp eax, dword ptr [rdx + 48] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov eax, dword ptr [rsi + 56] cmp eax, dword ptr [rdx + 56] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov eax, dword ptr [rsi + 60] cmp eax, dword ptr [rdx + 60] - sete dil + sete r8b mov eax, dword ptr [rsi + 64] mov ebx, dword ptr [rsi + 68] cmp eax, dword ptr [rdx + 64] mov eax, dword ptr [rsi + 72] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 68] mov ebx, dword ptr [rsi + 76] sete r10b @@ -146,144 +162,144 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 mov ebx, dword ptr [rsi + 84] sete r12b cmp eax, dword ptr [rdx + 80] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 84] mov eax, dword ptr [rsi + 88] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] sete r9b cmp eax, dword ptr [rdx + 96] mov eax, dword ptr [rsi + 100] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 112] mov eax, dword ptr [rsi + 116] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 116] mov eax, dword ptr [rsi + 120] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 120] mov eax, dword ptr [rsi + 124] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_24 -# %bb.25: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_26: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.27: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_30 +# %bb.31: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_32: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB0_28: # =>This Inner Loop Header: Depth=1 +.LBB0_34: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -291,7 +307,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -299,106 +316,122 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_28 - jmp .LBB0_123 -.LBB0_29: + cmp r12, r8 + jne .LBB0_34 + jmp .LBB0_153 +.LBB0_35: cmp edi, 8 - jle .LBB0_30 -# %bb.43: + jle .LBB0_36 +# %bb.52: cmp edi, 9 - je .LBB0_101 -# %bb.44: + je .LBB0_125 +# %bb.53: cmp edi, 11 - je .LBB0_112 -# %bb.45: + je .LBB0_139 +# %bb.54: cmp edi, 12 - jne .LBB0_123 -# %bb.46: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_50 -# %bb.47: - movsxd r10, eax + jne .LBB0_153 +# %bb.55: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_60 +# %bb.57: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB0_48: # =>This Inner Loop Header: Depth=1 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - ucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - setnp cl +.LBB0_58: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + movsd xmm0, qword ptr [rsi + 8*r14] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 8*r14] + setnp r10b sete bl - and bl, cl + and bl, r10b neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d + lea eax, [8*rdi] + sub ecx, eax mov eax, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB0_48 -# %bb.49: - add r12, 1 -.LBB0_50: - sar r15, 5 - cmp r14, 32 - jl .LBB0_54 -# %bb.51: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -8 + cmp r8, r14 + jne .LBB0_58 +# %bb.59: + sub rsi, r11 + sub rdx, r11 +.LBB0_60: + sub r12, r8 + je .LBB0_153 +# %bb.61: + add r15, 1 +.LBB0_62: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_66 +# %bb.63: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx] movsd xmm0, qword ptr [rsi + 8] # xmm0 = mem[0],zero setnp al sete cl and cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill + mov byte ptr [rsp + 29], cl # 1-byte Spill ucomisd xmm0, qword ptr [rdx + 8] setnp al sete cl and cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill + mov byte ptr [rsp + 22], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 16] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 16] setnp al sete cl and cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill + mov byte ptr [rsp + 28], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 24] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 24] setnp al sete cl and cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill + mov byte ptr [rsp + 31], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 32] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 32] setnp al sete cl and cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill + mov byte ptr [rsp + 30], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 40] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 40] setnp al @@ -414,13 +447,13 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill + mov byte ptr [rsp + 12], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill + mov byte ptr [rsp + 27], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 72] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 72] setnp al @@ -431,117 +464,116 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill + mov byte ptr [rsp + 26], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 88] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 88] setnp al sete cl and cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill + mov byte ptr [rsp + 25], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 96] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 96] setnp al sete cl and cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 11], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 104] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 104] setnp al sete cl and cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 112] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 112] setnp al sete cl and cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill + mov byte ptr [rsp + 21], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 120] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 120] setnp al sete cl and cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill + mov byte ptr [rsp + 20], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 128] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 128] setnp al sete cl and cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill + mov byte ptr [rsp + 23], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 136] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 136] setnp al sete cl and cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill + mov byte ptr [rsp + 19], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 144] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 144] setnp al sete cl and cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill + mov byte ptr [rsp + 18], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 152] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 152] setnp al - sete r14b - and r14b, al + sete r15b + and r15b, al movsd xmm0, qword ptr [rsi + 160] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 160] setnp al sete cl and cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 17], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 168] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 168] setnp al sete cl and cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 176] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 176] setnp al sete cl and cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill + mov byte ptr [rsp + 14], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 184] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 184] setnp al - sete r15b - and r15b, al + sete r10b + and r10b, al movsd xmm0, qword ptr [rsi + 192] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 192] setnp al sete cl and cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill + mov byte ptr [rsp + 15], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 200] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 200] setnp al - sete cl - and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + sete r12b + and r12b, al movsd xmm0, qword ptr [rsi + 208] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 208] setnp al - sete r11b - and r11b, al + sete r14b + and r14b, al movsd xmm0, qword ptr [rsi + 216] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 216] setnp al - sete r10b - and r10b, al + sete r11b + and r11b, al movsd xmm0, qword ptr [rsi + 224] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 224] setnp al sete cl and cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 13], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 232] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 232] setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill movsd xmm0, qword ptr [rsi + 240] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 240] setnp al @@ -553,110 +585,108 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 setnp al sete r8b and r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload shl dil, 5 shl r13b, 6 or r13b, dil mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload shl cl, 2 or cl, al mov eax, ebx add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload + add al, byte ptr [rsp + 27] # 1-byte Folded Reload mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 or al, r13b mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload shl bl, 3 or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 6 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload shl cl, 2 or cl, bl - shl r14b, 3 - or r14b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload shl bl, 4 - or bl, r14b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r14d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r14b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 or cl, r13b - or al, dil - shl r15b, 7 - or r15b, cl - or r15b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r11b, 2 - or r11b, cl - shl r10b, 3 - or r10b, r11b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload + shl r10b, 7 + or r10b, cl + or r10b, bl + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload shl cl, 4 - or cl, r10b - mov byte ptr [r12], r14b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 shl r9b, 6 or r9b, bl - mov byte ptr [r12 + 1], al + mov byte ptr [r15 + 1], dil shl r8b, 7 or r8b, r9b or r8b, cl - mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], r8b + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB0_52 -# %bb.53: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB0_54: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.55: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_64 +# %bb.65: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_66: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB0_56: # =>This Inner Loop Header: Depth=1 +.LBB0_68: # =>This Inner Loop Header: Depth=1 lea r9, [rcx + 1] movsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 8*rcx] @@ -666,7 +696,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg al mov rdi, rcx shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] xor al, r8b and cl, 7 mov bl, 1 @@ -674,95 +705,119 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl bl, cl and bl, al xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r15 + rdi], bl mov rcx, r9 - cmp r14, r9 - jne .LBB0_56 - jmp .LBB0_123 + cmp r12, r9 + jne .LBB0_68 + jmp .LBB0_153 .LBB0_2: cmp edi, 2 - je .LBB0_57 + mov r13, r15 + je .LBB0_69 # %bb.3: cmp edi, 3 - jne .LBB0_123 + jne .LBB0_153 # %bb.4: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_8 + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_11 # %bb.5: - cdqe - .p2align 4, 0x90 -.LBB0_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - sete r10b - neg r10b - lea rdi, [rax + 7] + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB0_9 +# %bb.6: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB0_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + sete r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB0_6 -# %bb.7: - add r12, 1 -.LBB0_8: - sar r15, 5 - cmp r14, 32 - jl .LBB0_12 -# %bb.9: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB0_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB0_9: + sub r12, rax + je .LBB0_153 +# %bb.10: + add r15, 1 +.LBB0_11: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_15 +# %bb.12: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] sete bl movzx eax, byte ptr [rsi + 2] cmp al, byte ptr [rdx + 2] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 3] cmp al, byte ptr [rdx + 3] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 4] cmp al, byte ptr [rdx + 4] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 5] cmp al, byte ptr [rdx + 5] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 6] cmp al, byte ptr [rdx + 6] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - sete r15b + sete r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 9] cmp al, byte ptr [rdx + 9] sete dil @@ -774,19 +829,19 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - sete r14b + sete r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 14] cmp al, byte ptr [rdx + 14] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 15] cmp al, byte ptr [rdx + 15] sete r8b movzx eax, byte ptr [rsi + 16] cmp al, byte ptr [rdx + 16] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 17] cmp al, byte ptr [rdx + 17] sete r12b @@ -795,148 +850,147 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r13b movzx eax, byte ptr [rsi + 19] cmp al, byte ptr [rdx + 19] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 20] cmp al, byte ptr [rdx + 20] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 21] cmp al, byte ptr [rdx + 21] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 22] cmp al, byte ptr [rdx + 22] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 23] cmp al, byte ptr [rdx + 23] sete r9b movzx eax, byte ptr [rsi + 24] cmp al, byte ptr [rdx + 24] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 25] cmp al, byte ptr [rdx + 25] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 26] cmp al, byte ptr [rdx + 26] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 27] cmp al, byte ptr [rdx + 27] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 28] cmp al, byte ptr [rdx + 28] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 29] cmp al, byte ptr [rdx + 29] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 30] cmp al, byte ptr [rdx + 30] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 31] add rsi, 32 cmp al, byte ptr [rdx + 31] sete cl add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload shl bl, 2 or bl, al mov eax, ebx add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r10b, 2 or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al mov edi, ebx shl r11b, 3 or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload shl dil, 6 shl r8b, 7 or r8b, dil - or r15b, bl + or r14b, bl or r8b, al add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 3 or al, r13b mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], r8b + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB0_10 -# %bb.11: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB0_12: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.13: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB0_13 +# %bb.14: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB0_15: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB0_14: # =>This Inner Loop Header: Depth=1 +.LBB0_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -944,7 +998,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -952,98 +1007,114 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_14 - jmp .LBB0_123 -.LBB0_30: + cmp r12, r8 + jne .LBB0_17 + jmp .LBB0_153 +.LBB0_36: cmp edi, 7 - je .LBB0_90 -# %bb.31: + je .LBB0_111 +# %bb.37: cmp edi, 8 - jne .LBB0_123 -# %bb.32: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_36 -# %bb.33: - cdqe + jne .LBB0_153 +# %bb.38: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_41: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_34 -# %bb.35: - add r12, 1 -.LBB0_36: - sar r15, 5 - cmp r14, 32 - jl .LBB0_40 -# %bb.37: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB0_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB0_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB0_43: + sub r12, r8 + je .LBB0_153 +# %bb.44: + add r15, 1 +.LBB0_45: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_49 +# %bb.46: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB0_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov rax, qword ptr [rsi + 24] cmp rax, qword ptr [rdx + 24] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov rax, qword ptr [rsi + 32] cmp rax, qword ptr [rdx + 32] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov rax, qword ptr [rsi + 40] cmp rax, qword ptr [rdx + 40] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov rax, qword ptr [rsi + 48] cmp rax, qword ptr [rdx + 48] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] sete r13b mov rax, qword ptr [rsi + 64] cmp rax, qword ptr [rdx + 64] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - sete r8b + sete dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] sete r11b @@ -1052,21 +1123,21 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r15b mov rax, qword ptr [rsi + 96] cmp rax, qword ptr [rdx + 96] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov rax, qword ptr [rsi + 112] cmp rax, qword ptr [rdx + 112] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov rax, qword ptr [rsi + 120] cmp rax, qword ptr [rdx + 120] - sete dil + sete r8b mov rax, qword ptr [rsi + 128] mov rbx, qword ptr [rsi + 136] cmp rax, qword ptr [rdx + 128] mov rax, qword ptr [rsi + 144] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 136] mov rbx, qword ptr [rsi + 152] sete r10b @@ -1077,144 +1148,144 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 mov rbx, qword ptr [rsi + 168] sete r12b cmp rax, qword ptr [rdx + 160] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 168] mov rax, qword ptr [rsi + 176] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] sete r9b cmp rax, qword ptr [rdx + 192] mov rax, qword ptr [rsi + 200] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 224] mov rax, qword ptr [rsi + 232] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 232] mov rax, qword ptr [rsi + 240] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 240] mov rax, qword ptr [rsi + 248] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_38 -# %bb.39: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_40: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.41: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_47 +# %bb.48: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_49: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB0_42: # =>This Inner Loop Header: Depth=1 +.LBB0_51: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -1222,7 +1293,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -1230,92 +1302,108 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_42 - jmp .LBB0_123 -.LBB0_68: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_72 -# %bb.69: - cdqe + cmp r12, r8 + jne .LBB0_51 + jmp .LBB0_153 +.LBB0_83: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_86: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_70 -# %bb.71: - add r12, 1 -.LBB0_72: - sar r15, 5 - cmp r14, 32 - jl .LBB0_76 -# %bb.73: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB0_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB0_88: + sub r12, r8 + je .LBB0_153 +# %bb.89: + add r15, 1 +.LBB0_90: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_94 +# %bb.91: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, word ptr [rsi + 6] cmp ax, word ptr [rdx + 6] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, word ptr [rsi + 8] cmp ax, word ptr [rdx + 8] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, word ptr [rsi + 10] cmp ax, word ptr [rdx + 10] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, word ptr [rsi + 12] cmp ax, word ptr [rdx + 12] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] sete r13b movzx eax, word ptr [rsi + 16] cmp ax, word ptr [rdx + 16] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - sete r8b + sete dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] sete r11b @@ -1324,21 +1412,21 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r15b movzx eax, word ptr [rsi + 24] cmp ax, word ptr [rdx + 24] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, word ptr [rsi + 28] cmp ax, word ptr [rdx + 28] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, word ptr [rsi + 30] cmp ax, word ptr [rdx + 30] - sete dil + sete r8b movzx eax, word ptr [rsi + 32] movzx ebx, word ptr [rsi + 34] cmp ax, word ptr [rdx + 32] movzx eax, word ptr [rsi + 36] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp bx, word ptr [rdx + 34] movzx ebx, word ptr [rsi + 38] sete r10b @@ -1349,144 +1437,144 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 movzx ebx, word ptr [rsi + 42] sete r12b cmp ax, word ptr [rdx + 40] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp bx, word ptr [rdx + 42] movzx eax, word ptr [rsi + 44] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] sete r9b cmp ax, word ptr [rdx + 48] movzx eax, word ptr [rsi + 50] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp ax, word ptr [rdx + 56] movzx eax, word ptr [rsi + 58] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp ax, word ptr [rdx + 58] movzx eax, word ptr [rsi + 60] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp ax, word ptr [rdx + 60] movzx eax, word ptr [rsi + 62] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_74 -# %bb.75: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_76: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.77: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_92 +# %bb.93: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_94: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB0_78: # =>This Inner Loop Header: Depth=1 +.LBB0_96: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -1494,7 +1582,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -1502,92 +1591,108 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_78 - jmp .LBB0_123 -.LBB0_79: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_83 -# %bb.80: - cdqe + cmp r12, r8 + jne .LBB0_96 + jmp .LBB0_153 +.LBB0_97: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_81 -# %bb.82: - add r12, 1 -.LBB0_83: - sar r15, 5 - cmp r14, 32 - jl .LBB0_87 -# %bb.84: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB0_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB0_102: + sub r12, r8 + je .LBB0_153 +# %bb.103: + add r15, 1 +.LBB0_104: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_108 +# %bb.105: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, word ptr [rsi + 6] cmp ax, word ptr [rdx + 6] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, word ptr [rsi + 8] cmp ax, word ptr [rdx + 8] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, word ptr [rsi + 10] cmp ax, word ptr [rdx + 10] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, word ptr [rsi + 12] cmp ax, word ptr [rdx + 12] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] sete r13b movzx eax, word ptr [rsi + 16] cmp ax, word ptr [rdx + 16] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - sete r8b + sete dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] sete r11b @@ -1596,21 +1701,21 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r15b movzx eax, word ptr [rsi + 24] cmp ax, word ptr [rdx + 24] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, word ptr [rsi + 28] cmp ax, word ptr [rdx + 28] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, word ptr [rsi + 30] cmp ax, word ptr [rdx + 30] - sete dil + sete r8b movzx eax, word ptr [rsi + 32] movzx ebx, word ptr [rsi + 34] cmp ax, word ptr [rdx + 32] movzx eax, word ptr [rsi + 36] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp bx, word ptr [rdx + 34] movzx ebx, word ptr [rsi + 38] sete r10b @@ -1621,144 +1726,144 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 movzx ebx, word ptr [rsi + 42] sete r12b cmp ax, word ptr [rdx + 40] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp bx, word ptr [rdx + 42] movzx eax, word ptr [rsi + 44] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] sete r9b cmp ax, word ptr [rdx + 48] movzx eax, word ptr [rsi + 50] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp ax, word ptr [rdx + 56] movzx eax, word ptr [rsi + 58] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp ax, word ptr [rdx + 58] movzx eax, word ptr [rsi + 60] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp ax, word ptr [rdx + 60] movzx eax, word ptr [rsi + 62] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_85 -# %bb.86: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_87: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.88: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_106 +# %bb.107: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_108: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB0_89: # =>This Inner Loop Header: Depth=1 +.LBB0_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -1766,7 +1871,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -1774,92 +1880,108 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_89 - jmp .LBB0_123 -.LBB0_101: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_105 -# %bb.102: - cdqe + cmp r12, r8 + jne .LBB0_110 + jmp .LBB0_153 +.LBB0_125: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_103 -# %bb.104: - add r12, 1 -.LBB0_105: - sar r15, 5 - cmp r14, 32 - jl .LBB0_109 -# %bb.106: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB0_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB0_130: + sub r12, r8 + je .LBB0_153 +# %bb.131: + add r15, 1 +.LBB0_132: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_136 +# %bb.133: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov rax, qword ptr [rsi + 24] cmp rax, qword ptr [rdx + 24] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov rax, qword ptr [rsi + 32] cmp rax, qword ptr [rdx + 32] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov rax, qword ptr [rsi + 40] cmp rax, qword ptr [rdx + 40] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov rax, qword ptr [rsi + 48] cmp rax, qword ptr [rdx + 48] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] sete r13b mov rax, qword ptr [rsi + 64] cmp rax, qword ptr [rdx + 64] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - sete r8b + sete dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] sete r11b @@ -1868,21 +1990,21 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r15b mov rax, qword ptr [rsi + 96] cmp rax, qword ptr [rdx + 96] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov rax, qword ptr [rsi + 112] cmp rax, qword ptr [rdx + 112] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov rax, qword ptr [rsi + 120] cmp rax, qword ptr [rdx + 120] - sete dil + sete r8b mov rax, qword ptr [rsi + 128] mov rbx, qword ptr [rsi + 136] cmp rax, qword ptr [rdx + 128] mov rax, qword ptr [rsi + 144] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 136] mov rbx, qword ptr [rsi + 152] sete r10b @@ -1893,144 +2015,144 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 mov rbx, qword ptr [rsi + 168] sete r12b cmp rax, qword ptr [rdx + 160] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 168] mov rax, qword ptr [rsi + 176] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] sete r9b cmp rax, qword ptr [rdx + 192] mov rax, qword ptr [rsi + 200] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 224] mov rax, qword ptr [rsi + 232] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 232] mov rax, qword ptr [rsi + 240] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 240] mov rax, qword ptr [rsi + 248] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_107 -# %bb.108: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_109: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.110: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_134 +# %bb.135: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_136: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.137: xor ecx, ecx .p2align 4, 0x90 -.LBB0_111: # =>This Inner Loop Header: Depth=1 +.LBB0_138: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -2038,7 +2160,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -2046,94 +2169,110 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_111 - jmp .LBB0_123 -.LBB0_112: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_116 -# %bb.113: - movsxd r10, eax + cmp r12, r8 + jne .LBB0_138 + jmp .LBB0_153 +.LBB0_139: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_144 +# %bb.141: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB0_114: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - ucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - setnp cl +.LBB0_142: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + movss xmm0, dword ptr [rsi + 4*r14] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 4*r14] + setnp r10b sete bl - and bl, cl + and bl, r10b neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d + lea eax, [8*rdi] + sub ecx, eax mov eax, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB0_114 -# %bb.115: - add r12, 1 -.LBB0_116: - sar r15, 5 - cmp r14, 32 - jl .LBB0_120 -# %bb.117: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -4 + cmp r8, r14 + jne .LBB0_142 +# %bb.143: + sub rsi, r11 + sub rdx, r11 +.LBB0_144: + sub r12, r8 + je .LBB0_153 +# %bb.145: + add r15, 1 +.LBB0_146: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_150 +# %bb.147: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx] movss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero setnp al sete cl and cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill + mov byte ptr [rsp + 29], cl # 1-byte Spill ucomiss xmm0, dword ptr [rdx + 4] setnp al sete cl and cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill + mov byte ptr [rsp + 22], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 8] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 8] setnp al sete cl and cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill + mov byte ptr [rsp + 28], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 12] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 12] setnp al sete cl and cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill + mov byte ptr [rsp + 31], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 16] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 16] setnp al sete cl and cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill + mov byte ptr [rsp + 30], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 20] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 20] setnp al @@ -2149,13 +2288,13 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill + mov byte ptr [rsp + 12], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 32] setnp al sete cl and cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill + mov byte ptr [rsp + 27], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 36] setnp al @@ -2166,78 +2305,78 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill + mov byte ptr [rsp + 26], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 44] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 44] setnp al sete cl and cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill + mov byte ptr [rsp + 25], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 48] setnp al sete cl and cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 11], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 52] setnp al sete cl and cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 56] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 56] setnp al sete cl and cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill + mov byte ptr [rsp + 21], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 60] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 60] setnp al sete cl and cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill + mov byte ptr [rsp + 20], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 64] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill + mov byte ptr [rsp + 23], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 68] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 68] setnp al sete cl and cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill + mov byte ptr [rsp + 19], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 72] setnp al sete cl and cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill + mov byte ptr [rsp + 18], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 76] setnp al - sete r11b - and r11b, al + sete r15b + and r15b, al movss xmm0, dword ptr [rsi + 80] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 80] setnp al sete cl and cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 17], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 84] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 84] setnp al sete cl and cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 88] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 88] setnp al sete cl and cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill + mov byte ptr [rsp + 14], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 92] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 92] setnp al @@ -2248,35 +2387,34 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill + mov byte ptr [rsp + 15], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 100] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 100] setnp al - sete cl - and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + sete r12b + and r12b, al movss xmm0, dword ptr [rsi + 104] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 104] setnp al - sete r15b - and r15b, al + sete r14b + and r14b, al movss xmm0, dword ptr [rsi + 108] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 108] setnp al - sete r14b - and r14b, al + sete r11b + and r11b, al movss xmm0, dword ptr [rsi + 112] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 112] setnp al sete cl and cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 13], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 116] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 116] setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill movss xmm0, dword ptr [rsi + 120] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 120] setnp al @@ -2288,110 +2426,108 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 setnp al sete r8b and r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload shl dil, 5 shl r13b, 6 or r13b, dil mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload shl cl, 2 or cl, al mov eax, ebx add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload + add al, byte ptr [rsp + 27] # 1-byte Folded Reload mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 or al, r13b mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload shl bl, 3 or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 6 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload shl cl, 2 or cl, bl - shl r11b, 3 - or r11b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload shl bl, 4 - or bl, r11b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r11d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r11b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 or cl, r13b - or al, dil + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload shl r10b, 7 or r10b, cl or r10b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r15b, 2 - or r15b, cl - shl r14b, 3 - or r14b, r15b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload shl cl, 4 - or cl, r14b - mov byte ptr [r12], r11b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 shl r9b, 6 or r9b, bl - mov byte ptr [r12 + 1], al + mov byte ptr [r15 + 1], dil shl r8b, 7 or r8b, r9b or r8b, cl - mov byte ptr [r12 + 2], r10b - mov byte ptr [r12 + 3], r8b + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB0_118 -# %bb.119: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB0_120: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.121: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_148 +# %bb.149: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_150: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.151: xor ecx, ecx .p2align 4, 0x90 -.LBB0_122: # =>This Inner Loop Header: Depth=1 +.LBB0_152: # =>This Inner Loop Header: Depth=1 lea r9, [rcx + 1] movss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 4*rcx] @@ -2401,7 +2537,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg al mov rdi, rcx shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] xor al, r8b and cl, 7 mov bl, 1 @@ -2409,89 +2546,112 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl bl, cl and bl, al xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r15 + rdi], bl mov rcx, r9 - cmp r14, r9 - jne .LBB0_122 - jmp .LBB0_123 -.LBB0_57: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_61 -# %bb.58: - cdqe - .p2align 4, 0x90 -.LBB0_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - sete r10b - neg r10b - lea rdi, [rax + 7] + cmp r12, r9 + jne .LBB0_152 + jmp .LBB0_153 +.LBB0_69: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB0_74 +# %bb.71: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB0_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + sete r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB0_59 -# %bb.60: - add r12, 1 -.LBB0_61: - sar r15, 5 - cmp r14, 32 - jl .LBB0_65 -# %bb.62: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB0_72 +# %bb.73: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB0_74: + sub r12, rax + je .LBB0_153 +# %bb.75: + add r15, 1 +.LBB0_76: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_80 +# %bb.77: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] sete bl movzx eax, byte ptr [rsi + 2] cmp al, byte ptr [rdx + 2] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 3] cmp al, byte ptr [rdx + 3] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 4] cmp al, byte ptr [rdx + 4] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 5] cmp al, byte ptr [rdx + 5] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 6] cmp al, byte ptr [rdx + 6] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - sete r15b + sete r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 9] cmp al, byte ptr [rdx + 9] sete dil @@ -2503,19 +2663,19 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - sete r14b + sete r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 14] cmp al, byte ptr [rdx + 14] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 15] cmp al, byte ptr [rdx + 15] sete r8b movzx eax, byte ptr [rsi + 16] cmp al, byte ptr [rdx + 16] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 17] cmp al, byte ptr [rdx + 17] sete r12b @@ -2524,148 +2684,147 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r13b movzx eax, byte ptr [rsi + 19] cmp al, byte ptr [rdx + 19] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 20] cmp al, byte ptr [rdx + 20] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 21] cmp al, byte ptr [rdx + 21] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 22] cmp al, byte ptr [rdx + 22] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 23] cmp al, byte ptr [rdx + 23] sete r9b movzx eax, byte ptr [rsi + 24] cmp al, byte ptr [rdx + 24] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 25] cmp al, byte ptr [rdx + 25] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 26] cmp al, byte ptr [rdx + 26] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 27] cmp al, byte ptr [rdx + 27] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 28] cmp al, byte ptr [rdx + 28] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 29] cmp al, byte ptr [rdx + 29] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 30] cmp al, byte ptr [rdx + 30] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 31] add rsi, 32 cmp al, byte ptr [rdx + 31] sete cl add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload shl bl, 2 or bl, al mov eax, ebx add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r10b, 2 or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al mov edi, ebx shl r11b, 3 or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload shl dil, 6 shl r8b, 7 or r8b, dil - or r15b, bl + or r14b, bl or r8b, al add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 3 or al, r13b mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], r8b + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB0_63 -# %bb.64: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB0_65: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.66: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB0_78 +# %bb.79: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB0_80: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.81: xor ecx, ecx .p2align 4, 0x90 -.LBB0_67: # =>This Inner Loop Header: Depth=1 +.LBB0_82: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -2673,7 +2832,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -2681,92 +2841,108 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_67 - jmp .LBB0_123 -.LBB0_90: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB0_94 -# %bb.91: - cdqe + cmp r12, r8 + jne .LBB0_82 + jmp .LBB0_153 +.LBB0_111: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB0_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB0_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB0_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - sete r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB0_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + sete r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB0_92 -# %bb.93: - add r12, 1 -.LBB0_94: - sar r15, 5 - cmp r14, 32 - jl .LBB0_98 -# %bb.95: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB0_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB0_116: + sub r12, r8 + je .LBB0_153 +# %bb.117: + add r15, 1 +.LBB0_118: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB0_122 +# %bb.119: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB0_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB0_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 13] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] - sete byte ptr [rsp + 21] # 1-byte Folded Spill + sete byte ptr [rsp + 30] # 1-byte Folded Spill mov eax, dword ptr [rsi + 12] cmp eax, dword ptr [rdx + 12] - sete byte ptr [rsp + 22] # 1-byte Folded Spill + sete byte ptr [rsp + 31] # 1-byte Folded Spill mov eax, dword ptr [rsi + 16] cmp eax, dword ptr [rdx + 16] - sete byte ptr [rsp + 23] # 1-byte Folded Spill + sete byte ptr [rsp + 11] # 1-byte Folded Spill mov eax, dword ptr [rsi + 20] cmp eax, dword ptr [rdx + 20] - sete byte ptr [rsp + 3] # 1-byte Folded Spill + sete byte ptr [rsp + 12] # 1-byte Folded Spill mov eax, dword ptr [rsi + 24] cmp eax, dword ptr [rdx + 24] - sete byte ptr [rsp + 5] # 1-byte Folded Spill + sete byte ptr [rsp + 14] # 1-byte Folded Spill mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] sete r13b mov eax, dword ptr [rsi + 32] cmp eax, dword ptr [rdx + 32] - sete byte ptr [rsp + 10] # 1-byte Folded Spill + sete byte ptr [rsp + 19] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - sete r8b + sete dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] sete r11b @@ -2775,21 +2951,21 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 sete r15b mov eax, dword ptr [rsi + 48] cmp eax, dword ptr [rdx + 48] - sete byte ptr [rsp + 6] # 1-byte Folded Spill + sete byte ptr [rsp + 15] # 1-byte Folded Spill mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] - sete byte ptr [rsp + 7] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill mov eax, dword ptr [rsi + 56] cmp eax, dword ptr [rdx + 56] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 17] # 1-byte Folded Spill mov eax, dword ptr [rsi + 60] cmp eax, dword ptr [rdx + 60] - sete dil + sete r8b mov eax, dword ptr [rsi + 64] mov ebx, dword ptr [rsi + 68] cmp eax, dword ptr [rdx + 64] mov eax, dword ptr [rsi + 72] - sete byte ptr [rsp + 11] # 1-byte Folded Spill + sete byte ptr [rsp + 20] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 68] mov ebx, dword ptr [rsi + 76] sete r10b @@ -2800,144 +2976,144 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 mov ebx, dword ptr [rsi + 84] sete r12b cmp eax, dword ptr [rdx + 80] - sete byte ptr [rsp + 9] # 1-byte Folded Spill + sete byte ptr [rsp + 18] # 1-byte Folded Spill cmp ebx, dword ptr [rdx + 84] mov eax, dword ptr [rsi + 88] - sete byte ptr [rsp + 12] # 1-byte Folded Spill + sete byte ptr [rsp + 21] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - sete byte ptr [rsp + 13] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] sete r9b cmp eax, dword ptr [rdx + 96] mov eax, dword ptr [rsi + 100] - sete byte ptr [rsp + 20] # 1-byte Folded Spill + sete byte ptr [rsp + 29] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - sete byte ptr [rsp + 14] # 1-byte Folded Spill + sete byte ptr [rsp + 22] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - sete byte ptr [rsp + 15] # 1-byte Folded Spill + sete byte ptr [rsp + 23] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 25] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 112] mov eax, dword ptr [rsi + 116] - sete byte ptr [rsp + 17] # 1-byte Folded Spill + sete byte ptr [rsp + 26] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 116] mov eax, dword ptr [rsi + 120] - sete byte ptr [rsp + 19] # 1-byte Folded Spill + sete byte ptr [rsp + 28] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 120] mov eax, dword ptr [rsi + 124] - sete byte ptr [rsp + 18] # 1-byte Folded Spill + sete byte ptr [rsp + 27] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] sete cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB0_96 -# %bb.97: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB0_98: - shl r15, 5 - cmp r15, r14 - jge .LBB0_123 -# %bb.99: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB0_120 +# %bb.121: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB0_122: + shl rax, 5 + sub r12, rax + jle .LBB0_153 +# %bb.123: xor ecx, ecx .p2align 4, 0x90 -.LBB0_100: # =>This Inner Loop Header: Depth=1 +.LBB0_124: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -2945,7 +3121,8 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -2953,11 +3130,11 @@ comparison_equal_arr_arr_sse4: # @comparison_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB0_100 -.LBB0_123: + cmp r12, r8 + jne .LBB0_124 +.LBB0_153: lea rsp, [rbp - 40] pop rbx pop r12 @@ -3077,256 +3254,266 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 push r12 push rbx and rsp, -16 - sub rsp, 304 + sub rsp, 320 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov r14, rcx + mov r15, r8 + mov r12, rcx cmp edi, 6 - jg .LBB1_27 + jg .LBB1_25 # %bb.1: cmp edi, 3 jle .LBB1_2 -# %bb.10: +# %bb.6: cmp edi, 4 - je .LBB1_101 -# %bb.11: + je .LBB1_114 +# %bb.7: cmp edi, 5 - je .LBB1_124 -# %bb.12: + je .LBB1_139 +# %bb.8: cmp edi, 6 - jne .LBB1_199 -# %bb.13: + jne .LBB1_222 +# %bb.9: mov r13d, dword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] + lea ecx, [r9 + 7] test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB1_17 + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB1_15 +# %bb.10: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_13 +# %bb.11: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB1_12: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + sete bl + neg bl + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 + # kill: def $cl killed $cl killed $ecx + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_12 +.LBB1_13: + sub r15, r8 + je .LBB1_222 # %bb.14: - movsxd rax, r9d + add r12, 1 +.LBB1_15: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_19 +# %bb.16: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_15: # =>This Inner Loop Header: Depth=1 +.LBB1_17: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_15 -# %bb.16: - add r14, 1 -.LBB1_17: - sar r11, 5 - cmp r10, 32 - jl .LBB1_21 -# %bb.18: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB1_19: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 136], r14 # 8-byte Spill - cmp dword ptr [rsi], r13d - sete byte ptr [rsp + 208] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d - sete r10b + sete r9b cmp dword ptr [rsi + 8], r13d sete r14b cmp dword ptr [rsi + 12], r13d - sete byte ptr [rsp + 176] # 1-byte Folded Spill + sete byte ptr [rsp + 192] # 1-byte Folded Spill cmp dword ptr [rsi + 16], r13d - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d sete al cmp dword ptr [rsi + 28], r13d - sete bl + sete r11b cmp dword ptr [rsi + 32], r13d - sete byte ptr [rsp + 192] # 1-byte Folded Spill + sete byte ptr [rsp + 224] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d - sete dil + sete cl cmp dword ptr [rsi + 40], r13d - sete r8b + sete dil cmp dword ptr [rsi + 44], r13d - sete r9b + sete r8b cmp dword ptr [rsi + 48], r13d - sete r11b + sete r10b cmp dword ptr [rsi + 52], r13d sete r12b cmp dword ptr [rsi + 56], r13d - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 208] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - sete cl + sete dl cmp dword ptr [rsi + 64], r13d - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp dword ptr [rsi + 68], r13d - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp dword ptr [rsi + 72], r13d - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 176] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp dword ptr [rsi + 88], r13d - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d sete r15b cmp dword ptr [rsi + 96], r13d - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp dword ptr [rsi + 104], r13d - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp dword ptr [rsi + 108], r13d - sete byte ptr [rsp + 24] # 1-byte Folded Spill + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp dword ptr [rsi + 112], r13d - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill cmp dword ptr [rsi + 116], r13d - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp dword ptr [rsi + 120], r13d - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 8] # 1-byte Folded Spill cmp dword ptr [rsi + 124], r13d - sete dl - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload + sete bl + add r9b, r9b + add r9b, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 3 or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 136] # 8-byte Reload - shl r8b, 2 + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b + or al, cl + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or r12b, r10b + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 - or al, dil - mov edi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 6 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 6 shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl + or r15b, cl + mov byte ptr [r12 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload + add al, byte ptr [rsp + 40] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, cl - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rsi, 128 - add r14, 4 - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB1_19 + add r12, 4 + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill + jne .LBB1_17 +# %bb.18: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 240] # 8-byte Reload +.LBB1_19: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_222 # %bb.20: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB1_21: - shl r11, 5 - cmp r11, r10 - jge .LBB1_199 -# %bb.22: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB1_23 -# %bb.144: + or rax, 1 + cmp r15, rax + je .LBB1_21 +# %bb.161: mov r10, r8 and r10, -2 xor r11d, r11d .p2align 4, 0x90 -.LBB1_145: # =>This Inner Loop Header: Depth=1 +.LBB1_162: # =>This Inner Loop Header: Depth=1 cmp dword ptr [rsi], r13d sete al neg al mov rdi, r11 shr rdi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rdi] + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -3334,7 +3521,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r14 + rdi], bl + mov byte ptr [r12 + rdi], bl add r11, 2 cmp dword ptr [rsi + 4], r13d lea rsi, [rsi + 8] @@ -3346,80 +3533,96 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r14 + rdi], dl + mov byte ptr [r12 + rdi], dl cmp r10, r11 - jne .LBB1_145 - jmp .LBB1_24 -.LBB1_27: + jne .LBB1_162 + jmp .LBB1_22 +.LBB1_25: cmp edi, 8 - jle .LBB1_28 + jle .LBB1_26 # %bb.43: cmp edi, 9 - je .LBB1_160 + je .LBB1_179 # %bb.44: cmp edi, 11 - je .LBB1_172 + je .LBB1_193 # %bb.45: cmp edi, 12 - jne .LBB1_199 + jne .LBB1_222 # %bb.46: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + mov r14, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero sub r9d, eax - je .LBB1_50 + je .LBB1_52 # %bb.47: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_50 +# %bb.48: + movsxd rdx, r9d + movq xmm0, r14 + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_48: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rsi] - lea rsi, [rsi + 8] +.LBB1_49: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rcx] + lea rsi, [rcx + 8] setnp cl - sete dl - and dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + sete bl + and bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_48 -# %bb.49: - add r14, 1 + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_49 .LBB1_50: - sar r11, 5 - cmp r10, 32 - jl .LBB1_54 + sub r15, r8 + je .LBB1_222 # %bb.51: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 272], r11 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill + add r12, 1 +.LBB1_52: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_56 +# %bb.53: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 152], r14 # 8-byte Spill + movq xmm0, r14 + mov qword ptr [rsp + 144], rax # 8-byte Spill + mov qword ptr [rsp + 288], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 136], r14 # 8-byte Spill +.LBB1_54: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill ucomisd xmm0, qword ptr [rsi] setnp al sete cl and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 8] setnp al sete r13b @@ -3428,17 +3631,17 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 24], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 24] setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 32] setnp al sete cl and cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 40] setnp al sete r12b @@ -3447,27 +3650,27 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 56] setnp al sete cl and cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 8], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 72] setnp al sete cl and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 80] setnp al sete cl and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 88] setnp al sete bl @@ -3476,22 +3679,22 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 104] setnp al sete cl and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 112] setnp al sete cl and cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 120] setnp al sete cl and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 128] setnp al sete cl @@ -3501,27 +3704,27 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 176], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 144] setnp al sete cl and cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 152] setnp al sete cl and cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 208], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 160] setnp al sete cl and cl, al - mov byte ptr [rsp + 192], cl # 1-byte Spill + mov byte ptr [rsp + 224], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 168] setnp al sete cl and cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 176] setnp al sete r15b @@ -3534,7 +3737,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 208], cl # 1-byte Spill + mov byte ptr [rsp + 192], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 200] setnp al sete r11b @@ -3551,12 +3754,12 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill + mov byte ptr [rsp + 240], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 232] setnp al sete cl and cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill + mov byte ptr [rsp + 256], cl # 1-byte Spill ucomisd xmm0, qword ptr [rsi + 240] setnp al sete dil @@ -3566,618 +3769,415 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 sete dl and dl, al add r13b, r13b - add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 32] # 1-byte Folded Reload mov eax, r13d shl r12b, 5 - movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 64] # 1-byte Folded Reload shl r13b, 6 or r13b, r12b - movzx r12d, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 48] # 1-byte Folded Reload shl r12b, 2 or r12b, al - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload + add cl, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, r13b - mov byte ptr [rsp + 4], al # 1-byte Spill - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + mov byte ptr [rsp + 8], al # 1-byte Spill + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 3 or al, r12b shl bl, 3 or bl, cl - movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 4 or al, bl - mov byte ptr [rsp + 8], al # 1-byte Spill - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + mov byte ptr [rsp + 24], al # 1-byte Spill + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload shl cl, 5 - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 6 or al, cl mov ecx, eax - movzx r14d, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx r14d, byte ptr [rsp + 112] # 1-byte Folded Reload shl r14b, 7 or r14b, al - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 88] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload shl bl, 2 or bl, cl - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload shl cl, 3 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 4 or cl, bl - mov r12d, ecx - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload or al, r13b - movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 5 shl r15b, 6 or r15b, bl - or r14b, byte ptr [rsp + 8] # 1-byte Folded Reload + or r14b, byte ptr [rsp + 24] # 1-byte Folded Reload shl r8b, 7 or r8b, r15b - or r8b, r12b + or r8b, cl add r11b, r11b - add r11b, byte ptr [rsp + 208] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 192] # 1-byte Folded Reload shl r10b, 2 or r10b, r11b shl r9b, 3 or r9b, r10b - movzx ebx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl bl, 4 - or bl, r9b - mov r9d, ebx - mov byte ptr [rcx], al - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 5 + movzx ecx, byte ptr [rsp + 240] # 1-byte Folded Reload + shl cl, 4 + or cl, r9b + mov ebx, ecx + mov byte ptr [r12], al + movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload + shl cl, 5 shl dil, 6 - or dil, bl - mov byte ptr [rcx + 1], r14b + or dil, cl + mov byte ptr [r12 + 1], r14b shl dl, 7 or dl, dil - or dl, r9b - mov byte ptr [rcx + 2], r8b - mov byte ptr [rcx + 3], dl + or dl, bl + mov byte ptr [r12 + 2], r8b + mov byte ptr [r12 + 3], dl add rsi, 256 - add rcx, 4 - mov r14, rcx - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB1_52 -# %bb.53: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 272] # 8-byte Reload -.LBB1_54: - shl r11, 5 - cmp r11, r10 - jge .LBB1_199 + add r12, 4 + add qword ptr [rsp + 288], -1 # 8-byte Folded Spill + jne .LBB1_54 # %bb.55: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB1_195 -# %bb.56: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r14, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 144] # 8-byte Reload +.LBB1_56: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_222 +# %bb.57: + movq xmm0, r14 + or rax, 1 + cmp r15, rax + jne .LBB1_218 +# %bb.58: xor r11d, r11d - jmp .LBB1_197 + jmp .LBB1_220 .LBB1_2: cmp edi, 2 - je .LBB1_57 + je .LBB1_59 # %bb.3: cmp edi, 3 - jne .LBB1_199 + jne .LBB1_222 # %bb.4: - mov r11b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + mov r14b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_8 -# %bb.5: - movsxd rax, r9d + je .LBB1_5 +# %bb.88: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_89 +# %bb.94: + movsxd rdx, r9d + mov r13, r8 .p2align 4, 0x90 -.LBB1_6: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r11b - lea rsi, [rsi + 1] - sete dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r12, r14 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB1_95: # =>This Inner Loop Header: Depth=1 + lea r11, [rsi + 1] + cmp byte ptr [rsi], r14b + sete bl + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov rax, r12 + movzx r9d, byte ptr [r12 + rsi] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_6 -# %bb.7: - add r14, 1 -.LBB1_8: - sar r15, 5 - cmp r10, 32 - jl .LBB1_9 -# %bb.83: - cmp r15, 16 - mov byte ptr [rsp + 4], r11b # 1-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 256], r15 # 8-byte Spill - jb .LBB1_84 -# %bb.85: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp r14, rax - jae .LBB1_87 -# %bb.86: - lea rax, [r14 + 4*r15] - cmp rsi, rax - jae .LBB1_87 -.LBB1_84: - xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov qword ptr [rsp + 88], r14 # 8-byte Spill -.LBB1_90: - sub r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r15 # 8-byte Spill + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rsi], dil + add rdx, 1 + mov rsi, r11 + add r13, -1 + jne .LBB1_95 +# %bb.90: + sub r15, r8 + jne .LBB1_91 + jmp .LBB1_222 +.LBB1_26: + cmp edi, 7 + je .LBB1_163 +# %bb.27: + cmp edi, 8 + jne .LBB1_222 +# %bb.28: + mov r13, qword ptr [rdx] + lea ecx, [r9 + 7] + test r9d, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB1_34 +# %bb.29: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_32 +# %bb.30: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_91: # =>This Inner Loop Header: Depth=1 +.LBB1_31: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + sete bl + neg bl + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 + # kill: def $cl killed $cl killed $ecx + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 mov rcx, rsi - cmp byte ptr [rsi], r11b - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [rsi + 1], r11b - sete sil - cmp byte ptr [rcx + 2], r11b - sete r15b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 3], al - sete r12b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 4], al - sete byte ptr [rsp + 176] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 5], al - sete byte ptr [rsp + 56] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 6], al - sete byte ptr [rsp + 208] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 7], al + add r11, -1 + jne .LBB1_31 +.LBB1_32: + sub r15, r8 + je .LBB1_222 +# %bb.33: + add r12, 1 +.LBB1_34: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_38 +# %bb.35: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB1_36: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill + cmp qword ptr [rsi], r13 + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp qword ptr [rsi + 8], r13 sete r9b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 8], al - sete byte ptr [rsp + 192] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 9], al - sete dl - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 10], al - sete dil - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 11], al - sete r10b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 12], al + cmp qword ptr [rsi + 16], r13 sete r14b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 13], al - sete r13b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], al + cmp qword ptr [rsi + 24], r13 + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 sete byte ptr [rsp + 112] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], al - sete r8b - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], bl - sete byte ptr [rsp + 120] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], bl - sete byte ptr [rsp + 128] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], bl - sete byte ptr [rsp + 96] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], bl - sete byte ptr [rsp + 104] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], bl + cmp qword ptr [rsi + 40], r13 sete byte ptr [rsp + 80] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], bl - sete byte ptr [rsp + 64] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], bl - sete byte ptr [rsp + 72] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], bl + cmp qword ptr [rsi + 48], r13 + sete al + cmp qword ptr [rsi + 56], r13 sete r11b - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], bl - sete byte ptr [rsp + 32] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], bl - sete byte ptr [rsp + 48] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], bl - sete byte ptr [rsp + 24] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], bl - sete byte ptr [rsp + 16] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], bl - sete byte ptr [rsp + 40] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], bl - sete byte ptr [rsp + 8] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], bl - sete byte ptr [rsp + 136] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], bl - sete bl - add sil, sil - add sil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 6 - shl r9b, 7 - or r9b, al - shl r15b, 2 - or r15b, sil - add dl, dl - add dl, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - movzx r15d, byte ptr [rsp + 4] # 1-byte Folded Reload - shl dil, 2 - or dil, dl - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 4 - or al, r12b - shl r10b, 3 - or r10b, dil - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 - or dl, al - shl r14b, 4 - or r14b, r10b - shl r13b, 5 - or r13b, r14b - movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r9b, dl - or r8b, r13b - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 120] # 1-byte Folded Reload - mov esi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 2 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov esi, edx - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - mov byte ptr [rdx], r9b - movzx edi, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dil, 6 - shl r11b, 7 - or r11b, dil - mov byte ptr [rdx + 1], r8b - or r11b, sil - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 5 - or al, sil - movzx esi, byte ptr [rsp + 136] # 1-byte Folded Reload - shl sil, 6 - shl bl, 7 - or bl, sil - or bl, al - mov byte ptr [rdx + 2], r11b - mov r11d, r15d - mov byte ptr [rdx + 3], bl - lea rsi, [rcx + 32] - add rdx, 4 - mov qword ptr [rsp + 88], rdx # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB1_91 -# %bb.92: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r15, qword ptr [rsp + 256] # 8-byte Reload - jmp .LBB1_93 -.LBB1_28: - cmp edi, 7 - je .LBB1_146 -# %bb.29: - cmp edi, 8 - jne .LBB1_199 -# %bb.30: - mov r13, qword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB1_34 -# %bb.31: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB1_32: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_32 -# %bb.33: - add r14, 1 -.LBB1_34: - sar r11, 5 - cmp r10, 32 - jl .LBB1_38 -# %bb.35: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB1_36: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 136], r14 # 8-byte Spill - cmp qword ptr [rsi], r13 - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 - sete r10b - cmp qword ptr [rsi + 16], r13 - sete r14b - cmp qword ptr [rsi + 24], r13 - sete byte ptr [rsp + 176] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 - sete al - cmp qword ptr [rsi + 56], r13 - sete bl cmp qword ptr [rsi + 64], r13 - sete byte ptr [rsp + 192] # 1-byte Folded Spill + sete byte ptr [rsp + 224] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 - sete dil + sete cl cmp qword ptr [rsi + 80], r13 - sete r8b + sete dil cmp qword ptr [rsi + 88], r13 - sete r9b + sete r8b cmp qword ptr [rsi + 96], r13 - sete r11b + sete r10b cmp qword ptr [rsi + 104], r13 sete r12b cmp qword ptr [rsi + 112], r13 - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 208] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - sete cl + sete dl cmp qword ptr [rsi + 128], r13 - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 176] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 sete r15b cmp qword ptr [rsi + 192], r13 - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - sete byte ptr [rsp + 24] # 1-byte Folded Spill + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill cmp qword ptr [rsi + 232], r13 - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp qword ptr [rsi + 240], r13 - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 8] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - sete dl - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload + sete bl + add r9b, r9b + add r9b, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 3 or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 136] # 8-byte Reload - shl r8b, 2 + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b + or al, cl + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or r12b, r10b + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 - or al, dil - mov edi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 6 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 6 shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl + or r15b, cl + mov byte ptr [r12 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload + add al, byte ptr [rsp + 40] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, cl - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rsi, 256 - add r14, 4 - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill + add r12, 4 + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill jne .LBB1_36 # %bb.37: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 240] # 8-byte Reload .LBB1_38: - shl r11, 5 - cmp r11, r10 - jge .LBB1_199 + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_222 # %bb.39: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 + or rax, 1 + cmp r15, rax je .LBB1_40 -# %bb.158: +# %bb.177: mov r10, r8 and r10, -2 xor r11d, r11d .p2align 4, 0x90 -.LBB1_159: # =>This Inner Loop Header: Depth=1 +.LBB1_178: # =>This Inner Loop Header: Depth=1 cmp qword ptr [rsi], r13 sete al neg al mov rdi, r11 shr rdi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rdi] + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -4185,7 +4185,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r14 + rdi], bl + mov byte ptr [r12 + rdi], bl add r11, 2 cmp qword ptr [rsi + 8], r13 lea rsi, [rsi + 16] @@ -4197,702 +4197,202 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 shl dl, cl and dl, al xor dl, bl - mov byte ptr [r14 + rdi], dl + mov byte ptr [r12 + rdi], dl cmp r10, r11 - jne .LBB1_159 + jne .LBB1_178 jmp .LBB1_41 -.LBB1_57: - mov r11b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 +.LBB1_114: + movzx r13d, word ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_61 -# %bb.58: - movsxd rax, r9d + je .LBB1_120 +# %bb.115: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_118 +# %bb.116: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_59: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r11b - lea rsi, [rsi + 1] - sete dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r12, r14 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB1_117: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + sete bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_59 -# %bb.60: - add r14, 1 -.LBB1_61: - sar r15, 5 - cmp r10, 32 - jl .LBB1_62 -# %bb.63: - cmp r15, 16 - mov byte ptr [rsp + 4], r11b # 1-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 256], r15 # 8-byte Spill - jb .LBB1_64 -# %bb.65: - mov rax, r15 - shl rax, 5 + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_117 +.LBB1_118: + sub r15, r8 + je .LBB1_222 +# %bb.119: + add r12, 1 +.LBB1_120: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB1_121 +# %bb.122: + cmp rcx, 8 + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rcx # 8-byte Spill + jb .LBB1_123 +# %bb.124: + mov rax, rcx + shl rax, 6 add rax, rsi - cmp r14, rax - jae .LBB1_67 -# %bb.66: - lea rax, [r14 + 4*r15] - cmp rsi, rax - jae .LBB1_67 -.LBB1_64: + cmp r12, rax + jae .LBB1_126 +# %bb.125: + lea rax, [r12 + 4*rcx] + cmp rax, rsi + jbe .LBB1_126 +.LBB1_123: xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov qword ptr [rsp + 56], r14 # 8-byte Spill -.LBB1_70: - sub r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 8], r12 # 8-byte Spill +.LBB1_129: + sub rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov qword ptr [rsp + 256], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB1_71: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp byte ptr [rsi], r11b - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp byte ptr [rsi + 1], r11b +.LBB1_130: # =>This Inner Loop Header: Depth=1 + mov r11, rsi + cmp word ptr [rsi], r13w + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [rsi + 2], r13w + sete r8b + cmp word ptr [rsi + 4], r13w + sete r14b + cmp word ptr [rsi + 6], r13w + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp word ptr [rsi + 8], r13w + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp word ptr [rsi + 10], r13w + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp word ptr [rsi + 12], r13w + sete al + cmp word ptr [rsi + 14], r13w + sete bl + cmp word ptr [rsi + 16], r13w + sete byte ptr [rsp + 224] # 1-byte Folded Spill + cmp word ptr [rsi + 18], r13w + sete cl + cmp word ptr [rsi + 20], r13w sete sil - cmp byte ptr [rcx + 2], r11b - sete r15b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 3], al + cmp word ptr [r11 + 22], r13w + sete r9b + cmp word ptr [r11 + 24], r13w + sete r10b + cmp word ptr [r11 + 26], r13w sete r12b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 4], al - sete byte ptr [rsp + 176] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 5], al - sete byte ptr [rsp + 64] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 6], al + cmp word ptr [r11 + 28], r13w sete byte ptr [rsp + 208] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 7], al - sete r9b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 8], al - sete byte ptr [rsp + 192] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 9], al - sete dl - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 10], al + cmp word ptr [r11 + 30], r13w sete dil - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 11], al - sete r10b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 12], al - sete r14b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 13], al - sete r13b - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], al - sete byte ptr [rsp + 112] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], al - sete r8b - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], bl - sete byte ptr [rsp + 120] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], bl - sete byte ptr [rsp + 128] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], bl - sete byte ptr [rsp + 96] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], bl + cmp word ptr [r11 + 32], r13w sete byte ptr [rsp + 104] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], bl - sete byte ptr [rsp + 80] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], bl - sete byte ptr [rsp + 72] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], bl + cmp word ptr [r11 + 34], r13w + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp word ptr [r11 + 36], r13w + sete byte ptr [rsp + 176] # 1-byte Folded Spill + cmp word ptr [r11 + 38], r13w + sete byte ptr [rsp + 96] # 1-byte Folded Spill + cmp word ptr [r11 + 40], r13w sete byte ptr [rsp + 88] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], bl - sete r11b - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], bl + cmp word ptr [r11 + 42], r13w + sete byte ptr [rsp + 72] # 1-byte Folded Spill + cmp word ptr [r11 + 44], r13w + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp word ptr [r11 + 46], r13w + sete r15b + cmp word ptr [r11 + 48], r13w + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp word ptr [r11 + 50], r13w + sete byte ptr [rsp + 56] # 1-byte Folded Spill + cmp word ptr [r11 + 52], r13w sete byte ptr [rsp + 32] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], bl + cmp word ptr [r11 + 54], r13w sete byte ptr [rsp + 48] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], bl - sete byte ptr [rsp + 24] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], bl + cmp word ptr [r11 + 56], r13w sete byte ptr [rsp + 16] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], bl - sete byte ptr [rsp + 40] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], bl - sete byte ptr [rsp + 8] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], bl - sete byte ptr [rsp + 136] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 4] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], bl - sete bl - add sil, sil - add sil, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 6 - shl r9b, 7 - or r9b, al - shl r15b, 2 - or r15b, sil - add dl, dl - add dl, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - movzx r15d, byte ptr [rsp + 4] # 1-byte Folded Reload - shl dil, 2 - or dil, dl - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 4 - or al, r12b - shl r10b, 3 - or r10b, dil - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 5 - or dl, al - shl r14b, 4 - or r14b, r10b - shl r13b, 5 - or r13b, r14b - movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r9b, dl - or r8b, r13b - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 120] # 1-byte Folded Reload - mov esi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 2 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov esi, edx - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - mov byte ptr [rdx], r9b - movzx edi, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dil, 6 - shl r11b, 7 - or r11b, dil - mov byte ptr [rdx + 1], r8b - or r11b, sil - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 5 - or al, sil - movzx esi, byte ptr [rsp + 136] # 1-byte Folded Reload - shl sil, 6 - shl bl, 7 - or bl, sil - or bl, al - mov byte ptr [rdx + 2], r11b - mov r11d, r15d - mov byte ptr [rdx + 3], bl - lea rsi, [rcx + 32] - add rdx, 4 - mov qword ptr [rsp + 56], rdx # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB1_71 -# %bb.72: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r15, qword ptr [rsp + 256] # 8-byte Reload - jmp .LBB1_73 -.LBB1_146: - mov r13d, dword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB1_150 -# %bb.147: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB1_148: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_148 -# %bb.149: - add r14, 1 -.LBB1_150: - sar r11, 5 - cmp r10, 32 - jl .LBB1_154 -# %bb.151: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB1_152: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 136], r14 # 8-byte Spill - cmp dword ptr [rsi], r13d - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - sete r10b - cmp dword ptr [rsi + 8], r13d - sete r14b - cmp dword ptr [rsi + 12], r13d - sete byte ptr [rsp + 176] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - sete al - cmp dword ptr [rsi + 28], r13d - sete bl - cmp dword ptr [rsi + 32], r13d - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d - sete dil - cmp dword ptr [rsi + 40], r13d - sete r8b - cmp dword ptr [rsi + 44], r13d - sete r9b - cmp dword ptr [rsi + 48], r13d - sete r11b - cmp dword ptr [rsi + 52], r13d - sete r12b - cmp dword ptr [rsi + 56], r13d - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - sete cl - cmp dword ptr [rsi + 64], r13d - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - sete byte ptr [rsp + 56] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d - sete r15b - cmp dword ptr [rsi + 96], r13d - sete byte ptr [rsp + 16] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - sete byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - sete byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - sete byte ptr [rsp + 24] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d - sete byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d - sete byte ptr [rsp + 8] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - sete byte ptr [rsp + 4] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - sete dl - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al - shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 136] # 8-byte Reload - shl r8b, 2 - or r8b, dil - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b - shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl - add rsi, 128 - add r14, 4 - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB1_152 -# %bb.153: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB1_154: - shl r11, 5 - cmp r11, r10 - jge .LBB1_199 -# %bb.155: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB1_156 -.LBB1_23: - xor r11d, r11d - jmp .LBB1_24 -.LBB1_101: - movzx r11d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB1_105 -# %bb.102: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB1_103: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r11w - lea rsi, [rsi + 2] - sete dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r12, r14 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_103 -# %bb.104: - add r14, 1 -.LBB1_105: - sar r15, 5 - cmp r10, 32 - jl .LBB1_106 -# %bb.107: - cmp r15, 8 - mov dword ptr [rsp + 4], r11d # 4-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r15 # 8-byte Spill - jb .LBB1_108 -# %bb.109: - mov rax, r15 - shl rax, 6 - add rax, rsi - cmp r14, rax - jae .LBB1_111 -# %bb.110: - lea rax, [r14 + 4*r15] - cmp rax, rsi - jbe .LBB1_111 -.LBB1_108: - xor eax, eax - mov qword ptr [rsp + 32], rax # 8-byte Spill - mov qword ptr [rsp + 8], r14 # 8-byte Spill -.LBB1_114: - sub r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB1_115: # =>This Inner Loop Header: Depth=1 - mov r10, rsi - cmp word ptr [rsi], r11w - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp word ptr [rsi + 2], r11w - sete r8b - cmp word ptr [rsi + 4], r11w - sete r14b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 6], ax - sete r13b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 8], ax - sete byte ptr [rsp + 128] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 10], ax - sete byte ptr [rsp + 88] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 12], ax - sete byte ptr [rsp + 208] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 14], ax - sete bl - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 16], ax - sete byte ptr [rsp + 192] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 18], ax - sete cl - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 20], ax - sete sil - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 22], ax - sete r9b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 24], ax - sete r11b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 26], ax - sete r12b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 28], ax - sete byte ptr [rsp + 112] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 30], ax - sete dil - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 32], dx - sete byte ptr [rsp + 104] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 34], dx - sete byte ptr [rsp + 176] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 36], dx - sete byte ptr [rsp + 120] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 38], dx - sete byte ptr [rsp + 96] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 40], dx - sete byte ptr [rsp + 80] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 42], dx - sete byte ptr [rsp + 72] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 44], dx - sete byte ptr [rsp + 64] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 46], dx - sete r15b - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 48], dx - sete byte ptr [rsp + 24] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 50], dx - sete byte ptr [rsp + 56] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 52], dx - sete byte ptr [rsp + 32] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 54], dx - sete byte ptr [rsp + 48] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 56], dx - sete byte ptr [rsp + 16] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 58], dx - sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 60], dx - sete byte ptr [rsp + 136] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 62], dx - sete dl - add r8b, r8b - add r8b, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + cmp word ptr [r11 + 58], r13w + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp word ptr [r11 + 60], r13w + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp word ptr [r11 + 62], r13w + sete dl + add r8b, r8b + add r8b, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r8b add cl, cl - add cl, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r14b - mov eax, dword ptr [rsp + 4] # 4-byte Reload + add cl, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b shl sil, 2 or sil, cl - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload shl cl, 4 - or cl, r13b + or cl, al mov r8d, ecx shl r9b, 3 or r9b, sil - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r11b, 4 - or r11b, r9b + shl r10b, 4 + or r10b, r9b shl r12b, 5 - or r12b, r11b - mov r11d, eax - movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload + or r12b, r10b + movzx esi, byte ptr [rsp + 208] # 1-byte Folded Reload shl sil, 6 shl dil, 7 or dil, sil or bl, cl or dil, r12b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 2 - or cl, al + or cl, sil mov esi, ecx movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 3 or cl, sil mov esi, ecx - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 4 or cl, sil mov esi, ecx @@ -4910,7 +4410,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 or r15b, sil movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload + add al, byte ptr [rsp + 40] # 1-byte Folded Reload mov ebx, eax movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 @@ -4924,235 +4424,217 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload shl bl, 6 shl dl, 7 or dl, bl or dl, al mov byte ptr [rcx + 2], r15b mov byte ptr [rcx + 3], dl - lea rsi, [r10 + 64] + lea rsi, [r11 + 64] add rcx, 4 mov qword ptr [rsp + 8], rcx # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB1_115 -# %bb.116: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r15, qword ptr [rsp + 240] # 8-byte Reload - jmp .LBB1_117 -.LBB1_124: - movzx r11d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill + jne .LBB1_130 +# %bb.131: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + jmp .LBB1_132 +.LBB1_139: + movzx r13d, word ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB1_128 -# %bb.125: - movsxd rax, r9d + je .LBB1_145 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_143 +# %bb.141: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_126: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r11w - lea rsi, [rsi + 2] - sete dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r12, r14 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB1_142: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + sete bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_126 -# %bb.127: - add r14, 1 -.LBB1_128: - sar r15, 5 - cmp r10, 32 - jl .LBB1_129 -# %bb.130: - cmp r15, 8 - mov dword ptr [rsp + 4], r11d # 4-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r15 # 8-byte Spill - jb .LBB1_131 -# %bb.132: - mov rax, r15 + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_142 +.LBB1_143: + sub r15, r8 + je .LBB1_222 +# %bb.144: + add r12, 1 +.LBB1_145: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB1_146 +# %bb.147: + cmp rcx, 8 + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rcx # 8-byte Spill + jb .LBB1_148 +# %bb.149: + mov rax, rcx shl rax, 6 add rax, rsi - cmp r14, rax - jae .LBB1_134 -# %bb.133: - lea rax, [r14 + 4*r15] + cmp r12, rax + jae .LBB1_151 +# %bb.150: + lea rax, [r12 + 4*rcx] cmp rax, rsi - jbe .LBB1_134 -.LBB1_131: + jbe .LBB1_151 +.LBB1_148: xor eax, eax mov qword ptr [rsp + 32], rax # 8-byte Spill - mov qword ptr [rsp + 8], r14 # 8-byte Spill -.LBB1_137: - sub r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 8], r12 # 8-byte Spill +.LBB1_154: + sub rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov qword ptr [rsp + 256], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB1_138: # =>This Inner Loop Header: Depth=1 - mov r10, rsi - cmp word ptr [rsi], r11w - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp word ptr [rsi + 2], r11w +.LBB1_155: # =>This Inner Loop Header: Depth=1 + mov r11, rsi + cmp word ptr [rsi], r13w + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [rsi + 2], r13w sete r8b - cmp word ptr [rsi + 4], r11w + cmp word ptr [rsi + 4], r13w sete r14b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 6], ax - sete r13b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 8], ax - sete byte ptr [rsp + 128] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 10], ax - sete byte ptr [rsp + 88] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 12], ax - sete byte ptr [rsp + 208] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 14], ax - sete bl - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 16], ax + cmp word ptr [rsi + 6], r13w sete byte ptr [rsp + 192] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 18], ax + cmp word ptr [rsi + 8], r13w + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp word ptr [rsi + 10], r13w + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp word ptr [rsi + 12], r13w + sete al + cmp word ptr [rsi + 14], r13w + sete bl + cmp word ptr [rsi + 16], r13w + sete byte ptr [rsp + 224] # 1-byte Folded Spill + cmp word ptr [rsi + 18], r13w sete cl - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [rsi + 20], ax + cmp word ptr [rsi + 20], r13w sete sil - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 22], ax + cmp word ptr [r11 + 22], r13w sete r9b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 24], ax - sete r11b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 26], ax + cmp word ptr [r11 + 24], r13w + sete r10b + cmp word ptr [r11 + 26], r13w sete r12b - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 28], ax - sete byte ptr [rsp + 112] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 30], ax + cmp word ptr [r11 + 28], r13w + sete byte ptr [rsp + 208] # 1-byte Folded Spill + cmp word ptr [r11 + 30], r13w sete dil - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 32], dx + cmp word ptr [r11 + 32], r13w sete byte ptr [rsp + 104] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 34], dx + cmp word ptr [r11 + 34], r13w + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp word ptr [r11 + 36], r13w sete byte ptr [rsp + 176] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 36], dx - sete byte ptr [rsp + 120] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 38], dx + cmp word ptr [r11 + 38], r13w sete byte ptr [rsp + 96] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 40], dx - sete byte ptr [rsp + 80] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 42], dx + cmp word ptr [r11 + 40], r13w + sete byte ptr [rsp + 88] # 1-byte Folded Spill + cmp word ptr [r11 + 42], r13w sete byte ptr [rsp + 72] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 44], dx + cmp word ptr [r11 + 44], r13w sete byte ptr [rsp + 64] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 46], dx + cmp word ptr [r11 + 46], r13w sete r15b - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 48], dx - sete byte ptr [rsp + 24] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 50], dx + cmp word ptr [r11 + 48], r13w + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp word ptr [r11 + 50], r13w sete byte ptr [rsp + 56] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 52], dx + cmp word ptr [r11 + 52], r13w sete byte ptr [rsp + 32] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 54], dx + cmp word ptr [r11 + 54], r13w sete byte ptr [rsp + 48] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 56], dx + cmp word ptr [r11 + 56], r13w sete byte ptr [rsp + 16] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 58], dx - sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 60], dx - sete byte ptr [rsp + 136] # 1-byte Folded Spill - mov edx, dword ptr [rsp + 4] # 4-byte Reload - cmp word ptr [r10 + 62], dx + cmp word ptr [r11 + 58], r13w + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp word ptr [r11 + 60], r13w + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp word ptr [r11 + 62], r13w sete dl add r8b, r8b - add r8b, byte ptr [rsp + 160] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + add r8b, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al shl r14b, 2 or r14b, r8b add cl, cl - add cl, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r14b - mov eax, dword ptr [rsp + 4] # 4-byte Reload + add cl, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b shl sil, 2 or sil, cl - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload shl cl, 4 - or cl, r13b + or cl, al mov r8d, ecx shl r9b, 3 or r9b, sil - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r11b, 4 - or r11b, r9b + shl r10b, 4 + or r10b, r9b shl r12b, 5 - or r12b, r11b - mov r11d, eax - movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload + or r12b, r10b + movzx esi, byte ptr [rsp + 208] # 1-byte Folded Reload shl sil, 6 shl dil, 7 or dil, sil or bl, cl or dil, r12b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 2 - or cl, al + or cl, sil mov esi, ecx movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 3 or cl, sil mov esi, ecx - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 4 or cl, sil mov esi, ecx @@ -5170,7 +4652,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 or r15b, sil movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload + add al, byte ptr [rsp + 40] # 1-byte Folded Reload mov ebx, eax movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 @@ -5184,318 +4666,344 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload shl bl, 6 shl dl, 7 or dl, bl or dl, al mov byte ptr [rcx + 2], r15b mov byte ptr [rcx + 3], dl - lea rsi, [r10 + 64] + lea rsi, [r11 + 64] add rcx, 4 mov qword ptr [rsp + 8], rcx # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB1_138 -# %bb.139: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r15, qword ptr [rsp + 240] # 8-byte Reload - jmp .LBB1_140 -.LBB1_160: + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill + jne .LBB1_155 +# %bb.156: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + jmp .LBB1_157 +.LBB1_179: mov r13, qword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] + lea ecx, [r9 + 7] test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB1_164 -# %bb.161: - movsxd rax, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB1_185 +# %bb.180: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_183 +# %bb.181: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_162: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - sete dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r14 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB1_182: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + sete bl + neg bl + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB1_162 -# %bb.163: - add r14, 1 -.LBB1_164: - sar r11, 5 - cmp r10, 32 - jl .LBB1_168 -# %bb.165: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 160], r11 # 8-byte Spill + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_182 +.LBB1_183: + sub r15, r8 + je .LBB1_222 +# %bb.184: + add r12, 1 +.LBB1_185: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_189 +# %bb.186: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill .p2align 4, 0x90 -.LBB1_166: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 136], r14 # 8-byte Spill +.LBB1_187: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill cmp qword ptr [rsi], r13 - sete byte ptr [rsp + 208] # 1-byte Folded Spill + sete byte ptr [rsp + 128] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 - sete r10b + sete r9b cmp qword ptr [rsi + 16], r13 sete r14b cmp qword ptr [rsi + 24], r13 - sete byte ptr [rsp + 176] # 1-byte Folded Spill + sete byte ptr [rsp + 192] # 1-byte Folded Spill cmp qword ptr [rsi + 32], r13 - sete byte ptr [rsp + 96] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp qword ptr [rsi + 40], r13 - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 48], r13 sete al cmp qword ptr [rsi + 56], r13 - sete bl + sete r11b cmp qword ptr [rsi + 64], r13 - sete byte ptr [rsp + 192] # 1-byte Folded Spill + sete byte ptr [rsp + 224] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 - sete dil + sete cl cmp qword ptr [rsi + 80], r13 - sete r8b + sete dil cmp qword ptr [rsi + 88], r13 - sete r9b + sete r8b cmp qword ptr [rsi + 96], r13 - sete r11b + sete r10b cmp qword ptr [rsi + 104], r13 sete r12b cmp qword ptr [rsi + 112], r13 - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 208] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - sete cl + sete dl cmp qword ptr [rsi + 128], r13 - sete byte ptr [rsp + 80] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 176] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 sete r15b cmp qword ptr [rsi + 192], r13 - sete byte ptr [rsp + 16] # 1-byte Folded Spill + sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - sete byte ptr [rsp + 32] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 - sete byte ptr [rsp + 24] # 1-byte Folded Spill + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 - sete byte ptr [rsp + 40] # 1-byte Folded Spill + sete byte ptr [rsp + 16] # 1-byte Folded Spill cmp qword ptr [rsi + 232], r13 - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp qword ptr [rsi + 240], r13 - sete byte ptr [rsp + 4] # 1-byte Folded Spill + sete byte ptr [rsp + 8] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - sete dl - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload + sete bl + add r9b, r9b + add r9b, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 3 or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 136] # 8-byte Reload - shl r8b, 2 + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b + or al, cl + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or r12b, r10b + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 80] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 104] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 - or al, dil - mov edi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 6 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 6 shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl + or r15b, cl + mov byte ptr [r12 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload + add al, byte ptr [rsp + 40] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, cl - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rsi, 256 - add r14, 4 - add qword ptr [rsp + 160], -1 # 8-byte Folded Spill - jne .LBB1_166 -# %bb.167: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB1_168: - shl r11, 5 - cmp r11, r10 - jge .LBB1_199 -# %bb.169: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB1_170 + add r12, 4 + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill + jne .LBB1_187 +# %bb.188: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 240] # 8-byte Reload +.LBB1_189: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_222 +# %bb.190: + or rax, 1 + cmp r15, rax + jne .LBB1_191 .LBB1_40: xor r11d, r11d jmp .LBB1_41 -.LBB1_172: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 +.LBB1_193: + mov r14d, dword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB1_176 -# %bb.173: - movsxd rax, r9d + je .LBB1_199 +# %bb.194: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_197 +# %bb.195: + movsxd rdx, r9d + movd xmm0, r14d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_174: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rsi] - lea rsi, [rsi + 4] +.LBB1_196: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rcx] + lea rsi, [rcx + 4] setnp cl - sete dl - and dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + sete bl + and bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB1_174 -# %bb.175: - add r14, 1 -.LBB1_176: - sar r11, 5 - cmp r10, 32 - jl .LBB1_177 -# %bb.178: - cmp r11, 4 - jb .LBB1_179 -# %bb.180: - mov rax, r11 + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_196 +.LBB1_197: + sub r15, r8 + je .LBB1_222 +# %bb.198: + add r12, 1 +.LBB1_199: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB1_200 +# %bb.201: + movd xmm0, r14d + cmp rcx, 4 + jb .LBB1_202 +# %bb.203: + mov rax, rcx shl rax, 7 add rax, rsi - cmp r14, rax - jae .LBB1_182 -# %bb.181: - lea rax, [r14 + 4*r11] + cmp r12, rax + jae .LBB1_205 +# %bb.204: + lea rax, [r12 + 4*rcx] cmp rax, rsi - jbe .LBB1_182 -.LBB1_179: - xor r8d, r8d + jbe .LBB1_205 +.LBB1_202: + xor eax, eax mov rbx, rsi - mov r15, r14 -.LBB1_185: + mov r13, r12 +.LBB1_208: + mov qword ptr [rsp + 120], r13 # 8-byte Spill + mov dword ptr [rsp + 288], r14d # 4-byte Spill mov qword ptr [rsp + 136], r15 # 8-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill - sub r11, r8 - mov qword ptr [rsp + 152], r11 # 8-byte Spill + mov qword ptr [rsp + 152], rcx # 8-byte Spill + sub rcx, rax + mov qword ptr [rsp + 240], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB1_186: # =>This Inner Loop Header: Depth=1 +.LBB1_209: # =>This Inner Loop Header: Depth=1 ucomiss xmm0, dword ptr [rbx] setnp al sete cl @@ -5509,52 +5017,52 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 12] setnp al sete cl and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 16] setnp al sete cl and cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 20] setnp al sete cl and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 24] setnp al sete cl and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 28] setnp al sete cl and cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill + mov byte ptr [rsp + 8], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 32] setnp al sete cl and cl, al - mov byte ptr [rsp + 24], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 36] setnp al sete cl and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 40] setnp al sete cl and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 44] setnp al sete cl and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 48] setnp al sete cl @@ -5564,22 +5072,22 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 56] setnp al sete cl and cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 176], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 60] setnp al sete cl and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 68] setnp al sete r12b @@ -5588,22 +5096,22 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 76] setnp al sete cl and cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 208], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 80] setnp al sete cl and cl, al - mov byte ptr [rsp + 192], cl # 1-byte Spill + mov byte ptr [rsp + 224], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 84] setnp al sete cl and cl, al - mov byte ptr [rsp + 208], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 88] setnp al sete r14b @@ -5616,7 +5124,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill + mov byte ptr [rsp + 192], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 100] setnp al sete r11b @@ -5637,7 +5145,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill + mov byte ptr [rsp + 256], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 120] setnp al sete dil @@ -5649,65 +5157,65 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 add dl, dl or dl, r13b mov r13d, edx - movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload shl dl, 5 - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 6 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, r13b mov r13d, eax - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 24] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, dl - mov byte ptr [rsp + 4], al # 1-byte Spill - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + mov byte ptr [rsp + 8], al # 1-byte Spill + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 3 or al, r13b mov r13d, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 4 or al, r13b movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload shl dl, 4 or dl, cl - movzx r13d, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 96] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 6 or cl, r13b - movzx r13d, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 112] # 1-byte Folded Reload shl r13b, 7 or r13b, cl add r12b, r12b - add r12b, byte ptr [rsp + 80] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 104] # 1-byte Folded Reload mov ecx, r12d - movzx r12d, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 160] # 1-byte Folded Reload shl r12b, 2 or r12b, cl - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload shl cl, 3 or cl, r12b mov r12d, ecx - movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 4 or cl, r12b - movzx r12d, byte ptr [rsp + 4] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 8] # 1-byte Folded Reload or r12b, al - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 5 shl r14b, 6 or r14b, al @@ -5716,16 +5224,16 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 or r8b, r14b or r8b, cl add r11b, r11b - add r11b, byte ptr [rsp + 176] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 192] # 1-byte Folded Reload shl r10b, 2 or r10b, r11b shl r9b, 3 or r9b, r10b shl r15b, 4 or r15b, r9b - mov rax, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 120] # 8-byte Reload mov byte ptr [rax], r12b - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload shl cl, 5 shl dil, 6 or dil, cl @@ -5737,405 +5245,333 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 mov byte ptr [rax + 3], sil add rbx, 128 add rax, 4 - mov qword ptr [rsp + 136], rax # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB1_186 -# %bb.187: + mov qword ptr [rsp + 120], rax # 8-byte Spill + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB1_209 +# %bb.210: + mov r13, qword ptr [rsp + 120] # 8-byte Reload mov r15, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 240] # 8-byte Reload - jmp .LBB1_188 -.LBB1_9: - mov qword ptr [rsp + 88], r14 # 8-byte Spill -.LBB1_93: - shl r15, 5 - cmp r15, r10 - jge .LBB1_199 -# %bb.94: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_96 -# %bb.95: - xor r9d, r9d - jmp .LBB1_99 -.LBB1_62: - mov qword ptr [rsp + 56], r14 # 8-byte Spill -.LBB1_73: - shl r15, 5 - cmp r15, r10 - jge .LBB1_199 -# %bb.74: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_76 -# %bb.75: - xor r9d, r9d - jmp .LBB1_79 -.LBB1_106: - mov qword ptr [rsp + 8], r14 # 8-byte Spill -.LBB1_117: - shl r15, 5 - cmp r15, r10 - jge .LBB1_199 -# %bb.118: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB1_119 -# %bb.122: - mov r9, r8 - and r9, -2 - xor r15d, r15d - mov r14, qword ptr [rsp + 8] # 8-byte Reload - .p2align 4, 0x90 -.LBB1_123: # =>This Inner Loop Header: Depth=1 - mov rax, rsi - cmp word ptr [rsi], r11w - sete dl - neg dl - mov rdi, r15 - shr rdi, 3 - movzx r10d, byte ptr [r14 + rdi] - mov ecx, r15d - and cl, 6 - mov bl, 1 - shl bl, cl - xor dl, r10b - and bl, dl - xor bl, r10b - mov byte ptr [r14 + rdi], bl - add r15, 2 - cmp word ptr [rsi + 2], r11w - lea rsi, [rsi + 4] - sete dl - neg dl - xor dl, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, bl - mov byte ptr [r14 + rdi], al - cmp r9, r15 - jne .LBB1_123 - jmp .LBB1_120 -.LBB1_129: - mov qword ptr [rsp + 8], r14 # 8-byte Spill -.LBB1_140: - shl r15, 5 - cmp r15, r10 - jge .LBB1_199 -# %bb.141: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB1_142 -.LBB1_119: - xor r15d, r15d - jmp .LBB1_120 -.LBB1_177: - mov r15, r14 - mov rbx, rsi -.LBB1_188: - shl r11, 5 - cmp r11, r10 - jge .LBB1_199 -# %bb.189: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB1_193 -# %bb.190: - xor esi, esi - jmp .LBB1_191 -.LBB1_156: - mov r10, r8 - and r10, -2 - xor r11d, r11d + mov r14d, dword ptr [rsp + 288] # 4-byte Reload + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + jmp .LBB1_211 +.LBB1_59: + mov r11b, byte ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB1_60 +# %bb.61: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_62 +# %bb.67: + movsxd rdx, r9d + mov rax, r8 .p2align 4, 0x90 -.LBB1_157: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - sete al - neg al - mov rdi, r11 - shr rdi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al +.LBB1_68: # =>This Inner Loop Header: Depth=1 + lea r14, [rsi + 1] + cmp byte ptr [rsi], r11b + sete bl + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rsi] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - sete al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r10, r11 - jne .LBB1_157 -.LBB1_24: - test r8b, 1 - je .LBB1_199 -# %bb.25: - cmp dword ptr [rsi], r13d - jmp .LBB1_26 -.LBB1_96: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 88] # 8-byte Reload + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rsi], dil + add rdx, 1 + mov rsi, r14 + add rax, -1 + jne .LBB1_68 +# %bb.63: + sub r15, r8 + jne .LBB1_64 + jmp .LBB1_222 +.LBB1_163: + mov r13d, dword ptr [rdx] + lea ecx, [r9 + 7] + test r9d, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB1_169 +# %bb.164: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB1_167 +# %bb.165: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB1_97: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r11b +.LBB1_166: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d sete bl neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r14 + rdi] - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp byte ptr [rsi + rax + 1], r11b - lea r9, [rax + 2] - sete bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, r9 - jne .LBB1_97 -# %bb.98: - add rsi, r9 -.LBB1_99: - test r8b, 1 - je .LBB1_199 -# %bb.100: - cmp byte ptr [rsi], r11b - sete al - neg al - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - jmp .LBB1_81 -.LBB1_76: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 56] # 8-byte Reload - .p2align 4, 0x90 -.LBB1_77: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r11b - sete bl - neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r14 + rdi] + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 + # kill: def $cl killed $cl killed $ecx + shl edx, cl and dl, bl xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp byte ptr [rsi + rax + 1], r11b - lea r9, [rax + 2] - sete bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, r9 - jne .LBB1_77 -# %bb.78: - add rsi, r9 -.LBB1_79: - test r8b, 1 - je .LBB1_199 -# %bb.80: - cmp byte ptr [rsi], r11b - sete al - neg al - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 56] # 8-byte Reload -.LBB1_81: - mov dil, byte ptr [r8 + rdx] - and r9b, 7 - mov bl, 1 - mov ecx, r9d - jmp .LBB1_82 -.LBB1_195: - mov r9, r8 - and r9, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB1_196: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rsi] - setnp cl - sete al - and al, cl - neg al - mov rdi, r11 - shr rdi, 3 - mov r15, r14 - movzx r10d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r10b - and bl, al - xor bl, r10b - mov byte ptr [r14 + rdi], bl - add r11, 2 - ucomisd xmm0, qword ptr [rsi + 8] - lea rsi, [rsi + 16] - setnp r10b - sete al - and al, r10b - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r9, r11 - jne .LBB1_196 -.LBB1_197: - test r8b, 1 - je .LBB1_199 -# %bb.198: - ucomisd xmm0, qword ptr [rsi] - setnp al - sete dl - and dl, al - neg dl - mov rax, r11 - shr rax, 3 - mov sil, byte ptr [r14 + rax] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor dl, sil - and bl, dl - xor bl, sil - mov byte ptr [r14 + rax], bl - jmp .LBB1_199 -.LBB1_170: - mov r10, r8 - and r10, -2 - xor r11d, r11d + mov byte ptr [r12 + rax], dl + add rdi, 1 + mov rcx, rsi + add r11, -1 + jne .LBB1_166 +.LBB1_167: + sub r15, r8 + je .LBB1_222 +# %bb.168: + add r12, 1 +.LBB1_169: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB1_173 +# %bb.170: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill .p2align 4, 0x90 .LBB1_171: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - sete al - neg al - mov rdi, r11 - shr rdi, 3 - mov r15, r14 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] + mov qword ptr [rsp + 120], r12 # 8-byte Spill + cmp dword ptr [rsi], r13d + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 4], r13d + sete r9b + cmp dword ptr [rsi + 8], r13d + sete r14b + cmp dword ptr [rsi + 12], r13d + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp dword ptr [rsi + 20], r13d + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 24], r13d sete al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r10, r11 + cmp dword ptr [rsi + 28], r13d + sete r11b + cmp dword ptr [rsi + 32], r13d + sete byte ptr [rsp + 224] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d + sete cl + cmp dword ptr [rsi + 40], r13d + sete dil + cmp dword ptr [rsi + 44], r13d + sete r8b + cmp dword ptr [rsi + 48], r13d + sete r10b + cmp dword ptr [rsi + 52], r13d + sete r12b + cmp dword ptr [rsi + 56], r13d + sete byte ptr [rsp + 208] # 1-byte Folded Spill + cmp dword ptr [rsi + 60], r13d + sete dl + cmp dword ptr [rsi + 64], r13d + sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + sete byte ptr [rsp + 176] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d + sete byte ptr [rsp + 96] # 1-byte Folded Spill + cmp dword ptr [rsi + 80], r13d + sete byte ptr [rsp + 88] # 1-byte Folded Spill + cmp dword ptr [rsi + 84], r13d + sete byte ptr [rsp + 72] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp dword ptr [rsi + 92], r13d + sete r15b + cmp dword ptr [rsi + 96], r13d + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp dword ptr [rsi + 100], r13d + sete byte ptr [rsp + 56] # 1-byte Folded Spill + cmp dword ptr [rsi + 104], r13d + sete byte ptr [rsp + 32] # 1-byte Folded Spill + cmp dword ptr [rsi + 108], r13d + sete byte ptr [rsp + 48] # 1-byte Folded Spill + cmp dword ptr [rsi + 112], r13d + sete byte ptr [rsp + 16] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp dword ptr [rsi + 120], r13d + sete byte ptr [rsp + 8] # 1-byte Folded Spill + cmp dword ptr [rsi + 124], r13d + sete bl + add r9b, r9b + add r9b, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 + or r8b, dil + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, cl + shl r10b, 4 + or r10b, r8b + shl r12b, 5 + or r12b, r10b + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 104] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 6 + shl r15b, 7 + or r15b, cl + mov byte ptr [r12 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 40] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl + add rsi, 128 + add r12, 4 + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill jne .LBB1_171 -.LBB1_41: - test r8b, 1 - je .LBB1_199 -# %bb.42: - cmp qword ptr [rsi], r13 -.LBB1_26: - sete al - neg al - mov rdx, r11 - shr rdx, 3 - mov sil, byte ptr [r14 + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, sil - and bl, al - xor bl, sil - mov byte ptr [r14 + rdx], bl - jmp .LBB1_199 -.LBB1_142: +# %bb.172: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 240] # 8-byte Reload +.LBB1_173: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB1_222 +# %bb.174: + or rax, 1 + cmp r15, rax + jne .LBB1_175 +.LBB1_21: + xor r11d, r11d + jmp .LBB1_22 +.LBB1_5: + mov r11, rsi + jmp .LBB1_92 +.LBB1_121: + mov qword ptr [rsp + 8], r12 # 8-byte Spill +.LBB1_132: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB1_222 +# %bb.133: + or rcx, 1 + cmp r15, rcx + je .LBB1_134 +# %bb.137: mov r9, r8 and r9, -2 - xor r15d, r15d - mov r14, qword ptr [rsp + 8] # 8-byte Reload + xor r14d, r14d + mov r11, qword ptr [rsp + 8] # 8-byte Reload .p2align 4, 0x90 -.LBB1_143: # =>This Inner Loop Header: Depth=1 +.LBB1_138: # =>This Inner Loop Header: Depth=1 mov rax, rsi - cmp word ptr [rsi], r11w + cmp word ptr [rsi], r13w sete dl neg dl - mov rdi, r15 + mov rdi, r14 shr rdi, 3 - movzx r10d, byte ptr [r14 + rdi] - mov ecx, r15d + movzx r10d, byte ptr [r11 + rdi] + mov ecx, r14d and cl, 6 mov bl, 1 shl bl, cl xor dl, r10b and bl, dl xor bl, r10b - mov byte ptr [r14 + rdi], bl - add r15, 2 - cmp word ptr [rsi + 2], r11w + mov byte ptr [r11 + rdi], bl + add r14, 2 + cmp word ptr [rsi + 2], r13w lea rsi, [rsi + 4] sete dl neg dl @@ -6145,2565 +5581,1039 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 shl al, cl and al, dl xor al, bl - mov byte ptr [r14 + rdi], al - cmp r9, r15 - jne .LBB1_143 -.LBB1_120: - test r8b, 1 - je .LBB1_199 -# %bb.121: - cmp word ptr [rsi], r11w - sete al - neg al - mov rdx, r15 - shr rdx, 3 - mov r8, qword ptr [rsp + 8] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and r15b, 7 - mov bl, 1 - mov ecx, r15d -.LBB1_82: - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r8 + rdx], bl -.LBB1_199: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.LBB1_193: - mov r9, r8 - and r9, -2 + mov byte ptr [r11 + rdi], al + cmp r9, r14 + jne .LBB1_138 + jmp .LBB1_135 +.LBB1_146: + mov qword ptr [rsp + 8], r12 # 8-byte Spill +.LBB1_157: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB1_222 +# %bb.158: + or rcx, 1 + cmp r15, rcx + jne .LBB1_159 +.LBB1_134: + xor r14d, r14d + jmp .LBB1_135 +.LBB1_200: + mov r13, r12 + mov rbx, rsi +.LBB1_211: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB1_222 +# %bb.212: + movd xmm0, r14d + or rcx, 1 + cmp r15, rcx + jne .LBB1_216 +# %bb.213: xor esi, esi - .p2align 4, 0x90 -.LBB1_194: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rbx] - setnp cl - sete dl - and dl, cl - neg dl - mov rdi, rsi - shr rdi, 3 - movzx r10d, byte ptr [r15 + rdi] - mov ecx, esi - and cl, 6 - mov r11b, 1 - shl r11b, cl - xor dl, r10b - and r11b, dl - xor r11b, r10b - mov byte ptr [r15 + rdi], r11b - add rsi, 2 - ucomiss xmm0, dword ptr [rbx + 4] - lea rbx, [rbx + 8] - setnp r10b - sete dl - and dl, r10b - mov r10, r15 - neg dl - xor dl, r11b - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, r11b - mov byte ptr [r15 + rdi], al - cmp r9, rsi - jne .LBB1_194 -.LBB1_191: - test r8b, 1 - je .LBB1_199 -# %bb.192: - ucomiss xmm0, dword ptr [rbx] - setnp al - sete dl - and dl, al - neg dl - mov rax, rsi - shr rax, 3 - mov dil, byte ptr [r15 + rax] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor dl, dil - and bl, dl - xor bl, dil - mov byte ptr [r15 + rax], bl - jmp .LBB1_199 -.LBB1_87: - and r15, -16 - mov rax, r15 + jmp .LBB1_214 +.LBB1_60: + mov r14, rsi + jmp .LBB1_65 +.LBB1_89: + mov r11, rsi + sub r15, r8 + je .LBB1_222 +.LBB1_91: + add r12, 1 +.LBB1_92: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB1_93 +# %bb.96: + cmp rcx, 16 + mov byte ptr [rsp + 8], r14b # 1-byte Spill + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 280], rcx # 8-byte Spill + jb .LBB1_97 +# %bb.98: + mov rax, rcx shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 232], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 88], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill + add rax, r11 + cmp r12, rax + jae .LBB1_100 +# %bb.99: + lea rax, [r12 + 4*rcx] + cmp r11, rax + jae .LBB1_100 +.LBB1_97: xor eax, eax - mov qword ptr [rsp + 136], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB1_88: # =>This Inner Loop Header: Depth=1 - mov rdi, rax mov qword ptr [rsp + 152], rax # 8-byte Spill - shl rdi, 5 - mov r11, rdi - mov r15, rdi - mov rbx, rdi - mov r12, rdi - mov r10, rdi - mov r14, rdi - mov r8, rdi - mov r9, rdi - mov rax, rdi - mov rdx, rdi - mov qword ptr [rsp + 104], rdi # 8-byte Spill - movzx ecx, byte ptr [rsi + rdi] - movd xmm15, ecx - movzx ecx, byte ptr [rsi + rdi + 1] - movd xmm5, ecx - movzx ecx, byte ptr [rsi + rdi + 2] - movd xmm6, ecx - movzx ecx, byte ptr [rsi + rdi + 3] - movd xmm2, ecx - movzx ecx, byte ptr [rsi + rdi + 4] - movd xmm1, ecx - movzx ecx, byte ptr [rsi + rdi + 5] - movd xmm8, ecx - movzx ecx, byte ptr [rsi + rdi + 6] - movd xmm3, ecx - movzx ecx, byte ptr [rsi + rdi + 7] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdi + 8] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdi + 9] - movd xmm10, ecx - movzx ecx, byte ptr [rsi + rdi + 10] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdi + 11] - movd xmm11, ecx - movzx ecx, byte ptr [rsi + rdi + 12] - movd xmm13, ecx - movzx ecx, byte ptr [rsi + rdi + 13] - movd xmm12, ecx - movzx ecx, byte ptr [rsi + rdi + 14] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - mov qword ptr [rsp + 40], rdi # 8-byte Spill - mov r13, rdi - or r13, 32 - mov qword ptr [rsp + 8], r13 # 8-byte Spill - mov rcx, rdi - or rcx, 64 - mov qword ptr [rsp + 80], rcx # 8-byte Spill - or r11, 96 - or rbx, 128 - or r15, 160 - or r12, 192 - or r10, 224 - or r14, 256 - or r9, 288 - mov qword ptr [rsp + 120], r9 # 8-byte Spill - or rax, 320 - mov qword ptr [rsp + 16], rax # 8-byte Spill - or rdx, 352 - mov qword ptr [rsp + 208], rdx # 8-byte Spill - mov r8, qword ptr [rsp + 104] # 8-byte Reload - or r8, 384 - mov rax, rdi - or rax, 416 - mov qword ptr [rsp + 24], rax # 8-byte Spill - mov rax, rdi - or rax, 448 - mov qword ptr [rsp + 72], rax # 8-byte Spill - mov rax, rdi - or rax, 480 - pinsrb xmm15, byte ptr [rsi + r13], 1 - pinsrb xmm15, byte ptr [rsi + rcx], 2 - pinsrb xmm15, byte ptr [rsi + r11], 3 - mov qword ptr [rsp + 48], rbx # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + rbx], 4 - mov qword ptr [rsp + 32], r15 # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r15], 5 - pinsrb xmm15, byte ptr [rsi + r12], 6 - mov rdi, r10 - mov qword ptr [rsp + 128], r10 # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r10], 7 - mov r10, r14 - pinsrb xmm15, byte ptr [rsi + r14], 8 - pinsrb xmm15, byte ptr [rsi + r9], 9 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r13], 10 - pinsrb xmm15, byte ptr [rsi + rdx], 11 - pinsrb xmm15, byte ptr [rsi + r8], 12 - mov r14, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r14], 13 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r9], 14 - pinsrb xmm15, byte ptr [rsi + rax], 15 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rcx + 1], 1 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rcx + 1], 2 - pinsrb xmm5, byte ptr [rsi + r11 + 1], 3 - mov rcx, r11 - pinsrb xmm5, byte ptr [rsi + rbx + 1], 4 - pinsrb xmm5, byte ptr [rsi + r15 + 1], 5 - pinsrb xmm5, byte ptr [rsi + r12 + 1], 6 - mov qword ptr [rsp + 112], r12 # 8-byte Spill - pinsrb xmm5, byte ptr [rsi + rdi + 1], 7 - pinsrb xmm5, byte ptr [rsi + r10 + 1], 8 - mov rbx, r10 - mov qword ptr [rsp + 56], r10 # 8-byte Spill - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r15 + 1], 9 - pinsrb xmm5, byte ptr [rsi + r13 + 1], 10 - pinsrb xmm5, byte ptr [rsi + rdx + 1], 11 - pinsrb xmm5, byte ptr [rsi + r8 + 1], 12 - mov r10, r8 - mov qword ptr [rsp + 104], r8 # 8-byte Spill - pinsrb xmm5, byte ptr [rsi + r14 + 1], 13 - pinsrb xmm5, byte ptr [rsi + r9 + 1], 14 - mov r14, r9 - pinsrb xmm5, byte ptr [rsi + rax + 1], 15 - mov r9, rax - movdqa xmm9, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm5, xmm9 - movdqa xmm7, xmm5 - movdqa xmm4, xmmword ptr [rip + .LCPI1_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm7, xmm4 - psubb xmm7, xmm5 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + r8 + 15] - movd xmm14, edx - pcmpeqb xmm15, xmm9 - mov r11, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r11 + 2], 1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rax + 2], 2 - mov r13, rcx - pinsrb xmm6, byte ptr [rsi + rcx + 2], 3 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 2], 4 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdi + 2], 5 - pinsrb xmm6, byte ptr [rsi + r12 + 2], 6 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 2], 7 - pinsrb xmm6, byte ptr [rsi + rbx + 2], 8 - mov rbx, r15 - pinsrb xmm6, byte ptr [rsi + r15 + 2], 9 - mov r15, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r15 + 2], 10 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r12 + 2], 11 - pinsrb xmm6, byte ptr [rsi + r10 + 2], 12 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r10 + 2], 13 - pinsrb xmm6, byte ptr [rsi + r14 + 2], 14 - mov qword ptr [rsp + 64], r9 # 8-byte Spill - pinsrb xmm6, byte ptr [rsi + r9 + 2], 15 - pand xmm15, xmm4 - pcmpeqb xmm6, xmm9 - movdqa xmm0, xmmword ptr [rip + .LCPI1_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm6, xmm0 - por xmm6, xmm15 - movzx edx, byte ptr [rsi + r8 + 16] - movd xmm15, edx - mov rdx, r11 - pinsrb xmm2, byte ptr [rsi + r11 + 3], 1 - pinsrb xmm2, byte ptr [rsi + rax + 3], 2 - pinsrb xmm2, byte ptr [rsi + r13 + 3], 3 - pinsrb xmm2, byte ptr [rsi + rcx + 3], 4 - mov r11, rcx - pinsrb xmm2, byte ptr [rsi + rdi + 3], 5 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 3], 6 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdi + 3], 7 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r8 + 3], 8 - pinsrb xmm2, byte ptr [rsi + rbx + 3], 9 - pinsrb xmm2, byte ptr [rsi + r15 + 3], 10 - mov r15, r12 - pinsrb xmm2, byte ptr [rsi + r12 + 3], 11 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r12 + 3], 12 - pinsrb xmm2, byte ptr [rsi + r10 + 3], 13 - pinsrb xmm2, byte ptr [rsi + r14 + 3], 14 - pinsrb xmm2, byte ptr [rsi + r9 + 3], 15 - pinsrb xmm1, byte ptr [rsi + rdx + 4], 1 - pinsrb xmm1, byte ptr [rsi + rax + 4], 2 - pinsrb xmm1, byte ptr [rsi + r13 + 4], 3 - pinsrb xmm1, byte ptr [rsi + r11 + 4], 4 - mov r11, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r11 + 4], 5 - pinsrb xmm1, byte ptr [rsi + rcx + 4], 6 - pinsrb xmm1, byte ptr [rsi + rdi + 4], 7 - pinsrb xmm1, byte ptr [rsi + r8 + 4], 8 - pinsrb xmm1, byte ptr [rsi + rbx + 4], 9 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rcx + 4], 10 - pinsrb xmm1, byte ptr [rsi + r15 + 4], 11 - pinsrb xmm1, byte ptr [rsi + r12 + 4], 12 - pinsrb xmm1, byte ptr [rsi + r10 + 4], 13 - pinsrb xmm1, byte ptr [rsi + r14 + 4], 14 - mov r8, r14 - pinsrb xmm1, byte ptr [rsi + r9 + 4], 15 - por xmm6, xmm7 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + rdi + 17] - movd xmm0, edx - pcmpeqb xmm2, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI1_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm2, xmm5 - pcmpeqb xmm1, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI1_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm1, xmm5 - por xmm1, xmm2 - movzx edx, byte ptr [rsi + rdi + 18] - movd xmm5, edx - mov r9, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r9 + 5], 1 - pinsrb xmm8, byte ptr [rsi + rax + 5], 2 - pinsrb xmm8, byte ptr [rsi + r13 + 5], 3 - mov qword ptr [rsp + 96], r13 # 8-byte Spill - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdx + 5], 4 - pinsrb xmm8, byte ptr [rsi + r11 + 5], 5 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdi + 5], 6 - mov r12, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r12 + 5], 7 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdx + 5], 8 - pinsrb xmm8, byte ptr [rsi + rbx + 5], 9 - pinsrb xmm8, byte ptr [rsi + rcx + 5], 10 - pinsrb xmm8, byte ptr [rsi + r15 + 5], 11 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rcx + 5], 12 - pinsrb xmm8, byte ptr [rsi + r10 + 5], 13 - mov r14, r10 - pinsrb xmm8, byte ptr [rsi + r8 + 5], 14 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r10 + 5], 15 - pcmpeqb xmm8, xmm9 - movdqa xmm2, xmmword ptr [rip + .LCPI1_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm8, xmm2 - por xmm8, xmm1 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + rcx + 19] - movd xmm7, edx - por xmm8, xmm6 - movzx edx, byte ptr [rsi + rcx + 20] - movd xmm6, edx - pinsrb xmm3, byte ptr [rsi + r9 + 6], 1 - pinsrb xmm3, byte ptr [rsi + rax + 6], 2 - pinsrb xmm3, byte ptr [rsi + r13 + 6], 3 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r11 + 6], 4 - mov r8, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r8 + 6], 5 - mov rcx, rdi - pinsrb xmm3, byte ptr [rsi + rdi + 6], 6 - mov rdi, r12 - pinsrb xmm3, byte ptr [rsi + r12 + 6], 7 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 6], 8 - pinsrb xmm3, byte ptr [rsi + rbx + 6], 9 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 6], 10 - pinsrb xmm3, byte ptr [rsi + r15 + 6], 11 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r12 + 6], 12 - pinsrb xmm3, byte ptr [rsi + r14 + 6], 13 - mov r13, r14 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r14 + 6], 14 - pinsrb xmm3, byte ptr [rsi + r10 + 6], 15 - movdqa xmm2, xmmword ptr [rsp + 176] # 16-byte Reload - pinsrb xmm2, byte ptr [rsi + r9 + 7], 1 - mov r10, rax - pinsrb xmm2, byte ptr [rsi + rax + 7], 2 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 7], 3 - pinsrb xmm2, byte ptr [rsi + r11 + 7], 4 - pinsrb xmm2, byte ptr [rsi + r8 + 7], 5 - pinsrb xmm2, byte ptr [rsi + rcx + 7], 6 - pinsrb xmm2, byte ptr [rsi + rdi + 7], 7 - mov rax, rdi - mov r8, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r8 + 7], 8 - pinsrb xmm2, byte ptr [rsi + rbx + 7], 9 - pinsrb xmm2, byte ptr [rsi + rdx + 7], 10 - pinsrb xmm2, byte ptr [rsi + r15 + 7], 11 - pinsrb xmm2, byte ptr [rsi + r12 + 7], 12 - pinsrb xmm2, byte ptr [rsi + r13 + 7], 13 - mov rdi, r14 - pinsrb xmm2, byte ptr [rsi + r14 + 7], 14 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r9 + 7], 15 - pcmpeqb xmm3, xmm9 - movdqa xmm1, xmmword ptr [rip + .LCPI1_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm1 - pcmpeqb xmm2, xmm9 - psllw xmm2, 7 - movdqa xmm1, xmmword ptr [rip + .LCPI1_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm2, xmm1 - por xmm2, xmm3 - movdqa xmm1, xmm2 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + rbx + 21] - movd xmm2, edx - mov r11, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r11 + 9], 1 - pinsrb xmm10, byte ptr [rsi + r10 + 9], 2 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rcx + 9], 3 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rcx + 9], 4 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdx + 9], 5 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r14 + 9], 6 - pinsrb xmm10, byte ptr [rsi + rax + 9], 7 - pinsrb xmm10, byte ptr [rsi + r8 + 9], 8 - mov r15, r8 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rax + 9], 9 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r10 + 9], 10 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdx + 9], 11 - pinsrb xmm10, byte ptr [rsi + r12 + 9], 12 - mov rax, r13 - pinsrb xmm10, byte ptr [rsi + r13 + 9], 13 - pinsrb xmm10, byte ptr [rsi + rdi + 9], 14 - pinsrb xmm10, byte ptr [rsi + r9 + 9], 15 - por xmm1, xmm8 - movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill - pcmpeqb xmm10, xmm9 - movdqa xmm1, xmm10 - movdqa xmm8, xmm4 - pand xmm1, xmm4 - psubb xmm1, xmm10 - movzx edx, byte ptr [rsi + rbx + 22] - movd xmm3, edx - movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload - pinsrb xmm4, byte ptr [rsi + r11 + 8], 1 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r13 + 8], 2 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r8 + 8], 3 - pinsrb xmm4, byte ptr [rsi + rcx + 8], 4 - mov r9, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r9 + 8], 5 - pinsrb xmm4, byte ptr [rsi + r14 + 8], 6 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r14 + 8], 7 - pinsrb xmm4, byte ptr [rsi + r15 + 8], 8 - mov rbx, r15 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 8], 9 - pinsrb xmm4, byte ptr [rsi + r10 + 8], 10 - mov r15, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r15 + 8], 11 - pinsrb xmm4, byte ptr [rsi + r12 + 8], 12 - pinsrb xmm4, byte ptr [rsi + rax + 8], 13 - pinsrb xmm4, byte ptr [rsi + rdi + 8], 14 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 8], 15 - pcmpeqb xmm4, xmm9 - pand xmm4, xmm8 - movdqa xmm10, xmmword ptr [rsp + 160] # 16-byte Reload - pinsrb xmm10, byte ptr [rsi + r11 + 10], 1 - pinsrb xmm10, byte ptr [rsi + r13 + 10], 2 - pinsrb xmm10, byte ptr [rsi + r8 + 10], 3 - mov r10, r8 - pinsrb xmm10, byte ptr [rsi + rcx + 10], 4 - pinsrb xmm10, byte ptr [rsi + r9 + 10], 5 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rcx + 10], 6 - mov r8, r14 - pinsrb xmm10, byte ptr [rsi + r14 + 10], 7 - pinsrb xmm10, byte ptr [rsi + rbx + 10], 8 - pinsrb xmm10, byte ptr [rsi + rdx + 10], 9 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdx + 10], 10 - mov rbx, rdx - pinsrb xmm10, byte ptr [rsi + r15 + 10], 11 - pinsrb xmm10, byte ptr [rsi + r12 + 10], 12 - mov r14, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r14 + 10], 13 - pinsrb xmm10, byte ptr [rsi + rdi + 10], 14 - pinsrb xmm10, byte ptr [rsi + rax + 10], 15 - pcmpeqb xmm10, xmm9 - pand xmm10, xmmword ptr [rip + .LCPI1_11] - por xmm10, xmm4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 23] - movd xmm8, edx - por xmm10, xmm1 - movdqa xmmword ptr [rsp + 160], xmm10 # 16-byte Spill - movzx edx, byte ptr [rsi + rax + 24] - movd xmm10, edx - pinsrb xmm11, byte ptr [rsi + r11 + 11], 1 - pinsrb xmm11, byte ptr [rsi + r13 + 11], 2 - pinsrb xmm11, byte ptr [rsi + r10 + 11], 3 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rax + 11], 4 - pinsrb xmm11, byte ptr [rsi + r9 + 11], 5 - pinsrb xmm11, byte ptr [rsi + rcx + 11], 6 - mov rdi, r8 - pinsrb xmm11, byte ptr [rsi + r8 + 11], 7 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r8 + 11], 8 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r9 + 11], 9 - pinsrb xmm11, byte ptr [rsi + rbx + 11], 10 - pinsrb xmm11, byte ptr [rsi + r15 + 11], 11 - pinsrb xmm11, byte ptr [rsi + r12 + 11], 12 - mov r10, r14 - pinsrb xmm11, byte ptr [rsi + r14 + 11], 13 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r14 + 11], 14 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 11], 15 - pinsrb xmm13, byte ptr [rsi + r11 + 12], 1 - pinsrb xmm13, byte ptr [rsi + r13 + 12], 2 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rbx + 12], 3 - pinsrb xmm13, byte ptr [rsi + rax + 12], 4 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rax + 12], 5 - pinsrb xmm13, byte ptr [rsi + rcx + 12], 6 - pinsrb xmm13, byte ptr [rsi + rdi + 12], 7 - pinsrb xmm13, byte ptr [rsi + r8 + 12], 8 - pinsrb xmm13, byte ptr [rsi + r9 + 12], 9 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rbx + 12], 10 - pinsrb xmm13, byte ptr [rsi + r15 + 12], 11 - pinsrb xmm13, byte ptr [rsi + r12 + 12], 12 - pinsrb xmm13, byte ptr [rsi + r10 + 12], 13 - mov r11, r10 - pinsrb xmm13, byte ptr [rsi + r14 + 12], 14 - pinsrb xmm13, byte ptr [rsi + rdx + 12], 15 - mov r10, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r10 + 13], 1 - pinsrb xmm12, byte ptr [rsi + r13 + 13], 2 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r13 + 13], 3 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rbx + 13], 4 - pinsrb xmm12, byte ptr [rsi + rax + 13], 5 - pinsrb xmm12, byte ptr [rsi + rcx + 13], 6 - pinsrb xmm12, byte ptr [rsi + rdi + 13], 7 - pinsrb xmm12, byte ptr [rsi + r8 + 13], 8 - pinsrb xmm12, byte ptr [rsi + r9 + 13], 9 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rbx + 13], 10 - pinsrb xmm12, byte ptr [rsi + r15 + 13], 11 - pinsrb xmm12, byte ptr [rsi + r12 + 13], 12 - pinsrb xmm12, byte ptr [rsi + r11 + 13], 13 - pinsrb xmm12, byte ptr [rsi + r14 + 13], 14 - pinsrb xmm12, byte ptr [rsi + rdx + 13], 15 - pcmpeqb xmm11, xmm9 - pand xmm11, xmmword ptr [rip + .LCPI1_12] - pcmpeqb xmm13, xmm9 - pand xmm13, xmmword ptr [rip + .LCPI1_13] - por xmm13, xmm11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 25] - movd xmm1, edx - pcmpeqb xmm12, xmm9 - pand xmm12, xmmword ptr [rip + .LCPI1_14] - por xmm12, xmm13 - movzx edx, byte ptr [rsi + rax + 26] - movd xmm11, edx - movdqa xmm4, xmmword ptr [rsp + 240] # 16-byte Reload - pinsrb xmm4, byte ptr [rsi + r10 + 14], 1 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r14 + 14], 2 - mov r10, r13 - pinsrb xmm4, byte ptr [rsi + r13 + 14], 3 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r11 + 14], 4 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 14], 5 - pinsrb xmm4, byte ptr [rsi + rcx + 14], 6 - pinsrb xmm4, byte ptr [rsi + rdi + 14], 7 - pinsrb xmm4, byte ptr [rsi + r8 + 14], 8 - pinsrb xmm4, byte ptr [rsi + r9 + 14], 9 - pinsrb xmm4, byte ptr [rsi + rbx + 14], 10 - pinsrb xmm4, byte ptr [rsi + r15 + 14], 11 - pinsrb xmm4, byte ptr [rsi + r12 + 14], 12 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 14], 13 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r13 + 14], 14 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 14], 15 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 15], 1 - pinsrb xmm14, byte ptr [rsi + r14 + 15], 2 - pinsrb xmm14, byte ptr [rsi + r10 + 15], 3 - pinsrb xmm14, byte ptr [rsi + r11 + 15], 4 - pinsrb xmm14, byte ptr [rsi + rax + 15], 5 - pinsrb xmm14, byte ptr [rsi + rcx + 15], 6 - pinsrb xmm14, byte ptr [rsi + rdi + 15], 7 - pinsrb xmm14, byte ptr [rsi + r8 + 15], 8 - pinsrb xmm14, byte ptr [rsi + r9 + 15], 9 - pinsrb xmm14, byte ptr [rsi + rbx + 15], 10 - pinsrb xmm14, byte ptr [rsi + r15 + 15], 11 - pinsrb xmm14, byte ptr [rsi + r12 + 15], 12 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 15], 13 - pinsrb xmm14, byte ptr [rsi + r13 + 15], 14 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 15], 15 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx + 16], 1 - pinsrb xmm15, byte ptr [rsi + r14 + 16], 2 - pinsrb xmm15, byte ptr [rsi + r10 + 16], 3 - pinsrb xmm15, byte ptr [rsi + r11 + 16], 4 - pinsrb xmm15, byte ptr [rsi + rax + 16], 5 - pinsrb xmm15, byte ptr [rsi + rcx + 16], 6 - pinsrb xmm15, byte ptr [rsi + rdi + 16], 7 - pinsrb xmm15, byte ptr [rsi + r8 + 16], 8 - pinsrb xmm15, byte ptr [rsi + r9 + 16], 9 - pinsrb xmm15, byte ptr [rsi + rbx + 16], 10 - pinsrb xmm15, byte ptr [rsi + r15 + 16], 11 - pinsrb xmm15, byte ptr [rsi + r12 + 16], 12 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx + 16], 13 - pinsrb xmm15, byte ptr [rsi + r13 + 16], 14 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 1 - pinsrb xmm0, byte ptr [rsi + r14 + 17], 2 - pinsrb xmm0, byte ptr [rsi + r10 + 17], 3 - pinsrb xmm0, byte ptr [rsi + r11 + 17], 4 - pinsrb xmm0, byte ptr [rsi + rax + 17], 5 - mov r13, rax - pinsrb xmm0, byte ptr [rsi + rcx + 17], 6 - pinsrb xmm0, byte ptr [rsi + rdi + 17], 7 - pinsrb xmm0, byte ptr [rsi + r8 + 17], 8 - pinsrb xmm0, byte ptr [rsi + r9 + 17], 9 - pinsrb xmm0, byte ptr [rsi + rbx + 17], 10 - pinsrb xmm0, byte ptr [rsi + r15 + 17], 11 - pinsrb xmm0, byte ptr [rsi + r12 + 17], 12 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 17], 13 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 14 - por xmm12, xmmword ptr [rsp + 160] # 16-byte Folded Reload - mov r14, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + r14 + 27] - movd xmm9, edx - movdqa xmm13, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm4, xmm13 - pand xmm4, xmmword ptr [rip + .LCPI1_15] - pcmpeqb xmm14, xmm13 - psllw xmm14, 7 - pand xmm14, xmmword ptr [rip + .LCPI1_6] - por xmm14, xmm4 - movzx edx, byte ptr [rsi + r14 + 28] - movd xmm4, edx - mov r8, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r8 + 17], 15 - por xmm14, xmm12 - pcmpeqb xmm0, xmm13 - movdqa xmm13, xmm0 - movdqa xmm12, xmmword ptr [rip + .LCPI1_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm13, xmm12 - psubb xmm13, xmm0 - movdqa xmmword ptr [rsp + 160], xmm13 # 16-byte Spill - movzx edx, byte ptr [rsi + r14 + 29] - movd xmm13, edx - pinsrb xmm15, byte ptr [rsi + r8 + 16], 15 - movdqa xmm0, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm15, xmm0 - mov r14, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r14 + 18], 1 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 18], 2 - pinsrb xmm5, byte ptr [rsi + r10 + 18], 3 - pinsrb xmm5, byte ptr [rsi + r11 + 18], 4 - pinsrb xmm5, byte ptr [rsi + r13 + 18], 5 - pinsrb xmm5, byte ptr [rsi + rcx + 18], 6 - pinsrb xmm5, byte ptr [rsi + rdi + 18], 7 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 18], 8 - pinsrb xmm5, byte ptr [rsi + r9 + 18], 9 - pinsrb xmm5, byte ptr [rsi + rbx + 18], 10 - pinsrb xmm5, byte ptr [rsi + r15 + 18], 11 - pinsrb xmm5, byte ptr [rsi + r12 + 18], 12 - pinsrb xmm5, byte ptr [rsi + rax + 18], 13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 18], 14 - pand xmm15, xmm12 - pinsrb xmm5, byte ptr [rsi + r8 + 18], 15 - pcmpeqb xmm5, xmm0 - pand xmm5, xmmword ptr [rip + .LCPI1_11] - por xmm5, xmm15 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 30] - movd xmm12, edx - pinsrb xmm7, byte ptr [rsi + r14 + 19], 1 - pinsrb xmm6, byte ptr [rsi + r14 + 20], 1 - pinsrb xmm2, byte ptr [rsi + r14 + 21], 1 - pinsrb xmm3, byte ptr [rsi + r14 + 22], 1 - pinsrb xmm8, byte ptr [rsi + r14 + 23], 1 - pinsrb xmm10, byte ptr [rsi + r14 + 24], 1 - pinsrb xmm1, byte ptr [rsi + r14 + 25], 1 - pinsrb xmm11, byte ptr [rsi + r14 + 26], 1 - pinsrb xmm9, byte ptr [rsi + r14 + 27], 1 - pinsrb xmm4, byte ptr [rsi + r14 + 28], 1 - pinsrb xmm13, byte ptr [rsi + r14 + 29], 1 - pinsrb xmm12, byte ptr [rsi + r14 + 30], 1 - movzx edx, byte ptr [rsi + rax + 31] - movd xmm0, edx - pinsrb xmm0, byte ptr [rsi + r14 + 31], 1 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 19], 2 - pinsrb xmm6, byte ptr [rsi + rdx + 20], 2 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 2 - pinsrb xmm3, byte ptr [rsi + rdx + 22], 2 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 2 - pinsrb xmm10, byte ptr [rsi + rdx + 24], 2 - pinsrb xmm1, byte ptr [rsi + rdx + 25], 2 - pinsrb xmm11, byte ptr [rsi + rdx + 26], 2 - pinsrb xmm9, byte ptr [rsi + rdx + 27], 2 - pinsrb xmm4, byte ptr [rsi + rdx + 28], 2 - pinsrb xmm13, byte ptr [rsi + rdx + 29], 2 - pinsrb xmm12, byte ptr [rsi + rdx + 30], 2 - pinsrb xmm0, byte ptr [rsi + rdx + 31], 2 - pinsrb xmm7, byte ptr [rsi + r10 + 19], 3 - pinsrb xmm7, byte ptr [rsi + r11 + 19], 4 - pinsrb xmm7, byte ptr [rsi + r13 + 19], 5 - pinsrb xmm7, byte ptr [rsi + rcx + 19], 6 - pinsrb xmm7, byte ptr [rsi + rdi + 19], 7 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r14 + 19], 8 - pinsrb xmm7, byte ptr [rsi + r9 + 19], 9 - pinsrb xmm7, byte ptr [rsi + rbx + 19], 10 - pinsrb xmm7, byte ptr [rsi + r15 + 19], 11 - pinsrb xmm7, byte ptr [rsi + r12 + 19], 12 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 19], 13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 19], 14 - pinsrb xmm7, byte ptr [rsi + r8 + 19], 15 - pinsrb xmm6, byte ptr [rsi + r10 + 20], 3 - pinsrb xmm6, byte ptr [rsi + r11 + 20], 4 - pinsrb xmm6, byte ptr [rsi + r13 + 20], 5 - pinsrb xmm6, byte ptr [rsi + rcx + 20], 6 - pinsrb xmm6, byte ptr [rsi + rdi + 20], 7 - pinsrb xmm6, byte ptr [rsi + r14 + 20], 8 - pinsrb xmm6, byte ptr [rsi + r9 + 20], 9 - pinsrb xmm6, byte ptr [rsi + rbx + 20], 10 - pinsrb xmm6, byte ptr [rsi + r15 + 20], 11 - pinsrb xmm6, byte ptr [rsi + r12 + 20], 12 - pinsrb xmm6, byte ptr [rsi + rdx + 20], 13 - pinsrb xmm6, byte ptr [rsi + rax + 20], 14 - por xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload - pinsrb xmm6, byte ptr [rsi + r8 + 20], 15 - movdqa xmm15, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm7, xmm15 - pand xmm7, xmmword ptr [rip + .LCPI1_12] - pcmpeqb xmm6, xmm15 - pand xmm6, xmmword ptr [rip + .LCPI1_13] - por xmm6, xmm7 - pinsrb xmm2, byte ptr [rsi + r10 + 21], 3 - pinsrb xmm2, byte ptr [rsi + r11 + 21], 4 - pinsrb xmm2, byte ptr [rsi + r13 + 21], 5 - pinsrb xmm2, byte ptr [rsi + rcx + 21], 6 - pinsrb xmm2, byte ptr [rsi + rdi + 21], 7 - pinsrb xmm2, byte ptr [rsi + r14 + 21], 8 - pinsrb xmm2, byte ptr [rsi + r9 + 21], 9 - pinsrb xmm2, byte ptr [rsi + rbx + 21], 10 - pinsrb xmm2, byte ptr [rsi + r15 + 21], 11 - pinsrb xmm2, byte ptr [rsi + r12 + 21], 12 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 13 - pinsrb xmm2, byte ptr [rsi + rax + 21], 14 - pinsrb xmm2, byte ptr [rsi + r8 + 21], 15 - pcmpeqb xmm2, xmm15 - movdqa xmm7, xmmword ptr [rip + .LCPI1_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm2, xmm7 - por xmm2, xmm6 - por xmm2, xmm5 - pinsrb xmm3, byte ptr [rsi + r10 + 22], 3 - pinsrb xmm3, byte ptr [rsi + r11 + 22], 4 - pinsrb xmm3, byte ptr [rsi + r13 + 22], 5 - pinsrb xmm3, byte ptr [rsi + rcx + 22], 6 - pinsrb xmm3, byte ptr [rsi + rdi + 22], 7 - pinsrb xmm3, byte ptr [rsi + r14 + 22], 8 - pinsrb xmm3, byte ptr [rsi + r9 + 22], 9 - pinsrb xmm3, byte ptr [rsi + rbx + 22], 10 - pinsrb xmm3, byte ptr [rsi + r15 + 22], 11 - pinsrb xmm3, byte ptr [rsi + r12 + 22], 12 - pinsrb xmm3, byte ptr [rsi + rdx + 22], 13 - pinsrb xmm3, byte ptr [rsi + rax + 22], 14 - pinsrb xmm3, byte ptr [rsi + r8 + 22], 15 - pinsrb xmm8, byte ptr [rsi + r10 + 23], 3 - pinsrb xmm8, byte ptr [rsi + r11 + 23], 4 - pinsrb xmm8, byte ptr [rsi + r13 + 23], 5 - pinsrb xmm8, byte ptr [rsi + rcx + 23], 6 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 7 - pinsrb xmm8, byte ptr [rsi + r14 + 23], 8 - pinsrb xmm8, byte ptr [rsi + r9 + 23], 9 - pinsrb xmm8, byte ptr [rsi + rbx + 23], 10 - pinsrb xmm8, byte ptr [rsi + r15 + 23], 11 - pinsrb xmm8, byte ptr [rsi + r12 + 23], 12 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 13 - pinsrb xmm8, byte ptr [rsi + rax + 23], 14 - pinsrb xmm8, byte ptr [rsi + r8 + 23], 15 - pcmpeqb xmm3, xmm15 - movdqa xmm5, xmmword ptr [rip + .LCPI1_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm5 - pcmpeqb xmm8, xmm15 - psllw xmm8, 7 - movdqa xmm6, xmmword ptr [rip + .LCPI1_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm8, xmm6 - por xmm8, xmm3 - pinsrb xmm1, byte ptr [rsi + r10 + 25], 3 - pinsrb xmm1, byte ptr [rsi + r11 + 25], 4 - pinsrb xmm1, byte ptr [rsi + r13 + 25], 5 - pinsrb xmm1, byte ptr [rsi + rcx + 25], 6 - pinsrb xmm1, byte ptr [rsi + rdi + 25], 7 - pinsrb xmm1, byte ptr [rsi + r14 + 25], 8 - pinsrb xmm1, byte ptr [rsi + r9 + 25], 9 - pinsrb xmm1, byte ptr [rsi + rbx + 25], 10 - pinsrb xmm1, byte ptr [rsi + r15 + 25], 11 - pinsrb xmm1, byte ptr [rsi + r12 + 25], 12 - pinsrb xmm1, byte ptr [rsi + rdx + 25], 13 - pinsrb xmm1, byte ptr [rsi + rax + 25], 14 - pinsrb xmm1, byte ptr [rsi + r8 + 25], 15 - por xmm8, xmm2 - pcmpeqb xmm1, xmm15 - movdqa xmm2, xmm1 - movdqa xmm3, xmmword ptr [rip + .LCPI1_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm2, xmm3 - psubb xmm2, xmm1 - pinsrb xmm10, byte ptr [rsi + r10 + 24], 3 - pinsrb xmm10, byte ptr [rsi + r11 + 24], 4 - pinsrb xmm10, byte ptr [rsi + r13 + 24], 5 - pinsrb xmm10, byte ptr [rsi + rcx + 24], 6 - pinsrb xmm10, byte ptr [rsi + rdi + 24], 7 - pinsrb xmm10, byte ptr [rsi + r14 + 24], 8 - pinsrb xmm10, byte ptr [rsi + r9 + 24], 9 - pinsrb xmm10, byte ptr [rsi + rbx + 24], 10 - pinsrb xmm10, byte ptr [rsi + r15 + 24], 11 - pinsrb xmm10, byte ptr [rsi + r12 + 24], 12 - pinsrb xmm10, byte ptr [rsi + rdx + 24], 13 - pinsrb xmm10, byte ptr [rsi + rax + 24], 14 - pinsrb xmm10, byte ptr [rsi + r8 + 24], 15 - pcmpeqb xmm10, xmm15 - pand xmm10, xmm3 - pinsrb xmm11, byte ptr [rsi + r10 + 26], 3 - pinsrb xmm11, byte ptr [rsi + r11 + 26], 4 - pinsrb xmm11, byte ptr [rsi + r13 + 26], 5 - pinsrb xmm11, byte ptr [rsi + rcx + 26], 6 - pinsrb xmm11, byte ptr [rsi + rdi + 26], 7 - pinsrb xmm11, byte ptr [rsi + r14 + 26], 8 - pinsrb xmm11, byte ptr [rsi + r9 + 26], 9 - pinsrb xmm11, byte ptr [rsi + rbx + 26], 10 - pinsrb xmm11, byte ptr [rsi + r15 + 26], 11 - pinsrb xmm11, byte ptr [rsi + r12 + 26], 12 - pinsrb xmm11, byte ptr [rsi + rdx + 26], 13 - pinsrb xmm11, byte ptr [rsi + rax + 26], 14 - pinsrb xmm11, byte ptr [rsi + r8 + 26], 15 - pcmpeqb xmm11, xmm15 - pand xmm11, xmmword ptr [rip + .LCPI1_11] - por xmm11, xmm10 - por xmm11, xmm2 - pinsrb xmm9, byte ptr [rsi + r10 + 27], 3 - pinsrb xmm9, byte ptr [rsi + r11 + 27], 4 - pinsrb xmm9, byte ptr [rsi + r13 + 27], 5 - pinsrb xmm9, byte ptr [rsi + rcx + 27], 6 - pinsrb xmm9, byte ptr [rsi + rdi + 27], 7 - pinsrb xmm9, byte ptr [rsi + r14 + 27], 8 - pinsrb xmm9, byte ptr [rsi + r9 + 27], 9 - pinsrb xmm9, byte ptr [rsi + rbx + 27], 10 - pinsrb xmm9, byte ptr [rsi + r15 + 27], 11 - pinsrb xmm9, byte ptr [rsi + r12 + 27], 12 - pinsrb xmm9, byte ptr [rsi + rdx + 27], 13 - pinsrb xmm9, byte ptr [rsi + rax + 27], 14 - pinsrb xmm9, byte ptr [rsi + r8 + 27], 15 - pinsrb xmm4, byte ptr [rsi + r10 + 28], 3 - pinsrb xmm4, byte ptr [rsi + r11 + 28], 4 - pinsrb xmm4, byte ptr [rsi + r13 + 28], 5 - pinsrb xmm4, byte ptr [rsi + rcx + 28], 6 - pinsrb xmm4, byte ptr [rsi + rdi + 28], 7 - pinsrb xmm4, byte ptr [rsi + r14 + 28], 8 - pinsrb xmm4, byte ptr [rsi + r9 + 28], 9 - pinsrb xmm4, byte ptr [rsi + rbx + 28], 10 - pinsrb xmm4, byte ptr [rsi + r15 + 28], 11 - pinsrb xmm4, byte ptr [rsi + r12 + 28], 12 - pinsrb xmm4, byte ptr [rsi + rdx + 28], 13 - pinsrb xmm4, byte ptr [rsi + rax + 28], 14 - pinsrb xmm4, byte ptr [rsi + r8 + 28], 15 - pinsrb xmm13, byte ptr [rsi + r10 + 29], 3 - pinsrb xmm13, byte ptr [rsi + r11 + 29], 4 - pinsrb xmm13, byte ptr [rsi + r13 + 29], 5 - pinsrb xmm13, byte ptr [rsi + rcx + 29], 6 - pinsrb xmm13, byte ptr [rsi + rdi + 29], 7 - pinsrb xmm13, byte ptr [rsi + r14 + 29], 8 - pinsrb xmm13, byte ptr [rsi + r9 + 29], 9 - pinsrb xmm13, byte ptr [rsi + rbx + 29], 10 - pinsrb xmm13, byte ptr [rsi + r15 + 29], 11 - pinsrb xmm13, byte ptr [rsi + r12 + 29], 12 - pinsrb xmm13, byte ptr [rsi + rdx + 29], 13 - pinsrb xmm13, byte ptr [rsi + rax + 29], 14 - movdqa xmm1, xmm15 - pcmpeqb xmm9, xmm15 - pand xmm9, xmmword ptr [rip + .LCPI1_12] - pcmpeqb xmm4, xmm15 - pand xmm4, xmmword ptr [rip + .LCPI1_13] - por xmm4, xmm9 - pinsrb xmm13, byte ptr [rsi + r8 + 29], 15 - pcmpeqb xmm13, xmm15 - pand xmm13, xmm7 - por xmm13, xmm4 - pinsrb xmm12, byte ptr [rsi + r10 + 30], 3 - pinsrb xmm0, byte ptr [rsi + r10 + 31], 3 - pinsrb xmm12, byte ptr [rsi + r11 + 30], 4 - pinsrb xmm0, byte ptr [rsi + r11 + 31], 4 - pinsrb xmm12, byte ptr [rsi + r13 + 30], 5 - pinsrb xmm0, byte ptr [rsi + r13 + 31], 5 - pinsrb xmm12, byte ptr [rsi + rcx + 30], 6 - pinsrb xmm0, byte ptr [rsi + rcx + 31], 6 - pinsrb xmm12, byte ptr [rsi + rdi + 30], 7 - pinsrb xmm0, byte ptr [rsi + rdi + 31], 7 - pinsrb xmm12, byte ptr [rsi + r14 + 30], 8 - pinsrb xmm0, byte ptr [rsi + r14 + 31], 8 - pinsrb xmm12, byte ptr [rsi + r9 + 30], 9 - pinsrb xmm0, byte ptr [rsi + r9 + 31], 9 - pinsrb xmm12, byte ptr [rsi + rbx + 30], 10 - pinsrb xmm0, byte ptr [rsi + rbx + 31], 10 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r15 + 30], 11 - pinsrb xmm0, byte ptr [rsi + r15 + 31], 11 - pinsrb xmm12, byte ptr [rsi + r12 + 30], 12 - pinsrb xmm0, byte ptr [rsi + r12 + 31], 12 - pinsrb xmm12, byte ptr [rsi + rdx + 30], 13 - pinsrb xmm0, byte ptr [rsi + rdx + 31], 13 - pinsrb xmm12, byte ptr [rsi + rax + 30], 14 - pinsrb xmm0, byte ptr [rsi + rax + 31], 14 - pinsrb xmm12, byte ptr [rsi + r8 + 30], 15 - pinsrb xmm0, byte ptr [rsi + r8 + 31], 15 - por xmm13, xmm11 - pcmpeqb xmm12, xmm15 - pand xmm12, xmm5 - pcmpeqb xmm0, xmm15 - psllw xmm0, 7 - pand xmm0, xmm6 - por xmm0, xmm12 - por xmm0, xmm13 - movdqa xmm1, xmm8 - punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - movdqa xmm4, xmmword ptr [rsp + 176] # 16-byte Reload - movdqa xmm2, xmm4 - punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] - movdqa xmm3, xmm2 - punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] - punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] - punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] - punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - movdqu xmmword ptr [rdi + 4*rcx + 48], xmm4 - movdqu xmmword ptr [rdi + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rdi + 4*rcx + 16], xmm2 - movdqu xmmword ptr [rdi + 4*rcx], xmm3 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB1_88 -# %bb.89: - mov r15, qword ptr [rsp + 256] # 8-byte Reload - cmp r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r11b, byte ptr [rsp + 4] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - jne .LBB1_90 - jmp .LBB1_93 -.LBB1_67: - and r15, -16 - mov rax, r15 - shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 232], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 56], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill - xor eax, eax - mov qword ptr [rsp + 136], r14 # 8-byte Spill + mov qword ptr [rsp + 144], r12 # 8-byte Spill + mov rsi, r11 +.LBB1_103: + sub rcx, qword ptr [rsp + 152] # 8-byte Folded Reload + mov qword ptr [rsp + 256], rcx # 8-byte Spill + mov r12, qword ptr [rsp + 144] # 8-byte Reload .p2align 4, 0x90 -.LBB1_68: # =>This Inner Loop Header: Depth=1 - mov r15, rax - mov qword ptr [rsp + 152], rax # 8-byte Spill - shl r15, 5 - mov rdi, r15 - mov rcx, r15 - mov r10, r15 - mov r8, r15 - mov r12, r15 - mov r9, r15 - mov r11, r15 - mov rbx, r15 - mov r14, r15 - mov rax, r15 - mov qword ptr [rsp + 104], r15 # 8-byte Spill - movzx edx, byte ptr [rsi + r15] - movd xmm15, edx - movzx edx, byte ptr [rsi + r15 + 1] - movd xmm5, edx - movzx edx, byte ptr [rsi + r15 + 2] - movd xmm6, edx - movzx edx, byte ptr [rsi + r15 + 3] - movd xmm2, edx - movzx edx, byte ptr [rsi + r15 + 4] - movd xmm1, edx - movzx edx, byte ptr [rsi + r15 + 5] - movd xmm8, edx - movzx edx, byte ptr [rsi + r15 + 6] - movd xmm3, edx - movzx edx, byte ptr [rsi + r15 + 7] - movd xmm0, edx - movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill - movzx edx, byte ptr [rsi + r15 + 8] - movd xmm0, edx - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - movzx edx, byte ptr [rsi + r15 + 9] - movd xmm10, edx - movzx edx, byte ptr [rsi + r15 + 10] - movd xmm0, edx - movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill - movzx edx, byte ptr [rsi + r15 + 11] - movd xmm11, edx - movzx edx, byte ptr [rsi + r15 + 12] - movd xmm13, edx - movzx edx, byte ptr [rsi + r15 + 13] - movd xmm12, edx - movzx edx, byte ptr [rsi + r15 + 14] - movd xmm0, edx - movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill - mov qword ptr [rsp + 48], r15 # 8-byte Spill - mov r13, r15 - or r13, 32 - mov qword ptr [rsp + 40], r13 # 8-byte Spill - or rdi, 64 - or rcx, 96 - mov qword ptr [rsp + 120], rcx # 8-byte Spill - or r10, 128 - or r8, 160 - or r12, 192 - or r9, 224 - or r11, 256 - or rbx, 288 - or r14, 320 - or rax, 352 - mov qword ptr [rsp + 128], rax # 8-byte Spill - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - or rdx, 384 - mov qword ptr [rsp + 104], rdx # 8-byte Spill - mov rax, r15 - or rax, 416 - mov qword ptr [rsp + 8], rax # 8-byte Spill - mov rax, r15 - or rax, 448 - mov qword ptr [rsp + 32], rax # 8-byte Spill - mov rax, r15 - or rax, 480 - mov qword ptr [rsp + 16], rax # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r13], 1 - pinsrb xmm15, byte ptr [rsi + rdi], 2 - pinsrb xmm15, byte ptr [rsi + rcx], 3 - pinsrb xmm15, byte ptr [rsi + r10], 4 - mov r15, r8 - mov qword ptr [rsp + 72], r8 # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r8], 5 - mov qword ptr [rsp + 96], r12 # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r12], 6 - mov r8, r9 - pinsrb xmm15, byte ptr [rsi + r9], 7 - mov r9, r11 - mov qword ptr [rsp + 24], r11 # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r11], 8 - mov qword ptr [rsp + 64], rbx # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + rbx], 9 - mov qword ptr [rsp + 88], r14 # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r14], 10 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r13], 11 - pinsrb xmm15, byte ptr [rsi + rdx], 12 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rcx], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rcx], 14 - pinsrb xmm15, byte ptr [rsi + rax], 15 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r11 + 1], 1 - pinsrb xmm5, byte ptr [rsi + rdi + 1], 2 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r11 + 1], 3 - pinsrb xmm5, byte ptr [rsi + r10 + 1], 4 - mov qword ptr [rsp + 80], r10 # 8-byte Spill - pinsrb xmm5, byte ptr [rsi + r15 + 1], 5 - pinsrb xmm5, byte ptr [rsi + r12 + 1], 6 - pinsrb xmm5, byte ptr [rsi + r8 + 1], 7 - mov r15, r8 - pinsrb xmm5, byte ptr [rsi + r9 + 1], 8 - pinsrb xmm5, byte ptr [rsi + rbx + 1], 9 - pinsrb xmm5, byte ptr [rsi + r14 + 1], 10 - pinsrb xmm5, byte ptr [rsi + r13 + 1], 11 - mov r8, r13 - pinsrb xmm5, byte ptr [rsi + rdx + 1], 12 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 1], 13 - pinsrb xmm5, byte ptr [rsi + rcx + 1], 14 - pinsrb xmm5, byte ptr [rsi + rax + 1], 15 - movdqa xmm9, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm5, xmm9 - movdqa xmm7, xmm5 - movdqa xmm4, xmmword ptr [rip + .LCPI1_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm7, xmm4 - psubb xmm7, xmm5 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 15] - movd xmm14, edx - pcmpeqb xmm15, xmm9 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 2], 1 - pinsrb xmm6, byte ptr [rsi + rdi + 2], 2 - mov r12, r11 - pinsrb xmm6, byte ptr [rsi + r11 + 2], 3 - pinsrb xmm6, byte ptr [rsi + r10 + 2], 4 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 2], 5 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r11 + 2], 6 - mov qword ptr [rsp + 112], r15 # 8-byte Spill - pinsrb xmm6, byte ptr [rsi + r15 + 2], 7 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r13 + 2], 8 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r14 + 2], 9 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r9 + 2], 10 - pinsrb xmm6, byte ptr [rsi + r8 + 2], 11 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 2], 12 - mov r10, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r10 + 2], 13 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 2], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 2], 15 - pand xmm15, xmm4 - pcmpeqb xmm6, xmm9 - movdqa xmm0, xmmword ptr [rip + .LCPI1_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm6, xmm0 - por xmm6, xmm15 - movzx edx, byte ptr [rsi + rax + 16] - movd xmm15, edx - pinsrb xmm2, byte ptr [rsi + rbx + 3], 1 - pinsrb xmm2, byte ptr [rsi + rdi + 3], 2 - mov rax, r12 - pinsrb xmm2, byte ptr [rsi + r12 + 3], 3 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r12 + 3], 4 - pinsrb xmm2, byte ptr [rsi + rcx + 3], 5 - pinsrb xmm2, byte ptr [rsi + r11 + 3], 6 - pinsrb xmm2, byte ptr [rsi + r15 + 3], 7 - pinsrb xmm2, byte ptr [rsi + r13 + 3], 8 - pinsrb xmm2, byte ptr [rsi + r14 + 3], 9 - pinsrb xmm2, byte ptr [rsi + r9 + 3], 10 - mov r14, r9 - pinsrb xmm2, byte ptr [rsi + r8 + 3], 11 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r15 + 3], 12 - pinsrb xmm2, byte ptr [rsi + r10 + 3], 13 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r13 + 3], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdx + 3], 15 - pinsrb xmm1, byte ptr [rsi + rbx + 4], 1 - pinsrb xmm1, byte ptr [rsi + rdi + 4], 2 - pinsrb xmm1, byte ptr [rsi + rax + 4], 3 - pinsrb xmm1, byte ptr [rsi + r12 + 4], 4 - pinsrb xmm1, byte ptr [rsi + rcx + 4], 5 - mov rcx, r11 - pinsrb xmm1, byte ptr [rsi + r11 + 4], 6 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r11 + 4], 7 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r9 + 4], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rbx + 4], 9 - pinsrb xmm1, byte ptr [rsi + r14 + 4], 10 - mov r12, r14 - pinsrb xmm1, byte ptr [rsi + r8 + 4], 11 - mov r14, r8 - pinsrb xmm1, byte ptr [rsi + r15 + 4], 12 - pinsrb xmm1, byte ptr [rsi + r10 + 4], 13 - pinsrb xmm1, byte ptr [rsi + r13 + 4], 14 - pinsrb xmm1, byte ptr [rsi + rdx + 4], 15 - mov r10, rdx - por xmm6, xmm7 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - movzx edx, byte ptr [rsi + rbx + 17] - movd xmm0, edx - pcmpeqb xmm2, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI1_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm2, xmm5 - pcmpeqb xmm1, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI1_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm1, xmm5 - por xmm1, xmm2 - movzx edx, byte ptr [rsi + rbx + 18] - movd xmm5, edx - mov r8, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r8 + 5], 1 - pinsrb xmm8, byte ptr [rsi + rdi + 5], 2 - pinsrb xmm8, byte ptr [rsi + rax + 5], 3 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdx + 5], 4 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdx + 5], 5 - pinsrb xmm8, byte ptr [rsi + rcx + 5], 6 - pinsrb xmm8, byte ptr [rsi + r11 + 5], 7 - pinsrb xmm8, byte ptr [rsi + r9 + 5], 8 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rcx + 5], 9 - pinsrb xmm8, byte ptr [rsi + r12 + 5], 10 - pinsrb xmm8, byte ptr [rsi + r14 + 5], 11 - pinsrb xmm8, byte ptr [rsi + r15 + 5], 12 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rcx + 5], 13 - pinsrb xmm8, byte ptr [rsi + r13 + 5], 14 - pinsrb xmm8, byte ptr [rsi + r10 + 5], 15 - pcmpeqb xmm8, xmm9 - movdqa xmm2, xmmword ptr [rip + .LCPI1_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm8, xmm2 - por xmm8, xmm1 - movzx edx, byte ptr [rsi + rbx + 19] - movd xmm7, edx - por xmm8, xmm6 - movzx edx, byte ptr [rsi + rbx + 20] - movd xmm6, edx - mov rdx, r8 - pinsrb xmm3, byte ptr [rsi + r8 + 6], 1 - pinsrb xmm3, byte ptr [rsi + rdi + 6], 2 - pinsrb xmm3, byte ptr [rsi + rax + 6], 3 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r11 + 6], 4 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r9 + 6], 5 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r8 + 6], 6 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r12 + 6], 7 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rax + 6], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rbx + 6], 9 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r14 + 6], 10 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 6], 11 - pinsrb xmm3, byte ptr [rsi + r15 + 6], 12 - mov r10, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r10 + 6], 13 - pinsrb xmm3, byte ptr [rsi + r13 + 6], 14 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 6], 15 - movdqa xmm2, xmmword ptr [rsp + 208] # 16-byte Reload - pinsrb xmm2, byte ptr [rsi + rdx + 7], 1 - pinsrb xmm2, byte ptr [rsi + rdi + 7], 2 - mov qword ptr [rsp + 160], rdi # 8-byte Spill - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 7], 3 - pinsrb xmm2, byte ptr [rsi + r11 + 7], 4 - pinsrb xmm2, byte ptr [rsi + r9 + 7], 5 - pinsrb xmm2, byte ptr [rsi + r8 + 7], 6 - pinsrb xmm2, byte ptr [rsi + r12 + 7], 7 - mov r11, r12 - pinsrb xmm2, byte ptr [rsi + rax + 7], 8 - pinsrb xmm2, byte ptr [rsi + rbx + 7], 9 - pinsrb xmm2, byte ptr [rsi + r14 + 7], 10 - mov r12, r14 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 7], 11 - pinsrb xmm2, byte ptr [rsi + r15 + 7], 12 - pinsrb xmm2, byte ptr [rsi + r10 + 7], 13 - pinsrb xmm2, byte ptr [rsi + r13 + 7], 14 - mov r14, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r14 + 7], 15 - pcmpeqb xmm3, xmm9 - movdqa xmm1, xmmword ptr [rip + .LCPI1_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm1 - pcmpeqb xmm2, xmm9 - psllw xmm2, 7 - movdqa xmm1, xmmword ptr [rip + .LCPI1_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm2, xmm1 - por xmm2, xmm3 - movdqa xmm1, xmm2 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - movzx edx, byte ptr [rsi + rbx + 21] - movd xmm2, edx - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdx + 9], 1 - pinsrb xmm10, byte ptr [rsi + rdi + 9], 2 - pinsrb xmm10, byte ptr [rsi + rcx + 9], 3 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdi + 9], 4 - pinsrb xmm10, byte ptr [rsi + r9 + 9], 5 - pinsrb xmm10, byte ptr [rsi + r8 + 9], 6 - pinsrb xmm10, byte ptr [rsi + r11 + 9], 7 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rcx + 9], 8 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rcx + 9], 9 - pinsrb xmm10, byte ptr [rsi + r12 + 9], 10 - pinsrb xmm10, byte ptr [rsi + rax + 9], 11 - pinsrb xmm10, byte ptr [rsi + r15 + 9], 12 - pinsrb xmm10, byte ptr [rsi + r10 + 9], 13 - pinsrb xmm10, byte ptr [rsi + r13 + 9], 14 - pinsrb xmm10, byte ptr [rsi + r14 + 9], 15 - por xmm1, xmm8 - movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill - pcmpeqb xmm10, xmm9 - movdqa xmm1, xmm10 - movdqa xmm8, xmm4 - pand xmm1, xmm4 - psubb xmm1, xmm10 - movzx edx, byte ptr [rsi + rbx + 22] - movd xmm3, edx - movdqa xmm4, xmmword ptr [rsp + 240] # 16-byte Reload - mov r10, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r10 + 8], 1 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r12 + 8], 2 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 8], 3 - pinsrb xmm4, byte ptr [rsi + rdi + 8], 4 - pinsrb xmm4, byte ptr [rsi + r9 + 8], 5 - pinsrb xmm4, byte ptr [rsi + r8 + 8], 6 - mov rbx, r11 - pinsrb xmm4, byte ptr [rsi + r11 + 8], 7 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 8], 8 - pinsrb xmm4, byte ptr [rsi + rcx + 8], 9 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 8], 10 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r14 + 8], 11 - pinsrb xmm4, byte ptr [rsi + r15 + 8], 12 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 8], 13 - pinsrb xmm4, byte ptr [rsi + r13 + 8], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 8], 15 - pcmpeqb xmm4, xmm9 - pand xmm4, xmm8 - movdqa xmm10, xmmword ptr [rsp + 176] # 16-byte Reload - pinsrb xmm10, byte ptr [rsi + r10 + 10], 1 - pinsrb xmm10, byte ptr [rsi + r12 + 10], 2 - pinsrb xmm10, byte ptr [rsi + rax + 10], 3 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r11 + 10], 4 - pinsrb xmm10, byte ptr [rsi + r9 + 10], 5 - pinsrb xmm10, byte ptr [rsi + r8 + 10], 6 - mov r10, r8 - pinsrb xmm10, byte ptr [rsi + rbx + 10], 7 - mov r8, rbx - pinsrb xmm10, byte ptr [rsi + rdx + 10], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx + 10], 9 - pinsrb xmm10, byte ptr [rsi + rcx + 10], 10 - pinsrb xmm10, byte ptr [rsi + r14 + 10], 11 - pinsrb xmm10, byte ptr [rsi + r15 + 10], 12 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rcx + 10], 13 - pinsrb xmm10, byte ptr [rsi + r13 + 10], 14 - pinsrb xmm10, byte ptr [rsi + rdi + 10], 15 - pcmpeqb xmm10, xmm9 - pand xmm10, xmmword ptr [rip + .LCPI1_11] - por xmm10, xmm4 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - movzx edx, byte ptr [rsi + rdi + 23] - movd xmm8, edx - por xmm10, xmm1 - movdqa xmmword ptr [rsp + 176], xmm10 # 16-byte Spill - movzx edx, byte ptr [rsi + rdi + 24] - movd xmm10, edx - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 11], 1 - pinsrb xmm11, byte ptr [rsi + r12 + 11], 2 - pinsrb xmm11, byte ptr [rsi + rax + 11], 3 - pinsrb xmm11, byte ptr [rsi + r11 + 11], 4 - pinsrb xmm11, byte ptr [rsi + r9 + 11], 5 - pinsrb xmm11, byte ptr [rsi + r10 + 11], 6 - pinsrb xmm11, byte ptr [rsi + r8 + 11], 7 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r9 + 11], 8 - mov r8, rbx - pinsrb xmm11, byte ptr [rsi + rbx + 11], 9 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdi + 11], 10 - pinsrb xmm11, byte ptr [rsi + r14 + 11], 11 - pinsrb xmm11, byte ptr [rsi + r15 + 11], 12 - pinsrb xmm11, byte ptr [rsi + rcx + 11], 13 - pinsrb xmm11, byte ptr [rsi + r13 + 11], 14 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rbx + 11], 15 - pinsrb xmm13, byte ptr [rsi + rdx + 12], 1 - pinsrb xmm13, byte ptr [rsi + r12 + 12], 2 - pinsrb xmm13, byte ptr [rsi + rax + 12], 3 - pinsrb xmm13, byte ptr [rsi + r11 + 12], 4 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r13 + 12], 5 - pinsrb xmm13, byte ptr [rsi + r10 + 12], 6 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rbx + 12], 7 - pinsrb xmm13, byte ptr [rsi + r9 + 12], 8 - mov r10, r9 - pinsrb xmm13, byte ptr [rsi + r8 + 12], 9 - mov r9, r8 - pinsrb xmm13, byte ptr [rsi + rdi + 12], 10 - mov r8, rdi - pinsrb xmm13, byte ptr [rsi + r14 + 12], 11 - pinsrb xmm13, byte ptr [rsi + r15 + 12], 12 - pinsrb xmm13, byte ptr [rsi + rcx + 12], 13 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r13 + 12], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rdi + 12], 15 - pinsrb xmm12, byte ptr [rsi + rdx + 13], 1 - pinsrb xmm12, byte ptr [rsi + r12 + 13], 2 - pinsrb xmm12, byte ptr [rsi + rax + 13], 3 - pinsrb xmm12, byte ptr [rsi + r11 + 13], 4 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rax + 13], 5 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rdx + 13], 6 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rbx + 13], 7 - pinsrb xmm12, byte ptr [rsi + r10 + 13], 8 - pinsrb xmm12, byte ptr [rsi + r9 + 13], 9 - pinsrb xmm12, byte ptr [rsi + r8 + 13], 10 - pinsrb xmm12, byte ptr [rsi + r14 + 13], 11 - pinsrb xmm12, byte ptr [rsi + r15 + 13], 12 - pinsrb xmm12, byte ptr [rsi + rcx + 13], 13 - pinsrb xmm12, byte ptr [rsi + r13 + 13], 14 - pinsrb xmm12, byte ptr [rsi + rdi + 13], 15 - pcmpeqb xmm11, xmm9 - pand xmm11, xmmword ptr [rip + .LCPI1_12] - pcmpeqb xmm13, xmm9 - pand xmm13, xmmword ptr [rip + .LCPI1_13] - por xmm13, xmm11 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - movzx edx, byte ptr [rsi + rcx + 25] - movd xmm1, edx - pcmpeqb xmm12, xmm9 - pand xmm12, xmmword ptr [rip + .LCPI1_14] - por xmm12, xmm13 - movzx edx, byte ptr [rsi + rcx + 26] - movd xmm11, edx - movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 14], 1 - pinsrb xmm4, byte ptr [rsi + r12 + 14], 2 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r10 + 14], 3 - pinsrb xmm4, byte ptr [rsi + r11 + 14], 4 - pinsrb xmm4, byte ptr [rsi + rax + 14], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 14], 6 - mov rdi, rbx - pinsrb xmm4, byte ptr [rsi + rbx + 14], 7 - mov r8, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r8 + 14], 8 - pinsrb xmm4, byte ptr [rsi + r9 + 14], 9 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rbx + 14], 10 - pinsrb xmm4, byte ptr [rsi + r14 + 14], 11 - pinsrb xmm4, byte ptr [rsi + r15 + 14], 12 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 14], 13 - pinsrb xmm4, byte ptr [rsi + r13 + 14], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 14], 15 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 15], 1 - pinsrb xmm14, byte ptr [rsi + r12 + 15], 2 - pinsrb xmm14, byte ptr [rsi + r10 + 15], 3 - pinsrb xmm14, byte ptr [rsi + r11 + 15], 4 - pinsrb xmm14, byte ptr [rsi + rax + 15], 5 - pinsrb xmm14, byte ptr [rsi + rcx + 15], 6 - pinsrb xmm14, byte ptr [rsi + rdi + 15], 7 - pinsrb xmm14, byte ptr [rsi + r8 + 15], 8 - pinsrb xmm14, byte ptr [rsi + r9 + 15], 9 - pinsrb xmm14, byte ptr [rsi + rbx + 15], 10 - pinsrb xmm14, byte ptr [rsi + r14 + 15], 11 - pinsrb xmm14, byte ptr [rsi + r15 + 15], 12 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 15], 13 - pinsrb xmm14, byte ptr [rsi + r13 + 15], 14 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 15], 15 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx + 16], 1 - pinsrb xmm15, byte ptr [rsi + r12 + 16], 2 - pinsrb xmm15, byte ptr [rsi + r10 + 16], 3 - pinsrb xmm15, byte ptr [rsi + r11 + 16], 4 - pinsrb xmm15, byte ptr [rsi + rax + 16], 5 - pinsrb xmm15, byte ptr [rsi + rcx + 16], 6 - pinsrb xmm15, byte ptr [rsi + rdi + 16], 7 - pinsrb xmm15, byte ptr [rsi + r8 + 16], 8 - pinsrb xmm15, byte ptr [rsi + r9 + 16], 9 - pinsrb xmm15, byte ptr [rsi + rbx + 16], 10 - pinsrb xmm15, byte ptr [rsi + r14 + 16], 11 - pinsrb xmm15, byte ptr [rsi + r15 + 16], 12 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx + 16], 13 - pinsrb xmm15, byte ptr [rsi + r13 + 16], 14 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 1 - pinsrb xmm0, byte ptr [rsi + r12 + 17], 2 - pinsrb xmm0, byte ptr [rsi + r10 + 17], 3 - pinsrb xmm0, byte ptr [rsi + r11 + 17], 4 - pinsrb xmm0, byte ptr [rsi + rax + 17], 5 - mov r13, rax - pinsrb xmm0, byte ptr [rsi + rcx + 17], 6 - pinsrb xmm0, byte ptr [rsi + rdi + 17], 7 - pinsrb xmm0, byte ptr [rsi + r8 + 17], 8 - mov rax, r8 - pinsrb xmm0, byte ptr [rsi + r9 + 17], 9 - pinsrb xmm0, byte ptr [rsi + rbx + 17], 10 - pinsrb xmm0, byte ptr [rsi + r14 + 17], 11 - pinsrb xmm0, byte ptr [rsi + r15 + 17], 12 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 13 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 14 - por xmm12, xmmword ptr [rsp + 176] # 16-byte Folded Reload - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx edx, byte ptr [rsi + r12 + 27] - movd xmm9, edx - movdqa xmm13, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm4, xmm13 - pand xmm4, xmmword ptr [rip + .LCPI1_15] - pcmpeqb xmm14, xmm13 - psllw xmm14, 7 - pand xmm14, xmmword ptr [rip + .LCPI1_6] - por xmm14, xmm4 - movzx edx, byte ptr [rsi + r12 + 28] - movd xmm4, edx - mov r8, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r8 + 17], 15 - por xmm14, xmm12 - pcmpeqb xmm0, xmm13 - movdqa xmm13, xmm0 - movdqa xmm12, xmmword ptr [rip + .LCPI1_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm13, xmm12 - psubb xmm13, xmm0 - movdqa xmmword ptr [rsp + 176], xmm13 # 16-byte Spill - movzx edx, byte ptr [rsi + r12 + 29] - movd xmm13, edx - pinsrb xmm15, byte ptr [rsi + r8 + 16], 15 - movdqa xmm0, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm15, xmm0 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r12 + 18], 1 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 18], 2 - pinsrb xmm5, byte ptr [rsi + r10 + 18], 3 - pinsrb xmm5, byte ptr [rsi + r11 + 18], 4 - pinsrb xmm5, byte ptr [rsi + r13 + 18], 5 - pinsrb xmm5, byte ptr [rsi + rcx + 18], 6 - pinsrb xmm5, byte ptr [rsi + rdi + 18], 7 - pinsrb xmm5, byte ptr [rsi + rax + 18], 8 - pinsrb xmm5, byte ptr [rsi + r9 + 18], 9 - pinsrb xmm5, byte ptr [rsi + rbx + 18], 10 - pinsrb xmm5, byte ptr [rsi + r14 + 18], 11 - pinsrb xmm5, byte ptr [rsi + r15 + 18], 12 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 18], 13 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 18], 14 - pand xmm15, xmm12 - pinsrb xmm5, byte ptr [rsi + r8 + 18], 15 - pcmpeqb xmm5, xmm0 - pand xmm5, xmmword ptr [rip + .LCPI1_11] - por xmm5, xmm15 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 30] - movd xmm12, edx - pinsrb xmm7, byte ptr [rsi + r12 + 19], 1 - pinsrb xmm6, byte ptr [rsi + r12 + 20], 1 - pinsrb xmm2, byte ptr [rsi + r12 + 21], 1 - pinsrb xmm3, byte ptr [rsi + r12 + 22], 1 - pinsrb xmm8, byte ptr [rsi + r12 + 23], 1 - pinsrb xmm10, byte ptr [rsi + r12 + 24], 1 - pinsrb xmm1, byte ptr [rsi + r12 + 25], 1 - pinsrb xmm11, byte ptr [rsi + r12 + 26], 1 - pinsrb xmm9, byte ptr [rsi + r12 + 27], 1 - pinsrb xmm4, byte ptr [rsi + r12 + 28], 1 - pinsrb xmm13, byte ptr [rsi + r12 + 29], 1 - pinsrb xmm12, byte ptr [rsi + r12 + 30], 1 - movzx edx, byte ptr [rsi + rax + 31] - movd xmm0, edx - pinsrb xmm0, byte ptr [rsi + r12 + 31], 1 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 19], 2 - pinsrb xmm6, byte ptr [rsi + rdx + 20], 2 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 2 - pinsrb xmm3, byte ptr [rsi + rdx + 22], 2 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 2 - pinsrb xmm10, byte ptr [rsi + rdx + 24], 2 - pinsrb xmm1, byte ptr [rsi + rdx + 25], 2 - pinsrb xmm11, byte ptr [rsi + rdx + 26], 2 - pinsrb xmm9, byte ptr [rsi + rdx + 27], 2 - pinsrb xmm4, byte ptr [rsi + rdx + 28], 2 - pinsrb xmm13, byte ptr [rsi + rdx + 29], 2 - pinsrb xmm12, byte ptr [rsi + rdx + 30], 2 - pinsrb xmm0, byte ptr [rsi + rdx + 31], 2 - pinsrb xmm7, byte ptr [rsi + r10 + 19], 3 - pinsrb xmm7, byte ptr [rsi + r11 + 19], 4 - pinsrb xmm7, byte ptr [rsi + r13 + 19], 5 - pinsrb xmm7, byte ptr [rsi + rcx + 19], 6 - pinsrb xmm7, byte ptr [rsi + rdi + 19], 7 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 19], 8 - pinsrb xmm7, byte ptr [rsi + r9 + 19], 9 - pinsrb xmm7, byte ptr [rsi + rbx + 19], 10 - pinsrb xmm7, byte ptr [rsi + r14 + 19], 11 - pinsrb xmm7, byte ptr [rsi + r15 + 19], 12 - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 19], 13 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r12 + 19], 14 - pinsrb xmm7, byte ptr [rsi + r8 + 19], 15 - pinsrb xmm6, byte ptr [rsi + r10 + 20], 3 - pinsrb xmm6, byte ptr [rsi + r11 + 20], 4 - pinsrb xmm6, byte ptr [rsi + r13 + 20], 5 - pinsrb xmm6, byte ptr [rsi + rcx + 20], 6 - pinsrb xmm6, byte ptr [rsi + rdi + 20], 7 - pinsrb xmm6, byte ptr [rsi + rax + 20], 8 - pinsrb xmm6, byte ptr [rsi + r9 + 20], 9 - pinsrb xmm6, byte ptr [rsi + rbx + 20], 10 - pinsrb xmm6, byte ptr [rsi + r14 + 20], 11 - pinsrb xmm6, byte ptr [rsi + r15 + 20], 12 - pinsrb xmm6, byte ptr [rsi + rdx + 20], 13 - pinsrb xmm6, byte ptr [rsi + r12 + 20], 14 - por xmm5, xmmword ptr [rsp + 176] # 16-byte Folded Reload - pinsrb xmm6, byte ptr [rsi + r8 + 20], 15 - movdqa xmm15, xmmword ptr [rsp + 192] # 16-byte Reload - pcmpeqb xmm7, xmm15 - pand xmm7, xmmword ptr [rip + .LCPI1_12] - pcmpeqb xmm6, xmm15 - pand xmm6, xmmword ptr [rip + .LCPI1_13] - por xmm6, xmm7 - pinsrb xmm2, byte ptr [rsi + r10 + 21], 3 - pinsrb xmm2, byte ptr [rsi + r11 + 21], 4 - pinsrb xmm2, byte ptr [rsi + r13 + 21], 5 - pinsrb xmm2, byte ptr [rsi + rcx + 21], 6 - pinsrb xmm2, byte ptr [rsi + rdi + 21], 7 - pinsrb xmm2, byte ptr [rsi + rax + 21], 8 - pinsrb xmm2, byte ptr [rsi + r9 + 21], 9 - pinsrb xmm2, byte ptr [rsi + rbx + 21], 10 - pinsrb xmm2, byte ptr [rsi + r14 + 21], 11 - pinsrb xmm2, byte ptr [rsi + r15 + 21], 12 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 13 - pinsrb xmm2, byte ptr [rsi + r12 + 21], 14 - pinsrb xmm2, byte ptr [rsi + r8 + 21], 15 - pcmpeqb xmm2, xmm15 - movdqa xmm7, xmmword ptr [rip + .LCPI1_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm2, xmm7 - por xmm2, xmm6 - por xmm2, xmm5 - pinsrb xmm3, byte ptr [rsi + r10 + 22], 3 - pinsrb xmm3, byte ptr [rsi + r11 + 22], 4 - pinsrb xmm3, byte ptr [rsi + r13 + 22], 5 - pinsrb xmm3, byte ptr [rsi + rcx + 22], 6 - pinsrb xmm3, byte ptr [rsi + rdi + 22], 7 - pinsrb xmm3, byte ptr [rsi + rax + 22], 8 - pinsrb xmm3, byte ptr [rsi + r9 + 22], 9 - pinsrb xmm3, byte ptr [rsi + rbx + 22], 10 - pinsrb xmm3, byte ptr [rsi + r14 + 22], 11 - pinsrb xmm3, byte ptr [rsi + r15 + 22], 12 - pinsrb xmm3, byte ptr [rsi + rdx + 22], 13 - pinsrb xmm3, byte ptr [rsi + r12 + 22], 14 - pinsrb xmm3, byte ptr [rsi + r8 + 22], 15 - pinsrb xmm8, byte ptr [rsi + r10 + 23], 3 - pinsrb xmm8, byte ptr [rsi + r11 + 23], 4 - pinsrb xmm8, byte ptr [rsi + r13 + 23], 5 - pinsrb xmm8, byte ptr [rsi + rcx + 23], 6 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 7 - pinsrb xmm8, byte ptr [rsi + rax + 23], 8 - pinsrb xmm8, byte ptr [rsi + r9 + 23], 9 - pinsrb xmm8, byte ptr [rsi + rbx + 23], 10 - pinsrb xmm8, byte ptr [rsi + r14 + 23], 11 - pinsrb xmm8, byte ptr [rsi + r15 + 23], 12 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 13 - pinsrb xmm8, byte ptr [rsi + r12 + 23], 14 - pinsrb xmm8, byte ptr [rsi + r8 + 23], 15 - pcmpeqb xmm3, xmm15 - movdqa xmm5, xmmword ptr [rip + .LCPI1_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm5 - pcmpeqb xmm8, xmm15 - psllw xmm8, 7 - movdqa xmm6, xmmword ptr [rip + .LCPI1_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm8, xmm6 - por xmm8, xmm3 - pinsrb xmm1, byte ptr [rsi + r10 + 25], 3 - pinsrb xmm1, byte ptr [rsi + r11 + 25], 4 - pinsrb xmm1, byte ptr [rsi + r13 + 25], 5 - pinsrb xmm1, byte ptr [rsi + rcx + 25], 6 - pinsrb xmm1, byte ptr [rsi + rdi + 25], 7 - pinsrb xmm1, byte ptr [rsi + rax + 25], 8 - pinsrb xmm1, byte ptr [rsi + r9 + 25], 9 - pinsrb xmm1, byte ptr [rsi + rbx + 25], 10 - pinsrb xmm1, byte ptr [rsi + r14 + 25], 11 - pinsrb xmm1, byte ptr [rsi + r15 + 25], 12 - pinsrb xmm1, byte ptr [rsi + rdx + 25], 13 - pinsrb xmm1, byte ptr [rsi + r12 + 25], 14 - pinsrb xmm1, byte ptr [rsi + r8 + 25], 15 - por xmm8, xmm2 - pcmpeqb xmm1, xmm15 - movdqa xmm2, xmm1 - movdqa xmm3, xmmword ptr [rip + .LCPI1_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm2, xmm3 - psubb xmm2, xmm1 - pinsrb xmm10, byte ptr [rsi + r10 + 24], 3 - pinsrb xmm10, byte ptr [rsi + r11 + 24], 4 - pinsrb xmm10, byte ptr [rsi + r13 + 24], 5 - pinsrb xmm10, byte ptr [rsi + rcx + 24], 6 - pinsrb xmm10, byte ptr [rsi + rdi + 24], 7 - pinsrb xmm10, byte ptr [rsi + rax + 24], 8 - pinsrb xmm10, byte ptr [rsi + r9 + 24], 9 - pinsrb xmm10, byte ptr [rsi + rbx + 24], 10 - pinsrb xmm10, byte ptr [rsi + r14 + 24], 11 - pinsrb xmm10, byte ptr [rsi + r15 + 24], 12 - pinsrb xmm10, byte ptr [rsi + rdx + 24], 13 - pinsrb xmm10, byte ptr [rsi + r12 + 24], 14 - pinsrb xmm10, byte ptr [rsi + r8 + 24], 15 - pcmpeqb xmm10, xmm15 - pand xmm10, xmm3 - pinsrb xmm11, byte ptr [rsi + r10 + 26], 3 - pinsrb xmm11, byte ptr [rsi + r11 + 26], 4 - pinsrb xmm11, byte ptr [rsi + r13 + 26], 5 - pinsrb xmm11, byte ptr [rsi + rcx + 26], 6 - pinsrb xmm11, byte ptr [rsi + rdi + 26], 7 - pinsrb xmm11, byte ptr [rsi + rax + 26], 8 - pinsrb xmm11, byte ptr [rsi + r9 + 26], 9 - pinsrb xmm11, byte ptr [rsi + rbx + 26], 10 - pinsrb xmm11, byte ptr [rsi + r14 + 26], 11 - pinsrb xmm11, byte ptr [rsi + r15 + 26], 12 - pinsrb xmm11, byte ptr [rsi + rdx + 26], 13 - pinsrb xmm11, byte ptr [rsi + r12 + 26], 14 - pinsrb xmm11, byte ptr [rsi + r8 + 26], 15 - pcmpeqb xmm11, xmm15 - pand xmm11, xmmword ptr [rip + .LCPI1_11] - por xmm11, xmm10 - por xmm11, xmm2 - pinsrb xmm9, byte ptr [rsi + r10 + 27], 3 - pinsrb xmm9, byte ptr [rsi + r11 + 27], 4 - pinsrb xmm9, byte ptr [rsi + r13 + 27], 5 - pinsrb xmm9, byte ptr [rsi + rcx + 27], 6 - pinsrb xmm9, byte ptr [rsi + rdi + 27], 7 - pinsrb xmm9, byte ptr [rsi + rax + 27], 8 - pinsrb xmm9, byte ptr [rsi + r9 + 27], 9 - pinsrb xmm9, byte ptr [rsi + rbx + 27], 10 - pinsrb xmm9, byte ptr [rsi + r14 + 27], 11 - pinsrb xmm9, byte ptr [rsi + r15 + 27], 12 - pinsrb xmm9, byte ptr [rsi + rdx + 27], 13 - pinsrb xmm9, byte ptr [rsi + r12 + 27], 14 - pinsrb xmm9, byte ptr [rsi + r8 + 27], 15 - pinsrb xmm4, byte ptr [rsi + r10 + 28], 3 - pinsrb xmm4, byte ptr [rsi + r11 + 28], 4 - pinsrb xmm4, byte ptr [rsi + r13 + 28], 5 - pinsrb xmm4, byte ptr [rsi + rcx + 28], 6 - pinsrb xmm4, byte ptr [rsi + rdi + 28], 7 - pinsrb xmm4, byte ptr [rsi + rax + 28], 8 - pinsrb xmm4, byte ptr [rsi + r9 + 28], 9 - pinsrb xmm4, byte ptr [rsi + rbx + 28], 10 - pinsrb xmm4, byte ptr [rsi + r14 + 28], 11 - pinsrb xmm4, byte ptr [rsi + r15 + 28], 12 - pinsrb xmm4, byte ptr [rsi + rdx + 28], 13 - pinsrb xmm4, byte ptr [rsi + r12 + 28], 14 - pinsrb xmm4, byte ptr [rsi + r8 + 28], 15 - pinsrb xmm13, byte ptr [rsi + r10 + 29], 3 - pinsrb xmm13, byte ptr [rsi + r11 + 29], 4 - pinsrb xmm13, byte ptr [rsi + r13 + 29], 5 - pinsrb xmm13, byte ptr [rsi + rcx + 29], 6 - pinsrb xmm13, byte ptr [rsi + rdi + 29], 7 - pinsrb xmm13, byte ptr [rsi + rax + 29], 8 - pinsrb xmm13, byte ptr [rsi + r9 + 29], 9 - pinsrb xmm13, byte ptr [rsi + rbx + 29], 10 - pinsrb xmm13, byte ptr [rsi + r14 + 29], 11 - pinsrb xmm13, byte ptr [rsi + r15 + 29], 12 - pinsrb xmm13, byte ptr [rsi + rdx + 29], 13 - pinsrb xmm13, byte ptr [rsi + r12 + 29], 14 - movdqa xmm1, xmm15 - pcmpeqb xmm9, xmm15 - pand xmm9, xmmword ptr [rip + .LCPI1_12] - pcmpeqb xmm4, xmm15 - pand xmm4, xmmword ptr [rip + .LCPI1_13] - por xmm4, xmm9 - pinsrb xmm13, byte ptr [rsi + r8 + 29], 15 - pcmpeqb xmm13, xmm15 - pand xmm13, xmm7 - por xmm13, xmm4 - pinsrb xmm12, byte ptr [rsi + r10 + 30], 3 - pinsrb xmm0, byte ptr [rsi + r10 + 31], 3 - pinsrb xmm12, byte ptr [rsi + r11 + 30], 4 - pinsrb xmm0, byte ptr [rsi + r11 + 31], 4 - pinsrb xmm12, byte ptr [rsi + r13 + 30], 5 - pinsrb xmm0, byte ptr [rsi + r13 + 31], 5 - pinsrb xmm12, byte ptr [rsi + rcx + 30], 6 - pinsrb xmm0, byte ptr [rsi + rcx + 31], 6 - pinsrb xmm12, byte ptr [rsi + rdi + 30], 7 - pinsrb xmm0, byte ptr [rsi + rdi + 31], 7 - pinsrb xmm12, byte ptr [rsi + rax + 30], 8 - pinsrb xmm0, byte ptr [rsi + rax + 31], 8 - pinsrb xmm12, byte ptr [rsi + r9 + 30], 9 - pinsrb xmm0, byte ptr [rsi + r9 + 31], 9 - pinsrb xmm12, byte ptr [rsi + rbx + 30], 10 - pinsrb xmm0, byte ptr [rsi + rbx + 31], 10 - pinsrb xmm12, byte ptr [rsi + r14 + 30], 11 - pinsrb xmm0, byte ptr [rsi + r14 + 31], 11 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r15 + 30], 12 - pinsrb xmm0, byte ptr [rsi + r15 + 31], 12 - pinsrb xmm12, byte ptr [rsi + rdx + 30], 13 - pinsrb xmm0, byte ptr [rsi + rdx + 31], 13 - pinsrb xmm12, byte ptr [rsi + r12 + 30], 14 - pinsrb xmm0, byte ptr [rsi + r12 + 31], 14 - pinsrb xmm12, byte ptr [rsi + r8 + 30], 15 - pinsrb xmm0, byte ptr [rsi + r8 + 31], 15 - por xmm13, xmm11 - pcmpeqb xmm12, xmm15 - pand xmm12, xmm5 - pcmpeqb xmm0, xmm15 - psllw xmm0, 7 - pand xmm0, xmm6 - por xmm0, xmm12 - por xmm0, xmm13 - movdqa xmm1, xmm8 - punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - movdqa xmm4, xmmword ptr [rsp + 208] # 16-byte Reload - movdqa xmm2, xmm4 - punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] - movdqa xmm3, xmm2 - punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] - punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] - punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] - punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx + 48], xmm4 - movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 - movdqu xmmword ptr [rax + 4*rcx], xmm3 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB1_68 +.LBB1_104: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r14b + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r14b + sete sil + cmp byte ptr [rcx + 2], r14b + sete r11b + cmp byte ptr [rcx + 3], r14b + sete r15b + cmp byte ptr [rcx + 4], r14b + sete byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 5], al + sete byte ptr [rsp + 72] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 6], al + sete r13b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 7], al + sete r8b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 8], al + sete byte ptr [rsp + 224] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 9], al + sete dl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 10], al + sete dil + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 11], al + sete r9b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 12], al + sete r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 13], al + sete byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 14], al + sete byte ptr [rsp + 208] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 15], al + sete al + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 16], bl + sete byte ptr [rsp + 160] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 17], bl + sete byte ptr [rsp + 176] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 18], bl + sete byte ptr [rsp + 96] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 19], bl + sete byte ptr [rsp + 104] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 20], bl + sete byte ptr [rsp + 88] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 21], bl + sete byte ptr [rsp + 56] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 22], bl + sete byte ptr [rsp + 80] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 23], bl + sete r10b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 24], bl + sete byte ptr [rsp + 64] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 25], bl + sete byte ptr [rsp + 32] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 26], bl + sete byte ptr [rsp + 48] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 27], bl + sete byte ptr [rsp + 40] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 28], bl + sete byte ptr [rsp + 16] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 29], bl + sete byte ptr [rsp + 24] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 30], bl + sete byte ptr [rsp + 120] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 31], bl + sete bl + add sil, sil + add sil, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r13b, 6 + shl r8b, 7 + or r8b, r13b + shl r11b, 2 + or r11b, sil + add dl, dl + add dl, byte ptr [rsp + 224] # 1-byte Folded Reload + shl r15b, 3 + or r15b, r11b + shl dil, 2 + or dil, dl + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, r15b + mov esi, edx + shl r9b, 3 + or r9b, dil + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov esi, edx + movzx edi, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r14b, 4 + or r14b, r9b + movzx edx, byte ptr [rsp + 192] # 1-byte Folded Reload + shl dl, 5 + or dl, r14b + mov r9d, edx + mov r14d, edi + movzx edx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl dl, 6 + shl al, 7 + or al, dl + or r8b, sil + or al, r9b + movzx edx, byte ptr [rsp + 176] # 1-byte Folded Reload + add dl, dl + add dl, byte ptr [rsp + 160] # 1-byte Folded Reload + mov esi, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 2 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov byte ptr [r12], r8b + movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + shl sil, 6 + shl r10b, 7 + or r10b, sil + mov byte ptr [r12 + 1], al + or r10b, dl + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 64] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [r12 + 2], r10b + mov byte ptr [r12 + 3], bl + lea rsi, [rcx + 32] + add r12, 4 + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill + jne .LBB1_104 +# %bb.105: + mov qword ptr [rsp + 144], r12 # 8-byte Spill + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 280] # 8-byte Reload + jmp .LBB1_106 +.LBB1_93: + mov qword ptr [rsp + 144], r12 # 8-byte Spill + mov rsi, r11 +.LBB1_106: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB1_222 +# %bb.107: + or rcx, 1 + cmp r15, rcx + jne .LBB1_109 +# %bb.108: + xor r9d, r9d + jmp .LBB1_112 +.LBB1_62: + mov r14, rsi + sub r15, r8 + je .LBB1_222 +.LBB1_64: + add r12, 1 +.LBB1_65: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB1_66 # %bb.69: - mov r15, qword ptr [rsp + 256] # 8-byte Reload - cmp r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r11b, byte ptr [rsp + 4] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - jne .LBB1_70 - jmp .LBB1_73 -.LBB1_111: - and r15, -8 - mov rax, r15 - shl rax, 6 - add rax, rsi - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 8], rax # 8-byte Spill - movd xmm0, r11d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] - xor r15d, r15d - movdqa xmm15, xmmword ptr [rip + .LCPI1_8] # xmm15 = <1,1,1,1,1,1,1,1,u,u,u,u,u,u,u,u> - movdqa xmm9, xmmword ptr [rip + .LCPI1_1] # xmm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - movdqa xmm10, xmmword ptr [rip + .LCPI1_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - movdqa xmm11, xmmword ptr [rip + .LCPI1_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - movdqa xmm12, xmmword ptr [rip + .LCPI1_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - movdqa xmm13, xmmword ptr [rip + .LCPI1_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] - movdqa xmm14, xmmword ptr [rip + .LCPI1_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - mov qword ptr [rsp + 136], r14 # 8-byte Spill + cmp rcx, 16 + mov byte ptr [rsp + 8], r11b # 1-byte Spill + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 280], rcx # 8-byte Spill + jb .LBB1_70 +# %bb.71: + mov rax, rcx + shl rax, 5 + add rax, r14 + cmp r12, rax + jae .LBB1_73 +# %bb.72: + lea rax, [r12 + 4*rcx] + cmp r14, rax + jae .LBB1_73 +.LBB1_70: + xor eax, eax + mov qword ptr [rsp + 152], rax # 8-byte Spill + mov qword ptr [rsp + 144], r12 # 8-byte Spill + mov rsi, r14 +.LBB1_76: + sub rcx, qword ptr [rsp + 152] # 8-byte Folded Reload + mov qword ptr [rsp + 240], rcx # 8-byte Spill + mov rdi, qword ptr [rsp + 144] # 8-byte Reload .p2align 4, 0x90 -.LBB1_112: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 40], r15 # 8-byte Spill - shl r15, 6 - mov r9, r15 - mov r12, r15 - mov r13, r15 - mov rcx, r15 - mov rdx, r15 - mov rbx, r15 - movzx r14d, word ptr [rsi + r15] - movzx eax, word ptr [rsi + r15 + 2] - movzx r10d, word ptr [rsi + r15 + 4] - movzx edi, word ptr [rsi + r15 + 6] - movzx r11d, word ptr [rsi + r15 + 8] - mov r8, r15 - or r8, 64 - or r9, 128 - or r12, 192 - or r13, 256 - or rcx, 320 - or rdx, 384 - or rbx, 448 - movd xmm4, r14d - pinsrw xmm4, word ptr [rsi + r8], 1 - pinsrw xmm4, word ptr [rsi + r9], 2 - pinsrw xmm4, word ptr [rsi + r12], 3 - pinsrw xmm4, word ptr [rsi + r13], 4 - pinsrw xmm4, word ptr [rsi + rcx], 5 - pinsrw xmm4, word ptr [rsi + rdx], 6 - pinsrw xmm4, word ptr [rsi + rbx], 7 - movzx r14d, word ptr [rsi + r15 + 10] - movd xmm6, eax - pinsrw xmm6, word ptr [rsi + r8 + 2], 1 - pinsrw xmm6, word ptr [rsi + r9 + 2], 2 - pinsrw xmm6, word ptr [rsi + r12 + 2], 3 - movzx eax, word ptr [rsi + r15 + 12] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + r13 + 2], 4 - movd xmm2, r10d - movzx eax, word ptr [rsi + r15 + 14] - mov dword ptr [rsp + 16], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + rcx + 2], 5 - movd xmm5, edi - movzx edi, word ptr [rsi + r15 + 16] - pinsrw xmm6, word ptr [rsi + rdx + 2], 6 - movd xmm3, r11d - movzx eax, word ptr [rsi + r15 + 18] - mov dword ptr [rsp + 48], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + rbx + 2], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - movdqa xmm1, xmm6 - pand xmm1, xmm15 - psubb xmm1, xmm6 - movd xmm6, r14d - movzx r10d, word ptr [rsi + r15 + 20] - pcmpeqw xmm4, xmm0 - packsswb xmm4, xmm4 - pand xmm4, xmm15 - pinsrw xmm2, word ptr [rsi + r8 + 4], 1 - pinsrw xmm2, word ptr [rsi + r9 + 4], 2 - pinsrw xmm2, word ptr [rsi + r12 + 4], 3 - pinsrw xmm2, word ptr [rsi + r13 + 4], 4 - pinsrw xmm2, word ptr [rsi + rcx + 4], 5 - pinsrw xmm2, word ptr [rsi + rdx + 4], 6 - pinsrw xmm2, word ptr [rsi + rbx + 4], 7 - pinsrw xmm5, word ptr [rsi + r8 + 6], 1 - pinsrw xmm5, word ptr [rsi + r9 + 6], 2 - pinsrw xmm5, word ptr [rsi + r12 + 6], 3 - pinsrw xmm5, word ptr [rsi + r13 + 6], 4 - pinsrw xmm5, word ptr [rsi + rcx + 6], 5 - pinsrw xmm5, word ptr [rsi + rdx + 6], 6 - pinsrw xmm5, word ptr [rsi + rbx + 6], 7 - pinsrw xmm3, word ptr [rsi + r8 + 8], 1 - pinsrw xmm3, word ptr [rsi + r9 + 8], 2 - pinsrw xmm3, word ptr [rsi + r12 + 8], 3 - pinsrw xmm3, word ptr [rsi + r13 + 8], 4 - pinsrw xmm3, word ptr [rsi + rcx + 8], 5 - pinsrw xmm3, word ptr [rsi + rdx + 8], 6 - pinsrw xmm3, word ptr [rsi + rbx + 8], 7 - por xmm1, xmm4 - movd xmm7, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 22] - pcmpeqw xmm2, xmm0 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 2 - pand xmm2, xmm9 - por xmm2, xmm1 - movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx r11d, word ptr [rsi + r15 + 24] - pcmpeqw xmm5, xmm0 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 3 - pand xmm5, xmm10 - pcmpeqw xmm3, xmm0 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 4 - pand xmm3, xmm11 - por xmm3, xmm5 - movd xmm1, edi - movzx edi, word ptr [rsi + r15 + 26] - pinsrw xmm6, word ptr [rsi + r8 + 10], 1 - pinsrw xmm6, word ptr [rsi + r9 + 10], 2 - pinsrw xmm6, word ptr [rsi + r12 + 10], 3 - pinsrw xmm6, word ptr [rsi + r13 + 10], 4 - pinsrw xmm6, word ptr [rsi + rcx + 10], 5 - pinsrw xmm6, word ptr [rsi + rdx + 10], 6 - pinsrw xmm6, word ptr [rsi + rbx + 10], 7 - pinsrw xmm7, word ptr [rsi + r8 + 12], 1 - pinsrw xmm7, word ptr [rsi + r9 + 12], 2 - pinsrw xmm7, word ptr [rsi + r12 + 12], 3 - pinsrw xmm7, word ptr [rsi + r13 + 12], 4 - pinsrw xmm7, word ptr [rsi + rcx + 12], 5 - pinsrw xmm7, word ptr [rsi + rdx + 12], 6 - pinsrw xmm7, word ptr [rsi + rbx + 12], 7 - por xmm3, xmm2 - movd xmm8, dword ptr [rsp + 48] # 4-byte Folded Reload - # xmm8 = mem[0],zero,zero,zero - movzx r14d, word ptr [rsi + r15 + 28] - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - pcmpeqw xmm7, xmm0 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 6 - pand xmm7, xmm13 - por xmm7, xmm6 - movd xmm5, r10d - movzx r10d, word ptr [rsi + r15 + 30] - pinsrw xmm4, word ptr [rsi + r8 + 14], 1 - pinsrw xmm4, word ptr [rsi + r9 + 14], 2 - pinsrw xmm4, word ptr [rsi + r12 + 14], 3 - pinsrw xmm4, word ptr [rsi + r13 + 14], 4 - pinsrw xmm4, word ptr [rsi + rcx + 14], 5 - pinsrw xmm4, word ptr [rsi + rdx + 14], 6 - pinsrw xmm4, word ptr [rsi + rbx + 14], 7 - pinsrw xmm8, word ptr [rsi + r8 + 18], 1 - pinsrw xmm8, word ptr [rsi + r9 + 18], 2 - pinsrw xmm8, word ptr [rsi + r12 + 18], 3 - pinsrw xmm8, word ptr [rsi + r13 + 18], 4 - pinsrw xmm8, word ptr [rsi + rcx + 18], 5 - pinsrw xmm8, word ptr [rsi + rdx + 18], 6 - pinsrw xmm8, word ptr [rsi + rbx + 18], 7 - pcmpeqw xmm4, xmm0 - packsswb xmm4, xmm4 - psllw xmm4, 7 - pand xmm4, xmm14 - por xmm4, xmm7 - movd xmm2, eax - movzx eax, word ptr [rsi + r15 + 32] - por xmm4, xmm3 - pcmpeqw xmm8, xmm0 - packsswb xmm8, xmm8 - movdqa xmm7, xmm8 - pand xmm7, xmm15 - psubb xmm7, xmm8 - movd xmm3, r11d - movzx r11d, word ptr [rsi + r15 + 34] - pinsrw xmm1, word ptr [rsi + r8 + 16], 1 - pinsrw xmm1, word ptr [rsi + r9 + 16], 2 - pinsrw xmm1, word ptr [rsi + r12 + 16], 3 - pinsrw xmm1, word ptr [rsi + r13 + 16], 4 - pinsrw xmm1, word ptr [rsi + rcx + 16], 5 - pinsrw xmm1, word ptr [rsi + rdx + 16], 6 - pinsrw xmm1, word ptr [rsi + rbx + 16], 7 - pcmpeqw xmm1, xmm0 - packsswb xmm1, xmm1 - pand xmm1, xmm15 - por xmm7, xmm1 - movd xmm6, edi - movzx edi, word ptr [rsi + r15 + 36] - mov dword ptr [rsp + 48], edi # 4-byte Spill - pinsrw xmm5, word ptr [rsi + r8 + 20], 1 - pinsrw xmm5, word ptr [rsi + r9 + 20], 2 - pinsrw xmm5, word ptr [rsi + r12 + 20], 3 - pinsrw xmm5, word ptr [rsi + r13 + 20], 4 - pinsrw xmm5, word ptr [rsi + rcx + 20], 5 - pinsrw xmm5, word ptr [rsi + rdx + 20], 6 - pinsrw xmm5, word ptr [rsi + rbx + 20], 7 - pcmpeqw xmm5, xmm0 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 2 - pand xmm5, xmm9 - por xmm5, xmm7 - movd xmm7, r14d - movzx edi, word ptr [rsi + r15 + 38] - mov dword ptr [rsp + 16], edi # 4-byte Spill - pinsrw xmm2, word ptr [rsi + r8 + 22], 1 - pinsrw xmm2, word ptr [rsi + r9 + 22], 2 - pinsrw xmm2, word ptr [rsi + r12 + 22], 3 - pinsrw xmm2, word ptr [rsi + r13 + 22], 4 - pinsrw xmm2, word ptr [rsi + rcx + 22], 5 - pinsrw xmm2, word ptr [rsi + rdx + 22], 6 - pinsrw xmm2, word ptr [rsi + rbx + 22], 7 - pinsrw xmm3, word ptr [rsi + r8 + 24], 1 - pinsrw xmm3, word ptr [rsi + r9 + 24], 2 - pinsrw xmm3, word ptr [rsi + r12 + 24], 3 - pinsrw xmm3, word ptr [rsi + r13 + 24], 4 - pinsrw xmm3, word ptr [rsi + rcx + 24], 5 - pinsrw xmm3, word ptr [rsi + rdx + 24], 6 - pinsrw xmm3, word ptr [rsi + rbx + 24], 7 - pcmpeqw xmm2, xmm0 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 3 - pand xmm2, xmm10 - pcmpeqw xmm3, xmm0 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 4 - pand xmm3, xmm11 - por xmm3, xmm2 - movd xmm2, r10d - movzx edi, word ptr [rsi + r15 + 40] - por xmm3, xmm5 - movd xmm5, eax - movzx eax, word ptr [rsi + r15 + 42] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + r8 + 26], 1 - pinsrw xmm6, word ptr [rsi + r9 + 26], 2 - pinsrw xmm6, word ptr [rsi + r12 + 26], 3 - pinsrw xmm6, word ptr [rsi + r13 + 26], 4 - pinsrw xmm6, word ptr [rsi + rcx + 26], 5 - pinsrw xmm6, word ptr [rsi + rdx + 26], 6 - pinsrw xmm6, word ptr [rsi + rbx + 26], 7 - pinsrw xmm7, word ptr [rsi + r8 + 28], 1 - pinsrw xmm7, word ptr [rsi + r9 + 28], 2 - pinsrw xmm7, word ptr [rsi + r12 + 28], 3 - pinsrw xmm7, word ptr [rsi + r13 + 28], 4 - pinsrw xmm7, word ptr [rsi + rcx + 28], 5 - pinsrw xmm7, word ptr [rsi + rdx + 28], 6 - pinsrw xmm7, word ptr [rsi + rbx + 28], 7 - pinsrw xmm2, word ptr [rsi + r8 + 30], 1 - pinsrw xmm2, word ptr [rsi + r9 + 30], 2 - pinsrw xmm2, word ptr [rsi + r12 + 30], 3 - pinsrw xmm2, word ptr [rsi + r13 + 30], 4 - pinsrw xmm2, word ptr [rsi + rcx + 30], 5 - pinsrw xmm2, word ptr [rsi + rdx + 30], 6 - pinsrw xmm2, word ptr [rsi + rbx + 30], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - pcmpeqw xmm7, xmm0 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 6 - pand xmm7, xmm13 - por xmm7, xmm6 - movd xmm1, r11d - movzx r10d, word ptr [rsi + r15 + 44] - pcmpeqw xmm2, xmm0 - packsswb xmm2, xmm2 - psllw xmm2, 7 - pand xmm2, xmm14 - por xmm2, xmm7 - movd xmm6, dword ptr [rsp + 48] # 4-byte Folded Reload - # xmm6 = mem[0],zero,zero,zero - movzx r14d, word ptr [rsi + r15 + 46] - pinsrw xmm5, word ptr [rsi + r8 + 32], 1 - pinsrw xmm5, word ptr [rsi + r9 + 32], 2 - pinsrw xmm5, word ptr [rsi + r12 + 32], 3 - pinsrw xmm5, word ptr [rsi + r13 + 32], 4 - pinsrw xmm5, word ptr [rsi + rcx + 32], 5 - pinsrw xmm5, word ptr [rsi + rdx + 32], 6 - pinsrw xmm1, word ptr [rsi + r8 + 34], 1 - pinsrw xmm1, word ptr [rsi + r9 + 34], 2 - pinsrw xmm1, word ptr [rsi + r12 + 34], 3 - pinsrw xmm1, word ptr [rsi + r13 + 34], 4 - pinsrw xmm1, word ptr [rsi + rcx + 34], 5 - pinsrw xmm1, word ptr [rsi + rdx + 34], 6 - pinsrw xmm1, word ptr [rsi + rbx + 34], 7 - por xmm2, xmm3 - pcmpeqw xmm1, xmm0 - packsswb xmm1, xmm1 - movdqa xmm7, xmm1 - pand xmm7, xmm15 - psubb xmm7, xmm1 - movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 48] - mov dword ptr [rsp + 16], eax # 4-byte Spill - pinsrw xmm5, word ptr [rsi + rbx + 32], 7 - pcmpeqw xmm5, xmm0 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - pinsrw xmm6, word ptr [rsi + r8 + 36], 1 - pinsrw xmm6, word ptr [rsi + r9 + 36], 2 - pinsrw xmm6, word ptr [rsi + r12 + 36], 3 - pinsrw xmm6, word ptr [rsi + r13 + 36], 4 - pinsrw xmm6, word ptr [rsi + rcx + 36], 5 - pinsrw xmm6, word ptr [rsi + rdx + 36], 6 - pinsrw xmm6, word ptr [rsi + rbx + 36], 7 - pinsrw xmm3, word ptr [rsi + r8 + 38], 1 - pinsrw xmm3, word ptr [rsi + r9 + 38], 2 - pinsrw xmm3, word ptr [rsi + r12 + 38], 3 - pinsrw xmm3, word ptr [rsi + r13 + 38], 4 - pinsrw xmm3, word ptr [rsi + rcx + 38], 5 - pinsrw xmm3, word ptr [rsi + rdx + 38], 6 - pinsrw xmm3, word ptr [rsi + rbx + 38], 7 - por xmm7, xmm5 - movd xmm5, edi - pinsrw xmm5, word ptr [rsi + r8 + 40], 1 - pinsrw xmm5, word ptr [rsi + r9 + 40], 2 - pinsrw xmm5, word ptr [rsi + r12 + 40], 3 - pinsrw xmm5, word ptr [rsi + r13 + 40], 4 - pinsrw xmm5, word ptr [rsi + rcx + 40], 5 - pinsrw xmm5, word ptr [rsi + rdx + 40], 6 - movzx eax, word ptr [rsi + r15 + 50] - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 2 - pand xmm6, xmm9 - por xmm6, xmm7 - movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx edi, word ptr [rsi + r15 + 52] - mov dword ptr [rsp + 24], edi # 4-byte Spill - pinsrw xmm5, word ptr [rsi + rbx + 40], 7 - pcmpeqw xmm3, xmm0 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 3 - pand xmm3, xmm10 - pcmpeqw xmm5, xmm0 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 4 - pand xmm5, xmm11 - por xmm5, xmm3 - movd xmm7, r10d - movzx r11d, word ptr [rsi + r15 + 54] - pinsrw xmm1, word ptr [rsi + r8 + 42], 1 - pinsrw xmm1, word ptr [rsi + r9 + 42], 2 - pinsrw xmm1, word ptr [rsi + r12 + 42], 3 - pinsrw xmm1, word ptr [rsi + r13 + 42], 4 - pinsrw xmm1, word ptr [rsi + rcx + 42], 5 - pinsrw xmm1, word ptr [rsi + rdx + 42], 6 - pinsrw xmm1, word ptr [rsi + rbx + 42], 7 - pinsrw xmm7, word ptr [rsi + r8 + 44], 1 - pinsrw xmm7, word ptr [rsi + r9 + 44], 2 - pinsrw xmm7, word ptr [rsi + r12 + 44], 3 - pinsrw xmm7, word ptr [rsi + r13 + 44], 4 - pinsrw xmm7, word ptr [rsi + rcx + 44], 5 - pinsrw xmm7, word ptr [rsi + rdx + 44], 6 - por xmm5, xmm6 - movd xmm3, r14d - movzx r10d, word ptr [rsi + r15 + 56] - pinsrw xmm7, word ptr [rsi + rbx + 44], 7 - pcmpeqw xmm1, xmm0 - packsswb xmm1, xmm1 - pand xmm1, xmm15 - psllw xmm1, 5 - pand xmm1, xmm12 - pcmpeqw xmm7, xmm0 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 6 - pand xmm7, xmm13 - por xmm7, xmm1 - movd xmm6, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm6 = mem[0],zero,zero,zero - movzx r14d, word ptr [rsi + r15 + 58] - pinsrw xmm3, word ptr [rsi + r8 + 46], 1 - pinsrw xmm3, word ptr [rsi + r9 + 46], 2 - pinsrw xmm3, word ptr [rsi + r12 + 46], 3 - pinsrw xmm3, word ptr [rsi + r13 + 46], 4 - pinsrw xmm3, word ptr [rsi + rcx + 46], 5 - pinsrw xmm3, word ptr [rsi + rdx + 46], 6 - pinsrw xmm3, word ptr [rsi + rbx + 46], 7 - pcmpeqw xmm3, xmm0 - packsswb xmm3, xmm3 - psllw xmm3, 7 - pand xmm3, xmm14 - por xmm3, xmm7 - movd xmm1, eax - movzx edi, word ptr [rsi + r15 + 60] - movzx r15d, word ptr [rsi + r15 + 62] - pinsrw xmm1, word ptr [rsi + r8 + 50], 1 - pinsrw xmm1, word ptr [rsi + r9 + 50], 2 - pinsrw xmm1, word ptr [rsi + r12 + 50], 3 - pinsrw xmm1, word ptr [rsi + r13 + 50], 4 - pinsrw xmm1, word ptr [rsi + rcx + 50], 5 - pinsrw xmm1, word ptr [rsi + rdx + 50], 6 - pinsrw xmm1, word ptr [rsi + rbx + 50], 7 - por xmm3, xmm5 - pcmpeqw xmm1, xmm0 - packsswb xmm1, xmm1 - movdqa xmm5, xmm1 - pand xmm5, xmm15 - psubb xmm5, xmm1 - movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - mov rax, qword ptr [rsp + 136] # 8-byte Reload - pinsrw xmm6, word ptr [rsi + r8 + 48], 1 - pinsrw xmm6, word ptr [rsi + r9 + 48], 2 - pinsrw xmm6, word ptr [rsi + r12 + 48], 3 - pinsrw xmm6, word ptr [rsi + r13 + 48], 4 - pinsrw xmm6, word ptr [rsi + rcx + 48], 5 - pinsrw xmm6, word ptr [rsi + rdx + 48], 6 - pinsrw xmm6, word ptr [rsi + rbx + 48], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - pinsrw xmm1, word ptr [rsi + r8 + 52], 1 - pinsrw xmm1, word ptr [rsi + r9 + 52], 2 - pinsrw xmm1, word ptr [rsi + r12 + 52], 3 - pinsrw xmm1, word ptr [rsi + r13 + 52], 4 - pinsrw xmm1, word ptr [rsi + rcx + 52], 5 - pand xmm6, xmm15 - pinsrw xmm1, word ptr [rsi + rdx + 52], 6 - por xmm5, xmm6 - movd xmm6, r11d - pinsrw xmm1, word ptr [rsi + rbx + 52], 7 - pcmpeqw xmm1, xmm0 - packsswb xmm1, xmm1 - pand xmm1, xmm15 - psllw xmm1, 2 - pand xmm1, xmm9 - por xmm1, xmm5 - movd xmm5, r10d - pinsrw xmm6, word ptr [rsi + r8 + 54], 1 - pinsrw xmm6, word ptr [rsi + r9 + 54], 2 - pinsrw xmm6, word ptr [rsi + r12 + 54], 3 - pinsrw xmm6, word ptr [rsi + r13 + 54], 4 - pinsrw xmm6, word ptr [rsi + rcx + 54], 5 - pinsrw xmm6, word ptr [rsi + rdx + 54], 6 - pinsrw xmm6, word ptr [rsi + rbx + 54], 7 - pinsrw xmm5, word ptr [rsi + r8 + 56], 1 - pinsrw xmm5, word ptr [rsi + r9 + 56], 2 - pinsrw xmm5, word ptr [rsi + r12 + 56], 3 - pinsrw xmm5, word ptr [rsi + r13 + 56], 4 - pinsrw xmm5, word ptr [rsi + rcx + 56], 5 - pinsrw xmm5, word ptr [rsi + rdx + 56], 6 - pinsrw xmm5, word ptr [rsi + rbx + 56], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 3 - pand xmm6, xmm10 - pcmpeqw xmm5, xmm0 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 4 - pand xmm5, xmm11 - por xmm5, xmm6 - movd xmm6, r14d - pinsrw xmm6, word ptr [rsi + r8 + 58], 1 - pinsrw xmm6, word ptr [rsi + r9 + 58], 2 - pinsrw xmm6, word ptr [rsi + r12 + 58], 3 - pinsrw xmm6, word ptr [rsi + r13 + 58], 4 - pinsrw xmm6, word ptr [rsi + rcx + 58], 5 - pinsrw xmm6, word ptr [rsi + rdx + 58], 6 - pinsrw xmm6, word ptr [rsi + rbx + 58], 7 - por xmm5, xmm1 - movd xmm1, edi - pinsrw xmm1, word ptr [rsi + r8 + 60], 1 - pinsrw xmm1, word ptr [rsi + r9 + 60], 2 - pinsrw xmm1, word ptr [rsi + r12 + 60], 3 - pinsrw xmm1, word ptr [rsi + r13 + 60], 4 - pinsrw xmm1, word ptr [rsi + rcx + 60], 5 - pinsrw xmm1, word ptr [rsi + rdx + 60], 6 - pinsrw xmm1, word ptr [rsi + rbx + 60], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - pcmpeqw xmm1, xmm0 - packsswb xmm1, xmm1 - pand xmm1, xmm15 - psllw xmm1, 6 - pand xmm1, xmm13 - por xmm1, xmm6 - movd xmm6, r15d - pinsrw xmm6, word ptr [rsi + r8 + 62], 1 - pinsrw xmm6, word ptr [rsi + r9 + 62], 2 - pinsrw xmm6, word ptr [rsi + r12 + 62], 3 - pinsrw xmm6, word ptr [rsi + r13 + 62], 4 - pinsrw xmm6, word ptr [rsi + rcx + 62], 5 - pinsrw xmm6, word ptr [rsi + rdx + 62], 6 - pinsrw xmm6, word ptr [rsi + rbx + 62], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - psllw xmm6, 7 - pand xmm6, xmm14 - por xmm6, xmm1 - por xmm6, xmm5 - movdqa xmm1, xmm4 - punpcklqdq xmm1, xmm2 # xmm1 = xmm1[0],xmm2[0] - movdqa xmm5, xmm3 - punpcklqdq xmm5, xmm6 # xmm5 = xmm5[0],xmm6[0] - movdqa xmm7, xmmword ptr [rip + .LCPI1_9] # xmm7 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> - pshufb xmm5, xmm7 - pshufb xmm1, xmm7 - punpcklwd xmm1, xmm5 # xmm1 = xmm1[0],xmm5[0],xmm1[1],xmm5[1],xmm1[2],xmm5[2],xmm1[3],xmm5[3] - punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] - punpcklbw xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7] - punpcklwd xmm4, xmm3 # xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3] - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx], xmm4 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm1 - add rcx, 8 - mov r15, rcx - cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB1_112 -# %bb.113: - mov r15, qword ptr [rsp + 240] # 8-byte Reload - cmp r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11d, dword ptr [rsp + 4] # 4-byte Reload - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - jne .LBB1_114 - jmp .LBB1_117 -.LBB1_134: - and r15, -8 - mov rax, r15 - shl rax, 6 - add rax, rsi - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 8], rax # 8-byte Spill - movd xmm0, r11d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] - xor r15d, r15d - movdqa xmm15, xmmword ptr [rip + .LCPI1_8] # xmm15 = <1,1,1,1,1,1,1,1,u,u,u,u,u,u,u,u> - movdqa xmm9, xmmword ptr [rip + .LCPI1_1] # xmm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - movdqa xmm10, xmmword ptr [rip + .LCPI1_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - movdqa xmm11, xmmword ptr [rip + .LCPI1_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - movdqa xmm12, xmmword ptr [rip + .LCPI1_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - movdqa xmm13, xmmword ptr [rip + .LCPI1_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] - movdqa xmm14, xmmword ptr [rip + .LCPI1_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - mov qword ptr [rsp + 136], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB1_135: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 40], r15 # 8-byte Spill - shl r15, 6 - mov r9, r15 - mov r12, r15 - mov r13, r15 - mov rcx, r15 - mov rdx, r15 - mov rbx, r15 - movzx r14d, word ptr [rsi + r15] - movzx eax, word ptr [rsi + r15 + 2] - movzx r10d, word ptr [rsi + r15 + 4] - movzx edi, word ptr [rsi + r15 + 6] - movzx r11d, word ptr [rsi + r15 + 8] +.LBB1_77: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r11b + sete byte ptr [rsp + 256] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r11b + sete sil + cmp byte ptr [rcx + 2], r11b + sete r15b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 3], al + sete byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 4], al + sete byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 5], al + sete byte ptr [rsp + 64] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 6], al + sete r13b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 7], al + sete r9b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 8], al + sete byte ptr [rsp + 224] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 9], al + sete dl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 10], al + sete r8b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 11], al + sete r10b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 12], al + sete r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 13], al + sete byte ptr [rsp + 128] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 14], al + sete byte ptr [rsp + 208] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 15], al + sete r12b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 16], bl + sete byte ptr [rsp + 160] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 17], bl + sete byte ptr [rsp + 176] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 18], bl + sete byte ptr [rsp + 96] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 19], bl + sete byte ptr [rsp + 104] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 20], bl + sete byte ptr [rsp + 88] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 21], bl + sete byte ptr [rsp + 72] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 22], bl + sete byte ptr [rsp + 80] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 23], bl + sete r11b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 24], bl + sete byte ptr [rsp + 56] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 25], bl + sete byte ptr [rsp + 32] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 26], bl + sete byte ptr [rsp + 48] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 27], bl + sete byte ptr [rsp + 40] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 28], bl + sete byte ptr [rsp + 16] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 29], bl + sete byte ptr [rsp + 24] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 30], bl + sete byte ptr [rsp + 120] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 31], bl + sete bl + add sil, sil + add sil, byte ptr [rsp + 256] # 1-byte Folded Reload + shl r13b, 6 + shl r9b, 7 + or r9b, r13b + shl r15b, 2 + or r15b, sil + add dl, dl + add dl, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r15b + movzx r15d, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r8b, 2 + or r8b, dl + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, al + mov esi, edx + shl r10b, 3 + or r10b, r8b + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + shl r14b, 4 + or r14b, r10b + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 208] # 1-byte Folded Reload + shl sil, 6 + shl r12b, 7 + or r12b, sil + or r9b, dl + or r12b, al + movzx edx, byte ptr [rsp + 176] # 1-byte Folded Reload + add dl, dl + add dl, byte ptr [rsp + 160] # 1-byte Folded Reload + mov esi, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 2 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov byte ptr [rdi], r9b + movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + shl sil, 6 + shl r11b, 7 + or r11b, sil + mov byte ptr [rdi + 1], r12b + or r11b, dl + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 56] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r11b + mov r11d, r15d + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB1_77 +# %bb.78: + mov qword ptr [rsp + 144], rdi # 8-byte Spill + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 280] # 8-byte Reload + jmp .LBB1_79 +.LBB1_66: + mov qword ptr [rsp + 144], r12 # 8-byte Spill + mov rsi, r14 +.LBB1_79: + shl rcx, 5 mov r8, r15 - or r8, 64 - or r9, 128 - or r12, 192 - or r13, 256 - or rcx, 320 - or rdx, 384 - or rbx, 448 - movd xmm4, r14d - pinsrw xmm4, word ptr [rsi + r8], 1 - pinsrw xmm4, word ptr [rsi + r9], 2 - pinsrw xmm4, word ptr [rsi + r12], 3 - pinsrw xmm4, word ptr [rsi + r13], 4 - pinsrw xmm4, word ptr [rsi + rcx], 5 - pinsrw xmm4, word ptr [rsi + rdx], 6 - pinsrw xmm4, word ptr [rsi + rbx], 7 - movzx r14d, word ptr [rsi + r15 + 10] - movd xmm6, eax - pinsrw xmm6, word ptr [rsi + r8 + 2], 1 - pinsrw xmm6, word ptr [rsi + r9 + 2], 2 - pinsrw xmm6, word ptr [rsi + r12 + 2], 3 - movzx eax, word ptr [rsi + r15 + 12] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + r13 + 2], 4 - movd xmm2, r10d - movzx eax, word ptr [rsi + r15 + 14] - mov dword ptr [rsp + 16], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + rcx + 2], 5 - movd xmm5, edi - movzx edi, word ptr [rsi + r15 + 16] - pinsrw xmm6, word ptr [rsi + rdx + 2], 6 - movd xmm3, r11d - movzx eax, word ptr [rsi + r15 + 18] - mov dword ptr [rsp + 48], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + rbx + 2], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - movdqa xmm1, xmm6 - pand xmm1, xmm15 - psubb xmm1, xmm6 - movd xmm6, r14d - movzx r10d, word ptr [rsi + r15 + 20] - pcmpeqw xmm4, xmm0 - packsswb xmm4, xmm4 - pand xmm4, xmm15 - pinsrw xmm2, word ptr [rsi + r8 + 4], 1 - pinsrw xmm2, word ptr [rsi + r9 + 4], 2 - pinsrw xmm2, word ptr [rsi + r12 + 4], 3 - pinsrw xmm2, word ptr [rsi + r13 + 4], 4 - pinsrw xmm2, word ptr [rsi + rcx + 4], 5 - pinsrw xmm2, word ptr [rsi + rdx + 4], 6 - pinsrw xmm2, word ptr [rsi + rbx + 4], 7 - pinsrw xmm5, word ptr [rsi + r8 + 6], 1 - pinsrw xmm5, word ptr [rsi + r9 + 6], 2 - pinsrw xmm5, word ptr [rsi + r12 + 6], 3 - pinsrw xmm5, word ptr [rsi + r13 + 6], 4 - pinsrw xmm5, word ptr [rsi + rcx + 6], 5 - pinsrw xmm5, word ptr [rsi + rdx + 6], 6 - pinsrw xmm5, word ptr [rsi + rbx + 6], 7 - pinsrw xmm3, word ptr [rsi + r8 + 8], 1 - pinsrw xmm3, word ptr [rsi + r9 + 8], 2 - pinsrw xmm3, word ptr [rsi + r12 + 8], 3 - pinsrw xmm3, word ptr [rsi + r13 + 8], 4 - pinsrw xmm3, word ptr [rsi + rcx + 8], 5 - pinsrw xmm3, word ptr [rsi + rdx + 8], 6 - pinsrw xmm3, word ptr [rsi + rbx + 8], 7 - por xmm1, xmm4 - movd xmm7, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 22] - pcmpeqw xmm2, xmm0 - packsswb xmm2, xmm2 + sub r8, rcx + jle .LBB1_222 +# %bb.80: + or rcx, 1 + cmp r15, rcx + jne .LBB1_82 +# %bb.81: + xor r9d, r9d + jmp .LBB1_85 +.LBB1_175: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB1_176: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d + sete al + neg al + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + sete al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB1_176 +.LBB1_22: + test r8b, 1 + je .LBB1_222 +# %bb.23: + cmp dword ptr [rsi], r13d + jmp .LBB1_24 +.LBB1_109: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 144] # 8-byte Reload + .p2align 4, 0x90 +.LBB1_110: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r14b + sete bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r14b + lea r9, [rax + 2] + sete bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB1_110 +# %bb.111: + add rsi, r9 +.LBB1_112: + test r8b, 1 + je .LBB1_222 +# %bb.113: + cmp byte ptr [rsi], r14b + sete al + neg al + mov rdx, r9 + shr rdx, 3 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + mov dil, byte ptr [r14 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r14 + rdx], bl + jmp .LBB1_222 +.LBB1_82: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r14, qword ptr [rsp + 144] # 8-byte Reload + .p2align 4, 0x90 +.LBB1_83: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r11b + sete bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r14 + rdi], dl + cmp byte ptr [rsi + rax + 1], r11b + lea r9, [rax + 2] + sete bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r14 + rdi], al + cmp r10, r9 + jne .LBB1_83 +# %bb.84: + add rsi, r9 +.LBB1_85: + test r8b, 1 + je .LBB1_222 +# %bb.86: + cmp byte ptr [rsi], r11b + sete al + neg al + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + jmp .LBB1_87 +.LBB1_218: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB1_219: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rsi] + setnp cl + sete al + and al, cl + neg al + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r10d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r10b + and bl, al + xor bl, r10b + mov byte ptr [r12 + rdi], bl + add r11, 2 + ucomisd xmm0, qword ptr [rsi + 8] + lea rsi, [rsi + 16] + setnp r10b + sete al + and al, r10b + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r9, r11 + jne .LBB1_219 +.LBB1_220: + test r8b, 1 + je .LBB1_222 +# %bb.221: + ucomisd xmm0, qword ptr [rsi] + setnp al + sete dl + and dl, al + neg dl + mov rax, r11 + shr rax, 3 + mov sil, byte ptr [r12 + rax] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor dl, sil + and bl, dl + xor bl, sil + mov byte ptr [r12 + rax], bl + jmp .LBB1_222 +.LBB1_191: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB1_192: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + sete al + neg al + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + sete al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB1_192 +.LBB1_41: + test r8b, 1 + je .LBB1_222 +# %bb.42: + cmp qword ptr [rsi], r13 +.LBB1_24: + sete al + neg al + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al + xor bl, sil + mov byte ptr [r12 + rdx], bl + jmp .LBB1_222 +.LBB1_159: + mov r9, r8 + and r9, -2 + xor r14d, r14d + mov r11, qword ptr [rsp + 8] # 8-byte Reload + .p2align 4, 0x90 +.LBB1_160: # =>This Inner Loop Header: Depth=1 + mov rax, rsi + cmp word ptr [rsi], r13w + sete dl + neg dl + mov rdi, r14 + shr rdi, 3 + movzx r10d, byte ptr [r11 + rdi] + mov ecx, r14d + and cl, 6 + mov bl, 1 + shl bl, cl + xor dl, r10b + and bl, dl + xor bl, r10b + mov byte ptr [r11 + rdi], bl + add r14, 2 + cmp word ptr [rsi + 2], r13w + lea rsi, [rsi + 4] + sete dl + neg dl + xor dl, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, bl + mov byte ptr [r11 + rdi], al + cmp r9, r14 + jne .LBB1_160 +.LBB1_135: + test r8b, 1 + je .LBB1_222 +# %bb.136: + cmp word ptr [rsi], r13w + sete al + neg al + mov rdx, r14 + shr rdx, 3 + mov r8, qword ptr [rsp + 8] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r14b, 7 + mov bl, 1 + mov ecx, r14d +.LBB1_87: + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r8 + rdx], bl + jmp .LBB1_222 +.LBB1_216: + mov r9, r8 + and r9, -2 + xor esi, esi + mov r14, r13 + .p2align 4, 0x90 +.LBB1_217: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rbx] + setnp cl + sete dl + and dl, cl + neg dl + mov rdi, rsi + shr rdi, 3 + movzx r10d, byte ptr [r14 + rdi] + mov ecx, esi + and cl, 6 + mov r11b, 1 + shl r11b, cl + xor dl, r10b + and r11b, dl + xor r11b, r10b + mov byte ptr [r14 + rdi], r11b + add rsi, 2 + ucomiss xmm0, dword ptr [rbx + 4] + lea rbx, [rbx + 8] + setnp r10b + sete dl + and dl, r10b + neg dl + xor dl, r11b + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, r11b + mov byte ptr [r14 + rdi], al + cmp r9, rsi + jne .LBB1_217 +.LBB1_214: + test r8b, 1 + je .LBB1_222 +# %bb.215: + ucomiss xmm0, dword ptr [rbx] + setnp al + sete dl + and dl, al + neg dl + mov rax, rsi + shr rax, 3 + mov dil, byte ptr [r13 + rax] + and sil, 7 + mov bl, 1 + mov ecx, esi + shl bl, cl + xor dl, dil + and bl, dl + xor bl, dil + mov byte ptr [r13 + rax], bl +.LBB1_222: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.LBB1_126: + and rcx, -8 + mov rax, rcx + shl rax, 6 + add rax, rsi + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 32], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 8], rax # 8-byte Spill + mov dword ptr [rsp + 56], r13d # 4-byte Spill + movd xmm0, r13d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] + xor r15d, r15d + movdqa xmm15, xmmword ptr [rip + .LCPI1_8] # xmm15 = <1,1,1,1,1,1,1,1,u,u,u,u,u,u,u,u> + movdqa xmm9, xmmword ptr [rip + .LCPI1_1] # xmm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + movdqa xmm10, xmmword ptr [rip + .LCPI1_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + movdqa xmm11, xmmword ptr [rip + .LCPI1_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + movdqa xmm12, xmmword ptr [rip + .LCPI1_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + movdqa xmm13, xmmword ptr [rip + .LCPI1_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] + movdqa xmm14, xmmword ptr [rip + .LCPI1_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + mov qword ptr [rsp + 120], r12 # 8-byte Spill + .p2align 4, 0x90 +.LBB1_127: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill + shl r15, 6 + mov r8, r15 + mov r12, r15 + mov rdx, r15 + mov rcx, r15 + mov rbx, r15 + mov rax, r15 + movzx r14d, word ptr [rsi + r15] + movzx edi, word ptr [rsi + r15 + 2] + movzx r11d, word ptr [rsi + r15 + 4] + movzx r13d, word ptr [rsi + r15 + 6] + movzx r10d, word ptr [rsi + r15 + 8] + mov r9, r15 + or r9, 64 + or r8, 128 + or r12, 192 + or rdx, 256 + or rcx, 320 + or rbx, 384 + or rax, 448 + movd xmm4, r14d + pinsrw xmm4, word ptr [rsi + r9], 1 + pinsrw xmm4, word ptr [rsi + r8], 2 + pinsrw xmm4, word ptr [rsi + r12], 3 + pinsrw xmm4, word ptr [rsi + rdx], 4 + pinsrw xmm4, word ptr [rsi + rcx], 5 + pinsrw xmm4, word ptr [rsi + rbx], 6 + pinsrw xmm4, word ptr [rsi + rax], 7 + movzx r14d, word ptr [rsi + r15 + 10] + movd xmm6, edi + pinsrw xmm6, word ptr [rsi + r9 + 2], 1 + pinsrw xmm6, word ptr [rsi + r8 + 2], 2 + pinsrw xmm6, word ptr [rsi + r12 + 2], 3 + movzx edi, word ptr [rsi + r15 + 12] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm6, word ptr [rsi + rdx + 2], 4 + movd xmm2, r11d + movzx r11d, word ptr [rsi + r15 + 14] + pinsrw xmm6, word ptr [rsi + rcx + 2], 5 + movd xmm5, r13d + movzx edi, word ptr [rsi + r15 + 16] + mov dword ptr [rsp + 40], edi # 4-byte Spill + pinsrw xmm6, word ptr [rsi + rbx + 2], 6 + movd xmm3, r10d + movzx edi, word ptr [rsi + r15 + 18] + mov dword ptr [rsp + 48], edi # 4-byte Spill + pinsrw xmm6, word ptr [rsi + rax + 2], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + movdqa xmm1, xmm6 + pand xmm1, xmm15 + psubb xmm1, xmm6 + movd xmm6, r14d + movzx r13d, word ptr [rsi + r15 + 20] + pcmpeqw xmm4, xmm0 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + pinsrw xmm2, word ptr [rsi + r9 + 4], 1 + pinsrw xmm2, word ptr [rsi + r8 + 4], 2 + pinsrw xmm2, word ptr [rsi + r12 + 4], 3 + pinsrw xmm2, word ptr [rsi + rdx + 4], 4 + pinsrw xmm2, word ptr [rsi + rcx + 4], 5 + pinsrw xmm2, word ptr [rsi + rbx + 4], 6 + pinsrw xmm2, word ptr [rsi + rax + 4], 7 + pinsrw xmm5, word ptr [rsi + r9 + 6], 1 + pinsrw xmm5, word ptr [rsi + r8 + 6], 2 + pinsrw xmm5, word ptr [rsi + r12 + 6], 3 + pinsrw xmm5, word ptr [rsi + rdx + 6], 4 + pinsrw xmm5, word ptr [rsi + rcx + 6], 5 + pinsrw xmm5, word ptr [rsi + rbx + 6], 6 + pinsrw xmm5, word ptr [rsi + rax + 6], 7 + pinsrw xmm3, word ptr [rsi + r9 + 8], 1 + pinsrw xmm3, word ptr [rsi + r8 + 8], 2 + pinsrw xmm3, word ptr [rsi + r12 + 8], 3 + pinsrw xmm3, word ptr [rsi + rdx + 8], 4 + pinsrw xmm3, word ptr [rsi + rcx + 8], 5 + pinsrw xmm3, word ptr [rsi + rbx + 8], 6 + pinsrw xmm3, word ptr [rsi + rax + 8], 7 + por xmm1, xmm4 + movd xmm7, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r14d, word ptr [rsi + r15 + 22] + pcmpeqw xmm2, xmm0 + packsswb xmm2, xmm2 pand xmm2, xmm15 psllw xmm2, 2 pand xmm2, xmm9 por xmm2, xmm1 - movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx r11d, word ptr [rsi + r15 + 24] + movd xmm4, r11d + movzx edi, word ptr [rsi + r15 + 24] pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 @@ -8715,26 +6625,27 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 psllw xmm3, 4 pand xmm3, xmm11 por xmm3, xmm5 - movd xmm1, edi - movzx edi, word ptr [rsi + r15 + 26] - pinsrw xmm6, word ptr [rsi + r8 + 10], 1 - pinsrw xmm6, word ptr [rsi + r9 + 10], 2 + movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r10d, word ptr [rsi + r15 + 26] + pinsrw xmm6, word ptr [rsi + r9 + 10], 1 + pinsrw xmm6, word ptr [rsi + r8 + 10], 2 pinsrw xmm6, word ptr [rsi + r12 + 10], 3 - pinsrw xmm6, word ptr [rsi + r13 + 10], 4 + pinsrw xmm6, word ptr [rsi + rdx + 10], 4 pinsrw xmm6, word ptr [rsi + rcx + 10], 5 - pinsrw xmm6, word ptr [rsi + rdx + 10], 6 - pinsrw xmm6, word ptr [rsi + rbx + 10], 7 - pinsrw xmm7, word ptr [rsi + r8 + 12], 1 - pinsrw xmm7, word ptr [rsi + r9 + 12], 2 + pinsrw xmm6, word ptr [rsi + rbx + 10], 6 + pinsrw xmm6, word ptr [rsi + rax + 10], 7 + pinsrw xmm7, word ptr [rsi + r9 + 12], 1 + pinsrw xmm7, word ptr [rsi + r8 + 12], 2 pinsrw xmm7, word ptr [rsi + r12 + 12], 3 - pinsrw xmm7, word ptr [rsi + r13 + 12], 4 + pinsrw xmm7, word ptr [rsi + rdx + 12], 4 pinsrw xmm7, word ptr [rsi + rcx + 12], 5 - pinsrw xmm7, word ptr [rsi + rdx + 12], 6 - pinsrw xmm7, word ptr [rsi + rbx + 12], 7 + pinsrw xmm7, word ptr [rsi + rbx + 12], 6 + pinsrw xmm7, word ptr [rsi + rax + 12], 7 por xmm3, xmm2 movd xmm8, dword ptr [rsp + 48] # 4-byte Folded Reload # xmm8 = mem[0],zero,zero,zero - movzx r14d, word ptr [rsi + r15 + 28] + movzx r11d, word ptr [rsi + r15 + 28] pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -8746,81 +6657,81 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 psllw xmm7, 6 pand xmm7, xmm13 por xmm7, xmm6 - movd xmm5, r10d - movzx r10d, word ptr [rsi + r15 + 30] - pinsrw xmm4, word ptr [rsi + r8 + 14], 1 - pinsrw xmm4, word ptr [rsi + r9 + 14], 2 + movd xmm5, r13d + movzx r13d, word ptr [rsi + r15 + 30] + pinsrw xmm4, word ptr [rsi + r9 + 14], 1 + pinsrw xmm4, word ptr [rsi + r8 + 14], 2 pinsrw xmm4, word ptr [rsi + r12 + 14], 3 - pinsrw xmm4, word ptr [rsi + r13 + 14], 4 + pinsrw xmm4, word ptr [rsi + rdx + 14], 4 pinsrw xmm4, word ptr [rsi + rcx + 14], 5 - pinsrw xmm4, word ptr [rsi + rdx + 14], 6 - pinsrw xmm4, word ptr [rsi + rbx + 14], 7 - pinsrw xmm8, word ptr [rsi + r8 + 18], 1 - pinsrw xmm8, word ptr [rsi + r9 + 18], 2 + pinsrw xmm4, word ptr [rsi + rbx + 14], 6 + pinsrw xmm4, word ptr [rsi + rax + 14], 7 + pinsrw xmm8, word ptr [rsi + r9 + 18], 1 + pinsrw xmm8, word ptr [rsi + r8 + 18], 2 pinsrw xmm8, word ptr [rsi + r12 + 18], 3 - pinsrw xmm8, word ptr [rsi + r13 + 18], 4 + pinsrw xmm8, word ptr [rsi + rdx + 18], 4 pinsrw xmm8, word ptr [rsi + rcx + 18], 5 - pinsrw xmm8, word ptr [rsi + rdx + 18], 6 - pinsrw xmm8, word ptr [rsi + rbx + 18], 7 + pinsrw xmm8, word ptr [rsi + rbx + 18], 6 + pinsrw xmm8, word ptr [rsi + rax + 18], 7 pcmpeqw xmm4, xmm0 packsswb xmm4, xmm4 psllw xmm4, 7 pand xmm4, xmm14 por xmm4, xmm7 - movd xmm2, eax - movzx eax, word ptr [rsi + r15 + 32] + movd xmm2, r14d + movzx r14d, word ptr [rsi + r15 + 32] por xmm4, xmm3 pcmpeqw xmm8, xmm0 packsswb xmm8, xmm8 movdqa xmm7, xmm8 pand xmm7, xmm15 psubb xmm7, xmm8 - movd xmm3, r11d - movzx r11d, word ptr [rsi + r15 + 34] - pinsrw xmm1, word ptr [rsi + r8 + 16], 1 - pinsrw xmm1, word ptr [rsi + r9 + 16], 2 + movd xmm3, edi + movzx edi, word ptr [rsi + r15 + 34] + mov dword ptr [rsp + 40], edi # 4-byte Spill + pinsrw xmm1, word ptr [rsi + r9 + 16], 1 + pinsrw xmm1, word ptr [rsi + r8 + 16], 2 pinsrw xmm1, word ptr [rsi + r12 + 16], 3 - pinsrw xmm1, word ptr [rsi + r13 + 16], 4 + pinsrw xmm1, word ptr [rsi + rdx + 16], 4 pinsrw xmm1, word ptr [rsi + rcx + 16], 5 - pinsrw xmm1, word ptr [rsi + rdx + 16], 6 - pinsrw xmm1, word ptr [rsi + rbx + 16], 7 + pinsrw xmm1, word ptr [rsi + rbx + 16], 6 + pinsrw xmm1, word ptr [rsi + rax + 16], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 por xmm7, xmm1 - movd xmm6, edi - movzx edi, word ptr [rsi + r15 + 36] - mov dword ptr [rsp + 48], edi # 4-byte Spill - pinsrw xmm5, word ptr [rsi + r8 + 20], 1 - pinsrw xmm5, word ptr [rsi + r9 + 20], 2 + movd xmm6, r10d + movzx r10d, word ptr [rsi + r15 + 36] + pinsrw xmm5, word ptr [rsi + r9 + 20], 1 + pinsrw xmm5, word ptr [rsi + r8 + 20], 2 pinsrw xmm5, word ptr [rsi + r12 + 20], 3 - pinsrw xmm5, word ptr [rsi + r13 + 20], 4 + pinsrw xmm5, word ptr [rsi + rdx + 20], 4 pinsrw xmm5, word ptr [rsi + rcx + 20], 5 - pinsrw xmm5, word ptr [rsi + rdx + 20], 6 - pinsrw xmm5, word ptr [rsi + rbx + 20], 7 + pinsrw xmm5, word ptr [rsi + rbx + 20], 6 + pinsrw xmm5, word ptr [rsi + rax + 20], 7 pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 psllw xmm5, 2 pand xmm5, xmm9 por xmm5, xmm7 - movd xmm7, r14d + movd xmm7, r11d movzx edi, word ptr [rsi + r15 + 38] mov dword ptr [rsp + 16], edi # 4-byte Spill - pinsrw xmm2, word ptr [rsi + r8 + 22], 1 - pinsrw xmm2, word ptr [rsi + r9 + 22], 2 + pinsrw xmm2, word ptr [rsi + r9 + 22], 1 + pinsrw xmm2, word ptr [rsi + r8 + 22], 2 pinsrw xmm2, word ptr [rsi + r12 + 22], 3 - pinsrw xmm2, word ptr [rsi + r13 + 22], 4 + pinsrw xmm2, word ptr [rsi + rdx + 22], 4 pinsrw xmm2, word ptr [rsi + rcx + 22], 5 - pinsrw xmm2, word ptr [rsi + rdx + 22], 6 - pinsrw xmm2, word ptr [rsi + rbx + 22], 7 - pinsrw xmm3, word ptr [rsi + r8 + 24], 1 - pinsrw xmm3, word ptr [rsi + r9 + 24], 2 + pinsrw xmm2, word ptr [rsi + rbx + 22], 6 + pinsrw xmm2, word ptr [rsi + rax + 22], 7 + pinsrw xmm3, word ptr [rsi + r9 + 24], 1 + pinsrw xmm3, word ptr [rsi + r8 + 24], 2 pinsrw xmm3, word ptr [rsi + r12 + 24], 3 - pinsrw xmm3, word ptr [rsi + r13 + 24], 4 + pinsrw xmm3, word ptr [rsi + rdx + 24], 4 pinsrw xmm3, word ptr [rsi + rcx + 24], 5 - pinsrw xmm3, word ptr [rsi + rdx + 24], 6 - pinsrw xmm3, word ptr [rsi + rbx + 24], 7 + pinsrw xmm3, word ptr [rsi + rbx + 24], 6 + pinsrw xmm3, word ptr [rsi + rax + 24], 7 pcmpeqw xmm2, xmm0 packsswb xmm2, xmm2 pand xmm2, xmm15 @@ -8832,33 +6743,32 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 psllw xmm3, 4 pand xmm3, xmm11 por xmm3, xmm2 - movd xmm2, r10d - movzx edi, word ptr [rsi + r15 + 40] + movd xmm2, r13d + movzx r11d, word ptr [rsi + r15 + 40] por xmm3, xmm5 - movd xmm5, eax - movzx eax, word ptr [rsi + r15 + 42] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + r8 + 26], 1 - pinsrw xmm6, word ptr [rsi + r9 + 26], 2 + movd xmm5, r14d + movzx r14d, word ptr [rsi + r15 + 42] + pinsrw xmm6, word ptr [rsi + r9 + 26], 1 + pinsrw xmm6, word ptr [rsi + r8 + 26], 2 pinsrw xmm6, word ptr [rsi + r12 + 26], 3 - pinsrw xmm6, word ptr [rsi + r13 + 26], 4 + pinsrw xmm6, word ptr [rsi + rdx + 26], 4 pinsrw xmm6, word ptr [rsi + rcx + 26], 5 - pinsrw xmm6, word ptr [rsi + rdx + 26], 6 - pinsrw xmm6, word ptr [rsi + rbx + 26], 7 - pinsrw xmm7, word ptr [rsi + r8 + 28], 1 - pinsrw xmm7, word ptr [rsi + r9 + 28], 2 + pinsrw xmm6, word ptr [rsi + rbx + 26], 6 + pinsrw xmm6, word ptr [rsi + rax + 26], 7 + pinsrw xmm7, word ptr [rsi + r9 + 28], 1 + pinsrw xmm7, word ptr [rsi + r8 + 28], 2 pinsrw xmm7, word ptr [rsi + r12 + 28], 3 - pinsrw xmm7, word ptr [rsi + r13 + 28], 4 + pinsrw xmm7, word ptr [rsi + rdx + 28], 4 pinsrw xmm7, word ptr [rsi + rcx + 28], 5 - pinsrw xmm7, word ptr [rsi + rdx + 28], 6 - pinsrw xmm7, word ptr [rsi + rbx + 28], 7 - pinsrw xmm2, word ptr [rsi + r8 + 30], 1 - pinsrw xmm2, word ptr [rsi + r9 + 30], 2 + pinsrw xmm7, word ptr [rsi + rbx + 28], 6 + pinsrw xmm7, word ptr [rsi + rax + 28], 7 + pinsrw xmm2, word ptr [rsi + r9 + 30], 1 + pinsrw xmm2, word ptr [rsi + r8 + 30], 2 pinsrw xmm2, word ptr [rsi + r12 + 30], 3 - pinsrw xmm2, word ptr [rsi + r13 + 30], 4 + pinsrw xmm2, word ptr [rsi + rdx + 30], 4 pinsrw xmm2, word ptr [rsi + rcx + 30], 5 - pinsrw xmm2, word ptr [rsi + rdx + 30], 6 - pinsrw xmm2, word ptr [rsi + rbx + 30], 7 + pinsrw xmm2, word ptr [rsi + rbx + 30], 6 + pinsrw xmm2, word ptr [rsi + rax + 30], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -8870,29 +6780,29 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 psllw xmm7, 6 pand xmm7, xmm13 por xmm7, xmm6 - movd xmm1, r11d - movzx r10d, word ptr [rsi + r15 + 44] + movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r13d, word ptr [rsi + r15 + 44] pcmpeqw xmm2, xmm0 packsswb xmm2, xmm2 psllw xmm2, 7 pand xmm2, xmm14 por xmm2, xmm7 - movd xmm6, dword ptr [rsp + 48] # 4-byte Folded Reload - # xmm6 = mem[0],zero,zero,zero - movzx r14d, word ptr [rsi + r15 + 46] - pinsrw xmm5, word ptr [rsi + r8 + 32], 1 - pinsrw xmm5, word ptr [rsi + r9 + 32], 2 + movd xmm6, r10d + movzx r10d, word ptr [rsi + r15 + 46] + pinsrw xmm5, word ptr [rsi + r9 + 32], 1 + pinsrw xmm5, word ptr [rsi + r8 + 32], 2 pinsrw xmm5, word ptr [rsi + r12 + 32], 3 - pinsrw xmm5, word ptr [rsi + r13 + 32], 4 + pinsrw xmm5, word ptr [rsi + rdx + 32], 4 pinsrw xmm5, word ptr [rsi + rcx + 32], 5 - pinsrw xmm5, word ptr [rsi + rdx + 32], 6 - pinsrw xmm1, word ptr [rsi + r8 + 34], 1 - pinsrw xmm1, word ptr [rsi + r9 + 34], 2 + pinsrw xmm5, word ptr [rsi + rbx + 32], 6 + pinsrw xmm1, word ptr [rsi + r9 + 34], 1 + pinsrw xmm1, word ptr [rsi + r8 + 34], 2 pinsrw xmm1, word ptr [rsi + r12 + 34], 3 - pinsrw xmm1, word ptr [rsi + r13 + 34], 4 + pinsrw xmm1, word ptr [rsi + rdx + 34], 4 pinsrw xmm1, word ptr [rsi + rcx + 34], 5 - pinsrw xmm1, word ptr [rsi + rdx + 34], 6 - pinsrw xmm1, word ptr [rsi + rbx + 34], 7 + pinsrw xmm1, word ptr [rsi + rbx + 34], 6 + pinsrw xmm1, word ptr [rsi + rax + 34], 7 por xmm2, xmm3 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 @@ -8901,46 +6811,44 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 psubb xmm7, xmm1 movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 48] - mov dword ptr [rsp + 16], eax # 4-byte Spill - pinsrw xmm5, word ptr [rsi + rbx + 32], 7 + movzx edi, word ptr [rsi + r15 + 48] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm5, word ptr [rsi + rax + 32], 7 pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 - pinsrw xmm6, word ptr [rsi + r8 + 36], 1 - pinsrw xmm6, word ptr [rsi + r9 + 36], 2 + pinsrw xmm6, word ptr [rsi + r9 + 36], 1 + pinsrw xmm6, word ptr [rsi + r8 + 36], 2 pinsrw xmm6, word ptr [rsi + r12 + 36], 3 - pinsrw xmm6, word ptr [rsi + r13 + 36], 4 + pinsrw xmm6, word ptr [rsi + rdx + 36], 4 pinsrw xmm6, word ptr [rsi + rcx + 36], 5 - pinsrw xmm6, word ptr [rsi + rdx + 36], 6 - pinsrw xmm6, word ptr [rsi + rbx + 36], 7 - pinsrw xmm3, word ptr [rsi + r8 + 38], 1 - pinsrw xmm3, word ptr [rsi + r9 + 38], 2 + pinsrw xmm6, word ptr [rsi + rbx + 36], 6 + pinsrw xmm6, word ptr [rsi + rax + 36], 7 + pinsrw xmm3, word ptr [rsi + r9 + 38], 1 + pinsrw xmm3, word ptr [rsi + r8 + 38], 2 pinsrw xmm3, word ptr [rsi + r12 + 38], 3 - pinsrw xmm3, word ptr [rsi + r13 + 38], 4 + pinsrw xmm3, word ptr [rsi + rdx + 38], 4 pinsrw xmm3, word ptr [rsi + rcx + 38], 5 - pinsrw xmm3, word ptr [rsi + rdx + 38], 6 - pinsrw xmm3, word ptr [rsi + rbx + 38], 7 + pinsrw xmm3, word ptr [rsi + rbx + 38], 6 + pinsrw xmm3, word ptr [rsi + rax + 38], 7 por xmm7, xmm5 - movd xmm5, edi - pinsrw xmm5, word ptr [rsi + r8 + 40], 1 - pinsrw xmm5, word ptr [rsi + r9 + 40], 2 + movd xmm5, r11d + pinsrw xmm5, word ptr [rsi + r9 + 40], 1 + pinsrw xmm5, word ptr [rsi + r8 + 40], 2 pinsrw xmm5, word ptr [rsi + r12 + 40], 3 - pinsrw xmm5, word ptr [rsi + r13 + 40], 4 + pinsrw xmm5, word ptr [rsi + rdx + 40], 4 pinsrw xmm5, word ptr [rsi + rcx + 40], 5 - pinsrw xmm5, word ptr [rsi + rdx + 40], 6 - movzx eax, word ptr [rsi + r15 + 50] + pinsrw xmm5, word ptr [rsi + rbx + 40], 6 + movzx edi, word ptr [rsi + r15 + 50] pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 psllw xmm6, 2 pand xmm6, xmm9 por xmm6, xmm7 - movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx edi, word ptr [rsi + r15 + 52] - mov dword ptr [rsp + 24], edi # 4-byte Spill - pinsrw xmm5, word ptr [rsi + rbx + 40], 7 + movd xmm1, r14d + movzx r11d, word ptr [rsi + r15 + 52] + pinsrw xmm5, word ptr [rsi + rax + 40], 7 pcmpeqw xmm3, xmm0 packsswb xmm3, xmm3 pand xmm3, xmm15 @@ -8952,25 +6860,25 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 psllw xmm5, 4 pand xmm5, xmm11 por xmm5, xmm3 - movd xmm7, r10d - movzx r11d, word ptr [rsi + r15 + 54] - pinsrw xmm1, word ptr [rsi + r8 + 42], 1 - pinsrw xmm1, word ptr [rsi + r9 + 42], 2 + movd xmm7, r13d + movzx r14d, word ptr [rsi + r15 + 54] + pinsrw xmm1, word ptr [rsi + r9 + 42], 1 + pinsrw xmm1, word ptr [rsi + r8 + 42], 2 pinsrw xmm1, word ptr [rsi + r12 + 42], 3 - pinsrw xmm1, word ptr [rsi + r13 + 42], 4 + pinsrw xmm1, word ptr [rsi + rdx + 42], 4 pinsrw xmm1, word ptr [rsi + rcx + 42], 5 - pinsrw xmm1, word ptr [rsi + rdx + 42], 6 - pinsrw xmm1, word ptr [rsi + rbx + 42], 7 - pinsrw xmm7, word ptr [rsi + r8 + 44], 1 - pinsrw xmm7, word ptr [rsi + r9 + 44], 2 + pinsrw xmm1, word ptr [rsi + rbx + 42], 6 + pinsrw xmm1, word ptr [rsi + rax + 42], 7 + pinsrw xmm7, word ptr [rsi + r9 + 44], 1 + pinsrw xmm7, word ptr [rsi + r8 + 44], 2 pinsrw xmm7, word ptr [rsi + r12 + 44], 3 - pinsrw xmm7, word ptr [rsi + r13 + 44], 4 + pinsrw xmm7, word ptr [rsi + rdx + 44], 4 pinsrw xmm7, word ptr [rsi + rcx + 44], 5 - pinsrw xmm7, word ptr [rsi + rdx + 44], 6 + pinsrw xmm7, word ptr [rsi + rbx + 44], 6 por xmm5, xmm6 - movd xmm3, r14d + movd xmm3, r10d movzx r10d, word ptr [rsi + r15 + 56] - pinsrw xmm7, word ptr [rsi + rbx + 44], 7 + pinsrw xmm7, word ptr [rsi + rax + 44], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 @@ -8984,57 +6892,55 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 por xmm7, xmm1 movd xmm6, dword ptr [rsp + 16] # 4-byte Folded Reload # xmm6 = mem[0],zero,zero,zero - movzx r14d, word ptr [rsi + r15 + 58] - pinsrw xmm3, word ptr [rsi + r8 + 46], 1 - pinsrw xmm3, word ptr [rsi + r9 + 46], 2 + movzx r13d, word ptr [rsi + r15 + 58] + pinsrw xmm3, word ptr [rsi + r9 + 46], 1 + pinsrw xmm3, word ptr [rsi + r8 + 46], 2 pinsrw xmm3, word ptr [rsi + r12 + 46], 3 - pinsrw xmm3, word ptr [rsi + r13 + 46], 4 + pinsrw xmm3, word ptr [rsi + rdx + 46], 4 pinsrw xmm3, word ptr [rsi + rcx + 46], 5 - pinsrw xmm3, word ptr [rsi + rdx + 46], 6 - pinsrw xmm3, word ptr [rsi + rbx + 46], 7 + pinsrw xmm3, word ptr [rsi + rbx + 46], 6 + pinsrw xmm3, word ptr [rsi + rax + 46], 7 pcmpeqw xmm3, xmm0 packsswb xmm3, xmm3 psllw xmm3, 7 pand xmm3, xmm14 por xmm3, xmm7 - movd xmm1, eax + movd xmm1, edi movzx edi, word ptr [rsi + r15 + 60] movzx r15d, word ptr [rsi + r15 + 62] - pinsrw xmm1, word ptr [rsi + r8 + 50], 1 - pinsrw xmm1, word ptr [rsi + r9 + 50], 2 + pinsrw xmm1, word ptr [rsi + r9 + 50], 1 + pinsrw xmm1, word ptr [rsi + r8 + 50], 2 pinsrw xmm1, word ptr [rsi + r12 + 50], 3 - pinsrw xmm1, word ptr [rsi + r13 + 50], 4 + pinsrw xmm1, word ptr [rsi + rdx + 50], 4 pinsrw xmm1, word ptr [rsi + rcx + 50], 5 - pinsrw xmm1, word ptr [rsi + rdx + 50], 6 - pinsrw xmm1, word ptr [rsi + rbx + 50], 7 + pinsrw xmm1, word ptr [rsi + rbx + 50], 6 + pinsrw xmm1, word ptr [rsi + rax + 50], 7 por xmm3, xmm5 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 movdqa xmm5, xmm1 pand xmm5, xmm15 psubb xmm5, xmm1 - movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - mov rax, qword ptr [rsp + 136] # 8-byte Reload - pinsrw xmm6, word ptr [rsi + r8 + 48], 1 - pinsrw xmm6, word ptr [rsi + r9 + 48], 2 + movd xmm1, r11d + pinsrw xmm6, word ptr [rsi + r9 + 48], 1 + pinsrw xmm6, word ptr [rsi + r8 + 48], 2 pinsrw xmm6, word ptr [rsi + r12 + 48], 3 - pinsrw xmm6, word ptr [rsi + r13 + 48], 4 + pinsrw xmm6, word ptr [rsi + rdx + 48], 4 pinsrw xmm6, word ptr [rsi + rcx + 48], 5 - pinsrw xmm6, word ptr [rsi + rdx + 48], 6 - pinsrw xmm6, word ptr [rsi + rbx + 48], 7 + pinsrw xmm6, word ptr [rsi + rbx + 48], 6 + pinsrw xmm6, word ptr [rsi + rax + 48], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 - pinsrw xmm1, word ptr [rsi + r8 + 52], 1 - pinsrw xmm1, word ptr [rsi + r9 + 52], 2 + pinsrw xmm1, word ptr [rsi + r9 + 52], 1 + pinsrw xmm1, word ptr [rsi + r8 + 52], 2 pinsrw xmm1, word ptr [rsi + r12 + 52], 3 - pinsrw xmm1, word ptr [rsi + r13 + 52], 4 + pinsrw xmm1, word ptr [rsi + rdx + 52], 4 pinsrw xmm1, word ptr [rsi + rcx + 52], 5 pand xmm6, xmm15 - pinsrw xmm1, word ptr [rsi + rdx + 52], 6 + pinsrw xmm1, word ptr [rsi + rbx + 52], 6 por xmm5, xmm6 - movd xmm6, r11d - pinsrw xmm1, word ptr [rsi + rbx + 52], 7 + movd xmm6, r14d + pinsrw xmm1, word ptr [rsi + rax + 52], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 @@ -9042,20 +6948,20 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 pand xmm1, xmm9 por xmm1, xmm5 movd xmm5, r10d - pinsrw xmm6, word ptr [rsi + r8 + 54], 1 - pinsrw xmm6, word ptr [rsi + r9 + 54], 2 + pinsrw xmm6, word ptr [rsi + r9 + 54], 1 + pinsrw xmm6, word ptr [rsi + r8 + 54], 2 pinsrw xmm6, word ptr [rsi + r12 + 54], 3 - pinsrw xmm6, word ptr [rsi + r13 + 54], 4 + pinsrw xmm6, word ptr [rsi + rdx + 54], 4 pinsrw xmm6, word ptr [rsi + rcx + 54], 5 - pinsrw xmm6, word ptr [rsi + rdx + 54], 6 - pinsrw xmm6, word ptr [rsi + rbx + 54], 7 - pinsrw xmm5, word ptr [rsi + r8 + 56], 1 - pinsrw xmm5, word ptr [rsi + r9 + 56], 2 + pinsrw xmm6, word ptr [rsi + rbx + 54], 6 + pinsrw xmm6, word ptr [rsi + rax + 54], 7 + pinsrw xmm5, word ptr [rsi + r9 + 56], 1 + pinsrw xmm5, word ptr [rsi + r8 + 56], 2 pinsrw xmm5, word ptr [rsi + r12 + 56], 3 - pinsrw xmm5, word ptr [rsi + r13 + 56], 4 + pinsrw xmm5, word ptr [rsi + rdx + 56], 4 pinsrw xmm5, word ptr [rsi + rcx + 56], 5 - pinsrw xmm5, word ptr [rsi + rdx + 56], 6 - pinsrw xmm5, word ptr [rsi + rbx + 56], 7 + pinsrw xmm5, word ptr [rsi + rbx + 56], 6 + pinsrw xmm5, word ptr [rsi + rax + 56], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -9067,23 +6973,23 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 psllw xmm5, 4 pand xmm5, xmm11 por xmm5, xmm6 - movd xmm6, r14d - pinsrw xmm6, word ptr [rsi + r8 + 58], 1 - pinsrw xmm6, word ptr [rsi + r9 + 58], 2 + movd xmm6, r13d + pinsrw xmm6, word ptr [rsi + r9 + 58], 1 + pinsrw xmm6, word ptr [rsi + r8 + 58], 2 pinsrw xmm6, word ptr [rsi + r12 + 58], 3 - pinsrw xmm6, word ptr [rsi + r13 + 58], 4 + pinsrw xmm6, word ptr [rsi + rdx + 58], 4 pinsrw xmm6, word ptr [rsi + rcx + 58], 5 - pinsrw xmm6, word ptr [rsi + rdx + 58], 6 - pinsrw xmm6, word ptr [rsi + rbx + 58], 7 + pinsrw xmm6, word ptr [rsi + rbx + 58], 6 + pinsrw xmm6, word ptr [rsi + rax + 58], 7 por xmm5, xmm1 movd xmm1, edi - pinsrw xmm1, word ptr [rsi + r8 + 60], 1 - pinsrw xmm1, word ptr [rsi + r9 + 60], 2 + pinsrw xmm1, word ptr [rsi + r9 + 60], 1 + pinsrw xmm1, word ptr [rsi + r8 + 60], 2 pinsrw xmm1, word ptr [rsi + r12 + 60], 3 - pinsrw xmm1, word ptr [rsi + r13 + 60], 4 + pinsrw xmm1, word ptr [rsi + rdx + 60], 4 pinsrw xmm1, word ptr [rsi + rcx + 60], 5 - pinsrw xmm1, word ptr [rsi + rdx + 60], 6 - pinsrw xmm1, word ptr [rsi + rbx + 60], 7 + pinsrw xmm1, word ptr [rsi + rbx + 60], 6 + pinsrw xmm1, word ptr [rsi + rax + 60], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -9096,13 +7002,14 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 pand xmm1, xmm13 por xmm1, xmm6 movd xmm6, r15d - pinsrw xmm6, word ptr [rsi + r8 + 62], 1 - pinsrw xmm6, word ptr [rsi + r9 + 62], 2 + pinsrw xmm6, word ptr [rsi + r9 + 62], 1 + pinsrw xmm6, word ptr [rsi + r8 + 62], 2 pinsrw xmm6, word ptr [rsi + r12 + 62], 3 - pinsrw xmm6, word ptr [rsi + r13 + 62], 4 + mov rdi, qword ptr [rsp + 120] # 8-byte Reload + pinsrw xmm6, word ptr [rsi + rdx + 62], 4 pinsrw xmm6, word ptr [rsi + rcx + 62], 5 - pinsrw xmm6, word ptr [rsi + rdx + 62], 6 - pinsrw xmm6, word ptr [rsi + rbx + 62], 7 + pinsrw xmm6, word ptr [rsi + rbx + 62], 6 + pinsrw xmm6, word ptr [rsi + rax + 62], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 psllw xmm6, 7 @@ -9120,32 +7027,575 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] punpcklbw xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7] punpcklwd xmm4, xmm3 # xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3] - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx], xmm4 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm1 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + movdqu xmmword ptr [rdi + 4*rcx], xmm4 + movdqu xmmword ptr [rdi + 4*rcx + 16], xmm1 add rcx, 8 mov r15, rcx cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB1_135 -# %bb.136: - mov r15, qword ptr [rsp + 240] # 8-byte Reload - cmp r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11d, dword ptr [rsp + 4] # 4-byte Reload - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - jne .LBB1_137 - jmp .LBB1_140 -.LBB1_182: - mov r8, r11 - and r8, -4 - mov rbx, r8 + jne .LBB1_127 +# %bb.128: + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r13d, dword ptr [rsp + 56] # 4-byte Reload + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + jne .LBB1_129 + jmp .LBB1_132 +.LBB1_151: + and rcx, -8 + mov rax, rcx + shl rax, 6 + add rax, rsi + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 32], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 8], rax # 8-byte Spill + mov dword ptr [rsp + 56], r13d # 4-byte Spill + movd xmm0, r13d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] + xor r15d, r15d + movdqa xmm15, xmmword ptr [rip + .LCPI1_8] # xmm15 = <1,1,1,1,1,1,1,1,u,u,u,u,u,u,u,u> + movdqa xmm9, xmmword ptr [rip + .LCPI1_1] # xmm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + movdqa xmm10, xmmword ptr [rip + .LCPI1_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + movdqa xmm11, xmmword ptr [rip + .LCPI1_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + movdqa xmm12, xmmword ptr [rip + .LCPI1_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + movdqa xmm13, xmmword ptr [rip + .LCPI1_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] + movdqa xmm14, xmmword ptr [rip + .LCPI1_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + mov qword ptr [rsp + 120], r12 # 8-byte Spill + .p2align 4, 0x90 +.LBB1_152: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill + shl r15, 6 + mov r8, r15 + mov r12, r15 + mov rdx, r15 + mov rcx, r15 + mov rbx, r15 + mov rax, r15 + movzx r14d, word ptr [rsi + r15] + movzx edi, word ptr [rsi + r15 + 2] + movzx r11d, word ptr [rsi + r15 + 4] + movzx r13d, word ptr [rsi + r15 + 6] + movzx r10d, word ptr [rsi + r15 + 8] + mov r9, r15 + or r9, 64 + or r8, 128 + or r12, 192 + or rdx, 256 + or rcx, 320 + or rbx, 384 + or rax, 448 + movd xmm4, r14d + pinsrw xmm4, word ptr [rsi + r9], 1 + pinsrw xmm4, word ptr [rsi + r8], 2 + pinsrw xmm4, word ptr [rsi + r12], 3 + pinsrw xmm4, word ptr [rsi + rdx], 4 + pinsrw xmm4, word ptr [rsi + rcx], 5 + pinsrw xmm4, word ptr [rsi + rbx], 6 + pinsrw xmm4, word ptr [rsi + rax], 7 + movzx r14d, word ptr [rsi + r15 + 10] + movd xmm6, edi + pinsrw xmm6, word ptr [rsi + r9 + 2], 1 + pinsrw xmm6, word ptr [rsi + r8 + 2], 2 + pinsrw xmm6, word ptr [rsi + r12 + 2], 3 + movzx edi, word ptr [rsi + r15 + 12] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm6, word ptr [rsi + rdx + 2], 4 + movd xmm2, r11d + movzx r11d, word ptr [rsi + r15 + 14] + pinsrw xmm6, word ptr [rsi + rcx + 2], 5 + movd xmm5, r13d + movzx edi, word ptr [rsi + r15 + 16] + mov dword ptr [rsp + 40], edi # 4-byte Spill + pinsrw xmm6, word ptr [rsi + rbx + 2], 6 + movd xmm3, r10d + movzx edi, word ptr [rsi + r15 + 18] + mov dword ptr [rsp + 48], edi # 4-byte Spill + pinsrw xmm6, word ptr [rsi + rax + 2], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + movdqa xmm1, xmm6 + pand xmm1, xmm15 + psubb xmm1, xmm6 + movd xmm6, r14d + movzx r13d, word ptr [rsi + r15 + 20] + pcmpeqw xmm4, xmm0 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + pinsrw xmm2, word ptr [rsi + r9 + 4], 1 + pinsrw xmm2, word ptr [rsi + r8 + 4], 2 + pinsrw xmm2, word ptr [rsi + r12 + 4], 3 + pinsrw xmm2, word ptr [rsi + rdx + 4], 4 + pinsrw xmm2, word ptr [rsi + rcx + 4], 5 + pinsrw xmm2, word ptr [rsi + rbx + 4], 6 + pinsrw xmm2, word ptr [rsi + rax + 4], 7 + pinsrw xmm5, word ptr [rsi + r9 + 6], 1 + pinsrw xmm5, word ptr [rsi + r8 + 6], 2 + pinsrw xmm5, word ptr [rsi + r12 + 6], 3 + pinsrw xmm5, word ptr [rsi + rdx + 6], 4 + pinsrw xmm5, word ptr [rsi + rcx + 6], 5 + pinsrw xmm5, word ptr [rsi + rbx + 6], 6 + pinsrw xmm5, word ptr [rsi + rax + 6], 7 + pinsrw xmm3, word ptr [rsi + r9 + 8], 1 + pinsrw xmm3, word ptr [rsi + r8 + 8], 2 + pinsrw xmm3, word ptr [rsi + r12 + 8], 3 + pinsrw xmm3, word ptr [rsi + rdx + 8], 4 + pinsrw xmm3, word ptr [rsi + rcx + 8], 5 + pinsrw xmm3, word ptr [rsi + rbx + 8], 6 + pinsrw xmm3, word ptr [rsi + rax + 8], 7 + por xmm1, xmm4 + movd xmm7, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r14d, word ptr [rsi + r15 + 22] + pcmpeqw xmm2, xmm0 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 2 + pand xmm2, xmm9 + por xmm2, xmm1 + movd xmm4, r11d + movzx edi, word ptr [rsi + r15 + 24] + pcmpeqw xmm5, xmm0 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 3 + pand xmm5, xmm10 + pcmpeqw xmm3, xmm0 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 4 + pand xmm3, xmm11 + por xmm3, xmm5 + movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r10d, word ptr [rsi + r15 + 26] + pinsrw xmm6, word ptr [rsi + r9 + 10], 1 + pinsrw xmm6, word ptr [rsi + r8 + 10], 2 + pinsrw xmm6, word ptr [rsi + r12 + 10], 3 + pinsrw xmm6, word ptr [rsi + rdx + 10], 4 + pinsrw xmm6, word ptr [rsi + rcx + 10], 5 + pinsrw xmm6, word ptr [rsi + rbx + 10], 6 + pinsrw xmm6, word ptr [rsi + rax + 10], 7 + pinsrw xmm7, word ptr [rsi + r9 + 12], 1 + pinsrw xmm7, word ptr [rsi + r8 + 12], 2 + pinsrw xmm7, word ptr [rsi + r12 + 12], 3 + pinsrw xmm7, word ptr [rsi + rdx + 12], 4 + pinsrw xmm7, word ptr [rsi + rcx + 12], 5 + pinsrw xmm7, word ptr [rsi + rbx + 12], 6 + pinsrw xmm7, word ptr [rsi + rax + 12], 7 + por xmm3, xmm2 + movd xmm8, dword ptr [rsp + 48] # 4-byte Folded Reload + # xmm8 = mem[0],zero,zero,zero + movzx r11d, word ptr [rsi + r15 + 28] + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + pcmpeqw xmm7, xmm0 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 6 + pand xmm7, xmm13 + por xmm7, xmm6 + movd xmm5, r13d + movzx r13d, word ptr [rsi + r15 + 30] + pinsrw xmm4, word ptr [rsi + r9 + 14], 1 + pinsrw xmm4, word ptr [rsi + r8 + 14], 2 + pinsrw xmm4, word ptr [rsi + r12 + 14], 3 + pinsrw xmm4, word ptr [rsi + rdx + 14], 4 + pinsrw xmm4, word ptr [rsi + rcx + 14], 5 + pinsrw xmm4, word ptr [rsi + rbx + 14], 6 + pinsrw xmm4, word ptr [rsi + rax + 14], 7 + pinsrw xmm8, word ptr [rsi + r9 + 18], 1 + pinsrw xmm8, word ptr [rsi + r8 + 18], 2 + pinsrw xmm8, word ptr [rsi + r12 + 18], 3 + pinsrw xmm8, word ptr [rsi + rdx + 18], 4 + pinsrw xmm8, word ptr [rsi + rcx + 18], 5 + pinsrw xmm8, word ptr [rsi + rbx + 18], 6 + pinsrw xmm8, word ptr [rsi + rax + 18], 7 + pcmpeqw xmm4, xmm0 + packsswb xmm4, xmm4 + psllw xmm4, 7 + pand xmm4, xmm14 + por xmm4, xmm7 + movd xmm2, r14d + movzx r14d, word ptr [rsi + r15 + 32] + por xmm4, xmm3 + pcmpeqw xmm8, xmm0 + packsswb xmm8, xmm8 + movdqa xmm7, xmm8 + pand xmm7, xmm15 + psubb xmm7, xmm8 + movd xmm3, edi + movzx edi, word ptr [rsi + r15 + 34] + mov dword ptr [rsp + 40], edi # 4-byte Spill + pinsrw xmm1, word ptr [rsi + r9 + 16], 1 + pinsrw xmm1, word ptr [rsi + r8 + 16], 2 + pinsrw xmm1, word ptr [rsi + r12 + 16], 3 + pinsrw xmm1, word ptr [rsi + rdx + 16], 4 + pinsrw xmm1, word ptr [rsi + rcx + 16], 5 + pinsrw xmm1, word ptr [rsi + rbx + 16], 6 + pinsrw xmm1, word ptr [rsi + rax + 16], 7 + pcmpeqw xmm1, xmm0 + packsswb xmm1, xmm1 + pand xmm1, xmm15 + por xmm7, xmm1 + movd xmm6, r10d + movzx r10d, word ptr [rsi + r15 + 36] + pinsrw xmm5, word ptr [rsi + r9 + 20], 1 + pinsrw xmm5, word ptr [rsi + r8 + 20], 2 + pinsrw xmm5, word ptr [rsi + r12 + 20], 3 + pinsrw xmm5, word ptr [rsi + rdx + 20], 4 + pinsrw xmm5, word ptr [rsi + rcx + 20], 5 + pinsrw xmm5, word ptr [rsi + rbx + 20], 6 + pinsrw xmm5, word ptr [rsi + rax + 20], 7 + pcmpeqw xmm5, xmm0 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 2 + pand xmm5, xmm9 + por xmm5, xmm7 + movd xmm7, r11d + movzx edi, word ptr [rsi + r15 + 38] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm2, word ptr [rsi + r9 + 22], 1 + pinsrw xmm2, word ptr [rsi + r8 + 22], 2 + pinsrw xmm2, word ptr [rsi + r12 + 22], 3 + pinsrw xmm2, word ptr [rsi + rdx + 22], 4 + pinsrw xmm2, word ptr [rsi + rcx + 22], 5 + pinsrw xmm2, word ptr [rsi + rbx + 22], 6 + pinsrw xmm2, word ptr [rsi + rax + 22], 7 + pinsrw xmm3, word ptr [rsi + r9 + 24], 1 + pinsrw xmm3, word ptr [rsi + r8 + 24], 2 + pinsrw xmm3, word ptr [rsi + r12 + 24], 3 + pinsrw xmm3, word ptr [rsi + rdx + 24], 4 + pinsrw xmm3, word ptr [rsi + rcx + 24], 5 + pinsrw xmm3, word ptr [rsi + rbx + 24], 6 + pinsrw xmm3, word ptr [rsi + rax + 24], 7 + pcmpeqw xmm2, xmm0 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 3 + pand xmm2, xmm10 + pcmpeqw xmm3, xmm0 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 4 + pand xmm3, xmm11 + por xmm3, xmm2 + movd xmm2, r13d + movzx r11d, word ptr [rsi + r15 + 40] + por xmm3, xmm5 + movd xmm5, r14d + movzx r14d, word ptr [rsi + r15 + 42] + pinsrw xmm6, word ptr [rsi + r9 + 26], 1 + pinsrw xmm6, word ptr [rsi + r8 + 26], 2 + pinsrw xmm6, word ptr [rsi + r12 + 26], 3 + pinsrw xmm6, word ptr [rsi + rdx + 26], 4 + pinsrw xmm6, word ptr [rsi + rcx + 26], 5 + pinsrw xmm6, word ptr [rsi + rbx + 26], 6 + pinsrw xmm6, word ptr [rsi + rax + 26], 7 + pinsrw xmm7, word ptr [rsi + r9 + 28], 1 + pinsrw xmm7, word ptr [rsi + r8 + 28], 2 + pinsrw xmm7, word ptr [rsi + r12 + 28], 3 + pinsrw xmm7, word ptr [rsi + rdx + 28], 4 + pinsrw xmm7, word ptr [rsi + rcx + 28], 5 + pinsrw xmm7, word ptr [rsi + rbx + 28], 6 + pinsrw xmm7, word ptr [rsi + rax + 28], 7 + pinsrw xmm2, word ptr [rsi + r9 + 30], 1 + pinsrw xmm2, word ptr [rsi + r8 + 30], 2 + pinsrw xmm2, word ptr [rsi + r12 + 30], 3 + pinsrw xmm2, word ptr [rsi + rdx + 30], 4 + pinsrw xmm2, word ptr [rsi + rcx + 30], 5 + pinsrw xmm2, word ptr [rsi + rbx + 30], 6 + pinsrw xmm2, word ptr [rsi + rax + 30], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + pcmpeqw xmm7, xmm0 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 6 + pand xmm7, xmm13 + por xmm7, xmm6 + movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r13d, word ptr [rsi + r15 + 44] + pcmpeqw xmm2, xmm0 + packsswb xmm2, xmm2 + psllw xmm2, 7 + pand xmm2, xmm14 + por xmm2, xmm7 + movd xmm6, r10d + movzx r10d, word ptr [rsi + r15 + 46] + pinsrw xmm5, word ptr [rsi + r9 + 32], 1 + pinsrw xmm5, word ptr [rsi + r8 + 32], 2 + pinsrw xmm5, word ptr [rsi + r12 + 32], 3 + pinsrw xmm5, word ptr [rsi + rdx + 32], 4 + pinsrw xmm5, word ptr [rsi + rcx + 32], 5 + pinsrw xmm5, word ptr [rsi + rbx + 32], 6 + pinsrw xmm1, word ptr [rsi + r9 + 34], 1 + pinsrw xmm1, word ptr [rsi + r8 + 34], 2 + pinsrw xmm1, word ptr [rsi + r12 + 34], 3 + pinsrw xmm1, word ptr [rsi + rdx + 34], 4 + pinsrw xmm1, word ptr [rsi + rcx + 34], 5 + pinsrw xmm1, word ptr [rsi + rbx + 34], 6 + pinsrw xmm1, word ptr [rsi + rax + 34], 7 + por xmm2, xmm3 + pcmpeqw xmm1, xmm0 + packsswb xmm1, xmm1 + movdqa xmm7, xmm1 + pand xmm7, xmm15 + psubb xmm7, xmm1 + movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx edi, word ptr [rsi + r15 + 48] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm5, word ptr [rsi + rax + 32], 7 + pcmpeqw xmm5, xmm0 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + pinsrw xmm6, word ptr [rsi + r9 + 36], 1 + pinsrw xmm6, word ptr [rsi + r8 + 36], 2 + pinsrw xmm6, word ptr [rsi + r12 + 36], 3 + pinsrw xmm6, word ptr [rsi + rdx + 36], 4 + pinsrw xmm6, word ptr [rsi + rcx + 36], 5 + pinsrw xmm6, word ptr [rsi + rbx + 36], 6 + pinsrw xmm6, word ptr [rsi + rax + 36], 7 + pinsrw xmm3, word ptr [rsi + r9 + 38], 1 + pinsrw xmm3, word ptr [rsi + r8 + 38], 2 + pinsrw xmm3, word ptr [rsi + r12 + 38], 3 + pinsrw xmm3, word ptr [rsi + rdx + 38], 4 + pinsrw xmm3, word ptr [rsi + rcx + 38], 5 + pinsrw xmm3, word ptr [rsi + rbx + 38], 6 + pinsrw xmm3, word ptr [rsi + rax + 38], 7 + por xmm7, xmm5 + movd xmm5, r11d + pinsrw xmm5, word ptr [rsi + r9 + 40], 1 + pinsrw xmm5, word ptr [rsi + r8 + 40], 2 + pinsrw xmm5, word ptr [rsi + r12 + 40], 3 + pinsrw xmm5, word ptr [rsi + rdx + 40], 4 + pinsrw xmm5, word ptr [rsi + rcx + 40], 5 + pinsrw xmm5, word ptr [rsi + rbx + 40], 6 + movzx edi, word ptr [rsi + r15 + 50] + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 2 + pand xmm6, xmm9 + por xmm6, xmm7 + movd xmm1, r14d + movzx r11d, word ptr [rsi + r15 + 52] + pinsrw xmm5, word ptr [rsi + rax + 40], 7 + pcmpeqw xmm3, xmm0 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 3 + pand xmm3, xmm10 + pcmpeqw xmm5, xmm0 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 4 + pand xmm5, xmm11 + por xmm5, xmm3 + movd xmm7, r13d + movzx r14d, word ptr [rsi + r15 + 54] + pinsrw xmm1, word ptr [rsi + r9 + 42], 1 + pinsrw xmm1, word ptr [rsi + r8 + 42], 2 + pinsrw xmm1, word ptr [rsi + r12 + 42], 3 + pinsrw xmm1, word ptr [rsi + rdx + 42], 4 + pinsrw xmm1, word ptr [rsi + rcx + 42], 5 + pinsrw xmm1, word ptr [rsi + rbx + 42], 6 + pinsrw xmm1, word ptr [rsi + rax + 42], 7 + pinsrw xmm7, word ptr [rsi + r9 + 44], 1 + pinsrw xmm7, word ptr [rsi + r8 + 44], 2 + pinsrw xmm7, word ptr [rsi + r12 + 44], 3 + pinsrw xmm7, word ptr [rsi + rdx + 44], 4 + pinsrw xmm7, word ptr [rsi + rcx + 44], 5 + pinsrw xmm7, word ptr [rsi + rbx + 44], 6 + por xmm5, xmm6 + movd xmm3, r10d + movzx r10d, word ptr [rsi + r15 + 56] + pinsrw xmm7, word ptr [rsi + rax + 44], 7 + pcmpeqw xmm1, xmm0 + packsswb xmm1, xmm1 + pand xmm1, xmm15 + psllw xmm1, 5 + pand xmm1, xmm12 + pcmpeqw xmm7, xmm0 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 6 + pand xmm7, xmm13 + por xmm7, xmm1 + movd xmm6, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm6 = mem[0],zero,zero,zero + movzx r13d, word ptr [rsi + r15 + 58] + pinsrw xmm3, word ptr [rsi + r9 + 46], 1 + pinsrw xmm3, word ptr [rsi + r8 + 46], 2 + pinsrw xmm3, word ptr [rsi + r12 + 46], 3 + pinsrw xmm3, word ptr [rsi + rdx + 46], 4 + pinsrw xmm3, word ptr [rsi + rcx + 46], 5 + pinsrw xmm3, word ptr [rsi + rbx + 46], 6 + pinsrw xmm3, word ptr [rsi + rax + 46], 7 + pcmpeqw xmm3, xmm0 + packsswb xmm3, xmm3 + psllw xmm3, 7 + pand xmm3, xmm14 + por xmm3, xmm7 + movd xmm1, edi + movzx edi, word ptr [rsi + r15 + 60] + movzx r15d, word ptr [rsi + r15 + 62] + pinsrw xmm1, word ptr [rsi + r9 + 50], 1 + pinsrw xmm1, word ptr [rsi + r8 + 50], 2 + pinsrw xmm1, word ptr [rsi + r12 + 50], 3 + pinsrw xmm1, word ptr [rsi + rdx + 50], 4 + pinsrw xmm1, word ptr [rsi + rcx + 50], 5 + pinsrw xmm1, word ptr [rsi + rbx + 50], 6 + pinsrw xmm1, word ptr [rsi + rax + 50], 7 + por xmm3, xmm5 + pcmpeqw xmm1, xmm0 + packsswb xmm1, xmm1 + movdqa xmm5, xmm1 + pand xmm5, xmm15 + psubb xmm5, xmm1 + movd xmm1, r11d + pinsrw xmm6, word ptr [rsi + r9 + 48], 1 + pinsrw xmm6, word ptr [rsi + r8 + 48], 2 + pinsrw xmm6, word ptr [rsi + r12 + 48], 3 + pinsrw xmm6, word ptr [rsi + rdx + 48], 4 + pinsrw xmm6, word ptr [rsi + rcx + 48], 5 + pinsrw xmm6, word ptr [rsi + rbx + 48], 6 + pinsrw xmm6, word ptr [rsi + rax + 48], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + pinsrw xmm1, word ptr [rsi + r9 + 52], 1 + pinsrw xmm1, word ptr [rsi + r8 + 52], 2 + pinsrw xmm1, word ptr [rsi + r12 + 52], 3 + pinsrw xmm1, word ptr [rsi + rdx + 52], 4 + pinsrw xmm1, word ptr [rsi + rcx + 52], 5 + pand xmm6, xmm15 + pinsrw xmm1, word ptr [rsi + rbx + 52], 6 + por xmm5, xmm6 + movd xmm6, r14d + pinsrw xmm1, word ptr [rsi + rax + 52], 7 + pcmpeqw xmm1, xmm0 + packsswb xmm1, xmm1 + pand xmm1, xmm15 + psllw xmm1, 2 + pand xmm1, xmm9 + por xmm1, xmm5 + movd xmm5, r10d + pinsrw xmm6, word ptr [rsi + r9 + 54], 1 + pinsrw xmm6, word ptr [rsi + r8 + 54], 2 + pinsrw xmm6, word ptr [rsi + r12 + 54], 3 + pinsrw xmm6, word ptr [rsi + rdx + 54], 4 + pinsrw xmm6, word ptr [rsi + rcx + 54], 5 + pinsrw xmm6, word ptr [rsi + rbx + 54], 6 + pinsrw xmm6, word ptr [rsi + rax + 54], 7 + pinsrw xmm5, word ptr [rsi + r9 + 56], 1 + pinsrw xmm5, word ptr [rsi + r8 + 56], 2 + pinsrw xmm5, word ptr [rsi + r12 + 56], 3 + pinsrw xmm5, word ptr [rsi + rdx + 56], 4 + pinsrw xmm5, word ptr [rsi + rcx + 56], 5 + pinsrw xmm5, word ptr [rsi + rbx + 56], 6 + pinsrw xmm5, word ptr [rsi + rax + 56], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 3 + pand xmm6, xmm10 + pcmpeqw xmm5, xmm0 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 4 + pand xmm5, xmm11 + por xmm5, xmm6 + movd xmm6, r13d + pinsrw xmm6, word ptr [rsi + r9 + 58], 1 + pinsrw xmm6, word ptr [rsi + r8 + 58], 2 + pinsrw xmm6, word ptr [rsi + r12 + 58], 3 + pinsrw xmm6, word ptr [rsi + rdx + 58], 4 + pinsrw xmm6, word ptr [rsi + rcx + 58], 5 + pinsrw xmm6, word ptr [rsi + rbx + 58], 6 + pinsrw xmm6, word ptr [rsi + rax + 58], 7 + por xmm5, xmm1 + movd xmm1, edi + pinsrw xmm1, word ptr [rsi + r9 + 60], 1 + pinsrw xmm1, word ptr [rsi + r8 + 60], 2 + pinsrw xmm1, word ptr [rsi + r12 + 60], 3 + pinsrw xmm1, word ptr [rsi + rdx + 60], 4 + pinsrw xmm1, word ptr [rsi + rcx + 60], 5 + pinsrw xmm1, word ptr [rsi + rbx + 60], 6 + pinsrw xmm1, word ptr [rsi + rax + 60], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + pcmpeqw xmm1, xmm0 + packsswb xmm1, xmm1 + pand xmm1, xmm15 + psllw xmm1, 6 + pand xmm1, xmm13 + por xmm1, xmm6 + movd xmm6, r15d + pinsrw xmm6, word ptr [rsi + r9 + 62], 1 + pinsrw xmm6, word ptr [rsi + r8 + 62], 2 + pinsrw xmm6, word ptr [rsi + r12 + 62], 3 + mov rdi, qword ptr [rsp + 120] # 8-byte Reload + pinsrw xmm6, word ptr [rsi + rdx + 62], 4 + pinsrw xmm6, word ptr [rsi + rcx + 62], 5 + pinsrw xmm6, word ptr [rsi + rbx + 62], 6 + pinsrw xmm6, word ptr [rsi + rax + 62], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + psllw xmm6, 7 + pand xmm6, xmm14 + por xmm6, xmm1 + por xmm6, xmm5 + movdqa xmm1, xmm4 + punpcklqdq xmm1, xmm2 # xmm1 = xmm1[0],xmm2[0] + movdqa xmm5, xmm3 + punpcklqdq xmm5, xmm6 # xmm5 = xmm5[0],xmm6[0] + movdqa xmm7, xmmword ptr [rip + .LCPI1_9] # xmm7 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> + pshufb xmm5, xmm7 + pshufb xmm1, xmm7 + punpcklwd xmm1, xmm5 # xmm1 = xmm1[0],xmm5[0],xmm1[1],xmm5[1],xmm1[2],xmm5[2],xmm1[3],xmm5[3] + punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] + punpcklbw xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7] + punpcklwd xmm4, xmm3 # xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3] + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + movdqu xmmword ptr [rdi + 4*rcx], xmm4 + movdqu xmmword ptr [rdi + 4*rcx + 16], xmm1 + add rcx, 8 + mov r15, rcx + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + jne .LBB1_152 +# %bb.153: + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r13d, dword ptr [rsp + 56] # 4-byte Reload + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + jne .LBB1_154 + jmp .LBB1_157 +.LBB1_205: + mov rax, rcx + and rax, -4 + mov rbx, rax shl rbx, 7 add rbx, rsi - lea r15, [r14 + 4*r8] - movaps xmm1, xmm0 + lea r13, [r12 + 4*rax] + movdqa xmm1, xmm0 shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] add rsi, 508 - xor ecx, ecx + xor edx, edx movdqa xmm15, xmmword ptr [rip + .LCPI1_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> movdqa xmm8, xmmword ptr [rip + .LCPI1_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] movdqa xmm10, xmmword ptr [rip + .LCPI1_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] @@ -9155,7 +7605,7 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 movdqa xmm14, xmmword ptr [rip + .LCPI1_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] movdqa xmm9, xmmword ptr [rip + .LCPI1_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] .p2align 4, 0x90 -.LBB1_183: # =>This Inner Loop Header: Depth=1 +.LBB1_206: # =>This Inner Loop Header: Depth=1 movss xmm6, dword ptr [rsi - 508] # xmm6 = mem[0],zero,zero,zero movss xmm7, dword ptr [rsi - 504] # xmm7 = mem[0],zero,zero,zero movss xmm5, dword ptr [rsi - 500] # xmm5 = mem[0],zero,zero,zero @@ -9496,1162 +7946,2159 @@ comparison_equal_arr_scalar_sse4: # @comparison_equal_arr_scalar_sse4 punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] pshufb xmm4, xmm9 - movdqu xmmword ptr [r14 + 4*rcx], xmm4 - add rcx, 4 + movdqu xmmword ptr [r12 + 4*rdx], xmm4 + add rdx, 4 add rsi, 512 - cmp r8, rcx - jne .LBB1_183 -# %bb.184: - cmp r11, r8 - jne .LBB1_185 - jmp .LBB1_188 -.Lfunc_end1: - .size comparison_equal_arr_scalar_sse4, .Lfunc_end1-comparison_equal_arr_scalar_sse4 - # -- End function - .section .rodata.cst16,"aM",@progbits,16 - .p2align 4 # -- Begin function comparison_equal_scalar_arr_sse4 -.LCPI2_0: - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI2_1: - .zero 16,252 -.LCPI2_2: - .zero 16,248 -.LCPI2_3: - .zero 16,240 -.LCPI2_4: - .zero 16,224 -.LCPI2_5: - .zero 16,192 -.LCPI2_6: - .zero 16,128 -.LCPI2_7: - .byte 0 # 0x0 - .byte 8 # 0x8 - .byte 1 # 0x1 - .byte 9 # 0x9 - .byte 2 # 0x2 - .byte 10 # 0xa - .byte 3 # 0x3 - .byte 11 # 0xb - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf -.LCPI2_8: - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI2_9: - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI2_10: - .zero 16,1 -.LCPI2_11: - .zero 16,4 -.LCPI2_12: - .zero 16,8 -.LCPI2_13: - .zero 16,16 -.LCPI2_14: - .zero 16,32 -.LCPI2_15: - .zero 16,64 - .text - .globl comparison_equal_scalar_arr_sse4 - .p2align 4, 0x90 - .type comparison_equal_scalar_arr_sse4,@function -comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 -# %bb.0: - push rbp - mov rbp, rsp - push r15 - push r14 - push r13 - push r12 - push rbx - and rsp, -16 - sub rsp, 304 - # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov qword ptr [rsp], rcx # 8-byte Spill - cmp edi, 6 - jg .LBB2_17 -# %bb.1: - cmp edi, 3 - jle .LBB2_32 -# %bb.2: - cmp edi, 4 - je .LBB2_83 -# %bb.3: - cmp edi, 5 - je .LBB2_95 -# %bb.4: - cmp edi, 6 - jne .LBB2_177 -# %bb.5: - mov r13d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB2_9 -# %bb.6: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload + cmp rax, rdx + jne .LBB1_206 +# %bb.207: + cmp rcx, rax + jne .LBB1_208 + jmp .LBB1_211 +.LBB1_100: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, r11 + mov qword ptr [rsp + 304], rax # 8-byte Spill + mov qword ptr [rsp + 152], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 144], rax # 8-byte Spill + movzx eax, r14b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 120], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB2_7: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - lea rdx, [rdx + 4] - sete bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r9 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r9 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_7 -# %bb.8: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_9: - sar r11, 5 - cmp r10, 32 - jl .LBB2_13 -# %bb.10: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB2_11: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 4] - sete r10b - cmp r13d, dword ptr [rdx + 8] - sete r14b - cmp r13d, dword ptr [rdx + 12] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 16] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 20] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 24] - sete bl - cmp r13d, dword ptr [rdx + 28] - sete dil - cmp r13d, dword ptr [rdx + 32] - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 36] - sete sil - cmp r13d, dword ptr [rdx + 40] - sete r8b - cmp r13d, dword ptr [rdx + 44] - sete r9b - cmp r13d, dword ptr [rdx + 48] - sete r11b - cmp r13d, dword ptr [rdx + 52] - sete r12b - cmp r13d, dword ptr [rdx + 56] - sete byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 60] - sete al - cmp r13d, dword ptr [rdx + 64] - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 68] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 72] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 76] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 80] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 84] - sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 88] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 92] - sete r15b - cmp r13d, dword ptr [rdx + 96] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 100] - sete byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 104] - sete byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 108] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 112] - sete byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 116] - sete byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 120] - sete byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 124] - sete cl - add r10b, r10b - add r10b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl dil, 7 - or dil, bl - shl r14b, 2 - or r14b, r10b - add sil, sil - add sil, byte ptr [rsp + 208] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 3 - or bl, r14b - mov r10d, ebx - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 4 - or bl, r10b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r11b, 4 - or r11b, r9b - shl r12b, 5 - or r12b, r11b - mov rsi, qword ptr [rsp] # 8-byte Reload - movzx r8d, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r8b, 6 - shl al, 7 - or al, r8b - or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov r8d, ebx - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 2 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 3 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl bl, 5 - or bl, r8b - mov byte ptr [rsi], dil - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 - shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], al - or r15b, bl - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], cl - add rdx, 128 - add rsi, 4 - mov qword ptr [rsp], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_11 -# %bb.12: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB2_13: - shl r11, 5 - cmp r11, r10 - jge .LBB2_177 -# %bb.14: +.LBB1_101: # =>This Inner Loop Header: Depth=1 + mov rsi, rax + mov qword ptr [rsp + 128], rax # 8-byte Spill + shl rsi, 5 + mov rbx, rsi + mov rdx, rsi + mov r8, rsi + mov rdi, rsi + mov rax, rsi + mov r13, rsi + mov r9, rsi + mov r10, rsi + mov r14, rsi + mov r15, rsi + mov qword ptr [rsp + 64], rsi # 8-byte Spill + movzx ecx, byte ptr [r11 + rsi] + movd xmm15, ecx + movzx ecx, byte ptr [r11 + rsi + 1] + movd xmm5, ecx + movzx ecx, byte ptr [r11 + rsi + 2] + movd xmm6, ecx + movzx ecx, byte ptr [r11 + rsi + 3] + movd xmm2, ecx + movzx ecx, byte ptr [r11 + rsi + 4] + movd xmm1, ecx + movzx ecx, byte ptr [r11 + rsi + 5] + movd xmm8, ecx + movzx ecx, byte ptr [r11 + rsi + 6] + movd xmm3, ecx + movzx ecx, byte ptr [r11 + rsi + 7] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rsi + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 256], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rsi + 9] + movd xmm10, ecx + movzx ecx, byte ptr [r11 + rsi + 10] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rsi + 11] + movd xmm11, ecx + movzx ecx, byte ptr [r11 + rsi + 12] + movd xmm13, ecx + movzx ecx, byte ptr [r11 + rsi + 13] + movd xmm12, ecx + movzx ecx, byte ptr [r11 + rsi + 14] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill + mov r12, rsi + or r12, 32 + mov qword ptr [rsp + 32], r12 # 8-byte Spill + or rbx, 64 + mov qword ptr [rsp + 48], rbx # 8-byte Spill + or rdx, 96 + mov qword ptr [rsp + 112], rdx # 8-byte Spill + or r8, 128 + or rdi, 160 + mov qword ptr [rsp + 96], rdi # 8-byte Spill + or rax, 192 + mov qword ptr [rsp + 88], rax # 8-byte Spill + or r13, 224 + or r9, 256 + mov qword ptr [rsp + 192], r9 # 8-byte Spill + or r10, 288 + or r14, 320 + or r15, 352 + mov qword ptr [rsp + 80], r15 # 8-byte Spill + mov rdi, qword ptr [rsp + 64] # 8-byte Reload + or rdi, 384 + mov qword ptr [rsp + 64], rdi # 8-byte Spill + mov rax, rsi + or rax, 416 + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov rax, rsi + mov rcx, rsi + mov qword ptr [rsp + 56], rsi # 8-byte Spill + or rax, 448 + or rcx, 480 + mov qword ptr [rsp + 40], rcx # 8-byte Spill + pinsrb xmm15, byte ptr [r11 + r12], 1 + pinsrb xmm15, byte ptr [r11 + rbx], 2 + pinsrb xmm15, byte ptr [r11 + rdx], 3 + pinsrb xmm15, byte ptr [r11 + r8], 4 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + r12], 5 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rbx], 6 + mov qword ptr [rsp + 72], r13 # 8-byte Spill + pinsrb xmm15, byte ptr [r11 + r13], 7 + pinsrb xmm15, byte ptr [r11 + r9], 8 + pinsrb xmm15, byte ptr [r11 + r10], 9 + pinsrb xmm15, byte ptr [r11 + r14], 10 + pinsrb xmm15, byte ptr [r11 + r15], 11 + pinsrb xmm15, byte ptr [r11 + rdi], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rsi], 13 + pinsrb xmm15, byte ptr [r11 + rax], 14 + pinsrb xmm15, byte ptr [r11 + rcx], 15 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rsi + 1], 1 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r15 + 1], 2 + pinsrb xmm5, byte ptr [r11 + rdx + 1], 3 + pinsrb xmm5, byte ptr [r11 + r8 + 1], 4 + pinsrb xmm5, byte ptr [r11 + r12 + 1], 5 + mov rdx, r12 + pinsrb xmm5, byte ptr [r11 + rbx + 1], 6 + pinsrb xmm5, byte ptr [r11 + r13 + 1], 7 + pinsrb xmm5, byte ptr [r11 + r9 + 1], 8 + pinsrb xmm5, byte ptr [r11 + r10 + 1], 9 + mov r12, r10 + pinsrb xmm5, byte ptr [r11 + r14 + 1], 10 + mov r15, r14 + mov qword ptr [rsp + 224], r14 # 8-byte Spill + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rsi + 1], 11 + pinsrb xmm5, byte ptr [r11 + rdi + 1], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rsi + 1], 13 + pinsrb xmm5, byte ptr [r11 + rax + 1], 14 + mov rbx, rax + mov qword ptr [rsp + 16], rax # 8-byte Spill + pinsrb xmm5, byte ptr [r11 + rcx + 1], 15 + movdqa xmm9, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm5, xmm9 + movdqa xmm7, xmm5 + movdqa xmm4, xmmword ptr [rip + .LCPI1_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm7, xmm4 + psubb xmm7, xmm5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 15] + movd xmm14, edi + pcmpeqb xmm15, xmm9 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rcx + 2], 1 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r13 + 2], 2 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r14 + 2], 3 + pinsrb xmm6, byte ptr [r11 + r8 + 2], 4 + pinsrb xmm6, byte ptr [r11 + rdx + 2], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rsi + 2], 6 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r9 + 2], 7 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r10 + 2], 8 + pinsrb xmm6, byte ptr [r11 + r12 + 2], 9 + pinsrb xmm6, byte ptr [r11 + r15 + 2], 10 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r15 + 2], 11 + mov rdi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdi + 2], 12 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdi + 2], 13 + pinsrb xmm6, byte ptr [r11 + rbx + 2], 14 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdi + 2], 15 + pand xmm15, xmm4 + pcmpeqb xmm6, xmm9 + movdqa xmm0, xmmword ptr [rip + .LCPI1_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm6, xmm0 + por xmm6, xmm15 + movzx edi, byte ptr [r11 + rax + 16] + movd xmm15, edi + mov rax, rcx + pinsrb xmm2, byte ptr [r11 + rcx + 3], 1 + pinsrb xmm2, byte ptr [r11 + r13 + 3], 2 + mov rbx, r14 + pinsrb xmm2, byte ptr [r11 + r14 + 3], 3 + mov r14, r8 + mov qword ptr [rsp + 104], r8 # 8-byte Spill + pinsrb xmm2, byte ptr [r11 + r8 + 3], 4 + pinsrb xmm2, byte ptr [r11 + rdx + 3], 5 + mov rcx, rsi + pinsrb xmm2, byte ptr [r11 + rsi + 3], 6 + mov rsi, r9 + pinsrb xmm2, byte ptr [r11 + r9 + 3], 7 mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB2_82 -# %bb.15: - mov r10, r8 - and r10, -2 - xor edi, edi - mov r11, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB2_16: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - sete al - neg al - mov rsi, rdi - shr rsi, 3 - movzx r9d, byte ptr [r11 + rsi] - mov ecx, edi - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r11 + rsi], bl - add rdi, 2 - cmp r13d, dword ptr [rdx + 4] - lea rdx, [rdx + 8] - sete r9b - neg r9b - xor r9b, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, r9b - xor al, bl - mov byte ptr [r11 + rsi], al - cmp r10, rdi - jne .LBB2_16 - jmp .LBB2_153 -.LBB2_17: - cmp edi, 8 - jle .LBB2_46 -# %bb.18: - cmp edi, 9 - je .LBB2_107 -# %bb.19: - cmp edi, 11 - je .LBB2_118 -# %bb.20: - cmp edi, 12 - jne .LBB2_177 -# %bb.21: - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - sub r9d, eax - je .LBB2_25 -# %bb.22: - movsxd rax, r9d - mov r11, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB2_23: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - setnp cl - sete bl - and bl, cl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] - xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_23 -# %bb.24: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_25: - sar r14, 5 - cmp r10, 32 - jl .LBB2_29 -# %bb.26: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r14 # 8-byte Spill - mov qword ptr [rsp + 152], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB2_27: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rdx] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 24], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 8] - setnp al - sete bl - and bl, al - ucomisd xmm0, qword ptr [rdx + 16] - setnp al - sete r13b - and r13b, al - ucomisd xmm0, qword ptr [rdx + 24] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 32] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 40] - setnp al - sete dil - and dil, al - ucomisd xmm0, qword ptr [rdx + 48] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 56] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 64] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 72] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 80] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 88] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 96] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 104] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 112] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 120] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 128] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 136] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 144] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 152] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 160] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 208], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 168] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 192], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 176] - setnp al - sete r15b - and r15b, al - ucomisd xmm0, qword ptr [rdx + 184] - setnp al - sete r9b - and r9b, al - ucomisd xmm0, qword ptr [rdx + 192] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 200] - setnp al - sete r14b - and r14b, al - ucomisd xmm0, qword ptr [rdx + 208] - setnp al - sete r11b - and r11b, al - ucomisd xmm0, qword ptr [rdx + 216] - setnp al - sete r10b - and r10b, al - ucomisd xmm0, qword ptr [rdx + 224] - setnp al - sete r12b - and r12b, al - ucomisd xmm0, qword ptr [rdx + 232] - setnp al - sete cl - and cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 240] - setnp al - sete r8b - and r8b, al - ucomisd xmm0, qword ptr [rdx + 248] - setnp al - sete sil - and sil, al - add bl, bl - add bl, byte ptr [rsp + 24] # 1-byte Folded Reload - shl dil, 5 - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 6 - or al, dil - mov edi, eax - shl r13b, 2 - or r13b, bl - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 7 - or al, dil - mov byte ptr [rsp + 8], al # 1-byte Spill - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 3 - or al, r13b - mov r13d, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov edi, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, r13b - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 4 - or bl, dil - movzx edi, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dil, 5 - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl cl, 6 - or cl, dil - movzx r13d, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r13b, 7 - or r13b, cl - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 80] # 1-byte Folded Reload - movzx edi, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dil, 2 - or dil, cl - movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload - shl cl, 3 - or cl, dil - mov edi, ecx - movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload - shl cl, 4 - or cl, dil - movzx edi, byte ptr [rsp + 8] # 1-byte Folded Reload - or dil, al - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload - shl al, 5 - shl r15b, 6 - or r15b, al - or r13b, bl - shl r9b, 7 - or r9b, r15b - mov rax, qword ptr [rsp] # 8-byte Reload - or r9b, cl - add r14b, r14b - add r14b, byte ptr [rsp + 160] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r14b - shl r10b, 3 - or r10b, r11b - shl r12b, 4 - or r12b, r10b - mov byte ptr [rax], dil - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl cl, 5 - shl r8b, 6 - or r8b, cl - mov byte ptr [rax + 1], r13b - shl sil, 7 - or sil, r8b - or sil, r12b - mov byte ptr [rax + 2], r9b - mov byte ptr [rax + 3], sil - add rdx, 256 - add rax, 4 - mov qword ptr [rsp], rax # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB2_27 -# %bb.28: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r14, qword ptr [rsp + 240] # 8-byte Reload -.LBB2_29: - shl r14, 5 - cmp r14, r10 - jge .LBB2_177 -# %bb.30: + pinsrb xmm2, byte ptr [r11 + r10 + 3], 8 + mov r9, r12 + pinsrb xmm2, byte ptr [r11 + r12 + 3], 9 + mov r10, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r10 + 3], 10 + pinsrb xmm2, byte ptr [r11 + r15 + 3], 11 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r12 + 3], 12 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 3], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 3], 14 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 3], 15 + pinsrb xmm1, byte ptr [r11 + rax + 4], 1 + pinsrb xmm1, byte ptr [r11 + r13 + 4], 2 + pinsrb xmm1, byte ptr [r11 + rbx + 4], 3 + pinsrb xmm1, byte ptr [r11 + r14 + 4], 4 + pinsrb xmm1, byte ptr [r11 + rdx + 4], 5 + pinsrb xmm1, byte ptr [r11 + rcx + 4], 6 + mov rbx, rcx + pinsrb xmm1, byte ptr [r11 + rsi + 4], 7 + pinsrb xmm1, byte ptr [r11 + r8 + 4], 8 + pinsrb xmm1, byte ptr [r11 + r9 + 4], 9 + mov r13, r9 + mov qword ptr [rsp + 288], r9 # 8-byte Spill + pinsrb xmm1, byte ptr [r11 + r10 + 4], 10 + pinsrb xmm1, byte ptr [r11 + r15 + 4], 11 + pinsrb xmm1, byte ptr [r11 + r12 + 4], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + rsi + 4], 13 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + rdx + 4], 14 + pinsrb xmm1, byte ptr [r11 + rdi + 4], 15 + por xmm6, xmm7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 17] + movd xmm0, edi + pcmpeqb xmm2, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI1_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm2, xmm5 + pcmpeqb xmm1, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI1_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm1, xmm5 + por xmm1, xmm2 + movzx edi, byte ptr [r11 + rax + 18] + movd xmm5, edi + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r8 + 5], 1 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r9 + 5], 2 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r14 + 5], 3 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r10 + 5], 4 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rcx + 5], 5 + pinsrb xmm8, byte ptr [r11 + rbx + 5], 6 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rbx + 5], 7 + mov r15, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r15 + 5], 8 + pinsrb xmm8, byte ptr [r11 + r13 + 5], 9 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r12 + 5], 10 + mov rdi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rdi + 5], 11 + mov rdi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rdi + 5], 12 + pinsrb xmm8, byte ptr [r11 + rsi + 5], 13 + pinsrb xmm8, byte ptr [r11 + rdx + 5], 14 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rsi + 5], 15 + pcmpeqb xmm8, xmm9 + movdqa xmm2, xmmword ptr [rip + .LCPI1_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm8, xmm2 + por xmm8, xmm1 + movzx edi, byte ptr [r11 + rax + 19] + movd xmm7, edi + por xmm8, xmm6 + movzx edi, byte ptr [r11 + rax + 20] + movd xmm6, edi + mov rdx, r8 + pinsrb xmm3, byte ptr [r11 + r8 + 6], 1 + mov r8, r9 + pinsrb xmm3, byte ptr [r11 + r9 + 6], 2 + pinsrb xmm3, byte ptr [r11 + r14 + 6], 3 + pinsrb xmm3, byte ptr [r11 + r10 + 6], 4 + pinsrb xmm3, byte ptr [r11 + rcx + 6], 5 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rcx + 6], 6 + pinsrb xmm3, byte ptr [r11 + rbx + 6], 7 + mov r9, r15 + pinsrb xmm3, byte ptr [r11 + r15 + 6], 8 + pinsrb xmm3, byte ptr [r11 + r13 + 6], 9 + mov r15, r12 + pinsrb xmm3, byte ptr [r11 + r12 + 6], 10 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rax + 6], 11 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + r12 + 6], 12 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rbx + 6], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rdi + 6], 14 + pinsrb xmm3, byte ptr [r11 + rsi + 6], 15 + movdqa xmm2, xmmword ptr [rsp + 208] # 16-byte Reload + pinsrb xmm2, byte ptr [r11 + rdx + 7], 1 + mov rdx, r8 + pinsrb xmm2, byte ptr [r11 + r8 + 7], 2 + pinsrb xmm2, byte ptr [r11 + r14 + 7], 3 + pinsrb xmm2, byte ptr [r11 + r10 + 7], 4 mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB2_162 -# %bb.31: - xor edi, edi - jmp .LBB2_164 -.LBB2_32: - cmp edi, 2 - je .LBB2_60 -# %bb.33: - cmp edi, 3 - jne .LBB2_177 -# %bb.34: - mov r14b, byte ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB2_38 -# %bb.35: - movsxd rax, r9d - mov r11, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB2_36: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rdx] - lea rdx, [rdx + 1] - sete bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] - xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_36 -# %bb.37: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_38: - sar r15, 5 - cmp r10, 32 - jl .LBB2_130 -# %bb.39: - cmp r15, 16 - mov byte ptr [rsp + 8], r14b # 1-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 232], r15 # 8-byte Spill - jb .LBB2_42 -# %bb.40: - mov rax, r15 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rsi + 7], 5 + pinsrb xmm2, byte ptr [r11 + rcx + 7], 6 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r14 + 7], 7 + mov rcx, r9 + pinsrb xmm2, byte ptr [r11 + r9 + 7], 8 + pinsrb xmm2, byte ptr [r11 + r13 + 7], 9 + pinsrb xmm2, byte ptr [r11 + r15 + 7], 10 + pinsrb xmm2, byte ptr [r11 + rax + 7], 11 + pinsrb xmm2, byte ptr [r11 + r12 + 7], 12 + pinsrb xmm2, byte ptr [r11 + rbx + 7], 13 + pinsrb xmm2, byte ptr [r11 + rdi + 7], 14 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdx + 7], 15 + pcmpeqb xmm3, xmm9 + movdqa xmm1, xmmword ptr [rip + .LCPI1_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm1 + pcmpeqb xmm2, xmm9 + psllw xmm2, 7 + movdqa xmm1, xmmword ptr [rip + .LCPI1_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm2, xmm1 + por xmm2, xmm3 + movdqa xmm1, xmm2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 21] + movd xmm2, edi + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + r13 + 9], 1 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rbx + 9], 2 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + r10 + 9], 3 + pinsrb xmm10, byte ptr [r11 + r8 + 9], 4 + pinsrb xmm10, byte ptr [r11 + rsi + 9], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rsi + 9], 6 + mov r9, r14 + pinsrb xmm10, byte ptr [r11 + r14 + 9], 7 + mov r14, rcx + pinsrb xmm10, byte ptr [r11 + rcx + 9], 8 + mov rcx, qword ptr [rsp + 288] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rcx + 9], 9 + pinsrb xmm10, byte ptr [r11 + r15 + 9], 10 + mov rdi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rdi + 9], 11 + pinsrb xmm10, byte ptr [r11 + r12 + 9], 12 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rdi + 9], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rdi + 9], 14 + pinsrb xmm10, byte ptr [r11 + rdx + 9], 15 + por xmm1, xmm8 + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill + pcmpeqb xmm10, xmm9 + movdqa xmm1, xmm10 + movdqa xmm8, xmm4 + pand xmm1, xmm4 + psubb xmm1, xmm10 + movzx edi, byte ptr [r11 + rax + 22] + movd xmm3, edi + movdqa xmm4, xmmword ptr [rsp + 256] # 16-byte Reload + pinsrb xmm4, byte ptr [r11 + r13 + 8], 1 + pinsrb xmm4, byte ptr [r11 + rbx + 8], 2 + pinsrb xmm4, byte ptr [r11 + r10 + 8], 3 + pinsrb xmm4, byte ptr [r11 + r8 + 8], 4 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdx + 8], 5 + pinsrb xmm4, byte ptr [r11 + rsi + 8], 6 + pinsrb xmm4, byte ptr [r11 + r9 + 8], 7 + mov r8, r14 + pinsrb xmm4, byte ptr [r11 + r14 + 8], 8 + mov r13, rcx + pinsrb xmm4, byte ptr [r11 + rcx + 8], 9 + pinsrb xmm4, byte ptr [r11 + r15 + 8], 10 + mov r12, r15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rax + 8], 11 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + r10 + 8], 12 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rcx + 8], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdi + 8], 14 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + r15 + 8], 15 + pcmpeqb xmm4, xmm9 + pand xmm4, xmm8 + movdqa xmm10, xmmword ptr [rsp + 160] # 16-byte Reload + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rsi + 10], 1 + pinsrb xmm10, byte ptr [r11 + rbx + 10], 2 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rbx + 10], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rsi + 10], 4 + pinsrb xmm10, byte ptr [r11 + rdx + 10], 5 + mov r14, rdx + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rdx + 10], 6 + pinsrb xmm10, byte ptr [r11 + r9 + 10], 7 + pinsrb xmm10, byte ptr [r11 + r8 + 10], 8 + pinsrb xmm10, byte ptr [r11 + r13 + 10], 9 + mov r9, r13 + pinsrb xmm10, byte ptr [r11 + r12 + 10], 10 + pinsrb xmm10, byte ptr [r11 + rax + 10], 11 + pinsrb xmm10, byte ptr [r11 + r10 + 10], 12 + mov rsi, r10 + pinsrb xmm10, byte ptr [r11 + rcx + 10], 13 + pinsrb xmm10, byte ptr [r11 + rdi + 10], 14 + pinsrb xmm10, byte ptr [r11 + r15 + 10], 15 + pcmpeqb xmm10, xmm9 + pand xmm10, xmmword ptr [rip + .LCPI1_11] + por xmm10, xmm4 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + movzx edi, byte ptr [r11 + rcx + 23] + movd xmm8, edi + por xmm10, xmm1 + movdqa xmmword ptr [rsp + 160], xmm10 # 16-byte Spill + movzx edi, byte ptr [r11 + rcx + 24] + movd xmm10, edi + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rdx + 11], 1 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + r13 + 11], 2 + pinsrb xmm11, byte ptr [r11 + rbx + 11], 3 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rcx + 11], 4 + pinsrb xmm11, byte ptr [r11 + r14 + 11], 5 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rcx + 11], 6 + mov rdi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rdi + 11], 7 + pinsrb xmm11, byte ptr [r11 + r8 + 11], 8 + pinsrb xmm11, byte ptr [r11 + r9 + 11], 9 + mov r10, r12 + pinsrb xmm11, byte ptr [r11 + r12 + 11], 10 + mov r15, rax + pinsrb xmm11, byte ptr [r11 + rax + 11], 11 + mov r12, rsi + pinsrb xmm11, byte ptr [r11 + rsi + 11], 12 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rax + 11], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rdi + 11], 14 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rsi + 11], 15 + pinsrb xmm13, byte ptr [r11 + rdx + 12], 1 + pinsrb xmm13, byte ptr [r11 + r13 + 12], 2 + pinsrb xmm13, byte ptr [r11 + rbx + 12], 3 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rsi + 12], 4 + pinsrb xmm13, byte ptr [r11 + r14 + 12], 5 + pinsrb xmm13, byte ptr [r11 + rcx + 12], 6 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + r13 + 12], 7 + pinsrb xmm13, byte ptr [r11 + r8 + 12], 8 + pinsrb xmm13, byte ptr [r11 + r9 + 12], 9 + pinsrb xmm13, byte ptr [r11 + r10 + 12], 10 + pinsrb xmm13, byte ptr [r11 + r15 + 12], 11 + pinsrb xmm13, byte ptr [r11 + r12 + 12], 12 + pinsrb xmm13, byte ptr [r11 + rax + 12], 13 + pinsrb xmm13, byte ptr [r11 + rdi + 12], 14 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rax + 12], 15 + pinsrb xmm12, byte ptr [r11 + rdx + 13], 1 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + r13 + 13], 2 + pinsrb xmm12, byte ptr [r11 + rbx + 13], 3 + pinsrb xmm12, byte ptr [r11 + rsi + 13], 4 + pinsrb xmm12, byte ptr [r11 + r14 + 13], 5 + pinsrb xmm12, byte ptr [r11 + rcx + 13], 6 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rsi + 13], 7 + pinsrb xmm12, byte ptr [r11 + r8 + 13], 8 + pinsrb xmm12, byte ptr [r11 + r9 + 13], 9 + pinsrb xmm12, byte ptr [r11 + r10 + 13], 10 + pinsrb xmm12, byte ptr [r11 + r15 + 13], 11 + pinsrb xmm12, byte ptr [r11 + r12 + 13], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rsi + 13], 13 + pinsrb xmm12, byte ptr [r11 + rdi + 13], 14 + pinsrb xmm12, byte ptr [r11 + rax + 13], 15 + pcmpeqb xmm11, xmm9 + pand xmm11, xmmword ptr [rip + .LCPI1_12] + pcmpeqb xmm13, xmm9 + pand xmm13, xmmword ptr [rip + .LCPI1_13] + por xmm13, xmm11 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 25] + movd xmm1, edi + pcmpeqb xmm12, xmm9 + pand xmm12, xmmword ptr [rip + .LCPI1_14] + por xmm12, xmm13 + movzx edi, byte ptr [r11 + rax + 26] + movd xmm11, edi + movdqa xmm4, xmmword ptr [rsp + 240] # 16-byte Reload + pinsrb xmm4, byte ptr [r11 + rdx + 14], 1 + mov r13, rdx + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rsi + 14], 2 + pinsrb xmm4, byte ptr [r11 + rbx + 14], 3 + mov r14, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + r14 + 14], 4 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rax + 14], 5 + pinsrb xmm4, byte ptr [r11 + rcx + 14], 6 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdx + 14], 7 + pinsrb xmm4, byte ptr [r11 + r8 + 14], 8 + pinsrb xmm4, byte ptr [r11 + r9 + 14], 9 + pinsrb xmm4, byte ptr [r11 + r10 + 14], 10 + pinsrb xmm4, byte ptr [r11 + r15 + 14], 11 + pinsrb xmm4, byte ptr [r11 + r12 + 14], 12 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdi + 14], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdi + 14], 14 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdi + 14], 15 + pinsrb xmm14, byte ptr [r11 + r13 + 15], 1 + pinsrb xmm14, byte ptr [r11 + rsi + 15], 2 + pinsrb xmm14, byte ptr [r11 + rbx + 15], 3 + pinsrb xmm14, byte ptr [r11 + r14 + 15], 4 + pinsrb xmm14, byte ptr [r11 + rax + 15], 5 + pinsrb xmm14, byte ptr [r11 + rcx + 15], 6 + pinsrb xmm14, byte ptr [r11 + rdx + 15], 7 + pinsrb xmm14, byte ptr [r11 + r8 + 15], 8 + pinsrb xmm14, byte ptr [r11 + r9 + 15], 9 + pinsrb xmm14, byte ptr [r11 + r10 + 15], 10 + pinsrb xmm14, byte ptr [r11 + r15 + 15], 11 + pinsrb xmm14, byte ptr [r11 + r12 + 15], 12 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + r13 + 15], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + rdi + 15], 14 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + rdi + 15], 15 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + r13 + 16], 1 + pinsrb xmm15, byte ptr [r11 + rsi + 16], 2 + pinsrb xmm15, byte ptr [r11 + rbx + 16], 3 + pinsrb xmm15, byte ptr [r11 + r14 + 16], 4 + pinsrb xmm15, byte ptr [r11 + rax + 16], 5 + pinsrb xmm15, byte ptr [r11 + rcx + 16], 6 + pinsrb xmm15, byte ptr [r11 + rdx + 16], 7 + pinsrb xmm15, byte ptr [r11 + r8 + 16], 8 + pinsrb xmm15, byte ptr [r11 + r9 + 16], 9 + pinsrb xmm15, byte ptr [r11 + r10 + 16], 10 + pinsrb xmm15, byte ptr [r11 + r15 + 16], 11 + pinsrb xmm15, byte ptr [r11 + r12 + 16], 12 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rdi + 16], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rdi + 16], 14 + pinsrb xmm0, byte ptr [r11 + r13 + 17], 1 + pinsrb xmm0, byte ptr [r11 + rsi + 17], 2 + pinsrb xmm0, byte ptr [r11 + rbx + 17], 3 + pinsrb xmm0, byte ptr [r11 + r14 + 17], 4 + pinsrb xmm0, byte ptr [r11 + rax + 17], 5 + mov r13, rax + pinsrb xmm0, byte ptr [r11 + rcx + 17], 6 + pinsrb xmm0, byte ptr [r11 + rdx + 17], 7 + pinsrb xmm0, byte ptr [r11 + r8 + 17], 8 + pinsrb xmm0, byte ptr [r11 + r9 + 17], 9 + pinsrb xmm0, byte ptr [r11 + r10 + 17], 10 + pinsrb xmm0, byte ptr [r11 + r15 + 17], 11 + pinsrb xmm0, byte ptr [r11 + r12 + 17], 12 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 17], 13 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rsi + 17], 14 + por xmm12, xmmword ptr [rsp + 160] # 16-byte Folded Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 27] + movd xmm9, edi + movdqa xmm13, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm4, xmm13 + pand xmm4, xmmword ptr [rip + .LCPI1_15] + pcmpeqb xmm14, xmm13 + psllw xmm14, 7 + pand xmm14, xmmword ptr [rip + .LCPI1_6] + por xmm14, xmm4 + movzx edi, byte ptr [r11 + rax + 28] + movd xmm4, edi + mov r10, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + r10 + 17], 15 + por xmm14, xmm12 + pcmpeqb xmm0, xmm13 + movdqa xmm13, xmm0 + movdqa xmm12, xmmword ptr [rip + .LCPI1_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm13, xmm12 + psubb xmm13, xmm0 + movdqa xmmword ptr [rsp + 160], xmm13 # 16-byte Spill + movzx edi, byte ptr [r11 + rax + 29] + movd xmm13, edi + pinsrb xmm15, byte ptr [r11 + r10 + 16], 15 + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm15, xmm0 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rdi + 18], 1 + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rdi + 18], 2 + pinsrb xmm5, byte ptr [r11 + rbx + 18], 3 + pinsrb xmm5, byte ptr [r11 + r14 + 18], 4 + pinsrb xmm5, byte ptr [r11 + r13 + 18], 5 + pinsrb xmm5, byte ptr [r11 + rcx + 18], 6 + pinsrb xmm5, byte ptr [r11 + rdx + 18], 7 + pinsrb xmm5, byte ptr [r11 + r8 + 18], 8 + pinsrb xmm5, byte ptr [r11 + r9 + 18], 9 + mov rax, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rax + 18], 10 + pinsrb xmm5, byte ptr [r11 + r15 + 18], 11 + pinsrb xmm5, byte ptr [r11 + r12 + 18], 12 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rdi + 18], 13 + pinsrb xmm5, byte ptr [r11 + rsi + 18], 14 + pand xmm15, xmm12 + pinsrb xmm5, byte ptr [r11 + r10 + 18], 15 + pcmpeqb xmm5, xmm0 + pand xmm5, xmmword ptr [rip + .LCPI1_11] + por xmm5, xmm15 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + movzx edi, byte ptr [r11 + rsi + 30] + movd xmm12, edi + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + rdi + 19], 1 + pinsrb xmm6, byte ptr [r11 + rdi + 20], 1 + pinsrb xmm2, byte ptr [r11 + rdi + 21], 1 + pinsrb xmm3, byte ptr [r11 + rdi + 22], 1 + pinsrb xmm8, byte ptr [r11 + rdi + 23], 1 + pinsrb xmm10, byte ptr [r11 + rdi + 24], 1 + pinsrb xmm1, byte ptr [r11 + rdi + 25], 1 + pinsrb xmm11, byte ptr [r11 + rdi + 26], 1 + pinsrb xmm9, byte ptr [r11 + rdi + 27], 1 + pinsrb xmm4, byte ptr [r11 + rdi + 28], 1 + pinsrb xmm13, byte ptr [r11 + rdi + 29], 1 + pinsrb xmm12, byte ptr [r11 + rdi + 30], 1 + movzx esi, byte ptr [r11 + rsi + 31] + movd xmm0, esi + pinsrb xmm0, byte ptr [r11 + rdi + 31], 1 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + rsi + 19], 2 + pinsrb xmm6, byte ptr [r11 + rsi + 20], 2 + pinsrb xmm2, byte ptr [r11 + rsi + 21], 2 + pinsrb xmm3, byte ptr [r11 + rsi + 22], 2 + pinsrb xmm8, byte ptr [r11 + rsi + 23], 2 + pinsrb xmm10, byte ptr [r11 + rsi + 24], 2 + pinsrb xmm1, byte ptr [r11 + rsi + 25], 2 + pinsrb xmm11, byte ptr [r11 + rsi + 26], 2 + pinsrb xmm9, byte ptr [r11 + rsi + 27], 2 + pinsrb xmm4, byte ptr [r11 + rsi + 28], 2 + pinsrb xmm13, byte ptr [r11 + rsi + 29], 2 + pinsrb xmm12, byte ptr [r11 + rsi + 30], 2 + pinsrb xmm0, byte ptr [r11 + rsi + 31], 2 + pinsrb xmm7, byte ptr [r11 + rbx + 19], 3 + pinsrb xmm7, byte ptr [r11 + r14 + 19], 4 + pinsrb xmm7, byte ptr [r11 + r13 + 19], 5 + pinsrb xmm7, byte ptr [r11 + rcx + 19], 6 + pinsrb xmm7, byte ptr [r11 + rdx + 19], 7 + pinsrb xmm7, byte ptr [r11 + r8 + 19], 8 + pinsrb xmm7, byte ptr [r11 + r9 + 19], 9 + pinsrb xmm7, byte ptr [r11 + rax + 19], 10 + pinsrb xmm7, byte ptr [r11 + r15 + 19], 11 + pinsrb xmm7, byte ptr [r11 + r12 + 19], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + rsi + 19], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + rdi + 19], 14 + pinsrb xmm7, byte ptr [r11 + r10 + 19], 15 + pinsrb xmm6, byte ptr [r11 + rbx + 20], 3 + pinsrb xmm6, byte ptr [r11 + r14 + 20], 4 + pinsrb xmm6, byte ptr [r11 + r13 + 20], 5 + pinsrb xmm6, byte ptr [r11 + rcx + 20], 6 + pinsrb xmm6, byte ptr [r11 + rdx + 20], 7 + pinsrb xmm6, byte ptr [r11 + r8 + 20], 8 + pinsrb xmm6, byte ptr [r11 + r9 + 20], 9 + pinsrb xmm6, byte ptr [r11 + rax + 20], 10 + pinsrb xmm6, byte ptr [r11 + r15 + 20], 11 + pinsrb xmm6, byte ptr [r11 + r12 + 20], 12 + pinsrb xmm6, byte ptr [r11 + rsi + 20], 13 + pinsrb xmm6, byte ptr [r11 + rdi + 20], 14 + por xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload + pinsrb xmm6, byte ptr [r11 + r10 + 20], 15 + movdqa xmm15, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm7, xmm15 + pand xmm7, xmmword ptr [rip + .LCPI1_12] + pcmpeqb xmm6, xmm15 + pand xmm6, xmmword ptr [rip + .LCPI1_13] + por xmm6, xmm7 + pinsrb xmm2, byte ptr [r11 + rbx + 21], 3 + pinsrb xmm2, byte ptr [r11 + r14 + 21], 4 + pinsrb xmm2, byte ptr [r11 + r13 + 21], 5 + pinsrb xmm2, byte ptr [r11 + rcx + 21], 6 + pinsrb xmm2, byte ptr [r11 + rdx + 21], 7 + pinsrb xmm2, byte ptr [r11 + r8 + 21], 8 + pinsrb xmm2, byte ptr [r11 + r9 + 21], 9 + pinsrb xmm2, byte ptr [r11 + rax + 21], 10 + pinsrb xmm2, byte ptr [r11 + r15 + 21], 11 + pinsrb xmm2, byte ptr [r11 + r12 + 21], 12 + pinsrb xmm2, byte ptr [r11 + rsi + 21], 13 + pinsrb xmm2, byte ptr [r11 + rdi + 21], 14 + pinsrb xmm2, byte ptr [r11 + r10 + 21], 15 + pcmpeqb xmm2, xmm15 + movdqa xmm7, xmmword ptr [rip + .LCPI1_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm2, xmm7 + por xmm2, xmm6 + por xmm2, xmm5 + pinsrb xmm3, byte ptr [r11 + rbx + 22], 3 + pinsrb xmm3, byte ptr [r11 + r14 + 22], 4 + pinsrb xmm3, byte ptr [r11 + r13 + 22], 5 + pinsrb xmm3, byte ptr [r11 + rcx + 22], 6 + pinsrb xmm3, byte ptr [r11 + rdx + 22], 7 + pinsrb xmm3, byte ptr [r11 + r8 + 22], 8 + pinsrb xmm3, byte ptr [r11 + r9 + 22], 9 + pinsrb xmm3, byte ptr [r11 + rax + 22], 10 + pinsrb xmm3, byte ptr [r11 + r15 + 22], 11 + pinsrb xmm3, byte ptr [r11 + r12 + 22], 12 + pinsrb xmm3, byte ptr [r11 + rsi + 22], 13 + pinsrb xmm3, byte ptr [r11 + rdi + 22], 14 + pinsrb xmm3, byte ptr [r11 + r10 + 22], 15 + pinsrb xmm8, byte ptr [r11 + rbx + 23], 3 + pinsrb xmm8, byte ptr [r11 + r14 + 23], 4 + pinsrb xmm8, byte ptr [r11 + r13 + 23], 5 + pinsrb xmm8, byte ptr [r11 + rcx + 23], 6 + pinsrb xmm8, byte ptr [r11 + rdx + 23], 7 + pinsrb xmm8, byte ptr [r11 + r8 + 23], 8 + pinsrb xmm8, byte ptr [r11 + r9 + 23], 9 + pinsrb xmm8, byte ptr [r11 + rax + 23], 10 + pinsrb xmm8, byte ptr [r11 + r15 + 23], 11 + pinsrb xmm8, byte ptr [r11 + r12 + 23], 12 + pinsrb xmm8, byte ptr [r11 + rsi + 23], 13 + pinsrb xmm8, byte ptr [r11 + rdi + 23], 14 + pinsrb xmm8, byte ptr [r11 + r10 + 23], 15 + pcmpeqb xmm3, xmm15 + movdqa xmm5, xmmword ptr [rip + .LCPI1_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm5 + pcmpeqb xmm8, xmm15 + psllw xmm8, 7 + movdqa xmm6, xmmword ptr [rip + .LCPI1_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm8, xmm6 + por xmm8, xmm3 + pinsrb xmm1, byte ptr [r11 + rbx + 25], 3 + pinsrb xmm1, byte ptr [r11 + r14 + 25], 4 + pinsrb xmm1, byte ptr [r11 + r13 + 25], 5 + pinsrb xmm1, byte ptr [r11 + rcx + 25], 6 + pinsrb xmm1, byte ptr [r11 + rdx + 25], 7 + pinsrb xmm1, byte ptr [r11 + r8 + 25], 8 + pinsrb xmm1, byte ptr [r11 + r9 + 25], 9 + pinsrb xmm1, byte ptr [r11 + rax + 25], 10 + pinsrb xmm1, byte ptr [r11 + r15 + 25], 11 + pinsrb xmm1, byte ptr [r11 + r12 + 25], 12 + pinsrb xmm1, byte ptr [r11 + rsi + 25], 13 + pinsrb xmm1, byte ptr [r11 + rdi + 25], 14 + pinsrb xmm1, byte ptr [r11 + r10 + 25], 15 + por xmm8, xmm2 + pcmpeqb xmm1, xmm15 + movdqa xmm2, xmm1 + movdqa xmm3, xmmword ptr [rip + .LCPI1_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm2, xmm3 + psubb xmm2, xmm1 + pinsrb xmm10, byte ptr [r11 + rbx + 24], 3 + pinsrb xmm10, byte ptr [r11 + r14 + 24], 4 + pinsrb xmm10, byte ptr [r11 + r13 + 24], 5 + pinsrb xmm10, byte ptr [r11 + rcx + 24], 6 + pinsrb xmm10, byte ptr [r11 + rdx + 24], 7 + pinsrb xmm10, byte ptr [r11 + r8 + 24], 8 + pinsrb xmm10, byte ptr [r11 + r9 + 24], 9 + pinsrb xmm10, byte ptr [r11 + rax + 24], 10 + pinsrb xmm10, byte ptr [r11 + r15 + 24], 11 + pinsrb xmm10, byte ptr [r11 + r12 + 24], 12 + pinsrb xmm10, byte ptr [r11 + rsi + 24], 13 + pinsrb xmm10, byte ptr [r11 + rdi + 24], 14 + pinsrb xmm10, byte ptr [r11 + r10 + 24], 15 + pcmpeqb xmm10, xmm15 + pand xmm10, xmm3 + pinsrb xmm11, byte ptr [r11 + rbx + 26], 3 + pinsrb xmm11, byte ptr [r11 + r14 + 26], 4 + pinsrb xmm11, byte ptr [r11 + r13 + 26], 5 + pinsrb xmm11, byte ptr [r11 + rcx + 26], 6 + pinsrb xmm11, byte ptr [r11 + rdx + 26], 7 + pinsrb xmm11, byte ptr [r11 + r8 + 26], 8 + pinsrb xmm11, byte ptr [r11 + r9 + 26], 9 + pinsrb xmm11, byte ptr [r11 + rax + 26], 10 + pinsrb xmm11, byte ptr [r11 + r15 + 26], 11 + pinsrb xmm11, byte ptr [r11 + r12 + 26], 12 + pinsrb xmm11, byte ptr [r11 + rsi + 26], 13 + pinsrb xmm11, byte ptr [r11 + rdi + 26], 14 + pinsrb xmm11, byte ptr [r11 + r10 + 26], 15 + pcmpeqb xmm11, xmm15 + pand xmm11, xmmword ptr [rip + .LCPI1_11] + por xmm11, xmm10 + por xmm11, xmm2 + pinsrb xmm9, byte ptr [r11 + rbx + 27], 3 + pinsrb xmm9, byte ptr [r11 + r14 + 27], 4 + pinsrb xmm9, byte ptr [r11 + r13 + 27], 5 + pinsrb xmm9, byte ptr [r11 + rcx + 27], 6 + pinsrb xmm9, byte ptr [r11 + rdx + 27], 7 + pinsrb xmm9, byte ptr [r11 + r8 + 27], 8 + pinsrb xmm9, byte ptr [r11 + r9 + 27], 9 + pinsrb xmm9, byte ptr [r11 + rax + 27], 10 + pinsrb xmm9, byte ptr [r11 + r15 + 27], 11 + pinsrb xmm9, byte ptr [r11 + r12 + 27], 12 + pinsrb xmm9, byte ptr [r11 + rsi + 27], 13 + pinsrb xmm9, byte ptr [r11 + rdi + 27], 14 + pinsrb xmm9, byte ptr [r11 + r10 + 27], 15 + pinsrb xmm4, byte ptr [r11 + rbx + 28], 3 + pinsrb xmm4, byte ptr [r11 + r14 + 28], 4 + pinsrb xmm4, byte ptr [r11 + r13 + 28], 5 + pinsrb xmm4, byte ptr [r11 + rcx + 28], 6 + pinsrb xmm4, byte ptr [r11 + rdx + 28], 7 + pinsrb xmm4, byte ptr [r11 + r8 + 28], 8 + pinsrb xmm4, byte ptr [r11 + r9 + 28], 9 + pinsrb xmm4, byte ptr [r11 + rax + 28], 10 + pinsrb xmm4, byte ptr [r11 + r15 + 28], 11 + pinsrb xmm4, byte ptr [r11 + r12 + 28], 12 + pinsrb xmm4, byte ptr [r11 + rsi + 28], 13 + pinsrb xmm4, byte ptr [r11 + rdi + 28], 14 + pinsrb xmm4, byte ptr [r11 + r10 + 28], 15 + pinsrb xmm13, byte ptr [r11 + rbx + 29], 3 + pinsrb xmm13, byte ptr [r11 + r14 + 29], 4 + pinsrb xmm13, byte ptr [r11 + r13 + 29], 5 + pinsrb xmm13, byte ptr [r11 + rcx + 29], 6 + pinsrb xmm13, byte ptr [r11 + rdx + 29], 7 + pinsrb xmm13, byte ptr [r11 + r8 + 29], 8 + pinsrb xmm13, byte ptr [r11 + r9 + 29], 9 + pinsrb xmm13, byte ptr [r11 + rax + 29], 10 + pinsrb xmm13, byte ptr [r11 + r15 + 29], 11 + pinsrb xmm13, byte ptr [r11 + r12 + 29], 12 + pinsrb xmm13, byte ptr [r11 + rsi + 29], 13 + pinsrb xmm13, byte ptr [r11 + rdi + 29], 14 + movdqa xmm1, xmm15 + pcmpeqb xmm9, xmm15 + pand xmm9, xmmword ptr [rip + .LCPI1_12] + pcmpeqb xmm4, xmm15 + pand xmm4, xmmword ptr [rip + .LCPI1_13] + por xmm4, xmm9 + pinsrb xmm13, byte ptr [r11 + r10 + 29], 15 + pcmpeqb xmm13, xmm15 + pand xmm13, xmm7 + por xmm13, xmm4 + pinsrb xmm12, byte ptr [r11 + rbx + 30], 3 + pinsrb xmm0, byte ptr [r11 + rbx + 31], 3 + pinsrb xmm12, byte ptr [r11 + r14 + 30], 4 + pinsrb xmm0, byte ptr [r11 + r14 + 31], 4 + pinsrb xmm12, byte ptr [r11 + r13 + 30], 5 + pinsrb xmm0, byte ptr [r11 + r13 + 31], 5 + pinsrb xmm12, byte ptr [r11 + rcx + 30], 6 + pinsrb xmm0, byte ptr [r11 + rcx + 31], 6 + pinsrb xmm12, byte ptr [r11 + rdx + 30], 7 + pinsrb xmm0, byte ptr [r11 + rdx + 31], 7 + pinsrb xmm12, byte ptr [r11 + r8 + 30], 8 + pinsrb xmm0, byte ptr [r11 + r8 + 31], 8 + pinsrb xmm12, byte ptr [r11 + r9 + 30], 9 + pinsrb xmm0, byte ptr [r11 + r9 + 31], 9 + pinsrb xmm12, byte ptr [r11 + rax + 30], 10 + pinsrb xmm0, byte ptr [r11 + rax + 31], 10 + pinsrb xmm12, byte ptr [r11 + r15 + 30], 11 + pinsrb xmm0, byte ptr [r11 + r15 + 31], 11 + pinsrb xmm12, byte ptr [r11 + r12 + 30], 12 + pinsrb xmm0, byte ptr [r11 + r12 + 31], 12 + pinsrb xmm12, byte ptr [r11 + rsi + 30], 13 + pinsrb xmm0, byte ptr [r11 + rsi + 31], 13 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rdi + 30], 14 + pinsrb xmm0, byte ptr [r11 + rdi + 31], 14 + pinsrb xmm12, byte ptr [r11 + r10 + 30], 15 + pinsrb xmm0, byte ptr [r11 + r10 + 31], 15 + por xmm13, xmm11 + pcmpeqb xmm12, xmm15 + pand xmm12, xmm5 + pcmpeqb xmm0, xmm15 + psllw xmm0, 7 + pand xmm0, xmm6 + por xmm0, xmm12 + por xmm0, xmm13 + movdqa xmm1, xmm8 + punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + movdqa xmm4, xmmword ptr [rsp + 208] # 16-byte Reload + movdqa xmm2, xmm4 + punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] + movdqa xmm3, xmm2 + punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] + punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] + punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] + punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] + movdqa xmm0, xmm4 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx + 48], xmm4 + movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 + movdqu xmmword ptr [rax + 4*rcx], xmm3 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 152] # 8-byte Folded Reload + jne .LBB1_101 +# %bb.102: + mov rcx, qword ptr [rsp + 280] # 8-byte Reload + cmp rcx, qword ptr [rsp + 152] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r14b, byte ptr [rsp + 8] # 1-byte Reload + mov rsi, qword ptr [rsp + 304] # 8-byte Reload + jne .LBB1_103 + jmp .LBB1_106 +.LBB1_73: + and rcx, -16 + mov rax, rcx shl rax, 5 - add rax, rdx - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB2_182 -# %bb.41: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] - cmp rdx, rax - jae .LBB2_182 -.LBB2_42: + add rax, r14 + mov qword ptr [rsp + 304], rax # 8-byte Spill + mov qword ptr [rsp + 152], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 144], rax # 8-byte Spill + movzx eax, r11b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill xor eax, eax - mov qword ptr [rsp + 224], rax # 8-byte Spill - mov rsi, rdx - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 104], rax # 8-byte Spill -.LBB2_43: - sub r15, qword ptr [rsp + 224] # 8-byte Folded Reload - mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 120], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB2_44: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp r14b, byte ptr [rsi] - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 1] - sete dil - cmp r14b, byte ptr [rsi + 2] - sete r11b - cmp r14b, byte ptr [rsi + 3] - sete r15b - cmp r14b, byte ptr [rsi + 4] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 5] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 6] - sete bl - cmp r14b, byte ptr [rsi + 7] - sete r13b - cmp r14b, byte ptr [rsi + 8] - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 9] - sete sil - cmp r14b, byte ptr [rcx + 10] - sete r8b - cmp r14b, byte ptr [rcx + 11] - sete r9b - cmp r14b, byte ptr [rcx + 12] - sete r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 13] - sete r12b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 14] - sete byte ptr [rsp + 176] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 15] - sete al - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 16] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 17] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 18] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 19] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 20] - sete byte ptr [rsp + 72] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 21] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 22] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 23] - sete r10b - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 24] - sete byte ptr [rsp + 32] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 25] - sete byte ptr [rsp + 56] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 26] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 27] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 28] - sete byte ptr [rsp + 48] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 29] - sete byte ptr [rsp + 16] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 30] - sete byte ptr [rsp] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 31] - sete dl - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl r13b, 7 - or r13b, bl - shl r11b, 2 - or r11b, dil - add sil, sil - add sil, byte ptr [rsp + 208] # 1-byte Folded Reload - shl r15b, 3 - or r15b, r11b - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 4 - or bl, r15b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r14b, 4 - or r14b, r9b - shl r12b, 5 - or r12b, r14b - movzx r14d, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload - shl sil, 6 - shl al, 7 - or al, sil - or r13b, bl - or al, r12b - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 120] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 2 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - mov byte ptr [rdi], r13b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl sil, 6 - shl r10b, 7 - or r10b, sil - mov byte ptr [rdi + 1], al - or r10b, bl - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, al - mov byte ptr [rdi + 2], r10b - mov byte ptr [rdi + 3], dl - lea rsi, [rcx + 32] - add rdi, 4 - mov qword ptr [rsp + 104], rdi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_44 -# %bb.45: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r15, qword ptr [rsp + 232] # 8-byte Reload - jmp .LBB2_131 -.LBB2_46: - cmp edi, 7 - je .LBB2_72 -# %bb.47: - cmp edi, 8 - jne .LBB2_177 -# %bb.48: - mov r13, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB2_52 -# %bb.49: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload +.LBB1_74: # =>This Inner Loop Header: Depth=1 + mov rsi, rax + mov qword ptr [rsp + 256], rax # 8-byte Spill + shl rsi, 5 + mov qword ptr [rsp + 24], rsi # 8-byte Spill + mov r10, rsi + mov r11, rsi + mov r13, rsi + mov r12, rsi + mov r8, rsi + mov rdi, rsi + mov r9, rsi + mov rbx, rsi + mov rdx, rsi + mov qword ptr [rsp + 72], rsi # 8-byte Spill + movzx ecx, byte ptr [r14 + rsi] + movd xmm15, ecx + movzx ecx, byte ptr [r14 + rsi + 1] + movd xmm5, ecx + movzx ecx, byte ptr [r14 + rsi + 2] + movd xmm6, ecx + movzx ecx, byte ptr [r14 + rsi + 3] + movd xmm2, ecx + movzx ecx, byte ptr [r14 + rsi + 4] + movd xmm1, ecx + movzx ecx, byte ptr [r14 + rsi + 5] + movd xmm8, ecx + movzx ecx, byte ptr [r14 + rsi + 6] + movd xmm3, ecx + movzx ecx, byte ptr [r14 + rsi + 7] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rsi + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 288], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rsi + 9] + movd xmm10, ecx + movzx ecx, byte ptr [r14 + rsi + 10] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rsi + 11] + movd xmm11, ecx + movzx ecx, byte ptr [r14 + rsi + 12] + movd xmm13, ecx + movzx ecx, byte ptr [r14 + rsi + 13] + movd xmm12, ecx + movzx ecx, byte ptr [r14 + rsi + 14] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill + mov qword ptr [rsp + 80], rsi # 8-byte Spill + mov r15, rsi + or r15, 32 + mov qword ptr [rsp + 48], r15 # 8-byte Spill + mov rax, qword ptr [rsp + 24] # 8-byte Reload + or rax, 64 + mov qword ptr [rsp + 24], rax # 8-byte Spill + or r10, 96 + or r11, 128 + or r13, 160 + or r12, 192 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + mov r12, rsi + or r12, 224 + or rdi, 256 + mov qword ptr [rsp + 32], rdi # 8-byte Spill + or r8, 288 + mov qword ptr [rsp + 104], r8 # 8-byte Spill + or r9, 320 + mov qword ptr [rsp + 160], r9 # 8-byte Spill + or rdx, 352 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + or rcx, 384 + mov qword ptr [rsp + 72], rcx # 8-byte Spill + or rbx, 416 + mov qword ptr [rsp + 16], rbx # 8-byte Spill + mov rbx, rsi + or rbx, 448 + mov qword ptr [rsp + 40], rbx # 8-byte Spill + mov rbx, rsi + or rbx, 480 + pinsrb xmm15, byte ptr [r14 + r15], 1 + pinsrb xmm15, byte ptr [r14 + rax], 2 + mov qword ptr [rsp + 112], r10 # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r10], 3 + mov rsi, r11 + mov qword ptr [rsp + 88], r11 # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r11], 4 + mov qword ptr [rsp + 64], r13 # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r13], 5 + mov r15, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r15], 6 + mov r11, r12 + mov qword ptr [rsp + 176], r12 # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r12], 7 + pinsrb xmm15, byte ptr [r14 + rdi], 8 + pinsrb xmm15, byte ptr [r14 + r8], 9 + pinsrb xmm15, byte ptr [r14 + r9], 10 + pinsrb xmm15, byte ptr [r14 + rdx], 11 + pinsrb xmm15, byte ptr [r14 + rcx], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 14 + pinsrb xmm15, byte ptr [r14 + rbx], 15 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r12 + 1], 1 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 2 + pinsrb xmm5, byte ptr [r14 + r10 + 1], 3 + pinsrb xmm5, byte ptr [r14 + rsi + 1], 4 + pinsrb xmm5, byte ptr [r14 + r13 + 1], 5 + pinsrb xmm5, byte ptr [r14 + r15 + 1], 6 + pinsrb xmm5, byte ptr [r14 + r11 + 1], 7 + pinsrb xmm5, byte ptr [r14 + rdi + 1], 8 + pinsrb xmm5, byte ptr [r14 + r8 + 1], 9 + pinsrb xmm5, byte ptr [r14 + r9 + 1], 10 + pinsrb xmm5, byte ptr [r14 + rdx + 1], 11 + mov r12, rdx + mov qword ptr [rsp + 96], rdx # 8-byte Spill + pinsrb xmm5, byte ptr [r14 + rcx + 1], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 13 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r8 + 1], 14 + pinsrb xmm5, byte ptr [r14 + rbx + 1], 15 + mov r10, rbx + mov qword ptr [rsp + 56], rbx # 8-byte Spill + movdqa xmm9, xmmword ptr [rsp + 208] # 16-byte Reload + pcmpeqb xmm5, xmm9 + movdqa xmm7, xmm5 + movdqa xmm4, xmmword ptr [rip + .LCPI1_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm7, xmm4 + psubb xmm7, xmm5 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 15] + movd xmm14, edx + pcmpeqb xmm15, xmm9 + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdi + 2], 1 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 2 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rcx + 2], 3 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r13 + 2], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdx + 2], 5 + pinsrb xmm6, byte ptr [r14 + r15 + 2], 6 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r15 + 2], 7 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r11 + 2], 8 + mov rbx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rbx + 2], 9 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r9 + 2], 10 + pinsrb xmm6, byte ptr [r14 + r12 + 2], 11 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdx + 2], 12 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r12 + 2], 13 + pinsrb xmm6, byte ptr [r14 + r8 + 2], 14 + pinsrb xmm6, byte ptr [r14 + r10 + 2], 15 + pand xmm15, xmm4 + pcmpeqb xmm6, xmm9 + movdqa xmm0, xmmword ptr [rip + .LCPI1_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm6, xmm0 + por xmm6, xmm15 + movzx edx, byte ptr [r14 + rax + 16] + movd xmm15, edx + mov rax, rdi + pinsrb xmm2, byte ptr [r14 + rdi + 3], 1 + mov rdi, rsi + pinsrb xmm2, byte ptr [r14 + rsi + 3], 2 + pinsrb xmm2, byte ptr [r14 + rcx + 3], 3 + mov r10, rcx + pinsrb xmm2, byte ptr [r14 + r13 + 3], 4 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdx + 3], 5 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rcx + 3], 6 + mov rsi, r15 + pinsrb xmm2, byte ptr [r14 + r15 + 3], 7 + pinsrb xmm2, byte ptr [r14 + r11 + 3], 8 + pinsrb xmm2, byte ptr [r14 + rbx + 3], 9 + pinsrb xmm2, byte ptr [r14 + r9 + 3], 10 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rbx + 3], 11 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r15 + 3], 12 + pinsrb xmm2, byte ptr [r14 + r12 + 3], 13 + pinsrb xmm2, byte ptr [r14 + r8 + 3], 14 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r9 + 3], 15 + pinsrb xmm1, byte ptr [r14 + rax + 4], 1 + pinsrb xmm1, byte ptr [r14 + rdi + 4], 2 + pinsrb xmm1, byte ptr [r14 + r10 + 4], 3 + pinsrb xmm1, byte ptr [r14 + r13 + 4], 4 + pinsrb xmm1, byte ptr [r14 + rdx + 4], 5 + pinsrb xmm1, byte ptr [r14 + rcx + 4], 6 + pinsrb xmm1, byte ptr [r14 + rsi + 4], 7 + pinsrb xmm1, byte ptr [r14 + r11 + 4], 8 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rsi + 4], 9 + mov rdi, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rdi + 4], 10 + pinsrb xmm1, byte ptr [r14 + rbx + 4], 11 + pinsrb xmm1, byte ptr [r14 + r15 + 4], 12 + pinsrb xmm1, byte ptr [r14 + r12 + 4], 13 + pinsrb xmm1, byte ptr [r14 + r8 + 4], 14 + pinsrb xmm1, byte ptr [r14 + r9 + 4], 15 + por xmm6, xmm7 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + movzx edx, byte ptr [r14 + rbx + 17] + movd xmm0, edx + pcmpeqb xmm2, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI1_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm2, xmm5 + pcmpeqb xmm1, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI1_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm1, xmm5 + por xmm1, xmm2 + movzx edx, byte ptr [r14 + rbx + 18] + movd xmm5, edx + pinsrb xmm8, byte ptr [r14 + rax + 5], 1 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rcx + 5], 2 + mov r8, r10 + pinsrb xmm8, byte ptr [r14 + r10 + 5], 3 + pinsrb xmm8, byte ptr [r14 + r13 + 5], 4 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rcx + 5], 5 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r11 + 5], 6 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rdx + 5], 7 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rdx + 5], 8 + pinsrb xmm8, byte ptr [r14 + rsi + 5], 9 + pinsrb xmm8, byte ptr [r14 + rdi + 5], 10 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rdx + 5], 11 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rdx + 5], 12 + pinsrb xmm8, byte ptr [r14 + r12 + 5], 13 + mov r10, r12 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rdi + 5], 14 + pinsrb xmm8, byte ptr [r14 + r9 + 5], 15 + pcmpeqb xmm8, xmm9 + movdqa xmm2, xmmword ptr [rip + .LCPI1_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm8, xmm2 + por xmm8, xmm1 + movzx edx, byte ptr [r14 + rbx + 19] + movd xmm7, edx + por xmm8, xmm6 + movzx edx, byte ptr [r14 + rbx + 20] + movd xmm6, edx + pinsrb xmm3, byte ptr [r14 + rax + 6], 1 + mov r9, rax + mov r13, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r13 + 6], 2 + pinsrb xmm3, byte ptr [r14 + r8 + 6], 3 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r12 + 6], 4 + pinsrb xmm3, byte ptr [r14 + rcx + 6], 5 + mov rcx, r11 + pinsrb xmm3, byte ptr [r14 + r11 + 6], 6 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rsi + 6], 7 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rax + 6], 8 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdx + 6], 9 + mov r11, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r11 + 6], 10 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rbx + 6], 11 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r15 + 6], 12 + pinsrb xmm3, byte ptr [r14 + r10 + 6], 13 + pinsrb xmm3, byte ptr [r14 + rdi + 6], 14 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r10 + 6], 15 + movdqa xmm2, xmmword ptr [rsp + 224] # 16-byte Reload + pinsrb xmm2, byte ptr [r14 + r9 + 7], 1 + mov rdi, r13 + pinsrb xmm2, byte ptr [r14 + r13 + 7], 2 + pinsrb xmm2, byte ptr [r14 + r8 + 7], 3 + pinsrb xmm2, byte ptr [r14 + r12 + 7], 4 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r9 + 7], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 7], 6 + mov r12, rcx + pinsrb xmm2, byte ptr [r14 + rsi + 7], 7 + pinsrb xmm2, byte ptr [r14 + rax + 7], 8 + pinsrb xmm2, byte ptr [r14 + rdx + 7], 9 + pinsrb xmm2, byte ptr [r14 + r11 + 7], 10 + mov r13, r11 + pinsrb xmm2, byte ptr [r14 + rbx + 7], 11 + pinsrb xmm2, byte ptr [r14 + r15 + 7], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rsi + 7], 13 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rcx + 7], 14 + pinsrb xmm2, byte ptr [r14 + r10 + 7], 15 + pcmpeqb xmm3, xmm9 + movdqa xmm1, xmmword ptr [rip + .LCPI1_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm1 + pcmpeqb xmm2, xmm9 + psllw xmm2, 7 + movdqa xmm1, xmmword ptr [rip + .LCPI1_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm2, xmm1 + por xmm2, xmm3 + movdqa xmm1, xmm2 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 21] + movd xmm2, edx + mov r10, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r10 + 9], 1 + pinsrb xmm10, byte ptr [r14 + rdi + 9], 2 + pinsrb xmm10, byte ptr [r14 + r8 + 9], 3 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rbx + 9], 4 + pinsrb xmm10, byte ptr [r14 + r9 + 9], 5 + pinsrb xmm10, byte ptr [r14 + r12 + 9], 6 + mov r11, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r11 + 9], 7 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdx + 9], 8 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdx + 9], 9 + pinsrb xmm10, byte ptr [r14 + r13 + 9], 10 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r13 + 9], 11 + pinsrb xmm10, byte ptr [r14 + r15 + 9], 12 + pinsrb xmm10, byte ptr [r14 + rsi + 9], 13 + pinsrb xmm10, byte ptr [r14 + rcx + 9], 14 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rcx + 9], 15 + por xmm1, xmm8 + movdqa xmmword ptr [rsp + 224], xmm1 # 16-byte Spill + pcmpeqb xmm10, xmm9 + movdqa xmm1, xmm10 + movdqa xmm8, xmm4 + pand xmm1, xmm4 + psubb xmm1, xmm10 + movzx edx, byte ptr [r14 + rax + 22] + movd xmm3, edx + movdqa xmm4, xmmword ptr [rsp + 288] # 16-byte Reload + pinsrb xmm4, byte ptr [r14 + r10 + 8], 1 + pinsrb xmm4, byte ptr [r14 + rdi + 8], 2 + pinsrb xmm4, byte ptr [r14 + r8 + 8], 3 + pinsrb xmm4, byte ptr [r14 + rbx + 8], 4 + pinsrb xmm4, byte ptr [r14 + r9 + 8], 5 + pinsrb xmm4, byte ptr [r14 + r12 + 8], 6 + mov rsi, r11 + pinsrb xmm4, byte ptr [r14 + r11 + 8], 7 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 8], 8 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r9 + 8], 9 + mov r11, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r11 + 8], 10 + pinsrb xmm4, byte ptr [r14 + r13 + 8], 11 + pinsrb xmm4, byte ptr [r14 + r15 + 8], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 8], 13 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r15 + 8], 14 + pinsrb xmm4, byte ptr [r14 + rcx + 8], 15 + mov rbx, rcx + pcmpeqb xmm4, xmm9 + pand xmm4, xmm8 + movdqa xmm10, xmmword ptr [rsp + 192] # 16-byte Reload + pinsrb xmm10, byte ptr [r14 + r10 + 10], 1 + pinsrb xmm10, byte ptr [r14 + rdi + 10], 2 + mov r10, rdi + pinsrb xmm10, byte ptr [r14 + r8 + 10], 3 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r8 + 10], 4 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rcx + 10], 5 + pinsrb xmm10, byte ptr [r14 + r12 + 10], 6 + pinsrb xmm10, byte ptr [r14 + rsi + 10], 7 + pinsrb xmm10, byte ptr [r14 + rax + 10], 8 + pinsrb xmm10, byte ptr [r14 + r9 + 10], 9 + pinsrb xmm10, byte ptr [r14 + r11 + 10], 10 + pinsrb xmm10, byte ptr [r14 + r13 + 10], 11 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r13 + 10], 12 + pinsrb xmm10, byte ptr [r14 + rdx + 10], 13 + pinsrb xmm10, byte ptr [r14 + r15 + 10], 14 + pinsrb xmm10, byte ptr [r14 + rbx + 10], 15 + pcmpeqb xmm10, xmm9 + pand xmm10, xmmword ptr [rip + .LCPI1_11] + por xmm10, xmm4 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 23] + movd xmm8, edx + por xmm10, xmm1 + movdqa xmmword ptr [rsp + 192], xmm10 # 16-byte Spill + movzx edx, byte ptr [r14 + rax + 24] + movd xmm10, edx + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdi + 11], 1 + pinsrb xmm11, byte ptr [r14 + r10 + 11], 2 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r10 + 11], 3 + pinsrb xmm11, byte ptr [r14 + r8 + 11], 4 + pinsrb xmm11, byte ptr [r14 + rcx + 11], 5 + mov rcx, r12 + pinsrb xmm11, byte ptr [r14 + r12 + 11], 6 + pinsrb xmm11, byte ptr [r14 + rsi + 11], 7 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r8 + 11], 8 + pinsrb xmm11, byte ptr [r14 + r9 + 11], 9 + pinsrb xmm11, byte ptr [r14 + r11 + 11], 10 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rbx + 11], 11 + mov r15, r13 + pinsrb xmm11, byte ptr [r14 + r13 + 11], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rax + 11], 13 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r12 + 11], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 15 + pinsrb xmm13, byte ptr [r14 + rdi + 12], 1 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rdi + 12], 2 + pinsrb xmm13, byte ptr [r14 + r10 + 12], 3 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + r13 + 12], 4 + mov rdi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rdi + 12], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 12], 6 + pinsrb xmm13, byte ptr [r14 + rsi + 12], 7 + pinsrb xmm13, byte ptr [r14 + r8 + 12], 8 + pinsrb xmm13, byte ptr [r14 + r9 + 12], 9 + pinsrb xmm13, byte ptr [r14 + r11 + 12], 10 + pinsrb xmm13, byte ptr [r14 + rbx + 12], 11 + pinsrb xmm13, byte ptr [r14 + r15 + 12], 12 + pinsrb xmm13, byte ptr [r14 + rax + 12], 13 + mov r10, rax + pinsrb xmm13, byte ptr [r14 + r12 + 12], 14 + pinsrb xmm13, byte ptr [r14 + rdx + 12], 15 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rax + 13], 1 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 2 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 3 + pinsrb xmm12, byte ptr [r14 + r13 + 13], 4 + pinsrb xmm12, byte ptr [r14 + rdi + 13], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 13], 6 + pinsrb xmm12, byte ptr [r14 + rsi + 13], 7 + pinsrb xmm12, byte ptr [r14 + r8 + 13], 8 + pinsrb xmm12, byte ptr [r14 + r9 + 13], 9 + pinsrb xmm12, byte ptr [r14 + r11 + 13], 10 + pinsrb xmm12, byte ptr [r14 + rbx + 13], 11 + pinsrb xmm12, byte ptr [r14 + r15 + 13], 12 + pinsrb xmm12, byte ptr [r14 + r10 + 13], 13 + pinsrb xmm12, byte ptr [r14 + r12 + 13], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 15 + pcmpeqb xmm11, xmm9 + pand xmm11, xmmword ptr [rip + .LCPI1_12] + pcmpeqb xmm13, xmm9 + pand xmm13, xmmword ptr [rip + .LCPI1_13] + por xmm13, xmm11 + mov rdi, qword ptr [rsp + 80] # 8-byte Reload + movzx edx, byte ptr [r14 + rdi + 25] + movd xmm1, edx + pcmpeqb xmm12, xmm9 + pand xmm12, xmmword ptr [rip + .LCPI1_14] + por xmm12, xmm13 + movzx edx, byte ptr [r14 + rdi + 26] + movd xmm11, edx + movdqa xmm4, xmmword ptr [rsp + 240] # 16-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 14], 1 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r12 + 14], 2 + mov rdi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdi + 14], 3 + mov r10, r13 + pinsrb xmm4, byte ptr [r14 + r13 + 14], 4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 14], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 14], 6 + pinsrb xmm4, byte ptr [r14 + rsi + 14], 7 + pinsrb xmm4, byte ptr [r14 + r8 + 14], 8 + pinsrb xmm4, byte ptr [r14 + r9 + 14], 9 + pinsrb xmm4, byte ptr [r14 + r11 + 14], 10 + pinsrb xmm4, byte ptr [r14 + rbx + 14], 11 + pinsrb xmm4, byte ptr [r14 + r15 + 14], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 14], 13 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r13 + 14], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 14], 15 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 1 + pinsrb xmm14, byte ptr [r14 + r12 + 15], 2 + pinsrb xmm14, byte ptr [r14 + rdi + 15], 3 + pinsrb xmm14, byte ptr [r14 + r10 + 15], 4 + pinsrb xmm14, byte ptr [r14 + rax + 15], 5 + pinsrb xmm14, byte ptr [r14 + rcx + 15], 6 + pinsrb xmm14, byte ptr [r14 + rsi + 15], 7 + pinsrb xmm14, byte ptr [r14 + r8 + 15], 8 + pinsrb xmm14, byte ptr [r14 + r9 + 15], 9 + pinsrb xmm14, byte ptr [r14 + r11 + 15], 10 + pinsrb xmm14, byte ptr [r14 + rbx + 15], 11 + pinsrb xmm14, byte ptr [r14 + r15 + 15], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 13 + pinsrb xmm14, byte ptr [r14 + r13 + 15], 14 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 15 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rdx + 16], 1 + pinsrb xmm15, byte ptr [r14 + r12 + 16], 2 + pinsrb xmm15, byte ptr [r14 + rdi + 16], 3 + pinsrb xmm15, byte ptr [r14 + r10 + 16], 4 + pinsrb xmm15, byte ptr [r14 + rax + 16], 5 + pinsrb xmm15, byte ptr [r14 + rcx + 16], 6 + pinsrb xmm15, byte ptr [r14 + rsi + 16], 7 + pinsrb xmm15, byte ptr [r14 + r8 + 16], 8 + pinsrb xmm15, byte ptr [r14 + r9 + 16], 9 + pinsrb xmm15, byte ptr [r14 + r11 + 16], 10 + pinsrb xmm15, byte ptr [r14 + rbx + 16], 11 + pinsrb xmm15, byte ptr [r14 + r15 + 16], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rdx + 16], 13 + pinsrb xmm15, byte ptr [r14 + r13 + 16], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 17], 1 + pinsrb xmm0, byte ptr [r14 + r12 + 17], 2 + pinsrb xmm0, byte ptr [r14 + rdi + 17], 3 + pinsrb xmm0, byte ptr [r14 + r10 + 17], 4 + pinsrb xmm0, byte ptr [r14 + rax + 17], 5 + mov r13, rax + pinsrb xmm0, byte ptr [r14 + rcx + 17], 6 + pinsrb xmm0, byte ptr [r14 + rsi + 17], 7 + pinsrb xmm0, byte ptr [r14 + r8 + 17], 8 + pinsrb xmm0, byte ptr [r14 + r9 + 17], 9 + pinsrb xmm0, byte ptr [r14 + r11 + 17], 10 + pinsrb xmm0, byte ptr [r14 + rbx + 17], 11 + pinsrb xmm0, byte ptr [r14 + r15 + 17], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 17], 13 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 17], 14 + por xmm12, xmmword ptr [rsp + 192] # 16-byte Folded Reload + mov r12, qword ptr [rsp + 80] # 8-byte Reload + movzx edx, byte ptr [r14 + r12 + 27] + movd xmm9, edx + movdqa xmm13, xmmword ptr [rsp + 208] # 16-byte Reload + pcmpeqb xmm4, xmm13 + pand xmm4, xmmword ptr [rip + .LCPI1_15] + pcmpeqb xmm14, xmm13 + psllw xmm14, 7 + pand xmm14, xmmword ptr [rip + .LCPI1_6] + por xmm14, xmm4 + movzx edx, byte ptr [r14 + r12 + 28] + movd xmm4, edx + mov r8, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r8 + 17], 15 + por xmm14, xmm12 + pcmpeqb xmm0, xmm13 + movdqa xmm13, xmm0 + movdqa xmm12, xmmword ptr [rip + .LCPI1_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm13, xmm12 + psubb xmm13, xmm0 + movdqa xmmword ptr [rsp + 192], xmm13 # 16-byte Spill + movzx edx, byte ptr [r14 + r12 + 29] + movd xmm13, edx + pinsrb xmm15, byte ptr [r14 + r8 + 16], 15 + movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload + pcmpeqb xmm15, xmm0 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r12 + 18], 1 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rdx + 18], 2 + pinsrb xmm5, byte ptr [r14 + rdi + 18], 3 + pinsrb xmm5, byte ptr [r14 + r10 + 18], 4 + pinsrb xmm5, byte ptr [r14 + r13 + 18], 5 + pinsrb xmm5, byte ptr [r14 + rcx + 18], 6 + pinsrb xmm5, byte ptr [r14 + rsi + 18], 7 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rdx + 18], 8 + pinsrb xmm5, byte ptr [r14 + r9 + 18], 9 + pinsrb xmm5, byte ptr [r14 + r11 + 18], 10 + pinsrb xmm5, byte ptr [r14 + rbx + 18], 11 + pinsrb xmm5, byte ptr [r14 + r15 + 18], 12 + pinsrb xmm5, byte ptr [r14 + rax + 18], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 18], 14 + pand xmm15, xmm12 + pinsrb xmm5, byte ptr [r14 + r8 + 18], 15 + pcmpeqb xmm5, xmm0 + pand xmm5, xmmword ptr [rip + .LCPI1_11] + por xmm5, xmm15 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 30] + movd xmm12, edx + pinsrb xmm7, byte ptr [r14 + r12 + 19], 1 + pinsrb xmm6, byte ptr [r14 + r12 + 20], 1 + pinsrb xmm2, byte ptr [r14 + r12 + 21], 1 + pinsrb xmm3, byte ptr [r14 + r12 + 22], 1 + pinsrb xmm8, byte ptr [r14 + r12 + 23], 1 + pinsrb xmm10, byte ptr [r14 + r12 + 24], 1 + pinsrb xmm1, byte ptr [r14 + r12 + 25], 1 + pinsrb xmm11, byte ptr [r14 + r12 + 26], 1 + pinsrb xmm9, byte ptr [r14 + r12 + 27], 1 + pinsrb xmm4, byte ptr [r14 + r12 + 28], 1 + pinsrb xmm13, byte ptr [r14 + r12 + 29], 1 + pinsrb xmm12, byte ptr [r14 + r12 + 30], 1 + movzx edx, byte ptr [r14 + rax + 31] + movd xmm0, edx + pinsrb xmm0, byte ptr [r14 + r12 + 31], 1 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdx + 19], 2 + pinsrb xmm6, byte ptr [r14 + rdx + 20], 2 + pinsrb xmm2, byte ptr [r14 + rdx + 21], 2 + pinsrb xmm3, byte ptr [r14 + rdx + 22], 2 + pinsrb xmm8, byte ptr [r14 + rdx + 23], 2 + pinsrb xmm10, byte ptr [r14 + rdx + 24], 2 + pinsrb xmm1, byte ptr [r14 + rdx + 25], 2 + pinsrb xmm11, byte ptr [r14 + rdx + 26], 2 + pinsrb xmm9, byte ptr [r14 + rdx + 27], 2 + pinsrb xmm4, byte ptr [r14 + rdx + 28], 2 + pinsrb xmm13, byte ptr [r14 + rdx + 29], 2 + pinsrb xmm12, byte ptr [r14 + rdx + 30], 2 + pinsrb xmm0, byte ptr [r14 + rdx + 31], 2 + pinsrb xmm7, byte ptr [r14 + rdi + 19], 3 + pinsrb xmm7, byte ptr [r14 + r10 + 19], 4 + pinsrb xmm7, byte ptr [r14 + r13 + 19], 5 + pinsrb xmm7, byte ptr [r14 + rcx + 19], 6 + pinsrb xmm7, byte ptr [r14 + rsi + 19], 7 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + r12 + 19], 8 + pinsrb xmm7, byte ptr [r14 + r9 + 19], 9 + pinsrb xmm7, byte ptr [r14 + r11 + 19], 10 + pinsrb xmm7, byte ptr [r14 + rbx + 19], 11 + pinsrb xmm7, byte ptr [r14 + r15 + 19], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdx + 19], 13 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rax + 19], 14 + pinsrb xmm7, byte ptr [r14 + r8 + 19], 15 + pinsrb xmm6, byte ptr [r14 + rdi + 20], 3 + pinsrb xmm6, byte ptr [r14 + r10 + 20], 4 + pinsrb xmm6, byte ptr [r14 + r13 + 20], 5 + pinsrb xmm6, byte ptr [r14 + rcx + 20], 6 + pinsrb xmm6, byte ptr [r14 + rsi + 20], 7 + pinsrb xmm6, byte ptr [r14 + r12 + 20], 8 + pinsrb xmm6, byte ptr [r14 + r9 + 20], 9 + pinsrb xmm6, byte ptr [r14 + r11 + 20], 10 + pinsrb xmm6, byte ptr [r14 + rbx + 20], 11 + pinsrb xmm6, byte ptr [r14 + r15 + 20], 12 + pinsrb xmm6, byte ptr [r14 + rdx + 20], 13 + pinsrb xmm6, byte ptr [r14 + rax + 20], 14 + por xmm5, xmmword ptr [rsp + 192] # 16-byte Folded Reload + pinsrb xmm6, byte ptr [r14 + r8 + 20], 15 + movdqa xmm15, xmmword ptr [rsp + 208] # 16-byte Reload + pcmpeqb xmm7, xmm15 + pand xmm7, xmmword ptr [rip + .LCPI1_12] + pcmpeqb xmm6, xmm15 + pand xmm6, xmmword ptr [rip + .LCPI1_13] + por xmm6, xmm7 + pinsrb xmm2, byte ptr [r14 + rdi + 21], 3 + pinsrb xmm2, byte ptr [r14 + r10 + 21], 4 + pinsrb xmm2, byte ptr [r14 + r13 + 21], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 21], 6 + pinsrb xmm2, byte ptr [r14 + rsi + 21], 7 + pinsrb xmm2, byte ptr [r14 + r12 + 21], 8 + pinsrb xmm2, byte ptr [r14 + r9 + 21], 9 + pinsrb xmm2, byte ptr [r14 + r11 + 21], 10 + pinsrb xmm2, byte ptr [r14 + rbx + 21], 11 + pinsrb xmm2, byte ptr [r14 + r15 + 21], 12 + pinsrb xmm2, byte ptr [r14 + rdx + 21], 13 + pinsrb xmm2, byte ptr [r14 + rax + 21], 14 + pinsrb xmm2, byte ptr [r14 + r8 + 21], 15 + pcmpeqb xmm2, xmm15 + movdqa xmm7, xmmword ptr [rip + .LCPI1_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm2, xmm7 + por xmm2, xmm6 + por xmm2, xmm5 + pinsrb xmm3, byte ptr [r14 + rdi + 22], 3 + pinsrb xmm3, byte ptr [r14 + r10 + 22], 4 + pinsrb xmm3, byte ptr [r14 + r13 + 22], 5 + pinsrb xmm3, byte ptr [r14 + rcx + 22], 6 + pinsrb xmm3, byte ptr [r14 + rsi + 22], 7 + pinsrb xmm3, byte ptr [r14 + r12 + 22], 8 + pinsrb xmm3, byte ptr [r14 + r9 + 22], 9 + pinsrb xmm3, byte ptr [r14 + r11 + 22], 10 + pinsrb xmm3, byte ptr [r14 + rbx + 22], 11 + pinsrb xmm3, byte ptr [r14 + r15 + 22], 12 + pinsrb xmm3, byte ptr [r14 + rdx + 22], 13 + pinsrb xmm3, byte ptr [r14 + rax + 22], 14 + pinsrb xmm3, byte ptr [r14 + r8 + 22], 15 + pinsrb xmm8, byte ptr [r14 + rdi + 23], 3 + pinsrb xmm8, byte ptr [r14 + r10 + 23], 4 + pinsrb xmm8, byte ptr [r14 + r13 + 23], 5 + pinsrb xmm8, byte ptr [r14 + rcx + 23], 6 + pinsrb xmm8, byte ptr [r14 + rsi + 23], 7 + pinsrb xmm8, byte ptr [r14 + r12 + 23], 8 + pinsrb xmm8, byte ptr [r14 + r9 + 23], 9 + pinsrb xmm8, byte ptr [r14 + r11 + 23], 10 + pinsrb xmm8, byte ptr [r14 + rbx + 23], 11 + pinsrb xmm8, byte ptr [r14 + r15 + 23], 12 + pinsrb xmm8, byte ptr [r14 + rdx + 23], 13 + pinsrb xmm8, byte ptr [r14 + rax + 23], 14 + pinsrb xmm8, byte ptr [r14 + r8 + 23], 15 + pcmpeqb xmm3, xmm15 + movdqa xmm5, xmmword ptr [rip + .LCPI1_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm5 + pcmpeqb xmm8, xmm15 + psllw xmm8, 7 + movdqa xmm6, xmmword ptr [rip + .LCPI1_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm8, xmm6 + por xmm8, xmm3 + pinsrb xmm1, byte ptr [r14 + rdi + 25], 3 + pinsrb xmm1, byte ptr [r14 + r10 + 25], 4 + pinsrb xmm1, byte ptr [r14 + r13 + 25], 5 + pinsrb xmm1, byte ptr [r14 + rcx + 25], 6 + pinsrb xmm1, byte ptr [r14 + rsi + 25], 7 + pinsrb xmm1, byte ptr [r14 + r12 + 25], 8 + pinsrb xmm1, byte ptr [r14 + r9 + 25], 9 + pinsrb xmm1, byte ptr [r14 + r11 + 25], 10 + pinsrb xmm1, byte ptr [r14 + rbx + 25], 11 + pinsrb xmm1, byte ptr [r14 + r15 + 25], 12 + pinsrb xmm1, byte ptr [r14 + rdx + 25], 13 + pinsrb xmm1, byte ptr [r14 + rax + 25], 14 + pinsrb xmm1, byte ptr [r14 + r8 + 25], 15 + por xmm8, xmm2 + pcmpeqb xmm1, xmm15 + movdqa xmm2, xmm1 + movdqa xmm3, xmmword ptr [rip + .LCPI1_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm2, xmm3 + psubb xmm2, xmm1 + pinsrb xmm10, byte ptr [r14 + rdi + 24], 3 + pinsrb xmm10, byte ptr [r14 + r10 + 24], 4 + pinsrb xmm10, byte ptr [r14 + r13 + 24], 5 + pinsrb xmm10, byte ptr [r14 + rcx + 24], 6 + pinsrb xmm10, byte ptr [r14 + rsi + 24], 7 + pinsrb xmm10, byte ptr [r14 + r12 + 24], 8 + pinsrb xmm10, byte ptr [r14 + r9 + 24], 9 + pinsrb xmm10, byte ptr [r14 + r11 + 24], 10 + pinsrb xmm10, byte ptr [r14 + rbx + 24], 11 + pinsrb xmm10, byte ptr [r14 + r15 + 24], 12 + pinsrb xmm10, byte ptr [r14 + rdx + 24], 13 + pinsrb xmm10, byte ptr [r14 + rax + 24], 14 + pinsrb xmm10, byte ptr [r14 + r8 + 24], 15 + pcmpeqb xmm10, xmm15 + pand xmm10, xmm3 + pinsrb xmm11, byte ptr [r14 + rdi + 26], 3 + pinsrb xmm11, byte ptr [r14 + r10 + 26], 4 + pinsrb xmm11, byte ptr [r14 + r13 + 26], 5 + pinsrb xmm11, byte ptr [r14 + rcx + 26], 6 + pinsrb xmm11, byte ptr [r14 + rsi + 26], 7 + pinsrb xmm11, byte ptr [r14 + r12 + 26], 8 + pinsrb xmm11, byte ptr [r14 + r9 + 26], 9 + pinsrb xmm11, byte ptr [r14 + r11 + 26], 10 + pinsrb xmm11, byte ptr [r14 + rbx + 26], 11 + pinsrb xmm11, byte ptr [r14 + r15 + 26], 12 + pinsrb xmm11, byte ptr [r14 + rdx + 26], 13 + pinsrb xmm11, byte ptr [r14 + rax + 26], 14 + pinsrb xmm11, byte ptr [r14 + r8 + 26], 15 + pcmpeqb xmm11, xmm15 + pand xmm11, xmmword ptr [rip + .LCPI1_11] + por xmm11, xmm10 + por xmm11, xmm2 + pinsrb xmm9, byte ptr [r14 + rdi + 27], 3 + pinsrb xmm9, byte ptr [r14 + r10 + 27], 4 + pinsrb xmm9, byte ptr [r14 + r13 + 27], 5 + pinsrb xmm9, byte ptr [r14 + rcx + 27], 6 + pinsrb xmm9, byte ptr [r14 + rsi + 27], 7 + pinsrb xmm9, byte ptr [r14 + r12 + 27], 8 + pinsrb xmm9, byte ptr [r14 + r9 + 27], 9 + pinsrb xmm9, byte ptr [r14 + r11 + 27], 10 + pinsrb xmm9, byte ptr [r14 + rbx + 27], 11 + pinsrb xmm9, byte ptr [r14 + r15 + 27], 12 + pinsrb xmm9, byte ptr [r14 + rdx + 27], 13 + pinsrb xmm9, byte ptr [r14 + rax + 27], 14 + pinsrb xmm9, byte ptr [r14 + r8 + 27], 15 + pinsrb xmm4, byte ptr [r14 + rdi + 28], 3 + pinsrb xmm4, byte ptr [r14 + r10 + 28], 4 + pinsrb xmm4, byte ptr [r14 + r13 + 28], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 28], 6 + pinsrb xmm4, byte ptr [r14 + rsi + 28], 7 + pinsrb xmm4, byte ptr [r14 + r12 + 28], 8 + pinsrb xmm4, byte ptr [r14 + r9 + 28], 9 + pinsrb xmm4, byte ptr [r14 + r11 + 28], 10 + pinsrb xmm4, byte ptr [r14 + rbx + 28], 11 + pinsrb xmm4, byte ptr [r14 + r15 + 28], 12 + pinsrb xmm4, byte ptr [r14 + rdx + 28], 13 + pinsrb xmm4, byte ptr [r14 + rax + 28], 14 + pinsrb xmm4, byte ptr [r14 + r8 + 28], 15 + pinsrb xmm13, byte ptr [r14 + rdi + 29], 3 + pinsrb xmm13, byte ptr [r14 + r10 + 29], 4 + pinsrb xmm13, byte ptr [r14 + r13 + 29], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 29], 6 + pinsrb xmm13, byte ptr [r14 + rsi + 29], 7 + pinsrb xmm13, byte ptr [r14 + r12 + 29], 8 + pinsrb xmm13, byte ptr [r14 + r9 + 29], 9 + pinsrb xmm13, byte ptr [r14 + r11 + 29], 10 + pinsrb xmm13, byte ptr [r14 + rbx + 29], 11 + pinsrb xmm13, byte ptr [r14 + r15 + 29], 12 + pinsrb xmm13, byte ptr [r14 + rdx + 29], 13 + pinsrb xmm13, byte ptr [r14 + rax + 29], 14 + movdqa xmm1, xmm15 + pcmpeqb xmm9, xmm15 + pand xmm9, xmmword ptr [rip + .LCPI1_12] + pcmpeqb xmm4, xmm15 + pand xmm4, xmmword ptr [rip + .LCPI1_13] + por xmm4, xmm9 + pinsrb xmm13, byte ptr [r14 + r8 + 29], 15 + pcmpeqb xmm13, xmm15 + pand xmm13, xmm7 + por xmm13, xmm4 + pinsrb xmm12, byte ptr [r14 + rdi + 30], 3 + pinsrb xmm0, byte ptr [r14 + rdi + 31], 3 + pinsrb xmm12, byte ptr [r14 + r10 + 30], 4 + pinsrb xmm0, byte ptr [r14 + r10 + 31], 4 + pinsrb xmm12, byte ptr [r14 + r13 + 30], 5 + pinsrb xmm0, byte ptr [r14 + r13 + 31], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 30], 6 + pinsrb xmm0, byte ptr [r14 + rcx + 31], 6 + pinsrb xmm12, byte ptr [r14 + rsi + 30], 7 + pinsrb xmm0, byte ptr [r14 + rsi + 31], 7 + pinsrb xmm12, byte ptr [r14 + r12 + 30], 8 + pinsrb xmm0, byte ptr [r14 + r12 + 31], 8 + pinsrb xmm12, byte ptr [r14 + r9 + 30], 9 + pinsrb xmm0, byte ptr [r14 + r9 + 31], 9 + pinsrb xmm12, byte ptr [r14 + r11 + 30], 10 + pinsrb xmm0, byte ptr [r14 + r11 + 31], 10 + pinsrb xmm12, byte ptr [r14 + rbx + 30], 11 + pinsrb xmm0, byte ptr [r14 + rbx + 31], 11 + pinsrb xmm12, byte ptr [r14 + r15 + 30], 12 + pinsrb xmm0, byte ptr [r14 + r15 + 31], 12 + pinsrb xmm12, byte ptr [r14 + rdx + 30], 13 + pinsrb xmm0, byte ptr [r14 + rdx + 31], 13 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rax + 30], 14 + pinsrb xmm0, byte ptr [r14 + rax + 31], 14 + pinsrb xmm12, byte ptr [r14 + r8 + 30], 15 + pinsrb xmm0, byte ptr [r14 + r8 + 31], 15 + por xmm13, xmm11 + pcmpeqb xmm12, xmm15 + pand xmm12, xmm5 + pcmpeqb xmm0, xmm15 + psllw xmm0, 7 + pand xmm0, xmm6 + por xmm0, xmm12 + por xmm0, xmm13 + movdqa xmm1, xmm8 + punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + movdqa xmm4, xmmword ptr [rsp + 224] # 16-byte Reload + movdqa xmm2, xmm4 + punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] + movdqa xmm3, xmm2 + punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] + punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] + punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] + punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] + movdqa xmm0, xmm4 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + movdqu xmmword ptr [rdx + 4*rcx + 48], xmm4 + movdqu xmmword ptr [rdx + 4*rcx + 32], xmm0 + movdqu xmmword ptr [rdx + 4*rcx + 16], xmm2 + movdqu xmmword ptr [rdx + 4*rcx], xmm3 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 152] # 8-byte Folded Reload + jne .LBB1_74 +# %bb.75: + mov rcx, qword ptr [rsp + 280] # 8-byte Reload + cmp rcx, qword ptr [rsp + 152] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r11b, byte ptr [rsp + 8] # 1-byte Reload + mov rsi, qword ptr [rsp + 304] # 8-byte Reload + jne .LBB1_76 + jmp .LBB1_79 +.Lfunc_end1: + .size comparison_equal_arr_scalar_sse4, .Lfunc_end1-comparison_equal_arr_scalar_sse4 + # -- End function + .section .rodata.cst16,"aM",@progbits,16 + .p2align 4 # -- Begin function comparison_equal_scalar_arr_sse4 +.LCPI2_0: + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI2_1: + .zero 16,252 +.LCPI2_2: + .zero 16,248 +.LCPI2_3: + .zero 16,240 +.LCPI2_4: + .zero 16,224 +.LCPI2_5: + .zero 16,192 +.LCPI2_6: + .zero 16,128 +.LCPI2_7: + .byte 0 # 0x0 + .byte 8 # 0x8 + .byte 1 # 0x1 + .byte 9 # 0x9 + .byte 2 # 0x2 + .byte 10 # 0xa + .byte 3 # 0x3 + .byte 11 # 0xb + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf +.LCPI2_8: + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI2_9: + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI2_10: + .zero 16,1 +.LCPI2_11: + .zero 16,4 +.LCPI2_12: + .zero 16,8 +.LCPI2_13: + .zero 16,16 +.LCPI2_14: + .zero 16,32 +.LCPI2_15: + .zero 16,64 + .text + .globl comparison_equal_scalar_arr_sse4 .p2align 4, 0x90 -.LBB2_50: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] - lea rdx, [rdx + 8] + .type comparison_equal_scalar_arr_sse4,@function +comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 +# %bb.0: + push rbp + mov rbp, rsp + push r15 + push r14 + push r13 + push r12 + push rbx + and rsp, -16 + sub rsp, 304 + # kill: def $r9d killed $r9d def $r9 + mov r15, r8 + mov r12, rcx + cmp edi, 6 + jg .LBB2_19 +# %bb.1: + cmp edi, 3 + jle .LBB2_36 +# %bb.2: + cmp edi, 4 + je .LBB2_59 +# %bb.3: + cmp edi, 5 + je .LBB2_73 +# %bb.4: + cmp edi, 6 + jne .LBB2_200 +# %bb.5: + mov r13d, dword ptr [rsi] + lea ecx, [r9 + 7] + test r9d, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB2_11 +# %bb.6: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_9 +# %bb.7: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rdx + .p2align 4, 0x90 +.LBB2_8: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r13d, dword ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r9 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov esi, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r9 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_50 -# %bb.51: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_52: - sar r11, 5 - cmp r10, 32 - jl .LBB2_56 -# %bb.53: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill + shl esi, cl + and sil, bl + xor sil, r9b + mov byte ptr [r12 + rax], sil + add rdi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_8 +.LBB2_9: + sub r15, r8 + je .LBB2_200 +# %bb.10: + add r12, 1 +.LBB2_11: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_15 +# %bb.12: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_54: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 8] - sete r10b - cmp r13, qword ptr [rdx + 16] - sete r14b - cmp r13, qword ptr [rdx + 24] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 32] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 40] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 48] - sete bl - cmp r13, qword ptr [rdx + 56] - sete dil - cmp r13, qword ptr [rdx + 64] - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 72] - sete sil - cmp r13, qword ptr [rdx + 80] - sete r8b - cmp r13, qword ptr [rdx + 88] +.LBB2_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + cmp r13d, dword ptr [rdx] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 4] sete r9b - cmp r13, qword ptr [rdx + 96] + cmp r13d, dword ptr [rdx + 8] + sete r14b + cmp r13d, dword ptr [rdx + 12] + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 16] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 20] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 24] + sete al + cmp r13d, dword ptr [rdx + 28] sete r11b - cmp r13, qword ptr [rdx + 104] + cmp r13d, dword ptr [rdx + 32] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 36] + sete sil + cmp r13d, dword ptr [rdx + 40] + sete dil + cmp r13d, dword ptr [rdx + 44] + sete r8b + cmp r13d, dword ptr [rdx + 48] + sete r10b + cmp r13d, dword ptr [rdx + 52] sete r12b - cmp r13, qword ptr [rdx + 112] + cmp r13d, dword ptr [rdx + 56] sete byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 120] - sete al - cmp r13, qword ptr [rdx + 128] + cmp r13d, dword ptr [rdx + 60] + sete bl + cmp r13d, dword ptr [rdx + 64] + sete byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 68] + sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 72] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 76] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 80] sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 136] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 144] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 152] + cmp r13d, dword ptr [rdx + 84] sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 160] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 168] - sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 176] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 184] + cmp r13d, dword ptr [rdx + 88] + sete byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 92] sete r15b - cmp r13, qword ptr [rdx + 192] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 200] + cmp r13d, dword ptr [rdx + 96] sete byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 208] - sete byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 216] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 224] + cmp r13d, dword ptr [rdx + 100] sete byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 232] - sete byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 240] + cmp r13d, dword ptr [rdx + 104] + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 108] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 112] sete byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 248] + cmp r13d, dword ptr [rdx + 116] + sete byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 120] + sete byte ptr [rsp] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 124] sete cl - add r10b, r10b - add r10b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl dil, 7 - or dil, bl + add r9b, r9b + add r9b, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b + or r14b, r9b add sil, sil - add sil, byte ptr [rsp + 208] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 3 - or bl, r14b - mov r10d, ebx - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 4 - or bl, r10b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r11b, 4 - or r11b, r9b + add sil, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r9d, eax + shl dil, 2 + or dil, sil + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 4 + or al, r9b + mov esi, eax + shl r8b, 3 + or r8b, dil + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 5 + or al, sil + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - mov rsi, qword ptr [rsp] # 8-byte Reload - movzx r8d, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r8b, 6 - shl al, 7 - or al, r8b - or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov r8d, ebx - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 2 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 3 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl bl, 5 - or bl, r8b - mov byte ptr [rsi], dil - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 + or r12b, r10b + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 6 + shl bl, 7 + or bl, sil + or r11b, al + or bl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 5 + or al, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], al - or r15b, bl - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], bl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload + add al, byte ptr [rsp + 32] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax @@ -10659,51 +10106,49 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], cl - add rdx, 256 - add rsi, 4 - mov qword ptr [rsp], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_54 -# %bb.55: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB2_56: - shl r11, 5 - cmp r11, r10 - jge .LBB2_177 -# %bb.57: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - je .LBB2_117 -# %bb.58: + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], cl + add rdx, 128 + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB2_13 +# %bb.14: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB2_15: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_200 +# %bb.16: + or rax, 1 + cmp r15, rax + je .LBB2_131 +# %bb.17: mov r10, r8 and r10, -2 xor edi, edi - mov r11, qword ptr [rsp] # 8-byte Reload .p2align 4, 0x90 -.LBB2_59: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] +.LBB2_18: # =>This Inner Loop Header: Depth=1 + cmp r13d, dword ptr [rdx] sete al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -10711,10 +10156,10 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r11 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 - cmp r13, qword ptr [rdx + 8] - lea rdx, [rdx + 16] + cmp r13d, dword ptr [rdx + 4] + lea rdx, [rdx + 8] sete r9b neg r9b xor r9b, bl @@ -10723,441 +10168,603 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl al, cl and al, r9b xor al, bl - mov byte ptr [r11 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB2_59 - jmp .LBB2_168 -.LBB2_60: - mov r14b, byte ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jne .LBB2_18 + jmp .LBB2_177 +.LBB2_19: + cmp edi, 8 + jle .LBB2_43 +# %bb.20: + cmp edi, 9 + je .LBB2_87 +# %bb.21: + cmp edi, 11 + je .LBB2_100 +# %bb.22: + cmp edi, 12 + jne .LBB2_200 +# %bb.23: + mov r14, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_64 -# %bb.61: - movsxd rax, r9d - mov r11, qword ptr [rsp] # 8-byte Reload + je .LBB2_29 +# %bb.24: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_27 +# %bb.25: + movsxd rsi, r9d + movq xmm0, r14 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_62: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rdx] - lea rdx, [rdx + 1] +.LBB2_26: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rcx] + lea rdx, [rcx + 8] + setnp cl sete bl + and bl, cl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_62 -# %bb.63: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_64: - sar r15, 5 - cmp r10, 32 - jl .LBB2_134 -# %bb.65: - cmp r15, 16 - mov byte ptr [rsp + 8], r14b # 1-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 232], r15 # 8-byte Spill - jb .LBB2_68 -# %bb.66: - mov rax, r15 - shl rax, 5 - add rax, rdx - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB2_185 -# %bb.67: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] - cmp rdx, rax - jae .LBB2_185 -.LBB2_68: - xor eax, eax - mov qword ptr [rsp + 224], rax # 8-byte Spill - mov rsi, rdx - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 104], rax # 8-byte Spill -.LBB2_69: - sub r15, qword ptr [rsp + 224] # 8-byte Folded Reload - mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_26 +.LBB2_27: + sub r15, r8 + je .LBB2_200 +# %bb.28: + add r12, 1 +.LBB2_29: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_33 +# %bb.30: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 256], r14 # 8-byte Spill + movq xmm0, r14 + mov qword ptr [rsp + 216], rax # 8-byte Spill + mov qword ptr [rsp + 272], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_70: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp r14b, byte ptr [rsi] - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 1] - sete dil - cmp r14b, byte ptr [rsi + 2] - sete r11b - cmp r14b, byte ptr [rsi + 3] - sete r15b - cmp r14b, byte ptr [rsi + 4] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 5] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 6] - sete bl - cmp r14b, byte ptr [rsi + 7] +.LBB2_31: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + ucomisd xmm0, qword ptr [rdx] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 24], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 8] + setnp al sete r13b - cmp r14b, byte ptr [rsi + 8] - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp r14b, byte ptr [rsi + 9] - sete sil - cmp r14b, byte ptr [rcx + 10] + and r13b, al + ucomisd xmm0, qword ptr [rdx + 16] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 40], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 24] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 8], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 32] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 32], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 40] + setnp al + sete r12b + and r12b, al + ucomisd xmm0, qword ptr [rdx + 48] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 56], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 56] + setnp al + sete cl + and cl, al + mov byte ptr [rsp], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 64] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 48], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 72] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 96], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 80] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 64], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 88] + setnp al + sete bl + and bl, al + ucomisd xmm0, qword ptr [rdx + 96] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 16], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 104] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 88], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 112] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 80], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 120] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 120], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 128] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 72], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 136] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 112], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 144] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 104], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 152] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 176], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 160] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 160], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 168] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 136], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 176] + setnp al + sete r15b + and r15b, al + ucomisd xmm0, qword ptr [rdx + 184] + setnp al sete r8b - cmp r14b, byte ptr [rcx + 11] + and r8b, al + ucomisd xmm0, qword ptr [rdx + 192] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 192], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 200] + setnp al + sete r11b + and r11b, al + ucomisd xmm0, qword ptr [rdx + 208] + setnp al + sete r10b + and r10b, al + ucomisd xmm0, qword ptr [rdx + 216] + setnp al sete r9b - cmp r14b, byte ptr [rcx + 12] - sete r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 13] - sete r12b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 14] - sete byte ptr [rsp + 176] # 1-byte Folded Spill + and r9b, al + ucomisd xmm0, qword ptr [rdx + 224] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 224], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 232] + setnp al + sete cl + and cl, al + mov byte ptr [rsp + 144], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 240] + setnp al + sete dil + and dil, al + ucomisd xmm0, qword ptr [rdx + 248] + setnp al + sete sil + and sil, al + add r13b, r13b + add r13b, byte ptr [rsp + 24] # 1-byte Folded Reload + mov eax, r13d + shl r12b, 5 + movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload + shl r13b, 6 + or r13b, r12b + movzx r12d, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + shl al, 7 + or al, r13b + mov byte ptr [rsp], al # 1-byte Spill + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 15] - sete al - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 16] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 17] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 18] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 19] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 20] - sete byte ptr [rsp + 72] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 21] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 22] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 23] - sete r10b - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 24] - sete byte ptr [rsp + 32] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 25] - sete byte ptr [rsp + 56] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 26] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 27] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 28] - sete byte ptr [rsp + 48] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 29] - sete byte ptr [rsp + 16] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 30] - sete byte ptr [rsp] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 31] - sete dl - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl r13b, 7 - or r13b, bl - shl r11b, 2 - or r11b, dil - add sil, sil - add sil, byte ptr [rsp + 208] # 1-byte Folded Reload - shl r15b, 3 - or r15b, r11b - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 4 - or bl, r15b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r14b, 4 - or r14b, r9b - shl r12b, 5 - or r12b, r14b - movzx r14d, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload - shl sil, 6 - shl al, 7 - or al, sil - or r13b, bl + shl al, 3 or al, r12b - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 120] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 2 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - mov byte ptr [rdi], r13b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl sil, 6 - shl r10b, 7 - or r10b, sil - mov byte ptr [rdi + 1], al - or r10b, bl - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax + or bl, cl + movzx r13d, byte ptr [rsp + 32] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 + shl al, 4 or al, bl - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, al - mov byte ptr [rdi + 2], r10b - mov byte ptr [rdi + 3], dl - lea rsi, [rcx + 32] - add rdi, 4 - mov qword ptr [rsp + 104], rdi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_70 -# %bb.71: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r15, qword ptr [rsp + 232] # 8-byte Reload - jmp .LBB2_135 -.LBB2_72: - mov r13d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + mov byte ptr [rsp + 16], al # 1-byte Spill + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 5 + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 6 + or al, cl + mov ecx, eax + movzx r14d, byte ptr [rsp + 120] # 1-byte Folded Reload + shl r14b, 7 + or r14b, al + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl bl, 2 + or bl, cl + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload + shl cl, 3 + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 4 + or cl, bl + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + or al, r13b + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl bl, 5 + shl r15b, 6 + or r15b, bl + or r14b, byte ptr [rsp + 16] # 1-byte Folded Reload + shl r8b, 7 + or r8b, r15b + or r8b, cl + add r11b, r11b + add r11b, byte ptr [rsp + 192] # 1-byte Folded Reload + shl r10b, 2 + or r10b, r11b + shl r9b, 3 + or r9b, r10b + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl cl, 4 + or cl, r9b + mov ebx, ecx + mov byte ptr [r12], al + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 5 + shl dil, 6 + or dil, cl + mov byte ptr [r12 + 1], r14b + shl sil, 7 + or sil, dil + or sil, bl + mov byte ptr [r12 + 2], r8b + mov byte ptr [r12 + 3], sil + add rdx, 256 + add r12, 4 + add qword ptr [rsp + 272], -1 # 8-byte Folded Spill + jne .LBB2_31 +# %bb.32: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14, qword ptr [rsp + 256] # 8-byte Reload + mov rax, qword ptr [rsp + 216] # 8-byte Reload +.LBB2_33: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_200 +# %bb.34: + movq xmm0, r14 + or rax, 1 + cmp r15, rax + jne .LBB2_186 +# %bb.35: + xor edi, edi + jmp .LBB2_188 +.LBB2_36: + cmp edi, 2 + je .LBB2_114 +# %bb.37: + cmp edi, 3 + jne .LBB2_200 +# %bb.38: + mov r11b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_76 -# %bb.73: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload + je .LBB2_132 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_147 +# %bb.40: + movsxd rsi, r9d + mov r13, r8 .p2align 4, 0x90 -.LBB2_74: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - lea rdx, [rdx + 4] - sete bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r9 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi +.LBB2_41: # =>This Inner Loop Header: Depth=1 + lea r14, [rdx + 1] + cmp r11b, byte ptr [rdx] + sete dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov rax, r12 + movzx r9d, byte ptr [r12 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r9 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_74 -# %bb.75: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_76: - sar r11, 5 - cmp r10, 32 - jl .LBB2_80 -# %bb.77: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill + and dil, dl + xor dil, r9b + mov byte ptr [r12 + rbx], dil + add rsi, 1 + mov rdx, r14 + add r13, -1 + jne .LBB2_41 +# %bb.42: + sub r15, r8 + jne .LBB2_148 + jmp .LBB2_200 +.LBB2_43: + cmp edi, 7 + je .LBB2_119 +# %bb.44: + cmp edi, 8 + jne .LBB2_200 +# %bb.45: + mov r13, qword ptr [rsi] + lea ecx, [r9 + 7] + test r9d, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB2_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_49 +# %bb.47: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_78: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 4] - sete r10b - cmp r13d, dword ptr [rdx + 8] +.LBB2_48: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r13, qword ptr [rcx] + sete bl + neg bl + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov esi, 1 + # kill: def $cl killed $cl killed $ecx + shl esi, cl + and sil, bl + xor sil, r9b + mov byte ptr [r12 + rax], sil + add rdi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_48 +.LBB2_49: + sub r15, r8 + je .LBB2_200 +# %bb.50: + add r12, 1 +.LBB2_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_55 +# %bb.52: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB2_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + cmp r13, qword ptr [rdx] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 8] + sete r9b + cmp r13, qword ptr [rdx + 16] sete r14b - cmp r13d, dword ptr [rdx + 12] + cmp r13, qword ptr [rdx + 24] + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 32] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 40] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 48] + sete al + cmp r13, qword ptr [rdx + 56] + sete r11b + cmp r13, qword ptr [rdx + 64] sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 16] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 20] - sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 24] - sete bl - cmp r13d, dword ptr [rdx + 28] - sete dil - cmp r13d, dword ptr [rdx + 32] - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 36] + cmp r13, qword ptr [rdx + 72] sete sil - cmp r13d, dword ptr [rdx + 40] + cmp r13, qword ptr [rdx + 80] + sete dil + cmp r13, qword ptr [rdx + 88] sete r8b - cmp r13d, dword ptr [rdx + 44] - sete r9b - cmp r13d, dword ptr [rdx + 48] - sete r11b - cmp r13d, dword ptr [rdx + 52] + cmp r13, qword ptr [rdx + 96] + sete r10b + cmp r13, qword ptr [rdx + 104] sete r12b - cmp r13d, dword ptr [rdx + 56] + cmp r13, qword ptr [rdx + 112] sete byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 60] - sete al - cmp r13d, dword ptr [rdx + 64] + cmp r13, qword ptr [rdx + 120] + sete bl + cmp r13, qword ptr [rdx + 128] + sete byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 136] + sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 144] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 152] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 160] sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 68] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 72] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 76] + cmp r13, qword ptr [rdx + 168] sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 80] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 84] - sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 88] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 92] + cmp r13, qword ptr [rdx + 176] + sete byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 184] sete r15b - cmp r13d, dword ptr [rdx + 96] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 100] + cmp r13, qword ptr [rdx + 192] sete byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 104] - sete byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 108] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 112] + cmp r13, qword ptr [rdx + 200] sete byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 116] - sete byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 120] + cmp r13, qword ptr [rdx + 208] + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 216] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 224] sete byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 124] + cmp r13, qword ptr [rdx + 232] + sete byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 240] + sete byte ptr [rsp] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 248] sete cl - add r10b, r10b - add r10b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl dil, 7 - or dil, bl + add r9b, r9b + add r9b, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b + or r14b, r9b add sil, sil - add sil, byte ptr [rsp + 208] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 3 - or bl, r14b - mov r10d, ebx - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 4 - or bl, r10b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r11b, 4 - or r11b, r9b + add sil, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r9d, eax + shl dil, 2 + or dil, sil + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 4 + or al, r9b + mov esi, eax + shl r8b, 3 + or r8b, dil + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 5 + or al, sil + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - mov rsi, qword ptr [rsp] # 8-byte Reload - movzx r8d, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r8b, 6 - shl al, 7 - or al, r8b - or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov r8d, ebx - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 2 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 3 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl bl, 5 - or bl, r8b - mov byte ptr [rsi], dil - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 + or r12b, r10b + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 6 + shl bl, 7 + or bl, sil + or r11b, al + or bl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 5 + or al, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], al - or r15b, bl - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], bl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload + add al, byte ptr [rsp + 32] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax @@ -11165,206 +10772,240 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], cl - add rdx, 128 - add rsi, 4 - mov qword ptr [rsp], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_78 -# %bb.79: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB2_80: - shl r11, 5 - cmp r11, r10 - jge .LBB2_177 -# %bb.81: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB2_151 -.LBB2_82: + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], cl + add rdx, 256 + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB2_53 +# %bb.54: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB2_55: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_200 +# %bb.56: + or rax, 1 + cmp r15, rax + je .LBB2_99 +# %bb.57: + mov r10, r8 + and r10, -2 xor edi, edi - jmp .LBB2_153 -.LBB2_83: - movzx r14d, word ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + .p2align 4, 0x90 +.LBB2_58: # =>This Inner Loop Header: Depth=1 + cmp r13, qword ptr [rdx] + sete al + neg al + mov rsi, rdi + shr rsi, 3 + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] + mov ecx, edi + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rsi], bl + add rdi, 2 + cmp r13, qword ptr [rdx + 8] + lea rdx, [rdx + 16] + sete r9b + neg r9b + xor r9b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r9b + xor al, bl + mov byte ptr [r12 + rsi], al + cmp r10, rdi + jne .LBB2_58 + jmp .LBB2_192 +.LBB2_59: + movzx r13d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_87 -# %bb.84: - movsxd rax, r9d - mov r11, qword ptr [rsp] # 8-byte Reload + je .LBB2_65 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_63 +# %bb.61: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_85: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] +.LBB2_62: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r13w, word ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_85 -# %bb.86: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_87: - sar r15, 5 - cmp r10, 32 - jl .LBB2_138 -# %bb.88: - cmp r15, 8 - mov dword ptr [rsp + 8], r14d # 4-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_62 +.LBB2_63: + sub r15, r8 + je .LBB2_200 +# %bb.64: + add r12, 1 +.LBB2_65: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB2_133 +# %bb.66: + cmp rcx, 8 mov qword ptr [rsp + 152], r15 # 8-byte Spill - jb .LBB2_91 -# %bb.89: - mov rax, r15 + mov qword ptr [rsp + 224], rcx # 8-byte Spill + jb .LBB2_69 +# %bb.67: + mov rax, rcx shl rax, 6 add rax, rdx - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB2_188 -# %bb.90: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] + cmp r12, rax + jae .LBB2_205 +# %bb.68: + lea rax, [r12 + 4*rcx] cmp rax, rdx - jbe .LBB2_188 -.LBB2_91: + jbe .LBB2_205 +.LBB2_69: xor eax, eax - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 24], rax # 8-byte Spill mov rsi, rdx - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 16], rax # 8-byte Spill -.LBB2_92: - sub r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp], r12 # 8-byte Spill +.LBB2_70: + sub rcx, qword ptr [rsp + 24] # 8-byte Folded Reload + mov qword ptr [rsp + 144], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB2_93: # =>This Inner Loop Header: Depth=1 - mov r10, rsi - cmp r14w, word ptr [rsi] - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 2] +.LBB2_71: # =>This Inner Loop Header: Depth=1 + mov r11, rsi + cmp r13w, word ptr [rsi] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 2] sete dil - cmp r14w, word ptr [rsi + 4] - sete r15b - cmp r14w, word ptr [rsi + 6] - sete r13b - cmp r14w, word ptr [rsi + 8] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 10] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 12] + cmp r13w, word ptr [rsi + 4] + sete r14b + cmp r13w, word ptr [rsi + 6] + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 8] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 10] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 12] sete al - cmp r14w, word ptr [rsi + 14] - sete r11b - cmp r14w, word ptr [rsi + 16] - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 18] + cmp r13w, word ptr [rsi + 14] + sete r10b + cmp r13w, word ptr [rsi + 16] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 18] sete cl - cmp r14w, word ptr [rsi + 20] + cmp r13w, word ptr [rsi + 20] sete dl - cmp r14w, word ptr [rsi + 22] + cmp r13w, word ptr [rsi + 22] sete sil - cmp r14w, word ptr [r10 + 24] + cmp r13w, word ptr [r11 + 24] sete r9b - cmp r14w, word ptr [r10 + 26] + cmp r13w, word ptr [r11 + 26] sete r12b - cmp r14w, word ptr [r10 + 28] + cmp r13w, word ptr [r11 + 28] sete byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 30] + cmp r13w, word ptr [r11 + 30] sete r8b - cmp r14w, word ptr [r10 + 32] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 34] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 36] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 38] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 40] - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 42] + cmp r13w, word ptr [r11 + 32] sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 44] + cmp r13w, word ptr [r11 + 34] sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 46] - sete r14b - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 48] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 50] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 52] - sete byte ptr [rsp + 32] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 54] + cmp r13w, word ptr [r11 + 36] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 38] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 40] + sete byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 42] + sete byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 44] sete byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 56] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 58] + cmp r13w, word ptr [r11 + 46] + sete r15b + cmp r13w, word ptr [r11 + 48] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 50] sete byte ptr [rsp + 48] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 60] - sete byte ptr [rsp] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 62] + cmp r13w, word ptr [r11 + 52] + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 54] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 56] + sete byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 58] + sete byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 60] + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 62] sete bl add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, dil + shl r10b, 7 + or r10b, al + shl r14b, 2 + or r14b, dil add cl, cl - add cl, byte ptr [rsp + 208] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b + add cl, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b shl dl, 2 or dl, cl - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 4 - or cl, r13b + or cl, al mov edi, ecx shl sil, 3 or sil, dl - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload shl cl, 5 or cl, dil shl r9b, 4 @@ -11375,16 +11016,17 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl dl, 6 shl r8b, 7 or r8b, dl - or r11b, cl + or r10b, cl or r8b, r12b - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 96] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl cl, 2 - or cl, al + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload mov edx, ecx movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 3 or cl, dl mov edx, ecx @@ -11392,219 +11034,221 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl cl, 4 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 5 or cl, dl mov esi, ecx - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - mov byte ptr [rcx], r11b - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + mov rcx, qword ptr [rsp] # 8-byte Reload + mov byte ptr [rcx], r10b + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload shl dl, 6 - shl r14b, 7 - or r14b, dl + shl r15b, 7 + or r15b, dl mov byte ptr [rcx + 1], r8b - or r14b, sil - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + or r15b, sil + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 32] # 1-byte Folded Reload mov edx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 3 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 4 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, dl - movzx edx, byte ptr [rsp] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload shl dl, 6 shl bl, 7 or bl, dl or bl, al - mov byte ptr [rcx + 2], r14b - mov r14d, dword ptr [rsp + 8] # 4-byte Reload + mov byte ptr [rcx + 2], r15b mov byte ptr [rcx + 3], bl - lea rsi, [r10 + 64] + lea rsi, [r11 + 64] add rcx, 4 - mov qword ptr [rsp + 16], rcx # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_93 -# %bb.94: - mov r10, qword ptr [rsp + 144] # 8-byte Reload + mov qword ptr [rsp], rcx # 8-byte Spill + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB2_71 +# %bb.72: mov r15, qword ptr [rsp + 152] # 8-byte Reload - jmp .LBB2_139 -.LBB2_95: - movzx r14d, word ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + jmp .LBB2_134 +.LBB2_73: + movzx r13d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB2_99 -# %bb.96: - movsxd rax, r9d - mov r11, qword ptr [rsp] # 8-byte Reload + je .LBB2_79 +# %bb.74: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_77 +# %bb.75: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_97: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] +.LBB2_76: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r13w, word ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_97 -# %bb.98: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_99: - sar r15, 5 - cmp r10, 32 - jl .LBB2_143 -# %bb.100: - cmp r15, 8 - mov dword ptr [rsp + 8], r14d # 4-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_76 +.LBB2_77: + sub r15, r8 + je .LBB2_200 +# %bb.78: + add r12, 1 +.LBB2_79: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB2_138 +# %bb.80: + cmp rcx, 8 mov qword ptr [rsp + 152], r15 # 8-byte Spill - jb .LBB2_103 -# %bb.101: - mov rax, r15 + mov qword ptr [rsp + 224], rcx # 8-byte Spill + jb .LBB2_83 +# %bb.81: + mov rax, rcx shl rax, 6 add rax, rdx - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB2_191 -# %bb.102: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] + cmp r12, rax + jae .LBB2_208 +# %bb.82: + lea rax, [r12 + 4*rcx] cmp rax, rdx - jbe .LBB2_191 -.LBB2_103: + jbe .LBB2_208 +.LBB2_83: xor eax, eax - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov qword ptr [rsp + 24], rax # 8-byte Spill mov rsi, rdx - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 16], rax # 8-byte Spill -.LBB2_104: - sub r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp], r12 # 8-byte Spill +.LBB2_84: + sub rcx, qword ptr [rsp + 24] # 8-byte Folded Reload + mov qword ptr [rsp + 144], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB2_105: # =>This Inner Loop Header: Depth=1 - mov r10, rsi - cmp r14w, word ptr [rsi] - sete byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 2] +.LBB2_85: # =>This Inner Loop Header: Depth=1 + mov r11, rsi + cmp r13w, word ptr [rsi] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 2] sete dil - cmp r14w, word ptr [rsi + 4] - sete r15b - cmp r14w, word ptr [rsi + 6] - sete r13b - cmp r14w, word ptr [rsi + 8] - sete byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 10] - sete byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 12] + cmp r13w, word ptr [rsi + 4] + sete r14b + cmp r13w, word ptr [rsi + 6] + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 8] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 10] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 12] sete al - cmp r14w, word ptr [rsi + 14] - sete r11b - cmp r14w, word ptr [rsi + 16] - sete byte ptr [rsp + 208] # 1-byte Folded Spill - cmp r14w, word ptr [rsi + 18] + cmp r13w, word ptr [rsi + 14] + sete r10b + cmp r13w, word ptr [rsi + 16] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 18] sete cl - cmp r14w, word ptr [rsi + 20] + cmp r13w, word ptr [rsi + 20] sete dl - cmp r14w, word ptr [rsi + 22] + cmp r13w, word ptr [rsi + 22] sete sil - cmp r14w, word ptr [r10 + 24] + cmp r13w, word ptr [r11 + 24] sete r9b - cmp r14w, word ptr [r10 + 26] + cmp r13w, word ptr [r11 + 26] sete r12b - cmp r14w, word ptr [r10 + 28] + cmp r13w, word ptr [r11 + 28] sete byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 30] + cmp r13w, word ptr [r11 + 30] sete r8b - cmp r14w, word ptr [r10 + 32] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 34] - sete byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 36] - sete byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 38] - sete byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 40] - sete byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 42] + cmp r13w, word ptr [r11 + 32] sete byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 44] + cmp r13w, word ptr [r11 + 34] sete byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [r10 + 46] - sete r14b - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 48] - sete byte ptr [rsp + 40] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 50] - sete byte ptr [rsp + 64] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 52] - sete byte ptr [rsp + 32] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 54] + cmp r13w, word ptr [r11 + 36] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 38] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 40] + sete byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 42] + sete byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 44] sete byte ptr [rsp + 56] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 56] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 58] + cmp r13w, word ptr [r11 + 46] + sete r15b + cmp r13w, word ptr [r11 + 48] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 50] sete byte ptr [rsp + 48] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 60] - sete byte ptr [rsp] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 8] # 4-byte Reload - cmp bx, word ptr [r10 + 62] + cmp r13w, word ptr [r11 + 52] + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 54] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 56] + sete byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 58] + sete byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 60] + sete byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 62] sete bl add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload + add dil, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 6 - shl r11b, 7 - or r11b, al - shl r15b, 2 - or r15b, dil + shl r10b, 7 + or r10b, al + shl r14b, 2 + or r14b, dil add cl, cl - add cl, byte ptr [rsp + 208] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r15b + add cl, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b shl dl, 2 or dl, cl - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 4 - or cl, r13b + or cl, al mov edi, ecx shl sil, 3 or sil, dl - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload shl cl, 5 or cl, dil shl r9b, 4 @@ -11615,16 +11259,17 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl dl, 6 shl r8b, 7 or r8b, dl - or r11b, cl + or r10b, cl or r8b, r12b - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 96] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl cl, 2 - or cl, al + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload mov edx, ecx movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 3 or cl, dl mov edx, ecx @@ -11632,234 +11277,247 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl cl, 4 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload shl cl, 5 or cl, dl mov esi, ecx - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - mov byte ptr [rcx], r11b - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + mov rcx, qword ptr [rsp] # 8-byte Reload + mov byte ptr [rcx], r10b + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload shl dl, 6 - shl r14b, 7 - or r14b, dl + shl r15b, 7 + or r15b, dl mov byte ptr [rcx + 1], r8b - or r14b, sil - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + or r15b, sil + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 32] # 1-byte Folded Reload mov edx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 3 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 4 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, dl - movzx edx, byte ptr [rsp] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload shl dl, 6 shl bl, 7 or bl, dl or bl, al - mov byte ptr [rcx + 2], r14b - mov r14d, dword ptr [rsp + 8] # 4-byte Reload + mov byte ptr [rcx + 2], r15b mov byte ptr [rcx + 3], bl - lea rsi, [r10 + 64] + lea rsi, [r11 + 64] add rcx, 4 - mov qword ptr [rsp + 16], rcx # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_105 -# %bb.106: - mov r10, qword ptr [rsp + 144] # 8-byte Reload + mov qword ptr [rsp], rcx # 8-byte Spill + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB2_85 +# %bb.86: mov r15, qword ptr [rsp + 152] # 8-byte Reload - jmp .LBB2_144 -.LBB2_107: + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + jmp .LBB2_139 +.LBB2_87: mov r13, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] + lea ecx, [r9 + 7] test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB2_111 -# %bb.108: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB2_93 +# %bb.88: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_91 +# %bb.89: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_109: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] - lea rdx, [rdx + 8] +.LBB2_90: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r13, qword ptr [rcx] sete bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r9 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov esi, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r9 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_109 -# %bb.110: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_111: - sar r11, 5 - cmp r10, 32 - jl .LBB2_115 -# %bb.112: - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 152], r11 # 8-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill + shl esi, cl + and sil, bl + xor sil, r9b + mov byte ptr [r12 + rax], sil + add rdi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_90 +.LBB2_91: + sub r15, r8 + je .LBB2_200 +# %bb.92: + add r12, 1 +.LBB2_93: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_97 +# %bb.94: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB2_113: # =>This Inner Loop Header: Depth=1 +.LBB2_95: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill cmp r13, qword ptr [rdx] - sete byte ptr [rsp + 192] # 1-byte Folded Spill + sete byte ptr [rsp + 136] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 8] - sete r10b + sete r9b cmp r13, qword ptr [rdx + 16] sete r14b cmp r13, qword ptr [rdx + 24] - sete byte ptr [rsp + 160] # 1-byte Folded Spill + sete byte ptr [rsp + 192] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 32] - sete byte ptr [rsp + 112] # 1-byte Folded Spill + sete byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 40] - sete byte ptr [rsp + 88] # 1-byte Folded Spill + sete byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 48] - sete bl + sete al cmp r13, qword ptr [rdx + 56] - sete dil + sete r11b cmp r13, qword ptr [rdx + 64] - sete byte ptr [rsp + 208] # 1-byte Folded Spill + sete byte ptr [rsp + 160] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 72] sete sil cmp r13, qword ptr [rdx + 80] - sete r8b + sete dil cmp r13, qword ptr [rdx + 88] - sete r9b + sete r8b cmp r13, qword ptr [rdx + 96] - sete r11b + sete r10b cmp r13, qword ptr [rdx + 104] sete r12b cmp r13, qword ptr [rdx + 112] sete byte ptr [rsp + 176] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 120] - sete al + sete bl cmp r13, qword ptr [rdx + 128] - sete byte ptr [rsp + 72] # 1-byte Folded Spill + sete byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 136] - sete byte ptr [rsp + 120] # 1-byte Folded Spill + sete byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 144] - sete byte ptr [rsp + 128] # 1-byte Folded Spill + sete byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 152] - sete byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 160] sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 160] + sete byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 168] - sete byte ptr [rsp + 104] # 1-byte Folded Spill + sete byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 176] - sete byte ptr [rsp + 64] # 1-byte Folded Spill + sete byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 184] sete r15b cmp r13, qword ptr [rdx + 192] - sete byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 200] sete byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 200] + sete byte ptr [rsp + 48] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 208] - sete byte ptr [rsp + 56] # 1-byte Folded Spill + sete byte ptr [rsp + 24] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 216] sete byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 224] - sete byte ptr [rsp + 48] # 1-byte Folded Spill + sete byte ptr [rsp + 8] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 232] sete byte ptr [rsp + 16] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 240] - sete byte ptr [rsp + 8] # 1-byte Folded Spill + sete byte ptr [rsp] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 248] sete cl - add r10b, r10b - add r10b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl dil, 7 - or dil, bl + add r9b, r9b + add r9b, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b + or r14b, r9b add sil, sil - add sil, byte ptr [rsp + 208] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 3 - or bl, r14b - mov r10d, ebx - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl bl, 4 - or bl, r10b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r11b, 4 - or r11b, r9b + add sil, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r9d, eax + shl dil, 2 + or dil, sil + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 4 + or al, r9b + mov esi, eax + shl r8b, 3 + or r8b, dil + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 5 + or al, sil + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - mov rsi, qword ptr [rsp] # 8-byte Reload - movzx r8d, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r8b, 6 - shl al, 7 - or al, r8b - or dil, bl - or al, r12b - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov r8d, ebx - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 2 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 3 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, r8b - mov r8d, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl bl, 5 - or bl, r8b - mov byte ptr [rsi], dil - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 + or r12b, r10b + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 6 + shl bl, 7 + or bl, sil + or r11b, al + or bl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 5 + or al, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl sil, 6 shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], al - or r15b, bl - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + or r15b, sil + mov byte ptr [r12 + 1], bl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload + add al, byte ptr [rsp + 32] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax @@ -11867,113 +11525,126 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], cl + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], cl add rdx, 256 - add rsi, 4 - mov qword ptr [rsp], rsi # 8-byte Spill - add qword ptr [rsp + 136], -1 # 8-byte Folded Spill - jne .LBB2_113 -# %bb.114: - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r11, qword ptr [rsp + 152] # 8-byte Reload -.LBB2_115: - shl r11, 5 - cmp r11, r10 - jge .LBB2_177 -# %bb.116: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB2_166 -.LBB2_117: + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB2_95 +# %bb.96: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB2_97: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_200 +# %bb.98: + or rax, 1 + cmp r15, rax + jne .LBB2_190 +.LBB2_99: xor edi, edi - jmp .LBB2_168 -.LBB2_118: - lea r14, [r10 + 31] - test r10, r10 - cmovns r14, r10 + jmp .LBB2_192 +.LBB2_100: + mov r14d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB2_122 -# %bb.119: - movsxd rax, r9d - mov r11, qword ptr [rsp] # 8-byte Reload + je .LBB2_106 +# %bb.101: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_104 +# %bb.102: + movsxd rsi, r9d + movd xmm0, r14d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB2_120: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] +.LBB2_103: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rcx] + lea rdx, [rcx + 4] setnp cl sete bl and bl, cl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r11 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB2_120 -# %bb.121: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB2_122: - sar r14, 5 - cmp r10, 32 - jl .LBB2_147 -# %bb.123: - cmp r14, 4 - jb .LBB2_126 -# %bb.124: - mov rax, r14 + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_103 +.LBB2_104: + sub r15, r8 + je .LBB2_200 +# %bb.105: + add r12, 1 +.LBB2_106: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB2_142 +# %bb.107: + movd xmm0, r14d + cmp rcx, 4 + jb .LBB2_110 +# %bb.108: + mov rax, rcx shl rax, 7 add rax, rdx - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB2_194 -# %bb.125: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r14] + cmp r12, rax + jae .LBB2_211 +# %bb.109: + lea rax, [r12 + 4*rcx] cmp rax, rdx - jbe .LBB2_194 -.LBB2_126: - xor r8d, r8d + jbe .LBB2_211 +.LBB2_110: + xor eax, eax mov rbx, rdx - mov r15, qword ptr [rsp] # 8-byte Reload -.LBB2_127: - mov qword ptr [rsp + 8], r15 # 8-byte Spill - mov qword ptr [rsp + 144], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r14 # 8-byte Spill - sub r14, r8 - mov qword ptr [rsp + 152], r14 # 8-byte Spill + mov r13, r12 +.LBB2_111: + mov qword ptr [rsp + 128], r13 # 8-byte Spill + mov dword ptr [rsp + 272], r14d # 4-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rcx # 8-byte Spill + sub rcx, rax + mov qword ptr [rsp + 224], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB2_128: # =>This Inner Loop Header: Depth=1 +.LBB2_112: # =>This Inner Loop Header: Depth=1 ucomiss xmm0, dword ptr [rbx] setnp al sete cl @@ -11987,12 +11658,12 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 24], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 12] setnp al sete cl and cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 8], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 16] setnp al sete cl @@ -12002,12 +11673,12 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 24] setnp al sete cl and cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 28] setnp al sete cl @@ -12022,42 +11693,42 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 40] setnp al sete cl and cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 44] setnp al sete cl and cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 48] setnp al sete cl and cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 52] setnp al sete cl and cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 56] setnp al sete cl and cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 60] setnp al sete cl and cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 64] setnp al sete cl and cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 88], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 68] setnp al sete r12b @@ -12066,7 +11737,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 76] setnp al sete cl @@ -12076,12 +11747,12 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 208], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 84] setnp al sete cl and cl, al - mov byte ptr [rsp + 192], cl # 1-byte Spill + mov byte ptr [rsp + 136], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 88] setnp al sete r14b @@ -12094,7 +11765,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill + mov byte ptr [rsp + 192], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 100] setnp al sete r11b @@ -12115,7 +11786,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 setnp al sete cl and cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 120] setnp al sete dil @@ -12127,65 +11798,65 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 add dl, dl or dl, r13b mov r13d, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 24] # 1-byte Folded Reload shl dl, 5 - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 6 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, r13b mov r13d, eax - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 40] # 1-byte Folded Reload movzx eax, byte ptr [rsp] # 1-byte Folded Reload shl al, 7 or al, dl mov byte ptr [rsp], al # 1-byte Spill - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 or al, r13b mov r13d, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, r13b - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload shl dl, 4 or dl, cl - movzx r13d, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 80] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload shl cl, 6 or cl, r13b - movzx r13d, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 120] # 1-byte Folded Reload shl r13b, 7 or r13b, cl add r12b, r12b - add r12b, byte ptr [rsp + 72] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 88] # 1-byte Folded Reload mov ecx, r12d - movzx r12d, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 104] # 1-byte Folded Reload shl r12b, 2 or r12b, cl movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 3 or cl, r12b mov r12d, ecx - movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload shl cl, 4 or cl, r12b movzx r12d, byte ptr [rsp] # 1-byte Folded Reload or r12b, al - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 5 shl r14b, 6 or r14b, al @@ -12194,16 +11865,16 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 or r8b, r14b or r8b, cl add r11b, r11b - add r11b, byte ptr [rsp + 160] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 192] # 1-byte Folded Reload shl r10b, 2 or r10b, r11b shl r9b, 3 or r9b, r10b shl r15b, 4 or r15b, r9b - mov rax, qword ptr [rsp + 8] # 8-byte Reload + mov rax, qword ptr [rsp + 128] # 8-byte Reload mov byte ptr [rax], r12b - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload shl cl, 5 shl dil, 6 or dil, cl @@ -12215,112 +11886,327 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 mov byte ptr [rax + 3], sil add rbx, 128 add rax, 4 - mov qword ptr [rsp + 8], rax # 8-byte Spill - add qword ptr [rsp + 152], -1 # 8-byte Folded Spill - jne .LBB2_128 -# %bb.129: - mov r15, qword ptr [rsp + 8] # 8-byte Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r14, qword ptr [rsp + 240] # 8-byte Reload - jmp .LBB2_148 -.LBB2_130: - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 104], rax # 8-byte Spill - mov rsi, rdx -.LBB2_131: - shl r15, 5 - cmp r15, r10 - jge .LBB2_177 -# %bb.132: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB2_137 -# %bb.155: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r11, qword ptr [rsp + 104] # 8-byte Reload + mov qword ptr [rsp + 128], rax # 8-byte Spill + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB2_112 +# %bb.113: + mov r13, qword ptr [rsp + 128] # 8-byte Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14d, dword ptr [rsp + 272] # 4-byte Reload + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + jmp .LBB2_143 +.LBB2_114: + mov r11b, byte ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB2_146 +# %bb.115: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_161 +# %bb.116: + movsxd rsi, r9d + mov rax, r8 .p2align 4, 0x90 -.LBB2_156: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp r14b, byte ptr [rsi + r9] +.LBB2_117: # =>This Inner Loop Header: Depth=1 + lea r14, [rdx + 1] + cmp r11b, byte ptr [rdx] + sete dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, dl + xor dil, r9b + mov byte ptr [r12 + rbx], dil + add rsi, 1 + mov rdx, r14 + add rax, -1 + jne .LBB2_117 +# %bb.118: + sub r15, r8 + jne .LBB2_162 + jmp .LBB2_200 +.LBB2_119: + mov r13d, dword ptr [rsi] + lea ecx, [r9 + 7] + test r9d, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB2_125 +# %bb.120: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB2_123 +# %bb.121: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rdx + .p2align 4, 0x90 +.LBB2_122: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r13d, dword ptr [rcx] sete bl neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r11 + rdi] + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp r14b, byte ptr [rsi + rax + 1] - lea r9, [rax + 2] + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov esi, 1 + # kill: def $cl killed $cl killed $ecx + shl esi, cl + and sil, bl + xor sil, r9b + mov byte ptr [r12 + rax], sil + add rdi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB2_122 +.LBB2_123: + sub r15, r8 + je .LBB2_200 +# %bb.124: + add r12, 1 +.LBB2_125: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB2_129 +# %bb.126: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB2_127: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + cmp r13d, dword ptr [rdx] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 4] + sete r9b + cmp r13d, dword ptr [rdx + 8] + sete r14b + cmp r13d, dword ptr [rdx + 12] + sete byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 16] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 20] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 24] + sete al + cmp r13d, dword ptr [rdx + 28] + sete r11b + cmp r13d, dword ptr [rdx + 32] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 36] + sete sil + cmp r13d, dword ptr [rdx + 40] + sete dil + cmp r13d, dword ptr [rdx + 44] + sete r8b + cmp r13d, dword ptr [rdx + 48] + sete r10b + cmp r13d, dword ptr [rdx + 52] + sete r12b + cmp r13d, dword ptr [rdx + 56] + sete byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 60] sete bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, r9 - jne .LBB2_156 - jmp .LBB2_159 -.LBB2_134: - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 104], rax # 8-byte Spill + cmp r13d, dword ptr [rdx + 64] + sete byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 68] + sete byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 72] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 76] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 80] + sete byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 84] + sete byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 88] + sete byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 92] + sete r15b + cmp r13d, dword ptr [rdx + 96] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 100] + sete byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 104] + sete byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 108] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 112] + sete byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 116] + sete byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 120] + sete byte ptr [rsp] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 124] + sete cl + add r9b, r9b + add r9b, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r9b + add sil, sil + add sil, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r9d, eax + shl dil, 2 + or dil, sil + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 4 + or al, r9b + mov esi, eax + shl r8b, 3 + or r8b, dil + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 5 + or al, sil + shl r10b, 4 + or r10b, r8b + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 6 + shl bl, 7 + or bl, sil + or r11b, al + or bl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, sil + mov esi, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 5 + or al, sil + mov byte ptr [r12], r11b + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [r12 + 1], bl + or r15b, al + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + shl bl, 6 + shl cl, 7 + or cl, bl + or cl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], cl + add rdx, 128 + add r12, 4 + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB2_127 +# %bb.128: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB2_129: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB2_200 +# %bb.130: + or rax, 1 + cmp r15, rax + jne .LBB2_175 +.LBB2_131: + xor edi, edi + jmp .LBB2_177 +.LBB2_132: + mov r14, rdx + jmp .LBB2_149 +.LBB2_133: + mov qword ptr [rsp], r12 # 8-byte Spill mov rsi, rdx -.LBB2_135: - shl r15, 5 - cmp r15, r10 - jge .LBB2_177 +.LBB2_134: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB2_200 +# %bb.135: + or rcx, 1 + cmp r15, rcx + je .LBB2_141 # %bb.136: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB2_157 -.LBB2_137: - xor r9d, r9d - test r8b, 1 - je .LBB2_177 - jmp .LBB2_161 -.LBB2_138: - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 16], rax # 8-byte Spill - mov rsi, rdx -.LBB2_139: - shl r15, 5 - cmp r15, r10 - jge .LBB2_177 -# %bb.140: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - je .LBB2_146 -# %bb.141: mov r9, r8 and r9, -2 - xor r15d, r15d - mov r11, qword ptr [rsp + 16] # 8-byte Reload + xor r14d, r14d + mov r11, qword ptr [rsp] # 8-byte Reload .p2align 4, 0x90 -.LBB2_142: # =>This Inner Loop Header: Depth=1 +.LBB2_137: # =>This Inner Loop Header: Depth=1 mov rax, rsi - cmp r14w, word ptr [rsi] + cmp r13w, word ptr [rsi] sete dl neg dl - mov rdi, r15 + mov rdi, r14 shr rdi, 3 movzx r10d, byte ptr [r11 + rdi] - mov ecx, r15d + mov ecx, r14d and cl, 6 mov bl, 1 shl bl, cl @@ -12328,8 +12214,8 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 and bl, dl xor bl, r10b mov byte ptr [r11 + rdi], bl - add r15, 2 - cmp r14w, word ptr [rsi + 2] + add r14, 2 + cmp r13w, word ptr [rsi + 2] lea rsi, [rsi + 4] sete dl neg dl @@ -12340,55 +12226,575 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 and al, dl xor al, bl mov byte ptr [r11 + rdi], al - cmp r9, r15 - jne .LBB2_142 - jmp .LBB2_173 -.LBB2_143: - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 16], rax # 8-byte Spill + cmp r9, r14 + jne .LBB2_137 + jmp .LBB2_197 +.LBB2_138: + mov qword ptr [rsp], r12 # 8-byte Spill mov rsi, rdx -.LBB2_144: - shl r15, 5 - cmp r15, r10 - jge .LBB2_177 +.LBB2_139: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB2_200 +# %bb.140: + or rcx, 1 + cmp r15, rcx + jne .LBB2_195 +.LBB2_141: + xor r14d, r14d + jmp .LBB2_197 +.LBB2_142: + mov r13, r12 + mov rbx, rdx +.LBB2_143: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB2_200 +# %bb.144: + movd xmm0, r14d + or rcx, 1 + cmp r15, rcx + jne .LBB2_201 # %bb.145: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB2_171 + xor esi, esi + jmp .LBB2_203 .LBB2_146: - xor r15d, r15d - jmp .LBB2_173 + mov r14, rdx + jmp .LBB2_163 .LBB2_147: - mov r15, qword ptr [rsp] # 8-byte Reload - mov rbx, rdx + mov r14, rdx + sub r15, r8 + je .LBB2_200 .LBB2_148: - shl r14, 5 - cmp r14, r10 - jge .LBB2_177 -# %bb.149: - mov r8, r10 - sub r8, r14 - not r14 - add r14, r10 - jne .LBB2_178 + add r12, 1 +.LBB2_149: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB2_157 # %bb.150: - xor esi, esi - jmp .LBB2_180 -.LBB2_151: - mov r10, r8 - and r10, -2 - xor edi, edi - mov r11, qword ptr [rsp] # 8-byte Reload + cmp rcx, 16 + mov byte ptr [rsp], r11b # 1-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 248], rcx # 8-byte Spill + jb .LBB2_153 +# %bb.151: + mov rax, rcx + shl rax, 5 + add rax, r14 + cmp r12, rax + jae .LBB2_214 +# %bb.152: + lea rax, [r12 + 4*rcx] + cmp r14, rax + jae .LBB2_214 +.LBB2_153: + xor eax, eax + mov qword ptr [rsp + 216], rax # 8-byte Spill + mov qword ptr [rsp + 96], r12 # 8-byte Spill + mov rsi, r14 +.LBB2_154: + sub rcx, qword ptr [rsp + 216] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB2_152: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - sete al +.LBB2_155: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp r11b, byte ptr [rsi] + sete byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r11b, byte ptr [rsi + 1] + sete dil + cmp r11b, byte ptr [rsi + 2] + sete r11b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 3] + sete r15b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 4] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 5] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 6] + sete bl + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 7] + sete r12b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 8] + sete byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 9] + sete sil + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 10] + sete r8b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 11] + sete r9b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 12] + sete r14b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 13] + sete byte ptr [rsp + 72] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 14] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 15] + sete r13b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 16] + sete byte ptr [rsp + 176] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 17] + sete byte ptr [rsp + 104] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 18] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 19] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 20] + sete byte ptr [rsp + 88] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 21] + sete byte ptr [rsp + 56] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 22] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 23] + sete r10b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 24] + sete byte ptr [rsp + 48] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 25] + sete byte ptr [rsp + 24] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 26] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 27] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 28] + sete byte ptr [rsp + 8] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 29] + sete byte ptr [rsp + 16] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 30] + sete byte ptr [rsp + 128] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 31] + sete dl + add dil, dil + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + shl bl, 6 + shl r12b, 7 + or r12b, bl + shl r11b, 2 + or r11b, dil + add sil, sil + add sil, byte ptr [rsp + 192] # 1-byte Folded Reload + shl r15b, 3 + or r15b, r11b + movzx r11d, byte ptr [rsp] # 1-byte Folded Reload + shl r8b, 2 + or r8b, sil + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl bl, 4 + or bl, r15b + mov eax, ebx + shl r9b, 3 + or r9b, r8b + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl bl, 5 + or bl, al + shl r14b, 4 + or r14b, r9b + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload + shl sil, 6 + shl r13b, 7 + or r13b, sil + or r12b, bl + or r13b, al + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 176] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 4 + or al, bl + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl bl, 5 + or bl, al + mov rdi, qword ptr [rsp + 96] # 8-byte Reload + mov byte ptr [rdi], r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 6 + shl r10b, 7 + or r10b, al + mov byte ptr [rdi + 1], r13b + or r10b, bl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rdi + 2], r10b + mov byte ptr [rdi + 3], dl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 96], rdi # 8-byte Spill + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB2_155 +# %bb.156: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + jmp .LBB2_158 +.LBB2_157: + mov qword ptr [rsp + 96], r12 # 8-byte Spill + mov rsi, r14 +.LBB2_158: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB2_200 +# %bb.159: + or rcx, 1 + cmp r15, rcx + je .LBB2_174 +# %bb.179: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r14, qword ptr [rsp + 96] # 8-byte Reload + .p2align 4, 0x90 +.LBB2_180: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r11b, byte ptr [rsi + r9] + sete bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r14 + rdi], dl + cmp r11b, byte ptr [rsi + rax + 1] + lea r9, [rax + 2] + sete bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r14 + rdi], al + cmp r10, r9 + jne .LBB2_180 + jmp .LBB2_183 +.LBB2_161: + mov r14, rdx + sub r15, r8 + je .LBB2_200 +.LBB2_162: + add r12, 1 +.LBB2_163: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB2_171 +# %bb.164: + cmp rcx, 16 + mov byte ptr [rsp], r11b # 1-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 248], rcx # 8-byte Spill + jb .LBB2_167 +# %bb.165: + mov rax, rcx + shl rax, 5 + add rax, r14 + cmp r12, rax + jae .LBB2_217 +# %bb.166: + lea rax, [r12 + 4*rcx] + cmp r14, rax + jae .LBB2_217 +.LBB2_167: + xor eax, eax + mov qword ptr [rsp + 216], rax # 8-byte Spill + mov qword ptr [rsp + 96], r12 # 8-byte Spill + mov rsi, r14 +.LBB2_168: + sub rcx, qword ptr [rsp + 216] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB2_169: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp r11b, byte ptr [rsi] + sete byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r11b, byte ptr [rsi + 1] + sete dil + cmp r11b, byte ptr [rsi + 2] + sete r11b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 3] + sete r15b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 4] + sete byte ptr [rsp + 136] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 5] + sete byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 6] + sete bl + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 7] + sete r12b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 8] + sete byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 9] + sete sil + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 10] + sete r8b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 11] + sete r9b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 12] + sete r14b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 13] + sete byte ptr [rsp + 72] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 14] + sete byte ptr [rsp + 160] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 15] + sete r13b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 16] + sete byte ptr [rsp + 176] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 17] + sete byte ptr [rsp + 104] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 18] + sete byte ptr [rsp + 120] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 19] + sete byte ptr [rsp + 80] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 20] + sete byte ptr [rsp + 88] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 21] + sete byte ptr [rsp + 56] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 22] + sete byte ptr [rsp + 64] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 23] + sete r10b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 24] + sete byte ptr [rsp + 48] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 25] + sete byte ptr [rsp + 24] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 26] + sete byte ptr [rsp + 40] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 27] + sete byte ptr [rsp + 32] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 28] + sete byte ptr [rsp + 8] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 29] + sete byte ptr [rsp + 16] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 30] + sete byte ptr [rsp + 128] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 31] + sete dl + add dil, dil + add dil, byte ptr [rsp + 144] # 1-byte Folded Reload + shl bl, 6 + shl r12b, 7 + or r12b, bl + shl r11b, 2 + or r11b, dil + add sil, sil + add sil, byte ptr [rsp + 192] # 1-byte Folded Reload + shl r15b, 3 + or r15b, r11b + movzx r11d, byte ptr [rsp] # 1-byte Folded Reload + shl r8b, 2 + or r8b, sil + movzx ebx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl bl, 4 + or bl, r15b + mov eax, ebx + shl r9b, 3 + or r9b, r8b + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl bl, 5 + or bl, al + shl r14b, 4 + or r14b, r9b + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload + shl sil, 6 + shl r13b, 7 + or r13b, sil + or r12b, bl + or r13b, al + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 176] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 4 + or al, bl + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl bl, 5 + or bl, al + mov rdi, qword ptr [rsp + 96] # 8-byte Reload + mov byte ptr [rdi], r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 6 + shl r10b, 7 + or r10b, al + mov byte ptr [rdi + 1], r13b + or r10b, bl + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rdi + 2], r10b + mov byte ptr [rdi + 3], dl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 96], rdi # 8-byte Spill + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB2_169 +# %bb.170: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + jmp .LBB2_172 +.LBB2_171: + mov qword ptr [rsp + 96], r12 # 8-byte Spill + mov rsi, r14 +.LBB2_172: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB2_200 +# %bb.173: + or rcx, 1 + cmp r15, rcx + jne .LBB2_181 +.LBB2_174: + xor r9d, r9d + jmp .LBB2_184 +.LBB2_175: + mov r10, r8 + and r10, -2 + xor edi, edi + .p2align 4, 0x90 +.LBB2_176: # =>This Inner Loop Header: Depth=1 + cmp r13d, dword ptr [rdx] + sete al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -12396,7 +12802,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r11 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 cmp r13d, dword ptr [rdx + 4] lea rdx, [rdx + 8] @@ -12408,24 +12814,24 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl al, cl and al, r9b xor al, bl - mov byte ptr [r11 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB2_152 -.LBB2_153: + jne .LBB2_176 +.LBB2_177: test r8b, 1 - je .LBB2_177 -# %bb.154: + je .LBB2_200 +# %bb.178: cmp r13d, dword ptr [rdx] - jmp .LBB2_170 -.LBB2_157: + jmp .LBB2_194 +.LBB2_181: mov r10, r8 and r10, -2 xor r9d, r9d - mov r11, qword ptr [rsp + 104] # 8-byte Reload + mov r14, qword ptr [rsp + 96] # 8-byte Reload .p2align 4, 0x90 -.LBB2_158: # =>This Inner Loop Header: Depth=1 +.LBB2_182: # =>This Inner Loop Header: Depth=1 mov rax, r9 - cmp r14b, byte ptr [rsi + r9] + cmp r11b, byte ptr [rsi + r9] sete bl neg bl mov rdi, r9 @@ -12434,12 +12840,12 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 and cl, 6 mov dl, 1 shl dl, cl - movzx r9d, byte ptr [r11 + rdi] + movzx r9d, byte ptr [r14 + rdi] xor bl, r9b and dl, bl xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp r14b, byte ptr [rsi + rax + 1] + mov byte ptr [r14 + rdi], dl + cmp r11b, byte ptr [rsi + rax + 1] lea r9, [rax + 2] sete bl neg bl @@ -12449,32 +12855,32 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl al, cl and al, bl xor al, dl - mov byte ptr [r11 + rdi], al + mov byte ptr [r14 + rdi], al cmp r10, r9 - jne .LBB2_158 -.LBB2_159: + jne .LBB2_182 +.LBB2_183: add rsi, r9 +.LBB2_184: test r8b, 1 - je .LBB2_177 -.LBB2_161: - cmp r14b, byte ptr [rsi] + je .LBB2_200 +# %bb.185: + cmp r11b, byte ptr [rsi] sete al neg al mov rdx, r9 shr rdx, 3 - mov r8, qword ptr [rsp + 104] # 8-byte Reload + mov r8, qword ptr [rsp + 96] # 8-byte Reload mov dil, byte ptr [r8 + rdx] and r9b, 7 mov bl, 1 mov ecx, r9d - jmp .LBB2_175 -.LBB2_162: + jmp .LBB2_199 +.LBB2_186: mov r9, r8 and r9, -2 xor edi, edi - mov r14, qword ptr [rsp] # 8-byte Reload .p2align 4, 0x90 -.LBB2_163: # =>This Inner Loop Header: Depth=1 +.LBB2_187: # =>This Inner Loop Header: Depth=1 ucomisd xmm0, qword ptr [rdx] setnp cl sete al @@ -12482,7 +12888,8 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 neg al mov rsi, rdi shr rsi, 3 - movzx r10d, byte ptr [r14 + rsi] + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov r11b, 1 @@ -12490,7 +12897,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor al, r10b and r11b, al xor r11b, r10b - mov byte ptr [r14 + rsi], r11b + mov byte ptr [r12 + rsi], r11b add rdi, 2 ucomisd xmm0, qword ptr [rdx + 8] lea rdx, [rdx + 16] @@ -12504,13 +12911,13 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl bl, cl and bl, al xor bl, r11b - mov byte ptr [r14 + rsi], bl + mov byte ptr [r12 + rsi], bl cmp r9, rdi - jne .LBB2_163 -.LBB2_164: + jne .LBB2_187 +.LBB2_188: test r8b, 1 - je .LBB2_177 -# %bb.165: + je .LBB2_200 +# %bb.189: ucomisd xmm0, qword ptr [rdx] setnp al sete dl @@ -12518,8 +12925,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 neg dl mov rax, rdi shr rax, 3 - mov r8, qword ptr [rsp] # 8-byte Reload - mov sil, byte ptr [r8 + rax] + mov sil, byte ptr [r12 + rax] and dil, 7 mov bl, 1 mov ecx, edi @@ -12527,21 +12933,21 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor dl, sil and bl, dl xor bl, sil - mov byte ptr [r8 + rax], bl - jmp .LBB2_177 -.LBB2_166: + mov byte ptr [r12 + rax], bl + jmp .LBB2_200 +.LBB2_190: mov r10, r8 and r10, -2 xor edi, edi - mov r11, qword ptr [rsp] # 8-byte Reload .p2align 4, 0x90 -.LBB2_167: # =>This Inner Loop Header: Depth=1 +.LBB2_191: # =>This Inner Loop Header: Depth=1 cmp r13, qword ptr [rdx] sete al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r11 + rsi] + mov r11, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 @@ -12549,7 +12955,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r11 + rsi], bl + mov byte ptr [r12 + rsi], bl add rdi, 2 cmp r13, qword ptr [rdx + 8] lea rdx, [rdx + 16] @@ -12561,21 +12967,20 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 shl al, cl and al, r9b xor al, bl - mov byte ptr [r11 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, rdi - jne .LBB2_167 -.LBB2_168: + jne .LBB2_191 +.LBB2_192: test r8b, 1 - je .LBB2_177 -# %bb.169: + je .LBB2_200 +# %bb.193: cmp r13, qword ptr [rdx] -.LBB2_170: +.LBB2_194: sete al neg al mov rdx, rdi shr rdx, 3 - mov r8, qword ptr [rsp] # 8-byte Reload - mov sil, byte ptr [r8 + rdx] + mov sil, byte ptr [r12 + rdx] and dil, 7 mov bl, 1 mov ecx, edi @@ -12583,22 +12988,23 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor al, sil and bl, al xor bl, sil - jmp .LBB2_176 -.LBB2_171: + mov byte ptr [r12 + rdx], bl + jmp .LBB2_200 +.LBB2_195: mov r9, r8 and r9, -2 - xor r15d, r15d - mov r11, qword ptr [rsp + 16] # 8-byte Reload + xor r14d, r14d + mov r11, qword ptr [rsp] # 8-byte Reload .p2align 4, 0x90 -.LBB2_172: # =>This Inner Loop Header: Depth=1 +.LBB2_196: # =>This Inner Loop Header: Depth=1 mov rax, rsi - cmp r14w, word ptr [rsi] + cmp r13w, word ptr [rsi] sete dl neg dl - mov rdi, r15 + mov rdi, r14 shr rdi, 3 movzx r10d, byte ptr [r11 + rdi] - mov ecx, r15d + mov ecx, r14d and cl, 6 mov bl, 1 shl bl, cl @@ -12606,8 +13012,8 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 and bl, dl xor bl, r10b mov byte ptr [r11 + rdi], bl - add r15, 2 - cmp r14w, word ptr [rsi + 2] + add r14, 2 + cmp r13w, word ptr [rsi + 2] lea rsi, [rsi + 4] sete dl neg dl @@ -12618,30 +13024,29 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 and al, dl xor al, bl mov byte ptr [r11 + rdi], al - cmp r9, r15 - jne .LBB2_172 -.LBB2_173: + cmp r9, r14 + jne .LBB2_196 +.LBB2_197: test r8b, 1 - je .LBB2_177 -# %bb.174: - cmp r14w, word ptr [rsi] + je .LBB2_200 +# %bb.198: + cmp r13w, word ptr [rsi] sete al neg al - mov rdx, r15 + mov rdx, r14 shr rdx, 3 - mov r8, qword ptr [rsp + 16] # 8-byte Reload + mov r8, qword ptr [rsp] # 8-byte Reload mov dil, byte ptr [r8 + rdx] - and r15b, 7 + and r14b, 7 mov bl, 1 - mov ecx, r15d -.LBB2_175: + mov ecx, r14d +.LBB2_199: shl bl, cl xor al, dil and bl, al xor bl, dil -.LBB2_176: mov byte ptr [r8 + rdx], bl -.LBB2_177: +.LBB2_200: lea rsp, [rbp - 40] pop rbx pop r12 @@ -12650,13 +13055,13 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 pop r15 pop rbp ret -.LBB2_178: +.LBB2_201: mov r9, r8 and r9, -2 xor esi, esi - mov r14, r15 + mov r14, r13 .p2align 4, 0x90 -.LBB2_179: # =>This Inner Loop Header: Depth=1 +.LBB2_202: # =>This Inner Loop Header: Depth=1 ucomiss xmm0, dword ptr [rbx] setnp cl sete dl @@ -12688,11 +13093,11 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor al, r11b mov byte ptr [r14 + rdi], al cmp r9, rsi - jne .LBB2_179 -.LBB2_180: + jne .LBB2_202 +.LBB2_203: test r8b, 1 - je .LBB2_177 -# %bb.181: + je .LBB2_200 +# %bb.204: ucomiss xmm0, dword ptr [rbx] setnp al sete dl @@ -12700,7 +13105,7 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 neg dl mov rax, rsi shr rax, 3 - mov dil, byte ptr [r15 + rax] + mov dil, byte ptr [r13 + rax] and sil, 7 mov bl, 1 mov ecx, esi @@ -12708,2063 +13113,241 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 xor dl, dil and bl, dl xor bl, dil - mov byte ptr [r15 + rax], bl - jmp .LBB2_177 -.LBB2_182: - and r15, -16 - mov rax, r15 - shl rax, 5 + mov byte ptr [r13 + rax], bl + jmp .LBB2_200 +.LBB2_205: + and rcx, -8 + mov rax, rcx + shl rax, 6 add rax, rdx - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 224], r15 # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] - mov qword ptr [rsp + 104], rax # 8-byte Spill - movzx eax, r14b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill - xor eax, eax - .p2align 4, 0x90 -.LBB2_183: # =>This Inner Loop Header: Depth=1 - mov rdi, rax - mov qword ptr [rsp + 152], rax # 8-byte Spill - shl rdi, 5 - mov rsi, rdi - mov r10, rdi - mov r14, rdi - mov r15, rdi - mov r12, rdi - mov r11, rdi - mov rax, rdi - mov r9, rdi - mov rbx, rdi - mov qword ptr [rsp + 80], rdi # 8-byte Spill - mov qword ptr [rsp + 96], rdi # 8-byte Spill - movzx ecx, byte ptr [rdx + rdi] - movd xmm15, ecx - movzx ecx, byte ptr [rdx + rdi + 1] - movd xmm5, ecx - movzx ecx, byte ptr [rdx + rdi + 2] - movd xmm6, ecx - movzx ecx, byte ptr [rdx + rdi + 3] - movd xmm2, ecx - movzx ecx, byte ptr [rdx + rdi + 4] - movd xmm1, ecx - movzx ecx, byte ptr [rdx + rdi + 5] - movd xmm8, ecx - movzx ecx, byte ptr [rdx + rdi + 6] - movd xmm3, ecx - movzx ecx, byte ptr [rdx + rdi + 7] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rdi + 8] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rdi + 9] - movd xmm10, ecx - movzx ecx, byte ptr [rdx + rdi + 10] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rdi + 11] - movd xmm11, ecx - movzx ecx, byte ptr [rdx + rdi + 12] - movd xmm13, ecx - movzx ecx, byte ptr [rdx + rdi + 13] - movd xmm12, ecx - movzx ecx, byte ptr [rdx + rdi + 14] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - mov qword ptr [rsp + 64], rdi # 8-byte Spill - mov r13, rdi - or r13, 32 - mov qword ptr [rsp + 24], r13 # 8-byte Spill - or rsi, 64 - mov qword ptr [rsp + 40], rsi # 8-byte Spill - mov rcx, rdi - or rcx, 96 - or r14, 128 - or r15, 160 - or r10, 192 - or r11, 224 - or r12, 256 - or r9, 288 - mov qword ptr [rsp + 72], r9 # 8-byte Spill - or rbx, 320 - mov qword ptr [rsp + 120], rbx # 8-byte Spill - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - or rbx, 352 - mov qword ptr [rsp + 80], rbx # 8-byte Spill - mov r8, qword ptr [rsp + 96] # 8-byte Reload - or r8, 384 - mov qword ptr [rsp + 96], r8 # 8-byte Spill - or rax, 416 - mov qword ptr [rsp + 16], rax # 8-byte Spill - mov rax, rdi - or rax, 448 - mov qword ptr [rsp + 48], rax # 8-byte Spill - mov rax, rdi - or rax, 480 - pinsrb xmm15, byte ptr [rdx + r13], 1 - pinsrb xmm15, byte ptr [rdx + rsi], 2 - mov qword ptr [rsp + 56], rcx # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + rcx], 3 - mov qword ptr [rsp + 112], r14 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r14], 4 - mov qword ptr [rsp + 128], r15 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r15], 5 - mov rdi, r10 - pinsrb xmm15, byte ptr [rdx + r10], 6 - mov r10, r11 - mov qword ptr [rsp + 88], r11 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r11], 7 - pinsrb xmm15, byte ptr [rdx + r12], 8 - pinsrb xmm15, byte ptr [rdx + r9], 9 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r13], 10 - pinsrb xmm15, byte ptr [rdx + rbx], 11 - pinsrb xmm15, byte ptr [rdx + r8], 12 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi], 14 - pinsrb xmm15, byte ptr [rdx + rax], 15 - mov r11, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r11 + 1], 1 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 1], 2 - pinsrb xmm5, byte ptr [rdx + rcx + 1], 3 - pinsrb xmm5, byte ptr [rdx + r14 + 1], 4 - pinsrb xmm5, byte ptr [rdx + r15 + 1], 5 - pinsrb xmm5, byte ptr [rdx + rdi + 1], 6 - pinsrb xmm5, byte ptr [rdx + r10 + 1], 7 - pinsrb xmm5, byte ptr [rdx + r12 + 1], 8 - mov r14, r12 - mov qword ptr [rsp + 192], r12 # 8-byte Spill - pinsrb xmm5, byte ptr [rdx + r9 + 1], 9 - pinsrb xmm5, byte ptr [rdx + r13 + 1], 10 - mov r15, r13 - pinsrb xmm5, byte ptr [rdx + rbx + 1], 11 - pinsrb xmm5, byte ptr [rdx + r8 + 1], 12 - mov r9, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r9 + 1], 13 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r11 + 1], 14 - pinsrb xmm5, byte ptr [rdx + rax + 1], 15 - movdqa xmm9, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm5, xmm9 - movdqa xmm7, xmm5 - movdqa xmm4, xmmword ptr [rip + .LCPI2_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm7, xmm4 - psubb xmm7, xmm5 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - movzx esi, byte ptr [rdx + r12 + 15] - movd xmm14, esi - pcmpeqb xmm15, xmm9 - mov r8, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r8 + 2], 1 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r10 + 2], 2 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rcx + 2], 3 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rbx + 2], 4 - mov rsi, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 2], 5 - pinsrb xmm6, byte ptr [rdx + rdi + 2], 6 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 2], 7 - pinsrb xmm6, byte ptr [rdx + r14 + 2], 8 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r13 + 2], 9 - pinsrb xmm6, byte ptr [rdx + r15 + 2], 10 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r14 + 2], 11 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r15 + 2], 12 - pinsrb xmm6, byte ptr [rdx + r9 + 2], 13 - pinsrb xmm6, byte ptr [rdx + r11 + 2], 14 - mov r9, rax - pinsrb xmm6, byte ptr [rdx + rax + 2], 15 - pand xmm15, xmm4 - pcmpeqb xmm6, xmm9 - movdqa xmm0, xmmword ptr [rip + .LCPI2_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm6, xmm0 - por xmm6, xmm15 - movzx esi, byte ptr [rdx + r12 + 16] - movd xmm15, esi - mov rsi, r8 - pinsrb xmm2, byte ptr [rdx + r8 + 3], 1 - mov rax, r10 - pinsrb xmm2, byte ptr [rdx + r10 + 3], 2 - pinsrb xmm2, byte ptr [rdx + rcx + 3], 3 - pinsrb xmm2, byte ptr [rdx + rbx + 3], 4 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 3], 5 - mov qword ptr [rsp + 136], rdi # 8-byte Spill - pinsrb xmm2, byte ptr [rdx + rdi + 3], 6 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r8 + 3], 7 - mov r10, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r10 + 3], 8 - pinsrb xmm2, byte ptr [rdx + r13 + 3], 9 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rbx + 3], 10 - pinsrb xmm2, byte ptr [rdx + r14 + 3], 11 - pinsrb xmm2, byte ptr [rdx + r15 + 3], 12 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r12 + 3], 13 - pinsrb xmm2, byte ptr [rdx + r11 + 3], 14 - pinsrb xmm2, byte ptr [rdx + r9 + 3], 15 - pinsrb xmm1, byte ptr [rdx + rsi + 4], 1 - pinsrb xmm1, byte ptr [rdx + rax + 4], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rsi + 4], 3 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rsi + 4], 4 - pinsrb xmm1, byte ptr [rdx + rcx + 4], 5 - pinsrb xmm1, byte ptr [rdx + rdi + 4], 6 - pinsrb xmm1, byte ptr [rdx + r8 + 4], 7 - pinsrb xmm1, byte ptr [rdx + r10 + 4], 8 - pinsrb xmm1, byte ptr [rdx + r13 + 4], 9 - pinsrb xmm1, byte ptr [rdx + rbx + 4], 10 - pinsrb xmm1, byte ptr [rdx + r14 + 4], 11 - pinsrb xmm1, byte ptr [rdx + r15 + 4], 12 - pinsrb xmm1, byte ptr [rdx + r12 + 4], 13 - pinsrb xmm1, byte ptr [rdx + r11 + 4], 14 - pinsrb xmm1, byte ptr [rdx + r9 + 4], 15 - mov rcx, r9 - mov qword ptr [rsp + 32], r9 # 8-byte Spill - por xmm6, xmm7 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - movzx esi, byte ptr [rdx + r9 + 17] - movd xmm0, esi - pcmpeqb xmm2, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI2_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm2, xmm5 - pcmpeqb xmm1, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI2_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm1, xmm5 - por xmm1, xmm2 - movzx esi, byte ptr [rdx + r9 + 18] - movd xmm5, esi - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r13 + 5], 1 - pinsrb xmm8, byte ptr [rdx + rax + 5], 2 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r11 + 5], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rax + 5], 4 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rdi + 5], 5 - mov r8, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r8 + 5], 6 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r10 + 5], 7 - mov rbx, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rbx + 5], 8 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rsi + 5], 9 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r14 + 5], 10 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r15 + 5], 11 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r12 + 5], 12 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rsi + 5], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rsi + 5], 14 - pinsrb xmm8, byte ptr [rdx + rcx + 5], 15 - pcmpeqb xmm8, xmm9 - movdqa xmm2, xmmword ptr [rip + .LCPI2_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm8, xmm2 - por xmm8, xmm1 - movzx esi, byte ptr [rdx + r9 + 19] - movd xmm7, esi - por xmm8, xmm6 - movzx esi, byte ptr [rdx + r9 + 20] - movd xmm6, esi - pinsrb xmm3, byte ptr [rdx + r13 + 6], 1 - mov r9, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r9 + 6], 2 - pinsrb xmm3, byte ptr [rdx + r11 + 6], 3 - pinsrb xmm3, byte ptr [rdx + rax + 6], 4 - mov rcx, rdi - pinsrb xmm3, byte ptr [rdx + rdi + 6], 5 - mov rdi, r8 - pinsrb xmm3, byte ptr [rdx + r8 + 6], 6 - pinsrb xmm3, byte ptr [rdx + r10 + 6], 7 - mov r10, rbx - pinsrb xmm3, byte ptr [rdx + rbx + 6], 8 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rax + 6], 9 - mov rbx, r14 - pinsrb xmm3, byte ptr [rdx + r14 + 6], 10 - mov rsi, r15 - pinsrb xmm3, byte ptr [rdx + r15 + 6], 11 - mov r15, r12 - pinsrb xmm3, byte ptr [rdx + r12 + 6], 12 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r12 + 6], 13 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r14 + 6], 14 - mov r8, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r8 + 6], 15 - movdqa xmm2, xmmword ptr [rsp + 208] # 16-byte Reload - pinsrb xmm2, byte ptr [rdx + r13 + 7], 1 - pinsrb xmm2, byte ptr [rdx + r9 + 7], 2 - pinsrb xmm2, byte ptr [rdx + r11 + 7], 3 - mov r13, r11 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r9 + 7], 4 - pinsrb xmm2, byte ptr [rdx + rcx + 7], 5 - pinsrb xmm2, byte ptr [rdx + rdi + 7], 6 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 7], 7 - pinsrb xmm2, byte ptr [rdx + r10 + 7], 8 - pinsrb xmm2, byte ptr [rdx + rax + 7], 9 - pinsrb xmm2, byte ptr [rdx + rbx + 7], 10 - pinsrb xmm2, byte ptr [rdx + rsi + 7], 11 - pinsrb xmm2, byte ptr [rdx + r15 + 7], 12 - pinsrb xmm2, byte ptr [rdx + r12 + 7], 13 - mov r15, r12 - pinsrb xmm2, byte ptr [rdx + r14 + 7], 14 - pinsrb xmm2, byte ptr [rdx + r8 + 7], 15 - pcmpeqb xmm3, xmm9 - movdqa xmm1, xmmword ptr [rip + .LCPI2_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm1 - pcmpeqb xmm2, xmm9 - psllw xmm2, 7 - movdqa xmm1, xmmword ptr [rip + .LCPI2_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm2, xmm1 - por xmm2, xmm3 - movdqa xmm1, xmm2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 21] - movd xmm2, esi - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rcx + 9], 1 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r11 + 9], 2 - pinsrb xmm10, byte ptr [rdx + r13 + 9], 3 - pinsrb xmm10, byte ptr [rdx + r9 + 9], 4 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r13 + 9], 5 - pinsrb xmm10, byte ptr [rdx + rdi + 9], 6 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r8 + 9], 7 - pinsrb xmm10, byte ptr [rdx + r10 + 9], 8 - mov r14, r10 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 9], 9 - pinsrb xmm10, byte ptr [rdx + rbx + 9], 10 - mov r12, rbx - mov r10, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r10 + 9], 11 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rbx + 9], 12 - pinsrb xmm10, byte ptr [rdx + r15 + 9], 13 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rdi + 9], 14 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 9], 15 - por xmm1, xmm8 - movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill - pcmpeqb xmm10, xmm9 - movdqa xmm1, xmm10 - movdqa xmm8, xmm4 - pand xmm1, xmm4 - psubb xmm1, xmm10 - movzx esi, byte ptr [rdx + rax + 22] - movd xmm3, esi - movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload - pinsrb xmm4, byte ptr [rdx + rcx + 8], 1 - pinsrb xmm4, byte ptr [rdx + r11 + 8], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 8], 3 - pinsrb xmm4, byte ptr [rdx + r9 + 8], 4 - pinsrb xmm4, byte ptr [rdx + r13 + 8], 5 - mov r15, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r15 + 8], 6 - pinsrb xmm4, byte ptr [rdx + r8 + 8], 7 - pinsrb xmm4, byte ptr [rdx + r14 + 8], 8 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rsi + 8], 9 - pinsrb xmm4, byte ptr [rdx + r12 + 8], 10 - pinsrb xmm4, byte ptr [rdx + r10 + 8], 11 - pinsrb xmm4, byte ptr [rdx + rbx + 8], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rbx + 8], 13 - pinsrb xmm4, byte ptr [rdx + rdi + 8], 14 - mov r10, rdi - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rcx + 8], 15 - pcmpeqb xmm4, xmm9 - pand xmm4, xmm8 - movdqa xmm10, xmmword ptr [rsp + 160] # 16-byte Reload - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rdi + 10], 1 - pinsrb xmm10, byte ptr [rdx + r11 + 10], 2 - pinsrb xmm10, byte ptr [rdx + rax + 10], 3 - pinsrb xmm10, byte ptr [rdx + r9 + 10], 4 - mov rax, r9 - mov r11, r13 - pinsrb xmm10, byte ptr [rdx + r13 + 10], 5 - mov r9, r15 - pinsrb xmm10, byte ptr [rdx + r15 + 10], 6 - pinsrb xmm10, byte ptr [rdx + r8 + 10], 7 - pinsrb xmm10, byte ptr [rdx + r14 + 10], 8 - pinsrb xmm10, byte ptr [rdx + rsi + 10], 9 - pinsrb xmm10, byte ptr [rdx + r12 + 10], 10 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r14 + 10], 11 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r15 + 10], 12 - pinsrb xmm10, byte ptr [rdx + rbx + 10], 13 - mov r13, rbx - pinsrb xmm10, byte ptr [rdx + r10 + 10], 14 - pinsrb xmm10, byte ptr [rdx + rcx + 10], 15 - pcmpeqb xmm10, xmm9 - pand xmm10, xmmword ptr [rip + .LCPI2_11] - por xmm10, xmm4 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 23] - movd xmm8, esi - por xmm10, xmm1 - movdqa xmmword ptr [rsp + 160], xmm10 # 16-byte Spill - movzx esi, byte ptr [rdx + rcx + 24] - movd xmm10, esi - pinsrb xmm11, byte ptr [rdx + rdi + 11], 1 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rcx + 11], 2 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rcx + 11], 3 - pinsrb xmm11, byte ptr [rdx + rax + 11], 4 - mov rcx, r11 - pinsrb xmm11, byte ptr [rdx + r11 + 11], 5 - mov rdi, r9 - pinsrb xmm11, byte ptr [rdx + r9 + 11], 6 - pinsrb xmm11, byte ptr [rdx + r8 + 11], 7 - mov r9, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r9 + 11], 8 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r11 + 11], 9 - pinsrb xmm11, byte ptr [rdx + r12 + 11], 10 - pinsrb xmm11, byte ptr [rdx + r14 + 11], 11 - pinsrb xmm11, byte ptr [rdx + r15 + 11], 12 - mov r10, rbx - pinsrb xmm11, byte ptr [rdx + rbx + 11], 13 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r12 + 11], 14 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rsi + 11], 15 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + r13 + 12], 1 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rbx + 12], 2 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rbx + 12], 3 - pinsrb xmm13, byte ptr [rdx + rax + 12], 4 - pinsrb xmm13, byte ptr [rdx + rcx + 12], 5 - pinsrb xmm13, byte ptr [rdx + rdi + 12], 6 - pinsrb xmm13, byte ptr [rdx + r8 + 12], 7 - pinsrb xmm13, byte ptr [rdx + r9 + 12], 8 - pinsrb xmm13, byte ptr [rdx + r11 + 12], 9 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rbx + 12], 10 - pinsrb xmm13, byte ptr [rdx + r14 + 12], 11 - pinsrb xmm13, byte ptr [rdx + r15 + 12], 12 - pinsrb xmm13, byte ptr [rdx + r10 + 12], 13 - mov r13, r10 - pinsrb xmm13, byte ptr [rdx + r12 + 12], 14 - pinsrb xmm13, byte ptr [rdx + rsi + 12], 15 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + r10 + 13], 1 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rsi + 13], 2 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rsi + 13], 3 - pinsrb xmm12, byte ptr [rdx + rax + 13], 4 - pinsrb xmm12, byte ptr [rdx + rcx + 13], 5 - pinsrb xmm12, byte ptr [rdx + rdi + 13], 6 - pinsrb xmm12, byte ptr [rdx + r8 + 13], 7 - pinsrb xmm12, byte ptr [rdx + r9 + 13], 8 - pinsrb xmm12, byte ptr [rdx + r11 + 13], 9 - pinsrb xmm12, byte ptr [rdx + rbx + 13], 10 - pinsrb xmm12, byte ptr [rdx + r14 + 13], 11 - pinsrb xmm12, byte ptr [rdx + r15 + 13], 12 - pinsrb xmm12, byte ptr [rdx + r13 + 13], 13 - pinsrb xmm12, byte ptr [rdx + r12 + 13], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rax + 13], 15 - pcmpeqb xmm11, xmm9 - pand xmm11, xmmword ptr [rip + .LCPI2_12] - pcmpeqb xmm13, xmm9 - pand xmm13, xmmword ptr [rip + .LCPI2_13] - por xmm13, xmm11 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 25] - movd xmm1, esi - pcmpeqb xmm12, xmm9 - pand xmm12, xmmword ptr [rip + .LCPI2_14] - por xmm12, xmm13 - movzx esi, byte ptr [rdx + rax + 26] - movd xmm11, esi - movdqa xmm4, xmmword ptr [rsp + 240] # 16-byte Reload - pinsrb xmm4, byte ptr [rdx + r10 + 14], 1 - mov rsi, r10 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r12 + 14], 2 - mov r10, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r10 + 14], 3 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r13 + 14], 4 - pinsrb xmm4, byte ptr [rdx + rcx + 14], 5 - pinsrb xmm4, byte ptr [rdx + rdi + 14], 6 - pinsrb xmm4, byte ptr [rdx + r8 + 14], 7 - pinsrb xmm4, byte ptr [rdx + r9 + 14], 8 - pinsrb xmm4, byte ptr [rdx + r11 + 14], 9 - pinsrb xmm4, byte ptr [rdx + rbx + 14], 10 - pinsrb xmm4, byte ptr [rdx + r14 + 14], 11 - pinsrb xmm4, byte ptr [rdx + r15 + 14], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 14], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 14], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 14], 15 - pinsrb xmm14, byte ptr [rdx + rsi + 15], 1 - pinsrb xmm14, byte ptr [rdx + r12 + 15], 2 - pinsrb xmm14, byte ptr [rdx + r10 + 15], 3 - pinsrb xmm14, byte ptr [rdx + r13 + 15], 4 - pinsrb xmm14, byte ptr [rdx + rcx + 15], 5 - pinsrb xmm14, byte ptr [rdx + rdi + 15], 6 - pinsrb xmm14, byte ptr [rdx + r8 + 15], 7 - pinsrb xmm14, byte ptr [rdx + r9 + 15], 8 - pinsrb xmm14, byte ptr [rdx + r11 + 15], 9 - pinsrb xmm14, byte ptr [rdx + rbx + 15], 10 - pinsrb xmm14, byte ptr [rdx + r14 + 15], 11 - pinsrb xmm14, byte ptr [rdx + r15 + 15], 12 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rsi + 15], 13 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rax + 15], 14 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rsi + 15], 15 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi + 16], 1 - pinsrb xmm15, byte ptr [rdx + r12 + 16], 2 - pinsrb xmm15, byte ptr [rdx + r10 + 16], 3 - pinsrb xmm15, byte ptr [rdx + r13 + 16], 4 - pinsrb xmm15, byte ptr [rdx + rcx + 16], 5 - pinsrb xmm15, byte ptr [rdx + rdi + 16], 6 - pinsrb xmm15, byte ptr [rdx + r8 + 16], 7 - pinsrb xmm15, byte ptr [rdx + r9 + 16], 8 - pinsrb xmm15, byte ptr [rdx + r11 + 16], 9 - pinsrb xmm15, byte ptr [rdx + rbx + 16], 10 - pinsrb xmm15, byte ptr [rdx + r14 + 16], 11 - pinsrb xmm15, byte ptr [rdx + r15 + 16], 12 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi + 16], 13 - pinsrb xmm15, byte ptr [rdx + rax + 16], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 17], 1 - pinsrb xmm0, byte ptr [rdx + r12 + 17], 2 - pinsrb xmm0, byte ptr [rdx + r10 + 17], 3 - pinsrb xmm0, byte ptr [rdx + r13 + 17], 4 - pinsrb xmm0, byte ptr [rdx + rcx + 17], 5 - pinsrb xmm0, byte ptr [rdx + rdi + 17], 6 - pinsrb xmm0, byte ptr [rdx + r8 + 17], 7 - mov rax, r8 - pinsrb xmm0, byte ptr [rdx + r9 + 17], 8 - pinsrb xmm0, byte ptr [rdx + r11 + 17], 9 - pinsrb xmm0, byte ptr [rdx + rbx + 17], 10 - pinsrb xmm0, byte ptr [rdx + r14 + 17], 11 - pinsrb xmm0, byte ptr [rdx + r15 + 17], 12 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 17], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 17], 14 - por xmm12, xmmword ptr [rsp + 160] # 16-byte Folded Reload - mov r12, qword ptr [rsp + 64] # 8-byte Reload - movzx esi, byte ptr [rdx + r12 + 27] - movd xmm9, esi - movdqa xmm13, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm4, xmm13 - pand xmm4, xmmword ptr [rip + .LCPI2_15] - pcmpeqb xmm14, xmm13 - psllw xmm14, 7 - pand xmm14, xmmword ptr [rip + .LCPI2_6] - por xmm14, xmm4 - movzx esi, byte ptr [rdx + r12 + 28] - movd xmm4, esi - mov r8, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r8 + 17], 15 - por xmm14, xmm12 - pcmpeqb xmm0, xmm13 - movdqa xmm13, xmm0 - movdqa xmm12, xmmword ptr [rip + .LCPI2_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm13, xmm12 - psubb xmm13, xmm0 - movdqa xmmword ptr [rsp + 160], xmm13 # 16-byte Spill - movzx esi, byte ptr [rdx + r12 + 29] - movd xmm13, esi - pinsrb xmm15, byte ptr [rdx + r8 + 16], 15 - movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm15, xmm0 - mov r12, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r12 + 18], 1 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 18], 2 - pinsrb xmm5, byte ptr [rdx + r10 + 18], 3 - pinsrb xmm5, byte ptr [rdx + r13 + 18], 4 - pinsrb xmm5, byte ptr [rdx + rcx + 18], 5 - pinsrb xmm5, byte ptr [rdx + rdi + 18], 6 - pinsrb xmm5, byte ptr [rdx + rax + 18], 7 - pinsrb xmm5, byte ptr [rdx + r9 + 18], 8 - pinsrb xmm5, byte ptr [rdx + r11 + 18], 9 - pinsrb xmm5, byte ptr [rdx + rbx + 18], 10 - pinsrb xmm5, byte ptr [rdx + r14 + 18], 11 - pinsrb xmm5, byte ptr [rdx + r15 + 18], 12 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 18], 13 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 18], 14 - pand xmm15, xmm12 - pinsrb xmm5, byte ptr [rdx + r8 + 18], 15 - pcmpeqb xmm5, xmm0 - pand xmm5, xmmword ptr [rip + .LCPI2_11] - por xmm5, xmm15 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 30] - movd xmm12, esi - pinsrb xmm7, byte ptr [rdx + r12 + 19], 1 - pinsrb xmm6, byte ptr [rdx + r12 + 20], 1 - pinsrb xmm2, byte ptr [rdx + r12 + 21], 1 - pinsrb xmm3, byte ptr [rdx + r12 + 22], 1 - pinsrb xmm8, byte ptr [rdx + r12 + 23], 1 - pinsrb xmm10, byte ptr [rdx + r12 + 24], 1 - pinsrb xmm1, byte ptr [rdx + r12 + 25], 1 - pinsrb xmm11, byte ptr [rdx + r12 + 26], 1 - pinsrb xmm9, byte ptr [rdx + r12 + 27], 1 - pinsrb xmm4, byte ptr [rdx + r12 + 28], 1 - pinsrb xmm13, byte ptr [rdx + r12 + 29], 1 - pinsrb xmm12, byte ptr [rdx + r12 + 30], 1 - movzx esi, byte ptr [rdx + rax + 31] - movd xmm0, esi - pinsrb xmm0, byte ptr [rdx + r12 + 31], 1 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 19], 2 - pinsrb xmm6, byte ptr [rdx + rsi + 20], 2 - pinsrb xmm2, byte ptr [rdx + rsi + 21], 2 - pinsrb xmm3, byte ptr [rdx + rsi + 22], 2 - pinsrb xmm8, byte ptr [rdx + rsi + 23], 2 - pinsrb xmm10, byte ptr [rdx + rsi + 24], 2 - pinsrb xmm1, byte ptr [rdx + rsi + 25], 2 - pinsrb xmm11, byte ptr [rdx + rsi + 26], 2 - pinsrb xmm9, byte ptr [rdx + rsi + 27], 2 - pinsrb xmm4, byte ptr [rdx + rsi + 28], 2 - pinsrb xmm13, byte ptr [rdx + rsi + 29], 2 - pinsrb xmm12, byte ptr [rdx + rsi + 30], 2 - pinsrb xmm0, byte ptr [rdx + rsi + 31], 2 - pinsrb xmm7, byte ptr [rdx + r10 + 19], 3 - pinsrb xmm7, byte ptr [rdx + r13 + 19], 4 - pinsrb xmm7, byte ptr [rdx + rcx + 19], 5 - pinsrb xmm7, byte ptr [rdx + rdi + 19], 6 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 19], 7 - pinsrb xmm7, byte ptr [rdx + r9 + 19], 8 - pinsrb xmm7, byte ptr [rdx + r11 + 19], 9 - pinsrb xmm7, byte ptr [rdx + rbx + 19], 10 - pinsrb xmm7, byte ptr [rdx + r14 + 19], 11 - pinsrb xmm7, byte ptr [rdx + r15 + 19], 12 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 19], 13 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r12 + 19], 14 - pinsrb xmm7, byte ptr [rdx + r8 + 19], 15 - pinsrb xmm6, byte ptr [rdx + r10 + 20], 3 - pinsrb xmm6, byte ptr [rdx + r13 + 20], 4 - pinsrb xmm6, byte ptr [rdx + rcx + 20], 5 - pinsrb xmm6, byte ptr [rdx + rdi + 20], 6 - pinsrb xmm6, byte ptr [rdx + rax + 20], 7 - pinsrb xmm6, byte ptr [rdx + r9 + 20], 8 - pinsrb xmm6, byte ptr [rdx + r11 + 20], 9 - pinsrb xmm6, byte ptr [rdx + rbx + 20], 10 - pinsrb xmm6, byte ptr [rdx + r14 + 20], 11 - pinsrb xmm6, byte ptr [rdx + r15 + 20], 12 - pinsrb xmm6, byte ptr [rdx + rsi + 20], 13 - pinsrb xmm6, byte ptr [rdx + r12 + 20], 14 - por xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload - pinsrb xmm6, byte ptr [rdx + r8 + 20], 15 - movdqa xmm15, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm7, xmm15 - pand xmm7, xmmword ptr [rip + .LCPI2_12] - pcmpeqb xmm6, xmm15 - pand xmm6, xmmword ptr [rip + .LCPI2_13] - por xmm6, xmm7 - pinsrb xmm2, byte ptr [rdx + r10 + 21], 3 - pinsrb xmm2, byte ptr [rdx + r13 + 21], 4 - pinsrb xmm2, byte ptr [rdx + rcx + 21], 5 - pinsrb xmm2, byte ptr [rdx + rdi + 21], 6 - pinsrb xmm2, byte ptr [rdx + rax + 21], 7 - pinsrb xmm2, byte ptr [rdx + r9 + 21], 8 - pinsrb xmm2, byte ptr [rdx + r11 + 21], 9 - pinsrb xmm2, byte ptr [rdx + rbx + 21], 10 - pinsrb xmm2, byte ptr [rdx + r14 + 21], 11 - pinsrb xmm2, byte ptr [rdx + r15 + 21], 12 - pinsrb xmm2, byte ptr [rdx + rsi + 21], 13 - pinsrb xmm2, byte ptr [rdx + r12 + 21], 14 - pinsrb xmm2, byte ptr [rdx + r8 + 21], 15 - pcmpeqb xmm2, xmm15 - movdqa xmm7, xmmword ptr [rip + .LCPI2_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm2, xmm7 - por xmm2, xmm6 - por xmm2, xmm5 - pinsrb xmm3, byte ptr [rdx + r10 + 22], 3 - pinsrb xmm3, byte ptr [rdx + r13 + 22], 4 - pinsrb xmm3, byte ptr [rdx + rcx + 22], 5 - pinsrb xmm3, byte ptr [rdx + rdi + 22], 6 - pinsrb xmm3, byte ptr [rdx + rax + 22], 7 - pinsrb xmm3, byte ptr [rdx + r9 + 22], 8 - pinsrb xmm3, byte ptr [rdx + r11 + 22], 9 - pinsrb xmm3, byte ptr [rdx + rbx + 22], 10 - pinsrb xmm3, byte ptr [rdx + r14 + 22], 11 - pinsrb xmm3, byte ptr [rdx + r15 + 22], 12 - pinsrb xmm3, byte ptr [rdx + rsi + 22], 13 - pinsrb xmm3, byte ptr [rdx + r12 + 22], 14 - pinsrb xmm3, byte ptr [rdx + r8 + 22], 15 - pinsrb xmm8, byte ptr [rdx + r10 + 23], 3 - pinsrb xmm8, byte ptr [rdx + r13 + 23], 4 - pinsrb xmm8, byte ptr [rdx + rcx + 23], 5 - pinsrb xmm8, byte ptr [rdx + rdi + 23], 6 - pinsrb xmm8, byte ptr [rdx + rax + 23], 7 - pinsrb xmm8, byte ptr [rdx + r9 + 23], 8 - pinsrb xmm8, byte ptr [rdx + r11 + 23], 9 - pinsrb xmm8, byte ptr [rdx + rbx + 23], 10 - pinsrb xmm8, byte ptr [rdx + r14 + 23], 11 - pinsrb xmm8, byte ptr [rdx + r15 + 23], 12 - pinsrb xmm8, byte ptr [rdx + rsi + 23], 13 - pinsrb xmm8, byte ptr [rdx + r12 + 23], 14 - pinsrb xmm8, byte ptr [rdx + r8 + 23], 15 - pcmpeqb xmm3, xmm15 - movdqa xmm5, xmmword ptr [rip + .LCPI2_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm5 - pcmpeqb xmm8, xmm15 - psllw xmm8, 7 - movdqa xmm6, xmmword ptr [rip + .LCPI2_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm8, xmm6 - por xmm8, xmm3 - pinsrb xmm1, byte ptr [rdx + r10 + 25], 3 - pinsrb xmm1, byte ptr [rdx + r13 + 25], 4 - pinsrb xmm1, byte ptr [rdx + rcx + 25], 5 - pinsrb xmm1, byte ptr [rdx + rdi + 25], 6 - pinsrb xmm1, byte ptr [rdx + rax + 25], 7 - pinsrb xmm1, byte ptr [rdx + r9 + 25], 8 - pinsrb xmm1, byte ptr [rdx + r11 + 25], 9 - pinsrb xmm1, byte ptr [rdx + rbx + 25], 10 - pinsrb xmm1, byte ptr [rdx + r14 + 25], 11 - pinsrb xmm1, byte ptr [rdx + r15 + 25], 12 - pinsrb xmm1, byte ptr [rdx + rsi + 25], 13 - pinsrb xmm1, byte ptr [rdx + r12 + 25], 14 - pinsrb xmm1, byte ptr [rdx + r8 + 25], 15 - por xmm8, xmm2 - pcmpeqb xmm1, xmm15 - movdqa xmm2, xmm1 - movdqa xmm3, xmmword ptr [rip + .LCPI2_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm2, xmm3 - psubb xmm2, xmm1 - pinsrb xmm10, byte ptr [rdx + r10 + 24], 3 - pinsrb xmm10, byte ptr [rdx + r13 + 24], 4 - pinsrb xmm10, byte ptr [rdx + rcx + 24], 5 - pinsrb xmm10, byte ptr [rdx + rdi + 24], 6 - pinsrb xmm10, byte ptr [rdx + rax + 24], 7 - pinsrb xmm10, byte ptr [rdx + r9 + 24], 8 - pinsrb xmm10, byte ptr [rdx + r11 + 24], 9 - pinsrb xmm10, byte ptr [rdx + rbx + 24], 10 - pinsrb xmm10, byte ptr [rdx + r14 + 24], 11 - pinsrb xmm10, byte ptr [rdx + r15 + 24], 12 - pinsrb xmm10, byte ptr [rdx + rsi + 24], 13 - pinsrb xmm10, byte ptr [rdx + r12 + 24], 14 - pinsrb xmm10, byte ptr [rdx + r8 + 24], 15 - pcmpeqb xmm10, xmm15 - pand xmm10, xmm3 - pinsrb xmm11, byte ptr [rdx + r10 + 26], 3 - pinsrb xmm11, byte ptr [rdx + r13 + 26], 4 - pinsrb xmm11, byte ptr [rdx + rcx + 26], 5 - pinsrb xmm11, byte ptr [rdx + rdi + 26], 6 - pinsrb xmm11, byte ptr [rdx + rax + 26], 7 - pinsrb xmm11, byte ptr [rdx + r9 + 26], 8 - pinsrb xmm11, byte ptr [rdx + r11 + 26], 9 - pinsrb xmm11, byte ptr [rdx + rbx + 26], 10 - pinsrb xmm11, byte ptr [rdx + r14 + 26], 11 - pinsrb xmm11, byte ptr [rdx + r15 + 26], 12 - pinsrb xmm11, byte ptr [rdx + rsi + 26], 13 - pinsrb xmm11, byte ptr [rdx + r12 + 26], 14 - pinsrb xmm11, byte ptr [rdx + r8 + 26], 15 - pcmpeqb xmm11, xmm15 - pand xmm11, xmmword ptr [rip + .LCPI2_11] - por xmm11, xmm10 - por xmm11, xmm2 - pinsrb xmm9, byte ptr [rdx + r10 + 27], 3 - pinsrb xmm9, byte ptr [rdx + r13 + 27], 4 - pinsrb xmm9, byte ptr [rdx + rcx + 27], 5 - pinsrb xmm9, byte ptr [rdx + rdi + 27], 6 - pinsrb xmm9, byte ptr [rdx + rax + 27], 7 - pinsrb xmm9, byte ptr [rdx + r9 + 27], 8 - pinsrb xmm9, byte ptr [rdx + r11 + 27], 9 - pinsrb xmm9, byte ptr [rdx + rbx + 27], 10 - pinsrb xmm9, byte ptr [rdx + r14 + 27], 11 - pinsrb xmm9, byte ptr [rdx + r15 + 27], 12 - pinsrb xmm9, byte ptr [rdx + rsi + 27], 13 - pinsrb xmm9, byte ptr [rdx + r12 + 27], 14 - pinsrb xmm9, byte ptr [rdx + r8 + 27], 15 - pinsrb xmm4, byte ptr [rdx + r10 + 28], 3 - pinsrb xmm4, byte ptr [rdx + r13 + 28], 4 - pinsrb xmm4, byte ptr [rdx + rcx + 28], 5 - pinsrb xmm4, byte ptr [rdx + rdi + 28], 6 - pinsrb xmm4, byte ptr [rdx + rax + 28], 7 - pinsrb xmm4, byte ptr [rdx + r9 + 28], 8 - pinsrb xmm4, byte ptr [rdx + r11 + 28], 9 - pinsrb xmm4, byte ptr [rdx + rbx + 28], 10 - pinsrb xmm4, byte ptr [rdx + r14 + 28], 11 - pinsrb xmm4, byte ptr [rdx + r15 + 28], 12 - pinsrb xmm4, byte ptr [rdx + rsi + 28], 13 - pinsrb xmm4, byte ptr [rdx + r12 + 28], 14 - pinsrb xmm4, byte ptr [rdx + r8 + 28], 15 - pinsrb xmm13, byte ptr [rdx + r10 + 29], 3 - pinsrb xmm13, byte ptr [rdx + r13 + 29], 4 - pinsrb xmm13, byte ptr [rdx + rcx + 29], 5 - pinsrb xmm13, byte ptr [rdx + rdi + 29], 6 - pinsrb xmm13, byte ptr [rdx + rax + 29], 7 - pinsrb xmm13, byte ptr [rdx + r9 + 29], 8 - pinsrb xmm13, byte ptr [rdx + r11 + 29], 9 - pinsrb xmm13, byte ptr [rdx + rbx + 29], 10 - pinsrb xmm13, byte ptr [rdx + r14 + 29], 11 - pinsrb xmm13, byte ptr [rdx + r15 + 29], 12 - pinsrb xmm13, byte ptr [rdx + rsi + 29], 13 - pinsrb xmm13, byte ptr [rdx + r12 + 29], 14 - movdqa xmm1, xmm15 - pcmpeqb xmm9, xmm15 - pand xmm9, xmmword ptr [rip + .LCPI2_12] - pcmpeqb xmm4, xmm15 - pand xmm4, xmmword ptr [rip + .LCPI2_13] - por xmm4, xmm9 - pinsrb xmm13, byte ptr [rdx + r8 + 29], 15 - pcmpeqb xmm13, xmm15 - pand xmm13, xmm7 - por xmm13, xmm4 - pinsrb xmm12, byte ptr [rdx + r10 + 30], 3 - pinsrb xmm0, byte ptr [rdx + r10 + 31], 3 - pinsrb xmm12, byte ptr [rdx + r13 + 30], 4 - pinsrb xmm0, byte ptr [rdx + r13 + 31], 4 - pinsrb xmm12, byte ptr [rdx + rcx + 30], 5 - pinsrb xmm0, byte ptr [rdx + rcx + 31], 5 - pinsrb xmm12, byte ptr [rdx + rdi + 30], 6 - pinsrb xmm0, byte ptr [rdx + rdi + 31], 6 - pinsrb xmm12, byte ptr [rdx + rax + 30], 7 - pinsrb xmm0, byte ptr [rdx + rax + 31], 7 - pinsrb xmm12, byte ptr [rdx + r9 + 30], 8 - pinsrb xmm0, byte ptr [rdx + r9 + 31], 8 - pinsrb xmm12, byte ptr [rdx + r11 + 30], 9 - pinsrb xmm0, byte ptr [rdx + r11 + 31], 9 - pinsrb xmm12, byte ptr [rdx + rbx + 30], 10 - pinsrb xmm0, byte ptr [rdx + rbx + 31], 10 - pinsrb xmm12, byte ptr [rdx + r14 + 30], 11 - pinsrb xmm0, byte ptr [rdx + r14 + 31], 11 - pinsrb xmm12, byte ptr [rdx + r15 + 30], 12 - pinsrb xmm0, byte ptr [rdx + r15 + 31], 12 - pinsrb xmm12, byte ptr [rdx + rsi + 30], 13 - pinsrb xmm0, byte ptr [rdx + rsi + 31], 13 - pinsrb xmm12, byte ptr [rdx + r12 + 30], 14 - pinsrb xmm0, byte ptr [rdx + r12 + 31], 14 - pinsrb xmm12, byte ptr [rdx + r8 + 30], 15 - pinsrb xmm0, byte ptr [rdx + r8 + 31], 15 - por xmm13, xmm11 - pcmpeqb xmm12, xmm15 - pand xmm12, xmm5 - pcmpeqb xmm0, xmm15 - psllw xmm0, 7 - pand xmm0, xmm6 - por xmm0, xmm12 - por xmm0, xmm13 - movdqa xmm1, xmm8 - punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - movdqa xmm4, xmmword ptr [rsp + 208] # 16-byte Reload - movdqa xmm2, xmm4 - punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] - movdqa xmm3, xmm2 - punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] - punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] - punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] - punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - mov rax, qword ptr [rsp] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx + 48], xmm4 - movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 - movdqu xmmword ptr [rax + 4*rcx], xmm3 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 224] # 8-byte Folded Reload - jne .LBB2_183 -# %bb.184: - mov r15, qword ptr [rsp + 232] # 8-byte Reload - cmp r15, qword ptr [rsp + 224] # 8-byte Folded Reload - mov r14b, byte ptr [rsp + 8] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - jne .LBB2_43 - jmp .LBB2_131 -.LBB2_185: - and r15, -16 - mov rax, r15 - shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 224], r15 # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] - mov qword ptr [rsp + 104], rax # 8-byte Spill - movzx eax, r14b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill - xor eax, eax + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 24], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp], rax # 8-byte Spill + mov dword ptr [rsp + 48], r13d # 4-byte Spill + movd xmm0, r13d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] + xor r15d, r15d + movdqa xmm15, xmmword ptr [rip + .LCPI2_8] # xmm15 = <1,1,1,1,1,1,1,1,u,u,u,u,u,u,u,u> + movdqa xmm9, xmmword ptr [rip + .LCPI2_1] # xmm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + movdqa xmm10, xmmword ptr [rip + .LCPI2_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + movdqa xmm11, xmmword ptr [rip + .LCPI2_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + movdqa xmm12, xmmword ptr [rip + .LCPI2_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + movdqa xmm13, xmmword ptr [rip + .LCPI2_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] + movdqa xmm14, xmmword ptr [rip + .LCPI2_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + mov qword ptr [rsp + 128], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB2_186: # =>This Inner Loop Header: Depth=1 - mov r15, rax - mov qword ptr [rsp + 152], rax # 8-byte Spill - shl r15, 5 +.LBB2_206: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 16], r15 # 8-byte Spill + shl r15, 6 + mov r8, r15 + mov r12, r15 + mov rdi, r15 + mov rcx, r15 mov rbx, r15 mov rax, r15 - mov rcx, r15 - mov rdi, r15 - mov r8, r15 + movzx r14d, word ptr [rdx + r15] + movzx esi, word ptr [rdx + r15 + 2] + movzx r11d, word ptr [rdx + r15 + 4] + movzx r13d, word ptr [rdx + r15 + 6] + movzx r10d, word ptr [rdx + r15 + 8] mov r9, r15 - mov r11, r15 - mov r12, r15 - mov r10, r15 - mov r13, r15 - mov qword ptr [rsp + 56], r15 # 8-byte Spill - movzx esi, byte ptr [rdx + r15] - movd xmm15, esi - movzx esi, byte ptr [rdx + r15 + 1] - movd xmm5, esi - movzx esi, byte ptr [rdx + r15 + 2] + or r9, 64 + or r8, 128 + or r12, 192 + or rdi, 256 + or rcx, 320 + or rbx, 384 + or rax, 448 + movd xmm4, r14d + pinsrw xmm4, word ptr [rdx + r9], 1 + pinsrw xmm4, word ptr [rdx + r8], 2 + pinsrw xmm4, word ptr [rdx + r12], 3 + pinsrw xmm4, word ptr [rdx + rdi], 4 + pinsrw xmm4, word ptr [rdx + rcx], 5 + pinsrw xmm4, word ptr [rdx + rbx], 6 + pinsrw xmm4, word ptr [rdx + rax], 7 + movzx r14d, word ptr [rdx + r15 + 10] movd xmm6, esi - movzx esi, byte ptr [rdx + r15 + 3] - movd xmm2, esi - movzx esi, byte ptr [rdx + r15 + 4] - movd xmm1, esi - movzx esi, byte ptr [rdx + r15 + 5] - movd xmm8, esi - movzx esi, byte ptr [rdx + r15 + 6] + pinsrw xmm6, word ptr [rdx + r9 + 2], 1 + pinsrw xmm6, word ptr [rdx + r8 + 2], 2 + pinsrw xmm6, word ptr [rdx + r12 + 2], 3 + movzx esi, word ptr [rdx + r15 + 12] + mov dword ptr [rsp + 8], esi # 4-byte Spill + pinsrw xmm6, word ptr [rdx + rdi + 2], 4 + movd xmm2, r11d + movzx r11d, word ptr [rdx + r15 + 14] + pinsrw xmm6, word ptr [rdx + rcx + 2], 5 + movd xmm5, r13d + movzx esi, word ptr [rdx + r15 + 16] + mov dword ptr [rsp + 32], esi # 4-byte Spill + pinsrw xmm6, word ptr [rdx + rbx + 2], 6 + movd xmm3, r10d + movzx esi, word ptr [rdx + r15 + 18] + mov dword ptr [rsp + 40], esi # 4-byte Spill + pinsrw xmm6, word ptr [rdx + rax + 2], 7 + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + movdqa xmm1, xmm6 + pand xmm1, xmm15 + psubb xmm1, xmm6 + movd xmm6, r14d + movzx r13d, word ptr [rdx + r15 + 20] + pcmpeqw xmm4, xmm0 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + pinsrw xmm2, word ptr [rdx + r9 + 4], 1 + pinsrw xmm2, word ptr [rdx + r8 + 4], 2 + pinsrw xmm2, word ptr [rdx + r12 + 4], 3 + pinsrw xmm2, word ptr [rdx + rdi + 4], 4 + pinsrw xmm2, word ptr [rdx + rcx + 4], 5 + pinsrw xmm2, word ptr [rdx + rbx + 4], 6 + pinsrw xmm2, word ptr [rdx + rax + 4], 7 + pinsrw xmm5, word ptr [rdx + r9 + 6], 1 + pinsrw xmm5, word ptr [rdx + r8 + 6], 2 + pinsrw xmm5, word ptr [rdx + r12 + 6], 3 + pinsrw xmm5, word ptr [rdx + rdi + 6], 4 + pinsrw xmm5, word ptr [rdx + rcx + 6], 5 + pinsrw xmm5, word ptr [rdx + rbx + 6], 6 + pinsrw xmm5, word ptr [rdx + rax + 6], 7 + pinsrw xmm3, word ptr [rdx + r9 + 8], 1 + pinsrw xmm3, word ptr [rdx + r8 + 8], 2 + pinsrw xmm3, word ptr [rdx + r12 + 8], 3 + pinsrw xmm3, word ptr [rdx + rdi + 8], 4 + pinsrw xmm3, word ptr [rdx + rcx + 8], 5 + pinsrw xmm3, word ptr [rdx + rbx + 8], 6 + pinsrw xmm3, word ptr [rdx + rax + 8], 7 + por xmm1, xmm4 + movd xmm7, dword ptr [rsp + 8] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r14d, word ptr [rdx + r15 + 22] + pcmpeqw xmm2, xmm0 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 2 + pand xmm2, xmm9 + por xmm2, xmm1 + movd xmm4, r11d + movzx esi, word ptr [rdx + r15 + 24] + pcmpeqw xmm5, xmm0 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 3 + pand xmm5, xmm10 + pcmpeqw xmm3, xmm0 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 4 + pand xmm3, xmm11 + por xmm3, xmm5 + movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r10d, word ptr [rdx + r15 + 26] + pinsrw xmm6, word ptr [rdx + r9 + 10], 1 + pinsrw xmm6, word ptr [rdx + r8 + 10], 2 + pinsrw xmm6, word ptr [rdx + r12 + 10], 3 + pinsrw xmm6, word ptr [rdx + rdi + 10], 4 + pinsrw xmm6, word ptr [rdx + rcx + 10], 5 + pinsrw xmm6, word ptr [rdx + rbx + 10], 6 + pinsrw xmm6, word ptr [rdx + rax + 10], 7 + pinsrw xmm7, word ptr [rdx + r9 + 12], 1 + pinsrw xmm7, word ptr [rdx + r8 + 12], 2 + pinsrw xmm7, word ptr [rdx + r12 + 12], 3 + pinsrw xmm7, word ptr [rdx + rdi + 12], 4 + pinsrw xmm7, word ptr [rdx + rcx + 12], 5 + pinsrw xmm7, word ptr [rdx + rbx + 12], 6 + pinsrw xmm7, word ptr [rdx + rax + 12], 7 + por xmm3, xmm2 + movd xmm8, dword ptr [rsp + 40] # 4-byte Folded Reload + # xmm8 = mem[0],zero,zero,zero + movzx r11d, word ptr [rdx + r15 + 28] + pcmpeqw xmm6, xmm0 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + pcmpeqw xmm7, xmm0 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 6 + pand xmm7, xmm13 + por xmm7, xmm6 + movd xmm5, r13d + movzx r13d, word ptr [rdx + r15 + 30] + pinsrw xmm4, word ptr [rdx + r9 + 14], 1 + pinsrw xmm4, word ptr [rdx + r8 + 14], 2 + pinsrw xmm4, word ptr [rdx + r12 + 14], 3 + pinsrw xmm4, word ptr [rdx + rdi + 14], 4 + pinsrw xmm4, word ptr [rdx + rcx + 14], 5 + pinsrw xmm4, word ptr [rdx + rbx + 14], 6 + pinsrw xmm4, word ptr [rdx + rax + 14], 7 + pinsrw xmm8, word ptr [rdx + r9 + 18], 1 + pinsrw xmm8, word ptr [rdx + r8 + 18], 2 + pinsrw xmm8, word ptr [rdx + r12 + 18], 3 + pinsrw xmm8, word ptr [rdx + rdi + 18], 4 + pinsrw xmm8, word ptr [rdx + rcx + 18], 5 + pinsrw xmm8, word ptr [rdx + rbx + 18], 6 + pinsrw xmm8, word ptr [rdx + rax + 18], 7 + pcmpeqw xmm4, xmm0 + packsswb xmm4, xmm4 + psllw xmm4, 7 + pand xmm4, xmm14 + por xmm4, xmm7 + movd xmm2, r14d + movzx r14d, word ptr [rdx + r15 + 32] + por xmm4, xmm3 + pcmpeqw xmm8, xmm0 + packsswb xmm8, xmm8 + movdqa xmm7, xmm8 + pand xmm7, xmm15 + psubb xmm7, xmm8 movd xmm3, esi - movzx esi, byte ptr [rdx + r15 + 7] - movd xmm0, esi - movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill - movzx esi, byte ptr [rdx + r15 + 8] - movd xmm0, esi - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - movzx esi, byte ptr [rdx + r15 + 9] - movd xmm10, esi - movzx esi, byte ptr [rdx + r15 + 10] - movd xmm0, esi - movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill - movzx esi, byte ptr [rdx + r15 + 11] - movd xmm11, esi - movzx esi, byte ptr [rdx + r15 + 12] - movd xmm13, esi - movzx esi, byte ptr [rdx + r15 + 13] - movd xmm12, esi - movzx esi, byte ptr [rdx + r15 + 14] - movd xmm0, esi - movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov r14, r15 - or r14, 32 - mov qword ptr [rsp + 16], r14 # 8-byte Spill - or rbx, 64 - mov qword ptr [rsp + 72], rbx # 8-byte Spill - or rax, 96 - mov qword ptr [rsp + 112], rax # 8-byte Spill - or rcx, 128 - or rdi, 160 - or r8, 192 - or r9, 224 - or r11, 256 - or r12, 288 - mov qword ptr [rsp + 64], r12 # 8-byte Spill - or r10, 320 - mov qword ptr [rsp + 88], r10 # 8-byte Spill - mov r10, r15 - or r10, 352 - mov qword ptr [rsp + 80], r10 # 8-byte Spill - mov r12, qword ptr [rsp + 56] # 8-byte Reload - or r12, 384 - mov rsi, r15 - or rsi, 416 - mov qword ptr [rsp + 48], rsi # 8-byte Spill - or r13, 448 - mov qword ptr [rsp + 24], r13 # 8-byte Spill - mov rsi, r15 - or rsi, 480 - mov qword ptr [rsp + 40], rsi # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r14], 1 - pinsrb xmm15, byte ptr [rdx + rbx], 2 - pinsrb xmm15, byte ptr [rdx + rax], 3 - mov qword ptr [rsp + 128], rcx # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + rcx], 4 - pinsrb xmm15, byte ptr [rdx + rdi], 5 - mov qword ptr [rsp + 96], r8 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r8], 6 - mov qword ptr [rsp + 208], r9 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r9], 7 - mov qword ptr [rsp + 120], r11 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r11], 8 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r14], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r15], 10 - pinsrb xmm15, byte ptr [rdx + r10], 11 - mov qword ptr [rsp + 56], r12 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r12], 12 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r10], 13 - pinsrb xmm15, byte ptr [rdx + r13], 14 - pinsrb xmm15, byte ptr [rdx + rsi], 15 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rbx + 1], 1 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rbx + 1], 2 - pinsrb xmm5, byte ptr [rdx + rax + 1], 3 - pinsrb xmm5, byte ptr [rdx + rcx + 1], 4 - pinsrb xmm5, byte ptr [rdx + rdi + 1], 5 - pinsrb xmm5, byte ptr [rdx + r8 + 1], 6 - pinsrb xmm5, byte ptr [rdx + r9 + 1], 7 - pinsrb xmm5, byte ptr [rdx + r11 + 1], 8 - pinsrb xmm5, byte ptr [rdx + r14 + 1], 9 - mov rax, r14 - pinsrb xmm5, byte ptr [rdx + r15 + 1], 10 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rcx + 1], 11 - pinsrb xmm5, byte ptr [rdx + r12 + 1], 12 - pinsrb xmm5, byte ptr [rdx + r10 + 1], 13 - pinsrb xmm5, byte ptr [rdx + r13 + 1], 14 - pinsrb xmm5, byte ptr [rdx + rsi + 1], 15 - movdqa xmm9, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm5, xmm9 - movdqa xmm7, xmm5 - movdqa xmm4, xmmword ptr [rip + .LCPI2_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm7, xmm4 - psubb xmm7, xmm5 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - movzx esi, byte ptr [rdx + r13 + 15] - movd xmm14, esi - pcmpeqb xmm15, xmm9 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rcx + 2], 1 - pinsrb xmm6, byte ptr [rdx + rbx + 2], 2 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r11 + 2], 3 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r8 + 2], 4 - pinsrb xmm6, byte ptr [rdx + rdi + 2], 5 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r12 + 2], 6 - mov r14, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r14 + 2], 7 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r15 + 2], 8 - pinsrb xmm6, byte ptr [rdx + rax + 2], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 2], 10 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r10 + 2], 11 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r9 + 2], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 2], 13 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 2], 14 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 2], 15 - pand xmm15, xmm4 - pcmpeqb xmm6, xmm9 - movdqa xmm0, xmmword ptr [rip + .LCPI2_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm6, xmm0 - por xmm6, xmm15 - movzx esi, byte ptr [rdx + r13 + 16] - movd xmm15, esi - pinsrb xmm2, byte ptr [rdx + rcx + 3], 1 - pinsrb xmm2, byte ptr [rdx + rbx + 3], 2 - mov rcx, r11 - pinsrb xmm2, byte ptr [rdx + r11 + 3], 3 - pinsrb xmm2, byte ptr [rdx + r8 + 3], 4 - mov qword ptr [rsp + 136], rdi # 8-byte Spill - pinsrb xmm2, byte ptr [rdx + rdi + 3], 5 - mov r11, r12 - pinsrb xmm2, byte ptr [rdx + r12 + 3], 6 - pinsrb xmm2, byte ptr [rdx + r14 + 3], 7 - mov rsi, r15 - pinsrb xmm2, byte ptr [rdx + r15 + 3], 8 - pinsrb xmm2, byte ptr [rdx + rax + 3], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r15 + 3], 10 - pinsrb xmm2, byte ptr [rdx + r10 + 3], 11 - pinsrb xmm2, byte ptr [rdx + r9 + 3], 12 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r12 + 3], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 3], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 3], 15 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r13 + 4], 1 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rbx + 4], 2 - pinsrb xmm1, byte ptr [rdx + rcx + 4], 3 - pinsrb xmm1, byte ptr [rdx + r8 + 4], 4 - pinsrb xmm1, byte ptr [rdx + rdi + 4], 5 - pinsrb xmm1, byte ptr [rdx + r11 + 4], 6 - pinsrb xmm1, byte ptr [rdx + r14 + 4], 7 - mov r8, r14 - pinsrb xmm1, byte ptr [rdx + rsi + 4], 8 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rsi + 4], 9 - pinsrb xmm1, byte ptr [rdx + r15 + 4], 10 - pinsrb xmm1, byte ptr [rdx + r10 + 4], 11 - mov r15, r10 - pinsrb xmm1, byte ptr [rdx + r9 + 4], 12 - pinsrb xmm1, byte ptr [rdx + r12 + 4], 13 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rbx + 4], 14 - pinsrb xmm1, byte ptr [rdx + rax + 4], 15 - mov r10, rax - por xmm6, xmm7 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - movzx esi, byte ptr [rdx + rdi + 17] - movd xmm0, esi - pcmpeqb xmm2, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI2_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm2, xmm5 - pcmpeqb xmm1, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI2_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm1, xmm5 - por xmm1, xmm2 - movzx esi, byte ptr [rdx + rdi + 18] - movd xmm5, esi - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r13 + 5], 1 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r11 + 5], 2 - pinsrb xmm8, byte ptr [rdx + rcx + 5], 3 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r14 + 5], 4 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r9 + 5], 5 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rax + 5], 6 - mov rcx, r8 - pinsrb xmm8, byte ptr [rdx + r8 + 5], 7 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r8 + 5], 8 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rsi + 5], 9 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rsi + 5], 10 - pinsrb xmm8, byte ptr [rdx + r15 + 5], 11 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r12 + 5], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rsi + 5], 13 - pinsrb xmm8, byte ptr [rdx + rbx + 5], 14 - pinsrb xmm8, byte ptr [rdx + r10 + 5], 15 - pcmpeqb xmm8, xmm9 - movdqa xmm2, xmmword ptr [rip + .LCPI2_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm8, xmm2 - por xmm8, xmm1 - movzx esi, byte ptr [rdx + rdi + 19] - movd xmm7, esi - por xmm8, xmm6 - movzx esi, byte ptr [rdx + rdi + 20] - movd xmm6, esi - pinsrb xmm3, byte ptr [rdx + r13 + 6], 1 - mov rsi, r11 - pinsrb xmm3, byte ptr [rdx + r11 + 6], 2 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r10 + 6], 3 - mov r11, r14 - pinsrb xmm3, byte ptr [rdx + r14 + 6], 4 - pinsrb xmm3, byte ptr [rdx + r9 + 6], 5 - pinsrb xmm3, byte ptr [rdx + rax + 6], 6 - pinsrb xmm3, byte ptr [rdx + rcx + 6], 7 - mov r14, rcx - pinsrb xmm3, byte ptr [rdx + r8 + 6], 8 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rdi + 6], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r15 + 6], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rax + 6], 11 - mov rbx, r12 - pinsrb xmm3, byte ptr [rdx + r12 + 6], 12 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r12 + 6], 13 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rcx + 6], 14 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rcx + 6], 15 - movdqa xmm2, xmmword ptr [rsp + 192] # 16-byte Reload - pinsrb xmm2, byte ptr [rdx + r13 + 7], 1 - pinsrb xmm2, byte ptr [rdx + rsi + 7], 2 - mov r13, rsi - pinsrb xmm2, byte ptr [rdx + r10 + 7], 3 - mov r10, r11 - pinsrb xmm2, byte ptr [rdx + r11 + 7], 4 - pinsrb xmm2, byte ptr [rdx + r9 + 7], 5 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 7], 6 - pinsrb xmm2, byte ptr [rdx + r14 + 7], 7 - pinsrb xmm2, byte ptr [rdx + r8 + 7], 8 - mov rcx, r8 - pinsrb xmm2, byte ptr [rdx + rdi + 7], 9 - pinsrb xmm2, byte ptr [rdx + r15 + 7], 10 - pinsrb xmm2, byte ptr [rdx + rax + 7], 11 - pinsrb xmm2, byte ptr [rdx + rbx + 7], 12 - pinsrb xmm2, byte ptr [rdx + r12 + 7], 13 - mov r11, r12 - mov r12, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r12 + 7], 14 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rbx + 7], 15 - pcmpeqb xmm3, xmm9 - movdqa xmm1, xmmword ptr [rip + .LCPI2_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm1 - pcmpeqb xmm2, xmm9 - psllw xmm2, 7 - movdqa xmm1, xmmword ptr [rip + .LCPI2_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm2, xmm1 - por xmm2, xmm3 - movdqa xmm1, xmm2 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 21] - movd xmm2, esi - mov r9, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r9 + 9], 1 - pinsrb xmm10, byte ptr [rdx + r13 + 9], 2 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r8 + 9], 3 - pinsrb xmm10, byte ptr [rdx + r10 + 9], 4 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rdi + 9], 5 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r13 + 9], 6 - pinsrb xmm10, byte ptr [rdx + r14 + 9], 7 - pinsrb xmm10, byte ptr [rdx + rcx + 9], 8 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 9], 9 - pinsrb xmm10, byte ptr [rdx + r15 + 9], 10 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 9], 11 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 9], 12 - pinsrb xmm10, byte ptr [rdx + r11 + 9], 13 - pinsrb xmm10, byte ptr [rdx + r12 + 9], 14 - pinsrb xmm10, byte ptr [rdx + rbx + 9], 15 - por xmm1, xmm8 - movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill - pcmpeqb xmm10, xmm9 - movdqa xmm1, xmm10 - movdqa xmm8, xmm4 - pand xmm1, xmm4 - psubb xmm1, xmm10 - movzx esi, byte ptr [rdx + rax + 22] - movd xmm3, esi - movdqa xmm4, xmmword ptr [rsp + 240] # 16-byte Reload - pinsrb xmm4, byte ptr [rdx + r9 + 8], 1 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r12 + 8], 2 - pinsrb xmm4, byte ptr [rdx + r8 + 8], 3 - mov r8, r10 - pinsrb xmm4, byte ptr [rdx + r10 + 8], 4 - pinsrb xmm4, byte ptr [rdx + rdi + 8], 5 - pinsrb xmm4, byte ptr [rdx + r13 + 8], 6 - pinsrb xmm4, byte ptr [rdx + r14 + 8], 7 - pinsrb xmm4, byte ptr [rdx + rcx + 8], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rbx + 8], 9 - pinsrb xmm4, byte ptr [rdx + r15 + 8], 10 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 8], 11 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rsi + 8], 12 - pinsrb xmm4, byte ptr [rdx + r11 + 8], 13 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r10 + 8], 14 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rcx + 8], 15 - pcmpeqb xmm4, xmm9 - pand xmm4, xmm8 - movdqa xmm10, xmmword ptr [rsp + 160] # 16-byte Reload - pinsrb xmm10, byte ptr [rdx + r9 + 10], 1 - pinsrb xmm10, byte ptr [rdx + r12 + 10], 2 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r9 + 10], 3 - pinsrb xmm10, byte ptr [rdx + r8 + 10], 4 - pinsrb xmm10, byte ptr [rdx + rdi + 10], 5 - pinsrb xmm10, byte ptr [rdx + r13 + 10], 6 - mov r8, r13 - pinsrb xmm10, byte ptr [rdx + r14 + 10], 7 - mov r13, r14 - mov r14, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r14 + 10], 8 - pinsrb xmm10, byte ptr [rdx + rbx + 10], 9 - pinsrb xmm10, byte ptr [rdx + r15 + 10], 10 - mov rbx, r15 - pinsrb xmm10, byte ptr [rdx + rax + 10], 11 - pinsrb xmm10, byte ptr [rdx + rsi + 10], 12 - pinsrb xmm10, byte ptr [rdx + r11 + 10], 13 - pinsrb xmm10, byte ptr [rdx + r10 + 10], 14 - pinsrb xmm10, byte ptr [rdx + rcx + 10], 15 - pcmpeqb xmm10, xmm9 - pand xmm10, xmmword ptr [rip + .LCPI2_11] - por xmm10, xmm4 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 23] - movd xmm8, esi - por xmm10, xmm1 - movdqa xmmword ptr [rsp + 160], xmm10 # 16-byte Spill - movzx esi, byte ptr [rdx + rcx + 24] - movd xmm10, esi - mov r10, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r10 + 11], 1 - pinsrb xmm11, byte ptr [rdx + r12 + 11], 2 - mov rcx, r9 - pinsrb xmm11, byte ptr [rdx + r9 + 11], 3 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r11 + 11], 4 - pinsrb xmm11, byte ptr [rdx + rdi + 11], 5 - pinsrb xmm11, byte ptr [rdx + r8 + 11], 6 - mov r15, r8 - pinsrb xmm11, byte ptr [rdx + r13 + 11], 7 - pinsrb xmm11, byte ptr [rdx + r14 + 11], 8 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r8 + 11], 9 - pinsrb xmm11, byte ptr [rdx + rbx + 11], 10 - mov rbx, rax - pinsrb xmm11, byte ptr [rdx + rax + 11], 11 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r13 + 11], 12 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r9 + 11], 13 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rsi + 11], 14 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rax + 11], 15 - pinsrb xmm13, byte ptr [rdx + r10 + 12], 1 - pinsrb xmm13, byte ptr [rdx + r12 + 12], 2 - pinsrb xmm13, byte ptr [rdx + rcx + 12], 3 - pinsrb xmm13, byte ptr [rdx + r11 + 12], 4 - pinsrb xmm13, byte ptr [rdx + rdi + 12], 5 - pinsrb xmm13, byte ptr [rdx + r15 + 12], 6 - mov r11, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + r11 + 12], 7 - pinsrb xmm13, byte ptr [rdx + r14 + 12], 8 - pinsrb xmm13, byte ptr [rdx + r8 + 12], 9 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + r15 + 12], 10 - pinsrb xmm13, byte ptr [rdx + rbx + 12], 11 - pinsrb xmm13, byte ptr [rdx + r13 + 12], 12 - pinsrb xmm13, byte ptr [rdx + r9 + 12], 13 - pinsrb xmm13, byte ptr [rdx + rsi + 12], 14 - pinsrb xmm13, byte ptr [rdx + rax + 12], 15 - pinsrb xmm12, byte ptr [rdx + r10 + 13], 1 - pinsrb xmm12, byte ptr [rdx + r12 + 13], 2 - pinsrb xmm12, byte ptr [rdx + rcx + 13], 3 - mov r10, rcx - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rcx + 13], 4 - pinsrb xmm12, byte ptr [rdx + rdi + 13], 5 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rdi + 13], 6 - pinsrb xmm12, byte ptr [rdx + r11 + 13], 7 - pinsrb xmm12, byte ptr [rdx + r14 + 13], 8 - mov r14, r8 - pinsrb xmm12, byte ptr [rdx + r8 + 13], 9 - pinsrb xmm12, byte ptr [rdx + r15 + 13], 10 - pinsrb xmm12, byte ptr [rdx + rbx + 13], 11 - pinsrb xmm12, byte ptr [rdx + r13 + 13], 12 - pinsrb xmm12, byte ptr [rdx + r9 + 13], 13 - mov r13, r9 - pinsrb xmm12, byte ptr [rdx + rsi + 13], 14 - pinsrb xmm12, byte ptr [rdx + rax + 13], 15 - pcmpeqb xmm11, xmm9 - pand xmm11, xmmword ptr [rip + .LCPI2_12] - pcmpeqb xmm13, xmm9 - pand xmm13, xmmword ptr [rip + .LCPI2_13] - por xmm13, xmm11 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - movzx esi, byte ptr [rdx + rbx + 25] - movd xmm1, esi - pcmpeqb xmm12, xmm9 - pand xmm12, xmmword ptr [rip + .LCPI2_14] - por xmm12, xmm13 - movzx esi, byte ptr [rdx + rbx + 26] - movd xmm11, esi - movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 14], 1 - pinsrb xmm4, byte ptr [rdx + r12 + 14], 2 - pinsrb xmm4, byte ptr [rdx + r10 + 14], 3 - mov rax, rcx - pinsrb xmm4, byte ptr [rdx + rcx + 14], 4 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rcx + 14], 5 - pinsrb xmm4, byte ptr [rdx + rdi + 14], 6 - mov r8, r11 - pinsrb xmm4, byte ptr [rdx + r11 + 14], 7 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r9 + 14], 8 - mov rbx, r14 - pinsrb xmm4, byte ptr [rdx + r14 + 14], 9 - mov r11, r15 - pinsrb xmm4, byte ptr [rdx + r15 + 14], 10 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r14 + 14], 11 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r15 + 14], 12 - pinsrb xmm4, byte ptr [rdx + r13 + 14], 13 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r13 + 14], 14 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rsi + 14], 15 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rsi + 15], 1 - pinsrb xmm14, byte ptr [rdx + r12 + 15], 2 - pinsrb xmm14, byte ptr [rdx + r10 + 15], 3 - pinsrb xmm14, byte ptr [rdx + rax + 15], 4 - pinsrb xmm14, byte ptr [rdx + rcx + 15], 5 - pinsrb xmm14, byte ptr [rdx + rdi + 15], 6 - pinsrb xmm14, byte ptr [rdx + r8 + 15], 7 - pinsrb xmm14, byte ptr [rdx + r9 + 15], 8 - pinsrb xmm14, byte ptr [rdx + rbx + 15], 9 - pinsrb xmm14, byte ptr [rdx + r11 + 15], 10 - pinsrb xmm14, byte ptr [rdx + r14 + 15], 11 - pinsrb xmm14, byte ptr [rdx + r15 + 15], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rsi + 15], 13 - pinsrb xmm14, byte ptr [rdx + r13 + 15], 14 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rsi + 15], 15 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi + 16], 1 - pinsrb xmm15, byte ptr [rdx + r12 + 16], 2 - pinsrb xmm15, byte ptr [rdx + r10 + 16], 3 - pinsrb xmm15, byte ptr [rdx + rax + 16], 4 - pinsrb xmm15, byte ptr [rdx + rcx + 16], 5 - pinsrb xmm15, byte ptr [rdx + rdi + 16], 6 - pinsrb xmm15, byte ptr [rdx + r8 + 16], 7 - pinsrb xmm15, byte ptr [rdx + r9 + 16], 8 - pinsrb xmm15, byte ptr [rdx + rbx + 16], 9 - pinsrb xmm15, byte ptr [rdx + r11 + 16], 10 - pinsrb xmm15, byte ptr [rdx + r14 + 16], 11 - pinsrb xmm15, byte ptr [rdx + r15 + 16], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi + 16], 13 - pinsrb xmm15, byte ptr [rdx + r13 + 16], 14 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 17], 1 - pinsrb xmm0, byte ptr [rdx + r12 + 17], 2 - pinsrb xmm0, byte ptr [rdx + r10 + 17], 3 - pinsrb xmm0, byte ptr [rdx + rax + 17], 4 - mov r13, rax - pinsrb xmm0, byte ptr [rdx + rcx + 17], 5 - pinsrb xmm0, byte ptr [rdx + rdi + 17], 6 - pinsrb xmm0, byte ptr [rdx + r8 + 17], 7 - mov rax, r8 - pinsrb xmm0, byte ptr [rdx + r9 + 17], 8 - pinsrb xmm0, byte ptr [rdx + rbx + 17], 9 - pinsrb xmm0, byte ptr [rdx + r11 + 17], 10 - pinsrb xmm0, byte ptr [rdx + r14 + 17], 11 - pinsrb xmm0, byte ptr [rdx + r15 + 17], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 17], 13 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 17], 14 - por xmm12, xmmword ptr [rsp + 160] # 16-byte Folded Reload - mov r12, qword ptr [rsp + 32] # 8-byte Reload - movzx esi, byte ptr [rdx + r12 + 27] - movd xmm9, esi - movdqa xmm13, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm4, xmm13 - pand xmm4, xmmword ptr [rip + .LCPI2_15] - pcmpeqb xmm14, xmm13 - psllw xmm14, 7 - pand xmm14, xmmword ptr [rip + .LCPI2_6] - por xmm14, xmm4 - movzx esi, byte ptr [rdx + r12 + 28] - movd xmm4, esi - mov r8, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r8 + 17], 15 - por xmm14, xmm12 - pcmpeqb xmm0, xmm13 - movdqa xmm13, xmm0 - movdqa xmm12, xmmword ptr [rip + .LCPI2_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm13, xmm12 - psubb xmm13, xmm0 - movdqa xmmword ptr [rsp + 160], xmm13 # 16-byte Spill - movzx esi, byte ptr [rdx + r12 + 29] - movd xmm13, esi - pinsrb xmm15, byte ptr [rdx + r8 + 16], 15 - movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm15, xmm0 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r12 + 18], 1 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 18], 2 - pinsrb xmm5, byte ptr [rdx + r10 + 18], 3 - pinsrb xmm5, byte ptr [rdx + r13 + 18], 4 - pinsrb xmm5, byte ptr [rdx + rcx + 18], 5 - pinsrb xmm5, byte ptr [rdx + rdi + 18], 6 - pinsrb xmm5, byte ptr [rdx + rax + 18], 7 - pinsrb xmm5, byte ptr [rdx + r9 + 18], 8 - pinsrb xmm5, byte ptr [rdx + rbx + 18], 9 - pinsrb xmm5, byte ptr [rdx + r11 + 18], 10 - pinsrb xmm5, byte ptr [rdx + r14 + 18], 11 - pinsrb xmm5, byte ptr [rdx + r15 + 18], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 18], 13 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 18], 14 - pand xmm15, xmm12 - pinsrb xmm5, byte ptr [rdx + r8 + 18], 15 - pcmpeqb xmm5, xmm0 - pand xmm5, xmmword ptr [rip + .LCPI2_11] - por xmm5, xmm15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 30] - movd xmm12, esi - pinsrb xmm7, byte ptr [rdx + r12 + 19], 1 - pinsrb xmm6, byte ptr [rdx + r12 + 20], 1 - pinsrb xmm2, byte ptr [rdx + r12 + 21], 1 - pinsrb xmm3, byte ptr [rdx + r12 + 22], 1 - pinsrb xmm8, byte ptr [rdx + r12 + 23], 1 - pinsrb xmm10, byte ptr [rdx + r12 + 24], 1 - pinsrb xmm1, byte ptr [rdx + r12 + 25], 1 - pinsrb xmm11, byte ptr [rdx + r12 + 26], 1 - pinsrb xmm9, byte ptr [rdx + r12 + 27], 1 - pinsrb xmm4, byte ptr [rdx + r12 + 28], 1 - pinsrb xmm13, byte ptr [rdx + r12 + 29], 1 - pinsrb xmm12, byte ptr [rdx + r12 + 30], 1 - movzx esi, byte ptr [rdx + rax + 31] - movd xmm0, esi - pinsrb xmm0, byte ptr [rdx + r12 + 31], 1 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 19], 2 - pinsrb xmm6, byte ptr [rdx + rsi + 20], 2 - pinsrb xmm2, byte ptr [rdx + rsi + 21], 2 - pinsrb xmm3, byte ptr [rdx + rsi + 22], 2 - pinsrb xmm8, byte ptr [rdx + rsi + 23], 2 - pinsrb xmm10, byte ptr [rdx + rsi + 24], 2 - pinsrb xmm1, byte ptr [rdx + rsi + 25], 2 - pinsrb xmm11, byte ptr [rdx + rsi + 26], 2 - pinsrb xmm9, byte ptr [rdx + rsi + 27], 2 - pinsrb xmm4, byte ptr [rdx + rsi + 28], 2 - pinsrb xmm13, byte ptr [rdx + rsi + 29], 2 - pinsrb xmm12, byte ptr [rdx + rsi + 30], 2 - pinsrb xmm0, byte ptr [rdx + rsi + 31], 2 - pinsrb xmm7, byte ptr [rdx + r10 + 19], 3 - pinsrb xmm7, byte ptr [rdx + r13 + 19], 4 - pinsrb xmm7, byte ptr [rdx + rcx + 19], 5 - pinsrb xmm7, byte ptr [rdx + rdi + 19], 6 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 19], 7 - pinsrb xmm7, byte ptr [rdx + r9 + 19], 8 - pinsrb xmm7, byte ptr [rdx + rbx + 19], 9 - pinsrb xmm7, byte ptr [rdx + r11 + 19], 10 - pinsrb xmm7, byte ptr [rdx + r14 + 19], 11 - pinsrb xmm7, byte ptr [rdx + r15 + 19], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 19], 13 - mov r12, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r12 + 19], 14 - pinsrb xmm7, byte ptr [rdx + r8 + 19], 15 - pinsrb xmm6, byte ptr [rdx + r10 + 20], 3 - pinsrb xmm6, byte ptr [rdx + r13 + 20], 4 - pinsrb xmm6, byte ptr [rdx + rcx + 20], 5 - pinsrb xmm6, byte ptr [rdx + rdi + 20], 6 - pinsrb xmm6, byte ptr [rdx + rax + 20], 7 - pinsrb xmm6, byte ptr [rdx + r9 + 20], 8 - pinsrb xmm6, byte ptr [rdx + rbx + 20], 9 - pinsrb xmm6, byte ptr [rdx + r11 + 20], 10 - pinsrb xmm6, byte ptr [rdx + r14 + 20], 11 - pinsrb xmm6, byte ptr [rdx + r15 + 20], 12 - pinsrb xmm6, byte ptr [rdx + rsi + 20], 13 - pinsrb xmm6, byte ptr [rdx + r12 + 20], 14 - por xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload - pinsrb xmm6, byte ptr [rdx + r8 + 20], 15 - movdqa xmm15, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm7, xmm15 - pand xmm7, xmmword ptr [rip + .LCPI2_12] - pcmpeqb xmm6, xmm15 - pand xmm6, xmmword ptr [rip + .LCPI2_13] - por xmm6, xmm7 - pinsrb xmm2, byte ptr [rdx + r10 + 21], 3 - pinsrb xmm2, byte ptr [rdx + r13 + 21], 4 - pinsrb xmm2, byte ptr [rdx + rcx + 21], 5 - pinsrb xmm2, byte ptr [rdx + rdi + 21], 6 - pinsrb xmm2, byte ptr [rdx + rax + 21], 7 - pinsrb xmm2, byte ptr [rdx + r9 + 21], 8 - pinsrb xmm2, byte ptr [rdx + rbx + 21], 9 - pinsrb xmm2, byte ptr [rdx + r11 + 21], 10 - pinsrb xmm2, byte ptr [rdx + r14 + 21], 11 - pinsrb xmm2, byte ptr [rdx + r15 + 21], 12 - pinsrb xmm2, byte ptr [rdx + rsi + 21], 13 - pinsrb xmm2, byte ptr [rdx + r12 + 21], 14 - pinsrb xmm2, byte ptr [rdx + r8 + 21], 15 - pcmpeqb xmm2, xmm15 - movdqa xmm7, xmmword ptr [rip + .LCPI2_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm2, xmm7 - por xmm2, xmm6 - por xmm2, xmm5 - pinsrb xmm3, byte ptr [rdx + r10 + 22], 3 - pinsrb xmm3, byte ptr [rdx + r13 + 22], 4 - pinsrb xmm3, byte ptr [rdx + rcx + 22], 5 - pinsrb xmm3, byte ptr [rdx + rdi + 22], 6 - pinsrb xmm3, byte ptr [rdx + rax + 22], 7 - pinsrb xmm3, byte ptr [rdx + r9 + 22], 8 - pinsrb xmm3, byte ptr [rdx + rbx + 22], 9 - pinsrb xmm3, byte ptr [rdx + r11 + 22], 10 - pinsrb xmm3, byte ptr [rdx + r14 + 22], 11 - pinsrb xmm3, byte ptr [rdx + r15 + 22], 12 - pinsrb xmm3, byte ptr [rdx + rsi + 22], 13 - pinsrb xmm3, byte ptr [rdx + r12 + 22], 14 - pinsrb xmm3, byte ptr [rdx + r8 + 22], 15 - pinsrb xmm8, byte ptr [rdx + r10 + 23], 3 - pinsrb xmm8, byte ptr [rdx + r13 + 23], 4 - pinsrb xmm8, byte ptr [rdx + rcx + 23], 5 - pinsrb xmm8, byte ptr [rdx + rdi + 23], 6 - pinsrb xmm8, byte ptr [rdx + rax + 23], 7 - pinsrb xmm8, byte ptr [rdx + r9 + 23], 8 - pinsrb xmm8, byte ptr [rdx + rbx + 23], 9 - pinsrb xmm8, byte ptr [rdx + r11 + 23], 10 - pinsrb xmm8, byte ptr [rdx + r14 + 23], 11 - pinsrb xmm8, byte ptr [rdx + r15 + 23], 12 - pinsrb xmm8, byte ptr [rdx + rsi + 23], 13 - pinsrb xmm8, byte ptr [rdx + r12 + 23], 14 - pinsrb xmm8, byte ptr [rdx + r8 + 23], 15 - pcmpeqb xmm3, xmm15 - movdqa xmm5, xmmword ptr [rip + .LCPI2_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm5 - pcmpeqb xmm8, xmm15 - psllw xmm8, 7 - movdqa xmm6, xmmword ptr [rip + .LCPI2_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm8, xmm6 - por xmm8, xmm3 - pinsrb xmm1, byte ptr [rdx + r10 + 25], 3 - pinsrb xmm1, byte ptr [rdx + r13 + 25], 4 - pinsrb xmm1, byte ptr [rdx + rcx + 25], 5 - pinsrb xmm1, byte ptr [rdx + rdi + 25], 6 - pinsrb xmm1, byte ptr [rdx + rax + 25], 7 - pinsrb xmm1, byte ptr [rdx + r9 + 25], 8 - pinsrb xmm1, byte ptr [rdx + rbx + 25], 9 - pinsrb xmm1, byte ptr [rdx + r11 + 25], 10 - pinsrb xmm1, byte ptr [rdx + r14 + 25], 11 - pinsrb xmm1, byte ptr [rdx + r15 + 25], 12 - pinsrb xmm1, byte ptr [rdx + rsi + 25], 13 - pinsrb xmm1, byte ptr [rdx + r12 + 25], 14 - pinsrb xmm1, byte ptr [rdx + r8 + 25], 15 - por xmm8, xmm2 - pcmpeqb xmm1, xmm15 - movdqa xmm2, xmm1 - movdqa xmm3, xmmword ptr [rip + .LCPI2_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm2, xmm3 - psubb xmm2, xmm1 - pinsrb xmm10, byte ptr [rdx + r10 + 24], 3 - pinsrb xmm10, byte ptr [rdx + r13 + 24], 4 - pinsrb xmm10, byte ptr [rdx + rcx + 24], 5 - pinsrb xmm10, byte ptr [rdx + rdi + 24], 6 - pinsrb xmm10, byte ptr [rdx + rax + 24], 7 - pinsrb xmm10, byte ptr [rdx + r9 + 24], 8 - pinsrb xmm10, byte ptr [rdx + rbx + 24], 9 - pinsrb xmm10, byte ptr [rdx + r11 + 24], 10 - pinsrb xmm10, byte ptr [rdx + r14 + 24], 11 - pinsrb xmm10, byte ptr [rdx + r15 + 24], 12 - pinsrb xmm10, byte ptr [rdx + rsi + 24], 13 - pinsrb xmm10, byte ptr [rdx + r12 + 24], 14 - pinsrb xmm10, byte ptr [rdx + r8 + 24], 15 - pcmpeqb xmm10, xmm15 - pand xmm10, xmm3 - pinsrb xmm11, byte ptr [rdx + r10 + 26], 3 - pinsrb xmm11, byte ptr [rdx + r13 + 26], 4 - pinsrb xmm11, byte ptr [rdx + rcx + 26], 5 - pinsrb xmm11, byte ptr [rdx + rdi + 26], 6 - pinsrb xmm11, byte ptr [rdx + rax + 26], 7 - pinsrb xmm11, byte ptr [rdx + r9 + 26], 8 - pinsrb xmm11, byte ptr [rdx + rbx + 26], 9 - pinsrb xmm11, byte ptr [rdx + r11 + 26], 10 - pinsrb xmm11, byte ptr [rdx + r14 + 26], 11 - pinsrb xmm11, byte ptr [rdx + r15 + 26], 12 - pinsrb xmm11, byte ptr [rdx + rsi + 26], 13 - pinsrb xmm11, byte ptr [rdx + r12 + 26], 14 - pinsrb xmm11, byte ptr [rdx + r8 + 26], 15 - pcmpeqb xmm11, xmm15 - pand xmm11, xmmword ptr [rip + .LCPI2_11] - por xmm11, xmm10 - por xmm11, xmm2 - pinsrb xmm9, byte ptr [rdx + r10 + 27], 3 - pinsrb xmm9, byte ptr [rdx + r13 + 27], 4 - pinsrb xmm9, byte ptr [rdx + rcx + 27], 5 - pinsrb xmm9, byte ptr [rdx + rdi + 27], 6 - pinsrb xmm9, byte ptr [rdx + rax + 27], 7 - pinsrb xmm9, byte ptr [rdx + r9 + 27], 8 - pinsrb xmm9, byte ptr [rdx + rbx + 27], 9 - pinsrb xmm9, byte ptr [rdx + r11 + 27], 10 - pinsrb xmm9, byte ptr [rdx + r14 + 27], 11 - pinsrb xmm9, byte ptr [rdx + r15 + 27], 12 - pinsrb xmm9, byte ptr [rdx + rsi + 27], 13 - pinsrb xmm9, byte ptr [rdx + r12 + 27], 14 - pinsrb xmm9, byte ptr [rdx + r8 + 27], 15 - pinsrb xmm4, byte ptr [rdx + r10 + 28], 3 - pinsrb xmm4, byte ptr [rdx + r13 + 28], 4 - pinsrb xmm4, byte ptr [rdx + rcx + 28], 5 - pinsrb xmm4, byte ptr [rdx + rdi + 28], 6 - pinsrb xmm4, byte ptr [rdx + rax + 28], 7 - pinsrb xmm4, byte ptr [rdx + r9 + 28], 8 - pinsrb xmm4, byte ptr [rdx + rbx + 28], 9 - pinsrb xmm4, byte ptr [rdx + r11 + 28], 10 - pinsrb xmm4, byte ptr [rdx + r14 + 28], 11 - pinsrb xmm4, byte ptr [rdx + r15 + 28], 12 - pinsrb xmm4, byte ptr [rdx + rsi + 28], 13 - pinsrb xmm4, byte ptr [rdx + r12 + 28], 14 - pinsrb xmm4, byte ptr [rdx + r8 + 28], 15 - pinsrb xmm13, byte ptr [rdx + r10 + 29], 3 - pinsrb xmm13, byte ptr [rdx + r13 + 29], 4 - pinsrb xmm13, byte ptr [rdx + rcx + 29], 5 - pinsrb xmm13, byte ptr [rdx + rdi + 29], 6 - pinsrb xmm13, byte ptr [rdx + rax + 29], 7 - pinsrb xmm13, byte ptr [rdx + r9 + 29], 8 - pinsrb xmm13, byte ptr [rdx + rbx + 29], 9 - pinsrb xmm13, byte ptr [rdx + r11 + 29], 10 - pinsrb xmm13, byte ptr [rdx + r14 + 29], 11 - pinsrb xmm13, byte ptr [rdx + r15 + 29], 12 - pinsrb xmm13, byte ptr [rdx + rsi + 29], 13 - pinsrb xmm13, byte ptr [rdx + r12 + 29], 14 - movdqa xmm1, xmm15 - pcmpeqb xmm9, xmm15 - pand xmm9, xmmword ptr [rip + .LCPI2_12] - pcmpeqb xmm4, xmm15 - pand xmm4, xmmword ptr [rip + .LCPI2_13] - por xmm4, xmm9 - pinsrb xmm13, byte ptr [rdx + r8 + 29], 15 - pcmpeqb xmm13, xmm15 - pand xmm13, xmm7 - por xmm13, xmm4 - pinsrb xmm12, byte ptr [rdx + r10 + 30], 3 - pinsrb xmm0, byte ptr [rdx + r10 + 31], 3 - pinsrb xmm12, byte ptr [rdx + r13 + 30], 4 - pinsrb xmm0, byte ptr [rdx + r13 + 31], 4 - pinsrb xmm12, byte ptr [rdx + rcx + 30], 5 - pinsrb xmm0, byte ptr [rdx + rcx + 31], 5 - pinsrb xmm12, byte ptr [rdx + rdi + 30], 6 - pinsrb xmm0, byte ptr [rdx + rdi + 31], 6 - pinsrb xmm12, byte ptr [rdx + rax + 30], 7 - pinsrb xmm0, byte ptr [rdx + rax + 31], 7 - pinsrb xmm12, byte ptr [rdx + r9 + 30], 8 - pinsrb xmm0, byte ptr [rdx + r9 + 31], 8 - pinsrb xmm12, byte ptr [rdx + rbx + 30], 9 - pinsrb xmm0, byte ptr [rdx + rbx + 31], 9 - pinsrb xmm12, byte ptr [rdx + r11 + 30], 10 - pinsrb xmm0, byte ptr [rdx + r11 + 31], 10 - pinsrb xmm12, byte ptr [rdx + r14 + 30], 11 - pinsrb xmm0, byte ptr [rdx + r14 + 31], 11 - pinsrb xmm12, byte ptr [rdx + r15 + 30], 12 - pinsrb xmm0, byte ptr [rdx + r15 + 31], 12 - pinsrb xmm12, byte ptr [rdx + rsi + 30], 13 - pinsrb xmm0, byte ptr [rdx + rsi + 31], 13 - pinsrb xmm12, byte ptr [rdx + r12 + 30], 14 - pinsrb xmm0, byte ptr [rdx + r12 + 31], 14 - pinsrb xmm12, byte ptr [rdx + r8 + 30], 15 - pinsrb xmm0, byte ptr [rdx + r8 + 31], 15 - por xmm13, xmm11 - pcmpeqb xmm12, xmm15 - pand xmm12, xmm5 - pcmpeqb xmm0, xmm15 - psllw xmm0, 7 - pand xmm0, xmm6 - por xmm0, xmm12 - por xmm0, xmm13 - movdqa xmm1, xmm8 - punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload - movdqa xmm2, xmm4 - punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] - movdqa xmm3, xmm2 - punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] - punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] - punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] - punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - mov rax, qword ptr [rsp] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx + 48], xmm4 - movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 - movdqu xmmword ptr [rax + 4*rcx], xmm3 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 224] # 8-byte Folded Reload - jne .LBB2_186 -# %bb.187: - mov r15, qword ptr [rsp + 232] # 8-byte Reload - cmp r15, qword ptr [rsp + 224] # 8-byte Folded Reload - mov r14b, byte ptr [rsp + 8] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - jne .LBB2_69 - jmp .LBB2_135 -.LBB2_188: - and r15, -8 - mov rax, r15 - shl rax, 6 - add rax, rdx - mov qword ptr [rsp + 64], rax # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 32], r15 # 8-byte Spill - lea rax, [rax + 4*r15] - mov qword ptr [rsp + 16], rax # 8-byte Spill - movd xmm0, r14d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] - xor r15d, r15d - movdqa xmm15, xmmword ptr [rip + .LCPI2_8] # xmm15 = <1,1,1,1,1,1,1,1,u,u,u,u,u,u,u,u> - movdqa xmm9, xmmword ptr [rip + .LCPI2_1] # xmm9 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - movdqa xmm10, xmmword ptr [rip + .LCPI2_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - movdqa xmm11, xmmword ptr [rip + .LCPI2_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - movdqa xmm12, xmmword ptr [rip + .LCPI2_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - movdqa xmm13, xmmword ptr [rip + .LCPI2_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] - movdqa xmm14, xmmword ptr [rip + .LCPI2_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - .p2align 4, 0x90 -.LBB2_189: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r15 # 8-byte Spill - shl r15, 6 - mov r9, r15 - mov r12, r15 - mov r13, r15 - mov rcx, r15 - mov rdi, r15 - mov rbx, r15 - movzx r14d, word ptr [rdx + r15] - movzx eax, word ptr [rdx + r15 + 2] - movzx r10d, word ptr [rdx + r15 + 4] - movzx esi, word ptr [rdx + r15 + 6] - movzx r11d, word ptr [rdx + r15 + 8] - mov r8, r15 - or r8, 64 - or r9, 128 - or r12, 192 - or r13, 256 - or rcx, 320 - or rdi, 384 - or rbx, 448 - movd xmm4, r14d - pinsrw xmm4, word ptr [rdx + r8], 1 - pinsrw xmm4, word ptr [rdx + r9], 2 - pinsrw xmm4, word ptr [rdx + r12], 3 - pinsrw xmm4, word ptr [rdx + r13], 4 - pinsrw xmm4, word ptr [rdx + rcx], 5 - pinsrw xmm4, word ptr [rdx + rdi], 6 - pinsrw xmm4, word ptr [rdx + rbx], 7 - movzx r14d, word ptr [rdx + r15 + 10] - movd xmm6, eax - pinsrw xmm6, word ptr [rdx + r8 + 2], 1 - pinsrw xmm6, word ptr [rdx + r9 + 2], 2 - pinsrw xmm6, word ptr [rdx + r12 + 2], 3 - movzx eax, word ptr [rdx + r15 + 12] - mov dword ptr [rsp + 40], eax # 4-byte Spill - pinsrw xmm6, word ptr [rdx + r13 + 2], 4 - movd xmm2, r10d - movzx eax, word ptr [rdx + r15 + 14] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm6, word ptr [rdx + rcx + 2], 5 - movd xmm5, esi - movzx esi, word ptr [rdx + r15 + 16] - pinsrw xmm6, word ptr [rdx + rdi + 2], 6 - movd xmm3, r11d - movzx eax, word ptr [rdx + r15 + 18] - mov dword ptr [rsp + 56], eax # 4-byte Spill - pinsrw xmm6, word ptr [rdx + rbx + 2], 7 - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - movdqa xmm1, xmm6 - pand xmm1, xmm15 - psubb xmm1, xmm6 - movd xmm6, r14d - movzx r10d, word ptr [rdx + r15 + 20] - pcmpeqw xmm4, xmm0 - packsswb xmm4, xmm4 - pand xmm4, xmm15 - pinsrw xmm2, word ptr [rdx + r8 + 4], 1 - pinsrw xmm2, word ptr [rdx + r9 + 4], 2 - pinsrw xmm2, word ptr [rdx + r12 + 4], 3 - pinsrw xmm2, word ptr [rdx + r13 + 4], 4 - pinsrw xmm2, word ptr [rdx + rcx + 4], 5 - pinsrw xmm2, word ptr [rdx + rdi + 4], 6 - pinsrw xmm2, word ptr [rdx + rbx + 4], 7 - pinsrw xmm5, word ptr [rdx + r8 + 6], 1 - pinsrw xmm5, word ptr [rdx + r9 + 6], 2 - pinsrw xmm5, word ptr [rdx + r12 + 6], 3 - pinsrw xmm5, word ptr [rdx + r13 + 6], 4 - pinsrw xmm5, word ptr [rdx + rcx + 6], 5 - pinsrw xmm5, word ptr [rdx + rdi + 6], 6 - pinsrw xmm5, word ptr [rdx + rbx + 6], 7 - pinsrw xmm3, word ptr [rdx + r8 + 8], 1 - pinsrw xmm3, word ptr [rdx + r9 + 8], 2 - pinsrw xmm3, word ptr [rdx + r12 + 8], 3 - pinsrw xmm3, word ptr [rdx + r13 + 8], 4 - pinsrw xmm3, word ptr [rdx + rcx + 8], 5 - pinsrw xmm3, word ptr [rdx + rdi + 8], 6 - pinsrw xmm3, word ptr [rdx + rbx + 8], 7 - por xmm1, xmm4 - movd xmm7, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx eax, word ptr [rdx + r15 + 22] - pcmpeqw xmm2, xmm0 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 2 - pand xmm2, xmm9 - por xmm2, xmm1 - movd xmm4, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx r11d, word ptr [rdx + r15 + 24] - pcmpeqw xmm5, xmm0 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 3 - pand xmm5, xmm10 - pcmpeqw xmm3, xmm0 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 4 - pand xmm3, xmm11 - por xmm3, xmm5 - movd xmm1, esi - movzx esi, word ptr [rdx + r15 + 26] - pinsrw xmm6, word ptr [rdx + r8 + 10], 1 - pinsrw xmm6, word ptr [rdx + r9 + 10], 2 - pinsrw xmm6, word ptr [rdx + r12 + 10], 3 - pinsrw xmm6, word ptr [rdx + r13 + 10], 4 - pinsrw xmm6, word ptr [rdx + rcx + 10], 5 - pinsrw xmm6, word ptr [rdx + rdi + 10], 6 - pinsrw xmm6, word ptr [rdx + rbx + 10], 7 - pinsrw xmm7, word ptr [rdx + r8 + 12], 1 - pinsrw xmm7, word ptr [rdx + r9 + 12], 2 - pinsrw xmm7, word ptr [rdx + r12 + 12], 3 - pinsrw xmm7, word ptr [rdx + r13 + 12], 4 - pinsrw xmm7, word ptr [rdx + rcx + 12], 5 - pinsrw xmm7, word ptr [rdx + rdi + 12], 6 - pinsrw xmm7, word ptr [rdx + rbx + 12], 7 - por xmm3, xmm2 - movd xmm8, dword ptr [rsp + 56] # 4-byte Folded Reload - # xmm8 = mem[0],zero,zero,zero - movzx r14d, word ptr [rdx + r15 + 28] - pcmpeqw xmm6, xmm0 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - pcmpeqw xmm7, xmm0 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 6 - pand xmm7, xmm13 - por xmm7, xmm6 - movd xmm5, r10d - movzx r10d, word ptr [rdx + r15 + 30] - pinsrw xmm4, word ptr [rdx + r8 + 14], 1 - pinsrw xmm4, word ptr [rdx + r9 + 14], 2 - pinsrw xmm4, word ptr [rdx + r12 + 14], 3 - pinsrw xmm4, word ptr [rdx + r13 + 14], 4 - pinsrw xmm4, word ptr [rdx + rcx + 14], 5 - pinsrw xmm4, word ptr [rdx + rdi + 14], 6 - pinsrw xmm4, word ptr [rdx + rbx + 14], 7 - pinsrw xmm8, word ptr [rdx + r8 + 18], 1 - pinsrw xmm8, word ptr [rdx + r9 + 18], 2 - pinsrw xmm8, word ptr [rdx + r12 + 18], 3 - pinsrw xmm8, word ptr [rdx + r13 + 18], 4 - pinsrw xmm8, word ptr [rdx + rcx + 18], 5 - pinsrw xmm8, word ptr [rdx + rdi + 18], 6 - pinsrw xmm8, word ptr [rdx + rbx + 18], 7 - pcmpeqw xmm4, xmm0 - packsswb xmm4, xmm4 - psllw xmm4, 7 - pand xmm4, xmm14 - por xmm4, xmm7 - movd xmm2, eax - movzx eax, word ptr [rdx + r15 + 32] - por xmm4, xmm3 - pcmpeqw xmm8, xmm0 - packsswb xmm8, xmm8 - movdqa xmm7, xmm8 - pand xmm7, xmm15 - psubb xmm7, xmm8 - movd xmm3, r11d - movzx r11d, word ptr [rdx + r15 + 34] - pinsrw xmm1, word ptr [rdx + r8 + 16], 1 - pinsrw xmm1, word ptr [rdx + r9 + 16], 2 + movzx esi, word ptr [rdx + r15 + 34] + mov dword ptr [rsp + 32], esi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + r9 + 16], 1 + pinsrw xmm1, word ptr [rdx + r8 + 16], 2 pinsrw xmm1, word ptr [rdx + r12 + 16], 3 - pinsrw xmm1, word ptr [rdx + r13 + 16], 4 + pinsrw xmm1, word ptr [rdx + rdi + 16], 4 pinsrw xmm1, word ptr [rdx + rcx + 16], 5 - pinsrw xmm1, word ptr [rdx + rdi + 16], 6 - pinsrw xmm1, word ptr [rdx + rbx + 16], 7 + pinsrw xmm1, word ptr [rdx + rbx + 16], 6 + pinsrw xmm1, word ptr [rdx + rax + 16], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 por xmm7, xmm1 - movd xmm6, esi - movzx esi, word ptr [rdx + r15 + 36] - mov dword ptr [rsp + 56], esi # 4-byte Spill - pinsrw xmm5, word ptr [rdx + r8 + 20], 1 - pinsrw xmm5, word ptr [rdx + r9 + 20], 2 + movd xmm6, r10d + movzx r10d, word ptr [rdx + r15 + 36] + pinsrw xmm5, word ptr [rdx + r9 + 20], 1 + pinsrw xmm5, word ptr [rdx + r8 + 20], 2 pinsrw xmm5, word ptr [rdx + r12 + 20], 3 - pinsrw xmm5, word ptr [rdx + r13 + 20], 4 + pinsrw xmm5, word ptr [rdx + rdi + 20], 4 pinsrw xmm5, word ptr [rdx + rcx + 20], 5 - pinsrw xmm5, word ptr [rdx + rdi + 20], 6 - pinsrw xmm5, word ptr [rdx + rbx + 20], 7 + pinsrw xmm5, word ptr [rdx + rbx + 20], 6 + pinsrw xmm5, word ptr [rdx + rax + 20], 7 pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 psllw xmm5, 2 pand xmm5, xmm9 por xmm5, xmm7 - movd xmm7, r14d + movd xmm7, r11d movzx esi, word ptr [rdx + r15 + 38] - mov dword ptr [rsp + 24], esi # 4-byte Spill - pinsrw xmm2, word ptr [rdx + r8 + 22], 1 - pinsrw xmm2, word ptr [rdx + r9 + 22], 2 + mov dword ptr [rsp + 8], esi # 4-byte Spill + pinsrw xmm2, word ptr [rdx + r9 + 22], 1 + pinsrw xmm2, word ptr [rdx + r8 + 22], 2 pinsrw xmm2, word ptr [rdx + r12 + 22], 3 - pinsrw xmm2, word ptr [rdx + r13 + 22], 4 + pinsrw xmm2, word ptr [rdx + rdi + 22], 4 pinsrw xmm2, word ptr [rdx + rcx + 22], 5 - pinsrw xmm2, word ptr [rdx + rdi + 22], 6 - pinsrw xmm2, word ptr [rdx + rbx + 22], 7 - pinsrw xmm3, word ptr [rdx + r8 + 24], 1 - pinsrw xmm3, word ptr [rdx + r9 + 24], 2 + pinsrw xmm2, word ptr [rdx + rbx + 22], 6 + pinsrw xmm2, word ptr [rdx + rax + 22], 7 + pinsrw xmm3, word ptr [rdx + r9 + 24], 1 + pinsrw xmm3, word ptr [rdx + r8 + 24], 2 pinsrw xmm3, word ptr [rdx + r12 + 24], 3 - pinsrw xmm3, word ptr [rdx + r13 + 24], 4 + pinsrw xmm3, word ptr [rdx + rdi + 24], 4 pinsrw xmm3, word ptr [rdx + rcx + 24], 5 - pinsrw xmm3, word ptr [rdx + rdi + 24], 6 - pinsrw xmm3, word ptr [rdx + rbx + 24], 7 + pinsrw xmm3, word ptr [rdx + rbx + 24], 6 + pinsrw xmm3, word ptr [rdx + rax + 24], 7 pcmpeqw xmm2, xmm0 packsswb xmm2, xmm2 pand xmm2, xmm15 @@ -14776,33 +13359,32 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm3, 4 pand xmm3, xmm11 por xmm3, xmm2 - movd xmm2, r10d - movzx r14d, word ptr [rdx + r15 + 40] + movd xmm2, r13d + movzx r11d, word ptr [rdx + r15 + 40] por xmm3, xmm5 - movd xmm5, eax - movzx eax, word ptr [rdx + r15 + 42] - mov dword ptr [rsp + 40], eax # 4-byte Spill - pinsrw xmm6, word ptr [rdx + r8 + 26], 1 - pinsrw xmm6, word ptr [rdx + r9 + 26], 2 + movd xmm5, r14d + movzx r14d, word ptr [rdx + r15 + 42] + pinsrw xmm6, word ptr [rdx + r9 + 26], 1 + pinsrw xmm6, word ptr [rdx + r8 + 26], 2 pinsrw xmm6, word ptr [rdx + r12 + 26], 3 - pinsrw xmm6, word ptr [rdx + r13 + 26], 4 + pinsrw xmm6, word ptr [rdx + rdi + 26], 4 pinsrw xmm6, word ptr [rdx + rcx + 26], 5 - pinsrw xmm6, word ptr [rdx + rdi + 26], 6 - pinsrw xmm6, word ptr [rdx + rbx + 26], 7 - pinsrw xmm7, word ptr [rdx + r8 + 28], 1 - pinsrw xmm7, word ptr [rdx + r9 + 28], 2 + pinsrw xmm6, word ptr [rdx + rbx + 26], 6 + pinsrw xmm6, word ptr [rdx + rax + 26], 7 + pinsrw xmm7, word ptr [rdx + r9 + 28], 1 + pinsrw xmm7, word ptr [rdx + r8 + 28], 2 pinsrw xmm7, word ptr [rdx + r12 + 28], 3 - pinsrw xmm7, word ptr [rdx + r13 + 28], 4 + pinsrw xmm7, word ptr [rdx + rdi + 28], 4 pinsrw xmm7, word ptr [rdx + rcx + 28], 5 - pinsrw xmm7, word ptr [rdx + rdi + 28], 6 - pinsrw xmm7, word ptr [rdx + rbx + 28], 7 - pinsrw xmm2, word ptr [rdx + r8 + 30], 1 - pinsrw xmm2, word ptr [rdx + r9 + 30], 2 + pinsrw xmm7, word ptr [rdx + rbx + 28], 6 + pinsrw xmm7, word ptr [rdx + rax + 28], 7 + pinsrw xmm2, word ptr [rdx + r9 + 30], 1 + pinsrw xmm2, word ptr [rdx + r8 + 30], 2 pinsrw xmm2, word ptr [rdx + r12 + 30], 3 - pinsrw xmm2, word ptr [rdx + r13 + 30], 4 + pinsrw xmm2, word ptr [rdx + rdi + 30], 4 pinsrw xmm2, word ptr [rdx + rcx + 30], 5 - pinsrw xmm2, word ptr [rdx + rdi + 30], 6 - pinsrw xmm2, word ptr [rdx + rbx + 30], 7 + pinsrw xmm2, word ptr [rdx + rbx + 30], 6 + pinsrw xmm2, word ptr [rdx + rax + 30], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -14814,75 +13396,75 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm7, 6 pand xmm7, xmm13 por xmm7, xmm6 - movd xmm1, r11d - movzx r10d, word ptr [rdx + r15 + 44] + movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r13d, word ptr [rdx + r15 + 44] pcmpeqw xmm2, xmm0 packsswb xmm2, xmm2 psllw xmm2, 7 pand xmm2, xmm14 por xmm2, xmm7 - movd xmm6, dword ptr [rsp + 56] # 4-byte Folded Reload - # xmm6 = mem[0],zero,zero,zero - movzx esi, word ptr [rdx + r15 + 46] - pinsrw xmm5, word ptr [rdx + r8 + 32], 1 - pinsrw xmm5, word ptr [rdx + r9 + 32], 2 + movd xmm6, r10d + movzx r10d, word ptr [rdx + r15 + 46] + pinsrw xmm5, word ptr [rdx + r9 + 32], 1 + pinsrw xmm5, word ptr [rdx + r8 + 32], 2 pinsrw xmm5, word ptr [rdx + r12 + 32], 3 - pinsrw xmm5, word ptr [rdx + r13 + 32], 4 + pinsrw xmm5, word ptr [rdx + rdi + 32], 4 pinsrw xmm5, word ptr [rdx + rcx + 32], 5 - pinsrw xmm5, word ptr [rdx + rdi + 32], 6 - pinsrw xmm1, word ptr [rdx + r8 + 34], 1 - pinsrw xmm1, word ptr [rdx + r9 + 34], 2 + pinsrw xmm5, word ptr [rdx + rbx + 32], 6 + pinsrw xmm1, word ptr [rdx + r9 + 34], 1 + pinsrw xmm1, word ptr [rdx + r8 + 34], 2 pinsrw xmm1, word ptr [rdx + r12 + 34], 3 - pinsrw xmm1, word ptr [rdx + r13 + 34], 4 + pinsrw xmm1, word ptr [rdx + rdi + 34], 4 pinsrw xmm1, word ptr [rdx + rcx + 34], 5 - pinsrw xmm1, word ptr [rdx + rdi + 34], 6 - pinsrw xmm1, word ptr [rdx + rbx + 34], 7 + pinsrw xmm1, word ptr [rdx + rbx + 34], 6 + pinsrw xmm1, word ptr [rdx + rax + 34], 7 por xmm2, xmm3 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 movdqa xmm7, xmm1 pand xmm7, xmm15 psubb xmm7, xmm1 - movd xmm3, dword ptr [rsp + 24] # 4-byte Folded Reload + movd xmm3, dword ptr [rsp + 8] # 4-byte Folded Reload # xmm3 = mem[0],zero,zero,zero - movzx r11d, word ptr [rdx + r15 + 48] - pinsrw xmm5, word ptr [rdx + rbx + 32], 7 + movzx esi, word ptr [rdx + r15 + 48] + mov dword ptr [rsp + 8], esi # 4-byte Spill + pinsrw xmm5, word ptr [rdx + rax + 32], 7 pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 - pinsrw xmm6, word ptr [rdx + r8 + 36], 1 - pinsrw xmm6, word ptr [rdx + r9 + 36], 2 + pinsrw xmm6, word ptr [rdx + r9 + 36], 1 + pinsrw xmm6, word ptr [rdx + r8 + 36], 2 pinsrw xmm6, word ptr [rdx + r12 + 36], 3 - pinsrw xmm6, word ptr [rdx + r13 + 36], 4 + pinsrw xmm6, word ptr [rdx + rdi + 36], 4 pinsrw xmm6, word ptr [rdx + rcx + 36], 5 - pinsrw xmm6, word ptr [rdx + rdi + 36], 6 - pinsrw xmm6, word ptr [rdx + rbx + 36], 7 - pinsrw xmm3, word ptr [rdx + r8 + 38], 1 - pinsrw xmm3, word ptr [rdx + r9 + 38], 2 + pinsrw xmm6, word ptr [rdx + rbx + 36], 6 + pinsrw xmm6, word ptr [rdx + rax + 36], 7 + pinsrw xmm3, word ptr [rdx + r9 + 38], 1 + pinsrw xmm3, word ptr [rdx + r8 + 38], 2 pinsrw xmm3, word ptr [rdx + r12 + 38], 3 - pinsrw xmm3, word ptr [rdx + r13 + 38], 4 + pinsrw xmm3, word ptr [rdx + rdi + 38], 4 pinsrw xmm3, word ptr [rdx + rcx + 38], 5 - pinsrw xmm3, word ptr [rdx + rdi + 38], 6 - pinsrw xmm3, word ptr [rdx + rbx + 38], 7 + pinsrw xmm3, word ptr [rdx + rbx + 38], 6 + pinsrw xmm3, word ptr [rdx + rax + 38], 7 por xmm7, xmm5 - movd xmm5, r14d - pinsrw xmm5, word ptr [rdx + r8 + 40], 1 - pinsrw xmm5, word ptr [rdx + r9 + 40], 2 + movd xmm5, r11d + pinsrw xmm5, word ptr [rdx + r9 + 40], 1 + pinsrw xmm5, word ptr [rdx + r8 + 40], 2 pinsrw xmm5, word ptr [rdx + r12 + 40], 3 - pinsrw xmm5, word ptr [rdx + r13 + 40], 4 + pinsrw xmm5, word ptr [rdx + rdi + 40], 4 pinsrw xmm5, word ptr [rdx + rcx + 40], 5 - pinsrw xmm5, word ptr [rdx + rdi + 40], 6 - movzx eax, word ptr [rdx + r15 + 50] + pinsrw xmm5, word ptr [rdx + rbx + 40], 6 + movzx esi, word ptr [rdx + r15 + 50] pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 psllw xmm6, 2 pand xmm6, xmm9 por xmm6, xmm7 - movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx r14d, word ptr [rdx + r15 + 52] - pinsrw xmm5, word ptr [rdx + rbx + 40], 7 + movd xmm1, r14d + movzx r11d, word ptr [rdx + r15 + 52] + pinsrw xmm5, word ptr [rdx + rax + 40], 7 pcmpeqw xmm3, xmm0 packsswb xmm3, xmm3 pand xmm3, xmm15 @@ -14894,25 +13476,25 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm5, 4 pand xmm5, xmm11 por xmm5, xmm3 - movd xmm7, r10d - movzx r10d, word ptr [rdx + r15 + 54] - pinsrw xmm1, word ptr [rdx + r8 + 42], 1 - pinsrw xmm1, word ptr [rdx + r9 + 42], 2 + movd xmm7, r13d + movzx r14d, word ptr [rdx + r15 + 54] + pinsrw xmm1, word ptr [rdx + r9 + 42], 1 + pinsrw xmm1, word ptr [rdx + r8 + 42], 2 pinsrw xmm1, word ptr [rdx + r12 + 42], 3 - pinsrw xmm1, word ptr [rdx + r13 + 42], 4 + pinsrw xmm1, word ptr [rdx + rdi + 42], 4 pinsrw xmm1, word ptr [rdx + rcx + 42], 5 - pinsrw xmm1, word ptr [rdx + rdi + 42], 6 - pinsrw xmm1, word ptr [rdx + rbx + 42], 7 - pinsrw xmm7, word ptr [rdx + r8 + 44], 1 - pinsrw xmm7, word ptr [rdx + r9 + 44], 2 + pinsrw xmm1, word ptr [rdx + rbx + 42], 6 + pinsrw xmm1, word ptr [rdx + rax + 42], 7 + pinsrw xmm7, word ptr [rdx + r9 + 44], 1 + pinsrw xmm7, word ptr [rdx + r8 + 44], 2 pinsrw xmm7, word ptr [rdx + r12 + 44], 3 - pinsrw xmm7, word ptr [rdx + r13 + 44], 4 + pinsrw xmm7, word ptr [rdx + rdi + 44], 4 pinsrw xmm7, word ptr [rdx + rcx + 44], 5 - pinsrw xmm7, word ptr [rdx + rdi + 44], 6 + pinsrw xmm7, word ptr [rdx + rbx + 44], 6 por xmm5, xmm6 - movd xmm3, esi - movzx esi, word ptr [rdx + r15 + 56] - pinsrw xmm7, word ptr [rdx + rbx + 44], 7 + movd xmm3, r10d + movzx r10d, word ptr [rdx + r15 + 56] + pinsrw xmm7, word ptr [rdx + rax + 44], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 @@ -14924,77 +13506,78 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm7, 6 pand xmm7, xmm13 por xmm7, xmm1 - movd xmm6, r11d - movzx r11d, word ptr [rdx + r15 + 58] - pinsrw xmm3, word ptr [rdx + r8 + 46], 1 - pinsrw xmm3, word ptr [rdx + r9 + 46], 2 + movd xmm6, dword ptr [rsp + 8] # 4-byte Folded Reload + # xmm6 = mem[0],zero,zero,zero + movzx r13d, word ptr [rdx + r15 + 58] + pinsrw xmm3, word ptr [rdx + r9 + 46], 1 + pinsrw xmm3, word ptr [rdx + r8 + 46], 2 pinsrw xmm3, word ptr [rdx + r12 + 46], 3 - pinsrw xmm3, word ptr [rdx + r13 + 46], 4 + pinsrw xmm3, word ptr [rdx + rdi + 46], 4 pinsrw xmm3, word ptr [rdx + rcx + 46], 5 - pinsrw xmm3, word ptr [rdx + rdi + 46], 6 - pinsrw xmm3, word ptr [rdx + rbx + 46], 7 + pinsrw xmm3, word ptr [rdx + rbx + 46], 6 + pinsrw xmm3, word ptr [rdx + rax + 46], 7 pcmpeqw xmm3, xmm0 packsswb xmm3, xmm3 psllw xmm3, 7 pand xmm3, xmm14 por xmm3, xmm7 - movd xmm1, eax - movzx eax, word ptr [rdx + r15 + 60] + movd xmm1, esi + movzx esi, word ptr [rdx + r15 + 60] movzx r15d, word ptr [rdx + r15 + 62] - pinsrw xmm1, word ptr [rdx + r8 + 50], 1 - pinsrw xmm1, word ptr [rdx + r9 + 50], 2 + pinsrw xmm1, word ptr [rdx + r9 + 50], 1 + pinsrw xmm1, word ptr [rdx + r8 + 50], 2 pinsrw xmm1, word ptr [rdx + r12 + 50], 3 - pinsrw xmm1, word ptr [rdx + r13 + 50], 4 + pinsrw xmm1, word ptr [rdx + rdi + 50], 4 pinsrw xmm1, word ptr [rdx + rcx + 50], 5 - pinsrw xmm1, word ptr [rdx + rdi + 50], 6 - pinsrw xmm1, word ptr [rdx + rbx + 50], 7 + pinsrw xmm1, word ptr [rdx + rbx + 50], 6 + pinsrw xmm1, word ptr [rdx + rax + 50], 7 por xmm3, xmm5 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 movdqa xmm5, xmm1 pand xmm5, xmm15 psubb xmm5, xmm1 - movd xmm1, r14d - pinsrw xmm6, word ptr [rdx + r8 + 48], 1 - pinsrw xmm6, word ptr [rdx + r9 + 48], 2 + movd xmm1, r11d + pinsrw xmm6, word ptr [rdx + r9 + 48], 1 + pinsrw xmm6, word ptr [rdx + r8 + 48], 2 pinsrw xmm6, word ptr [rdx + r12 + 48], 3 - pinsrw xmm6, word ptr [rdx + r13 + 48], 4 + pinsrw xmm6, word ptr [rdx + rdi + 48], 4 pinsrw xmm6, word ptr [rdx + rcx + 48], 5 - pinsrw xmm6, word ptr [rdx + rdi + 48], 6 - pinsrw xmm6, word ptr [rdx + rbx + 48], 7 + pinsrw xmm6, word ptr [rdx + rbx + 48], 6 + pinsrw xmm6, word ptr [rdx + rax + 48], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 - pinsrw xmm1, word ptr [rdx + r8 + 52], 1 - pinsrw xmm1, word ptr [rdx + r9 + 52], 2 + pinsrw xmm1, word ptr [rdx + r9 + 52], 1 + pinsrw xmm1, word ptr [rdx + r8 + 52], 2 pinsrw xmm1, word ptr [rdx + r12 + 52], 3 - pinsrw xmm1, word ptr [rdx + r13 + 52], 4 + pinsrw xmm1, word ptr [rdx + rdi + 52], 4 pinsrw xmm1, word ptr [rdx + rcx + 52], 5 pand xmm6, xmm15 - pinsrw xmm1, word ptr [rdx + rdi + 52], 6 + pinsrw xmm1, word ptr [rdx + rbx + 52], 6 por xmm5, xmm6 - movd xmm6, r10d - pinsrw xmm1, word ptr [rdx + rbx + 52], 7 + movd xmm6, r14d + pinsrw xmm1, word ptr [rdx + rax + 52], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 psllw xmm1, 2 pand xmm1, xmm9 por xmm1, xmm5 - movd xmm5, esi - pinsrw xmm6, word ptr [rdx + r8 + 54], 1 - pinsrw xmm6, word ptr [rdx + r9 + 54], 2 + movd xmm5, r10d + pinsrw xmm6, word ptr [rdx + r9 + 54], 1 + pinsrw xmm6, word ptr [rdx + r8 + 54], 2 pinsrw xmm6, word ptr [rdx + r12 + 54], 3 - pinsrw xmm6, word ptr [rdx + r13 + 54], 4 + pinsrw xmm6, word ptr [rdx + rdi + 54], 4 pinsrw xmm6, word ptr [rdx + rcx + 54], 5 - pinsrw xmm6, word ptr [rdx + rdi + 54], 6 - pinsrw xmm6, word ptr [rdx + rbx + 54], 7 - pinsrw xmm5, word ptr [rdx + r8 + 56], 1 - pinsrw xmm5, word ptr [rdx + r9 + 56], 2 + pinsrw xmm6, word ptr [rdx + rbx + 54], 6 + pinsrw xmm6, word ptr [rdx + rax + 54], 7 + pinsrw xmm5, word ptr [rdx + r9 + 56], 1 + pinsrw xmm5, word ptr [rdx + r8 + 56], 2 pinsrw xmm5, word ptr [rdx + r12 + 56], 3 - pinsrw xmm5, word ptr [rdx + r13 + 56], 4 + pinsrw xmm5, word ptr [rdx + rdi + 56], 4 pinsrw xmm5, word ptr [rdx + rcx + 56], 5 - pinsrw xmm5, word ptr [rdx + rdi + 56], 6 - pinsrw xmm5, word ptr [rdx + rbx + 56], 7 + pinsrw xmm5, word ptr [rdx + rbx + 56], 6 + pinsrw xmm5, word ptr [rdx + rax + 56], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -15006,24 +13589,23 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm5, 4 pand xmm5, xmm11 por xmm5, xmm6 - movd xmm6, r11d - mov rsi, qword ptr [rsp] # 8-byte Reload - pinsrw xmm6, word ptr [rdx + r8 + 58], 1 - pinsrw xmm6, word ptr [rdx + r9 + 58], 2 + movd xmm6, r13d + pinsrw xmm6, word ptr [rdx + r9 + 58], 1 + pinsrw xmm6, word ptr [rdx + r8 + 58], 2 pinsrw xmm6, word ptr [rdx + r12 + 58], 3 - pinsrw xmm6, word ptr [rdx + r13 + 58], 4 + pinsrw xmm6, word ptr [rdx + rdi + 58], 4 pinsrw xmm6, word ptr [rdx + rcx + 58], 5 - pinsrw xmm6, word ptr [rdx + rdi + 58], 6 - pinsrw xmm6, word ptr [rdx + rbx + 58], 7 + pinsrw xmm6, word ptr [rdx + rbx + 58], 6 + pinsrw xmm6, word ptr [rdx + rax + 58], 7 por xmm5, xmm1 - movd xmm1, eax - pinsrw xmm1, word ptr [rdx + r8 + 60], 1 - pinsrw xmm1, word ptr [rdx + r9 + 60], 2 + movd xmm1, esi + pinsrw xmm1, word ptr [rdx + r9 + 60], 1 + pinsrw xmm1, word ptr [rdx + r8 + 60], 2 pinsrw xmm1, word ptr [rdx + r12 + 60], 3 - pinsrw xmm1, word ptr [rdx + r13 + 60], 4 + pinsrw xmm1, word ptr [rdx + rdi + 60], 4 pinsrw xmm1, word ptr [rdx + rcx + 60], 5 - pinsrw xmm1, word ptr [rdx + rdi + 60], 6 - pinsrw xmm1, word ptr [rdx + rbx + 60], 7 + pinsrw xmm1, word ptr [rdx + rbx + 60], 6 + pinsrw xmm1, word ptr [rdx + rax + 60], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -15036,13 +13618,14 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 pand xmm1, xmm13 por xmm1, xmm6 movd xmm6, r15d - pinsrw xmm6, word ptr [rdx + r8 + 62], 1 - pinsrw xmm6, word ptr [rdx + r9 + 62], 2 + pinsrw xmm6, word ptr [rdx + r9 + 62], 1 + pinsrw xmm6, word ptr [rdx + r8 + 62], 2 pinsrw xmm6, word ptr [rdx + r12 + 62], 3 - pinsrw xmm6, word ptr [rdx + r13 + 62], 4 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + pinsrw xmm6, word ptr [rdx + rdi + 62], 4 pinsrw xmm6, word ptr [rdx + rcx + 62], 5 - pinsrw xmm6, word ptr [rdx + rdi + 62], 6 - pinsrw xmm6, word ptr [rdx + rbx + 62], 7 + pinsrw xmm6, word ptr [rdx + rbx + 62], 6 + pinsrw xmm6, word ptr [rdx + rax + 62], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 psllw xmm6, 7 @@ -15060,33 +13643,32 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] punpcklbw xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7] punpcklwd xmm4, xmm3 # xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3] - mov rcx, qword ptr [rsp + 48] # 8-byte Reload + mov rcx, qword ptr [rsp + 16] # 8-byte Reload movdqu xmmword ptr [rsi + 4*rcx], xmm4 - mov qword ptr [rsp], rsi # 8-byte Spill movdqu xmmword ptr [rsi + 4*rcx + 16], xmm1 add rcx, 8 mov r15, rcx - cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB2_189 -# %bb.190: + cmp rcx, qword ptr [rsp + 24] # 8-byte Folded Reload + jne .LBB2_206 +# %bb.207: + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + cmp rcx, qword ptr [rsp + 24] # 8-byte Folded Reload mov r15, qword ptr [rsp + 152] # 8-byte Reload - cmp r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r14d, dword ptr [rsp + 8] # 4-byte Reload - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - jne .LBB2_92 - jmp .LBB2_139 -.LBB2_191: - and r15, -8 - mov rax, r15 + mov r13d, dword ptr [rsp + 48] # 4-byte Reload + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + jne .LBB2_70 + jmp .LBB2_134 +.LBB2_208: + and rcx, -8 + mov rax, rcx shl rax, 6 add rax, rdx - mov qword ptr [rsp + 64], rax # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 32], r15 # 8-byte Spill - lea rax, [rax + 4*r15] - mov qword ptr [rsp + 16], rax # 8-byte Spill - movd xmm0, r14d + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 24], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp], rax # 8-byte Spill + mov dword ptr [rsp + 48], r13d # 4-byte Spill + movd xmm0, r13d pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] xor r15d, r15d @@ -15097,100 +13679,100 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 movdqa xmm12, xmmword ptr [rip + .LCPI2_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] movdqa xmm13, xmmword ptr [rip + .LCPI2_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] movdqa xmm14, xmmword ptr [rip + .LCPI2_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + mov qword ptr [rsp + 128], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB2_192: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r15 # 8-byte Spill +.LBB2_209: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 16], r15 # 8-byte Spill shl r15, 6 - mov r9, r15 + mov r8, r15 mov r12, r15 - mov r13, r15 - mov rcx, r15 mov rdi, r15 + mov rcx, r15 mov rbx, r15 + mov rax, r15 movzx r14d, word ptr [rdx + r15] - movzx eax, word ptr [rdx + r15 + 2] - movzx r10d, word ptr [rdx + r15 + 4] - movzx esi, word ptr [rdx + r15 + 6] - movzx r11d, word ptr [rdx + r15 + 8] - mov r8, r15 - or r8, 64 - or r9, 128 + movzx esi, word ptr [rdx + r15 + 2] + movzx r11d, word ptr [rdx + r15 + 4] + movzx r13d, word ptr [rdx + r15 + 6] + movzx r10d, word ptr [rdx + r15 + 8] + mov r9, r15 + or r9, 64 + or r8, 128 or r12, 192 - or r13, 256 + or rdi, 256 or rcx, 320 - or rdi, 384 - or rbx, 448 + or rbx, 384 + or rax, 448 movd xmm4, r14d - pinsrw xmm4, word ptr [rdx + r8], 1 - pinsrw xmm4, word ptr [rdx + r9], 2 + pinsrw xmm4, word ptr [rdx + r9], 1 + pinsrw xmm4, word ptr [rdx + r8], 2 pinsrw xmm4, word ptr [rdx + r12], 3 - pinsrw xmm4, word ptr [rdx + r13], 4 + pinsrw xmm4, word ptr [rdx + rdi], 4 pinsrw xmm4, word ptr [rdx + rcx], 5 - pinsrw xmm4, word ptr [rdx + rdi], 6 - pinsrw xmm4, word ptr [rdx + rbx], 7 + pinsrw xmm4, word ptr [rdx + rbx], 6 + pinsrw xmm4, word ptr [rdx + rax], 7 movzx r14d, word ptr [rdx + r15 + 10] - movd xmm6, eax - pinsrw xmm6, word ptr [rdx + r8 + 2], 1 - pinsrw xmm6, word ptr [rdx + r9 + 2], 2 + movd xmm6, esi + pinsrw xmm6, word ptr [rdx + r9 + 2], 1 + pinsrw xmm6, word ptr [rdx + r8 + 2], 2 pinsrw xmm6, word ptr [rdx + r12 + 2], 3 - movzx eax, word ptr [rdx + r15 + 12] - mov dword ptr [rsp + 40], eax # 4-byte Spill - pinsrw xmm6, word ptr [rdx + r13 + 2], 4 - movd xmm2, r10d - movzx eax, word ptr [rdx + r15 + 14] - mov dword ptr [rsp + 24], eax # 4-byte Spill + movzx esi, word ptr [rdx + r15 + 12] + mov dword ptr [rsp + 8], esi # 4-byte Spill + pinsrw xmm6, word ptr [rdx + rdi + 2], 4 + movd xmm2, r11d + movzx r11d, word ptr [rdx + r15 + 14] pinsrw xmm6, word ptr [rdx + rcx + 2], 5 - movd xmm5, esi + movd xmm5, r13d movzx esi, word ptr [rdx + r15 + 16] - pinsrw xmm6, word ptr [rdx + rdi + 2], 6 - movd xmm3, r11d - movzx eax, word ptr [rdx + r15 + 18] - mov dword ptr [rsp + 56], eax # 4-byte Spill - pinsrw xmm6, word ptr [rdx + rbx + 2], 7 + mov dword ptr [rsp + 32], esi # 4-byte Spill + pinsrw xmm6, word ptr [rdx + rbx + 2], 6 + movd xmm3, r10d + movzx esi, word ptr [rdx + r15 + 18] + mov dword ptr [rsp + 40], esi # 4-byte Spill + pinsrw xmm6, word ptr [rdx + rax + 2], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 movdqa xmm1, xmm6 pand xmm1, xmm15 psubb xmm1, xmm6 movd xmm6, r14d - movzx r10d, word ptr [rdx + r15 + 20] + movzx r13d, word ptr [rdx + r15 + 20] pcmpeqw xmm4, xmm0 packsswb xmm4, xmm4 pand xmm4, xmm15 - pinsrw xmm2, word ptr [rdx + r8 + 4], 1 - pinsrw xmm2, word ptr [rdx + r9 + 4], 2 + pinsrw xmm2, word ptr [rdx + r9 + 4], 1 + pinsrw xmm2, word ptr [rdx + r8 + 4], 2 pinsrw xmm2, word ptr [rdx + r12 + 4], 3 - pinsrw xmm2, word ptr [rdx + r13 + 4], 4 + pinsrw xmm2, word ptr [rdx + rdi + 4], 4 pinsrw xmm2, word ptr [rdx + rcx + 4], 5 - pinsrw xmm2, word ptr [rdx + rdi + 4], 6 - pinsrw xmm2, word ptr [rdx + rbx + 4], 7 - pinsrw xmm5, word ptr [rdx + r8 + 6], 1 - pinsrw xmm5, word ptr [rdx + r9 + 6], 2 + pinsrw xmm2, word ptr [rdx + rbx + 4], 6 + pinsrw xmm2, word ptr [rdx + rax + 4], 7 + pinsrw xmm5, word ptr [rdx + r9 + 6], 1 + pinsrw xmm5, word ptr [rdx + r8 + 6], 2 pinsrw xmm5, word ptr [rdx + r12 + 6], 3 - pinsrw xmm5, word ptr [rdx + r13 + 6], 4 + pinsrw xmm5, word ptr [rdx + rdi + 6], 4 pinsrw xmm5, word ptr [rdx + rcx + 6], 5 - pinsrw xmm5, word ptr [rdx + rdi + 6], 6 - pinsrw xmm5, word ptr [rdx + rbx + 6], 7 - pinsrw xmm3, word ptr [rdx + r8 + 8], 1 - pinsrw xmm3, word ptr [rdx + r9 + 8], 2 + pinsrw xmm5, word ptr [rdx + rbx + 6], 6 + pinsrw xmm5, word ptr [rdx + rax + 6], 7 + pinsrw xmm3, word ptr [rdx + r9 + 8], 1 + pinsrw xmm3, word ptr [rdx + r8 + 8], 2 pinsrw xmm3, word ptr [rdx + r12 + 8], 3 - pinsrw xmm3, word ptr [rdx + r13 + 8], 4 + pinsrw xmm3, word ptr [rdx + rdi + 8], 4 pinsrw xmm3, word ptr [rdx + rcx + 8], 5 - pinsrw xmm3, word ptr [rdx + rdi + 8], 6 - pinsrw xmm3, word ptr [rdx + rbx + 8], 7 + pinsrw xmm3, word ptr [rdx + rbx + 8], 6 + pinsrw xmm3, word ptr [rdx + rax + 8], 7 por xmm1, xmm4 - movd xmm7, dword ptr [rsp + 40] # 4-byte Folded Reload + movd xmm7, dword ptr [rsp + 8] # 4-byte Folded Reload # xmm7 = mem[0],zero,zero,zero - movzx eax, word ptr [rdx + r15 + 22] + movzx r14d, word ptr [rdx + r15 + 22] pcmpeqw xmm2, xmm0 packsswb xmm2, xmm2 pand xmm2, xmm15 psllw xmm2, 2 pand xmm2, xmm9 por xmm2, xmm1 - movd xmm4, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx r11d, word ptr [rdx + r15 + 24] + movd xmm4, r11d + movzx esi, word ptr [rdx + r15 + 24] pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 @@ -15202,26 +13784,27 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm3, 4 pand xmm3, xmm11 por xmm3, xmm5 - movd xmm1, esi - movzx esi, word ptr [rdx + r15 + 26] - pinsrw xmm6, word ptr [rdx + r8 + 10], 1 - pinsrw xmm6, word ptr [rdx + r9 + 10], 2 + movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r10d, word ptr [rdx + r15 + 26] + pinsrw xmm6, word ptr [rdx + r9 + 10], 1 + pinsrw xmm6, word ptr [rdx + r8 + 10], 2 pinsrw xmm6, word ptr [rdx + r12 + 10], 3 - pinsrw xmm6, word ptr [rdx + r13 + 10], 4 + pinsrw xmm6, word ptr [rdx + rdi + 10], 4 pinsrw xmm6, word ptr [rdx + rcx + 10], 5 - pinsrw xmm6, word ptr [rdx + rdi + 10], 6 - pinsrw xmm6, word ptr [rdx + rbx + 10], 7 - pinsrw xmm7, word ptr [rdx + r8 + 12], 1 - pinsrw xmm7, word ptr [rdx + r9 + 12], 2 + pinsrw xmm6, word ptr [rdx + rbx + 10], 6 + pinsrw xmm6, word ptr [rdx + rax + 10], 7 + pinsrw xmm7, word ptr [rdx + r9 + 12], 1 + pinsrw xmm7, word ptr [rdx + r8 + 12], 2 pinsrw xmm7, word ptr [rdx + r12 + 12], 3 - pinsrw xmm7, word ptr [rdx + r13 + 12], 4 + pinsrw xmm7, word ptr [rdx + rdi + 12], 4 pinsrw xmm7, word ptr [rdx + rcx + 12], 5 - pinsrw xmm7, word ptr [rdx + rdi + 12], 6 - pinsrw xmm7, word ptr [rdx + rbx + 12], 7 + pinsrw xmm7, word ptr [rdx + rbx + 12], 6 + pinsrw xmm7, word ptr [rdx + rax + 12], 7 por xmm3, xmm2 - movd xmm8, dword ptr [rsp + 56] # 4-byte Folded Reload + movd xmm8, dword ptr [rsp + 40] # 4-byte Folded Reload # xmm8 = mem[0],zero,zero,zero - movzx r14d, word ptr [rdx + r15 + 28] + movzx r11d, word ptr [rdx + r15 + 28] pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -15233,81 +13816,81 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm7, 6 pand xmm7, xmm13 por xmm7, xmm6 - movd xmm5, r10d - movzx r10d, word ptr [rdx + r15 + 30] - pinsrw xmm4, word ptr [rdx + r8 + 14], 1 - pinsrw xmm4, word ptr [rdx + r9 + 14], 2 + movd xmm5, r13d + movzx r13d, word ptr [rdx + r15 + 30] + pinsrw xmm4, word ptr [rdx + r9 + 14], 1 + pinsrw xmm4, word ptr [rdx + r8 + 14], 2 pinsrw xmm4, word ptr [rdx + r12 + 14], 3 - pinsrw xmm4, word ptr [rdx + r13 + 14], 4 + pinsrw xmm4, word ptr [rdx + rdi + 14], 4 pinsrw xmm4, word ptr [rdx + rcx + 14], 5 - pinsrw xmm4, word ptr [rdx + rdi + 14], 6 - pinsrw xmm4, word ptr [rdx + rbx + 14], 7 - pinsrw xmm8, word ptr [rdx + r8 + 18], 1 - pinsrw xmm8, word ptr [rdx + r9 + 18], 2 + pinsrw xmm4, word ptr [rdx + rbx + 14], 6 + pinsrw xmm4, word ptr [rdx + rax + 14], 7 + pinsrw xmm8, word ptr [rdx + r9 + 18], 1 + pinsrw xmm8, word ptr [rdx + r8 + 18], 2 pinsrw xmm8, word ptr [rdx + r12 + 18], 3 - pinsrw xmm8, word ptr [rdx + r13 + 18], 4 + pinsrw xmm8, word ptr [rdx + rdi + 18], 4 pinsrw xmm8, word ptr [rdx + rcx + 18], 5 - pinsrw xmm8, word ptr [rdx + rdi + 18], 6 - pinsrw xmm8, word ptr [rdx + rbx + 18], 7 + pinsrw xmm8, word ptr [rdx + rbx + 18], 6 + pinsrw xmm8, word ptr [rdx + rax + 18], 7 pcmpeqw xmm4, xmm0 packsswb xmm4, xmm4 psllw xmm4, 7 pand xmm4, xmm14 por xmm4, xmm7 - movd xmm2, eax - movzx eax, word ptr [rdx + r15 + 32] + movd xmm2, r14d + movzx r14d, word ptr [rdx + r15 + 32] por xmm4, xmm3 pcmpeqw xmm8, xmm0 packsswb xmm8, xmm8 movdqa xmm7, xmm8 pand xmm7, xmm15 psubb xmm7, xmm8 - movd xmm3, r11d - movzx r11d, word ptr [rdx + r15 + 34] - pinsrw xmm1, word ptr [rdx + r8 + 16], 1 - pinsrw xmm1, word ptr [rdx + r9 + 16], 2 + movd xmm3, esi + movzx esi, word ptr [rdx + r15 + 34] + mov dword ptr [rsp + 32], esi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + r9 + 16], 1 + pinsrw xmm1, word ptr [rdx + r8 + 16], 2 pinsrw xmm1, word ptr [rdx + r12 + 16], 3 - pinsrw xmm1, word ptr [rdx + r13 + 16], 4 + pinsrw xmm1, word ptr [rdx + rdi + 16], 4 pinsrw xmm1, word ptr [rdx + rcx + 16], 5 - pinsrw xmm1, word ptr [rdx + rdi + 16], 6 - pinsrw xmm1, word ptr [rdx + rbx + 16], 7 + pinsrw xmm1, word ptr [rdx + rbx + 16], 6 + pinsrw xmm1, word ptr [rdx + rax + 16], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 por xmm7, xmm1 - movd xmm6, esi - movzx esi, word ptr [rdx + r15 + 36] - mov dword ptr [rsp + 56], esi # 4-byte Spill - pinsrw xmm5, word ptr [rdx + r8 + 20], 1 - pinsrw xmm5, word ptr [rdx + r9 + 20], 2 + movd xmm6, r10d + movzx r10d, word ptr [rdx + r15 + 36] + pinsrw xmm5, word ptr [rdx + r9 + 20], 1 + pinsrw xmm5, word ptr [rdx + r8 + 20], 2 pinsrw xmm5, word ptr [rdx + r12 + 20], 3 - pinsrw xmm5, word ptr [rdx + r13 + 20], 4 + pinsrw xmm5, word ptr [rdx + rdi + 20], 4 pinsrw xmm5, word ptr [rdx + rcx + 20], 5 - pinsrw xmm5, word ptr [rdx + rdi + 20], 6 - pinsrw xmm5, word ptr [rdx + rbx + 20], 7 + pinsrw xmm5, word ptr [rdx + rbx + 20], 6 + pinsrw xmm5, word ptr [rdx + rax + 20], 7 pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 psllw xmm5, 2 pand xmm5, xmm9 por xmm5, xmm7 - movd xmm7, r14d + movd xmm7, r11d movzx esi, word ptr [rdx + r15 + 38] - mov dword ptr [rsp + 24], esi # 4-byte Spill - pinsrw xmm2, word ptr [rdx + r8 + 22], 1 - pinsrw xmm2, word ptr [rdx + r9 + 22], 2 + mov dword ptr [rsp + 8], esi # 4-byte Spill + pinsrw xmm2, word ptr [rdx + r9 + 22], 1 + pinsrw xmm2, word ptr [rdx + r8 + 22], 2 pinsrw xmm2, word ptr [rdx + r12 + 22], 3 - pinsrw xmm2, word ptr [rdx + r13 + 22], 4 + pinsrw xmm2, word ptr [rdx + rdi + 22], 4 pinsrw xmm2, word ptr [rdx + rcx + 22], 5 - pinsrw xmm2, word ptr [rdx + rdi + 22], 6 - pinsrw xmm2, word ptr [rdx + rbx + 22], 7 - pinsrw xmm3, word ptr [rdx + r8 + 24], 1 - pinsrw xmm3, word ptr [rdx + r9 + 24], 2 + pinsrw xmm2, word ptr [rdx + rbx + 22], 6 + pinsrw xmm2, word ptr [rdx + rax + 22], 7 + pinsrw xmm3, word ptr [rdx + r9 + 24], 1 + pinsrw xmm3, word ptr [rdx + r8 + 24], 2 pinsrw xmm3, word ptr [rdx + r12 + 24], 3 - pinsrw xmm3, word ptr [rdx + r13 + 24], 4 + pinsrw xmm3, word ptr [rdx + rdi + 24], 4 pinsrw xmm3, word ptr [rdx + rcx + 24], 5 - pinsrw xmm3, word ptr [rdx + rdi + 24], 6 - pinsrw xmm3, word ptr [rdx + rbx + 24], 7 + pinsrw xmm3, word ptr [rdx + rbx + 24], 6 + pinsrw xmm3, word ptr [rdx + rax + 24], 7 pcmpeqw xmm2, xmm0 packsswb xmm2, xmm2 pand xmm2, xmm15 @@ -15319,33 +13902,32 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm3, 4 pand xmm3, xmm11 por xmm3, xmm2 - movd xmm2, r10d - movzx r14d, word ptr [rdx + r15 + 40] + movd xmm2, r13d + movzx r11d, word ptr [rdx + r15 + 40] por xmm3, xmm5 - movd xmm5, eax - movzx eax, word ptr [rdx + r15 + 42] - mov dword ptr [rsp + 40], eax # 4-byte Spill - pinsrw xmm6, word ptr [rdx + r8 + 26], 1 - pinsrw xmm6, word ptr [rdx + r9 + 26], 2 + movd xmm5, r14d + movzx r14d, word ptr [rdx + r15 + 42] + pinsrw xmm6, word ptr [rdx + r9 + 26], 1 + pinsrw xmm6, word ptr [rdx + r8 + 26], 2 pinsrw xmm6, word ptr [rdx + r12 + 26], 3 - pinsrw xmm6, word ptr [rdx + r13 + 26], 4 + pinsrw xmm6, word ptr [rdx + rdi + 26], 4 pinsrw xmm6, word ptr [rdx + rcx + 26], 5 - pinsrw xmm6, word ptr [rdx + rdi + 26], 6 - pinsrw xmm6, word ptr [rdx + rbx + 26], 7 - pinsrw xmm7, word ptr [rdx + r8 + 28], 1 - pinsrw xmm7, word ptr [rdx + r9 + 28], 2 + pinsrw xmm6, word ptr [rdx + rbx + 26], 6 + pinsrw xmm6, word ptr [rdx + rax + 26], 7 + pinsrw xmm7, word ptr [rdx + r9 + 28], 1 + pinsrw xmm7, word ptr [rdx + r8 + 28], 2 pinsrw xmm7, word ptr [rdx + r12 + 28], 3 - pinsrw xmm7, word ptr [rdx + r13 + 28], 4 + pinsrw xmm7, word ptr [rdx + rdi + 28], 4 pinsrw xmm7, word ptr [rdx + rcx + 28], 5 - pinsrw xmm7, word ptr [rdx + rdi + 28], 6 - pinsrw xmm7, word ptr [rdx + rbx + 28], 7 - pinsrw xmm2, word ptr [rdx + r8 + 30], 1 - pinsrw xmm2, word ptr [rdx + r9 + 30], 2 + pinsrw xmm7, word ptr [rdx + rbx + 28], 6 + pinsrw xmm7, word ptr [rdx + rax + 28], 7 + pinsrw xmm2, word ptr [rdx + r9 + 30], 1 + pinsrw xmm2, word ptr [rdx + r8 + 30], 2 pinsrw xmm2, word ptr [rdx + r12 + 30], 3 - pinsrw xmm2, word ptr [rdx + r13 + 30], 4 + pinsrw xmm2, word ptr [rdx + rdi + 30], 4 pinsrw xmm2, word ptr [rdx + rcx + 30], 5 - pinsrw xmm2, word ptr [rdx + rdi + 30], 6 - pinsrw xmm2, word ptr [rdx + rbx + 30], 7 + pinsrw xmm2, word ptr [rdx + rbx + 30], 6 + pinsrw xmm2, word ptr [rdx + rax + 30], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -15357,75 +13939,75 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm7, 6 pand xmm7, xmm13 por xmm7, xmm6 - movd xmm1, r11d - movzx r10d, word ptr [rdx + r15 + 44] + movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r13d, word ptr [rdx + r15 + 44] pcmpeqw xmm2, xmm0 packsswb xmm2, xmm2 psllw xmm2, 7 pand xmm2, xmm14 por xmm2, xmm7 - movd xmm6, dword ptr [rsp + 56] # 4-byte Folded Reload - # xmm6 = mem[0],zero,zero,zero - movzx esi, word ptr [rdx + r15 + 46] - pinsrw xmm5, word ptr [rdx + r8 + 32], 1 - pinsrw xmm5, word ptr [rdx + r9 + 32], 2 + movd xmm6, r10d + movzx r10d, word ptr [rdx + r15 + 46] + pinsrw xmm5, word ptr [rdx + r9 + 32], 1 + pinsrw xmm5, word ptr [rdx + r8 + 32], 2 pinsrw xmm5, word ptr [rdx + r12 + 32], 3 - pinsrw xmm5, word ptr [rdx + r13 + 32], 4 + pinsrw xmm5, word ptr [rdx + rdi + 32], 4 pinsrw xmm5, word ptr [rdx + rcx + 32], 5 - pinsrw xmm5, word ptr [rdx + rdi + 32], 6 - pinsrw xmm1, word ptr [rdx + r8 + 34], 1 - pinsrw xmm1, word ptr [rdx + r9 + 34], 2 + pinsrw xmm5, word ptr [rdx + rbx + 32], 6 + pinsrw xmm1, word ptr [rdx + r9 + 34], 1 + pinsrw xmm1, word ptr [rdx + r8 + 34], 2 pinsrw xmm1, word ptr [rdx + r12 + 34], 3 - pinsrw xmm1, word ptr [rdx + r13 + 34], 4 + pinsrw xmm1, word ptr [rdx + rdi + 34], 4 pinsrw xmm1, word ptr [rdx + rcx + 34], 5 - pinsrw xmm1, word ptr [rdx + rdi + 34], 6 - pinsrw xmm1, word ptr [rdx + rbx + 34], 7 + pinsrw xmm1, word ptr [rdx + rbx + 34], 6 + pinsrw xmm1, word ptr [rdx + rax + 34], 7 por xmm2, xmm3 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 movdqa xmm7, xmm1 pand xmm7, xmm15 psubb xmm7, xmm1 - movd xmm3, dword ptr [rsp + 24] # 4-byte Folded Reload + movd xmm3, dword ptr [rsp + 8] # 4-byte Folded Reload # xmm3 = mem[0],zero,zero,zero - movzx r11d, word ptr [rdx + r15 + 48] - pinsrw xmm5, word ptr [rdx + rbx + 32], 7 + movzx esi, word ptr [rdx + r15 + 48] + mov dword ptr [rsp + 8], esi # 4-byte Spill + pinsrw xmm5, word ptr [rdx + rax + 32], 7 pcmpeqw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 - pinsrw xmm6, word ptr [rdx + r8 + 36], 1 - pinsrw xmm6, word ptr [rdx + r9 + 36], 2 + pinsrw xmm6, word ptr [rdx + r9 + 36], 1 + pinsrw xmm6, word ptr [rdx + r8 + 36], 2 pinsrw xmm6, word ptr [rdx + r12 + 36], 3 - pinsrw xmm6, word ptr [rdx + r13 + 36], 4 + pinsrw xmm6, word ptr [rdx + rdi + 36], 4 pinsrw xmm6, word ptr [rdx + rcx + 36], 5 - pinsrw xmm6, word ptr [rdx + rdi + 36], 6 - pinsrw xmm6, word ptr [rdx + rbx + 36], 7 - pinsrw xmm3, word ptr [rdx + r8 + 38], 1 - pinsrw xmm3, word ptr [rdx + r9 + 38], 2 + pinsrw xmm6, word ptr [rdx + rbx + 36], 6 + pinsrw xmm6, word ptr [rdx + rax + 36], 7 + pinsrw xmm3, word ptr [rdx + r9 + 38], 1 + pinsrw xmm3, word ptr [rdx + r8 + 38], 2 pinsrw xmm3, word ptr [rdx + r12 + 38], 3 - pinsrw xmm3, word ptr [rdx + r13 + 38], 4 + pinsrw xmm3, word ptr [rdx + rdi + 38], 4 pinsrw xmm3, word ptr [rdx + rcx + 38], 5 - pinsrw xmm3, word ptr [rdx + rdi + 38], 6 - pinsrw xmm3, word ptr [rdx + rbx + 38], 7 + pinsrw xmm3, word ptr [rdx + rbx + 38], 6 + pinsrw xmm3, word ptr [rdx + rax + 38], 7 por xmm7, xmm5 - movd xmm5, r14d - pinsrw xmm5, word ptr [rdx + r8 + 40], 1 - pinsrw xmm5, word ptr [rdx + r9 + 40], 2 + movd xmm5, r11d + pinsrw xmm5, word ptr [rdx + r9 + 40], 1 + pinsrw xmm5, word ptr [rdx + r8 + 40], 2 pinsrw xmm5, word ptr [rdx + r12 + 40], 3 - pinsrw xmm5, word ptr [rdx + r13 + 40], 4 + pinsrw xmm5, word ptr [rdx + rdi + 40], 4 pinsrw xmm5, word ptr [rdx + rcx + 40], 5 - pinsrw xmm5, word ptr [rdx + rdi + 40], 6 - movzx eax, word ptr [rdx + r15 + 50] + pinsrw xmm5, word ptr [rdx + rbx + 40], 6 + movzx esi, word ptr [rdx + r15 + 50] pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 psllw xmm6, 2 pand xmm6, xmm9 por xmm6, xmm7 - movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx r14d, word ptr [rdx + r15 + 52] - pinsrw xmm5, word ptr [rdx + rbx + 40], 7 + movd xmm1, r14d + movzx r11d, word ptr [rdx + r15 + 52] + pinsrw xmm5, word ptr [rdx + rax + 40], 7 pcmpeqw xmm3, xmm0 packsswb xmm3, xmm3 pand xmm3, xmm15 @@ -15437,25 +14019,25 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm5, 4 pand xmm5, xmm11 por xmm5, xmm3 - movd xmm7, r10d - movzx r10d, word ptr [rdx + r15 + 54] - pinsrw xmm1, word ptr [rdx + r8 + 42], 1 - pinsrw xmm1, word ptr [rdx + r9 + 42], 2 + movd xmm7, r13d + movzx r14d, word ptr [rdx + r15 + 54] + pinsrw xmm1, word ptr [rdx + r9 + 42], 1 + pinsrw xmm1, word ptr [rdx + r8 + 42], 2 pinsrw xmm1, word ptr [rdx + r12 + 42], 3 - pinsrw xmm1, word ptr [rdx + r13 + 42], 4 + pinsrw xmm1, word ptr [rdx + rdi + 42], 4 pinsrw xmm1, word ptr [rdx + rcx + 42], 5 - pinsrw xmm1, word ptr [rdx + rdi + 42], 6 - pinsrw xmm1, word ptr [rdx + rbx + 42], 7 - pinsrw xmm7, word ptr [rdx + r8 + 44], 1 - pinsrw xmm7, word ptr [rdx + r9 + 44], 2 + pinsrw xmm1, word ptr [rdx + rbx + 42], 6 + pinsrw xmm1, word ptr [rdx + rax + 42], 7 + pinsrw xmm7, word ptr [rdx + r9 + 44], 1 + pinsrw xmm7, word ptr [rdx + r8 + 44], 2 pinsrw xmm7, word ptr [rdx + r12 + 44], 3 - pinsrw xmm7, word ptr [rdx + r13 + 44], 4 + pinsrw xmm7, word ptr [rdx + rdi + 44], 4 pinsrw xmm7, word ptr [rdx + rcx + 44], 5 - pinsrw xmm7, word ptr [rdx + rdi + 44], 6 + pinsrw xmm7, word ptr [rdx + rbx + 44], 6 por xmm5, xmm6 - movd xmm3, esi - movzx esi, word ptr [rdx + r15 + 56] - pinsrw xmm7, word ptr [rdx + rbx + 44], 7 + movd xmm3, r10d + movzx r10d, word ptr [rdx + r15 + 56] + pinsrw xmm7, word ptr [rdx + rax + 44], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 @@ -15467,77 +14049,78 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm7, 6 pand xmm7, xmm13 por xmm7, xmm1 - movd xmm6, r11d - movzx r11d, word ptr [rdx + r15 + 58] - pinsrw xmm3, word ptr [rdx + r8 + 46], 1 - pinsrw xmm3, word ptr [rdx + r9 + 46], 2 + movd xmm6, dword ptr [rsp + 8] # 4-byte Folded Reload + # xmm6 = mem[0],zero,zero,zero + movzx r13d, word ptr [rdx + r15 + 58] + pinsrw xmm3, word ptr [rdx + r9 + 46], 1 + pinsrw xmm3, word ptr [rdx + r8 + 46], 2 pinsrw xmm3, word ptr [rdx + r12 + 46], 3 - pinsrw xmm3, word ptr [rdx + r13 + 46], 4 + pinsrw xmm3, word ptr [rdx + rdi + 46], 4 pinsrw xmm3, word ptr [rdx + rcx + 46], 5 - pinsrw xmm3, word ptr [rdx + rdi + 46], 6 - pinsrw xmm3, word ptr [rdx + rbx + 46], 7 + pinsrw xmm3, word ptr [rdx + rbx + 46], 6 + pinsrw xmm3, word ptr [rdx + rax + 46], 7 pcmpeqw xmm3, xmm0 packsswb xmm3, xmm3 psllw xmm3, 7 pand xmm3, xmm14 por xmm3, xmm7 - movd xmm1, eax - movzx eax, word ptr [rdx + r15 + 60] + movd xmm1, esi + movzx esi, word ptr [rdx + r15 + 60] movzx r15d, word ptr [rdx + r15 + 62] - pinsrw xmm1, word ptr [rdx + r8 + 50], 1 - pinsrw xmm1, word ptr [rdx + r9 + 50], 2 + pinsrw xmm1, word ptr [rdx + r9 + 50], 1 + pinsrw xmm1, word ptr [rdx + r8 + 50], 2 pinsrw xmm1, word ptr [rdx + r12 + 50], 3 - pinsrw xmm1, word ptr [rdx + r13 + 50], 4 + pinsrw xmm1, word ptr [rdx + rdi + 50], 4 pinsrw xmm1, word ptr [rdx + rcx + 50], 5 - pinsrw xmm1, word ptr [rdx + rdi + 50], 6 - pinsrw xmm1, word ptr [rdx + rbx + 50], 7 + pinsrw xmm1, word ptr [rdx + rbx + 50], 6 + pinsrw xmm1, word ptr [rdx + rax + 50], 7 por xmm3, xmm5 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 movdqa xmm5, xmm1 pand xmm5, xmm15 psubb xmm5, xmm1 - movd xmm1, r14d - pinsrw xmm6, word ptr [rdx + r8 + 48], 1 - pinsrw xmm6, word ptr [rdx + r9 + 48], 2 + movd xmm1, r11d + pinsrw xmm6, word ptr [rdx + r9 + 48], 1 + pinsrw xmm6, word ptr [rdx + r8 + 48], 2 pinsrw xmm6, word ptr [rdx + r12 + 48], 3 - pinsrw xmm6, word ptr [rdx + r13 + 48], 4 + pinsrw xmm6, word ptr [rdx + rdi + 48], 4 pinsrw xmm6, word ptr [rdx + rcx + 48], 5 - pinsrw xmm6, word ptr [rdx + rdi + 48], 6 - pinsrw xmm6, word ptr [rdx + rbx + 48], 7 + pinsrw xmm6, word ptr [rdx + rbx + 48], 6 + pinsrw xmm6, word ptr [rdx + rax + 48], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 - pinsrw xmm1, word ptr [rdx + r8 + 52], 1 - pinsrw xmm1, word ptr [rdx + r9 + 52], 2 + pinsrw xmm1, word ptr [rdx + r9 + 52], 1 + pinsrw xmm1, word ptr [rdx + r8 + 52], 2 pinsrw xmm1, word ptr [rdx + r12 + 52], 3 - pinsrw xmm1, word ptr [rdx + r13 + 52], 4 + pinsrw xmm1, word ptr [rdx + rdi + 52], 4 pinsrw xmm1, word ptr [rdx + rcx + 52], 5 pand xmm6, xmm15 - pinsrw xmm1, word ptr [rdx + rdi + 52], 6 + pinsrw xmm1, word ptr [rdx + rbx + 52], 6 por xmm5, xmm6 - movd xmm6, r10d - pinsrw xmm1, word ptr [rdx + rbx + 52], 7 + movd xmm6, r14d + pinsrw xmm1, word ptr [rdx + rax + 52], 7 pcmpeqw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 psllw xmm1, 2 pand xmm1, xmm9 por xmm1, xmm5 - movd xmm5, esi - pinsrw xmm6, word ptr [rdx + r8 + 54], 1 - pinsrw xmm6, word ptr [rdx + r9 + 54], 2 + movd xmm5, r10d + pinsrw xmm6, word ptr [rdx + r9 + 54], 1 + pinsrw xmm6, word ptr [rdx + r8 + 54], 2 pinsrw xmm6, word ptr [rdx + r12 + 54], 3 - pinsrw xmm6, word ptr [rdx + r13 + 54], 4 + pinsrw xmm6, word ptr [rdx + rdi + 54], 4 pinsrw xmm6, word ptr [rdx + rcx + 54], 5 - pinsrw xmm6, word ptr [rdx + rdi + 54], 6 - pinsrw xmm6, word ptr [rdx + rbx + 54], 7 - pinsrw xmm5, word ptr [rdx + r8 + 56], 1 - pinsrw xmm5, word ptr [rdx + r9 + 56], 2 + pinsrw xmm6, word ptr [rdx + rbx + 54], 6 + pinsrw xmm6, word ptr [rdx + rax + 54], 7 + pinsrw xmm5, word ptr [rdx + r9 + 56], 1 + pinsrw xmm5, word ptr [rdx + r8 + 56], 2 pinsrw xmm5, word ptr [rdx + r12 + 56], 3 - pinsrw xmm5, word ptr [rdx + r13 + 56], 4 + pinsrw xmm5, word ptr [rdx + rdi + 56], 4 pinsrw xmm5, word ptr [rdx + rcx + 56], 5 - pinsrw xmm5, word ptr [rdx + rdi + 56], 6 - pinsrw xmm5, word ptr [rdx + rbx + 56], 7 + pinsrw xmm5, word ptr [rdx + rbx + 56], 6 + pinsrw xmm5, word ptr [rdx + rax + 56], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -15549,24 +14132,23 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 psllw xmm5, 4 pand xmm5, xmm11 por xmm5, xmm6 - movd xmm6, r11d - mov rsi, qword ptr [rsp] # 8-byte Reload - pinsrw xmm6, word ptr [rdx + r8 + 58], 1 - pinsrw xmm6, word ptr [rdx + r9 + 58], 2 + movd xmm6, r13d + pinsrw xmm6, word ptr [rdx + r9 + 58], 1 + pinsrw xmm6, word ptr [rdx + r8 + 58], 2 pinsrw xmm6, word ptr [rdx + r12 + 58], 3 - pinsrw xmm6, word ptr [rdx + r13 + 58], 4 + pinsrw xmm6, word ptr [rdx + rdi + 58], 4 pinsrw xmm6, word ptr [rdx + rcx + 58], 5 - pinsrw xmm6, word ptr [rdx + rdi + 58], 6 - pinsrw xmm6, word ptr [rdx + rbx + 58], 7 + pinsrw xmm6, word ptr [rdx + rbx + 58], 6 + pinsrw xmm6, word ptr [rdx + rax + 58], 7 por xmm5, xmm1 - movd xmm1, eax - pinsrw xmm1, word ptr [rdx + r8 + 60], 1 - pinsrw xmm1, word ptr [rdx + r9 + 60], 2 + movd xmm1, esi + pinsrw xmm1, word ptr [rdx + r9 + 60], 1 + pinsrw xmm1, word ptr [rdx + r8 + 60], 2 pinsrw xmm1, word ptr [rdx + r12 + 60], 3 - pinsrw xmm1, word ptr [rdx + r13 + 60], 4 + pinsrw xmm1, word ptr [rdx + rdi + 60], 4 pinsrw xmm1, word ptr [rdx + rcx + 60], 5 - pinsrw xmm1, word ptr [rdx + rdi + 60], 6 - pinsrw xmm1, word ptr [rdx + rbx + 60], 7 + pinsrw xmm1, word ptr [rdx + rbx + 60], 6 + pinsrw xmm1, word ptr [rdx + rax + 60], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -15579,13 +14161,14 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 pand xmm1, xmm13 por xmm1, xmm6 movd xmm6, r15d - pinsrw xmm6, word ptr [rdx + r8 + 62], 1 - pinsrw xmm6, word ptr [rdx + r9 + 62], 2 + pinsrw xmm6, word ptr [rdx + r9 + 62], 1 + pinsrw xmm6, word ptr [rdx + r8 + 62], 2 pinsrw xmm6, word ptr [rdx + r12 + 62], 3 - pinsrw xmm6, word ptr [rdx + r13 + 62], 4 + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + pinsrw xmm6, word ptr [rdx + rdi + 62], 4 pinsrw xmm6, word ptr [rdx + rcx + 62], 5 - pinsrw xmm6, word ptr [rdx + rdi + 62], 6 - pinsrw xmm6, word ptr [rdx + rbx + 62], 7 + pinsrw xmm6, word ptr [rdx + rbx + 62], 6 + pinsrw xmm6, word ptr [rdx + rax + 62], 7 pcmpeqw xmm6, xmm0 packsswb xmm6, xmm6 psllw xmm6, 7 @@ -15603,34 +14186,32 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] punpcklbw xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7] punpcklwd xmm4, xmm3 # xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3] - mov rcx, qword ptr [rsp + 48] # 8-byte Reload + mov rcx, qword ptr [rsp + 16] # 8-byte Reload movdqu xmmword ptr [rsi + 4*rcx], xmm4 - mov qword ptr [rsp], rsi # 8-byte Spill movdqu xmmword ptr [rsi + 4*rcx + 16], xmm1 add rcx, 8 mov r15, rcx - cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB2_192 -# %bb.193: + cmp rcx, qword ptr [rsp + 24] # 8-byte Folded Reload + jne .LBB2_209 +# %bb.210: + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + cmp rcx, qword ptr [rsp + 24] # 8-byte Folded Reload mov r15, qword ptr [rsp + 152] # 8-byte Reload - cmp r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 144] # 8-byte Reload - mov r14d, dword ptr [rsp + 8] # 4-byte Reload - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - jne .LBB2_104 - jmp .LBB2_144 -.LBB2_194: - mov r8, r14 - and r8, -4 - mov rbx, r8 + mov r13d, dword ptr [rsp + 48] # 4-byte Reload + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + jne .LBB2_84 + jmp .LBB2_139 +.LBB2_211: + mov rax, rcx + and rax, -4 + mov rbx, rax shl rbx, 7 add rbx, rdx - mov rax, qword ptr [rsp] # 8-byte Reload - lea r15, [rax + 4*r8] - movaps xmm1, xmm0 + lea r13, [r12 + 4*rax] + movdqa xmm1, xmm0 shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] add rdx, 508 - xor ecx, ecx + xor esi, esi movdqa xmm15, xmmword ptr [rip + .LCPI2_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> movdqa xmm8, xmmword ptr [rip + .LCPI2_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] movdqa xmm10, xmmword ptr [rip + .LCPI2_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] @@ -15639,9 +14220,8 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 movdqa xmm13, xmmword ptr [rip + .LCPI2_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] movdqa xmm14, xmmword ptr [rip + .LCPI2_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] movdqa xmm9, xmmword ptr [rip + .LCPI2_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] - mov rax, qword ptr [rsp] # 8-byte Reload .p2align 4, 0x90 -.LBB2_195: # =>This Inner Loop Header: Depth=1 +.LBB2_212: # =>This Inner Loop Header: Depth=1 movss xmm6, dword ptr [rdx - 508] # xmm6 = mem[0],zero,zero,zero movss xmm7, dword ptr [rdx - 504] # xmm7 = mem[0],zero,zero,zero movss xmm5, dword ptr [rdx - 500] # xmm5 = mem[0],zero,zero,zero @@ -15982,1240 +14562,2150 @@ comparison_equal_scalar_arr_sse4: # @comparison_equal_scalar_arr_sse4 punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] pshufb xmm4, xmm9 - movdqu xmmword ptr [rax + 4*rcx], xmm4 - add rcx, 4 - add rdx, 512 - cmp r8, rcx - jne .LBB2_195 -# %bb.196: - cmp r14, r8 - jne .LBB2_127 - jmp .LBB2_148 -.Lfunc_end2: - .size comparison_equal_scalar_arr_sse4, .Lfunc_end2-comparison_equal_scalar_arr_sse4 - # -- End function - .globl comparison_not_equal_arr_arr_sse4 # -- Begin function comparison_not_equal_arr_arr_sse4 - .p2align 4, 0x90 - .type comparison_not_equal_arr_arr_sse4,@function -comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 -# %bb.0: - push rbp - mov rbp, rsp - push r15 - push r14 - push r13 - push r12 - push rbx - and rsp, -8 - sub rsp, 72 - mov eax, r9d - mov r14, r8 - mov r12, rcx - cmp edi, 6 - jg .LBB3_29 -# %bb.1: - cmp edi, 3 - jle .LBB3_2 -# %bb.15: - cmp edi, 4 - je .LBB3_68 -# %bb.16: - cmp edi, 5 - je .LBB3_79 -# %bb.17: - cmp edi, 6 - jne .LBB3_123 -# %bb.18: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_22 -# %bb.19: - cdqe - .p2align 4, 0x90 -.LBB3_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] + movdqu xmmword ptr [r12 + 4*rsi], xmm4 add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB3_20 -# %bb.21: - add r12, 1 -.LBB3_22: - sar r15, 5 - cmp r14, 32 - jl .LBB3_26 -# %bb.23: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB3_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - mov eax, dword ptr [rsi] - mov ecx, dword ptr [rsi + 4] - cmp eax, dword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill - cmp ecx, dword ptr [rdx + 4] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 8] - cmp eax, dword ptr [rdx + 8] - setne byte ptr [rsp + 21] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 12] - cmp eax, dword ptr [rdx + 12] - setne byte ptr [rsp + 22] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 16] - cmp eax, dword ptr [rdx + 16] - setne byte ptr [rsp + 23] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 20] - cmp eax, dword ptr [rdx + 20] - setne byte ptr [rsp + 3] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 24] - cmp eax, dword ptr [rdx + 24] - setne byte ptr [rsp + 5] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 28] - cmp eax, dword ptr [rdx + 28] - setne r13b - mov eax, dword ptr [rsi + 32] - cmp eax, dword ptr [rdx + 32] - setne byte ptr [rsp + 10] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 36] - cmp eax, dword ptr [rdx + 36] - setne r8b - mov eax, dword ptr [rsi + 40] - cmp eax, dword ptr [rdx + 40] - setne r11b - mov eax, dword ptr [rsi + 44] - cmp eax, dword ptr [rdx + 44] - setne r15b - mov eax, dword ptr [rsi + 48] - cmp eax, dword ptr [rdx + 48] - setne byte ptr [rsp + 6] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 52] - cmp eax, dword ptr [rdx + 52] - setne byte ptr [rsp + 7] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 56] - cmp eax, dword ptr [rdx + 56] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 60] - cmp eax, dword ptr [rdx + 60] - setne dil - mov eax, dword ptr [rsi + 64] - mov ebx, dword ptr [rsi + 68] - cmp eax, dword ptr [rdx + 64] - mov eax, dword ptr [rsi + 72] - setne byte ptr [rsp + 11] # 1-byte Folded Spill - cmp ebx, dword ptr [rdx + 68] - mov ebx, dword ptr [rsi + 76] - setne r10b - cmp eax, dword ptr [rdx + 72] - mov eax, dword ptr [rsi + 80] - setne r14b - cmp ebx, dword ptr [rdx + 76] - mov ebx, dword ptr [rsi + 84] - setne r12b - cmp eax, dword ptr [rdx + 80] - setne byte ptr [rsp + 9] # 1-byte Folded Spill - cmp ebx, dword ptr [rdx + 84] - mov eax, dword ptr [rsi + 88] - setne byte ptr [rsp + 12] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 88] - mov eax, dword ptr [rsi + 92] - setne byte ptr [rsp + 13] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 92] - mov eax, dword ptr [rsi + 96] - setne r9b - cmp eax, dword ptr [rdx + 96] - mov eax, dword ptr [rsi + 100] - setne byte ptr [rsp + 20] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 100] - mov eax, dword ptr [rsi + 104] - setne byte ptr [rsp + 14] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 104] - mov eax, dword ptr [rsi + 108] - setne byte ptr [rsp + 15] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 108] - mov eax, dword ptr [rsi + 112] - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 112] - mov eax, dword ptr [rsi + 116] - setne byte ptr [rsp + 17] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 116] - mov eax, dword ptr [rsi + 120] - setne byte ptr [rsp + 19] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 120] - mov eax, dword ptr [rsi + 124] - setne byte ptr [rsp + 18] # 1-byte Folded Spill - sub rsi, -128 - cmp eax, dword ptr [rdx + 124] - setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload - shl al, 6 - shl r13b, 7 - or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload - shl al, 2 - or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload - shl bl, 3 - or bl, al - mov eax, ebx - shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload - shl bl, 4 - or bl, al - mov r8d, ebx - shl r15b, 3 - or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload - shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload - shl al, 4 - or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload - shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b - or r13b, bl - or dil, al - add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r10b - shl r12b, 3 - or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload - shl al, 4 - or al, r12b - mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload - shl al, 5 - or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload - shl bl, 6 - shl r9b, 7 - or r9b, bl - mov byte ptr [r12 + 1], dil - or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload - shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl - add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_24 -# %bb.25: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_26: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.27: - sub r14, r15 - xor ecx, ecx + add rdx, 512 + cmp rax, rsi + jne .LBB2_212 +# %bb.213: + cmp rcx, rax + jne .LBB2_111 + jmp .LBB2_143 +.LBB2_214: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, r14 + mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 216], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 96], rax # 8-byte Spill + movzx eax, r11b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 128], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB3_28: # =>This Inner Loop Header: Depth=1 - lea r8, [rcx + 1] - mov edi, dword ptr [rsi + 4*rcx] - cmp edi, dword ptr [rdx + 4*rcx] - setne bl - neg bl +.LBB2_215: # =>This Inner Loop Header: Depth=1 + mov rdx, rax + mov qword ptr [rsp + 144], rax # 8-byte Spill + shl rdx, 5 + mov rax, rdx + mov r8, rdx + mov r11, rdx + mov rsi, rdx + mov r13, rdx + mov qword ptr [rsp + 48], rdx # 8-byte Spill + mov r9, rdx + mov r10, rdx + mov rdi, rdx + mov r15, rdx + mov qword ptr [rsp + 64], rdx # 8-byte Spill + movzx ecx, byte ptr [r14 + rdx] + movd xmm15, ecx + movzx ecx, byte ptr [r14 + rdx + 1] + movd xmm5, ecx + movzx ecx, byte ptr [r14 + rdx + 2] + movd xmm6, ecx + movzx ecx, byte ptr [r14 + rdx + 3] + movd xmm2, ecx + movzx ecx, byte ptr [r14 + rdx + 4] + movd xmm1, ecx + movzx ecx, byte ptr [r14 + rdx + 5] + movd xmm8, ecx + movzx ecx, byte ptr [r14 + rdx + 6] + movd xmm3, ecx + movzx ecx, byte ptr [r14 + rdx + 7] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rdx + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rdx + 9] + movd xmm10, ecx + movzx ecx, byte ptr [r14 + rdx + 10] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rdx + 11] + movd xmm11, ecx + movzx ecx, byte ptr [r14 + rdx + 12] + movd xmm13, ecx + movzx ecx, byte ptr [r14 + rdx + 13] + movd xmm12, ecx + movzx ecx, byte ptr [r14 + rdx + 14] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill + mov r12, rdx + or r12, 32 + mov qword ptr [rsp + 32], r12 # 8-byte Spill + or rax, 64 + mov qword ptr [rsp + 40], rax # 8-byte Spill + or r8, 96 + or r11, 128 + or rsi, 160 + mov qword ptr [rsp + 72], rsi # 8-byte Spill + or r13, 192 + or qword ptr [rsp + 48], 224 # 8-byte Folded Spill + or r9, 256 + or r10, 288 + mov rbx, rdx + or rbx, 320 + mov qword ptr [rsp + 120], rbx # 8-byte Spill + or r15, 352 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + or rsi, 384 + mov qword ptr [rsp + 64], rsi # 8-byte Spill + mov rcx, rdx + or rcx, 416 + mov qword ptr [rsp + 16], rcx # 8-byte Spill + mov rcx, rdx + mov qword ptr [rsp + 56], rdx # 8-byte Spill + or rdi, 448 + mov qword ptr [rsp + 8], rdi # 8-byte Spill + or rcx, 480 + mov qword ptr [rsp + 24], rcx # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r12], 1 + pinsrb xmm15, byte ptr [r14 + rax], 2 + pinsrb xmm15, byte ptr [r14 + r8], 3 + mov rdx, r11 + pinsrb xmm15, byte ptr [r14 + r11], 4 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r12], 5 + pinsrb xmm15, byte ptr [r14 + r13], 6 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 7 + pinsrb xmm15, byte ptr [r14 + r9], 8 + pinsrb xmm15, byte ptr [r14 + r10], 9 + pinsrb xmm15, byte ptr [r14 + rbx], 10 + pinsrb xmm15, byte ptr [r14 + r15], 11 + pinsrb xmm15, byte ptr [r14 + rsi], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 13 + pinsrb xmm15, byte ptr [r14 + rdi], 14 + pinsrb xmm15, byte ptr [r14 + rcx], 15 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r11 + 1], 1 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 2 + pinsrb xmm5, byte ptr [r14 + r8 + 1], 3 + pinsrb xmm5, byte ptr [r14 + rdx + 1], 4 + pinsrb xmm5, byte ptr [r14 + r12 + 1], 5 + pinsrb xmm5, byte ptr [r14 + r13 + 1], 6 + mov r12, r13 + mov qword ptr [rsp + 88], r13 # 8-byte Spill + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 7 + pinsrb xmm5, byte ptr [r14 + r9 + 1], 8 + pinsrb xmm5, byte ptr [r14 + r10 + 1], 9 + pinsrb xmm5, byte ptr [r14 + rbx + 1], 10 + pinsrb xmm5, byte ptr [r14 + r15 + 1], 11 + pinsrb xmm5, byte ptr [r14 + rsi + 1], 12 + mov r11, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r11 + 1], 13 + pinsrb xmm5, byte ptr [r14 + rdi + 1], 14 + pinsrb xmm5, byte ptr [r14 + rcx + 1], 15 + movdqa xmm9, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm5, xmm9 + movdqa xmm7, xmm5 + movdqa xmm4, xmmword ptr [rip + .LCPI2_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm7, xmm4 + psubb xmm7, xmm5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 15] + movd xmm14, esi + pcmpeqb xmm15, xmm9 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rcx + 2], 1 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r13 + 2], 2 + mov rdi, r8 + pinsrb xmm6, byte ptr [r14 + r8 + 2], 3 + mov rbx, rdx + pinsrb xmm6, byte ptr [r14 + rdx + 2], 4 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdx + 2], 5 + pinsrb xmm6, byte ptr [r14 + r12 + 2], 6 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r8 + 2], 7 + pinsrb xmm6, byte ptr [r14 + r9 + 2], 8 + mov qword ptr [rsp + 112], r10 # 8-byte Spill + pinsrb xmm6, byte ptr [r14 + r10 + 2], 9 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r12 + 2], 10 + mov qword ptr [rsp + 104], r15 # 8-byte Spill + pinsrb xmm6, byte ptr [r14 + r15 + 2], 11 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 12 + pinsrb xmm6, byte ptr [r14 + r11 + 2], 13 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 14 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 15 + pand xmm15, xmm4 + pcmpeqb xmm6, xmm9 + movdqa xmm0, xmmword ptr [rip + .LCPI2_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm6, xmm0 + por xmm6, xmm15 + movzx esi, byte ptr [r14 + rax + 16] + movd xmm15, esi + mov rax, rcx + pinsrb xmm2, byte ptr [r14 + rcx + 3], 1 + pinsrb xmm2, byte ptr [r14 + r13 + 3], 2 + mov qword ptr [rsp + 80], rdi # 8-byte Spill + pinsrb xmm2, byte ptr [r14 + rdi + 3], 3 + pinsrb xmm2, byte ptr [r14 + rbx + 3], 4 + pinsrb xmm2, byte ptr [r14 + rdx + 3], 5 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rcx + 3], 6 + pinsrb xmm2, byte ptr [r14 + r8 + 3], 7 + pinsrb xmm2, byte ptr [r14 + r9 + 3], 8 + pinsrb xmm2, byte ptr [r14 + r10 + 3], 9 + pinsrb xmm2, byte ptr [r14 + r12 + 3], 10 + pinsrb xmm2, byte ptr [r14 + r15 + 3], 11 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r12 + 3], 12 + pinsrb xmm2, byte ptr [r14 + r11 + 3], 13 + mov r15, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r15 + 3], 14 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rsi + 3], 15 + pinsrb xmm1, byte ptr [r14 + rax + 4], 1 + pinsrb xmm1, byte ptr [r14 + r13 + 4], 2 + pinsrb xmm1, byte ptr [r14 + rdi + 4], 3 + pinsrb xmm1, byte ptr [r14 + rbx + 4], 4 + pinsrb xmm1, byte ptr [r14 + rdx + 4], 5 + pinsrb xmm1, byte ptr [r14 + rcx + 4], 6 + pinsrb xmm1, byte ptr [r14 + r8 + 4], 7 + pinsrb xmm1, byte ptr [r14 + r9 + 4], 8 + pinsrb xmm1, byte ptr [r14 + r10 + 4], 9 + mov r10, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + r10 + 4], 10 + mov rdi, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rdi + 4], 11 + pinsrb xmm1, byte ptr [r14 + r12 + 4], 12 + pinsrb xmm1, byte ptr [r14 + r11 + 4], 13 + mov r12, r11 + pinsrb xmm1, byte ptr [r14 + r15 + 4], 14 + pinsrb xmm1, byte ptr [r14 + rsi + 4], 15 + por xmm6, xmm7 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 17] + movd xmm0, esi + pcmpeqb xmm2, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI2_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm2, xmm5 + pcmpeqb xmm1, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI2_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm1, xmm5 + por xmm1, xmm2 + movzx esi, byte ptr [r14 + rax + 18] + movd xmm5, esi + mov r15, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r15 + 5], 1 + pinsrb xmm8, byte ptr [r14 + r13 + 5], 2 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rcx + 5], 3 + pinsrb xmm8, byte ptr [r14 + rbx + 5], 4 + pinsrb xmm8, byte ptr [r14 + rdx + 5], 5 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 6 + mov qword ptr [rsp + 48], r8 # 8-byte Spill + pinsrb xmm8, byte ptr [r14 + r8 + 5], 7 + pinsrb xmm8, byte ptr [r14 + r9 + 5], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 9 + mov r11, r10 + pinsrb xmm8, byte ptr [r14 + r10 + 5], 10 + pinsrb xmm8, byte ptr [r14 + rdi + 5], 11 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 12 + pinsrb xmm8, byte ptr [r14 + r12 + 5], 13 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 14 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 15 + pcmpeqb xmm8, xmm9 + movdqa xmm2, xmmword ptr [rip + .LCPI2_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm8, xmm2 + por xmm8, xmm1 + movzx esi, byte ptr [r14 + rax + 19] + movd xmm7, esi + por xmm8, xmm6 + movzx esi, byte ptr [r14 + rax + 20] + movd xmm6, esi + pinsrb xmm3, byte ptr [r14 + r15 + 6], 1 + mov r10, r15 + pinsrb xmm3, byte ptr [r14 + r13 + 6], 2 + pinsrb xmm3, byte ptr [r14 + rcx + 6], 3 mov rdi, rcx - shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] - xor bl, r9b - and cl, 7 - mov al, 1 - # kill: def $cl killed $cl killed $rcx - shl al, cl - and al, bl - xor al, r9b - mov byte ptr [r12 + rdi], al - mov rcx, r8 - cmp r14, r8 - jne .LBB3_28 - jmp .LBB3_123 -.LBB3_29: - cmp edi, 8 - jle .LBB3_30 -# %bb.43: - cmp edi, 9 - je .LBB3_101 -# %bb.44: - cmp edi, 11 - je .LBB3_112 -# %bb.45: - cmp edi, 12 - jne .LBB3_123 -# %bb.46: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_50 -# %bb.47: - movsxd r10, eax - .p2align 4, 0x90 -.LBB3_48: # =>This Inner Loop Header: Depth=1 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - ucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - setp cl - setne bl - or bl, cl - neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 - sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d - mov eax, 1 - # kill: def $cl killed $cl killed $ecx - shl eax, cl - and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB3_48 -# %bb.49: - add r12, 1 -.LBB3_50: - sar r15, 5 - cmp r14, 32 - jl .LBB3_54 -# %bb.51: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + mov r13, rbx + pinsrb xmm3, byte ptr [r14 + rbx + 6], 4 + pinsrb xmm3, byte ptr [r14 + rdx + 6], 5 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rcx + 6], 6 + pinsrb xmm3, byte ptr [r14 + r8 + 6], 7 + mov rax, r9 + pinsrb xmm3, byte ptr [r14 + r9 + 6], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rsi + 6], 9 + pinsrb xmm3, byte ptr [r14 + r11 + 6], 10 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r15 + 6], 11 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r12 + 6], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rbx + 6], 13 + mov r9, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r9 + 6], 14 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r8 + 6], 15 + movdqa xmm2, xmmword ptr [rsp + 192] # 16-byte Reload + pinsrb xmm2, byte ptr [r14 + r10 + 7], 1 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rbx + 7], 2 + pinsrb xmm2, byte ptr [r14 + rdi + 7], 3 + pinsrb xmm2, byte ptr [r14 + r13 + 7], 4 + mov r10, r13 + mov qword ptr [rsp + 136], r13 # 8-byte Spill + pinsrb xmm2, byte ptr [r14 + rdx + 7], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 7], 6 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rcx + 7], 7 + pinsrb xmm2, byte ptr [r14 + rax + 7], 8 + mov rbx, rax + mov qword ptr [rsp + 256], rax # 8-byte Spill + pinsrb xmm2, byte ptr [r14 + rsi + 7], 9 + pinsrb xmm2, byte ptr [r14 + r11 + 7], 10 + pinsrb xmm2, byte ptr [r14 + r15 + 7], 11 + mov r11, r15 + pinsrb xmm2, byte ptr [r14 + r12 + 7], 12 + mov r13, r12 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdi + 7], 13 + pinsrb xmm2, byte ptr [r14 + r9 + 7], 14 + pinsrb xmm2, byte ptr [r14 + r8 + 7], 15 + pcmpeqb xmm3, xmm9 + movdqa xmm1, xmmword ptr [rip + .LCPI2_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm1 + pcmpeqb xmm2, xmm9 + psllw xmm2, 7 + movdqa xmm1, xmmword ptr [rip + .LCPI2_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm2, xmm1 + por xmm2, xmm3 + movdqa xmm1, xmm2 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 21] + movd xmm2, esi + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rcx + 9], 1 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdx + 9], 2 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdx + 9], 3 + pinsrb xmm10, byte ptr [r14 + r10 + 9], 4 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r10 + 9], 5 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r9 + 9], 6 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rsi + 9], 7 + pinsrb xmm10, byte ptr [r14 + rbx + 9], 8 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r15 + 9], 9 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r12 + 9], 10 + pinsrb xmm10, byte ptr [r14 + r11 + 9], 11 + pinsrb xmm10, byte ptr [r14 + r13 + 9], 12 + pinsrb xmm10, byte ptr [r14 + rdi + 9], 13 + mov rdi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdi + 9], 14 + pinsrb xmm10, byte ptr [r14 + r8 + 9], 15 + por xmm1, xmm8 + movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill + pcmpeqb xmm10, xmm9 + movdqa xmm1, xmm10 + movdqa xmm8, xmm4 + pand xmm1, xmm4 + psubb xmm1, xmm10 + movzx esi, byte ptr [r14 + rax + 22] + movd xmm3, esi + movdqa xmm4, xmmword ptr [rsp + 224] # 16-byte Reload + pinsrb xmm4, byte ptr [r14 + rcx + 8], 1 + mov r8, rcx + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rbx + 8], 2 + pinsrb xmm4, byte ptr [r14 + rdx + 8], 3 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 8], 4 + mov rdx, r10 + pinsrb xmm4, byte ptr [r14 + r10 + 8], 5 + pinsrb xmm4, byte ptr [r14 + r9 + 8], 6 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r11 + 8], 7 + mov rax, qword ptr [rsp + 256] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 8], 8 + mov rsi, r15 + pinsrb xmm4, byte ptr [r14 + r15 + 8], 9 + mov r15, r12 + pinsrb xmm4, byte ptr [r14 + r12 + 8], 10 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rcx + 8], 11 + pinsrb xmm4, byte ptr [r14 + r13 + 8], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rcx + 8], 13 + pinsrb xmm4, byte ptr [r14 + rdi + 8], 14 + mov r10, rdi + mov r9, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r9 + 8], 15 + pcmpeqb xmm4, xmm9 + pand xmm4, xmm8 + movdqa xmm10, xmmword ptr [rsp + 160] # 16-byte Reload + pinsrb xmm10, byte ptr [r14 + r8 + 10], 1 + pinsrb xmm10, byte ptr [r14 + rbx + 10], 2 + mov rdi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdi + 10], 3 + mov rbx, rdi + mov rdi, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdi + 10], 4 + pinsrb xmm10, byte ptr [r14 + rdx + 10], 5 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r12 + 10], 6 + mov r8, r11 + pinsrb xmm10, byte ptr [r14 + r11 + 10], 7 + pinsrb xmm10, byte ptr [r14 + rax + 10], 8 + mov r11, rax + pinsrb xmm10, byte ptr [r14 + rsi + 10], 9 + pinsrb xmm10, byte ptr [r14 + r15 + 10], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rax + 10], 11 + pinsrb xmm10, byte ptr [r14 + r13 + 10], 12 + pinsrb xmm10, byte ptr [r14 + rcx + 10], 13 + pinsrb xmm10, byte ptr [r14 + r10 + 10], 14 + pinsrb xmm10, byte ptr [r14 + r9 + 10], 15 + pcmpeqb xmm10, xmm9 + pand xmm10, xmmword ptr [rip + .LCPI2_11] + por xmm10, xmm4 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r14 + rcx + 23] + movd xmm8, esi + por xmm10, xmm1 + movdqa xmmword ptr [rsp + 160], xmm10 # 16-byte Spill + movzx esi, byte ptr [r14 + rcx + 24] + movd xmm10, esi + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 1 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rcx + 11], 2 + pinsrb xmm11, byte ptr [r14 + rbx + 11], 3 + pinsrb xmm11, byte ptr [r14 + rdi + 11], 4 + mov rdi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdi + 11], 5 + mov rcx, r12 + pinsrb xmm11, byte ptr [r14 + r12 + 11], 6 + pinsrb xmm11, byte ptr [r14 + r8 + 11], 7 + mov r9, r11 + pinsrb xmm11, byte ptr [r14 + r11 + 11], 8 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r10 + 11], 9 + mov r11, r15 + pinsrb xmm11, byte ptr [r14 + r15 + 11], 10 + mov r15, rax + pinsrb xmm11, byte ptr [r14 + rax + 11], 11 + mov r12, r13 + pinsrb xmm11, byte ptr [r14 + r13 + 11], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rax + 11], 13 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rsi + 11], 14 + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rbx + 11], 15 + pinsrb xmm13, byte ptr [r14 + rdx + 12], 1 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + r13 + 12], 2 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rbx + 12], 3 + mov r13, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + r13 + 12], 4 + pinsrb xmm13, byte ptr [r14 + rdi + 12], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 12], 6 + pinsrb xmm13, byte ptr [r14 + r8 + 12], 7 + pinsrb xmm13, byte ptr [r14 + r9 + 12], 8 + pinsrb xmm13, byte ptr [r14 + r10 + 12], 9 + pinsrb xmm13, byte ptr [r14 + r11 + 12], 10 + pinsrb xmm13, byte ptr [r14 + r15 + 12], 11 + pinsrb xmm13, byte ptr [r14 + r12 + 12], 12 + pinsrb xmm13, byte ptr [r14 + rax + 12], 13 + pinsrb xmm13, byte ptr [r14 + rsi + 12], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rax + 12], 15 + pinsrb xmm12, byte ptr [r14 + rdx + 13], 1 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 2 + pinsrb xmm12, byte ptr [r14 + rbx + 13], 3 + mov rbx, r13 + pinsrb xmm12, byte ptr [r14 + r13 + 13], 4 + pinsrb xmm12, byte ptr [r14 + rdi + 13], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 13], 6 + pinsrb xmm12, byte ptr [r14 + r8 + 13], 7 + pinsrb xmm12, byte ptr [r14 + r9 + 13], 8 + pinsrb xmm12, byte ptr [r14 + r10 + 13], 9 + pinsrb xmm12, byte ptr [r14 + r11 + 13], 10 + pinsrb xmm12, byte ptr [r14 + r15 + 13], 11 + pinsrb xmm12, byte ptr [r14 + r12 + 13], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 13 + pinsrb xmm12, byte ptr [r14 + rsi + 13], 14 + pinsrb xmm12, byte ptr [r14 + rax + 13], 15 + pcmpeqb xmm11, xmm9 + pand xmm11, xmmword ptr [rip + .LCPI2_12] + pcmpeqb xmm13, xmm9 + pand xmm13, xmmword ptr [rip + .LCPI2_13] + por xmm13, xmm11 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 25] + movd xmm1, esi + pcmpeqb xmm12, xmm9 + pand xmm12, xmmword ptr [rip + .LCPI2_14] + por xmm12, xmm13 + movzx esi, byte ptr [r14 + rax + 26] + movd xmm11, esi + movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 14], 1 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r13 + 14], 2 + mov rdi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdi + 14], 3 + pinsrb xmm4, byte ptr [r14 + rbx + 14], 4 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 14], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 14], 6 + pinsrb xmm4, byte ptr [r14 + r8 + 14], 7 + pinsrb xmm4, byte ptr [r14 + r9 + 14], 8 + pinsrb xmm4, byte ptr [r14 + r10 + 14], 9 + mov rsi, r11 + pinsrb xmm4, byte ptr [r14 + r11 + 14], 10 + pinsrb xmm4, byte ptr [r14 + r15 + 14], 11 + pinsrb xmm4, byte ptr [r14 + r12 + 14], 12 + pinsrb xmm4, byte ptr [r14 + rdx + 14], 13 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 14], 14 + mov r11, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r11 + 14], 15 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 1 + pinsrb xmm14, byte ptr [r14 + r13 + 15], 2 + pinsrb xmm14, byte ptr [r14 + rdi + 15], 3 + pinsrb xmm14, byte ptr [r14 + rbx + 15], 4 + pinsrb xmm14, byte ptr [r14 + rax + 15], 5 + pinsrb xmm14, byte ptr [r14 + rcx + 15], 6 + pinsrb xmm14, byte ptr [r14 + r8 + 15], 7 + pinsrb xmm14, byte ptr [r14 + r9 + 15], 8 + pinsrb xmm14, byte ptr [r14 + r10 + 15], 9 + pinsrb xmm14, byte ptr [r14 + rsi + 15], 10 + pinsrb xmm14, byte ptr [r14 + r15 + 15], 11 + pinsrb xmm14, byte ptr [r14 + r12 + 15], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 13 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 14 + pinsrb xmm14, byte ptr [r14 + r11 + 15], 15 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rdx + 16], 1 + pinsrb xmm15, byte ptr [r14 + r13 + 16], 2 + pinsrb xmm15, byte ptr [r14 + rdi + 16], 3 + pinsrb xmm15, byte ptr [r14 + rbx + 16], 4 + pinsrb xmm15, byte ptr [r14 + rax + 16], 5 + pinsrb xmm15, byte ptr [r14 + rcx + 16], 6 + pinsrb xmm15, byte ptr [r14 + r8 + 16], 7 + pinsrb xmm15, byte ptr [r14 + r9 + 16], 8 + pinsrb xmm15, byte ptr [r14 + r10 + 16], 9 + pinsrb xmm15, byte ptr [r14 + rsi + 16], 10 + pinsrb xmm15, byte ptr [r14 + r15 + 16], 11 + pinsrb xmm15, byte ptr [r14 + r12 + 16], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rdx + 16], 13 + mov r11, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r11 + 16], 14 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 17], 1 + pinsrb xmm0, byte ptr [r14 + r13 + 17], 2 + pinsrb xmm0, byte ptr [r14 + rdi + 17], 3 + pinsrb xmm0, byte ptr [r14 + rbx + 17], 4 + pinsrb xmm0, byte ptr [r14 + rax + 17], 5 + mov r13, rax + pinsrb xmm0, byte ptr [r14 + rcx + 17], 6 + pinsrb xmm0, byte ptr [r14 + r8 + 17], 7 + pinsrb xmm0, byte ptr [r14 + r9 + 17], 8 + pinsrb xmm0, byte ptr [r14 + r10 + 17], 9 + pinsrb xmm0, byte ptr [r14 + rsi + 17], 10 + pinsrb xmm0, byte ptr [r14 + r15 + 17], 11 + pinsrb xmm0, byte ptr [r14 + r12 + 17], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 17], 13 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 17], 14 + por xmm12, xmmword ptr [rsp + 160] # 16-byte Folded Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 27] + movd xmm9, esi + movdqa xmm13, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm4, xmm13 + pand xmm4, xmmword ptr [rip + .LCPI2_15] + pcmpeqb xmm14, xmm13 + psllw xmm14, 7 + pand xmm14, xmmword ptr [rip + .LCPI2_6] + por xmm14, xmm4 + movzx esi, byte ptr [r14 + rax + 28] + movd xmm4, esi + mov r11, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r11 + 17], 15 + por xmm14, xmm12 + pcmpeqb xmm0, xmm13 + movdqa xmm13, xmm0 + movdqa xmm12, xmmword ptr [rip + .LCPI2_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm13, xmm12 + psubb xmm13, xmm0 + movdqa xmmword ptr [rsp + 160], xmm13 # 16-byte Spill + movzx esi, byte ptr [r14 + rax + 29] + movd xmm13, esi + pinsrb xmm15, byte ptr [r14 + r11 + 16], 15 + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm15, xmm0 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rsi + 18], 1 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rsi + 18], 2 + pinsrb xmm5, byte ptr [r14 + rdi + 18], 3 + pinsrb xmm5, byte ptr [r14 + rbx + 18], 4 + pinsrb xmm5, byte ptr [r14 + r13 + 18], 5 + pinsrb xmm5, byte ptr [r14 + rcx + 18], 6 + pinsrb xmm5, byte ptr [r14 + r8 + 18], 7 + pinsrb xmm5, byte ptr [r14 + r9 + 18], 8 + pinsrb xmm5, byte ptr [r14 + r10 + 18], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 18], 10 + pinsrb xmm5, byte ptr [r14 + r15 + 18], 11 + pinsrb xmm5, byte ptr [r14 + r12 + 18], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rsi + 18], 13 + pinsrb xmm5, byte ptr [r14 + rdx + 18], 14 + pand xmm15, xmm12 + pinsrb xmm5, byte ptr [r14 + r11 + 18], 15 + pcmpeqb xmm5, xmm0 + pand xmm5, xmmword ptr [rip + .LCPI2_11] + por xmm5, xmm15 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r14 + rdx + 30] + movd xmm12, esi + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rsi + 19], 1 + pinsrb xmm6, byte ptr [r14 + rsi + 20], 1 + pinsrb xmm2, byte ptr [r14 + rsi + 21], 1 + pinsrb xmm3, byte ptr [r14 + rsi + 22], 1 + pinsrb xmm8, byte ptr [r14 + rsi + 23], 1 + pinsrb xmm10, byte ptr [r14 + rsi + 24], 1 + pinsrb xmm1, byte ptr [r14 + rsi + 25], 1 + pinsrb xmm11, byte ptr [r14 + rsi + 26], 1 + pinsrb xmm9, byte ptr [r14 + rsi + 27], 1 + pinsrb xmm4, byte ptr [r14 + rsi + 28], 1 + pinsrb xmm13, byte ptr [r14 + rsi + 29], 1 + pinsrb xmm12, byte ptr [r14 + rsi + 30], 1 + movzx edx, byte ptr [r14 + rdx + 31] + movd xmm0, edx + pinsrb xmm0, byte ptr [r14 + rsi + 31], 1 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdx + 19], 2 + pinsrb xmm6, byte ptr [r14 + rdx + 20], 2 + pinsrb xmm2, byte ptr [r14 + rdx + 21], 2 + pinsrb xmm3, byte ptr [r14 + rdx + 22], 2 + pinsrb xmm8, byte ptr [r14 + rdx + 23], 2 + pinsrb xmm10, byte ptr [r14 + rdx + 24], 2 + pinsrb xmm1, byte ptr [r14 + rdx + 25], 2 + pinsrb xmm11, byte ptr [r14 + rdx + 26], 2 + pinsrb xmm9, byte ptr [r14 + rdx + 27], 2 + pinsrb xmm4, byte ptr [r14 + rdx + 28], 2 + pinsrb xmm13, byte ptr [r14 + rdx + 29], 2 + pinsrb xmm12, byte ptr [r14 + rdx + 30], 2 + pinsrb xmm0, byte ptr [r14 + rdx + 31], 2 + pinsrb xmm7, byte ptr [r14 + rdi + 19], 3 + pinsrb xmm7, byte ptr [r14 + rbx + 19], 4 + pinsrb xmm7, byte ptr [r14 + r13 + 19], 5 + pinsrb xmm7, byte ptr [r14 + rcx + 19], 6 + pinsrb xmm7, byte ptr [r14 + r8 + 19], 7 + pinsrb xmm7, byte ptr [r14 + r9 + 19], 8 + pinsrb xmm7, byte ptr [r14 + r10 + 19], 9 + pinsrb xmm7, byte ptr [r14 + rax + 19], 10 + pinsrb xmm7, byte ptr [r14 + r15 + 19], 11 + pinsrb xmm7, byte ptr [r14 + r12 + 19], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdx + 19], 13 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rsi + 19], 14 + pinsrb xmm7, byte ptr [r14 + r11 + 19], 15 + pinsrb xmm6, byte ptr [r14 + rdi + 20], 3 + pinsrb xmm6, byte ptr [r14 + rbx + 20], 4 + pinsrb xmm6, byte ptr [r14 + r13 + 20], 5 + pinsrb xmm6, byte ptr [r14 + rcx + 20], 6 + pinsrb xmm6, byte ptr [r14 + r8 + 20], 7 + pinsrb xmm6, byte ptr [r14 + r9 + 20], 8 + pinsrb xmm6, byte ptr [r14 + r10 + 20], 9 + pinsrb xmm6, byte ptr [r14 + rax + 20], 10 + pinsrb xmm6, byte ptr [r14 + r15 + 20], 11 + pinsrb xmm6, byte ptr [r14 + r12 + 20], 12 + pinsrb xmm6, byte ptr [r14 + rdx + 20], 13 + pinsrb xmm6, byte ptr [r14 + rsi + 20], 14 + por xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload + pinsrb xmm6, byte ptr [r14 + r11 + 20], 15 + movdqa xmm15, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm7, xmm15 + pand xmm7, xmmword ptr [rip + .LCPI2_12] + pcmpeqb xmm6, xmm15 + pand xmm6, xmmword ptr [rip + .LCPI2_13] + por xmm6, xmm7 + pinsrb xmm2, byte ptr [r14 + rdi + 21], 3 + pinsrb xmm2, byte ptr [r14 + rbx + 21], 4 + pinsrb xmm2, byte ptr [r14 + r13 + 21], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 21], 6 + pinsrb xmm2, byte ptr [r14 + r8 + 21], 7 + pinsrb xmm2, byte ptr [r14 + r9 + 21], 8 + pinsrb xmm2, byte ptr [r14 + r10 + 21], 9 + pinsrb xmm2, byte ptr [r14 + rax + 21], 10 + pinsrb xmm2, byte ptr [r14 + r15 + 21], 11 + pinsrb xmm2, byte ptr [r14 + r12 + 21], 12 + pinsrb xmm2, byte ptr [r14 + rdx + 21], 13 + pinsrb xmm2, byte ptr [r14 + rsi + 21], 14 + pinsrb xmm2, byte ptr [r14 + r11 + 21], 15 + pcmpeqb xmm2, xmm15 + movdqa xmm7, xmmword ptr [rip + .LCPI2_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm2, xmm7 + por xmm2, xmm6 + por xmm2, xmm5 + pinsrb xmm3, byte ptr [r14 + rdi + 22], 3 + pinsrb xmm3, byte ptr [r14 + rbx + 22], 4 + pinsrb xmm3, byte ptr [r14 + r13 + 22], 5 + pinsrb xmm3, byte ptr [r14 + rcx + 22], 6 + pinsrb xmm3, byte ptr [r14 + r8 + 22], 7 + pinsrb xmm3, byte ptr [r14 + r9 + 22], 8 + pinsrb xmm3, byte ptr [r14 + r10 + 22], 9 + pinsrb xmm3, byte ptr [r14 + rax + 22], 10 + pinsrb xmm3, byte ptr [r14 + r15 + 22], 11 + pinsrb xmm3, byte ptr [r14 + r12 + 22], 12 + pinsrb xmm3, byte ptr [r14 + rdx + 22], 13 + pinsrb xmm3, byte ptr [r14 + rsi + 22], 14 + pinsrb xmm3, byte ptr [r14 + r11 + 22], 15 + pinsrb xmm8, byte ptr [r14 + rdi + 23], 3 + pinsrb xmm8, byte ptr [r14 + rbx + 23], 4 + pinsrb xmm8, byte ptr [r14 + r13 + 23], 5 + pinsrb xmm8, byte ptr [r14 + rcx + 23], 6 + pinsrb xmm8, byte ptr [r14 + r8 + 23], 7 + pinsrb xmm8, byte ptr [r14 + r9 + 23], 8 + pinsrb xmm8, byte ptr [r14 + r10 + 23], 9 + pinsrb xmm8, byte ptr [r14 + rax + 23], 10 + pinsrb xmm8, byte ptr [r14 + r15 + 23], 11 + pinsrb xmm8, byte ptr [r14 + r12 + 23], 12 + pinsrb xmm8, byte ptr [r14 + rdx + 23], 13 + pinsrb xmm8, byte ptr [r14 + rsi + 23], 14 + pinsrb xmm8, byte ptr [r14 + r11 + 23], 15 + pcmpeqb xmm3, xmm15 + movdqa xmm5, xmmword ptr [rip + .LCPI2_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm5 + pcmpeqb xmm8, xmm15 + psllw xmm8, 7 + movdqa xmm6, xmmword ptr [rip + .LCPI2_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm8, xmm6 + por xmm8, xmm3 + pinsrb xmm1, byte ptr [r14 + rdi + 25], 3 + pinsrb xmm1, byte ptr [r14 + rbx + 25], 4 + pinsrb xmm1, byte ptr [r14 + r13 + 25], 5 + pinsrb xmm1, byte ptr [r14 + rcx + 25], 6 + pinsrb xmm1, byte ptr [r14 + r8 + 25], 7 + pinsrb xmm1, byte ptr [r14 + r9 + 25], 8 + pinsrb xmm1, byte ptr [r14 + r10 + 25], 9 + pinsrb xmm1, byte ptr [r14 + rax + 25], 10 + pinsrb xmm1, byte ptr [r14 + r15 + 25], 11 + pinsrb xmm1, byte ptr [r14 + r12 + 25], 12 + pinsrb xmm1, byte ptr [r14 + rdx + 25], 13 + pinsrb xmm1, byte ptr [r14 + rsi + 25], 14 + pinsrb xmm1, byte ptr [r14 + r11 + 25], 15 + por xmm8, xmm2 + pcmpeqb xmm1, xmm15 + movdqa xmm2, xmm1 + movdqa xmm3, xmmword ptr [rip + .LCPI2_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm2, xmm3 + psubb xmm2, xmm1 + pinsrb xmm10, byte ptr [r14 + rdi + 24], 3 + pinsrb xmm10, byte ptr [r14 + rbx + 24], 4 + pinsrb xmm10, byte ptr [r14 + r13 + 24], 5 + pinsrb xmm10, byte ptr [r14 + rcx + 24], 6 + pinsrb xmm10, byte ptr [r14 + r8 + 24], 7 + pinsrb xmm10, byte ptr [r14 + r9 + 24], 8 + pinsrb xmm10, byte ptr [r14 + r10 + 24], 9 + pinsrb xmm10, byte ptr [r14 + rax + 24], 10 + pinsrb xmm10, byte ptr [r14 + r15 + 24], 11 + pinsrb xmm10, byte ptr [r14 + r12 + 24], 12 + pinsrb xmm10, byte ptr [r14 + rdx + 24], 13 + pinsrb xmm10, byte ptr [r14 + rsi + 24], 14 + pinsrb xmm10, byte ptr [r14 + r11 + 24], 15 + pcmpeqb xmm10, xmm15 + pand xmm10, xmm3 + pinsrb xmm11, byte ptr [r14 + rdi + 26], 3 + pinsrb xmm11, byte ptr [r14 + rbx + 26], 4 + pinsrb xmm11, byte ptr [r14 + r13 + 26], 5 + pinsrb xmm11, byte ptr [r14 + rcx + 26], 6 + pinsrb xmm11, byte ptr [r14 + r8 + 26], 7 + pinsrb xmm11, byte ptr [r14 + r9 + 26], 8 + pinsrb xmm11, byte ptr [r14 + r10 + 26], 9 + pinsrb xmm11, byte ptr [r14 + rax + 26], 10 + pinsrb xmm11, byte ptr [r14 + r15 + 26], 11 + pinsrb xmm11, byte ptr [r14 + r12 + 26], 12 + pinsrb xmm11, byte ptr [r14 + rdx + 26], 13 + pinsrb xmm11, byte ptr [r14 + rsi + 26], 14 + pinsrb xmm11, byte ptr [r14 + r11 + 26], 15 + pcmpeqb xmm11, xmm15 + pand xmm11, xmmword ptr [rip + .LCPI2_11] + por xmm11, xmm10 + por xmm11, xmm2 + pinsrb xmm9, byte ptr [r14 + rdi + 27], 3 + pinsrb xmm9, byte ptr [r14 + rbx + 27], 4 + pinsrb xmm9, byte ptr [r14 + r13 + 27], 5 + pinsrb xmm9, byte ptr [r14 + rcx + 27], 6 + pinsrb xmm9, byte ptr [r14 + r8 + 27], 7 + pinsrb xmm9, byte ptr [r14 + r9 + 27], 8 + pinsrb xmm9, byte ptr [r14 + r10 + 27], 9 + pinsrb xmm9, byte ptr [r14 + rax + 27], 10 + pinsrb xmm9, byte ptr [r14 + r15 + 27], 11 + pinsrb xmm9, byte ptr [r14 + r12 + 27], 12 + pinsrb xmm9, byte ptr [r14 + rdx + 27], 13 + pinsrb xmm9, byte ptr [r14 + rsi + 27], 14 + pinsrb xmm9, byte ptr [r14 + r11 + 27], 15 + pinsrb xmm4, byte ptr [r14 + rdi + 28], 3 + pinsrb xmm4, byte ptr [r14 + rbx + 28], 4 + pinsrb xmm4, byte ptr [r14 + r13 + 28], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 28], 6 + pinsrb xmm4, byte ptr [r14 + r8 + 28], 7 + pinsrb xmm4, byte ptr [r14 + r9 + 28], 8 + pinsrb xmm4, byte ptr [r14 + r10 + 28], 9 + pinsrb xmm4, byte ptr [r14 + rax + 28], 10 + pinsrb xmm4, byte ptr [r14 + r15 + 28], 11 + pinsrb xmm4, byte ptr [r14 + r12 + 28], 12 + pinsrb xmm4, byte ptr [r14 + rdx + 28], 13 + pinsrb xmm4, byte ptr [r14 + rsi + 28], 14 + pinsrb xmm4, byte ptr [r14 + r11 + 28], 15 + pinsrb xmm13, byte ptr [r14 + rdi + 29], 3 + pinsrb xmm13, byte ptr [r14 + rbx + 29], 4 + pinsrb xmm13, byte ptr [r14 + r13 + 29], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 29], 6 + pinsrb xmm13, byte ptr [r14 + r8 + 29], 7 + pinsrb xmm13, byte ptr [r14 + r9 + 29], 8 + pinsrb xmm13, byte ptr [r14 + r10 + 29], 9 + pinsrb xmm13, byte ptr [r14 + rax + 29], 10 + pinsrb xmm13, byte ptr [r14 + r15 + 29], 11 + pinsrb xmm13, byte ptr [r14 + r12 + 29], 12 + pinsrb xmm13, byte ptr [r14 + rdx + 29], 13 + pinsrb xmm13, byte ptr [r14 + rsi + 29], 14 + movdqa xmm1, xmm15 + pcmpeqb xmm9, xmm15 + pand xmm9, xmmword ptr [rip + .LCPI2_12] + pcmpeqb xmm4, xmm15 + pand xmm4, xmmword ptr [rip + .LCPI2_13] + por xmm4, xmm9 + pinsrb xmm13, byte ptr [r14 + r11 + 29], 15 + pcmpeqb xmm13, xmm15 + pand xmm13, xmm7 + por xmm13, xmm4 + pinsrb xmm12, byte ptr [r14 + rdi + 30], 3 + pinsrb xmm0, byte ptr [r14 + rdi + 31], 3 + pinsrb xmm12, byte ptr [r14 + rbx + 30], 4 + pinsrb xmm0, byte ptr [r14 + rbx + 31], 4 + pinsrb xmm12, byte ptr [r14 + r13 + 30], 5 + pinsrb xmm0, byte ptr [r14 + r13 + 31], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 30], 6 + pinsrb xmm0, byte ptr [r14 + rcx + 31], 6 + pinsrb xmm12, byte ptr [r14 + r8 + 30], 7 + pinsrb xmm0, byte ptr [r14 + r8 + 31], 7 + pinsrb xmm12, byte ptr [r14 + r9 + 30], 8 + pinsrb xmm0, byte ptr [r14 + r9 + 31], 8 + pinsrb xmm12, byte ptr [r14 + r10 + 30], 9 + pinsrb xmm0, byte ptr [r14 + r10 + 31], 9 + pinsrb xmm12, byte ptr [r14 + rax + 30], 10 + pinsrb xmm0, byte ptr [r14 + rax + 31], 10 + pinsrb xmm12, byte ptr [r14 + r15 + 30], 11 + pinsrb xmm0, byte ptr [r14 + r15 + 31], 11 + pinsrb xmm12, byte ptr [r14 + r12 + 30], 12 + pinsrb xmm0, byte ptr [r14 + r12 + 31], 12 + pinsrb xmm12, byte ptr [r14 + rdx + 30], 13 + pinsrb xmm0, byte ptr [r14 + rdx + 31], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rsi + 30], 14 + pinsrb xmm0, byte ptr [r14 + rsi + 31], 14 + pinsrb xmm12, byte ptr [r14 + r11 + 30], 15 + pinsrb xmm0, byte ptr [r14 + r11 + 31], 15 + por xmm13, xmm11 + pcmpeqb xmm12, xmm15 + pand xmm12, xmm5 + pcmpeqb xmm0, xmm15 + psllw xmm0, 7 + pand xmm0, xmm6 + por xmm0, xmm12 + por xmm0, xmm13 + movdqa xmm1, xmm8 + punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload + movdqa xmm2, xmm4 + punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] + movdqa xmm3, xmm2 + punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] + punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] + punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] + punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] + movdqa xmm0, xmm4 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx + 48], xmm4 + movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 + movdqu xmmword ptr [rax + 4*rcx], xmm3 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 216] # 8-byte Folded Reload + jne .LBB2_215 +# %bb.216: + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + cmp rcx, qword ptr [rsp + 216] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r11b, byte ptr [rsp] # 1-byte Reload + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + jne .LBB2_154 + jmp .LBB2_158 +.LBB2_217: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, r14 + mov qword ptr [rsp + 288], rax # 8-byte Spill + mov qword ptr [rsp + 216], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 96], rax # 8-byte Spill + movzx eax, r11b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 128], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB3_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx] - movsd xmm0, qword ptr [rsi + 8] # xmm0 = mem[0],zero - setp al - setne cl - or cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 8] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 16] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 16] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 24] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 24] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 32] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 32] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 40] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 40] - setp al - setne dil - or dil, al - movsd xmm0, qword ptr [rsi + 48] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 48] - setp al - setne r13b - or r13b, al - movsd xmm0, qword ptr [rsi + 56] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 56] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 64] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 72] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 72] - setp al - setne bl - or bl, al - movsd xmm0, qword ptr [rsi + 80] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 80] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 88] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 88] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 96] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 96] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 104] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 104] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 112] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 112] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 120] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 120] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 128] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 128] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 136] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 136] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 144] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 144] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 152] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 152] - setp al - setne r14b - or r14b, al - movsd xmm0, qword ptr [rsi + 160] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 160] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 168] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 168] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 176] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 176] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 184] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 184] - setp al - setne r15b - or r15b, al - movsd xmm0, qword ptr [rsi + 192] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 192] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 200] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 200] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 208] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 208] - setp al - setne r11b - or r11b, al - movsd xmm0, qword ptr [rsi + 216] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 216] - setp al - setne r10b - or r10b, al - movsd xmm0, qword ptr [rsi + 224] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 224] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 232] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 232] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill - movsd xmm0, qword ptr [rsi + 240] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 240] - setp al - setne r9b - or r9b, al - movsd xmm0, qword ptr [rsi + 248] # xmm0 = mem[0],zero - add rsi, 256 - ucomisd xmm0, qword ptr [rdx + 248] - setp al - setne r8b - or r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload - shl dil, 5 - shl r13b, 6 - or r13b, dil - mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload - shl cl, 2 - or cl, al - mov eax, ebx - add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload - mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload - shl al, 7 - or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload - shl al, 2 - or al, r13b - mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload - shl al, 3 - or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload - shl bl, 3 - or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload - shl r13b, 4 - or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload - shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload - shl al, 6 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - shl r14b, 3 - or r14b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl bl, 4 - or bl, r14b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r14d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r14b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload - shl cl, 6 - or cl, r13b - or al, dil - shl r15b, 7 - or r15b, cl - or r15b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r11b, 2 - or r11b, cl - shl r10b, 3 - or r10b, r11b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl cl, 4 - or cl, r10b - mov byte ptr [r12], r14b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl bl, 5 - shl r9b, 6 - or r9b, bl - mov byte ptr [r12 + 1], al - shl r8b, 7 - or r8b, r9b - or r8b, cl - mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], r8b - add rdx, 256 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB3_52 -# %bb.53: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB3_54: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.55: - sub r14, r15 - xor ecx, ecx - .p2align 4, 0x90 -.LBB3_56: # =>This Inner Loop Header: Depth=1 - lea r9, [rcx + 1] - movsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero - ucomisd xmm0, qword ptr [rdx + 8*rcx] - setp bl - setne al - or al, bl - neg al - mov rdi, rcx - shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor al, r8b - and cl, 7 - mov bl, 1 - # kill: def $cl killed $cl killed $rcx - shl bl, cl - and bl, al - xor bl, r8b - mov byte ptr [r12 + rdi], bl +.LBB2_218: # =>This Inner Loop Header: Depth=1 + mov rdx, rax + mov qword ptr [rsp + 224], rax # 8-byte Spill + shl rdx, 5 + mov r8, rdx + mov rax, rdx + mov r10, rdx + mov r13, rdx + mov qword ptr [rsp + 56], rdx # 8-byte Spill + mov r11, rdx + mov rbx, rdx + mov r15, rdx + mov rdi, rdx + mov r9, rdx + mov rsi, rdx + movzx ecx, byte ptr [r14 + rdx] + movd xmm15, ecx + movzx ecx, byte ptr [r14 + rdx + 1] + movd xmm5, ecx + movzx ecx, byte ptr [r14 + rdx + 2] + movd xmm6, ecx + movzx ecx, byte ptr [r14 + rdx + 3] + movd xmm2, ecx + movzx ecx, byte ptr [r14 + rdx + 4] + movd xmm1, ecx + movzx ecx, byte ptr [r14 + rdx + 5] + movd xmm8, ecx + movzx ecx, byte ptr [r14 + rdx + 6] + movd xmm3, ecx + movzx ecx, byte ptr [r14 + rdx + 7] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rdx + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rdx + 9] + movd xmm10, ecx + movzx ecx, byte ptr [r14 + rdx + 10] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rdx + 11] + movd xmm11, ecx + movzx ecx, byte ptr [r14 + rdx + 12] + movd xmm13, ecx + movzx ecx, byte ptr [r14 + rdx + 13] + movd xmm12, ecx + movzx ecx, byte ptr [r14 + rdx + 14] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 256], xmm0 # 16-byte Spill + mov r12, rdx + or r12, 32 + mov qword ptr [rsp + 32], r12 # 8-byte Spill + or r8, 64 + or rax, 96 + or r10, 128 + or r13, 160 + mov qword ptr [rsp + 80], r13 # 8-byte Spill + mov r13, qword ptr [rsp + 56] # 8-byte Reload + or r13, 192 + or r11, 224 + mov qword ptr [rsp + 88], r11 # 8-byte Spill + or rbx, 256 + or r15, 288 + or rdi, 320 + mov qword ptr [rsp + 48], rdi # 8-byte Spill + or r9, 352 + or rsi, 384 + mov rcx, rdx + or rcx, 416 + mov qword ptr [rsp + 8], rcx # 8-byte Spill + mov rcx, rdx + mov qword ptr [rsp + 24], rdx # 8-byte Spill + or rcx, 448 + mov qword ptr [rsp + 16], rcx # 8-byte Spill + mov rcx, rdx + or rcx, 480 + mov qword ptr [rsp + 40], rcx # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r12], 1 + pinsrb xmm15, byte ptr [r14 + r8], 2 + mov rdx, rax + pinsrb xmm15, byte ptr [r14 + rax], 3 + pinsrb xmm15, byte ptr [r14 + r10], 4 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r12], 5 + mov qword ptr [rsp + 56], r13 # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r13], 6 + pinsrb xmm15, byte ptr [r14 + r11], 7 + pinsrb xmm15, byte ptr [r14 + rbx], 8 + pinsrb xmm15, byte ptr [r14 + r15], 9 + pinsrb xmm15, byte ptr [r14 + rdi], 10 + pinsrb xmm15, byte ptr [r14 + r9], 11 + pinsrb xmm15, byte ptr [r14 + rsi], 12 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 14 + pinsrb xmm15, byte ptr [r14 + rcx], 15 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r13 + 1], 1 + pinsrb xmm5, byte ptr [r14 + r8 + 1], 2 + mov r13, r8 + pinsrb xmm5, byte ptr [r14 + rdx + 1], 3 + pinsrb xmm5, byte ptr [r14 + r10 + 1], 4 + pinsrb xmm5, byte ptr [r14 + r12 + 1], 5 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r8 + 1], 6 + pinsrb xmm5, byte ptr [r14 + r11 + 1], 7 + pinsrb xmm5, byte ptr [r14 + rbx + 1], 8 + mov r11, rbx + pinsrb xmm5, byte ptr [r14 + r15 + 1], 9 + mov rbx, r15 + pinsrb xmm5, byte ptr [r14 + rdi + 1], 10 + pinsrb xmm5, byte ptr [r14 + r9 + 1], 11 + mov r15, r9 + pinsrb xmm5, byte ptr [r14 + rsi + 1], 12 + mov r9, rsi + mov qword ptr [rsp + 120], rsi # 8-byte Spill + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 14 + pinsrb xmm5, byte ptr [r14 + rcx + 1], 15 + movdqa xmm9, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm5, xmm9 + movdqa xmm7, xmm5 + movdqa xmm4, xmmword ptr [rip + .LCPI2_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm7, xmm4 + psubb xmm7, xmm5 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 15] + movd xmm14, esi + pcmpeqb xmm15, xmm9 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rcx + 2], 1 + mov qword ptr [rsp + 64], r13 # 8-byte Spill + pinsrb xmm6, byte ptr [r14 + r13 + 2], 2 + pinsrb xmm6, byte ptr [r14 + rdx + 2], 3 + mov rdi, r10 + mov qword ptr [rsp + 72], r10 # 8-byte Spill + pinsrb xmm6, byte ptr [r14 + r10 + 2], 4 + pinsrb xmm6, byte ptr [r14 + r12 + 2], 5 + pinsrb xmm6, byte ptr [r14 + r8 + 2], 6 + mov r10, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r10 + 2], 7 + mov qword ptr [rsp + 144], r11 # 8-byte Spill + pinsrb xmm6, byte ptr [r14 + r11 + 2], 8 + mov qword ptr [rsp + 112], rbx # 8-byte Spill + pinsrb xmm6, byte ptr [r14 + rbx + 2], 9 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r8 + 2], 10 + pinsrb xmm6, byte ptr [r14 + r15 + 2], 11 + pinsrb xmm6, byte ptr [r14 + r9 + 2], 12 + mov r9, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r9 + 2], 13 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 14 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 15 + pand xmm15, xmm4 + pcmpeqb xmm6, xmm9 + movdqa xmm0, xmmword ptr [rip + .LCPI2_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm6, xmm0 + por xmm6, xmm15 + movzx esi, byte ptr [r14 + rax + 16] + movd xmm15, esi + pinsrb xmm2, byte ptr [r14 + rcx + 3], 1 + pinsrb xmm2, byte ptr [r14 + r13 + 3], 2 + mov rax, rdx + pinsrb xmm2, byte ptr [r14 + rdx + 3], 3 + pinsrb xmm2, byte ptr [r14 + rdi + 3], 4 + mov rdx, r12 + pinsrb xmm2, byte ptr [r14 + r12 + 3], 5 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rcx + 3], 6 + pinsrb xmm2, byte ptr [r14 + r10 + 3], 7 + pinsrb xmm2, byte ptr [r14 + r11 + 3], 8 + pinsrb xmm2, byte ptr [r14 + rbx + 3], 9 + pinsrb xmm2, byte ptr [r14 + r8 + 3], 10 + pinsrb xmm2, byte ptr [r14 + r15 + 3], 11 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r12 + 3], 12 + pinsrb xmm2, byte ptr [r14 + r9 + 3], 13 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rsi + 3], 14 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdi + 3], 15 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + r13 + 4], 1 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + r13 + 4], 2 + pinsrb xmm1, byte ptr [r14 + rax + 4], 3 + mov rdi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rdi + 4], 4 + pinsrb xmm1, byte ptr [r14 + rdx + 4], 5 + pinsrb xmm1, byte ptr [r14 + rcx + 4], 6 + pinsrb xmm1, byte ptr [r14 + r10 + 4], 7 + pinsrb xmm1, byte ptr [r14 + r11 + 4], 8 + pinsrb xmm1, byte ptr [r14 + rbx + 4], 9 + pinsrb xmm1, byte ptr [r14 + r8 + 4], 10 + pinsrb xmm1, byte ptr [r14 + r15 + 4], 11 + mov qword ptr [rsp + 104], r15 # 8-byte Spill + pinsrb xmm1, byte ptr [r14 + r12 + 4], 12 + pinsrb xmm1, byte ptr [r14 + r9 + 4], 13 + pinsrb xmm1, byte ptr [r14 + rsi + 4], 14 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + r8 + 4], 15 + por xmm6, xmm7 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + movzx esi, byte ptr [r14 + rdi + 17] + movd xmm0, esi + pcmpeqb xmm2, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI2_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm2, xmm5 + pcmpeqb xmm1, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI2_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm1, xmm5 + por xmm1, xmm2 + movzx esi, byte ptr [r14 + rdi + 18] + movd xmm5, esi + mov r10, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r10 + 5], 1 + pinsrb xmm8, byte ptr [r14 + r13 + 5], 2 + mov qword ptr [rsp + 136], rax # 8-byte Spill + pinsrb xmm8, byte ptr [r14 + rax + 5], 3 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rdx + 5], 4 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rcx + 5], 5 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r9 + 5], 6 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r11 + 5], 7 + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rbx + 5], 8 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r12 + 5], 9 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 10 + pinsrb xmm8, byte ptr [r14 + r15 + 5], 11 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 12 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 13 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r15 + 5], 14 + pinsrb xmm8, byte ptr [r14 + r8 + 5], 15 + pcmpeqb xmm8, xmm9 + movdqa xmm2, xmmword ptr [rip + .LCPI2_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm8, xmm2 + por xmm8, xmm1 + movzx esi, byte ptr [r14 + rdi + 19] + movd xmm7, esi + por xmm8, xmm6 + movzx esi, byte ptr [r14 + rdi + 20] + movd xmm6, esi + mov r8, r10 + pinsrb xmm3, byte ptr [r14 + r10 + 6], 1 + pinsrb xmm3, byte ptr [r14 + r13 + 6], 2 + pinsrb xmm3, byte ptr [r14 + rax + 6], 3 + mov r10, rdx + pinsrb xmm3, byte ptr [r14 + rdx + 6], 4 + pinsrb xmm3, byte ptr [r14 + rcx + 6], 5 mov rcx, r9 - cmp r14, r9 - jne .LBB3_56 - jmp .LBB3_123 -.LBB3_2: - cmp edi, 2 - je .LBB3_57 -# %bb.3: + pinsrb xmm3, byte ptr [r14 + r9 + 6], 6 + mov r9, r11 + pinsrb xmm3, byte ptr [r14 + r11 + 6], 7 + pinsrb xmm3, byte ptr [r14 + rbx + 6], 8 + pinsrb xmm3, byte ptr [r14 + r12 + 6], 9 + mov r11, r12 + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdi + 6], 10 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdx + 6], 11 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r12 + 6], 12 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rsi + 6], 13 + pinsrb xmm3, byte ptr [r14 + r15 + 6], 14 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rax + 6], 15 + movdqa xmm2, xmmword ptr [rsp + 192] # 16-byte Reload + pinsrb xmm2, byte ptr [r14 + r8 + 7], 1 + mov r15, r8 + pinsrb xmm2, byte ptr [r14 + r13 + 7], 2 + mov r8, r13 + mov rdx, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdx + 7], 3 + pinsrb xmm2, byte ptr [r14 + r10 + 7], 4 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdx + 7], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 7], 6 + mov r10, rcx + pinsrb xmm2, byte ptr [r14 + r9 + 7], 7 + pinsrb xmm2, byte ptr [r14 + rbx + 7], 8 + pinsrb xmm2, byte ptr [r14 + r11 + 7], 9 + pinsrb xmm2, byte ptr [r14 + rdi + 7], 10 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rcx + 7], 11 + pinsrb xmm2, byte ptr [r14 + r12 + 7], 12 + pinsrb xmm2, byte ptr [r14 + rsi + 7], 13 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdi + 7], 14 + pinsrb xmm2, byte ptr [r14 + rax + 7], 15 + pcmpeqb xmm3, xmm9 + movdqa xmm1, xmmword ptr [rip + .LCPI2_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm1 + pcmpeqb xmm2, xmm9 + psllw xmm2, 7 + movdqa xmm1, xmmword ptr [rip + .LCPI2_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm2, xmm1 + por xmm2, xmm3 + movdqa xmm1, xmm2 + mov r9, qword ptr [rsp + 24] # 8-byte Reload + movzx esi, byte ptr [r14 + r9 + 21] + movd xmm2, esi + pinsrb xmm10, byte ptr [r14 + r15 + 9], 1 + pinsrb xmm10, byte ptr [r14 + r13 + 9], 2 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rax + 9], 3 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r13 + 9], 4 + pinsrb xmm10, byte ptr [r14 + rdx + 9], 5 + pinsrb xmm10, byte ptr [r14 + r10 + 9], 6 + mov r11, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r11 + 9], 7 + pinsrb xmm10, byte ptr [r14 + rbx + 9], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rsi + 9], 9 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rsi + 9], 10 + pinsrb xmm10, byte ptr [r14 + rcx + 9], 11 + pinsrb xmm10, byte ptr [r14 + r12 + 9], 12 + mov rcx, r12 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdx + 9], 13 + pinsrb xmm10, byte ptr [r14 + rdi + 9], 14 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r10 + 9], 15 + por xmm1, xmm8 + movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill + pcmpeqb xmm10, xmm9 + movdqa xmm1, xmm10 + movdqa xmm8, xmm4 + pand xmm1, xmm4 + psubb xmm1, xmm10 + movzx esi, byte ptr [r14 + r9 + 22] + movd xmm3, esi + movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload + mov r9, r15 + pinsrb xmm4, byte ptr [r14 + r15 + 8], 1 + pinsrb xmm4, byte ptr [r14 + r8 + 8], 2 + pinsrb xmm4, byte ptr [r14 + rax + 8], 3 + mov r12, rax + pinsrb xmm4, byte ptr [r14 + r13 + 8], 4 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r15 + 8], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 8], 6 + mov r8, r11 + pinsrb xmm4, byte ptr [r14 + r11 + 8], 7 + mov rdi, rbx + pinsrb xmm4, byte ptr [r14 + rbx + 8], 8 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rbx + 8], 9 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rsi + 8], 10 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r11 + 8], 11 + pinsrb xmm4, byte ptr [r14 + rcx + 8], 12 + pinsrb xmm4, byte ptr [r14 + rdx + 8], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 8], 14 + pinsrb xmm4, byte ptr [r14 + r10 + 8], 15 + pcmpeqb xmm4, xmm9 + pand xmm4, xmm8 + movdqa xmm10, xmmword ptr [rsp + 160] # 16-byte Reload + pinsrb xmm10, byte ptr [r14 + r9 + 10], 1 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r9 + 10], 2 + pinsrb xmm10, byte ptr [r14 + r12 + 10], 3 + pinsrb xmm10, byte ptr [r14 + r13 + 10], 4 + mov rdx, r15 + pinsrb xmm10, byte ptr [r14 + r15 + 10], 5 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r15 + 10], 6 + pinsrb xmm10, byte ptr [r14 + r8 + 10], 7 + mov r10, r8 + pinsrb xmm10, byte ptr [r14 + rdi + 10], 8 + pinsrb xmm10, byte ptr [r14 + rbx + 10], 9 + pinsrb xmm10, byte ptr [r14 + rsi + 10], 10 + mov rdi, rsi + pinsrb xmm10, byte ptr [r14 + r11 + 10], 11 + pinsrb xmm10, byte ptr [r14 + rcx + 10], 12 + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rsi + 10], 13 + pinsrb xmm10, byte ptr [r14 + rax + 10], 14 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r11 + 10], 15 + pcmpeqb xmm10, xmm9 + pand xmm10, xmmword ptr [rip + .LCPI2_11] + por xmm10, xmm4 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 23] + movd xmm8, esi + por xmm10, xmm1 + movdqa xmmword ptr [rsp + 160], xmm10 # 16-byte Spill + movzx esi, byte ptr [r14 + rax + 24] + movd xmm10, esi + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r8 + 11], 1 + mov rbx, r9 + pinsrb xmm11, byte ptr [r14 + r9 + 11], 2 + mov rsi, r12 + pinsrb xmm11, byte ptr [r14 + r12 + 11], 3 + pinsrb xmm11, byte ptr [r14 + r13 + 11], 4 + pinsrb xmm11, byte ptr [r14 + rdx + 11], 5 + mov rcx, r15 + pinsrb xmm11, byte ptr [r14 + r15 + 11], 6 + pinsrb xmm11, byte ptr [r14 + r10 + 11], 7 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r10 + 11], 8 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r13 + 11], 9 + pinsrb xmm11, byte ptr [r14 + rdi + 11], 10 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r15 + 11], 11 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r12 + 11], 12 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rax + 11], 13 + mov r9, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r9 + 11], 14 + pinsrb xmm11, byte ptr [r14 + r11 + 11], 15 + pinsrb xmm13, byte ptr [r14 + r8 + 12], 1 + pinsrb xmm13, byte ptr [r14 + rbx + 12], 2 + pinsrb xmm13, byte ptr [r14 + rsi + 12], 3 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rbx + 12], 4 + pinsrb xmm13, byte ptr [r14 + rdx + 12], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 12], 6 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rbx + 12], 7 + pinsrb xmm13, byte ptr [r14 + r10 + 12], 8 + mov rbx, r13 + pinsrb xmm13, byte ptr [r14 + r13 + 12], 9 + pinsrb xmm13, byte ptr [r14 + rdi + 12], 10 + pinsrb xmm13, byte ptr [r14 + r15 + 12], 11 + pinsrb xmm13, byte ptr [r14 + r12 + 12], 12 + pinsrb xmm13, byte ptr [r14 + rax + 12], 13 + pinsrb xmm13, byte ptr [r14 + r9 + 12], 14 + pinsrb xmm13, byte ptr [r14 + r11 + 12], 15 + pinsrb xmm12, byte ptr [r14 + r8 + 13], 1 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + r13 + 13], 2 + pinsrb xmm12, byte ptr [r14 + rsi + 13], 3 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rsi + 13], 4 + pinsrb xmm12, byte ptr [r14 + rdx + 13], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 13], 6 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 7 + mov r13, r10 + pinsrb xmm12, byte ptr [r14 + r10 + 13], 8 + pinsrb xmm12, byte ptr [r14 + rbx + 13], 9 + pinsrb xmm12, byte ptr [r14 + rdi + 13], 10 + pinsrb xmm12, byte ptr [r14 + r15 + 13], 11 + pinsrb xmm12, byte ptr [r14 + r12 + 13], 12 + pinsrb xmm12, byte ptr [r14 + rax + 13], 13 + pinsrb xmm12, byte ptr [r14 + r9 + 13], 14 + pinsrb xmm12, byte ptr [r14 + r11 + 13], 15 + pcmpeqb xmm11, xmm9 + pand xmm11, xmmword ptr [rip + .LCPI2_12] + pcmpeqb xmm13, xmm9 + pand xmm13, xmmword ptr [rip + .LCPI2_13] + por xmm13, xmm11 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + movzx esi, byte ptr [r14 + rax + 25] + movd xmm1, esi + pcmpeqb xmm12, xmm9 + pand xmm12, xmmword ptr [rip + .LCPI2_14] + por xmm12, xmm13 + movzx esi, byte ptr [r14 + rax + 26] + movd xmm11, esi + movdqa xmm4, xmmword ptr [rsp + 256] # 16-byte Reload + pinsrb xmm4, byte ptr [r14 + r8 + 14], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rsi + 14], 2 + mov rdi, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdi + 14], 3 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r10 + 14], 4 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 14], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 14], 6 + mov r8, rdx + pinsrb xmm4, byte ptr [r14 + rdx + 14], 7 + mov r9, r13 + pinsrb xmm4, byte ptr [r14 + r13 + 14], 8 + mov r11, rbx + pinsrb xmm4, byte ptr [r14 + rbx + 14], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rbx + 14], 10 + pinsrb xmm4, byte ptr [r14 + r15 + 14], 11 + pinsrb xmm4, byte ptr [r14 + r12 + 14], 12 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 14], 13 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 14], 14 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r13 + 14], 15 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 1 + pinsrb xmm14, byte ptr [r14 + rsi + 15], 2 + pinsrb xmm14, byte ptr [r14 + rdi + 15], 3 + pinsrb xmm14, byte ptr [r14 + r10 + 15], 4 + pinsrb xmm14, byte ptr [r14 + rax + 15], 5 + pinsrb xmm14, byte ptr [r14 + rcx + 15], 6 + pinsrb xmm14, byte ptr [r14 + r8 + 15], 7 + pinsrb xmm14, byte ptr [r14 + r9 + 15], 8 + pinsrb xmm14, byte ptr [r14 + r11 + 15], 9 + pinsrb xmm14, byte ptr [r14 + rbx + 15], 10 + pinsrb xmm14, byte ptr [r14 + r15 + 15], 11 + pinsrb xmm14, byte ptr [r14 + r12 + 15], 12 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 13 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 15], 14 + pinsrb xmm14, byte ptr [r14 + r13 + 15], 15 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r13 + 16], 1 + pinsrb xmm15, byte ptr [r14 + rsi + 16], 2 + pinsrb xmm15, byte ptr [r14 + rdi + 16], 3 + pinsrb xmm15, byte ptr [r14 + r10 + 16], 4 + pinsrb xmm15, byte ptr [r14 + rax + 16], 5 + pinsrb xmm15, byte ptr [r14 + rcx + 16], 6 + pinsrb xmm15, byte ptr [r14 + r8 + 16], 7 + pinsrb xmm15, byte ptr [r14 + r9 + 16], 8 + pinsrb xmm15, byte ptr [r14 + r11 + 16], 9 + pinsrb xmm15, byte ptr [r14 + rbx + 16], 10 + pinsrb xmm15, byte ptr [r14 + r15 + 16], 11 + pinsrb xmm15, byte ptr [r14 + r12 + 16], 12 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rdx + 16], 13 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rdx + 16], 14 + pinsrb xmm0, byte ptr [r14 + r13 + 17], 1 + pinsrb xmm0, byte ptr [r14 + rsi + 17], 2 + pinsrb xmm0, byte ptr [r14 + rdi + 17], 3 + pinsrb xmm0, byte ptr [r14 + r10 + 17], 4 + pinsrb xmm0, byte ptr [r14 + rax + 17], 5 + mov r13, rax + pinsrb xmm0, byte ptr [r14 + rcx + 17], 6 + pinsrb xmm0, byte ptr [r14 + r8 + 17], 7 + pinsrb xmm0, byte ptr [r14 + r9 + 17], 8 + pinsrb xmm0, byte ptr [r14 + r11 + 17], 9 + pinsrb xmm0, byte ptr [r14 + rbx + 17], 10 + pinsrb xmm0, byte ptr [r14 + r15 + 17], 11 + pinsrb xmm0, byte ptr [r14 + r12 + 17], 12 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 17], 13 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rsi + 17], 14 + por xmm12, xmmword ptr [rsp + 160] # 16-byte Folded Reload + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + movzx esi, byte ptr [r14 + rbx + 27] + movd xmm9, esi + movdqa xmm13, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm4, xmm13 + pand xmm4, xmmword ptr [rip + .LCPI2_15] + pcmpeqb xmm14, xmm13 + psllw xmm14, 7 + pand xmm14, xmmword ptr [rip + .LCPI2_6] + por xmm14, xmm4 + movzx esi, byte ptr [r14 + rbx + 28] + movd xmm4, esi + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 17], 15 + por xmm14, xmm12 + pcmpeqb xmm0, xmm13 + movdqa xmm13, xmm0 + movdqa xmm12, xmmword ptr [rip + .LCPI2_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm13, xmm12 + psubb xmm13, xmm0 + movdqa xmmword ptr [rsp + 160], xmm13 # 16-byte Spill + movzx esi, byte ptr [r14 + rbx + 29] + movd xmm13, esi + mov rbx, rax + pinsrb xmm15, byte ptr [r14 + rax + 16], 15 + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm15, xmm0 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rsi + 18], 1 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rsi + 18], 2 + pinsrb xmm5, byte ptr [r14 + rdi + 18], 3 + pinsrb xmm5, byte ptr [r14 + r10 + 18], 4 + pinsrb xmm5, byte ptr [r14 + r13 + 18], 5 + pinsrb xmm5, byte ptr [r14 + rcx + 18], 6 + pinsrb xmm5, byte ptr [r14 + r8 + 18], 7 + pinsrb xmm5, byte ptr [r14 + r9 + 18], 8 + pinsrb xmm5, byte ptr [r14 + r11 + 18], 9 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 18], 10 + pinsrb xmm5, byte ptr [r14 + r15 + 18], 11 + pinsrb xmm5, byte ptr [r14 + r12 + 18], 12 + pinsrb xmm5, byte ptr [r14 + rdx + 18], 13 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rdx + 18], 14 + pand xmm15, xmm12 + pinsrb xmm5, byte ptr [r14 + rbx + 18], 15 + pcmpeqb xmm5, xmm0 + pand xmm5, xmmword ptr [rip + .LCPI2_11] + por xmm5, xmm15 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + movzx esi, byte ptr [r14 + rdx + 30] + movd xmm12, esi + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rsi + 19], 1 + pinsrb xmm6, byte ptr [r14 + rsi + 20], 1 + pinsrb xmm2, byte ptr [r14 + rsi + 21], 1 + pinsrb xmm3, byte ptr [r14 + rsi + 22], 1 + pinsrb xmm8, byte ptr [r14 + rsi + 23], 1 + pinsrb xmm10, byte ptr [r14 + rsi + 24], 1 + pinsrb xmm1, byte ptr [r14 + rsi + 25], 1 + pinsrb xmm11, byte ptr [r14 + rsi + 26], 1 + pinsrb xmm9, byte ptr [r14 + rsi + 27], 1 + pinsrb xmm4, byte ptr [r14 + rsi + 28], 1 + pinsrb xmm13, byte ptr [r14 + rsi + 29], 1 + pinsrb xmm12, byte ptr [r14 + rsi + 30], 1 + movzx edx, byte ptr [r14 + rdx + 31] + movd xmm0, edx + pinsrb xmm0, byte ptr [r14 + rsi + 31], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdx + 19], 2 + pinsrb xmm6, byte ptr [r14 + rdx + 20], 2 + pinsrb xmm2, byte ptr [r14 + rdx + 21], 2 + pinsrb xmm3, byte ptr [r14 + rdx + 22], 2 + pinsrb xmm8, byte ptr [r14 + rdx + 23], 2 + pinsrb xmm10, byte ptr [r14 + rdx + 24], 2 + pinsrb xmm1, byte ptr [r14 + rdx + 25], 2 + pinsrb xmm11, byte ptr [r14 + rdx + 26], 2 + pinsrb xmm9, byte ptr [r14 + rdx + 27], 2 + pinsrb xmm4, byte ptr [r14 + rdx + 28], 2 + pinsrb xmm13, byte ptr [r14 + rdx + 29], 2 + pinsrb xmm12, byte ptr [r14 + rdx + 30], 2 + pinsrb xmm0, byte ptr [r14 + rdx + 31], 2 + pinsrb xmm7, byte ptr [r14 + rdi + 19], 3 + pinsrb xmm7, byte ptr [r14 + r10 + 19], 4 + pinsrb xmm7, byte ptr [r14 + r13 + 19], 5 + pinsrb xmm7, byte ptr [r14 + rcx + 19], 6 + pinsrb xmm7, byte ptr [r14 + r8 + 19], 7 + pinsrb xmm7, byte ptr [r14 + r9 + 19], 8 + pinsrb xmm7, byte ptr [r14 + r11 + 19], 9 + pinsrb xmm7, byte ptr [r14 + rax + 19], 10 + pinsrb xmm7, byte ptr [r14 + r15 + 19], 11 + pinsrb xmm7, byte ptr [r14 + r12 + 19], 12 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdx + 19], 13 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rsi + 19], 14 + pinsrb xmm7, byte ptr [r14 + rbx + 19], 15 + pinsrb xmm6, byte ptr [r14 + rdi + 20], 3 + pinsrb xmm6, byte ptr [r14 + r10 + 20], 4 + pinsrb xmm6, byte ptr [r14 + r13 + 20], 5 + pinsrb xmm6, byte ptr [r14 + rcx + 20], 6 + pinsrb xmm6, byte ptr [r14 + r8 + 20], 7 + pinsrb xmm6, byte ptr [r14 + r9 + 20], 8 + pinsrb xmm6, byte ptr [r14 + r11 + 20], 9 + pinsrb xmm6, byte ptr [r14 + rax + 20], 10 + pinsrb xmm6, byte ptr [r14 + r15 + 20], 11 + pinsrb xmm6, byte ptr [r14 + r12 + 20], 12 + pinsrb xmm6, byte ptr [r14 + rdx + 20], 13 + pinsrb xmm6, byte ptr [r14 + rsi + 20], 14 + por xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload + pinsrb xmm6, byte ptr [r14 + rbx + 20], 15 + movdqa xmm15, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm7, xmm15 + pand xmm7, xmmword ptr [rip + .LCPI2_12] + pcmpeqb xmm6, xmm15 + pand xmm6, xmmword ptr [rip + .LCPI2_13] + por xmm6, xmm7 + pinsrb xmm2, byte ptr [r14 + rdi + 21], 3 + pinsrb xmm2, byte ptr [r14 + r10 + 21], 4 + pinsrb xmm2, byte ptr [r14 + r13 + 21], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 21], 6 + pinsrb xmm2, byte ptr [r14 + r8 + 21], 7 + pinsrb xmm2, byte ptr [r14 + r9 + 21], 8 + pinsrb xmm2, byte ptr [r14 + r11 + 21], 9 + pinsrb xmm2, byte ptr [r14 + rax + 21], 10 + pinsrb xmm2, byte ptr [r14 + r15 + 21], 11 + pinsrb xmm2, byte ptr [r14 + r12 + 21], 12 + pinsrb xmm2, byte ptr [r14 + rdx + 21], 13 + pinsrb xmm2, byte ptr [r14 + rsi + 21], 14 + pinsrb xmm2, byte ptr [r14 + rbx + 21], 15 + pcmpeqb xmm2, xmm15 + movdqa xmm7, xmmword ptr [rip + .LCPI2_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm2, xmm7 + por xmm2, xmm6 + por xmm2, xmm5 + pinsrb xmm3, byte ptr [r14 + rdi + 22], 3 + pinsrb xmm3, byte ptr [r14 + r10 + 22], 4 + pinsrb xmm3, byte ptr [r14 + r13 + 22], 5 + pinsrb xmm3, byte ptr [r14 + rcx + 22], 6 + pinsrb xmm3, byte ptr [r14 + r8 + 22], 7 + pinsrb xmm3, byte ptr [r14 + r9 + 22], 8 + pinsrb xmm3, byte ptr [r14 + r11 + 22], 9 + pinsrb xmm3, byte ptr [r14 + rax + 22], 10 + pinsrb xmm3, byte ptr [r14 + r15 + 22], 11 + pinsrb xmm3, byte ptr [r14 + r12 + 22], 12 + pinsrb xmm3, byte ptr [r14 + rdx + 22], 13 + pinsrb xmm3, byte ptr [r14 + rsi + 22], 14 + pinsrb xmm3, byte ptr [r14 + rbx + 22], 15 + pinsrb xmm8, byte ptr [r14 + rdi + 23], 3 + pinsrb xmm8, byte ptr [r14 + r10 + 23], 4 + pinsrb xmm8, byte ptr [r14 + r13 + 23], 5 + pinsrb xmm8, byte ptr [r14 + rcx + 23], 6 + pinsrb xmm8, byte ptr [r14 + r8 + 23], 7 + pinsrb xmm8, byte ptr [r14 + r9 + 23], 8 + pinsrb xmm8, byte ptr [r14 + r11 + 23], 9 + pinsrb xmm8, byte ptr [r14 + rax + 23], 10 + pinsrb xmm8, byte ptr [r14 + r15 + 23], 11 + pinsrb xmm8, byte ptr [r14 + r12 + 23], 12 + pinsrb xmm8, byte ptr [r14 + rdx + 23], 13 + pinsrb xmm8, byte ptr [r14 + rsi + 23], 14 + pinsrb xmm8, byte ptr [r14 + rbx + 23], 15 + pcmpeqb xmm3, xmm15 + movdqa xmm5, xmmword ptr [rip + .LCPI2_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm5 + pcmpeqb xmm8, xmm15 + psllw xmm8, 7 + movdqa xmm6, xmmword ptr [rip + .LCPI2_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm8, xmm6 + por xmm8, xmm3 + pinsrb xmm1, byte ptr [r14 + rdi + 25], 3 + pinsrb xmm1, byte ptr [r14 + r10 + 25], 4 + pinsrb xmm1, byte ptr [r14 + r13 + 25], 5 + pinsrb xmm1, byte ptr [r14 + rcx + 25], 6 + pinsrb xmm1, byte ptr [r14 + r8 + 25], 7 + pinsrb xmm1, byte ptr [r14 + r9 + 25], 8 + pinsrb xmm1, byte ptr [r14 + r11 + 25], 9 + pinsrb xmm1, byte ptr [r14 + rax + 25], 10 + pinsrb xmm1, byte ptr [r14 + r15 + 25], 11 + pinsrb xmm1, byte ptr [r14 + r12 + 25], 12 + pinsrb xmm1, byte ptr [r14 + rdx + 25], 13 + pinsrb xmm1, byte ptr [r14 + rsi + 25], 14 + pinsrb xmm1, byte ptr [r14 + rbx + 25], 15 + por xmm8, xmm2 + pcmpeqb xmm1, xmm15 + movdqa xmm2, xmm1 + movdqa xmm3, xmmword ptr [rip + .LCPI2_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm2, xmm3 + psubb xmm2, xmm1 + pinsrb xmm10, byte ptr [r14 + rdi + 24], 3 + pinsrb xmm10, byte ptr [r14 + r10 + 24], 4 + pinsrb xmm10, byte ptr [r14 + r13 + 24], 5 + pinsrb xmm10, byte ptr [r14 + rcx + 24], 6 + pinsrb xmm10, byte ptr [r14 + r8 + 24], 7 + pinsrb xmm10, byte ptr [r14 + r9 + 24], 8 + pinsrb xmm10, byte ptr [r14 + r11 + 24], 9 + pinsrb xmm10, byte ptr [r14 + rax + 24], 10 + pinsrb xmm10, byte ptr [r14 + r15 + 24], 11 + pinsrb xmm10, byte ptr [r14 + r12 + 24], 12 + pinsrb xmm10, byte ptr [r14 + rdx + 24], 13 + pinsrb xmm10, byte ptr [r14 + rsi + 24], 14 + pinsrb xmm10, byte ptr [r14 + rbx + 24], 15 + pcmpeqb xmm10, xmm15 + pand xmm10, xmm3 + pinsrb xmm11, byte ptr [r14 + rdi + 26], 3 + pinsrb xmm11, byte ptr [r14 + r10 + 26], 4 + pinsrb xmm11, byte ptr [r14 + r13 + 26], 5 + pinsrb xmm11, byte ptr [r14 + rcx + 26], 6 + pinsrb xmm11, byte ptr [r14 + r8 + 26], 7 + pinsrb xmm11, byte ptr [r14 + r9 + 26], 8 + pinsrb xmm11, byte ptr [r14 + r11 + 26], 9 + pinsrb xmm11, byte ptr [r14 + rax + 26], 10 + pinsrb xmm11, byte ptr [r14 + r15 + 26], 11 + pinsrb xmm11, byte ptr [r14 + r12 + 26], 12 + pinsrb xmm11, byte ptr [r14 + rdx + 26], 13 + pinsrb xmm11, byte ptr [r14 + rsi + 26], 14 + pinsrb xmm11, byte ptr [r14 + rbx + 26], 15 + pcmpeqb xmm11, xmm15 + pand xmm11, xmmword ptr [rip + .LCPI2_11] + por xmm11, xmm10 + por xmm11, xmm2 + pinsrb xmm9, byte ptr [r14 + rdi + 27], 3 + pinsrb xmm9, byte ptr [r14 + r10 + 27], 4 + pinsrb xmm9, byte ptr [r14 + r13 + 27], 5 + pinsrb xmm9, byte ptr [r14 + rcx + 27], 6 + pinsrb xmm9, byte ptr [r14 + r8 + 27], 7 + pinsrb xmm9, byte ptr [r14 + r9 + 27], 8 + pinsrb xmm9, byte ptr [r14 + r11 + 27], 9 + pinsrb xmm9, byte ptr [r14 + rax + 27], 10 + pinsrb xmm9, byte ptr [r14 + r15 + 27], 11 + pinsrb xmm9, byte ptr [r14 + r12 + 27], 12 + pinsrb xmm9, byte ptr [r14 + rdx + 27], 13 + pinsrb xmm9, byte ptr [r14 + rsi + 27], 14 + pinsrb xmm9, byte ptr [r14 + rbx + 27], 15 + pinsrb xmm4, byte ptr [r14 + rdi + 28], 3 + pinsrb xmm4, byte ptr [r14 + r10 + 28], 4 + pinsrb xmm4, byte ptr [r14 + r13 + 28], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 28], 6 + pinsrb xmm4, byte ptr [r14 + r8 + 28], 7 + pinsrb xmm4, byte ptr [r14 + r9 + 28], 8 + pinsrb xmm4, byte ptr [r14 + r11 + 28], 9 + pinsrb xmm4, byte ptr [r14 + rax + 28], 10 + pinsrb xmm4, byte ptr [r14 + r15 + 28], 11 + pinsrb xmm4, byte ptr [r14 + r12 + 28], 12 + pinsrb xmm4, byte ptr [r14 + rdx + 28], 13 + pinsrb xmm4, byte ptr [r14 + rsi + 28], 14 + pinsrb xmm4, byte ptr [r14 + rbx + 28], 15 + pinsrb xmm13, byte ptr [r14 + rdi + 29], 3 + pinsrb xmm13, byte ptr [r14 + r10 + 29], 4 + pinsrb xmm13, byte ptr [r14 + r13 + 29], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 29], 6 + pinsrb xmm13, byte ptr [r14 + r8 + 29], 7 + pinsrb xmm13, byte ptr [r14 + r9 + 29], 8 + pinsrb xmm13, byte ptr [r14 + r11 + 29], 9 + pinsrb xmm13, byte ptr [r14 + rax + 29], 10 + pinsrb xmm13, byte ptr [r14 + r15 + 29], 11 + pinsrb xmm13, byte ptr [r14 + r12 + 29], 12 + pinsrb xmm13, byte ptr [r14 + rdx + 29], 13 + pinsrb xmm13, byte ptr [r14 + rsi + 29], 14 + movdqa xmm1, xmm15 + pcmpeqb xmm9, xmm15 + pand xmm9, xmmword ptr [rip + .LCPI2_12] + pcmpeqb xmm4, xmm15 + pand xmm4, xmmword ptr [rip + .LCPI2_13] + por xmm4, xmm9 + pinsrb xmm13, byte ptr [r14 + rbx + 29], 15 + pcmpeqb xmm13, xmm15 + pand xmm13, xmm7 + por xmm13, xmm4 + pinsrb xmm12, byte ptr [r14 + rdi + 30], 3 + pinsrb xmm0, byte ptr [r14 + rdi + 31], 3 + pinsrb xmm12, byte ptr [r14 + r10 + 30], 4 + pinsrb xmm0, byte ptr [r14 + r10 + 31], 4 + pinsrb xmm12, byte ptr [r14 + r13 + 30], 5 + pinsrb xmm0, byte ptr [r14 + r13 + 31], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 30], 6 + pinsrb xmm0, byte ptr [r14 + rcx + 31], 6 + pinsrb xmm12, byte ptr [r14 + r8 + 30], 7 + pinsrb xmm0, byte ptr [r14 + r8 + 31], 7 + pinsrb xmm12, byte ptr [r14 + r9 + 30], 8 + pinsrb xmm0, byte ptr [r14 + r9 + 31], 8 + pinsrb xmm12, byte ptr [r14 + r11 + 30], 9 + pinsrb xmm0, byte ptr [r14 + r11 + 31], 9 + pinsrb xmm12, byte ptr [r14 + rax + 30], 10 + pinsrb xmm0, byte ptr [r14 + rax + 31], 10 + pinsrb xmm12, byte ptr [r14 + r15 + 30], 11 + pinsrb xmm0, byte ptr [r14 + r15 + 31], 11 + pinsrb xmm12, byte ptr [r14 + r12 + 30], 12 + pinsrb xmm0, byte ptr [r14 + r12 + 31], 12 + pinsrb xmm12, byte ptr [r14 + rdx + 30], 13 + pinsrb xmm0, byte ptr [r14 + rdx + 31], 13 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rsi + 30], 14 + pinsrb xmm0, byte ptr [r14 + rsi + 31], 14 + pinsrb xmm12, byte ptr [r14 + rbx + 30], 15 + pinsrb xmm0, byte ptr [r14 + rbx + 31], 15 + por xmm13, xmm11 + pcmpeqb xmm12, xmm15 + pand xmm12, xmm5 + pcmpeqb xmm0, xmm15 + psllw xmm0, 7 + pand xmm0, xmm6 + por xmm0, xmm12 + por xmm0, xmm13 + movdqa xmm1, xmm8 + punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload + movdqa xmm2, xmm4 + punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] + movdqa xmm3, xmm2 + punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] + punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] + punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] + punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] + movdqa xmm0, xmm4 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx + 48], xmm4 + movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 + movdqu xmmword ptr [rax + 4*rcx], xmm3 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 216] # 8-byte Folded Reload + jne .LBB2_218 +# %bb.219: + mov rcx, qword ptr [rsp + 248] # 8-byte Reload + cmp rcx, qword ptr [rsp + 216] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r11b, byte ptr [rsp] # 1-byte Reload + mov rsi, qword ptr [rsp + 288] # 8-byte Reload + jne .LBB2_168 + jmp .LBB2_172 +.Lfunc_end2: + .size comparison_equal_scalar_arr_sse4, .Lfunc_end2-comparison_equal_scalar_arr_sse4 + # -- End function + .globl comparison_not_equal_arr_arr_sse4 # -- Begin function comparison_not_equal_arr_arr_sse4 + .p2align 4, 0x90 + .type comparison_not_equal_arr_arr_sse4,@function +comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 +# %bb.0: + push rbp + mov rbp, rsp + push r15 + push r14 + push r13 + push r12 + push rbx + and rsp, -8 + sub rsp, 72 + # kill: def $r9d killed $r9d def $r9 + mov r12, r8 + mov r15, rcx + cmp edi, 6 + jg .LBB3_35 +# %bb.1: cmp edi, 3 - jne .LBB3_123 -# %bb.4: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_8 -# %bb.5: - cdqe + jle .LBB3_2 +# %bb.18: + cmp edi, 4 + je .LBB3_83 +# %bb.19: + cmp edi, 5 + je .LBB3_97 +# %bb.20: + cmp edi, 6 + jne .LBB3_153 +# %bb.21: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_26 +# %bb.23: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_24: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_6 -# %bb.7: - add r12, 1 -.LBB3_8: - sar r15, 5 - cmp r14, 32 - jl .LBB3_12 -# %bb.9: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB3_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB3_26: + sub r12, r8 + je .LBB3_153 +# %bb.27: + add r15, 1 +.LBB3_28: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_32 +# %bb.29: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - movzx eax, byte ptr [rsi] - movzx ecx, byte ptr [rsi + 1] - cmp al, byte ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill - cmp cl, byte ptr [rdx + 1] - setne bl - movzx eax, byte ptr [rsi + 2] - cmp al, byte ptr [rdx + 2] - setne byte ptr [rsp + 21] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 3] - cmp al, byte ptr [rdx + 3] - setne byte ptr [rsp + 22] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 4] - cmp al, byte ptr [rdx + 4] - setne byte ptr [rsp + 23] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 5] - cmp al, byte ptr [rdx + 5] - setne byte ptr [rsp + 3] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 6] - cmp al, byte ptr [rdx + 6] - setne byte ptr [rsp + 5] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 7] - cmp al, byte ptr [rdx + 7] - setne r15b - movzx eax, byte ptr [rsi + 8] - cmp al, byte ptr [rdx + 8] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 9] - cmp al, byte ptr [rdx + 9] - setne dil - movzx eax, byte ptr [rsi + 10] - cmp al, byte ptr [rdx + 10] - setne r10b - movzx eax, byte ptr [rsi + 11] - cmp al, byte ptr [rdx + 11] - setne r11b - movzx eax, byte ptr [rsi + 12] - cmp al, byte ptr [rdx + 12] - setne r14b - movzx eax, byte ptr [rsi + 13] - cmp al, byte ptr [rdx + 13] - setne byte ptr [rsp + 6] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 14] - cmp al, byte ptr [rdx + 14] - setne byte ptr [rsp + 7] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 15] - cmp al, byte ptr [rdx + 15] - setne r8b - movzx eax, byte ptr [rsi + 16] - cmp al, byte ptr [rdx + 16] - setne byte ptr [rsp + 14] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 17] - cmp al, byte ptr [rdx + 17] - setne r12b - movzx eax, byte ptr [rsi + 18] - cmp al, byte ptr [rdx + 18] - setne r13b - movzx eax, byte ptr [rsi + 19] - cmp al, byte ptr [rdx + 19] - setne byte ptr [rsp + 9] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 20] - cmp al, byte ptr [rdx + 20] - setne byte ptr [rsp + 10] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 21] - cmp al, byte ptr [rdx + 21] +.LBB3_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + mov eax, dword ptr [rsi] + mov ecx, dword ptr [rsi + 4] + cmp eax, dword ptr [rdx] + setne byte ptr [rsp + 13] # 1-byte Folded Spill + cmp ecx, dword ptr [rdx + 4] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 8] + cmp eax, dword ptr [rdx + 8] + setne byte ptr [rsp + 30] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 12] + cmp eax, dword ptr [rdx + 12] + setne byte ptr [rsp + 31] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 16] + cmp eax, dword ptr [rdx + 16] setne byte ptr [rsp + 11] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 22] - cmp al, byte ptr [rdx + 22] + mov eax, dword ptr [rsi + 20] + cmp eax, dword ptr [rdx + 20] setne byte ptr [rsp + 12] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 23] - cmp al, byte ptr [rdx + 23] - setne r9b - movzx eax, byte ptr [rsi + 24] - cmp al, byte ptr [rdx + 24] - setne byte ptr [rsp + 20] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 25] - cmp al, byte ptr [rdx + 25] - setne byte ptr [rsp + 13] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 26] - cmp al, byte ptr [rdx + 26] + mov eax, dword ptr [rsi + 24] + cmp eax, dword ptr [rdx + 24] + setne byte ptr [rsp + 14] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 28] + cmp eax, dword ptr [rdx + 28] + setne r13b + mov eax, dword ptr [rsi + 32] + cmp eax, dword ptr [rdx + 32] + setne byte ptr [rsp + 19] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 36] + cmp eax, dword ptr [rdx + 36] + setne dil + mov eax, dword ptr [rsi + 40] + cmp eax, dword ptr [rdx + 40] + setne r11b + mov eax, dword ptr [rsi + 44] + cmp eax, dword ptr [rdx + 44] + setne r15b + mov eax, dword ptr [rsi + 48] + cmp eax, dword ptr [rdx + 48] setne byte ptr [rsp + 15] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 27] - cmp al, byte ptr [rdx + 27] + mov eax, dword ptr [rsi + 52] + cmp eax, dword ptr [rdx + 52] setne byte ptr [rsp + 16] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 28] - cmp al, byte ptr [rdx + 28] + mov eax, dword ptr [rsi + 56] + cmp eax, dword ptr [rdx + 56] setne byte ptr [rsp + 17] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 29] - cmp al, byte ptr [rdx + 29] - setne byte ptr [rsp + 18] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 30] - cmp al, byte ptr [rdx + 30] - setne byte ptr [rsp + 19] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 31] - add rsi, 32 - cmp al, byte ptr [rdx + 31] - setne cl - add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload - mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload - shl bl, 2 - or bl, al - mov eax, ebx - add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload - shl bl, 3 - or bl, al - mov eax, ebx - shl r10b, 2 - or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload - shl bl, 4 - or bl, al - mov edi, ebx - shl r11b, 3 - or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload - shl bl, 5 - or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload - shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload - shl dil, 6 - shl r8b, 7 - or r8b, dil - or r15b, bl - or r8b, al - add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload - shl r13b, 2 - or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload - shl al, 3 - or al, r13b - mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 5 - or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload - shl bl, 6 - shl r9b, 7 - or r9b, bl - mov byte ptr [r12 + 1], r8b - or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload - shl bl, 6 - shl cl, 7 - or cl, bl - or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl - add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB3_10 -# %bb.11: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB3_12: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.13: - sub r14, r15 - xor ecx, ecx - .p2align 4, 0x90 -.LBB3_14: # =>This Inner Loop Header: Depth=1 - lea r8, [rcx + 1] - movzx ebx, byte ptr [rsi + rcx] - cmp bl, byte ptr [rdx + rcx] - setne bl - neg bl - mov rdi, rcx - shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] - xor bl, r9b - and cl, 7 - mov al, 1 - # kill: def $cl killed $cl killed $rcx - shl al, cl - and al, bl - xor al, r9b - mov byte ptr [r12 + rdi], al - mov rcx, r8 - cmp r14, r8 - jne .LBB3_14 - jmp .LBB3_123 -.LBB3_30: - cmp edi, 7 - je .LBB3_90 -# %bb.31: - cmp edi, 8 - jne .LBB3_123 -# %bb.32: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_36 -# %bb.33: - cdqe - .p2align 4, 0x90 -.LBB3_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB3_34 -# %bb.35: - add r12, 1 -.LBB3_36: - sar r15, 5 - cmp r14, 32 - jl .LBB3_40 -# %bb.37: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB3_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - mov rax, qword ptr [rsi] - mov rcx, qword ptr [rsi + 8] - cmp rax, qword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill - cmp rcx, qword ptr [rdx + 8] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 16] - cmp rax, qword ptr [rdx + 16] - setne byte ptr [rsp + 21] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 24] - cmp rax, qword ptr [rdx + 24] - setne byte ptr [rsp + 22] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 32] - cmp rax, qword ptr [rdx + 32] - setne byte ptr [rsp + 23] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 40] - cmp rax, qword ptr [rdx + 40] - setne byte ptr [rsp + 3] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 48] - cmp rax, qword ptr [rdx + 48] - setne byte ptr [rsp + 5] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 56] - cmp rax, qword ptr [rdx + 56] - setne r13b - mov rax, qword ptr [rsi + 64] - cmp rax, qword ptr [rdx + 64] - setne byte ptr [rsp + 10] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 72] - cmp rax, qword ptr [rdx + 72] + mov eax, dword ptr [rsi + 60] + cmp eax, dword ptr [rdx + 60] setne r8b - mov rax, qword ptr [rsi + 80] - cmp rax, qword ptr [rdx + 80] - setne r11b - mov rax, qword ptr [rsi + 88] - cmp rax, qword ptr [rdx + 88] - setne r15b - mov rax, qword ptr [rsi + 96] - cmp rax, qword ptr [rdx + 96] - setne byte ptr [rsp + 6] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 104] - cmp rax, qword ptr [rdx + 104] - setne byte ptr [rsp + 7] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 112] - cmp rax, qword ptr [rdx + 112] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 120] - cmp rax, qword ptr [rdx + 120] - setne dil - mov rax, qword ptr [rsi + 128] - mov rbx, qword ptr [rsi + 136] - cmp rax, qword ptr [rdx + 128] - mov rax, qword ptr [rsi + 144] - setne byte ptr [rsp + 11] # 1-byte Folded Spill - cmp rbx, qword ptr [rdx + 136] - mov rbx, qword ptr [rsi + 152] + mov eax, dword ptr [rsi + 64] + mov ebx, dword ptr [rsi + 68] + cmp eax, dword ptr [rdx + 64] + mov eax, dword ptr [rsi + 72] + setne byte ptr [rsp + 20] # 1-byte Folded Spill + cmp ebx, dword ptr [rdx + 68] + mov ebx, dword ptr [rsi + 76] setne r10b - cmp rax, qword ptr [rdx + 144] - mov rax, qword ptr [rsi + 160] + cmp eax, dword ptr [rdx + 72] + mov eax, dword ptr [rsi + 80] setne r14b - cmp rbx, qword ptr [rdx + 152] - mov rbx, qword ptr [rsi + 168] + cmp ebx, dword ptr [rdx + 76] + mov ebx, dword ptr [rsi + 84] setne r12b - cmp rax, qword ptr [rdx + 160] - setne byte ptr [rsp + 9] # 1-byte Folded Spill - cmp rbx, qword ptr [rdx + 168] - mov rax, qword ptr [rsi + 176] - setne byte ptr [rsp + 12] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 176] - mov rax, qword ptr [rsi + 184] - setne byte ptr [rsp + 13] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 184] - mov rax, qword ptr [rsi + 192] - setne r9b - cmp rax, qword ptr [rdx + 192] - mov rax, qword ptr [rsi + 200] - setne byte ptr [rsp + 20] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 200] - mov rax, qword ptr [rsi + 208] - setne byte ptr [rsp + 14] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 208] - mov rax, qword ptr [rsi + 216] - setne byte ptr [rsp + 15] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 216] - mov rax, qword ptr [rsi + 224] - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 224] - mov rax, qword ptr [rsi + 232] - setne byte ptr [rsp + 17] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 232] - mov rax, qword ptr [rsi + 240] - setne byte ptr [rsp + 19] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 240] - mov rax, qword ptr [rsi + 248] + cmp eax, dword ptr [rdx + 80] setne byte ptr [rsp + 18] # 1-byte Folded Spill - add rsi, 256 - cmp rax, qword ptr [rdx + 248] + cmp ebx, dword ptr [rdx + 84] + mov eax, dword ptr [rsi + 88] + setne byte ptr [rsp + 21] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 88] + mov eax, dword ptr [rsi + 92] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 92] + mov eax, dword ptr [rsi + 96] + setne r9b + cmp eax, dword ptr [rdx + 96] + mov eax, dword ptr [rsi + 100] + setne byte ptr [rsp + 29] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 100] + mov eax, dword ptr [rsi + 104] + setne byte ptr [rsp + 22] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 104] + mov eax, dword ptr [rsi + 108] + setne byte ptr [rsp + 23] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 108] + mov eax, dword ptr [rsi + 112] + setne byte ptr [rsp + 25] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 112] + mov eax, dword ptr [rsi + 116] + setne byte ptr [rsp + 26] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 116] + mov eax, dword ptr [rsi + 120] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 120] + mov eax, dword ptr [rsi + 124] + setne byte ptr [rsp + 27] # 1-byte Folded Spill + sub rsi, -128 + cmp eax, dword ptr [rdx + 124] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl - add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_38 -# %bb.39: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_40: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.41: - sub r14, r15 + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl + add rdx, 128 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_30 +# %bb.31: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_32: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB3_42: # =>This Inner Loop Header: Depth=1 +.LBB3_34: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] - mov rdi, qword ptr [rsi + 8*rcx] - cmp rdi, qword ptr [rdx + 8*rcx] + mov edi, dword ptr [rsi + 4*rcx] + cmp edi, dword ptr [rdx + 4*rcx] setne bl neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -17223,543 +16713,690 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_42 - jmp .LBB3_123 -.LBB3_68: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_72 -# %bb.69: - cdqe + cmp r12, r8 + jne .LBB3_34 + jmp .LBB3_153 +.LBB3_35: + cmp edi, 8 + jle .LBB3_36 +# %bb.52: + cmp edi, 9 + je .LBB3_125 +# %bb.53: + cmp edi, 11 + je .LBB3_139 +# %bb.54: + cmp edi, 12 + jne .LBB3_153 +# %bb.55: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_60 +# %bb.57: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB3_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_58: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + movsd xmm0, qword ptr [rsi + 8*r14] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 8*r14] + setp r10b + setne bl + or bl, r10b + neg bl + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB3_70 -# %bb.71: - add r12, 1 -.LBB3_72: - sar r15, 5 - cmp r14, 32 - jl .LBB3_76 -# %bb.73: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + lea eax, [8*rdi] + sub ecx, eax + mov eax, 1 + # kill: def $cl killed $cl killed $rcx + shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl + and al, bl + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -8 + cmp r8, r14 + jne .LBB3_58 +# %bb.59: + sub rsi, r11 + sub rdx, r11 +.LBB3_60: + sub r12, r8 + je .LBB3_153 +# %bb.61: + add r15, 1 +.LBB3_62: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_66 +# %bb.63: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - movzx eax, word ptr [rsi] - movzx ecx, word ptr [rsi + 2] - cmp ax, word ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill - cmp cx, word ptr [rdx + 2] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 4] - cmp ax, word ptr [rdx + 4] - setne byte ptr [rsp + 21] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 6] - cmp ax, word ptr [rdx + 6] - setne byte ptr [rsp + 22] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 8] - cmp ax, word ptr [rdx + 8] - setne byte ptr [rsp + 23] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 10] - cmp ax, word ptr [rdx + 10] - setne byte ptr [rsp + 3] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 12] - cmp ax, word ptr [rdx + 12] - setne byte ptr [rsp + 5] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 14] - cmp ax, word ptr [rdx + 14] +.LBB3_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx] + movsd xmm0, qword ptr [rsi + 8] # xmm0 = mem[0],zero + setp al + setne cl + or cl, al + mov byte ptr [rsp + 29], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 8] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 22], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 16] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 16] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 28], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 24] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 24] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 31], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 32] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 32] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 30], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 40] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 40] + setp al + setne dil + or dil, al + movsd xmm0, qword ptr [rsi + 48] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 48] + setp al setne r13b - movzx eax, word ptr [rsi + 16] - cmp ax, word ptr [rdx + 16] - setne byte ptr [rsp + 10] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 18] - cmp ax, word ptr [rdx + 18] - setne r8b - movzx eax, word ptr [rsi + 20] - cmp ax, word ptr [rdx + 20] - setne r11b - movzx eax, word ptr [rsi + 22] - cmp ax, word ptr [rdx + 22] + or r13b, al + movsd xmm0, qword ptr [rsi + 56] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 56] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 12], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 64] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 27], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 72] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 72] + setp al + setne bl + or bl, al + movsd xmm0, qword ptr [rsi + 80] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 80] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 26], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 88] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 88] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 25], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 96] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 96] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 11], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 104] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 104] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 24], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 112] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 112] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 21], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 120] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 120] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 20], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 128] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 128] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 23], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 136] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 136] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 19], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 144] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 144] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 18], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 152] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 152] + setp al setne r15b - movzx eax, word ptr [rsi + 24] - cmp ax, word ptr [rdx + 24] - setne byte ptr [rsp + 6] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 26] - cmp ax, word ptr [rdx + 26] - setne byte ptr [rsp + 7] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 28] - cmp ax, word ptr [rdx + 28] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 30] - cmp ax, word ptr [rdx + 30] - setne dil - movzx eax, word ptr [rsi + 32] - movzx ebx, word ptr [rsi + 34] - cmp ax, word ptr [rdx + 32] - movzx eax, word ptr [rsi + 36] - setne byte ptr [rsp + 11] # 1-byte Folded Spill - cmp bx, word ptr [rdx + 34] - movzx ebx, word ptr [rsi + 38] + or r15b, al + movsd xmm0, qword ptr [rsi + 160] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 160] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 17], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 168] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 168] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 16], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 176] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 176] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 14], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 184] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 184] + setp al setne r10b - cmp ax, word ptr [rdx + 36] - movzx eax, word ptr [rsi + 40] - setne r14b - cmp bx, word ptr [rdx + 38] - movzx ebx, word ptr [rsi + 42] + or r10b, al + movsd xmm0, qword ptr [rsi + 192] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 192] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 15], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 200] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 200] + setp al setne r12b - cmp ax, word ptr [rdx + 40] - setne byte ptr [rsp + 9] # 1-byte Folded Spill - cmp bx, word ptr [rdx + 42] - movzx eax, word ptr [rsi + 44] - setne byte ptr [rsp + 12] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 44] - movzx eax, word ptr [rsi + 46] - setne byte ptr [rsp + 13] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 46] - movzx eax, word ptr [rsi + 48] - setne r9b - cmp ax, word ptr [rdx + 48] - movzx eax, word ptr [rsi + 50] - setne byte ptr [rsp + 20] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 50] - movzx eax, word ptr [rsi + 52] - setne byte ptr [rsp + 14] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 52] - movzx eax, word ptr [rsi + 54] - setne byte ptr [rsp + 15] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 54] - movzx eax, word ptr [rsi + 56] - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 56] - movzx eax, word ptr [rsi + 58] - setne byte ptr [rsp + 17] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 58] - movzx eax, word ptr [rsi + 60] - setne byte ptr [rsp + 19] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 60] - movzx eax, word ptr [rsi + 62] - setne byte ptr [rsp + 18] # 1-byte Folded Spill - add rsi, 64 - cmp ax, word ptr [rdx + 62] + or r12b, al + movsd xmm0, qword ptr [rsi + 208] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 208] + setp al + setne r14b + or r14b, al + movsd xmm0, qword ptr [rsi + 216] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 216] + setp al + setne r11b + or r11b, al + movsd xmm0, qword ptr [rsi + 224] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 224] + setp al setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, al + mov byte ptr [rsp + 13], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 232] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 232] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 56], cl # 1-byte Spill + movsd xmm0, qword ptr [rsi + 240] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 240] + setp al + setne r9b + or r9b, al + movsd xmm0, qword ptr [rsi + 248] # xmm0 = mem[0],zero + add rsi, 256 + ucomisd xmm0, qword ptr [rdx + 248] + setp al + setne r8b + or r8b, al + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload - shl al, 6 - shl r13b, 7 - or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload - shl al, 2 - or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload - shl bl, 3 - or bl, al + add al, byte ptr [rsp + 29] # 1-byte Folded Reload + shl dil, 5 + shl r13b, 6 + or r13b, dil + mov edi, r13d + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl cl, 2 + or cl, al mov eax, ebx - shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload - shl bl, 4 - or bl, al - mov r8d, ebx - shl r15b, 3 - or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload - shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload - shl al, 4 - or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload - shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b - or r13b, bl - or dil, al - add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r10b - shl r12b, 3 - or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload - shl al, 4 - or al, r12b - mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload + add al, bl + add al, byte ptr [rsp + 27] # 1-byte Folded Reload + mov r13d, eax movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload - shl al, 5 - or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload - shl bl, 6 - shl r9b, 7 - or r9b, bl - mov byte ptr [r12 + 1], dil - or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + shl al, 7 + or al, dil + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or al, r13b + mov edi, eax + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + or al, cl + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload + shl bl, 3 + or bl, dil + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload - shl al, 5 + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl bl, 5 + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + shl al, 6 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload - shl bl, 6 - shl cl, 7 + mov ebx, eax + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload + shl cl, 2 or cl, bl - or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl - add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_74 -# %bb.75: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_76: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.77: - sub r14, r15 + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + shl bl, 4 + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload + shl r13b, 5 + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload + shl cl, 6 + or cl, r13b + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload + shl r10b, 7 + or r10b, cl + or r10b, bl + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload + shl cl, 4 + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl bl, 5 + shl r9b, 6 + or r9b, bl + mov byte ptr [r15 + 1], dil + shl r8b, 7 + or r8b, r9b + or r8b, cl + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b + add rdx, 256 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_64 +# %bb.65: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_66: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB3_78: # =>This Inner Loop Header: Depth=1 - lea r8, [rcx + 1] - movzx edi, word ptr [rsi + 2*rcx] - cmp di, word ptr [rdx + 2*rcx] - setne bl - neg bl +.LBB3_68: # =>This Inner Loop Header: Depth=1 + lea r9, [rcx + 1] + movsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 8*rcx] + setp bl + setne al + or al, bl + neg al mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] - xor bl, r9b + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] + xor al, r8b and cl, 7 - mov al, 1 + mov bl, 1 # kill: def $cl killed $cl killed $rcx - shl al, cl - and al, bl - xor al, r9b - mov byte ptr [r12 + rdi], al - mov rcx, r8 - cmp r14, r8 - jne .LBB3_78 - jmp .LBB3_123 -.LBB3_79: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_83 -# %bb.80: - cdqe - .p2align 4, 0x90 -.LBB3_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setne r10b - neg r10b - lea rdi, [rax + 7] + shl bl, cl + and bl, al + xor bl, r8b + mov byte ptr [r15 + rdi], bl + mov rcx, r9 + cmp r12, r9 + jne .LBB3_68 + jmp .LBB3_153 +.LBB3_2: + cmp edi, 2 + mov r13, r15 + je .LBB3_69 +# %bb.3: + cmp edi, 3 + jne .LBB3_153 +# %bb.4: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_11 +# %bb.5: + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB3_9 +# %bb.6: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB3_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setne r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB3_81 -# %bb.82: - add r12, 1 -.LBB3_83: - sar r15, 5 - cmp r14, 32 - jl .LBB3_87 -# %bb.84: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB3_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB3_9: + sub r12, rax + je .LBB3_153 +# %bb.10: + add r15, 1 +.LBB3_11: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_15 +# %bb.12: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - movzx eax, word ptr [rsi] - movzx ecx, word ptr [rsi + 2] - cmp ax, word ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill - cmp cx, word ptr [rdx + 2] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 4] - cmp ax, word ptr [rdx + 4] - setne byte ptr [rsp + 21] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 6] - cmp ax, word ptr [rdx + 6] - setne byte ptr [rsp + 22] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 8] - cmp ax, word ptr [rdx + 8] - setne byte ptr [rsp + 23] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 10] - cmp ax, word ptr [rdx + 10] - setne byte ptr [rsp + 3] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 12] - cmp ax, word ptr [rdx + 12] - setne byte ptr [rsp + 5] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 14] - cmp ax, word ptr [rdx + 14] - setne r13b - movzx eax, word ptr [rsi + 16] - cmp ax, word ptr [rdx + 16] - setne byte ptr [rsp + 10] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 18] - cmp ax, word ptr [rdx + 18] - setne r8b - movzx eax, word ptr [rsi + 20] - cmp ax, word ptr [rdx + 20] - setne r11b - movzx eax, word ptr [rsi + 22] - cmp ax, word ptr [rdx + 22] - setne r15b - movzx eax, word ptr [rsi + 24] - cmp ax, word ptr [rdx + 24] - setne byte ptr [rsp + 6] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 26] - cmp ax, word ptr [rdx + 26] - setne byte ptr [rsp + 7] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 28] - cmp ax, word ptr [rdx + 28] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - movzx eax, word ptr [rsi + 30] - cmp ax, word ptr [rdx + 30] - setne dil - movzx eax, word ptr [rsi + 32] - movzx ebx, word ptr [rsi + 34] - cmp ax, word ptr [rdx + 32] - movzx eax, word ptr [rsi + 36] +.LBB3_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + movzx eax, byte ptr [rsi] + movzx ecx, byte ptr [rsi + 1] + cmp al, byte ptr [rdx] + setne byte ptr [rsp + 13] # 1-byte Folded Spill + cmp cl, byte ptr [rdx + 1] + setne bl + movzx eax, byte ptr [rsi + 2] + cmp al, byte ptr [rdx + 2] + setne byte ptr [rsp + 30] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 3] + cmp al, byte ptr [rdx + 3] + setne byte ptr [rsp + 31] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 4] + cmp al, byte ptr [rdx + 4] setne byte ptr [rsp + 11] # 1-byte Folded Spill - cmp bx, word ptr [rdx + 34] - movzx ebx, word ptr [rsi + 38] - setne r10b - cmp ax, word ptr [rdx + 36] - movzx eax, word ptr [rsi + 40] - setne r14b - cmp bx, word ptr [rdx + 38] - movzx ebx, word ptr [rsi + 42] - setne r12b - cmp ax, word ptr [rdx + 40] - setne byte ptr [rsp + 9] # 1-byte Folded Spill - cmp bx, word ptr [rdx + 42] - movzx eax, word ptr [rsi + 44] + movzx eax, byte ptr [rsi + 5] + cmp al, byte ptr [rdx + 5] setne byte ptr [rsp + 12] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 44] - movzx eax, word ptr [rsi + 46] - setne byte ptr [rsp + 13] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 46] - movzx eax, word ptr [rsi + 48] - setne r9b - cmp ax, word ptr [rdx + 48] - movzx eax, word ptr [rsi + 50] - setne byte ptr [rsp + 20] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 50] - movzx eax, word ptr [rsi + 52] + movzx eax, byte ptr [rsi + 6] + cmp al, byte ptr [rdx + 6] setne byte ptr [rsp + 14] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 52] - movzx eax, word ptr [rsi + 54] + movzx eax, byte ptr [rsi + 7] + cmp al, byte ptr [rdx + 7] + setne r14b + movzx eax, byte ptr [rsi + 8] + cmp al, byte ptr [rdx + 8] + setne byte ptr [rsp + 17] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 9] + cmp al, byte ptr [rdx + 9] + setne dil + movzx eax, byte ptr [rsi + 10] + cmp al, byte ptr [rdx + 10] + setne r10b + movzx eax, byte ptr [rsi + 11] + cmp al, byte ptr [rdx + 11] + setne r11b + movzx eax, byte ptr [rsi + 12] + cmp al, byte ptr [rdx + 12] + setne r15b + movzx eax, byte ptr [rsi + 13] + cmp al, byte ptr [rdx + 13] setne byte ptr [rsp + 15] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 54] - movzx eax, word ptr [rsi + 56] + movzx eax, byte ptr [rsi + 14] + cmp al, byte ptr [rdx + 14] setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 56] - movzx eax, word ptr [rsi + 58] - setne byte ptr [rsp + 17] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 58] - movzx eax, word ptr [rsi + 60] - setne byte ptr [rsp + 19] # 1-byte Folded Spill - cmp ax, word ptr [rdx + 60] - movzx eax, word ptr [rsi + 62] + movzx eax, byte ptr [rsi + 15] + cmp al, byte ptr [rdx + 15] + setne r8b + movzx eax, byte ptr [rsi + 16] + cmp al, byte ptr [rdx + 16] + setne byte ptr [rsp + 23] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 17] + cmp al, byte ptr [rdx + 17] + setne r12b + movzx eax, byte ptr [rsi + 18] + cmp al, byte ptr [rdx + 18] + setne r13b + movzx eax, byte ptr [rsi + 19] + cmp al, byte ptr [rdx + 19] setne byte ptr [rsp + 18] # 1-byte Folded Spill - add rsi, 64 - cmp ax, word ptr [rdx + 62] + movzx eax, byte ptr [rsi + 20] + cmp al, byte ptr [rdx + 20] + setne byte ptr [rsp + 19] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 21] + cmp al, byte ptr [rdx + 21] + setne byte ptr [rsp + 20] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 22] + cmp al, byte ptr [rdx + 22] + setne byte ptr [rsp + 21] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 23] + cmp al, byte ptr [rdx + 23] + setne r9b + movzx eax, byte ptr [rsi + 24] + cmp al, byte ptr [rdx + 24] + setne byte ptr [rsp + 29] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 25] + cmp al, byte ptr [rdx + 25] + setne byte ptr [rsp + 22] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 26] + cmp al, byte ptr [rdx + 26] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 27] + cmp al, byte ptr [rdx + 27] + setne byte ptr [rsp + 25] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 28] + cmp al, byte ptr [rdx + 28] + setne byte ptr [rsp + 26] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 29] + cmp al, byte ptr [rdx + 29] + setne byte ptr [rsp + 27] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 30] + cmp al, byte ptr [rdx + 30] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 31] + add rsi, 32 + cmp al, byte ptr [rdx + 31] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload - shl al, 6 - shl r13b, 7 - or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload - shl al, 2 - or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload + mov eax, ebx + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload + shl bl, 6 + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload + shl bl, 2 + or bl, al + mov eax, ebx + add dil, dil + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx - shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + shl r10b, 2 + or r10b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx - shl r15b, 3 - or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + mov edi, ebx + shl r11b, 3 + or r11b, r10b + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload - shl al, 4 - or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + or bl, dil + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b - or r13b, bl - or dil, al - add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r10b - shl r12b, 3 - or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil + or r14b, bl + or r8b, al + add r12b, r12b + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload + shl r13b, 2 + or r13b, r12b + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + shl al, 3 + or al, r13b + mov ebx, eax + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 4 - or al, r12b + or al, bl mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl - add rdx, 64 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_85 -# %bb.86: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_87: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.88: - sub r14, r15 + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl + add rdx, 32 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB3_13 +# %bb.14: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB3_15: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB3_89: # =>This Inner Loop Header: Depth=1 +.LBB3_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] - movzx edi, word ptr [rsi + 2*rcx] - cmp di, word ptr [rdx + 2*rcx] + movzx ebx, byte ptr [rsi + rcx] + cmp bl, byte ptr [rdx + rcx] setne bl neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -17767,92 +17404,114 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_89 - jmp .LBB3_123 -.LBB3_101: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_105 -# %bb.102: - cdqe + cmp r12, r8 + jne .LBB3_17 + jmp .LBB3_153 +.LBB3_36: + cmp edi, 7 + je .LBB3_111 +# %bb.37: + cmp edi, 8 + jne .LBB3_153 +# %bb.38: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_41: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_103 -# %bb.104: - add r12, 1 -.LBB3_105: - sar r15, 5 - cmp r14, 32 - jl .LBB3_109 -# %bb.106: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB3_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB3_43: + sub r12, r8 + je .LBB3_153 +# %bb.44: + add r15, 1 +.LBB3_45: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_49 +# %bb.46: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill +.LBB3_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill + setne byte ptr [rsp + 13] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] - setne byte ptr [rsp + 21] # 1-byte Folded Spill + setne byte ptr [rsp + 30] # 1-byte Folded Spill mov rax, qword ptr [rsi + 24] cmp rax, qword ptr [rdx + 24] - setne byte ptr [rsp + 22] # 1-byte Folded Spill + setne byte ptr [rsp + 31] # 1-byte Folded Spill mov rax, qword ptr [rsi + 32] cmp rax, qword ptr [rdx + 32] - setne byte ptr [rsp + 23] # 1-byte Folded Spill + setne byte ptr [rsp + 11] # 1-byte Folded Spill mov rax, qword ptr [rsi + 40] cmp rax, qword ptr [rdx + 40] - setne byte ptr [rsp + 3] # 1-byte Folded Spill + setne byte ptr [rsp + 12] # 1-byte Folded Spill mov rax, qword ptr [rsi + 48] cmp rax, qword ptr [rdx + 48] - setne byte ptr [rsp + 5] # 1-byte Folded Spill + setne byte ptr [rsp + 14] # 1-byte Folded Spill mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] setne r13b mov rax, qword ptr [rsi + 64] cmp rax, qword ptr [rdx + 64] - setne byte ptr [rsp + 10] # 1-byte Folded Spill + setne byte ptr [rsp + 19] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setne r8b + setne dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setne r11b @@ -17861,21 +17520,21 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 setne r15b mov rax, qword ptr [rsi + 96] cmp rax, qword ptr [rdx + 96] - setne byte ptr [rsp + 6] # 1-byte Folded Spill + setne byte ptr [rsp + 15] # 1-byte Folded Spill mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] - setne byte ptr [rsp + 7] # 1-byte Folded Spill + setne byte ptr [rsp + 16] # 1-byte Folded Spill mov rax, qword ptr [rsi + 112] cmp rax, qword ptr [rdx + 112] - setne byte ptr [rsp + 8] # 1-byte Folded Spill + setne byte ptr [rsp + 17] # 1-byte Folded Spill mov rax, qword ptr [rsi + 120] cmp rax, qword ptr [rdx + 120] - setne dil + setne r8b mov rax, qword ptr [rsi + 128] mov rbx, qword ptr [rsi + 136] cmp rax, qword ptr [rdx + 128] mov rax, qword ptr [rsi + 144] - setne byte ptr [rsp + 11] # 1-byte Folded Spill + setne byte ptr [rsp + 20] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 136] mov rbx, qword ptr [rsi + 152] setne r10b @@ -17886,144 +17545,144 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 mov rbx, qword ptr [rsi + 168] setne r12b cmp rax, qword ptr [rdx + 160] - setne byte ptr [rsp + 9] # 1-byte Folded Spill + setne byte ptr [rsp + 18] # 1-byte Folded Spill cmp rbx, qword ptr [rdx + 168] mov rax, qword ptr [rsi + 176] - setne byte ptr [rsp + 12] # 1-byte Folded Spill + setne byte ptr [rsp + 21] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setne byte ptr [rsp + 13] # 1-byte Folded Spill + setne byte ptr [rsp + 24] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setne r9b cmp rax, qword ptr [rdx + 192] mov rax, qword ptr [rsi + 200] - setne byte ptr [rsp + 20] # 1-byte Folded Spill + setne byte ptr [rsp + 29] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setne byte ptr [rsp + 14] # 1-byte Folded Spill + setne byte ptr [rsp + 22] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setne byte ptr [rsp + 15] # 1-byte Folded Spill + setne byte ptr [rsp + 23] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] - setne byte ptr [rsp + 16] # 1-byte Folded Spill + setne byte ptr [rsp + 25] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 224] mov rax, qword ptr [rsi + 232] - setne byte ptr [rsp + 17] # 1-byte Folded Spill + setne byte ptr [rsp + 26] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 232] mov rax, qword ptr [rsi + 240] - setne byte ptr [rsp + 19] # 1-byte Folded Spill + setne byte ptr [rsp + 28] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 240] mov rax, qword ptr [rsi + 248] - setne byte ptr [rsp + 18] # 1-byte Folded Spill + setne byte ptr [rsp + 27] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl add rdx, 256 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_107 -# %bb.108: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_109: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.110: - sub r14, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_47 +# %bb.48: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_49: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB3_111: # =>This Inner Loop Header: Depth=1 +.LBB3_51: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -18031,7 +17690,8 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -18039,634 +17699,288 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_111 - jmp .LBB3_123 -.LBB3_112: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_116 -# %bb.113: - movsxd r10, eax + cmp r12, r8 + jne .LBB3_51 + jmp .LBB3_153 +.LBB3_83: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_114: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - ucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - setp cl - setne bl - or bl, cl - neg bl - lea rdi, [r10 + 7] - test r10, r10 - cmovns rdi, r10 +.LBB3_86: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor bl, r8b - lea r9d, [8*rdi] - mov ecx, r10d - sub ecx, r9d - mov eax, 1 - # kill: def $cl killed $cl killed $ecx - shl eax, cl - and al, bl - xor al, r8b - mov byte ptr [r12 + rdi], al - add r10, 1 - cmp r10, 8 - jne .LBB3_114 -# %bb.115: - add r12, 1 -.LBB3_116: - sar r15, 5 - cmp r14, 32 - jl .LBB3_120 -# %bb.117: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl + add rax, 1 + add r10, -2 + cmp r8, rax + jne .LBB3_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB3_88: + sub r12, r8 + je .LBB3_153 +# %bb.89: + add r15, 1 +.LBB3_90: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_94 +# %bb.91: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx] - movss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero - setp al - setne cl - or cl, al - mov byte ptr [rsp + 21], cl # 1-byte Spill - ucomiss xmm0, dword ptr [rdx + 4] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 13], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 8] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 8] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 20], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 12] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 12] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 23], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 16] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 16] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 22], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 20] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 20] - setp al - setne dil - or dil, al - movss xmm0, dword ptr [rsi + 24] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 24] - setp al +.LBB3_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + movzx eax, word ptr [rsi] + movzx ecx, word ptr [rsi + 2] + cmp ax, word ptr [rdx] + setne byte ptr [rsp + 13] # 1-byte Folded Spill + cmp cx, word ptr [rdx + 2] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 4] + cmp ax, word ptr [rdx + 4] + setne byte ptr [rsp + 30] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 6] + cmp ax, word ptr [rdx + 6] + setne byte ptr [rsp + 31] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 8] + cmp ax, word ptr [rdx + 8] + setne byte ptr [rsp + 11] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 10] + cmp ax, word ptr [rdx + 10] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 12] + cmp ax, word ptr [rdx + 12] + setne byte ptr [rsp + 14] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 14] + cmp ax, word ptr [rdx + 14] setne r13b - or r13b, al - movss xmm0, dword ptr [rsi + 28] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 28] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 3], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 32] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 19], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 36] - setp al - setne bl - or bl, al - movss xmm0, dword ptr [rsi + 40] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 40] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 18], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 44] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 44] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 17], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 48] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 52] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 15], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 56] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 56] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 12], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 60] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 60] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 11], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 64] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 64] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 14], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 68] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 68] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 10], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 72] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 9], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 76] - setp al + movzx eax, word ptr [rsi + 16] + cmp ax, word ptr [rdx + 16] + setne byte ptr [rsp + 19] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 18] + cmp ax, word ptr [rdx + 18] + setne dil + movzx eax, word ptr [rsi + 20] + cmp ax, word ptr [rdx + 20] setne r11b - or r11b, al - movss xmm0, dword ptr [rsi + 80] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 80] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 84] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 84] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 7], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 88] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 88] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 5], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 92] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 92] - setp al - setne r10b - or r10b, al - movss xmm0, dword ptr [rsi + 96] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 96] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 6], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 100] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 100] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 104] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 104] - setp al + movzx eax, word ptr [rsi + 22] + cmp ax, word ptr [rdx + 22] setne r15b - or r15b, al - movss xmm0, dword ptr [rsi + 108] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 108] - setp al - setne r14b - or r14b, al - movss xmm0, dword ptr [rsi + 112] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 112] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 4], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 116] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 116] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill - movss xmm0, dword ptr [rsi + 120] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 120] - setp al - setne r9b - or r9b, al - movss xmm0, dword ptr [rsi + 124] # xmm0 = mem[0],zero,zero,zero - sub rsi, -128 - ucomiss xmm0, dword ptr [rdx + 124] - setp al + movzx eax, word ptr [rsi + 24] + cmp ax, word ptr [rdx + 24] + setne byte ptr [rsp + 15] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 26] + cmp ax, word ptr [rdx + 26] + setne byte ptr [rsp + 16] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 28] + cmp ax, word ptr [rdx + 28] + setne byte ptr [rsp + 17] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 30] + cmp ax, word ptr [rdx + 30] setne r8b - or r8b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 21] # 1-byte Folded Reload - shl dil, 5 - shl r13b, 6 - or r13b, dil - mov edi, r13d - movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload - shl cl, 2 - or cl, al - mov eax, ebx - add al, bl - add al, byte ptr [rsp + 19] # 1-byte Folded Reload - mov r13d, eax - movzx eax, byte ptr [rsp + 3] # 1-byte Folded Reload - shl al, 7 - or al, dil - mov byte ptr [rsp + 3], al # 1-byte Spill - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload - shl al, 2 - or al, r13b - mov edi, eax - movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload - shl al, 3 - or al, cl - movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload - shl bl, 3 - or bl, dil - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload - shl r13b, 4 - or r13b, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov edi, eax - movzx ebx, byte ptr [rsp + 15] # 1-byte Folded Reload - shl bl, 5 - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload - shl al, 6 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 7 - or al, bl - movzx ebx, byte ptr [rsp + 10] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 14] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 9] # 1-byte Folded Reload - shl cl, 2 - or cl, bl - shl r11b, 3 - or r11b, cl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl bl, 4 - or bl, r11b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx r11d, byte ptr [rsp + 3] # 1-byte Folded Reload - or r11b, r13b - movzx r13d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r13b, 5 - movzx ecx, byte ptr [rsp + 5] # 1-byte Folded Reload - shl cl, 6 - or cl, r13b - or al, dil - shl r10b, 7 - or r10b, cl - or r10b, bl - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 6] # 1-byte Folded Reload - shl r15b, 2 - or r15b, cl - shl r14b, 3 - or r14b, r15b - movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload - shl cl, 4 - or cl, r14b - mov byte ptr [r12], r11b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl bl, 5 - shl r9b, 6 - or r9b, bl - mov byte ptr [r12 + 1], al - shl r8b, 7 - or r8b, r9b - or r8b, cl - mov byte ptr [r12 + 2], r10b - mov byte ptr [r12 + 3], r8b - add rdx, 128 - add r12, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB3_118 -# %bb.119: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB3_120: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.121: - sub r14, r15 - xor ecx, ecx - .p2align 4, 0x90 -.LBB3_122: # =>This Inner Loop Header: Depth=1 - lea r9, [rcx + 1] - movss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 4*rcx] - setp bl - setne al - or al, bl - neg al - mov rdi, rcx - shr rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor al, r8b - and cl, 7 - mov bl, 1 - # kill: def $cl killed $cl killed $rcx - shl bl, cl - and bl, al - xor bl, r8b - mov byte ptr [r12 + rdi], bl - mov rcx, r9 - cmp r14, r9 - jne .LBB3_122 - jmp .LBB3_123 -.LBB3_57: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_61 -# %bb.58: - cdqe - .p2align 4, 0x90 -.LBB3_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB3_59 -# %bb.60: - add r12, 1 -.LBB3_61: - sar r15, 5 - cmp r14, 32 - jl .LBB3_65 -# %bb.62: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB3_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - movzx eax, byte ptr [rsi] - movzx ecx, byte ptr [rsi + 1] - cmp al, byte ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill - cmp cl, byte ptr [rdx + 1] - setne bl - movzx eax, byte ptr [rsi + 2] - cmp al, byte ptr [rdx + 2] - setne byte ptr [rsp + 21] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 3] - cmp al, byte ptr [rdx + 3] - setne byte ptr [rsp + 22] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 4] - cmp al, byte ptr [rdx + 4] - setne byte ptr [rsp + 23] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 5] - cmp al, byte ptr [rdx + 5] - setne byte ptr [rsp + 3] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 6] - cmp al, byte ptr [rdx + 6] - setne byte ptr [rsp + 5] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 7] - cmp al, byte ptr [rdx + 7] - setne r15b - movzx eax, byte ptr [rsi + 8] - cmp al, byte ptr [rdx + 8] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 9] - cmp al, byte ptr [rdx + 9] - setne dil - movzx eax, byte ptr [rsi + 10] - cmp al, byte ptr [rdx + 10] + movzx eax, word ptr [rsi + 32] + movzx ebx, word ptr [rsi + 34] + cmp ax, word ptr [rdx + 32] + movzx eax, word ptr [rsi + 36] + setne byte ptr [rsp + 20] # 1-byte Folded Spill + cmp bx, word ptr [rdx + 34] + movzx ebx, word ptr [rsi + 38] setne r10b - movzx eax, byte ptr [rsi + 11] - cmp al, byte ptr [rdx + 11] - setne r11b - movzx eax, byte ptr [rsi + 12] - cmp al, byte ptr [rdx + 12] + cmp ax, word ptr [rdx + 36] + movzx eax, word ptr [rsi + 40] setne r14b - movzx eax, byte ptr [rsi + 13] - cmp al, byte ptr [rdx + 13] - setne byte ptr [rsp + 6] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 14] - cmp al, byte ptr [rdx + 14] - setne byte ptr [rsp + 7] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 15] - cmp al, byte ptr [rdx + 15] - setne r8b - movzx eax, byte ptr [rsi + 16] - cmp al, byte ptr [rdx + 16] - setne byte ptr [rsp + 14] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 17] - cmp al, byte ptr [rdx + 17] + cmp bx, word ptr [rdx + 38] + movzx ebx, word ptr [rsi + 42] setne r12b - movzx eax, byte ptr [rsi + 18] - cmp al, byte ptr [rdx + 18] - setne r13b - movzx eax, byte ptr [rsi + 19] - cmp al, byte ptr [rdx + 19] - setne byte ptr [rsp + 9] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 20] - cmp al, byte ptr [rdx + 20] - setne byte ptr [rsp + 10] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 21] - cmp al, byte ptr [rdx + 21] - setne byte ptr [rsp + 11] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 22] - cmp al, byte ptr [rdx + 22] - setne byte ptr [rsp + 12] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 23] - cmp al, byte ptr [rdx + 23] - setne r9b - movzx eax, byte ptr [rsi + 24] - cmp al, byte ptr [rdx + 24] - setne byte ptr [rsp + 20] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 25] - cmp al, byte ptr [rdx + 25] - setne byte ptr [rsp + 13] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 26] - cmp al, byte ptr [rdx + 26] - setne byte ptr [rsp + 15] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 27] - cmp al, byte ptr [rdx + 27] - setne byte ptr [rsp + 16] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 28] - cmp al, byte ptr [rdx + 28] - setne byte ptr [rsp + 17] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 29] - cmp al, byte ptr [rdx + 29] + cmp ax, word ptr [rdx + 40] setne byte ptr [rsp + 18] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 30] - cmp al, byte ptr [rdx + 30] - setne byte ptr [rsp + 19] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 31] - add rsi, 32 - cmp al, byte ptr [rdx + 31] + cmp bx, word ptr [rdx + 42] + movzx eax, word ptr [rsi + 44] + setne byte ptr [rsp + 21] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 44] + movzx eax, word ptr [rsi + 46] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 46] + movzx eax, word ptr [rsi + 48] + setne r9b + cmp ax, word ptr [rdx + 48] + movzx eax, word ptr [rsi + 50] + setne byte ptr [rsp + 29] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 50] + movzx eax, word ptr [rsi + 52] + setne byte ptr [rsp + 22] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 52] + movzx eax, word ptr [rsi + 54] + setne byte ptr [rsp + 23] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 54] + movzx eax, word ptr [rsi + 56] + setne byte ptr [rsp + 25] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 56] + movzx eax, word ptr [rsi + 58] + setne byte ptr [rsp + 26] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 58] + movzx eax, word ptr [rsi + 60] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 60] + movzx eax, word ptr [rsi + 62] + setne byte ptr [rsp + 27] # 1-byte Folded Spill + add rsi, 64 + cmp ax, word ptr [rdx + 62] setne cl - add bl, bl - add bl, byte ptr [rsp + 4] # 1-byte Folded Reload - mov eax, ebx - movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload - shl bl, 2 - or bl, al - mov eax, ebx + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 13] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + shl al, 6 + shl r13b, 7 + or r13b, al + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload + shl al, 2 + or al, bl add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx - shl r10b, 2 - or r10b, dil - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + shl r11b, 2 + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al mov edi, ebx - shl r11b, 3 - or r11b, r10b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + shl r15b, 3 + or r15b, r11b + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 or bl, dil - shl r14b, 4 - or r14b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + shl al, 4 + or al, r15b + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r14b - movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload shl dil, 6 shl r8b, 7 or r8b, dil - or r15b, bl + or r13b, bl or r8b, al - add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload - shl r13b, 2 - or r13b, r12b - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload - shl al, 3 - or al, r13b - mov ebx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + add r10b, r10b + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r12b, 3 + or r12b, r14b + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 - or al, bl + or al, r12b mov ebx, eax - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r15b - movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], r8b + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl - add rdx, 32 - add r12, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB3_63 -# %bb.64: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB3_65: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.66: - sub r14, r15 + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl + add rdx, 64 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_92 +# %bb.93: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_94: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB3_67: # =>This Inner Loop Header: Depth=1 +.LBB3_96: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] - movzx ebx, byte ptr [rsi + rcx] - cmp bl, byte ptr [rdx + rcx] + movzx edi, word ptr [rsi + 2*rcx] + cmp di, word ptr [rdx + 2*rcx] setne bl neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -18674,271 +17988,288 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_67 - jmp .LBB3_123 -.LBB3_90: - lea r15, [r14 + 31] - test r14, r14 - cmovns r15, r14 - lea ecx, [rax + 7] - test eax, eax - cmovns ecx, eax - and ecx, -8 - sub eax, ecx - je .LBB3_94 -# %bb.91: - cdqe + cmp r12, r8 + jne .LBB3_96 + jmp .LBB3_153 +.LBB3_97: + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB3_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB3_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setne r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r12 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r12 + rdi], bl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB3_92 -# %bb.93: - add r12, 1 -.LBB3_94: - sar r15, 5 - cmp r14, 32 - jl .LBB3_98 -# %bb.95: - mov qword ptr [rsp + 24], r14 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB3_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB3_102: + sub r12, r8 + je .LBB3_153 +# %bb.103: + add r15, 1 +.LBB3_104: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_108 +# %bb.105: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB3_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r12 # 8-byte Spill - mov eax, dword ptr [rsi] - mov ecx, dword ptr [rsi + 4] - cmp eax, dword ptr [rdx] - setne byte ptr [rsp + 4] # 1-byte Folded Spill - cmp ecx, dword ptr [rdx + 4] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 8] - cmp eax, dword ptr [rdx + 8] - setne byte ptr [rsp + 21] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 12] - cmp eax, dword ptr [rdx + 12] - setne byte ptr [rsp + 22] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 16] - cmp eax, dword ptr [rdx + 16] - setne byte ptr [rsp + 23] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 20] - cmp eax, dword ptr [rdx + 20] - setne byte ptr [rsp + 3] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 24] - cmp eax, dword ptr [rdx + 24] - setne byte ptr [rsp + 5] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 28] - cmp eax, dword ptr [rdx + 28] - setne r13b - mov eax, dword ptr [rsi + 32] - cmp eax, dword ptr [rdx + 32] - setne byte ptr [rsp + 10] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 36] - cmp eax, dword ptr [rdx + 36] - setne r8b - mov eax, dword ptr [rsi + 40] - cmp eax, dword ptr [rdx + 40] - setne r11b - mov eax, dword ptr [rsi + 44] - cmp eax, dword ptr [rdx + 44] - setne r15b - mov eax, dword ptr [rsi + 48] - cmp eax, dword ptr [rdx + 48] - setne byte ptr [rsp + 6] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 52] - cmp eax, dword ptr [rdx + 52] - setne byte ptr [rsp + 7] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 56] - cmp eax, dword ptr [rdx + 56] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 60] - cmp eax, dword ptr [rdx + 60] - setne dil - mov eax, dword ptr [rsi + 64] - mov ebx, dword ptr [rsi + 68] - cmp eax, dword ptr [rdx + 64] - mov eax, dword ptr [rsi + 72] +.LBB3_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + movzx eax, word ptr [rsi] + movzx ecx, word ptr [rsi + 2] + cmp ax, word ptr [rdx] + setne byte ptr [rsp + 13] # 1-byte Folded Spill + cmp cx, word ptr [rdx + 2] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 4] + cmp ax, word ptr [rdx + 4] + setne byte ptr [rsp + 30] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 6] + cmp ax, word ptr [rdx + 6] + setne byte ptr [rsp + 31] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 8] + cmp ax, word ptr [rdx + 8] setne byte ptr [rsp + 11] # 1-byte Folded Spill - cmp ebx, dword ptr [rdx + 68] - mov ebx, dword ptr [rsi + 76] - setne r10b - cmp eax, dword ptr [rdx + 72] - mov eax, dword ptr [rsi + 80] - setne r14b - cmp ebx, dword ptr [rdx + 76] - mov ebx, dword ptr [rsi + 84] - setne r12b - cmp eax, dword ptr [rdx + 80] - setne byte ptr [rsp + 9] # 1-byte Folded Spill - cmp ebx, dword ptr [rdx + 84] - mov eax, dword ptr [rsi + 88] + movzx eax, word ptr [rsi + 10] + cmp ax, word ptr [rdx + 10] setne byte ptr [rsp + 12] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 88] - mov eax, dword ptr [rsi + 92] - setne byte ptr [rsp + 13] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 92] - mov eax, dword ptr [rsi + 96] - setne r9b - cmp eax, dword ptr [rdx + 96] - mov eax, dword ptr [rsi + 100] - setne byte ptr [rsp + 20] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 100] - mov eax, dword ptr [rsi + 104] + movzx eax, word ptr [rsi + 12] + cmp ax, word ptr [rdx + 12] setne byte ptr [rsp + 14] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 104] - mov eax, dword ptr [rsi + 108] + movzx eax, word ptr [rsi + 14] + cmp ax, word ptr [rdx + 14] + setne r13b + movzx eax, word ptr [rsi + 16] + cmp ax, word ptr [rdx + 16] + setne byte ptr [rsp + 19] # 1-byte Folded Spill + movzx eax, word ptr [rsi + 18] + cmp ax, word ptr [rdx + 18] + setne dil + movzx eax, word ptr [rsi + 20] + cmp ax, word ptr [rdx + 20] + setne r11b + movzx eax, word ptr [rsi + 22] + cmp ax, word ptr [rdx + 22] + setne r15b + movzx eax, word ptr [rsi + 24] + cmp ax, word ptr [rdx + 24] setne byte ptr [rsp + 15] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 108] - mov eax, dword ptr [rsi + 112] + movzx eax, word ptr [rsi + 26] + cmp ax, word ptr [rdx + 26] setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 112] - mov eax, dword ptr [rsi + 116] + movzx eax, word ptr [rsi + 28] + cmp ax, word ptr [rdx + 28] setne byte ptr [rsp + 17] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 116] - mov eax, dword ptr [rsi + 120] - setne byte ptr [rsp + 19] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 120] - mov eax, dword ptr [rsi + 124] + movzx eax, word ptr [rsi + 30] + cmp ax, word ptr [rdx + 30] + setne r8b + movzx eax, word ptr [rsi + 32] + movzx ebx, word ptr [rsi + 34] + cmp ax, word ptr [rdx + 32] + movzx eax, word ptr [rsi + 36] + setne byte ptr [rsp + 20] # 1-byte Folded Spill + cmp bx, word ptr [rdx + 34] + movzx ebx, word ptr [rsi + 38] + setne r10b + cmp ax, word ptr [rdx + 36] + movzx eax, word ptr [rsi + 40] + setne r14b + cmp bx, word ptr [rdx + 38] + movzx ebx, word ptr [rsi + 42] + setne r12b + cmp ax, word ptr [rdx + 40] setne byte ptr [rsp + 18] # 1-byte Folded Spill - sub rsi, -128 - cmp eax, dword ptr [rdx + 124] + cmp bx, word ptr [rdx + 42] + movzx eax, word ptr [rsi + 44] + setne byte ptr [rsp + 21] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 44] + movzx eax, word ptr [rsi + 46] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 46] + movzx eax, word ptr [rsi + 48] + setne r9b + cmp ax, word ptr [rdx + 48] + movzx eax, word ptr [rsi + 50] + setne byte ptr [rsp + 29] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 50] + movzx eax, word ptr [rsi + 52] + setne byte ptr [rsp + 22] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 52] + movzx eax, word ptr [rsi + 54] + setne byte ptr [rsp + 23] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 54] + movzx eax, word ptr [rsi + 56] + setne byte ptr [rsp + 25] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 56] + movzx eax, word ptr [rsi + 58] + setne byte ptr [rsp + 26] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 58] + movzx eax, word ptr [rsi + 60] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + cmp ax, word ptr [rdx + 60] + movzx eax, word ptr [rsi + 62] + setne byte ptr [rsp + 27] # 1-byte Folded Spill + add rsi, 64 + cmp ax, word ptr [rdx + 62] setne cl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 4] # 1-byte Folded Reload + add al, byte ptr [rsp + 13] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 shl r13b, 7 or r13b, al - movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload shl al, 2 or al, bl - add r8b, r8b - add r8b, byte ptr [rsp + 10] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 22] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload shl bl, 3 or bl, al mov eax, ebx shl r11b, 2 - or r11b, r8b - movzx ebx, byte ptr [rsp + 23] # 1-byte Folded Reload + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload shl bl, 4 or bl, al - mov r8d, ebx + mov edi, ebx shl r15b, 3 or r15b, r11b - movzx ebx, byte ptr [rsp + 3] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload shl bl, 5 - or bl, r8b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 7] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r8b, 6 - shl dil, 7 - or dil, r8b + or al, dil + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload + shl dil, 6 + shl r8b, 7 + or r8b, dil or r13b, bl - or dil, al + or r8b, al add r10b, r10b - add r10b, byte ptr [rsp + 11] # 1-byte Folded Reload + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload shl r14b, 2 or r14b, r10b shl r12b, 3 or r12b, r14b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, r12b mov ebx, eax - mov r12, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 or al, bl - mov byte ptr [r12], r13b - movzx ebx, byte ptr [rsp + 13] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 shl r9b, 7 or r9b, bl - mov byte ptr [r12 + 1], dil + mov byte ptr [r15 + 1], r8b or r9b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload shl bl, 6 shl cl, 7 or cl, bl or cl, al - mov byte ptr [r12 + 2], r9b - mov byte ptr [r12 + 3], cl - add rdx, 128 - add r12, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB3_96 -# %bb.97: - mov r14, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB3_98: - shl r15, 5 - cmp r15, r14 - jge .LBB3_123 -# %bb.99: - sub r14, r15 + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl + add rdx, 64 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_106 +# %bb.107: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_108: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB3_100: # =>This Inner Loop Header: Depth=1 +.LBB3_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] - mov edi, dword ptr [rsi + 4*rcx] - cmp edi, dword ptr [rdx + 4*rcx] + movzx edi, word ptr [rsi + 2*rcx] + cmp di, word ptr [rdx + 2*rcx] setne bl neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -18946,1747 +18277,1646 @@ comparison_not_equal_arr_arr_sse4: # @comparison_not_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r12 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r14, r8 - jne .LBB3_100 -.LBB3_123: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.Lfunc_end3: - .size comparison_not_equal_arr_arr_sse4, .Lfunc_end3-comparison_not_equal_arr_arr_sse4 - # -- End function - .section .rodata.cst16,"aM",@progbits,16 - .p2align 4 # -- Begin function comparison_not_equal_arr_scalar_sse4 -.LCPI4_0: - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_1: - .zero 16,252 -.LCPI4_2: - .zero 16,248 -.LCPI4_3: - .zero 16,240 -.LCPI4_4: - .zero 16,224 -.LCPI4_5: - .zero 16,192 -.LCPI4_6: - .zero 16,128 -.LCPI4_7: - .byte 0 # 0x0 - .byte 8 # 0x8 - .byte 1 # 0x1 - .byte 9 # 0x9 - .byte 2 # 0x2 - .byte 10 # 0xa - .byte 3 # 0x3 - .byte 11 # 0xb - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf -.LCPI4_8: - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_9: - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_10: - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_11: - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_12: - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_13: - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_14: - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_15: - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI4_16: - .zero 16,2 -.LCPI4_17: - .zero 16,4 -.LCPI4_18: - .zero 16,8 -.LCPI4_19: - .zero 16,16 -.LCPI4_20: - .zero 16,32 -.LCPI4_21: - .zero 16,64 -.LCPI4_22: - .zero 16,255 - .text - .globl comparison_not_equal_arr_scalar_sse4 - .p2align 4, 0x90 - .type comparison_not_equal_arr_scalar_sse4,@function -comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 -# %bb.0: - push rbp - mov rbp, rsp - push r15 - push r14 - push r13 - push r12 - push rbx - and rsp, -16 - sub rsp, 320 - # kill: def $r9d killed $r9d def $r9 - mov r14, r8 - mov r12, rcx - cmp edi, 6 - jg .LBB4_17 -# %bb.1: - cmp edi, 3 - jle .LBB4_32 -# %bb.2: - cmp edi, 4 - je .LBB4_83 -# %bb.3: - cmp edi, 5 - je .LBB4_99 -# %bb.4: - cmp edi, 6 - jne .LBB4_174 -# %bb.5: - mov r13d, dword ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + cmp r12, r8 + jne .LBB3_110 + jmp .LBB3_153 +.LBB3_125: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_9 -# %bb.6: - movsxd rax, r9d + je .LBB3_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB4_7: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r12 - movzx r8d, byte ptr [r12 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r12 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_7 -# %bb.8: - add r12, 1 -.LBB4_9: - sar r10, 5 - cmp r14, 32 - jl .LBB4_13 -# %bb.10: - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill +.LBB3_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl + add rax, 1 + add r10, -8 + cmp r8, rax + jne .LBB3_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB3_130: + sub r12, r8 + je .LBB3_153 +# %bb.131: + add r15, 1 +.LBB3_132: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_136 +# %bb.133: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_11: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r12 # 8-byte Spill - cmp dword ptr [rsi], r13d - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - setne r10b - cmp dword ptr [rsi + 8], r13d - setne r14b - cmp dword ptr [rsi + 12], r13d - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - setne al - cmp dword ptr [rsi + 28], r13d - setne bl - cmp dword ptr [rsi + 32], r13d - setne byte ptr [rsp + 224] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d +.LBB3_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + mov rax, qword ptr [rsi] + mov rcx, qword ptr [rsi + 8] + cmp rax, qword ptr [rdx] + setne byte ptr [rsp + 13] # 1-byte Folded Spill + cmp rcx, qword ptr [rdx + 8] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 16] + cmp rax, qword ptr [rdx + 16] + setne byte ptr [rsp + 30] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 24] + cmp rax, qword ptr [rdx + 24] + setne byte ptr [rsp + 31] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 32] + cmp rax, qword ptr [rdx + 32] + setne byte ptr [rsp + 11] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 40] + cmp rax, qword ptr [rdx + 40] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 48] + cmp rax, qword ptr [rdx + 48] + setne byte ptr [rsp + 14] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 56] + cmp rax, qword ptr [rdx + 56] + setne r13b + mov rax, qword ptr [rsi + 64] + cmp rax, qword ptr [rdx + 64] + setne byte ptr [rsp + 19] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 72] + cmp rax, qword ptr [rdx + 72] setne dil - cmp dword ptr [rsi + 40], r13d - setne r8b - cmp dword ptr [rsi + 44], r13d - setne r9b - cmp dword ptr [rsi + 48], r13d + mov rax, qword ptr [rsi + 80] + cmp rax, qword ptr [rdx + 80] setne r11b - cmp dword ptr [rsi + 52], r13d - setne r12b - cmp dword ptr [rsi + 56], r13d - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - setne cl - cmp dword ptr [rsi + 64], r13d - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d + mov rax, qword ptr [rsi + 88] + cmp rax, qword ptr [rdx + 88] setne r15b - cmp dword ptr [rsi + 96], r13d - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d + mov rax, qword ptr [rsi + 96] + cmp rax, qword ptr [rdx + 96] + setne byte ptr [rsp + 15] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 104] + cmp rax, qword ptr [rdx + 104] setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d + mov rax, qword ptr [rsi + 112] + cmp rax, qword ptr [rdx + 112] + setne byte ptr [rsp + 17] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 120] + cmp rax, qword ptr [rdx + 120] + setne r8b + mov rax, qword ptr [rsi + 128] + mov rbx, qword ptr [rsi + 136] + cmp rax, qword ptr [rdx + 128] + mov rax, qword ptr [rsi + 144] + setne byte ptr [rsp + 20] # 1-byte Folded Spill + cmp rbx, qword ptr [rdx + 136] + mov rbx, qword ptr [rsi + 152] + setne r10b + cmp rax, qword ptr [rdx + 144] + mov rax, qword ptr [rsi + 160] + setne r14b + cmp rbx, qword ptr [rdx + 152] + mov rbx, qword ptr [rsi + 168] + setne r12b + cmp rax, qword ptr [rdx + 160] + setne byte ptr [rsp + 18] # 1-byte Folded Spill + cmp rbx, qword ptr [rdx + 168] + mov rax, qword ptr [rsi + 176] + setne byte ptr [rsp + 21] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 176] + mov rax, qword ptr [rsi + 184] setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - setne byte ptr [rsp + 8] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - setne dl - add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + cmp rax, qword ptr [rdx + 184] + mov rax, qword ptr [rsi + 192] + setne r9b + cmp rax, qword ptr [rdx + 192] + mov rax, qword ptr [rsi + 200] + setne byte ptr [rsp + 29] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 200] + mov rax, qword ptr [rsi + 208] + setne byte ptr [rsp + 22] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 208] + mov rax, qword ptr [rsi + 216] + setne byte ptr [rsp + 23] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 216] + mov rax, qword ptr [rsi + 224] + setne byte ptr [rsp + 25] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 224] + mov rax, qword ptr [rsi + 232] + setne byte ptr [rsp + 26] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 232] + mov rax, qword ptr [rsi + 240] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 240] + mov rax, qword ptr [rsi + 248] + setne byte ptr [rsp + 27] # 1-byte Folded Spill + add rsi, 256 + cmp rax, qword ptr [rdx + 248] + setne cl + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 13] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al - shl r14b, 2 - or r14b, r10b + shl r13b, 7 + or r13b, al + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload + shl al, 2 + or al, bl add dil, dil - add dil, byte ptr [rsp + 224] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov r10d, eax - shl r8b, 2 - or r8b, dil - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload + shl bl, 3 + or bl, al + mov eax, ebx + shl r11b, 2 + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload + shl bl, 4 + or bl, al + mov edi, ebx + shl r15b, 3 + or r15b, r11b + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + shl bl, 5 + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 - or al, r10b + or al, r15b mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, dil - shl r11b, 4 - or r11b, r9b - shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - mov r12, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 96] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl r8b, 7 + or r8b, dil + or r13b, bl + or r8b, al + add r10b, r10b + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r12b, 3 + or r12b, r14b + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or al, r12b + mov ebx, eax + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [r12], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + or al, bl + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r12 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl r9b, 7 + or r9b, bl + mov byte ptr [r15 + 1], r8b + or r9b, al + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], dl - add rsi, 128 - add r12, 4 - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB4_11 -# %bb.12: - mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB4_13: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.14: - mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - je .LBB4_82 -# %bb.15: - mov r10, r8 - and r10, -2 - xor r11d, r11d + or al, bl + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload + shl bl, 6 + shl cl, 7 + or cl, bl + or cl, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl + add rdx, 256 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_134 +# %bb.135: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_136: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.137: + xor ecx, ecx .p2align 4, 0x90 -.LBB4_16: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - setne al - neg al - mov rdi, r11 +.LBB3_138: # =>This Inner Loop Header: Depth=1 + lea r8, [rcx + 1] + mov rdi, qword ptr [rsi + 8*rcx] + cmp rdi, qword ptr [rdx + 8*rcx] + setne bl + neg bl + mov rdi, rcx shr rdi, 3 - mov r14, r12 - movzx r9d, byte ptr [r12 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b - mov byte ptr [r12 + rdi], bl - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - setne al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r12 + rdi], dl - cmp r10, r11 - jne .LBB4_16 - jmp .LBB4_151 -.LBB4_17: - cmp edi, 8 - jle .LBB4_46 -# %bb.18: - cmp edi, 9 - je .LBB4_114 -# %bb.19: - cmp edi, 11 - je .LBB4_125 -# %bb.20: - cmp edi, 12 - jne .LBB4_174 -# %bb.21: - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + and cl, 7 + mov al, 1 + # kill: def $cl killed $cl killed $rcx + shl al, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + mov rcx, r8 + cmp r12, r8 + jne .LBB3_138 + jmp .LBB3_153 +.LBB3_139: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero sub r9d, eax - je .LBB4_25 -# %bb.22: - movsxd rax, r9d + je .LBB3_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_144 +# %bb.141: + movsxd r9, r9d + xor r11d, r11d + xor r14d, r14d .p2align 4, 0x90 -.LBB4_23: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rsi] - lea rsi, [rsi + 8] - setp cl - setne dl - or dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB3_142: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + r14] + movss xmm0, dword ptr [rsi + 4*r14] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 4*r14] + setp r10b + setne bl + or bl, r10b + neg bl + lea rdi, [r9 + r14] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - mov r11, r12 - movzx r9d, byte ptr [r12 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_23 -# %bb.24: - add r12, 1 -.LBB4_25: - sar r10, 5 - cmp r14, 32 - jl .LBB4_29 -# %bb.26: - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 216], r10 # 8-byte Spill - mov qword ptr [rsp + 272], r10 # 8-byte Spill + lea eax, [8*rdi] + sub ecx, eax + mov eax, 1 + # kill: def $cl killed $cl killed $rcx + shl eax, cl + mov r10, r15 + movzx ecx, byte ptr [r15 + rdi] + xor bl, cl + and al, bl + xor al, cl + mov byte ptr [r15 + rdi], al + add r14, 1 + add r11, -4 + cmp r8, r14 + jne .LBB3_142 +# %bb.143: + sub rsi, r11 + sub rdx, r11 +.LBB3_144: + sub r12, r8 + je .LBB3_153 +# %bb.145: + add r15, 1 +.LBB3_146: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_150 +# %bb.147: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_27: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r12 # 8-byte Spill - ucomisd xmm0, qword ptr [rsi] +.LBB3_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx] + movss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero setp al setne cl or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 8] - setp al - setne r13b - or r13b, al - ucomisd xmm0, qword ptr [rsi + 16] + mov byte ptr [rsp + 29], cl # 1-byte Spill + ucomiss xmm0, dword ptr [rdx + 4] setp al setne cl or cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 24] + mov byte ptr [rsp + 22], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 8] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 8] setp al setne cl or cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 32] + mov byte ptr [rsp + 28], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 12] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 12] setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 40] - setp al - setne r12b - or r12b, al - ucomisd xmm0, qword ptr [rsi + 48] + mov byte ptr [rsp + 31], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 16] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 16] setp al setne cl or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 56] + mov byte ptr [rsp + 30], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 20] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 20] setp al - setne cl - or cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 64] + setne dil + or dil, al + movss xmm0, dword ptr [rsi + 24] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 24] setp al - setne cl - or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 72] + setne r13b + or r13b, al + movss xmm0, dword ptr [rsi + 28] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 28] setp al setne cl or cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 80] + mov byte ptr [rsp + 12], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 32] setp al setne cl or cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 88] + mov byte ptr [rsp + 27], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 36] setp al setne bl or bl, al - ucomisd xmm0, qword ptr [rsi + 96] + movss xmm0, dword ptr [rsi + 40] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 40] setp al setne cl or cl, al - mov byte ptr [rsp + 24], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 104] + mov byte ptr [rsp + 26], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 44] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 44] setp al setne cl or cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 112] + mov byte ptr [rsp + 25], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 48] setp al setne cl or cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 120] + mov byte ptr [rsp + 11], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 52] setp al setne cl or cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 128] + mov byte ptr [rsp + 24], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 56] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 56] setp al setne cl or cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 136] + mov byte ptr [rsp + 21], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 60] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 60] setp al setne cl or cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 144] + mov byte ptr [rsp + 20], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 64] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 64] setp al setne cl or cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 152] + mov byte ptr [rsp + 23], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 68] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 68] setp al setne cl or cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 160] + mov byte ptr [rsp + 19], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 72] setp al setne cl or cl, al - mov byte ptr [rsp + 224], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 168] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 176] + mov byte ptr [rsp + 18], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 76] setp al setne r15b or r15b, al - ucomisd xmm0, qword ptr [rsi + 184] + movss xmm0, dword ptr [rsi + 80] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 80] setp al - setne r8b - or r8b, al - ucomisd xmm0, qword ptr [rsi + 192] + setne cl + or cl, al + mov byte ptr [rsp + 17], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 84] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 84] setp al setne cl or cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 200] + mov byte ptr [rsp + 16], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 88] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 88] setp al - setne r11b - or r11b, al - ucomisd xmm0, qword ptr [rsi + 208] + setne cl + or cl, al + mov byte ptr [rsp + 14], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 92] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 92] setp al setne r10b or r10b, al - ucomisd xmm0, qword ptr [rsi + 216] + movss xmm0, dword ptr [rsi + 96] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 96] setp al - setne r9b - or r9b, al - ucomisd xmm0, qword ptr [rsi + 224] + setne cl + or cl, al + mov byte ptr [rsp + 15], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 100] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 100] + setp al + setne r12b + or r12b, al + movss xmm0, dword ptr [rsi + 104] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 104] + setp al + setne r14b + or r14b, al + movss xmm0, dword ptr [rsi + 108] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 108] + setp al + setne r11b + or r11b, al + movss xmm0, dword ptr [rsi + 112] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 112] setp al setne cl or cl, al - mov byte ptr [rsp + 192], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 232] + mov byte ptr [rsp + 13], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 116] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 116] setp al setne cl or cl, al - mov byte ptr [rsp + 240], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rsi + 240] + mov byte ptr [rsp + 56], cl # 1-byte Spill + movss xmm0, dword ptr [rsi + 120] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 120] setp al - setne dil - or dil, al - ucomisd xmm0, qword ptr [rsi + 248] + setne r9b + or r9b, al + movss xmm0, dword ptr [rsi + 124] # xmm0 = mem[0],zero,zero,zero + sub rsi, -128 + ucomiss xmm0, dword ptr [rdx + 124] setp al - setne dl - or dl, al - add r13b, r13b - add r13b, byte ptr [rsp + 32] # 1-byte Folded Reload - mov eax, r13d - shl r12b, 5 - movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload + setne r8b + or r8b, al + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 29] # 1-byte Folded Reload + shl dil, 5 shl r13b, 6 - or r13b, r12b - movzx r12d, byte ptr [rsp + 48] # 1-byte Folded Reload - shl r12b, 2 - or r12b, al - movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 64] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + or r13b, dil + mov edi, r13d + movzx ecx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl cl, 2 + or cl, al + mov eax, ebx + add al, bl + add al, byte ptr [rsp + 27] # 1-byte Folded Reload + mov r13d, eax + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 - or al, r13b - mov byte ptr [rsp + 8], al # 1-byte Spill - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + or al, dil + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or al, r13b + mov edi, eax + movzx eax, byte ptr [rsp + 31] # 1-byte Folded Reload shl al, 3 - or al, r12b + or al, cl + movzx ebx, byte ptr [rsp + 25] # 1-byte Folded Reload shl bl, 3 - or bl, cl - movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload + or bl, dil + movzx r13d, byte ptr [rsp + 30] # 1-byte Folded Reload shl r13b, 4 or r13b, al - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 4 or al, bl - mov byte ptr [rsp + 24], al # 1-byte Spill - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl cl, 5 - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + mov byte ptr [rsp + 11], al # 1-byte Spill + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl bl, 5 + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 6 - or al, cl - mov ecx, eax - movzx r14d, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r14b, 7 - or r14b, al - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 80] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload - shl bl, 2 - or bl, cl - mov r12, qword ptr [rsp + 128] # 8-byte Reload - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload - shl cl, 4 + or al, bl + mov ebx, eax + movzx edi, byte ptr [rsp + 20] # 1-byte Folded Reload + shl dil, 7 + or dil, al + movzx ebx, byte ptr [rsp + 19] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 23] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 18] # 1-byte Folded Reload + shl cl, 2 or cl, bl - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r15b, 3 + or r15b, cl + movzx ebx, byte ptr [rsp + 17] # 1-byte Folded Reload + shl bl, 4 + or bl, r15b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload or al, r13b - movzx ebx, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload + shl r13b, 5 + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload + shl cl, 6 + or cl, r13b + or dil, byte ptr [rsp + 11] # 1-byte Folded Reload + shl r10b, 7 + or r10b, cl + or r10b, bl + add r12b, r12b + add r12b, byte ptr [rsp + 15] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r12b + shl r11b, 3 + or r11b, r14b + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload + shl cl, 4 + or cl, r11b + mov byte ptr [r15], al + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload shl bl, 5 - shl r15b, 6 - or r15b, bl - or r14b, byte ptr [rsp + 24] # 1-byte Folded Reload + shl r9b, 6 + or r9b, bl + mov byte ptr [r15 + 1], dil shl r8b, 7 - or r8b, r15b + or r8b, r9b or r8b, cl - add r11b, r11b - add r11b, byte ptr [rsp + 136] # 1-byte Folded Reload - shl r10b, 2 - or r10b, r11b - shl r9b, 3 - or r9b, r10b - movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload - shl cl, 4 - or cl, r9b - mov ebx, ecx - mov byte ptr [r12], al - movzx ecx, byte ptr [rsp + 240] # 1-byte Folded Reload - shl cl, 5 - shl dil, 6 - or dil, cl - mov byte ptr [r12 + 1], r14b - shl dl, 7 - or dl, dil - or dl, bl - mov byte ptr [r12 + 2], r8b - mov byte ptr [r12 + 3], dl - add rsi, 256 - add r12, 4 - add qword ptr [rsp + 272], -1 # 8-byte Folded Spill - jne .LBB4_27 -# %bb.28: - mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 216] # 8-byte Reload -.LBB4_29: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.30: - mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - jne .LBB4_160 -# %bb.31: - xor r11d, r11d - jmp .LBB4_162 -.LBB4_32: - cmp edi, 2 - je .LBB4_60 -# %bb.33: - cmp edi, 3 - jne .LBB4_174 -# %bb.34: - mov r11b, byte ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + mov byte ptr [r15 + 2], r10b + mov byte ptr [r15 + 3], r8b + add rdx, 128 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_148 +# %bb.149: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_150: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.151: + xor ecx, ecx + .p2align 4, 0x90 +.LBB3_152: # =>This Inner Loop Header: Depth=1 + lea r9, [rcx + 1] + movss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 4*rcx] + setp bl + setne al + or al, bl + neg al + mov rdi, rcx + shr rdi, 3 + mov r10, r15 + movzx r8d, byte ptr [r15 + rdi] + xor al, r8b + and cl, 7 + mov bl, 1 + # kill: def $cl killed $cl killed $rcx + shl bl, cl + and bl, al + xor bl, r8b + mov byte ptr [r15 + rdi], bl + mov rcx, r9 + cmp r12, r9 + jne .LBB3_152 + jmp .LBB3_153 +.LBB3_69: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_38 -# %bb.35: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB4_36: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r11b - lea rsi, [rsi + 1] - setne dl - neg dl - lea rdi, [rax + 7] + je .LBB3_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r12 + cmovg rax, r12 test rax, rax - cmovns rdi, rax + jle .LBB3_74 +# %bb.71: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + movsxd rbx, r9d + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB3_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setne r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - mov r15, r12 - movzx r9d, byte ptr [r12 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r8, r13 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_36 -# %bb.37: - add r12, 1 -.LBB4_38: - sar r10, 5 - cmp r14, 32 - jl .LBB4_137 -# %bb.39: - cmp r10, 16 - mov byte ptr [rsp + 8], r11b # 1-byte Spill - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 264], r10 # 8-byte Spill - jb .LBB4_42 -# %bb.40: - mov rax, r10 - shl rax, 5 - add rax, rsi - cmp r12, rax - jae .LBB4_179 -# %bb.41: - lea rax, [r12 + 4*r10] - cmp rsi, rax - jae .LBB4_179 -.LBB4_42: - xor eax, eax - mov qword ptr [rsp + 216], rax # 8-byte Spill - mov qword ptr [rsp + 104], r12 # 8-byte Spill -.LBB4_43: - sub r10, qword ptr [rsp + 216] # 8-byte Folded Reload - mov qword ptr [rsp + 192], r10 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov r15, r13 + mov byte ptr [r13 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB3_72 +# %bb.73: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + mov r12, qword ptr [rsp + 40] # 8-byte Reload +.LBB3_74: + sub r12, rax + je .LBB3_153 +# %bb.75: + add r15, 1 +.LBB3_76: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_80 +# %bb.77: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_44: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp byte ptr [rsi], r11b - setne byte ptr [rsp + 240] # 1-byte Folded Spill - cmp byte ptr [rsi + 1], r11b - setne sil - cmp byte ptr [rcx + 2], r11b - setne r15b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 3], al - setne r12b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 4], al - setne byte ptr [rsp + 136] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 5], al - setne byte ptr [rsp + 56] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 6], al - setne byte ptr [rsp + 152] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 7], al - setne r9b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 8], al - setne byte ptr [rsp + 224] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 9], al - setne dl - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 10], al +.LBB3_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + movzx eax, byte ptr [rsi] + movzx ecx, byte ptr [rsi + 1] + cmp al, byte ptr [rdx] + setne byte ptr [rsp + 13] # 1-byte Folded Spill + cmp cl, byte ptr [rdx + 1] + setne bl + movzx eax, byte ptr [rsi + 2] + cmp al, byte ptr [rdx + 2] + setne byte ptr [rsp + 30] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 3] + cmp al, byte ptr [rdx + 3] + setne byte ptr [rsp + 31] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 4] + cmp al, byte ptr [rdx + 4] + setne byte ptr [rsp + 11] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 5] + cmp al, byte ptr [rdx + 5] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 6] + cmp al, byte ptr [rdx + 6] + setne byte ptr [rsp + 14] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 7] + cmp al, byte ptr [rdx + 7] + setne r14b + movzx eax, byte ptr [rsi + 8] + cmp al, byte ptr [rdx + 8] + setne byte ptr [rsp + 17] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 9] + cmp al, byte ptr [rdx + 9] setne dil - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 11], al + movzx eax, byte ptr [rsi + 10] + cmp al, byte ptr [rdx + 10] setne r10b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 12], al - setne r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 13], al - setne r13b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], al - setne byte ptr [rsp + 160] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], al - setne r8b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], bl - setne byte ptr [rsp + 176] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], bl - setne byte ptr [rsp + 120] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], bl - setne byte ptr [rsp + 112] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], bl - setne byte ptr [rsp + 88] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], bl - setne byte ptr [rsp + 96] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], bl - setne byte ptr [rsp + 72] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], bl - setne byte ptr [rsp + 80] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], bl + movzx eax, byte ptr [rsi + 11] + cmp al, byte ptr [rdx + 11] setne r11b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], bl - setne byte ptr [rsp + 64] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], bl - setne byte ptr [rsp + 32] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], bl - setne byte ptr [rsp + 48] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], bl - setne byte ptr [rsp + 40] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], bl + movzx eax, byte ptr [rsi + 12] + cmp al, byte ptr [rdx + 12] + setne r15b + movzx eax, byte ptr [rsi + 13] + cmp al, byte ptr [rdx + 13] + setne byte ptr [rsp + 15] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 14] + cmp al, byte ptr [rdx + 14] setne byte ptr [rsp + 16] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], bl + movzx eax, byte ptr [rsi + 15] + cmp al, byte ptr [rdx + 15] + setne r8b + movzx eax, byte ptr [rsi + 16] + cmp al, byte ptr [rdx + 16] + setne byte ptr [rsp + 23] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 17] + cmp al, byte ptr [rdx + 17] + setne r12b + movzx eax, byte ptr [rsi + 18] + cmp al, byte ptr [rdx + 18] + setne r13b + movzx eax, byte ptr [rsi + 19] + cmp al, byte ptr [rdx + 19] + setne byte ptr [rsp + 18] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 20] + cmp al, byte ptr [rdx + 20] + setne byte ptr [rsp + 19] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 21] + cmp al, byte ptr [rdx + 21] + setne byte ptr [rsp + 20] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 22] + cmp al, byte ptr [rdx + 22] + setne byte ptr [rsp + 21] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 23] + cmp al, byte ptr [rdx + 23] + setne r9b + movzx eax, byte ptr [rsi + 24] + cmp al, byte ptr [rdx + 24] + setne byte ptr [rsp + 29] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 25] + cmp al, byte ptr [rdx + 25] + setne byte ptr [rsp + 22] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 26] + cmp al, byte ptr [rdx + 26] setne byte ptr [rsp + 24] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], bl - setne byte ptr [rsp + 128] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], bl - setne bl - add sil, sil - add sil, byte ptr [rsp + 240] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload - shl al, 6 - shl r9b, 7 - or r9b, al - shl r15b, 2 - or r15b, sil - add dl, dl - add dl, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - movzx r15d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl dil, 2 - or dil, dl - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 4 - or al, r12b - shl r10b, 3 - or r10b, dil - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 - or dl, al - shl r14b, 4 - or r14b, r10b - shl r13b, 5 - or r13b, r14b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r9b, dl - or r8b, r13b - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 176] # 1-byte Folded Reload - mov esi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 2 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov esi, edx - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - mov byte ptr [rdx], r9b - movzx edi, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsi + 27] + cmp al, byte ptr [rdx + 27] + setne byte ptr [rsp + 25] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 28] + cmp al, byte ptr [rdx + 28] + setne byte ptr [rsp + 26] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 29] + cmp al, byte ptr [rdx + 29] + setne byte ptr [rsp + 27] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 30] + cmp al, byte ptr [rdx + 30] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 31] + add rsi, 32 + cmp al, byte ptr [rdx + 31] + setne cl + add bl, bl + add bl, byte ptr [rsp + 13] # 1-byte Folded Reload + mov eax, ebx + movzx ebx, byte ptr [rsp + 14] # 1-byte Folded Reload + shl bl, 6 + shl r14b, 7 + or r14b, bl + movzx ebx, byte ptr [rsp + 30] # 1-byte Folded Reload + shl bl, 2 + or bl, al + mov eax, ebx + add dil, dil + add dil, byte ptr [rsp + 17] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload + shl bl, 3 + or bl, al + mov eax, ebx + shl r10b, 2 + or r10b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload + shl bl, 4 + or bl, al + mov edi, ebx + shl r11b, 3 + or r11b, r10b + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + shl bl, 5 + or bl, dil + shl r15b, 4 + or r15b, r11b + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + shl al, 5 + or al, r15b + movzx edi, byte ptr [rsp + 16] # 1-byte Folded Reload shl dil, 6 - shl r11b, 7 - or r11b, dil - mov byte ptr [rdx + 1], r8b - or r11b, sil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl r8b, 7 + or r8b, dil + or r14b, bl + or r8b, al + add r12b, r12b + add r12b, byte ptr [rsp + 23] # 1-byte Folded Reload + shl r13b, 2 + or r13b, r12b + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + shl al, 3 + or al, r13b + mov ebx, eax + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload + shl al, 5 + or al, bl + mov byte ptr [r15], r14b + movzx ebx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl bl, 6 + shl r9b, 7 + or r9b, bl + mov byte ptr [r15 + 1], r8b + or r9b, al + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 64] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 27] # 1-byte Folded Reload shl al, 5 - or al, sil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload - shl sil, 6 - shl bl, 7 - or bl, sil - or bl, al - mov byte ptr [rdx + 2], r11b - mov r11d, r15d - mov byte ptr [rdx + 3], bl - lea rsi, [rcx + 32] - add rdx, 4 - mov qword ptr [rsp + 104], rdx # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB4_44 -# %bb.45: - mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 264] # 8-byte Reload - jmp .LBB4_138 -.LBB4_46: - cmp edi, 7 - je .LBB4_72 -# %bb.47: - cmp edi, 8 - jne .LBB4_174 -# %bb.48: - mov r13, qword ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + or al, bl + movzx ebx, byte ptr [rsp + 28] # 1-byte Folded Reload + shl bl, 6 + shl cl, 7 + or cl, bl + or cl, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl + add rdx, 32 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB3_78 +# %bb.79: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 48] # 8-byte Reload +.LBB3_80: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.81: + xor ecx, ecx + .p2align 4, 0x90 +.LBB3_82: # =>This Inner Loop Header: Depth=1 + lea r8, [rcx + 1] + movzx ebx, byte ptr [rsi + rcx] + cmp bl, byte ptr [rdx + rcx] + setne bl + neg bl + mov rdi, rcx + shr rdi, 3 + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] + xor bl, r9b + and cl, 7 + mov al, 1 + # kill: def $cl killed $cl killed $rcx + shl al, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + mov rcx, r8 + cmp r12, r8 + jne .LBB3_82 + jmp .LBB3_153 +.LBB3_111: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_52 -# %bb.49: - movsxd rax, r9d + je .LBB3_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB3_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB4_50: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r12 - movzx r8d, byte ptr [r12 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r12 + rbx], dil +.LBB3_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setne r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + mov r14, r15 + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB4_50 -# %bb.51: - add r12, 1 -.LBB4_52: - sar r10, 5 - cmp r14, 32 - jl .LBB4_56 -# %bb.53: - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB3_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB3_116: + sub r12, r8 + je .LBB3_153 +# %bb.117: + add r15, 1 +.LBB3_118: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB3_122 +# %bb.119: + mov qword ptr [rsp + 40], r12 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_54: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r12 # 8-byte Spill - cmp qword ptr [rsi], r13 - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 - setne r10b - cmp qword ptr [rsi + 16], r13 - setne r14b - cmp qword ptr [rsi + 24], r13 - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 - setne al - cmp qword ptr [rsi + 56], r13 - setne bl - cmp qword ptr [rsi + 64], r13 - setne byte ptr [rsp + 224] # 1-byte Folded Spill - cmp qword ptr [rsi + 72], r13 +.LBB3_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + mov eax, dword ptr [rsi] + mov ecx, dword ptr [rsi + 4] + cmp eax, dword ptr [rdx] + setne byte ptr [rsp + 13] # 1-byte Folded Spill + cmp ecx, dword ptr [rdx + 4] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 8] + cmp eax, dword ptr [rdx + 8] + setne byte ptr [rsp + 30] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 12] + cmp eax, dword ptr [rdx + 12] + setne byte ptr [rsp + 31] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 16] + cmp eax, dword ptr [rdx + 16] + setne byte ptr [rsp + 11] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 20] + cmp eax, dword ptr [rdx + 20] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 24] + cmp eax, dword ptr [rdx + 24] + setne byte ptr [rsp + 14] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 28] + cmp eax, dword ptr [rdx + 28] + setne r13b + mov eax, dword ptr [rsi + 32] + cmp eax, dword ptr [rdx + 32] + setne byte ptr [rsp + 19] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 36] + cmp eax, dword ptr [rdx + 36] setne dil - cmp qword ptr [rsi + 80], r13 - setne r8b - cmp qword ptr [rsi + 88], r13 - setne r9b - cmp qword ptr [rsi + 96], r13 + mov eax, dword ptr [rsi + 40] + cmp eax, dword ptr [rdx + 40] setne r11b - cmp qword ptr [rsi + 104], r13 - setne r12b - cmp qword ptr [rsi + 112], r13 - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 120], r13 - setne cl - cmp qword ptr [rsi + 128], r13 - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp qword ptr [rsi + 136], r13 - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp qword ptr [rsi + 152], r13 - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp qword ptr [rsi + 160], r13 - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 168], r13 - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp qword ptr [rsi + 176], r13 - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp qword ptr [rsi + 184], r13 + mov eax, dword ptr [rsi + 44] + cmp eax, dword ptr [rdx + 44] setne r15b - cmp qword ptr [rsi + 192], r13 - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp qword ptr [rsi + 200], r13 - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp qword ptr [rsi + 208], r13 - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp qword ptr [rsi + 216], r13 - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp qword ptr [rsi + 224], r13 + mov eax, dword ptr [rsi + 48] + cmp eax, dword ptr [rdx + 48] + setne byte ptr [rsp + 15] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 52] + cmp eax, dword ptr [rdx + 52] setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp qword ptr [rsi + 232], r13 + mov eax, dword ptr [rsi + 56] + cmp eax, dword ptr [rdx + 56] + setne byte ptr [rsp + 17] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 60] + cmp eax, dword ptr [rdx + 60] + setne r8b + mov eax, dword ptr [rsi + 64] + mov ebx, dword ptr [rsi + 68] + cmp eax, dword ptr [rdx + 64] + mov eax, dword ptr [rsi + 72] + setne byte ptr [rsp + 20] # 1-byte Folded Spill + cmp ebx, dword ptr [rdx + 68] + mov ebx, dword ptr [rsi + 76] + setne r10b + cmp eax, dword ptr [rdx + 72] + mov eax, dword ptr [rsi + 80] + setne r14b + cmp ebx, dword ptr [rdx + 76] + mov ebx, dword ptr [rsi + 84] + setne r12b + cmp eax, dword ptr [rdx + 80] + setne byte ptr [rsp + 18] # 1-byte Folded Spill + cmp ebx, dword ptr [rdx + 84] + mov eax, dword ptr [rsi + 88] + setne byte ptr [rsp + 21] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 88] + mov eax, dword ptr [rsi + 92] setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp qword ptr [rsi + 240], r13 - setne byte ptr [rsp + 8] # 1-byte Folded Spill - cmp qword ptr [rsi + 248], r13 - setne dl - add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + cmp eax, dword ptr [rdx + 92] + mov eax, dword ptr [rsi + 96] + setne r9b + cmp eax, dword ptr [rdx + 96] + mov eax, dword ptr [rsi + 100] + setne byte ptr [rsp + 29] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 100] + mov eax, dword ptr [rsi + 104] + setne byte ptr [rsp + 22] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 104] + mov eax, dword ptr [rsi + 108] + setne byte ptr [rsp + 23] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 108] + mov eax, dword ptr [rsi + 112] + setne byte ptr [rsp + 25] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 112] + mov eax, dword ptr [rsi + 116] + setne byte ptr [rsp + 26] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 116] + mov eax, dword ptr [rsi + 120] + setne byte ptr [rsp + 28] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 120] + mov eax, dword ptr [rsi + 124] + setne byte ptr [rsp + 27] # 1-byte Folded Spill + sub rsi, -128 + cmp eax, dword ptr [rdx + 124] + setne cl + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 13] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al - shl r14b, 2 - or r14b, r10b + shl r13b, 7 + or r13b, al + movzx eax, byte ptr [rsp + 30] # 1-byte Folded Reload + shl al, 2 + or al, bl add dil, dil - add dil, byte ptr [rsp + 224] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov r10d, eax - shl r8b, 2 - or r8b, dil - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + add dil, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 31] # 1-byte Folded Reload + shl bl, 3 + or bl, al + mov eax, ebx + shl r11b, 2 + or r11b, dil + movzx ebx, byte ptr [rsp + 11] # 1-byte Folded Reload + shl bl, 4 + or bl, al + mov edi, ebx + shl r15b, 3 + or r15b, r11b + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + shl bl, 5 + or bl, dil + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 4 - or al, r10b + or al, r15b mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, dil - shl r11b, 4 - or r11b, r9b - shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 17] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - mov r12, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 96] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl r8b, 7 + or r8b, dil + or r13b, bl + or r8b, al + add r10b, r10b + add r10b, byte ptr [rsp + 20] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r12b, 3 + or r12b, r14b + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + or al, r12b + mov ebx, eax + movzx eax, byte ptr [rsp + 21] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [r12], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + or al, bl + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 32] # 8-byte Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r12 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl r9b, 7 + or r9b, bl + mov byte ptr [r15 + 1], r8b + or r9b, al + movzx eax, byte ptr [rsp + 22] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, byte ptr [rsp + 29] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 23] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 25] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 26] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 28] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], dl - add rsi, 256 - add r12, 4 - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB4_54 -# %bb.55: - mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB4_56: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.57: - mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - je .LBB4_124 -# %bb.58: - mov r10, r8 - and r10, -2 - xor r11d, r11d + or al, bl + movzx ebx, byte ptr [rsp + 27] # 1-byte Folded Reload + shl bl, 6 + shl cl, 7 + or cl, bl + or cl, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], cl + add rdx, 128 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB3_120 +# %bb.121: + mov r12, qword ptr [rsp + 40] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB3_122: + shl rax, 5 + sub r12, rax + jle .LBB3_153 +# %bb.123: + xor ecx, ecx .p2align 4, 0x90 -.LBB4_59: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - setne al - neg al - mov rdi, r11 +.LBB3_124: # =>This Inner Loop Header: Depth=1 + lea r8, [rcx + 1] + mov edi, dword ptr [rsi + 4*rcx] + cmp edi, dword ptr [rdx + 4*rcx] + setne bl + neg bl + mov rdi, rcx shr rdi, 3 - mov r14, r12 - movzx r9d, byte ptr [r12 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al + mov r10, r15 + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b - mov byte ptr [r12 + rdi], bl - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] - setne al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r12 + rdi], dl - cmp r10, r11 - jne .LBB4_59 - jmp .LBB4_170 -.LBB4_60: - mov r11b, byte ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + and cl, 7 + mov al, 1 + # kill: def $cl killed $cl killed $rcx + shl al, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + mov rcx, r8 + cmp r12, r8 + jne .LBB3_124 +.LBB3_153: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.Lfunc_end3: + .size comparison_not_equal_arr_arr_sse4, .Lfunc_end3-comparison_not_equal_arr_arr_sse4 + # -- End function + .section .rodata.cst16,"aM",@progbits,16 + .p2align 4 # -- Begin function comparison_not_equal_arr_scalar_sse4 +.LCPI4_0: + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_1: + .zero 16,252 +.LCPI4_2: + .zero 16,248 +.LCPI4_3: + .zero 16,240 +.LCPI4_4: + .zero 16,224 +.LCPI4_5: + .zero 16,192 +.LCPI4_6: + .zero 16,128 +.LCPI4_7: + .byte 0 # 0x0 + .byte 8 # 0x8 + .byte 1 # 0x1 + .byte 9 # 0x9 + .byte 2 # 0x2 + .byte 10 # 0xa + .byte 3 # 0x3 + .byte 11 # 0xb + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf +.LCPI4_8: + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_9: + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_10: + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_11: + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_12: + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_13: + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_14: + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_15: + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI4_16: + .zero 16,2 +.LCPI4_17: + .zero 16,4 +.LCPI4_18: + .zero 16,8 +.LCPI4_19: + .zero 16,16 +.LCPI4_20: + .zero 16,32 +.LCPI4_21: + .zero 16,64 +.LCPI4_22: + .zero 16,255 + .text + .globl comparison_not_equal_arr_scalar_sse4 + .p2align 4, 0x90 + .type comparison_not_equal_arr_scalar_sse4,@function +comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 +# %bb.0: + push rbp + mov rbp, rsp + push r15 + push r14 + push r13 + push r12 + push rbx + and rsp, -16 + sub rsp, 288 + # kill: def $r9d killed $r9d def $r9 + mov r14, r8 + mov r12, rcx + cmp edi, 6 + jg .LBB4_19 +# %bb.1: + cmp edi, 3 + jle .LBB4_36 +# %bb.2: + cmp edi, 4 + je .LBB4_59 +# %bb.3: + cmp edi, 5 + je .LBB4_64 +# %bb.4: + cmp edi, 6 + jne .LBB4_208 +# %bb.5: + mov r13d, dword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_64 -# %bb.61: - movsxd rax, r9d + je .LBB4_11 +# %bb.6: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_9 +# %bb.7: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_62: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r11b - lea rsi, [rsi + 1] - setne dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB4_8: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx sar rdi, 3 mov r15, r12 movzx r9d, byte ptr [r12 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl xor bl, r9b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_62 -# %bb.63: + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_8 +.LBB4_9: + sub r14, r8 + je .LBB4_208 +# %bb.10: add r12, 1 -.LBB4_64: - sar r10, 5 +.LBB4_11: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 cmp r14, 32 - jl .LBB4_141 -# %bb.65: - cmp r10, 16 - mov byte ptr [rsp + 8], r11b # 1-byte Spill + jl .LBB4_15 +# %bb.12: mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 288], r10 # 8-byte Spill - jb .LBB4_68 -# %bb.66: - mov rax, r10 - shl rax, 5 - add rax, rsi - cmp r12, rax - jae .LBB4_182 -# %bb.67: - lea rax, [r12 + 4*r10] - cmp rsi, rax - jae .LBB4_182 -.LBB4_68: - xor eax, eax - mov qword ptr [rsp + 216], rax # 8-byte Spill - mov qword ptr [rsp + 104], r12 # 8-byte Spill -.LBB4_69: - sub r10, qword ptr [rsp + 216] # 8-byte Folded Reload - mov qword ptr [rsp + 192], r10 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_70: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp byte ptr [rsi], r11b - setne byte ptr [rsp + 240] # 1-byte Folded Spill - cmp byte ptr [rsi + 1], r11b - setne sil - cmp byte ptr [rcx + 2], r11b - setne r15b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 3], al - setne r12b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 4], al - setne byte ptr [rsp + 136] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 5], al - setne byte ptr [rsp + 56] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 6], al +.LBB4_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill + cmp dword ptr [rsi], r13d setne byte ptr [rsp + 152] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 7], al - setne r9b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 8], al - setne byte ptr [rsp + 224] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 9], al - setne dl - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 10], al - setne dil - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 11], al + cmp dword ptr [rsi + 4], r13d setne r10b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 12], al + cmp dword ptr [rsi + 8], r13d setne r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 13], al - setne r13b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], al - setne byte ptr [rsp + 160] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], al - setne r8b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], bl - setne byte ptr [rsp + 176] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], bl - setne byte ptr [rsp + 120] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], bl + cmp dword ptr [rsi + 12], r13d + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d setne byte ptr [rsp + 112] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], bl - setne byte ptr [rsp + 88] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], bl - setne byte ptr [rsp + 96] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], bl + cmp dword ptr [rsi + 20], r13d setne byte ptr [rsp + 72] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], bl - setne byte ptr [rsp + 80] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], bl + cmp dword ptr [rsi + 24], r13d + setne al + cmp dword ptr [rsi + 28], r13d + setne bl + cmp dword ptr [rsi + 32], r13d + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d + setne dil + cmp dword ptr [rsi + 40], r13d + setne r8b + cmp dword ptr [rsi + 44], r13d + setne r9b + cmp dword ptr [rsi + 48], r13d setne r11b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], bl + cmp dword ptr [rsi + 52], r13d + setne r12b + cmp dword ptr [rsi + 56], r13d + setne byte ptr [rsp + 224] # 1-byte Folded Spill + cmp dword ptr [rsi + 60], r13d + setne dl + cmp dword ptr [rsi + 64], r13d + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + setne byte ptr [rsp + 208] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp dword ptr [rsi + 80], r13d + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp dword ptr [rsi + 84], r13d + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d setne byte ptr [rsp + 64] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], bl + cmp dword ptr [rsi + 92], r13d + setne r15b + cmp dword ptr [rsi + 96], r13d setne byte ptr [rsp + 32] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], bl - setne byte ptr [rsp + 48] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], bl + cmp dword ptr [rsi + 100], r13d + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp dword ptr [rsi + 104], r13d setne byte ptr [rsp + 40] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], bl + cmp dword ptr [rsi + 108], r13d + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp dword ptr [rsi + 112], r13d setne byte ptr [rsp + 16] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], bl + cmp dword ptr [rsi + 116], r13d setne byte ptr [rsp + 24] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], bl - setne byte ptr [rsp + 128] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], bl - setne bl - add sil, sil - add sil, byte ptr [rsp + 240] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + cmp dword ptr [rsi + 120], r13d + setne byte ptr [rsp + 8] # 1-byte Folded Spill + cmp dword ptr [rsi + 124], r13d + setne cl + add r10b, r10b + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 6 - shl r9b, 7 - or r9b, al - shl r15b, 2 - or r15b, sil - add dl, dl - add dl, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - movzx r15d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl dil, 2 - or dil, dl + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, r10b + add dil, dil + add dil, byte ptr [rsp + 128] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 4 - or al, r12b - shl r10b, 3 - or r10b, dil - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 - or dl, al - shl r14b, 4 - or r14b, r10b - shl r13b, 5 - or r13b, r14b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r9b, dl - or r8b, r13b - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 176] # 1-byte Folded Reload - mov esi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 2 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov esi, edx - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - mov byte ptr [rdx], r9b - movzx edi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dil, 6 - shl r11b, 7 - or r11b, dil - mov byte ptr [rdx + 1], r8b - or r11b, sil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 64] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 5 - or al, sil - movzx esi, byte ptr [rsp + 128] # 1-byte Folded Reload - shl sil, 6 - shl bl, 7 - or bl, sil - or bl, al - mov byte ptr [rdx + 2], r11b - mov r11d, r15d - mov byte ptr [rdx + 3], bl - lea rsi, [rcx + 32] - add rdx, 4 - mov qword ptr [rsp + 104], rdx # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB4_70 -# %bb.71: - mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 288] # 8-byte Reload - jmp .LBB4_142 -.LBB4_72: - mov r13d, dword ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB4_76 -# %bb.73: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB4_74: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r12 - movzx r8d, byte ptr [r12 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r12 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_74 -# %bb.75: - add r12, 1 -.LBB4_76: - sar r10, 5 - cmp r14, 32 - jl .LBB4_80 -# %bb.77: - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - .p2align 4, 0x90 -.LBB4_78: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r12 # 8-byte Spill - cmp dword ptr [rsi], r13d - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - setne r10b - cmp dword ptr [rsi + 8], r13d - setne r14b - cmp dword ptr [rsi + 12], r13d - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - setne al - cmp dword ptr [rsi + 28], r13d - setne bl - cmp dword ptr [rsi + 32], r13d - setne byte ptr [rsp + 224] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d - setne dil - cmp dword ptr [rsi + 40], r13d - setne r8b - cmp dword ptr [rsi + 44], r13d - setne r9b - cmp dword ptr [rsi + 48], r13d - setne r11b - cmp dword ptr [rsi + 52], r13d - setne r12b - cmp dword ptr [rsi + 56], r13d - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - setne cl - cmp dword ptr [rsi + 64], r13d - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d - setne r15b - cmp dword ptr [rsi + 96], r13d - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - setne byte ptr [rsp + 8] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - setne dl - add r10b, r10b - add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al - shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 224] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov r10d, eax - shl r8b, 2 - or r8b, dil - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r10d, eax + shl r8b, 2 + or r8b, dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 4 or al, r10b mov edi, eax @@ -20699,18 +19929,18 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 224] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - mov r12, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax @@ -20718,634 +19948,561 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, dil mov byte ptr [r12], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r12 + 1], cl + mov byte ptr [r12 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al + or al, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], dl + mov byte ptr [r12 + 3], cl add rsi, 128 add r12, 4 add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB4_78 -# %bb.79: + jne .LBB4_13 +# %bb.14: mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB4_80: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.81: + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_15: + shl rax, 5 mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - jne .LBB4_149 -.LBB4_82: + sub r8, rax + jle .LBB4_208 +# %bb.16: + or rax, 1 + cmp r14, rax + je .LBB4_113 +# %bb.17: + mov r10, r8 + and r10, -2 xor r11d, r11d - jmp .LBB4_151 -.LBB4_83: - movzx r13d, word ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + .p2align 4, 0x90 +.LBB4_18: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d + setne al + neg al + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + setne al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB4_18 + jmp .LBB4_177 +.LBB4_19: + cmp edi, 8 + jle .LBB4_43 +# %bb.20: + cmp edi, 9 + je .LBB4_69 +# %bb.21: + cmp edi, 11 + je .LBB4_82 +# %bb.22: + cmp edi, 12 + jne .LBB4_208 +# %bb.23: + mov r15, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_87 -# %bb.84: - movsxd rax, r9d + je .LBB4_29 +# %bb.24: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_27 +# %bb.25: + movsxd rdx, r9d + movq xmm0, r15 + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_85: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - setne dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r15, r12 - movzx r9d, byte ptr [r12 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB4_26: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rcx] + lea rsi, [rcx + 8] + setp cl + setne bl + or bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_85 -# %bb.86: + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_26 +.LBB4_27: + sub r14, r8 + je .LBB4_208 +# %bb.28: add r12, 1 -.LBB4_87: - sar r10, 5 +.LBB4_29: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 cmp r14, 32 - jl .LBB4_95 -# %bb.88: - cmp r10, 8 + jl .LBB4_33 +# %bb.30: mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - jb .LBB4_91 -# %bb.89: - mov rax, r10 - shl rax, 6 - add rax, rsi - cmp r12, rax - jae .LBB4_185 -# %bb.90: - lea rax, [r12 + 4*r10] - cmp rax, rsi - jbe .LBB4_185 -.LBB4_91: - xor eax, eax - mov qword ptr [rsp + 32], rax # 8-byte Spill -.LBB4_92: - mov qword ptr [rsp + 8], r12 # 8-byte Spill - sub r10, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 240], r10 # 8-byte Spill + mov qword ptr [rsp + 160], r15 # 8-byte Spill + movq xmm0, r15 + mov qword ptr [rsp + 264], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_93: # =>This Inner Loop Header: Depth=1 - mov r11, rsi - cmp word ptr [rsi], r13w - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp word ptr [rsi + 2], r13w - setne sil - cmp word ptr [r11 + 4], r13w - setne r15b - cmp word ptr [r11 + 6], r13w +.LBB4_31: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill + ucomisd xmm0, qword ptr [rsi] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 40], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 8] + setp al + setne r13b + or r13b, al + ucomisd xmm0, qword ptr [rsi + 16] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 48], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 24] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 16], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 32] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 32], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 40] + setp al setne r12b - cmp word ptr [r11 + 8], r13w - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp word ptr [r11 + 10], r13w - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp word ptr [r11 + 12], r13w - setne al - cmp word ptr [r11 + 14], r13w + or r12b, al + ucomisd xmm0, qword ptr [rsi + 48] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 64], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 56] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 8], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 64] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 56], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 72] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 80], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 80] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 72], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 88] + setp al setne bl - cmp word ptr [r11 + 16], r13w - setne byte ptr [rsp + 224] # 1-byte Folded Spill - cmp word ptr [r11 + 18], r13w + or bl, al + ucomisd xmm0, qword ptr [rsi + 96] + setp al setne cl - cmp word ptr [r11 + 20], r13w + or cl, al + mov byte ptr [rsp + 24], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 104] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 96], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 112] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 88], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 120] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 112], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 128] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 104], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 136] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 192], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 144] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 208], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 152] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 224], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 160] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 128], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 168] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 152], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 176] + setp al + setne r15b + or r15b, al + ucomisd xmm0, qword ptr [rsi + 184] + setp al setne r8b - cmp word ptr [r11 + 22], r13w + or r8b, al + ucomisd xmm0, qword ptr [rsi + 192] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 136], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 200] + setp al + setne r11b + or r11b, al + ucomisd xmm0, qword ptr [rsi + 208] + setp al + setne r10b + or r10b, al + ucomisd xmm0, qword ptr [rsi + 216] + setp al setne r9b - cmp word ptr [r11 + 24], r13w - setne r14b - cmp word ptr [r11 + 26], r13w - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp word ptr [r11 + 28], r13w - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp word ptr [r11 + 30], r13w + or r9b, al + ucomisd xmm0, qword ptr [rsi + 224] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 176], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 232] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 240], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rsi + 240] + setp al setne dil - cmp word ptr [r11 + 32], r13w - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp word ptr [r11 + 34], r13w - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp word ptr [r11 + 36], r13w - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp word ptr [r11 + 38], r13w - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp word ptr [r11 + 40], r13w - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp word ptr [r11 + 42], r13w - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp word ptr [r11 + 44], r13w - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp word ptr [r11 + 46], r13w - setne r10b - cmp word ptr [r11 + 48], r13w - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp word ptr [r11 + 50], r13w - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp word ptr [r11 + 52], r13w - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp word ptr [r11 + 54], r13w - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp word ptr [r11 + 56], r13w - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp word ptr [r11 + 58], r13w - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp word ptr [r11 + 60], r13w - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp word ptr [r11 + 62], r13w + or dil, al + ucomisd xmm0, qword ptr [rsi + 248] + setp al setne dl - add sil, sil - add sil, byte ptr [rsp + 152] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al - shl r15b, 2 - or r15b, sil + or dl, al + add r13b, r13b + add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload + mov eax, r13d + shl r12b, 5 + movzx r13d, byte ptr [rsp + 64] # 1-byte Folded Reload + shl r13b, 6 + or r13b, r12b + movzx r12d, byte ptr [rsp + 48] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - shl r8b, 2 - or r8b, cl - movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload - shl cl, 4 - or cl, r12b - mov esi, ecx - shl r9b, 3 - or r9b, r8b - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl cl, 5 - or cl, sil - shl r14b, 4 - or r14b, r9b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 5 - or al, r14b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl dil, 7 - or dil, sil + add cl, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 7 + or al, r13b + mov byte ptr [rsp + 8], al # 1-byte Spill + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 3 + or al, r12b + shl bl, 3 or bl, cl - or dil, al - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 80] # 1-byte Folded Reload - mov esi, ecx - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl cl, 2 - or cl, sil - mov esi, ecx + movzx r13d, byte ptr [rsp + 32] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov byte ptr [rsp + 24], al # 1-byte Spill movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 5 + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 6 + or al, cl + mov ecx, eax + movzx r14d, byte ptr [rsp + 112] # 1-byte Folded Reload + shl r14b, 7 + or r14b, al + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl bl, 2 + or bl, cl + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 3 - or cl, sil - mov esi, ecx - movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload shl cl, 4 - or cl, sil - mov esi, ecx - movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + or cl, bl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + or al, r13b + movzx ebx, byte ptr [rsp + 152] # 1-byte Folded Reload + shl bl, 5 + shl r15b, 6 + or r15b, bl + or r14b, byte ptr [rsp + 24] # 1-byte Folded Reload + shl r8b, 7 + or r8b, r15b + or r8b, cl + add r11b, r11b + add r11b, byte ptr [rsp + 136] # 1-byte Folded Reload + shl r10b, 2 + or r10b, r11b + shl r9b, 3 + or r9b, r10b + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload + shl cl, 4 + or cl, r9b + mov ebx, ecx + mov byte ptr [r12], al + movzx ecx, byte ptr [rsp + 240] # 1-byte Folded Reload shl cl, 5 - or cl, sil - mov esi, ecx - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - mov byte ptr [rcx], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 6 - shl r10b, 7 - or r10b, bl - mov byte ptr [rcx + 1], dil - or r10b, sil - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 48] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 + shl dil, 6 + or dil, cl + mov byte ptr [r12 + 1], r14b shl dl, 7 + or dl, dil or dl, bl - or dl, al - mov byte ptr [rcx + 2], r10b - mov byte ptr [rcx + 3], dl - lea rsi, [r11 + 64] - add rcx, 4 - mov qword ptr [rsp + 8], rcx # 8-byte Spill - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB4_93 -# %bb.94: + mov byte ptr [r12 + 2], r8b + mov byte ptr [r12 + 3], dl + add rsi, 256 + add r12, 4 + add qword ptr [rsp + 168], -1 # 8-byte Folded Spill + jne .LBB4_31 +# %bb.32: mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload - mov r12, qword ptr [rsp + 8] # 8-byte Reload -.LBB4_95: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.96: + mov r15, qword ptr [rsp + 160] # 8-byte Reload + mov rax, qword ptr [rsp + 264] # 8-byte Reload +.LBB4_33: + shl rax, 5 mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - je .LBB4_113 -# %bb.97: - mov r9, r8 - and r9, -2 - xor r14d, r14d - .p2align 4, 0x90 -.LBB4_98: # =>This Inner Loop Header: Depth=1 - mov rax, rsi - cmp word ptr [rsi], r13w - setne dl - neg dl - mov rdi, r14 - shr rdi, 3 - movzx r10d, byte ptr [r12 + rdi] - mov ecx, r14d - and cl, 6 - mov bl, 1 - shl bl, cl - xor dl, r10b - and bl, dl - xor bl, r10b - mov byte ptr [r12 + rdi], bl - add r14, 2 - cmp word ptr [rsi + 2], r13w - lea rsi, [rsi + 4] - setne dl - neg dl - xor dl, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, bl - mov byte ptr [r12 + rdi], al - cmp r9, r14 - jne .LBB4_98 - jmp .LBB4_166 -.LBB4_99: - movzx r13d, word ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + sub r8, rax + jle .LBB4_208 +# %bb.34: + movq xmm0, r15 + or rax, 1 + cmp r14, rax + jne .LBB4_190 +# %bb.35: + xor r11d, r11d + jmp .LBB4_192 +.LBB4_36: + cmp edi, 2 + je .LBB4_96 +# %bb.37: + cmp edi, 3 + jne .LBB4_208 +# %bb.38: + mov r15b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_103 -# %bb.100: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB4_101: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - setne dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - mov r15, r12 - movzx r9d, byte ptr [r12 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_101 -# %bb.102: - add r12, 1 -.LBB4_103: - sar r10, 5 - cmp r14, 32 - jl .LBB4_111 -# %bb.104: - cmp r10, 8 - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - jb .LBB4_107 -# %bb.105: - mov rax, r10 - shl rax, 6 - add rax, rsi - cmp r12, rax - jae .LBB4_191 -# %bb.106: - lea rax, [r12 + 4*r10] - cmp rax, rsi - jbe .LBB4_191 -.LBB4_107: - xor eax, eax - mov qword ptr [rsp + 32], rax # 8-byte Spill -.LBB4_108: - mov qword ptr [rsp + 8], r12 # 8-byte Spill - sub r10, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 240], r10 # 8-byte Spill + je .LBB4_114 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_120 +# %bb.40: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB4_109: # =>This Inner Loop Header: Depth=1 - mov r11, rsi - cmp word ptr [rsi], r13w - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp word ptr [rsi + 2], r13w - setne sil - cmp word ptr [r11 + 4], r13w - setne r15b - cmp word ptr [r11 + 6], r13w - setne r12b - cmp word ptr [r11 + 8], r13w - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp word ptr [r11 + 10], r13w - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp word ptr [r11 + 12], r13w - setne al - cmp word ptr [r11 + 14], r13w +.LBB4_41: # =>This Inner Loop Header: Depth=1 + lea r13, [rsi + 1] + cmp byte ptr [rsi], r15b setne bl - cmp word ptr [r11 + 16], r13w - setne byte ptr [rsp + 224] # 1-byte Folded Spill - cmp word ptr [r11 + 18], r13w - setne cl - cmp word ptr [r11 + 20], r13w - setne r8b - cmp word ptr [r11 + 22], r13w - setne r9b - cmp word ptr [r11 + 24], r13w - setne r14b - cmp word ptr [r11 + 26], r13w - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp word ptr [r11 + 28], r13w - setne byte ptr [rsp + 160] # 1-byte Folded Spill - cmp word ptr [r11 + 30], r13w - setne dil - cmp word ptr [r11 + 32], r13w - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp word ptr [r11 + 34], r13w - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp word ptr [r11 + 36], r13w - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp word ptr [r11 + 38], r13w - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp word ptr [r11 + 40], r13w - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp word ptr [r11 + 42], r13w - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp word ptr [r11 + 44], r13w - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp word ptr [r11 + 46], r13w - setne r10b - cmp word ptr [r11 + 48], r13w - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp word ptr [r11 + 50], r13w - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp word ptr [r11 + 52], r13w - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp word ptr [r11 + 54], r13w - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp word ptr [r11 + 56], r13w - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp word ptr [r11 + 58], r13w - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp word ptr [r11 + 60], r13w - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp word ptr [r11 + 62], r13w - setne dl - add sil, sil - add sil, byte ptr [rsp + 152] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al - shl r15b, 2 - or r15b, sil - add cl, cl - add cl, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - shl r8b, 2 - or r8b, cl - movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload - shl cl, 4 - or cl, r12b - mov esi, ecx - shl r9b, 3 - or r9b, r8b - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl cl, 5 - or cl, sil - shl r14b, 4 - or r14b, r9b - movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload - shl al, 5 - or al, r14b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl dil, 7 - or dil, sil - or bl, cl - or dil, al - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 80] # 1-byte Folded Reload - mov esi, ecx - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl cl, 2 - or cl, sil - mov esi, ecx - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl cl, 3 - or cl, sil - mov esi, ecx - movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl cl, 4 - or cl, sil - mov esi, ecx - movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl cl, 5 - or cl, sil - mov esi, ecx - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - mov byte ptr [rcx], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 6 - shl r10b, 7 - or r10b, bl - mov byte ptr [rcx + 1], dil - or r10b, sil - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 48] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, al - mov byte ptr [rcx + 2], r10b - mov byte ptr [rcx + 3], dl - lea rsi, [r11 + 64] - add rcx, 4 - mov qword ptr [rsp + 8], rcx # 8-byte Spill - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB4_109 -# %bb.110: - mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload - mov r12, qword ptr [rsp + 8] # 8-byte Reload -.LBB4_111: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.112: - mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - jne .LBB4_164 -.LBB4_113: - xor r14d, r14d - jmp .LBB4_166 -.LBB4_114: + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov rdi, r12 + movzx r9d, byte ptr [r12 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rsi], al + add rdx, 1 + mov rsi, r13 + add r11, -1 + jne .LBB4_41 +# %bb.42: + sub r14, r8 + jne .LBB4_121 + jmp .LBB4_208 +.LBB4_43: + cmp edi, 7 + je .LBB4_101 +# %bb.44: + cmp edi, 8 + jne .LBB4_208 +# %bb.45: mov r13, qword ptr [rdx] - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB4_118 -# %bb.115: - movsxd rax, r9d + je .LBB4_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_49 +# %bb.47: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_116: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setne dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - mov r9, r12 - movzx r8d, byte ptr [r12 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB4_48: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + mov r15, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r12 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB4_116 -# %bb.117: + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_48 +.LBB4_49: + sub r14, r8 + je .LBB4_208 +# %bb.50: add r12, 1 -.LBB4_118: - sar r10, 5 +.LBB4_51: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 cmp r14, 32 - jl .LBB4_122 -# %bb.119: + jl .LBB4_55 +# %bb.52: mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_120: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r12 # 8-byte Spill +.LBB4_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill cmp qword ptr [rsi], r13 setne byte ptr [rsp + 152] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 @@ -21363,7 +20520,7 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 cmp qword ptr [rsi + 56], r13 setne bl cmp qword ptr [rsi + 64], r13 - setne byte ptr [rsp + 224] # 1-byte Folded Spill + setne byte ptr [rsp + 128] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 setne dil cmp qword ptr [rsi + 80], r13 @@ -21375,31 +20532,31 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 cmp qword ptr [rsi + 104], r13 setne r12b cmp qword ptr [rsi + 112], r13 - setne byte ptr [rsp + 160] # 1-byte Folded Spill + setne byte ptr [rsp + 224] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - setne cl + setne dl cmp qword ptr [rsi + 128], r13 setne byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - setne byte ptr [rsp + 176] # 1-byte Folded Spill + setne byte ptr [rsp + 208] # 1-byte Folded Spill cmp qword ptr [rsi + 144], r13 - setne byte ptr [rsp + 120] # 1-byte Folded Spill + setne byte ptr [rsp + 192] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 setne byte ptr [rsp + 88] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 168], r13 setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp qword ptr [rsi + 168], r13 + setne byte ptr [rsp + 80] # 1-byte Folded Spill cmp qword ptr [rsi + 176], r13 - setne byte ptr [rsp + 56] # 1-byte Folded Spill + setne byte ptr [rsp + 64] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 setne r15b cmp qword ptr [rsi + 192], r13 - setne byte ptr [rsp + 40] # 1-byte Folded Spill + setne byte ptr [rsp + 32] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - setne byte ptr [rsp + 64] # 1-byte Folded Spill + setne byte ptr [rsp + 56] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 - setne byte ptr [rsp + 32] # 1-byte Folded Spill + setne byte ptr [rsp + 40] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 setne byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 224], r13 @@ -21409,7 +20566,7 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 cmp qword ptr [rsi + 240], r13 setne byte ptr [rsp + 8] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - setne dl + setne cl add r10b, r10b add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 6 @@ -21418,7 +20575,7 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 shl r14b, 2 or r14b, r10b add dil, dil - add dil, byte ptr [rsp + 224] # 1-byte Folded Reload + add dil, byte ptr [rsp + 128] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 3 or al, r14b @@ -21438,18 +20595,18 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 or r11b, r9b shl r12b, 5 or r12b, r11b - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx edi, byte ptr [rsp + 224] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil + shl dl, 7 + or dl, dil or bl, al - or cl, r12b - mov r12, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 96] # 1-byte Folded Reload mov edi, eax - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 2 or al, dil mov edi, eax @@ -21457,137 +20614,519 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 shl al, 3 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, dil mov edi, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, dil mov byte ptr [r12], bl - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r12 + 1], cl + mov byte ptr [r12 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax + or al, dl + mov edx, eax movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al + or al, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al mov byte ptr [r12 + 2], r15b - mov byte ptr [r12 + 3], dl + mov byte ptr [r12 + 3], cl add rsi, 256 add r12, 4 add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB4_120 -# %bb.121: + jne .LBB4_53 +# %bb.54: mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB4_122: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.123: + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_55: + shl rax, 5 mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - jne .LBB4_168 -.LBB4_124: + sub r8, rax + jle .LBB4_208 +# %bb.56: + or rax, 1 + cmp r14, rax + je .LBB4_81 +# %bb.57: + mov r10, r8 + and r10, -2 xor r11d, r11d - jmp .LBB4_170 -.LBB4_125: - lea r10, [r14 + 31] - test r14, r14 - cmovns r10, r14 + .p2align 4, 0x90 +.LBB4_58: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + setne al + neg al + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + setne al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB4_58 + jmp .LBB4_196 +.LBB4_59: + movzx r13d, word ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB4_129 -# %bb.126: - movsxd rax, r9d + je .LBB4_136 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_134 +# %bb.61: + movsxd rdx, r9d + mov r15d, r13d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB4_127: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rsi] - lea rsi, [rsi + 4] - setp cl - setne dl - or dl, cl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB4_62: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r15w + setne bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_62 +# %bb.63: + sub r14, r8 + jne .LBB4_135 + jmp .LBB4_208 +.LBB4_64: + movzx r13d, word ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB4_150 +# %bb.65: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_148 +# %bb.66: + movsxd rdx, r9d + mov r15d, r13d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB4_67: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r15w + setne bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_67 +# %bb.68: + sub r14, r8 + jne .LBB4_149 + jmp .LBB4_208 +.LBB4_69: + mov r13, qword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB4_75 +# %bb.70: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_73 +# %bb.71: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB4_72: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + setne bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx sar rdi, 3 - mov r11, r12 + mov r15, r12 movzx r9d, byte ptr [r12 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_72 +.LBB4_73: + sub r14, r8 + je .LBB4_208 +# %bb.74: + add r12, 1 +.LBB4_75: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB4_79 +# %bb.76: + mov qword ptr [rsp + 144], r14 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB4_77: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill + cmp qword ptr [rsi], r13 + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp qword ptr [rsi + 8], r13 + setne r10b + cmp qword ptr [rsi + 16], r13 + setne r14b + cmp qword ptr [rsi + 24], r13 + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp qword ptr [rsi + 40], r13 + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp qword ptr [rsi + 48], r13 + setne al + cmp qword ptr [rsi + 56], r13 + setne bl + cmp qword ptr [rsi + 64], r13 + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp qword ptr [rsi + 72], r13 + setne dil + cmp qword ptr [rsi + 80], r13 + setne r8b + cmp qword ptr [rsi + 88], r13 + setne r9b + cmp qword ptr [rsi + 96], r13 + setne r11b + cmp qword ptr [rsi + 104], r13 + setne r12b + cmp qword ptr [rsi + 112], r13 + setne byte ptr [rsp + 224] # 1-byte Folded Spill + cmp qword ptr [rsi + 120], r13 + setne dl + cmp qword ptr [rsi + 128], r13 + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp qword ptr [rsi + 136], r13 + setne byte ptr [rsp + 208] # 1-byte Folded Spill + cmp qword ptr [rsi + 144], r13 + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp qword ptr [rsi + 152], r13 + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp qword ptr [rsi + 160], r13 + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp qword ptr [rsi + 168], r13 + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp qword ptr [rsi + 176], r13 + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp qword ptr [rsi + 184], r13 + setne r15b + cmp qword ptr [rsi + 192], r13 + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp qword ptr [rsi + 200], r13 + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp qword ptr [rsi + 208], r13 + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp qword ptr [rsi + 216], r13 + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp qword ptr [rsi + 224], r13 + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp qword ptr [rsi + 232], r13 + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp qword ptr [rsi + 240], r13 + setne byte ptr [rsp + 8] # 1-byte Folded Spill + cmp qword ptr [rsi + 248], r13 + setne cl + add r10b, r10b + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, r10b + add dil, dil + add dil, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r10d, eax + shl r8b, 2 + or r8b, dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 4 + or al, r10b + mov edi, eax + shl r9b, 3 + or r9b, r8b + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, dil + shl r11b, 4 + or r11b, r9b + shl r12b, 5 + or r12b, r11b + movzx edi, byte ptr [rsp + 224] # 1-byte Folded Reload + shl dil, 6 + shl dl, 7 + or dl, dil + or bl, al + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 96] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 2 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 3 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 4 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, dil + mov byte ptr [r12], bl + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + shl r15b, 7 + or r15b, bl + mov byte ptr [r12 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], cl + add rsi, 256 + add r12, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB4_77 +# %bb.78: + mov r14, qword ptr [rsp + 144] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_79: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB4_208 +# %bb.80: + or rax, 1 + cmp r14, rax + jne .LBB4_194 +.LBB4_81: + xor r11d, r11d + jmp .LBB4_196 +.LBB4_82: + mov r15d, dword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB4_88 +# %bb.83: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_86 +# %bb.84: + movsxd rdx, r9d + movd xmm0, r15d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB4_85: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rcx] + lea rsi, [rcx + 4] + setp cl + setne bl + or bl, cl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r12 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB4_127 -# %bb.128: + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_85 +.LBB4_86: + sub r14, r8 + je .LBB4_208 +# %bb.87: add r12, 1 -.LBB4_129: - sar r10, 5 +.LBB4_88: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 cmp r14, 32 - jl .LBB4_145 -# %bb.130: - cmp r10, 4 - jb .LBB4_133 -# %bb.131: - mov rax, r10 + jl .LBB4_115 +# %bb.89: + movd xmm0, r15d + cmp rcx, 4 + jb .LBB4_92 +# %bb.90: + mov rax, rcx shl rax, 7 add rax, rsi cmp r12, rax - jae .LBB4_188 -# %bb.132: - lea rax, [r12 + 4*r10] + jae .LBB4_209 +# %bb.91: + lea rax, [r12 + 4*rcx] cmp rax, rsi - jbe .LBB4_188 -.LBB4_133: - xor r8d, r8d + jbe .LBB4_209 +.LBB4_92: + xor r9d, r9d mov rbx, rsi - mov r15, r12 -.LBB4_134: - mov qword ptr [rsp + 128], r15 # 8-byte Spill + mov r13, r12 +.LBB4_93: + mov qword ptr [rsp + 120], r13 # 8-byte Spill + mov dword ptr [rsp + 168], r15d # 4-byte Spill mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov qword ptr [rsp + 272], r10 # 8-byte Spill - sub r10, r8 - mov qword ptr [rsp + 192], r10 # 8-byte Spill + mov qword ptr [rsp + 160], rcx # 8-byte Spill + sub rcx, r9 + mov qword ptr [rsp + 176], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB4_135: # =>This Inner Loop Header: Depth=1 +.LBB4_94: # =>This Inner Loop Header: Depth=1 ucomiss xmm0, dword ptr [rbx] setp al setne cl @@ -21601,7 +21140,7 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 12] setp al setne cl @@ -21616,12 +21155,12 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 24] setp al setne cl or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 28] setp al setne cl @@ -21636,12 +21175,12 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 40] setp al setne cl or cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 44] setp al setne cl @@ -21651,7 +21190,7 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 52] setp al setne cl @@ -21661,7 +21200,7 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 192], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 60] setp al setne cl @@ -21680,17 +21219,17 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill + mov byte ptr [rsp + 208], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 76] setp al setne cl or cl, al - mov byte ptr [rsp + 160], cl # 1-byte Spill + mov byte ptr [rsp + 224], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 80] setp al setne cl or cl, al - mov byte ptr [rsp + 224], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 84] setp al setne cl @@ -21741,24 +21280,24 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 add dl, dl or dl, r13b mov r13d, edx - movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 40] # 1-byte Folded Reload shl dl, 5 - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 6 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 2 or al, r13b mov r13d, eax - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 48] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, dl mov byte ptr [rsp + 8], al # 1-byte Spill - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -21773,12 +21312,12 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 4 or al, r13b - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload shl dl, 4 or dl, cl movzx r13d, byte ptr [rsp + 88] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload shl cl, 6 or cl, r13b movzx r13d, byte ptr [rsp + 112] # 1-byte Folded Reload @@ -21787,14 +21326,14 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 add r12b, r12b add r12b, byte ptr [rsp + 96] # 1-byte Folded Reload mov ecx, r12d - movzx r12d, byte ptr [rsp + 176] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 208] # 1-byte Folded Reload shl r12b, 2 or r12b, cl - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 3 or cl, r12b mov r12d, ecx - movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload shl cl, 4 or cl, r12b movzx r12d, byte ptr [rsp + 8] # 1-byte Folded Reload @@ -21815,7 +21354,7 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 or r9b, r10b shl r15b, 4 or r15b, r9b - mov rax, qword ptr [rsp + 128] # 8-byte Reload + mov rax, qword ptr [rsp + 120] # 8-byte Reload mov byte ptr [rax], r12b movzx ecx, byte ptr [rsp + 240] # 1-byte Folded Reload shl cl, 5 @@ -21829,6237 +21368,6910 @@ comparison_not_equal_arr_scalar_sse4: # @comparison_not_equal_arr_scalar_sse4 mov byte ptr [rax + 3], sil add rbx, 128 add rax, 4 - mov qword ptr [rsp + 128], rax # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB4_135 -# %bb.136: - mov r15, qword ptr [rsp + 128] # 8-byte Reload + mov qword ptr [rsp + 120], rax # 8-byte Spill + add qword ptr [rsp + 176], -1 # 8-byte Folded Spill + jne .LBB4_94 +# %bb.95: + mov r13, qword ptr [rsp + 120] # 8-byte Reload mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r10, qword ptr [rsp + 272] # 8-byte Reload - jmp .LBB4_146 -.LBB4_137: - mov qword ptr [rsp + 104], r12 # 8-byte Spill -.LBB4_138: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.139: - mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - je .LBB4_144 -# %bb.153: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 104] # 8-byte Reload + mov r15d, dword ptr [rsp + 168] # 4-byte Reload + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + jmp .LBB4_116 +.LBB4_96: + mov r15b, byte ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB4_119 +# %bb.97: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_161 +# %bb.98: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB4_154: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r11b +.LBB4_99: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r15b setne bl neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r14 + rdi] + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rsi] xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp byte ptr [rsi + rax + 1], r11b - lea r9, [rax + 2] + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB4_99 +# %bb.100: + sub r14, r8 + jne .LBB4_162 + jmp .LBB4_208 +.LBB4_101: + mov r13d, dword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB4_107 +# %bb.102: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB4_105 +# %bb.103: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB4_104: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d setne bl neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, r9 - jne .LBB4_154 - jmp .LBB4_157 -.LBB4_141: - mov qword ptr [rsp + 104], r12 # 8-byte Spill -.LBB4_142: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.143: - mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - jne .LBB4_155 -.LBB4_144: - xor r9d, r9d - test r8b, 1 - je .LBB4_174 - jmp .LBB4_159 -.LBB4_145: + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 mov r15, r12 - mov rbx, rsi -.LBB4_146: - shl r10, 5 - cmp r10, r14 - jge .LBB4_174 -# %bb.147: - mov r8, r14 - sub r8, r10 - not r10 - add r10, r14 - jne .LBB4_175 -# %bb.148: - xor esi, esi - jmp .LBB4_177 -.LBB4_149: - mov r10, r8 - and r10, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB4_150: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - setne al - neg al - mov rdi, r11 - shr rdi, 3 - mov r14, r12 movzx r9d, byte ptr [r12 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r12 + rdi], bl - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - setne al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r12 + rdi], dl - cmp r10, r11 - jne .LBB4_150 -.LBB4_151: - test r8b, 1 - je .LBB4_174 -# %bb.152: - cmp dword ptr [rsi], r13d - jmp .LBB4_172 -.LBB4_155: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 104] # 8-byte Reload - .p2align 4, 0x90 -.LBB4_156: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r11b - setne bl - neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r14 + rdi] xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp byte ptr [rsi + rax + 1], r11b - lea r9, [rax + 2] - setne bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl and al, bl - xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, r9 - jne .LBB4_156 -.LBB4_157: - add rsi, r9 - test r8b, 1 - je .LBB4_174 -.LBB4_159: - cmp byte ptr [rsi], r11b - setne al - neg al - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and r9b, 7 - mov bl, 1 - mov ecx, r9d - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r8 + rdx], bl - jmp .LBB4_174 -.LBB4_160: - mov r9, r8 - and r9, -2 - xor r11d, r11d + xor al, r9b + mov byte ptr [r12 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB4_104 +.LBB4_105: + sub r14, r8 + je .LBB4_208 +# %bb.106: + add r12, 1 +.LBB4_107: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB4_111 +# %bb.108: + mov qword ptr [rsp + 144], r14 # 8-byte Spill + mov qword ptr [rsp + 176], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill .p2align 4, 0x90 -.LBB4_161: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rsi] - setp cl - setne al - or al, cl - neg al - mov rdi, r11 - shr rdi, 3 - mov r14, r12 - movzx r10d, byte ptr [r12 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r10b - and bl, al - xor bl, r10b - mov byte ptr [r12 + rdi], bl - add r11, 2 - ucomisd xmm0, qword ptr [rsi + 8] - lea rsi, [rsi + 16] - setp r10b +.LBB4_109: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 120], r12 # 8-byte Spill + cmp dword ptr [rsi], r13d + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp dword ptr [rsi + 4], r13d + setne r10b + cmp dword ptr [rsi + 8], r13d + setne r14b + cmp dword ptr [rsi + 12], r13d + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp dword ptr [rsi + 20], r13d + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp dword ptr [rsi + 24], r13d setne al - or al, r10b - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r12 + rdi], dl - cmp r9, r11 - jne .LBB4_161 -.LBB4_162: - test r8b, 1 - je .LBB4_174 -# %bb.163: - ucomisd xmm0, qword ptr [rsi] - setp al - setne dl - or dl, al - neg dl - mov rax, r11 - shr rax, 3 - mov sil, byte ptr [r12 + rax] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor dl, sil - and bl, dl - xor bl, sil - mov byte ptr [r12 + rax], bl - jmp .LBB4_174 -.LBB4_164: - mov r9, r8 - and r9, -2 - xor r14d, r14d - .p2align 4, 0x90 -.LBB4_165: # =>This Inner Loop Header: Depth=1 - mov rax, rsi - cmp word ptr [rsi], r13w - setne dl - neg dl - mov rdi, r14 - shr rdi, 3 - movzx r10d, byte ptr [r12 + rdi] - mov ecx, r14d - and cl, 6 - mov bl, 1 - shl bl, cl - xor dl, r10b - and bl, dl - xor bl, r10b - mov byte ptr [r12 + rdi], bl - add r14, 2 - cmp word ptr [rsi + 2], r13w - lea rsi, [rsi + 4] + cmp dword ptr [rsi + 28], r13d + setne bl + cmp dword ptr [rsi + 32], r13d + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d + setne dil + cmp dword ptr [rsi + 40], r13d + setne r8b + cmp dword ptr [rsi + 44], r13d + setne r9b + cmp dword ptr [rsi + 48], r13d + setne r11b + cmp dword ptr [rsi + 52], r13d + setne r12b + cmp dword ptr [rsi + 56], r13d + setne byte ptr [rsp + 224] # 1-byte Folded Spill + cmp dword ptr [rsi + 60], r13d setne dl - neg dl - xor dl, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, bl - mov byte ptr [r12 + rdi], al - cmp r9, r14 - jne .LBB4_165 -.LBB4_166: - test r8b, 1 - je .LBB4_174 -# %bb.167: - cmp word ptr [rsi], r13w - setne al - neg al - mov rdx, r14 - shr rdx, 3 - mov dil, byte ptr [r12 + rdx] - and r14b, 7 - mov bl, 1 - mov ecx, r14d - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - jmp .LBB4_173 -.LBB4_168: - mov r10, r8 - and r10, -2 + cmp dword ptr [rsi + 64], r13d + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + setne byte ptr [rsp + 208] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp dword ptr [rsi + 80], r13d + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp dword ptr [rsi + 84], r13d + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp dword ptr [rsi + 92], r13d + setne r15b + cmp dword ptr [rsi + 96], r13d + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp dword ptr [rsi + 100], r13d + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp dword ptr [rsi + 104], r13d + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp dword ptr [rsi + 108], r13d + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp dword ptr [rsi + 112], r13d + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp dword ptr [rsi + 120], r13d + setne byte ptr [rsp + 8] # 1-byte Folded Spill + cmp dword ptr [rsi + 124], r13d + setne cl + add r10b, r10b + add r10b, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, r10b + add dil, dil + add dil, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 3 + or al, r14b + mov r10d, eax + shl r8b, 2 + or r8b, dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 4 + or al, r10b + mov edi, eax + shl r9b, 3 + or r9b, r8b + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, dil + shl r11b, 4 + or r11b, r9b + shl r12b, 5 + or r12b, r11b + movzx edi, byte ptr [rsp + 224] # 1-byte Folded Reload + shl dil, 6 + shl dl, 7 + or dl, dil + or bl, al + or dl, r12b + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 96] # 1-byte Folded Reload + mov edi, eax + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 2 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 3 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 4 + or al, dil + mov edi, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, dil + mov byte ptr [r12], bl + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + shl r15b, 7 + or r15b, bl + mov byte ptr [r12 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl cl, 7 + or cl, dl + or cl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], cl + add rsi, 128 + add r12, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB4_109 +# %bb.110: + mov r14, qword ptr [rsp + 144] # 8-byte Reload + mov rax, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_111: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB4_208 +# %bb.112: + or rax, 1 + cmp r14, rax + jne .LBB4_175 +.LBB4_113: xor r11d, r11d - .p2align 4, 0x90 -.LBB4_169: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - setne al - neg al - mov rdi, r11 - shr rdi, 3 - mov r14, r12 - movzx r9d, byte ptr [r12 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r12 + rdi], bl - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] - setne al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r12 + rdi], dl - cmp r10, r11 - jne .LBB4_169 -.LBB4_170: - test r8b, 1 - je .LBB4_174 -# %bb.171: - cmp qword ptr [rsi], r13 -.LBB4_172: - setne al - neg al - mov rdx, r11 - shr rdx, 3 - mov sil, byte ptr [r12 + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, sil - and bl, al - xor bl, sil -.LBB4_173: - mov byte ptr [r12 + rdx], bl -.LBB4_174: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.LBB4_175: - mov r9, r8 - and r9, -2 + jmp .LBB4_177 +.LBB4_114: + mov r13, rsi + jmp .LBB4_122 +.LBB4_115: + mov r13, r12 + mov rbx, rsi +.LBB4_116: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB4_208 +# %bb.117: + movd xmm0, r15d + or rcx, 1 + cmp r14, rcx + jne .LBB4_199 +# %bb.118: xor esi, esi - mov r14, r15 - .p2align 4, 0x90 -.LBB4_176: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rbx] - setp cl - setne dl - or dl, cl - neg dl + jmp .LBB4_201 +.LBB4_119: mov rdi, rsi - shr rdi, 3 - movzx r10d, byte ptr [r14 + rdi] - mov ecx, esi - and cl, 6 - mov r11b, 1 - shl r11b, cl - xor dl, r10b - and r11b, dl - xor r11b, r10b - mov byte ptr [r14 + rdi], r11b - add rsi, 2 - ucomiss xmm0, dword ptr [rbx + 4] - lea rbx, [rbx + 8] - setp r10b - setne dl - or dl, r10b - neg dl - xor dl, r11b - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, r11b - mov byte ptr [r14 + rdi], al - cmp r9, rsi - jne .LBB4_176 -.LBB4_177: - test r8b, 1 - je .LBB4_174 -# %bb.178: - ucomiss xmm0, dword ptr [rbx] - setp al - setne dl - or dl, al - neg dl - mov rax, rsi - shr rax, 3 - mov dil, byte ptr [r15 + rax] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor dl, dil - and bl, dl - xor bl, dil - mov byte ptr [r15 + rax], bl - jmp .LBB4_174 -.LBB4_179: - and r10, -16 - mov rax, r10 + jmp .LBB4_163 +.LBB4_120: + mov r13, rsi + sub r14, r8 + je .LBB4_208 +.LBB4_121: + add r12, 1 +.LBB4_122: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB4_130 +# %bb.123: + cmp rcx, 16 + mov byte ptr [rsp + 8], r15b # 1-byte Spill + mov qword ptr [rsp + 144], r14 # 8-byte Spill + mov qword ptr [rsp + 264], rcx # 8-byte Spill + jb .LBB4_126 +# %bb.124: + mov rax, rcx shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 304], rax # 8-byte Spill - mov qword ptr [rsp + 216], r10 # 8-byte Spill - lea rax, [r12 + 4*r10] - mov qword ptr [rsp + 104], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill + add rax, r13 + cmp r12, rax + jae .LBB4_212 +# %bb.125: + lea rax, [r12 + 4*rcx] + cmp r13, rax + jae .LBB4_212 +.LBB4_126: xor eax, eax - mov qword ptr [rsp + 128], r12 # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 160], r12 # 8-byte Spill +.LBB4_127: + sub rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov qword ptr [rsp + 176], rcx # 8-byte Spill + mov rdi, qword ptr [rsp + 160] # 8-byte Reload .p2align 4, 0x90 -.LBB4_180: # =>This Inner Loop Header: Depth=1 - mov r9, rax - mov qword ptr [rsp + 152], rax # 8-byte Spill - mov rcx, rax - shl rcx, 5 - mov r11, rcx - mov r8, rcx - mov r14, rcx - mov r13, rcx - mov rbx, rcx - mov r12, rcx - mov r15, rcx - mov rdi, rcx - mov r9, rcx - mov qword ptr [rsp + 48], rcx # 8-byte Spill - mov rax, rcx - mov rdx, rcx - movzx ecx, byte ptr [rsi + rcx] - movd xmm4, ecx - movzx ecx, byte ptr [rsi + rdx + 1] - movd xmm3, ecx - movzx ecx, byte ptr [rsi + rdx + 2] - movd xmm5, ecx - movzx ecx, byte ptr [rsi + rdx + 3] - movd xmm7, ecx - movzx ecx, byte ptr [rsi + rdx + 4] - movd xmm1, ecx - movzx ecx, byte ptr [rsi + rdx + 5] - movd xmm2, ecx - movzx ecx, byte ptr [rsi + rdx + 6] - movd xmm8, ecx - movzx ecx, byte ptr [rsi + rdx + 7] - movd xmm14, ecx - movzx ecx, byte ptr [rsi + rdx + 8] - movd xmm9, ecx - movzx ecx, byte ptr [rsi + rdx + 9] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdx + 10] - movd xmm12, ecx - movzx ecx, byte ptr [rsi + rdx + 11] - movd xmm13, ecx - movzx ecx, byte ptr [rsi + rdx + 12] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdx + 13] - movd xmm11, ecx - movzx ecx, byte ptr [rsi + rdx + 14] - movd xmm15, ecx - movzx ecx, byte ptr [rsi + rdx + 15] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill - mov qword ptr [rsp + 32], rdx # 8-byte Spill - mov rcx, rdx - or rcx, 32 - mov qword ptr [rsp + 24], rcx # 8-byte Spill - or r11, 64 - mov qword ptr [rsp + 112], r11 # 8-byte Spill - or r8, 96 - mov qword ptr [rsp + 64], r8 # 8-byte Spill - or r14, 128 - or r13, 160 - mov r10, rbx - or r10, 192 - mov qword ptr [rsp + 72], r10 # 8-byte Spill - or r12, 224 - or r15, 256 - or rdi, 288 - mov qword ptr [rsp + 224], rdi # 8-byte Spill - or r9, 320 - mov qword ptr [rsp + 40], r9 # 8-byte Spill - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - or rbx, 352 - mov qword ptr [rsp + 48], rbx # 8-byte Spill - or rax, 384 - mov qword ptr [rsp + 80], rax # 8-byte Spill - mov rax, rdx - or rax, 416 - mov rcx, rdx - or rcx, 448 - mov qword ptr [rsp + 16], rcx # 8-byte Spill - mov rcx, rdx - or rcx, 480 - mov qword ptr [rsp + 56], rcx # 8-byte Spill - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx], 1 - pinsrb xmm4, byte ptr [rsi + r11], 2 - pinsrb xmm4, byte ptr [rsi + r8], 3 - pinsrb xmm4, byte ptr [rsi + r14], 4 - pinsrb xmm4, byte ptr [rsi + r13], 5 - pinsrb xmm4, byte ptr [rsi + r10], 6 - pinsrb xmm4, byte ptr [rsi + r12], 7 - pinsrb xmm4, byte ptr [rsi + r15], 8 - pinsrb xmm4, byte ptr [rsi + rdi], 9 - pinsrb xmm4, byte ptr [rsi + r9], 10 - pinsrb xmm4, byte ptr [rsi + rbx], 11 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx], 12 - pinsrb xmm4, byte ptr [rsi + rax], 13 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rbx], 14 - pinsrb xmm4, byte ptr [rsi + rcx], 15 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rbx + 1], 1 - pinsrb xmm3, byte ptr [rsi + r11 + 1], 2 - pinsrb xmm3, byte ptr [rsi + r8 + 1], 3 - pinsrb xmm3, byte ptr [rsi + r14 + 1], 4 - pinsrb xmm3, byte ptr [rsi + r13 + 1], 5 - mov r11, r13 - pinsrb xmm3, byte ptr [rsi + r10 + 1], 6 - pinsrb xmm3, byte ptr [rsi + r12 + 1], 7 - mov r13, r12 - pinsrb xmm3, byte ptr [rsi + r15 + 1], 8 - pinsrb xmm3, byte ptr [rsi + rdi + 1], 9 - pinsrb xmm3, byte ptr [rsi + r9 + 1], 10 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r12 + 1], 11 - pinsrb xmm3, byte ptr [rsi + rdx + 1], 12 - pinsrb xmm3, byte ptr [rsi + rax + 1], 13 - mov r8, rax - mov qword ptr [rsp + 88], rax # 8-byte Spill - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rax + 1], 14 - movdqa xmm6, xmmword ptr [rsp + 288] # 16-byte Reload - pcmpeqb xmm4, xmm6 - pinsrb xmm3, byte ptr [rsi + rcx + 1], 15 - pcmpeqb xmm3, xmm6 - movdqa xmm0, xmmword ptr [rip + .LCPI4_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] - pandn xmm3, xmm0 - paddb xmm3, xmm4 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 16] - movd xmm10, edx - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 2], 1 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r10 + 2], 2 - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdi + 2], 3 - pinsrb xmm5, byte ptr [rsi + r14 + 2], 4 - pinsrb xmm5, byte ptr [rsi + r11 + 2], 5 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r9 + 2], 6 - mov rbx, r13 - pinsrb xmm5, byte ptr [rsi + r13 + 2], 7 - pinsrb xmm5, byte ptr [rsi + r15 + 2], 8 - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 2], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 2], 10 - pinsrb xmm5, byte ptr [rsi + r12 + 2], 11 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rcx + 2], 12 - pinsrb xmm5, byte ptr [rsi + r8 + 2], 13 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r13 + 2], 14 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r8 + 2], 15 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 3], 1 - pinsrb xmm7, byte ptr [rsi + r10 + 3], 2 - pinsrb xmm7, byte ptr [rsi + rdi + 3], 3 - pinsrb xmm7, byte ptr [rsi + r14 + 3], 4 - pinsrb xmm7, byte ptr [rsi + r11 + 3], 5 - pinsrb xmm7, byte ptr [rsi + r9 + 3], 6 - pinsrb xmm7, byte ptr [rsi + rbx + 3], 7 - pinsrb xmm7, byte ptr [rsi + r15 + 3], 8 - pinsrb xmm7, byte ptr [rsi + rdx + 3], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 3], 10 - pinsrb xmm7, byte ptr [rsi + r12 + 3], 11 - pinsrb xmm7, byte ptr [rsi + rcx + 3], 12 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 3], 13 - pinsrb xmm7, byte ptr [rsi + r13 + 3], 14 - pinsrb xmm7, byte ptr [rsi + r8 + 3], 15 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rax + 4], 1 - pinsrb xmm1, byte ptr [rsi + r10 + 4], 2 - pinsrb xmm1, byte ptr [rsi + rdi + 4], 3 - pinsrb xmm1, byte ptr [rsi + r14 + 4], 4 - pinsrb xmm1, byte ptr [rsi + r11 + 4], 5 - mov rax, r11 - mov qword ptr [rsp + 136], r11 # 8-byte Spill - pinsrb xmm1, byte ptr [rsi + r9 + 4], 6 - pinsrb xmm1, byte ptr [rsi + rbx + 4], 7 - mov rdi, rbx - pinsrb xmm1, byte ptr [rsi + r15 + 4], 8 - pinsrb xmm1, byte ptr [rsi + rdx + 4], 9 - mov rbx, rdx - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rdx + 4], 10 - pinsrb xmm1, byte ptr [rsi + r12 + 4], 11 - pinsrb xmm1, byte ptr [rsi + rcx + 4], 12 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r11 + 4], 13 - pinsrb xmm1, byte ptr [rsi + r13 + 4], 14 - pinsrb xmm1, byte ptr [rsi + r8 + 4], 15 - pcmpeqb xmm5, xmm6 - movdqa xmm0, xmmword ptr [rip + .LCPI4_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm5, xmm0 - pcmpeqb xmm7, xmm6 - movdqa xmm0, xmmword ptr [rip + .LCPI4_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm7, xmm0 - por xmm7, xmm5 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - movzx edx, byte ptr [rsi + rcx + 17] - movd xmm4, edx - pcmpeqb xmm1, xmm6 - movdqa xmm0, xmmword ptr [rip + .LCPI4_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm1, xmm0 - por xmm1, xmm7 - movzx edx, byte ptr [rsi + rcx + 18] - movd xmm7, edx - pcmpeqd xmm0, xmm0 - psubb xmm3, xmm0 - por xmm1, xmm3 - movzx edx, byte ptr [rsi + rcx + 19] - movd xmm5, edx - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdx + 5], 1 - pinsrb xmm2, byte ptr [rsi + r10 + 5], 2 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 5], 3 - mov qword ptr [rsp + 120], r14 # 8-byte Spill - pinsrb xmm2, byte ptr [rsi + r14 + 5], 4 - pinsrb xmm2, byte ptr [rsi + rax + 5], 5 - mov r12, r9 - pinsrb xmm2, byte ptr [rsi + r9 + 5], 6 +.LBB4_128: # =>This Inner Loop Header: Depth=1 + mov rcx, r13 + cmp byte ptr [r13], r15b + setne byte ptr [rsp + 240] # 1-byte Folded Spill + cmp byte ptr [r13 + 1], r15b + setne sil + cmp byte ptr [r13 + 2], r15b + mov eax, r15d + setne r15b + cmp byte ptr [r13 + 3], al + setne byte ptr [rsp + 136] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [r13 + 4], al + setne byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [r13 + 5], al + setne byte ptr [rsp + 64] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [r13 + 6], al + setne r13b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 7], al + setne r9b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 8], al + setne byte ptr [rsp + 128] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 9], al + setne dl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 10], al + setne r8b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 11], al + setne r10b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 12], al + setne r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 13], al + setne byte ptr [rsp + 152] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 14], al + setne byte ptr [rsp + 224] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 15], al + setne r12b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 16], bl + setne byte ptr [rsp + 208] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 17], bl + setne byte ptr [rsp + 192] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 18], bl + setne byte ptr [rsp + 88] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 19], bl + setne byte ptr [rsp + 96] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 20], bl + setne byte ptr [rsp + 104] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 21], bl + setne byte ptr [rsp + 80] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 22], bl + setne byte ptr [rsp + 72] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 23], bl + setne r11b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 24], bl + setne byte ptr [rsp + 56] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 25], bl + setne byte ptr [rsp + 40] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 26], bl + setne byte ptr [rsp + 48] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 27], bl + setne byte ptr [rsp + 32] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 28], bl + setne byte ptr [rsp + 16] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 29], bl + setne byte ptr [rsp + 24] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 30], bl + setne byte ptr [rsp + 120] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 31], bl + setne bl + add sil, sil + add sil, byte ptr [rsp + 240] # 1-byte Folded Reload + shl r13b, 6 + shl r9b, 7 + or r9b, r13b + shl r15b, 2 + or r15b, sil + add dl, dl + add dl, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 3 + or al, r15b + shl r8b, 2 + or r8b, dl + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, al + mov esi, edx + movzx r15d, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r10b, 3 + or r10b, r8b + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + shl r14b, 4 + or r14b, r10b + movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 224] # 1-byte Folded Reload + shl sil, 6 + shl r12b, 7 + or r12b, sil + or r9b, dl + or r12b, al + movzx edx, byte ptr [rsp + 192] # 1-byte Folded Reload + add dl, dl + add dl, byte ptr [rsp + 208] # 1-byte Folded Reload + mov esi, edx + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 2 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov byte ptr [rdi], r9b + movzx esi, byte ptr [rsp + 72] # 1-byte Folded Reload + shl sil, 6 + shl r11b, 7 + or r11b, sil + mov byte ptr [rdi + 1], r12b + or r11b, dl + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 56] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r11b + mov byte ptr [rdi + 3], bl + lea r13, [rcx + 32] + add rdi, 4 + add qword ptr [rsp + 176], -1 # 8-byte Folded Spill + jne .LBB4_128 +# %bb.129: mov qword ptr [rsp + 160], rdi # 8-byte Spill - pinsrb xmm2, byte ptr [rsi + rdi + 5], 7 - pinsrb xmm2, byte ptr [rsi + r15 + 5], 8 - mov r9, rbx - pinsrb xmm2, byte ptr [rsi + rbx + 5], 9 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 5], 10 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 5], 11 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r13 + 5], 12 - mov r8, r11 - pinsrb xmm2, byte ptr [rsi + r11 + 5], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 5], 14 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r11 + 5], 15 - pinsrb xmm8, byte ptr [rsi + rdx + 6], 1 - pinsrb xmm8, byte ptr [rsi + r10 + 6], 2 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rbx + 6], 3 - pinsrb xmm8, byte ptr [rsi + r14 + 6], 4 - mov rbx, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rbx + 6], 5 - pinsrb xmm8, byte ptr [rsi + r12 + 6], 6 - pinsrb xmm8, byte ptr [rsi + rdi + 6], 7 - pinsrb xmm8, byte ptr [rsi + r15 + 6], 8 - pinsrb xmm8, byte ptr [rsi + r9 + 6], 9 - pinsrb xmm8, byte ptr [rsi + rax + 6], 10 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rbx + 6], 11 - pinsrb xmm8, byte ptr [rsi + r13 + 6], 12 - pinsrb xmm8, byte ptr [rsi + r8 + 6], 13 - pinsrb xmm8, byte ptr [rsi + rcx + 6], 14 - pinsrb xmm8, byte ptr [rsi + r11 + 6], 15 - mov rcx, r11 - pinsrb xmm14, byte ptr [rsi + rdx + 7], 1 - pinsrb xmm14, byte ptr [rsi + r10 + 7], 2 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 7], 3 - pinsrb xmm14, byte ptr [rsi + r14 + 7], 4 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r11 + 7], 5 - pinsrb xmm14, byte ptr [rsi + r12 + 7], 6 - pinsrb xmm14, byte ptr [rsi + rdi + 7], 7 - pinsrb xmm14, byte ptr [rsi + r15 + 7], 8 - mov r12, r15 - mov qword ptr [rsp + 96], r15 # 8-byte Spill - pinsrb xmm14, byte ptr [rsi + r9 + 7], 9 - pinsrb xmm14, byte ptr [rsi + rax + 7], 10 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rbx + 7], 11 - pinsrb xmm14, byte ptr [rsi + r13 + 7], 12 - mov r14, r13 - mov rdi, r8 - pinsrb xmm14, byte ptr [rsi + r8 + 7], 13 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r13 + 7], 14 - pcmpeqb xmm2, xmm6 - movdqa xmm0, xmmword ptr [rip + .LCPI4_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm0 - pcmpeqb xmm8, xmm6 - movdqa xmm0, xmmword ptr [rip + .LCPI4_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm8, xmm0 - por xmm8, xmm2 - mov r9, qword ptr [rsp + 32] # 8-byte Reload - movzx edx, byte ptr [rsi + r9 + 20] - movd xmm3, edx - mov rax, rcx - pinsrb xmm14, byte ptr [rsi + rcx + 7], 15 - pcmpeqb xmm14, xmm6 - movdqa xmm0, xmmword ptr [rip + .LCPI4_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm14, xmm0 - por xmm14, xmm8 - movzx edx, byte ptr [rsi + r9 + 21] - movd xmm2, edx - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rcx + 8], 1 - pinsrb xmm9, byte ptr [rsi + r10 + 8], 2 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r8 + 8], 3 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdx + 8], 4 - pinsrb xmm9, byte ptr [rsi + r11 + 8], 5 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdx + 8], 6 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r15 + 8], 7 - pinsrb xmm9, byte ptr [rsi + r12 + 8], 8 - mov r12, qword ptr [rsp + 224] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r12 + 8], 9 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdx + 8], 10 - pinsrb xmm9, byte ptr [rsi + rbx + 8], 11 - pinsrb xmm9, byte ptr [rsi + r14 + 8], 12 - pinsrb xmm9, byte ptr [rsi + rdi + 8], 13 - pinsrb xmm9, byte ptr [rsi + r13 + 8], 14 - pinsrb xmm9, byte ptr [rsi + rax + 8], 15 - por xmm14, xmm1 - movdqa xmmword ptr [rsp + 272], xmm14 # 16-byte Spill - movzx edx, byte ptr [rsi + r9 + 22] - movd xmm1, edx - movdqa xmm0, xmm6 - pcmpeqb xmm9, xmm6 - movdqa xmm14, xmmword ptr [rsp + 192] # 16-byte Reload - pinsrb xmm14, byte ptr [rsi + rcx + 9], 1 - pinsrb xmm14, byte ptr [rsi + r10 + 9], 2 - pinsrb xmm14, byte ptr [rsi + r8 + 9], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 9], 4 - pinsrb xmm14, byte ptr [rsi + r11 + 9], 5 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 9], 6 - mov rdi, r15 - pinsrb xmm14, byte ptr [rsi + r15 + 9], 7 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r15 + 9], 8 - mov r9, r12 - pinsrb xmm14, byte ptr [rsi + r12 + 9], 9 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r13 + 9], 10 - pinsrb xmm14, byte ptr [rsi + rbx + 9], 11 - mov r12, r14 - pinsrb xmm14, byte ptr [rsi + r14 + 9], 12 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r14 + 9], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 9], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 9], 15 - mov r10, rcx - pinsrb xmm12, byte ptr [rsi + rcx + 10], 1 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rcx + 10], 2 - pinsrb xmm12, byte ptr [rsi + r8 + 10], 3 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rcx + 10], 4 - pinsrb xmm12, byte ptr [rsi + r11 + 10], 5 - pinsrb xmm12, byte ptr [rsi + rdx + 10], 6 - pinsrb xmm12, byte ptr [rsi + rdi + 10], 7 - pinsrb xmm12, byte ptr [rsi + r15 + 10], 8 - pinsrb xmm12, byte ptr [rsi + r9 + 10], 9 - pinsrb xmm12, byte ptr [rsi + r13 + 10], 10 - pinsrb xmm12, byte ptr [rsi + rbx + 10], 11 - pinsrb xmm12, byte ptr [rsi + r12 + 10], 12 - pinsrb xmm12, byte ptr [rsi + r14 + 10], 13 - mov r14, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r14 + 10], 14 - pinsrb xmm12, byte ptr [rsi + rax + 10], 15 - pinsrb xmm13, byte ptr [rsi + r10 + 11], 1 - mov r10, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r10 + 11], 2 - pinsrb xmm13, byte ptr [rsi + r8 + 11], 3 - pinsrb xmm13, byte ptr [rsi + rcx + 11], 4 - pinsrb xmm13, byte ptr [rsi + r11 + 11], 5 - pinsrb xmm13, byte ptr [rsi + rdx + 11], 6 - pinsrb xmm13, byte ptr [rsi + rdi + 11], 7 - pinsrb xmm13, byte ptr [rsi + r15 + 11], 8 - pinsrb xmm13, byte ptr [rsi + r9 + 11], 9 - pinsrb xmm13, byte ptr [rsi + r13 + 11], 10 - pinsrb xmm13, byte ptr [rsi + rbx + 11], 11 - mov r15, rbx - pinsrb xmm13, byte ptr [rsi + r12 + 11], 12 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r13 + 11], 13 - pinsrb xmm13, byte ptr [rsi + r14 + 11], 14 - pinsrb xmm13, byte ptr [rsi + rax + 11], 15 - pcmpeqb xmm14, xmm6 - pandn xmm14, xmmword ptr [rip + .LCPI4_16] - paddb xmm14, xmm9 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 23] - movd xmm8, edx - pcmpeqb xmm12, xmm6 - pandn xmm12, xmmword ptr [rip + .LCPI4_17] - pcmpeqb xmm13, xmm6 - pandn xmm13, xmmword ptr [rip + .LCPI4_18] - por xmm13, xmm12 - movzx edx, byte ptr [rsi + rax + 24] - movd xmm12, edx - movdqa xmm9, xmmword ptr [rsp + 240] # 16-byte Reload - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rax + 12], 1 - pinsrb xmm9, byte ptr [rsi + r10 + 12], 2 - mov rax, r8 - pinsrb xmm9, byte ptr [rsi + r8 + 12], 3 - mov r14, rcx - pinsrb xmm9, byte ptr [rsi + rcx + 12], 4 - mov r8, r11 - pinsrb xmm9, byte ptr [rsi + r11 + 12], 5 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r11 + 12], 6 - mov rbx, rdi - pinsrb xmm9, byte ptr [rsi + rdi + 12], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rcx + 12], 8 - pinsrb xmm9, byte ptr [rsi + r9 + 12], 9 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdi + 12], 10 - pinsrb xmm9, byte ptr [rsi + r15 + 12], 11 - pinsrb xmm9, byte ptr [rsi + r12 + 12], 12 - pinsrb xmm9, byte ptr [rsi + r13 + 12], 13 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdx + 12], 14 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdx + 12], 15 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 13], 1 - pinsrb xmm11, byte ptr [rsi + r10 + 13], 2 - pinsrb xmm11, byte ptr [rsi + rax + 13], 3 - pinsrb xmm11, byte ptr [rsi + r14 + 13], 4 - pinsrb xmm11, byte ptr [rsi + r8 + 13], 5 - pinsrb xmm11, byte ptr [rsi + r11 + 13], 6 - pinsrb xmm11, byte ptr [rsi + rbx + 13], 7 - pinsrb xmm11, byte ptr [rsi + rcx + 13], 8 - pinsrb xmm11, byte ptr [rsi + r9 + 13], 9 - pinsrb xmm11, byte ptr [rsi + rdi + 13], 10 - pinsrb xmm11, byte ptr [rsi + r15 + 13], 11 - pinsrb xmm11, byte ptr [rsi + r12 + 13], 12 - pinsrb xmm11, byte ptr [rsi + r13 + 13], 13 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 13], 14 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 13], 15 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx + 14], 1 - pinsrb xmm15, byte ptr [rsi + r10 + 14], 2 - pinsrb xmm15, byte ptr [rsi + rax + 14], 3 - pinsrb xmm15, byte ptr [rsi + r14 + 14], 4 - pinsrb xmm15, byte ptr [rsi + r8 + 14], 5 - pinsrb xmm15, byte ptr [rsi + r11 + 14], 6 - pinsrb xmm15, byte ptr [rsi + rbx + 14], 7 - pinsrb xmm15, byte ptr [rsi + rcx + 14], 8 - pinsrb xmm15, byte ptr [rsi + r9 + 14], 9 - pinsrb xmm15, byte ptr [rsi + rdi + 14], 10 - pinsrb xmm15, byte ptr [rsi + r15 + 14], 11 - pinsrb xmm15, byte ptr [rsi + r12 + 14], 12 - pinsrb xmm15, byte ptr [rsi + r13 + 14], 13 - mov r15, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r15 + 14], 14 - pcmpeqb xmm9, xmm6 - pandn xmm9, xmmword ptr [rip + .LCPI4_19] - por xmm9, xmm13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - movzx edx, byte ptr [rsi + rcx + 25] - movd xmm13, edx - psubb xmm14, xmmword ptr [rip + .LCPI4_22] - por xmm9, xmm14 - movzx edx, byte ptr [rsi + rcx + 26] - movd xmm0, edx - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rax + 14], 15 - pcmpeqb xmm11, xmm6 - pandn xmm11, xmmword ptr [rip + .LCPI4_20] - pcmpeqb xmm15, xmm6 - movdqa xmm14, xmm6 - pandn xmm15, xmmword ptr [rip + .LCPI4_21] - por xmm15, xmm11 - movzx edx, byte ptr [rsi + rcx + 27] - movd xmm11, edx - movdqa xmm6, xmmword ptr [rsp + 176] # 16-byte Reload - mov r11, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r11 + 15], 1 - pinsrb xmm6, byte ptr [rsi + r10 + 15], 2 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 15], 3 - pinsrb xmm6, byte ptr [rsi + r14 + 15], 4 - pinsrb xmm6, byte ptr [rsi + r8 + 15], 5 - mov r12, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r12 + 15], 6 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 15], 7 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 15], 8 - pinsrb xmm6, byte ptr [rsi + r9 + 15], 9 - pinsrb xmm6, byte ptr [rsi + rdi + 15], 10 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 15], 11 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r14 + 15], 12 - pinsrb xmm6, byte ptr [rsi + r13 + 15], 13 - pinsrb xmm6, byte ptr [rsi + r15 + 15], 14 - pinsrb xmm6, byte ptr [rsi + rax + 15], 15 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmmword ptr [rip + .LCPI4_6] - por xmm6, xmm15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 28] - movd xmm15, edx - por xmm6, xmm9 - movdqa xmmword ptr [rsp + 176], xmm6 # 16-byte Spill - movzx edx, byte ptr [rsi + rax + 29] - movd xmm9, edx - pinsrb xmm10, byte ptr [rsi + r11 + 16], 1 - pinsrb xmm10, byte ptr [rsi + r10 + 16], 2 - pinsrb xmm10, byte ptr [rsi + rbx + 16], 3 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r13 + 16], 4 - pinsrb xmm10, byte ptr [rsi + r8 + 16], 5 - pinsrb xmm10, byte ptr [rsi + r12 + 16], 6 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r12 + 16], 7 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdx + 16], 8 - pinsrb xmm10, byte ptr [rsi + r9 + 16], 9 - pinsrb xmm10, byte ptr [rsi + rdi + 16], 10 - pinsrb xmm10, byte ptr [rsi + rcx + 16], 11 - pinsrb xmm10, byte ptr [rsi + r14 + 16], 12 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r14 + 16], 13 - pinsrb xmm10, byte ptr [rsi + r15 + 16], 14 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rax + 16], 15 - pinsrb xmm4, byte ptr [rsi + r11 + 17], 1 - pinsrb xmm4, byte ptr [rsi + r10 + 17], 2 - pinsrb xmm4, byte ptr [rsi + rbx + 17], 3 - mov r10, r13 - pinsrb xmm4, byte ptr [rsi + r13 + 17], 4 - pinsrb xmm4, byte ptr [rsi + r8 + 17], 5 - mov r11, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r11 + 17], 6 - mov rbx, r12 - pinsrb xmm4, byte ptr [rsi + r12 + 17], 7 - pinsrb xmm4, byte ptr [rsi + rdx + 17], 8 - pinsrb xmm4, byte ptr [rsi + r9 + 17], 9 - pinsrb xmm4, byte ptr [rsi + rdi + 17], 10 - pinsrb xmm4, byte ptr [rsi + rcx + 17], 11 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 17], 12 - mov r13, r14 - pinsrb xmm4, byte ptr [rsi + r14 + 17], 13 - pinsrb xmm4, byte ptr [rsi + r15 + 17], 14 - mov r12, r15 - pinsrb xmm4, byte ptr [rsi + rax + 17], 15 - mov r15, rax - movdqa xmm6, xmm14 - pcmpeqb xmm10, xmm14 - pcmpeqb xmm4, xmm14 - pandn xmm4, xmmword ptr [rip + .LCPI4_16] - paddb xmm4, xmm10 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - movzx edx, byte ptr [rsi + rdi + 30] - movd xmm10, edx - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 18], 1 - pinsrb xmm5, byte ptr [rsi + rax + 19], 1 - pinsrb xmm3, byte ptr [rsi + rax + 20], 1 - pinsrb xmm2, byte ptr [rsi + rax + 21], 1 - pinsrb xmm1, byte ptr [rsi + rax + 22], 1 - pinsrb xmm8, byte ptr [rsi + rax + 23], 1 - pinsrb xmm12, byte ptr [rsi + rax + 24], 1 - pinsrb xmm13, byte ptr [rsi + rax + 25], 1 - pinsrb xmm0, byte ptr [rsi + rax + 26], 1 - pinsrb xmm11, byte ptr [rsi + rax + 27], 1 - pinsrb xmm15, byte ptr [rsi + rax + 28], 1 - pinsrb xmm9, byte ptr [rsi + rax + 29], 1 - pinsrb xmm10, byte ptr [rsi + rax + 30], 1 - movzx edx, byte ptr [rsi + rdi + 31] - movd xmm6, edx - pinsrb xmm6, byte ptr [rsi + rax + 31], 1 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 18], 2 - pinsrb xmm5, byte ptr [rsi + rdx + 19], 2 - pinsrb xmm3, byte ptr [rsi + rdx + 20], 2 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 2 - pinsrb xmm1, byte ptr [rsi + rdx + 22], 2 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 2 - pinsrb xmm12, byte ptr [rsi + rdx + 24], 2 - pinsrb xmm13, byte ptr [rsi + rdx + 25], 2 - pinsrb xmm0, byte ptr [rsi + rdx + 26], 2 - pinsrb xmm11, byte ptr [rsi + rdx + 27], 2 - pinsrb xmm15, byte ptr [rsi + rdx + 28], 2 - pinsrb xmm9, byte ptr [rsi + rdx + 29], 2 - pinsrb xmm10, byte ptr [rsi + rdx + 30], 2 - pinsrb xmm6, byte ptr [rsi + rdx + 31], 2 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 18], 3 - mov r14, r10 - pinsrb xmm7, byte ptr [rsi + r10 + 18], 4 - pinsrb xmm7, byte ptr [rsi + r8 + 18], 5 - pinsrb xmm7, byte ptr [rsi + r11 + 18], 6 - pinsrb xmm7, byte ptr [rsi + rbx + 18], 7 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 18], 8 - pinsrb xmm7, byte ptr [rsi + r9 + 18], 9 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdi + 18], 10 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r10 + 18], 11 - pinsrb xmm7, byte ptr [rsi + rcx + 18], 12 - pinsrb xmm7, byte ptr [rsi + r13 + 18], 13 - pinsrb xmm7, byte ptr [rsi + r12 + 18], 14 - pinsrb xmm7, byte ptr [rsi + r15 + 18], 15 - pinsrb xmm5, byte ptr [rsi + rdx + 19], 3 - pinsrb xmm5, byte ptr [rsi + r14 + 19], 4 - pinsrb xmm5, byte ptr [rsi + r8 + 19], 5 - pinsrb xmm5, byte ptr [rsi + r11 + 19], 6 - pinsrb xmm5, byte ptr [rsi + rbx + 19], 7 - pinsrb xmm5, byte ptr [rsi + rax + 19], 8 - pinsrb xmm5, byte ptr [rsi + r9 + 19], 9 - pinsrb xmm5, byte ptr [rsi + rdi + 19], 10 - pinsrb xmm5, byte ptr [rsi + r10 + 19], 11 - pinsrb xmm5, byte ptr [rsi + rcx + 19], 12 - pinsrb xmm5, byte ptr [rsi + r13 + 19], 13 - pinsrb xmm5, byte ptr [rsi + r12 + 19], 14 - pinsrb xmm5, byte ptr [rsi + r15 + 19], 15 - pinsrb xmm3, byte ptr [rsi + rdx + 20], 3 - pinsrb xmm3, byte ptr [rsi + r14 + 20], 4 - pinsrb xmm3, byte ptr [rsi + r8 + 20], 5 - pinsrb xmm3, byte ptr [rsi + r11 + 20], 6 - pinsrb xmm3, byte ptr [rsi + rbx + 20], 7 - pinsrb xmm3, byte ptr [rsi + rax + 20], 8 - pinsrb xmm3, byte ptr [rsi + r9 + 20], 9 - pinsrb xmm3, byte ptr [rsi + rdi + 20], 10 - pinsrb xmm3, byte ptr [rsi + r10 + 20], 11 - pinsrb xmm3, byte ptr [rsi + rcx + 20], 12 - pinsrb xmm3, byte ptr [rsi + r13 + 20], 13 - pinsrb xmm3, byte ptr [rsi + r12 + 20], 14 - pcmpeqb xmm7, xmm14 - pandn xmm7, xmmword ptr [rip + .LCPI4_17] - pcmpeqb xmm5, xmm14 - pandn xmm5, xmmword ptr [rip + .LCPI4_18] - por xmm5, xmm7 - pinsrb xmm3, byte ptr [rsi + r15 + 20], 15 - pcmpeqb xmm3, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI4_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm3, xmm7 - por xmm3, xmm5 - pcmpeqd xmm5, xmm5 - psubb xmm4, xmm5 - por xmm3, xmm4 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 3 - pinsrb xmm2, byte ptr [rsi + r14 + 21], 4 - pinsrb xmm2, byte ptr [rsi + r8 + 21], 5 - pinsrb xmm2, byte ptr [rsi + r11 + 21], 6 - pinsrb xmm2, byte ptr [rsi + rbx + 21], 7 - pinsrb xmm2, byte ptr [rsi + rax + 21], 8 - pinsrb xmm2, byte ptr [rsi + r9 + 21], 9 - pinsrb xmm2, byte ptr [rsi + rdi + 21], 10 - pinsrb xmm2, byte ptr [rsi + r10 + 21], 11 - pinsrb xmm2, byte ptr [rsi + rcx + 21], 12 - pinsrb xmm2, byte ptr [rsi + r13 + 21], 13 - pinsrb xmm2, byte ptr [rsi + r12 + 21], 14 - pinsrb xmm2, byte ptr [rsi + r15 + 21], 15 - pinsrb xmm1, byte ptr [rsi + rdx + 22], 3 - pinsrb xmm1, byte ptr [rsi + r14 + 22], 4 - pinsrb xmm1, byte ptr [rsi + r8 + 22], 5 - pinsrb xmm1, byte ptr [rsi + r11 + 22], 6 - pinsrb xmm1, byte ptr [rsi + rbx + 22], 7 - pinsrb xmm1, byte ptr [rsi + rax + 22], 8 - pinsrb xmm1, byte ptr [rsi + r9 + 22], 9 - pinsrb xmm1, byte ptr [rsi + rdi + 22], 10 - pinsrb xmm1, byte ptr [rsi + r10 + 22], 11 - pinsrb xmm1, byte ptr [rsi + rcx + 22], 12 - pinsrb xmm1, byte ptr [rsi + r13 + 22], 13 - pinsrb xmm1, byte ptr [rsi + r12 + 22], 14 - pinsrb xmm1, byte ptr [rsi + r15 + 22], 15 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 3 - pinsrb xmm8, byte ptr [rsi + r14 + 23], 4 - pinsrb xmm8, byte ptr [rsi + r8 + 23], 5 - pinsrb xmm8, byte ptr [rsi + r11 + 23], 6 - pinsrb xmm8, byte ptr [rsi + rbx + 23], 7 - pinsrb xmm8, byte ptr [rsi + rax + 23], 8 - pinsrb xmm8, byte ptr [rsi + r9 + 23], 9 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 10 - pinsrb xmm8, byte ptr [rsi + r10 + 23], 11 - pinsrb xmm8, byte ptr [rsi + rcx + 23], 12 - pinsrb xmm8, byte ptr [rsi + r13 + 23], 13 - pinsrb xmm8, byte ptr [rsi + r12 + 23], 14 - movdqa xmm4, xmm14 - pcmpeqb xmm2, xmm14 - movdqa xmm5, xmmword ptr [rip + .LCPI4_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm5 - pcmpeqb xmm1, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI4_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm1, xmm7 - por xmm1, xmm2 - pinsrb xmm8, byte ptr [rsi + r15 + 23], 15 - pcmpeqb xmm8, xmm14 - movdqa xmm2, xmm14 - movdqa xmm4, xmmword ptr [rip + .LCPI4_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm8, xmm4 - por xmm8, xmm1 - pinsrb xmm12, byte ptr [rsi + rdx + 24], 3 - pinsrb xmm12, byte ptr [rsi + r14 + 24], 4 - pinsrb xmm12, byte ptr [rsi + r8 + 24], 5 - pinsrb xmm12, byte ptr [rsi + r11 + 24], 6 - pinsrb xmm12, byte ptr [rsi + rbx + 24], 7 - pinsrb xmm12, byte ptr [rsi + rax + 24], 8 - pinsrb xmm12, byte ptr [rsi + r9 + 24], 9 - pinsrb xmm12, byte ptr [rsi + rdi + 24], 10 - pinsrb xmm12, byte ptr [rsi + r10 + 24], 11 - pinsrb xmm12, byte ptr [rsi + rcx + 24], 12 - pinsrb xmm12, byte ptr [rsi + r13 + 24], 13 - pinsrb xmm12, byte ptr [rsi + r12 + 24], 14 - pinsrb xmm12, byte ptr [rsi + r15 + 24], 15 - por xmm8, xmm3 - pcmpeqb xmm12, xmm14 - pinsrb xmm13, byte ptr [rsi + rdx + 25], 3 - pinsrb xmm13, byte ptr [rsi + r14 + 25], 4 - pinsrb xmm13, byte ptr [rsi + r8 + 25], 5 - pinsrb xmm13, byte ptr [rsi + r11 + 25], 6 - pinsrb xmm13, byte ptr [rsi + rbx + 25], 7 - pinsrb xmm13, byte ptr [rsi + rax + 25], 8 - pinsrb xmm13, byte ptr [rsi + r9 + 25], 9 - pinsrb xmm13, byte ptr [rsi + rdi + 25], 10 - pinsrb xmm13, byte ptr [rsi + r10 + 25], 11 - pinsrb xmm13, byte ptr [rsi + rcx + 25], 12 - pinsrb xmm13, byte ptr [rsi + r13 + 25], 13 - pinsrb xmm13, byte ptr [rsi + r12 + 25], 14 - pinsrb xmm13, byte ptr [rsi + r15 + 25], 15 - pinsrb xmm0, byte ptr [rsi + rdx + 26], 3 - pinsrb xmm0, byte ptr [rsi + r14 + 26], 4 - pinsrb xmm0, byte ptr [rsi + r8 + 26], 5 - pinsrb xmm0, byte ptr [rsi + r11 + 26], 6 - pinsrb xmm0, byte ptr [rsi + rbx + 26], 7 - pinsrb xmm0, byte ptr [rsi + rax + 26], 8 - pinsrb xmm0, byte ptr [rsi + r9 + 26], 9 - pinsrb xmm0, byte ptr [rsi + rdi + 26], 10 - pinsrb xmm0, byte ptr [rsi + r10 + 26], 11 - pinsrb xmm0, byte ptr [rsi + rcx + 26], 12 - pinsrb xmm0, byte ptr [rsi + r13 + 26], 13 - pinsrb xmm0, byte ptr [rsi + r12 + 26], 14 - pinsrb xmm0, byte ptr [rsi + r15 + 26], 15 - pinsrb xmm11, byte ptr [rsi + rdx + 27], 3 - pinsrb xmm11, byte ptr [rsi + r14 + 27], 4 - pinsrb xmm11, byte ptr [rsi + r8 + 27], 5 - pinsrb xmm11, byte ptr [rsi + r11 + 27], 6 - pinsrb xmm11, byte ptr [rsi + rbx + 27], 7 - pinsrb xmm11, byte ptr [rsi + rax + 27], 8 - pinsrb xmm11, byte ptr [rsi + r9 + 27], 9 - pinsrb xmm11, byte ptr [rsi + rdi + 27], 10 - pinsrb xmm11, byte ptr [rsi + r10 + 27], 11 - pinsrb xmm11, byte ptr [rsi + rcx + 27], 12 - pinsrb xmm11, byte ptr [rsi + r13 + 27], 13 - pinsrb xmm11, byte ptr [rsi + r12 + 27], 14 - pcmpeqb xmm13, xmm14 - pandn xmm13, xmmword ptr [rip + .LCPI4_16] - paddb xmm13, xmm12 - pinsrb xmm11, byte ptr [rsi + r15 + 27], 15 - pcmpeqb xmm0, xmm14 - pandn xmm0, xmmword ptr [rip + .LCPI4_17] - pcmpeqb xmm11, xmm14 - pandn xmm11, xmmword ptr [rip + .LCPI4_18] - por xmm11, xmm0 - pinsrb xmm15, byte ptr [rsi + rdx + 28], 3 - pinsrb xmm9, byte ptr [rsi + rdx + 29], 3 - pinsrb xmm10, byte ptr [rsi + rdx + 30], 3 - pinsrb xmm6, byte ptr [rsi + rdx + 31], 3 - pinsrb xmm15, byte ptr [rsi + r14 + 28], 4 - pinsrb xmm9, byte ptr [rsi + r14 + 29], 4 - pinsrb xmm10, byte ptr [rsi + r14 + 30], 4 - pinsrb xmm6, byte ptr [rsi + r14 + 31], 4 - pinsrb xmm15, byte ptr [rsi + r8 + 28], 5 - pinsrb xmm9, byte ptr [rsi + r8 + 29], 5 - pinsrb xmm10, byte ptr [rsi + r8 + 30], 5 - pinsrb xmm6, byte ptr [rsi + r8 + 31], 5 - mov rdx, r11 - pinsrb xmm15, byte ptr [rsi + r11 + 28], 6 - pinsrb xmm9, byte ptr [rsi + r11 + 29], 6 - pinsrb xmm10, byte ptr [rsi + r11 + 30], 6 - pinsrb xmm6, byte ptr [rsi + r11 + 31], 6 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - mov rdx, rbx - pinsrb xmm15, byte ptr [rsi + rbx + 28], 7 - pinsrb xmm9, byte ptr [rsi + rbx + 29], 7 - pinsrb xmm10, byte ptr [rsi + rbx + 30], 7 - pinsrb xmm6, byte ptr [rsi + rbx + 31], 7 - pinsrb xmm15, byte ptr [rsi + rax + 28], 8 - pinsrb xmm9, byte ptr [rsi + rax + 29], 8 - pinsrb xmm10, byte ptr [rsi + rax + 30], 8 - pinsrb xmm6, byte ptr [rsi + rax + 31], 8 - pinsrb xmm15, byte ptr [rsi + r9 + 28], 9 - pinsrb xmm9, byte ptr [rsi + r9 + 29], 9 - pinsrb xmm10, byte ptr [rsi + r9 + 30], 9 - pinsrb xmm6, byte ptr [rsi + r9 + 31], 9 - pinsrb xmm15, byte ptr [rsi + rdi + 28], 10 - pinsrb xmm9, byte ptr [rsi + rdi + 29], 10 - pinsrb xmm10, byte ptr [rsi + rdi + 30], 10 - pinsrb xmm6, byte ptr [rsi + rdi + 31], 10 - mov rax, r10 - pinsrb xmm15, byte ptr [rsi + r10 + 28], 11 - pinsrb xmm9, byte ptr [rsi + r10 + 29], 11 - pinsrb xmm10, byte ptr [rsi + r10 + 30], 11 - pinsrb xmm6, byte ptr [rsi + r10 + 31], 11 - pinsrb xmm15, byte ptr [rsi + rcx + 28], 12 - pinsrb xmm9, byte ptr [rsi + rcx + 29], 12 - pinsrb xmm10, byte ptr [rsi + rcx + 30], 12 - pinsrb xmm6, byte ptr [rsi + rcx + 31], 12 - mov rax, r13 - pinsrb xmm15, byte ptr [rsi + r13 + 28], 13 - pinsrb xmm9, byte ptr [rsi + r13 + 29], 13 - pinsrb xmm10, byte ptr [rsi + r13 + 30], 13 - pinsrb xmm6, byte ptr [rsi + r13 + 31], 13 - mov rax, r12 - pinsrb xmm15, byte ptr [rsi + r12 + 28], 14 - pinsrb xmm9, byte ptr [rsi + r12 + 29], 14 - pinsrb xmm10, byte ptr [rsi + r12 + 30], 14 - pinsrb xmm6, byte ptr [rsi + r12 + 31], 14 - pinsrb xmm15, byte ptr [rsi + r15 + 28], 15 - pinsrb xmm9, byte ptr [rsi + r15 + 29], 15 - pinsrb xmm10, byte ptr [rsi + r15 + 30], 15 - pcmpeqb xmm15, xmm14 - pandn xmm15, xmmword ptr [rip + .LCPI4_19] - por xmm15, xmm11 - pinsrb xmm6, byte ptr [rsi + r15 + 31], 15 - psubb xmm13, xmmword ptr [rip + .LCPI4_22] - por xmm15, xmm13 - pcmpeqb xmm9, xmm14 - pandn xmm9, xmm5 - pcmpeqb xmm10, xmm14 - pandn xmm10, xmm7 - por xmm10, xmm9 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmm4 - por xmm6, xmm10 - por xmm6, xmm15 - movdqa xmm0, xmm8 - punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] - movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload - movdqa xmm1, xmm4 - movdqa xmm3, xmmword ptr [rsp + 176] # 16-byte Reload - punpcklbw xmm1, xmm3 # xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7] - movdqa xmm2, xmm1 - punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] - punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] - punpckhbw xmm4, xmm3 # xmm4 = xmm4[8],xmm3[8],xmm4[9],xmm3[9],xmm4[10],xmm3[10],xmm4[11],xmm3[11],xmm4[12],xmm3[12],xmm4[13],xmm3[13],xmm4[14],xmm3[14],xmm4[15],xmm3[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - movdqu xmmword ptr [r8 + 4*rcx + 48], xmm4 - movdqu xmmword ptr [r8 + 4*rcx + 32], xmm0 - movdqu xmmword ptr [r8 + 4*rcx + 16], xmm1 - movdqu xmmword ptr [r8 + 4*rcx], xmm2 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 216] # 8-byte Folded Reload - jne .LBB4_180 -# %bb.181: - mov r10, qword ptr [rsp + 264] # 8-byte Reload - cmp r10, qword ptr [rsp + 216] # 8-byte Folded Reload - mov r11b, byte ptr [rsp + 8] # 1-byte Reload - mov rsi, qword ptr [rsp + 304] # 8-byte Reload mov r14, qword ptr [rsp + 144] # 8-byte Reload - jne .LBB4_43 - jmp .LBB4_138 -.LBB4_182: - and r10, -16 - mov rax, r10 - shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 216], r10 # 8-byte Spill - lea rax, [r12 + 4*r10] - mov qword ptr [rsp + 104], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 160], xmm1 # 16-byte Spill - xor eax, eax - mov qword ptr [rsp + 128], r12 # 8-byte Spill - .p2align 4, 0x90 -.LBB4_183: # =>This Inner Loop Header: Depth=1 - mov r9, rax - mov qword ptr [rsp + 152], rax # 8-byte Spill - shl r9, 5 - mov r12, r9 - mov r13, r9 - mov r10, r9 - mov qword ptr [rsp + 64], r9 # 8-byte Spill - mov r15, r9 - mov r11, r9 - mov r14, r9 - mov rdx, r9 - mov r8, r9 - mov rbx, r9 - mov rdi, r9 - movzx eax, byte ptr [rsi + r9] - movd xmm4, eax - movzx eax, byte ptr [rsi + r9 + 1] - movd xmm3, eax - movzx eax, byte ptr [rsi + r9 + 2] - movd xmm5, eax - movzx eax, byte ptr [rsi + r9 + 3] - movd xmm7, eax - movzx eax, byte ptr [rsi + r9 + 4] - movd xmm9, eax - movzx eax, byte ptr [rsi + r9 + 5] - movd xmm2, eax - movzx eax, byte ptr [rsi + r9 + 6] - movd xmm8, eax - movzx eax, byte ptr [rsi + r9 + 7] - movd xmm14, eax - movzx eax, byte ptr [rsi + r9 + 8] - movd xmm0, eax - movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill - movzx eax, byte ptr [rsi + r9 + 9] - movd xmm11, eax - movzx eax, byte ptr [rsi + r9 + 10] - movd xmm12, eax - movzx eax, byte ptr [rsi + r9 + 11] - movd xmm13, eax - movzx eax, byte ptr [rsi + r9 + 12] - movd xmm0, eax - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - movzx eax, byte ptr [rsi + r9 + 13] - movd xmm6, eax - movzx eax, byte ptr [rsi + r9 + 14] - movd xmm15, eax - movzx eax, byte ptr [rsi + r9 + 15] - movd xmm0, eax - movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill - mov qword ptr [rsp + 72], r9 # 8-byte Spill - mov rcx, r9 - or rcx, 32 - mov qword ptr [rsp + 48], rcx # 8-byte Spill - or r12, 64 - or r13, 96 - or r10, 128 - mov qword ptr [rsp + 112], r10 # 8-byte Spill - mov r10, qword ptr [rsp + 64] # 8-byte Reload - or r10, 160 - mov qword ptr [rsp + 64], r10 # 8-byte Spill - or r15, 192 - mov qword ptr [rsp + 32], r15 # 8-byte Spill - or r11, 224 - or r14, 256 - mov qword ptr [rsp + 176], r14 # 8-byte Spill - or rdx, 288 - or r8, 320 - mov qword ptr [rsp + 120], r8 # 8-byte Spill - or rbx, 352 - mov qword ptr [rsp + 88], rbx # 8-byte Spill - or rdi, 384 - mov qword ptr [rsp + 40], rdi # 8-byte Spill - mov rax, r9 - or rax, 416 - mov qword ptr [rsp + 16], rax # 8-byte Spill - mov rax, r9 - or rax, 448 - mov qword ptr [rsp + 24], rax # 8-byte Spill - mov rdi, r9 - or rdi, 480 - pinsrb xmm4, byte ptr [rsi + rcx], 1 - mov qword ptr [rsp + 96], r12 # 8-byte Spill - pinsrb xmm4, byte ptr [rsi + r12], 2 - pinsrb xmm4, byte ptr [rsi + r13], 3 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx], 4 - pinsrb xmm4, byte ptr [rsi + r10], 5 - pinsrb xmm4, byte ptr [rsi + r15], 6 - pinsrb xmm4, byte ptr [rsi + r11], 7 - pinsrb xmm4, byte ptr [rsi + r14], 8 - pinsrb xmm4, byte ptr [rsi + rdx], 9 - pinsrb xmm4, byte ptr [rsi + r8], 10 - pinsrb xmm4, byte ptr [rsi + rbx], 11 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx], 12 - mov r9, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r9], 13 - pinsrb xmm4, byte ptr [rsi + rax], 14 - pinsrb xmm4, byte ptr [rsi + rdi], 15 - mov r9, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r9 + 1], 1 - pinsrb xmm3, byte ptr [rsi + r12 + 1], 2 - pinsrb xmm3, byte ptr [rsi + r13 + 1], 3 - mov r12, r13 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r13 + 1], 4 - pinsrb xmm3, byte ptr [rsi + r10 + 1], 5 - pinsrb xmm3, byte ptr [rsi + r15 + 1], 6 - pinsrb xmm3, byte ptr [rsi + r11 + 1], 7 - mov r10, r11 - pinsrb xmm3, byte ptr [rsi + r14 + 1], 8 - pinsrb xmm3, byte ptr [rsi + rdx + 1], 9 - mov r14, rdx - pinsrb xmm3, byte ptr [rsi + r8 + 1], 10 - pinsrb xmm3, byte ptr [rsi + rbx + 1], 11 - pinsrb xmm3, byte ptr [rsi + rcx + 1], 12 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 1], 13 - pinsrb xmm3, byte ptr [rsi + rax + 1], 14 - movdqa xmm1, xmmword ptr [rsp + 160] # 16-byte Reload - pcmpeqb xmm4, xmm1 - pinsrb xmm3, byte ptr [rsi + rdi + 1], 15 - mov rcx, rdi - pcmpeqb xmm3, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI4_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] - pandn xmm3, xmm0 - paddb xmm3, xmm4 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 16] - movd xmm10, edx - mov rdx, r9 - pinsrb xmm5, byte ptr [rsi + r9 + 2], 1 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdi + 2], 2 - mov qword ptr [rsp + 56], r12 # 8-byte Spill - pinsrb xmm5, byte ptr [rsi + r12 + 2], 3 - mov r8, r13 - pinsrb xmm5, byte ptr [rsi + r13 + 2], 4 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r11 + 2], 5 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r13 + 2], 6 - mov rbx, r10 - pinsrb xmm5, byte ptr [rsi + r10 + 2], 7 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r15 + 2], 8 - mov r9, r14 - pinsrb xmm5, byte ptr [rsi + r14 + 2], 9 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r10 + 2], 10 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r14 + 2], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 2], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 2], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 2], 14 - mov qword ptr [rsp + 80], rcx # 8-byte Spill - pinsrb xmm5, byte ptr [rsi + rcx + 2], 15 - pinsrb xmm7, byte ptr [rsi + rdx + 3], 1 - pinsrb xmm7, byte ptr [rsi + rdi + 3], 2 - pinsrb xmm7, byte ptr [rsi + r12 + 3], 3 - pinsrb xmm7, byte ptr [rsi + r8 + 3], 4 - pinsrb xmm7, byte ptr [rsi + r11 + 3], 5 - pinsrb xmm7, byte ptr [rsi + r13 + 3], 6 - pinsrb xmm7, byte ptr [rsi + rbx + 3], 7 - pinsrb xmm7, byte ptr [rsi + r15 + 3], 8 - pinsrb xmm7, byte ptr [rsi + r9 + 3], 9 - pinsrb xmm7, byte ptr [rsi + r10 + 3], 10 - pinsrb xmm7, byte ptr [rsi + r14 + 3], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 3], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 3], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 3], 14 - pinsrb xmm7, byte ptr [rsi + rcx + 3], 15 - pinsrb xmm9, byte ptr [rsi + rdx + 4], 1 - pinsrb xmm9, byte ptr [rsi + rdi + 4], 2 - pinsrb xmm9, byte ptr [rsi + r12 + 4], 3 - pinsrb xmm9, byte ptr [rsi + r8 + 4], 4 - mov rdi, r8 - pinsrb xmm9, byte ptr [rsi + r11 + 4], 5 - pinsrb xmm9, byte ptr [rsi + r13 + 4], 6 - pinsrb xmm9, byte ptr [rsi + rbx + 4], 7 - pinsrb xmm9, byte ptr [rsi + r15 + 4], 8 - pinsrb xmm9, byte ptr [rsi + r9 + 4], 9 - pinsrb xmm9, byte ptr [rsi + r10 + 4], 10 - pinsrb xmm9, byte ptr [rsi + r14 + 4], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rax + 4], 12 - mov r8, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r8 + 4], 13 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdx + 4], 14 - pinsrb xmm9, byte ptr [rsi + rcx + 4], 15 - pcmpeqb xmm5, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI4_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm5, xmm0 - pcmpeqb xmm7, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI4_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm7, xmm0 - por xmm7, xmm5 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - movzx edx, byte ptr [rsi + rcx + 17] - movd xmm4, edx - pcmpeqb xmm9, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI4_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm9, xmm0 - por xmm9, xmm7 - movzx edx, byte ptr [rsi + rcx + 18] - movd xmm7, edx - pcmpeqd xmm0, xmm0 - psubb xmm3, xmm0 - por xmm9, xmm3 - movzx edx, byte ptr [rsi + rcx + 19] - movd xmm5, edx - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r12 + 5], 1 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r13 + 5], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 5], 3 - pinsrb xmm2, byte ptr [rsi + rdi + 5], 4 - mov rdi, r11 - pinsrb xmm2, byte ptr [rsi + r11 + 5], 5 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 5], 6 - mov qword ptr [rsp + 272], rbx # 8-byte Spill - pinsrb xmm2, byte ptr [rsi + rbx + 5], 7 - pinsrb xmm2, byte ptr [rsi + r15 + 5], 8 - mov qword ptr [rsp + 136], r9 # 8-byte Spill - pinsrb xmm2, byte ptr [rsi + r9 + 5], 9 - pinsrb xmm2, byte ptr [rsi + r10 + 5], 10 - pinsrb xmm2, byte ptr [rsi + r14 + 5], 11 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdx + 5], 12 - mov rcx, r8 - pinsrb xmm2, byte ptr [rsi + r8 + 5], 13 - mov r8, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r8 + 5], 14 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r11 + 5], 15 - pinsrb xmm8, byte ptr [rsi + r12 + 6], 1 - pinsrb xmm8, byte ptr [rsi + r13 + 6], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rax + 6], 3 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r13 + 6], 4 - pinsrb xmm8, byte ptr [rsi + rdi + 6], 5 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rax + 6], 6 - mov r13, rax - pinsrb xmm8, byte ptr [rsi + rbx + 6], 7 - pinsrb xmm8, byte ptr [rsi + r15 + 6], 8 - pinsrb xmm8, byte ptr [rsi + r9 + 6], 9 - pinsrb xmm8, byte ptr [rsi + r10 + 6], 10 - pinsrb xmm8, byte ptr [rsi + r14 + 6], 11 - pinsrb xmm8, byte ptr [rsi + rdx + 6], 12 - pinsrb xmm8, byte ptr [rsi + rcx + 6], 13 - pinsrb xmm8, byte ptr [rsi + r8 + 6], 14 - pinsrb xmm8, byte ptr [rsi + r11 + 6], 15 - pinsrb xmm14, byte ptr [rsi + r12 + 7], 1 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r12 + 7], 2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 7], 3 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r11 + 7], 4 - pinsrb xmm14, byte ptr [rsi + rdi + 7], 5 - mov rax, r13 - pinsrb xmm14, byte ptr [rsi + r13 + 7], 6 - pinsrb xmm14, byte ptr [rsi + rbx + 7], 7 - pinsrb xmm14, byte ptr [rsi + r15 + 7], 8 - mov rbx, r15 - pinsrb xmm14, byte ptr [rsi + r9 + 7], 9 - pinsrb xmm14, byte ptr [rsi + r10 + 7], 10 - pinsrb xmm14, byte ptr [rsi + r14 + 7], 11 - pinsrb xmm14, byte ptr [rsi + rdx + 7], 12 - pinsrb xmm14, byte ptr [rsi + rcx + 7], 13 - mov r13, rcx - pinsrb xmm14, byte ptr [rsi + r8 + 7], 14 - movdqa xmm1, xmm14 - movdqa xmm14, xmmword ptr [rsp + 160] # 16-byte Reload - pcmpeqb xmm2, xmm14 - movdqa xmm0, xmmword ptr [rip + .LCPI4_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm0 - pcmpeqb xmm8, xmm14 - movdqa xmm0, xmmword ptr [rip + .LCPI4_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm8, xmm0 - por xmm8, xmm2 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - movzx edx, byte ptr [rsi + rdi + 20] - movd xmm3, edx - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rcx + 7], 15 - pcmpeqb xmm1, xmm14 - movdqa xmm0, xmmword ptr [rip + .LCPI4_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm1, xmm0 - por xmm1, xmm8 - movzx edx, byte ptr [rsi + rdi + 21] - movd xmm2, edx - movdqa xmm0, xmmword ptr [rsp + 192] # 16-byte Reload - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 8], 1 - pinsrb xmm0, byte ptr [rsi + r12 + 8], 2 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r12 + 8], 3 - pinsrb xmm0, byte ptr [rsi + r11 + 8], 4 - mov r8, r11 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r14 + 8], 5 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 8], 6 - mov r11, qword ptr [rsp + 272] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r11 + 8], 7 - pinsrb xmm0, byte ptr [rsi + r15 + 8], 8 - mov r10, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r10 + 8], 9 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r15 + 8], 10 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 8], 11 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 8], 12 - pinsrb xmm0, byte ptr [rsi + r13 + 8], 13 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 8], 14 - pinsrb xmm0, byte ptr [rsi + rcx + 8], 15 - por xmm1, xmm9 - movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill - movzx edx, byte ptr [rsi + rdi + 22] - movd xmm1, edx - pcmpeqb xmm0, xmm14 - pinsrb xmm11, byte ptr [rsi + rax + 9], 1 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdi + 9], 2 - pinsrb xmm11, byte ptr [rsi + r12 + 9], 3 - pinsrb xmm11, byte ptr [rsi + r8 + 9], 4 - pinsrb xmm11, byte ptr [rsi + r14 + 9], 5 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r13 + 9], 6 - pinsrb xmm11, byte ptr [rsi + r11 + 9], 7 - pinsrb xmm11, byte ptr [rsi + rbx + 9], 8 - mov rcx, r10 - pinsrb xmm11, byte ptr [rsi + r10 + 9], 9 - mov r9, r15 - pinsrb xmm11, byte ptr [rsi + r15 + 9], 10 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r10 + 9], 11 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r15 + 9], 12 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 9], 13 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 9], 14 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 9], 15 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rax + 10], 1 - pinsrb xmm12, byte ptr [rsi + rdi + 10], 2 - pinsrb xmm12, byte ptr [rsi + r12 + 10], 3 - pinsrb xmm12, byte ptr [rsi + r8 + 10], 4 - pinsrb xmm12, byte ptr [rsi + r14 + 10], 5 - pinsrb xmm12, byte ptr [rsi + r13 + 10], 6 - pinsrb xmm12, byte ptr [rsi + r11 + 10], 7 - pinsrb xmm12, byte ptr [rsi + rbx + 10], 8 - pinsrb xmm12, byte ptr [rsi + rcx + 10], 9 - pinsrb xmm12, byte ptr [rsi + r9 + 10], 10 - pinsrb xmm12, byte ptr [rsi + r10 + 10], 11 - pinsrb xmm12, byte ptr [rsi + r15 + 10], 12 - mov r14, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r14 + 10], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rax + 10], 14 - pinsrb xmm12, byte ptr [rsi + rdx + 10], 15 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rax + 11], 1 - pinsrb xmm13, byte ptr [rsi + rdi + 11], 2 - mov r14, rdi - pinsrb xmm13, byte ptr [rsi + r12 + 11], 3 - pinsrb xmm13, byte ptr [rsi + r8 + 11], 4 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rax + 11], 5 - pinsrb xmm13, byte ptr [rsi + r13 + 11], 6 - pinsrb xmm13, byte ptr [rsi + r11 + 11], 7 - mov r12, r11 - pinsrb xmm13, byte ptr [rsi + rbx + 11], 8 - pinsrb xmm13, byte ptr [rsi + rcx + 11], 9 - pinsrb xmm13, byte ptr [rsi + r9 + 11], 10 - pinsrb xmm13, byte ptr [rsi + r10 + 11], 11 - pinsrb xmm13, byte ptr [rsi + r15 + 11], 12 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rdi + 11], 13 - mov r13, rdi - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r9 + 11], 14 - pinsrb xmm13, byte ptr [rsi + rdx + 11], 15 - pcmpeqb xmm11, xmm14 - pandn xmm11, xmmword ptr [rip + .LCPI4_16] - paddb xmm11, xmm0 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - movzx edx, byte ptr [rsi + rdi + 23] - movd xmm8, edx - pcmpeqb xmm12, xmm14 - pandn xmm12, xmmword ptr [rip + .LCPI4_17] - pcmpeqb xmm13, xmm14 - pandn xmm13, xmmword ptr [rip + .LCPI4_18] - por xmm13, xmm12 - movzx edx, byte ptr [rsi + rdi + 24] - movd xmm12, edx - movdqa xmm9, xmmword ptr [rsp + 240] # 16-byte Reload - mov r11, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r11 + 12], 1 + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + jmp .LBB4_131 +.LBB4_130: + mov qword ptr [rsp + 160], r12 # 8-byte Spill +.LBB4_131: + shl rcx, 5 mov r8, r14 - pinsrb xmm9, byte ptr [rsi + r14 + 12], 2 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdi + 12], 3 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r14 + 12], 4 - pinsrb xmm9, byte ptr [rsi + rax + 12], 5 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rdx + 12], 6 - mov r15, r12 - pinsrb xmm9, byte ptr [rsi + r12 + 12], 7 - pinsrb xmm9, byte ptr [rsi + rbx + 12], 8 - pinsrb xmm9, byte ptr [rsi + rcx + 12], 9 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r12 + 12], 10 - pinsrb xmm9, byte ptr [rsi + r10 + 12], 11 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r10 + 12], 12 - pinsrb xmm9, byte ptr [rsi + r13 + 12], 13 - pinsrb xmm9, byte ptr [rsi + r9 + 12], 14 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r13 + 12], 15 - pinsrb xmm6, byte ptr [rsi + r11 + 13], 1 - pinsrb xmm6, byte ptr [rsi + r8 + 13], 2 - pinsrb xmm6, byte ptr [rsi + rdi + 13], 3 - pinsrb xmm6, byte ptr [rsi + r14 + 13], 4 - pinsrb xmm6, byte ptr [rsi + rax + 13], 5 - pinsrb xmm6, byte ptr [rsi + rdx + 13], 6 - pinsrb xmm6, byte ptr [rsi + r15 + 13], 7 - pinsrb xmm6, byte ptr [rsi + rbx + 13], 8 - pinsrb xmm6, byte ptr [rsi + rcx + 13], 9 - pinsrb xmm6, byte ptr [rsi + r12 + 13], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 13], 11 - pinsrb xmm6, byte ptr [rsi + r10 + 13], 12 - mov r13, r10 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r10 + 13], 13 - pinsrb xmm6, byte ptr [rsi + r9 + 13], 14 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r9 + 13], 15 - pinsrb xmm15, byte ptr [rsi + r11 + 14], 1 - pinsrb xmm15, byte ptr [rsi + r8 + 14], 2 - pinsrb xmm15, byte ptr [rsi + rdi + 14], 3 - pinsrb xmm15, byte ptr [rsi + r14 + 14], 4 - pinsrb xmm15, byte ptr [rsi + rax + 14], 5 - pinsrb xmm15, byte ptr [rsi + rdx + 14], 6 - pinsrb xmm15, byte ptr [rsi + r15 + 14], 7 - mov rdi, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdi + 14], 8 - pinsrb xmm15, byte ptr [rsi + rcx + 14], 9 - mov r11, r12 - pinsrb xmm15, byte ptr [rsi + r12 + 14], 10 - pinsrb xmm15, byte ptr [rsi + rbx + 14], 11 - mov r12, r13 - pinsrb xmm15, byte ptr [rsi + r13 + 14], 12 - mov r13, r10 - pinsrb xmm15, byte ptr [rsi + r10 + 14], 13 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r10 + 14], 14 - pcmpeqb xmm9, xmm14 - pandn xmm9, xmmword ptr [rip + .LCPI4_19] - por xmm9, xmm13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 25] - movd xmm13, edx - psubb xmm11, xmmword ptr [rip + .LCPI4_22] - por xmm9, xmm11 - movzx edx, byte ptr [rsi + rax + 26] - movd xmm0, edx - pinsrb xmm15, byte ptr [rsi + r9 + 14], 15 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmmword ptr [rip + .LCPI4_20] - pcmpeqb xmm15, xmm14 - pandn xmm15, xmmword ptr [rip + .LCPI4_21] - por xmm15, xmm6 - movzx edx, byte ptr [rsi + rax + 27] - movd xmm11, edx - movdqa xmm6, xmmword ptr [rsp + 224] # 16-byte Reload - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 15], 1 - pinsrb xmm6, byte ptr [rsi + r8 + 15], 2 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r9 + 15], 3 - pinsrb xmm6, byte ptr [rsi + r14 + 15], 4 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 15], 5 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 15], 6 - pinsrb xmm6, byte ptr [rsi + r15 + 15], 7 - pinsrb xmm6, byte ptr [rsi + rdi + 15], 8 - mov rdi, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdi + 15], 9 - pinsrb xmm6, byte ptr [rsi + r11 + 15], 10 - pinsrb xmm6, byte ptr [rsi + rbx + 15], 11 - pinsrb xmm6, byte ptr [rsi + r12 + 15], 12 - pinsrb xmm6, byte ptr [rsi + r13 + 15], 13 - pinsrb xmm6, byte ptr [rsi + r10 + 15], 14 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r10 + 15], 15 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmmword ptr [rip + .LCPI4_6] - por xmm6, xmm15 - movzx edx, byte ptr [rsi + rax + 28] - movd xmm15, edx - por xmm6, xmm9 - movdqa xmmword ptr [rsp + 224], xmm6 # 16-byte Spill - movzx edx, byte ptr [rsi + rax + 29] - movd xmm9, edx - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdx + 16], 1 - pinsrb xmm10, byte ptr [rsi + r8 + 16], 2 - pinsrb xmm10, byte ptr [rsi + r9 + 16], 3 - pinsrb xmm10, byte ptr [rsi + r14 + 16], 4 - pinsrb xmm10, byte ptr [rsi + rcx + 16], 5 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r12 + 16], 6 - pinsrb xmm10, byte ptr [rsi + r15 + 16], 7 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rcx + 16], 8 - pinsrb xmm10, byte ptr [rsi + rdi + 16], 9 - pinsrb xmm10, byte ptr [rsi + r11 + 16], 10 - pinsrb xmm10, byte ptr [rsi + rbx + 16], 11 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rax + 16], 12 - mov rax, r13 - pinsrb xmm10, byte ptr [rsi + r13 + 16], 13 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r13 + 16], 14 - pinsrb xmm10, byte ptr [rsi + r10 + 16], 15 - pinsrb xmm4, byte ptr [rsi + rdx + 17], 1 - pinsrb xmm4, byte ptr [rsi + r8 + 17], 2 - pinsrb xmm4, byte ptr [rsi + r9 + 17], 3 - pinsrb xmm4, byte ptr [rsi + r14 + 17], 4 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r8 + 17], 5 - mov r9, r12 - pinsrb xmm4, byte ptr [rsi + r12 + 17], 6 - pinsrb xmm4, byte ptr [rsi + r15 + 17], 7 - pinsrb xmm4, byte ptr [rsi + rcx + 17], 8 - pinsrb xmm4, byte ptr [rsi + rdi + 17], 9 - pinsrb xmm4, byte ptr [rsi + r11 + 17], 10 - pinsrb xmm4, byte ptr [rsi + rbx + 17], 11 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r12 + 17], 12 - pinsrb xmm4, byte ptr [rsi + rax + 17], 13 - pinsrb xmm4, byte ptr [rsi + r13 + 17], 14 - pinsrb xmm4, byte ptr [rsi + r10 + 17], 15 - mov rdi, r10 - pcmpeqb xmm10, xmm14 - pcmpeqb xmm4, xmm14 - movdqa xmm6, xmmword ptr [rip + .LCPI4_16] # xmm6 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] - pandn xmm4, xmm6 - paddb xmm4, xmm10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - movzx edx, byte ptr [rsi + rcx + 30] - movd xmm10, edx - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 18], 1 - pinsrb xmm5, byte ptr [rsi + rax + 19], 1 - pinsrb xmm3, byte ptr [rsi + rax + 20], 1 - pinsrb xmm2, byte ptr [rsi + rax + 21], 1 - pinsrb xmm1, byte ptr [rsi + rax + 22], 1 - pinsrb xmm8, byte ptr [rsi + rax + 23], 1 - pinsrb xmm12, byte ptr [rsi + rax + 24], 1 - pinsrb xmm13, byte ptr [rsi + rax + 25], 1 - pinsrb xmm0, byte ptr [rsi + rax + 26], 1 - pinsrb xmm11, byte ptr [rsi + rax + 27], 1 - pinsrb xmm15, byte ptr [rsi + rax + 28], 1 - pinsrb xmm9, byte ptr [rsi + rax + 29], 1 - pinsrb xmm10, byte ptr [rsi + rax + 30], 1 - movzx edx, byte ptr [rsi + rcx + 31] - movd xmm6, edx - pinsrb xmm6, byte ptr [rsi + rax + 31], 1 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 18], 2 - pinsrb xmm5, byte ptr [rsi + rdx + 19], 2 - pinsrb xmm3, byte ptr [rsi + rdx + 20], 2 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 2 - pinsrb xmm1, byte ptr [rsi + rdx + 22], 2 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 2 - pinsrb xmm12, byte ptr [rsi + rdx + 24], 2 - pinsrb xmm13, byte ptr [rsi + rdx + 25], 2 - pinsrb xmm0, byte ptr [rsi + rdx + 26], 2 - pinsrb xmm11, byte ptr [rsi + rdx + 27], 2 - pinsrb xmm15, byte ptr [rsi + rdx + 28], 2 - pinsrb xmm9, byte ptr [rsi + rdx + 29], 2 - pinsrb xmm10, byte ptr [rsi + rdx + 30], 2 - pinsrb xmm6, byte ptr [rsi + rdx + 31], 2 - mov rdx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdx + 18], 3 - pinsrb xmm7, byte ptr [rsi + r14 + 18], 4 - pinsrb xmm7, byte ptr [rsi + r8 + 18], 5 - mov rbx, r9 - pinsrb xmm7, byte ptr [rsi + r9 + 18], 6 - pinsrb xmm7, byte ptr [rsi + r15 + 18], 7 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r11 + 18], 8 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rcx + 18], 9 - mov r9, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r9 + 18], 10 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r10 + 18], 11 - mov rax, r12 - pinsrb xmm7, byte ptr [rsi + r12 + 18], 12 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r12 + 18], 13 - pinsrb xmm7, byte ptr [rsi + r13 + 18], 14 - pinsrb xmm7, byte ptr [rsi + rdi + 18], 15 - pinsrb xmm5, byte ptr [rsi + rdx + 19], 3 - pinsrb xmm5, byte ptr [rsi + r14 + 19], 4 - pinsrb xmm5, byte ptr [rsi + r8 + 19], 5 - pinsrb xmm5, byte ptr [rsi + rbx + 19], 6 - pinsrb xmm5, byte ptr [rsi + r15 + 19], 7 - pinsrb xmm5, byte ptr [rsi + r11 + 19], 8 - pinsrb xmm5, byte ptr [rsi + rcx + 19], 9 - pinsrb xmm5, byte ptr [rsi + r9 + 19], 10 - pinsrb xmm5, byte ptr [rsi + r10 + 19], 11 - pinsrb xmm5, byte ptr [rsi + rax + 19], 12 - pinsrb xmm5, byte ptr [rsi + r12 + 19], 13 - pinsrb xmm5, byte ptr [rsi + r13 + 19], 14 - pinsrb xmm5, byte ptr [rsi + rdi + 19], 15 - pinsrb xmm3, byte ptr [rsi + rdx + 20], 3 - pinsrb xmm3, byte ptr [rsi + r14 + 20], 4 - pinsrb xmm3, byte ptr [rsi + r8 + 20], 5 - pinsrb xmm3, byte ptr [rsi + rbx + 20], 6 - pinsrb xmm3, byte ptr [rsi + r15 + 20], 7 - pinsrb xmm3, byte ptr [rsi + r11 + 20], 8 - pinsrb xmm3, byte ptr [rsi + rcx + 20], 9 - pinsrb xmm3, byte ptr [rsi + r9 + 20], 10 - pinsrb xmm3, byte ptr [rsi + r10 + 20], 11 - pinsrb xmm3, byte ptr [rsi + rax + 20], 12 - pinsrb xmm3, byte ptr [rsi + r12 + 20], 13 - pinsrb xmm3, byte ptr [rsi + r13 + 20], 14 - pcmpeqb xmm7, xmm14 - movdqa xmm14, xmmword ptr [rip + .LCPI4_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm7, xmm14 - pcmpeqb xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload - movdqa xmm14, xmmword ptr [rip + .LCPI4_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm5, xmm14 - por xmm5, xmm7 - pinsrb xmm3, byte ptr [rsi + rdi + 20], 15 - movdqa xmm14, xmmword ptr [rsp + 160] # 16-byte Reload - pcmpeqb xmm3, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI4_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm3, xmm7 - por xmm3, xmm5 - pcmpeqd xmm5, xmm5 - psubb xmm4, xmm5 - por xmm3, xmm4 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 3 - pinsrb xmm2, byte ptr [rsi + r14 + 21], 4 - pinsrb xmm2, byte ptr [rsi + r8 + 21], 5 - pinsrb xmm2, byte ptr [rsi + rbx + 21], 6 - pinsrb xmm2, byte ptr [rsi + r15 + 21], 7 - pinsrb xmm2, byte ptr [rsi + r11 + 21], 8 - pinsrb xmm2, byte ptr [rsi + rcx + 21], 9 - pinsrb xmm2, byte ptr [rsi + r9 + 21], 10 - pinsrb xmm2, byte ptr [rsi + r10 + 21], 11 - pinsrb xmm2, byte ptr [rsi + rax + 21], 12 - pinsrb xmm2, byte ptr [rsi + r12 + 21], 13 - pinsrb xmm2, byte ptr [rsi + r13 + 21], 14 - pinsrb xmm2, byte ptr [rsi + rdi + 21], 15 - pinsrb xmm1, byte ptr [rsi + rdx + 22], 3 - pinsrb xmm1, byte ptr [rsi + r14 + 22], 4 - pinsrb xmm1, byte ptr [rsi + r8 + 22], 5 - pinsrb xmm1, byte ptr [rsi + rbx + 22], 6 - pinsrb xmm1, byte ptr [rsi + r15 + 22], 7 - pinsrb xmm1, byte ptr [rsi + r11 + 22], 8 - pinsrb xmm1, byte ptr [rsi + rcx + 22], 9 - pinsrb xmm1, byte ptr [rsi + r9 + 22], 10 - pinsrb xmm1, byte ptr [rsi + r10 + 22], 11 - pinsrb xmm1, byte ptr [rsi + rax + 22], 12 - pinsrb xmm1, byte ptr [rsi + r12 + 22], 13 - pinsrb xmm1, byte ptr [rsi + r13 + 22], 14 - pinsrb xmm1, byte ptr [rsi + rdi + 22], 15 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 3 - pinsrb xmm8, byte ptr [rsi + r14 + 23], 4 - pinsrb xmm8, byte ptr [rsi + r8 + 23], 5 - pinsrb xmm8, byte ptr [rsi + rbx + 23], 6 - pinsrb xmm8, byte ptr [rsi + r15 + 23], 7 - pinsrb xmm8, byte ptr [rsi + r11 + 23], 8 - pinsrb xmm8, byte ptr [rsi + rcx + 23], 9 - pinsrb xmm8, byte ptr [rsi + r9 + 23], 10 - pinsrb xmm8, byte ptr [rsi + r10 + 23], 11 - pinsrb xmm8, byte ptr [rsi + rax + 23], 12 - pinsrb xmm8, byte ptr [rsi + r12 + 23], 13 - pinsrb xmm8, byte ptr [rsi + r13 + 23], 14 - pcmpeqb xmm2, xmm14 - movdqa xmm5, xmmword ptr [rip + .LCPI4_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm5 - pcmpeqb xmm1, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI4_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm1, xmm7 - por xmm1, xmm2 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 15 - pcmpeqb xmm8, xmm14 - movdqa xmm4, xmmword ptr [rip + .LCPI4_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm8, xmm4 - por xmm8, xmm1 - pinsrb xmm12, byte ptr [rsi + rdx + 24], 3 - pinsrb xmm12, byte ptr [rsi + r14 + 24], 4 - pinsrb xmm12, byte ptr [rsi + r8 + 24], 5 - pinsrb xmm12, byte ptr [rsi + rbx + 24], 6 - pinsrb xmm12, byte ptr [rsi + r15 + 24], 7 - pinsrb xmm12, byte ptr [rsi + r11 + 24], 8 - pinsrb xmm12, byte ptr [rsi + rcx + 24], 9 - pinsrb xmm12, byte ptr [rsi + r9 + 24], 10 - pinsrb xmm12, byte ptr [rsi + r10 + 24], 11 - pinsrb xmm12, byte ptr [rsi + rax + 24], 12 - pinsrb xmm12, byte ptr [rsi + r12 + 24], 13 - pinsrb xmm12, byte ptr [rsi + r13 + 24], 14 - pinsrb xmm12, byte ptr [rsi + rdi + 24], 15 - por xmm8, xmm3 - pcmpeqb xmm12, xmm14 - pinsrb xmm13, byte ptr [rsi + rdx + 25], 3 - pinsrb xmm13, byte ptr [rsi + r14 + 25], 4 - pinsrb xmm13, byte ptr [rsi + r8 + 25], 5 - pinsrb xmm13, byte ptr [rsi + rbx + 25], 6 - pinsrb xmm13, byte ptr [rsi + r15 + 25], 7 - pinsrb xmm13, byte ptr [rsi + r11 + 25], 8 - pinsrb xmm13, byte ptr [rsi + rcx + 25], 9 - pinsrb xmm13, byte ptr [rsi + r9 + 25], 10 - pinsrb xmm13, byte ptr [rsi + r10 + 25], 11 - pinsrb xmm13, byte ptr [rsi + rax + 25], 12 - pinsrb xmm13, byte ptr [rsi + r12 + 25], 13 - pinsrb xmm13, byte ptr [rsi + r13 + 25], 14 - pinsrb xmm13, byte ptr [rsi + rdi + 25], 15 - pinsrb xmm0, byte ptr [rsi + rdx + 26], 3 - pinsrb xmm0, byte ptr [rsi + r14 + 26], 4 - pinsrb xmm0, byte ptr [rsi + r8 + 26], 5 - pinsrb xmm0, byte ptr [rsi + rbx + 26], 6 - pinsrb xmm0, byte ptr [rsi + r15 + 26], 7 - pinsrb xmm0, byte ptr [rsi + r11 + 26], 8 - pinsrb xmm0, byte ptr [rsi + rcx + 26], 9 - pinsrb xmm0, byte ptr [rsi + r9 + 26], 10 - pinsrb xmm0, byte ptr [rsi + r10 + 26], 11 - pinsrb xmm0, byte ptr [rsi + rax + 26], 12 - pinsrb xmm0, byte ptr [rsi + r12 + 26], 13 - pinsrb xmm0, byte ptr [rsi + r13 + 26], 14 - pinsrb xmm0, byte ptr [rsi + rdi + 26], 15 - pinsrb xmm11, byte ptr [rsi + rdx + 27], 3 - pinsrb xmm11, byte ptr [rsi + r14 + 27], 4 - pinsrb xmm11, byte ptr [rsi + r8 + 27], 5 - pinsrb xmm11, byte ptr [rsi + rbx + 27], 6 - pinsrb xmm11, byte ptr [rsi + r15 + 27], 7 - pinsrb xmm11, byte ptr [rsi + r11 + 27], 8 - pinsrb xmm11, byte ptr [rsi + rcx + 27], 9 - pinsrb xmm11, byte ptr [rsi + r9 + 27], 10 - pinsrb xmm11, byte ptr [rsi + r10 + 27], 11 - pinsrb xmm11, byte ptr [rsi + rax + 27], 12 - pinsrb xmm11, byte ptr [rsi + r12 + 27], 13 - pinsrb xmm11, byte ptr [rsi + r13 + 27], 14 - pcmpeqb xmm13, xmm14 - pandn xmm13, xmmword ptr [rip + .LCPI4_16] - paddb xmm13, xmm12 - pinsrb xmm11, byte ptr [rsi + rdi + 27], 15 - pcmpeqb xmm0, xmm14 - pandn xmm0, xmmword ptr [rip + .LCPI4_17] - pcmpeqb xmm11, xmm14 - pandn xmm11, xmmword ptr [rip + .LCPI4_18] - por xmm11, xmm0 - pinsrb xmm15, byte ptr [rsi + rdx + 28], 3 - pinsrb xmm9, byte ptr [rsi + rdx + 29], 3 - pinsrb xmm10, byte ptr [rsi + rdx + 30], 3 - pinsrb xmm6, byte ptr [rsi + rdx + 31], 3 - pinsrb xmm15, byte ptr [rsi + r14 + 28], 4 - pinsrb xmm9, byte ptr [rsi + r14 + 29], 4 - pinsrb xmm10, byte ptr [rsi + r14 + 30], 4 - pinsrb xmm6, byte ptr [rsi + r14 + 31], 4 - mov rdx, r8 - pinsrb xmm15, byte ptr [rsi + r8 + 28], 5 - pinsrb xmm9, byte ptr [rsi + r8 + 29], 5 - pinsrb xmm10, byte ptr [rsi + r8 + 30], 5 - pinsrb xmm6, byte ptr [rsi + r8 + 31], 5 - pinsrb xmm15, byte ptr [rsi + rbx + 28], 6 - pinsrb xmm9, byte ptr [rsi + rbx + 29], 6 - pinsrb xmm10, byte ptr [rsi + rbx + 30], 6 - pinsrb xmm6, byte ptr [rsi + rbx + 31], 6 - pinsrb xmm15, byte ptr [rsi + r15 + 28], 7 - pinsrb xmm9, byte ptr [rsi + r15 + 29], 7 - pinsrb xmm10, byte ptr [rsi + r15 + 30], 7 - pinsrb xmm6, byte ptr [rsi + r15 + 31], 7 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r11 + 28], 8 - pinsrb xmm9, byte ptr [rsi + r11 + 29], 8 - pinsrb xmm10, byte ptr [rsi + r11 + 30], 8 - pinsrb xmm6, byte ptr [rsi + r11 + 31], 8 - pinsrb xmm15, byte ptr [rsi + rcx + 28], 9 - pinsrb xmm9, byte ptr [rsi + rcx + 29], 9 - pinsrb xmm10, byte ptr [rsi + rcx + 30], 9 - pinsrb xmm6, byte ptr [rsi + rcx + 31], 9 - mov rdx, r9 - pinsrb xmm15, byte ptr [rsi + r9 + 28], 10 - pinsrb xmm9, byte ptr [rsi + r9 + 29], 10 - pinsrb xmm10, byte ptr [rsi + r9 + 30], 10 - pinsrb xmm6, byte ptr [rsi + r9 + 31], 10 - mov rdx, r10 - pinsrb xmm15, byte ptr [rsi + r10 + 28], 11 - pinsrb xmm9, byte ptr [rsi + r10 + 29], 11 - pinsrb xmm10, byte ptr [rsi + r10 + 30], 11 - pinsrb xmm6, byte ptr [rsi + r10 + 31], 11 - pinsrb xmm15, byte ptr [rsi + rax + 28], 12 - pinsrb xmm9, byte ptr [rsi + rax + 29], 12 - pinsrb xmm10, byte ptr [rsi + rax + 30], 12 - pinsrb xmm6, byte ptr [rsi + rax + 31], 12 - mov rax, r12 - pinsrb xmm15, byte ptr [rsi + r12 + 28], 13 - pinsrb xmm9, byte ptr [rsi + r12 + 29], 13 - pinsrb xmm10, byte ptr [rsi + r12 + 30], 13 - pinsrb xmm6, byte ptr [rsi + r12 + 31], 13 - pinsrb xmm15, byte ptr [rsi + r13 + 28], 14 - pinsrb xmm9, byte ptr [rsi + r13 + 29], 14 - pinsrb xmm10, byte ptr [rsi + r13 + 30], 14 - pinsrb xmm6, byte ptr [rsi + r13 + 31], 14 - mov rax, rdi - pinsrb xmm15, byte ptr [rsi + rdi + 28], 15 - pinsrb xmm9, byte ptr [rsi + rdi + 29], 15 - pinsrb xmm10, byte ptr [rsi + rdi + 30], 15 - pcmpeqb xmm15, xmm14 - pandn xmm15, xmmword ptr [rip + .LCPI4_19] - por xmm15, xmm11 - pinsrb xmm6, byte ptr [rsi + rdi + 31], 15 - psubb xmm13, xmmword ptr [rip + .LCPI4_22] - por xmm15, xmm13 - pcmpeqb xmm9, xmm14 - pandn xmm9, xmm5 - pcmpeqb xmm10, xmm14 - pandn xmm10, xmm7 - por xmm10, xmm9 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmm4 - por xmm6, xmm10 - por xmm6, xmm15 - movdqa xmm0, xmm8 - punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] - movdqa xmm3, xmmword ptr [rsp + 192] # 16-byte Reload - movdqa xmm1, xmm3 - movdqa xmm4, xmmword ptr [rsp + 224] # 16-byte Reload - punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] - movdqa xmm2, xmm1 - punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] - punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] - punpckhbw xmm3, xmm4 # xmm3 = xmm3[8],xmm4[8],xmm3[9],xmm4[9],xmm3[10],xmm4[10],xmm3[11],xmm4[11],xmm3[12],xmm4[12],xmm3[13],xmm4[13],xmm3[14],xmm4[14],xmm3[15],xmm4[15] - movdqa xmm0, xmm3 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - movdqu xmmword ptr [rbx + 4*rcx + 48], xmm3 - movdqu xmmword ptr [rbx + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rbx + 4*rcx + 16], xmm1 - movdqu xmmword ptr [rbx + 4*rcx], xmm2 - add rcx, 16 + sub r8, rcx + jle .LBB4_208 +# %bb.132: + or rcx, 1 + cmp r14, rcx + jne .LBB4_179 +# %bb.133: + xor r9d, r9d + jmp .LBB4_182 +.LBB4_134: + mov r15d, r13d + sub r14, r8 + je .LBB4_208 +.LBB4_135: + mov r13d, r15d + add r12, 1 +.LBB4_136: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB4_144 +# %bb.137: + cmp rcx, 8 + mov qword ptr [rsp + 144], r14 # 8-byte Spill + mov qword ptr [rsp + 176], rcx # 8-byte Spill + jb .LBB4_140 +# %bb.138: mov rax, rcx - cmp rcx, qword ptr [rsp + 216] # 8-byte Folded Reload - jne .LBB4_183 -# %bb.184: - mov r10, qword ptr [rsp + 288] # 8-byte Reload - cmp r10, qword ptr [rsp + 216] # 8-byte Folded Reload - mov r11b, byte ptr [rsp + 8] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r14, qword ptr [rsp + 144] # 8-byte Reload - jne .LBB4_69 - jmp .LBB4_142 -.LBB4_185: - and r10, -8 - mov rax, r10 shl rax, 6 add rax, rsi - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov qword ptr [rsp + 32], r10 # 8-byte Spill - lea rax, [r12 + 4*r10] - mov qword ptr [rsp + 8], rax # 8-byte Spill - mov dword ptr [rsp + 64], r13d # 4-byte Spill - movd xmm0, r13d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] - xor r15d, r15d - mov qword ptr [rsp + 128], r12 # 8-byte Spill - pxor xmm15, xmm15 + cmp r12, rax + jae .LBB4_215 +# %bb.139: + lea rax, [r12 + 4*rcx] + cmp rax, rsi + jbe .LBB4_215 +.LBB4_140: + xor eax, eax + mov qword ptr [rsp + 40], rax # 8-byte Spill +.LBB4_141: + mov qword ptr [rsp + 8], r12 # 8-byte Spill + sub rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + mov qword ptr [rsp + 240], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB4_186: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 24], r15 # 8-byte Spill - shl r15, 6 - mov r8, r15 - mov r12, r15 - mov r13, r15 - mov rbx, r15 - mov rdi, r15 - mov r9, r15 - movzx eax, word ptr [rsi + r15] - movd xmm5, eax - movzx eax, word ptr [rsi + r15 + 2] - movd xmm0, eax - movzx eax, word ptr [rsi + r15 + 4] - movd xmm1, eax - movzx eax, word ptr [rsi + r15 + 6] - movd xmm7, eax - movzx eax, word ptr [rsi + r15 + 8] - movd xmm8, eax - movzx eax, word ptr [rsi + r15 + 10] - movd xmm4, eax - movzx eax, word ptr [rsi + r15 + 12] - movzx r10d, word ptr [rsi + r15 + 14] - movzx r11d, word ptr [rsi + r15 + 16] - movzx edx, word ptr [rsi + r15 + 18] - movzx r14d, word ptr [rsi + r15 + 20] - mov rcx, r15 - or rcx, 64 - or r8, 128 - or r12, 192 - or r13, 256 - or rbx, 320 - or rdi, 384 - pinsrw xmm5, word ptr [rsi + rcx], 1 - pinsrw xmm5, word ptr [rsi + r8], 2 - pinsrw xmm5, word ptr [rsi + r12], 3 - pinsrw xmm5, word ptr [rsi + r13], 4 - pinsrw xmm5, word ptr [rsi + rbx], 5 - pinsrw xmm5, word ptr [rsi + rdi], 6 - pinsrw xmm0, word ptr [rsi + rcx + 2], 1 - pinsrw xmm0, word ptr [rsi + r8 + 2], 2 - pinsrw xmm0, word ptr [rsi + r12 + 2], 3 - pinsrw xmm0, word ptr [rsi + r13 + 2], 4 - pinsrw xmm0, word ptr [rsi + rbx + 2], 5 - pinsrw xmm0, word ptr [rsi + rdi + 2], 6 - or r9, 448 - pinsrw xmm0, word ptr [rsi + r9 + 2], 7 - movd xmm2, eax - movzx eax, word ptr [rsi + r15 + 22] - mov dword ptr [rsp + 16], eax # 4-byte Spill - pcmpeqw xmm0, xmm11 - pinsrw xmm1, word ptr [rsi + rcx + 4], 1 - pinsrw xmm1, word ptr [rsi + r8 + 4], 2 - pinsrw xmm1, word ptr [rsi + r12 + 4], 3 - pinsrw xmm1, word ptr [rsi + r13 + 4], 4 - pinsrw xmm1, word ptr [rsi + rbx + 4], 5 - pinsrw xmm1, word ptr [rsi + rdi + 4], 6 - pinsrw xmm1, word ptr [rsi + r9 + 4], 7 - packsswb xmm0, xmm0 - pcmpeqw xmm1, xmm11 - movdqa xmm9, xmmword ptr [rip + .LCPI4_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm3, xmm9 - pblendvb xmm3, xmm15, xmm0 - packsswb xmm1, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI4_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm0 - movdqa xmm14, xmm0 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm15, xmm0 - movd xmm1, r10d - movzx r10d, word ptr [rsi + r15 + 24] - pinsrw xmm5, word ptr [rsi + r9], 7 - pcmpeqw xmm5, xmm11 - pcmpeqd xmm0, xmm0 - pxor xmm5, xmm0 - packsswb xmm5, xmm5 - pinsrw xmm7, word ptr [rsi + rcx + 6], 1 - pinsrw xmm7, word ptr [rsi + r8 + 6], 2 - pinsrw xmm7, word ptr [rsi + r12 + 6], 3 - pinsrw xmm7, word ptr [rsi + r13 + 6], 4 - pinsrw xmm7, word ptr [rsi + rbx + 6], 5 - pinsrw xmm7, word ptr [rsi + rdi + 6], 6 - pinsrw xmm7, word ptr [rsi + r9 + 6], 7 - pcmpeqw xmm7, xmm11 - packsswb xmm7, xmm7 - pinsrw xmm8, word ptr [rsi + rcx + 8], 1 - pinsrw xmm8, word ptr [rsi + r8 + 8], 2 - pinsrw xmm8, word ptr [rsi + r12 + 8], 3 - pinsrw xmm8, word ptr [rsi + r13 + 8], 4 - pinsrw xmm8, word ptr [rsi + rbx + 8], 5 - pinsrw xmm8, word ptr [rsi + rdi + 8], 6 - pinsrw xmm8, word ptr [rsi + r9 + 8], 7 - psubb xmm3, xmm5 - movdqa xmm12, xmmword ptr [rip + .LCPI4_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm7 - pblendvb xmm12, xmm15, xmm0 - movd xmm7, r11d - movzx eax, word ptr [rsi + r15 + 26] - pcmpeqw xmm8, xmm11 - packsswb xmm8, xmm8 - por xmm12, xmm6 - movdqa xmm13, xmmword ptr [rip + .LCPI4_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm8 - pblendvb xmm13, xmm15, xmm0 - movd xmm6, edx - movzx r11d, word ptr [rsi + r15 + 28] - pinsrw xmm4, word ptr [rsi + rcx + 10], 1 - pinsrw xmm4, word ptr [rsi + r8 + 10], 2 - pinsrw xmm4, word ptr [rsi + r12 + 10], 3 - pinsrw xmm4, word ptr [rsi + r13 + 10], 4 - pinsrw xmm4, word ptr [rsi + rbx + 10], 5 - pinsrw xmm4, word ptr [rsi + rdi + 10], 6 - pinsrw xmm4, word ptr [rsi + r9 + 10], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - pinsrw xmm2, word ptr [rsi + rcx + 12], 1 - pinsrw xmm2, word ptr [rsi + r8 + 12], 2 - pinsrw xmm2, word ptr [rsi + r12 + 12], 3 - pinsrw xmm2, word ptr [rsi + r13 + 12], 4 - pinsrw xmm2, word ptr [rsi + rbx + 12], 5 - pinsrw xmm2, word ptr [rsi + rdi + 12], 6 - por xmm12, xmm3 - movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm5, xmm15, xmm0 - movd xmm4, r14d - movzx edx, word ptr [rsi + r15 + 30] - mov dword ptr [rsp + 48], edx # 4-byte Spill - pinsrw xmm2, word ptr [rsi + r9 + 12], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm13 - movdqa xmm13, xmmword ptr [rip + .LCPI4_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm13, xmm15, xmm0 - movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx edx, word ptr [rsi + r15 + 32] - mov dword ptr [rsp + 40], edx # 4-byte Spill - pinsrw xmm1, word ptr [rsi + rcx + 14], 1 - pinsrw xmm1, word ptr [rsi + r8 + 14], 2 - pinsrw xmm1, word ptr [rsi + r12 + 14], 3 - pinsrw xmm1, word ptr [rsi + r13 + 14], 4 - pinsrw xmm1, word ptr [rsi + rbx + 14], 5 - pinsrw xmm1, word ptr [rsi + rdi + 14], 6 - por xmm13, xmm5 - movd xmm2, r10d - movzx edx, word ptr [rsi + r15 + 34] - mov dword ptr [rsp + 16], edx # 4-byte Spill - pinsrw xmm1, word ptr [rsi + r9 + 14], 7 - pcmpeqw xmm1, xmm11 - pinsrw xmm6, word ptr [rsi + rcx + 18], 1 - pinsrw xmm6, word ptr [rsi + r8 + 18], 2 - pinsrw xmm6, word ptr [rsi + r12 + 18], 3 - pinsrw xmm6, word ptr [rsi + r13 + 18], 4 - pinsrw xmm6, word ptr [rsi + rbx + 18], 5 - pinsrw xmm6, word ptr [rsi + rdi + 18], 6 - packsswb xmm1, xmm1 - pinsrw xmm6, word ptr [rsi + r9 + 18], 7 - pcmpeqw xmm6, xmm11 - packsswb xmm6, xmm6 - por xmm13, xmm12 - movdqa xmm12, xmmword ptr [rip + .LCPI4_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm12, xmm15, xmm0 - movdqa xmm8, xmm9 - movdqa xmm0, xmm6 - pblendvb xmm8, xmm15, xmm0 - movd xmm1, eax - movzx r14d, word ptr [rsi + r15 + 36] - pinsrw xmm7, word ptr [rsi + rcx + 16], 1 - pinsrw xmm7, word ptr [rsi + r8 + 16], 2 - pinsrw xmm7, word ptr [rsi + r12 + 16], 3 - pinsrw xmm7, word ptr [rsi + r13 + 16], 4 - pinsrw xmm7, word ptr [rsi + rbx + 16], 5 - pinsrw xmm7, word ptr [rsi + rdi + 16], 6 - pinsrw xmm4, word ptr [rsi + rcx + 20], 1 - pinsrw xmm4, word ptr [rsi + r8 + 20], 2 - pinsrw xmm4, word ptr [rsi + r12 + 20], 3 - pinsrw xmm4, word ptr [rsi + r13 + 20], 4 - pinsrw xmm4, word ptr [rsi + rbx + 20], 5 - pinsrw xmm4, word ptr [rsi + rdi + 20], 6 - pinsrw xmm4, word ptr [rsi + r9 + 20], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm12, xmm13 - movdqa xmm5, xmm14 - movdqa xmm0, xmm4 - pblendvb xmm5, xmm15, xmm0 - movd xmm4, r11d - movzx r11d, word ptr [rsi + r15 + 38] - pinsrw xmm7, word ptr [rsi + r9 + 16], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI4_22] - packsswb xmm7, xmm7 - pinsrw xmm3, word ptr [rsi + rcx + 22], 1 - pinsrw xmm3, word ptr [rsi + r8 + 22], 2 - pinsrw xmm3, word ptr [rsi + r12 + 22], 3 - pinsrw xmm3, word ptr [rsi + r13 + 22], 4 - pinsrw xmm3, word ptr [rsi + rbx + 22], 5 - pinsrw xmm3, word ptr [rsi + rdi + 22], 6 - pinsrw xmm3, word ptr [rsi + r9 + 22], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [rsi + rcx + 24], 1 - pinsrw xmm2, word ptr [rsi + r8 + 24], 2 - pinsrw xmm2, word ptr [rsi + r12 + 24], 3 - pinsrw xmm2, word ptr [rsi + r13 + 24], 4 - pinsrw xmm2, word ptr [rsi + rbx + 24], 5 - pinsrw xmm2, word ptr [rsi + rdi + 24], 6 - pinsrw xmm2, word ptr [rsi + r9 + 24], 7 - psubb xmm8, xmm7 - movdqa xmm10, xmmword ptr [rip + .LCPI4_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm14, xmm10 - movdqa xmm0, xmm3 - pblendvb xmm14, xmm15, xmm0 - movd xmm3, dword ptr [rsp + 48] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 40] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm14, xmm5 - movdqa xmm9, xmmword ptr [rip + .LCPI4_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm13, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm13, xmm15, xmm0 - movd xmm7, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r10d, word ptr [rsi + r15 + 42] - pinsrw xmm1, word ptr [rsi + rcx + 26], 1 - pinsrw xmm1, word ptr [rsi + r8 + 26], 2 - pinsrw xmm1, word ptr [rsi + r12 + 26], 3 - pinsrw xmm1, word ptr [rsi + r13 + 26], 4 - pinsrw xmm1, word ptr [rsi + rbx + 26], 5 - pinsrw xmm1, word ptr [rsi + rdi + 26], 6 - pinsrw xmm1, word ptr [rsi + r9 + 26], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm4, word ptr [rsi + rcx + 28], 1 - pinsrw xmm4, word ptr [rsi + r8 + 28], 2 - pinsrw xmm4, word ptr [rsi + r12 + 28], 3 - pinsrw xmm4, word ptr [rsi + r13 + 28], 4 - pinsrw xmm4, word ptr [rsi + rbx + 28], 5 - pinsrw xmm4, word ptr [rsi + rdi + 28], 6 - por xmm14, xmm8 - movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm5, xmm15, xmm0 - movd xmm2, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm2 = mem[0],zero,zero,zero - movzx edx, word ptr [rsi + r15 + 44] - mov dword ptr [rsp + 40], edx # 4-byte Spill - pinsrw xmm4, word ptr [rsi + r9 + 28], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm5, xmm13 - movdqa xmm6, xmmword ptr [rip + .LCPI4_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm15, xmm0 - movd xmm4, r14d - movzx edx, word ptr [rsi + r15 + 46] - mov dword ptr [rsp + 16], edx # 4-byte Spill - pinsrw xmm3, word ptr [rsi + rcx + 30], 1 - pinsrw xmm3, word ptr [rsi + r8 + 30], 2 - pinsrw xmm3, word ptr [rsi + r12 + 30], 3 - pinsrw xmm3, word ptr [rsi + r13 + 30], 4 - pinsrw xmm3, word ptr [rsi + rbx + 30], 5 - pinsrw xmm3, word ptr [rsi + rdi + 30], 6 - por xmm6, xmm5 - movd xmm1, r11d - movzx r11d, word ptr [rsi + r15 + 48] - pinsrw xmm3, word ptr [rsi + r9 + 30], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm2, word ptr [rsi + rcx + 34], 1 - pinsrw xmm2, word ptr [rsi + r8 + 34], 2 - pinsrw xmm2, word ptr [rsi + r12 + 34], 3 - pinsrw xmm2, word ptr [rsi + r13 + 34], 4 - pinsrw xmm2, word ptr [rsi + rbx + 34], 5 - pinsrw xmm2, word ptr [rsi + rdi + 34], 6 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [rsi + r9 + 34], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm6, xmm14 - movdqa xmm14, xmmword ptr [rip + .LCPI4_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm13, xmm14 - movdqa xmm0, xmm3 - pblendvb xmm13, xmm15, xmm0 - movdqa xmm8, xmmword ptr [rip + .LCPI4_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm8, xmm15, xmm0 - movd xmm2, eax - movzx r14d, word ptr [rsi + r15 + 50] - pinsrw xmm7, word ptr [rsi + rcx + 32], 1 - pinsrw xmm7, word ptr [rsi + r8 + 32], 2 - pinsrw xmm7, word ptr [rsi + r12 + 32], 3 - pinsrw xmm7, word ptr [rsi + r13 + 32], 4 - pinsrw xmm7, word ptr [rsi + rbx + 32], 5 - pinsrw xmm7, word ptr [rsi + rdi + 32], 6 - pinsrw xmm4, word ptr [rsi + rcx + 36], 1 - pinsrw xmm4, word ptr [rsi + r8 + 36], 2 - pinsrw xmm4, word ptr [rsi + r12 + 36], 3 - pinsrw xmm4, word ptr [rsi + r13 + 36], 4 - pinsrw xmm4, word ptr [rsi + rbx + 36], 5 - pinsrw xmm4, word ptr [rsi + rdi + 36], 6 - pinsrw xmm4, word ptr [rsi + r9 + 36], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm13, xmm6 - movdqa xmm6, xmmword ptr [rip + .LCPI4_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm15, xmm0 - movd xmm3, r10d - movzx edx, word ptr [rsi + r15 + 52] - pinsrw xmm7, word ptr [rsi + r9 + 32], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI4_22] - packsswb xmm7, xmm7 - pinsrw xmm1, word ptr [rsi + rcx + 38], 1 - pinsrw xmm1, word ptr [rsi + r8 + 38], 2 - pinsrw xmm1, word ptr [rsi + r12 + 38], 3 - pinsrw xmm1, word ptr [rsi + r13 + 38], 4 - pinsrw xmm1, word ptr [rsi + rbx + 38], 5 - pinsrw xmm1, word ptr [rsi + rdi + 38], 6 - pinsrw xmm1, word ptr [rsi + r9 + 38], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm2, word ptr [rsi + rcx + 40], 1 - pinsrw xmm2, word ptr [rsi + r8 + 40], 2 - pinsrw xmm2, word ptr [rsi + r12 + 40], 3 - pinsrw xmm2, word ptr [rsi + r13 + 40], 4 - pinsrw xmm2, word ptr [rsi + rbx + 40], 5 - pinsrw xmm2, word ptr [rsi + rdi + 40], 6 - pinsrw xmm2, word ptr [rsi + r9 + 40], 7 - psubb xmm8, xmm7 - movdqa xmm5, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm5, xmm15, xmm0 - movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx r10d, word ptr [rsi + r15 + 54] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm6 - movdqa xmm6, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm6, xmm15, xmm0 - movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 56] - pinsrw xmm3, word ptr [rsi + rcx + 42], 1 - pinsrw xmm3, word ptr [rsi + r8 + 42], 2 - pinsrw xmm3, word ptr [rsi + r12 + 42], 3 - pinsrw xmm3, word ptr [rsi + r13 + 42], 4 - pinsrw xmm3, word ptr [rsi + rbx + 42], 5 - pinsrw xmm3, word ptr [rsi + rdi + 42], 6 - pinsrw xmm3, word ptr [rsi + r9 + 42], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [rsi + rcx + 44], 1 - pinsrw xmm1, word ptr [rsi + r8 + 44], 2 - pinsrw xmm1, word ptr [rsi + r12 + 44], 3 - pinsrw xmm1, word ptr [rsi + r13 + 44], 4 - pinsrw xmm1, word ptr [rsi + rbx + 44], 5 - pinsrw xmm1, word ptr [rsi + rdi + 44], 6 - por xmm5, xmm8 - movdqa xmm9, xmmword ptr [rip + .LCPI4_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm2, xmm9 - movdqa xmm0, xmm3 - pblendvb xmm2, xmm15, xmm0 - movd xmm7, r11d - movzx r11d, word ptr [rsi + r15 + 58] - pinsrw xmm1, word ptr [rsi + r9 + 44], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm2, xmm6 - movdqa xmm10, xmmword ptr [rip + .LCPI4_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm15, xmm0 - movd xmm1, r14d - movzx r14d, word ptr [rsi + r15 + 60] - por xmm6, xmm2 - movd xmm2, edx - pinsrw xmm4, word ptr [rsi + rcx + 46], 1 - pinsrw xmm4, word ptr [rsi + r8 + 46], 2 - pinsrw xmm4, word ptr [rsi + r12 + 46], 3 - pinsrw xmm4, word ptr [rsi + r13 + 46], 4 - pinsrw xmm4, word ptr [rsi + rbx + 46], 5 - pinsrw xmm4, word ptr [rsi + rdi + 46], 6 - pinsrw xmm4, word ptr [rsi + r9 + 46], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm6, xmm5 - movdqa xmm8, xmm14 - movdqa xmm0, xmm4 - pblendvb xmm8, xmm15, xmm0 - movd xmm3, r10d - pinsrw xmm1, word ptr [rsi + rcx + 50], 1 - pinsrw xmm1, word ptr [rsi + r8 + 50], 2 - pinsrw xmm1, word ptr [rsi + r12 + 50], 3 - pinsrw xmm1, word ptr [rsi + r13 + 50], 4 - pinsrw xmm1, word ptr [rsi + rbx + 50], 5 - pinsrw xmm1, word ptr [rsi + rdi + 50], 6 - pinsrw xmm1, word ptr [rsi + r9 + 50], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm8, xmm6 - movdqa xmm4, xmmword ptr [rip + .LCPI4_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm15, xmm0 - movd xmm1, eax - pinsrw xmm7, word ptr [rsi + rcx + 48], 1 - pinsrw xmm7, word ptr [rsi + r8 + 48], 2 - pinsrw xmm7, word ptr [rsi + r12 + 48], 3 - pinsrw xmm7, word ptr [rsi + r13 + 48], 4 - pinsrw xmm7, word ptr [rsi + rbx + 48], 5 - pinsrw xmm7, word ptr [rsi + rdi + 48], 6 - pinsrw xmm7, word ptr [rsi + r9 + 48], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI4_22] - pinsrw xmm2, word ptr [rsi + rcx + 52], 1 - pinsrw xmm2, word ptr [rsi + r8 + 52], 2 - pinsrw xmm2, word ptr [rsi + r12 + 52], 3 - pinsrw xmm2, word ptr [rsi + r13 + 52], 4 - pinsrw xmm2, word ptr [rsi + rbx + 52], 5 - pinsrw xmm2, word ptr [rsi + rdi + 52], 6 - packsswb xmm7, xmm7 - pinsrw xmm2, word ptr [rsi + r9 + 52], 7 - pcmpeqw xmm2, xmm11 - pinsrw xmm3, word ptr [rsi + rcx + 54], 1 - pinsrw xmm3, word ptr [rsi + r8 + 54], 2 - pinsrw xmm3, word ptr [rsi + r12 + 54], 3 - pinsrw xmm3, word ptr [rsi + r13 + 54], 4 - pinsrw xmm3, word ptr [rsi + rbx + 54], 5 - pinsrw xmm3, word ptr [rsi + rdi + 54], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [rsi + r9 + 54], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm1, word ptr [rsi + rcx + 56], 1 - pinsrw xmm1, word ptr [rsi + r8 + 56], 2 - pinsrw xmm1, word ptr [rsi + r12 + 56], 3 - pinsrw xmm1, word ptr [rsi + r13 + 56], 4 - pinsrw xmm1, word ptr [rsi + rbx + 56], 5 - pinsrw xmm1, word ptr [rsi + rdi + 56], 6 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [rsi + r9 + 56], 7 - psubb xmm4, xmm7 - movdqa xmm5, xmmword ptr [rip + .LCPI4_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm5, xmm15, xmm0 - movdqa xmm6, xmmword ptr [rip + .LCPI4_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm3 - pblendvb xmm6, xmm15, xmm0 - movd xmm2, r11d - pcmpeqw xmm1, xmm11 - pinsrw xmm2, word ptr [rsi + rcx + 58], 1 - pinsrw xmm2, word ptr [rsi + r8 + 58], 2 - pinsrw xmm2, word ptr [rsi + r12 + 58], 3 - pinsrw xmm2, word ptr [rsi + r13 + 58], 4 - pinsrw xmm2, word ptr [rsi + rbx + 58], 5 - pinsrw xmm2, word ptr [rsi + rdi + 58], 6 - pinsrw xmm2, word ptr [rsi + r9 + 58], 7 - packsswb xmm1, xmm1 - pcmpeqw xmm2, xmm11 - por xmm6, xmm5 - movd xmm3, r14d - pinsrw xmm3, word ptr [rsi + rcx + 60], 1 - pinsrw xmm3, word ptr [rsi + r8 + 60], 2 - pinsrw xmm3, word ptr [rsi + r12 + 60], 3 - pinsrw xmm3, word ptr [rsi + r13 + 60], 4 - pinsrw xmm3, word ptr [rsi + rbx + 60], 5 - pinsrw xmm3, word ptr [rsi + rdi + 60], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [rsi + r9 + 60], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - por xmm6, xmm4 - movdqa xmm4, xmmword ptr [rip + .LCPI4_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm15, xmm0 - movdqa xmm1, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm1, xmm15, xmm0 - movdqa xmm0, xmm3 - pblendvb xmm10, xmm15, xmm0 - por xmm1, xmm4 - movzx eax, word ptr [rsi + r15 + 62] - por xmm10, xmm1 - movd xmm0, eax - pinsrw xmm0, word ptr [rsi + rcx + 62], 1 - pinsrw xmm0, word ptr [rsi + r8 + 62], 2 - pinsrw xmm0, word ptr [rsi + r12 + 62], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrw xmm0, word ptr [rsi + r13 + 62], 4 - pinsrw xmm0, word ptr [rsi + rbx + 62], 5 - pinsrw xmm0, word ptr [rsi + rdi + 62], 6 - pinsrw xmm0, word ptr [rsi + r9 + 62], 7 - pcmpeqw xmm0, xmm11 - packsswb xmm0, xmm0 - por xmm10, xmm6 - pblendvb xmm14, xmm15, xmm0 - por xmm14, xmm10 - movdqa xmm0, xmm12 - punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] - movdqa xmm2, xmm8 - punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] - movdqa xmm3, xmmword ptr [rip + .LCPI4_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> - pshufb xmm2, xmm3 - pshufb xmm0, xmm3 - punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] - punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] - punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] - punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx], xmm12 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm0 - add rcx, 8 - mov r15, rcx - cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB4_186 -# %bb.187: - mov r10, qword ptr [rsp + 192] # 8-byte Reload - cmp r10, qword ptr [rsp + 32] # 8-byte Folded Reload +.LBB4_142: # =>This Inner Loop Header: Depth=1 + mov r11, rsi + cmp word ptr [rsi], r13w + setne byte ptr [rsp + 152] # 1-byte Folded Spill + cmp word ptr [rsi + 2], r13w + setne sil + cmp word ptr [r11 + 4], r13w + setne r15b + cmp word ptr [r11 + 6], r13w + setne r12b + cmp word ptr [r11 + 8], r13w + setne byte ptr [rsp + 208] # 1-byte Folded Spill + cmp word ptr [r11 + 10], r13w + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp word ptr [r11 + 12], r13w + setne al + cmp word ptr [r11 + 14], r13w + setne bl + cmp word ptr [r11 + 16], r13w + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [r11 + 18], r13w + setne cl + cmp word ptr [r11 + 20], r13w + setne r8b + cmp word ptr [r11 + 22], r13w + setne r9b + cmp word ptr [r11 + 24], r13w + setne r14b + cmp word ptr [r11 + 26], r13w + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp word ptr [r11 + 28], r13w + setne byte ptr [rsp + 224] # 1-byte Folded Spill + cmp word ptr [r11 + 30], r13w + setne dil + cmp word ptr [r11 + 32], r13w + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp word ptr [r11 + 34], r13w + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp word ptr [r11 + 36], r13w + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp word ptr [r11 + 38], r13w + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp word ptr [r11 + 40], r13w + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp word ptr [r11 + 42], r13w + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp word ptr [r11 + 44], r13w + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp word ptr [r11 + 46], r13w + setne r10b + cmp word ptr [r11 + 48], r13w + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp word ptr [r11 + 50], r13w + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp word ptr [r11 + 52], r13w + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp word ptr [r11 + 54], r13w + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp word ptr [r11 + 56], r13w + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp word ptr [r11 + 58], r13w + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp word ptr [r11 + 60], r13w + setne byte ptr [rsp + 120] # 1-byte Folded Spill + cmp word ptr [r11 + 62], r13w + setne dl + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r15b, 2 + or r15b, sil + add cl, cl + add cl, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r12b, 3 + or r12b, r15b + shl r8b, 2 + or r8b, cl + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl cl, 4 + or cl, r12b + mov esi, ecx + shl r9b, 3 + or r9b, r8b + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + shl r14b, 4 + or r14b, r9b + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 224] # 1-byte Folded Reload + shl sil, 6 + shl dil, 7 + or dil, sil + or bl, cl + or dil, al + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov esi, ecx + mov rcx, qword ptr [rsp + 8] # 8-byte Reload + mov byte ptr [rcx], bl + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + shl r10b, 7 + or r10b, bl + mov byte ptr [rcx + 1], dil + or r10b, sil + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rcx + 2], r10b + mov byte ptr [rcx + 3], dl + lea rsi, [r11 + 64] + add rcx, 4 + mov qword ptr [rsp + 8], rcx # 8-byte Spill + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB4_142 +# %bb.143: mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r13d, dword ptr [rsp + 64] # 4-byte Reload mov r12, qword ptr [rsp + 8] # 8-byte Reload - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - jne .LBB4_92 - jmp .LBB4_95 -.LBB4_188: - mov r8, r10 - and r8, -4 - mov rbx, r8 - shl rbx, 7 - add rbx, rsi - lea r15, [r12 + 4*r8] - movaps xmm1, xmm0 - shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] - add rsi, 508 - xor ecx, ecx - movdqa xmm15, xmmword ptr [rip + .LCPI4_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> - movdqa xmm8, xmmword ptr [rip + .LCPI4_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - movdqa xmm10, xmmword ptr [rip + .LCPI4_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - movdqa xmm11, xmmword ptr [rip + .LCPI4_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - movdqa xmm12, xmmword ptr [rip + .LCPI4_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - movdqa xmm13, xmmword ptr [rip + .LCPI4_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] - movdqa xmm14, xmmword ptr [rip + .LCPI4_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - movdqa xmm9, xmmword ptr [rip + .LCPI4_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] + mov rcx, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_144: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB4_208 +# %bb.145: + or rcx, 1 + cmp r14, rcx + je .LBB4_160 +# %bb.146: + mov r9, r8 + and r9, -2 + xor r14d, r14d .p2align 4, 0x90 -.LBB4_189: # =>This Inner Loop Header: Depth=1 - movss xmm6, dword ptr [rsi - 508] # xmm6 = mem[0],zero,zero,zero - movss xmm7, dword ptr [rsi - 504] # xmm7 = mem[0],zero,zero,zero - movss xmm5, dword ptr [rsi - 500] # xmm5 = mem[0],zero,zero,zero - movss xmm4, dword ptr [rsi - 496] # xmm4 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rsi - 380], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rsi - 252], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rsi - 124], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - insertps xmm7, dword ptr [rsi - 376], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rsi - 248], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rsi - 120], 48 # xmm7 = xmm7[0,1,2],mem[0] - insertps xmm5, dword ptr [rsi - 372], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rsi - 244], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rsi - 116], 48 # xmm5 = xmm5[0,1,2],mem[0] - insertps xmm4, dword ptr [rsi - 368], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] - insertps xmm4, dword ptr [rsi - 240], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] - insertps xmm4, dword ptr [rsi - 112], 48 # xmm4 = xmm4[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - movdqa xmm2, xmm7 - pand xmm2, xmm15 - psubb xmm2, xmm7 - movss xmm7, dword ptr [rsi - 492] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rsi - 364], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rsi - 236], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rsi - 108], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm2, xmm6 - movss xmm6, dword ptr [rsi - 488] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rsi - 360], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rsi - 232], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rsi - 104], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 2 - pand xmm5, xmm8 - por xmm5, xmm2 - movss xmm3, dword ptr [rsi - 484] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rsi - 356], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rsi - 228], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [rsi - 100], 48 # xmm3 = xmm3[0,1,2],mem[0] - cmpneqps xmm4, xmm1 - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 - pand xmm4, xmm15 - psllw xmm4, 3 - pand xmm4, xmm10 - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 4 - pand xmm7, xmm11 - por xmm7, xmm4 - movss xmm4, dword ptr [rsi - 480] # xmm4 = mem[0],zero,zero,zero - insertps xmm4, dword ptr [rsi - 352], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] - insertps xmm4, dword ptr [rsi - 224], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] - insertps xmm4, dword ptr [rsi - 96], 48 # xmm4 = xmm4[0,1,2],mem[0] - por xmm7, xmm5 - movss xmm5, dword ptr [rsi - 476] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rsi - 348], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rsi - 220], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rsi - 92], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 6 - pand xmm3, xmm13 - por xmm3, xmm6 - movss xmm2, dword ptr [rsi - 472] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rsi - 344], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rsi - 216], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rsi - 88], 48 # xmm2 = xmm2[0,1,2],mem[0] - packsswb xmm5, xmm5 - cmpneqps xmm4, xmm1 - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 - psllw xmm4, 7 - pand xmm4, xmm14 - por xmm4, xmm3 - movss xmm3, dword ptr [rsi - 468] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rsi - 340], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rsi - 212], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - pand xmm5, xmm15 - insertps xmm3, dword ptr [rsi - 84], 48 # xmm3 = xmm3[0,1,2],mem[0] - por xmm4, xmm7 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm6, xmm2 - pand xmm6, xmm15 - psubb xmm6, xmm2 - movss xmm7, dword ptr [rsi - 464] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rsi - 336], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rsi - 208], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rsi - 80], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm6, xmm5 - movss xmm5, dword ptr [rsi - 460] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rsi - 332], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rsi - 204], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rsi - 76], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm6 - movss xmm6, dword ptr [rsi - 456] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rsi - 328], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rsi - 200], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rsi - 72], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 3 - pand xmm7, xmm10 - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 4 - pand xmm5, xmm11 - por xmm5, xmm7 - movss xmm2, dword ptr [rsi - 452] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rsi - 324], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rsi - 196], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rsi - 68], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm5, xmm3 - movss xmm7, dword ptr [rsi - 448] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rsi - 320], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rsi - 192], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rsi - 64], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm6 - movss xmm6, dword ptr [rsi - 444] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rsi - 316], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rsi - 188], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rsi - 60], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - psllw xmm7, 7 - pand xmm7, xmm14 - por xmm7, xmm2 - movss xmm2, dword ptr [rsi - 440] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rsi - 312], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rsi - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rsi - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm7, xmm5 - movss xmm3, dword ptr [rsi - 436] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rsi - 308], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rsi - 180], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - pand xmm6, xmm15 - insertps xmm3, dword ptr [rsi - 52], 48 # xmm3 = xmm3[0,1,2],mem[0] - punpckldq xmm4, xmm7 # xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1] - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm7, xmm2 - pand xmm7, xmm15 - psubb xmm7, xmm2 - movss xmm5, dword ptr [rsi - 432] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rsi - 304], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rsi - 176], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rsi - 48], 48 # xmm5 = xmm5[0,1,2],mem[0] - por xmm7, xmm6 - movss xmm6, dword ptr [rsi - 428] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rsi - 300], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rsi - 172], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rsi - 44], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm7 - movss xmm7, dword ptr [rsi - 424] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rsi - 296], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rsi - 168], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rsi - 40], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 3 - pand xmm5, xmm10 - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 4 - pand xmm6, xmm11 - por xmm6, xmm5 - movss xmm2, dword ptr [rsi - 420] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rsi - 292], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rsi - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rsi - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm6, xmm3 - movss xmm5, dword ptr [rsi - 416] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rsi - 288], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rsi - 160], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rsi - 32], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 5 - pand xmm7, xmm12 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm7 - movss xmm7, dword ptr [rsi - 412] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rsi - 284], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rsi - 156], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rsi - 28], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - psllw xmm5, 7 - pand xmm5, xmm14 - por xmm5, xmm2 - movss xmm2, dword ptr [rsi - 408] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rsi - 280], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rsi - 152], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - pand xmm7, xmm15 - insertps xmm2, dword ptr [rsi - 24], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm5, xmm6 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm6, xmm2 - pand xmm6, xmm15 - psubb xmm6, xmm2 - movss xmm3, dword ptr [rsi - 404] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rsi - 276], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rsi - 148], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [rsi - 20], 48 # xmm3 = xmm3[0,1,2],mem[0] - por xmm6, xmm7 - movss xmm2, dword ptr [rsi - 400] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rsi - 272], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rsi - 144], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rsi - 16], 48 # xmm2 = xmm2[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm6 - movss xmm6, dword ptr [rsi - 396] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rsi - 268], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rsi - 140], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rsi - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 3 - pand xmm2, xmm10 - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 4 - pand xmm6, xmm11 - por xmm6, xmm2 - movss xmm7, dword ptr [rsi - 392] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rsi - 264], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rsi - 136], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rsi - 8], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm6, xmm3 - movss xmm2, dword ptr [rsi - 388] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rsi - 260], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rsi - 132], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rsi - 4], 48 # xmm2 = xmm2[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 5 - pand xmm7, xmm12 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm7 - movss xmm3, dword ptr [rsi - 384] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rsi - 256], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rsi - 128], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [rsi], 48 # xmm3 = xmm3[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - psllw xmm3, 7 - pand xmm3, xmm14 - por xmm3, xmm2 - por xmm3, xmm6 - punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] - punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] - pshufb xmm4, xmm9 - movdqu xmmword ptr [r12 + 4*rcx], xmm4 - add rcx, 4 - add rsi, 512 - cmp r8, rcx - jne .LBB4_189 -# %bb.190: - cmp r10, r8 - jne .LBB4_134 - jmp .LBB4_146 -.LBB4_191: - and r10, -8 - mov rax, r10 +.LBB4_147: # =>This Inner Loop Header: Depth=1 + mov rax, rsi + cmp word ptr [rsi], r13w + setne dl + neg dl + mov rdi, r14 + shr rdi, 3 + movzx r10d, byte ptr [r12 + rdi] + mov ecx, r14d + and cl, 6 + mov bl, 1 + shl bl, cl + xor dl, r10b + and bl, dl + xor bl, r10b + mov byte ptr [r12 + rdi], bl + add r14, 2 + cmp word ptr [rsi + 2], r13w + lea rsi, [rsi + 4] + setne dl + neg dl + xor dl, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, bl + mov byte ptr [r12 + rdi], al + cmp r9, r14 + jne .LBB4_147 + jmp .LBB4_205 +.LBB4_148: + mov r15d, r13d + sub r14, r8 + je .LBB4_208 +.LBB4_149: + mov r13d, r15d + add r12, 1 +.LBB4_150: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB4_158 +# %bb.151: + cmp rcx, 8 + mov qword ptr [rsp + 144], r14 # 8-byte Spill + mov qword ptr [rsp + 176], rcx # 8-byte Spill + jb .LBB4_154 +# %bb.152: + mov rax, rcx shl rax, 6 add rax, rsi - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov qword ptr [rsp + 32], r10 # 8-byte Spill - lea rax, [r12 + 4*r10] - mov qword ptr [rsp + 8], rax # 8-byte Spill - mov dword ptr [rsp + 64], r13d # 4-byte Spill - movd xmm0, r13d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] - xor r15d, r15d - mov qword ptr [rsp + 128], r12 # 8-byte Spill - pxor xmm15, xmm15 + cmp r12, rax + jae .LBB4_218 +# %bb.153: + lea rax, [r12 + 4*rcx] + cmp rax, rsi + jbe .LBB4_218 +.LBB4_154: + xor eax, eax + mov qword ptr [rsp + 40], rax # 8-byte Spill +.LBB4_155: + mov qword ptr [rsp + 8], r12 # 8-byte Spill + sub rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + mov qword ptr [rsp + 240], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB4_192: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 24], r15 # 8-byte Spill - shl r15, 6 - mov r8, r15 - mov r12, r15 - mov r13, r15 - mov rbx, r15 - mov rdi, r15 - mov r9, r15 - movzx eax, word ptr [rsi + r15] - movd xmm5, eax - movzx eax, word ptr [rsi + r15 + 2] - movd xmm0, eax - movzx eax, word ptr [rsi + r15 + 4] - movd xmm1, eax - movzx eax, word ptr [rsi + r15 + 6] - movd xmm7, eax - movzx eax, word ptr [rsi + r15 + 8] - movd xmm8, eax - movzx eax, word ptr [rsi + r15 + 10] - movd xmm4, eax - movzx eax, word ptr [rsi + r15 + 12] - movzx r10d, word ptr [rsi + r15 + 14] - movzx r11d, word ptr [rsi + r15 + 16] - movzx edx, word ptr [rsi + r15 + 18] - movzx r14d, word ptr [rsi + r15 + 20] - mov rcx, r15 - or rcx, 64 - or r8, 128 - or r12, 192 - or r13, 256 - or rbx, 320 - or rdi, 384 - pinsrw xmm5, word ptr [rsi + rcx], 1 - pinsrw xmm5, word ptr [rsi + r8], 2 - pinsrw xmm5, word ptr [rsi + r12], 3 - pinsrw xmm5, word ptr [rsi + r13], 4 - pinsrw xmm5, word ptr [rsi + rbx], 5 - pinsrw xmm5, word ptr [rsi + rdi], 6 - pinsrw xmm0, word ptr [rsi + rcx + 2], 1 - pinsrw xmm0, word ptr [rsi + r8 + 2], 2 - pinsrw xmm0, word ptr [rsi + r12 + 2], 3 - pinsrw xmm0, word ptr [rsi + r13 + 2], 4 - pinsrw xmm0, word ptr [rsi + rbx + 2], 5 - pinsrw xmm0, word ptr [rsi + rdi + 2], 6 - or r9, 448 - pinsrw xmm0, word ptr [rsi + r9 + 2], 7 - movd xmm2, eax - movzx eax, word ptr [rsi + r15 + 22] - mov dword ptr [rsp + 16], eax # 4-byte Spill - pcmpeqw xmm0, xmm11 - pinsrw xmm1, word ptr [rsi + rcx + 4], 1 - pinsrw xmm1, word ptr [rsi + r8 + 4], 2 - pinsrw xmm1, word ptr [rsi + r12 + 4], 3 - pinsrw xmm1, word ptr [rsi + r13 + 4], 4 - pinsrw xmm1, word ptr [rsi + rbx + 4], 5 - pinsrw xmm1, word ptr [rsi + rdi + 4], 6 - pinsrw xmm1, word ptr [rsi + r9 + 4], 7 - packsswb xmm0, xmm0 - pcmpeqw xmm1, xmm11 - movdqa xmm9, xmmword ptr [rip + .LCPI4_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm3, xmm9 - pblendvb xmm3, xmm15, xmm0 - packsswb xmm1, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI4_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm0 - movdqa xmm14, xmm0 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm15, xmm0 - movd xmm1, r10d - movzx r10d, word ptr [rsi + r15 + 24] - pinsrw xmm5, word ptr [rsi + r9], 7 - pcmpeqw xmm5, xmm11 - pcmpeqd xmm0, xmm0 - pxor xmm5, xmm0 - packsswb xmm5, xmm5 - pinsrw xmm7, word ptr [rsi + rcx + 6], 1 - pinsrw xmm7, word ptr [rsi + r8 + 6], 2 - pinsrw xmm7, word ptr [rsi + r12 + 6], 3 - pinsrw xmm7, word ptr [rsi + r13 + 6], 4 - pinsrw xmm7, word ptr [rsi + rbx + 6], 5 - pinsrw xmm7, word ptr [rsi + rdi + 6], 6 - pinsrw xmm7, word ptr [rsi + r9 + 6], 7 - pcmpeqw xmm7, xmm11 - packsswb xmm7, xmm7 - pinsrw xmm8, word ptr [rsi + rcx + 8], 1 - pinsrw xmm8, word ptr [rsi + r8 + 8], 2 - pinsrw xmm8, word ptr [rsi + r12 + 8], 3 - pinsrw xmm8, word ptr [rsi + r13 + 8], 4 - pinsrw xmm8, word ptr [rsi + rbx + 8], 5 - pinsrw xmm8, word ptr [rsi + rdi + 8], 6 - pinsrw xmm8, word ptr [rsi + r9 + 8], 7 - psubb xmm3, xmm5 - movdqa xmm12, xmmword ptr [rip + .LCPI4_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm7 - pblendvb xmm12, xmm15, xmm0 - movd xmm7, r11d - movzx eax, word ptr [rsi + r15 + 26] - pcmpeqw xmm8, xmm11 - packsswb xmm8, xmm8 - por xmm12, xmm6 - movdqa xmm13, xmmword ptr [rip + .LCPI4_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm8 - pblendvb xmm13, xmm15, xmm0 - movd xmm6, edx - movzx r11d, word ptr [rsi + r15 + 28] - pinsrw xmm4, word ptr [rsi + rcx + 10], 1 - pinsrw xmm4, word ptr [rsi + r8 + 10], 2 - pinsrw xmm4, word ptr [rsi + r12 + 10], 3 - pinsrw xmm4, word ptr [rsi + r13 + 10], 4 - pinsrw xmm4, word ptr [rsi + rbx + 10], 5 - pinsrw xmm4, word ptr [rsi + rdi + 10], 6 - pinsrw xmm4, word ptr [rsi + r9 + 10], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - pinsrw xmm2, word ptr [rsi + rcx + 12], 1 - pinsrw xmm2, word ptr [rsi + r8 + 12], 2 - pinsrw xmm2, word ptr [rsi + r12 + 12], 3 - pinsrw xmm2, word ptr [rsi + r13 + 12], 4 - pinsrw xmm2, word ptr [rsi + rbx + 12], 5 - pinsrw xmm2, word ptr [rsi + rdi + 12], 6 - por xmm12, xmm3 - movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm5, xmm15, xmm0 - movd xmm4, r14d - movzx edx, word ptr [rsi + r15 + 30] - mov dword ptr [rsp + 48], edx # 4-byte Spill - pinsrw xmm2, word ptr [rsi + r9 + 12], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm13 - movdqa xmm13, xmmword ptr [rip + .LCPI4_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm13, xmm15, xmm0 - movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx edx, word ptr [rsi + r15 + 32] - mov dword ptr [rsp + 40], edx # 4-byte Spill - pinsrw xmm1, word ptr [rsi + rcx + 14], 1 - pinsrw xmm1, word ptr [rsi + r8 + 14], 2 - pinsrw xmm1, word ptr [rsi + r12 + 14], 3 - pinsrw xmm1, word ptr [rsi + r13 + 14], 4 - pinsrw xmm1, word ptr [rsi + rbx + 14], 5 - pinsrw xmm1, word ptr [rsi + rdi + 14], 6 - por xmm13, xmm5 - movd xmm2, r10d - movzx edx, word ptr [rsi + r15 + 34] - mov dword ptr [rsp + 16], edx # 4-byte Spill - pinsrw xmm1, word ptr [rsi + r9 + 14], 7 - pcmpeqw xmm1, xmm11 - pinsrw xmm6, word ptr [rsi + rcx + 18], 1 - pinsrw xmm6, word ptr [rsi + r8 + 18], 2 - pinsrw xmm6, word ptr [rsi + r12 + 18], 3 - pinsrw xmm6, word ptr [rsi + r13 + 18], 4 - pinsrw xmm6, word ptr [rsi + rbx + 18], 5 - pinsrw xmm6, word ptr [rsi + rdi + 18], 6 - packsswb xmm1, xmm1 - pinsrw xmm6, word ptr [rsi + r9 + 18], 7 - pcmpeqw xmm6, xmm11 - packsswb xmm6, xmm6 - por xmm13, xmm12 - movdqa xmm12, xmmword ptr [rip + .LCPI4_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm12, xmm15, xmm0 - movdqa xmm8, xmm9 - movdqa xmm0, xmm6 - pblendvb xmm8, xmm15, xmm0 - movd xmm1, eax - movzx r14d, word ptr [rsi + r15 + 36] - pinsrw xmm7, word ptr [rsi + rcx + 16], 1 - pinsrw xmm7, word ptr [rsi + r8 + 16], 2 - pinsrw xmm7, word ptr [rsi + r12 + 16], 3 - pinsrw xmm7, word ptr [rsi + r13 + 16], 4 - pinsrw xmm7, word ptr [rsi + rbx + 16], 5 - pinsrw xmm7, word ptr [rsi + rdi + 16], 6 - pinsrw xmm4, word ptr [rsi + rcx + 20], 1 - pinsrw xmm4, word ptr [rsi + r8 + 20], 2 - pinsrw xmm4, word ptr [rsi + r12 + 20], 3 - pinsrw xmm4, word ptr [rsi + r13 + 20], 4 - pinsrw xmm4, word ptr [rsi + rbx + 20], 5 - pinsrw xmm4, word ptr [rsi + rdi + 20], 6 - pinsrw xmm4, word ptr [rsi + r9 + 20], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm12, xmm13 - movdqa xmm5, xmm14 - movdqa xmm0, xmm4 - pblendvb xmm5, xmm15, xmm0 - movd xmm4, r11d - movzx r11d, word ptr [rsi + r15 + 38] - pinsrw xmm7, word ptr [rsi + r9 + 16], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI4_22] - packsswb xmm7, xmm7 - pinsrw xmm3, word ptr [rsi + rcx + 22], 1 - pinsrw xmm3, word ptr [rsi + r8 + 22], 2 - pinsrw xmm3, word ptr [rsi + r12 + 22], 3 - pinsrw xmm3, word ptr [rsi + r13 + 22], 4 - pinsrw xmm3, word ptr [rsi + rbx + 22], 5 - pinsrw xmm3, word ptr [rsi + rdi + 22], 6 - pinsrw xmm3, word ptr [rsi + r9 + 22], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [rsi + rcx + 24], 1 - pinsrw xmm2, word ptr [rsi + r8 + 24], 2 - pinsrw xmm2, word ptr [rsi + r12 + 24], 3 - pinsrw xmm2, word ptr [rsi + r13 + 24], 4 - pinsrw xmm2, word ptr [rsi + rbx + 24], 5 - pinsrw xmm2, word ptr [rsi + rdi + 24], 6 - pinsrw xmm2, word ptr [rsi + r9 + 24], 7 - psubb xmm8, xmm7 - movdqa xmm10, xmmword ptr [rip + .LCPI4_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm14, xmm10 - movdqa xmm0, xmm3 - pblendvb xmm14, xmm15, xmm0 - movd xmm3, dword ptr [rsp + 48] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 40] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm14, xmm5 - movdqa xmm9, xmmword ptr [rip + .LCPI4_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm13, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm13, xmm15, xmm0 - movd xmm7, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r10d, word ptr [rsi + r15 + 42] - pinsrw xmm1, word ptr [rsi + rcx + 26], 1 - pinsrw xmm1, word ptr [rsi + r8 + 26], 2 - pinsrw xmm1, word ptr [rsi + r12 + 26], 3 - pinsrw xmm1, word ptr [rsi + r13 + 26], 4 - pinsrw xmm1, word ptr [rsi + rbx + 26], 5 - pinsrw xmm1, word ptr [rsi + rdi + 26], 6 - pinsrw xmm1, word ptr [rsi + r9 + 26], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm4, word ptr [rsi + rcx + 28], 1 - pinsrw xmm4, word ptr [rsi + r8 + 28], 2 - pinsrw xmm4, word ptr [rsi + r12 + 28], 3 - pinsrw xmm4, word ptr [rsi + r13 + 28], 4 - pinsrw xmm4, word ptr [rsi + rbx + 28], 5 - pinsrw xmm4, word ptr [rsi + rdi + 28], 6 - por xmm14, xmm8 - movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm5, xmm15, xmm0 - movd xmm2, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm2 = mem[0],zero,zero,zero - movzx edx, word ptr [rsi + r15 + 44] - mov dword ptr [rsp + 40], edx # 4-byte Spill - pinsrw xmm4, word ptr [rsi + r9 + 28], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm5, xmm13 - movdqa xmm6, xmmword ptr [rip + .LCPI4_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm15, xmm0 - movd xmm4, r14d - movzx edx, word ptr [rsi + r15 + 46] - mov dword ptr [rsp + 16], edx # 4-byte Spill - pinsrw xmm3, word ptr [rsi + rcx + 30], 1 - pinsrw xmm3, word ptr [rsi + r8 + 30], 2 - pinsrw xmm3, word ptr [rsi + r12 + 30], 3 - pinsrw xmm3, word ptr [rsi + r13 + 30], 4 - pinsrw xmm3, word ptr [rsi + rbx + 30], 5 - pinsrw xmm3, word ptr [rsi + rdi + 30], 6 - por xmm6, xmm5 - movd xmm1, r11d - movzx r11d, word ptr [rsi + r15 + 48] - pinsrw xmm3, word ptr [rsi + r9 + 30], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm2, word ptr [rsi + rcx + 34], 1 - pinsrw xmm2, word ptr [rsi + r8 + 34], 2 - pinsrw xmm2, word ptr [rsi + r12 + 34], 3 - pinsrw xmm2, word ptr [rsi + r13 + 34], 4 - pinsrw xmm2, word ptr [rsi + rbx + 34], 5 - pinsrw xmm2, word ptr [rsi + rdi + 34], 6 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [rsi + r9 + 34], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm6, xmm14 - movdqa xmm14, xmmword ptr [rip + .LCPI4_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm13, xmm14 - movdqa xmm0, xmm3 - pblendvb xmm13, xmm15, xmm0 - movdqa xmm8, xmmword ptr [rip + .LCPI4_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm8, xmm15, xmm0 - movd xmm2, eax - movzx r14d, word ptr [rsi + r15 + 50] - pinsrw xmm7, word ptr [rsi + rcx + 32], 1 - pinsrw xmm7, word ptr [rsi + r8 + 32], 2 - pinsrw xmm7, word ptr [rsi + r12 + 32], 3 - pinsrw xmm7, word ptr [rsi + r13 + 32], 4 - pinsrw xmm7, word ptr [rsi + rbx + 32], 5 - pinsrw xmm7, word ptr [rsi + rdi + 32], 6 - pinsrw xmm4, word ptr [rsi + rcx + 36], 1 - pinsrw xmm4, word ptr [rsi + r8 + 36], 2 - pinsrw xmm4, word ptr [rsi + r12 + 36], 3 - pinsrw xmm4, word ptr [rsi + r13 + 36], 4 - pinsrw xmm4, word ptr [rsi + rbx + 36], 5 - pinsrw xmm4, word ptr [rsi + rdi + 36], 6 - pinsrw xmm4, word ptr [rsi + r9 + 36], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm13, xmm6 - movdqa xmm6, xmmword ptr [rip + .LCPI4_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm15, xmm0 - movd xmm3, r10d - movzx edx, word ptr [rsi + r15 + 52] - pinsrw xmm7, word ptr [rsi + r9 + 32], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI4_22] - packsswb xmm7, xmm7 - pinsrw xmm1, word ptr [rsi + rcx + 38], 1 - pinsrw xmm1, word ptr [rsi + r8 + 38], 2 - pinsrw xmm1, word ptr [rsi + r12 + 38], 3 - pinsrw xmm1, word ptr [rsi + r13 + 38], 4 - pinsrw xmm1, word ptr [rsi + rbx + 38], 5 - pinsrw xmm1, word ptr [rsi + rdi + 38], 6 - pinsrw xmm1, word ptr [rsi + r9 + 38], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm2, word ptr [rsi + rcx + 40], 1 - pinsrw xmm2, word ptr [rsi + r8 + 40], 2 - pinsrw xmm2, word ptr [rsi + r12 + 40], 3 - pinsrw xmm2, word ptr [rsi + r13 + 40], 4 - pinsrw xmm2, word ptr [rsi + rbx + 40], 5 - pinsrw xmm2, word ptr [rsi + rdi + 40], 6 - pinsrw xmm2, word ptr [rsi + r9 + 40], 7 - psubb xmm8, xmm7 - movdqa xmm5, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm5, xmm15, xmm0 - movd xmm1, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx r10d, word ptr [rsi + r15 + 54] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm6 - movdqa xmm6, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm6, xmm15, xmm0 - movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx eax, word ptr [rsi + r15 + 56] - pinsrw xmm3, word ptr [rsi + rcx + 42], 1 - pinsrw xmm3, word ptr [rsi + r8 + 42], 2 - pinsrw xmm3, word ptr [rsi + r12 + 42], 3 - pinsrw xmm3, word ptr [rsi + r13 + 42], 4 - pinsrw xmm3, word ptr [rsi + rbx + 42], 5 - pinsrw xmm3, word ptr [rsi + rdi + 42], 6 - pinsrw xmm3, word ptr [rsi + r9 + 42], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [rsi + rcx + 44], 1 - pinsrw xmm1, word ptr [rsi + r8 + 44], 2 - pinsrw xmm1, word ptr [rsi + r12 + 44], 3 - pinsrw xmm1, word ptr [rsi + r13 + 44], 4 - pinsrw xmm1, word ptr [rsi + rbx + 44], 5 - pinsrw xmm1, word ptr [rsi + rdi + 44], 6 - por xmm5, xmm8 - movdqa xmm9, xmmword ptr [rip + .LCPI4_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm2, xmm9 - movdqa xmm0, xmm3 - pblendvb xmm2, xmm15, xmm0 - movd xmm7, r11d - movzx r11d, word ptr [rsi + r15 + 58] - pinsrw xmm1, word ptr [rsi + r9 + 44], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm2, xmm6 - movdqa xmm10, xmmword ptr [rip + .LCPI4_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm15, xmm0 - movd xmm1, r14d - movzx r14d, word ptr [rsi + r15 + 60] - por xmm6, xmm2 - movd xmm2, edx - pinsrw xmm4, word ptr [rsi + rcx + 46], 1 - pinsrw xmm4, word ptr [rsi + r8 + 46], 2 - pinsrw xmm4, word ptr [rsi + r12 + 46], 3 - pinsrw xmm4, word ptr [rsi + r13 + 46], 4 - pinsrw xmm4, word ptr [rsi + rbx + 46], 5 - pinsrw xmm4, word ptr [rsi + rdi + 46], 6 - pinsrw xmm4, word ptr [rsi + r9 + 46], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm6, xmm5 - movdqa xmm8, xmm14 - movdqa xmm0, xmm4 - pblendvb xmm8, xmm15, xmm0 - movd xmm3, r10d - pinsrw xmm1, word ptr [rsi + rcx + 50], 1 - pinsrw xmm1, word ptr [rsi + r8 + 50], 2 - pinsrw xmm1, word ptr [rsi + r12 + 50], 3 - pinsrw xmm1, word ptr [rsi + r13 + 50], 4 - pinsrw xmm1, word ptr [rsi + rbx + 50], 5 - pinsrw xmm1, word ptr [rsi + rdi + 50], 6 - pinsrw xmm1, word ptr [rsi + r9 + 50], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm8, xmm6 - movdqa xmm4, xmmword ptr [rip + .LCPI4_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm15, xmm0 - movd xmm1, eax - pinsrw xmm7, word ptr [rsi + rcx + 48], 1 - pinsrw xmm7, word ptr [rsi + r8 + 48], 2 - pinsrw xmm7, word ptr [rsi + r12 + 48], 3 - pinsrw xmm7, word ptr [rsi + r13 + 48], 4 - pinsrw xmm7, word ptr [rsi + rbx + 48], 5 - pinsrw xmm7, word ptr [rsi + rdi + 48], 6 - pinsrw xmm7, word ptr [rsi + r9 + 48], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI4_22] - pinsrw xmm2, word ptr [rsi + rcx + 52], 1 - pinsrw xmm2, word ptr [rsi + r8 + 52], 2 - pinsrw xmm2, word ptr [rsi + r12 + 52], 3 - pinsrw xmm2, word ptr [rsi + r13 + 52], 4 - pinsrw xmm2, word ptr [rsi + rbx + 52], 5 - pinsrw xmm2, word ptr [rsi + rdi + 52], 6 - packsswb xmm7, xmm7 - pinsrw xmm2, word ptr [rsi + r9 + 52], 7 - pcmpeqw xmm2, xmm11 - pinsrw xmm3, word ptr [rsi + rcx + 54], 1 - pinsrw xmm3, word ptr [rsi + r8 + 54], 2 - pinsrw xmm3, word ptr [rsi + r12 + 54], 3 - pinsrw xmm3, word ptr [rsi + r13 + 54], 4 - pinsrw xmm3, word ptr [rsi + rbx + 54], 5 - pinsrw xmm3, word ptr [rsi + rdi + 54], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [rsi + r9 + 54], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm1, word ptr [rsi + rcx + 56], 1 - pinsrw xmm1, word ptr [rsi + r8 + 56], 2 - pinsrw xmm1, word ptr [rsi + r12 + 56], 3 - pinsrw xmm1, word ptr [rsi + r13 + 56], 4 - pinsrw xmm1, word ptr [rsi + rbx + 56], 5 - pinsrw xmm1, word ptr [rsi + rdi + 56], 6 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [rsi + r9 + 56], 7 - psubb xmm4, xmm7 - movdqa xmm5, xmmword ptr [rip + .LCPI4_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm5, xmm15, xmm0 - movdqa xmm6, xmmword ptr [rip + .LCPI4_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm3 - pblendvb xmm6, xmm15, xmm0 - movd xmm2, r11d - pcmpeqw xmm1, xmm11 - pinsrw xmm2, word ptr [rsi + rcx + 58], 1 - pinsrw xmm2, word ptr [rsi + r8 + 58], 2 - pinsrw xmm2, word ptr [rsi + r12 + 58], 3 - pinsrw xmm2, word ptr [rsi + r13 + 58], 4 - pinsrw xmm2, word ptr [rsi + rbx + 58], 5 - pinsrw xmm2, word ptr [rsi + rdi + 58], 6 - pinsrw xmm2, word ptr [rsi + r9 + 58], 7 - packsswb xmm1, xmm1 - pcmpeqw xmm2, xmm11 - por xmm6, xmm5 - movd xmm3, r14d - pinsrw xmm3, word ptr [rsi + rcx + 60], 1 - pinsrw xmm3, word ptr [rsi + r8 + 60], 2 - pinsrw xmm3, word ptr [rsi + r12 + 60], 3 - pinsrw xmm3, word ptr [rsi + r13 + 60], 4 - pinsrw xmm3, word ptr [rsi + rbx + 60], 5 - pinsrw xmm3, word ptr [rsi + rdi + 60], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [rsi + r9 + 60], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - por xmm6, xmm4 - movdqa xmm4, xmmword ptr [rip + .LCPI4_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm15, xmm0 - movdqa xmm1, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm1, xmm15, xmm0 - movdqa xmm0, xmm3 - pblendvb xmm10, xmm15, xmm0 - por xmm1, xmm4 - movzx eax, word ptr [rsi + r15 + 62] - por xmm10, xmm1 - movd xmm0, eax - pinsrw xmm0, word ptr [rsi + rcx + 62], 1 - pinsrw xmm0, word ptr [rsi + r8 + 62], 2 - pinsrw xmm0, word ptr [rsi + r12 + 62], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrw xmm0, word ptr [rsi + r13 + 62], 4 - pinsrw xmm0, word ptr [rsi + rbx + 62], 5 - pinsrw xmm0, word ptr [rsi + rdi + 62], 6 - pinsrw xmm0, word ptr [rsi + r9 + 62], 7 - pcmpeqw xmm0, xmm11 - packsswb xmm0, xmm0 - por xmm10, xmm6 - pblendvb xmm14, xmm15, xmm0 - por xmm14, xmm10 - movdqa xmm0, xmm12 - punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] - movdqa xmm2, xmm8 - punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] - movdqa xmm3, xmmword ptr [rip + .LCPI4_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> - pshufb xmm2, xmm3 - pshufb xmm0, xmm3 - punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] - punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] - punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] - punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx], xmm12 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm0 - add rcx, 8 - mov r15, rcx - cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB4_192 -# %bb.193: - mov r10, qword ptr [rsp + 192] # 8-byte Reload - cmp r10, qword ptr [rsp + 32] # 8-byte Folded Reload - mov r14, qword ptr [rsp + 144] # 8-byte Reload - mov r13d, dword ptr [rsp + 64] # 4-byte Reload - mov r12, qword ptr [rsp + 8] # 8-byte Reload - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - jne .LBB4_108 - jmp .LBB4_111 -.Lfunc_end4: - .size comparison_not_equal_arr_scalar_sse4, .Lfunc_end4-comparison_not_equal_arr_scalar_sse4 - # -- End function - .section .rodata.cst16,"aM",@progbits,16 - .p2align 4 # -- Begin function comparison_not_equal_scalar_arr_sse4 -.LCPI5_0: - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_1: - .zero 16,252 -.LCPI5_2: - .zero 16,248 -.LCPI5_3: - .zero 16,240 -.LCPI5_4: - .zero 16,224 -.LCPI5_5: - .zero 16,192 -.LCPI5_6: - .zero 16,128 -.LCPI5_7: - .byte 0 # 0x0 - .byte 8 # 0x8 - .byte 1 # 0x1 - .byte 9 # 0x9 - .byte 2 # 0x2 - .byte 10 # 0xa - .byte 3 # 0x3 - .byte 11 # 0xb - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf -.LCPI5_8: - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .byte 2 # 0x2 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_9: - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .byte 4 # 0x4 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_10: - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .byte 8 # 0x8 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_11: - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .byte 16 # 0x10 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_12: - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .byte 32 # 0x20 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_13: - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .byte 64 # 0x40 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_14: - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .byte 128 # 0x80 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_15: - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI5_16: - .zero 16,2 -.LCPI5_17: - .zero 16,4 -.LCPI5_18: - .zero 16,8 -.LCPI5_19: - .zero 16,16 -.LCPI5_20: - .zero 16,32 -.LCPI5_21: - .zero 16,64 -.LCPI5_22: - .zero 16,255 - .text - .globl comparison_not_equal_scalar_arr_sse4 - .p2align 4, 0x90 - .type comparison_not_equal_scalar_arr_sse4,@function -comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 -# %bb.0: - push rbp - mov rbp, rsp - push r15 - push r14 - push r13 - push r12 - push rbx - and rsp, -16 - sub rsp, 288 - # kill: def $r9d killed $r9d def $r9 - mov r15, r8 - mov qword ptr [rsp + 8], rcx # 8-byte Spill - mov r14, rdx - cmp edi, 6 - jg .LBB5_27 -# %bb.1: - cmp edi, 3 - jle .LBB5_2 -# %bb.10: - cmp edi, 4 - je .LBB5_100 -# %bb.11: - cmp edi, 5 - je .LBB5_123 -# %bb.12: - cmp edi, 6 - jne .LBB5_198 -# %bb.13: - mov r11d, dword ptr [rsi] - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB5_17 -# %bb.14: - movsxd rax, r9d - mov rdx, qword ptr [rsp + 8] # 8-byte Reload - .p2align 4, 0x90 -.LBB5_15: # =>This Inner Loop Header: Depth=1 - cmp r11d, dword ptr [r14] - lea r14, [r14 + 4] - setne bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [rdx + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [rdx + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_15 -# %bb.16: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_17: - sar r10, 5 - cmp r15, 32 - jl .LBB5_21 -# %bb.18: - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r10 # 8-byte Spill - .p2align 4, 0x90 -.LBB5_19: # =>This Inner Loop Header: Depth=1 - cmp r11d, dword ptr [r14 + 124] - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 120] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 116] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 112] - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 108] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 104] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 100] - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 92] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 88] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 84] - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 80] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 76] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 72] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 68] - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 60] - setne r8b - cmp r11d, dword ptr [r14 + 56] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 52] +.LBB4_156: # =>This Inner Loop Header: Depth=1 + mov r11, rsi + cmp word ptr [rsi], r13w setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 48] - setne dil - cmp r11d, dword ptr [r14 + 44] - setne r10b - cmp r11d, dword ptr [r14 + 40] - setne r9b - cmp r11d, dword ptr [r14 + 36] + cmp word ptr [rsi + 2], r13w setne sil - cmp r11d, dword ptr [r14 + 28] + cmp word ptr [r11 + 4], r13w + setne r15b + cmp word ptr [r11 + 6], r13w + setne r12b + cmp word ptr [r11 + 8], r13w + setne byte ptr [rsp + 208] # 1-byte Folded Spill + cmp word ptr [r11 + 10], r13w + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp word ptr [r11 + 12], r13w setne al - cmp r11d, dword ptr [r14 + 24] + cmp word ptr [r11 + 14], r13w setne bl - cmp r11d, dword ptr [r14 + 20] - setne dl - cmp r11d, dword ptr [r14 + 16] + cmp word ptr [r11 + 16], r13w + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [r11 + 18], r13w setne cl - cmp r11d, dword ptr [r14 + 12] - setne r13b - cmp r11d, dword ptr [r14 + 8] - setne r15b - cmp r11d, dword ptr [r14] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 4] - mov r12, r14 + cmp word ptr [r11 + 20], r13w + setne r8b + cmp word ptr [r11 + 22], r13w + setne r9b + cmp word ptr [r11 + 24], r13w setne r14b - cmp r11d, dword ptr [r12 + 32] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r11d, dword ptr [r12 + 64] - setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r11d, dword ptr [r12 + 96] + cmp word ptr [r11 + 26], r13w + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp word ptr [r11 + 28], r13w + setne byte ptr [rsp + 224] # 1-byte Folded Spill + cmp word ptr [r11 + 30], r13w + setne dil + cmp word ptr [r11 + 32], r13w + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp word ptr [r11 + 34], r13w + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp word ptr [r11 + 36], r13w setne byte ptr [rsp + 112] # 1-byte Folded Spill - add r14b, r14b - add r14b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r15b, 2 - or r15b, r14b - mov r14, r12 - shl r13b, 3 - or r13b, r15b - shl cl, 4 - or cl, r13b - mov r15, qword ptr [rsp + 8] # 8-byte Reload - shl dl, 5 - or dl, cl + cmp word ptr [r11 + 38], r13w + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp word ptr [r11 + 40], r13w + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp word ptr [r11 + 42], r13w + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp word ptr [r11 + 44], r13w + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp word ptr [r11 + 46], r13w + setne r10b + cmp word ptr [r11 + 48], r13w + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp word ptr [r11 + 50], r13w + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp word ptr [r11 + 52], r13w + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp word ptr [r11 + 54], r13w + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp word ptr [r11 + 56], r13w + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp word ptr [r11 + 58], r13w + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp word ptr [r11 + 60], r13w + setne byte ptr [rsp + 120] # 1-byte Folded Spill + cmp word ptr [r11 + 62], r13w + setne dl + add sil, sil + add sil, byte ptr [rsp + 152] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r15b, 2 + or r15b, sil + add cl, cl + add cl, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r12b, 3 + or r12b, r15b + shl r8b, 2 + or r8b, cl + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl cl, 4 + or cl, r12b + mov esi, ecx + shl r9b, 3 + or r9b, r8b + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + shl r14b, 4 + or r14b, r9b + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 224] # 1-byte Folded Reload + shl sil, 6 + shl dil, 7 + or dil, sil + or bl, cl + or dil, al + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 104] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov esi, ecx + mov rcx, qword ptr [rsp + 8] # 8-byte Reload + mov byte ptr [rcx], bl + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload shl bl, 6 - shl al, 7 + shl r10b, 7 + or r10b, bl + mov byte ptr [rcx + 1], dil + or r10b, sil + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 or al, bl - or al, dl - mov byte ptr [r15], al + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rcx + 2], r10b + mov byte ptr [rcx + 3], dl + lea rsi, [r11 + 64] + add rcx, 4 + mov qword ptr [rsp + 8], rcx # 8-byte Spill + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB4_156 +# %bb.157: + mov r14, qword ptr [rsp + 144] # 8-byte Reload + mov r12, qword ptr [rsp + 8] # 8-byte Reload + mov rcx, qword ptr [rsp + 176] # 8-byte Reload +.LBB4_158: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB4_208 +# %bb.159: + or rcx, 1 + cmp r14, rcx + jne .LBB4_203 +.LBB4_160: + xor r14d, r14d + jmp .LBB4_205 +.LBB4_161: + mov rdi, rsi + sub r14, r8 + je .LBB4_208 +.LBB4_162: + add r12, 1 +.LBB4_163: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB4_171 +# %bb.164: + cmp rcx, 16 + mov byte ptr [rsp + 8], r15b # 1-byte Spill + mov qword ptr [rsp + 144], r14 # 8-byte Spill + mov qword ptr [rsp + 264], rcx # 8-byte Spill + jb .LBB4_167 +# %bb.165: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r12, rax + jae .LBB4_221 +# %bb.166: + lea rax, [r12 + 4*rcx] + cmp rdi, rax + jae .LBB4_221 +.LBB4_167: + xor eax, eax + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov qword ptr [rsp + 160], r12 # 8-byte Spill + mov rsi, rdi +.LBB4_168: + sub rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov qword ptr [rsp + 176], rcx # 8-byte Spill + mov rdi, qword ptr [rsp + 160] # 8-byte Reload + .p2align 4, 0x90 +.LBB4_169: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r15b + setne byte ptr [rsp + 240] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r15b + setne sil + cmp byte ptr [rcx + 2], r15b + mov eax, r15d + setne r15b + cmp byte ptr [rcx + 3], al + setne byte ptr [rsp + 136] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 4], al + setne byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 5], al + setne byte ptr [rsp + 64] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 6], al + setne r13b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 7], al + setne r9b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 8], al + setne byte ptr [rsp + 128] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 9], al + setne dl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 10], al + setne r8b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 11], al + setne r10b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 12], al + setne r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 13], al + setne byte ptr [rsp + 152] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 14], al + setne byte ptr [rsp + 224] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 15], al + setne r12b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 16], bl + setne byte ptr [rsp + 208] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 17], bl + setne byte ptr [rsp + 192] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 18], bl + setne byte ptr [rsp + 88] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 19], bl + setne byte ptr [rsp + 96] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 20], bl + setne byte ptr [rsp + 104] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 21], bl + setne byte ptr [rsp + 80] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 22], bl + setne byte ptr [rsp + 72] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 23], bl + setne r11b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 24], bl + setne byte ptr [rsp + 56] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 25], bl + setne byte ptr [rsp + 40] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 26], bl + setne byte ptr [rsp + 48] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 27], bl + setne byte ptr [rsp + 32] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 28], bl + setne byte ptr [rsp + 16] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 29], bl + setne byte ptr [rsp + 24] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 30], bl + setne byte ptr [rsp + 120] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 31], bl + setne bl add sil, sil - add sil, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r9b, 2 - or r9b, sil + add sil, byte ptr [rsp + 240] # 1-byte Folded Reload + shl r13b, 6 + shl r9b, 7 + or r9b, r13b + shl r15b, 2 + or r15b, sil + add dl, dl + add dl, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 3 + or al, r15b + shl r8b, 2 + or r8b, dl + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, al + mov esi, edx + movzx r15d, byte ptr [rsp + 8] # 1-byte Folded Reload shl r10b, 3 - or r10b, r9b - shl dil, 4 - or dil, r10b + or r10b, r8b + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + shl r14b, 4 + or r14b, r10b movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload shl al, 5 - or al, dil - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + or al, r14b + movzx esi, byte ptr [rsp + 224] # 1-byte Folded Reload + shl sil, 6 + shl r12b, 7 + or r12b, sil + or r9b, dl + or r12b, al + movzx edx, byte ptr [rsp + 192] # 1-byte Folded Reload + add dl, dl + add dl, byte ptr [rsp + 208] # 1-byte Folded Reload + mov esi, edx + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 2 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov byte ptr [rdi], r9b + movzx esi, byte ptr [rsp + 72] # 1-byte Folded Reload + shl sil, 6 + shl r11b, 7 + or r11b, sil + mov byte ptr [rdi + 1], r12b + or r11b, dl + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + add al, byte ptr [rsp + 56] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 7 or al, dl - or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax + mov edx, eax movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 5 - or al, cl - mov ecx, eax - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 7 or al, dl - or al, cl - mov byte ptr [r15 + 3], al - sub r14, -128 - add r15, 4 - mov qword ptr [rsp + 8], r15 # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_19 -# %bb.20: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload -.LBB5_21: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.22: - mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - je .LBB5_23 -# %bb.143: - mov r9, r8 - and r9, -2 - xor edi, edi - mov r15, qword ptr [rsp + 8] # 8-byte Reload + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r11b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + add qword ptr [rsp + 176], -1 # 8-byte Folded Spill + jne .LBB4_169 +# %bb.170: + mov qword ptr [rsp + 160], rdi # 8-byte Spill + mov r14, qword ptr [rsp + 144] # 8-byte Reload + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + jmp .LBB4_172 +.LBB4_171: + mov qword ptr [rsp + 160], r12 # 8-byte Spill + mov rsi, rdi +.LBB4_172: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB4_208 +# %bb.173: + or rcx, 1 + cmp r14, rcx + jne .LBB4_184 +# %bb.174: + xor r9d, r9d + jmp .LBB4_187 +.LBB4_175: + mov r10, r8 + and r10, -2 + xor r11d, r11d .p2align 4, 0x90 -.LBB5_144: # =>This Inner Loop Header: Depth=1 - cmp r11d, dword ptr [r14] +.LBB4_176: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d setne al neg al - mov rsi, rdi - shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - mov ecx, edi + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + setne al + neg al + xor al, bl + or cl, 1 mov dl, 1 shl dl, cl - xor al, r10b and dl, al - xor dl, r10b - mov byte ptr [r15 + rsi], dl - add rdi, 2 - cmp r11d, dword ptr [r14 + 4] - lea r14, [r14 + 8] - setne al - neg al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB4_176 +.LBB4_177: + test r8b, 1 + je .LBB4_208 +# %bb.178: + cmp dword ptr [rsi], r13d + jmp .LBB4_198 +.LBB4_179: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 160] # 8-byte Reload + .p2align 4, 0x90 +.LBB4_180: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [r13 + r9], r15b + setne bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [r13 + rax + 1], r15b + lea r9, [rax + 2] + setne bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB4_180 +# %bb.181: + add r13, r9 +.LBB4_182: + test r8b, 1 + je .LBB4_208 +# %bb.183: + cmp byte ptr [r13], r15b + jmp .LBB4_189 +.LBB4_184: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 160] # 8-byte Reload + .p2align 4, 0x90 +.LBB4_185: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r15b + setne bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r15b + lea r9, [rax + 2] + setne bl + neg bl + xor bl, dl or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB4_185 +# %bb.186: + add rsi, r9 +.LBB4_187: + test r8b, 1 + je .LBB4_208 +# %bb.188: + cmp byte ptr [rsi], r15b +.LBB4_189: + setne al + neg al + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 160] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 mov bl, 1 + mov ecx, r9d shl bl, cl + xor al, dil and bl, al - xor bl, dl - mov byte ptr [r15 + rsi], bl - cmp r9, rdi - jne .LBB5_144 - jmp .LBB5_24 -.LBB5_27: - cmp edi, 8 - jle .LBB5_28 -# %bb.43: - cmp edi, 9 - je .LBB5_159 -# %bb.44: - cmp edi, 11 - je .LBB5_171 -# %bb.45: - cmp edi, 12 - jne .LBB5_198 -# %bb.46: - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - sub r9d, eax - je .LBB5_50 -# %bb.47: - movsxd rax, r9d - mov r8, qword ptr [rsp + 8] # 8-byte Reload + xor bl, dil + mov byte ptr [r8 + rdx], bl + jmp .LBB4_208 +.LBB4_190: + mov r9, r8 + and r9, -2 + xor r11d, r11d .p2align 4, 0x90 -.LBB5_48: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [r14] - lea r14, [r14 + 8] +.LBB4_191: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rsi] setp cl + setne al + or al, cl + neg al + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r10d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r10b + and bl, al + xor bl, r10b + mov byte ptr [r12 + rdi], bl + add r11, 2 + ucomisd xmm0, qword ptr [rsi + 8] + lea rsi, [rsi + 16] + setp r10b + setne al + or al, r10b + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r9, r11 + jne .LBB4_191 +.LBB4_192: + test r8b, 1 + je .LBB4_208 +# %bb.193: + ucomisd xmm0, qword ptr [rsi] + setp al setne dl - or dl, cl + or dl, al neg dl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx ebx, byte ptr [r8 + rsi] + mov rax, r11 + shr rax, 3 + mov sil, byte ptr [r12 + rax] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor dl, sil + and bl, dl + xor bl, sil + mov byte ptr [r12 + rax], bl + jmp .LBB4_208 +.LBB4_194: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB4_195: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + setne al + neg al + mov rdi, r11 + shr rdi, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + setne al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al xor dl, bl - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, bl - mov byte ptr [r8 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_48 -# %bb.49: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_50: - sar r10, 5 - cmp r15, 32 - jl .LBB5_54 -# %bb.51: - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB4_195 +.LBB4_196: + test r8b, 1 + je .LBB4_208 +# %bb.197: + cmp qword ptr [rsi], r13 +.LBB4_198: + setne al + neg al + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al + xor bl, sil + jmp .LBB4_207 +.LBB4_199: + mov r9, r8 + and r9, -2 + xor esi, esi + mov r14, r13 .p2align 4, 0x90 -.LBB5_52: # =>This Inner Loop Header: Depth=1 - mov rdx, r14 - ucomisd xmm0, qword ptr [r14] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 24], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 8] - setp al - setne r11b - or r11b, al - ucomisd xmm0, qword ptr [r14 + 16] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 24] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 32] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 16], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 40] - setp al - setne r9b - or r9b, al - ucomisd xmm0, qword ptr [r14 + 48] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 56] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 64] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 72] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 80] - setp al - setne bl - or bl, al - mov byte ptr [rsp + 80], bl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 88] - setp al - setne bl - or bl, al - mov byte ptr [rsp + 72], bl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 96] - setp al - setne bl - or bl, al - mov byte ptr [rsp + 104], bl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 104] - setp al - setne bl - or bl, al - mov byte ptr [rsp + 96], bl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 112] - setp al - setne r13b - or r13b, al - ucomisd xmm0, qword ptr [r14 + 120] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 128] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 136] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 144] - setp al - setne bl - or bl, al - ucomisd xmm0, qword ptr [r14 + 152] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 160] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 168] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 176] - setp al - setne r12b - or r12b, al - ucomisd xmm0, qword ptr [r14 + 184] - setp al - setne r8b - or r8b, al - ucomisd xmm0, qword ptr [r14 + 192] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill - ucomisd xmm0, qword ptr [r14 + 200] - setp al - setne r15b - or r15b, al - ucomisd xmm0, qword ptr [r14 + 208] - setp al - setne r14b - or r14b, al - ucomisd xmm0, qword ptr [rdx + 216] - setp al - setne r10b - or r10b, al - ucomisd xmm0, qword ptr [rdx + 224] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 192], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 232] - setp al - setne cl - or cl, al - mov byte ptr [rsp + 168], cl # 1-byte Spill - ucomisd xmm0, qword ptr [rdx + 240] - setp al - setne dil - or dil, al - ucomisd xmm0, qword ptr [rdx + 248] +.LBB4_200: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rbx] + setp cl + setne dl + or dl, cl + neg dl + mov rdi, rsi + shr rdi, 3 + movzx r10d, byte ptr [r14 + rdi] + mov ecx, esi + and cl, 6 + mov r11b, 1 + shl r11b, cl + xor dl, r10b + and r11b, dl + xor r11b, r10b + mov byte ptr [r14 + rdi], r11b + add rsi, 2 + ucomiss xmm0, dword ptr [rbx + 4] + lea rbx, [rbx + 8] + setp r10b + setne dl + or dl, r10b + neg dl + xor dl, r11b + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, r11b + mov byte ptr [r14 + rdi], al + cmp r9, rsi + jne .LBB4_200 +.LBB4_201: + test r8b, 1 + je .LBB4_208 +# %bb.202: + ucomiss xmm0, dword ptr [rbx] setp al - setne sil - or sil, al - add r11b, r11b - add r11b, byte ptr [rsp + 24] # 1-byte Folded Reload - shl r9b, 5 - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 6 - or al, r9b - mov r9d, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 2 - or al, r11b - mov r11d, eax - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 48] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 7 - or al, r9b - mov r9d, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 3 - or al, r11b - mov r11d, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, r11b - mov byte ptr [rsp + 16], al # 1-byte Spill - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov r11d, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 5 - shl r13b, 6 - or r13b, al - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 7 - or al, r13b - mov r13d, eax - mov rax, qword ptr [rsp + 8] # 8-byte Reload - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 120] # 1-byte Folded Reload - shl bl, 2 - or bl, cl - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload - shl cl, 3 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl cl, 4 - or cl, bl - or r9b, byte ptr [rsp + 16] # 1-byte Folded Reload - movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload - shl bl, 5 - shl r12b, 6 - or r12b, bl - or r13b, r11b - shl r8b, 7 - or r8b, r12b - or r8b, cl - add r15b, r15b - add r15b, byte ptr [rsp + 144] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r15b - shl r10b, 3 - or r10b, r14b - movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload - shl cl, 4 - or cl, r10b - mov byte ptr [rax], r9b - movzx ebx, byte ptr [rsp + 168] # 1-byte Folded Reload - shl bl, 5 - shl dil, 6 - or dil, bl - mov byte ptr [rax + 1], r13b - shl sil, 7 - or sil, dil - or sil, cl - mov byte ptr [rax + 2], r8b - mov byte ptr [rax + 3], sil - lea r14, [rdx + 256] - add rax, 4 + setne dl + or dl, al + neg dl + mov rax, rsi + shr rax, 3 + mov dil, byte ptr [r13 + rax] + and sil, 7 + mov bl, 1 + mov ecx, esi + shl bl, cl + xor dl, dil + and bl, dl + xor bl, dil + mov byte ptr [r13 + rax], bl + jmp .LBB4_208 +.LBB4_203: + mov r9, r8 + and r9, -2 + xor r14d, r14d + .p2align 4, 0x90 +.LBB4_204: # =>This Inner Loop Header: Depth=1 + mov rax, rsi + cmp word ptr [rsi], r13w + setne dl + neg dl + mov rdi, r14 + shr rdi, 3 + movzx r10d, byte ptr [r12 + rdi] + mov ecx, r14d + and cl, 6 + mov bl, 1 + shl bl, cl + xor dl, r10b + and bl, dl + xor bl, r10b + mov byte ptr [r12 + rdi], bl + add r14, 2 + cmp word ptr [rsi + 2], r13w + lea rsi, [rsi + 4] + setne dl + neg dl + xor dl, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, bl + mov byte ptr [r12 + rdi], al + cmp r9, r14 + jne .LBB4_204 +.LBB4_205: + test r8b, 1 + je .LBB4_208 +# %bb.206: + cmp word ptr [rsi], r13w + setne al + neg al + mov rdx, r14 + shr rdx, 3 + mov dil, byte ptr [r12 + rdx] + and r14b, 7 + mov bl, 1 + mov ecx, r14d + shl bl, cl + xor al, dil + and bl, al + xor bl, dil +.LBB4_207: + mov byte ptr [r12 + rdx], bl +.LBB4_208: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.LBB4_209: + mov r9, rcx + and r9, -4 + mov rbx, r9 + shl rbx, 7 + add rbx, rsi + lea r13, [r12 + 4*r9] + movdqa xmm1, xmm0 + shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] + add rsi, 508 + xor edx, edx + movdqa xmm15, xmmword ptr [rip + .LCPI4_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> + movdqa xmm8, xmmword ptr [rip + .LCPI4_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + movdqa xmm10, xmmword ptr [rip + .LCPI4_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + movdqa xmm11, xmmword ptr [rip + .LCPI4_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + movdqa xmm12, xmmword ptr [rip + .LCPI4_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + movdqa xmm13, xmmword ptr [rip + .LCPI4_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] + movdqa xmm14, xmmword ptr [rip + .LCPI4_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + movdqa xmm9, xmmword ptr [rip + .LCPI4_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] + .p2align 4, 0x90 +.LBB4_210: # =>This Inner Loop Header: Depth=1 + movss xmm6, dword ptr [rsi - 508] # xmm6 = mem[0],zero,zero,zero + movss xmm7, dword ptr [rsi - 504] # xmm7 = mem[0],zero,zero,zero + movss xmm5, dword ptr [rsi - 500] # xmm5 = mem[0],zero,zero,zero + movss xmm4, dword ptr [rsi - 496] # xmm4 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rsi - 380], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rsi - 252], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rsi - 124], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + insertps xmm7, dword ptr [rsi - 376], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rsi - 248], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rsi - 120], 48 # xmm7 = xmm7[0,1,2],mem[0] + insertps xmm5, dword ptr [rsi - 372], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rsi - 244], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rsi - 116], 48 # xmm5 = xmm5[0,1,2],mem[0] + insertps xmm4, dword ptr [rsi - 368], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] + insertps xmm4, dword ptr [rsi - 240], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] + insertps xmm4, dword ptr [rsi - 112], 48 # xmm4 = xmm4[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + movdqa xmm2, xmm7 + pand xmm2, xmm15 + psubb xmm2, xmm7 + movss xmm7, dword ptr [rsi - 492] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rsi - 364], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rsi - 236], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rsi - 108], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm2, xmm6 + movss xmm6, dword ptr [rsi - 488] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rsi - 360], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rsi - 232], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rsi - 104], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 2 + pand xmm5, xmm8 + por xmm5, xmm2 + movss xmm3, dword ptr [rsi - 484] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 356], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 228], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rsi - 100], 48 # xmm3 = xmm3[0,1,2],mem[0] + cmpneqps xmm4, xmm1 + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + psllw xmm4, 3 + pand xmm4, xmm10 + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 4 + pand xmm7, xmm11 + por xmm7, xmm4 + movss xmm4, dword ptr [rsi - 480] # xmm4 = mem[0],zero,zero,zero + insertps xmm4, dword ptr [rsi - 352], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] + insertps xmm4, dword ptr [rsi - 224], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] + insertps xmm4, dword ptr [rsi - 96], 48 # xmm4 = xmm4[0,1,2],mem[0] + por xmm7, xmm5 + movss xmm5, dword ptr [rsi - 476] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rsi - 348], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rsi - 220], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rsi - 92], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 6 + pand xmm3, xmm13 + por xmm3, xmm6 + movss xmm2, dword ptr [rsi - 472] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rsi - 344], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rsi - 216], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rsi - 88], 48 # xmm2 = xmm2[0,1,2],mem[0] + packsswb xmm5, xmm5 + cmpneqps xmm4, xmm1 + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + psllw xmm4, 7 + pand xmm4, xmm14 + por xmm4, xmm3 + movss xmm3, dword ptr [rsi - 468] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 340], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 212], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + pand xmm5, xmm15 + insertps xmm3, dword ptr [rsi - 84], 48 # xmm3 = xmm3[0,1,2],mem[0] + por xmm4, xmm7 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm6, xmm2 + pand xmm6, xmm15 + psubb xmm6, xmm2 + movss xmm7, dword ptr [rsi - 464] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rsi - 336], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rsi - 208], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rsi - 80], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm6, xmm5 + movss xmm5, dword ptr [rsi - 460] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rsi - 332], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rsi - 204], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rsi - 76], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm6 + movss xmm6, dword ptr [rsi - 456] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rsi - 328], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rsi - 200], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rsi - 72], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 3 + pand xmm7, xmm10 + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 4 + pand xmm5, xmm11 + por xmm5, xmm7 + movss xmm2, dword ptr [rsi - 452] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rsi - 324], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rsi - 196], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rsi - 68], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm5, xmm3 + movss xmm7, dword ptr [rsi - 448] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rsi - 320], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rsi - 192], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rsi - 64], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm6 + movss xmm6, dword ptr [rsi - 444] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rsi - 316], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rsi - 188], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rsi - 60], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + psllw xmm7, 7 + pand xmm7, xmm14 + por xmm7, xmm2 + movss xmm2, dword ptr [rsi - 440] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rsi - 312], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rsi - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rsi - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm7, xmm5 + movss xmm3, dword ptr [rsi - 436] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 308], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 180], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + pand xmm6, xmm15 + insertps xmm3, dword ptr [rsi - 52], 48 # xmm3 = xmm3[0,1,2],mem[0] + punpckldq xmm4, xmm7 # xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1] + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm7, xmm2 + pand xmm7, xmm15 + psubb xmm7, xmm2 + movss xmm5, dword ptr [rsi - 432] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rsi - 304], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rsi - 176], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rsi - 48], 48 # xmm5 = xmm5[0,1,2],mem[0] + por xmm7, xmm6 + movss xmm6, dword ptr [rsi - 428] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rsi - 300], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rsi - 172], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rsi - 44], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm7 + movss xmm7, dword ptr [rsi - 424] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rsi - 296], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rsi - 168], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rsi - 40], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 3 + pand xmm5, xmm10 + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 4 + pand xmm6, xmm11 + por xmm6, xmm5 + movss xmm2, dword ptr [rsi - 420] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rsi - 292], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rsi - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rsi - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm6, xmm3 + movss xmm5, dword ptr [rsi - 416] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rsi - 288], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rsi - 160], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rsi - 32], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 5 + pand xmm7, xmm12 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm7 + movss xmm7, dword ptr [rsi - 412] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rsi - 284], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rsi - 156], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rsi - 28], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + psllw xmm5, 7 + pand xmm5, xmm14 + por xmm5, xmm2 + movss xmm2, dword ptr [rsi - 408] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rsi - 280], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rsi - 152], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + pand xmm7, xmm15 + insertps xmm2, dword ptr [rsi - 24], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm5, xmm6 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm6, xmm2 + pand xmm6, xmm15 + psubb xmm6, xmm2 + movss xmm3, dword ptr [rsi - 404] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 276], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 148], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rsi - 20], 48 # xmm3 = xmm3[0,1,2],mem[0] + por xmm6, xmm7 + movss xmm2, dword ptr [rsi - 400] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rsi - 272], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rsi - 144], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rsi - 16], 48 # xmm2 = xmm2[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm6 + movss xmm6, dword ptr [rsi - 396] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rsi - 268], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rsi - 140], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rsi - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 3 + pand xmm2, xmm10 + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 4 + pand xmm6, xmm11 + por xmm6, xmm2 + movss xmm7, dword ptr [rsi - 392] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rsi - 264], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rsi - 136], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rsi - 8], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm6, xmm3 + movss xmm2, dword ptr [rsi - 388] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rsi - 260], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rsi - 132], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rsi - 4], 48 # xmm2 = xmm2[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 5 + pand xmm7, xmm12 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm7 + movss xmm3, dword ptr [rsi - 384] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 256], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 128], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rsi], 48 # xmm3 = xmm3[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + psllw xmm3, 7 + pand xmm3, xmm14 + por xmm3, xmm2 + por xmm3, xmm6 + punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] + punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] + pshufb xmm4, xmm9 + movdqu xmmword ptr [r12 + 4*rdx], xmm4 + add rdx, 4 + add rsi, 512 + cmp r9, rdx + jne .LBB4_210 +# %bb.211: + cmp rcx, r9 + jne .LBB4_93 + jmp .LBB4_116 +.LBB4_212: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, r13 + mov qword ptr [rsp + 272], rax # 8-byte Spill + mov qword ptr [rsp + 168], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 160], rax # 8-byte Spill + movzx eax, r15b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 120], r12 # 8-byte Spill + .p2align 4, 0x90 +.LBB4_213: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 152], rax # 8-byte Spill + shl rax, 5 + mov r14, rax + mov r11, rax + mov r8, rax + mov r12, rax + mov rdx, rax + mov rsi, rax + mov r10, rax + mov rbx, rax + mov r15, rax + mov qword ptr [rsp + 88], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + movzx ecx, byte ptr [r13 + rax] + movd xmm4, ecx + movzx ecx, byte ptr [r13 + rax + 1] + movd xmm3, ecx + movzx ecx, byte ptr [r13 + rax + 2] + movd xmm5, ecx + movzx ecx, byte ptr [r13 + rax + 3] + movd xmm7, ecx + movzx ecx, byte ptr [r13 + rax + 4] + movd xmm9, ecx + movzx ecx, byte ptr [r13 + rax + 5] + movd xmm2, ecx + movzx ecx, byte ptr [r13 + rax + 6] + movd xmm8, ecx + movzx ecx, byte ptr [r13 + rax + 7] + movd xmm14, ecx + movzx ecx, byte ptr [r13 + rax + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r13 + rax + 9] + movd xmm11, ecx + movzx ecx, byte ptr [r13 + rax + 10] + movd xmm12, ecx + movzx ecx, byte ptr [r13 + rax + 11] + movd xmm13, ecx + movzx ecx, byte ptr [r13 + rax + 12] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r13 + rax + 13] + movd xmm6, ecx + movzx ecx, byte ptr [r13 + rax + 14] + movd xmm15, ecx + movzx ecx, byte ptr [r13 + rax + 15] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov rdi, rax + or rdi, 32 + or r14, 64 + mov qword ptr [rsp + 112], r14 # 8-byte Spill + or r11, 96 + mov qword ptr [rsp + 96], r11 # 8-byte Spill + or r8, 128 + mov qword ptr [rsp + 80], r8 # 8-byte Spill + or r12, 160 + or rdx, 192 + mov qword ptr [rsp + 192], rdx # 8-byte Spill + or rsi, 224 + mov qword ptr [rsp + 40], rsi # 8-byte Spill + or r10, 256 + mov qword ptr [rsp + 104], r10 # 8-byte Spill + or rbx, 288 + mov qword ptr [rsp + 72], rbx # 8-byte Spill + or r15, 320 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + or r9, 352 + mov qword ptr [rsp + 88], r9 # 8-byte Spill + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + or rbx, 384 + mov qword ptr [rsp + 56], rbx # 8-byte Spill + mov rcx, rax + or rcx, 416 + mov qword ptr [rsp + 16], rcx # 8-byte Spill + mov rdx, rax + or rdx, 448 + mov qword ptr [rsp + 48], rdx # 8-byte Spill + or rax, 480 + mov qword ptr [rsp + 24], rax # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + rdi], 1 + pinsrb xmm4, byte ptr [r13 + r14], 2 + pinsrb xmm4, byte ptr [r13 + r11], 3 + pinsrb xmm4, byte ptr [r13 + r8], 4 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r12], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + r12], 6 + pinsrb xmm4, byte ptr [r13 + rsi], 7 + pinsrb xmm4, byte ptr [r13 + r10], 8 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rdx], 9 + pinsrb xmm4, byte ptr [r13 + r15], 10 + pinsrb xmm4, byte ptr [r13 + r9], 11 + pinsrb xmm4, byte ptr [r13 + rbx], 12 + pinsrb xmm4, byte ptr [r13 + rcx], 13 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rax], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rax], 15 + pinsrb xmm3, byte ptr [r13 + rdi + 1], 1 + mov qword ptr [rsp + 32], rdi # 8-byte Spill + pinsrb xmm3, byte ptr [r13 + r14 + 1], 2 + pinsrb xmm3, byte ptr [r13 + r11 + 1], 3 + pinsrb xmm3, byte ptr [r13 + r8 + 1], 4 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + r11 + 1], 5 + pinsrb xmm3, byte ptr [r13 + r12 + 1], 6 + pinsrb xmm3, byte ptr [r13 + rsi + 1], 7 + pinsrb xmm3, byte ptr [r13 + r10 + 1], 8 + pinsrb xmm3, byte ptr [r13 + rdx + 1], 9 + pinsrb xmm3, byte ptr [r13 + r15 + 1], 10 + pinsrb xmm3, byte ptr [r13 + r9 + 1], 11 + pinsrb xmm3, byte ptr [r13 + rbx + 1], 12 + pinsrb xmm3, byte ptr [r13 + rcx + 1], 13 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + r14 + 1], 14 + movdqa xmm1, xmmword ptr [rsp + 208] # 16-byte Reload + pcmpeqb xmm4, xmm1 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + r8 + 1], 15 + pcmpeqb xmm3, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pandn xmm3, xmm0 + paddb xmm3, xmm4 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edx, byte ptr [r13 + rax + 16] + movd xmm10, edx + pinsrb xmm5, byte ptr [r13 + rdi + 2], 1 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r9 + 2], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rsi + 2], 3 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r10 + 2], 4 + pinsrb xmm5, byte ptr [r13 + r11 + 2], 5 + mov rbx, r12 + pinsrb xmm5, byte ptr [r13 + r12 + 2], 6 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rax + 2], 7 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rcx + 2], 8 + mov rdi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rdi + 2], 9 + mov rdx, r15 + pinsrb xmm5, byte ptr [r13 + r15 + 2], 10 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r15 + 2], 11 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r12 + 2], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rax + 2], 13 + pinsrb xmm5, byte ptr [r13 + r14 + 2], 14 + pinsrb xmm5, byte ptr [r13 + r8 + 2], 15 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 1 + pinsrb xmm7, byte ptr [r13 + r9 + 3], 2 + pinsrb xmm7, byte ptr [r13 + rsi + 3], 3 + pinsrb xmm7, byte ptr [r13 + r10 + 3], 4 + pinsrb xmm7, byte ptr [r13 + r11 + 3], 5 + pinsrb xmm7, byte ptr [r13 + rbx + 3], 6 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 7 + pinsrb xmm7, byte ptr [r13 + rcx + 3], 8 + pinsrb xmm7, byte ptr [r13 + rdi + 3], 9 + pinsrb xmm7, byte ptr [r13 + rdx + 3], 10 + pinsrb xmm7, byte ptr [r13 + r15 + 3], 11 + pinsrb xmm7, byte ptr [r13 + r12 + 3], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 13 + pinsrb xmm7, byte ptr [r13 + r14 + 3], 14 + pinsrb xmm7, byte ptr [r13 + r8 + 3], 15 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rax + 4], 1 + pinsrb xmm9, byte ptr [r13 + r9 + 4], 2 + pinsrb xmm9, byte ptr [r13 + rsi + 4], 3 + pinsrb xmm9, byte ptr [r13 + r10 + 4], 4 + pinsrb xmm9, byte ptr [r13 + r11 + 4], 5 + pinsrb xmm9, byte ptr [r13 + rbx + 4], 6 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rsi + 4], 7 + pinsrb xmm9, byte ptr [r13 + rcx + 4], 8 + pinsrb xmm9, byte ptr [r13 + rdi + 4], 9 + mov r10, rdi + pinsrb xmm9, byte ptr [r13 + rdx + 4], 10 + mov rdi, rdx + mov qword ptr [rsp + 136], rdx # 8-byte Spill + pinsrb xmm9, byte ptr [r13 + r15 + 4], 11 + pinsrb xmm9, byte ptr [r13 + r12 + 4], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rdx + 4], 13 + mov rsi, rdx + pinsrb xmm9, byte ptr [r13 + r14 + 4], 14 + pinsrb xmm9, byte ptr [r13 + r8 + 4], 15 + pcmpeqb xmm5, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm5, xmm0 + pcmpeqb xmm7, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm7, xmm0 + por xmm7, xmm5 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + movzx edx, byte ptr [r13 + r8 + 17] + movd xmm4, edx + pcmpeqb xmm9, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm9, xmm0 + por xmm9, xmm7 + movzx edx, byte ptr [r13 + r8 + 18] + movd xmm7, edx + pcmpeqd xmm0, xmm0 + psubb xmm3, xmm0 + por xmm9, xmm3 + movzx edx, byte ptr [r13 + r8 + 19] + movd xmm5, edx + mov r8, rax + pinsrb xmm2, byte ptr [r13 + rax + 5], 1 + pinsrb xmm2, byte ptr [r13 + r9 + 5], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rdx + 5], 3 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r14 + 5], 4 + pinsrb xmm2, byte ptr [r13 + r11 + 5], 5 + pinsrb xmm2, byte ptr [r13 + rbx + 5], 6 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rax + 5], 7 + pinsrb xmm2, byte ptr [r13 + rcx + 5], 8 + pinsrb xmm2, byte ptr [r13 + r10 + 5], 9 + pinsrb xmm2, byte ptr [r13 + rdi + 5], 10 + pinsrb xmm2, byte ptr [r13 + r15 + 5], 11 + mov rdi, r12 + pinsrb xmm2, byte ptr [r13 + r12 + 5], 12 + pinsrb xmm2, byte ptr [r13 + rsi + 5], 13 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rsi + 5], 14 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r12 + 5], 15 + pinsrb xmm8, byte ptr [r13 + r8 + 6], 1 + pinsrb xmm8, byte ptr [r13 + r9 + 6], 2 + pinsrb xmm8, byte ptr [r13 + rdx + 6], 3 + pinsrb xmm8, byte ptr [r13 + r14 + 6], 4 + pinsrb xmm8, byte ptr [r13 + r11 + 6], 5 + pinsrb xmm8, byte ptr [r13 + rbx + 6], 6 + pinsrb xmm8, byte ptr [r13 + rax + 6], 7 + pinsrb xmm8, byte ptr [r13 + rcx + 6], 8 + pinsrb xmm8, byte ptr [r13 + r10 + 6], 9 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + r11 + 6], 10 + pinsrb xmm8, byte ptr [r13 + r15 + 6], 11 + pinsrb xmm8, byte ptr [r13 + rdi + 6], 12 + mov r10, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + r10 + 6], 13 + pinsrb xmm8, byte ptr [r13 + rsi + 6], 14 + pinsrb xmm8, byte ptr [r13 + r12 + 6], 15 + pinsrb xmm14, byte ptr [r13 + r8 + 7], 1 + pinsrb xmm14, byte ptr [r13 + r9 + 7], 2 + pinsrb xmm14, byte ptr [r13 + rdx + 7], 3 + pinsrb xmm14, byte ptr [r13 + r14 + 7], 4 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + rdx + 7], 5 + pinsrb xmm14, byte ptr [r13 + rbx + 7], 6 + pinsrb xmm14, byte ptr [r13 + rax + 7], 7 + pinsrb xmm14, byte ptr [r13 + rcx + 7], 8 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + r12 + 7], 9 + pinsrb xmm14, byte ptr [r13 + r11 + 7], 10 + mov r10, r11 + pinsrb xmm14, byte ptr [r13 + r15 + 7], 11 + pinsrb xmm14, byte ptr [r13 + rdi + 7], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + rax + 7], 13 + pinsrb xmm14, byte ptr [r13 + rsi + 7], 14 + movdqa xmm1, xmm14 + movdqa xmm14, xmmword ptr [rsp + 208] # 16-byte Reload + pcmpeqb xmm2, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI4_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm0 + pcmpeqb xmm8, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI4_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm8, xmm0 + por xmm8, xmm2 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + movzx edx, byte ptr [r13 + r8 + 20] + movd xmm3, edx + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm1, byte ptr [r13 + rcx + 7], 15 + pcmpeqb xmm1, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI4_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm1, xmm0 + por xmm1, xmm8 + movzx edx, byte ptr [r13 + r8 + 21] + movd xmm2, edx + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rax + 8], 1 + pinsrb xmm0, byte ptr [r13 + r9 + 8], 2 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rbx + 8], 3 + pinsrb xmm0, byte ptr [r13 + r14 + 8], 4 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r11 + 8], 5 + mov r14, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r14 + 8], 6 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rdi + 8], 7 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r15 + 8], 8 + pinsrb xmm0, byte ptr [r13 + r12 + 8], 9 + pinsrb xmm0, byte ptr [r13 + r10 + 8], 10 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r12 + 8], 11 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rdx + 8], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rdx + 8], 13 + pinsrb xmm0, byte ptr [r13 + rsi + 8], 14 + pinsrb xmm0, byte ptr [r13 + rcx + 8], 15 + por xmm1, xmm9 + movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + movzx edx, byte ptr [r13 + r8 + 22] + movd xmm1, edx + pcmpeqb xmm0, xmm14 + pinsrb xmm11, byte ptr [r13 + rax + 9], 1 + pinsrb xmm11, byte ptr [r13 + r9 + 9], 2 + mov r8, rbx + pinsrb xmm11, byte ptr [r13 + rbx + 9], 3 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rax + 9], 4 + pinsrb xmm11, byte ptr [r13 + r11 + 9], 5 + mov rbx, r14 + pinsrb xmm11, byte ptr [r13 + r14 + 9], 6 + mov rdx, rdi + pinsrb xmm11, byte ptr [r13 + rdi + 9], 7 + mov rcx, r15 + pinsrb xmm11, byte ptr [r13 + r15 + 9], 8 + mov rdi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rdi + 9], 9 + pinsrb xmm11, byte ptr [r13 + r10 + 9], 10 + mov r15, r12 + pinsrb xmm11, byte ptr [r13 + r12 + 9], 11 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + r12 + 9], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rsi + 9], 13 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rax + 9], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rax + 9], 15 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + r14 + 10], 1 + pinsrb xmm12, byte ptr [r13 + r9 + 10], 2 + pinsrb xmm12, byte ptr [r13 + r8 + 10], 3 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + r14 + 10], 4 + pinsrb xmm12, byte ptr [r13 + r11 + 10], 5 + pinsrb xmm12, byte ptr [r13 + rbx + 10], 6 + pinsrb xmm12, byte ptr [r13 + rdx + 10], 7 + pinsrb xmm12, byte ptr [r13 + rcx + 10], 8 + pinsrb xmm12, byte ptr [r13 + rdi + 10], 9 + pinsrb xmm12, byte ptr [r13 + r10 + 10], 10 + pinsrb xmm12, byte ptr [r13 + r15 + 10], 11 + pinsrb xmm12, byte ptr [r13 + r12 + 10], 12 + pinsrb xmm12, byte ptr [r13 + rsi + 10], 13 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + rax + 10], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + rax + 10], 15 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rax + 11], 1 + pinsrb xmm13, byte ptr [r13 + r9 + 11], 2 + pinsrb xmm13, byte ptr [r13 + r8 + 11], 3 + pinsrb xmm13, byte ptr [r13 + r14 + 11], 4 + pinsrb xmm13, byte ptr [r13 + r11 + 11], 5 + pinsrb xmm13, byte ptr [r13 + rbx + 11], 6 + pinsrb xmm13, byte ptr [r13 + rdx + 11], 7 + pinsrb xmm13, byte ptr [r13 + rcx + 11], 8 + pinsrb xmm13, byte ptr [r13 + rdi + 11], 9 + pinsrb xmm13, byte ptr [r13 + r10 + 11], 10 + pinsrb xmm13, byte ptr [r13 + r15 + 11], 11 + pinsrb xmm13, byte ptr [r13 + r12 + 11], 12 + pinsrb xmm13, byte ptr [r13 + rsi + 11], 13 + mov rdi, rsi + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rax + 11], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rax + 11], 15 + pcmpeqb xmm11, xmm14 + pandn xmm11, xmmword ptr [rip + .LCPI4_16] + paddb xmm11, xmm0 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edx, byte ptr [r13 + rax + 23] + movd xmm8, edx + pcmpeqb xmm12, xmm14 + pandn xmm12, xmmword ptr [rip + .LCPI4_17] + pcmpeqb xmm13, xmm14 + pandn xmm13, xmmword ptr [rip + .LCPI4_18] + por xmm13, xmm12 + movzx edx, byte ptr [r13 + rax + 24] + movd xmm12, edx + movdqa xmm9, xmmword ptr [rsp + 240] # 16-byte Reload + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rax + 12], 1 + pinsrb xmm9, byte ptr [r13 + r9 + 12], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rsi + 12], 3 + pinsrb xmm9, byte ptr [r13 + r14 + 12], 4 + mov r8, r11 + pinsrb xmm9, byte ptr [r13 + r11 + 12], 5 + mov r11, rbx + pinsrb xmm9, byte ptr [r13 + rbx + 12], 6 + mov rbx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rbx + 12], 7 + pinsrb xmm9, byte ptr [r13 + rcx + 12], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rax + 12], 9 + pinsrb xmm9, byte ptr [r13 + r10 + 12], 10 + pinsrb xmm9, byte ptr [r13 + r15 + 12], 11 + pinsrb xmm9, byte ptr [r13 + r12 + 12], 12 + pinsrb xmm9, byte ptr [r13 + rdi + 12], 13 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rdx + 12], 14 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rdi + 12], 15 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdi + 13], 1 + pinsrb xmm6, byte ptr [r13 + r9 + 13], 2 + pinsrb xmm6, byte ptr [r13 + rsi + 13], 3 + pinsrb xmm6, byte ptr [r13 + r14 + 13], 4 + pinsrb xmm6, byte ptr [r13 + r8 + 13], 5 + pinsrb xmm6, byte ptr [r13 + r11 + 13], 6 + pinsrb xmm6, byte ptr [r13 + rbx + 13], 7 + pinsrb xmm6, byte ptr [r13 + rcx + 13], 8 + pinsrb xmm6, byte ptr [r13 + rax + 13], 9 + pinsrb xmm6, byte ptr [r13 + r10 + 13], 10 + pinsrb xmm6, byte ptr [r13 + r15 + 13], 11 + pinsrb xmm6, byte ptr [r13 + r12 + 13], 12 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdi + 13], 13 + pinsrb xmm6, byte ptr [r13 + rdx + 13], 14 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdi + 13], 15 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rdi + 14], 1 + pinsrb xmm15, byte ptr [r13 + r9 + 14], 2 + pinsrb xmm15, byte ptr [r13 + rsi + 14], 3 + mov r9, rsi + pinsrb xmm15, byte ptr [r13 + r14 + 14], 4 + pinsrb xmm15, byte ptr [r13 + r8 + 14], 5 + pinsrb xmm15, byte ptr [r13 + r11 + 14], 6 + pinsrb xmm15, byte ptr [r13 + rbx + 14], 7 + mov r11, rbx + pinsrb xmm15, byte ptr [r13 + rcx + 14], 8 + pinsrb xmm15, byte ptr [r13 + rax + 14], 9 + mov rbx, rax + pinsrb xmm15, byte ptr [r13 + r10 + 14], 10 + mov rdi, r10 + pinsrb xmm15, byte ptr [r13 + r15 + 14], 11 + pinsrb xmm15, byte ptr [r13 + r12 + 14], 12 + mov r14, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + r14 + 14], 13 + pinsrb xmm15, byte ptr [r13 + rdx + 14], 14 + mov r15, rdx + pcmpeqb xmm9, xmm14 + pandn xmm9, xmmword ptr [rip + .LCPI4_19] + por xmm9, xmm13 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edx, byte ptr [r13 + rax + 25] + movd xmm13, edx + psubb xmm11, xmmword ptr [rip + .LCPI4_22] + por xmm9, xmm11 + movzx edx, byte ptr [r13 + rax + 26] + movd xmm0, edx + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rcx + 14], 15 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmmword ptr [rip + .LCPI4_20] + pcmpeqb xmm15, xmm14 + pandn xmm15, xmmword ptr [rip + .LCPI4_21] + por xmm15, xmm6 + movzx edx, byte ptr [r13 + rax + 27] + movd xmm11, edx + movdqa xmm6, xmmword ptr [rsp + 224] # 16-byte Reload + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rsi + 15], 1 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdx + 15], 2 + pinsrb xmm6, byte ptr [r13 + r9 + 15], 3 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r10 + 15], 4 + pinsrb xmm6, byte ptr [r13 + r8 + 15], 5 + mov r12, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r12 + 15], 6 + pinsrb xmm6, byte ptr [r13 + r11 + 15], 7 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdx + 15], 8 + pinsrb xmm6, byte ptr [r13 + rbx + 15], 9 + pinsrb xmm6, byte ptr [r13 + rdi + 15], 10 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rbx + 15], 11 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r11 + 15], 12 + pinsrb xmm6, byte ptr [r13 + r14 + 15], 13 + pinsrb xmm6, byte ptr [r13 + r15 + 15], 14 + pinsrb xmm6, byte ptr [r13 + rcx + 15], 15 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmmword ptr [rip + .LCPI4_6] + por xmm6, xmm15 + movzx edx, byte ptr [r13 + rax + 28] + movd xmm15, edx + por xmm6, xmm9 + movdqa xmmword ptr [rsp + 224], xmm6 # 16-byte Spill + movzx edx, byte ptr [r13 + rax + 29] + movd xmm9, edx + mov rdx, rsi + pinsrb xmm10, byte ptr [r13 + rsi + 16], 1 + mov rdi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rdi + 16], 2 + mov rsi, r9 + pinsrb xmm10, byte ptr [r13 + r9 + 16], 3 + pinsrb xmm10, byte ptr [r13 + r10 + 16], 4 + pinsrb xmm10, byte ptr [r13 + r8 + 16], 5 + pinsrb xmm10, byte ptr [r13 + r12 + 16], 6 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r9 + 16], 7 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rcx + 16], 8 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r15 + 16], 9 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r12 + 16], 10 + pinsrb xmm10, byte ptr [r13 + rbx + 16], 11 + pinsrb xmm10, byte ptr [r13 + r11 + 16], 12 + pinsrb xmm10, byte ptr [r13 + r14 + 16], 13 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r11 + 16], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rax + 16], 15 + pinsrb xmm4, byte ptr [r13 + rdx + 17], 1 + pinsrb xmm4, byte ptr [r13 + rdi + 17], 2 + pinsrb xmm4, byte ptr [r13 + rsi + 17], 3 + pinsrb xmm4, byte ptr [r13 + r10 + 17], 4 + pinsrb xmm4, byte ptr [r13 + r8 + 17], 5 + mov rdi, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rdi + 17], 6 + pinsrb xmm4, byte ptr [r13 + r9 + 17], 7 + pinsrb xmm4, byte ptr [r13 + rcx + 17], 8 + mov rcx, r15 + pinsrb xmm4, byte ptr [r13 + r15 + 17], 9 + mov rsi, r12 + pinsrb xmm4, byte ptr [r13 + r12 + 17], 10 + pinsrb xmm4, byte ptr [r13 + rbx + 17], 11 + mov r10, rbx + mov r12, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + r12 + 17], 12 + pinsrb xmm4, byte ptr [r13 + r14 + 17], 13 + mov r15, r11 + pinsrb xmm4, byte ptr [r13 + r11 + 17], 14 + pinsrb xmm4, byte ptr [r13 + rax + 17], 15 + pcmpeqb xmm10, xmm14 + pcmpeqb xmm4, xmm14 + movdqa xmm6, xmmword ptr [rip + .LCPI4_16] # xmm6 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pandn xmm4, xmm6 + paddb xmm4, xmm10 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + movzx edx, byte ptr [r13 + rbx + 30] + movd xmm10, edx + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 18], 1 + pinsrb xmm5, byte ptr [r13 + rax + 19], 1 + pinsrb xmm3, byte ptr [r13 + rax + 20], 1 + pinsrb xmm2, byte ptr [r13 + rax + 21], 1 + pinsrb xmm1, byte ptr [r13 + rax + 22], 1 + pinsrb xmm8, byte ptr [r13 + rax + 23], 1 + pinsrb xmm12, byte ptr [r13 + rax + 24], 1 + pinsrb xmm13, byte ptr [r13 + rax + 25], 1 + pinsrb xmm0, byte ptr [r13 + rax + 26], 1 + pinsrb xmm11, byte ptr [r13 + rax + 27], 1 + pinsrb xmm15, byte ptr [r13 + rax + 28], 1 + pinsrb xmm9, byte ptr [r13 + rax + 29], 1 + pinsrb xmm10, byte ptr [r13 + rax + 30], 1 + movzx edx, byte ptr [r13 + rbx + 31] + movd xmm6, edx + pinsrb xmm6, byte ptr [r13 + rax + 31], 1 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rdx + 18], 2 + pinsrb xmm5, byte ptr [r13 + rdx + 19], 2 + pinsrb xmm3, byte ptr [r13 + rdx + 20], 2 + pinsrb xmm2, byte ptr [r13 + rdx + 21], 2 + pinsrb xmm1, byte ptr [r13 + rdx + 22], 2 + pinsrb xmm8, byte ptr [r13 + rdx + 23], 2 + pinsrb xmm12, byte ptr [r13 + rdx + 24], 2 + pinsrb xmm13, byte ptr [r13 + rdx + 25], 2 + pinsrb xmm0, byte ptr [r13 + rdx + 26], 2 + pinsrb xmm11, byte ptr [r13 + rdx + 27], 2 + pinsrb xmm15, byte ptr [r13 + rdx + 28], 2 + pinsrb xmm9, byte ptr [r13 + rdx + 29], 2 + pinsrb xmm10, byte ptr [r13 + rdx + 30], 2 + pinsrb xmm6, byte ptr [r13 + rdx + 31], 2 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rdx + 18], 3 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r14 + 18], 4 + pinsrb xmm7, byte ptr [r13 + r8 + 18], 5 + pinsrb xmm7, byte ptr [r13 + rdi + 18], 6 + mov rbx, r9 + pinsrb xmm7, byte ptr [r13 + r9 + 18], 7 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r9 + 18], 8 + mov rax, rcx + pinsrb xmm7, byte ptr [r13 + rcx + 18], 9 + pinsrb xmm7, byte ptr [r13 + rsi + 18], 10 + pinsrb xmm7, byte ptr [r13 + r10 + 18], 11 + mov rcx, r12 + pinsrb xmm7, byte ptr [r13 + r12 + 18], 12 + mov r11, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r11 + 18], 13 + pinsrb xmm7, byte ptr [r13 + r15 + 18], 14 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r12 + 18], 15 + pinsrb xmm5, byte ptr [r13 + rdx + 19], 3 + pinsrb xmm5, byte ptr [r13 + r14 + 19], 4 + pinsrb xmm5, byte ptr [r13 + r8 + 19], 5 + pinsrb xmm5, byte ptr [r13 + rdi + 19], 6 + pinsrb xmm5, byte ptr [r13 + rbx + 19], 7 + pinsrb xmm5, byte ptr [r13 + r9 + 19], 8 + pinsrb xmm5, byte ptr [r13 + rax + 19], 9 + pinsrb xmm5, byte ptr [r13 + rsi + 19], 10 + pinsrb xmm5, byte ptr [r13 + r10 + 19], 11 + pinsrb xmm5, byte ptr [r13 + rcx + 19], 12 + pinsrb xmm5, byte ptr [r13 + r11 + 19], 13 + pinsrb xmm5, byte ptr [r13 + r15 + 19], 14 + pinsrb xmm5, byte ptr [r13 + r12 + 19], 15 + pinsrb xmm3, byte ptr [r13 + rdx + 20], 3 + pinsrb xmm3, byte ptr [r13 + r14 + 20], 4 + pinsrb xmm3, byte ptr [r13 + r8 + 20], 5 + pinsrb xmm3, byte ptr [r13 + rdi + 20], 6 + pinsrb xmm3, byte ptr [r13 + rbx + 20], 7 + pinsrb xmm3, byte ptr [r13 + r9 + 20], 8 + pinsrb xmm3, byte ptr [r13 + rax + 20], 9 + pinsrb xmm3, byte ptr [r13 + rsi + 20], 10 + pinsrb xmm3, byte ptr [r13 + r10 + 20], 11 + pinsrb xmm3, byte ptr [r13 + rcx + 20], 12 + pinsrb xmm3, byte ptr [r13 + r11 + 20], 13 + pinsrb xmm3, byte ptr [r13 + r15 + 20], 14 + pcmpeqb xmm7, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI4_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm7, xmm14 + pcmpeqb xmm5, xmmword ptr [rsp + 208] # 16-byte Folded Reload + movdqa xmm14, xmmword ptr [rip + .LCPI4_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm5, xmm14 + por xmm5, xmm7 + pinsrb xmm3, byte ptr [r13 + r12 + 20], 15 + movdqa xmm14, xmmword ptr [rsp + 208] # 16-byte Reload + pcmpeqb xmm3, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI4_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm3, xmm7 + por xmm3, xmm5 + pcmpeqd xmm5, xmm5 + psubb xmm4, xmm5 + por xmm3, xmm4 + pinsrb xmm2, byte ptr [r13 + rdx + 21], 3 + pinsrb xmm2, byte ptr [r13 + r14 + 21], 4 + pinsrb xmm2, byte ptr [r13 + r8 + 21], 5 + pinsrb xmm2, byte ptr [r13 + rdi + 21], 6 + pinsrb xmm2, byte ptr [r13 + rbx + 21], 7 + pinsrb xmm2, byte ptr [r13 + r9 + 21], 8 + pinsrb xmm2, byte ptr [r13 + rax + 21], 9 + pinsrb xmm2, byte ptr [r13 + rsi + 21], 10 + pinsrb xmm2, byte ptr [r13 + r10 + 21], 11 + pinsrb xmm2, byte ptr [r13 + rcx + 21], 12 + pinsrb xmm2, byte ptr [r13 + r11 + 21], 13 + pinsrb xmm2, byte ptr [r13 + r15 + 21], 14 + pinsrb xmm2, byte ptr [r13 + r12 + 21], 15 + pinsrb xmm1, byte ptr [r13 + rdx + 22], 3 + pinsrb xmm1, byte ptr [r13 + r14 + 22], 4 + pinsrb xmm1, byte ptr [r13 + r8 + 22], 5 + pinsrb xmm1, byte ptr [r13 + rdi + 22], 6 + pinsrb xmm1, byte ptr [r13 + rbx + 22], 7 + pinsrb xmm1, byte ptr [r13 + r9 + 22], 8 + pinsrb xmm1, byte ptr [r13 + rax + 22], 9 + pinsrb xmm1, byte ptr [r13 + rsi + 22], 10 + pinsrb xmm1, byte ptr [r13 + r10 + 22], 11 + pinsrb xmm1, byte ptr [r13 + rcx + 22], 12 + pinsrb xmm1, byte ptr [r13 + r11 + 22], 13 + pinsrb xmm1, byte ptr [r13 + r15 + 22], 14 + pinsrb xmm1, byte ptr [r13 + r12 + 22], 15 + pinsrb xmm8, byte ptr [r13 + rdx + 23], 3 + pinsrb xmm8, byte ptr [r13 + r14 + 23], 4 + pinsrb xmm8, byte ptr [r13 + r8 + 23], 5 + pinsrb xmm8, byte ptr [r13 + rdi + 23], 6 + pinsrb xmm8, byte ptr [r13 + rbx + 23], 7 + pinsrb xmm8, byte ptr [r13 + r9 + 23], 8 + pinsrb xmm8, byte ptr [r13 + rax + 23], 9 + pinsrb xmm8, byte ptr [r13 + rsi + 23], 10 + pinsrb xmm8, byte ptr [r13 + r10 + 23], 11 + pinsrb xmm8, byte ptr [r13 + rcx + 23], 12 + pinsrb xmm8, byte ptr [r13 + r11 + 23], 13 + pinsrb xmm8, byte ptr [r13 + r15 + 23], 14 + pcmpeqb xmm2, xmm14 + movdqa xmm5, xmmword ptr [rip + .LCPI4_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm5 + pcmpeqb xmm1, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI4_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm1, xmm7 + por xmm1, xmm2 + pinsrb xmm8, byte ptr [r13 + r12 + 23], 15 + pcmpeqb xmm8, xmm14 + movdqa xmm4, xmmword ptr [rip + .LCPI4_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm8, xmm4 + por xmm8, xmm1 + pinsrb xmm12, byte ptr [r13 + rdx + 24], 3 + pinsrb xmm12, byte ptr [r13 + r14 + 24], 4 + pinsrb xmm12, byte ptr [r13 + r8 + 24], 5 + pinsrb xmm12, byte ptr [r13 + rdi + 24], 6 + pinsrb xmm12, byte ptr [r13 + rbx + 24], 7 + pinsrb xmm12, byte ptr [r13 + r9 + 24], 8 + pinsrb xmm12, byte ptr [r13 + rax + 24], 9 + pinsrb xmm12, byte ptr [r13 + rsi + 24], 10 + pinsrb xmm12, byte ptr [r13 + r10 + 24], 11 + pinsrb xmm12, byte ptr [r13 + rcx + 24], 12 + pinsrb xmm12, byte ptr [r13 + r11 + 24], 13 + pinsrb xmm12, byte ptr [r13 + r15 + 24], 14 + pinsrb xmm12, byte ptr [r13 + r12 + 24], 15 + por xmm8, xmm3 + pcmpeqb xmm12, xmm14 + pinsrb xmm13, byte ptr [r13 + rdx + 25], 3 + pinsrb xmm13, byte ptr [r13 + r14 + 25], 4 + pinsrb xmm13, byte ptr [r13 + r8 + 25], 5 + pinsrb xmm13, byte ptr [r13 + rdi + 25], 6 + pinsrb xmm13, byte ptr [r13 + rbx + 25], 7 + pinsrb xmm13, byte ptr [r13 + r9 + 25], 8 + pinsrb xmm13, byte ptr [r13 + rax + 25], 9 + pinsrb xmm13, byte ptr [r13 + rsi + 25], 10 + pinsrb xmm13, byte ptr [r13 + r10 + 25], 11 + pinsrb xmm13, byte ptr [r13 + rcx + 25], 12 + pinsrb xmm13, byte ptr [r13 + r11 + 25], 13 + pinsrb xmm13, byte ptr [r13 + r15 + 25], 14 + pinsrb xmm13, byte ptr [r13 + r12 + 25], 15 + pinsrb xmm0, byte ptr [r13 + rdx + 26], 3 + pinsrb xmm0, byte ptr [r13 + r14 + 26], 4 + pinsrb xmm0, byte ptr [r13 + r8 + 26], 5 + pinsrb xmm0, byte ptr [r13 + rdi + 26], 6 + pinsrb xmm0, byte ptr [r13 + rbx + 26], 7 + pinsrb xmm0, byte ptr [r13 + r9 + 26], 8 + pinsrb xmm0, byte ptr [r13 + rax + 26], 9 + pinsrb xmm0, byte ptr [r13 + rsi + 26], 10 + pinsrb xmm0, byte ptr [r13 + r10 + 26], 11 + pinsrb xmm0, byte ptr [r13 + rcx + 26], 12 + pinsrb xmm0, byte ptr [r13 + r11 + 26], 13 + pinsrb xmm0, byte ptr [r13 + r15 + 26], 14 + pinsrb xmm0, byte ptr [r13 + r12 + 26], 15 + pinsrb xmm11, byte ptr [r13 + rdx + 27], 3 + pinsrb xmm11, byte ptr [r13 + r14 + 27], 4 + pinsrb xmm11, byte ptr [r13 + r8 + 27], 5 + pinsrb xmm11, byte ptr [r13 + rdi + 27], 6 + pinsrb xmm11, byte ptr [r13 + rbx + 27], 7 + pinsrb xmm11, byte ptr [r13 + r9 + 27], 8 + pinsrb xmm11, byte ptr [r13 + rax + 27], 9 + pinsrb xmm11, byte ptr [r13 + rsi + 27], 10 + pinsrb xmm11, byte ptr [r13 + r10 + 27], 11 + pinsrb xmm11, byte ptr [r13 + rcx + 27], 12 + pinsrb xmm11, byte ptr [r13 + r11 + 27], 13 + pinsrb xmm11, byte ptr [r13 + r15 + 27], 14 + pcmpeqb xmm13, xmm14 + pandn xmm13, xmmword ptr [rip + .LCPI4_16] + paddb xmm13, xmm12 + pinsrb xmm11, byte ptr [r13 + r12 + 27], 15 + pcmpeqb xmm0, xmm14 + pandn xmm0, xmmword ptr [rip + .LCPI4_17] + pcmpeqb xmm11, xmm14 + pandn xmm11, xmmword ptr [rip + .LCPI4_18] + por xmm11, xmm0 + pinsrb xmm15, byte ptr [r13 + rdx + 28], 3 + pinsrb xmm9, byte ptr [r13 + rdx + 29], 3 + pinsrb xmm10, byte ptr [r13 + rdx + 30], 3 + pinsrb xmm6, byte ptr [r13 + rdx + 31], 3 + pinsrb xmm15, byte ptr [r13 + r14 + 28], 4 + pinsrb xmm9, byte ptr [r13 + r14 + 29], 4 + pinsrb xmm10, byte ptr [r13 + r14 + 30], 4 + pinsrb xmm6, byte ptr [r13 + r14 + 31], 4 + pinsrb xmm15, byte ptr [r13 + r8 + 28], 5 + pinsrb xmm9, byte ptr [r13 + r8 + 29], 5 + pinsrb xmm10, byte ptr [r13 + r8 + 30], 5 + pinsrb xmm6, byte ptr [r13 + r8 + 31], 5 + mov rdx, rdi + pinsrb xmm15, byte ptr [r13 + rdi + 28], 6 + pinsrb xmm9, byte ptr [r13 + rdi + 29], 6 + pinsrb xmm10, byte ptr [r13 + rdi + 30], 6 + pinsrb xmm6, byte ptr [r13 + rdi + 31], 6 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + mov rdx, rbx + pinsrb xmm15, byte ptr [r13 + rbx + 28], 7 + pinsrb xmm9, byte ptr [r13 + rbx + 29], 7 + pinsrb xmm10, byte ptr [r13 + rbx + 30], 7 + pinsrb xmm6, byte ptr [r13 + rbx + 31], 7 + mov rdx, r9 + pinsrb xmm15, byte ptr [r13 + r9 + 28], 8 + pinsrb xmm9, byte ptr [r13 + r9 + 29], 8 + pinsrb xmm10, byte ptr [r13 + r9 + 30], 8 + pinsrb xmm6, byte ptr [r13 + r9 + 31], 8 + pinsrb xmm15, byte ptr [r13 + rax + 28], 9 + pinsrb xmm9, byte ptr [r13 + rax + 29], 9 + pinsrb xmm10, byte ptr [r13 + rax + 30], 9 + pinsrb xmm6, byte ptr [r13 + rax + 31], 9 + pinsrb xmm15, byte ptr [r13 + rsi + 28], 10 + pinsrb xmm9, byte ptr [r13 + rsi + 29], 10 + pinsrb xmm10, byte ptr [r13 + rsi + 30], 10 + pinsrb xmm6, byte ptr [r13 + rsi + 31], 10 + mov rax, r10 + pinsrb xmm15, byte ptr [r13 + r10 + 28], 11 + pinsrb xmm9, byte ptr [r13 + r10 + 29], 11 + pinsrb xmm10, byte ptr [r13 + r10 + 30], 11 + pinsrb xmm6, byte ptr [r13 + r10 + 31], 11 + pinsrb xmm15, byte ptr [r13 + rcx + 28], 12 + pinsrb xmm9, byte ptr [r13 + rcx + 29], 12 + pinsrb xmm10, byte ptr [r13 + rcx + 30], 12 + pinsrb xmm6, byte ptr [r13 + rcx + 31], 12 + mov rax, r11 + pinsrb xmm15, byte ptr [r13 + r11 + 28], 13 + pinsrb xmm9, byte ptr [r13 + r11 + 29], 13 + pinsrb xmm10, byte ptr [r13 + r11 + 30], 13 + pinsrb xmm6, byte ptr [r13 + r11 + 31], 13 + mov rax, r15 + pinsrb xmm15, byte ptr [r13 + r15 + 28], 14 + pinsrb xmm9, byte ptr [r13 + r15 + 29], 14 + pinsrb xmm10, byte ptr [r13 + r15 + 30], 14 + pinsrb xmm6, byte ptr [r13 + r15 + 31], 14 + mov rax, r12 + pinsrb xmm15, byte ptr [r13 + r12 + 28], 15 + pinsrb xmm9, byte ptr [r13 + r12 + 29], 15 + pinsrb xmm10, byte ptr [r13 + r12 + 30], 15 + pcmpeqb xmm15, xmm14 + pandn xmm15, xmmword ptr [rip + .LCPI4_19] + por xmm15, xmm11 + pinsrb xmm6, byte ptr [r13 + r12 + 31], 15 + psubb xmm13, xmmword ptr [rip + .LCPI4_22] + por xmm15, xmm13 + pcmpeqb xmm9, xmm14 + pandn xmm9, xmm5 + pcmpeqb xmm10, xmm14 + pandn xmm10, xmm7 + por xmm10, xmm9 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmm4 + por xmm6, xmm10 + por xmm6, xmm15 + movdqa xmm0, xmm8 + punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] + movdqa xmm3, xmmword ptr [rsp + 176] # 16-byte Reload + movdqa xmm1, xmm3 + movdqa xmm4, xmmword ptr [rsp + 224] # 16-byte Reload + punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] + movdqa xmm2, xmm1 + punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] + punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] + punpckhbw xmm3, xmm4 # xmm3 = xmm3[8],xmm4[8],xmm3[9],xmm4[9],xmm3[10],xmm4[10],xmm3[11],xmm4[11],xmm3[12],xmm4[12],xmm3[13],xmm4[13],xmm3[14],xmm4[14],xmm3[15],xmm4[15] + movdqa xmm0, xmm3 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + movdqu xmmword ptr [r8 + 4*rcx + 48], xmm3 + movdqu xmmword ptr [r8 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r8 + 4*rcx + 16], xmm1 + movdqu xmmword ptr [r8 + 4*rcx], xmm2 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + jne .LBB4_213 +# %bb.214: + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov r15b, byte ptr [rsp + 8] # 1-byte Reload + mov r13, qword ptr [rsp + 272] # 8-byte Reload + mov r14, qword ptr [rsp + 144] # 8-byte Reload + jne .LBB4_127 + jmp .LBB4_131 +.LBB4_215: + and rcx, -8 + mov rax, rcx + shl rax, 6 + add rax, rsi + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 40], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] mov qword ptr [rsp + 8], rax # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB5_52 -# %bb.53: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 240] # 8-byte Reload -.LBB5_54: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.55: + mov dword ptr [rsp + 56], r13d # 4-byte Spill + movd xmm0, r13d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] + xor r15d, r15d + mov qword ptr [rsp + 120], r12 # 8-byte Spill + pxor xmm15, xmm15 + .p2align 4, 0x90 +.LBB4_216: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill + shl r15, 6 + mov r9, r15 + mov r12, r15 + mov r13, r15 + mov rdi, r15 + mov rbx, r15 mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - jne .LBB5_194 -# %bb.56: - xor edi, edi - jmp .LBB5_196 -.LBB5_2: - cmp edi, 2 - je .LBB5_57 -# %bb.3: - cmp edi, 3 - jne .LBB5_198 -# %bb.4: - mov al, byte ptr [rsi] - mov byte ptr [rsp + 16], al # 1-byte Spill - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB5_8 -# %bb.5: - movsxd rax, r9d - mov rdx, qword ptr [rsp + 8] # 8-byte Reload + movzx eax, word ptr [rsi + r15] + movd xmm5, eax + movzx eax, word ptr [rsi + r15 + 2] + movd xmm0, eax + movzx eax, word ptr [rsi + r15 + 4] + movd xmm1, eax + movzx eax, word ptr [rsi + r15 + 6] + movd xmm7, eax + movzx eax, word ptr [rsi + r15 + 8] + movd xmm8, eax + movzx eax, word ptr [rsi + r15 + 10] + movd xmm4, eax + movzx eax, word ptr [rsi + r15 + 12] + movzx r10d, word ptr [rsi + r15 + 14] + movzx r11d, word ptr [rsi + r15 + 16] + movzx edx, word ptr [rsi + r15 + 18] + movzx r14d, word ptr [rsi + r15 + 20] + mov rcx, r15 + or rcx, 64 + or r9, 128 + or r12, 192 + or r13, 256 + or rdi, 320 + or rbx, 384 + pinsrw xmm5, word ptr [rsi + rcx], 1 + pinsrw xmm5, word ptr [rsi + r9], 2 + pinsrw xmm5, word ptr [rsi + r12], 3 + pinsrw xmm5, word ptr [rsi + r13], 4 + pinsrw xmm5, word ptr [rsi + rdi], 5 + pinsrw xmm5, word ptr [rsi + rbx], 6 + pinsrw xmm0, word ptr [rsi + rcx + 2], 1 + pinsrw xmm0, word ptr [rsi + r9 + 2], 2 + pinsrw xmm0, word ptr [rsi + r12 + 2], 3 + pinsrw xmm0, word ptr [rsi + r13 + 2], 4 + pinsrw xmm0, word ptr [rsi + rdi + 2], 5 + pinsrw xmm0, word ptr [rsi + rbx + 2], 6 + or r8, 448 + pinsrw xmm0, word ptr [rsi + r8 + 2], 7 + movd xmm2, eax + movzx eax, word ptr [rsi + r15 + 22] + mov dword ptr [rsp + 16], eax # 4-byte Spill + pcmpeqw xmm0, xmm11 + pinsrw xmm1, word ptr [rsi + rcx + 4], 1 + pinsrw xmm1, word ptr [rsi + r9 + 4], 2 + pinsrw xmm1, word ptr [rsi + r12 + 4], 3 + pinsrw xmm1, word ptr [rsi + r13 + 4], 4 + pinsrw xmm1, word ptr [rsi + rdi + 4], 5 + pinsrw xmm1, word ptr [rsi + rbx + 4], 6 + pinsrw xmm1, word ptr [rsi + r8 + 4], 7 + packsswb xmm0, xmm0 + pcmpeqw xmm1, xmm11 + movdqa xmm9, xmmword ptr [rip + .LCPI4_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm3, xmm9 + pblendvb xmm3, xmm15, xmm0 + packsswb xmm1, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm0 + movdqa xmm14, xmm0 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r10d + movzx r10d, word ptr [rsi + r15 + 24] + pinsrw xmm5, word ptr [rsi + r8], 7 + pcmpeqw xmm5, xmm11 + pcmpeqd xmm0, xmm0 + pxor xmm5, xmm0 + packsswb xmm5, xmm5 + pinsrw xmm7, word ptr [rsi + rcx + 6], 1 + pinsrw xmm7, word ptr [rsi + r9 + 6], 2 + pinsrw xmm7, word ptr [rsi + r12 + 6], 3 + pinsrw xmm7, word ptr [rsi + r13 + 6], 4 + pinsrw xmm7, word ptr [rsi + rdi + 6], 5 + pinsrw xmm7, word ptr [rsi + rbx + 6], 6 + pinsrw xmm7, word ptr [rsi + r8 + 6], 7 + pcmpeqw xmm7, xmm11 + packsswb xmm7, xmm7 + pinsrw xmm8, word ptr [rsi + rcx + 8], 1 + pinsrw xmm8, word ptr [rsi + r9 + 8], 2 + pinsrw xmm8, word ptr [rsi + r12 + 8], 3 + pinsrw xmm8, word ptr [rsi + r13 + 8], 4 + pinsrw xmm8, word ptr [rsi + rdi + 8], 5 + pinsrw xmm8, word ptr [rsi + rbx + 8], 6 + pinsrw xmm8, word ptr [rsi + r8 + 8], 7 + psubb xmm3, xmm5 + movdqa xmm12, xmmword ptr [rip + .LCPI4_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm7 + pblendvb xmm12, xmm15, xmm0 + movd xmm7, r11d + movzx eax, word ptr [rsi + r15 + 26] + pcmpeqw xmm8, xmm11 + packsswb xmm8, xmm8 + por xmm12, xmm6 + movdqa xmm13, xmmword ptr [rip + .LCPI4_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm8 + pblendvb xmm13, xmm15, xmm0 + movd xmm6, edx + movzx r11d, word ptr [rsi + r15 + 28] + pinsrw xmm4, word ptr [rsi + rcx + 10], 1 + pinsrw xmm4, word ptr [rsi + r9 + 10], 2 + pinsrw xmm4, word ptr [rsi + r12 + 10], 3 + pinsrw xmm4, word ptr [rsi + r13 + 10], 4 + pinsrw xmm4, word ptr [rsi + rdi + 10], 5 + pinsrw xmm4, word ptr [rsi + rbx + 10], 6 + pinsrw xmm4, word ptr [rsi + r8 + 10], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + pinsrw xmm2, word ptr [rsi + rcx + 12], 1 + pinsrw xmm2, word ptr [rsi + r9 + 12], 2 + pinsrw xmm2, word ptr [rsi + r12 + 12], 3 + pinsrw xmm2, word ptr [rsi + r13 + 12], 4 + pinsrw xmm2, word ptr [rsi + rdi + 12], 5 + pinsrw xmm2, word ptr [rsi + rbx + 12], 6 + por xmm12, xmm3 + movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, r14d + movzx edx, word ptr [rsi + r15 + 30] + mov dword ptr [rsp + 48], edx # 4-byte Spill + pinsrw xmm2, word ptr [rsi + r8 + 12], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm13 + movdqa xmm13, xmmword ptr [rip + .LCPI4_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx edx, word ptr [rsi + r15 + 32] + mov dword ptr [rsp + 32], edx # 4-byte Spill + pinsrw xmm1, word ptr [rsi + rcx + 14], 1 + pinsrw xmm1, word ptr [rsi + r9 + 14], 2 + pinsrw xmm1, word ptr [rsi + r12 + 14], 3 + pinsrw xmm1, word ptr [rsi + r13 + 14], 4 + pinsrw xmm1, word ptr [rsi + rdi + 14], 5 + pinsrw xmm1, word ptr [rsi + rbx + 14], 6 + por xmm13, xmm5 + movd xmm2, r10d + movzx edx, word ptr [rsi + r15 + 34] + mov dword ptr [rsp + 16], edx # 4-byte Spill + pinsrw xmm1, word ptr [rsi + r8 + 14], 7 + pcmpeqw xmm1, xmm11 + pinsrw xmm6, word ptr [rsi + rcx + 18], 1 + pinsrw xmm6, word ptr [rsi + r9 + 18], 2 + pinsrw xmm6, word ptr [rsi + r12 + 18], 3 + pinsrw xmm6, word ptr [rsi + r13 + 18], 4 + pinsrw xmm6, word ptr [rsi + rdi + 18], 5 + pinsrw xmm6, word ptr [rsi + rbx + 18], 6 + packsswb xmm1, xmm1 + pinsrw xmm6, word ptr [rsi + r8 + 18], 7 + pcmpeqw xmm6, xmm11 + packsswb xmm6, xmm6 + por xmm13, xmm12 + movdqa xmm12, xmmword ptr [rip + .LCPI4_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm12, xmm15, xmm0 + movdqa xmm8, xmm9 + movdqa xmm0, xmm6 + pblendvb xmm8, xmm15, xmm0 + movd xmm1, eax + movzx r14d, word ptr [rsi + r15 + 36] + pinsrw xmm7, word ptr [rsi + rcx + 16], 1 + pinsrw xmm7, word ptr [rsi + r9 + 16], 2 + pinsrw xmm7, word ptr [rsi + r12 + 16], 3 + pinsrw xmm7, word ptr [rsi + r13 + 16], 4 + pinsrw xmm7, word ptr [rsi + rdi + 16], 5 + pinsrw xmm7, word ptr [rsi + rbx + 16], 6 + pinsrw xmm4, word ptr [rsi + rcx + 20], 1 + pinsrw xmm4, word ptr [rsi + r9 + 20], 2 + pinsrw xmm4, word ptr [rsi + r12 + 20], 3 + pinsrw xmm4, word ptr [rsi + r13 + 20], 4 + pinsrw xmm4, word ptr [rsi + rdi + 20], 5 + pinsrw xmm4, word ptr [rsi + rbx + 20], 6 + pinsrw xmm4, word ptr [rsi + r8 + 20], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm12, xmm13 + movdqa xmm5, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, r11d + movzx r11d, word ptr [rsi + r15 + 38] + pinsrw xmm7, word ptr [rsi + r8 + 16], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI4_22] + packsswb xmm7, xmm7 + pinsrw xmm3, word ptr [rsi + rcx + 22], 1 + pinsrw xmm3, word ptr [rsi + r9 + 22], 2 + pinsrw xmm3, word ptr [rsi + r12 + 22], 3 + pinsrw xmm3, word ptr [rsi + r13 + 22], 4 + pinsrw xmm3, word ptr [rsi + rdi + 22], 5 + pinsrw xmm3, word ptr [rsi + rbx + 22], 6 + pinsrw xmm3, word ptr [rsi + r8 + 22], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rsi + rcx + 24], 1 + pinsrw xmm2, word ptr [rsi + r9 + 24], 2 + pinsrw xmm2, word ptr [rsi + r12 + 24], 3 + pinsrw xmm2, word ptr [rsi + r13 + 24], 4 + pinsrw xmm2, word ptr [rsi + rdi + 24], 5 + pinsrw xmm2, word ptr [rsi + rbx + 24], 6 + pinsrw xmm2, word ptr [rsi + r8 + 24], 7 + psubb xmm8, xmm7 + movdqa xmm10, xmmword ptr [rip + .LCPI4_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm14, xmm10 + movdqa xmm0, xmm3 + pblendvb xmm14, xmm15, xmm0 + movd xmm3, dword ptr [rsp + 48] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx eax, word ptr [rsi + r15 + 40] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm14, xmm5 + movdqa xmm9, xmmword ptr [rip + .LCPI4_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm7, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r10d, word ptr [rsi + r15 + 42] + pinsrw xmm1, word ptr [rsi + rcx + 26], 1 + pinsrw xmm1, word ptr [rsi + r9 + 26], 2 + pinsrw xmm1, word ptr [rsi + r12 + 26], 3 + pinsrw xmm1, word ptr [rsi + r13 + 26], 4 + pinsrw xmm1, word ptr [rsi + rdi + 26], 5 + pinsrw xmm1, word ptr [rsi + rbx + 26], 6 + pinsrw xmm1, word ptr [rsi + r8 + 26], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm4, word ptr [rsi + rcx + 28], 1 + pinsrw xmm4, word ptr [rsi + r9 + 28], 2 + pinsrw xmm4, word ptr [rsi + r12 + 28], 3 + pinsrw xmm4, word ptr [rsi + r13 + 28], 4 + pinsrw xmm4, word ptr [rsi + rdi + 28], 5 + pinsrw xmm4, word ptr [rsi + rbx + 28], 6 + por xmm14, xmm8 + movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm2, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm2 = mem[0],zero,zero,zero + movzx edx, word ptr [rsi + r15 + 44] + mov dword ptr [rsp + 32], edx # 4-byte Spill + pinsrw xmm4, word ptr [rsi + r8 + 28], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm5, xmm13 + movdqa xmm6, xmmword ptr [rip + .LCPI4_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, r14d + movzx edx, word ptr [rsi + r15 + 46] + mov dword ptr [rsp + 16], edx # 4-byte Spill + pinsrw xmm3, word ptr [rsi + rcx + 30], 1 + pinsrw xmm3, word ptr [rsi + r9 + 30], 2 + pinsrw xmm3, word ptr [rsi + r12 + 30], 3 + pinsrw xmm3, word ptr [rsi + r13 + 30], 4 + pinsrw xmm3, word ptr [rsi + rdi + 30], 5 + pinsrw xmm3, word ptr [rsi + rbx + 30], 6 + por xmm6, xmm5 + movd xmm1, r11d + movzx r11d, word ptr [rsi + r15 + 48] + pinsrw xmm3, word ptr [rsi + r8 + 30], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm2, word ptr [rsi + rcx + 34], 1 + pinsrw xmm2, word ptr [rsi + r9 + 34], 2 + pinsrw xmm2, word ptr [rsi + r12 + 34], 3 + pinsrw xmm2, word ptr [rsi + r13 + 34], 4 + pinsrw xmm2, word ptr [rsi + rdi + 34], 5 + pinsrw xmm2, word ptr [rsi + rbx + 34], 6 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rsi + r8 + 34], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm6, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI4_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm14 + movdqa xmm0, xmm3 + pblendvb xmm13, xmm15, xmm0 + movdqa xmm8, xmmword ptr [rip + .LCPI4_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm8, xmm15, xmm0 + movd xmm2, eax + movzx r14d, word ptr [rsi + r15 + 50] + pinsrw xmm7, word ptr [rsi + rcx + 32], 1 + pinsrw xmm7, word ptr [rsi + r9 + 32], 2 + pinsrw xmm7, word ptr [rsi + r12 + 32], 3 + pinsrw xmm7, word ptr [rsi + r13 + 32], 4 + pinsrw xmm7, word ptr [rsi + rdi + 32], 5 + pinsrw xmm7, word ptr [rsi + rbx + 32], 6 + pinsrw xmm4, word ptr [rsi + rcx + 36], 1 + pinsrw xmm4, word ptr [rsi + r9 + 36], 2 + pinsrw xmm4, word ptr [rsi + r12 + 36], 3 + pinsrw xmm4, word ptr [rsi + r13 + 36], 4 + pinsrw xmm4, word ptr [rsi + rdi + 36], 5 + pinsrw xmm4, word ptr [rsi + rbx + 36], 6 + pinsrw xmm4, word ptr [rsi + r8 + 36], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm13, xmm6 + movdqa xmm6, xmmword ptr [rip + .LCPI4_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm3, r10d + movzx edx, word ptr [rsi + r15 + 52] + pinsrw xmm7, word ptr [rsi + r8 + 32], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI4_22] + packsswb xmm7, xmm7 + pinsrw xmm1, word ptr [rsi + rcx + 38], 1 + pinsrw xmm1, word ptr [rsi + r9 + 38], 2 + pinsrw xmm1, word ptr [rsi + r12 + 38], 3 + pinsrw xmm1, word ptr [rsi + r13 + 38], 4 + pinsrw xmm1, word ptr [rsi + rdi + 38], 5 + pinsrw xmm1, word ptr [rsi + rbx + 38], 6 + pinsrw xmm1, word ptr [rsi + r8 + 38], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm2, word ptr [rsi + rcx + 40], 1 + pinsrw xmm2, word ptr [rsi + r9 + 40], 2 + pinsrw xmm2, word ptr [rsi + r12 + 40], 3 + pinsrw xmm2, word ptr [rsi + r13 + 40], 4 + pinsrw xmm2, word ptr [rsi + rdi + 40], 5 + pinsrw xmm2, word ptr [rsi + rbx + 40], 6 + pinsrw xmm2, word ptr [rsi + r8 + 40], 7 + psubb xmm8, xmm7 + movdqa xmm5, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r10d, word ptr [rsi + r15 + 54] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm6 + movdqa xmm6, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx eax, word ptr [rsi + r15 + 56] + pinsrw xmm3, word ptr [rsi + rcx + 42], 1 + pinsrw xmm3, word ptr [rsi + r9 + 42], 2 + pinsrw xmm3, word ptr [rsi + r12 + 42], 3 + pinsrw xmm3, word ptr [rsi + r13 + 42], 4 + pinsrw xmm3, word ptr [rsi + rdi + 42], 5 + pinsrw xmm3, word ptr [rsi + rbx + 42], 6 + pinsrw xmm3, word ptr [rsi + r8 + 42], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rsi + rcx + 44], 1 + pinsrw xmm1, word ptr [rsi + r9 + 44], 2 + pinsrw xmm1, word ptr [rsi + r12 + 44], 3 + pinsrw xmm1, word ptr [rsi + r13 + 44], 4 + pinsrw xmm1, word ptr [rsi + rdi + 44], 5 + pinsrw xmm1, word ptr [rsi + rbx + 44], 6 + por xmm5, xmm8 + movdqa xmm9, xmmword ptr [rip + .LCPI4_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm2, xmm9 + movdqa xmm0, xmm3 + pblendvb xmm2, xmm15, xmm0 + movd xmm7, r11d + movzx r11d, word ptr [rsi + r15 + 58] + pinsrw xmm1, word ptr [rsi + r8 + 44], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm2, xmm6 + movdqa xmm10, xmmword ptr [rip + .LCPI4_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r14d + movzx r14d, word ptr [rsi + r15 + 60] + por xmm6, xmm2 + movd xmm2, edx + pinsrw xmm4, word ptr [rsi + rcx + 46], 1 + pinsrw xmm4, word ptr [rsi + r9 + 46], 2 + pinsrw xmm4, word ptr [rsi + r12 + 46], 3 + pinsrw xmm4, word ptr [rsi + r13 + 46], 4 + pinsrw xmm4, word ptr [rsi + rdi + 46], 5 + pinsrw xmm4, word ptr [rsi + rbx + 46], 6 + pinsrw xmm4, word ptr [rsi + r8 + 46], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm6, xmm5 + movdqa xmm8, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm8, xmm15, xmm0 + movd xmm3, r10d + pinsrw xmm1, word ptr [rsi + rcx + 50], 1 + pinsrw xmm1, word ptr [rsi + r9 + 50], 2 + pinsrw xmm1, word ptr [rsi + r12 + 50], 3 + pinsrw xmm1, word ptr [rsi + r13 + 50], 4 + pinsrw xmm1, word ptr [rsi + rdi + 50], 5 + pinsrw xmm1, word ptr [rsi + rbx + 50], 6 + pinsrw xmm1, word ptr [rsi + r8 + 50], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm8, xmm6 + movdqa xmm4, xmmword ptr [rip + .LCPI4_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movd xmm1, eax + pinsrw xmm7, word ptr [rsi + rcx + 48], 1 + pinsrw xmm7, word ptr [rsi + r9 + 48], 2 + pinsrw xmm7, word ptr [rsi + r12 + 48], 3 + pinsrw xmm7, word ptr [rsi + r13 + 48], 4 + pinsrw xmm7, word ptr [rsi + rdi + 48], 5 + pinsrw xmm7, word ptr [rsi + rbx + 48], 6 + pinsrw xmm7, word ptr [rsi + r8 + 48], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI4_22] + pinsrw xmm2, word ptr [rsi + rcx + 52], 1 + pinsrw xmm2, word ptr [rsi + r9 + 52], 2 + pinsrw xmm2, word ptr [rsi + r12 + 52], 3 + pinsrw xmm2, word ptr [rsi + r13 + 52], 4 + pinsrw xmm2, word ptr [rsi + rdi + 52], 5 + pinsrw xmm2, word ptr [rsi + rbx + 52], 6 + packsswb xmm7, xmm7 + pinsrw xmm2, word ptr [rsi + r8 + 52], 7 + pcmpeqw xmm2, xmm11 + pinsrw xmm3, word ptr [rsi + rcx + 54], 1 + pinsrw xmm3, word ptr [rsi + r9 + 54], 2 + pinsrw xmm3, word ptr [rsi + r12 + 54], 3 + pinsrw xmm3, word ptr [rsi + r13 + 54], 4 + pinsrw xmm3, word ptr [rsi + rdi + 54], 5 + pinsrw xmm3, word ptr [rsi + rbx + 54], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rsi + r8 + 54], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm1, word ptr [rsi + rcx + 56], 1 + pinsrw xmm1, word ptr [rsi + r9 + 56], 2 + pinsrw xmm1, word ptr [rsi + r12 + 56], 3 + pinsrw xmm1, word ptr [rsi + r13 + 56], 4 + pinsrw xmm1, word ptr [rsi + rdi + 56], 5 + pinsrw xmm1, word ptr [rsi + rbx + 56], 6 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rsi + r8 + 56], 7 + psubb xmm4, xmm7 + movdqa xmm5, xmmword ptr [rip + .LCPI4_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm5, xmm15, xmm0 + movdqa xmm6, xmmword ptr [rip + .LCPI4_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm3 + pblendvb xmm6, xmm15, xmm0 + movd xmm2, r11d + pcmpeqw xmm1, xmm11 + pinsrw xmm2, word ptr [rsi + rcx + 58], 1 + pinsrw xmm2, word ptr [rsi + r9 + 58], 2 + pinsrw xmm2, word ptr [rsi + r12 + 58], 3 + pinsrw xmm2, word ptr [rsi + r13 + 58], 4 + pinsrw xmm2, word ptr [rsi + rdi + 58], 5 + pinsrw xmm2, word ptr [rsi + rbx + 58], 6 + pinsrw xmm2, word ptr [rsi + r8 + 58], 7 + packsswb xmm1, xmm1 + pcmpeqw xmm2, xmm11 + por xmm6, xmm5 + movd xmm3, r14d + pinsrw xmm3, word ptr [rsi + rcx + 60], 1 + pinsrw xmm3, word ptr [rsi + r9 + 60], 2 + pinsrw xmm3, word ptr [rsi + r12 + 60], 3 + pinsrw xmm3, word ptr [rsi + r13 + 60], 4 + pinsrw xmm3, word ptr [rsi + rdi + 60], 5 + pinsrw xmm3, word ptr [rsi + rbx + 60], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rsi + r8 + 60], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + por xmm6, xmm4 + movdqa xmm4, xmmword ptr [rip + .LCPI4_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movdqa xmm1, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm1, xmm15, xmm0 + movdqa xmm0, xmm3 + pblendvb xmm10, xmm15, xmm0 + por xmm1, xmm4 + movzx eax, word ptr [rsi + r15 + 62] + por xmm10, xmm1 + movd xmm0, eax + pinsrw xmm0, word ptr [rsi + rcx + 62], 1 + pinsrw xmm0, word ptr [rsi + r9 + 62], 2 + pinsrw xmm0, word ptr [rsi + r12 + 62], 3 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + pinsrw xmm0, word ptr [rsi + r13 + 62], 4 + pinsrw xmm0, word ptr [rsi + rdi + 62], 5 + pinsrw xmm0, word ptr [rsi + rbx + 62], 6 + pinsrw xmm0, word ptr [rsi + r8 + 62], 7 + pcmpeqw xmm0, xmm11 + packsswb xmm0, xmm0 + por xmm10, xmm6 + pblendvb xmm14, xmm15, xmm0 + por xmm14, xmm10 + movdqa xmm0, xmm12 + punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] + movdqa xmm2, xmm8 + punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] + movdqa xmm3, xmmword ptr [rip + .LCPI4_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> + pshufb xmm2, xmm3 + pshufb xmm0, xmm3 + punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] + punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] + punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] + punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx], xmm12 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm0 + add rcx, 8 + mov r15, rcx + cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + jne .LBB4_216 +# %bb.217: + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + mov r14, qword ptr [rsp + 144] # 8-byte Reload + mov r13d, dword ptr [rsp + 56] # 4-byte Reload + mov r12, qword ptr [rsp + 8] # 8-byte Reload + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + jne .LBB4_141 + jmp .LBB4_144 +.LBB4_218: + and rcx, -8 + mov rax, rcx + shl rax, 6 + add rax, rsi + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 40], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 8], rax # 8-byte Spill + mov dword ptr [rsp + 56], r13d # 4-byte Spill + movd xmm0, r13d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] + xor r15d, r15d + mov qword ptr [rsp + 120], r12 # 8-byte Spill + pxor xmm15, xmm15 .p2align 4, 0x90 -.LBB5_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload - cmp cl, byte ptr [r14] - lea r14, [r14 + 1] - setne bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [rdx + rsi] - xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [rdx + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_6 -# %bb.7: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_8: - sar r10, 5 - cmp r15, 32 - jl .LBB5_9 -# %bb.82: - cmp r10, 16 - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 264], r10 # 8-byte Spill - jb .LBB5_83 -# %bb.84: - mov rax, r10 +.LBB4_219: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill + shl r15, 6 + mov r9, r15 + mov r12, r15 + mov r13, r15 + mov rdi, r15 + mov rbx, r15 + mov r8, r15 + movzx eax, word ptr [rsi + r15] + movd xmm5, eax + movzx eax, word ptr [rsi + r15 + 2] + movd xmm0, eax + movzx eax, word ptr [rsi + r15 + 4] + movd xmm1, eax + movzx eax, word ptr [rsi + r15 + 6] + movd xmm7, eax + movzx eax, word ptr [rsi + r15 + 8] + movd xmm8, eax + movzx eax, word ptr [rsi + r15 + 10] + movd xmm4, eax + movzx eax, word ptr [rsi + r15 + 12] + movzx r10d, word ptr [rsi + r15 + 14] + movzx r11d, word ptr [rsi + r15 + 16] + movzx edx, word ptr [rsi + r15 + 18] + movzx r14d, word ptr [rsi + r15 + 20] + mov rcx, r15 + or rcx, 64 + or r9, 128 + or r12, 192 + or r13, 256 + or rdi, 320 + or rbx, 384 + pinsrw xmm5, word ptr [rsi + rcx], 1 + pinsrw xmm5, word ptr [rsi + r9], 2 + pinsrw xmm5, word ptr [rsi + r12], 3 + pinsrw xmm5, word ptr [rsi + r13], 4 + pinsrw xmm5, word ptr [rsi + rdi], 5 + pinsrw xmm5, word ptr [rsi + rbx], 6 + pinsrw xmm0, word ptr [rsi + rcx + 2], 1 + pinsrw xmm0, word ptr [rsi + r9 + 2], 2 + pinsrw xmm0, word ptr [rsi + r12 + 2], 3 + pinsrw xmm0, word ptr [rsi + r13 + 2], 4 + pinsrw xmm0, word ptr [rsi + rdi + 2], 5 + pinsrw xmm0, word ptr [rsi + rbx + 2], 6 + or r8, 448 + pinsrw xmm0, word ptr [rsi + r8 + 2], 7 + movd xmm2, eax + movzx eax, word ptr [rsi + r15 + 22] + mov dword ptr [rsp + 16], eax # 4-byte Spill + pcmpeqw xmm0, xmm11 + pinsrw xmm1, word ptr [rsi + rcx + 4], 1 + pinsrw xmm1, word ptr [rsi + r9 + 4], 2 + pinsrw xmm1, word ptr [rsi + r12 + 4], 3 + pinsrw xmm1, word ptr [rsi + r13 + 4], 4 + pinsrw xmm1, word ptr [rsi + rdi + 4], 5 + pinsrw xmm1, word ptr [rsi + rbx + 4], 6 + pinsrw xmm1, word ptr [rsi + r8 + 4], 7 + packsswb xmm0, xmm0 + pcmpeqw xmm1, xmm11 + movdqa xmm9, xmmword ptr [rip + .LCPI4_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm3, xmm9 + pblendvb xmm3, xmm15, xmm0 + packsswb xmm1, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm0 + movdqa xmm14, xmm0 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r10d + movzx r10d, word ptr [rsi + r15 + 24] + pinsrw xmm5, word ptr [rsi + r8], 7 + pcmpeqw xmm5, xmm11 + pcmpeqd xmm0, xmm0 + pxor xmm5, xmm0 + packsswb xmm5, xmm5 + pinsrw xmm7, word ptr [rsi + rcx + 6], 1 + pinsrw xmm7, word ptr [rsi + r9 + 6], 2 + pinsrw xmm7, word ptr [rsi + r12 + 6], 3 + pinsrw xmm7, word ptr [rsi + r13 + 6], 4 + pinsrw xmm7, word ptr [rsi + rdi + 6], 5 + pinsrw xmm7, word ptr [rsi + rbx + 6], 6 + pinsrw xmm7, word ptr [rsi + r8 + 6], 7 + pcmpeqw xmm7, xmm11 + packsswb xmm7, xmm7 + pinsrw xmm8, word ptr [rsi + rcx + 8], 1 + pinsrw xmm8, word ptr [rsi + r9 + 8], 2 + pinsrw xmm8, word ptr [rsi + r12 + 8], 3 + pinsrw xmm8, word ptr [rsi + r13 + 8], 4 + pinsrw xmm8, word ptr [rsi + rdi + 8], 5 + pinsrw xmm8, word ptr [rsi + rbx + 8], 6 + pinsrw xmm8, word ptr [rsi + r8 + 8], 7 + psubb xmm3, xmm5 + movdqa xmm12, xmmword ptr [rip + .LCPI4_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm7 + pblendvb xmm12, xmm15, xmm0 + movd xmm7, r11d + movzx eax, word ptr [rsi + r15 + 26] + pcmpeqw xmm8, xmm11 + packsswb xmm8, xmm8 + por xmm12, xmm6 + movdqa xmm13, xmmword ptr [rip + .LCPI4_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm8 + pblendvb xmm13, xmm15, xmm0 + movd xmm6, edx + movzx r11d, word ptr [rsi + r15 + 28] + pinsrw xmm4, word ptr [rsi + rcx + 10], 1 + pinsrw xmm4, word ptr [rsi + r9 + 10], 2 + pinsrw xmm4, word ptr [rsi + r12 + 10], 3 + pinsrw xmm4, word ptr [rsi + r13 + 10], 4 + pinsrw xmm4, word ptr [rsi + rdi + 10], 5 + pinsrw xmm4, word ptr [rsi + rbx + 10], 6 + pinsrw xmm4, word ptr [rsi + r8 + 10], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + pinsrw xmm2, word ptr [rsi + rcx + 12], 1 + pinsrw xmm2, word ptr [rsi + r9 + 12], 2 + pinsrw xmm2, word ptr [rsi + r12 + 12], 3 + pinsrw xmm2, word ptr [rsi + r13 + 12], 4 + pinsrw xmm2, word ptr [rsi + rdi + 12], 5 + pinsrw xmm2, word ptr [rsi + rbx + 12], 6 + por xmm12, xmm3 + movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, r14d + movzx edx, word ptr [rsi + r15 + 30] + mov dword ptr [rsp + 48], edx # 4-byte Spill + pinsrw xmm2, word ptr [rsi + r8 + 12], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm13 + movdqa xmm13, xmmword ptr [rip + .LCPI4_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx edx, word ptr [rsi + r15 + 32] + mov dword ptr [rsp + 32], edx # 4-byte Spill + pinsrw xmm1, word ptr [rsi + rcx + 14], 1 + pinsrw xmm1, word ptr [rsi + r9 + 14], 2 + pinsrw xmm1, word ptr [rsi + r12 + 14], 3 + pinsrw xmm1, word ptr [rsi + r13 + 14], 4 + pinsrw xmm1, word ptr [rsi + rdi + 14], 5 + pinsrw xmm1, word ptr [rsi + rbx + 14], 6 + por xmm13, xmm5 + movd xmm2, r10d + movzx edx, word ptr [rsi + r15 + 34] + mov dword ptr [rsp + 16], edx # 4-byte Spill + pinsrw xmm1, word ptr [rsi + r8 + 14], 7 + pcmpeqw xmm1, xmm11 + pinsrw xmm6, word ptr [rsi + rcx + 18], 1 + pinsrw xmm6, word ptr [rsi + r9 + 18], 2 + pinsrw xmm6, word ptr [rsi + r12 + 18], 3 + pinsrw xmm6, word ptr [rsi + r13 + 18], 4 + pinsrw xmm6, word ptr [rsi + rdi + 18], 5 + pinsrw xmm6, word ptr [rsi + rbx + 18], 6 + packsswb xmm1, xmm1 + pinsrw xmm6, word ptr [rsi + r8 + 18], 7 + pcmpeqw xmm6, xmm11 + packsswb xmm6, xmm6 + por xmm13, xmm12 + movdqa xmm12, xmmword ptr [rip + .LCPI4_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm12, xmm15, xmm0 + movdqa xmm8, xmm9 + movdqa xmm0, xmm6 + pblendvb xmm8, xmm15, xmm0 + movd xmm1, eax + movzx r14d, word ptr [rsi + r15 + 36] + pinsrw xmm7, word ptr [rsi + rcx + 16], 1 + pinsrw xmm7, word ptr [rsi + r9 + 16], 2 + pinsrw xmm7, word ptr [rsi + r12 + 16], 3 + pinsrw xmm7, word ptr [rsi + r13 + 16], 4 + pinsrw xmm7, word ptr [rsi + rdi + 16], 5 + pinsrw xmm7, word ptr [rsi + rbx + 16], 6 + pinsrw xmm4, word ptr [rsi + rcx + 20], 1 + pinsrw xmm4, word ptr [rsi + r9 + 20], 2 + pinsrw xmm4, word ptr [rsi + r12 + 20], 3 + pinsrw xmm4, word ptr [rsi + r13 + 20], 4 + pinsrw xmm4, word ptr [rsi + rdi + 20], 5 + pinsrw xmm4, word ptr [rsi + rbx + 20], 6 + pinsrw xmm4, word ptr [rsi + r8 + 20], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm12, xmm13 + movdqa xmm5, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, r11d + movzx r11d, word ptr [rsi + r15 + 38] + pinsrw xmm7, word ptr [rsi + r8 + 16], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI4_22] + packsswb xmm7, xmm7 + pinsrw xmm3, word ptr [rsi + rcx + 22], 1 + pinsrw xmm3, word ptr [rsi + r9 + 22], 2 + pinsrw xmm3, word ptr [rsi + r12 + 22], 3 + pinsrw xmm3, word ptr [rsi + r13 + 22], 4 + pinsrw xmm3, word ptr [rsi + rdi + 22], 5 + pinsrw xmm3, word ptr [rsi + rbx + 22], 6 + pinsrw xmm3, word ptr [rsi + r8 + 22], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rsi + rcx + 24], 1 + pinsrw xmm2, word ptr [rsi + r9 + 24], 2 + pinsrw xmm2, word ptr [rsi + r12 + 24], 3 + pinsrw xmm2, word ptr [rsi + r13 + 24], 4 + pinsrw xmm2, word ptr [rsi + rdi + 24], 5 + pinsrw xmm2, word ptr [rsi + rbx + 24], 6 + pinsrw xmm2, word ptr [rsi + r8 + 24], 7 + psubb xmm8, xmm7 + movdqa xmm10, xmmword ptr [rip + .LCPI4_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm14, xmm10 + movdqa xmm0, xmm3 + pblendvb xmm14, xmm15, xmm0 + movd xmm3, dword ptr [rsp + 48] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx eax, word ptr [rsi + r15 + 40] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm14, xmm5 + movdqa xmm9, xmmword ptr [rip + .LCPI4_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm7, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r10d, word ptr [rsi + r15 + 42] + pinsrw xmm1, word ptr [rsi + rcx + 26], 1 + pinsrw xmm1, word ptr [rsi + r9 + 26], 2 + pinsrw xmm1, word ptr [rsi + r12 + 26], 3 + pinsrw xmm1, word ptr [rsi + r13 + 26], 4 + pinsrw xmm1, word ptr [rsi + rdi + 26], 5 + pinsrw xmm1, word ptr [rsi + rbx + 26], 6 + pinsrw xmm1, word ptr [rsi + r8 + 26], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm4, word ptr [rsi + rcx + 28], 1 + pinsrw xmm4, word ptr [rsi + r9 + 28], 2 + pinsrw xmm4, word ptr [rsi + r12 + 28], 3 + pinsrw xmm4, word ptr [rsi + r13 + 28], 4 + pinsrw xmm4, word ptr [rsi + rdi + 28], 5 + pinsrw xmm4, word ptr [rsi + rbx + 28], 6 + por xmm14, xmm8 + movdqa xmm5, xmmword ptr [rip + .LCPI4_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm2, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm2 = mem[0],zero,zero,zero + movzx edx, word ptr [rsi + r15 + 44] + mov dword ptr [rsp + 32], edx # 4-byte Spill + pinsrw xmm4, word ptr [rsi + r8 + 28], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm5, xmm13 + movdqa xmm6, xmmword ptr [rip + .LCPI4_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, r14d + movzx edx, word ptr [rsi + r15 + 46] + mov dword ptr [rsp + 16], edx # 4-byte Spill + pinsrw xmm3, word ptr [rsi + rcx + 30], 1 + pinsrw xmm3, word ptr [rsi + r9 + 30], 2 + pinsrw xmm3, word ptr [rsi + r12 + 30], 3 + pinsrw xmm3, word ptr [rsi + r13 + 30], 4 + pinsrw xmm3, word ptr [rsi + rdi + 30], 5 + pinsrw xmm3, word ptr [rsi + rbx + 30], 6 + por xmm6, xmm5 + movd xmm1, r11d + movzx r11d, word ptr [rsi + r15 + 48] + pinsrw xmm3, word ptr [rsi + r8 + 30], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm2, word ptr [rsi + rcx + 34], 1 + pinsrw xmm2, word ptr [rsi + r9 + 34], 2 + pinsrw xmm2, word ptr [rsi + r12 + 34], 3 + pinsrw xmm2, word ptr [rsi + r13 + 34], 4 + pinsrw xmm2, word ptr [rsi + rdi + 34], 5 + pinsrw xmm2, word ptr [rsi + rbx + 34], 6 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rsi + r8 + 34], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm6, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI4_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm14 + movdqa xmm0, xmm3 + pblendvb xmm13, xmm15, xmm0 + movdqa xmm8, xmmword ptr [rip + .LCPI4_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm8, xmm15, xmm0 + movd xmm2, eax + movzx r14d, word ptr [rsi + r15 + 50] + pinsrw xmm7, word ptr [rsi + rcx + 32], 1 + pinsrw xmm7, word ptr [rsi + r9 + 32], 2 + pinsrw xmm7, word ptr [rsi + r12 + 32], 3 + pinsrw xmm7, word ptr [rsi + r13 + 32], 4 + pinsrw xmm7, word ptr [rsi + rdi + 32], 5 + pinsrw xmm7, word ptr [rsi + rbx + 32], 6 + pinsrw xmm4, word ptr [rsi + rcx + 36], 1 + pinsrw xmm4, word ptr [rsi + r9 + 36], 2 + pinsrw xmm4, word ptr [rsi + r12 + 36], 3 + pinsrw xmm4, word ptr [rsi + r13 + 36], 4 + pinsrw xmm4, word ptr [rsi + rdi + 36], 5 + pinsrw xmm4, word ptr [rsi + rbx + 36], 6 + pinsrw xmm4, word ptr [rsi + r8 + 36], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm13, xmm6 + movdqa xmm6, xmmword ptr [rip + .LCPI4_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm3, r10d + movzx edx, word ptr [rsi + r15 + 52] + pinsrw xmm7, word ptr [rsi + r8 + 32], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI4_22] + packsswb xmm7, xmm7 + pinsrw xmm1, word ptr [rsi + rcx + 38], 1 + pinsrw xmm1, word ptr [rsi + r9 + 38], 2 + pinsrw xmm1, word ptr [rsi + r12 + 38], 3 + pinsrw xmm1, word ptr [rsi + r13 + 38], 4 + pinsrw xmm1, word ptr [rsi + rdi + 38], 5 + pinsrw xmm1, word ptr [rsi + rbx + 38], 6 + pinsrw xmm1, word ptr [rsi + r8 + 38], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm2, word ptr [rsi + rcx + 40], 1 + pinsrw xmm2, word ptr [rsi + r9 + 40], 2 + pinsrw xmm2, word ptr [rsi + r12 + 40], 3 + pinsrw xmm2, word ptr [rsi + r13 + 40], 4 + pinsrw xmm2, word ptr [rsi + rdi + 40], 5 + pinsrw xmm2, word ptr [rsi + rbx + 40], 6 + pinsrw xmm2, word ptr [rsi + r8 + 40], 7 + psubb xmm8, xmm7 + movdqa xmm5, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx r10d, word ptr [rsi + r15 + 54] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm6 + movdqa xmm6, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx eax, word ptr [rsi + r15 + 56] + pinsrw xmm3, word ptr [rsi + rcx + 42], 1 + pinsrw xmm3, word ptr [rsi + r9 + 42], 2 + pinsrw xmm3, word ptr [rsi + r12 + 42], 3 + pinsrw xmm3, word ptr [rsi + r13 + 42], 4 + pinsrw xmm3, word ptr [rsi + rdi + 42], 5 + pinsrw xmm3, word ptr [rsi + rbx + 42], 6 + pinsrw xmm3, word ptr [rsi + r8 + 42], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rsi + rcx + 44], 1 + pinsrw xmm1, word ptr [rsi + r9 + 44], 2 + pinsrw xmm1, word ptr [rsi + r12 + 44], 3 + pinsrw xmm1, word ptr [rsi + r13 + 44], 4 + pinsrw xmm1, word ptr [rsi + rdi + 44], 5 + pinsrw xmm1, word ptr [rsi + rbx + 44], 6 + por xmm5, xmm8 + movdqa xmm9, xmmword ptr [rip + .LCPI4_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm2, xmm9 + movdqa xmm0, xmm3 + pblendvb xmm2, xmm15, xmm0 + movd xmm7, r11d + movzx r11d, word ptr [rsi + r15 + 58] + pinsrw xmm1, word ptr [rsi + r8 + 44], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm2, xmm6 + movdqa xmm10, xmmword ptr [rip + .LCPI4_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r14d + movzx r14d, word ptr [rsi + r15 + 60] + por xmm6, xmm2 + movd xmm2, edx + pinsrw xmm4, word ptr [rsi + rcx + 46], 1 + pinsrw xmm4, word ptr [rsi + r9 + 46], 2 + pinsrw xmm4, word ptr [rsi + r12 + 46], 3 + pinsrw xmm4, word ptr [rsi + r13 + 46], 4 + pinsrw xmm4, word ptr [rsi + rdi + 46], 5 + pinsrw xmm4, word ptr [rsi + rbx + 46], 6 + pinsrw xmm4, word ptr [rsi + r8 + 46], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm6, xmm5 + movdqa xmm8, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm8, xmm15, xmm0 + movd xmm3, r10d + pinsrw xmm1, word ptr [rsi + rcx + 50], 1 + pinsrw xmm1, word ptr [rsi + r9 + 50], 2 + pinsrw xmm1, word ptr [rsi + r12 + 50], 3 + pinsrw xmm1, word ptr [rsi + r13 + 50], 4 + pinsrw xmm1, word ptr [rsi + rdi + 50], 5 + pinsrw xmm1, word ptr [rsi + rbx + 50], 6 + pinsrw xmm1, word ptr [rsi + r8 + 50], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm8, xmm6 + movdqa xmm4, xmmword ptr [rip + .LCPI4_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movd xmm1, eax + pinsrw xmm7, word ptr [rsi + rcx + 48], 1 + pinsrw xmm7, word ptr [rsi + r9 + 48], 2 + pinsrw xmm7, word ptr [rsi + r12 + 48], 3 + pinsrw xmm7, word ptr [rsi + r13 + 48], 4 + pinsrw xmm7, word ptr [rsi + rdi + 48], 5 + pinsrw xmm7, word ptr [rsi + rbx + 48], 6 + pinsrw xmm7, word ptr [rsi + r8 + 48], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI4_22] + pinsrw xmm2, word ptr [rsi + rcx + 52], 1 + pinsrw xmm2, word ptr [rsi + r9 + 52], 2 + pinsrw xmm2, word ptr [rsi + r12 + 52], 3 + pinsrw xmm2, word ptr [rsi + r13 + 52], 4 + pinsrw xmm2, word ptr [rsi + rdi + 52], 5 + pinsrw xmm2, word ptr [rsi + rbx + 52], 6 + packsswb xmm7, xmm7 + pinsrw xmm2, word ptr [rsi + r8 + 52], 7 + pcmpeqw xmm2, xmm11 + pinsrw xmm3, word ptr [rsi + rcx + 54], 1 + pinsrw xmm3, word ptr [rsi + r9 + 54], 2 + pinsrw xmm3, word ptr [rsi + r12 + 54], 3 + pinsrw xmm3, word ptr [rsi + r13 + 54], 4 + pinsrw xmm3, word ptr [rsi + rdi + 54], 5 + pinsrw xmm3, word ptr [rsi + rbx + 54], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rsi + r8 + 54], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm1, word ptr [rsi + rcx + 56], 1 + pinsrw xmm1, word ptr [rsi + r9 + 56], 2 + pinsrw xmm1, word ptr [rsi + r12 + 56], 3 + pinsrw xmm1, word ptr [rsi + r13 + 56], 4 + pinsrw xmm1, word ptr [rsi + rdi + 56], 5 + pinsrw xmm1, word ptr [rsi + rbx + 56], 6 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rsi + r8 + 56], 7 + psubb xmm4, xmm7 + movdqa xmm5, xmmword ptr [rip + .LCPI4_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm5, xmm15, xmm0 + movdqa xmm6, xmmword ptr [rip + .LCPI4_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm3 + pblendvb xmm6, xmm15, xmm0 + movd xmm2, r11d + pcmpeqw xmm1, xmm11 + pinsrw xmm2, word ptr [rsi + rcx + 58], 1 + pinsrw xmm2, word ptr [rsi + r9 + 58], 2 + pinsrw xmm2, word ptr [rsi + r12 + 58], 3 + pinsrw xmm2, word ptr [rsi + r13 + 58], 4 + pinsrw xmm2, word ptr [rsi + rdi + 58], 5 + pinsrw xmm2, word ptr [rsi + rbx + 58], 6 + pinsrw xmm2, word ptr [rsi + r8 + 58], 7 + packsswb xmm1, xmm1 + pcmpeqw xmm2, xmm11 + por xmm6, xmm5 + movd xmm3, r14d + pinsrw xmm3, word ptr [rsi + rcx + 60], 1 + pinsrw xmm3, word ptr [rsi + r9 + 60], 2 + pinsrw xmm3, word ptr [rsi + r12 + 60], 3 + pinsrw xmm3, word ptr [rsi + r13 + 60], 4 + pinsrw xmm3, word ptr [rsi + rdi + 60], 5 + pinsrw xmm3, word ptr [rsi + rbx + 60], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rsi + r8 + 60], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + por xmm6, xmm4 + movdqa xmm4, xmmword ptr [rip + .LCPI4_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movdqa xmm1, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm1, xmm15, xmm0 + movdqa xmm0, xmm3 + pblendvb xmm10, xmm15, xmm0 + por xmm1, xmm4 + movzx eax, word ptr [rsi + r15 + 62] + por xmm10, xmm1 + movd xmm0, eax + pinsrw xmm0, word ptr [rsi + rcx + 62], 1 + pinsrw xmm0, word ptr [rsi + r9 + 62], 2 + pinsrw xmm0, word ptr [rsi + r12 + 62], 3 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + pinsrw xmm0, word ptr [rsi + r13 + 62], 4 + pinsrw xmm0, word ptr [rsi + rdi + 62], 5 + pinsrw xmm0, word ptr [rsi + rbx + 62], 6 + pinsrw xmm0, word ptr [rsi + r8 + 62], 7 + pcmpeqw xmm0, xmm11 + packsswb xmm0, xmm0 + por xmm10, xmm6 + pblendvb xmm14, xmm15, xmm0 + por xmm14, xmm10 + movdqa xmm0, xmm12 + punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] + movdqa xmm2, xmm8 + punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] + movdqa xmm3, xmmword ptr [rip + .LCPI4_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> + pshufb xmm2, xmm3 + pshufb xmm0, xmm3 + punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] + punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] + punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] + punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx], xmm12 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm0 + add rcx, 8 + mov r15, rcx + cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + jne .LBB4_219 +# %bb.220: + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + mov r14, qword ptr [rsp + 144] # 8-byte Reload + mov r13d, dword ptr [rsp + 56] # 4-byte Reload + mov r12, qword ptr [rsp + 8] # 8-byte Reload + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + jne .LBB4_155 + jmp .LBB4_158 +.LBB4_221: + and rcx, -16 + mov rax, rcx shl rax, 5 - add rax, r14 - cmp qword ptr [rsp + 8], rax # 8-byte Folded Reload - jae .LBB5_86 -# %bb.85: - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - cmp r14, rax - jae .LBB5_86 -.LBB5_83: + add rax, rdi + mov qword ptr [rsp + 272], rax # 8-byte Spill + mov qword ptr [rsp + 168], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 160], rax # 8-byte Spill + movzx eax, r15b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov rax, qword ptr [rsp + 8] # 8-byte Reload - mov qword ptr [rsp + 80], rax # 8-byte Spill -.LBB5_89: - sub r10, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 208], r10 # 8-byte Spill + mov qword ptr [rsp + 120], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB5_90: # =>This Inner Loop Header: Depth=1 - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - cmp al, byte ptr [r14 + 31] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 30] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 29] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 28] - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 27] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 26] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 25] - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 23] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 22] - setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 21] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 20] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 19] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 18] - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 17] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 15] - setne r10b - cmp al, byte ptr [r14 + 14] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 13] - setne r13b - cmp al, byte ptr [r14 + 12] - setne r12b - cmp al, byte ptr [r14 + 11] - setne r15b - cmp al, byte ptr [r14 + 10] - setne bl - cmp al, byte ptr [r14 + 9] - setne r11b - cmp al, byte ptr [r14 + 7] - setne sil - cmp al, byte ptr [r14 + 6] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 5] - setne r9b - cmp al, byte ptr [r14 + 4] - setne r8b - cmp al, byte ptr [r14 + 3] - setne dil - cmp al, byte ptr [r14 + 2] - setne dl - cmp al, byte ptr [r14] - setne byte ptr [rsp + 168] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 1] - setne cl - cmp al, byte ptr [r14 + 8] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 16] - setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 24] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - add cl, cl - add cl, byte ptr [rsp + 168] # 1-byte Folded Reload - shl dl, 2 - or dl, cl - shl dil, 3 - or dil, dl - shl r8b, 4 - or r8b, dil - shl r9b, 5 - or r9b, r8b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 6 - shl sil, 7 - or sil, al - or sil, r9b +.LBB4_222: # =>This Inner Loop Header: Depth=1 + mov r9, rax + mov qword ptr [rsp + 152], rax # 8-byte Spill + shl rax, 5 + mov r8, rax + mov rcx, rax + mov r15, rax + mov rsi, rax + mov r14, rax + mov r10, rax + mov r11, rax + mov qword ptr [rsp + 72], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov r13, rax + mov qword ptr [rsp + 80], rax # 8-byte Spill + mov rdx, rax + movzx eax, byte ptr [rdi + rax] + movd xmm4, eax + movzx eax, byte ptr [rdi + rdx + 1] + movd xmm3, eax + movzx eax, byte ptr [rdi + rdx + 2] + movd xmm5, eax + movzx eax, byte ptr [rdi + rdx + 3] + movd xmm7, eax + movzx eax, byte ptr [rdi + rdx + 4] + movd xmm9, eax + movzx eax, byte ptr [rdi + rdx + 5] + movd xmm2, eax + movzx eax, byte ptr [rdi + rdx + 6] + movd xmm8, eax + movzx eax, byte ptr [rdi + rdx + 7] + movd xmm14, eax + movzx eax, byte ptr [rdi + rdx + 8] + movd xmm0, eax + movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill + movzx eax, byte ptr [rdi + rdx + 9] + movd xmm11, eax + movzx eax, byte ptr [rdi + rdx + 10] + movd xmm12, eax + movzx eax, byte ptr [rdi + rdx + 11] + movd xmm13, eax + movzx eax, byte ptr [rdi + rdx + 12] + movd xmm0, eax + movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill + movzx eax, byte ptr [rdi + rdx + 13] + movd xmm6, eax + movzx eax, byte ptr [rdi + rdx + 14] + movd xmm15, eax + movzx eax, byte ptr [rdi + rdx + 15] + movd xmm0, eax + movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill + mov qword ptr [rsp + 104], rdx # 8-byte Spill + mov r12, rdx + or r12, 32 + mov qword ptr [rsp + 24], r12 # 8-byte Spill + or r8, 64 + mov qword ptr [rsp + 32], r8 # 8-byte Spill + or rcx, 96 + mov qword ptr [rsp + 96], rcx # 8-byte Spill + or r15, 128 + or rsi, 160 + or r14, 192 + or r10, 224 + or r11, 256 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + or r9, 288 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + or rbx, 320 + or r13, 352 + or qword ptr [rsp + 80], 384 # 8-byte Folded Spill + mov rax, rdx + or rax, 416 + mov qword ptr [rsp + 16], rax # 8-byte Spill + mov rax, rdx + or rax, 448 + mov qword ptr [rsp + 88], rax # 8-byte Spill + mov rax, rdx + or rdx, 480 + mov qword ptr [rsp + 64], rdx # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r12], 1 + pinsrb xmm4, byte ptr [rdi + r8], 2 + pinsrb xmm4, byte ptr [rdi + rcx], 3 + mov qword ptr [rsp + 112], r15 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r15], 4 + mov rax, rsi + pinsrb xmm4, byte ptr [rdi + rsi], 5 + mov qword ptr [rsp + 128], r14 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r14], 6 + pinsrb xmm4, byte ptr [rdi + r10], 7 + mov qword ptr [rsp + 224], r11 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r11], 8 + mov rcx, r9 + pinsrb xmm4, byte ptr [rdi + r9], 9 + mov qword ptr [rsp + 56], rbx # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + rbx], 10 + mov qword ptr [rsp + 40], r13 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r13], 11 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r12], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rsi], 13 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r9], 14 + pinsrb xmm4, byte ptr [rdi + rdx], 15 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 1], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r8 + 1], 2 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 1], 3 + pinsrb xmm3, byte ptr [rdi + r15 + 1], 4 + pinsrb xmm3, byte ptr [rdi + rax + 1], 5 + pinsrb xmm3, byte ptr [rdi + r14 + 1], 6 + pinsrb xmm3, byte ptr [rdi + r10 + 1], 7 + mov r15, r10 + pinsrb xmm3, byte ptr [rdi + r11 + 1], 8 + pinsrb xmm3, byte ptr [rdi + rcx + 1], 9 + mov r10, rcx + pinsrb xmm3, byte ptr [rdi + rbx + 1], 10 + pinsrb xmm3, byte ptr [rdi + r13 + 1], 11 + pinsrb xmm3, byte ptr [rdi + r12 + 1], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 1], 13 + pinsrb xmm3, byte ptr [rdi + r9 + 1], 14 + movdqa xmm1, xmmword ptr [rsp + 192] # 16-byte Reload + pcmpeqb xmm4, xmm1 + pinsrb xmm3, byte ptr [rdi + rdx + 1], 15 + pcmpeqb xmm3, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pandn xmm3, xmm0 + paddb xmm3, xmm4 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 16] + movd xmm10, edx + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rcx + 2], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r8 + 2], 2 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r13 + 2], 3 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r14 + 2], 4 + mov qword ptr [rsp + 48], rax # 8-byte Spill + pinsrb xmm5, byte ptr [rdi + rax + 2], 5 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r11 + 2], 6 + mov rbx, r15 + pinsrb xmm5, byte ptr [rdi + r15 + 2], 7 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rcx + 2], 8 + mov r9, r10 + mov qword ptr [rsp + 72], r10 # 8-byte Spill + pinsrb xmm5, byte ptr [rdi + r10 + 2], 9 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r10 + 2], 10 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r15 + 2], 11 + pinsrb xmm5, byte ptr [rdi + r12 + 2], 12 + pinsrb xmm5, byte ptr [rdi + rsi + 2], 13 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rdx + 2], 14 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rsi + 2], 15 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 3], 1 + pinsrb xmm7, byte ptr [rdi + r8 + 3], 2 + pinsrb xmm7, byte ptr [rdi + r13 + 3], 3 + pinsrb xmm7, byte ptr [rdi + r14 + 3], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 3], 5 + pinsrb xmm7, byte ptr [rdi + r11 + 3], 6 + pinsrb xmm7, byte ptr [rdi + rbx + 3], 7 + pinsrb xmm7, byte ptr [rdi + rcx + 3], 8 + pinsrb xmm7, byte ptr [rdi + r9 + 3], 9 + pinsrb xmm7, byte ptr [rdi + r10 + 3], 10 + pinsrb xmm7, byte ptr [rdi + r15 + 3], 11 + pinsrb xmm7, byte ptr [rdi + r12 + 3], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 3], 13 + pinsrb xmm7, byte ptr [rdi + rdx + 3], 14 + pinsrb xmm7, byte ptr [rdi + rsi + 3], 15 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 4], 1 + pinsrb xmm9, byte ptr [rdi + r8 + 4], 2 + pinsrb xmm9, byte ptr [rdi + r13 + 4], 3 + pinsrb xmm9, byte ptr [rdi + r14 + 4], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 4], 5 + pinsrb xmm9, byte ptr [rdi + r11 + 4], 6 + pinsrb xmm9, byte ptr [rdi + rbx + 4], 7 + pinsrb xmm9, byte ptr [rdi + rcx + 4], 8 + pinsrb xmm9, byte ptr [rdi + r9 + 4], 9 + pinsrb xmm9, byte ptr [rdi + r10 + 4], 10 + pinsrb xmm9, byte ptr [rdi + r15 + 4], 11 + pinsrb xmm9, byte ptr [rdi + r12 + 4], 12 + mov r9, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r9 + 4], 13 + pinsrb xmm9, byte ptr [rdi + rdx + 4], 14 + pinsrb xmm9, byte ptr [rdi + rsi + 4], 15 + pcmpeqb xmm5, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm5, xmm0 + pcmpeqb xmm7, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm7, xmm0 + por xmm7, xmm5 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + movzx edx, byte ptr [rdi + rsi + 17] + movd xmm4, edx + pcmpeqb xmm9, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI4_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm9, xmm0 + por xmm9, xmm7 + movzx edx, byte ptr [rdi + rsi + 18] + movd xmm7, edx + pcmpeqd xmm0, xmm0 + psubb xmm3, xmm0 + por xmm9, xmm3 + movzx edx, byte ptr [rdi + rsi + 19] + movd xmm5, edx + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rdx + 5], 1 + pinsrb xmm2, byte ptr [rdi + r8 + 5], 2 + pinsrb xmm2, byte ptr [rdi + r13 + 5], 3 + pinsrb xmm2, byte ptr [rdi + r14 + 5], 4 + pinsrb xmm2, byte ptr [rdi + rax + 5], 5 + pinsrb xmm2, byte ptr [rdi + r11 + 5], 6 + pinsrb xmm2, byte ptr [rdi + rbx + 5], 7 + pinsrb xmm2, byte ptr [rdi + rcx + 5], 8 + mov r11, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r11 + 5], 9 + pinsrb xmm2, byte ptr [rdi + r10 + 5], 10 + mov r15, r10 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rsi + 5], 11 + pinsrb xmm2, byte ptr [rdi + r12 + 5], 12 + mov rsi, r9 + pinsrb xmm2, byte ptr [rdi + r9 + 5], 13 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r9 + 5], 14 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r10 + 5], 15 + pinsrb xmm8, byte ptr [rdi + rdx + 6], 1 + pinsrb xmm8, byte ptr [rdi + r8 + 6], 2 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r13 + 6], 3 + pinsrb xmm8, byte ptr [rdi + r14 + 6], 4 + pinsrb xmm8, byte ptr [rdi + rax + 6], 5 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r13 + 6], 6 + pinsrb xmm8, byte ptr [rdi + rbx + 6], 7 + pinsrb xmm8, byte ptr [rdi + rcx + 6], 8 + pinsrb xmm8, byte ptr [rdi + r11 + 6], 9 + pinsrb xmm8, byte ptr [rdi + r15 + 6], 10 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r11 + 6], 11 + pinsrb xmm8, byte ptr [rdi + r12 + 6], 12 + pinsrb xmm8, byte ptr [rdi + rsi + 6], 13 + pinsrb xmm8, byte ptr [rdi + r9 + 6], 14 + pinsrb xmm8, byte ptr [rdi + r10 + 6], 15 + pinsrb xmm14, byte ptr [rdi + rdx + 7], 1 + pinsrb xmm14, byte ptr [rdi + r8 + 7], 2 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r15 + 7], 3 + pinsrb xmm14, byte ptr [rdi + r14 + 7], 4 + pinsrb xmm14, byte ptr [rdi + rax + 7], 5 + mov r8, r13 + pinsrb xmm14, byte ptr [rdi + r13 + 7], 6 + pinsrb xmm14, byte ptr [rdi + rbx + 7], 7 + pinsrb xmm14, byte ptr [rdi + rcx + 7], 8 + mov r14, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r14 + 7], 9 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r10 + 7], 10 + pinsrb xmm14, byte ptr [rdi + r11 + 7], 11 + pinsrb xmm14, byte ptr [rdi + r12 + 7], 12 + pinsrb xmm14, byte ptr [rdi + rsi + 7], 13 + pinsrb xmm14, byte ptr [rdi + r9 + 7], 14 + movdqa xmm1, xmm14 + movdqa xmm14, xmmword ptr [rsp + 192] # 16-byte Reload + pcmpeqb xmm2, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI4_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm0 + pcmpeqb xmm8, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI4_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm8, xmm0 + por xmm8, xmm2 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + movzx edx, byte ptr [rdi + r11 + 20] + movd xmm3, edx + mov r9, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + r9 + 7], 15 + pcmpeqb xmm1, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI4_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm1, xmm0 + por xmm1, xmm8 + movzx edx, byte ptr [rdi + r11 + 21] + movd xmm2, edx + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rsi + 8], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rcx + 8], 2 + pinsrb xmm0, byte ptr [rdi + r15 + 8], 3 + mov r13, r15 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rax + 8], 4 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 8], 5 + pinsrb xmm0, byte ptr [rdi + r8 + 8], 6 + pinsrb xmm0, byte ptr [rdi + rbx + 8], 7 + mov r12, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r12 + 8], 8 + mov r15, r14 + pinsrb xmm0, byte ptr [rdi + r14 + 8], 9 + pinsrb xmm0, byte ptr [rdi + r10 + 8], 10 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 8], 11 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 8], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rax + 8], 13 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r14 + 8], 14 + pinsrb xmm0, byte ptr [rdi + r9 + 8], 15 + por xmm1, xmm9 + movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + movzx edx, byte ptr [rdi + r11 + 22] + movd xmm1, edx + pcmpeqb xmm0, xmm14 + pinsrb xmm11, byte ptr [rdi + rsi + 9], 1 + pinsrb xmm11, byte ptr [rdi + rcx + 9], 2 + pinsrb xmm11, byte ptr [rdi + r13 + 9], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rax + 9], 4 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r8 + 9], 5 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r11 + 9], 6 + pinsrb xmm11, byte ptr [rdi + rbx + 9], 7 + mov rdx, r12 + pinsrb xmm11, byte ptr [rdi + r12 + 9], 8 + mov r9, r15 + pinsrb xmm11, byte ptr [rdi + r15 + 9], 9 + pinsrb xmm11, byte ptr [rdi + r10 + 9], 10 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r15 + 9], 11 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r12 + 9], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rsi + 9], 13 + pinsrb xmm11, byte ptr [rdi + r14 + 9], 14 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rcx + 9], 15 + mov r14, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + r14 + 10], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rax + 10], 2 + pinsrb xmm12, byte ptr [rdi + r13 + 10], 3 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rax + 10], 4 + pinsrb xmm12, byte ptr [rdi + r8 + 10], 5 + pinsrb xmm12, byte ptr [rdi + r11 + 10], 6 + pinsrb xmm12, byte ptr [rdi + rbx + 10], 7 + pinsrb xmm12, byte ptr [rdi + rdx + 10], 8 + pinsrb xmm12, byte ptr [rdi + r9 + 10], 9 + pinsrb xmm12, byte ptr [rdi + r10 + 10], 10 + pinsrb xmm12, byte ptr [rdi + r15 + 10], 11 + pinsrb xmm12, byte ptr [rdi + r12 + 10], 12 + mov rax, rsi + pinsrb xmm12, byte ptr [rdi + rsi + 10], 13 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + r14 + 10], 14 + pinsrb xmm12, byte ptr [rdi + rcx + 10], 15 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + rax + 11], 1 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + rsi + 11], 2 + pinsrb xmm13, byte ptr [rdi + r13 + 11], 3 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + rsi + 11], 4 + pinsrb xmm13, byte ptr [rdi + r8 + 11], 5 + pinsrb xmm13, byte ptr [rdi + r11 + 11], 6 + pinsrb xmm13, byte ptr [rdi + rbx + 11], 7 + pinsrb xmm13, byte ptr [rdi + rdx + 11], 8 + pinsrb xmm13, byte ptr [rdi + r9 + 11], 9 + pinsrb xmm13, byte ptr [rdi + r10 + 11], 10 + pinsrb xmm13, byte ptr [rdi + r15 + 11], 11 + pinsrb xmm13, byte ptr [rdi + r12 + 11], 12 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r13 + 11], 13 + pinsrb xmm13, byte ptr [rdi + r14 + 11], 14 + pinsrb xmm13, byte ptr [rdi + rcx + 11], 15 + pcmpeqb xmm11, xmm14 + pandn xmm11, xmmword ptr [rip + .LCPI4_16] + paddb xmm11, xmm0 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 23] + movd xmm8, edx + pcmpeqb xmm12, xmm14 + pandn xmm12, xmmword ptr [rip + .LCPI4_17] + pcmpeqb xmm13, xmm14 + pandn xmm13, xmmword ptr [rip + .LCPI4_18] + por xmm13, xmm12 + movzx edx, byte ptr [rdi + rcx + 24] + movd xmm12, edx + movdqa xmm9, xmmword ptr [rsp + 240] # 16-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 12], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r8 + 12], 2 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rcx + 12], 3 + mov r14, rsi + pinsrb xmm9, byte ptr [rdi + rsi + 12], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 12], 5 + mov rsi, r11 + pinsrb xmm9, byte ptr [rdi + r11 + 12], 6 + mov r11, rbx + pinsrb xmm9, byte ptr [rdi + rbx + 12], 7 + mov rbx, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rbx + 12], 8 + pinsrb xmm9, byte ptr [rdi + r9 + 12], 9 + pinsrb xmm9, byte ptr [rdi + r10 + 12], 10 + pinsrb xmm9, byte ptr [rdi + r15 + 12], 11 + pinsrb xmm9, byte ptr [rdi + r12 + 12], 12 + pinsrb xmm9, byte ptr [rdi + r13 + 12], 13 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rdx + 12], 14 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r13 + 12], 15 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 13], 1 + pinsrb xmm6, byte ptr [rdi + r8 + 13], 2 + pinsrb xmm6, byte ptr [rdi + rcx + 13], 3 + pinsrb xmm6, byte ptr [rdi + r14 + 13], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 13], 5 + pinsrb xmm6, byte ptr [rdi + rsi + 13], 6 + pinsrb xmm6, byte ptr [rdi + r11 + 13], 7 + pinsrb xmm6, byte ptr [rdi + rbx + 13], 8 + pinsrb xmm6, byte ptr [rdi + r9 + 13], 9 + pinsrb xmm6, byte ptr [rdi + r10 + 13], 10 + pinsrb xmm6, byte ptr [rdi + r15 + 13], 11 + pinsrb xmm6, byte ptr [rdi + r12 + 13], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 13], 13 + pinsrb xmm6, byte ptr [rdi + rdx + 13], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rax + 14], 1 + pinsrb xmm15, byte ptr [rdi + r8 + 14], 2 + pinsrb xmm15, byte ptr [rdi + rcx + 14], 3 + pinsrb xmm15, byte ptr [rdi + r14 + 14], 4 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rax + 14], 5 + pinsrb xmm15, byte ptr [rdi + rsi + 14], 6 + mov r13, rsi + pinsrb xmm15, byte ptr [rdi + r11 + 14], 7 + mov rcx, r11 + mov qword ptr [rsp + 136], r11 # 8-byte Spill + pinsrb xmm15, byte ptr [rdi + rbx + 14], 8 + mov r11, rbx + pinsrb xmm15, byte ptr [rdi + r9 + 14], 9 + pinsrb xmm15, byte ptr [rdi + r10 + 14], 10 + pinsrb xmm15, byte ptr [rdi + r15 + 14], 11 + pinsrb xmm15, byte ptr [rdi + r12 + 14], 12 + mov r9, r12 + mov qword ptr [rsp + 80], r12 # 8-byte Spill + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rsi + 14], 13 + pinsrb xmm15, byte ptr [rdi + rdx + 14], 14 + mov r15, rdx + pcmpeqb xmm9, xmm14 + pandn xmm9, xmmword ptr [rip + .LCPI4_19] + por xmm9, xmm13 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 25] + movd xmm13, edx + psubb xmm11, xmmword ptr [rip + .LCPI4_22] + por xmm9, xmm11 + movzx edx, byte ptr [rdi + rax + 26] + movd xmm0, edx + mov r12, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r12 + 14], 15 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmmword ptr [rip + .LCPI4_20] + pcmpeqb xmm15, xmm14 + pandn xmm15, xmmword ptr [rip + .LCPI4_21] + por xmm15, xmm6 + movzx edx, byte ptr [rdi + rax + 27] + movd xmm11, edx + movdqa xmm6, xmmword ptr [rsp + 208] # 16-byte Reload + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r8 + 15], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rdx + 15], 2 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rbx + 15], 3 + pinsrb xmm6, byte ptr [rdi + r14 + 15], 4 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r10 + 15], 5 + pinsrb xmm6, byte ptr [rdi + r13 + 15], 6 + pinsrb xmm6, byte ptr [rdi + rcx + 15], 7 + pinsrb xmm6, byte ptr [rdi + r11 + 15], 8 + mov r14, r11 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rcx + 15], 9 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rdx + 15], 10 + mov r11, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r11 + 15], 11 + pinsrb xmm6, byte ptr [rdi + r9 + 15], 12 + pinsrb xmm6, byte ptr [rdi + rsi + 15], 13 + pinsrb xmm6, byte ptr [rdi + r15 + 15], 14 + pinsrb xmm6, byte ptr [rdi + r12 + 15], 15 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmmword ptr [rip + .LCPI4_6] + por xmm6, xmm15 + movzx edx, byte ptr [rdi + rax + 28] + movd xmm15, edx + por xmm6, xmm9 + movdqa xmmword ptr [rsp + 208], xmm6 # 16-byte Spill + movzx edx, byte ptr [rdi + rax + 29] + movd xmm9, edx + mov rdx, r8 + pinsrb xmm10, byte ptr [rdi + r8 + 16], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r8 + 16], 2 + pinsrb xmm10, byte ptr [rdi + rbx + 16], 3 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r9 + 16], 4 + pinsrb xmm10, byte ptr [rdi + r10 + 16], 5 + pinsrb xmm10, byte ptr [rdi + r13 + 16], 6 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rax + 16], 7 + pinsrb xmm10, byte ptr [rdi + r14 + 16], 8 + pinsrb xmm10, byte ptr [rdi + rcx + 16], 9 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rcx + 16], 10 + pinsrb xmm10, byte ptr [rdi + r11 + 16], 11 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rsi + 16], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rax + 16], 13 + pinsrb xmm10, byte ptr [rdi + r15 + 16], 14 + pinsrb xmm10, byte ptr [rdi + r12 + 16], 15 + pinsrb xmm4, byte ptr [rdi + rdx + 17], 1 + pinsrb xmm4, byte ptr [rdi + r8 + 17], 2 + pinsrb xmm4, byte ptr [rdi + rbx + 17], 3 + mov r8, rbx + pinsrb xmm4, byte ptr [rdi + r9 + 17], 4 + pinsrb xmm4, byte ptr [rdi + r10 + 17], 5 + pinsrb xmm4, byte ptr [rdi + r13 + 17], 6 + mov r10, qword ptr [rsp + 136] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r10 + 17], 7 + mov rbx, r14 + pinsrb xmm4, byte ptr [rdi + r14 + 17], 8 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rdx + 17], 9 + pinsrb xmm4, byte ptr [rdi + rcx + 17], 10 + pinsrb xmm4, byte ptr [rdi + r11 + 17], 11 + pinsrb xmm4, byte ptr [rdi + rsi + 17], 12 + pinsrb xmm4, byte ptr [rdi + rax + 17], 13 + pinsrb xmm4, byte ptr [rdi + r15 + 17], 14 + mov rsi, r12 + pinsrb xmm4, byte ptr [rdi + r12 + 17], 15 + pcmpeqb xmm10, xmm14 + pcmpeqb xmm4, xmm14 + movdqa xmm6, xmmword ptr [rip + .LCPI4_16] # xmm6 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pandn xmm4, xmm6 + paddb xmm4, xmm10 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 30] + movd xmm10, edx + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 18], 1 + pinsrb xmm5, byte ptr [rdi + rax + 19], 1 + pinsrb xmm3, byte ptr [rdi + rax + 20], 1 + pinsrb xmm2, byte ptr [rdi + rax + 21], 1 + pinsrb xmm1, byte ptr [rdi + rax + 22], 1 + pinsrb xmm8, byte ptr [rdi + rax + 23], 1 + pinsrb xmm12, byte ptr [rdi + rax + 24], 1 + pinsrb xmm13, byte ptr [rdi + rax + 25], 1 + pinsrb xmm0, byte ptr [rdi + rax + 26], 1 + pinsrb xmm11, byte ptr [rdi + rax + 27], 1 + pinsrb xmm15, byte ptr [rdi + rax + 28], 1 + pinsrb xmm9, byte ptr [rdi + rax + 29], 1 + pinsrb xmm10, byte ptr [rdi + rax + 30], 1 + movzx edx, byte ptr [rdi + rcx + 31] + movd xmm6, edx + pinsrb xmm6, byte ptr [rdi + rax + 31], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rdx + 18], 2 + pinsrb xmm5, byte ptr [rdi + rdx + 19], 2 + pinsrb xmm3, byte ptr [rdi + rdx + 20], 2 + pinsrb xmm2, byte ptr [rdi + rdx + 21], 2 + pinsrb xmm1, byte ptr [rdi + rdx + 22], 2 + pinsrb xmm8, byte ptr [rdi + rdx + 23], 2 + pinsrb xmm12, byte ptr [rdi + rdx + 24], 2 + pinsrb xmm13, byte ptr [rdi + rdx + 25], 2 + pinsrb xmm0, byte ptr [rdi + rdx + 26], 2 + pinsrb xmm11, byte ptr [rdi + rdx + 27], 2 + pinsrb xmm15, byte ptr [rdi + rdx + 28], 2 + pinsrb xmm9, byte ptr [rdi + rdx + 29], 2 + pinsrb xmm10, byte ptr [rdi + rdx + 30], 2 + pinsrb xmm6, byte ptr [rdi + rdx + 31], 2 + mov rdx, r8 + pinsrb xmm7, byte ptr [rdi + r8 + 18], 3 + mov r14, r9 + pinsrb xmm7, byte ptr [rdi + r9 + 18], 4 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r8 + 18], 5 + pinsrb xmm7, byte ptr [rdi + r13 + 18], 6 + mov r11, r10 + pinsrb xmm7, byte ptr [rdi + r10 + 18], 7 + pinsrb xmm7, byte ptr [rdi + rbx + 18], 8 + mov r9, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r9 + 18], 9 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rcx + 18], 10 + mov r10, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r10 + 18], 11 mov rax, qword ptr [rsp + 80] # 8-byte Reload - mov byte ptr [rax], sil - add r11b, r11b - add r11b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 2 - or bl, r11b - shl r15b, 3 - or r15b, bl - shl r12b, 4 - or r12b, r15b - shl r13b, 5 - or r13b, r12b - movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl cl, 6 - shl r10b, 7 - or r10b, cl - or r10b, r13b - mov byte ptr [rax + 1], r10b - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 144] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl cl, 5 - or cl, dl - mov edx, ecx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl bl, 6 - movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl cl, 7 - or cl, bl - or cl, dl - mov byte ptr [rax + 2], cl - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 136] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload - shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload - shl cl, 5 - or cl, dl - mov edx, ecx - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 7 - or cl, bl - or cl, dl - mov byte ptr [rax + 3], cl - add r14, 32 - add rax, 4 - mov qword ptr [rsp + 80], rax # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB5_90 -# %bb.91: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 264] # 8-byte Reload - jmp .LBB5_92 -.LBB5_28: - cmp edi, 7 - je .LBB5_145 -# %bb.29: - cmp edi, 8 - jne .LBB5_198 -# %bb.30: - mov r11, qword ptr [rsi] - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 + pinsrb xmm7, byte ptr [rdi + rax + 18], 12 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r12 + 18], 13 + pinsrb xmm7, byte ptr [rdi + r15 + 18], 14 + pinsrb xmm7, byte ptr [rdi + rsi + 18], 15 + pinsrb xmm5, byte ptr [rdi + rdx + 19], 3 + pinsrb xmm5, byte ptr [rdi + r14 + 19], 4 + pinsrb xmm5, byte ptr [rdi + r8 + 19], 5 + pinsrb xmm5, byte ptr [rdi + r13 + 19], 6 + pinsrb xmm5, byte ptr [rdi + r11 + 19], 7 + pinsrb xmm5, byte ptr [rdi + rbx + 19], 8 + pinsrb xmm5, byte ptr [rdi + r9 + 19], 9 + pinsrb xmm5, byte ptr [rdi + rcx + 19], 10 + pinsrb xmm5, byte ptr [rdi + r10 + 19], 11 + pinsrb xmm5, byte ptr [rdi + rax + 19], 12 + pinsrb xmm5, byte ptr [rdi + r12 + 19], 13 + pinsrb xmm5, byte ptr [rdi + r15 + 19], 14 + pinsrb xmm5, byte ptr [rdi + rsi + 19], 15 + pinsrb xmm3, byte ptr [rdi + rdx + 20], 3 + pinsrb xmm3, byte ptr [rdi + r14 + 20], 4 + pinsrb xmm3, byte ptr [rdi + r8 + 20], 5 + pinsrb xmm3, byte ptr [rdi + r13 + 20], 6 + pinsrb xmm3, byte ptr [rdi + r11 + 20], 7 + pinsrb xmm3, byte ptr [rdi + rbx + 20], 8 + pinsrb xmm3, byte ptr [rdi + r9 + 20], 9 + pinsrb xmm3, byte ptr [rdi + rcx + 20], 10 + pinsrb xmm3, byte ptr [rdi + r10 + 20], 11 + pinsrb xmm3, byte ptr [rdi + rax + 20], 12 + pinsrb xmm3, byte ptr [rdi + r12 + 20], 13 + pinsrb xmm3, byte ptr [rdi + r15 + 20], 14 + pcmpeqb xmm7, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI4_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm7, xmm14 + pcmpeqb xmm5, xmmword ptr [rsp + 192] # 16-byte Folded Reload + movdqa xmm14, xmmword ptr [rip + .LCPI4_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm5, xmm14 + por xmm5, xmm7 + pinsrb xmm3, byte ptr [rdi + rsi + 20], 15 + movdqa xmm14, xmmword ptr [rsp + 192] # 16-byte Reload + pcmpeqb xmm3, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI4_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm3, xmm7 + por xmm3, xmm5 + pcmpeqd xmm5, xmm5 + psubb xmm4, xmm5 + por xmm3, xmm4 + pinsrb xmm2, byte ptr [rdi + rdx + 21], 3 + pinsrb xmm2, byte ptr [rdi + r14 + 21], 4 + pinsrb xmm2, byte ptr [rdi + r8 + 21], 5 + pinsrb xmm2, byte ptr [rdi + r13 + 21], 6 + pinsrb xmm2, byte ptr [rdi + r11 + 21], 7 + pinsrb xmm2, byte ptr [rdi + rbx + 21], 8 + pinsrb xmm2, byte ptr [rdi + r9 + 21], 9 + pinsrb xmm2, byte ptr [rdi + rcx + 21], 10 + pinsrb xmm2, byte ptr [rdi + r10 + 21], 11 + pinsrb xmm2, byte ptr [rdi + rax + 21], 12 + pinsrb xmm2, byte ptr [rdi + r12 + 21], 13 + pinsrb xmm2, byte ptr [rdi + r15 + 21], 14 + pinsrb xmm2, byte ptr [rdi + rsi + 21], 15 + pinsrb xmm1, byte ptr [rdi + rdx + 22], 3 + pinsrb xmm1, byte ptr [rdi + r14 + 22], 4 + pinsrb xmm1, byte ptr [rdi + r8 + 22], 5 + pinsrb xmm1, byte ptr [rdi + r13 + 22], 6 + pinsrb xmm1, byte ptr [rdi + r11 + 22], 7 + pinsrb xmm1, byte ptr [rdi + rbx + 22], 8 + pinsrb xmm1, byte ptr [rdi + r9 + 22], 9 + pinsrb xmm1, byte ptr [rdi + rcx + 22], 10 + pinsrb xmm1, byte ptr [rdi + r10 + 22], 11 + pinsrb xmm1, byte ptr [rdi + rax + 22], 12 + pinsrb xmm1, byte ptr [rdi + r12 + 22], 13 + pinsrb xmm1, byte ptr [rdi + r15 + 22], 14 + pinsrb xmm1, byte ptr [rdi + rsi + 22], 15 + pinsrb xmm8, byte ptr [rdi + rdx + 23], 3 + pinsrb xmm8, byte ptr [rdi + r14 + 23], 4 + pinsrb xmm8, byte ptr [rdi + r8 + 23], 5 + pinsrb xmm8, byte ptr [rdi + r13 + 23], 6 + pinsrb xmm8, byte ptr [rdi + r11 + 23], 7 + pinsrb xmm8, byte ptr [rdi + rbx + 23], 8 + pinsrb xmm8, byte ptr [rdi + r9 + 23], 9 + pinsrb xmm8, byte ptr [rdi + rcx + 23], 10 + pinsrb xmm8, byte ptr [rdi + r10 + 23], 11 + pinsrb xmm8, byte ptr [rdi + rax + 23], 12 + pinsrb xmm8, byte ptr [rdi + r12 + 23], 13 + pinsrb xmm8, byte ptr [rdi + r15 + 23], 14 + pcmpeqb xmm2, xmm14 + movdqa xmm5, xmmword ptr [rip + .LCPI4_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm5 + pcmpeqb xmm1, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI4_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm1, xmm7 + por xmm1, xmm2 + pinsrb xmm8, byte ptr [rdi + rsi + 23], 15 + pcmpeqb xmm8, xmm14 + movdqa xmm4, xmmword ptr [rip + .LCPI4_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm8, xmm4 + por xmm8, xmm1 + pinsrb xmm12, byte ptr [rdi + rdx + 24], 3 + pinsrb xmm12, byte ptr [rdi + r14 + 24], 4 + pinsrb xmm12, byte ptr [rdi + r8 + 24], 5 + pinsrb xmm12, byte ptr [rdi + r13 + 24], 6 + pinsrb xmm12, byte ptr [rdi + r11 + 24], 7 + pinsrb xmm12, byte ptr [rdi + rbx + 24], 8 + pinsrb xmm12, byte ptr [rdi + r9 + 24], 9 + pinsrb xmm12, byte ptr [rdi + rcx + 24], 10 + pinsrb xmm12, byte ptr [rdi + r10 + 24], 11 + pinsrb xmm12, byte ptr [rdi + rax + 24], 12 + pinsrb xmm12, byte ptr [rdi + r12 + 24], 13 + pinsrb xmm12, byte ptr [rdi + r15 + 24], 14 + pinsrb xmm12, byte ptr [rdi + rsi + 24], 15 + por xmm8, xmm3 + pcmpeqb xmm12, xmm14 + pinsrb xmm13, byte ptr [rdi + rdx + 25], 3 + pinsrb xmm13, byte ptr [rdi + r14 + 25], 4 + pinsrb xmm13, byte ptr [rdi + r8 + 25], 5 + pinsrb xmm13, byte ptr [rdi + r13 + 25], 6 + pinsrb xmm13, byte ptr [rdi + r11 + 25], 7 + pinsrb xmm13, byte ptr [rdi + rbx + 25], 8 + pinsrb xmm13, byte ptr [rdi + r9 + 25], 9 + pinsrb xmm13, byte ptr [rdi + rcx + 25], 10 + pinsrb xmm13, byte ptr [rdi + r10 + 25], 11 + pinsrb xmm13, byte ptr [rdi + rax + 25], 12 + pinsrb xmm13, byte ptr [rdi + r12 + 25], 13 + pinsrb xmm13, byte ptr [rdi + r15 + 25], 14 + pinsrb xmm13, byte ptr [rdi + rsi + 25], 15 + pinsrb xmm0, byte ptr [rdi + rdx + 26], 3 + pinsrb xmm0, byte ptr [rdi + r14 + 26], 4 + pinsrb xmm0, byte ptr [rdi + r8 + 26], 5 + pinsrb xmm0, byte ptr [rdi + r13 + 26], 6 + pinsrb xmm0, byte ptr [rdi + r11 + 26], 7 + pinsrb xmm0, byte ptr [rdi + rbx + 26], 8 + pinsrb xmm0, byte ptr [rdi + r9 + 26], 9 + pinsrb xmm0, byte ptr [rdi + rcx + 26], 10 + pinsrb xmm0, byte ptr [rdi + r10 + 26], 11 + pinsrb xmm0, byte ptr [rdi + rax + 26], 12 + pinsrb xmm0, byte ptr [rdi + r12 + 26], 13 + pinsrb xmm0, byte ptr [rdi + r15 + 26], 14 + pinsrb xmm0, byte ptr [rdi + rsi + 26], 15 + pinsrb xmm11, byte ptr [rdi + rdx + 27], 3 + pinsrb xmm11, byte ptr [rdi + r14 + 27], 4 + pinsrb xmm11, byte ptr [rdi + r8 + 27], 5 + pinsrb xmm11, byte ptr [rdi + r13 + 27], 6 + pinsrb xmm11, byte ptr [rdi + r11 + 27], 7 + pinsrb xmm11, byte ptr [rdi + rbx + 27], 8 + pinsrb xmm11, byte ptr [rdi + r9 + 27], 9 + pinsrb xmm11, byte ptr [rdi + rcx + 27], 10 + pinsrb xmm11, byte ptr [rdi + r10 + 27], 11 + pinsrb xmm11, byte ptr [rdi + rax + 27], 12 + pinsrb xmm11, byte ptr [rdi + r12 + 27], 13 + pinsrb xmm11, byte ptr [rdi + r15 + 27], 14 + pcmpeqb xmm13, xmm14 + pandn xmm13, xmmword ptr [rip + .LCPI4_16] + paddb xmm13, xmm12 + pinsrb xmm11, byte ptr [rdi + rsi + 27], 15 + mov r12, rsi + pcmpeqb xmm0, xmm14 + pandn xmm0, xmmword ptr [rip + .LCPI4_17] + pcmpeqb xmm11, xmm14 + pandn xmm11, xmmword ptr [rip + .LCPI4_18] + por xmm11, xmm0 + pinsrb xmm15, byte ptr [rdi + rdx + 28], 3 + pinsrb xmm9, byte ptr [rdi + rdx + 29], 3 + pinsrb xmm10, byte ptr [rdi + rdx + 30], 3 + pinsrb xmm6, byte ptr [rdi + rdx + 31], 3 + pinsrb xmm15, byte ptr [rdi + r14 + 28], 4 + pinsrb xmm9, byte ptr [rdi + r14 + 29], 4 + pinsrb xmm10, byte ptr [rdi + r14 + 30], 4 + pinsrb xmm6, byte ptr [rdi + r14 + 31], 4 + mov rdx, r8 + pinsrb xmm15, byte ptr [rdi + r8 + 28], 5 + pinsrb xmm9, byte ptr [rdi + r8 + 29], 5 + pinsrb xmm10, byte ptr [rdi + r8 + 30], 5 + pinsrb xmm6, byte ptr [rdi + r8 + 31], 5 + pinsrb xmm15, byte ptr [rdi + r13 + 28], 6 + pinsrb xmm9, byte ptr [rdi + r13 + 29], 6 + pinsrb xmm10, byte ptr [rdi + r13 + 30], 6 + pinsrb xmm6, byte ptr [rdi + r13 + 31], 6 + mov rdx, r11 + pinsrb xmm15, byte ptr [rdi + r11 + 28], 7 + pinsrb xmm9, byte ptr [rdi + r11 + 29], 7 + pinsrb xmm10, byte ptr [rdi + r11 + 30], 7 + pinsrb xmm6, byte ptr [rdi + r11 + 31], 7 + mov rsi, qword ptr [rsp + 120] # 8-byte Reload + mov rdx, rbx + pinsrb xmm15, byte ptr [rdi + rbx + 28], 8 + pinsrb xmm9, byte ptr [rdi + rbx + 29], 8 + pinsrb xmm10, byte ptr [rdi + rbx + 30], 8 + pinsrb xmm6, byte ptr [rdi + rbx + 31], 8 + mov rdx, r9 + pinsrb xmm15, byte ptr [rdi + r9 + 28], 9 + pinsrb xmm9, byte ptr [rdi + r9 + 29], 9 + pinsrb xmm10, byte ptr [rdi + r9 + 30], 9 + pinsrb xmm6, byte ptr [rdi + r9 + 31], 9 + pinsrb xmm15, byte ptr [rdi + rcx + 28], 10 + pinsrb xmm9, byte ptr [rdi + rcx + 29], 10 + pinsrb xmm10, byte ptr [rdi + rcx + 30], 10 + pinsrb xmm6, byte ptr [rdi + rcx + 31], 10 + mov rdx, r10 + pinsrb xmm15, byte ptr [rdi + r10 + 28], 11 + pinsrb xmm9, byte ptr [rdi + r10 + 29], 11 + pinsrb xmm10, byte ptr [rdi + r10 + 30], 11 + pinsrb xmm6, byte ptr [rdi + r10 + 31], 11 + pinsrb xmm15, byte ptr [rdi + rax + 28], 12 + pinsrb xmm9, byte ptr [rdi + rax + 29], 12 + pinsrb xmm10, byte ptr [rdi + rax + 30], 12 + pinsrb xmm6, byte ptr [rdi + rax + 31], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rax + 28], 13 + pinsrb xmm9, byte ptr [rdi + rax + 29], 13 + pinsrb xmm10, byte ptr [rdi + rax + 30], 13 + pinsrb xmm6, byte ptr [rdi + rax + 31], 13 + pinsrb xmm15, byte ptr [rdi + r15 + 28], 14 + pinsrb xmm9, byte ptr [rdi + r15 + 29], 14 + pinsrb xmm10, byte ptr [rdi + r15 + 30], 14 + pinsrb xmm6, byte ptr [rdi + r15 + 31], 14 + mov rax, r12 + pinsrb xmm15, byte ptr [rdi + r12 + 28], 15 + pinsrb xmm9, byte ptr [rdi + r12 + 29], 15 + pinsrb xmm10, byte ptr [rdi + r12 + 30], 15 + pcmpeqb xmm15, xmm14 + pandn xmm15, xmmword ptr [rip + .LCPI4_19] + por xmm15, xmm11 + pinsrb xmm6, byte ptr [rdi + r12 + 31], 15 + psubb xmm13, xmmword ptr [rip + .LCPI4_22] + por xmm15, xmm13 + pcmpeqb xmm9, xmm14 + pandn xmm9, xmm5 + pcmpeqb xmm10, xmm14 + pandn xmm10, xmm7 + por xmm10, xmm9 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmm4 + por xmm6, xmm10 + por xmm6, xmm15 + movdqa xmm0, xmm8 + punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] + movdqa xmm3, xmmword ptr [rsp + 176] # 16-byte Reload + movdqa xmm1, xmm3 + movdqa xmm4, xmmword ptr [rsp + 208] # 16-byte Reload + punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] + movdqa xmm2, xmm1 + punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] + punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] + punpckhbw xmm3, xmm4 # xmm3 = xmm3[8],xmm4[8],xmm3[9],xmm4[9],xmm3[10],xmm4[10],xmm3[11],xmm4[11],xmm3[12],xmm4[12],xmm3[13],xmm4[13],xmm3[14],xmm4[14],xmm3[15],xmm4[15] + movdqa xmm0, xmm3 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] + mov rcx, qword ptr [rsp + 152] # 8-byte Reload + movdqu xmmword ptr [rsi + 4*rcx + 48], xmm3 + movdqu xmmword ptr [rsi + 4*rcx + 32], xmm0 + movdqu xmmword ptr [rsi + 4*rcx + 16], xmm1 + movdqu xmmword ptr [rsi + 4*rcx], xmm2 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + jne .LBB4_222 +# %bb.223: + mov rcx, qword ptr [rsp + 264] # 8-byte Reload + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov r15b, byte ptr [rsp + 8] # 1-byte Reload + mov rsi, qword ptr [rsp + 272] # 8-byte Reload + mov r14, qword ptr [rsp + 144] # 8-byte Reload + jne .LBB4_168 + jmp .LBB4_172 +.Lfunc_end4: + .size comparison_not_equal_arr_scalar_sse4, .Lfunc_end4-comparison_not_equal_arr_scalar_sse4 + # -- End function + .section .rodata.cst16,"aM",@progbits,16 + .p2align 4 # -- Begin function comparison_not_equal_scalar_arr_sse4 +.LCPI5_0: + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_1: + .zero 16,252 +.LCPI5_2: + .zero 16,248 +.LCPI5_3: + .zero 16,240 +.LCPI5_4: + .zero 16,224 +.LCPI5_5: + .zero 16,192 +.LCPI5_6: + .zero 16,128 +.LCPI5_7: + .byte 0 # 0x0 + .byte 8 # 0x8 + .byte 1 # 0x1 + .byte 9 # 0x9 + .byte 2 # 0x2 + .byte 10 # 0xa + .byte 3 # 0x3 + .byte 11 # 0xb + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf +.LCPI5_8: + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .byte 2 # 0x2 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_9: + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .byte 4 # 0x4 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_10: + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .byte 8 # 0x8 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_11: + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .byte 16 # 0x10 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_12: + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .byte 32 # 0x20 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_13: + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .byte 64 # 0x40 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_14: + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .byte 128 # 0x80 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_15: + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI5_16: + .zero 16,2 +.LCPI5_17: + .zero 16,4 +.LCPI5_18: + .zero 16,8 +.LCPI5_19: + .zero 16,16 +.LCPI5_20: + .zero 16,32 +.LCPI5_21: + .zero 16,64 +.LCPI5_22: + .zero 16,255 + .text + .globl comparison_not_equal_scalar_arr_sse4 + .p2align 4, 0x90 + .type comparison_not_equal_scalar_arr_sse4,@function +comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 +# %bb.0: + push rbp + mov rbp, rsp + push r15 + push r14 + push r13 + push r12 + push rbx + and rsp, -16 + sub rsp, 272 + # kill: def $r9d killed $r9d def $r9 + mov r15, r8 + mov r12, rcx + cmp edi, 6 + jg .LBB5_19 +# %bb.1: + cmp edi, 3 + jle .LBB5_36 +# %bb.2: + cmp edi, 4 + je .LBB5_59 +# %bb.3: + cmp edi, 5 + je .LBB5_73 +# %bb.4: + cmp edi, 6 + jne .LBB5_200 +# %bb.5: + mov r8d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_34 -# %bb.31: - movsxd rax, r9d - mov r8, qword ptr [rsp + 8] # 8-byte Reload + je .LBB5_11 +# %bb.6: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB5_9 +# %bb.7: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_32: # =>This Inner Loop Header: Depth=1 - cmp r11, qword ptr [r14] - lea r14, [r14 + 8] - setne dl - neg dl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx ebx, byte ptr [r8 + rsi] - xor dl, bl - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB5_8: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] + setne bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, bl - mov byte ptr [r8 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_32 -# %bb.33: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_34: - sar r10, 5 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_8 +.LBB5_9: + sub r15, r14 + je .LBB5_200 +# %bb.10: + add r12, 1 +.LBB5_11: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - jl .LBB5_38 -# %bb.35: - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r10 # 8-byte Spill + jl .LBB5_15 +# %bb.12: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_36: # =>This Inner Loop Header: Depth=1 - cmp r11, qword ptr [r14 + 248] +.LBB5_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8d, dword ptr [rdx + 124] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 120] + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 116] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 112] setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 240] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 232] + cmp r8d, dword ptr [rdx + 108] setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 224] - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 216] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 208] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 200] + cmp r8d, dword ptr [rdx + 104] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 184] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 176] + cmp r8d, dword ptr [rdx + 100] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 92] setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 168] + cmp r8d, dword ptr [rdx + 88] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 84] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 80] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 76] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 72] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 160] + cmp r8d, dword ptr [rdx + 68] setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 152] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 144] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 136] - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 120] - setne r8b - cmp r11, qword ptr [r14 + 112] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 104] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 96] + cmp r8d, dword ptr [rdx + 60] setne dil - cmp r11, qword ptr [r14 + 88] + cmp r8d, dword ptr [rdx + 56] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] + setne r11b + cmp r8d, dword ptr [rdx + 44] setne r10b - cmp r11, qword ptr [r14 + 80] + cmp r8d, dword ptr [rdx + 40] setne r9b - cmp r11, qword ptr [r14 + 72] + cmp r8d, dword ptr [rdx + 36] setne sil - cmp r11, qword ptr [r14 + 56] + cmp r8d, dword ptr [rdx + 28] setne al - cmp r11, qword ptr [r14 + 48] + cmp r8d, dword ptr [rdx + 24] setne bl - cmp r11, qword ptr [r14 + 40] + cmp r8d, dword ptr [rdx + 20] setne cl - cmp r11, qword ptr [r14 + 32] - setne dl - cmp r11, qword ptr [r14 + 24] - setne r15b - cmp r11, qword ptr [r14 + 16] + cmp r8d, dword ptr [rdx + 16] setne r12b - cmp r11, qword ptr [r14] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 8] + cmp r8d, dword ptr [rdx + 12] setne r13b - cmp r11, qword ptr [r14 + 64] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 128] + cmp r8d, dword ptr [rdx + 8] + setne r15b + cmp r8d, dword ptr [rdx] + setne byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 4] + setne r14b + cmp r8d, dword ptr [rdx + 32] setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 192] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - add r13b, r13b - add r13b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r12b, 2 + cmp r8d, dword ptr [rdx + 64] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setne byte ptr [rsp + 120] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 + or r13b, r15b + shl r12b, 4 or r12b, r13b - mov r13, qword ptr [rsp + 8] # 8-byte Reload - shl r15b, 3 - or r15b, r12b - shl dl, 4 - or dl, r15b shl cl, 5 - or cl, dl + or cl, r12b + mov r12, qword ptr [rsp + 136] # 8-byte Reload shl bl, 6 shl al, 7 or al, bl or al, cl - mov byte ptr [r13], al + mov byte ptr [r12], al add sil, sil - add sil, byte ptr [rsp + 176] # 1-byte Folded Reload + add sil, byte ptr [rsp + 144] # 1-byte Folded Reload shl r9b, 2 or r9b, sil shl r10b, 3 or r10b, r9b - shl dil, 4 - or dil, r10b - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 5 - or al, dil - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + or al, r11b + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r13 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 192] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r13 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + mov byte ptr [r12 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 120] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r13 + 3], al - add r14, 256 - add r13, 4 - mov qword ptr [rsp + 8], r13 # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_36 -# %bb.37: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload -.LBB5_38: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.39: - mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - je .LBB5_40 -# %bb.157: - mov r9, r8 - and r9, -2 + mov byte ptr [r12 + 3], al + sub rdx, -128 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB5_13 +# %bb.14: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB5_15: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB5_200 +# %bb.16: + or rax, 1 + cmp r15, rax + je .LBB5_131 +# %bb.17: + mov r11, r9 + and r11, -2 xor edi, edi - mov r15, qword ptr [rsp + 8] # 8-byte Reload .p2align 4, 0x90 -.LBB5_158: # =>This Inner Loop Header: Depth=1 - cmp r11, qword ptr [r14] +.LBB5_18: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] setne al neg al mov rsi, rdi shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 - mov dl, 1 - shl dl, cl - xor al, r10b - and dl, al - xor dl, r10b - mov byte ptr [r15 + rsi], dl - add rdi, 2 - cmp r11, qword ptr [r14 + 8] - lea r14, [r14 + 16] - setne al - neg al - xor al, dl - or cl, 1 mov bl, 1 shl bl, cl + xor al, r10b and bl, al - xor bl, dl - mov byte ptr [r15 + rsi], bl - cmp r9, rdi - jne .LBB5_158 - jmp .LBB5_41 -.LBB5_57: - mov al, byte ptr [rsi] - mov byte ptr [rsp + 64], al # 1-byte Spill - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 + xor bl, r10b + mov byte ptr [r12 + rsi], bl + add rdi, 2 + cmp r8d, dword ptr [rdx + 4] + lea rdx, [rdx + 8] + setne r10b + neg r10b + xor r10b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r10b + xor al, bl + mov byte ptr [r12 + rsi], al + cmp r11, rdi + jne .LBB5_18 + jmp .LBB5_177 +.LBB5_19: + cmp edi, 8 + jle .LBB5_43 +# %bb.20: + cmp edi, 9 + je .LBB5_87 +# %bb.21: + cmp edi, 11 + je .LBB5_100 +# %bb.22: + cmp edi, 12 + jne .LBB5_200 +# %bb.23: + mov r14, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_61 -# %bb.58: - movsxd rax, r9d - mov rdx, qword ptr [rsp + 8] # 8-byte Reload + je .LBB5_29 +# %bb.24: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB5_27 +# %bb.25: + movsxd rsi, r9d + movq xmm0, r14 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload - cmp cl, byte ptr [r14] - lea r14, [r14 + 1] +.LBB5_26: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rcx] + lea rdx, [rcx + 8] + setp cl setne bl + or bl, cl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [rdx + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [rdx + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_59 -# %bb.60: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_61: - sar r10, 5 + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_26 +.LBB5_27: + sub r15, r8 + je .LBB5_200 +# %bb.28: + add r12, 1 +.LBB5_29: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - jl .LBB5_62 -# %bb.63: - cmp r10, 16 - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 264], r10 # 8-byte Spill - jb .LBB5_64 -# %bb.65: - mov rax, r10 - shl rax, 5 - add rax, r14 - cmp qword ptr [rsp + 8], rax # 8-byte Folded Reload - jae .LBB5_67 -# %bb.66: - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - cmp r14, rax - jae .LBB5_67 -.LBB5_64: - xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov rax, qword ptr [rsp + 8] # 8-byte Reload - mov qword ptr [rsp + 104], rax # 8-byte Spill -.LBB5_70: - sub r10, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 208], r10 # 8-byte Spill + jl .LBB5_33 +# %bb.30: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 240], r14 # 8-byte Spill + movq xmm0, r14 + mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 168], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_71: # =>This Inner Loop Header: Depth=1 - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - cmp al, byte ptr [r14 + 31] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 30] - setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 29] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 28] - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 27] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 26] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 25] - setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 23] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 22] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 21] - setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 20] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 19] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 18] - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 17] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 15] - setne r10b - cmp al, byte ptr [r14 + 14] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 13] +.LBB5_31: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + ucomisd xmm0, qword ptr [rdx] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 48], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 8] + setp al setne r13b - cmp al, byte ptr [r14 + 12] + or r13b, al + ucomisd xmm0, qword ptr [rdx + 16] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 32], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 24] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 24], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 32] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 16], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 40] + setp al setne r12b - cmp al, byte ptr [r14 + 11] - setne r15b - cmp al, byte ptr [r14 + 10] + or r12b, al + ucomisd xmm0, qword ptr [rdx + 48] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 72], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 56] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 12], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 64] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 56], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 72] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 64], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 80] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 88], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 88] + setp al setne bl - cmp al, byte ptr [r14 + 9] + or bl, al + ucomisd xmm0, qword ptr [rdx + 96] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 40], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 104] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 112], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 112] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 104], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 120] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 96], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 128] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 80], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 136] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 120], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 144] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 128], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 152] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 176], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 160] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 192], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 168] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 160], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 176] + setp al + setne r15b + or r15b, al + ucomisd xmm0, qword ptr [rdx + 184] + setp al + setne r8b + or r8b, al + ucomisd xmm0, qword ptr [rdx + 192] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 144], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 200] + setp al setne r11b - cmp al, byte ptr [r14 + 7] - setne sil - cmp al, byte ptr [r14 + 6] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 5] + or r11b, al + ucomisd xmm0, qword ptr [rdx + 208] + setp al + setne r10b + or r10b, al + ucomisd xmm0, qword ptr [rdx + 216] + setp al setne r9b - cmp al, byte ptr [r14 + 4] - setne r8b - cmp al, byte ptr [r14 + 3] - setne dil - cmp al, byte ptr [r14 + 2] - setne dl - cmp al, byte ptr [r14] - setne byte ptr [rsp + 168] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 1] + or r9b, al + ucomisd xmm0, qword ptr [rdx + 224] + setp al setne cl - cmp al, byte ptr [r14 + 8] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 16] - setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp al, byte ptr [r14 + 24] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - add cl, cl - add cl, byte ptr [rsp + 168] # 1-byte Folded Reload - shl dl, 2 - or dl, cl - shl dil, 3 - or dil, dl - shl r8b, 4 - or r8b, dil - shl r9b, 5 - or r9b, r8b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 6 - shl sil, 7 + or cl, al + mov byte ptr [rsp + 208], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 232] + setp al + setne cl + or cl, al + mov byte ptr [rsp + 224], cl # 1-byte Spill + ucomisd xmm0, qword ptr [rdx + 240] + setp al + setne dil + or dil, al + ucomisd xmm0, qword ptr [rdx + 248] + setp al + setne sil or sil, al - or sil, r9b - mov rax, qword ptr [rsp + 104] # 8-byte Reload - mov byte ptr [rax], sil - add r11b, r11b - add r11b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 2 - or bl, r11b - shl r15b, 3 - or r15b, bl - shl r12b, 4 - or r12b, r15b - shl r13b, 5 + add r13b, r13b + add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload + mov eax, r13d + shl r12b, 5 + movzx r13d, byte ptr [rsp + 72] # 1-byte Folded Reload + shl r13b, 6 or r13b, r12b - movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload - shl cl, 6 - shl r10b, 7 - or r10b, cl - or r10b, r13b - mov byte ptr [rax + 1], r10b + movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + shl al, 7 + or al, r13b + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 3 + or al, r12b + shl bl, 3 + or bl, cl + movzx r13d, byte ptr [rsp + 16] # 1-byte Folded Reload + shl r13b, 4 + or r13b, al + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov byte ptr [rsp + 40], al # 1-byte Spill movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 144] # 1-byte Folded Reload - mov edx, ecx + shl cl, 5 + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 6 + or al, cl + mov ecx, eax + movzx r14d, byte ptr [rsp + 96] # 1-byte Folded Reload + shl r14b, 7 + or r14b, al movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 2 + or bl, cl + mov r12, qword ptr [rsp + 136] # 8-byte Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + or cl, bl + mov ebx, ecx + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl cl, 5 - or cl, dl - mov edx, ecx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 6 - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl cl, 7 or cl, bl - or cl, dl - mov byte ptr [rax + 2], cl - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 136] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + or al, r13b + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl bl, 5 + shl r15b, 6 + or r15b, bl + or r14b, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r8b, 7 + or r8b, r15b + or r8b, cl + add r11b, r11b + add r11b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r10b, 2 + or r10b, r11b + shl r9b, 3 + or r9b, r10b + movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + or cl, r9b + mov ebx, ecx + mov byte ptr [r12], al + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 5 - or cl, dl - mov edx, ecx - movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload - shl bl, 6 - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 7 - or cl, bl - or cl, dl - mov byte ptr [rax + 3], cl - add r14, 32 - add rax, 4 - mov qword ptr [rsp + 104], rax # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB5_71 -# %bb.72: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 264] # 8-byte Reload - jmp .LBB5_73 -.LBB5_145: - mov r11d, dword ptr [rsi] - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 + shl dil, 6 + or dil, cl + mov byte ptr [r12 + 1], r14b + shl sil, 7 + or sil, dil + or sil, bl + mov byte ptr [r12 + 2], r8b + mov byte ptr [r12 + 3], sil + add rdx, 256 + add r12, 4 + add qword ptr [rsp + 168], -1 # 8-byte Folded Spill + jne .LBB5_31 +# %bb.32: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14, qword ptr [rsp + 240] # 8-byte Reload + mov rax, qword ptr [rsp + 248] # 8-byte Reload +.LBB5_33: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB5_200 +# %bb.34: + movq xmm0, r14 + or rax, 1 + cmp r15, rax + jne .LBB5_186 +# %bb.35: + xor edi, edi + jmp .LBB5_188 +.LBB5_36: + cmp edi, 2 + je .LBB5_114 +# %bb.37: + cmp edi, 3 + jne .LBB5_200 +# %bb.38: + mov r14b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_149 -# %bb.146: - movsxd rax, r9d - mov r8, qword ptr [rsp + 8] # 8-byte Reload + je .LBB5_132 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB5_147 +# %bb.40: + movsxd rsi, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB5_147: # =>This Inner Loop Header: Depth=1 - cmp r11d, dword ptr [r14] - lea r14, [r14 + 4] +.LBB5_41: # =>This Inner Loop Header: Depth=1 + lea r13, [rdx + 1] + cmp r14b, byte ptr [rdx] setne dl neg dl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx ebx, byte ptr [r8 + rsi] - xor dl, bl - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov rdi, r12 + movzx r9d, byte ptr [r12 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, bl - mov byte ptr [r8 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_147 -# %bb.148: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_149: - sar r10, 5 + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r12 + rbx], al + add rsi, 1 + mov rdx, r13 + add r11, -1 + jne .LBB5_41 +# %bb.42: + sub r15, r8 + jne .LBB5_148 + jmp .LBB5_200 +.LBB5_43: + cmp edi, 7 + je .LBB5_119 +# %bb.44: + cmp edi, 8 + jne .LBB5_200 +# %bb.45: + mov r8, qword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB5_51 +# %bb.46: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB5_49 +# %bb.47: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx + .p2align 4, 0x90 +.LBB5_48: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] + setne bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_48 +.LBB5_49: + sub r15, r14 + je .LBB5_200 +# %bb.50: + add r12, 1 +.LBB5_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - jl .LBB5_153 -# %bb.150: - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r10 # 8-byte Spill + jl .LBB5_55 +# %bb.52: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_151: # =>This Inner Loop Header: Depth=1 - cmp r11d, dword ptr [r14 + 124] +.LBB5_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8, qword ptr [rdx + 248] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 240] + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 232] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 224] setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 120] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 116] + cmp r8, qword ptr [rdx + 216] setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 112] - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 108] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 104] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 100] + cmp r8, qword ptr [rdx + 208] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 92] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 88] + cmp r8, qword ptr [rdx + 200] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 184] setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 84] + cmp r8, qword ptr [rdx + 176] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 168] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 160] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 152] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 144] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 80] + cmp r8, qword ptr [rdx + 136] setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 76] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 72] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 68] - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 60] - setne r8b - cmp r11d, dword ptr [r14 + 56] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 52] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 48] + cmp r8, qword ptr [rdx + 120] setne dil - cmp r11d, dword ptr [r14 + 44] + cmp r8, qword ptr [rdx + 112] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 104] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 96] + setne r11b + cmp r8, qword ptr [rdx + 88] setne r10b - cmp r11d, dword ptr [r14 + 40] + cmp r8, qword ptr [rdx + 80] setne r9b - cmp r11d, dword ptr [r14 + 36] + cmp r8, qword ptr [rdx + 72] setne sil - cmp r11d, dword ptr [r14 + 28] + cmp r8, qword ptr [rdx + 56] setne al - cmp r11d, dword ptr [r14 + 24] + cmp r8, qword ptr [rdx + 48] setne bl - cmp r11d, dword ptr [r14 + 20] + cmp r8, qword ptr [rdx + 40] setne cl - cmp r11d, dword ptr [r14 + 16] - setne dl - cmp r11d, dword ptr [r14 + 12] - setne r15b - cmp r11d, dword ptr [r14 + 8] + cmp r8, qword ptr [rdx + 32] setne r12b - cmp r11d, dword ptr [r14] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 4] + cmp r8, qword ptr [rdx + 24] setne r13b - cmp r11d, dword ptr [r14 + 32] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 64] + cmp r8, qword ptr [rdx + 16] + setne r15b + cmp r8, qword ptr [rdx] + setne byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 8] + setne r14b + cmp r8, qword ptr [rdx + 64] setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r11d, dword ptr [r14 + 96] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - add r13b, r13b - add r13b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r12b, 2 + cmp r8, qword ptr [rdx + 128] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setne byte ptr [rsp + 120] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 + or r13b, r15b + shl r12b, 4 or r12b, r13b - mov r13, qword ptr [rsp + 8] # 8-byte Reload - shl r15b, 3 - or r15b, r12b - shl dl, 4 - or dl, r15b shl cl, 5 - or cl, dl + or cl, r12b + mov r12, qword ptr [rsp + 136] # 8-byte Reload shl bl, 6 shl al, 7 or al, bl or al, cl - mov byte ptr [r13], al + mov byte ptr [r12], al add sil, sil - add sil, byte ptr [rsp + 176] # 1-byte Folded Reload + add sil, byte ptr [rsp + 144] # 1-byte Folded Reload shl r9b, 2 or r9b, sil shl r10b, 3 or r10b, r9b - shl dil, 4 - or dil, r10b - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 5 - or al, dil - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + or al, r11b + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r13 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 192] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r13 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + mov byte ptr [r12 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 120] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r13 + 3], al - sub r14, -128 - add r13, 4 - mov qword ptr [rsp + 8], r13 # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_151 -# %bb.152: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload -.LBB5_153: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.154: - mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - jne .LBB5_155 -.LBB5_23: + mov byte ptr [r12 + 3], al + add rdx, 256 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB5_53 +# %bb.54: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB5_55: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB5_200 +# %bb.56: + or rax, 1 + cmp r15, rax + je .LBB5_99 +# %bb.57: + mov r11, r9 + and r11, -2 xor edi, edi - jmp .LBB5_24 -.LBB5_100: - movzx r11d, word ptr [rsi] - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 + .p2align 4, 0x90 +.LBB5_58: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] + setne al + neg al + mov rsi, rdi + shr rsi, 3 + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] + mov ecx, edi + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r10b + and bl, al + xor bl, r10b + mov byte ptr [r12 + rsi], bl + add rdi, 2 + cmp r8, qword ptr [rdx + 8] + lea rdx, [rdx + 16] + setne r10b + neg r10b + xor r10b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r10b + xor al, bl + mov byte ptr [r12 + rsi], al + cmp r11, rdi + jne .LBB5_58 + jmp .LBB5_192 +.LBB5_59: + movzx r14d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_104 -# %bb.101: - movsxd rax, r9d - mov rdx, qword ptr [rsp + 8] # 8-byte Reload + je .LBB5_65 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB5_63 +# %bb.61: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_102: # =>This Inner Loop Header: Depth=1 - cmp r11w, word ptr [r14] - lea r14, [r14 + 2] +.LBB5_62: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r14w, word ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [rdx + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [rdx + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_102 -# %bb.103: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_104: - sar r10, 5 + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_62 +.LBB5_63: + sub r15, r8 + je .LBB5_200 +# %bb.64: + add r12, 1 +.LBB5_65: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 cmp r15, 32 - jl .LBB5_105 -# %bb.106: - cmp r10, 8 - mov dword ptr [rsp + 16], r11d # 4-byte Spill - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - jb .LBB5_107 -# %bb.108: - mov rax, r10 + jl .LBB5_133 +# %bb.66: + cmp rcx, 8 + mov dword ptr [rsp + 12], r14d # 4-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rcx # 8-byte Spill + jb .LBB5_69 +# %bb.67: + mov rax, rcx shl rax, 6 - add rax, r14 - cmp qword ptr [rsp + 8], rax # 8-byte Folded Reload - jae .LBB5_110 -# %bb.109: - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - cmp rax, r14 - jbe .LBB5_110 -.LBB5_107: + add rax, rdx + cmp r12, rax + jae .LBB5_205 +# %bb.68: + lea rax, [r12 + 4*rcx] + cmp rax, rdx + jbe .LBB5_205 +.LBB5_69: xor eax, eax - mov qword ptr [rsp + 40], rax # 8-byte Spill - mov r12, qword ptr [rsp + 8] # 8-byte Reload -.LBB5_113: - sub r10, qword ptr [rsp + 40] # 8-byte Folded Reload - mov qword ptr [rsp + 168], r10 # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r13, r12 +.LBB5_70: + sub rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov qword ptr [rsp + 208], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB5_114: # =>This Inner Loop Header: Depth=1 - cmp r11w, word ptr [r14 + 62] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 60] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 58] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 56] +.LBB5_71: # =>This Inner Loop Header: Depth=1 + cmp r14w, word ptr [rdx + 62] + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 60] setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 54] + cmp r14w, word ptr [rdx + 58] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 52] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 50] + cmp r14w, word ptr [rdx + 56] + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 54] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 52] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 46] + cmp r14w, word ptr [rdx + 50] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 46] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 44] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 42] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 40] setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 44] + cmp r14w, word ptr [rdx + 38] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 36] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 42] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 40] + cmp r14w, word ptr [rdx + 34] setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 38] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 36] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 34] + cmp r14w, word ptr [rdx + 30] + setne r10b + cmp r14w, word ptr [rdx + 28] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 26] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 30] - setne r9b - cmp r11w, word ptr [r14 + 28] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 26] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 24] - setne r13b - cmp r11w, word ptr [r14 + 22] + cmp r14w, word ptr [rdx + 24] + setne r12b + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 22] setne r15b - cmp r11w, word ptr [r14 + 20] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 20] + setne r14b + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 18] setne r11b - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 18] - setne r10b - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 14] - setne dl - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 12] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 14] + setne sil + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 12] setne byte ptr [rsp + 144] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 10] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 10] + setne r9b + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 8] setne r8b - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 8] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 6] setne dil - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 6] - setne sil - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 4] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 4] setne cl - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 2] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx] + setne byte ptr [rsp + 224] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 2] setne al - mov rbx, r12 - mov r12d, dword ptr [rsp + 16] # 4-byte Reload - cmp r12w, word ptr [r14 + 16] - mov r12, rbx - setne byte ptr [rsp + 176] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 16] # 4-byte Reload - cmp bx, word ptr [r14 + 32] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 16] # 4-byte Reload - cmp bx, word ptr [r14 + 48] - setne bl + mov rbx, r13 + mov r13d, dword ptr [rsp + 12] # 4-byte Reload + cmp r13w, word ptr [rdx + 16] + mov r13, rbx + setne byte ptr [rsp + 160] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 12] # 4-byte Reload + cmp bx, word ptr [rdx + 32] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 12] # 4-byte Reload + cmp bx, word ptr [rdx + 48] + setne byte ptr [rsp + 128] # 1-byte Folded Spill add al, al - add al, byte ptr [rsp + 192] # 1-byte Folded Reload + add al, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 2 or cl, al - shl sil, 3 - or sil, cl - shl dil, 4 - or dil, sil - shl r8b, 5 + shl dil, 3 + or dil, cl + shl r8b, 4 or r8b, dil + shl r9b, 5 + or r9b, r8b movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 6 - shl dl, 7 - or dl, al - or dl, r8b - mov byte ptr [r12], dl - add r10b, r10b - add r10b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r10b + shl sil, 7 + or sil, al + or sil, r9b + mov byte ptr [r13], sil + add r11b, r11b + add r11b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r11b shl r15b, 3 - or r15b, r11b - mov r11d, dword ptr [rsp + 16] # 4-byte Reload - shl r13b, 4 - or r13b, r15b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 - or al, r13b - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + or al, r12b + mov r14d, dword ptr [rsp + 12] # 4-byte Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 6 - shl r9b, 7 - or r9b, cl - or r9b, al - mov byte ptr [r12 + 1], r9b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl r10b, 7 + or r10b, cl + or r10b, al + mov byte ptr [r13 + 1], r10b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 152] # 1-byte Folded Reload + add al, byte ptr [rsp + 192] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, cl - mov ecx, eax - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + mov ecx, eax + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r12 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + mov byte ptr [r13 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - or al, bl + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r12 + 3], al - add r14, 64 - add r12, 4 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_114 -# %bb.115: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload - jmp .LBB5_116 -.LBB5_123: - movzx r11d, word ptr [rsi] - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 + mov byte ptr [r13 + 3], al + add rdx, 64 + add r13, 4 + add qword ptr [rsp + 208], -1 # 8-byte Folded Spill + jne .LBB5_71 +# %bb.72: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + jmp .LBB5_134 +.LBB5_73: + movzx r14d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_127 -# %bb.124: - movsxd rax, r9d - mov rdx, qword ptr [rsp + 8] # 8-byte Reload + je .LBB5_79 +# %bb.74: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB5_77 +# %bb.75: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_125: # =>This Inner Loop Header: Depth=1 - cmp r11w, word ptr [r14] - lea r14, [r14 + 2] +.LBB5_76: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r14w, word ptr [rcx] setne bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [rdx + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [rdx + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_125 -# %bb.126: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_127: - sar r10, 5 + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_76 +.LBB5_77: + sub r15, r8 + je .LBB5_200 +# %bb.78: + add r12, 1 +.LBB5_79: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 cmp r15, 32 - jl .LBB5_128 -# %bb.129: - cmp r10, 8 - mov dword ptr [rsp + 16], r11d # 4-byte Spill - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - jb .LBB5_130 -# %bb.131: - mov rax, r10 + jl .LBB5_138 +# %bb.80: + cmp rcx, 8 + mov dword ptr [rsp + 12], r14d # 4-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 168], rcx # 8-byte Spill + jb .LBB5_83 +# %bb.81: + mov rax, rcx shl rax, 6 - add rax, r14 - cmp qword ptr [rsp + 8], rax # 8-byte Folded Reload - jae .LBB5_133 -# %bb.132: - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - cmp rax, r14 - jbe .LBB5_133 -.LBB5_130: + add rax, rdx + cmp r12, rax + jae .LBB5_208 +# %bb.82: + lea rax, [r12 + 4*rcx] + cmp rax, rdx + jbe .LBB5_208 +.LBB5_83: xor eax, eax - mov qword ptr [rsp + 40], rax # 8-byte Spill - mov r12, qword ptr [rsp + 8] # 8-byte Reload -.LBB5_136: - sub r10, qword ptr [rsp + 40] # 8-byte Folded Reload - mov qword ptr [rsp + 168], r10 # 8-byte Spill + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r13, r12 +.LBB5_84: + sub rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov qword ptr [rsp + 208], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB5_137: # =>This Inner Loop Header: Depth=1 - cmp r11w, word ptr [r14 + 62] - setne byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 60] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 58] - setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 56] +.LBB5_85: # =>This Inner Loop Header: Depth=1 + cmp r14w, word ptr [rdx + 62] + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 60] setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 54] + cmp r14w, word ptr [rdx + 58] setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 52] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 50] + cmp r14w, word ptr [rdx + 56] + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 54] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 52] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 46] + cmp r14w, word ptr [rdx + 50] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 46] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 44] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 42] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 40] setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 44] + cmp r14w, word ptr [rdx + 38] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 36] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 42] - setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 40] + cmp r14w, word ptr [rdx + 34] setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 38] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 36] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 34] + cmp r14w, word ptr [rdx + 30] + setne r10b + cmp r14w, word ptr [rdx + 28] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 26] setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 30] - setne r9b - cmp r11w, word ptr [r14 + 28] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 26] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r11w, word ptr [r14 + 24] - setne r13b - cmp r11w, word ptr [r14 + 22] + cmp r14w, word ptr [rdx + 24] + setne r12b + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 22] setne r15b - cmp r11w, word ptr [r14 + 20] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 20] + setne r14b + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 18] setne r11b - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 18] - setne r10b - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 14] - setne dl - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 12] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 14] + setne sil + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 12] setne byte ptr [rsp + 144] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 10] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 10] + setne r9b + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 8] setne r8b - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 8] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 6] setne dil - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 6] - setne sil - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 4] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 4] setne cl - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - mov eax, dword ptr [rsp + 16] # 4-byte Reload - cmp ax, word ptr [r14 + 2] + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx] + setne byte ptr [rsp + 224] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 12] # 4-byte Reload + cmp ax, word ptr [rdx + 2] setne al - mov rbx, r12 - mov r12d, dword ptr [rsp + 16] # 4-byte Reload - cmp r12w, word ptr [r14 + 16] - mov r12, rbx - setne byte ptr [rsp + 176] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 16] # 4-byte Reload - cmp bx, word ptr [r14 + 32] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - mov ebx, dword ptr [rsp + 16] # 4-byte Reload - cmp bx, word ptr [r14 + 48] - setne bl + mov rbx, r13 + mov r13d, dword ptr [rsp + 12] # 4-byte Reload + cmp r13w, word ptr [rdx + 16] + mov r13, rbx + setne byte ptr [rsp + 160] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 12] # 4-byte Reload + cmp bx, word ptr [rdx + 32] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 12] # 4-byte Reload + cmp bx, word ptr [rdx + 48] + setne byte ptr [rsp + 128] # 1-byte Folded Spill add al, al - add al, byte ptr [rsp + 192] # 1-byte Folded Reload + add al, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 2 or cl, al - shl sil, 3 - or sil, cl - shl dil, 4 - or dil, sil - shl r8b, 5 + shl dil, 3 + or dil, cl + shl r8b, 4 or r8b, dil + shl r9b, 5 + or r9b, r8b movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload shl al, 6 - shl dl, 7 - or dl, al - or dl, r8b - mov byte ptr [r12], dl - add r10b, r10b - add r10b, byte ptr [rsp + 176] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r10b + shl sil, 7 + or sil, al + or sil, r9b + mov byte ptr [r13], sil + add r11b, r11b + add r11b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r11b shl r15b, 3 - or r15b, r11b - mov r11d, dword ptr [rsp + 16] # 4-byte Reload - shl r13b, 4 - or r13b, r15b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 - or al, r13b - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + or al, r12b + mov r14d, dword ptr [rsp + 12] # 4-byte Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 6 - shl r9b, 7 - or r9b, cl - or r9b, al - mov byte ptr [r12 + 1], r9b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl r10b, 7 + or r10b, cl + or r10b, al + mov byte ptr [r13 + 1], r10b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 152] # 1-byte Folded Reload + add al, byte ptr [rsp + 192] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r12 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + mov byte ptr [r13 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - or al, bl + add al, byte ptr [rsp + 128] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r12 + 3], al - add r14, 64 - add r12, 4 - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_137 -# %bb.138: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload + mov byte ptr [r13 + 3], al + add rdx, 64 + add r13, 4 + add qword ptr [rsp + 208], -1 # 8-byte Folded Spill + jne .LBB5_85 +# %bb.86: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 168] # 8-byte Reload jmp .LBB5_139 -.LBB5_159: - mov r11, qword ptr [rsi] - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 +.LBB5_87: + mov r8, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB5_163 -# %bb.160: - movsxd rax, r9d - mov r8, qword ptr [rsp + 8] # 8-byte Reload + je .LBB5_93 +# %bb.88: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB5_91 +# %bb.89: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_161: # =>This Inner Loop Header: Depth=1 - cmp r11, qword ptr [r14] - lea r14, [r14 + 8] - setne dl - neg dl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx ebx, byte ptr [r8 + rsi] - xor dl, bl - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB5_90: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] + setne bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, bl - mov byte ptr [r8 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_161 -# %bb.162: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_163: - sar r10, 5 + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_90 +.LBB5_91: + sub r15, r14 + je .LBB5_200 +# %bb.92: + add r12, 1 +.LBB5_93: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 cmp r15, 32 - jl .LBB5_167 -# %bb.164: - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - mov qword ptr [rsp + 168], r10 # 8-byte Spill + jl .LBB5_97 +# %bb.94: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB5_165: # =>This Inner Loop Header: Depth=1 - cmp r11, qword ptr [r14 + 248] +.LBB5_95: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8, qword ptr [rdx + 248] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 240] + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 232] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 224] setne byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 240] - setne byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 232] + cmp r8, qword ptr [rdx + 216] setne byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 224] - setne byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 216] - setne byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 208] - setne byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 200] + cmp r8, qword ptr [rdx + 208] setne byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 184] - setne byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 176] + cmp r8, qword ptr [rdx + 200] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 184] setne byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 168] + cmp r8, qword ptr [rdx + 176] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 168] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 160] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 152] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 144] setne byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 160] + cmp r8, qword ptr [rdx + 136] setne byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 152] - setne byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 144] - setne byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 136] - setne byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 120] - setne r8b - cmp r11, qword ptr [r14 + 112] - setne byte ptr [rsp + 136] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 104] - setne byte ptr [rsp + 152] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 96] + cmp r8, qword ptr [rdx + 120] setne dil - cmp r11, qword ptr [r14 + 88] + cmp r8, qword ptr [rdx + 112] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 104] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 96] + setne r11b + cmp r8, qword ptr [rdx + 88] setne r10b - cmp r11, qword ptr [r14 + 80] + cmp r8, qword ptr [rdx + 80] setne r9b - cmp r11, qword ptr [r14 + 72] + cmp r8, qword ptr [rdx + 72] setne sil - cmp r11, qword ptr [r14 + 56] + cmp r8, qword ptr [rdx + 56] setne al - cmp r11, qword ptr [r14 + 48] + cmp r8, qword ptr [rdx + 48] setne bl - cmp r11, qword ptr [r14 + 40] + cmp r8, qword ptr [rdx + 40] setne cl - cmp r11, qword ptr [r14 + 32] - setne dl - cmp r11, qword ptr [r14 + 24] - setne r15b - cmp r11, qword ptr [r14 + 16] + cmp r8, qword ptr [rdx + 32] setne r12b - cmp r11, qword ptr [r14] - setne byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 8] + cmp r8, qword ptr [rdx + 24] setne r13b - cmp r11, qword ptr [r14 + 64] - setne byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 128] + cmp r8, qword ptr [rdx + 16] + setne r15b + cmp r8, qword ptr [rdx] + setne byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 8] + setne r14b + cmp r8, qword ptr [rdx + 64] setne byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r11, qword ptr [r14 + 192] - setne byte ptr [rsp + 112] # 1-byte Folded Spill - add r13b, r13b - add r13b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r12b, 2 + cmp r8, qword ptr [rdx + 128] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setne byte ptr [rsp + 120] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 + or r13b, r15b + shl r12b, 4 or r12b, r13b - mov r13, qword ptr [rsp + 8] # 8-byte Reload - shl r15b, 3 - or r15b, r12b - shl dl, 4 - or dl, r15b shl cl, 5 - or cl, dl + or cl, r12b + mov r12, qword ptr [rsp + 136] # 8-byte Reload shl bl, 6 shl al, 7 or al, bl or al, cl - mov byte ptr [r13], al + mov byte ptr [r12], al add sil, sil - add sil, byte ptr [rsp + 176] # 1-byte Folded Reload + add sil, byte ptr [rsp + 144] # 1-byte Folded Reload shl r9b, 2 or r9b, sil shl r10b, 3 or r10b, r9b - shl dil, 4 - or dil, r10b - movzx eax, byte ptr [rsp + 152] # 1-byte Folded Reload + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 5 - or al, dil - movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + or al, r11b + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r13 + 1], r8b - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 192] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r13 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + mov byte ptr [r12 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, byte ptr [rsp + 120] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 6 - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 - or al, dl + or al, bl or al, cl - mov byte ptr [r13 + 3], al - add r14, 256 - add r13, 4 - mov qword ptr [rsp + 8], r13 # 8-byte Spill - add qword ptr [rsp + 168], -1 # 8-byte Folded Spill - jne .LBB5_165 -# %bb.166: - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload -.LBB5_167: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.168: - mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - jne .LBB5_169 -.LBB5_40: + mov byte ptr [r12 + 3], al + add rdx, 256 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB5_95 +# %bb.96: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB5_97: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB5_200 +# %bb.98: + or rax, 1 + cmp r15, rax + jne .LBB5_190 +.LBB5_99: xor edi, edi - jmp .LBB5_41 -.LBB5_171: - lea r10, [r15 + 31] - test r15, r15 - cmovns r10, r15 + jmp .LBB5_192 +.LBB5_100: + mov r14d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB5_175 -# %bb.172: - movsxd rax, r9d - mov r8, qword ptr [rsp + 8] # 8-byte Reload + je .LBB5_106 +# %bb.101: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB5_104 +# %bb.102: + movsxd rsi, r9d + movd xmm0, r14d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB5_173: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [r14] - lea r14, [r14 + 4] +.LBB5_103: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rcx] + lea rdx, [rcx + 4] setp cl - setne dl - or dl, cl - neg dl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx ebx, byte ptr [r8 + rsi] - xor dl, bl - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi + setne bl + or bl, cl + neg bl + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl - and dil, dl - xor dil, bl - mov byte ptr [r8 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB5_173 -# %bb.174: - add qword ptr [rsp + 8], 1 # 8-byte Folded Spill -.LBB5_175: - sar r10, 5 + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_103 +.LBB5_104: + sub r15, r8 + je .LBB5_200 +# %bb.105: + add r12, 1 +.LBB5_106: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 cmp r15, 32 - jl .LBB5_176 -# %bb.177: - cmp r10, 4 - jb .LBB5_178 -# %bb.179: - mov rax, r10 + jl .LBB5_142 +# %bb.107: + movd xmm0, r14d + cmp rcx, 4 + jb .LBB5_110 +# %bb.108: + mov rax, rcx shl rax, 7 - add rax, r14 - cmp qword ptr [rsp + 8], rax # 8-byte Folded Reload - jae .LBB5_181 -# %bb.180: - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - cmp rax, r14 - jbe .LBB5_181 -.LBB5_178: - xor r8d, r8d - mov rbx, r14 - mov r12, qword ptr [rsp + 8] # 8-byte Reload -.LBB5_184: - mov qword ptr [rsp + 16], r12 # 8-byte Spill - mov qword ptr [rsp + 160], r15 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - sub r10, r8 - mov qword ptr [rsp + 208], r10 # 8-byte Spill + add rax, rdx + cmp r12, rax + jae .LBB5_211 +# %bb.109: + lea rax, [r12 + 4*rcx] + cmp rax, rdx + jbe .LBB5_211 +.LBB5_110: + xor r9d, r9d + mov rbx, rdx + mov r13, r12 +.LBB5_111: + mov qword ptr [rsp + 136], r13 # 8-byte Spill + mov dword ptr [rsp + 168], r14d # 4-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rcx # 8-byte Spill + sub rcx, r9 + mov qword ptr [rsp + 208], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB5_185: # =>This Inner Loop Header: Depth=1 +.LBB5_112: # =>This Inner Loop Header: Depth=1 ucomiss xmm0, dword ptr [rbx] setp al setne cl @@ -28073,77 +28285,77 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 24], cl # 1-byte Spill + mov byte ptr [rsp + 16], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 12] setp al setne cl or cl, al - mov byte ptr [rsp + 32], cl # 1-byte Spill + mov byte ptr [rsp + 24], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 16] setp al setne cl or cl, al - mov byte ptr [rsp + 64], cl # 1-byte Spill + mov byte ptr [rsp + 40], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 20] setp al setne cl or cl, al - mov byte ptr [rsp + 56], cl # 1-byte Spill + mov byte ptr [rsp + 48], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 24] setp al setne cl or cl, al - mov byte ptr [rsp + 48], cl # 1-byte Spill + mov byte ptr [rsp + 56], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 28] setp al setne cl or cl, al - mov byte ptr [rsp + 8], cl # 1-byte Spill + mov byte ptr [rsp + 12], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 32] setp al setne cl or cl, al - mov byte ptr [rsp + 40], cl # 1-byte Spill + mov byte ptr [rsp + 32], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 36] setp al setne cl or cl, al - mov byte ptr [rsp + 80], cl # 1-byte Spill + mov byte ptr [rsp + 72], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 40] setp al setne cl or cl, al - mov byte ptr [rsp + 72], cl # 1-byte Spill + mov byte ptr [rsp + 64], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 44] setp al setne cl or cl, al - mov byte ptr [rsp + 104], cl # 1-byte Spill + mov byte ptr [rsp + 88], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 48] setp al setne cl or cl, al - mov byte ptr [rsp + 96], cl # 1-byte Spill + mov byte ptr [rsp + 80], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 52] setp al setne cl or cl, al - mov byte ptr [rsp + 128], cl # 1-byte Spill + mov byte ptr [rsp + 104], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 56] setp al setne cl or cl, al - mov byte ptr [rsp + 112], cl # 1-byte Spill + mov byte ptr [rsp + 120], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 60] setp al setne cl or cl, al - mov byte ptr [rsp + 120], cl # 1-byte Spill + mov byte ptr [rsp + 96], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 64] setp al setne cl or cl, al - mov byte ptr [rsp + 88], cl # 1-byte Spill + mov byte ptr [rsp + 112], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 68] setp al setne r12b @@ -28152,22 +28364,22 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 136], cl # 1-byte Spill + mov byte ptr [rsp + 128], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 76] setp al setne cl or cl, al - mov byte ptr [rsp + 152], cl # 1-byte Spill + mov byte ptr [rsp + 176], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 80] setp al setne cl or cl, al - mov byte ptr [rsp + 144], cl # 1-byte Spill + mov byte ptr [rsp + 192], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 84] setp al setne cl or cl, al - mov byte ptr [rsp + 192], cl # 1-byte Spill + mov byte ptr [rsp + 160], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 88] setp al setne r14b @@ -28180,7 +28392,7 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 176], cl # 1-byte Spill + mov byte ptr [rsp + 144], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 100] setp al setne r11b @@ -28201,7 +28413,7 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 setp al setne cl or cl, al - mov byte ptr [rsp + 168], cl # 1-byte Spill + mov byte ptr [rsp + 224], cl # 1-byte Spill ucomiss xmm0, dword ptr [rbx + 120] setp al setne dil @@ -28213,65 +28425,65 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 add dl, dl or dl, r13b mov r13d, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 48] # 1-byte Folded Reload shl dl, 5 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 6 or al, dl mov edx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 2 or al, r13b mov r13d, eax - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + add cl, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload shl al, 7 or al, dl - mov byte ptr [rsp + 8], al # 1-byte Spill - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + mov byte ptr [rsp + 12], al # 1-byte Spill + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 or al, r13b mov r13d, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 4 or al, r13b - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload shl dl, 4 or dl, cl - movzx r13d, byte ptr [rsp + 128] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 104] # 1-byte Folded Reload shl r13b, 5 - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 6 or cl, r13b - movzx r13d, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 96] # 1-byte Folded Reload shl r13b, 7 or r13b, cl add r12b, r12b - add r12b, byte ptr [rsp + 88] # 1-byte Folded Reload + add r12b, byte ptr [rsp + 112] # 1-byte Folded Reload mov ecx, r12d - movzx r12d, byte ptr [rsp + 136] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 128] # 1-byte Folded Reload shl r12b, 2 or r12b, cl - movzx ecx, byte ptr [rsp + 152] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 3 or cl, r12b mov r12d, ecx - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload shl cl, 4 or cl, r12b - movzx r12d, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 12] # 1-byte Folded Reload or r12b, al - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 5 shl r14b, 6 or r14b, al @@ -28280,16 +28492,16 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 or r8b, r14b or r8b, cl add r11b, r11b - add r11b, byte ptr [rsp + 176] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 144] # 1-byte Folded Reload shl r10b, 2 or r10b, r11b shl r9b, 3 or r9b, r10b shl r15b, 4 or r15b, r9b - mov rax, qword ptr [rsp + 16] # 8-byte Reload + mov rax, qword ptr [rsp + 136] # 8-byte Reload mov byte ptr [rax], r12b - movzx ecx, byte ptr [rsp + 168] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 5 shl dil, 6 or dil, cl @@ -28301,70 +28513,324 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 mov byte ptr [rax + 3], sil add rbx, 128 add rax, 4 - mov qword ptr [rsp + 16], rax # 8-byte Spill + mov qword ptr [rsp + 136], rax # 8-byte Spill add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB5_185 -# %bb.186: - mov r12, qword ptr [rsp + 16] # 8-byte Reload - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r10, qword ptr [rsp + 240] # 8-byte Reload - jmp .LBB5_187 -.LBB5_9: - mov rax, qword ptr [rsp + 8] # 8-byte Reload - mov qword ptr [rsp + 80], rax # 8-byte Spill -.LBB5_92: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.93: - mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - jne .LBB5_95 -# %bb.94: - xor esi, esi - jmp .LBB5_98 -.LBB5_62: - mov rax, qword ptr [rsp + 8] # 8-byte Reload - mov qword ptr [rsp + 104], rax # 8-byte Spill -.LBB5_73: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.74: - mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - jne .LBB5_76 -# %bb.75: - xor esi, esi - jmp .LBB5_79 -.LBB5_105: - mov r12, qword ptr [rsp + 8] # 8-byte Reload -.LBB5_116: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.117: - mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - je .LBB5_118 + jne .LBB5_112 +# %bb.113: + mov r13, qword ptr [rsp + 136] # 8-byte Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14d, dword ptr [rsp + 168] # 4-byte Reload + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + jmp .LBB5_143 +.LBB5_114: + mov r14b, byte ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB5_146 +# %bb.115: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB5_161 +# %bb.116: + movsxd rsi, r9d + mov r11, r8 + .p2align 4, 0x90 +.LBB5_117: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r14b, byte ptr [rdx] + setne dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r12 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB5_117 +# %bb.118: + sub r15, r8 + jne .LBB5_162 + jmp .LBB5_200 +.LBB5_119: + mov r8d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB5_125 +# %bb.120: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB5_123 # %bb.121: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx + .p2align 4, 0x90 +.LBB5_122: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] + setne bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB5_122 +.LBB5_123: + sub r15, r14 + je .LBB5_200 +# %bb.124: + add r12, 1 +.LBB5_125: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB5_129 +# %bb.126: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB5_127: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8d, dword ptr [rdx + 124] + setne byte ptr [rsp + 12] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 120] + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 116] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 112] + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 108] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 104] + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 100] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 92] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 88] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 84] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 80] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 76] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 72] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 68] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 60] + setne dil + cmp r8d, dword ptr [rdx + 56] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] + setne r11b + cmp r8d, dword ptr [rdx + 44] + setne r10b + cmp r8d, dword ptr [rdx + 40] + setne r9b + cmp r8d, dword ptr [rdx + 36] + setne sil + cmp r8d, dword ptr [rdx + 28] + setne al + cmp r8d, dword ptr [rdx + 24] + setne bl + cmp r8d, dword ptr [rdx + 20] + setne cl + cmp r8d, dword ptr [rdx + 16] + setne r12b + cmp r8d, dword ptr [rdx + 12] + setne r13b + cmp r8d, dword ptr [rdx + 8] + setne r15b + cmp r8d, dword ptr [rdx] + setne byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 4] + setne r14b + cmp r8d, dword ptr [rdx + 32] + setne byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 64] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setne byte ptr [rsp + 120] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r13b, 3 + or r13b, r15b + shl r12b, 4 + or r12b, r13b + shl cl, 5 + or cl, r12b + mov r12, qword ptr [rsp + 136] # 8-byte Reload + shl bl, 6 + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r12], al + add sil, sil + add sil, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r9b, 2 + or r9b, sil + shl r10b, 3 + or r10b, r9b + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + shl al, 5 + or al, r11b + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl cl, 6 + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 192] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r12 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 120] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl bl, 6 + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r12 + 3], al + sub rdx, -128 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB5_127 +# %bb.128: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB5_129: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB5_200 +# %bb.130: + or rax, 1 + cmp r15, rax + jne .LBB5_175 +.LBB5_131: + xor edi, edi + jmp .LBB5_177 +.LBB5_132: + mov r13, rdx + jmp .LBB5_149 +.LBB5_133: + mov r13, r12 +.LBB5_134: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB5_200 +# %bb.135: + or rcx, 1 + cmp r15, rcx + je .LBB5_141 +# %bb.136: mov r9, r8 and r9, -2 xor esi, esi .p2align 4, 0x90 -.LBB5_122: # =>This Inner Loop Header: Depth=1 - cmp r11w, word ptr [r14] +.LBB5_137: # =>This Inner Loop Header: Depth=1 + mov rax, rdx + cmp r14w, word ptr [rdx] setne dl neg dl mov rdi, rsi shr rdi, 3 - movzx r10d, byte ptr [r12 + rdi] + movzx r10d, byte ptr [r13 + rdi] mov ecx, esi and cl, 6 mov bl, 1 @@ -28372,119 +28838,305 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 xor dl, r10b and bl, dl xor bl, r10b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r13 + rdi], bl add rsi, 2 - cmp r11w, word ptr [r14 + 2] - lea r14, [r14 + 4] - setne dl - neg dl - xor dl, bl + cmp r14w, word ptr [rax + 2] + lea rdx, [rax + 4] + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, dl + and al, r10b xor al, bl - mov byte ptr [r12 + rdi], al + mov byte ptr [r13 + rdi], al cmp r9, rsi - jne .LBB5_122 - jmp .LBB5_119 -.LBB5_128: - mov r12, qword ptr [rsp + 8] # 8-byte Reload + jne .LBB5_137 + jmp .LBB5_197 +.LBB5_138: + mov r13, r12 .LBB5_139: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.140: + shl rcx, 5 mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - jne .LBB5_141 -.LBB5_118: + sub r8, rcx + jle .LBB5_200 +# %bb.140: + or rcx, 1 + cmp r15, rcx + jne .LBB5_195 +.LBB5_141: xor esi, esi - jmp .LBB5_119 -.LBB5_176: - mov r12, qword ptr [rsp + 8] # 8-byte Reload - mov rbx, r14 -.LBB5_187: - shl r10, 5 - cmp r10, r15 - jge .LBB5_198 -# %bb.188: + jmp .LBB5_197 +.LBB5_142: + mov r13, r12 + mov rbx, rdx +.LBB5_143: + shl rcx, 5 mov r8, r15 - sub r8, r10 - not r10 - add r10, r15 - jne .LBB5_192 -# %bb.189: + sub r8, rcx + jle .LBB5_200 +# %bb.144: + movd xmm0, r14d + or rcx, 1 + cmp r15, rcx + jne .LBB5_201 +# %bb.145: xor esi, esi - jmp .LBB5_190 -.LBB5_155: - mov r9, r8 - and r9, -2 - xor edi, edi - mov r15, qword ptr [rsp + 8] # 8-byte Reload + jmp .LBB5_203 +.LBB5_146: + mov rdi, rdx + jmp .LBB5_163 +.LBB5_147: + mov r13, rdx + sub r15, r8 + je .LBB5_200 +.LBB5_148: + add r12, 1 +.LBB5_149: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB5_157 +# %bb.150: + cmp rcx, 16 + mov byte ptr [rsp + 12], r14b # 1-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rcx # 8-byte Spill + jb .LBB5_153 +# %bb.151: + mov rax, rcx + shl rax, 5 + add rax, r13 + cmp r12, rax + jae .LBB5_214 +# %bb.152: + lea rax, [r12 + 4*rcx] + cmp r13, rax + jae .LBB5_214 +.LBB5_153: + xor eax, eax + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov rdi, r13 + mov r13, r12 +.LBB5_154: + sub rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB5_156: # =>This Inner Loop Header: Depth=1 - cmp r11d, dword ptr [r14] - setne al - neg al - mov rsi, rdi - shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - mov ecx, edi - and cl, 6 - mov dl, 1 - shl dl, cl - xor al, r10b - and dl, al - xor dl, r10b - mov byte ptr [r15 + rsi], dl - add rdi, 2 - cmp r11d, dword ptr [r14 + 4] - lea r14, [r14 + 8] +.LBB5_155: # =>This Inner Loop Header: Depth=1 + cmp r14b, byte ptr [rdi + 31] + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 30] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 29] + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 28] + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 27] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 26] + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 25] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 23] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 22] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 21] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 20] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 19] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 18] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 17] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 15] + setne r10b + cmp r14b, byte ptr [rdi + 14] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 13] + setne byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 12] + setne r12b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 11] + setne r15b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 10] + setne r14b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 9] + setne r11b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 7] + setne dl + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 6] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 5] + setne r9b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 4] + setne r8b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 3] + setne sil + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 2] + setne cl + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi] + setne byte ptr [rsp + 160] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 1] setne al - neg al - xor al, dl - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, al - xor bl, dl - mov byte ptr [r15 + rsi], bl - cmp r9, rdi - jne .LBB5_156 -.LBB5_24: - test r8b, 1 - je .LBB5_198 -# %bb.25: - cmp r11d, dword ptr [r14] - jmp .LBB5_26 -.LBB5_95: + mov rbx, r13 + movzx r13d, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp r13b, byte ptr [rdi + 8] + mov r13, rbx + setne byte ptr [rsp + 144] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp bl, byte ptr [rdi + 16] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp bl, byte ptr [rdi + 24] + setne bl + add al, al + add al, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, al + shl sil, 3 + or sil, cl + shl r8b, 4 + or r8b, sil + shl r9b, 5 + or r9b, r8b + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 6 + shl dl, 7 + or dl, al + or dl, r9b + mov byte ptr [r13], dl + add r11b, r11b + add r11b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r11b + shl r15b, 3 + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 5 + or al, r12b + movzx r14d, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl cl, 6 + shl r10b, 7 + or r10b, cl + or r10b, al + mov byte ptr [r13 + 1], r10b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 176] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + or al, bl + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 3], al + add rdi, 32 + add r13, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB5_155 +# %bb.156: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + jmp .LBB5_158 +.LBB5_157: + mov rdi, r13 + mov r13, r12 +.LBB5_158: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB5_200 +# %bb.159: + or rcx, 1 + cmp r15, rcx + je .LBB5_174 +# %bb.179: mov r10, r8 and r10, -2 - xor esi, esi - mov r11, qword ptr [rsp + 80] # 8-byte Reload + xor r9d, r9d .p2align 4, 0x90 -.LBB5_96: # =>This Inner Loop Header: Depth=1 - mov rax, rsi - movzx esi, byte ptr [rsp + 16] # 1-byte Folded Reload - cmp sil, byte ptr [r14 + rax] +.LBB5_180: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r14b, byte ptr [rdi + r9] setne bl neg bl - mov rdi, rax - shr rdi, 3 + mov rsi, r9 + shr rsi, 3 mov ecx, eax and cl, 6 mov dl, 1 shl dl, cl - movzx r9d, byte ptr [r11 + rdi] + movzx r9d, byte ptr [r13 + rsi] xor bl, r9b and dl, bl xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp sil, byte ptr [r14 + rax + 1] - lea rsi, [rax + 2] + mov byte ptr [r13 + rsi], dl + cmp r14b, byte ptr [rdi + rax + 1] + lea r9, [rax + 2] setne bl neg bl xor bl, dl @@ -28493,48 +29145,302 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 shl al, cl and al, bl xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB5_96 -# %bb.97: - add r14, rsi -.LBB5_98: - test r8b, 1 - je .LBB5_198 -# %bb.99: - mov al, byte ptr [rsp + 16] # 1-byte Reload - cmp al, byte ptr [r14] + mov byte ptr [r13 + rsi], al + cmp r10, r9 + jne .LBB5_180 + jmp .LBB5_183 +.LBB5_161: + mov rdi, rdx + sub r15, r8 + je .LBB5_200 +.LBB5_162: + add r12, 1 +.LBB5_163: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB5_171 +# %bb.164: + cmp rcx, 16 + mov byte ptr [rsp + 12], r14b # 1-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 240], rcx # 8-byte Spill + jb .LBB5_167 +# %bb.165: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r12, rax + jae .LBB5_217 +# %bb.166: + lea rax, [r12 + 4*rcx] + cmp rdi, rax + jae .LBB5_217 +.LBB5_167: + xor eax, eax + mov qword ptr [rsp + 168], rax # 8-byte Spill + mov r13, r12 +.LBB5_168: + sub rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB5_169: # =>This Inner Loop Header: Depth=1 + cmp r14b, byte ptr [rdi + 31] + setne byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 30] + setne byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 29] + setne byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 28] + setne byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 27] + setne byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 26] + setne byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 25] + setne byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 23] + setne byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 22] + setne byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 21] + setne byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 20] + setne byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 19] + setne byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 18] + setne byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 17] + setne byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 15] + setne r10b + cmp r14b, byte ptr [rdi + 14] + setne byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 13] + setne byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 12] + setne r12b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 11] + setne r15b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 10] + setne r14b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 9] + setne r11b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 7] + setne dl + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 6] + setne byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 5] + setne r9b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 4] + setne r8b + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 3] + setne sil + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 2] + setne cl + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi] + setne byte ptr [rsp + 160] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 1] + setne al + mov rbx, r13 + movzx r13d, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp r13b, byte ptr [rdi + 8] + mov r13, rbx + setne byte ptr [rsp + 144] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp bl, byte ptr [rdi + 16] + setne byte ptr [rsp + 176] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 12] # 1-byte Folded Reload + cmp bl, byte ptr [rdi + 24] + setne bl + add al, al + add al, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, al + shl sil, 3 + or sil, cl + shl r8b, 4 + or r8b, sil + shl r9b, 5 + or r9b, r8b + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 6 + shl dl, 7 + or dl, al + or dl, r9b + mov byte ptr [r13], dl + add r11b, r11b + add r11b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r11b + shl r15b, 3 + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 5 + or al, r12b + movzx r14d, byte ptr [rsp + 12] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl cl, 6 + shl r10b, 7 + or r10b, cl + or r10b, al + mov byte ptr [r13 + 1], r10b + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 176] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + or al, bl + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 3], al + add rdi, 32 + add r13, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB5_169 +# %bb.170: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + jmp .LBB5_172 +.LBB5_171: + mov r13, r12 +.LBB5_172: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB5_200 +# %bb.173: + or rcx, 1 + cmp r15, rcx + jne .LBB5_181 +.LBB5_174: + xor r9d, r9d + jmp .LBB5_184 +.LBB5_175: + mov r11, r9 + and r11, -2 + xor edi, edi + .p2align 4, 0x90 +.LBB5_176: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] setne al neg al - mov rdx, rsi - shr rdx, 3 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - jmp .LBB5_81 -.LBB5_76: + mov rsi, rdi + shr rsi, 3 + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] + mov ecx, edi + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r10b + and bl, al + xor bl, r10b + mov byte ptr [r12 + rsi], bl + add rdi, 2 + cmp r8d, dword ptr [rdx + 4] + lea rdx, [rdx + 8] + setne r10b + neg r10b + xor r10b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r10b + xor al, bl + mov byte ptr [r12 + rsi], al + cmp r11, rdi + jne .LBB5_176 +.LBB5_177: + test r9b, 1 + je .LBB5_200 +# %bb.178: + cmp r8d, dword ptr [rdx] + jmp .LBB5_194 +.LBB5_181: mov r10, r8 and r10, -2 - xor esi, esi - mov r11, qword ptr [rsp + 104] # 8-byte Reload + xor r9d, r9d .p2align 4, 0x90 -.LBB5_77: # =>This Inner Loop Header: Depth=1 - mov rax, rsi - movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload - cmp sil, byte ptr [r14 + rax] +.LBB5_182: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r14b, byte ptr [rdi + r9] setne bl neg bl - mov rdi, rax - shr rdi, 3 + mov rsi, r9 + shr rsi, 3 mov ecx, eax and cl, 6 mov dl, 1 shl dl, cl - movzx r9d, byte ptr [r11 + rdi] + movzx r9d, byte ptr [r13 + rsi] xor bl, r9b and dl, bl xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp sil, byte ptr [r14 + rax + 1] - lea rsi, [rax + 2] + mov byte ptr [r13 + rsi], dl + cmp r14b, byte ptr [rdi + rax + 1] + lea r9, [rax + 2] setne bl neg bl xor bl, dl @@ -28543,85 +29449,76 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 shl al, cl and al, bl xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, rsi - jne .LBB5_77 -# %bb.78: - add r14, rsi -.LBB5_79: + mov byte ptr [r13 + rsi], al + cmp r10, r9 + jne .LBB5_182 +.LBB5_183: + add rdi, r9 +.LBB5_184: test r8b, 1 - je .LBB5_198 -# %bb.80: - mov al, byte ptr [rsp + 64] # 1-byte Reload - cmp al, byte ptr [r14] + je .LBB5_200 +# %bb.185: + cmp r14b, byte ptr [rdi] setne al neg al - mov rdx, rsi + mov rdx, r9 shr rdx, 3 - mov r8, qword ptr [rsp + 104] # 8-byte Reload -.LBB5_81: - mov dil, byte ptr [r8 + rdx] - and sil, 7 + mov dil, byte ptr [r13 + rdx] + and r9b, 7 mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r8 + rdx], bl - jmp .LBB5_198 -.LBB5_194: + mov ecx, r9d + jmp .LBB5_199 +.LBB5_186: mov r9, r8 and r9, -2 xor edi, edi - mov r11, qword ptr [rsp + 8] # 8-byte Reload .p2align 4, 0x90 -.LBB5_195: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [r14] +.LBB5_187: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rdx] setp cl setne al or al, cl neg al mov rsi, rdi shr rsi, 3 - movzx edx, byte ptr [r11 + rsi] + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 + mov r11b, 1 + shl r11b, cl + xor al, r10b + and r11b, al + xor r11b, r10b + mov byte ptr [r12 + rsi], r11b + add rdi, 2 + ucomisd xmm0, qword ptr [rdx + 8] + lea rdx, [rdx + 16] + setp r10b + setne al + or al, r10b + neg al + xor al, r11b + or cl, 1 mov bl, 1 shl bl, cl - xor al, dl and bl, al - xor bl, dl - mov byte ptr [r11 + rsi], bl - add rdi, 2 - ucomisd xmm0, qword ptr [r14 + 8] - lea r14, [r14 + 16] - setp al - setne dl - or dl, al - neg dl - xor dl, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, bl - mov byte ptr [r11 + rsi], al + xor bl, r11b + mov byte ptr [r12 + rsi], bl cmp r9, rdi - jne .LBB5_195 -.LBB5_196: + jne .LBB5_187 +.LBB5_188: test r8b, 1 - je .LBB5_198 -# %bb.197: - ucomisd xmm0, qword ptr [r14] + je .LBB5_200 +# %bb.189: + ucomisd xmm0, qword ptr [rdx] setp al setne dl or dl, al neg dl mov rax, rdi shr rax, 3 - mov r8, qword ptr [rsp + 8] # 8-byte Reload - mov sil, byte ptr [r8 + rax] + mov sil, byte ptr [r12 + rax] and dil, 7 mov bl, 1 mov ecx, edi @@ -28629,55 +29526,54 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 xor dl, sil and bl, dl xor bl, sil - mov byte ptr [r8 + rax], bl - jmp .LBB5_198 -.LBB5_169: - mov r9, r8 - and r9, -2 + mov byte ptr [r12 + rax], bl + jmp .LBB5_200 +.LBB5_190: + mov r11, r9 + and r11, -2 xor edi, edi - mov r15, qword ptr [rsp + 8] # 8-byte Reload .p2align 4, 0x90 -.LBB5_170: # =>This Inner Loop Header: Depth=1 - cmp r11, qword ptr [r14] +.LBB5_191: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] setne al neg al mov rsi, rdi shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 - mov dl, 1 - shl dl, cl - xor al, r10b - and dl, al - xor dl, r10b - mov byte ptr [r15 + rsi], dl - add rdi, 2 - cmp r11, qword ptr [r14 + 8] - lea r14, [r14 + 16] - setne al - neg al - xor al, dl - or cl, 1 mov bl, 1 shl bl, cl + xor al, r10b and bl, al - xor bl, dl - mov byte ptr [r15 + rsi], bl - cmp r9, rdi - jne .LBB5_170 -.LBB5_41: - test r8b, 1 - je .LBB5_198 -# %bb.42: - cmp r11, qword ptr [r14] -.LBB5_26: + xor bl, r10b + mov byte ptr [r12 + rsi], bl + add rdi, 2 + cmp r8, qword ptr [rdx + 8] + lea rdx, [rdx + 16] + setne r10b + neg r10b + xor r10b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r10b + xor al, bl + mov byte ptr [r12 + rsi], al + cmp r11, rdi + jne .LBB5_191 +.LBB5_192: + test r9b, 1 + je .LBB5_200 +# %bb.193: + cmp r8, qword ptr [rdx] +.LBB5_194: setne al neg al mov rdx, rdi shr rdx, 3 - mov r8, qword ptr [rsp + 8] # 8-byte Reload - mov sil, byte ptr [r8 + rdx] + mov sil, byte ptr [r12 + rdx] and dil, 7 mov bl, 1 mov ecx, edi @@ -28685,20 +29581,21 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 xor al, sil and bl, al xor bl, sil - mov byte ptr [r8 + rdx], bl - jmp .LBB5_198 -.LBB5_141: + mov byte ptr [r12 + rdx], bl + jmp .LBB5_200 +.LBB5_195: mov r9, r8 and r9, -2 xor esi, esi .p2align 4, 0x90 -.LBB5_142: # =>This Inner Loop Header: Depth=1 - cmp r11w, word ptr [r14] +.LBB5_196: # =>This Inner Loop Header: Depth=1 + mov rax, rdx + cmp r14w, word ptr [rdx] setne dl neg dl mov rdi, rsi shr rdi, 3 - movzx r10d, byte ptr [r12 + rdi] + movzx r10d, byte ptr [r13 + rdi] mov ecx, esi and cl, 6 mov bl, 1 @@ -28706,47 +29603,56 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 xor dl, r10b and bl, dl xor bl, r10b - mov byte ptr [r12 + rdi], bl + mov byte ptr [r13 + rdi], bl add rsi, 2 - cmp r11w, word ptr [r14 + 2] - lea r14, [r14 + 4] - setne dl - neg dl - xor dl, bl + cmp r14w, word ptr [rax + 2] + lea rdx, [rax + 4] + setne r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, dl + and al, r10b xor al, bl - mov byte ptr [r12 + rdi], al + mov byte ptr [r13 + rdi], al cmp r9, rsi - jne .LBB5_142 -.LBB5_119: + jne .LBB5_196 +.LBB5_197: test r8b, 1 - je .LBB5_198 -# %bb.120: - cmp r11w, word ptr [r14] + je .LBB5_200 +# %bb.198: + cmp r14w, word ptr [rdx] setne al neg al mov rdx, rsi shr rdx, 3 - mov dil, byte ptr [r12 + rdx] + mov dil, byte ptr [r13 + rdx] and sil, 7 mov bl, 1 mov ecx, esi +.LBB5_199: shl bl, cl xor al, dil and bl, al xor bl, dil - mov byte ptr [r12 + rdx], bl - jmp .LBB5_198 -.LBB5_192: + mov byte ptr [r13 + rdx], bl +.LBB5_200: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.LBB5_201: mov r9, r8 and r9, -2 xor esi, esi - mov r14, r12 + mov r14, r13 .p2align 4, 0x90 -.LBB5_193: # =>This Inner Loop Header: Depth=1 +.LBB5_202: # =>This Inner Loop Header: Depth=1 ucomiss xmm0, dword ptr [rbx] setp cl setne dl @@ -28754,1162 +29660,1734 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 neg dl mov rdi, rsi shr rdi, 3 - movzx r10d, byte ptr [r14 + rdi] - mov ecx, esi - and cl, 6 - mov r11b, 1 - shl r11b, cl - xor dl, r10b - and r11b, dl - xor r11b, r10b - mov byte ptr [r14 + rdi], r11b - add rsi, 2 - ucomiss xmm0, dword ptr [rbx + 4] - lea rbx, [rbx + 8] - setp r10b - setne dl - or dl, r10b - neg dl - xor dl, r11b - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, r11b - mov byte ptr [r14 + rdi], al - cmp r9, rsi - jne .LBB5_193 -.LBB5_190: - test r8b, 1 - je .LBB5_198 -# %bb.191: - ucomiss xmm0, dword ptr [rbx] - setp al - setne dl - or dl, al - neg dl - mov rax, rsi - shr rax, 3 - mov dil, byte ptr [r12 + rax] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor dl, dil - and bl, dl - xor bl, dil - mov byte ptr [r12 + rax], bl -.LBB5_198: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.LBB5_86: - and r10, -16 - mov rax, r10 - shl rax, 5 - add rax, r14 - mov qword ptr [rsp + 272], rax # 8-byte Spill - mov qword ptr [rsp + 232], r10 # 8-byte Spill - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - mov qword ptr [rsp + 80], rax # 8-byte Spill - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill - xor eax, eax - .p2align 4, 0x90 -.LBB5_87: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 168], rax # 8-byte Spill - shl rax, 5 - mov rdx, rax - mov r12, rax - mov r8, rax - mov r10, rax - mov r15, rax - mov r9, rax - mov r11, rax - mov rbx, rax - mov rsi, rax - mov qword ptr [rsp + 72], rax # 8-byte Spill - mov r13, rax - movzx ecx, byte ptr [r14 + rax] - movd xmm4, ecx - movzx ecx, byte ptr [r14 + rax + 1] - movd xmm3, ecx - movzx ecx, byte ptr [r14 + rax + 2] - movd xmm5, ecx - movzx ecx, byte ptr [r14 + rax + 3] - movd xmm7, ecx - movzx ecx, byte ptr [r14 + rax + 4] - movd xmm9, ecx - movzx ecx, byte ptr [r14 + rax + 5] - movd xmm2, ecx - movzx ecx, byte ptr [r14 + rax + 6] - movd xmm8, ecx - movzx ecx, byte ptr [r14 + rax + 7] - movd xmm14, ecx - movzx ecx, byte ptr [r14 + rax + 8] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - movzx ecx, byte ptr [r14 + rax + 9] - movd xmm11, ecx - movzx ecx, byte ptr [r14 + rax + 10] - movd xmm12, ecx - movzx ecx, byte ptr [r14 + rax + 11] - movd xmm13, ecx - movzx ecx, byte ptr [r14 + rax + 12] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill - movzx ecx, byte ptr [r14 + rax + 13] - movd xmm6, ecx - movzx ecx, byte ptr [r14 + rax + 14] - movd xmm15, ecx - movzx ecx, byte ptr [r14 + rax + 15] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill - mov rcx, rax - mov qword ptr [rsp + 128], rax # 8-byte Spill - mov rdi, rax - or rdi, 32 - or rdx, 64 - mov qword ptr [rsp + 40], rdx # 8-byte Spill - or r12, 96 - or r8, 128 - or r10, 160 - or r15, 192 - or r9, 224 - or r11, 256 - or rbx, 288 - or rsi, 320 - mov qword ptr [rsp + 104], rsi # 8-byte Spill - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - or rsi, 352 - mov qword ptr [rsp + 72], rsi # 8-byte Spill - or r13, 384 - mov qword ptr [rsp + 112], r13 # 8-byte Spill - or rax, 416 - mov qword ptr [rsp + 64], rax # 8-byte Spill - mov r13, rcx - or r13, 448 - mov qword ptr [rsp + 56], r13 # 8-byte Spill - or rcx, 480 - mov qword ptr [rsp + 32], rcx # 8-byte Spill - mov rcx, rdi - pinsrb xmm4, byte ptr [r14 + rdi], 1 - pinsrb xmm4, byte ptr [r14 + rdx], 2 - mov qword ptr [rsp + 120], r12 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r12], 3 - pinsrb xmm4, byte ptr [r14 + r8], 4 - mov qword ptr [rsp + 96], r10 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r10], 5 - mov qword ptr [rsp + 136], r15 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r15], 6 - pinsrb xmm4, byte ptr [r14 + r9], 7 - pinsrb xmm4, byte ptr [r14 + r11], 8 - mov qword ptr [rsp + 88], rbx # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + rbx], 9 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rbx], 10 - pinsrb xmm4, byte ptr [r14 + rsi], 11 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rdi], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rax], 13 - pinsrb xmm4, byte ptr [r14 + r13], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rax], 15 - pinsrb xmm3, byte ptr [r14 + rcx + 1], 1 - pinsrb xmm3, byte ptr [r14 + rdx + 1], 2 - pinsrb xmm3, byte ptr [r14 + r12 + 1], 3 - pinsrb xmm3, byte ptr [r14 + r8 + 1], 4 - mov rdx, r8 - pinsrb xmm3, byte ptr [r14 + r10 + 1], 5 - pinsrb xmm3, byte ptr [r14 + r15 + 1], 6 - pinsrb xmm3, byte ptr [r14 + r9 + 1], 7 - mov r8, r9 - pinsrb xmm3, byte ptr [r14 + r11 + 1], 8 - mov r10, r11 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm3, byte ptr [r14 + r12 + 1], 9 - pinsrb xmm3, byte ptr [r14 + rbx + 1], 10 - pinsrb xmm3, byte ptr [r14 + rsi + 1], 11 - pinsrb xmm3, byte ptr [r14 + rdi + 1], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm3, byte ptr [r14 + rax + 1], 13 - pinsrb xmm3, byte ptr [r14 + r13 + 1], 14 - movdqa xmm1, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm4, xmm1 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [r14 + r13 + 1], 15 - pcmpeqb xmm3, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI5_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] - pandn xmm3, xmm0 - paddb xmm3, xmm4 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - movzx esi, byte ptr [r14 + rax + 16] - movd xmm10, esi - pinsrb xmm5, byte ptr [r14 + rcx + 2], 1 + movzx r10d, byte ptr [r14 + rdi] + mov ecx, esi + and cl, 6 + mov r11b, 1 + shl r11b, cl + xor dl, r10b + and r11b, dl + xor r11b, r10b + mov byte ptr [r14 + rdi], r11b + add rsi, 2 + ucomiss xmm0, dword ptr [rbx + 4] + lea rbx, [rbx + 8] + setp r10b + setne dl + or dl, r10b + neg dl + xor dl, r11b + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, r11b + mov byte ptr [r14 + rdi], al + cmp r9, rsi + jne .LBB5_202 +.LBB5_203: + test r8b, 1 + je .LBB5_200 +# %bb.204: + ucomiss xmm0, dword ptr [rbx] + setp al + setne dl + or dl, al + neg dl + mov rax, rsi + shr rax, 3 + mov dil, byte ptr [r13 + rax] + and sil, 7 + mov bl, 1 + mov ecx, esi + shl bl, cl + xor dl, dil + and bl, dl + xor bl, dil + mov byte ptr [r13 + rax], bl + jmp .LBB5_200 +.LBB5_205: + and rcx, -8 mov rax, rcx - mov qword ptr [rsp + 24], rcx # 8-byte Spill - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rcx + 2], 2 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r15 + 2], 3 - mov rbx, rdx - pinsrb xmm5, byte ptr [r14 + rdx + 2], 4 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r9 + 2], 5 - mov r11, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r11 + 2], 6 - mov rdx, r8 - mov qword ptr [rsp + 48], r8 # 8-byte Spill - pinsrb xmm5, byte ptr [r14 + r8 + 2], 7 - pinsrb xmm5, byte ptr [r14 + r10 + 2], 8 - pinsrb xmm5, byte ptr [r14 + r12 + 2], 9 - mov r8, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r8 + 2], 10 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rcx + 2], 11 - pinsrb xmm5, byte ptr [r14 + rdi + 2], 12 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rsi + 2], 13 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rsi + 2], 14 - pinsrb xmm5, byte ptr [r14 + r13 + 2], 15 - pinsrb xmm7, byte ptr [r14 + rax + 3], 1 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 3], 2 - pinsrb xmm7, byte ptr [r14 + r15 + 3], 3 - pinsrb xmm7, byte ptr [r14 + rbx + 3], 4 - pinsrb xmm7, byte ptr [r14 + r9 + 3], 5 - pinsrb xmm7, byte ptr [r14 + r11 + 3], 6 - pinsrb xmm7, byte ptr [r14 + rdx + 3], 7 - pinsrb xmm7, byte ptr [r14 + r10 + 3], 8 - pinsrb xmm7, byte ptr [r14 + r12 + 3], 9 - pinsrb xmm7, byte ptr [r14 + r8 + 3], 10 - pinsrb xmm7, byte ptr [r14 + rcx + 3], 11 - pinsrb xmm7, byte ptr [r14 + rdi + 3], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 3], 13 - pinsrb xmm7, byte ptr [r14 + rsi + 3], 14 - pinsrb xmm7, byte ptr [r14 + r13 + 3], 15 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 4], 1 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 4], 2 - pinsrb xmm9, byte ptr [r14 + r15 + 4], 3 - pinsrb xmm9, byte ptr [r14 + rbx + 4], 4 - pinsrb xmm9, byte ptr [r14 + r9 + 4], 5 - pinsrb xmm9, byte ptr [r14 + r11 + 4], 6 - pinsrb xmm9, byte ptr [r14 + rdx + 4], 7 - pinsrb xmm9, byte ptr [r14 + r10 + 4], 8 - mov qword ptr [rsp + 144], r10 # 8-byte Spill - pinsrb xmm9, byte ptr [r14 + r12 + 4], 9 - pinsrb xmm9, byte ptr [r14 + r8 + 4], 10 - pinsrb xmm9, byte ptr [r14 + rcx + 4], 11 - pinsrb xmm9, byte ptr [r14 + rdi + 4], 12 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rdx + 4], 13 - pinsrb xmm9, byte ptr [r14 + rsi + 4], 14 - pinsrb xmm9, byte ptr [r14 + r13 + 4], 15 - pcmpeqb xmm5, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI5_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm5, xmm0 - pcmpeqb xmm7, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI5_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm7, xmm0 - por xmm7, xmm5 - mov r9, qword ptr [rsp + 128] # 8-byte Reload - movzx esi, byte ptr [r14 + r9 + 17] - movd xmm4, esi - pcmpeqb xmm9, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI5_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm9, xmm0 - por xmm9, xmm7 - movzx esi, byte ptr [r14 + r9 + 18] - movd xmm7, esi + shl rax, 6 + add rax, rdx + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 32], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 48], rax # 8-byte Spill + movd xmm0, r14d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] + xor r14d, r14d + mov qword ptr [rsp + 136], r12 # 8-byte Spill + pxor xmm15, xmm15 + .p2align 4, 0x90 +.LBB5_206: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 40], r14 # 8-byte Spill + shl r14, 6 + mov r9, r14 + mov r15, r14 + mov r12, r14 + mov r13, r14 + mov rsi, r14 + mov r8, r14 + movzx eax, word ptr [rdx + r14] + movd xmm5, eax + movzx eax, word ptr [rdx + r14 + 2] + movd xmm0, eax + movzx eax, word ptr [rdx + r14 + 4] + movd xmm1, eax + movzx eax, word ptr [rdx + r14 + 6] + movd xmm7, eax + movzx eax, word ptr [rdx + r14 + 8] + movd xmm8, eax + movzx eax, word ptr [rdx + r14 + 10] + movd xmm4, eax + movzx eax, word ptr [rdx + r14 + 12] + movzx r10d, word ptr [rdx + r14 + 14] + movzx ebx, word ptr [rdx + r14 + 16] + movzx edi, word ptr [rdx + r14 + 18] + movzx ecx, word ptr [rdx + r14 + 20] + mov dword ptr [rsp + 24], ecx # 4-byte Spill + mov rcx, r14 + or rcx, 64 + or r9, 128 + or r15, 192 + or r12, 256 + or r13, 320 + or rsi, 384 + pinsrw xmm5, word ptr [rdx + rcx], 1 + pinsrw xmm5, word ptr [rdx + r9], 2 + pinsrw xmm5, word ptr [rdx + r15], 3 + pinsrw xmm5, word ptr [rdx + r12], 4 + pinsrw xmm5, word ptr [rdx + r13], 5 + pinsrw xmm5, word ptr [rdx + rsi], 6 + pinsrw xmm0, word ptr [rdx + rcx + 2], 1 + pinsrw xmm0, word ptr [rdx + r9 + 2], 2 + pinsrw xmm0, word ptr [rdx + r15 + 2], 3 + pinsrw xmm0, word ptr [rdx + r12 + 2], 4 + pinsrw xmm0, word ptr [rdx + r13 + 2], 5 + pinsrw xmm0, word ptr [rdx + rsi + 2], 6 + or r8, 448 + pinsrw xmm0, word ptr [rdx + r8 + 2], 7 + movd xmm2, eax + movzx eax, word ptr [rdx + r14 + 22] + mov dword ptr [rsp + 16], eax # 4-byte Spill + pcmpeqw xmm0, xmm11 + pinsrw xmm1, word ptr [rdx + rcx + 4], 1 + pinsrw xmm1, word ptr [rdx + r9 + 4], 2 + pinsrw xmm1, word ptr [rdx + r15 + 4], 3 + pinsrw xmm1, word ptr [rdx + r12 + 4], 4 + pinsrw xmm1, word ptr [rdx + r13 + 4], 5 + pinsrw xmm1, word ptr [rdx + rsi + 4], 6 + pinsrw xmm1, word ptr [rdx + r8 + 4], 7 + packsswb xmm0, xmm0 + pcmpeqw xmm1, xmm11 + movdqa xmm9, xmmword ptr [rip + .LCPI5_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm3, xmm9 + pblendvb xmm3, xmm15, xmm0 + packsswb xmm1, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI5_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm0 + movdqa xmm14, xmm0 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r10d + movzx r11d, word ptr [rdx + r14 + 24] + pinsrw xmm5, word ptr [rdx + r8], 7 + pcmpeqw xmm5, xmm11 pcmpeqd xmm0, xmm0 - psubb xmm3, xmm0 - por xmm9, xmm3 - movzx esi, byte ptr [r14 + r9 + 19] - movd xmm5, esi - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + r9 + 5], 1 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + rax + 5], 2 - pinsrb xmm2, byte ptr [r14 + r15 + 5], 3 - pinsrb xmm2, byte ptr [r14 + rbx + 5], 4 - mov r12, rbx - mov qword ptr [rsp + 152], rbx # 8-byte Spill - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + r13 + 5], 5 - pinsrb xmm2, byte ptr [r14 + r11 + 5], 6 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + rsi + 5], 7 - pinsrb xmm2, byte ptr [r14 + r10 + 5], 8 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + r15 + 5], 9 - pinsrb xmm2, byte ptr [r14 + r8 + 5], 10 - pinsrb xmm2, byte ptr [r14 + rcx + 5], 11 - pinsrb xmm2, byte ptr [r14 + rdi + 5], 12 - pinsrb xmm2, byte ptr [r14 + rdx + 5], 13 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + r11 + 5], 14 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + r10 + 5], 15 - pinsrb xmm8, byte ptr [r14 + r9 + 6], 1 - pinsrb xmm8, byte ptr [r14 + rax + 6], 2 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm8, byte ptr [r14 + rbx + 6], 3 - pinsrb xmm8, byte ptr [r14 + r12 + 6], 4 - pinsrb xmm8, byte ptr [r14 + r13 + 6], 5 - mov r12, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm8, byte ptr [r14 + r12 + 6], 6 - pinsrb xmm8, byte ptr [r14 + rsi + 6], 7 - mov r12, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm8, byte ptr [r14 + r12 + 6], 8 - pinsrb xmm8, byte ptr [r14 + r15 + 6], 9 - pinsrb xmm8, byte ptr [r14 + r8 + 6], 10 - pinsrb xmm8, byte ptr [r14 + rcx + 6], 11 - pinsrb xmm8, byte ptr [r14 + rdi + 6], 12 - pinsrb xmm8, byte ptr [r14 + rdx + 6], 13 - pinsrb xmm8, byte ptr [r14 + r11 + 6], 14 - pinsrb xmm8, byte ptr [r14 + r10 + 6], 15 - pinsrb xmm14, byte ptr [r14 + r9 + 7], 1 - pinsrb xmm14, byte ptr [r14 + rax + 7], 2 - mov r15, rax - pinsrb xmm14, byte ptr [r14 + rbx + 7], 3 - mov r11, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm14, byte ptr [r14 + r11 + 7], 4 - pinsrb xmm14, byte ptr [r14 + r13 + 7], 5 - mov rax, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm14, byte ptr [r14 + rax + 7], 6 - pinsrb xmm14, byte ptr [r14 + rsi + 7], 7 - mov r9, r12 - pinsrb xmm14, byte ptr [r14 + r12 + 7], 8 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm14, byte ptr [r14 + r12 + 7], 9 - pinsrb xmm14, byte ptr [r14 + r8 + 7], 10 - pinsrb xmm14, byte ptr [r14 + rcx + 7], 11 - pinsrb xmm14, byte ptr [r14 + rdi + 7], 12 - pinsrb xmm14, byte ptr [r14 + rdx + 7], 13 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm14, byte ptr [r14 + rdi + 7], 14 - movdqa xmm1, xmm14 - movdqa xmm14, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm2, xmm14 - movdqa xmm0, xmmword ptr [rip + .LCPI5_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm0 - pcmpeqb xmm8, xmm14 - movdqa xmm0, xmmword ptr [rip + .LCPI5_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm8, xmm0 - por xmm8, xmm2 - mov r10, qword ptr [rsp + 128] # 8-byte Reload - movzx esi, byte ptr [r14 + r10 + 20] - movd xmm3, esi - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm1, byte ptr [r14 + rax + 7], 15 - pcmpeqb xmm1, xmm14 - movdqa xmm0, xmmword ptr [rip + .LCPI5_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm1, xmm0 - por xmm1, xmm8 - movzx esi, byte ptr [r14 + r10 + 21] - movd xmm2, esi - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - movdqa xmm0, xmmword ptr [rsp + 240] # 16-byte Reload - pinsrb xmm0, byte ptr [r14 + rdx + 8], 1 - pinsrb xmm0, byte ptr [r14 + r15 + 8], 2 - pinsrb xmm0, byte ptr [r14 + rbx + 8], 3 - mov r15, rbx - mov rbx, r11 - pinsrb xmm0, byte ptr [r14 + r11 + 8], 4 - mov r11, r13 - pinsrb xmm0, byte ptr [r14 + r13 + 8], 5 - mov r13, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + r13 + 8], 6 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + rcx + 8], 7 - pinsrb xmm0, byte ptr [r14 + r9 + 8], 8 - pinsrb xmm0, byte ptr [r14 + r12 + 8], 9 - pinsrb xmm0, byte ptr [r14 + r8 + 8], 10 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + r8 + 8], 11 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + r9 + 8], 12 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + rsi + 8], 13 - pinsrb xmm0, byte ptr [r14 + rdi + 8], 14 - pinsrb xmm0, byte ptr [r14 + rax + 8], 15 - por xmm1, xmm9 - movdqa xmmword ptr [rsp + 240], xmm1 # 16-byte Spill - movzx esi, byte ptr [r14 + r10 + 22] - movd xmm1, esi - pcmpeqb xmm0, xmm14 - pinsrb xmm11, byte ptr [r14 + rdx + 9], 1 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + rax + 9], 2 - pinsrb xmm11, byte ptr [r14 + r15 + 9], 3 - pinsrb xmm11, byte ptr [r14 + rbx + 9], 4 - mov rdx, r11 - pinsrb xmm11, byte ptr [r14 + r11 + 9], 5 - pinsrb xmm11, byte ptr [r14 + r13 + 9], 6 - pinsrb xmm11, byte ptr [r14 + rcx + 9], 7 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + r10 + 9], 8 - mov rcx, r12 - pinsrb xmm11, byte ptr [r14 + r12 + 9], 9 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + rsi + 9], 10 - mov rdx, r8 - pinsrb xmm11, byte ptr [r14 + r8 + 9], 11 - mov rdi, r9 - pinsrb xmm11, byte ptr [r14 + r9 + 9], 12 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + r11 + 9], 13 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + r12 + 9], 14 - mov r8, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + r8 + 9], 15 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm12, byte ptr [r14 + r9 + 10], 1 - pinsrb xmm12, byte ptr [r14 + rax + 10], 2 - pinsrb xmm12, byte ptr [r14 + r15 + 10], 3 - pinsrb xmm12, byte ptr [r14 + rbx + 10], 4 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm12, byte ptr [r14 + rbx + 10], 5 - pinsrb xmm12, byte ptr [r14 + r13 + 10], 6 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm12, byte ptr [r14 + r15 + 10], 7 - pinsrb xmm12, byte ptr [r14 + r10 + 10], 8 - pinsrb xmm12, byte ptr [r14 + rcx + 10], 9 - pinsrb xmm12, byte ptr [r14 + rsi + 10], 10 - pinsrb xmm12, byte ptr [r14 + rdx + 10], 11 - pinsrb xmm12, byte ptr [r14 + rdi + 10], 12 - pinsrb xmm12, byte ptr [r14 + r11 + 10], 13 - pinsrb xmm12, byte ptr [r14 + r12 + 10], 14 - mov r11, r12 - pinsrb xmm12, byte ptr [r14 + r8 + 10], 15 - mov r12, r8 - pinsrb xmm13, byte ptr [r14 + r9 + 11], 1 - pinsrb xmm13, byte ptr [r14 + rax + 11], 2 - mov r8, rax - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + r15 + 11], 3 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + r9 + 11], 4 - pinsrb xmm13, byte ptr [r14 + rbx + 11], 5 - pinsrb xmm13, byte ptr [r14 + r13 + 11], 6 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + rax + 11], 7 - pinsrb xmm13, byte ptr [r14 + r10 + 11], 8 - pinsrb xmm13, byte ptr [r14 + rcx + 11], 9 - pinsrb xmm13, byte ptr [r14 + rsi + 11], 10 - pinsrb xmm13, byte ptr [r14 + rdx + 11], 11 - pinsrb xmm13, byte ptr [r14 + rdi + 11], 12 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + rax + 11], 13 - pinsrb xmm13, byte ptr [r14 + r11 + 11], 14 - pinsrb xmm13, byte ptr [r14 + r12 + 11], 15 - pcmpeqb xmm11, xmm14 - pandn xmm11, xmmword ptr [rip + .LCPI5_16] - paddb xmm11, xmm0 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - movzx esi, byte ptr [r14 + rax + 23] - movd xmm8, esi - pcmpeqb xmm12, xmm14 - pandn xmm12, xmmword ptr [rip + .LCPI5_17] - pcmpeqb xmm13, xmm14 - pandn xmm13, xmmword ptr [rip + .LCPI5_18] + pxor xmm5, xmm0 + packsswb xmm5, xmm5 + pinsrw xmm7, word ptr [rdx + rcx + 6], 1 + pinsrw xmm7, word ptr [rdx + r9 + 6], 2 + pinsrw xmm7, word ptr [rdx + r15 + 6], 3 + pinsrw xmm7, word ptr [rdx + r12 + 6], 4 + pinsrw xmm7, word ptr [rdx + r13 + 6], 5 + pinsrw xmm7, word ptr [rdx + rsi + 6], 6 + pinsrw xmm7, word ptr [rdx + r8 + 6], 7 + pcmpeqw xmm7, xmm11 + packsswb xmm7, xmm7 + pinsrw xmm8, word ptr [rdx + rcx + 8], 1 + pinsrw xmm8, word ptr [rdx + r9 + 8], 2 + pinsrw xmm8, word ptr [rdx + r15 + 8], 3 + pinsrw xmm8, word ptr [rdx + r12 + 8], 4 + pinsrw xmm8, word ptr [rdx + r13 + 8], 5 + pinsrw xmm8, word ptr [rdx + rsi + 8], 6 + pinsrw xmm8, word ptr [rdx + r8 + 8], 7 + psubb xmm3, xmm5 + movdqa xmm12, xmmword ptr [rip + .LCPI5_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm7 + pblendvb xmm12, xmm15, xmm0 + movd xmm7, ebx + movzx eax, word ptr [rdx + r14 + 26] + pcmpeqw xmm8, xmm11 + packsswb xmm8, xmm8 + por xmm12, xmm6 + movdqa xmm13, xmmword ptr [rip + .LCPI5_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm8 + pblendvb xmm13, xmm15, xmm0 + movd xmm6, edi + movzx r10d, word ptr [rdx + r14 + 28] + pinsrw xmm4, word ptr [rdx + rcx + 10], 1 + pinsrw xmm4, word ptr [rdx + r9 + 10], 2 + pinsrw xmm4, word ptr [rdx + r15 + 10], 3 + pinsrw xmm4, word ptr [rdx + r12 + 10], 4 + pinsrw xmm4, word ptr [rdx + r13 + 10], 5 + pinsrw xmm4, word ptr [rdx + rsi + 10], 6 + pinsrw xmm4, word ptr [rdx + r8 + 10], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + pinsrw xmm2, word ptr [rdx + rcx + 12], 1 + pinsrw xmm2, word ptr [rdx + r9 + 12], 2 + pinsrw xmm2, word ptr [rdx + r15 + 12], 3 + pinsrw xmm2, word ptr [rdx + r12 + 12], 4 + pinsrw xmm2, word ptr [rdx + r13 + 12], 5 + pinsrw xmm2, word ptr [rdx + rsi + 12], 6 + por xmm12, xmm3 + movdqa xmm5, xmmword ptr [rip + .LCPI5_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 24] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 30] + pinsrw xmm2, word ptr [rdx + r8 + 12], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm13 + movdqa xmm13, xmmword ptr [rip + .LCPI5_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx edi, word ptr [rdx + r14 + 32] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + rcx + 14], 1 + pinsrw xmm1, word ptr [rdx + r9 + 14], 2 + pinsrw xmm1, word ptr [rdx + r15 + 14], 3 + pinsrw xmm1, word ptr [rdx + r12 + 14], 4 + pinsrw xmm1, word ptr [rdx + r13 + 14], 5 + pinsrw xmm1, word ptr [rdx + rsi + 14], 6 + por xmm13, xmm5 + movd xmm2, r11d + movzx edi, word ptr [rdx + r14 + 34] + mov dword ptr [rsp + 24], edi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + r8 + 14], 7 + pcmpeqw xmm1, xmm11 + pinsrw xmm6, word ptr [rdx + rcx + 18], 1 + pinsrw xmm6, word ptr [rdx + r9 + 18], 2 + pinsrw xmm6, word ptr [rdx + r15 + 18], 3 + pinsrw xmm6, word ptr [rdx + r12 + 18], 4 + pinsrw xmm6, word ptr [rdx + r13 + 18], 5 + pinsrw xmm6, word ptr [rdx + rsi + 18], 6 + packsswb xmm1, xmm1 + pinsrw xmm6, word ptr [rdx + r8 + 18], 7 + pcmpeqw xmm6, xmm11 + packsswb xmm6, xmm6 por xmm13, xmm12 - movzx esi, byte ptr [r14 + rax + 24] - movd xmm12, esi - movdqa xmm9, xmmword ptr [rsp + 208] # 16-byte Reload - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 12], 1 - mov r12, r8 - pinsrb xmm9, byte ptr [r14 + r8 + 12], 2 - pinsrb xmm9, byte ptr [r14 + r15 + 12], 3 - mov rbx, r9 - pinsrb xmm9, byte ptr [r14 + r9 + 12], 4 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r9 + 12], 5 - mov r11, r13 - pinsrb xmm9, byte ptr [r14 + r13 + 12], 6 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r8 + 12], 7 - mov rsi, r10 - pinsrb xmm9, byte ptr [r14 + r10 + 12], 8 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rcx + 12], 9 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r10 + 12], 10 - pinsrb xmm9, byte ptr [r14 + rdx + 12], 11 - pinsrb xmm9, byte ptr [r14 + rdi + 12], 12 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r13 + 12], 13 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 12], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 12], 15 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rax + 13], 1 - pinsrb xmm6, byte ptr [r14 + r12 + 13], 2 - pinsrb xmm6, byte ptr [r14 + r15 + 13], 3 - pinsrb xmm6, byte ptr [r14 + rbx + 13], 4 - pinsrb xmm6, byte ptr [r14 + r9 + 13], 5 - pinsrb xmm6, byte ptr [r14 + r11 + 13], 6 - pinsrb xmm6, byte ptr [r14 + r8 + 13], 7 - pinsrb xmm6, byte ptr [r14 + rsi + 13], 8 - pinsrb xmm6, byte ptr [r14 + rcx + 13], 9 - pinsrb xmm6, byte ptr [r14 + r10 + 13], 10 - pinsrb xmm6, byte ptr [r14 + rdx + 13], 11 - pinsrb xmm6, byte ptr [r14 + rdi + 13], 12 - pinsrb xmm6, byte ptr [r14 + r13 + 13], 13 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rax + 13], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rax + 13], 15 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [r14 + rax + 14], 1 - pinsrb xmm15, byte ptr [r14 + r12 + 14], 2 - pinsrb xmm15, byte ptr [r14 + r15 + 14], 3 - pinsrb xmm15, byte ptr [r14 + rbx + 14], 4 - pinsrb xmm15, byte ptr [r14 + r9 + 14], 5 - pinsrb xmm15, byte ptr [r14 + r11 + 14], 6 - pinsrb xmm15, byte ptr [r14 + r8 + 14], 7 - pinsrb xmm15, byte ptr [r14 + rsi + 14], 8 - pinsrb xmm15, byte ptr [r14 + rcx + 14], 9 - pinsrb xmm15, byte ptr [r14 + r10 + 14], 10 - pinsrb xmm15, byte ptr [r14 + rdx + 14], 11 - pinsrb xmm15, byte ptr [r14 + rdi + 14], 12 - pinsrb xmm15, byte ptr [r14 + r13 + 14], 13 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm15, byte ptr [r14 + r12 + 14], 14 - pcmpeqb xmm9, xmm14 - pandn xmm9, xmmword ptr [rip + .LCPI5_19] - por xmm9, xmm13 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - movzx esi, byte ptr [r14 + r15 + 25] - movd xmm13, esi - psubb xmm11, xmmword ptr [rip + .LCPI5_22] - por xmm9, xmm11 - movzx esi, byte ptr [r14 + r15 + 26] - movd xmm0, esi - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm15, byte ptr [r14 + rbx + 14], 15 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmmword ptr [rip + .LCPI5_20] - pcmpeqb xmm15, xmm14 - pandn xmm15, xmmword ptr [rip + .LCPI5_21] - por xmm15, xmm6 - movzx esi, byte ptr [r14 + r15 + 27] - movd xmm11, esi - movdqa xmm6, xmmword ptr [rsp + 192] # 16-byte Reload - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rax + 15], 1 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rdi + 15], 2 - mov rdx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rdx + 15], 3 - mov rcx, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rcx + 15], 4 - pinsrb xmm6, byte ptr [r14 + r9 + 15], 5 - pinsrb xmm6, byte ptr [r14 + r11 + 15], 6 - pinsrb xmm6, byte ptr [r14 + r8 + 15], 7 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r8 + 15], 8 - mov r9, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r9 + 15], 9 - pinsrb xmm6, byte ptr [r14 + r10 + 15], 10 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r10 + 15], 11 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rsi + 15], 12 - pinsrb xmm6, byte ptr [r14 + r13 + 15], 13 - pinsrb xmm6, byte ptr [r14 + r12 + 15], 14 - pinsrb xmm6, byte ptr [r14 + rbx + 15], 15 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmmword ptr [rip + .LCPI5_6] - por xmm6, xmm15 - movzx esi, byte ptr [r14 + r15 + 28] - movd xmm15, esi - por xmm6, xmm9 - movdqa xmmword ptr [rsp + 192], xmm6 # 16-byte Spill - movzx esi, byte ptr [r14 + r15 + 29] - movd xmm9, esi - pinsrb xmm10, byte ptr [r14 + rax + 16], 1 - pinsrb xmm10, byte ptr [r14 + rdi + 16], 2 - pinsrb xmm10, byte ptr [r14 + rdx + 16], 3 - pinsrb xmm10, byte ptr [r14 + rcx + 16], 4 - mov rsi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rsi + 16], 5 - pinsrb xmm10, byte ptr [r14 + r11 + 16], 6 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rsi + 16], 7 - pinsrb xmm10, byte ptr [r14 + r8 + 16], 8 - pinsrb xmm10, byte ptr [r14 + r9 + 16], 9 - mov rsi, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rsi + 16], 10 - pinsrb xmm10, byte ptr [r14 + r10 + 16], 11 - mov rsi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rsi + 16], 12 - pinsrb xmm10, byte ptr [r14 + r13 + 16], 13 - pinsrb xmm10, byte ptr [r14 + r12 + 16], 14 - pinsrb xmm10, byte ptr [r14 + rbx + 16], 15 - pinsrb xmm4, byte ptr [r14 + rax + 17], 1 - pinsrb xmm4, byte ptr [r14 + rdi + 17], 2 - pinsrb xmm4, byte ptr [r14 + rdx + 17], 3 - pinsrb xmm4, byte ptr [r14 + rcx + 17], 4 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + r9 + 17], 5 - pinsrb xmm4, byte ptr [r14 + r11 + 17], 6 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + r8 + 17], 7 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rdi + 17], 8 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rcx + 17], 9 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + r10 + 17], 10 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rdx + 17], 11 - pinsrb xmm4, byte ptr [r14 + rsi + 17], 12 - pinsrb xmm4, byte ptr [r14 + r13 + 17], 13 - pinsrb xmm4, byte ptr [r14 + r12 + 17], 14 - pinsrb xmm4, byte ptr [r14 + rbx + 17], 15 - pcmpeqb xmm10, xmm14 - pcmpeqb xmm4, xmm14 - movdqa xmm6, xmmword ptr [rip + .LCPI5_16] # xmm6 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] - pandn xmm4, xmm6 - paddb xmm4, xmm10 - movzx esi, byte ptr [r14 + r15 + 30] - movd xmm10, esi - mov rsi, rax - pinsrb xmm7, byte ptr [r14 + rax + 18], 1 - pinsrb xmm5, byte ptr [r14 + rax + 19], 1 - pinsrb xmm3, byte ptr [r14 + rax + 20], 1 - pinsrb xmm2, byte ptr [r14 + rax + 21], 1 - pinsrb xmm1, byte ptr [r14 + rax + 22], 1 - pinsrb xmm8, byte ptr [r14 + rax + 23], 1 - pinsrb xmm12, byte ptr [r14 + rax + 24], 1 - pinsrb xmm13, byte ptr [r14 + rax + 25], 1 - pinsrb xmm0, byte ptr [r14 + rax + 26], 1 - pinsrb xmm11, byte ptr [r14 + rax + 27], 1 - pinsrb xmm15, byte ptr [r14 + rax + 28], 1 - pinsrb xmm9, byte ptr [r14 + rax + 29], 1 - pinsrb xmm10, byte ptr [r14 + rax + 30], 1 - movzx eax, byte ptr [r14 + r15 + 31] - movd xmm6, eax - pinsrb xmm6, byte ptr [r14 + rsi + 31], 1 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 18], 2 - pinsrb xmm5, byte ptr [r14 + rax + 19], 2 - pinsrb xmm3, byte ptr [r14 + rax + 20], 2 - pinsrb xmm2, byte ptr [r14 + rax + 21], 2 - pinsrb xmm1, byte ptr [r14 + rax + 22], 2 - pinsrb xmm8, byte ptr [r14 + rax + 23], 2 - pinsrb xmm12, byte ptr [r14 + rax + 24], 2 - pinsrb xmm13, byte ptr [r14 + rax + 25], 2 - pinsrb xmm0, byte ptr [r14 + rax + 26], 2 - pinsrb xmm11, byte ptr [r14 + rax + 27], 2 - pinsrb xmm15, byte ptr [r14 + rax + 28], 2 - pinsrb xmm9, byte ptr [r14 + rax + 29], 2 - pinsrb xmm10, byte ptr [r14 + rax + 30], 2 - pinsrb xmm6, byte ptr [r14 + rax + 31], 2 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + r15 + 18], 3 - mov rax, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 18], 4 - pinsrb xmm7, byte ptr [r14 + r9 + 18], 5 - pinsrb xmm7, byte ptr [r14 + r11 + 18], 6 - pinsrb xmm7, byte ptr [r14 + r8 + 18], 7 - mov rsi, rdi - pinsrb xmm7, byte ptr [r14 + rdi + 18], 8 - pinsrb xmm7, byte ptr [r14 + rcx + 18], 9 - pinsrb xmm7, byte ptr [r14 + r10 + 18], 10 - pinsrb xmm7, byte ptr [r14 + rdx + 18], 11 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rdi + 18], 12 - pinsrb xmm7, byte ptr [r14 + r13 + 18], 13 - pinsrb xmm7, byte ptr [r14 + r12 + 18], 14 - pinsrb xmm7, byte ptr [r14 + rbx + 18], 15 - pinsrb xmm5, byte ptr [r14 + r15 + 19], 3 - pinsrb xmm5, byte ptr [r14 + rax + 19], 4 - pinsrb xmm5, byte ptr [r14 + r9 + 19], 5 - pinsrb xmm5, byte ptr [r14 + r11 + 19], 6 - pinsrb xmm5, byte ptr [r14 + r8 + 19], 7 - pinsrb xmm5, byte ptr [r14 + rsi + 19], 8 - pinsrb xmm5, byte ptr [r14 + rcx + 19], 9 - pinsrb xmm5, byte ptr [r14 + r10 + 19], 10 - pinsrb xmm5, byte ptr [r14 + rdx + 19], 11 - pinsrb xmm5, byte ptr [r14 + rdi + 19], 12 - pinsrb xmm5, byte ptr [r14 + r13 + 19], 13 - pinsrb xmm5, byte ptr [r14 + r12 + 19], 14 - pinsrb xmm5, byte ptr [r14 + rbx + 19], 15 - pinsrb xmm3, byte ptr [r14 + r15 + 20], 3 - pinsrb xmm3, byte ptr [r14 + rax + 20], 4 - pinsrb xmm3, byte ptr [r14 + r9 + 20], 5 - pinsrb xmm3, byte ptr [r14 + r11 + 20], 6 - pinsrb xmm3, byte ptr [r14 + r8 + 20], 7 - pinsrb xmm3, byte ptr [r14 + rsi + 20], 8 - pinsrb xmm3, byte ptr [r14 + rcx + 20], 9 - pinsrb xmm3, byte ptr [r14 + r10 + 20], 10 - pinsrb xmm3, byte ptr [r14 + rdx + 20], 11 - pinsrb xmm3, byte ptr [r14 + rdi + 20], 12 - pinsrb xmm3, byte ptr [r14 + r13 + 20], 13 - pinsrb xmm3, byte ptr [r14 + r12 + 20], 14 - pcmpeqb xmm7, xmm14 - movdqa xmm14, xmmword ptr [rip + .LCPI5_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm7, xmm14 - pcmpeqb xmm5, xmmword ptr [rsp + 176] # 16-byte Folded Reload - movdqa xmm14, xmmword ptr [rip + .LCPI5_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm5, xmm14 - por xmm5, xmm7 - pinsrb xmm3, byte ptr [r14 + rbx + 20], 15 - movdqa xmm14, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm3, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI5_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm3, xmm7 - por xmm3, xmm5 - pcmpeqd xmm5, xmm5 - psubb xmm4, xmm5 - por xmm3, xmm4 - pinsrb xmm2, byte ptr [r14 + r15 + 21], 3 - pinsrb xmm2, byte ptr [r14 + rax + 21], 4 - pinsrb xmm2, byte ptr [r14 + r9 + 21], 5 - pinsrb xmm2, byte ptr [r14 + r11 + 21], 6 - pinsrb xmm2, byte ptr [r14 + r8 + 21], 7 - pinsrb xmm2, byte ptr [r14 + rsi + 21], 8 - pinsrb xmm2, byte ptr [r14 + rcx + 21], 9 - pinsrb xmm2, byte ptr [r14 + r10 + 21], 10 - pinsrb xmm2, byte ptr [r14 + rdx + 21], 11 - pinsrb xmm2, byte ptr [r14 + rdi + 21], 12 - pinsrb xmm2, byte ptr [r14 + r13 + 21], 13 - pinsrb xmm2, byte ptr [r14 + r12 + 21], 14 - pinsrb xmm2, byte ptr [r14 + rbx + 21], 15 - pinsrb xmm1, byte ptr [r14 + r15 + 22], 3 - pinsrb xmm1, byte ptr [r14 + rax + 22], 4 - pinsrb xmm1, byte ptr [r14 + r9 + 22], 5 - pinsrb xmm1, byte ptr [r14 + r11 + 22], 6 - pinsrb xmm1, byte ptr [r14 + r8 + 22], 7 - pinsrb xmm1, byte ptr [r14 + rsi + 22], 8 - pinsrb xmm1, byte ptr [r14 + rcx + 22], 9 - pinsrb xmm1, byte ptr [r14 + r10 + 22], 10 - pinsrb xmm1, byte ptr [r14 + rdx + 22], 11 - pinsrb xmm1, byte ptr [r14 + rdi + 22], 12 - pinsrb xmm1, byte ptr [r14 + r13 + 22], 13 - pinsrb xmm1, byte ptr [r14 + r12 + 22], 14 - pinsrb xmm1, byte ptr [r14 + rbx + 22], 15 - pinsrb xmm8, byte ptr [r14 + r15 + 23], 3 - pinsrb xmm8, byte ptr [r14 + rax + 23], 4 - pinsrb xmm8, byte ptr [r14 + r9 + 23], 5 - pinsrb xmm8, byte ptr [r14 + r11 + 23], 6 - pinsrb xmm8, byte ptr [r14 + r8 + 23], 7 - pinsrb xmm8, byte ptr [r14 + rsi + 23], 8 - pinsrb xmm8, byte ptr [r14 + rcx + 23], 9 - pinsrb xmm8, byte ptr [r14 + r10 + 23], 10 - pinsrb xmm8, byte ptr [r14 + rdx + 23], 11 - pinsrb xmm8, byte ptr [r14 + rdi + 23], 12 - pinsrb xmm8, byte ptr [r14 + r13 + 23], 13 - pinsrb xmm8, byte ptr [r14 + r12 + 23], 14 - pcmpeqb xmm2, xmm14 - movdqa xmm5, xmmword ptr [rip + .LCPI5_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm5 - pcmpeqb xmm1, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI5_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm1, xmm7 - por xmm1, xmm2 - pinsrb xmm8, byte ptr [r14 + rbx + 23], 15 - pcmpeqb xmm8, xmm14 - movdqa xmm4, xmmword ptr [rip + .LCPI5_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm8, xmm4 - por xmm8, xmm1 - pinsrb xmm12, byte ptr [r14 + r15 + 24], 3 - pinsrb xmm12, byte ptr [r14 + rax + 24], 4 - pinsrb xmm12, byte ptr [r14 + r9 + 24], 5 - pinsrb xmm12, byte ptr [r14 + r11 + 24], 6 - pinsrb xmm12, byte ptr [r14 + r8 + 24], 7 - pinsrb xmm12, byte ptr [r14 + rsi + 24], 8 - pinsrb xmm12, byte ptr [r14 + rcx + 24], 9 - pinsrb xmm12, byte ptr [r14 + r10 + 24], 10 - pinsrb xmm12, byte ptr [r14 + rdx + 24], 11 - pinsrb xmm12, byte ptr [r14 + rdi + 24], 12 - pinsrb xmm12, byte ptr [r14 + r13 + 24], 13 - pinsrb xmm12, byte ptr [r14 + r12 + 24], 14 - pinsrb xmm12, byte ptr [r14 + rbx + 24], 15 - por xmm8, xmm3 - pcmpeqb xmm12, xmm14 - pinsrb xmm13, byte ptr [r14 + r15 + 25], 3 - pinsrb xmm13, byte ptr [r14 + rax + 25], 4 - pinsrb xmm13, byte ptr [r14 + r9 + 25], 5 - pinsrb xmm13, byte ptr [r14 + r11 + 25], 6 - pinsrb xmm13, byte ptr [r14 + r8 + 25], 7 - pinsrb xmm13, byte ptr [r14 + rsi + 25], 8 - pinsrb xmm13, byte ptr [r14 + rcx + 25], 9 - pinsrb xmm13, byte ptr [r14 + r10 + 25], 10 - pinsrb xmm13, byte ptr [r14 + rdx + 25], 11 - pinsrb xmm13, byte ptr [r14 + rdi + 25], 12 - pinsrb xmm13, byte ptr [r14 + r13 + 25], 13 - pinsrb xmm13, byte ptr [r14 + r12 + 25], 14 - pinsrb xmm13, byte ptr [r14 + rbx + 25], 15 - pinsrb xmm0, byte ptr [r14 + r15 + 26], 3 - pinsrb xmm0, byte ptr [r14 + rax + 26], 4 - pinsrb xmm0, byte ptr [r14 + r9 + 26], 5 - pinsrb xmm0, byte ptr [r14 + r11 + 26], 6 - pinsrb xmm0, byte ptr [r14 + r8 + 26], 7 - pinsrb xmm0, byte ptr [r14 + rsi + 26], 8 - pinsrb xmm0, byte ptr [r14 + rcx + 26], 9 - pinsrb xmm0, byte ptr [r14 + r10 + 26], 10 - pinsrb xmm0, byte ptr [r14 + rdx + 26], 11 - pinsrb xmm0, byte ptr [r14 + rdi + 26], 12 - pinsrb xmm0, byte ptr [r14 + r13 + 26], 13 - pinsrb xmm0, byte ptr [r14 + r12 + 26], 14 - pinsrb xmm0, byte ptr [r14 + rbx + 26], 15 - pinsrb xmm11, byte ptr [r14 + r15 + 27], 3 - pinsrb xmm11, byte ptr [r14 + rax + 27], 4 - pinsrb xmm11, byte ptr [r14 + r9 + 27], 5 - pinsrb xmm11, byte ptr [r14 + r11 + 27], 6 - pinsrb xmm11, byte ptr [r14 + r8 + 27], 7 - pinsrb xmm11, byte ptr [r14 + rsi + 27], 8 - pinsrb xmm11, byte ptr [r14 + rcx + 27], 9 - pinsrb xmm11, byte ptr [r14 + r10 + 27], 10 - pinsrb xmm11, byte ptr [r14 + rdx + 27], 11 - pinsrb xmm11, byte ptr [r14 + rdi + 27], 12 - pinsrb xmm11, byte ptr [r14 + r13 + 27], 13 - pinsrb xmm11, byte ptr [r14 + r12 + 27], 14 - pcmpeqb xmm13, xmm14 - pandn xmm13, xmmword ptr [rip + .LCPI5_16] - paddb xmm13, xmm12 - pinsrb xmm11, byte ptr [r14 + rbx + 27], 15 - pcmpeqb xmm0, xmm14 - pandn xmm0, xmmword ptr [rip + .LCPI5_17] - pcmpeqb xmm11, xmm14 - pandn xmm11, xmmword ptr [rip + .LCPI5_18] - por xmm11, xmm0 - pinsrb xmm15, byte ptr [r14 + r15 + 28], 3 - pinsrb xmm9, byte ptr [r14 + r15 + 29], 3 - pinsrb xmm10, byte ptr [r14 + r15 + 30], 3 - pinsrb xmm6, byte ptr [r14 + r15 + 31], 3 - pinsrb xmm15, byte ptr [r14 + rax + 28], 4 - pinsrb xmm9, byte ptr [r14 + rax + 29], 4 - pinsrb xmm10, byte ptr [r14 + rax + 30], 4 - pinsrb xmm6, byte ptr [r14 + rax + 31], 4 - mov rax, r9 - pinsrb xmm15, byte ptr [r14 + r9 + 28], 5 - pinsrb xmm9, byte ptr [r14 + r9 + 29], 5 - pinsrb xmm10, byte ptr [r14 + r9 + 30], 5 - pinsrb xmm6, byte ptr [r14 + r9 + 31], 5 - pinsrb xmm15, byte ptr [r14 + r11 + 28], 6 - pinsrb xmm9, byte ptr [r14 + r11 + 29], 6 - pinsrb xmm10, byte ptr [r14 + r11 + 30], 6 - pinsrb xmm6, byte ptr [r14 + r11 + 31], 6 - mov rax, r8 - pinsrb xmm15, byte ptr [r14 + r8 + 28], 7 - pinsrb xmm9, byte ptr [r14 + r8 + 29], 7 - pinsrb xmm10, byte ptr [r14 + r8 + 30], 7 - pinsrb xmm6, byte ptr [r14 + r8 + 31], 7 - mov rax, rsi - pinsrb xmm15, byte ptr [r14 + rsi + 28], 8 - pinsrb xmm9, byte ptr [r14 + rsi + 29], 8 - pinsrb xmm10, byte ptr [r14 + rsi + 30], 8 - pinsrb xmm6, byte ptr [r14 + rsi + 31], 8 + movdqa xmm12, xmmword ptr [rip + .LCPI5_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm12, xmm15, xmm0 + movdqa xmm8, xmm9 + movdqa xmm0, xmm6 + pblendvb xmm8, xmm15, xmm0 + movd xmm1, eax + movzx r11d, word ptr [rdx + r14 + 36] + pinsrw xmm7, word ptr [rdx + rcx + 16], 1 + pinsrw xmm7, word ptr [rdx + r9 + 16], 2 + pinsrw xmm7, word ptr [rdx + r15 + 16], 3 + pinsrw xmm7, word ptr [rdx + r12 + 16], 4 + pinsrw xmm7, word ptr [rdx + r13 + 16], 5 + pinsrw xmm7, word ptr [rdx + rsi + 16], 6 + pinsrw xmm4, word ptr [rdx + rcx + 20], 1 + pinsrw xmm4, word ptr [rdx + r9 + 20], 2 + pinsrw xmm4, word ptr [rdx + r15 + 20], 3 + pinsrw xmm4, word ptr [rdx + r12 + 20], 4 + pinsrw xmm4, word ptr [rdx + r13 + 20], 5 + pinsrw xmm4, word ptr [rdx + rsi + 20], 6 + pinsrw xmm4, word ptr [rdx + r8 + 20], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm12, xmm13 + movdqa xmm5, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, r10d + movzx edi, word ptr [rdx + r14 + 38] + pinsrw xmm7, word ptr [rdx + r8 + 16], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI5_22] + packsswb xmm7, xmm7 + pinsrw xmm3, word ptr [rdx + rcx + 22], 1 + pinsrw xmm3, word ptr [rdx + r9 + 22], 2 + pinsrw xmm3, word ptr [rdx + r15 + 22], 3 + pinsrw xmm3, word ptr [rdx + r12 + 22], 4 + pinsrw xmm3, word ptr [rdx + r13 + 22], 5 + pinsrw xmm3, word ptr [rdx + rsi + 22], 6 + pinsrw xmm3, word ptr [rdx + r8 + 22], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rdx + rcx + 24], 1 + pinsrw xmm2, word ptr [rdx + r9 + 24], 2 + pinsrw xmm2, word ptr [rdx + r15 + 24], 3 + pinsrw xmm2, word ptr [rdx + r12 + 24], 4 + pinsrw xmm2, word ptr [rdx + r13 + 24], 5 + pinsrw xmm2, word ptr [rdx + rsi + 24], 6 + pinsrw xmm2, word ptr [rdx + r8 + 24], 7 + psubb xmm8, xmm7 + movdqa xmm10, xmmword ptr [rip + .LCPI5_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm14, xmm10 + movdqa xmm0, xmm3 + pblendvb xmm14, xmm15, xmm0 + movd xmm3, ebx + movzx eax, word ptr [rdx + r14 + 40] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm14, xmm5 + movdqa xmm9, xmmword ptr [rip + .LCPI5_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm7, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r10d, word ptr [rdx + r14 + 42] + pinsrw xmm1, word ptr [rdx + rcx + 26], 1 + pinsrw xmm1, word ptr [rdx + r9 + 26], 2 + pinsrw xmm1, word ptr [rdx + r15 + 26], 3 + pinsrw xmm1, word ptr [rdx + r12 + 26], 4 + pinsrw xmm1, word ptr [rdx + r13 + 26], 5 + pinsrw xmm1, word ptr [rdx + rsi + 26], 6 + pinsrw xmm1, word ptr [rdx + r8 + 26], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm4, word ptr [rdx + rcx + 28], 1 + pinsrw xmm4, word ptr [rdx + r9 + 28], 2 + pinsrw xmm4, word ptr [rdx + r15 + 28], 3 + pinsrw xmm4, word ptr [rdx + r12 + 28], 4 + pinsrw xmm4, word ptr [rdx + r13 + 28], 5 + pinsrw xmm4, word ptr [rdx + rsi + 28], 6 + por xmm14, xmm8 + movdqa xmm5, xmmword ptr [rip + .LCPI5_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm2, dword ptr [rsp + 24] # 4-byte Folded Reload + # xmm2 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 44] + mov dword ptr [rsp + 16], ebx # 4-byte Spill + pinsrw xmm4, word ptr [rdx + r8 + 28], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm5, xmm13 + movdqa xmm6, xmmword ptr [rip + .LCPI5_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, r11d + movzx ebx, word ptr [rdx + r14 + 46] + mov dword ptr [rsp + 24], ebx # 4-byte Spill + pinsrw xmm3, word ptr [rdx + rcx + 30], 1 + pinsrw xmm3, word ptr [rdx + r9 + 30], 2 + pinsrw xmm3, word ptr [rdx + r15 + 30], 3 + pinsrw xmm3, word ptr [rdx + r12 + 30], 4 + pinsrw xmm3, word ptr [rdx + r13 + 30], 5 + pinsrw xmm3, word ptr [rdx + rsi + 30], 6 + por xmm6, xmm5 + movd xmm1, edi + movzx edi, word ptr [rdx + r14 + 48] + pinsrw xmm3, word ptr [rdx + r8 + 30], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm2, word ptr [rdx + rcx + 34], 1 + pinsrw xmm2, word ptr [rdx + r9 + 34], 2 + pinsrw xmm2, word ptr [rdx + r15 + 34], 3 + pinsrw xmm2, word ptr [rdx + r12 + 34], 4 + pinsrw xmm2, word ptr [rdx + r13 + 34], 5 + pinsrw xmm2, word ptr [rdx + rsi + 34], 6 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rdx + r8 + 34], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm6, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI5_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm14 + movdqa xmm0, xmm3 + pblendvb xmm13, xmm15, xmm0 + movdqa xmm8, xmmword ptr [rip + .LCPI5_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm8, xmm15, xmm0 + movd xmm2, eax + movzx r11d, word ptr [rdx + r14 + 50] + pinsrw xmm7, word ptr [rdx + rcx + 32], 1 + pinsrw xmm7, word ptr [rdx + r9 + 32], 2 + pinsrw xmm7, word ptr [rdx + r15 + 32], 3 + pinsrw xmm7, word ptr [rdx + r12 + 32], 4 + pinsrw xmm7, word ptr [rdx + r13 + 32], 5 + pinsrw xmm7, word ptr [rdx + rsi + 32], 6 + pinsrw xmm4, word ptr [rdx + rcx + 36], 1 + pinsrw xmm4, word ptr [rdx + r9 + 36], 2 + pinsrw xmm4, word ptr [rdx + r15 + 36], 3 + pinsrw xmm4, word ptr [rdx + r12 + 36], 4 + pinsrw xmm4, word ptr [rdx + r13 + 36], 5 + pinsrw xmm4, word ptr [rdx + rsi + 36], 6 + pinsrw xmm4, word ptr [rdx + r8 + 36], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm13, xmm6 + movdqa xmm6, xmmword ptr [rip + .LCPI5_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm3, r10d + movzx r10d, word ptr [rdx + r14 + 52] + pinsrw xmm7, word ptr [rdx + r8 + 32], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI5_22] + packsswb xmm7, xmm7 + pinsrw xmm1, word ptr [rdx + rcx + 38], 1 + pinsrw xmm1, word ptr [rdx + r9 + 38], 2 + pinsrw xmm1, word ptr [rdx + r15 + 38], 3 + pinsrw xmm1, word ptr [rdx + r12 + 38], 4 + pinsrw xmm1, word ptr [rdx + r13 + 38], 5 + pinsrw xmm1, word ptr [rdx + rsi + 38], 6 + pinsrw xmm1, word ptr [rdx + r8 + 38], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm2, word ptr [rdx + rcx + 40], 1 + pinsrw xmm2, word ptr [rdx + r9 + 40], 2 + pinsrw xmm2, word ptr [rdx + r15 + 40], 3 + pinsrw xmm2, word ptr [rdx + r12 + 40], 4 + pinsrw xmm2, word ptr [rdx + r13 + 40], 5 + pinsrw xmm2, word ptr [rdx + rsi + 40], 6 + pinsrw xmm2, word ptr [rdx + r8 + 40], 7 + psubb xmm8, xmm7 + movdqa xmm5, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm1, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx eax, word ptr [rdx + r14 + 54] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm6 + movdqa xmm6, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 24] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 56] + pinsrw xmm3, word ptr [rdx + rcx + 42], 1 + pinsrw xmm3, word ptr [rdx + r9 + 42], 2 + pinsrw xmm3, word ptr [rdx + r15 + 42], 3 + pinsrw xmm3, word ptr [rdx + r12 + 42], 4 + pinsrw xmm3, word ptr [rdx + r13 + 42], 5 + pinsrw xmm3, word ptr [rdx + rsi + 42], 6 + pinsrw xmm3, word ptr [rdx + r8 + 42], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rdx + rcx + 44], 1 + pinsrw xmm1, word ptr [rdx + r9 + 44], 2 + pinsrw xmm1, word ptr [rdx + r15 + 44], 3 + pinsrw xmm1, word ptr [rdx + r12 + 44], 4 + pinsrw xmm1, word ptr [rdx + r13 + 44], 5 + pinsrw xmm1, word ptr [rdx + rsi + 44], 6 + por xmm5, xmm8 + movdqa xmm9, xmmword ptr [rip + .LCPI5_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm2, xmm9 + movdqa xmm0, xmm3 + pblendvb xmm2, xmm15, xmm0 + movd xmm7, edi + movzx edi, word ptr [rdx + r14 + 58] + pinsrw xmm1, word ptr [rdx + r8 + 44], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm2, xmm6 + movdqa xmm10, xmmword ptr [rip + .LCPI5_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r11d + movzx r11d, word ptr [rdx + r14 + 60] + por xmm6, xmm2 + movd xmm2, r10d + pinsrw xmm4, word ptr [rdx + rcx + 46], 1 + pinsrw xmm4, word ptr [rdx + r9 + 46], 2 + pinsrw xmm4, word ptr [rdx + r15 + 46], 3 + pinsrw xmm4, word ptr [rdx + r12 + 46], 4 + pinsrw xmm4, word ptr [rdx + r13 + 46], 5 + pinsrw xmm4, word ptr [rdx + rsi + 46], 6 + pinsrw xmm4, word ptr [rdx + r8 + 46], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm6, xmm5 + movdqa xmm8, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm8, xmm15, xmm0 + movd xmm3, eax + pinsrw xmm1, word ptr [rdx + rcx + 50], 1 + pinsrw xmm1, word ptr [rdx + r9 + 50], 2 + pinsrw xmm1, word ptr [rdx + r15 + 50], 3 + pinsrw xmm1, word ptr [rdx + r12 + 50], 4 + pinsrw xmm1, word ptr [rdx + r13 + 50], 5 + pinsrw xmm1, word ptr [rdx + rsi + 50], 6 + pinsrw xmm1, word ptr [rdx + r8 + 50], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm8, xmm6 + movdqa xmm4, xmmword ptr [rip + .LCPI5_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movd xmm1, ebx + pinsrw xmm7, word ptr [rdx + rcx + 48], 1 + pinsrw xmm7, word ptr [rdx + r9 + 48], 2 + pinsrw xmm7, word ptr [rdx + r15 + 48], 3 + pinsrw xmm7, word ptr [rdx + r12 + 48], 4 + pinsrw xmm7, word ptr [rdx + r13 + 48], 5 + pinsrw xmm7, word ptr [rdx + rsi + 48], 6 + pinsrw xmm7, word ptr [rdx + r8 + 48], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI5_22] + pinsrw xmm2, word ptr [rdx + rcx + 52], 1 + pinsrw xmm2, word ptr [rdx + r9 + 52], 2 + pinsrw xmm2, word ptr [rdx + r15 + 52], 3 + pinsrw xmm2, word ptr [rdx + r12 + 52], 4 + pinsrw xmm2, word ptr [rdx + r13 + 52], 5 + pinsrw xmm2, word ptr [rdx + rsi + 52], 6 + packsswb xmm7, xmm7 + pinsrw xmm2, word ptr [rdx + r8 + 52], 7 + pcmpeqw xmm2, xmm11 + pinsrw xmm3, word ptr [rdx + rcx + 54], 1 + pinsrw xmm3, word ptr [rdx + r9 + 54], 2 + pinsrw xmm3, word ptr [rdx + r15 + 54], 3 + pinsrw xmm3, word ptr [rdx + r12 + 54], 4 + pinsrw xmm3, word ptr [rdx + r13 + 54], 5 + pinsrw xmm3, word ptr [rdx + rsi + 54], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rdx + r8 + 54], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm1, word ptr [rdx + rcx + 56], 1 + pinsrw xmm1, word ptr [rdx + r9 + 56], 2 + pinsrw xmm1, word ptr [rdx + r15 + 56], 3 + pinsrw xmm1, word ptr [rdx + r12 + 56], 4 + pinsrw xmm1, word ptr [rdx + r13 + 56], 5 + pinsrw xmm1, word ptr [rdx + rsi + 56], 6 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rdx + r8 + 56], 7 + psubb xmm4, xmm7 + movdqa xmm5, xmmword ptr [rip + .LCPI5_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm5, xmm15, xmm0 + movdqa xmm6, xmmword ptr [rip + .LCPI5_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm3 + pblendvb xmm6, xmm15, xmm0 + movd xmm2, edi + pcmpeqw xmm1, xmm11 + pinsrw xmm2, word ptr [rdx + rcx + 58], 1 + pinsrw xmm2, word ptr [rdx + r9 + 58], 2 + pinsrw xmm2, word ptr [rdx + r15 + 58], 3 + pinsrw xmm2, word ptr [rdx + r12 + 58], 4 + pinsrw xmm2, word ptr [rdx + r13 + 58], 5 + pinsrw xmm2, word ptr [rdx + rsi + 58], 6 + pinsrw xmm2, word ptr [rdx + r8 + 58], 7 + packsswb xmm1, xmm1 + pcmpeqw xmm2, xmm11 + por xmm6, xmm5 + movd xmm3, r11d + pinsrw xmm3, word ptr [rdx + rcx + 60], 1 + pinsrw xmm3, word ptr [rdx + r9 + 60], 2 + pinsrw xmm3, word ptr [rdx + r15 + 60], 3 + pinsrw xmm3, word ptr [rdx + r12 + 60], 4 + pinsrw xmm3, word ptr [rdx + r13 + 60], 5 + pinsrw xmm3, word ptr [rdx + rsi + 60], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rdx + r8 + 60], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + por xmm6, xmm4 + movdqa xmm4, xmmword ptr [rip + .LCPI5_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movdqa xmm1, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm1, xmm15, xmm0 + movdqa xmm0, xmm3 + pblendvb xmm10, xmm15, xmm0 + por xmm1, xmm4 + movzx eax, word ptr [rdx + r14 + 62] + por xmm10, xmm1 + movd xmm0, eax + pinsrw xmm0, word ptr [rdx + rcx + 62], 1 + pinsrw xmm0, word ptr [rdx + r9 + 62], 2 + pinsrw xmm0, word ptr [rdx + r15 + 62], 3 + pinsrw xmm0, word ptr [rdx + r12 + 62], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + pinsrw xmm0, word ptr [rdx + r13 + 62], 5 + pinsrw xmm0, word ptr [rdx + rsi + 62], 6 + pinsrw xmm0, word ptr [rdx + r8 + 62], 7 + pcmpeqw xmm0, xmm11 + packsswb xmm0, xmm0 + por xmm10, xmm6 + pblendvb xmm14, xmm15, xmm0 + por xmm14, xmm10 + movdqa xmm0, xmm12 + punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] + movdqa xmm2, xmm8 + punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] + movdqa xmm3, xmmword ptr [rip + .LCPI5_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> + pshufb xmm2, xmm3 + pshufb xmm0, xmm3 + punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] + punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] + punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] + punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx], xmm12 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm0 + add rcx, 8 + mov r14, rcx + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + jne .LBB5_206 +# %bb.207: + mov rcx, qword ptr [rsp + 168] # 8-byte Reload + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14d, dword ptr [rsp + 12] # 4-byte Reload + mov r13, qword ptr [rsp + 48] # 8-byte Reload + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + jne .LBB5_70 + jmp .LBB5_134 +.LBB5_208: + and rcx, -8 mov rax, rcx - pinsrb xmm15, byte ptr [r14 + rcx + 28], 9 - pinsrb xmm9, byte ptr [r14 + rcx + 29], 9 - pinsrb xmm10, byte ptr [r14 + rcx + 30], 9 - pinsrb xmm6, byte ptr [r14 + rcx + 31], 9 - mov rax, r10 - pinsrb xmm15, byte ptr [r14 + r10 + 28], 10 - pinsrb xmm9, byte ptr [r14 + r10 + 29], 10 - pinsrb xmm10, byte ptr [r14 + r10 + 30], 10 - pinsrb xmm6, byte ptr [r14 + r10 + 31], 10 - mov rax, rdx - pinsrb xmm15, byte ptr [r14 + rdx + 28], 11 - pinsrb xmm9, byte ptr [r14 + rdx + 29], 11 - pinsrb xmm10, byte ptr [r14 + rdx + 30], 11 - pinsrb xmm6, byte ptr [r14 + rdx + 31], 11 - mov rax, rdi - pinsrb xmm15, byte ptr [r14 + rdi + 28], 12 - pinsrb xmm9, byte ptr [r14 + rdi + 29], 12 - pinsrb xmm10, byte ptr [r14 + rdi + 30], 12 - pinsrb xmm6, byte ptr [r14 + rdi + 31], 12 - pinsrb xmm15, byte ptr [r14 + r13 + 28], 13 - pinsrb xmm9, byte ptr [r14 + r13 + 29], 13 - pinsrb xmm10, byte ptr [r14 + r13 + 30], 13 - pinsrb xmm6, byte ptr [r14 + r13 + 31], 13 - pinsrb xmm15, byte ptr [r14 + r12 + 28], 14 - pinsrb xmm9, byte ptr [r14 + r12 + 29], 14 - pinsrb xmm10, byte ptr [r14 + r12 + 30], 14 - pinsrb xmm6, byte ptr [r14 + r12 + 31], 14 - pinsrb xmm15, byte ptr [r14 + rbx + 28], 15 - pinsrb xmm9, byte ptr [r14 + rbx + 29], 15 - pinsrb xmm10, byte ptr [r14 + rbx + 30], 15 - pcmpeqb xmm15, xmm14 - pandn xmm15, xmmword ptr [rip + .LCPI5_19] - por xmm15, xmm11 - pinsrb xmm6, byte ptr [r14 + rbx + 31], 15 - psubb xmm13, xmmword ptr [rip + .LCPI5_22] - por xmm15, xmm13 - pcmpeqb xmm9, xmm14 - pandn xmm9, xmm5 - pcmpeqb xmm10, xmm14 - pandn xmm10, xmm7 - por xmm10, xmm9 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmm4 - por xmm6, xmm10 - por xmm6, xmm15 + shl rax, 6 + add rax, rdx + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 32], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 48], rax # 8-byte Spill + movd xmm0, r14d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] + xor r14d, r14d + mov qword ptr [rsp + 136], r12 # 8-byte Spill + pxor xmm15, xmm15 + .p2align 4, 0x90 +.LBB5_209: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 40], r14 # 8-byte Spill + shl r14, 6 + mov r9, r14 + mov r15, r14 + mov r12, r14 + mov r13, r14 + mov rsi, r14 + mov r8, r14 + movzx eax, word ptr [rdx + r14] + movd xmm5, eax + movzx eax, word ptr [rdx + r14 + 2] + movd xmm0, eax + movzx eax, word ptr [rdx + r14 + 4] + movd xmm1, eax + movzx eax, word ptr [rdx + r14 + 6] + movd xmm7, eax + movzx eax, word ptr [rdx + r14 + 8] + movd xmm8, eax + movzx eax, word ptr [rdx + r14 + 10] + movd xmm4, eax + movzx eax, word ptr [rdx + r14 + 12] + movzx r10d, word ptr [rdx + r14 + 14] + movzx ebx, word ptr [rdx + r14 + 16] + movzx edi, word ptr [rdx + r14 + 18] + movzx ecx, word ptr [rdx + r14 + 20] + mov dword ptr [rsp + 24], ecx # 4-byte Spill + mov rcx, r14 + or rcx, 64 + or r9, 128 + or r15, 192 + or r12, 256 + or r13, 320 + or rsi, 384 + pinsrw xmm5, word ptr [rdx + rcx], 1 + pinsrw xmm5, word ptr [rdx + r9], 2 + pinsrw xmm5, word ptr [rdx + r15], 3 + pinsrw xmm5, word ptr [rdx + r12], 4 + pinsrw xmm5, word ptr [rdx + r13], 5 + pinsrw xmm5, word ptr [rdx + rsi], 6 + pinsrw xmm0, word ptr [rdx + rcx + 2], 1 + pinsrw xmm0, word ptr [rdx + r9 + 2], 2 + pinsrw xmm0, word ptr [rdx + r15 + 2], 3 + pinsrw xmm0, word ptr [rdx + r12 + 2], 4 + pinsrw xmm0, word ptr [rdx + r13 + 2], 5 + pinsrw xmm0, word ptr [rdx + rsi + 2], 6 + or r8, 448 + pinsrw xmm0, word ptr [rdx + r8 + 2], 7 + movd xmm2, eax + movzx eax, word ptr [rdx + r14 + 22] + mov dword ptr [rsp + 16], eax # 4-byte Spill + pcmpeqw xmm0, xmm11 + pinsrw xmm1, word ptr [rdx + rcx + 4], 1 + pinsrw xmm1, word ptr [rdx + r9 + 4], 2 + pinsrw xmm1, word ptr [rdx + r15 + 4], 3 + pinsrw xmm1, word ptr [rdx + r12 + 4], 4 + pinsrw xmm1, word ptr [rdx + r13 + 4], 5 + pinsrw xmm1, word ptr [rdx + rsi + 4], 6 + pinsrw xmm1, word ptr [rdx + r8 + 4], 7 + packsswb xmm0, xmm0 + pcmpeqw xmm1, xmm11 + movdqa xmm9, xmmword ptr [rip + .LCPI5_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm3, xmm9 + pblendvb xmm3, xmm15, xmm0 + packsswb xmm1, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI5_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm0 + movdqa xmm14, xmm0 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r10d + movzx r11d, word ptr [rdx + r14 + 24] + pinsrw xmm5, word ptr [rdx + r8], 7 + pcmpeqw xmm5, xmm11 + pcmpeqd xmm0, xmm0 + pxor xmm5, xmm0 + packsswb xmm5, xmm5 + pinsrw xmm7, word ptr [rdx + rcx + 6], 1 + pinsrw xmm7, word ptr [rdx + r9 + 6], 2 + pinsrw xmm7, word ptr [rdx + r15 + 6], 3 + pinsrw xmm7, word ptr [rdx + r12 + 6], 4 + pinsrw xmm7, word ptr [rdx + r13 + 6], 5 + pinsrw xmm7, word ptr [rdx + rsi + 6], 6 + pinsrw xmm7, word ptr [rdx + r8 + 6], 7 + pcmpeqw xmm7, xmm11 + packsswb xmm7, xmm7 + pinsrw xmm8, word ptr [rdx + rcx + 8], 1 + pinsrw xmm8, word ptr [rdx + r9 + 8], 2 + pinsrw xmm8, word ptr [rdx + r15 + 8], 3 + pinsrw xmm8, word ptr [rdx + r12 + 8], 4 + pinsrw xmm8, word ptr [rdx + r13 + 8], 5 + pinsrw xmm8, word ptr [rdx + rsi + 8], 6 + pinsrw xmm8, word ptr [rdx + r8 + 8], 7 + psubb xmm3, xmm5 + movdqa xmm12, xmmword ptr [rip + .LCPI5_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm7 + pblendvb xmm12, xmm15, xmm0 + movd xmm7, ebx + movzx eax, word ptr [rdx + r14 + 26] + pcmpeqw xmm8, xmm11 + packsswb xmm8, xmm8 + por xmm12, xmm6 + movdqa xmm13, xmmword ptr [rip + .LCPI5_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> movdqa xmm0, xmm8 - punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] - movdqa xmm3, xmmword ptr [rsp + 240] # 16-byte Reload - movdqa xmm1, xmm3 - movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload - punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] - movdqa xmm2, xmm1 - punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] - punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] - punpckhbw xmm3, xmm4 # xmm3 = xmm3[8],xmm4[8],xmm3[9],xmm4[9],xmm3[10],xmm4[10],xmm3[11],xmm4[11],xmm3[12],xmm4[12],xmm3[13],xmm4[13],xmm3[14],xmm4[14],xmm3[15],xmm4[15] + pblendvb xmm13, xmm15, xmm0 + movd xmm6, edi + movzx r10d, word ptr [rdx + r14 + 28] + pinsrw xmm4, word ptr [rdx + rcx + 10], 1 + pinsrw xmm4, word ptr [rdx + r9 + 10], 2 + pinsrw xmm4, word ptr [rdx + r15 + 10], 3 + pinsrw xmm4, word ptr [rdx + r12 + 10], 4 + pinsrw xmm4, word ptr [rdx + r13 + 10], 5 + pinsrw xmm4, word ptr [rdx + rsi + 10], 6 + pinsrw xmm4, word ptr [rdx + r8 + 10], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + pinsrw xmm2, word ptr [rdx + rcx + 12], 1 + pinsrw xmm2, word ptr [rdx + r9 + 12], 2 + pinsrw xmm2, word ptr [rdx + r15 + 12], 3 + pinsrw xmm2, word ptr [rdx + r12 + 12], 4 + pinsrw xmm2, word ptr [rdx + r13 + 12], 5 + pinsrw xmm2, word ptr [rdx + rsi + 12], 6 + por xmm12, xmm3 + movdqa xmm5, xmmword ptr [rip + .LCPI5_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 24] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 30] + pinsrw xmm2, word ptr [rdx + r8 + 12], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm13 + movdqa xmm13, xmmword ptr [rip + .LCPI5_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx edi, word ptr [rdx + r14 + 32] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + rcx + 14], 1 + pinsrw xmm1, word ptr [rdx + r9 + 14], 2 + pinsrw xmm1, word ptr [rdx + r15 + 14], 3 + pinsrw xmm1, word ptr [rdx + r12 + 14], 4 + pinsrw xmm1, word ptr [rdx + r13 + 14], 5 + pinsrw xmm1, word ptr [rdx + rsi + 14], 6 + por xmm13, xmm5 + movd xmm2, r11d + movzx edi, word ptr [rdx + r14 + 34] + mov dword ptr [rsp + 24], edi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + r8 + 14], 7 + pcmpeqw xmm1, xmm11 + pinsrw xmm6, word ptr [rdx + rcx + 18], 1 + pinsrw xmm6, word ptr [rdx + r9 + 18], 2 + pinsrw xmm6, word ptr [rdx + r15 + 18], 3 + pinsrw xmm6, word ptr [rdx + r12 + 18], 4 + pinsrw xmm6, word ptr [rdx + r13 + 18], 5 + pinsrw xmm6, word ptr [rdx + rsi + 18], 6 + packsswb xmm1, xmm1 + pinsrw xmm6, word ptr [rdx + r8 + 18], 7 + pcmpeqw xmm6, xmm11 + packsswb xmm6, xmm6 + por xmm13, xmm12 + movdqa xmm12, xmmword ptr [rip + .LCPI5_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm12, xmm15, xmm0 + movdqa xmm8, xmm9 + movdqa xmm0, xmm6 + pblendvb xmm8, xmm15, xmm0 + movd xmm1, eax + movzx r11d, word ptr [rdx + r14 + 36] + pinsrw xmm7, word ptr [rdx + rcx + 16], 1 + pinsrw xmm7, word ptr [rdx + r9 + 16], 2 + pinsrw xmm7, word ptr [rdx + r15 + 16], 3 + pinsrw xmm7, word ptr [rdx + r12 + 16], 4 + pinsrw xmm7, word ptr [rdx + r13 + 16], 5 + pinsrw xmm7, word ptr [rdx + rsi + 16], 6 + pinsrw xmm4, word ptr [rdx + rcx + 20], 1 + pinsrw xmm4, word ptr [rdx + r9 + 20], 2 + pinsrw xmm4, word ptr [rdx + r15 + 20], 3 + pinsrw xmm4, word ptr [rdx + r12 + 20], 4 + pinsrw xmm4, word ptr [rdx + r13 + 20], 5 + pinsrw xmm4, word ptr [rdx + rsi + 20], 6 + pinsrw xmm4, word ptr [rdx + r8 + 20], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm12, xmm13 + movdqa xmm5, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, r10d + movzx edi, word ptr [rdx + r14 + 38] + pinsrw xmm7, word ptr [rdx + r8 + 16], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI5_22] + packsswb xmm7, xmm7 + pinsrw xmm3, word ptr [rdx + rcx + 22], 1 + pinsrw xmm3, word ptr [rdx + r9 + 22], 2 + pinsrw xmm3, word ptr [rdx + r15 + 22], 3 + pinsrw xmm3, word ptr [rdx + r12 + 22], 4 + pinsrw xmm3, word ptr [rdx + r13 + 22], 5 + pinsrw xmm3, word ptr [rdx + rsi + 22], 6 + pinsrw xmm3, word ptr [rdx + r8 + 22], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rdx + rcx + 24], 1 + pinsrw xmm2, word ptr [rdx + r9 + 24], 2 + pinsrw xmm2, word ptr [rdx + r15 + 24], 3 + pinsrw xmm2, word ptr [rdx + r12 + 24], 4 + pinsrw xmm2, word ptr [rdx + r13 + 24], 5 + pinsrw xmm2, word ptr [rdx + rsi + 24], 6 + pinsrw xmm2, word ptr [rdx + r8 + 24], 7 + psubb xmm8, xmm7 + movdqa xmm10, xmmword ptr [rip + .LCPI5_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm14, xmm10 + movdqa xmm0, xmm3 + pblendvb xmm14, xmm15, xmm0 + movd xmm3, ebx + movzx eax, word ptr [rdx + r14 + 40] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm14, xmm5 + movdqa xmm9, xmmword ptr [rip + .LCPI5_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm7, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r10d, word ptr [rdx + r14 + 42] + pinsrw xmm1, word ptr [rdx + rcx + 26], 1 + pinsrw xmm1, word ptr [rdx + r9 + 26], 2 + pinsrw xmm1, word ptr [rdx + r15 + 26], 3 + pinsrw xmm1, word ptr [rdx + r12 + 26], 4 + pinsrw xmm1, word ptr [rdx + r13 + 26], 5 + pinsrw xmm1, word ptr [rdx + rsi + 26], 6 + pinsrw xmm1, word ptr [rdx + r8 + 26], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm4, word ptr [rdx + rcx + 28], 1 + pinsrw xmm4, word ptr [rdx + r9 + 28], 2 + pinsrw xmm4, word ptr [rdx + r15 + 28], 3 + pinsrw xmm4, word ptr [rdx + r12 + 28], 4 + pinsrw xmm4, word ptr [rdx + r13 + 28], 5 + pinsrw xmm4, word ptr [rdx + rsi + 28], 6 + por xmm14, xmm8 + movdqa xmm5, xmmword ptr [rip + .LCPI5_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm2, dword ptr [rsp + 24] # 4-byte Folded Reload + # xmm2 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 44] + mov dword ptr [rsp + 16], ebx # 4-byte Spill + pinsrw xmm4, word ptr [rdx + r8 + 28], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm5, xmm13 + movdqa xmm6, xmmword ptr [rip + .LCPI5_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, r11d + movzx ebx, word ptr [rdx + r14 + 46] + mov dword ptr [rsp + 24], ebx # 4-byte Spill + pinsrw xmm3, word ptr [rdx + rcx + 30], 1 + pinsrw xmm3, word ptr [rdx + r9 + 30], 2 + pinsrw xmm3, word ptr [rdx + r15 + 30], 3 + pinsrw xmm3, word ptr [rdx + r12 + 30], 4 + pinsrw xmm3, word ptr [rdx + r13 + 30], 5 + pinsrw xmm3, word ptr [rdx + rsi + 30], 6 + por xmm6, xmm5 + movd xmm1, edi + movzx edi, word ptr [rdx + r14 + 48] + pinsrw xmm3, word ptr [rdx + r8 + 30], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm2, word ptr [rdx + rcx + 34], 1 + pinsrw xmm2, word ptr [rdx + r9 + 34], 2 + pinsrw xmm2, word ptr [rdx + r15 + 34], 3 + pinsrw xmm2, word ptr [rdx + r12 + 34], 4 + pinsrw xmm2, word ptr [rdx + r13 + 34], 5 + pinsrw xmm2, word ptr [rdx + rsi + 34], 6 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rdx + r8 + 34], 7 + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm6, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI5_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm14 + movdqa xmm0, xmm3 + pblendvb xmm13, xmm15, xmm0 + movdqa xmm8, xmmword ptr [rip + .LCPI5_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm8, xmm15, xmm0 + movd xmm2, eax + movzx r11d, word ptr [rdx + r14 + 50] + pinsrw xmm7, word ptr [rdx + rcx + 32], 1 + pinsrw xmm7, word ptr [rdx + r9 + 32], 2 + pinsrw xmm7, word ptr [rdx + r15 + 32], 3 + pinsrw xmm7, word ptr [rdx + r12 + 32], 4 + pinsrw xmm7, word ptr [rdx + r13 + 32], 5 + pinsrw xmm7, word ptr [rdx + rsi + 32], 6 + pinsrw xmm4, word ptr [rdx + rcx + 36], 1 + pinsrw xmm4, word ptr [rdx + r9 + 36], 2 + pinsrw xmm4, word ptr [rdx + r15 + 36], 3 + pinsrw xmm4, word ptr [rdx + r12 + 36], 4 + pinsrw xmm4, word ptr [rdx + r13 + 36], 5 + pinsrw xmm4, word ptr [rdx + rsi + 36], 6 + pinsrw xmm4, word ptr [rdx + r8 + 36], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm13, xmm6 + movdqa xmm6, xmmword ptr [rip + .LCPI5_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm3, r10d + movzx r10d, word ptr [rdx + r14 + 52] + pinsrw xmm7, word ptr [rdx + r8 + 32], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI5_22] + packsswb xmm7, xmm7 + pinsrw xmm1, word ptr [rdx + rcx + 38], 1 + pinsrw xmm1, word ptr [rdx + r9 + 38], 2 + pinsrw xmm1, word ptr [rdx + r15 + 38], 3 + pinsrw xmm1, word ptr [rdx + r12 + 38], 4 + pinsrw xmm1, word ptr [rdx + r13 + 38], 5 + pinsrw xmm1, word ptr [rdx + rsi + 38], 6 + pinsrw xmm1, word ptr [rdx + r8 + 38], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm2, word ptr [rdx + rcx + 40], 1 + pinsrw xmm2, word ptr [rdx + r9 + 40], 2 + pinsrw xmm2, word ptr [rdx + r15 + 40], 3 + pinsrw xmm2, word ptr [rdx + r12 + 40], 4 + pinsrw xmm2, word ptr [rdx + r13 + 40], 5 + pinsrw xmm2, word ptr [rdx + rsi + 40], 6 + pinsrw xmm2, word ptr [rdx + r8 + 40], 7 + psubb xmm8, xmm7 + movdqa xmm5, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm1, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx eax, word ptr [rdx + r14 + 54] + pcmpeqw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm6 + movdqa xmm6, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 24] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 56] + pinsrw xmm3, word ptr [rdx + rcx + 42], 1 + pinsrw xmm3, word ptr [rdx + r9 + 42], 2 + pinsrw xmm3, word ptr [rdx + r15 + 42], 3 + pinsrw xmm3, word ptr [rdx + r12 + 42], 4 + pinsrw xmm3, word ptr [rdx + r13 + 42], 5 + pinsrw xmm3, word ptr [rdx + rsi + 42], 6 + pinsrw xmm3, word ptr [rdx + r8 + 42], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rdx + rcx + 44], 1 + pinsrw xmm1, word ptr [rdx + r9 + 44], 2 + pinsrw xmm1, word ptr [rdx + r15 + 44], 3 + pinsrw xmm1, word ptr [rdx + r12 + 44], 4 + pinsrw xmm1, word ptr [rdx + r13 + 44], 5 + pinsrw xmm1, word ptr [rdx + rsi + 44], 6 + por xmm5, xmm8 + movdqa xmm9, xmmword ptr [rip + .LCPI5_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm2, xmm9 + movdqa xmm0, xmm3 + pblendvb xmm2, xmm15, xmm0 + movd xmm7, edi + movzx edi, word ptr [rdx + r14 + 58] + pinsrw xmm1, word ptr [rdx + r8 + 44], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm2, xmm6 + movdqa xmm10, xmmword ptr [rip + .LCPI5_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r11d + movzx r11d, word ptr [rdx + r14 + 60] + por xmm6, xmm2 + movd xmm2, r10d + pinsrw xmm4, word ptr [rdx + rcx + 46], 1 + pinsrw xmm4, word ptr [rdx + r9 + 46], 2 + pinsrw xmm4, word ptr [rdx + r15 + 46], 3 + pinsrw xmm4, word ptr [rdx + r12 + 46], 4 + pinsrw xmm4, word ptr [rdx + r13 + 46], 5 + pinsrw xmm4, word ptr [rdx + rsi + 46], 6 + pinsrw xmm4, word ptr [rdx + r8 + 46], 7 + pcmpeqw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm6, xmm5 + movdqa xmm8, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm8, xmm15, xmm0 + movd xmm3, eax + pinsrw xmm1, word ptr [rdx + rcx + 50], 1 + pinsrw xmm1, word ptr [rdx + r9 + 50], 2 + pinsrw xmm1, word ptr [rdx + r15 + 50], 3 + pinsrw xmm1, word ptr [rdx + r12 + 50], 4 + pinsrw xmm1, word ptr [rdx + r13 + 50], 5 + pinsrw xmm1, word ptr [rdx + rsi + 50], 6 + pinsrw xmm1, word ptr [rdx + r8 + 50], 7 + pcmpeqw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm8, xmm6 + movdqa xmm4, xmmword ptr [rip + .LCPI5_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movd xmm1, ebx + pinsrw xmm7, word ptr [rdx + rcx + 48], 1 + pinsrw xmm7, word ptr [rdx + r9 + 48], 2 + pinsrw xmm7, word ptr [rdx + r15 + 48], 3 + pinsrw xmm7, word ptr [rdx + r12 + 48], 4 + pinsrw xmm7, word ptr [rdx + r13 + 48], 5 + pinsrw xmm7, word ptr [rdx + rsi + 48], 6 + pinsrw xmm7, word ptr [rdx + r8 + 48], 7 + pcmpeqw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI5_22] + pinsrw xmm2, word ptr [rdx + rcx + 52], 1 + pinsrw xmm2, word ptr [rdx + r9 + 52], 2 + pinsrw xmm2, word ptr [rdx + r15 + 52], 3 + pinsrw xmm2, word ptr [rdx + r12 + 52], 4 + pinsrw xmm2, word ptr [rdx + r13 + 52], 5 + pinsrw xmm2, word ptr [rdx + rsi + 52], 6 + packsswb xmm7, xmm7 + pinsrw xmm2, word ptr [rdx + r8 + 52], 7 + pcmpeqw xmm2, xmm11 + pinsrw xmm3, word ptr [rdx + rcx + 54], 1 + pinsrw xmm3, word ptr [rdx + r9 + 54], 2 + pinsrw xmm3, word ptr [rdx + r15 + 54], 3 + pinsrw xmm3, word ptr [rdx + r12 + 54], 4 + pinsrw xmm3, word ptr [rdx + r13 + 54], 5 + pinsrw xmm3, word ptr [rdx + rsi + 54], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rdx + r8 + 54], 7 + pcmpeqw xmm3, xmm11 + pinsrw xmm1, word ptr [rdx + rcx + 56], 1 + pinsrw xmm1, word ptr [rdx + r9 + 56], 2 + pinsrw xmm1, word ptr [rdx + r15 + 56], 3 + pinsrw xmm1, word ptr [rdx + r12 + 56], 4 + pinsrw xmm1, word ptr [rdx + r13 + 56], 5 + pinsrw xmm1, word ptr [rdx + rsi + 56], 6 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rdx + r8 + 56], 7 + psubb xmm4, xmm7 + movdqa xmm5, xmmword ptr [rip + .LCPI5_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm5, xmm15, xmm0 + movdqa xmm6, xmmword ptr [rip + .LCPI5_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> movdqa xmm0, xmm3 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] + pblendvb xmm6, xmm15, xmm0 + movd xmm2, edi + pcmpeqw xmm1, xmm11 + pinsrw xmm2, word ptr [rdx + rcx + 58], 1 + pinsrw xmm2, word ptr [rdx + r9 + 58], 2 + pinsrw xmm2, word ptr [rdx + r15 + 58], 3 + pinsrw xmm2, word ptr [rdx + r12 + 58], 4 + pinsrw xmm2, word ptr [rdx + r13 + 58], 5 + pinsrw xmm2, word ptr [rdx + rsi + 58], 6 + pinsrw xmm2, word ptr [rdx + r8 + 58], 7 + packsswb xmm1, xmm1 + pcmpeqw xmm2, xmm11 + por xmm6, xmm5 + movd xmm3, r11d + pinsrw xmm3, word ptr [rdx + rcx + 60], 1 + pinsrw xmm3, word ptr [rdx + r9 + 60], 2 + pinsrw xmm3, word ptr [rdx + r15 + 60], 3 + pinsrw xmm3, word ptr [rdx + r12 + 60], 4 + pinsrw xmm3, word ptr [rdx + r13 + 60], 5 + pinsrw xmm3, word ptr [rdx + rsi + 60], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rdx + r8 + 60], 7 + pcmpeqw xmm3, xmm11 + packsswb xmm3, xmm3 + por xmm6, xmm4 + movdqa xmm4, xmmword ptr [rip + .LCPI5_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movdqa xmm1, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm1, xmm15, xmm0 + movdqa xmm0, xmm3 + pblendvb xmm10, xmm15, xmm0 + por xmm1, xmm4 + movzx eax, word ptr [rdx + r14 + 62] + por xmm10, xmm1 + movd xmm0, eax + pinsrw xmm0, word ptr [rdx + rcx + 62], 1 + pinsrw xmm0, word ptr [rdx + r9 + 62], 2 + pinsrw xmm0, word ptr [rdx + r15 + 62], 3 + pinsrw xmm0, word ptr [rdx + r12 + 62], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + pinsrw xmm0, word ptr [rdx + r13 + 62], 5 + pinsrw xmm0, word ptr [rdx + rsi + 62], 6 + pinsrw xmm0, word ptr [rdx + r8 + 62], 7 + pcmpeqw xmm0, xmm11 + packsswb xmm0, xmm0 + por xmm10, xmm6 + pblendvb xmm14, xmm15, xmm0 + por xmm14, xmm10 + movdqa xmm0, xmm12 + punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] + movdqa xmm2, xmm8 + punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] + movdqa xmm3, xmmword ptr [rip + .LCPI5_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> + pshufb xmm2, xmm3 + pshufb xmm0, xmm3 + punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] + punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] + punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] + punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx], xmm12 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm0 + add rcx, 8 + mov r14, rcx + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + jne .LBB5_209 +# %bb.210: mov rcx, qword ptr [rsp + 168] # 8-byte Reload - mov rax, qword ptr [rsp + 8] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx + 48], xmm3 - movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm1 - movdqu xmmword ptr [rax + 4*rcx], xmm2 - add rcx, 16 + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14d, dword ptr [rsp + 12] # 4-byte Reload + mov r13, qword ptr [rsp + 48] # 8-byte Reload + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + jne .LBB5_84 + jmp .LBB5_139 +.LBB5_211: + mov r9, rcx + and r9, -4 + mov rbx, r9 + shl rbx, 7 + add rbx, rdx + lea r13, [r12 + 4*r9] + movdqa xmm1, xmm0 + shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] + add rdx, 508 + xor esi, esi + movdqa xmm15, xmmword ptr [rip + .LCPI5_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> + movdqa xmm8, xmmword ptr [rip + .LCPI5_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + movdqa xmm10, xmmword ptr [rip + .LCPI5_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + movdqa xmm11, xmmword ptr [rip + .LCPI5_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + movdqa xmm12, xmmword ptr [rip + .LCPI5_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + movdqa xmm13, xmmword ptr [rip + .LCPI5_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] + movdqa xmm14, xmmword ptr [rip + .LCPI5_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + movdqa xmm9, xmmword ptr [rip + .LCPI5_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] + .p2align 4, 0x90 +.LBB5_212: # =>This Inner Loop Header: Depth=1 + movss xmm6, dword ptr [rdx - 508] # xmm6 = mem[0],zero,zero,zero + movss xmm7, dword ptr [rdx - 504] # xmm7 = mem[0],zero,zero,zero + movss xmm5, dword ptr [rdx - 500] # xmm5 = mem[0],zero,zero,zero + movss xmm4, dword ptr [rdx - 496] # xmm4 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 380], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 252], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 124], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + insertps xmm7, dword ptr [rdx - 376], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 248], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 120], 48 # xmm7 = xmm7[0,1,2],mem[0] + insertps xmm5, dword ptr [rdx - 372], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 244], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 116], 48 # xmm5 = xmm5[0,1,2],mem[0] + insertps xmm4, dword ptr [rdx - 368], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] + insertps xmm4, dword ptr [rdx - 240], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] + insertps xmm4, dword ptr [rdx - 112], 48 # xmm4 = xmm4[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + movdqa xmm2, xmm7 + pand xmm2, xmm15 + psubb xmm2, xmm7 + movss xmm7, dword ptr [rdx - 492] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 364], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 236], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 108], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm2, xmm6 + movss xmm6, dword ptr [rdx - 488] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 360], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 232], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 104], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 2 + pand xmm5, xmm8 + por xmm5, xmm2 + movss xmm3, dword ptr [rdx - 484] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 356], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 228], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rdx - 100], 48 # xmm3 = xmm3[0,1,2],mem[0] + cmpneqps xmm4, xmm1 + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + psllw xmm4, 3 + pand xmm4, xmm10 + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 4 + pand xmm7, xmm11 + por xmm7, xmm4 + movss xmm4, dword ptr [rdx - 480] # xmm4 = mem[0],zero,zero,zero + insertps xmm4, dword ptr [rdx - 352], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] + insertps xmm4, dword ptr [rdx - 224], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] + insertps xmm4, dword ptr [rdx - 96], 48 # xmm4 = xmm4[0,1,2],mem[0] + por xmm7, xmm5 + movss xmm5, dword ptr [rdx - 476] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 348], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 220], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 92], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 6 + pand xmm3, xmm13 + por xmm3, xmm6 + movss xmm2, dword ptr [rdx - 472] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 344], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 216], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 88], 48 # xmm2 = xmm2[0,1,2],mem[0] + packsswb xmm5, xmm5 + cmpneqps xmm4, xmm1 + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + psllw xmm4, 7 + pand xmm4, xmm14 + por xmm4, xmm3 + movss xmm3, dword ptr [rdx - 468] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 340], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 212], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + pand xmm5, xmm15 + insertps xmm3, dword ptr [rdx - 84], 48 # xmm3 = xmm3[0,1,2],mem[0] + por xmm4, xmm7 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm6, xmm2 + pand xmm6, xmm15 + psubb xmm6, xmm2 + movss xmm7, dword ptr [rdx - 464] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 336], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 208], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 80], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm6, xmm5 + movss xmm5, dword ptr [rdx - 460] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 332], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 204], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 76], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm6 + movss xmm6, dword ptr [rdx - 456] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 328], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 200], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 72], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 3 + pand xmm7, xmm10 + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 4 + pand xmm5, xmm11 + por xmm5, xmm7 + movss xmm2, dword ptr [rdx - 452] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 324], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 196], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 68], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm5, xmm3 + movss xmm7, dword ptr [rdx - 448] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 320], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 192], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 64], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm6 + movss xmm6, dword ptr [rdx - 444] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 316], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 188], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 60], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + psllw xmm7, 7 + pand xmm7, xmm14 + por xmm7, xmm2 + movss xmm2, dword ptr [rdx - 440] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 312], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm7, xmm5 + movss xmm3, dword ptr [rdx - 436] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 308], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 180], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + pand xmm6, xmm15 + insertps xmm3, dword ptr [rdx - 52], 48 # xmm3 = xmm3[0,1,2],mem[0] + punpckldq xmm4, xmm7 # xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1] + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm7, xmm2 + pand xmm7, xmm15 + psubb xmm7, xmm2 + movss xmm5, dword ptr [rdx - 432] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 304], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 176], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 48], 48 # xmm5 = xmm5[0,1,2],mem[0] + por xmm7, xmm6 + movss xmm6, dword ptr [rdx - 428] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 300], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 172], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 44], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm7 + movss xmm7, dword ptr [rdx - 424] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 296], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 168], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 40], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 3 + pand xmm5, xmm10 + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 4 + pand xmm6, xmm11 + por xmm6, xmm5 + movss xmm2, dword ptr [rdx - 420] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 292], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm6, xmm3 + movss xmm5, dword ptr [rdx - 416] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 288], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 160], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 32], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 5 + pand xmm7, xmm12 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm7 + movss xmm7, dword ptr [rdx - 412] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 284], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 156], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 28], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + cmpneqps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + psllw xmm5, 7 + pand xmm5, xmm14 + por xmm5, xmm2 + movss xmm2, dword ptr [rdx - 408] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 280], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 152], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + pand xmm7, xmm15 + insertps xmm2, dword ptr [rdx - 24], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm5, xmm6 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm6, xmm2 + pand xmm6, xmm15 + psubb xmm6, xmm2 + movss xmm3, dword ptr [rdx - 404] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 276], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 148], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rdx - 20], 48 # xmm3 = xmm3[0,1,2],mem[0] + por xmm6, xmm7 + movss xmm2, dword ptr [rdx - 400] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 272], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 144], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 16], 48 # xmm2 = xmm2[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm6 + movss xmm6, dword ptr [rdx - 396] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 268], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 140], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 3 + pand xmm2, xmm10 + cmpneqps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 4 + pand xmm6, xmm11 + por xmm6, xmm2 + movss xmm7, dword ptr [rdx - 392] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 264], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 136], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 8], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm6, xmm3 + movss xmm2, dword ptr [rdx - 388] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 260], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 132], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 4], 48 # xmm2 = xmm2[0,1,2],mem[0] + cmpneqps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 5 + pand xmm7, xmm12 + cmpneqps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm7 + movss xmm3, dword ptr [rdx - 384] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 256], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 128], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rdx], 48 # xmm3 = xmm3[0,1,2],mem[0] + cmpneqps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + psllw xmm3, 7 + pand xmm3, xmm14 + por xmm3, xmm2 + por xmm3, xmm6 + punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] + punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] + pshufb xmm4, xmm9 + movdqu xmmword ptr [r12 + 4*rsi], xmm4 + add rsi, 4 + add rdx, 512 + cmp r9, rsi + jne .LBB5_212 +# %bb.213: + cmp rcx, r9 + jne .LBB5_111 + jmp .LBB5_143 +.LBB5_214: + and rcx, -16 mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB5_87 -# %bb.88: - mov r10, qword ptr [rsp + 264] # 8-byte Reload - cmp r10, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r15, qword ptr [rsp + 160] # 8-byte Reload - jne .LBB5_89 - jmp .LBB5_92 -.LBB5_67: - and r10, -16 - mov rax, r10 shl rax, 5 - add rax, r14 - mov qword ptr [rsp + 272], rax # 8-byte Spill - mov qword ptr [rsp + 232], r10 # 8-byte Spill - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - mov qword ptr [rsp + 104], rax # 8-byte Spill - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + add rax, r13 + mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 168], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 256], rax # 8-byte Spill + movzx eax, r14b movd xmm1, eax pxor xmm0, xmm0 pshufb xmm1, xmm0 movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill xor eax, eax + mov qword ptr [rsp + 136], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB5_68: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 168], rax # 8-byte Spill +.LBB5_215: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 160], rax # 8-byte Spill shl rax, 5 - mov r13, rax - mov rdi, rax - mov r15, rax mov rbx, rax - mov r10, rax - mov r9, rax + mov rsi, rax + mov r11, rax mov r8, rax + mov rdi, rax mov r12, rax + mov r10, rax + mov qword ptr [rsp + 88], rax # 8-byte Spill + mov r14, rax mov rdx, rax - mov rsi, rax - mov qword ptr [rsp + 96], rax # 8-byte Spill - movzx ecx, byte ptr [r14 + rax] + mov qword ptr [rsp + 72], rax # 8-byte Spill + movzx ecx, byte ptr [r13 + rax] movd xmm4, ecx - movzx ecx, byte ptr [r14 + rax + 1] + movzx ecx, byte ptr [r13 + rax + 1] movd xmm3, ecx - movzx ecx, byte ptr [r14 + rax + 2] + movzx ecx, byte ptr [r13 + rax + 2] movd xmm5, ecx - movzx ecx, byte ptr [r14 + rax + 3] + movzx ecx, byte ptr [r13 + rax + 3] movd xmm7, ecx - movzx ecx, byte ptr [r14 + rax + 4] + movzx ecx, byte ptr [r13 + rax + 4] movd xmm9, ecx - movzx ecx, byte ptr [r14 + rax + 5] + movzx ecx, byte ptr [r13 + rax + 5] movd xmm2, ecx - movzx ecx, byte ptr [r14 + rax + 6] + movzx ecx, byte ptr [r13 + rax + 6] movd xmm8, ecx - movzx ecx, byte ptr [r14 + rax + 7] + movzx ecx, byte ptr [r13 + rax + 7] movd xmm14, ecx - movzx ecx, byte ptr [r14 + rax + 8] + movzx ecx, byte ptr [r13 + rax + 8] movd xmm0, ecx - movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill - movzx ecx, byte ptr [r14 + rax + 9] + movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r13 + rax + 9] movd xmm11, ecx - movzx ecx, byte ptr [r14 + rax + 10] + movzx ecx, byte ptr [r13 + rax + 10] movd xmm12, ecx - movzx ecx, byte ptr [r14 + rax + 11] + movzx ecx, byte ptr [r13 + rax + 11] movd xmm13, ecx - movzx ecx, byte ptr [r14 + rax + 12] + movzx ecx, byte ptr [r13 + rax + 12] movd xmm0, ecx - movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill - movzx ecx, byte ptr [r14 + rax + 13] + movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r13 + rax + 13] movd xmm6, ecx - movzx ecx, byte ptr [r14 + rax + 14] + movzx ecx, byte ptr [r13 + rax + 14] movd xmm15, ecx - movzx ecx, byte ptr [r14 + rax + 15] + movzx ecx, byte ptr [r13 + rax + 15] movd xmm0, ecx movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov r11, rax - or r11, 32 - mov qword ptr [rsp + 16], r11 # 8-byte Spill - or r13, 64 - or rdi, 96 - or r15, 128 - or rbx, 160 - or r10, 192 - or r9, 224 - or r8, 256 - or r12, 288 - or rdx, 320 - mov qword ptr [rsp + 112], rdx # 8-byte Spill - or rsi, 352 - mov qword ptr [rsp + 152], rsi # 8-byte Spill - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - or rcx, 384 - mov qword ptr [rsp + 96], rcx # 8-byte Spill - mov rdx, rax - or rdx, 416 - mov qword ptr [rsp + 24], rdx # 8-byte Spill + mov qword ptr [rsp + 120], rax # 8-byte Spill + mov r15, rax + or r15, 32 + mov qword ptr [rsp + 40], r15 # 8-byte Spill + or rbx, 64 + or rsi, 96 + mov qword ptr [rsp + 112], rsi # 8-byte Spill + or r11, 128 + or r8, 160 + mov qword ptr [rsp + 56], r8 # 8-byte Spill + mov rcx, rax + or rcx, 192 + mov qword ptr [rsp + 32], rcx # 8-byte Spill + mov r9, rax + or r9, 224 + or r10, 256 + mov qword ptr [rsp + 16], r10 # 8-byte Spill + mov r12, qword ptr [rsp + 88] # 8-byte Reload + or r12, 288 + or rdi, 320 + or rdx, 352 + mov qword ptr [rsp + 128], rdx # 8-byte Spill + mov r10, qword ptr [rsp + 72] # 8-byte Reload + or r10, 384 + mov qword ptr [rsp + 72], r10 # 8-byte Spill + or r14, 416 mov rdx, rax or rdx, 448 - mov qword ptr [rsp + 32], rdx # 8-byte Spill - mov rdx, rax - or rdx, 480 - mov qword ptr [rsp + 80], rdx # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r11], 1 - mov qword ptr [rsp + 48], r13 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r13], 2 - mov qword ptr [rsp + 40], rdi # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + rdi], 3 - mov qword ptr [rsp + 120], r15 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r15], 4 - mov qword ptr [rsp + 128], rbx # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + rbx], 5 - mov qword ptr [rsp + 144], r10 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r10], 6 - mov qword ptr [rsp + 88], r9 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r9], 7 - mov qword ptr [rsp + 72], r8 # 8-byte Spill - pinsrb xmm4, byte ptr [r14 + r8], 8 - mov r8, r12 - pinsrb xmm4, byte ptr [r14 + r12], 9 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + r12], 10 - pinsrb xmm4, byte ptr [r14 + rsi], 11 - pinsrb xmm4, byte ptr [r14 + rcx], 12 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rax], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rax], 14 - pinsrb xmm4, byte ptr [r14 + rdx], 15 - pinsrb xmm3, byte ptr [r14 + r11 + 1], 1 - pinsrb xmm3, byte ptr [r14 + r13 + 1], 2 - pinsrb xmm3, byte ptr [r14 + rdi + 1], 3 - pinsrb xmm3, byte ptr [r14 + r15 + 1], 4 - pinsrb xmm3, byte ptr [r14 + rbx + 1], 5 - pinsrb xmm3, byte ptr [r14 + r10 + 1], 6 - pinsrb xmm3, byte ptr [r14 + r9 + 1], 7 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm3, byte ptr [r14 + r13 + 1], 8 - pinsrb xmm3, byte ptr [r14 + r8 + 1], 9 - mov rdi, r8 - pinsrb xmm3, byte ptr [r14 + r12 + 1], 10 - mov r15, r12 - pinsrb xmm3, byte ptr [r14 + rsi + 1], 11 - pinsrb xmm3, byte ptr [r14 + rcx + 1], 12 - mov r11, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [r14 + r11 + 1], 13 + mov qword ptr [rsp + 96], rdx # 8-byte Spill + or rax, 480 + mov qword ptr [rsp + 24], rax # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r15], 1 + mov rax, rbx + mov qword ptr [rsp + 104], rbx # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + rbx], 2 + pinsrb xmm4, byte ptr [r13 + rsi], 3 + mov rdx, r11 + mov qword ptr [rsp + 64], r11 # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r11], 4 + pinsrb xmm4, byte ptr [r13 + r8], 5 + pinsrb xmm4, byte ptr [r13 + rcx], 6 + pinsrb xmm4, byte ptr [r13 + r9], 7 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + r15], 8 + pinsrb xmm4, byte ptr [r13 + r12], 9 + mov qword ptr [rsp + 144], rdi # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + rdi], 10 + mov r11, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + r11], 11 + pinsrb xmm4, byte ptr [r13 + r10], 12 + mov rbx, r14 + mov qword ptr [rsp + 48], r14 # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r14], 13 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rcx], 14 + mov r14, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + r14], 15 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + rsi + 1], 1 + pinsrb xmm3, byte ptr [r13 + rax + 1], 2 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + rax + 1], 3 + pinsrb xmm3, byte ptr [r13 + rdx + 1], 4 + pinsrb xmm3, byte ptr [r13 + r8 + 1], 5 mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [r14 + rax + 1], 14 + pinsrb xmm3, byte ptr [r13 + rax + 1], 6 + pinsrb xmm3, byte ptr [r13 + r9 + 1], 7 + mov r8, r9 + pinsrb xmm3, byte ptr [r13 + r15 + 1], 8 + pinsrb xmm3, byte ptr [r13 + r12 + 1], 9 + mov rdx, r12 + mov qword ptr [rsp + 88], r12 # 8-byte Spill + pinsrb xmm3, byte ptr [r13 + rdi + 1], 10 + pinsrb xmm3, byte ptr [r13 + r11 + 1], 11 + pinsrb xmm3, byte ptr [r13 + r10 + 1], 12 + pinsrb xmm3, byte ptr [r13 + rbx + 1], 13 + pinsrb xmm3, byte ptr [r13 + rcx + 1], 14 + mov r9, rcx movdqa xmm1, xmmword ptr [rsp + 176] # 16-byte Reload pcmpeqb xmm4, xmm1 - pinsrb xmm3, byte ptr [r14 + rdx + 1], 15 + pinsrb xmm3, byte ptr [r13 + r14 + 1], 15 pcmpeqb xmm3, xmm1 movdqa xmm0, xmmword ptr [rip + .LCPI5_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] pandn xmm3, xmm0 paddb xmm3, xmm4 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [r14 + rax + 16] + mov rax, qword ptr [rsp + 120] # 8-byte Reload + movzx esi, byte ptr [r13 + rax + 16] movd xmm10, esi - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rax + 2], 1 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r12 + 2], 2 mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rax + 2], 3 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rbx + 2], 4 - mov r10, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r10 + 2], 5 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r9 + 2], 6 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r8 + 2], 7 - pinsrb xmm5, byte ptr [r14 + r13 + 2], 8 - mov rcx, rdi - pinsrb xmm5, byte ptr [r14 + rdi + 2], 9 - pinsrb xmm5, byte ptr [r14 + r15 + 2], 10 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rdx + 2], 11 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rdi + 2], 12 - pinsrb xmm5, byte ptr [r14 + r11 + 2], 13 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + rsi + 2], 14 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [r14 + r11 + 2], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 3], 1 - pinsrb xmm7, byte ptr [r14 + r12 + 3], 2 + pinsrb xmm5, byte ptr [r13 + rax + 2], 1 + mov rdi, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rdi + 2], 2 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rbx + 2], 3 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r14 + 2], 4 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r12 + 2], 5 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r10 + 2], 6 + mov qword ptr [rsp + 80], r8 # 8-byte Spill + pinsrb xmm5, byte ptr [r13 + r8 + 2], 7 + pinsrb xmm5, byte ptr [r13 + r15 + 2], 8 + pinsrb xmm5, byte ptr [r13 + rdx + 2], 9 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rsi + 2], 10 + pinsrb xmm5, byte ptr [r13 + r11 + 2], 11 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rcx + 2], 12 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r11 + 2], 13 + pinsrb xmm5, byte ptr [r13 + r9 + 2], 14 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rdx + 2], 15 mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 3], 3 - pinsrb xmm7, byte ptr [r14 + rbx + 3], 4 - pinsrb xmm7, byte ptr [r14 + r10 + 3], 5 - pinsrb xmm7, byte ptr [r14 + r9 + 3], 6 - pinsrb xmm7, byte ptr [r14 + r8 + 3], 7 - pinsrb xmm7, byte ptr [r14 + r13 + 3], 8 - pinsrb xmm7, byte ptr [r14 + rcx + 3], 9 - pinsrb xmm7, byte ptr [r14 + r15 + 3], 10 - pinsrb xmm7, byte ptr [r14 + rdx + 3], 11 - pinsrb xmm7, byte ptr [r14 + rdi + 3], 12 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 3], 13 - pinsrb xmm7, byte ptr [r14 + rsi + 3], 14 - pinsrb xmm7, byte ptr [r14 + r11 + 3], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 4], 1 - pinsrb xmm9, byte ptr [r14 + r12 + 4], 2 + pinsrb xmm7, byte ptr [r13 + rax + 3], 1 + pinsrb xmm7, byte ptr [r13 + rdi + 3], 2 + pinsrb xmm7, byte ptr [r13 + rbx + 3], 3 + pinsrb xmm7, byte ptr [r13 + r14 + 3], 4 + pinsrb xmm7, byte ptr [r13 + r12 + 3], 5 + pinsrb xmm7, byte ptr [r13 + r10 + 3], 6 + pinsrb xmm7, byte ptr [r13 + r8 + 3], 7 + pinsrb xmm7, byte ptr [r13 + r15 + 3], 8 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 9 + pinsrb xmm7, byte ptr [r13 + rsi + 3], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 11 + pinsrb xmm7, byte ptr [r13 + rcx + 3], 12 + pinsrb xmm7, byte ptr [r13 + r11 + 3], 13 + pinsrb xmm7, byte ptr [r13 + r9 + 3], 14 + pinsrb xmm7, byte ptr [r13 + rdx + 3], 15 mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 4], 3 - pinsrb xmm9, byte ptr [r14 + rbx + 4], 4 - pinsrb xmm9, byte ptr [r14 + r10 + 4], 5 - pinsrb xmm9, byte ptr [r14 + r9 + 4], 6 - pinsrb xmm9, byte ptr [r14 + r8 + 4], 7 - pinsrb xmm9, byte ptr [r14 + r13 + 4], 8 - mov rax, r13 - pinsrb xmm9, byte ptr [r14 + rcx + 4], 9 - pinsrb xmm9, byte ptr [r14 + r15 + 4], 10 - pinsrb xmm9, byte ptr [r14 + rdx + 4], 11 - pinsrb xmm9, byte ptr [r14 + rdi + 4], 12 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r13 + 4], 13 - pinsrb xmm9, byte ptr [r14 + rsi + 4], 14 - pinsrb xmm9, byte ptr [r14 + r11 + 4], 15 + pinsrb xmm9, byte ptr [r13 + rax + 4], 1 + pinsrb xmm9, byte ptr [r13 + rdi + 4], 2 + mov rax, rdi + pinsrb xmm9, byte ptr [r13 + rbx + 4], 3 + mov rdi, rbx + pinsrb xmm9, byte ptr [r13 + r14 + 4], 4 + mov rbx, r14 + pinsrb xmm9, byte ptr [r13 + r12 + 4], 5 + pinsrb xmm9, byte ptr [r13 + r10 + 4], 6 + pinsrb xmm9, byte ptr [r13 + r8 + 4], 7 + pinsrb xmm9, byte ptr [r13 + r15 + 4], 8 + mov r12, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r12 + 4], 9 + pinsrb xmm9, byte ptr [r13 + rsi + 4], 10 + mov r8, rsi + mov r10, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r10 + 4], 11 + pinsrb xmm9, byte ptr [r13 + rcx + 4], 12 + pinsrb xmm9, byte ptr [r13 + r11 + 4], 13 + pinsrb xmm9, byte ptr [r13 + r9 + 4], 14 + pinsrb xmm9, byte ptr [r13 + rdx + 4], 15 pcmpeqb xmm5, xmm1 movdqa xmm0, xmmword ptr [rip + .LCPI5_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] pandn xmm5, xmm0 @@ -29917,80 +31395,85 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 movdqa xmm0, xmmword ptr [rip + .LCPI5_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] pandn xmm7, xmm0 por xmm7, xmm5 - mov r11, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [r14 + r11 + 17] + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + movzx esi, byte ptr [r13 + rdx + 17] movd xmm4, esi pcmpeqb xmm9, xmm1 movdqa xmm0, xmmword ptr [rip + .LCPI5_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] pandn xmm9, xmm0 por xmm9, xmm7 - movzx esi, byte ptr [r14 + r11 + 18] + movzx esi, byte ptr [r13 + rdx + 18] movd xmm7, esi pcmpeqd xmm0, xmm0 psubb xmm3, xmm0 por xmm9, xmm3 - movzx esi, byte ptr [r14 + r11 + 19] + movzx esi, byte ptr [r13 + rdx + 19] movd xmm5, esi - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + rsi + 5], 1 - pinsrb xmm2, byte ptr [r14 + r12 + 5], 2 mov r15, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + r15 + 5], 3 - pinsrb xmm2, byte ptr [r14 + rbx + 5], 4 - pinsrb xmm2, byte ptr [r14 + r10 + 5], 5 - pinsrb xmm2, byte ptr [r14 + r9 + 5], 6 - pinsrb xmm2, byte ptr [r14 + r8 + 5], 7 - pinsrb xmm2, byte ptr [r14 + rax + 5], 8 - mov qword ptr [rsp + 136], rcx # 8-byte Spill - pinsrb xmm2, byte ptr [r14 + rcx + 5], 9 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + rax + 5], 10 - pinsrb xmm2, byte ptr [r14 + rdx + 5], 11 - pinsrb xmm2, byte ptr [r14 + rdi + 5], 12 - mov r11, r13 - pinsrb xmm2, byte ptr [r14 + r13 + 5], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + rax + 5], 14 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [r14 + r13 + 5], 15 - pinsrb xmm8, byte ptr [r14 + rsi + 6], 1 - pinsrb xmm8, byte ptr [r14 + r12 + 6], 2 - pinsrb xmm8, byte ptr [r14 + r15 + 6], 3 - pinsrb xmm8, byte ptr [r14 + rbx + 6], 4 - pinsrb xmm8, byte ptr [r14 + r10 + 6], 5 - pinsrb xmm8, byte ptr [r14 + r9 + 6], 6 - pinsrb xmm8, byte ptr [r14 + r8 + 6], 7 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm8, byte ptr [r14 + rax + 6], 8 - pinsrb xmm8, byte ptr [r14 + rcx + 6], 9 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm8, byte ptr [r14 + rax + 6], 10 - pinsrb xmm8, byte ptr [r14 + rdx + 6], 11 - pinsrb xmm8, byte ptr [r14 + rdi + 6], 12 - pinsrb xmm8, byte ptr [r14 + r11 + 6], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm8, byte ptr [r14 + rax + 6], 14 - pinsrb xmm8, byte ptr [r14 + r13 + 6], 15 - mov rax, r13 - pinsrb xmm14, byte ptr [r14 + rsi + 7], 1 - pinsrb xmm14, byte ptr [r14 + r12 + 7], 2 - pinsrb xmm14, byte ptr [r14 + r15 + 7], 3 - pinsrb xmm14, byte ptr [r14 + rbx + 7], 4 - mov r12, rbx - pinsrb xmm14, byte ptr [r14 + r10 + 7], 5 - pinsrb xmm14, byte ptr [r14 + r9 + 7], 6 - pinsrb xmm14, byte ptr [r14 + r8 + 7], 7 + pinsrb xmm2, byte ptr [r13 + r15 + 5], 1 + mov rsi, rax + pinsrb xmm2, byte ptr [r13 + rax + 5], 2 + pinsrb xmm2, byte ptr [r13 + rdi + 5], 3 + mov r14, rdi + pinsrb xmm2, byte ptr [r13 + rbx + 5], 4 + mov r11, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r11 + 5], 5 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rdi + 5], 6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rax + 5], 7 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rdx + 5], 8 + pinsrb xmm2, byte ptr [r13 + r12 + 5], 9 mov r9, r8 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm14, byte ptr [r14 + r13 + 7], 8 - pinsrb xmm14, byte ptr [r14 + rcx + 7], 9 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm14, byte ptr [r14 + r15 + 7], 10 - pinsrb xmm14, byte ptr [r14 + rdx + 7], 11 - pinsrb xmm14, byte ptr [r14 + rdi + 7], 12 - pinsrb xmm14, byte ptr [r14 + r11 + 7], 13 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm14, byte ptr [r14 + rcx + 7], 14 + pinsrb xmm2, byte ptr [r13 + r8 + 5], 10 + pinsrb xmm2, byte ptr [r13 + r10 + 5], 11 + mov rdx, rcx + pinsrb xmm2, byte ptr [r13 + rcx + 5], 12 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rbx + 5], 13 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r8 + 5], 14 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rcx + 5], 15 + pinsrb xmm8, byte ptr [r13 + r15 + 6], 1 + pinsrb xmm8, byte ptr [r13 + rsi + 6], 2 + pinsrb xmm8, byte ptr [r13 + r14 + 6], 3 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + r14 + 6], 4 + pinsrb xmm8, byte ptr [r13 + r11 + 6], 5 + pinsrb xmm8, byte ptr [r13 + rdi + 6], 6 + pinsrb xmm8, byte ptr [r13 + rax + 6], 7 + mov r14, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + r14 + 6], 8 + pinsrb xmm8, byte ptr [r13 + r12 + 6], 9 + pinsrb xmm8, byte ptr [r13 + r9 + 6], 10 + pinsrb xmm8, byte ptr [r13 + r10 + 6], 11 + mov r9, r10 + pinsrb xmm8, byte ptr [r13 + rdx + 6], 12 + pinsrb xmm8, byte ptr [r13 + rbx + 6], 13 + pinsrb xmm8, byte ptr [r13 + r8 + 6], 14 + mov rcx, r8 + mov r10, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + r10 + 6], 15 + pinsrb xmm14, byte ptr [r13 + r15 + 7], 1 + pinsrb xmm14, byte ptr [r13 + rsi + 7], 2 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + rbx + 7], 3 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + rsi + 7], 4 + pinsrb xmm14, byte ptr [r13 + r11 + 7], 5 + pinsrb xmm14, byte ptr [r13 + rdi + 7], 6 + pinsrb xmm14, byte ptr [r13 + rax + 7], 7 + pinsrb xmm14, byte ptr [r13 + r14 + 7], 8 + pinsrb xmm14, byte ptr [r13 + r12 + 7], 9 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + r8 + 7], 10 + pinsrb xmm14, byte ptr [r13 + r9 + 7], 11 + pinsrb xmm14, byte ptr [r13 + rdx + 7], 12 + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + rdi + 7], 13 + pinsrb xmm14, byte ptr [r13 + rcx + 7], 14 movdqa xmm1, xmm14 movdqa xmm14, xmmword ptr [rsp + 176] # 16-byte Reload pcmpeqb xmm2, xmm14 @@ -30000,2064 +31483,1508 @@ comparison_not_equal_scalar_arr_sse4: # @comparison_not_equal_scalar_arr_sse4 movdqa xmm0, xmmword ptr [rip + .LCPI5_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] pandn xmm8, xmm0 por xmm8, xmm2 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [r14 + r8 + 20] + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + movzx esi, byte ptr [r13 + rcx + 20] movd xmm3, esi - pinsrb xmm1, byte ptr [r14 + rax + 7], 15 + pinsrb xmm1, byte ptr [r13 + r10 + 7], 15 + mov r14, r10 pcmpeqb xmm1, xmm14 movdqa xmm0, xmmword ptr [rip + .LCPI5_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] pandn xmm1, xmm0 por xmm1, xmm8 - movzx esi, byte ptr [r14 + r8 + 21] + movzx esi, byte ptr [r13 + rcx + 21] movd xmm2, esi - movdqa xmm0, xmmword ptr [rsp + 240] # 16-byte Reload - mov r11, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + r11 + 8], 1 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + rbx + 8], 2 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + rdi + 8], 3 - pinsrb xmm0, byte ptr [r14 + r12 + 8], 4 - mov rdx, r12 - pinsrb xmm0, byte ptr [r14 + r10 + 8], 5 - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + rsi + 8], 6 - pinsrb xmm0, byte ptr [r14 + r9 + 8], 7 - pinsrb xmm0, byte ptr [r14 + r13 + 8], 8 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + rsi + 8], 9 - pinsrb xmm0, byte ptr [r14 + r15 + 8], 10 - mov r9, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + r9 + 8], 11 - mov r12, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + r12 + 8], 12 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [r14 + rsi + 8], 13 - pinsrb xmm0, byte ptr [r14 + rcx + 8], 14 - pinsrb xmm0, byte ptr [r14 + rax + 8], 15 + movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload + mov rax, r15 + pinsrb xmm0, byte ptr [r13 + r15 + 8], 1 + mov rsi, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rsi + 8], 2 + pinsrb xmm0, byte ptr [r13 + rbx + 8], 3 + mov r15, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r15 + 8], 4 + mov r10, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r10 + 8], 5 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rsi + 8], 6 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r11 + 8], 7 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rsi + 8], 8 + pinsrb xmm0, byte ptr [r13 + r12 + 8], 9 + pinsrb xmm0, byte ptr [r13 + r8 + 8], 10 + pinsrb xmm0, byte ptr [r13 + r9 + 8], 11 + pinsrb xmm0, byte ptr [r13 + rdx + 8], 12 + pinsrb xmm0, byte ptr [r13 + rdi + 8], 13 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rsi + 8], 14 + pinsrb xmm0, byte ptr [r13 + r14 + 8], 15 por xmm1, xmm9 - movdqa xmmword ptr [rsp + 240], xmm1 # 16-byte Spill - movzx esi, byte ptr [r14 + r8 + 22] + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill + movzx esi, byte ptr [r13 + rcx + 22] movd xmm1, esi pcmpeqb xmm0, xmm14 - pinsrb xmm11, byte ptr [r14 + r11 + 9], 1 - mov r10, r11 - pinsrb xmm11, byte ptr [r14 + rbx + 9], 2 - mov rax, rdi - pinsrb xmm11, byte ptr [r14 + rdi + 9], 3 - pinsrb xmm11, byte ptr [r14 + rdx + 9], 4 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + rcx + 9], 5 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + r11 + 9], 6 - mov rsi, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + rsi + 9], 7 - pinsrb xmm11, byte ptr [r14 + r13 + 9], 8 - mov rcx, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + rcx + 9], 9 - pinsrb xmm11, byte ptr [r14 + r15 + 9], 10 - mov rdx, r9 - pinsrb xmm11, byte ptr [r14 + r9 + 9], 11 - mov rdi, r12 - pinsrb xmm11, byte ptr [r14 + r12 + 9], 12 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + rbx + 9], 13 - mov r8, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + r8 + 9], 14 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm11, byte ptr [r14 + r9 + 9], 15 - pinsrb xmm12, byte ptr [r14 + r10 + 10], 1 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm12, byte ptr [r14 + r10 + 10], 2 - pinsrb xmm12, byte ptr [r14 + rax + 10], 3 - mov r12, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm12, byte ptr [r14 + r12 + 10], 4 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm12, byte ptr [r14 + rbx + 10], 5 - pinsrb xmm12, byte ptr [r14 + r11 + 10], 6 - pinsrb xmm12, byte ptr [r14 + rsi + 10], 7 - pinsrb xmm12, byte ptr [r14 + r13 + 10], 8 - pinsrb xmm12, byte ptr [r14 + rcx + 10], 9 - pinsrb xmm12, byte ptr [r14 + r15 + 10], 10 - pinsrb xmm12, byte ptr [r14 + rdx + 10], 11 - pinsrb xmm12, byte ptr [r14 + rdi + 10], 12 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm12, byte ptr [r14 + rbx + 10], 13 - pinsrb xmm12, byte ptr [r14 + r8 + 10], 14 - pinsrb xmm12, byte ptr [r14 + r9 + 10], 15 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + rbx + 11], 1 - pinsrb xmm13, byte ptr [r14 + r10 + 11], 2 - mov r12, r10 - pinsrb xmm13, byte ptr [r14 + rax + 11], 3 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + r10 + 11], 4 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + rax + 11], 5 - pinsrb xmm13, byte ptr [r14 + r11 + 11], 6 - pinsrb xmm13, byte ptr [r14 + rsi + 11], 7 - pinsrb xmm13, byte ptr [r14 + r13 + 11], 8 - pinsrb xmm13, byte ptr [r14 + rcx + 11], 9 - pinsrb xmm13, byte ptr [r14 + r15 + 11], 10 - mov rcx, r15 - pinsrb xmm13, byte ptr [r14 + rdx + 11], 11 - pinsrb xmm13, byte ptr [r14 + rdi + 11], 12 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [r14 + r13 + 11], 13 - pinsrb xmm13, byte ptr [r14 + r8 + 11], 14 - pinsrb xmm13, byte ptr [r14 + r9 + 11], 15 + pinsrb xmm11, byte ptr [r13 + rax + 9], 1 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rcx + 9], 2 + pinsrb xmm11, byte ptr [r13 + rbx + 9], 3 + mov r14, r15 + pinsrb xmm11, byte ptr [r13 + r15 + 9], 4 + pinsrb xmm11, byte ptr [r13 + r10 + 9], 5 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + r10 + 9], 6 + pinsrb xmm11, byte ptr [r13 + r11 + 9], 7 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + r15 + 9], 8 + pinsrb xmm11, byte ptr [r13 + r12 + 9], 9 + pinsrb xmm11, byte ptr [r13 + r8 + 9], 10 + mov rsi, r9 + pinsrb xmm11, byte ptr [r13 + r9 + 9], 11 + mov rax, rdx + pinsrb xmm11, byte ptr [r13 + rdx + 9], 12 + pinsrb xmm11, byte ptr [r13 + rdi + 9], 13 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + r9 + 9], 14 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rdx + 9], 15 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + rdx + 10], 1 + pinsrb xmm12, byte ptr [r13 + rcx + 10], 2 + pinsrb xmm12, byte ptr [r13 + rbx + 10], 3 + pinsrb xmm12, byte ptr [r13 + r14 + 10], 4 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + rdx + 10], 5 + pinsrb xmm12, byte ptr [r13 + r10 + 10], 6 + pinsrb xmm12, byte ptr [r13 + r11 + 10], 7 + pinsrb xmm12, byte ptr [r13 + r15 + 10], 8 + pinsrb xmm12, byte ptr [r13 + r12 + 10], 9 + pinsrb xmm12, byte ptr [r13 + r8 + 10], 10 + pinsrb xmm12, byte ptr [r13 + rsi + 10], 11 + pinsrb xmm12, byte ptr [r13 + rax + 10], 12 + pinsrb xmm12, byte ptr [r13 + rdi + 10], 13 + pinsrb xmm12, byte ptr [r13 + r9 + 10], 14 + mov r11, r9 + mov r9, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + r9 + 10], 15 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rax + 11], 1 + pinsrb xmm13, byte ptr [r13 + rcx + 11], 2 + pinsrb xmm13, byte ptr [r13 + rbx + 11], 3 + mov rcx, rbx + pinsrb xmm13, byte ptr [r13 + r14 + 11], 4 + mov rbx, r14 + pinsrb xmm13, byte ptr [r13 + rdx + 11], 5 + pinsrb xmm13, byte ptr [r13 + r10 + 11], 6 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rdx + 11], 7 + pinsrb xmm13, byte ptr [r13 + r15 + 11], 8 + mov rdx, r15 + pinsrb xmm13, byte ptr [r13 + r12 + 11], 9 + pinsrb xmm13, byte ptr [r13 + r8 + 11], 10 + pinsrb xmm13, byte ptr [r13 + rsi + 11], 11 + mov r12, rsi + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rsi + 11], 12 + pinsrb xmm13, byte ptr [r13 + rdi + 11], 13 + pinsrb xmm13, byte ptr [r13 + r11 + 11], 14 + pinsrb xmm13, byte ptr [r13 + r9 + 11], 15 pcmpeqb xmm11, xmm14 pandn xmm11, xmmword ptr [rip + .LCPI5_16] paddb xmm11, xmm0 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [r14 + rax + 23] + mov rax, qword ptr [rsp + 120] # 8-byte Reload + movzx esi, byte ptr [r13 + rax + 23] movd xmm8, esi pcmpeqb xmm12, xmm14 pandn xmm12, xmmword ptr [rip + .LCPI5_17] pcmpeqb xmm13, xmm14 pandn xmm13, xmmword ptr [rip + .LCPI5_18] por xmm13, xmm12 - movzx esi, byte ptr [r14 + rax + 24] + movzx esi, byte ptr [r13 + rax + 24] movd xmm12, esi - movdqa xmm9, xmmword ptr [rsp + 208] # 16-byte Reload - pinsrb xmm9, byte ptr [r14 + rbx + 12], 1 - pinsrb xmm9, byte ptr [r14 + r12 + 12], 2 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r15 + 12], 3 - mov rbx, r10 - pinsrb xmm9, byte ptr [r14 + r10 + 12], 4 - mov r10, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r10 + 12], 5 - mov r9, r11 - pinsrb xmm9, byte ptr [r14 + r11 + 12], 6 - mov r11, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r11 + 12], 7 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + r8 + 12], 8 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rsi + 12], 9 - pinsrb xmm9, byte ptr [r14 + rcx + 12], 10 - pinsrb xmm9, byte ptr [r14 + rdx + 12], 11 - pinsrb xmm9, byte ptr [r14 + rdi + 12], 12 - pinsrb xmm9, byte ptr [r14 + r13 + 12], 13 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 12], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm9, byte ptr [r14 + rax + 12], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rax + 13], 1 - pinsrb xmm6, byte ptr [r14 + r12 + 13], 2 - pinsrb xmm6, byte ptr [r14 + r15 + 13], 3 - pinsrb xmm6, byte ptr [r14 + rbx + 13], 4 - pinsrb xmm6, byte ptr [r14 + r10 + 13], 5 - pinsrb xmm6, byte ptr [r14 + r9 + 13], 6 - pinsrb xmm6, byte ptr [r14 + r11 + 13], 7 - pinsrb xmm6, byte ptr [r14 + r8 + 13], 8 - pinsrb xmm6, byte ptr [r14 + rsi + 13], 9 - pinsrb xmm6, byte ptr [r14 + rcx + 13], 10 - pinsrb xmm6, byte ptr [r14 + rdx + 13], 11 - pinsrb xmm6, byte ptr [r14 + rdi + 13], 12 - pinsrb xmm6, byte ptr [r14 + r13 + 13], 13 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r13 + 13], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rax + 13], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [r14 + rax + 14], 1 - pinsrb xmm15, byte ptr [r14 + r12 + 14], 2 - pinsrb xmm15, byte ptr [r14 + r15 + 14], 3 - pinsrb xmm15, byte ptr [r14 + rbx + 14], 4 - pinsrb xmm15, byte ptr [r14 + r10 + 14], 5 - mov r12, r10 - pinsrb xmm15, byte ptr [r14 + r9 + 14], 6 - mov r10, r9 - pinsrb xmm15, byte ptr [r14 + r11 + 14], 7 - mov r9, r11 - pinsrb xmm15, byte ptr [r14 + r8 + 14], 8 - pinsrb xmm15, byte ptr [r14 + rsi + 14], 9 - pinsrb xmm15, byte ptr [r14 + rcx + 14], 10 - mov r11, rcx - pinsrb xmm15, byte ptr [r14 + rdx + 14], 11 - pinsrb xmm15, byte ptr [r14 + rdi + 14], 12 - mov rdx, rdi + movdqa xmm9, xmmword ptr [rsp + 224] # 16-byte Reload + mov r14, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r14 + 12], 1 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rax + 12], 2 + pinsrb xmm9, byte ptr [r13 + rcx + 12], 3 + pinsrb xmm9, byte ptr [r13 + rbx + 12], 4 + mov r15, rbx + mov r9, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r9 + 12], 5 + pinsrb xmm9, byte ptr [r13 + r10 + 12], 6 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rsi + 12], 7 + pinsrb xmm9, byte ptr [r13 + rdx + 12], 8 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rcx + 12], 9 + pinsrb xmm9, byte ptr [r13 + r8 + 12], 10 + mov rcx, r12 + pinsrb xmm9, byte ptr [r13 + r12 + 12], 11 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rdx + 12], 12 + mov r10, rdi + pinsrb xmm9, byte ptr [r13 + rdi + 12], 13 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r11 + 12], 14 mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [r14 + rbx + 14], 13 - pinsrb xmm15, byte ptr [r14 + r13 + 14], 14 + pinsrb xmm9, byte ptr [r13 + rbx + 12], 15 + pinsrb xmm6, byte ptr [r13 + r14 + 13], 1 + pinsrb xmm6, byte ptr [r13 + rax + 13], 2 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r12 + 13], 3 + pinsrb xmm6, byte ptr [r13 + r15 + 13], 4 + pinsrb xmm6, byte ptr [r13 + r9 + 13], 5 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdi + 13], 6 + pinsrb xmm6, byte ptr [r13 + rsi + 13], 7 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r15 + 13], 8 + mov rdi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdi + 13], 9 + pinsrb xmm6, byte ptr [r13 + r8 + 13], 10 + pinsrb xmm6, byte ptr [r13 + rcx + 13], 11 + pinsrb xmm6, byte ptr [r13 + rdx + 13], 12 + pinsrb xmm6, byte ptr [r13 + r10 + 13], 13 + pinsrb xmm6, byte ptr [r13 + r11 + 13], 14 + pinsrb xmm6, byte ptr [r13 + rbx + 13], 15 + pinsrb xmm15, byte ptr [r13 + r14 + 14], 1 + pinsrb xmm15, byte ptr [r13 + rax + 14], 2 + pinsrb xmm15, byte ptr [r13 + r12 + 14], 3 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rax + 14], 4 + pinsrb xmm15, byte ptr [r13 + r9 + 14], 5 + mov r14, r9 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rbx + 14], 6 + pinsrb xmm15, byte ptr [r13 + rsi + 14], 7 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + r15 + 14], 8 + mov r9, rdi + pinsrb xmm15, byte ptr [r13 + rdi + 14], 9 + pinsrb xmm15, byte ptr [r13 + r8 + 14], 10 + mov rax, r8 + pinsrb xmm15, byte ptr [r13 + rcx + 14], 11 + pinsrb xmm15, byte ptr [r13 + rdx + 14], 12 + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rdi + 14], 13 + mov r10, r11 + pinsrb xmm15, byte ptr [r13 + r11 + 14], 14 pcmpeqb xmm9, xmm14 pandn xmm9, xmmword ptr [rip + .LCPI5_19] por xmm9, xmm13 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [r14 + rcx + 25] + mov r12, qword ptr [rsp + 120] # 8-byte Reload + movzx esi, byte ptr [r13 + r12 + 25] movd xmm13, esi psubb xmm11, xmmword ptr [rip + .LCPI5_22] por xmm9, xmm11 - movzx esi, byte ptr [r14 + rcx + 26] + movzx esi, byte ptr [r13 + r12 + 26] movd xmm0, esi - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm15, byte ptr [r14 + rax + 14], 15 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rcx + 14], 15 pcmpeqb xmm6, xmm14 pandn xmm6, xmmword ptr [rip + .LCPI5_20] pcmpeqb xmm15, xmm14 pandn xmm15, xmmword ptr [rip + .LCPI5_21] por xmm15, xmm6 - movzx esi, byte ptr [r14 + rcx + 27] + movzx esi, byte ptr [r13 + r12 + 27] movd xmm11, esi movdqa xmm6, xmmword ptr [rsp + 192] # 16-byte Reload - mov r15, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r15 + 15], 1 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rcx + 15], 2 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rdi + 15], 3 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r8 + 15], 4 - pinsrb xmm6, byte ptr [r14 + r12 + 15], 5 - mov rcx, r10 - pinsrb xmm6, byte ptr [r14 + r10 + 15], 6 - pinsrb xmm6, byte ptr [r14 + r9 + 15], 7 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + rsi + 15], 8 - mov r9, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r9 + 15], 9 - pinsrb xmm6, byte ptr [r14 + r11 + 15], 10 - mov r10, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm6, byte ptr [r14 + r10 + 15], 11 - pinsrb xmm6, byte ptr [r14 + rdx + 15], 12 - pinsrb xmm6, byte ptr [r14 + rbx + 15], 13 - pinsrb xmm6, byte ptr [r14 + r13 + 15], 14 - pinsrb xmm6, byte ptr [r14 + rax + 15], 15 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdx + 15], 1 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdx + 15], 2 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r11 + 15], 3 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r8 + 15], 4 + pinsrb xmm6, byte ptr [r13 + r14 + 15], 5 + pinsrb xmm6, byte ptr [r13 + rbx + 15], 6 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rsi + 15], 7 + pinsrb xmm6, byte ptr [r13 + r15 + 15], 8 + mov r14, r15 + mov r15, r9 + pinsrb xmm6, byte ptr [r13 + r9 + 15], 9 + pinsrb xmm6, byte ptr [r13 + rax + 15], 10 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rax + 15], 11 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rbx + 15], 12 + pinsrb xmm6, byte ptr [r13 + rdi + 15], 13 + pinsrb xmm6, byte ptr [r13 + r10 + 15], 14 + pinsrb xmm6, byte ptr [r13 + rcx + 15], 15 pcmpeqb xmm6, xmm14 pandn xmm6, xmmword ptr [rip + .LCPI5_6] por xmm6, xmm15 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [r14 + rax + 28] + movzx esi, byte ptr [r13 + r12 + 28] movd xmm15, esi por xmm6, xmm9 movdqa xmmword ptr [rsp + 192], xmm6 # 16-byte Spill - movzx esi, byte ptr [r14 + rax + 29] + movzx esi, byte ptr [r13 + r12 + 29] movd xmm9, esi - mov rsi, r15 - pinsrb xmm10, byte ptr [r14 + r15 + 16], 1 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rsi + 16], 1 + pinsrb xmm10, byte ptr [r13 + rdx + 16], 2 + mov r10, rdx + mov rcx, r11 + pinsrb xmm10, byte ptr [r13 + r11 + 16], 3 + pinsrb xmm10, byte ptr [r13 + r8 + 16], 4 + mov r11, r8 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r9 + 16], 5 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rdi + 16], 6 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r8 + 16], 7 + pinsrb xmm10, byte ptr [r13 + r14 + 16], 8 + mov rdx, r15 + pinsrb xmm10, byte ptr [r13 + r15 + 16], 9 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r14 + 16], 10 + pinsrb xmm10, byte ptr [r13 + rax + 16], 11 + pinsrb xmm10, byte ptr [r13 + rbx + 16], 12 mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rax + 16], 2 - pinsrb xmm10, byte ptr [r14 + rdi + 16], 3 - mov r11, rdi - pinsrb xmm10, byte ptr [r14 + r8 + 16], 4 - pinsrb xmm10, byte ptr [r14 + r12 + 16], 5 - pinsrb xmm10, byte ptr [r14 + rcx + 16], 6 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rdx + 16], 7 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rcx + 16], 8 - pinsrb xmm10, byte ptr [r14 + r9 + 16], 9 - mov r15, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + r15 + 16], 10 - pinsrb xmm10, byte ptr [r14 + r10 + 16], 11 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rdi + 16], 12 - pinsrb xmm10, byte ptr [r14 + rbx + 16], 13 - pinsrb xmm10, byte ptr [r14 + r13 + 16], 14 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [r14 + rax + 16], 15 - pinsrb xmm4, byte ptr [r14 + rsi + 17], 1 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rsi + 17], 2 - pinsrb xmm4, byte ptr [r14 + r11 + 17], 3 - pinsrb xmm4, byte ptr [r14 + r8 + 17], 4 - pinsrb xmm4, byte ptr [r14 + r12 + 17], 5 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + r10 + 17], 6 - pinsrb xmm4, byte ptr [r14 + rdx + 17], 7 - pinsrb xmm4, byte ptr [r14 + rcx + 17], 8 - pinsrb xmm4, byte ptr [r14 + r9 + 17], 9 - mov r8, r15 - pinsrb xmm4, byte ptr [r14 + r15 + 17], 10 - mov rdx, qword ptr [rsp + 152] # 8-byte Reload - pinsrb xmm4, byte ptr [r14 + rdx + 17], 11 - pinsrb xmm4, byte ptr [r14 + rdi + 17], 12 - mov r11, rdi - pinsrb xmm4, byte ptr [r14 + rbx + 17], 13 - pinsrb xmm4, byte ptr [r14 + r13 + 17], 14 - pinsrb xmm4, byte ptr [r14 + rax + 17], 15 - mov rcx, rax + pinsrb xmm10, byte ptr [r13 + rax + 16], 13 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rbx + 16], 14 + mov r15, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r15 + 16], 15 + pinsrb xmm4, byte ptr [r13 + rsi + 17], 1 + pinsrb xmm4, byte ptr [r13 + r10 + 17], 2 + pinsrb xmm4, byte ptr [r13 + rcx + 17], 3 + pinsrb xmm4, byte ptr [r13 + r11 + 17], 4 + pinsrb xmm4, byte ptr [r13 + r9 + 17], 5 + pinsrb xmm4, byte ptr [r13 + rdi + 17], 6 + pinsrb xmm4, byte ptr [r13 + r8 + 17], 7 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rcx + 17], 8 + pinsrb xmm4, byte ptr [r13 + rdx + 17], 9 + mov r8, r14 + pinsrb xmm4, byte ptr [r13 + r14 + 17], 10 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rcx + 17], 11 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rdx + 17], 12 + pinsrb xmm4, byte ptr [r13 + rax + 17], 13 + pinsrb xmm4, byte ptr [r13 + rbx + 17], 14 + mov r10, r15 + pinsrb xmm4, byte ptr [r13 + r15 + 17], 15 pcmpeqb xmm10, xmm14 pcmpeqb xmm4, xmm14 movdqa xmm6, xmmword ptr [rip + .LCPI5_16] # xmm6 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] pandn xmm4, xmm6 paddb xmm4, xmm10 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [r14 + rax + 30] + movzx esi, byte ptr [r13 + r12 + 30] movd xmm10, esi - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rsi + 18], 1 - pinsrb xmm5, byte ptr [r14 + rsi + 19], 1 - pinsrb xmm3, byte ptr [r14 + rsi + 20], 1 - pinsrb xmm2, byte ptr [r14 + rsi + 21], 1 - pinsrb xmm1, byte ptr [r14 + rsi + 22], 1 - pinsrb xmm8, byte ptr [r14 + rsi + 23], 1 - pinsrb xmm12, byte ptr [r14 + rsi + 24], 1 - pinsrb xmm13, byte ptr [r14 + rsi + 25], 1 - pinsrb xmm0, byte ptr [r14 + rsi + 26], 1 - pinsrb xmm11, byte ptr [r14 + rsi + 27], 1 - pinsrb xmm15, byte ptr [r14 + rsi + 28], 1 - pinsrb xmm9, byte ptr [r14 + rsi + 29], 1 - pinsrb xmm10, byte ptr [r14 + rsi + 30], 1 - movzx eax, byte ptr [r14 + rax + 31] + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rsi + 18], 1 + pinsrb xmm5, byte ptr [r13 + rsi + 19], 1 + pinsrb xmm3, byte ptr [r13 + rsi + 20], 1 + pinsrb xmm2, byte ptr [r13 + rsi + 21], 1 + pinsrb xmm1, byte ptr [r13 + rsi + 22], 1 + pinsrb xmm8, byte ptr [r13 + rsi + 23], 1 + pinsrb xmm12, byte ptr [r13 + rsi + 24], 1 + pinsrb xmm13, byte ptr [r13 + rsi + 25], 1 + pinsrb xmm0, byte ptr [r13 + rsi + 26], 1 + pinsrb xmm11, byte ptr [r13 + rsi + 27], 1 + pinsrb xmm15, byte ptr [r13 + rsi + 28], 1 + pinsrb xmm9, byte ptr [r13 + rsi + 29], 1 + pinsrb xmm10, byte ptr [r13 + rsi + 30], 1 + movzx eax, byte ptr [r13 + r12 + 31] movd xmm6, eax - pinsrb xmm6, byte ptr [r14 + rsi + 31], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 18], 2 - pinsrb xmm5, byte ptr [r14 + rax + 19], 2 - pinsrb xmm3, byte ptr [r14 + rax + 20], 2 - pinsrb xmm2, byte ptr [r14 + rax + 21], 2 - pinsrb xmm1, byte ptr [r14 + rax + 22], 2 - pinsrb xmm8, byte ptr [r14 + rax + 23], 2 - pinsrb xmm12, byte ptr [r14 + rax + 24], 2 - pinsrb xmm13, byte ptr [r14 + rax + 25], 2 - pinsrb xmm0, byte ptr [r14 + rax + 26], 2 - pinsrb xmm11, byte ptr [r14 + rax + 27], 2 - pinsrb xmm15, byte ptr [r14 + rax + 28], 2 - pinsrb xmm9, byte ptr [r14 + rax + 29], 2 - pinsrb xmm10, byte ptr [r14 + rax + 30], 2 - pinsrb xmm6, byte ptr [r14 + rax + 31], 2 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + r15 + 18], 3 - mov rax, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rax + 18], 4 - pinsrb xmm7, byte ptr [r14 + r12 + 18], 5 - pinsrb xmm7, byte ptr [r14 + r10 + 18], 6 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rdi + 18], 7 - mov r9, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + r9 + 18], 8 - mov rsi, qword ptr [rsp + 136] # 8-byte Reload - pinsrb xmm7, byte ptr [r14 + rsi + 18], 9 - pinsrb xmm7, byte ptr [r14 + r8 + 18], 10 - pinsrb xmm7, byte ptr [r14 + rdx + 18], 11 - pinsrb xmm7, byte ptr [r14 + r11 + 18], 12 - pinsrb xmm7, byte ptr [r14 + rbx + 18], 13 - pinsrb xmm7, byte ptr [r14 + r13 + 18], 14 - pinsrb xmm7, byte ptr [r14 + rcx + 18], 15 - pinsrb xmm5, byte ptr [r14 + r15 + 19], 3 - pinsrb xmm5, byte ptr [r14 + rax + 19], 4 - pinsrb xmm5, byte ptr [r14 + r12 + 19], 5 - pinsrb xmm5, byte ptr [r14 + r10 + 19], 6 - pinsrb xmm5, byte ptr [r14 + rdi + 19], 7 - pinsrb xmm5, byte ptr [r14 + r9 + 19], 8 - pinsrb xmm5, byte ptr [r14 + rsi + 19], 9 - pinsrb xmm5, byte ptr [r14 + r8 + 19], 10 - pinsrb xmm5, byte ptr [r14 + rdx + 19], 11 - pinsrb xmm5, byte ptr [r14 + r11 + 19], 12 - pinsrb xmm5, byte ptr [r14 + rbx + 19], 13 - pinsrb xmm5, byte ptr [r14 + r13 + 19], 14 - pinsrb xmm5, byte ptr [r14 + rcx + 19], 15 - pinsrb xmm3, byte ptr [r14 + r15 + 20], 3 - pinsrb xmm3, byte ptr [r14 + rax + 20], 4 - pinsrb xmm3, byte ptr [r14 + r12 + 20], 5 - pinsrb xmm3, byte ptr [r14 + r10 + 20], 6 - pinsrb xmm3, byte ptr [r14 + rdi + 20], 7 - pinsrb xmm3, byte ptr [r14 + r9 + 20], 8 - pinsrb xmm3, byte ptr [r14 + rsi + 20], 9 - pinsrb xmm3, byte ptr [r14 + r8 + 20], 10 - pinsrb xmm3, byte ptr [r14 + rdx + 20], 11 - pinsrb xmm3, byte ptr [r14 + r11 + 20], 12 - pinsrb xmm3, byte ptr [r14 + rbx + 20], 13 - pinsrb xmm3, byte ptr [r14 + r13 + 20], 14 - pcmpeqb xmm7, xmm14 - movdqa xmm14, xmmword ptr [rip + .LCPI5_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm7, xmm14 - pcmpeqb xmm5, xmmword ptr [rsp + 176] # 16-byte Folded Reload - movdqa xmm14, xmmword ptr [rip + .LCPI5_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm5, xmm14 - por xmm5, xmm7 - pinsrb xmm3, byte ptr [r14 + rcx + 20], 15 - movdqa xmm14, xmmword ptr [rsp + 176] # 16-byte Reload - pcmpeqb xmm3, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI5_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm3, xmm7 - por xmm3, xmm5 - pcmpeqd xmm5, xmm5 - psubb xmm4, xmm5 - por xmm3, xmm4 - pinsrb xmm2, byte ptr [r14 + r15 + 21], 3 - pinsrb xmm2, byte ptr [r14 + rax + 21], 4 - pinsrb xmm2, byte ptr [r14 + r12 + 21], 5 - pinsrb xmm2, byte ptr [r14 + r10 + 21], 6 - pinsrb xmm2, byte ptr [r14 + rdi + 21], 7 - pinsrb xmm2, byte ptr [r14 + r9 + 21], 8 - pinsrb xmm2, byte ptr [r14 + rsi + 21], 9 - pinsrb xmm2, byte ptr [r14 + r8 + 21], 10 - pinsrb xmm2, byte ptr [r14 + rdx + 21], 11 - pinsrb xmm2, byte ptr [r14 + r11 + 21], 12 - pinsrb xmm2, byte ptr [r14 + rbx + 21], 13 - pinsrb xmm2, byte ptr [r14 + r13 + 21], 14 - pinsrb xmm2, byte ptr [r14 + rcx + 21], 15 - pinsrb xmm1, byte ptr [r14 + r15 + 22], 3 - pinsrb xmm1, byte ptr [r14 + rax + 22], 4 - pinsrb xmm1, byte ptr [r14 + r12 + 22], 5 - pinsrb xmm1, byte ptr [r14 + r10 + 22], 6 - pinsrb xmm1, byte ptr [r14 + rdi + 22], 7 - pinsrb xmm1, byte ptr [r14 + r9 + 22], 8 - pinsrb xmm1, byte ptr [r14 + rsi + 22], 9 - pinsrb xmm1, byte ptr [r14 + r8 + 22], 10 - pinsrb xmm1, byte ptr [r14 + rdx + 22], 11 - pinsrb xmm1, byte ptr [r14 + r11 + 22], 12 - pinsrb xmm1, byte ptr [r14 + rbx + 22], 13 - pinsrb xmm1, byte ptr [r14 + r13 + 22], 14 - pinsrb xmm1, byte ptr [r14 + rcx + 22], 15 - pinsrb xmm8, byte ptr [r14 + r15 + 23], 3 - pinsrb xmm8, byte ptr [r14 + rax + 23], 4 - pinsrb xmm8, byte ptr [r14 + r12 + 23], 5 - pinsrb xmm8, byte ptr [r14 + r10 + 23], 6 - pinsrb xmm8, byte ptr [r14 + rdi + 23], 7 - pinsrb xmm8, byte ptr [r14 + r9 + 23], 8 - pinsrb xmm8, byte ptr [r14 + rsi + 23], 9 - pinsrb xmm8, byte ptr [r14 + r8 + 23], 10 - pinsrb xmm8, byte ptr [r14 + rdx + 23], 11 - pinsrb xmm8, byte ptr [r14 + r11 + 23], 12 - pinsrb xmm8, byte ptr [r14 + rbx + 23], 13 - pinsrb xmm8, byte ptr [r14 + r13 + 23], 14 - pcmpeqb xmm2, xmm14 - movdqa xmm5, xmmword ptr [rip + .LCPI5_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm5 - pcmpeqb xmm1, xmm14 - movdqa xmm7, xmmword ptr [rip + .LCPI5_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm1, xmm7 - por xmm1, xmm2 - pinsrb xmm8, byte ptr [r14 + rcx + 23], 15 - pcmpeqb xmm8, xmm14 - movdqa xmm4, xmmword ptr [rip + .LCPI5_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm8, xmm4 - por xmm8, xmm1 - pinsrb xmm12, byte ptr [r14 + r15 + 24], 3 - pinsrb xmm12, byte ptr [r14 + rax + 24], 4 - pinsrb xmm12, byte ptr [r14 + r12 + 24], 5 - pinsrb xmm12, byte ptr [r14 + r10 + 24], 6 - pinsrb xmm12, byte ptr [r14 + rdi + 24], 7 - pinsrb xmm12, byte ptr [r14 + r9 + 24], 8 - pinsrb xmm12, byte ptr [r14 + rsi + 24], 9 - pinsrb xmm12, byte ptr [r14 + r8 + 24], 10 - pinsrb xmm12, byte ptr [r14 + rdx + 24], 11 - pinsrb xmm12, byte ptr [r14 + r11 + 24], 12 - pinsrb xmm12, byte ptr [r14 + rbx + 24], 13 - pinsrb xmm12, byte ptr [r14 + r13 + 24], 14 - pinsrb xmm12, byte ptr [r14 + rcx + 24], 15 - por xmm8, xmm3 - pcmpeqb xmm12, xmm14 - pinsrb xmm13, byte ptr [r14 + r15 + 25], 3 - pinsrb xmm13, byte ptr [r14 + rax + 25], 4 - pinsrb xmm13, byte ptr [r14 + r12 + 25], 5 - pinsrb xmm13, byte ptr [r14 + r10 + 25], 6 - pinsrb xmm13, byte ptr [r14 + rdi + 25], 7 - pinsrb xmm13, byte ptr [r14 + r9 + 25], 8 - pinsrb xmm13, byte ptr [r14 + rsi + 25], 9 - pinsrb xmm13, byte ptr [r14 + r8 + 25], 10 - pinsrb xmm13, byte ptr [r14 + rdx + 25], 11 - pinsrb xmm13, byte ptr [r14 + r11 + 25], 12 - pinsrb xmm13, byte ptr [r14 + rbx + 25], 13 - pinsrb xmm13, byte ptr [r14 + r13 + 25], 14 - pinsrb xmm13, byte ptr [r14 + rcx + 25], 15 - pinsrb xmm0, byte ptr [r14 + r15 + 26], 3 - pinsrb xmm0, byte ptr [r14 + rax + 26], 4 - pinsrb xmm0, byte ptr [r14 + r12 + 26], 5 - pinsrb xmm0, byte ptr [r14 + r10 + 26], 6 - pinsrb xmm0, byte ptr [r14 + rdi + 26], 7 - pinsrb xmm0, byte ptr [r14 + r9 + 26], 8 - pinsrb xmm0, byte ptr [r14 + rsi + 26], 9 - pinsrb xmm0, byte ptr [r14 + r8 + 26], 10 - pinsrb xmm0, byte ptr [r14 + rdx + 26], 11 - pinsrb xmm0, byte ptr [r14 + r11 + 26], 12 - pinsrb xmm0, byte ptr [r14 + rbx + 26], 13 - pinsrb xmm0, byte ptr [r14 + r13 + 26], 14 - pinsrb xmm0, byte ptr [r14 + rcx + 26], 15 - pinsrb xmm11, byte ptr [r14 + r15 + 27], 3 - pinsrb xmm11, byte ptr [r14 + rax + 27], 4 - pinsrb xmm11, byte ptr [r14 + r12 + 27], 5 - pinsrb xmm11, byte ptr [r14 + r10 + 27], 6 - pinsrb xmm11, byte ptr [r14 + rdi + 27], 7 - pinsrb xmm11, byte ptr [r14 + r9 + 27], 8 - pinsrb xmm11, byte ptr [r14 + rsi + 27], 9 - pinsrb xmm11, byte ptr [r14 + r8 + 27], 10 - pinsrb xmm11, byte ptr [r14 + rdx + 27], 11 - pinsrb xmm11, byte ptr [r14 + r11 + 27], 12 - pinsrb xmm11, byte ptr [r14 + rbx + 27], 13 - pinsrb xmm11, byte ptr [r14 + r13 + 27], 14 - pcmpeqb xmm13, xmm14 - pandn xmm13, xmmword ptr [rip + .LCPI5_16] - paddb xmm13, xmm12 - pinsrb xmm11, byte ptr [r14 + rcx + 27], 15 - pcmpeqb xmm0, xmm14 - pandn xmm0, xmmword ptr [rip + .LCPI5_17] - pcmpeqb xmm11, xmm14 - pandn xmm11, xmmword ptr [rip + .LCPI5_18] - por xmm11, xmm0 - pinsrb xmm15, byte ptr [r14 + r15 + 28], 3 - pinsrb xmm9, byte ptr [r14 + r15 + 29], 3 - pinsrb xmm10, byte ptr [r14 + r15 + 30], 3 - pinsrb xmm6, byte ptr [r14 + r15 + 31], 3 - pinsrb xmm15, byte ptr [r14 + rax + 28], 4 - pinsrb xmm9, byte ptr [r14 + rax + 29], 4 - pinsrb xmm10, byte ptr [r14 + rax + 30], 4 - pinsrb xmm6, byte ptr [r14 + rax + 31], 4 - pinsrb xmm15, byte ptr [r14 + r12 + 28], 5 - pinsrb xmm9, byte ptr [r14 + r12 + 29], 5 - pinsrb xmm10, byte ptr [r14 + r12 + 30], 5 - pinsrb xmm6, byte ptr [r14 + r12 + 31], 5 - mov rax, r10 - pinsrb xmm15, byte ptr [r14 + r10 + 28], 6 - pinsrb xmm9, byte ptr [r14 + r10 + 29], 6 - pinsrb xmm10, byte ptr [r14 + r10 + 30], 6 - pinsrb xmm6, byte ptr [r14 + r10 + 31], 6 - mov rax, rdi - pinsrb xmm15, byte ptr [r14 + rdi + 28], 7 - pinsrb xmm9, byte ptr [r14 + rdi + 29], 7 - pinsrb xmm10, byte ptr [r14 + rdi + 30], 7 - pinsrb xmm6, byte ptr [r14 + rdi + 31], 7 - mov rax, r9 - pinsrb xmm15, byte ptr [r14 + r9 + 28], 8 - pinsrb xmm9, byte ptr [r14 + r9 + 29], 8 - pinsrb xmm10, byte ptr [r14 + r9 + 30], 8 - pinsrb xmm6, byte ptr [r14 + r9 + 31], 8 - mov rax, rsi - pinsrb xmm15, byte ptr [r14 + rsi + 28], 9 - pinsrb xmm9, byte ptr [r14 + rsi + 29], 9 - pinsrb xmm10, byte ptr [r14 + rsi + 30], 9 - pinsrb xmm6, byte ptr [r14 + rsi + 31], 9 - mov rax, r8 - pinsrb xmm15, byte ptr [r14 + r8 + 28], 10 - pinsrb xmm9, byte ptr [r14 + r8 + 29], 10 - pinsrb xmm10, byte ptr [r14 + r8 + 30], 10 - pinsrb xmm6, byte ptr [r14 + r8 + 31], 10 - mov rax, rdx - pinsrb xmm15, byte ptr [r14 + rdx + 28], 11 - pinsrb xmm9, byte ptr [r14 + rdx + 29], 11 - pinsrb xmm10, byte ptr [r14 + rdx + 30], 11 - pinsrb xmm6, byte ptr [r14 + rdx + 31], 11 - mov rax, r11 - pinsrb xmm15, byte ptr [r14 + r11 + 28], 12 - pinsrb xmm9, byte ptr [r14 + r11 + 29], 12 - pinsrb xmm10, byte ptr [r14 + r11 + 30], 12 - pinsrb xmm6, byte ptr [r14 + r11 + 31], 12 - pinsrb xmm15, byte ptr [r14 + rbx + 28], 13 - pinsrb xmm9, byte ptr [r14 + rbx + 29], 13 - pinsrb xmm10, byte ptr [r14 + rbx + 30], 13 - pinsrb xmm6, byte ptr [r14 + rbx + 31], 13 - mov rax, r13 - pinsrb xmm15, byte ptr [r14 + r13 + 28], 14 - pinsrb xmm9, byte ptr [r14 + r13 + 29], 14 - pinsrb xmm10, byte ptr [r14 + r13 + 30], 14 - pinsrb xmm6, byte ptr [r14 + r13 + 31], 14 - pinsrb xmm15, byte ptr [r14 + rcx + 28], 15 - pinsrb xmm9, byte ptr [r14 + rcx + 29], 15 - pinsrb xmm10, byte ptr [r14 + rcx + 30], 15 - pcmpeqb xmm15, xmm14 - pandn xmm15, xmmword ptr [rip + .LCPI5_19] - por xmm15, xmm11 - pinsrb xmm6, byte ptr [r14 + rcx + 31], 15 - psubb xmm13, xmmword ptr [rip + .LCPI5_22] - por xmm15, xmm13 - pcmpeqb xmm9, xmm14 - pandn xmm9, xmm5 - pcmpeqb xmm10, xmm14 - pandn xmm10, xmm7 - por xmm10, xmm9 - pcmpeqb xmm6, xmm14 - pandn xmm6, xmm4 - por xmm6, xmm10 - por xmm6, xmm15 - movdqa xmm0, xmm8 - punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] - movdqa xmm3, xmmword ptr [rsp + 240] # 16-byte Reload - movdqa xmm1, xmm3 - movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload - punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] - movdqa xmm2, xmm1 - punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] - punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] - punpckhbw xmm3, xmm4 # xmm3 = xmm3[8],xmm4[8],xmm3[9],xmm4[9],xmm3[10],xmm4[10],xmm3[11],xmm4[11],xmm3[12],xmm4[12],xmm3[13],xmm4[13],xmm3[14],xmm4[14],xmm3[15],xmm4[15] - movdqa xmm0, xmm3 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] - mov rcx, qword ptr [rsp + 168] # 8-byte Reload - mov rax, qword ptr [rsp + 8] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx + 48], xmm3 - movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm1 - movdqu xmmword ptr [rax + 4*rcx], xmm2 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB5_68 -# %bb.69: - mov r10, qword ptr [rsp + 264] # 8-byte Reload - cmp r10, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r14, qword ptr [rsp + 272] # 8-byte Reload - mov r15, qword ptr [rsp + 160] # 8-byte Reload - jne .LBB5_70 - jmp .LBB5_73 -.LBB5_110: - and r10, -8 - mov rax, r10 - shl rax, 6 - add rax, r14 - mov qword ptr [rsp + 48], rax # 8-byte Spill - mov qword ptr [rsp + 40], r10 # 8-byte Spill - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - mov qword ptr [rsp + 56], rax # 8-byte Spill - movd xmm0, r11d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] - xor edi, edi - pxor xmm9, xmm9 - .p2align 4, 0x90 -.LBB5_111: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 64], rdi # 8-byte Spill - shl rdi, 6 - mov r15, rdi - mov rsi, rdi - mov r12, rdi - mov rdx, rdi - mov rbx, rdi - mov r9, rdi - movzx eax, word ptr [r14 + rdi] - movd xmm5, eax - movzx eax, word ptr [r14 + rdi + 2] - movd xmm0, eax - movzx eax, word ptr [r14 + rdi + 4] - movd xmm1, eax - movzx eax, word ptr [r14 + rdi + 6] - movd xmm7, eax - movzx eax, word ptr [r14 + rdi + 8] - movd xmm8, eax - movzx eax, word ptr [r14 + rdi + 10] - movd xmm4, eax - movzx eax, word ptr [r14 + rdi + 12] - movzx r8d, word ptr [r14 + rdi + 14] - movzx r10d, word ptr [r14 + rdi + 16] - movzx r13d, word ptr [r14 + rdi + 18] - movzx ecx, word ptr [r14 + rdi + 20] - mov dword ptr [rsp + 32], ecx # 4-byte Spill - mov rcx, rdi - or rcx, 64 - or r15, 128 - or rsi, 192 - or r12, 256 - or rdx, 320 - or rbx, 384 - pinsrw xmm5, word ptr [r14 + rcx], 1 - pinsrw xmm5, word ptr [r14 + r15], 2 - pinsrw xmm5, word ptr [r14 + rsi], 3 - pinsrw xmm5, word ptr [r14 + r12], 4 - pinsrw xmm5, word ptr [r14 + rdx], 5 - pinsrw xmm5, word ptr [r14 + rbx], 6 - pinsrw xmm0, word ptr [r14 + rcx + 2], 1 - pinsrw xmm0, word ptr [r14 + r15 + 2], 2 - pinsrw xmm0, word ptr [r14 + rsi + 2], 3 - pinsrw xmm0, word ptr [r14 + r12 + 2], 4 - pinsrw xmm0, word ptr [r14 + rdx + 2], 5 - pinsrw xmm0, word ptr [r14 + rbx + 2], 6 - or r9, 448 - pinsrw xmm0, word ptr [r14 + r9 + 2], 7 - movd xmm2, eax - movzx eax, word ptr [r14 + rdi + 22] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pcmpeqw xmm0, xmm11 - pinsrw xmm1, word ptr [r14 + rcx + 4], 1 - pinsrw xmm1, word ptr [r14 + r15 + 4], 2 - pinsrw xmm1, word ptr [r14 + rsi + 4], 3 - pinsrw xmm1, word ptr [r14 + r12 + 4], 4 - pinsrw xmm1, word ptr [r14 + rdx + 4], 5 - pinsrw xmm1, word ptr [r14 + rbx + 4], 6 - pinsrw xmm1, word ptr [r14 + r9 + 4], 7 - packsswb xmm0, xmm0 - pcmpeqw xmm1, xmm11 - movdqa xmm14, xmmword ptr [rip + .LCPI5_8] # xmm14 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm3, xmm14 - pblendvb xmm3, xmm9, xmm0 - packsswb xmm1, xmm1 - movdqa xmm15, xmmword ptr [rip + .LCPI5_9] # xmm15 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm15 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm9, xmm0 - movd xmm1, r8d - movzx r11d, word ptr [r14 + rdi + 24] - pinsrw xmm5, word ptr [r14 + r9], 7 - pcmpeqw xmm5, xmm11 - pcmpeqd xmm0, xmm0 - pxor xmm5, xmm0 - packsswb xmm5, xmm5 - pinsrw xmm7, word ptr [r14 + rcx + 6], 1 - pinsrw xmm7, word ptr [r14 + r15 + 6], 2 - pinsrw xmm7, word ptr [r14 + rsi + 6], 3 - pinsrw xmm7, word ptr [r14 + r12 + 6], 4 - pinsrw xmm7, word ptr [r14 + rdx + 6], 5 - pinsrw xmm7, word ptr [r14 + rbx + 6], 6 - pinsrw xmm7, word ptr [r14 + r9 + 6], 7 - pcmpeqw xmm7, xmm11 - packsswb xmm7, xmm7 - pinsrw xmm8, word ptr [r14 + rcx + 8], 1 - pinsrw xmm8, word ptr [r14 + r15 + 8], 2 - pinsrw xmm8, word ptr [r14 + rsi + 8], 3 - pinsrw xmm8, word ptr [r14 + r12 + 8], 4 - pinsrw xmm8, word ptr [r14 + rdx + 8], 5 - pinsrw xmm8, word ptr [r14 + rbx + 8], 6 - pinsrw xmm8, word ptr [r14 + r9 + 8], 7 - psubb xmm3, xmm5 - movdqa xmm12, xmmword ptr [rip + .LCPI5_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm7 - pblendvb xmm12, xmm9, xmm0 - movd xmm7, r10d - movzx r8d, word ptr [r14 + rdi + 26] - pcmpeqw xmm8, xmm11 - packsswb xmm8, xmm8 - por xmm12, xmm6 - movdqa xmm13, xmmword ptr [rip + .LCPI5_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm8 - pblendvb xmm13, xmm9, xmm0 - movd xmm6, r13d - movzx r13d, word ptr [r14 + rdi + 28] - pinsrw xmm4, word ptr [r14 + rcx + 10], 1 - pinsrw xmm4, word ptr [r14 + r15 + 10], 2 - pinsrw xmm4, word ptr [r14 + rsi + 10], 3 - pinsrw xmm4, word ptr [r14 + r12 + 10], 4 - pinsrw xmm4, word ptr [r14 + rdx + 10], 5 - pinsrw xmm4, word ptr [r14 + rbx + 10], 6 - pinsrw xmm4, word ptr [r14 + r9 + 10], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - pinsrw xmm2, word ptr [r14 + rcx + 12], 1 - pinsrw xmm2, word ptr [r14 + r15 + 12], 2 - pinsrw xmm2, word ptr [r14 + rsi + 12], 3 - pinsrw xmm2, word ptr [r14 + r12 + 12], 4 - pinsrw xmm2, word ptr [r14 + rdx + 12], 5 - pinsrw xmm2, word ptr [r14 + rbx + 12], 6 - por xmm12, xmm3 - movdqa xmm5, xmmword ptr [rip + .LCPI5_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm5, xmm9, xmm0 - movd xmm4, dword ptr [rsp + 32] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx r10d, word ptr [r14 + rdi + 30] - pinsrw xmm2, word ptr [r14 + r9 + 12], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm13 - movdqa xmm13, xmmword ptr [rip + .LCPI5_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm13, xmm9, xmm0 - movd xmm3, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [r14 + rdi + 32] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm1, word ptr [r14 + rcx + 14], 1 - pinsrw xmm1, word ptr [r14 + r15 + 14], 2 - pinsrw xmm1, word ptr [r14 + rsi + 14], 3 - pinsrw xmm1, word ptr [r14 + r12 + 14], 4 - pinsrw xmm1, word ptr [r14 + rdx + 14], 5 - pinsrw xmm1, word ptr [r14 + rbx + 14], 6 - por xmm13, xmm5 - movd xmm2, r11d - movzx eax, word ptr [r14 + rdi + 34] - mov dword ptr [rsp + 32], eax # 4-byte Spill - pinsrw xmm1, word ptr [r14 + r9 + 14], 7 - pcmpeqw xmm1, xmm11 - pinsrw xmm6, word ptr [r14 + rcx + 18], 1 - pinsrw xmm6, word ptr [r14 + r15 + 18], 2 - pinsrw xmm6, word ptr [r14 + rsi + 18], 3 - pinsrw xmm6, word ptr [r14 + r12 + 18], 4 - pinsrw xmm6, word ptr [r14 + rdx + 18], 5 - pinsrw xmm6, word ptr [r14 + rbx + 18], 6 - packsswb xmm1, xmm1 - pinsrw xmm6, word ptr [r14 + r9 + 18], 7 - pcmpeqw xmm6, xmm11 - packsswb xmm6, xmm6 - por xmm13, xmm12 - movdqa xmm10, xmmword ptr [rip + .LCPI5_14] # xmm10 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm12, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm12, xmm9, xmm0 - movdqa xmm8, xmm14 - movdqa xmm0, xmm6 - pblendvb xmm8, xmm9, xmm0 - movd xmm1, r8d - movzx r11d, word ptr [r14 + rdi + 36] - pinsrw xmm7, word ptr [r14 + rcx + 16], 1 - pinsrw xmm7, word ptr [r14 + r15 + 16], 2 - pinsrw xmm7, word ptr [r14 + rsi + 16], 3 - pinsrw xmm7, word ptr [r14 + r12 + 16], 4 - pinsrw xmm7, word ptr [r14 + rdx + 16], 5 - pinsrw xmm7, word ptr [r14 + rbx + 16], 6 - pinsrw xmm4, word ptr [r14 + rcx + 20], 1 - pinsrw xmm4, word ptr [r14 + r15 + 20], 2 - pinsrw xmm4, word ptr [r14 + rsi + 20], 3 - pinsrw xmm4, word ptr [r14 + r12 + 20], 4 - pinsrw xmm4, word ptr [r14 + rdx + 20], 5 - pinsrw xmm4, word ptr [r14 + rbx + 20], 6 - pinsrw xmm4, word ptr [r14 + r9 + 20], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm12, xmm13 - movdqa xmm0, xmm4 - pblendvb xmm15, xmm9, xmm0 - movd xmm4, r13d - movzx r13d, word ptr [r14 + rdi + 38] - pinsrw xmm7, word ptr [r14 + r9 + 16], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI5_22] - packsswb xmm7, xmm7 - pinsrw xmm3, word ptr [r14 + rcx + 22], 1 - pinsrw xmm3, word ptr [r14 + r15 + 22], 2 - pinsrw xmm3, word ptr [r14 + rsi + 22], 3 - pinsrw xmm3, word ptr [r14 + r12 + 22], 4 - pinsrw xmm3, word ptr [r14 + rdx + 22], 5 - pinsrw xmm3, word ptr [r14 + rbx + 22], 6 - pinsrw xmm3, word ptr [r14 + r9 + 22], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [r14 + rcx + 24], 1 - pinsrw xmm2, word ptr [r14 + r15 + 24], 2 - pinsrw xmm2, word ptr [r14 + rsi + 24], 3 - pinsrw xmm2, word ptr [r14 + r12 + 24], 4 - pinsrw xmm2, word ptr [r14 + rdx + 24], 5 - pinsrw xmm2, word ptr [r14 + rbx + 24], 6 - pinsrw xmm2, word ptr [r14 + r9 + 24], 7 - psubb xmm8, xmm7 - movdqa xmm14, xmmword ptr [rip + .LCPI5_10] # xmm14 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm3 - pblendvb xmm14, xmm9, xmm0 - movd xmm3, r10d - movzx r8d, word ptr [r14 + rdi + 40] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm14, xmm15 - movdqa xmm13, xmmword ptr [rip + .LCPI5_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm13, xmm9, xmm0 - movd xmm7, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r10d, word ptr [r14 + rdi + 42] - pinsrw xmm1, word ptr [r14 + rcx + 26], 1 - pinsrw xmm1, word ptr [r14 + r15 + 26], 2 - pinsrw xmm1, word ptr [r14 + rsi + 26], 3 - pinsrw xmm1, word ptr [r14 + r12 + 26], 4 - pinsrw xmm1, word ptr [r14 + rdx + 26], 5 - pinsrw xmm1, word ptr [r14 + rbx + 26], 6 - pinsrw xmm1, word ptr [r14 + r9 + 26], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm4, word ptr [r14 + rcx + 28], 1 - pinsrw xmm4, word ptr [r14 + r15 + 28], 2 - pinsrw xmm4, word ptr [r14 + rsi + 28], 3 - pinsrw xmm4, word ptr [r14 + r12 + 28], 4 - pinsrw xmm4, word ptr [r14 + rdx + 28], 5 - pinsrw xmm4, word ptr [r14 + rbx + 28], 6 - por xmm14, xmm8 - movdqa xmm15, xmmword ptr [rip + .LCPI5_12] # xmm15 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm5, xmm15 - movdqa xmm0, xmm1 - pblendvb xmm5, xmm9, xmm0 - movd xmm2, dword ptr [rsp + 32] # 4-byte Folded Reload - # xmm2 = mem[0],zero,zero,zero - movzx eax, word ptr [r14 + rdi + 44] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm4, word ptr [r14 + r9 + 28], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm5, xmm13 - movdqa xmm6, xmmword ptr [rip + .LCPI5_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm9, xmm0 - movd xmm4, r11d - movzx r11d, word ptr [r14 + rdi + 46] - pinsrw xmm3, word ptr [r14 + rcx + 30], 1 - pinsrw xmm3, word ptr [r14 + r15 + 30], 2 - pinsrw xmm3, word ptr [r14 + rsi + 30], 3 - pinsrw xmm3, word ptr [r14 + r12 + 30], 4 - pinsrw xmm3, word ptr [r14 + rdx + 30], 5 - pinsrw xmm3, word ptr [r14 + rbx + 30], 6 - por xmm6, xmm5 - movd xmm1, r13d - movzx eax, word ptr [r14 + rdi + 48] - mov dword ptr [rsp + 32], eax # 4-byte Spill - pinsrw xmm3, word ptr [r14 + r9 + 30], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm2, word ptr [r14 + rcx + 34], 1 - pinsrw xmm2, word ptr [r14 + r15 + 34], 2 - pinsrw xmm2, word ptr [r14 + rsi + 34], 3 - pinsrw xmm2, word ptr [r14 + r12 + 34], 4 - pinsrw xmm2, word ptr [r14 + rdx + 34], 5 - pinsrw xmm2, word ptr [r14 + rbx + 34], 6 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [r14 + r9 + 34], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm6, xmm14 - movdqa xmm13, xmm10 - movdqa xmm0, xmm3 - pblendvb xmm13, xmm9, xmm0 - movdqa xmm8, xmmword ptr [rip + .LCPI5_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm8, xmm9, xmm0 - movd xmm2, r8d - movzx r13d, word ptr [r14 + rdi + 50] - pinsrw xmm7, word ptr [r14 + rcx + 32], 1 - pinsrw xmm7, word ptr [r14 + r15 + 32], 2 - pinsrw xmm7, word ptr [r14 + rsi + 32], 3 - pinsrw xmm7, word ptr [r14 + r12 + 32], 4 - pinsrw xmm7, word ptr [r14 + rdx + 32], 5 - pinsrw xmm7, word ptr [r14 + rbx + 32], 6 - pinsrw xmm4, word ptr [r14 + rcx + 36], 1 - pinsrw xmm4, word ptr [r14 + r15 + 36], 2 - pinsrw xmm4, word ptr [r14 + rsi + 36], 3 - pinsrw xmm4, word ptr [r14 + r12 + 36], 4 - pinsrw xmm4, word ptr [r14 + rdx + 36], 5 - pinsrw xmm4, word ptr [r14 + rbx + 36], 6 - pinsrw xmm4, word ptr [r14 + r9 + 36], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm13, xmm6 - movdqa xmm6, xmmword ptr [rip + .LCPI5_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm9, xmm0 - movd xmm3, r10d - movzx r10d, word ptr [r14 + rdi + 52] - pinsrw xmm7, word ptr [r14 + r9 + 32], 7 - pcmpeqw xmm7, xmm11 - pcmpeqd xmm14, xmm14 - pxor xmm7, xmm14 - packsswb xmm7, xmm7 - pinsrw xmm1, word ptr [r14 + rcx + 38], 1 - pinsrw xmm1, word ptr [r14 + r15 + 38], 2 - pinsrw xmm1, word ptr [r14 + rsi + 38], 3 - pinsrw xmm1, word ptr [r14 + r12 + 38], 4 - pinsrw xmm1, word ptr [r14 + rdx + 38], 5 - pinsrw xmm1, word ptr [r14 + rbx + 38], 6 - pinsrw xmm1, word ptr [r14 + r9 + 38], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm2, word ptr [r14 + rcx + 40], 1 - pinsrw xmm2, word ptr [r14 + r15 + 40], 2 - pinsrw xmm2, word ptr [r14 + rsi + 40], 3 - pinsrw xmm2, word ptr [r14 + r12 + 40], 4 - pinsrw xmm2, word ptr [r14 + rdx + 40], 5 - pinsrw xmm2, word ptr [r14 + rbx + 40], 6 - pinsrw xmm2, word ptr [r14 + r9 + 40], 7 - psubb xmm8, xmm7 - movdqa xmm5, xmmword ptr [rip + .LCPI5_10] # xmm5 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm5, xmm9, xmm0 - movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx r8d, word ptr [r14 + rdi + 54] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm6 - movdqa xmm6, xmmword ptr [rip + .LCPI5_11] # xmm6 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm6, xmm9, xmm0 - movd xmm4, r11d - movzx eax, word ptr [r14 + rdi + 56] - pinsrw xmm3, word ptr [r14 + rcx + 42], 1 - pinsrw xmm3, word ptr [r14 + r15 + 42], 2 - pinsrw xmm3, word ptr [r14 + rsi + 42], 3 - pinsrw xmm3, word ptr [r14 + r12 + 42], 4 - pinsrw xmm3, word ptr [r14 + rdx + 42], 5 - pinsrw xmm3, word ptr [r14 + rbx + 42], 6 - pinsrw xmm3, word ptr [r14 + r9 + 42], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [r14 + rcx + 44], 1 - pinsrw xmm1, word ptr [r14 + r15 + 44], 2 - pinsrw xmm1, word ptr [r14 + rsi + 44], 3 - pinsrw xmm1, word ptr [r14 + r12 + 44], 4 - pinsrw xmm1, word ptr [r14 + rdx + 44], 5 - pinsrw xmm1, word ptr [r14 + rbx + 44], 6 - por xmm5, xmm8 - movdqa xmm2, xmm15 + pinsrb xmm6, byte ptr [r13 + rsi + 31], 1 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 18], 2 + pinsrb xmm5, byte ptr [r13 + rax + 19], 2 + pinsrb xmm3, byte ptr [r13 + rax + 20], 2 + pinsrb xmm2, byte ptr [r13 + rax + 21], 2 + pinsrb xmm1, byte ptr [r13 + rax + 22], 2 + pinsrb xmm8, byte ptr [r13 + rax + 23], 2 + pinsrb xmm12, byte ptr [r13 + rax + 24], 2 + pinsrb xmm13, byte ptr [r13 + rax + 25], 2 + pinsrb xmm0, byte ptr [r13 + rax + 26], 2 + pinsrb xmm11, byte ptr [r13 + rax + 27], 2 + pinsrb xmm15, byte ptr [r13 + rax + 28], 2 + pinsrb xmm9, byte ptr [r13 + rax + 29], 2 + pinsrb xmm10, byte ptr [r13 + rax + 30], 2 + pinsrb xmm6, byte ptr [r13 + rax + 31], 2 + mov r11, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r11 + 18], 3 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r14 + 18], 4 + mov r12, r9 + pinsrb xmm7, byte ptr [r13 + r9 + 18], 5 + pinsrb xmm7, byte ptr [r13 + rdi + 18], 6 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r9 + 18], 7 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 18], 8 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rsi + 18], 9 + pinsrb xmm7, byte ptr [r13 + r8 + 18], 10 + pinsrb xmm7, byte ptr [r13 + rcx + 18], 11 + pinsrb xmm7, byte ptr [r13 + rdx + 18], 12 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r15 + 18], 13 + pinsrb xmm7, byte ptr [r13 + rbx + 18], 14 + pinsrb xmm7, byte ptr [r13 + r10 + 18], 15 + pinsrb xmm5, byte ptr [r13 + r11 + 19], 3 + pinsrb xmm5, byte ptr [r13 + r14 + 19], 4 + pinsrb xmm5, byte ptr [r13 + r12 + 19], 5 + pinsrb xmm5, byte ptr [r13 + rdi + 19], 6 + pinsrb xmm5, byte ptr [r13 + r9 + 19], 7 + pinsrb xmm5, byte ptr [r13 + rax + 19], 8 + pinsrb xmm5, byte ptr [r13 + rsi + 19], 9 + pinsrb xmm5, byte ptr [r13 + r8 + 19], 10 + pinsrb xmm5, byte ptr [r13 + rcx + 19], 11 + pinsrb xmm5, byte ptr [r13 + rdx + 19], 12 + pinsrb xmm5, byte ptr [r13 + r15 + 19], 13 + pinsrb xmm5, byte ptr [r13 + rbx + 19], 14 + pinsrb xmm5, byte ptr [r13 + r10 + 19], 15 + pinsrb xmm3, byte ptr [r13 + r11 + 20], 3 + pinsrb xmm3, byte ptr [r13 + r14 + 20], 4 + pinsrb xmm3, byte ptr [r13 + r12 + 20], 5 + pinsrb xmm3, byte ptr [r13 + rdi + 20], 6 + pinsrb xmm3, byte ptr [r13 + r9 + 20], 7 + pinsrb xmm3, byte ptr [r13 + rax + 20], 8 + pinsrb xmm3, byte ptr [r13 + rsi + 20], 9 + mov r15, rsi + pinsrb xmm3, byte ptr [r13 + r8 + 20], 10 + pinsrb xmm3, byte ptr [r13 + rcx + 20], 11 + pinsrb xmm3, byte ptr [r13 + rdx + 20], 12 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + r12 + 20], 13 + pinsrb xmm3, byte ptr [r13 + rbx + 20], 14 + pcmpeqb xmm7, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI5_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm7, xmm14 + pcmpeqb xmm5, xmmword ptr [rsp + 176] # 16-byte Folded Reload + movdqa xmm14, xmmword ptr [rip + .LCPI5_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm5, xmm14 + por xmm5, xmm7 + pinsrb xmm3, byte ptr [r13 + r10 + 20], 15 + movdqa xmm14, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm3, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI5_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm3, xmm7 + por xmm3, xmm5 + pcmpeqd xmm5, xmm5 + psubb xmm4, xmm5 + por xmm3, xmm4 + pinsrb xmm2, byte ptr [r13 + r11 + 21], 3 + pinsrb xmm2, byte ptr [r13 + r14 + 21], 4 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rsi + 21], 5 + pinsrb xmm2, byte ptr [r13 + rdi + 21], 6 + pinsrb xmm2, byte ptr [r13 + r9 + 21], 7 + pinsrb xmm2, byte ptr [r13 + rax + 21], 8 + pinsrb xmm2, byte ptr [r13 + r15 + 21], 9 + pinsrb xmm2, byte ptr [r13 + r8 + 21], 10 + pinsrb xmm2, byte ptr [r13 + rcx + 21], 11 + pinsrb xmm2, byte ptr [r13 + rdx + 21], 12 + pinsrb xmm2, byte ptr [r13 + r12 + 21], 13 + pinsrb xmm2, byte ptr [r13 + rbx + 21], 14 + pinsrb xmm2, byte ptr [r13 + r10 + 21], 15 + pinsrb xmm1, byte ptr [r13 + r11 + 22], 3 + pinsrb xmm1, byte ptr [r13 + r14 + 22], 4 + pinsrb xmm1, byte ptr [r13 + rsi + 22], 5 + pinsrb xmm1, byte ptr [r13 + rdi + 22], 6 + pinsrb xmm1, byte ptr [r13 + r9 + 22], 7 + pinsrb xmm1, byte ptr [r13 + rax + 22], 8 + pinsrb xmm1, byte ptr [r13 + r15 + 22], 9 + pinsrb xmm1, byte ptr [r13 + r8 + 22], 10 + pinsrb xmm1, byte ptr [r13 + rcx + 22], 11 + pinsrb xmm1, byte ptr [r13 + rdx + 22], 12 + pinsrb xmm1, byte ptr [r13 + r12 + 22], 13 + pinsrb xmm1, byte ptr [r13 + rbx + 22], 14 + pinsrb xmm1, byte ptr [r13 + r10 + 22], 15 + pinsrb xmm8, byte ptr [r13 + r11 + 23], 3 + pinsrb xmm8, byte ptr [r13 + r14 + 23], 4 + pinsrb xmm8, byte ptr [r13 + rsi + 23], 5 + pinsrb xmm8, byte ptr [r13 + rdi + 23], 6 + pinsrb xmm8, byte ptr [r13 + r9 + 23], 7 + pinsrb xmm8, byte ptr [r13 + rax + 23], 8 + pinsrb xmm8, byte ptr [r13 + r15 + 23], 9 + pinsrb xmm8, byte ptr [r13 + r8 + 23], 10 + pinsrb xmm8, byte ptr [r13 + rcx + 23], 11 + pinsrb xmm8, byte ptr [r13 + rdx + 23], 12 + pinsrb xmm8, byte ptr [r13 + r12 + 23], 13 + pinsrb xmm8, byte ptr [r13 + rbx + 23], 14 + pcmpeqb xmm2, xmm14 + movdqa xmm5, xmmword ptr [rip + .LCPI5_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm5 + pcmpeqb xmm1, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI5_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm1, xmm7 + por xmm1, xmm2 + pinsrb xmm8, byte ptr [r13 + r10 + 23], 15 + pcmpeqb xmm8, xmm14 + movdqa xmm4, xmmword ptr [rip + .LCPI5_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm8, xmm4 + por xmm8, xmm1 + pinsrb xmm12, byte ptr [r13 + r11 + 24], 3 + pinsrb xmm12, byte ptr [r13 + r14 + 24], 4 + pinsrb xmm12, byte ptr [r13 + rsi + 24], 5 + pinsrb xmm12, byte ptr [r13 + rdi + 24], 6 + pinsrb xmm12, byte ptr [r13 + r9 + 24], 7 + pinsrb xmm12, byte ptr [r13 + rax + 24], 8 + pinsrb xmm12, byte ptr [r13 + r15 + 24], 9 + pinsrb xmm12, byte ptr [r13 + r8 + 24], 10 + pinsrb xmm12, byte ptr [r13 + rcx + 24], 11 + pinsrb xmm12, byte ptr [r13 + rdx + 24], 12 + pinsrb xmm12, byte ptr [r13 + r12 + 24], 13 + pinsrb xmm12, byte ptr [r13 + rbx + 24], 14 + pinsrb xmm12, byte ptr [r13 + r10 + 24], 15 + por xmm8, xmm3 + pcmpeqb xmm12, xmm14 + pinsrb xmm13, byte ptr [r13 + r11 + 25], 3 + pinsrb xmm13, byte ptr [r13 + r14 + 25], 4 + pinsrb xmm13, byte ptr [r13 + rsi + 25], 5 + pinsrb xmm13, byte ptr [r13 + rdi + 25], 6 + pinsrb xmm13, byte ptr [r13 + r9 + 25], 7 + pinsrb xmm13, byte ptr [r13 + rax + 25], 8 + pinsrb xmm13, byte ptr [r13 + r15 + 25], 9 + pinsrb xmm13, byte ptr [r13 + r8 + 25], 10 + pinsrb xmm13, byte ptr [r13 + rcx + 25], 11 + pinsrb xmm13, byte ptr [r13 + rdx + 25], 12 + pinsrb xmm13, byte ptr [r13 + r12 + 25], 13 + pinsrb xmm13, byte ptr [r13 + rbx + 25], 14 + pinsrb xmm13, byte ptr [r13 + r10 + 25], 15 + pinsrb xmm0, byte ptr [r13 + r11 + 26], 3 + pinsrb xmm0, byte ptr [r13 + r14 + 26], 4 + pinsrb xmm0, byte ptr [r13 + rsi + 26], 5 + pinsrb xmm0, byte ptr [r13 + rdi + 26], 6 + pinsrb xmm0, byte ptr [r13 + r9 + 26], 7 + pinsrb xmm0, byte ptr [r13 + rax + 26], 8 + pinsrb xmm0, byte ptr [r13 + r15 + 26], 9 + pinsrb xmm0, byte ptr [r13 + r8 + 26], 10 + pinsrb xmm0, byte ptr [r13 + rcx + 26], 11 + pinsrb xmm0, byte ptr [r13 + rdx + 26], 12 + pinsrb xmm0, byte ptr [r13 + r12 + 26], 13 + pinsrb xmm0, byte ptr [r13 + rbx + 26], 14 + pinsrb xmm0, byte ptr [r13 + r10 + 26], 15 + pinsrb xmm11, byte ptr [r13 + r11 + 27], 3 + pinsrb xmm11, byte ptr [r13 + r14 + 27], 4 + pinsrb xmm11, byte ptr [r13 + rsi + 27], 5 + pinsrb xmm11, byte ptr [r13 + rdi + 27], 6 + pinsrb xmm11, byte ptr [r13 + r9 + 27], 7 + pinsrb xmm11, byte ptr [r13 + rax + 27], 8 + pinsrb xmm11, byte ptr [r13 + r15 + 27], 9 + pinsrb xmm11, byte ptr [r13 + r8 + 27], 10 + pinsrb xmm11, byte ptr [r13 + rcx + 27], 11 + pinsrb xmm11, byte ptr [r13 + rdx + 27], 12 + pinsrb xmm11, byte ptr [r13 + r12 + 27], 13 + pinsrb xmm11, byte ptr [r13 + rbx + 27], 14 + pcmpeqb xmm13, xmm14 + pandn xmm13, xmmword ptr [rip + .LCPI5_16] + paddb xmm13, xmm12 + pinsrb xmm11, byte ptr [r13 + r10 + 27], 15 + pcmpeqb xmm0, xmm14 + pandn xmm0, xmmword ptr [rip + .LCPI5_17] + pcmpeqb xmm11, xmm14 + pandn xmm11, xmmword ptr [rip + .LCPI5_18] + por xmm11, xmm0 + pinsrb xmm15, byte ptr [r13 + r11 + 28], 3 + pinsrb xmm9, byte ptr [r13 + r11 + 29], 3 + pinsrb xmm10, byte ptr [r13 + r11 + 30], 3 + pinsrb xmm6, byte ptr [r13 + r11 + 31], 3 + pinsrb xmm15, byte ptr [r13 + r14 + 28], 4 + pinsrb xmm9, byte ptr [r13 + r14 + 29], 4 + pinsrb xmm10, byte ptr [r13 + r14 + 30], 4 + pinsrb xmm6, byte ptr [r13 + r14 + 31], 4 + pinsrb xmm15, byte ptr [r13 + rsi + 28], 5 + pinsrb xmm9, byte ptr [r13 + rsi + 29], 5 + pinsrb xmm10, byte ptr [r13 + rsi + 30], 5 + pinsrb xmm6, byte ptr [r13 + rsi + 31], 5 + mov rsi, rdi + pinsrb xmm15, byte ptr [r13 + rdi + 28], 6 + pinsrb xmm9, byte ptr [r13 + rdi + 29], 6 + pinsrb xmm10, byte ptr [r13 + rdi + 30], 6 + pinsrb xmm6, byte ptr [r13 + rdi + 31], 6 + mov r11, qword ptr [rsp + 136] # 8-byte Reload + mov rsi, r9 + pinsrb xmm15, byte ptr [r13 + r9 + 28], 7 + pinsrb xmm9, byte ptr [r13 + r9 + 29], 7 + pinsrb xmm10, byte ptr [r13 + r9 + 30], 7 + pinsrb xmm6, byte ptr [r13 + r9 + 31], 7 + pinsrb xmm15, byte ptr [r13 + rax + 28], 8 + pinsrb xmm9, byte ptr [r13 + rax + 29], 8 + pinsrb xmm10, byte ptr [r13 + rax + 30], 8 + pinsrb xmm6, byte ptr [r13 + rax + 31], 8 + mov rax, r15 + pinsrb xmm15, byte ptr [r13 + r15 + 28], 9 + pinsrb xmm9, byte ptr [r13 + r15 + 29], 9 + pinsrb xmm10, byte ptr [r13 + r15 + 30], 9 + pinsrb xmm6, byte ptr [r13 + r15 + 31], 9 + mov rax, r8 + pinsrb xmm15, byte ptr [r13 + r8 + 28], 10 + pinsrb xmm9, byte ptr [r13 + r8 + 29], 10 + pinsrb xmm10, byte ptr [r13 + r8 + 30], 10 + pinsrb xmm6, byte ptr [r13 + r8 + 31], 10 + mov rax, rcx + pinsrb xmm15, byte ptr [r13 + rcx + 28], 11 + pinsrb xmm9, byte ptr [r13 + rcx + 29], 11 + pinsrb xmm10, byte ptr [r13 + rcx + 30], 11 + pinsrb xmm6, byte ptr [r13 + rcx + 31], 11 + mov rax, rdx + pinsrb xmm15, byte ptr [r13 + rdx + 28], 12 + pinsrb xmm9, byte ptr [r13 + rdx + 29], 12 + pinsrb xmm10, byte ptr [r13 + rdx + 30], 12 + pinsrb xmm6, byte ptr [r13 + rdx + 31], 12 + pinsrb xmm15, byte ptr [r13 + r12 + 28], 13 + pinsrb xmm9, byte ptr [r13 + r12 + 29], 13 + pinsrb xmm10, byte ptr [r13 + r12 + 30], 13 + pinsrb xmm6, byte ptr [r13 + r12 + 31], 13 + pinsrb xmm15, byte ptr [r13 + rbx + 28], 14 + pinsrb xmm9, byte ptr [r13 + rbx + 29], 14 + pinsrb xmm10, byte ptr [r13 + rbx + 30], 14 + pinsrb xmm6, byte ptr [r13 + rbx + 31], 14 + mov rax, r10 + pinsrb xmm15, byte ptr [r13 + r10 + 28], 15 + pinsrb xmm9, byte ptr [r13 + r10 + 29], 15 + pinsrb xmm10, byte ptr [r13 + r10 + 30], 15 + pcmpeqb xmm15, xmm14 + pandn xmm15, xmmword ptr [rip + .LCPI5_19] + por xmm15, xmm11 + pinsrb xmm6, byte ptr [r13 + r10 + 31], 15 + psubb xmm13, xmmword ptr [rip + .LCPI5_22] + por xmm15, xmm13 + pcmpeqb xmm9, xmm14 + pandn xmm9, xmm5 + pcmpeqb xmm10, xmm14 + pandn xmm10, xmm7 + por xmm10, xmm9 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmm4 + por xmm6, xmm10 + por xmm6, xmm15 + movdqa xmm0, xmm8 + punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] + movdqa xmm3, xmmword ptr [rsp + 208] # 16-byte Reload + movdqa xmm1, xmm3 + movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload + punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] + movdqa xmm2, xmm1 + punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] + punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] + punpckhbw xmm3, xmm4 # xmm3 = xmm3[8],xmm4[8],xmm3[9],xmm4[9],xmm3[10],xmm4[10],xmm3[11],xmm4[11],xmm3[12],xmm4[12],xmm3[13],xmm4[13],xmm3[14],xmm4[14],xmm3[15],xmm4[15] movdqa xmm0, xmm3 - pblendvb xmm2, xmm9, xmm0 - movd xmm7, dword ptr [rsp + 32] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r11d, word ptr [r14 + rdi + 58] - pinsrw xmm1, word ptr [r14 + r9 + 44], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm2, xmm6 - movdqa xmm15, xmmword ptr [rip + .LCPI5_13] # xmm15 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm15 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm9, xmm0 - movd xmm1, r13d - movzx r13d, word ptr [r14 + rdi + 60] - por xmm6, xmm2 - movd xmm2, r10d - pinsrw xmm4, word ptr [r14 + rcx + 46], 1 - pinsrw xmm4, word ptr [r14 + r15 + 46], 2 - pinsrw xmm4, word ptr [r14 + rsi + 46], 3 - pinsrw xmm4, word ptr [r14 + r12 + 46], 4 - pinsrw xmm4, word ptr [r14 + rdx + 46], 5 - pinsrw xmm4, word ptr [r14 + rbx + 46], 6 - pinsrw xmm4, word ptr [r14 + r9 + 46], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm6, xmm5 - movdqa xmm8, xmm10 - movdqa xmm0, xmm4 - pblendvb xmm8, xmm9, xmm0 - movd xmm3, r8d - pinsrw xmm1, word ptr [r14 + rcx + 50], 1 - pinsrw xmm1, word ptr [r14 + r15 + 50], 2 - pinsrw xmm1, word ptr [r14 + rsi + 50], 3 - pinsrw xmm1, word ptr [r14 + r12 + 50], 4 - pinsrw xmm1, word ptr [r14 + rdx + 50], 5 - pinsrw xmm1, word ptr [r14 + rbx + 50], 6 - pinsrw xmm1, word ptr [r14 + r9 + 50], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm8, xmm6 - movdqa xmm4, xmmword ptr [rip + .LCPI5_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm9, xmm0 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + movdqu xmmword ptr [r11 + 4*rcx + 48], xmm3 + movdqu xmmword ptr [r11 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r11 + 4*rcx + 16], xmm1 + movdqu xmmword ptr [r11 + 4*rcx], xmm2 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + jne .LBB5_215 +# %bb.216: + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14b, byte ptr [rsp + 12] # 1-byte Reload + mov r13, qword ptr [rsp + 256] # 8-byte Reload + mov rdi, qword ptr [rsp + 248] # 8-byte Reload + jne .LBB5_154 + jmp .LBB5_158 +.LBB5_217: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, rdi + mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 168], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 256], rax # 8-byte Spill + movzx eax, r14b movd xmm1, eax - pinsrw xmm7, word ptr [r14 + rcx + 48], 1 - pinsrw xmm7, word ptr [r14 + r15 + 48], 2 - pinsrw xmm7, word ptr [r14 + rsi + 48], 3 - pinsrw xmm7, word ptr [r14 + r12 + 48], 4 - pinsrw xmm7, word ptr [r14 + rdx + 48], 5 - pinsrw xmm7, word ptr [r14 + rbx + 48], 6 - pinsrw xmm7, word ptr [r14 + r9 + 48], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmm14 - pinsrw xmm2, word ptr [r14 + rcx + 52], 1 - pinsrw xmm2, word ptr [r14 + r15 + 52], 2 - pinsrw xmm2, word ptr [r14 + rsi + 52], 3 - pinsrw xmm2, word ptr [r14 + r12 + 52], 4 - pinsrw xmm2, word ptr [r14 + rdx + 52], 5 - pinsrw xmm2, word ptr [r14 + rbx + 52], 6 - packsswb xmm7, xmm7 - pinsrw xmm2, word ptr [r14 + r9 + 52], 7 - pcmpeqw xmm2, xmm11 - pinsrw xmm3, word ptr [r14 + rcx + 54], 1 - pinsrw xmm3, word ptr [r14 + r15 + 54], 2 - pinsrw xmm3, word ptr [r14 + rsi + 54], 3 - pinsrw xmm3, word ptr [r14 + r12 + 54], 4 - pinsrw xmm3, word ptr [r14 + rdx + 54], 5 - pinsrw xmm3, word ptr [r14 + rbx + 54], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [r14 + r9 + 54], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm1, word ptr [r14 + rcx + 56], 1 - pinsrw xmm1, word ptr [r14 + r15 + 56], 2 - pinsrw xmm1, word ptr [r14 + rsi + 56], 3 - pinsrw xmm1, word ptr [r14 + r12 + 56], 4 - pinsrw xmm1, word ptr [r14 + rdx + 56], 5 - pinsrw xmm1, word ptr [r14 + rbx + 56], 6 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [r14 + r9 + 56], 7 - psubb xmm4, xmm7 - movdqa xmm5, xmmword ptr [rip + .LCPI5_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm5, xmm9, xmm0 - movdqa xmm6, xmmword ptr [rip + .LCPI5_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm3 - pblendvb xmm6, xmm9, xmm0 - movd xmm2, r11d - pcmpeqw xmm1, xmm11 - pinsrw xmm2, word ptr [r14 + rcx + 58], 1 - pinsrw xmm2, word ptr [r14 + r15 + 58], 2 - pinsrw xmm2, word ptr [r14 + rsi + 58], 3 - pinsrw xmm2, word ptr [r14 + r12 + 58], 4 - pinsrw xmm2, word ptr [r14 + rdx + 58], 5 - pinsrw xmm2, word ptr [r14 + rbx + 58], 6 - pinsrw xmm2, word ptr [r14 + r9 + 58], 7 - packsswb xmm1, xmm1 - pcmpeqw xmm2, xmm11 - por xmm6, xmm5 - movd xmm3, r13d - mov r8, qword ptr [rsp + 8] # 8-byte Reload - pinsrw xmm3, word ptr [r14 + rcx + 60], 1 - pinsrw xmm3, word ptr [r14 + r15 + 60], 2 - pinsrw xmm3, word ptr [r14 + rsi + 60], 3 - pinsrw xmm3, word ptr [r14 + r12 + 60], 4 - pinsrw xmm3, word ptr [r14 + rdx + 60], 5 - pinsrw xmm3, word ptr [r14 + rbx + 60], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [r14 + r9 + 60], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - por xmm6, xmm4 - movdqa xmm4, xmmword ptr [rip + .LCPI5_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm9, xmm0 - movdqa xmm1, xmmword ptr [rip + .LCPI5_12] # xmm1 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm1, xmm9, xmm0 - movdqa xmm2, xmm15 - movdqa xmm0, xmm3 - pblendvb xmm2, xmm9, xmm0 - por xmm1, xmm4 - movzx eax, word ptr [r14 + rdi + 62] - por xmm2, xmm1 - movd xmm0, eax - pinsrw xmm0, word ptr [r14 + rcx + 62], 1 - pinsrw xmm0, word ptr [r14 + r15 + 62], 2 - pinsrw xmm0, word ptr [r14 + rsi + 62], 3 - pinsrw xmm0, word ptr [r14 + r12 + 62], 4 - pinsrw xmm0, word ptr [r14 + rdx + 62], 5 - pinsrw xmm0, word ptr [r14 + rbx + 62], 6 - pinsrw xmm0, word ptr [r14 + r9 + 62], 7 - pcmpeqw xmm0, xmm11 - packsswb xmm0, xmm0 - por xmm2, xmm6 - pblendvb xmm10, xmm9, xmm0 - por xmm10, xmm2 - movdqa xmm0, xmm12 - punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] - movdqa xmm2, xmm8 - punpcklqdq xmm2, xmm10 # xmm2 = xmm2[0],xmm10[0] - movdqa xmm3, xmmword ptr [rip + .LCPI5_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> - pshufb xmm2, xmm3 - pshufb xmm0, xmm3 - punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] - punpcklbw xmm8, xmm10 # xmm8 = xmm8[0],xmm10[0],xmm8[1],xmm10[1],xmm8[2],xmm10[2],xmm8[3],xmm10[3],xmm8[4],xmm10[4],xmm8[5],xmm10[5],xmm8[6],xmm10[6],xmm8[7],xmm10[7] - punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] - punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - movdqu xmmword ptr [r8 + 4*rcx], xmm12 - mov qword ptr [rsp + 8], r8 # 8-byte Spill - movdqu xmmword ptr [r8 + 4*rcx + 16], xmm0 - add rcx, 8 - mov rdi, rcx - cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload - jne .LBB5_111 -# %bb.112: - mov r10, qword ptr [rsp + 208] # 8-byte Reload - cmp r10, qword ptr [rsp + 40] # 8-byte Folded Reload - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r11d, dword ptr [rsp + 16] # 4-byte Reload - mov r12, qword ptr [rsp + 56] # 8-byte Reload - mov r14, qword ptr [rsp + 48] # 8-byte Reload - jne .LBB5_113 - jmp .LBB5_116 -.LBB5_133: - and r10, -8 - mov rax, r10 - shl rax, 6 - add rax, r14 - mov qword ptr [rsp + 48], rax # 8-byte Spill - mov qword ptr [rsp + 40], r10 # 8-byte Spill - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea rax, [rax + 4*r10] - mov qword ptr [rsp + 56], rax # 8-byte Spill - movd xmm0, r11d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] - xor edi, edi - pxor xmm9, xmm9 + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 136], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB5_134: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 64], rdi # 8-byte Spill - shl rdi, 6 - mov r15, rdi - mov rsi, rdi - mov r12, rdi - mov rdx, rdi - mov rbx, rdi - mov r9, rdi - movzx eax, word ptr [r14 + rdi] - movd xmm5, eax - movzx eax, word ptr [r14 + rdi + 2] - movd xmm0, eax - movzx eax, word ptr [r14 + rdi + 4] - movd xmm1, eax - movzx eax, word ptr [r14 + rdi + 6] - movd xmm7, eax - movzx eax, word ptr [r14 + rdi + 8] - movd xmm8, eax - movzx eax, word ptr [r14 + rdi + 10] - movd xmm4, eax - movzx eax, word ptr [r14 + rdi + 12] - movzx r8d, word ptr [r14 + rdi + 14] - movzx r10d, word ptr [r14 + rdi + 16] - movzx r13d, word ptr [r14 + rdi + 18] - movzx ecx, word ptr [r14 + rdi + 20] - mov dword ptr [rsp + 32], ecx # 4-byte Spill - mov rcx, rdi - or rcx, 64 +.LBB5_218: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 160], rax # 8-byte Spill + shl rax, 5 + mov r8, rax + mov r14, rax + mov r15, rax + mov r10, rax + mov r11, rax + mov r12, rax + mov r9, rax + mov rbx, rax + mov qword ptr [rsp + 96], rax # 8-byte Spill + mov rsi, rax + mov qword ptr [rsp + 88], rax # 8-byte Spill + movzx ecx, byte ptr [rdi + rax] + movd xmm4, ecx + movzx ecx, byte ptr [rdi + rax + 1] + movd xmm3, ecx + movzx ecx, byte ptr [rdi + rax + 2] + movd xmm5, ecx + movzx ecx, byte ptr [rdi + rax + 3] + movd xmm7, ecx + movzx ecx, byte ptr [rdi + rax + 4] + movd xmm9, ecx + movzx ecx, byte ptr [rdi + rax + 5] + movd xmm2, ecx + movzx ecx, byte ptr [rdi + rax + 6] + movd xmm8, ecx + movzx ecx, byte ptr [rdi + rax + 7] + movd xmm14, ecx + movzx ecx, byte ptr [rdi + rax + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill + movzx ecx, byte ptr [rdi + rax + 9] + movd xmm11, ecx + movzx ecx, byte ptr [rdi + rax + 10] + movd xmm12, ecx + movzx ecx, byte ptr [rdi + rax + 11] + movd xmm13, ecx + movzx ecx, byte ptr [rdi + rax + 12] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill + movzx ecx, byte ptr [rdi + rax + 13] + movd xmm6, ecx + movzx ecx, byte ptr [rdi + rax + 14] + movd xmm15, ecx + movzx ecx, byte ptr [rdi + rax + 15] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill + mov qword ptr [rsp + 72], rax # 8-byte Spill + mov r13, rax + or r13, 32 + or r8, 64 + or r14, 96 or r15, 128 - or rsi, 192 - or r12, 256 - or rdx, 320 - or rbx, 384 - pinsrw xmm5, word ptr [r14 + rcx], 1 - pinsrw xmm5, word ptr [r14 + r15], 2 - pinsrw xmm5, word ptr [r14 + rsi], 3 - pinsrw xmm5, word ptr [r14 + r12], 4 - pinsrw xmm5, word ptr [r14 + rdx], 5 - pinsrw xmm5, word ptr [r14 + rbx], 6 - pinsrw xmm0, word ptr [r14 + rcx + 2], 1 - pinsrw xmm0, word ptr [r14 + r15 + 2], 2 - pinsrw xmm0, word ptr [r14 + rsi + 2], 3 - pinsrw xmm0, word ptr [r14 + r12 + 2], 4 - pinsrw xmm0, word ptr [r14 + rdx + 2], 5 - pinsrw xmm0, word ptr [r14 + rbx + 2], 6 - or r9, 448 - pinsrw xmm0, word ptr [r14 + r9 + 2], 7 - movd xmm2, eax - movzx eax, word ptr [r14 + rdi + 22] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pcmpeqw xmm0, xmm11 - pinsrw xmm1, word ptr [r14 + rcx + 4], 1 - pinsrw xmm1, word ptr [r14 + r15 + 4], 2 - pinsrw xmm1, word ptr [r14 + rsi + 4], 3 - pinsrw xmm1, word ptr [r14 + r12 + 4], 4 - pinsrw xmm1, word ptr [r14 + rdx + 4], 5 - pinsrw xmm1, word ptr [r14 + rbx + 4], 6 - pinsrw xmm1, word ptr [r14 + r9 + 4], 7 - packsswb xmm0, xmm0 - pcmpeqw xmm1, xmm11 - movdqa xmm14, xmmword ptr [rip + .LCPI5_8] # xmm14 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm3, xmm14 - pblendvb xmm3, xmm9, xmm0 - packsswb xmm1, xmm1 - movdqa xmm15, xmmword ptr [rip + .LCPI5_9] # xmm15 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm15 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm9, xmm0 - movd xmm1, r8d - movzx r11d, word ptr [r14 + rdi + 24] - pinsrw xmm5, word ptr [r14 + r9], 7 - pcmpeqw xmm5, xmm11 + or r10, 160 + or r11, 192 + or r12, 224 + or r9, 256 + mov rdx, rax + or rdx, 288 + mov qword ptr [rsp + 56], rdx # 8-byte Spill + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + or rbx, 320 + or rsi, 352 + mov qword ptr [rsp + 64], rsi # 8-byte Spill + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + or rsi, 384 + mov qword ptr [rsp + 88], rsi # 8-byte Spill + mov rcx, rax + or rcx, 416 + mov qword ptr [rsp + 24], rcx # 8-byte Spill + mov rcx, rax + or rcx, 448 + mov qword ptr [rsp + 16], rcx # 8-byte Spill + or rax, 480 + mov qword ptr [rsp + 40], rax # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r13], 1 + mov qword ptr [rsp + 104], r8 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r8], 2 + mov qword ptr [rsp + 32], r14 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r14], 3 + pinsrb xmm4, byte ptr [rdi + r15], 4 + mov qword ptr [rsp + 112], r10 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r10], 5 + pinsrb xmm4, byte ptr [rdi + r11], 6 + pinsrb xmm4, byte ptr [rdi + r12], 7 + mov qword ptr [rsp + 80], r9 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r9], 8 + pinsrb xmm4, byte ptr [rdi + rdx], 9 + mov r8, rbx + pinsrb xmm4, byte ptr [rdi + rbx], 10 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rbx], 11 + pinsrb xmm4, byte ptr [rdi + rsi], 12 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax], 13 + pinsrb xmm4, byte ptr [rdi + rcx], 14 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax], 15 + pinsrb xmm3, byte ptr [rdi + r13 + 1], 1 + mov qword ptr [rsp + 48], r13 # 8-byte Spill + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rax + 1], 2 + pinsrb xmm3, byte ptr [rdi + r14 + 1], 3 + pinsrb xmm3, byte ptr [rdi + r15 + 1], 4 + mov r14, r15 + pinsrb xmm3, byte ptr [rdi + r10 + 1], 5 + pinsrb xmm3, byte ptr [rdi + r11 + 1], 6 + mov r10, r11 + pinsrb xmm3, byte ptr [rdi + r12 + 1], 7 + mov r15, r12 + pinsrb xmm3, byte ptr [rdi + r9 + 1], 8 + pinsrb xmm3, byte ptr [rdi + rdx + 1], 9 + pinsrb xmm3, byte ptr [rdi + r8 + 1], 10 + pinsrb xmm3, byte ptr [rdi + rbx + 1], 11 + mov rdx, rbx + pinsrb xmm3, byte ptr [rdi + rsi + 1], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 1], 13 + pinsrb xmm3, byte ptr [rdi + rcx + 1], 14 + movdqa xmm1, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm4, xmm1 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rax + 1], 15 + pcmpeqb xmm3, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI5_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pandn xmm3, xmm0 + paddb xmm3, xmm4 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + movzx esi, byte ptr [rdi + rcx + 16] + movd xmm10, esi + pinsrb xmm5, byte ptr [rdi + r13 + 2], 1 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r12 + 2], 2 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r11 + 2], 3 + mov qword ptr [rsp + 128], r14 # 8-byte Spill + pinsrb xmm5, byte ptr [rdi + r14 + 2], 4 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rbx + 2], 5 + mov r9, r10 + pinsrb xmm5, byte ptr [rdi + r10 + 2], 6 + mov r10, r15 + pinsrb xmm5, byte ptr [rdi + r15 + 2], 7 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r15 + 2], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rax + 2], 9 + pinsrb xmm5, byte ptr [rdi + r8 + 2], 10 + pinsrb xmm5, byte ptr [rdi + rdx + 2], 11 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rcx + 2], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rsi + 2], 13 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rdx + 2], 14 + mov r13, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r13 + 2], 15 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 3], 1 + pinsrb xmm7, byte ptr [rdi + r12 + 3], 2 + pinsrb xmm7, byte ptr [rdi + r11 + 3], 3 + pinsrb xmm7, byte ptr [rdi + r14 + 3], 4 + pinsrb xmm7, byte ptr [rdi + rbx + 3], 5 + pinsrb xmm7, byte ptr [rdi + r9 + 3], 6 + pinsrb xmm7, byte ptr [rdi + r10 + 3], 7 + pinsrb xmm7, byte ptr [rdi + r15 + 3], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 3], 9 + pinsrb xmm7, byte ptr [rdi + r8 + 3], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 3], 11 + pinsrb xmm7, byte ptr [rdi + rcx + 3], 12 + pinsrb xmm7, byte ptr [rdi + rsi + 3], 13 + pinsrb xmm7, byte ptr [rdi + rdx + 3], 14 + pinsrb xmm7, byte ptr [rdi + r13 + 3], 15 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 4], 1 + pinsrb xmm9, byte ptr [rdi + r12 + 4], 2 + pinsrb xmm9, byte ptr [rdi + r11 + 4], 3 + pinsrb xmm9, byte ptr [rdi + r14 + 4], 4 + pinsrb xmm9, byte ptr [rdi + rbx + 4], 5 + pinsrb xmm9, byte ptr [rdi + r9 + 4], 6 + mov qword ptr [rsp + 120], r9 # 8-byte Spill + pinsrb xmm9, byte ptr [rdi + r10 + 4], 7 + pinsrb xmm9, byte ptr [rdi + r15 + 4], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 4], 9 + pinsrb xmm9, byte ptr [rdi + r8 + 4], 10 + mov r15, r8 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r8 + 4], 11 + pinsrb xmm9, byte ptr [rdi + rcx + 4], 12 + pinsrb xmm9, byte ptr [rdi + rsi + 4], 13 + pinsrb xmm9, byte ptr [rdi + rdx + 4], 14 + pinsrb xmm9, byte ptr [rdi + r13 + 4], 15 + pcmpeqb xmm5, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI5_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm5, xmm0 + pcmpeqb xmm7, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI5_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm7, xmm0 + por xmm7, xmm5 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 17] + movd xmm4, esi + pcmpeqb xmm9, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI5_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm9, xmm0 + por xmm9, xmm7 + movzx esi, byte ptr [rdi + rdx + 18] + movd xmm7, esi pcmpeqd xmm0, xmm0 - pxor xmm5, xmm0 - packsswb xmm5, xmm5 - pinsrw xmm7, word ptr [r14 + rcx + 6], 1 - pinsrw xmm7, word ptr [r14 + r15 + 6], 2 - pinsrw xmm7, word ptr [r14 + rsi + 6], 3 - pinsrw xmm7, word ptr [r14 + r12 + 6], 4 - pinsrw xmm7, word ptr [r14 + rdx + 6], 5 - pinsrw xmm7, word ptr [r14 + rbx + 6], 6 - pinsrw xmm7, word ptr [r14 + r9 + 6], 7 - pcmpeqw xmm7, xmm11 - packsswb xmm7, xmm7 - pinsrw xmm8, word ptr [r14 + rcx + 8], 1 - pinsrw xmm8, word ptr [r14 + r15 + 8], 2 - pinsrw xmm8, word ptr [r14 + rsi + 8], 3 - pinsrw xmm8, word ptr [r14 + r12 + 8], 4 - pinsrw xmm8, word ptr [r14 + rdx + 8], 5 - pinsrw xmm8, word ptr [r14 + rbx + 8], 6 - pinsrw xmm8, word ptr [r14 + r9 + 8], 7 - psubb xmm3, xmm5 - movdqa xmm12, xmmword ptr [rip + .LCPI5_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm7 - pblendvb xmm12, xmm9, xmm0 - movd xmm7, r10d - movzx r8d, word ptr [r14 + rdi + 26] - pcmpeqw xmm8, xmm11 - packsswb xmm8, xmm8 - por xmm12, xmm6 - movdqa xmm13, xmmword ptr [rip + .LCPI5_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm8 - pblendvb xmm13, xmm9, xmm0 - movd xmm6, r13d - movzx r13d, word ptr [r14 + rdi + 28] - pinsrw xmm4, word ptr [r14 + rcx + 10], 1 - pinsrw xmm4, word ptr [r14 + r15 + 10], 2 - pinsrw xmm4, word ptr [r14 + rsi + 10], 3 - pinsrw xmm4, word ptr [r14 + r12 + 10], 4 - pinsrw xmm4, word ptr [r14 + rdx + 10], 5 - pinsrw xmm4, word ptr [r14 + rbx + 10], 6 - pinsrw xmm4, word ptr [r14 + r9 + 10], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - pinsrw xmm2, word ptr [r14 + rcx + 12], 1 - pinsrw xmm2, word ptr [r14 + r15 + 12], 2 - pinsrw xmm2, word ptr [r14 + rsi + 12], 3 - pinsrw xmm2, word ptr [r14 + r12 + 12], 4 - pinsrw xmm2, word ptr [r14 + rdx + 12], 5 - pinsrw xmm2, word ptr [r14 + rbx + 12], 6 - por xmm12, xmm3 - movdqa xmm5, xmmword ptr [rip + .LCPI5_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm5, xmm9, xmm0 - movd xmm4, dword ptr [rsp + 32] # 4-byte Folded Reload - # xmm4 = mem[0],zero,zero,zero - movzx r10d, word ptr [r14 + rdi + 30] - pinsrw xmm2, word ptr [r14 + r9 + 12], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm13 - movdqa xmm13, xmmword ptr [rip + .LCPI5_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm13, xmm9, xmm0 - movd xmm3, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [r14 + rdi + 32] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm1, word ptr [r14 + rcx + 14], 1 - pinsrw xmm1, word ptr [r14 + r15 + 14], 2 - pinsrw xmm1, word ptr [r14 + rsi + 14], 3 - pinsrw xmm1, word ptr [r14 + r12 + 14], 4 - pinsrw xmm1, word ptr [r14 + rdx + 14], 5 - pinsrw xmm1, word ptr [r14 + rbx + 14], 6 - por xmm13, xmm5 - movd xmm2, r11d - movzx eax, word ptr [r14 + rdi + 34] - mov dword ptr [rsp + 32], eax # 4-byte Spill - pinsrw xmm1, word ptr [r14 + r9 + 14], 7 - pcmpeqw xmm1, xmm11 - pinsrw xmm6, word ptr [r14 + rcx + 18], 1 - pinsrw xmm6, word ptr [r14 + r15 + 18], 2 - pinsrw xmm6, word ptr [r14 + rsi + 18], 3 - pinsrw xmm6, word ptr [r14 + r12 + 18], 4 - pinsrw xmm6, word ptr [r14 + rdx + 18], 5 - pinsrw xmm6, word ptr [r14 + rbx + 18], 6 - packsswb xmm1, xmm1 - pinsrw xmm6, word ptr [r14 + r9 + 18], 7 - pcmpeqw xmm6, xmm11 - packsswb xmm6, xmm6 - por xmm13, xmm12 - movdqa xmm10, xmmword ptr [rip + .LCPI5_14] # xmm10 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm12, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm12, xmm9, xmm0 - movdqa xmm8, xmm14 - movdqa xmm0, xmm6 - pblendvb xmm8, xmm9, xmm0 - movd xmm1, r8d - movzx r11d, word ptr [r14 + rdi + 36] - pinsrw xmm7, word ptr [r14 + rcx + 16], 1 - pinsrw xmm7, word ptr [r14 + r15 + 16], 2 - pinsrw xmm7, word ptr [r14 + rsi + 16], 3 - pinsrw xmm7, word ptr [r14 + r12 + 16], 4 - pinsrw xmm7, word ptr [r14 + rdx + 16], 5 - pinsrw xmm7, word ptr [r14 + rbx + 16], 6 - pinsrw xmm4, word ptr [r14 + rcx + 20], 1 - pinsrw xmm4, word ptr [r14 + r15 + 20], 2 - pinsrw xmm4, word ptr [r14 + rsi + 20], 3 - pinsrw xmm4, word ptr [r14 + r12 + 20], 4 - pinsrw xmm4, word ptr [r14 + rdx + 20], 5 - pinsrw xmm4, word ptr [r14 + rbx + 20], 6 - pinsrw xmm4, word ptr [r14 + r9 + 20], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm12, xmm13 - movdqa xmm0, xmm4 - pblendvb xmm15, xmm9, xmm0 - movd xmm4, r13d - movzx r13d, word ptr [r14 + rdi + 38] - pinsrw xmm7, word ptr [r14 + r9 + 16], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI5_22] - packsswb xmm7, xmm7 - pinsrw xmm3, word ptr [r14 + rcx + 22], 1 - pinsrw xmm3, word ptr [r14 + r15 + 22], 2 - pinsrw xmm3, word ptr [r14 + rsi + 22], 3 - pinsrw xmm3, word ptr [r14 + r12 + 22], 4 - pinsrw xmm3, word ptr [r14 + rdx + 22], 5 - pinsrw xmm3, word ptr [r14 + rbx + 22], 6 - pinsrw xmm3, word ptr [r14 + r9 + 22], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [r14 + rcx + 24], 1 - pinsrw xmm2, word ptr [r14 + r15 + 24], 2 - pinsrw xmm2, word ptr [r14 + rsi + 24], 3 - pinsrw xmm2, word ptr [r14 + r12 + 24], 4 - pinsrw xmm2, word ptr [r14 + rdx + 24], 5 - pinsrw xmm2, word ptr [r14 + rbx + 24], 6 - pinsrw xmm2, word ptr [r14 + r9 + 24], 7 - psubb xmm8, xmm7 - movdqa xmm14, xmmword ptr [rip + .LCPI5_10] # xmm14 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm3 - pblendvb xmm14, xmm9, xmm0 - movd xmm3, r10d - movzx r8d, word ptr [r14 + rdi + 40] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm14, xmm15 - movdqa xmm13, xmmword ptr [rip + .LCPI5_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm13, xmm9, xmm0 - movd xmm7, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r10d, word ptr [r14 + rdi + 42] - pinsrw xmm1, word ptr [r14 + rcx + 26], 1 - pinsrw xmm1, word ptr [r14 + r15 + 26], 2 - pinsrw xmm1, word ptr [r14 + rsi + 26], 3 - pinsrw xmm1, word ptr [r14 + r12 + 26], 4 - pinsrw xmm1, word ptr [r14 + rdx + 26], 5 - pinsrw xmm1, word ptr [r14 + rbx + 26], 6 - pinsrw xmm1, word ptr [r14 + r9 + 26], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm4, word ptr [r14 + rcx + 28], 1 - pinsrw xmm4, word ptr [r14 + r15 + 28], 2 - pinsrw xmm4, word ptr [r14 + rsi + 28], 3 - pinsrw xmm4, word ptr [r14 + r12 + 28], 4 - pinsrw xmm4, word ptr [r14 + rdx + 28], 5 - pinsrw xmm4, word ptr [r14 + rbx + 28], 6 - por xmm14, xmm8 - movdqa xmm15, xmmword ptr [rip + .LCPI5_12] # xmm15 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm5, xmm15 - movdqa xmm0, xmm1 - pblendvb xmm5, xmm9, xmm0 - movd xmm2, dword ptr [rsp + 32] # 4-byte Folded Reload - # xmm2 = mem[0],zero,zero,zero - movzx eax, word ptr [r14 + rdi + 44] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm4, word ptr [r14 + r9 + 28], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm5, xmm13 - movdqa xmm6, xmmword ptr [rip + .LCPI5_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm9, xmm0 - movd xmm4, r11d - movzx r11d, word ptr [r14 + rdi + 46] - pinsrw xmm3, word ptr [r14 + rcx + 30], 1 - pinsrw xmm3, word ptr [r14 + r15 + 30], 2 - pinsrw xmm3, word ptr [r14 + rsi + 30], 3 - pinsrw xmm3, word ptr [r14 + r12 + 30], 4 - pinsrw xmm3, word ptr [r14 + rdx + 30], 5 - pinsrw xmm3, word ptr [r14 + rbx + 30], 6 - por xmm6, xmm5 - movd xmm1, r13d - movzx eax, word ptr [r14 + rdi + 48] - mov dword ptr [rsp + 32], eax # 4-byte Spill - pinsrw xmm3, word ptr [r14 + r9 + 30], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm2, word ptr [r14 + rcx + 34], 1 - pinsrw xmm2, word ptr [r14 + r15 + 34], 2 - pinsrw xmm2, word ptr [r14 + rsi + 34], 3 - pinsrw xmm2, word ptr [r14 + r12 + 34], 4 - pinsrw xmm2, word ptr [r14 + rdx + 34], 5 - pinsrw xmm2, word ptr [r14 + rbx + 34], 6 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [r14 + r9 + 34], 7 - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm6, xmm14 - movdqa xmm13, xmm10 - movdqa xmm0, xmm3 - pblendvb xmm13, xmm9, xmm0 - movdqa xmm8, xmmword ptr [rip + .LCPI5_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm8, xmm9, xmm0 - movd xmm2, r8d - movzx r13d, word ptr [r14 + rdi + 50] - pinsrw xmm7, word ptr [r14 + rcx + 32], 1 - pinsrw xmm7, word ptr [r14 + r15 + 32], 2 - pinsrw xmm7, word ptr [r14 + rsi + 32], 3 - pinsrw xmm7, word ptr [r14 + r12 + 32], 4 - pinsrw xmm7, word ptr [r14 + rdx + 32], 5 - pinsrw xmm7, word ptr [r14 + rbx + 32], 6 - pinsrw xmm4, word ptr [r14 + rcx + 36], 1 - pinsrw xmm4, word ptr [r14 + r15 + 36], 2 - pinsrw xmm4, word ptr [r14 + rsi + 36], 3 - pinsrw xmm4, word ptr [r14 + r12 + 36], 4 - pinsrw xmm4, word ptr [r14 + rdx + 36], 5 - pinsrw xmm4, word ptr [r14 + rbx + 36], 6 - pinsrw xmm4, word ptr [r14 + r9 + 36], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm13, xmm6 - movdqa xmm6, xmmword ptr [rip + .LCPI5_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm9, xmm0 - movd xmm3, r10d - movzx r10d, word ptr [r14 + rdi + 52] - pinsrw xmm7, word ptr [r14 + r9 + 32], 7 - pcmpeqw xmm7, xmm11 - pcmpeqd xmm14, xmm14 - pxor xmm7, xmm14 - packsswb xmm7, xmm7 - pinsrw xmm1, word ptr [r14 + rcx + 38], 1 - pinsrw xmm1, word ptr [r14 + r15 + 38], 2 - pinsrw xmm1, word ptr [r14 + rsi + 38], 3 - pinsrw xmm1, word ptr [r14 + r12 + 38], 4 - pinsrw xmm1, word ptr [r14 + rdx + 38], 5 - pinsrw xmm1, word ptr [r14 + rbx + 38], 6 - pinsrw xmm1, word ptr [r14 + r9 + 38], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm2, word ptr [r14 + rcx + 40], 1 - pinsrw xmm2, word ptr [r14 + r15 + 40], 2 - pinsrw xmm2, word ptr [r14 + rsi + 40], 3 - pinsrw xmm2, word ptr [r14 + r12 + 40], 4 - pinsrw xmm2, word ptr [r14 + rdx + 40], 5 - pinsrw xmm2, word ptr [r14 + rbx + 40], 6 - pinsrw xmm2, word ptr [r14 + r9 + 40], 7 - psubb xmm8, xmm7 - movdqa xmm5, xmmword ptr [rip + .LCPI5_10] # xmm5 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm5, xmm9, xmm0 - movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - movzx r8d, word ptr [r14 + rdi + 54] - pcmpeqw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm6 - movdqa xmm6, xmmword ptr [rip + .LCPI5_11] # xmm6 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm6, xmm9, xmm0 - movd xmm4, r11d - movzx eax, word ptr [r14 + rdi + 56] - pinsrw xmm3, word ptr [r14 + rcx + 42], 1 - pinsrw xmm3, word ptr [r14 + r15 + 42], 2 - pinsrw xmm3, word ptr [r14 + rsi + 42], 3 - pinsrw xmm3, word ptr [r14 + r12 + 42], 4 - pinsrw xmm3, word ptr [r14 + rdx + 42], 5 - pinsrw xmm3, word ptr [r14 + rbx + 42], 6 - pinsrw xmm3, word ptr [r14 + r9 + 42], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [r14 + rcx + 44], 1 - pinsrw xmm1, word ptr [r14 + r15 + 44], 2 - pinsrw xmm1, word ptr [r14 + rsi + 44], 3 - pinsrw xmm1, word ptr [r14 + r12 + 44], 4 - pinsrw xmm1, word ptr [r14 + rdx + 44], 5 - pinsrw xmm1, word ptr [r14 + rbx + 44], 6 - por xmm5, xmm8 - movdqa xmm2, xmm15 - movdqa xmm0, xmm3 - pblendvb xmm2, xmm9, xmm0 - movd xmm7, dword ptr [rsp + 32] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r11d, word ptr [r14 + rdi + 58] - pinsrw xmm1, word ptr [r14 + r9 + 44], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm2, xmm6 - movdqa xmm15, xmmword ptr [rip + .LCPI5_13] # xmm15 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm15 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm9, xmm0 - movd xmm1, r13d - movzx r13d, word ptr [r14 + rdi + 60] - por xmm6, xmm2 - movd xmm2, r10d - pinsrw xmm4, word ptr [r14 + rcx + 46], 1 - pinsrw xmm4, word ptr [r14 + r15 + 46], 2 - pinsrw xmm4, word ptr [r14 + rsi + 46], 3 - pinsrw xmm4, word ptr [r14 + r12 + 46], 4 - pinsrw xmm4, word ptr [r14 + rdx + 46], 5 - pinsrw xmm4, word ptr [r14 + rbx + 46], 6 - pinsrw xmm4, word ptr [r14 + r9 + 46], 7 - pcmpeqw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm6, xmm5 - movdqa xmm8, xmm10 - movdqa xmm0, xmm4 - pblendvb xmm8, xmm9, xmm0 - movd xmm3, r8d - pinsrw xmm1, word ptr [r14 + rcx + 50], 1 - pinsrw xmm1, word ptr [r14 + r15 + 50], 2 - pinsrw xmm1, word ptr [r14 + rsi + 50], 3 - pinsrw xmm1, word ptr [r14 + r12 + 50], 4 - pinsrw xmm1, word ptr [r14 + rdx + 50], 5 - pinsrw xmm1, word ptr [r14 + rbx + 50], 6 - pinsrw xmm1, word ptr [r14 + r9 + 50], 7 - pcmpeqw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm8, xmm6 - movdqa xmm4, xmmword ptr [rip + .LCPI5_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm9, xmm0 - movd xmm1, eax - pinsrw xmm7, word ptr [r14 + rcx + 48], 1 - pinsrw xmm7, word ptr [r14 + r15 + 48], 2 - pinsrw xmm7, word ptr [r14 + rsi + 48], 3 - pinsrw xmm7, word ptr [r14 + r12 + 48], 4 - pinsrw xmm7, word ptr [r14 + rdx + 48], 5 - pinsrw xmm7, word ptr [r14 + rbx + 48], 6 - pinsrw xmm7, word ptr [r14 + r9 + 48], 7 - pcmpeqw xmm7, xmm11 - pxor xmm7, xmm14 - pinsrw xmm2, word ptr [r14 + rcx + 52], 1 - pinsrw xmm2, word ptr [r14 + r15 + 52], 2 - pinsrw xmm2, word ptr [r14 + rsi + 52], 3 - pinsrw xmm2, word ptr [r14 + r12 + 52], 4 - pinsrw xmm2, word ptr [r14 + rdx + 52], 5 - pinsrw xmm2, word ptr [r14 + rbx + 52], 6 - packsswb xmm7, xmm7 - pinsrw xmm2, word ptr [r14 + r9 + 52], 7 - pcmpeqw xmm2, xmm11 - pinsrw xmm3, word ptr [r14 + rcx + 54], 1 - pinsrw xmm3, word ptr [r14 + r15 + 54], 2 - pinsrw xmm3, word ptr [r14 + rsi + 54], 3 - pinsrw xmm3, word ptr [r14 + r12 + 54], 4 - pinsrw xmm3, word ptr [r14 + rdx + 54], 5 - pinsrw xmm3, word ptr [r14 + rbx + 54], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [r14 + r9 + 54], 7 - pcmpeqw xmm3, xmm11 - pinsrw xmm1, word ptr [r14 + rcx + 56], 1 - pinsrw xmm1, word ptr [r14 + r15 + 56], 2 - pinsrw xmm1, word ptr [r14 + rsi + 56], 3 - pinsrw xmm1, word ptr [r14 + r12 + 56], 4 - pinsrw xmm1, word ptr [r14 + rdx + 56], 5 - pinsrw xmm1, word ptr [r14 + rbx + 56], 6 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [r14 + r9 + 56], 7 - psubb xmm4, xmm7 - movdqa xmm5, xmmword ptr [rip + .LCPI5_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm5, xmm9, xmm0 - movdqa xmm6, xmmword ptr [rip + .LCPI5_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm3 - pblendvb xmm6, xmm9, xmm0 - movd xmm2, r11d - pcmpeqw xmm1, xmm11 - pinsrw xmm2, word ptr [r14 + rcx + 58], 1 - pinsrw xmm2, word ptr [r14 + r15 + 58], 2 - pinsrw xmm2, word ptr [r14 + rsi + 58], 3 - pinsrw xmm2, word ptr [r14 + r12 + 58], 4 - pinsrw xmm2, word ptr [r14 + rdx + 58], 5 - pinsrw xmm2, word ptr [r14 + rbx + 58], 6 - pinsrw xmm2, word ptr [r14 + r9 + 58], 7 - packsswb xmm1, xmm1 - pcmpeqw xmm2, xmm11 - por xmm6, xmm5 - movd xmm3, r13d - mov r8, qword ptr [rsp + 8] # 8-byte Reload - pinsrw xmm3, word ptr [r14 + rcx + 60], 1 - pinsrw xmm3, word ptr [r14 + r15 + 60], 2 - pinsrw xmm3, word ptr [r14 + rsi + 60], 3 - pinsrw xmm3, word ptr [r14 + r12 + 60], 4 - pinsrw xmm3, word ptr [r14 + rdx + 60], 5 - pinsrw xmm3, word ptr [r14 + rbx + 60], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [r14 + r9 + 60], 7 - pcmpeqw xmm3, xmm11 - packsswb xmm3, xmm3 - por xmm6, xmm4 - movdqa xmm4, xmmword ptr [rip + .LCPI5_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm9, xmm0 - movdqa xmm1, xmmword ptr [rip + .LCPI5_12] # xmm1 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm1, xmm9, xmm0 - movdqa xmm2, xmm15 - movdqa xmm0, xmm3 - pblendvb xmm2, xmm9, xmm0 - por xmm1, xmm4 - movzx eax, word ptr [r14 + rdi + 62] - por xmm2, xmm1 - movd xmm0, eax - pinsrw xmm0, word ptr [r14 + rcx + 62], 1 - pinsrw xmm0, word ptr [r14 + r15 + 62], 2 - pinsrw xmm0, word ptr [r14 + rsi + 62], 3 - pinsrw xmm0, word ptr [r14 + r12 + 62], 4 - pinsrw xmm0, word ptr [r14 + rdx + 62], 5 - pinsrw xmm0, word ptr [r14 + rbx + 62], 6 - pinsrw xmm0, word ptr [r14 + r9 + 62], 7 - pcmpeqw xmm0, xmm11 - packsswb xmm0, xmm0 - por xmm2, xmm6 - pblendvb xmm10, xmm9, xmm0 - por xmm10, xmm2 - movdqa xmm0, xmm12 - punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] - movdqa xmm2, xmm8 - punpcklqdq xmm2, xmm10 # xmm2 = xmm2[0],xmm10[0] - movdqa xmm3, xmmword ptr [rip + .LCPI5_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> - pshufb xmm2, xmm3 - pshufb xmm0, xmm3 - punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] - punpcklbw xmm8, xmm10 # xmm8 = xmm8[0],xmm10[0],xmm8[1],xmm10[1],xmm8[2],xmm10[2],xmm8[3],xmm10[3],xmm8[4],xmm10[4],xmm8[5],xmm10[5],xmm8[6],xmm10[6],xmm8[7],xmm10[7] - punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] - punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] + psubb xmm3, xmm0 + por xmm9, xmm3 + movzx esi, byte ptr [rdi + rdx + 19] + movd xmm5, esi + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rdx + 5], 1 + pinsrb xmm2, byte ptr [rdi + r12 + 5], 2 + pinsrb xmm2, byte ptr [rdi + r11 + 5], 3 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r14 + 5], 4 + pinsrb xmm2, byte ptr [rdi + rbx + 5], 5 + pinsrb xmm2, byte ptr [rdi + r9 + 5], 6 + mov r11, r10 + pinsrb xmm2, byte ptr [rdi + r10 + 5], 7 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r10 + 5], 8 + pinsrb xmm2, byte ptr [rdi + rax + 5], 9 + mov rsi, r15 + mov qword ptr [rsp + 96], r15 # 8-byte Spill + pinsrb xmm2, byte ptr [rdi + r15 + 5], 10 + mov r13, r8 + pinsrb xmm2, byte ptr [rdi + r8 + 5], 11 + pinsrb xmm2, byte ptr [rdi + rcx + 5], 12 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r8 + 5], 13 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rbx + 5], 14 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r9 + 5], 15 + pinsrb xmm8, byte ptr [rdi + rdx + 6], 1 + pinsrb xmm8, byte ptr [rdi + r12 + 6], 2 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r15 + 6], 3 + pinsrb xmm8, byte ptr [rdi + r14 + 6], 4 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rbx + 6], 5 + mov rbx, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rbx + 6], 6 + pinsrb xmm8, byte ptr [rdi + r11 + 6], 7 + pinsrb xmm8, byte ptr [rdi + r10 + 6], 8 + pinsrb xmm8, byte ptr [rdi + rax + 6], 9 + pinsrb xmm8, byte ptr [rdi + rsi + 6], 10 + pinsrb xmm8, byte ptr [rdi + r13 + 6], 11 + pinsrb xmm8, byte ptr [rdi + rcx + 6], 12 + pinsrb xmm8, byte ptr [rdi + r8 + 6], 13 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rbx + 6], 14 + pinsrb xmm8, byte ptr [rdi + r9 + 6], 15 + pinsrb xmm14, byte ptr [rdi + rdx + 7], 1 + pinsrb xmm14, byte ptr [rdi + r12 + 7], 2 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r15 + 7], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rdx + 7], 4 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rdx + 7], 5 + mov r9, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r9 + 7], 6 + pinsrb xmm14, byte ptr [rdi + r11 + 7], 7 + pinsrb xmm14, byte ptr [rdi + r10 + 7], 8 + pinsrb xmm14, byte ptr [rdi + rax + 7], 9 + mov r14, rax + pinsrb xmm14, byte ptr [rdi + rsi + 7], 10 + pinsrb xmm14, byte ptr [rdi + r13 + 7], 11 + pinsrb xmm14, byte ptr [rdi + rcx + 7], 12 + pinsrb xmm14, byte ptr [rdi + r8 + 7], 13 + pinsrb xmm14, byte ptr [rdi + rbx + 7], 14 + movdqa xmm1, xmm14 + movdqa xmm14, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm2, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI5_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm0 + pcmpeqb xmm8, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI5_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm8, xmm0 + por xmm8, xmm2 + mov rbx, qword ptr [rsp + 72] # 8-byte Reload + movzx esi, byte ptr [rdi + rbx + 20] + movd xmm3, esi + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rax + 7], 15 + pcmpeqb xmm1, xmm14 + movdqa xmm0, xmmword ptr [rip + .LCPI5_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm1, xmm0 + por xmm1, xmm8 + movzx esi, byte ptr [rdi + rbx + 21] + movd xmm2, esi + movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload + mov r10, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r10 + 8], 1 + pinsrb xmm0, byte ptr [rdi + r12 + 8], 2 + pinsrb xmm0, byte ptr [rdi + r15 + 8], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 8], 4 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rcx + 8], 5 + pinsrb xmm0, byte ptr [rdi + r9 + 8], 6 + pinsrb xmm0, byte ptr [rdi + r11 + 8], 7 + mov r15, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r15 + 8], 8 + pinsrb xmm0, byte ptr [rdi + r14 + 8], 9 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r13 + 8], 10 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rsi + 8], 11 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rsi + 8], 12 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r8 + 8], 13 + mov r14, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r14 + 8], 14 + pinsrb xmm0, byte ptr [rdi + rax + 8], 15 + por xmm1, xmm9 + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill + movzx esi, byte ptr [rdi + rbx + 22] + movd xmm1, esi + pcmpeqb xmm0, xmm14 + pinsrb xmm11, byte ptr [rdi + r10 + 9], 1 + pinsrb xmm11, byte ptr [rdi + r12 + 9], 2 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rax + 9], 3 + pinsrb xmm11, byte ptr [rdi + rdx + 9], 4 + mov rbx, rdx + pinsrb xmm11, byte ptr [rdi + rcx + 9], 5 + pinsrb xmm11, byte ptr [rdi + r9 + 9], 6 + mov qword ptr [rsp + 144], r11 # 8-byte Spill + pinsrb xmm11, byte ptr [rdi + r11 + 9], 7 + pinsrb xmm11, byte ptr [rdi + r15 + 9], 8 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rsi + 9], 9 + mov rax, r13 + pinsrb xmm11, byte ptr [rdi + r13 + 9], 10 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r13 + 9], 11 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rdx + 9], 12 + pinsrb xmm11, byte ptr [rdi + r8 + 9], 13 + mov r12, r8 + pinsrb xmm11, byte ptr [rdi + r14 + 9], 14 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r8 + 9], 15 + pinsrb xmm12, byte ptr [rdi + r10 + 10], 1 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rcx + 10], 2 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rcx + 10], 3 + pinsrb xmm12, byte ptr [rdi + rbx + 10], 4 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rbx + 10], 5 + pinsrb xmm12, byte ptr [rdi + r9 + 10], 6 + pinsrb xmm12, byte ptr [rdi + r11 + 10], 7 + pinsrb xmm12, byte ptr [rdi + r15 + 10], 8 + pinsrb xmm12, byte ptr [rdi + rsi + 10], 9 + pinsrb xmm12, byte ptr [rdi + rax + 10], 10 + pinsrb xmm12, byte ptr [rdi + r13 + 10], 11 + pinsrb xmm12, byte ptr [rdi + rdx + 10], 12 + pinsrb xmm12, byte ptr [rdi + r12 + 10], 13 + pinsrb xmm12, byte ptr [rdi + r14 + 10], 14 + mov r11, r14 + pinsrb xmm12, byte ptr [rdi + r8 + 10], 15 + pinsrb xmm13, byte ptr [rdi + r10 + 11], 1 + mov r14, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r14 + 11], 2 + pinsrb xmm13, byte ptr [rdi + rcx + 11], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + rcx + 11], 4 + pinsrb xmm13, byte ptr [rdi + rbx + 11], 5 + pinsrb xmm13, byte ptr [rdi + r9 + 11], 6 + mov r9, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r9 + 11], 7 + pinsrb xmm13, byte ptr [rdi + r15 + 11], 8 + pinsrb xmm13, byte ptr [rdi + rsi + 11], 9 + pinsrb xmm13, byte ptr [rdi + rax + 11], 10 + pinsrb xmm13, byte ptr [rdi + r13 + 11], 11 + pinsrb xmm13, byte ptr [rdi + rdx + 11], 12 + pinsrb xmm13, byte ptr [rdi + r12 + 11], 13 + pinsrb xmm13, byte ptr [rdi + r11 + 11], 14 + pinsrb xmm13, byte ptr [rdi + r8 + 11], 15 + pcmpeqb xmm11, xmm14 + pandn xmm11, xmmword ptr [rip + .LCPI5_16] + paddb xmm11, xmm0 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + movzx esi, byte ptr [rdi + r8 + 23] + movd xmm8, esi + pcmpeqb xmm12, xmm14 + pandn xmm12, xmmword ptr [rip + .LCPI5_17] + pcmpeqb xmm13, xmm14 + pandn xmm13, xmmword ptr [rip + .LCPI5_18] + por xmm13, xmm12 + movzx esi, byte ptr [rdi + r8 + 24] + movd xmm12, esi + movdqa xmm9, xmmword ptr [rsp + 224] # 16-byte Reload + pinsrb xmm9, byte ptr [rdi + r10 + 12], 1 + mov r12, r14 + pinsrb xmm9, byte ptr [rdi + r14 + 12], 2 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r11 + 12], 3 + mov r14, rcx + pinsrb xmm9, byte ptr [rdi + rcx + 12], 4 + pinsrb xmm9, byte ptr [rdi + rbx + 12], 5 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r8 + 12], 6 + mov r10, r9 + pinsrb xmm9, byte ptr [rdi + r9 + 12], 7 + mov r9, r15 + pinsrb xmm9, byte ptr [rdi + r15 + 12], 8 + mov r15, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r15 + 12], 9 + mov r13, rax + pinsrb xmm9, byte ptr [rdi + rax + 12], 10 mov rcx, qword ptr [rsp + 64] # 8-byte Reload - movdqu xmmword ptr [r8 + 4*rcx], xmm12 - mov qword ptr [rsp + 8], r8 # 8-byte Spill - movdqu xmmword ptr [r8 + 4*rcx + 16], xmm0 - add rcx, 8 - mov rdi, rcx - cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload - jne .LBB5_134 -# %bb.135: - mov r10, qword ptr [rsp + 208] # 8-byte Reload - cmp r10, qword ptr [rsp + 40] # 8-byte Folded Reload - mov r15, qword ptr [rsp + 160] # 8-byte Reload - mov r11d, dword ptr [rsp + 16] # 4-byte Reload - mov r12, qword ptr [rsp + 56] # 8-byte Reload - mov r14, qword ptr [rsp + 48] # 8-byte Reload - jne .LBB5_136 - jmp .LBB5_139 -.LBB5_181: + pinsrb xmm9, byte ptr [rdi + rcx + 12], 11 + pinsrb xmm9, byte ptr [rdi + rdx + 12], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rsi + 12], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 12], 14 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rax + 12], 15 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 13], 1 + pinsrb xmm6, byte ptr [rdi + r12 + 13], 2 + pinsrb xmm6, byte ptr [rdi + r11 + 13], 3 + pinsrb xmm6, byte ptr [rdi + r14 + 13], 4 + pinsrb xmm6, byte ptr [rdi + rbx + 13], 5 + pinsrb xmm6, byte ptr [rdi + r8 + 13], 6 + pinsrb xmm6, byte ptr [rdi + r10 + 13], 7 + pinsrb xmm6, byte ptr [rdi + r9 + 13], 8 + pinsrb xmm6, byte ptr [rdi + r15 + 13], 9 + pinsrb xmm6, byte ptr [rdi + r13 + 13], 10 + pinsrb xmm6, byte ptr [rdi + rcx + 13], 11 + pinsrb xmm6, byte ptr [rdi + rdx + 13], 12 + pinsrb xmm6, byte ptr [rdi + rsi + 13], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 13], 14 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 13], 15 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rax + 14], 1 + pinsrb xmm15, byte ptr [rdi + r12 + 14], 2 + pinsrb xmm15, byte ptr [rdi + r11 + 14], 3 + pinsrb xmm15, byte ptr [rdi + r14 + 14], 4 + pinsrb xmm15, byte ptr [rdi + rbx + 14], 5 + pinsrb xmm15, byte ptr [rdi + r8 + 14], 6 + pinsrb xmm15, byte ptr [rdi + r10 + 14], 7 + pinsrb xmm15, byte ptr [rdi + r9 + 14], 8 + pinsrb xmm15, byte ptr [rdi + r15 + 14], 9 + pinsrb xmm15, byte ptr [rdi + r13 + 14], 10 + pinsrb xmm15, byte ptr [rdi + rcx + 14], 11 + mov r15, rcx + pinsrb xmm15, byte ptr [rdi + rdx + 14], 12 + mov r13, rdx + pinsrb xmm15, byte ptr [rdi + rsi + 14], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rax + 14], 14 + pcmpeqb xmm9, xmm14 + pandn xmm9, xmmword ptr [rip + .LCPI5_19] + por xmm9, xmm13 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 25] + movd xmm13, esi + psubb xmm11, xmmword ptr [rip + .LCPI5_22] + por xmm9, xmm11 + movzx esi, byte ptr [rdi + rax + 26] + movd xmm0, esi + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rcx + 14], 15 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmmword ptr [rip + .LCPI5_20] + pcmpeqb xmm15, xmm14 + pandn xmm15, xmmword ptr [rip + .LCPI5_21] + por xmm15, xmm6 + movzx esi, byte ptr [rdi + rax + 27] + movd xmm11, esi + movdqa xmm6, xmmword ptr [rsp + 192] # 16-byte Reload + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r11 + 15], 1 + pinsrb xmm6, byte ptr [rdi + r12 + 15], 2 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rdx + 15], 3 + pinsrb xmm6, byte ptr [rdi + r14 + 15], 4 + pinsrb xmm6, byte ptr [rdi + rbx + 15], 5 + pinsrb xmm6, byte ptr [rdi + r8 + 15], 6 mov r8, r10 - and r8, -4 - mov rbx, r8 - shl rbx, 7 - add rbx, r14 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - lea r12, [rax + 4*r8] - movaps xmm1, xmm0 - shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] - add r14, 508 - xor ecx, ecx - movdqa xmm15, xmmword ptr [rip + .LCPI5_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> - movdqa xmm8, xmmword ptr [rip + .LCPI5_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - movdqa xmm10, xmmword ptr [rip + .LCPI5_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - movdqa xmm11, xmmword ptr [rip + .LCPI5_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - movdqa xmm12, xmmword ptr [rip + .LCPI5_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - movdqa xmm13, xmmword ptr [rip + .LCPI5_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] - movdqa xmm14, xmmword ptr [rip + .LCPI5_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - movdqa xmm9, xmmword ptr [rip + .LCPI5_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] - mov rax, qword ptr [rsp + 8] # 8-byte Reload - .p2align 4, 0x90 -.LBB5_182: # =>This Inner Loop Header: Depth=1 - movss xmm6, dword ptr [r14 - 508] # xmm6 = mem[0],zero,zero,zero - movss xmm7, dword ptr [r14 - 504] # xmm7 = mem[0],zero,zero,zero - movss xmm5, dword ptr [r14 - 500] # xmm5 = mem[0],zero,zero,zero - movss xmm4, dword ptr [r14 - 496] # xmm4 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [r14 - 380], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [r14 - 252], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [r14 - 124], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - insertps xmm7, dword ptr [r14 - 376], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [r14 - 248], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [r14 - 120], 48 # xmm7 = xmm7[0,1,2],mem[0] - insertps xmm5, dword ptr [r14 - 372], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [r14 - 244], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [r14 - 116], 48 # xmm5 = xmm5[0,1,2],mem[0] - insertps xmm4, dword ptr [r14 - 368], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] - insertps xmm4, dword ptr [r14 - 240], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] - insertps xmm4, dword ptr [r14 - 112], 48 # xmm4 = xmm4[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - movdqa xmm2, xmm7 - pand xmm2, xmm15 - psubb xmm2, xmm7 - movss xmm7, dword ptr [r14 - 492] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [r14 - 364], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [r14 - 236], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [r14 - 108], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm2, xmm6 - movss xmm6, dword ptr [r14 - 488] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [r14 - 360], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [r14 - 232], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [r14 - 104], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 2 - pand xmm5, xmm8 - por xmm5, xmm2 - movss xmm3, dword ptr [r14 - 484] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [r14 - 356], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [r14 - 228], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [r14 - 100], 48 # xmm3 = xmm3[0,1,2],mem[0] - cmpneqps xmm4, xmm1 - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 - pand xmm4, xmm15 - psllw xmm4, 3 - pand xmm4, xmm10 - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 4 - pand xmm7, xmm11 - por xmm7, xmm4 - movss xmm4, dword ptr [r14 - 480] # xmm4 = mem[0],zero,zero,zero - insertps xmm4, dword ptr [r14 - 352], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] - insertps xmm4, dword ptr [r14 - 224], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] - insertps xmm4, dword ptr [r14 - 96], 48 # xmm4 = xmm4[0,1,2],mem[0] - por xmm7, xmm5 - movss xmm5, dword ptr [r14 - 476] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [r14 - 348], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [r14 - 220], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [r14 - 92], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 6 - pand xmm3, xmm13 - por xmm3, xmm6 - movss xmm2, dword ptr [r14 - 472] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [r14 - 344], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [r14 - 216], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [r14 - 88], 48 # xmm2 = xmm2[0,1,2],mem[0] - packsswb xmm5, xmm5 - cmpneqps xmm4, xmm1 - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 - psllw xmm4, 7 - pand xmm4, xmm14 - por xmm4, xmm3 - movss xmm3, dword ptr [r14 - 468] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [r14 - 340], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [r14 - 212], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - pand xmm5, xmm15 - insertps xmm3, dword ptr [r14 - 84], 48 # xmm3 = xmm3[0,1,2],mem[0] - por xmm4, xmm7 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm6, xmm2 - pand xmm6, xmm15 - psubb xmm6, xmm2 - movss xmm7, dword ptr [r14 - 464] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [r14 - 336], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [r14 - 208], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [r14 - 80], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm6, xmm5 - movss xmm5, dword ptr [r14 - 460] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [r14 - 332], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [r14 - 204], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [r14 - 76], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm6 - movss xmm6, dword ptr [r14 - 456] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [r14 - 328], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [r14 - 200], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [r14 - 72], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 3 - pand xmm7, xmm10 - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 4 - pand xmm5, xmm11 + pinsrb xmm6, byte ptr [rdi + r10 + 15], 7 + pinsrb xmm6, byte ptr [rdi + r9 + 15], 8 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r9 + 15], 9 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r10 + 15], 10 + pinsrb xmm6, byte ptr [rdi + r15 + 15], 11 + pinsrb xmm6, byte ptr [rdi + r13 + 15], 12 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rsi + 15], 13 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rsi + 15], 14 + pinsrb xmm6, byte ptr [rdi + rcx + 15], 15 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmmword ptr [rip + .LCPI5_6] + por xmm6, xmm15 + movzx esi, byte ptr [rdi + rax + 28] + movd xmm15, esi + por xmm6, xmm9 + movdqa xmmword ptr [rsp + 192], xmm6 # 16-byte Spill + movzx esi, byte ptr [rdi + rax + 29] + movd xmm9, esi + mov rax, r11 + pinsrb xmm10, byte ptr [rdi + r11 + 16], 1 + pinsrb xmm10, byte ptr [rdi + r12 + 16], 2 + pinsrb xmm10, byte ptr [rdi + rdx + 16], 3 + pinsrb xmm10, byte ptr [rdi + r14 + 16], 4 + pinsrb xmm10, byte ptr [rdi + rbx + 16], 5 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rdx + 16], 6 + pinsrb xmm10, byte ptr [rdi + r8 + 16], 7 + mov r11, r8 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r8 + 16], 8 + pinsrb xmm10, byte ptr [rdi + r9 + 16], 9 + pinsrb xmm10, byte ptr [rdi + r10 + 16], 10 + pinsrb xmm10, byte ptr [rdi + r15 + 16], 11 + pinsrb xmm10, byte ptr [rdi + r13 + 16], 12 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rcx + 16], 13 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rcx + 16], 14 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rsi + 16], 15 + pinsrb xmm4, byte ptr [rdi + rax + 17], 1 + pinsrb xmm4, byte ptr [rdi + r12 + 17], 2 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r12 + 17], 3 + pinsrb xmm4, byte ptr [rdi + r14 + 17], 4 + pinsrb xmm4, byte ptr [rdi + rbx + 17], 5 + pinsrb xmm4, byte ptr [rdi + rdx + 17], 6 + pinsrb xmm4, byte ptr [rdi + r11 + 17], 7 + pinsrb xmm4, byte ptr [rdi + r8 + 17], 8 + pinsrb xmm4, byte ptr [rdi + r9 + 17], 9 + pinsrb xmm4, byte ptr [rdi + r10 + 17], 10 + pinsrb xmm4, byte ptr [rdi + r15 + 17], 11 + pinsrb xmm4, byte ptr [rdi + r13 + 17], 12 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rdx + 17], 13 + pinsrb xmm4, byte ptr [rdi + rcx + 17], 14 + mov r9, rcx + pinsrb xmm4, byte ptr [rdi + rsi + 17], 15 + pcmpeqb xmm10, xmm14 + pcmpeqb xmm4, xmm14 + movdqa xmm6, xmmword ptr [rip + .LCPI5_16] # xmm6 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pandn xmm4, xmm6 + paddb xmm4, xmm10 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 30] + movd xmm10, esi + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 18], 1 + pinsrb xmm5, byte ptr [rdi + rsi + 19], 1 + pinsrb xmm3, byte ptr [rdi + rsi + 20], 1 + pinsrb xmm2, byte ptr [rdi + rsi + 21], 1 + pinsrb xmm1, byte ptr [rdi + rsi + 22], 1 + pinsrb xmm8, byte ptr [rdi + rsi + 23], 1 + pinsrb xmm12, byte ptr [rdi + rsi + 24], 1 + pinsrb xmm13, byte ptr [rdi + rsi + 25], 1 + pinsrb xmm0, byte ptr [rdi + rsi + 26], 1 + pinsrb xmm11, byte ptr [rdi + rsi + 27], 1 + pinsrb xmm15, byte ptr [rdi + rsi + 28], 1 + pinsrb xmm9, byte ptr [rdi + rsi + 29], 1 + pinsrb xmm10, byte ptr [rdi + rsi + 30], 1 + movzx eax, byte ptr [rdi + rax + 31] + movd xmm6, eax + pinsrb xmm6, byte ptr [rdi + rsi + 31], 1 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 18], 2 + pinsrb xmm5, byte ptr [rdi + rax + 19], 2 + pinsrb xmm3, byte ptr [rdi + rax + 20], 2 + pinsrb xmm2, byte ptr [rdi + rax + 21], 2 + pinsrb xmm1, byte ptr [rdi + rax + 22], 2 + pinsrb xmm8, byte ptr [rdi + rax + 23], 2 + pinsrb xmm12, byte ptr [rdi + rax + 24], 2 + pinsrb xmm13, byte ptr [rdi + rax + 25], 2 + pinsrb xmm0, byte ptr [rdi + rax + 26], 2 + pinsrb xmm11, byte ptr [rdi + rax + 27], 2 + pinsrb xmm15, byte ptr [rdi + rax + 28], 2 + pinsrb xmm9, byte ptr [rdi + rax + 29], 2 + pinsrb xmm10, byte ptr [rdi + rax + 30], 2 + pinsrb xmm6, byte ptr [rdi + rax + 31], 2 + mov r11, r12 + pinsrb xmm7, byte ptr [rdi + r12 + 18], 3 + pinsrb xmm7, byte ptr [rdi + r14 + 18], 4 + pinsrb xmm7, byte ptr [rdi + rbx + 18], 5 + mov r8, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r8 + 18], 6 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r10 + 18], 7 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rcx + 18], 8 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 18], 9 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 18], 10 + pinsrb xmm7, byte ptr [rdi + r15 + 18], 11 + pinsrb xmm7, byte ptr [rdi + r13 + 18], 12 + pinsrb xmm7, byte ptr [rdi + rdx + 18], 13 + pinsrb xmm7, byte ptr [rdi + r9 + 18], 14 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r12 + 18], 15 + pinsrb xmm5, byte ptr [rdi + r11 + 19], 3 + pinsrb xmm5, byte ptr [rdi + r14 + 19], 4 + pinsrb xmm5, byte ptr [rdi + rbx + 19], 5 + pinsrb xmm5, byte ptr [rdi + r8 + 19], 6 + pinsrb xmm5, byte ptr [rdi + r10 + 19], 7 + pinsrb xmm5, byte ptr [rdi + rcx + 19], 8 + pinsrb xmm5, byte ptr [rdi + rax + 19], 9 + pinsrb xmm5, byte ptr [rdi + rsi + 19], 10 + pinsrb xmm5, byte ptr [rdi + r15 + 19], 11 + pinsrb xmm5, byte ptr [rdi + r13 + 19], 12 + pinsrb xmm5, byte ptr [rdi + rdx + 19], 13 + pinsrb xmm5, byte ptr [rdi + r9 + 19], 14 + pinsrb xmm5, byte ptr [rdi + r12 + 19], 15 + pinsrb xmm3, byte ptr [rdi + r11 + 20], 3 + pinsrb xmm3, byte ptr [rdi + r14 + 20], 4 + pinsrb xmm3, byte ptr [rdi + rbx + 20], 5 + pinsrb xmm3, byte ptr [rdi + r8 + 20], 6 + pinsrb xmm3, byte ptr [rdi + r10 + 20], 7 + pinsrb xmm3, byte ptr [rdi + rcx + 20], 8 + pinsrb xmm3, byte ptr [rdi + rax + 20], 9 + pinsrb xmm3, byte ptr [rdi + rsi + 20], 10 + pinsrb xmm3, byte ptr [rdi + r15 + 20], 11 + pinsrb xmm3, byte ptr [rdi + r13 + 20], 12 + pinsrb xmm3, byte ptr [rdi + rdx + 20], 13 + pinsrb xmm3, byte ptr [rdi + r9 + 20], 14 + pcmpeqb xmm7, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI5_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm7, xmm14 + pcmpeqb xmm5, xmmword ptr [rsp + 176] # 16-byte Folded Reload + movdqa xmm14, xmmword ptr [rip + .LCPI5_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm5, xmm14 por xmm5, xmm7 - movss xmm2, dword ptr [r14 - 452] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [r14 - 324], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [r14 - 196], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [r14 - 68], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm5, xmm3 - movss xmm7, dword ptr [r14 - 448] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [r14 - 320], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [r14 - 192], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [r14 - 64], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm6 - movss xmm6, dword ptr [r14 - 444] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [r14 - 316], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [r14 - 188], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [r14 - 60], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - psllw xmm7, 7 - pand xmm7, xmm14 - por xmm7, xmm2 - movss xmm2, dword ptr [r14 - 440] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [r14 - 312], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [r14 - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [r14 - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm7, xmm5 - movss xmm3, dword ptr [r14 - 436] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [r14 - 308], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [r14 - 180], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - pand xmm6, xmm15 - insertps xmm3, dword ptr [r14 - 52], 48 # xmm3 = xmm3[0,1,2],mem[0] - punpckldq xmm4, xmm7 # xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1] - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm7, xmm2 - pand xmm7, xmm15 - psubb xmm7, xmm2 - movss xmm5, dword ptr [r14 - 432] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [r14 - 304], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [r14 - 176], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [r14 - 48], 48 # xmm5 = xmm5[0,1,2],mem[0] - por xmm7, xmm6 - movss xmm6, dword ptr [r14 - 428] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [r14 - 300], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [r14 - 172], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [r14 - 44], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm7 - movss xmm7, dword ptr [r14 - 424] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [r14 - 296], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [r14 - 168], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [r14 - 40], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 3 - pand xmm5, xmm10 - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 4 - pand xmm6, xmm11 - por xmm6, xmm5 - movss xmm2, dword ptr [r14 - 420] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [r14 - 292], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [r14 - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [r14 - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm6, xmm3 - movss xmm5, dword ptr [r14 - 416] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [r14 - 288], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [r14 - 160], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [r14 - 32], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 5 - pand xmm7, xmm12 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm7 - movss xmm7, dword ptr [r14 - 412] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [r14 - 284], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [r14 - 156], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [r14 - 28], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - cmpneqps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - psllw xmm5, 7 - pand xmm5, xmm14 - por xmm5, xmm2 - movss xmm2, dword ptr [r14 - 408] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [r14 - 280], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [r14 - 152], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - pand xmm7, xmm15 - insertps xmm2, dword ptr [r14 - 24], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm5, xmm6 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm6, xmm2 - pand xmm6, xmm15 - psubb xmm6, xmm2 - movss xmm3, dword ptr [r14 - 404] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [r14 - 276], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [r14 - 148], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [r14 - 20], 48 # xmm3 = xmm3[0,1,2],mem[0] - por xmm6, xmm7 - movss xmm2, dword ptr [r14 - 400] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [r14 - 272], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [r14 - 144], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [r14 - 16], 48 # xmm2 = xmm2[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm6 - movss xmm6, dword ptr [r14 - 396] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [r14 - 268], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [r14 - 140], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [r14 - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 3 - pand xmm2, xmm10 - cmpneqps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 4 - pand xmm6, xmm11 - por xmm6, xmm2 - movss xmm7, dword ptr [r14 - 392] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [r14 - 264], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [r14 - 136], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [r14 - 8], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm6, xmm3 - movss xmm2, dword ptr [r14 - 388] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [r14 - 260], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [r14 - 132], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [r14 - 4], 48 # xmm2 = xmm2[0,1,2],mem[0] - cmpneqps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 5 - pand xmm7, xmm12 - cmpneqps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm7 - movss xmm3, dword ptr [r14 - 384] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [r14 - 256], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [r14 - 128], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [r14], 48 # xmm3 = xmm3[0,1,2],mem[0] - cmpneqps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - psllw xmm3, 7 - pand xmm3, xmm14 - por xmm3, xmm2 - por xmm3, xmm6 - punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] - punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] - pshufb xmm4, xmm9 - movdqu xmmword ptr [rax + 4*rcx], xmm4 - add rcx, 4 - add r14, 512 - cmp r8, rcx - jne .LBB5_182 -# %bb.183: - cmp r10, r8 - jne .LBB5_184 - jmp .LBB5_187 + pinsrb xmm3, byte ptr [rdi + r12 + 20], 15 + movdqa xmm14, xmmword ptr [rsp + 176] # 16-byte Reload + pcmpeqb xmm3, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI5_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm3, xmm7 + por xmm3, xmm5 + pcmpeqd xmm5, xmm5 + psubb xmm4, xmm5 + por xmm3, xmm4 + pinsrb xmm2, byte ptr [rdi + r11 + 21], 3 + pinsrb xmm2, byte ptr [rdi + r14 + 21], 4 + pinsrb xmm2, byte ptr [rdi + rbx + 21], 5 + pinsrb xmm2, byte ptr [rdi + r8 + 21], 6 + pinsrb xmm2, byte ptr [rdi + r10 + 21], 7 + pinsrb xmm2, byte ptr [rdi + rcx + 21], 8 + pinsrb xmm2, byte ptr [rdi + rax + 21], 9 + pinsrb xmm2, byte ptr [rdi + rsi + 21], 10 + pinsrb xmm2, byte ptr [rdi + r15 + 21], 11 + pinsrb xmm2, byte ptr [rdi + r13 + 21], 12 + pinsrb xmm2, byte ptr [rdi + rdx + 21], 13 + pinsrb xmm2, byte ptr [rdi + r9 + 21], 14 + pinsrb xmm2, byte ptr [rdi + r12 + 21], 15 + pinsrb xmm1, byte ptr [rdi + r11 + 22], 3 + pinsrb xmm1, byte ptr [rdi + r14 + 22], 4 + pinsrb xmm1, byte ptr [rdi + rbx + 22], 5 + pinsrb xmm1, byte ptr [rdi + r8 + 22], 6 + pinsrb xmm1, byte ptr [rdi + r10 + 22], 7 + pinsrb xmm1, byte ptr [rdi + rcx + 22], 8 + pinsrb xmm1, byte ptr [rdi + rax + 22], 9 + pinsrb xmm1, byte ptr [rdi + rsi + 22], 10 + pinsrb xmm1, byte ptr [rdi + r15 + 22], 11 + pinsrb xmm1, byte ptr [rdi + r13 + 22], 12 + pinsrb xmm1, byte ptr [rdi + rdx + 22], 13 + pinsrb xmm1, byte ptr [rdi + r9 + 22], 14 + pinsrb xmm1, byte ptr [rdi + r12 + 22], 15 + pinsrb xmm8, byte ptr [rdi + r11 + 23], 3 + pinsrb xmm8, byte ptr [rdi + r14 + 23], 4 + pinsrb xmm8, byte ptr [rdi + rbx + 23], 5 + pinsrb xmm8, byte ptr [rdi + r8 + 23], 6 + pinsrb xmm8, byte ptr [rdi + r10 + 23], 7 + pinsrb xmm8, byte ptr [rdi + rcx + 23], 8 + pinsrb xmm8, byte ptr [rdi + rax + 23], 9 + pinsrb xmm8, byte ptr [rdi + rsi + 23], 10 + pinsrb xmm8, byte ptr [rdi + r15 + 23], 11 + pinsrb xmm8, byte ptr [rdi + r13 + 23], 12 + pinsrb xmm8, byte ptr [rdi + rdx + 23], 13 + pinsrb xmm8, byte ptr [rdi + r9 + 23], 14 + pcmpeqb xmm2, xmm14 + movdqa xmm5, xmmword ptr [rip + .LCPI5_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm5 + pcmpeqb xmm1, xmm14 + movdqa xmm7, xmmword ptr [rip + .LCPI5_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm1, xmm7 + por xmm1, xmm2 + pinsrb xmm8, byte ptr [rdi + r12 + 23], 15 + pcmpeqb xmm8, xmm14 + movdqa xmm4, xmmword ptr [rip + .LCPI5_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm8, xmm4 + por xmm8, xmm1 + pinsrb xmm12, byte ptr [rdi + r11 + 24], 3 + pinsrb xmm12, byte ptr [rdi + r14 + 24], 4 + pinsrb xmm12, byte ptr [rdi + rbx + 24], 5 + pinsrb xmm12, byte ptr [rdi + r8 + 24], 6 + pinsrb xmm12, byte ptr [rdi + r10 + 24], 7 + pinsrb xmm12, byte ptr [rdi + rcx + 24], 8 + pinsrb xmm12, byte ptr [rdi + rax + 24], 9 + pinsrb xmm12, byte ptr [rdi + rsi + 24], 10 + pinsrb xmm12, byte ptr [rdi + r15 + 24], 11 + pinsrb xmm12, byte ptr [rdi + r13 + 24], 12 + pinsrb xmm12, byte ptr [rdi + rdx + 24], 13 + pinsrb xmm12, byte ptr [rdi + r9 + 24], 14 + pinsrb xmm12, byte ptr [rdi + r12 + 24], 15 + por xmm8, xmm3 + pcmpeqb xmm12, xmm14 + pinsrb xmm13, byte ptr [rdi + r11 + 25], 3 + pinsrb xmm13, byte ptr [rdi + r14 + 25], 4 + pinsrb xmm13, byte ptr [rdi + rbx + 25], 5 + pinsrb xmm13, byte ptr [rdi + r8 + 25], 6 + pinsrb xmm13, byte ptr [rdi + r10 + 25], 7 + pinsrb xmm13, byte ptr [rdi + rcx + 25], 8 + pinsrb xmm13, byte ptr [rdi + rax + 25], 9 + pinsrb xmm13, byte ptr [rdi + rsi + 25], 10 + pinsrb xmm13, byte ptr [rdi + r15 + 25], 11 + pinsrb xmm13, byte ptr [rdi + r13 + 25], 12 + pinsrb xmm13, byte ptr [rdi + rdx + 25], 13 + pinsrb xmm13, byte ptr [rdi + r9 + 25], 14 + pinsrb xmm13, byte ptr [rdi + r12 + 25], 15 + pinsrb xmm0, byte ptr [rdi + r11 + 26], 3 + pinsrb xmm0, byte ptr [rdi + r14 + 26], 4 + pinsrb xmm0, byte ptr [rdi + rbx + 26], 5 + pinsrb xmm0, byte ptr [rdi + r8 + 26], 6 + pinsrb xmm0, byte ptr [rdi + r10 + 26], 7 + pinsrb xmm0, byte ptr [rdi + rcx + 26], 8 + pinsrb xmm0, byte ptr [rdi + rax + 26], 9 + pinsrb xmm0, byte ptr [rdi + rsi + 26], 10 + pinsrb xmm0, byte ptr [rdi + r15 + 26], 11 + pinsrb xmm0, byte ptr [rdi + r13 + 26], 12 + pinsrb xmm0, byte ptr [rdi + rdx + 26], 13 + pinsrb xmm0, byte ptr [rdi + r9 + 26], 14 + pinsrb xmm0, byte ptr [rdi + r12 + 26], 15 + pinsrb xmm11, byte ptr [rdi + r11 + 27], 3 + pinsrb xmm11, byte ptr [rdi + r14 + 27], 4 + pinsrb xmm11, byte ptr [rdi + rbx + 27], 5 + pinsrb xmm11, byte ptr [rdi + r8 + 27], 6 + pinsrb xmm11, byte ptr [rdi + r10 + 27], 7 + pinsrb xmm11, byte ptr [rdi + rcx + 27], 8 + pinsrb xmm11, byte ptr [rdi + rax + 27], 9 + pinsrb xmm11, byte ptr [rdi + rsi + 27], 10 + pinsrb xmm11, byte ptr [rdi + r15 + 27], 11 + pinsrb xmm11, byte ptr [rdi + r13 + 27], 12 + pinsrb xmm11, byte ptr [rdi + rdx + 27], 13 + pinsrb xmm11, byte ptr [rdi + r9 + 27], 14 + pcmpeqb xmm13, xmm14 + pandn xmm13, xmmword ptr [rip + .LCPI5_16] + paddb xmm13, xmm12 + pinsrb xmm11, byte ptr [rdi + r12 + 27], 15 + pcmpeqb xmm0, xmm14 + pandn xmm0, xmmword ptr [rip + .LCPI5_17] + pcmpeqb xmm11, xmm14 + pandn xmm11, xmmword ptr [rip + .LCPI5_18] + por xmm11, xmm0 + pinsrb xmm15, byte ptr [rdi + r11 + 28], 3 + pinsrb xmm9, byte ptr [rdi + r11 + 29], 3 + pinsrb xmm10, byte ptr [rdi + r11 + 30], 3 + pinsrb xmm6, byte ptr [rdi + r11 + 31], 3 + pinsrb xmm15, byte ptr [rdi + r14 + 28], 4 + pinsrb xmm9, byte ptr [rdi + r14 + 29], 4 + pinsrb xmm10, byte ptr [rdi + r14 + 30], 4 + pinsrb xmm6, byte ptr [rdi + r14 + 31], 4 + pinsrb xmm15, byte ptr [rdi + rbx + 28], 5 + pinsrb xmm9, byte ptr [rdi + rbx + 29], 5 + pinsrb xmm10, byte ptr [rdi + rbx + 30], 5 + pinsrb xmm6, byte ptr [rdi + rbx + 31], 5 + mov rbx, r8 + pinsrb xmm15, byte ptr [rdi + r8 + 28], 6 + pinsrb xmm9, byte ptr [rdi + r8 + 29], 6 + pinsrb xmm10, byte ptr [rdi + r8 + 30], 6 + pinsrb xmm6, byte ptr [rdi + r8 + 31], 6 + mov rbx, r10 + pinsrb xmm15, byte ptr [rdi + r10 + 28], 7 + pinsrb xmm9, byte ptr [rdi + r10 + 29], 7 + pinsrb xmm10, byte ptr [rdi + r10 + 30], 7 + pinsrb xmm6, byte ptr [rdi + r10 + 31], 7 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + mov rbx, rcx + pinsrb xmm15, byte ptr [rdi + rcx + 28], 8 + pinsrb xmm9, byte ptr [rdi + rcx + 29], 8 + pinsrb xmm10, byte ptr [rdi + rcx + 30], 8 + pinsrb xmm6, byte ptr [rdi + rcx + 31], 8 + pinsrb xmm15, byte ptr [rdi + rax + 28], 9 + pinsrb xmm9, byte ptr [rdi + rax + 29], 9 + pinsrb xmm10, byte ptr [rdi + rax + 30], 9 + pinsrb xmm6, byte ptr [rdi + rax + 31], 9 + mov rax, rsi + pinsrb xmm15, byte ptr [rdi + rsi + 28], 10 + pinsrb xmm9, byte ptr [rdi + rsi + 29], 10 + pinsrb xmm10, byte ptr [rdi + rsi + 30], 10 + pinsrb xmm6, byte ptr [rdi + rsi + 31], 10 + pinsrb xmm15, byte ptr [rdi + r15 + 28], 11 + pinsrb xmm9, byte ptr [rdi + r15 + 29], 11 + pinsrb xmm10, byte ptr [rdi + r15 + 30], 11 + pinsrb xmm6, byte ptr [rdi + r15 + 31], 11 + pinsrb xmm15, byte ptr [rdi + r13 + 28], 12 + pinsrb xmm9, byte ptr [rdi + r13 + 29], 12 + pinsrb xmm10, byte ptr [rdi + r13 + 30], 12 + pinsrb xmm6, byte ptr [rdi + r13 + 31], 12 + mov rax, rdx + pinsrb xmm15, byte ptr [rdi + rdx + 28], 13 + pinsrb xmm9, byte ptr [rdi + rdx + 29], 13 + pinsrb xmm10, byte ptr [rdi + rdx + 30], 13 + pinsrb xmm6, byte ptr [rdi + rdx + 31], 13 + mov rax, r9 + pinsrb xmm15, byte ptr [rdi + r9 + 28], 14 + pinsrb xmm9, byte ptr [rdi + r9 + 29], 14 + pinsrb xmm10, byte ptr [rdi + r9 + 30], 14 + pinsrb xmm6, byte ptr [rdi + r9 + 31], 14 + mov rax, r12 + pinsrb xmm15, byte ptr [rdi + r12 + 28], 15 + pinsrb xmm9, byte ptr [rdi + r12 + 29], 15 + pinsrb xmm10, byte ptr [rdi + r12 + 30], 15 + pcmpeqb xmm15, xmm14 + pandn xmm15, xmmword ptr [rip + .LCPI5_19] + por xmm15, xmm11 + pinsrb xmm6, byte ptr [rdi + r12 + 31], 15 + psubb xmm13, xmmword ptr [rip + .LCPI5_22] + por xmm15, xmm13 + pcmpeqb xmm9, xmm14 + pandn xmm9, xmm5 + pcmpeqb xmm10, xmm14 + pandn xmm10, xmm7 + por xmm10, xmm9 + pcmpeqb xmm6, xmm14 + pandn xmm6, xmm4 + por xmm6, xmm10 + por xmm6, xmm15 + movdqa xmm0, xmm8 + punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] + movdqa xmm3, xmmword ptr [rsp + 208] # 16-byte Reload + movdqa xmm1, xmm3 + movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload + punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] + movdqa xmm2, xmm1 + punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] + punpckhwd xmm1, xmm0 # xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + punpckhbw xmm8, xmm6 # xmm8 = xmm8[8],xmm6[8],xmm8[9],xmm6[9],xmm8[10],xmm6[10],xmm8[11],xmm6[11],xmm8[12],xmm6[12],xmm8[13],xmm6[13],xmm8[14],xmm6[14],xmm8[15],xmm6[15] + punpckhbw xmm3, xmm4 # xmm3 = xmm3[8],xmm4[8],xmm3[9],xmm4[9],xmm3[10],xmm4[10],xmm3[11],xmm4[11],xmm3[12],xmm4[12],xmm3[13],xmm4[13],xmm3[14],xmm4[14],xmm3[15],xmm4[15] + movdqa xmm0, xmm3 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + movdqu xmmword ptr [r8 + 4*rcx + 48], xmm3 + movdqu xmmword ptr [r8 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r8 + 4*rcx + 16], xmm1 + movdqu xmmword ptr [r8 + 4*rcx], xmm2 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + jne .LBB5_218 +# %bb.219: + mov rcx, qword ptr [rsp + 240] # 8-byte Reload + cmp rcx, qword ptr [rsp + 168] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14b, byte ptr [rsp + 12] # 1-byte Reload + mov r13, qword ptr [rsp + 256] # 8-byte Reload + mov rdi, qword ptr [rsp + 248] # 8-byte Reload + jne .LBB5_168 + jmp .LBB5_172 .Lfunc_end5: .size comparison_not_equal_scalar_arr_sse4, .Lfunc_end5-comparison_not_equal_scalar_arr_sse4 # -- End function @@ -32076,76 +33003,91 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 and rsp, -8 sub rsp, 72 # kill: def $r9d killed $r9d def $r9 - mov r11, r8 - mov r14, rcx + mov r13, r8 + mov r15, rcx cmp edi, 6 - jg .LBB6_29 + jg .LBB6_35 # %bb.1: cmp edi, 3 jle .LBB6_2 -# %bb.15: +# %bb.18: cmp edi, 4 - je .LBB6_68 -# %bb.16: + je .LBB6_83 +# %bb.19: cmp edi, 5 - je .LBB6_79 -# %bb.17: + je .LBB6_97 +# %bb.20: cmp edi, 6 - jne .LBB6_123 -# %bb.18: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB6_153 +# %bb.21: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_22 -# %bb.19: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rdx] - add rdx, 4 - cmp ecx, dword ptr [rsi] - lea rsi, [rsi + 4] - sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB6_20 -# %bb.21: - add r14, 1 -.LBB6_22: - sar r15, 5 - cmp r11, 32 - jl .LBB6_26 + je .LBB6_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_26 # %bb.23: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 .LBB6_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill + lea rcx, [r9 + rax] + mov ebx, dword ptr [rdx + 4*rax] + cmp ebx, dword ptr [rsi + 4*rax] + sbb r11d, r11d + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl + add rax, 1 + add r10, -4 + cmp r8, rax + jne .LBB6_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB6_26: + sub r13, r8 + je .LBB6_153 +# %bb.27: + add r15, 1 +.LBB6_28: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_32 +# %bb.29: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB6_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] mov eax, dword ptr [rsi + 8] seta r13b @@ -32166,7 +33108,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 mov eax, dword ptr [rsi + 28] cmp eax, dword ptr [rdx + 28] mov eax, dword ptr [rsi + 32] - seta r15b + seta r14b cmp eax, dword ptr [rdx + 32] seta byte ptr [rsp + 9] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] @@ -32180,7 +33122,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 mov eax, dword ptr [rsi + 48] seta r9b cmp eax, dword ptr [rdx + 48] - seta r12b + seta r15b mov eax, dword ptr [rsi + 52] cmp eax, dword ptr [rdx + 52] mov eax, dword ptr [rsi + 56] @@ -32196,7 +33138,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 cmp r11d, dword ptr [rdx + 64] seta byte ptr [rsp + 10] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 68] - seta r14b + seta r12b cmp eax, dword ptr [rdx + 72] mov eax, dword ptr [rsi + 76] seta byte ptr [rsp + 6] # 1-byte Folded Spill @@ -32240,11 +33182,11 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 cmp eax, dword ptr [rdx + 124] seta al add r13b, r13b - add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, r13b @@ -32264,23 +33206,23 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r12b, 4 - or r12b, r9b + shl r15b, 4 + or r15b, r9b movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload shl bl, 5 - or bl, r12b + or bl, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload shl r8b, 6 shl r10b, 7 or r10b, r8b - or r15b, cl + or r14b, cl or r10b, bl - add r14b, r14b - add r14b, byte ptr [rsp + 10] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 10] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 6] # 1-byte Folded Reload shl cl, 2 - or cl, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or cl, r12b shl r11b, 3 or r11b, cl movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload @@ -32290,12 +33232,12 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 5 or cl, bl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx r8d, byte ptr [rsp + 13] # 1-byte Folded Reload shl r8b, 6 shl dil, 7 or dil, r8b - mov byte ptr [r14 + 1], r10b + mov byte ptr [r15 + 1], r10b or dil, cl movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload add cl, cl @@ -32319,31 +33261,30 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, 7 or al, bl or al, cl - mov byte ptr [r14 + 2], dil - mov byte ptr [r14 + 3], al + mov byte ptr [r15 + 2], dil + mov byte ptr [r15 + 3], al add rdx, 128 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_24 -# %bb.25: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_26: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.27: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_30 +# %bb.31: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_32: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB6_28: # =>This Inner Loop Header: Depth=1 +.LBB6_34: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rdx + 4*rcx] cmp edi, dword ptr [rsi + 4*rcx] sbb edi, edi mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -32351,74 +33292,89 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_28 - jmp .LBB6_123 -.LBB6_29: + cmp r13, r8 + jne .LBB6_34 + jmp .LBB6_153 +.LBB6_35: cmp edi, 8 - jle .LBB6_30 -# %bb.43: + jle .LBB6_36 +# %bb.52: cmp edi, 9 - je .LBB6_101 -# %bb.44: + je .LBB6_125 +# %bb.53: cmp edi, 11 - je .LBB6_112 -# %bb.45: + je .LBB6_139 +# %bb.54: cmp edi, 12 - jne .LBB6_123 -# %bb.46: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB6_153 +# %bb.55: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_50 -# %bb.47: - movsxd rax, r9d + je .LBB6_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_60 +# %bb.57: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_48: # =>This Inner Loop Header: Depth=1 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - ucomisd xmm0, qword ptr [rdx] - seta r10b - add rdx, 8 - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_58: # =>This Inner Loop Header: Depth=1 + movsd xmm0, qword ptr [rsi + 8*rax] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 8*rax] + lea rcx, [r9 + rax] + seta r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_48 -# %bb.49: - add r14, 1 -.LBB6_50: - sar r15, 5 - cmp r11, 32 - jl .LBB6_54 -# %bb.51: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB6_58 +# %bb.59: + sub rsi, r10 + sub rdx, r10 +.LBB6_60: + sub r13, r8 + je .LBB6_153 +# %bb.61: + add r15, 1 +.LBB6_62: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_66 +# %bb.63: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx] seta byte ptr [rsp + 4] # 1-byte Folded Spill @@ -32442,7 +33398,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 seta al movsd xmm0, qword ptr [rsi + 56] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 56] - seta r15b + seta r14b movsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 64] seta byte ptr [rsp + 8] # 1-byte Folded Spill @@ -32457,7 +33413,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 seta r11b movsd xmm0, qword ptr [rsi + 96] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 96] - seta r14b + seta r15b movsd xmm0, qword ptr [rsi + 104] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 104] seta byte ptr [rsp + 5] # 1-byte Folded Spill @@ -32519,8 +33475,8 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 add cl, cl add cl, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 - shl r15b, 7 - or r15b, al + shl r14b, 7 + or r14b, al movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 2 or al, cl @@ -32541,26 +33497,26 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 or al, cl @@ -32568,12 +33524,12 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al @@ -32599,24 +33555,23 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB6_52 -# %bb.53: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB6_54: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.55: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB6_64 +# %bb.65: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB6_66: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB6_56: # =>This Inner Loop Header: Depth=1 +.LBB6_68: # =>This Inner Loop Header: Depth=1 movsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 8*rcx] lea r8, [rcx + 1] @@ -32624,7 +33579,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -32632,72 +33587,93 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_56 - jmp .LBB6_123 + cmp r13, r8 + jne .LBB6_68 + jmp .LBB6_153 .LBB6_2: cmp edi, 2 - je .LBB6_57 + mov r8, r15 + je .LBB6_69 # %bb.3: cmp edi, 3 - jne .LBB6_123 + jne .LBB6_153 # %bb.4: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_8 + je .LBB6_11 # %bb.5: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setg r10b - neg r10b - lea rdi, [rax + 7] + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 test rax, rax - cmovns rdi, rax + jle .LBB6_9 +# %bb.6: + movsxd rbx, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB6_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setg r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r15, r8 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB6_6 -# %bb.7: - add r14, 1 -.LBB6_8: - sar r15, 5 - cmp r11, 32 - jl .LBB6_12 -# %bb.9: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov byte ptr [r8 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB6_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB6_9: + sub r13, rax + je .LBB6_153 +# %bb.10: + add r15, 1 +.LBB6_11: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_15 +# %bb.12: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setg cl movzx eax, byte ptr [rsi + 2] @@ -32717,7 +33693,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 setg byte ptr [rsp + 4] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setg r15b + setg r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] setg byte ptr [rsp + 7] # 1-byte Folded Spill @@ -32732,7 +33708,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 setg r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setg r14b + setg r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] setg byte ptr [rsp + 5] # 1-byte Folded Spill @@ -32792,12 +33768,12 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 cmp al, byte ptr [rdx + 31] setg r8b add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload mov eax, ecx movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, al @@ -32819,26 +33795,26 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 6] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 13] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 4 or al, cl @@ -32846,12 +33822,12 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al @@ -32877,24 +33853,23 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_10 -# %bb.11: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_12: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.13: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_13 +# %bb.14: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_15: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB6_14: # =>This Inner Loop Header: Depth=1 +.LBB6_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -32902,7 +33877,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -32910,71 +33885,86 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_14 - jmp .LBB6_123 -.LBB6_30: + cmp r13, r8 + jne .LBB6_17 + jmp .LBB6_153 +.LBB6_36: cmp edi, 7 - je .LBB6_90 -# %bb.31: + je .LBB6_111 +# %bb.37: cmp edi, 8 - jne .LBB6_123 -# %bb.32: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB6_153 +# %bb.38: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_36 -# %bb.33: - movsxd rax, r9d + je .LBB6_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rdx] - add rdx, 8 - cmp rcx, qword ptr [rsi] - lea rsi, [rsi + 8] - sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB6_41: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rdx + 8*rax] + cmp rbx, qword ptr [rsi + 8*rax] + sbb r11d, r11d + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_34 -# %bb.35: - add r14, 1 -.LBB6_36: - sar r15, 5 - cmp r11, 32 - jl .LBB6_40 -# %bb.37: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB6_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB6_43: + sub r13, r8 + je .LBB6_153 +# %bb.44: + add r15, 1 +.LBB6_45: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_49 +# %bb.46: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] mov rax, qword ptr [rsi + 16] seta r13b @@ -32995,7 +33985,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 mov rax, qword ptr [rsi + 56] cmp rax, qword ptr [rdx + 56] mov rax, qword ptr [rsi + 64] - seta r15b + seta r14b cmp rax, qword ptr [rdx + 64] seta byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] @@ -33009,7 +33999,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 mov rax, qword ptr [rsi + 96] seta r9b cmp rax, qword ptr [rdx + 96] - seta r12b + seta r15b mov rax, qword ptr [rsi + 104] cmp rax, qword ptr [rdx + 104] mov rax, qword ptr [rsi + 112] @@ -33025,7 +34015,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 cmp r11, qword ptr [rdx + 128] seta byte ptr [rsp + 10] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 136] - seta r14b + seta r12b cmp rax, qword ptr [rdx + 144] mov rax, qword ptr [rsi + 152] seta byte ptr [rsp + 6] # 1-byte Folded Spill @@ -33069,11 +34059,11 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 cmp rax, qword ptr [rdx + 248] seta al add r13b, r13b - add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, r13b @@ -33093,23 +34083,23 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r12b, 4 - or r12b, r9b + shl r15b, 4 + or r15b, r9b movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload shl bl, 5 - or bl, r12b + or bl, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload shl r8b, 6 shl r10b, 7 or r10b, r8b - or r15b, cl + or r14b, cl or r10b, bl - add r14b, r14b - add r14b, byte ptr [rsp + 10] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 10] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 6] # 1-byte Folded Reload shl cl, 2 - or cl, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or cl, r12b shl r11b, 3 or r11b, cl movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload @@ -33119,12 +34109,12 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 5 or cl, bl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx r8d, byte ptr [rsp + 13] # 1-byte Folded Reload shl r8b, 6 shl dil, 7 or dil, r8b - mov byte ptr [r14 + 1], r10b + mov byte ptr [r15 + 1], r10b or dil, cl movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload add cl, cl @@ -33148,31 +34138,30 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, 7 or al, bl or al, cl - mov byte ptr [r14 + 2], dil - mov byte ptr [r14 + 3], al + mov byte ptr [r15 + 2], dil + mov byte ptr [r15 + 3], al add rdx, 256 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_38 -# %bb.39: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_40: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.41: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_47 +# %bb.48: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_49: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB6_42: # =>This Inner Loop Header: Depth=1 +.LBB6_51: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rdx + 8*rcx] cmp rdi, qword ptr [rsi + 8*rcx] sbb edi, edi mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -33180,65 +34169,80 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_42 - jmp .LBB6_123 -.LBB6_68: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_51 + jmp .LBB6_153 +.LBB6_83: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_72 -# %bb.69: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rdx] - add rdx, 2 - cmp cx, word ptr [rsi] - lea rsi, [rsi + 2] - sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil + je .LBB6_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax + .p2align 4, 0x90 +.LBB6_86: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rdx + 2*rax] + cmp bx, word ptr [rsi + 2*rax] + sbb r11d, r11d + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_70 -# %bb.71: - add r14, 1 -.LBB6_72: - sar r15, 5 - cmp r11, 32 - jl .LBB6_76 -# %bb.73: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB6_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB6_88: + sub r13, r8 + je .LBB6_153 +# %bb.89: + add r15, 1 +.LBB6_90: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_94 +# %bb.91: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] movzx eax, word ptr [rsi + 4] seta r13b @@ -33259,7 +34263,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx eax, word ptr [rsi + 14] cmp ax, word ptr [rdx + 14] movzx eax, word ptr [rsi + 16] - seta r15b + seta r14b cmp ax, word ptr [rdx + 16] seta byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] @@ -33273,7 +34277,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx eax, word ptr [rsi + 24] seta r9b cmp ax, word ptr [rdx + 24] - seta r12b + seta r15b movzx eax, word ptr [rsi + 26] cmp ax, word ptr [rdx + 26] movzx eax, word ptr [rsi + 28] @@ -33289,7 +34293,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 cmp r11w, word ptr [rdx + 32] seta byte ptr [rsp + 10] # 1-byte Folded Spill cmp cx, word ptr [rdx + 34] - seta r14b + seta r12b cmp ax, word ptr [rdx + 36] movzx eax, word ptr [rsi + 38] seta byte ptr [rsp + 6] # 1-byte Folded Spill @@ -33333,11 +34337,11 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 cmp ax, word ptr [rdx + 62] seta al add r13b, r13b - add r13b, byte ptr [rsp + 40] # 1-byte Folded Reload + add r13b, byte ptr [rsp + 48] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, r13b @@ -33357,23 +34361,23 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 5 or cl, r8b - shl r12b, 4 - or r12b, r9b + shl r15b, 4 + or r15b, r9b movzx ebx, byte ptr [rsp + 5] # 1-byte Folded Reload shl bl, 5 - or bl, r12b + or bl, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload shl r8b, 6 shl r10b, 7 or r10b, r8b - or r15b, cl + or r14b, cl or r10b, bl - add r14b, r14b - add r14b, byte ptr [rsp + 10] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 10] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 6] # 1-byte Folded Reload shl cl, 2 - or cl, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or cl, r12b shl r11b, 3 or r11b, cl movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload @@ -33383,12 +34387,12 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 5 or cl, bl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx r8d, byte ptr [rsp + 13] # 1-byte Folded Reload shl r8b, 6 shl dil, 7 or dil, r8b - mov byte ptr [r14 + 1], r10b + mov byte ptr [r15 + 1], r10b or dil, cl movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload add cl, cl @@ -33412,31 +34416,30 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, 7 or al, bl or al, cl - mov byte ptr [r14 + 2], dil - mov byte ptr [r14 + 3], al + mov byte ptr [r15 + 2], dil + mov byte ptr [r15 + 3], al add rdx, 64 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_74 -# %bb.75: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_76: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.77: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_92 +# %bb.93: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_94: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB6_78: # =>This Inner Loop Header: Depth=1 +.LBB6_96: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rdx + 2*rcx] cmp di, word ptr [rsi + 2*rcx] sbb edi, edi mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -33444,68 +34447,83 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_78 - jmp .LBB6_123 -.LBB6_79: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_96 + jmp .LBB6_153 +.LBB6_97: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_83 -# %bb.80: - movsxd rax, r9d + je .LBB6_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setg r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setg r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_81 -# %bb.82: - add r14, 1 -.LBB6_83: - sar r15, 5 - cmp r11, 32 - jl .LBB6_87 -# %bb.84: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB6_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB6_102: + sub r13, r8 + je .LBB6_153 +# %bb.103: + add r15, 1 +.LBB6_104: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_108 +# %bb.105: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] setg byte ptr [rsp + 20] # 1-byte Folded Spill @@ -33529,7 +34547,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 setg byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setg r8b + setg dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setg r11b @@ -33569,7 +34587,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 setg byte ptr [rsp + 11] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setg byte ptr [rsp + 12] # 1-byte Folded Spill + setg byte ptr [rsp + 14] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setg r9b @@ -33578,10 +34596,10 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 setg byte ptr [rsp + 19] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setg byte ptr [rsp + 13] # 1-byte Folded Spill + setg byte ptr [rsp + 12] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setg byte ptr [rsp + 14] # 1-byte Folded Spill + setg byte ptr [rsp + 13] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] setg byte ptr [rsp + 15] # 1-byte Folded Spill @@ -33596,10 +34614,10 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 setg byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] - setg dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setg r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -33608,34 +34626,34 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -33648,22 +34666,23 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -33680,27 +34699,26 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 64 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB6_85 -# %bb.86: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB6_87: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.88: - sub r11, r15 + jne .LBB6_106 +# %bb.107: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB6_108: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB6_89: # =>This Inner Loop Header: Depth=1 +.LBB6_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -33708,7 +34726,7 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -33716,68 +34734,83 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_89 - jmp .LBB6_123 -.LBB6_101: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_110 + jmp .LBB6_153 +.LBB6_125: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_105 -# %bb.102: - movsxd rax, r9d + je .LBB6_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setg r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setg r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_103 -# %bb.104: - add r14, 1 -.LBB6_105: - sar r15, 5 - cmp r11, 32 - jl .LBB6_109 -# %bb.106: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB6_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB6_130: + sub r13, r8 + je .LBB6_153 +# %bb.131: + add r15, 1 +.LBB6_132: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_136 +# %bb.133: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB6_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill + setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 40] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] setg byte ptr [rsp + 20] # 1-byte Folded Spill @@ -33801,422 +34834,154 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 setg byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setg r8b + setg dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setg r11b mov rax, qword ptr [rsi + 88] - cmp rax, qword ptr [rdx + 88] - setg r15b - mov rax, qword ptr [rsi + 96] - cmp rax, qword ptr [rdx + 96] - setg byte ptr [rsp + 5] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 104] - cmp rax, qword ptr [rdx + 104] - setg byte ptr [rsp + 6] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 112] - cmp rax, qword ptr [rdx + 112] - setg byte ptr [rsp + 7] # 1-byte Folded Spill - mov rax, qword ptr [rsi + 120] - cmp rax, qword ptr [rdx + 120] - setg bl - mov rax, qword ptr [rsi + 128] - mov rcx, qword ptr [rsi + 136] - cmp rax, qword ptr [rdx + 128] - mov rax, qword ptr [rsi + 144] - setg byte ptr [rsp + 10] # 1-byte Folded Spill - cmp rcx, qword ptr [rdx + 136] - mov rcx, qword ptr [rsi + 152] - setg r10b - cmp rax, qword ptr [rdx + 144] - mov rax, qword ptr [rsi + 160] - setg r14b - cmp rcx, qword ptr [rdx + 152] - mov rcx, qword ptr [rsi + 168] - setg r12b - cmp rax, qword ptr [rdx + 160] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp rcx, qword ptr [rdx + 168] - mov rax, qword ptr [rsi + 176] - setg byte ptr [rsp + 11] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 176] - mov rax, qword ptr [rsi + 184] - setg byte ptr [rsp + 12] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 184] - mov rax, qword ptr [rsi + 192] - setg r9b - cmp rax, qword ptr [rdx + 192] - mov rax, qword ptr [rsi + 200] - setg byte ptr [rsp + 19] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 200] - mov rax, qword ptr [rsi + 208] - setg byte ptr [rsp + 13] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 208] - mov rax, qword ptr [rsi + 216] - setg byte ptr [rsp + 14] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 216] - mov rax, qword ptr [rsi + 224] - setg byte ptr [rsp + 15] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 224] - mov rax, qword ptr [rsi + 232] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 232] - mov rax, qword ptr [rsi + 240] - setg byte ptr [rsp + 18] # 1-byte Folded Spill - cmp rax, qword ptr [rdx + 240] - mov rax, qword ptr [rsi + 248] - setg byte ptr [rsp + 17] # 1-byte Folded Spill - add rsi, 256 - cmp rax, qword ptr [rdx + 248] - setg dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload - shl al, 6 - shl r13b, 7 - or r13b, al - movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload - shl al, 2 - or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload - shl cl, 3 - or cl, al - mov eax, ecx - shl r11b, 2 - or r11b, r8b - movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload - shl cl, 4 - or cl, al - mov r8d, ecx - shl r15b, 3 - or r15b, r11b - movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload - shl cl, 5 - or cl, r8b - movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload - shl al, 4 - or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload - shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 - shl bl, 7 - or bl, r8b - or r13b, cl - or bl, al - add r10b, r10b - add r10b, byte ptr [rsp + 10] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r10b - shl r12b, 3 - or r12b, r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 4 - or al, r12b - mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload - shl cl, 6 - shl r9b, 7 - or r9b, cl - mov byte ptr [r14 + 1], bl - or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 19] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload - shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload - shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil - add rdx, 256 - add r14, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB6_107 -# %bb.108: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB6_109: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.110: - sub r11, r15 - xor ecx, ecx - .p2align 4, 0x90 -.LBB6_111: # =>This Inner Loop Header: Depth=1 - lea r8, [rcx + 1] - mov rdi, qword ptr [rsi + 8*rcx] - cmp rdi, qword ptr [rdx + 8*rcx] - setg bl - neg bl - mov rdi, rcx - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor bl, r9b - and cl, 7 - mov al, 1 - # kill: def $cl killed $cl killed $rcx - shl al, cl - and al, bl - xor al, r9b - mov byte ptr [r14 + rdi], al - mov rcx, r8 - cmp r11, r8 - jne .LBB6_111 - jmp .LBB6_123 -.LBB6_112: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB6_116 -# %bb.113: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_114: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - ucomiss xmm0, dword ptr [rdx] - seta r10b - add rdx, 4 - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB6_114 -# %bb.115: - add r14, 1 -.LBB6_116: - sar r15, 5 - cmp r11, 32 - jl .LBB6_120 -# %bb.117: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB6_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx] - seta byte ptr [rsp + 4] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 4] - seta cl - movss xmm0, dword ptr [rsi + 8] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 8] - seta byte ptr [rsp + 6] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 12] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 12] - seta byte ptr [rsp + 21] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 16] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 16] - seta byte ptr [rsp + 22] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 20] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 20] - seta byte ptr [rsp + 23] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 24] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 24] - seta al - movss xmm0, dword ptr [rsi + 28] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 28] - seta r15b - movss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 32] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 36] - seta dil - movss xmm0, dword ptr [rsi + 40] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 40] - seta r10b - movss xmm0, dword ptr [rsi + 44] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 44] - seta r11b - movss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 48] - seta r14b - movss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 52] - seta byte ptr [rsp + 5] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 56] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 56] - seta byte ptr [rsp + 7] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 60] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 60] - seta bl - movss xmm0, dword ptr [rsi + 64] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 64] - seta byte ptr [rsp + 14] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 68] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 68] - seta r12b - movss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 72] - seta r13b - movss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 76] - seta byte ptr [rsp + 9] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 80] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 80] - seta byte ptr [rsp + 10] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 84] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 84] - seta byte ptr [rsp + 11] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 88] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 88] - seta byte ptr [rsp + 12] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 92] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 92] - seta r9b - movss xmm0, dword ptr [rsi + 96] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 96] - seta byte ptr [rsp + 20] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 100] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 100] - seta byte ptr [rsp + 13] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 104] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 104] - seta byte ptr [rsp + 15] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 108] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 108] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 112] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 112] - seta byte ptr [rsp + 18] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 116] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 116] - seta byte ptr [rsp + 19] # 1-byte Folded Spill - movss xmm0, dword ptr [rsi + 120] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 120] - movss xmm0, dword ptr [rsi + 124] # xmm0 = mem[0],zero,zero,zero - seta byte ptr [rsp + 17] # 1-byte Folded Spill - sub rsi, -128 - ucomiss xmm0, dword ptr [rdx + 124] - seta r8b - add cl, cl - add cl, byte ptr [rsp + 4] # 1-byte Folded Reload + cmp rax, qword ptr [rdx + 88] + setg r15b + mov rax, qword ptr [rsi + 96] + cmp rax, qword ptr [rdx + 96] + setg byte ptr [rsp + 5] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 104] + cmp rax, qword ptr [rdx + 104] + setg byte ptr [rsp + 6] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 112] + cmp rax, qword ptr [rdx + 112] + setg byte ptr [rsp + 7] # 1-byte Folded Spill + mov rax, qword ptr [rsi + 120] + cmp rax, qword ptr [rdx + 120] + setg bl + mov rax, qword ptr [rsi + 128] + mov rcx, qword ptr [rsi + 136] + cmp rax, qword ptr [rdx + 128] + mov rax, qword ptr [rsi + 144] + setg byte ptr [rsp + 10] # 1-byte Folded Spill + cmp rcx, qword ptr [rdx + 136] + mov rcx, qword ptr [rsi + 152] + setg r10b + cmp rax, qword ptr [rdx + 144] + mov rax, qword ptr [rsi + 160] + setg r14b + cmp rcx, qword ptr [rdx + 152] + mov rcx, qword ptr [rsi + 168] + setg r12b + cmp rax, qword ptr [rdx + 160] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp rcx, qword ptr [rdx + 168] + mov rax, qword ptr [rsi + 176] + setg byte ptr [rsp + 11] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 176] + mov rax, qword ptr [rsi + 184] + setg byte ptr [rsp + 14] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 184] + mov rax, qword ptr [rsi + 192] + setg r9b + cmp rax, qword ptr [rdx + 192] + mov rax, qword ptr [rsi + 200] + setg byte ptr [rsp + 19] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 200] + mov rax, qword ptr [rsi + 208] + setg byte ptr [rsp + 12] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 208] + mov rax, qword ptr [rsi + 216] + setg byte ptr [rsp + 13] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 216] + mov rax, qword ptr [rsi + 224] + setg byte ptr [rsp + 15] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 224] + mov rax, qword ptr [rsi + 232] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 232] + mov rax, qword ptr [rsi + 240] + setg byte ptr [rsp + 18] # 1-byte Folded Spill + cmp rax, qword ptr [rdx + 240] + mov rax, qword ptr [rsi + 248] + setg byte ptr [rsp + 17] # 1-byte Folded Spill + add rsi, 256 + cmp rax, qword ptr [rdx + 248] + setg r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 - shl r15b, 7 - or r15b, al - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl r13b, 7 + or r13b, al + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl add dil, dil - add dil, byte ptr [rsp + 8] # 1-byte Folded Reload + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx - shl r10b, 2 - or r10b, dil + shl r11b, 2 + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al mov edi, ecx - shl r11b, 3 - or r11b, r10b + shl r15b, 3 + or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + shl al, 4 + or al, r15b + mov edi, eax + movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, dil movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r13b, cl or bl, al - add r12b, r12b - add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload - shl r13b, 2 - or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload - shl al, 3 - or al, r13b - mov ecx, eax - movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload + add r10b, r10b + add r10b, byte ptr [rsp + 10] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r12b, 3 + or r12b, r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 4 - or al, cl + or al, r12b mov ecx, eax movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 20] # 1-byte Folded Reload + add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 5 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload @@ -34224,32 +34989,31 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b - add rdx, 128 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB6_118 -# %bb.119: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB6_120: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.121: - sub r11, r15 + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b + add rdx, 256 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB6_134 +# %bb.135: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB6_136: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.137: xor ecx, ecx .p2align 4, 0x90 -.LBB6_122: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, dword ptr [rdx + 4*rcx] +.LBB6_138: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] - seta bl + mov rdi, qword ptr [rsi + 8*rcx] + cmp rdi, qword ptr [rdx + 8*rcx] + setg bl neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -34257,535 +35021,282 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_122 - jmp .LBB6_123 -.LBB6_57: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB6_138 + jmp .LBB6_153 +.LBB6_139: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB6_61 -# %bb.58: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rdx] - add rdx, 1 - cmp cl, byte ptr [rsi] - lea rsi, [rsi + 1] - sbb r10d, r10d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB6_59 -# %bb.60: - add r14, 1 -.LBB6_61: - sar r15, 5 - cmp r11, 32 - jl .LBB6_65 -# %bb.62: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + je .LBB6_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_144 +# %bb.141: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB6_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill - movzx eax, byte ptr [rsi] - movzx ecx, byte ptr [rsi + 1] - cmp al, byte ptr [rdx] - seta byte ptr [rsp + 4] # 1-byte Folded Spill - cmp cl, byte ptr [rdx + 1] - seta r13b - movzx eax, byte ptr [rsi + 2] - cmp al, byte ptr [rdx + 2] - movzx eax, byte ptr [rsi + 3] - seta byte ptr [rsp + 20] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 3] - seta byte ptr [rsp + 22] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 4] - cmp al, byte ptr [rdx + 4] - movzx eax, byte ptr [rsi + 5] - seta byte ptr [rsp + 21] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 5] - seta byte ptr [rsp + 23] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 6] - cmp al, byte ptr [rdx + 6] - movzx eax, byte ptr [rsi + 7] - seta byte ptr [rsp + 40] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 7] - seta r15b - movzx eax, byte ptr [rsi + 8] - cmp al, byte ptr [rdx + 8] - movzx eax, byte ptr [rsi + 9] - seta byte ptr [rsp + 7] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 9] - seta cl - movzx eax, byte ptr [rsi + 10] - cmp al, byte ptr [rdx + 10] - movzx eax, byte ptr [rsi + 11] - seta r9b - cmp al, byte ptr [rdx + 11] +.LBB6_142: # =>This Inner Loop Header: Depth=1 + movss xmm0, dword ptr [rsi + 4*rax] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 4*rax] + lea rcx, [r9 + rax] seta r11b - movzx eax, byte ptr [rsi + 12] - cmp al, byte ptr [rdx + 12] - movzx eax, byte ptr [rsi + 13] - seta r10b - cmp al, byte ptr [rdx + 13] - seta byte ptr [rsp + 6] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 14] - cmp al, byte ptr [rdx + 14] - movzx eax, byte ptr [rsi + 15] - seta byte ptr [rsp + 5] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 15] - seta bl - movzx eax, byte ptr [rsi + 16] - cmp al, byte ptr [rdx + 16] - movzx eax, byte ptr [rsi + 17] - seta byte ptr [rsp + 12] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 17] - seta r12b - movzx eax, byte ptr [rsi + 18] - cmp al, byte ptr [rdx + 18] - movzx eax, byte ptr [rsi + 19] - seta r14b - cmp al, byte ptr [rdx + 19] - seta byte ptr [rsp + 9] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 20] - cmp al, byte ptr [rdx + 20] - movzx eax, byte ptr [rsi + 21] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 21] - seta byte ptr [rsp + 11] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 22] - cmp al, byte ptr [rdx + 22] - movzx eax, byte ptr [rsi + 23] - seta byte ptr [rsp + 10] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 23] - seta r8b - movzx eax, byte ptr [rsi + 24] - cmp al, byte ptr [rdx + 24] - movzx eax, byte ptr [rsi + 25] - seta byte ptr [rsp + 18] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 25] - seta byte ptr [rsp + 14] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 26] - cmp al, byte ptr [rdx + 26] - movzx eax, byte ptr [rsi + 27] - seta byte ptr [rsp + 13] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 27] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 28] - cmp al, byte ptr [rdx + 28] - movzx eax, byte ptr [rsi + 29] - seta byte ptr [rsp + 15] # 1-byte Folded Spill - cmp al, byte ptr [rdx + 29] - seta byte ptr [rsp + 17] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 30] - cmp al, byte ptr [rdx + 30] - seta byte ptr [rsp + 19] # 1-byte Folded Spill - movzx eax, byte ptr [rsi + 31] - add rsi, 32 - cmp al, byte ptr [rdx + 31] - seta dil - add r13b, r13b - add r13b, byte ptr [rsp + 4] # 1-byte Folded Reload - mov eax, r13d - movzx r13d, byte ptr [rsp + 40] # 1-byte Folded Reload - shl r13b, 6 - shl r15b, 7 - or r15b, r13b - movzx r13d, byte ptr [rsp + 20] # 1-byte Folded Reload - shl r13b, 2 - or r13b, al - mov eax, r13d - add cl, cl - add cl, byte ptr [rsp + 7] # 1-byte Folded Reload - movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload - shl r13b, 3 - or r13b, al - shl r9b, 2 - or r9b, cl - movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload - shl cl, 4 - or cl, r13b - mov r13d, ecx - shl r11b, 3 - or r11b, r9b - movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload - shl cl, 5 - or cl, r13b - shl r10b, 4 - or r10b, r11b - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload - shl al, 5 - or al, r10b - movzx r9d, byte ptr [rsp + 5] # 1-byte Folded Reload - shl r9b, 6 - shl bl, 7 - or bl, r9b - or r15b, cl - or bl, al - add r12b, r12b - add r12b, byte ptr [rsp + 12] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r12b - movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 4 - or cl, al - movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov byte ptr [r14], r15b - movzx ecx, byte ptr [rsp + 10] # 1-byte Folded Reload - shl cl, 6 - shl r8b, 7 - or r8b, cl - mov byte ptr [r14 + 1], bl - or r8b, al - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 18] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload - shl cl, 2 - or cl, al - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 3 - or al, cl - movzx ecx, byte ptr [rsp + 15] # 1-byte Folded Reload - shl cl, 4 - or cl, al - mov eax, ecx - movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload - shl al, 6 - shl dil, 7 - or dil, al - or dil, cl - mov byte ptr [r14 + 2], r8b - mov byte ptr [r14 + 3], dil - add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB6_63 -# %bb.64: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB6_65: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.66: - sub r11, r15 - xor ecx, ecx - .p2align 4, 0x90 -.LBB6_67: # =>This Inner Loop Header: Depth=1 - lea r8, [rcx + 1] - movzx ebx, byte ptr [rdx + rcx] - cmp bl, byte ptr [rsi + rcx] - sbb edi, edi - mov rbx, rcx - shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] - xor dil, r9b - and cl, 7 - mov al, 1 - # kill: def $cl killed $cl killed $rcx - shl al, cl - and al, dil - xor al, r9b - mov byte ptr [r14 + rbx], al - mov rcx, r8 - cmp r11, r8 - jne .LBB6_67 - jmp .LBB6_123 -.LBB6_90: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB6_94 -# %bb.91: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB6_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setg r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB6_92 -# %bb.93: - add r14, 1 -.LBB6_94: - sar r15, 5 - cmp r11, 32 - jl .LBB6_98 -# %bb.95: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB6_142 +# %bb.143: + sub rsi, r10 + sub rdx, r10 +.LBB6_144: + sub r13, r8 + je .LBB6_153 +# %bb.145: + add r15, 1 +.LBB6_146: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_150 +# %bb.147: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB6_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill - mov eax, dword ptr [rsi] - mov ecx, dword ptr [rsi + 4] - cmp eax, dword ptr [rdx] - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp ecx, dword ptr [rdx + 4] - setg byte ptr [rsp + 32] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 8] - cmp eax, dword ptr [rdx + 8] - setg byte ptr [rsp + 20] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 12] - cmp eax, dword ptr [rdx + 12] - setg byte ptr [rsp + 21] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 16] - cmp eax, dword ptr [rdx + 16] - setg byte ptr [rsp + 22] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 20] - cmp eax, dword ptr [rdx + 20] - setg byte ptr [rsp + 23] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 24] - cmp eax, dword ptr [rdx + 24] - setg byte ptr [rsp + 4] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 28] - cmp eax, dword ptr [rdx + 28] - setg r13b - mov eax, dword ptr [rsi + 32] - cmp eax, dword ptr [rdx + 32] - setg byte ptr [rsp + 9] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 36] - cmp eax, dword ptr [rdx + 36] - setg r8b - mov eax, dword ptr [rsi + 40] - cmp eax, dword ptr [rdx + 40] - setg r11b - mov eax, dword ptr [rsi + 44] - cmp eax, dword ptr [rdx + 44] - setg r15b - mov eax, dword ptr [rsi + 48] - cmp eax, dword ptr [rdx + 48] - setg byte ptr [rsp + 5] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 52] - cmp eax, dword ptr [rdx + 52] - setg byte ptr [rsp + 6] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 56] - cmp eax, dword ptr [rdx + 56] - setg byte ptr [rsp + 7] # 1-byte Folded Spill - mov eax, dword ptr [rsi + 60] - cmp eax, dword ptr [rdx + 60] - setg bl - mov eax, dword ptr [rsi + 64] - mov ecx, dword ptr [rsi + 68] - cmp eax, dword ptr [rdx + 64] - mov eax, dword ptr [rsi + 72] - setg byte ptr [rsp + 10] # 1-byte Folded Spill - cmp ecx, dword ptr [rdx + 68] - mov ecx, dword ptr [rsi + 76] - setg r10b - cmp eax, dword ptr [rdx + 72] - mov eax, dword ptr [rsi + 80] - setg r14b - cmp ecx, dword ptr [rdx + 76] - mov ecx, dword ptr [rsi + 84] - setg r12b - cmp eax, dword ptr [rdx + 80] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp ecx, dword ptr [rdx + 84] - mov eax, dword ptr [rsi + 88] - setg byte ptr [rsp + 11] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 88] - mov eax, dword ptr [rsi + 92] - setg byte ptr [rsp + 12] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 92] - mov eax, dword ptr [rsi + 96] - setg r9b - cmp eax, dword ptr [rdx + 96] - mov eax, dword ptr [rsi + 100] - setg byte ptr [rsp + 19] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 100] - mov eax, dword ptr [rsi + 104] - setg byte ptr [rsp + 13] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 104] - mov eax, dword ptr [rsi + 108] - setg byte ptr [rsp + 14] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 108] - mov eax, dword ptr [rsi + 112] - setg byte ptr [rsp + 15] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 112] - mov eax, dword ptr [rsi + 116] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 116] - mov eax, dword ptr [rsi + 120] - setg byte ptr [rsp + 18] # 1-byte Folded Spill - cmp eax, dword ptr [rdx + 120] - mov eax, dword ptr [rsi + 124] - setg byte ptr [rsp + 17] # 1-byte Folded Spill +.LBB6_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill + movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx] + seta byte ptr [rsp + 4] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 4] + seta cl + movss xmm0, dword ptr [rsi + 8] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 8] + seta byte ptr [rsp + 6] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 12] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 12] + seta byte ptr [rsp + 21] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 16] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 16] + seta byte ptr [rsp + 22] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 20] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 20] + seta byte ptr [rsp + 23] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 24] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 24] + seta al + movss xmm0, dword ptr [rsi + 28] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 28] + seta r14b + movss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 32] + seta byte ptr [rsp + 8] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 36] + seta dil + movss xmm0, dword ptr [rsi + 40] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 40] + seta r10b + movss xmm0, dword ptr [rsi + 44] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 44] + seta r11b + movss xmm0, dword ptr [rsi + 48] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 48] + seta r15b + movss xmm0, dword ptr [rsi + 52] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 52] + seta byte ptr [rsp + 5] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 56] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 56] + seta byte ptr [rsp + 7] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 60] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 60] + seta bl + movss xmm0, dword ptr [rsi + 64] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 64] + seta byte ptr [rsp + 14] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 68] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 68] + seta r12b + movss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 72] + seta r13b + movss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 76] + seta byte ptr [rsp + 9] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 80] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 80] + seta byte ptr [rsp + 10] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 84] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 84] + seta byte ptr [rsp + 11] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 88] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 88] + seta byte ptr [rsp + 12] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 92] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 92] + seta r9b + movss xmm0, dword ptr [rsi + 96] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 96] + seta byte ptr [rsp + 20] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 100] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 100] + seta byte ptr [rsp + 13] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 104] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 104] + seta byte ptr [rsp + 15] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 108] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 108] + seta byte ptr [rsp + 16] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 112] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 112] + seta byte ptr [rsp + 18] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 116] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 116] + seta byte ptr [rsp + 19] # 1-byte Folded Spill + movss xmm0, dword ptr [rsi + 120] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 120] + movss xmm0, dword ptr [rsi + 124] # xmm0 = mem[0],zero,zero,zero + seta byte ptr [rsp + 17] # 1-byte Folded Spill sub rsi, -128 - cmp eax, dword ptr [rdx + 124] - setg dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload + ucomiss xmm0, dword ptr [rdx + 124] + seta r8b + add cl, cl + add cl, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 - shl r13b, 7 - or r13b, al - movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload + shl r14b, 7 + or r14b, al + movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 8] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx - shl r11b, 2 - or r11b, r8b + shl r10b, 2 + or r10b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx - shl r15b, 3 - or r15b, r11b + mov edi, ecx + shl r11b, 3 + or r11b, r10b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload - shl al, 4 - or al, r15b - mov r8d, eax - movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, r15b + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b - or r13b, cl + or bl, dil + or r14b, cl or bl, al - add r10b, r10b - add r10b, byte ptr [rsp + 10] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r10b - shl r12b, 3 - or r12b, r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + add r12b, r12b + add r12b, byte ptr [rsp + 14] # 1-byte Folded Reload + shl r13b, 2 + or r13b, r12b + movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload + shl al, 3 + or al, r13b + mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 - or al, r12b + or al, cl mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 19] # 1-byte Folded Reload + add al, byte ptr [rsp + 20] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload shl al, 5 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r14, 4 - add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB6_96 -# %bb.97: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB6_98: - shl r15, 5 - cmp r15, r11 - jge .LBB6_123 -# %bb.99: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB6_148 +# %bb.149: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB6_150: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.151: xor ecx, ecx .p2align 4, 0x90 -.LBB6_100: # =>This Inner Loop Header: Depth=1 +.LBB6_152: # =>This Inner Loop Header: Depth=1 + movss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 4*rcx] lea r8, [rcx + 1] - mov edi, dword ptr [rsi + 4*rcx] - cmp edi, dword ptr [rdx + 4*rcx] - setg bl + seta bl neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -34793,1080 +35304,909 @@ comparison_greater_arr_arr_sse4: # @comparison_greater_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB6_100 -.LBB6_123: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.Lfunc_end6: - .size comparison_greater_arr_arr_sse4, .Lfunc_end6-comparison_greater_arr_arr_sse4 - # -- End function - .section .rodata.cst16,"aM",@progbits,16 - .p2align 4 # -- Begin function comparison_greater_arr_scalar_sse4 -.LCPI7_0: - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI7_1: - .zero 16,252 -.LCPI7_2: - .zero 16,248 -.LCPI7_3: - .zero 16,240 -.LCPI7_4: - .zero 16,224 -.LCPI7_5: - .zero 16,192 -.LCPI7_6: - .zero 16,128 -.LCPI7_7: - .byte 0 # 0x0 - .byte 8 # 0x8 - .byte 1 # 0x1 - .byte 9 # 0x9 - .byte 2 # 0x2 - .byte 10 # 0xa - .byte 3 # 0x3 - .byte 11 # 0xb - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf -.LCPI7_8: - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .byte 1 # 0x1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI7_9: - .byte 4 # 0x4 - .byte 12 # 0xc - .byte 5 # 0x5 - .byte 13 # 0xd - .byte 6 # 0x6 - .byte 14 # 0xe - .byte 7 # 0x7 - .byte 15 # 0xf - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 - .zero 1 -.LCPI7_10: - .zero 16,1 -.LCPI7_11: - .zero 16,4 -.LCPI7_12: - .zero 16,8 -.LCPI7_13: - .zero 16,16 -.LCPI7_14: - .zero 16,32 -.LCPI7_15: - .zero 16,64 -.LCPI7_16: - .zero 16,255 - .text - .globl comparison_greater_arr_scalar_sse4 - .p2align 4, 0x90 - .type comparison_greater_arr_scalar_sse4,@function -comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 -# %bb.0: - push rbp - mov rbp, rsp - push r15 - push r14 - push r13 - push r12 - push rbx - and rsp, -16 - sub rsp, 336 - # kill: def $r9d killed $r9d def $r9 - mov r11, r8 - mov qword ptr [rsp], rcx # 8-byte Spill - cmp edi, 6 - jg .LBB7_26 -# %bb.1: - cmp edi, 3 - jle .LBB7_2 -# %bb.10: - cmp edi, 4 - je .LBB7_98 -# %bb.11: - cmp edi, 5 - je .LBB7_114 -# %bb.12: - cmp edi, 6 - jne .LBB7_202 -# %bb.13: - mov r13d, dword ptr [rdx] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB7_17 -# %bb.14: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_15: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rsi] - lea rsi, [rsi + 4] - sbb edx, edx - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r9 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r9 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_15 -# %bb.16: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_17: - sar r10, 5 - cmp r11, 32 - jl .LBB7_21 -# %bb.18: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - .p2align 4, 0x90 -.LBB7_19: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - seta byte ptr [rsp + 208] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - seta r10b - cmp dword ptr [rsi + 8], r13d - seta dil - cmp dword ptr [rsi + 12], r13d - seta byte ptr [rsp + 176] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - seta byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - seta byte ptr [rsp + 88] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - seta al - cmp dword ptr [rsi + 28], r13d - seta r14b - cmp dword ptr [rsi + 32], r13d - seta byte ptr [rsp + 128] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d - seta dl - cmp dword ptr [rsi + 40], r13d - seta r9b - cmp dword ptr [rsi + 44], r13d - seta r11b - cmp dword ptr [rsi + 48], r13d - seta bl - cmp dword ptr [rsi + 52], r13d - seta r12b - cmp dword ptr [rsi + 56], r13d - seta byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - seta cl - cmp dword ptr [rsi + 64], r13d - seta byte ptr [rsp + 72] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - seta byte ptr [rsp + 144] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - seta byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - seta byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - seta byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - seta byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - seta byte ptr [rsp + 64] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d - seta r15b - cmp dword ptr [rsi + 96], r13d - seta byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - seta byte ptr [rsp + 56] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - seta byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - seta byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d - seta byte ptr [rsp + 24] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d - seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - seta byte ptr [rsp + 8] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - seta r8b - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 6 - shl r14b, 7 - or r14b, al - shl dil, 2 - or dil, r10b - add dl, dl - add dl, byte ptr [rsp + 128] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov r10, qword ptr [rsp] # 8-byte Reload - shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx - shl r11b, 3 - or r11b, r9b - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - shl bl, 4 - or bl, r11b - shl r12b, 5 - or r12b, bl - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or r14b, dl - or cl, r12b - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - mov byte ptr [r10], r14b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r10 + 1], cl - or r15b, dl - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload - shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload - shl cl, 5 - or cl, dl - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl dl, 6 - shl r8b, 7 - or r8b, dl - or r8b, cl - mov byte ptr [r10 + 2], r15b - mov byte ptr [r10 + 3], r8b - add rsi, 128 - add r10, 4 - mov qword ptr [rsp], r10 # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB7_19 -# %bb.20: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 240] # 8-byte Reload -.LBB7_21: - shl r10, 5 - cmp r10, r11 - jge .LBB7_202 -# %bb.22: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB7_137 -# %bb.23: - xor r11d, r11d - jmp .LBB7_24 -.LBB7_26: - cmp edi, 8 - jle .LBB7_27 -# %bb.42: - cmp edi, 9 - je .LBB7_157 -# %bb.43: - cmp edi, 11 - je .LBB7_172 -# %bb.44: - cmp edi, 12 - jne .LBB7_202 -# %bb.45: - lea r14, [r11 + 31] - test r11, r11 - cmovns r14, r11 + cmp r13, r8 + jne .LBB6_152 + jmp .LBB6_153 +.LBB6_69: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero sub r9d, eax - je .LBB7_49 -# %bb.46: - movsxd rax, r9d - mov r10, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_47: # =>This Inner Loop Header: Depth=1 - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - add rsi, 8 - ucomisd xmm1, xmm0 - seta dl - neg dl - lea rdi, [rax + 7] + je .LBB6_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 test rax, rax - cmovns rdi, rax + jle .LBB6_74 +# %bb.71: + movsxd rbx, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r11d, r11d + xor r12d, r12d + .p2align 4, 0x90 +.LBB6_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rdx + r12] + cmp cl, byte ptr [rsi + r12] + sbb r10d, r10d + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r9d, byte ptr [r10 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r15, r8 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r10 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_47 -# %bb.48: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_49: - sar r14, 5 - cmp r11, 32 - jl .LBB7_53 -# %bb.50: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r14 # 8-byte Spill - mov qword ptr [rsp + 208], r14 # 8-byte Spill + shl eax, cl + xor r10b, r14b + and al, r10b + xor al, r14b + mov byte ptr [r8 + rdi], al + add r12, 1 + add rbx, 1 + add r11, -1 + cmp r9, r11 + jne .LBB6_72 +# %bb.73: + sub rsi, r11 + sub rdx, r11 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB6_74: + sub r13, rax + je .LBB6_153 +# %bb.75: + add r15, 1 +.LBB6_76: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_80 +# %bb.77: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_51: # =>This Inner Loop Header: Depth=1 - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - movsd xmm2, qword ptr [rsi + 8] # xmm2 = mem[0],zero - ucomisd xmm1, xmm0 - seta byte ptr [rsp + 24] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - seta bl - movsd xmm1, qword ptr [rsi + 16] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 24] # xmm1 = mem[0],zero +.LBB6_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill + movzx eax, byte ptr [rsi] + movzx ecx, byte ptr [rsi + 1] + cmp al, byte ptr [rdx] + seta byte ptr [rsp + 4] # 1-byte Folded Spill + cmp cl, byte ptr [rdx + 1] seta r13b - ucomisd xmm1, xmm0 - seta r12b - movsd xmm1, qword ptr [rsi + 32] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 40] # xmm1 = mem[0],zero - seta byte ptr [rsp + 80] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - seta byte ptr [rsp + 96] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 48] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 56] # xmm1 = mem[0],zero - seta byte ptr [rsp + 88] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - seta byte ptr [rsp + 64] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 64] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 72] # xmm1 = mem[0],zero - seta byte ptr [rsp + 16] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - seta al - movsd xmm1, qword ptr [rsi + 80] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 88] # xmm1 = mem[0],zero - seta byte ptr [rsp + 56] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - seta byte ptr [rsp + 32] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 96] # xmm1 = mem[0],zero - movsd xmm3, qword ptr [rsi + 104] # xmm3 = mem[0],zero - ucomisd xmm1, xmm0 - movsd xmm5, qword ptr [rsi + 112] # xmm5 = mem[0],zero - movsd xmm6, qword ptr [rsi + 120] # xmm6 = mem[0],zero - seta byte ptr [rsp + 120] # 1-byte Folded Spill - movsd xmm8, qword ptr [rsi + 128] # xmm8 = mem[0],zero - movsd xmm9, qword ptr [rsi + 136] # xmm9 = mem[0],zero - ucomisd xmm3, xmm0 - movsd xmm10, qword ptr [rsi + 144] # xmm10 = mem[0],zero - movsd xmm11, qword ptr [rsi + 152] # xmm11 = mem[0],zero - seta byte ptr [rsp + 144] # 1-byte Folded Spill - movsd xmm12, qword ptr [rsi + 160] # xmm12 = mem[0],zero - movsd xmm13, qword ptr [rsi + 168] # xmm13 = mem[0],zero - ucomisd xmm5, xmm0 - movsd xmm14, qword ptr [rsi + 176] # xmm14 = mem[0],zero - movsd xmm2, qword ptr [rsi + 184] # xmm2 = mem[0],zero - seta byte ptr [rsp + 128] # 1-byte Folded Spill - movsd xmm3, qword ptr [rsi + 192] # xmm3 = mem[0],zero - movsd xmm4, qword ptr [rsi + 200] # xmm4 = mem[0],zero - ucomisd xmm6, xmm0 - movsd xmm6, qword ptr [rsi + 208] # xmm6 = mem[0],zero - movsd xmm7, qword ptr [rsi + 216] # xmm7 = mem[0],zero - seta r11b - movsd xmm1, qword ptr [rsi + 224] # xmm1 = mem[0],zero - movsd xmm5, qword ptr [rsi + 232] # xmm5 = mem[0],zero - ucomisd xmm8, xmm0 - seta byte ptr [rsp + 176] # 1-byte Folded Spill - ucomisd xmm9, xmm0 - seta cl - ucomisd xmm10, xmm0 - seta dil - ucomisd xmm11, xmm0 - seta r8b - ucomisd xmm12, xmm0 - seta r10b - ucomisd xmm13, xmm0 + movzx eax, byte ptr [rsi + 2] + cmp al, byte ptr [rdx + 2] + movzx eax, byte ptr [rsi + 3] + seta byte ptr [rsp + 20] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 3] + seta byte ptr [rsp + 22] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 4] + cmp al, byte ptr [rdx + 4] + movzx eax, byte ptr [rsi + 5] + seta byte ptr [rsp + 21] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 5] + seta byte ptr [rsp + 23] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 6] + cmp al, byte ptr [rdx + 6] + movzx eax, byte ptr [rsi + 7] + seta byte ptr [rsp + 48] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 7] seta r14b - ucomisd xmm14, xmm0 - seta byte ptr [rsp + 160] # 1-byte Folded Spill - ucomisd xmm2, xmm0 + movzx eax, byte ptr [rsi + 8] + cmp al, byte ptr [rdx + 8] + movzx eax, byte ptr [rsi + 9] + seta byte ptr [rsp + 7] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 9] + seta cl + movzx eax, byte ptr [rsi + 10] + cmp al, byte ptr [rdx + 10] + movzx eax, byte ptr [rsi + 11] seta r9b - ucomisd xmm3, xmm0 - seta byte ptr [rsp + 104] # 1-byte Folded Spill - ucomisd xmm4, xmm0 + cmp al, byte ptr [rdx + 11] + seta r11b + movzx eax, byte ptr [rsi + 12] + cmp al, byte ptr [rdx + 12] + movzx eax, byte ptr [rsi + 13] + seta r10b + cmp al, byte ptr [rdx + 13] + seta byte ptr [rsp + 6] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 14] + cmp al, byte ptr [rdx + 14] + movzx eax, byte ptr [rsi + 15] + seta byte ptr [rsp + 5] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 15] + seta bl + movzx eax, byte ptr [rsi + 16] + cmp al, byte ptr [rdx + 16] + movzx eax, byte ptr [rsi + 17] + seta byte ptr [rsp + 12] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 17] seta r15b - ucomisd xmm6, xmm0 - seta byte ptr [rsp + 112] # 1-byte Folded Spill - ucomisd xmm7, xmm0 - seta byte ptr [rsp + 72] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - seta byte ptr [rsp + 40] # 1-byte Folded Spill - ucomisd xmm5, xmm0 - movsd xmm1, qword ptr [rsi + 240] # xmm1 = mem[0],zero - seta byte ptr [rsp + 48] # 1-byte Folded Spill - ucomisd xmm1, xmm0 + movzx eax, byte ptr [rsi + 18] + cmp al, byte ptr [rdx + 18] + movzx eax, byte ptr [rsi + 19] + seta r12b + cmp al, byte ptr [rdx + 19] + seta byte ptr [rsp + 9] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 20] + cmp al, byte ptr [rdx + 20] + movzx eax, byte ptr [rsi + 21] seta byte ptr [rsp + 8] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 248] # xmm1 = mem[0],zero - add rsi, 256 - ucomisd xmm1, xmm0 - seta dl - add bl, bl - add bl, byte ptr [rsp + 24] # 1-byte Folded Reload + cmp al, byte ptr [rdx + 21] + seta byte ptr [rsp + 11] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 22] + cmp al, byte ptr [rdx + 22] + movzx eax, byte ptr [rsi + 23] + seta byte ptr [rsp + 10] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 23] + seta r8b + movzx eax, byte ptr [rsi + 24] + cmp al, byte ptr [rdx + 24] + movzx eax, byte ptr [rsi + 25] + seta byte ptr [rsp + 18] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 25] + seta byte ptr [rsp + 14] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 26] + cmp al, byte ptr [rdx + 26] + movzx eax, byte ptr [rsi + 27] + seta byte ptr [rsp + 13] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 27] + seta byte ptr [rsp + 16] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 28] + cmp al, byte ptr [rdx + 28] + movzx eax, byte ptr [rsi + 29] + seta byte ptr [rsp + 15] # 1-byte Folded Spill + cmp al, byte ptr [rdx + 29] + seta byte ptr [rsp + 17] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 30] + cmp al, byte ptr [rdx + 30] + seta byte ptr [rsp + 19] # 1-byte Folded Spill + movzx eax, byte ptr [rsi + 31] + add rsi, 32 + cmp al, byte ptr [rdx + 31] + seta dil + add r13b, r13b + add r13b, byte ptr [rsp + 4] # 1-byte Folded Reload + mov eax, r13d + movzx r13d, byte ptr [rsp + 48] # 1-byte Folded Reload + shl r13b, 6 + shl r14b, 7 + or r14b, r13b + movzx r13d, byte ptr [rsp + 20] # 1-byte Folded Reload shl r13b, 2 - or r13b, bl - shl r12b, 3 - or r12b, r13b - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, r12b - mov r12d, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 5 - or bl, r12b - movzx r12d, byte ptr [rsp + 88] # 1-byte Folded Reload - shl r12b, 6 - movzx r13d, byte ptr [rsp + 64] # 1-byte Folded Reload - shl r13b, 7 - or r13b, r12b - add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload - movzx r12d, byte ptr [rsp + 56] # 1-byte Folded Reload - shl r12b, 2 - or r12b, al - mov eax, r12d - movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload - shl r12b, 3 - or r12b, al - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 4 - or al, r12b - or r13b, bl - movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl bl, 5 - or bl, al - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al + or r13b, al + mov eax, r13d add cl, cl - add cl, byte ptr [rsp + 176] # 1-byte Folded Reload - shl dil, 2 - or dil, cl - shl r8b, 3 - or r8b, dil + add cl, byte ptr [rsp + 7] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 22] # 1-byte Folded Reload + shl r13b, 3 + or r13b, al + shl r9b, 2 + or r9b, cl + movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl cl, 4 + or cl, r13b + mov r13d, ecx + shl r11b, 3 + or r11b, r9b + movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload + shl cl, 5 + or cl, r13b shl r10b, 4 - or r10b, r8b - shl r14b, 5 - or r14b, r10b - or r11b, bl - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 6 - shl r9b, 7 - or r9b, al - mov rax, qword ptr [rsp] # 8-byte Reload - mov byte ptr [rax], r13b - or r9b, r14b + or r10b, r11b + movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl al, 5 + or al, r10b + movzx r9d, byte ptr [rsp + 5] # 1-byte Folded Reload + shl r9b, 6 + shl bl, 7 + or bl, r9b + or r14b, cl + or bl, al add r15b, r15b - add r15b, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 2 - or al, r15b - mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + add r15b, byte ptr [rsp + 12] # 1-byte Folded Reload + shl r12b, 2 + or r12b, r15b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 + or al, r12b + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl cl, 4 + or cl, al + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + shl al, 5 or al, cl - mov ebx, eax - mov rax, qword ptr [rsp] # 8-byte Reload - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r15], r14b + movzx ecx, byte ptr [rsp + 10] # 1-byte Folded Reload + shl cl, 6 + shl r8b, 7 + or r8b, cl + mov byte ptr [r15 + 1], bl + or r8b, al + movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 18] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 13] # 1-byte Folded Reload + shl cl, 2 + or cl, al + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 3 + or al, cl + movzx ecx, byte ptr [rsp + 15] # 1-byte Folded Reload shl cl, 4 - or cl, bl - mov ebx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload + or cl, al + mov eax, ecx + movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 5 - or cl, bl - mov byte ptr [rax + 1], r11b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - mov byte ptr [rax + 2], r9b - or dl, cl - mov byte ptr [rax + 3], dl - add rax, 4 - mov qword ptr [rsp], rax # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB7_51 -# %bb.52: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r14, qword ptr [rsp + 192] # 8-byte Reload -.LBB7_53: - shl r14, 5 - cmp r14, r11 - jge .LBB7_202 -# %bb.54: - mov r8, r11 - sub r8, r14 - not r14 - add r14, r11 - jne .LBB7_196 -# %bb.55: - xor r10d, r10d - jmp .LBB7_198 -.LBB7_2: - cmp edi, 2 - je .LBB7_56 -# %bb.3: - cmp edi, 3 - jne .LBB7_202 -# %bb.4: - mov r12b, byte ptr [rdx] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + or cl, al + movzx eax, byte ptr [rsp + 19] # 1-byte Folded Reload + shl al, 6 + shl dil, 7 + or dil, al + or dil, cl + mov byte ptr [r15 + 2], r8b + mov byte ptr [r15 + 3], dil + add rdx, 32 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB6_78 +# %bb.79: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB6_80: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.81: + xor ecx, ecx + .p2align 4, 0x90 +.LBB6_82: # =>This Inner Loop Header: Depth=1 + lea r8, [rcx + 1] + movzx ebx, byte ptr [rdx + rcx] + cmp bl, byte ptr [rsi + rcx] + sbb edi, edi + mov rbx, rcx + shr rbx, 3 + movzx r9d, byte ptr [r15 + rbx] + xor dil, r9b + and cl, 7 + mov al, 1 + # kill: def $cl killed $cl killed $rcx + shl al, cl + and al, dil + xor al, r9b + mov byte ptr [r15 + rbx], al + mov rcx, r8 + cmp r13, r8 + jne .LBB6_82 + jmp .LBB6_153 +.LBB6_111: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_8 -# %bb.5: - movsxd rax, r9d - mov r14, qword ptr [rsp] # 8-byte Reload + je .LBB6_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB6_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB7_6: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r12b - lea rsi, [rsi + 1] - setg dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB6_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setg r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB7_6 -# %bb.7: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_8: - sar r10, 5 - cmp r11, 32 - jl .LBB7_9 -# %bb.80: - cmp r10, 16 - mov byte ptr [rsp + 8], r12b # 1-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 288], r10 # 8-byte Spill - jb .LBB7_81 -# %bb.82: - mov rax, r10 - shl rax, 5 - add rax, rsi - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB7_84 -# %bb.83: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r10] - cmp rsi, rax - jae .LBB7_84 -.LBB7_81: - xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 96], rax # 8-byte Spill -.LBB7_87: - sub r10, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 240], r10 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB6_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB6_116: + sub r13, r8 + je .LBB6_153 +# %bb.117: + add r15, 1 +.LBB6_118: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB6_122 +# %bb.119: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_88: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp byte ptr [rsi], r12b - setg byte ptr [rsp + 192] # 1-byte Folded Spill - cmp byte ptr [rsi + 1], r12b - setg sil - cmp byte ptr [rcx + 2], r12b - setg r15b - cmp byte ptr [rcx + 3], r12b - setg r12b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 4], al - setg byte ptr [rsp + 176] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 5], al - setg byte ptr [rsp + 64] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 6], al - setg byte ptr [rsp + 208] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 7], al - setg r9b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 8], al - setg byte ptr [rsp + 128] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 9], al - setg dl - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 10], al - setg dil - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 11], al - setg r10b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 12], al - setg r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 13], al +.LBB6_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill + mov eax, dword ptr [rsi] + mov ecx, dword ptr [rsi + 4] + cmp eax, dword ptr [rdx] + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp ecx, dword ptr [rdx + 4] + setg byte ptr [rsp + 40] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 8] + cmp eax, dword ptr [rdx + 8] + setg byte ptr [rsp + 20] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 12] + cmp eax, dword ptr [rdx + 12] + setg byte ptr [rsp + 21] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 16] + cmp eax, dword ptr [rdx + 16] + setg byte ptr [rsp + 22] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 20] + cmp eax, dword ptr [rdx + 20] + setg byte ptr [rsp + 23] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 24] + cmp eax, dword ptr [rdx + 24] + setg byte ptr [rsp + 4] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 28] + cmp eax, dword ptr [rdx + 28] setg r13b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], al - setg byte ptr [rsp + 160] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], al - setg r8b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], bl - setg byte ptr [rsp + 144] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], bl - setg byte ptr [rsp + 112] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], bl - setg byte ptr [rsp + 104] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], bl - setg byte ptr [rsp + 120] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], bl - setg byte ptr [rsp + 72] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], bl - setg byte ptr [rsp + 88] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], bl - setg byte ptr [rsp + 80] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], bl + mov eax, dword ptr [rsi + 32] + cmp eax, dword ptr [rdx + 32] + setg byte ptr [rsp + 9] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 36] + cmp eax, dword ptr [rdx + 36] + setg dil + mov eax, dword ptr [rsi + 40] + cmp eax, dword ptr [rdx + 40] setg r11b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], bl - setg byte ptr [rsp + 56] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], bl - setg byte ptr [rsp + 40] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], bl - setg byte ptr [rsp + 48] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], bl - setg byte ptr [rsp + 32] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], bl - setg byte ptr [rsp + 24] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], bl - setg byte ptr [rsp + 16] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], bl - setg byte ptr [rsp] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], bl + mov eax, dword ptr [rsi + 44] + cmp eax, dword ptr [rdx + 44] + setg r15b + mov eax, dword ptr [rsi + 48] + cmp eax, dword ptr [rdx + 48] + setg byte ptr [rsp + 5] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 52] + cmp eax, dword ptr [rdx + 52] + setg byte ptr [rsp + 6] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 56] + cmp eax, dword ptr [rdx + 56] + setg byte ptr [rsp + 7] # 1-byte Folded Spill + mov eax, dword ptr [rsi + 60] + cmp eax, dword ptr [rdx + 60] setg bl - add sil, sil - add sil, byte ptr [rsp + 192] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + mov eax, dword ptr [rsi + 64] + mov ecx, dword ptr [rsi + 68] + cmp eax, dword ptr [rdx + 64] + mov eax, dword ptr [rsi + 72] + setg byte ptr [rsp + 10] # 1-byte Folded Spill + cmp ecx, dword ptr [rdx + 68] + mov ecx, dword ptr [rsi + 76] + setg r10b + cmp eax, dword ptr [rdx + 72] + mov eax, dword ptr [rsi + 80] + setg r14b + cmp ecx, dword ptr [rdx + 76] + mov ecx, dword ptr [rsi + 84] + setg r12b + cmp eax, dword ptr [rdx + 80] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp ecx, dword ptr [rdx + 84] + mov eax, dword ptr [rsi + 88] + setg byte ptr [rsp + 11] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 88] + mov eax, dword ptr [rsi + 92] + setg byte ptr [rsp + 14] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 92] + mov eax, dword ptr [rsi + 96] + setg r9b + cmp eax, dword ptr [rdx + 96] + mov eax, dword ptr [rsi + 100] + setg byte ptr [rsp + 19] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 100] + mov eax, dword ptr [rsi + 104] + setg byte ptr [rsp + 12] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 104] + mov eax, dword ptr [rsi + 108] + setg byte ptr [rsp + 13] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 108] + mov eax, dword ptr [rsi + 112] + setg byte ptr [rsp + 15] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 112] + mov eax, dword ptr [rsi + 116] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 116] + mov eax, dword ptr [rsi + 120] + setg byte ptr [rsp + 18] # 1-byte Folded Spill + cmp eax, dword ptr [rdx + 120] + mov eax, dword ptr [rsi + 124] + setg byte ptr [rsp + 17] # 1-byte Folded Spill + sub rsi, -128 + cmp eax, dword ptr [rdx + 124] + setg r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 - shl r9b, 7 - or r9b, al - shl r15b, 2 - or r15b, sil - add dl, dl - add dl, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r13b, 7 + or r13b, al + movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload + shl al, 2 + or al, cl + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload + shl cl, 3 + or cl, al + mov eax, ecx + shl r11b, 2 + or r11b, dil + movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r15b, 3 + or r15b, r11b + movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload + shl al, 4 + or al, r15b + mov edi, eax + movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload + shl al, 5 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 + shl bl, 7 + or bl, dil + or r13b, cl + or bl, al + add r10b, r10b + add r10b, byte ptr [rsp + 10] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b shl r12b, 3 - or r12b, r15b - shl dil, 2 - or dil, dl - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or r12b, r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 4 or al, r12b - movzx r12d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl r10b, 3 - or r10b, dil - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 5 - or dl, al - shl r14b, 4 - or r14b, r10b - shl r13b, 5 - or r13b, r14b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r9b, dl - or r8b, r13b - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 144] # 1-byte Folded Reload - mov esi, edx - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 2 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov esi, edx - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - mov byte ptr [rdx], r9b - movzx edi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dil, 6 - shl r11b, 7 - or r11b, dil - mov byte ptr [rdx + 1], r8b - or r11b, sil - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload + shl cl, 6 + shl r9b, 7 + or r9b, cl + mov byte ptr [r15 + 1], bl + or r9b, al + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 56] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 19] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 15] # 1-byte Folded Reload shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 18] # 1-byte Folded Reload shl al, 5 - or al, sil - movzx esi, byte ptr [rsp] # 1-byte Folded Reload - shl sil, 6 - shl bl, 7 - or bl, sil - or bl, al - mov byte ptr [rdx + 2], r11b - mov byte ptr [rdx + 3], bl - lea rsi, [rcx + 32] - add rdx, 4 - mov qword ptr [rsp + 96], rdx # 8-byte Spill - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB7_88 -# %bb.89: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 288] # 8-byte Reload - jmp .LBB7_90 -.LBB7_27: - cmp edi, 7 - je .LBB7_139 -# %bb.28: - cmp edi, 8 - jne .LBB7_202 -# %bb.29: - mov r13, qword ptr [rdx] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + or al, cl + movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload + shl cl, 6 + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b + add rdx, 128 + add r15, 4 + add qword ptr [rsp + 56], -1 # 8-byte Folded Spill + jne .LBB6_120 +# %bb.121: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB6_122: + shl rax, 5 + sub r13, rax + jle .LBB6_153 +# %bb.123: + xor ecx, ecx + .p2align 4, 0x90 +.LBB6_124: # =>This Inner Loop Header: Depth=1 + lea r8, [rcx + 1] + mov edi, dword ptr [rsi + 4*rcx] + cmp edi, dword ptr [rdx + 4*rcx] + setg bl + neg bl + mov rdi, rcx + shr rdi, 3 + movzx r9d, byte ptr [r15 + rdi] + xor bl, r9b + and cl, 7 + mov al, 1 + # kill: def $cl killed $cl killed $rcx + shl al, cl + and al, bl + xor al, r9b + mov byte ptr [r15 + rdi], al + mov rcx, r8 + cmp r13, r8 + jne .LBB6_124 +.LBB6_153: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.Lfunc_end6: + .size comparison_greater_arr_arr_sse4, .Lfunc_end6-comparison_greater_arr_arr_sse4 + # -- End function + .section .rodata.cst16,"aM",@progbits,16 + .p2align 4 # -- Begin function comparison_greater_arr_scalar_sse4 +.LCPI7_0: + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI7_1: + .zero 16,252 +.LCPI7_2: + .zero 16,248 +.LCPI7_3: + .zero 16,240 +.LCPI7_4: + .zero 16,224 +.LCPI7_5: + .zero 16,192 +.LCPI7_6: + .zero 16,128 +.LCPI7_7: + .byte 0 # 0x0 + .byte 8 # 0x8 + .byte 1 # 0x1 + .byte 9 # 0x9 + .byte 2 # 0x2 + .byte 10 # 0xa + .byte 3 # 0x3 + .byte 11 # 0xb + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf +.LCPI7_8: + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .byte 1 # 0x1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI7_9: + .byte 4 # 0x4 + .byte 12 # 0xc + .byte 5 # 0x5 + .byte 13 # 0xd + .byte 6 # 0x6 + .byte 14 # 0xe + .byte 7 # 0x7 + .byte 15 # 0xf + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 + .zero 1 +.LCPI7_10: + .zero 16,1 +.LCPI7_11: + .zero 16,4 +.LCPI7_12: + .zero 16,8 +.LCPI7_13: + .zero 16,16 +.LCPI7_14: + .zero 16,32 +.LCPI7_15: + .zero 16,64 +.LCPI7_16: + .zero 16,255 + .text + .globl comparison_greater_arr_scalar_sse4 + .p2align 4, 0x90 + .type comparison_greater_arr_scalar_sse4,@function +comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 +# %bb.0: + push rbp + mov rbp, rsp + push r15 + push r14 + push r13 + push r12 + push rbx + and rsp, -16 + sub rsp, 352 + # kill: def $r9d killed $r9d def $r9 + mov r15, r8 + mov r12, rcx + cmp edi, 6 + jg .LBB7_24 +# %bb.1: + cmp edi, 3 + jle .LBB7_2 +# %bb.6: + cmp edi, 4 + je .LBB7_112 +# %bb.7: + cmp edi, 5 + je .LBB7_130 +# %bb.8: + cmp edi, 6 + jne .LBB7_226 +# %bb.9: + mov r13d, dword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_33 -# %bb.30: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload + je .LBB7_15 +# %bb.10: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_13 +# %bb.11: + movsxd rdx, r9d + mov rax, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_31: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rsi] - lea rsi, [rsi + 8] - sbb edx, edx - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r9 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB7_12: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp r13d, dword ptr [rcx] + sbb r11d, r11d + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r9 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_31 -# %bb.32: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_33: - sar r10, 5 - cmp r11, 32 - jl .LBB7_37 -# %bb.34: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add rdx, 1 + mov rcx, rsi + add rax, -1 + jne .LBB7_12 +.LBB7_13: + sub r15, r8 + je .LBB7_226 +# %bb.14: + add r12, 1 +.LBB7_15: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_19 +# %bb.16: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_35: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 +.LBB7_17: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + cmp dword ptr [rsi], r13d seta byte ptr [rsp + 208] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 - seta r10b - cmp qword ptr [rsi + 16], r13 + cmp dword ptr [rsi + 4], r13d seta dil - cmp qword ptr [rsi + 24], r13 + cmp dword ptr [rsi + 8], r13d + seta r14b + cmp dword ptr [rsi + 12], r13d seta byte ptr [rsp + 176] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - seta byte ptr [rsp + 104] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - seta byte ptr [rsp + 88] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 + cmp dword ptr [rsi + 16], r13d + seta byte ptr [rsp + 112] # 1-byte Folded Spill + cmp dword ptr [rsi + 20], r13d + seta byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 24], r13d seta al - cmp qword ptr [rsi + 56], r13 - seta r14b - cmp qword ptr [rsi + 64], r13 - seta byte ptr [rsp + 128] # 1-byte Folded Spill - cmp qword ptr [rsi + 72], r13 - seta dl - cmp qword ptr [rsi + 80], r13 + cmp dword ptr [rsi + 28], r13d + seta bl + cmp dword ptr [rsi + 32], r13d + seta byte ptr [rsp + 192] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d + seta cl + cmp dword ptr [rsi + 40], r13d seta r9b - cmp qword ptr [rsi + 88], r13 + cmp dword ptr [rsi + 44], r13d + seta r10b + cmp dword ptr [rsi + 48], r13d seta r11b - cmp qword ptr [rsi + 96], r13 - seta bl - cmp qword ptr [rsi + 104], r13 + cmp dword ptr [rsi + 52], r13d seta r12b - cmp qword ptr [rsi + 112], r13 - seta byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 120], r13 - seta cl - cmp qword ptr [rsi + 128], r13 - seta byte ptr [rsp + 72] # 1-byte Folded Spill - cmp qword ptr [rsi + 136], r13 + cmp dword ptr [rsi + 56], r13d seta byte ptr [rsp + 144] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 - seta byte ptr [rsp + 112] # 1-byte Folded Spill - cmp qword ptr [rsi + 152], r13 + cmp dword ptr [rsi + 60], r13d + seta dl + cmp dword ptr [rsi + 64], r13d + seta byte ptr [rsp + 88] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + seta byte ptr [rsp + 160] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + seta byte ptr [rsp + 104] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d seta byte ptr [rsp + 120] # 1-byte Folded Spill - cmp qword ptr [rsi + 160], r13 - seta byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 168], r13 + cmp dword ptr [rsi + 80], r13d + seta byte ptr [rsp + 72] # 1-byte Folded Spill + cmp dword ptr [rsi + 84], r13d seta byte ptr [rsp + 96] # 1-byte Folded Spill - cmp qword ptr [rsi + 176], r13 + cmp dword ptr [rsi + 88], r13d seta byte ptr [rsp + 64] # 1-byte Folded Spill - cmp qword ptr [rsi + 184], r13 + cmp dword ptr [rsi + 92], r13d seta r15b - cmp qword ptr [rsi + 192], r13 - seta byte ptr [rsp + 32] # 1-byte Folded Spill - cmp qword ptr [rsi + 200], r13 + cmp dword ptr [rsi + 96], r13d + seta byte ptr [rsp + 24] # 1-byte Folded Spill + cmp dword ptr [rsi + 100], r13d seta byte ptr [rsp + 56] # 1-byte Folded Spill - cmp qword ptr [rsi + 208], r13 + cmp dword ptr [rsi + 104], r13d seta byte ptr [rsp + 40] # 1-byte Folded Spill - cmp qword ptr [rsi + 216], r13 + cmp dword ptr [rsi + 108], r13d seta byte ptr [rsp + 48] # 1-byte Folded Spill - cmp qword ptr [rsi + 224], r13 - seta byte ptr [rsp + 24] # 1-byte Folded Spill - cmp qword ptr [rsi + 232], r13 + cmp dword ptr [rsi + 112], r13d + seta byte ptr [rsp + 32] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp qword ptr [rsi + 240], r13 + cmp dword ptr [rsi + 120], r13d seta byte ptr [rsp + 8] # 1-byte Folded Spill - cmp qword ptr [rsi + 248], r13 + cmp dword ptr [rsi + 124], r13d seta r8b - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 6 - shl r14b, 7 - or r14b, al - shl dil, 2 - or dil, r10b - add dl, dl - add dl, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 192] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 3 - or al, dil - mov r10, qword ptr [rsp] # 8-byte Reload + or al, r14b shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx - shl r11b, 3 - or r11b, r9b - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - shl bl, 4 - or bl, r11b + or r9b, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r10b, 3 + or r10b, r9b + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r11b, 4 + or r11b, r10b shl r12b, 5 - or r12b, bl - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload + or r12b, r11b + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or r14b, dl - or cl, r12b - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov byte ptr [r10], r14b + or bl, cl + or dl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r12], bl movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r10 + 1], cl - or r15b, dl + mov byte ptr [r12 + 1], dl + or r15b, cl movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload + add cl, byte ptr [rsp + 24] # 1-byte Folded Reload mov edx, ecx movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload shl cl, 2 @@ -35876,7 +36216,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl cl, 3 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload shl cl, 4 or cl, dl mov edx, ecx @@ -35888,456 +36228,551 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl r8b, 7 or r8b, dl or r8b, cl - mov byte ptr [r10 + 2], r15b - mov byte ptr [r10 + 3], r8b - add rsi, 256 - add r10, 4 - mov qword ptr [rsp], r10 # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB7_35 -# %bb.36: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 240] # 8-byte Reload -.LBB7_37: - shl r10, 5 - cmp r10, r11 - jge .LBB7_202 -# %bb.38: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], r8b + add rsi, 128 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_17 +# %bb.18: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload +.LBB7_19: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_226 +# %bb.20: + or rax, 1 + cmp r15, rax jne .LBB7_155 -# %bb.39: +# %bb.21: xor r11d, r11d - jmp .LBB7_40 -.LBB7_56: - mov r10b, byte ptr [rdx] - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jmp .LBB7_22 +.LBB7_24: + cmp edi, 8 + jle .LBB7_25 +# %bb.42: + cmp edi, 9 + je .LBB7_177 +# %bb.43: + cmp edi, 11 + je .LBB7_194 +# %bb.44: + cmp edi, 12 + jne .LBB7_226 +# %bb.45: + mov r14, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_60 -# %bb.57: - movsxd rax, r9d - mov r14, qword ptr [rsp] # 8-byte Reload + je .LBB7_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_49 +# %bb.47: + movsxd rdx, r9d + movq xmm0, r14 + mov r11, r8 .p2align 4, 0x90 -.LBB7_58: # =>This Inner Loop Header: Depth=1 - cmp r10b, byte ptr [rsi] - lea rsi, [rsi + 1] - sbb edx, edx - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB7_48: # =>This Inner Loop Header: Depth=1 + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + add rsi, 8 + ucomisd xmm1, xmm0 + seta bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_58 -# %bb.59: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_60: - sar r15, 5 - cmp r11, 32 - jl .LBB7_61 -# %bb.62: - cmp r15, 16 - mov byte ptr [rsp + 8], r10b # 1-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 264], r15 # 8-byte Spill - jb .LBB7_63 -# %bb.64: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB7_66 -# %bb.65: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] - cmp rsi, rax - jae .LBB7_66 -.LBB7_63: - xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov r12, rsi - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 120], rax # 8-byte Spill -.LBB7_69: - sub r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 192], r15 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + add r11, -1 + jne .LBB7_48 +.LBB7_49: + sub r15, r8 + je .LBB7_226 +# %bb.50: + add r12, 1 +.LBB7_51: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_55 +# %bb.52: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 224], r14 # 8-byte Spill + movq xmm0, r14 + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_70: # =>This Inner Loop Header: Depth=1 - mov rcx, r12 - cmp byte ptr [r12], r10b - seta byte ptr [rsp + 208] # 1-byte Folded Spill - cmp byte ptr [r12 + 1], r10b - seta r14b - cmp byte ptr [r12 + 2], r10b - seta r11b - cmp byte ptr [r12 + 3], r10b - seta r15b - cmp byte ptr [r12 + 4], r10b - seta byte ptr [rsp + 176] # 1-byte Folded Spill - cmp byte ptr [r12 + 5], r10b +.LBB7_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + movsd xmm2, qword ptr [rsi + 8] # xmm2 = mem[0],zero + ucomisd xmm1, xmm0 + seta byte ptr [rsp + 32] # 1-byte Folded Spill + ucomisd xmm2, xmm0 + seta dl + movsd xmm1, qword ptr [rsi + 16] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 24] # xmm1 = mem[0],zero + seta r13b + ucomisd xmm1, xmm0 + seta r12b + movsd xmm1, qword ptr [rsi + 32] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 40] # xmm1 = mem[0],zero + seta byte ptr [rsp + 72] # 1-byte Folded Spill + ucomisd xmm1, xmm0 seta byte ptr [rsp + 96] # 1-byte Folded Spill - cmp byte ptr [r12 + 6], r10b + movsd xmm1, qword ptr [rsi + 48] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 56] # xmm1 = mem[0],zero + seta byte ptr [rsp + 80] # 1-byte Folded Spill + ucomisd xmm1, xmm0 + seta byte ptr [rsp + 64] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 64] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 72] # xmm1 = mem[0],zero + seta byte ptr [rsp + 16] # 1-byte Folded Spill + ucomisd xmm1, xmm0 seta al - cmp byte ptr [r12 + 7], r10b - seta r8b - cmp byte ptr [r12 + 8], r10b - seta byte ptr [rsp + 128] # 1-byte Folded Spill - cmp byte ptr [r12 + 9], r10b - seta sil - cmp byte ptr [r12 + 10], r10b + movsd xmm1, qword ptr [rsi + 80] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 88] # xmm1 = mem[0],zero + seta byte ptr [rsp + 40] # 1-byte Folded Spill + ucomisd xmm1, xmm0 + seta byte ptr [rsp + 24] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 96] # xmm1 = mem[0],zero + movsd xmm3, qword ptr [rsi + 104] # xmm3 = mem[0],zero + ucomisd xmm1, xmm0 + movsd xmm5, qword ptr [rsi + 112] # xmm5 = mem[0],zero + movsd xmm6, qword ptr [rsi + 120] # xmm6 = mem[0],zero + seta byte ptr [rsp + 120] # 1-byte Folded Spill + movsd xmm8, qword ptr [rsi + 128] # xmm8 = mem[0],zero + movsd xmm9, qword ptr [rsi + 136] # xmm9 = mem[0],zero + ucomisd xmm3, xmm0 + movsd xmm10, qword ptr [rsi + 144] # xmm10 = mem[0],zero + movsd xmm11, qword ptr [rsi + 152] # xmm11 = mem[0],zero + seta byte ptr [rsp + 160] # 1-byte Folded Spill + movsd xmm12, qword ptr [rsi + 160] # xmm12 = mem[0],zero + movsd xmm13, qword ptr [rsi + 168] # xmm13 = mem[0],zero + ucomisd xmm5, xmm0 + movsd xmm14, qword ptr [rsi + 176] # xmm14 = mem[0],zero + movsd xmm2, qword ptr [rsi + 184] # xmm2 = mem[0],zero + seta byte ptr [rsp + 192] # 1-byte Folded Spill + movsd xmm3, qword ptr [rsi + 192] # xmm3 = mem[0],zero + movsd xmm4, qword ptr [rsi + 200] # xmm4 = mem[0],zero + ucomisd xmm6, xmm0 + movsd xmm6, qword ptr [rsi + 208] # xmm6 = mem[0],zero + movsd xmm7, qword ptr [rsi + 216] # xmm7 = mem[0],zero + seta r11b + movsd xmm1, qword ptr [rsi + 224] # xmm1 = mem[0],zero + movsd xmm5, qword ptr [rsi + 232] # xmm5 = mem[0],zero + ucomisd xmm8, xmm0 + seta byte ptr [rsp + 176] # 1-byte Folded Spill + ucomisd xmm9, xmm0 + seta cl + ucomisd xmm10, xmm0 seta dil - cmp byte ptr [r12 + 11], r10b - seta r9b - cmp byte ptr [r12 + 12], r10b + ucomisd xmm11, xmm0 + seta r8b + ucomisd xmm12, xmm0 seta r10b - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [r12 + 13], dl - seta r12b - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], dl - seta byte ptr [rsp + 160] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], dl - seta bl - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], dl + ucomisd xmm13, xmm0 + seta r14b + ucomisd xmm14, xmm0 seta byte ptr [rsp + 144] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], dl - seta r13b - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], dl + ucomisd xmm2, xmm0 + seta r9b + ucomisd xmm3, xmm0 seta byte ptr [rsp + 112] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], dl + ucomisd xmm4, xmm0 + seta r15b + ucomisd xmm6, xmm0 seta byte ptr [rsp + 104] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], dl - seta byte ptr [rsp + 72] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], dl + ucomisd xmm7, xmm0 seta byte ptr [rsp + 88] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], dl - seta byte ptr [rsp + 80] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], dl + ucomisd xmm1, xmm0 seta byte ptr [rsp + 56] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], dl - seta byte ptr [rsp + 64] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], dl - seta byte ptr [rsp + 40] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], dl - seta byte ptr [rsp + 32] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], dl + ucomisd xmm5, xmm0 + movsd xmm1, qword ptr [rsi + 240] # xmm1 = mem[0],zero seta byte ptr [rsp + 48] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], dl - seta byte ptr [rsp + 24] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], dl - seta byte ptr [rsp + 16] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], dl - seta byte ptr [rsp] # 1-byte Folded Spill - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], dl - seta dl - add r14b, r14b - add r14b, byte ptr [rsp + 208] # 1-byte Folded Reload + ucomisd xmm1, xmm0 + seta byte ptr [rsp + 8] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 248] # xmm1 = mem[0],zero + add rsi, 256 + ucomisd xmm1, xmm0 + seta bl + add dl, dl + add dl, byte ptr [rsp + 32] # 1-byte Folded Reload + shl r13b, 2 + or r13b, dl + shl r12b, 3 + or r12b, r13b + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 4 + or dl, r12b + mov r12d, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 5 + or dl, r12b + movzx r12d, byte ptr [rsp + 80] # 1-byte Folded Reload + shl r12b, 6 + movzx r13d, byte ptr [rsp + 64] # 1-byte Folded Reload + shl r13b, 7 + or r13b, r12b + add al, al + add al, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx r12d, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r12b, 2 + or r12b, al + mov eax, r12d + movzx r12d, byte ptr [rsp + 24] # 1-byte Folded Reload + shl r12b, 3 + or r12b, al + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 4 + or al, r12b + or r13b, dl + movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl dl, 5 + or dl, al + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 6 - shl r8b, 7 - or r8b, al - shl r11b, 2 - or r11b, r14b - add sil, sil - add sil, byte ptr [rsp + 128] # 1-byte Folded Reload - shl r15b, 3 - or r15b, r11b + shl r11b, 7 + or r11b, al + add cl, cl + add cl, byte ptr [rsp + 176] # 1-byte Folded Reload shl dil, 2 - or dil, sil - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 4 - or al, r15b - mov esi, eax - shl r9b, 3 - or r9b, dil - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 5 - or al, sil + or dil, cl + shl r8b, 3 + or r8b, dil shl r10b, 4 - or r10b, r9b - shl r12b, 5 - or r12b, r10b - movzx r10d, byte ptr [rsp + 8] # 1-byte Folded Reload - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl bl, 7 - or bl, sil - or r8b, al - or bl, r12b - add r13b, r13b - add r13b, byte ptr [rsp + 144] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 2 - or al, r13b - mov esi, eax + or r10b, r8b + shl r14b, 5 + or r14b, r10b + or r11b, dl + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + shl al, 6 + shl r9b, 7 + or r9b, al + mov rax, qword ptr [rsp + 128] # 8-byte Reload + mov byte ptr [rax], r13b + or r9b, r14b + add r15b, r15b + add r15b, byte ptr [rsp + 112] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 2 + or al, r15b + mov ecx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + or al, cl + mov ecx, eax + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 5 - or al, sil - mov r9d, eax - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - mov byte ptr [rsi], r8b - movzx edi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dil, 6 - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 7 - or al, dil - mov byte ptr [rsi + 1], bl - or al, r9b - movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 64] # 1-byte Folded Reload - mov edi, ebx - movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload - shl bl, 2 - or bl, dil - mov edi, ebx - movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl bl, 3 - or bl, dil - mov edi, ebx - movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload - shl bl, 4 - or bl, dil - mov edi, ebx - movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload - shl bl, 5 - or bl, dil - movzx edi, byte ptr [rsp] # 1-byte Folded Reload - shl dil, 6 - shl dl, 7 - or dl, dil - or dl, bl - mov byte ptr [rsi + 2], al - mov byte ptr [rsi + 3], dl - lea r12, [rcx + 32] - add rsi, 4 - mov qword ptr [rsp + 120], rsi # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB7_70 -# %bb.71: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r15, qword ptr [rsp + 264] # 8-byte Reload - jmp .LBB7_72 -.LBB7_139: - mov r13d, dword ptr [rdx] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + or al, cl + mov byte ptr [r12 + 1], r11b + movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + mov byte ptr [r12 + 2], r9b + or bl, al + mov byte ptr [r12 + 3], bl + add r12, 4 + add qword ptr [rsp + 208], -1 # 8-byte Folded Spill + jne .LBB7_53 +# %bb.54: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r14, qword ptr [rsp + 224] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload +.LBB7_55: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_226 +# %bb.56: + movq xmm0, r14 + or rax, 1 + cmp r15, rax + jne .LBB7_220 +# %bb.57: + xor r10d, r10d + jmp .LBB7_222 +.LBB7_2: + cmp edi, 2 + je .LBB7_58 +# %bb.3: + cmp edi, 3 + jne .LBB7_226 +# %bb.4: + mov r13b, byte ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB7_5 +# %bb.85: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_86 +# %bb.91: + movsxd rdx, r9d + mov rax, r8 + .p2align 4, 0x90 +.LBB7_92: # =>This Inner Loop Header: Depth=1 + lea r14, [rsi + 1] + cmp byte ptr [rsi], r13b + setg bl + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + movzx r9d, byte ptr [r12 + rsi] + xor bl, r9b + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rsi], dil + add rdx, 1 + mov rsi, r14 + add rax, -1 + jne .LBB7_92 +# %bb.87: + sub r15, r8 + jne .LBB7_88 + jmp .LBB7_226 +.LBB7_25: + cmp edi, 7 + je .LBB7_157 +# %bb.26: + cmp edi, 8 + jne .LBB7_226 +# %bb.27: + mov r13, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_143 -# %bb.140: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload + je .LBB7_33 +# %bb.28: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_31 +# %bb.29: + movsxd rdx, r9d + mov rax, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_141: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setg dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r9 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB7_30: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp r13, qword ptr [rcx] + sbb r11d, r11d + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r9 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_141 -# %bb.142: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_143: - sar r10, 5 - cmp r11, 32 - jl .LBB7_147 -# %bb.144: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add rdx, 1 + mov rcx, rsi + add rax, -1 + jne .LBB7_30 +.LBB7_31: + sub r15, r8 + je .LBB7_226 +# %bb.32: + add r12, 1 +.LBB7_33: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_37 +# %bb.34: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_145: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - setg byte ptr [rsp + 208] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - setg r10b - cmp dword ptr [rsi + 8], r13d - setg dil - cmp dword ptr [rsi + 12], r13d - setg byte ptr [rsp + 176] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - setg al - cmp dword ptr [rsi + 28], r13d - setg r14b - cmp dword ptr [rsi + 32], r13d - setg byte ptr [rsp + 128] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d - setg dl - cmp dword ptr [rsi + 40], r13d - setg r9b - cmp dword ptr [rsi + 44], r13d - setg r11b - cmp dword ptr [rsi + 48], r13d - setg bl - cmp dword ptr [rsi + 52], r13d - setg r12b - cmp dword ptr [rsi + 56], r13d - setg byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - setg cl - cmp dword ptr [rsi + 64], r13d - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - setg byte ptr [rsp + 144] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d - setg r15b - cmp dword ptr [rsi + 96], r13d - setg byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - setg byte ptr [rsp + 56] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - setg r8b - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload +.LBB7_35: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + cmp qword ptr [rsi], r13 + seta byte ptr [rsp + 208] # 1-byte Folded Spill + cmp qword ptr [rsi + 8], r13 + seta dil + cmp qword ptr [rsi + 16], r13 + seta r14b + cmp qword ptr [rsi + 24], r13 + seta byte ptr [rsp + 176] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + seta byte ptr [rsp + 112] # 1-byte Folded Spill + cmp qword ptr [rsi + 40], r13 + seta byte ptr [rsp + 80] # 1-byte Folded Spill + cmp qword ptr [rsi + 48], r13 + seta al + cmp qword ptr [rsi + 56], r13 + seta bl + cmp qword ptr [rsi + 64], r13 + seta byte ptr [rsp + 192] # 1-byte Folded Spill + cmp qword ptr [rsi + 72], r13 + seta cl + cmp qword ptr [rsi + 80], r13 + seta r9b + cmp qword ptr [rsi + 88], r13 + seta r10b + cmp qword ptr [rsi + 96], r13 + seta r11b + cmp qword ptr [rsi + 104], r13 + seta r12b + cmp qword ptr [rsi + 112], r13 + seta byte ptr [rsp + 144] # 1-byte Folded Spill + cmp qword ptr [rsi + 120], r13 + seta dl + cmp qword ptr [rsi + 128], r13 + seta byte ptr [rsp + 88] # 1-byte Folded Spill + cmp qword ptr [rsi + 136], r13 + seta byte ptr [rsp + 160] # 1-byte Folded Spill + cmp qword ptr [rsi + 144], r13 + seta byte ptr [rsp + 104] # 1-byte Folded Spill + cmp qword ptr [rsi + 152], r13 + seta byte ptr [rsp + 120] # 1-byte Folded Spill + cmp qword ptr [rsi + 160], r13 + seta byte ptr [rsp + 72] # 1-byte Folded Spill + cmp qword ptr [rsi + 168], r13 + seta byte ptr [rsp + 96] # 1-byte Folded Spill + cmp qword ptr [rsi + 176], r13 + seta byte ptr [rsp + 64] # 1-byte Folded Spill + cmp qword ptr [rsi + 184], r13 + seta r15b + cmp qword ptr [rsi + 192], r13 + seta byte ptr [rsp + 24] # 1-byte Folded Spill + cmp qword ptr [rsi + 200], r13 + seta byte ptr [rsp + 56] # 1-byte Folded Spill + cmp qword ptr [rsi + 208], r13 + seta byte ptr [rsp + 40] # 1-byte Folded Spill + cmp qword ptr [rsi + 216], r13 + seta byte ptr [rsp + 48] # 1-byte Folded Spill + cmp qword ptr [rsi + 224], r13 + seta byte ptr [rsp + 32] # 1-byte Folded Spill + cmp qword ptr [rsi + 232], r13 + seta byte ptr [rsp + 16] # 1-byte Folded Spill + cmp qword ptr [rsi + 240], r13 + seta byte ptr [rsp + 8] # 1-byte Folded Spill + cmp qword ptr [rsi + 248], r13 + seta r8b + add dil, dil + add dil, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 6 - shl r14b, 7 - or r14b, al - shl dil, 2 - or dil, r10b - add dl, dl - add dl, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 192] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 3 - or al, dil - mov r10, qword ptr [rsp] # 8-byte Reload + or al, r14b shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx - shl r11b, 3 - or r11b, r9b - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - shl bl, 4 - or bl, r11b + or r9b, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r10b, 3 + or r10b, r9b + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r11b, 4 + or r11b, r10b shl r12b, 5 - or r12b, bl - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload + or r12b, r11b + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or r14b, dl - or cl, r12b - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov byte ptr [r10], r14b + or bl, cl + or dl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r12], bl movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r10 + 1], cl - or r15b, dl + mov byte ptr [r12 + 1], dl + or r15b, cl movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload + add cl, byte ptr [rsp + 24] # 1-byte Folded Reload mov edx, ecx movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload shl cl, 2 @@ -36347,7 +36782,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl cl, 3 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload shl cl, 4 or cl, dl mov edx, ecx @@ -36359,118 +36794,129 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl r8b, 7 or r8b, dl or r8b, cl - mov byte ptr [r10 + 2], r15b - mov byte ptr [r10 + 3], r8b - add rsi, 128 - add r10, 4 - mov qword ptr [rsp], r10 # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB7_145 -# %bb.146: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 240] # 8-byte Reload -.LBB7_147: - shl r10, 5 - cmp r10, r11 - jge .LBB7_202 -# %bb.148: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB7_153 -# %bb.149: + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], r8b + add rsi, 256 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_35 +# %bb.36: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload +.LBB7_37: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_226 +# %bb.38: + or rax, 1 + cmp r15, rax + jne .LBB7_175 +# %bb.39: xor r11d, r11d - jmp .LBB7_150 -.LBB7_98: + jmp .LBB7_40 +.LBB7_112: movzx r13d, word ptr [rdx] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_102 -# %bb.99: - movsxd rax, r9d - mov rdx, qword ptr [rsp] # 8-byte Reload + je .LBB7_118 +# %bb.113: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_116 +# %bb.114: + movsxd rdx, r9d + mov rax, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_100: # =>This Inner Loop Header: Depth=1 - cmp r13w, word ptr [rsi] - lea rsi, [rsi + 2] - sbb r9d, r9d - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [rdx + rbx] - xor r9b, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB7_115: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp r13w, word ptr [rcx] + sbb r11d, r11d + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r9b - xor dil, r8b - mov byte ptr [rdx + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_100 -# %bb.101: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_102: - sar r10, 5 - cmp r11, 32 - jl .LBB7_106 -# %bb.103: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add rdx, 1 + mov rcx, rsi + add rax, -1 + jne .LBB7_115 +.LBB7_116: + sub r15, r8 + je .LBB7_226 +# %bb.117: + add r12, 1 +.LBB7_118: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_122 +# %bb.119: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_104: # =>This Inner Loop Header: Depth=1 +.LBB7_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill cmp word ptr [rsi], r13w - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp word ptr [rsi + 2], r13w - seta r10b - cmp word ptr [rsi + 4], r13w seta dil + cmp word ptr [rsi + 4], r13w + seta r14b cmp word ptr [rsi + 6], r13w seta byte ptr [rsp + 208] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - seta byte ptr [rsp + 128] # 1-byte Folded Spill + seta byte ptr [rsp + 176] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w seta byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w seta al cmp word ptr [rsi + 14], r13w - seta r14b + seta bl cmp word ptr [rsi + 16], r13w - seta byte ptr [rsp + 24] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w - seta dl + seta cl cmp word ptr [rsi + 20], r13w seta r9b cmp word ptr [rsi + 22], r13w - seta r11b + seta r10b cmp word ptr [rsi + 24], r13w - seta bl + seta r11b cmp word ptr [rsi + 26], r13w seta r12b cmp word ptr [rsi + 28], r13w - seta byte ptr [rsp + 176] # 1-byte Folded Spill + seta byte ptr [rsp + 192] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - seta cl + seta dl cmp word ptr [rsi + 32], r13w seta byte ptr [rsp + 16] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w seta byte ptr [rsp + 160] # 1-byte Folded Spill cmp word ptr [rsi + 36], r13w - seta byte ptr [rsp + 112] # 1-byte Folded Spill - cmp word ptr [rsi + 38], r13w seta byte ptr [rsp + 104] # 1-byte Folded Spill + cmp word ptr [rsi + 38], r13w + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w @@ -36482,96 +36928,96 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 cmp word ptr [rsi + 48], r13w seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w - seta byte ptr [rsp + 88] # 1-byte Folded Spill - cmp word ptr [rsi + 52], r13w seta byte ptr [rsp + 96] # 1-byte Folded Spill + cmp word ptr [rsi + 52], r13w + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w - seta byte ptr [rsp + 64] # 1-byte Folded Spill - cmp word ptr [rsi + 56], r13w seta byte ptr [rsp + 40] # 1-byte Folded Spill - cmp word ptr [rsi + 58], r13w + cmp word ptr [rsi + 56], r13w seta byte ptr [rsp + 48] # 1-byte Folded Spill + cmp word ptr [rsi + 58], r13w + seta byte ptr [rsp + 24] # 1-byte Folded Spill cmp word ptr [rsi + 60], r13w seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [rsi + 62], r13w seta r8b - add r10b, r10b - add r10b, byte ptr [rsp + 56] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 6 - shl r14b, 7 - or r14b, al - shl dil, 2 - or dil, r10b - add dl, dl - add dl, byte ptr [rsp + 24] # 1-byte Folded Reload + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 64] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 3 - or al, dil - mov r10, qword ptr [rsp] # 8-byte Reload + or al, r14b shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx - shl r11b, 3 - or r11b, r9b - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - shl bl, 4 - or bl, r11b + or r9b, cl + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r10b, 3 + or r10b, r9b + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r11b, 4 + or r11b, r10b shl r12b, 5 - or r12b, bl - movzx edi, byte ptr [rsp + 176] # 1-byte Folded Reload + or r12b, r11b + movzx edi, byte ptr [rsp + 192] # 1-byte Folded Reload shl dil, 6 - shl cl, 7 - or cl, dil - or r14b, dl - or cl, r12b - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 16] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 + shl dl, 7 or dl, dil - mov byte ptr [r10], r14b + or bl, cl + or dl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 16] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r12], bl movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 6 shl r15b, 7 or r15b, bl - mov byte ptr [r10 + 1], cl - or r15b, dl - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + mov byte ptr [r12 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload add cl, cl add cl, byte ptr [rsp + 8] # 1-byte Folded Reload mov edx, ecx - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload shl cl, 2 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload shl cl, 3 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload shl cl, 4 or cl, dl mov edx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload shl cl, 5 or cl, dl movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload @@ -36579,102 +37025,107 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl r8b, 7 or r8b, dl or r8b, cl - mov byte ptr [r10 + 2], r15b - mov byte ptr [r10 + 3], r8b + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], r8b add rsi, 64 - add r10, 4 - mov qword ptr [rsp], r10 # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB7_104 -# %bb.105: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 240] # 8-byte Reload -.LBB7_106: - shl r10, 5 - cmp r10, r11 - jge .LBB7_202 -# %bb.107: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB7_112 -# %bb.108: + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_120 +# %bb.121: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload +.LBB7_122: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_226 +# %bb.123: + or rax, 1 + cmp r15, rax + jne .LBB7_128 +# %bb.124: xor r11d, r11d - jmp .LBB7_109 -.LBB7_114: - movzx eax, word ptr [rdx] - mov dword ptr [rsp + 240], eax # 4-byte Spill - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jmp .LBB7_125 +.LBB7_130: + movzx r13d, word ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB7_118 -# %bb.115: - movsxd rax, r9d - mov r10d, dword ptr [rsp + 240] # 4-byte Reload - mov r14, qword ptr [rsp] # 8-byte Reload + je .LBB7_136 +# %bb.131: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_134 +# %bb.132: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_116: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r10w - lea rsi, [rsi + 2] - setg dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB7_133: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + setg bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_116 -# %bb.117: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_118: - sar r15, 5 - cmp r11, 32 - jl .LBB7_119 -# %bb.120: - cmp r15, 8 - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 272], r15 # 8-byte Spill - jb .LBB7_121 -# %bb.122: - mov rax, r15 + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB7_133 +.LBB7_134: + sub r15, r8 + je .LBB7_226 +# %bb.135: + add r12, 1 +.LBB7_136: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB7_137 +# %bb.138: + cmp rcx, 8 + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rcx # 8-byte Spill + jb .LBB7_139 +# %bb.140: + mov rax, rcx shl rax, 6 add rax, rsi - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB7_124 -# %bb.123: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] + cmp r12, rax + jae .LBB7_142 +# %bb.141: + lea rax, [r12 + 4*rcx] cmp rax, rsi - jbe .LBB7_124 -.LBB7_121: + jbe .LBB7_142 +.LBB7_139: xor eax, eax mov qword ptr [rsp + 40], rax # 8-byte Spill - mov r14, qword ptr [rsp] # 8-byte Reload -.LBB7_127: - mov qword ptr [rsp + 8], r14 # 8-byte Spill - sub r15, qword ptr [rsp + 40] # 8-byte Folded Reload - mov qword ptr [rsp + 192], r15 # 8-byte Spill - mov r13d, dword ptr [rsp + 240] # 4-byte Reload + mov qword ptr [rsp + 8], r12 # 8-byte Spill +.LBB7_145: + sub rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB7_128: # =>This Inner Loop Header: Depth=1 +.LBB7_146: # =>This Inner Loop Header: Depth=1 mov r11, rsi cmp word ptr [rsi], r13w setg byte ptr [rsp + 208] # 1-byte Folded Spill @@ -36685,15 +37136,15 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 cmp word ptr [rsi + 6], r13w setg byte ptr [rsp + 176] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - setg byte ptr [rsp + 104] # 1-byte Folded Spill + setg byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - setg byte ptr [rsp + 88] # 1-byte Folded Spill + setg byte ptr [rsp + 80] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w setg al cmp word ptr [rsi + 14], r13w setg bl cmp word ptr [rsi + 16], r13w - setg byte ptr [rsp + 128] # 1-byte Folded Spill + setg byte ptr [rsp + 192] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w setg cl cmp word ptr [rsi + 20], r13w @@ -36705,19 +37156,19 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 cmp word ptr [r11 + 26], r13w setg r12b cmp word ptr [r11 + 28], r13w - setg byte ptr [rsp + 160] # 1-byte Folded Spill + setg byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [r11 + 30], r13w setg dil cmp word ptr [r11 + 32], r13w - setg byte ptr [rsp + 72] # 1-byte Folded Spill + setg byte ptr [rsp + 88] # 1-byte Folded Spill cmp word ptr [r11 + 34], r13w - setg byte ptr [rsp + 144] # 1-byte Folded Spill + setg byte ptr [rsp + 160] # 1-byte Folded Spill cmp word ptr [r11 + 36], r13w - setg byte ptr [rsp + 112] # 1-byte Folded Spill + setg byte ptr [rsp + 104] # 1-byte Folded Spill cmp word ptr [r11 + 38], r13w setg byte ptr [rsp + 120] # 1-byte Folded Spill cmp word ptr [r11 + 40], r13w - setg byte ptr [rsp + 80] # 1-byte Folded Spill + setg byte ptr [rsp + 72] # 1-byte Folded Spill cmp word ptr [r11 + 42], r13w setg byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [r11 + 44], r13w @@ -36725,7 +37176,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 cmp word ptr [r11 + 46], r13w setg r15b cmp word ptr [r11 + 48], r13w - setg byte ptr [rsp + 32] # 1-byte Folded Spill + setg byte ptr [rsp + 24] # 1-byte Folded Spill cmp word ptr [r11 + 50], r13w setg byte ptr [rsp + 56] # 1-byte Folded Spill cmp word ptr [r11 + 52], r13w @@ -36733,11 +37184,11 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 cmp word ptr [r11 + 54], r13w setg byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [r11 + 56], r13w - setg byte ptr [rsp + 24] # 1-byte Folded Spill + setg byte ptr [rsp + 32] # 1-byte Folded Spill cmp word ptr [r11 + 58], r13w setg byte ptr [rsp + 16] # 1-byte Folded Spill cmp word ptr [r11 + 60], r13w - setg byte ptr [rsp] # 1-byte Folded Spill + setg byte ptr [rsp + 128] # 1-byte Folded Spill cmp word ptr [r11 + 62], r13w setg dl add r8b, r8b @@ -36748,36 +37199,36 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl r14b, 2 or r14b, r8b add cl, cl - add cl, byte ptr [rsp + 128] # 1-byte Folded Reload + add cl, byte ptr [rsp + 192] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 3 or al, r14b shl sil, 2 or sil, cl - movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload shl cl, 4 or cl, al mov r8d, ecx shl r9b, 3 or r9b, sil - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 5 or cl, r8b shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload shl sil, 6 shl dil, 7 or dil, sil or bl, cl or dil, r12b - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 72] # 1-byte Folded Reload + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload mov esi, ecx - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload shl cl, 2 or cl, sil mov esi, ecx @@ -36785,7 +37236,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl cl, 3 or cl, sil mov esi, ecx - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload shl cl, 4 or cl, sil mov esi, ecx @@ -36803,7 +37254,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 or r15b, sil movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, byte ptr [rsp + 24] # 1-byte Folded Reload mov ebx, eax movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 @@ -36813,14 +37264,14 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 shl dl, 7 or dl, bl @@ -36830,3003 +37281,1800 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 lea rsi, [r11 + 64] add rcx, 4 mov qword ptr [rsp + 8], rcx # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB7_128 -# %bb.129: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r15, qword ptr [rsp + 272] # 8-byte Reload - mov r14, qword ptr [rsp + 8] # 8-byte Reload - jmp .LBB7_130 -.LBB7_157: - mov r13, qword ptr [rdx] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB7_161 -# %bb.158: - movsxd rax, r9d - mov r9, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_159: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setg dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r9 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r9 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB7_159 -# %bb.160: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_161: - sar r10, 5 - cmp r11, 32 - jl .LBB7_165 -# %bb.162: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 240], r10 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - .p2align 4, 0x90 -.LBB7_163: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - setg byte ptr [rsp + 208] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 - setg r10b - cmp qword ptr [rsi + 16], r13 - setg dil - cmp qword ptr [rsi + 24], r13 - setg byte ptr [rsp + 176] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 - setg al - cmp qword ptr [rsi + 56], r13 - setg r14b - cmp qword ptr [rsi + 64], r13 - setg byte ptr [rsp + 128] # 1-byte Folded Spill - cmp qword ptr [rsi + 72], r13 - setg dl - cmp qword ptr [rsi + 80], r13 - setg r9b - cmp qword ptr [rsi + 88], r13 - setg r11b - cmp qword ptr [rsi + 96], r13 - setg bl - cmp qword ptr [rsi + 104], r13 - setg r12b - cmp qword ptr [rsi + 112], r13 - setg byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 120], r13 - setg cl - cmp qword ptr [rsi + 128], r13 - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp qword ptr [rsi + 136], r13 - setg byte ptr [rsp + 144] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp qword ptr [rsi + 152], r13 - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp qword ptr [rsi + 160], r13 - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 168], r13 - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp qword ptr [rsi + 176], r13 - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp qword ptr [rsi + 184], r13 - setg r15b - cmp qword ptr [rsi + 192], r13 - setg byte ptr [rsp + 32] # 1-byte Folded Spill - cmp qword ptr [rsi + 200], r13 - setg byte ptr [rsp + 56] # 1-byte Folded Spill - cmp qword ptr [rsi + 208], r13 - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp qword ptr [rsi + 216], r13 - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp qword ptr [rsi + 224], r13 - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp qword ptr [rsi + 232], r13 - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp qword ptr [rsi + 240], r13 - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp qword ptr [rsi + 248], r13 - setg r8b - add r10b, r10b - add r10b, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 6 - shl r14b, 7 - or r14b, al - shl dil, 2 - or dil, r10b - add dl, dl - add dl, byte ptr [rsp + 128] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov r10, qword ptr [rsp] # 8-byte Reload - shl r9b, 2 - or r9b, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 4 - or dl, al - mov edi, edx - shl r11b, 3 - or r11b, r9b - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - shl bl, 4 - or bl, r11b - shl r12b, 5 - or r12b, bl - movzx edi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or r14b, dl - or cl, r12b - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 72] # 1-byte Folded Reload - mov edi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 2 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl dl, 3 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, dil - mov edi, edx - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 5 - or dl, dil - mov byte ptr [r10], r14b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r10 + 1], cl - or r15b, dl - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 32] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload - shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload - shl cl, 5 - or cl, dl - movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl dl, 6 - shl r8b, 7 - or r8b, dl - or r8b, cl - mov byte ptr [r10 + 2], r15b - mov byte ptr [r10 + 3], r8b - add rsi, 256 - add r10, 4 - mov qword ptr [rsp], r10 # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB7_163 -# %bb.164: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 240] # 8-byte Reload -.LBB7_165: - shl r10, 5 - cmp r10, r11 - jge .LBB7_202 -# %bb.166: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB7_170 -# %bb.167: - xor r11d, r11d - jmp .LBB7_168 -.LBB7_172: - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - movss xmm11, dword ptr [rdx] # xmm11 = mem[0],zero,zero,zero - sub r9d, eax - je .LBB7_176 -# %bb.173: - movsxd rax, r9d - mov r14, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_174: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - ucomiss xmm0, xmm11 - seta dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB7_174 -# %bb.175: - add qword ptr [rsp], 1 # 8-byte Folded Spill -.LBB7_176: - sar r10, 5 - cmp r11, 32 - jl .LBB7_177 -# %bb.178: - cmp r10, 4 - jb .LBB7_179 -# %bb.180: - mov rax, r10 - shl rax, 7 - add rax, rsi - cmp qword ptr [rsp], rax # 8-byte Folded Reload - jae .LBB7_182 -# %bb.181: - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r10] - cmp rax, rsi - jbe .LBB7_182 -.LBB7_179: - xor eax, eax - mov rdx, rsi - mov r15, qword ptr [rsp] # 8-byte Reload -.LBB7_185: - mov qword ptr [rsp], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - sub r10, rax - mov qword ptr [rsp + 208], r10 # 8-byte Spill - .p2align 4, 0x90 -.LBB7_186: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero - movss xmm1, dword ptr [rdx + 4] # xmm1 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - seta byte ptr [rsp + 24] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - seta bl - movss xmm0, dword ptr [rdx + 8] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 12] # xmm0 = mem[0],zero,zero,zero - seta r13b - ucomiss xmm0, xmm11 - seta r12b - movss xmm0, dword ptr [rdx + 16] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 20] # xmm0 = mem[0],zero,zero,zero - seta byte ptr [rsp + 80] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - seta byte ptr [rsp + 96] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 24] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 28] # xmm0 = mem[0],zero,zero,zero - seta byte ptr [rsp + 88] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - seta byte ptr [rsp + 64] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 32] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 36] # xmm0 = mem[0],zero,zero,zero - seta byte ptr [rsp + 16] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - seta al - movss xmm0, dword ptr [rdx + 40] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 44] # xmm0 = mem[0],zero,zero,zero - seta byte ptr [rsp + 40] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - seta byte ptr [rsp + 32] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 48] # xmm0 = mem[0],zero,zero,zero - movss xmm2, dword ptr [rdx + 52] # xmm2 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - movss xmm4, dword ptr [rdx + 56] # xmm4 = mem[0],zero,zero,zero - movss xmm5, dword ptr [rdx + 60] # xmm5 = mem[0],zero,zero,zero - seta byte ptr [rsp + 120] # 1-byte Folded Spill - movss xmm8, dword ptr [rdx + 64] # xmm8 = mem[0],zero,zero,zero - movss xmm9, dword ptr [rdx + 68] # xmm9 = mem[0],zero,zero,zero - ucomiss xmm2, xmm11 - movss xmm10, dword ptr [rdx + 72] # xmm10 = mem[0],zero,zero,zero - movss xmm12, dword ptr [rdx + 76] # xmm12 = mem[0],zero,zero,zero - seta byte ptr [rsp + 144] # 1-byte Folded Spill - movss xmm13, dword ptr [rdx + 80] # xmm13 = mem[0],zero,zero,zero - movss xmm14, dword ptr [rdx + 84] # xmm14 = mem[0],zero,zero,zero - ucomiss xmm4, xmm11 - movss xmm4, dword ptr [rdx + 88] # xmm4 = mem[0],zero,zero,zero - movss xmm0, dword ptr [rdx + 92] # xmm0 = mem[0],zero,zero,zero - seta byte ptr [rsp + 128] # 1-byte Folded Spill - movss xmm1, dword ptr [rdx + 96] # xmm1 = mem[0],zero,zero,zero - movss xmm2, dword ptr [rdx + 100] # xmm2 = mem[0],zero,zero,zero - ucomiss xmm5, xmm11 - movss xmm5, dword ptr [rdx + 104] # xmm5 = mem[0],zero,zero,zero - movss xmm3, dword ptr [rdx + 108] # xmm3 = mem[0],zero,zero,zero - seta r11b - movss xmm6, dword ptr [rdx + 112] # xmm6 = mem[0],zero,zero,zero - movss xmm7, dword ptr [rdx + 116] # xmm7 = mem[0],zero,zero,zero - ucomiss xmm8, xmm11 - seta byte ptr [rsp + 176] # 1-byte Folded Spill - ucomiss xmm9, xmm11 - seta cl - ucomiss xmm10, xmm11 - seta sil - ucomiss xmm12, xmm11 - seta r8b - ucomiss xmm13, xmm11 - seta r10b - ucomiss xmm14, xmm11 - seta r14b - ucomiss xmm4, xmm11 - seta byte ptr [rsp + 160] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - seta r9b - ucomiss xmm1, xmm11 - seta byte ptr [rsp + 104] # 1-byte Folded Spill - ucomiss xmm2, xmm11 - seta r15b - ucomiss xmm5, xmm11 - seta byte ptr [rsp + 112] # 1-byte Folded Spill - ucomiss xmm3, xmm11 - seta byte ptr [rsp + 72] # 1-byte Folded Spill - ucomiss xmm6, xmm11 - seta byte ptr [rsp + 56] # 1-byte Folded Spill - ucomiss xmm7, xmm11 - movss xmm0, dword ptr [rdx + 120] # xmm0 = mem[0],zero,zero,zero - seta byte ptr [rsp + 48] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - seta byte ptr [rsp + 8] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 124] # xmm0 = mem[0],zero,zero,zero - sub rdx, -128 - ucomiss xmm0, xmm11 - seta dil - add bl, bl - add bl, byte ptr [rsp + 24] # 1-byte Folded Reload - shl r13b, 2 - or r13b, bl - shl r12b, 3 - or r12b, r13b - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, r12b - mov r12d, ebx - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl bl, 5 - or bl, r12b - movzx r12d, byte ptr [rsp + 88] # 1-byte Folded Reload - shl r12b, 6 - movzx r13d, byte ptr [rsp + 64] # 1-byte Folded Reload - shl r13b, 7 - or r13b, r12b - add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload - movzx r12d, byte ptr [rsp + 40] # 1-byte Folded Reload - shl r12b, 2 - or r12b, al - mov eax, r12d - movzx r12d, byte ptr [rsp + 32] # 1-byte Folded Reload - shl r12b, 3 - or r12b, al - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 4 - or al, r12b - or r13b, bl - movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl bl, 5 - or bl, al - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - add cl, cl - add cl, byte ptr [rsp + 176] # 1-byte Folded Reload - shl sil, 2 - or sil, cl - shl r8b, 3 - or r8b, sil - shl r10b, 4 - or r10b, r8b - shl r14b, 5 - or r14b, r10b - or r11b, bl - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 6 - shl r9b, 7 - or r9b, al - mov rsi, qword ptr [rsp] # 8-byte Reload - mov byte ptr [rsi], r13b - or r9b, r14b - add r15b, r15b - add r15b, byte ptr [rsp + 104] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 2 - or al, r15b - mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 4 - or al, cl - movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl bl, 5 - or bl, al - mov byte ptr [rsi + 1], r11b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 6 - shl dil, 7 - or dil, al - mov byte ptr [rsi + 2], r9b - or dil, bl - mov byte ptr [rsi + 3], dil - add rsi, 4 - mov qword ptr [rsp], rsi # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB7_186 -# %bb.187: - mov r15, qword ptr [rsp] # 8-byte Reload - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload - jmp .LBB7_188 -.LBB7_9: - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 96], rax # 8-byte Spill -.LBB7_90: - shl r10, 5 - cmp r10, r11 - jge .LBB7_202 -# %bb.91: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB7_93 -# %bb.92: - xor r9d, r9d - jmp .LBB7_96 -.LBB7_61: - mov rax, qword ptr [rsp] # 8-byte Reload - mov qword ptr [rsp + 120], rax # 8-byte Spill - mov r12, rsi -.LBB7_72: - shl r15, 5 - cmp r15, r11 - jge .LBB7_202 -# %bb.73: - mov r8, r11 - sub r8, r15 - not r15 - add r15, r11 - jne .LBB7_75 -# %bb.74: - xor eax, eax - jmp .LBB7_78 -.LBB7_119: - mov r14, qword ptr [rsp] # 8-byte Reload -.LBB7_130: - shl r15, 5 - cmp r15, r11 - jge .LBB7_202 -# %bb.131: - mov r8, r11 - sub r8, r15 - not r15 - add r15, r11 - jne .LBB7_135 -# %bb.132: - xor r15d, r15d - jmp .LBB7_133 -.LBB7_177: - mov r15, qword ptr [rsp] # 8-byte Reload - mov rdx, rsi -.LBB7_188: - shl r10, 5 - cmp r10, r11 - jge .LBB7_202 -# %bb.189: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB7_193 -# %bb.190: - xor r11d, r11d - jmp .LBB7_191 -.LBB7_155: - mov r9, r8 - and r9, -2 - xor r11d, r11d - mov r14, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_156: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rsi] - sbb edi, edi - mov rdx, r11 - shr rdx, 3 - movzx r10d, byte ptr [r14 + rdx] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r14 + rdx], al - add r11, 2 - cmp r13, qword ptr [rsi + 8] - lea rsi, [rsi + 16] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rdx], bl - cmp r9, r11 - jne .LBB7_156 -.LBB7_40: - test r8b, 1 - je .LBB7_202 -# %bb.41: - cmp r13, qword ptr [rsi] - jmp .LBB7_111 -.LBB7_153: - mov r10, r8 - and r10, -2 - xor r11d, r11d - mov r14, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_154: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - setg al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - setg al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r10, r11 - jne .LBB7_154 -.LBB7_150: - test r8b, 1 - je .LBB7_202 -# %bb.151: - cmp dword ptr [rsi], r13d - jmp .LBB7_152 -.LBB7_93: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r11, qword ptr [rsp + 96] # 8-byte Reload + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_146 +# %bb.147: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + jmp .LBB7_148 +.LBB7_177: + mov r13, qword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB7_183 +# %bb.178: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_181 +# %bb.179: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB7_94: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r12b +.LBB7_180: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 setg bl neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r11 + rdi] + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r12 + rdi] xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - cmp byte ptr [rsi + rax + 1], r12b - lea r9, [rax + 2] - setg bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - cmp r10, r9 - jne .LBB7_94 -# %bb.95: - add rsi, r9 -.LBB7_96: - test r8b, 1 - je .LBB7_202 -# %bb.97: - cmp byte ptr [rsi], r12b - setg al - neg al - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and r9b, 7 - mov bl, 1 - mov ecx, r9d - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r8 + rdx], bl - jmp .LBB7_202 -.LBB7_75: - mov r9, r8 - and r9, -2 - xor eax, eax - mov r11, qword ptr [rsp + 120] # 8-byte Reload + xor al, r9b + mov byte ptr [r12 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB7_180 +.LBB7_181: + sub r15, r8 + je .LBB7_226 +# %bb.182: + add r12, 1 +.LBB7_183: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_187 +# %bb.184: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB7_76: # =>This Inner Loop Header: Depth=1 - cmp r10b, byte ptr [r12 + rax] - sbb esi, esi - mov rdi, rax - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx ebx, byte ptr [r11 + rdi] - xor sil, bl - and dl, sil - xor dl, bl - mov byte ptr [r11 + rdi], dl - cmp r10b, byte ptr [r12 + rax + 1] - lea rax, [rax + 2] - sbb esi, esi - xor sil, dl - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, sil - xor bl, dl - mov byte ptr [r11 + rdi], bl - cmp r9, rax - jne .LBB7_76 -# %bb.77: - add r12, rax -.LBB7_78: - test r8b, 1 - je .LBB7_202 -# %bb.79: - cmp r10b, byte ptr [r12] - sbb edx, edx - mov rsi, rax - shr rsi, 3 - mov r8, qword ptr [rsp + 120] # 8-byte Reload - mov dil, byte ptr [r8 + rsi] - and al, 7 - mov bl, 1 - mov ecx, eax - shl bl, cl - xor dl, dil - and bl, dl - xor bl, dil - mov byte ptr [r8 + rsi], bl - jmp .LBB7_202 -.LBB7_137: - mov r9, r8 - and r9, -2 +.LBB7_185: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + cmp qword ptr [rsi], r13 + setg byte ptr [rsp + 208] # 1-byte Folded Spill + cmp qword ptr [rsi + 8], r13 + setg dil + cmp qword ptr [rsi + 16], r13 + setg r14b + cmp qword ptr [rsi + 24], r13 + setg byte ptr [rsp + 176] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp qword ptr [rsi + 40], r13 + setg byte ptr [rsp + 80] # 1-byte Folded Spill + cmp qword ptr [rsi + 48], r13 + setg al + cmp qword ptr [rsi + 56], r13 + setg bl + cmp qword ptr [rsi + 64], r13 + setg byte ptr [rsp + 192] # 1-byte Folded Spill + cmp qword ptr [rsi + 72], r13 + setg cl + cmp qword ptr [rsi + 80], r13 + setg r9b + cmp qword ptr [rsi + 88], r13 + setg r10b + cmp qword ptr [rsi + 96], r13 + setg r11b + cmp qword ptr [rsi + 104], r13 + setg r12b + cmp qword ptr [rsi + 112], r13 + setg byte ptr [rsp + 144] # 1-byte Folded Spill + cmp qword ptr [rsi + 120], r13 + setg dl + cmp qword ptr [rsi + 128], r13 + setg byte ptr [rsp + 88] # 1-byte Folded Spill + cmp qword ptr [rsi + 136], r13 + setg byte ptr [rsp + 160] # 1-byte Folded Spill + cmp qword ptr [rsi + 144], r13 + setg byte ptr [rsp + 104] # 1-byte Folded Spill + cmp qword ptr [rsi + 152], r13 + setg byte ptr [rsp + 120] # 1-byte Folded Spill + cmp qword ptr [rsi + 160], r13 + setg byte ptr [rsp + 72] # 1-byte Folded Spill + cmp qword ptr [rsi + 168], r13 + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp qword ptr [rsi + 176], r13 + setg byte ptr [rsp + 64] # 1-byte Folded Spill + cmp qword ptr [rsi + 184], r13 + setg r15b + cmp qword ptr [rsi + 192], r13 + setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp qword ptr [rsi + 200], r13 + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp qword ptr [rsi + 208], r13 + setg byte ptr [rsp + 40] # 1-byte Folded Spill + cmp qword ptr [rsi + 216], r13 + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp qword ptr [rsi + 224], r13 + setg byte ptr [rsp + 32] # 1-byte Folded Spill + cmp qword ptr [rsi + 232], r13 + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp qword ptr [rsi + 240], r13 + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp qword ptr [rsi + 248], r13 + setg r8b + add dil, dil + add dil, byte ptr [rsp + 208] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl r9b, 2 + or r9b, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r10b, 3 + or r10b, r9b + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r11b, 4 + or r11b, r10b + shl r12b, 5 + or r12b, r11b + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dil, 6 + shl dl, 7 + or dl, dil + or bl, cl + or dl, r12b + mov r12, qword ptr [rsp + 128] # 8-byte Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r12], bl + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + shl r15b, 7 + or r15b, bl + mov byte ptr [r12 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 24] # 1-byte Folded Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl cl, 3 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 4 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload + shl cl, 5 + or cl, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl r8b, 7 + or r8b, dl + or r8b, cl + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], r8b + add rsi, 256 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_185 +# %bb.186: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload +.LBB7_187: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_226 +# %bb.188: + or rax, 1 + cmp r15, rax + jne .LBB7_192 +# %bb.189: xor r11d, r11d - mov r14, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_138: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rsi] - sbb edi, edi - mov rdx, r11 - shr rdx, 3 - movzx r10d, byte ptr [r14 + rdx] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r14 + rdx], al - add r11, 2 - cmp r13d, dword ptr [rsi + 4] - lea rsi, [rsi + 8] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rdx], bl - cmp r9, r11 - jne .LBB7_138 -.LBB7_24: - test r8b, 1 - je .LBB7_202 -# %bb.25: - cmp r13d, dword ptr [rsi] - jmp .LBB7_111 -.LBB7_196: - mov r9, r8 - and r9, -2 - xor r10d, r10d - mov r11, qword ptr [rsp] # 8-byte Reload + jmp .LBB7_190 +.LBB7_194: + mov r14d, dword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB7_200 +# %bb.195: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_198 +# %bb.196: + movsxd rdx, r9d + movd xmm0, r14d + mov r11, r8 .p2align 4, 0x90 .LBB7_197: # =>This Inner Loop Header: Depth=1 - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - seta al - neg al - mov rdi, r10 - shr rdi, 3 - mov ecx, r10d - and cl, 6 - mov bl, 1 - shl bl, cl - movzx edx, byte ptr [r11 + rdi] - xor al, dl - and bl, al - xor bl, dl - mov byte ptr [r11 + rdi], bl - add r10, 2 - movsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero - add rsi, 16 - ucomisd xmm1, xmm0 - seta al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r11 + rdi], dl - cmp r9, r10 + movss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + add rsi, 4 + ucomiss xmm1, xmm0 + seta bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + add r11, -1 jne .LBB7_197 .LBB7_198: - test r8b, 1 - je .LBB7_202 + sub r15, r8 + je .LBB7_226 # %bb.199: - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - seta al - neg al - mov rdx, r10 - shr rdx, 3 - mov rdi, qword ptr [rsp] # 8-byte Reload - mov sil, byte ptr [rdi + rdx] - and r10b, 7 - mov bl, 1 - mov ecx, r10d - jmp .LBB7_200 -.LBB7_112: - mov r9, r8 - and r9, -2 - xor r11d, r11d - mov r14, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_113: # =>This Inner Loop Header: Depth=1 - cmp r13w, word ptr [rsi] - sbb edi, edi - mov rdx, r11 - shr rdx, 3 - movzx r10d, byte ptr [r14 + rdx] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r14 + rdx], al - add r11, 2 - cmp r13w, word ptr [rsi + 2] - lea rsi, [rsi + 4] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rdx], bl - cmp r9, r11 - jne .LBB7_113 -.LBB7_109: - test r8b, 1 - je .LBB7_202 -# %bb.110: - cmp r13w, word ptr [rsi] -.LBB7_111: - sbb eax, eax - mov rdx, r11 - shr rdx, 3 - mov rdi, qword ptr [rsp] # 8-byte Reload - mov sil, byte ptr [rdi + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, sil - and bl, al - jmp .LBB7_201 -.LBB7_170: - mov r10, r8 - and r10, -2 - xor r11d, r11d - mov r14, qword ptr [rsp] # 8-byte Reload - .p2align 4, 0x90 -.LBB7_171: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - setg al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] - setg al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r10, r11 - jne .LBB7_171 -.LBB7_168: - test r8b, 1 - je .LBB7_202 -# %bb.169: - cmp qword ptr [rsi], r13 -.LBB7_152: - setg al - neg al - mov rdx, r11 - shr rdx, 3 - mov rdi, qword ptr [rsp] # 8-byte Reload - mov sil, byte ptr [rdi + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d + add r12, 1 .LBB7_200: - shl bl, cl - xor al, sil - and bl, al -.LBB7_201: - xor bl, sil - mov byte ptr [rdi + rdx], bl -.LBB7_202: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.LBB7_135: - mov r9, r8 - and r9, -2 - xor r15d, r15d - mov r11d, dword ptr [rsp + 240] # 4-byte Reload - .p2align 4, 0x90 -.LBB7_136: # =>This Inner Loop Header: Depth=1 - mov rax, rsi - cmp word ptr [rsi], r11w - setg dl - neg dl - mov rdi, r15 - shr rdi, 3 - movzx r10d, byte ptr [r14 + rdi] - mov ecx, r15d - and cl, 6 - mov bl, 1 - shl bl, cl - xor dl, r10b - and bl, dl - xor bl, r10b - mov byte ptr [r14 + rdi], bl - add r15, 2 - cmp word ptr [rsi + 2], r11w - lea rsi, [rsi + 4] - setg dl - neg dl - xor dl, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, bl - mov byte ptr [r14 + rdi], al - cmp r9, r15 - jne .LBB7_136 -.LBB7_133: - test r8b, 1 - je .LBB7_202 -# %bb.134: - mov eax, dword ptr [rsp + 240] # 4-byte Reload - cmp word ptr [rsi], ax - setg al - neg al - mov rdx, r15 - shr rdx, 3 - mov dil, byte ptr [r14 + rdx] - and r15b, 7 - mov bl, 1 - mov ecx, r15d - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r14 + rdx], bl - jmp .LBB7_202 -.LBB7_193: - mov r9, r8 - and r9, -2 - xor r11d, r11d - mov r10, r15 - mov rsi, rdx + lea rdi, [r15 + 31] + test r15, r15 + cmovns rdi, r15 + sar rdi, 5 + cmp r15, 32 + jl .LBB7_201 +# %bb.202: + movd xmm11, r14d + cmp rdi, 4 + jb .LBB7_203 +# %bb.204: + mov rax, rdi + shl rax, 7 + add rax, rsi + cmp r12, rax + jae .LBB7_206 +# %bb.205: + lea rax, [r12 + 4*rdi] + cmp rax, rsi + jbe .LBB7_206 +.LBB7_203: + xor eax, eax + mov rcx, rsi + mov r10, r12 +.LBB7_209: + mov qword ptr [rsp + 128], r10 # 8-byte Spill + mov dword ptr [rsp + 256], r14d # 4-byte Spill + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 320], rdi # 8-byte Spill + sub rdi, rax + mov qword ptr [rsp + 224], rdi # 8-byte Spill .p2align 4, 0x90 -.LBB7_194: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero +.LBB7_210: # =>This Inner Loop Header: Depth=1 + movss xmm0, dword ptr [rcx] # xmm0 = mem[0],zero,zero,zero + movss xmm1, dword ptr [rcx + 4] # xmm1 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + seta byte ptr [rsp + 24] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + seta r13b + movss xmm0, dword ptr [rcx + 8] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 12] # xmm0 = mem[0],zero,zero,zero + seta r12b + ucomiss xmm0, xmm11 + seta byte ptr [rsp + 40] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 16] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 20] # xmm0 = mem[0],zero,zero,zero seta bl - neg bl - mov rdi, r11 - shr rdi, 3 - mov ecx, r11d - and cl, 6 - mov dl, 1 - shl dl, cl - movzx eax, byte ptr [r10 + rdi] - xor bl, al - and dl, bl - xor dl, al - mov byte ptr [r10 + rdi], dl - add r11, 2 - movss xmm0, dword ptr [rsi + 4] # xmm0 = mem[0],zero,zero,zero - add rsi, 8 ucomiss xmm0, xmm11 - seta al - neg al - xor al, dl - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, al - xor bl, dl - mov byte ptr [r10 + rdi], bl - cmp r9, r11 - jne .LBB7_194 -# %bb.195: - mov rdx, rsi -.LBB7_191: - test r8b, 1 - je .LBB7_202 -# %bb.192: - movss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero + seta byte ptr [rsp + 8] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 24] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 28] # xmm0 = mem[0],zero,zero,zero + seta byte ptr [rsp + 72] # 1-byte Folded Spill + ucomiss xmm0, xmm11 + seta byte ptr [rsp + 80] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 32] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 36] # xmm0 = mem[0],zero,zero,zero + seta byte ptr [rsp + 32] # 1-byte Folded Spill ucomiss xmm0, xmm11 + seta byte ptr [rsp + 56] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 40] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 44] # xmm0 = mem[0],zero,zero,zero + seta byte ptr [rsp + 64] # 1-byte Folded Spill + ucomiss xmm0, xmm11 + seta byte ptr [rsp + 208] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 48] # xmm0 = mem[0],zero,zero,zero + movss xmm3, dword ptr [rcx + 52] # xmm3 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 56] # xmm0 = mem[0],zero,zero,zero + movss xmm5, dword ptr [rcx + 60] # xmm5 = mem[0],zero,zero,zero + seta byte ptr [rsp + 120] # 1-byte Folded Spill + movss xmm8, dword ptr [rcx + 64] # xmm8 = mem[0],zero,zero,zero + movss xmm9, dword ptr [rcx + 68] # xmm9 = mem[0],zero,zero,zero + ucomiss xmm3, xmm11 + movss xmm10, dword ptr [rcx + 72] # xmm10 = mem[0],zero,zero,zero + movss xmm12, dword ptr [rcx + 76] # xmm12 = mem[0],zero,zero,zero + seta byte ptr [rsp + 160] # 1-byte Folded Spill + movss xmm13, dword ptr [rcx + 80] # xmm13 = mem[0],zero,zero,zero + movss xmm14, dword ptr [rcx + 84] # xmm14 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 88] # xmm0 = mem[0],zero,zero,zero + movss xmm1, dword ptr [rcx + 92] # xmm1 = mem[0],zero,zero,zero + seta byte ptr [rsp + 192] # 1-byte Folded Spill + movss xmm2, dword ptr [rcx + 96] # xmm2 = mem[0],zero,zero,zero + movss xmm3, dword ptr [rcx + 100] # xmm3 = mem[0],zero,zero,zero + ucomiss xmm5, xmm11 + movss xmm5, dword ptr [rcx + 104] # xmm5 = mem[0],zero,zero,zero + movss xmm4, dword ptr [rcx + 108] # xmm4 = mem[0],zero,zero,zero + seta r10b + movss xmm6, dword ptr [rcx + 112] # xmm6 = mem[0],zero,zero,zero + movss xmm7, dword ptr [rcx + 116] # xmm7 = mem[0],zero,zero,zero + ucomiss xmm8, xmm11 + seta byte ptr [rsp + 176] # 1-byte Folded Spill + ucomiss xmm9, xmm11 seta al - neg al - mov rdx, r11 - shr rdx, 3 - mov dil, byte ptr [r15 + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r15 + rdx], bl - jmp .LBB7_202 -.LBB7_84: - and r10, -16 - mov rax, r10 - shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 232], r10 # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r10] - mov qword ptr [rsp + 96], rax # 8-byte Spill - movzx eax, r12b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 144], xmm1 # 16-byte Spill - xor eax, eax - .p2align 4, 0x90 -.LBB7_85: # =>This Inner Loop Header: Depth=1 - mov rdi, rax - mov qword ptr [rsp + 240], rax # 8-byte Spill - shl rdi, 5 - mov r12, rdi - mov rdx, rdi - mov r11, rdi - mov r9, rdi - mov rax, rdi - mov r8, rdi - mov r14, rdi - mov r10, rdi - mov r15, rdi - mov rbx, rdi - mov qword ptr [rsp + 56], rdi # 8-byte Spill - movzx ecx, byte ptr [rsi + rdi] - movd xmm15, ecx - movzx ecx, byte ptr [rsi + rdi + 1] - movd xmm5, ecx - movzx ecx, byte ptr [rsi + rdi + 2] - movd xmm6, ecx - movzx ecx, byte ptr [rsi + rdi + 3] - movd xmm2, ecx - movzx ecx, byte ptr [rsi + rdi + 4] - movd xmm1, ecx - movzx ecx, byte ptr [rsi + rdi + 5] - movd xmm8, ecx - movzx ecx, byte ptr [rsi + rdi + 6] - movd xmm3, ecx - movzx ecx, byte ptr [rsi + rdi + 7] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdi + 8] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 304], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdi + 9] - movd xmm10, ecx - movzx ecx, byte ptr [rsi + rdi + 10] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + rdi + 11] - movd xmm11, ecx - movzx ecx, byte ptr [rsi + rdi + 12] - movd xmm13, ecx - movzx ecx, byte ptr [rsi + rdi + 13] - movd xmm12, ecx - movzx ecx, byte ptr [rsi + rdi + 14] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill - mov qword ptr [rsp + 40], rdi # 8-byte Spill - mov r13, rdi - or r13, 32 - mov qword ptr [rsp + 32], r13 # 8-byte Spill - or r12, 64 - or rdx, 96 - mov qword ptr [rsp + 104], rdx # 8-byte Spill - or r11, 128 - mov qword ptr [rsp + 64], r11 # 8-byte Spill - mov r11, rdi - or r11, 160 - or rax, 192 - mov qword ptr [rsp + 80], rax # 8-byte Spill - or r9, 224 - or r14, 256 - mov qword ptr [rsp + 128], r14 # 8-byte Spill - or r10, 288 - mov qword ptr [rsp + 120], r10 # 8-byte Spill - or r8, 320 - mov qword ptr [rsp + 72], r8 # 8-byte Spill - or rbx, 352 - mov qword ptr [rsp + 88], rbx # 8-byte Spill - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - or rcx, 384 - mov qword ptr [rsp + 56], rcx # 8-byte Spill - mov rax, rdi - or rax, 416 - mov qword ptr [rsp + 16], rax # 8-byte Spill - mov rax, rdi - or rax, 448 - mov qword ptr [rsp + 24], rax # 8-byte Spill - mov rax, rdi - or rax, 480 - mov qword ptr [rsp + 48], rax # 8-byte Spill - pinsrb xmm15, byte ptr [rsi + r13], 1 - pinsrb xmm15, byte ptr [rsi + r12], 2 - pinsrb xmm15, byte ptr [rsi + rdx], 3 - mov r13, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r13], 4 - mov rdi, r11 - pinsrb xmm15, byte ptr [rsi + r11], 5 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r15], 6 - pinsrb xmm15, byte ptr [rsi + r9], 7 - pinsrb xmm15, byte ptr [rsi + r14], 8 - pinsrb xmm15, byte ptr [rsi + r10], 9 - pinsrb xmm15, byte ptr [rsi + r8], 10 - pinsrb xmm15, byte ptr [rsi + rbx], 11 - pinsrb xmm15, byte ptr [rsi + rcx], 12 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx], 13 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx], 14 - pinsrb xmm15, byte ptr [rsi + rax], 15 - mov r11, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r11 + 1], 1 - pinsrb xmm5, byte ptr [rsi + r12 + 1], 2 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r11 + 1], 3 - pinsrb xmm5, byte ptr [rsi + r13 + 1], 4 - pinsrb xmm5, byte ptr [rsi + rdi + 1], 5 - pinsrb xmm5, byte ptr [rsi + r15 + 1], 6 - pinsrb xmm5, byte ptr [rsi + r9 + 1], 7 - mov r13, r9 - pinsrb xmm5, byte ptr [rsi + r14 + 1], 8 - pinsrb xmm5, byte ptr [rsi + r10 + 1], 9 - pinsrb xmm5, byte ptr [rsi + r8 + 1], 10 - pinsrb xmm5, byte ptr [rsi + rbx + 1], 11 - pinsrb xmm5, byte ptr [rsi + rcx + 1], 12 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rcx + 1], 13 - pinsrb xmm5, byte ptr [rsi + rdx + 1], 14 - pinsrb xmm5, byte ptr [rsi + rax + 1], 15 - movdqa xmm9, xmmword ptr [rsp + 144] # 16-byte Reload - pcmpgtb xmm5, xmm9 - movdqa xmm7, xmm5 - movdqa xmm4, xmmword ptr [rip + .LCPI7_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm7, xmm4 - psubb xmm7, xmm5 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + rax + 15] - movd xmm14, ebx - pcmpgtb xmm15, xmm9 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r14 + 2], 1 - mov rcx, r12 - pinsrb xmm6, byte ptr [rsi + r12 + 2], 2 - mov rdx, r11 - pinsrb xmm6, byte ptr [rsi + r11 + 2], 3 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r8 + 2], 4 - pinsrb xmm6, byte ptr [rsi + rdi + 2], 5 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r12 + 2], 6 - mov qword ptr [rsp + 192], r9 # 8-byte Spill - pinsrb xmm6, byte ptr [rsi + r9 + 2], 7 + ucomiss xmm10, xmm11 + seta sil + ucomiss xmm12, xmm11 + seta r8b + ucomiss xmm13, xmm11 + seta r9b + ucomiss xmm14, xmm11 + seta r11b + ucomiss xmm0, xmm11 + seta byte ptr [rsp + 144] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + seta r15b + ucomiss xmm2, xmm11 + seta byte ptr [rsp + 112] # 1-byte Folded Spill + ucomiss xmm3, xmm11 + seta r14b + ucomiss xmm5, xmm11 + seta byte ptr [rsp + 104] # 1-byte Folded Spill + ucomiss xmm4, xmm11 + seta byte ptr [rsp + 88] # 1-byte Folded Spill + ucomiss xmm6, xmm11 + seta byte ptr [rsp + 96] # 1-byte Folded Spill + ucomiss xmm7, xmm11 + movss xmm0, dword ptr [rcx + 120] # xmm0 = mem[0],zero,zero,zero + seta byte ptr [rsp + 48] # 1-byte Folded Spill + ucomiss xmm0, xmm11 + seta byte ptr [rsp + 16] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 124] # xmm0 = mem[0],zero,zero,zero + sub rcx, -128 + ucomiss xmm0, xmm11 + seta dil + add r13b, r13b + add r13b, byte ptr [rsp + 24] # 1-byte Folded Reload + shl r12b, 2 + or r12b, r13b + mov r13d, r12d + movzx r12d, byte ptr [rsp + 40] # 1-byte Folded Reload + shl r12b, 3 + or r12b, r13b + shl bl, 4 + or bl, r12b + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 5 + or dl, bl + mov byte ptr [rsp + 8], dl # 1-byte Spill + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl bl, 6 + movzx r12d, byte ptr [rsp + 80] # 1-byte Folded Reload + shl r12b, 7 + or r12b, bl + movzx r13d, byte ptr [rsp + 56] # 1-byte Folded Reload + add r13b, r13b + add r13b, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 2 + or bl, r13b + mov r13d, ebx + movzx ebx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl bl, 3 + or bl, r13b + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 4 + or dl, bl + or r12b, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx r13d, byte ptr [rsp + 160] # 1-byte Folded Reload + shl r13b, 5 + or r13b, dl + movzx edx, byte ptr [rsp + 192] # 1-byte Folded Reload + shl dl, 6 + shl r10b, 7 + or r10b, dl + add al, al + add al, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 2 + or sil, al + shl r8b, 3 + or r8b, sil + shl r9b, 4 + or r9b, r8b + shl r11b, 5 + or r11b, r9b + or r10b, r13b + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + shl al, 6 + shl r15b, 7 + or r15b, al + mov rsi, qword ptr [rsp + 128] # 8-byte Reload + mov byte ptr [rsi], r12b + or r15b, r11b + add r14b, r14b + add r14b, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 2 + or al, r14b + mov edx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov ebx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 4 + or al, bl + movzx ebx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl bl, 5 + or bl, al + mov byte ptr [rsi + 1], r10b + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 6 + shl dil, 7 + or dil, al + mov byte ptr [rsi + 2], r15b + or dil, bl + mov byte ptr [rsi + 3], dil + add rsi, 4 + mov qword ptr [rsp + 128], rsi # 8-byte Spill + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_210 +# %bb.211: mov r10, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r10 + 2], 8 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r11 + 2], 9 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r15 + 2], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 2], 11 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 2], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 2], 13 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 2], 14 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rbx + 2], 15 - pand xmm15, xmm4 - pcmpgtb xmm6, xmm9 - movdqa xmm0, xmmword ptr [rip + .LCPI7_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm6, xmm0 - por xmm6, xmm15 - movzx ebx, byte ptr [rsi + rax + 16] - movd xmm15, ebx - pinsrb xmm2, byte ptr [rsi + r14 + 3], 1 - pinsrb xmm2, byte ptr [rsi + rcx + 3], 2 - mov rbx, rdx - pinsrb xmm2, byte ptr [rsi + rdx + 3], 3 - mov r9, r8 - pinsrb xmm2, byte ptr [rsi + r8 + 3], 4 - mov rdx, rdi - mov qword ptr [rsp + 112], rdi # 8-byte Spill - pinsrb xmm2, byte ptr [rsi + rdi + 3], 5 - mov rdi, r12 - pinsrb xmm2, byte ptr [rsi + r12 + 3], 6 - pinsrb xmm2, byte ptr [rsi + r13 + 3], 7 - pinsrb xmm2, byte ptr [rsi + r10 + 3], 8 - pinsrb xmm2, byte ptr [rsi + r11 + 3], 9 - pinsrb xmm2, byte ptr [rsi + r15 + 3], 10 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r12 + 3], 11 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r13 + 3], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 3], 13 - mov r8, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r8 + 3], 14 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r8 + 3], 15 - pinsrb xmm1, byte ptr [rsi + r14 + 4], 1 - pinsrb xmm1, byte ptr [rsi + rcx + 4], 2 - pinsrb xmm1, byte ptr [rsi + rbx + 4], 3 - pinsrb xmm1, byte ptr [rsi + r9 + 4], 4 - pinsrb xmm1, byte ptr [rsi + rdx + 4], 5 - pinsrb xmm1, byte ptr [rsi + rdi + 4], 6 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rax + 4], 7 - pinsrb xmm1, byte ptr [rsi + r10 + 4], 8 - pinsrb xmm1, byte ptr [rsi + r11 + 4], 9 - pinsrb xmm1, byte ptr [rsi + r15 + 4], 10 - pinsrb xmm1, byte ptr [rsi + r12 + 4], 11 - pinsrb xmm1, byte ptr [rsi + r13 + 4], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rax + 4], 13 - mov r14, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r14 + 4], 14 - mov rdx, r8 - pinsrb xmm1, byte ptr [rsi + r8 + 4], 15 - mov r15, r8 - por xmm6, xmm7 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + rdx + 17] - movd xmm0, ebx - pcmpgtb xmm2, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI7_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm2, xmm5 - pcmpgtb xmm1, xmm9 - movdqa xmm5, xmmword ptr [rip + .LCPI7_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm1, xmm5 - por xmm1, xmm2 - movzx ebx, byte ptr [rsi + rdx + 18] - movd xmm5, ebx - mov r8, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r8 + 5], 1 - pinsrb xmm8, byte ptr [rsi + rcx + 5], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdi + 5], 3 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r9 + 5], 4 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdx + 5], 5 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r10 + 5], 6 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r11 + 5], 7 + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r14d, dword ptr [rsp + 256] # 4-byte Reload + mov rdi, qword ptr [rsp + 320] # 8-byte Reload + jmp .LBB7_212 +.LBB7_58: + mov r11b, byte ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + mov byte ptr [rsp + 280], r11b # 1-byte Spill + je .LBB7_59 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_61 +# %bb.67: + movsxd rdx, r9d + mov rax, r8 + .p2align 4, 0x90 +.LBB7_68: # =>This Inner Loop Header: Depth=1 + lea r14, [rsi + 1] + cmp r11b, byte ptr [rsi] + sbb esi, esi + lea rbx, [rdx + 7] + test rdx, rdx + cmovns rbx, rdx + sar rbx, 3 + movzx r9d, byte ptr [r12 + rbx] + xor sil, r9b + lea r10d, [8*rbx] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, sil + xor dil, r9b + mov byte ptr [r12 + rbx], dil + add rdx, 1 + mov rsi, r14 + add rax, -1 + jne .LBB7_68 +# %bb.62: + sub r15, r8 + jne .LBB7_63 + jmp .LBB7_226 +.LBB7_157: + mov r13d, dword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB7_163 +# %bb.158: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB7_161 +# %bb.159: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi + .p2align 4, 0x90 +.LBB7_160: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + setg bl + neg bl + lea rdi, [rdx + 7] + test rdx, rdx + cmovns rdi, rdx + sar rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB7_160 +.LBB7_161: + sub r15, r8 + je .LBB7_226 +# %bb.162: + add r12, 1 +.LBB7_163: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB7_167 +# %bb.164: + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB7_165: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + cmp dword ptr [rsi], r13d + setg byte ptr [rsp + 208] # 1-byte Folded Spill + cmp dword ptr [rsi + 4], r13d + setg dil + cmp dword ptr [rsi + 8], r13d + setg r14b + cmp dword ptr [rsi + 12], r13d + setg byte ptr [rsp + 176] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp dword ptr [rsi + 20], r13d + setg byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 24], r13d + setg al + cmp dword ptr [rsi + 28], r13d + setg bl + cmp dword ptr [rsi + 32], r13d + setg byte ptr [rsp + 192] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d + setg cl + cmp dword ptr [rsi + 40], r13d + setg r9b + cmp dword ptr [rsi + 44], r13d + setg r10b + cmp dword ptr [rsi + 48], r13d + setg r11b + cmp dword ptr [rsi + 52], r13d + setg r12b + cmp dword ptr [rsi + 56], r13d + setg byte ptr [rsp + 144] # 1-byte Folded Spill + cmp dword ptr [rsi + 60], r13d + setg dl + cmp dword ptr [rsi + 64], r13d + setg byte ptr [rsp + 88] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + setg byte ptr [rsp + 160] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setg byte ptr [rsp + 104] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d + setg byte ptr [rsp + 120] # 1-byte Folded Spill + cmp dword ptr [rsi + 80], r13d + setg byte ptr [rsp + 72] # 1-byte Folded Spill + cmp dword ptr [rsi + 84], r13d + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + setg byte ptr [rsp + 64] # 1-byte Folded Spill + cmp dword ptr [rsi + 92], r13d + setg r15b + cmp dword ptr [rsi + 96], r13d + setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp dword ptr [rsi + 100], r13d + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp dword ptr [rsi + 104], r13d + setg byte ptr [rsp + 40] # 1-byte Folded Spill + cmp dword ptr [rsi + 108], r13d + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp dword ptr [rsi + 112], r13d + setg byte ptr [rsp + 32] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp dword ptr [rsi + 120], r13d + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp dword ptr [rsi + 124], r13d + setg r8b + add dil, dil + add dil, byte ptr [rsp + 208] # 1-byte Folded Reload + shl al, 6 + shl bl, 7 + or bl, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl r9b, 2 + or r9b, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r10b, 3 + or r10b, r9b + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r11b, 4 + or r11b, r10b + shl r12b, 5 + or r12b, r11b + movzx edi, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dil, 6 + shl dl, 7 + or dl, dil + or bl, cl + or dl, r12b mov r12, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r12 + 5], 8 - mov r13, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r13 + 5], 9 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rbx + 5], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rbx + 5], 11 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rbx + 5], 12 - pinsrb xmm8, byte ptr [rsi + rax + 5], 13 - pinsrb xmm8, byte ptr [rsi + r14 + 5], 14 - mov rax, r15 - pinsrb xmm8, byte ptr [rsi + r15 + 5], 15 - pcmpgtb xmm8, xmm9 - movdqa xmm2, xmmword ptr [rip + .LCPI7_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm8, xmm2 - por xmm8, xmm1 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + rax + 19] - movd xmm7, ebx - por xmm8, xmm6 - movzx ebx, byte ptr [rsi + rax + 20] - movd xmm6, ebx - pinsrb xmm3, byte ptr [rsi + r8 + 6], 1 - pinsrb xmm3, byte ptr [rsi + rcx + 6], 2 - mov r14, rdi - pinsrb xmm3, byte ptr [rsi + rdi + 6], 3 - mov r15, r9 - pinsrb xmm3, byte ptr [rsi + r9 + 6], 4 - pinsrb xmm3, byte ptr [rsi + rdx + 6], 5 - mov rdi, r10 - pinsrb xmm3, byte ptr [rsi + r10 + 6], 6 - mov r9, r11 - pinsrb xmm3, byte ptr [rsi + r11 + 6], 7 + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov edi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 2 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 3 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 4 + or cl, dil + mov edi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + mov byte ptr [r12], bl + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 6 + shl r15b, 7 + or r15b, bl + mov byte ptr [r12 + 1], dl + or r15b, cl + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 24] # 1-byte Folded Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl cl, 3 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 4 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload + shl cl, 5 + or cl, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl r8b, 7 + or r8b, dl + or r8b, cl + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], r8b + add rsi, 128 + add r12, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_165 +# %bb.166: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 256] # 8-byte Reload +.LBB7_167: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB7_226 +# %bb.168: + or rax, 1 + cmp r15, rax + jne .LBB7_173 +# %bb.169: + xor r11d, r11d + jmp .LBB7_170 +.LBB7_5: + mov r14, rsi + jmp .LBB7_89 +.LBB7_137: + mov qword ptr [rsp + 8], r12 # 8-byte Spill +.LBB7_148: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB7_226 +# %bb.149: + or rcx, 1 + cmp r15, rcx + jne .LBB7_153 +# %bb.150: + xor r14d, r14d + jmp .LBB7_151 +.LBB7_201: mov r10, r12 - pinsrb xmm3, byte ptr [rsi + r12 + 6], 8 - mov rbx, r13 - pinsrb xmm3, byte ptr [rsi + r13 + 6], 9 - mov rdx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 6], 10 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r12 + 6], 11 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r13 + 6], 12 - mov r11, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r11 + 6], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rax + 6], 14 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rax + 6], 15 - movdqa xmm2, xmmword ptr [rsp + 160] # 16-byte Reload - pinsrb xmm2, byte ptr [rsi + r8 + 7], 1 - pinsrb xmm2, byte ptr [rsi + rcx + 7], 2 - pinsrb xmm2, byte ptr [rsi + r14 + 7], 3 - pinsrb xmm2, byte ptr [rsi + r15 + 7], 4 - mov r14, r15 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 7], 5 - pinsrb xmm2, byte ptr [rsi + rdi + 7], 6 - pinsrb xmm2, byte ptr [rsi + r9 + 7], 7 - pinsrb xmm2, byte ptr [rsi + r10 + 7], 8 - pinsrb xmm2, byte ptr [rsi + rbx + 7], 9 - pinsrb xmm2, byte ptr [rsi + rdx + 7], 10 - pinsrb xmm2, byte ptr [rsi + r12 + 7], 11 - pinsrb xmm2, byte ptr [rsi + r13 + 7], 12 - pinsrb xmm2, byte ptr [rsi + r11 + 7], 13 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdi + 7], 14 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdx + 7], 15 - pcmpgtb xmm3, xmm9 - movdqa xmm1, xmmword ptr [rip + .LCPI7_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm1 - pcmpgtb xmm2, xmm9 - psllw xmm2, 7 - movdqa xmm1, xmmword ptr [rip + .LCPI7_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm2, xmm1 - por xmm2, xmm3 - movdqa xmm1, xmm2 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + r8 + 21] - movd xmm2, ebx - mov r9, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r9 + 9], 1 - pinsrb xmm10, byte ptr [rsi + rcx + 9], 2 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r15 + 9], 3 - pinsrb xmm10, byte ptr [rsi + r14 + 9], 4 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx + 9], 5 - mov rbx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx + 9], 6 - mov r10, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r10 + 9], 7 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r11 + 9], 8 - mov rbx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx + 9], 9 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx + 9], 10 - pinsrb xmm10, byte ptr [rsi + r12 + 9], 11 - pinsrb xmm10, byte ptr [rsi + r13 + 9], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx + 9], 13 - pinsrb xmm10, byte ptr [rsi + rdi + 9], 14 - pinsrb xmm10, byte ptr [rsi + rdx + 9], 15 - por xmm1, xmm8 - movdqa xmmword ptr [rsp + 160], xmm1 # 16-byte Spill - pcmpgtb xmm10, xmm9 - movdqa xmm1, xmm10 - movdqa xmm8, xmm4 - pand xmm1, xmm4 - psubb xmm1, xmm10 - movzx ebx, byte ptr [rsi + r8 + 22] - movd xmm3, ebx - movdqa xmm4, xmmword ptr [rsp + 304] # 16-byte Reload - mov rbx, r9 - pinsrb xmm4, byte ptr [rsi + r9 + 8], 1 - pinsrb xmm4, byte ptr [rsi + rcx + 8], 2 - mov r12, rcx - pinsrb xmm4, byte ptr [rsi + r15 + 8], 3 - mov r13, r14 - pinsrb xmm4, byte ptr [rsi + r14 + 8], 4 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 8], 5 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 8], 6 - mov r9, r10 - pinsrb xmm4, byte ptr [rsi + r10 + 8], 7 - mov r10, r11 - pinsrb xmm4, byte ptr [rsi + r11 + 8], 8 - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 8], 9 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 8], 10 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r14 + 8], 11 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 8], 12 - mov r11, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r11 + 8], 13 - mov r8, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r8 + 8], 14 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 8], 15 - pcmpgtb xmm4, xmm9 - pand xmm4, xmm8 - movdqa xmm10, xmmword ptr [rsp + 176] # 16-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx + 10], 1 - pinsrb xmm10, byte ptr [rsi + r12 + 10], 2 - pinsrb xmm10, byte ptr [rsi + r15 + 10], 3 - pinsrb xmm10, byte ptr [rsi + r13 + 10], 4 - pinsrb xmm10, byte ptr [rsi + rdx + 10], 5 - pinsrb xmm10, byte ptr [rsi + rdi + 10], 6 - pinsrb xmm10, byte ptr [rsi + r9 + 10], 7 - pinsrb xmm10, byte ptr [rsi + r10 + 10], 8 - pinsrb xmm10, byte ptr [rsi + rcx + 10], 9 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r15 + 10], 10 - pinsrb xmm10, byte ptr [rsi + r14 + 10], 11 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r13 + 10], 12 - pinsrb xmm10, byte ptr [rsi + r11 + 10], 13 - pinsrb xmm10, byte ptr [rsi + r8 + 10], 14 - mov r11, r8 - pinsrb xmm10, byte ptr [rsi + rax + 10], 15 - pcmpgtb xmm10, xmm9 - pand xmm10, xmmword ptr [rip + .LCPI7_11] - por xmm10, xmm4 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + rax + 23] - movd xmm8, ebx - por xmm10, xmm1 - movdqa xmmword ptr [rsp + 176], xmm10 # 16-byte Spill - movzx ebx, byte ptr [rsi + rax + 24] - movd xmm10, ebx - mov r14, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r14 + 11], 1 - mov rcx, r12 - mov qword ptr [rsp + 208], r12 # 8-byte Spill - pinsrb xmm11, byte ptr [rsi + r12 + 11], 2 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rax + 11], 3 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rbx + 11], 4 - pinsrb xmm11, byte ptr [rsi + rdx + 11], 5 - pinsrb xmm11, byte ptr [rsi + rdi + 11], 6 - mov r8, r9 - pinsrb xmm11, byte ptr [rsi + r9 + 11], 7 - mov r9, r10 - pinsrb xmm11, byte ptr [rsi + r10 + 11], 8 - mov r10, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r10 + 11], 9 - pinsrb xmm11, byte ptr [rsi + r15 + 11], 10 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r12 + 11], 11 - pinsrb xmm11, byte ptr [rsi + r13 + 11], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rbx + 11], 13 - pinsrb xmm11, byte ptr [rsi + r11 + 11], 14 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r11 + 11], 15 - pinsrb xmm13, byte ptr [rsi + r14 + 12], 1 - pinsrb xmm13, byte ptr [rsi + rcx + 12], 2 - pinsrb xmm13, byte ptr [rsi + rax + 12], 3 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r14 + 12], 4 - pinsrb xmm13, byte ptr [rsi + rdx + 12], 5 - pinsrb xmm13, byte ptr [rsi + rdi + 12], 6 - pinsrb xmm13, byte ptr [rsi + r8 + 12], 7 - pinsrb xmm13, byte ptr [rsi + r9 + 12], 8 - pinsrb xmm13, byte ptr [rsi + r10 + 12], 9 - pinsrb xmm13, byte ptr [rsi + r15 + 12], 10 - pinsrb xmm13, byte ptr [rsi + r12 + 12], 11 - pinsrb xmm13, byte ptr [rsi + r13 + 12], 12 - pinsrb xmm13, byte ptr [rsi + rbx + 12], 13 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rbx + 12], 14 - pinsrb xmm13, byte ptr [rsi + r11 + 12], 15 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rax + 13], 1 - pinsrb xmm12, byte ptr [rsi + rcx + 13], 2 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rcx + 13], 3 - pinsrb xmm12, byte ptr [rsi + r14 + 13], 4 - pinsrb xmm12, byte ptr [rsi + rdx + 13], 5 - pinsrb xmm12, byte ptr [rsi + rdi + 13], 6 - pinsrb xmm12, byte ptr [rsi + r8 + 13], 7 - pinsrb xmm12, byte ptr [rsi + r9 + 13], 8 - pinsrb xmm12, byte ptr [rsi + r10 + 13], 9 - pinsrb xmm12, byte ptr [rsi + r15 + 13], 10 - pinsrb xmm12, byte ptr [rsi + r12 + 13], 11 - pinsrb xmm12, byte ptr [rsi + r13 + 13], 12 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rdi + 13], 13 - pinsrb xmm12, byte ptr [rsi + rbx + 13], 14 - pinsrb xmm12, byte ptr [rsi + r11 + 13], 15 - pcmpgtb xmm11, xmm9 - pand xmm11, xmmword ptr [rip + .LCPI7_12] - pcmpgtb xmm13, xmm9 - pand xmm13, xmmword ptr [rip + .LCPI7_13] - por xmm13, xmm11 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + rdi + 25] - movd xmm1, ebx - pcmpgtb xmm12, xmm9 - pand xmm12, xmmword ptr [rip + .LCPI7_14] - por xmm12, xmm13 - movzx ebx, byte ptr [rsi + rdi + 26] - movd xmm11, ebx - movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 14], 1 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rbx + 14], 2 - mov r11, rcx - pinsrb xmm4, byte ptr [rsi + rcx + 14], 3 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 14], 4 - mov rcx, rdx - pinsrb xmm4, byte ptr [rsi + rdx + 14], 5 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 14], 6 - pinsrb xmm4, byte ptr [rsi + r8 + 14], 7 - pinsrb xmm4, byte ptr [rsi + r9 + 14], 8 - pinsrb xmm4, byte ptr [rsi + r10 + 14], 9 - pinsrb xmm4, byte ptr [rsi + r15 + 14], 10 - pinsrb xmm4, byte ptr [rsi + r12 + 14], 11 - pinsrb xmm4, byte ptr [rsi + r13 + 14], 12 - mov r14, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r14 + 14], 13 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 14], 14 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 14], 15 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdi + 15], 1 - pinsrb xmm14, byte ptr [rsi + rbx + 15], 2 - pinsrb xmm14, byte ptr [rsi + r11 + 15], 3 - pinsrb xmm14, byte ptr [rsi + rax + 15], 4 - pinsrb xmm14, byte ptr [rsi + rcx + 15], 5 - pinsrb xmm14, byte ptr [rsi + rdx + 15], 6 - pinsrb xmm14, byte ptr [rsi + r8 + 15], 7 - pinsrb xmm14, byte ptr [rsi + r9 + 15], 8 - pinsrb xmm14, byte ptr [rsi + r10 + 15], 9 - pinsrb xmm14, byte ptr [rsi + r15 + 15], 10 - pinsrb xmm14, byte ptr [rsi + r12 + 15], 11 - pinsrb xmm14, byte ptr [rsi + r13 + 15], 12 - pinsrb xmm14, byte ptr [rsi + r14 + 15], 13 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdi + 15], 14 - mov r14, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r14 + 15], 15 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdi + 16], 1 - pinsrb xmm15, byte ptr [rsi + rbx + 16], 2 - pinsrb xmm15, byte ptr [rsi + r11 + 16], 3 - pinsrb xmm15, byte ptr [rsi + rax + 16], 4 - pinsrb xmm15, byte ptr [rsi + rcx + 16], 5 - pinsrb xmm15, byte ptr [rsi + rdx + 16], 6 - pinsrb xmm15, byte ptr [rsi + r8 + 16], 7 - pinsrb xmm15, byte ptr [rsi + r9 + 16], 8 - pinsrb xmm15, byte ptr [rsi + r10 + 16], 9 - pinsrb xmm15, byte ptr [rsi + r15 + 16], 10 - pinsrb xmm15, byte ptr [rsi + r12 + 16], 11 - pinsrb xmm15, byte ptr [rsi + r13 + 16], 12 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdi + 16], 13 - mov r14, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r14 + 16], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdi + 17], 1 - pinsrb xmm0, byte ptr [rsi + rbx + 17], 2 - pinsrb xmm0, byte ptr [rsi + r11 + 17], 3 - pinsrb xmm0, byte ptr [rsi + rax + 17], 4 - pinsrb xmm0, byte ptr [rsi + rcx + 17], 5 - pinsrb xmm0, byte ptr [rsi + rdx + 17], 6 - pinsrb xmm0, byte ptr [rsi + r8 + 17], 7 - pinsrb xmm0, byte ptr [rsi + r9 + 17], 8 - pinsrb xmm0, byte ptr [rsi + r10 + 17], 9 - pinsrb xmm0, byte ptr [rsi + r15 + 17], 10 - pinsrb xmm0, byte ptr [rsi + r12 + 17], 11 - pinsrb xmm0, byte ptr [rsi + r13 + 17], 12 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdi + 17], 13 - pinsrb xmm0, byte ptr [rsi + r14 + 17], 14 - por xmm12, xmmword ptr [rsp + 176] # 16-byte Folded Reload - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + rdi + 27] - movd xmm9, ebx - movdqa xmm13, xmmword ptr [rsp + 144] # 16-byte Reload - pcmpgtb xmm4, xmm13 - pand xmm4, xmmword ptr [rip + .LCPI7_15] - pcmpgtb xmm14, xmm13 - psllw xmm14, 7 - pand xmm14, xmmword ptr [rip + .LCPI7_6] - por xmm14, xmm4 - movzx ebx, byte ptr [rsi + rdi + 28] - movd xmm4, ebx - mov r14, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r14 + 17], 15 - por xmm14, xmm12 - pcmpgtb xmm0, xmm13 - movdqa xmm13, xmm0 - movdqa xmm12, xmmword ptr [rip + .LCPI7_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm13, xmm12 - psubb xmm13, xmm0 - movdqa xmmword ptr [rsp + 176], xmm13 # 16-byte Spill - movzx ebx, byte ptr [rsi + rdi + 29] - movd xmm13, ebx - pinsrb xmm15, byte ptr [rsi + r14 + 16], 15 - movdqa xmm0, xmmword ptr [rsp + 144] # 16-byte Reload - pcmpgtb xmm15, xmm0 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdi + 18], 1 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rbx + 18], 2 - pinsrb xmm5, byte ptr [rsi + r11 + 18], 3 - pinsrb xmm5, byte ptr [rsi + rax + 18], 4 - pinsrb xmm5, byte ptr [rsi + rcx + 18], 5 - pinsrb xmm5, byte ptr [rsi + rdx + 18], 6 - pinsrb xmm5, byte ptr [rsi + r8 + 18], 7 - pinsrb xmm5, byte ptr [rsi + r9 + 18], 8 - pinsrb xmm5, byte ptr [rsi + r10 + 18], 9 - pinsrb xmm5, byte ptr [rsi + r15 + 18], 10 - pinsrb xmm5, byte ptr [rsi + r12 + 18], 11 - pinsrb xmm5, byte ptr [rsi + r13 + 18], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rbx + 18], 13 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rbx + 18], 14 - pand xmm15, xmm12 - pinsrb xmm5, byte ptr [rsi + r14 + 18], 15 - pcmpgtb xmm5, xmm0 - pand xmm5, xmmword ptr [rip + .LCPI7_11] - por xmm5, xmm15 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - movzx ebx, byte ptr [rsi + rax + 30] - movd xmm12, ebx - mov rbx, rdi - pinsrb xmm7, byte ptr [rsi + rdi + 19], 1 - pinsrb xmm6, byte ptr [rsi + rdi + 20], 1 - pinsrb xmm2, byte ptr [rsi + rdi + 21], 1 - pinsrb xmm3, byte ptr [rsi + rdi + 22], 1 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 1 - pinsrb xmm10, byte ptr [rsi + rdi + 24], 1 - pinsrb xmm1, byte ptr [rsi + rdi + 25], 1 - pinsrb xmm11, byte ptr [rsi + rdi + 26], 1 - pinsrb xmm9, byte ptr [rsi + rdi + 27], 1 - pinsrb xmm4, byte ptr [rsi + rdi + 28], 1 - pinsrb xmm13, byte ptr [rsi + rdi + 29], 1 - pinsrb xmm12, byte ptr [rsi + rdi + 30], 1 - movzx edi, byte ptr [rsi + rax + 31] - movd xmm0, edi - pinsrb xmm0, byte ptr [rsi + rbx + 31], 1 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdi + 19], 2 - pinsrb xmm6, byte ptr [rsi + rdi + 20], 2 - pinsrb xmm2, byte ptr [rsi + rdi + 21], 2 - pinsrb xmm3, byte ptr [rsi + rdi + 22], 2 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 2 - pinsrb xmm10, byte ptr [rsi + rdi + 24], 2 - pinsrb xmm1, byte ptr [rsi + rdi + 25], 2 - pinsrb xmm11, byte ptr [rsi + rdi + 26], 2 - pinsrb xmm9, byte ptr [rsi + rdi + 27], 2 - pinsrb xmm4, byte ptr [rsi + rdi + 28], 2 - pinsrb xmm13, byte ptr [rsi + rdi + 29], 2 - pinsrb xmm12, byte ptr [rsi + rdi + 30], 2 - pinsrb xmm0, byte ptr [rsi + rdi + 31], 2 - pinsrb xmm7, byte ptr [rsi + r11 + 19], 3 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 19], 4 - pinsrb xmm7, byte ptr [rsi + rcx + 19], 5 - pinsrb xmm7, byte ptr [rsi + rdx + 19], 6 - pinsrb xmm7, byte ptr [rsi + r8 + 19], 7 - pinsrb xmm7, byte ptr [rsi + r9 + 19], 8 - pinsrb xmm7, byte ptr [rsi + r10 + 19], 9 - pinsrb xmm7, byte ptr [rsi + r15 + 19], 10 - pinsrb xmm7, byte ptr [rsi + r12 + 19], 11 - pinsrb xmm7, byte ptr [rsi + r13 + 19], 12 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdi + 19], 13 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rbx + 19], 14 - pinsrb xmm7, byte ptr [rsi + r14 + 19], 15 - pinsrb xmm6, byte ptr [rsi + r11 + 20], 3 - pinsrb xmm6, byte ptr [rsi + rax + 20], 4 - pinsrb xmm6, byte ptr [rsi + rcx + 20], 5 - pinsrb xmm6, byte ptr [rsi + rdx + 20], 6 - pinsrb xmm6, byte ptr [rsi + r8 + 20], 7 - pinsrb xmm6, byte ptr [rsi + r9 + 20], 8 - pinsrb xmm6, byte ptr [rsi + r10 + 20], 9 - pinsrb xmm6, byte ptr [rsi + r15 + 20], 10 - pinsrb xmm6, byte ptr [rsi + r12 + 20], 11 - pinsrb xmm6, byte ptr [rsi + r13 + 20], 12 - pinsrb xmm6, byte ptr [rsi + rdi + 20], 13 - pinsrb xmm6, byte ptr [rsi + rbx + 20], 14 - por xmm5, xmmword ptr [rsp + 176] # 16-byte Folded Reload - pinsrb xmm6, byte ptr [rsi + r14 + 20], 15 - movdqa xmm15, xmmword ptr [rsp + 144] # 16-byte Reload - pcmpgtb xmm7, xmm15 - pand xmm7, xmmword ptr [rip + .LCPI7_12] - pcmpgtb xmm6, xmm15 - pand xmm6, xmmword ptr [rip + .LCPI7_13] - por xmm6, xmm7 - pinsrb xmm2, byte ptr [rsi + r11 + 21], 3 - pinsrb xmm2, byte ptr [rsi + rax + 21], 4 - pinsrb xmm2, byte ptr [rsi + rcx + 21], 5 - pinsrb xmm2, byte ptr [rsi + rdx + 21], 6 - pinsrb xmm2, byte ptr [rsi + r8 + 21], 7 - pinsrb xmm2, byte ptr [rsi + r9 + 21], 8 - pinsrb xmm2, byte ptr [rsi + r10 + 21], 9 - pinsrb xmm2, byte ptr [rsi + r15 + 21], 10 - pinsrb xmm2, byte ptr [rsi + r12 + 21], 11 - pinsrb xmm2, byte ptr [rsi + r13 + 21], 12 - pinsrb xmm2, byte ptr [rsi + rdi + 21], 13 - pinsrb xmm2, byte ptr [rsi + rbx + 21], 14 - pinsrb xmm2, byte ptr [rsi + r14 + 21], 15 - pcmpgtb xmm2, xmm15 - movdqa xmm7, xmmword ptr [rip + .LCPI7_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm2, xmm7 - por xmm2, xmm6 - por xmm2, xmm5 - pinsrb xmm3, byte ptr [rsi + r11 + 22], 3 - pinsrb xmm3, byte ptr [rsi + rax + 22], 4 - pinsrb xmm3, byte ptr [rsi + rcx + 22], 5 - pinsrb xmm3, byte ptr [rsi + rdx + 22], 6 - pinsrb xmm3, byte ptr [rsi + r8 + 22], 7 - pinsrb xmm3, byte ptr [rsi + r9 + 22], 8 - pinsrb xmm3, byte ptr [rsi + r10 + 22], 9 - pinsrb xmm3, byte ptr [rsi + r15 + 22], 10 - pinsrb xmm3, byte ptr [rsi + r12 + 22], 11 - pinsrb xmm3, byte ptr [rsi + r13 + 22], 12 - pinsrb xmm3, byte ptr [rsi + rdi + 22], 13 - pinsrb xmm3, byte ptr [rsi + rbx + 22], 14 - pinsrb xmm3, byte ptr [rsi + r14 + 22], 15 - pinsrb xmm8, byte ptr [rsi + r11 + 23], 3 - pinsrb xmm8, byte ptr [rsi + rax + 23], 4 - pinsrb xmm8, byte ptr [rsi + rcx + 23], 5 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 6 - pinsrb xmm8, byte ptr [rsi + r8 + 23], 7 - pinsrb xmm8, byte ptr [rsi + r9 + 23], 8 - pinsrb xmm8, byte ptr [rsi + r10 + 23], 9 - pinsrb xmm8, byte ptr [rsi + r15 + 23], 10 - pinsrb xmm8, byte ptr [rsi + r12 + 23], 11 - pinsrb xmm8, byte ptr [rsi + r13 + 23], 12 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 13 - pinsrb xmm8, byte ptr [rsi + rbx + 23], 14 - pinsrb xmm8, byte ptr [rsi + r14 + 23], 15 - pcmpgtb xmm3, xmm15 - movdqa xmm5, xmmword ptr [rip + .LCPI7_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm3, xmm5 - pcmpgtb xmm8, xmm15 - psllw xmm8, 7 - movdqa xmm6, xmmword ptr [rip + .LCPI7_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm8, xmm6 - por xmm8, xmm3 - pinsrb xmm1, byte ptr [rsi + r11 + 25], 3 - pinsrb xmm1, byte ptr [rsi + rax + 25], 4 - pinsrb xmm1, byte ptr [rsi + rcx + 25], 5 - pinsrb xmm1, byte ptr [rsi + rdx + 25], 6 - pinsrb xmm1, byte ptr [rsi + r8 + 25], 7 - pinsrb xmm1, byte ptr [rsi + r9 + 25], 8 - pinsrb xmm1, byte ptr [rsi + r10 + 25], 9 - pinsrb xmm1, byte ptr [rsi + r15 + 25], 10 - pinsrb xmm1, byte ptr [rsi + r12 + 25], 11 - pinsrb xmm1, byte ptr [rsi + r13 + 25], 12 - pinsrb xmm1, byte ptr [rsi + rdi + 25], 13 - pinsrb xmm1, byte ptr [rsi + rbx + 25], 14 - pinsrb xmm1, byte ptr [rsi + r14 + 25], 15 - por xmm8, xmm2 - pcmpgtb xmm1, xmm15 - movdqa xmm2, xmm1 - movdqa xmm3, xmmword ptr [rip + .LCPI7_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm2, xmm3 - psubb xmm2, xmm1 - pinsrb xmm10, byte ptr [rsi + r11 + 24], 3 - pinsrb xmm10, byte ptr [rsi + rax + 24], 4 - pinsrb xmm10, byte ptr [rsi + rcx + 24], 5 - pinsrb xmm10, byte ptr [rsi + rdx + 24], 6 - pinsrb xmm10, byte ptr [rsi + r8 + 24], 7 - pinsrb xmm10, byte ptr [rsi + r9 + 24], 8 - pinsrb xmm10, byte ptr [rsi + r10 + 24], 9 - pinsrb xmm10, byte ptr [rsi + r15 + 24], 10 - pinsrb xmm10, byte ptr [rsi + r12 + 24], 11 - pinsrb xmm10, byte ptr [rsi + r13 + 24], 12 - pinsrb xmm10, byte ptr [rsi + rdi + 24], 13 - pinsrb xmm10, byte ptr [rsi + rbx + 24], 14 - pinsrb xmm10, byte ptr [rsi + r14 + 24], 15 - pcmpgtb xmm10, xmm15 - pand xmm10, xmm3 - pinsrb xmm11, byte ptr [rsi + r11 + 26], 3 - pinsrb xmm11, byte ptr [rsi + rax + 26], 4 - pinsrb xmm11, byte ptr [rsi + rcx + 26], 5 - pinsrb xmm11, byte ptr [rsi + rdx + 26], 6 - pinsrb xmm11, byte ptr [rsi + r8 + 26], 7 - pinsrb xmm11, byte ptr [rsi + r9 + 26], 8 - pinsrb xmm11, byte ptr [rsi + r10 + 26], 9 - pinsrb xmm11, byte ptr [rsi + r15 + 26], 10 - pinsrb xmm11, byte ptr [rsi + r12 + 26], 11 - pinsrb xmm11, byte ptr [rsi + r13 + 26], 12 - pinsrb xmm11, byte ptr [rsi + rdi + 26], 13 - pinsrb xmm11, byte ptr [rsi + rbx + 26], 14 - pinsrb xmm11, byte ptr [rsi + r14 + 26], 15 - pcmpgtb xmm11, xmm15 - pand xmm11, xmmword ptr [rip + .LCPI7_11] - por xmm11, xmm10 - por xmm11, xmm2 - pinsrb xmm9, byte ptr [rsi + r11 + 27], 3 - pinsrb xmm9, byte ptr [rsi + rax + 27], 4 - pinsrb xmm9, byte ptr [rsi + rcx + 27], 5 - pinsrb xmm9, byte ptr [rsi + rdx + 27], 6 - pinsrb xmm9, byte ptr [rsi + r8 + 27], 7 - pinsrb xmm9, byte ptr [rsi + r9 + 27], 8 - pinsrb xmm9, byte ptr [rsi + r10 + 27], 9 - pinsrb xmm9, byte ptr [rsi + r15 + 27], 10 - pinsrb xmm9, byte ptr [rsi + r12 + 27], 11 - pinsrb xmm9, byte ptr [rsi + r13 + 27], 12 - pinsrb xmm9, byte ptr [rsi + rdi + 27], 13 - pinsrb xmm9, byte ptr [rsi + rbx + 27], 14 - pinsrb xmm9, byte ptr [rsi + r14 + 27], 15 - pinsrb xmm4, byte ptr [rsi + r11 + 28], 3 - pinsrb xmm4, byte ptr [rsi + rax + 28], 4 - pinsrb xmm4, byte ptr [rsi + rcx + 28], 5 - pinsrb xmm4, byte ptr [rsi + rdx + 28], 6 - pinsrb xmm4, byte ptr [rsi + r8 + 28], 7 - pinsrb xmm4, byte ptr [rsi + r9 + 28], 8 - pinsrb xmm4, byte ptr [rsi + r10 + 28], 9 - pinsrb xmm4, byte ptr [rsi + r15 + 28], 10 - pinsrb xmm4, byte ptr [rsi + r12 + 28], 11 - pinsrb xmm4, byte ptr [rsi + r13 + 28], 12 - pinsrb xmm4, byte ptr [rsi + rdi + 28], 13 - pinsrb xmm4, byte ptr [rsi + rbx + 28], 14 - pinsrb xmm4, byte ptr [rsi + r14 + 28], 15 - pinsrb xmm13, byte ptr [rsi + r11 + 29], 3 - pinsrb xmm13, byte ptr [rsi + rax + 29], 4 - pinsrb xmm13, byte ptr [rsi + rcx + 29], 5 - pinsrb xmm13, byte ptr [rsi + rdx + 29], 6 - pinsrb xmm13, byte ptr [rsi + r8 + 29], 7 - pinsrb xmm13, byte ptr [rsi + r9 + 29], 8 - pinsrb xmm13, byte ptr [rsi + r10 + 29], 9 - pinsrb xmm13, byte ptr [rsi + r15 + 29], 10 - pinsrb xmm13, byte ptr [rsi + r12 + 29], 11 - pinsrb xmm13, byte ptr [rsi + r13 + 29], 12 - pinsrb xmm13, byte ptr [rsi + rdi + 29], 13 - pinsrb xmm13, byte ptr [rsi + rbx + 29], 14 - movdqa xmm1, xmm15 - pcmpgtb xmm9, xmm15 - pand xmm9, xmmword ptr [rip + .LCPI7_12] - pcmpgtb xmm4, xmm15 - pand xmm4, xmmword ptr [rip + .LCPI7_13] - por xmm4, xmm9 - pinsrb xmm13, byte ptr [rsi + r14 + 29], 15 - pcmpgtb xmm13, xmm15 - pand xmm13, xmm7 - por xmm13, xmm4 - pinsrb xmm12, byte ptr [rsi + r11 + 30], 3 - pinsrb xmm0, byte ptr [rsi + r11 + 31], 3 - pinsrb xmm12, byte ptr [rsi + rax + 30], 4 - pinsrb xmm0, byte ptr [rsi + rax + 31], 4 - pinsrb xmm12, byte ptr [rsi + rcx + 30], 5 - pinsrb xmm0, byte ptr [rsi + rcx + 31], 5 - pinsrb xmm12, byte ptr [rsi + rdx + 30], 6 - pinsrb xmm0, byte ptr [rsi + rdx + 31], 6 - pinsrb xmm12, byte ptr [rsi + r8 + 30], 7 - pinsrb xmm0, byte ptr [rsi + r8 + 31], 7 - pinsrb xmm12, byte ptr [rsi + r9 + 30], 8 - pinsrb xmm0, byte ptr [rsi + r9 + 31], 8 - pinsrb xmm12, byte ptr [rsi + r10 + 30], 9 - pinsrb xmm0, byte ptr [rsi + r10 + 31], 9 - pinsrb xmm12, byte ptr [rsi + r15 + 30], 10 - pinsrb xmm0, byte ptr [rsi + r15 + 31], 10 - pinsrb xmm12, byte ptr [rsi + r12 + 30], 11 - pinsrb xmm0, byte ptr [rsi + r12 + 31], 11 - pinsrb xmm12, byte ptr [rsi + r13 + 30], 12 - pinsrb xmm0, byte ptr [rsi + r13 + 31], 12 - pinsrb xmm12, byte ptr [rsi + rdi + 30], 13 - pinsrb xmm0, byte ptr [rsi + rdi + 31], 13 - pinsrb xmm12, byte ptr [rsi + rbx + 30], 14 - pinsrb xmm0, byte ptr [rsi + rbx + 31], 14 - pinsrb xmm12, byte ptr [rsi + r14 + 30], 15 - pinsrb xmm0, byte ptr [rsi + r14 + 31], 15 - por xmm13, xmm11 - pcmpgtb xmm12, xmm15 - pand xmm12, xmm5 - pcmpgtb xmm0, xmm15 - psllw xmm0, 7 - pand xmm0, xmm6 - por xmm0, xmm12 - por xmm0, xmm13 - movdqa xmm1, xmm8 - punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - movdqa xmm4, xmmword ptr [rsp + 160] # 16-byte Reload - movdqa xmm2, xmm4 - punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] - movdqa xmm3, xmm2 - punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] - punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] - punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] - punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - mov rax, qword ptr [rsp] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx + 48], xmm4 - movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 - movdqu xmmword ptr [rax + 4*rcx], xmm3 - add rcx, 16 + mov rcx, rsi +.LBB7_212: + shl rdi, 5 + mov r8, r15 + sub r8, rdi + jle .LBB7_226 +# %bb.213: + movd xmm0, r14d + or rdi, 1 + cmp r15, rdi + jne .LBB7_217 +# %bb.214: + xor r14d, r14d + jmp .LBB7_215 +.LBB7_59: + mov r14, rsi + jmp .LBB7_64 +.LBB7_86: + mov r14, rsi + sub r15, r8 + je .LBB7_226 +.LBB7_88: + add r12, 1 +.LBB7_89: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB7_90 +# %bb.93: + cmp rcx, 16 + mov byte ptr [rsp + 8], r13b # 1-byte Spill + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 280], rcx # 8-byte Spill + jb .LBB7_94 +# %bb.95: mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB7_85 -# %bb.86: - mov r10, qword ptr [rsp + 288] # 8-byte Reload - cmp r10, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r12b, byte ptr [rsp + 8] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r11, qword ptr [rsp + 136] # 8-byte Reload - jne .LBB7_87 - jmp .LBB7_90 -.LBB7_66: - and r15, -16 - mov rax, r15 shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 320], rax # 8-byte Spill - mov qword ptr [rsp + 232], r15 # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] - mov qword ptr [rsp + 120], rax # 8-byte Spill - movzx eax, r10b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill + add rax, r14 + cmp r12, rax + jae .LBB7_97 +# %bb.96: + lea rax, [r12 + 4*rcx] + cmp r14, rax + jae .LBB7_97 +.LBB7_94: + xor eax, eax + mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 288], r12 # 8-byte Spill + mov rsi, r14 +.LBB7_100: + sub rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov qword ptr [rsp + 256], rcx # 8-byte Spill + mov rdi, qword ptr [rsp + 288] # 8-byte Reload + .p2align 4, 0x90 +.LBB7_101: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r13b + setg byte ptr [rsp + 224] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r13b + setg sil + cmp byte ptr [rcx + 2], r13b + setg r15b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 3], al + setg byte ptr [rsp + 176] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 4], al + setg byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 5], al + setg byte ptr [rsp + 64] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 6], al + setg r13b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 7], al + setg r9b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 8], al + setg byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 9], al + setg dl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 10], al + setg r8b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 11], al + setg r10b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 12], al + setg r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 13], al + setg byte ptr [rsp + 208] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 14], al + setg byte ptr [rsp + 144] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 15], al + setg r12b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 16], bl + setg byte ptr [rsp + 160] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 17], bl + setg byte ptr [rsp + 104] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 18], bl + setg byte ptr [rsp + 120] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 19], bl + setg byte ptr [rsp + 88] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 20], bl + setg byte ptr [rsp + 72] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 21], bl + setg byte ptr [rsp + 96] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 22], bl + setg byte ptr [rsp + 80] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 23], bl + setg r11b + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 24], bl + setg byte ptr [rsp + 56] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 25], bl + setg byte ptr [rsp + 40] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 26], bl + setg byte ptr [rsp + 48] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 27], bl + setg byte ptr [rsp + 24] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 28], bl + setg byte ptr [rsp + 32] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 29], bl + setg byte ptr [rsp + 16] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 30], bl + setg byte ptr [rsp + 128] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp byte ptr [rcx + 31], bl + setg bl + add sil, sil + add sil, byte ptr [rsp + 224] # 1-byte Folded Reload + shl r13b, 6 + shl r9b, 7 + or r9b, r13b + shl r15b, 2 + or r15b, sil + add dl, dl + add dl, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + shl al, 3 + or al, r15b + movzx r13d, byte ptr [rsp + 8] # 1-byte Folded Reload + shl r8b, 2 + or r8b, dl + movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl dl, 4 + or dl, al + mov esi, edx + shl r10b, 3 + or r10b, r8b + movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + shl r14b, 4 + or r14b, r10b + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload + shl sil, 6 + shl r12b, 7 + or r12b, sil + or r9b, dl + or r12b, al + movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload + add dl, dl + add dl, byte ptr [rsp + 160] # 1-byte Folded Reload + mov esi, edx + movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl dl, 2 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov byte ptr [rdi], r9b + movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload + shl sil, 6 + shl r11b, 7 + or r11b, sil + mov byte ptr [rdi + 1], r12b + or r11b, dl + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 56] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r11b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + add qword ptr [rsp + 256], -1 # 8-byte Folded Spill + jne .LBB7_101 +# %bb.102: + mov qword ptr [rsp + 288], rdi # 8-byte Spill + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 280] # 8-byte Reload + jmp .LBB7_103 +.LBB7_90: + mov qword ptr [rsp + 288], r12 # 8-byte Spill + mov rsi, r14 +.LBB7_103: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB7_226 +# %bb.104: + or rcx, 1 + cmp r15, rcx + jne .LBB7_106 +# %bb.105: + xor r9d, r9d + jmp .LBB7_109 +.LBB7_61: + mov r14, rsi + sub r15, r8 + je .LBB7_226 +.LBB7_63: + add r12, 1 +.LBB7_64: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB7_77 +# %bb.65: + cmp rcx, 16 + mov qword ptr [rsp + 136], r15 # 8-byte Spill + mov qword ptr [rsp + 312], rcx # 8-byte Spill + jb .LBB7_66 +# %bb.69: + mov rax, rcx + shl rax, 5 + add rax, r14 + cmp r12, rax + jae .LBB7_71 +# %bb.70: + lea rax, [r12 + 4*rcx] + cmp r14, rax + jae .LBB7_71 +.LBB7_66: + xor eax, eax + mov qword ptr [rsp + 248], rax # 8-byte Spill +.LBB7_74: + mov qword ptr [rsp + 96], r12 # 8-byte Spill + sub rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill + mov r12b, byte ptr [rsp + 280] # 1-byte Reload + .p2align 4, 0x90 +.LBB7_75: # =>This Inner Loop Header: Depth=1 + mov rcx, r14 + cmp byte ptr [r14], r12b + seta byte ptr [rsp + 208] # 1-byte Folded Spill + cmp byte ptr [r14 + 1], r12b + seta sil + cmp byte ptr [r14 + 2], r12b + seta r11b + cmp byte ptr [r14 + 3], r12b + seta r14b + cmp byte ptr [rcx + 4], r12b + seta byte ptr [rsp + 160] # 1-byte Folded Spill + cmp byte ptr [rcx + 5], r12b + seta byte ptr [rsp + 104] # 1-byte Folded Spill + cmp byte ptr [rcx + 6], r12b + seta al + cmp byte ptr [rcx + 7], r12b + seta r8b + cmp byte ptr [rcx + 8], r12b + seta byte ptr [rsp + 192] # 1-byte Folded Spill + cmp byte ptr [rcx + 9], r12b + seta dl + cmp byte ptr [rcx + 10], r12b + seta dil + cmp byte ptr [rcx + 11], r12b + seta r9b + cmp byte ptr [rcx + 12], r12b + seta r10b + cmp byte ptr [rcx + 13], r12b + seta r13b + cmp byte ptr [rcx + 14], r12b + seta byte ptr [rsp + 144] # 1-byte Folded Spill + cmp byte ptr [rcx + 15], r12b + seta bl + cmp byte ptr [rcx + 16], r12b + seta byte ptr [rsp + 120] # 1-byte Folded Spill + cmp byte ptr [rcx + 17], r12b + seta byte ptr [rsp + 176] # 1-byte Folded Spill + cmp byte ptr [rcx + 18], r12b + seta byte ptr [rsp + 112] # 1-byte Folded Spill + cmp byte ptr [rcx + 19], r12b + seta byte ptr [rsp + 88] # 1-byte Folded Spill + cmp byte ptr [rcx + 20], r12b + seta byte ptr [rsp + 72] # 1-byte Folded Spill + cmp byte ptr [rcx + 21], r12b + seta byte ptr [rsp + 80] # 1-byte Folded Spill + cmp byte ptr [rcx + 22], r12b + seta byte ptr [rsp + 64] # 1-byte Folded Spill + cmp byte ptr [rcx + 23], r12b + seta byte ptr [rsp + 56] # 1-byte Folded Spill + cmp byte ptr [rcx + 24], r12b + seta byte ptr [rsp + 48] # 1-byte Folded Spill + cmp byte ptr [rcx + 25], r12b + seta byte ptr [rsp + 40] # 1-byte Folded Spill + cmp byte ptr [rcx + 26], r12b + seta byte ptr [rsp + 24] # 1-byte Folded Spill + cmp byte ptr [rcx + 27], r12b + seta byte ptr [rsp + 32] # 1-byte Folded Spill + cmp byte ptr [rcx + 28], r12b + seta byte ptr [rsp + 16] # 1-byte Folded Spill + cmp byte ptr [rcx + 29], r12b + seta byte ptr [rsp + 128] # 1-byte Folded Spill + cmp byte ptr [rcx + 30], r12b + seta byte ptr [rsp + 8] # 1-byte Folded Spill + cmp byte ptr [rcx + 31], r12b + seta r15b + add sil, sil + add sil, byte ptr [rsp + 208] # 1-byte Folded Reload + shl al, 6 + shl r8b, 7 + or r8b, al + shl r11b, 2 + or r11b, sil + add dl, dl + add dl, byte ptr [rsp + 192] # 1-byte Folded Reload + shl r14b, 3 + or r14b, r11b + shl dil, 2 + or dil, dl + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + shl al, 4 + or al, r14b + mov edx, eax + shl r9b, 3 + or r9b, dil + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 5 + or al, dl + shl r10b, 4 + or r10b, r9b + shl r13b, 5 + or r13b, r10b + movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or r8b, al + or bl, r13b + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 120] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 5 + or al, dl + mov esi, eax + mov rax, qword ptr [rsp + 96] # 8-byte Reload + mov byte ptr [rax], r8b + movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dil, 6 + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 7 + or dl, dil + mov byte ptr [rax + 1], bl + or dl, sil + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload + add bl, bl + add bl, byte ptr [rsp + 48] # 1-byte Folded Reload + mov esi, ebx + movzx ebx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl bl, 2 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl bl, 3 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload + shl bl, 4 + or bl, sil + mov esi, ebx + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 5 + or bl, sil + movzx esi, byte ptr [rsp + 8] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + or r15b, bl + mov byte ptr [rax + 2], dl + mov byte ptr [rax + 3], r15b + lea r14, [rcx + 32] + add rax, 4 + mov qword ptr [rsp + 96], rax # 8-byte Spill + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB7_75 +# %bb.76: + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r12, qword ptr [rsp + 96] # 8-byte Reload + mov rcx, qword ptr [rsp + 312] # 8-byte Reload +.LBB7_77: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB7_226 +# %bb.78: + or rcx, 1 + cmp r15, rcx + jne .LBB7_80 +# %bb.79: xor eax, eax + jmp .LBB7_83 +.LBB7_175: + mov r9, r8 + and r9, -2 + xor r11d, r11d .p2align 4, 0x90 -.LBB7_67: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 176], rax # 8-byte Spill - mov rax, qword ptr [rsp + 176] # 8-byte Reload - shl rax, 5 - mov qword ptr [rsp + 32], rax # 8-byte Spill - mov r14, rax - mov rdx, rax +.LBB7_176: # =>This Inner Loop Header: Depth=1 + cmp r13, qword ptr [rsi] + sbb edi, edi + mov rdx, r11 + shr rdx, 3 + movzx r10d, byte ptr [r12 + rdx] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r12 + rdx], al + add r11, 2 + cmp r13, qword ptr [rsi + 8] + lea rsi, [rsi + 16] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r12 + rdx], bl + cmp r9, r11 + jne .LBB7_176 +.LBB7_40: + test r8b, 1 + je .LBB7_226 +# %bb.41: + cmp r13, qword ptr [rsi] + jmp .LBB7_127 +.LBB7_173: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB7_174: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d + setg al + neg al + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + setg al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB7_174 +.LBB7_170: + test r8b, 1 + je .LBB7_226 +# %bb.171: + cmp dword ptr [rsi], r13d + jmp .LBB7_172 +.LBB7_106: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r14, qword ptr [rsp + 288] # 8-byte Reload + .p2align 4, 0x90 +.LBB7_107: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r13b + setg bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r14 + rdi], dl + cmp byte ptr [rsi + rax + 1], r13b + lea r9, [rax + 2] + setg bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r14 + rdi], al + cmp r10, r9 + jne .LBB7_107 +# %bb.108: + add rsi, r9 +.LBB7_109: + test r8b, 1 + je .LBB7_226 +# %bb.110: + cmp byte ptr [rsi], r13b + setg al + neg al + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 288] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + jmp .LBB7_111 +.LBB7_80: + mov r9, r8 + and r9, -2 + xor eax, eax + mov r10b, byte ptr [rsp + 280] # 1-byte Reload + .p2align 4, 0x90 +.LBB7_81: # =>This Inner Loop Header: Depth=1 + cmp r10b, byte ptr [r14 + rax] + sbb esi, esi mov rdi, rax - mov r13, rax - mov r9, rax - mov r10, rax - mov r11, rax - mov r15, rax - mov r8, rax - mov qword ptr [rsp + 56], rax # 8-byte Spill - movzx ecx, byte ptr [rsi + rax] - movd xmm10, ecx - movzx ecx, byte ptr [rsi + rax + 1] - movd xmm4, ecx - movzx ecx, byte ptr [rsi + rax + 2] - movd xmm6, ecx - movzx ecx, byte ptr [rsi + rax + 3] - movd xmm5, ecx - movzx ecx, byte ptr [rsi + rax + 4] - movd xmm9, ecx - movzx ecx, byte ptr [rsi + rax + 5] - movd xmm7, ecx - movzx ecx, byte ptr [rsi + rax + 6] - movd xmm0, ecx - movzx ecx, byte ptr [rsi + rax + 7] - movd xmm1, ecx - movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill - movzx ecx, byte ptr [rsi + rax + 8] - movd xmm14, ecx - movzx ecx, byte ptr [rsi + rax + 9] - movd xmm1, ecx - movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill - movzx ecx, byte ptr [rsi + rax + 10] - movd xmm2, ecx - movzx ecx, byte ptr [rsi + rax + 11] - movd xmm11, ecx - movzx ecx, byte ptr [rsi + rax + 12] - movd xmm1, ecx - movdqa xmmword ptr [rsp + 304], xmm1 # 16-byte Spill - movzx ecx, byte ptr [rsi + rax + 16] - movd xmm13, ecx - mov qword ptr [rsp + 160], rax # 8-byte Spill - movzx ecx, byte ptr [rsi + rax + 24] - movd xmm15, ecx - mov r12, rax - or r12, 32 - mov qword ptr [rsp + 96], r12 # 8-byte Spill - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - or rcx, 64 - mov qword ptr [rsp + 32], rcx # 8-byte Spill - or r14, 96 - or rdx, 128 - or rdi, 160 - or r13, 192 - mov qword ptr [rsp + 104], r13 # 8-byte Spill - or r9, 224 - or r10, 256 - mov qword ptr [rsp + 112], r10 # 8-byte Spill - or r11, 288 - or r15, 320 - or r8, 352 - mov qword ptr [rsp + 40], r8 # 8-byte Spill - mov r8, qword ptr [rsp + 56] # 8-byte Reload - or r8, 384 - mov rbx, rax - or rbx, 416 - mov qword ptr [rsp + 16], rbx # 8-byte Spill - mov rbx, rax - or rbx, 448 - mov qword ptr [rsp + 24], rbx # 8-byte Spill - or rax, 480 - mov qword ptr [rsp + 72], rax # 8-byte Spill - pinsrb xmm10, byte ptr [rsi + r12], 1 - pinsrb xmm10, byte ptr [rsi + rcx], 2 - pinsrb xmm10, byte ptr [rsi + r14], 3 - mov qword ptr [rsp + 64], r14 # 8-byte Spill - pinsrb xmm10, byte ptr [rsi + rdx], 4 - pinsrb xmm10, byte ptr [rsi + rdi], 5 - pinsrb xmm10, byte ptr [rsi + r13], 6 - pinsrb xmm10, byte ptr [rsi + r9], 7 - pinsrb xmm10, byte ptr [rsi + r10], 8 - pinsrb xmm10, byte ptr [rsi + r11], 9 - pinsrb xmm10, byte ptr [rsi + r15], 10 - mov r12, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r12], 11 - pinsrb xmm10, byte ptr [rsi + r8], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rbx], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rax], 14 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r10], 15 - movdqa xmm8, xmm10 - movdqa xmm12, xmmword ptr [rsp + 288] # 16-byte Reload - pminub xmm8, xmm12 - pcmpeqb xmm8, xmm10 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 1], 1 - pinsrb xmm4, byte ptr [rsi + rcx + 1], 2 - pinsrb xmm4, byte ptr [rsi + r14 + 1], 3 - pinsrb xmm4, byte ptr [rsi + rdx + 1], 4 - pinsrb xmm4, byte ptr [rsi + rdi + 1], 5 - pinsrb xmm4, byte ptr [rsi + r13 + 1], 6 - mov r14, r9 - pinsrb xmm4, byte ptr [rsi + r9 + 1], 7 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rbx + 1], 8 - pinsrb xmm4, byte ptr [rsi + r11 + 1], 9 - pinsrb xmm4, byte ptr [rsi + r15 + 1], 10 - pinsrb xmm4, byte ptr [rsi + r12 + 1], 11 - pinsrb xmm4, byte ptr [rsi + r8 + 1], 12 - mov r9, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r9 + 1], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 1], 14 - pinsrb xmm4, byte ptr [rsi + r10 + 1], 15 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r9 + 2], 1 - pinsrb xmm6, byte ptr [rsi + rcx + 2], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rax + 2], 3 - pinsrb xmm6, byte ptr [rsi + rdx + 2], 4 - pinsrb xmm6, byte ptr [rsi + rdi + 2], 5 - pinsrb xmm6, byte ptr [rsi + r13 + 2], 6 - pinsrb xmm6, byte ptr [rsi + r14 + 2], 7 - pinsrb xmm6, byte ptr [rsi + rbx + 2], 8 - pinsrb xmm6, byte ptr [rsi + r11 + 2], 9 - pinsrb xmm6, byte ptr [rsi + r15 + 2], 10 - pinsrb xmm6, byte ptr [rsi + r12 + 2], 11 - pinsrb xmm6, byte ptr [rsi + r8 + 2], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rax + 2], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rax + 2], 14 - pinsrb xmm6, byte ptr [rsi + r10 + 2], 15 - pinsrb xmm14, byte ptr [rsi + r9 + 8], 1 - pinsrb xmm14, byte ptr [rsi + rcx + 8], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 8], 3 - pinsrb xmm14, byte ptr [rsi + rdx + 8], 4 - pinsrb xmm14, byte ptr [rsi + rdi + 8], 5 - pinsrb xmm14, byte ptr [rsi + r13 + 8], 6 - pinsrb xmm14, byte ptr [rsi + r14 + 8], 7 - pinsrb xmm14, byte ptr [rsi + rbx + 8], 8 - pinsrb xmm14, byte ptr [rsi + r11 + 8], 9 - pinsrb xmm14, byte ptr [rsi + r15 + 8], 10 - pinsrb xmm14, byte ptr [rsi + r12 + 8], 11 - pinsrb xmm14, byte ptr [rsi + r8 + 8], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 8], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 8], 14 - pinsrb xmm14, byte ptr [rsi + r10 + 8], 15 - movdqa xmm10, xmm14 - pminub xmm10, xmm12 - pcmpeqb xmm10, xmm14 - pinsrb xmm13, byte ptr [rsi + r9 + 16], 1 - pinsrb xmm13, byte ptr [rsi + rcx + 16], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rax + 16], 3 - pinsrb xmm13, byte ptr [rsi + rdx + 16], 4 - mov rax, rdx - mov qword ptr [rsp + 88], rdx # 8-byte Spill - pinsrb xmm13, byte ptr [rsi + rdi + 16], 5 - mov qword ptr [rsp + 80], rdi # 8-byte Spill - pinsrb xmm13, byte ptr [rsi + r13 + 16], 6 - pinsrb xmm13, byte ptr [rsi + r14 + 16], 7 - pinsrb xmm13, byte ptr [rsi + rbx + 16], 8 - mov r13, rbx - pinsrb xmm13, byte ptr [rsi + r11 + 16], 9 - mov qword ptr [rsp + 128], r11 # 8-byte Spill - pinsrb xmm13, byte ptr [rsi + r15 + 16], 10 - mov qword ptr [rsp + 48], r15 # 8-byte Spill - pinsrb xmm13, byte ptr [rsi + r12 + 16], 11 - pinsrb xmm13, byte ptr [rsi + r8 + 16], 12 - mov rbx, r8 - mov qword ptr [rsp + 56], r8 # 8-byte Spill - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rdx + 16], 13 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r10 + 16], 14 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r8 + 16], 15 - movdqa xmm3, xmm13 - pminub xmm3, xmm12 - pcmpeqb xmm3, xmm13 - movdqa xmmword ptr [rsp + 272], xmm3 # 16-byte Spill - pinsrb xmm15, byte ptr [rsi + r9 + 24], 1 - pinsrb xmm15, byte ptr [rsi + rcx + 24], 2 - mov r9, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r9 + 24], 3 - pinsrb xmm15, byte ptr [rsi + rax + 24], 4 - pinsrb xmm15, byte ptr [rsi + rdi + 24], 5 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rax + 24], 6 - pinsrb xmm15, byte ptr [rsi + r14 + 24], 7 - pinsrb xmm15, byte ptr [rsi + r13 + 24], 8 - mov rax, r13 - pinsrb xmm15, byte ptr [rsi + r11 + 24], 9 - pinsrb xmm15, byte ptr [rsi + r15 + 24], 10 - pinsrb xmm15, byte ptr [rsi + r12 + 24], 11 - mov rcx, r12 - pinsrb xmm15, byte ptr [rsi + rbx + 24], 12 - pinsrb xmm15, byte ptr [rsi + rdx + 24], 13 - pinsrb xmm15, byte ptr [rsi + r10 + 24], 14 - mov r13, r10 - pinsrb xmm15, byte ptr [rsi + r8 + 24], 15 - movdqa xmm3, xmm15 - pminub xmm3, xmm12 - pcmpeqb xmm3, xmm15 - movdqa xmmword ptr [rsp + 240], xmm3 # 16-byte Spill - movdqa xmm14, xmm4 - pminub xmm14, xmm12 - pcmpeqb xmm14, xmm4 - movdqa xmm13, xmm14 - movdqa xmm4, xmmword ptr [rip + .LCPI7_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pandn xmm13, xmm4 - paddb xmm13, xmm14 - movdqa xmm14, xmm6 - pminub xmm14, xmm12 - pcmpeqb xmm14, xmm6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - movzx edx, byte ptr [rsi + rdx + 13] - movd xmm6, edx - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdi + 3], 1 - mov r11, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r11 + 3], 2 - pinsrb xmm5, byte ptr [rsi + r9 + 3], 3 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rbx + 3], 4 - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 3], 5 - mov rdx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 3], 6 - mov qword ptr [rsp + 144], r14 # 8-byte Spill - pinsrb xmm5, byte ptr [rsi + r14 + 3], 7 - pinsrb xmm5, byte ptr [rsi + rax + 3], 8 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r15 + 3], 9 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r12 + 3], 10 - pinsrb xmm5, byte ptr [rsi + rcx + 3], 11 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 3], 12 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r10 + 3], 13 - mov r14, r13 - pinsrb xmm5, byte ptr [rsi + r13 + 3], 14 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r13 + 3], 15 - pinsrb xmm9, byte ptr [rsi + rdi + 4], 1 - pinsrb xmm9, byte ptr [rsi + r11 + 4], 2 - pinsrb xmm9, byte ptr [rsi + r9 + 4], 3 - pinsrb xmm9, byte ptr [rsi + rbx + 4], 4 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r8 + 4], 5 - pinsrb xmm9, byte ptr [rsi + rdx + 4], 6 - mov rcx, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rcx + 4], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rcx + 4], 8 - pinsrb xmm9, byte ptr [rsi + r15 + 4], 9 - pinsrb xmm9, byte ptr [rsi + r12 + 4], 10 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rcx + 4], 11 - mov r8, rax - pinsrb xmm9, byte ptr [rsi + rax + 4], 12 - pinsrb xmm9, byte ptr [rsi + r10 + 4], 13 - pinsrb xmm9, byte ptr [rsi + r14 + 4], 14 - pinsrb xmm9, byte ptr [rsi + r13 + 4], 15 - pinsrb xmm7, byte ptr [rsi + rdi + 5], 1 - pinsrb xmm7, byte ptr [rsi + r11 + 5], 2 - pinsrb xmm7, byte ptr [rsi + r9 + 5], 3 - pinsrb xmm7, byte ptr [rsi + rbx + 5], 4 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 5], 5 - pinsrb xmm7, byte ptr [rsi + rdx + 5], 6 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 5], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rcx + 5], 8 - pinsrb xmm7, byte ptr [rsi + r15 + 5], 9 - pinsrb xmm7, byte ptr [rsi + r12 + 5], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 5], 11 - pinsrb xmm7, byte ptr [rsi + r8 + 5], 12 - pinsrb xmm7, byte ptr [rsi + r10 + 5], 13 - pinsrb xmm7, byte ptr [rsi + r14 + 5], 14 - pinsrb xmm7, byte ptr [rsi + r13 + 5], 15 - pinsrb xmm0, byte ptr [rsi + rdi + 6], 1 - pinsrb xmm0, byte ptr [rsi + r11 + 6], 2 - pinsrb xmm0, byte ptr [rsi + r9 + 6], 3 - pinsrb xmm0, byte ptr [rsi + rbx + 6], 4 - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdi + 6], 5 - pinsrb xmm0, byte ptr [rsi + rdx + 6], 6 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r9 + 6], 7 - pinsrb xmm0, byte ptr [rsi + rcx + 6], 8 - pinsrb xmm0, byte ptr [rsi + r15 + 6], 9 - pinsrb xmm0, byte ptr [rsi + r12 + 6], 10 - pinsrb xmm0, byte ptr [rsi + rax + 6], 11 - pinsrb xmm0, byte ptr [rsi + r8 + 6], 12 - pinsrb xmm0, byte ptr [rsi + r10 + 6], 13 - pandn xmm8, xmm4 - pinsrb xmm0, byte ptr [rsi + r14 + 6], 14 - mov r12, r14 - movdqa xmm4, xmmword ptr [rip + .LCPI7_11] # xmm4 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm14, xmm4 - por xmm14, xmm8 - movdqa xmm15, xmm5 - pminub xmm15, xmm12 - pcmpeqb xmm15, xmm5 - mov rbx, qword ptr [rsp + 160] # 8-byte Reload - movzx edx, byte ptr [rsi + rbx + 14] - movd xmm5, edx - movdqa xmm4, xmmword ptr [rip + .LCPI7_12] # xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm15, xmm4 - por xmm15, xmm14 - movzx edx, byte ptr [rsi + rbx + 15] - movd xmm8, edx - pcmpeqd xmm3, xmm3 - psubb xmm13, xmm3 - pcmpeqd xmm14, xmm14 - por xmm15, xmm13 - movdqa xmm4, xmm9 - pminub xmm4, xmm12 - pcmpeqb xmm4, xmm9 - movdqa xmm9, xmm7 - pminub xmm9, xmm12 - pcmpeqb xmm9, xmm7 - movzx edx, byte ptr [rsi + rbx + 17] - movd xmm7, edx - pinsrb xmm0, byte ptr [rsi + r13 + 6], 15 - movdqa xmm1, xmmword ptr [rip + .LCPI7_13] # xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm4, xmm1 - movdqa xmm1, xmmword ptr [rip + .LCPI7_14] # xmm1 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm9, xmm1 - por xmm9, xmm4 - movdqa xmm4, xmm0 - pminub xmm4, xmm12 - pcmpeqb xmm4, xmm0 - movzx edx, byte ptr [rsi + rbx + 18] - movd xmm1, edx - movdqa xmm0, xmmword ptr [rsp + 192] # 16-byte Reload - mov r10, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r10 + 7], 1 - mov r11, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r11 + 7], 2 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r14 + 7], 3 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rcx + 7], 4 - pinsrb xmm0, byte ptr [rsi + rdi + 7], 5 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r15 + 7], 6 - pinsrb xmm0, byte ptr [rsi + r9 + 7], 7 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rcx + 7], 8 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rcx + 7], 9 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rcx + 7], 10 - mov r8, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r8 + 7], 11 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rcx + 7], 12 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 7], 13 - pinsrb xmm0, byte ptr [rsi + r12 + 7], 14 - pinsrb xmm0, byte ptr [rsi + r13 + 7], 15 - movdqa xmm3, xmmword ptr [rip + .LCPI7_15] # xmm3 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm4, xmm3 - por xmm4, xmm9 - movdqa xmm9, xmm0 - pminub xmm9, xmm12 - pcmpeqb xmm9, xmm0 - movzx edx, byte ptr [rsi + rbx + 19] - movd xmm3, edx - pxor xmm9, xmm14 - psllw xmm9, 7 - movdqa xmm0, xmmword ptr [rip + .LCPI7_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm9, xmm0 - por xmm9, xmm4 - movdqa xmm4, xmm9 - movzx edx, byte ptr [rsi + rbx + 20] - movd xmm9, edx - movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload - mov r12, r10 - pinsrb xmm0, byte ptr [rsi + r10 + 9], 1 - pinsrb xmm0, byte ptr [rsi + r11 + 9], 2 - mov r13, r14 - pinsrb xmm0, byte ptr [rsi + r14 + 9], 3 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 9], 4 - pinsrb xmm0, byte ptr [rsi + rdi + 9], 5 - mov r9, r15 - pinsrb xmm0, byte ptr [rsi + r15 + 9], 6 - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 9], 7 - mov r14, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r14 + 9], 8 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r11 + 9], 9 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r15 + 9], 10 - pinsrb xmm0, byte ptr [rsi + r8 + 9], 11 - pinsrb xmm0, byte ptr [rsi + rcx + 9], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rbx + 9], 13 - mov r10, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r10 + 9], 14 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 9], 15 - pinsrb xmm2, byte ptr [rsi + r12 + 10], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 10], 2 - pinsrb xmm2, byte ptr [rsi + r13 + 10], 3 - mov r12, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r12 + 10], 4 - pinsrb xmm2, byte ptr [rsi + rdi + 10], 5 - pinsrb xmm2, byte ptr [rsi + r9 + 10], 6 - pinsrb xmm2, byte ptr [rsi + rdx + 10], 7 - mov rdi, rdx - pinsrb xmm2, byte ptr [rsi + r14 + 10], 8 - pinsrb xmm2, byte ptr [rsi + r11 + 10], 9 - pinsrb xmm2, byte ptr [rsi + r15 + 10], 10 - pinsrb xmm2, byte ptr [rsi + r8 + 10], 11 - pinsrb xmm2, byte ptr [rsi + rcx + 10], 12 - pinsrb xmm2, byte ptr [rsi + rbx + 10], 13 - pinsrb xmm2, byte ptr [rsi + r10 + 10], 14 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r13 + 10], 15 - por xmm4, xmm15 - movdqa xmmword ptr [rsp + 208], xmm4 # 16-byte Spill - movdqa xmm4, xmm0 - pminub xmm4, xmm12 - pcmpeqb xmm4, xmm0 - movdqa xmm13, xmm4 - movdqa xmm14, xmmword ptr [rip + .LCPI7_10] # xmm14 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pandn xmm13, xmm14 - paddb xmm13, xmm4 - movdqa xmm0, xmm2 - pminub xmm0, xmm12 - pcmpeqb xmm0, xmm2 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 21] - movd xmm4, edx - pandn xmm10, xmm14 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r11 + 11], 1 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r10 + 11], 2 - mov r14, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r14 + 11], 3 - mov r8, r12 - pinsrb xmm11, byte ptr [rsi + r12 + 11], 4 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r9 + 11], 5 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rcx + 11], 6 - pinsrb xmm11, byte ptr [rsi + rdi + 11], 7 - mov r12, rdi - mov r15, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r15 + 11], 8 - mov rbx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rbx + 11], 9 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 11], 10 - mov rdx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 11], 11 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdi + 11], 12 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 11], 13 - mov rdx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 11], 14 - pinsrb xmm11, byte ptr [rsi + r13 + 11], 15 - pandn xmm0, xmmword ptr [rip + .LCPI7_11] - por xmm0, xmm10 - movdqa xmm10, xmm11 - pminub xmm10, xmm12 - pcmpeqb xmm10, xmm11 - movzx edx, byte ptr [rsi + rax + 22] - movd xmm15, edx - pandn xmm10, xmmword ptr [rip + .LCPI7_12] - por xmm10, xmm0 - movzx edx, byte ptr [rsi + rax + 23] - movd xmm11, edx - mov rax, r11 - movdqa xmm0, xmmword ptr [rsp + 304] # 16-byte Reload - pinsrb xmm0, byte ptr [rsi + r11 + 12], 1 - pinsrb xmm0, byte ptr [rsi + r10 + 12], 2 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx ebx, byte ptr [r12 + rdi] + xor sil, bl + and dl, sil + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10b, byte ptr [r14 + rax + 1] + lea rax, [rax + 2] + sbb esi, esi + xor sil, dl + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, sil + xor bl, dl + mov byte ptr [r12 + rdi], bl + cmp r9, rax + jne .LBB7_81 +# %bb.82: + add r14, rax +.LBB7_83: + test r8b, 1 + je .LBB7_226 +# %bb.84: + mov cl, byte ptr [rsp + 280] # 1-byte Reload + cmp cl, byte ptr [r14] + sbb edx, edx + mov rsi, rax + shr rsi, 3 + mov dil, byte ptr [r12 + rsi] + and al, 7 + mov bl, 1 + mov ecx, eax + shl bl, cl + xor dl, dil + and bl, dl + xor bl, dil + mov byte ptr [r12 + rsi], bl + jmp .LBB7_226 +.LBB7_155: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB7_156: # =>This Inner Loop Header: Depth=1 + cmp r13d, dword ptr [rsi] + sbb edi, edi + mov rdx, r11 + shr rdx, 3 + movzx r10d, byte ptr [r12 + rdx] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r12 + rdx], al + add r11, 2 + cmp r13d, dword ptr [rsi + 4] + lea rsi, [rsi + 8] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r12 + rdx], bl + cmp r9, r11 + jne .LBB7_156 +.LBB7_22: + test r8b, 1 + je .LBB7_226 +# %bb.23: + cmp r13d, dword ptr [rsi] + jmp .LBB7_127 +.LBB7_220: + mov r9, r8 + and r9, -2 + xor r10d, r10d + .p2align 4, 0x90 +.LBB7_221: # =>This Inner Loop Header: Depth=1 + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + seta al + neg al + mov rdi, r10 + shr rdi, 3 + mov ecx, r10d + and cl, 6 + mov bl, 1 + shl bl, cl + movzx edx, byte ptr [r12 + rdi] + xor al, dl + and bl, al + xor bl, dl + mov byte ptr [r12 + rdi], bl + add r10, 2 + movsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero + add rsi, 16 + ucomisd xmm1, xmm0 + seta al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r9, r10 + jne .LBB7_221 +.LBB7_222: + test r8b, 1 + je .LBB7_226 +# %bb.223: + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + seta al + neg al + mov rdx, r10 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r10b, 7 + mov bl, 1 + mov ecx, r10d + jmp .LBB7_224 +.LBB7_128: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB7_129: # =>This Inner Loop Header: Depth=1 + cmp r13w, word ptr [rsi] + sbb edi, edi + mov rdx, r11 + shr rdx, 3 + movzx r10d, byte ptr [r12 + rdx] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r12 + rdx], al + add r11, 2 + cmp r13w, word ptr [rsi + 2] + lea rsi, [rsi + 4] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r12 + rdx], bl + cmp r9, r11 + jne .LBB7_129 +.LBB7_125: + test r8b, 1 + je .LBB7_226 +# %bb.126: + cmp r13w, word ptr [rsi] +.LBB7_127: + sbb eax, eax + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al + jmp .LBB7_225 +.LBB7_192: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB7_193: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + setg al + neg al + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + setg al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB7_193 +.LBB7_190: + test r8b, 1 + je .LBB7_226 +# %bb.191: + cmp qword ptr [rsi], r13 +.LBB7_172: + setg al + neg al + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d +.LBB7_224: + shl bl, cl + xor al, sil + and bl, al +.LBB7_225: + xor bl, sil + mov byte ptr [r12 + rdx], bl + jmp .LBB7_226 +.LBB7_153: + mov r9, r8 + and r9, -2 + xor r14d, r14d + mov r11, qword ptr [rsp + 8] # 8-byte Reload + .p2align 4, 0x90 +.LBB7_154: # =>This Inner Loop Header: Depth=1 + mov rax, rsi + cmp word ptr [rsi], r13w + setg dl + neg dl + mov rdi, r14 + shr rdi, 3 + movzx r10d, byte ptr [r11 + rdi] + mov ecx, r14d + and cl, 6 + mov bl, 1 + shl bl, cl + xor dl, r10b + and bl, dl + xor bl, r10b + mov byte ptr [r11 + rdi], bl + add r14, 2 + cmp word ptr [rsi + 2], r13w + lea rsi, [rsi + 4] + setg dl + neg dl + xor dl, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, bl + mov byte ptr [r11 + rdi], al + cmp r9, r14 + jne .LBB7_154 +.LBB7_151: + test r8b, 1 + je .LBB7_226 +# %bb.152: + cmp word ptr [rsi], r13w + setg al + neg al + mov rdx, r14 + shr rdx, 3 + mov r8, qword ptr [rsp + 8] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r14b, 7 + mov bl, 1 + mov ecx, r14d +.LBB7_111: + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r8 + rdx], bl + jmp .LBB7_226 +.LBB7_217: + mov r9, r8 + and r9, -2 + xor r14d, r14d mov r11, r10 + mov rsi, rcx + .p2align 4, 0x90 +.LBB7_218: # =>This Inner Loop Header: Depth=1 + movss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + ucomiss xmm1, xmm0 + seta bl + neg bl + mov rdi, r14 + shr rdi, 3 + mov ecx, r14d + and cl, 6 + mov dl, 1 + shl dl, cl + movzx eax, byte ptr [r11 + rdi] + xor bl, al + and dl, bl + xor dl, al + mov byte ptr [r11 + rdi], dl + add r14, 2 + movss xmm1, dword ptr [rsi + 4] # xmm1 = mem[0],zero,zero,zero + add rsi, 8 + ucomiss xmm1, xmm0 + seta al + neg al + xor al, dl + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, al + xor bl, dl + mov byte ptr [r11 + rdi], bl + cmp r9, r14 + jne .LBB7_218 +# %bb.219: + mov rcx, rsi +.LBB7_215: + test r8b, 1 + je .LBB7_226 +# %bb.216: + movss xmm1, dword ptr [rcx] # xmm1 = mem[0],zero,zero,zero + ucomiss xmm1, xmm0 + seta al + neg al mov rdx, r14 - pinsrb xmm0, byte ptr [rsi + r14 + 12], 3 - pinsrb xmm0, byte ptr [rsi + r8 + 12], 4 - pinsrb xmm0, byte ptr [rsi + r9 + 12], 5 - pinsrb xmm0, byte ptr [rsi + rcx + 12], 6 - pinsrb xmm0, byte ptr [rsi + r12 + 12], 7 - pinsrb xmm0, byte ptr [rsi + r15 + 12], 8 - mov r12, rbx - pinsrb xmm0, byte ptr [rsi + rbx + 12], 9 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rbx + 12], 10 - mov r14, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r14 + 12], 11 - pinsrb xmm0, byte ptr [rsi + rdi + 12], 12 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rbx + 12], 13 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r9 + 12], 14 - mov r10, r13 - pinsrb xmm0, byte ptr [rsi + r13 + 12], 15 - pinsrb xmm6, byte ptr [rsi + rax + 13], 1 - pinsrb xmm6, byte ptr [rsi + r11 + 13], 2 - pinsrb xmm6, byte ptr [rsi + rdx + 13], 3 - pinsrb xmm6, byte ptr [rsi + r8 + 13], 4 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rax + 13], 5 - pinsrb xmm6, byte ptr [rsi + rcx + 13], 6 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r11 + 13], 7 - pinsrb xmm6, byte ptr [rsi + r15 + 13], 8 - pinsrb xmm6, byte ptr [rsi + r12 + 13], 9 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 13], 10 - pinsrb xmm6, byte ptr [rsi + r14 + 13], 11 - pinsrb xmm6, byte ptr [rsi + rdi + 13], 12 - pinsrb xmm6, byte ptr [rsi + rbx + 13], 13 - pinsrb xmm6, byte ptr [rsi + r9 + 13], 14 - pinsrb xmm6, byte ptr [rsi + r13 + 13], 15 - mov r9, r13 - psubb xmm13, xmmword ptr [rip + .LCPI7_16] - por xmm10, xmm13 - movdqa xmm2, xmm0 - movdqa xmm13, xmm12 - pminub xmm2, xmm12 - pcmpeqb xmm2, xmm0 - movdqa xmm0, xmm6 - pminub xmm0, xmm12 - pcmpeqb xmm0, xmm6 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - movzx edx, byte ptr [rsi + rdx + 25] - movd xmm12, edx - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rbx + 14], 1 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r13 + 14], 2 - mov rdx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rdx + 14], 3 - pinsrb xmm5, byte ptr [rsi + r8 + 14], 4 - mov r8, rax - pinsrb xmm5, byte ptr [rsi + rax + 14], 5 - pinsrb xmm5, byte ptr [rsi + rcx + 14], 6 - mov r10, r11 - pinsrb xmm5, byte ptr [rsi + r11 + 14], 7 - mov r14, r15 - pinsrb xmm5, byte ptr [rsi + r15 + 14], 8 - mov rdi, r12 - pinsrb xmm5, byte ptr [rsi + r12 + 14], 9 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r11 + 14], 10 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r15 + 14], 11 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r12 + 14], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 14], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 14], 14 - pinsrb xmm5, byte ptr [rsi + r9 + 14], 15 - pinsrb xmm8, byte ptr [rsi + rbx + 15], 1 - pinsrb xmm8, byte ptr [rsi + r13 + 15], 2 - pinsrb xmm8, byte ptr [rsi + rdx + 15], 3 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r13 + 15], 4 - pinsrb xmm8, byte ptr [rsi + r8 + 15], 5 - pinsrb xmm8, byte ptr [rsi + rcx + 15], 6 - pinsrb xmm8, byte ptr [rsi + r10 + 15], 7 - pinsrb xmm8, byte ptr [rsi + r14 + 15], 8 - pinsrb xmm8, byte ptr [rsi + rdi + 15], 9 - pinsrb xmm8, byte ptr [rsi + r11 + 15], 10 - pinsrb xmm8, byte ptr [rsi + r15 + 15], 11 - pinsrb xmm8, byte ptr [rsi + r12 + 15], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rax + 15], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rax + 15], 14 - pinsrb xmm8, byte ptr [rsi + r9 + 15], 15 - pinsrb xmm7, byte ptr [rsi + rbx + 17], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 17], 2 - pinsrb xmm7, byte ptr [rsi + rdx + 17], 3 - pinsrb xmm7, byte ptr [rsi + r13 + 17], 4 - pinsrb xmm7, byte ptr [rsi + r8 + 17], 5 - pinsrb xmm7, byte ptr [rsi + rcx + 17], 6 - pinsrb xmm7, byte ptr [rsi + r10 + 17], 7 - pinsrb xmm7, byte ptr [rsi + r14 + 17], 8 - pinsrb xmm7, byte ptr [rsi + rdi + 17], 9 - pinsrb xmm7, byte ptr [rsi + r11 + 17], 10 - pinsrb xmm7, byte ptr [rsi + r15 + 17], 11 - pinsrb xmm7, byte ptr [rsi + r12 + 17], 12 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r13 + 17], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rax + 17], 14 - pinsrb xmm7, byte ptr [rsi + r9 + 17], 15 - pinsrb xmm1, byte ptr [rsi + rbx + 18], 1 - mov rbx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rbx + 18], 2 - pinsrb xmm1, byte ptr [rsi + rdx + 18], 3 - mov rax, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rax + 18], 4 - pinsrb xmm1, byte ptr [rsi + r8 + 18], 5 - pinsrb xmm1, byte ptr [rsi + rcx + 18], 6 - pinsrb xmm1, byte ptr [rsi + r10 + 18], 7 - pinsrb xmm1, byte ptr [rsi + r14 + 18], 8 - mov r10, r14 - pinsrb xmm1, byte ptr [rsi + rdi + 18], 9 - pinsrb xmm1, byte ptr [rsi + r11 + 18], 10 - pinsrb xmm1, byte ptr [rsi + r15 + 18], 11 - pinsrb xmm1, byte ptr [rsi + r12 + 18], 12 - pinsrb xmm1, byte ptr [rsi + r13 + 18], 13 - pandn xmm2, xmmword ptr [rip + .LCPI7_13] - pandn xmm0, xmmword ptr [rip + .LCPI7_14] - por xmm0, xmm2 - movdqa xmm2, xmm5 - pminub xmm2, xmm13 - pcmpeqb xmm2, xmm5 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 26] - movd xmm5, edx - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r9 + 18], 14 - pandn xmm2, xmmword ptr [rip + .LCPI7_15] - por xmm2, xmm0 - movdqa xmm6, xmm8 - pminub xmm6, xmm13 - pcmpeqb xmm6, xmm8 - movzx edx, byte ptr [rsi + rax + 27] - movd xmm0, edx - mov r8, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r8 + 18], 15 - pxor xmm6, xmmword ptr [rip + .LCPI7_16] - psllw xmm6, 7 - pand xmm6, xmmword ptr [rip + .LCPI7_6] - por xmm6, xmm2 - movzx edx, byte ptr [rsi + rax + 28] - movd xmm8, edx - por xmm6, xmm10 - movdqa xmmword ptr [rsp + 192], xmm6 # 16-byte Spill - movdqa xmm2, xmm7 - pminub xmm2, xmm13 - pcmpeqb xmm2, xmm7 - movdqa xmm14, xmm2 - pandn xmm14, xmmword ptr [rip + .LCPI7_10] - paddb xmm14, xmm2 - movdqa xmm10, xmm1 - pminub xmm10, xmm13 - pcmpeqb xmm10, xmm1 - movzx edx, byte ptr [rsi + rax + 29] - movd xmm6, edx - movzx edx, byte ptr [rsi + rax + 30] - movzx ecx, byte ptr [rsi + rax + 31] - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rax + 19], 1 - pinsrb xmm9, byte ptr [rsi + rax + 20], 1 - pinsrb xmm4, byte ptr [rsi + rax + 21], 1 - pinsrb xmm15, byte ptr [rsi + rax + 22], 1 - pinsrb xmm11, byte ptr [rsi + rax + 23], 1 - pinsrb xmm12, byte ptr [rsi + rax + 25], 1 - pinsrb xmm5, byte ptr [rsi + rax + 26], 1 - pinsrb xmm0, byte ptr [rsi + rax + 27], 1 - pinsrb xmm8, byte ptr [rsi + rax + 28], 1 - pinsrb xmm6, byte ptr [rsi + rax + 29], 1 - movd xmm1, edx - pinsrb xmm1, byte ptr [rsi + rax + 30], 1 - movd xmm7, ecx - pinsrb xmm7, byte ptr [rsi + rax + 31], 1 - mov rax, rbx - pinsrb xmm3, byte ptr [rsi + rbx + 19], 2 - pinsrb xmm9, byte ptr [rsi + rbx + 20], 2 - pinsrb xmm4, byte ptr [rsi + rbx + 21], 2 - pinsrb xmm15, byte ptr [rsi + rbx + 22], 2 - pinsrb xmm11, byte ptr [rsi + rbx + 23], 2 - pinsrb xmm12, byte ptr [rsi + rbx + 25], 2 - pinsrb xmm5, byte ptr [rsi + rbx + 26], 2 - pinsrb xmm0, byte ptr [rsi + rbx + 27], 2 - pinsrb xmm8, byte ptr [rsi + rbx + 28], 2 - pinsrb xmm6, byte ptr [rsi + rbx + 29], 2 - pinsrb xmm1, byte ptr [rsi + rbx + 30], 2 - pinsrb xmm7, byte ptr [rsi + rbx + 31], 2 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rax + 19], 3 - mov rdx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 19], 4 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 19], 5 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdi + 19], 6 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r14 + 19], 7 - mov r12, r10 - pinsrb xmm3, byte ptr [rsi + r10 + 19], 8 - mov r11, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r11 + 19], 9 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r15 + 19], 10 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r10 + 19], 11 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rbx + 19], 12 - pinsrb xmm3, byte ptr [rsi + r13 + 19], 13 - pinsrb xmm3, byte ptr [rsi + r9 + 19], 14 - pinsrb xmm3, byte ptr [rsi + r8 + 19], 15 - pinsrb xmm9, byte ptr [rsi + rax + 20], 3 - pinsrb xmm9, byte ptr [rsi + rdx + 20], 4 - pinsrb xmm9, byte ptr [rsi + rcx + 20], 5 - pinsrb xmm9, byte ptr [rsi + rdi + 20], 6 - pinsrb xmm9, byte ptr [rsi + r14 + 20], 7 - pinsrb xmm9, byte ptr [rsi + r12 + 20], 8 - pinsrb xmm9, byte ptr [rsi + r11 + 20], 9 - pinsrb xmm9, byte ptr [rsi + r15 + 20], 10 - pinsrb xmm9, byte ptr [rsi + r10 + 20], 11 - pinsrb xmm9, byte ptr [rsi + rbx + 20], 12 - pinsrb xmm9, byte ptr [rsi + r13 + 20], 13 - pinsrb xmm9, byte ptr [rsi + r9 + 20], 14 - pinsrb xmm9, byte ptr [rsi + r8 + 20], 15 - pinsrb xmm4, byte ptr [rsi + rax + 21], 3 - pinsrb xmm4, byte ptr [rsi + rdx + 21], 4 - pinsrb xmm4, byte ptr [rsi + rcx + 21], 5 - pinsrb xmm4, byte ptr [rsi + rdi + 21], 6 - pinsrb xmm4, byte ptr [rsi + r14 + 21], 7 - pinsrb xmm4, byte ptr [rsi + r12 + 21], 8 - pinsrb xmm4, byte ptr [rsi + r11 + 21], 9 - pinsrb xmm4, byte ptr [rsi + r15 + 21], 10 - pinsrb xmm4, byte ptr [rsi + r10 + 21], 11 - pinsrb xmm4, byte ptr [rsi + rbx + 21], 12 - mov r8, rbx - pinsrb xmm4, byte ptr [rsi + r13 + 21], 13 - pinsrb xmm4, byte ptr [rsi + r9 + 21], 14 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rbx + 21], 15 - pinsrb xmm15, byte ptr [rsi + rax + 22], 3 - pinsrb xmm15, byte ptr [rsi + rdx + 22], 4 - pinsrb xmm15, byte ptr [rsi + rcx + 22], 5 - pinsrb xmm15, byte ptr [rsi + rdi + 22], 6 - pinsrb xmm15, byte ptr [rsi + r14 + 22], 7 - pinsrb xmm15, byte ptr [rsi + r12 + 22], 8 - pinsrb xmm15, byte ptr [rsi + r11 + 22], 9 - pinsrb xmm15, byte ptr [rsi + r15 + 22], 10 - movdqa xmm2, xmmword ptr [rsp + 272] # 16-byte Reload - pandn xmm2, xmmword ptr [rip + .LCPI7_10] - pinsrb xmm15, byte ptr [rsi + r10 + 22], 11 - pandn xmm10, xmmword ptr [rip + .LCPI7_11] - por xmm10, xmm2 - pinsrb xmm15, byte ptr [rsi + r8 + 22], 12 - movdqa xmm2, xmm3 - pminub xmm2, xmm13 - pcmpeqb xmm2, xmm3 - pinsrb xmm15, byte ptr [rsi + r13 + 22], 13 - pandn xmm2, xmmword ptr [rip + .LCPI7_12] - por xmm2, xmm10 - pinsrb xmm15, byte ptr [rsi + r9 + 22], 14 - mov rdi, r9 - psubb xmm14, xmmword ptr [rip + .LCPI7_16] - por xmm2, xmm14 - movdqa xmm10, xmm9 - pminub xmm10, xmm13 - pcmpeqb xmm10, xmm9 - movdqa xmm3, xmm4 - movdqa xmm9, xmm13 - pminub xmm3, xmm13 - pcmpeqb xmm3, xmm4 - pinsrb xmm15, byte ptr [rsi + rbx + 22], 15 - movdqa xmm13, xmmword ptr [rip + .LCPI7_13] # xmm13 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm10, xmm13 - movdqa xmm4, xmmword ptr [rip + .LCPI7_14] # xmm4 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm3, xmm4 - por xmm3, xmm10 - movdqa xmm4, xmm15 - pminub xmm4, xmm9 - movdqa xmm13, xmm9 - pcmpeqb xmm4, xmm15 - pinsrb xmm11, byte ptr [rsi + rax + 23], 3 - pinsrb xmm11, byte ptr [rsi + rdx + 23], 4 - pinsrb xmm11, byte ptr [rsi + rcx + 23], 5 - mov r8, rcx - mov r9, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r9 + 23], 6 - pinsrb xmm11, byte ptr [rsi + r14 + 23], 7 - pinsrb xmm11, byte ptr [rsi + r12 + 23], 8 - pinsrb xmm11, byte ptr [rsi + r11 + 23], 9 - pinsrb xmm11, byte ptr [rsi + r15 + 23], 10 - pinsrb xmm11, byte ptr [rsi + r10 + 23], 11 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rcx + 23], 12 - pinsrb xmm11, byte ptr [rsi + r13 + 23], 13 - pinsrb xmm11, byte ptr [rsi + rdi + 23], 14 - pinsrb xmm11, byte ptr [rsi + rbx + 23], 15 - movdqa xmm15, xmmword ptr [rip + .LCPI7_15] # xmm15 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm4, xmm15 - por xmm4, xmm3 - movdqa xmm3, xmm11 - pminub xmm3, xmm9 - pcmpeqb xmm3, xmm11 - pxor xmm3, xmmword ptr [rip + .LCPI7_16] - psllw xmm3, 7 - movdqa xmm11, xmmword ptr [rip + .LCPI7_6] # xmm11 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm3, xmm11 - por xmm3, xmm4 - pinsrb xmm12, byte ptr [rsi + rax + 25], 3 - pinsrb xmm12, byte ptr [rsi + rdx + 25], 4 - pinsrb xmm12, byte ptr [rsi + r8 + 25], 5 - pinsrb xmm12, byte ptr [rsi + r9 + 25], 6 - pinsrb xmm12, byte ptr [rsi + r14 + 25], 7 - pinsrb xmm12, byte ptr [rsi + r12 + 25], 8 - pinsrb xmm12, byte ptr [rsi + r11 + 25], 9 - pinsrb xmm12, byte ptr [rsi + r15 + 25], 10 - pinsrb xmm12, byte ptr [rsi + r10 + 25], 11 - pinsrb xmm12, byte ptr [rsi + rcx + 25], 12 - pinsrb xmm12, byte ptr [rsi + r13 + 25], 13 - pinsrb xmm12, byte ptr [rsi + rdi + 25], 14 - pinsrb xmm12, byte ptr [rsi + rbx + 25], 15 - pinsrb xmm5, byte ptr [rsi + rax + 26], 3 - pinsrb xmm5, byte ptr [rsi + rdx + 26], 4 - pinsrb xmm5, byte ptr [rsi + r8 + 26], 5 - pinsrb xmm5, byte ptr [rsi + r9 + 26], 6 - pinsrb xmm5, byte ptr [rsi + r14 + 26], 7 - pinsrb xmm5, byte ptr [rsi + r12 + 26], 8 - pinsrb xmm5, byte ptr [rsi + r11 + 26], 9 - pinsrb xmm5, byte ptr [rsi + r15 + 26], 10 - pinsrb xmm5, byte ptr [rsi + r10 + 26], 11 - pinsrb xmm5, byte ptr [rsi + rcx + 26], 12 - pinsrb xmm5, byte ptr [rsi + r13 + 26], 13 - pinsrb xmm5, byte ptr [rsi + rdi + 26], 14 - pinsrb xmm5, byte ptr [rsi + rbx + 26], 15 - por xmm3, xmm2 - movdqa xmm2, xmm12 - pminub xmm2, xmm9 - pcmpeqb xmm2, xmm12 - movdqa xmm9, xmm2 - movdqa xmm10, xmmword ptr [rip + .LCPI7_10] # xmm10 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pandn xmm9, xmm10 - paddb xmm9, xmm2 - movdqa xmm4, xmm5 - pminub xmm4, xmm13 - pcmpeqb xmm4, xmm5 - movdqa xmm2, xmmword ptr [rsp + 240] # 16-byte Reload - pandn xmm2, xmm10 - pinsrb xmm0, byte ptr [rsi + rax + 27], 3 - pinsrb xmm0, byte ptr [rsi + rdx + 27], 4 - pinsrb xmm0, byte ptr [rsi + r8 + 27], 5 - pinsrb xmm0, byte ptr [rsi + r9 + 27], 6 - pinsrb xmm0, byte ptr [rsi + r14 + 27], 7 - pinsrb xmm0, byte ptr [rsi + r12 + 27], 8 - pinsrb xmm0, byte ptr [rsi + r11 + 27], 9 - pinsrb xmm0, byte ptr [rsi + r15 + 27], 10 - pinsrb xmm0, byte ptr [rsi + r10 + 27], 11 - pinsrb xmm0, byte ptr [rsi + rcx + 27], 12 - pinsrb xmm0, byte ptr [rsi + r13 + 27], 13 - pinsrb xmm0, byte ptr [rsi + rdi + 27], 14 - pinsrb xmm0, byte ptr [rsi + rbx + 27], 15 - pandn xmm4, xmmword ptr [rip + .LCPI7_11] - por xmm4, xmm2 - movdqa xmm2, xmm0 - pminub xmm2, xmm13 - pcmpeqb xmm2, xmm0 - pandn xmm2, xmmword ptr [rip + .LCPI7_12] - por xmm2, xmm4 - pinsrb xmm8, byte ptr [rsi + rax + 28], 3 - pinsrb xmm8, byte ptr [rsi + rdx + 28], 4 - pinsrb xmm8, byte ptr [rsi + r8 + 28], 5 - pinsrb xmm8, byte ptr [rsi + r9 + 28], 6 - pinsrb xmm8, byte ptr [rsi + r14 + 28], 7 - pinsrb xmm8, byte ptr [rsi + r12 + 28], 8 - pinsrb xmm8, byte ptr [rsi + r11 + 28], 9 - pinsrb xmm8, byte ptr [rsi + r15 + 28], 10 - pinsrb xmm8, byte ptr [rsi + r10 + 28], 11 - pinsrb xmm8, byte ptr [rsi + rcx + 28], 12 - pinsrb xmm8, byte ptr [rsi + r13 + 28], 13 - pinsrb xmm8, byte ptr [rsi + rdi + 28], 14 - pinsrb xmm8, byte ptr [rsi + rbx + 28], 15 - pinsrb xmm6, byte ptr [rsi + rax + 29], 3 - pinsrb xmm6, byte ptr [rsi + rdx + 29], 4 - pinsrb xmm6, byte ptr [rsi + r8 + 29], 5 - pinsrb xmm6, byte ptr [rsi + r9 + 29], 6 - pinsrb xmm6, byte ptr [rsi + r14 + 29], 7 - pinsrb xmm6, byte ptr [rsi + r12 + 29], 8 - pinsrb xmm6, byte ptr [rsi + r11 + 29], 9 - pinsrb xmm6, byte ptr [rsi + r15 + 29], 10 - pinsrb xmm6, byte ptr [rsi + r10 + 29], 11 - pinsrb xmm6, byte ptr [rsi + rcx + 29], 12 - pinsrb xmm6, byte ptr [rsi + r13 + 29], 13 - pinsrb xmm6, byte ptr [rsi + rdi + 29], 14 - pinsrb xmm6, byte ptr [rsi + rbx + 29], 15 - pcmpeqd xmm10, xmm10 - psubb xmm9, xmm10 - por xmm2, xmm9 - movdqa xmm0, xmm8 - pminub xmm0, xmm13 - pcmpeqb xmm0, xmm8 - movdqa xmm4, xmm6 - pminub xmm4, xmm13 - pcmpeqb xmm4, xmm6 - pinsrb xmm1, byte ptr [rsi + rax + 30], 3 - pinsrb xmm7, byte ptr [rsi + rax + 31], 3 - pinsrb xmm1, byte ptr [rsi + rdx + 30], 4 - pinsrb xmm7, byte ptr [rsi + rdx + 31], 4 - pinsrb xmm1, byte ptr [rsi + r8 + 30], 5 - pinsrb xmm7, byte ptr [rsi + r8 + 31], 5 - pinsrb xmm1, byte ptr [rsi + r9 + 30], 6 - pinsrb xmm7, byte ptr [rsi + r9 + 31], 6 - pinsrb xmm1, byte ptr [rsi + r14 + 30], 7 - pinsrb xmm7, byte ptr [rsi + r14 + 31], 7 - pinsrb xmm1, byte ptr [rsi + r12 + 30], 8 - pinsrb xmm7, byte ptr [rsi + r12 + 31], 8 - pinsrb xmm1, byte ptr [rsi + r11 + 30], 9 - pinsrb xmm7, byte ptr [rsi + r11 + 31], 9 - pinsrb xmm1, byte ptr [rsi + r15 + 30], 10 - pinsrb xmm7, byte ptr [rsi + r15 + 31], 10 - mov rax, qword ptr [rsp] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r10 + 30], 11 - pinsrb xmm7, byte ptr [rsi + r10 + 31], 11 - pinsrb xmm1, byte ptr [rsi + rcx + 30], 12 - pinsrb xmm7, byte ptr [rsi + rcx + 31], 12 - pinsrb xmm1, byte ptr [rsi + r13 + 30], 13 - pinsrb xmm7, byte ptr [rsi + r13 + 31], 13 - pinsrb xmm1, byte ptr [rsi + rdi + 30], 14 - pinsrb xmm7, byte ptr [rsi + rdi + 31], 14 - pinsrb xmm1, byte ptr [rsi + rbx + 30], 15 - pinsrb xmm7, byte ptr [rsi + rbx + 31], 15 - pandn xmm0, xmmword ptr [rip + .LCPI7_13] - pandn xmm4, xmmword ptr [rip + .LCPI7_14] - por xmm4, xmm0 - movdqa xmm0, xmm1 - pminub xmm0, xmm13 - pcmpeqb xmm0, xmm1 - pandn xmm0, xmm15 - por xmm0, xmm4 - movdqa xmm1, xmm7 - pminub xmm1, xmm13 - pcmpeqb xmm1, xmm7 - pxor xmm1, xmm10 - psllw xmm1, 7 - pand xmm1, xmm11 - por xmm1, xmm0 - por xmm1, xmm2 - movdqa xmm0, xmm3 - punpcklbw xmm0, xmm1 # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7] - movdqa xmm5, xmmword ptr [rsp + 208] # 16-byte Reload - movdqa xmm2, xmm5 - movdqa xmm6, xmmword ptr [rsp + 192] # 16-byte Reload - punpcklbw xmm2, xmm6 # xmm2 = xmm2[0],xmm6[0],xmm2[1],xmm6[1],xmm2[2],xmm6[2],xmm2[3],xmm6[3],xmm2[4],xmm6[4],xmm2[5],xmm6[5],xmm2[6],xmm6[6],xmm2[7],xmm6[7] - movdqa xmm4, xmm2 - punpcklwd xmm4, xmm0 # xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3] - punpckhwd xmm2, xmm0 # xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7] - punpckhbw xmm3, xmm1 # xmm3 = xmm3[8],xmm1[8],xmm3[9],xmm1[9],xmm3[10],xmm1[10],xmm3[11],xmm1[11],xmm3[12],xmm1[12],xmm3[13],xmm1[13],xmm3[14],xmm1[14],xmm3[15],xmm1[15] - punpckhbw xmm5, xmm6 # xmm5 = xmm5[8],xmm6[8],xmm5[9],xmm6[9],xmm5[10],xmm6[10],xmm5[11],xmm6[11],xmm5[12],xmm6[12],xmm5[13],xmm6[13],xmm5[14],xmm6[14],xmm5[15],xmm6[15] - movdqa xmm0, xmm5 - punpcklwd xmm0, xmm3 # xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3] - punpckhwd xmm5, xmm3 # xmm5 = xmm5[4],xmm3[4],xmm5[5],xmm3[5],xmm5[6],xmm3[6],xmm5[7],xmm3[7] - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - movdqu xmmword ptr [rax + 4*rcx + 48], xmm5 - movdqu xmmword ptr [rax + 4*rcx + 32], xmm0 - movdqu xmmword ptr [rax + 4*rcx + 16], xmm2 - mov qword ptr [rsp], rax # 8-byte Spill - movdqu xmmword ptr [rax + 4*rcx], xmm4 - add rcx, 16 + shr rdx, 3 + mov dil, byte ptr [r10 + rdx] + and r14b, 7 + mov bl, 1 + mov ecx, r14d + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r10 + rdx], bl +.LBB7_226: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.LBB7_142: + and rcx, -8 mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB7_67 -# %bb.68: - mov r15, qword ptr [rsp + 264] # 8-byte Reload - cmp r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10b, byte ptr [rsp + 8] # 1-byte Reload - mov r12, qword ptr [rsp + 320] # 8-byte Reload - jne .LBB7_69 - jmp .LBB7_72 -.LBB7_124: - and r15, -8 - mov rax, r15 shl rax, 6 add rax, rsi - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill - mov rax, qword ptr [rsp] # 8-byte Reload - lea rax, [rax + 4*r15] + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 40], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] mov qword ptr [rsp + 8], rax # 8-byte Spill - movd xmm0, dword ptr [rsp + 240] # 4-byte Folded Reload - # xmm0 = mem[0],zero,zero,zero + mov dword ptr [rsp + 56], r13d # 4-byte Spill + movd xmm0, r13d pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] xor r15d, r15d @@ -39837,55 +39085,56 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movdqa xmm12, xmmword ptr [rip + .LCPI7_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] movdqa xmm13, xmmword ptr [rip + .LCPI7_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] movdqa xmm14, xmmword ptr [rip + .LCPI7_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + mov qword ptr [rsp + 128], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB7_125: # =>This Inner Loop Header: Depth=1 +.LBB7_143: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 16], r15 # 8-byte Spill shl r15, 6 - mov r9, r15 + mov r8, r15 mov r12, r15 mov r13, r15 mov rcx, r15 - mov rdi, r15 mov rbx, r15 + mov rdi, r15 movzx r14d, word ptr [rsi + r15] movzx eax, word ptr [rsi + r15 + 2] movzx r11d, word ptr [rsi + r15 + 4] movzx edx, word ptr [rsi + r15 + 6] movzx r10d, word ptr [rsi + r15 + 8] - mov r8, r15 - or r8, 64 - or r9, 128 + mov r9, r15 + or r9, 64 + or r8, 128 or r12, 192 or r13, 256 or rcx, 320 - or rdi, 384 - or rbx, 448 + or rbx, 384 + or rdi, 448 movd xmm4, r14d - pinsrw xmm4, word ptr [rsi + r8], 1 - pinsrw xmm4, word ptr [rsi + r9], 2 + pinsrw xmm4, word ptr [rsi + r9], 1 + pinsrw xmm4, word ptr [rsi + r8], 2 pinsrw xmm4, word ptr [rsi + r12], 3 pinsrw xmm4, word ptr [rsi + r13], 4 pinsrw xmm4, word ptr [rsi + rcx], 5 - pinsrw xmm4, word ptr [rsi + rdi], 6 - pinsrw xmm4, word ptr [rsi + rbx], 7 + pinsrw xmm4, word ptr [rsi + rbx], 6 + pinsrw xmm4, word ptr [rsi + rdi], 7 movzx r14d, word ptr [rsi + r15 + 10] movd xmm6, eax - pinsrw xmm6, word ptr [rsi + r8 + 2], 1 - pinsrw xmm6, word ptr [rsi + r9 + 2], 2 + pinsrw xmm6, word ptr [rsi + r9 + 2], 1 + pinsrw xmm6, word ptr [rsi + r8 + 2], 2 pinsrw xmm6, word ptr [rsi + r12 + 2], 3 movzx eax, word ptr [rsi + r15 + 12] - mov dword ptr [rsp + 32], eax # 4-byte Spill + mov dword ptr [rsp + 24], eax # 4-byte Spill pinsrw xmm6, word ptr [rsi + r13 + 2], 4 movd xmm2, r11d movzx r11d, word ptr [rsi + r15 + 14] pinsrw xmm6, word ptr [rsi + rcx + 2], 5 movd xmm5, edx movzx edx, word ptr [rsi + r15 + 16] - pinsrw xmm6, word ptr [rsi + rdi + 2], 6 + pinsrw xmm6, word ptr [rsi + rbx + 2], 6 movd xmm3, r10d movzx eax, word ptr [rsi + r15 + 18] - mov dword ptr [rsp + 24], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + rbx + 2], 7 + mov dword ptr [rsp + 32], eax # 4-byte Spill + pinsrw xmm6, word ptr [rsi + rdi + 2], 7 pcmpgtw xmm6, xmm0 packsswb xmm6, xmm6 movdqa xmm1, xmm6 @@ -39896,29 +39145,29 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 pcmpgtw xmm4, xmm0 packsswb xmm4, xmm4 pand xmm4, xmm15 - pinsrw xmm2, word ptr [rsi + r8 + 4], 1 - pinsrw xmm2, word ptr [rsi + r9 + 4], 2 + pinsrw xmm2, word ptr [rsi + r9 + 4], 1 + pinsrw xmm2, word ptr [rsi + r8 + 4], 2 pinsrw xmm2, word ptr [rsi + r12 + 4], 3 pinsrw xmm2, word ptr [rsi + r13 + 4], 4 pinsrw xmm2, word ptr [rsi + rcx + 4], 5 - pinsrw xmm2, word ptr [rsi + rdi + 4], 6 - pinsrw xmm2, word ptr [rsi + rbx + 4], 7 - pinsrw xmm5, word ptr [rsi + r8 + 6], 1 - pinsrw xmm5, word ptr [rsi + r9 + 6], 2 + pinsrw xmm2, word ptr [rsi + rbx + 4], 6 + pinsrw xmm2, word ptr [rsi + rdi + 4], 7 + pinsrw xmm5, word ptr [rsi + r9 + 6], 1 + pinsrw xmm5, word ptr [rsi + r8 + 6], 2 pinsrw xmm5, word ptr [rsi + r12 + 6], 3 pinsrw xmm5, word ptr [rsi + r13 + 6], 4 pinsrw xmm5, word ptr [rsi + rcx + 6], 5 - pinsrw xmm5, word ptr [rsi + rdi + 6], 6 - pinsrw xmm5, word ptr [rsi + rbx + 6], 7 - pinsrw xmm3, word ptr [rsi + r8 + 8], 1 - pinsrw xmm3, word ptr [rsi + r9 + 8], 2 + pinsrw xmm5, word ptr [rsi + rbx + 6], 6 + pinsrw xmm5, word ptr [rsi + rdi + 6], 7 + pinsrw xmm3, word ptr [rsi + r9 + 8], 1 + pinsrw xmm3, word ptr [rsi + r8 + 8], 2 pinsrw xmm3, word ptr [rsi + r12 + 8], 3 pinsrw xmm3, word ptr [rsi + r13 + 8], 4 pinsrw xmm3, word ptr [rsi + rcx + 8], 5 - pinsrw xmm3, word ptr [rsi + rdi + 8], 6 - pinsrw xmm3, word ptr [rsi + rbx + 8], 7 + pinsrw xmm3, word ptr [rsi + rbx + 8], 6 + pinsrw xmm3, word ptr [rsi + rdi + 8], 7 por xmm1, xmm4 - movd xmm7, dword ptr [rsp + 32] # 4-byte Folded Reload + movd xmm7, dword ptr [rsp + 24] # 4-byte Folded Reload # xmm7 = mem[0],zero,zero,zero movzx eax, word ptr [rsi + r15 + 22] pcmpgtw xmm2, xmm0 @@ -39942,22 +39191,22 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 por xmm3, xmm5 movd xmm1, edx movzx edx, word ptr [rsi + r15 + 26] - pinsrw xmm6, word ptr [rsi + r8 + 10], 1 - pinsrw xmm6, word ptr [rsi + r9 + 10], 2 + pinsrw xmm6, word ptr [rsi + r9 + 10], 1 + pinsrw xmm6, word ptr [rsi + r8 + 10], 2 pinsrw xmm6, word ptr [rsi + r12 + 10], 3 pinsrw xmm6, word ptr [rsi + r13 + 10], 4 pinsrw xmm6, word ptr [rsi + rcx + 10], 5 - pinsrw xmm6, word ptr [rsi + rdi + 10], 6 - pinsrw xmm6, word ptr [rsi + rbx + 10], 7 - pinsrw xmm7, word ptr [rsi + r8 + 12], 1 - pinsrw xmm7, word ptr [rsi + r9 + 12], 2 + pinsrw xmm6, word ptr [rsi + rbx + 10], 6 + pinsrw xmm6, word ptr [rsi + rdi + 10], 7 + pinsrw xmm7, word ptr [rsi + r9 + 12], 1 + pinsrw xmm7, word ptr [rsi + r8 + 12], 2 pinsrw xmm7, word ptr [rsi + r12 + 12], 3 pinsrw xmm7, word ptr [rsi + r13 + 12], 4 pinsrw xmm7, word ptr [rsi + rcx + 12], 5 - pinsrw xmm7, word ptr [rsi + rdi + 12], 6 - pinsrw xmm7, word ptr [rsi + rbx + 12], 7 + pinsrw xmm7, word ptr [rsi + rbx + 12], 6 + pinsrw xmm7, word ptr [rsi + rdi + 12], 7 por xmm3, xmm2 - movd xmm8, dword ptr [rsp + 24] # 4-byte Folded Reload + movd xmm8, dword ptr [rsp + 32] # 4-byte Folded Reload # xmm8 = mem[0],zero,zero,zero movzx r14d, word ptr [rsi + r15 + 28] pcmpgtw xmm6, xmm0 @@ -39973,20 +39222,20 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 por xmm7, xmm6 movd xmm5, r10d movzx r10d, word ptr [rsi + r15 + 30] - pinsrw xmm4, word ptr [rsi + r8 + 14], 1 - pinsrw xmm4, word ptr [rsi + r9 + 14], 2 + pinsrw xmm4, word ptr [rsi + r9 + 14], 1 + pinsrw xmm4, word ptr [rsi + r8 + 14], 2 pinsrw xmm4, word ptr [rsi + r12 + 14], 3 pinsrw xmm4, word ptr [rsi + r13 + 14], 4 pinsrw xmm4, word ptr [rsi + rcx + 14], 5 - pinsrw xmm4, word ptr [rsi + rdi + 14], 6 - pinsrw xmm4, word ptr [rsi + rbx + 14], 7 - pinsrw xmm8, word ptr [rsi + r8 + 18], 1 - pinsrw xmm8, word ptr [rsi + r9 + 18], 2 + pinsrw xmm4, word ptr [rsi + rbx + 14], 6 + pinsrw xmm4, word ptr [rsi + rdi + 14], 7 + pinsrw xmm8, word ptr [rsi + r9 + 18], 1 + pinsrw xmm8, word ptr [rsi + r8 + 18], 2 pinsrw xmm8, word ptr [rsi + r12 + 18], 3 pinsrw xmm8, word ptr [rsi + r13 + 18], 4 pinsrw xmm8, word ptr [rsi + rcx + 18], 5 - pinsrw xmm8, word ptr [rsi + rdi + 18], 6 - pinsrw xmm8, word ptr [rsi + rbx + 18], 7 + pinsrw xmm8, word ptr [rsi + rbx + 18], 6 + pinsrw xmm8, word ptr [rsi + rdi + 18], 7 pcmpgtw xmm4, xmm0 packsswb xmm4, xmm4 psllw xmm4, 7 @@ -40002,13 +39251,13 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 psubb xmm7, xmm8 movd xmm3, r11d movzx r11d, word ptr [rsi + r15 + 34] - pinsrw xmm1, word ptr [rsi + r8 + 16], 1 - pinsrw xmm1, word ptr [rsi + r9 + 16], 2 + pinsrw xmm1, word ptr [rsi + r9 + 16], 1 + pinsrw xmm1, word ptr [rsi + r8 + 16], 2 pinsrw xmm1, word ptr [rsi + r12 + 16], 3 pinsrw xmm1, word ptr [rsi + r13 + 16], 4 pinsrw xmm1, word ptr [rsi + rcx + 16], 5 - pinsrw xmm1, word ptr [rsi + rdi + 16], 6 - pinsrw xmm1, word ptr [rsi + rbx + 16], 7 + pinsrw xmm1, word ptr [rsi + rbx + 16], 6 + pinsrw xmm1, word ptr [rsi + rdi + 16], 7 pcmpgtw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 @@ -40016,13 +39265,13 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movd xmm6, edx movzx edx, word ptr [rsi + r15 + 36] mov dword ptr [rsp + 48], edx # 4-byte Spill - pinsrw xmm5, word ptr [rsi + r8 + 20], 1 - pinsrw xmm5, word ptr [rsi + r9 + 20], 2 + pinsrw xmm5, word ptr [rsi + r9 + 20], 1 + pinsrw xmm5, word ptr [rsi + r8 + 20], 2 pinsrw xmm5, word ptr [rsi + r12 + 20], 3 pinsrw xmm5, word ptr [rsi + r13 + 20], 4 pinsrw xmm5, word ptr [rsi + rcx + 20], 5 - pinsrw xmm5, word ptr [rsi + rdi + 20], 6 - pinsrw xmm5, word ptr [rsi + rbx + 20], 7 + pinsrw xmm5, word ptr [rsi + rbx + 20], 6 + pinsrw xmm5, word ptr [rsi + rdi + 20], 7 pcmpgtw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 @@ -40031,21 +39280,21 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 por xmm5, xmm7 movd xmm7, r14d movzx edx, word ptr [rsi + r15 + 38] - mov dword ptr [rsp + 24], edx # 4-byte Spill - pinsrw xmm2, word ptr [rsi + r8 + 22], 1 - pinsrw xmm2, word ptr [rsi + r9 + 22], 2 + mov dword ptr [rsp + 32], edx # 4-byte Spill + pinsrw xmm2, word ptr [rsi + r9 + 22], 1 + pinsrw xmm2, word ptr [rsi + r8 + 22], 2 pinsrw xmm2, word ptr [rsi + r12 + 22], 3 pinsrw xmm2, word ptr [rsi + r13 + 22], 4 pinsrw xmm2, word ptr [rsi + rcx + 22], 5 - pinsrw xmm2, word ptr [rsi + rdi + 22], 6 - pinsrw xmm2, word ptr [rsi + rbx + 22], 7 - pinsrw xmm3, word ptr [rsi + r8 + 24], 1 - pinsrw xmm3, word ptr [rsi + r9 + 24], 2 + pinsrw xmm2, word ptr [rsi + rbx + 22], 6 + pinsrw xmm2, word ptr [rsi + rdi + 22], 7 + pinsrw xmm3, word ptr [rsi + r9 + 24], 1 + pinsrw xmm3, word ptr [rsi + r8 + 24], 2 pinsrw xmm3, word ptr [rsi + r12 + 24], 3 pinsrw xmm3, word ptr [rsi + r13 + 24], 4 pinsrw xmm3, word ptr [rsi + rcx + 24], 5 - pinsrw xmm3, word ptr [rsi + rdi + 24], 6 - pinsrw xmm3, word ptr [rsi + rbx + 24], 7 + pinsrw xmm3, word ptr [rsi + rbx + 24], 6 + pinsrw xmm3, word ptr [rsi + rdi + 24], 7 pcmpgtw xmm2, xmm0 packsswb xmm2, xmm2 pand xmm2, xmm15 @@ -40062,28 +39311,28 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 por xmm3, xmm5 movd xmm5, eax movzx eax, word ptr [rsi + r15 + 42] - mov dword ptr [rsp + 32], eax # 4-byte Spill - pinsrw xmm6, word ptr [rsi + r8 + 26], 1 - pinsrw xmm6, word ptr [rsi + r9 + 26], 2 + mov dword ptr [rsp + 24], eax # 4-byte Spill + pinsrw xmm6, word ptr [rsi + r9 + 26], 1 + pinsrw xmm6, word ptr [rsi + r8 + 26], 2 pinsrw xmm6, word ptr [rsi + r12 + 26], 3 pinsrw xmm6, word ptr [rsi + r13 + 26], 4 pinsrw xmm6, word ptr [rsi + rcx + 26], 5 - pinsrw xmm6, word ptr [rsi + rdi + 26], 6 - pinsrw xmm6, word ptr [rsi + rbx + 26], 7 - pinsrw xmm7, word ptr [rsi + r8 + 28], 1 - pinsrw xmm7, word ptr [rsi + r9 + 28], 2 + pinsrw xmm6, word ptr [rsi + rbx + 26], 6 + pinsrw xmm6, word ptr [rsi + rdi + 26], 7 + pinsrw xmm7, word ptr [rsi + r9 + 28], 1 + pinsrw xmm7, word ptr [rsi + r8 + 28], 2 pinsrw xmm7, word ptr [rsi + r12 + 28], 3 pinsrw xmm7, word ptr [rsi + r13 + 28], 4 pinsrw xmm7, word ptr [rsi + rcx + 28], 5 - pinsrw xmm7, word ptr [rsi + rdi + 28], 6 - pinsrw xmm7, word ptr [rsi + rbx + 28], 7 - pinsrw xmm2, word ptr [rsi + r8 + 30], 1 - pinsrw xmm2, word ptr [rsi + r9 + 30], 2 + pinsrw xmm7, word ptr [rsi + rbx + 28], 6 + pinsrw xmm7, word ptr [rsi + rdi + 28], 7 + pinsrw xmm2, word ptr [rsi + r9 + 30], 1 + pinsrw xmm2, word ptr [rsi + r8 + 30], 2 pinsrw xmm2, word ptr [rsi + r12 + 30], 3 pinsrw xmm2, word ptr [rsi + r13 + 30], 4 pinsrw xmm2, word ptr [rsi + rcx + 30], 5 - pinsrw xmm2, word ptr [rsi + rdi + 30], 6 - pinsrw xmm2, word ptr [rsi + rbx + 30], 7 + pinsrw xmm2, word ptr [rsi + rbx + 30], 6 + pinsrw xmm2, word ptr [rsi + rdi + 30], 7 pcmpgtw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -40105,54 +39354,54 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movd xmm6, dword ptr [rsp + 48] # 4-byte Folded Reload # xmm6 = mem[0],zero,zero,zero movzx edx, word ptr [rsi + r15 + 46] - pinsrw xmm5, word ptr [rsi + r8 + 32], 1 - pinsrw xmm5, word ptr [rsi + r9 + 32], 2 + pinsrw xmm5, word ptr [rsi + r9 + 32], 1 + pinsrw xmm5, word ptr [rsi + r8 + 32], 2 pinsrw xmm5, word ptr [rsi + r12 + 32], 3 pinsrw xmm5, word ptr [rsi + r13 + 32], 4 pinsrw xmm5, word ptr [rsi + rcx + 32], 5 - pinsrw xmm5, word ptr [rsi + rdi + 32], 6 - pinsrw xmm1, word ptr [rsi + r8 + 34], 1 - pinsrw xmm1, word ptr [rsi + r9 + 34], 2 + pinsrw xmm5, word ptr [rsi + rbx + 32], 6 + pinsrw xmm1, word ptr [rsi + r9 + 34], 1 + pinsrw xmm1, word ptr [rsi + r8 + 34], 2 pinsrw xmm1, word ptr [rsi + r12 + 34], 3 pinsrw xmm1, word ptr [rsi + r13 + 34], 4 pinsrw xmm1, word ptr [rsi + rcx + 34], 5 - pinsrw xmm1, word ptr [rsi + rdi + 34], 6 - pinsrw xmm1, word ptr [rsi + rbx + 34], 7 + pinsrw xmm1, word ptr [rsi + rbx + 34], 6 + pinsrw xmm1, word ptr [rsi + rdi + 34], 7 por xmm2, xmm3 pcmpgtw xmm1, xmm0 packsswb xmm1, xmm1 movdqa xmm7, xmm1 pand xmm7, xmm15 psubb xmm7, xmm1 - movd xmm3, dword ptr [rsp + 24] # 4-byte Folded Reload + movd xmm3, dword ptr [rsp + 32] # 4-byte Folded Reload # xmm3 = mem[0],zero,zero,zero movzx r11d, word ptr [rsi + r15 + 48] - pinsrw xmm5, word ptr [rsi + rbx + 32], 7 + pinsrw xmm5, word ptr [rsi + rdi + 32], 7 pcmpgtw xmm5, xmm0 packsswb xmm5, xmm5 pand xmm5, xmm15 - pinsrw xmm6, word ptr [rsi + r8 + 36], 1 - pinsrw xmm6, word ptr [rsi + r9 + 36], 2 + pinsrw xmm6, word ptr [rsi + r9 + 36], 1 + pinsrw xmm6, word ptr [rsi + r8 + 36], 2 pinsrw xmm6, word ptr [rsi + r12 + 36], 3 pinsrw xmm6, word ptr [rsi + r13 + 36], 4 pinsrw xmm6, word ptr [rsi + rcx + 36], 5 - pinsrw xmm6, word ptr [rsi + rdi + 36], 6 - pinsrw xmm6, word ptr [rsi + rbx + 36], 7 - pinsrw xmm3, word ptr [rsi + r8 + 38], 1 - pinsrw xmm3, word ptr [rsi + r9 + 38], 2 + pinsrw xmm6, word ptr [rsi + rbx + 36], 6 + pinsrw xmm6, word ptr [rsi + rdi + 36], 7 + pinsrw xmm3, word ptr [rsi + r9 + 38], 1 + pinsrw xmm3, word ptr [rsi + r8 + 38], 2 pinsrw xmm3, word ptr [rsi + r12 + 38], 3 pinsrw xmm3, word ptr [rsi + r13 + 38], 4 pinsrw xmm3, word ptr [rsi + rcx + 38], 5 - pinsrw xmm3, word ptr [rsi + rdi + 38], 6 - pinsrw xmm3, word ptr [rsi + rbx + 38], 7 + pinsrw xmm3, word ptr [rsi + rbx + 38], 6 + pinsrw xmm3, word ptr [rsi + rdi + 38], 7 por xmm7, xmm5 movd xmm5, r14d - pinsrw xmm5, word ptr [rsi + r8 + 40], 1 - pinsrw xmm5, word ptr [rsi + r9 + 40], 2 + pinsrw xmm5, word ptr [rsi + r9 + 40], 1 + pinsrw xmm5, word ptr [rsi + r8 + 40], 2 pinsrw xmm5, word ptr [rsi + r12 + 40], 3 pinsrw xmm5, word ptr [rsi + r13 + 40], 4 pinsrw xmm5, word ptr [rsi + rcx + 40], 5 - pinsrw xmm5, word ptr [rsi + rdi + 40], 6 + pinsrw xmm5, word ptr [rsi + rbx + 40], 6 movzx eax, word ptr [rsi + r15 + 50] pcmpgtw xmm6, xmm0 packsswb xmm6, xmm6 @@ -40160,10 +39409,10 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 psllw xmm6, 2 pand xmm6, xmm9 por xmm6, xmm7 - movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload # xmm1 = mem[0],zero,zero,zero movzx r14d, word ptr [rsi + r15 + 52] - pinsrw xmm5, word ptr [rsi + rbx + 40], 7 + pinsrw xmm5, word ptr [rsi + rdi + 40], 7 pcmpgtw xmm3, xmm0 packsswb xmm3, xmm3 pand xmm3, xmm15 @@ -40177,23 +39426,23 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 por xmm5, xmm3 movd xmm7, r10d movzx r10d, word ptr [rsi + r15 + 54] - pinsrw xmm1, word ptr [rsi + r8 + 42], 1 - pinsrw xmm1, word ptr [rsi + r9 + 42], 2 + pinsrw xmm1, word ptr [rsi + r9 + 42], 1 + pinsrw xmm1, word ptr [rsi + r8 + 42], 2 pinsrw xmm1, word ptr [rsi + r12 + 42], 3 pinsrw xmm1, word ptr [rsi + r13 + 42], 4 pinsrw xmm1, word ptr [rsi + rcx + 42], 5 - pinsrw xmm1, word ptr [rsi + rdi + 42], 6 - pinsrw xmm1, word ptr [rsi + rbx + 42], 7 - pinsrw xmm7, word ptr [rsi + r8 + 44], 1 - pinsrw xmm7, word ptr [rsi + r9 + 44], 2 + pinsrw xmm1, word ptr [rsi + rbx + 42], 6 + pinsrw xmm1, word ptr [rsi + rdi + 42], 7 + pinsrw xmm7, word ptr [rsi + r9 + 44], 1 + pinsrw xmm7, word ptr [rsi + r8 + 44], 2 pinsrw xmm7, word ptr [rsi + r12 + 44], 3 pinsrw xmm7, word ptr [rsi + r13 + 44], 4 pinsrw xmm7, word ptr [rsi + rcx + 44], 5 - pinsrw xmm7, word ptr [rsi + rdi + 44], 6 + pinsrw xmm7, word ptr [rsi + rbx + 44], 6 por xmm5, xmm6 movd xmm3, edx movzx edx, word ptr [rsi + r15 + 56] - pinsrw xmm7, word ptr [rsi + rbx + 44], 7 + pinsrw xmm7, word ptr [rsi + rdi + 44], 7 pcmpgtw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 @@ -40207,13 +39456,13 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 por xmm7, xmm1 movd xmm6, r11d movzx r11d, word ptr [rsi + r15 + 58] - pinsrw xmm3, word ptr [rsi + r8 + 46], 1 - pinsrw xmm3, word ptr [rsi + r9 + 46], 2 + pinsrw xmm3, word ptr [rsi + r9 + 46], 1 + pinsrw xmm3, word ptr [rsi + r8 + 46], 2 pinsrw xmm3, word ptr [rsi + r12 + 46], 3 pinsrw xmm3, word ptr [rsi + r13 + 46], 4 pinsrw xmm3, word ptr [rsi + rcx + 46], 5 - pinsrw xmm3, word ptr [rsi + rdi + 46], 6 - pinsrw xmm3, word ptr [rsi + rbx + 46], 7 + pinsrw xmm3, word ptr [rsi + rbx + 46], 6 + pinsrw xmm3, word ptr [rsi + rdi + 46], 7 pcmpgtw xmm3, xmm0 packsswb xmm3, xmm3 psllw xmm3, 7 @@ -40222,13 +39471,13 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movd xmm1, eax movzx eax, word ptr [rsi + r15 + 60] movzx r15d, word ptr [rsi + r15 + 62] - pinsrw xmm1, word ptr [rsi + r8 + 50], 1 - pinsrw xmm1, word ptr [rsi + r9 + 50], 2 + pinsrw xmm1, word ptr [rsi + r9 + 50], 1 + pinsrw xmm1, word ptr [rsi + r8 + 50], 2 pinsrw xmm1, word ptr [rsi + r12 + 50], 3 pinsrw xmm1, word ptr [rsi + r13 + 50], 4 pinsrw xmm1, word ptr [rsi + rcx + 50], 5 - pinsrw xmm1, word ptr [rsi + rdi + 50], 6 - pinsrw xmm1, word ptr [rsi + rbx + 50], 7 + pinsrw xmm1, word ptr [rsi + rbx + 50], 6 + pinsrw xmm1, word ptr [rsi + rdi + 50], 7 por xmm3, xmm5 pcmpgtw xmm1, xmm0 packsswb xmm1, xmm1 @@ -40236,26 +39485,25 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 pand xmm5, xmm15 psubb xmm5, xmm1 movd xmm1, r14d - mov r14, qword ptr [rsp] # 8-byte Reload - pinsrw xmm6, word ptr [rsi + r8 + 48], 1 - pinsrw xmm6, word ptr [rsi + r9 + 48], 2 + pinsrw xmm6, word ptr [rsi + r9 + 48], 1 + pinsrw xmm6, word ptr [rsi + r8 + 48], 2 pinsrw xmm6, word ptr [rsi + r12 + 48], 3 pinsrw xmm6, word ptr [rsi + r13 + 48], 4 pinsrw xmm6, word ptr [rsi + rcx + 48], 5 - pinsrw xmm6, word ptr [rsi + rdi + 48], 6 - pinsrw xmm6, word ptr [rsi + rbx + 48], 7 + pinsrw xmm6, word ptr [rsi + rbx + 48], 6 + pinsrw xmm6, word ptr [rsi + rdi + 48], 7 pcmpgtw xmm6, xmm0 packsswb xmm6, xmm6 - pinsrw xmm1, word ptr [rsi + r8 + 52], 1 - pinsrw xmm1, word ptr [rsi + r9 + 52], 2 + pinsrw xmm1, word ptr [rsi + r9 + 52], 1 + pinsrw xmm1, word ptr [rsi + r8 + 52], 2 pinsrw xmm1, word ptr [rsi + r12 + 52], 3 pinsrw xmm1, word ptr [rsi + r13 + 52], 4 pinsrw xmm1, word ptr [rsi + rcx + 52], 5 pand xmm6, xmm15 - pinsrw xmm1, word ptr [rsi + rdi + 52], 6 + pinsrw xmm1, word ptr [rsi + rbx + 52], 6 por xmm5, xmm6 movd xmm6, r10d - pinsrw xmm1, word ptr [rsi + rbx + 52], 7 + pinsrw xmm1, word ptr [rsi + rdi + 52], 7 pcmpgtw xmm1, xmm0 packsswb xmm1, xmm1 pand xmm1, xmm15 @@ -40263,20 +39511,20 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 pand xmm1, xmm9 por xmm1, xmm5 movd xmm5, edx - pinsrw xmm6, word ptr [rsi + r8 + 54], 1 - pinsrw xmm6, word ptr [rsi + r9 + 54], 2 + pinsrw xmm6, word ptr [rsi + r9 + 54], 1 + pinsrw xmm6, word ptr [rsi + r8 + 54], 2 pinsrw xmm6, word ptr [rsi + r12 + 54], 3 pinsrw xmm6, word ptr [rsi + r13 + 54], 4 pinsrw xmm6, word ptr [rsi + rcx + 54], 5 - pinsrw xmm6, word ptr [rsi + rdi + 54], 6 - pinsrw xmm6, word ptr [rsi + rbx + 54], 7 - pinsrw xmm5, word ptr [rsi + r8 + 56], 1 - pinsrw xmm5, word ptr [rsi + r9 + 56], 2 + pinsrw xmm6, word ptr [rsi + rbx + 54], 6 + pinsrw xmm6, word ptr [rsi + rdi + 54], 7 + pinsrw xmm5, word ptr [rsi + r9 + 56], 1 + pinsrw xmm5, word ptr [rsi + r8 + 56], 2 pinsrw xmm5, word ptr [rsi + r12 + 56], 3 pinsrw xmm5, word ptr [rsi + r13 + 56], 4 pinsrw xmm5, word ptr [rsi + rcx + 56], 5 - pinsrw xmm5, word ptr [rsi + rdi + 56], 6 - pinsrw xmm5, word ptr [rsi + rbx + 56], 7 + pinsrw xmm5, word ptr [rsi + rbx + 56], 6 + pinsrw xmm5, word ptr [rsi + rdi + 56], 7 pcmpgtw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -40289,22 +39537,22 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 pand xmm5, xmm11 por xmm5, xmm6 movd xmm6, r11d - pinsrw xmm6, word ptr [rsi + r8 + 58], 1 - pinsrw xmm6, word ptr [rsi + r9 + 58], 2 + pinsrw xmm6, word ptr [rsi + r9 + 58], 1 + pinsrw xmm6, word ptr [rsi + r8 + 58], 2 pinsrw xmm6, word ptr [rsi + r12 + 58], 3 pinsrw xmm6, word ptr [rsi + r13 + 58], 4 pinsrw xmm6, word ptr [rsi + rcx + 58], 5 - pinsrw xmm6, word ptr [rsi + rdi + 58], 6 - pinsrw xmm6, word ptr [rsi + rbx + 58], 7 + pinsrw xmm6, word ptr [rsi + rbx + 58], 6 + pinsrw xmm6, word ptr [rsi + rdi + 58], 7 por xmm5, xmm1 movd xmm1, eax - pinsrw xmm1, word ptr [rsi + r8 + 60], 1 - pinsrw xmm1, word ptr [rsi + r9 + 60], 2 + pinsrw xmm1, word ptr [rsi + r9 + 60], 1 + pinsrw xmm1, word ptr [rsi + r8 + 60], 2 pinsrw xmm1, word ptr [rsi + r12 + 60], 3 pinsrw xmm1, word ptr [rsi + r13 + 60], 4 pinsrw xmm1, word ptr [rsi + rcx + 60], 5 - pinsrw xmm1, word ptr [rsi + rdi + 60], 6 - pinsrw xmm1, word ptr [rsi + rbx + 60], 7 + pinsrw xmm1, word ptr [rsi + rbx + 60], 6 + pinsrw xmm1, word ptr [rsi + rdi + 60], 7 pcmpgtw xmm6, xmm0 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -40317,13 +39565,14 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 pand xmm1, xmm13 por xmm1, xmm6 movd xmm6, r15d - pinsrw xmm6, word ptr [rsi + r8 + 62], 1 - pinsrw xmm6, word ptr [rsi + r9 + 62], 2 + pinsrw xmm6, word ptr [rsi + r9 + 62], 1 + pinsrw xmm6, word ptr [rsi + r8 + 62], 2 pinsrw xmm6, word ptr [rsi + r12 + 62], 3 + mov r12, qword ptr [rsp + 128] # 8-byte Reload pinsrw xmm6, word ptr [rsi + r13 + 62], 4 pinsrw xmm6, word ptr [rsi + rcx + 62], 5 - pinsrw xmm6, word ptr [rsi + rdi + 62], 6 - pinsrw xmm6, word ptr [rsi + rbx + 62], 7 + pinsrw xmm6, word ptr [rsi + rbx + 62], 6 + pinsrw xmm6, word ptr [rsi + rdi + 62], 7 pcmpgtw xmm6, xmm0 packsswb xmm6, xmm6 psllw xmm6, 7 @@ -40342,37 +39591,34 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 punpcklbw xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7] punpcklwd xmm4, xmm3 # xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3] mov rcx, qword ptr [rsp + 16] # 8-byte Reload - movdqu xmmword ptr [r14 + 4*rcx], xmm4 - mov qword ptr [rsp], r14 # 8-byte Spill - movdqu xmmword ptr [r14 + 4*rcx + 16], xmm1 + movdqu xmmword ptr [r12 + 4*rcx], xmm4 + movdqu xmmword ptr [r12 + 4*rcx + 16], xmm1 add rcx, 8 mov r15, rcx cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload - jne .LBB7_125 -# %bb.126: - mov r15, qword ptr [rsp + 272] # 8-byte Reload - cmp r15, qword ptr [rsp + 40] # 8-byte Folded Reload - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r14, qword ptr [rsp + 8] # 8-byte Reload - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - jne .LBB7_127 - jmp .LBB7_130 -.LBB7_182: - mov rax, r10 + jne .LBB7_143 +# %bb.144: + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + cmp rcx, qword ptr [rsp + 40] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r13d, dword ptr [rsp + 56] # 4-byte Reload + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + jne .LBB7_145 + jmp .LBB7_148 +.LBB7_206: + mov rax, rdi and rax, -4 - mov rdx, rax - shl rdx, 7 - add rdx, rsi - mov rcx, qword ptr [rsp] # 8-byte Reload - lea r15, [rcx + 4*rax] - movaps xmm13, xmm11 - shufps xmm13, xmm11, 0 # xmm13 = xmm13[0,0],xmm11[0,0] + mov rcx, rax + shl rcx, 7 + add rcx, rsi + lea r10, [r12 + 4*rax] + movdqa xmm14, xmm11 + shufps xmm14, xmm11, 0 # xmm14 = xmm14[0,0],xmm11[0,0] add rsi, 508 - xor ecx, ecx + xor edx, edx movdqa xmm15, xmmword ptr [rip + .LCPI7_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> - mov rdi, qword ptr [rsp] # 8-byte Reload .p2align 4, 0x90 -.LBB7_183: # =>This Inner Loop Header: Depth=1 +.LBB7_207: # =>This Inner Loop Header: Depth=1 movss xmm3, dword ptr [rsi - 508] # xmm3 = mem[0],zero,zero,zero movss xmm10, dword ptr [rsi - 504] # xmm10 = mem[0],zero,zero,zero movss xmm9, dword ptr [rsi - 500] # xmm9 = mem[0],zero,zero,zero @@ -40392,7 +39638,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movss xmm8, dword ptr [rsi - 492] # xmm8 = mem[0],zero,zero,zero insertps xmm8, dword ptr [rsi - 364], 16 # xmm8 = xmm8[0],mem[0],xmm8[2,3] insertps xmm8, dword ptr [rsi - 236], 32 # xmm8 = xmm8[0,1],mem[0],xmm8[3] - movaps xmm12, xmm13 + movaps xmm12, xmm14 insertps xmm8, dword ptr [rsi - 108], 48 # xmm8 = xmm8[0,1,2],mem[0] movss xmm2, dword ptr [rsi - 488] # xmm2 = mem[0],zero,zero,zero insertps xmm2, dword ptr [rsi - 360], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] @@ -40409,45 +39655,45 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 insertps xmm4, dword ptr [rsi - 220], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] packsswb xmm12, xmm12 insertps xmm4, dword ptr [rsi - 92], 48 # xmm4 = xmm4[0,1,2],mem[0] - movaps xmm7, xmm13 + movaps xmm7, xmm14 movss xmm5, dword ptr [rsi - 444] # xmm5 = mem[0],zero,zero,zero insertps xmm5, dword ptr [rsi - 316], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] insertps xmm5, dword ptr [rsi - 188], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] cmpltps xmm7, xmm4 insertps xmm5, dword ptr [rsi - 60], 48 # xmm5 = xmm5[0,1,2],mem[0] - movaps xmm6, xmm13 - movss xmm0, dword ptr [rsi - 412] # xmm0 = mem[0],zero,zero,zero - insertps xmm0, dword ptr [rsi - 284], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] - insertps xmm0, dword ptr [rsi - 156], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] + movaps xmm6, xmm14 + movss xmm13, dword ptr [rsi - 412] # xmm13 = mem[0],zero,zero,zero + insertps xmm13, dword ptr [rsi - 284], 16 # xmm13 = xmm13[0],mem[0],xmm13[2,3] + insertps xmm13, dword ptr [rsi - 156], 32 # xmm13 = xmm13[0,1],mem[0],xmm13[3] cmpltps xmm6, xmm5 - insertps xmm0, dword ptr [rsi - 28], 48 # xmm0 = xmm0[0,1,2],mem[0] - movaps xmm4, xmm13 - cmpltps xmm4, xmm0 - movaps xmm0, xmm13 - cmpltps xmm0, xmm10 - packssdw xmm0, xmm0 - packsswb xmm0, xmm0 - movdqa xmm14, xmm0 - pand xmm14, xmm15 - psubb xmm14, xmm0 + insertps xmm13, dword ptr [rsi - 28], 48 # xmm13 = xmm13[0,1,2],mem[0] + movaps xmm4, xmm14 + cmpltps xmm4, xmm13 + movaps xmm5, xmm14 + cmpltps xmm5, xmm10 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + movdqa xmm0, xmm5 + pand xmm0, xmm15 + psubb xmm0, xmm5 movss xmm10, dword ptr [rsi - 480] # xmm10 = mem[0],zero,zero,zero insertps xmm10, dword ptr [rsi - 352], 16 # xmm10 = xmm10[0],mem[0],xmm10[2,3] pand xmm12, xmm15 insertps xmm10, dword ptr [rsi - 224], 32 # xmm10 = xmm10[0,1],mem[0],xmm10[3] - por xmm14, xmm12 - movaps xmm5, xmm13 + por xmm0, xmm12 + movaps xmm5, xmm14 cmpltps xmm5, xmm9 insertps xmm10, dword ptr [rsi - 96], 48 # xmm10 = xmm10[0,1,2],mem[0] packssdw xmm5, xmm5 packsswb xmm5, xmm5 pand xmm5, xmm15 psllw xmm5, 2 - movdqa xmm0, xmmword ptr [rip + .LCPI7_1] # xmm0 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - pand xmm5, xmm0 - por xmm5, xmm14 - movaps xmm0, xmm13 + movdqa xmm13, xmmword ptr [rip + .LCPI7_1] # xmm13 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + pand xmm5, xmm13 + por xmm5, xmm0 + movaps xmm0, xmm14 cmpltps xmm0, xmm1 - movaps xmm1, xmm13 + movaps xmm1, xmm14 cmpltps xmm1, xmm8 movss xmm9, dword ptr [rsi - 472] # xmm9 = mem[0],zero,zero,zero insertps xmm9, dword ptr [rsi - 344], 16 # xmm9 = xmm9[0],mem[0],xmm9[2,3] @@ -40457,23 +39703,23 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 3 - movdqa xmm14, xmmword ptr [rip + .LCPI7_2] # xmm14 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - pand xmm0, xmm14 + movdqa xmm13, xmmword ptr [rip + .LCPI7_2] # xmm13 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + pand xmm0, xmm13 packssdw xmm1, xmm1 packsswb xmm1, xmm1 pand xmm1, xmm15 psllw xmm1, 4 - movdqa xmm14, xmmword ptr [rip + .LCPI7_3] # xmm14 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - pand xmm1, xmm14 + movdqa xmm13, xmmword ptr [rip + .LCPI7_3] # xmm13 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + pand xmm1, xmm13 por xmm1, xmm0 movss xmm12, dword ptr [rsi - 468] # xmm12 = mem[0],zero,zero,zero insertps xmm12, dword ptr [rsi - 340], 16 # xmm12 = xmm12[0],mem[0],xmm12[2,3] insertps xmm12, dword ptr [rsi - 212], 32 # xmm12 = xmm12[0,1],mem[0],xmm12[3] insertps xmm12, dword ptr [rsi - 84], 48 # xmm12 = xmm12[0,1,2],mem[0] por xmm1, xmm5 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm2 - movaps xmm5, xmm13 + movaps xmm5, xmm14 cmpltps xmm5, xmm3 movss xmm2, dword ptr [rsi - 464] # xmm2 = mem[0],zero,zero,zero insertps xmm2, dword ptr [rsi - 336], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] @@ -40484,8 +39730,8 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 5 - movdqa xmm14, xmmword ptr [rip + .LCPI7_4] # xmm14 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - pand xmm0, xmm14 + movdqa xmm13, xmmword ptr [rip + .LCPI7_4] # xmm13 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + pand xmm0, xmm13 packssdw xmm5, xmm5 packsswb xmm5, xmm5 pand xmm5, xmm15 @@ -40493,7 +39739,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movdqa xmm3, xmmword ptr [rip + .LCPI7_5] # xmm3 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] pand xmm5, xmm3 por xmm5, xmm0 - movaps xmm8, xmm13 + movaps xmm8, xmm14 cmpltps xmm8, xmm10 movss xmm3, dword ptr [rsi - 460] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 332], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -40511,7 +39757,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 packsswb xmm7, xmm7 insertps xmm10, dword ptr [rsi - 72], 48 # xmm10 = xmm10[0,1,2],mem[0] por xmm8, xmm1 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm9 packssdw xmm0, xmm0 packsswb xmm0, xmm0 @@ -40523,7 +39769,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 pand xmm7, xmm15 insertps xmm9, dword ptr [rsi - 196], 32 # xmm9 = xmm9[0,1],mem[0],xmm9[3] por xmm1, xmm7 - movaps xmm5, xmm13 + movaps xmm5, xmm14 cmpltps xmm5, xmm12 insertps xmm9, dword ptr [rsi - 68], 48 # xmm9 = xmm9[0,1,2],mem[0] packssdw xmm5, xmm5 @@ -40532,9 +39778,9 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 psllw xmm5, 2 pand xmm5, xmmword ptr [rip + .LCPI7_1] por xmm5, xmm1 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm2 - movaps xmm1, xmm13 + movaps xmm1, xmm14 cmpltps xmm1, xmm3 movss xmm3, dword ptr [rsi - 448] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 320], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -40557,9 +39803,9 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 insertps xmm2, dword ptr [rsi - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] insertps xmm2, dword ptr [rsi - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] por xmm1, xmm5 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm10 - movaps xmm5, xmm13 + movaps xmm5, xmm14 cmpltps xmm5, xmm9 movss xmm7, dword ptr [rsi - 436] # xmm7 = mem[0],zero,zero,zero insertps xmm7, dword ptr [rsi - 308], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] @@ -40570,14 +39816,14 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 5 - pand xmm0, xmm14 + pand xmm0, xmm13 packssdw xmm5, xmm5 packsswb xmm5, xmm5 pand xmm5, xmm15 psllw xmm5, 6 pand xmm5, xmmword ptr [rip + .LCPI7_5] por xmm5, xmm0 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm3 movss xmm3, dword ptr [rsi - 432] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 304], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -40600,7 +39846,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 packsswb xmm6, xmm6 insertps xmm9, dword ptr [rsi - 40], 48 # xmm9 = xmm9[0,1,2],mem[0] punpckldq xmm8, xmm0 # xmm8 = xmm8[0],xmm0[0],xmm8[1],xmm0[1] - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm2 packssdw xmm0, xmm0 packsswb xmm0, xmm0 @@ -40612,7 +39858,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 pand xmm6, xmm15 insertps xmm2, dword ptr [rsi - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] por xmm1, xmm6 - movaps xmm6, xmm13 + movaps xmm6, xmm14 cmpltps xmm6, xmm7 insertps xmm2, dword ptr [rsi - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] packssdw xmm6, xmm6 @@ -40622,9 +39868,9 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movdqa xmm0, xmmword ptr [rip + .LCPI7_1] # xmm0 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] pand xmm6, xmm0 por xmm6, xmm1 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm3 - movaps xmm1, xmm13 + movaps xmm1, xmm14 cmpltps xmm1, xmm5 movss xmm3, dword ptr [rsi - 416] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 288], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -40647,9 +39893,9 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 insertps xmm5, dword ptr [rsi - 152], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] insertps xmm5, dword ptr [rsi - 24], 48 # xmm5 = xmm5[0,1,2],mem[0] por xmm1, xmm6 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpltps xmm0, xmm9 - movaps xmm6, xmm13 + movaps xmm6, xmm14 cmpltps xmm6, xmm2 movss xmm7, dword ptr [rsi - 404] # xmm7 = mem[0],zero,zero,zero insertps xmm7, dword ptr [rsi - 276], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] @@ -40660,7 +39906,7 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 5 - pand xmm0, xmm14 + pand xmm0, xmm13 packssdw xmm6, xmm6 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -40668,12 +39914,12 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 movdqa xmm9, xmmword ptr [rip + .LCPI7_5] # xmm9 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] pand xmm6, xmm9 por xmm6, xmm0 - movaps xmm2, xmm13 + movaps xmm2, xmm14 cmpltps xmm2, xmm3 - movss xmm0, dword ptr [rsi - 400] # xmm0 = mem[0],zero,zero,zero - insertps xmm0, dword ptr [rsi - 272], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] - insertps xmm0, dword ptr [rsi - 144], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] - insertps xmm0, dword ptr [rsi - 16], 48 # xmm0 = xmm0[0,1,2],mem[0] + movss xmm3, dword ptr [rsi - 400] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 272], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 144], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rsi - 16], 48 # xmm3 = xmm3[0,1,2],mem[0] packssdw xmm2, xmm2 packsswb xmm2, xmm2 psllw xmm2, 7 @@ -40685,86 +39931,2013 @@ comparison_greater_arr_scalar_sse4: # @comparison_greater_arr_scalar_sse4 packsswb xmm4, xmm4 insertps xmm6, dword ptr [rsi - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] por xmm2, xmm1 - movaps xmm1, xmm13 - cmpltps xmm1, xmm5 - packssdw xmm1, xmm1 - packsswb xmm1, xmm1 - movdqa xmm5, xmm1 - pand xmm5, xmm15 - psubb xmm5, xmm1 - movss xmm3, dword ptr [rsi - 392] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rsi - 264], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + movaps xmm0, xmm14 + cmpltps xmm0, xmm5 + packssdw xmm0, xmm0 + packsswb xmm0, xmm0 + movdqa xmm1, xmm0 + pand xmm1, xmm15 + psubb xmm1, xmm0 + movss xmm5, dword ptr [rsi - 392] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rsi - 264], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] pand xmm4, xmm15 - insertps xmm3, dword ptr [rsi - 136], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - por xmm5, xmm4 - movaps xmm4, xmm13 + insertps xmm5, dword ptr [rsi - 136], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + por xmm1, xmm4 + movaps xmm4, xmm14 cmpltps xmm4, xmm7 - insertps xmm3, dword ptr [rsi - 8], 48 # xmm3 = xmm3[0,1,2],mem[0] + insertps xmm5, dword ptr [rsi - 8], 48 # xmm5 = xmm5[0,1,2],mem[0] packssdw xmm4, xmm4 packsswb xmm4, xmm4 pand xmm4, xmm15 psllw xmm4, 2 pand xmm4, xmmword ptr [rip + .LCPI7_1] - por xmm4, xmm5 - movaps xmm5, xmm13 - cmpltps xmm5, xmm0 - movaps xmm1, xmm13 + por xmm4, xmm1 + movaps xmm0, xmm14 + cmpltps xmm0, xmm3 + movaps xmm1, xmm14 cmpltps xmm1, xmm6 - movss xmm0, dword ptr [rsi - 388] # xmm0 = mem[0],zero,zero,zero - insertps xmm0, dword ptr [rsi - 260], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] - insertps xmm0, dword ptr [rsi - 132], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] - insertps xmm0, dword ptr [rsi - 4], 48 # xmm0 = xmm0[0,1,2],mem[0] - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 3 - pand xmm5, xmmword ptr [rip + .LCPI7_2] + movss xmm3, dword ptr [rsi - 388] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 260], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 132], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rsi - 4], 48 # xmm3 = xmm3[0,1,2],mem[0] + packssdw xmm0, xmm0 + packsswb xmm0, xmm0 + pand xmm0, xmm15 + psllw xmm0, 3 + pand xmm0, xmmword ptr [rip + .LCPI7_2] packssdw xmm1, xmm1 packsswb xmm1, xmm1 pand xmm1, xmm15 psllw xmm1, 4 pand xmm1, xmm12 - por xmm1, xmm5 - movss xmm5, dword ptr [rsi - 384] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rsi - 256], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rsi - 128], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + por xmm1, xmm0 + movss xmm0, dword ptr [rsi - 384] # xmm0 = mem[0],zero,zero,zero + insertps xmm0, dword ptr [rsi - 256], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] + insertps xmm0, dword ptr [rsi - 128], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] por xmm1, xmm4 - movaps xmm4, xmm13 - cmpltps xmm4, xmm3 - movaps xmm3, xmm13 - cmpltps xmm3, xmm0 - insertps xmm5, dword ptr [rsi], 48 # xmm5 = xmm5[0,1,2],mem[0] + movaps xmm4, xmm14 + cmpltps xmm4, xmm5 + movaps xmm5, xmm14 + cmpltps xmm5, xmm3 + insertps xmm0, dword ptr [rsi], 48 # xmm0 = xmm0[0,1,2],mem[0] packssdw xmm4, xmm4 packsswb xmm4, xmm4 pand xmm4, xmm15 psllw xmm4, 5 - pand xmm4, xmm14 + pand xmm4, xmm13 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 6 + pand xmm5, xmm9 + por xmm5, xmm4 + movaps xmm3, xmm14 + cmpltps xmm3, xmm0 packssdw xmm3, xmm3 packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 6 - pand xmm3, xmm9 + psllw xmm3, 7 + pand xmm3, xmm10 + por xmm3, xmm5 + por xmm3, xmm1 + punpckldq xmm2, xmm3 # xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1] + punpcklbw xmm8, xmm2 # xmm8 = xmm8[0],xmm2[0],xmm8[1],xmm2[1],xmm8[2],xmm2[2],xmm8[3],xmm2[3],xmm8[4],xmm2[4],xmm8[5],xmm2[5],xmm8[6],xmm2[6],xmm8[7],xmm2[7] + pshufb xmm8, xmmword ptr [rip + .LCPI7_7] # xmm8 = xmm8[0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] + movdqu xmmword ptr [r12 + 4*rdx], xmm8 + add rdx, 4 + add rsi, 512 + cmp rax, rdx + jne .LBB7_207 +# %bb.208: + cmp rdi, rax + jne .LBB7_209 + jmp .LBB7_212 +.LBB7_97: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, r14 + mov qword ptr [rsp + 312], rax # 8-byte Spill + mov qword ptr [rsp + 248], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 288], rax # 8-byte Spill + movzx eax, r13b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 160], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 128], r12 # 8-byte Spill + .p2align 4, 0x90 +.LBB7_98: # =>This Inner Loop Header: Depth=1 + mov rsi, rax + mov qword ptr [rsp + 208], rax # 8-byte Spill + shl rsi, 5 + mov rax, rsi + mov rdx, rsi + mov r10, rsi + mov r12, rsi + mov r15, rsi + mov rdi, rsi + mov r8, rsi + mov r9, rsi + mov r11, rsi + mov qword ptr [rsp + 40], rsi # 8-byte Spill + mov rbx, rsi + movzx ecx, byte ptr [r14 + rsi] + movd xmm15, ecx + movzx ecx, byte ptr [r14 + rsi + 1] + movd xmm5, ecx + movzx ecx, byte ptr [r14 + rsi + 2] + movd xmm6, ecx + movzx ecx, byte ptr [r14 + rsi + 3] + movd xmm2, ecx + movzx ecx, byte ptr [r14 + rsi + 4] + movd xmm1, ecx + movzx ecx, byte ptr [r14 + rsi + 5] + movd xmm8, ecx + movzx ecx, byte ptr [r14 + rsi + 6] + movd xmm3, ecx + movzx ecx, byte ptr [r14 + rsi + 7] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rsi + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rsi + 9] + movd xmm10, ecx + movzx ecx, byte ptr [r14 + rsi + 10] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 144], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r14 + rsi + 11] + movd xmm11, ecx + movzx ecx, byte ptr [r14 + rsi + 12] + movd xmm13, ecx + movzx ecx, byte ptr [r14 + rsi + 13] + movd xmm12, ecx + movzx ecx, byte ptr [r14 + rsi + 14] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 256], xmm0 # 16-byte Spill + mov r13, rsi + or r13, 32 + mov qword ptr [rsp + 32], r13 # 8-byte Spill + or rax, 64 + mov qword ptr [rsp + 96], rax # 8-byte Spill + or rdx, 96 + mov qword ptr [rsp + 88], rdx # 8-byte Spill + or r10, 128 + or r12, 160 + or r15, 192 + mov qword ptr [rsp + 80], r15 # 8-byte Spill + or rdi, 224 + mov qword ptr [rsp + 56], rdi # 8-byte Spill + or r8, 256 + or r9, 288 + or r11, 320 + mov qword ptr [rsp + 120], r11 # 8-byte Spill + mov r15, qword ptr [rsp + 40] # 8-byte Reload + or r15, 352 + mov rdi, rsi + or rdi, 384 + mov qword ptr [rsp + 72], rdi # 8-byte Spill + mov rcx, rsi + or rcx, 416 + mov qword ptr [rsp + 16], rcx # 8-byte Spill + mov rcx, rsi + mov qword ptr [rsp + 64], rsi # 8-byte Spill + or rbx, 448 + mov qword ptr [rsp + 24], rbx # 8-byte Spill + or rcx, 480 + mov qword ptr [rsp + 48], rcx # 8-byte Spill + pinsrb xmm15, byte ptr [r14 + r13], 1 + pinsrb xmm15, byte ptr [r14 + rax], 2 + pinsrb xmm15, byte ptr [r14 + rdx], 3 + mov rsi, r10 + pinsrb xmm15, byte ptr [r14 + r10], 4 + pinsrb xmm15, byte ptr [r14 + r12], 5 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 6 + mov r13, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r13], 7 + pinsrb xmm15, byte ptr [r14 + r8], 8 + pinsrb xmm15, byte ptr [r14 + r9], 9 + pinsrb xmm15, byte ptr [r14 + r11], 10 + pinsrb xmm15, byte ptr [r14 + r15], 11 + pinsrb xmm15, byte ptr [r14 + rdi], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rax], 13 + pinsrb xmm15, byte ptr [r14 + rbx], 14 + pinsrb xmm15, byte ptr [r14 + rcx], 15 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r10 + 1], 1 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r10 + 1], 2 + pinsrb xmm5, byte ptr [r14 + rdx + 1], 3 + pinsrb xmm5, byte ptr [r14 + rsi + 1], 4 + pinsrb xmm5, byte ptr [r14 + r12 + 1], 5 + mov rdx, r12 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 6 + pinsrb xmm5, byte ptr [r14 + r13 + 1], 7 + mov r12, r13 + pinsrb xmm5, byte ptr [r14 + r8 + 1], 8 + pinsrb xmm5, byte ptr [r14 + r9 + 1], 9 + pinsrb xmm5, byte ptr [r14 + r11 + 1], 10 + pinsrb xmm5, byte ptr [r14 + r15 + 1], 11 + mov r11, r15 + mov qword ptr [rsp + 40], r15 # 8-byte Spill + pinsrb xmm5, byte ptr [r14 + rdi + 1], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 1], 13 + pinsrb xmm5, byte ptr [r14 + rbx + 1], 14 + pinsrb xmm5, byte ptr [r14 + rcx + 1], 15 + movdqa xmm9, xmmword ptr [rsp + 160] # 16-byte Reload + pcmpgtb xmm5, xmm9 + movdqa xmm7, xmm5 + movdqa xmm4, xmmword ptr [rip + .LCPI7_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm7, xmm4 + psubb xmm7, xmm5 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edi, byte ptr [r14 + rax + 15] + movd xmm14, edi + pcmpgtb xmm15, xmm9 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rcx + 2], 1 + mov r13, r10 + pinsrb xmm6, byte ptr [r14 + r10 + 2], 2 + mov r10, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r10 + 2], 3 + mov rbx, rsi + pinsrb xmm6, byte ptr [r14 + rsi + 2], 4 + pinsrb xmm6, byte ptr [r14 + rdx + 2], 5 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 6 + pinsrb xmm6, byte ptr [r14 + r12 + 2], 7 + pinsrb xmm6, byte ptr [r14 + r8 + 2], 8 + mov qword ptr [rsp + 112], r9 # 8-byte Spill + pinsrb xmm6, byte ptr [r14 + r9 + 2], 9 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r15 + 2], 10 + pinsrb xmm6, byte ptr [r14 + r11 + 2], 11 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r12 + 2], 12 + mov r11, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r11 + 2], 13 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdi + 2], 14 + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdi + 2], 15 + pand xmm15, xmm4 + pcmpgtb xmm6, xmm9 + movdqa xmm0, xmmword ptr [rip + .LCPI7_11] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm6, xmm0 + por xmm6, xmm15 + movzx edi, byte ptr [r14 + rax + 16] + movd xmm15, edi + mov rax, rcx + pinsrb xmm2, byte ptr [r14 + rcx + 3], 1 + pinsrb xmm2, byte ptr [r14 + r13 + 3], 2 + pinsrb xmm2, byte ptr [r14 + r10 + 3], 3 + pinsrb xmm2, byte ptr [r14 + rbx + 3], 4 + pinsrb xmm2, byte ptr [r14 + rdx + 3], 5 + mov rcx, rsi + pinsrb xmm2, byte ptr [r14 + rsi + 3], 6 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rsi + 3], 7 + pinsrb xmm2, byte ptr [r14 + r8 + 3], 8 + pinsrb xmm2, byte ptr [r14 + r9 + 3], 9 + pinsrb xmm2, byte ptr [r14 + r15 + 3], 10 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r15 + 3], 11 + pinsrb xmm2, byte ptr [r14 + r12 + 3], 12 + pinsrb xmm2, byte ptr [r14 + r11 + 3], 13 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdi + 3], 14 + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdi + 3], 15 + pinsrb xmm1, byte ptr [r14 + rax + 4], 1 + pinsrb xmm1, byte ptr [r14 + r13 + 4], 2 + pinsrb xmm1, byte ptr [r14 + r10 + 4], 3 + pinsrb xmm1, byte ptr [r14 + rbx + 4], 4 + mov r13, rbx + mov qword ptr [rsp + 176], rbx # 8-byte Spill + pinsrb xmm1, byte ptr [r14 + rdx + 4], 5 + mov rbx, rdx + pinsrb xmm1, byte ptr [r14 + rcx + 4], 6 + pinsrb xmm1, byte ptr [r14 + rsi + 4], 7 + pinsrb xmm1, byte ptr [r14 + r8 + 4], 8 + pinsrb xmm1, byte ptr [r14 + r9 + 4], 9 + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rcx + 4], 10 + pinsrb xmm1, byte ptr [r14 + r15 + 4], 11 + pinsrb xmm1, byte ptr [r14 + r12 + 4], 12 + pinsrb xmm1, byte ptr [r14 + r11 + 4], 13 + mov r9, r11 + mov r11, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + r11 + 4], 14 + pinsrb xmm1, byte ptr [r14 + rdi + 4], 15 + por xmm6, xmm7 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edi, byte ptr [r14 + rax + 17] + movd xmm0, edi + pcmpgtb xmm2, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI7_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm2, xmm5 + pcmpgtb xmm1, xmm9 + movdqa xmm5, xmmword ptr [rip + .LCPI7_13] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm1, xmm5 + por xmm1, xmm2 + movzx edi, byte ptr [r14 + rax + 18] + movd xmm5, edi + mov r15, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r15 + 5], 1 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rdx + 5], 2 + pinsrb xmm8, byte ptr [r14 + r10 + 5], 3 + pinsrb xmm8, byte ptr [r14 + r13 + 5], 4 + pinsrb xmm8, byte ptr [r14 + rbx + 5], 5 + mov qword ptr [rsp + 104], rbx # 8-byte Spill + mov r12, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r12 + 5], 6 + pinsrb xmm8, byte ptr [r14 + rsi + 5], 7 + pinsrb xmm8, byte ptr [r14 + r8 + 5], 8 + mov rsi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rsi + 5], 9 + pinsrb xmm8, byte ptr [r14 + rcx + 5], 10 + mov rsi, rcx + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rcx + 5], 11 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rcx + 5], 12 + pinsrb xmm8, byte ptr [r14 + r9 + 5], 13 + pinsrb xmm8, byte ptr [r14 + r11 + 5], 14 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r9 + 5], 15 + pcmpgtb xmm8, xmm9 + movdqa xmm2, xmmword ptr [rip + .LCPI7_14] # xmm2 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm8, xmm2 + por xmm8, xmm1 + movzx edi, byte ptr [r14 + rax + 19] + movd xmm7, edi + por xmm8, xmm6 + movzx edi, byte ptr [r14 + rax + 20] + movd xmm6, edi + pinsrb xmm3, byte ptr [r14 + r15 + 6], 1 + mov r13, r15 + pinsrb xmm3, byte ptr [r14 + rdx + 6], 2 + mov r11, rdx + pinsrb xmm3, byte ptr [r14 + r10 + 6], 3 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdx + 6], 4 + pinsrb xmm3, byte ptr [r14 + rbx + 6], 5 + mov rcx, r12 + pinsrb xmm3, byte ptr [r14 + r12 + 6], 6 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rax + 6], 7 + mov r12, r8 + pinsrb xmm3, byte ptr [r14 + r8 + 6], 8 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r8 + 6], 9 + pinsrb xmm3, byte ptr [r14 + rsi + 6], 10 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdi + 6], 11 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rax + 6], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rbx + 6], 13 + mov r15, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r15 + 6], 14 + pinsrb xmm3, byte ptr [r14 + r9 + 6], 15 + movdqa xmm2, xmmword ptr [rsp + 192] # 16-byte Reload + pinsrb xmm2, byte ptr [r14 + r13 + 7], 1 + pinsrb xmm2, byte ptr [r14 + r11 + 7], 2 + pinsrb xmm2, byte ptr [r14 + r10 + 7], 3 + mov rbx, r10 + pinsrb xmm2, byte ptr [r14 + rdx + 7], 4 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdx + 7], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 7], 6 + mov r9, rcx + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rcx + 7], 7 + pinsrb xmm2, byte ptr [r14 + r12 + 7], 8 + mov qword ptr [rsp + 320], r12 # 8-byte Spill + pinsrb xmm2, byte ptr [r14 + r8 + 7], 9 + pinsrb xmm2, byte ptr [r14 + rsi + 7], 10 + pinsrb xmm2, byte ptr [r14 + rdi + 7], 11 + pinsrb xmm2, byte ptr [r14 + rax + 7], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rsi + 7], 13 + pinsrb xmm2, byte ptr [r14 + r15 + 7], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdx + 7], 15 + pcmpgtb xmm3, xmm9 + movdqa xmm1, xmmword ptr [rip + .LCPI7_15] # xmm1 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm1 + pcmpgtb xmm2, xmm9 + psllw xmm2, 7 + movdqa xmm1, xmmword ptr [rip + .LCPI7_6] # xmm1 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm2, xmm1 + por xmm2, xmm3 + movdqa xmm1, xmm2 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edi, byte ptr [r14 + rax + 21] + movd xmm2, edi + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rcx + 9], 1 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r10 + 9], 2 + mov r8, rbx + pinsrb xmm10, byte ptr [r14 + rbx + 9], 3 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r13 + 9], 4 + mov r11, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r11 + 9], 5 + pinsrb xmm10, byte ptr [r14 + r9 + 9], 6 + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rbx + 9], 7 + pinsrb xmm10, byte ptr [r14 + r12 + 9], 8 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r15 + 9], 9 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r12 + 9], 10 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdi + 9], 11 + mov rdi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdi + 9], 12 + pinsrb xmm10, byte ptr [r14 + rsi + 9], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rsi + 9], 14 + pinsrb xmm10, byte ptr [r14 + rdx + 9], 15 + por xmm1, xmm8 + movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill + pcmpgtb xmm10, xmm9 + movdqa xmm1, xmm10 + movdqa xmm8, xmm4 + pand xmm1, xmm4 + psubb xmm1, xmm10 + movzx edi, byte ptr [r14 + rax + 22] + movd xmm3, edi + movdqa xmm4, xmmword ptr [rsp + 224] # 16-byte Reload + pinsrb xmm4, byte ptr [r14 + rcx + 8], 1 + mov r9, rcx + pinsrb xmm4, byte ptr [r14 + r10 + 8], 2 + pinsrb xmm4, byte ptr [r14 + r8 + 8], 3 + pinsrb xmm4, byte ptr [r14 + r13 + 8], 4 + mov rdx, r11 + pinsrb xmm4, byte ptr [r14 + r11 + 8], 5 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r11 + 8], 6 + pinsrb xmm4, byte ptr [r14 + rbx + 8], 7 + mov rax, qword ptr [rsp + 320] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 8], 8 + mov rdi, r15 + pinsrb xmm4, byte ptr [r14 + r15 + 8], 9 + mov r15, r12 + pinsrb xmm4, byte ptr [r14 + r12 + 8], 10 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rcx + 8], 11 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r12 + 8], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rcx + 8], 13 + pinsrb xmm4, byte ptr [r14 + rsi + 8], 14 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r8 + 8], 15 + pcmpgtb xmm4, xmm9 + pand xmm4, xmm8 + movdqa xmm10, xmmword ptr [rsp + 144] # 16-byte Reload + pinsrb xmm10, byte ptr [r14 + r9 + 10], 1 + pinsrb xmm10, byte ptr [r14 + r10 + 10], 2 + mov rbx, r10 + mov r10, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r10 + 10], 3 + pinsrb xmm10, byte ptr [r14 + r13 + 10], 4 + pinsrb xmm10, byte ptr [r14 + rdx + 10], 5 + mov r9, r11 + pinsrb xmm10, byte ptr [r14 + r11 + 10], 6 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdx + 10], 7 + pinsrb xmm10, byte ptr [r14 + rax + 10], 8 + mov r11, rax + pinsrb xmm10, byte ptr [r14 + rdi + 10], 9 + pinsrb xmm10, byte ptr [r14 + r15 + 10], 10 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rax + 10], 11 + pinsrb xmm10, byte ptr [r14 + r12 + 10], 12 + pinsrb xmm10, byte ptr [r14 + rcx + 10], 13 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r13 + 10], 14 + pinsrb xmm10, byte ptr [r14 + r8 + 10], 15 + pcmpgtb xmm10, xmm9 + pand xmm10, xmmword ptr [rip + .LCPI7_11] + por xmm10, xmm4 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + movzx edi, byte ptr [r14 + rcx + 23] + movd xmm8, edi + por xmm10, xmm1 + movdqa xmmword ptr [rsp + 144], xmm10 # 16-byte Spill + movzx edi, byte ptr [r14 + rcx + 24] + movd xmm10, edi + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rsi + 11], 1 + pinsrb xmm11, byte ptr [r14 + rbx + 11], 2 + pinsrb xmm11, byte ptr [r14 + r10 + 11], 3 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rbx + 11], 4 + mov r10, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r10 + 11], 5 + mov rcx, r9 + pinsrb xmm11, byte ptr [r14 + r9 + 11], 6 + pinsrb xmm11, byte ptr [r14 + rdx + 11], 7 + mov r8, r11 + pinsrb xmm11, byte ptr [r14 + r11 + 11], 8 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r9 + 11], 9 + mov r11, r15 + pinsrb xmm11, byte ptr [r14 + r15 + 11], 10 + mov r15, rax + pinsrb xmm11, byte ptr [r14 + rax + 11], 11 + pinsrb xmm11, byte ptr [r14 + r12 + 11], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rax + 11], 13 + mov rdi, r13 + pinsrb xmm11, byte ptr [r14 + r13 + 11], 14 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 15 + pinsrb xmm13, byte ptr [r14 + rsi + 12], 1 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rdx + 12], 2 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + r13 + 12], 3 + pinsrb xmm13, byte ptr [r14 + rbx + 12], 4 + pinsrb xmm13, byte ptr [r14 + r10 + 12], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 12], 6 + mov r13, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + r13 + 12], 7 + pinsrb xmm13, byte ptr [r14 + r8 + 12], 8 + pinsrb xmm13, byte ptr [r14 + r9 + 12], 9 + pinsrb xmm13, byte ptr [r14 + r11 + 12], 10 + pinsrb xmm13, byte ptr [r14 + r15 + 12], 11 + pinsrb xmm13, byte ptr [r14 + r12 + 12], 12 + pinsrb xmm13, byte ptr [r14 + rax + 12], 13 + pinsrb xmm13, byte ptr [r14 + rdi + 12], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rax + 12], 15 + pinsrb xmm12, byte ptr [r14 + rsi + 13], 1 + pinsrb xmm12, byte ptr [r14 + rdx + 13], 2 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 3 + mov r10, rdx + pinsrb xmm12, byte ptr [r14 + rbx + 13], 4 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rdx + 13], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 13], 6 + pinsrb xmm12, byte ptr [r14 + r13 + 13], 7 + pinsrb xmm12, byte ptr [r14 + r8 + 13], 8 + pinsrb xmm12, byte ptr [r14 + r9 + 13], 9 + pinsrb xmm12, byte ptr [r14 + r11 + 13], 10 + pinsrb xmm12, byte ptr [r14 + r15 + 13], 11 + pinsrb xmm12, byte ptr [r14 + r12 + 13], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + rsi + 13], 13 + pinsrb xmm12, byte ptr [r14 + rdi + 13], 14 + pinsrb xmm12, byte ptr [r14 + rax + 13], 15 + pcmpgtb xmm11, xmm9 + pand xmm11, xmmword ptr [rip + .LCPI7_12] + pcmpgtb xmm13, xmm9 + pand xmm13, xmmword ptr [rip + .LCPI7_13] + por xmm13, xmm11 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edi, byte ptr [r14 + rax + 25] + movd xmm1, edi + pcmpgtb xmm12, xmm9 + pand xmm12, xmmword ptr [rip + .LCPI7_14] + por xmm12, xmm13 + movzx edi, byte ptr [r14 + rax + 26] + movd xmm11, edi + movdqa xmm4, xmmword ptr [rsp + 256] # 16-byte Reload + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 14], 1 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r13 + 14], 2 + pinsrb xmm4, byte ptr [r14 + r10 + 14], 3 + pinsrb xmm4, byte ptr [r14 + rbx + 14], 4 + mov rax, rdx + pinsrb xmm4, byte ptr [r14 + rdx + 14], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 14], 6 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 14], 7 + pinsrb xmm4, byte ptr [r14 + r8 + 14], 8 + pinsrb xmm4, byte ptr [r14 + r9 + 14], 9 + mov rdi, r11 + pinsrb xmm4, byte ptr [r14 + r11 + 14], 10 + pinsrb xmm4, byte ptr [r14 + r15 + 14], 11 + pinsrb xmm4, byte ptr [r14 + r12 + 14], 12 + pinsrb xmm4, byte ptr [r14 + rsi + 14], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rsi + 14], 14 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + r11 + 14], 15 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rsi + 15], 1 + pinsrb xmm14, byte ptr [r14 + r13 + 15], 2 + pinsrb xmm14, byte ptr [r14 + r10 + 15], 3 + pinsrb xmm14, byte ptr [r14 + rbx + 15], 4 + pinsrb xmm14, byte ptr [r14 + rax + 15], 5 + pinsrb xmm14, byte ptr [r14 + rcx + 15], 6 + pinsrb xmm14, byte ptr [r14 + rdx + 15], 7 + pinsrb xmm14, byte ptr [r14 + r8 + 15], 8 + pinsrb xmm14, byte ptr [r14 + r9 + 15], 9 + pinsrb xmm14, byte ptr [r14 + rdi + 15], 10 + pinsrb xmm14, byte ptr [r14 + r15 + 15], 11 + pinsrb xmm14, byte ptr [r14 + r12 + 15], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rsi + 15], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rsi + 15], 14 + pinsrb xmm14, byte ptr [r14 + r11 + 15], 15 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rsi + 16], 1 + pinsrb xmm15, byte ptr [r14 + r13 + 16], 2 + pinsrb xmm15, byte ptr [r14 + r10 + 16], 3 + pinsrb xmm15, byte ptr [r14 + rbx + 16], 4 + pinsrb xmm15, byte ptr [r14 + rax + 16], 5 + pinsrb xmm15, byte ptr [r14 + rcx + 16], 6 + pinsrb xmm15, byte ptr [r14 + rdx + 16], 7 + pinsrb xmm15, byte ptr [r14 + r8 + 16], 8 + pinsrb xmm15, byte ptr [r14 + r9 + 16], 9 + pinsrb xmm15, byte ptr [r14 + rdi + 16], 10 + pinsrb xmm15, byte ptr [r14 + r15 + 16], 11 + pinsrb xmm15, byte ptr [r14 + r12 + 16], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + rsi + 16], 13 + mov r11, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r11 + 16], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rsi + 17], 1 + pinsrb xmm0, byte ptr [r14 + r13 + 17], 2 + pinsrb xmm0, byte ptr [r14 + r10 + 17], 3 + pinsrb xmm0, byte ptr [r14 + rbx + 17], 4 + pinsrb xmm0, byte ptr [r14 + rax + 17], 5 + mov r13, rax + pinsrb xmm0, byte ptr [r14 + rcx + 17], 6 + pinsrb xmm0, byte ptr [r14 + rdx + 17], 7 + pinsrb xmm0, byte ptr [r14 + r8 + 17], 8 + pinsrb xmm0, byte ptr [r14 + r9 + 17], 9 + pinsrb xmm0, byte ptr [r14 + rdi + 17], 10 + pinsrb xmm0, byte ptr [r14 + r15 + 17], 11 + pinsrb xmm0, byte ptr [r14 + r12 + 17], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 17], 13 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rsi + 17], 14 + por xmm12, xmmword ptr [rsp + 144] # 16-byte Folded Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload + movzx edi, byte ptr [r14 + rax + 27] + movd xmm9, edi + movdqa xmm13, xmmword ptr [rsp + 160] # 16-byte Reload + pcmpgtb xmm4, xmm13 + pand xmm4, xmmword ptr [rip + .LCPI7_15] + pcmpgtb xmm14, xmm13 + psllw xmm14, 7 + pand xmm14, xmmword ptr [rip + .LCPI7_6] + por xmm14, xmm4 + movzx edi, byte ptr [r14 + rax + 28] + movd xmm4, edi + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r11 + 17], 15 + por xmm14, xmm12 + pcmpgtb xmm0, xmm13 + movdqa xmm13, xmm0 + movdqa xmm12, xmmword ptr [rip + .LCPI7_10] # xmm12 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm13, xmm12 + psubb xmm13, xmm0 + movdqa xmmword ptr [rsp + 144], xmm13 # 16-byte Spill + movzx edi, byte ptr [r14 + rax + 29] + movd xmm13, edi + pinsrb xmm15, byte ptr [r14 + r11 + 16], 15 + movdqa xmm0, xmmword ptr [rsp + 160] # 16-byte Reload + pcmpgtb xmm15, xmm0 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rdi + 18], 1 + mov rdi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rdi + 18], 2 + pinsrb xmm5, byte ptr [r14 + r10 + 18], 3 + pinsrb xmm5, byte ptr [r14 + rbx + 18], 4 + pinsrb xmm5, byte ptr [r14 + r13 + 18], 5 + pinsrb xmm5, byte ptr [r14 + rcx + 18], 6 + pinsrb xmm5, byte ptr [r14 + rdx + 18], 7 + pinsrb xmm5, byte ptr [r14 + r8 + 18], 8 + pinsrb xmm5, byte ptr [r14 + r9 + 18], 9 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 18], 10 + pinsrb xmm5, byte ptr [r14 + r15 + 18], 11 + pinsrb xmm5, byte ptr [r14 + r12 + 18], 12 + mov rdi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rdi + 18], 13 + pinsrb xmm5, byte ptr [r14 + rsi + 18], 14 + pand xmm15, xmm12 + pinsrb xmm5, byte ptr [r14 + r11 + 18], 15 + pcmpgtb xmm5, xmm0 + pand xmm5, xmmword ptr [rip + .LCPI7_11] + por xmm5, xmm15 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + movzx edi, byte ptr [r14 + rsi + 30] + movd xmm12, edi + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdi + 19], 1 + pinsrb xmm6, byte ptr [r14 + rdi + 20], 1 + pinsrb xmm2, byte ptr [r14 + rdi + 21], 1 + pinsrb xmm3, byte ptr [r14 + rdi + 22], 1 + pinsrb xmm8, byte ptr [r14 + rdi + 23], 1 + pinsrb xmm10, byte ptr [r14 + rdi + 24], 1 + pinsrb xmm1, byte ptr [r14 + rdi + 25], 1 + pinsrb xmm11, byte ptr [r14 + rdi + 26], 1 + pinsrb xmm9, byte ptr [r14 + rdi + 27], 1 + pinsrb xmm4, byte ptr [r14 + rdi + 28], 1 + pinsrb xmm13, byte ptr [r14 + rdi + 29], 1 + pinsrb xmm12, byte ptr [r14 + rdi + 30], 1 + movzx esi, byte ptr [r14 + rsi + 31] + movd xmm0, esi + pinsrb xmm0, byte ptr [r14 + rdi + 31], 1 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rsi + 19], 2 + pinsrb xmm6, byte ptr [r14 + rsi + 20], 2 + pinsrb xmm2, byte ptr [r14 + rsi + 21], 2 + pinsrb xmm3, byte ptr [r14 + rsi + 22], 2 + pinsrb xmm8, byte ptr [r14 + rsi + 23], 2 + pinsrb xmm10, byte ptr [r14 + rsi + 24], 2 + pinsrb xmm1, byte ptr [r14 + rsi + 25], 2 + pinsrb xmm11, byte ptr [r14 + rsi + 26], 2 + pinsrb xmm9, byte ptr [r14 + rsi + 27], 2 + pinsrb xmm4, byte ptr [r14 + rsi + 28], 2 + pinsrb xmm13, byte ptr [r14 + rsi + 29], 2 + pinsrb xmm12, byte ptr [r14 + rsi + 30], 2 + pinsrb xmm0, byte ptr [r14 + rsi + 31], 2 + pinsrb xmm7, byte ptr [r14 + r10 + 19], 3 + pinsrb xmm7, byte ptr [r14 + rbx + 19], 4 + pinsrb xmm7, byte ptr [r14 + r13 + 19], 5 + pinsrb xmm7, byte ptr [r14 + rcx + 19], 6 + pinsrb xmm7, byte ptr [r14 + rdx + 19], 7 + pinsrb xmm7, byte ptr [r14 + r8 + 19], 8 + pinsrb xmm7, byte ptr [r14 + r9 + 19], 9 + pinsrb xmm7, byte ptr [r14 + rax + 19], 10 + pinsrb xmm7, byte ptr [r14 + r15 + 19], 11 + pinsrb xmm7, byte ptr [r14 + r12 + 19], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rsi + 19], 13 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rdi + 19], 14 + pinsrb xmm7, byte ptr [r14 + r11 + 19], 15 + pinsrb xmm6, byte ptr [r14 + r10 + 20], 3 + pinsrb xmm6, byte ptr [r14 + rbx + 20], 4 + pinsrb xmm6, byte ptr [r14 + r13 + 20], 5 + pinsrb xmm6, byte ptr [r14 + rcx + 20], 6 + pinsrb xmm6, byte ptr [r14 + rdx + 20], 7 + pinsrb xmm6, byte ptr [r14 + r8 + 20], 8 + pinsrb xmm6, byte ptr [r14 + r9 + 20], 9 + pinsrb xmm6, byte ptr [r14 + rax + 20], 10 + pinsrb xmm6, byte ptr [r14 + r15 + 20], 11 + pinsrb xmm6, byte ptr [r14 + r12 + 20], 12 + pinsrb xmm6, byte ptr [r14 + rsi + 20], 13 + pinsrb xmm6, byte ptr [r14 + rdi + 20], 14 + por xmm5, xmmword ptr [rsp + 144] # 16-byte Folded Reload + pinsrb xmm6, byte ptr [r14 + r11 + 20], 15 + movdqa xmm15, xmmword ptr [rsp + 160] # 16-byte Reload + pcmpgtb xmm7, xmm15 + pand xmm7, xmmword ptr [rip + .LCPI7_12] + pcmpgtb xmm6, xmm15 + pand xmm6, xmmword ptr [rip + .LCPI7_13] + por xmm6, xmm7 + pinsrb xmm2, byte ptr [r14 + r10 + 21], 3 + pinsrb xmm2, byte ptr [r14 + rbx + 21], 4 + pinsrb xmm2, byte ptr [r14 + r13 + 21], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 21], 6 + pinsrb xmm2, byte ptr [r14 + rdx + 21], 7 + pinsrb xmm2, byte ptr [r14 + r8 + 21], 8 + pinsrb xmm2, byte ptr [r14 + r9 + 21], 9 + pinsrb xmm2, byte ptr [r14 + rax + 21], 10 + pinsrb xmm2, byte ptr [r14 + r15 + 21], 11 + pinsrb xmm2, byte ptr [r14 + r12 + 21], 12 + pinsrb xmm2, byte ptr [r14 + rsi + 21], 13 + pinsrb xmm2, byte ptr [r14 + rdi + 21], 14 + pinsrb xmm2, byte ptr [r14 + r11 + 21], 15 + pcmpgtb xmm2, xmm15 + movdqa xmm7, xmmword ptr [rip + .LCPI7_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm2, xmm7 + por xmm2, xmm6 + por xmm2, xmm5 + pinsrb xmm3, byte ptr [r14 + r10 + 22], 3 + pinsrb xmm3, byte ptr [r14 + rbx + 22], 4 + pinsrb xmm3, byte ptr [r14 + r13 + 22], 5 + pinsrb xmm3, byte ptr [r14 + rcx + 22], 6 + pinsrb xmm3, byte ptr [r14 + rdx + 22], 7 + pinsrb xmm3, byte ptr [r14 + r8 + 22], 8 + pinsrb xmm3, byte ptr [r14 + r9 + 22], 9 + pinsrb xmm3, byte ptr [r14 + rax + 22], 10 + pinsrb xmm3, byte ptr [r14 + r15 + 22], 11 + pinsrb xmm3, byte ptr [r14 + r12 + 22], 12 + pinsrb xmm3, byte ptr [r14 + rsi + 22], 13 + pinsrb xmm3, byte ptr [r14 + rdi + 22], 14 + pinsrb xmm3, byte ptr [r14 + r11 + 22], 15 + pinsrb xmm8, byte ptr [r14 + r10 + 23], 3 + pinsrb xmm8, byte ptr [r14 + rbx + 23], 4 + pinsrb xmm8, byte ptr [r14 + r13 + 23], 5 + pinsrb xmm8, byte ptr [r14 + rcx + 23], 6 + pinsrb xmm8, byte ptr [r14 + rdx + 23], 7 + pinsrb xmm8, byte ptr [r14 + r8 + 23], 8 + pinsrb xmm8, byte ptr [r14 + r9 + 23], 9 + pinsrb xmm8, byte ptr [r14 + rax + 23], 10 + pinsrb xmm8, byte ptr [r14 + r15 + 23], 11 + pinsrb xmm8, byte ptr [r14 + r12 + 23], 12 + pinsrb xmm8, byte ptr [r14 + rsi + 23], 13 + pinsrb xmm8, byte ptr [r14 + rdi + 23], 14 + pinsrb xmm8, byte ptr [r14 + r11 + 23], 15 + pcmpgtb xmm3, xmm15 + movdqa xmm5, xmmword ptr [rip + .LCPI7_15] # xmm5 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm3, xmm5 + pcmpgtb xmm8, xmm15 + psllw xmm8, 7 + movdqa xmm6, xmmword ptr [rip + .LCPI7_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm8, xmm6 + por xmm8, xmm3 + pinsrb xmm1, byte ptr [r14 + r10 + 25], 3 + pinsrb xmm1, byte ptr [r14 + rbx + 25], 4 + pinsrb xmm1, byte ptr [r14 + r13 + 25], 5 + pinsrb xmm1, byte ptr [r14 + rcx + 25], 6 + pinsrb xmm1, byte ptr [r14 + rdx + 25], 7 + pinsrb xmm1, byte ptr [r14 + r8 + 25], 8 + pinsrb xmm1, byte ptr [r14 + r9 + 25], 9 + pinsrb xmm1, byte ptr [r14 + rax + 25], 10 + pinsrb xmm1, byte ptr [r14 + r15 + 25], 11 + pinsrb xmm1, byte ptr [r14 + r12 + 25], 12 + pinsrb xmm1, byte ptr [r14 + rsi + 25], 13 + pinsrb xmm1, byte ptr [r14 + rdi + 25], 14 + pinsrb xmm1, byte ptr [r14 + r11 + 25], 15 + por xmm8, xmm2 + pcmpgtb xmm1, xmm15 + movdqa xmm2, xmm1 + movdqa xmm3, xmmword ptr [rip + .LCPI7_10] # xmm3 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm2, xmm3 + psubb xmm2, xmm1 + pinsrb xmm10, byte ptr [r14 + r10 + 24], 3 + pinsrb xmm10, byte ptr [r14 + rbx + 24], 4 + pinsrb xmm10, byte ptr [r14 + r13 + 24], 5 + pinsrb xmm10, byte ptr [r14 + rcx + 24], 6 + pinsrb xmm10, byte ptr [r14 + rdx + 24], 7 + pinsrb xmm10, byte ptr [r14 + r8 + 24], 8 + pinsrb xmm10, byte ptr [r14 + r9 + 24], 9 + pinsrb xmm10, byte ptr [r14 + rax + 24], 10 + pinsrb xmm10, byte ptr [r14 + r15 + 24], 11 + pinsrb xmm10, byte ptr [r14 + r12 + 24], 12 + pinsrb xmm10, byte ptr [r14 + rsi + 24], 13 + pinsrb xmm10, byte ptr [r14 + rdi + 24], 14 + pinsrb xmm10, byte ptr [r14 + r11 + 24], 15 + pcmpgtb xmm10, xmm15 + pand xmm10, xmm3 + pinsrb xmm11, byte ptr [r14 + r10 + 26], 3 + pinsrb xmm11, byte ptr [r14 + rbx + 26], 4 + pinsrb xmm11, byte ptr [r14 + r13 + 26], 5 + pinsrb xmm11, byte ptr [r14 + rcx + 26], 6 + pinsrb xmm11, byte ptr [r14 + rdx + 26], 7 + pinsrb xmm11, byte ptr [r14 + r8 + 26], 8 + pinsrb xmm11, byte ptr [r14 + r9 + 26], 9 + pinsrb xmm11, byte ptr [r14 + rax + 26], 10 + pinsrb xmm11, byte ptr [r14 + r15 + 26], 11 + pinsrb xmm11, byte ptr [r14 + r12 + 26], 12 + pinsrb xmm11, byte ptr [r14 + rsi + 26], 13 + pinsrb xmm11, byte ptr [r14 + rdi + 26], 14 + pinsrb xmm11, byte ptr [r14 + r11 + 26], 15 + pcmpgtb xmm11, xmm15 + pand xmm11, xmmword ptr [rip + .LCPI7_11] + por xmm11, xmm10 + por xmm11, xmm2 + pinsrb xmm9, byte ptr [r14 + r10 + 27], 3 + pinsrb xmm9, byte ptr [r14 + rbx + 27], 4 + pinsrb xmm9, byte ptr [r14 + r13 + 27], 5 + pinsrb xmm9, byte ptr [r14 + rcx + 27], 6 + pinsrb xmm9, byte ptr [r14 + rdx + 27], 7 + pinsrb xmm9, byte ptr [r14 + r8 + 27], 8 + pinsrb xmm9, byte ptr [r14 + r9 + 27], 9 + pinsrb xmm9, byte ptr [r14 + rax + 27], 10 + pinsrb xmm9, byte ptr [r14 + r15 + 27], 11 + pinsrb xmm9, byte ptr [r14 + r12 + 27], 12 + pinsrb xmm9, byte ptr [r14 + rsi + 27], 13 + pinsrb xmm9, byte ptr [r14 + rdi + 27], 14 + pinsrb xmm9, byte ptr [r14 + r11 + 27], 15 + pinsrb xmm4, byte ptr [r14 + r10 + 28], 3 + pinsrb xmm4, byte ptr [r14 + rbx + 28], 4 + pinsrb xmm4, byte ptr [r14 + r13 + 28], 5 + pinsrb xmm4, byte ptr [r14 + rcx + 28], 6 + pinsrb xmm4, byte ptr [r14 + rdx + 28], 7 + pinsrb xmm4, byte ptr [r14 + r8 + 28], 8 + pinsrb xmm4, byte ptr [r14 + r9 + 28], 9 + pinsrb xmm4, byte ptr [r14 + rax + 28], 10 + pinsrb xmm4, byte ptr [r14 + r15 + 28], 11 + pinsrb xmm4, byte ptr [r14 + r12 + 28], 12 + pinsrb xmm4, byte ptr [r14 + rsi + 28], 13 + pinsrb xmm4, byte ptr [r14 + rdi + 28], 14 + pinsrb xmm4, byte ptr [r14 + r11 + 28], 15 + pinsrb xmm13, byte ptr [r14 + r10 + 29], 3 + pinsrb xmm13, byte ptr [r14 + rbx + 29], 4 + pinsrb xmm13, byte ptr [r14 + r13 + 29], 5 + pinsrb xmm13, byte ptr [r14 + rcx + 29], 6 + pinsrb xmm13, byte ptr [r14 + rdx + 29], 7 + pinsrb xmm13, byte ptr [r14 + r8 + 29], 8 + pinsrb xmm13, byte ptr [r14 + r9 + 29], 9 + pinsrb xmm13, byte ptr [r14 + rax + 29], 10 + pinsrb xmm13, byte ptr [r14 + r15 + 29], 11 + pinsrb xmm13, byte ptr [r14 + r12 + 29], 12 + pinsrb xmm13, byte ptr [r14 + rsi + 29], 13 + pinsrb xmm13, byte ptr [r14 + rdi + 29], 14 + movdqa xmm1, xmm15 + pcmpgtb xmm9, xmm15 + pand xmm9, xmmword ptr [rip + .LCPI7_12] + pcmpgtb xmm4, xmm15 + pand xmm4, xmmword ptr [rip + .LCPI7_13] + por xmm4, xmm9 + pinsrb xmm13, byte ptr [r14 + r11 + 29], 15 + pcmpgtb xmm13, xmm15 + pand xmm13, xmm7 + por xmm13, xmm4 + pinsrb xmm12, byte ptr [r14 + r10 + 30], 3 + pinsrb xmm0, byte ptr [r14 + r10 + 31], 3 + pinsrb xmm12, byte ptr [r14 + rbx + 30], 4 + pinsrb xmm0, byte ptr [r14 + rbx + 31], 4 + pinsrb xmm12, byte ptr [r14 + r13 + 30], 5 + pinsrb xmm0, byte ptr [r14 + r13 + 31], 5 + pinsrb xmm12, byte ptr [r14 + rcx + 30], 6 + pinsrb xmm0, byte ptr [r14 + rcx + 31], 6 + pinsrb xmm12, byte ptr [r14 + rdx + 30], 7 + pinsrb xmm0, byte ptr [r14 + rdx + 31], 7 + pinsrb xmm12, byte ptr [r14 + r8 + 30], 8 + pinsrb xmm0, byte ptr [r14 + r8 + 31], 8 + pinsrb xmm12, byte ptr [r14 + r9 + 30], 9 + pinsrb xmm0, byte ptr [r14 + r9 + 31], 9 + pinsrb xmm12, byte ptr [r14 + rax + 30], 10 + pinsrb xmm0, byte ptr [r14 + rax + 31], 10 + pinsrb xmm12, byte ptr [r14 + r15 + 30], 11 + pinsrb xmm0, byte ptr [r14 + r15 + 31], 11 + pinsrb xmm12, byte ptr [r14 + r12 + 30], 12 + pinsrb xmm0, byte ptr [r14 + r12 + 31], 12 + pinsrb xmm12, byte ptr [r14 + rsi + 30], 13 + pinsrb xmm0, byte ptr [r14 + rsi + 31], 13 + pinsrb xmm12, byte ptr [r14 + rdi + 30], 14 + pinsrb xmm0, byte ptr [r14 + rdi + 31], 14 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm12, byte ptr [r14 + r11 + 30], 15 + pinsrb xmm0, byte ptr [r14 + r11 + 31], 15 + por xmm13, xmm11 + pcmpgtb xmm12, xmm15 + pand xmm12, xmm5 + pcmpgtb xmm0, xmm15 + psllw xmm0, 7 + pand xmm0, xmm6 + por xmm0, xmm12 + por xmm0, xmm13 + movdqa xmm1, xmm8 + punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload + movdqa xmm2, xmm4 + punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] + movdqa xmm3, xmm2 + punpcklwd xmm3, xmm1 # xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3] + punpckhwd xmm2, xmm1 # xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] + punpckhbw xmm8, xmm0 # xmm8 = xmm8[8],xmm0[8],xmm8[9],xmm0[9],xmm8[10],xmm0[10],xmm8[11],xmm0[11],xmm8[12],xmm0[12],xmm8[13],xmm0[13],xmm8[14],xmm0[14],xmm8[15],xmm0[15] + punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] + movdqa xmm0, xmm4 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + movdqu xmmword ptr [r12 + 4*rcx + 48], xmm4 + movdqu xmmword ptr [r12 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r12 + 4*rcx + 16], xmm2 + movdqu xmmword ptr [r12 + 4*rcx], xmm3 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + jne .LBB7_98 +# %bb.99: + mov rcx, qword ptr [rsp + 280] # 8-byte Reload + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r13b, byte ptr [rsp + 8] # 1-byte Reload + mov rsi, qword ptr [rsp + 312] # 8-byte Reload + jne .LBB7_100 + jmp .LBB7_103 +.LBB7_71: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, r14 + mov qword ptr [rsp + 336], rax # 8-byte Spill + mov qword ptr [rsp + 248], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 96], rax # 8-byte Spill + movzx eax, byte ptr [rsp + 280] # 1-byte Folded Reload + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 128], r12 # 8-byte Spill + .p2align 4, 0x90 +.LBB7_72: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 192], rax # 8-byte Spill + mov rax, qword ptr [rsp + 192] # 8-byte Reload + shl rax, 5 + mov r8, rax + mov rdi, rax + mov r9, rax + mov qword ptr [rsp + 80], rax # 8-byte Spill + mov r12, rax + mov r11, rax + mov r15, rax + mov r10, rax + mov rbx, rax + mov r13, rax + mov qword ptr [rsp + 16], rax # 8-byte Spill + movzx ecx, byte ptr [r14 + rax] + movd xmm10, ecx + movzx ecx, byte ptr [r14 + rax + 1] + movd xmm4, ecx + movzx ecx, byte ptr [r14 + rax + 2] + movd xmm6, ecx + movzx ecx, byte ptr [r14 + rax + 3] + movd xmm5, ecx + movzx ecx, byte ptr [r14 + rax + 4] + movd xmm9, ecx + movzx ecx, byte ptr [r14 + rax + 5] + movd xmm7, ecx + movzx ecx, byte ptr [r14 + rax + 6] + movd xmm0, ecx + movzx ecx, byte ptr [r14 + rax + 7] + movd xmm1, ecx + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill + movzx ecx, byte ptr [r14 + rax + 8] + movd xmm14, ecx + movzx ecx, byte ptr [r14 + rax + 9] + movd xmm1, ecx + movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + movzx ecx, byte ptr [r14 + rax + 10] + movd xmm2, ecx + movzx ecx, byte ptr [r14 + rax + 11] + movd xmm11, ecx + movzx ecx, byte ptr [r14 + rax + 12] + movd xmm1, ecx + movdqa xmmword ptr [rsp + 320], xmm1 # 16-byte Spill + movzx ecx, byte ptr [r14 + rax + 16] + movd xmm13, ecx + mov qword ptr [rsp + 120], rax # 8-byte Spill + movzx ecx, byte ptr [r14 + rax + 24] + movd xmm15, ecx + mov rsi, rax + or rsi, 32 + or r8, 64 + mov qword ptr [rsp + 72], r8 # 8-byte Spill + or rdi, 96 + mov qword ptr [rsp + 40], rdi # 8-byte Spill + or r9, 128 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + or rcx, 160 + mov qword ptr [rsp + 80], rcx # 8-byte Spill + mov rdi, rax + or rdi, 192 + mov qword ptr [rsp + 56], rdi # 8-byte Spill + or r11, 224 + or r15, 256 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + or r10, 288 + or rbx, 320 + or r13, 352 + or qword ptr [rsp + 16], 384 # 8-byte Folded Spill + mov rdx, rax + or rdx, 416 + mov qword ptr [rsp + 24], rdx # 8-byte Spill + mov rdx, rax + or rdx, 448 + mov qword ptr [rsp + 8], rdx # 8-byte Spill + or r12, 480 + pinsrb xmm10, byte ptr [r14 + rsi], 1 + mov rax, rsi + mov qword ptr [rsp + 48], rsi # 8-byte Spill + pinsrb xmm10, byte ptr [r14 + r8], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rdx], 3 + mov rsi, rdx + pinsrb xmm10, byte ptr [r14 + r9], 4 + mov rdx, r9 + mov qword ptr [rsp + 144], r9 # 8-byte Spill + pinsrb xmm10, byte ptr [r14 + rcx], 5 + pinsrb xmm10, byte ptr [r14 + rdi], 6 + pinsrb xmm10, byte ptr [r14 + r11], 7 + pinsrb xmm10, byte ptr [r14 + r15], 8 + pinsrb xmm10, byte ptr [r14 + r10], 9 + mov r15, r10 + pinsrb xmm10, byte ptr [r14 + rbx], 10 + mov rdi, rbx + mov qword ptr [rsp + 160], rbx # 8-byte Spill + pinsrb xmm10, byte ptr [r14 + r13], 11 + mov r10, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r10], 12 + mov r9, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + r9], 13 + mov rbx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm10, byte ptr [r14 + rbx], 14 + pinsrb xmm10, byte ptr [r14 + r12], 15 + movdqa xmm8, xmm10 + movdqa xmm12, xmmword ptr [rsp + 288] # 16-byte Reload + pminub xmm8, xmm12 + pcmpeqb xmm8, xmm10 + pinsrb xmm4, byte ptr [r14 + rax + 1], 1 + pinsrb xmm4, byte ptr [r14 + r8 + 1], 2 + pinsrb xmm4, byte ptr [r14 + rsi + 1], 3 + pinsrb xmm4, byte ptr [r14 + rdx + 1], 4 + pinsrb xmm4, byte ptr [r14 + rcx + 1], 5 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rax + 1], 6 + pinsrb xmm4, byte ptr [r14 + r11 + 1], 7 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [r14 + rdx + 1], 8 + mov rdx, r15 + mov qword ptr [rsp + 104], r15 # 8-byte Spill + pinsrb xmm4, byte ptr [r14 + r15 + 1], 9 + pinsrb xmm4, byte ptr [r14 + rdi + 1], 10 + pinsrb xmm4, byte ptr [r14 + r13 + 1], 11 + pinsrb xmm4, byte ptr [r14 + r10 + 1], 12 + pinsrb xmm4, byte ptr [r14 + r9 + 1], 13 + pinsrb xmm4, byte ptr [r14 + rbx + 1], 14 + pinsrb xmm4, byte ptr [r14 + r12 + 1], 15 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rsi + 2], 1 + pinsrb xmm6, byte ptr [r14 + r8 + 2], 2 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r15 + 2], 3 + mov rdi, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdi + 2], 4 + pinsrb xmm6, byte ptr [r14 + rcx + 2], 5 + pinsrb xmm6, byte ptr [r14 + rax + 2], 6 + pinsrb xmm6, byte ptr [r14 + r11 + 2], 7 + mov r15, r11 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + r11 + 2], 8 + pinsrb xmm6, byte ptr [r14 + rdx + 2], 9 + mov rdi, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdi + 2], 10 + pinsrb xmm6, byte ptr [r14 + r13 + 2], 11 + pinsrb xmm6, byte ptr [r14 + r10 + 2], 12 + pinsrb xmm6, byte ptr [r14 + r9 + 2], 13 + pinsrb xmm6, byte ptr [r14 + rbx + 2], 14 + pinsrb xmm6, byte ptr [r14 + r12 + 2], 15 + pinsrb xmm14, byte ptr [r14 + rsi + 8], 1 + pinsrb xmm14, byte ptr [r14 + r8 + 8], 2 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rsi + 8], 3 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rdx + 8], 4 + pinsrb xmm14, byte ptr [r14 + rcx + 8], 5 + pinsrb xmm14, byte ptr [r14 + rax + 8], 6 + pinsrb xmm14, byte ptr [r14 + r15 + 8], 7 + pinsrb xmm14, byte ptr [r14 + r11 + 8], 8 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm14, byte ptr [r14 + rax + 8], 9 + pinsrb xmm14, byte ptr [r14 + rdi + 8], 10 + pinsrb xmm14, byte ptr [r14 + r13 + 8], 11 + pinsrb xmm14, byte ptr [r14 + r10 + 8], 12 + pinsrb xmm14, byte ptr [r14 + r9 + 8], 13 + pinsrb xmm14, byte ptr [r14 + rbx + 8], 14 + pinsrb xmm14, byte ptr [r14 + r12 + 8], 15 + movdqa xmm10, xmm14 + pminub xmm10, xmm12 + pcmpeqb xmm10, xmm14 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + r9 + 16], 1 + pinsrb xmm13, byte ptr [r14 + r8 + 16], 2 + pinsrb xmm13, byte ptr [r14 + rsi + 16], 3 + pinsrb xmm13, byte ptr [r14 + rdx + 16], 4 + pinsrb xmm13, byte ptr [r14 + rcx + 16], 5 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rsi + 16], 6 + mov r11, r15 + mov qword ptr [rsp + 112], r15 # 8-byte Spill + pinsrb xmm13, byte ptr [r14 + r15 + 16], 7 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + r15 + 16], 8 + mov rbx, rax + pinsrb xmm13, byte ptr [r14 + rax + 16], 9 + mov rdx, rdi + pinsrb xmm13, byte ptr [r14 + rdi + 16], 10 + pinsrb xmm13, byte ptr [r14 + r13 + 16], 11 + pinsrb xmm13, byte ptr [r14 + r10 + 16], 12 + mov rdi, r10 + mov qword ptr [rsp + 16], r10 # 8-byte Spill + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rax + 16], 13 + mov rcx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm13, byte ptr [r14 + rcx + 16], 14 + mov qword ptr [rsp + 64], r12 # 8-byte Spill + pinsrb xmm13, byte ptr [r14 + r12 + 16], 15 + movdqa xmm3, xmm13 + pminub xmm3, xmm12 + pcmpeqb xmm3, xmm13 + movdqa xmmword ptr [rsp + 256], xmm3 # 16-byte Spill + pinsrb xmm15, byte ptr [r14 + r9 + 24], 1 + pinsrb xmm15, byte ptr [r14 + r8 + 24], 2 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r9 + 24], 3 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r10 + 24], 4 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm15, byte ptr [r14 + r8 + 24], 5 + pinsrb xmm15, byte ptr [r14 + rsi + 24], 6 + pinsrb xmm15, byte ptr [r14 + r11 + 24], 7 + pinsrb xmm15, byte ptr [r14 + r15 + 24], 8 + pinsrb xmm15, byte ptr [r14 + rbx + 24], 9 + pinsrb xmm15, byte ptr [r14 + rdx + 24], 10 + mov r11, rdx + pinsrb xmm15, byte ptr [r14 + r13 + 24], 11 + pinsrb xmm15, byte ptr [r14 + rdi + 24], 12 + pinsrb xmm15, byte ptr [r14 + rax + 24], 13 + pinsrb xmm15, byte ptr [r14 + rcx + 24], 14 + pinsrb xmm15, byte ptr [r14 + r12 + 24], 15 + movdqa xmm3, xmm15 + pminub xmm3, xmm12 + pcmpeqb xmm3, xmm15 + movdqa xmmword ptr [rsp + 224], xmm3 # 16-byte Spill + movdqa xmm14, xmm4 + pminub xmm14, xmm12 + pcmpeqb xmm14, xmm4 + movdqa xmm13, xmm14 + movdqa xmm4, xmmword ptr [rip + .LCPI7_10] # xmm4 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pandn xmm13, xmm4 + paddb xmm13, xmm14 + movdqa xmm14, xmm6 + pminub xmm14, xmm12 + pcmpeqb xmm14, xmm6 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 13] + movd xmm6, edx + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 3], 1 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rcx + 3], 2 + mov rsi, r9 + pinsrb xmm5, byte ptr [r14 + r9 + 3], 3 + mov rdi, r10 + pinsrb xmm5, byte ptr [r14 + r10 + 3], 4 + mov rdx, r8 + pinsrb xmm5, byte ptr [r14 + r8 + 3], 5 + mov r9, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r9 + 3], 6 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r15 + 3], 7 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r10 + 3], 8 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r8 + 3], 9 + pinsrb xmm5, byte ptr [r14 + r11 + 3], 10 + mov qword ptr [rsp + 88], r13 # 8-byte Spill + pinsrb xmm5, byte ptr [r14 + r13 + 3], 11 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rbx + 3], 12 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r12 + 3], 13 + mov r13, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r13 + 3], 14 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r11 + 3], 15 + pinsrb xmm9, byte ptr [r14 + rax + 4], 1 + pinsrb xmm9, byte ptr [r14 + rcx + 4], 2 + pinsrb xmm9, byte ptr [r14 + rsi + 4], 3 + pinsrb xmm9, byte ptr [r14 + rdi + 4], 4 + pinsrb xmm9, byte ptr [r14 + rdx + 4], 5 + pinsrb xmm9, byte ptr [r14 + r9 + 4], 6 + pinsrb xmm9, byte ptr [r14 + r15 + 4], 7 + pinsrb xmm9, byte ptr [r14 + r10 + 4], 8 + pinsrb xmm9, byte ptr [r14 + r8 + 4], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm9, byte ptr [r14 + rbx + 4], 10 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm9, byte ptr [r14 + rbx + 4], 11 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm9, byte ptr [r14 + rbx + 4], 12 + pinsrb xmm9, byte ptr [r14 + r12 + 4], 13 + pinsrb xmm9, byte ptr [r14 + r13 + 4], 14 + pinsrb xmm9, byte ptr [r14 + r11 + 4], 15 + pinsrb xmm7, byte ptr [r14 + rax + 5], 1 + pinsrb xmm7, byte ptr [r14 + rcx + 5], 2 + pinsrb xmm7, byte ptr [r14 + rsi + 5], 3 + pinsrb xmm7, byte ptr [r14 + rdi + 5], 4 + pinsrb xmm7, byte ptr [r14 + rdx + 5], 5 + pinsrb xmm7, byte ptr [r14 + r9 + 5], 6 + pinsrb xmm7, byte ptr [r14 + r15 + 5], 7 + pinsrb xmm7, byte ptr [r14 + r10 + 5], 8 + pinsrb xmm7, byte ptr [r14 + r8 + 5], 9 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rbx + 5], 10 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rbx + 5], 11 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rbx + 5], 12 + pinsrb xmm7, byte ptr [r14 + r12 + 5], 13 + pinsrb xmm7, byte ptr [r14 + r13 + 5], 14 + pinsrb xmm7, byte ptr [r14 + r11 + 5], 15 + pinsrb xmm0, byte ptr [r14 + rax + 6], 1 + pinsrb xmm0, byte ptr [r14 + rcx + 6], 2 + pinsrb xmm0, byte ptr [r14 + rsi + 6], 3 + mov r11, rsi + pinsrb xmm0, byte ptr [r14 + rdi + 6], 4 + pinsrb xmm0, byte ptr [r14 + rdx + 6], 5 + pinsrb xmm0, byte ptr [r14 + r9 + 6], 6 + pinsrb xmm0, byte ptr [r14 + r15 + 6], 7 + pinsrb xmm0, byte ptr [r14 + r10 + 6], 8 + pinsrb xmm0, byte ptr [r14 + r8 + 6], 9 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r9 + 6], 10 + mov rax, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 6], 11 + pinsrb xmm0, byte ptr [r14 + rbx + 6], 12 + pinsrb xmm0, byte ptr [r14 + r12 + 6], 13 + pandn xmm8, xmm4 + pinsrb xmm0, byte ptr [r14 + r13 + 6], 14 + movdqa xmm4, xmmword ptr [rip + .LCPI7_11] # xmm4 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm14, xmm4 + por xmm14, xmm8 + movdqa xmm15, xmm5 + pminub xmm15, xmm12 + pcmpeqb xmm15, xmm5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 14] + movd xmm5, edx + movdqa xmm4, xmmword ptr [rip + .LCPI7_12] # xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm15, xmm4 + por xmm15, xmm14 + movzx edx, byte ptr [r14 + rax + 15] + movd xmm8, edx + pcmpeqd xmm3, xmm3 + psubb xmm13, xmm3 + pcmpeqd xmm14, xmm14 + por xmm15, xmm13 + movdqa xmm4, xmm9 + pminub xmm4, xmm12 + pcmpeqb xmm4, xmm9 + movdqa xmm9, xmm7 + pminub xmm9, xmm12 + pcmpeqb xmm9, xmm7 + movzx edx, byte ptr [r14 + rax + 17] + movd xmm7, edx + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rcx + 6], 15 + movdqa xmm1, xmmword ptr [rip + .LCPI7_13] # xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm4, xmm1 + movdqa xmm1, xmmword ptr [rip + .LCPI7_14] # xmm1 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm9, xmm1 + por xmm9, xmm4 + movdqa xmm4, xmm0 + pminub xmm4, xmm12 + pcmpeqb xmm4, xmm0 + movzx edx, byte ptr [r14 + rax + 18] + mov r10, rax + movd xmm1, edx + movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rsi + 7], 1 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 7], 2 + pinsrb xmm0, byte ptr [r14 + r11 + 7], 3 + pinsrb xmm0, byte ptr [r14 + rdi + 7], 4 + mov r12, rdi + mov rdi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdi + 7], 5 + mov r8, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r8 + 7], 6 + mov r11, r15 + pinsrb xmm0, byte ptr [r14 + r15 + 7], 7 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r15 + 7], 8 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 7], 9 + mov rbx, r9 + pinsrb xmm0, byte ptr [r14 + r9 + 7], 10 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r13 + 7], 11 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 7], 12 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 7], 13 + mov r9, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r9 + 7], 14 + pinsrb xmm0, byte ptr [r14 + rcx + 7], 15 + movdqa xmm3, xmmword ptr [rip + .LCPI7_15] # xmm3 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm4, xmm3 + por xmm4, xmm9 + movdqa xmm9, xmm0 + pminub xmm9, xmm12 + pcmpeqb xmm9, xmm0 + movzx edx, byte ptr [r14 + r10 + 19] + movd xmm3, edx + pxor xmm9, xmm14 + psllw xmm9, 7 + movdqa xmm0, xmmword ptr [rip + .LCPI7_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm9, xmm0 + por xmm9, xmm4 + movdqa xmm4, xmm9 + movzx edx, byte ptr [r14 + r10 + 20] + movd xmm9, edx + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + pinsrb xmm0, byte ptr [r14 + rsi + 9], 1 + pinsrb xmm0, byte ptr [r14 + rax + 9], 2 + mov r10, rax + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 9], 3 + mov rax, r12 + pinsrb xmm0, byte ptr [r14 + r12 + 9], 4 + pinsrb xmm0, byte ptr [r14 + rdi + 9], 5 + mov rcx, r8 + pinsrb xmm0, byte ptr [r14 + r8 + 9], 6 + pinsrb xmm0, byte ptr [r14 + r11 + 9], 7 + mov r12, r15 + pinsrb xmm0, byte ptr [r14 + r15 + 9], 8 + mov rdi, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdi + 9], 9 + pinsrb xmm0, byte ptr [r14 + rbx + 9], 10 + pinsrb xmm0, byte ptr [r14 + r13 + 9], 11 + mov r15, r13 + mov r8, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r8 + 9], 12 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r13 + 9], 13 + pinsrb xmm0, byte ptr [r14 + r9 + 9], 14 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r11 + 9], 15 + pinsrb xmm2, byte ptr [r14 + rsi + 10], 1 + pinsrb xmm2, byte ptr [r14 + r10 + 10], 2 + pinsrb xmm2, byte ptr [r14 + rdx + 10], 3 + pinsrb xmm2, byte ptr [r14 + rax + 10], 4 + mov r10, rax + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rsi + 10], 5 + pinsrb xmm2, byte ptr [r14 + rcx + 10], 6 + mov rdi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + rdi + 10], 7 + pinsrb xmm2, byte ptr [r14 + r12 + 10], 8 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm2, byte ptr [r14 + r12 + 10], 9 + pinsrb xmm2, byte ptr [r14 + rbx + 10], 10 + pinsrb xmm2, byte ptr [r14 + r15 + 10], 11 + pinsrb xmm2, byte ptr [r14 + r8 + 10], 12 + mov r15, r8 + pinsrb xmm2, byte ptr [r14 + r13 + 10], 13 + pinsrb xmm2, byte ptr [r14 + r9 + 10], 14 + pinsrb xmm2, byte ptr [r14 + r11 + 10], 15 + por xmm4, xmm15 + movdqa xmmword ptr [rsp + 176], xmm4 # 16-byte Spill + movdqa xmm4, xmm0 + pminub xmm4, xmm12 + pcmpeqb xmm4, xmm0 + movdqa xmm13, xmm4 + movdqa xmm14, xmmword ptr [rip + .LCPI7_10] # xmm14 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pandn xmm13, xmm14 + paddb xmm13, xmm4 + movdqa xmm0, xmm2 + pminub xmm0, xmm12 + pcmpeqb xmm0, xmm2 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 21] + movd xmm4, edx + pandn xmm10, xmm14 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rcx + 11], 1 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 3 + pinsrb xmm11, byte ptr [r14 + r10 + 11], 4 + pinsrb xmm11, byte ptr [r14 + rsi + 11], 5 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 6 + pinsrb xmm11, byte ptr [r14 + rdi + 11], 7 + mov r9, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + r9 + 11], 8 + mov r8, r12 + pinsrb xmm11, byte ptr [r14 + r12 + 11], 9 + pinsrb xmm11, byte ptr [r14 + rbx + 11], 10 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 11 + pinsrb xmm11, byte ptr [r14 + r15 + 11], 12 + mov r12, r13 + pinsrb xmm11, byte ptr [r14 + r13 + 11], 13 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rdx + 11], 14 + pinsrb xmm11, byte ptr [r14 + r11 + 11], 15 + pandn xmm0, xmmword ptr [rip + .LCPI7_11] + por xmm0, xmm10 + movdqa xmm10, xmm11 + pminub xmm10, xmm12 + pcmpeqb xmm10, xmm11 + movzx edx, byte ptr [r14 + rax + 22] + movd xmm15, edx + pandn xmm10, xmmword ptr [rip + .LCPI7_12] + por xmm10, xmm0 + movzx edx, byte ptr [r14 + rax + 23] + movd xmm11, edx + movdqa xmm0, xmmword ptr [rsp + 320] # 16-byte Reload + pinsrb xmm0, byte ptr [r14 + rcx + 12], 1 + mov r10, rcx + mov r15, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r15 + 12], 2 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rcx + 12], 3 + mov rsi, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rsi + 12], 4 + mov r11, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r11 + 12], 5 + mov rdi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdi + 12], 6 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 12], 7 + pinsrb xmm0, byte ptr [r14 + r9 + 12], 8 + pinsrb xmm0, byte ptr [r14 + r8 + 12], 9 + pinsrb xmm0, byte ptr [r14 + rbx + 12], 10 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r13 + 12], 11 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rdx + 12], 12 + pinsrb xmm0, byte ptr [r14 + r12 + 12], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + rax + 12], 14 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm0, byte ptr [r14 + r9 + 12], 15 + pinsrb xmm6, byte ptr [r14 + r10 + 13], 1 + pinsrb xmm6, byte ptr [r14 + r15 + 13], 2 + mov rax, r15 + pinsrb xmm6, byte ptr [r14 + rcx + 13], 3 + mov r10, rcx + pinsrb xmm6, byte ptr [r14 + rsi + 13], 4 + pinsrb xmm6, byte ptr [r14 + r11 + 13], 5 + mov r15, r11 + pinsrb xmm6, byte ptr [r14 + rdi + 13], 6 + mov r11, rdi + mov rdi, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdi + 13], 7 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rcx + 13], 8 + pinsrb xmm6, byte ptr [r14 + r8 + 13], 9 + pinsrb xmm6, byte ptr [r14 + rbx + 13], 10 + pinsrb xmm6, byte ptr [r14 + r13 + 13], 11 + pinsrb xmm6, byte ptr [r14 + rdx + 13], 12 + pinsrb xmm6, byte ptr [r14 + r12 + 13], 13 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm6, byte ptr [r14 + rdx + 13], 14 + pinsrb xmm6, byte ptr [r14 + r9 + 13], 15 + psubb xmm13, xmmword ptr [rip + .LCPI7_16] + por xmm10, xmm13 + movdqa xmm2, xmm0 + movdqa xmm13, xmm12 + pminub xmm2, xmm12 + pcmpeqb xmm2, xmm0 + movdqa xmm0, xmm6 + pminub xmm0, xmm12 + pcmpeqb xmm0, xmm6 + mov rdx, qword ptr [rsp + 120] # 8-byte Reload + movzx edx, byte ptr [r14 + rdx + 25] + movd xmm12, edx + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rcx + 14], 1 + pinsrb xmm5, byte ptr [r14 + rax + 14], 2 + mov rdx, r10 + pinsrb xmm5, byte ptr [r14 + r10 + 14], 3 + mov r12, rsi + pinsrb xmm5, byte ptr [r14 + rsi + 14], 4 + mov rcx, r15 + pinsrb xmm5, byte ptr [r14 + r15 + 14], 5 + mov rsi, r11 + pinsrb xmm5, byte ptr [r14 + r11 + 14], 6 + mov r11, rdi + pinsrb xmm5, byte ptr [r14 + rdi + 14], 7 + mov r15, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r15 + 14], 8 + mov r10, r8 + pinsrb xmm5, byte ptr [r14 + r8 + 14], 9 + mov rdi, rbx + pinsrb xmm5, byte ptr [r14 + rbx + 14], 10 + mov rbx, r13 + pinsrb xmm5, byte ptr [r14 + r13 + 14], 11 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + r13 + 14], 12 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 14], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm5, byte ptr [r14 + rax + 14], 14 + pinsrb xmm5, byte ptr [r14 + r9 + 14], 15 + mov r9, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r9 + 15], 1 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + r8 + 15], 2 + pinsrb xmm8, byte ptr [r14 + rdx + 15], 3 + pinsrb xmm8, byte ptr [r14 + r12 + 15], 4 + pinsrb xmm8, byte ptr [r14 + rcx + 15], 5 + pinsrb xmm8, byte ptr [r14 + rsi + 15], 6 + pinsrb xmm8, byte ptr [r14 + r11 + 15], 7 + pinsrb xmm8, byte ptr [r14 + r15 + 15], 8 + pinsrb xmm8, byte ptr [r14 + r10 + 15], 9 + pinsrb xmm8, byte ptr [r14 + rdi + 15], 10 + pinsrb xmm8, byte ptr [r14 + rbx + 15], 11 + pinsrb xmm8, byte ptr [r14 + r13 + 15], 12 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rax + 15], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rax + 15], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm8, byte ptr [r14 + rax + 15], 15 + pinsrb xmm7, byte ptr [r14 + r9 + 17], 1 + pinsrb xmm7, byte ptr [r14 + r8 + 17], 2 + pinsrb xmm7, byte ptr [r14 + rdx + 17], 3 + pinsrb xmm7, byte ptr [r14 + r12 + 17], 4 + pinsrb xmm7, byte ptr [r14 + rcx + 17], 5 + pinsrb xmm7, byte ptr [r14 + rsi + 17], 6 + pinsrb xmm7, byte ptr [r14 + r11 + 17], 7 + pinsrb xmm7, byte ptr [r14 + r15 + 17], 8 + pinsrb xmm7, byte ptr [r14 + r10 + 17], 9 + pinsrb xmm7, byte ptr [r14 + rdi + 17], 10 + pinsrb xmm7, byte ptr [r14 + rbx + 17], 11 + pinsrb xmm7, byte ptr [r14 + r13 + 17], 12 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rax + 17], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rax + 17], 14 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [r14 + rax + 17], 15 + pinsrb xmm1, byte ptr [r14 + r9 + 18], 1 + pinsrb xmm1, byte ptr [r14 + r8 + 18], 2 + pinsrb xmm1, byte ptr [r14 + rdx + 18], 3 + pinsrb xmm1, byte ptr [r14 + r12 + 18], 4 + pinsrb xmm1, byte ptr [r14 + rcx + 18], 5 + mov r9, rcx + pinsrb xmm1, byte ptr [r14 + rsi + 18], 6 + pinsrb xmm1, byte ptr [r14 + r11 + 18], 7 + pinsrb xmm1, byte ptr [r14 + r15 + 18], 8 + pinsrb xmm1, byte ptr [r14 + r10 + 18], 9 + mov r11, r10 + pinsrb xmm1, byte ptr [r14 + rdi + 18], 10 + mov r10, rdi + pinsrb xmm1, byte ptr [r14 + rbx + 18], 11 + mov rcx, rbx + pinsrb xmm1, byte ptr [r14 + r13 + 18], 12 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + r8 + 18], 13 + pandn xmm2, xmmword ptr [rip + .LCPI7_13] + pandn xmm0, xmmword ptr [rip + .LCPI7_14] + por xmm0, xmm2 + movdqa xmm2, xmm5 + pminub xmm2, xmm13 + pcmpeqb xmm2, xmm5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + movzx edx, byte ptr [r14 + rax + 26] + movd xmm5, edx + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rdx + 18], 14 + pandn xmm2, xmmword ptr [rip + .LCPI7_15] + por xmm2, xmm0 + movdqa xmm6, xmm8 + pminub xmm6, xmm13 + pcmpeqb xmm6, xmm8 + movzx edx, byte ptr [r14 + rax + 27] + movd xmm0, edx + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rbx + 18], 15 + pxor xmm6, xmmword ptr [rip + .LCPI7_16] + psllw xmm6, 7 + pand xmm6, xmmword ptr [rip + .LCPI7_6] + por xmm6, xmm2 + movzx edx, byte ptr [r14 + rax + 28] + movd xmm8, edx + por xmm6, xmm10 + movdqa xmmword ptr [rsp + 208], xmm6 # 16-byte Spill + movdqa xmm2, xmm7 + pminub xmm2, xmm13 + pcmpeqb xmm2, xmm7 + movdqa xmm14, xmm2 + pandn xmm14, xmmword ptr [rip + .LCPI7_10] + paddb xmm14, xmm2 + movdqa xmm10, xmm1 + pminub xmm10, xmm13 + pcmpeqb xmm10, xmm1 + movzx edx, byte ptr [r14 + rax + 29] + movd xmm6, edx + movzx edx, byte ptr [r14 + rax + 30] + movzx esi, byte ptr [r14 + rax + 31] + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rax + 19], 1 + pinsrb xmm9, byte ptr [r14 + rax + 20], 1 + pinsrb xmm4, byte ptr [r14 + rax + 21], 1 + pinsrb xmm15, byte ptr [r14 + rax + 22], 1 + pinsrb xmm11, byte ptr [r14 + rax + 23], 1 + pinsrb xmm12, byte ptr [r14 + rax + 25], 1 + pinsrb xmm5, byte ptr [r14 + rax + 26], 1 + pinsrb xmm0, byte ptr [r14 + rax + 27], 1 + pinsrb xmm8, byte ptr [r14 + rax + 28], 1 + pinsrb xmm6, byte ptr [r14 + rax + 29], 1 + movd xmm1, edx + pinsrb xmm1, byte ptr [r14 + rax + 30], 1 + movd xmm7, esi + pinsrb xmm7, byte ptr [r14 + rax + 31], 1 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdx + 19], 2 + pinsrb xmm9, byte ptr [r14 + rdx + 20], 2 + pinsrb xmm4, byte ptr [r14 + rdx + 21], 2 + pinsrb xmm15, byte ptr [r14 + rdx + 22], 2 + pinsrb xmm11, byte ptr [r14 + rdx + 23], 2 + pinsrb xmm12, byte ptr [r14 + rdx + 25], 2 + pinsrb xmm5, byte ptr [r14 + rdx + 26], 2 + pinsrb xmm0, byte ptr [r14 + rdx + 27], 2 + pinsrb xmm8, byte ptr [r14 + rdx + 28], 2 + pinsrb xmm6, byte ptr [r14 + rdx + 29], 2 + pinsrb xmm1, byte ptr [r14 + rdx + 30], 2 + pinsrb xmm7, byte ptr [r14 + rdx + 31], 2 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdx + 19], 3 + pinsrb xmm3, byte ptr [r14 + r12 + 19], 4 + mov rsi, r9 + pinsrb xmm3, byte ptr [r14 + r9 + 19], 5 + mov rdi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rdi + 19], 6 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + r9 + 19], 7 + pinsrb xmm3, byte ptr [r14 + r15 + 19], 8 + pinsrb xmm3, byte ptr [r14 + r11 + 19], 9 + pinsrb xmm3, byte ptr [r14 + r10 + 19], 10 + mov r13, rcx + pinsrb xmm3, byte ptr [r14 + rcx + 19], 11 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rcx + 19], 12 + pinsrb xmm3, byte ptr [r14 + r8 + 19], 13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm3, byte ptr [r14 + rax + 19], 14 + pinsrb xmm3, byte ptr [r14 + rbx + 19], 15 + pinsrb xmm9, byte ptr [r14 + rdx + 20], 3 + pinsrb xmm9, byte ptr [r14 + r12 + 20], 4 + pinsrb xmm9, byte ptr [r14 + rsi + 20], 5 + pinsrb xmm9, byte ptr [r14 + rdi + 20], 6 + pinsrb xmm9, byte ptr [r14 + r9 + 20], 7 + pinsrb xmm9, byte ptr [r14 + r15 + 20], 8 + pinsrb xmm9, byte ptr [r14 + r11 + 20], 9 + pinsrb xmm9, byte ptr [r14 + r10 + 20], 10 + pinsrb xmm9, byte ptr [r14 + r13 + 20], 11 + pinsrb xmm9, byte ptr [r14 + rcx + 20], 12 + pinsrb xmm9, byte ptr [r14 + r8 + 20], 13 + pinsrb xmm9, byte ptr [r14 + rax + 20], 14 + pinsrb xmm9, byte ptr [r14 + rbx + 20], 15 + pinsrb xmm4, byte ptr [r14 + rdx + 21], 3 + pinsrb xmm4, byte ptr [r14 + r12 + 21], 4 + pinsrb xmm4, byte ptr [r14 + rsi + 21], 5 + pinsrb xmm4, byte ptr [r14 + rdi + 21], 6 + pinsrb xmm4, byte ptr [r14 + r9 + 21], 7 + pinsrb xmm4, byte ptr [r14 + r15 + 21], 8 + pinsrb xmm4, byte ptr [r14 + r11 + 21], 9 + pinsrb xmm4, byte ptr [r14 + r10 + 21], 10 + pinsrb xmm4, byte ptr [r14 + r13 + 21], 11 + pinsrb xmm4, byte ptr [r14 + rcx + 21], 12 + pinsrb xmm4, byte ptr [r14 + r8 + 21], 13 + pinsrb xmm4, byte ptr [r14 + rax + 21], 14 + pinsrb xmm4, byte ptr [r14 + rbx + 21], 15 + pinsrb xmm15, byte ptr [r14 + rdx + 22], 3 + pinsrb xmm15, byte ptr [r14 + r12 + 22], 4 + pinsrb xmm15, byte ptr [r14 + rsi + 22], 5 + pinsrb xmm15, byte ptr [r14 + rdi + 22], 6 + pinsrb xmm15, byte ptr [r14 + r9 + 22], 7 + pinsrb xmm15, byte ptr [r14 + r15 + 22], 8 + pinsrb xmm15, byte ptr [r14 + r11 + 22], 9 + pinsrb xmm15, byte ptr [r14 + r10 + 22], 10 + movdqa xmm2, xmmword ptr [rsp + 256] # 16-byte Reload + pandn xmm2, xmmword ptr [rip + .LCPI7_10] + pinsrb xmm15, byte ptr [r14 + r13 + 22], 11 + mov r10, r13 + pandn xmm10, xmmword ptr [rip + .LCPI7_11] + por xmm10, xmm2 + pinsrb xmm15, byte ptr [r14 + rcx + 22], 12 + movdqa xmm2, xmm3 + pminub xmm2, xmm13 + pcmpeqb xmm2, xmm3 + pinsrb xmm15, byte ptr [r14 + r8 + 22], 13 + pandn xmm2, xmmword ptr [rip + .LCPI7_12] + por xmm2, xmm10 + pinsrb xmm15, byte ptr [r14 + rax + 22], 14 + mov r15, rax + psubb xmm14, xmmword ptr [rip + .LCPI7_16] + por xmm2, xmm14 + movdqa xmm10, xmm9 + pminub xmm10, xmm13 + pcmpeqb xmm10, xmm9 + movdqa xmm3, xmm4 + movdqa xmm9, xmm13 + pminub xmm3, xmm13 + pcmpeqb xmm3, xmm4 + mov r13, rbx + pinsrb xmm15, byte ptr [r14 + rbx + 22], 15 + movdqa xmm13, xmmword ptr [rip + .LCPI7_13] # xmm13 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm10, xmm13 + movdqa xmm4, xmmword ptr [rip + .LCPI7_14] # xmm4 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm3, xmm4 + por xmm3, xmm10 + movdqa xmm4, xmm15 + pminub xmm4, xmm9 + movdqa xmm13, xmm9 + pcmpeqb xmm4, xmm15 + pinsrb xmm11, byte ptr [r14 + rdx + 23], 3 + pinsrb xmm11, byte ptr [r14 + r12 + 23], 4 + pinsrb xmm11, byte ptr [r14 + rsi + 23], 5 + pinsrb xmm11, byte ptr [r14 + rdi + 23], 6 + pinsrb xmm11, byte ptr [r14 + r9 + 23], 7 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rbx + 23], 8 + pinsrb xmm11, byte ptr [r14 + r11 + 23], 9 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm11, byte ptr [r14 + rax + 23], 10 + pinsrb xmm11, byte ptr [r14 + r10 + 23], 11 + pinsrb xmm11, byte ptr [r14 + rcx + 23], 12 + pinsrb xmm11, byte ptr [r14 + r8 + 23], 13 + pinsrb xmm11, byte ptr [r14 + r15 + 23], 14 + pinsrb xmm11, byte ptr [r14 + r13 + 23], 15 + movdqa xmm15, xmmword ptr [rip + .LCPI7_15] # xmm15 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm4, xmm15 + por xmm4, xmm3 + movdqa xmm3, xmm11 + pminub xmm3, xmm9 + pcmpeqb xmm3, xmm11 + pxor xmm3, xmmword ptr [rip + .LCPI7_16] + psllw xmm3, 7 + movdqa xmm11, xmmword ptr [rip + .LCPI7_6] # xmm11 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm3, xmm11 por xmm3, xmm4 - movaps xmm0, xmm13 - cmpltps xmm0, xmm5 - packssdw xmm0, xmm0 - packsswb xmm0, xmm0 - psllw xmm0, 7 - pand xmm0, xmm10 - por xmm0, xmm3 - por xmm0, xmm1 - punpckldq xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1] - punpcklbw xmm8, xmm2 # xmm8 = xmm8[0],xmm2[0],xmm8[1],xmm2[1],xmm8[2],xmm2[2],xmm8[3],xmm2[3],xmm8[4],xmm2[4],xmm8[5],xmm2[5],xmm8[6],xmm2[6],xmm8[7],xmm2[7] - pshufb xmm8, xmmword ptr [rip + .LCPI7_7] # xmm8 = xmm8[0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] - movdqu xmmword ptr [rdi + 4*rcx], xmm8 - add rcx, 4 - add rsi, 512 - cmp rax, rcx - jne .LBB7_183 -# %bb.184: - cmp r10, rax - jne .LBB7_185 - jmp .LBB7_188 + pinsrb xmm12, byte ptr [r14 + rdx + 25], 3 + pinsrb xmm12, byte ptr [r14 + r12 + 25], 4 + pinsrb xmm12, byte ptr [r14 + rsi + 25], 5 + pinsrb xmm12, byte ptr [r14 + rdi + 25], 6 + pinsrb xmm12, byte ptr [r14 + r9 + 25], 7 + pinsrb xmm12, byte ptr [r14 + rbx + 25], 8 + pinsrb xmm12, byte ptr [r14 + r11 + 25], 9 + pinsrb xmm12, byte ptr [r14 + rax + 25], 10 + pinsrb xmm12, byte ptr [r14 + r10 + 25], 11 + pinsrb xmm12, byte ptr [r14 + rcx + 25], 12 + pinsrb xmm12, byte ptr [r14 + r8 + 25], 13 + pinsrb xmm12, byte ptr [r14 + r15 + 25], 14 + pinsrb xmm12, byte ptr [r14 + r13 + 25], 15 + pinsrb xmm5, byte ptr [r14 + rdx + 26], 3 + pinsrb xmm5, byte ptr [r14 + r12 + 26], 4 + pinsrb xmm5, byte ptr [r14 + rsi + 26], 5 + pinsrb xmm5, byte ptr [r14 + rdi + 26], 6 + pinsrb xmm5, byte ptr [r14 + r9 + 26], 7 + pinsrb xmm5, byte ptr [r14 + rbx + 26], 8 + pinsrb xmm5, byte ptr [r14 + r11 + 26], 9 + pinsrb xmm5, byte ptr [r14 + rax + 26], 10 + pinsrb xmm5, byte ptr [r14 + r10 + 26], 11 + pinsrb xmm5, byte ptr [r14 + rcx + 26], 12 + pinsrb xmm5, byte ptr [r14 + r8 + 26], 13 + pinsrb xmm5, byte ptr [r14 + r15 + 26], 14 + pinsrb xmm5, byte ptr [r14 + r13 + 26], 15 + por xmm3, xmm2 + movdqa xmm2, xmm12 + pminub xmm2, xmm9 + pcmpeqb xmm2, xmm12 + movdqa xmm9, xmm2 + movdqa xmm10, xmmword ptr [rip + .LCPI7_10] # xmm10 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pandn xmm9, xmm10 + paddb xmm9, xmm2 + movdqa xmm4, xmm5 + pminub xmm4, xmm13 + pcmpeqb xmm4, xmm5 + movdqa xmm2, xmmword ptr [rsp + 224] # 16-byte Reload + pandn xmm2, xmm10 + pinsrb xmm0, byte ptr [r14 + rdx + 27], 3 + pinsrb xmm0, byte ptr [r14 + r12 + 27], 4 + pinsrb xmm0, byte ptr [r14 + rsi + 27], 5 + pinsrb xmm0, byte ptr [r14 + rdi + 27], 6 + pinsrb xmm0, byte ptr [r14 + r9 + 27], 7 + pinsrb xmm0, byte ptr [r14 + rbx + 27], 8 + pinsrb xmm0, byte ptr [r14 + r11 + 27], 9 + pinsrb xmm0, byte ptr [r14 + rax + 27], 10 + pinsrb xmm0, byte ptr [r14 + r10 + 27], 11 + pinsrb xmm0, byte ptr [r14 + rcx + 27], 12 + pinsrb xmm0, byte ptr [r14 + r8 + 27], 13 + pinsrb xmm0, byte ptr [r14 + r15 + 27], 14 + pinsrb xmm0, byte ptr [r14 + r13 + 27], 15 + pandn xmm4, xmmword ptr [rip + .LCPI7_11] + por xmm4, xmm2 + movdqa xmm2, xmm0 + pminub xmm2, xmm13 + pcmpeqb xmm2, xmm0 + pandn xmm2, xmmword ptr [rip + .LCPI7_12] + por xmm2, xmm4 + pinsrb xmm8, byte ptr [r14 + rdx + 28], 3 + pinsrb xmm8, byte ptr [r14 + r12 + 28], 4 + pinsrb xmm8, byte ptr [r14 + rsi + 28], 5 + pinsrb xmm8, byte ptr [r14 + rdi + 28], 6 + pinsrb xmm8, byte ptr [r14 + r9 + 28], 7 + pinsrb xmm8, byte ptr [r14 + rbx + 28], 8 + pinsrb xmm8, byte ptr [r14 + r11 + 28], 9 + pinsrb xmm8, byte ptr [r14 + rax + 28], 10 + pinsrb xmm8, byte ptr [r14 + r10 + 28], 11 + pinsrb xmm8, byte ptr [r14 + rcx + 28], 12 + pinsrb xmm8, byte ptr [r14 + r8 + 28], 13 + pinsrb xmm8, byte ptr [r14 + r15 + 28], 14 + pinsrb xmm8, byte ptr [r14 + r13 + 28], 15 + pinsrb xmm6, byte ptr [r14 + rdx + 29], 3 + pinsrb xmm6, byte ptr [r14 + r12 + 29], 4 + pinsrb xmm6, byte ptr [r14 + rsi + 29], 5 + pinsrb xmm6, byte ptr [r14 + rdi + 29], 6 + pinsrb xmm6, byte ptr [r14 + r9 + 29], 7 + pinsrb xmm6, byte ptr [r14 + rbx + 29], 8 + pinsrb xmm6, byte ptr [r14 + r11 + 29], 9 + pinsrb xmm6, byte ptr [r14 + rax + 29], 10 + pinsrb xmm6, byte ptr [r14 + r10 + 29], 11 + pinsrb xmm6, byte ptr [r14 + rcx + 29], 12 + pinsrb xmm6, byte ptr [r14 + r8 + 29], 13 + pinsrb xmm6, byte ptr [r14 + r15 + 29], 14 + pinsrb xmm6, byte ptr [r14 + r13 + 29], 15 + pcmpeqd xmm10, xmm10 + psubb xmm9, xmm10 + por xmm2, xmm9 + movdqa xmm0, xmm8 + pminub xmm0, xmm13 + pcmpeqb xmm0, xmm8 + movdqa xmm4, xmm6 + pminub xmm4, xmm13 + pcmpeqb xmm4, xmm6 + pinsrb xmm1, byte ptr [r14 + rdx + 30], 3 + pinsrb xmm7, byte ptr [r14 + rdx + 31], 3 + pinsrb xmm1, byte ptr [r14 + r12 + 30], 4 + pinsrb xmm7, byte ptr [r14 + r12 + 31], 4 + pinsrb xmm1, byte ptr [r14 + rsi + 30], 5 + pinsrb xmm7, byte ptr [r14 + rsi + 31], 5 + pinsrb xmm1, byte ptr [r14 + rdi + 30], 6 + pinsrb xmm7, byte ptr [r14 + rdi + 31], 6 + pinsrb xmm1, byte ptr [r14 + r9 + 30], 7 + pinsrb xmm7, byte ptr [r14 + r9 + 31], 7 + pinsrb xmm1, byte ptr [r14 + rbx + 30], 8 + pinsrb xmm7, byte ptr [r14 + rbx + 31], 8 + pinsrb xmm1, byte ptr [r14 + r11 + 30], 9 + pinsrb xmm7, byte ptr [r14 + r11 + 31], 9 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm1, byte ptr [r14 + rax + 30], 10 + pinsrb xmm7, byte ptr [r14 + rax + 31], 10 + pinsrb xmm1, byte ptr [r14 + r10 + 30], 11 + pinsrb xmm7, byte ptr [r14 + r10 + 31], 11 + pinsrb xmm1, byte ptr [r14 + rcx + 30], 12 + pinsrb xmm7, byte ptr [r14 + rcx + 31], 12 + pinsrb xmm1, byte ptr [r14 + r8 + 30], 13 + pinsrb xmm7, byte ptr [r14 + r8 + 31], 13 + pinsrb xmm1, byte ptr [r14 + r15 + 30], 14 + pinsrb xmm7, byte ptr [r14 + r15 + 31], 14 + pinsrb xmm1, byte ptr [r14 + r13 + 30], 15 + pinsrb xmm7, byte ptr [r14 + r13 + 31], 15 + pandn xmm0, xmmword ptr [rip + .LCPI7_13] + pandn xmm4, xmmword ptr [rip + .LCPI7_14] + por xmm4, xmm0 + movdqa xmm0, xmm1 + pminub xmm0, xmm13 + pcmpeqb xmm0, xmm1 + pandn xmm0, xmm15 + por xmm0, xmm4 + movdqa xmm1, xmm7 + pminub xmm1, xmm13 + pcmpeqb xmm1, xmm7 + pxor xmm1, xmm10 + psllw xmm1, 7 + pand xmm1, xmm11 + por xmm1, xmm0 + por xmm1, xmm2 + movdqa xmm0, xmm3 + punpcklbw xmm0, xmm1 # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7] + movdqa xmm5, xmmword ptr [rsp + 176] # 16-byte Reload + movdqa xmm2, xmm5 + movdqa xmm6, xmmword ptr [rsp + 208] # 16-byte Reload + punpcklbw xmm2, xmm6 # xmm2 = xmm2[0],xmm6[0],xmm2[1],xmm6[1],xmm2[2],xmm6[2],xmm2[3],xmm6[3],xmm2[4],xmm6[4],xmm2[5],xmm6[5],xmm2[6],xmm6[6],xmm2[7],xmm6[7] + movdqa xmm4, xmm2 + punpcklwd xmm4, xmm0 # xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3] + punpckhwd xmm2, xmm0 # xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7] + punpckhbw xmm3, xmm1 # xmm3 = xmm3[8],xmm1[8],xmm3[9],xmm1[9],xmm3[10],xmm1[10],xmm3[11],xmm1[11],xmm3[12],xmm1[12],xmm3[13],xmm1[13],xmm3[14],xmm1[14],xmm3[15],xmm1[15] + punpckhbw xmm5, xmm6 # xmm5 = xmm5[8],xmm6[8],xmm5[9],xmm6[9],xmm5[10],xmm6[10],xmm5[11],xmm6[11],xmm5[12],xmm6[12],xmm5[13],xmm6[13],xmm5[14],xmm6[14],xmm5[15],xmm6[15] + movdqa xmm0, xmm5 + punpcklwd xmm0, xmm3 # xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3] + punpckhwd xmm5, xmm3 # xmm5 = xmm5[4],xmm3[4],xmm5[5],xmm3[5],xmm5[6],xmm3[6],xmm5[7],xmm3[7] + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + movdqu xmmword ptr [r12 + 4*rcx + 48], xmm5 + movdqu xmmword ptr [r12 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r12 + 4*rcx + 16], xmm2 + movdqu xmmword ptr [r12 + 4*rcx], xmm4 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + jne .LBB7_72 +# %bb.73: + mov rcx, qword ptr [rsp + 312] # 8-byte Reload + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 136] # 8-byte Reload + mov r12, qword ptr [rsp + 96] # 8-byte Reload + mov r14, qword ptr [rsp + 336] # 8-byte Reload + jne .LBB7_74 + jmp .LBB7_77 .Lfunc_end7: .size comparison_greater_arr_scalar_sse4, .Lfunc_end7-comparison_greater_arr_scalar_sse4 # -- End function @@ -40880,70 +42053,83 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 and rsp, -16 sub rsp, 336 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 + mov r12, r8 mov r14, rcx cmp edi, 6 - jg .LBB8_16 + jg .LBB8_18 # %bb.1: cmp edi, 3 - jle .LBB8_31 + jle .LBB8_35 # %bb.2: cmp edi, 4 - je .LBB8_81 + je .LBB8_57 # %bb.3: cmp edi, 5 - je .LBB8_92 + je .LBB8_70 # %bb.4: cmp edi, 6 - jne .LBB8_182 + jne .LBB8_215 # %bb.5: mov r13d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_9 + je .LBB8_11 # %bb.6: - movsxd rax, r9d + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_9 +# %bb.7: + movsxd rsi, r9d + mov rax, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_7: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rdx], r13d - lea rdx, [rdx + 4] - sbb esi, esi - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB8_8: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp dword ptr [rcx], r13d + sbb r11d, r11d + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_7 -# %bb.8: - add r14, 1 + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add rsi, 1 + mov rcx, rdx + add rax, -1 + jne .LBB8_8 .LBB8_9: - sar r11, 5 - cmp r10, 32 - jl .LBB8_13 + sub r12, r8 + je .LBB8_215 # %bb.10: - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill - mov qword ptr [rsp + 208], r11 # 8-byte Spill + add r14, 1 +.LBB8_11: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB8_15 +# %bb.12: + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_11: # =>This Inner Loop Header: Depth=1 +.LBB8_13: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 128], r14 # 8-byte Spill cmp r13d, dword ptr [rdx] seta byte ptr [rsp + 192] # 1-byte Folded Spill @@ -40954,7 +42140,7 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 cmp r13d, dword ptr [rdx + 12] seta byte ptr [rsp + 120] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 16] - seta byte ptr [rsp + 144] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 20] seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 24] @@ -40964,9 +42150,9 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 cmp r13d, dword ptr [rdx + 32] seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 36] - seta sil + seta cl cmp r13d, dword ptr [rdx + 40] - seta r8b + seta sil cmp r13d, dword ptr [rdx + 44] seta r9b cmp r13d, dword ptr [rdx + 48] @@ -40974,37 +42160,37 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 cmp r13d, dword ptr [rdx + 52] seta r12b cmp r13d, dword ptr [rdx + 56] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 176] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 60] - seta cl + seta r8b cmp r13d, dword ptr [rdx + 64] seta byte ptr [rsp + 88] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 68] - seta byte ptr [rsp + 176] # 1-byte Folded Spill + seta byte ptr [rsp + 144] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 72] - seta byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 76] seta byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 76] + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 80] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 84] - seta byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 88] seta byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 88] + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 92] seta r15b cmp r13d, dword ptr [rdx + 96] seta byte ptr [rsp + 24] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 100] - seta byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 104] seta byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 104] + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 108] seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 112] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 116] seta byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 116] + seta byte ptr [rsp + 8] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 120] seta byte ptr [rsp] # 1-byte Folded Spill cmp r13d, dword ptr [rdx + 124] @@ -41016,65 +42202,64 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 112] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 112] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b mov r14, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 88] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, sil + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, sil mov byte ptr [r14], r11b - movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 24] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -41082,11 +42267,11 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 5 or al, cl movzx ecx, byte ptr [rsp] # 1-byte Folded Reload @@ -41098,85 +42283,100 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 mov byte ptr [r14 + 3], bl add rdx, 128 add r14, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_11 -# %bb.12: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r11, qword ptr [rsp + 240] # 8-byte Reload -.LBB8_13: - shl r11, 5 - cmp r11, r10 - jge .LBB8_182 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB8_13 # %bb.14: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB8_162 -# %bb.15: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB8_15: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB8_215 +# %bb.16: + or rax, 1 + cmp r12, rax + jne .LBB8_185 +# %bb.17: xor r11d, r11d - jmp .LBB8_164 -.LBB8_16: + jmp .LBB8_187 +.LBB8_18: cmp edi, 8 - jle .LBB8_45 -# %bb.17: + jle .LBB8_42 +# %bb.19: cmp edi, 9 - je .LBB8_104 -# %bb.18: + je .LBB8_84 +# %bb.20: cmp edi, 11 - je .LBB8_115 -# %bb.19: + je .LBB8_97 +# %bb.21: cmp edi, 12 - jne .LBB8_182 -# %bb.20: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jne .LBB8_215 +# %bb.22: + mov r15, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero sub r9d, eax - je .LBB8_24 -# %bb.21: - movsxd rax, r9d + je .LBB8_28 +# %bb.23: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_26 +# %bb.24: + movsxd rsi, r9d + movq xmm0, r15 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_22: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rdx] +.LBB8_25: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rcx] seta bl - add rdx, 8 + lea rdx, [rcx + 8] neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r14 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_22 -# %bb.23: + mov byte ptr [r14 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_25 +.LBB8_26: + sub r12, r8 + je .LBB8_215 +# %bb.27: add r14, 1 -.LBB8_24: - sar r11, 5 - cmp r10, 32 - jl .LBB8_28 -# %bb.25: - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r11 # 8-byte Spill +.LBB8_28: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB8_32 +# %bb.29: + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 224], r15 # 8-byte Spill + movq xmm0, r15 + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 192], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_26: # =>This Inner Loop Header: Depth=1 +.LBB8_30: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 128], r14 # 8-byte Spill ucomisd xmm0, qword ptr [rdx] seta byte ptr [rsp + 120] # 1-byte Folded Spill @@ -41187,7 +42387,7 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 ucomisd xmm0, qword ptr [rdx + 24] seta r13b ucomisd xmm0, qword ptr [rdx + 32] - seta byte ptr [rsp + 144] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 40] seta byte ptr [rsp + 72] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 48] @@ -41195,11 +42395,11 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 ucomisd xmm0, qword ptr [rdx + 56] seta r11b ucomisd xmm0, qword ptr [rdx + 64] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 176] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 72] - seta sil + seta cl ucomisd xmm0, qword ptr [rdx + 80] - seta dil + seta sil ucomisd xmm0, qword ptr [rdx + 88] seta r9b ucomisd xmm0, qword ptr [rdx + 96] @@ -41207,37 +42407,37 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 ucomisd xmm0, qword ptr [rdx + 104] seta r12b ucomisd xmm0, qword ptr [rdx + 112] - seta byte ptr [rsp + 176] # 1-byte Folded Spill + seta byte ptr [rsp + 144] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 120] - seta cl + seta dil ucomisd xmm0, qword ptr [rdx + 128] seta byte ptr [rsp + 88] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 136] seta byte ptr [rsp + 112] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 144] - seta byte ptr [rsp + 96] # 1-byte Folded Spill - ucomisd xmm0, qword ptr [rdx + 152] seta byte ptr [rsp + 160] # 1-byte Folded Spill + ucomisd xmm0, qword ptr [rdx + 152] + seta byte ptr [rsp + 96] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 160] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 104] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 168] - seta byte ptr [rsp + 56] # 1-byte Folded Spill - ucomisd xmm0, qword ptr [rdx + 176] seta byte ptr [rsp + 64] # 1-byte Folded Spill + ucomisd xmm0, qword ptr [rdx + 176] + seta byte ptr [rsp + 56] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 184] seta r15b ucomisd xmm0, qword ptr [rdx + 192] seta byte ptr [rsp + 24] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 200] - seta byte ptr [rsp + 40] # 1-byte Folded Spill - ucomisd xmm0, qword ptr [rdx + 208] seta byte ptr [rsp + 48] # 1-byte Folded Spill + ucomisd xmm0, qword ptr [rdx + 208] + seta byte ptr [rsp + 40] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 216] seta byte ptr [rsp + 32] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 224] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - ucomisd xmm0, qword ptr [rdx + 232] seta byte ptr [rsp + 16] # 1-byte Folded Spill + ucomisd xmm0, qword ptr [rdx + 232] + seta byte ptr [rsp + 8] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 240] seta byte ptr [rsp] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 248] @@ -41249,554 +42449,62 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 or r11b, al shl r14b, 2 or r14b, r8b - add sil, sil - add sil, byte ptr [rsp + 104] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 176] # 1-byte Folded Reload shl r13b, 3 or r13b, r14b - shl dil, 2 - or dil, sil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 4 - or al, r13b - mov r8d, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 4 + or cl, r13b + mov r8d, ecx mov r14, qword ptr [rsp + 128] # 8-byte Reload shl r9b, 3 - or r9b, dil - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 5 - or al, r8b - shl r10b, 4 - or r10b, r9b - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload - shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 88] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov byte ptr [r14], r11b - movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl sil, 6 - shl r15b, 7 - or r15b, sil - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp] # 1-byte Folded Reload - shl cl, 6 - shl bl, 7 - or bl, cl - or bl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], bl - add rdx, 256 - add r14, 4 - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB8_26 -# %bb.27: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r11, qword ptr [rsp + 208] # 8-byte Reload -.LBB8_28: - shl r11, 5 - cmp r11, r10 - jge .LBB8_182 -# %bb.29: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB8_166 -# %bb.30: - xor edi, edi - jmp .LBB8_168 -.LBB8_31: - cmp edi, 2 - je .LBB8_58 -# %bb.32: - cmp edi, 3 - jne .LBB8_182 -# %bb.33: - mov r11b, byte ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB8_37 -# %bb.34: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB8_35: # =>This Inner Loop Header: Depth=1 - cmp r11b, byte ptr [rdx] - lea rdx, [rdx + 1] - setg bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r14 + rsi] - xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_35 -# %bb.36: - add r14, 1 -.LBB8_37: - sar r15, 5 - cmp r10, 32 - jl .LBB8_127 -# %bb.38: - cmp r15, 16 - mov byte ptr [rsp], r11b # 1-byte Spill - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 256], r15 # 8-byte Spill - jb .LBB8_41 -# %bb.39: - mov rax, r15 - shl rax, 5 - add rax, rdx - cmp r14, rax - jae .LBB8_191 -# %bb.40: - lea rax, [r14 + 4*r15] - cmp rdx, rax - jae .LBB8_191 -.LBB8_41: - xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov rsi, rdx - mov qword ptr [rsp + 88], r14 # 8-byte Spill -.LBB8_42: - mov r14, r15 - sub r14, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 208], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_43: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp r11b, byte ptr [rsi] - setg byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r11b, byte ptr [rsi + 1] - setg dil - cmp r11b, byte ptr [rsi + 2] - setg r11b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 3] - setg r15b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 4] - setg byte ptr [rsp + 120] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 5] - setg byte ptr [rsp + 64] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 6] - setg bl - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 7] - setg r13b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 8] - setg byte ptr [rsp + 112] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 9] - setg sil - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 10] - setg r8b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 11] - setg r9b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 12] - setg r14b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 13] - setg r12b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 14] - setg byte ptr [rsp + 104] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 15] - setg al - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 16] - setg byte ptr [rsp + 176] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 17] - setg byte ptr [rsp + 96] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 18] - setg byte ptr [rsp + 144] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 19] - setg byte ptr [rsp + 160] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 20] - setg byte ptr [rsp + 80] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 21] - setg byte ptr [rsp + 56] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 22] - setg byte ptr [rsp + 72] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 23] - setg r10b - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 24] - setg byte ptr [rsp + 40] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 25] - setg byte ptr [rsp + 48] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 26] - setg byte ptr [rsp + 32] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 27] - setg byte ptr [rsp + 24] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 28] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 29] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 30] - setg byte ptr [rsp + 128] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 31] - setg dl - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl r13b, 7 - or r13b, bl - shl r11b, 2 - or r11b, dil - add sil, sil - add sil, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r15b, 3 - or r15b, r11b - movzx r11d, byte ptr [rsp] # 1-byte Folded Reload - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl bl, 4 - or bl, r15b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r14b, 4 - or r14b, r9b - shl r12b, 5 - or r12b, r14b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload - shl sil, 6 - shl al, 7 - or al, sil - or r13b, bl - or al, r12b - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 176] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl bl, 2 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - mov byte ptr [rdi], r13b - movzx esi, byte ptr [rsp + 72] # 1-byte Folded Reload - shl sil, 6 - shl r10b, 7 - or r10b, sil - mov byte ptr [rdi + 1], al - or r10b, bl - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, al - mov byte ptr [rdi + 2], r10b - mov byte ptr [rdi + 3], dl - lea rsi, [rcx + 32] - add rdi, 4 - mov qword ptr [rsp + 88], rdi # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_43 -# %bb.44: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r15, qword ptr [rsp + 256] # 8-byte Reload - jmp .LBB8_128 -.LBB8_45: - cmp edi, 7 - je .LBB8_70 -# %bb.46: - cmp edi, 8 - jne .LBB8_182 -# %bb.47: - mov r13, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB8_51 -# %bb.48: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB8_49: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rdx], r13 - lea rdx, [rdx + 8] - sbb esi, esi - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_49 -# %bb.50: - add r14, 1 -.LBB8_51: - sar r11, 5 - cmp r10, 32 - jl .LBB8_55 -# %bb.52: - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill - mov qword ptr [rsp + 208], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_53: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r14 # 8-byte Spill - cmp r13, qword ptr [rdx] - seta byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 8] - seta dil - cmp r13, qword ptr [rdx + 16] - seta r14b - cmp r13, qword ptr [rdx + 24] - seta byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 32] - seta byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 40] - seta byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 48] - seta al - cmp r13, qword ptr [rdx + 56] - seta r11b - cmp r13, qword ptr [rdx + 64] - seta byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 72] - seta sil - cmp r13, qword ptr [rdx + 80] - seta r8b - cmp r13, qword ptr [rdx + 88] - seta r9b - cmp r13, qword ptr [rdx + 96] - seta r10b - cmp r13, qword ptr [rdx + 104] - seta r12b - cmp r13, qword ptr [rdx + 112] - seta byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 120] - seta cl - cmp r13, qword ptr [rdx + 128] - seta byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 136] - seta byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 144] - seta byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 152] - seta byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 160] - seta byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 168] - seta byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 176] - seta byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 184] - seta r15b - cmp r13, qword ptr [rdx + 192] - seta byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 200] - seta byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 208] - seta byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 216] - seta byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 224] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 232] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 240] - seta byte ptr [rsp] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 248] - seta bl - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r14b, 2 - or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, r8b shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b - mov r14, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + shl dil, 7 + or dil, sil + or r11b, cl + or dil, r12b + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 88] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, sil + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, al + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, sil mov byte ptr [r14], r11b - movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 1], dil + or r15b, cl + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 24] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -41804,11 +42512,11 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 5 or al, cl movzx ecx, byte ptr [rsp] # 1-byte Folded Reload @@ -41820,396 +42528,210 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 mov byte ptr [r14 + 3], bl add rdx, 256 add r14, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_53 -# %bb.54: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r11, qword ptr [rsp + 240] # 8-byte Reload -.LBB8_55: - shl r11, 5 - cmp r11, r10 - jge .LBB8_182 -# %bb.56: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB8_143 -# %bb.57: - xor r11d, r11d - jmp .LBB8_145 -.LBB8_58: - mov r11b, byte ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + add qword ptr [rsp + 192], -1 # 8-byte Folded Spill + jne .LBB8_30 +# %bb.31: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov r15, qword ptr [rsp + 224] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB8_32: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB8_215 +# %bb.33: + movq xmm0, r15 + or rax, 1 + cmp r12, rax + jne .LBB8_189 +# %bb.34: + xor edi, edi + jmp .LBB8_191 +.LBB8_35: + cmp edi, 2 + je .LBB8_111 +# %bb.36: + cmp edi, 3 + jne .LBB8_215 +# %bb.37: + mov r15b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_62 -# %bb.59: - movsxd rax, r9d + je .LBB8_129 +# %bb.38: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_139 +# %bb.39: + movsxd rsi, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB8_60: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rdx], r11b - lea rdx, [rdx + 1] - sbb esi, esi - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB8_40: # =>This Inner Loop Header: Depth=1 + lea rdi, [rdx + 1] + cmp r15b, byte ptr [rdx] + setg dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + movzx r9d, byte ptr [r14 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r14 + rbx], al + add rsi, 1 + mov rdx, rdi + add r11, -1 + jne .LBB8_40 +# %bb.41: + sub r12, r8 + jne .LBB8_140 + jmp .LBB8_215 +.LBB8_42: + cmp edi, 7 + je .LBB8_116 +# %bb.43: + cmp edi, 8 + jne .LBB8_215 +# %bb.44: + mov r13, qword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB8_50 +# %bb.45: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_48 +# %bb.46: + movsxd rsi, r9d + mov rax, r8 + mov rcx, rdx + .p2align 4, 0x90 +.LBB8_47: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp qword ptr [rcx], r13 + sbb r11d, r11d + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi sar rdi, 3 movzx r9d, byte ptr [r14 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d mov ebx, 1 # kill: def $cl killed $cl killed $ecx shl ebx, cl - and bl, sil + and bl, r11b xor bl, r9b mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB8_60 -# %bb.61: + add rsi, 1 + mov rcx, rdx + add rax, -1 + jne .LBB8_47 +.LBB8_48: + sub r12, r8 + je .LBB8_215 +# %bb.49: add r14, 1 -.LBB8_62: - sar r15, 5 - cmp r10, 32 - jl .LBB8_131 -# %bb.63: - cmp r15, 16 - mov byte ptr [rsp], r11b # 1-byte Spill - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 256], r15 # 8-byte Spill - jb .LBB8_66 -# %bb.64: - mov rax, r15 - shl rax, 5 - add rax, rdx - cmp r14, rax - jae .LBB8_194 -# %bb.65: - lea rax, [r14 + 4*r15] - cmp rdx, rax - jae .LBB8_194 -.LBB8_66: - xor eax, eax - mov qword ptr [rsp + 232], rax # 8-byte Spill - mov rsi, rdx - mov qword ptr [rsp + 48], r14 # 8-byte Spill -.LBB8_67: - mov r14, r15 - sub r14, qword ptr [rsp + 232] # 8-byte Folded Reload - mov qword ptr [rsp + 208], r14 # 8-byte Spill +.LBB8_50: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB8_54 +# %bb.51: + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_68: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp r11b, byte ptr [rsi] +.LBB8_52: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r14 # 8-byte Spill + cmp r13, qword ptr [rdx] seta byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r11b, byte ptr [rsi + 1] + cmp r13, qword ptr [rdx + 8] seta dil - cmp r11b, byte ptr [rsi + 2] - seta r11b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 3] - seta r15b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 4] + cmp r13, qword ptr [rdx + 16] + seta r14b + cmp r13, qword ptr [rdx + 24] seta byte ptr [rsp + 120] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 5] - seta byte ptr [rsp + 56] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 6] - seta bl - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 7] - seta r13b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 8] + cmp r13, qword ptr [rdx + 32] + seta byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 40] + seta byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 48] + seta al + cmp r13, qword ptr [rdx + 56] + seta r11b + cmp r13, qword ptr [rdx + 64] seta byte ptr [rsp + 112] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rsi + 9] + cmp r13, qword ptr [rdx + 72] + seta cl + cmp r13, qword ptr [rdx + 80] seta sil - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 10] - seta r8b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 11] + cmp r13, qword ptr [rdx + 88] seta r9b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 12] - seta r14b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 13] + cmp r13, qword ptr [rdx + 96] + seta r10b + cmp r13, qword ptr [rdx + 104] seta r12b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 14] - seta byte ptr [rsp + 104] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rcx + 15] - seta al - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 16] + cmp r13, qword ptr [rdx + 112] seta byte ptr [rsp + 176] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 17] - seta byte ptr [rsp + 96] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 18] + cmp r13, qword ptr [rdx + 120] + seta r8b + cmp r13, qword ptr [rdx + 128] + seta byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 136] seta byte ptr [rsp + 144] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 19] + cmp r13, qword ptr [rdx + 144] seta byte ptr [rsp + 160] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 20] - seta byte ptr [rsp + 88] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 21] - seta byte ptr [rsp + 72] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 22] - seta byte ptr [rsp + 80] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 23] - seta r10b - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 24] + cmp r13, qword ptr [rdx + 152] + seta byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 160] + seta byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 168] seta byte ptr [rsp + 64] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 25] + cmp r13, qword ptr [rdx + 176] + seta byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 184] + seta r15b + cmp r13, qword ptr [rdx + 192] + seta byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 200] + seta byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 208] seta byte ptr [rsp + 40] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 26] + cmp r13, qword ptr [rdx + 216] seta byte ptr [rsp + 32] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 27] - seta byte ptr [rsp + 24] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 28] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 29] + cmp r13, qword ptr [rdx + 224] seta byte ptr [rsp + 16] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 30] - seta byte ptr [rsp + 128] # 1-byte Folded Spill - movzx edx, byte ptr [rsp] # 1-byte Folded Reload - cmp dl, byte ptr [rcx + 31] - seta dl - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 6 - shl r13b, 7 - or r13b, bl - shl r11b, 2 - or r11b, dil - add sil, sil - add sil, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r15b, 3 - or r15b, r11b - movzx r11d, byte ptr [rsp] # 1-byte Folded Reload - shl r8b, 2 - or r8b, sil - movzx ebx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl bl, 4 - or bl, r15b - mov esi, ebx - shl r9b, 3 - or r9b, r8b - movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - shl r14b, 4 - or r14b, r9b - shl r12b, 5 - or r12b, r14b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload - shl sil, 6 - shl al, 7 - or al, sil - or r13b, bl - or al, r12b - movzx ebx, byte ptr [rsp + 96] # 1-byte Folded Reload - add bl, bl - add bl, byte ptr [rsp + 176] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl bl, 2 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl bl, 4 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 5 - or bl, sil - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - mov byte ptr [rdi], r13b - movzx esi, byte ptr [rsp + 80] # 1-byte Folded Reload - shl sil, 6 - shl r10b, 7 - or r10b, sil - mov byte ptr [rdi + 1], al - or r10b, bl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 64] # 1-byte Folded Reload - mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 2 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 3 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 4 - or al, bl - mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 - shl dl, 7 - or dl, bl - or dl, al - mov byte ptr [rdi + 2], r10b - mov byte ptr [rdi + 3], dl - lea rsi, [rcx + 32] - add rdi, 4 - mov qword ptr [rsp + 48], rdi # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_68 -# %bb.69: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r15, qword ptr [rsp + 256] # 8-byte Reload - jmp .LBB8_132 -.LBB8_70: - mov r13d, dword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB8_74 -# %bb.71: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB8_72: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - lea rdx, [rdx + 4] - setg bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_72 -# %bb.73: - add r14, 1 -.LBB8_74: - sar r11, 5 - cmp r10, 32 - jl .LBB8_78 -# %bb.75: - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill - mov qword ptr [rsp + 208], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_76: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r14 # 8-byte Spill - cmp r13d, dword ptr [rdx] - setg byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 4] - setg dil - cmp r13d, dword ptr [rdx + 8] - setg r14b - cmp r13d, dword ptr [rdx + 12] - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 16] - setg byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 20] - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 24] - setg al - cmp r13d, dword ptr [rdx + 28] - setg r11b - cmp r13d, dword ptr [rdx + 32] - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 36] - setg sil - cmp r13d, dword ptr [rdx + 40] - setg r8b - cmp r13d, dword ptr [rdx + 44] - setg r9b - cmp r13d, dword ptr [rdx + 48] - setg r10b - cmp r13d, dword ptr [rdx + 52] - setg r12b - cmp r13d, dword ptr [rdx + 56] - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 60] - setg cl - cmp r13d, dword ptr [rdx + 64] - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 68] - setg byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 72] - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 76] - setg byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 80] - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 84] - setg byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 88] - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 92] - setg r15b - cmp r13d, dword ptr [rdx + 96] - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 100] - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 104] - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 108] - setg byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 112] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 116] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 120] - setg byte ptr [rsp] # 1-byte Folded Spill - cmp r13d, dword ptr [rdx + 124] - setg bl + cmp r13, qword ptr [rdx + 232] + seta byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 240] + seta byte ptr [rsp] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 248] + seta bl add dil, dil add dil, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 6 @@ -42217,65 +42739,64 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 112] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 112] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b mov r14, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 88] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, sil + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, sil mov byte ptr [r14], r11b - movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 24] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -42283,11 +42804,11 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 5 or al, cl movzx ecx, byte ptr [rsp] # 1-byte Folded Reload @@ -42297,97 +42818,109 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 or bl, al mov byte ptr [r14 + 2], r15b mov byte ptr [r14 + 3], bl - add rdx, 128 + add rdx, 256 add r14, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_76 -# %bb.77: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r11, qword ptr [rsp + 240] # 8-byte Reload -.LBB8_78: - shl r11, 5 - cmp r11, r10 - jge .LBB8_182 -# %bb.79: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB8_147 -# %bb.80: - xor edi, edi - jmp .LBB8_149 -.LBB8_81: + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB8_52 +# %bb.53: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB8_54: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB8_215 +# %bb.55: + or rax, 1 + cmp r12, rax + jne .LBB8_167 +# %bb.56: + xor r11d, r11d + jmp .LBB8_169 +.LBB8_57: movzx r13d, word ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB8_85 -# %bb.82: - movsxd rax, r9d + je .LBB8_63 +# %bb.58: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_61 +# %bb.59: + movsxd rsi, r9d + mov rax, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_83: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rdx], r13w - lea rdx, [rdx + 2] - sbb esi, esi - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB8_60: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp word ptr [rcx], r13w + sbb r11d, r11d + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor r11b, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_83 -# %bb.84: + shl ebx, cl + and bl, r11b + xor bl, r9b + mov byte ptr [r14 + rdi], bl + add rsi, 1 + mov rcx, rdx + add rax, -1 + jne .LBB8_60 +.LBB8_61: + sub r12, r8 + je .LBB8_215 +# %bb.62: add r14, 1 -.LBB8_85: - sar r11, 5 - cmp r10, 32 - jl .LBB8_89 -# %bb.86: - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill - mov qword ptr [rsp + 208], r11 # 8-byte Spill +.LBB8_63: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB8_67 +# %bb.64: + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_87: # =>This Inner Loop Header: Depth=1 +.LBB8_65: # =>This Inner Loop Header: Depth=1 mov qword ptr [rsp + 128], r14 # 8-byte Spill cmp r13w, word ptr [rdx] - seta byte ptr [rsp + 96] # 1-byte Folded Spill + seta al cmp r13w, word ptr [rdx + 2] seta dil cmp r13w, word ptr [rdx + 4] seta r14b cmp r13w, word ptr [rdx + 6] - seta byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 8] seta byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 8] + seta byte ptr [rsp + 112] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 10] - seta byte ptr [rsp + 104] # 1-byte Folded Spill + seta byte ptr [rsp + 144] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 12] - seta al + seta byte ptr [rsp + 192] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 14] seta r11b cmp r13w, word ptr [rdx + 16] - seta byte ptr [rsp + 56] # 1-byte Folded Spill + seta byte ptr [rsp + 160] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 18] - seta sil + seta cl cmp r13w, word ptr [rdx + 20] - seta r8b + seta sil cmp r13w, word ptr [rdx + 22] seta r9b cmp r13w, word ptr [rdx + 24] @@ -42395,560 +42928,107 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 cmp r13w, word ptr [rdx + 26] seta r12b cmp r13w, word ptr [rdx + 28] - seta byte ptr [rsp + 112] # 1-byte Folded Spill + seta byte ptr [rsp + 176] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 30] - seta cl + seta r8b cmp r13w, word ptr [rdx + 32] - seta byte ptr [rsp + 40] # 1-byte Folded Spill + seta byte ptr [rsp + 72] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 34] - seta byte ptr [rsp + 176] # 1-byte Folded Spill + seta byte ptr [rsp + 80] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 36] - seta byte ptr [rsp + 144] # 1-byte Folded Spill + seta byte ptr [rsp + 96] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 38] - seta byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 40] seta byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 40] + seta byte ptr [rsp + 104] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 42] - seta byte ptr [rsp + 80] # 1-byte Folded Spill + seta byte ptr [rsp + 64] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 44] - seta byte ptr [rsp + 72] # 1-byte Folded Spill + seta byte ptr [rsp + 56] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 46] seta r15b cmp r13w, word ptr [rdx + 48] - seta byte ptr [rsp] # 1-byte Folded Spill + seta byte ptr [rsp + 24] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 50] - seta byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 52] seta byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 52] + seta byte ptr [rsp + 40] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 54] seta byte ptr [rsp + 32] # 1-byte Folded Spill cmp r13w, word ptr [rdx + 56] - seta byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 58] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 60] seta byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13w, word ptr [rdx + 62] - seta bl - add dil, dil - add dil, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 6 - shl r11b, 7 - or r11b, al - shl r14b, 2 - or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 56] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - shl al, 5 - or al, dil - shl r10b, 4 - or r10b, r9b - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b - mov r14, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 5 - or al, sil - mov byte ptr [r14], r11b - movzx esi, byte ptr [rsp + 72] # 1-byte Folded Reload - shl sil, 6 - shl r15b, 7 - or r15b, sil - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload - shl cl, 6 - shl bl, 7 - or bl, cl - or bl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], bl - add rdx, 64 - add r14, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_87 -# %bb.88: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r11, qword ptr [rsp + 240] # 8-byte Reload -.LBB8_89: - shl r11, 5 - cmp r11, r10 - jge .LBB8_182 -# %bb.90: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB8_170 -# %bb.91: - xor r11d, r11d - jmp .LBB8_172 -.LBB8_92: - movzx r13d, word ptr [rsi] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB8_96 -# %bb.93: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB8_94: # =>This Inner Loop Header: Depth=1 - cmp r13w, word ptr [rdx] - lea rdx, [rdx + 2] - setg bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r14 + rsi] - xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_94 -# %bb.95: - add r14, 1 -.LBB8_96: - sar r15, 5 - cmp r10, 32 - jl .LBB8_135 -# %bb.97: - cmp r15, 8 - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r15 # 8-byte Spill - jb .LBB8_100 -# %bb.98: - mov rax, r15 - shl rax, 6 - add rax, rdx - cmp r14, rax - jae .LBB8_197 -# %bb.99: - lea rax, [r14 + 4*r15] - cmp rax, rdx - jbe .LBB8_197 -.LBB8_100: - xor eax, eax - mov qword ptr [rsp + 32], rax # 8-byte Spill - mov rsi, rdx - mov r12, r14 -.LBB8_101: - mov qword ptr [rsp], r12 # 8-byte Spill - mov r14, r15 - sub r14, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 208], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_102: # =>This Inner Loop Header: Depth=1 - mov r11, rsi - cmp r13w, word ptr [rsi] - setg byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13w, word ptr [rsi + 2] - setg dil - cmp r13w, word ptr [rsi + 4] - setg r14b - cmp r13w, word ptr [rsi + 6] - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13w, word ptr [rsi + 8] - setg byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r13w, word ptr [rsi + 10] - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13w, word ptr [rsi + 12] - setg al - cmp r13w, word ptr [rsi + 14] - setg r10b - cmp r13w, word ptr [rsi + 16] - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13w, word ptr [rsi + 18] - setg cl - cmp r13w, word ptr [rsi + 20] - setg dl - cmp r13w, word ptr [rsi + 22] - setg sil - cmp r13w, word ptr [r11 + 24] - setg r9b - cmp r13w, word ptr [r11 + 26] - setg r12b - cmp r13w, word ptr [r11 + 28] - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 30] - setg r8b - cmp r13w, word ptr [r11 + 32] - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 34] - setg byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 36] - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 38] - setg byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 40] - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 42] - setg byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 44] - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 46] - setg r15b - cmp r13w, word ptr [r11 + 48] - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 50] - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 52] - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 54] - setg byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 56] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 58] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 60] - setg byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r13w, word ptr [r11 + 62] - setg bl - add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload - shl al, 6 - shl r10b, 7 - or r10b, al - shl r14b, 2 - or r14b, dil - add cl, cl - add cl, byte ptr [rsp + 112] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload - shl al, 3 - or al, r14b - shl dl, 2 - or dl, cl - movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl cl, 4 - or cl, al - mov edi, ecx - shl sil, 3 - or sil, dl - movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl cl, 5 - or cl, dil - shl r9b, 4 - or r9b, sil - shl r12b, 5 - or r12b, r9b - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 6 - shl r8b, 7 - or r8b, dl - or r10b, cl - or r8b, r12b - movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 88] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl cl, 5 - or cl, dl - mov esi, ecx - mov rcx, qword ptr [rsp] # 8-byte Reload - mov byte ptr [rcx], r10b - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 6 - shl r15b, 7 - or r15b, dl - mov byte ptr [rcx + 1], r8b - or r15b, sil - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 6 - shl bl, 7 - or bl, dl - or bl, al - mov byte ptr [rcx + 2], r15b - mov byte ptr [rcx + 3], bl - lea rsi, [r11 + 64] - add rcx, 4 - mov qword ptr [rsp], rcx # 8-byte Spill - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_102 -# %bb.103: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r15, qword ptr [rsp + 240] # 8-byte Reload - mov r12, qword ptr [rsp] # 8-byte Reload - jmp .LBB8_136 -.LBB8_104: - mov r13, qword ptr [rsi] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB8_108 -# %bb.105: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB8_106: # =>This Inner Loop Header: Depth=1 - cmp r13, qword ptr [rdx] - lea rdx, [rdx + 8] - setg bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r14 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_106 -# %bb.107: - add r14, 1 -.LBB8_108: - sar r11, 5 - cmp r10, 32 - jl .LBB8_112 -# %bb.109: - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill - mov qword ptr [rsp + 208], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_110: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], r14 # 8-byte Spill - cmp r13, qword ptr [rdx] - setg byte ptr [rsp + 192] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 8] - setg dil - cmp r13, qword ptr [rdx + 16] - setg r14b - cmp r13, qword ptr [rdx + 24] - setg byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 32] - setg byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 40] - setg byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 48] - setg al - cmp r13, qword ptr [rdx + 56] - setg r11b - cmp r13, qword ptr [rdx + 64] - setg byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 72] - setg sil - cmp r13, qword ptr [rdx + 80] - setg r8b - cmp r13, qword ptr [rdx + 88] - setg r9b - cmp r13, qword ptr [rdx + 96] - setg r10b - cmp r13, qword ptr [rdx + 104] - setg r12b - cmp r13, qword ptr [rdx + 112] - setg byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 120] - setg cl - cmp r13, qword ptr [rdx + 128] - setg byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 136] - setg byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 144] - setg byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 152] - setg byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 160] - setg byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 168] - setg byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 176] - setg byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 184] - setg r15b - cmp r13, qword ptr [rdx + 192] - setg byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 200] - setg byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 208] - setg byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 216] - setg byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 224] - setg byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 232] - setg byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 240] - setg byte ptr [rsp] # 1-byte Folded Spill - cmp r13, qword ptr [rdx + 248] - setg bl + cmp r13w, word ptr [rdx + 58] + seta byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 60] + seta byte ptr [rsp] # 1-byte Folded Spill + cmp r13w, word ptr [rdx + 62] + seta bl add dil, dil - add dil, byte ptr [rsp + 192] # 1-byte Folded Reload + or dil, al + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 6 shl r11b, 7 or r11b, al shl r14b, 2 or r14b, dil - add sil, sil - add sil, byte ptr [rsp + 112] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 160] # 1-byte Folded Reload movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 3 or al, r14b - mov edi, eax - shl r8b, 2 - or r8b, sil - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload - shl al, 5 - or al, dil + or r9b, sil + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 5 + or cl, dil shl r10b, 4 or r10b, r9b shl r12b, 5 or r12b, r10b - movzx esi, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload shl sil, 6 - shl cl, 7 - or cl, sil - or r11b, al - or cl, r12b + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b mov r14, qword ptr [rsp + 128] # 8-byte Reload - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 88] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - shl al, 5 - or al, sil + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 72] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, sil mov byte ptr [r14], r11b - movzx esi, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload shl sil, 6 shl r15b, 7 or r15b, sil - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + mov byte ptr [r14 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 24] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -42956,11 +43036,11 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 5 or al, cl movzx ecx, byte ptr [rsp] # 1-byte Folded Reload @@ -42970,2808 +43050,2123 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 or bl, al mov byte ptr [r14 + 2], r15b mov byte ptr [r14 + 3], bl - add rdx, 256 + add rdx, 64 add r14, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB8_110 -# %bb.111: - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r11, qword ptr [rsp + 240] # 8-byte Reload -.LBB8_112: - shl r11, 5 - cmp r11, r10 - jge .LBB8_182 -# %bb.113: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB8_175 -# %bb.114: - xor edi, edi - jmp .LBB8_177 -.LBB8_115: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB8_65 +# %bb.66: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB8_67: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB8_215 +# %bb.68: + or rax, 1 + cmp r12, rax + jne .LBB8_193 +# %bb.69: + xor r11d, r11d + jmp .LBB8_195 +.LBB8_70: + movzx r13d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero sub r9d, eax - je .LBB8_119 -# %bb.116: - movsxd rax, r9d + je .LBB8_76 +# %bb.71: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_74 +# %bb.72: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_117: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rdx] - seta bl - add rdx, 4 +.LBB8_73: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r13w, word ptr [rcx] + setg bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r14 + rsi] + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + movzx r9d, byte ptr [r14 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r14 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB8_117 -# %bb.118: + mov byte ptr [r14 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_73 +.LBB8_74: + sub r12, r8 + je .LBB8_215 +# %bb.75: add r14, 1 -.LBB8_119: - sar r11, 5 - cmp r10, 32 - jl .LBB8_139 -# %bb.120: - cmp r11, 4 - jb .LBB8_123 -# %bb.121: - mov rax, r11 - shl rax, 7 +.LBB8_76: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB8_130 +# %bb.77: + cmp rcx, 8 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 208], rcx # 8-byte Spill + jb .LBB8_80 +# %bb.78: + mov rax, rcx + shl rax, 6 add rax, rdx cmp r14, rax - jae .LBB8_200 -# %bb.122: - lea rax, [r14 + 4*r11] + jae .LBB8_216 +# %bb.79: + lea rax, [r14 + 4*rcx] cmp rax, rdx - jbe .LBB8_200 -.LBB8_123: - xor r8d, r8d - mov rbx, rdx - mov r15, r14 -.LBB8_124: - mov qword ptr [rsp], r15 # 8-byte Spill - mov qword ptr [rsp + 136], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r11 # 8-byte Spill - sub r11, r8 - mov qword ptr [rsp + 192], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_125: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rbx] - seta byte ptr [rsp + 120] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 4] - seta r8b - ucomiss xmm0, dword ptr [rbx + 8] - seta r14b - ucomiss xmm0, dword ptr [rbx + 12] - seta r13b - ucomiss xmm0, dword ptr [rbx + 16] - seta byte ptr [rsp + 144] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 20] - seta byte ptr [rsp + 72] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 24] - seta al - ucomiss xmm0, dword ptr [rbx + 28] - seta r11b - ucomiss xmm0, dword ptr [rbx + 32] - seta byte ptr [rsp + 104] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 36] - seta dl - ucomiss xmm0, dword ptr [rbx + 40] - seta sil - ucomiss xmm0, dword ptr [rbx + 44] - seta dil - ucomiss xmm0, dword ptr [rbx + 48] - seta r10b - ucomiss xmm0, dword ptr [rbx + 52] - seta r12b - ucomiss xmm0, dword ptr [rbx + 56] - seta byte ptr [rsp + 176] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 60] - seta r9b - ucomiss xmm0, dword ptr [rbx + 64] - seta byte ptr [rsp + 88] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 68] - seta byte ptr [rsp + 112] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 72] - seta byte ptr [rsp + 96] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 76] - seta byte ptr [rsp + 160] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 80] - seta byte ptr [rsp + 80] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 84] - seta byte ptr [rsp + 56] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 88] - seta byte ptr [rsp + 64] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 92] - seta r15b - ucomiss xmm0, dword ptr [rbx + 96] - seta byte ptr [rsp + 24] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 100] - seta byte ptr [rsp + 40] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 104] - seta byte ptr [rsp + 48] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 108] - seta byte ptr [rsp + 32] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 112] - seta byte ptr [rsp + 8] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 116] - seta byte ptr [rsp + 16] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 120] - seta byte ptr [rsp + 128] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 124] - seta cl - add r8b, r8b - add r8b, byte ptr [rsp + 120] # 1-byte Folded Reload + jbe .LBB8_216 +.LBB8_80: + xor eax, eax + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov rsi, rdx + mov qword ptr [rsp], r14 # 8-byte Spill +.LBB8_81: + sub rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB8_82: # =>This Inner Loop Header: Depth=1 + mov r11, rsi + cmp r13w, word ptr [rsi] + setg byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 2] + setg dil + cmp r13w, word ptr [rsi + 4] + setg r14b + cmp r13w, word ptr [rsi + 6] + setg byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 8] + setg byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 10] + setg byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 12] + setg al + cmp r13w, word ptr [rsi + 14] + setg r10b + cmp r13w, word ptr [rsi + 16] + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13w, word ptr [rsi + 18] + setg cl + cmp r13w, word ptr [rsi + 20] + setg dl + cmp r13w, word ptr [rsi + 22] + setg sil + cmp r13w, word ptr [r11 + 24] + setg r9b + cmp r13w, word ptr [r11 + 26] + setg r12b + cmp r13w, word ptr [r11 + 28] + setg byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 30] + setg r8b + cmp r13w, word ptr [r11 + 32] + setg byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 34] + setg byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 36] + setg byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 38] + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 40] + setg byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 42] + setg byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 44] + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 46] + setg r15b + cmp r13w, word ptr [r11 + 48] + setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 50] + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 52] + setg byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 54] + setg byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 56] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 58] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 60] + setg byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r13w, word ptr [r11 + 62] + setg bl + add dil, dil + add dil, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 6 - shl r11b, 7 - or r11b, al + shl r10b, 7 + or r10b, al shl r14b, 2 - or r14b, r8b - add dl, dl - add dl, byte ptr [rsp + 104] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r14b - shl sil, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl dl, 2 + or dl, cl + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl sil, 3 or sil, dl - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - shl dil, 3 - or dil, sil - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, dil - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload - shl sil, 6 - shl r9b, 7 + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r9b, 4 or r9b, sil - or r11b, dl - or r9b, r12b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 88] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov rsi, qword ptr [rsp] # 8-byte Reload - mov byte ptr [rsi], r11b - movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dil, 6 - shl r15b, 7 - or r15b, dil - mov byte ptr [rsi + 1], r9b - or r15b, dl - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, dl - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r12b, 5 + or r12b, r9b + movzx edx, byte ptr [rsp + 176] # 1-byte Folded Reload shl dl, 6 - shl cl, 7 + shl r8b, 7 + or r8b, dl + or r10b, cl + or r8b, r12b + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 or cl, dl - or cl, al - mov byte ptr [rsi + 2], r15b - mov byte ptr [rsi + 3], cl - add rbx, 128 - add rsi, 4 - mov qword ptr [rsp], rsi # 8-byte Spill - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB8_125 -# %bb.126: - mov r15, qword ptr [rsp] # 8-byte Reload - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r11, qword ptr [rsp + 208] # 8-byte Reload - jmp .LBB8_140 -.LBB8_127: - mov qword ptr [rsp + 88], r14 # 8-byte Spill - mov rsi, rdx -.LBB8_128: - shl r15, 5 - cmp r15, r10 - jge .LBB8_182 -# %bb.129: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB8_151 -# %bb.130: - xor r9d, r9d - jmp .LBB8_154 -.LBB8_131: - mov qword ptr [rsp + 48], r14 # 8-byte Spill - mov rsi, rdx -.LBB8_132: - shl r15, 5 - cmp r15, r10 - jge .LBB8_182 -# %bb.133: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB8_156 -# %bb.134: - xor r9d, r9d - jmp .LBB8_159 -.LBB8_135: - mov r12, r14 - mov rsi, rdx -.LBB8_136: - shl r15, 5 - cmp r15, r10 - jge .LBB8_182 -# %bb.137: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB8_183 -# %bb.138: - xor r14d, r14d - jmp .LBB8_185 -.LBB8_139: - mov r15, r14 - mov rbx, rdx -.LBB8_140: - shl r11, 5 - cmp r11, r10 - jge .LBB8_182 -# %bb.141: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB8_187 -# %bb.142: - xor esi, esi - jmp .LBB8_189 -.LBB8_143: - mov r9, r8 - and r9, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB8_144: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rdx], r13 - sbb edi, edi - mov rsi, r11 - shr rsi, 3 - movzx r10d, byte ptr [r14 + rsi] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r14 + rsi], al - add r11, 2 - cmp qword ptr [rdx + 8], r13 - lea rdx, [rdx + 16] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rsi], bl - cmp r9, r11 - jne .LBB8_144 -.LBB8_145: - test r8b, 1 - je .LBB8_182 -# %bb.146: - cmp qword ptr [rdx], r13 - jmp .LBB8_174 -.LBB8_147: - mov r10, r8 - and r10, -2 - xor edi, edi - .p2align 4, 0x90 -.LBB8_148: # =>This Inner Loop Header: Depth=1 - cmp r13d, dword ptr [rdx] - setg al - neg al - mov rsi, rdi - shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] - mov ecx, edi - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rsi], bl - add rdi, 2 - cmp r13d, dword ptr [rdx + 4] - lea rdx, [rdx + 8] - setg r9b - neg r9b - xor r9b, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, r9b - xor al, bl - mov byte ptr [r14 + rsi], al - cmp r10, rdi - jne .LBB8_148 -.LBB8_149: - test r8b, 1 - je .LBB8_182 -# %bb.150: - cmp r13d, dword ptr [rdx] - jmp .LBB8_179 -.LBB8_151: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 88] # 8-byte Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, dl + mov esi, ecx + mov rcx, qword ptr [rsp] # 8-byte Reload + mov byte ptr [rcx], r10b + movzx edx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dl, 6 + shl r15b, 7 + or r15b, dl + mov byte ptr [rcx + 1], r8b + or r15b, sil + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 24] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rcx + 2], r15b + mov byte ptr [rcx + 3], bl + lea rsi, [r11 + 64] + add rcx, 4 + mov qword ptr [rsp], rcx # 8-byte Spill + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB8_82 +# %bb.83: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + jmp .LBB8_131 +.LBB8_84: + mov r13, qword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB8_90 +# %bb.85: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_88 +# %bb.86: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_152: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp r11b, byte ptr [rsi + r9] +.LBB8_87: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r13, qword ptr [rcx] setg bl neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 movzx r9d, byte ptr [r14 + rdi] xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp r11b, byte ptr [rsi + rax + 1] - lea r9, [rax + 2] - setg bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl and al, bl - xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, r9 - jne .LBB8_152 -# %bb.153: - add rsi, r9 -.LBB8_154: - test r8b, 1 - je .LBB8_182 -# %bb.155: - cmp r11b, byte ptr [rsi] - setg al - neg al - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and r9b, 7 - mov bl, 1 - mov ecx, r9d - shl bl, cl - xor al, dil - and bl, al - jmp .LBB8_161 -.LBB8_156: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 48] # 8-byte Reload - .p2align 4, 0x90 -.LBB8_157: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r11b - sbb edi, edi - mov rbx, r9 - shr rbx, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r14 + rbx] - xor dil, r9b - and dl, dil - xor dl, r9b - mov byte ptr [r14 + rbx], dl - cmp byte ptr [rsi + rax + 1], r11b - lea r9, [rax + 2] - sbb edi, edi - xor dil, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, dil - xor al, dl - mov byte ptr [r14 + rbx], al - cmp r10, r9 - jne .LBB8_157 -# %bb.158: - add rsi, r9 -.LBB8_159: - test r8b, 1 - je .LBB8_182 -# %bb.160: - cmp byte ptr [rsi], r11b - sbb eax, eax - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and r9b, 7 - mov bl, 1 - mov ecx, r9d - shl bl, cl - xor al, dil - and bl, al -.LBB8_161: - xor bl, dil - mov byte ptr [r8 + rdx], bl - jmp .LBB8_182 -.LBB8_162: - mov r9, r8 - and r9, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB8_163: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rdx], r13d - sbb edi, edi - mov rsi, r11 - shr rsi, 3 - movzx r10d, byte ptr [r14 + rsi] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r14 + rsi], al - add r11, 2 - cmp dword ptr [rdx + 4], r13d - lea rdx, [rdx + 8] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rsi], bl - cmp r9, r11 - jne .LBB8_163 -.LBB8_164: - test r8b, 1 - je .LBB8_182 -# %bb.165: - cmp dword ptr [rdx], r13d - jmp .LBB8_174 -.LBB8_166: - mov r10, r8 - and r10, -2 - xor edi, edi - .p2align 4, 0x90 -.LBB8_167: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rdx] - seta al - neg al - mov rsi, rdi - shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] - mov ecx, edi - and cl, 6 - mov bl, 1 - shl bl, cl xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rsi], bl - add rdi, 2 - ucomisd xmm0, qword ptr [rdx + 8] - seta r9b - add rdx, 16 - neg r9b - xor r9b, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, r9b - xor al, bl - mov byte ptr [r14 + rsi], al - cmp r10, rdi - jne .LBB8_167 -.LBB8_168: - test r8b, 1 - je .LBB8_182 -# %bb.169: - ucomisd xmm0, qword ptr [rdx] - seta al - jmp .LBB8_180 -.LBB8_170: - mov r9, r8 - and r9, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB8_171: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rdx], r13w - sbb edi, edi - mov rsi, r11 - shr rsi, 3 - movzx r10d, byte ptr [r14 + rsi] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dil, r10b - and al, dil - xor al, r10b - mov byte ptr [r14 + rsi], al - add r11, 2 - cmp word ptr [rdx + 2], r13w - lea rdx, [rdx + 4] - sbb edi, edi - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rsi], bl - cmp r9, r11 - jne .LBB8_171 -.LBB8_172: - test r8b, 1 - je .LBB8_182 -# %bb.173: - cmp word ptr [rdx], r13w -.LBB8_174: - sbb eax, eax - mov rdx, r11 - shr rdx, 3 - mov sil, byte ptr [r14 + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, sil - and bl, al - jmp .LBB8_181 -.LBB8_175: - mov r10, r8 - and r10, -2 - xor edi, edi + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_87 +.LBB8_88: + sub r12, r8 + je .LBB8_215 +# %bb.89: + add r14, 1 +.LBB8_90: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB8_94 +# %bb.91: + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill .p2align 4, 0x90 -.LBB8_176: # =>This Inner Loop Header: Depth=1 +.LBB8_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r14 # 8-byte Spill cmp r13, qword ptr [rdx] - setg al - neg al - mov rsi, rdi - shr rsi, 3 - movzx r9d, byte ptr [r14 + rsi] - mov ecx, edi - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rsi], bl - add rdi, 2 + setg byte ptr [rsp + 192] # 1-byte Folded Spill cmp r13, qword ptr [rdx + 8] - lea rdx, [rdx + 16] - setg r9b - neg r9b - xor r9b, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, r9b - xor al, bl - mov byte ptr [r14 + rsi], al - cmp r10, rdi - jne .LBB8_176 -.LBB8_177: - test r8b, 1 - je .LBB8_182 -# %bb.178: - cmp r13, qword ptr [rdx] -.LBB8_179: - setg al -.LBB8_180: - neg al - mov rdx, rdi - shr rdx, 3 - mov sil, byte ptr [r14 + rdx] - and dil, 7 - mov bl, 1 - mov ecx, edi - shl bl, cl - xor al, sil - and bl, al -.LBB8_181: - xor bl, sil - mov byte ptr [r14 + rdx], bl -.LBB8_182: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.LBB8_183: - mov r9, r8 - and r9, -2 - xor r14d, r14d - .p2align 4, 0x90 -.LBB8_184: # =>This Inner Loop Header: Depth=1 - mov rax, rsi - cmp r13w, word ptr [rsi] - setg dl - neg dl - mov rdi, r14 - shr rdi, 3 - movzx r10d, byte ptr [r12 + rdi] - mov ecx, r14d - and cl, 6 - mov bl, 1 - shl bl, cl - xor dl, r10b - and bl, dl - xor bl, r10b - mov byte ptr [r12 + rdi], bl - add r14, 2 - cmp r13w, word ptr [rsi + 2] - lea rsi, [rsi + 4] - setg dl - neg dl - xor dl, bl - or cl, 1 - mov al, 1 - shl al, cl - and al, dl - xor al, bl - mov byte ptr [r12 + rdi], al - cmp r9, r14 - jne .LBB8_184 -.LBB8_185: - test r8b, 1 - je .LBB8_182 -# %bb.186: - cmp r13w, word ptr [rsi] + setg dil + cmp r13, qword ptr [rdx + 16] + setg r14b + cmp r13, qword ptr [rdx + 24] + setg byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 32] + setg byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 40] + setg byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 48] setg al - neg al - mov rdx, r14 - shr rdx, 3 - mov dil, byte ptr [r12 + rdx] - and r14b, 7 - mov bl, 1 - mov ecx, r14d - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r12 + rdx], bl - jmp .LBB8_182 -.LBB8_187: - mov r10, r8 - and r10, -2 - xor esi, esi - mov r11, r15 + cmp r13, qword ptr [rdx + 56] + setg r11b + cmp r13, qword ptr [rdx + 64] + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 72] + setg cl + cmp r13, qword ptr [rdx + 80] + setg sil + cmp r13, qword ptr [rdx + 88] + setg r9b + cmp r13, qword ptr [rdx + 96] + setg r10b + cmp r13, qword ptr [rdx + 104] + setg r12b + cmp r13, qword ptr [rdx + 112] + setg byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 120] + setg r8b + cmp r13, qword ptr [rdx + 128] + setg byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 136] + setg byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 144] + setg byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 152] + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 160] + setg byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 168] + setg byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 176] + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 184] + setg r15b + cmp r13, qword ptr [rdx + 192] + setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 200] + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 208] + setg byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 216] + setg byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 224] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 232] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 240] + setg byte ptr [rsp] # 1-byte Folded Spill + cmp r13, qword ptr [rdx + 248] + setg bl + add dil, dil + add dil, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r9b, 3 + or r9b, sil + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r10b, 4 + or r10b, r9b + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 6 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b + mov r14, qword ptr [rsp + 128] # 8-byte Reload + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r14], r11b + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [r14 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 24] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], bl + add rdx, 256 + add r14, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB8_92 +# %bb.93: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB8_94: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB8_215 +# %bb.95: + or rax, 1 + cmp r12, rax + jne .LBB8_198 +# %bb.96: + xor edi, edi + jmp .LBB8_200 +.LBB8_97: + mov r15d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB8_103 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_101 +# %bb.99: + movsxd rsi, r9d + movd xmm0, r15d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB8_188: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rbx] - seta dl - neg dl - mov rdi, rsi - shr rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - mov ecx, esi - and cl, 6 - mov al, 1 - shl al, cl - xor dl, r9b - and al, dl - xor al, r9b - mov byte ptr [r11 + rdi], al - add rsi, 2 - ucomiss xmm0, dword ptr [rbx + 4] - seta r9b - add rbx, 8 - neg r9b - xor r9b, al - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, r9b - xor dl, al - mov byte ptr [r11 + rdi], dl - cmp r10, rsi - jne .LBB8_188 -.LBB8_189: - test r8b, 1 - je .LBB8_182 -# %bb.190: - ucomiss xmm0, dword ptr [rbx] - seta al - neg al - mov rdx, rsi - shr rdx, 3 - mov r14, r15 - mov dil, byte ptr [r15 + rdx] - and sil, 7 - mov bl, 1 +.LBB8_100: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rcx] + seta bl + lea rdx, [rcx + 4] + neg bl + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + movzx r9d, byte ptr [r14 + rax] + xor bl, r9b + lea r10d, [8*rax] mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r15 + rdx], bl - jmp .LBB8_182 -.LBB8_191: - and r15, -16 - mov rax, r15 - shl rax, 5 + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r14 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_100 +.LBB8_101: + sub r12, r8 + je .LBB8_215 +# %bb.102: + add r14, 1 +.LBB8_103: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB8_134 +# %bb.104: + movd xmm0, r15d + cmp rcx, 4 + jb .LBB8_107 +# %bb.105: + mov rax, rcx + shl rax, 7 add rax, rdx - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 232], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 88], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill - xor eax, eax - mov qword ptr [rsp + 128], r14 # 8-byte Spill - .p2align 4, 0x90 -.LBB8_192: # =>This Inner Loop Header: Depth=1 - mov r9, rax - mov qword ptr [rsp + 120], rax # 8-byte Spill - shl rax, 5 - mov qword ptr [rsp + 64], rax # 8-byte Spill - mov r11, rax - mov r9, rax - mov r12, rax - mov r14, rax - mov r13, rax - mov rsi, rax - mov r10, rax - mov r15, rax - mov rbx, rax - mov qword ptr [rsp + 72], rax # 8-byte Spill - movzx ecx, byte ptr [rdx + rax] - movd xmm8, ecx - movzx ecx, byte ptr [rdx + rax + 1] - movd xmm7, ecx - movzx ecx, byte ptr [rdx + rax + 2] - movd xmm6, ecx - movzx ecx, byte ptr [rdx + rax + 3] - movd xmm15, ecx - movzx ecx, byte ptr [rdx + rax + 4] - movd xmm5, ecx - movzx ecx, byte ptr [rdx + rax + 5] - movd xmm2, ecx - movzx ecx, byte ptr [rdx + rax + 6] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rax + 7] - movd xmm1, ecx - movzx ecx, byte ptr [rdx + rax + 8] - movd xmm12, ecx - movzx ecx, byte ptr [rdx + rax + 9] - movd xmm0, ecx - movzx ecx, byte ptr [rdx + rax + 10] - movd xmm9, ecx - movzx ecx, byte ptr [rdx + rax + 11] - movd xmm10, ecx - movzx ecx, byte ptr [rdx + rax + 12] - movd xmm11, ecx - movzx ecx, byte ptr [rdx + rax + 16] - movd xmm14, ecx - movzx ecx, byte ptr [rdx + rax + 24] - movd xmm4, ecx - mov qword ptr [rsp + 56], rax # 8-byte Spill - mov rcx, rax - or rcx, 32 - mov qword ptr [rsp + 16], rcx # 8-byte Spill - mov r8, qword ptr [rsp + 64] # 8-byte Reload - or r8, 64 - mov qword ptr [rsp + 64], r8 # 8-byte Spill - or r11, 96 - or r9, 128 - or r12, 160 - mov qword ptr [rsp + 160], r12 # 8-byte Spill - or r14, 192 - mov qword ptr [rsp + 144], r14 # 8-byte Spill - mov rdi, rax - or rdi, 224 - or r13, 256 - mov qword ptr [rsp + 32], r13 # 8-byte Spill - or r10, 288 - or r15, 320 - or rbx, 352 - or qword ptr [rsp + 72], 384 # 8-byte Folded Spill - mov rcx, rax - or rcx, 416 - mov qword ptr [rsp + 8], rcx # 8-byte Spill - or rsi, 448 - mov rcx, rax - or rcx, 480 - mov qword ptr [rsp + 48], rcx # 8-byte Spill - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rax], 1 - pinsrb xmm8, byte ptr [rdx + r8], 2 - pinsrb xmm8, byte ptr [rdx + r11], 3 - pinsrb xmm8, byte ptr [rdx + r9], 4 - pinsrb xmm8, byte ptr [rdx + r12], 5 - pinsrb xmm8, byte ptr [rdx + r14], 6 - pinsrb xmm8, byte ptr [rdx + rdi], 7 - pinsrb xmm8, byte ptr [rdx + r13], 8 - pinsrb xmm8, byte ptr [rdx + r10], 9 - mov r12, r15 - mov qword ptr [rsp + 96], r15 # 8-byte Spill - pinsrb xmm8, byte ptr [rdx + r15], 10 - pinsrb xmm8, byte ptr [rdx + rbx], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r15], 12 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rax], 13 - pinsrb xmm8, byte ptr [rdx + rsi], 14 - pinsrb xmm8, byte ptr [rdx + rcx], 15 - movdqa xmm13, xmmword ptr [rsp + 288] # 16-byte Reload - movdqa xmm3, xmm13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 1], 1 - pinsrb xmm7, byte ptr [rdx + r8 + 1], 2 - pinsrb xmm7, byte ptr [rdx + r11 + 1], 3 - pinsrb xmm7, byte ptr [rdx + r9 + 1], 4 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r13 + 1], 5 - pinsrb xmm7, byte ptr [rdx + r14 + 1], 6 - pinsrb xmm7, byte ptr [rdx + rdi + 1], 7 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 1], 8 - pinsrb xmm7, byte ptr [rdx + r10 + 1], 9 - pinsrb xmm7, byte ptr [rdx + r12 + 1], 10 - pinsrb xmm7, byte ptr [rdx + rbx + 1], 11 - pinsrb xmm7, byte ptr [rdx + r15 + 1], 12 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 1], 13 - pinsrb xmm7, byte ptr [rdx + rsi + 1], 14 - pinsrb xmm7, byte ptr [rdx + rcx + 1], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 2], 1 - pinsrb xmm6, byte ptr [rdx + r8 + 2], 2 - pinsrb xmm6, byte ptr [rdx + r11 + 2], 3 - pinsrb xmm6, byte ptr [rdx + r9 + 2], 4 - pinsrb xmm6, byte ptr [rdx + r13 + 2], 5 - pinsrb xmm6, byte ptr [rdx + r14 + 2], 6 - pinsrb xmm6, byte ptr [rdx + rdi + 2], 7 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 2], 8 - pinsrb xmm6, byte ptr [rdx + r10 + 2], 9 - pinsrb xmm6, byte ptr [rdx + r12 + 2], 10 - pinsrb xmm6, byte ptr [rdx + rbx + 2], 11 - pinsrb xmm6, byte ptr [rdx + r15 + 2], 12 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 2], 13 - pinsrb xmm6, byte ptr [rdx + rsi + 2], 14 - pinsrb xmm6, byte ptr [rdx + rcx + 2], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rax + 8], 1 - pinsrb xmm12, byte ptr [rdx + r8 + 8], 2 - pinsrb xmm12, byte ptr [rdx + r11 + 8], 3 - pinsrb xmm12, byte ptr [rdx + r9 + 8], 4 - pinsrb xmm12, byte ptr [rdx + r13 + 8], 5 - pinsrb xmm12, byte ptr [rdx + r14 + 8], 6 - pinsrb xmm12, byte ptr [rdx + rdi + 8], 7 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rax + 8], 8 - pinsrb xmm12, byte ptr [rdx + r10 + 8], 9 - pinsrb xmm12, byte ptr [rdx + r12 + 8], 10 - pinsrb xmm12, byte ptr [rdx + rbx + 8], 11 - pinsrb xmm12, byte ptr [rdx + r15 + 8], 12 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rax + 8], 13 - pinsrb xmm12, byte ptr [rdx + rsi + 8], 14 - pinsrb xmm12, byte ptr [rdx + rcx + 8], 15 - pcmpgtb xmm3, xmm8 - movdqa xmmword ptr [rsp + 272], xmm3 # 16-byte Spill - movdqa xmm3, xmm13 - pcmpgtb xmm3, xmm12 - movdqa xmmword ptr [rsp + 304], xmm3 # 16-byte Spill - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rcx + 16], 1 - pinsrb xmm14, byte ptr [rdx + r8 + 16], 2 - pinsrb xmm14, byte ptr [rdx + r11 + 16], 3 - pinsrb xmm14, byte ptr [rdx + r9 + 16], 4 - pinsrb xmm14, byte ptr [rdx + r13 + 16], 5 - pinsrb xmm14, byte ptr [rdx + r14 + 16], 6 - pinsrb xmm14, byte ptr [rdx + rdi + 16], 7 - mov r14, rdi - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rcx + 16], 8 - pinsrb xmm14, byte ptr [rdx + r10 + 16], 9 - pinsrb xmm14, byte ptr [rdx + r12 + 16], 10 - pinsrb xmm14, byte ptr [rdx + rbx + 16], 11 - pinsrb xmm14, byte ptr [rdx + r15 + 16], 12 - mov rcx, rax - pinsrb xmm14, byte ptr [rdx + rax + 16], 13 - mov qword ptr [rsp + 24], rsi # 8-byte Spill - pinsrb xmm14, byte ptr [rdx + rsi + 16], 14 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rdi + 16], 15 - movdqa xmm3, xmm13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 24], 1 - pinsrb xmm4, byte ptr [rdx + r8 + 24], 2 - pinsrb xmm4, byte ptr [rdx + r11 + 24], 3 - pinsrb xmm4, byte ptr [rdx + r9 + 24], 4 - pinsrb xmm4, byte ptr [rdx + r13 + 24], 5 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r8 + 24], 6 - pinsrb xmm4, byte ptr [rdx + r14 + 24], 7 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 24], 8 - pinsrb xmm4, byte ptr [rdx + r10 + 24], 9 - mov qword ptr [rsp + 176], r10 # 8-byte Spill - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax + 24], 10 - pinsrb xmm4, byte ptr [rdx + rbx + 24], 11 - pinsrb xmm4, byte ptr [rdx + r15 + 24], 12 - pinsrb xmm4, byte ptr [rdx + rcx + 24], 13 - pinsrb xmm4, byte ptr [rdx + rsi + 24], 14 - pcmpgtb xmm3, xmm14 - movdqa xmmword ptr [rsp + 240], xmm3 # 16-byte Spill - pinsrb xmm4, byte ptr [rdx + rdi + 24], 15 - movdqa xmm3, xmm13 - pcmpgtb xmm3, xmm4 - movdqa xmmword ptr [rsp + 208], xmm3 # 16-byte Spill - movdqa xmm4, xmm13 - pcmpgtb xmm4, xmm7 - movdqa xmm12, xmm4 - movdqa xmm8, xmmword ptr [rip + .LCPI8_10] # xmm8 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm12, xmm8 - psubb xmm12, xmm4 - movdqa xmm4, xmm13 - movdqa xmm14, xmm13 - pcmpgtb xmm4, xmm6 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 13] - movd xmm7, esi - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi + 3], 1 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rax + 3], 2 - mov qword ptr [rsp + 40], r11 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r11 + 3], 3 - mov rcx, r9 - mov qword ptr [rsp + 112], r9 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r9 + 3], 4 - pinsrb xmm15, byte ptr [rdx + r13 + 3], 5 - pinsrb xmm15, byte ptr [rdx + r8 + 3], 6 - mov qword ptr [rsp + 80], r14 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r14 + 3], 7 - mov r12, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r12 + 3], 8 - pinsrb xmm15, byte ptr [rdx + r10 + 3], 9 - mov r9, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r9 + 3], 10 - mov qword ptr [rsp + 104], rbx # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + rbx + 3], 11 - pinsrb xmm15, byte ptr [rdx + r15 + 3], 12 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rdi + 3], 13 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rdi + 3], 14 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r10 + 3], 15 - pinsrb xmm5, byte ptr [rdx + rsi + 4], 1 - mov r10, rsi - pinsrb xmm5, byte ptr [rdx + rax + 4], 2 - pinsrb xmm5, byte ptr [rdx + r11 + 4], 3 - pinsrb xmm5, byte ptr [rdx + rcx + 4], 4 - pinsrb xmm5, byte ptr [rdx + r13 + 4], 5 - pinsrb xmm5, byte ptr [rdx + r8 + 4], 6 - pinsrb xmm5, byte ptr [rdx + r14 + 4], 7 - pinsrb xmm5, byte ptr [rdx + r12 + 4], 8 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rcx + 4], 9 - pinsrb xmm5, byte ptr [rdx + r9 + 4], 10 - mov r11, r9 - pinsrb xmm5, byte ptr [rdx + rbx + 4], 11 - pinsrb xmm5, byte ptr [rdx + r15 + 4], 12 - mov r9, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r9 + 4], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 4], 14 - movdqa xmm3, xmmword ptr [rsp + 272] # 16-byte Reload - pand xmm3, xmm8 - movdqa xmm6, xmmword ptr [rip + .LCPI8_11] # xmm6 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm4, xmm6 - por xmm4, xmm3 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rdi + 14] - movd xmm6, esi - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rbx + 4], 15 - por xmm4, xmm12 - movdqa xmm12, xmm13 - pcmpgtb xmm12, xmm15 - pcmpgtb xmm13, xmm5 - movzx esi, byte ptr [rdx + rdi + 15] - movd xmm5, esi - pinsrb xmm2, byte ptr [rdx + r10 + 5], 1 - mov r8, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r8 + 5], 2 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rdi + 5], 3 - mov r13, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r13 + 5], 4 - mov rsi, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rsi + 5], 5 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r14 + 5], 6 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r10 + 5], 7 - pinsrb xmm2, byte ptr [rdx + r12 + 5], 8 - pinsrb xmm2, byte ptr [rdx + rcx + 5], 9 - pinsrb xmm2, byte ptr [rdx + r11 + 5], 10 - mov rcx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 5], 11 - pinsrb xmm2, byte ptr [rdx + r15 + 5], 12 - pinsrb xmm2, byte ptr [rdx + r9 + 5], 13 - mov r11, r9 - pinsrb xmm2, byte ptr [rdx + rax + 5], 14 - pinsrb xmm2, byte ptr [rdx + rbx + 5], 15 - movdqa xmm3, xmmword ptr [rip + .LCPI8_12] # xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm12, xmm3 - movdqa xmm3, xmmword ptr [rip + .LCPI8_13] # xmm3 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm13, xmm3 - por xmm13, xmm12 - movdqa xmm12, xmm14 - pcmpgtb xmm12, xmm2 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 17] - movd xmm2, esi - movdqa xmm3, xmmword ptr [rip + .LCPI8_14] # xmm3 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm12, xmm3 - por xmm12, xmm13 - movzx esi, byte ptr [rdx + rax + 18] - movd xmm15, esi - movdqa xmm3, xmmword ptr [rsp + 192] # 16-byte Reload - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rax + 6], 1 - mov r9, r8 - pinsrb xmm3, byte ptr [rdx + r8 + 6], 2 - pinsrb xmm3, byte ptr [rdx + rdi + 6], 3 - mov rcx, r13 - pinsrb xmm3, byte ptr [rdx + r13 + 6], 4 - mov r13, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r13 + 6], 5 - pinsrb xmm3, byte ptr [rdx + r14 + 6], 6 - pinsrb xmm3, byte ptr [rdx + r10 + 6], 7 - pinsrb xmm3, byte ptr [rdx + r12 + 6], 8 - mov rsi, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rsi + 6], 9 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r8 + 6], 10 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rbx + 6], 11 - mov qword ptr [rsp + 72], r15 # 8-byte Spill - pinsrb xmm3, byte ptr [rdx + r15 + 6], 12 - mov rdi, r11 - pinsrb xmm3, byte ptr [rdx + r11 + 6], 13 - mov r11, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r11 + 6], 14 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r10 + 6], 15 - pinsrb xmm1, byte ptr [rdx + rax + 7], 1 - pinsrb xmm1, byte ptr [rdx + r9 + 7], 2 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rax + 7], 3 - pinsrb xmm1, byte ptr [rdx + rcx + 7], 4 - pinsrb xmm1, byte ptr [rdx + r13 + 7], 5 - pinsrb xmm1, byte ptr [rdx + r14 + 7], 6 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r14 + 7], 7 - pinsrb xmm1, byte ptr [rdx + r12 + 7], 8 - pinsrb xmm1, byte ptr [rdx + rsi + 7], 9 - pinsrb xmm1, byte ptr [rdx + r8 + 7], 10 - pinsrb xmm1, byte ptr [rdx + rbx + 7], 11 - pinsrb xmm1, byte ptr [rdx + r15 + 7], 12 - pinsrb xmm1, byte ptr [rdx + rdi + 7], 13 - pinsrb xmm1, byte ptr [rdx + r11 + 7], 14 - pinsrb xmm1, byte ptr [rdx + r10 + 7], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 9], 1 - pinsrb xmm0, byte ptr [rdx + r9 + 9], 2 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 9], 3 - pinsrb xmm0, byte ptr [rdx + rcx + 9], 4 - pinsrb xmm0, byte ptr [rdx + r13 + 9], 5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 9], 6 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 9], 7 - pinsrb xmm0, byte ptr [rdx + r12 + 9], 8 - pinsrb xmm0, byte ptr [rdx + rsi + 9], 9 - pinsrb xmm0, byte ptr [rdx + r8 + 9], 10 - pinsrb xmm0, byte ptr [rdx + rbx + 9], 11 - pinsrb xmm0, byte ptr [rdx + r15 + 9], 12 - pinsrb xmm0, byte ptr [rdx + rdi + 9], 13 - pinsrb xmm0, byte ptr [rdx + r11 + 9], 14 - mov r14, r11 - pinsrb xmm0, byte ptr [rdx + r10 + 9], 15 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 10], 1 - pinsrb xmm9, byte ptr [rdx + r9 + 10], 2 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 10], 3 - pinsrb xmm9, byte ptr [rdx + rcx + 10], 4 - pinsrb xmm9, byte ptr [rdx + r13 + 10], 5 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r11 + 10], 6 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rcx + 10], 7 - pinsrb xmm9, byte ptr [rdx + r12 + 10], 8 - pinsrb xmm9, byte ptr [rdx + rsi + 10], 9 - pinsrb xmm9, byte ptr [rdx + r8 + 10], 10 - pinsrb xmm9, byte ptr [rdx + rbx + 10], 11 - pinsrb xmm9, byte ptr [rdx + r15 + 10], 12 - pinsrb xmm9, byte ptr [rdx + rdi + 10], 13 - por xmm12, xmm4 - movdqa xmm13, xmm14 - movdqa xmm4, xmm14 - pcmpgtb xmm4, xmm3 - pcmpgtb xmm14, xmm1 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rdi + 19] - movd xmm1, esi - pinsrb xmm9, byte ptr [rdx + r14 + 10], 14 - movdqa xmm3, xmmword ptr [rip + .LCPI8_15] # xmm3 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm4, xmm3 - psllw xmm14, 7 - movdqa xmm3, xmmword ptr [rip + .LCPI8_6] # xmm3 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm14, xmm3 - por xmm14, xmm4 - movzx esi, byte ptr [rdx + rdi + 20] - movd xmm4, esi - mov r13, r10 - pinsrb xmm9, byte ptr [rdx + r10 + 10], 15 - por xmm14, xmm12 - movdqa xmmword ptr [rsp + 192], xmm14 # 16-byte Spill - movdqa xmm14, xmm13 - movdqa xmm3, xmm13 - pcmpgtb xmm3, xmm0 - movdqa xmm12, xmm3 - pand xmm12, xmm8 - psubb xmm12, xmm3 - pcmpgtb xmm13, xmm9 - movzx esi, byte ptr [rdx + rdi + 21] - movd xmm0, esi - mov r10, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r10 + 11], 1 - mov rax, r9 - pinsrb xmm10, byte ptr [rdx + r9 + 11], 2 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rdi + 11], 3 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r8 + 11], 4 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r9 + 11], 5 - pinsrb xmm10, byte ptr [rdx + r11 + 11], 6 - mov rbx, rcx - pinsrb xmm10, byte ptr [rdx + rcx + 11], 7 - pinsrb xmm10, byte ptr [rdx + r12 + 11], 8 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rcx + 11], 9 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r14 + 11], 10 - mov r15, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r15 + 11], 11 - mov rsi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 11], 12 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 11], 13 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 11], 14 - pinsrb xmm10, byte ptr [rdx + r13 + 11], 15 - pinsrb xmm11, byte ptr [rdx + r10 + 12], 1 - pinsrb xmm11, byte ptr [rdx + rax + 12], 2 - pinsrb xmm11, byte ptr [rdx + rdi + 12], 3 - pinsrb xmm11, byte ptr [rdx + r8 + 12], 4 - pinsrb xmm11, byte ptr [rdx + r9 + 12], 5 - pinsrb xmm11, byte ptr [rdx + r11 + 12], 6 - pinsrb xmm11, byte ptr [rdx + rbx + 12], 7 - pinsrb xmm11, byte ptr [rdx + r12 + 12], 8 - pinsrb xmm11, byte ptr [rdx + rcx + 12], 9 - mov r12, rcx - mov r8, r14 - pinsrb xmm11, byte ptr [rdx + r14 + 12], 10 - mov rbx, r15 - pinsrb xmm11, byte ptr [rdx + r15 + 12], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r15 + 12], 12 - mov rdi, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rdi + 12], 13 - pinsrb xmm11, byte ptr [rdx + rsi + 12], 14 - mov r10, rsi - movdqa xmm3, xmmword ptr [rsp + 304] # 16-byte Reload - pand xmm3, xmm8 - pand xmm13, xmmword ptr [rip + .LCPI8_11] - por xmm13, xmm3 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 22] - movd xmm8, esi - pinsrb xmm11, byte ptr [rdx + r13 + 12], 15 - por xmm13, xmm12 - movdqa xmm12, xmm14 - pcmpgtb xmm12, xmm10 - movdqa xmm3, xmm14 - pcmpgtb xmm3, xmm11 - movzx esi, byte ptr [rdx + rax + 23] - movd xmm9, esi - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 13], 1 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rcx + 13], 2 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r11 + 13], 3 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rcx + 13], 4 - pinsrb xmm7, byte ptr [rdx + r9 + 13], 5 - mov r14, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r14 + 13], 6 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 13], 7 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 13], 8 - pinsrb xmm7, byte ptr [rdx + r12 + 13], 9 - pinsrb xmm7, byte ptr [rdx + r8 + 13], 10 - pinsrb xmm7, byte ptr [rdx + rbx + 13], 11 - pinsrb xmm7, byte ptr [rdx + r15 + 13], 12 - pinsrb xmm7, byte ptr [rdx + rdi + 13], 13 - pinsrb xmm7, byte ptr [rdx + r10 + 13], 14 - pinsrb xmm7, byte ptr [rdx + r13 + 13], 15 - pand xmm12, xmmword ptr [rip + .LCPI8_12] - pand xmm3, xmmword ptr [rip + .LCPI8_13] - por xmm3, xmm12 - movdqa xmm10, xmm14 - pcmpgtb xmm10, xmm7 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + r12 + 25] - movd xmm11, esi - pand xmm10, xmmword ptr [rip + .LCPI8_14] - por xmm10, xmm3 - movzx esi, byte ptr [rdx + r12 + 26] - movd xmm7, esi - pinsrb xmm6, byte ptr [rdx + rax + 14], 1 - mov rsi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 14], 2 - mov r10, r11 - pinsrb xmm6, byte ptr [rdx + r11 + 14], 3 - mov r12, rcx - pinsrb xmm6, byte ptr [rdx + rcx + 14], 4 - mov rdi, r9 - pinsrb xmm6, byte ptr [rdx + r9 + 14], 5 + cmp r14, rax + jae .LBB8_219 +# %bb.106: + lea rax, [r14 + 4*rcx] + cmp rax, rdx + jbe .LBB8_219 +.LBB8_107: + xor r9d, r9d + mov rbx, rdx mov r11, r14 - pinsrb xmm6, byte ptr [rdx + r14 + 14], 6 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r14 + 14], 7 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rcx + 14], 8 - mov r9, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r9 + 14], 9 - pinsrb xmm6, byte ptr [rdx + r8 + 14], 10 - pinsrb xmm6, byte ptr [rdx + rbx + 14], 11 - pinsrb xmm6, byte ptr [rdx + r15 + 14], 12 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 14], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 14], 14 - pinsrb xmm6, byte ptr [rdx + r13 + 14], 15 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r13 + 15], 1 - pinsrb xmm5, byte ptr [rdx + rsi + 15], 2 - pinsrb xmm5, byte ptr [rdx + r10 + 15], 3 - pinsrb xmm5, byte ptr [rdx + r12 + 15], 4 - pinsrb xmm5, byte ptr [rdx + rdi + 15], 5 - pinsrb xmm5, byte ptr [rdx + r11 + 15], 6 - pinsrb xmm5, byte ptr [rdx + r14 + 15], 7 - pinsrb xmm5, byte ptr [rdx + rcx + 15], 8 - pinsrb xmm5, byte ptr [rdx + r9 + 15], 9 - pinsrb xmm5, byte ptr [rdx + r8 + 15], 10 - pinsrb xmm5, byte ptr [rdx + rbx + 15], 11 - pinsrb xmm5, byte ptr [rdx + r15 + 15], 12 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 15], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 15], 14 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 15], 15 - pinsrb xmm2, byte ptr [rdx + r13 + 17], 1 - pinsrb xmm2, byte ptr [rdx + rsi + 17], 2 - pinsrb xmm2, byte ptr [rdx + r10 + 17], 3 - pinsrb xmm2, byte ptr [rdx + r12 + 17], 4 - pinsrb xmm2, byte ptr [rdx + rdi + 17], 5 - pinsrb xmm2, byte ptr [rdx + r11 + 17], 6 - pinsrb xmm2, byte ptr [rdx + r14 + 17], 7 - pinsrb xmm2, byte ptr [rdx + rcx + 17], 8 - pinsrb xmm2, byte ptr [rdx + r9 + 17], 9 - pinsrb xmm2, byte ptr [rdx + r8 + 17], 10 - pinsrb xmm2, byte ptr [rdx + rbx + 17], 11 - pinsrb xmm2, byte ptr [rdx + r15 + 17], 12 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 17], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 17], 14 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 17], 15 - pinsrb xmm15, byte ptr [rdx + r13 + 18], 1 - pinsrb xmm15, byte ptr [rdx + rsi + 18], 2 - pinsrb xmm15, byte ptr [rdx + r10 + 18], 3 - mov r13, r10 - pinsrb xmm15, byte ptr [rdx + r12 + 18], 4 - pinsrb xmm15, byte ptr [rdx + rdi + 18], 5 - pinsrb xmm15, byte ptr [rdx + r11 + 18], 6 - pinsrb xmm15, byte ptr [rdx + r14 + 18], 7 - pinsrb xmm15, byte ptr [rdx + rcx + 18], 8 - pinsrb xmm15, byte ptr [rdx + r9 + 18], 9 - pinsrb xmm15, byte ptr [rdx + r8 + 18], 10 - pinsrb xmm15, byte ptr [rdx + rbx + 18], 11 - mov rdi, rbx - pinsrb xmm15, byte ptr [rdx + r15 + 18], 12 - mov r10, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r10 + 18], 13 - por xmm10, xmm13 - movdqa xmm13, xmm14 - pcmpgtb xmm13, xmm6 - movdqa xmm3, xmm14 - pcmpgtb xmm3, xmm5 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 27] - movd xmm5, esi - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rcx + 18], 14 - pand xmm13, xmmword ptr [rip + .LCPI8_15] - psllw xmm3, 7 - pand xmm3, xmmword ptr [rip + .LCPI8_6] - por xmm3, xmm13 - movzx esi, byte ptr [rdx + rax + 28] - movd xmm6, esi - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rcx + 18], 15 - por xmm3, xmm10 - movdqa xmmword ptr [rsp + 272], xmm3 # 16-byte Spill - movdqa xmm3, xmm14 - pcmpgtb xmm3, xmm2 - movdqa xmm13, xmm3 - movdqa xmm2, xmmword ptr [rip + .LCPI8_10] # xmm2 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm13, xmm2 - psubb xmm13, xmm3 - movdqa xmm10, xmm14 - pcmpgtb xmm10, xmm15 - movzx esi, byte ptr [rdx + rax + 29] - movd xmm3, esi - movdqa xmm15, xmmword ptr [rsp + 240] # 16-byte Reload - pand xmm15, xmm2 - movdqa xmm2, xmmword ptr [rip + .LCPI8_11] # xmm2 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm10, xmm2 - por xmm10, xmm15 - movzx esi, byte ptr [rdx + rax + 30] - movd xmm2, esi - movzx eax, byte ptr [rdx + rax + 31] - mov dword ptr [rsp + 56], eax # 4-byte Spill - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rax + 19], 1 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rcx + 19], 2 - pinsrb xmm1, byte ptr [rdx + r13 + 19], 3 - pinsrb xmm1, byte ptr [rdx + r12 + 19], 4 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r8 + 19], 5 - pinsrb xmm1, byte ptr [rdx + r11 + 19], 6 - mov rbx, r11 - pinsrb xmm1, byte ptr [rdx + r14 + 19], 7 - mov r15, r14 - mov rsi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rsi + 19], 8 - pinsrb xmm1, byte ptr [rdx + r9 + 19], 9 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r11 + 19], 10 - pinsrb xmm1, byte ptr [rdx + rdi + 19], 11 - mov rdi, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rdi + 19], 12 - pinsrb xmm1, byte ptr [rdx + r10 + 19], 13 - mov r14, r10 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rdi + 19], 14 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r10 + 19], 15 - pinsrb xmm4, byte ptr [rdx + rax + 20], 1 - pinsrb xmm4, byte ptr [rdx + rcx + 20], 2 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r13 + 20], 3 - pinsrb xmm4, byte ptr [rdx + r12 + 20], 4 - pinsrb xmm4, byte ptr [rdx + r8 + 20], 5 - pinsrb xmm4, byte ptr [rdx + rbx + 20], 6 - pinsrb xmm4, byte ptr [rdx + r15 + 20], 7 - pinsrb xmm4, byte ptr [rdx + rsi + 20], 8 - pinsrb xmm4, byte ptr [rdx + r9 + 20], 9 - mov r8, r11 - pinsrb xmm4, byte ptr [rdx + r11 + 20], 10 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rbx + 20], 11 - mov r15, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r15 + 20], 12 - pinsrb xmm4, byte ptr [rdx + r14 + 20], 13 - pinsrb xmm4, byte ptr [rdx + rdi + 20], 14 - mov r9, r10 - pinsrb xmm4, byte ptr [rdx + r10 + 20], 15 - por xmm10, xmm13 - movdqa xmm13, xmm14 - pcmpgtb xmm13, xmm1 - movdqa xmm15, xmm14 - pcmpgtb xmm15, xmm4 - movd xmm1, dword ptr [rsp + 56] # 4-byte Folded Reload - # xmm1 = mem[0],zero,zero,zero - pinsrb xmm0, byte ptr [rdx + rax + 21], 1 - pinsrb xmm8, byte ptr [rdx + rax + 22], 1 - pinsrb xmm9, byte ptr [rdx + rax + 23], 1 - pinsrb xmm11, byte ptr [rdx + rax + 25], 1 - pinsrb xmm7, byte ptr [rdx + rax + 26], 1 - pinsrb xmm5, byte ptr [rdx + rax + 27], 1 - pinsrb xmm6, byte ptr [rdx + rax + 28], 1 - pinsrb xmm3, byte ptr [rdx + rax + 29], 1 - pinsrb xmm2, byte ptr [rdx + rax + 30], 1 - pinsrb xmm1, byte ptr [rdx + rax + 31], 1 - pinsrb xmm0, byte ptr [rdx + rcx + 21], 2 - pinsrb xmm8, byte ptr [rdx + rcx + 22], 2 - pinsrb xmm9, byte ptr [rdx + rcx + 23], 2 - pinsrb xmm11, byte ptr [rdx + rcx + 25], 2 - pinsrb xmm7, byte ptr [rdx + rcx + 26], 2 - pinsrb xmm5, byte ptr [rdx + rcx + 27], 2 - pinsrb xmm6, byte ptr [rdx + rcx + 28], 2 - pinsrb xmm3, byte ptr [rdx + rcx + 29], 2 - pinsrb xmm2, byte ptr [rdx + rcx + 30], 2 - pinsrb xmm1, byte ptr [rdx + rcx + 31], 2 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r13 + 21], 3 - pinsrb xmm0, byte ptr [rdx + r12 + 21], 4 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rdi + 21], 5 - mov r11, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r11 + 21], 6 - mov r14, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r14 + 21], 7 - pinsrb xmm0, byte ptr [rdx + rsi + 21], 8 - mov r10, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r10 + 21], 9 - pinsrb xmm0, byte ptr [rdx + r8 + 21], 10 - pinsrb xmm0, byte ptr [rdx + rbx + 21], 11 - pinsrb xmm0, byte ptr [rdx + r15 + 21], 12 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rcx + 21], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 21], 14 - pinsrb xmm0, byte ptr [rdx + r9 + 21], 15 - movdqa xmm4, xmmword ptr [rip + .LCPI8_12] # xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm13, xmm4 - movdqa xmm4, xmmword ptr [rip + .LCPI8_13] # xmm4 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm15, xmm4 - por xmm15, xmm13 - movdqa xmm13, xmm14 - pcmpgtb xmm13, xmm0 - movdqa xmm0, xmmword ptr [rip + .LCPI8_14] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm13, xmm0 - por xmm13, xmm15 - pinsrb xmm8, byte ptr [rdx + r13 + 22], 3 - pinsrb xmm8, byte ptr [rdx + r12 + 22], 4 - pinsrb xmm8, byte ptr [rdx + rdi + 22], 5 - pinsrb xmm8, byte ptr [rdx + r11 + 22], 6 - pinsrb xmm8, byte ptr [rdx + r14 + 22], 7 - pinsrb xmm8, byte ptr [rdx + rsi + 22], 8 - pinsrb xmm8, byte ptr [rdx + r10 + 22], 9 - pinsrb xmm8, byte ptr [rdx + r8 + 22], 10 - pinsrb xmm8, byte ptr [rdx + rbx + 22], 11 - pinsrb xmm8, byte ptr [rdx + r15 + 22], 12 - pinsrb xmm8, byte ptr [rdx + rcx + 22], 13 - pinsrb xmm8, byte ptr [rdx + rax + 22], 14 - pinsrb xmm8, byte ptr [rdx + r9 + 22], 15 - pinsrb xmm9, byte ptr [rdx + r13 + 23], 3 - pinsrb xmm9, byte ptr [rdx + r12 + 23], 4 - pinsrb xmm9, byte ptr [rdx + rdi + 23], 5 - pinsrb xmm9, byte ptr [rdx + r11 + 23], 6 - pinsrb xmm9, byte ptr [rdx + r14 + 23], 7 - pinsrb xmm9, byte ptr [rdx + rsi + 23], 8 - pinsrb xmm9, byte ptr [rdx + r10 + 23], 9 - pinsrb xmm9, byte ptr [rdx + r8 + 23], 10 - pinsrb xmm9, byte ptr [rdx + rbx + 23], 11 - pinsrb xmm9, byte ptr [rdx + r15 + 23], 12 - pinsrb xmm9, byte ptr [rdx + rcx + 23], 13 - pinsrb xmm9, byte ptr [rdx + rax + 23], 14 - pinsrb xmm9, byte ptr [rdx + r9 + 23], 15 - pinsrb xmm11, byte ptr [rdx + r13 + 25], 3 - pinsrb xmm11, byte ptr [rdx + r12 + 25], 4 - pinsrb xmm11, byte ptr [rdx + rdi + 25], 5 - pinsrb xmm11, byte ptr [rdx + r11 + 25], 6 - pinsrb xmm11, byte ptr [rdx + r14 + 25], 7 - pinsrb xmm11, byte ptr [rdx + rsi + 25], 8 - pinsrb xmm11, byte ptr [rdx + r10 + 25], 9 - pinsrb xmm11, byte ptr [rdx + r8 + 25], 10 - pinsrb xmm11, byte ptr [rdx + rbx + 25], 11 - pinsrb xmm11, byte ptr [rdx + r15 + 25], 12 - pinsrb xmm11, byte ptr [rdx + rcx + 25], 13 - pinsrb xmm11, byte ptr [rdx + rax + 25], 14 - pinsrb xmm11, byte ptr [rdx + r9 + 25], 15 - pinsrb xmm7, byte ptr [rdx + r13 + 26], 3 - pinsrb xmm7, byte ptr [rdx + r12 + 26], 4 - pinsrb xmm7, byte ptr [rdx + rdi + 26], 5 - pinsrb xmm7, byte ptr [rdx + r11 + 26], 6 - pinsrb xmm7, byte ptr [rdx + r14 + 26], 7 - pinsrb xmm7, byte ptr [rdx + rsi + 26], 8 - pinsrb xmm7, byte ptr [rdx + r10 + 26], 9 - pinsrb xmm7, byte ptr [rdx + r8 + 26], 10 - pinsrb xmm7, byte ptr [rdx + rbx + 26], 11 - pinsrb xmm7, byte ptr [rdx + r15 + 26], 12 - pinsrb xmm7, byte ptr [rdx + rcx + 26], 13 - pinsrb xmm7, byte ptr [rdx + rax + 26], 14 - por xmm13, xmm10 - movdqa xmm12, xmm14 - movdqa xmm4, xmm14 - pcmpgtb xmm4, xmm8 - movdqa xmm0, xmm14 - pcmpgtb xmm0, xmm9 - movdqa xmm14, xmmword ptr [rip + .LCPI8_15] # xmm14 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm4, xmm14 - psllw xmm0, 7 - movdqa xmm15, xmmword ptr [rip + .LCPI8_6] # xmm15 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm0, xmm15 - por xmm0, xmm4 - pinsrb xmm7, byte ptr [rdx + r9 + 26], 15 - por xmm0, xmm13 - movdqa xmm4, xmm12 - pcmpgtb xmm4, xmm11 - movdqa xmm8, xmm4 - movdqa xmm11, xmmword ptr [rip + .LCPI8_10] # xmm11 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pand xmm8, xmm11 - psubb xmm8, xmm4 - movdqa xmm4, xmm12 - pcmpgtb xmm4, xmm7 - pinsrb xmm5, byte ptr [rdx + r13 + 27], 3 - pinsrb xmm5, byte ptr [rdx + r12 + 27], 4 - pinsrb xmm5, byte ptr [rdx + rdi + 27], 5 - pinsrb xmm5, byte ptr [rdx + r11 + 27], 6 - pinsrb xmm5, byte ptr [rdx + r14 + 27], 7 - pinsrb xmm5, byte ptr [rdx + rsi + 27], 8 - pinsrb xmm5, byte ptr [rdx + r10 + 27], 9 - pinsrb xmm5, byte ptr [rdx + r8 + 27], 10 - pinsrb xmm5, byte ptr [rdx + rbx + 27], 11 - pinsrb xmm5, byte ptr [rdx + r15 + 27], 12 - pinsrb xmm5, byte ptr [rdx + rcx + 27], 13 - pinsrb xmm5, byte ptr [rdx + rax + 27], 14 - pinsrb xmm5, byte ptr [rdx + r9 + 27], 15 - pinsrb xmm6, byte ptr [rdx + r13 + 28], 3 - pinsrb xmm6, byte ptr [rdx + r12 + 28], 4 - pinsrb xmm6, byte ptr [rdx + rdi + 28], 5 - pinsrb xmm6, byte ptr [rdx + r11 + 28], 6 - pinsrb xmm6, byte ptr [rdx + r14 + 28], 7 - pinsrb xmm6, byte ptr [rdx + rsi + 28], 8 - pinsrb xmm6, byte ptr [rdx + r10 + 28], 9 - pinsrb xmm6, byte ptr [rdx + r8 + 28], 10 - pinsrb xmm6, byte ptr [rdx + rbx + 28], 11 - pinsrb xmm6, byte ptr [rdx + r15 + 28], 12 - pinsrb xmm6, byte ptr [rdx + rcx + 28], 13 - movdqa xmm7, xmmword ptr [rsp + 208] # 16-byte Reload - pand xmm7, xmm11 - pinsrb xmm6, byte ptr [rdx + rax + 28], 14 - pand xmm4, xmmword ptr [rip + .LCPI8_11] - por xmm4, xmm7 - pinsrb xmm6, byte ptr [rdx + r9 + 28], 15 - por xmm4, xmm8 - movdqa xmm7, xmm12 - pcmpgtb xmm7, xmm5 - movdqa xmm5, xmm12 - pcmpgtb xmm5, xmm6 - pinsrb xmm3, byte ptr [rdx + r13 + 29], 3 - pinsrb xmm3, byte ptr [rdx + r12 + 29], 4 - pinsrb xmm3, byte ptr [rdx + rdi + 29], 5 - pinsrb xmm3, byte ptr [rdx + r11 + 29], 6 - pinsrb xmm3, byte ptr [rdx + r14 + 29], 7 - pinsrb xmm3, byte ptr [rdx + rsi + 29], 8 - pinsrb xmm3, byte ptr [rdx + r10 + 29], 9 - pinsrb xmm3, byte ptr [rdx + r8 + 29], 10 - pinsrb xmm3, byte ptr [rdx + rbx + 29], 11 - pinsrb xmm3, byte ptr [rdx + r15 + 29], 12 - pinsrb xmm3, byte ptr [rdx + rcx + 29], 13 - pinsrb xmm3, byte ptr [rdx + rax + 29], 14 - pinsrb xmm3, byte ptr [rdx + r9 + 29], 15 - pand xmm7, xmmword ptr [rip + .LCPI8_12] - pand xmm5, xmmword ptr [rip + .LCPI8_13] - por xmm5, xmm7 - movdqa xmm6, xmm12 - pcmpgtb xmm6, xmm3 - pand xmm6, xmmword ptr [rip + .LCPI8_14] - por xmm6, xmm5 - pinsrb xmm2, byte ptr [rdx + r13 + 30], 3 - pinsrb xmm1, byte ptr [rdx + r13 + 31], 3 - pinsrb xmm2, byte ptr [rdx + r12 + 30], 4 - pinsrb xmm1, byte ptr [rdx + r12 + 31], 4 - pinsrb xmm2, byte ptr [rdx + rdi + 30], 5 - pinsrb xmm1, byte ptr [rdx + rdi + 31], 5 - pinsrb xmm2, byte ptr [rdx + r11 + 30], 6 - pinsrb xmm1, byte ptr [rdx + r11 + 31], 6 - pinsrb xmm2, byte ptr [rdx + r14 + 30], 7 - pinsrb xmm1, byte ptr [rdx + r14 + 31], 7 - pinsrb xmm2, byte ptr [rdx + rsi + 30], 8 - pinsrb xmm1, byte ptr [rdx + rsi + 31], 8 - pinsrb xmm2, byte ptr [rdx + r10 + 30], 9 - pinsrb xmm1, byte ptr [rdx + r10 + 31], 9 +.LBB8_108: + mov qword ptr [rsp], r11 # 8-byte Spill + mov dword ptr [rsp + 224], r15d # 4-byte Spill + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 208], rcx # 8-byte Spill + sub rcx, r9 + mov qword ptr [rsp + 192], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB8_109: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rbx] + seta byte ptr [rsp + 120] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 4] + seta r8b + ucomiss xmm0, dword ptr [rbx + 8] + seta r14b + ucomiss xmm0, dword ptr [rbx + 12] + seta r13b + ucomiss xmm0, dword ptr [rbx + 16] + seta byte ptr [rsp + 80] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 20] + seta byte ptr [rsp + 72] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 24] + seta al + ucomiss xmm0, dword ptr [rbx + 28] + seta r11b + ucomiss xmm0, dword ptr [rbx + 32] + seta byte ptr [rsp + 176] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 36] + seta cl + ucomiss xmm0, dword ptr [rbx + 40] + seta sil + ucomiss xmm0, dword ptr [rbx + 44] + seta dil + ucomiss xmm0, dword ptr [rbx + 48] + seta r10b + ucomiss xmm0, dword ptr [rbx + 52] + seta r12b + ucomiss xmm0, dword ptr [rbx + 56] + seta byte ptr [rsp + 144] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 60] + seta r9b + ucomiss xmm0, dword ptr [rbx + 64] + seta byte ptr [rsp + 88] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 68] + seta byte ptr [rsp + 112] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 72] + seta byte ptr [rsp + 160] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 76] + seta byte ptr [rsp + 96] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 80] + seta byte ptr [rsp + 104] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 84] + seta byte ptr [rsp + 64] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 88] + seta byte ptr [rsp + 56] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 92] + seta r15b + ucomiss xmm0, dword ptr [rbx + 96] + seta byte ptr [rsp + 24] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 100] + seta byte ptr [rsp + 48] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 104] + seta byte ptr [rsp + 40] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 108] + seta byte ptr [rsp + 32] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 112] + seta byte ptr [rsp + 16] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 116] + seta byte ptr [rsp + 8] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 120] + seta byte ptr [rsp + 128] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 124] + seta dl + add r8b, r8b + add r8b, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r8b + add cl, cl + add cl, byte ptr [rsp + 176] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 4 + or cl, r13b + mov r8d, ecx + shl dil, 3 + or dil, sil + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 144] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, cl + or r9b, r12b + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, al + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov rsi, qword ptr [rsp] # 8-byte Reload + mov byte ptr [rsi], r11b + movzx edi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl dil, 6 + shl r15b, 7 + or r15b, dil + mov byte ptr [rsi + 1], r9b + or r15b, cl + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 24] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or dl, al + mov byte ptr [rsi + 2], r15b + mov byte ptr [rsi + 3], dl + add rbx, 128 + add rsi, 4 + mov qword ptr [rsp], rsi # 8-byte Spill + add qword ptr [rsp + 192], -1 # 8-byte Folded Spill + jne .LBB8_109 +# %bb.110: + mov r11, qword ptr [rsp] # 8-byte Reload + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov r15d, dword ptr [rsp + 224] # 4-byte Reload + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + jmp .LBB8_135 +.LBB8_111: + mov r15b, byte ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB8_138 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_153 +# %bb.113: + movsxd rsi, r9d + mov rax, r8 + .p2align 4, 0x90 +.LBB8_114: # =>This Inner Loop Header: Depth=1 + lea r11, [rdx + 1] + cmp byte ptr [rdx], r15b + sbb edx, edx + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + movzx r9d, byte ptr [r14 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, dl + xor dil, r9b + mov byte ptr [r14 + rbx], dil + add rsi, 1 + mov rdx, r11 + add rax, -1 + jne .LBB8_114 +# %bb.115: + sub r12, r8 + jne .LBB8_154 + jmp .LBB8_215 +.LBB8_116: + mov r13d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB8_122 +# %bb.117: + mov r8d, 8 + sub r8d, r9d + cmp r8, r12 + cmovg r8, r12 + test r8, r8 + jle .LBB8_120 +# %bb.118: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx + .p2align 4, 0x90 +.LBB8_119: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r13d, dword ptr [rcx] + setg bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB8_119 +.LBB8_120: + sub r12, r8 + je .LBB8_215 +# %bb.121: + add r14, 1 +.LBB8_122: + lea rax, [r12 + 31] + test r12, r12 + cmovns rax, r12 + sar rax, 5 + cmp r12, 32 + jl .LBB8_126 +# %bb.123: + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 208], rax # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB8_124: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 128], r14 # 8-byte Spill + cmp r13d, dword ptr [rdx] + setg byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 4] + setg dil + cmp r13d, dword ptr [rdx + 8] + setg r14b + cmp r13d, dword ptr [rdx + 12] + setg byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 16] + setg byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 20] + setg byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 24] + setg al + cmp r13d, dword ptr [rdx + 28] + setg r11b + cmp r13d, dword ptr [rdx + 32] + setg byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 36] + setg cl + cmp r13d, dword ptr [rdx + 40] + setg sil + cmp r13d, dword ptr [rdx + 44] + setg r9b + cmp r13d, dword ptr [rdx + 48] + setg r10b + cmp r13d, dword ptr [rdx + 52] + setg r12b + cmp r13d, dword ptr [rdx + 56] + setg byte ptr [rsp + 176] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 60] + setg r8b + cmp r13d, dword ptr [rdx + 64] + setg byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 68] + setg byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 72] + setg byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 76] + setg byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 80] + setg byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 84] + setg byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 88] + setg byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 92] + setg r15b + cmp r13d, dword ptr [rdx + 96] + setg byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 100] + setg byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 104] + setg byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 108] + setg byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 112] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 116] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 120] + setg byte ptr [rsp] # 1-byte Folded Spill + cmp r13d, dword ptr [rdx + 124] + setg bl + add dil, dil + add dil, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, dil + add cl, cl + add cl, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + shl cl, 4 + or cl, al + mov edi, ecx + shl r9b, 3 + or r9b, sil + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, dil + shl r10b, 4 + or r10b, r9b + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 6 + shl r8b, 7 + or r8b, sil + or r11b, cl + or r8b, r12b mov r14, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r8 + 30], 10 - pinsrb xmm1, byte ptr [rdx + r8 + 31], 10 - pinsrb xmm2, byte ptr [rdx + rbx + 30], 11 - pinsrb xmm1, byte ptr [rdx + rbx + 31], 11 - pinsrb xmm2, byte ptr [rdx + r15 + 30], 12 - pinsrb xmm1, byte ptr [rdx + r15 + 31], 12 - pinsrb xmm2, byte ptr [rdx + rcx + 30], 13 - pinsrb xmm1, byte ptr [rdx + rcx + 31], 13 - pinsrb xmm2, byte ptr [rdx + rax + 30], 14 - pinsrb xmm1, byte ptr [rdx + rax + 31], 14 - pinsrb xmm2, byte ptr [rdx + r9 + 30], 15 - pinsrb xmm1, byte ptr [rdx + r9 + 31], 15 - por xmm6, xmm4 - movdqa xmm3, xmm12 - pcmpgtb xmm3, xmm2 - pand xmm3, xmm14 - pcmpgtb xmm12, xmm1 - psllw xmm12, 7 - pand xmm12, xmm15 - por xmm12, xmm3 - por xmm12, xmm6 - movdqa xmm1, xmm0 - punpcklbw xmm1, xmm12 # xmm1 = xmm1[0],xmm12[0],xmm1[1],xmm12[1],xmm1[2],xmm12[2],xmm1[3],xmm12[3],xmm1[4],xmm12[4],xmm1[5],xmm12[5],xmm1[6],xmm12[6],xmm1[7],xmm12[7] - movdqa xmm5, xmmword ptr [rsp + 192] # 16-byte Reload - movdqa xmm3, xmm5 - movdqa xmm6, xmmword ptr [rsp + 272] # 16-byte Reload - punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] - movdqa xmm4, xmm3 - punpcklwd xmm4, xmm1 # xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3] - punpckhwd xmm3, xmm1 # xmm3 = xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7] - punpckhbw xmm0, xmm12 # xmm0 = xmm0[8],xmm12[8],xmm0[9],xmm12[9],xmm0[10],xmm12[10],xmm0[11],xmm12[11],xmm0[12],xmm12[12],xmm0[13],xmm12[13],xmm0[14],xmm12[14],xmm0[15],xmm12[15] - punpckhbw xmm5, xmm6 # xmm5 = xmm5[8],xmm6[8],xmm5[9],xmm6[9],xmm5[10],xmm6[10],xmm5[11],xmm6[11],xmm5[12],xmm6[12],xmm5[13],xmm6[13],xmm5[14],xmm6[14],xmm5[15],xmm6[15] - movdqa xmm1, xmm5 - punpcklwd xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3] - punpckhwd xmm5, xmm0 # xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7] - mov rcx, qword ptr [rsp + 120] # 8-byte Reload - movdqu xmmword ptr [r14 + 4*rcx + 48], xmm5 - movdqu xmmword ptr [r14 + 4*rcx + 32], xmm1 - movdqu xmmword ptr [r14 + 4*rcx + 16], xmm3 - movdqu xmmword ptr [r14 + 4*rcx], xmm4 - add rcx, 16 + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 88] # 1-byte Folded Reload + mov esi, ecx + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 2 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl cl, 5 + or cl, sil + mov byte ptr [r14], r11b + movzx esi, byte ptr [rsp + 56] # 1-byte Folded Reload + shl sil, 6 + shl r15b, 7 + or r15b, sil + mov byte ptr [r14 + 1], r8b + or r15b, cl + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 24] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r14 + 2], r15b + mov byte ptr [r14 + 3], bl + add rdx, 128 + add r14, 4 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB8_124 +# %bb.125: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rax, qword ptr [rsp + 208] # 8-byte Reload +.LBB8_126: + shl rax, 5 + mov r8, r12 + sub r8, rax + jle .LBB8_215 +# %bb.127: + or rax, 1 + cmp r12, rax + jne .LBB8_171 +# %bb.128: + xor edi, edi + jmp .LBB8_173 +.LBB8_129: + mov rdi, rdx + jmp .LBB8_141 +.LBB8_130: + mov qword ptr [rsp], r14 # 8-byte Spill + mov rsi, rdx +.LBB8_131: + shl rcx, 5 + mov r8, r12 + sub r8, rcx + jle .LBB8_215 +# %bb.132: + or rcx, 1 + cmp r12, rcx + jne .LBB8_205 +# %bb.133: + xor r14d, r14d + jmp .LBB8_207 +.LBB8_134: + mov r11, r14 + mov rbx, rdx +.LBB8_135: + shl rcx, 5 + mov r8, r12 + sub r8, rcx + jle .LBB8_215 +# %bb.136: + movd xmm0, r15d + or rcx, 1 + cmp r12, rcx + jne .LBB8_211 +# %bb.137: + xor esi, esi + jmp .LBB8_213 +.LBB8_138: + mov r11, rdx + jmp .LBB8_155 +.LBB8_139: + mov rdi, rdx + sub r12, r8 + je .LBB8_215 +.LBB8_140: + add r14, 1 +.LBB8_141: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB8_149 +# %bb.142: + cmp rcx, 16 + mov byte ptr [rsp], r15b # 1-byte Spill + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 256], rcx # 8-byte Spill + jb .LBB8_145 +# %bb.143: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r14, rax + jae .LBB8_222 +# %bb.144: + lea rax, [r14 + 4*rcx] + cmp rdi, rax + jae .LBB8_222 +.LBB8_145: + xor eax, eax + mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 104], r14 # 8-byte Spill + mov rsi, rdi +.LBB8_146: + sub rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov qword ptr [rsp + 208], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB8_147: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp r15b, byte ptr [rsi] + setg byte ptr [rsp + 224] # 1-byte Folded Spill + cmp r15b, byte ptr [rsi + 1] + setg dil + cmp r15b, byte ptr [rsi + 2] + setg r11b + cmp r15b, byte ptr [rsi + 3] + setg r15b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 4] + setg byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 5] + setg byte ptr [rsp + 160] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 6] + setg bl + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 7] + setg r12b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 8] + setg byte ptr [rsp + 120] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 9] + setg sil + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 10] + setg r8b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 11] + setg r9b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 12] + setg r14b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 13] + setg byte ptr [rsp + 72] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 14] + setg byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 15] + setg r13b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 16] + setg byte ptr [rsp + 176] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 17] + setg byte ptr [rsp + 144] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 18] + setg byte ptr [rsp + 80] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 19] + setg byte ptr [rsp + 96] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 20] + setg byte ptr [rsp + 88] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 21] + setg byte ptr [rsp + 56] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 22] + setg byte ptr [rsp + 64] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 23] + setg r10b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 24] + setg byte ptr [rsp + 48] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 25] + setg byte ptr [rsp + 40] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 26] + setg byte ptr [rsp + 32] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 27] + setg byte ptr [rsp + 24] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 28] + setg byte ptr [rsp + 16] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 29] + setg byte ptr [rsp + 8] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 30] + setg byte ptr [rsp + 128] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 31] + setg dl + add dil, dil + add dil, byte ptr [rsp + 224] # 1-byte Folded Reload + shl bl, 6 + shl r12b, 7 + or r12b, bl + shl r11b, 2 + or r11b, dil + add sil, sil + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + shl r15b, 3 + or r15b, r11b + shl r8b, 2 + or r8b, sil + movzx ebx, byte ptr [rsp + 192] # 1-byte Folded Reload + shl bl, 4 + or bl, r15b + mov eax, ebx + movzx r15d, byte ptr [rsp] # 1-byte Folded Reload + shl r9b, 3 + or r9b, r8b + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl bl, 5 + or bl, al + shl r14b, 4 + or r14b, r9b + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload + shl sil, 6 + shl r13b, 7 + or r13b, sil + or r12b, bl + or r13b, al + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 176] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 4 + or al, bl + movzx ebx, byte ptr [rsp + 56] # 1-byte Folded Reload + shl bl, 5 + or bl, al + mov rdi, qword ptr [rsp + 104] # 8-byte Reload + mov byte ptr [rdi], r12b + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 6 + shl r10b, 7 + or r10b, al + mov byte ptr [rdi + 1], r13b + or r10b, bl + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rdi + 2], r10b + mov byte ptr [rdi + 3], dl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 104], rdi # 8-byte Spill + add qword ptr [rsp + 208], -1 # 8-byte Folded Spill + jne .LBB8_147 +# %bb.148: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + jmp .LBB8_150 +.LBB8_149: + mov qword ptr [rsp + 104], r14 # 8-byte Spill + mov rsi, rdi +.LBB8_150: + shl rcx, 5 + mov r8, r12 + sub r8, rcx + jle .LBB8_215 +# %bb.151: + or rcx, 1 + cmp r12, rcx + jne .LBB8_175 +# %bb.152: + xor r9d, r9d + jmp .LBB8_178 +.LBB8_153: + mov r11, rdx + sub r12, r8 + je .LBB8_215 +.LBB8_154: + add r14, 1 +.LBB8_155: + lea rcx, [r12 + 31] + test r12, r12 + cmovns rcx, r12 + sar rcx, 5 + cmp r12, 32 + jl .LBB8_163 +# %bb.156: + cmp rcx, 16 + mov byte ptr [rsp], r15b # 1-byte Spill + mov qword ptr [rsp + 136], r12 # 8-byte Spill + mov qword ptr [rsp + 256], rcx # 8-byte Spill + jb .LBB8_159 +# %bb.157: mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB8_192 -# %bb.193: - mov r15, qword ptr [rsp + 256] # 8-byte Reload - cmp r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r11b, byte ptr [rsp] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r10, qword ptr [rsp + 136] # 8-byte Reload - jne .LBB8_42 - jmp .LBB8_128 -.LBB8_194: - and r15, -16 - mov rax, r15 shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 264], rax # 8-byte Spill - mov qword ptr [rsp + 232], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 48], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill + add rax, r11 + cmp r14, rax + jae .LBB8_225 +# %bb.158: + lea rax, [r14 + 4*rcx] + cmp r11, rax + jae .LBB8_225 +.LBB8_159: xor eax, eax - mov qword ptr [rsp + 128], r14 # 8-byte Spill + mov qword ptr [rsp + 248], rax # 8-byte Spill + mov qword ptr [rsp + 48], r14 # 8-byte Spill + mov rsi, r11 +.LBB8_160: + sub rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov qword ptr [rsp + 208], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB8_195: # =>This Inner Loop Header: Depth=1 - mov r9, rax - mov qword ptr [rsp + 240], rax # 8-byte Spill - mov rcx, rax +.LBB8_161: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp r15b, byte ptr [rsi] + seta byte ptr [rsp + 224] # 1-byte Folded Spill + cmp r15b, byte ptr [rsi + 1] + seta dil + cmp r15b, byte ptr [rsi + 2] + seta r11b + cmp r15b, byte ptr [rsi + 3] + seta r15b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 4] + seta byte ptr [rsp + 192] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 5] + seta byte ptr [rsp + 160] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 6] + seta bl + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 7] + seta r12b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 8] + seta byte ptr [rsp + 120] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rsi + 9] + seta sil + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 10] + seta r8b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 11] + seta r9b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 12] + seta r14b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 13] + seta byte ptr [rsp + 104] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 14] + seta byte ptr [rsp + 112] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp al, byte ptr [rcx + 15] + seta r13b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 16] + seta byte ptr [rsp + 176] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 17] + seta byte ptr [rsp + 144] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 18] + seta byte ptr [rsp + 80] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 19] + seta byte ptr [rsp + 96] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 20] + seta byte ptr [rsp + 88] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 21] + seta byte ptr [rsp + 64] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 22] + seta byte ptr [rsp + 72] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 23] + seta r10b + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 24] + seta byte ptr [rsp + 56] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 25] + seta byte ptr [rsp + 40] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 26] + seta byte ptr [rsp + 32] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 27] + seta byte ptr [rsp + 24] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 28] + seta byte ptr [rsp + 16] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 29] + seta byte ptr [rsp + 8] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 30] + seta byte ptr [rsp + 128] # 1-byte Folded Spill + movzx edx, byte ptr [rsp] # 1-byte Folded Reload + cmp dl, byte ptr [rcx + 31] + seta dl + add dil, dil + add dil, byte ptr [rsp + 224] # 1-byte Folded Reload + shl bl, 6 + shl r12b, 7 + or r12b, bl + shl r11b, 2 + or r11b, dil + add sil, sil + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload + shl r15b, 3 + or r15b, r11b + shl r8b, 2 + or r8b, sil + movzx ebx, byte ptr [rsp + 192] # 1-byte Folded Reload + shl bl, 4 + or bl, r15b + mov eax, ebx + movzx r15d, byte ptr [rsp] # 1-byte Folded Reload + shl r9b, 3 + or r9b, r8b + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl bl, 5 + or bl, al + shl r14b, 4 + or r14b, r9b + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 112] # 1-byte Folded Reload + shl sil, 6 + shl r13b, 7 + or r13b, sil + or r12b, bl + or r13b, al + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 176] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 4 + or al, bl + movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + shl bl, 5 + or bl, al + mov rdi, qword ptr [rsp + 48] # 8-byte Reload + mov byte ptr [rdi], r12b + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 6 + shl r10b, 7 + or r10b, al + mov byte ptr [rdi + 1], r13b + or r10b, bl + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 56] # 1-byte Folded Reload + mov ebx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 2 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 3 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, bl + mov ebx, eax + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + shl al, 5 + or al, bl + movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl bl, 6 + shl dl, 7 + or dl, bl + or dl, al + mov byte ptr [rdi + 2], r10b + mov byte ptr [rdi + 3], dl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 48], rdi # 8-byte Spill + add qword ptr [rsp + 208], -1 # 8-byte Folded Spill + jne .LBB8_161 +# %bb.162: + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + jmp .LBB8_164 +.LBB8_163: + mov qword ptr [rsp + 48], r14 # 8-byte Spill + mov rsi, r11 +.LBB8_164: shl rcx, 5 - mov r14, rcx - mov rbx, rcx - mov rax, rcx - mov r11, rcx - mov r10, rcx - mov r8, rcx - mov r9, rcx - mov qword ptr [rsp + 64], rcx # 8-byte Spill - mov r12, rcx - mov r15, rcx - mov rdi, rcx - mov rsi, rcx - movzx ecx, byte ptr [rdx + rcx] - movd xmm9, ecx - movzx ecx, byte ptr [rdx + rsi + 1] - movd xmm5, ecx - movzx ecx, byte ptr [rdx + rsi + 2] - movd xmm7, ecx - movzx ecx, byte ptr [rdx + rsi + 3] - movd xmm15, ecx - movzx ecx, byte ptr [rdx + rsi + 4] - movd xmm3, ecx - movzx ecx, byte ptr [rdx + rsi + 5] - movd xmm2, ecx - movzx ecx, byte ptr [rdx + rsi + 6] - movd xmm8, ecx - movzx ecx, byte ptr [rdx + rsi + 7] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rsi + 8] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rsi + 9] - movd xmm11, ecx - movzx ecx, byte ptr [rdx + rsi + 10] - movd xmm12, ecx - movzx ecx, byte ptr [rdx + rsi + 11] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 144], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rsi + 12] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 304], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rsi + 13] - movd xmm14, ecx - movzx ecx, byte ptr [rdx + rsi + 14] - movd xmm13, ecx - mov qword ptr [rsp + 56], rsi # 8-byte Spill - mov r13, rsi - or r13, 32 - mov qword ptr [rsp + 8], r13 # 8-byte Spill - or r14, 64 - mov qword ptr [rsp + 32], r14 # 8-byte Spill - or rbx, 96 - mov qword ptr [rsp + 88], rbx # 8-byte Spill - or rax, 128 - mov rbx, r11 - or rbx, 160 - mov r11, r10 - or r11, 192 - mov qword ptr [rsp + 96], r11 # 8-byte Spill - or r8, 224 - or r9, 256 - mov qword ptr [rsp + 80], r9 # 8-byte Spill - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - or rcx, 288 - or r12, 320 - or r15, 352 - mov qword ptr [rsp + 40], r15 # 8-byte Spill - mov r10, rdi - or r10, 384 - mov rdi, rsi - or rdi, 416 - mov qword ptr [rsp + 104], rdi # 8-byte Spill - mov rdi, rsi - or rdi, 448 - mov qword ptr [rsp + 16], rdi # 8-byte Spill - mov rdi, rsi - or rdi, 480 - mov qword ptr [rsp + 24], rdi # 8-byte Spill - pinsrb xmm5, byte ptr [rdx + r13 + 1], 1 - pinsrb xmm5, byte ptr [rdx + r14 + 1], 2 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r13 + 1], 3 - pinsrb xmm5, byte ptr [rdx + rax + 1], 4 - mov r14, rax - pinsrb xmm5, byte ptr [rdx + rbx + 1], 5 - pinsrb xmm5, byte ptr [rdx + r11 + 1], 6 - pinsrb xmm5, byte ptr [rdx + r8 + 1], 7 - pinsrb xmm5, byte ptr [rdx + r9 + 1], 8 - pinsrb xmm5, byte ptr [rdx + rcx + 1], 9 - pinsrb xmm5, byte ptr [rdx + r12 + 1], 10 - pinsrb xmm5, byte ptr [rdx + r15 + 1], 11 - pinsrb xmm5, byte ptr [rdx + r10 + 1], 12 - mov r9, r10 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r11 + 1], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 1], 14 - pinsrb xmm5, byte ptr [rdx + rdi + 1], 15 - movdqa xmm10, xmmword ptr [rsp + 288] # 16-byte Reload - pminub xmm5, xmm10 - pcmpeqb xmm5, xmm10 - movdqa xmm6, xmm5 - movdqa xmm1, xmmword ptr [rip + .LCPI8_10] # xmm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pandn xmm6, xmm1 - paddb xmm6, xmm5 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rsi + 15] - movd xmm0, esi - movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax], 1 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r10], 2 - pinsrb xmm9, byte ptr [rdx + r13], 3 - mov rsi, r14 - pinsrb xmm9, byte ptr [rdx + r14], 4 - mov r14, rbx - pinsrb xmm9, byte ptr [rdx + rbx], 5 - mov rbx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rbx], 6 - pinsrb xmm9, byte ptr [rdx + r8], 7 - mov r15, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r15], 8 - mov qword ptr [rsp + 64], rcx # 8-byte Spill - pinsrb xmm9, byte ptr [rdx + rcx], 9 - mov qword ptr [rsp + 72], r12 # 8-byte Spill - pinsrb xmm9, byte ptr [rdx + r12], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rdi], 11 - pinsrb xmm9, byte ptr [rdx + r9], 12 - pinsrb xmm9, byte ptr [rdx + r11], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax], 14 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r13], 15 - pminub xmm9, xmm10 - pcmpeqb xmm9, xmm10 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 2], 1 - pinsrb xmm7, byte ptr [rdx + r10 + 2], 2 - mov r13, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r13 + 2], 3 - pinsrb xmm7, byte ptr [rdx + rsi + 2], 4 - pinsrb xmm7, byte ptr [rdx + r14 + 2], 5 - pinsrb xmm7, byte ptr [rdx + rbx + 2], 6 - pinsrb xmm7, byte ptr [rdx + r8 + 2], 7 - pinsrb xmm7, byte ptr [rdx + r15 + 2], 8 - pinsrb xmm7, byte ptr [rdx + rcx + 2], 9 - pinsrb xmm7, byte ptr [rdx + r12 + 2], 10 - pinsrb xmm7, byte ptr [rdx + rdi + 2], 11 - pinsrb xmm7, byte ptr [rdx + r9 + 2], 12 - pinsrb xmm7, byte ptr [rdx + r11 + 2], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 2], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 2], 15 - movdqa xmm0, xmm15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 3], 1 - pinsrb xmm0, byte ptr [rdx + r10 + 3], 2 - pinsrb xmm0, byte ptr [rdx + r13 + 3], 3 - pinsrb xmm0, byte ptr [rdx + rsi + 3], 4 - pinsrb xmm0, byte ptr [rdx + r14 + 3], 5 - pinsrb xmm0, byte ptr [rdx + rbx + 3], 6 - pinsrb xmm0, byte ptr [rdx + r8 + 3], 7 - pinsrb xmm0, byte ptr [rdx + r15 + 3], 8 - pinsrb xmm0, byte ptr [rdx + rcx + 3], 9 - pinsrb xmm0, byte ptr [rdx + r12 + 3], 10 - pinsrb xmm0, byte ptr [rdx + rdi + 3], 11 - pinsrb xmm0, byte ptr [rdx + r9 + 3], 12 - pinsrb xmm0, byte ptr [rdx + r11 + 3], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 3], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 3], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rax + 4], 1 - pinsrb xmm3, byte ptr [rdx + r10 + 4], 2 - pinsrb xmm3, byte ptr [rdx + r13 + 4], 3 - pinsrb xmm3, byte ptr [rdx + rsi + 4], 4 - pinsrb xmm3, byte ptr [rdx + r14 + 4], 5 - pinsrb xmm3, byte ptr [rdx + rbx + 4], 6 - pinsrb xmm3, byte ptr [rdx + r8 + 4], 7 - pinsrb xmm3, byte ptr [rdx + r15 + 4], 8 - pinsrb xmm3, byte ptr [rdx + rcx + 4], 9 - pinsrb xmm3, byte ptr [rdx + r12 + 4], 10 - pinsrb xmm3, byte ptr [rdx + rdi + 4], 11 - pinsrb xmm3, byte ptr [rdx + r9 + 4], 12 - pinsrb xmm3, byte ptr [rdx + r11 + 4], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rax + 4], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rax + 4], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 5], 1 - pinsrb xmm2, byte ptr [rdx + r10 + 5], 2 - pinsrb xmm2, byte ptr [rdx + r13 + 5], 3 - pinsrb xmm2, byte ptr [rdx + rsi + 5], 4 - mov r10, rsi - mov qword ptr [rsp + 192], rsi # 8-byte Spill - pinsrb xmm2, byte ptr [rdx + r14 + 5], 5 - pinsrb xmm2, byte ptr [rdx + rbx + 5], 6 - pinsrb xmm2, byte ptr [rdx + r8 + 5], 7 - pinsrb xmm2, byte ptr [rdx + r15 + 5], 8 - pinsrb xmm2, byte ptr [rdx + rcx + 5], 9 - pinsrb xmm2, byte ptr [rdx + r12 + 5], 10 - pinsrb xmm2, byte ptr [rdx + rdi + 5], 11 - pinsrb xmm2, byte ptr [rdx + r9 + 5], 12 - pinsrb xmm2, byte ptr [rdx + r11 + 5], 13 - mov rdi, r11 - pandn xmm9, xmm1 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 5], 14 - pminub xmm7, xmm10 - pcmpeqb xmm7, xmm10 - movdqa xmm1, xmmword ptr [rip + .LCPI8_11] # xmm1 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm7, xmm1 - por xmm7, xmm9 - mov r12, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + r12 + 16] - movd xmm5, esi - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 5], 15 - pminub xmm0, xmm10 - pcmpeqb xmm0, xmm10 - movdqa xmm1, xmmword ptr [rip + .LCPI8_12] # xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm0, xmm1 - por xmm0, xmm7 - movzx esi, byte ptr [rdx + r12 + 17] - movd xmm1, esi - pcmpeqd xmm7, xmm7 - psubb xmm6, xmm7 - pcmpeqd xmm9, xmm9 - por xmm0, xmm6 - movzx esi, byte ptr [rdx + r12 + 18] - movd xmm7, esi - pminub xmm3, xmm10 - pcmpeqb xmm3, xmm10 - movdqa xmm6, xmmword ptr [rip + .LCPI8_13] # xmm6 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm3, xmm6 - pminub xmm2, xmm10 - pcmpeqb xmm2, xmm10 - movdqa xmm6, xmmword ptr [rip + .LCPI8_14] # xmm6 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm2, xmm6 - por xmm2, xmm3 - movzx esi, byte ptr [rdx + r12 + 19] - movd xmm15, esi - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rcx + 6], 1 - mov r11, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r11 + 6], 2 - pinsrb xmm8, byte ptr [rdx + r13 + 6], 3 - pinsrb xmm8, byte ptr [rdx + r10 + 6], 4 - mov qword ptr [rsp + 120], r14 # 8-byte Spill - pinsrb xmm8, byte ptr [rdx + r14 + 6], 5 - pinsrb xmm8, byte ptr [rdx + rbx + 6], 6 - mov qword ptr [rsp + 208], r8 # 8-byte Spill - pinsrb xmm8, byte ptr [rdx + r8 + 6], 7 - pinsrb xmm8, byte ptr [rdx + r15 + 6], 8 - mov r15, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r15 + 6], 9 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rax + 6], 10 - mov r10, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r10 + 6], 11 - pinsrb xmm8, byte ptr [rdx + r9 + 6], 12 - pinsrb xmm8, byte ptr [rdx + rdi + 6], 13 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rbx + 6], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rax + 6], 15 - pminub xmm8, xmm10 - pcmpeqb xmm8, xmm10 - movdqa xmm3, xmmword ptr [rip + .LCPI8_15] # xmm3 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm8, xmm3 - por xmm8, xmm2 - movzx esi, byte ptr [rdx + r12 + 20] - movd xmm4, esi - movdqa xmm6, xmmword ptr [rsp + 160] # 16-byte Reload - pinsrb xmm6, byte ptr [rdx + rcx + 7], 1 - pinsrb xmm6, byte ptr [rdx + r11 + 7], 2 - pinsrb xmm6, byte ptr [rdx + r13 + 7], 3 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rcx + 7], 4 - pinsrb xmm6, byte ptr [rdx + r14 + 7], 5 - mov r14, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r14 + 7], 6 - pinsrb xmm6, byte ptr [rdx + r8 + 7], 7 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r12 + 7], 8 - pinsrb xmm6, byte ptr [rdx + r15 + 7], 9 - mov r8, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r8 + 7], 10 - pinsrb xmm6, byte ptr [rdx + r10 + 7], 11 - pinsrb xmm6, byte ptr [rdx + r9 + 7], 12 - pinsrb xmm6, byte ptr [rdx + rdi + 7], 13 - mov r15, rdi - pinsrb xmm6, byte ptr [rdx + rbx + 7], 14 - pinsrb xmm6, byte ptr [rdx + rax + 7], 15 - pminub xmm6, xmm10 - pcmpeqb xmm6, xmm10 - pxor xmm6, xmm9 - pcmpeqd xmm3, xmm3 - psllw xmm6, 7 - movdqa xmm2, xmmword ptr [rip + .LCPI8_6] # xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm6, xmm2 - por xmm6, xmm8 - movdqa xmm8, xmm6 - mov rax, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 21] - movd xmm6, esi - movdqa xmm2, xmmword ptr [rsp + 272] # 16-byte Reload - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 8], 1 - mov rax, r11 - pinsrb xmm2, byte ptr [rdx + r11 + 8], 2 - mov rdi, r13 - pinsrb xmm2, byte ptr [rdx + r13 + 8], 3 - mov r10, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r10 + 8], 4 - mov r11, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r11 + 8], 5 - mov r13, r14 - pinsrb xmm2, byte ptr [rdx + r14 + 8], 6 - mov rsi, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rsi + 8], 7 - mov r14, r12 - pinsrb xmm2, byte ptr [rdx + r12 + 8], 8 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rbx + 8], 9 - mov r12, r8 - pinsrb xmm2, byte ptr [rdx + r8 + 8], 10 - mov rbx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rbx + 8], 11 - mov qword ptr [rsp + 112], r9 # 8-byte Spill - pinsrb xmm2, byte ptr [rdx + r9 + 8], 12 - mov r8, r15 - pinsrb xmm2, byte ptr [rdx + r15 + 8], 13 - mov r15, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r15 + 8], 14 - pinsrb xmm11, byte ptr [rdx + rcx + 9], 1 - pinsrb xmm11, byte ptr [rdx + rax + 9], 2 - pinsrb xmm11, byte ptr [rdx + rdi + 9], 3 - pinsrb xmm11, byte ptr [rdx + r10 + 9], 4 - mov rbx, r10 - pinsrb xmm11, byte ptr [rdx + r11 + 9], 5 - mov rdi, r11 - pinsrb xmm11, byte ptr [rdx + r13 + 9], 6 - mov r10, r13 - pinsrb xmm11, byte ptr [rdx + rsi + 9], 7 - pinsrb xmm11, byte ptr [rdx + r14 + 9], 8 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rax + 9], 9 - pinsrb xmm11, byte ptr [rdx + r12 + 9], 10 - mov r11, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r11 + 9], 11 - pinsrb xmm11, byte ptr [rdx + r9 + 9], 12 - pinsrb xmm11, byte ptr [rdx + r8 + 9], 13 - mov r13, r8 - mov r8, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r8 + 9], 14 - mov r15, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r15 + 9], 15 - por xmm8, xmm0 - movdqa xmmword ptr [rsp + 160], xmm8 # 16-byte Spill - pminub xmm11, xmm10 - pcmpeqb xmm11, xmm10 - movdqa xmm0, xmm11 - movdqa xmm8, xmmword ptr [rip + .LCPI8_10] # xmm8 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pandn xmm0, xmm8 - paddb xmm0, xmm11 - mov r9, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + r9 + 22] - movd xmm9, esi - pinsrb xmm2, byte ptr [rdx + r15 + 8], 15 - pminub xmm2, xmm10 - pcmpeqb xmm2, xmm10 - pandn xmm2, xmm8 - pinsrb xmm12, byte ptr [rdx + rcx + 10], 1 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rcx + 10], 2 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rcx + 10], 3 - pinsrb xmm12, byte ptr [rdx + rbx + 10], 4 - pinsrb xmm12, byte ptr [rdx + rdi + 10], 5 - pinsrb xmm12, byte ptr [rdx + r10 + 10], 6 - mov rbx, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rbx + 10], 7 - pinsrb xmm12, byte ptr [rdx + r14 + 10], 8 - pinsrb xmm12, byte ptr [rdx + rax + 10], 9 - mov r14, rax - pinsrb xmm12, byte ptr [rdx + r12 + 10], 10 - pinsrb xmm12, byte ptr [rdx + r11 + 10], 11 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rax + 10], 12 - pinsrb xmm12, byte ptr [rdx + r13 + 10], 13 - pinsrb xmm12, byte ptr [rdx + r8 + 10], 14 - pinsrb xmm12, byte ptr [rdx + r15 + 10], 15 - mov r12, r15 - pminub xmm12, xmm10 - pcmpeqb xmm12, xmm10 - pandn xmm12, xmmword ptr [rip + .LCPI8_11] - por xmm12, xmm2 + mov r8, r12 + sub r8, rcx + jle .LBB8_215 +# %bb.165: + or rcx, 1 + cmp r12, rcx + jne .LBB8_180 +# %bb.166: + xor r9d, r9d + jmp .LBB8_183 +.LBB8_167: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB8_168: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rdx], r13 + sbb edi, edi + mov rsi, r11 + shr rsi, 3 + movzx r10d, byte ptr [r14 + rsi] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r14 + rsi], al + add r11, 2 + cmp qword ptr [rdx + 8], r13 + lea rdx, [rdx + 16] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r14 + rsi], bl + cmp r9, r11 + jne .LBB8_168 +.LBB8_169: + test r8b, 1 + je .LBB8_215 +# %bb.170: + cmp qword ptr [rdx], r13 + jmp .LBB8_197 +.LBB8_171: + mov r10, r8 + and r10, -2 + xor edi, edi + .p2align 4, 0x90 +.LBB8_172: # =>This Inner Loop Header: Depth=1 + cmp r13d, dword ptr [rdx] + setg al + neg al + mov rsi, rdi + shr rsi, 3 + movzx r9d, byte ptr [r14 + rsi] + mov ecx, edi + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rsi], bl + add rdi, 2 + cmp r13d, dword ptr [rdx + 4] + lea rdx, [rdx + 8] + setg r9b + neg r9b + xor r9b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r9b + xor al, bl + mov byte ptr [r14 + rsi], al + cmp r10, rdi + jne .LBB8_172 +.LBB8_173: + test r8b, 1 + je .LBB8_215 +# %bb.174: + cmp r13d, dword ptr [rdx] + jmp .LBB8_202 +.LBB8_175: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 104] # 8-byte Reload + .p2align 4, 0x90 +.LBB8_176: # =>This Inner Loop Header: Depth=1 mov rax, r9 - movzx esi, byte ptr [rdx + r9 + 23] - movd xmm8, esi - movdqa xmm2, xmmword ptr [rsp + 144] # 16-byte Reload - mov r8, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r8 + 11], 1 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r15 + 11], 2 - pinsrb xmm2, byte ptr [rdx + rcx + 11], 3 - mov r11, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r11 + 11], 4 - pinsrb xmm2, byte ptr [rdx + rdi + 11], 5 - pinsrb xmm2, byte ptr [rdx + r10 + 11], 6 - pinsrb xmm2, byte ptr [rdx + rbx + 11], 7 - mov rsi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rsi + 11], 8 - pinsrb xmm2, byte ptr [rdx + r14 + 11], 9 - mov r14, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r14 + 11], 10 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rdi + 11], 11 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r9 + 11], 12 - pinsrb xmm2, byte ptr [rdx + r13 + 11], 13 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rsi + 11], 14 - pinsrb xmm2, byte ptr [rdx + r12 + 11], 15 - mov r13, r12 - pminub xmm2, xmm10 - pcmpeqb xmm2, xmm10 - pandn xmm2, xmmword ptr [rip + .LCPI8_12] - por xmm2, xmm12 - movzx esi, byte ptr [rdx + rax + 24] - movd xmm11, esi - psubb xmm0, xmm3 - por xmm2, xmm0 - movdqa xmmword ptr [rsp + 144], xmm2 # 16-byte Spill - movzx esi, byte ptr [rdx + rax + 25] - movd xmm3, esi - movdqa xmm2, xmmword ptr [rsp + 304] # 16-byte Reload - pinsrb xmm2, byte ptr [rdx + r8 + 12], 1 - pinsrb xmm2, byte ptr [rdx + r15 + 12], 2 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r8 + 12], 3 - mov r10, r11 - pinsrb xmm2, byte ptr [rdx + r11 + 12], 4 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rsi + 12], 5 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r15 + 12], 6 - pinsrb xmm2, byte ptr [rdx + rbx + 12], 7 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r11 + 12], 8 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 12], 9 - pinsrb xmm2, byte ptr [rdx + r14 + 12], 10 - pinsrb xmm2, byte ptr [rdx + rdi + 12], 11 - pinsrb xmm2, byte ptr [rdx + r9 + 12], 12 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r12 + 12], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 12], 14 - pinsrb xmm2, byte ptr [rdx + r13 + 12], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rax + 13], 1 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + r13 + 13], 2 - pinsrb xmm14, byte ptr [rdx + r8 + 13], 3 - pinsrb xmm14, byte ptr [rdx + r10 + 13], 4 - pinsrb xmm14, byte ptr [rdx + rsi + 13], 5 - pinsrb xmm14, byte ptr [rdx + r15 + 13], 6 - pinsrb xmm14, byte ptr [rdx + rbx + 13], 7 - pinsrb xmm14, byte ptr [rdx + r11 + 13], 8 - pinsrb xmm14, byte ptr [rdx + rcx + 13], 9 - pinsrb xmm14, byte ptr [rdx + r14 + 13], 10 - pinsrb xmm14, byte ptr [rdx + rdi + 13], 11 - pinsrb xmm14, byte ptr [rdx + r9 + 13], 12 - pinsrb xmm14, byte ptr [rdx + r12 + 13], 13 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + r13 + 13], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rax + 13], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rax + 14], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rax + 14], 2 - pinsrb xmm13, byte ptr [rdx + r8 + 14], 3 - pinsrb xmm13, byte ptr [rdx + r10 + 14], 4 - pinsrb xmm13, byte ptr [rdx + rsi + 14], 5 - pinsrb xmm13, byte ptr [rdx + r15 + 14], 6 - pinsrb xmm13, byte ptr [rdx + rbx + 14], 7 - pinsrb xmm13, byte ptr [rdx + r11 + 14], 8 - pinsrb xmm13, byte ptr [rdx + rcx + 14], 9 - pinsrb xmm13, byte ptr [rdx + r14 + 14], 10 - pinsrb xmm13, byte ptr [rdx + rdi + 14], 11 - pinsrb xmm13, byte ptr [rdx + r9 + 14], 12 - pinsrb xmm13, byte ptr [rdx + r12 + 14], 13 - pinsrb xmm13, byte ptr [rdx + r13 + 14], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rax + 14], 15 - movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 15], 1 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r13 + 15], 2 - pinsrb xmm0, byte ptr [rdx + r8 + 15], 3 - pinsrb xmm0, byte ptr [rdx + r10 + 15], 4 - pinsrb xmm0, byte ptr [rdx + rsi + 15], 5 - pinsrb xmm0, byte ptr [rdx + r15 + 15], 6 - pinsrb xmm0, byte ptr [rdx + rbx + 15], 7 - pinsrb xmm0, byte ptr [rdx + r11 + 15], 8 - pinsrb xmm0, byte ptr [rdx + rcx + 15], 9 - pinsrb xmm0, byte ptr [rdx + r14 + 15], 10 - pinsrb xmm0, byte ptr [rdx + rdi + 15], 11 - pinsrb xmm0, byte ptr [rdx + r9 + 15], 12 - pinsrb xmm0, byte ptr [rdx + r12 + 15], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 15], 14 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 15], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rax + 17], 1 - pinsrb xmm1, byte ptr [rdx + r13 + 17], 2 - pinsrb xmm1, byte ptr [rdx + r8 + 17], 3 - pinsrb xmm1, byte ptr [rdx + r10 + 17], 4 - pinsrb xmm1, byte ptr [rdx + rsi + 17], 5 - pinsrb xmm1, byte ptr [rdx + r15 + 17], 6 - pinsrb xmm1, byte ptr [rdx + rbx + 17], 7 - pinsrb xmm1, byte ptr [rdx + r11 + 17], 8 - pinsrb xmm1, byte ptr [rdx + rcx + 17], 9 - pinsrb xmm1, byte ptr [rdx + r14 + 17], 10 - pinsrb xmm1, byte ptr [rdx + rdi + 17], 11 - mov r14, rdi - pinsrb xmm1, byte ptr [rdx + r9 + 17], 12 - pinsrb xmm1, byte ptr [rdx + r12 + 17], 13 - pminub xmm2, xmm10 - pcmpeqb xmm2, xmm10 - pandn xmm2, xmmword ptr [rip + .LCPI8_13] - pminub xmm14, xmm10 - pcmpeqb xmm14, xmm10 - pandn xmm14, xmmword ptr [rip + .LCPI8_14] - por xmm14, xmm2 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - movzx esi, byte ptr [rdx + rdi + 26] - movd xmm2, esi - mov r9, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r9 + 17], 14 - pminub xmm13, xmm10 - pcmpeqb xmm13, xmm10 - pandn xmm13, xmmword ptr [rip + .LCPI8_15] - por xmm13, xmm14 - movzx esi, byte ptr [rdx + rdi + 27] - movd xmm12, esi - pminub xmm0, xmm10 - pcmpeqb xmm0, xmm10 - pxor xmm0, xmmword ptr [rip + .LCPI8_16] - psllw xmm0, 7 - pand xmm0, xmmword ptr [rip + .LCPI8_6] - por xmm0, xmm13 - movzx esi, byte ptr [rdx + rdi + 28] - movd xmm13, esi - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r13 + 17], 15 - por xmm0, xmmword ptr [rsp + 144] # 16-byte Folded Reload - movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill - pminub xmm1, xmm10 - pcmpeqb xmm1, xmm10 - movdqa xmm0, xmm10 - movdqa xmm14, xmm1 - movdqa xmm10, xmmword ptr [rip + .LCPI8_10] # xmm10 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pandn xmm14, xmm10 - paddb xmm14, xmm1 - movdqa xmmword ptr [rsp + 144], xmm14 # 16-byte Spill - movzx esi, byte ptr [rdx + rdi + 29] - movd xmm10, esi - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 16], 1 - pinsrb xmm7, byte ptr [rdx + rax + 18], 1 - pinsrb xmm15, byte ptr [rdx + rax + 19], 1 - pinsrb xmm4, byte ptr [rdx + rax + 20], 1 - pinsrb xmm6, byte ptr [rdx + rax + 21], 1 - pinsrb xmm9, byte ptr [rdx + rax + 22], 1 - pinsrb xmm8, byte ptr [rdx + rax + 23], 1 - pinsrb xmm11, byte ptr [rdx + rax + 24], 1 - pinsrb xmm3, byte ptr [rdx + rax + 25], 1 - pinsrb xmm2, byte ptr [rdx + rax + 26], 1 - pinsrb xmm12, byte ptr [rdx + rax + 27], 1 - pinsrb xmm13, byte ptr [rdx + rax + 28], 1 - pinsrb xmm10, byte ptr [rdx + rax + 29], 1 - movzx esi, byte ptr [rdx + rdi + 30] - movd xmm14, esi - pinsrb xmm14, byte ptr [rdx + rax + 30], 1 - movzx esi, byte ptr [rdx + rdi + 31] - movd xmm1, esi - pinsrb xmm1, byte ptr [rdx + rax + 31], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 16], 2 - pinsrb xmm7, byte ptr [rdx + rax + 18], 2 - pinsrb xmm15, byte ptr [rdx + rax + 19], 2 - pinsrb xmm4, byte ptr [rdx + rax + 20], 2 - pinsrb xmm6, byte ptr [rdx + rax + 21], 2 - pinsrb xmm9, byte ptr [rdx + rax + 22], 2 - pinsrb xmm8, byte ptr [rdx + rax + 23], 2 - pinsrb xmm11, byte ptr [rdx + rax + 24], 2 - pinsrb xmm3, byte ptr [rdx + rax + 25], 2 - pinsrb xmm2, byte ptr [rdx + rax + 26], 2 - pinsrb xmm12, byte ptr [rdx + rax + 27], 2 - pinsrb xmm13, byte ptr [rdx + rax + 28], 2 - pinsrb xmm10, byte ptr [rdx + rax + 29], 2 - pinsrb xmm14, byte ptr [rdx + rax + 30], 2 - pinsrb xmm1, byte ptr [rdx + rax + 31], 2 - pinsrb xmm5, byte ptr [rdx + r8 + 16], 3 - pinsrb xmm5, byte ptr [rdx + r10 + 16], 4 - mov rsi, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 16], 5 - pinsrb xmm5, byte ptr [rdx + r15 + 16], 6 - pinsrb xmm5, byte ptr [rdx + rbx + 16], 7 - pinsrb xmm5, byte ptr [rdx + r11 + 16], 8 - pinsrb xmm5, byte ptr [rdx + rcx + 16], 9 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 16], 10 - pinsrb xmm5, byte ptr [rdx + r14 + 16], 11 - mov r12, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r12 + 16], 12 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rdi + 16], 13 - pinsrb xmm5, byte ptr [rdx + r9 + 16], 14 - pinsrb xmm5, byte ptr [rdx + r13 + 16], 15 - pminub xmm5, xmm0 - pcmpeqb xmm5, xmm0 - pinsrb xmm7, byte ptr [rdx + r8 + 18], 3 - pinsrb xmm7, byte ptr [rdx + r10 + 18], 4 - pinsrb xmm7, byte ptr [rdx + rsi + 18], 5 - pinsrb xmm7, byte ptr [rdx + r15 + 18], 6 - pinsrb xmm7, byte ptr [rdx + rbx + 18], 7 - pinsrb xmm7, byte ptr [rdx + r11 + 18], 8 - pinsrb xmm7, byte ptr [rdx + rcx + 18], 9 - pinsrb xmm7, byte ptr [rdx + rax + 18], 10 - pinsrb xmm7, byte ptr [rdx + r14 + 18], 11 - pinsrb xmm7, byte ptr [rdx + r12 + 18], 12 - pinsrb xmm7, byte ptr [rdx + rdi + 18], 13 - pinsrb xmm7, byte ptr [rdx + r9 + 18], 14 - pinsrb xmm7, byte ptr [rdx + r13 + 18], 15 - pinsrb xmm15, byte ptr [rdx + r8 + 19], 3 - pinsrb xmm15, byte ptr [rdx + r10 + 19], 4 - pinsrb xmm15, byte ptr [rdx + rsi + 19], 5 - pinsrb xmm15, byte ptr [rdx + r15 + 19], 6 - pinsrb xmm15, byte ptr [rdx + rbx + 19], 7 - pinsrb xmm15, byte ptr [rdx + r11 + 19], 8 - pinsrb xmm15, byte ptr [rdx + rcx + 19], 9 - pinsrb xmm15, byte ptr [rdx + rax + 19], 10 - pinsrb xmm15, byte ptr [rdx + r14 + 19], 11 - pinsrb xmm15, byte ptr [rdx + r12 + 19], 12 - pinsrb xmm15, byte ptr [rdx + rdi + 19], 13 - pinsrb xmm15, byte ptr [rdx + r9 + 19], 14 - pinsrb xmm15, byte ptr [rdx + r13 + 19], 15 - pinsrb xmm4, byte ptr [rdx + r8 + 20], 3 - pinsrb xmm4, byte ptr [rdx + r10 + 20], 4 - pinsrb xmm4, byte ptr [rdx + rsi + 20], 5 - pinsrb xmm4, byte ptr [rdx + r15 + 20], 6 - pinsrb xmm4, byte ptr [rdx + rbx + 20], 7 - pinsrb xmm4, byte ptr [rdx + r11 + 20], 8 - pinsrb xmm4, byte ptr [rdx + rcx + 20], 9 - pinsrb xmm4, byte ptr [rdx + rax + 20], 10 - pinsrb xmm4, byte ptr [rdx + r14 + 20], 11 - pinsrb xmm4, byte ptr [rdx + r12 + 20], 12 - pinsrb xmm4, byte ptr [rdx + rdi + 20], 13 - pinsrb xmm4, byte ptr [rdx + r9 + 20], 14 - pinsrb xmm4, byte ptr [rdx + r13 + 20], 15 - pinsrb xmm6, byte ptr [rdx + r8 + 21], 3 - pinsrb xmm6, byte ptr [rdx + r10 + 21], 4 - mov rax, r10 - pinsrb xmm6, byte ptr [rdx + rsi + 21], 5 - pinsrb xmm6, byte ptr [rdx + r15 + 21], 6 - pinsrb xmm6, byte ptr [rdx + rbx + 21], 7 - pinsrb xmm6, byte ptr [rdx + r11 + 21], 8 - pinsrb xmm6, byte ptr [rdx + rcx + 21], 9 - mov r10, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r10 + 21], 10 - pinsrb xmm6, byte ptr [rdx + r14 + 21], 11 - pinsrb xmm6, byte ptr [rdx + r12 + 21], 12 - pinsrb xmm6, byte ptr [rdx + rdi + 21], 13 - pinsrb xmm6, byte ptr [rdx + r9 + 21], 14 - pandn xmm5, xmmword ptr [rip + .LCPI8_10] - pminub xmm7, xmm0 - pcmpeqb xmm7, xmm0 - pandn xmm7, xmmword ptr [rip + .LCPI8_11] - por xmm7, xmm5 - pminub xmm15, xmm0 - pcmpeqb xmm15, xmm0 - movdqa xmm5, xmmword ptr [rip + .LCPI8_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm15, xmm5 - por xmm15, xmm7 - pinsrb xmm6, byte ptr [rdx + r13 + 21], 15 - pcmpeqd xmm5, xmm5 - movdqa xmm7, xmmword ptr [rsp + 144] # 16-byte Reload - psubb xmm7, xmm5 - por xmm15, xmm7 - pminub xmm4, xmm0 - pcmpeqb xmm4, xmm0 - movdqa xmm7, xmmword ptr [rip + .LCPI8_13] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm4, xmm7 - pminub xmm6, xmm0 - pcmpeqb xmm6, xmm0 - movdqa xmm7, xmmword ptr [rip + .LCPI8_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm6, xmm7 - por xmm6, xmm4 - pinsrb xmm9, byte ptr [rdx + r8 + 22], 3 - pinsrb xmm9, byte ptr [rdx + rax + 22], 4 - pinsrb xmm9, byte ptr [rdx + rsi + 22], 5 - pinsrb xmm9, byte ptr [rdx + r15 + 22], 6 - pinsrb xmm9, byte ptr [rdx + rbx + 22], 7 - pinsrb xmm9, byte ptr [rdx + r11 + 22], 8 - pinsrb xmm9, byte ptr [rdx + rcx + 22], 9 - pinsrb xmm9, byte ptr [rdx + r10 + 22], 10 - pinsrb xmm9, byte ptr [rdx + r14 + 22], 11 - pinsrb xmm9, byte ptr [rdx + r12 + 22], 12 - pinsrb xmm9, byte ptr [rdx + rdi + 22], 13 - pinsrb xmm9, byte ptr [rdx + r9 + 22], 14 - pinsrb xmm9, byte ptr [rdx + r13 + 22], 15 - pminub xmm9, xmm0 - pcmpeqb xmm9, xmm0 - movdqa xmm7, xmmword ptr [rip + .LCPI8_15] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm9, xmm7 - por xmm9, xmm6 - pinsrb xmm8, byte ptr [rdx + r8 + 23], 3 - pinsrb xmm8, byte ptr [rdx + rax + 23], 4 - pinsrb xmm8, byte ptr [rdx + rsi + 23], 5 - pinsrb xmm8, byte ptr [rdx + r15 + 23], 6 - pinsrb xmm8, byte ptr [rdx + rbx + 23], 7 - pinsrb xmm8, byte ptr [rdx + r11 + 23], 8 - pinsrb xmm8, byte ptr [rdx + rcx + 23], 9 - pinsrb xmm8, byte ptr [rdx + r10 + 23], 10 - pinsrb xmm8, byte ptr [rdx + r14 + 23], 11 - pinsrb xmm8, byte ptr [rdx + r12 + 23], 12 - pinsrb xmm8, byte ptr [rdx + rdi + 23], 13 - pinsrb xmm8, byte ptr [rdx + r9 + 23], 14 - pinsrb xmm8, byte ptr [rdx + r13 + 23], 15 - pminub xmm8, xmm0 - pcmpeqb xmm8, xmm0 - pxor xmm8, xmm5 - pcmpeqd xmm5, xmm5 - psllw xmm8, 7 - movdqa xmm6, xmmword ptr [rip + .LCPI8_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm8, xmm6 - por xmm8, xmm9 - pinsrb xmm11, byte ptr [rdx + r8 + 24], 3 - pinsrb xmm11, byte ptr [rdx + rax + 24], 4 - pinsrb xmm11, byte ptr [rdx + rsi + 24], 5 - pinsrb xmm11, byte ptr [rdx + r15 + 24], 6 - pinsrb xmm11, byte ptr [rdx + rbx + 24], 7 - pinsrb xmm11, byte ptr [rdx + r11 + 24], 8 - pinsrb xmm11, byte ptr [rdx + rcx + 24], 9 - pinsrb xmm11, byte ptr [rdx + r10 + 24], 10 - pinsrb xmm11, byte ptr [rdx + r14 + 24], 11 - pinsrb xmm11, byte ptr [rdx + r12 + 24], 12 - pinsrb xmm11, byte ptr [rdx + rdi + 24], 13 - pinsrb xmm11, byte ptr [rdx + r9 + 24], 14 - pinsrb xmm3, byte ptr [rdx + r8 + 25], 3 - pinsrb xmm3, byte ptr [rdx + rax + 25], 4 - pinsrb xmm3, byte ptr [rdx + rsi + 25], 5 - pinsrb xmm3, byte ptr [rdx + r15 + 25], 6 - pinsrb xmm3, byte ptr [rdx + rbx + 25], 7 - pinsrb xmm3, byte ptr [rdx + r11 + 25], 8 - pinsrb xmm3, byte ptr [rdx + rcx + 25], 9 - pinsrb xmm3, byte ptr [rdx + r10 + 25], 10 - pinsrb xmm3, byte ptr [rdx + r14 + 25], 11 - pinsrb xmm3, byte ptr [rdx + r12 + 25], 12 - pinsrb xmm3, byte ptr [rdx + rdi + 25], 13 - pinsrb xmm3, byte ptr [rdx + r9 + 25], 14 - pinsrb xmm3, byte ptr [rdx + r13 + 25], 15 - por xmm8, xmm15 - movdqa xmm4, xmm0 - pminub xmm3, xmm0 - pcmpeqb xmm3, xmm0 - movdqa xmm0, xmm3 - movdqa xmm9, xmmword ptr [rip + .LCPI8_10] # xmm9 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] - pandn xmm0, xmm9 - paddb xmm0, xmm3 - pinsrb xmm11, byte ptr [rdx + r13 + 24], 15 - pminub xmm11, xmm4 - pcmpeqb xmm11, xmm4 - pandn xmm11, xmm9 - pinsrb xmm2, byte ptr [rdx + r8 + 26], 3 - pinsrb xmm2, byte ptr [rdx + rax + 26], 4 - pinsrb xmm2, byte ptr [rdx + rsi + 26], 5 - pinsrb xmm2, byte ptr [rdx + r15 + 26], 6 - pinsrb xmm2, byte ptr [rdx + rbx + 26], 7 - pinsrb xmm2, byte ptr [rdx + r11 + 26], 8 - pinsrb xmm2, byte ptr [rdx + rcx + 26], 9 - pinsrb xmm2, byte ptr [rdx + r10 + 26], 10 - pinsrb xmm2, byte ptr [rdx + r14 + 26], 11 - pinsrb xmm2, byte ptr [rdx + r12 + 26], 12 - pinsrb xmm2, byte ptr [rdx + rdi + 26], 13 - pinsrb xmm2, byte ptr [rdx + r9 + 26], 14 - pinsrb xmm2, byte ptr [rdx + r13 + 26], 15 - pminub xmm2, xmm4 - pcmpeqb xmm2, xmm4 - pandn xmm2, xmmword ptr [rip + .LCPI8_11] - por xmm2, xmm11 - pinsrb xmm12, byte ptr [rdx + r8 + 27], 3 - pinsrb xmm12, byte ptr [rdx + rax + 27], 4 - pinsrb xmm12, byte ptr [rdx + rsi + 27], 5 - pinsrb xmm12, byte ptr [rdx + r15 + 27], 6 - pinsrb xmm12, byte ptr [rdx + rbx + 27], 7 - pinsrb xmm12, byte ptr [rdx + r11 + 27], 8 - pinsrb xmm12, byte ptr [rdx + rcx + 27], 9 - pinsrb xmm12, byte ptr [rdx + r10 + 27], 10 - pinsrb xmm12, byte ptr [rdx + r14 + 27], 11 - pinsrb xmm12, byte ptr [rdx + r12 + 27], 12 - pinsrb xmm12, byte ptr [rdx + rdi + 27], 13 - pinsrb xmm12, byte ptr [rdx + r9 + 27], 14 - pinsrb xmm12, byte ptr [rdx + r13 + 27], 15 - pminub xmm12, xmm4 - pcmpeqb xmm12, xmm4 - movdqa xmm3, xmm4 - pandn xmm12, xmmword ptr [rip + .LCPI8_12] - por xmm12, xmm2 - psubb xmm0, xmm5 - por xmm12, xmm0 - pinsrb xmm13, byte ptr [rdx + r8 + 28], 3 - pinsrb xmm10, byte ptr [rdx + r8 + 29], 3 - pinsrb xmm14, byte ptr [rdx + r8 + 30], 3 - pinsrb xmm1, byte ptr [rdx + r8 + 31], 3 - pinsrb xmm13, byte ptr [rdx + rax + 28], 4 - pinsrb xmm10, byte ptr [rdx + rax + 29], 4 - pinsrb xmm14, byte ptr [rdx + rax + 30], 4 - pinsrb xmm1, byte ptr [rdx + rax + 31], 4 - pinsrb xmm13, byte ptr [rdx + rsi + 28], 5 - pinsrb xmm10, byte ptr [rdx + rsi + 29], 5 - pinsrb xmm14, byte ptr [rdx + rsi + 30], 5 - pinsrb xmm1, byte ptr [rdx + rsi + 31], 5 - pinsrb xmm13, byte ptr [rdx + r15 + 28], 6 - pinsrb xmm10, byte ptr [rdx + r15 + 29], 6 - pinsrb xmm14, byte ptr [rdx + r15 + 30], 6 - pinsrb xmm1, byte ptr [rdx + r15 + 31], 6 - mov r14, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rbx + 28], 7 - pinsrb xmm10, byte ptr [rdx + rbx + 29], 7 - pinsrb xmm14, byte ptr [rdx + rbx + 30], 7 - pinsrb xmm1, byte ptr [rdx + rbx + 31], 7 - pinsrb xmm13, byte ptr [rdx + r11 + 28], 8 - pinsrb xmm10, byte ptr [rdx + r11 + 29], 8 - pinsrb xmm14, byte ptr [rdx + r11 + 30], 8 - pinsrb xmm1, byte ptr [rdx + r11 + 31], 8 - pinsrb xmm13, byte ptr [rdx + rcx + 28], 9 - pinsrb xmm10, byte ptr [rdx + rcx + 29], 9 - pinsrb xmm14, byte ptr [rdx + rcx + 30], 9 - pinsrb xmm1, byte ptr [rdx + rcx + 31], 9 - mov rax, r10 - pinsrb xmm13, byte ptr [rdx + r10 + 28], 10 - pinsrb xmm10, byte ptr [rdx + r10 + 29], 10 - pinsrb xmm14, byte ptr [rdx + r10 + 30], 10 - pinsrb xmm1, byte ptr [rdx + r10 + 31], 10 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rax + 28], 11 - pinsrb xmm10, byte ptr [rdx + rax + 29], 11 - pinsrb xmm14, byte ptr [rdx + rax + 30], 11 - pinsrb xmm1, byte ptr [rdx + rax + 31], 11 - mov rax, r12 - pinsrb xmm13, byte ptr [rdx + r12 + 28], 12 - pinsrb xmm10, byte ptr [rdx + r12 + 29], 12 - pinsrb xmm14, byte ptr [rdx + r12 + 30], 12 - pinsrb xmm1, byte ptr [rdx + r12 + 31], 12 - pinsrb xmm13, byte ptr [rdx + rdi + 28], 13 - pinsrb xmm10, byte ptr [rdx + rdi + 29], 13 - pinsrb xmm14, byte ptr [rdx + rdi + 30], 13 - pinsrb xmm1, byte ptr [rdx + rdi + 31], 13 - pinsrb xmm13, byte ptr [rdx + r9 + 28], 14 - pinsrb xmm10, byte ptr [rdx + r9 + 29], 14 - pinsrb xmm14, byte ptr [rdx + r9 + 30], 14 - pinsrb xmm1, byte ptr [rdx + r9 + 31], 14 - mov rax, r13 - pinsrb xmm13, byte ptr [rdx + r13 + 28], 15 - pinsrb xmm10, byte ptr [rdx + r13 + 29], 15 - pinsrb xmm14, byte ptr [rdx + r13 + 30], 15 - movdqa xmm0, xmm4 - pminub xmm13, xmm4 - pcmpeqb xmm13, xmm4 - pandn xmm13, xmmword ptr [rip + .LCPI8_13] - pminub xmm10, xmm4 - pcmpeqb xmm10, xmm4 - pandn xmm10, xmmword ptr [rip + .LCPI8_14] - por xmm10, xmm13 - pinsrb xmm1, byte ptr [rdx + r13 + 31], 15 - pminub xmm14, xmm4 - pcmpeqb xmm14, xmm4 - pandn xmm14, xmm7 - por xmm14, xmm10 - pminub xmm1, xmm4 - pcmpeqb xmm1, xmm4 - pxor xmm1, xmm5 - psllw xmm1, 7 - pand xmm1, xmm6 - por xmm1, xmm14 - por xmm1, xmm12 - movdqa xmm0, xmm8 - punpcklbw xmm0, xmm1 # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7] - movdqa xmm4, xmmword ptr [rsp + 160] # 16-byte Reload - movdqa xmm2, xmm4 - movdqa xmm5, xmmword ptr [rsp + 176] # 16-byte Reload - punpcklbw xmm2, xmm5 # xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1],xmm2[2],xmm5[2],xmm2[3],xmm5[3],xmm2[4],xmm5[4],xmm2[5],xmm5[5],xmm2[6],xmm5[6],xmm2[7],xmm5[7] - movdqa xmm3, xmm2 - punpcklwd xmm3, xmm0 # xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3] - punpckhwd xmm2, xmm0 # xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7] - punpckhbw xmm8, xmm1 # xmm8 = xmm8[8],xmm1[8],xmm8[9],xmm1[9],xmm8[10],xmm1[10],xmm8[11],xmm1[11],xmm8[12],xmm1[12],xmm8[13],xmm1[13],xmm8[14],xmm1[14],xmm8[15],xmm1[15] - punpckhbw xmm4, xmm5 # xmm4 = xmm4[8],xmm5[8],xmm4[9],xmm5[9],xmm4[10],xmm5[10],xmm4[11],xmm5[11],xmm4[12],xmm5[12],xmm4[13],xmm5[13],xmm4[14],xmm5[14],xmm4[15],xmm5[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] - punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] - mov rcx, qword ptr [rsp + 240] # 8-byte Reload - movdqu xmmword ptr [r14 + 4*rcx + 48], xmm4 - movdqu xmmword ptr [r14 + 4*rcx + 32], xmm0 - movdqu xmmword ptr [r14 + 4*rcx + 16], xmm2 - movdqu xmmword ptr [r14 + 4*rcx], xmm3 - add rcx, 16 + cmp r15b, byte ptr [rsi + r9] + setg bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp r15b, byte ptr [rsi + rax + 1] + lea r9, [rax + 2] + setg bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB8_176 +# %bb.177: + add rsi, r9 +.LBB8_178: + test r8b, 1 + je .LBB8_215 +# %bb.179: + cmp r15b, byte ptr [rsi] + setg al + neg al + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 104] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + jmp .LBB8_209 +.LBB8_180: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 48] # 8-byte Reload + .p2align 4, 0x90 +.LBB8_181: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r15b + sbb edi, edi + mov rbx, r9 + shr rbx, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rbx] + xor dil, r9b + and dl, dil + xor dl, r9b + mov byte ptr [r11 + rbx], dl + cmp byte ptr [rsi + rax + 1], r15b + lea r9, [rax + 2] + sbb edi, edi + xor dil, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, dil + xor al, dl + mov byte ptr [r11 + rbx], al + cmp r10, r9 + jne .LBB8_181 +# %bb.182: + add rsi, r9 +.LBB8_183: + test r8b, 1 + je .LBB8_215 +# %bb.184: + cmp byte ptr [rsi], r15b + sbb eax, eax + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + shl bl, cl + xor al, dil + and bl, al + jmp .LBB8_210 +.LBB8_185: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB8_186: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rdx], r13d + sbb edi, edi + mov rsi, r11 + shr rsi, 3 + movzx r10d, byte ptr [r14 + rsi] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r14 + rsi], al + add r11, 2 + cmp dword ptr [rdx + 4], r13d + lea rdx, [rdx + 8] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r14 + rsi], bl + cmp r9, r11 + jne .LBB8_186 +.LBB8_187: + test r8b, 1 + je .LBB8_215 +# %bb.188: + cmp dword ptr [rdx], r13d + jmp .LBB8_197 +.LBB8_189: + mov r10, r8 + and r10, -2 + xor edi, edi + .p2align 4, 0x90 +.LBB8_190: # =>This Inner Loop Header: Depth=1 + ucomisd xmm0, qword ptr [rdx] + seta al + neg al + mov rsi, rdi + shr rsi, 3 + movzx r9d, byte ptr [r14 + rsi] + mov ecx, edi + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rsi], bl + add rdi, 2 + ucomisd xmm0, qword ptr [rdx + 8] + seta r9b + add rdx, 16 + neg r9b + xor r9b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r9b + xor al, bl + mov byte ptr [r14 + rsi], al + cmp r10, rdi + jne .LBB8_190 +.LBB8_191: + test r8b, 1 + je .LBB8_215 +# %bb.192: + ucomisd xmm0, qword ptr [rdx] + seta al + jmp .LBB8_203 +.LBB8_193: + mov r9, r8 + and r9, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB8_194: # =>This Inner Loop Header: Depth=1 + cmp word ptr [rdx], r13w + sbb edi, edi + mov rsi, r11 + shr rsi, 3 + movzx r10d, byte ptr [r14 + rsi] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dil, r10b + and al, dil + xor al, r10b + mov byte ptr [r14 + rsi], al + add r11, 2 + cmp word ptr [rdx + 2], r13w + lea rdx, [rdx + 4] + sbb edi, edi + xor dil, al + or cl, 1 + mov bl, 1 + shl bl, cl + and bl, dil + xor bl, al + mov byte ptr [r14 + rsi], bl + cmp r9, r11 + jne .LBB8_194 +.LBB8_195: + test r8b, 1 + je .LBB8_215 +# %bb.196: + cmp word ptr [rdx], r13w +.LBB8_197: + sbb eax, eax + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r14 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al + jmp .LBB8_204 +.LBB8_198: + mov r10, r8 + and r10, -2 + xor edi, edi + .p2align 4, 0x90 +.LBB8_199: # =>This Inner Loop Header: Depth=1 + cmp r13, qword ptr [rdx] + setg al + neg al + mov rsi, rdi + shr rsi, 3 + movzx r9d, byte ptr [r14 + rsi] + mov ecx, edi + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r14 + rsi], bl + add rdi, 2 + cmp r13, qword ptr [rdx + 8] + lea rdx, [rdx + 16] + setg r9b + neg r9b + xor r9b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r9b + xor al, bl + mov byte ptr [r14 + rsi], al + cmp r10, rdi + jne .LBB8_199 +.LBB8_200: + test r8b, 1 + je .LBB8_215 +# %bb.201: + cmp r13, qword ptr [rdx] +.LBB8_202: + setg al +.LBB8_203: + neg al + mov rdx, rdi + shr rdx, 3 + mov sil, byte ptr [r14 + rdx] + and dil, 7 + mov bl, 1 + mov ecx, edi + shl bl, cl + xor al, sil + and bl, al +.LBB8_204: + xor bl, sil + mov byte ptr [r14 + rdx], bl + jmp .LBB8_215 +.LBB8_205: + mov r9, r8 + and r9, -2 + xor r14d, r14d + mov r11, qword ptr [rsp] # 8-byte Reload + .p2align 4, 0x90 +.LBB8_206: # =>This Inner Loop Header: Depth=1 + mov rax, rsi + cmp r13w, word ptr [rsi] + setg dl + neg dl + mov rdi, r14 + shr rdi, 3 + movzx r10d, byte ptr [r11 + rdi] + mov ecx, r14d + and cl, 6 + mov bl, 1 + shl bl, cl + xor dl, r10b + and bl, dl + xor bl, r10b + mov byte ptr [r11 + rdi], bl + add r14, 2 + cmp r13w, word ptr [rsi + 2] + lea rsi, [rsi + 4] + setg dl + neg dl + xor dl, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, dl + xor al, bl + mov byte ptr [r11 + rdi], al + cmp r9, r14 + jne .LBB8_206 +.LBB8_207: + test r8b, 1 + je .LBB8_215 +# %bb.208: + cmp r13w, word ptr [rsi] + setg al + neg al + mov rdx, r14 + shr rdx, 3 + mov r8, qword ptr [rsp] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r14b, 7 + mov bl, 1 + mov ecx, r14d +.LBB8_209: + shl bl, cl + xor al, dil + and bl, al +.LBB8_210: + xor bl, dil + mov byte ptr [r8 + rdx], bl + jmp .LBB8_215 +.LBB8_211: + mov r10, r8 + and r10, -2 + xor esi, esi + mov r14, r11 + .p2align 4, 0x90 +.LBB8_212: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rbx] + seta dl + neg dl + mov rdi, rsi + shr rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, esi + and cl, 6 + mov al, 1 + shl al, cl + xor dl, r9b + and al, dl + xor al, r9b + mov byte ptr [r14 + rdi], al + add rsi, 2 + ucomiss xmm0, dword ptr [rbx + 4] + seta r9b + add rbx, 8 + neg r9b + xor r9b, al + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, r9b + xor dl, al + mov byte ptr [r14 + rdi], dl + cmp r10, rsi + jne .LBB8_212 +.LBB8_213: + test r8b, 1 + je .LBB8_215 +# %bb.214: + ucomiss xmm0, dword ptr [rbx] + seta al + neg al + mov rdx, rsi + shr rdx, 3 + mov dil, byte ptr [r11 + rdx] + and sil, 7 + mov bl, 1 + mov ecx, esi + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r11 + rdx], bl +.LBB8_215: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.LBB8_216: + and rcx, -8 mov rax, rcx - cmp rcx, qword ptr [rsp + 232] # 8-byte Folded Reload - jne .LBB8_195 -# %bb.196: - mov r15, qword ptr [rsp + 256] # 8-byte Reload - cmp r15, qword ptr [rsp + 232] # 8-byte Folded Reload - mov r11b, byte ptr [rsp] # 1-byte Reload - mov rsi, qword ptr [rsp + 264] # 8-byte Reload - mov r10, qword ptr [rsp + 136] # 8-byte Reload - jne .LBB8_67 - jmp .LBB8_132 -.LBB8_197: - and r15, -8 - mov rax, r15 shl rax, 6 add rax, rdx - mov qword ptr [rsp + 40], rax # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov qword ptr [rsp + 32], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] mov qword ptr [rsp], rax # 8-byte Spill - mov dword ptr [rsp + 48], r13d # 4-byte Spill + mov dword ptr [rsp + 40], r13d # 4-byte Spill movd xmm0, r13d pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] pshufd xmm15, xmm0, 0 # xmm15 = xmm0[0,0,0,0] - xor r9d, r9d + xor r8d, r8d mov qword ptr [rsp + 128], r14 # 8-byte Spill movdqa xmm8, xmmword ptr [rip + .LCPI8_8] # xmm8 = <1,1,1,1,1,1,1,1,u,u,u,u,u,u,u,u> .p2align 4, 0x90 -.LBB8_198: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 16], r9 # 8-byte Spill - shl r9, 6 - mov r8, r9 - mov r12, r9 - mov r13, r9 - mov rcx, r9 - mov rdi, r9 - mov rbx, r9 - movzx eax, word ptr [rdx + r9] +.LBB8_217: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 8], r8 # 8-byte Spill + shl r8, 6 + mov r9, r8 + mov r12, r8 + mov r13, r8 + mov rcx, r8 + mov rbx, r8 + mov rdi, r8 + movzx eax, word ptr [rdx + r8] movd xmm5, eax - movzx eax, word ptr [rdx + r9 + 2] + movzx eax, word ptr [rdx + r8 + 2] movd xmm3, eax - movzx eax, word ptr [rdx + r9 + 4] + movzx eax, word ptr [rdx + r8 + 4] movd xmm2, eax - movzx eax, word ptr [rdx + r9 + 6] + movzx eax, word ptr [rdx + r8 + 6] movd xmm4, eax - movzx r10d, word ptr [rdx + r9 + 8] - movzx esi, word ptr [rdx + r9 + 10] - movzx r11d, word ptr [rdx + r9 + 12] - movzx eax, word ptr [rdx + r9 + 14] - mov dword ptr [rsp + 8], eax # 4-byte Spill - movzx eax, word ptr [rdx + r9 + 16] + movzx r10d, word ptr [rdx + r8 + 8] + movzx esi, word ptr [rdx + r8 + 10] + movzx r11d, word ptr [rdx + r8 + 12] + movzx eax, word ptr [rdx + r8 + 14] + mov dword ptr [rsp + 16], eax # 4-byte Spill + movzx eax, word ptr [rdx + r8 + 16] movd xmm6, eax - movzx eax, word ptr [rdx + r9 + 32] + movzx eax, word ptr [rdx + r8 + 32] movd xmm1, eax - movzx eax, word ptr [rdx + r9 + 48] - mov r15, r9 + movzx eax, word ptr [rdx + r8 + 48] + mov r15, r8 or r15, 64 - or r8, 128 + or r9, 128 or r12, 192 or r13, 256 or rcx, 320 - or rdi, 384 + or rbx, 384 pinsrw xmm5, word ptr [rdx + r15], 1 - pinsrw xmm5, word ptr [rdx + r8], 2 + pinsrw xmm5, word ptr [rdx + r9], 2 pinsrw xmm5, word ptr [rdx + r12], 3 pinsrw xmm5, word ptr [rdx + r13], 4 pinsrw xmm5, word ptr [rdx + rcx], 5 - pinsrw xmm5, word ptr [rdx + rdi], 6 - or rbx, 448 - pinsrw xmm5, word ptr [rdx + rbx], 7 + pinsrw xmm5, word ptr [rdx + rbx], 6 + or rdi, 448 + pinsrw xmm5, word ptr [rdx + rdi], 7 movd xmm9, eax - movzx eax, word ptr [rdx + r9 + 18] + movzx eax, word ptr [rdx + r8 + 18] mov dword ptr [rsp + 24], eax # 4-byte Spill movdqa xmm0, xmm15 pcmpgtw xmm0, xmm5 pinsrw xmm3, word ptr [rdx + r15 + 2], 1 - pinsrw xmm3, word ptr [rdx + r8 + 2], 2 + pinsrw xmm3, word ptr [rdx + r9 + 2], 2 pinsrw xmm3, word ptr [rdx + r12 + 2], 3 pinsrw xmm3, word ptr [rdx + r13 + 2], 4 pinsrw xmm3, word ptr [rdx + rcx + 2], 5 - pinsrw xmm3, word ptr [rdx + rdi + 2], 6 - pinsrw xmm3, word ptr [rdx + rbx + 2], 7 + pinsrw xmm3, word ptr [rdx + rbx + 2], 6 + pinsrw xmm3, word ptr [rdx + rdi + 2], 7 pinsrw xmm6, word ptr [rdx + r15 + 16], 1 - pinsrw xmm6, word ptr [rdx + r8 + 16], 2 + pinsrw xmm6, word ptr [rdx + r9 + 16], 2 pinsrw xmm6, word ptr [rdx + r12 + 16], 3 pinsrw xmm6, word ptr [rdx + r13 + 16], 4 pinsrw xmm6, word ptr [rdx + rcx + 16], 5 - pinsrw xmm6, word ptr [rdx + rdi + 16], 6 - pinsrw xmm6, word ptr [rdx + rbx + 16], 7 + pinsrw xmm6, word ptr [rdx + rbx + 16], 6 + pinsrw xmm6, word ptr [rdx + rdi + 16], 7 movdqa xmm10, xmm15 pinsrw xmm1, word ptr [rdx + r15 + 32], 1 - pinsrw xmm1, word ptr [rdx + r8 + 32], 2 + pinsrw xmm1, word ptr [rdx + r9 + 32], 2 pinsrw xmm1, word ptr [rdx + r12 + 32], 3 pinsrw xmm1, word ptr [rdx + r13 + 32], 4 pinsrw xmm1, word ptr [rdx + rcx + 32], 5 - pinsrw xmm1, word ptr [rdx + rdi + 32], 6 - pinsrw xmm1, word ptr [rdx + rbx + 32], 7 + pinsrw xmm1, word ptr [rdx + rbx + 32], 6 + pinsrw xmm1, word ptr [rdx + rdi + 32], 7 pcmpgtw xmm10, xmm6 movdqa xmm6, xmm15 pcmpgtw xmm6, xmm1 pinsrw xmm9, word ptr [rdx + r15 + 48], 1 - pinsrw xmm9, word ptr [rdx + r8 + 48], 2 + pinsrw xmm9, word ptr [rdx + r9 + 48], 2 pinsrw xmm9, word ptr [rdx + r12 + 48], 3 pinsrw xmm9, word ptr [rdx + r13 + 48], 4 pinsrw xmm9, word ptr [rdx + rcx + 48], 5 - pinsrw xmm9, word ptr [rdx + rdi + 48], 6 - pinsrw xmm9, word ptr [rdx + rbx + 48], 7 + pinsrw xmm9, word ptr [rdx + rbx + 48], 6 + pinsrw xmm9, word ptr [rdx + rdi + 48], 7 movdqa xmm5, xmm15 pcmpgtw xmm5, xmm9 movdqa xmm1, xmm15 @@ -45781,35 +45176,35 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pand xmm3, xmm8 psubb xmm3, xmm1 movd xmm1, r10d - movzx r14d, word ptr [rdx + r9 + 20] + movzx r14d, word ptr [rdx + r8 + 20] packsswb xmm0, xmm0 pinsrw xmm2, word ptr [rdx + r15 + 4], 1 - pinsrw xmm2, word ptr [rdx + r8 + 4], 2 + pinsrw xmm2, word ptr [rdx + r9 + 4], 2 pinsrw xmm2, word ptr [rdx + r12 + 4], 3 pinsrw xmm2, word ptr [rdx + r13 + 4], 4 pinsrw xmm2, word ptr [rdx + rcx + 4], 5 - pinsrw xmm2, word ptr [rdx + rdi + 4], 6 - pinsrw xmm2, word ptr [rdx + rbx + 4], 7 + pinsrw xmm2, word ptr [rdx + rbx + 4], 6 + pinsrw xmm2, word ptr [rdx + rdi + 4], 7 pinsrw xmm4, word ptr [rdx + r15 + 6], 1 - pinsrw xmm4, word ptr [rdx + r8 + 6], 2 + pinsrw xmm4, word ptr [rdx + r9 + 6], 2 pinsrw xmm4, word ptr [rdx + r12 + 6], 3 pinsrw xmm4, word ptr [rdx + r13 + 6], 4 pinsrw xmm4, word ptr [rdx + rcx + 6], 5 - pinsrw xmm4, word ptr [rdx + rdi + 6], 6 - pinsrw xmm4, word ptr [rdx + rbx + 6], 7 + pinsrw xmm4, word ptr [rdx + rbx + 6], 6 + pinsrw xmm4, word ptr [rdx + rdi + 6], 7 pinsrw xmm1, word ptr [rdx + r15 + 8], 1 - pinsrw xmm1, word ptr [rdx + r8 + 8], 2 + pinsrw xmm1, word ptr [rdx + r9 + 8], 2 pinsrw xmm1, word ptr [rdx + r12 + 8], 3 pinsrw xmm1, word ptr [rdx + r13 + 8], 4 pinsrw xmm1, word ptr [rdx + rcx + 8], 5 - pinsrw xmm1, word ptr [rdx + rdi + 8], 6 + pinsrw xmm1, word ptr [rdx + rbx + 8], 6 pand xmm0, xmm8 por xmm3, xmm0 movdqa xmm7, xmm15 pcmpgtw xmm7, xmm2 movd xmm2, esi - movzx esi, word ptr [rdx + r9 + 22] - pinsrw xmm1, word ptr [rdx + rbx + 8], 7 + movzx esi, word ptr [rdx + r8 + 22] + pinsrw xmm1, word ptr [rdx + rdi + 8], 7 packsswb xmm7, xmm7 pand xmm7, xmm8 psllw xmm7, 2 @@ -45821,20 +45216,20 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 movdqa xmm0, xmm15 pcmpgtw xmm0, xmm1 movd xmm1, r11d - movzx r11d, word ptr [rdx + r9 + 24] + movzx r11d, word ptr [rdx + r8 + 24] pinsrw xmm2, word ptr [rdx + r15 + 10], 1 - pinsrw xmm2, word ptr [rdx + r8 + 10], 2 + pinsrw xmm2, word ptr [rdx + r9 + 10], 2 pinsrw xmm2, word ptr [rdx + r12 + 10], 3 pinsrw xmm2, word ptr [rdx + r13 + 10], 4 pinsrw xmm2, word ptr [rdx + rcx + 10], 5 - pinsrw xmm2, word ptr [rdx + rdi + 10], 6 - pinsrw xmm2, word ptr [rdx + rbx + 10], 7 + pinsrw xmm2, word ptr [rdx + rbx + 10], 6 + pinsrw xmm2, word ptr [rdx + rdi + 10], 7 pinsrw xmm1, word ptr [rdx + r15 + 12], 1 - pinsrw xmm1, word ptr [rdx + r8 + 12], 2 + pinsrw xmm1, word ptr [rdx + r9 + 12], 2 pinsrw xmm1, word ptr [rdx + r12 + 12], 3 pinsrw xmm1, word ptr [rdx + r13 + 12], 4 pinsrw xmm1, word ptr [rdx + rcx + 12], 5 - pinsrw xmm1, word ptr [rdx + rdi + 12], 6 + pinsrw xmm1, word ptr [rdx + rbx + 12], 6 packsswb xmm3, xmm3 pand xmm3, xmm8 psllw xmm3, 3 @@ -45846,10 +45241,10 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 movdqa xmm13, xmmword ptr [rip + .LCPI8_3] # xmm13 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] pand xmm0, xmm13 por xmm0, xmm3 - movd xmm3, dword ptr [rsp + 8] # 4-byte Folded Reload + movd xmm3, dword ptr [rsp + 16] # 4-byte Folded Reload # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [rdx + r9 + 26] - pinsrw xmm1, word ptr [rdx + rbx + 12], 7 + movzx eax, word ptr [rdx + r8 + 26] + pinsrw xmm1, word ptr [rdx + rdi + 12], 7 por xmm0, xmm7 movdqa xmm4, xmm15 pcmpgtw xmm4, xmm2 @@ -45857,14 +45252,14 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pcmpgtw xmm7, xmm1 movd xmm1, dword ptr [rsp + 24] # 4-byte Folded Reload # xmm1 = mem[0],zero,zero,zero - movzx r10d, word ptr [rdx + r9 + 28] + movzx r10d, word ptr [rdx + r8 + 28] pinsrw xmm3, word ptr [rdx + r15 + 14], 1 - pinsrw xmm3, word ptr [rdx + r8 + 14], 2 + pinsrw xmm3, word ptr [rdx + r9 + 14], 2 pinsrw xmm3, word ptr [rdx + r12 + 14], 3 pinsrw xmm3, word ptr [rdx + r13 + 14], 4 pinsrw xmm3, word ptr [rdx + rcx + 14], 5 - pinsrw xmm3, word ptr [rdx + rdi + 14], 6 - pinsrw xmm3, word ptr [rdx + rbx + 14], 7 + pinsrw xmm3, word ptr [rdx + rbx + 14], 6 + pinsrw xmm3, word ptr [rdx + rdi + 14], 7 packsswb xmm4, xmm4 pand xmm4, xmm8 psllw xmm4, 5 @@ -45879,22 +45274,22 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 movdqa xmm9, xmm15 pcmpgtw xmm9, xmm3 movd xmm3, r14d - movzx r14d, word ptr [rdx + r9 + 30] + movzx r14d, word ptr [rdx + r8 + 30] packsswb xmm9, xmm9 psllw xmm9, 7 movdqa xmm2, xmmword ptr [rip + .LCPI8_6] # xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] pand xmm9, xmm2 por xmm9, xmm7 movd xmm4, esi - movzx esi, word ptr [rdx + r9 + 34] + movzx esi, word ptr [rdx + r8 + 34] mov dword ptr [rsp + 24], esi # 4-byte Spill pinsrw xmm1, word ptr [rdx + r15 + 18], 1 - pinsrw xmm1, word ptr [rdx + r8 + 18], 2 + pinsrw xmm1, word ptr [rdx + r9 + 18], 2 pinsrw xmm1, word ptr [rdx + r12 + 18], 3 pinsrw xmm1, word ptr [rdx + r13 + 18], 4 pinsrw xmm1, word ptr [rdx + rcx + 18], 5 - pinsrw xmm1, word ptr [rdx + rdi + 18], 6 - pinsrw xmm1, word ptr [rdx + rbx + 18], 7 + pinsrw xmm1, word ptr [rdx + rbx + 18], 6 + pinsrw xmm1, word ptr [rdx + rdi + 18], 7 por xmm9, xmm0 movdqa xmm0, xmm15 pcmpgtw xmm0, xmm1 @@ -45903,36 +45298,36 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pand xmm1, xmm8 psubb xmm1, xmm0 movd xmm7, r11d - movzx esi, word ptr [rdx + r9 + 36] - mov dword ptr [rsp + 8], esi # 4-byte Spill + movzx esi, word ptr [rdx + r8 + 36] + mov dword ptr [rsp + 16], esi # 4-byte Spill packsswb xmm10, xmm10 pinsrw xmm3, word ptr [rdx + r15 + 20], 1 - pinsrw xmm3, word ptr [rdx + r8 + 20], 2 + pinsrw xmm3, word ptr [rdx + r9 + 20], 2 pinsrw xmm3, word ptr [rdx + r12 + 20], 3 pinsrw xmm3, word ptr [rdx + r13 + 20], 4 pinsrw xmm3, word ptr [rdx + rcx + 20], 5 - pinsrw xmm3, word ptr [rdx + rdi + 20], 6 - pinsrw xmm3, word ptr [rdx + rbx + 20], 7 + pinsrw xmm3, word ptr [rdx + rbx + 20], 6 + pinsrw xmm3, word ptr [rdx + rdi + 20], 7 pinsrw xmm4, word ptr [rdx + r15 + 22], 1 - pinsrw xmm4, word ptr [rdx + r8 + 22], 2 + pinsrw xmm4, word ptr [rdx + r9 + 22], 2 pinsrw xmm4, word ptr [rdx + r12 + 22], 3 pinsrw xmm4, word ptr [rdx + r13 + 22], 4 pinsrw xmm4, word ptr [rdx + rcx + 22], 5 - pinsrw xmm4, word ptr [rdx + rdi + 22], 6 - pinsrw xmm4, word ptr [rdx + rbx + 22], 7 + pinsrw xmm4, word ptr [rdx + rbx + 22], 6 + pinsrw xmm4, word ptr [rdx + rdi + 22], 7 pinsrw xmm7, word ptr [rdx + r15 + 24], 1 - pinsrw xmm7, word ptr [rdx + r8 + 24], 2 + pinsrw xmm7, word ptr [rdx + r9 + 24], 2 pinsrw xmm7, word ptr [rdx + r12 + 24], 3 pinsrw xmm7, word ptr [rdx + r13 + 24], 4 pinsrw xmm7, word ptr [rdx + rcx + 24], 5 - pinsrw xmm7, word ptr [rdx + rdi + 24], 6 - pinsrw xmm7, word ptr [rdx + rbx + 24], 7 + pinsrw xmm7, word ptr [rdx + rbx + 24], 6 + pinsrw xmm7, word ptr [rdx + rdi + 24], 7 pand xmm10, xmm8 por xmm1, xmm10 movdqa xmm2, xmm15 pcmpgtw xmm2, xmm3 movd xmm3, eax - movzx r11d, word ptr [rdx + r9 + 38] + movzx r11d, word ptr [rdx + r8 + 38] packsswb xmm2, xmm2 pand xmm2, xmm8 psllw xmm2, 2 @@ -45944,21 +45339,21 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 movdqa xmm0, xmm15 pcmpgtw xmm0, xmm7 movd xmm4, r10d - movzx r10d, word ptr [rdx + r9 + 40] + movzx r10d, word ptr [rdx + r8 + 40] pinsrw xmm3, word ptr [rdx + r15 + 26], 1 - pinsrw xmm3, word ptr [rdx + r8 + 26], 2 + pinsrw xmm3, word ptr [rdx + r9 + 26], 2 pinsrw xmm3, word ptr [rdx + r12 + 26], 3 pinsrw xmm3, word ptr [rdx + r13 + 26], 4 pinsrw xmm3, word ptr [rdx + rcx + 26], 5 - pinsrw xmm3, word ptr [rdx + rdi + 26], 6 - pinsrw xmm3, word ptr [rdx + rbx + 26], 7 + pinsrw xmm3, word ptr [rdx + rbx + 26], 6 + pinsrw xmm3, word ptr [rdx + rdi + 26], 7 pinsrw xmm4, word ptr [rdx + r15 + 28], 1 - pinsrw xmm4, word ptr [rdx + r8 + 28], 2 + pinsrw xmm4, word ptr [rdx + r9 + 28], 2 pinsrw xmm4, word ptr [rdx + r12 + 28], 3 pinsrw xmm4, word ptr [rdx + r13 + 28], 4 pinsrw xmm4, word ptr [rdx + rcx + 28], 5 - pinsrw xmm4, word ptr [rdx + rdi + 28], 6 - pinsrw xmm4, word ptr [rdx + rbx + 28], 7 + pinsrw xmm4, word ptr [rdx + rbx + 28], 6 + pinsrw xmm4, word ptr [rdx + rdi + 28], 7 packsswb xmm1, xmm1 pand xmm1, xmm8 psllw xmm1, 3 @@ -45971,7 +45366,7 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pand xmm0, xmm12 por xmm0, xmm1 movd xmm1, r14d - movzx eax, word ptr [rdx + r9 + 42] + movzx eax, word ptr [rdx + r8 + 42] por xmm0, xmm2 movdqa xmm2, xmm15 pcmpgtw xmm2, xmm3 @@ -45979,14 +45374,14 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pcmpgtw xmm7, xmm4 movd xmm4, dword ptr [rsp + 24] # 4-byte Folded Reload # xmm4 = mem[0],zero,zero,zero - movzx r14d, word ptr [rdx + r9 + 44] + movzx r14d, word ptr [rdx + r8 + 44] pinsrw xmm1, word ptr [rdx + r15 + 30], 1 - pinsrw xmm1, word ptr [rdx + r8 + 30], 2 + pinsrw xmm1, word ptr [rdx + r9 + 30], 2 pinsrw xmm1, word ptr [rdx + r12 + 30], 3 pinsrw xmm1, word ptr [rdx + r13 + 30], 4 pinsrw xmm1, word ptr [rdx + rcx + 30], 5 - pinsrw xmm1, word ptr [rdx + rdi + 30], 6 - pinsrw xmm1, word ptr [rdx + rbx + 30], 7 + pinsrw xmm1, word ptr [rdx + rbx + 30], 6 + pinsrw xmm1, word ptr [rdx + rdi + 30], 7 packsswb xmm2, xmm2 pand xmm2, xmm8 psllw xmm2, 5 @@ -45999,9 +45394,9 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 por xmm7, xmm2 movdqa xmm10, xmm15 pcmpgtw xmm10, xmm1 - movd xmm1, dword ptr [rsp + 8] # 4-byte Folded Reload + movd xmm1, dword ptr [rsp + 16] # 4-byte Folded Reload # xmm1 = mem[0],zero,zero,zero - movzx esi, word ptr [rdx + r9 + 46] + movzx esi, word ptr [rdx + r8 + 46] mov dword ptr [rsp + 24], esi # 4-byte Spill packsswb xmm10, xmm10 psllw xmm10, 7 @@ -46009,14 +45404,14 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pand xmm10, xmm14 por xmm10, xmm7 movd xmm2, r11d - movzx r11d, word ptr [rdx + r9 + 50] + movzx r11d, word ptr [rdx + r8 + 50] pinsrw xmm4, word ptr [rdx + r15 + 34], 1 - pinsrw xmm4, word ptr [rdx + r8 + 34], 2 + pinsrw xmm4, word ptr [rdx + r9 + 34], 2 pinsrw xmm4, word ptr [rdx + r12 + 34], 3 pinsrw xmm4, word ptr [rdx + r13 + 34], 4 pinsrw xmm4, word ptr [rdx + rcx + 34], 5 - pinsrw xmm4, word ptr [rdx + rdi + 34], 6 - pinsrw xmm4, word ptr [rdx + rbx + 34], 7 + pinsrw xmm4, word ptr [rdx + rbx + 34], 6 + pinsrw xmm4, word ptr [rdx + rdi + 34], 7 por xmm10, xmm0 movdqa xmm0, xmm15 pcmpgtw xmm0, xmm4 @@ -46025,36 +45420,36 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pand xmm4, xmm8 psubb xmm4, xmm0 movd xmm0, r10d - movzx esi, word ptr [rdx + r9 + 52] - mov dword ptr [rsp + 8], esi # 4-byte Spill + movzx esi, word ptr [rdx + r8 + 52] + mov dword ptr [rsp + 16], esi # 4-byte Spill packsswb xmm6, xmm6 pinsrw xmm1, word ptr [rdx + r15 + 36], 1 - pinsrw xmm1, word ptr [rdx + r8 + 36], 2 + pinsrw xmm1, word ptr [rdx + r9 + 36], 2 pinsrw xmm1, word ptr [rdx + r12 + 36], 3 pinsrw xmm1, word ptr [rdx + r13 + 36], 4 pinsrw xmm1, word ptr [rdx + rcx + 36], 5 - pinsrw xmm1, word ptr [rdx + rdi + 36], 6 - pinsrw xmm1, word ptr [rdx + rbx + 36], 7 + pinsrw xmm1, word ptr [rdx + rbx + 36], 6 + pinsrw xmm1, word ptr [rdx + rdi + 36], 7 pinsrw xmm2, word ptr [rdx + r15 + 38], 1 - pinsrw xmm2, word ptr [rdx + r8 + 38], 2 + pinsrw xmm2, word ptr [rdx + r9 + 38], 2 pinsrw xmm2, word ptr [rdx + r12 + 38], 3 pinsrw xmm2, word ptr [rdx + r13 + 38], 4 pinsrw xmm2, word ptr [rdx + rcx + 38], 5 - pinsrw xmm2, word ptr [rdx + rdi + 38], 6 - pinsrw xmm2, word ptr [rdx + rbx + 38], 7 + pinsrw xmm2, word ptr [rdx + rbx + 38], 6 + pinsrw xmm2, word ptr [rdx + rdi + 38], 7 pinsrw xmm0, word ptr [rdx + r15 + 40], 1 - pinsrw xmm0, word ptr [rdx + r8 + 40], 2 + pinsrw xmm0, word ptr [rdx + r9 + 40], 2 pinsrw xmm0, word ptr [rdx + r12 + 40], 3 pinsrw xmm0, word ptr [rdx + r13 + 40], 4 pinsrw xmm0, word ptr [rdx + rcx + 40], 5 - pinsrw xmm0, word ptr [rdx + rdi + 40], 6 + pinsrw xmm0, word ptr [rdx + rbx + 40], 6 pand xmm6, xmm8 por xmm4, xmm6 movdqa xmm6, xmm15 pcmpgtw xmm6, xmm1 movd xmm7, eax - movzx r10d, word ptr [rdx + r9 + 54] - pinsrw xmm0, word ptr [rdx + rbx + 40], 7 + movzx r10d, word ptr [rdx + r8 + 54] + pinsrw xmm0, word ptr [rdx + rdi + 40], 7 packsswb xmm6, xmm6 pand xmm6, xmm8 psllw xmm6, 2 @@ -46065,20 +45460,20 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 movdqa xmm1, xmm15 pcmpgtw xmm1, xmm0 movd xmm0, r14d - movzx eax, word ptr [rdx + r9 + 56] + movzx eax, word ptr [rdx + r8 + 56] pinsrw xmm7, word ptr [rdx + r15 + 42], 1 - pinsrw xmm7, word ptr [rdx + r8 + 42], 2 + pinsrw xmm7, word ptr [rdx + r9 + 42], 2 pinsrw xmm7, word ptr [rdx + r12 + 42], 3 pinsrw xmm7, word ptr [rdx + r13 + 42], 4 pinsrw xmm7, word ptr [rdx + rcx + 42], 5 - pinsrw xmm7, word ptr [rdx + rdi + 42], 6 - pinsrw xmm7, word ptr [rdx + rbx + 42], 7 + pinsrw xmm7, word ptr [rdx + rbx + 42], 6 + pinsrw xmm7, word ptr [rdx + rdi + 42], 7 pinsrw xmm0, word ptr [rdx + r15 + 44], 1 - pinsrw xmm0, word ptr [rdx + r8 + 44], 2 + pinsrw xmm0, word ptr [rdx + r9 + 44], 2 pinsrw xmm0, word ptr [rdx + r12 + 44], 3 pinsrw xmm0, word ptr [rdx + r13 + 44], 4 pinsrw xmm0, word ptr [rdx + rcx + 44], 5 - pinsrw xmm0, word ptr [rdx + rdi + 44], 6 + pinsrw xmm0, word ptr [rdx + rbx + 44], 6 packsswb xmm4, xmm4 pand xmm4, xmm8 psllw xmm4, 3 @@ -46091,23 +45486,23 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 por xmm1, xmm4 movd xmm2, dword ptr [rsp + 24] # 4-byte Folded Reload # xmm2 = mem[0],zero,zero,zero - movzx esi, word ptr [rdx + r9 + 58] - pinsrw xmm0, word ptr [rdx + rbx + 44], 7 + movzx esi, word ptr [rdx + r8 + 58] + pinsrw xmm0, word ptr [rdx + rdi + 44], 7 por xmm1, xmm6 movdqa xmm4, xmm15 pcmpgtw xmm4, xmm7 movdqa xmm6, xmm15 pcmpgtw xmm6, xmm0 movd xmm7, r11d - movzx r11d, word ptr [rdx + r9 + 60] + movzx r11d, word ptr [rdx + r8 + 60] pinsrw xmm2, word ptr [rdx + r15 + 46], 1 - pinsrw xmm2, word ptr [rdx + r8 + 46], 2 + pinsrw xmm2, word ptr [rdx + r9 + 46], 2 pinsrw xmm2, word ptr [rdx + r12 + 46], 3 pinsrw xmm2, word ptr [rdx + r13 + 46], 4 pinsrw xmm2, word ptr [rdx + rcx + 46], 5 - pinsrw xmm2, word ptr [rdx + rdi + 46], 6 - movzx r9d, word ptr [rdx + r9 + 62] - pinsrw xmm2, word ptr [rdx + rbx + 46], 7 + pinsrw xmm2, word ptr [rdx + rbx + 46], 6 + movzx r8d, word ptr [rdx + r8 + 62] + pinsrw xmm2, word ptr [rdx + rdi + 46], 7 packsswb xmm4, xmm4 pand xmm4, xmm8 psllw xmm4, 5 @@ -46120,15 +45515,15 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 por xmm6, xmm4 movdqa xmm0, xmm15 pcmpgtw xmm0, xmm2 - movd xmm2, dword ptr [rsp + 8] # 4-byte Folded Reload + movd xmm2, dword ptr [rsp + 16] # 4-byte Folded Reload # xmm2 = mem[0],zero,zero,zero pinsrw xmm7, word ptr [rdx + r15 + 50], 1 - pinsrw xmm7, word ptr [rdx + r8 + 50], 2 + pinsrw xmm7, word ptr [rdx + r9 + 50], 2 pinsrw xmm7, word ptr [rdx + r12 + 50], 3 pinsrw xmm7, word ptr [rdx + r13 + 50], 4 pinsrw xmm7, word ptr [rdx + rcx + 50], 5 - pinsrw xmm7, word ptr [rdx + rdi + 50], 6 - pinsrw xmm7, word ptr [rdx + rbx + 50], 7 + pinsrw xmm7, word ptr [rdx + rbx + 50], 6 + pinsrw xmm7, word ptr [rdx + rdi + 50], 7 packsswb xmm0, xmm0 psllw xmm0, 7 pand xmm0, xmm14 @@ -46144,38 +45539,38 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 movd xmm3, eax packsswb xmm5, xmm5 pinsrw xmm2, word ptr [rdx + r15 + 52], 1 - pinsrw xmm2, word ptr [rdx + r8 + 52], 2 + pinsrw xmm2, word ptr [rdx + r9 + 52], 2 pinsrw xmm2, word ptr [rdx + r12 + 52], 3 pinsrw xmm2, word ptr [rdx + r13 + 52], 4 pinsrw xmm2, word ptr [rdx + rcx + 52], 5 - pinsrw xmm2, word ptr [rdx + rdi + 52], 6 + pinsrw xmm2, word ptr [rdx + rbx + 52], 6 pand xmm5, xmm8 - pinsrw xmm2, word ptr [rdx + rbx + 52], 7 + pinsrw xmm2, word ptr [rdx + rdi + 52], 7 por xmm7, xmm5 movdqa xmm5, xmm15 pcmpgtw xmm5, xmm2 movd xmm4, esi pinsrw xmm6, word ptr [rdx + r15 + 54], 1 - pinsrw xmm6, word ptr [rdx + r8 + 54], 2 + pinsrw xmm6, word ptr [rdx + r9 + 54], 2 pinsrw xmm6, word ptr [rdx + r12 + 54], 3 pinsrw xmm6, word ptr [rdx + r13 + 54], 4 pinsrw xmm6, word ptr [rdx + rcx + 54], 5 - pinsrw xmm6, word ptr [rdx + rdi + 54], 6 - pinsrw xmm6, word ptr [rdx + rbx + 54], 7 + pinsrw xmm6, word ptr [rdx + rbx + 54], 6 + pinsrw xmm6, word ptr [rdx + rdi + 54], 7 pinsrw xmm3, word ptr [rdx + r15 + 56], 1 - pinsrw xmm3, word ptr [rdx + r8 + 56], 2 + pinsrw xmm3, word ptr [rdx + r9 + 56], 2 pinsrw xmm3, word ptr [rdx + r12 + 56], 3 pinsrw xmm3, word ptr [rdx + r13 + 56], 4 pinsrw xmm3, word ptr [rdx + rcx + 56], 5 - pinsrw xmm3, word ptr [rdx + rdi + 56], 6 - pinsrw xmm3, word ptr [rdx + rbx + 56], 7 + pinsrw xmm3, word ptr [rdx + rbx + 56], 6 + pinsrw xmm3, word ptr [rdx + rdi + 56], 7 pinsrw xmm4, word ptr [rdx + r15 + 58], 1 - pinsrw xmm4, word ptr [rdx + r8 + 58], 2 + pinsrw xmm4, word ptr [rdx + r9 + 58], 2 pinsrw xmm4, word ptr [rdx + r12 + 58], 3 pinsrw xmm4, word ptr [rdx + r13 + 58], 4 pinsrw xmm4, word ptr [rdx + rcx + 58], 5 - pinsrw xmm4, word ptr [rdx + rdi + 58], 6 - pinsrw xmm4, word ptr [rdx + rbx + 58], 7 + pinsrw xmm4, word ptr [rdx + rbx + 58], 6 + pinsrw xmm4, word ptr [rdx + rdi + 58], 7 packsswb xmm5, xmm5 pand xmm5, xmm8 psllw xmm5, 2 @@ -46187,12 +45582,12 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 pcmpgtw xmm1, xmm3 movd xmm3, r11d pinsrw xmm3, word ptr [rdx + r15 + 60], 1 - pinsrw xmm3, word ptr [rdx + r8 + 60], 2 + pinsrw xmm3, word ptr [rdx + r9 + 60], 2 pinsrw xmm3, word ptr [rdx + r12 + 60], 3 pinsrw xmm3, word ptr [rdx + r13 + 60], 4 pinsrw xmm3, word ptr [rdx + rcx + 60], 5 - pinsrw xmm3, word ptr [rdx + rdi + 60], 6 - pinsrw xmm3, word ptr [rdx + rbx + 60], 7 + pinsrw xmm3, word ptr [rdx + rbx + 60], 6 + pinsrw xmm3, word ptr [rdx + rdi + 60], 7 packsswb xmm2, xmm2 pand xmm2, xmm8 psllw xmm2, 3 @@ -46202,15 +45597,15 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 psllw xmm1, 4 pand xmm1, xmm13 por xmm1, xmm2 - movd xmm2, r9d + movd xmm2, r8d pinsrw xmm2, word ptr [rdx + r15 + 62], 1 - pinsrw xmm2, word ptr [rdx + r8 + 62], 2 + pinsrw xmm2, word ptr [rdx + r9 + 62], 2 pinsrw xmm2, word ptr [rdx + r12 + 62], 3 mov r14, qword ptr [rsp + 128] # 8-byte Reload pinsrw xmm2, word ptr [rdx + r13 + 62], 4 pinsrw xmm2, word ptr [rdx + rcx + 62], 5 - pinsrw xmm2, word ptr [rdx + rdi + 62], 6 - pinsrw xmm2, word ptr [rdx + rbx + 62], 7 + pinsrw xmm2, word ptr [rdx + rbx + 62], 6 + pinsrw xmm2, word ptr [rdx + rdi + 62], 7 por xmm1, xmm5 movdqa xmm5, xmm15 pcmpgtw xmm5, xmm4 @@ -46243,33 +45638,32 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 punpcklbw xmm0, xmm3 # xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7] punpcklbw xmm9, xmm10 # xmm9 = xmm9[0],xmm10[0],xmm9[1],xmm10[1],xmm9[2],xmm10[2],xmm9[3],xmm10[3],xmm9[4],xmm10[4],xmm9[5],xmm10[5],xmm9[6],xmm10[6],xmm9[7],xmm10[7] punpcklwd xmm9, xmm0 # xmm9 = xmm9[0],xmm0[0],xmm9[1],xmm0[1],xmm9[2],xmm0[2],xmm9[3],xmm0[3] - mov rcx, qword ptr [rsp + 16] # 8-byte Reload + mov rcx, qword ptr [rsp + 8] # 8-byte Reload movdqu xmmword ptr [r14 + 4*rcx], xmm9 movdqu xmmword ptr [r14 + 4*rcx + 16], xmm1 add rcx, 8 - mov r9, rcx + mov r8, rcx cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB8_198 -# %bb.199: - mov r15, qword ptr [rsp + 240] # 8-byte Reload - cmp r15, qword ptr [rsp + 32] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 136] # 8-byte Reload - mov r13d, dword ptr [rsp + 48] # 4-byte Reload - mov r12, qword ptr [rsp] # 8-byte Reload - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - jne .LBB8_101 - jmp .LBB8_136 -.LBB8_200: - mov r8, r11 - and r8, -4 - mov rbx, r8 + jne .LBB8_217 +# %bb.218: + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov r13d, dword ptr [rsp + 40] # 4-byte Reload + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + jne .LBB8_81 + jmp .LBB8_131 +.LBB8_219: + mov r9, rcx + and r9, -4 + mov rbx, r9 shl rbx, 7 add rbx, rdx - lea r15, [r14 + 4*r8] - movaps xmm1, xmm0 + lea r11, [r14 + 4*r9] + movdqa xmm1, xmm0 shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] add rdx, 508 - xor ecx, ecx + xor esi, esi movdqa xmm15, xmmword ptr [rip + .LCPI8_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> movdqa xmm8, xmmword ptr [rip + .LCPI8_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] movdqa xmm10, xmmword ptr [rip + .LCPI8_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] @@ -46279,7 +45673,7 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 movdqa xmm14, xmmword ptr [rip + .LCPI8_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] movdqa xmm9, xmmword ptr [rip + .LCPI8_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] .p2align 4, 0x90 -.LBB8_201: # =>This Inner Loop Header: Depth=1 +.LBB8_220: # =>This Inner Loop Header: Depth=1 movss xmm6, dword ptr [rdx - 508] # xmm6 = mem[0],zero,zero,zero movss xmm7, dword ptr [rdx - 504] # xmm7 = mem[0],zero,zero,zero movss xmm5, dword ptr [rdx - 500] # xmm5 = mem[0],zero,zero,zero @@ -46615,20 +46009,1935 @@ comparison_greater_scalar_arr_sse4: # @comparison_greater_scalar_arr_sse4 packsswb xmm3, xmm3 psllw xmm3, 7 pand xmm3, xmm14 - por xmm3, xmm2 - por xmm3, xmm6 - punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] - punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] - pshufb xmm4, xmm9 + por xmm3, xmm2 + por xmm3, xmm6 + punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] + punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] + pshufb xmm4, xmm9 + movdqu xmmword ptr [r14 + 4*rsi], xmm4 + add rsi, 4 + add rdx, 512 + cmp r9, rsi + jne .LBB8_220 +# %bb.221: + cmp rcx, r9 + jne .LBB8_108 + jmp .LBB8_135 +.LBB8_222: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, rdi + mov qword ptr [rsp + 264], rax # 8-byte Spill + mov qword ptr [rsp + 248], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] + mov qword ptr [rsp + 104], rax # 8-byte Spill + movzx eax, r15b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 128], r14 # 8-byte Spill + .p2align 4, 0x90 +.LBB8_223: # =>This Inner Loop Header: Depth=1 + mov r9, rax + mov qword ptr [rsp + 120], rax # 8-byte Spill + shl rax, 5 + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r11, rax + mov rbx, rax + mov r13, rax + mov r14, rax + mov r8, rax + mov r12, rax + mov r10, rax + mov r15, rax + mov rsi, rax + mov rdx, rax + movzx ecx, byte ptr [rdi + rax] + movd xmm8, ecx + movzx ecx, byte ptr [rdi + rax + 1] + movd xmm7, ecx + movzx ecx, byte ptr [rdi + rax + 2] + movd xmm6, ecx + movzx ecx, byte ptr [rdi + rax + 3] + movd xmm15, ecx + movzx ecx, byte ptr [rdi + rax + 4] + movd xmm5, ecx + movzx ecx, byte ptr [rdi + rax + 5] + movd xmm2, ecx + movzx ecx, byte ptr [rdi + rax + 6] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill + movzx ecx, byte ptr [rdi + rax + 7] + movd xmm1, ecx + movzx ecx, byte ptr [rdi + rax + 8] + movd xmm12, ecx + movzx ecx, byte ptr [rdi + rax + 9] + movd xmm0, ecx + movzx ecx, byte ptr [rdi + rax + 10] + movd xmm9, ecx + movzx ecx, byte ptr [rdi + rax + 11] + movd xmm10, ecx + movzx ecx, byte ptr [rdi + rax + 12] + movd xmm11, ecx + movzx ecx, byte ptr [rdi + rax + 16] + movd xmm14, ecx + movzx ecx, byte ptr [rdi + rax + 24] + movd xmm4, ecx + mov qword ptr [rsp + 80], rax # 8-byte Spill + mov rcx, rax + or rcx, 32 + mov qword ptr [rsp + 8], rcx # 8-byte Spill + mov r9, qword ptr [rsp + 24] # 8-byte Reload + or r9, 64 + mov qword ptr [rsp + 24], r9 # 8-byte Spill + or r11, 96 + mov qword ptr [rsp + 144], r11 # 8-byte Spill + or rbx, 128 + or r13, 160 + mov qword ptr [rsp + 160], r13 # 8-byte Spill + or r14, 192 + or r8, 224 + mov r13, rax + or r13, 256 + mov qword ptr [rsp + 40], r13 # 8-byte Spill + or r10, 288 + or r15, 320 + or rsi, 352 + or r12, 384 + mov rcx, rax + or rcx, 416 + mov qword ptr [rsp + 16], rcx # 8-byte Spill + or rdx, 448 + mov rcx, rax + or rcx, 480 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rax], 1 + pinsrb xmm8, byte ptr [rdi + r9], 2 + pinsrb xmm8, byte ptr [rdi + r11], 3 + pinsrb xmm8, byte ptr [rdi + rbx], 4 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rax], 5 + pinsrb xmm8, byte ptr [rdi + r14], 6 + pinsrb xmm8, byte ptr [rdi + r8], 7 + pinsrb xmm8, byte ptr [rdi + r13], 8 + pinsrb xmm8, byte ptr [rdi + r10], 9 + mov qword ptr [rsp + 32], r15 # 8-byte Spill + pinsrb xmm8, byte ptr [rdi + r15], 10 + pinsrb xmm8, byte ptr [rdi + rsi], 11 + mov r15, r12 + pinsrb xmm8, byte ptr [rdi + r12], 12 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r12], 13 + pinsrb xmm8, byte ptr [rdi + rdx], 14 + pinsrb xmm8, byte ptr [rdi + rcx], 15 + movdqa xmm13, xmmword ptr [rsp + 288] # 16-byte Reload + movdqa xmm3, xmm13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 1], 1 + pinsrb xmm7, byte ptr [rdi + r9 + 1], 2 + pinsrb xmm7, byte ptr [rdi + r11 + 1], 3 + pinsrb xmm7, byte ptr [rdi + rbx + 1], 4 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r13 + 1], 5 + pinsrb xmm7, byte ptr [rdi + r14 + 1], 6 + pinsrb xmm7, byte ptr [rdi + r8 + 1], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 1], 8 + pinsrb xmm7, byte ptr [rdi + r10 + 1], 9 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 1], 10 + pinsrb xmm7, byte ptr [rdi + rsi + 1], 11 + pinsrb xmm7, byte ptr [rdi + r15 + 1], 12 + pinsrb xmm7, byte ptr [rdi + r12 + 1], 13 + pinsrb xmm7, byte ptr [rdi + rdx + 1], 14 + pinsrb xmm7, byte ptr [rdi + rcx + 1], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 2], 1 + pinsrb xmm6, byte ptr [rdi + r9 + 2], 2 + pinsrb xmm6, byte ptr [rdi + r11 + 2], 3 + pinsrb xmm6, byte ptr [rdi + rbx + 2], 4 + pinsrb xmm6, byte ptr [rdi + r13 + 2], 5 + pinsrb xmm6, byte ptr [rdi + r14 + 2], 6 + pinsrb xmm6, byte ptr [rdi + r8 + 2], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 2], 8 + pinsrb xmm6, byte ptr [rdi + r10 + 2], 9 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 2], 10 + pinsrb xmm6, byte ptr [rdi + rsi + 2], 11 + pinsrb xmm6, byte ptr [rdi + r15 + 2], 12 + pinsrb xmm6, byte ptr [rdi + r12 + 2], 13 + pinsrb xmm6, byte ptr [rdi + rdx + 2], 14 + pinsrb xmm6, byte ptr [rdi + rcx + 2], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rax + 8], 1 + pinsrb xmm12, byte ptr [rdi + r9 + 8], 2 + pinsrb xmm12, byte ptr [rdi + r11 + 8], 3 + pinsrb xmm12, byte ptr [rdi + rbx + 8], 4 + pinsrb xmm12, byte ptr [rdi + r13 + 8], 5 + pinsrb xmm12, byte ptr [rdi + r14 + 8], 6 + pinsrb xmm12, byte ptr [rdi + r8 + 8], 7 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rax + 8], 8 + pinsrb xmm12, byte ptr [rdi + r10 + 8], 9 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rax + 8], 10 + pinsrb xmm12, byte ptr [rdi + rsi + 8], 11 + pinsrb xmm12, byte ptr [rdi + r15 + 8], 12 + pinsrb xmm12, byte ptr [rdi + r12 + 8], 13 + pinsrb xmm12, byte ptr [rdi + rdx + 8], 14 + pinsrb xmm12, byte ptr [rdi + rcx + 8], 15 + pcmpgtb xmm3, xmm8 + movdqa xmmword ptr [rsp + 272], xmm3 # 16-byte Spill + movdqa xmm3, xmm13 + pcmpgtb xmm3, xmm12 + movdqa xmmword ptr [rsp + 304], xmm3 # 16-byte Spill + mov r12, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r12 + 16], 1 + pinsrb xmm14, byte ptr [rdi + r9 + 16], 2 + pinsrb xmm14, byte ptr [rdi + r11 + 16], 3 + pinsrb xmm14, byte ptr [rdi + rbx + 16], 4 + mov qword ptr [rsp + 64], rbx # 8-byte Spill + pinsrb xmm14, byte ptr [rdi + r13 + 16], 5 + pinsrb xmm14, byte ptr [rdi + r14 + 16], 6 + pinsrb xmm14, byte ptr [rdi + r8 + 16], 7 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r12 + 16], 8 + pinsrb xmm14, byte ptr [rdi + r10 + 16], 9 + mov r11, r10 + mov qword ptr [rsp + 88], r10 # 8-byte Spill + pinsrb xmm14, byte ptr [rdi + rax + 16], 10 + pinsrb xmm14, byte ptr [rdi + rsi + 16], 11 + mov r10, rsi + pinsrb xmm14, byte ptr [rdi + r15 + 16], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rsi + 16], 13 + pinsrb xmm14, byte ptr [rdi + rdx + 16], 14 + mov qword ptr [rsp + 48], rcx # 8-byte Spill + pinsrb xmm14, byte ptr [rdi + rcx + 16], 15 + movdqa xmm3, xmm13 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax + 24], 1 + pinsrb xmm4, byte ptr [rdi + r9 + 24], 2 + mov r9, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r9 + 24], 3 + pinsrb xmm4, byte ptr [rdi + rbx + 24], 4 + pinsrb xmm4, byte ptr [rdi + r13 + 24], 5 + pinsrb xmm4, byte ptr [rdi + r14 + 24], 6 + pinsrb xmm4, byte ptr [rdi + r8 + 24], 7 + mov qword ptr [rsp + 56], r8 # 8-byte Spill + pinsrb xmm4, byte ptr [rdi + r12 + 24], 8 + pinsrb xmm4, byte ptr [rdi + r11 + 24], 9 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax + 24], 10 + pinsrb xmm4, byte ptr [rdi + r10 + 24], 11 + mov rbx, r10 + pinsrb xmm4, byte ptr [rdi + r15 + 24], 12 + pinsrb xmm4, byte ptr [rdi + rsi + 24], 13 + pinsrb xmm4, byte ptr [rdi + rdx + 24], 14 + mov r10, rdx + mov qword ptr [rsp + 72], rdx # 8-byte Spill + pcmpgtb xmm3, xmm14 + movdqa xmmword ptr [rsp + 208], xmm3 # 16-byte Spill + pinsrb xmm4, byte ptr [rdi + rcx + 24], 15 + movdqa xmm3, xmm13 + pcmpgtb xmm3, xmm4 + movdqa xmmword ptr [rsp + 224], xmm3 # 16-byte Spill + movdqa xmm4, xmm13 + pcmpgtb xmm4, xmm7 + movdqa xmm12, xmm4 + movdqa xmm8, xmmword ptr [rip + .LCPI8_10] # xmm8 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm12, xmm8 + psubb xmm12, xmm4 + movdqa xmm4, xmm13 + movdqa xmm14, xmm13 + pcmpgtb xmm4, xmm6 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 13] + movd xmm7, esi + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rsi + 3], 1 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rax + 3], 2 + mov r11, r9 + pinsrb xmm15, byte ptr [rdi + r9 + 3], 3 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rcx + 3], 4 + mov rdx, r13 + pinsrb xmm15, byte ptr [rdi + r13 + 3], 5 + mov qword ptr [rsp + 96], r14 # 8-byte Spill + pinsrb xmm15, byte ptr [rdi + r14 + 3], 6 + pinsrb xmm15, byte ptr [rdi + r8 + 3], 7 + pinsrb xmm15, byte ptr [rdi + r12 + 3], 8 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r9 + 3], 9 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r8 + 3], 10 + mov qword ptr [rsp + 176], rbx # 8-byte Spill + pinsrb xmm15, byte ptr [rdi + rbx + 3], 11 + pinsrb xmm15, byte ptr [rdi + r15 + 3], 12 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r13 + 3], 13 + pinsrb xmm15, byte ptr [rdi + r10 + 3], 14 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r10 + 3], 15 + pinsrb xmm5, byte ptr [rdi + rsi + 4], 1 + pinsrb xmm5, byte ptr [rdi + rax + 4], 2 + pinsrb xmm5, byte ptr [rdi + r11 + 4], 3 + pinsrb xmm5, byte ptr [rdi + rcx + 4], 4 + pinsrb xmm5, byte ptr [rdi + rdx + 4], 5 + pinsrb xmm5, byte ptr [rdi + r14 + 4], 6 + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rcx + 4], 7 + pinsrb xmm5, byte ptr [rdi + r12 + 4], 8 + pinsrb xmm5, byte ptr [rdi + r9 + 4], 9 + pinsrb xmm5, byte ptr [rdi + r8 + 4], 10 + pinsrb xmm5, byte ptr [rdi + rbx + 4], 11 + pinsrb xmm5, byte ptr [rdi + r15 + 4], 12 + pinsrb xmm5, byte ptr [rdi + r13 + 4], 13 + mov rdx, r13 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rax + 4], 14 + movdqa xmm3, xmmword ptr [rsp + 272] # 16-byte Reload + pand xmm3, xmm8 + movdqa xmm6, xmmword ptr [rip + .LCPI8_11] # xmm6 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm4, xmm6 + por xmm4, xmm3 + mov r10, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [rdi + r10 + 14] + movd xmm6, esi + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r11 + 4], 15 + por xmm4, xmm12 + movdqa xmm12, xmm13 + pcmpgtb xmm12, xmm15 + pcmpgtb xmm13, xmm5 + movzx esi, byte ptr [rdi + r10 + 15] + movd xmm5, esi + mov r14, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r14 + 5], 1 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rsi + 5], 2 + mov r13, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r13 + 5], 3 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rsi + 5], 4 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rbx + 5], 5 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rsi + 5], 6 + pinsrb xmm2, byte ptr [rdi + rcx + 5], 7 + pinsrb xmm2, byte ptr [rdi + r12 + 5], 8 + pinsrb xmm2, byte ptr [rdi + r9 + 5], 9 + pinsrb xmm2, byte ptr [rdi + r8 + 5], 10 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rcx + 5], 11 + pinsrb xmm2, byte ptr [rdi + r15 + 5], 12 + pinsrb xmm2, byte ptr [rdi + rdx + 5], 13 + pinsrb xmm2, byte ptr [rdi + rax + 5], 14 + pinsrb xmm2, byte ptr [rdi + r11 + 5], 15 + movdqa xmm3, xmmword ptr [rip + .LCPI8_12] # xmm3 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm12, xmm3 + movdqa xmm3, xmmword ptr [rip + .LCPI8_13] # xmm3 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm13, xmm3 + por xmm13, xmm12 + movdqa xmm12, xmm14 + pcmpgtb xmm12, xmm2 + movzx esi, byte ptr [rdi + r10 + 17] + movd xmm2, esi + movdqa xmm3, xmmword ptr [rip + .LCPI8_14] # xmm3 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm12, xmm3 + por xmm12, xmm13 + movzx esi, byte ptr [rdi + r10 + 18] + movd xmm15, esi + movdqa xmm3, xmmword ptr [rsp + 192] # 16-byte Reload + pinsrb xmm3, byte ptr [rdi + r14 + 6], 1 + mov rax, r14 + mov r9, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r9 + 6], 2 + pinsrb xmm3, byte ptr [rdi + r13 + 6], 3 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rcx + 6], 4 + mov r13, rbx + pinsrb xmm3, byte ptr [rdi + rbx + 6], 5 + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 6], 6 + mov r14, rsi + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 6], 7 + pinsrb xmm3, byte ptr [rdi + r12 + 6], 8 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 6], 9 + pinsrb xmm3, byte ptr [rdi + r8 + 6], 10 + mov rbx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rbx + 6], 11 + mov qword ptr [rsp + 112], r15 # 8-byte Spill + pinsrb xmm3, byte ptr [rdi + r15 + 6], 12 + pinsrb xmm3, byte ptr [rdi + rdx + 6], 13 + mov r10, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r10 + 6], 14 + pinsrb xmm3, byte ptr [rdi + r11 + 6], 15 + pinsrb xmm1, byte ptr [rdi + rax + 7], 1 + pinsrb xmm1, byte ptr [rdi + r9 + 7], 2 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rax + 7], 3 + pinsrb xmm1, byte ptr [rdi + rcx + 7], 4 + pinsrb xmm1, byte ptr [rdi + r13 + 7], 5 + pinsrb xmm1, byte ptr [rdi + r14 + 7], 6 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + r14 + 7], 7 + pinsrb xmm1, byte ptr [rdi + r12 + 7], 8 + pinsrb xmm1, byte ptr [rdi + rsi + 7], 9 + pinsrb xmm1, byte ptr [rdi + r8 + 7], 10 + pinsrb xmm1, byte ptr [rdi + rbx + 7], 11 + pinsrb xmm1, byte ptr [rdi + r15 + 7], 12 + pinsrb xmm1, byte ptr [rdi + rdx + 7], 13 + pinsrb xmm1, byte ptr [rdi + r10 + 7], 14 + pinsrb xmm1, byte ptr [rdi + r11 + 7], 15 + mov r14, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r14 + 9], 1 + pinsrb xmm0, byte ptr [rdi + r9 + 9], 2 + pinsrb xmm0, byte ptr [rdi + rax + 9], 3 + pinsrb xmm0, byte ptr [rdi + rcx + 9], 4 + pinsrb xmm0, byte ptr [rdi + r13 + 9], 5 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rax + 9], 6 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rax + 9], 7 + pinsrb xmm0, byte ptr [rdi + r12 + 9], 8 + pinsrb xmm0, byte ptr [rdi + rsi + 9], 9 + pinsrb xmm0, byte ptr [rdi + r8 + 9], 10 + pinsrb xmm0, byte ptr [rdi + rbx + 9], 11 + pinsrb xmm0, byte ptr [rdi + r15 + 9], 12 + pinsrb xmm0, byte ptr [rdi + rdx + 9], 13 + pinsrb xmm0, byte ptr [rdi + r10 + 9], 14 + mov rax, r10 + pinsrb xmm0, byte ptr [rdi + r11 + 9], 15 + pinsrb xmm9, byte ptr [rdi + r14 + 10], 1 + pinsrb xmm9, byte ptr [rdi + r9 + 10], 2 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r10 + 10], 3 + pinsrb xmm9, byte ptr [rdi + rcx + 10], 4 + pinsrb xmm9, byte ptr [rdi + r13 + 10], 5 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r11 + 10], 6 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r14 + 10], 7 + pinsrb xmm9, byte ptr [rdi + r12 + 10], 8 + pinsrb xmm9, byte ptr [rdi + rsi + 10], 9 + pinsrb xmm9, byte ptr [rdi + r8 + 10], 10 + pinsrb xmm9, byte ptr [rdi + rbx + 10], 11 + pinsrb xmm9, byte ptr [rdi + r15 + 10], 12 + pinsrb xmm9, byte ptr [rdi + rdx + 10], 13 + por xmm12, xmm4 + movdqa xmm13, xmm14 + movdqa xmm4, xmm14 + pcmpgtb xmm4, xmm3 + pcmpgtb xmm14, xmm1 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [rdi + rbx + 19] + movd xmm1, esi + pinsrb xmm9, byte ptr [rdi + rax + 10], 14 + mov rdx, rax + movdqa xmm3, xmmword ptr [rip + .LCPI8_15] # xmm3 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm4, xmm3 + psllw xmm14, 7 + movdqa xmm3, xmmword ptr [rip + .LCPI8_6] # xmm3 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm14, xmm3 + por xmm14, xmm4 + movzx esi, byte ptr [rdi + rbx + 20] + movd xmm4, esi + mov r13, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r13 + 10], 15 + por xmm14, xmm12 + movdqa xmmword ptr [rsp + 192], xmm14 # 16-byte Spill + movdqa xmm14, xmm13 + movdqa xmm3, xmm13 + pcmpgtb xmm3, xmm0 + movdqa xmm12, xmm3 + pand xmm12, xmm8 + psubb xmm12, xmm3 + pcmpgtb xmm13, xmm9 + movzx esi, byte ptr [rdi + rbx + 21] + movd xmm0, esi + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rsi + 11], 1 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r8 + 11], 2 + pinsrb xmm10, byte ptr [rdi + r10 + 11], 3 + pinsrb xmm10, byte ptr [rdi + rcx + 11], 4 + mov r9, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r9 + 11], 5 + pinsrb xmm10, byte ptr [rdi + r11 + 11], 6 + mov rbx, r14 + pinsrb xmm10, byte ptr [rdi + r14 + 11], 7 + pinsrb xmm10, byte ptr [rdi + r12 + 11], 8 + mov r14, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r14 + 11], 9 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rax + 11], 10 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r15 + 11], 11 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + r12 + 11], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rax + 11], 13 + pinsrb xmm10, byte ptr [rdi + rdx + 11], 14 + pinsrb xmm10, byte ptr [rdi + r13 + 11], 15 + pinsrb xmm11, byte ptr [rdi + rsi + 12], 1 + pinsrb xmm11, byte ptr [rdi + r8 + 12], 2 + pinsrb xmm11, byte ptr [rdi + r10 + 12], 3 + pinsrb xmm11, byte ptr [rdi + rcx + 12], 4 + pinsrb xmm11, byte ptr [rdi + r9 + 12], 5 + pinsrb xmm11, byte ptr [rdi + r11 + 12], 6 + pinsrb xmm11, byte ptr [rdi + rbx + 12], 7 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rcx + 12], 8 + pinsrb xmm11, byte ptr [rdi + r14 + 12], 9 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r8 + 12], 10 + mov rbx, r15 + pinsrb xmm11, byte ptr [rdi + r15 + 12], 11 + mov r15, r12 + pinsrb xmm11, byte ptr [rdi + r12 + 12], 12 + pinsrb xmm11, byte ptr [rdi + rax + 12], 13 + pinsrb xmm11, byte ptr [rdi + rdx + 12], 14 + mov rcx, rdx + movdqa xmm3, xmmword ptr [rsp + 304] # 16-byte Reload + pand xmm3, xmm8 + pand xmm13, xmmword ptr [rip + .LCPI8_11] + por xmm13, xmm3 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [rdi + rdx + 22] + movd xmm8, esi + pinsrb xmm11, byte ptr [rdi + r13 + 12], 15 + por xmm13, xmm12 + movdqa xmm12, xmm14 + pcmpgtb xmm12, xmm10 + movdqa xmm3, xmm14 + pcmpgtb xmm3, xmm11 + movzx esi, byte ptr [rdi + rdx + 23] + movd xmm9, esi + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rax + 13], 1 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 13], 2 + pinsrb xmm7, byte ptr [rdi + r10 + 13], 3 + mov r11, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r11 + 13], 4 + pinsrb xmm7, byte ptr [rdi + r9 + 13], 5 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r14 + 13], 6 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 13], 7 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r12 + 13], 8 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 13], 9 + pinsrb xmm7, byte ptr [rdi + r8 + 13], 10 + pinsrb xmm7, byte ptr [rdi + rbx + 13], 11 + pinsrb xmm7, byte ptr [rdi + r15 + 13], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 13], 13 + pinsrb xmm7, byte ptr [rdi + rcx + 13], 14 + pinsrb xmm7, byte ptr [rdi + r13 + 13], 15 + pand xmm12, xmmword ptr [rip + .LCPI8_12] + pand xmm3, xmmword ptr [rip + .LCPI8_13] + por xmm3, xmm12 + movdqa xmm10, xmm14 + pcmpgtb xmm10, xmm7 + movzx esi, byte ptr [rdi + rdx + 25] + movd xmm11, esi + pand xmm10, xmmword ptr [rip + .LCPI8_14] + por xmm10, xmm3 + movzx esi, byte ptr [rdi + rdx + 26] + movd xmm7, esi + pinsrb xmm6, byte ptr [rdi + rax + 14], 1 + mov rsi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rsi + 14], 2 + pinsrb xmm6, byte ptr [rdi + r10 + 14], 3 + mov r13, r11 + pinsrb xmm6, byte ptr [rdi + r11 + 14], 4 + mov rdx, r9 + pinsrb xmm6, byte ptr [rdi + r9 + 14], 5 + mov r11, r14 + pinsrb xmm6, byte ptr [rdi + r14 + 14], 6 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r14 + 14], 7 + mov rcx, r12 + pinsrb xmm6, byte ptr [rdi + r12 + 14], 8 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r9 + 14], 9 + pinsrb xmm6, byte ptr [rdi + r8 + 14], 10 + pinsrb xmm6, byte ptr [rdi + rbx + 14], 11 + pinsrb xmm6, byte ptr [rdi + r15 + 14], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 14], 13 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 14], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rax + 14], 15 + mov r12, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r12 + 15], 1 + pinsrb xmm5, byte ptr [rdi + rsi + 15], 2 + pinsrb xmm5, byte ptr [rdi + r10 + 15], 3 + pinsrb xmm5, byte ptr [rdi + r13 + 15], 4 + pinsrb xmm5, byte ptr [rdi + rdx + 15], 5 + pinsrb xmm5, byte ptr [rdi + r11 + 15], 6 + pinsrb xmm5, byte ptr [rdi + r14 + 15], 7 + pinsrb xmm5, byte ptr [rdi + rcx + 15], 8 + pinsrb xmm5, byte ptr [rdi + r9 + 15], 9 + pinsrb xmm5, byte ptr [rdi + r8 + 15], 10 + pinsrb xmm5, byte ptr [rdi + rbx + 15], 11 + pinsrb xmm5, byte ptr [rdi + r15 + 15], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rax + 15], 13 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r12 + 15], 14 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rax + 15], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rax + 17], 1 + pinsrb xmm2, byte ptr [rdi + rsi + 17], 2 + pinsrb xmm2, byte ptr [rdi + r10 + 17], 3 + pinsrb xmm2, byte ptr [rdi + r13 + 17], 4 + pinsrb xmm2, byte ptr [rdi + rdx + 17], 5 + pinsrb xmm2, byte ptr [rdi + r11 + 17], 6 + pinsrb xmm2, byte ptr [rdi + r14 + 17], 7 + pinsrb xmm2, byte ptr [rdi + rcx + 17], 8 + pinsrb xmm2, byte ptr [rdi + r9 + 17], 9 + pinsrb xmm2, byte ptr [rdi + r8 + 17], 10 + pinsrb xmm2, byte ptr [rdi + rbx + 17], 11 + pinsrb xmm2, byte ptr [rdi + r15 + 17], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rax + 17], 13 + pinsrb xmm2, byte ptr [rdi + r12 + 17], 14 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r12 + 17], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rax + 18], 1 + pinsrb xmm15, byte ptr [rdi + rsi + 18], 2 + pinsrb xmm15, byte ptr [rdi + r10 + 18], 3 + pinsrb xmm15, byte ptr [rdi + r13 + 18], 4 + pinsrb xmm15, byte ptr [rdi + rdx + 18], 5 + pinsrb xmm15, byte ptr [rdi + r11 + 18], 6 + pinsrb xmm15, byte ptr [rdi + r14 + 18], 7 + mov r13, r14 + pinsrb xmm15, byte ptr [rdi + rcx + 18], 8 + pinsrb xmm15, byte ptr [rdi + r9 + 18], 9 + pinsrb xmm15, byte ptr [rdi + r8 + 18], 10 + pinsrb xmm15, byte ptr [rdi + rbx + 18], 11 + mov r9, rbx + pinsrb xmm15, byte ptr [rdi + r15 + 18], 12 + mov r8, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r8 + 18], 13 + por xmm10, xmm13 + movdqa xmm13, xmm14 + pcmpgtb xmm13, xmm6 + movdqa xmm3, xmm14 + pcmpgtb xmm3, xmm5 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [rdi + rax + 27] + movd xmm5, esi + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rcx + 18], 14 + pand xmm13, xmmword ptr [rip + .LCPI8_15] + psllw xmm3, 7 + pand xmm3, xmmword ptr [rip + .LCPI8_6] + por xmm3, xmm13 + movzx esi, byte ptr [rdi + rax + 28] + movd xmm6, esi + pinsrb xmm15, byte ptr [rdi + r12 + 18], 15 + por xmm3, xmm10 + movdqa xmmword ptr [rsp + 272], xmm3 # 16-byte Spill + movdqa xmm3, xmm14 + pcmpgtb xmm3, xmm2 + movdqa xmm13, xmm3 + movdqa xmm2, xmmword ptr [rip + .LCPI8_10] # xmm2 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm13, xmm2 + psubb xmm13, xmm3 + movdqa xmm10, xmm14 + pcmpgtb xmm10, xmm15 + movzx esi, byte ptr [rdi + rax + 29] + movd xmm3, esi + movdqa xmm15, xmmword ptr [rsp + 208] # 16-byte Reload + pand xmm15, xmm2 + movdqa xmm2, xmmword ptr [rip + .LCPI8_11] # xmm2 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm10, xmm2 + por xmm10, xmm15 + movzx esi, byte ptr [rdi + rax + 30] + movd xmm2, esi + movzx eax, byte ptr [rdi + rax + 31] + mov dword ptr [rsp + 80], eax # 4-byte Spill + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rax + 19], 1 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rcx + 19], 2 + pinsrb xmm1, byte ptr [rdi + r10 + 19], 3 + mov rdx, r10 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rsi + 19], 4 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + r10 + 19], 5 + pinsrb xmm1, byte ptr [rdi + r11 + 19], 6 + mov r14, r11 + pinsrb xmm1, byte ptr [rdi + r13 + 19], 7 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rsi + 19], 8 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rbx + 19], 9 + mov r11, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + r11 + 19], 10 + mov r15, r9 + pinsrb xmm1, byte ptr [rdi + r9 + 19], 11 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + r13 + 19], 12 + mov r9, r8 + pinsrb xmm1, byte ptr [rdi + r8 + 19], 13 + mov r8, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + r8 + 19], 14 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + r12 + 19], 15 + pinsrb xmm4, byte ptr [rdi + rax + 20], 1 + pinsrb xmm4, byte ptr [rdi + rcx + 20], 2 + pinsrb xmm4, byte ptr [rdi + rdx + 20], 3 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rdx + 20], 4 + pinsrb xmm4, byte ptr [rdi + r10 + 20], 5 + mov rdx, r10 + pinsrb xmm4, byte ptr [rdi + r14 + 20], 6 + mov r14, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r14 + 20], 7 + pinsrb xmm4, byte ptr [rdi + rsi + 20], 8 + mov rsi, rbx + pinsrb xmm4, byte ptr [rdi + rbx + 20], 9 + pinsrb xmm4, byte ptr [rdi + r11 + 20], 10 + mov rbx, r15 + pinsrb xmm4, byte ptr [rdi + r15 + 20], 11 + mov r15, r13 + pinsrb xmm4, byte ptr [rdi + r13 + 20], 12 + pinsrb xmm4, byte ptr [rdi + r9 + 20], 13 + pinsrb xmm4, byte ptr [rdi + r8 + 20], 14 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r12 + 20], 15 + por xmm10, xmm13 + movdqa xmm13, xmm14 + pcmpgtb xmm13, xmm1 + movdqa xmm15, xmm14 + pcmpgtb xmm15, xmm4 + movd xmm1, dword ptr [rsp + 80] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + pinsrb xmm0, byte ptr [rdi + rax + 21], 1 + pinsrb xmm8, byte ptr [rdi + rax + 22], 1 + pinsrb xmm9, byte ptr [rdi + rax + 23], 1 + pinsrb xmm11, byte ptr [rdi + rax + 25], 1 + pinsrb xmm7, byte ptr [rdi + rax + 26], 1 + pinsrb xmm5, byte ptr [rdi + rax + 27], 1 + pinsrb xmm6, byte ptr [rdi + rax + 28], 1 + pinsrb xmm3, byte ptr [rdi + rax + 29], 1 + pinsrb xmm2, byte ptr [rdi + rax + 30], 1 + pinsrb xmm1, byte ptr [rdi + rax + 31], 1 + pinsrb xmm0, byte ptr [rdi + rcx + 21], 2 + pinsrb xmm8, byte ptr [rdi + rcx + 22], 2 + pinsrb xmm9, byte ptr [rdi + rcx + 23], 2 + pinsrb xmm11, byte ptr [rdi + rcx + 25], 2 + pinsrb xmm7, byte ptr [rdi + rcx + 26], 2 + pinsrb xmm5, byte ptr [rdi + rcx + 27], 2 + pinsrb xmm6, byte ptr [rdi + rcx + 28], 2 + pinsrb xmm3, byte ptr [rdi + rcx + 29], 2 + pinsrb xmm2, byte ptr [rdi + rcx + 30], 2 + pinsrb xmm1, byte ptr [rdi + rcx + 31], 2 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r10 + 21], 3 + mov r13, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r13 + 21], 4 + pinsrb xmm0, byte ptr [rdi + rdx + 21], 5 + mov r11, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r11 + 21], 6 + pinsrb xmm0, byte ptr [rdi + r14 + 21], 7 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r9 + 21], 8 + pinsrb xmm0, byte ptr [rdi + rsi + 21], 9 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r8 + 21], 10 + pinsrb xmm0, byte ptr [rdi + rbx + 21], 11 + pinsrb xmm0, byte ptr [rdi + r15 + 21], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rcx + 21], 13 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rax + 21], 14 + pinsrb xmm0, byte ptr [rdi + r12 + 21], 15 + movdqa xmm4, xmmword ptr [rip + .LCPI8_12] # xmm4 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm13, xmm4 + movdqa xmm4, xmmword ptr [rip + .LCPI8_13] # xmm4 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm15, xmm4 + por xmm15, xmm13 + movdqa xmm13, xmm14 + pcmpgtb xmm13, xmm0 + movdqa xmm0, xmmword ptr [rip + .LCPI8_14] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm13, xmm0 + por xmm13, xmm15 + pinsrb xmm8, byte ptr [rdi + r10 + 22], 3 + pinsrb xmm8, byte ptr [rdi + r13 + 22], 4 + pinsrb xmm8, byte ptr [rdi + rdx + 22], 5 + pinsrb xmm8, byte ptr [rdi + r11 + 22], 6 + pinsrb xmm8, byte ptr [rdi + r14 + 22], 7 + pinsrb xmm8, byte ptr [rdi + r9 + 22], 8 + pinsrb xmm8, byte ptr [rdi + rsi + 22], 9 + pinsrb xmm8, byte ptr [rdi + r8 + 22], 10 + pinsrb xmm8, byte ptr [rdi + rbx + 22], 11 + pinsrb xmm8, byte ptr [rdi + r15 + 22], 12 + pinsrb xmm8, byte ptr [rdi + rcx + 22], 13 + pinsrb xmm8, byte ptr [rdi + rax + 22], 14 + pinsrb xmm8, byte ptr [rdi + r12 + 22], 15 + pinsrb xmm9, byte ptr [rdi + r10 + 23], 3 + pinsrb xmm9, byte ptr [rdi + r13 + 23], 4 + pinsrb xmm9, byte ptr [rdi + rdx + 23], 5 + pinsrb xmm9, byte ptr [rdi + r11 + 23], 6 + pinsrb xmm9, byte ptr [rdi + r14 + 23], 7 + pinsrb xmm9, byte ptr [rdi + r9 + 23], 8 + pinsrb xmm9, byte ptr [rdi + rsi + 23], 9 + pinsrb xmm9, byte ptr [rdi + r8 + 23], 10 + pinsrb xmm9, byte ptr [rdi + rbx + 23], 11 + pinsrb xmm9, byte ptr [rdi + r15 + 23], 12 + pinsrb xmm9, byte ptr [rdi + rcx + 23], 13 + pinsrb xmm9, byte ptr [rdi + rax + 23], 14 + pinsrb xmm9, byte ptr [rdi + r12 + 23], 15 + pinsrb xmm11, byte ptr [rdi + r10 + 25], 3 + pinsrb xmm11, byte ptr [rdi + r13 + 25], 4 + pinsrb xmm11, byte ptr [rdi + rdx + 25], 5 + pinsrb xmm11, byte ptr [rdi + r11 + 25], 6 + pinsrb xmm11, byte ptr [rdi + r14 + 25], 7 + pinsrb xmm11, byte ptr [rdi + r9 + 25], 8 + pinsrb xmm11, byte ptr [rdi + rsi + 25], 9 + pinsrb xmm11, byte ptr [rdi + r8 + 25], 10 + pinsrb xmm11, byte ptr [rdi + rbx + 25], 11 + pinsrb xmm11, byte ptr [rdi + r15 + 25], 12 + pinsrb xmm11, byte ptr [rdi + rcx + 25], 13 + pinsrb xmm11, byte ptr [rdi + rax + 25], 14 + pinsrb xmm11, byte ptr [rdi + r12 + 25], 15 + pinsrb xmm7, byte ptr [rdi + r10 + 26], 3 + pinsrb xmm7, byte ptr [rdi + r13 + 26], 4 + pinsrb xmm7, byte ptr [rdi + rdx + 26], 5 + pinsrb xmm7, byte ptr [rdi + r11 + 26], 6 + pinsrb xmm7, byte ptr [rdi + r14 + 26], 7 + pinsrb xmm7, byte ptr [rdi + r9 + 26], 8 + pinsrb xmm7, byte ptr [rdi + rsi + 26], 9 + mov r9, rsi + pinsrb xmm7, byte ptr [rdi + r8 + 26], 10 + pinsrb xmm7, byte ptr [rdi + rbx + 26], 11 + pinsrb xmm7, byte ptr [rdi + r15 + 26], 12 + pinsrb xmm7, byte ptr [rdi + rcx + 26], 13 + pinsrb xmm7, byte ptr [rdi + rax + 26], 14 + por xmm13, xmm10 + movdqa xmm12, xmm14 + movdqa xmm4, xmm14 + pcmpgtb xmm4, xmm8 + movdqa xmm0, xmm14 + pcmpgtb xmm0, xmm9 + movdqa xmm14, xmmword ptr [rip + .LCPI8_15] # xmm14 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm4, xmm14 + psllw xmm0, 7 + movdqa xmm15, xmmword ptr [rip + .LCPI8_6] # xmm15 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm0, xmm15 + por xmm0, xmm4 + pinsrb xmm7, byte ptr [rdi + r12 + 26], 15 + por xmm0, xmm13 + movdqa xmm4, xmm12 + pcmpgtb xmm4, xmm11 + movdqa xmm8, xmm4 + movdqa xmm11, xmmword ptr [rip + .LCPI8_10] # xmm11 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pand xmm8, xmm11 + psubb xmm8, xmm4 + movdqa xmm4, xmm12 + pcmpgtb xmm4, xmm7 + pinsrb xmm5, byte ptr [rdi + r10 + 27], 3 + pinsrb xmm5, byte ptr [rdi + r13 + 27], 4 + pinsrb xmm5, byte ptr [rdi + rdx + 27], 5 + pinsrb xmm5, byte ptr [rdi + r11 + 27], 6 + pinsrb xmm5, byte ptr [rdi + r14 + 27], 7 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rsi + 27], 8 + pinsrb xmm5, byte ptr [rdi + r9 + 27], 9 + pinsrb xmm5, byte ptr [rdi + r8 + 27], 10 + pinsrb xmm5, byte ptr [rdi + rbx + 27], 11 + pinsrb xmm5, byte ptr [rdi + r15 + 27], 12 + pinsrb xmm5, byte ptr [rdi + rcx + 27], 13 + pinsrb xmm5, byte ptr [rdi + rax + 27], 14 + pinsrb xmm5, byte ptr [rdi + r12 + 27], 15 + pinsrb xmm6, byte ptr [rdi + r10 + 28], 3 + pinsrb xmm6, byte ptr [rdi + r13 + 28], 4 + pinsrb xmm6, byte ptr [rdi + rdx + 28], 5 + pinsrb xmm6, byte ptr [rdi + r11 + 28], 6 + pinsrb xmm6, byte ptr [rdi + r14 + 28], 7 + pinsrb xmm6, byte ptr [rdi + rsi + 28], 8 + pinsrb xmm6, byte ptr [rdi + r9 + 28], 9 + pinsrb xmm6, byte ptr [rdi + r8 + 28], 10 + pinsrb xmm6, byte ptr [rdi + rbx + 28], 11 + pinsrb xmm6, byte ptr [rdi + r15 + 28], 12 + pinsrb xmm6, byte ptr [rdi + rcx + 28], 13 + movdqa xmm7, xmmword ptr [rsp + 224] # 16-byte Reload + pand xmm7, xmm11 + pinsrb xmm6, byte ptr [rdi + rax + 28], 14 + pand xmm4, xmmword ptr [rip + .LCPI8_11] + por xmm4, xmm7 + pinsrb xmm6, byte ptr [rdi + r12 + 28], 15 + por xmm4, xmm8 + movdqa xmm7, xmm12 + pcmpgtb xmm7, xmm5 + movdqa xmm5, xmm12 + pcmpgtb xmm5, xmm6 + pinsrb xmm3, byte ptr [rdi + r10 + 29], 3 + pinsrb xmm3, byte ptr [rdi + r13 + 29], 4 + pinsrb xmm3, byte ptr [rdi + rdx + 29], 5 + pinsrb xmm3, byte ptr [rdi + r11 + 29], 6 + pinsrb xmm3, byte ptr [rdi + r14 + 29], 7 + pinsrb xmm3, byte ptr [rdi + rsi + 29], 8 + pinsrb xmm3, byte ptr [rdi + r9 + 29], 9 + pinsrb xmm3, byte ptr [rdi + r8 + 29], 10 + pinsrb xmm3, byte ptr [rdi + rbx + 29], 11 + pinsrb xmm3, byte ptr [rdi + r15 + 29], 12 + pinsrb xmm3, byte ptr [rdi + rcx + 29], 13 + pinsrb xmm3, byte ptr [rdi + rax + 29], 14 + pinsrb xmm3, byte ptr [rdi + r12 + 29], 15 + pand xmm7, xmmword ptr [rip + .LCPI8_12] + pand xmm5, xmmword ptr [rip + .LCPI8_13] + por xmm5, xmm7 + movdqa xmm6, xmm12 + pcmpgtb xmm6, xmm3 + pand xmm6, xmmword ptr [rip + .LCPI8_14] + por xmm6, xmm5 + pinsrb xmm2, byte ptr [rdi + r10 + 30], 3 + pinsrb xmm1, byte ptr [rdi + r10 + 31], 3 + pinsrb xmm2, byte ptr [rdi + r13 + 30], 4 + pinsrb xmm1, byte ptr [rdi + r13 + 31], 4 + pinsrb xmm2, byte ptr [rdi + rdx + 30], 5 + pinsrb xmm1, byte ptr [rdi + rdx + 31], 5 + pinsrb xmm2, byte ptr [rdi + r11 + 30], 6 + pinsrb xmm1, byte ptr [rdi + r11 + 31], 6 + pinsrb xmm2, byte ptr [rdi + r14 + 30], 7 + pinsrb xmm1, byte ptr [rdi + r14 + 31], 7 + pinsrb xmm2, byte ptr [rdi + rsi + 30], 8 + pinsrb xmm1, byte ptr [rdi + rsi + 31], 8 + pinsrb xmm2, byte ptr [rdi + r9 + 30], 9 + pinsrb xmm1, byte ptr [rdi + r9 + 31], 9 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r8 + 30], 10 + pinsrb xmm1, byte ptr [rdi + r8 + 31], 10 + pinsrb xmm2, byte ptr [rdi + rbx + 30], 11 + pinsrb xmm1, byte ptr [rdi + rbx + 31], 11 + pinsrb xmm2, byte ptr [rdi + r15 + 30], 12 + pinsrb xmm1, byte ptr [rdi + r15 + 31], 12 + pinsrb xmm2, byte ptr [rdi + rcx + 30], 13 + pinsrb xmm1, byte ptr [rdi + rcx + 31], 13 + pinsrb xmm2, byte ptr [rdi + rax + 30], 14 + pinsrb xmm1, byte ptr [rdi + rax + 31], 14 + pinsrb xmm2, byte ptr [rdi + r12 + 30], 15 + pinsrb xmm1, byte ptr [rdi + r12 + 31], 15 + por xmm6, xmm4 + movdqa xmm3, xmm12 + pcmpgtb xmm3, xmm2 + pand xmm3, xmm14 + pcmpgtb xmm12, xmm1 + psllw xmm12, 7 + pand xmm12, xmm15 + por xmm12, xmm3 + por xmm12, xmm6 + movdqa xmm1, xmm0 + punpcklbw xmm1, xmm12 # xmm1 = xmm1[0],xmm12[0],xmm1[1],xmm12[1],xmm1[2],xmm12[2],xmm1[3],xmm12[3],xmm1[4],xmm12[4],xmm1[5],xmm12[5],xmm1[6],xmm12[6],xmm1[7],xmm12[7] + movdqa xmm5, xmmword ptr [rsp + 192] # 16-byte Reload + movdqa xmm3, xmm5 + movdqa xmm6, xmmword ptr [rsp + 272] # 16-byte Reload + punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] + movdqa xmm4, xmm3 + punpcklwd xmm4, xmm1 # xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3] + punpckhwd xmm3, xmm1 # xmm3 = xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7] + punpckhbw xmm0, xmm12 # xmm0 = xmm0[8],xmm12[8],xmm0[9],xmm12[9],xmm0[10],xmm12[10],xmm0[11],xmm12[11],xmm0[12],xmm12[12],xmm0[13],xmm12[13],xmm0[14],xmm12[14],xmm0[15],xmm12[15] + punpckhbw xmm5, xmm6 # xmm5 = xmm5[8],xmm6[8],xmm5[9],xmm6[9],xmm5[10],xmm6[10],xmm5[11],xmm6[11],xmm5[12],xmm6[12],xmm5[13],xmm6[13],xmm5[14],xmm6[14],xmm5[15],xmm6[15] + movdqa xmm1, xmm5 + punpcklwd xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3] + punpckhwd xmm5, xmm0 # xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7] + mov rcx, qword ptr [rsp + 120] # 8-byte Reload + movdqu xmmword ptr [r14 + 4*rcx + 48], xmm5 + movdqu xmmword ptr [r14 + 4*rcx + 32], xmm1 + movdqu xmmword ptr [r14 + 4*rcx + 16], xmm3 movdqu xmmword ptr [r14 + 4*rcx], xmm4 - add rcx, 4 - add rdx, 512 - cmp r8, rcx - jne .LBB8_201 -# %bb.202: - cmp r11, r8 - jne .LBB8_124 - jmp .LBB8_140 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + jne .LBB8_223 +# %bb.224: + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov r15b, byte ptr [rsp] # 1-byte Reload + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + jne .LBB8_146 + jmp .LBB8_150 +.LBB8_225: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, r11 + mov qword ptr [rsp + 264], rax # 8-byte Spill + mov qword ptr [rsp + 248], rcx # 8-byte Spill + lea rax, [r14 + 4*rcx] + mov qword ptr [rsp + 48], rax # 8-byte Spill + movzx eax, r15b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 128], r14 # 8-byte Spill + .p2align 4, 0x90 +.LBB8_226: # =>This Inner Loop Header: Depth=1 + mov r9, rax + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov rcx, rax + shl rcx, 5 + mov r14, rcx + mov rbx, rcx + mov rax, rcx + mov r9, rcx + mov r10, rcx + mov r8, rcx + mov qword ptr [rsp + 56], rcx # 8-byte Spill + mov rsi, rcx + mov r12, rcx + mov r15, rcx + mov rdx, rcx + mov rdi, rcx + movzx ecx, byte ptr [r11 + rcx] + movd xmm9, ecx + movzx ecx, byte ptr [r11 + rdi + 1] + movd xmm5, ecx + movzx ecx, byte ptr [r11 + rdi + 2] + movd xmm7, ecx + movzx ecx, byte ptr [r11 + rdi + 3] + movd xmm15, ecx + movzx ecx, byte ptr [r11 + rdi + 4] + movd xmm3, ecx + movzx ecx, byte ptr [r11 + rdi + 5] + movd xmm2, ecx + movzx ecx, byte ptr [r11 + rdi + 6] + movd xmm8, ecx + movzx ecx, byte ptr [r11 + rdi + 7] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rdi + 8] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rdi + 9] + movd xmm11, ecx + movzx ecx, byte ptr [r11 + rdi + 10] + movd xmm12, ecx + movzx ecx, byte ptr [r11 + rdi + 11] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 144], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rdi + 12] + movd xmm0, ecx + movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rdi + 13] + movd xmm14, ecx + movzx ecx, byte ptr [r11 + rdi + 14] + movd xmm13, ecx + mov qword ptr [rsp + 72], rdi # 8-byte Spill + mov r13, rdi + or r13, 32 + mov qword ptr [rsp + 8], r13 # 8-byte Spill + or r14, 64 + mov qword ptr [rsp + 32], r14 # 8-byte Spill + or rbx, 96 + mov qword ptr [rsp + 120], rbx # 8-byte Spill + or rax, 128 + or r9, 160 + or r10, 192 + mov qword ptr [rsp + 96], r10 # 8-byte Spill + mov rbx, r8 + or rbx, 224 + mov qword ptr [rsp + 80], rbx # 8-byte Spill + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + or rcx, 256 + or rsi, 288 + mov qword ptr [rsp + 88], rsi # 8-byte Spill + or r12, 320 + or r15, 352 + mov qword ptr [rsp + 104], r15 # 8-byte Spill + mov r8, rdx + or r8, 384 + mov rdx, rdi + or rdx, 416 + mov qword ptr [rsp + 40], rdx # 8-byte Spill + mov rdx, rdi + or rdx, 448 + mov qword ptr [rsp + 16], rdx # 8-byte Spill + mov rdx, rdi + or rdx, 480 + mov qword ptr [rsp + 24], rdx # 8-byte Spill + pinsrb xmm5, byte ptr [r11 + r13 + 1], 1 + pinsrb xmm5, byte ptr [r11 + r14 + 1], 2 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r13 + 1], 3 + pinsrb xmm5, byte ptr [r11 + rax + 1], 4 + mov r14, rax + pinsrb xmm5, byte ptr [r11 + r9 + 1], 5 + pinsrb xmm5, byte ptr [r11 + r10 + 1], 6 + pinsrb xmm5, byte ptr [r11 + rbx + 1], 7 + pinsrb xmm5, byte ptr [r11 + rcx + 1], 8 + pinsrb xmm5, byte ptr [r11 + rsi + 1], 9 + pinsrb xmm5, byte ptr [r11 + r12 + 1], 10 + pinsrb xmm5, byte ptr [r11 + r15 + 1], 11 + pinsrb xmm5, byte ptr [r11 + r8 + 1], 12 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rsi + 1], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rax + 1], 14 + pinsrb xmm5, byte ptr [r11 + rdx + 1], 15 + movdqa xmm10, xmmword ptr [rsp + 288] # 16-byte Reload + pminub xmm5, xmm10 + pcmpeqb xmm5, xmm10 + movdqa xmm6, xmm5 + movdqa xmm1, xmmword ptr [rip + .LCPI8_10] # xmm1 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pandn xmm6, xmm1 + paddb xmm6, xmm5 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + movzx edi, byte ptr [r11 + rdx + 15] + movd xmm0, edi + movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rax], 1 + mov r10, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r10], 2 + pinsrb xmm9, byte ptr [r11 + r13], 3 + mov rdi, r14 + pinsrb xmm9, byte ptr [r11 + r14], 4 + pinsrb xmm9, byte ptr [r11 + r9], 5 + mov rbx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rbx], 6 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r14], 7 + pinsrb xmm9, byte ptr [r11 + rcx], 8 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r15], 9 + pinsrb xmm9, byte ptr [r11 + r12], 10 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rdx], 11 + mov qword ptr [rsp + 112], r8 # 8-byte Spill + pinsrb xmm9, byte ptr [r11 + r8], 12 + pinsrb xmm9, byte ptr [r11 + rsi], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rax], 14 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r13], 15 + pminub xmm9, xmm10 + pcmpeqb xmm9, xmm10 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + rax + 2], 1 + pinsrb xmm7, byte ptr [r11 + r10 + 2], 2 + mov r13, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + r13 + 2], 3 + pinsrb xmm7, byte ptr [r11 + rdi + 2], 4 + pinsrb xmm7, byte ptr [r11 + r9 + 2], 5 + pinsrb xmm7, byte ptr [r11 + rbx + 2], 6 + pinsrb xmm7, byte ptr [r11 + r14 + 2], 7 + pinsrb xmm7, byte ptr [r11 + rcx + 2], 8 + pinsrb xmm7, byte ptr [r11 + r15 + 2], 9 + pinsrb xmm7, byte ptr [r11 + r12 + 2], 10 + pinsrb xmm7, byte ptr [r11 + rdx + 2], 11 + pinsrb xmm7, byte ptr [r11 + r8 + 2], 12 + pinsrb xmm7, byte ptr [r11 + rsi + 2], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + rax + 2], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + rax + 2], 15 + movdqa xmm0, xmm15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 3], 1 + pinsrb xmm0, byte ptr [r11 + r10 + 3], 2 + pinsrb xmm0, byte ptr [r11 + r13 + 3], 3 + pinsrb xmm0, byte ptr [r11 + rdi + 3], 4 + pinsrb xmm0, byte ptr [r11 + r9 + 3], 5 + pinsrb xmm0, byte ptr [r11 + rbx + 3], 6 + pinsrb xmm0, byte ptr [r11 + r14 + 3], 7 + pinsrb xmm0, byte ptr [r11 + rcx + 3], 8 + pinsrb xmm0, byte ptr [r11 + r15 + 3], 9 + pinsrb xmm0, byte ptr [r11 + r12 + 3], 10 + pinsrb xmm0, byte ptr [r11 + rdx + 3], 11 + pinsrb xmm0, byte ptr [r11 + r8 + 3], 12 + pinsrb xmm0, byte ptr [r11 + rsi + 3], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 3], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 3], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rax + 4], 1 + pinsrb xmm3, byte ptr [r11 + r10 + 4], 2 + pinsrb xmm3, byte ptr [r11 + r13 + 4], 3 + pinsrb xmm3, byte ptr [r11 + rdi + 4], 4 + pinsrb xmm3, byte ptr [r11 + r9 + 4], 5 + pinsrb xmm3, byte ptr [r11 + rbx + 4], 6 + pinsrb xmm3, byte ptr [r11 + r14 + 4], 7 + pinsrb xmm3, byte ptr [r11 + rcx + 4], 8 + pinsrb xmm3, byte ptr [r11 + r15 + 4], 9 + pinsrb xmm3, byte ptr [r11 + r12 + 4], 10 + pinsrb xmm3, byte ptr [r11 + rdx + 4], 11 + pinsrb xmm3, byte ptr [r11 + r8 + 4], 12 + pinsrb xmm3, byte ptr [r11 + rsi + 4], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rax + 4], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rax + 4], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rax + 5], 1 + pinsrb xmm2, byte ptr [r11 + r10 + 5], 2 + pinsrb xmm2, byte ptr [r11 + r13 + 5], 3 + pinsrb xmm2, byte ptr [r11 + rdi + 5], 4 + mov r10, rdi + pinsrb xmm2, byte ptr [r11 + r9 + 5], 5 + pinsrb xmm2, byte ptr [r11 + rbx + 5], 6 + pinsrb xmm2, byte ptr [r11 + r14 + 5], 7 + pinsrb xmm2, byte ptr [r11 + rcx + 5], 8 + mov qword ptr [rsp + 56], rcx # 8-byte Spill + pinsrb xmm2, byte ptr [r11 + r15 + 5], 9 + pinsrb xmm2, byte ptr [r11 + r12 + 5], 10 + mov qword ptr [rsp + 64], r12 # 8-byte Spill + pinsrb xmm2, byte ptr [r11 + rdx + 5], 11 + pinsrb xmm2, byte ptr [r11 + r8 + 5], 12 + pinsrb xmm2, byte ptr [r11 + rsi + 5], 13 + pandn xmm9, xmm1 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rax + 5], 14 + pminub xmm7, xmm10 + pcmpeqb xmm7, xmm10 + movdqa xmm1, xmmword ptr [rip + .LCPI8_11] # xmm1 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm7, xmm1 + por xmm7, xmm9 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 16] + movd xmm5, edi + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdx + 5], 15 + pminub xmm0, xmm10 + pcmpeqb xmm0, xmm10 + movdqa xmm1, xmmword ptr [rip + .LCPI8_12] # xmm1 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm0, xmm1 + por xmm0, xmm7 + movzx edi, byte ptr [r11 + rax + 17] + movd xmm1, edi + pcmpeqd xmm7, xmm7 + psubb xmm6, xmm7 + pcmpeqd xmm9, xmm9 + por xmm0, xmm6 + movzx edi, byte ptr [r11 + rax + 18] + mov rdx, rax + movd xmm7, edi + pminub xmm3, xmm10 + pcmpeqb xmm3, xmm10 + movdqa xmm6, xmmword ptr [rip + .LCPI8_13] # xmm6 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm3, xmm6 + pminub xmm2, xmm10 + pcmpeqb xmm2, xmm10 + movdqa xmm6, xmmword ptr [rip + .LCPI8_14] # xmm6 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm2, xmm6 + por xmm2, xmm3 + movzx edi, byte ptr [r11 + rax + 19] + movd xmm15, edi + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rsi + 6], 1 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r8 + 6], 2 + pinsrb xmm8, byte ptr [r11 + r13 + 6], 3 + pinsrb xmm8, byte ptr [r11 + r10 + 6], 4 + pinsrb xmm8, byte ptr [r11 + r9 + 6], 5 + pinsrb xmm8, byte ptr [r11 + rbx + 6], 6 + pinsrb xmm8, byte ptr [r11 + r14 + 6], 7 + pinsrb xmm8, byte ptr [r11 + rcx + 6], 8 + pinsrb xmm8, byte ptr [r11 + r15 + 6], 9 + pinsrb xmm8, byte ptr [r11 + r12 + 6], 10 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r15 + 6], 11 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r14 + 6], 12 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + r12 + 6], 13 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rcx + 6], 14 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm8, byte ptr [r11 + rax + 6], 15 + pminub xmm8, xmm10 + pcmpeqb xmm8, xmm10 + movdqa xmm3, xmmword ptr [rip + .LCPI8_15] # xmm3 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm8, xmm3 + por xmm8, xmm2 + movzx edi, byte ptr [r11 + rdx + 20] + movd xmm4, edi + movdqa xmm6, xmmword ptr [rsp + 160] # 16-byte Reload + pinsrb xmm6, byte ptr [r11 + rsi + 7], 1 + pinsrb xmm6, byte ptr [r11 + r8 + 7], 2 + pinsrb xmm6, byte ptr [r11 + r13 + 7], 3 + pinsrb xmm6, byte ptr [r11 + r10 + 7], 4 + pinsrb xmm6, byte ptr [r11 + r9 + 7], 5 + pinsrb xmm6, byte ptr [r11 + rbx + 7], 6 + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rbx + 7], 7 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdx + 7], 8 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdx + 7], 9 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdx + 7], 10 + mov rsi, r15 + pinsrb xmm6, byte ptr [r11 + r15 + 7], 11 + mov r15, r14 + pinsrb xmm6, byte ptr [r11 + r14 + 7], 12 + pinsrb xmm6, byte ptr [r11 + r12 + 7], 13 + pinsrb xmm6, byte ptr [r11 + rcx + 7], 14 + pinsrb xmm6, byte ptr [r11 + rax + 7], 15 + pminub xmm6, xmm10 + pcmpeqb xmm6, xmm10 + pxor xmm6, xmm9 + pcmpeqd xmm3, xmm3 + psllw xmm6, 7 + movdqa xmm2, xmmword ptr [rip + .LCPI8_6] # xmm2 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm6, xmm2 + por xmm6, xmm8 + movdqa xmm8, xmm6 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 21] + movd xmm6, edi + movdqa xmm2, xmmword ptr [rsp + 208] # 16-byte Reload + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rax + 8], 1 + mov r14, r8 + pinsrb xmm2, byte ptr [r11 + r8 + 8], 2 + mov rcx, r13 + pinsrb xmm2, byte ptr [r11 + r13 + 8], 3 + mov qword ptr [rsp + 304], r10 # 8-byte Spill + pinsrb xmm2, byte ptr [r11 + r10 + 8], 4 + pinsrb xmm2, byte ptr [r11 + r9 + 8], 5 + mov rdi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 8], 6 + pinsrb xmm2, byte ptr [r11 + rbx + 8], 7 + mov r13, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r13 + 8], 8 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdx + 8], 9 + mov r12, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r12 + 8], 10 + pinsrb xmm2, byte ptr [r11 + rsi + 8], 11 + mov r8, r15 + pinsrb xmm2, byte ptr [r11 + r15 + 8], 12 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rsi + 8], 13 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r15 + 8], 14 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rax + 9], 1 + pinsrb xmm11, byte ptr [r11 + r14 + 9], 2 + mov r15, r14 + pinsrb xmm11, byte ptr [r11 + rcx + 9], 3 + pinsrb xmm11, byte ptr [r11 + r10 + 9], 4 + pinsrb xmm11, byte ptr [r11 + r9 + 9], 5 + pinsrb xmm11, byte ptr [r11 + rdi + 9], 6 + pinsrb xmm11, byte ptr [r11 + rbx + 9], 7 + pinsrb xmm11, byte ptr [r11 + r13 + 9], 8 + mov rcx, r13 + pinsrb xmm11, byte ptr [r11 + rdx + 9], 9 + pinsrb xmm11, byte ptr [r11 + r12 + 9], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rax + 9], 11 + pinsrb xmm11, byte ptr [r11 + r8 + 9], 12 + mov rbx, r8 + pinsrb xmm11, byte ptr [r11 + rsi + 9], 13 + mov r12, rsi + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rsi + 9], 14 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + r13 + 9], 15 + por xmm8, xmm0 + movdqa xmmword ptr [rsp + 160], xmm8 # 16-byte Spill + pminub xmm11, xmm10 + pcmpeqb xmm11, xmm10 + movdqa xmm0, xmm11 + movdqa xmm8, xmmword ptr [rip + .LCPI8_10] # xmm8 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pandn xmm0, xmm8 + paddb xmm0, xmm11 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + movzx edi, byte ptr [r11 + rax + 22] + movd xmm9, edi + pinsrb xmm2, byte ptr [r11 + r13 + 8], 15 + pminub xmm2, xmm10 + pcmpeqb xmm2, xmm10 + pandn xmm2, xmm8 + mov r14, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + r14 + 10], 1 + pinsrb xmm12, byte ptr [r11 + r15 + 10], 2 + mov r15, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + r15 + 10], 3 + pinsrb xmm12, byte ptr [r11 + r10 + 10], 4 + mov qword ptr [rsp + 192], r9 # 8-byte Spill + pinsrb xmm12, byte ptr [r11 + r9 + 10], 5 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + r8 + 10], 6 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rdx + 10], 7 + pinsrb xmm12, byte ptr [r11 + rcx + 10], 8 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rcx + 10], 9 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rcx + 10], 10 + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rdx + 10], 11 + pinsrb xmm12, byte ptr [r11 + rbx + 10], 12 + mov r10, rbx + pinsrb xmm12, byte ptr [r11 + r12 + 10], 13 + pinsrb xmm12, byte ptr [r11 + rsi + 10], 14 + pinsrb xmm12, byte ptr [r11 + r13 + 10], 15 + mov rbx, r13 + pminub xmm12, xmm10 + pcmpeqb xmm12, xmm10 + pandn xmm12, xmmword ptr [rip + .LCPI8_11] + por xmm12, xmm2 + mov rsi, rax + movzx edi, byte ptr [r11 + rax + 23] + movd xmm8, edi + movdqa xmm2, xmmword ptr [rsp + 144] # 16-byte Reload + mov rax, r14 + pinsrb xmm2, byte ptr [r11 + r14 + 11], 1 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 11], 2 + mov r13, rdi + mov r14, r15 + pinsrb xmm2, byte ptr [r11 + r15 + 11], 3 + mov r15, qword ptr [rsp + 304] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r15 + 11], 4 + pinsrb xmm2, byte ptr [r11 + r9 + 11], 5 + pinsrb xmm2, byte ptr [r11 + r8 + 11], 6 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r9 + 11], 7 + mov rdi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 11], 8 + mov r8, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r8 + 11], 9 + pinsrb xmm2, byte ptr [r11 + rcx + 11], 10 + pinsrb xmm2, byte ptr [r11 + rdx + 11], 11 + pinsrb xmm2, byte ptr [r11 + r10 + 11], 12 + pinsrb xmm2, byte ptr [r11 + r12 + 11], 13 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rcx + 11], 14 + pinsrb xmm2, byte ptr [r11 + rbx + 11], 15 + pminub xmm2, xmm10 + pcmpeqb xmm2, xmm10 + pandn xmm2, xmmword ptr [rip + .LCPI8_12] + por xmm2, xmm12 + movzx edi, byte ptr [r11 + rsi + 24] + movd xmm11, edi + psubb xmm0, xmm3 + por xmm2, xmm0 + movdqa xmmword ptr [rsp + 144], xmm2 # 16-byte Spill + movzx edi, byte ptr [r11 + rsi + 25] + movd xmm3, edi + movdqa xmm2, xmmword ptr [rsp + 272] # 16-byte Reload + pinsrb xmm2, byte ptr [r11 + rax + 12], 1 + pinsrb xmm2, byte ptr [r11 + r13 + 12], 2 + mov rsi, r14 + pinsrb xmm2, byte ptr [r11 + r14 + 12], 3 + mov r10, r15 + pinsrb xmm2, byte ptr [r11 + r15 + 12], 4 + mov rdi, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 12], 5 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r15 + 12], 6 + pinsrb xmm2, byte ptr [r11 + r9 + 12], 7 + mov r12, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r12 + 12], 8 + mov rbx, r8 + pinsrb xmm2, byte ptr [r11 + r8 + 12], 9 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r14 + 12], 10 + mov rax, rdx + pinsrb xmm2, byte ptr [r11 + rdx + 12], 11 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r8 + 12], 12 + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rcx + 12], 13 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rcx + 12], 14 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdx + 12], 15 + mov rdx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + rdx + 13], 1 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + r13 + 13], 2 + pinsrb xmm14, byte ptr [r11 + rsi + 13], 3 + pinsrb xmm14, byte ptr [r11 + r10 + 13], 4 + pinsrb xmm14, byte ptr [r11 + rdi + 13], 5 + pinsrb xmm14, byte ptr [r11 + r15 + 13], 6 + pinsrb xmm14, byte ptr [r11 + r9 + 13], 7 + pinsrb xmm14, byte ptr [r11 + r12 + 13], 8 + pinsrb xmm14, byte ptr [r11 + rbx + 13], 9 + pinsrb xmm14, byte ptr [r11 + r14 + 13], 10 + mov rdx, rax + pinsrb xmm14, byte ptr [r11 + rax + 13], 11 + pinsrb xmm14, byte ptr [r11 + r8 + 13], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + rax + 13], 13 + pinsrb xmm14, byte ptr [r11 + rcx + 13], 14 + mov r13, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + r13 + 13], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rax + 14], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rax + 14], 2 + pinsrb xmm13, byte ptr [r11 + rsi + 14], 3 + pinsrb xmm13, byte ptr [r11 + r10 + 14], 4 + pinsrb xmm13, byte ptr [r11 + rdi + 14], 5 + pinsrb xmm13, byte ptr [r11 + r15 + 14], 6 + pinsrb xmm13, byte ptr [r11 + r9 + 14], 7 + pinsrb xmm13, byte ptr [r11 + r12 + 14], 8 + pinsrb xmm13, byte ptr [r11 + rbx + 14], 9 + pinsrb xmm13, byte ptr [r11 + r14 + 14], 10 + pinsrb xmm13, byte ptr [r11 + rdx + 14], 11 + pinsrb xmm13, byte ptr [r11 + r8 + 14], 12 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rax + 14], 13 + pinsrb xmm13, byte ptr [r11 + rcx + 14], 14 + pinsrb xmm13, byte ptr [r11 + r13 + 14], 15 + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + mov rcx, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rcx + 15], 1 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + r13 + 15], 2 + pinsrb xmm0, byte ptr [r11 + rsi + 15], 3 + pinsrb xmm0, byte ptr [r11 + r10 + 15], 4 + pinsrb xmm0, byte ptr [r11 + rdi + 15], 5 + pinsrb xmm0, byte ptr [r11 + r15 + 15], 6 + pinsrb xmm0, byte ptr [r11 + r9 + 15], 7 + pinsrb xmm0, byte ptr [r11 + r12 + 15], 8 + pinsrb xmm0, byte ptr [r11 + rbx + 15], 9 + pinsrb xmm0, byte ptr [r11 + r14 + 15], 10 + pinsrb xmm0, byte ptr [r11 + rdx + 15], 11 + pinsrb xmm0, byte ptr [r11 + r8 + 15], 12 + pinsrb xmm0, byte ptr [r11 + rax + 15], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 15], 14 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rcx + 15], 15 + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + rax + 17], 1 + pinsrb xmm1, byte ptr [r11 + r13 + 17], 2 + pinsrb xmm1, byte ptr [r11 + rsi + 17], 3 + pinsrb xmm1, byte ptr [r11 + r10 + 17], 4 + pinsrb xmm1, byte ptr [r11 + rdi + 17], 5 + pinsrb xmm1, byte ptr [r11 + r15 + 17], 6 + pinsrb xmm1, byte ptr [r11 + r9 + 17], 7 + pinsrb xmm1, byte ptr [r11 + r12 + 17], 8 + pinsrb xmm1, byte ptr [r11 + rbx + 17], 9 + pinsrb xmm1, byte ptr [r11 + r14 + 17], 10 + mov r14, rdx + pinsrb xmm1, byte ptr [r11 + rdx + 17], 11 + pinsrb xmm1, byte ptr [r11 + r8 + 17], 12 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + r8 + 17], 13 + pminub xmm2, xmm10 + pcmpeqb xmm2, xmm10 + pandn xmm2, xmmword ptr [rip + .LCPI8_13] + pminub xmm14, xmm10 + pcmpeqb xmm14, xmm10 + pandn xmm14, xmmword ptr [rip + .LCPI8_14] + por xmm14, xmm2 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + movzx edi, byte ptr [r11 + rdx + 26] + movd xmm2, edi + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + rax + 17], 14 + pminub xmm13, xmm10 + pcmpeqb xmm13, xmm10 + pandn xmm13, xmmword ptr [rip + .LCPI8_15] + por xmm13, xmm14 + movzx edi, byte ptr [r11 + rdx + 27] + movd xmm12, edi + pminub xmm0, xmm10 + pcmpeqb xmm0, xmm10 + pxor xmm0, xmmword ptr [rip + .LCPI8_16] + psllw xmm0, 7 + pand xmm0, xmmword ptr [rip + .LCPI8_6] + por xmm0, xmm13 + movzx edi, byte ptr [r11 + rdx + 28] + movd xmm13, edi + pinsrb xmm1, byte ptr [r11 + rcx + 17], 15 + mov r13, rcx + por xmm0, xmmword ptr [rsp + 144] # 16-byte Folded Reload + movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill + pminub xmm1, xmm10 + pcmpeqb xmm1, xmm10 + movdqa xmm0, xmm10 + movdqa xmm14, xmm1 + movdqa xmm10, xmmword ptr [rip + .LCPI8_10] # xmm10 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pandn xmm14, xmm10 + paddb xmm14, xmm1 + movdqa xmmword ptr [rsp + 144], xmm14 # 16-byte Spill + movzx edi, byte ptr [r11 + rdx + 29] + movd xmm10, edi + mov rax, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rax + 16], 1 + pinsrb xmm7, byte ptr [r11 + rax + 18], 1 + pinsrb xmm15, byte ptr [r11 + rax + 19], 1 + pinsrb xmm4, byte ptr [r11 + rax + 20], 1 + pinsrb xmm6, byte ptr [r11 + rax + 21], 1 + pinsrb xmm9, byte ptr [r11 + rax + 22], 1 + pinsrb xmm8, byte ptr [r11 + rax + 23], 1 + pinsrb xmm11, byte ptr [r11 + rax + 24], 1 + pinsrb xmm3, byte ptr [r11 + rax + 25], 1 + pinsrb xmm2, byte ptr [r11 + rax + 26], 1 + pinsrb xmm12, byte ptr [r11 + rax + 27], 1 + pinsrb xmm13, byte ptr [r11 + rax + 28], 1 + pinsrb xmm10, byte ptr [r11 + rax + 29], 1 + movzx edi, byte ptr [r11 + rdx + 30] + movd xmm14, edi + pinsrb xmm14, byte ptr [r11 + rax + 30], 1 + movzx edi, byte ptr [r11 + rdx + 31] + movd xmm1, edi + pinsrb xmm1, byte ptr [r11 + rax + 31], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rax + 16], 2 + pinsrb xmm7, byte ptr [r11 + rax + 18], 2 + pinsrb xmm15, byte ptr [r11 + rax + 19], 2 + pinsrb xmm4, byte ptr [r11 + rax + 20], 2 + pinsrb xmm6, byte ptr [r11 + rax + 21], 2 + pinsrb xmm9, byte ptr [r11 + rax + 22], 2 + pinsrb xmm8, byte ptr [r11 + rax + 23], 2 + pinsrb xmm11, byte ptr [r11 + rax + 24], 2 + pinsrb xmm3, byte ptr [r11 + rax + 25], 2 + pinsrb xmm2, byte ptr [r11 + rax + 26], 2 + pinsrb xmm12, byte ptr [r11 + rax + 27], 2 + pinsrb xmm13, byte ptr [r11 + rax + 28], 2 + pinsrb xmm10, byte ptr [r11 + rax + 29], 2 + pinsrb xmm14, byte ptr [r11 + rax + 30], 2 + pinsrb xmm1, byte ptr [r11 + rax + 31], 2 + pinsrb xmm5, byte ptr [r11 + rsi + 16], 3 + pinsrb xmm5, byte ptr [r11 + r10 + 16], 4 + mov rdi, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rdi + 16], 5 + pinsrb xmm5, byte ptr [r11 + r15 + 16], 6 + pinsrb xmm5, byte ptr [r11 + r9 + 16], 7 + mov rcx, r12 + pinsrb xmm5, byte ptr [r11 + r12 + 16], 8 + pinsrb xmm5, byte ptr [r11 + rbx + 16], 9 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rax + 16], 10 + pinsrb xmm5, byte ptr [r11 + r14 + 16], 11 + mov r12, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r12 + 16], 12 + mov rdx, r8 + pinsrb xmm5, byte ptr [r11 + r8 + 16], 13 + mov r8, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r8 + 16], 14 + pinsrb xmm5, byte ptr [r11 + r13 + 16], 15 + pminub xmm5, xmm0 + pcmpeqb xmm5, xmm0 + pinsrb xmm7, byte ptr [r11 + rsi + 18], 3 + pinsrb xmm7, byte ptr [r11 + r10 + 18], 4 + pinsrb xmm7, byte ptr [r11 + rdi + 18], 5 + pinsrb xmm7, byte ptr [r11 + r15 + 18], 6 + pinsrb xmm7, byte ptr [r11 + r9 + 18], 7 + pinsrb xmm7, byte ptr [r11 + rcx + 18], 8 + pinsrb xmm7, byte ptr [r11 + rbx + 18], 9 + pinsrb xmm7, byte ptr [r11 + rax + 18], 10 + pinsrb xmm7, byte ptr [r11 + r14 + 18], 11 + pinsrb xmm7, byte ptr [r11 + r12 + 18], 12 + pinsrb xmm7, byte ptr [r11 + rdx + 18], 13 + pinsrb xmm7, byte ptr [r11 + r8 + 18], 14 + pinsrb xmm7, byte ptr [r11 + r13 + 18], 15 + pinsrb xmm15, byte ptr [r11 + rsi + 19], 3 + pinsrb xmm15, byte ptr [r11 + r10 + 19], 4 + pinsrb xmm15, byte ptr [r11 + rdi + 19], 5 + pinsrb xmm15, byte ptr [r11 + r15 + 19], 6 + pinsrb xmm15, byte ptr [r11 + r9 + 19], 7 + pinsrb xmm15, byte ptr [r11 + rcx + 19], 8 + pinsrb xmm15, byte ptr [r11 + rbx + 19], 9 + pinsrb xmm15, byte ptr [r11 + rax + 19], 10 + pinsrb xmm15, byte ptr [r11 + r14 + 19], 11 + pinsrb xmm15, byte ptr [r11 + r12 + 19], 12 + pinsrb xmm15, byte ptr [r11 + rdx + 19], 13 + pinsrb xmm15, byte ptr [r11 + r8 + 19], 14 + pinsrb xmm15, byte ptr [r11 + r13 + 19], 15 + pinsrb xmm4, byte ptr [r11 + rsi + 20], 3 + pinsrb xmm4, byte ptr [r11 + r10 + 20], 4 + pinsrb xmm4, byte ptr [r11 + rdi + 20], 5 + pinsrb xmm4, byte ptr [r11 + r15 + 20], 6 + pinsrb xmm4, byte ptr [r11 + r9 + 20], 7 + pinsrb xmm4, byte ptr [r11 + rcx + 20], 8 + pinsrb xmm4, byte ptr [r11 + rbx + 20], 9 + pinsrb xmm4, byte ptr [r11 + rax + 20], 10 + pinsrb xmm4, byte ptr [r11 + r14 + 20], 11 + pinsrb xmm4, byte ptr [r11 + r12 + 20], 12 + pinsrb xmm4, byte ptr [r11 + rdx + 20], 13 + pinsrb xmm4, byte ptr [r11 + r8 + 20], 14 + pinsrb xmm4, byte ptr [r11 + r13 + 20], 15 + pinsrb xmm6, byte ptr [r11 + rsi + 21], 3 + pinsrb xmm6, byte ptr [r11 + r10 + 21], 4 + mov rax, r10 + pinsrb xmm6, byte ptr [r11 + rdi + 21], 5 + pinsrb xmm6, byte ptr [r11 + r15 + 21], 6 + pinsrb xmm6, byte ptr [r11 + r9 + 21], 7 + pinsrb xmm6, byte ptr [r11 + rcx + 21], 8 + pinsrb xmm6, byte ptr [r11 + rbx + 21], 9 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r10 + 21], 10 + pinsrb xmm6, byte ptr [r11 + r14 + 21], 11 + pinsrb xmm6, byte ptr [r11 + r12 + 21], 12 + pinsrb xmm6, byte ptr [r11 + rdx + 21], 13 + pinsrb xmm6, byte ptr [r11 + r8 + 21], 14 + pandn xmm5, xmmword ptr [rip + .LCPI8_10] + pminub xmm7, xmm0 + pcmpeqb xmm7, xmm0 + pandn xmm7, xmmword ptr [rip + .LCPI8_11] + por xmm7, xmm5 + pminub xmm15, xmm0 + pcmpeqb xmm15, xmm0 + movdqa xmm5, xmmword ptr [rip + .LCPI8_12] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm15, xmm5 + por xmm15, xmm7 + pinsrb xmm6, byte ptr [r11 + r13 + 21], 15 + pcmpeqd xmm5, xmm5 + movdqa xmm7, xmmword ptr [rsp + 144] # 16-byte Reload + psubb xmm7, xmm5 + por xmm15, xmm7 + pminub xmm4, xmm0 + pcmpeqb xmm4, xmm0 + movdqa xmm7, xmmword ptr [rip + .LCPI8_13] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm4, xmm7 + pminub xmm6, xmm0 + pcmpeqb xmm6, xmm0 + movdqa xmm7, xmmword ptr [rip + .LCPI8_14] # xmm7 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm6, xmm7 + por xmm6, xmm4 + pinsrb xmm9, byte ptr [r11 + rsi + 22], 3 + pinsrb xmm9, byte ptr [r11 + rax + 22], 4 + pinsrb xmm9, byte ptr [r11 + rdi + 22], 5 + pinsrb xmm9, byte ptr [r11 + r15 + 22], 6 + pinsrb xmm9, byte ptr [r11 + r9 + 22], 7 + pinsrb xmm9, byte ptr [r11 + rcx + 22], 8 + pinsrb xmm9, byte ptr [r11 + rbx + 22], 9 + pinsrb xmm9, byte ptr [r11 + r10 + 22], 10 + pinsrb xmm9, byte ptr [r11 + r14 + 22], 11 + pinsrb xmm9, byte ptr [r11 + r12 + 22], 12 + pinsrb xmm9, byte ptr [r11 + rdx + 22], 13 + pinsrb xmm9, byte ptr [r11 + r8 + 22], 14 + pinsrb xmm9, byte ptr [r11 + r13 + 22], 15 + pminub xmm9, xmm0 + pcmpeqb xmm9, xmm0 + movdqa xmm7, xmmword ptr [rip + .LCPI8_15] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm9, xmm7 + por xmm9, xmm6 + pinsrb xmm8, byte ptr [r11 + rsi + 23], 3 + pinsrb xmm8, byte ptr [r11 + rax + 23], 4 + pinsrb xmm8, byte ptr [r11 + rdi + 23], 5 + pinsrb xmm8, byte ptr [r11 + r15 + 23], 6 + pinsrb xmm8, byte ptr [r11 + r9 + 23], 7 + pinsrb xmm8, byte ptr [r11 + rcx + 23], 8 + pinsrb xmm8, byte ptr [r11 + rbx + 23], 9 + pinsrb xmm8, byte ptr [r11 + r10 + 23], 10 + pinsrb xmm8, byte ptr [r11 + r14 + 23], 11 + pinsrb xmm8, byte ptr [r11 + r12 + 23], 12 + pinsrb xmm8, byte ptr [r11 + rdx + 23], 13 + pinsrb xmm8, byte ptr [r11 + r8 + 23], 14 + pinsrb xmm8, byte ptr [r11 + r13 + 23], 15 + pminub xmm8, xmm0 + pcmpeqb xmm8, xmm0 + pxor xmm8, xmm5 + pcmpeqd xmm5, xmm5 + psllw xmm8, 7 + movdqa xmm6, xmmword ptr [rip + .LCPI8_6] # xmm6 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm8, xmm6 + por xmm8, xmm9 + pinsrb xmm11, byte ptr [r11 + rsi + 24], 3 + pinsrb xmm11, byte ptr [r11 + rax + 24], 4 + pinsrb xmm11, byte ptr [r11 + rdi + 24], 5 + pinsrb xmm11, byte ptr [r11 + r15 + 24], 6 + pinsrb xmm11, byte ptr [r11 + r9 + 24], 7 + pinsrb xmm11, byte ptr [r11 + rcx + 24], 8 + pinsrb xmm11, byte ptr [r11 + rbx + 24], 9 + pinsrb xmm11, byte ptr [r11 + r10 + 24], 10 + pinsrb xmm11, byte ptr [r11 + r14 + 24], 11 + pinsrb xmm11, byte ptr [r11 + r12 + 24], 12 + pinsrb xmm11, byte ptr [r11 + rdx + 24], 13 + pinsrb xmm11, byte ptr [r11 + r8 + 24], 14 + pinsrb xmm3, byte ptr [r11 + rsi + 25], 3 + pinsrb xmm3, byte ptr [r11 + rax + 25], 4 + pinsrb xmm3, byte ptr [r11 + rdi + 25], 5 + pinsrb xmm3, byte ptr [r11 + r15 + 25], 6 + pinsrb xmm3, byte ptr [r11 + r9 + 25], 7 + pinsrb xmm3, byte ptr [r11 + rcx + 25], 8 + pinsrb xmm3, byte ptr [r11 + rbx + 25], 9 + pinsrb xmm3, byte ptr [r11 + r10 + 25], 10 + pinsrb xmm3, byte ptr [r11 + r14 + 25], 11 + pinsrb xmm3, byte ptr [r11 + r12 + 25], 12 + pinsrb xmm3, byte ptr [r11 + rdx + 25], 13 + pinsrb xmm3, byte ptr [r11 + r8 + 25], 14 + pinsrb xmm3, byte ptr [r11 + r13 + 25], 15 + por xmm8, xmm15 + movdqa xmm4, xmm0 + pminub xmm3, xmm0 + pcmpeqb xmm3, xmm0 + movdqa xmm0, xmm3 + movdqa xmm9, xmmword ptr [rip + .LCPI8_10] # xmm9 = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1] + pandn xmm0, xmm9 + paddb xmm0, xmm3 + pinsrb xmm11, byte ptr [r11 + r13 + 24], 15 + pminub xmm11, xmm4 + pcmpeqb xmm11, xmm4 + pandn xmm11, xmm9 + pinsrb xmm2, byte ptr [r11 + rsi + 26], 3 + pinsrb xmm2, byte ptr [r11 + rax + 26], 4 + pinsrb xmm2, byte ptr [r11 + rdi + 26], 5 + pinsrb xmm2, byte ptr [r11 + r15 + 26], 6 + pinsrb xmm2, byte ptr [r11 + r9 + 26], 7 + pinsrb xmm2, byte ptr [r11 + rcx + 26], 8 + pinsrb xmm2, byte ptr [r11 + rbx + 26], 9 + pinsrb xmm2, byte ptr [r11 + r10 + 26], 10 + pinsrb xmm2, byte ptr [r11 + r14 + 26], 11 + pinsrb xmm2, byte ptr [r11 + r12 + 26], 12 + pinsrb xmm2, byte ptr [r11 + rdx + 26], 13 + pinsrb xmm2, byte ptr [r11 + r8 + 26], 14 + pinsrb xmm2, byte ptr [r11 + r13 + 26], 15 + pminub xmm2, xmm4 + pcmpeqb xmm2, xmm4 + pandn xmm2, xmmword ptr [rip + .LCPI8_11] + por xmm2, xmm11 + pinsrb xmm12, byte ptr [r11 + rsi + 27], 3 + pinsrb xmm12, byte ptr [r11 + rax + 27], 4 + pinsrb xmm12, byte ptr [r11 + rdi + 27], 5 + pinsrb xmm12, byte ptr [r11 + r15 + 27], 6 + pinsrb xmm12, byte ptr [r11 + r9 + 27], 7 + pinsrb xmm12, byte ptr [r11 + rcx + 27], 8 + pinsrb xmm12, byte ptr [r11 + rbx + 27], 9 + pinsrb xmm12, byte ptr [r11 + r10 + 27], 10 + pinsrb xmm12, byte ptr [r11 + r14 + 27], 11 + pinsrb xmm12, byte ptr [r11 + r12 + 27], 12 + pinsrb xmm12, byte ptr [r11 + rdx + 27], 13 + pinsrb xmm12, byte ptr [r11 + r8 + 27], 14 + pinsrb xmm12, byte ptr [r11 + r13 + 27], 15 + pminub xmm12, xmm4 + pcmpeqb xmm12, xmm4 + movdqa xmm3, xmm4 + pandn xmm12, xmmword ptr [rip + .LCPI8_12] + por xmm12, xmm2 + psubb xmm0, xmm5 + por xmm12, xmm0 + pinsrb xmm13, byte ptr [r11 + rsi + 28], 3 + pinsrb xmm10, byte ptr [r11 + rsi + 29], 3 + pinsrb xmm14, byte ptr [r11 + rsi + 30], 3 + pinsrb xmm1, byte ptr [r11 + rsi + 31], 3 + pinsrb xmm13, byte ptr [r11 + rax + 28], 4 + pinsrb xmm10, byte ptr [r11 + rax + 29], 4 + pinsrb xmm14, byte ptr [r11 + rax + 30], 4 + pinsrb xmm1, byte ptr [r11 + rax + 31], 4 + pinsrb xmm13, byte ptr [r11 + rdi + 28], 5 + pinsrb xmm10, byte ptr [r11 + rdi + 29], 5 + pinsrb xmm14, byte ptr [r11 + rdi + 30], 5 + pinsrb xmm1, byte ptr [r11 + rdi + 31], 5 + pinsrb xmm13, byte ptr [r11 + r15 + 28], 6 + pinsrb xmm10, byte ptr [r11 + r15 + 29], 6 + pinsrb xmm14, byte ptr [r11 + r15 + 30], 6 + pinsrb xmm1, byte ptr [r11 + r15 + 31], 6 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + r9 + 28], 7 + pinsrb xmm10, byte ptr [r11 + r9 + 29], 7 + pinsrb xmm14, byte ptr [r11 + r9 + 30], 7 + pinsrb xmm1, byte ptr [r11 + r9 + 31], 7 + mov rax, rcx + pinsrb xmm13, byte ptr [r11 + rcx + 28], 8 + pinsrb xmm10, byte ptr [r11 + rcx + 29], 8 + pinsrb xmm14, byte ptr [r11 + rcx + 30], 8 + pinsrb xmm1, byte ptr [r11 + rcx + 31], 8 + pinsrb xmm13, byte ptr [r11 + rbx + 28], 9 + pinsrb xmm10, byte ptr [r11 + rbx + 29], 9 + pinsrb xmm14, byte ptr [r11 + rbx + 30], 9 + pinsrb xmm1, byte ptr [r11 + rbx + 31], 9 + mov rax, r10 + pinsrb xmm13, byte ptr [r11 + r10 + 28], 10 + pinsrb xmm10, byte ptr [r11 + r10 + 29], 10 + pinsrb xmm14, byte ptr [r11 + r10 + 30], 10 + pinsrb xmm1, byte ptr [r11 + r10 + 31], 10 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rax + 28], 11 + pinsrb xmm10, byte ptr [r11 + rax + 29], 11 + pinsrb xmm14, byte ptr [r11 + rax + 30], 11 + pinsrb xmm1, byte ptr [r11 + rax + 31], 11 + mov rax, r12 + pinsrb xmm13, byte ptr [r11 + r12 + 28], 12 + pinsrb xmm10, byte ptr [r11 + r12 + 29], 12 + pinsrb xmm14, byte ptr [r11 + r12 + 30], 12 + pinsrb xmm1, byte ptr [r11 + r12 + 31], 12 + pinsrb xmm13, byte ptr [r11 + rdx + 28], 13 + pinsrb xmm10, byte ptr [r11 + rdx + 29], 13 + pinsrb xmm14, byte ptr [r11 + rdx + 30], 13 + pinsrb xmm1, byte ptr [r11 + rdx + 31], 13 + pinsrb xmm13, byte ptr [r11 + r8 + 28], 14 + pinsrb xmm10, byte ptr [r11 + r8 + 29], 14 + pinsrb xmm14, byte ptr [r11 + r8 + 30], 14 + pinsrb xmm1, byte ptr [r11 + r8 + 31], 14 + mov rax, r13 + pinsrb xmm13, byte ptr [r11 + r13 + 28], 15 + pinsrb xmm10, byte ptr [r11 + r13 + 29], 15 + pinsrb xmm14, byte ptr [r11 + r13 + 30], 15 + movdqa xmm0, xmm4 + pminub xmm13, xmm4 + pcmpeqb xmm13, xmm4 + pandn xmm13, xmmword ptr [rip + .LCPI8_13] + pminub xmm10, xmm4 + pcmpeqb xmm10, xmm4 + pandn xmm10, xmmword ptr [rip + .LCPI8_14] + por xmm10, xmm13 + pinsrb xmm1, byte ptr [r11 + r13 + 31], 15 + pminub xmm14, xmm4 + pcmpeqb xmm14, xmm4 + pandn xmm14, xmm7 + por xmm14, xmm10 + pminub xmm1, xmm4 + pcmpeqb xmm1, xmm4 + pxor xmm1, xmm5 + psllw xmm1, 7 + pand xmm1, xmm6 + por xmm1, xmm14 + por xmm1, xmm12 + movdqa xmm0, xmm8 + punpcklbw xmm0, xmm1 # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7] + movdqa xmm4, xmmword ptr [rsp + 160] # 16-byte Reload + movdqa xmm2, xmm4 + movdqa xmm5, xmmword ptr [rsp + 176] # 16-byte Reload + punpcklbw xmm2, xmm5 # xmm2 = xmm2[0],xmm5[0],xmm2[1],xmm5[1],xmm2[2],xmm5[2],xmm2[3],xmm5[3],xmm2[4],xmm5[4],xmm2[5],xmm5[5],xmm2[6],xmm5[6],xmm2[7],xmm5[7] + movdqa xmm3, xmm2 + punpcklwd xmm3, xmm0 # xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3] + punpckhwd xmm2, xmm0 # xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7] + punpckhbw xmm8, xmm1 # xmm8 = xmm8[8],xmm1[8],xmm8[9],xmm1[9],xmm8[10],xmm1[10],xmm8[11],xmm1[11],xmm8[12],xmm1[12],xmm8[13],xmm1[13],xmm8[14],xmm1[14],xmm8[15],xmm1[15] + punpckhbw xmm4, xmm5 # xmm4 = xmm4[8],xmm5[8],xmm4[9],xmm5[9],xmm4[10],xmm5[10],xmm4[11],xmm5[11],xmm4[12],xmm5[12],xmm4[13],xmm5[13],xmm4[14],xmm5[14],xmm4[15],xmm5[15] + movdqa xmm0, xmm4 + punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] + punpckhwd xmm4, xmm8 # xmm4 = xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7] + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movdqu xmmword ptr [r14 + 4*rcx + 48], xmm4 + movdqu xmmword ptr [r14 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r14 + 4*rcx + 16], xmm2 + movdqu xmmword ptr [r14 + 4*rcx], xmm3 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + jne .LBB8_226 +# %bb.227: + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + cmp rcx, qword ptr [rsp + 248] # 8-byte Folded Reload + mov r12, qword ptr [rsp + 136] # 8-byte Reload + mov r15b, byte ptr [rsp] # 1-byte Reload + mov rsi, qword ptr [rsp + 264] # 8-byte Reload + jne .LBB8_160 + jmp .LBB8_164 .Lfunc_end8: .size comparison_greater_scalar_arr_sse4, .Lfunc_end8-comparison_greater_scalar_arr_sse4 # -- End function @@ -46647,79 +47956,94 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 and rsp, -8 sub rsp, 72 # kill: def $r9d killed $r9d def $r9 - mov r11, r8 - mov r14, rcx + mov r13, r8 + mov r15, rcx cmp edi, 6 - jg .LBB9_29 + jg .LBB9_35 # %bb.1: cmp edi, 3 jle .LBB9_2 -# %bb.15: +# %bb.18: cmp edi, 4 - je .LBB9_68 -# %bb.16: + je .LBB9_83 +# %bb.19: cmp edi, 5 - je .LBB9_79 -# %bb.17: + je .LBB9_97 +# %bb.20: cmp edi, 6 - jne .LBB9_123 -# %bb.18: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB9_153 +# %bb.21: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_22 -# %bb.19: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB9_20: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB9_20 -# %bb.21: - add r14, 1 -.LBB9_22: - sar r15, 5 - cmp r11, 32 - jl .LBB9_26 + je .LBB9_28 +# %bb.22: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_26 # %bb.23: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 .LBB9_24: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill + mov ecx, dword ptr [rsi + 4*rax] + cmp ecx, dword ptr [rdx + 4*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl + add rax, 1 + add r10, -4 + cmp r8, rax + jne .LBB9_24 +# %bb.25: + sub rsi, r10 + sub rdx, r10 +.LBB9_26: + sub r13, r8 + je .LBB9_153 +# %bb.27: + add r15, 1 +.LBB9_28: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_32 +# %bb.29: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB9_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - setae byte ptr [rsp + 32] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] setae byte ptr [rsp + 20] # 1-byte Folded Spill @@ -46743,7 +48067,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 9] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - setae r8b + setae dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] setae r11b @@ -46783,7 +48107,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 11] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - setae byte ptr [rsp + 12] # 1-byte Folded Spill + setae byte ptr [rsp + 14] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] setae r9b @@ -46792,10 +48116,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 19] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - setae byte ptr [rsp + 13] # 1-byte Folded Spill + setae byte ptr [rsp + 12] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - setae byte ptr [rsp + 14] # 1-byte Folded Spill + setae byte ptr [rsp + 13] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] setae byte ptr [rsp + 15] # 1-byte Folded Spill @@ -46810,10 +48134,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 17] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] - setae dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setae r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -46822,34 +48146,34 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -46862,22 +48186,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -46894,27 +48219,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_24 -# %bb.25: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_26: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.27: - sub r11, r15 + jne .LBB9_30 +# %bb.31: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_32: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.33: xor ecx, ecx .p2align 4, 0x90 -.LBB9_28: # =>This Inner Loop Header: Depth=1 +.LBB9_34: # =>This Inner Loop Header: Depth=1 mov eax, dword ptr [rsi + 4*rcx] cmp eax, dword ptr [rdx + 4*rcx] lea r8, [rcx + 1] @@ -46922,7 +48246,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -46930,74 +48254,89 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_28 - jmp .LBB9_123 -.LBB9_29: + cmp r13, r8 + jne .LBB9_34 + jmp .LBB9_153 +.LBB9_35: cmp edi, 8 - jle .LBB9_30 -# %bb.43: + jle .LBB9_36 +# %bb.52: cmp edi, 9 - je .LBB9_101 -# %bb.44: + je .LBB9_125 +# %bb.53: cmp edi, 11 - je .LBB9_112 -# %bb.45: + je .LBB9_139 +# %bb.54: cmp edi, 12 - jne .LBB9_123 -# %bb.46: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB9_153 +# %bb.55: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_50 -# %bb.47: - movsxd rax, r9d + je .LBB9_62 +# %bb.56: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_60 +# %bb.57: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_48: # =>This Inner Loop Header: Depth=1 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero - add rsi, 8 - ucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_58: # =>This Inner Loop Header: Depth=1 + movsd xmm0, qword ptr [rsi + 8*rax] # xmm0 = mem[0],zero + ucomisd xmm0, qword ptr [rdx + 8*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_48 -# %bb.49: - add r14, 1 -.LBB9_50: - sar r15, 5 - cmp r11, 32 - jl .LBB9_54 -# %bb.51: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB9_58 +# %bb.59: + sub rsi, r10 + sub rdx, r10 +.LBB9_60: + sub r13, r8 + je .LBB9_153 +# %bb.61: + add r15, 1 +.LBB9_62: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_66 +# %bb.63: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_52: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_64: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero movsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero ucomisd xmm0, qword ptr [rdx] @@ -47021,7 +48360,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movsd xmm0, qword ptr [rsi + 56] # xmm0 = mem[0],zero setae r13b ucomisd xmm0, qword ptr [rdx + 56] - setae r15b + setae r14b movsd xmm0, qword ptr [rsi + 64] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 64] movsd xmm0, qword ptr [rsi + 72] # xmm0 = mem[0],zero @@ -47052,7 +48391,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 14] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 136] movsd xmm0, qword ptr [rsi + 144] # xmm0 = mem[0],zero - setae r14b + setae r15b ucomisd xmm0, qword ptr [rdx + 144] movsd xmm0, qword ptr [rsi + 152] # xmm0 = mem[0],zero setae r12b @@ -47098,8 +48437,8 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 add al, al add al, byte ptr [rsp + 4] # 1-byte Folded Reload shl r13b, 6 - shl r15b, 7 - or r15b, r13b + shl r14b, 7 + or r14b, r13b movzx r13d, byte ptr [rsp + 5] # 1-byte Folded Reload shl r13b, 2 or r13b, al @@ -47129,17 +48468,17 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl r9b, 6 shl bl, 7 or bl, r9b - or r15b, cl + or r14b, cl or bl, al - add r14b, r14b - add r14b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r15b, r15b + add r15b, byte ptr [rsp + 14] # 1-byte Folded Reload shl r12b, 2 - or r12b, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or r12b, r15b movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 or al, r12b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 or al, cl @@ -47147,12 +48486,12 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r8b, 7 or r8b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r8b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al @@ -47177,24 +48516,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl dil, 7 or dil, al or dil, cl - mov byte ptr [r14 + 2], r8b - mov byte ptr [r14 + 3], dil + mov byte ptr [r15 + 2], r8b + mov byte ptr [r15 + 3], dil add rdx, 256 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB9_52 -# %bb.53: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB9_54: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.55: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB9_64 +# %bb.65: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB9_66: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.67: xor ecx, ecx .p2align 4, 0x90 -.LBB9_56: # =>This Inner Loop Header: Depth=1 +.LBB9_68: # =>This Inner Loop Header: Depth=1 movsd xmm0, qword ptr [rsi + 8*rcx] # xmm0 = mem[0],zero ucomisd xmm0, qword ptr [rdx + 8*rcx] lea r8, [rcx + 1] @@ -47202,7 +48540,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -47210,72 +48548,93 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_56 - jmp .LBB9_123 + cmp r13, r8 + jne .LBB9_68 + jmp .LBB9_153 .LBB9_2: cmp edi, 2 - je .LBB9_57 + mov r8, r15 + je .LBB9_69 # %bb.3: cmp edi, 3 - jne .LBB9_123 + jne .LBB9_153 # %bb.4: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_8 + je .LBB9_11 # %bb.5: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB9_6: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - setge r10b - neg r10b - lea rdi, [rax + 7] + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 test rax, rax - cmovns rdi, rax + jle .LBB9_9 +# %bb.6: + movsxd rbx, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB9_7: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + setge r12b + neg r12b + lea rdi, [rbx + 7] + test rbx, rbx + cmovns rdi, rbx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d - mov ebx, 1 + movzx r14d, byte ptr [r15 + rdi] + lea r15d, [8*rdi] + mov ecx, ebx + sub ecx, r15d + mov r15, r8 + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB9_6 -# %bb.7: - add r14, 1 -.LBB9_8: - sar r15, 5 - cmp r11, 32 - jl .LBB9_12 -# %bb.9: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl eax, cl + xor r12b, r14b + and al, r12b + xor al, r14b + mov byte ptr [r8 + rdi], al + add r11, 1 + add rbx, 1 + add r10, -1 + cmp r9, r10 + jne .LBB9_7 +# %bb.8: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB9_9: + sub r13, rax + je .LBB9_153 +# %bb.10: + add r15, 1 +.LBB9_11: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_15 +# %bb.12: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_10: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setge cl movzx eax, byte ptr [rsi + 2] @@ -47295,7 +48654,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 4] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setge r15b + setge r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] setge byte ptr [rsp + 7] # 1-byte Folded Spill @@ -47310,7 +48669,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setge r14b + setge r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] setge byte ptr [rsp + 5] # 1-byte Folded Spill @@ -47370,12 +48729,12 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 cmp al, byte ptr [rdx + 31] setge r8b add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload mov eax, ecx movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, al @@ -47397,26 +48756,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 6] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 13] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 4 or al, cl @@ -47424,12 +48783,12 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al @@ -47455,24 +48814,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB9_10 -# %bb.11: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB9_12: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.13: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB9_13 +# %bb.14: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB9_15: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.16: xor ecx, ecx .p2align 4, 0x90 -.LBB9_14: # =>This Inner Loop Header: Depth=1 +.LBB9_17: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx ebx, byte ptr [rsi + rcx] cmp bl, byte ptr [rdx + rcx] @@ -47480,7 +48838,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -47488,74 +48846,89 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_14 - jmp .LBB9_123 -.LBB9_30: + cmp r13, r8 + jne .LBB9_17 + jmp .LBB9_153 +.LBB9_36: cmp edi, 7 - je .LBB9_90 -# %bb.31: + je .LBB9_111 +# %bb.37: cmp edi, 8 - jne .LBB9_123 -# %bb.32: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + jne .LBB9_153 +# %bb.38: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_36 -# %bb.33: - movsxd rax, r9d + je .LBB9_45 +# %bb.39: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_43 +# %bb.40: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_34: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_41: # =>This Inner Loop Header: Depth=1 + mov rcx, qword ptr [rsi + 8*rax] + cmp rcx, qword ptr [rdx + 8*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_34 -# %bb.35: - add r14, 1 -.LBB9_36: - sar r15, 5 - cmp r11, 32 - jl .LBB9_40 -# %bb.37: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB9_41 +# %bb.42: + sub rsi, r10 + sub rdx, r10 +.LBB9_43: + sub r13, r8 + je .LBB9_153 +# %bb.44: + add r15, 1 +.LBB9_45: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_49 +# %bb.46: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_38: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_47: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setae byte ptr [rsp + 32] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] setae byte ptr [rsp + 20] # 1-byte Folded Spill @@ -47579,7 +48952,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setae r8b + setae dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setae r11b @@ -47619,7 +48992,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 11] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setae byte ptr [rsp + 12] # 1-byte Folded Spill + setae byte ptr [rsp + 14] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setae r9b @@ -47628,10 +49001,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 19] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setae byte ptr [rsp + 13] # 1-byte Folded Spill + setae byte ptr [rsp + 12] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setae byte ptr [rsp + 14] # 1-byte Folded Spill + setae byte ptr [rsp + 13] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] setae byte ptr [rsp + 15] # 1-byte Folded Spill @@ -47646,10 +49019,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] - setae dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setae r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -47658,34 +49031,34 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -47698,22 +49071,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -47730,27 +49104,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_38 -# %bb.39: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_40: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.41: - sub r11, r15 + jne .LBB9_47 +# %bb.48: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_49: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.50: xor ecx, ecx .p2align 4, 0x90 -.LBB9_42: # =>This Inner Loop Header: Depth=1 +.LBB9_51: # =>This Inner Loop Header: Depth=1 mov rax, qword ptr [rsi + 8*rcx] cmp rax, qword ptr [rdx + 8*rcx] lea r8, [rcx + 1] @@ -47758,7 +49131,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -47766,68 +49139,83 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_42 - jmp .LBB9_123 -.LBB9_68: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_51 + jmp .LBB9_153 +.LBB9_83: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_72 -# %bb.69: - movsxd rax, r9d + je .LBB9_90 +# %bb.84: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_88 +# %bb.85: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_70: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_86: # =>This Inner Loop Header: Depth=1 + movzx ecx, word ptr [rsi + 2*rax] + cmp cx, word ptr [rdx + 2*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_70 -# %bb.71: - add r14, 1 -.LBB9_72: - sar r15, 5 - cmp r11, 32 - jl .LBB9_76 -# %bb.73: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB9_86 +# %bb.87: + sub rsi, r10 + sub rdx, r10 +.LBB9_88: + sub r13, r8 + je .LBB9_153 +# %bb.89: + add r15, 1 +.LBB9_90: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_94 +# %bb.91: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_74: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setae byte ptr [rsp + 32] # 1-byte Folded Spill + setae byte ptr [rsp + 40] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] setae byte ptr [rsp + 20] # 1-byte Folded Spill @@ -47851,7 +49239,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setae r8b + setae dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setae r11b @@ -47891,7 +49279,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 11] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setae byte ptr [rsp + 12] # 1-byte Folded Spill + setae byte ptr [rsp + 14] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setae r9b @@ -47900,10 +49288,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 19] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setae byte ptr [rsp + 13] # 1-byte Folded Spill + setae byte ptr [rsp + 12] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setae byte ptr [rsp + 14] # 1-byte Folded Spill + setae byte ptr [rsp + 13] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] setae byte ptr [rsp + 15] # 1-byte Folded Spill @@ -47918,10 +49306,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] - setae dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setae r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -47930,34 +49318,34 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -47970,22 +49358,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -48002,27 +49391,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 64 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_74 -# %bb.75: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_76: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.77: - sub r11, r15 + jne .LBB9_92 +# %bb.93: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_94: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.95: xor ecx, ecx .p2align 4, 0x90 -.LBB9_78: # =>This Inner Loop Header: Depth=1 +.LBB9_96: # =>This Inner Loop Header: Depth=1 movzx eax, word ptr [rsi + 2*rcx] cmp ax, word ptr [rdx + 2*rcx] lea r8, [rcx + 1] @@ -48030,7 +49418,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -48038,68 +49426,83 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_78 - jmp .LBB9_123 -.LBB9_79: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_96 + jmp .LBB9_153 +.LBB9_97: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_83 -# %bb.80: - movsxd rax, r9d + je .LBB9_104 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_102 +# %bb.99: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_81: # =>This Inner Loop Header: Depth=1 - movzx ecx, word ptr [rsi] - add rsi, 2 - cmp cx, word ptr [rdx] - lea rdx, [rdx + 2] - setge r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB9_100: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + movzx ebx, word ptr [rsi + 2*rax] + cmp bx, word ptr [rdx + 2*rax] + setge r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_81 -# %bb.82: - add r14, 1 -.LBB9_83: - sar r15, 5 - cmp r11, 32 - jl .LBB9_87 -# %bb.84: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -2 + cmp r8, rax + jne .LBB9_100 +# %bb.101: + sub rsi, r10 + sub rdx, r10 +.LBB9_102: + sub r13, r8 + je .LBB9_153 +# %bb.103: + add r15, 1 +.LBB9_104: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_108 +# %bb.105: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_85: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_106: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, word ptr [rsi] movzx ecx, word ptr [rsi + 2] cmp ax, word ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp cx, word ptr [rdx + 2] - setge byte ptr [rsp + 32] # 1-byte Folded Spill + setge byte ptr [rsp + 40] # 1-byte Folded Spill movzx eax, word ptr [rsi + 4] cmp ax, word ptr [rdx + 4] setge byte ptr [rsp + 20] # 1-byte Folded Spill @@ -48123,7 +49526,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 9] # 1-byte Folded Spill movzx eax, word ptr [rsi + 18] cmp ax, word ptr [rdx + 18] - setge r8b + setge dil movzx eax, word ptr [rsi + 20] cmp ax, word ptr [rdx + 20] setge r11b @@ -48163,7 +49566,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 11] # 1-byte Folded Spill cmp ax, word ptr [rdx + 44] movzx eax, word ptr [rsi + 46] - setge byte ptr [rsp + 12] # 1-byte Folded Spill + setge byte ptr [rsp + 14] # 1-byte Folded Spill cmp ax, word ptr [rdx + 46] movzx eax, word ptr [rsi + 48] setge r9b @@ -48172,10 +49575,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 19] # 1-byte Folded Spill cmp ax, word ptr [rdx + 50] movzx eax, word ptr [rsi + 52] - setge byte ptr [rsp + 13] # 1-byte Folded Spill + setge byte ptr [rsp + 12] # 1-byte Folded Spill cmp ax, word ptr [rdx + 52] movzx eax, word ptr [rsi + 54] - setge byte ptr [rsp + 14] # 1-byte Folded Spill + setge byte ptr [rsp + 13] # 1-byte Folded Spill cmp ax, word ptr [rdx + 54] movzx eax, word ptr [rsi + 56] setge byte ptr [rsp + 15] # 1-byte Folded Spill @@ -48190,10 +49593,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 64 cmp ax, word ptr [rdx + 62] - setge dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setge r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -48202,34 +49605,34 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -48242,22 +49645,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -48274,27 +49678,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 64 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_85 -# %bb.86: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_87: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.88: - sub r11, r15 + jne .LBB9_106 +# %bb.107: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_108: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.109: xor ecx, ecx .p2align 4, 0x90 -.LBB9_89: # =>This Inner Loop Header: Depth=1 +.LBB9_110: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] movzx edi, word ptr [rsi + 2*rcx] cmp di, word ptr [rdx + 2*rcx] @@ -48302,7 +49705,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -48310,68 +49713,83 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_89 - jmp .LBB9_123 -.LBB9_101: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_110 + jmp .LBB9_153 +.LBB9_125: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_105 -# %bb.102: - movsxd rax, r9d + je .LBB9_132 +# %bb.126: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_130 +# %bb.127: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_103: # =>This Inner Loop Header: Depth=1 - mov rcx, qword ptr [rsi] - add rsi, 8 - cmp rcx, qword ptr [rdx] - lea rdx, [rdx + 8] - setge r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB9_128: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov rbx, qword ptr [rsi + 8*rax] + cmp rbx, qword ptr [rdx + 8*rax] + setge r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_103 -# %bb.104: - add r14, 1 -.LBB9_105: - sar r15, 5 - cmp r11, 32 - jl .LBB9_109 -# %bb.106: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -8 + cmp r8, rax + jne .LBB9_128 +# %bb.129: + sub rsi, r10 + sub rdx, r10 +.LBB9_130: + sub r13, r8 + je .LBB9_153 +# %bb.131: + add r15, 1 +.LBB9_132: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_136 +# %bb.133: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_107: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_134: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov rax, qword ptr [rsi] mov rcx, qword ptr [rsi + 8] cmp rax, qword ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp rcx, qword ptr [rdx + 8] - setge byte ptr [rsp + 32] # 1-byte Folded Spill + setge byte ptr [rsp + 40] # 1-byte Folded Spill mov rax, qword ptr [rsi + 16] cmp rax, qword ptr [rdx + 16] setge byte ptr [rsp + 20] # 1-byte Folded Spill @@ -48395,7 +49813,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 9] # 1-byte Folded Spill mov rax, qword ptr [rsi + 72] cmp rax, qword ptr [rdx + 72] - setge r8b + setge dil mov rax, qword ptr [rsi + 80] cmp rax, qword ptr [rdx + 80] setge r11b @@ -48435,7 +49853,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 11] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 176] mov rax, qword ptr [rsi + 184] - setge byte ptr [rsp + 12] # 1-byte Folded Spill + setge byte ptr [rsp + 14] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 184] mov rax, qword ptr [rsi + 192] setge r9b @@ -48444,10 +49862,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 19] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 200] mov rax, qword ptr [rsi + 208] - setge byte ptr [rsp + 13] # 1-byte Folded Spill + setge byte ptr [rsp + 12] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 208] mov rax, qword ptr [rsi + 216] - setge byte ptr [rsp + 14] # 1-byte Folded Spill + setge byte ptr [rsp + 13] # 1-byte Folded Spill cmp rax, qword ptr [rdx + 216] mov rax, qword ptr [rsi + 224] setge byte ptr [rsp + 15] # 1-byte Folded Spill @@ -48462,10 +49880,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 17] # 1-byte Folded Spill add rsi, 256 cmp rax, qword ptr [rdx + 248] - setge dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setge r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -48474,34 +49892,34 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -48514,22 +49932,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -48546,27 +49965,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 256 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_107 -# %bb.108: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_109: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.110: - sub r11, r15 + jne .LBB9_134 +# %bb.135: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_136: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.137: xor ecx, ecx .p2align 4, 0x90 -.LBB9_111: # =>This Inner Loop Header: Depth=1 +.LBB9_138: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov rdi, qword ptr [rsi + 8*rcx] cmp rdi, qword ptr [rdx + 8*rcx] @@ -48574,7 +49992,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -48582,62 +50000,77 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_111 - jmp .LBB9_123 -.LBB9_112: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_138 + jmp .LBB9_153 +.LBB9_139: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_116 -# %bb.113: - movsxd rax, r9d + je .LBB9_146 +# %bb.140: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_144 +# %bb.141: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_114: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - ucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil +.LBB9_142: # =>This Inner Loop Header: Depth=1 + movss xmm0, dword ptr [rsi + 4*rax] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, dword ptr [rdx + 4*rax] + lea rcx, [r9 + rax] + mov r11d, 0 + adc r11b, -1 + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx + sar rdi, 3 + lea ebx, [8*rdi] + sub ecx, ebx + mov ebx, 1 + # kill: def $cl killed $cl killed $rcx + shl ebx, cl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_114 -# %bb.115: - add r14, 1 -.LBB9_116: - sar r15, 5 - cmp r11, 32 - jl .LBB9_120 -# %bb.117: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill - mov qword ptr [rsp + 40], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB9_142 +# %bb.143: + sub rsi, r10 + sub rdx, r10 +.LBB9_144: + sub r13, r8 + je .LBB9_153 +# %bb.145: + add r15, 1 +.LBB9_146: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_150 +# %bb.147: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill + mov qword ptr [rsp + 48], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_118: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_148: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero movss xmm1, dword ptr [rsi + 4] # xmm1 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx] @@ -48661,7 +50094,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movss xmm0, dword ptr [rsi + 28] # xmm0 = mem[0],zero,zero,zero setae r13b ucomiss xmm0, dword ptr [rdx + 28] - setae r15b + setae r14b movss xmm0, dword ptr [rsi + 32] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 32] movss xmm0, dword ptr [rsi + 36] # xmm0 = mem[0],zero,zero,zero @@ -48692,7 +50125,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 14] # 1-byte Folded Spill ucomiss xmm0, dword ptr [rdx + 68] movss xmm0, dword ptr [rsi + 72] # xmm0 = mem[0],zero,zero,zero - setae r14b + setae r15b ucomiss xmm0, dword ptr [rdx + 72] movss xmm0, dword ptr [rsi + 76] # xmm0 = mem[0],zero,zero,zero setae r12b @@ -48738,8 +50171,8 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 add al, al add al, byte ptr [rsp + 4] # 1-byte Folded Reload shl r13b, 6 - shl r15b, 7 - or r15b, r13b + shl r14b, 7 + or r14b, r13b movzx r13d, byte ptr [rsp + 5] # 1-byte Folded Reload shl r13b, 2 or r13b, al @@ -48769,17 +50202,17 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl r9b, 6 shl bl, 7 or bl, r9b - or r15b, cl + or r14b, cl or bl, al - add r14b, r14b - add r14b, byte ptr [rsp + 14] # 1-byte Folded Reload + add r15b, r15b + add r15b, byte ptr [rsp + 14] # 1-byte Folded Reload shl r12b, 2 - or r12b, r14b - mov r14, qword ptr [rsp + 48] # 8-byte Reload + or r12b, r15b movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 3 or al, r12b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 4 or al, cl @@ -48787,12 +50220,12 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload shl cl, 6 shl r8b, 7 or r8b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r8b, al movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload add al, al @@ -48817,24 +50250,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl dil, 7 or dil, al or dil, cl - mov byte ptr [r14 + 2], r8b - mov byte ptr [r14 + 3], dil + mov byte ptr [r15 + 2], r8b + mov byte ptr [r15 + 3], dil add rdx, 128 - add r14, 4 - add qword ptr [rsp + 40], -1 # 8-byte Folded Spill - jne .LBB9_118 -# %bb.119: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 32] # 8-byte Reload -.LBB9_120: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.121: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 48], -1 # 8-byte Folded Spill + jne .LBB9_148 +# %bb.149: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 40] # 8-byte Reload +.LBB9_150: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.151: xor ecx, ecx .p2align 4, 0x90 -.LBB9_122: # =>This Inner Loop Header: Depth=1 +.LBB9_152: # =>This Inner Loop Header: Depth=1 movss xmm0, dword ptr [rsi + 4*rcx] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, dword ptr [rdx + 4*rcx] lea r8, [rcx + 1] @@ -48842,7 +50274,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -48850,66 +50282,86 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_122 - jmp .LBB9_123 -.LBB9_57: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_152 + jmp .LBB9_153 +.LBB9_69: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_61 -# %bb.58: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB9_59: # =>This Inner Loop Header: Depth=1 - movzx ecx, byte ptr [rsi] - add rsi, 1 - cmp cl, byte ptr [rdx] - lea rdx, [rdx + 1] - mov r10d, 0 - adc r10b, -1 - lea rbx, [rax + 7] + je .LBB9_76 +# %bb.70: + mov eax, 8 + sub eax, r9d + cmp rax, r13 + cmovg rax, r13 test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor r10b, r8b - lea r9d, [8*rbx] - mov ecx, eax - sub ecx, r9d - mov edi, 1 + jle .LBB9_74 +# %bb.71: + movsxd r12, r9d + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r9, rax + neg r9 + xor r10d, r10d + xor r11d, r11d + .p2align 4, 0x90 +.LBB9_72: # =>This Inner Loop Header: Depth=1 + movzx ecx, byte ptr [rsi + r11] + cmp cl, byte ptr [rdx + r11] + mov edi, 0 + adc dil, -1 + lea rax, [r12 + 7] + test r12, r12 + cmovns rax, r12 + sar rax, 3 + movzx r14d, byte ptr [r15 + rax] + lea r15d, [8*rax] + mov ecx, r12d + sub ecx, r15d + mov r15, r8 + mov ebx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, r10b - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB9_59 -# %bb.60: - add r14, 1 -.LBB9_61: - sar r15, 5 - cmp r11, 32 - jl .LBB9_65 -# %bb.62: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill - mov qword ptr [rsp + 32], r15 # 8-byte Spill + shl ebx, cl + xor dil, r14b + and bl, dil + xor bl, r14b + mov byte ptr [r8 + rax], bl + add r11, 1 + add r12, 1 + add r10, -1 + cmp r9, r10 + jne .LBB9_72 +# %bb.73: + sub rsi, r10 + sub rdx, r10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload +.LBB9_74: + sub r13, rax + je .LBB9_153 +# %bb.75: + add r15, 1 +.LBB9_76: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_80 +# %bb.77: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 40], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_63: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_78: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill movzx eax, byte ptr [rsi] movzx ecx, byte ptr [rsi + 1] cmp al, byte ptr [rdx] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp cl, byte ptr [rdx + 1] setae cl movzx eax, byte ptr [rsi + 2] @@ -48929,7 +50381,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae byte ptr [rsp + 4] # 1-byte Folded Spill movzx eax, byte ptr [rsi + 7] cmp al, byte ptr [rdx + 7] - setae r15b + setae r14b movzx eax, byte ptr [rsi + 8] cmp al, byte ptr [rdx + 8] setae byte ptr [rsp + 7] # 1-byte Folded Spill @@ -48944,7 +50396,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setae r11b movzx eax, byte ptr [rsi + 12] cmp al, byte ptr [rdx + 12] - setae r14b + setae r15b movzx eax, byte ptr [rsi + 13] cmp al, byte ptr [rdx + 13] setae byte ptr [rsp + 5] # 1-byte Folded Spill @@ -49004,12 +50456,12 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 cmp al, byte ptr [rdx + 31] setae r8b add cl, cl - add cl, byte ptr [rsp + 40] # 1-byte Folded Reload + add cl, byte ptr [rsp + 48] # 1-byte Folded Reload mov eax, ecx movzx ecx, byte ptr [rsp + 4] # 1-byte Folded Reload shl cl, 6 - shl r15b, 7 - or r15b, cl + shl r14b, 7 + or r14b, cl movzx ecx, byte ptr [rsp + 20] # 1-byte Folded Reload shl cl, 2 or cl, al @@ -49031,26 +50483,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 or cl, dil - shl r14b, 4 - or r14b, r11b + shl r15b, 4 + or r15b, r11b movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 5 - or al, r14b + or al, r15b movzx edi, byte ptr [rsp + 6] # 1-byte Folded Reload shl dil, 6 shl bl, 7 or bl, dil - or r15b, cl + or r14b, cl or bl, al add r12b, r12b add r12b, byte ptr [rsp + 13] # 1-byte Folded Reload shl r13b, 2 or r13b, r12b - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 3 or al, r13b mov ecx, eax + mov r15, qword ptr [rsp + 24] # 8-byte Reload movzx eax, byte ptr [rsp + 9] # 1-byte Folded Reload shl al, 4 or al, cl @@ -49058,12 +50510,12 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 10] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r15b + mov byte ptr [r15], r14b movzx ecx, byte ptr [rsp + 11] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al @@ -49089,24 +50541,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl r8b, 7 or r8b, cl or r8b, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], r8b + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 32 - add r14, 4 - add qword ptr [rsp + 32], -1 # 8-byte Folded Spill - jne .LBB9_63 -# %bb.64: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 56] # 8-byte Reload -.LBB9_65: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.66: - sub r11, r15 + add r15, 4 + add qword ptr [rsp + 40], -1 # 8-byte Folded Spill + jne .LBB9_78 +# %bb.79: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 56] # 8-byte Reload +.LBB9_80: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.81: xor ecx, ecx .p2align 4, 0x90 -.LBB9_67: # =>This Inner Loop Header: Depth=1 +.LBB9_82: # =>This Inner Loop Header: Depth=1 movzx eax, byte ptr [rsi + rcx] cmp al, byte ptr [rdx + rcx] lea r8, [rcx + 1] @@ -49114,7 +50565,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 adc dil, -1 mov rbx, rcx shr rbx, 3 - movzx r9d, byte ptr [r14 + rbx] + movzx r9d, byte ptr [r15 + rbx] xor dil, r9b and cl, 7 mov al, 1 @@ -49122,68 +50573,83 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, dil xor al, r9b - mov byte ptr [r14 + rbx], al + mov byte ptr [r15 + rbx], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_67 - jmp .LBB9_123 -.LBB9_90: - lea r15, [r11 + 31] - test r11, r11 - cmovns r15, r11 + cmp r13, r8 + jne .LBB9_82 + jmp .LBB9_153 +.LBB9_111: lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB9_94 -# %bb.91: - movsxd rax, r9d + je .LBB9_118 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r13 + cmovg r8, r13 + test r8, r8 + jle .LBB9_116 +# %bb.113: + movsxd r9, r9d + xor r10d, r10d + xor eax, eax .p2align 4, 0x90 -.LBB9_92: # =>This Inner Loop Header: Depth=1 - mov ecx, dword ptr [rsi] - add rsi, 4 - cmp ecx, dword ptr [rdx] - lea rdx, [rdx + 4] - setge r10b - neg r10b - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax +.LBB9_114: # =>This Inner Loop Header: Depth=1 + lea rcx, [r9 + rax] + mov ebx, dword ptr [rsi + 4*rax] + cmp ebx, dword ptr [rdx + 4*rax] + setge r11b + neg r11b + lea rdi, [r9 + rax] + add rdi, 7 + test rcx, rcx + cmovns rdi, rcx sar rdi, 3 - movzx r8d, byte ptr [r14 + rdi] - xor r10b, r8b - lea r9d, [8*rdi] - mov ecx, eax - sub ecx, r9d + lea ebx, [8*rdi] + sub ecx, ebx mov ebx, 1 - # kill: def $cl killed $cl killed $ecx + # kill: def $cl killed $cl killed $rcx shl ebx, cl - and bl, r10b - xor bl, r8b - mov byte ptr [r14 + rdi], bl + movzx ecx, byte ptr [r15 + rdi] + xor r11b, cl + and bl, r11b + xor bl, cl + mov byte ptr [r15 + rdi], bl add rax, 1 - cmp rax, 8 - jne .LBB9_92 -# %bb.93: - add r14, 1 -.LBB9_94: - sar r15, 5 - cmp r11, 32 - jl .LBB9_98 -# %bb.95: - mov qword ptr [rsp + 24], r11 # 8-byte Spill - mov qword ptr [rsp + 64], r15 # 8-byte Spill - mov qword ptr [rsp + 56], r15 # 8-byte Spill + add r10, -4 + cmp r8, rax + jne .LBB9_114 +# %bb.115: + sub rsi, r10 + sub rdx, r10 +.LBB9_116: + sub r13, r8 + je .LBB9_153 +# %bb.117: + add r15, 1 +.LBB9_118: + lea rax, [r13 + 31] + test r13, r13 + cmovns rax, r13 + sar rax, 5 + cmp r13, 32 + jl .LBB9_122 +# %bb.119: + mov qword ptr [rsp + 32], r13 # 8-byte Spill + mov qword ptr [rsp + 64], rax # 8-byte Spill + mov qword ptr [rsp + 56], rax # 8-byte Spill .p2align 4, 0x90 -.LBB9_96: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 48], r14 # 8-byte Spill +.LBB9_120: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 24], r15 # 8-byte Spill mov eax, dword ptr [rsi] mov ecx, dword ptr [rsi + 4] cmp eax, dword ptr [rdx] - setge byte ptr [rsp + 40] # 1-byte Folded Spill + setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp ecx, dword ptr [rdx + 4] - setge byte ptr [rsp + 32] # 1-byte Folded Spill + setge byte ptr [rsp + 40] # 1-byte Folded Spill mov eax, dword ptr [rsi + 8] cmp eax, dword ptr [rdx + 8] setge byte ptr [rsp + 20] # 1-byte Folded Spill @@ -49207,7 +50673,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 9] # 1-byte Folded Spill mov eax, dword ptr [rsi + 36] cmp eax, dword ptr [rdx + 36] - setge r8b + setge dil mov eax, dword ptr [rsi + 40] cmp eax, dword ptr [rdx + 40] setge r11b @@ -49247,7 +50713,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 11] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 88] mov eax, dword ptr [rsi + 92] - setge byte ptr [rsp + 12] # 1-byte Folded Spill + setge byte ptr [rsp + 14] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 92] mov eax, dword ptr [rsi + 96] setge r9b @@ -49256,10 +50722,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 19] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 100] mov eax, dword ptr [rsi + 104] - setge byte ptr [rsp + 13] # 1-byte Folded Spill + setge byte ptr [rsp + 12] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 104] mov eax, dword ptr [rsi + 108] - setge byte ptr [rsp + 14] # 1-byte Folded Spill + setge byte ptr [rsp + 13] # 1-byte Folded Spill cmp eax, dword ptr [rdx + 108] mov eax, dword ptr [rsi + 112] setge byte ptr [rsp + 15] # 1-byte Folded Spill @@ -49274,10 +50740,10 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 setge byte ptr [rsp + 17] # 1-byte Folded Spill sub rsi, -128 cmp eax, dword ptr [rdx + 124] - setge dil - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + setge r8b + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 40] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 4] # 1-byte Folded Reload shl al, 6 @@ -49286,34 +50752,34 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 movzx eax, byte ptr [rsp + 20] # 1-byte Folded Reload shl al, 2 or al, cl - add r8b, r8b - add r8b, byte ptr [rsp + 9] # 1-byte Folded Reload + add dil, dil + add dil, byte ptr [rsp + 9] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 21] # 1-byte Folded Reload shl cl, 3 or cl, al mov eax, ecx shl r11b, 2 - or r11b, r8b + or r11b, dil movzx ecx, byte ptr [rsp + 22] # 1-byte Folded Reload shl cl, 4 or cl, al - mov r8d, ecx + mov edi, ecx shl r15b, 3 or r15b, r11b movzx ecx, byte ptr [rsp + 23] # 1-byte Folded Reload shl cl, 5 - or cl, r8b + or cl, dil movzx eax, byte ptr [rsp + 5] # 1-byte Folded Reload shl al, 4 or al, r15b - mov r8d, eax + mov edi, eax movzx eax, byte ptr [rsp + 6] # 1-byte Folded Reload shl al, 5 - or al, r8b - movzx r8d, byte ptr [rsp + 7] # 1-byte Folded Reload - shl r8b, 6 + or al, dil + movzx edi, byte ptr [rsp + 7] # 1-byte Folded Reload + shl dil, 6 shl bl, 7 - or bl, r8b + or bl, dil or r13b, cl or bl, al add r10b, r10b @@ -49326,22 +50792,23 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, 4 or al, r12b mov ecx, eax - mov r14, qword ptr [rsp + 48] # 8-byte Reload movzx eax, byte ptr [rsp + 11] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r14], r13b - movzx ecx, byte ptr [rsp + 12] # 1-byte Folded Reload + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + mov byte ptr [rdi], r13b + mov r15, qword ptr [rsp + 24] # 8-byte Reload + movzx ecx, byte ptr [rsp + 14] # 1-byte Folded Reload shl cl, 6 shl r9b, 7 or r9b, cl - mov byte ptr [r14 + 1], bl + mov byte ptr [r15 + 1], bl or r9b, al - movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 12] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 19] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 14] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 13] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax @@ -49358,27 +50825,26 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 or al, cl movzx ecx, byte ptr [rsp + 17] # 1-byte Folded Reload shl cl, 6 - shl dil, 7 - or dil, cl - or dil, al - mov byte ptr [r14 + 2], r9b - mov byte ptr [r14 + 3], dil + shl r8b, 7 + or r8b, cl + or r8b, al + mov byte ptr [r15 + 2], r9b + mov byte ptr [r15 + 3], r8b add rdx, 128 - add r14, 4 + add r15, 4 add qword ptr [rsp + 56], -1 # 8-byte Folded Spill - jne .LBB9_96 -# %bb.97: - mov r11, qword ptr [rsp + 24] # 8-byte Reload - mov r15, qword ptr [rsp + 64] # 8-byte Reload -.LBB9_98: - shl r15, 5 - cmp r15, r11 - jge .LBB9_123 -# %bb.99: - sub r11, r15 + jne .LBB9_120 +# %bb.121: + mov r13, qword ptr [rsp + 32] # 8-byte Reload + mov rax, qword ptr [rsp + 64] # 8-byte Reload +.LBB9_122: + shl rax, 5 + sub r13, rax + jle .LBB9_153 +# %bb.123: xor ecx, ecx .p2align 4, 0x90 -.LBB9_100: # =>This Inner Loop Header: Depth=1 +.LBB9_124: # =>This Inner Loop Header: Depth=1 lea r8, [rcx + 1] mov edi, dword ptr [rsi + 4*rcx] cmp edi, dword ptr [rdx + 4*rcx] @@ -49386,7 +50852,7 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 neg bl mov rdi, rcx shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] + movzx r9d, byte ptr [r15 + rdi] xor bl, r9b and cl, 7 mov al, 1 @@ -49394,11 +50860,11 @@ comparison_greater_equal_arr_arr_sse4: # @comparison_greater_equal_arr_arr_sse4 shl al, cl and al, bl xor al, r9b - mov byte ptr [r14 + rdi], al + mov byte ptr [r15 + rdi], al mov rcx, r8 - cmp r11, r8 - jne .LBB9_100 -.LBB9_123: + cmp r13, r8 + jne .LBB9_124 +.LBB9_153: lea rsp, [rbp - 40] pop rbx pop r12 @@ -49622,126 +51088,139 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar push r12 push rbx and rsp, -16 - sub rsp, 496 + sub rsp, 480 # kill: def $r9d killed $r9d def $r9 - mov r10, r8 - mov r14, rcx + mov r14, r8 + mov r12, rcx cmp edi, 6 - jg .LBB10_26 + jg .LBB10_24 # %bb.1: cmp edi, 3 jle .LBB10_2 -# %bb.10: +# %bb.6: cmp edi, 4 - je .LBB10_99 -# %bb.11: - cmp edi, 5 je .LBB10_114 -# %bb.12: +# %bb.7: + cmp edi, 5 + je .LBB10_131 +# %bb.8: cmp edi, 6 - jne .LBB10_201 -# %bb.13: + jne .LBB10_227 +# %bb.9: mov r13d, dword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] + lea ecx, [r9 + 7] test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB10_17 -# %bb.14: - movsxd rax, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB10_15 +# %bb.10: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_13 +# %bb.11: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_15: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - mov edx, 0 - adc dl, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_12: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + mov ebx, 0 + adc bl, -1 + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_15 + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_12 +.LBB10_13: + sub r14, r8 + je .LBB10_227 +# %bb.14: + add r12, 1 +.LBB10_15: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB10_19 # %bb.16: - add r14, 1 -.LBB10_17: - sar r11, 5 - cmp r10, 32 - jl .LBB10_21 -# %bb.18: - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 368], r11 # 8-byte Spill - mov qword ptr [rsp + 320], r11 # 8-byte Spill + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 352], rax # 8-byte Spill + mov qword ptr [rsp + 304], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_19: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 352], r14 # 8-byte Spill +.LBB10_17: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 8], r12 # 8-byte Spill cmp dword ptr [rsi], r13d - setae byte ptr [rsp + 240] # 1-byte Folded Spill + setae byte ptr [rsp + 320] # 1-byte Folded Spill cmp dword ptr [rsi + 4], r13d - setae r10b + setae r9b cmp dword ptr [rsi + 8], r13d setae r14b cmp dword ptr [rsi + 12], r13d - setae byte ptr [rsp + 272] # 1-byte Folded Spill + setae byte ptr [rsp + 240] # 1-byte Folded Spill cmp dword ptr [rsi + 16], r13d - setae byte ptr [rsp + 208] # 1-byte Folded Spill + setae byte ptr [rsp + 224] # 1-byte Folded Spill cmp dword ptr [rsi + 20], r13d - setae byte ptr [rsp + 192] # 1-byte Folded Spill + setae byte ptr [rsp + 176] # 1-byte Folded Spill cmp dword ptr [rsi + 24], r13d setae al cmp dword ptr [rsi + 28], r13d - setae bl + setae r11b cmp dword ptr [rsi + 32], r13d setae byte ptr [rsp + 336] # 1-byte Folded Spill cmp dword ptr [rsi + 36], r13d - setae dil + setae cl cmp dword ptr [rsi + 40], r13d - setae r8b + setae dil cmp dword ptr [rsi + 44], r13d - setae r9b + setae r8b cmp dword ptr [rsi + 48], r13d - setae r11b + setae r10b cmp dword ptr [rsi + 52], r13d setae r12b cmp dword ptr [rsi + 56], r13d setae byte ptr [rsp + 288] # 1-byte Folded Spill cmp dword ptr [rsi + 60], r13d - setae cl + setae dl cmp dword ptr [rsi + 64], r13d setae byte ptr [rsp + 160] # 1-byte Folded Spill cmp dword ptr [rsi + 68], r13d - setae byte ptr [rsp + 304] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d setae byte ptr [rsp + 256] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setae byte ptr [rsp + 272] # 1-byte Folded Spill cmp dword ptr [rsi + 76], r13d - setae byte ptr [rsp + 224] # 1-byte Folded Spill + setae byte ptr [rsp + 208] # 1-byte Folded Spill cmp dword ptr [rsi + 80], r13d - setae byte ptr [rsp + 176] # 1-byte Folded Spill + setae byte ptr [rsp + 192] # 1-byte Folded Spill cmp dword ptr [rsi + 84], r13d - setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + setae byte ptr [rsp + 144] # 1-byte Folded Spill cmp dword ptr [rsi + 92], r13d setae r15b cmp dword ptr [rsi + 96], r13d setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp dword ptr [rsi + 100], r13d - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill cmp dword ptr [rsi + 104], r13d setae byte ptr [rsp + 96] # 1-byte Folded Spill cmp dword ptr [rsi + 108], r13d @@ -49751,826 +51230,346 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar cmp dword ptr [rsi + 116], r13d setae byte ptr [rsp + 16] # 1-byte Folded Spill cmp dword ptr [rsi + 120], r13d - setae byte ptr [rsp + 8] # 1-byte Folded Spill + setae byte ptr [rsp] # 1-byte Folded Spill cmp dword ptr [rsi + 124], r13d - setae dl - add r10b, r10b - add r10b, byte ptr [rsp + 240] # 1-byte Folded Reload + setae bl + add r9b, r9b + add r9b, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 336] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 336] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload shl al, 3 or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 352] # 8-byte Reload - shl r8b, 2 + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b + or al, cl + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 288] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 304] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 160] # 1-byte Folded Reload - mov edi, eax + or r12b, r10b + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 8] # 8-byte Reload movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 224] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 5 or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl - add rsi, 128 - add r14, 4 - add qword ptr [rsp + 320], -1 # 8-byte Folded Spill - jne .LBB10_19 -# %bb.20: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r11, qword ptr [rsp + 368] # 8-byte Reload -.LBB10_21: - shl r11, 5 - cmp r11, r10 - jge .LBB10_201 -# %bb.22: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB10_137 -# %bb.23: - xor r11d, r11d - jmp .LBB10_24 -.LBB10_26: - cmp edi, 8 - jle .LBB10_27 -# %bb.42: - cmp edi, 9 - je .LBB10_157 -# %bb.43: - cmp edi, 11 - je .LBB10_172 -# %bb.44: - cmp edi, 12 - jne .LBB10_201 -# %bb.45: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - movsd xmm0, qword ptr [rdx] # xmm0 = mem[0],zero - sub r9d, eax - je .LBB10_49 -# %bb.46: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB10_47: # =>This Inner Loop Header: Depth=1 - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - add rsi, 8 - ucomisd xmm1, xmm0 - mov edx, 0 - adc dl, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_47 -# %bb.48: - add r14, 1 -.LBB10_49: - sar r11, 5 - cmp r10, 32 - jl .LBB10_53 -# %bb.50: - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 320], r11 # 8-byte Spill - mov qword ptr [rsp + 240], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB10_51: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 352], r14 # 8-byte Spill - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - movsd xmm2, qword ptr [rsi + 8] # xmm2 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 288] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - setae dl - movsd xmm1, qword ptr [rsi + 16] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae dil - movsd xmm1, qword ptr [rsi + 24] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae r8b - movsd xmm1, qword ptr [rsi + 32] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae r9b - movsd xmm1, qword ptr [rsi + 40] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 272] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 48] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 304] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 56] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 336] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 64] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 192] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 72] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae r10b - movsd xmm1, qword ptr [rsi + 80] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae bl - movsd xmm1, qword ptr [rsi + 88] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae r15b - movsd xmm1, qword ptr [rsi + 96] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae al - movsd xmm1, qword ptr [rsi + 104] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 208] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 112] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 176] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 120] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 224] # 1-byte Folded Spill - movsd xmm1, qword ptr [rsi + 128] # xmm1 = mem[0],zero - movsd xmm2, qword ptr [rsi + 136] # xmm2 = mem[0],zero - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 144] # xmm1 = mem[0],zero - setae byte ptr [rsp + 144] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - movsd xmm2, qword ptr [rsi + 152] # xmm2 = mem[0],zero - setae r11b - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 160] # xmm1 = mem[0],zero - setae r14b - ucomisd xmm2, xmm0 - movsd xmm2, qword ptr [rsi + 168] # xmm2 = mem[0],zero - setae r12b - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 176] # xmm1 = mem[0],zero - setae byte ptr [rsp + 256] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - movsd xmm2, qword ptr [rsi + 184] # xmm2 = mem[0],zero - setae byte ptr [rsp + 160] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 192] # xmm1 = mem[0],zero - setae byte ptr [rsp + 112] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - movsd xmm2, qword ptr [rsi + 200] # xmm2 = mem[0],zero - setae r13b - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 208] # xmm1 = mem[0],zero - setae byte ptr [rsp + 16] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - movsd xmm2, qword ptr [rsi + 216] # xmm2 = mem[0],zero - setae byte ptr [rsp + 128] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 224] # xmm1 = mem[0],zero - setae byte ptr [rsp + 96] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - movsd xmm2, qword ptr [rsi + 232] # xmm2 = mem[0],zero - setae byte ptr [rsp + 80] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - movsd xmm1, qword ptr [rsi + 240] # xmm1 = mem[0],zero - setae byte ptr [rsp + 48] # 1-byte Folded Spill - ucomisd xmm2, xmm0 - movsd xmm2, qword ptr [rsi + 248] # xmm2 = mem[0],zero - setae byte ptr [rsp + 32] # 1-byte Folded Spill - ucomisd xmm1, xmm0 - setae byte ptr [rsp + 8] # 1-byte Folded Spill - add rsi, 256 - ucomisd xmm2, xmm0 - setae cl - add dl, dl - add dl, byte ptr [rsp + 288] # 1-byte Folded Reload - shl dil, 2 - or dil, dl - shl r8b, 3 - or r8b, dil - shl r9b, 4 - or r9b, r8b - movzx edx, byte ptr [rsp + 272] # 1-byte Folded Reload - shl dl, 5 - or dl, r9b - mov edi, edx - movzx r8d, byte ptr [rsp + 304] # 1-byte Folded Reload - shl r8b, 6 - movzx edx, byte ptr [rsp + 336] # 1-byte Folded Reload - shl dl, 7 - or dl, r8b - add r10b, r10b - add r10b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl bl, 2 - or bl, r10b - shl r15b, 3 - or r15b, bl - shl al, 4 - or al, r15b - or dl, dil - movzx ebx, byte ptr [rsp + 208] # 1-byte Folded Reload - shl bl, 5 - or bl, al - mov edi, ebx - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 6 - movzx ebx, byte ptr [rsp + 224] # 1-byte Folded Reload - shl bl, 7 - or bl, al - add r11b, r11b - add r11b, byte ptr [rsp + 144] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r11b - shl r12b, 3 - or r12b, r14b - mov r14, qword ptr [rsp + 352] # 8-byte Reload - movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload - shl al, 4 - or al, r12b - mov r8d, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 5 - or al, r8b - or bl, dil - movzx edi, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dil, 6 - shl r13b, 7 - or r13b, dil - mov byte ptr [r14], dl - or r13b, al - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r15b, 7 + or r15b, cl + mov byte ptr [r12 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 4 - or al, dl - movzx edx, byte ptr [rsp + 32] # 1-byte Folded Reload - shl dl, 5 - or dl, al - mov byte ptr [r14 + 1], bl - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl bl, 6 - shl cl, 7 - or cl, bl - mov byte ptr [r14 + 2], r13b - or cl, dl - mov byte ptr [r14 + 3], cl - add r14, 4 - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill - jne .LBB10_51 -# %bb.52: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r11, qword ptr [rsp + 320] # 8-byte Reload -.LBB10_53: - shl r11, 5 - cmp r11, r10 - jge .LBB10_201 -# %bb.54: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB10_195 -# %bb.55: - xor r11d, r11d - jmp .LBB10_197 -.LBB10_2: - cmp edi, 2 - je .LBB10_56 -# %bb.3: - cmp edi, 3 - jne .LBB10_201 -# %bb.4: - mov r11b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB10_8 -# %bb.5: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB10_6: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r11b - lea rsi, [rsi + 1] - setge dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_6 -# %bb.7: - add r14, 1 -.LBB10_8: - sar r15, 5 - cmp r10, 32 - jl .LBB10_9 -# %bb.81: - cmp r15, 16 - mov byte ptr [rsp + 8], r11b # 1-byte Spill - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 432], r15 # 8-byte Spill - jb .LBB10_82 -# %bb.83: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp r14, rax - jae .LBB10_85 -# %bb.84: - lea rax, [r14 + 4*r15] - cmp rsi, rax - jae .LBB10_85 -.LBB10_82: - xor eax, eax - mov qword ptr [rsp + 240], rax # 8-byte Spill - mov qword ptr [rsp + 144], r14 # 8-byte Spill -.LBB10_88: - sub r15, qword ptr [rsp + 240] # 8-byte Folded Reload - mov qword ptr [rsp + 368], r15 # 8-byte Spill - .p2align 4, 0x90 -.LBB10_89: # =>This Inner Loop Header: Depth=1 - mov rcx, rsi - cmp byte ptr [rsi], r11b - setge byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [rsi + 1], r11b - setge sil - cmp byte ptr [rcx + 2], r11b - setge r15b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 3], al - setge r12b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 4], al - setge byte ptr [rsp + 272] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 5], al - setge byte ptr [rsp + 112] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 6], al - setge byte ptr [rsp + 240] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 7], al - setge r9b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 8], al - setge byte ptr [rsp + 336] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 9], al - setge dl - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 10], al - setge dil - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 11], al - setge r10b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 12], al - setge r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 13], al - setge r13b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], al - setge byte ptr [rsp + 288] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], al - setge r8b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], bl - setge byte ptr [rsp + 304] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], bl - setge byte ptr [rsp + 256] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], bl - setge byte ptr [rsp + 208] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], bl - setge byte ptr [rsp + 224] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], bl - setge byte ptr [rsp + 160] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], bl - setge byte ptr [rsp + 192] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], bl - setge byte ptr [rsp + 176] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], bl - setge r11b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], bl - setge byte ptr [rsp + 128] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], bl - setge byte ptr [rsp + 96] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], bl - setge byte ptr [rsp + 80] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], bl - setge byte ptr [rsp + 48] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], bl - setge byte ptr [rsp + 32] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], bl - setge byte ptr [rsp + 16] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], bl - setge byte ptr [rsp + 352] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], bl - setge bl - add sil, sil - add sil, byte ptr [rsp + 320] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload - shl al, 6 - shl r9b, 7 - or r9b, al - shl r15b, 2 - or r15b, sil - add dl, dl - add dl, byte ptr [rsp + 336] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - movzx r15d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl dil, 2 - or dil, dl - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload - shl al, 4 - or al, r12b - shl r10b, 3 - or r10b, dil - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 5 - or dl, al - shl r14b, 4 - or r14b, r10b - shl r13b, 5 - or r13b, r14b - movzx esi, byte ptr [rsp + 288] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r9b, dl - or r8b, r13b - movzx edx, byte ptr [rsp + 256] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 304] # 1-byte Folded Reload - mov esi, edx - movzx edx, byte ptr [rsp + 208] # 1-byte Folded Reload - shl dl, 2 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 224] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 192] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov esi, edx - mov rdx, qword ptr [rsp + 144] # 8-byte Reload - mov byte ptr [rdx], r9b - movzx edi, byte ptr [rsp + 176] # 1-byte Folded Reload - shl dil, 6 - shl r11b, 7 - or r11b, dil - mov byte ptr [rdx + 1], r8b - or r11b, sil + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ecx, eax movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 128] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 3 - or al, sil - mov esi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 - or al, sil - mov esi, eax + or al, cl + mov ecx, eax movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 - or al, sil - movzx esi, byte ptr [rsp + 352] # 1-byte Folded Reload - shl sil, 6 + or al, cl + movzx ecx, byte ptr [rsp] # 1-byte Folded Reload + shl cl, 6 shl bl, 7 - or bl, sil + or bl, cl or bl, al - mov byte ptr [rdx + 2], r11b - mov r11d, r15d - mov byte ptr [rdx + 3], bl - lea rsi, [rcx + 32] - add rdx, 4 - mov qword ptr [rsp + 144], rdx # 8-byte Spill - add qword ptr [rsp + 368], -1 # 8-byte Folded Spill - jne .LBB10_89 -# %bb.90: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r15, qword ptr [rsp + 432] # 8-byte Reload - jmp .LBB10_91 -.LBB10_27: - cmp edi, 7 - je .LBB10_139 -# %bb.28: + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl + add rsi, 128 + add r12, 4 + add qword ptr [rsp + 304], -1 # 8-byte Folded Spill + jne .LBB10_17 +# %bb.18: + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rax, qword ptr [rsp + 352] # 8-byte Reload +.LBB10_19: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB10_227 +# %bb.20: + or rax, 1 + cmp r14, rax + jne .LBB10_156 +# %bb.21: + xor r11d, r11d + jmp .LBB10_22 +.LBB10_24: cmp edi, 8 - jne .LBB10_201 -# %bb.29: - mov r13, qword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 + jle .LBB10_25 +# %bb.42: + cmp edi, 9 + je .LBB10_178 +# %bb.43: + cmp edi, 11 + je .LBB10_195 +# %bb.44: + cmp edi, 12 + jne .LBB10_227 +# %bb.45: + mov r15, qword ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_33 -# %bb.30: - movsxd rax, r9d + je .LBB10_51 +# %bb.46: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_49 +# %bb.47: + movsxd rdx, r9d + movq xmm0, r15 + mov r11, r8 .p2align 4, 0x90 -.LBB10_31: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - mov edx, 0 - adc dl, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi +.LBB10_48: # =>This Inner Loop Header: Depth=1 + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + add rsi, 8 + ucomisd xmm1, xmm0 + mov ebx, 0 + adc bl, -1 + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_31 -# %bb.32: - add r14, 1 -.LBB10_33: - sar r11, 5 - cmp r10, 32 - jl .LBB10_37 -# %bb.34: - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 368], r11 # 8-byte Spill - mov qword ptr [rsp + 320], r11 # 8-byte Spill + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + add r11, -1 + jne .LBB10_48 +.LBB10_49: + sub r14, r8 + je .LBB10_227 +# %bb.50: + add r12, 1 +.LBB10_51: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB10_55 +# %bb.52: + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 304], r15 # 8-byte Spill + movq xmm0, r15 + mov qword ptr [rsp + 352], rax # 8-byte Spill + mov qword ptr [rsp + 320], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_35: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 352], r14 # 8-byte Spill - cmp qword ptr [rsi], r13 - setae byte ptr [rsp + 240] # 1-byte Folded Spill - cmp qword ptr [rsi + 8], r13 - setae r10b - cmp qword ptr [rsi + 16], r13 - setae r14b - cmp qword ptr [rsi + 24], r13 - setae byte ptr [rsp + 272] # 1-byte Folded Spill - cmp qword ptr [rsi + 32], r13 - setae byte ptr [rsp + 208] # 1-byte Folded Spill - cmp qword ptr [rsi + 40], r13 - setae byte ptr [rsp + 192] # 1-byte Folded Spill - cmp qword ptr [rsi + 48], r13 +.LBB10_53: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 8], r12 # 8-byte Spill + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + movsd xmm2, qword ptr [rsi + 8] # xmm2 = mem[0],zero + ucomisd xmm1, xmm0 + setae byte ptr [rsp + 288] # 1-byte Folded Spill + ucomisd xmm2, xmm0 setae al - cmp qword ptr [rsi + 56], r13 - setae bl - cmp qword ptr [rsi + 64], r13 - setae byte ptr [rsp + 336] # 1-byte Folded Spill - cmp qword ptr [rsi + 72], r13 + movsd xmm1, qword ptr [rsi + 16] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 setae dil - cmp qword ptr [rsi + 80], r13 + movsd xmm1, qword ptr [rsi + 24] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 setae r8b - cmp qword ptr [rsi + 88], r13 + movsd xmm1, qword ptr [rsi + 32] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 setae r9b - cmp qword ptr [rsi + 96], r13 - setae r11b - cmp qword ptr [rsi + 104], r13 - setae r12b - cmp qword ptr [rsi + 112], r13 - setae byte ptr [rsp + 288] # 1-byte Folded Spill - cmp qword ptr [rsi + 120], r13 - setae cl - cmp qword ptr [rsi + 128], r13 - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp qword ptr [rsi + 136], r13 - setae byte ptr [rsp + 304] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 + movsd xmm1, qword ptr [rsi + 40] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae byte ptr [rsp + 240] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 48] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 setae byte ptr [rsp + 256] # 1-byte Folded Spill - cmp qword ptr [rsi + 152], r13 - setae byte ptr [rsp + 224] # 1-byte Folded Spill - cmp qword ptr [rsi + 160], r13 + movsd xmm1, qword ptr [rsi + 56] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae byte ptr [rsp + 336] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 64] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 setae byte ptr [rsp + 176] # 1-byte Folded Spill - cmp qword ptr [rsi + 168], r13 + movsd xmm1, qword ptr [rsi + 72] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae r10b + movsd xmm1, qword ptr [rsi + 80] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae bl + movsd xmm1, qword ptr [rsi + 88] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae r15b + movsd xmm1, qword ptr [rsi + 96] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae cl + movsd xmm1, qword ptr [rsi + 104] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae byte ptr [rsp + 224] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 112] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae byte ptr [rsp + 160] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 120] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + setae byte ptr [rsp + 208] # 1-byte Folded Spill + movsd xmm1, qword ptr [rsi + 128] # xmm1 = mem[0],zero + movsd xmm2, qword ptr [rsi + 136] # xmm2 = mem[0],zero + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 144] # xmm1 = mem[0],zero setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp qword ptr [rsi + 176], r13 + ucomisd xmm2, xmm0 + movsd xmm2, qword ptr [rsi + 152] # xmm2 = mem[0],zero + setae r11b + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 160] # xmm1 = mem[0],zero + setae r14b + ucomisd xmm2, xmm0 + movsd xmm2, qword ptr [rsi + 168] # xmm2 = mem[0],zero + setae r12b + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 176] # xmm1 = mem[0],zero + setae byte ptr [rsp + 272] # 1-byte Folded Spill + ucomisd xmm2, xmm0 + movsd xmm2, qword ptr [rsi + 184] # xmm2 = mem[0],zero + setae byte ptr [rsp + 192] # 1-byte Folded Spill + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 192] # xmm1 = mem[0],zero setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp qword ptr [rsi + 184], r13 - setae r15b - cmp qword ptr [rsi + 192], r13 - setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp qword ptr [rsi + 200], r13 + ucomisd xmm2, xmm0 + movsd xmm2, qword ptr [rsi + 200] # xmm2 = mem[0],zero + setae r13b + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 208] # xmm1 = mem[0],zero + setae byte ptr [rsp + 16] # 1-byte Folded Spill + ucomisd xmm2, xmm0 + movsd xmm2, qword ptr [rsi + 216] # xmm2 = mem[0],zero setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp qword ptr [rsi + 208], r13 + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 224] # xmm1 = mem[0],zero setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp qword ptr [rsi + 216], r13 + ucomisd xmm2, xmm0 + movsd xmm2, qword ptr [rsi + 232] # xmm2 = mem[0],zero setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp qword ptr [rsi + 224], r13 + ucomisd xmm1, xmm0 + movsd xmm1, qword ptr [rsi + 240] # xmm1 = mem[0],zero + setae byte ptr [rsp + 48] # 1-byte Folded Spill + ucomisd xmm2, xmm0 + movsd xmm2, qword ptr [rsi + 248] # xmm2 = mem[0],zero setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp qword ptr [rsi + 232], r13 - setae byte ptr [rsp + 16] # 1-byte Folded Spill - cmp qword ptr [rsi + 240], r13 - setae byte ptr [rsp + 8] # 1-byte Folded Spill - cmp qword ptr [rsi + 248], r13 + ucomisd xmm1, xmm0 + setae byte ptr [rsp] # 1-byte Folded Spill + add rsi, 256 + ucomisd xmm2, xmm0 setae dl - add r10b, r10b - add r10b, byte ptr [rsp + 240] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al - shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 336] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload - shl al, 3 - or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 352] # 8-byte Reload - shl r8b, 2 + add al, al + add al, byte ptr [rsp + 288] # 1-byte Folded Reload + shl dil, 2 + or dil, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 + shl r9b, 4 or r9b, r8b - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b - shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 288] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 304] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 160] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 224] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 4 - or al, dil + or al, r9b mov edi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 + movzx r8d, byte ptr [rsp + 256] # 1-byte Folded Reload + shl r8b, 6 + movzx eax, byte ptr [rsp + 336] # 1-byte Folded Reload + shl al, 7 + or al, r8b + add r10b, r10b + add r10b, byte ptr [rsp + 176] # 1-byte Folded Reload + shl bl, 2 + or bl, r10b + shl r15b, 3 or r15b, bl - mov byte ptr [r14 + 1], cl - or r15b, al + shl cl, 4 + or cl, r15b + or al, dil + movzx ebx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl bl, 5 + or bl, cl + mov edi, ebx + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl cl, 6 + movzx ebx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl bl, 7 + or bl, cl + add r11b, r11b + add r11b, byte ptr [rsp + 112] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r11b + shl r12b, 3 + or r12b, r14b + movzx ecx, byte ptr [rsp + 272] # 1-byte Folded Reload + shl cl, 4 + or cl, r12b + mov r8d, ecx + mov r12, qword ptr [rsp + 8] # 8-byte Reload + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload + shl cl, 5 + or cl, r8b + or bl, dil + movzx edi, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dil, 6 + shl r13b, 7 + or r13b, dil + mov byte ptr [r12], al + or r13b, cl movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 16] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 2 @@ -50580,475 +51579,287 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 5 or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 6 + mov byte ptr [r12 + 1], bl + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + shl bl, 6 shl dl, 7 - or dl, cl + or dl, bl + mov byte ptr [r12 + 2], r13b or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl - add rsi, 256 - add r14, 4 + mov byte ptr [r12 + 3], dl + add r12, 4 add qword ptr [rsp + 320], -1 # 8-byte Folded Spill - jne .LBB10_35 -# %bb.36: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r11, qword ptr [rsp + 368] # 8-byte Reload -.LBB10_37: - shl r11, 5 - cmp r11, r10 - jge .LBB10_201 -# %bb.38: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB10_155 -# %bb.39: + jne .LBB10_53 +# %bb.54: + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov r15, qword ptr [rsp + 304] # 8-byte Reload + mov rax, qword ptr [rsp + 352] # 8-byte Reload +.LBB10_55: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB10_227 +# %bb.56: + movq xmm0, r15 + or rax, 1 + cmp r14, rax + jne .LBB10_221 +# %bb.57: xor r11d, r11d - jmp .LBB10_40 -.LBB10_56: - mov r11b, byte ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jmp .LBB10_223 +.LBB10_2: + cmp edi, 2 + je .LBB10_58 +# %bb.3: + cmp edi, 3 + jne .LBB10_227 +# %bb.4: + mov r15b, byte ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_60 -# %bb.57: - movsxd rax, r9d + je .LBB10_5 +# %bb.86: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_87 +# %bb.92: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB10_58: # =>This Inner Loop Header: Depth=1 - cmp byte ptr [rsi], r11b - lea rsi, [rsi + 1] - mov edx, 0 - adc dl, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB10_93: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r15b + setge bl + neg bl + lea rsi, [rdx + 7] + test rdx, rdx + cmovns rsi, rdx + sar rsi, 3 + movzx r9d, byte ptr [r12 + rsi] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_58 -# %bb.59: - add r14, 1 -.LBB10_60: - sar r15, 5 - cmp r10, 32 - jl .LBB10_61 -# %bb.62: - cmp r15, 16 - mov byte ptr [rsp + 8], r11b # 1-byte Spill - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 464], r15 # 8-byte Spill - jb .LBB10_63 -# %bb.64: - mov rax, r15 - shl rax, 5 - add rax, rsi - cmp r14, rax - jae .LBB10_66 -# %bb.65: - lea rax, [r14 + 4*r15] - cmp rsi, rax - jae .LBB10_66 -.LBB10_63: - xor eax, eax - mov qword ptr [rsp + 416], rax # 8-byte Spill - mov qword ptr [rsp + 224], r14 # 8-byte Spill -.LBB10_69: - sub r15, qword ptr [rsp + 416] # 8-byte Folded Reload - mov qword ptr [rsp + 368], r15 # 8-byte Spill + lea r10d, [8*rsi] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rsi], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB10_93 +# %bb.88: + sub r14, r8 + jne .LBB10_89 + jmp .LBB10_227 +.LBB10_25: + cmp edi, 7 + je .LBB10_158 +# %bb.26: + cmp edi, 8 + jne .LBB10_227 +# %bb.27: + mov r13, qword ptr [rdx] + lea ecx, [r9 + 7] + test r9d, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB10_33 +# %bb.28: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_31 +# %bb.29: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_70: # =>This Inner Loop Header: Depth=1 +.LBB10_30: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + mov ebx, 0 + adc bl, -1 + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 + # kill: def $cl killed $cl killed $ecx + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 mov rcx, rsi - cmp byte ptr [rsi], r11b + add r11, -1 + jne .LBB10_30 +.LBB10_31: + sub r14, r8 + je .LBB10_227 +# %bb.32: + add r12, 1 +.LBB10_33: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB10_37 +# %bb.34: + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 352], rax # 8-byte Spill + mov qword ptr [rsp + 304], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB10_35: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 8], r12 # 8-byte Spill + cmp qword ptr [rsi], r13 setae byte ptr [rsp + 320] # 1-byte Folded Spill - cmp byte ptr [rsi + 1], r11b - setae sil - cmp byte ptr [rcx + 2], r11b - setae r15b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 3], al - setae r12b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 4], al - setae byte ptr [rsp + 272] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 5], al - setae byte ptr [rsp + 128] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 6], al - setae byte ptr [rsp + 240] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 7], al + cmp qword ptr [rsi + 8], r13 setae r9b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 8], al + cmp qword ptr [rsi + 16], r13 + setae r14b + cmp qword ptr [rsi + 24], r13 + setae byte ptr [rsp + 240] # 1-byte Folded Spill + cmp qword ptr [rsi + 32], r13 + setae byte ptr [rsp + 224] # 1-byte Folded Spill + cmp qword ptr [rsi + 40], r13 + setae byte ptr [rsp + 176] # 1-byte Folded Spill + cmp qword ptr [rsi + 48], r13 + setae al + cmp qword ptr [rsi + 56], r13 + setae r11b + cmp qword ptr [rsi + 64], r13 setae byte ptr [rsp + 336] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 9], al - setae dl - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 10], al + cmp qword ptr [rsi + 72], r13 + setae cl + cmp qword ptr [rsi + 80], r13 setae dil - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 11], al + cmp qword ptr [rsi + 88], r13 + setae r8b + cmp qword ptr [rsi + 96], r13 setae r10b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 12], al - setae r14b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 13], al - setae r13b - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 14], al + cmp qword ptr [rsi + 104], r13 + setae r12b + cmp qword ptr [rsi + 112], r13 setae byte ptr [rsp + 288] # 1-byte Folded Spill - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 15], al - setae r8b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 16], bl - setae byte ptr [rsp + 304] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 17], bl + cmp qword ptr [rsi + 120], r13 + setae dl + cmp qword ptr [rsi + 128], r13 + setae byte ptr [rsp + 160] # 1-byte Folded Spill + cmp qword ptr [rsi + 136], r13 setae byte ptr [rsp + 256] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 18], bl + cmp qword ptr [rsi + 144], r13 + setae byte ptr [rsp + 272] # 1-byte Folded Spill + cmp qword ptr [rsi + 152], r13 setae byte ptr [rsp + 208] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 19], bl - setae byte ptr [rsp + 160] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 20], bl - setae byte ptr [rsp + 176] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 21], bl - setae byte ptr [rsp + 112] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 22], bl + cmp qword ptr [rsi + 160], r13 setae byte ptr [rsp + 192] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 23], bl - setae r11b - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 24], bl + cmp qword ptr [rsi + 168], r13 + setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp qword ptr [rsi + 176], r13 setae byte ptr [rsp + 144] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 25], bl + cmp qword ptr [rsi + 184], r13 + setae r15b + cmp qword ptr [rsi + 192], r13 + setae byte ptr [rsp + 48] # 1-byte Folded Spill + cmp qword ptr [rsi + 200], r13 + setae byte ptr [rsp + 112] # 1-byte Folded Spill + cmp qword ptr [rsi + 208], r13 setae byte ptr [rsp + 96] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 26], bl + cmp qword ptr [rsi + 216], r13 setae byte ptr [rsp + 80] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 27], bl - setae byte ptr [rsp + 48] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 28], bl + cmp qword ptr [rsi + 224], r13 setae byte ptr [rsp + 32] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 29], bl + cmp qword ptr [rsi + 232], r13 setae byte ptr [rsp + 16] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 30], bl - setae byte ptr [rsp + 352] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - cmp byte ptr [rcx + 31], bl + cmp qword ptr [rsi + 240], r13 + setae byte ptr [rsp] # 1-byte Folded Spill + cmp qword ptr [rsi + 248], r13 setae bl - add sil, sil - add sil, byte ptr [rsp + 320] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload + add r9b, r9b + add r9b, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 6 - shl r9b, 7 - or r9b, al - shl r15b, 2 - or r15b, sil - add dl, dl - add dl, byte ptr [rsp + 336] # 1-byte Folded Reload - shl r12b, 3 - or r12b, r15b - movzx r15d, byte ptr [rsp + 8] # 1-byte Folded Reload - shl dil, 2 - or dil, dl - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload - shl al, 4 - or al, r12b - shl r10b, 3 - or r10b, dil - movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl dl, 5 - or dl, al - shl r14b, 4 - or r14b, r10b - shl r13b, 5 - or r13b, r14b - movzx esi, byte ptr [rsp + 288] # 1-byte Folded Reload - shl sil, 6 - shl r8b, 7 - or r8b, sil - or r9b, dl - or r8b, r13b - movzx edx, byte ptr [rsp + 256] # 1-byte Folded Reload - add dl, dl - add dl, byte ptr [rsp + 304] # 1-byte Folded Reload - mov esi, edx - movzx edx, byte ptr [rsp + 208] # 1-byte Folded Reload - shl dl, 2 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 176] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov esi, edx - mov rdx, qword ptr [rsp + 224] # 8-byte Reload - mov byte ptr [rdx], r9b - movzx edi, byte ptr [rsp + 192] # 1-byte Folded Reload - shl dil, 6 shl r11b, 7 - or r11b, dil - mov byte ptr [rdx + 1], r8b - or r11b, sil - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload - mov esi, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 2 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 3 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 4 - or al, sil - mov esi, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, sil - movzx esi, byte ptr [rsp + 352] # 1-byte Folded Reload - shl sil, 6 - shl bl, 7 - or bl, sil - or bl, al - mov byte ptr [rdx + 2], r11b - mov r11d, r15d - mov byte ptr [rdx + 3], bl - lea rsi, [rcx + 32] - add rdx, 4 - mov qword ptr [rsp + 224], rdx # 8-byte Spill - add qword ptr [rsp + 368], -1 # 8-byte Folded Spill - jne .LBB10_70 -# %bb.71: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r15, qword ptr [rsp + 464] # 8-byte Reload - jmp .LBB10_72 -.LBB10_139: - mov r13d, dword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB10_143 -# %bb.140: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB10_141: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - lea rsi, [rsi + 4] - setge dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_141 -# %bb.142: - add r14, 1 -.LBB10_143: - sar r11, 5 - cmp r10, 32 - jl .LBB10_147 -# %bb.144: - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 368], r11 # 8-byte Spill - mov qword ptr [rsp + 320], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB10_145: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 352], r14 # 8-byte Spill - cmp dword ptr [rsi], r13d - setge byte ptr [rsp + 240] # 1-byte Folded Spill - cmp dword ptr [rsi + 4], r13d - setge r10b - cmp dword ptr [rsi + 8], r13d - setge r14b - cmp dword ptr [rsi + 12], r13d - setge byte ptr [rsp + 272] # 1-byte Folded Spill - cmp dword ptr [rsi + 16], r13d - setge byte ptr [rsp + 208] # 1-byte Folded Spill - cmp dword ptr [rsi + 20], r13d - setge byte ptr [rsp + 192] # 1-byte Folded Spill - cmp dword ptr [rsi + 24], r13d - setge al - cmp dword ptr [rsi + 28], r13d - setge bl - cmp dword ptr [rsi + 32], r13d - setge byte ptr [rsp + 336] # 1-byte Folded Spill - cmp dword ptr [rsi + 36], r13d - setge dil - cmp dword ptr [rsi + 40], r13d - setge r8b - cmp dword ptr [rsi + 44], r13d - setge r9b - cmp dword ptr [rsi + 48], r13d - setge r11b - cmp dword ptr [rsi + 52], r13d - setge r12b - cmp dword ptr [rsi + 56], r13d - setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp dword ptr [rsi + 60], r13d - setge cl - cmp dword ptr [rsi + 64], r13d - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp dword ptr [rsi + 68], r13d - setge byte ptr [rsp + 304] # 1-byte Folded Spill - cmp dword ptr [rsi + 72], r13d - setge byte ptr [rsp + 256] # 1-byte Folded Spill - cmp dword ptr [rsi + 76], r13d - setge byte ptr [rsp + 224] # 1-byte Folded Spill - cmp dword ptr [rsi + 80], r13d - setge byte ptr [rsp + 176] # 1-byte Folded Spill - cmp dword ptr [rsi + 84], r13d - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp dword ptr [rsi + 88], r13d - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp dword ptr [rsi + 92], r13d - setge r15b - cmp dword ptr [rsi + 96], r13d - setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp dword ptr [rsi + 100], r13d - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp dword ptr [rsi + 104], r13d - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp dword ptr [rsi + 108], r13d - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp dword ptr [rsi + 112], r13d - setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp dword ptr [rsi + 116], r13d - setge byte ptr [rsp + 16] # 1-byte Folded Spill - cmp dword ptr [rsi + 120], r13d - setge byte ptr [rsp + 8] # 1-byte Folded Spill - cmp dword ptr [rsi + 124], r13d - setge dl - add r10b, r10b - add r10b, byte ptr [rsp + 240] # 1-byte Folded Reload - shl al, 6 - shl bl, 7 - or bl, al + or r11b, al shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 336] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 336] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload shl al, 3 or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 352] # 8-byte Reload - shl r8b, 2 + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b + or al, cl + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 288] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 304] # 1-byte Folded Reload + or r12b, r10b + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 8] # 8-byte Reload + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 160] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 224] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 6 shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl + or r15b, cl + mov byte ptr [r12 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax @@ -51067,135 +51878,147 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp] # 1-byte Folded Reload shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl - add rsi, 128 - add r14, 4 - add qword ptr [rsp + 320], -1 # 8-byte Folded Spill - jne .LBB10_145 -# %bb.146: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r11, qword ptr [rsp + 368] # 8-byte Reload -.LBB10_147: - shl r11, 5 - cmp r11, r10 - jge .LBB10_201 -# %bb.148: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB10_153 -# %bb.149: + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl + add rsi, 256 + add r12, 4 + add qword ptr [rsp + 304], -1 # 8-byte Folded Spill + jne .LBB10_35 +# %bb.36: + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rax, qword ptr [rsp + 352] # 8-byte Reload +.LBB10_37: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB10_227 +# %bb.38: + or rax, 1 + cmp r14, rax + jne .LBB10_176 +# %bb.39: xor r11d, r11d - jmp .LBB10_150 -.LBB10_99: + jmp .LBB10_40 +.LBB10_114: movzx r13d, word ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] + lea ecx, [r9 + 7] test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB10_103 -# %bb.100: - movsxd rax, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB10_120 +# %bb.115: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_118 +# %bb.116: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_101: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - lea rsi, [rsi + 2] - mov edx, 0 - adc dl, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_117: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r13w + mov ebx, 0 + adc bl, -1 + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_101 -# %bb.102: - add r14, 1 -.LBB10_103: - sar r11, 5 - cmp r10, 32 - jl .LBB10_107 -# %bb.104: - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 368], r11 # 8-byte Spill - mov qword ptr [rsp + 320], r11 # 8-byte Spill + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_117 +.LBB10_118: + sub r14, r8 + je .LBB10_227 +# %bb.119: + add r12, 1 +.LBB10_120: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB10_124 +# %bb.121: + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 352], rax # 8-byte Spill + mov qword ptr [rsp + 304], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_105: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 352], r14 # 8-byte Spill +.LBB10_122: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 8], r12 # 8-byte Spill cmp word ptr [rsi], r13w - setae byte ptr [rsp + 240] # 1-byte Folded Spill + setae byte ptr [rsp + 320] # 1-byte Folded Spill cmp word ptr [rsi + 2], r13w - setae r10b + setae r9b cmp word ptr [rsi + 4], r13w setae r14b cmp word ptr [rsi + 6], r13w - setae byte ptr [rsp + 272] # 1-byte Folded Spill + setae byte ptr [rsp + 240] # 1-byte Folded Spill cmp word ptr [rsi + 8], r13w - setae byte ptr [rsp + 208] # 1-byte Folded Spill + setae byte ptr [rsp + 224] # 1-byte Folded Spill cmp word ptr [rsi + 10], r13w - setae byte ptr [rsp + 192] # 1-byte Folded Spill + setae byte ptr [rsp + 176] # 1-byte Folded Spill cmp word ptr [rsi + 12], r13w setae al cmp word ptr [rsi + 14], r13w - setae bl + setae r11b cmp word ptr [rsi + 16], r13w setae byte ptr [rsp + 336] # 1-byte Folded Spill cmp word ptr [rsi + 18], r13w - setae dil + setae cl cmp word ptr [rsi + 20], r13w - setae r8b + setae dil cmp word ptr [rsi + 22], r13w - setae r9b + setae r8b cmp word ptr [rsi + 24], r13w - setae r11b + setae r10b cmp word ptr [rsi + 26], r13w setae r12b cmp word ptr [rsi + 28], r13w setae byte ptr [rsp + 288] # 1-byte Folded Spill cmp word ptr [rsi + 30], r13w - setae cl + setae dl cmp word ptr [rsi + 32], r13w setae byte ptr [rsp + 160] # 1-byte Folded Spill cmp word ptr [rsi + 34], r13w - setae byte ptr [rsp + 304] # 1-byte Folded Spill - cmp word ptr [rsi + 36], r13w setae byte ptr [rsp + 256] # 1-byte Folded Spill + cmp word ptr [rsi + 36], r13w + setae byte ptr [rsp + 272] # 1-byte Folded Spill cmp word ptr [rsi + 38], r13w - setae byte ptr [rsp + 224] # 1-byte Folded Spill + setae byte ptr [rsp + 208] # 1-byte Folded Spill cmp word ptr [rsi + 40], r13w - setae byte ptr [rsp + 176] # 1-byte Folded Spill + setae byte ptr [rsp + 192] # 1-byte Folded Spill cmp word ptr [rsi + 42], r13w - setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp word ptr [rsi + 44], r13w setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp word ptr [rsi + 44], r13w + setae byte ptr [rsp + 144] # 1-byte Folded Spill cmp word ptr [rsi + 46], r13w setae r15b cmp word ptr [rsi + 48], r13w setae byte ptr [rsp + 48] # 1-byte Folded Spill cmp word ptr [rsi + 50], r13w - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill cmp word ptr [rsi + 52], r13w setae byte ptr [rsp + 96] # 1-byte Folded Spill cmp word ptr [rsi + 54], r13w @@ -51205,71 +52028,69 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar cmp word ptr [rsi + 58], r13w setae byte ptr [rsp + 16] # 1-byte Folded Spill cmp word ptr [rsi + 60], r13w - setae byte ptr [rsp + 8] # 1-byte Folded Spill + setae byte ptr [rsp] # 1-byte Folded Spill cmp word ptr [rsi + 62], r13w - setae dl - add r10b, r10b - add r10b, byte ptr [rsp + 240] # 1-byte Folded Reload + setae bl + add r9b, r9b + add r9b, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 336] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 336] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload shl al, 3 or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 352] # 8-byte Reload - shl r8b, 2 + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b + or al, cl + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 288] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 304] # 1-byte Folded Reload + or r12b, r10b + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 8] # 8-byte Reload + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 160] # 1-byte Folded Reload - mov edi, eax - movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 224] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 6 shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl + or r15b, cl + mov byte ptr [r12 + 1], dl or r15b, al - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax @@ -51288,170 +52109,199 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl + movzx ecx, byte ptr [rsp] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl add rsi, 64 - add r14, 4 - add qword ptr [rsp + 320], -1 # 8-byte Folded Spill - jne .LBB10_105 -# %bb.106: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r11, qword ptr [rsp + 368] # 8-byte Reload -.LBB10_107: - shl r11, 5 - cmp r11, r10 - jge .LBB10_201 -# %bb.108: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB10_112 -# %bb.109: + add r12, 4 + add qword ptr [rsp + 304], -1 # 8-byte Folded Spill + jne .LBB10_122 +# %bb.123: + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rax, qword ptr [rsp + 352] # 8-byte Reload +.LBB10_124: + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB10_227 +# %bb.125: + or rax, 1 + cmp r14, rax + jne .LBB10_129 +# %bb.126: xor r11d, r11d - jmp .LBB10_110 -.LBB10_114: - movzx r11d, word ptr [rdx] - lea r15, [r10 + 31] - test r10, r10 - cmovns r15, r10 + jmp .LBB10_127 +.LBB10_131: + movzx r15d, word ptr [rdx] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB10_118 -# %bb.115: - movsxd rax, r9d + je .LBB10_137 +# %bb.132: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_135 +# %bb.133: + movsxd rdx, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_116: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r11w - lea rsi, [rsi + 2] - setge dl - neg dl - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl +.LBB10_134: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 2] + cmp word ptr [rcx], r15w + setge bl + neg bl + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_116 -# %bb.117: - add r14, 1 -.LBB10_118: - sar r15, 5 - cmp r10, 32 - mov dword ptr [rsp + 392], r11d # 4-byte Spill - jl .LBB10_119 -# %bb.120: - cmp r15, 8 - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 456], r15 # 8-byte Spill - jb .LBB10_121 -# %bb.122: - mov rax, r15 + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_134 +.LBB10_135: + sub r14, r8 + je .LBB10_227 +# %bb.136: + add r12, 1 +.LBB10_137: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB10_138 +# %bb.139: + cmp rcx, 8 + mov dword ptr [rsp], r15d # 4-byte Spill + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 440], rcx # 8-byte Spill + jb .LBB10_140 +# %bb.141: + mov rax, rcx shl rax, 6 add rax, rsi - cmp r14, rax - jae .LBB10_124 -# %bb.123: - lea rax, [r14 + 4*r15] + cmp r12, rax + jae .LBB10_143 +# %bb.142: + lea rax, [r12 + 4*rcx] cmp rax, rsi - jbe .LBB10_124 -.LBB10_121: + jbe .LBB10_143 +.LBB10_140: xor eax, eax - mov qword ptr [rsp + 400], rax # 8-byte Spill + mov qword ptr [rsp + 376], rax # 8-byte Spill mov r11, rsi - mov r12, r14 -.LBB10_127: mov qword ptr [rsp + 8], r12 # 8-byte Spill - sub r15, qword ptr [rsp + 400] # 8-byte Folded Reload - mov qword ptr [rsp + 320], r15 # 8-byte Spill - mov r13d, dword ptr [rsp + 392] # 4-byte Reload +.LBB10_146: + sub rcx, qword ptr [rsp + 376] # 8-byte Folded Reload + mov qword ptr [rsp + 352], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB10_128: # =>This Inner Loop Header: Depth=1 - cmp word ptr [r11], r13w - setge byte ptr [rsp + 240] # 1-byte Folded Spill - cmp word ptr [r11 + 2], r13w +.LBB10_147: # =>This Inner Loop Header: Depth=1 + cmp word ptr [r11], r15w + setge byte ptr [rsp + 304] # 1-byte Folded Spill + cmp word ptr [r11 + 2], r15w setge r8b - cmp word ptr [r11 + 4], r13w + cmp word ptr [r11 + 4], r15w setge r14b - cmp word ptr [r11 + 6], r13w + cmp word ptr [r11 + 6], r15w + setge r13b + cmp word ptr [r11 + 8], r15w setge byte ptr [rsp + 272] # 1-byte Folded Spill - cmp word ptr [r11 + 8], r13w - setge byte ptr [rsp + 208] # 1-byte Folded Spill - cmp word ptr [r11 + 10], r13w + cmp word ptr [r11 + 10], r15w setge byte ptr [rsp + 192] # 1-byte Folded Spill - cmp word ptr [r11 + 12], r13w - setge al - cmp word ptr [r11 + 14], r13w + cmp word ptr [r11 + 12], r15w + setge byte ptr [rsp + 320] # 1-byte Folded Spill + cmp word ptr [r11 + 14], r15w setge bl - cmp word ptr [r11 + 16], r13w + cmp word ptr [r11 + 16], r15w setge byte ptr [rsp + 336] # 1-byte Folded Spill - cmp word ptr [r11 + 18], r13w + cmp word ptr [r11 + 18], r15w setge cl - cmp word ptr [r11 + 20], r13w + cmp word ptr [r11 + 20], r15w setge sil - cmp word ptr [r11 + 22], r13w + cmp word ptr [r11 + 22], r15w setge r9b - cmp word ptr [r11 + 24], r13w + cmp word ptr [r11 + 24], r15w setge r10b - cmp word ptr [r11 + 26], r13w - setge r12b - cmp word ptr [r11 + 28], r13w + cmp word ptr [r11 + 26], r15w + setge r15b + mov eax, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 28], ax setge byte ptr [rsp + 288] # 1-byte Folded Spill - cmp word ptr [r11 + 30], r13w + mov eax, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 30], ax setge dil - cmp word ptr [r11 + 32], r13w - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp word ptr [r11 + 34], r13w - setge byte ptr [rsp + 304] # 1-byte Folded Spill - cmp word ptr [r11 + 36], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 32], dx + setge byte ptr [rsp + 208] # 1-byte Folded Spill + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 34], dx + setge byte ptr [rsp + 240] # 1-byte Folded Spill + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 36], dx setge byte ptr [rsp + 256] # 1-byte Folded Spill - cmp word ptr [r11 + 38], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 38], dx setge byte ptr [rsp + 224] # 1-byte Folded Spill - cmp word ptr [r11 + 40], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 40], dx + setge byte ptr [rsp + 160] # 1-byte Folded Spill + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 42], dx setge byte ptr [rsp + 176] # 1-byte Folded Spill - cmp word ptr [r11 + 42], r13w - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp word ptr [r11 + 44], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 44], dx setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp word ptr [r11 + 46], r13w - setge r15b - cmp word ptr [r11 + 48], r13w - setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp word ptr [r11 + 50], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 46], dx + setge r12b + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 48], dx + setge byte ptr [rsp + 80] # 1-byte Folded Spill + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 50], dx setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp word ptr [r11 + 52], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 52], dx + setge byte ptr [rsp + 112] # 1-byte Folded Spill + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 54], dx setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp word ptr [r11 + 54], r13w - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp word ptr [r11 + 56], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 56], dx + setge byte ptr [rsp + 48] # 1-byte Folded Spill + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 58], dx setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp word ptr [r11 + 58], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 60], dx setge byte ptr [rsp + 16] # 1-byte Folded Spill - cmp word ptr [r11 + 60], r13w - setge byte ptr [rsp + 352] # 1-byte Folded Spill - cmp word ptr [r11 + 62], r13w + mov edx, dword ptr [rsp] # 4-byte Reload + cmp word ptr [r11 + 62], dx setge dl add r8b, r8b - add r8b, byte ptr [rsp + 240] # 1-byte Folded Reload + add r8b, byte ptr [rsp + 304] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 6 shl bl, 7 or bl, al @@ -51459,14 +52309,13 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar or r14b, r8b add cl, cl add cl, byte ptr [rsp + 336] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload - shl al, 3 - or al, r14b + shl r13b, 3 + or r13b, r14b shl sil, 2 or sil, cl - movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 272] # 1-byte Folded Reload shl cl, 4 - or cl, al + or cl, r13b mov r8d, ecx shl r9b, 3 or r9b, sil @@ -51475,31 +52324,31 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar or cl, r8b shl r10b, 4 or r10b, r9b - shl r12b, 5 - or r12b, r10b + shl r15b, 5 + or r15b, r10b movzx esi, byte ptr [rsp + 288] # 1-byte Folded Reload shl sil, 6 shl dil, 7 or dil, sil or bl, cl - or dil, r12b - movzx ecx, byte ptr [rsp + 304] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 160] # 1-byte Folded Reload - mov esi, ecx + or dil, r15b + mov r15d, dword ptr [rsp] # 4-byte Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 208] # 1-byte Folded Reload movzx ecx, byte ptr [rsp + 256] # 1-byte Folded Reload shl cl, 2 - or cl, sil + or cl, al mov esi, ecx movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload shl cl, 3 or cl, sil mov esi, ecx - movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload shl cl, 4 or cl, sil mov esi, ecx - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 176] # 1-byte Folded Reload shl cl, 5 or cl, sil mov esi, ecx @@ -51507,148 +52356,160 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar mov byte ptr [rcx], bl movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload shl bl, 6 - shl r15b, 7 - or r15b, bl + shl r12b, 7 + or r12b, bl mov byte ptr [rcx + 1], dil - or r15b, sil + or r12b, sil movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 80] # 1-byte Folded Reload mov ebx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 4 or al, bl mov ebx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 5 or al, bl - movzx ebx, byte ptr [rsp + 352] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload shl bl, 6 shl dl, 7 or dl, bl or dl, al - mov byte ptr [rcx + 2], r15b + mov byte ptr [rcx + 2], r12b mov byte ptr [rcx + 3], dl add r11, 64 add rcx, 4 mov qword ptr [rsp + 8], rcx # 8-byte Spill - add qword ptr [rsp + 320], -1 # 8-byte Folded Spill - jne .LBB10_128 -# %bb.129: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r15, qword ptr [rsp + 456] # 8-byte Reload - mov r12, qword ptr [rsp + 8] # 8-byte Reload - jmp .LBB10_130 -.LBB10_157: + add qword ptr [rsp + 352], -1 # 8-byte Folded Spill + jne .LBB10_147 +# %bb.148: + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rcx, qword ptr [rsp + 440] # 8-byte Reload + jmp .LBB10_149 +.LBB10_178: mov r13, qword ptr [rdx] - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] + lea ecx, [r9 + 7] test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB10_161 -# %bb.158: - movsxd rax, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB10_184 +# %bb.179: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_182 +# %bb.180: + movsxd rdi, r9d + mov r11, r8 + mov rcx, rsi .p2align 4, 0x90 -.LBB10_159: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - lea rsi, [rsi + 8] - setge dl - neg dl - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r14 + rbx] - xor dl, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB10_181: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 8] + cmp qword ptr [rcx], r13 + setge bl + neg bl + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, dl - xor dil, r8b - mov byte ptr [r14 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB10_159 -# %bb.160: - add r14, 1 -.LBB10_161: - sar r11, 5 - cmp r10, 32 - jl .LBB10_165 -# %bb.162: - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 368], r11 # 8-byte Spill - mov qword ptr [rsp + 320], r11 # 8-byte Spill + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_181 +.LBB10_182: + sub r14, r8 + je .LBB10_227 +# %bb.183: + add r12, 1 +.LBB10_184: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB10_188 +# %bb.185: + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 352], rax # 8-byte Spill + mov qword ptr [rsp + 304], rax # 8-byte Spill .p2align 4, 0x90 -.LBB10_163: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 352], r14 # 8-byte Spill +.LBB10_186: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 8], r12 # 8-byte Spill cmp qword ptr [rsi], r13 - setge byte ptr [rsp + 240] # 1-byte Folded Spill + setge byte ptr [rsp + 320] # 1-byte Folded Spill cmp qword ptr [rsi + 8], r13 - setge r10b + setge r9b cmp qword ptr [rsi + 16], r13 setge r14b cmp qword ptr [rsi + 24], r13 - setge byte ptr [rsp + 272] # 1-byte Folded Spill + setge byte ptr [rsp + 240] # 1-byte Folded Spill cmp qword ptr [rsi + 32], r13 - setge byte ptr [rsp + 208] # 1-byte Folded Spill + setge byte ptr [rsp + 224] # 1-byte Folded Spill cmp qword ptr [rsi + 40], r13 - setge byte ptr [rsp + 192] # 1-byte Folded Spill + setge byte ptr [rsp + 176] # 1-byte Folded Spill cmp qword ptr [rsi + 48], r13 setge al cmp qword ptr [rsi + 56], r13 - setge bl + setge r11b cmp qword ptr [rsi + 64], r13 setge byte ptr [rsp + 336] # 1-byte Folded Spill cmp qword ptr [rsi + 72], r13 - setge dil + setge cl cmp qword ptr [rsi + 80], r13 - setge r8b + setge dil cmp qword ptr [rsi + 88], r13 - setge r9b + setge r8b cmp qword ptr [rsi + 96], r13 - setge r11b + setge r10b cmp qword ptr [rsi + 104], r13 setge r12b cmp qword ptr [rsi + 112], r13 setge byte ptr [rsp + 288] # 1-byte Folded Spill cmp qword ptr [rsi + 120], r13 - setge cl + setge dl cmp qword ptr [rsi + 128], r13 setge byte ptr [rsp + 160] # 1-byte Folded Spill cmp qword ptr [rsi + 136], r13 - setge byte ptr [rsp + 304] # 1-byte Folded Spill - cmp qword ptr [rsi + 144], r13 setge byte ptr [rsp + 256] # 1-byte Folded Spill + cmp qword ptr [rsi + 144], r13 + setge byte ptr [rsp + 272] # 1-byte Folded Spill cmp qword ptr [rsi + 152], r13 - setge byte ptr [rsp + 224] # 1-byte Folded Spill + setge byte ptr [rsp + 208] # 1-byte Folded Spill cmp qword ptr [rsi + 160], r13 - setge byte ptr [rsp + 176] # 1-byte Folded Spill + setge byte ptr [rsp + 192] # 1-byte Folded Spill cmp qword ptr [rsi + 168], r13 - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp qword ptr [rsi + 176], r13 setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp qword ptr [rsi + 176], r13 + setge byte ptr [rsp + 144] # 1-byte Folded Spill cmp qword ptr [rsi + 184], r13 setge r15b cmp qword ptr [rsi + 192], r13 setge byte ptr [rsp + 48] # 1-byte Folded Spill cmp qword ptr [rsi + 200], r13 - setge byte ptr [rsp + 144] # 1-byte Folded Spill + setge byte ptr [rsp + 112] # 1-byte Folded Spill cmp qword ptr [rsi + 208], r13 setge byte ptr [rsp + 96] # 1-byte Folded Spill cmp qword ptr [rsi + 216], r13 @@ -51658,339 +52519,71 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar cmp qword ptr [rsi + 232], r13 setge byte ptr [rsp + 16] # 1-byte Folded Spill cmp qword ptr [rsi + 240], r13 - setge byte ptr [rsp + 8] # 1-byte Folded Spill + setge byte ptr [rsp] # 1-byte Folded Spill cmp qword ptr [rsi + 248], r13 - setge dl - add r10b, r10b - add r10b, byte ptr [rsp + 240] # 1-byte Folded Reload + setge bl + add r9b, r9b + add r9b, byte ptr [rsp + 320] # 1-byte Folded Reload shl al, 6 - shl bl, 7 - or bl, al + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r10b - add dil, dil - add dil, byte ptr [rsp + 336] # 1-byte Folded Reload - movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 336] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload shl al, 3 or al, r14b - mov r10d, eax - mov r14, qword ptr [rsp + 352] # 8-byte Reload - shl r8b, 2 + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 or r8b, dil - movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload - shl al, 4 - or al, r10b - mov edi, eax - shl r9b, 3 - or r9b, r8b - movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload shl al, 5 - or al, dil - shl r11b, 4 - or r11b, r9b + or al, cl + shl r10b, 4 + or r10b, r8b shl r12b, 5 - or r12b, r11b - movzx edi, byte ptr [rsp + 288] # 1-byte Folded Reload - shl dil, 6 - shl cl, 7 - or cl, dil - or bl, al - or cl, r12b - movzx eax, byte ptr [rsp + 304] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 160] # 1-byte Folded Reload - mov edi, eax + or r12b, r10b + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 8] # 8-byte Reload movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload - shl al, 2 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 224] # 1-byte Folded Reload - shl al, 3 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 4 - or al, dil - mov edi, eax - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 5 - or al, dil - mov byte ptr [r14], bl - movzx ebx, byte ptr [rsp + 128] # 1-byte Folded Reload - shl bl, 6 - shl r15b, 7 - or r15b, bl - mov byte ptr [r14 + 1], cl - or r15b, al - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 48] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload - shl al, 5 - or al, cl - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl cl, 6 - shl dl, 7 - or dl, cl - or dl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], dl - add rsi, 256 - add r14, 4 - add qword ptr [rsp + 320], -1 # 8-byte Folded Spill - jne .LBB10_163 -# %bb.164: - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r11, qword ptr [rsp + 368] # 8-byte Reload -.LBB10_165: - shl r11, 5 - cmp r11, r10 - jge .LBB10_201 -# %bb.166: - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 - jne .LBB10_170 -# %bb.167: - xor r11d, r11d - jmp .LBB10_168 -.LBB10_172: - lea r11, [r10 + 31] - test r10, r10 - cmovns r11, r10 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - movss xmm11, dword ptr [rdx] # xmm11 = mem[0],zero,zero,zero - sub r9d, eax - je .LBB10_176 -# %bb.173: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB10_174: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - add rsi, 4 - ucomiss xmm0, xmm11 - mov edx, 0 - adc dl, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor dl, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, dl - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB10_174 -# %bb.175: - add r14, 1 -.LBB10_176: - sar r11, 5 - cmp r10, 32 - jl .LBB10_177 -# %bb.178: - cmp r11, 4 - jb .LBB10_179 -# %bb.180: - mov rax, r11 - shl rax, 7 - add rax, rsi - cmp r14, rax - jae .LBB10_182 -# %bb.181: - lea rax, [r14 + 4*r11] - cmp rax, rsi - jbe .LBB10_182 -.LBB10_179: - xor eax, eax - mov rdx, rsi - mov r15, r14 -.LBB10_185: - mov qword ptr [rsp + 8], r15 # 8-byte Spill - mov qword ptr [rsp + 72], r10 # 8-byte Spill - mov qword ptr [rsp + 320], r11 # 8-byte Spill - sub r11, rax - mov qword ptr [rsp + 240], r11 # 8-byte Spill - .p2align 4, 0x90 -.LBB10_186: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rdx] # xmm0 = mem[0],zero,zero,zero - movss xmm1, dword ptr [rdx + 4] # xmm1 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 288] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - setae cl - movss xmm0, dword ptr [rdx + 8] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae sil - movss xmm0, dword ptr [rdx + 12] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae dil - movss xmm0, dword ptr [rdx + 16] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae r8b - movss xmm0, dword ptr [rdx + 20] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 272] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 24] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 304] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 28] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 336] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 32] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 192] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 36] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae r9b - movss xmm0, dword ptr [rdx + 40] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae r11b - movss xmm0, dword ptr [rdx + 44] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae r15b - movss xmm0, dword ptr [rdx + 48] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae al - movss xmm0, dword ptr [rdx + 52] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 208] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 56] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 176] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 60] # xmm0 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 224] # 1-byte Folded Spill - movss xmm0, dword ptr [rdx + 64] # xmm0 = mem[0],zero,zero,zero - movss xmm1, dword ptr [rdx + 68] # xmm1 = mem[0],zero,zero,zero - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 72] # xmm0 = mem[0],zero,zero,zero - setae byte ptr [rsp + 144] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - movss xmm1, dword ptr [rdx + 76] # xmm1 = mem[0],zero,zero,zero - setae r10b - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 80] # xmm0 = mem[0],zero,zero,zero - setae r14b - ucomiss xmm1, xmm11 - movss xmm1, dword ptr [rdx + 84] # xmm1 = mem[0],zero,zero,zero - setae r12b - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 88] # xmm0 = mem[0],zero,zero,zero - setae byte ptr [rsp + 256] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - movss xmm1, dword ptr [rdx + 92] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 160] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 96] # xmm0 = mem[0],zero,zero,zero - setae byte ptr [rsp + 112] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - movss xmm1, dword ptr [rdx + 100] # xmm1 = mem[0],zero,zero,zero - setae r13b - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 104] # xmm0 = mem[0],zero,zero,zero - setae byte ptr [rsp + 16] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - movss xmm1, dword ptr [rdx + 108] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 128] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 112] # xmm0 = mem[0],zero,zero,zero - setae byte ptr [rsp + 96] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - movss xmm1, dword ptr [rdx + 116] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 80] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - movss xmm0, dword ptr [rdx + 120] # xmm0 = mem[0],zero,zero,zero - setae byte ptr [rsp + 48] # 1-byte Folded Spill - ucomiss xmm1, xmm11 - movss xmm1, dword ptr [rdx + 124] # xmm1 = mem[0],zero,zero,zero - setae byte ptr [rsp + 32] # 1-byte Folded Spill - ucomiss xmm0, xmm11 - setae byte ptr [rsp + 352] # 1-byte Folded Spill - sub rdx, -128 - ucomiss xmm1, xmm11 - setae bl - add cl, cl - add cl, byte ptr [rsp + 288] # 1-byte Folded Reload - shl sil, 2 - or sil, cl - shl dil, 3 - or dil, sil - shl r8b, 4 - or r8b, dil - movzx ecx, byte ptr [rsp + 272] # 1-byte Folded Reload - shl cl, 5 - or cl, r8b - movzx edi, byte ptr [rsp + 304] # 1-byte Folded Reload - shl dil, 6 - movzx esi, byte ptr [rsp + 336] # 1-byte Folded Reload - shl sil, 7 - or sil, dil - add r9b, r9b - add r9b, byte ptr [rsp + 192] # 1-byte Folded Reload - shl r11b, 2 - or r11b, r9b - shl r15b, 3 - or r15b, r11b - shl al, 4 - or al, r15b - or sil, cl - movzx ecx, byte ptr [rsp + 208] # 1-byte Folded Reload - shl cl, 5 - or cl, al - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload - shl al, 6 - movzx edi, byte ptr [rsp + 224] # 1-byte Folded Reload - shl dil, 7 - or dil, al - add r10b, r10b - add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r10b - shl r12b, 3 - or r12b, r14b - movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload - shl al, 4 - or al, r12b - mov r8d, eax - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload - shl al, 5 - or al, r8b - or dil, cl - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl cl, 6 - shl r13b, 7 - or r13b, cl - mov r8, qword ptr [rsp + 8] # 8-byte Reload - mov byte ptr [r8], sil - or r13b, al movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 6 + shl r15b, 7 + or r15b, cl + mov byte ptr [r12 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 16] # 1-byte Folded Reload + add al, byte ptr [rsp + 48] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 2 @@ -52000,2561 +52593,1744 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, cl - mov byte ptr [r8 + 1], dil - movzx ecx, byte ptr [rsp + 352] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp] # 1-byte Folded Reload shl cl, 6 shl bl, 7 or bl, cl - mov byte ptr [r8 + 2], r13b or bl, al - mov byte ptr [r8 + 3], bl - add r8, 4 - mov qword ptr [rsp + 8], r8 # 8-byte Spill - add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl + add rsi, 256 + add r12, 4 + add qword ptr [rsp + 304], -1 # 8-byte Folded Spill jne .LBB10_186 # %bb.187: - mov r15, qword ptr [rsp + 8] # 8-byte Reload - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r11, qword ptr [rsp + 320] # 8-byte Reload - jmp .LBB10_188 -.LBB10_9: - mov qword ptr [rsp + 144], r14 # 8-byte Spill -.LBB10_91: - shl r15, 5 - cmp r15, r10 - jge .LBB10_201 -# %bb.92: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_94 -# %bb.93: - xor r9d, r9d - jmp .LBB10_97 -.LBB10_61: - mov qword ptr [rsp + 224], r14 # 8-byte Spill -.LBB10_72: - shl r15, 5 - cmp r15, r10 - jge .LBB10_201 -# %bb.73: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_75 -# %bb.74: - xor r9d, r9d - jmp .LBB10_78 -.LBB10_119: - mov r12, r14 - mov r11, rsi -.LBB10_130: - shl r15, 5 - cmp r15, r10 - jge .LBB10_201 -# %bb.131: - mov r8, r10 - sub r8, r15 - not r15 - add r15, r10 - jne .LBB10_135 -# %bb.132: - xor esi, esi - jmp .LBB10_133 -.LBB10_177: - mov r15, r14 - mov rdx, rsi + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rax, qword ptr [rsp + 352] # 8-byte Reload .LBB10_188: - shl r11, 5 - cmp r11, r10 - jge .LBB10_201 + shl rax, 5 + mov r8, r14 + sub r8, rax + jle .LBB10_227 # %bb.189: - mov rax, rdx - mov r8, r10 - sub r8, r11 - not r11 - add r11, r10 + or rax, 1 + cmp r14, rax jne .LBB10_193 # %bb.190: - xor esi, esi - jmp .LBB10_191 -.LBB10_155: - mov r9, r8 - and r9, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB10_156: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - mov edi, 0 - adc dil, -1 - mov rdx, r11 - shr rdx, 3 - movzx r10d, byte ptr [r14 + rdx] - xor dil, r10b - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - and al, dil - xor al, r10b - mov byte ptr [r14 + rdx], al - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] - mov edi, 0 - adc dil, -1 - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rdx], bl - cmp r9, r11 - jne .LBB10_156 -.LBB10_40: - test r8b, 1 - je .LBB10_201 -# %bb.41: - xor eax, eax - cmp qword ptr [rsi], r13 - jmp .LBB10_199 -.LBB10_153: - mov r10, r8 - and r10, -2 xor r11d, r11d - .p2align 4, 0x90 -.LBB10_154: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - setge al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - setge al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r10, r11 - jne .LBB10_154 -.LBB10_150: - test r8b, 1 - je .LBB10_201 -# %bb.151: - cmp dword ptr [rsi], r13d - jmp .LBB10_152 -.LBB10_94: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 144] # 8-byte Reload - .p2align 4, 0x90 -.LBB10_95: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r11b - setge bl - neg bl - mov rdi, r9 - shr rdi, 3 - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - movzx r9d, byte ptr [r14 + rdi] - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp byte ptr [rsi + rax + 1], r11b - lea r9, [rax + 2] - setge bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, r9 - jne .LBB10_95 -# %bb.96: - add rsi, r9 -.LBB10_97: - test r8b, 1 + jmp .LBB10_191 +.LBB10_195: + mov r15d, dword ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax je .LBB10_201 -# %bb.98: - cmp byte ptr [rsi], r11b - setge al - neg al - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and r9b, 7 - mov bl, 1 - mov ecx, r9d - shl bl, cl - xor al, dil - and bl, al - jmp .LBB10_80 -.LBB10_75: - mov r10, r8 - and r10, -2 - xor r9d, r9d - mov r14, qword ptr [rsp + 224] # 8-byte Reload +# %bb.196: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_199 +# %bb.197: + movsxd rdx, r9d + movd xmm0, r15d + mov r11, r8 .p2align 4, 0x90 -.LBB10_76: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp byte ptr [rsi + r9], r11b - mov ebx, 0 - adc bl, -1 - mov rdi, r9 - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, eax - and cl, 6 - mov dl, 1 - shl dl, cl - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r14 + rdi], dl - cmp byte ptr [rsi + rax + 1], r11b - lea r9, [rax + 2] +.LBB10_198: # =>This Inner Loop Header: Depth=1 + movss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + add rsi, 4 + ucomiss xmm1, xmm0 mov ebx, 0 adc bl, -1 - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r14 + rdi], al - cmp r10, r9 - jne .LBB10_76 -# %bb.77: - add rsi, r9 -.LBB10_78: - test r8b, 1 - je .LBB10_201 -# %bb.79: - xor eax, eax - cmp byte ptr [rsi], r11b - adc al, -1 - mov rdx, r9 - shr rdx, 3 - mov r8, qword ptr [rsp + 224] # 8-byte Reload - mov dil, byte ptr [r8 + rdx] - and r9b, 7 - mov bl, 1 - mov ecx, r9d - shl bl, cl - xor al, dil - and bl, al -.LBB10_80: - xor bl, dil - mov byte ptr [r8 + rdx], bl - jmp .LBB10_201 -.LBB10_137: - mov r9, r8 - and r9, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB10_138: # =>This Inner Loop Header: Depth=1 - cmp dword ptr [rsi], r13d - mov edi, 0 - adc dil, -1 - mov rdx, r11 - shr rdx, 3 - movzx r10d, byte ptr [r14 + rdx] - xor dil, r10b - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - and al, dil - xor al, r10b - mov byte ptr [r14 + rdx], al - add r11, 2 - cmp dword ptr [rsi + 4], r13d - lea rsi, [rsi + 8] - mov edi, 0 - adc dil, -1 - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rdx], bl - cmp r9, r11 - jne .LBB10_138 -.LBB10_24: - test r8b, 1 - je .LBB10_201 -# %bb.25: - xor eax, eax - cmp dword ptr [rsi], r13d - jmp .LBB10_199 -.LBB10_195: - mov r10, r8 - and r10, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB10_196: # =>This Inner Loop Header: Depth=1 - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - ucomisd xmm1, xmm0 - mov eax, 0 - adc al, -1 - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - xor al, r9b - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - and bl, al + lea rax, [rdx + 7] + test rdx, rdx + cmovns rax, rdx + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r14 + rdi], bl - add r11, 2 - movsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero - add rsi, 16 - ucomisd xmm1, xmm0 - mov eax, 0 - adc al, -1 - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r10, r11 - jne .LBB10_196 -.LBB10_197: - test r8b, 1 - je .LBB10_201 -# %bb.198: - movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero - xor eax, eax - ucomisd xmm1, xmm0 - jmp .LBB10_199 -.LBB10_112: - mov r9, r8 - and r9, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB10_113: # =>This Inner Loop Header: Depth=1 - cmp word ptr [rsi], r13w - mov edi, 0 - adc dil, -1 - mov rdx, r11 - shr rdx, 3 - movzx r10d, byte ptr [r14 + rdx] - xor dil, r10b - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - and al, dil - xor al, r10b - mov byte ptr [r14 + rdx], al - add r11, 2 - cmp word ptr [rsi + 2], r13w - lea rsi, [rsi + 4] - mov edi, 0 - adc dil, -1 - xor dil, al - or cl, 1 - mov bl, 1 - shl bl, cl - and bl, dil - xor bl, al - mov byte ptr [r14 + rdx], bl - cmp r9, r11 - jne .LBB10_113 -.LBB10_110: - test r8b, 1 - je .LBB10_201 -# %bb.111: - xor eax, eax - cmp word ptr [rsi], r13w + lea r10d, [8*rax] + mov ecx, edx + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rdx, 1 + add r11, -1 + jne .LBB10_198 .LBB10_199: - adc al, -1 - mov rdx, r11 - shr rdx, 3 - mov sil, byte ptr [r14 + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, sil - and bl, al - jmp .LBB10_200 -.LBB10_170: - mov r10, r8 - and r10, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB10_171: # =>This Inner Loop Header: Depth=1 - cmp qword ptr [rsi], r13 - setge al - neg al - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov bl, 1 - shl bl, cl - xor al, r9b - and bl, al - xor bl, r9b - mov byte ptr [r14 + rdi], bl - add r11, 2 - cmp qword ptr [rsi + 8], r13 - lea rsi, [rsi + 16] - setge al - neg al - xor al, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, al - xor dl, bl - mov byte ptr [r14 + rdi], dl - cmp r10, r11 - jne .LBB10_171 -.LBB10_168: - test r8b, 1 - je .LBB10_201 -# %bb.169: - cmp qword ptr [rsi], r13 -.LBB10_152: - setge al - neg al - mov rdx, r11 - shr rdx, 3 - mov sil, byte ptr [r14 + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, sil - and bl, al -.LBB10_200: - xor bl, sil - mov byte ptr [r14 + rdx], bl + sub r14, r8 + je .LBB10_227 +# %bb.200: + add r12, 1 .LBB10_201: - lea rsp, [rbp - 40] - pop rbx - pop r12 - pop r13 - pop r14 - pop r15 - pop rbp - ret -.LBB10_135: - mov r10, r8 - and r10, -2 - xor esi, esi - mov r14d, dword ptr [rsp + 392] # 4-byte Reload - .p2align 4, 0x90 -.LBB10_136: # =>This Inner Loop Header: Depth=1 - cmp word ptr [r11], r14w - setge bl - neg bl - mov rdi, rsi - shr rdi, 3 - movzx r9d, byte ptr [r12 + rdi] - mov ecx, esi - and cl, 6 - mov dl, 1 - shl dl, cl - xor bl, r9b - and dl, bl - xor dl, r9b - mov byte ptr [r12 + rdi], dl - add rsi, 2 - cmp word ptr [r11 + 2], r14w - lea r11, [r11 + 4] - setge bl - neg bl - xor bl, dl - or cl, 1 - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r12 + rdi], al - cmp r10, rsi - jne .LBB10_136 -.LBB10_133: - test r8b, 1 - je .LBB10_201 -# %bb.134: - mov eax, dword ptr [rsp + 392] # 4-byte Reload - cmp word ptr [r11], ax - setge al - neg al - mov rdx, rsi - shr rdx, 3 - mov dil, byte ptr [r12 + rdx] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r12 + rdx], bl - jmp .LBB10_201 -.LBB10_193: - mov r10, r8 - and r10, -2 - xor esi, esi - mov r11, r15 - .p2align 4, 0x90 -.LBB10_194: # =>This Inner Loop Header: Depth=1 - movss xmm0, dword ptr [rax] # xmm0 = mem[0],zero,zero,zero + lea rdi, [r14 + 31] + test r14, r14 + cmovns rdi, r14 + sar rdi, 5 + cmp r14, 32 + jl .LBB10_202 +# %bb.203: + movd xmm11, r15d + cmp rdi, 4 + jb .LBB10_204 +# %bb.205: + mov rax, rdi + shl rax, 7 + add rax, rsi + cmp r12, rax + jae .LBB10_207 +# %bb.206: + lea rax, [r12 + 4*rdi] + cmp rax, rsi + jbe .LBB10_207 +.LBB10_204: + xor eax, eax + mov rcx, rsi + mov r11, r12 +.LBB10_210: + mov qword ptr [rsp], r11 # 8-byte Spill + mov dword ptr [rsp + 304], r15d # 4-byte Spill + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 352], rdi # 8-byte Spill + sub rdi, rax + mov qword ptr [rsp + 320], rdi # 8-byte Spill + .p2align 4, 0x90 +.LBB10_211: # =>This Inner Loop Header: Depth=1 + movss xmm0, dword ptr [rcx] # xmm0 = mem[0],zero,zero,zero + movss xmm1, dword ptr [rcx + 4] # xmm1 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 288] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + setae dl + movss xmm0, dword ptr [rcx + 8] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae sil + movss xmm0, dword ptr [rcx + 12] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae dil + movss xmm0, dword ptr [rcx + 16] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae r8b + movss xmm0, dword ptr [rcx + 20] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 240] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 24] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 256] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 28] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 336] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 32] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 176] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 36] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae r9b + movss xmm0, dword ptr [rcx + 40] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae r11b + movss xmm0, dword ptr [rcx + 44] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, xmm11 - mov ebx, 0 - adc bl, -1 - mov rdi, rsi - shr rdi, 3 - movzx r9d, byte ptr [r11 + rdi] - xor bl, r9b - mov ecx, esi - and cl, 6 - mov dl, 1 - shl dl, cl - and dl, bl - xor dl, r9b - mov byte ptr [r11 + rdi], dl - add rsi, 2 - movss xmm0, dword ptr [rax + 4] # xmm0 = mem[0],zero,zero,zero - add rax, 8 + setae r15b + movss xmm0, dword ptr [rcx + 48] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, xmm11 - mov ebx, 0 - adc bl, -1 - xor bl, dl - or cl, 1 - mov r9, rax - mov al, 1 - shl al, cl - and al, bl - xor al, dl - mov byte ptr [r11 + rdi], al - mov rax, r9 - cmp r10, rsi - jne .LBB10_194 -.LBB10_191: - test r8b, 1 - je .LBB10_201 -# %bb.192: - movss xmm0, dword ptr [rax] # xmm0 = mem[0],zero,zero,zero - xor eax, eax + setae al + movss xmm0, dword ptr [rcx + 52] # xmm0 = mem[0],zero,zero,zero ucomiss xmm0, xmm11 - adc al, -1 - mov rdx, rsi - shr rdx, 3 - mov dil, byte ptr [r15 + rdx] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r15 + rdx], bl - jmp .LBB10_201 -.LBB10_85: - and r15, -16 - mov rax, r15 - shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 368], rax # 8-byte Spill - mov qword ptr [rsp + 240], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 144], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 320], xmm1 # 16-byte Spill - xor r8d, r8d - mov qword ptr [rsp + 352], r14 # 8-byte Spill + setae byte ptr [rsp + 224] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 56] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 192] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 60] # xmm0 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 208] # 1-byte Folded Spill + movss xmm0, dword ptr [rcx + 64] # xmm0 = mem[0],zero,zero,zero + movss xmm1, dword ptr [rcx + 68] # xmm1 = mem[0],zero,zero,zero + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 72] # xmm0 = mem[0],zero,zero,zero + setae byte ptr [rsp + 112] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + movss xmm1, dword ptr [rcx + 76] # xmm1 = mem[0],zero,zero,zero + setae r10b + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 80] # xmm0 = mem[0],zero,zero,zero + setae r14b + ucomiss xmm1, xmm11 + movss xmm1, dword ptr [rcx + 84] # xmm1 = mem[0],zero,zero,zero + setae r12b + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 88] # xmm0 = mem[0],zero,zero,zero + setae byte ptr [rsp + 272] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + movss xmm1, dword ptr [rcx + 92] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 160] # 1-byte Folded Spill + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 96] # xmm0 = mem[0],zero,zero,zero + setae byte ptr [rsp + 128] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + movss xmm1, dword ptr [rcx + 100] # xmm1 = mem[0],zero,zero,zero + setae r13b + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 104] # xmm0 = mem[0],zero,zero,zero + setae byte ptr [rsp + 16] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + movss xmm1, dword ptr [rcx + 108] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 144] # 1-byte Folded Spill + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 112] # xmm0 = mem[0],zero,zero,zero + setae byte ptr [rsp + 96] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + movss xmm1, dword ptr [rcx + 116] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 80] # 1-byte Folded Spill + ucomiss xmm0, xmm11 + movss xmm0, dword ptr [rcx + 120] # xmm0 = mem[0],zero,zero,zero + setae byte ptr [rsp + 48] # 1-byte Folded Spill + ucomiss xmm1, xmm11 + movss xmm1, dword ptr [rcx + 124] # xmm1 = mem[0],zero,zero,zero + setae byte ptr [rsp + 32] # 1-byte Folded Spill + ucomiss xmm0, xmm11 + setae byte ptr [rsp + 8] # 1-byte Folded Spill + sub rcx, -128 + ucomiss xmm1, xmm11 + setae bl + add dl, dl + add dl, byte ptr [rsp + 288] # 1-byte Folded Reload + shl sil, 2 + or sil, dl + shl dil, 3 + or dil, sil + shl r8b, 4 + or r8b, dil + movzx edx, byte ptr [rsp + 240] # 1-byte Folded Reload + shl dl, 5 + or dl, r8b + movzx edi, byte ptr [rsp + 256] # 1-byte Folded Reload + shl dil, 6 + movzx esi, byte ptr [rsp + 336] # 1-byte Folded Reload + shl sil, 7 + or sil, dil + add r9b, r9b + add r9b, byte ptr [rsp + 176] # 1-byte Folded Reload + shl r11b, 2 + or r11b, r9b + shl r15b, 3 + or r15b, r11b + shl al, 4 + or al, r15b + or sil, dl + movzx edx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl dl, 5 + or dl, al + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 6 + movzx edi, byte ptr [rsp + 208] # 1-byte Folded Reload + shl dil, 7 + or dil, al + add r10b, r10b + add r10b, byte ptr [rsp + 112] # 1-byte Folded Reload + shl r14b, 2 + or r14b, r10b + shl r12b, 3 + or r12b, r14b + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + shl al, 4 + or al, r12b + mov r8d, eax + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + shl al, 5 + or al, r8b + or dil, dl + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dl, 6 + shl r13b, 7 + or r13b, dl + mov r8, qword ptr [rsp] # 8-byte Reload + mov byte ptr [r8], sil + or r13b, al + movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 16] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 5 + or al, dl + mov byte ptr [r8 + 1], dil + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + mov byte ptr [r8 + 2], r13b + or bl, al + mov byte ptr [r8 + 3], bl + add r8, 4 + mov qword ptr [rsp], r8 # 8-byte Spill + add qword ptr [rsp + 320], -1 # 8-byte Folded Spill + jne .LBB10_211 +# %bb.212: + mov r11, qword ptr [rsp] # 8-byte Reload + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov r15d, dword ptr [rsp + 304] # 4-byte Reload + mov rdi, qword ptr [rsp + 352] # 8-byte Reload + jmp .LBB10_213 +.LBB10_58: + mov r13b, byte ptr [rdx] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB10_59 +# %bb.60: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_61 +# %bb.66: + movsxd rdx, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB10_86: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 256], r8 # 8-byte Spill - shl r8, 5 - mov r9, r8 - mov rdi, r8 - mov qword ptr [rsp + 128], r8 # 8-byte Spill - mov r12, r8 - mov r15, r8 - mov qword ptr [rsp + 16], r8 # 8-byte Spill +.LBB10_67: # =>This Inner Loop Header: Depth=1 + lea rdi, [rsi + 1] + cmp byte ptr [rsi], r13b + mov esi, 0 + adc sil, -1 + lea rbx, [rdx + 7] + test rdx, rdx + cmovns rbx, rdx + sar rbx, 3 + movzx r9d, byte ptr [r12 + rbx] + xor sil, r9b + lea r10d, [8*rbx] + mov ecx, edx + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, sil + xor al, r9b + mov byte ptr [r12 + rbx], al + add rdx, 1 + mov rsi, rdi + add r11, -1 + jne .LBB10_67 +# %bb.62: + sub r14, r8 + jne .LBB10_63 + jmp .LBB10_227 +.LBB10_158: + mov r13d, dword ptr [rdx] + lea ecx, [r9 + 7] + test r9d, r9d + cmovns ecx, r9d + and ecx, -8 + sub r9d, ecx + je .LBB10_164 +# %bb.159: + mov r8d, 8 + sub r8d, r9d + cmp r8, r14 + cmovg r8, r14 + test r8, r8 + jle .LBB10_162 +# %bb.160: + movsxd rdi, r9d mov r11, r8 - mov r10, r8 - mov rax, r8 - mov rdx, r8 - mov r14, r8 - movzx ecx, byte ptr [rsi + r8] - movd xmm9, ecx - movzx ecx, byte ptr [rsi + r8 + 1] - movd xmm2, ecx - movzx ecx, byte ptr [rsi + r8 + 2] - movd xmm3, ecx - movzx ecx, byte ptr [rsi + r8 + 3] - movd xmm4, ecx - movzx ecx, byte ptr [rsi + r8 + 4] - movd xmm6, ecx - movzx ecx, byte ptr [rsi + r8 + 5] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 112], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + r8 + 6] - movd xmm7, ecx - movzx ecx, byte ptr [rsi + r8 + 7] - movd xmm0, ecx - movdqa xmmword ptr [rsp + 304], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rsi + r8 + 8] - movd xmm13, ecx - movzx ecx, byte ptr [rsi + r8 + 9] - movd xmm8, ecx - movzx ecx, byte ptr [rsi + r8 + 10] - movd xmm10, ecx - movzx ecx, byte ptr [rsi + r8 + 11] - movd xmm1, ecx - movzx ecx, byte ptr [rsi + r8 + 12] - movd xmm12, ecx - movzx ecx, byte ptr [rsi + r8 + 16] - movd xmm14, ecx - mov qword ptr [rsp + 192], r8 # 8-byte Spill - movzx ecx, byte ptr [rsi + r8 + 24] - movd xmm5, ecx - mov rcx, r8 - or rcx, 32 - mov r13, rcx - mov qword ptr [rsp + 80], rcx # 8-byte Spill - or r9, 64 - mov qword ptr [rsp + 32], r9 # 8-byte Spill - mov rcx, r9 - mov r9, r8 - or r9, 96 - or qword ptr [rsp + 128], 128 # 8-byte Folded Spill - or r12, 160 - or r15, 192 - mov rbx, qword ptr [rsp + 16] # 8-byte Reload - or rbx, 224 - or r11, 256 - or r10, 288 - or rax, 320 - or rdx, 352 - mov qword ptr [rsp + 48], rdx # 8-byte Spill - or r14, 384 - mov qword ptr [rsp + 176], r14 # 8-byte Spill - or rdi, 416 - mov qword ptr [rsp + 96], rdi # 8-byte Spill - mov rdi, r8 - or rdi, 448 - mov qword ptr [rsp + 16], rdi # 8-byte Spill - mov rdi, r8 - or rdi, 480 - pinsrb xmm9, byte ptr [rsi + r13], 1 - pinsrb xmm9, byte ptr [rsi + rcx], 2 - pinsrb xmm9, byte ptr [rsi + r9], 3 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r8], 4 - pinsrb xmm9, byte ptr [rsi + r12], 5 - pinsrb xmm9, byte ptr [rsi + r15], 6 - pinsrb xmm9, byte ptr [rsi + rbx], 7 - pinsrb xmm9, byte ptr [rsi + r11], 8 - pinsrb xmm9, byte ptr [rsi + r10], 9 - pinsrb xmm9, byte ptr [rsi + rax], 10 - pinsrb xmm9, byte ptr [rsi + rdx], 11 - pinsrb xmm9, byte ptr [rsi + r14], 12 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + r13], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rsi + rcx], 14 - mov qword ptr [rsp + 208], rdi # 8-byte Spill - pinsrb xmm9, byte ptr [rsi + rdi], 15 - movdqa xmm15, xmmword ptr [rsp + 320] # 16-byte Reload - movdqa xmm11, xmm15 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 1], 1 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 1], 2 - pinsrb xmm2, byte ptr [rsi + r9 + 1], 3 - pinsrb xmm2, byte ptr [rsi + r8 + 1], 4 - pinsrb xmm2, byte ptr [rsi + r12 + 1], 5 - pinsrb xmm2, byte ptr [rsi + r15 + 1], 6 - pinsrb xmm2, byte ptr [rsi + rbx + 1], 7 - pinsrb xmm2, byte ptr [rsi + r11 + 1], 8 - pinsrb xmm2, byte ptr [rsi + r10 + 1], 9 - pinsrb xmm2, byte ptr [rsi + rax + 1], 10 - pinsrb xmm2, byte ptr [rsi + rdx + 1], 11 - pinsrb xmm2, byte ptr [rsi + r14 + 1], 12 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r13 + 1], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rcx + 1], 14 - pinsrb xmm2, byte ptr [rsi + rdi + 1], 15 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 2], 1 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r13 + 2], 2 - pinsrb xmm3, byte ptr [rsi + r9 + 2], 3 - pinsrb xmm3, byte ptr [rsi + r8 + 2], 4 - pinsrb xmm3, byte ptr [rsi + r12 + 2], 5 - pinsrb xmm3, byte ptr [rsi + r15 + 2], 6 - pinsrb xmm3, byte ptr [rsi + rbx + 2], 7 - pinsrb xmm3, byte ptr [rsi + r11 + 2], 8 - pinsrb xmm3, byte ptr [rsi + r10 + 2], 9 - pinsrb xmm3, byte ptr [rsi + rax + 2], 10 - pinsrb xmm3, byte ptr [rsi + rdx + 2], 11 - pinsrb xmm3, byte ptr [rsi + r14 + 2], 12 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 2], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 2], 14 - pinsrb xmm3, byte ptr [rsi + rdi + 2], 15 - movdqa xmm0, xmm3 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 3], 1 - pinsrb xmm4, byte ptr [rsi + r13 + 3], 2 - pinsrb xmm4, byte ptr [rsi + r9 + 3], 3 - pinsrb xmm4, byte ptr [rsi + r8 + 3], 4 - pinsrb xmm4, byte ptr [rsi + r12 + 3], 5 - pinsrb xmm4, byte ptr [rsi + r15 + 3], 6 - pinsrb xmm4, byte ptr [rsi + rbx + 3], 7 - pinsrb xmm4, byte ptr [rsi + r11 + 3], 8 - pinsrb xmm4, byte ptr [rsi + r10 + 3], 9 - pinsrb xmm4, byte ptr [rsi + rax + 3], 10 - pinsrb xmm4, byte ptr [rsi + rdx + 3], 11 - pinsrb xmm4, byte ptr [rsi + r14 + 3], 12 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 3], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 3], 14 - pinsrb xmm4, byte ptr [rsi + rdi + 3], 15 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 4], 1 - pinsrb xmm6, byte ptr [rsi + r13 + 4], 2 - pinsrb xmm6, byte ptr [rsi + r9 + 4], 3 - pinsrb xmm6, byte ptr [rsi + r8 + 4], 4 - pinsrb xmm6, byte ptr [rsi + r12 + 4], 5 - pinsrb xmm6, byte ptr [rsi + r15 + 4], 6 - pinsrb xmm6, byte ptr [rsi + rbx + 4], 7 - pinsrb xmm6, byte ptr [rsi + r11 + 4], 8 - pinsrb xmm6, byte ptr [rsi + r10 + 4], 9 - pinsrb xmm6, byte ptr [rsi + rax + 4], 10 - pinsrb xmm6, byte ptr [rsi + rdx + 4], 11 - pinsrb xmm6, byte ptr [rsi + r14 + 4], 12 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 4], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rcx + 4], 14 - pinsrb xmm6, byte ptr [rsi + rdi + 4], 15 - movdqa xmm3, xmmword ptr [rsp + 112] # 16-byte Reload - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 5], 1 - pinsrb xmm3, byte ptr [rsi + r13 + 5], 2 - pinsrb xmm3, byte ptr [rsi + r9 + 5], 3 - pinsrb xmm3, byte ptr [rsi + r8 + 5], 4 - pinsrb xmm3, byte ptr [rsi + r12 + 5], 5 - pinsrb xmm3, byte ptr [rsi + r15 + 5], 6 - pinsrb xmm3, byte ptr [rsi + rbx + 5], 7 - pinsrb xmm3, byte ptr [rsi + r11 + 5], 8 - pinsrb xmm3, byte ptr [rsi + r10 + 5], 9 - pinsrb xmm3, byte ptr [rsi + rax + 5], 10 - pinsrb xmm3, byte ptr [rsi + rdx + 5], 11 - pinsrb xmm3, byte ptr [rsi + r14 + 5], 12 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 5], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 5], 14 - pinsrb xmm3, byte ptr [rsi + rdi + 5], 15 - movdqa xmmword ptr [rsp + 112], xmm3 # 16-byte Spill - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdi + 6], 1 - mov rcx, r13 - pinsrb xmm7, byte ptr [rsi + r13 + 6], 2 - pinsrb xmm7, byte ptr [rsi + r9 + 6], 3 - pinsrb xmm7, byte ptr [rsi + r8 + 6], 4 - pinsrb xmm7, byte ptr [rsi + r12 + 6], 5 - pinsrb xmm7, byte ptr [rsi + r15 + 6], 6 - pinsrb xmm7, byte ptr [rsi + rbx + 6], 7 - pinsrb xmm7, byte ptr [rsi + r11 + 6], 8 - pinsrb xmm7, byte ptr [rsi + r10 + 6], 9 - pinsrb xmm7, byte ptr [rsi + rax + 6], 10 - pinsrb xmm7, byte ptr [rsi + rdx + 6], 11 - pinsrb xmm7, byte ptr [rsi + r14 + 6], 12 - pinsrb xmm13, byte ptr [rsi + rdi + 8], 1 - mov r13, rdi - pinsrb xmm13, byte ptr [rsi + rcx + 8], 2 - pinsrb xmm13, byte ptr [rsi + r9 + 8], 3 - pinsrb xmm13, byte ptr [rsi + r8 + 8], 4 - pinsrb xmm13, byte ptr [rsi + r12 + 8], 5 - pinsrb xmm13, byte ptr [rsi + r15 + 8], 6 - pinsrb xmm13, byte ptr [rsi + rbx + 8], 7 - pinsrb xmm13, byte ptr [rsi + r11 + 8], 8 - pinsrb xmm13, byte ptr [rsi + r10 + 8], 9 - pinsrb xmm13, byte ptr [rsi + rax + 8], 10 - pinsrb xmm13, byte ptr [rsi + rdx + 8], 11 - pinsrb xmm13, byte ptr [rsi + r14 + 8], 12 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + r8 + 8], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rcx + 8], 14 - pcmpgtb xmm11, xmm9 - mov rdi, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rdi + 8], 15 - movdqa xmm9, xmm15 - pcmpgtb xmm9, xmm13 - pinsrb xmm14, byte ptr [rsi + r13 + 16], 1 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rcx + 16], 2 - pinsrb xmm14, byte ptr [rsi + r9 + 16], 3 - mov r14, r9 - mov qword ptr [rsp + 160], r9 # 8-byte Spill - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rcx + 16], 4 - pinsrb xmm14, byte ptr [rsi + r12 + 16], 5 - mov qword ptr [rsp + 224], r12 # 8-byte Spill - pinsrb xmm14, byte ptr [rsi + r15 + 16], 6 - pinsrb xmm14, byte ptr [rsi + rbx + 16], 7 - pinsrb xmm14, byte ptr [rsi + r11 + 16], 8 - pinsrb xmm14, byte ptr [rsi + r10 + 16], 9 - pinsrb xmm14, byte ptr [rsi + rax + 16], 10 - mov r9, rax - pinsrb xmm14, byte ptr [rsi + rdx + 16], 11 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 16], 12 - pinsrb xmm14, byte ptr [rsi + r8 + 16], 13 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r13 + 16], 14 - pinsrb xmm14, byte ptr [rsi + rdi + 16], 15 - movdqa xmm3, xmm15 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 24], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 24], 2 - pinsrb xmm5, byte ptr [rsi + r14 + 24], 3 - pinsrb xmm5, byte ptr [rsi + rcx + 24], 4 - pinsrb xmm5, byte ptr [rsi + r12 + 24], 5 - pinsrb xmm5, byte ptr [rsi + r15 + 24], 6 - mov r14, r15 - pinsrb xmm5, byte ptr [rsi + rbx + 24], 7 - pinsrb xmm5, byte ptr [rsi + r11 + 24], 8 - pinsrb xmm5, byte ptr [rsi + r10 + 24], 9 - pinsrb xmm5, byte ptr [rsi + r9 + 24], 10 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 24], 11 - pinsrb xmm5, byte ptr [rsi + rdx + 24], 12 - pinsrb xmm5, byte ptr [rsi + r8 + 24], 13 - pinsrb xmm5, byte ptr [rsi + r13 + 24], 14 - pinsrb xmm5, byte ptr [rsi + rdi + 24], 15 - pcmpgtb xmm3, xmm14 - movdqa xmmword ptr [rsp + 336], xmm3 # 16-byte Spill - movdqa xmm3, xmm15 - pcmpgtb xmm3, xmm5 - movdqa xmmword ptr [rsp + 288], xmm3 # 16-byte Spill - movdqa xmm5, xmm15 - pcmpgtb xmm5, xmm2 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - movzx edx, byte ptr [rsi + rcx + 13] - movd xmm2, edx - pinsrb xmm7, byte ptr [rsi + r8 + 6], 13 - movdqa xmm3, xmmword ptr [rip + .LCPI10_16] # xmm3 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] - pandn xmm5, xmm3 - paddb xmm5, xmm11 - movdqa xmm13, xmm15 - pcmpgtb xmm13, xmm0 - movdqa xmm3, xmm15 - pcmpgtb xmm3, xmm4 - movzx edx, byte ptr [rsi + rcx + 14] - movd xmm4, edx - pinsrb xmm7, byte ptr [rsi + r13 + 6], 14 - movdqa xmm0, xmmword ptr [rip + .LCPI10_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pandn xmm13, xmm0 - movdqa xmm0, xmmword ptr [rip + .LCPI10_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pandn xmm3, xmm0 - por xmm3, xmm13 - movdqa xmm14, xmm15 - pcmpgtb xmm14, xmm6 - movzx edx, byte ptr [rsi + rcx + 15] - movd xmm6, edx - movdqa xmm0, xmmword ptr [rip + .LCPI10_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pandn xmm14, xmm0 - por xmm14, xmm3 - movzx edx, byte ptr [rsi + rcx + 17] - movd xmm3, edx - pinsrb xmm7, byte ptr [rsi + rdi + 6], 15 - pcmpeqd xmm0, xmm0 - psubb xmm5, xmm0 - por xmm14, xmm5 - movdqa xmm5, xmm15 - pcmpgtb xmm5, xmmword ptr [rsp + 112] # 16-byte Folded Reload - movdqa xmm13, xmm15 - movdqa xmm11, xmm15 - pcmpgtb xmm13, xmm7 - movzx edx, byte ptr [rsi + rcx + 18] - movd xmm7, edx - movdqa xmm0, xmmword ptr [rip + .LCPI10_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm5, xmm0 - movdqa xmm0, xmmword ptr [rip + .LCPI10_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm13, xmm0 - por xmm13, xmm5 - movzx edx, byte ptr [rsi + rcx + 19] - movd xmm15, edx - movdqa xmm0, xmmword ptr [rsp + 304] # 16-byte Reload - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdi + 7], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 7], 2 - mov rcx, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rcx + 7], 3 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 7], 4 - mov r15, qword ptr [rsp + 224] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r15 + 7], 5 - pinsrb xmm0, byte ptr [rsi + r14 + 7], 6 - pinsrb xmm0, byte ptr [rsi + rbx + 7], 7 - pinsrb xmm0, byte ptr [rsi + r11 + 7], 8 - pinsrb xmm0, byte ptr [rsi + r10 + 7], 9 - pinsrb xmm0, byte ptr [rsi + r9 + 7], 10 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 7], 11 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 7], 12 - pinsrb xmm0, byte ptr [rsi + r8 + 7], 13 - pinsrb xmm0, byte ptr [rsi + r13 + 7], 14 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r12 + 7], 15 - pinsrb xmm8, byte ptr [rsi + rdi + 9], 1 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r13 + 9], 2 - pinsrb xmm8, byte ptr [rsi + rcx + 9], 3 - pinsrb xmm8, byte ptr [rsi + rax + 9], 4 - pinsrb xmm8, byte ptr [rsi + r15 + 9], 5 - pinsrb xmm8, byte ptr [rsi + r14 + 9], 6 - pinsrb xmm8, byte ptr [rsi + rbx + 9], 7 - pinsrb xmm8, byte ptr [rsi + r11 + 9], 8 - pinsrb xmm8, byte ptr [rsi + r10 + 9], 9 - pinsrb xmm8, byte ptr [rsi + r9 + 9], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdi + 9], 11 - pinsrb xmm8, byte ptr [rsi + rdx + 9], 12 - pinsrb xmm8, byte ptr [rsi + r8 + 9], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rdi + 9], 14 - pinsrb xmm8, byte ptr [rsi + r12 + 9], 15 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r13 + 10], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdi + 10], 2 - pinsrb xmm10, byte ptr [rsi + rcx + 10], 3 - pinsrb xmm10, byte ptr [rsi + rax + 10], 4 - pinsrb xmm10, byte ptr [rsi + r15 + 10], 5 - pinsrb xmm10, byte ptr [rsi + r14 + 10], 6 - pinsrb xmm10, byte ptr [rsi + rbx + 10], 7 - pinsrb xmm10, byte ptr [rsi + r11 + 10], 8 - pinsrb xmm10, byte ptr [rsi + r10 + 10], 9 - pinsrb xmm10, byte ptr [rsi + r9 + 10], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdi + 10], 11 - pinsrb xmm10, byte ptr [rsi + rdx + 10], 12 - pinsrb xmm10, byte ptr [rsi + r8 + 10], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdi + 10], 14 - pinsrb xmm10, byte ptr [rsi + r12 + 10], 15 - pinsrb xmm1, byte ptr [rsi + r13 + 11], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rdi + 11], 2 - pinsrb xmm1, byte ptr [rsi + rcx + 11], 3 - pinsrb xmm1, byte ptr [rsi + rax + 11], 4 - pinsrb xmm1, byte ptr [rsi + r15 + 11], 5 - pinsrb xmm1, byte ptr [rsi + r14 + 11], 6 - pinsrb xmm1, byte ptr [rsi + rbx + 11], 7 - pinsrb xmm1, byte ptr [rsi + r11 + 11], 8 - pinsrb xmm1, byte ptr [rsi + r10 + 11], 9 - pinsrb xmm1, byte ptr [rsi + r9 + 11], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rdi + 11], 11 - pinsrb xmm1, byte ptr [rsi + rdx + 11], 12 - pinsrb xmm1, byte ptr [rsi + r8 + 11], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rdi + 11], 14 - pinsrb xmm1, byte ptr [rsi + r12 + 11], 15 - pinsrb xmm12, byte ptr [rsi + r13 + 12], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rdi + 12], 2 - pinsrb xmm12, byte ptr [rsi + rcx + 12], 3 - pinsrb xmm12, byte ptr [rsi + rax + 12], 4 - pinsrb xmm12, byte ptr [rsi + r15 + 12], 5 - pinsrb xmm12, byte ptr [rsi + r14 + 12], 6 - pinsrb xmm12, byte ptr [rsi + rbx + 12], 7 - pinsrb xmm12, byte ptr [rsi + r11 + 12], 8 - pinsrb xmm12, byte ptr [rsi + r10 + 12], 9 - pinsrb xmm12, byte ptr [rsi + r9 + 12], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rdi + 12], 11 - pinsrb xmm12, byte ptr [rsi + rdx + 12], 12 - pinsrb xmm12, byte ptr [rsi + r8 + 12], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rdi + 12], 14 - pinsrb xmm12, byte ptr [rsi + r12 + 12], 15 - pinsrb xmm2, byte ptr [rsi + r13 + 13], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdi + 13], 2 - pinsrb xmm2, byte ptr [rsi + rcx + 13], 3 - pinsrb xmm2, byte ptr [rsi + rax + 13], 4 - pinsrb xmm2, byte ptr [rsi + r15 + 13], 5 - pinsrb xmm2, byte ptr [rsi + r14 + 13], 6 - pinsrb xmm2, byte ptr [rsi + rbx + 13], 7 - pinsrb xmm2, byte ptr [rsi + r11 + 13], 8 - pinsrb xmm2, byte ptr [rsi + r10 + 13], 9 - pinsrb xmm2, byte ptr [rsi + r9 + 13], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdi + 13], 11 - pinsrb xmm2, byte ptr [rsi + rdx + 13], 12 - pinsrb xmm2, byte ptr [rsi + r8 + 13], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdi + 13], 14 - pinsrb xmm2, byte ptr [rsi + r12 + 13], 15 - pinsrb xmm4, byte ptr [rsi + r13 + 14], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 14], 2 - pinsrb xmm4, byte ptr [rsi + rcx + 14], 3 - pinsrb xmm4, byte ptr [rsi + rax + 14], 4 - pinsrb xmm4, byte ptr [rsi + r15 + 14], 5 - pinsrb xmm4, byte ptr [rsi + r14 + 14], 6 - pinsrb xmm4, byte ptr [rsi + rbx + 14], 7 - pinsrb xmm4, byte ptr [rsi + r11 + 14], 8 - pinsrb xmm4, byte ptr [rsi + r10 + 14], 9 - pinsrb xmm4, byte ptr [rsi + r9 + 14], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 14], 11 - pinsrb xmm4, byte ptr [rsi + rdx + 14], 12 - pinsrb xmm4, byte ptr [rsi + r8 + 14], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 14], 14 - pinsrb xmm4, byte ptr [rsi + r12 + 14], 15 - pinsrb xmm6, byte ptr [rsi + r13 + 15], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdi + 15], 2 - pinsrb xmm6, byte ptr [rsi + rcx + 15], 3 - pinsrb xmm6, byte ptr [rsi + rax + 15], 4 - pinsrb xmm6, byte ptr [rsi + r15 + 15], 5 - pinsrb xmm6, byte ptr [rsi + r14 + 15], 6 - pinsrb xmm6, byte ptr [rsi + rbx + 15], 7 - pinsrb xmm6, byte ptr [rsi + r11 + 15], 8 - pinsrb xmm6, byte ptr [rsi + r10 + 15], 9 - pinsrb xmm6, byte ptr [rsi + r9 + 15], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdi + 15], 11 - pinsrb xmm6, byte ptr [rsi + rdx + 15], 12 - pinsrb xmm6, byte ptr [rsi + r8 + 15], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdi + 15], 14 - pinsrb xmm6, byte ptr [rsi + r12 + 15], 15 - pinsrb xmm3, byte ptr [rsi + r13 + 17], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdi + 17], 2 - pinsrb xmm3, byte ptr [rsi + rcx + 17], 3 - pinsrb xmm3, byte ptr [rsi + rax + 17], 4 - pinsrb xmm3, byte ptr [rsi + r15 + 17], 5 - pinsrb xmm3, byte ptr [rsi + r14 + 17], 6 - pinsrb xmm3, byte ptr [rsi + rbx + 17], 7 - pinsrb xmm3, byte ptr [rsi + r11 + 17], 8 - pinsrb xmm3, byte ptr [rsi + r10 + 17], 9 - pinsrb xmm3, byte ptr [rsi + r9 + 17], 10 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdi + 17], 11 - pinsrb xmm3, byte ptr [rsi + rdx + 17], 12 - pinsrb xmm3, byte ptr [rsi + r8 + 17], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdi + 17], 14 - pinsrb xmm3, byte ptr [rsi + r12 + 17], 15 - pinsrb xmm7, byte ptr [rsi + r13 + 18], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdi + 18], 2 - pinsrb xmm7, byte ptr [rsi + rcx + 18], 3 - pinsrb xmm7, byte ptr [rsi + rax + 18], 4 - pinsrb xmm7, byte ptr [rsi + r15 + 18], 5 - pinsrb xmm7, byte ptr [rsi + r14 + 18], 6 - pinsrb xmm7, byte ptr [rsi + rbx + 18], 7 - pinsrb xmm7, byte ptr [rsi + r11 + 18], 8 - pinsrb xmm7, byte ptr [rsi + r10 + 18], 9 - pinsrb xmm7, byte ptr [rsi + r9 + 18], 10 - mov qword ptr [rsp + 272], r9 # 8-byte Spill - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + rdi + 18], 11 - pinsrb xmm7, byte ptr [rsi + rdx + 18], 12 - mov r15, rdx - pinsrb xmm7, byte ptr [rsi + r8 + 18], 13 - mov r8, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rsi + r8 + 18], 14 - pinsrb xmm7, byte ptr [rsi + r12 + 18], 15 - pinsrb xmm15, byte ptr [rsi + r13 + 19], 1 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r13 + 19], 2 - pinsrb xmm15, byte ptr [rsi + rcx + 19], 3 - pinsrb xmm15, byte ptr [rsi + rax + 19], 4 - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rcx + 19], 5 - pinsrb xmm15, byte ptr [rsi + r14 + 19], 6 - pinsrb xmm15, byte ptr [rsi + rbx + 19], 7 - pinsrb xmm15, byte ptr [rsi + r11 + 19], 8 - pinsrb xmm15, byte ptr [rsi + r10 + 19], 9 - pinsrb xmm15, byte ptr [rsi + r9 + 19], 10 - pinsrb xmm15, byte ptr [rsi + rdi + 19], 11 - movdqa xmm5, xmm11 - pcmpgtb xmm5, xmm0 - movdqa xmm0, xmmword ptr [rip + .LCPI10_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm5, xmm0 - por xmm5, xmm13 - mov rax, qword ptr [rsp + 192] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 20] - movd xmm0, edx - por xmm5, xmm14 - movdqa xmmword ptr [rsp + 112], xmm5 # 16-byte Spill - movdqa xmm13, xmm11 - pcmpgtb xmm13, xmm8 - movzx edx, byte ptr [rsi + rax + 21] - movd xmm8, edx - pinsrb xmm15, byte ptr [rsi + r15 + 19], 12 - pandn xmm13, xmmword ptr [rip + .LCPI10_16] - paddb xmm13, xmm9 - movdqa xmm5, xmm11 - pcmpgtb xmm5, xmm10 - movdqa xmm9, xmm11 - pcmpgtb xmm9, xmm1 - movzx edx, byte ptr [rsi + rax + 22] - movd xmm10, edx - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdx + 19], 13 - pandn xmm5, xmmword ptr [rip + .LCPI10_17] - pandn xmm9, xmmword ptr [rip + .LCPI10_18] - por xmm9, xmm5 - movdqa xmm1, xmm11 - pcmpgtb xmm1, xmm12 - movzx edx, byte ptr [rsi + rax + 23] - movd xmm5, edx - pandn xmm1, xmmword ptr [rip + .LCPI10_19] - por xmm1, xmm9 - movzx edx, byte ptr [rsi + rax + 25] - movd xmm9, edx - pinsrb xmm15, byte ptr [rsi + r8 + 19], 14 - psubb xmm13, xmmword ptr [rip + .LCPI10_22] - por xmm1, xmm13 - movdqa xmm14, xmm11 - pcmpgtb xmm14, xmm2 - movdqa xmm13, xmm11 - pcmpgtb xmm13, xmm4 - movzx edx, byte ptr [rsi + rax + 26] - movd xmm12, edx - pinsrb xmm15, byte ptr [rsi + r12 + 19], 15 - pandn xmm14, xmmword ptr [rip + .LCPI10_20] - pandn xmm13, xmmword ptr [rip + .LCPI10_21] - por xmm13, xmm14 - movdqa xmm4, xmm11 - movdqa xmm14, xmm11 - pcmpgtb xmm14, xmm6 - movzx edx, byte ptr [rsi + rax + 27] - movd xmm2, edx - pandn xmm14, xmmword ptr [rip + .LCPI10_6] - por xmm14, xmm13 - movzx edx, byte ptr [rsi + rax + 28] - movd xmm6, edx - por xmm14, xmm1 - pcmpgtb xmm11, xmm3 - movzx edx, byte ptr [rsi + rax + 29] - movd xmm3, edx - pandn xmm11, xmmword ptr [rip + .LCPI10_16] - paddb xmm11, xmmword ptr [rsp + 336] # 16-byte Folded Reload - movdqa xmm1, xmm4 - pcmpgtb xmm1, xmm7 - movdqa xmm13, xmm4 - movdqa xmm7, xmm4 - pcmpgtb xmm13, xmm15 - movzx edx, byte ptr [rsi + rax + 30] - movd xmm4, edx - movzx edx, byte ptr [rsi + rax + 31] - pandn xmm1, xmmword ptr [rip + .LCPI10_17] - pandn xmm13, xmmword ptr [rip + .LCPI10_18] - por xmm13, xmm1 - movd xmm15, edx - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 20], 1 - pinsrb xmm8, byte ptr [rsi + rax + 21], 1 - pinsrb xmm10, byte ptr [rsi + rax + 22], 1 - pinsrb xmm5, byte ptr [rsi + rax + 23], 1 - pinsrb xmm9, byte ptr [rsi + rax + 25], 1 - pinsrb xmm12, byte ptr [rsi + rax + 26], 1 - pinsrb xmm2, byte ptr [rsi + rax + 27], 1 - pinsrb xmm6, byte ptr [rsi + rax + 28], 1 - pinsrb xmm3, byte ptr [rsi + rax + 29], 1 - pinsrb xmm4, byte ptr [rsi + rax + 30], 1 - pinsrb xmm15, byte ptr [rsi + rax + 31], 1 - pinsrb xmm0, byte ptr [rsi + r13 + 20], 2 - pinsrb xmm8, byte ptr [rsi + r13 + 21], 2 - pinsrb xmm10, byte ptr [rsi + r13 + 22], 2 - pinsrb xmm5, byte ptr [rsi + r13 + 23], 2 - pinsrb xmm9, byte ptr [rsi + r13 + 25], 2 - pinsrb xmm12, byte ptr [rsi + r13 + 26], 2 - pinsrb xmm2, byte ptr [rsi + r13 + 27], 2 - pinsrb xmm6, byte ptr [rsi + r13 + 28], 2 - pinsrb xmm3, byte ptr [rsi + r13 + 29], 2 - pinsrb xmm4, byte ptr [rsi + r13 + 30], 2 - pinsrb xmm15, byte ptr [rsi + r13 + 31], 2 - mov rdx, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 20], 3 - pinsrb xmm8, byte ptr [rsi + rdx + 21], 3 - pinsrb xmm10, byte ptr [rsi + rdx + 22], 3 - pinsrb xmm5, byte ptr [rsi + rdx + 23], 3 - pinsrb xmm9, byte ptr [rsi + rdx + 25], 3 - pinsrb xmm12, byte ptr [rsi + rdx + 26], 3 - pinsrb xmm2, byte ptr [rsi + rdx + 27], 3 - pinsrb xmm6, byte ptr [rsi + rdx + 28], 3 - pinsrb xmm3, byte ptr [rsi + rdx + 29], 3 - pinsrb xmm4, byte ptr [rsi + rdx + 30], 3 - pinsrb xmm15, byte ptr [rsi + rdx + 31], 3 - mov rdx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 20], 4 - pinsrb xmm8, byte ptr [rsi + rdx + 21], 4 - pinsrb xmm10, byte ptr [rsi + rdx + 22], 4 - pinsrb xmm5, byte ptr [rsi + rdx + 23], 4 - pinsrb xmm9, byte ptr [rsi + rdx + 25], 4 - pinsrb xmm12, byte ptr [rsi + rdx + 26], 4 - pinsrb xmm2, byte ptr [rsi + rdx + 27], 4 - pinsrb xmm6, byte ptr [rsi + rdx + 28], 4 - pinsrb xmm3, byte ptr [rsi + rdx + 29], 4 - pinsrb xmm4, byte ptr [rsi + rdx + 30], 4 - pinsrb xmm15, byte ptr [rsi + rdx + 31], 4 - pinsrb xmm0, byte ptr [rsi + rcx + 20], 5 - pinsrb xmm8, byte ptr [rsi + rcx + 21], 5 - pinsrb xmm10, byte ptr [rsi + rcx + 22], 5 - pinsrb xmm5, byte ptr [rsi + rcx + 23], 5 - pinsrb xmm9, byte ptr [rsi + rcx + 25], 5 - pinsrb xmm12, byte ptr [rsi + rcx + 26], 5 - pinsrb xmm2, byte ptr [rsi + rcx + 27], 5 - pinsrb xmm6, byte ptr [rsi + rcx + 28], 5 - pinsrb xmm3, byte ptr [rsi + rcx + 29], 5 - pinsrb xmm4, byte ptr [rsi + rcx + 30], 5 - pinsrb xmm15, byte ptr [rsi + rcx + 31], 5 - pinsrb xmm0, byte ptr [rsi + r14 + 20], 6 - pinsrb xmm8, byte ptr [rsi + r14 + 21], 6 - pinsrb xmm10, byte ptr [rsi + r14 + 22], 6 - pinsrb xmm5, byte ptr [rsi + r14 + 23], 6 - pinsrb xmm9, byte ptr [rsi + r14 + 25], 6 - pinsrb xmm12, byte ptr [rsi + r14 + 26], 6 - pinsrb xmm2, byte ptr [rsi + r14 + 27], 6 - pinsrb xmm6, byte ptr [rsi + r14 + 28], 6 - pinsrb xmm3, byte ptr [rsi + r14 + 29], 6 - pinsrb xmm4, byte ptr [rsi + r14 + 30], 6 - pinsrb xmm15, byte ptr [rsi + r14 + 31], 6 - pinsrb xmm0, byte ptr [rsi + rbx + 20], 7 - pinsrb xmm8, byte ptr [rsi + rbx + 21], 7 - pinsrb xmm10, byte ptr [rsi + rbx + 22], 7 - pinsrb xmm5, byte ptr [rsi + rbx + 23], 7 - pinsrb xmm9, byte ptr [rsi + rbx + 25], 7 - pinsrb xmm12, byte ptr [rsi + rbx + 26], 7 - pinsrb xmm2, byte ptr [rsi + rbx + 27], 7 - pinsrb xmm6, byte ptr [rsi + rbx + 28], 7 - pinsrb xmm3, byte ptr [rsi + rbx + 29], 7 - pinsrb xmm4, byte ptr [rsi + rbx + 30], 7 - pinsrb xmm15, byte ptr [rsi + rbx + 31], 7 - pinsrb xmm0, byte ptr [rsi + r11 + 20], 8 - pinsrb xmm8, byte ptr [rsi + r11 + 21], 8 - pinsrb xmm10, byte ptr [rsi + r11 + 22], 8 - pinsrb xmm5, byte ptr [rsi + r11 + 23], 8 - pinsrb xmm9, byte ptr [rsi + r11 + 25], 8 - pinsrb xmm12, byte ptr [rsi + r11 + 26], 8 - pinsrb xmm2, byte ptr [rsi + r11 + 27], 8 - pinsrb xmm6, byte ptr [rsi + r11 + 28], 8 - pinsrb xmm3, byte ptr [rsi + r11 + 29], 8 - pinsrb xmm4, byte ptr [rsi + r11 + 30], 8 - pinsrb xmm15, byte ptr [rsi + r11 + 31], 8 - pinsrb xmm0, byte ptr [rsi + r10 + 20], 9 - pinsrb xmm8, byte ptr [rsi + r10 + 21], 9 - pinsrb xmm10, byte ptr [rsi + r10 + 22], 9 - pinsrb xmm5, byte ptr [rsi + r10 + 23], 9 - pinsrb xmm9, byte ptr [rsi + r10 + 25], 9 - pinsrb xmm12, byte ptr [rsi + r10 + 26], 9 - pinsrb xmm2, byte ptr [rsi + r10 + 27], 9 - pinsrb xmm6, byte ptr [rsi + r10 + 28], 9 - pinsrb xmm3, byte ptr [rsi + r10 + 29], 9 - pinsrb xmm4, byte ptr [rsi + r10 + 30], 9 - pinsrb xmm15, byte ptr [rsi + r10 + 31], 9 - mov r10, qword ptr [rsp + 272] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r10 + 20], 10 - pinsrb xmm8, byte ptr [rsi + r10 + 21], 10 - pinsrb xmm10, byte ptr [rsi + r10 + 22], 10 - pinsrb xmm5, byte ptr [rsi + r10 + 23], 10 - pinsrb xmm9, byte ptr [rsi + r10 + 25], 10 - pinsrb xmm12, byte ptr [rsi + r10 + 26], 10 - pinsrb xmm2, byte ptr [rsi + r10 + 27], 10 - pinsrb xmm6, byte ptr [rsi + r10 + 28], 10 - pinsrb xmm3, byte ptr [rsi + r10 + 29], 10 - pinsrb xmm4, byte ptr [rsi + r10 + 30], 10 - pinsrb xmm15, byte ptr [rsi + r10 + 31], 10 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r10 + 20], 11 - pinsrb xmm8, byte ptr [rsi + r10 + 21], 11 - pinsrb xmm10, byte ptr [rsi + r10 + 22], 11 - pinsrb xmm5, byte ptr [rsi + r10 + 23], 11 - pinsrb xmm9, byte ptr [rsi + r10 + 25], 11 - pinsrb xmm12, byte ptr [rsi + r10 + 26], 11 - pinsrb xmm2, byte ptr [rsi + r10 + 27], 11 - pinsrb xmm6, byte ptr [rsi + r10 + 28], 11 - pinsrb xmm3, byte ptr [rsi + r10 + 29], 11 - pinsrb xmm4, byte ptr [rsi + r10 + 30], 11 - pinsrb xmm15, byte ptr [rsi + r10 + 31], 11 - pinsrb xmm0, byte ptr [rsi + r15 + 20], 12 - pinsrb xmm8, byte ptr [rsi + r15 + 21], 12 - pinsrb xmm10, byte ptr [rsi + r15 + 22], 12 - pinsrb xmm5, byte ptr [rsi + r15 + 23], 12 - pinsrb xmm9, byte ptr [rsi + r15 + 25], 12 - pinsrb xmm12, byte ptr [rsi + r15 + 26], 12 - pinsrb xmm2, byte ptr [rsi + r15 + 27], 12 - pinsrb xmm6, byte ptr [rsi + r15 + 28], 12 - pinsrb xmm3, byte ptr [rsi + r15 + 29], 12 - pinsrb xmm4, byte ptr [rsi + r15 + 30], 12 - pinsrb xmm15, byte ptr [rsi + r15 + 31], 12 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 20], 13 - pinsrb xmm8, byte ptr [rsi + rax + 21], 13 - pinsrb xmm10, byte ptr [rsi + rax + 22], 13 - pinsrb xmm5, byte ptr [rsi + rax + 23], 13 - pinsrb xmm9, byte ptr [rsi + rax + 25], 13 - pinsrb xmm12, byte ptr [rsi + rax + 26], 13 - pinsrb xmm2, byte ptr [rsi + rax + 27], 13 - pinsrb xmm6, byte ptr [rsi + rax + 28], 13 - pinsrb xmm3, byte ptr [rsi + rax + 29], 13 - pinsrb xmm4, byte ptr [rsi + rax + 30], 13 - pinsrb xmm15, byte ptr [rsi + rax + 31], 13 - pinsrb xmm0, byte ptr [rsi + r8 + 20], 14 - pinsrb xmm8, byte ptr [rsi + r8 + 21], 14 - pinsrb xmm10, byte ptr [rsi + r8 + 22], 14 - pinsrb xmm5, byte ptr [rsi + r8 + 23], 14 - pinsrb xmm9, byte ptr [rsi + r8 + 25], 14 - pinsrb xmm12, byte ptr [rsi + r8 + 26], 14 - pinsrb xmm2, byte ptr [rsi + r8 + 27], 14 - pinsrb xmm6, byte ptr [rsi + r8 + 28], 14 - pinsrb xmm3, byte ptr [rsi + r8 + 29], 14 - pinsrb xmm4, byte ptr [rsi + r8 + 30], 14 - pinsrb xmm15, byte ptr [rsi + r8 + 31], 14 - pinsrb xmm0, byte ptr [rsi + r12 + 20], 15 - pinsrb xmm8, byte ptr [rsi + r12 + 21], 15 - pinsrb xmm10, byte ptr [rsi + r12 + 22], 15 - pinsrb xmm5, byte ptr [rsi + r12 + 23], 15 - pinsrb xmm9, byte ptr [rsi + r12 + 25], 15 - pinsrb xmm12, byte ptr [rsi + r12 + 26], 15 - movdqa xmm1, xmm7 - pcmpgtb xmm1, xmm0 - pinsrb xmm2, byte ptr [rsi + r12 + 27], 15 - pandn xmm1, xmmword ptr [rip + .LCPI10_19] - por xmm1, xmm13 - pcmpeqd xmm13, xmm13 - psubb xmm11, xmm13 - por xmm1, xmm11 - movdqa xmm0, xmm7 - pcmpgtb xmm0, xmm8 - movdqa xmm8, xmm7 - pcmpgtb xmm7, xmm10 - movdqa xmm10, xmmword ptr [rip + .LCPI10_20] # xmm10 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pandn xmm0, xmm10 - movdqa xmm11, xmmword ptr [rip + .LCPI10_21] # xmm11 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pandn xmm7, xmm11 - por xmm7, xmm0 - movdqa xmm0, xmm8 - pcmpgtb xmm0, xmm5 - pinsrb xmm6, byte ptr [rsi + r12 + 28], 15 - movdqa xmm5, xmmword ptr [rip + .LCPI10_6] # xmm5 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pandn xmm0, xmm5 - por xmm0, xmm7 - pinsrb xmm3, byte ptr [rsi + r12 + 29], 15 - por xmm0, xmm1 - movdqa xmm1, xmm8 - pcmpgtb xmm1, xmm9 - pandn xmm1, xmmword ptr [rip + .LCPI10_16] - paddb xmm1, xmmword ptr [rsp + 288] # 16-byte Folded Reload - movdqa xmm5, xmm8 - pcmpgtb xmm5, xmm12 - movdqa xmm7, xmm8 - pcmpgtb xmm7, xmm2 - pandn xmm5, xmmword ptr [rip + .LCPI10_17] - pandn xmm7, xmmword ptr [rip + .LCPI10_18] - por xmm7, xmm5 - movdqa xmm2, xmm8 - pcmpgtb xmm2, xmm6 - pinsrb xmm4, byte ptr [rsi + r12 + 30], 15 - pandn xmm2, xmmword ptr [rip + .LCPI10_19] - por xmm2, xmm7 - psubb xmm1, xmm13 - por xmm2, xmm1 - movdqa xmm1, xmm8 - pcmpgtb xmm1, xmm3 - movdqa xmm3, xmm8 - pcmpgtb xmm3, xmm4 - pinsrb xmm15, byte ptr [rsi + r12 + 31], 15 - mov r14, qword ptr [rsp + 352] # 8-byte Reload - pandn xmm1, xmm10 - pandn xmm3, xmm11 - por xmm3, xmm1 - movdqa xmm1, xmm8 - pcmpgtb xmm1, xmm15 - pandn xmm1, xmmword ptr [rip + .LCPI10_6] - por xmm1, xmm3 - por xmm1, xmm2 - movdqa xmm2, xmm0 - punpcklbw xmm2, xmm1 # xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] - movdqa xmm5, xmmword ptr [rsp + 112] # 16-byte Reload - movdqa xmm3, xmm5 - punpcklbw xmm3, xmm14 # xmm3 = xmm3[0],xmm14[0],xmm3[1],xmm14[1],xmm3[2],xmm14[2],xmm3[3],xmm14[3],xmm3[4],xmm14[4],xmm3[5],xmm14[5],xmm3[6],xmm14[6],xmm3[7],xmm14[7] - movdqa xmm4, xmm3 - punpcklwd xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3] - punpckhwd xmm3, xmm2 # xmm3 = xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7] - punpckhbw xmm0, xmm1 # xmm0 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15] - punpckhbw xmm5, xmm14 # xmm5 = xmm5[8],xmm14[8],xmm5[9],xmm14[9],xmm5[10],xmm14[10],xmm5[11],xmm14[11],xmm5[12],xmm14[12],xmm5[13],xmm14[13],xmm5[14],xmm14[14],xmm5[15],xmm14[15] - movdqa xmm1, xmm5 - punpcklwd xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3] - punpckhwd xmm5, xmm0 # xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7] - mov rcx, qword ptr [rsp + 256] # 8-byte Reload - movdqu xmmword ptr [r14 + 4*rcx + 48], xmm5 - movdqu xmmword ptr [r14 + 4*rcx + 32], xmm1 - movdqu xmmword ptr [r14 + 4*rcx + 16], xmm3 - movdqu xmmword ptr [r14 + 4*rcx], xmm4 - add rcx, 16 - mov r8, rcx - cmp rcx, qword ptr [rsp + 240] # 8-byte Folded Reload - jne .LBB10_86 -# %bb.87: - mov r15, qword ptr [rsp + 432] # 8-byte Reload - cmp r15, qword ptr [rsp + 240] # 8-byte Folded Reload - mov r11b, byte ptr [rsp + 8] # 1-byte Reload - mov rsi, qword ptr [rsp + 368] # 8-byte Reload - mov r10, qword ptr [rsp + 72] # 8-byte Reload - jne .LBB10_88 - jmp .LBB10_91 -.LBB10_66: - and r15, -16 - mov rax, r15 + mov rcx, rsi + .p2align 4, 0x90 +.LBB10_161: # =>This Inner Loop Header: Depth=1 + lea rsi, [rcx + 4] + cmp dword ptr [rcx], r13d + setge bl + neg bl + lea rax, [rdi + 7] + test rdi, rdi + cmovns rax, rdi + sar rax, 3 + movzx r9d, byte ptr [r12 + rax] + xor bl, r9b + lea r10d, [8*rax] + mov ecx, edi + sub ecx, r10d + mov edx, 1 + # kill: def $cl killed $cl killed $ecx + shl edx, cl + and dl, bl + xor dl, r9b + mov byte ptr [r12 + rax], dl + add rdi, 1 + mov rcx, rsi + add r11, -1 + jne .LBB10_161 +.LBB10_162: + sub r14, r8 + je .LBB10_227 +# %bb.163: + add r12, 1 +.LBB10_164: + lea rax, [r14 + 31] + test r14, r14 + cmovns rax, r14 + sar rax, 5 + cmp r14, 32 + jl .LBB10_168 +# %bb.165: + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 352], rax # 8-byte Spill + mov qword ptr [rsp + 304], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB10_166: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 8], r12 # 8-byte Spill + cmp dword ptr [rsi], r13d + setge byte ptr [rsp + 320] # 1-byte Folded Spill + cmp dword ptr [rsi + 4], r13d + setge r9b + cmp dword ptr [rsi + 8], r13d + setge r14b + cmp dword ptr [rsi + 12], r13d + setge byte ptr [rsp + 240] # 1-byte Folded Spill + cmp dword ptr [rsi + 16], r13d + setge byte ptr [rsp + 224] # 1-byte Folded Spill + cmp dword ptr [rsi + 20], r13d + setge byte ptr [rsp + 176] # 1-byte Folded Spill + cmp dword ptr [rsi + 24], r13d + setge al + cmp dword ptr [rsi + 28], r13d + setge r11b + cmp dword ptr [rsi + 32], r13d + setge byte ptr [rsp + 336] # 1-byte Folded Spill + cmp dword ptr [rsi + 36], r13d + setge cl + cmp dword ptr [rsi + 40], r13d + setge dil + cmp dword ptr [rsi + 44], r13d + setge r8b + cmp dword ptr [rsi + 48], r13d + setge r10b + cmp dword ptr [rsi + 52], r13d + setge r12b + cmp dword ptr [rsi + 56], r13d + setge byte ptr [rsp + 288] # 1-byte Folded Spill + cmp dword ptr [rsi + 60], r13d + setge dl + cmp dword ptr [rsi + 64], r13d + setge byte ptr [rsp + 160] # 1-byte Folded Spill + cmp dword ptr [rsi + 68], r13d + setge byte ptr [rsp + 256] # 1-byte Folded Spill + cmp dword ptr [rsi + 72], r13d + setge byte ptr [rsp + 272] # 1-byte Folded Spill + cmp dword ptr [rsi + 76], r13d + setge byte ptr [rsp + 208] # 1-byte Folded Spill + cmp dword ptr [rsi + 80], r13d + setge byte ptr [rsp + 192] # 1-byte Folded Spill + cmp dword ptr [rsi + 84], r13d + setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp dword ptr [rsi + 88], r13d + setge byte ptr [rsp + 144] # 1-byte Folded Spill + cmp dword ptr [rsi + 92], r13d + setge r15b + cmp dword ptr [rsi + 96], r13d + setge byte ptr [rsp + 48] # 1-byte Folded Spill + cmp dword ptr [rsi + 100], r13d + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp dword ptr [rsi + 104], r13d + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp dword ptr [rsi + 108], r13d + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp dword ptr [rsi + 112], r13d + setge byte ptr [rsp + 32] # 1-byte Folded Spill + cmp dword ptr [rsi + 116], r13d + setge byte ptr [rsp + 16] # 1-byte Folded Spill + cmp dword ptr [rsi + 120], r13d + setge byte ptr [rsp] # 1-byte Folded Spill + cmp dword ptr [rsi + 124], r13d + setge bl + add r9b, r9b + add r9b, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 6 + shl r11b, 7 + or r11b, al + shl r14b, 2 + or r14b, r9b + add cl, cl + add cl, byte ptr [rsp + 336] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload + shl al, 3 + or al, r14b + shl dil, 2 + or dil, cl + movzx ecx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl cl, 4 + or cl, al + shl r8b, 3 + or r8b, dil + movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + shl al, 5 + or al, cl + shl r10b, 4 + or r10b, r8b + shl r12b, 5 + or r12b, r10b + movzx ecx, byte ptr [rsp + 288] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or r11b, al + or dl, r12b + mov r12, qword ptr [rsp + 8] # 8-byte Reload + movzx eax, byte ptr [rsp + 256] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 160] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 272] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov byte ptr [r12], r11b + movzx ecx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 6 + shl r15b, 7 + or r15b, cl + mov byte ptr [r12 + 1], dl + or r15b, al + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 48] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp] # 1-byte Folded Reload + shl cl, 6 + shl bl, 7 + or bl, cl + or bl, al + mov byte ptr [r12 + 2], r15b + mov byte ptr [r12 + 3], bl + add rsi, 128 + add r12, 4 + add qword ptr [rsp + 304], -1 # 8-byte Folded Spill + jne .LBB10_166 +# %bb.167: + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rax, qword ptr [rsp + 352] # 8-byte Reload +.LBB10_168: shl rax, 5 - add rax, rsi - mov qword ptr [rsp + 392], rax # 8-byte Spill - mov qword ptr [rsp + 416], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] - mov qword ptr [rsp + 224], rax # 8-byte Spill - movzx eax, r11b - movd xmm1, eax - pxor xmm0, xmm0 - pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 400], xmm1 # 16-byte Spill + mov r8, r14 + sub r8, rax + jle .LBB10_227 +# %bb.169: + or rax, 1 + cmp r14, rax + jne .LBB10_174 +# %bb.170: + xor r11d, r11d + jmp .LBB10_171 +.LBB10_5: + mov rdi, rsi + jmp .LBB10_90 +.LBB10_138: + mov qword ptr [rsp + 8], r12 # 8-byte Spill + mov r11, rsi +.LBB10_149: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB10_227 +# %bb.150: + or rcx, 1 + cmp r14, rcx + jne .LBB10_154 +# %bb.151: + xor esi, esi + jmp .LBB10_152 +.LBB10_202: + mov r11, r12 + mov rcx, rsi +.LBB10_213: + shl rdi, 5 + mov r8, r14 + sub r8, rdi + jle .LBB10_227 +# %bb.214: + movd xmm0, r15d + or rdi, 1 + cmp r14, rdi + jne .LBB10_218 +# %bb.215: + xor r15d, r15d + jmp .LBB10_216 +.LBB10_59: + mov rdi, rsi + jmp .LBB10_64 +.LBB10_87: + mov rdi, rsi + sub r14, r8 + je .LBB10_227 +.LBB10_89: + add r12, 1 +.LBB10_90: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB10_91 +# %bb.94: + cmp rcx, 16 + mov byte ptr [rsp], r15b # 1-byte Spill + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 400], rcx # 8-byte Spill + jb .LBB10_95 +# %bb.96: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r12, rax + jae .LBB10_98 +# %bb.97: + lea rax, [r12 + 4*rcx] + cmp rdi, rax + jae .LBB10_98 +.LBB10_95: xor eax, eax - mov qword ptr [rsp + 352], r14 # 8-byte Spill + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov qword ptr [rsp + 112], r12 # 8-byte Spill + mov rsi, rdi +.LBB10_101: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 304], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB10_67: # =>This Inner Loop Header: Depth=1 - mov r9, rax - mov qword ptr [rsp + 336], rax # 8-byte Spill - shl r9, 5 - mov rbx, r9 - mov rdi, r9 - mov rdx, r9 - mov qword ptr [rsp + 48], r9 # 8-byte Spill - mov r14, r9 - mov r8, r9 - mov r10, r9 - mov r12, r9 - mov r11, r9 - mov r13, r9 - mov qword ptr [rsp + 208], r9 # 8-byte Spill - movzx ecx, byte ptr [rsi + r9] - movd xmm0, ecx - movzx ecx, byte ptr [rsi + r9 + 1] - movd xmm11, ecx - movzx ecx, byte ptr [rsi + r9 + 2] - movd xmm14, ecx - movzx ecx, byte ptr [rsi + r9 + 3] - movd xmm5, ecx - movzx ecx, byte ptr [rsi + r9 + 4] - movd xmm3, ecx - movzx ecx, byte ptr [rsi + r9 + 5] - movd xmm1, ecx - movzx ecx, byte ptr [rsi + r9 + 6] - movd xmm4, ecx - movzx ecx, byte ptr [rsi + r9 + 7] - movd xmm2, ecx - movdqa xmmword ptr [rsp + 320], xmm2 # 16-byte Spill - movzx ecx, byte ptr [rsi + r9 + 8] - movd xmm13, ecx - movzx ecx, byte ptr [rsi + r9 + 9] - movd xmm2, ecx - movdqa xmmword ptr [rsp + 272], xmm2 # 16-byte Spill - movzx ecx, byte ptr [rsi + r9 + 10] - movd xmm8, ecx - movzx ecx, byte ptr [rsi + r9 + 11] - movd xmm10, ecx - movzx ecx, byte ptr [rsi + r9 + 12] - movd xmm6, ecx - movzx ecx, byte ptr [rsi + r9 + 16] - movd xmm12, ecx - movzx ecx, byte ptr [rsi + r9 + 24] - movd xmm2, ecx - mov qword ptr [rsp + 144], r9 # 8-byte Spill - mov r15, r9 - or r15, 32 - mov qword ptr [rsp + 80], r15 # 8-byte Spill - or rbx, 64 - mov qword ptr [rsp + 128], rbx # 8-byte Spill - or rdi, 96 - mov qword ptr [rsp + 192], rdi # 8-byte Spill - or rdx, 128 - mov qword ptr [rsp + 112], rdx # 8-byte Spill - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - or rcx, 160 - or r14, 192 - or r8, 224 - or r10, 256 - or r12, 288 - or r11, 320 - or r13, 352 - mov qword ptr [rsp + 160], r13 # 8-byte Spill - mov r13, qword ptr [rsp + 208] # 8-byte Reload - or r13, 384 - mov qword ptr [rsp + 208], r13 # 8-byte Spill - mov rax, r9 - or rax, 416 - mov qword ptr [rsp + 96], rax # 8-byte Spill - mov rax, r9 - or rax, 448 - mov qword ptr [rsp + 16], rax # 8-byte Spill - mov rax, r9 - or rax, 480 - mov qword ptr [rsp + 32], rax # 8-byte Spill - pinsrb xmm0, byte ptr [rsi + r15], 1 - pinsrb xmm0, byte ptr [rsi + rbx], 2 - pinsrb xmm0, byte ptr [rsi + rdi], 3 - pinsrb xmm0, byte ptr [rsi + rdx], 4 - mov qword ptr [rsp + 48], rcx # 8-byte Spill - pinsrb xmm0, byte ptr [rsi + rcx], 5 - pinsrb xmm0, byte ptr [rsi + r14], 6 - pinsrb xmm0, byte ptr [rsi + r8], 7 - mov r9, r10 - pinsrb xmm0, byte ptr [rsi + r10], 8 - pinsrb xmm0, byte ptr [rsi + r12], 9 - pinsrb xmm0, byte ptr [rsi + r11], 10 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r15], 11 - pinsrb xmm0, byte ptr [rsi + r13], 12 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdi], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rcx], 14 - pinsrb xmm0, byte ptr [rsi + rax], 15 - movdqa xmm9, xmm0 - movdqa xmm7, xmmword ptr [rsp + 400] # 16-byte Reload - pmaxub xmm9, xmm7 - movdqa xmm15, xmm7 - pcmpeqb xmm9, xmm0 - movdqa xmm0, xmm9 - mov r10, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r10 + 1], 1 - pinsrb xmm11, byte ptr [rsi + rbx + 1], 2 - mov r13, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r13 + 1], 3 - pinsrb xmm11, byte ptr [rsi + rdx + 1], 4 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rcx + 1], 5 - pinsrb xmm11, byte ptr [rsi + r14 + 1], 6 - pinsrb xmm11, byte ptr [rsi + r8 + 1], 7 - pinsrb xmm11, byte ptr [rsi + r9 + 1], 8 - mov rax, r12 - mov qword ptr [rsp + 304], r12 # 8-byte Spill - pinsrb xmm11, byte ptr [rsi + r12 + 1], 9 - pinsrb xmm11, byte ptr [rsi + r11 + 1], 10 - pinsrb xmm11, byte ptr [rsi + r15 + 1], 11 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r12 + 1], 12 - pinsrb xmm11, byte ptr [rsi + rdi + 1], 13 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r12 + 1], 14 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdi + 1], 15 - pinsrb xmm13, byte ptr [rsi + r10 + 8], 1 - pinsrb xmm13, byte ptr [rsi + rbx + 8], 2 - pinsrb xmm13, byte ptr [rsi + r13 + 8], 3 - pinsrb xmm13, byte ptr [rsi + rdx + 8], 4 - pinsrb xmm13, byte ptr [rsi + rcx + 8], 5 - pinsrb xmm13, byte ptr [rsi + r14 + 8], 6 - pinsrb xmm13, byte ptr [rsi + r8 + 8], 7 - pinsrb xmm13, byte ptr [rsi + r9 + 8], 8 - pinsrb xmm13, byte ptr [rsi + rax + 8], 9 - pinsrb xmm13, byte ptr [rsi + r11 + 8], 10 - pinsrb xmm13, byte ptr [rsi + r15 + 8], 11 - mov rax, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rax + 8], 12 - mov rdi, rax - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rax + 8], 13 - pinsrb xmm13, byte ptr [rsi + r12 + 8], 14 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm13, byte ptr [rsi + rax + 8], 15 - movdqa xmm9, xmm13 - pmaxub xmm9, xmm7 - pcmpeqb xmm9, xmm13 - pinsrb xmm12, byte ptr [rsi + r10 + 16], 1 - pinsrb xmm12, byte ptr [rsi + rbx + 16], 2 - pinsrb xmm12, byte ptr [rsi + r13 + 16], 3 - pinsrb xmm12, byte ptr [rsi + rdx + 16], 4 - pinsrb xmm12, byte ptr [rsi + rcx + 16], 5 - pinsrb xmm12, byte ptr [rsi + r14 + 16], 6 - pinsrb xmm12, byte ptr [rsi + r8 + 16], 7 - mov rdx, r8 - mov qword ptr [rsp + 432], r8 # 8-byte Spill - pinsrb xmm12, byte ptr [rsi + r9 + 16], 8 - mov r12, qword ptr [rsp + 304] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r12 + 16], 9 - pinsrb xmm12, byte ptr [rsi + r11 + 16], 10 - mov qword ptr [rsp + 176], r11 # 8-byte Spill - pinsrb xmm12, byte ptr [rsi + r15 + 16], 11 - mov rcx, rdi - pinsrb xmm12, byte ptr [rsi + rdi + 16], 12 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + rdi + 16], 13 - mov r8, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rsi + r8 + 16], 14 - pinsrb xmm12, byte ptr [rsi + rax + 16], 15 - movdqa xmm7, xmm12 - pmaxub xmm7, xmm15 - pcmpeqb xmm7, xmm12 - movdqa xmmword ptr [rsp + 368], xmm7 # 16-byte Spill - pinsrb xmm2, byte ptr [rsi + r10 + 24], 1 - pinsrb xmm2, byte ptr [rsi + rbx + 24], 2 - pinsrb xmm2, byte ptr [rsi + r13 + 24], 3 - mov rbx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rbx + 24], 4 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r10 + 24], 5 - pinsrb xmm2, byte ptr [rsi + r14 + 24], 6 - pinsrb xmm2, byte ptr [rsi + rdx + 24], 7 - pinsrb xmm2, byte ptr [rsi + r9 + 24], 8 - pinsrb xmm2, byte ptr [rsi + r12 + 24], 9 - pinsrb xmm2, byte ptr [rsi + r11 + 24], 10 - pinsrb xmm2, byte ptr [rsi + r15 + 24], 11 - mov r12, r15 - pinsrb xmm2, byte ptr [rsi + rcx + 24], 12 - pinsrb xmm2, byte ptr [rsi + rdi + 24], 13 - pinsrb xmm2, byte ptr [rsi + r8 + 24], 14 - mov r13, r8 - pinsrb xmm2, byte ptr [rsi + rax + 24], 15 - movdqa xmm7, xmm2 - pmaxub xmm7, xmm15 - pcmpeqb xmm7, xmm2 - movdqa xmmword ptr [rsp + 240], xmm7 # 16-byte Spill - movdqa xmm12, xmm11 - movdqa xmm13, xmm15 - pmaxub xmm12, xmm15 - pcmpeqb xmm12, xmm11 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 13] - movd xmm15, edx - mov r8, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r8 + 2], 1 - mov r15, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r15 + 2], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdi + 2], 3 - mov r11, rbx - pinsrb xmm14, byte ptr [rsi + rbx + 2], 4 - pinsrb xmm14, byte ptr [rsi + r10 + 2], 5 - pinsrb xmm14, byte ptr [rsi + r14 + 2], 6 - mov rbx, qword ptr [rsp + 432] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rbx + 2], 7 - mov rdx, r9 - mov qword ptr [rsp + 256], r9 # 8-byte Spill - pinsrb xmm14, byte ptr [rsi + r9 + 2], 8 - mov r9, qword ptr [rsp + 304] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r9 + 2], 9 - mov rax, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 2], 10 - pinsrb xmm14, byte ptr [rsi + r12 + 2], 11 - mov r12, rcx - pinsrb xmm14, byte ptr [rsi + rcx + 2], 12 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rcx + 2], 13 - pinsrb xmm14, byte ptr [rsi + r13 + 2], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r13 + 2], 15 - pinsrb xmm5, byte ptr [rsi + r8 + 3], 1 - pinsrb xmm5, byte ptr [rsi + r15 + 3], 2 - pinsrb xmm5, byte ptr [rsi + rdi + 3], 3 - mov r8, rdi - pinsrb xmm5, byte ptr [rsi + r11 + 3], 4 - pinsrb xmm5, byte ptr [rsi + r10 + 3], 5 - pinsrb xmm5, byte ptr [rsi + r14 + 3], 6 - pinsrb xmm5, byte ptr [rsi + rbx + 3], 7 - pinsrb xmm5, byte ptr [rsi + rdx + 3], 8 - pinsrb xmm5, byte ptr [rsi + r9 + 3], 9 - pinsrb xmm5, byte ptr [rsi + rax + 3], 10 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + r15 + 3], 11 - pinsrb xmm5, byte ptr [rsi + r12 + 3], 12 - pinsrb xmm5, byte ptr [rsi + rcx + 3], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 3], 14 - pinsrb xmm5, byte ptr [rsi + r13 + 3], 15 - movdqa xmm2, xmmword ptr [rip + .LCPI10_16] # xmm2 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] - pand xmm12, xmm2 - psubb xmm12, xmm0 - movdqa xmm11, xmm14 - pmaxub xmm11, xmm13 - pcmpeqb xmm11, xmm14 - movdqa xmm2, xmm5 - pmaxub xmm2, xmm13 - pcmpeqb xmm2, xmm5 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 14] - movd xmm14, edx - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdi + 4], 1 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rax + 4], 2 - pinsrb xmm3, byte ptr [rsi + r8 + 4], 3 - pinsrb xmm3, byte ptr [rsi + r11 + 4], 4 - mov rcx, r10 - pinsrb xmm3, byte ptr [rsi + r10 + 4], 5 - pinsrb xmm3, byte ptr [rsi + r14 + 4], 6 - pinsrb xmm3, byte ptr [rsi + rbx + 4], 7 - mov r10, qword ptr [rsp + 256] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r10 + 4], 8 - pinsrb xmm3, byte ptr [rsi + r9 + 4], 9 - mov r8, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r8 + 4], 10 - pinsrb xmm3, byte ptr [rsi + r15 + 4], 11 - pinsrb xmm3, byte ptr [rsi + r12 + 4], 12 - mov r11, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r11 + 4], 13 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 4], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r13 + 4], 15 - pinsrb xmm1, byte ptr [rsi + rdi + 5], 1 - pinsrb xmm1, byte ptr [rsi + rax + 5], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rdi + 5], 3 - mov rdi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + rdi + 5], 4 - pinsrb xmm1, byte ptr [rsi + rcx + 5], 5 - pinsrb xmm1, byte ptr [rsi + r14 + 5], 6 - pinsrb xmm1, byte ptr [rsi + rbx + 5], 7 - pinsrb xmm1, byte ptr [rsi + r10 + 5], 8 - mov rcx, r10 - pinsrb xmm1, byte ptr [rsi + r9 + 5], 9 - pinsrb xmm1, byte ptr [rsi + r8 + 5], 10 - pinsrb xmm1, byte ptr [rsi + r15 + 5], 11 - mov r10, r15 - pinsrb xmm1, byte ptr [rsi + r12 + 5], 12 - pinsrb xmm1, byte ptr [rsi + r11 + 5], 13 - pinsrb xmm1, byte ptr [rsi + rdx + 5], 14 - movdqa xmm5, xmmword ptr [rip + .LCPI10_17] # xmm5 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] - pand xmm11, xmm5 - movdqa xmm5, xmmword ptr [rip + .LCPI10_18] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] - pand xmm2, xmm5 - por xmm2, xmm11 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + rdi + 15] - movd xmm11, edx - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm1, byte ptr [rsi + r13 + 5], 15 - por xmm2, xmm12 - movdqa xmm12, xmm3 - pmaxub xmm12, xmm13 - pcmpeqb xmm12, xmm3 - movdqa xmm5, xmm1 - pmaxub xmm5, xmm13 - pcmpeqb xmm5, xmm1 - movzx edx, byte ptr [rsi + rdi + 17] - movd xmm0, edx - mov r8, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r8 + 6], 1 - pinsrb xmm4, byte ptr [rsi + rax + 6], 2 - mov rdi, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdi + 6], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rax + 6], 4 - mov r11, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r11 + 6], 5 - pinsrb xmm4, byte ptr [rsi + r14 + 6], 6 - pinsrb xmm4, byte ptr [rsi + rbx + 6], 7 - pinsrb xmm4, byte ptr [rsi + rcx + 6], 8 - pinsrb xmm4, byte ptr [rsi + r9 + 6], 9 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r15 + 6], 10 - pinsrb xmm4, byte ptr [rsi + r10 + 6], 11 - pinsrb xmm4, byte ptr [rsi + r12 + 6], 12 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 6], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 6], 14 - pinsrb xmm4, byte ptr [rsi + r13 + 6], 15 - movdqa xmm3, xmmword ptr [rsp + 320] # 16-byte Reload - pinsrb xmm3, byte ptr [rsi + r8 + 7], 1 - mov r8, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r8 + 7], 2 - pinsrb xmm3, byte ptr [rsi + rdi + 7], 3 - pinsrb xmm3, byte ptr [rsi + rax + 7], 4 - mov rdi, r11 - pinsrb xmm3, byte ptr [rsi + r11 + 7], 5 - pinsrb xmm3, byte ptr [rsi + r14 + 7], 6 - mov qword ptr [rsp + 288], r14 # 8-byte Spill - pinsrb xmm3, byte ptr [rsi + rbx + 7], 7 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r11 + 7], 8 - pinsrb xmm3, byte ptr [rsi + r9 + 7], 9 - pinsrb xmm3, byte ptr [rsi + r15 + 7], 10 - pinsrb xmm3, byte ptr [rsi + r10 + 7], 11 - pinsrb xmm3, byte ptr [rsi + r12 + 7], 12 - pinsrb xmm3, byte ptr [rsi + rdx + 7], 13 - pinsrb xmm3, byte ptr [rsi + rcx + 7], 14 - pinsrb xmm3, byte ptr [rsi + r13 + 7], 15 - movdqa xmm1, xmmword ptr [rip + .LCPI10_19] # xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm12, xmm1 - movdqa xmm1, xmmword ptr [rip + .LCPI10_20] # xmm1 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm5, xmm1 - por xmm5, xmm12 - movdqa xmm1, xmm4 - pmaxub xmm1, xmm13 - pcmpeqb xmm1, xmm4 - mov r10, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + r10 + 18] - movd xmm4, edx - movdqa xmm7, xmmword ptr [rip + .LCPI10_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm1, xmm7 - por xmm1, xmm5 - movzx edx, byte ptr [rsi + r10 + 19] - movd xmm5, edx - por xmm1, xmm2 - movdqa xmm2, xmm3 - pmaxub xmm2, xmm13 - pcmpeqb xmm2, xmm3 - movdqa xmm12, xmm2 - movzx edx, byte ptr [rsi + r10 + 20] - movd xmm2, edx - movdqa xmm3, xmmword ptr [rsp + 272] # 16-byte Reload - mov rdi, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdi + 9], 1 - mov rax, r8 - pinsrb xmm3, byte ptr [rsi + r8 + 9], 2 - mov rcx, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 9], 3 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rcx + 9], 4 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r8 + 9], 5 - pinsrb xmm3, byte ptr [rsi + r14 + 9], 6 - pinsrb xmm3, byte ptr [rsi + rbx + 9], 7 - pinsrb xmm3, byte ptr [rsi + r11 + 9], 8 - pinsrb xmm3, byte ptr [rsi + r9 + 9], 9 - pinsrb xmm3, byte ptr [rsi + r15 + 9], 10 - mov r12, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r12 + 9], 11 - mov rdx, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 9], 12 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + r13 + 9], 13 - mov rdx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 9], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm3, byte ptr [rsi + rdx + 9], 15 - movdqa xmm7, xmmword ptr [rip + .LCPI10_6] # xmm7 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm12, xmm7 - por xmm12, xmm1 - movdqa xmmword ptr [rsp + 272], xmm12 # 16-byte Spill - movdqa xmm7, xmm3 - pmaxub xmm7, xmm13 - pcmpeqb xmm7, xmm3 - movzx edx, byte ptr [rsi + r10 + 21] - movd xmm3, edx - pinsrb xmm8, byte ptr [rsi + rdi + 10], 1 - pinsrb xmm8, byte ptr [rsi + rax + 10], 2 - mov r14, rax - mov r10, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r10 + 10], 3 - pinsrb xmm8, byte ptr [rsi + rcx + 10], 4 - pinsrb xmm8, byte ptr [rsi + r8 + 10], 5 - mov rax, qword ptr [rsp + 288] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rax + 10], 6 - pinsrb xmm8, byte ptr [rsi + rbx + 10], 7 - pinsrb xmm8, byte ptr [rsi + r11 + 10], 8 - pinsrb xmm8, byte ptr [rsi + r9 + 10], 9 - mov rax, r15 - pinsrb xmm8, byte ptr [rsi + r15 + 10], 10 - mov rdx, r12 - pinsrb xmm8, byte ptr [rsi + r12 + 10], 11 - mov r12, qword ptr [rsp + 208] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r12 + 10], 12 - mov r15, r13 - pinsrb xmm8, byte ptr [rsi + r13 + 10], 13 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + rcx + 10], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm8, byte ptr [rsi + r13 + 10], 15 - pinsrb xmm10, byte ptr [rsi + rdi + 11], 1 - pinsrb xmm10, byte ptr [rsi + r14 + 11], 2 - pinsrb xmm10, byte ptr [rsi + r10 + 11], 3 +.LBB10_102: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r15b + setge byte ptr [rsp + 320] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r15b + setge sil + cmp byte ptr [rcx + 2], r15b + setge r11b + cmp byte ptr [rcx + 3], r15b + setge r15b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 4], al + setge byte ptr [rsp + 272] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 5], al + setge byte ptr [rsp + 128] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 6], al + setge r13b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 7], al + setge r8b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 8], al + setge byte ptr [rsp + 240] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 9], al + setge dl + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 10], al + setge dil + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 11], al + setge r9b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 12], al + setge r14b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 13], al + setge r12b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 14], al + setge byte ptr [rsp + 336] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 15], al + setge al + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 16], bl + setge byte ptr [rsp + 288] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 17], bl + setge byte ptr [rsp + 256] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 18], bl + setge byte ptr [rsp + 224] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 19], bl + setge byte ptr [rsp + 208] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 20], bl + setge byte ptr [rsp + 160] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 21], bl + setge byte ptr [rsp + 176] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 22], bl + setge byte ptr [rsp + 192] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 23], bl + setge r10b + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 24], bl + setge byte ptr [rsp + 144] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 25], bl + setge byte ptr [rsp + 96] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 26], bl + setge byte ptr [rsp + 80] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 27], bl + setge byte ptr [rsp + 48] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 28], bl + setge byte ptr [rsp + 32] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 29], bl + setge byte ptr [rsp + 16] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 30], bl + setge byte ptr [rsp + 8] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 31], bl + setge bl + add sil, sil + add sil, byte ptr [rsp + 320] # 1-byte Folded Reload + shl r13b, 6 + shl r8b, 7 + or r8b, r13b + shl r11b, 2 + or r11b, sil + add dl, dl + add dl, byte ptr [rsp + 240] # 1-byte Folded Reload + shl r15b, 3 + or r15b, r11b + shl dil, 2 + or dil, dl + movzx edx, byte ptr [rsp + 272] # 1-byte Folded Reload + shl dl, 4 + or dl, r15b + mov esi, edx + movzx r15d, byte ptr [rsp] # 1-byte Folded Reload + shl r9b, 3 + or r9b, dil + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + shl r14b, 4 + or r14b, r9b + shl r12b, 5 + or r12b, r14b + movzx esi, byte ptr [rsp + 336] # 1-byte Folded Reload + shl sil, 6 + shl al, 7 + or al, sil + or r8b, dl + or al, r12b + movzx edx, byte ptr [rsp + 256] # 1-byte Folded Reload + add dl, dl + add dl, byte ptr [rsp + 288] # 1-byte Folded Reload + mov esi, edx + movzx edx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl dl, 2 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 176] # 1-byte Folded Reload + shl dl, 5 + or dl, sil mov rdi, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + rdi + 11], 4 - pinsrb xmm10, byte ptr [rsi + r8 + 11], 5 - mov r14, qword ptr [rsp + 288] # 8-byte Reload - pinsrb xmm10, byte ptr [rsi + r14 + 11], 6 - pinsrb xmm10, byte ptr [rsi + rbx + 11], 7 - pinsrb xmm10, byte ptr [rsi + r11 + 11], 8 - pinsrb xmm10, byte ptr [rsi + r9 + 11], 9 - pinsrb xmm10, byte ptr [rsi + rax + 11], 10 - pinsrb xmm10, byte ptr [rsi + rdx + 11], 11 - pinsrb xmm10, byte ptr [rsi + r12 + 11], 12 - pinsrb xmm10, byte ptr [rsi + r15 + 11], 13 - pinsrb xmm10, byte ptr [rsi + rcx + 11], 14 - pinsrb xmm10, byte ptr [rsi + r13 + 11], 15 - pand xmm7, xmmword ptr [rip + .LCPI10_16] - psubb xmm7, xmm9 - movdqa xmm1, xmm8 - pmaxub xmm1, xmm13 - pcmpeqb xmm1, xmm8 - movdqa xmm9, xmm10 - pmaxub xmm9, xmm13 - pcmpeqb xmm9, xmm10 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 22] - movd xmm10, edx - mov r8, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r8 + 12], 1 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rax + 12], 2 - pinsrb xmm6, byte ptr [rsi + r10 + 12], 3 - mov r15, r10 - mov rcx, rdi - pinsrb xmm6, byte ptr [rsi + rdi + 12], 4 - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdi + 12], 5 - pinsrb xmm6, byte ptr [rsi + r14 + 12], 6 - pinsrb xmm6, byte ptr [rsi + rbx + 12], 7 - pinsrb xmm6, byte ptr [rsi + r11 + 12], 8 - pinsrb xmm6, byte ptr [rsi + r9 + 12], 9 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 12], 10 - mov r11, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r11 + 12], 11 - pinsrb xmm6, byte ptr [rsi + r12 + 12], 12 - mov rdx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + rdx + 12], 13 - mov r10, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r10 + 12], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rsi + r13 + 12], 15 - pinsrb xmm15, byte ptr [rsi + r8 + 13], 1 - pinsrb xmm15, byte ptr [rsi + rax + 13], 2 - pinsrb xmm15, byte ptr [rsi + r15 + 13], 3 - pinsrb xmm15, byte ptr [rsi + rcx + 13], 4 - pinsrb xmm15, byte ptr [rsi + rdi + 13], 5 - mov r8, rdi - pinsrb xmm15, byte ptr [rsi + r14 + 13], 6 - pinsrb xmm15, byte ptr [rsi + rbx + 13], 7 - mov rdi, qword ptr [rsp + 256] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + rdi + 13], 8 - pinsrb xmm15, byte ptr [rsi + r9 + 13], 9 - mov r15, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r15 + 13], 10 - pinsrb xmm15, byte ptr [rsi + r11 + 13], 11 - pinsrb xmm15, byte ptr [rsi + r12 + 13], 12 - pinsrb xmm15, byte ptr [rsi + rdx + 13], 13 - mov r11, rdx - pinsrb xmm15, byte ptr [rsi + r10 + 13], 14 - pand xmm1, xmmword ptr [rip + .LCPI10_17] - pand xmm9, xmmword ptr [rip + .LCPI10_18] - por xmm9, xmm1 - mov rax, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + rax + 23] - movd xmm8, edx - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm15, byte ptr [rsi + r13 + 13], 15 - por xmm9, xmm7 - movdqa xmm1, xmm6 - pmaxub xmm1, xmm13 - pcmpeqb xmm1, xmm6 - movdqa xmm7, xmm15 - pmaxub xmm7, xmm13 - pcmpeqb xmm7, xmm15 - movzx edx, byte ptr [rsi + rax + 25] - movd xmm15, edx - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rax + 14], 1 - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rcx + 14], 2 - mov r10, qword ptr [rsp + 192] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + r10 + 14], 3 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdx + 14], 4 - pinsrb xmm14, byte ptr [rsi + r8 + 14], 5 + mov byte ptr [rdi], r8b + movzx esi, byte ptr [rsp + 192] # 1-byte Folded Reload + shl sil, 6 + shl r10b, 7 + or r10b, sil + mov byte ptr [rdi + 1], al + or r10b, dl + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 144] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r10b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + mov qword ptr [rsp + 112], rdi # 8-byte Spill + add qword ptr [rsp + 304], -1 # 8-byte Folded Spill + jne .LBB10_102 +# %bb.103: + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rcx, qword ptr [rsp + 400] # 8-byte Reload + jmp .LBB10_104 +.LBB10_91: + mov qword ptr [rsp + 112], r12 # 8-byte Spill + mov rsi, rdi +.LBB10_104: + shl rcx, 5 mov r8, r14 - pinsrb xmm14, byte ptr [rsi + r14 + 14], 6 - pinsrb xmm14, byte ptr [rsi + rbx + 14], 7 - pinsrb xmm14, byte ptr [rsi + rdi + 14], 8 - mov r14, rdi - pinsrb xmm14, byte ptr [rsi + r9 + 14], 9 - pinsrb xmm14, byte ptr [rsi + r15 + 14], 10 - mov rdi, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdi + 14], 11 - pinsrb xmm14, byte ptr [rsi + r12 + 14], 12 - pinsrb xmm14, byte ptr [rsi + r11 + 14], 13 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rsi + rdi + 14], 14 - pinsrb xmm14, byte ptr [rsi + r13 + 14], 15 - pinsrb xmm11, byte ptr [rsi + rax + 15], 1 - pinsrb xmm11, byte ptr [rsi + rcx + 15], 2 - pinsrb xmm11, byte ptr [rsi + r10 + 15], 3 - pinsrb xmm11, byte ptr [rsi + rdx + 15], 4 - mov rcx, rdx - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + rdx + 15], 5 - pinsrb xmm11, byte ptr [rsi + r8 + 15], 6 - pinsrb xmm11, byte ptr [rsi + rbx + 15], 7 - pinsrb xmm11, byte ptr [rsi + r14 + 15], 8 - pinsrb xmm11, byte ptr [rsi + r9 + 15], 9 - pinsrb xmm11, byte ptr [rsi + r15 + 15], 10 - mov r8, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm11, byte ptr [rsi + r8 + 15], 11 - pinsrb xmm11, byte ptr [rsi + r12 + 15], 12 - pinsrb xmm11, byte ptr [rsi + r11 + 15], 13 - pinsrb xmm11, byte ptr [rsi + rdi + 15], 14 - pinsrb xmm11, byte ptr [rsi + r13 + 15], 15 - pand xmm1, xmmword ptr [rip + .LCPI10_19] - pand xmm7, xmmword ptr [rip + .LCPI10_20] - por xmm7, xmm1 - movdqa xmm1, xmm14 - pmaxub xmm1, xmm13 - pcmpeqb xmm1, xmm14 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + rdi + 26] - movd xmm6, edx - pand xmm1, xmmword ptr [rip + .LCPI10_21] - por xmm1, xmm7 - movzx edx, byte ptr [rsi + rdi + 27] - movd xmm7, edx - por xmm1, xmm9 - movdqa xmm14, xmm11 - pmaxub xmm14, xmm13 - pcmpeqb xmm14, xmm11 - movzx edx, byte ptr [rsi + rdi + 28] - movd xmm9, edx - pinsrb xmm0, byte ptr [rsi + rax + 17], 1 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rax + 17], 2 - pinsrb xmm0, byte ptr [rsi + r10 + 17], 3 - pinsrb xmm0, byte ptr [rsi + rcx + 17], 4 - mov rdx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 5 - mov r9, qword ptr [rsp + 288] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r9 + 17], 6 - pinsrb xmm0, byte ptr [rsi + rbx + 17], 7 - mov r11, qword ptr [rsp + 256] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r11 + 17], 8 - mov r15, qword ptr [rsp + 304] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r15 + 17], 9 - mov rdx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 10 - pinsrb xmm0, byte ptr [rsi + r8 + 17], 11 - pinsrb xmm0, byte ptr [rsi + r12 + 17], 12 - mov r13, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r13 + 17], 13 - mov r14, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + r14 + 17], 14 - mov rdx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rsi + rdx + 17], 15 - pand xmm14, xmmword ptr [rip + .LCPI10_6] - por xmm14, xmm1 - movdqa xmm1, xmm0 - movdqa xmm12, xmm13 - pmaxub xmm1, xmm13 - pcmpeqb xmm1, xmm0 - movzx edx, byte ptr [rsi + rdi + 29] - movd xmm0, edx - mov rdx, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rdx + 18], 1 - pinsrb xmm4, byte ptr [rsi + rax + 18], 2 - pinsrb xmm4, byte ptr [rsi + r10 + 18], 3 - pinsrb xmm4, byte ptr [rsi + rcx + 18], 4 - mov rcx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + rcx + 18], 5 - mov rdi, r9 - pinsrb xmm4, byte ptr [rsi + r9 + 18], 6 - pinsrb xmm4, byte ptr [rsi + rbx + 18], 7 - mov r8, r11 - pinsrb xmm4, byte ptr [rsi + r11 + 18], 8 - mov r9, r15 - pinsrb xmm4, byte ptr [rsi + r15 + 18], 9 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r11 + 18], 10 - mov r15, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r15 + 18], 11 - pinsrb xmm4, byte ptr [rsi + r12 + 18], 12 - mov rdx, r13 - pinsrb xmm4, byte ptr [rsi + r13 + 18], 13 - pinsrb xmm4, byte ptr [rsi + r14 + 18], 14 - mov r13, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r13 + 18], 15 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 19], 1 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 19], 2 - pinsrb xmm5, byte ptr [rsi + r10 + 19], 3 - mov rax, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 19], 4 - pinsrb xmm5, byte ptr [rsi + rcx + 19], 5 - pinsrb xmm5, byte ptr [rsi + rdi + 19], 6 - pinsrb xmm5, byte ptr [rsi + rbx + 19], 7 - pinsrb xmm5, byte ptr [rsi + r8 + 19], 8 - mov r14, r8 - pinsrb xmm5, byte ptr [rsi + r9 + 19], 9 - pinsrb xmm5, byte ptr [rsi + r11 + 19], 10 - pinsrb xmm5, byte ptr [rsi + r15 + 19], 11 - pinsrb xmm5, byte ptr [rsi + r12 + 19], 12 - pinsrb xmm5, byte ptr [rsi + rdx + 19], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rsi + rax + 19], 14 - pinsrb xmm5, byte ptr [rsi + r13 + 19], 15 - pand xmm1, xmmword ptr [rip + .LCPI10_16] - psubb xmm1, xmmword ptr [rsp + 368] # 16-byte Folded Reload - movdqa xmm13, xmm4 - pmaxub xmm13, xmm12 - pcmpeqb xmm13, xmm4 - movdqa xmm11, xmm5 - pmaxub xmm11, xmm12 - pcmpeqb xmm11, xmm5 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - movzx edx, byte ptr [rsi + r8 + 30] - movd xmm4, edx - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 20], 1 - pinsrb xmm3, byte ptr [rsi + rax + 21], 1 - pinsrb xmm10, byte ptr [rsi + rax + 22], 1 - pinsrb xmm8, byte ptr [rsi + rax + 23], 1 - pinsrb xmm15, byte ptr [rsi + rax + 25], 1 - pinsrb xmm6, byte ptr [rsi + rax + 26], 1 - pinsrb xmm7, byte ptr [rsi + rax + 27], 1 - pinsrb xmm9, byte ptr [rsi + rax + 28], 1 - pinsrb xmm0, byte ptr [rsi + rax + 29], 1 - movzx edx, byte ptr [rsi + r8 + 31] - pinsrb xmm4, byte ptr [rsi + rax + 30], 1 - movd xmm5, edx - pinsrb xmm5, byte ptr [rsi + rax + 31], 1 - mov rax, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 20], 2 - pinsrb xmm3, byte ptr [rsi + rax + 21], 2 - pinsrb xmm10, byte ptr [rsi + rax + 22], 2 - pinsrb xmm8, byte ptr [rsi + rax + 23], 2 - pinsrb xmm15, byte ptr [rsi + rax + 25], 2 - pinsrb xmm6, byte ptr [rsi + rax + 26], 2 - pinsrb xmm7, byte ptr [rsi + rax + 27], 2 - pinsrb xmm9, byte ptr [rsi + rax + 28], 2 - pinsrb xmm0, byte ptr [rsi + rax + 29], 2 - pinsrb xmm4, byte ptr [rsi + rax + 30], 2 - pinsrb xmm5, byte ptr [rsi + rax + 31], 2 - pinsrb xmm2, byte ptr [rsi + r10 + 20], 3 - mov rdx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rdx + 20], 4 - pinsrb xmm2, byte ptr [rsi + rcx + 20], 5 - pinsrb xmm2, byte ptr [rsi + rdi + 20], 6 - pinsrb xmm2, byte ptr [rsi + rbx + 20], 7 - pinsrb xmm2, byte ptr [rsi + r14 + 20], 8 - pinsrb xmm2, byte ptr [rsi + r9 + 20], 9 - pinsrb xmm2, byte ptr [rsi + r11 + 20], 10 - pinsrb xmm2, byte ptr [rsi + r15 + 20], 11 - pinsrb xmm2, byte ptr [rsi + r12 + 20], 12 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + r8 + 20], 13 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm2, byte ptr [rsi + rax + 20], 14 - pinsrb xmm2, byte ptr [rsi + r13 + 20], 15 - pinsrb xmm3, byte ptr [rsi + r10 + 21], 3 - pinsrb xmm3, byte ptr [rsi + rdx + 21], 4 - pinsrb xmm3, byte ptr [rsi + rcx + 21], 5 - pinsrb xmm3, byte ptr [rsi + rdi + 21], 6 - pinsrb xmm3, byte ptr [rsi + rbx + 21], 7 - pinsrb xmm3, byte ptr [rsi + r14 + 21], 8 - pinsrb xmm3, byte ptr [rsi + r9 + 21], 9 - pinsrb xmm3, byte ptr [rsi + r11 + 21], 10 - pinsrb xmm3, byte ptr [rsi + r15 + 21], 11 - pinsrb xmm3, byte ptr [rsi + r12 + 21], 12 - pinsrb xmm3, byte ptr [rsi + r8 + 21], 13 - pinsrb xmm3, byte ptr [rsi + rax + 21], 14 - pand xmm13, xmmword ptr [rip + .LCPI10_17] - pand xmm11, xmmword ptr [rip + .LCPI10_18] - por xmm11, xmm13 - pinsrb xmm3, byte ptr [rsi + r13 + 21], 15 - por xmm11, xmm1 - movdqa xmm1, xmm2 - pmaxub xmm1, xmm12 - pcmpeqb xmm1, xmm2 - movdqa xmm2, xmm3 - pmaxub xmm2, xmm12 - pcmpeqb xmm2, xmm3 - pinsrb xmm10, byte ptr [rsi + r10 + 22], 3 - pinsrb xmm10, byte ptr [rsi + rdx + 22], 4 - pinsrb xmm10, byte ptr [rsi + rcx + 22], 5 - pinsrb xmm10, byte ptr [rsi + rdi + 22], 6 - pinsrb xmm10, byte ptr [rsi + rbx + 22], 7 - pinsrb xmm10, byte ptr [rsi + r14 + 22], 8 - pinsrb xmm10, byte ptr [rsi + r9 + 22], 9 - pinsrb xmm10, byte ptr [rsi + r11 + 22], 10 - pinsrb xmm10, byte ptr [rsi + r15 + 22], 11 - pinsrb xmm10, byte ptr [rsi + r12 + 22], 12 - pinsrb xmm10, byte ptr [rsi + r8 + 22], 13 - pinsrb xmm10, byte ptr [rsi + rax + 22], 14 - pinsrb xmm10, byte ptr [rsi + r13 + 22], 15 - pinsrb xmm8, byte ptr [rsi + r10 + 23], 3 - pinsrb xmm8, byte ptr [rsi + rdx + 23], 4 - pinsrb xmm8, byte ptr [rsi + rcx + 23], 5 - pinsrb xmm8, byte ptr [rsi + rdi + 23], 6 - pinsrb xmm8, byte ptr [rsi + rbx + 23], 7 - pinsrb xmm8, byte ptr [rsi + r14 + 23], 8 - pinsrb xmm8, byte ptr [rsi + r9 + 23], 9 - pinsrb xmm8, byte ptr [rsi + r11 + 23], 10 - pinsrb xmm8, byte ptr [rsi + r15 + 23], 11 - pinsrb xmm8, byte ptr [rsi + r12 + 23], 12 - pinsrb xmm8, byte ptr [rsi + r8 + 23], 13 - pand xmm1, xmmword ptr [rip + .LCPI10_19] - pand xmm2, xmmword ptr [rip + .LCPI10_20] - por xmm2, xmm1 - movdqa xmm1, xmm10 - pmaxub xmm1, xmm12 - pcmpeqb xmm1, xmm10 - pinsrb xmm8, byte ptr [rsi + rax + 23], 14 - pand xmm1, xmmword ptr [rip + .LCPI10_21] - por xmm1, xmm2 - pinsrb xmm8, byte ptr [rsi + r13 + 23], 15 - por xmm1, xmm11 - movdqa xmm10, xmm8 - pmaxub xmm10, xmm12 - pcmpeqb xmm10, xmm8 - pinsrb xmm15, byte ptr [rsi + r10 + 25], 3 - pinsrb xmm15, byte ptr [rsi + rdx + 25], 4 - pinsrb xmm15, byte ptr [rsi + rcx + 25], 5 - pinsrb xmm15, byte ptr [rsi + rdi + 25], 6 - pinsrb xmm15, byte ptr [rsi + rbx + 25], 7 - pinsrb xmm15, byte ptr [rsi + r14 + 25], 8 - pinsrb xmm15, byte ptr [rsi + r9 + 25], 9 - pinsrb xmm15, byte ptr [rsi + r11 + 25], 10 - pinsrb xmm15, byte ptr [rsi + r15 + 25], 11 - pinsrb xmm15, byte ptr [rsi + r12 + 25], 12 - pinsrb xmm15, byte ptr [rsi + r8 + 25], 13 - pinsrb xmm15, byte ptr [rsi + rax + 25], 14 - pinsrb xmm15, byte ptr [rsi + r13 + 25], 15 - movdqa xmm11, xmmword ptr [rip + .LCPI10_6] # xmm11 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm10, xmm11 - por xmm10, xmm1 - movdqa xmm3, xmm15 - pmaxub xmm3, xmm12 - pcmpeqb xmm3, xmm15 - pinsrb xmm6, byte ptr [rsi + r10 + 26], 3 - pinsrb xmm6, byte ptr [rsi + rdx + 26], 4 - pinsrb xmm6, byte ptr [rsi + rcx + 26], 5 - pinsrb xmm6, byte ptr [rsi + rdi + 26], 6 - pinsrb xmm6, byte ptr [rsi + rbx + 26], 7 - pinsrb xmm6, byte ptr [rsi + r14 + 26], 8 - pinsrb xmm6, byte ptr [rsi + r9 + 26], 9 - pinsrb xmm6, byte ptr [rsi + r11 + 26], 10 - pinsrb xmm6, byte ptr [rsi + r15 + 26], 11 - pinsrb xmm6, byte ptr [rsi + r12 + 26], 12 - pinsrb xmm6, byte ptr [rsi + r8 + 26], 13 - pinsrb xmm6, byte ptr [rsi + rax + 26], 14 - pinsrb xmm6, byte ptr [rsi + r13 + 26], 15 - pinsrb xmm7, byte ptr [rsi + r10 + 27], 3 - pinsrb xmm7, byte ptr [rsi + rdx + 27], 4 - pinsrb xmm7, byte ptr [rsi + rcx + 27], 5 - pinsrb xmm7, byte ptr [rsi + rdi + 27], 6 - pinsrb xmm7, byte ptr [rsi + rbx + 27], 7 - pinsrb xmm7, byte ptr [rsi + r14 + 27], 8 - pinsrb xmm7, byte ptr [rsi + r9 + 27], 9 - pinsrb xmm7, byte ptr [rsi + r11 + 27], 10 - pinsrb xmm7, byte ptr [rsi + r15 + 27], 11 - pinsrb xmm7, byte ptr [rsi + r12 + 27], 12 - pinsrb xmm7, byte ptr [rsi + r8 + 27], 13 - pinsrb xmm7, byte ptr [rsi + rax + 27], 14 - pinsrb xmm7, byte ptr [rsi + r13 + 27], 15 - pand xmm3, xmmword ptr [rip + .LCPI10_16] - psubb xmm3, xmmword ptr [rsp + 240] # 16-byte Folded Reload - movdqa xmm2, xmm6 - pmaxub xmm2, xmm12 - pcmpeqb xmm2, xmm6 - movdqa xmm1, xmm7 - pmaxub xmm1, xmm12 - pcmpeqb xmm1, xmm7 - pinsrb xmm9, byte ptr [rsi + r10 + 28], 3 - pinsrb xmm9, byte ptr [rsi + rdx + 28], 4 - pinsrb xmm9, byte ptr [rsi + rcx + 28], 5 - pinsrb xmm9, byte ptr [rsi + rdi + 28], 6 - pinsrb xmm9, byte ptr [rsi + rbx + 28], 7 - pinsrb xmm9, byte ptr [rsi + r14 + 28], 8 - pinsrb xmm9, byte ptr [rsi + r9 + 28], 9 - pinsrb xmm9, byte ptr [rsi + r11 + 28], 10 - pinsrb xmm9, byte ptr [rsi + r15 + 28], 11 - pinsrb xmm9, byte ptr [rsi + r12 + 28], 12 - pinsrb xmm9, byte ptr [rsi + r8 + 28], 13 - pinsrb xmm9, byte ptr [rsi + rax + 28], 14 - pinsrb xmm9, byte ptr [rsi + r13 + 28], 15 - pinsrb xmm0, byte ptr [rsi + r10 + 29], 3 - pinsrb xmm0, byte ptr [rsi + rdx + 29], 4 - pinsrb xmm0, byte ptr [rsi + rcx + 29], 5 - pinsrb xmm0, byte ptr [rsi + rdi + 29], 6 - pinsrb xmm0, byte ptr [rsi + rbx + 29], 7 - pinsrb xmm0, byte ptr [rsi + r14 + 29], 8 - pinsrb xmm0, byte ptr [rsi + r9 + 29], 9 - pinsrb xmm0, byte ptr [rsi + r11 + 29], 10 - pinsrb xmm0, byte ptr [rsi + r15 + 29], 11 - pinsrb xmm0, byte ptr [rsi + r12 + 29], 12 - pinsrb xmm0, byte ptr [rsi + r8 + 29], 13 - pinsrb xmm0, byte ptr [rsi + rax + 29], 14 - pinsrb xmm0, byte ptr [rsi + r13 + 29], 15 - pand xmm2, xmmword ptr [rip + .LCPI10_17] - pand xmm1, xmmword ptr [rip + .LCPI10_18] - por xmm1, xmm2 - por xmm1, xmm3 - movdqa xmm2, xmm9 - pmaxub xmm2, xmm12 - pcmpeqb xmm2, xmm9 - movdqa xmm3, xmm0 - pmaxub xmm3, xmm12 - pcmpeqb xmm3, xmm0 - pinsrb xmm4, byte ptr [rsi + r10 + 30], 3 - pinsrb xmm5, byte ptr [rsi + r10 + 31], 3 - pinsrb xmm4, byte ptr [rsi + rdx + 30], 4 - pinsrb xmm5, byte ptr [rsi + rdx + 31], 4 - pinsrb xmm4, byte ptr [rsi + rcx + 30], 5 - pinsrb xmm5, byte ptr [rsi + rcx + 31], 5 - pinsrb xmm4, byte ptr [rsi + rdi + 30], 6 - pinsrb xmm5, byte ptr [rsi + rdi + 31], 6 - pinsrb xmm4, byte ptr [rsi + rbx + 30], 7 - pinsrb xmm5, byte ptr [rsi + rbx + 31], 7 - pinsrb xmm4, byte ptr [rsi + r14 + 30], 8 - pinsrb xmm5, byte ptr [rsi + r14 + 31], 8 - pinsrb xmm4, byte ptr [rsi + r9 + 30], 9 - pinsrb xmm5, byte ptr [rsi + r9 + 31], 9 - pinsrb xmm4, byte ptr [rsi + r11 + 30], 10 - pinsrb xmm5, byte ptr [rsi + r11 + 31], 10 - mov r14, qword ptr [rsp + 352] # 8-byte Reload - pinsrb xmm4, byte ptr [rsi + r15 + 30], 11 - pinsrb xmm5, byte ptr [rsi + r15 + 31], 11 - pinsrb xmm4, byte ptr [rsi + r12 + 30], 12 - pinsrb xmm5, byte ptr [rsi + r12 + 31], 12 - pinsrb xmm4, byte ptr [rsi + r8 + 30], 13 - pinsrb xmm5, byte ptr [rsi + r8 + 31], 13 - pinsrb xmm4, byte ptr [rsi + rax + 30], 14 - pinsrb xmm5, byte ptr [rsi + rax + 31], 14 - pinsrb xmm4, byte ptr [rsi + r13 + 30], 15 - pand xmm2, xmmword ptr [rip + .LCPI10_19] - pand xmm3, xmmword ptr [rip + .LCPI10_20] - por xmm3, xmm2 - movdqa xmm0, xmm4 - pmaxub xmm0, xmm12 - pcmpeqb xmm0, xmm4 - pinsrb xmm5, byte ptr [rsi + r13 + 31], 15 - pand xmm0, xmmword ptr [rip + .LCPI10_21] - por xmm0, xmm3 - por xmm0, xmm1 - movdqa xmm1, xmm5 - pmaxub xmm1, xmm12 - pcmpeqb xmm1, xmm5 - pand xmm1, xmm11 - por xmm1, xmm0 - movdqa xmm0, xmm10 - punpcklbw xmm0, xmm1 # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7] - movdqa xmm4, xmmword ptr [rsp + 272] # 16-byte Reload - movdqa xmm2, xmm4 - punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] - movdqa xmm3, xmm2 - punpcklwd xmm3, xmm0 # xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3] - punpckhwd xmm2, xmm0 # xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7] - punpckhbw xmm10, xmm1 # xmm10 = xmm10[8],xmm1[8],xmm10[9],xmm1[9],xmm10[10],xmm1[10],xmm10[11],xmm1[11],xmm10[12],xmm1[12],xmm10[13],xmm1[13],xmm10[14],xmm1[14],xmm10[15],xmm1[15] - punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] - movdqa xmm0, xmm4 - punpcklwd xmm0, xmm10 # xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1],xmm0[2],xmm10[2],xmm0[3],xmm10[3] - punpckhwd xmm4, xmm10 # xmm4 = xmm4[4],xmm10[4],xmm4[5],xmm10[5],xmm4[6],xmm10[6],xmm4[7],xmm10[7] - mov rcx, qword ptr [rsp + 336] # 8-byte Reload - movdqu xmmword ptr [r14 + 4*rcx + 48], xmm4 - movdqu xmmword ptr [r14 + 4*rcx + 32], xmm0 - movdqu xmmword ptr [r14 + 4*rcx + 16], xmm2 - movdqu xmmword ptr [r14 + 4*rcx], xmm3 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 416] # 8-byte Folded Reload - jne .LBB10_67 + sub r8, rcx + jle .LBB10_227 +# %bb.105: + or rcx, 1 + cmp r14, rcx + jne .LBB10_107 +# %bb.106: + xor r9d, r9d + jmp .LBB10_110 +.LBB10_61: + mov rdi, rsi + sub r14, r8 + je .LBB10_227 +.LBB10_63: + add r12, 1 +.LBB10_64: + lea rcx, [r14 + 31] + test r14, r14 + cmovns rcx, r14 + sar rcx, 5 + cmp r14, 32 + jl .LBB10_65 # %bb.68: - mov r15, qword ptr [rsp + 464] # 8-byte Reload - cmp r15, qword ptr [rsp + 416] # 8-byte Folded Reload - mov r11b, byte ptr [rsp + 8] # 1-byte Reload - mov rsi, qword ptr [rsp + 392] # 8-byte Reload - mov r10, qword ptr [rsp + 72] # 8-byte Reload - jne .LBB10_69 - jmp .LBB10_72 -.LBB10_124: - and r15, -8 - mov r11, r15 + cmp rcx, 16 + mov byte ptr [rsp], r13b # 1-byte Spill + mov qword ptr [rsp + 72], r14 # 8-byte Spill + mov qword ptr [rsp + 376], rcx # 8-byte Spill + jb .LBB10_69 +# %bb.70: + mov rax, rcx + shl rax, 5 + add rax, rdi + cmp r12, rax + jae .LBB10_72 +# %bb.71: + lea rax, [r12 + 4*rcx] + cmp rdi, rax + jae .LBB10_72 +.LBB10_69: + xor eax, eax + mov qword ptr [rsp + 384], rax # 8-byte Spill + mov qword ptr [rsp + 400], r12 # 8-byte Spill + mov rsi, rdi +.LBB10_75: + sub rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov qword ptr [rsp + 352], rcx # 8-byte Spill + mov rdi, qword ptr [rsp + 400] # 8-byte Reload + .p2align 4, 0x90 +.LBB10_76: # =>This Inner Loop Header: Depth=1 + mov rcx, rsi + cmp byte ptr [rsi], r13b + setae byte ptr [rsp + 304] # 1-byte Folded Spill + cmp byte ptr [rsi + 1], r13b + setae sil + cmp byte ptr [rcx + 2], r13b + setae r15b + cmp byte ptr [rcx + 3], r13b + setae byte ptr [rsp + 240] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 4], al + setae byte ptr [rsp + 224] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 5], al + setae byte ptr [rsp + 144] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 6], al + setae r13b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 7], al + setae r9b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 8], al + setae byte ptr [rsp + 336] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 9], al + setae dl + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 10], al + setae r8b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 11], al + setae r10b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 12], al + setae r14b + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 13], al + setae byte ptr [rsp + 320] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 14], al + setae byte ptr [rsp + 288] # 1-byte Folded Spill + movzx eax, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 15], al + setae r12b + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 16], bl + setae byte ptr [rsp + 256] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 17], bl + setae byte ptr [rsp + 272] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 18], bl + setae byte ptr [rsp + 208] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 19], bl + setae byte ptr [rsp + 160] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 20], bl + setae byte ptr [rsp + 192] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 21], bl + setae byte ptr [rsp + 128] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 22], bl + setae byte ptr [rsp + 176] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 23], bl + setae r11b + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 24], bl + setae byte ptr [rsp + 112] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 25], bl + setae byte ptr [rsp + 96] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 26], bl + setae byte ptr [rsp + 80] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 27], bl + setae byte ptr [rsp + 48] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 28], bl + setae byte ptr [rsp + 32] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 29], bl + setae byte ptr [rsp + 16] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 30], bl + setae byte ptr [rsp + 8] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + cmp byte ptr [rcx + 31], bl + setae bl + add sil, sil + add sil, byte ptr [rsp + 304] # 1-byte Folded Reload + shl r13b, 6 + shl r9b, 7 + or r9b, r13b + shl r15b, 2 + or r15b, sil + add dl, dl + add dl, byte ptr [rsp + 336] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 240] # 1-byte Folded Reload + shl al, 3 + or al, r15b + shl r8b, 2 + or r8b, dl + movzx edx, byte ptr [rsp + 224] # 1-byte Folded Reload + shl dl, 4 + or dl, al + mov esi, edx + movzx r13d, byte ptr [rsp] # 1-byte Folded Reload + shl r10b, 3 + or r10b, r8b + movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + shl r14b, 4 + or r14b, r10b + movzx eax, byte ptr [rsp + 320] # 1-byte Folded Reload + shl al, 5 + or al, r14b + movzx esi, byte ptr [rsp + 288] # 1-byte Folded Reload + shl sil, 6 + shl r12b, 7 + or r12b, sil + or r9b, dl + or r12b, al + movzx edx, byte ptr [rsp + 272] # 1-byte Folded Reload + add dl, dl + add dl, byte ptr [rsp + 256] # 1-byte Folded Reload + mov esi, edx + movzx edx, byte ptr [rsp + 208] # 1-byte Folded Reload + shl dl, 2 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 160] # 1-byte Folded Reload + shl dl, 3 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 192] # 1-byte Folded Reload + shl dl, 4 + or dl, sil + mov esi, edx + movzx edx, byte ptr [rsp + 128] # 1-byte Folded Reload + shl dl, 5 + or dl, sil + mov byte ptr [rdi], r9b + movzx esi, byte ptr [rsp + 176] # 1-byte Folded Reload + shl sil, 6 + shl r11b, 7 + or r11b, sil + mov byte ptr [rdi + 1], r12b + or r11b, dl + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 112] # 1-byte Folded Reload + mov edx, eax + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + shl al, 2 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 3 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + shl al, 4 + or al, dl + mov edx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 5 + or al, dl + movzx edx, byte ptr [rsp + 8] # 1-byte Folded Reload + shl dl, 6 + shl bl, 7 + or bl, dl + or bl, al + mov byte ptr [rdi + 2], r11b + mov byte ptr [rdi + 3], bl + lea rsi, [rcx + 32] + add rdi, 4 + add qword ptr [rsp + 352], -1 # 8-byte Folded Spill + jne .LBB10_76 +# %bb.77: + mov qword ptr [rsp + 400], rdi # 8-byte Spill + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov rcx, qword ptr [rsp + 376] # 8-byte Reload + jmp .LBB10_78 +.LBB10_65: + mov qword ptr [rsp + 400], r12 # 8-byte Spill + mov rsi, rdi +.LBB10_78: + shl rcx, 5 + mov r8, r14 + sub r8, rcx + jle .LBB10_227 +# %bb.79: + or rcx, 1 + cmp r14, rcx + jne .LBB10_81 +# %bb.80: + xor r9d, r9d + jmp .LBB10_84 +.LBB10_176: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB10_177: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + mov eax, 0 + adc al, -1 + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor al, r9b + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + mov eax, 0 + adc al, -1 + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB10_177 +.LBB10_40: + test r8b, 1 + je .LBB10_227 +# %bb.41: + xor eax, eax + cmp qword ptr [rsi], r13 + jmp .LBB10_225 +.LBB10_174: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB10_175: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d + setge al + neg al + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + setge al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB10_175 +.LBB10_171: + test r8b, 1 + je .LBB10_227 +# %bb.172: + cmp dword ptr [rsi], r13d + jmp .LBB10_173 +.LBB10_107: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 112] # 8-byte Reload + .p2align 4, 0x90 +.LBB10_108: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r15b + setge bl + neg bl + mov rdi, r9 + shr rdi, 3 + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r11 + rdi] + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r15b + lea r9, [rax + 2] + setge bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB10_108 +# %bb.109: + add rsi, r9 +.LBB10_110: + test r8b, 1 + je .LBB10_227 +# %bb.111: + cmp byte ptr [rsi], r15b + setge al + neg al + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 112] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + jmp .LBB10_112 +.LBB10_81: + mov r10, r8 + and r10, -2 + xor r9d, r9d + mov r11, qword ptr [rsp + 400] # 8-byte Reload + .p2align 4, 0x90 +.LBB10_82: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp byte ptr [rsi + r9], r13b + mov ebx, 0 + adc bl, -1 + mov rdi, r9 + shr rdi, 3 + movzx r9d, byte ptr [r11 + rdi] + mov ecx, eax + and cl, 6 + mov dl, 1 + shl dl, cl + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp byte ptr [rsi + rax + 1], r13b + lea r9, [rax + 2] + mov ebx, 0 + adc bl, -1 + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, r9 + jne .LBB10_82 +# %bb.83: + add rsi, r9 +.LBB10_84: + test r8b, 1 + je .LBB10_227 +# %bb.85: + xor eax, eax + cmp byte ptr [rsi], r13b + adc al, -1 + mov rdx, r9 + shr rdx, 3 + mov r8, qword ptr [rsp + 400] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and r9b, 7 + mov bl, 1 + mov ecx, r9d + shl bl, cl + xor al, dil + and bl, al + jmp .LBB10_113 +.LBB10_156: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB10_157: # =>This Inner Loop Header: Depth=1 + cmp dword ptr [rsi], r13d + mov eax, 0 + adc al, -1 + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor al, r9b + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp dword ptr [rsi + 4], r13d + lea rsi, [rsi + 8] + mov eax, 0 + adc al, -1 + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB10_157 +.LBB10_22: + test r8b, 1 + je .LBB10_227 +# %bb.23: + xor eax, eax + cmp dword ptr [rsi], r13d + jmp .LBB10_225 +.LBB10_221: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB10_222: # =>This Inner Loop Header: Depth=1 + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + ucomisd xmm1, xmm0 + mov eax, 0 + adc al, -1 + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor al, r9b + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + movsd xmm1, qword ptr [rsi + 8] # xmm1 = mem[0],zero + add rsi, 16 + ucomisd xmm1, xmm0 + mov eax, 0 + adc al, -1 + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB10_222 +.LBB10_223: + test r8b, 1 + je .LBB10_227 +# %bb.224: + movsd xmm1, qword ptr [rsi] # xmm1 = mem[0],zero + xor eax, eax + ucomisd xmm1, xmm0 + jmp .LBB10_225 +.LBB10_129: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB10_130: # =>This Inner Loop Header: Depth=1 + cmp word ptr [rsi], r13w + mov eax, 0 + adc al, -1 + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + xor al, r9b + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp word ptr [rsi + 2], r13w + lea rsi, [rsi + 4] + mov eax, 0 + adc al, -1 + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB10_130 +.LBB10_127: + test r8b, 1 + je .LBB10_227 +# %bb.128: + xor eax, eax + cmp word ptr [rsi], r13w +.LBB10_225: + adc al, -1 + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al + jmp .LBB10_226 +.LBB10_193: + mov r10, r8 + and r10, -2 + xor r11d, r11d + .p2align 4, 0x90 +.LBB10_194: # =>This Inner Loop Header: Depth=1 + cmp qword ptr [rsi], r13 + setge al + neg al + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r12 + rdi] + mov ecx, r11d + and cl, 6 + mov bl, 1 + shl bl, cl + xor al, r9b + and bl, al + xor bl, r9b + mov byte ptr [r12 + rdi], bl + add r11, 2 + cmp qword ptr [rsi + 8], r13 + lea rsi, [rsi + 16] + setge al + neg al + xor al, bl + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, al + xor dl, bl + mov byte ptr [r12 + rdi], dl + cmp r10, r11 + jne .LBB10_194 +.LBB10_191: + test r8b, 1 + je .LBB10_227 +# %bb.192: + cmp qword ptr [rsi], r13 +.LBB10_173: + setge al + neg al + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al +.LBB10_226: + xor bl, sil + mov byte ptr [r12 + rdx], bl + jmp .LBB10_227 +.LBB10_154: + mov r10, r8 + and r10, -2 + xor esi, esi + mov r14, qword ptr [rsp + 8] # 8-byte Reload + .p2align 4, 0x90 +.LBB10_155: # =>This Inner Loop Header: Depth=1 + cmp word ptr [r11], r15w + setge bl + neg bl + mov rdi, rsi + shr rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, esi + and cl, 6 + mov dl, 1 + shl dl, cl + xor bl, r9b + and dl, bl + xor dl, r9b + mov byte ptr [r14 + rdi], dl + add rsi, 2 + cmp word ptr [r11 + 2], r15w + lea r11, [r11 + 4] + setge bl + neg bl + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r14 + rdi], al + cmp r10, rsi + jne .LBB10_155 +.LBB10_152: + test r8b, 1 + je .LBB10_227 +# %bb.153: + cmp word ptr [r11], r15w + setge al + neg al + mov rdx, rsi + shr rdx, 3 + mov r8, qword ptr [rsp + 8] # 8-byte Reload + mov dil, byte ptr [r8 + rdx] + and sil, 7 + mov bl, 1 + mov ecx, esi +.LBB10_112: + shl bl, cl + xor al, dil + and bl, al +.LBB10_113: + xor bl, dil + mov byte ptr [r8 + rdx], bl + jmp .LBB10_227 +.LBB10_218: + mov r10, r8 + and r10, -2 + xor r15d, r15d + mov r14, r11 + mov rsi, rcx + .p2align 4, 0x90 +.LBB10_219: # =>This Inner Loop Header: Depth=1 + movss xmm1, dword ptr [rsi] # xmm1 = mem[0],zero,zero,zero + ucomiss xmm1, xmm0 + mov ebx, 0 + adc bl, -1 + mov rdi, r15 + shr rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + xor bl, r9b + mov ecx, r15d + and cl, 6 + mov dl, 1 + shl dl, cl + and dl, bl + xor dl, r9b + mov byte ptr [r14 + rdi], dl + add r15, 2 + movss xmm1, dword ptr [rsi + 4] # xmm1 = mem[0],zero,zero,zero + add rsi, 8 + ucomiss xmm1, xmm0 + mov ebx, 0 + adc bl, -1 + xor bl, dl + or cl, 1 + mov al, 1 + shl al, cl + and al, bl + xor al, dl + mov byte ptr [r14 + rdi], al + cmp r10, r15 + jne .LBB10_219 +# %bb.220: + mov rcx, rsi +.LBB10_216: + test r8b, 1 + je .LBB10_227 +# %bb.217: + movss xmm1, dword ptr [rcx] # xmm1 = mem[0],zero,zero,zero + xor eax, eax + ucomiss xmm1, xmm0 + adc al, -1 + mov rdx, r15 + shr rdx, 3 + mov dil, byte ptr [r11 + rdx] + and r15b, 7 + mov bl, 1 + mov ecx, r15d + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + mov byte ptr [r11 + rdx], bl +.LBB10_227: + lea rsp, [rbp - 40] + pop rbx + pop r12 + pop r13 + pop r14 + pop r15 + pop rbp + ret +.LBB10_143: + and rcx, -8 + mov r11, rcx shl r11, 6 add r11, rsi - mov qword ptr [rsp + 400], r15 # 8-byte Spill - lea rax, [r14 + 4*r15] + mov qword ptr [rsp + 376], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] mov qword ptr [rsp + 8], rax # 8-byte Spill - movd xmm0, dword ptr [rsp + 392] # 4-byte Folded Reload - # xmm0 = mem[0],zero,zero,zero + movd xmm0, r15d pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] pshufd xmm0, xmm0, 0 # xmm0 = xmm0[0,0,0,0] - movdqa xmmword ptr [rsp + 464], xmm0 # 16-byte Spill + movdqa xmmword ptr [rsp + 448], xmm0 # 16-byte Spill xor r10d, r10d .p2align 4, 0x90 -.LBB10_125: # =>This Inner Loop Header: Depth=1 - mov r9, r10 - shl r9, 6 - mov r8, r9 - mov rdi, r9 - mov rbx, r9 - mov r15, r9 - mov r12, r9 - mov r13, r9 - movzx ecx, word ptr [rsi + r9] +.LBB10_144: # =>This Inner Loop Header: Depth=1 + mov r8, r10 + shl r8, 6 + mov r9, r8 + mov rbx, r8 + mov rdi, r8 + mov rax, r8 + mov r15, r12 + mov r12, r8 + mov r13, r8 + movzx ecx, word ptr [rsi + r8] movd xmm11, ecx - movzx ecx, word ptr [rsi + r9 + 2] + movzx ecx, word ptr [rsi + r8 + 2] movd xmm0, ecx - movdqa xmmword ptr [rsp + 16], xmm0 # 16-byte Spill - movzx ecx, word ptr [rsi + r9 + 4] + movdqa xmmword ptr [rsp + 32], xmm0 # 16-byte Spill + movzx ecx, word ptr [rsi + r8 + 4] movd xmm9, ecx - movzx ecx, word ptr [rsi + r9 + 6] + movzx ecx, word ptr [rsi + r8 + 6] movd xmm10, ecx - movzx ecx, word ptr [rsi + r9 + 8] + movzx ecx, word ptr [rsi + r8 + 8] movd xmm12, ecx - movzx ecx, word ptr [rsi + r9 + 10] + movzx ecx, word ptr [rsi + r8 + 10] movd xmm13, ecx - movzx ecx, word ptr [rsi + r9 + 12] + movzx ecx, word ptr [rsi + r8 + 12] movd xmm14, ecx - movzx ecx, word ptr [rsi + r9 + 14] + movzx ecx, word ptr [rsi + r8 + 14] movd xmm8, ecx - movzx ecx, word ptr [rsi + r9 + 16] + movzx ecx, word ptr [rsi + r8 + 16] movd xmm1, ecx - movzx ecx, word ptr [rsi + r9 + 18] + movzx ecx, word ptr [rsi + r8 + 18] movd xmm2, ecx - movzx ecx, word ptr [rsi + r9 + 20] + movzx ecx, word ptr [rsi + r8 + 20] movd xmm3, ecx - movzx ecx, word ptr [rsi + r9 + 22] + movzx ecx, word ptr [rsi + r8 + 22] movd xmm4, ecx - movzx ecx, word ptr [rsi + r9 + 24] + movzx ecx, word ptr [rsi + r8 + 24] movd xmm5, ecx - movzx ecx, word ptr [rsi + r9 + 26] + movzx ecx, word ptr [rsi + r8 + 26] movd xmm6, ecx - movzx eax, word ptr [rsi + r9 + 28] - movzx edx, word ptr [rsi + r9 + 30] - mov rcx, r9 + movzx edx, word ptr [rsi + r8 + 28] + movzx r14d, word ptr [rsi + r8 + 30] + mov rcx, r8 or rcx, 64 - or r8, 128 - or rdi, 192 - or rbx, 256 - or r15, 320 + or r9, 128 + or rbx, 192 + or rdi, 256 + or rax, 320 or r12, 384 or r13, 448 pinsrw xmm11, word ptr [rsi + rcx], 1 - pinsrw xmm11, word ptr [rsi + r8], 2 - pinsrw xmm11, word ptr [rsi + rdi], 3 - pinsrw xmm11, word ptr [rsi + rbx], 4 - pinsrw xmm11, word ptr [rsi + r15], 5 + pinsrw xmm11, word ptr [rsi + r9], 2 + pinsrw xmm11, word ptr [rsi + rbx], 3 + pinsrw xmm11, word ptr [rsi + rdi], 4 + pinsrw xmm11, word ptr [rsi + rax], 5 pinsrw xmm11, word ptr [rsi + r12], 6 pinsrw xmm11, word ptr [rsi + r13], 7 - movd xmm15, eax - movdqa xmm0, xmmword ptr [rsp + 464] # 16-byte Reload + movd xmm15, edx + movdqa xmm0, xmmword ptr [rsp + 448] # 16-byte Reload movdqa xmm7, xmm0 pcmpgtw xmm7, xmm11 - movdqa xmmword ptr [rsp + 352], xmm7 # 16-byte Spill - movdqa xmm7, xmmword ptr [rsp + 16] # 16-byte Reload + movdqa xmmword ptr [rsp + 16], xmm7 # 16-byte Spill + movdqa xmm7, xmmword ptr [rsp + 32] # 16-byte Reload pinsrw xmm7, word ptr [rsi + rcx + 2], 1 - pinsrw xmm7, word ptr [rsi + r8 + 2], 2 - pinsrw xmm7, word ptr [rsi + rdi + 2], 3 - pinsrw xmm7, word ptr [rsi + rbx + 2], 4 - pinsrw xmm7, word ptr [rsi + r15 + 2], 5 + pinsrw xmm7, word ptr [rsi + r9 + 2], 2 + pinsrw xmm7, word ptr [rsi + rbx + 2], 3 + pinsrw xmm7, word ptr [rsi + rdi + 2], 4 + pinsrw xmm7, word ptr [rsi + rax + 2], 5 pinsrw xmm7, word ptr [rsi + r12 + 2], 6 pinsrw xmm7, word ptr [rsi + r13 + 2], 7 movdqa xmm11, xmm0 pinsrw xmm9, word ptr [rsi + rcx + 4], 1 - pinsrw xmm9, word ptr [rsi + r8 + 4], 2 - pinsrw xmm9, word ptr [rsi + rdi + 4], 3 - pinsrw xmm9, word ptr [rsi + rbx + 4], 4 - pinsrw xmm9, word ptr [rsi + r15 + 4], 5 + pinsrw xmm9, word ptr [rsi + r9 + 4], 2 + pinsrw xmm9, word ptr [rsi + rbx + 4], 3 + pinsrw xmm9, word ptr [rsi + rdi + 4], 4 + pinsrw xmm9, word ptr [rsi + rax + 4], 5 pinsrw xmm9, word ptr [rsi + r12 + 4], 6 pcmpgtw xmm11, xmm7 pinsrw xmm9, word ptr [rsi + r13 + 4], 7 movdqa xmm7, xmm0 pcmpgtw xmm7, xmm9 - movdqa xmmword ptr [rsp + 80], xmm7 # 16-byte Spill + movdqa xmmword ptr [rsp + 96], xmm7 # 16-byte Spill pinsrw xmm10, word ptr [rsi + rcx + 6], 1 - pinsrw xmm10, word ptr [rsi + r8 + 6], 2 - pinsrw xmm10, word ptr [rsi + rdi + 6], 3 - pinsrw xmm10, word ptr [rsi + rbx + 6], 4 - pinsrw xmm10, word ptr [rsi + r15 + 6], 5 + pinsrw xmm10, word ptr [rsi + r9 + 6], 2 + pinsrw xmm10, word ptr [rsi + rbx + 6], 3 + pinsrw xmm10, word ptr [rsi + rdi + 6], 4 + pinsrw xmm10, word ptr [rsi + rax + 6], 5 pinsrw xmm10, word ptr [rsi + r12 + 6], 6 pinsrw xmm10, word ptr [rsi + r13 + 6], 7 movdqa xmm7, xmm0 pinsrw xmm12, word ptr [rsi + rcx + 8], 1 - pinsrw xmm12, word ptr [rsi + r8 + 8], 2 - pinsrw xmm12, word ptr [rsi + rdi + 8], 3 - pinsrw xmm12, word ptr [rsi + rbx + 8], 4 - pinsrw xmm12, word ptr [rsi + r15 + 8], 5 + pinsrw xmm12, word ptr [rsi + r9 + 8], 2 + pinsrw xmm12, word ptr [rsi + rbx + 8], 3 + pinsrw xmm12, word ptr [rsi + rdi + 8], 4 + pinsrw xmm12, word ptr [rsi + rax + 8], 5 pinsrw xmm12, word ptr [rsi + r12 + 8], 6 pinsrw xmm12, word ptr [rsi + r13 + 8], 7 pcmpgtw xmm7, xmm10 movdqa xmmword ptr [rsp + 144], xmm7 # 16-byte Spill movdqa xmm7, xmm0 pcmpgtw xmm7, xmm12 - movdqa xmmword ptr [rsp + 32], xmm7 # 16-byte Spill + movdqa xmmword ptr [rsp + 48], xmm7 # 16-byte Spill pinsrw xmm13, word ptr [rsi + rcx + 10], 1 - pinsrw xmm13, word ptr [rsi + r8 + 10], 2 - pinsrw xmm13, word ptr [rsi + rdi + 10], 3 - pinsrw xmm13, word ptr [rsi + rbx + 10], 4 - pinsrw xmm13, word ptr [rsi + r15 + 10], 5 + pinsrw xmm13, word ptr [rsi + r9 + 10], 2 + pinsrw xmm13, word ptr [rsi + rbx + 10], 3 + pinsrw xmm13, word ptr [rsi + rdi + 10], 4 + pinsrw xmm13, word ptr [rsi + rax + 10], 5 pinsrw xmm13, word ptr [rsi + r12 + 10], 6 pinsrw xmm13, word ptr [rsi + r13 + 10], 7 movdqa xmm7, xmm0 pinsrw xmm14, word ptr [rsi + rcx + 12], 1 - pinsrw xmm14, word ptr [rsi + r8 + 12], 2 - pinsrw xmm14, word ptr [rsi + rdi + 12], 3 - pinsrw xmm14, word ptr [rsi + rbx + 12], 4 - pinsrw xmm14, word ptr [rsi + r15 + 12], 5 + pinsrw xmm14, word ptr [rsi + r9 + 12], 2 + pinsrw xmm14, word ptr [rsi + rbx + 12], 3 + pinsrw xmm14, word ptr [rsi + rdi + 12], 4 + pinsrw xmm14, word ptr [rsi + rax + 12], 5 pinsrw xmm14, word ptr [rsi + r12 + 12], 6 pcmpgtw xmm7, xmm13 movdqa xmmword ptr [rsp + 128], xmm7 # 16-byte Spill @@ -54563,88 +54339,88 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar pcmpgtw xmm7, xmm14 movdqa xmm14, xmm7 pinsrw xmm8, word ptr [rsi + rcx + 14], 1 - pinsrw xmm8, word ptr [rsi + r8 + 14], 2 - pinsrw xmm8, word ptr [rsi + rdi + 14], 3 - pinsrw xmm8, word ptr [rsi + rbx + 14], 4 - pinsrw xmm8, word ptr [rsi + r15 + 14], 5 + pinsrw xmm8, word ptr [rsi + r9 + 14], 2 + pinsrw xmm8, word ptr [rsi + rbx + 14], 3 + pinsrw xmm8, word ptr [rsi + rdi + 14], 4 + pinsrw xmm8, word ptr [rsi + rax + 14], 5 pinsrw xmm8, word ptr [rsi + r12 + 14], 6 pinsrw xmm8, word ptr [rsi + r13 + 14], 7 movdqa xmm7, xmm0 pinsrw xmm1, word ptr [rsi + rcx + 16], 1 - pinsrw xmm1, word ptr [rsi + r8 + 16], 2 - pinsrw xmm1, word ptr [rsi + rdi + 16], 3 - pinsrw xmm1, word ptr [rsi + rbx + 16], 4 - pinsrw xmm1, word ptr [rsi + r15 + 16], 5 + pinsrw xmm1, word ptr [rsi + r9 + 16], 2 + pinsrw xmm1, word ptr [rsi + rbx + 16], 3 + pinsrw xmm1, word ptr [rsi + rdi + 16], 4 + pinsrw xmm1, word ptr [rsi + rax + 16], 5 pinsrw xmm1, word ptr [rsi + r12 + 16], 6 pinsrw xmm1, word ptr [rsi + r13 + 16], 7 pcmpgtw xmm7, xmm8 - movdqa xmmword ptr [rsp + 96], xmm7 # 16-byte Spill + movdqa xmmword ptr [rsp + 112], xmm7 # 16-byte Spill movdqa xmm7, xmm0 pcmpgtw xmm7, xmm1 - movdqa xmmword ptr [rsp + 432], xmm7 # 16-byte Spill + movdqa xmmword ptr [rsp + 416], xmm7 # 16-byte Spill pinsrw xmm2, word ptr [rsi + rcx + 18], 1 - pinsrw xmm2, word ptr [rsi + r8 + 18], 2 - pinsrw xmm2, word ptr [rsi + rdi + 18], 3 - pinsrw xmm2, word ptr [rsi + rbx + 18], 4 - pinsrw xmm2, word ptr [rsi + r15 + 18], 5 + pinsrw xmm2, word ptr [rsi + r9 + 18], 2 + pinsrw xmm2, word ptr [rsi + rbx + 18], 3 + pinsrw xmm2, word ptr [rsi + rdi + 18], 4 + pinsrw xmm2, word ptr [rsi + rax + 18], 5 pinsrw xmm2, word ptr [rsi + r12 + 18], 6 pinsrw xmm2, word ptr [rsi + r13 + 18], 7 movdqa xmm1, xmm0 pinsrw xmm3, word ptr [rsi + rcx + 20], 1 - pinsrw xmm3, word ptr [rsi + r8 + 20], 2 - pinsrw xmm3, word ptr [rsi + rdi + 20], 3 - pinsrw xmm3, word ptr [rsi + rbx + 20], 4 - pinsrw xmm3, word ptr [rsi + r15 + 20], 5 + pinsrw xmm3, word ptr [rsi + r9 + 20], 2 + pinsrw xmm3, word ptr [rsi + rbx + 20], 3 + pinsrw xmm3, word ptr [rsi + rdi + 20], 4 + pinsrw xmm3, word ptr [rsi + rax + 20], 5 pinsrw xmm3, word ptr [rsi + r12 + 20], 6 pcmpgtw xmm1, xmm2 - movdqa xmmword ptr [rsp + 160], xmm1 # 16-byte Spill + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill pinsrw xmm3, word ptr [rsi + r13 + 20], 7 movdqa xmm1, xmm0 pcmpgtw xmm1, xmm3 - movdqa xmmword ptr [rsp + 48], xmm1 # 16-byte Spill + movdqa xmmword ptr [rsp + 80], xmm1 # 16-byte Spill pinsrw xmm4, word ptr [rsi + rcx + 22], 1 - pinsrw xmm4, word ptr [rsi + r8 + 22], 2 - pinsrw xmm4, word ptr [rsi + rdi + 22], 3 - pinsrw xmm4, word ptr [rsi + rbx + 22], 4 - pinsrw xmm4, word ptr [rsi + r15 + 22], 5 + pinsrw xmm4, word ptr [rsi + r9 + 22], 2 + pinsrw xmm4, word ptr [rsi + rbx + 22], 3 + pinsrw xmm4, word ptr [rsi + rdi + 22], 4 + pinsrw xmm4, word ptr [rsi + rax + 22], 5 pinsrw xmm4, word ptr [rsi + r12 + 22], 6 pinsrw xmm4, word ptr [rsi + r13 + 22], 7 movdqa xmm1, xmm0 pinsrw xmm5, word ptr [rsi + rcx + 24], 1 - pinsrw xmm5, word ptr [rsi + r8 + 24], 2 - pinsrw xmm5, word ptr [rsi + rdi + 24], 3 - pinsrw xmm5, word ptr [rsi + rbx + 24], 4 - pinsrw xmm5, word ptr [rsi + r15 + 24], 5 + pinsrw xmm5, word ptr [rsi + r9 + 24], 2 + pinsrw xmm5, word ptr [rsi + rbx + 24], 3 + pinsrw xmm5, word ptr [rsi + rdi + 24], 4 + pinsrw xmm5, word ptr [rsi + rax + 24], 5 pinsrw xmm5, word ptr [rsi + r12 + 24], 6 pinsrw xmm5, word ptr [rsi + r13 + 24], 7 pcmpgtw xmm1, xmm4 - movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + movdqa xmmword ptr [rsp + 160], xmm1 # 16-byte Spill movdqa xmm1, xmm0 pcmpgtw xmm1, xmm5 - movdqa xmmword ptr [rsp + 16], xmm1 # 16-byte Spill + movdqa xmmword ptr [rsp + 32], xmm1 # 16-byte Spill pinsrw xmm6, word ptr [rsi + rcx + 26], 1 - pinsrw xmm6, word ptr [rsi + r8 + 26], 2 - pinsrw xmm6, word ptr [rsi + rdi + 26], 3 - pinsrw xmm6, word ptr [rsi + rbx + 26], 4 - pinsrw xmm6, word ptr [rsi + r15 + 26], 5 + pinsrw xmm6, word ptr [rsi + r9 + 26], 2 + pinsrw xmm6, word ptr [rsi + rbx + 26], 3 + pinsrw xmm6, word ptr [rsi + rdi + 26], 4 + pinsrw xmm6, word ptr [rsi + rax + 26], 5 pinsrw xmm6, word ptr [rsi + r12 + 26], 6 pinsrw xmm6, word ptr [rsi + r13 + 26], 7 movdqa xmm1, xmm0 pinsrw xmm15, word ptr [rsi + rcx + 28], 1 - pinsrw xmm15, word ptr [rsi + r8 + 28], 2 - pinsrw xmm15, word ptr [rsi + rdi + 28], 3 - pinsrw xmm15, word ptr [rsi + rbx + 28], 4 - pinsrw xmm15, word ptr [rsi + r15 + 28], 5 + pinsrw xmm15, word ptr [rsi + r9 + 28], 2 + pinsrw xmm15, word ptr [rsi + rbx + 28], 3 + pinsrw xmm15, word ptr [rsi + rdi + 28], 4 + pinsrw xmm15, word ptr [rsi + rax + 28], 5 pinsrw xmm15, word ptr [rsi + r12 + 28], 6 pcmpgtw xmm1, xmm6 movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill pinsrw xmm15, word ptr [rsi + r13 + 28], 7 - movd xmm1, edx + movd xmm1, r14d pinsrw xmm1, word ptr [rsi + rcx + 30], 1 - pinsrw xmm1, word ptr [rsi + r8 + 30], 2 - pinsrw xmm1, word ptr [rsi + rdi + 30], 3 - pinsrw xmm1, word ptr [rsi + rbx + 30], 4 - pinsrw xmm1, word ptr [rsi + r15 + 30], 5 + pinsrw xmm1, word ptr [rsi + r9 + 30], 2 + pinsrw xmm1, word ptr [rsi + rbx + 30], 3 + pinsrw xmm1, word ptr [rsi + rdi + 30], 4 + pinsrw xmm1, word ptr [rsi + rax + 30], 5 pinsrw xmm1, word ptr [rsi + r12 + 30], 6 movdqa xmm2, xmm0 pcmpgtw xmm2, xmm15 @@ -54652,188 +54428,189 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar pinsrw xmm1, word ptr [rsi + r13 + 30], 7 movdqa xmm2, xmm0 pcmpgtw xmm2, xmm1 - movdqa xmmword ptr [rsp + 112], xmm2 # 16-byte Spill - movzx eax, word ptr [rsi + r9 + 32] - movd xmm1, eax + movdqa xmmword ptr [rsp + 176], xmm2 # 16-byte Spill + movzx edx, word ptr [rsi + r8 + 32] + movd xmm1, edx pinsrw xmm1, word ptr [rsi + rcx + 32], 1 - pinsrw xmm1, word ptr [rsi + r8 + 32], 2 - pinsrw xmm1, word ptr [rsi + rdi + 32], 3 - pinsrw xmm1, word ptr [rsi + rbx + 32], 4 - pinsrw xmm1, word ptr [rsi + r15 + 32], 5 + pinsrw xmm1, word ptr [rsi + r9 + 32], 2 + pinsrw xmm1, word ptr [rsi + rbx + 32], 3 + pinsrw xmm1, word ptr [rsi + rdi + 32], 4 + pinsrw xmm1, word ptr [rsi + rax + 32], 5 pinsrw xmm1, word ptr [rsi + r12 + 32], 6 pinsrw xmm1, word ptr [rsi + r13 + 32], 7 - movzx eax, word ptr [rsi + r9 + 34] - movd xmm2, eax + movzx edx, word ptr [rsi + r8 + 34] + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 34], 1 - pinsrw xmm2, word ptr [rsi + r8 + 34], 2 - pinsrw xmm2, word ptr [rsi + rdi + 34], 3 - pinsrw xmm2, word ptr [rsi + rbx + 34], 4 - pinsrw xmm2, word ptr [rsi + r15 + 34], 5 + pinsrw xmm2, word ptr [rsi + r9 + 34], 2 + pinsrw xmm2, word ptr [rsi + rbx + 34], 3 + pinsrw xmm2, word ptr [rsi + rdi + 34], 4 + pinsrw xmm2, word ptr [rsi + rax + 34], 5 pinsrw xmm2, word ptr [rsi + r12 + 34], 6 pinsrw xmm2, word ptr [rsi + r13 + 34], 7 movdqa xmm3, xmm0 pcmpgtw xmm3, xmm1 - movdqa xmmword ptr [rsp + 208], xmm3 # 16-byte Spill + movdqa xmmword ptr [rsp + 272], xmm3 # 16-byte Spill movdqa xmm1, xmm0 pcmpgtw xmm1, xmm2 movdqa xmmword ptr [rsp + 256], xmm1 # 16-byte Spill - movzx eax, word ptr [rsi + r9 + 36] - movd xmm1, eax + movzx edx, word ptr [rsi + r8 + 36] + movd xmm1, edx pinsrw xmm1, word ptr [rsi + rcx + 36], 1 - pinsrw xmm1, word ptr [rsi + r8 + 36], 2 - pinsrw xmm1, word ptr [rsi + rdi + 36], 3 - pinsrw xmm1, word ptr [rsi + rbx + 36], 4 - pinsrw xmm1, word ptr [rsi + r15 + 36], 5 + pinsrw xmm1, word ptr [rsi + r9 + 36], 2 + pinsrw xmm1, word ptr [rsi + rbx + 36], 3 + pinsrw xmm1, word ptr [rsi + rdi + 36], 4 + pinsrw xmm1, word ptr [rsi + rax + 36], 5 pinsrw xmm1, word ptr [rsi + r12 + 36], 6 - movzx eax, word ptr [rsi + r9 + 38] + movzx edx, word ptr [rsi + r8 + 38] pinsrw xmm1, word ptr [rsi + r13 + 36], 7 - movd xmm2, eax + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 38], 1 - pinsrw xmm2, word ptr [rsi + r8 + 38], 2 - pinsrw xmm2, word ptr [rsi + rdi + 38], 3 - pinsrw xmm2, word ptr [rsi + rbx + 38], 4 - pinsrw xmm2, word ptr [rsi + r15 + 38], 5 + pinsrw xmm2, word ptr [rsi + r9 + 38], 2 + pinsrw xmm2, word ptr [rsi + rbx + 38], 3 + pinsrw xmm2, word ptr [rsi + rdi + 38], 4 + pinsrw xmm2, word ptr [rsi + rax + 38], 5 pinsrw xmm2, word ptr [rsi + r12 + 38], 6 movdqa xmm3, xmm0 pcmpgtw xmm3, xmm1 - movdqa xmmword ptr [rsp + 288], xmm3 # 16-byte Spill + movdqa xmmword ptr [rsp + 336], xmm3 # 16-byte Spill pinsrw xmm2, word ptr [rsi + r13 + 38], 7 movdqa xmm1, xmm0 pcmpgtw xmm1, xmm2 - movdqa xmmword ptr [rsp + 304], xmm1 # 16-byte Spill - movzx eax, word ptr [rsi + r9 + 40] - movd xmm1, eax + movdqa xmmword ptr [rsp + 288], xmm1 # 16-byte Spill + movzx edx, word ptr [rsi + r8 + 40] + movd xmm1, edx pinsrw xmm1, word ptr [rsi + rcx + 40], 1 - pinsrw xmm1, word ptr [rsi + r8 + 40], 2 - pinsrw xmm1, word ptr [rsi + rdi + 40], 3 - pinsrw xmm1, word ptr [rsi + rbx + 40], 4 - pinsrw xmm1, word ptr [rsi + r15 + 40], 5 + pinsrw xmm1, word ptr [rsi + r9 + 40], 2 + pinsrw xmm1, word ptr [rsi + rbx + 40], 3 + pinsrw xmm1, word ptr [rsi + rdi + 40], 4 + pinsrw xmm1, word ptr [rsi + rax + 40], 5 pinsrw xmm1, word ptr [rsi + r12 + 40], 6 pinsrw xmm1, word ptr [rsi + r13 + 40], 7 - movzx eax, word ptr [rsi + r9 + 42] - movd xmm2, eax + movzx edx, word ptr [rsi + r8 + 42] + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 42], 1 - pinsrw xmm2, word ptr [rsi + r8 + 42], 2 - pinsrw xmm2, word ptr [rsi + rdi + 42], 3 - pinsrw xmm2, word ptr [rsi + rbx + 42], 4 - pinsrw xmm2, word ptr [rsi + r15 + 42], 5 + pinsrw xmm2, word ptr [rsi + r9 + 42], 2 + pinsrw xmm2, word ptr [rsi + rbx + 42], 3 + pinsrw xmm2, word ptr [rsi + rdi + 42], 4 + pinsrw xmm2, word ptr [rsi + rax + 42], 5 pinsrw xmm2, word ptr [rsi + r12 + 42], 6 pinsrw xmm2, word ptr [rsi + r13 + 42], 7 movdqa xmm3, xmm0 pcmpgtw xmm3, xmm1 - movdqa xmmword ptr [rsp + 336], xmm3 # 16-byte Spill + movdqa xmmword ptr [rsp + 240], xmm3 # 16-byte Spill movdqa xmm1, xmm0 pcmpgtw xmm1, xmm2 - movdqa xmmword ptr [rsp + 272], xmm1 # 16-byte Spill - movzx eax, word ptr [rsi + r9 + 44] - movd xmm1, eax + movdqa xmmword ptr [rsp + 320], xmm1 # 16-byte Spill + movzx edx, word ptr [rsi + r8 + 44] + movd xmm1, edx pinsrw xmm1, word ptr [rsi + rcx + 44], 1 - pinsrw xmm1, word ptr [rsi + r8 + 44], 2 - pinsrw xmm1, word ptr [rsi + rdi + 44], 3 - pinsrw xmm1, word ptr [rsi + rbx + 44], 4 - pinsrw xmm1, word ptr [rsi + r15 + 44], 5 + pinsrw xmm1, word ptr [rsi + r9 + 44], 2 + pinsrw xmm1, word ptr [rsi + rbx + 44], 3 + pinsrw xmm1, word ptr [rsi + rdi + 44], 4 + pinsrw xmm1, word ptr [rsi + rax + 44], 5 pinsrw xmm1, word ptr [rsi + r12 + 44], 6 - movzx eax, word ptr [rsi + r9 + 46] + movzx edx, word ptr [rsi + r8 + 46] pinsrw xmm1, word ptr [rsi + r13 + 44], 7 - movd xmm2, eax + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 46], 1 - pinsrw xmm2, word ptr [rsi + r8 + 46], 2 - pinsrw xmm2, word ptr [rsi + rdi + 46], 3 - pinsrw xmm2, word ptr [rsi + rbx + 46], 4 - pinsrw xmm2, word ptr [rsi + r15 + 46], 5 + pinsrw xmm2, word ptr [rsi + r9 + 46], 2 + pinsrw xmm2, word ptr [rsi + rbx + 46], 3 + pinsrw xmm2, word ptr [rsi + rdi + 46], 4 + pinsrw xmm2, word ptr [rsi + rax + 46], 5 pinsrw xmm2, word ptr [rsi + r12 + 46], 6 movdqa xmm3, xmm0 pcmpgtw xmm3, xmm1 - movdqa xmmword ptr [rsp + 320], xmm3 # 16-byte Spill + movdqa xmmword ptr [rsp + 352], xmm3 # 16-byte Spill pinsrw xmm2, word ptr [rsi + r13 + 46], 7 movdqa xmm1, xmm0 pcmpgtw xmm1, xmm2 - movdqa xmmword ptr [rsp + 240], xmm1 # 16-byte Spill - movzx eax, word ptr [rsi + r9 + 48] - movd xmm1, eax + movdqa xmmword ptr [rsp + 304], xmm1 # 16-byte Spill + movzx edx, word ptr [rsi + r8 + 48] + movd xmm1, edx pinsrw xmm1, word ptr [rsi + rcx + 48], 1 - pinsrw xmm1, word ptr [rsi + r8 + 48], 2 - pinsrw xmm1, word ptr [rsi + rdi + 48], 3 - pinsrw xmm1, word ptr [rsi + rbx + 48], 4 - pinsrw xmm1, word ptr [rsi + r15 + 48], 5 + pinsrw xmm1, word ptr [rsi + r9 + 48], 2 + pinsrw xmm1, word ptr [rsi + rbx + 48], 3 + pinsrw xmm1, word ptr [rsi + rdi + 48], 4 + pinsrw xmm1, word ptr [rsi + rax + 48], 5 pinsrw xmm1, word ptr [rsi + r12 + 48], 6 pinsrw xmm1, word ptr [rsi + r13 + 48], 7 - movzx eax, word ptr [rsi + r9 + 50] - movd xmm2, eax + movzx edx, word ptr [rsi + r8 + 50] + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 50], 1 - pinsrw xmm2, word ptr [rsi + r8 + 50], 2 - pinsrw xmm2, word ptr [rsi + rdi + 50], 3 - pinsrw xmm2, word ptr [rsi + rbx + 50], 4 - pinsrw xmm2, word ptr [rsi + r15 + 50], 5 + pinsrw xmm2, word ptr [rsi + r9 + 50], 2 + pinsrw xmm2, word ptr [rsi + rbx + 50], 3 + pinsrw xmm2, word ptr [rsi + rdi + 50], 4 + pinsrw xmm2, word ptr [rsi + rax + 50], 5 pinsrw xmm2, word ptr [rsi + r12 + 50], 6 pinsrw xmm2, word ptr [rsi + r13 + 50], 7 movdqa xmm13, xmm0 pcmpgtw xmm13, xmm1 movdqa xmm1, xmm0 pcmpgtw xmm1, xmm2 - movdqa xmmword ptr [rsp + 368], xmm1 # 16-byte Spill - movzx eax, word ptr [rsi + r9 + 52] - movd xmm1, eax + movdqa xmmword ptr [rsp + 384], xmm1 # 16-byte Spill + movzx edx, word ptr [rsi + r8 + 52] + movd xmm1, edx pinsrw xmm1, word ptr [rsi + rcx + 52], 1 - pinsrw xmm1, word ptr [rsi + r8 + 52], 2 - pinsrw xmm1, word ptr [rsi + rdi + 52], 3 - pinsrw xmm1, word ptr [rsi + rbx + 52], 4 - pinsrw xmm1, word ptr [rsi + r15 + 52], 5 + pinsrw xmm1, word ptr [rsi + r9 + 52], 2 + pinsrw xmm1, word ptr [rsi + rbx + 52], 3 + pinsrw xmm1, word ptr [rsi + rdi + 52], 4 + pinsrw xmm1, word ptr [rsi + rax + 52], 5 pinsrw xmm1, word ptr [rsi + r12 + 52], 6 - movzx eax, word ptr [rsi + r9 + 54] + movzx edx, word ptr [rsi + r8 + 54] pinsrw xmm1, word ptr [rsi + r13 + 52], 7 - movd xmm2, eax + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 54], 1 - pinsrw xmm2, word ptr [rsi + r8 + 54], 2 - pinsrw xmm2, word ptr [rsi + rdi + 54], 3 - pinsrw xmm2, word ptr [rsi + rbx + 54], 4 - pinsrw xmm2, word ptr [rsi + r15 + 54], 5 + pinsrw xmm2, word ptr [rsi + r9 + 54], 2 + pinsrw xmm2, word ptr [rsi + rbx + 54], 3 + pinsrw xmm2, word ptr [rsi + rdi + 54], 4 + pinsrw xmm2, word ptr [rsi + rax + 54], 5 pinsrw xmm2, word ptr [rsi + r12 + 54], 6 movdqa xmm3, xmm0 pcmpgtw xmm3, xmm1 - movdqa xmmword ptr [rsp + 416], xmm3 # 16-byte Spill + movdqa xmmword ptr [rsp + 400], xmm3 # 16-byte Spill pinsrw xmm2, word ptr [rsi + r13 + 54], 7 movdqa xmm15, xmm0 pcmpgtw xmm15, xmm2 - movzx eax, word ptr [rsi + r9 + 56] - movd xmm1, eax + movzx edx, word ptr [rsi + r8 + 56] + movd xmm1, edx pinsrw xmm1, word ptr [rsi + rcx + 56], 1 - pinsrw xmm1, word ptr [rsi + r8 + 56], 2 - pinsrw xmm1, word ptr [rsi + rdi + 56], 3 - pinsrw xmm1, word ptr [rsi + rbx + 56], 4 - pinsrw xmm1, word ptr [rsi + r15 + 56], 5 + pinsrw xmm1, word ptr [rsi + r9 + 56], 2 + pinsrw xmm1, word ptr [rsi + rbx + 56], 3 + pinsrw xmm1, word ptr [rsi + rdi + 56], 4 + pinsrw xmm1, word ptr [rsi + rax + 56], 5 pinsrw xmm1, word ptr [rsi + r12 + 56], 6 pinsrw xmm1, word ptr [rsi + r13 + 56], 7 - movzx eax, word ptr [rsi + r9 + 58] - movd xmm2, eax + movzx edx, word ptr [rsi + r8 + 58] + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 58], 1 - pinsrw xmm2, word ptr [rsi + r8 + 58], 2 - pinsrw xmm2, word ptr [rsi + rdi + 58], 3 - pinsrw xmm2, word ptr [rsi + rbx + 58], 4 - pinsrw xmm2, word ptr [rsi + r15 + 58], 5 + pinsrw xmm2, word ptr [rsi + r9 + 58], 2 + pinsrw xmm2, word ptr [rsi + rbx + 58], 3 + pinsrw xmm2, word ptr [rsi + rdi + 58], 4 + pinsrw xmm2, word ptr [rsi + rax + 58], 5 pinsrw xmm2, word ptr [rsi + r12 + 58], 6 pinsrw xmm2, word ptr [rsi + r13 + 58], 7 movdqa xmm9, xmm0 pcmpgtw xmm9, xmm1 movdqa xmm12, xmm0 pcmpgtw xmm12, xmm2 - movzx eax, word ptr [rsi + r9 + 60] - movd xmm2, eax + movzx edx, word ptr [rsi + r8 + 60] + movd xmm2, edx pinsrw xmm2, word ptr [rsi + rcx + 60], 1 - pinsrw xmm2, word ptr [rsi + r8 + 60], 2 - pinsrw xmm2, word ptr [rsi + rdi + 60], 3 - pinsrw xmm2, word ptr [rsi + rbx + 60], 4 - pinsrw xmm2, word ptr [rsi + r15 + 60], 5 + pinsrw xmm2, word ptr [rsi + r9 + 60], 2 + pinsrw xmm2, word ptr [rsi + rbx + 60], 3 + pinsrw xmm2, word ptr [rsi + rdi + 60], 4 + pinsrw xmm2, word ptr [rsi + rax + 60], 5 pinsrw xmm2, word ptr [rsi + r12 + 60], 6 - movzx eax, word ptr [rsi + r9 + 62] + movzx edx, word ptr [rsi + r8 + 62] pinsrw xmm2, word ptr [rsi + r13 + 60], 7 - movd xmm7, eax + movd xmm7, edx pinsrw xmm7, word ptr [rsi + rcx + 62], 1 - pinsrw xmm7, word ptr [rsi + r8 + 62], 2 - pinsrw xmm7, word ptr [rsi + rdi + 62], 3 - pinsrw xmm7, word ptr [rsi + rbx + 62], 4 - pinsrw xmm7, word ptr [rsi + r15 + 62], 5 + pinsrw xmm7, word ptr [rsi + r9 + 62], 2 + pinsrw xmm7, word ptr [rsi + rbx + 62], 3 + pinsrw xmm7, word ptr [rsi + rdi + 62], 4 + pinsrw xmm7, word ptr [rsi + rax + 62], 5 pinsrw xmm7, word ptr [rsi + r12 + 62], 6 + mov r12, r15 movdqa xmm5, xmm0 pcmpgtw xmm5, xmm2 pinsrw xmm7, word ptr [rsi + r13 + 62], 7 @@ -54846,13 +54623,13 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movdqa xmm0, xmm11 pxor xmm4, xmm4 pblendvb xmm7, xmm4, xmm0 - movdqa xmm2, xmmword ptr [rsp + 80] # 16-byte Reload + movdqa xmm2, xmmword ptr [rsp + 96] # 16-byte Reload packsswb xmm2, xmm2 movdqa xmm1, xmmword ptr [rip + .LCPI10_9] # xmm1 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> movdqa xmm0, xmm2 pblendvb xmm1, xmm4, xmm0 pcmpeqd xmm2, xmm2 - movdqa xmm0, xmmword ptr [rsp + 352] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 16] # 16-byte Reload pxor xmm0, xmm2 pcmpeqd xmm8, xmm8 packsswb xmm0, xmm0 @@ -54863,7 +54640,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movdqa xmm0, xmm2 pblendvb xmm11, xmm4, xmm0 por xmm11, xmm1 - movdqa xmm2, xmmword ptr [rsp + 32] # 16-byte Reload + movdqa xmm2, xmmword ptr [rsp + 48] # 16-byte Reload packsswb xmm2, xmm2 movdqa xmm1, xmmword ptr [rip + .LCPI10_11] # xmm1 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> movdqa xmm0, xmm2 @@ -54881,35 +54658,35 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movdqa xmm0, xmm14 pblendvb xmm1, xmm4, xmm0 por xmm1, xmm7 - movdqa xmm2, xmmword ptr [rsp + 96] # 16-byte Reload + movdqa xmm2, xmmword ptr [rsp + 112] # 16-byte Reload packsswb xmm2, xmm2 movdqa xmm14, xmmword ptr [rip + .LCPI10_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> movdqa xmm0, xmm2 pblendvb xmm14, xmm4, xmm0 por xmm1, xmm11 - movdqa xmm0, xmmword ptr [rsp + 160] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload packsswb xmm0, xmm0 movdqa xmm11, xmm3 movdqa xmm7, xmm3 pblendvb xmm7, xmm4, xmm0 por xmm14, xmm1 - movdqa xmm0, xmmword ptr [rsp + 432] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload pxor xmm0, xmm8 packsswb xmm0, xmm0 psubb xmm7, xmm0 - movdqa xmm0, xmmword ptr [rsp + 48] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 80] # 16-byte Reload packsswb xmm0, xmm0 movdqa xmm3, xmmword ptr [rip + .LCPI10_9] # xmm3 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> movdqa xmm1, xmm3 pblendvb xmm1, xmm4, xmm0 - movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 160] # 16-byte Reload packsswb xmm0, xmm0 movdqa xmm8, xmmword ptr [rip + .LCPI10_10] # xmm8 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> movdqa xmm2, xmm8 pblendvb xmm2, xmm4, xmm0 por xmm2, xmm1 por xmm2, xmm7 - movdqa xmm0, xmmword ptr [rsp + 16] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 32] # 16-byte Reload packsswb xmm0, xmm0 movdqa xmm1, xmmword ptr [rip + .LCPI10_11] # xmm1 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> pblendvb xmm1, xmm4, xmm0 @@ -54923,7 +54700,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar pblendvb xmm1, xmm4, xmm0 por xmm1, xmm10 por xmm1, xmm2 - movdqa xmm0, xmmword ptr [rsp + 112] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload packsswb xmm0, xmm0 movdqa xmm10, xmmword ptr [rip + .LCPI10_14] # xmm10 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> pblendvb xmm10, xmm4, xmm0 @@ -54932,23 +54709,23 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm0, xmm0 movdqa xmm1, xmm11 pblendvb xmm1, xmm4, xmm0 - movdqa xmm0, xmmword ptr [rsp + 288] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 336] # 16-byte Reload packsswb xmm0, xmm0 movdqa xmm2, xmm3 pblendvb xmm2, xmm4, xmm0 - movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 272] # 16-byte Reload pxor xmm0, xmmword ptr [rip + .LCPI10_22] pcmpeqd xmm3, xmm3 packsswb xmm0, xmm0 psubb xmm1, xmm0 - movdqa xmm0, xmmword ptr [rsp + 304] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 288] # 16-byte Reload packsswb xmm0, xmm0 movdqa xmm7, xmm8 pblendvb xmm7, xmm4, xmm0 por xmm7, xmm2 - movdqa xmm0, xmmword ptr [rsp + 336] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 240] # 16-byte Reload packsswb xmm0, xmm0 - movdqa xmm11, xmmword ptr [rsp + 272] # 16-byte Reload + movdqa xmm11, xmmword ptr [rsp + 320] # 16-byte Reload packsswb xmm11, xmm11 por xmm7, xmm1 movdqa xmm1, xmmword ptr [rip + .LCPI10_11] # xmm1 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> @@ -54956,15 +54733,15 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movdqa xmm2, xmmword ptr [rip + .LCPI10_12] # xmm2 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> movdqa xmm0, xmm11 pblendvb xmm2, xmm4, xmm0 - movdqa xmm0, xmmword ptr [rsp + 320] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 352] # 16-byte Reload packsswb xmm0, xmm0 por xmm2, xmm1 movdqa xmm1, xmmword ptr [rip + .LCPI10_13] # xmm1 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> pblendvb xmm1, xmm4, xmm0 por xmm1, xmm2 - movdqa xmm0, xmmword ptr [rsp + 240] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 304] # 16-byte Reload packsswb xmm0, xmm0 - movdqa xmm11, xmmword ptr [rsp + 368] # 16-byte Reload + movdqa xmm11, xmmword ptr [rsp + 384] # 16-byte Reload packsswb xmm11, xmm11 por xmm1, xmm7 movdqa xmm7, xmmword ptr [rip + .LCPI10_14] # xmm7 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> @@ -54975,7 +54752,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar por xmm7, xmm1 pxor xmm13, xmm3 packsswb xmm13, xmm13 - movdqa xmm0, xmmword ptr [rsp + 416] # 16-byte Reload + movdqa xmm0, xmmword ptr [rsp + 400] # 16-byte Reload packsswb xmm0, xmm0 packsswb xmm15, xmm15 psubb xmm2, xmm13 @@ -55016,32 +54793,32 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar punpcklbw xmm7, xmm2 # xmm7 = xmm7[0],xmm2[0],xmm7[1],xmm2[1],xmm7[2],xmm2[2],xmm7[3],xmm2[3],xmm7[4],xmm2[4],xmm7[5],xmm2[5],xmm7[6],xmm2[6],xmm7[7],xmm2[7] punpcklbw xmm14, xmm10 # xmm14 = xmm14[0],xmm10[0],xmm14[1],xmm10[1],xmm14[2],xmm10[2],xmm14[3],xmm10[3],xmm14[4],xmm10[4],xmm14[5],xmm10[5],xmm14[6],xmm10[6],xmm14[7],xmm10[7] punpcklwd xmm14, xmm7 # xmm14 = xmm14[0],xmm7[0],xmm14[1],xmm7[1],xmm14[2],xmm7[2],xmm14[3],xmm7[3] - movdqu xmmword ptr [r14 + 4*r10], xmm14 - movdqu xmmword ptr [r14 + 4*r10 + 16], xmm0 + movdqu xmmword ptr [r15 + 4*r10], xmm14 + movdqu xmmword ptr [r15 + 4*r10 + 16], xmm0 add r10, 8 - cmp r10, qword ptr [rsp + 400] # 8-byte Folded Reload - jne .LBB10_125 -# %bb.126: - mov r15, qword ptr [rsp + 456] # 8-byte Reload - cmp r15, qword ptr [rsp + 400] # 8-byte Folded Reload - mov r10, qword ptr [rsp + 72] # 8-byte Reload - mov r12, qword ptr [rsp + 8] # 8-byte Reload - jne .LBB10_127 - jmp .LBB10_130 -.LBB10_182: - mov rax, r11 + cmp r10, qword ptr [rsp + 376] # 8-byte Folded Reload + jne .LBB10_144 +# %bb.145: + mov rcx, qword ptr [rsp + 440] # 8-byte Reload + cmp rcx, qword ptr [rsp + 376] # 8-byte Folded Reload + mov r14, qword ptr [rsp + 72] # 8-byte Reload + mov r15d, dword ptr [rsp] # 4-byte Reload + jne .LBB10_146 + jmp .LBB10_149 +.LBB10_207: + mov rax, rdi and rax, -4 - mov rdx, rax - shl rdx, 7 - add rdx, rsi - lea r15, [r14 + 4*rax] - movaps xmm13, xmm11 - shufps xmm13, xmm11, 0 # xmm13 = xmm13[0,0],xmm11[0,0] + mov rcx, rax + shl rcx, 7 + add rcx, rsi + lea r11, [r12 + 4*rax] + movdqa xmm14, xmm11 + shufps xmm14, xmm11, 0 # xmm14 = xmm14[0,0],xmm11[0,0] add rsi, 508 - xor ecx, ecx + xor edx, edx movdqa xmm15, xmmword ptr [rip + .LCPI10_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> .p2align 4, 0x90 -.LBB10_183: # =>This Inner Loop Header: Depth=1 +.LBB10_208: # =>This Inner Loop Header: Depth=1 movss xmm3, dword ptr [rsi - 508] # xmm3 = mem[0],zero,zero,zero movss xmm10, dword ptr [rsi - 504] # xmm10 = mem[0],zero,zero,zero movss xmm9, dword ptr [rsi - 500] # xmm9 = mem[0],zero,zero,zero @@ -55061,7 +54838,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movss xmm8, dword ptr [rsi - 492] # xmm8 = mem[0],zero,zero,zero insertps xmm8, dword ptr [rsi - 364], 16 # xmm8 = xmm8[0],mem[0],xmm8[2,3] insertps xmm8, dword ptr [rsi - 236], 32 # xmm8 = xmm8[0,1],mem[0],xmm8[3] - movaps xmm12, xmm13 + movaps xmm12, xmm14 insertps xmm8, dword ptr [rsi - 108], 48 # xmm8 = xmm8[0,1,2],mem[0] movss xmm2, dword ptr [rsi - 488] # xmm2 = mem[0],zero,zero,zero insertps xmm2, dword ptr [rsi - 360], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] @@ -55078,45 +54855,45 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar insertps xmm4, dword ptr [rsi - 220], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] packsswb xmm12, xmm12 insertps xmm4, dword ptr [rsi - 92], 48 # xmm4 = xmm4[0,1,2],mem[0] - movaps xmm7, xmm13 + movaps xmm7, xmm14 movss xmm5, dword ptr [rsi - 444] # xmm5 = mem[0],zero,zero,zero insertps xmm5, dword ptr [rsi - 316], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] insertps xmm5, dword ptr [rsi - 188], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] cmpleps xmm7, xmm4 insertps xmm5, dword ptr [rsi - 60], 48 # xmm5 = xmm5[0,1,2],mem[0] - movaps xmm6, xmm13 - movss xmm0, dword ptr [rsi - 412] # xmm0 = mem[0],zero,zero,zero - insertps xmm0, dword ptr [rsi - 284], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] - insertps xmm0, dword ptr [rsi - 156], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] + movaps xmm6, xmm14 + movss xmm13, dword ptr [rsi - 412] # xmm13 = mem[0],zero,zero,zero + insertps xmm13, dword ptr [rsi - 284], 16 # xmm13 = xmm13[0],mem[0],xmm13[2,3] + insertps xmm13, dword ptr [rsi - 156], 32 # xmm13 = xmm13[0,1],mem[0],xmm13[3] cmpleps xmm6, xmm5 - insertps xmm0, dword ptr [rsi - 28], 48 # xmm0 = xmm0[0,1,2],mem[0] - movaps xmm4, xmm13 - cmpleps xmm4, xmm0 - movaps xmm0, xmm13 - cmpleps xmm0, xmm10 - packssdw xmm0, xmm0 - packsswb xmm0, xmm0 - movdqa xmm14, xmm0 - pand xmm14, xmm15 - psubb xmm14, xmm0 + insertps xmm13, dword ptr [rsi - 28], 48 # xmm13 = xmm13[0,1,2],mem[0] + movaps xmm4, xmm14 + cmpleps xmm4, xmm13 + movaps xmm5, xmm14 + cmpleps xmm5, xmm10 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + movdqa xmm0, xmm5 + pand xmm0, xmm15 + psubb xmm0, xmm5 movss xmm10, dword ptr [rsi - 480] # xmm10 = mem[0],zero,zero,zero insertps xmm10, dword ptr [rsi - 352], 16 # xmm10 = xmm10[0],mem[0],xmm10[2,3] pand xmm12, xmm15 insertps xmm10, dword ptr [rsi - 224], 32 # xmm10 = xmm10[0,1],mem[0],xmm10[3] - por xmm14, xmm12 - movaps xmm5, xmm13 + por xmm0, xmm12 + movaps xmm5, xmm14 cmpleps xmm5, xmm9 insertps xmm10, dword ptr [rsi - 96], 48 # xmm10 = xmm10[0,1,2],mem[0] packssdw xmm5, xmm5 packsswb xmm5, xmm5 pand xmm5, xmm15 psllw xmm5, 2 - movdqa xmm0, xmmword ptr [rip + .LCPI10_1] # xmm0 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - pand xmm5, xmm0 - por xmm5, xmm14 - movaps xmm0, xmm13 + movdqa xmm13, xmmword ptr [rip + .LCPI10_1] # xmm13 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + pand xmm5, xmm13 + por xmm5, xmm0 + movaps xmm0, xmm14 cmpleps xmm0, xmm1 - movaps xmm1, xmm13 + movaps xmm1, xmm14 cmpleps xmm1, xmm8 movss xmm9, dword ptr [rsi - 472] # xmm9 = mem[0],zero,zero,zero insertps xmm9, dword ptr [rsi - 344], 16 # xmm9 = xmm9[0],mem[0],xmm9[2,3] @@ -55126,23 +54903,23 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 3 - movdqa xmm14, xmmword ptr [rip + .LCPI10_2] # xmm14 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - pand xmm0, xmm14 + movdqa xmm13, xmmword ptr [rip + .LCPI10_2] # xmm13 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + pand xmm0, xmm13 packssdw xmm1, xmm1 packsswb xmm1, xmm1 pand xmm1, xmm15 psllw xmm1, 4 - movdqa xmm14, xmmword ptr [rip + .LCPI10_3] # xmm14 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - pand xmm1, xmm14 + movdqa xmm13, xmmword ptr [rip + .LCPI10_3] # xmm13 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + pand xmm1, xmm13 por xmm1, xmm0 movss xmm12, dword ptr [rsi - 468] # xmm12 = mem[0],zero,zero,zero insertps xmm12, dword ptr [rsi - 340], 16 # xmm12 = xmm12[0],mem[0],xmm12[2,3] insertps xmm12, dword ptr [rsi - 212], 32 # xmm12 = xmm12[0,1],mem[0],xmm12[3] insertps xmm12, dword ptr [rsi - 84], 48 # xmm12 = xmm12[0,1,2],mem[0] por xmm1, xmm5 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm2 - movaps xmm5, xmm13 + movaps xmm5, xmm14 cmpleps xmm5, xmm3 movss xmm2, dword ptr [rsi - 464] # xmm2 = mem[0],zero,zero,zero insertps xmm2, dword ptr [rsi - 336], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] @@ -55153,8 +54930,8 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 5 - movdqa xmm14, xmmword ptr [rip + .LCPI10_4] # xmm14 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - pand xmm0, xmm14 + movdqa xmm13, xmmword ptr [rip + .LCPI10_4] # xmm13 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + pand xmm0, xmm13 packssdw xmm5, xmm5 packsswb xmm5, xmm5 pand xmm5, xmm15 @@ -55162,7 +54939,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movdqa xmm3, xmmword ptr [rip + .LCPI10_5] # xmm3 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] pand xmm5, xmm3 por xmm5, xmm0 - movaps xmm8, xmm13 + movaps xmm8, xmm14 cmpleps xmm8, xmm10 movss xmm3, dword ptr [rsi - 460] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 332], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -55180,7 +54957,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm7, xmm7 insertps xmm10, dword ptr [rsi - 72], 48 # xmm10 = xmm10[0,1,2],mem[0] por xmm8, xmm1 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm9 packssdw xmm0, xmm0 packsswb xmm0, xmm0 @@ -55192,7 +54969,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar pand xmm7, xmm15 insertps xmm9, dword ptr [rsi - 196], 32 # xmm9 = xmm9[0,1],mem[0],xmm9[3] por xmm1, xmm7 - movaps xmm5, xmm13 + movaps xmm5, xmm14 cmpleps xmm5, xmm12 insertps xmm9, dword ptr [rsi - 68], 48 # xmm9 = xmm9[0,1,2],mem[0] packssdw xmm5, xmm5 @@ -55201,9 +54978,9 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar psllw xmm5, 2 pand xmm5, xmmword ptr [rip + .LCPI10_1] por xmm5, xmm1 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm2 - movaps xmm1, xmm13 + movaps xmm1, xmm14 cmpleps xmm1, xmm3 movss xmm3, dword ptr [rsi - 448] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 320], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -55226,9 +55003,9 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar insertps xmm2, dword ptr [rsi - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] insertps xmm2, dword ptr [rsi - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] por xmm1, xmm5 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm10 - movaps xmm5, xmm13 + movaps xmm5, xmm14 cmpleps xmm5, xmm9 movss xmm7, dword ptr [rsi - 436] # xmm7 = mem[0],zero,zero,zero insertps xmm7, dword ptr [rsi - 308], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] @@ -55239,14 +55016,14 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 5 - pand xmm0, xmm14 + pand xmm0, xmm13 packssdw xmm5, xmm5 packsswb xmm5, xmm5 pand xmm5, xmm15 psllw xmm5, 6 pand xmm5, xmmword ptr [rip + .LCPI10_5] por xmm5, xmm0 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm3 movss xmm3, dword ptr [rsi - 432] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 304], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -55269,7 +55046,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm6, xmm6 insertps xmm9, dword ptr [rsi - 40], 48 # xmm9 = xmm9[0,1,2],mem[0] punpckldq xmm8, xmm0 # xmm8 = xmm8[0],xmm0[0],xmm8[1],xmm0[1] - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm2 packssdw xmm0, xmm0 packsswb xmm0, xmm0 @@ -55281,7 +55058,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar pand xmm6, xmm15 insertps xmm2, dword ptr [rsi - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] por xmm1, xmm6 - movaps xmm6, xmm13 + movaps xmm6, xmm14 cmpleps xmm6, xmm7 insertps xmm2, dword ptr [rsi - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] packssdw xmm6, xmm6 @@ -55291,9 +55068,9 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movdqa xmm0, xmmword ptr [rip + .LCPI10_1] # xmm0 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] pand xmm6, xmm0 por xmm6, xmm1 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm3 - movaps xmm1, xmm13 + movaps xmm1, xmm14 cmpleps xmm1, xmm5 movss xmm3, dword ptr [rsi - 416] # xmm3 = mem[0],zero,zero,zero insertps xmm3, dword ptr [rsi - 288], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] @@ -55316,9 +55093,9 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar insertps xmm5, dword ptr [rsi - 152], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] insertps xmm5, dword ptr [rsi - 24], 48 # xmm5 = xmm5[0,1,2],mem[0] por xmm1, xmm6 - movaps xmm0, xmm13 + movaps xmm0, xmm14 cmpleps xmm0, xmm9 - movaps xmm6, xmm13 + movaps xmm6, xmm14 cmpleps xmm6, xmm2 movss xmm7, dword ptr [rsi - 404] # xmm7 = mem[0],zero,zero,zero insertps xmm7, dword ptr [rsi - 276], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] @@ -55329,7 +55106,7 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm0, xmm0 pand xmm0, xmm15 psllw xmm0, 5 - pand xmm0, xmm14 + pand xmm0, xmm13 packssdw xmm6, xmm6 packsswb xmm6, xmm6 pand xmm6, xmm15 @@ -55337,12 +55114,12 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar movdqa xmm9, xmmword ptr [rip + .LCPI10_5] # xmm9 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] pand xmm6, xmm9 por xmm6, xmm0 - movaps xmm2, xmm13 + movaps xmm2, xmm14 cmpleps xmm2, xmm3 - movss xmm0, dword ptr [rsi - 400] # xmm0 = mem[0],zero,zero,zero - insertps xmm0, dword ptr [rsi - 272], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] - insertps xmm0, dword ptr [rsi - 144], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] - insertps xmm0, dword ptr [rsi - 16], 48 # xmm0 = xmm0[0,1,2],mem[0] + movss xmm3, dword ptr [rsi - 400] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 272], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 144], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rsi - 16], 48 # xmm3 = xmm3[0,1,2],mem[0] packssdw xmm2, xmm2 packsswb xmm2, xmm2 psllw xmm2, 7 @@ -55354,86 +55131,1919 @@ comparison_greater_equal_arr_scalar_sse4: # @comparison_greater_equal_arr_scalar packsswb xmm4, xmm4 insertps xmm6, dword ptr [rsi - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] por xmm2, xmm1 - movaps xmm1, xmm13 - cmpleps xmm1, xmm5 + movaps xmm0, xmm14 + cmpleps xmm0, xmm5 + packssdw xmm0, xmm0 + packsswb xmm0, xmm0 + movdqa xmm1, xmm0 + pand xmm1, xmm15 + psubb xmm1, xmm0 + movss xmm5, dword ptr [rsi - 392] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rsi - 264], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + pand xmm4, xmm15 + insertps xmm5, dword ptr [rsi - 136], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + por xmm1, xmm4 + movaps xmm4, xmm14 + cmpleps xmm4, xmm7 + insertps xmm5, dword ptr [rsi - 8], 48 # xmm5 = xmm5[0,1,2],mem[0] + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + psllw xmm4, 2 + pand xmm4, xmmword ptr [rip + .LCPI10_1] + por xmm4, xmm1 + movaps xmm0, xmm14 + cmpleps xmm0, xmm3 + movaps xmm1, xmm14 + cmpleps xmm1, xmm6 + movss xmm3, dword ptr [rsi - 388] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rsi - 260], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rsi - 132], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rsi - 4], 48 # xmm3 = xmm3[0,1,2],mem[0] + packssdw xmm0, xmm0 + packsswb xmm0, xmm0 + pand xmm0, xmm15 + psllw xmm0, 3 + pand xmm0, xmmword ptr [rip + .LCPI10_2] packssdw xmm1, xmm1 packsswb xmm1, xmm1 + pand xmm1, xmm15 + psllw xmm1, 4 + pand xmm1, xmm12 + por xmm1, xmm0 + movss xmm0, dword ptr [rsi - 384] # xmm0 = mem[0],zero,zero,zero + insertps xmm0, dword ptr [rsi - 256], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] + insertps xmm0, dword ptr [rsi - 128], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] + por xmm1, xmm4 + movaps xmm4, xmm14 + cmpleps xmm4, xmm5 + movaps xmm5, xmm14 + cmpleps xmm5, xmm3 + insertps xmm0, dword ptr [rsi], 48 # xmm0 = xmm0[0,1,2],mem[0] + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + psllw xmm4, 5 + pand xmm4, xmm13 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 6 + pand xmm5, xmm9 + por xmm5, xmm4 + movaps xmm3, xmm14 + cmpleps xmm3, xmm0 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + psllw xmm3, 7 + pand xmm3, xmm10 + por xmm3, xmm5 + por xmm3, xmm1 + punpckldq xmm2, xmm3 # xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1] + punpcklbw xmm8, xmm2 # xmm8 = xmm8[0],xmm2[0],xmm8[1],xmm2[1],xmm8[2],xmm2[2],xmm8[3],xmm2[3],xmm8[4],xmm2[4],xmm8[5],xmm2[5],xmm8[6],xmm2[6],xmm8[7],xmm2[7] + pshufb xmm8, xmmword ptr [rip + .LCPI10_7] # xmm8 = xmm8[0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] + movdqu xmmword ptr [r12 + 4*rdx], xmm8 + add rdx, 4 + add rsi, 512 + cmp rax, rdx + jne .LBB10_208 +# %bb.209: + cmp rdi, rax + jne .LBB10_210 + jmp .LBB10_213 +.LBB10_98: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, rdi + mov qword ptr [rsp + 376], rax # 8-byte Spill + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 112], rax # 8-byte Spill + movzx eax, r15b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill + xor r8d, r8d + mov qword ptr [rsp + 8], r12 # 8-byte Spill + .p2align 4, 0x90 +.LBB10_99: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 224], r8 # 8-byte Spill + shl r8, 5 + mov qword ptr [rsp + 192], r8 # 8-byte Spill + mov rsi, r8 + mov qword ptr [rsp + 128], r8 # 8-byte Spill + mov r12, r8 + mov r15, r8 + mov r14, r8 + mov rbx, r8 + mov r11, r8 + mov rdx, r8 + mov r10, r8 + mov qword ptr [rsp + 144], r8 # 8-byte Spill + movzx eax, byte ptr [rdi + r8] + movd xmm9, eax + movzx eax, byte ptr [rdi + r8 + 1] + movd xmm2, eax + movzx eax, byte ptr [rdi + r8 + 2] + movd xmm3, eax + movzx eax, byte ptr [rdi + r8 + 3] + movd xmm4, eax + movzx eax, byte ptr [rdi + r8 + 4] + movd xmm6, eax + movzx eax, byte ptr [rdi + r8 + 5] + movd xmm0, eax + movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill + movzx eax, byte ptr [rdi + r8 + 6] + movd xmm7, eax + movzx eax, byte ptr [rdi + r8 + 7] + movd xmm0, eax + movdqa xmmword ptr [rsp + 272], xmm0 # 16-byte Spill + movzx eax, byte ptr [rdi + r8 + 8] + movd xmm13, eax + movzx eax, byte ptr [rdi + r8 + 9] + movd xmm8, eax + movzx eax, byte ptr [rdi + r8 + 10] + movd xmm10, eax + movzx eax, byte ptr [rdi + r8 + 11] + movd xmm1, eax + movzx eax, byte ptr [rdi + r8 + 12] + movd xmm12, eax + movzx eax, byte ptr [rdi + r8 + 16] + movd xmm14, eax + mov qword ptr [rsp + 208], r8 # 8-byte Spill + movzx eax, byte ptr [rdi + r8 + 24] + movd xmm5, eax + mov rax, r8 + or rax, 32 + mov r13, rax + mov qword ptr [rsp + 96], rax # 8-byte Spill + mov r9, qword ptr [rsp + 192] # 8-byte Reload + or r9, 64 + mov qword ptr [rsp + 192], r9 # 8-byte Spill + or rsi, 96 + mov qword ptr [rsp + 176], rsi # 8-byte Spill + mov rcx, rsi + mov rax, qword ptr [rsp + 128] # 8-byte Reload + or rax, 128 + mov qword ptr [rsp + 128], rax # 8-byte Spill + or r12, 160 + mov qword ptr [rsp + 352], r12 # 8-byte Spill + or r15, 192 + or r14, 224 + or rbx, 256 + or r11, 288 + or rdx, 320 + or r10, 352 + or qword ptr [rsp + 144], 384 # 8-byte Folded Spill + mov rsi, r8 + or rsi, 416 + mov qword ptr [rsp + 16], rsi # 8-byte Spill + mov rsi, r8 + or rsi, 448 + mov qword ptr [rsp + 80], rsi # 8-byte Spill + mov rsi, r8 + or rsi, 480 + pinsrb xmm9, byte ptr [rdi + r13], 1 + pinsrb xmm9, byte ptr [rdi + r9], 2 + pinsrb xmm9, byte ptr [rdi + rcx], 3 + pinsrb xmm9, byte ptr [rdi + rax], 4 + pinsrb xmm9, byte ptr [rdi + r12], 5 + pinsrb xmm9, byte ptr [rdi + r15], 6 + pinsrb xmm9, byte ptr [rdi + r14], 7 + pinsrb xmm9, byte ptr [rdi + rbx], 8 + pinsrb xmm9, byte ptr [rdi + r11], 9 + pinsrb xmm9, byte ptr [rdi + rdx], 10 + pinsrb xmm9, byte ptr [rdi + r10], 11 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r8], 12 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + r13], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm9, byte ptr [rdi + rcx], 14 + mov qword ptr [rsp + 32], rsi # 8-byte Spill + pinsrb xmm9, byte ptr [rdi + rsi], 15 + movdqa xmm15, xmmword ptr [rsp + 416] # 16-byte Reload + movdqa xmm11, xmm15 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rcx + 1], 1 + pinsrb xmm2, byte ptr [rdi + r9 + 1], 2 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rcx + 1], 3 + pinsrb xmm2, byte ptr [rdi + rax + 1], 4 + pinsrb xmm2, byte ptr [rdi + r12 + 1], 5 + pinsrb xmm2, byte ptr [rdi + r15 + 1], 6 + pinsrb xmm2, byte ptr [rdi + r14 + 1], 7 + pinsrb xmm2, byte ptr [rdi + rbx + 1], 8 + pinsrb xmm2, byte ptr [rdi + r11 + 1], 9 + pinsrb xmm2, byte ptr [rdi + rdx + 1], 10 + pinsrb xmm2, byte ptr [rdi + r10 + 1], 11 + pinsrb xmm2, byte ptr [rdi + r8 + 1], 12 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r13 + 1], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rcx + 1], 14 + pinsrb xmm2, byte ptr [rdi + rsi + 1], 15 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rcx + 2], 1 + pinsrb xmm3, byte ptr [rdi + r9 + 2], 2 + mov r13, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r13 + 2], 3 + pinsrb xmm3, byte ptr [rdi + rax + 2], 4 + pinsrb xmm3, byte ptr [rdi + r12 + 2], 5 + pinsrb xmm3, byte ptr [rdi + r15 + 2], 6 + pinsrb xmm3, byte ptr [rdi + r14 + 2], 7 + pinsrb xmm3, byte ptr [rdi + rbx + 2], 8 + pinsrb xmm3, byte ptr [rdi + r11 + 2], 9 + pinsrb xmm3, byte ptr [rdi + rdx + 2], 10 + pinsrb xmm3, byte ptr [rdi + r10 + 2], 11 + pinsrb xmm3, byte ptr [rdi + r8 + 2], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rcx + 2], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rcx + 2], 14 + pinsrb xmm3, byte ptr [rdi + rsi + 2], 15 + movdqa xmm0, xmm3 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rcx + 3], 1 + pinsrb xmm4, byte ptr [rdi + r9 + 3], 2 + pinsrb xmm4, byte ptr [rdi + r13 + 3], 3 + pinsrb xmm4, byte ptr [rdi + rax + 3], 4 + pinsrb xmm4, byte ptr [rdi + r12 + 3], 5 + pinsrb xmm4, byte ptr [rdi + r15 + 3], 6 + pinsrb xmm4, byte ptr [rdi + r14 + 3], 7 + pinsrb xmm4, byte ptr [rdi + rbx + 3], 8 + pinsrb xmm4, byte ptr [rdi + r11 + 3], 9 + pinsrb xmm4, byte ptr [rdi + rdx + 3], 10 + pinsrb xmm4, byte ptr [rdi + r10 + 3], 11 + pinsrb xmm4, byte ptr [rdi + r8 + 3], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rcx + 3], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rcx + 3], 14 + pinsrb xmm4, byte ptr [rdi + rsi + 3], 15 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rcx + 4], 1 + pinsrb xmm6, byte ptr [rdi + r9 + 4], 2 + pinsrb xmm6, byte ptr [rdi + r13 + 4], 3 + pinsrb xmm6, byte ptr [rdi + rax + 4], 4 + pinsrb xmm6, byte ptr [rdi + r12 + 4], 5 + pinsrb xmm6, byte ptr [rdi + r15 + 4], 6 + pinsrb xmm6, byte ptr [rdi + r14 + 4], 7 + pinsrb xmm6, byte ptr [rdi + rbx + 4], 8 + pinsrb xmm6, byte ptr [rdi + r11 + 4], 9 + pinsrb xmm6, byte ptr [rdi + rdx + 4], 10 + pinsrb xmm6, byte ptr [rdi + r10 + 4], 11 + pinsrb xmm6, byte ptr [rdi + r8 + 4], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rcx + 4], 13 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rcx + 4], 14 + pinsrb xmm6, byte ptr [rdi + rsi + 4], 15 + movdqa xmm3, xmmword ptr [rsp + 160] # 16-byte Reload + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rcx + 5], 1 + pinsrb xmm3, byte ptr [rdi + r9 + 5], 2 + pinsrb xmm3, byte ptr [rdi + r13 + 5], 3 + pinsrb xmm3, byte ptr [rdi + rax + 5], 4 + pinsrb xmm3, byte ptr [rdi + r12 + 5], 5 + pinsrb xmm3, byte ptr [rdi + r15 + 5], 6 + pinsrb xmm3, byte ptr [rdi + r14 + 5], 7 + pinsrb xmm3, byte ptr [rdi + rbx + 5], 8 + pinsrb xmm3, byte ptr [rdi + r11 + 5], 9 + pinsrb xmm3, byte ptr [rdi + rdx + 5], 10 + pinsrb xmm3, byte ptr [rdi + r10 + 5], 11 + pinsrb xmm3, byte ptr [rdi + r8 + 5], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rcx + 5], 13 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r13 + 5], 14 + pinsrb xmm3, byte ptr [rdi + rsi + 5], 15 + movdqa xmmword ptr [rsp + 160], xmm3 # 16-byte Spill + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 6], 1 + pinsrb xmm7, byte ptr [rdi + r9 + 6], 2 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rcx + 6], 3 + pinsrb xmm7, byte ptr [rdi + rax + 6], 4 + pinsrb xmm7, byte ptr [rdi + r12 + 6], 5 + pinsrb xmm7, byte ptr [rdi + r15 + 6], 6 + pinsrb xmm7, byte ptr [rdi + r14 + 6], 7 + pinsrb xmm7, byte ptr [rdi + rbx + 6], 8 + pinsrb xmm7, byte ptr [rdi + r11 + 6], 9 + pinsrb xmm7, byte ptr [rdi + rdx + 6], 10 + pinsrb xmm7, byte ptr [rdi + r10 + 6], 11 + pinsrb xmm7, byte ptr [rdi + r8 + 6], 12 + pinsrb xmm13, byte ptr [rdi + rsi + 8], 1 + pinsrb xmm13, byte ptr [rdi + r9 + 8], 2 + pinsrb xmm13, byte ptr [rdi + rcx + 8], 3 + pinsrb xmm13, byte ptr [rdi + rax + 8], 4 + pinsrb xmm13, byte ptr [rdi + r12 + 8], 5 + pinsrb xmm13, byte ptr [rdi + r15 + 8], 6 + pinsrb xmm13, byte ptr [rdi + r14 + 8], 7 + pinsrb xmm13, byte ptr [rdi + rbx + 8], 8 + pinsrb xmm13, byte ptr [rdi + r11 + 8], 9 + pinsrb xmm13, byte ptr [rdi + rdx + 8], 10 + pinsrb xmm13, byte ptr [rdi + r10 + 8], 11 + pinsrb xmm13, byte ptr [rdi + r8 + 8], 12 + mov r8, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r8 + 8], 13 + pinsrb xmm13, byte ptr [rdi + r13 + 8], 14 + pcmpgtb xmm11, xmm9 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r13 + 8], 15 + movdqa xmm9, xmm15 + pcmpgtb xmm9, xmm13 + pinsrb xmm14, byte ptr [rdi + rsi + 16], 1 + pinsrb xmm14, byte ptr [rdi + r9 + 16], 2 + pinsrb xmm14, byte ptr [rdi + rcx + 16], 3 + pinsrb xmm14, byte ptr [rdi + rax + 16], 4 + pinsrb xmm14, byte ptr [rdi + r12 + 16], 5 + pinsrb xmm14, byte ptr [rdi + r15 + 16], 6 + mov qword ptr [rsp + 240], r15 # 8-byte Spill + pinsrb xmm14, byte ptr [rdi + r14 + 16], 7 + mov r12, r14 + mov qword ptr [rsp + 336], r14 # 8-byte Spill + pinsrb xmm14, byte ptr [rdi + rbx + 16], 8 + mov qword ptr [rsp + 320], rbx # 8-byte Spill + pinsrb xmm14, byte ptr [rdi + r11 + 16], 9 + pinsrb xmm14, byte ptr [rdi + rdx + 16], 10 + mov qword ptr [rsp + 48], rdx # 8-byte Spill + pinsrb xmm14, byte ptr [rdi + r10 + 16], 11 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rax + 16], 12 + pinsrb xmm14, byte ptr [rdi + r8 + 16], 13 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r13 + 16], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rsi + 16], 15 + movdqa xmm3, xmm15 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r14 + 24], 1 + pinsrb xmm5, byte ptr [rdi + r9 + 24], 2 + pinsrb xmm5, byte ptr [rdi + rcx + 24], 3 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rcx + 24], 4 + mov r9, qword ptr [rsp + 352] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r9 + 24], 5 + pinsrb xmm5, byte ptr [rdi + r15 + 24], 6 + pinsrb xmm5, byte ptr [rdi + r12 + 24], 7 + pinsrb xmm5, byte ptr [rdi + rbx + 24], 8 + pinsrb xmm5, byte ptr [rdi + r11 + 24], 9 + mov r12, r11 + pinsrb xmm5, byte ptr [rdi + rdx + 24], 10 + pinsrb xmm5, byte ptr [rdi + r10 + 24], 11 + mov r15, r10 + pinsrb xmm5, byte ptr [rdi + rax + 24], 12 + pinsrb xmm5, byte ptr [rdi + r8 + 24], 13 + pinsrb xmm5, byte ptr [rdi + r13 + 24], 14 + mov rax, r13 + pinsrb xmm5, byte ptr [rdi + rsi + 24], 15 + pcmpgtb xmm3, xmm14 + movdqa xmmword ptr [rsp + 288], xmm3 # 16-byte Spill + movdqa xmm3, xmm15 + pcmpgtb xmm3, xmm5 + movdqa xmmword ptr [rsp + 256], xmm3 # 16-byte Spill + movdqa xmm5, xmm15 + pcmpgtb xmm5, xmm2 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + movzx edx, byte ptr [rdi + rcx + 13] + movd xmm2, edx + pinsrb xmm7, byte ptr [rdi + r8 + 6], 13 + mov r13, r8 + movdqa xmm3, xmmword ptr [rip + .LCPI10_16] # xmm3 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pandn xmm5, xmm3 + paddb xmm5, xmm11 + movdqa xmm13, xmm15 + pcmpgtb xmm13, xmm0 + movdqa xmm3, xmm15 + pcmpgtb xmm3, xmm4 + movzx edx, byte ptr [rdi + rcx + 14] + movd xmm4, edx + pinsrb xmm7, byte ptr [rdi + rax + 6], 14 + movdqa xmm0, xmmword ptr [rip + .LCPI10_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pandn xmm13, xmm0 + movdqa xmm0, xmmword ptr [rip + .LCPI10_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pandn xmm3, xmm0 + por xmm3, xmm13 + movdqa xmm14, xmm15 + pcmpgtb xmm14, xmm6 + movzx edx, byte ptr [rdi + rcx + 15] + movd xmm6, edx + movdqa xmm0, xmmword ptr [rip + .LCPI10_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pandn xmm14, xmm0 + por xmm14, xmm3 + movzx edx, byte ptr [rdi + rcx + 17] + movd xmm3, edx + pinsrb xmm7, byte ptr [rdi + rsi + 6], 15 + pcmpeqd xmm0, xmm0 + psubb xmm5, xmm0 + por xmm14, xmm5 + movdqa xmm5, xmm15 + pcmpgtb xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload + movdqa xmm13, xmm15 + movdqa xmm11, xmm15 + pcmpgtb xmm13, xmm7 + movzx edx, byte ptr [rdi + rcx + 18] + movd xmm7, edx + movdqa xmm0, xmmword ptr [rip + .LCPI10_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm5, xmm0 + movdqa xmm0, xmmword ptr [rip + .LCPI10_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm13, xmm0 + por xmm13, xmm5 + movzx edx, byte ptr [rdi + rcx + 19] + movd xmm15, edx + movdqa xmm0, xmmword ptr [rsp + 272] # 16-byte Reload + pinsrb xmm0, byte ptr [rdi + r14 + 7], 1 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rcx + 7], 2 + mov rsi, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rsi + 7], 3 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rax + 7], 4 + mov r14, r9 + pinsrb xmm0, byte ptr [rdi + r9 + 7], 5 + mov r11, qword ptr [rsp + 240] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r11 + 7], 6 + mov r10, qword ptr [rsp + 336] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r10 + 7], 7 + mov r9, qword ptr [rsp + 320] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r9 + 7], 8 + mov r8, r12 + pinsrb xmm0, byte ptr [rdi + r12 + 7], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rbx + 7], 10 + mov qword ptr [rsp + 304], r15 # 8-byte Spill + pinsrb xmm0, byte ptr [rdi + r15 + 7], 11 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 7], 12 + pinsrb xmm0, byte ptr [rdi + r13 + 7], 13 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r13 + 7], 14 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r12 + 7], 15 + mov r12, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r12 + 9], 1 + pinsrb xmm8, byte ptr [rdi + rcx + 9], 2 + pinsrb xmm8, byte ptr [rdi + rsi + 9], 3 + pinsrb xmm8, byte ptr [rdi + rax + 9], 4 + pinsrb xmm8, byte ptr [rdi + r14 + 9], 5 + pinsrb xmm8, byte ptr [rdi + r11 + 9], 6 + pinsrb xmm8, byte ptr [rdi + r10 + 9], 7 + pinsrb xmm8, byte ptr [rdi + r9 + 9], 8 + pinsrb xmm8, byte ptr [rdi + r8 + 9], 9 + pinsrb xmm8, byte ptr [rdi + rbx + 9], 10 + pinsrb xmm8, byte ptr [rdi + r15 + 9], 11 + pinsrb xmm8, byte ptr [rdi + rdx + 9], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rbx + 9], 13 + pinsrb xmm8, byte ptr [rdi + r13 + 9], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rbx + 9], 15 + pinsrb xmm10, byte ptr [rdi + r12 + 10], 1 + pinsrb xmm10, byte ptr [rdi + rcx + 10], 2 + pinsrb xmm10, byte ptr [rdi + rsi + 10], 3 + pinsrb xmm10, byte ptr [rdi + rax + 10], 4 + pinsrb xmm10, byte ptr [rdi + r14 + 10], 5 + pinsrb xmm10, byte ptr [rdi + r11 + 10], 6 + pinsrb xmm10, byte ptr [rdi + r10 + 10], 7 + pinsrb xmm10, byte ptr [rdi + r9 + 10], 8 + pinsrb xmm10, byte ptr [rdi + r8 + 10], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rbx + 10], 10 + pinsrb xmm10, byte ptr [rdi + r15 + 10], 11 + pinsrb xmm10, byte ptr [rdi + rdx + 10], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rbx + 10], 13 + pinsrb xmm10, byte ptr [rdi + r13 + 10], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rbx + 10], 15 + pinsrb xmm1, byte ptr [rdi + r12 + 11], 1 + pinsrb xmm1, byte ptr [rdi + rcx + 11], 2 + pinsrb xmm1, byte ptr [rdi + rsi + 11], 3 + pinsrb xmm1, byte ptr [rdi + rax + 11], 4 + pinsrb xmm1, byte ptr [rdi + r14 + 11], 5 + pinsrb xmm1, byte ptr [rdi + r11 + 11], 6 + pinsrb xmm1, byte ptr [rdi + r10 + 11], 7 + pinsrb xmm1, byte ptr [rdi + r9 + 11], 8 + pinsrb xmm1, byte ptr [rdi + r8 + 11], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rbx + 11], 10 + pinsrb xmm1, byte ptr [rdi + r15 + 11], 11 + pinsrb xmm1, byte ptr [rdi + rdx + 11], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rbx + 11], 13 + pinsrb xmm1, byte ptr [rdi + r13 + 11], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rbx + 11], 15 + pinsrb xmm12, byte ptr [rdi + r12 + 12], 1 + pinsrb xmm12, byte ptr [rdi + rcx + 12], 2 + pinsrb xmm12, byte ptr [rdi + rsi + 12], 3 + pinsrb xmm12, byte ptr [rdi + rax + 12], 4 + pinsrb xmm12, byte ptr [rdi + r14 + 12], 5 + pinsrb xmm12, byte ptr [rdi + r11 + 12], 6 + pinsrb xmm12, byte ptr [rdi + r10 + 12], 7 + pinsrb xmm12, byte ptr [rdi + r9 + 12], 8 + pinsrb xmm12, byte ptr [rdi + r8 + 12], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rbx + 12], 10 + pinsrb xmm12, byte ptr [rdi + r15 + 12], 11 + pinsrb xmm12, byte ptr [rdi + rdx + 12], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rbx + 12], 13 + pinsrb xmm12, byte ptr [rdi + r13 + 12], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rbx + 12], 15 + pinsrb xmm2, byte ptr [rdi + r12 + 13], 1 + pinsrb xmm2, byte ptr [rdi + rcx + 13], 2 + pinsrb xmm2, byte ptr [rdi + rsi + 13], 3 + pinsrb xmm2, byte ptr [rdi + rax + 13], 4 + pinsrb xmm2, byte ptr [rdi + r14 + 13], 5 + pinsrb xmm2, byte ptr [rdi + r11 + 13], 6 + pinsrb xmm2, byte ptr [rdi + r10 + 13], 7 + pinsrb xmm2, byte ptr [rdi + r9 + 13], 8 + pinsrb xmm2, byte ptr [rdi + r8 + 13], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rbx + 13], 10 + pinsrb xmm2, byte ptr [rdi + r15 + 13], 11 + pinsrb xmm2, byte ptr [rdi + rdx + 13], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rbx + 13], 13 + pinsrb xmm2, byte ptr [rdi + r13 + 13], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rbx + 13], 15 + pinsrb xmm4, byte ptr [rdi + r12 + 14], 1 + pinsrb xmm4, byte ptr [rdi + rcx + 14], 2 + pinsrb xmm4, byte ptr [rdi + rsi + 14], 3 + pinsrb xmm4, byte ptr [rdi + rax + 14], 4 + pinsrb xmm4, byte ptr [rdi + r14 + 14], 5 + pinsrb xmm4, byte ptr [rdi + r11 + 14], 6 + pinsrb xmm4, byte ptr [rdi + r10 + 14], 7 + pinsrb xmm4, byte ptr [rdi + r9 + 14], 8 + pinsrb xmm4, byte ptr [rdi + r8 + 14], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rbx + 14], 10 + pinsrb xmm4, byte ptr [rdi + r15 + 14], 11 + pinsrb xmm4, byte ptr [rdi + rdx + 14], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rbx + 14], 13 + pinsrb xmm4, byte ptr [rdi + r13 + 14], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rbx + 14], 15 + pinsrb xmm6, byte ptr [rdi + r12 + 15], 1 + pinsrb xmm6, byte ptr [rdi + rcx + 15], 2 + pinsrb xmm6, byte ptr [rdi + rsi + 15], 3 + pinsrb xmm6, byte ptr [rdi + rax + 15], 4 + pinsrb xmm6, byte ptr [rdi + r14 + 15], 5 + pinsrb xmm6, byte ptr [rdi + r11 + 15], 6 + pinsrb xmm6, byte ptr [rdi + r10 + 15], 7 + pinsrb xmm6, byte ptr [rdi + r9 + 15], 8 + pinsrb xmm6, byte ptr [rdi + r8 + 15], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rbx + 15], 10 + pinsrb xmm6, byte ptr [rdi + r15 + 15], 11 + pinsrb xmm6, byte ptr [rdi + rdx + 15], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rbx + 15], 13 + pinsrb xmm6, byte ptr [rdi + r13 + 15], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rbx + 15], 15 + pinsrb xmm3, byte ptr [rdi + r12 + 17], 1 + pinsrb xmm3, byte ptr [rdi + rcx + 17], 2 + pinsrb xmm3, byte ptr [rdi + rsi + 17], 3 + pinsrb xmm3, byte ptr [rdi + rax + 17], 4 + pinsrb xmm3, byte ptr [rdi + r14 + 17], 5 + pinsrb xmm3, byte ptr [rdi + r11 + 17], 6 + pinsrb xmm3, byte ptr [rdi + r10 + 17], 7 + pinsrb xmm3, byte ptr [rdi + r9 + 17], 8 + pinsrb xmm3, byte ptr [rdi + r8 + 17], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rbx + 17], 10 + pinsrb xmm3, byte ptr [rdi + r15 + 17], 11 + pinsrb xmm3, byte ptr [rdi + rdx + 17], 12 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rbx + 17], 13 + pinsrb xmm3, byte ptr [rdi + r13 + 17], 14 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rbx + 17], 15 + pinsrb xmm7, byte ptr [rdi + r12 + 18], 1 + pinsrb xmm7, byte ptr [rdi + rcx + 18], 2 + pinsrb xmm7, byte ptr [rdi + rsi + 18], 3 + pinsrb xmm7, byte ptr [rdi + rax + 18], 4 + pinsrb xmm7, byte ptr [rdi + r14 + 18], 5 + pinsrb xmm7, byte ptr [rdi + r11 + 18], 6 + pinsrb xmm7, byte ptr [rdi + r10 + 18], 7 + pinsrb xmm7, byte ptr [rdi + r9 + 18], 8 + pinsrb xmm7, byte ptr [rdi + r8 + 18], 9 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rbx + 18], 10 + pinsrb xmm7, byte ptr [rdi + r15 + 18], 11 + pinsrb xmm7, byte ptr [rdi + rdx + 18], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + rsi + 18], 13 + pinsrb xmm7, byte ptr [rdi + r13 + 18], 14 + mov r13, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm7, byte ptr [rdi + r13 + 18], 15 + pinsrb xmm15, byte ptr [rdi + r12 + 19], 1 + pinsrb xmm15, byte ptr [rdi + rcx + 19], 2 + mov rcx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rcx + 19], 3 + pinsrb xmm15, byte ptr [rdi + rax + 19], 4 + pinsrb xmm15, byte ptr [rdi + r14 + 19], 5 + pinsrb xmm15, byte ptr [rdi + r11 + 19], 6 + pinsrb xmm15, byte ptr [rdi + r10 + 19], 7 + pinsrb xmm15, byte ptr [rdi + r9 + 19], 8 + pinsrb xmm15, byte ptr [rdi + r8 + 19], 9 + pinsrb xmm15, byte ptr [rdi + rbx + 19], 10 + pinsrb xmm15, byte ptr [rdi + r15 + 19], 11 + movdqa xmm5, xmm11 + pcmpgtb xmm5, xmm0 + movdqa xmm0, xmmword ptr [rip + .LCPI10_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm5, xmm0 + por xmm5, xmm13 + mov rax, qword ptr [rsp + 208] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 20] + movd xmm0, edx + por xmm5, xmm14 + movdqa xmmword ptr [rsp + 160], xmm5 # 16-byte Spill + movdqa xmm13, xmm11 + pcmpgtb xmm13, xmm8 + movzx edx, byte ptr [rdi + rax + 21] + movd xmm8, edx + mov rbx, qword ptr [rsp + 144] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rbx + 19], 12 + pandn xmm13, xmmword ptr [rip + .LCPI10_16] + paddb xmm13, xmm9 + movdqa xmm5, xmm11 + pcmpgtb xmm5, xmm10 + movdqa xmm9, xmm11 + pcmpgtb xmm9, xmm1 + movzx edx, byte ptr [rdi + rax + 22] + movd xmm10, edx + pinsrb xmm15, byte ptr [rdi + rsi + 19], 13 + mov r15, rsi + pandn xmm5, xmmword ptr [rip + .LCPI10_17] + pandn xmm9, xmmword ptr [rip + .LCPI10_18] + por xmm9, xmm5 + movdqa xmm1, xmm11 + pcmpgtb xmm1, xmm12 + movzx edx, byte ptr [rdi + rax + 23] + movd xmm5, edx + pandn xmm1, xmmword ptr [rip + .LCPI10_19] + por xmm1, xmm9 + movzx edx, byte ptr [rdi + rax + 25] + movd xmm9, edx + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rsi + 19], 14 + psubb xmm13, xmmword ptr [rip + .LCPI10_22] + por xmm1, xmm13 + movdqa xmm14, xmm11 + pcmpgtb xmm14, xmm2 + movdqa xmm13, xmm11 + pcmpgtb xmm13, xmm4 + movzx edx, byte ptr [rdi + rax + 26] + movd xmm12, edx + pinsrb xmm15, byte ptr [rdi + r13 + 19], 15 + pandn xmm14, xmmword ptr [rip + .LCPI10_20] + pandn xmm13, xmmword ptr [rip + .LCPI10_21] + por xmm13, xmm14 + movdqa xmm4, xmm11 + movdqa xmm14, xmm11 + pcmpgtb xmm14, xmm6 + movzx edx, byte ptr [rdi + rax + 27] + movd xmm2, edx + pandn xmm14, xmmword ptr [rip + .LCPI10_6] + por xmm14, xmm13 + movzx edx, byte ptr [rdi + rax + 28] + movd xmm6, edx + por xmm14, xmm1 + pcmpgtb xmm11, xmm3 + movzx edx, byte ptr [rdi + rax + 29] + movd xmm3, edx + pandn xmm11, xmmword ptr [rip + .LCPI10_16] + paddb xmm11, xmmword ptr [rsp + 288] # 16-byte Folded Reload + movdqa xmm1, xmm4 + pcmpgtb xmm1, xmm7 + movdqa xmm13, xmm4 + movdqa xmm7, xmm4 + pcmpgtb xmm13, xmm15 + movzx edx, byte ptr [rdi + rax + 30] + movd xmm4, edx + movzx edx, byte ptr [rdi + rax + 31] + pandn xmm1, xmmword ptr [rip + .LCPI10_17] + pandn xmm13, xmmword ptr [rip + .LCPI10_18] + por xmm13, xmm1 + movd xmm15, edx + mov rax, r12 + pinsrb xmm0, byte ptr [rdi + r12 + 20], 1 + pinsrb xmm8, byte ptr [rdi + r12 + 21], 1 + pinsrb xmm10, byte ptr [rdi + r12 + 22], 1 + pinsrb xmm5, byte ptr [rdi + r12 + 23], 1 + pinsrb xmm9, byte ptr [rdi + r12 + 25], 1 + pinsrb xmm12, byte ptr [rdi + r12 + 26], 1 + pinsrb xmm2, byte ptr [rdi + r12 + 27], 1 + pinsrb xmm6, byte ptr [rdi + r12 + 28], 1 + pinsrb xmm3, byte ptr [rdi + r12 + 29], 1 + pinsrb xmm4, byte ptr [rdi + r12 + 30], 1 + pinsrb xmm15, byte ptr [rdi + r12 + 31], 1 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rax + 20], 2 + pinsrb xmm8, byte ptr [rdi + rax + 21], 2 + pinsrb xmm10, byte ptr [rdi + rax + 22], 2 + pinsrb xmm5, byte ptr [rdi + rax + 23], 2 + pinsrb xmm9, byte ptr [rdi + rax + 25], 2 + pinsrb xmm12, byte ptr [rdi + rax + 26], 2 + pinsrb xmm2, byte ptr [rdi + rax + 27], 2 + pinsrb xmm6, byte ptr [rdi + rax + 28], 2 + pinsrb xmm3, byte ptr [rdi + rax + 29], 2 + pinsrb xmm4, byte ptr [rdi + rax + 30], 2 + pinsrb xmm15, byte ptr [rdi + rax + 31], 2 + mov rdx, rcx + pinsrb xmm0, byte ptr [rdi + rcx + 20], 3 + pinsrb xmm8, byte ptr [rdi + rcx + 21], 3 + pinsrb xmm10, byte ptr [rdi + rcx + 22], 3 + pinsrb xmm5, byte ptr [rdi + rcx + 23], 3 + pinsrb xmm9, byte ptr [rdi + rcx + 25], 3 + pinsrb xmm12, byte ptr [rdi + rcx + 26], 3 + pinsrb xmm2, byte ptr [rdi + rcx + 27], 3 + pinsrb xmm6, byte ptr [rdi + rcx + 28], 3 + pinsrb xmm3, byte ptr [rdi + rcx + 29], 3 + pinsrb xmm4, byte ptr [rdi + rcx + 30], 3 + pinsrb xmm15, byte ptr [rdi + rcx + 31], 3 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 20], 4 + pinsrb xmm8, byte ptr [rdi + rdx + 21], 4 + pinsrb xmm10, byte ptr [rdi + rdx + 22], 4 + pinsrb xmm5, byte ptr [rdi + rdx + 23], 4 + pinsrb xmm9, byte ptr [rdi + rdx + 25], 4 + pinsrb xmm12, byte ptr [rdi + rdx + 26], 4 + pinsrb xmm2, byte ptr [rdi + rdx + 27], 4 + pinsrb xmm6, byte ptr [rdi + rdx + 28], 4 + pinsrb xmm3, byte ptr [rdi + rdx + 29], 4 + pinsrb xmm4, byte ptr [rdi + rdx + 30], 4 + pinsrb xmm15, byte ptr [rdi + rdx + 31], 4 + pinsrb xmm0, byte ptr [rdi + r14 + 20], 5 + pinsrb xmm8, byte ptr [rdi + r14 + 21], 5 + pinsrb xmm10, byte ptr [rdi + r14 + 22], 5 + pinsrb xmm5, byte ptr [rdi + r14 + 23], 5 + pinsrb xmm9, byte ptr [rdi + r14 + 25], 5 + pinsrb xmm12, byte ptr [rdi + r14 + 26], 5 + pinsrb xmm2, byte ptr [rdi + r14 + 27], 5 + pinsrb xmm6, byte ptr [rdi + r14 + 28], 5 + pinsrb xmm3, byte ptr [rdi + r14 + 29], 5 + pinsrb xmm4, byte ptr [rdi + r14 + 30], 5 + pinsrb xmm15, byte ptr [rdi + r14 + 31], 5 + pinsrb xmm0, byte ptr [rdi + r11 + 20], 6 + pinsrb xmm8, byte ptr [rdi + r11 + 21], 6 + pinsrb xmm10, byte ptr [rdi + r11 + 22], 6 + pinsrb xmm5, byte ptr [rdi + r11 + 23], 6 + pinsrb xmm9, byte ptr [rdi + r11 + 25], 6 + pinsrb xmm12, byte ptr [rdi + r11 + 26], 6 + pinsrb xmm2, byte ptr [rdi + r11 + 27], 6 + pinsrb xmm6, byte ptr [rdi + r11 + 28], 6 + pinsrb xmm3, byte ptr [rdi + r11 + 29], 6 + pinsrb xmm4, byte ptr [rdi + r11 + 30], 6 + pinsrb xmm15, byte ptr [rdi + r11 + 31], 6 + mov r12, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r10 + 20], 7 + pinsrb xmm8, byte ptr [rdi + r10 + 21], 7 + pinsrb xmm10, byte ptr [rdi + r10 + 22], 7 + pinsrb xmm5, byte ptr [rdi + r10 + 23], 7 + pinsrb xmm9, byte ptr [rdi + r10 + 25], 7 + pinsrb xmm12, byte ptr [rdi + r10 + 26], 7 + pinsrb xmm2, byte ptr [rdi + r10 + 27], 7 + pinsrb xmm6, byte ptr [rdi + r10 + 28], 7 + pinsrb xmm3, byte ptr [rdi + r10 + 29], 7 + pinsrb xmm4, byte ptr [rdi + r10 + 30], 7 + pinsrb xmm15, byte ptr [rdi + r10 + 31], 7 + pinsrb xmm0, byte ptr [rdi + r9 + 20], 8 + pinsrb xmm8, byte ptr [rdi + r9 + 21], 8 + pinsrb xmm10, byte ptr [rdi + r9 + 22], 8 + pinsrb xmm5, byte ptr [rdi + r9 + 23], 8 + pinsrb xmm9, byte ptr [rdi + r9 + 25], 8 + pinsrb xmm12, byte ptr [rdi + r9 + 26], 8 + pinsrb xmm2, byte ptr [rdi + r9 + 27], 8 + pinsrb xmm6, byte ptr [rdi + r9 + 28], 8 + pinsrb xmm3, byte ptr [rdi + r9 + 29], 8 + pinsrb xmm4, byte ptr [rdi + r9 + 30], 8 + pinsrb xmm15, byte ptr [rdi + r9 + 31], 8 + pinsrb xmm0, byte ptr [rdi + r8 + 20], 9 + pinsrb xmm8, byte ptr [rdi + r8 + 21], 9 + pinsrb xmm10, byte ptr [rdi + r8 + 22], 9 + pinsrb xmm5, byte ptr [rdi + r8 + 23], 9 + pinsrb xmm9, byte ptr [rdi + r8 + 25], 9 + pinsrb xmm12, byte ptr [rdi + r8 + 26], 9 + pinsrb xmm2, byte ptr [rdi + r8 + 27], 9 + pinsrb xmm6, byte ptr [rdi + r8 + 28], 9 + pinsrb xmm3, byte ptr [rdi + r8 + 29], 9 + pinsrb xmm4, byte ptr [rdi + r8 + 30], 9 + pinsrb xmm15, byte ptr [rdi + r8 + 31], 9 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r14 + 20], 10 + pinsrb xmm8, byte ptr [rdi + r14 + 21], 10 + pinsrb xmm10, byte ptr [rdi + r14 + 22], 10 + pinsrb xmm5, byte ptr [rdi + r14 + 23], 10 + pinsrb xmm9, byte ptr [rdi + r14 + 25], 10 + pinsrb xmm12, byte ptr [rdi + r14 + 26], 10 + pinsrb xmm2, byte ptr [rdi + r14 + 27], 10 + pinsrb xmm6, byte ptr [rdi + r14 + 28], 10 + pinsrb xmm3, byte ptr [rdi + r14 + 29], 10 + pinsrb xmm4, byte ptr [rdi + r14 + 30], 10 + pinsrb xmm15, byte ptr [rdi + r14 + 31], 10 + mov r14, qword ptr [rsp + 304] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r14 + 20], 11 + pinsrb xmm8, byte ptr [rdi + r14 + 21], 11 + pinsrb xmm10, byte ptr [rdi + r14 + 22], 11 + pinsrb xmm5, byte ptr [rdi + r14 + 23], 11 + pinsrb xmm9, byte ptr [rdi + r14 + 25], 11 + pinsrb xmm12, byte ptr [rdi + r14 + 26], 11 + pinsrb xmm2, byte ptr [rdi + r14 + 27], 11 + pinsrb xmm6, byte ptr [rdi + r14 + 28], 11 + pinsrb xmm3, byte ptr [rdi + r14 + 29], 11 + pinsrb xmm4, byte ptr [rdi + r14 + 30], 11 + pinsrb xmm15, byte ptr [rdi + r14 + 31], 11 + pinsrb xmm0, byte ptr [rdi + rbx + 20], 12 + pinsrb xmm8, byte ptr [rdi + rbx + 21], 12 + pinsrb xmm10, byte ptr [rdi + rbx + 22], 12 + pinsrb xmm5, byte ptr [rdi + rbx + 23], 12 + pinsrb xmm9, byte ptr [rdi + rbx + 25], 12 + pinsrb xmm12, byte ptr [rdi + rbx + 26], 12 + pinsrb xmm2, byte ptr [rdi + rbx + 27], 12 + pinsrb xmm6, byte ptr [rdi + rbx + 28], 12 + pinsrb xmm3, byte ptr [rdi + rbx + 29], 12 + pinsrb xmm4, byte ptr [rdi + rbx + 30], 12 + pinsrb xmm15, byte ptr [rdi + rbx + 31], 12 + pinsrb xmm0, byte ptr [rdi + r15 + 20], 13 + pinsrb xmm8, byte ptr [rdi + r15 + 21], 13 + pinsrb xmm10, byte ptr [rdi + r15 + 22], 13 + pinsrb xmm5, byte ptr [rdi + r15 + 23], 13 + pinsrb xmm9, byte ptr [rdi + r15 + 25], 13 + pinsrb xmm12, byte ptr [rdi + r15 + 26], 13 + pinsrb xmm2, byte ptr [rdi + r15 + 27], 13 + pinsrb xmm6, byte ptr [rdi + r15 + 28], 13 + pinsrb xmm3, byte ptr [rdi + r15 + 29], 13 + pinsrb xmm4, byte ptr [rdi + r15 + 30], 13 + pinsrb xmm15, byte ptr [rdi + r15 + 31], 13 + mov rax, rsi + pinsrb xmm0, byte ptr [rdi + rsi + 20], 14 + pinsrb xmm8, byte ptr [rdi + rsi + 21], 14 + pinsrb xmm10, byte ptr [rdi + rsi + 22], 14 + pinsrb xmm5, byte ptr [rdi + rsi + 23], 14 + pinsrb xmm9, byte ptr [rdi + rsi + 25], 14 + pinsrb xmm12, byte ptr [rdi + rsi + 26], 14 + pinsrb xmm2, byte ptr [rdi + rsi + 27], 14 + pinsrb xmm6, byte ptr [rdi + rsi + 28], 14 + pinsrb xmm3, byte ptr [rdi + rsi + 29], 14 + pinsrb xmm4, byte ptr [rdi + rsi + 30], 14 + pinsrb xmm15, byte ptr [rdi + rsi + 31], 14 + pinsrb xmm0, byte ptr [rdi + r13 + 20], 15 + pinsrb xmm8, byte ptr [rdi + r13 + 21], 15 + pinsrb xmm10, byte ptr [rdi + r13 + 22], 15 + pinsrb xmm5, byte ptr [rdi + r13 + 23], 15 + pinsrb xmm9, byte ptr [rdi + r13 + 25], 15 + pinsrb xmm12, byte ptr [rdi + r13 + 26], 15 + movdqa xmm1, xmm7 + pcmpgtb xmm1, xmm0 + pinsrb xmm2, byte ptr [rdi + r13 + 27], 15 + pandn xmm1, xmmword ptr [rip + .LCPI10_19] + por xmm1, xmm13 + pcmpeqd xmm13, xmm13 + psubb xmm11, xmm13 + por xmm1, xmm11 + movdqa xmm0, xmm7 + pcmpgtb xmm0, xmm8 + movdqa xmm8, xmm7 + pcmpgtb xmm7, xmm10 + movdqa xmm10, xmmword ptr [rip + .LCPI10_20] # xmm10 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pandn xmm0, xmm10 + movdqa xmm11, xmmword ptr [rip + .LCPI10_21] # xmm11 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pandn xmm7, xmm11 + por xmm7, xmm0 + movdqa xmm0, xmm8 + pcmpgtb xmm0, xmm5 + pinsrb xmm6, byte ptr [rdi + r13 + 28], 15 + movdqa xmm5, xmmword ptr [rip + .LCPI10_6] # xmm5 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pandn xmm0, xmm5 + por xmm0, xmm7 + pinsrb xmm3, byte ptr [rdi + r13 + 29], 15 + por xmm0, xmm1 + movdqa xmm1, xmm8 + pcmpgtb xmm1, xmm9 + pandn xmm1, xmmword ptr [rip + .LCPI10_16] + paddb xmm1, xmmword ptr [rsp + 256] # 16-byte Folded Reload + movdqa xmm5, xmm8 + pcmpgtb xmm5, xmm12 + movdqa xmm7, xmm8 + pcmpgtb xmm7, xmm2 + pandn xmm5, xmmword ptr [rip + .LCPI10_17] + pandn xmm7, xmmword ptr [rip + .LCPI10_18] + por xmm7, xmm5 + movdqa xmm2, xmm8 + pcmpgtb xmm2, xmm6 + pinsrb xmm4, byte ptr [rdi + r13 + 30], 15 + pandn xmm2, xmmword ptr [rip + .LCPI10_19] + por xmm2, xmm7 + psubb xmm1, xmm13 + por xmm2, xmm1 + movdqa xmm1, xmm8 + pcmpgtb xmm1, xmm3 + movdqa xmm3, xmm8 + pcmpgtb xmm3, xmm4 + pinsrb xmm15, byte ptr [rdi + r13 + 31], 15 + pandn xmm1, xmm10 + pandn xmm3, xmm11 + por xmm3, xmm1 + movdqa xmm1, xmm8 + pcmpgtb xmm1, xmm15 + pandn xmm1, xmmword ptr [rip + .LCPI10_6] + por xmm1, xmm3 + por xmm1, xmm2 + movdqa xmm2, xmm0 + punpcklbw xmm2, xmm1 # xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7] + movdqa xmm5, xmmword ptr [rsp + 160] # 16-byte Reload + movdqa xmm3, xmm5 + punpcklbw xmm3, xmm14 # xmm3 = xmm3[0],xmm14[0],xmm3[1],xmm14[1],xmm3[2],xmm14[2],xmm3[3],xmm14[3],xmm3[4],xmm14[4],xmm3[5],xmm14[5],xmm3[6],xmm14[6],xmm3[7],xmm14[7] + movdqa xmm4, xmm3 + punpcklwd xmm4, xmm2 # xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3] + punpckhwd xmm3, xmm2 # xmm3 = xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7] + punpckhbw xmm0, xmm1 # xmm0 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15] + punpckhbw xmm5, xmm14 # xmm5 = xmm5[8],xmm14[8],xmm5[9],xmm14[9],xmm5[10],xmm14[10],xmm5[11],xmm14[11],xmm5[12],xmm14[12],xmm5[13],xmm14[13],xmm5[14],xmm14[14],xmm5[15],xmm14[15] + movdqa xmm1, xmm5 + punpcklwd xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3] + punpckhwd xmm5, xmm0 # xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7] + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + movdqu xmmword ptr [r12 + 4*rcx + 48], xmm5 + movdqu xmmword ptr [r12 + 4*rcx + 32], xmm1 + movdqu xmmword ptr [r12 + 4*rcx + 16], xmm3 + movdqu xmmword ptr [r12 + 4*rcx], xmm4 + add rcx, 16 + mov r8, rcx + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + jne .LBB10_99 +# %bb.100: + mov rcx, qword ptr [rsp + 400] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r15b, byte ptr [rsp] # 1-byte Reload + mov rsi, qword ptr [rsp + 376] # 8-byte Reload + mov r14, qword ptr [rsp + 72] # 8-byte Reload + jne .LBB10_101 + jmp .LBB10_104 +.LBB10_72: + and rcx, -16 + mov rax, rcx + shl rax, 5 + add rax, rdi + mov qword ptr [rsp + 448], rax # 8-byte Spill + mov qword ptr [rsp + 384], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 400], rax # 8-byte Spill + movzx eax, r13b + movd xmm1, eax + pxor xmm0, xmm0 + pshufb xmm1, xmm0 + movdqa xmmword ptr [rsp + 416], xmm1 # 16-byte Spill + xor eax, eax + mov qword ptr [rsp + 8], r12 # 8-byte Spill + .p2align 4, 0x90 +.LBB10_73: # =>This Inner Loop Header: Depth=1 + mov rcx, rax + mov qword ptr [rsp + 336], rax # 8-byte Spill + shl rcx, 5 + mov qword ptr [rsp + 32], rcx # 8-byte Spill + mov r12, rcx + mov r9, rcx + mov r8, rcx + mov rsi, rcx + mov r11, rcx + mov r14, rcx + mov r10, rcx + mov r15, rcx + mov rbx, rcx + mov r13, rcx + movzx eax, byte ptr [rdi + rcx] + movd xmm0, eax + movzx eax, byte ptr [rdi + rcx + 1] + movd xmm11, eax + movzx eax, byte ptr [rdi + rcx + 2] + movd xmm14, eax + movzx eax, byte ptr [rdi + rcx + 3] + movd xmm5, eax + movzx eax, byte ptr [rdi + rcx + 4] + movd xmm3, eax + movzx eax, byte ptr [rdi + rcx + 5] + movd xmm1, eax + movzx eax, byte ptr [rdi + rcx + 6] + movd xmm4, eax + movzx eax, byte ptr [rdi + rcx + 7] + movd xmm2, eax + movdqa xmmword ptr [rsp + 304], xmm2 # 16-byte Spill + movzx eax, byte ptr [rdi + rcx + 8] + movd xmm13, eax + movzx eax, byte ptr [rdi + rcx + 9] + movd xmm2, eax + movdqa xmmword ptr [rsp + 240], xmm2 # 16-byte Spill + movzx eax, byte ptr [rdi + rcx + 10] + movd xmm8, eax + movzx eax, byte ptr [rdi + rcx + 11] + movd xmm10, eax + movzx eax, byte ptr [rdi + rcx + 12] + movd xmm6, eax + movzx eax, byte ptr [rdi + rcx + 16] + movd xmm12, eax + movzx eax, byte ptr [rdi + rcx + 24] + movd xmm2, eax + mov qword ptr [rsp + 144], rcx # 8-byte Spill + mov rax, rcx + or rax, 32 + mov qword ptr [rsp + 96], rax # 8-byte Spill + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + or rdx, 64 + or r12, 96 + mov qword ptr [rsp + 160], r12 # 8-byte Spill + or r9, 128 + mov qword ptr [rsp + 272], r9 # 8-byte Spill + or r8, 160 + mov qword ptr [rsp + 208], r8 # 8-byte Spill + or rsi, 192 + mov qword ptr [rsp + 224], rsi # 8-byte Spill + or r11, 224 + mov qword ptr [rsp + 256], r11 # 8-byte Spill + or r14, 256 + mov qword ptr [rsp + 112], r14 # 8-byte Spill + or r10, 288 + or r15, 320 + mov qword ptr [rsp + 288], r15 # 8-byte Spill + or rbx, 352 + mov qword ptr [rsp + 176], rbx # 8-byte Spill + or r13, 384 + mov rax, rcx + or rax, 416 + mov qword ptr [rsp + 16], rax # 8-byte Spill + mov rax, rcx + or rax, 448 + mov qword ptr [rsp + 48], rax # 8-byte Spill + mov rax, rcx + or rax, 480 + mov rcx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rcx], 1 + pinsrb xmm0, byte ptr [rdi + rdx], 2 + pinsrb xmm0, byte ptr [rdi + r12], 3 + pinsrb xmm0, byte ptr [rdi + r9], 4 + pinsrb xmm0, byte ptr [rdi + r8], 5 + pinsrb xmm0, byte ptr [rdi + rsi], 6 + pinsrb xmm0, byte ptr [rdi + r11], 7 + pinsrb xmm0, byte ptr [rdi + r14], 8 + pinsrb xmm0, byte ptr [rdi + r10], 9 + pinsrb xmm0, byte ptr [rdi + r15], 10 + pinsrb xmm0, byte ptr [rdi + rbx], 11 + mov qword ptr [rsp + 128], r13 # 8-byte Spill + pinsrb xmm0, byte ptr [rdi + r13], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rcx], 13 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r8], 14 + mov r14, rax + pinsrb xmm0, byte ptr [rdi + rax], 15 + movdqa xmm9, xmm0 + movdqa xmm7, xmmword ptr [rsp + 416] # 16-byte Reload + pmaxub xmm9, xmm7 + movdqa xmm15, xmm7 + pcmpeqb xmm9, xmm0 + movdqa xmm0, xmm9 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rax + 1], 1 + pinsrb xmm11, byte ptr [rdi + rdx + 1], 2 + pinsrb xmm11, byte ptr [rdi + r12 + 1], 3 + pinsrb xmm11, byte ptr [rdi + r9 + 1], 4 + mov rcx, qword ptr [rsp + 208] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rcx + 1], 5 + pinsrb xmm11, byte ptr [rdi + rsi + 1], 6 + pinsrb xmm11, byte ptr [rdi + r11 + 1], 7 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rax + 1], 8 + pinsrb xmm11, byte ptr [rdi + r10 + 1], 9 + pinsrb xmm11, byte ptr [rdi + r15 + 1], 10 + pinsrb xmm11, byte ptr [rdi + rbx + 1], 11 + pinsrb xmm11, byte ptr [rdi + r13 + 1], 12 + mov r15, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r15 + 1], 13 + pinsrb xmm11, byte ptr [rdi + r8 + 1], 14 + pinsrb xmm11, byte ptr [rdi + r14 + 1], 15 + mov r8, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r8 + 8], 1 + pinsrb xmm13, byte ptr [rdi + rdx + 8], 2 + pinsrb xmm13, byte ptr [rdi + r12 + 8], 3 + pinsrb xmm13, byte ptr [rdi + r9 + 8], 4 + pinsrb xmm13, byte ptr [rdi + rcx + 8], 5 + pinsrb xmm13, byte ptr [rdi + rsi + 8], 6 + pinsrb xmm13, byte ptr [rdi + r11 + 8], 7 + pinsrb xmm13, byte ptr [rdi + rax + 8], 8 + pinsrb xmm13, byte ptr [rdi + r10 + 8], 9 + mov r11, qword ptr [rsp + 288] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r11 + 8], 10 + pinsrb xmm13, byte ptr [rdi + rbx + 8], 11 + pinsrb xmm13, byte ptr [rdi + r13 + 8], 12 + pinsrb xmm13, byte ptr [rdi + r15 + 8], 13 + mov r12, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm13, byte ptr [rdi + r12 + 8], 14 + pinsrb xmm13, byte ptr [rdi + r14 + 8], 15 + movdqa xmm9, xmm13 + pmaxub xmm9, xmm7 + pcmpeqb xmm9, xmm13 + pinsrb xmm12, byte ptr [rdi + r8 + 16], 1 + mov r15, r8 + pinsrb xmm12, byte ptr [rdi + rdx + 16], 2 + mov rbx, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rbx + 16], 3 + pinsrb xmm12, byte ptr [rdi + r9 + 16], 4 + pinsrb xmm12, byte ptr [rdi + rcx + 16], 5 + pinsrb xmm12, byte ptr [rdi + rsi + 16], 6 + mov rsi, qword ptr [rsp + 256] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rsi + 16], 7 + pinsrb xmm12, byte ptr [rdi + rax + 16], 8 + mov r8, rax + pinsrb xmm12, byte ptr [rdi + r10 + 16], 9 + mov qword ptr [rsp + 192], r10 # 8-byte Spill + pinsrb xmm12, byte ptr [rdi + r11 + 16], 10 + mov rax, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + rax + 16], 11 + pinsrb xmm12, byte ptr [rdi + r13 + 16], 12 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm12, byte ptr [rdi + r13 + 16], 13 + pinsrb xmm12, byte ptr [rdi + r12 + 16], 14 + pinsrb xmm12, byte ptr [rdi + r14 + 16], 15 + mov qword ptr [rsp + 80], r14 # 8-byte Spill + movdqa xmm7, xmm12 + pmaxub xmm7, xmm15 + pcmpeqb xmm7, xmm12 + movdqa xmmword ptr [rsp + 352], xmm7 # 16-byte Spill + pinsrb xmm2, byte ptr [rdi + r15 + 24], 1 + pinsrb xmm2, byte ptr [rdi + rdx + 24], 2 + mov r15, rdx + mov qword ptr [rsp + 32], rdx # 8-byte Spill + pinsrb xmm2, byte ptr [rdi + rbx + 24], 3 + mov rdx, qword ptr [rsp + 272] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rdx + 24], 4 + pinsrb xmm2, byte ptr [rdi + rcx + 24], 5 + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rcx + 24], 6 + pinsrb xmm2, byte ptr [rdi + rsi + 24], 7 + pinsrb xmm2, byte ptr [rdi + r8 + 24], 8 + mov rbx, r8 + pinsrb xmm2, byte ptr [rdi + r10 + 24], 9 + pinsrb xmm2, byte ptr [rdi + r11 + 24], 10 + mov r10, r11 + pinsrb xmm2, byte ptr [rdi + rax + 24], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rax + 24], 12 + pinsrb xmm2, byte ptr [rdi + r13 + 24], 13 + pinsrb xmm2, byte ptr [rdi + r12 + 24], 14 + pinsrb xmm2, byte ptr [rdi + r14 + 24], 15 + movdqa xmm7, xmm2 + pmaxub xmm7, xmm15 + pcmpeqb xmm7, xmm2 + movdqa xmmword ptr [rsp + 320], xmm7 # 16-byte Spill + movdqa xmm12, xmm11 + movdqa xmm13, xmm15 + pmaxub xmm12, xmm15 + pcmpeqb xmm12, xmm11 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 13] + movd xmm15, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rdx + 2], 1 + pinsrb xmm14, byte ptr [rdi + r15 + 2], 2 + mov r15, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r15 + 2], 3 + mov r9, qword ptr [rsp + 272] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r9 + 2], 4 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rsi + 2], 5 + mov r8, rcx + pinsrb xmm14, byte ptr [rdi + rcx + 2], 6 + mov r11, qword ptr [rsp + 256] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r11 + 2], 7 + pinsrb xmm14, byte ptr [rdi + rbx + 2], 8 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rcx + 2], 9 + mov rbx, r10 + pinsrb xmm14, byte ptr [rdi + r10 + 2], 10 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r10 + 2], 11 + mov rax, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rax + 2], 12 + pinsrb xmm14, byte ptr [rdi + r13 + 2], 13 + mov r14, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r14 + 2], 14 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r12 + 2], 15 + pinsrb xmm5, byte ptr [rdi + rdx + 3], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rdx + 3], 2 + pinsrb xmm5, byte ptr [rdi + r15 + 3], 3 + pinsrb xmm5, byte ptr [rdi + r9 + 3], 4 + pinsrb xmm5, byte ptr [rdi + rsi + 3], 5 + pinsrb xmm5, byte ptr [rdi + r8 + 3], 6 + pinsrb xmm5, byte ptr [rdi + r11 + 3], 7 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rdx + 3], 8 + pinsrb xmm5, byte ptr [rdi + rcx + 3], 9 + pinsrb xmm5, byte ptr [rdi + rbx + 3], 10 + pinsrb xmm5, byte ptr [rdi + r10 + 3], 11 + pinsrb xmm5, byte ptr [rdi + rax + 3], 12 + pinsrb xmm5, byte ptr [rdi + r13 + 3], 13 + mov rax, r13 + pinsrb xmm5, byte ptr [rdi + r14 + 3], 14 + pinsrb xmm5, byte ptr [rdi + r12 + 3], 15 + movdqa xmm2, xmmword ptr [rip + .LCPI10_16] # xmm2 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] + pand xmm12, xmm2 + psubb xmm12, xmm0 + movdqa xmm11, xmm14 + pmaxub xmm11, xmm13 + pcmpeqb xmm11, xmm14 + movdqa xmm2, xmm5 + pmaxub xmm2, xmm13 + pcmpeqb xmm2, xmm5 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 14] + movd xmm14, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rdx + 4], 1 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r12 + 4], 2 + pinsrb xmm3, byte ptr [rdi + r15 + 4], 3 + pinsrb xmm3, byte ptr [rdi + r9 + 4], 4 + pinsrb xmm3, byte ptr [rdi + rsi + 4], 5 + pinsrb xmm3, byte ptr [rdi + r8 + 4], 6 + pinsrb xmm3, byte ptr [rdi + r11 + 4], 7 + mov r13, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r13 + 4], 8 + pinsrb xmm3, byte ptr [rdi + rcx + 4], 9 + pinsrb xmm3, byte ptr [rdi + rbx + 4], 10 + pinsrb xmm3, byte ptr [rdi + r10 + 4], 11 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r14 + 4], 12 + pinsrb xmm3, byte ptr [rdi + rax + 4], 13 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rax + 4], 14 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rax + 4], 15 + pinsrb xmm1, byte ptr [rdi + rdx + 5], 1 + pinsrb xmm1, byte ptr [rdi + r12 + 5], 2 + pinsrb xmm1, byte ptr [rdi + r15 + 5], 3 + pinsrb xmm1, byte ptr [rdi + r9 + 5], 4 + pinsrb xmm1, byte ptr [rdi + rsi + 5], 5 + pinsrb xmm1, byte ptr [rdi + r8 + 5], 6 + pinsrb xmm1, byte ptr [rdi + r11 + 5], 7 + pinsrb xmm1, byte ptr [rdi + r13 + 5], 8 + pinsrb xmm1, byte ptr [rdi + rcx + 5], 9 + pinsrb xmm1, byte ptr [rdi + rbx + 5], 10 + pinsrb xmm1, byte ptr [rdi + r10 + 5], 11 + pinsrb xmm1, byte ptr [rdi + r14 + 5], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rax + 5], 13 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rax + 5], 14 + movdqa xmm5, xmmword ptr [rip + .LCPI10_17] # xmm5 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] + pand xmm11, xmm5 + movdqa xmm5, xmmword ptr [rip + .LCPI10_18] # xmm5 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] + pand xmm2, xmm5 + por xmm2, xmm11 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 15] + movd xmm11, edx + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm1, byte ptr [rdi + rdx + 5], 15 + por xmm2, xmm12 + movdqa xmm12, xmm3 + pmaxub xmm12, xmm13 + pcmpeqb xmm12, xmm3 movdqa xmm5, xmm1 - pand xmm5, xmm15 - psubb xmm5, xmm1 - movss xmm3, dword ptr [rsi - 392] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rsi - 264], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - pand xmm4, xmm15 - insertps xmm3, dword ptr [rsi - 136], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - por xmm5, xmm4 - movaps xmm4, xmm13 - cmpleps xmm4, xmm7 - insertps xmm3, dword ptr [rsi - 8], 48 # xmm3 = xmm3[0,1,2],mem[0] - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 - pand xmm4, xmm15 - psllw xmm4, 2 - pand xmm4, xmmword ptr [rip + .LCPI10_1] - por xmm4, xmm5 - movaps xmm5, xmm13 - cmpleps xmm5, xmm0 - movaps xmm1, xmm13 - cmpleps xmm1, xmm6 - movss xmm0, dword ptr [rsi - 388] # xmm0 = mem[0],zero,zero,zero - insertps xmm0, dword ptr [rsi - 260], 16 # xmm0 = xmm0[0],mem[0],xmm0[2,3] - insertps xmm0, dword ptr [rsi - 132], 32 # xmm0 = xmm0[0,1],mem[0],xmm0[3] - insertps xmm0, dword ptr [rsi - 4], 48 # xmm0 = xmm0[0,1,2],mem[0] - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 3 - pand xmm5, xmmword ptr [rip + .LCPI10_2] - packssdw xmm1, xmm1 - packsswb xmm1, xmm1 - pand xmm1, xmm15 - psllw xmm1, 4 - pand xmm1, xmm12 + pmaxub xmm5, xmm13 + pcmpeqb xmm5, xmm1 + movzx edx, byte ptr [rdi + rax + 17] + movd xmm0, edx + mov r13, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r13 + 6], 1 + pinsrb xmm4, byte ptr [rdi + r12 + 6], 2 + pinsrb xmm4, byte ptr [rdi + r15 + 6], 3 + pinsrb xmm4, byte ptr [rdi + r9 + 6], 4 + pinsrb xmm4, byte ptr [rdi + rsi + 6], 5 + pinsrb xmm4, byte ptr [rdi + r8 + 6], 6 + pinsrb xmm4, byte ptr [rdi + r11 + 6], 7 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rdx + 6], 8 + pinsrb xmm4, byte ptr [rdi + rcx + 6], 9 + pinsrb xmm4, byte ptr [rdi + rbx + 6], 10 + pinsrb xmm4, byte ptr [rdi + r10 + 6], 11 + mov r14, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r14 + 6], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax + 6], 13 + mov rax, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax + 6], 14 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax + 6], 15 + movdqa xmm3, xmmword ptr [rsp + 304] # 16-byte Reload + pinsrb xmm3, byte ptr [rdi + r13 + 7], 1 + pinsrb xmm3, byte ptr [rdi + r12 + 7], 2 + pinsrb xmm3, byte ptr [rdi + r15 + 7], 3 + pinsrb xmm3, byte ptr [rdi + r9 + 7], 4 + pinsrb xmm3, byte ptr [rdi + rsi + 7], 5 + pinsrb xmm3, byte ptr [rdi + r8 + 7], 6 + pinsrb xmm3, byte ptr [rdi + r11 + 7], 7 + pinsrb xmm3, byte ptr [rdi + rdx + 7], 8 + mov r13, rdx + pinsrb xmm3, byte ptr [rdi + rcx + 7], 9 + pinsrb xmm3, byte ptr [rdi + rbx + 7], 10 + pinsrb xmm3, byte ptr [rdi + r10 + 7], 11 + pinsrb xmm3, byte ptr [rdi + r14 + 7], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rax + 7], 13 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rsi + 7], 14 + mov rcx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rcx + 7], 15 + movdqa xmm1, xmmword ptr [rip + .LCPI10_19] # xmm1 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm12, xmm1 + movdqa xmm1, xmmword ptr [rip + .LCPI10_20] # xmm1 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] + pand xmm5, xmm1 + por xmm5, xmm12 + movdqa xmm1, xmm4 + pmaxub xmm1, xmm13 + pcmpeqb xmm1, xmm4 + mov r8, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + r8 + 18] + movd xmm4, edx + movdqa xmm7, xmmword ptr [rip + .LCPI10_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm1, xmm7 por xmm1, xmm5 - movss xmm5, dword ptr [rsi - 384] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rsi - 256], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rsi - 128], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - por xmm1, xmm4 - movaps xmm4, xmm13 - cmpleps xmm4, xmm3 - movaps xmm3, xmm13 - cmpleps xmm3, xmm0 - insertps xmm5, dword ptr [rsi], 48 # xmm5 = xmm5[0,1,2],mem[0] - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 - pand xmm4, xmm15 - psllw xmm4, 5 - pand xmm4, xmm14 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 6 - pand xmm3, xmm9 - por xmm3, xmm4 - movaps xmm0, xmm13 - cmpleps xmm0, xmm5 - packssdw xmm0, xmm0 - packsswb xmm0, xmm0 - psllw xmm0, 7 - pand xmm0, xmm10 + movzx edx, byte ptr [rdi + r8 + 19] + movd xmm5, edx + por xmm1, xmm2 + movdqa xmm2, xmm3 + pmaxub xmm2, xmm13 + pcmpeqb xmm2, xmm3 + movdqa xmm12, xmm2 + movzx edx, byte ptr [rdi + r8 + 20] + movd xmm2, edx + movdqa xmm3, xmmword ptr [rsp + 240] # 16-byte Reload + mov rax, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rax + 9], 1 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rbx + 9], 2 + pinsrb xmm3, byte ptr [rdi + r15 + 9], 3 + pinsrb xmm3, byte ptr [rdi + r9 + 9], 4 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r10 + 9], 5 + mov r11, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r11 + 9], 6 + mov r14, qword ptr [rsp + 256] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r14 + 9], 7 + mov r12, r13 + pinsrb xmm3, byte ptr [rdi + r13 + 9], 8 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rdx + 9], 9 + mov r13, qword ptr [rsp + 288] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + r13 + 9], 10 + mov rdx, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rdx + 9], 11 + mov rdx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rdx + 9], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm3, byte ptr [rdi + rdx + 9], 13 + pinsrb xmm3, byte ptr [rdi + rsi + 9], 14 + pinsrb xmm3, byte ptr [rdi + rcx + 9], 15 + movdqa xmm7, xmmword ptr [rip + .LCPI10_6] # xmm7 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm12, xmm7 + por xmm12, xmm1 + movdqa xmmword ptr [rsp + 240], xmm12 # 16-byte Spill + movdqa xmm7, xmm3 + pmaxub xmm7, xmm13 + pcmpeqb xmm7, xmm3 + movzx edx, byte ptr [rdi + r8 + 21] + movd xmm3, edx + pinsrb xmm8, byte ptr [rdi + rax + 10], 1 + pinsrb xmm8, byte ptr [rdi + rbx + 10], 2 + pinsrb xmm8, byte ptr [rdi + r15 + 10], 3 + pinsrb xmm8, byte ptr [rdi + r9 + 10], 4 + mov rsi, r10 + pinsrb xmm8, byte ptr [rdi + r10 + 10], 5 + mov r8, r11 + pinsrb xmm8, byte ptr [rdi + r11 + 10], 6 + mov r11, r14 + pinsrb xmm8, byte ptr [rdi + r14 + 10], 7 + pinsrb xmm8, byte ptr [rdi + r12 + 10], 8 + mov rcx, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rcx + 10], 9 + mov rbx, r13 + pinsrb xmm8, byte ptr [rdi + r13 + 10], 10 + mov r10, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r10 + 10], 11 + mov r12, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r12 + 10], 12 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r13 + 10], 13 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + rdx + 10], 14 + mov r14, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm8, byte ptr [rdi + r14 + 10], 15 + pinsrb xmm10, byte ptr [rdi + rax + 11], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rax + 11], 2 + pinsrb xmm10, byte ptr [rdi + r15 + 11], 3 + pinsrb xmm10, byte ptr [rdi + r9 + 11], 4 + pinsrb xmm10, byte ptr [rdi + rsi + 11], 5 + pinsrb xmm10, byte ptr [rdi + r8 + 11], 6 + pinsrb xmm10, byte ptr [rdi + r11 + 11], 7 + mov rax, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [rdi + rax + 11], 8 + pinsrb xmm10, byte ptr [rdi + rcx + 11], 9 + pinsrb xmm10, byte ptr [rdi + rbx + 11], 10 + pinsrb xmm10, byte ptr [rdi + r10 + 11], 11 + pinsrb xmm10, byte ptr [rdi + r12 + 11], 12 + mov rax, r12 + pinsrb xmm10, byte ptr [rdi + r13 + 11], 13 + pinsrb xmm10, byte ptr [rdi + rdx + 11], 14 + pinsrb xmm10, byte ptr [rdi + r14 + 11], 15 + pand xmm7, xmmword ptr [rip + .LCPI10_16] + psubb xmm7, xmm9 + movdqa xmm1, xmm8 + pmaxub xmm1, xmm13 + pcmpeqb xmm1, xmm8 + movdqa xmm9, xmm10 + pmaxub xmm9, xmm13 + pcmpeqb xmm9, xmm10 + mov rdx, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + rdx + 22] + movd xmm10, edx + mov r12, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r12 + 12], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rdx + 12], 2 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r14 + 12], 3 + pinsrb xmm6, byte ptr [rdi + r9 + 12], 4 + pinsrb xmm6, byte ptr [rdi + rsi + 12], 5 + pinsrb xmm6, byte ptr [rdi + r8 + 12], 6 + pinsrb xmm6, byte ptr [rdi + r11 + 12], 7 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + rdx + 12], 8 + pinsrb xmm6, byte ptr [rdi + rcx + 12], 9 + pinsrb xmm6, byte ptr [rdi + rbx + 12], 10 + pinsrb xmm6, byte ptr [rdi + r10 + 12], 11 + pinsrb xmm6, byte ptr [rdi + rax + 12], 12 + pinsrb xmm6, byte ptr [rdi + r13 + 12], 13 + mov r15, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r15 + 12], 14 + mov r13, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [rdi + r13 + 12], 15 + pinsrb xmm15, byte ptr [rdi + r12 + 13], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rdx + 13], 2 + pinsrb xmm15, byte ptr [rdi + r14 + 13], 3 + mov r12, r14 + pinsrb xmm15, byte ptr [rdi + r9 + 13], 4 + pinsrb xmm15, byte ptr [rdi + rsi + 13], 5 + pinsrb xmm15, byte ptr [rdi + r8 + 13], 6 + pinsrb xmm15, byte ptr [rdi + r11 + 13], 7 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + rdx + 13], 8 + pinsrb xmm15, byte ptr [rdi + rcx + 13], 9 + pinsrb xmm15, byte ptr [rdi + rbx + 13], 10 + pinsrb xmm15, byte ptr [rdi + r10 + 13], 11 + pinsrb xmm15, byte ptr [rdi + rax + 13], 12 + mov r13, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r13 + 13], 13 + pinsrb xmm15, byte ptr [rdi + r15 + 13], 14 + pand xmm1, xmmword ptr [rip + .LCPI10_17] + pand xmm9, xmmword ptr [rip + .LCPI10_18] + por xmm9, xmm1 + mov rax, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + rax + 23] + movd xmm8, edx + mov r8, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm15, byte ptr [rdi + r8 + 13], 15 + por xmm9, xmm7 + movdqa xmm1, xmm6 + pmaxub xmm1, xmm13 + pcmpeqb xmm1, xmm6 + movdqa xmm7, xmm15 + pmaxub xmm7, xmm13 + pcmpeqb xmm7, xmm15 + movzx edx, byte ptr [rdi + rax + 25] + movd xmm15, edx + mov r14, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r14 + 14], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rax + 14], 2 + pinsrb xmm14, byte ptr [rdi + r12 + 14], 3 + pinsrb xmm14, byte ptr [rdi + r9 + 14], 4 + pinsrb xmm14, byte ptr [rdi + rsi + 14], 5 + mov r12, rsi + mov rdx, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rdx + 14], 6 + pinsrb xmm14, byte ptr [rdi + r11 + 14], 7 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r15 + 14], 8 + mov rdx, rcx + pinsrb xmm14, byte ptr [rdi + rcx + 14], 9 + pinsrb xmm14, byte ptr [rdi + rbx + 14], 10 + mov rsi, r10 + pinsrb xmm14, byte ptr [rdi + r10 + 14], 11 + mov rcx, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + rcx + 14], 12 + pinsrb xmm14, byte ptr [rdi + r13 + 14], 13 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm14, byte ptr [rdi + r10 + 14], 14 + pinsrb xmm14, byte ptr [rdi + r8 + 14], 15 + pinsrb xmm11, byte ptr [rdi + r14 + 15], 1 + pinsrb xmm11, byte ptr [rdi + rax + 15], 2 + mov rax, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rax + 15], 3 + pinsrb xmm11, byte ptr [rdi + r9 + 15], 4 + pinsrb xmm11, byte ptr [rdi + r12 + 15], 5 + mov r8, qword ptr [rsp + 224] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + r8 + 15], 6 + pinsrb xmm11, byte ptr [rdi + r11 + 15], 7 + pinsrb xmm11, byte ptr [rdi + r15 + 15], 8 + pinsrb xmm11, byte ptr [rdi + rdx + 15], 9 + pinsrb xmm11, byte ptr [rdi + rbx + 15], 10 + pinsrb xmm11, byte ptr [rdi + rsi + 15], 11 + pinsrb xmm11, byte ptr [rdi + rcx + 15], 12 + pinsrb xmm11, byte ptr [rdi + r13 + 15], 13 + pinsrb xmm11, byte ptr [rdi + r10 + 15], 14 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm11, byte ptr [rdi + rax + 15], 15 + pand xmm1, xmmword ptr [rip + .LCPI10_19] + pand xmm7, xmmword ptr [rip + .LCPI10_20] + por xmm7, xmm1 + movdqa xmm1, xmm14 + pmaxub xmm1, xmm13 + pcmpeqb xmm1, xmm14 + mov r10, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + r10 + 26] + movd xmm6, edx + pand xmm1, xmmword ptr [rip + .LCPI10_21] + por xmm1, xmm7 + movzx edx, byte ptr [rdi + r10 + 27] + movd xmm7, edx + por xmm1, xmm9 + movdqa xmm14, xmm11 + pmaxub xmm14, xmm13 + pcmpeqb xmm14, xmm11 + movzx edx, byte ptr [rdi + r10 + 28] + movd xmm9, edx + pinsrb xmm0, byte ptr [rdi + r14 + 17], 1 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rcx + 17], 2 + mov r12, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r12 + 17], 3 + pinsrb xmm0, byte ptr [rdi + r9 + 17], 4 + mov rsi, qword ptr [rsp + 208] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rsi + 17], 5 + pinsrb xmm0, byte ptr [rdi + r8 + 17], 6 + pinsrb xmm0, byte ptr [rdi + r11 + 17], 7 + mov rdx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 17], 8 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 17], 9 + pinsrb xmm0, byte ptr [rdi + rbx + 17], 10 + mov r15, qword ptr [rsp + 176] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r15 + 17], 11 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + r13 + 17], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 17], 13 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [rdi + rdx + 17], 14 + pinsrb xmm0, byte ptr [rdi + rax + 17], 15 + pand xmm14, xmmword ptr [rip + .LCPI10_6] + por xmm14, xmm1 + movdqa xmm1, xmm0 + movdqa xmm12, xmm13 + pmaxub xmm1, xmm13 + pcmpeqb xmm1, xmm0 + movzx edx, byte ptr [rdi + r10 + 29] + movd xmm0, edx + pinsrb xmm4, byte ptr [rdi + r14 + 18], 1 + pinsrb xmm4, byte ptr [rdi + rcx + 18], 2 + pinsrb xmm4, byte ptr [rdi + r12 + 18], 3 + pinsrb xmm4, byte ptr [rdi + r9 + 18], 4 + pinsrb xmm4, byte ptr [rdi + rsi + 18], 5 + pinsrb xmm4, byte ptr [rdi + r8 + 18], 6 + pinsrb xmm4, byte ptr [rdi + r11 + 18], 7 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rcx + 18], 8 + mov r10, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r10 + 18], 9 + mov r9, rbx + pinsrb xmm4, byte ptr [rdi + rbx + 18], 10 + mov rbx, r15 + pinsrb xmm4, byte ptr [rdi + r15 + 18], 11 + mov r15, r13 + pinsrb xmm4, byte ptr [rdi + r13 + 18], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rdx + 18], 13 + mov r13, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r13 + 18], 14 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax + 18], 15 + mov r14, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + r14 + 19], 1 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rax + 19], 2 + pinsrb xmm5, byte ptr [rdi + r12 + 19], 3 + mov rax, qword ptr [rsp + 272] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rax + 19], 4 + pinsrb xmm5, byte ptr [rdi + rsi + 19], 5 + pinsrb xmm5, byte ptr [rdi + r8 + 19], 6 + pinsrb xmm5, byte ptr [rdi + r11 + 19], 7 + pinsrb xmm5, byte ptr [rdi + rcx + 19], 8 + pinsrb xmm5, byte ptr [rdi + r10 + 19], 9 + pinsrb xmm5, byte ptr [rdi + r9 + 19], 10 + pinsrb xmm5, byte ptr [rdi + rbx + 19], 11 + pinsrb xmm5, byte ptr [rdi + r15 + 19], 12 + pinsrb xmm5, byte ptr [rdi + rdx + 19], 13 + pinsrb xmm5, byte ptr [rdi + r13 + 19], 14 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm5, byte ptr [rdi + rdx + 19], 15 + pand xmm1, xmmword ptr [rip + .LCPI10_16] + psubb xmm1, xmmword ptr [rsp + 352] # 16-byte Folded Reload + movdqa xmm13, xmm4 + pmaxub xmm13, xmm12 + pcmpeqb xmm13, xmm4 + movdqa xmm11, xmm5 + pmaxub xmm11, xmm12 + pcmpeqb xmm11, xmm5 + mov r14, qword ptr [rsp + 144] # 8-byte Reload + movzx edx, byte ptr [rdi + r14 + 30] + movd xmm4, edx + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rdx + 20], 1 + pinsrb xmm3, byte ptr [rdi + rdx + 21], 1 + pinsrb xmm10, byte ptr [rdi + rdx + 22], 1 + pinsrb xmm8, byte ptr [rdi + rdx + 23], 1 + pinsrb xmm15, byte ptr [rdi + rdx + 25], 1 + pinsrb xmm6, byte ptr [rdi + rdx + 26], 1 + pinsrb xmm7, byte ptr [rdi + rdx + 27], 1 + pinsrb xmm9, byte ptr [rdi + rdx + 28], 1 + pinsrb xmm0, byte ptr [rdi + rdx + 29], 1 + movzx r14d, byte ptr [rdi + r14 + 31] + pinsrb xmm4, byte ptr [rdi + rdx + 30], 1 + movd xmm5, r14d + pinsrb xmm5, byte ptr [rdi + rdx + 31], 1 + mov rdx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rdx + 20], 2 + pinsrb xmm3, byte ptr [rdi + rdx + 21], 2 + pinsrb xmm10, byte ptr [rdi + rdx + 22], 2 + pinsrb xmm8, byte ptr [rdi + rdx + 23], 2 + pinsrb xmm15, byte ptr [rdi + rdx + 25], 2 + pinsrb xmm6, byte ptr [rdi + rdx + 26], 2 + pinsrb xmm7, byte ptr [rdi + rdx + 27], 2 + pinsrb xmm9, byte ptr [rdi + rdx + 28], 2 + pinsrb xmm0, byte ptr [rdi + rdx + 29], 2 + pinsrb xmm4, byte ptr [rdi + rdx + 30], 2 + pinsrb xmm5, byte ptr [rdi + rdx + 31], 2 + mov r14, r12 + pinsrb xmm2, byte ptr [rdi + r12 + 20], 3 + pinsrb xmm2, byte ptr [rdi + rax + 20], 4 + pinsrb xmm2, byte ptr [rdi + rsi + 20], 5 + pinsrb xmm2, byte ptr [rdi + r8 + 20], 6 + pinsrb xmm2, byte ptr [rdi + r11 + 20], 7 + pinsrb xmm2, byte ptr [rdi + rcx + 20], 8 + pinsrb xmm2, byte ptr [rdi + r10 + 20], 9 + pinsrb xmm2, byte ptr [rdi + r9 + 20], 10 + pinsrb xmm2, byte ptr [rdi + rbx + 20], 11 + pinsrb xmm2, byte ptr [rdi + r15 + 20], 12 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + r12 + 20], 13 + pinsrb xmm2, byte ptr [rdi + r13 + 20], 14 + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [rdi + rdx + 20], 15 + pinsrb xmm3, byte ptr [rdi + r14 + 21], 3 + pinsrb xmm3, byte ptr [rdi + rax + 21], 4 + pinsrb xmm3, byte ptr [rdi + rsi + 21], 5 + pinsrb xmm3, byte ptr [rdi + r8 + 21], 6 + pinsrb xmm3, byte ptr [rdi + r11 + 21], 7 + pinsrb xmm3, byte ptr [rdi + rcx + 21], 8 + pinsrb xmm3, byte ptr [rdi + r10 + 21], 9 + pinsrb xmm3, byte ptr [rdi + r9 + 21], 10 + pinsrb xmm3, byte ptr [rdi + rbx + 21], 11 + pinsrb xmm3, byte ptr [rdi + r15 + 21], 12 + pinsrb xmm3, byte ptr [rdi + r12 + 21], 13 + pinsrb xmm3, byte ptr [rdi + r13 + 21], 14 + pand xmm13, xmmword ptr [rip + .LCPI10_17] + pand xmm11, xmmword ptr [rip + .LCPI10_18] + por xmm11, xmm13 + pinsrb xmm3, byte ptr [rdi + rdx + 21], 15 + por xmm11, xmm1 + movdqa xmm1, xmm2 + pmaxub xmm1, xmm12 + pcmpeqb xmm1, xmm2 + movdqa xmm2, xmm3 + pmaxub xmm2, xmm12 + pcmpeqb xmm2, xmm3 + pinsrb xmm10, byte ptr [rdi + r14 + 22], 3 + pinsrb xmm10, byte ptr [rdi + rax + 22], 4 + pinsrb xmm10, byte ptr [rdi + rsi + 22], 5 + pinsrb xmm10, byte ptr [rdi + r8 + 22], 6 + pinsrb xmm10, byte ptr [rdi + r11 + 22], 7 + pinsrb xmm10, byte ptr [rdi + rcx + 22], 8 + pinsrb xmm10, byte ptr [rdi + r10 + 22], 9 + pinsrb xmm10, byte ptr [rdi + r9 + 22], 10 + pinsrb xmm10, byte ptr [rdi + rbx + 22], 11 + pinsrb xmm10, byte ptr [rdi + r15 + 22], 12 + pinsrb xmm10, byte ptr [rdi + r12 + 22], 13 + pinsrb xmm10, byte ptr [rdi + r13 + 22], 14 + pinsrb xmm10, byte ptr [rdi + rdx + 22], 15 + pinsrb xmm8, byte ptr [rdi + r14 + 23], 3 + pinsrb xmm8, byte ptr [rdi + rax + 23], 4 + pinsrb xmm8, byte ptr [rdi + rsi + 23], 5 + pinsrb xmm8, byte ptr [rdi + r8 + 23], 6 + pinsrb xmm8, byte ptr [rdi + r11 + 23], 7 + pinsrb xmm8, byte ptr [rdi + rcx + 23], 8 + pinsrb xmm8, byte ptr [rdi + r10 + 23], 9 + pinsrb xmm8, byte ptr [rdi + r9 + 23], 10 + pinsrb xmm8, byte ptr [rdi + rbx + 23], 11 + pinsrb xmm8, byte ptr [rdi + r15 + 23], 12 + pinsrb xmm8, byte ptr [rdi + r12 + 23], 13 + pand xmm1, xmmword ptr [rip + .LCPI10_19] + pand xmm2, xmmword ptr [rip + .LCPI10_20] + por xmm2, xmm1 + movdqa xmm1, xmm10 + pmaxub xmm1, xmm12 + pcmpeqb xmm1, xmm10 + pinsrb xmm8, byte ptr [rdi + r13 + 23], 14 + pand xmm1, xmmword ptr [rip + .LCPI10_21] + por xmm1, xmm2 + pinsrb xmm8, byte ptr [rdi + rdx + 23], 15 + por xmm1, xmm11 + movdqa xmm10, xmm8 + pmaxub xmm10, xmm12 + pcmpeqb xmm10, xmm8 + pinsrb xmm15, byte ptr [rdi + r14 + 25], 3 + pinsrb xmm15, byte ptr [rdi + rax + 25], 4 + pinsrb xmm15, byte ptr [rdi + rsi + 25], 5 + pinsrb xmm15, byte ptr [rdi + r8 + 25], 6 + pinsrb xmm15, byte ptr [rdi + r11 + 25], 7 + pinsrb xmm15, byte ptr [rdi + rcx + 25], 8 + pinsrb xmm15, byte ptr [rdi + r10 + 25], 9 + pinsrb xmm15, byte ptr [rdi + r9 + 25], 10 + pinsrb xmm15, byte ptr [rdi + rbx + 25], 11 + pinsrb xmm15, byte ptr [rdi + r15 + 25], 12 + pinsrb xmm15, byte ptr [rdi + r12 + 25], 13 + pinsrb xmm15, byte ptr [rdi + r13 + 25], 14 + pinsrb xmm15, byte ptr [rdi + rdx + 25], 15 + movdqa xmm11, xmmword ptr [rip + .LCPI10_6] # xmm11 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm10, xmm11 + por xmm10, xmm1 + movdqa xmm3, xmm15 + pmaxub xmm3, xmm12 + pcmpeqb xmm3, xmm15 + pinsrb xmm6, byte ptr [rdi + r14 + 26], 3 + pinsrb xmm6, byte ptr [rdi + rax + 26], 4 + pinsrb xmm6, byte ptr [rdi + rsi + 26], 5 + pinsrb xmm6, byte ptr [rdi + r8 + 26], 6 + pinsrb xmm6, byte ptr [rdi + r11 + 26], 7 + pinsrb xmm6, byte ptr [rdi + rcx + 26], 8 + pinsrb xmm6, byte ptr [rdi + r10 + 26], 9 + pinsrb xmm6, byte ptr [rdi + r9 + 26], 10 + pinsrb xmm6, byte ptr [rdi + rbx + 26], 11 + pinsrb xmm6, byte ptr [rdi + r15 + 26], 12 + pinsrb xmm6, byte ptr [rdi + r12 + 26], 13 + pinsrb xmm6, byte ptr [rdi + r13 + 26], 14 + pinsrb xmm6, byte ptr [rdi + rdx + 26], 15 + pinsrb xmm7, byte ptr [rdi + r14 + 27], 3 + pinsrb xmm7, byte ptr [rdi + rax + 27], 4 + pinsrb xmm7, byte ptr [rdi + rsi + 27], 5 + pinsrb xmm7, byte ptr [rdi + r8 + 27], 6 + pinsrb xmm7, byte ptr [rdi + r11 + 27], 7 + pinsrb xmm7, byte ptr [rdi + rcx + 27], 8 + pinsrb xmm7, byte ptr [rdi + r10 + 27], 9 + pinsrb xmm7, byte ptr [rdi + r9 + 27], 10 + pinsrb xmm7, byte ptr [rdi + rbx + 27], 11 + pinsrb xmm7, byte ptr [rdi + r15 + 27], 12 + pinsrb xmm7, byte ptr [rdi + r12 + 27], 13 + pinsrb xmm7, byte ptr [rdi + r13 + 27], 14 + pinsrb xmm7, byte ptr [rdi + rdx + 27], 15 + pand xmm3, xmmword ptr [rip + .LCPI10_16] + psubb xmm3, xmmword ptr [rsp + 320] # 16-byte Folded Reload + movdqa xmm2, xmm6 + pmaxub xmm2, xmm12 + pcmpeqb xmm2, xmm6 + movdqa xmm1, xmm7 + pmaxub xmm1, xmm12 + pcmpeqb xmm1, xmm7 + pinsrb xmm9, byte ptr [rdi + r14 + 28], 3 + pinsrb xmm9, byte ptr [rdi + rax + 28], 4 + pinsrb xmm9, byte ptr [rdi + rsi + 28], 5 + pinsrb xmm9, byte ptr [rdi + r8 + 28], 6 + pinsrb xmm9, byte ptr [rdi + r11 + 28], 7 + pinsrb xmm9, byte ptr [rdi + rcx + 28], 8 + pinsrb xmm9, byte ptr [rdi + r10 + 28], 9 + pinsrb xmm9, byte ptr [rdi + r9 + 28], 10 + pinsrb xmm9, byte ptr [rdi + rbx + 28], 11 + pinsrb xmm9, byte ptr [rdi + r15 + 28], 12 + pinsrb xmm9, byte ptr [rdi + r12 + 28], 13 + pinsrb xmm9, byte ptr [rdi + r13 + 28], 14 + pinsrb xmm9, byte ptr [rdi + rdx + 28], 15 + pinsrb xmm0, byte ptr [rdi + r14 + 29], 3 + pinsrb xmm0, byte ptr [rdi + rax + 29], 4 + pinsrb xmm0, byte ptr [rdi + rsi + 29], 5 + pinsrb xmm0, byte ptr [rdi + r8 + 29], 6 + pinsrb xmm0, byte ptr [rdi + r11 + 29], 7 + pinsrb xmm0, byte ptr [rdi + rcx + 29], 8 + pinsrb xmm0, byte ptr [rdi + r10 + 29], 9 + pinsrb xmm0, byte ptr [rdi + r9 + 29], 10 + pinsrb xmm0, byte ptr [rdi + rbx + 29], 11 + pinsrb xmm0, byte ptr [rdi + r15 + 29], 12 + pinsrb xmm0, byte ptr [rdi + r12 + 29], 13 + pinsrb xmm0, byte ptr [rdi + r13 + 29], 14 + pinsrb xmm0, byte ptr [rdi + rdx + 29], 15 + pand xmm2, xmmword ptr [rip + .LCPI10_17] + pand xmm1, xmmword ptr [rip + .LCPI10_18] + por xmm1, xmm2 + por xmm1, xmm3 + movdqa xmm2, xmm9 + pmaxub xmm2, xmm12 + pcmpeqb xmm2, xmm9 + movdqa xmm3, xmm0 + pmaxub xmm3, xmm12 + pcmpeqb xmm3, xmm0 + pinsrb xmm4, byte ptr [rdi + r14 + 30], 3 + pinsrb xmm5, byte ptr [rdi + r14 + 31], 3 + pinsrb xmm4, byte ptr [rdi + rax + 30], 4 + pinsrb xmm5, byte ptr [rdi + rax + 31], 4 + pinsrb xmm4, byte ptr [rdi + rsi + 30], 5 + pinsrb xmm5, byte ptr [rdi + rsi + 31], 5 + pinsrb xmm4, byte ptr [rdi + r8 + 30], 6 + pinsrb xmm5, byte ptr [rdi + r8 + 31], 6 + pinsrb xmm4, byte ptr [rdi + r11 + 30], 7 + pinsrb xmm5, byte ptr [rdi + r11 + 31], 7 + pinsrb xmm4, byte ptr [rdi + rcx + 30], 8 + pinsrb xmm5, byte ptr [rdi + rcx + 31], 8 + pinsrb xmm4, byte ptr [rdi + r10 + 30], 9 + pinsrb xmm5, byte ptr [rdi + r10 + 31], 9 + mov r12, qword ptr [rsp + 8] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + r9 + 30], 10 + pinsrb xmm5, byte ptr [rdi + r9 + 31], 10 + pinsrb xmm4, byte ptr [rdi + rbx + 30], 11 + pinsrb xmm5, byte ptr [rdi + rbx + 31], 11 + pinsrb xmm4, byte ptr [rdi + r15 + 30], 12 + pinsrb xmm5, byte ptr [rdi + r15 + 31], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm4, byte ptr [rdi + rax + 30], 13 + pinsrb xmm5, byte ptr [rdi + rax + 31], 13 + pinsrb xmm4, byte ptr [rdi + r13 + 30], 14 + pinsrb xmm5, byte ptr [rdi + r13 + 31], 14 + pinsrb xmm4, byte ptr [rdi + rdx + 30], 15 + pand xmm2, xmmword ptr [rip + .LCPI10_19] + pand xmm3, xmmword ptr [rip + .LCPI10_20] + por xmm3, xmm2 + movdqa xmm0, xmm4 + pmaxub xmm0, xmm12 + pcmpeqb xmm0, xmm4 + pinsrb xmm5, byte ptr [rdi + rdx + 31], 15 + pand xmm0, xmmword ptr [rip + .LCPI10_21] por xmm0, xmm3 por xmm0, xmm1 - punpckldq xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1] - punpcklbw xmm8, xmm2 # xmm8 = xmm8[0],xmm2[0],xmm8[1],xmm2[1],xmm8[2],xmm2[2],xmm8[3],xmm2[3],xmm8[4],xmm2[4],xmm8[5],xmm2[5],xmm8[6],xmm2[6],xmm8[7],xmm2[7] - pshufb xmm8, xmmword ptr [rip + .LCPI10_7] # xmm8 = xmm8[0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] - movdqu xmmword ptr [r14 + 4*rcx], xmm8 - add rcx, 4 - add rsi, 512 - cmp rax, rcx - jne .LBB10_183 -# %bb.184: - cmp r11, rax - jne .LBB10_185 - jmp .LBB10_188 + movdqa xmm1, xmm5 + pmaxub xmm1, xmm12 + pcmpeqb xmm1, xmm5 + pand xmm1, xmm11 + por xmm1, xmm0 + movdqa xmm0, xmm10 + punpcklbw xmm0, xmm1 # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7] + movdqa xmm4, xmmword ptr [rsp + 240] # 16-byte Reload + movdqa xmm2, xmm4 + punpcklbw xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0],xmm2[1],xmm14[1],xmm2[2],xmm14[2],xmm2[3],xmm14[3],xmm2[4],xmm14[4],xmm2[5],xmm14[5],xmm2[6],xmm14[6],xmm2[7],xmm14[7] + movdqa xmm3, xmm2 + punpcklwd xmm3, xmm0 # xmm3 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3] + punpckhwd xmm2, xmm0 # xmm2 = xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7] + punpckhbw xmm10, xmm1 # xmm10 = xmm10[8],xmm1[8],xmm10[9],xmm1[9],xmm10[10],xmm1[10],xmm10[11],xmm1[11],xmm10[12],xmm1[12],xmm10[13],xmm1[13],xmm10[14],xmm1[14],xmm10[15],xmm1[15] + punpckhbw xmm4, xmm14 # xmm4 = xmm4[8],xmm14[8],xmm4[9],xmm14[9],xmm4[10],xmm14[10],xmm4[11],xmm14[11],xmm4[12],xmm14[12],xmm4[13],xmm14[13],xmm4[14],xmm14[14],xmm4[15],xmm14[15] + movdqa xmm0, xmm4 + punpcklwd xmm0, xmm10 # xmm0 = xmm0[0],xmm10[0],xmm0[1],xmm10[1],xmm0[2],xmm10[2],xmm0[3],xmm10[3] + punpckhwd xmm4, xmm10 # xmm4 = xmm4[4],xmm10[4],xmm4[5],xmm10[5],xmm4[6],xmm10[6],xmm4[7],xmm10[7] + mov rcx, qword ptr [rsp + 336] # 8-byte Reload + movdqu xmmword ptr [r12 + 4*rcx + 48], xmm4 + movdqu xmmword ptr [r12 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r12 + 4*rcx + 16], xmm2 + movdqu xmmword ptr [r12 + 4*rcx], xmm3 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + jne .LBB10_73 +# %bb.74: + mov rcx, qword ptr [rsp + 376] # 8-byte Reload + cmp rcx, qword ptr [rsp + 384] # 8-byte Folded Reload + mov r13b, byte ptr [rsp] # 1-byte Reload + mov rsi, qword ptr [rsp + 448] # 8-byte Reload + mov r14, qword ptr [rsp + 72] # 8-byte Reload + jne .LBB10_75 + jmp .LBB10_78 .Lfunc_end10: .size comparison_greater_equal_arr_scalar_sse4, .Lfunc_end10-comparison_greater_equal_arr_scalar_sse4 # -- End function @@ -55651,172 +57261,186 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr and rsp, -16 sub rsp, 304 # kill: def $r9d killed $r9d def $r9 - mov r11, r8 - mov r15, rcx + mov r15, r8 + mov r12, rcx cmp edi, 6 - jg .LBB11_26 + jg .LBB11_18 # %bb.1: cmp edi, 3 - jle .LBB11_2 -# %bb.10: + jle .LBB11_35 +# %bb.2: cmp edi, 4 - je .LBB11_99 -# %bb.11: + je .LBB11_57 +# %bb.3: cmp edi, 5 - je .LBB11_114 -# %bb.12: + je .LBB11_70 +# %bb.4: cmp edi, 6 - jne .LBB11_201 -# %bb.13: - mov r14d, dword ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + jne .LBB11_215 +# %bb.5: + mov r8d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_17 -# %bb.14: - movsxd rax, r9d + je .LBB11_11 +# %bb.6: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB11_9 +# %bb.7: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_15: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] - lea rdx, [rdx + 4] - mov esi, 0 - adc sil, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r15 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB11_8: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r15 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_15 -# %bb.16: - add r15, 1 -.LBB11_17: - sar r10, 5 - cmp r11, 32 - jl .LBB11_21 -# %bb.18: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_8 +.LBB11_9: + sub r15, r14 + je .LBB11_215 +# %bb.10: + add r12, 1 +.LBB11_11: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB11_15 +# %bb.12: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_19: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 120], r15 # 8-byte Spill - cmp r14d, dword ptr [rdx + 124] - setae byte ptr [rsp] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 120] - setae byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 116] +.LBB11_13: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8d, dword ptr [rdx + 124] setae byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 112] - setae byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 108] + cmp r8d, dword ptr [rdx + 120] setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 104] + cmp r8d, dword ptr [rdx + 116] + setae byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 112] setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 100] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 92] + cmp r8d, dword ptr [rdx + 108] + setae byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 104] setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 88] - setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 84] + cmp r8d, dword ptr [rdx + 100] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 92] setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 80] + cmp r8d, dword ptr [rdx + 88] + setae byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 84] setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 76] + cmp r8d, dword ptr [rdx + 80] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 76] setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 72] + cmp r8d, dword ptr [rdx + 72] setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 68] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 60] - setae r8b - cmp r14d, dword ptr [rdx + 56] - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 52] + cmp r8d, dword ptr [rdx + 68] setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 48] + cmp r8d, dword ptr [rdx + 60] + setae dil + cmp r8d, dword ptr [rdx + 56] + setae byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] setae r11b - cmp r14d, dword ptr [rdx + 44] + cmp r8d, dword ptr [rdx + 44] setae r10b - cmp r14d, dword ptr [rdx + 40] + cmp r8d, dword ptr [rdx + 40] setae r9b - cmp r14d, dword ptr [rdx + 36] - setae dil - cmp r14d, dword ptr [rdx + 28] + cmp r8d, dword ptr [rdx + 36] + setae sil + cmp r8d, dword ptr [rdx + 28] setae al - cmp r14d, dword ptr [rdx + 24] + cmp r8d, dword ptr [rdx + 24] setae bl - cmp r14d, dword ptr [rdx + 20] - setae sil - cmp r14d, dword ptr [rdx + 16] + cmp r8d, dword ptr [rdx + 20] setae cl - cmp r14d, dword ptr [rdx + 12] + cmp r8d, dword ptr [rdx + 16] setae r13b - cmp r14d, dword ptr [rdx + 8] + cmp r8d, dword ptr [rdx + 12] setae r12b - cmp r14d, dword ptr [rdx] - setae byte ptr [rsp + 224] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 4] + cmp r8d, dword ptr [rdx + 8] setae r15b - cmp r14d, dword ptr [rdx + 32] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 64] - setae byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 96] + cmp r8d, dword ptr [rdx] setae byte ptr [rsp + 144] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 2 + cmp r8d, dword ptr [rdx + 4] + setae r14b + cmp r8d, dword ptr [rdx + 32] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 64] + setae byte ptr [rsp + 208] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setae byte ptr [rsp + 160] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b - mov r15, qword ptr [rsp + 120] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 128] # 1-byte Folded Reload + or al, cl + mov byte ptr [r12], al + add sil, sil + add sil, byte ptr [rsp + 128] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 176] # 1-byte Folded Reload + add al, byte ptr [rsp + 208] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 2 @@ -55826,130 +57450,146 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al + mov byte ptr [r12 + 2], al movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al + mov byte ptr [r12 + 3], al sub rdx, -128 - add r15, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB11_19 -# %bb.20: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB11_21: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.22: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_137 -# %bb.23: - xor r11d, r11d - jmp .LBB11_24 -.LBB11_26: + add r12, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB11_13 +# %bb.14: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB11_15: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB11_215 +# %bb.16: + or rax, 1 + cmp r15, rax + jne .LBB11_185 +# %bb.17: + xor r14d, r14d + jmp .LBB11_187 +.LBB11_18: cmp edi, 8 - jle .LBB11_27 -# %bb.42: + jle .LBB11_42 +# %bb.19: cmp edi, 9 - je .LBB11_157 -# %bb.43: + je .LBB11_84 +# %bb.20: cmp edi, 11 - je .LBB11_172 -# %bb.44: + je .LBB11_97 +# %bb.21: cmp edi, 12 - jne .LBB11_201 -# %bb.45: - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + jne .LBB11_215 +# %bb.22: + mov r14, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 - movsd xmm0, qword ptr [rsi] # xmm0 = mem[0],zero sub r9d, eax - je .LBB11_49 -# %bb.46: - movsxd rax, r9d + je .LBB11_28 +# %bb.23: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB11_26 +# %bb.24: + movsxd rsi, r9d + movq xmm0, r14 + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_47: # =>This Inner Loop Header: Depth=1 - ucomisd xmm0, qword ptr [rdx] - lea rdx, [rdx + 8] - mov esi, 0 - adc sil, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, sil +.LBB11_25: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + ucomisd xmm0, qword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r15 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB11_47 -# %bb.48: - add r15, 1 -.LBB11_49: - sar r10, 5 - cmp r11, 32 - jl .LBB11_53 -# %bb.50: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - mov qword ptr [rsp + 224], r10 # 8-byte Spill + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_25 +.LBB11_26: + sub r15, r8 + je .LBB11_215 +# %bb.27: + add r12, 1 +.LBB11_28: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB11_32 +# %bb.29: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 240], r14 # 8-byte Spill + movq xmm0, r14 + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 144], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_51: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 120], r15 # 8-byte Spill +.LBB11_30: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill ucomisd xmm0, qword ptr [rdx] setae byte ptr [rsp + 128] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 8] @@ -55959,15 +57599,15 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr ucomisd xmm0, qword ptr [rdx + 24] setae r13b ucomisd xmm0, qword ptr [rdx + 32] - setae byte ptr [rsp + 176] # 1-byte Folded Spill + setae byte ptr [rsp + 208] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 40] - setae byte ptr [rsp + 64] # 1-byte Folded Spill + setae byte ptr [rsp + 80] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 48] setae bl ucomisd xmm0, qword ptr [rdx + 56] setae r12b ucomisd xmm0, qword ptr [rdx + 64] - setae byte ptr [rsp + 112] # 1-byte Folded Spill + setae byte ptr [rsp + 120] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 72] setae sil ucomisd xmm0, qword ptr [rdx + 80] @@ -55979,39 +57619,39 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr ucomisd xmm0, qword ptr [rdx + 104] setae r15b ucomisd xmm0, qword ptr [rdx + 112] - setae byte ptr [rsp + 160] # 1-byte Folded Spill + setae byte ptr [rsp + 192] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 120] setae cl ucomisd xmm0, qword ptr [rdx + 128] setae byte ptr [rsp + 96] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 136] - setae byte ptr [rsp + 144] # 1-byte Folded Spill + setae byte ptr [rsp + 160] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 144] - setae byte ptr [rsp + 104] # 1-byte Folded Spill + setae byte ptr [rsp + 112] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 152] setae byte ptr [rsp + 88] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 160] - setae byte ptr [rsp + 80] # 1-byte Folded Spill + setae byte ptr [rsp + 104] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 168] setae byte ptr [rsp + 72] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 176] - setae byte ptr [rsp + 48] # 1-byte Folded Spill + setae byte ptr [rsp + 64] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 184] setae r14b ucomisd xmm0, qword ptr [rdx + 192] - setae byte ptr [rsp + 24] # 1-byte Folded Spill + setae byte ptr [rsp + 32] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 200] setae byte ptr [rsp + 56] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 208] - setae byte ptr [rsp + 32] # 1-byte Folded Spill + setae byte ptr [rsp + 48] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 216] - setae byte ptr [rsp + 40] # 1-byte Folded Spill + setae byte ptr [rsp + 24] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 224] - setae byte ptr [rsp + 8] # 1-byte Folded Spill - ucomisd xmm0, qword ptr [rdx + 232] setae byte ptr [rsp + 16] # 1-byte Folded Spill + ucomisd xmm0, qword ptr [rdx + 232] + setae byte ptr [rsp + 40] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 240] - setae byte ptr [rsp] # 1-byte Folded Spill + setae byte ptr [rsp + 8] # 1-byte Folded Spill ucomisd xmm0, qword ptr [rdx + 248] setae al add r9b, r9b @@ -56022,294 +57662,329 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl r11b, 2 or r11b, r9b add sil, sil - add sil, byte ptr [rsp + 112] # 1-byte Folded Reload + add sil, byte ptr [rsp + 120] # 1-byte Folded Reload shl r13b, 3 or r13b, r11b shl dil, 2 or dil, sil - movzx ebx, byte ptr [rsp + 176] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 208] # 1-byte Folded Reload shl bl, 4 or bl, r13b - mov esi, ebx + mov r9d, ebx + mov rsi, qword ptr [rsp + 136] # 8-byte Reload shl r8b, 3 or r8b, dil - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 5 - or bl, sil + or bl, r9b shl r10b, 4 or r10b, r8b shl r15b, 5 or r15b, r10b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 + movzx edi, byte ptr [rsp + 192] # 1-byte Folded Reload + shl dil, 6 shl cl, 7 - or cl, sil + or cl, dil or r12b, bl or cl, r15b - mov r15, qword ptr [rsp + 120] # 8-byte Reload - movzx ebx, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 160] # 1-byte Folded Reload add bl, bl add bl, byte ptr [rsp + 96] # 1-byte Folded Reload - mov esi, ebx - movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload + mov edi, ebx + movzx ebx, byte ptr [rsp + 112] # 1-byte Folded Reload shl bl, 2 - or bl, sil - mov esi, ebx + or bl, dil + mov edi, ebx movzx ebx, byte ptr [rsp + 88] # 1-byte Folded Reload shl bl, 3 - or bl, sil - mov esi, ebx - movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload + or bl, dil + mov edi, ebx + movzx ebx, byte ptr [rsp + 104] # 1-byte Folded Reload shl bl, 4 - or bl, sil - mov esi, ebx + or bl, dil + mov edi, ebx movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 5 - or bl, sil - mov byte ptr [r15], r12b - movzx esi, byte ptr [rsp + 48] # 1-byte Folded Reload - shl sil, 6 + or bl, dil + mov byte ptr [rsi], r12b + movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dil, 6 shl r14b, 7 - or r14b, sil - mov byte ptr [r15 + 1], cl + or r14b, dil + mov byte ptr [rsi + 1], cl or r14b, bl movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload add cl, cl - add cl, byte ptr [rsp + 24] # 1-byte Folded Reload + add cl, byte ptr [rsp + 32] # 1-byte Folded Reload mov ebx, ecx - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload shl cl, 2 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload shl cl, 3 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload shl cl, 4 or cl, bl mov ebx, ecx - movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload shl cl, 5 or cl, bl - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload shl bl, 6 shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], r14b - mov byte ptr [r15 + 3], al + mov byte ptr [rsi + 2], r14b + mov byte ptr [rsi + 3], al add rdx, 256 - add r15, 4 - add qword ptr [rsp + 224], -1 # 8-byte Folded Spill - jne .LBB11_51 -# %bb.52: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload -.LBB11_53: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.54: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_195 -# %bb.55: + add rsi, 4 + mov r12, rsi + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB11_30 +# %bb.31: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14, qword ptr [rsp + 240] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB11_32: + shl rax, 5 + mov r8, r15 + sub r8, rax + jle .LBB11_215 +# %bb.33: + movq xmm0, r14 + or rax, 1 + cmp r15, rax + jne .LBB11_189 +# %bb.34: xor r11d, r11d - jmp .LBB11_197 -.LBB11_2: + jmp .LBB11_191 +.LBB11_35: cmp edi, 2 - je .LBB11_56 -# %bb.3: + je .LBB11_111 +# %bb.36: cmp edi, 3 - jne .LBB11_201 -# %bb.4: + jne .LBB11_215 +# %bb.37: mov r14b, byte ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_8 -# %bb.5: - movsxd rax, r9d + je .LBB11_129 +# %bb.38: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB11_139 +# %bb.39: + movsxd rsi, r9d + mov r11, r8 .p2align 4, 0x90 -.LBB11_6: # =>This Inner Loop Header: Depth=1 +.LBB11_40: # =>This Inner Loop Header: Depth=1 + lea r13, [rdx + 1] cmp r14b, byte ptr [rdx] - lea rdx, [rdx + 1] - setge bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r15 + rsi] + setge dl + neg dl + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov rdi, r12 + movzx r9d, byte ptr [r12 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, dl + xor al, r9b + mov byte ptr [r12 + rbx], al + add rsi, 1 + mov rdx, r13 + add r11, -1 + jne .LBB11_40 +# %bb.41: + sub r15, r8 + jne .LBB11_140 + jmp .LBB11_215 +.LBB11_42: + cmp edi, 7 + je .LBB11_116 +# %bb.43: + cmp edi, 8 + jne .LBB11_215 +# %bb.44: + mov r8, qword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB11_50 +# %bb.45: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB11_48 +# %bb.46: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx + .p2align 4, 0x90 +.LBB11_47: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d - mov edi, 1 + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r9b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_6 -# %bb.7: - add r15, 1 -.LBB11_8: - sar r10, 5 - cmp r11, 32 - jl .LBB11_9 -# %bb.81: - cmp r10, 16 - mov byte ptr [rsp], r14b # 1-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 248], r10 # 8-byte Spill - jb .LBB11_82 -# %bb.83: - mov rax, r10 - shl rax, 5 - add rax, rdx - cmp r15, rax - jae .LBB11_85 -# %bb.84: - lea rax, [r15 + 4*r10] - cmp rdx, rax - jae .LBB11_85 -.LBB11_82: - xor eax, eax - mov qword ptr [rsp + 256], rax # 8-byte Spill - mov r13, r15 -.LBB11_88: - sub r10, qword ptr [rsp + 256] # 8-byte Folded Reload - mov qword ptr [rsp + 192], r10 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_47 +.LBB11_48: + sub r15, r14 + je .LBB11_215 +# %bb.49: + add r12, 1 +.LBB11_50: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB11_54 +# %bb.51: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_89: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rdx + 31] - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 30] - setge byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 29] - setge byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 28] - setge byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 27] - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 26] - setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 25] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 23] - setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 22] - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 21] - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 20] - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 19] - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 18] - setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 17] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 15] - setge r10b - cmp r14b, byte ptr [rdx + 14] - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 13] - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 12] - setge r12b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 11] - setge r15b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 10] - setge r14b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 9] - setge r11b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 7] - setge sil - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 6] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 5] - setge r9b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 4] - setge r8b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 3] - setge dil - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 2] - setge cl - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx] - setge byte ptr [rsp + 208] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 1] - setge al - mov rbx, r13 - movzx r13d, byte ptr [rsp] # 1-byte Folded Reload - cmp r13b, byte ptr [rdx + 8] - mov r13, rbx - setge byte ptr [rsp + 224] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload - cmp bl, byte ptr [rdx + 16] - setge byte ptr [rsp + 176] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload - cmp bl, byte ptr [rdx + 24] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - add al, al - add al, byte ptr [rsp + 208] # 1-byte Folded Reload - shl cl, 2 - or cl, al - shl dil, 3 - or dil, cl - shl r8b, 4 - or r8b, dil - shl r9b, 5 - or r9b, r8b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload - shl al, 6 - shl sil, 7 - or sil, al - or sil, r9b - mov byte ptr [r13], sil - add r11b, r11b - add r11b, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r14b, 2 - or r14b, r11b - shl r15b, 3 +.LBB11_52: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8, qword ptr [rdx + 248] + setae byte ptr [rsp + 8] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 240] + setae byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 232] + setae byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 224] + setae byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 216] + setae byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 208] + setae byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 200] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 184] + setae byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 176] + setae byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 168] + setae byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 160] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 152] + setae byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 144] + setae byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 136] + setae byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 120] + setae dil + cmp r8, qword ptr [rdx + 112] + setae byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 104] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 96] + setae r11b + cmp r8, qword ptr [rdx + 88] + setae r10b + cmp r8, qword ptr [rdx + 80] + setae r9b + cmp r8, qword ptr [rdx + 72] + setae sil + cmp r8, qword ptr [rdx + 56] + setae al + cmp r8, qword ptr [rdx + 48] + setae bl + cmp r8, qword ptr [rdx + 40] + setae cl + cmp r8, qword ptr [rdx + 32] + setae r13b + cmp r8, qword ptr [rdx + 24] + setae r12b + cmp r8, qword ptr [rdx + 16] + setae r15b + cmp r8, qword ptr [rdx] + setae byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 8] + setae r14b + cmp r8, qword ptr [rdx + 64] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 128] + setae byte ptr [rsp + 208] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setae byte ptr [rsp + 160] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r15b, 2 or r15b, r14b - shl r12b, 4 + shl r12b, 3 or r12b, r15b - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r13b, 4 + or r13b, r12b + mov r12, qword ptr [rsp + 136] # 8-byte Reload + shl cl, 5 + or cl, r13b + shl bl, 6 + shl al, 7 + or al, bl + or al, cl + mov byte ptr [r12], al + add sil, sil + add sil, byte ptr [rsp + 128] # 1-byte Folded Reload + shl r9b, 2 + or r9b, sil + shl r10b, 3 + or r10b, r9b + shl r11b, 4 + or r11b, r10b + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 - or al, r12b - movzx r14d, byte ptr [rsp] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + or al, r11b + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload shl cl, 6 - shl r10b, 7 - or r10b, cl - or r10b, al - mov byte ptr [r13 + 1], r10b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 176] # 1-byte Folded Reload + add al, byte ptr [rsp + 208] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 2 @@ -56319,34 +57994,34 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r13 + 2], al + mov byte ptr [r12 + 2], al movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -56354,398 +58029,430 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r13 + 3], al - add rdx, 32 - add r13, 4 - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB11_89 -# %bb.90: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - jmp .LBB11_91 -.LBB11_27: - cmp edi, 7 - je .LBB11_139 -# %bb.28: - cmp edi, 8 - jne .LBB11_201 -# %bb.29: - mov r14, qword ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + mov byte ptr [r12 + 3], al + add rdx, 256 + add r12, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB11_52 +# %bb.53: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB11_54: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB11_215 +# %bb.55: + or rax, 1 + cmp r15, rax + jne .LBB11_167 +# %bb.56: + xor r14d, r14d + jmp .LBB11_169 +.LBB11_57: + movzx r8d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_33 -# %bb.30: - movsxd rax, r9d + je .LBB11_63 +# %bb.58: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB11_61 +# %bb.59: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_31: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] - lea rdx, [rdx + 8] - mov esi, 0 - adc sil, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r15 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 +.LBB11_60: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r8w, word ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r15 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_31 -# %bb.32: - add r15, 1 -.LBB11_33: - sar r10, 5 - cmp r11, 32 - jl .LBB11_37 -# %bb.34: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_60 +.LBB11_61: + sub r15, r14 + je .LBB11_215 +# %bb.62: + add r12, 1 +.LBB11_63: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB11_67 +# %bb.64: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_35: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 120], r15 # 8-byte Spill - cmp r14, qword ptr [rdx + 248] - setae byte ptr [rsp] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 240] - setae byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 232] +.LBB11_65: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8w, word ptr [rdx + 62] setae byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 224] - setae byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 216] + cmp r8w, word ptr [rdx + 60] setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 208] + cmp r8w, word ptr [rdx + 58] + setae byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 56] setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 200] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 184] + cmp r8w, word ptr [rdx + 54] + setae byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 52] setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 176] + cmp r8w, word ptr [rdx + 50] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 46] setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 168] - setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 160] + cmp r8w, word ptr [rdx + 44] setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 152] + cmp r8w, word ptr [rdx + 42] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 40] setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 144] + cmp r8w, word ptr [rdx + 38] setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 136] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 120] - setae r8b - cmp r14, qword ptr [rdx + 112] - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 104] + cmp r8w, word ptr [rdx + 36] setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 96] + cmp r8w, word ptr [rdx + 34] + setae byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 30] + setae dil + cmp r8w, word ptr [rdx + 28] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 26] + setae byte ptr [rsp + 208] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 24] setae r11b - cmp r14, qword ptr [rdx + 88] + cmp r8w, word ptr [rdx + 22] setae r10b - cmp r14, qword ptr [rdx + 80] + cmp r8w, word ptr [rdx + 20] setae r9b - cmp r14, qword ptr [rdx + 72] - setae dil - cmp r14, qword ptr [rdx + 56] + cmp r8w, word ptr [rdx + 18] + setae sil + cmp r8w, word ptr [rdx + 14] setae al - cmp r14, qword ptr [rdx + 48] + cmp r8w, word ptr [rdx + 12] setae bl - cmp r14, qword ptr [rdx + 40] - setae sil - cmp r14, qword ptr [rdx + 32] + cmp r8w, word ptr [rdx + 10] setae cl - cmp r14, qword ptr [rdx + 24] + cmp r8w, word ptr [rdx + 8] setae r13b - cmp r14, qword ptr [rdx + 16] + cmp r8w, word ptr [rdx + 6] setae r12b - cmp r14, qword ptr [rdx] - setae byte ptr [rsp + 224] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 8] + cmp r8w, word ptr [rdx + 4] setae r15b - cmp r14, qword ptr [rdx + 64] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 128] - setae byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 192] + cmp r8w, word ptr [rdx] setae byte ptr [rsp + 144] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 2 + cmp r8w, word ptr [rdx + 2] + setae r14b + cmp r8w, word ptr [rdx + 16] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 32] + setae byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r8w, word ptr [rdx + 48] + setae byte ptr [rsp + 64] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b - mov r15, qword ptr [rsp + 120] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 128] # 1-byte Folded Reload + or al, cl + mov byte ptr [r12], al + add sil, sil + add sil, byte ptr [rsp + 128] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 192] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 176] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al + mov byte ptr [r12 + 2], al movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 64] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al - add rdx, 256 - add r15, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB11_35 -# %bb.36: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB11_37: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.38: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_155 -# %bb.39: - xor r11d, r11d - jmp .LBB11_40 -.LBB11_56: - mov r14b, byte ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + mov byte ptr [r12 + 3], al + add rdx, 64 + add r12, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB11_65 +# %bb.66: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB11_67: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB11_215 +# %bb.68: + or rax, 1 + cmp r15, rax + jne .LBB11_193 +# %bb.69: + xor r14d, r14d + jmp .LBB11_195 +.LBB11_70: + movzx r14d, word ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_60 -# %bb.57: - movsxd rax, r9d + je .LBB11_76 +# %bb.71: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB11_74 +# %bb.72: + movsxd rsi, r9d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_58: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rdx] - lea rdx, [rdx + 1] - mov esi, 0 - adc sil, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, sil +.LBB11_73: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 2] + cmp r14w, word ptr [rcx] + setge bl + neg bl + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - mov byte ptr [r15 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB11_58 -# %bb.59: - add r15, 1 -.LBB11_60: - sar r10, 5 - cmp r11, 32 - jl .LBB11_61 -# %bb.62: - cmp r10, 16 - mov byte ptr [rsp], r14b # 1-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 248], r10 # 8-byte Spill - jb .LBB11_63 -# %bb.64: - mov rax, r10 - shl rax, 5 + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d + mov edi, 1 + # kill: def $cl killed $cl killed $ecx + shl edi, cl + and dil, bl + xor dil, r9b + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_73 +.LBB11_74: + sub r15, r8 + je .LBB11_215 +# %bb.75: + add r12, 1 +.LBB11_76: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB11_130 +# %bb.77: + cmp rcx, 8 + mov dword ptr [rsp + 8], r14d # 4-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 184], rcx # 8-byte Spill + jb .LBB11_80 +# %bb.78: + mov rax, rcx + shl rax, 6 add rax, rdx - cmp r15, rax - jae .LBB11_66 -# %bb.65: - lea rax, [r15 + 4*r10] - cmp rdx, rax - jae .LBB11_66 -.LBB11_63: + cmp r12, rax + jae .LBB11_216 +# %bb.79: + lea rax, [r12 + 4*rcx] + cmp rax, rdx + jbe .LBB11_216 +.LBB11_80: xor eax, eax - mov qword ptr [rsp + 192], rax # 8-byte Spill - mov r13, r15 -.LBB11_69: - sub r10, qword ptr [rsp + 192] # 8-byte Folded Reload - mov qword ptr [rsp + 192], r10 # 8-byte Spill + mov qword ptr [rsp + 24], rax # 8-byte Spill + mov r13, r12 +.LBB11_81: + sub rcx, qword ptr [rsp + 24] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB11_70: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rdx + 31] - setae byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 30] - setae byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 29] - setae byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 28] - setae byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 27] - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 26] - setae byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 25] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 23] - setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 22] - setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 21] - setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 20] - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 19] - setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 18] - setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 17] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 15] - setae r10b - cmp r14b, byte ptr [rdx + 14] - setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 13] - setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14b, byte ptr [rdx + 12] - setae r12b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 11] - setae r15b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 10] - setae r14b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 9] - setae r11b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 7] - setae sil - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 6] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 5] - setae r9b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 4] - setae r8b - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 3] - setae dil - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 2] - setae cl - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx] - setae byte ptr [rsp + 208] # 1-byte Folded Spill - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - cmp al, byte ptr [rdx + 1] - setae al +.LBB11_82: # =>This Inner Loop Header: Depth=1 + cmp r14w, word ptr [rdx + 62] + setge byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 60] + setge byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 58] + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 56] + setge byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 54] + setge byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 52] + setge byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 50] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 46] + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 44] + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 42] + setge byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 40] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 38] + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 36] + setge byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 34] + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 30] + setge r10b + cmp r14w, word ptr [rdx + 28] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 26] + setge byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r14w, word ptr [rdx + 24] + setge r12b + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 22] + setge r15b + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 20] + setge r14b + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 18] + setge r11b + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 14] + setge sil + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 12] + setge byte ptr [rsp + 128] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 10] + setge r9b + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 8] + setge r8b + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 6] + setge dil + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 4] + setge cl + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx] + setge byte ptr [rsp + 240] # 1-byte Folded Spill + mov eax, dword ptr [rsp + 8] # 4-byte Reload + cmp ax, word ptr [rdx + 2] + setge al mov rbx, r13 - movzx r13d, byte ptr [rsp] # 1-byte Folded Reload - cmp r13b, byte ptr [rdx + 8] + mov r13d, dword ptr [rsp + 8] # 4-byte Reload + cmp r13w, word ptr [rdx + 16] mov r13, rbx - setae byte ptr [rsp + 224] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload - cmp bl, byte ptr [rdx + 16] - setae byte ptr [rsp + 176] # 1-byte Folded Spill - movzx ebx, byte ptr [rsp] # 1-byte Folded Reload - cmp bl, byte ptr [rdx + 24] - setae byte ptr [rsp + 160] # 1-byte Folded Spill + setge byte ptr [rsp + 144] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 8] # 4-byte Reload + cmp bx, word ptr [rdx + 32] + setge byte ptr [rsp + 208] # 1-byte Folded Spill + mov ebx, dword ptr [rsp + 8] # 4-byte Reload + cmp bx, word ptr [rdx + 48] + setge byte ptr [rsp + 192] # 1-byte Folded Spill add al, al - add al, byte ptr [rsp + 208] # 1-byte Folded Reload + add al, byte ptr [rsp + 240] # 1-byte Folded Reload shl cl, 2 or cl, al shl dil, 3 @@ -56761,26 +58468,26 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr or sil, r9b mov byte ptr [r13], sil add r11b, r11b - add r11b, byte ptr [rsp + 224] # 1-byte Folded Reload + add r11b, byte ptr [rsp + 144] # 1-byte Folded Reload shl r14b, 2 or r14b, r11b shl r15b, 3 or r15b, r14b shl r12b, 4 or r12b, r15b - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload shl al, 5 or al, r12b - movzx r14d, byte ptr [rsp] # 1-byte Folded Reload - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + mov r14d, dword ptr [rsp + 8] # 4-byte Reload + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload shl cl, 6 shl r10b, 7 or r10b, cl or r10b, al mov byte ptr [r13 + 1], r10b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 176] # 1-byte Folded Reload + add al, byte ptr [rsp + 208] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 2 @@ -56790,7 +58497,7 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -56798,429 +58505,222 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 80] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl mov byte ptr [r13 + 2], al movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 160] # 1-byte Folded Reload + add al, byte ptr [rsp + 192] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl mov byte ptr [r13 + 3], al - add rdx, 32 + add rdx, 64 add r13, 4 - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB11_70 -# %bb.71: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 248] # 8-byte Reload - jmp .LBB11_72 -.LBB11_139: - mov r14d, dword ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + add qword ptr [rsp + 224], -1 # 8-byte Folded Spill + jne .LBB11_82 +# %bb.83: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + jmp .LBB11_131 +.LBB11_84: + mov r8, qword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_143 -# %bb.140: - movsxd rax, r9d + je .LBB11_90 +# %bb.85: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB11_88 +# %bb.86: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_141: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] - lea rdx, [rdx + 4] +.LBB11_87: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 8] + cmp r8, qword ptr [rcx] setge bl neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r15 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi - mov edi, 1 + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_141 -# %bb.142: - add r15, 1 -.LBB11_143: - sar r10, 5 - cmp r11, 32 - jl .LBB11_147 -# %bb.144: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_87 +.LBB11_88: + sub r15, r14 + je .LBB11_215 +# %bb.89: + add r12, 1 +.LBB11_90: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB11_94 +# %bb.91: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill .p2align 4, 0x90 -.LBB11_145: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 120], r15 # 8-byte Spill - cmp r14d, dword ptr [rdx + 124] - setge byte ptr [rsp] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 120] - setge byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 116] +.LBB11_92: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8, qword ptr [rdx + 248] setge byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 112] - setge byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 108] + cmp r8, qword ptr [rdx + 240] setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 104] + cmp r8, qword ptr [rdx + 232] + setge byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 224] setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 100] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 92] + cmp r8, qword ptr [rdx + 216] + setge byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 208] setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 88] - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 84] + cmp r8, qword ptr [rdx + 200] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 184] setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 80] + cmp r8, qword ptr [rdx + 176] + setge byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 168] setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 76] + cmp r8, qword ptr [rdx + 160] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 152] setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 72] + cmp r8, qword ptr [rdx + 144] setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 68] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 60] - setge r8b - cmp r14d, dword ptr [rdx + 56] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 52] + cmp r8, qword ptr [rdx + 136] setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 48] + cmp r8, qword ptr [rdx + 120] + setge dil + cmp r8, qword ptr [rdx + 112] + setge byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 104] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 96] setge r11b - cmp r14d, dword ptr [rdx + 44] + cmp r8, qword ptr [rdx + 88] setge r10b - cmp r14d, dword ptr [rdx + 40] + cmp r8, qword ptr [rdx + 80] setge r9b - cmp r14d, dword ptr [rdx + 36] - setge dil - cmp r14d, dword ptr [rdx + 28] + cmp r8, qword ptr [rdx + 72] + setge sil + cmp r8, qword ptr [rdx + 56] setge al - cmp r14d, dword ptr [rdx + 24] + cmp r8, qword ptr [rdx + 48] setge bl - cmp r14d, dword ptr [rdx + 20] - setge sil - cmp r14d, dword ptr [rdx + 16] + cmp r8, qword ptr [rdx + 40] setge cl - cmp r14d, dword ptr [rdx + 12] - setge r13b - cmp r14d, dword ptr [rdx + 8] - setge r12b - cmp r14d, dword ptr [rdx] - setge byte ptr [rsp + 224] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 4] - setge r15b - cmp r14d, dword ptr [rdx + 32] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 64] - setge byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14d, dword ptr [rdx + 96] - setge byte ptr [rsp + 144] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 2 - or r12b, r15b - mov r15, qword ptr [rsp + 120] # 8-byte Reload - shl r13b, 3 - or r13b, r12b - shl cl, 4 - or cl, r13b - shl sil, 5 - or sil, cl - shl bl, 6 - shl al, 7 - or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 128] # 1-byte Folded Reload - shl r9b, 2 - or r9b, dil - shl r10b, 3 - or r10b, r9b - shl r11b, 4 - or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload - shl al, 5 - or al, r11b - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload - shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 176] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload - add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload - mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload - shl al, 2 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload - shl al, 3 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload - shl al, 4 - or al, cl - mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload - shl al, 5 - or al, cl - mov ecx, eax - movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload - shl bl, 6 - movzx eax, byte ptr [rsp] # 1-byte Folded Reload - shl al, 7 - or al, bl - or al, cl - mov byte ptr [r15 + 3], al - sub rdx, -128 - add r15, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB11_145 -# %bb.146: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB11_147: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.148: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_153 -# %bb.149: - xor edi, edi - jmp .LBB11_150 -.LBB11_99: - movzx r14d, word ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - sub r9d, eax - je .LBB11_103 -# %bb.100: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB11_101: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] - mov esi, 0 - adc sil, -1 - lea rbx, [rax + 7] - test rax, rax - cmovns rbx, rax - sar rbx, 3 - movzx r8d, byte ptr [r15 + rbx] - xor sil, r8b - lea edi, [8*rbx] - mov ecx, eax - sub ecx, edi - mov edi, 1 - # kill: def $cl killed $cl killed $ecx - shl edi, cl - and dil, sil - xor dil, r8b - mov byte ptr [r15 + rbx], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_101 -# %bb.102: - add r15, 1 -.LBB11_103: - sar r10, 5 - cmp r11, 32 - jl .LBB11_107 -# %bb.104: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - .p2align 4, 0x90 -.LBB11_105: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 120], r15 # 8-byte Spill - cmp r14w, word ptr [rdx + 62] - setae byte ptr [rsp] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 60] - setae byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 58] - setae byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 56] - setae byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 54] - setae byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 52] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 50] - setae byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 46] - setae byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 44] - setae byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 42] - setae byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 40] - setae byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 38] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 36] - setae byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 34] - setae byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 30] - setae r8b - cmp r14w, word ptr [rdx + 28] - setae byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 26] - setae byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 24] - setae r11b - cmp r14w, word ptr [rdx + 22] - setae r10b - cmp r14w, word ptr [rdx + 20] - setae r9b - cmp r14w, word ptr [rdx + 18] - setae dil - cmp r14w, word ptr [rdx + 14] - setae al - cmp r14w, word ptr [rdx + 12] - setae bl - cmp r14w, word ptr [rdx + 10] - setae sil - cmp r14w, word ptr [rdx + 8] - setae cl - cmp r14w, word ptr [rdx + 6] - setae r13b - cmp r14w, word ptr [rdx + 4] - setae r12b - cmp r14w, word ptr [rdx] - setae byte ptr [rsp + 224] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 2] - setae r15b - cmp r14w, word ptr [rdx + 16] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 32] - setae byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [rdx + 48] - setae byte ptr [rsp + 32] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 2 + cmp r8, qword ptr [rdx + 32] + setge r13b + cmp r8, qword ptr [rdx + 24] + setge r12b + cmp r8, qword ptr [rdx + 16] + setge r15b + cmp r8, qword ptr [rdx] + setge byte ptr [rsp + 144] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 8] + setge r14b + cmp r8, qword ptr [rdx + 64] + setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 128] + setge byte ptr [rsp + 208] # 1-byte Folded Spill + cmp r8, qword ptr [rdx + 192] + setge byte ptr [rsp + 160] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b - mov r15, qword ptr [rsp + 120] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 128] # 1-byte Folded Reload + or al, cl + mov byte ptr [r12], al + add sil, sil + add sil, byte ptr [rsp + 128] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 96] # 1-byte Folded Reload + add al, byte ptr [rsp + 208] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax @@ -57228,457 +58728,515 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + mov byte ptr [r12 + 2], al + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 32] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al - add rdx, 64 - add r15, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB11_105 -# %bb.106: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB11_107: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.108: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_112 -# %bb.109: - xor r11d, r11d - jmp .LBB11_110 -.LBB11_114: - movzx r14d, word ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + mov byte ptr [r12 + 3], al + add rdx, 256 + add r12, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB11_92 +# %bb.93: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB11_94: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB11_215 +# %bb.95: + or rax, 1 + cmp r15, rax + jne .LBB11_199 +# %bb.96: + xor edi, edi + jmp .LBB11_201 +.LBB11_97: + mov r14d, dword ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_118 -# %bb.115: - movsxd rax, r9d + je .LBB11_103 +# %bb.98: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB11_101 +# %bb.99: + movsxd rsi, r9d + movd xmm0, r14d + mov r11, r8 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_116: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] - lea rdx, [rdx + 2] - setge bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r9d, byte ptr [r15 + rsi] +.LBB11_100: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + ucomiss xmm0, dword ptr [rcx] + mov ebx, 0 + adc bl, -1 + lea rax, [rsi + 7] + test rsi, rsi + cmovns rax, rsi + sar rax, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rax] xor bl, r9b - lea r8d, [8*rsi] - mov ecx, eax - sub ecx, r8d + lea r10d, [8*rax] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl and dil, bl xor dil, r9b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_116 -# %bb.117: - add r15, 1 -.LBB11_118: - sar r10, 5 - cmp r11, 32 - jl .LBB11_119 -# %bb.120: - cmp r10, 8 - mov dword ptr [rsp], r14d # 4-byte Spill - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 256], r10 # 8-byte Spill - jb .LBB11_121 -# %bb.122: - mov rax, r10 - shl rax, 6 + mov byte ptr [r12 + rax], dil + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_100 +.LBB11_101: + sub r15, r8 + je .LBB11_215 +# %bb.102: + add r12, 1 +.LBB11_103: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB11_134 +# %bb.104: + movd xmm0, r14d + cmp rcx, 4 + jb .LBB11_107 +# %bb.105: + mov rax, rcx + shl rax, 7 add rax, rdx - cmp r15, rax - jae .LBB11_124 -# %bb.123: - lea rax, [r15 + 4*r10] + cmp r12, rax + jae .LBB11_219 +# %bb.106: + lea rax, [r12 + 4*rcx] cmp rax, rdx - jbe .LBB11_124 -.LBB11_121: - xor eax, eax - mov qword ptr [rsp + 32], rax # 8-byte Spill - mov rax, rdx - mov r12, r15 -.LBB11_127: - sub r10, qword ptr [rsp + 32] # 8-byte Folded Reload - mov qword ptr [rsp + 192], r10 # 8-byte Spill + jbe .LBB11_219 +.LBB11_107: + xor r9d, r9d + mov rbx, rdx + mov r13, r12 +.LBB11_108: + mov qword ptr [rsp + 8], r13 # 8-byte Spill + mov dword ptr [rsp + 240], r14d # 4-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rcx # 8-byte Spill + sub rcx, r9 + mov qword ptr [rsp + 144], rcx # 8-byte Spill .p2align 4, 0x90 -.LBB11_128: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rax + 62] - setge byte ptr [rsp + 120] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 60] - setge byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 58] - setge byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 56] - setge byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 54] - setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 52] - setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 50] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 46] - setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 44] - setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 42] - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 40] - setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 38] - setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 36] - setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 34] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 30] - setge r10b - cmp r14w, word ptr [rax + 28] - setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 26] - mov rcx, rax - setge byte ptr [rsp + 144] # 1-byte Folded Spill - cmp r14w, word ptr [rax + 24] - setge r13b - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 22] - setge r15b - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 20] - setge r14b - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 18] - setge r11b - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 14] - setge sil - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 12] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 10] - setge r9b - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 8] - setge r8b - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 6] - setge dil - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 4] - setge dl - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx] - setge byte ptr [rsp + 208] # 1-byte Folded Spill - mov eax, dword ptr [rsp] # 4-byte Reload - cmp ax, word ptr [rcx + 2] - setge al - mov rbx, r12 - mov r12d, dword ptr [rsp] # 4-byte Reload - cmp r12w, word ptr [rcx + 16] - mov r12, rbx - setge byte ptr [rsp + 224] # 1-byte Folded Spill - mov ebx, dword ptr [rsp] # 4-byte Reload - cmp bx, word ptr [rcx + 32] - setge byte ptr [rsp + 176] # 1-byte Folded Spill - mov ebx, dword ptr [rsp] # 4-byte Reload - cmp bx, word ptr [rcx + 48] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - add al, al - add al, byte ptr [rsp + 208] # 1-byte Folded Reload - shl dl, 2 - or dl, al - shl dil, 3 - or dil, dl - shl r8b, 4 - or r8b, dil - shl r9b, 5 - or r9b, r8b - movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload +.LBB11_109: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rbx] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 4] + setae r8b + ucomiss xmm0, dword ptr [rbx + 8] + setae r14b + ucomiss xmm0, dword ptr [rbx + 12] + setae r13b + ucomiss xmm0, dword ptr [rbx + 16] + setae byte ptr [rsp + 112] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 20] + setae byte ptr [rsp + 80] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 24] + setae al + ucomiss xmm0, dword ptr [rbx + 28] + setae r11b + ucomiss xmm0, dword ptr [rbx + 32] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 36] + setae cl + ucomiss xmm0, dword ptr [rbx + 40] + setae sil + ucomiss xmm0, dword ptr [rbx + 44] + setae dil + ucomiss xmm0, dword ptr [rbx + 48] + setae r10b + ucomiss xmm0, dword ptr [rbx + 52] + setae r12b + ucomiss xmm0, dword ptr [rbx + 56] + setae byte ptr [rsp + 192] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 60] + setae r9b + ucomiss xmm0, dword ptr [rbx + 64] + setae byte ptr [rsp + 96] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 68] + setae byte ptr [rsp + 208] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 72] + setae byte ptr [rsp + 160] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 76] + setae byte ptr [rsp + 88] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 80] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 84] + setae byte ptr [rsp + 72] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 88] + setae byte ptr [rsp + 64] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 92] + setae r15b + ucomiss xmm0, dword ptr [rbx + 96] + setae byte ptr [rsp + 32] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 100] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 104] + setae byte ptr [rsp + 48] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 108] + setae byte ptr [rsp + 24] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 112] + setae byte ptr [rsp + 16] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 116] + setae byte ptr [rsp + 40] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 120] + setae byte ptr [rsp + 136] # 1-byte Folded Spill + ucomiss xmm0, dword ptr [rbx + 124] + setae dl + add r8b, r8b + add r8b, byte ptr [rsp + 128] # 1-byte Folded Reload shl al, 6 - shl sil, 7 - or sil, al - or sil, r9b - mov byte ptr [r12], sil - add r11b, r11b - add r11b, byte ptr [rsp + 224] # 1-byte Folded Reload + shl r11b, 7 + or r11b, al shl r14b, 2 - or r14b, r11b - shl r15b, 3 - or r15b, r14b - shl r13b, 4 - or r13b, r15b - movzx eax, byte ptr [rsp + 144] # 1-byte Folded Reload - shl al, 5 - or al, r13b - mov r14d, dword ptr [rsp] # 4-byte Reload - movzx edx, byte ptr [rsp + 112] # 1-byte Folded Reload - shl dl, 6 - shl r10b, 7 - or r10b, dl - or r10b, al - mov rax, rcx - mov byte ptr [r12 + 1], r10b - movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + or r14b, r8b add cl, cl - add cl, byte ptr [rsp + 176] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload - shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload + add cl, byte ptr [rsp + 120] # 1-byte Folded Reload + shl r13b, 3 + or r13b, r14b + shl sil, 2 + or sil, cl + movzx ecx, byte ptr [rsp + 112] # 1-byte Folded Reload shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + or cl, r13b + mov r8d, ecx + shl dil, 3 + or dil, sil + movzx ecx, byte ptr [rsp + 80] # 1-byte Folded Reload shl cl, 5 - or cl, dl - mov edx, ecx - movzx ebx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl bl, 6 - movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload - shl cl, 7 - or cl, bl - or cl, dl - mov byte ptr [r12 + 2], cl - movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload - add cl, cl - add cl, byte ptr [rsp + 160] # 1-byte Folded Reload - mov edx, ecx - movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + or cl, r8b + shl r10b, 4 + or r10b, dil + shl r12b, 5 + or r12b, r10b + movzx esi, byte ptr [rsp + 192] # 1-byte Folded Reload + shl sil, 6 + shl r9b, 7 + or r9b, sil + or r11b, cl + or r9b, r12b + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 96] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload shl cl, 2 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + or cl, al + mov esi, ecx + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload shl cl, 3 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload shl cl, 4 - or cl, dl - mov edx, ecx - movzx ecx, byte ptr [rsp + 16] # 1-byte Folded Reload + or cl, sil + mov esi, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload shl cl, 5 - or cl, dl - mov edx, ecx - movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload - shl bl, 6 - movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload - shl cl, 7 - or cl, bl - or cl, dl - mov byte ptr [r12 + 3], cl - add rax, 64 - add r12, 4 - add qword ptr [rsp + 192], -1 # 8-byte Folded Spill - jne .LBB11_128 -# %bb.129: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 256] # 8-byte Reload - jmp .LBB11_130 -.LBB11_157: - mov r14, qword ptr [rsi] - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 + or cl, sil + mov rsi, qword ptr [rsp + 8] # 8-byte Reload + mov byte ptr [rsi], r11b + movzx edi, byte ptr [rsp + 64] # 1-byte Folded Reload + shl dil, 6 + shl r15b, 7 + or r15b, dil + mov byte ptr [rsi + 1], r9b + or r15b, cl + movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload + add al, al + add al, byte ptr [rsp + 32] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + shl al, 5 + or al, cl + movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl cl, 6 + shl dl, 7 + or dl, cl + or dl, al + mov byte ptr [rsi + 2], r15b + mov byte ptr [rsi + 3], dl + add rbx, 128 + add rsi, 4 + mov qword ptr [rsp + 8], rsi # 8-byte Spill + add qword ptr [rsp + 144], -1 # 8-byte Folded Spill + jne .LBB11_109 +# %bb.110: + mov r13, qword ptr [rsp + 8] # 8-byte Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14d, dword ptr [rsp + 240] # 4-byte Reload + mov rcx, qword ptr [rsp + 224] # 8-byte Reload + jmp .LBB11_135 +.LBB11_111: + mov r13b, byte ptr [rsi] lea eax, [r9 + 7] test r9d, r9d cmovns eax, r9d and eax, -8 sub r9d, eax - je .LBB11_161 -# %bb.158: - movsxd rax, r9d + je .LBB11_138 +# %bb.112: + mov r8d, 8 + sub r8d, r9d + cmp r8, r15 + cmovg r8, r15 + test r8, r8 + jle .LBB11_153 +# %bb.113: + movsxd rsi, r9d + mov rax, r8 .p2align 4, 0x90 -.LBB11_159: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] - lea rdx, [rdx + 8] - setge bl - neg bl - lea rsi, [rax + 7] - test rax, rax - cmovns rsi, rax - sar rsi, 3 - movzx r8d, byte ptr [r15 + rsi] - xor bl, r8b - lea edi, [8*rsi] - mov ecx, eax - sub ecx, edi +.LBB11_114: # =>This Inner Loop Header: Depth=1 + lea r11, [rdx + 1] + cmp r13b, byte ptr [rdx] + mov edx, 0 + adc dl, -1 + lea rbx, [rsi + 7] + test rsi, rsi + cmovns rbx, rsi + sar rbx, 3 + mov r14, r12 + movzx r9d, byte ptr [r12 + rbx] + xor dl, r9b + lea r10d, [8*rbx] + mov ecx, esi + sub ecx, r10d mov edi, 1 # kill: def $cl killed $cl killed $ecx shl edi, cl - and dil, bl - xor dil, r8b - mov byte ptr [r15 + rsi], dil - add rax, 1 - cmp rax, 8 - jne .LBB11_159 -# %bb.160: - add r15, 1 -.LBB11_161: - sar r10, 5 - cmp r11, 32 - jl .LBB11_165 -# %bb.162: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill + and dil, dl + xor dil, r9b + mov byte ptr [r12 + rbx], dil + add rsi, 1 + mov rdx, r11 + add rax, -1 + jne .LBB11_114 +# %bb.115: + sub r15, r8 + jne .LBB11_154 + jmp .LBB11_215 +.LBB11_116: + mov r8d, dword ptr [rsi] + lea eax, [r9 + 7] + test r9d, r9d + cmovns eax, r9d + and eax, -8 + sub r9d, eax + je .LBB11_122 +# %bb.117: + mov r14d, 8 + sub r14d, r9d + cmp r14, r15 + cmovg r14, r15 + test r14, r14 + jle .LBB11_120 +# %bb.118: + movsxd rsi, r9d + mov r11, r14 + mov rcx, rdx .p2align 4, 0x90 -.LBB11_163: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 120], r15 # 8-byte Spill - cmp r14, qword ptr [rdx + 248] - setge byte ptr [rsp] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 240] - setge byte ptr [rsp + 16] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 232] +.LBB11_119: # =>This Inner Loop Header: Depth=1 + lea rdx, [rcx + 4] + cmp r8d, dword ptr [rcx] + setge bl + neg bl + lea rdi, [rsi + 7] + test rsi, rsi + cmovns rdi, rsi + sar rdi, 3 + mov r13, r12 + movzx r9d, byte ptr [r12 + rdi] + xor bl, r9b + lea r10d, [8*rdi] + mov ecx, esi + sub ecx, r10d + mov eax, 1 + # kill: def $cl killed $cl killed $ecx + shl eax, cl + and al, bl + xor al, r9b + mov byte ptr [r12 + rdi], al + add rsi, 1 + mov rcx, rdx + add r11, -1 + jne .LBB11_119 +.LBB11_120: + sub r15, r14 + je .LBB11_215 +# %bb.121: + add r12, 1 +.LBB11_122: + lea rax, [r15 + 31] + test r15, r15 + cmovns rax, r15 + sar rax, 5 + cmp r15, 32 + jl .LBB11_126 +# %bb.123: + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 224], rax # 8-byte Spill + mov qword ptr [rsp + 240], rax # 8-byte Spill + .p2align 4, 0x90 +.LBB11_124: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 136], r12 # 8-byte Spill + cmp r8d, dword ptr [rdx + 124] setge byte ptr [rsp + 8] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 224] - setge byte ptr [rsp + 24] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 216] + cmp r8d, dword ptr [rdx + 120] setge byte ptr [rsp + 40] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 208] + cmp r8d, dword ptr [rdx + 116] + setge byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 112] setge byte ptr [rsp + 32] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 200] - setge byte ptr [rsp + 56] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 184] + cmp r8d, dword ptr [rdx + 108] + setge byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 104] setge byte ptr [rsp + 48] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 176] - setge byte ptr [rsp + 72] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 168] + cmp r8d, dword ptr [rdx + 100] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 92] setge byte ptr [rsp + 64] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 160] + cmp r8d, dword ptr [rdx + 88] + setge byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 84] setge byte ptr [rsp + 80] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 152] + cmp r8d, dword ptr [rdx + 80] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 76] setge byte ptr [rsp + 96] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 144] + cmp r8d, dword ptr [rdx + 72] setge byte ptr [rsp + 88] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 136] - setge byte ptr [rsp + 104] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 120] - setge r8b - cmp r14, qword ptr [rdx + 112] - setge byte ptr [rsp + 160] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 104] + cmp r8d, dword ptr [rdx + 68] setge byte ptr [rsp + 112] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 96] + cmp r8d, dword ptr [rdx + 60] + setge dil + cmp r8d, dword ptr [rdx + 56] + setge byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 52] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 48] setge r11b - cmp r14, qword ptr [rdx + 88] + cmp r8d, dword ptr [rdx + 44] setge r10b - cmp r14, qword ptr [rdx + 80] + cmp r8d, dword ptr [rdx + 40] setge r9b - cmp r14, qword ptr [rdx + 72] - setge dil - cmp r14, qword ptr [rdx + 56] + cmp r8d, dword ptr [rdx + 36] + setge sil + cmp r8d, dword ptr [rdx + 28] setge al - cmp r14, qword ptr [rdx + 48] + cmp r8d, dword ptr [rdx + 24] setge bl - cmp r14, qword ptr [rdx + 40] - setge sil - cmp r14, qword ptr [rdx + 32] + cmp r8d, dword ptr [rdx + 20] setge cl - cmp r14, qword ptr [rdx + 24] + cmp r8d, dword ptr [rdx + 16] setge r13b - cmp r14, qword ptr [rdx + 16] + cmp r8d, dword ptr [rdx + 12] setge r12b - cmp r14, qword ptr [rdx] - setge byte ptr [rsp + 224] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 8] + cmp r8d, dword ptr [rdx + 8] setge r15b - cmp r14, qword ptr [rdx + 64] - setge byte ptr [rsp + 128] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 128] - setge byte ptr [rsp + 176] # 1-byte Folded Spill - cmp r14, qword ptr [rdx + 192] + cmp r8d, dword ptr [rdx] setge byte ptr [rsp + 144] # 1-byte Folded Spill - add r15b, r15b - add r15b, byte ptr [rsp + 224] # 1-byte Folded Reload - shl r12b, 2 + cmp r8d, dword ptr [rdx + 4] + setge r14b + cmp r8d, dword ptr [rdx + 32] + setge byte ptr [rsp + 128] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 64] + setge byte ptr [rsp + 208] # 1-byte Folded Spill + cmp r8d, dword ptr [rdx + 96] + setge byte ptr [rsp + 160] # 1-byte Folded Spill + add r14b, r14b + add r14b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r15b, 2 + or r15b, r14b + shl r12b, 3 or r12b, r15b - mov r15, qword ptr [rsp + 120] # 8-byte Reload - shl r13b, 3 + shl r13b, 4 or r13b, r12b - shl cl, 4 + mov r12, qword ptr [rsp + 136] # 8-byte Reload + shl cl, 5 or cl, r13b - shl sil, 5 - or sil, cl shl bl, 6 shl al, 7 or al, bl - or al, sil - mov byte ptr [r15], al - add dil, dil - add dil, byte ptr [rsp + 128] # 1-byte Folded Reload + or al, cl + mov byte ptr [r12], al + add sil, sil + add sil, byte ptr [rsp + 128] # 1-byte Folded Reload shl r9b, 2 - or r9b, dil + or r9b, sil shl r10b, 3 or r10b, r9b shl r11b, 4 or r11b, r10b - movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 120] # 1-byte Folded Reload shl al, 5 or al, r11b - movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload shl cl, 6 - shl r8b, 7 - or r8b, cl - or r8b, al - mov byte ptr [r15 + 1], r8b - movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl dil, 7 + or dil, cl + or dil, al + mov byte ptr [r12 + 1], dil + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 176] # 1-byte Folded Reload + add al, byte ptr [rsp + 208] # 1-byte Folded Reload mov ecx, eax movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload shl al, 2 @@ -57688,376 +59246,582 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 80] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax movzx ebx, byte ptr [rsp + 72] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 2], al + mov byte ptr [r12 + 2], al movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 144] # 1-byte Folded Reload + add al, byte ptr [rsp + 160] # 1-byte Folded Reload mov ecx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 or al, cl mov ecx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload shl al, 5 or al, cl mov ecx, eax - movzx ebx, byte ptr [rsp + 16] # 1-byte Folded Reload + movzx ebx, byte ptr [rsp + 40] # 1-byte Folded Reload shl bl, 6 - movzx eax, byte ptr [rsp] # 1-byte Folded Reload + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload shl al, 7 or al, bl or al, cl - mov byte ptr [r15 + 3], al - add rdx, 256 - add r15, 4 - add qword ptr [rsp + 208], -1 # 8-byte Folded Spill - jne .LBB11_163 -# %bb.164: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 192] # 8-byte Reload -.LBB11_165: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.166: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_170 -# %bb.167: - xor edi, edi - jmp .LBB11_168 -.LBB11_172: - lea r10, [r11 + 31] - test r11, r11 - cmovns r10, r11 - lea eax, [r9 + 7] - test r9d, r9d - cmovns eax, r9d - and eax, -8 - movss xmm0, dword ptr [rsi] # xmm0 = mem[0],zero,zero,zero - sub r9d, eax - je .LBB11_176 -# %bb.173: - movsxd rax, r9d - .p2align 4, 0x90 -.LBB11_174: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rdx] - lea rdx, [rdx + 4] - mov esi, 0 - adc sil, -1 - lea rdi, [rax + 7] - test rax, rax - cmovns rdi, rax - sar rdi, 3 - movzx r9d, byte ptr [r15 + rdi] - xor sil, r9b - lea r8d, [8*rdi] - mov ecx, eax - sub ecx, r8d - mov ebx, 1 - # kill: def $cl killed $cl killed $ecx - shl ebx, cl - and bl, sil - xor bl, r9b - mov byte ptr [r15 + rdi], bl - add rax, 1 - cmp rax, 8 - jne .LBB11_174 -# %bb.175: - add r15, 1 -.LBB11_176: - sar r10, 5 - cmp r11, 32 - jl .LBB11_177 -# %bb.178: - cmp r10, 4 - jb .LBB11_179 -# %bb.180: - mov rax, r10 - shl rax, 7 - add rax, rdx + mov byte ptr [r12 + 3], al + sub rdx, -128 + add r12, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB11_124 +# %bb.125: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rax, qword ptr [rsp + 224] # 8-byte Reload +.LBB11_126: + shl rax, 5 + mov r9, r15 + sub r9, rax + jle .LBB11_215 +# %bb.127: + or rax, 1 cmp r15, rax - jae .LBB11_182 -# %bb.181: - lea rax, [r15 + 4*r10] - cmp rax, rdx - jbe .LBB11_182 -.LBB11_179: - xor r8d, r8d + jne .LBB11_171 +# %bb.128: + xor edi, edi + jmp .LBB11_173 +.LBB11_129: + mov r13, rdx + jmp .LBB11_141 +.LBB11_130: + mov r13, r12 +.LBB11_131: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB11_215 +# %bb.132: + or rcx, 1 + cmp r15, rcx + jne .LBB11_205 +# %bb.133: + xor esi, esi + jmp .LBB11_207 +.LBB11_134: + mov r13, r12 mov rbx, rdx - mov r14, r15 -.LBB11_185: - mov qword ptr [rsp + 136], r11 # 8-byte Spill - mov qword ptr [rsp + 208], r10 # 8-byte Spill - sub r10, r8 - mov qword ptr [rsp + 224], r10 # 8-byte Spill - .p2align 4, 0x90 -.LBB11_186: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp], r14 # 8-byte Spill - ucomiss xmm0, dword ptr [rbx] - setae byte ptr [rsp + 128] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 4] - setae r8b - ucomiss xmm0, dword ptr [rbx + 8] - setae r14b - ucomiss xmm0, dword ptr [rbx + 12] - setae r13b - ucomiss xmm0, dword ptr [rbx + 16] - setae byte ptr [rsp + 104] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 20] - setae byte ptr [rsp + 64] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 24] - setae al - ucomiss xmm0, dword ptr [rbx + 28] - setae r11b - ucomiss xmm0, dword ptr [rbx + 32] - setae byte ptr [rsp + 112] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 36] - setae dl - ucomiss xmm0, dword ptr [rbx + 40] - setae sil - ucomiss xmm0, dword ptr [rbx + 44] - setae r9b - ucomiss xmm0, dword ptr [rbx + 48] - setae r10b - ucomiss xmm0, dword ptr [rbx + 52] - setae r12b - ucomiss xmm0, dword ptr [rbx + 56] - setae byte ptr [rsp + 160] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 60] - setae dil - ucomiss xmm0, dword ptr [rbx + 64] - setae byte ptr [rsp + 96] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 68] - setae byte ptr [rsp + 176] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 72] - setae byte ptr [rsp + 144] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 76] - setae byte ptr [rsp + 88] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 80] - setae byte ptr [rsp + 80] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 84] - setae byte ptr [rsp + 72] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 88] - setae byte ptr [rsp + 48] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 92] - setae r15b - ucomiss xmm0, dword ptr [rbx + 96] - setae byte ptr [rsp + 24] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 100] - setae byte ptr [rsp + 56] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 104] - setae byte ptr [rsp + 32] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 108] - setae byte ptr [rsp + 40] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 112] - setae byte ptr [rsp + 8] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 116] - setae byte ptr [rsp + 16] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 120] - setae byte ptr [rsp + 120] # 1-byte Folded Spill - ucomiss xmm0, dword ptr [rbx + 124] - setae cl - add r8b, r8b - add r8b, byte ptr [rsp + 128] # 1-byte Folded Reload +.LBB11_135: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB11_215 +# %bb.136: + movd xmm0, r14d + or rcx, 1 + cmp r15, rcx + jne .LBB11_210 +# %bb.137: + xor r11d, r11d + jmp .LBB11_212 +.LBB11_138: + mov r11, rdx + jmp .LBB11_155 +.LBB11_139: + mov r13, rdx + sub r15, r8 + je .LBB11_215 +.LBB11_140: + add r12, 1 +.LBB11_141: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB11_149 +# %bb.142: + cmp rcx, 16 + mov byte ptr [rsp + 8], r14b # 1-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 272], rcx # 8-byte Spill + jb .LBB11_145 +# %bb.143: + mov rax, rcx + shl rax, 5 + add rax, r13 + cmp r12, rax + jae .LBB11_222 +# %bb.144: + lea rax, [r12 + 4*rcx] + cmp r13, rax + jae .LBB11_222 +.LBB11_145: + xor eax, eax + mov qword ptr [rsp + 184], rax # 8-byte Spill + mov rdi, r13 + mov r13, r12 +.LBB11_146: + sub rcx, qword ptr [rsp + 184] # 8-byte Folded Reload + mov qword ptr [rsp + 240], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB11_147: # =>This Inner Loop Header: Depth=1 + cmp r14b, byte ptr [rdi + 31] + setge byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 30] + setge byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 29] + setge byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 28] + setge byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 27] + setge byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 26] + setge byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 25] + setge byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 23] + setge byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 22] + setge byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 21] + setge byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 20] + setge byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 19] + setge byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 18] + setge byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 17] + setge byte ptr [rsp + 112] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 15] + setge r10b + cmp r14b, byte ptr [rdi + 14] + setge byte ptr [rsp + 192] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 13] + setge byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r14b, byte ptr [rdi + 12] + setge r12b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 11] + setge r15b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 10] + setge r14b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 9] + setge r11b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 7] + setge dl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 6] + setge byte ptr [rsp + 208] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 5] + setge r9b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 4] + setge r8b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 3] + setge sil + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 2] + setge cl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi] + setge byte ptr [rsp + 144] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rdi + 1] + setge al + mov rbx, r13 + movzx r13d, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp r13b, byte ptr [rdi + 8] + mov r13, rbx + setge byte ptr [rsp + 128] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp bl, byte ptr [rdi + 16] + setge byte ptr [rsp + 120] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp bl, byte ptr [rdi + 24] + setge bl + add al, al + add al, byte ptr [rsp + 144] # 1-byte Folded Reload + shl cl, 2 + or cl, al + shl sil, 3 + or sil, cl + shl r8b, 4 + or r8b, sil + shl r9b, 5 + or r9b, r8b + movzx eax, byte ptr [rsp + 208] # 1-byte Folded Reload shl al, 6 - shl r11b, 7 - or r11b, al + shl dl, 7 + or dl, al + or dl, r9b + mov byte ptr [r13], dl + add r11b, r11b + add r11b, byte ptr [rsp + 128] # 1-byte Folded Reload shl r14b, 2 - or r14b, r8b - add dl, dl - add dl, byte ptr [rsp + 112] # 1-byte Folded Reload - shl r13b, 3 - or r13b, r14b - shl sil, 2 - or sil, dl - movzx edx, byte ptr [rsp + 104] # 1-byte Folded Reload - shl dl, 4 - or dl, r13b - mov r8d, edx - mov r14, qword ptr [rsp] # 8-byte Reload - shl r9b, 3 - or r9b, sil - movzx edx, byte ptr [rsp + 64] # 1-byte Folded Reload - shl dl, 5 - or dl, r8b - shl r10b, 4 - or r10b, r9b - shl r12b, 5 - or r12b, r10b - movzx esi, byte ptr [rsp + 160] # 1-byte Folded Reload - shl sil, 6 - shl dil, 7 - or dil, sil - or r11b, dl - or dil, r12b - movzx eax, byte ptr [rsp + 176] # 1-byte Folded Reload + or r14b, r11b + shl r15b, 3 + or r15b, r14b + shl r12b, 4 + or r12b, r15b + movzx eax, byte ptr [rsp + 160] # 1-byte Folded Reload + shl al, 5 + or al, r12b + movzx r14d, byte ptr [rsp + 8] # 1-byte Folded Reload + movzx ecx, byte ptr [rsp + 192] # 1-byte Folded Reload + shl cl, 6 + shl r10b, 7 + or r10b, cl + or r10b, al + mov byte ptr [r13 + 1], r10b + movzx eax, byte ptr [rsp + 112] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 96] # 1-byte Folded Reload - movzx edx, byte ptr [rsp + 144] # 1-byte Folded Reload - shl dl, 2 - or dl, al - mov esi, edx - movzx edx, byte ptr [rsp + 88] # 1-byte Folded Reload - shl dl, 3 - or dl, sil - mov esi, edx + add al, byte ptr [rsp + 120] # 1-byte Folded Reload + mov ecx, eax + movzx eax, byte ptr [rsp + 88] # 1-byte Folded Reload + shl al, 2 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 96] # 1-byte Folded Reload + shl al, 3 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 104] # 1-byte Folded Reload + shl al, 4 + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 72] # 1-byte Folded Reload + shl al, 5 + or al, cl + mov ecx, eax movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload - shl dl, 4 - or dl, sil - mov esi, edx - movzx edx, byte ptr [rsp + 72] # 1-byte Folded Reload - shl dl, 5 - or dl, sil - mov byte ptr [r14], r11b - movzx esi, byte ptr [rsp + 48] # 1-byte Folded Reload - shl sil, 6 - shl r15b, 7 - or r15b, sil - mov byte ptr [r14 + 1], dil - or r15b, dl + shl dl, 6 + movzx eax, byte ptr [rsp + 64] # 1-byte Folded Reload + shl al, 7 + or al, dl + or al, cl + mov byte ptr [r13 + 2], al movzx eax, byte ptr [rsp + 56] # 1-byte Folded Reload add al, al - add al, byte ptr [rsp + 24] # 1-byte Folded Reload - mov edx, eax - movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload + or al, bl + mov ecx, eax + movzx eax, byte ptr [rsp + 48] # 1-byte Folded Reload shl al, 2 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 24] # 1-byte Folded Reload shl al, 3 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 32] # 1-byte Folded Reload shl al, 4 - or al, dl - mov edx, eax - movzx eax, byte ptr [rsp + 16] # 1-byte Folded Reload + or al, cl + mov ecx, eax + movzx eax, byte ptr [rsp + 40] # 1-byte Folded Reload shl al, 5 + or al, cl + mov ecx, eax + movzx edx, byte ptr [rsp + 16] # 1-byte Folded Reload + shl dl, 6 + movzx eax, byte ptr [rsp + 136] # 1-byte Folded Reload + shl al, 7 or al, dl - movzx edx, byte ptr [rsp + 120] # 1-byte Folded Reload + or al, cl + mov byte ptr [r13 + 3], al + add rdi, 32 + add r13, 4 + add qword ptr [rsp + 240], -1 # 8-byte Folded Spill + jne .LBB11_147 +# %bb.148: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 272] # 8-byte Reload + jmp .LBB11_150 +.LBB11_149: + mov rdi, r13 + mov r13, r12 +.LBB11_150: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB11_215 +# %bb.151: + or rcx, 1 + cmp r15, rcx + jne .LBB11_175 +# %bb.152: + xor r9d, r9d + jmp .LBB11_178 +.LBB11_153: + mov r11, rdx + sub r15, r8 + je .LBB11_215 +.LBB11_154: + add r12, 1 +.LBB11_155: + lea rcx, [r15 + 31] + test r15, r15 + cmovns rcx, r15 + sar rcx, 5 + cmp r15, 32 + jl .LBB11_163 +# %bb.156: + cmp rcx, 16 + mov byte ptr [rsp + 8], r13b # 1-byte Spill + mov qword ptr [rsp + 152], r15 # 8-byte Spill + mov qword ptr [rsp + 256], rcx # 8-byte Spill + jb .LBB11_159 +# %bb.157: + mov rax, rcx + shl rax, 5 + add rax, r11 + cmp r12, rax + jae .LBB11_225 +# %bb.158: + lea rax, [r12 + 4*rcx] + cmp r11, rax + jae .LBB11_225 +.LBB11_159: + xor eax, eax + mov qword ptr [rsp + 184], rax # 8-byte Spill + mov rbx, r11 + mov qword ptr [rsp + 112], r12 # 8-byte Spill +.LBB11_160: + sub rcx, qword ptr [rsp + 184] # 8-byte Folded Reload + mov qword ptr [rsp + 224], rcx # 8-byte Spill + .p2align 4, 0x90 +.LBB11_161: # =>This Inner Loop Header: Depth=1 + cmp r13b, byte ptr [rbx + 31] + setae byte ptr [rsp + 136] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 30] + setae byte ptr [rsp + 16] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 29] + setae byte ptr [rsp + 40] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 28] + setae byte ptr [rsp + 32] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 27] + setae byte ptr [rsp + 24] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 26] + setae byte ptr [rsp + 48] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 25] + setae byte ptr [rsp + 56] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 23] + setae byte ptr [rsp + 64] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 22] + setae byte ptr [rsp + 80] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 21] + setae byte ptr [rsp + 72] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 20] + setae byte ptr [rsp + 104] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 19] + setae byte ptr [rsp + 96] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 18] + setae byte ptr [rsp + 88] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 17] + setae byte ptr [rsp + 160] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 15] + setae r9b + cmp r13b, byte ptr [rbx + 14] + setae byte ptr [rsp + 120] # 1-byte Folded Spill + cmp r13b, byte ptr [rbx + 13] + setae r12b + cmp r13b, byte ptr [rbx + 12] + setae r15b + cmp r13b, byte ptr [rbx + 11] + setae r14b + cmp r13b, byte ptr [rbx + 10] + setae r11b + cmp r13b, byte ptr [rbx + 9] + setae r10b + cmp r13b, byte ptr [rbx + 7] + setae dl + cmp r13b, byte ptr [rbx + 6] + setae byte ptr [rsp + 128] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rbx + 5] + setae r8b + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rbx + 4] + setae dil + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rbx + 3] + setae sil + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rbx + 2] + setae cl + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rbx] + setae byte ptr [rsp + 240] # 1-byte Folded Spill + movzx eax, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp al, byte ptr [rbx + 1] + setae al + movzx r13d, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp r13b, byte ptr [rbx + 8] + setae byte ptr [rsp + 144] # 1-byte Folded Spill + mov r13, rbx + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp bl, byte ptr [r13 + 16] + setae byte ptr [rsp + 208] # 1-byte Folded Spill + movzx ebx, byte ptr [rsp + 8] # 1-byte Folded Reload + cmp bl, byte ptr [r13 + 24] + mov rbx, r13 + setae byte ptr [rsp + 192] # 1-byte Folded Spill + add al, al + add al, byte ptr [rsp + 240] # 1-byte Folded Reload + shl cl, 2 + or cl, al + shl sil, 3 + or sil, cl + shl dil, 4 + or dil, sil + shl r8b, 5 + or r8b, dil + movzx eax, byte ptr [rsp + 128] # 1-byte Folded Reload + shl al, 6 + shl dl, 7 + or dl, al + movzx r13d, byte ptr [rsp + 8] # 1-byte Folded Reload + or dl, r8b + mov rax, qword ptr [rsp + 112] # 8-byte Reload + mov byte ptr [rax], dl + add r10b, r10b + add r10b, byte ptr [rsp + 144] # 1-byte Folded Reload + shl r11b, 2 + or r11b, r10b + shl r14b, 3 + or r14b, r11b + shl r15b, 4 + or r15b, r14b + shl r12b, 5 + or r12b, r15b + movzx ecx, byte ptr [rsp + 120] # 1-byte Folded Reload + shl cl, 6 + shl r9b, 7 + or r9b, cl + or r9b, r12b + mov byte ptr [rax + 1], r9b + movzx ecx, byte ptr [rsp + 160] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 208] # 1-byte Folded Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 88] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 96] # 1-byte Folded Reload + shl cl, 3 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 104] # 1-byte Folded Reload + shl cl, 4 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 72] # 1-byte Folded Reload + shl cl, 5 + or cl, dl + mov esi, ecx + movzx edx, byte ptr [rsp + 80] # 1-byte Folded Reload shl dl, 6 + movzx ecx, byte ptr [rsp + 64] # 1-byte Folded Reload shl cl, 7 or cl, dl - or cl, al - mov byte ptr [r14 + 2], r15b - mov byte ptr [r14 + 3], cl - add rbx, 128 - add r14, 4 + or cl, sil + mov byte ptr [rax + 2], cl + movzx ecx, byte ptr [rsp + 56] # 1-byte Folded Reload + add cl, cl + add cl, byte ptr [rsp + 192] # 1-byte Folded Reload + mov edx, ecx + movzx ecx, byte ptr [rsp + 48] # 1-byte Folded Reload + shl cl, 2 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 24] # 1-byte Folded Reload + shl cl, 3 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 32] # 1-byte Folded Reload + shl cl, 4 + or cl, dl + mov edx, ecx + movzx ecx, byte ptr [rsp + 40] # 1-byte Folded Reload + shl cl, 5 + or cl, dl + mov esi, ecx + movzx edx, byte ptr [rsp + 16] # 1-byte Folded Reload + shl dl, 6 + movzx ecx, byte ptr [rsp + 136] # 1-byte Folded Reload + shl cl, 7 + or cl, dl + or cl, sil + mov byte ptr [rax + 3], cl + add rbx, 32 + add rax, 4 + mov qword ptr [rsp + 112], rax # 8-byte Spill add qword ptr [rsp + 224], -1 # 8-byte Folded Spill - jne .LBB11_186 -# %bb.187: - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r10, qword ptr [rsp + 208] # 8-byte Reload - jmp .LBB11_188 -.LBB11_9: - mov r13, r15 -.LBB11_91: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.92: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_94 -# %bb.93: - xor esi, esi - jmp .LBB11_97 -.LBB11_61: - mov r13, r15 -.LBB11_72: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.73: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_75 -# %bb.74: - xor r9d, r9d - jmp .LBB11_78 -.LBB11_119: - mov r12, r15 - mov rax, rdx -.LBB11_130: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.131: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_135 -# %bb.132: + jne .LBB11_161 +# %bb.162: + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + jmp .LBB11_164 +.LBB11_163: + mov qword ptr [rsp + 112], r12 # 8-byte Spill + mov rbx, r11 +.LBB11_164: + shl rcx, 5 + mov r8, r15 + sub r8, rcx + jle .LBB11_215 +# %bb.165: + or rcx, 1 + cmp r15, rcx + jne .LBB11_180 +# %bb.166: xor esi, esi - jmp .LBB11_133 -.LBB11_177: - mov r14, r15 - mov rbx, rdx -.LBB11_188: - shl r10, 5 - cmp r10, r11 - jge .LBB11_201 -# %bb.189: - mov r8, r11 - sub r8, r10 - not r10 - add r10, r11 - jne .LBB11_193 -# %bb.190: - xor r11d, r11d - jmp .LBB11_191 -.LBB11_155: - mov r9, r8 - and r9, -2 - xor r11d, r11d + jmp .LBB11_183 +.LBB11_167: + mov r10, r9 + and r10, -2 + xor r14d, r14d .p2align 4, 0x90 -.LBB11_156: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] +.LBB11_168: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] mov edi, 0 adc dil, -1 - mov rsi, r11 + mov rsi, r14 shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - xor dil, r10b - mov ecx, r11d + mov r15, r12 + movzx r11d, byte ptr [r12 + rsi] + xor dil, r11b + mov ecx, r14d and cl, 6 mov al, 1 shl al, cl and al, dil - xor al, r10b - mov byte ptr [r15 + rsi], al - add r11, 2 - cmp r14, qword ptr [rdx + 8] + xor al, r11b + mov byte ptr [r12 + rsi], al + add r14, 2 + cmp r8, qword ptr [rdx + 8] lea rdx, [rdx + 16] mov edi, 0 adc dil, -1 @@ -58067,186 +59831,188 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB11_156 -.LBB11_40: - test r8b, 1 - je .LBB11_201 -# %bb.41: + mov byte ptr [r12 + rsi], bl + cmp r10, r14 + jne .LBB11_168 +.LBB11_169: + test r9b, 1 + je .LBB11_215 +# %bb.170: xor eax, eax - cmp r14, qword ptr [rdx] - jmp .LBB11_199 -.LBB11_153: - mov r10, r8 - and r10, -2 + cmp r8, qword ptr [rdx] + jmp .LBB11_197 +.LBB11_171: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB11_154: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] +.LBB11_172: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] setge al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r15 + rsi] + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b - mov byte ptr [r15 + rsi], bl + xor bl, r10b + mov byte ptr [r12 + rsi], bl add rdi, 2 - cmp r14d, dword ptr [rdx + 4] + cmp r8d, dword ptr [rdx + 4] lea rdx, [rdx + 8] - setge r9b - neg r9b - xor r9b, bl + setge r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl - mov byte ptr [r15 + rsi], al - cmp r10, rdi - jne .LBB11_154 -.LBB11_150: - test r8b, 1 - je .LBB11_201 -# %bb.151: - cmp r14d, dword ptr [rdx] - jmp .LBB11_152 -.LBB11_94: + mov byte ptr [r12 + rsi], al + cmp r11, rdi + jne .LBB11_172 +.LBB11_173: + test r9b, 1 + je .LBB11_215 +# %bb.174: + cmp r8d, dword ptr [rdx] + jmp .LBB11_203 +.LBB11_175: mov r10, r8 and r10, -2 - xor esi, esi + xor r9d, r9d .p2align 4, 0x90 -.LBB11_95: # =>This Inner Loop Header: Depth=1 - cmp r14b, byte ptr [rdx + rsi] - setge al - neg al - mov rdi, rsi - shr rdi, 3 - mov ecx, esi +.LBB11_176: # =>This Inner Loop Header: Depth=1 + mov rax, r9 + cmp r14b, byte ptr [rdi + r9] + setge bl + neg bl + mov rsi, r9 + shr rsi, 3 + mov ecx, eax and cl, 6 - mov bl, 1 - shl bl, cl - movzx r9d, byte ptr [r13 + rdi] - xor al, r9b - and bl, al + mov dl, 1 + shl dl, cl + movzx r9d, byte ptr [r13 + rsi] xor bl, r9b - mov byte ptr [r13 + rdi], bl - cmp r14b, byte ptr [rdx + rsi + 1] - lea rsi, [rsi + 2] - setge r9b - neg r9b - xor r9b, bl + and dl, bl + xor dl, r9b + mov byte ptr [r13 + rsi], dl + cmp r14b, byte ptr [rdi + rax + 1] + lea r9, [rax + 2] + setge bl + neg bl + xor bl, dl or cl, 1 mov al, 1 shl al, cl - and al, r9b - xor al, bl - mov byte ptr [r13 + rdi], al - cmp r10, rsi - jne .LBB11_95 -# %bb.96: - add rdx, rsi -.LBB11_97: + and al, bl + xor al, dl + mov byte ptr [r13 + rsi], al + cmp r10, r9 + jne .LBB11_176 +# %bb.177: + add rdi, r9 +.LBB11_178: test r8b, 1 - je .LBB11_201 -# %bb.98: - cmp r14b, byte ptr [rdx] + je .LBB11_215 +# %bb.179: + cmp r14b, byte ptr [rdi] setge al neg al - mov rdx, rsi + mov rdx, r9 shr rdx, 3 mov dil, byte ptr [r13 + rdx] - and sil, 7 + and r9b, 7 mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - jmp .LBB11_80 -.LBB11_75: + mov ecx, r9d + jmp .LBB11_209 +.LBB11_180: mov r10, r8 and r10, -2 - xor r9d, r9d + xor esi, esi + mov r11, qword ptr [rsp + 112] # 8-byte Reload .p2align 4, 0x90 -.LBB11_76: # =>This Inner Loop Header: Depth=1 - mov rax, r9 - cmp r14b, byte ptr [rdx + r9] - mov esi, 0 - adc sil, -1 - mov rdi, r9 +.LBB11_181: # =>This Inner Loop Header: Depth=1 + cmp r13b, byte ptr [rbx + rsi] + mov r15, rbx + mov ebx, 0 + adc bl, -1 + mov rdi, rsi shr rdi, 3 - movzx r9d, byte ptr [r13 + rdi] - mov ecx, eax + movzx r9d, byte ptr [r11 + rdi] + mov ecx, esi and cl, 6 - mov bl, 1 - shl bl, cl - xor sil, r9b - and bl, sil + mov dl, 1 + shl dl, cl xor bl, r9b - mov byte ptr [r13 + rdi], bl - cmp r14b, byte ptr [rdx + rax + 1] - lea r9, [rax + 2] - mov esi, 0 - adc sil, -1 - xor sil, bl + and dl, bl + xor dl, r9b + mov byte ptr [r11 + rdi], dl + cmp r13b, byte ptr [r15 + rsi + 1] + lea rsi, [rsi + 2] + mov ebx, 0 + adc bl, -1 + xor bl, dl or cl, 1 mov al, 1 shl al, cl - and al, sil - xor al, bl - mov byte ptr [r13 + rdi], al - cmp r10, r9 - jne .LBB11_76 -# %bb.77: - add rdx, r9 -.LBB11_78: + and al, bl + mov rbx, r15 + xor al, dl + mov byte ptr [r11 + rdi], al + cmp r10, rsi + jne .LBB11_181 +# %bb.182: + add rbx, rsi +.LBB11_183: test r8b, 1 - je .LBB11_201 -# %bb.79: + je .LBB11_215 +# %bb.184: xor eax, eax - cmp r14b, byte ptr [rdx] + cmp r13b, byte ptr [rbx] adc al, -1 - mov rdx, r9 + mov rdx, rsi shr rdx, 3 - mov dil, byte ptr [r13 + rdx] - and r9b, 7 + mov r14, qword ptr [rsp + 112] # 8-byte Reload + mov dil, byte ptr [r14 + rdx] + and sil, 7 mov bl, 1 - mov ecx, r9d + mov ecx, esi shl bl, cl xor al, dil and bl, al -.LBB11_80: xor bl, dil - mov byte ptr [r13 + rdx], bl - jmp .LBB11_201 -.LBB11_137: - mov r9, r8 - and r9, -2 - xor r11d, r11d + mov byte ptr [r14 + rdx], bl + jmp .LBB11_215 +.LBB11_185: + mov r10, r9 + and r10, -2 + xor r14d, r14d .p2align 4, 0x90 -.LBB11_138: # =>This Inner Loop Header: Depth=1 - cmp r14d, dword ptr [rdx] +.LBB11_186: # =>This Inner Loop Header: Depth=1 + cmp r8d, dword ptr [rdx] mov edi, 0 adc dil, -1 - mov rsi, r11 + mov rsi, r14 shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - xor dil, r10b - mov ecx, r11d + mov r15, r12 + movzx r11d, byte ptr [r12 + rsi] + xor dil, r11b + mov ecx, r14d and cl, 6 mov al, 1 shl al, cl and al, dil - xor al, r10b - mov byte ptr [r15 + rsi], al - add r11, 2 - cmp r14d, dword ptr [rdx + 4] + xor al, r11b + mov byte ptr [r12 + rsi], al + add r14, 2 + cmp r8d, dword ptr [rdx + 4] lea rdx, [rdx + 8] mov edi, 0 adc dil, -1 @@ -58256,28 +60022,29 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB11_138 -.LBB11_24: - test r8b, 1 - je .LBB11_201 -# %bb.25: + mov byte ptr [r12 + rsi], bl + cmp r10, r14 + jne .LBB11_186 +.LBB11_187: + test r9b, 1 + je .LBB11_215 +# %bb.188: xor eax, eax - cmp r14d, dword ptr [rdx] - jmp .LBB11_199 -.LBB11_195: + cmp r8d, dword ptr [rdx] + jmp .LBB11_197 +.LBB11_189: mov r10, r8 and r10, -2 xor r11d, r11d .p2align 4, 0x90 -.LBB11_196: # =>This Inner Loop Header: Depth=1 +.LBB11_190: # =>This Inner Loop Header: Depth=1 ucomisd xmm0, qword ptr [rdx] mov eax, 0 adc al, -1 mov rsi, r11 shr rsi, 3 - movzx r9d, byte ptr [r15 + rsi] + mov r14, r12 + movzx r9d, byte ptr [r12 + rsi] mov ecx, r11d and cl, 6 mov bl, 1 @@ -58285,7 +60052,7 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr xor al, r9b and bl, al xor bl, r9b - mov byte ptr [r15 + rsi], bl + mov byte ptr [r12 + rsi], bl add r11, 2 ucomisd xmm0, qword ptr [rdx + 8] lea rdx, [rdx + 16] @@ -58297,38 +60064,46 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl al, cl and al, dil xor al, bl - mov byte ptr [r15 + rsi], al + mov byte ptr [r12 + rsi], al cmp r10, r11 - jne .LBB11_196 -.LBB11_197: + jne .LBB11_190 +.LBB11_191: test r8b, 1 - je .LBB11_201 -# %bb.198: + je .LBB11_215 +# %bb.192: xor eax, eax ucomisd xmm0, qword ptr [rdx] - jmp .LBB11_199 -.LBB11_112: - mov r9, r8 - and r9, -2 - xor r11d, r11d + adc al, -1 + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r12 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + jmp .LBB11_198 +.LBB11_193: + mov r10, r9 + and r10, -2 + xor r14d, r14d .p2align 4, 0x90 -.LBB11_113: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rdx] +.LBB11_194: # =>This Inner Loop Header: Depth=1 + cmp r8w, word ptr [rdx] mov edi, 0 adc dil, -1 - mov rsi, r11 + mov rsi, r14 shr rsi, 3 - movzx r10d, byte ptr [r15 + rsi] - xor dil, r10b - mov ecx, r11d + mov r15, r12 + movzx r11d, byte ptr [r12 + rsi] + xor dil, r11b + mov ecx, r14d and cl, 6 mov al, 1 shl al, cl and al, dil - xor al, r10b - mov byte ptr [r15 + rsi], al - add r11, 2 - cmp r14w, word ptr [rdx + 2] + xor al, r11b + mov byte ptr [r12 + rsi], al + add r14, 2 + cmp r8w, word ptr [rdx + 2] lea rdx, [rdx + 4] mov edi, 0 adc dil, -1 @@ -58338,82 +60113,193 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr shl bl, cl and bl, dil xor bl, al - mov byte ptr [r15 + rsi], bl - cmp r9, r11 - jne .LBB11_113 -.LBB11_110: - test r8b, 1 - je .LBB11_201 -# %bb.111: + mov byte ptr [r12 + rsi], bl + cmp r10, r14 + jne .LBB11_194 +.LBB11_195: + test r9b, 1 + je .LBB11_215 +# %bb.196: xor eax, eax - cmp r14w, word ptr [rdx] -.LBB11_199: + cmp r8w, word ptr [rdx] +.LBB11_197: adc al, -1 - mov rdx, r11 + mov rdx, r14 shr rdx, 3 - mov sil, byte ptr [r15 + rdx] - and r11b, 7 + mov sil, byte ptr [r12 + rdx] + and r14b, 7 mov bl, 1 - mov ecx, r11d + mov ecx, r14d +.LBB11_198: shl bl, cl xor al, sil and bl, al - jmp .LBB11_200 -.LBB11_170: - mov r10, r8 - and r10, -2 + jmp .LBB11_204 +.LBB11_199: + mov r11, r9 + and r11, -2 xor edi, edi .p2align 4, 0x90 -.LBB11_171: # =>This Inner Loop Header: Depth=1 - cmp r14, qword ptr [rdx] +.LBB11_200: # =>This Inner Loop Header: Depth=1 + cmp r8, qword ptr [rdx] setge al neg al mov rsi, rdi shr rsi, 3 - movzx r9d, byte ptr [r15 + rsi] + mov r14, r12 + movzx r10d, byte ptr [r12 + rsi] mov ecx, edi and cl, 6 mov bl, 1 shl bl, cl - xor al, r9b + xor al, r10b and bl, al - xor bl, r9b - mov byte ptr [r15 + rsi], bl + xor bl, r10b + mov byte ptr [r12 + rsi], bl add rdi, 2 - cmp r14, qword ptr [rdx + 8] + cmp r8, qword ptr [rdx + 8] lea rdx, [rdx + 16] - setge r9b - neg r9b - xor r9b, bl + setge r10b + neg r10b + xor r10b, bl or cl, 1 mov al, 1 shl al, cl - and al, r9b + and al, r10b xor al, bl - mov byte ptr [r15 + rsi], al - cmp r10, rdi - jne .LBB11_171 -.LBB11_168: - test r8b, 1 - je .LBB11_201 -# %bb.169: - cmp r14, qword ptr [rdx] -.LBB11_152: + mov byte ptr [r12 + rsi], al + cmp r11, rdi + jne .LBB11_200 +.LBB11_201: + test r9b, 1 + je .LBB11_215 +# %bb.202: + cmp r8, qword ptr [rdx] +.LBB11_203: setge al neg al mov rdx, rdi shr rdx, 3 - mov sil, byte ptr [r15 + rdx] + mov sil, byte ptr [r12 + rdx] and dil, 7 mov bl, 1 mov ecx, edi shl bl, cl xor al, sil and bl, al -.LBB11_200: +.LBB11_204: xor bl, sil - mov byte ptr [r15 + rdx], bl -.LBB11_201: + mov byte ptr [r12 + rdx], bl + jmp .LBB11_215 +.LBB11_205: + mov r9, r8 + and r9, -2 + xor esi, esi + .p2align 4, 0x90 +.LBB11_206: # =>This Inner Loop Header: Depth=1 + mov rax, rdx + cmp r14w, word ptr [rdx] + setge dl + neg dl + mov rdi, rsi + shr rdi, 3 + movzx r10d, byte ptr [r13 + rdi] + mov ecx, esi + and cl, 6 + mov bl, 1 + shl bl, cl + xor dl, r10b + and bl, dl + xor bl, r10b + mov byte ptr [r13 + rdi], bl + add rsi, 2 + cmp r14w, word ptr [rax + 2] + lea rdx, [rax + 4] + setge r10b + neg r10b + xor r10b, bl + or cl, 1 + mov al, 1 + shl al, cl + and al, r10b + xor al, bl + mov byte ptr [r13 + rdi], al + cmp r9, rsi + jne .LBB11_206 +.LBB11_207: + test r8b, 1 + je .LBB11_215 +# %bb.208: + cmp r14w, word ptr [rdx] + setge al + neg al + mov rdx, rsi + shr rdx, 3 + mov dil, byte ptr [r13 + rdx] + and sil, 7 + mov bl, 1 + mov ecx, esi +.LBB11_209: + shl bl, cl + xor al, dil + and bl, al + xor bl, dil + jmp .LBB11_214 +.LBB11_210: + mov r10, r8 + and r10, -2 + xor r11d, r11d + mov r14, r13 + .p2align 4, 0x90 +.LBB11_211: # =>This Inner Loop Header: Depth=1 + ucomiss xmm0, dword ptr [rbx] + mov edx, 0 + adc dl, -1 + mov rdi, r11 + shr rdi, 3 + movzx r9d, byte ptr [r14 + rdi] + mov ecx, r11d + and cl, 6 + mov al, 1 + shl al, cl + xor dl, r9b + and al, dl + xor al, r9b + mov byte ptr [r14 + rdi], al + add r11, 2 + ucomiss xmm0, dword ptr [rbx + 4] + lea rbx, [rbx + 8] + mov esi, 0 + adc sil, -1 + xor sil, al + or cl, 1 + mov dl, 1 + shl dl, cl + and dl, sil + xor dl, al + mov byte ptr [r14 + rdi], dl + cmp r10, r11 + jne .LBB11_211 +.LBB11_212: + test r8b, 1 + je .LBB11_215 +# %bb.213: + xor eax, eax + ucomiss xmm0, dword ptr [rbx] + adc al, -1 + mov rdx, r11 + shr rdx, 3 + mov sil, byte ptr [r13 + rdx] + and r11b, 7 + mov bl, 1 + mov ecx, r11d + shl bl, cl + xor al, sil + and bl, al + xor bl, sil +.LBB11_214: + mov byte ptr [r13 + rdx], bl +.LBB11_215: lea rsp, [rbp - 40] pop rbx pop r12 @@ -58422,323 +60308,1135 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr pop r15 pop rbp ret -.LBB11_135: - mov r9, r8 - and r9, -2 +.LBB11_216: + and rcx, -8 + mov rax, rcx + shl rax, 6 + add rax, rdx + mov qword ptr [rsp + 56], rax # 8-byte Spill + mov qword ptr [rsp + 24], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 48], rax # 8-byte Spill + movd xmm0, r14d + pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] + pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] + xor r14d, r14d + mov qword ptr [rsp + 136], r12 # 8-byte Spill + pxor xmm15, xmm15 + .p2align 4, 0x90 +.LBB11_217: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 40], r14 # 8-byte Spill + shl r14, 6 + mov r9, r14 + mov r15, r14 + mov r12, r14 + mov r13, r14 + mov rsi, r14 + mov r8, r14 + movzx eax, word ptr [rdx + r14] + movd xmm5, eax + movzx eax, word ptr [rdx + r14 + 2] + movd xmm0, eax + movzx eax, word ptr [rdx + r14 + 4] + movd xmm1, eax + movzx eax, word ptr [rdx + r14 + 6] + movd xmm7, eax + movzx eax, word ptr [rdx + r14 + 8] + movd xmm8, eax + movzx eax, word ptr [rdx + r14 + 10] + movd xmm4, eax + movzx eax, word ptr [rdx + r14 + 12] + movzx r10d, word ptr [rdx + r14 + 14] + movzx ebx, word ptr [rdx + r14 + 16] + movzx edi, word ptr [rdx + r14 + 18] + movzx ecx, word ptr [rdx + r14 + 20] + mov dword ptr [rsp + 16], ecx # 4-byte Spill + mov rcx, r14 + or rcx, 64 + or r9, 128 + or r15, 192 + or r12, 256 + or r13, 320 + or rsi, 384 + pinsrw xmm5, word ptr [rdx + rcx], 1 + pinsrw xmm5, word ptr [rdx + r9], 2 + pinsrw xmm5, word ptr [rdx + r15], 3 + pinsrw xmm5, word ptr [rdx + r12], 4 + pinsrw xmm5, word ptr [rdx + r13], 5 + pinsrw xmm5, word ptr [rdx + rsi], 6 + pinsrw xmm0, word ptr [rdx + rcx + 2], 1 + pinsrw xmm0, word ptr [rdx + r9 + 2], 2 + pinsrw xmm0, word ptr [rdx + r15 + 2], 3 + pinsrw xmm0, word ptr [rdx + r12 + 2], 4 + pinsrw xmm0, word ptr [rdx + r13 + 2], 5 + pinsrw xmm0, word ptr [rdx + rsi + 2], 6 + or r8, 448 + pinsrw xmm0, word ptr [rdx + r8 + 2], 7 + movd xmm2, eax + movzx eax, word ptr [rdx + r14 + 22] + mov dword ptr [rsp + 32], eax # 4-byte Spill + pcmpgtw xmm0, xmm11 + pinsrw xmm1, word ptr [rdx + rcx + 4], 1 + pinsrw xmm1, word ptr [rdx + r9 + 4], 2 + pinsrw xmm1, word ptr [rdx + r15 + 4], 3 + pinsrw xmm1, word ptr [rdx + r12 + 4], 4 + pinsrw xmm1, word ptr [rdx + r13 + 4], 5 + pinsrw xmm1, word ptr [rdx + rsi + 4], 6 + pinsrw xmm1, word ptr [rdx + r8 + 4], 7 + packsswb xmm0, xmm0 + pcmpgtw xmm1, xmm11 + movdqa xmm9, xmmword ptr [rip + .LCPI11_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm3, xmm9 + pblendvb xmm3, xmm15, xmm0 + packsswb xmm1, xmm1 + movdqa xmm0, xmmword ptr [rip + .LCPI11_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm0 + movdqa xmm14, xmm0 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r10d + movzx r11d, word ptr [rdx + r14 + 24] + pinsrw xmm5, word ptr [rdx + r8], 7 + pcmpgtw xmm5, xmm11 + pcmpeqd xmm0, xmm0 + pxor xmm5, xmm0 + packsswb xmm5, xmm5 + pinsrw xmm7, word ptr [rdx + rcx + 6], 1 + pinsrw xmm7, word ptr [rdx + r9 + 6], 2 + pinsrw xmm7, word ptr [rdx + r15 + 6], 3 + pinsrw xmm7, word ptr [rdx + r12 + 6], 4 + pinsrw xmm7, word ptr [rdx + r13 + 6], 5 + pinsrw xmm7, word ptr [rdx + rsi + 6], 6 + pinsrw xmm7, word ptr [rdx + r8 + 6], 7 + pcmpgtw xmm7, xmm11 + packsswb xmm7, xmm7 + pinsrw xmm8, word ptr [rdx + rcx + 8], 1 + pinsrw xmm8, word ptr [rdx + r9 + 8], 2 + pinsrw xmm8, word ptr [rdx + r15 + 8], 3 + pinsrw xmm8, word ptr [rdx + r12 + 8], 4 + pinsrw xmm8, word ptr [rdx + r13 + 8], 5 + pinsrw xmm8, word ptr [rdx + rsi + 8], 6 + pinsrw xmm8, word ptr [rdx + r8 + 8], 7 + psubb xmm3, xmm5 + movdqa xmm12, xmmword ptr [rip + .LCPI11_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm7 + pblendvb xmm12, xmm15, xmm0 + movd xmm7, ebx + movzx eax, word ptr [rdx + r14 + 26] + pcmpgtw xmm8, xmm11 + packsswb xmm8, xmm8 + por xmm12, xmm6 + movdqa xmm13, xmmword ptr [rip + .LCPI11_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm8 + pblendvb xmm13, xmm15, xmm0 + movd xmm6, edi + movzx r10d, word ptr [rdx + r14 + 28] + pinsrw xmm4, word ptr [rdx + rcx + 10], 1 + pinsrw xmm4, word ptr [rdx + r9 + 10], 2 + pinsrw xmm4, word ptr [rdx + r15 + 10], 3 + pinsrw xmm4, word ptr [rdx + r12 + 10], 4 + pinsrw xmm4, word ptr [rdx + r13 + 10], 5 + pinsrw xmm4, word ptr [rdx + rsi + 10], 6 + pinsrw xmm4, word ptr [rdx + r8 + 10], 7 + pcmpgtw xmm4, xmm11 + packsswb xmm4, xmm4 + pinsrw xmm2, word ptr [rdx + rcx + 12], 1 + pinsrw xmm2, word ptr [rdx + r9 + 12], 2 + pinsrw xmm2, word ptr [rdx + r15 + 12], 3 + pinsrw xmm2, word ptr [rdx + r12 + 12], 4 + pinsrw xmm2, word ptr [rdx + r13 + 12], 5 + pinsrw xmm2, word ptr [rdx + rsi + 12], 6 + por xmm12, xmm3 + movdqa xmm5, xmmword ptr [rip + .LCPI11_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 30] + pinsrw xmm2, word ptr [rdx + r8 + 12], 7 + pcmpgtw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm13 + movdqa xmm13, xmmword ptr [rip + .LCPI11_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm3, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm3 = mem[0],zero,zero,zero + movzx edi, word ptr [rdx + r14 + 32] + mov dword ptr [rsp + 32], edi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + rcx + 14], 1 + pinsrw xmm1, word ptr [rdx + r9 + 14], 2 + pinsrw xmm1, word ptr [rdx + r15 + 14], 3 + pinsrw xmm1, word ptr [rdx + r12 + 14], 4 + pinsrw xmm1, word ptr [rdx + r13 + 14], 5 + pinsrw xmm1, word ptr [rdx + rsi + 14], 6 + por xmm13, xmm5 + movd xmm2, r11d + movzx edi, word ptr [rdx + r14 + 34] + mov dword ptr [rsp + 16], edi # 4-byte Spill + pinsrw xmm1, word ptr [rdx + r8 + 14], 7 + pcmpgtw xmm1, xmm11 + pinsrw xmm6, word ptr [rdx + rcx + 18], 1 + pinsrw xmm6, word ptr [rdx + r9 + 18], 2 + pinsrw xmm6, word ptr [rdx + r15 + 18], 3 + pinsrw xmm6, word ptr [rdx + r12 + 18], 4 + pinsrw xmm6, word ptr [rdx + r13 + 18], 5 + pinsrw xmm6, word ptr [rdx + rsi + 18], 6 + packsswb xmm1, xmm1 + pinsrw xmm6, word ptr [rdx + r8 + 18], 7 + pcmpgtw xmm6, xmm11 + packsswb xmm6, xmm6 + por xmm13, xmm12 + movdqa xmm12, xmmword ptr [rip + .LCPI11_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm12, xmm15, xmm0 + movdqa xmm8, xmm9 + movdqa xmm0, xmm6 + pblendvb xmm8, xmm15, xmm0 + movd xmm1, eax + movzx r11d, word ptr [rdx + r14 + 36] + pinsrw xmm7, word ptr [rdx + rcx + 16], 1 + pinsrw xmm7, word ptr [rdx + r9 + 16], 2 + pinsrw xmm7, word ptr [rdx + r15 + 16], 3 + pinsrw xmm7, word ptr [rdx + r12 + 16], 4 + pinsrw xmm7, word ptr [rdx + r13 + 16], 5 + pinsrw xmm7, word ptr [rdx + rsi + 16], 6 + pinsrw xmm4, word ptr [rdx + rcx + 20], 1 + pinsrw xmm4, word ptr [rdx + r9 + 20], 2 + pinsrw xmm4, word ptr [rdx + r15 + 20], 3 + pinsrw xmm4, word ptr [rdx + r12 + 20], 4 + pinsrw xmm4, word ptr [rdx + r13 + 20], 5 + pinsrw xmm4, word ptr [rdx + rsi + 20], 6 + pinsrw xmm4, word ptr [rdx + r8 + 20], 7 + pcmpgtw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm12, xmm13 + movdqa xmm5, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm5, xmm15, xmm0 + movd xmm4, r10d + movzx edi, word ptr [rdx + r14 + 38] + pinsrw xmm7, word ptr [rdx + r8 + 16], 7 + pcmpgtw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI11_22] + packsswb xmm7, xmm7 + pinsrw xmm3, word ptr [rdx + rcx + 22], 1 + pinsrw xmm3, word ptr [rdx + r9 + 22], 2 + pinsrw xmm3, word ptr [rdx + r15 + 22], 3 + pinsrw xmm3, word ptr [rdx + r12 + 22], 4 + pinsrw xmm3, word ptr [rdx + r13 + 22], 5 + pinsrw xmm3, word ptr [rdx + rsi + 22], 6 + pinsrw xmm3, word ptr [rdx + r8 + 22], 7 + pcmpgtw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rdx + rcx + 24], 1 + pinsrw xmm2, word ptr [rdx + r9 + 24], 2 + pinsrw xmm2, word ptr [rdx + r15 + 24], 3 + pinsrw xmm2, word ptr [rdx + r12 + 24], 4 + pinsrw xmm2, word ptr [rdx + r13 + 24], 5 + pinsrw xmm2, word ptr [rdx + rsi + 24], 6 + pinsrw xmm2, word ptr [rdx + r8 + 24], 7 + psubb xmm8, xmm7 + movdqa xmm10, xmmword ptr [rip + .LCPI11_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm14, xmm10 + movdqa xmm0, xmm3 + pblendvb xmm14, xmm15, xmm0 + movd xmm3, ebx + movzx eax, word ptr [rdx + r14 + 40] + pcmpgtw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm14, xmm5 + movdqa xmm9, xmmword ptr [rip + .LCPI11_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm13, xmm15, xmm0 + movd xmm7, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm7 = mem[0],zero,zero,zero + movzx r10d, word ptr [rdx + r14 + 42] + pinsrw xmm1, word ptr [rdx + rcx + 26], 1 + pinsrw xmm1, word ptr [rdx + r9 + 26], 2 + pinsrw xmm1, word ptr [rdx + r15 + 26], 3 + pinsrw xmm1, word ptr [rdx + r12 + 26], 4 + pinsrw xmm1, word ptr [rdx + r13 + 26], 5 + pinsrw xmm1, word ptr [rdx + rsi + 26], 6 + pinsrw xmm1, word ptr [rdx + r8 + 26], 7 + pcmpgtw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm4, word ptr [rdx + rcx + 28], 1 + pinsrw xmm4, word ptr [rdx + r9 + 28], 2 + pinsrw xmm4, word ptr [rdx + r15 + 28], 3 + pinsrw xmm4, word ptr [rdx + r12 + 28], 4 + pinsrw xmm4, word ptr [rdx + r13 + 28], 5 + pinsrw xmm4, word ptr [rdx + rsi + 28], 6 + por xmm14, xmm8 + movdqa xmm5, xmmword ptr [rip + .LCPI11_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm2, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm2 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 44] + mov dword ptr [rsp + 32], ebx # 4-byte Spill + pinsrw xmm4, word ptr [rdx + r8 + 28], 7 + pcmpgtw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm5, xmm13 + movdqa xmm6, xmmword ptr [rip + .LCPI11_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, r11d + movzx ebx, word ptr [rdx + r14 + 46] + mov dword ptr [rsp + 16], ebx # 4-byte Spill + pinsrw xmm3, word ptr [rdx + rcx + 30], 1 + pinsrw xmm3, word ptr [rdx + r9 + 30], 2 + pinsrw xmm3, word ptr [rdx + r15 + 30], 3 + pinsrw xmm3, word ptr [rdx + r12 + 30], 4 + pinsrw xmm3, word ptr [rdx + r13 + 30], 5 + pinsrw xmm3, word ptr [rdx + rsi + 30], 6 + por xmm6, xmm5 + movd xmm1, edi + movzx edi, word ptr [rdx + r14 + 48] + pinsrw xmm3, word ptr [rdx + r8 + 30], 7 + pcmpgtw xmm3, xmm11 + pinsrw xmm2, word ptr [rdx + rcx + 34], 1 + pinsrw xmm2, word ptr [rdx + r9 + 34], 2 + pinsrw xmm2, word ptr [rdx + r15 + 34], 3 + pinsrw xmm2, word ptr [rdx + r12 + 34], 4 + pinsrw xmm2, word ptr [rdx + r13 + 34], 5 + pinsrw xmm2, word ptr [rdx + rsi + 34], 6 + packsswb xmm3, xmm3 + pinsrw xmm2, word ptr [rdx + r8 + 34], 7 + pcmpgtw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm6, xmm14 + movdqa xmm14, xmmword ptr [rip + .LCPI11_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> + movdqa xmm13, xmm14 + movdqa xmm0, xmm3 + pblendvb xmm13, xmm15, xmm0 + movdqa xmm8, xmmword ptr [rip + .LCPI11_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm8, xmm15, xmm0 + movd xmm2, eax + movzx r11d, word ptr [rdx + r14 + 50] + pinsrw xmm7, word ptr [rdx + rcx + 32], 1 + pinsrw xmm7, word ptr [rdx + r9 + 32], 2 + pinsrw xmm7, word ptr [rdx + r15 + 32], 3 + pinsrw xmm7, word ptr [rdx + r12 + 32], 4 + pinsrw xmm7, word ptr [rdx + r13 + 32], 5 + pinsrw xmm7, word ptr [rdx + rsi + 32], 6 + pinsrw xmm4, word ptr [rdx + rcx + 36], 1 + pinsrw xmm4, word ptr [rdx + r9 + 36], 2 + pinsrw xmm4, word ptr [rdx + r15 + 36], 3 + pinsrw xmm4, word ptr [rdx + r12 + 36], 4 + pinsrw xmm4, word ptr [rdx + r13 + 36], 5 + pinsrw xmm4, word ptr [rdx + rsi + 36], 6 + pinsrw xmm4, word ptr [rdx + r8 + 36], 7 + pcmpgtw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm13, xmm6 + movdqa xmm6, xmmword ptr [rip + .LCPI11_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm4 + pblendvb xmm6, xmm15, xmm0 + movd xmm3, r10d + movzx r10d, word ptr [rdx + r14 + 52] + pinsrw xmm7, word ptr [rdx + r8 + 32], 7 + pcmpgtw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI11_22] + packsswb xmm7, xmm7 + pinsrw xmm1, word ptr [rdx + rcx + 38], 1 + pinsrw xmm1, word ptr [rdx + r9 + 38], 2 + pinsrw xmm1, word ptr [rdx + r15 + 38], 3 + pinsrw xmm1, word ptr [rdx + r12 + 38], 4 + pinsrw xmm1, word ptr [rdx + r13 + 38], 5 + pinsrw xmm1, word ptr [rdx + rsi + 38], 6 + pinsrw xmm1, word ptr [rdx + r8 + 38], 7 + pcmpgtw xmm1, xmm11 + packsswb xmm1, xmm1 + pinsrw xmm2, word ptr [rdx + rcx + 40], 1 + pinsrw xmm2, word ptr [rdx + r9 + 40], 2 + pinsrw xmm2, word ptr [rdx + r15 + 40], 3 + pinsrw xmm2, word ptr [rdx + r12 + 40], 4 + pinsrw xmm2, word ptr [rdx + r13 + 40], 5 + pinsrw xmm2, word ptr [rdx + rsi + 40], 6 + pinsrw xmm2, word ptr [rdx + r8 + 40], 7 + psubb xmm8, xmm7 + movdqa xmm5, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm5, xmm15, xmm0 + movd xmm1, dword ptr [rsp + 32] # 4-byte Folded Reload + # xmm1 = mem[0],zero,zero,zero + movzx eax, word ptr [rdx + r14 + 54] + pcmpgtw xmm2, xmm11 + packsswb xmm2, xmm2 + por xmm5, xmm6 + movdqa xmm6, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm6, xmm15, xmm0 + movd xmm4, dword ptr [rsp + 16] # 4-byte Folded Reload + # xmm4 = mem[0],zero,zero,zero + movzx ebx, word ptr [rdx + r14 + 56] + pinsrw xmm3, word ptr [rdx + rcx + 42], 1 + pinsrw xmm3, word ptr [rdx + r9 + 42], 2 + pinsrw xmm3, word ptr [rdx + r15 + 42], 3 + pinsrw xmm3, word ptr [rdx + r12 + 42], 4 + pinsrw xmm3, word ptr [rdx + r13 + 42], 5 + pinsrw xmm3, word ptr [rdx + rsi + 42], 6 + pinsrw xmm3, word ptr [rdx + r8 + 42], 7 + pcmpgtw xmm3, xmm11 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rdx + rcx + 44], 1 + pinsrw xmm1, word ptr [rdx + r9 + 44], 2 + pinsrw xmm1, word ptr [rdx + r15 + 44], 3 + pinsrw xmm1, word ptr [rdx + r12 + 44], 4 + pinsrw xmm1, word ptr [rdx + r13 + 44], 5 + pinsrw xmm1, word ptr [rdx + rsi + 44], 6 + por xmm5, xmm8 + movdqa xmm9, xmmword ptr [rip + .LCPI11_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> + movdqa xmm2, xmm9 + movdqa xmm0, xmm3 + pblendvb xmm2, xmm15, xmm0 + movd xmm7, edi + movzx edi, word ptr [rdx + r14 + 58] + pinsrw xmm1, word ptr [rdx + r8 + 44], 7 + pcmpgtw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm2, xmm6 + movdqa xmm10, xmmword ptr [rip + .LCPI11_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> + movdqa xmm6, xmm10 + movdqa xmm0, xmm1 + pblendvb xmm6, xmm15, xmm0 + movd xmm1, r11d + movzx r11d, word ptr [rdx + r14 + 60] + por xmm6, xmm2 + movd xmm2, r10d + pinsrw xmm4, word ptr [rdx + rcx + 46], 1 + pinsrw xmm4, word ptr [rdx + r9 + 46], 2 + pinsrw xmm4, word ptr [rdx + r15 + 46], 3 + pinsrw xmm4, word ptr [rdx + r12 + 46], 4 + pinsrw xmm4, word ptr [rdx + r13 + 46], 5 + pinsrw xmm4, word ptr [rdx + rsi + 46], 6 + pinsrw xmm4, word ptr [rdx + r8 + 46], 7 + pcmpgtw xmm4, xmm11 + packsswb xmm4, xmm4 + por xmm6, xmm5 + movdqa xmm8, xmm14 + movdqa xmm0, xmm4 + pblendvb xmm8, xmm15, xmm0 + movd xmm3, eax + pinsrw xmm1, word ptr [rdx + rcx + 50], 1 + pinsrw xmm1, word ptr [rdx + r9 + 50], 2 + pinsrw xmm1, word ptr [rdx + r15 + 50], 3 + pinsrw xmm1, word ptr [rdx + r12 + 50], 4 + pinsrw xmm1, word ptr [rdx + r13 + 50], 5 + pinsrw xmm1, word ptr [rdx + rsi + 50], 6 + pinsrw xmm1, word ptr [rdx + r8 + 50], 7 + pcmpgtw xmm1, xmm11 + packsswb xmm1, xmm1 + por xmm8, xmm6 + movdqa xmm4, xmmword ptr [rip + .LCPI11_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movd xmm1, ebx + pinsrw xmm7, word ptr [rdx + rcx + 48], 1 + pinsrw xmm7, word ptr [rdx + r9 + 48], 2 + pinsrw xmm7, word ptr [rdx + r15 + 48], 3 + pinsrw xmm7, word ptr [rdx + r12 + 48], 4 + pinsrw xmm7, word ptr [rdx + r13 + 48], 5 + pinsrw xmm7, word ptr [rdx + rsi + 48], 6 + pinsrw xmm7, word ptr [rdx + r8 + 48], 7 + pcmpgtw xmm7, xmm11 + pxor xmm7, xmmword ptr [rip + .LCPI11_22] + pinsrw xmm2, word ptr [rdx + rcx + 52], 1 + pinsrw xmm2, word ptr [rdx + r9 + 52], 2 + pinsrw xmm2, word ptr [rdx + r15 + 52], 3 + pinsrw xmm2, word ptr [rdx + r12 + 52], 4 + pinsrw xmm2, word ptr [rdx + r13 + 52], 5 + pinsrw xmm2, word ptr [rdx + rsi + 52], 6 + packsswb xmm7, xmm7 + pinsrw xmm2, word ptr [rdx + r8 + 52], 7 + pcmpgtw xmm2, xmm11 + pinsrw xmm3, word ptr [rdx + rcx + 54], 1 + pinsrw xmm3, word ptr [rdx + r9 + 54], 2 + pinsrw xmm3, word ptr [rdx + r15 + 54], 3 + pinsrw xmm3, word ptr [rdx + r12 + 54], 4 + pinsrw xmm3, word ptr [rdx + r13 + 54], 5 + pinsrw xmm3, word ptr [rdx + rsi + 54], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rdx + r8 + 54], 7 + pcmpgtw xmm3, xmm11 + pinsrw xmm1, word ptr [rdx + rcx + 56], 1 + pinsrw xmm1, word ptr [rdx + r9 + 56], 2 + pinsrw xmm1, word ptr [rdx + r15 + 56], 3 + pinsrw xmm1, word ptr [rdx + r12 + 56], 4 + pinsrw xmm1, word ptr [rdx + r13 + 56], 5 + pinsrw xmm1, word ptr [rdx + rsi + 56], 6 + packsswb xmm3, xmm3 + pinsrw xmm1, word ptr [rdx + r8 + 56], 7 + psubb xmm4, xmm7 + movdqa xmm5, xmmword ptr [rip + .LCPI11_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm2 + pblendvb xmm5, xmm15, xmm0 + movdqa xmm6, xmmword ptr [rip + .LCPI11_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm3 + pblendvb xmm6, xmm15, xmm0 + movd xmm2, edi + pcmpgtw xmm1, xmm11 + pinsrw xmm2, word ptr [rdx + rcx + 58], 1 + pinsrw xmm2, word ptr [rdx + r9 + 58], 2 + pinsrw xmm2, word ptr [rdx + r15 + 58], 3 + pinsrw xmm2, word ptr [rdx + r12 + 58], 4 + pinsrw xmm2, word ptr [rdx + r13 + 58], 5 + pinsrw xmm2, word ptr [rdx + rsi + 58], 6 + pinsrw xmm2, word ptr [rdx + r8 + 58], 7 + packsswb xmm1, xmm1 + pcmpgtw xmm2, xmm11 + por xmm6, xmm5 + movd xmm3, r11d + pinsrw xmm3, word ptr [rdx + rcx + 60], 1 + pinsrw xmm3, word ptr [rdx + r9 + 60], 2 + pinsrw xmm3, word ptr [rdx + r15 + 60], 3 + pinsrw xmm3, word ptr [rdx + r12 + 60], 4 + pinsrw xmm3, word ptr [rdx + r13 + 60], 5 + pinsrw xmm3, word ptr [rdx + rsi + 60], 6 + packsswb xmm2, xmm2 + pinsrw xmm3, word ptr [rdx + r8 + 60], 7 + pcmpgtw xmm3, xmm11 + packsswb xmm3, xmm3 + por xmm6, xmm4 + movdqa xmm4, xmmword ptr [rip + .LCPI11_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> + movdqa xmm0, xmm1 + pblendvb xmm4, xmm15, xmm0 + movdqa xmm1, xmm9 + movdqa xmm0, xmm2 + pblendvb xmm1, xmm15, xmm0 + movdqa xmm0, xmm3 + pblendvb xmm10, xmm15, xmm0 + por xmm1, xmm4 + movzx eax, word ptr [rdx + r14 + 62] + por xmm10, xmm1 + movd xmm0, eax + pinsrw xmm0, word ptr [rdx + rcx + 62], 1 + pinsrw xmm0, word ptr [rdx + r9 + 62], 2 + pinsrw xmm0, word ptr [rdx + r15 + 62], 3 + pinsrw xmm0, word ptr [rdx + r12 + 62], 4 + mov rax, qword ptr [rsp + 136] # 8-byte Reload + pinsrw xmm0, word ptr [rdx + r13 + 62], 5 + pinsrw xmm0, word ptr [rdx + rsi + 62], 6 + pinsrw xmm0, word ptr [rdx + r8 + 62], 7 + pcmpgtw xmm0, xmm11 + packsswb xmm0, xmm0 + por xmm10, xmm6 + pblendvb xmm14, xmm15, xmm0 + por xmm14, xmm10 + movdqa xmm0, xmm12 + punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] + movdqa xmm2, xmm8 + punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] + movdqa xmm3, xmmword ptr [rip + .LCPI11_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> + pshufb xmm2, xmm3 + pshufb xmm0, xmm3 + punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] + punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] + punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] + punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] + mov rcx, qword ptr [rsp + 40] # 8-byte Reload + movdqu xmmword ptr [rax + 4*rcx], xmm12 + movdqu xmmword ptr [rax + 4*rcx + 16], xmm0 + add rcx, 8 + mov r14, rcx + cmp rcx, qword ptr [rsp + 24] # 8-byte Folded Reload + jne .LBB11_217 +# %bb.218: + mov rcx, qword ptr [rsp + 184] # 8-byte Reload + cmp rcx, qword ptr [rsp + 24] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14d, dword ptr [rsp + 8] # 4-byte Reload + mov r13, qword ptr [rsp + 48] # 8-byte Reload + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + jne .LBB11_81 + jmp .LBB11_131 +.LBB11_219: + mov r9, rcx + and r9, -4 + mov rbx, r9 + shl rbx, 7 + add rbx, rdx + lea r13, [r12 + 4*r9] + movdqa xmm1, xmm0 + shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] + add rdx, 508 xor esi, esi + movdqa xmm15, xmmword ptr [rip + .LCPI11_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> + movdqa xmm8, xmmword ptr [rip + .LCPI11_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] + movdqa xmm10, xmmword ptr [rip + .LCPI11_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] + movdqa xmm11, xmmword ptr [rip + .LCPI11_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] + movdqa xmm12, xmmword ptr [rip + .LCPI11_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] + movdqa xmm13, xmmword ptr [rip + .LCPI11_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] + movdqa xmm14, xmmword ptr [rip + .LCPI11_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + movdqa xmm9, xmmword ptr [rip + .LCPI11_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] .p2align 4, 0x90 -.LBB11_136: # =>This Inner Loop Header: Depth=1 - cmp r14w, word ptr [rax] - setge dl - neg dl - mov rdi, rsi - shr rdi, 3 - movzx r10d, byte ptr [r12 + rdi] - mov ecx, esi - and cl, 6 - mov bl, 1 - shl bl, cl - xor dl, r10b - and bl, dl - xor bl, r10b - mov byte ptr [r12 + rdi], bl - add rsi, 2 - cmp r14w, word ptr [rax + 2] - lea rax, [rax + 4] - setge r10b - neg r10b - xor r10b, bl - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, r10b - xor dl, bl - mov byte ptr [r12 + rdi], dl +.LBB11_220: # =>This Inner Loop Header: Depth=1 + movss xmm6, dword ptr [rdx - 508] # xmm6 = mem[0],zero,zero,zero + movss xmm7, dword ptr [rdx - 504] # xmm7 = mem[0],zero,zero,zero + movss xmm5, dword ptr [rdx - 500] # xmm5 = mem[0],zero,zero,zero + movss xmm4, dword ptr [rdx - 496] # xmm4 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 380], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 252], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 124], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpleps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + insertps xmm7, dword ptr [rdx - 376], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 248], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 120], 48 # xmm7 = xmm7[0,1,2],mem[0] + insertps xmm5, dword ptr [rdx - 372], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 244], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 116], 48 # xmm5 = xmm5[0,1,2],mem[0] + insertps xmm4, dword ptr [rdx - 368], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] + insertps xmm4, dword ptr [rdx - 240], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] + insertps xmm4, dword ptr [rdx - 112], 48 # xmm4 = xmm4[0,1,2],mem[0] + cmpleps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + movdqa xmm2, xmm7 + pand xmm2, xmm15 + psubb xmm2, xmm7 + movss xmm7, dword ptr [rdx - 492] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 364], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 236], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 108], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm2, xmm6 + movss xmm6, dword ptr [rdx - 488] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 360], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 232], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 104], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpleps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 2 + pand xmm5, xmm8 + por xmm5, xmm2 + movss xmm3, dword ptr [rdx - 484] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 356], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 228], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rdx - 100], 48 # xmm3 = xmm3[0,1,2],mem[0] + cmpleps xmm4, xmm1 + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + pand xmm4, xmm15 + psllw xmm4, 3 + pand xmm4, xmm10 + cmpleps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 4 + pand xmm7, xmm11 + por xmm7, xmm4 + movss xmm4, dword ptr [rdx - 480] # xmm4 = mem[0],zero,zero,zero + insertps xmm4, dword ptr [rdx - 352], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] + insertps xmm4, dword ptr [rdx - 224], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] + insertps xmm4, dword ptr [rdx - 96], 48 # xmm4 = xmm4[0,1,2],mem[0] + por xmm7, xmm5 + movss xmm5, dword ptr [rdx - 476] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 348], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 220], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 92], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpleps xmm5, xmm1 + packssdw xmm5, xmm5 + cmpleps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + cmpleps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 6 + pand xmm3, xmm13 + por xmm3, xmm6 + movss xmm2, dword ptr [rdx - 472] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 344], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 216], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 88], 48 # xmm2 = xmm2[0,1,2],mem[0] + packsswb xmm5, xmm5 + cmpleps xmm4, xmm1 + packssdw xmm4, xmm4 + packsswb xmm4, xmm4 + psllw xmm4, 7 + pand xmm4, xmm14 + por xmm4, xmm3 + movss xmm3, dword ptr [rdx - 468] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 340], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 212], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + pand xmm5, xmm15 + insertps xmm3, dword ptr [rdx - 84], 48 # xmm3 = xmm3[0,1,2],mem[0] + por xmm4, xmm7 + cmpleps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm6, xmm2 + pand xmm6, xmm15 + psubb xmm6, xmm2 + movss xmm7, dword ptr [rdx - 464] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 336], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 208], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 80], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm6, xmm5 + movss xmm5, dword ptr [rdx - 460] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 332], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 204], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 76], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpleps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm6 + movss xmm6, dword ptr [rdx - 456] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 328], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 200], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 72], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpleps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 3 + pand xmm7, xmm10 + cmpleps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 4 + pand xmm5, xmm11 + por xmm5, xmm7 + movss xmm2, dword ptr [rdx - 452] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 324], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 196], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 68], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm5, xmm3 + movss xmm7, dword ptr [rdx - 448] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 320], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 192], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 64], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpleps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 5 + pand xmm6, xmm12 + cmpleps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm6 + movss xmm6, dword ptr [rdx - 444] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 316], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 188], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 60], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpleps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + cmpleps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + psllw xmm7, 7 + pand xmm7, xmm14 + por xmm7, xmm2 + movss xmm2, dword ptr [rdx - 440] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 312], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm7, xmm5 + movss xmm3, dword ptr [rdx - 436] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 308], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 180], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + pand xmm6, xmm15 + insertps xmm3, dword ptr [rdx - 52], 48 # xmm3 = xmm3[0,1,2],mem[0] + punpckldq xmm4, xmm7 # xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1] + cmpleps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm7, xmm2 + pand xmm7, xmm15 + psubb xmm7, xmm2 + movss xmm5, dword ptr [rdx - 432] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 304], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 176], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 48], 48 # xmm5 = xmm5[0,1,2],mem[0] + por xmm7, xmm6 + movss xmm6, dword ptr [rdx - 428] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 300], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 172], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 44], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpleps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm7 + movss xmm7, dword ptr [rdx - 424] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 296], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 168], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 40], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpleps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + pand xmm5, xmm15 + psllw xmm5, 3 + pand xmm5, xmm10 + cmpleps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 4 + pand xmm6, xmm11 + por xmm6, xmm5 + movss xmm2, dword ptr [rdx - 420] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 292], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm6, xmm3 + movss xmm5, dword ptr [rdx - 416] # xmm5 = mem[0],zero,zero,zero + insertps xmm5, dword ptr [rdx - 288], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] + insertps xmm5, dword ptr [rdx - 160], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] + insertps xmm5, dword ptr [rdx - 32], 48 # xmm5 = xmm5[0,1,2],mem[0] + cmpleps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 5 + pand xmm7, xmm12 + cmpleps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm7 + movss xmm7, dword ptr [rdx - 412] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 284], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 156], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 28], 48 # xmm7 = xmm7[0,1,2],mem[0] + cmpleps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + cmpleps xmm5, xmm1 + packssdw xmm5, xmm5 + packsswb xmm5, xmm5 + psllw xmm5, 7 + pand xmm5, xmm14 + por xmm5, xmm2 + movss xmm2, dword ptr [rdx - 408] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 280], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 152], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + pand xmm7, xmm15 + insertps xmm2, dword ptr [rdx - 24], 48 # xmm2 = xmm2[0,1,2],mem[0] + por xmm5, xmm6 + cmpleps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + movdqa xmm6, xmm2 + pand xmm6, xmm15 + psubb xmm6, xmm2 + movss xmm3, dword ptr [rdx - 404] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 276], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 148], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rdx - 20], 48 # xmm3 = xmm3[0,1,2],mem[0] + por xmm6, xmm7 + movss xmm2, dword ptr [rdx - 400] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 272], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 144], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 16], 48 # xmm2 = xmm2[0,1,2],mem[0] + cmpleps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + pand xmm3, xmm15 + psllw xmm3, 2 + pand xmm3, xmm8 + por xmm3, xmm6 + movss xmm6, dword ptr [rdx - 396] # xmm6 = mem[0],zero,zero,zero + insertps xmm6, dword ptr [rdx - 268], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] + insertps xmm6, dword ptr [rdx - 140], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] + insertps xmm6, dword ptr [rdx - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] + cmpleps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 3 + pand xmm2, xmm10 + cmpleps xmm6, xmm1 + packssdw xmm6, xmm6 + packsswb xmm6, xmm6 + pand xmm6, xmm15 + psllw xmm6, 4 + pand xmm6, xmm11 + por xmm6, xmm2 + movss xmm7, dword ptr [rdx - 392] # xmm7 = mem[0],zero,zero,zero + insertps xmm7, dword ptr [rdx - 264], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] + insertps xmm7, dword ptr [rdx - 136], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] + insertps xmm7, dword ptr [rdx - 8], 48 # xmm7 = xmm7[0,1,2],mem[0] + por xmm6, xmm3 + movss xmm2, dword ptr [rdx - 388] # xmm2 = mem[0],zero,zero,zero + insertps xmm2, dword ptr [rdx - 260], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] + insertps xmm2, dword ptr [rdx - 132], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] + insertps xmm2, dword ptr [rdx - 4], 48 # xmm2 = xmm2[0,1,2],mem[0] + cmpleps xmm7, xmm1 + packssdw xmm7, xmm7 + packsswb xmm7, xmm7 + pand xmm7, xmm15 + psllw xmm7, 5 + pand xmm7, xmm12 + cmpleps xmm2, xmm1 + packssdw xmm2, xmm2 + packsswb xmm2, xmm2 + pand xmm2, xmm15 + psllw xmm2, 6 + pand xmm2, xmm13 + por xmm2, xmm7 + movss xmm3, dword ptr [rdx - 384] # xmm3 = mem[0],zero,zero,zero + insertps xmm3, dword ptr [rdx - 256], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] + insertps xmm3, dword ptr [rdx - 128], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] + insertps xmm3, dword ptr [rdx], 48 # xmm3 = xmm3[0,1,2],mem[0] + cmpleps xmm3, xmm1 + packssdw xmm3, xmm3 + packsswb xmm3, xmm3 + psllw xmm3, 7 + pand xmm3, xmm14 + por xmm3, xmm2 + por xmm3, xmm6 + punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] + punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] + pshufb xmm4, xmm9 + movdqu xmmword ptr [r12 + 4*rsi], xmm4 + add rsi, 4 + add rdx, 512 cmp r9, rsi - jne .LBB11_136 -.LBB11_133: - test r8b, 1 - je .LBB11_201 -# %bb.134: - cmp r14w, word ptr [rax] - setge al - neg al - mov rdx, rsi - shr rdx, 3 - mov dil, byte ptr [r12 + rdx] - and sil, 7 - mov bl, 1 - mov ecx, esi - shl bl, cl - xor al, dil - and bl, al - xor bl, dil - mov byte ptr [r12 + rdx], bl - jmp .LBB11_201 -.LBB11_193: - mov r10, r8 - and r10, -2 - xor r11d, r11d - .p2align 4, 0x90 -.LBB11_194: # =>This Inner Loop Header: Depth=1 - ucomiss xmm0, dword ptr [rbx] - mov edx, 0 - adc dl, -1 - mov rdi, r11 - shr rdi, 3 - movzx r9d, byte ptr [r14 + rdi] - mov ecx, r11d - and cl, 6 - mov al, 1 - shl al, cl - xor dl, r9b - and al, dl - xor al, r9b - mov byte ptr [r14 + rdi], al - add r11, 2 - ucomiss xmm0, dword ptr [rbx + 4] - lea rbx, [rbx + 8] - mov esi, 0 - adc sil, -1 - xor sil, al - or cl, 1 - mov dl, 1 - shl dl, cl - and dl, sil - xor dl, al - mov byte ptr [r14 + rdi], dl - cmp r10, r11 - jne .LBB11_194 -.LBB11_191: - test r8b, 1 - je .LBB11_201 -# %bb.192: - xor eax, eax - ucomiss xmm0, dword ptr [rbx] - adc al, -1 - mov rdx, r11 - shr rdx, 3 - mov sil, byte ptr [r14 + rdx] - and r11b, 7 - mov bl, 1 - mov ecx, r11d - shl bl, cl - xor al, sil - and bl, al - xor bl, sil - mov byte ptr [r14 + rdx], bl - jmp .LBB11_201 -.LBB11_85: - and r10, -16 - mov rax, r10 + jne .LBB11_220 +# %bb.221: + cmp rcx, r9 + jne .LBB11_108 + jmp .LBB11_135 +.LBB11_222: + and rcx, -16 + mov rax, rcx shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 280], rax # 8-byte Spill - mov qword ptr [rsp + 256], r10 # 8-byte Spill - lea rax, [r15 + 4*r10] - mov qword ptr [rsp + 288], rax # 8-byte Spill + add rax, r13 + mov qword ptr [rsp + 256], rax # 8-byte Spill + mov qword ptr [rsp + 184], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 264], rax # 8-byte Spill movzx eax, r14b movd xmm1, eax pxor xmm0, xmm0 pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 144], xmm1 # 16-byte Spill + movdqa xmmword ptr [rsp + 160], xmm1 # 16-byte Spill xor eax, eax - mov qword ptr [rsp + 120], r15 # 8-byte Spill + mov qword ptr [rsp + 136], r12 # 8-byte Spill .p2align 4, 0x90 -.LBB11_86: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 224], rax # 8-byte Spill +.LBB11_223: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 144], rax # 8-byte Spill shl rax, 5 - mov rdi, rax - mov rsi, rax - mov r9, rax - mov r10, rax - mov r12, rax + mov r8, rax mov r14, rax mov r15, rax - mov r13, rax - mov qword ptr [rsp + 56], rax # 8-byte Spill + mov r10, rax mov r11, rax - mov r8, rax - movzx ecx, byte ptr [rdx + rax] + mov r12, rax + mov r9, rax + mov rbx, rax + mov qword ptr [rsp + 80], rax # 8-byte Spill + mov rsi, rax + mov qword ptr [rsp + 96], rax # 8-byte Spill + movzx ecx, byte ptr [r13 + rax] movd xmm4, ecx - movzx ecx, byte ptr [rdx + rax + 1] + movzx ecx, byte ptr [r13 + rax + 1] movd xmm3, ecx - movzx ecx, byte ptr [rdx + rax + 2] + movzx ecx, byte ptr [r13 + rax + 2] movd xmm5, ecx - movzx ecx, byte ptr [rdx + rax + 3] + movzx ecx, byte ptr [r13 + rax + 3] movd xmm7, ecx - movzx ecx, byte ptr [rdx + rax + 4] + movzx ecx, byte ptr [r13 + rax + 4] movd xmm9, ecx - movzx ecx, byte ptr [rdx + rax + 5] + movzx ecx, byte ptr [r13 + rax + 5] movd xmm2, ecx - movzx ecx, byte ptr [rdx + rax + 6] + movzx ecx, byte ptr [r13 + rax + 6] movd xmm8, ecx - movzx ecx, byte ptr [rdx + rax + 7] + movzx ecx, byte ptr [r13 + rax + 7] movd xmm14, ecx - movzx ecx, byte ptr [rdx + rax + 8] + movzx ecx, byte ptr [r13 + rax + 8] movd xmm0, ecx - movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rax + 9] + movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r13 + rax + 9] movd xmm11, ecx - movzx ecx, byte ptr [rdx + rax + 10] + movzx ecx, byte ptr [r13 + rax + 10] movd xmm12, ecx - movzx ecx, byte ptr [rdx + rax + 11] + movzx ecx, byte ptr [r13 + rax + 11] movd xmm13, ecx - movzx ecx, byte ptr [rdx + rax + 12] + movzx ecx, byte ptr [r13 + rax + 12] movd xmm0, ecx - movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rax + 13] + movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r13 + rax + 13] movd xmm6, ecx - movzx ecx, byte ptr [rdx + rax + 14] + movzx ecx, byte ptr [r13 + rax + 14] movd xmm15, ecx - movzx ecx, byte ptr [rdx + rax + 15] + movzx ecx, byte ptr [r13 + rax + 15] movd xmm0, ecx - movdqa xmmword ptr [rsp + 160], xmm0 # 16-byte Spill - mov qword ptr [rsp + 72], rax # 8-byte Spill - mov rbx, rax - or rbx, 32 - mov qword ptr [rsp + 8], rbx # 8-byte Spill - or rdi, 64 - mov qword ptr [rsp + 32], rdi # 8-byte Spill - or rsi, 96 - mov qword ptr [rsp + 24], rsi # 8-byte Spill - or r9, 128 + movdqa xmmword ptr [rsp + 192], xmm0 # 16-byte Spill + mov qword ptr [rsp + 104], rax # 8-byte Spill + mov rdi, rax + or rdi, 32 + or r8, 64 + or r14, 96 + or r15, 128 or r10, 160 - or r12, 192 - mov qword ptr [rsp + 64], r12 # 8-byte Spill - or r14, 224 - or r15, 256 - mov qword ptr [rsp + 88], r15 # 8-byte Spill - or r13, 288 - mov qword ptr [rsp + 80], r13 # 8-byte Spill - mov r12, qword ptr [rsp + 56] # 8-byte Reload - or r12, 320 - or r11, 352 - or r8, 384 - mov qword ptr [rsp + 96], r8 # 8-byte Spill + or r11, 192 + or r12, 224 + or r9, 256 + mov rdx, rax + or rdx, 288 + mov qword ptr [rsp + 72], rdx # 8-byte Spill + mov rbx, qword ptr [rsp + 80] # 8-byte Reload + or rbx, 320 + or rsi, 352 + mov qword ptr [rsp + 64], rsi # 8-byte Spill + mov rsi, qword ptr [rsp + 96] # 8-byte Reload + or rsi, 384 + mov qword ptr [rsp + 96], rsi # 8-byte Spill mov rcx, rax or rcx, 416 - mov qword ptr [rsp + 48], rcx # 8-byte Spill + mov qword ptr [rsp + 32], rcx # 8-byte Spill mov rcx, rax or rcx, 448 - mov qword ptr [rsp + 40], rcx # 8-byte Spill - mov rsi, rax - or rsi, 480 - mov qword ptr [rsp + 16], rsi # 8-byte Spill - pinsrb xmm4, byte ptr [rdx + rbx], 1 - pinsrb xmm4, byte ptr [rdx + rdi], 2 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rbx], 3 - pinsrb xmm4, byte ptr [rdx + r9], 4 - pinsrb xmm4, byte ptr [rdx + r10], 5 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax], 6 - pinsrb xmm4, byte ptr [rdx + r14], 7 - pinsrb xmm4, byte ptr [rdx + r15], 8 - pinsrb xmm4, byte ptr [rdx + r13], 9 - mov r15, r12 - mov qword ptr [rsp + 56], r12 # 8-byte Spill - pinsrb xmm4, byte ptr [rdx + r12], 10 - pinsrb xmm4, byte ptr [rdx + r11], 11 - pinsrb xmm4, byte ptr [rdx + r8], 12 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + rax], 13 - pinsrb xmm4, byte ptr [rdx + rcx], 14 - pinsrb xmm4, byte ptr [rdx + rsi], 15 - mov r12, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r12 + 1], 1 - pinsrb xmm3, byte ptr [rdx + rdi + 1], 2 - pinsrb xmm3, byte ptr [rdx + rbx + 1], 3 - pinsrb xmm3, byte ptr [rdx + r9 + 1], 4 - pinsrb xmm3, byte ptr [rdx + r10 + 1], 5 + mov qword ptr [rsp + 16], rcx # 8-byte Spill + or rax, 480 + mov qword ptr [rsp + 40], rax # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + rdi], 1 + mov qword ptr [rsp + 24], r8 # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r8], 2 + mov qword ptr [rsp + 48], r14 # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r14], 3 + pinsrb xmm4, byte ptr [r13 + r15], 4 + mov qword ptr [rsp + 112], r10 # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r10], 5 + pinsrb xmm4, byte ptr [r13 + r11], 6 + pinsrb xmm4, byte ptr [r13 + r12], 7 + mov qword ptr [rsp + 88], r9 # 8-byte Spill + pinsrb xmm4, byte ptr [r13 + r9], 8 + pinsrb xmm4, byte ptr [r13 + rdx], 9 + mov r8, rbx + pinsrb xmm4, byte ptr [r13 + rbx], 10 mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rbx + 1], 6 - pinsrb xmm3, byte ptr [rdx + r14 + 1], 7 - mov rdi, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rdi + 1], 8 - pinsrb xmm3, byte ptr [rdx + r13 + 1], 9 - pinsrb xmm3, byte ptr [rdx + r15 + 1], 10 - pinsrb xmm3, byte ptr [rdx + r11 + 1], 11 - mov r15, r11 - pinsrb xmm3, byte ptr [rdx + r8 + 1], 12 - mov r13, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r13 + 1], 13 - pinsrb xmm3, byte ptr [rdx + rcx + 1], 14 - movdqa xmm1, xmmword ptr [rsp + 144] # 16-byte Reload + pinsrb xmm4, byte ptr [r13 + rbx], 11 + pinsrb xmm4, byte ptr [r13 + rsi], 12 + mov rax, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rax], 13 + pinsrb xmm4, byte ptr [r13 + rcx], 14 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rax], 15 + pinsrb xmm3, byte ptr [r13 + rdi + 1], 1 + mov qword ptr [rsp + 56], rdi # 8-byte Spill + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + rax + 1], 2 + pinsrb xmm3, byte ptr [r13 + r14 + 1], 3 + pinsrb xmm3, byte ptr [r13 + r15 + 1], 4 + mov r14, r15 + pinsrb xmm3, byte ptr [r13 + r10 + 1], 5 + pinsrb xmm3, byte ptr [r13 + r11 + 1], 6 + mov r10, r11 + pinsrb xmm3, byte ptr [r13 + r12 + 1], 7 + mov r15, r12 + pinsrb xmm3, byte ptr [r13 + r9 + 1], 8 + pinsrb xmm3, byte ptr [r13 + rdx + 1], 9 + pinsrb xmm3, byte ptr [r13 + r8 + 1], 10 + pinsrb xmm3, byte ptr [r13 + rbx + 1], 11 + mov rdx, rbx + pinsrb xmm3, byte ptr [r13 + rsi + 1], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + rsi + 1], 13 + pinsrb xmm3, byte ptr [r13 + rcx + 1], 14 + movdqa xmm1, xmmword ptr [rsp + 160] # 16-byte Reload pcmpgtb xmm4, xmm1 - pinsrb xmm3, byte ptr [rdx + rsi + 1], 15 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm3, byte ptr [r13 + rax + 1], 15 pcmpgtb xmm3, xmm1 movdqa xmm0, xmmword ptr [rip + .LCPI11_16] # xmm0 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] pandn xmm3, xmm0 paddb xmm3, xmm4 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 16] + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + movzx esi, byte ptr [r13 + rcx + 16] movd xmm10, esi - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 2], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 2], 2 - mov r11, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r11 + 2], 3 - pinsrb xmm5, byte ptr [rdx + r9 + 2], 4 - pinsrb xmm5, byte ptr [rdx + r10 + 2], 5 - pinsrb xmm5, byte ptr [rdx + rbx + 2], 6 - mov qword ptr [rsp + 104], r14 # 8-byte Spill - pinsrb xmm5, byte ptr [rdx + r14 + 2], 7 - mov r12, rdi - pinsrb xmm5, byte ptr [rdx + rdi + 2], 8 - mov r8, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r8 + 2], 9 - mov rdi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rdi + 2], 10 - mov qword ptr [rsp + 176], r15 # 8-byte Spill - pinsrb xmm5, byte ptr [rdx + r15 + 2], 11 + pinsrb xmm5, byte ptr [r13 + rdi + 2], 1 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r12 + 2], 2 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r11 + 2], 3 + mov qword ptr [rsp + 120], r14 # 8-byte Spill + pinsrb xmm5, byte ptr [r13 + r14 + 2], 4 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rbx + 2], 5 + mov r9, r10 + pinsrb xmm5, byte ptr [r13 + r10 + 2], 6 + mov r10, r15 + pinsrb xmm5, byte ptr [r13 + r15 + 2], 7 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + r15 + 2], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rax + 2], 9 + mov qword ptr [rsp + 80], r8 # 8-byte Spill + pinsrb xmm5, byte ptr [r13 + r8 + 2], 10 + pinsrb xmm5, byte ptr [r13 + rdx + 2], 11 mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rcx + 2], 12 - mov rsi, r13 - pinsrb xmm5, byte ptr [rdx + r13 + 2], 13 - mov r13, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r13 + 2], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 2], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 3], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 3], 2 - pinsrb xmm7, byte ptr [rdx + r11 + 3], 3 - pinsrb xmm7, byte ptr [rdx + r9 + 3], 4 - pinsrb xmm7, byte ptr [rdx + r10 + 3], 5 - pinsrb xmm7, byte ptr [rdx + rbx + 3], 6 - pinsrb xmm7, byte ptr [rdx + r14 + 3], 7 - pinsrb xmm7, byte ptr [rdx + r12 + 3], 8 - pinsrb xmm7, byte ptr [rdx + r8 + 3], 9 - pinsrb xmm7, byte ptr [rdx + rdi + 3], 10 - pinsrb xmm7, byte ptr [rdx + r15 + 3], 11 - pinsrb xmm7, byte ptr [rdx + rcx + 3], 12 - pinsrb xmm7, byte ptr [rdx + rsi + 3], 13 - pinsrb xmm7, byte ptr [rdx + r13 + 3], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 3], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 4], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 4], 2 - pinsrb xmm9, byte ptr [rdx + r11 + 4], 3 - pinsrb xmm9, byte ptr [rdx + r9 + 4], 4 - mov qword ptr [rsp + 128], r9 # 8-byte Spill - pinsrb xmm9, byte ptr [rdx + r10 + 4], 5 - pinsrb xmm9, byte ptr [rdx + rbx + 4], 6 - pinsrb xmm9, byte ptr [rdx + r14 + 4], 7 - pinsrb xmm9, byte ptr [rdx + r12 + 4], 8 - pinsrb xmm9, byte ptr [rdx + r8 + 4], 9 - pinsrb xmm9, byte ptr [rdx + rdi + 4], 10 - pinsrb xmm9, byte ptr [rdx + r15 + 4], 11 - pinsrb xmm9, byte ptr [rdx + rcx + 4], 12 - pinsrb xmm9, byte ptr [rdx + rsi + 4], 13 - pinsrb xmm9, byte ptr [rdx + r13 + 4], 14 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 4], 15 - mov r13, rax + pinsrb xmm5, byte ptr [r13 + rcx + 2], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rsi + 2], 13 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rdx + 2], 14 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm5, byte ptr [r13 + rdi + 2], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 1 + pinsrb xmm7, byte ptr [r13 + r12 + 3], 2 + pinsrb xmm7, byte ptr [r13 + r11 + 3], 3 + pinsrb xmm7, byte ptr [r13 + r14 + 3], 4 + pinsrb xmm7, byte ptr [r13 + rbx + 3], 5 + pinsrb xmm7, byte ptr [r13 + r9 + 3], 6 + pinsrb xmm7, byte ptr [r13 + r10 + 3], 7 + pinsrb xmm7, byte ptr [r13 + r15 + 3], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 9 + pinsrb xmm7, byte ptr [r13 + r8 + 3], 10 + mov rax, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 3], 11 + pinsrb xmm7, byte ptr [r13 + rcx + 3], 12 + pinsrb xmm7, byte ptr [r13 + rsi + 3], 13 + pinsrb xmm7, byte ptr [r13 + rdx + 3], 14 + pinsrb xmm7, byte ptr [r13 + rdi + 3], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rax + 4], 1 + pinsrb xmm9, byte ptr [r13 + r12 + 4], 2 + pinsrb xmm9, byte ptr [r13 + r11 + 4], 3 + pinsrb xmm9, byte ptr [r13 + r14 + 4], 4 + pinsrb xmm9, byte ptr [r13 + rbx + 4], 5 + pinsrb xmm9, byte ptr [r13 + r9 + 4], 6 + pinsrb xmm9, byte ptr [r13 + r10 + 4], 7 + pinsrb xmm9, byte ptr [r13 + r15 + 4], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rax + 4], 9 + pinsrb xmm9, byte ptr [r13 + r8 + 4], 10 + mov r8, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r8 + 4], 11 + pinsrb xmm9, byte ptr [r13 + rcx + 4], 12 + pinsrb xmm9, byte ptr [r13 + rsi + 4], 13 + pinsrb xmm9, byte ptr [r13 + rdx + 4], 14 + pinsrb xmm9, byte ptr [r13 + rdi + 4], 15 pcmpgtb xmm5, xmm1 movdqa xmm0, xmmword ptr [rip + .LCPI11_17] # xmm0 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] pandn xmm5, xmm0 @@ -58746,89 +61444,89 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr movdqa xmm0, xmmword ptr [rip + .LCPI11_18] # xmm0 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] pandn xmm7, xmm0 por xmm7, xmm5 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 17] + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + movzx esi, byte ptr [r13 + rdx + 17] movd xmm4, esi pcmpgtb xmm9, xmm1 movdqa xmm0, xmmword ptr [rip + .LCPI11_19] # xmm0 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] pandn xmm9, xmm0 por xmm9, xmm7 - movzx esi, byte ptr [rdx + rax + 18] + movzx esi, byte ptr [r13 + rdx + 18] movd xmm7, esi pcmpeqd xmm0, xmm0 psubb xmm3, xmm0 por xmm9, xmm3 - movzx esi, byte ptr [rdx + rax + 19] + movzx esi, byte ptr [r13 + rdx + 19] movd xmm5, esi - mov r8, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r8 + 5], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rdi + 5], 2 - pinsrb xmm2, byte ptr [rdx + r11 + 5], 3 - pinsrb xmm2, byte ptr [rdx + r9 + 5], 4 - pinsrb xmm2, byte ptr [rdx + r10 + 5], 5 - mov r12, r10 - mov r14, rbx - pinsrb xmm2, byte ptr [rdx + rbx + 5], 6 - mov rbx, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rbx + 5], 7 - mov r15, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r15 + 5], 8 - mov r9, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r9 + 5], 9 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rsi + 5], 10 - mov r11, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r11 + 5], 11 - pinsrb xmm2, byte ptr [rdx + rcx + 5], 12 - mov r10, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r10 + 5], 13 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 5], 14 - pinsrb xmm2, byte ptr [rdx + r13 + 5], 15 - pinsrb xmm8, byte ptr [rdx + r8 + 6], 1 - pinsrb xmm8, byte ptr [rdx + rdi + 6], 2 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r13 + 6], 3 - mov r13, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + r13 + 6], 4 - pinsrb xmm8, byte ptr [rdx + r12 + 6], 5 - pinsrb xmm8, byte ptr [rdx + r14 + 6], 6 - pinsrb xmm8, byte ptr [rdx + rbx + 6], 7 - pinsrb xmm8, byte ptr [rdx + r15 + 6], 8 - pinsrb xmm8, byte ptr [rdx + r9 + 6], 9 - pinsrb xmm8, byte ptr [rdx + rsi + 6], 10 - pinsrb xmm8, byte ptr [rdx + r11 + 6], 11 - mov r15, r11 - pinsrb xmm8, byte ptr [rdx + rcx + 6], 12 - pinsrb xmm8, byte ptr [rdx + r10 + 6], 13 - pinsrb xmm8, byte ptr [rdx + rax + 6], 14 - mov r10, rax - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm8, byte ptr [rdx + rax + 6], 15 - pinsrb xmm14, byte ptr [rdx + r8 + 7], 1 - pinsrb xmm14, byte ptr [rdx + rdi + 7], 2 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rax + 7], 3 - mov r9, r13 - pinsrb xmm14, byte ptr [rdx + r13 + 7], 4 - mov rdi, r12 - pinsrb xmm14, byte ptr [rdx + r12 + 7], 5 - pinsrb xmm14, byte ptr [rdx + r14 + 7], 6 - pinsrb xmm14, byte ptr [rdx + rbx + 7], 7 - mov r11, rbx - mov r12, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + r12 + 7], 8 - mov r13, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + r13 + 7], 9 - pinsrb xmm14, byte ptr [rdx + rsi + 7], 10 - pinsrb xmm14, byte ptr [rdx + r15 + 7], 11 - pinsrb xmm14, byte ptr [rdx + rcx + 7], 12 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rdx + 5], 1 + pinsrb xmm2, byte ptr [r13 + r12 + 5], 2 + pinsrb xmm2, byte ptr [r13 + r11 + 5], 3 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r14 + 5], 4 + pinsrb xmm2, byte ptr [r13 + rbx + 5], 5 + pinsrb xmm2, byte ptr [r13 + r9 + 5], 6 + mov r15, r9 + mov r11, r10 + mov qword ptr [rsp + 208], r10 # 8-byte Spill + pinsrb xmm2, byte ptr [r13 + r10 + 5], 7 + mov r10, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r10 + 5], 8 + pinsrb xmm2, byte ptr [r13 + rax + 5], 9 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rsi + 5], 10 + mov rdi, r8 + pinsrb xmm2, byte ptr [r13 + r8 + 5], 11 + pinsrb xmm2, byte ptr [r13 + rcx + 5], 12 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r8 + 5], 13 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + rbx + 5], 14 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r13 + r9 + 5], 15 + pinsrb xmm8, byte ptr [r13 + rdx + 6], 1 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + r12 + 6], 2 mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rbx + 7], 13 - pinsrb xmm14, byte ptr [rdx + r10 + 7], 14 + pinsrb xmm8, byte ptr [r13 + rbx + 6], 3 + pinsrb xmm8, byte ptr [r13 + r14 + 6], 4 + mov r12, r14 + mov rbx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + rbx + 6], 5 + pinsrb xmm8, byte ptr [r13 + r15 + 6], 6 + mov r14, r15 + pinsrb xmm8, byte ptr [r13 + r11 + 6], 7 + pinsrb xmm8, byte ptr [r13 + r10 + 6], 8 + pinsrb xmm8, byte ptr [r13 + rax + 6], 9 + pinsrb xmm8, byte ptr [r13 + rsi + 6], 10 + pinsrb xmm8, byte ptr [r13 + rdi + 6], 11 + pinsrb xmm8, byte ptr [r13 + rcx + 6], 12 + pinsrb xmm8, byte ptr [r13 + r8 + 6], 13 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm8, byte ptr [r13 + rbx + 6], 14 + pinsrb xmm8, byte ptr [r13 + r9 + 6], 15 + pinsrb xmm14, byte ptr [r13 + rdx + 7], 1 + mov r11, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + r11 + 7], 2 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + rdx + 7], 3 + mov rdx, r12 + pinsrb xmm14, byte ptr [r13 + r12 + 7], 4 + mov r15, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + r15 + 7], 5 + pinsrb xmm14, byte ptr [r13 + r14 + 7], 6 + mov r10, qword ptr [rsp + 208] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + r10 + 7], 7 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm14, byte ptr [r13 + rdx + 7], 8 + pinsrb xmm14, byte ptr [r13 + rax + 7], 9 + pinsrb xmm14, byte ptr [r13 + rsi + 7], 10 + pinsrb xmm14, byte ptr [r13 + rdi + 7], 11 + pinsrb xmm14, byte ptr [r13 + rcx + 7], 12 + pinsrb xmm14, byte ptr [r13 + r8 + 7], 13 + pinsrb xmm14, byte ptr [r13 + rbx + 7], 14 movdqa xmm1, xmm14 - movdqa xmm14, xmmword ptr [rsp + 144] # 16-byte Reload + movdqa xmm14, xmmword ptr [rsp + 160] # 16-byte Reload pcmpgtb xmm2, xmm14 movdqa xmm0, xmmword ptr [rip + .LCPI11_20] # xmm0 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] pandn xmm2, xmm0 @@ -58836,377 +61534,378 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr movdqa xmm0, xmmword ptr [rip + .LCPI11_21] # xmm0 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] pandn xmm8, xmm0 por xmm8, xmm2 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 20] + mov rdx, qword ptr [rsp + 104] # 8-byte Reload + movzx esi, byte ptr [r13 + rdx + 20] movd xmm3, esi - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rcx + 7], 15 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm1, byte ptr [r13 + rax + 7], 15 pcmpgtb xmm1, xmm14 movdqa xmm0, xmmword ptr [rip + .LCPI11_6] # xmm0 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] pandn xmm1, xmm0 por xmm1, xmm8 - movzx esi, byte ptr [rdx + rax + 21] + movzx esi, byte ptr [r13 + rdx + 21] movd xmm2, esi - movdqa xmm0, xmmword ptr [rsp + 192] # 16-byte Reload - pinsrb xmm0, byte ptr [rdx + r8 + 8], 1 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r14 + 8], 2 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 8], 3 - pinsrb xmm0, byte ptr [rdx + r9 + 8], 4 - pinsrb xmm0, byte ptr [rdx + rdi + 8], 5 - mov r10, rdi - mov rdi, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rdi + 8], 6 - pinsrb xmm0, byte ptr [rdx + r11 + 8], 7 - pinsrb xmm0, byte ptr [rdx + r12 + 8], 8 - pinsrb xmm0, byte ptr [rdx + r13 + 8], 9 - mov r8, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r8 + 8], 10 - pinsrb xmm0, byte ptr [rdx + r15 + 8], 11 + movdqa xmm0, xmmword ptr [rsp + 224] # 16-byte Reload + mov rbx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rbx + 8], 1 + pinsrb xmm0, byte ptr [r13 + r11 + 8], 2 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rcx + 8], 3 + pinsrb xmm0, byte ptr [r13 + r12 + 8], 4 + pinsrb xmm0, byte ptr [r13 + r15 + 8], 5 + pinsrb xmm0, byte ptr [r13 + r14 + 8], 6 + mov r9, r14 + pinsrb xmm0, byte ptr [r13 + r10 + 8], 7 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rsi + 8], 8 + mov rdi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rdi + 8], 9 + mov r12, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r12 + 8], 10 + mov rsi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + rsi + 8], 11 mov rsi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 8], 12 - pinsrb xmm0, byte ptr [rdx + rbx + 8], 13 - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 8], 14 - pinsrb xmm0, byte ptr [rdx + rcx + 8], 15 + pinsrb xmm0, byte ptr [r13 + rsi + 8], 12 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r8 + 8], 13 + mov r14, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r13 + r14 + 8], 14 + pinsrb xmm0, byte ptr [r13 + rax + 8], 15 por xmm1, xmm9 - movdqa xmmword ptr [rsp + 192], xmm1 # 16-byte Spill - movzx esi, byte ptr [rdx + rax + 22] + movdqa xmmword ptr [rsp + 224], xmm1 # 16-byte Spill + movzx esi, byte ptr [r13 + rdx + 22] movd xmm1, esi pcmpgtb xmm0, xmm14 - mov r11, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r11 + 9], 1 - mov rbx, r11 - mov rax, r14 - pinsrb xmm11, byte ptr [rdx + r14 + 9], 2 - mov r11, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r11 + 9], 3 - pinsrb xmm11, byte ptr [rdx + r9 + 9], 4 - mov qword ptr [rsp + 112], r10 # 8-byte Spill - pinsrb xmm11, byte ptr [rdx + r10 + 9], 5 - pinsrb xmm11, byte ptr [rdx + rdi + 9], 6 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r14 + 9], 7 - pinsrb xmm11, byte ptr [rdx + r12 + 9], 8 - pinsrb xmm11, byte ptr [rdx + r13 + 9], 9 - mov rsi, r8 - pinsrb xmm11, byte ptr [rdx + r8 + 9], 10 - mov rcx, r15 - pinsrb xmm11, byte ptr [rdx + r15 + 9], 11 - mov r8, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r8 + 9], 12 - mov r15, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r15 + 9], 13 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rdi + 9], 14 - mov rdi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rdi + 9], 15 - pinsrb xmm12, byte ptr [rdx + rbx + 10], 1 - pinsrb xmm12, byte ptr [rdx + rax + 10], 2 - pinsrb xmm12, byte ptr [rdx + r11 + 10], 3 - pinsrb xmm12, byte ptr [rdx + r9 + 10], 4 - pinsrb xmm12, byte ptr [rdx + r10 + 10], 5 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rbx + 10], 6 - pinsrb xmm12, byte ptr [rdx + r14 + 10], 7 - pinsrb xmm12, byte ptr [rdx + r12 + 10], 8 - pinsrb xmm12, byte ptr [rdx + r13 + 10], 9 - pinsrb xmm12, byte ptr [rdx + rsi + 10], 10 - pinsrb xmm12, byte ptr [rdx + rcx + 10], 11 - pinsrb xmm12, byte ptr [rdx + r8 + 10], 12 - pinsrb xmm12, byte ptr [rdx + r15 + 10], 13 - mov r11, r15 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + r15 + 10], 14 - pinsrb xmm12, byte ptr [rdx + rdi + 10], 15 - mov rbx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rbx + 11], 1 - pinsrb xmm13, byte ptr [rdx + rax + 11], 2 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rax + 11], 3 - pinsrb xmm13, byte ptr [rdx + r9 + 11], 4 - pinsrb xmm13, byte ptr [rdx + r10 + 11], 5 - mov r10, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + r10 + 11], 6 - pinsrb xmm13, byte ptr [rdx + r14 + 11], 7 - pinsrb xmm13, byte ptr [rdx + r12 + 11], 8 - pinsrb xmm13, byte ptr [rdx + r13 + 11], 9 - pinsrb xmm13, byte ptr [rdx + rsi + 11], 10 - pinsrb xmm13, byte ptr [rdx + rcx + 11], 11 - pinsrb xmm13, byte ptr [rdx + r8 + 11], 12 - pinsrb xmm13, byte ptr [rdx + r11 + 11], 13 - pinsrb xmm13, byte ptr [rdx + r15 + 11], 14 - pinsrb xmm13, byte ptr [rdx + rdi + 11], 15 + pinsrb xmm11, byte ptr [r13 + rbx + 9], 1 + mov rax, r11 + pinsrb xmm11, byte ptr [r13 + r11 + 9], 2 + pinsrb xmm11, byte ptr [r13 + rcx + 9], 3 + mov r11, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + r11 + 9], 4 + pinsrb xmm11, byte ptr [r13 + r15 + 9], 5 + mov qword ptr [rsp + 128], r9 # 8-byte Spill + pinsrb xmm11, byte ptr [r13 + r9 + 9], 6 + pinsrb xmm11, byte ptr [r13 + r10 + 9], 7 + mov r15, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + r15 + 9], 8 + mov rsi, rdi + pinsrb xmm11, byte ptr [r13 + rdi + 9], 9 + mov rax, r12 + pinsrb xmm11, byte ptr [r13 + r12 + 9], 10 + mov rdi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rdi + 9], 11 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + rdx + 9], 12 + pinsrb xmm11, byte ptr [r13 + r8 + 9], 13 + pinsrb xmm11, byte ptr [r13 + r14 + 9], 14 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [r13 + r8 + 9], 15 + pinsrb xmm12, byte ptr [r13 + rbx + 10], 1 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + r12 + 10], 2 + pinsrb xmm12, byte ptr [r13 + rcx + 10], 3 + pinsrb xmm12, byte ptr [r13 + r11 + 10], 4 + mov rcx, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + rcx + 10], 5 + pinsrb xmm12, byte ptr [r13 + r9 + 10], 6 + pinsrb xmm12, byte ptr [r13 + r10 + 10], 7 + pinsrb xmm12, byte ptr [r13 + r15 + 10], 8 + pinsrb xmm12, byte ptr [r13 + rsi + 10], 9 + pinsrb xmm12, byte ptr [r13 + rax + 10], 10 + pinsrb xmm12, byte ptr [r13 + rdi + 10], 11 + pinsrb xmm12, byte ptr [r13 + rdx + 10], 12 + mov r12, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm12, byte ptr [r13 + r12 + 10], 13 + pinsrb xmm12, byte ptr [r13 + r14 + 10], 14 + mov r10, r14 + pinsrb xmm12, byte ptr [r13 + r8 + 10], 15 + pinsrb xmm13, byte ptr [r13 + rbx + 11], 1 + mov r11, rbx + mov rbx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rbx + 11], 2 + mov rbx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + rbx + 11], 3 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + r14 + 11], 4 + pinsrb xmm13, byte ptr [r13 + rcx + 11], 5 + pinsrb xmm13, byte ptr [r13 + r9 + 11], 6 + mov r9, qword ptr [rsp + 208] # 8-byte Reload + pinsrb xmm13, byte ptr [r13 + r9 + 11], 7 + pinsrb xmm13, byte ptr [r13 + r15 + 11], 8 + pinsrb xmm13, byte ptr [r13 + rsi + 11], 9 + pinsrb xmm13, byte ptr [r13 + rax + 11], 10 + pinsrb xmm13, byte ptr [r13 + rdi + 11], 11 + pinsrb xmm13, byte ptr [r13 + rdx + 11], 12 + pinsrb xmm13, byte ptr [r13 + r12 + 11], 13 + pinsrb xmm13, byte ptr [r13 + r10 + 11], 14 + pinsrb xmm13, byte ptr [r13 + r8 + 11], 15 pcmpgtb xmm11, xmm14 pandn xmm11, xmmword ptr [rip + .LCPI11_16] paddb xmm11, xmm0 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 23] + mov rdi, qword ptr [rsp + 104] # 8-byte Reload + movzx esi, byte ptr [r13 + rdi + 23] movd xmm8, esi pcmpgtb xmm12, xmm14 pandn xmm12, xmmword ptr [rip + .LCPI11_17] pcmpgtb xmm13, xmm14 pandn xmm13, xmmword ptr [rip + .LCPI11_18] por xmm13, xmm12 - movzx esi, byte ptr [rdx + rcx + 24] + movzx esi, byte ptr [r13 + rdi + 24] movd xmm12, esi - movdqa xmm9, xmmword ptr [rsp + 208] # 16-byte Reload - pinsrb xmm9, byte ptr [rdx + rbx + 12], 1 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r15 + 12], 2 - mov r11, rax - pinsrb xmm9, byte ptr [rdx + rax + 12], 3 - mov rdi, r9 - pinsrb xmm9, byte ptr [rdx + r9 + 12], 4 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r9 + 12], 5 - mov rbx, r10 - pinsrb xmm9, byte ptr [rdx + r10 + 12], 6 - mov r10, r14 - pinsrb xmm9, byte ptr [rdx + r14 + 12], 7 - mov r14, r12 - pinsrb xmm9, byte ptr [rdx + r12 + 12], 8 - mov r12, r13 - pinsrb xmm9, byte ptr [rdx + r13 + 12], 9 - mov r13, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r13 + 12], 10 - mov rcx, qword ptr [rsp + 176] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rcx + 12], 11 - pinsrb xmm9, byte ptr [rdx + r8 + 12], 12 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rsi + 12], 13 + movdqa xmm9, xmmword ptr [rsp + 240] # 16-byte Reload + pinsrb xmm9, byte ptr [r13 + r11 + 12], 1 + mov r12, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r12 + 12], 2 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r11 + 12], 3 + pinsrb xmm9, byte ptr [r13 + r14 + 12], 4 + mov rbx, rcx + pinsrb xmm9, byte ptr [r13 + rcx + 12], 5 + mov r8, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r8 + 12], 6 + mov r10, r9 + pinsrb xmm9, byte ptr [r13 + r9 + 12], 7 + mov r9, r15 + pinsrb xmm9, byte ptr [r13 + r15 + 12], 8 + mov r15, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + r15 + 12], 9 + mov rdi, rax + pinsrb xmm9, byte ptr [r13 + rax + 12], 10 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rcx + 12], 11 + pinsrb xmm9, byte ptr [r13 + rdx + 12], 12 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rsi + 12], 13 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm9, byte ptr [r13 + rax + 12], 14 mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 12], 14 + pinsrb xmm9, byte ptr [r13 + rax + 12], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rax + 13], 1 + pinsrb xmm6, byte ptr [r13 + r12 + 13], 2 + pinsrb xmm6, byte ptr [r13 + r11 + 13], 3 + pinsrb xmm6, byte ptr [r13 + r14 + 13], 4 + pinsrb xmm6, byte ptr [r13 + rbx + 13], 5 + pinsrb xmm6, byte ptr [r13 + r8 + 13], 6 + pinsrb xmm6, byte ptr [r13 + r10 + 13], 7 + pinsrb xmm6, byte ptr [r13 + r9 + 13], 8 + pinsrb xmm6, byte ptr [r13 + r15 + 13], 9 + pinsrb xmm6, byte ptr [r13 + rdi + 13], 10 + pinsrb xmm6, byte ptr [r13 + rcx + 13], 11 + pinsrb xmm6, byte ptr [r13 + rdx + 13], 12 + pinsrb xmm6, byte ptr [r13 + rsi + 13], 13 mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 12], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 13], 1 - pinsrb xmm6, byte ptr [rdx + r15 + 13], 2 - pinsrb xmm6, byte ptr [rdx + r11 + 13], 3 - pinsrb xmm6, byte ptr [rdx + rdi + 13], 4 - pinsrb xmm6, byte ptr [rdx + r9 + 13], 5 - pinsrb xmm6, byte ptr [rdx + rbx + 13], 6 - pinsrb xmm6, byte ptr [rdx + r10 + 13], 7 - pinsrb xmm6, byte ptr [rdx + r14 + 13], 8 - pinsrb xmm6, byte ptr [rdx + r12 + 13], 9 - pinsrb xmm6, byte ptr [rdx + r13 + 13], 10 - pinsrb xmm6, byte ptr [rdx + rcx + 13], 11 - pinsrb xmm6, byte ptr [rdx + r8 + 13], 12 - pinsrb xmm6, byte ptr [rdx + rsi + 13], 13 + pinsrb xmm6, byte ptr [r13 + rax + 13], 14 mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 13], 14 + pinsrb xmm6, byte ptr [r13 + rax + 13], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rax + 14], 1 + pinsrb xmm15, byte ptr [r13 + r12 + 14], 2 + pinsrb xmm15, byte ptr [r13 + r11 + 14], 3 + pinsrb xmm15, byte ptr [r13 + r14 + 14], 4 + pinsrb xmm15, byte ptr [r13 + rbx + 14], 5 + pinsrb xmm15, byte ptr [r13 + r8 + 14], 6 + pinsrb xmm15, byte ptr [r13 + r10 + 14], 7 + pinsrb xmm15, byte ptr [r13 + r9 + 14], 8 + pinsrb xmm15, byte ptr [r13 + r15 + 14], 9 + pinsrb xmm15, byte ptr [r13 + rdi + 14], 10 + pinsrb xmm15, byte ptr [r13 + rcx + 14], 11 + mov r15, rcx + pinsrb xmm15, byte ptr [r13 + rdx + 14], 12 + pinsrb xmm15, byte ptr [r13 + rsi + 14], 13 mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 13], 15 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rax + 14], 1 - pinsrb xmm15, byte ptr [rdx + r15 + 14], 2 - pinsrb xmm15, byte ptr [rdx + r11 + 14], 3 - pinsrb xmm15, byte ptr [rdx + rdi + 14], 4 - mov r11, rdi - pinsrb xmm15, byte ptr [rdx + r9 + 14], 5 - pinsrb xmm15, byte ptr [rdx + rbx + 14], 6 - pinsrb xmm15, byte ptr [rdx + r10 + 14], 7 - pinsrb xmm15, byte ptr [rdx + r14 + 14], 8 - pinsrb xmm15, byte ptr [rdx + r12 + 14], 9 - pinsrb xmm15, byte ptr [rdx + r13 + 14], 10 - pinsrb xmm15, byte ptr [rdx + rcx + 14], 11 - mov r13, rcx - pinsrb xmm15, byte ptr [rdx + r8 + 14], 12 - mov r12, r8 - pinsrb xmm15, byte ptr [rdx + rsi + 14], 13 - mov r15, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r15 + 14], 14 + pinsrb xmm15, byte ptr [r13 + rax + 14], 14 pcmpgtb xmm9, xmm14 pandn xmm9, xmmword ptr [rip + .LCPI11_19] por xmm9, xmm13 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 25] + mov rax, qword ptr [rsp + 104] # 8-byte Reload + movzx esi, byte ptr [r13 + rax + 25] movd xmm13, esi psubb xmm11, xmmword ptr [rip + .LCPI11_22] por xmm9, xmm11 - movzx esi, byte ptr [rdx + rax + 26] + movzx esi, byte ptr [r13 + rax + 26] movd xmm0, esi - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rcx + 14], 15 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rdi + 14], 15 pcmpgtb xmm6, xmm14 pandn xmm6, xmmword ptr [rip + .LCPI11_20] pcmpgtb xmm15, xmm14 pandn xmm15, xmmword ptr [rip + .LCPI11_21] por xmm15, xmm6 - movzx esi, byte ptr [rdx + rax + 27] + movzx esi, byte ptr [r13 + rax + 27] movd xmm11, esi - movdqa xmm6, xmmword ptr [rsp + 160] # 16-byte Reload - mov r8, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r8 + 15], 1 - mov rdi, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rdi + 15], 2 - mov rsi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 15], 3 - pinsrb xmm6, byte ptr [rdx + r11 + 15], 4 - pinsrb xmm6, byte ptr [rdx + r9 + 15], 5 - mov r9, rbx - pinsrb xmm6, byte ptr [rdx + rbx + 15], 6 - pinsrb xmm6, byte ptr [rdx + r10 + 15], 7 - pinsrb xmm6, byte ptr [rdx + r14 + 15], 8 - mov r10, r14 - mov r11, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r11 + 15], 9 - mov rbx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rbx + 15], 10 - pinsrb xmm6, byte ptr [rdx + r13 + 15], 11 - pinsrb xmm6, byte ptr [rdx + r12 + 15], 12 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r12 + 15], 13 - pinsrb xmm6, byte ptr [rdx + r15 + 15], 14 - pinsrb xmm6, byte ptr [rdx + rcx + 15], 15 + movdqa xmm6, xmmword ptr [rsp + 192] # 16-byte Reload + mov r11, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r11 + 15], 1 + pinsrb xmm6, byte ptr [r13 + r12 + 15], 2 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rcx + 15], 3 + pinsrb xmm6, byte ptr [r13 + r14 + 15], 4 + pinsrb xmm6, byte ptr [r13 + rbx + 15], 5 + pinsrb xmm6, byte ptr [r13 + r8 + 15], 6 + pinsrb xmm6, byte ptr [r13 + r10 + 15], 7 + pinsrb xmm6, byte ptr [r13 + r9 + 15], 8 + mov rdx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rdx + 15], 9 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rsi + 15], 10 + pinsrb xmm6, byte ptr [r13 + r15 + 15], 11 + mov r15, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + r15 + 15], 12 + mov rbx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rbx + 15], 13 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r13 + rsi + 15], 14 + pinsrb xmm6, byte ptr [r13 + rdi + 15], 15 pcmpgtb xmm6, xmm14 pandn xmm6, xmmword ptr [rip + .LCPI11_6] por xmm6, xmm15 - movzx esi, byte ptr [rdx + rax + 28] + movzx esi, byte ptr [r13 + rax + 28] movd xmm15, esi por xmm6, xmm9 - movdqa xmmword ptr [rsp + 160], xmm6 # 16-byte Spill - movzx esi, byte ptr [rdx + rax + 29] + movdqa xmmword ptr [rsp + 192], xmm6 # 16-byte Spill + movzx esi, byte ptr [r13 + rax + 29] movd xmm9, esi - mov rax, r8 - pinsrb xmm10, byte ptr [rdx + r8 + 16], 1 - mov r14, rdi - pinsrb xmm10, byte ptr [rdx + rdi + 16], 2 - mov rcx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rcx + 16], 3 - mov rdi, qword ptr [rsp + 128] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rdi + 16], 4 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r8 + 16], 5 - pinsrb xmm10, byte ptr [rdx + r9 + 16], 6 - mov r9, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r9 + 16], 7 - pinsrb xmm10, byte ptr [rdx + r10 + 16], 8 - pinsrb xmm10, byte ptr [rdx + r11 + 16], 9 - pinsrb xmm10, byte ptr [rdx + rbx + 16], 10 - pinsrb xmm10, byte ptr [rdx + r13 + 16], 11 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + r15 + 16], 12 - pinsrb xmm10, byte ptr [rdx + r12 + 16], 13 - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rcx + 16], 14 - mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rsi + 16], 15 - pinsrb xmm4, byte ptr [rdx + rax + 17], 1 - pinsrb xmm4, byte ptr [rdx + r14 + 17], 2 - mov r14, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r14 + 17], 3 - pinsrb xmm4, byte ptr [rdx + rdi + 17], 4 - pinsrb xmm4, byte ptr [rdx + r8 + 17], 5 - mov r12, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r12 + 17], 6 - pinsrb xmm4, byte ptr [rdx + r9 + 17], 7 - pinsrb xmm4, byte ptr [rdx + r10 + 17], 8 - pinsrb xmm4, byte ptr [rdx + r11 + 17], 9 - pinsrb xmm4, byte ptr [rdx + rbx + 17], 10 - pinsrb xmm4, byte ptr [rdx + r13 + 17], 11 - mov rbx, r15 - pinsrb xmm4, byte ptr [rdx + r15 + 17], 12 - mov r8, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r8 + 17], 13 - pinsrb xmm4, byte ptr [rdx + rcx + 17], 14 - mov r9, rcx - pinsrb xmm4, byte ptr [rdx + rsi + 17], 15 - mov r15, rsi + mov rax, r11 + pinsrb xmm10, byte ptr [r13 + r11 + 16], 1 + pinsrb xmm10, byte ptr [r13 + r12 + 16], 2 + pinsrb xmm10, byte ptr [r13 + rcx + 16], 3 + pinsrb xmm10, byte ptr [r13 + r14 + 16], 4 + mov r12, r14 + mov r10, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r10 + 16], 5 + pinsrb xmm10, byte ptr [r13 + r8 + 16], 6 + mov r11, r8 + mov r8, qword ptr [rsp + 208] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r8 + 16], 7 + mov r14, r9 + pinsrb xmm10, byte ptr [r13 + r9 + 16], 8 + pinsrb xmm10, byte ptr [r13 + rdx + 16], 9 + mov rdi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rdi + 16], 10 + mov r9, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + r9 + 16], 11 + pinsrb xmm10, byte ptr [r13 + r15 + 16], 12 + pinsrb xmm10, byte ptr [r13 + rbx + 16], 13 + mov rbx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rbx + 16], 14 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r13 + rsi + 16], 15 + pinsrb xmm4, byte ptr [r13 + rax + 17], 1 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rax + 17], 2 + pinsrb xmm4, byte ptr [r13 + rcx + 17], 3 + pinsrb xmm4, byte ptr [r13 + r12 + 17], 4 + pinsrb xmm4, byte ptr [r13 + r10 + 17], 5 + pinsrb xmm4, byte ptr [r13 + r11 + 17], 6 + pinsrb xmm4, byte ptr [r13 + r8 + 17], 7 + mov r10, r8 + mov r8, r14 + pinsrb xmm4, byte ptr [r13 + r14 + 17], 8 + pinsrb xmm4, byte ptr [r13 + rdx + 17], 9 + pinsrb xmm4, byte ptr [r13 + rdi + 17], 10 + pinsrb xmm4, byte ptr [r13 + r9 + 17], 11 + mov rdx, r15 + pinsrb xmm4, byte ptr [r13 + r15 + 17], 12 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm4, byte ptr [r13 + rcx + 17], 13 + pinsrb xmm4, byte ptr [r13 + rbx + 17], 14 + pinsrb xmm4, byte ptr [r13 + rsi + 17], 15 pcmpgtb xmm10, xmm14 pcmpgtb xmm4, xmm14 movdqa xmm6, xmmword ptr [rip + .LCPI11_16] # xmm6 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] pandn xmm4, xmm6 paddb xmm4, xmm10 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 30] + mov rax, qword ptr [rsp + 104] # 8-byte Reload + movzx esi, byte ptr [r13 + rax + 30] movd xmm10, esi - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 18], 1 - pinsrb xmm5, byte ptr [rdx + rsi + 19], 1 - pinsrb xmm3, byte ptr [rdx + rsi + 20], 1 - pinsrb xmm2, byte ptr [rdx + rsi + 21], 1 - pinsrb xmm1, byte ptr [rdx + rsi + 22], 1 - pinsrb xmm8, byte ptr [rdx + rsi + 23], 1 - pinsrb xmm12, byte ptr [rdx + rsi + 24], 1 - pinsrb xmm13, byte ptr [rdx + rsi + 25], 1 - pinsrb xmm0, byte ptr [rdx + rsi + 26], 1 - pinsrb xmm11, byte ptr [rdx + rsi + 27], 1 - pinsrb xmm15, byte ptr [rdx + rsi + 28], 1 - pinsrb xmm9, byte ptr [rdx + rsi + 29], 1 - pinsrb xmm10, byte ptr [rdx + rsi + 30], 1 - movzx eax, byte ptr [rdx + rax + 31] - movd xmm6, eax - pinsrb xmm6, byte ptr [rdx + rsi + 31], 1 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 18], 2 - pinsrb xmm5, byte ptr [rdx + rax + 19], 2 - pinsrb xmm3, byte ptr [rdx + rax + 20], 2 - pinsrb xmm2, byte ptr [rdx + rax + 21], 2 - pinsrb xmm1, byte ptr [rdx + rax + 22], 2 - pinsrb xmm8, byte ptr [rdx + rax + 23], 2 - pinsrb xmm12, byte ptr [rdx + rax + 24], 2 - pinsrb xmm13, byte ptr [rdx + rax + 25], 2 - pinsrb xmm0, byte ptr [rdx + rax + 26], 2 - pinsrb xmm11, byte ptr [rdx + rax + 27], 2 - pinsrb xmm15, byte ptr [rdx + rax + 28], 2 - pinsrb xmm9, byte ptr [rdx + rax + 29], 2 - pinsrb xmm10, byte ptr [rdx + rax + 30], 2 - pinsrb xmm6, byte ptr [rdx + rax + 31], 2 - mov r11, r14 - pinsrb xmm7, byte ptr [rdx + r14 + 18], 3 - pinsrb xmm7, byte ptr [rdx + rdi + 18], 4 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rcx + 18], 5 - pinsrb xmm7, byte ptr [rdx + r12 + 18], 6 - mov r10, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r10 + 18], 7 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + r14 + 18], 8 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rax + 18], 9 mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rsi + 18], 10 - pinsrb xmm7, byte ptr [rdx + r13 + 18], 11 - pinsrb xmm7, byte ptr [rdx + rbx + 18], 12 - pinsrb xmm7, byte ptr [rdx + r8 + 18], 13 - pinsrb xmm7, byte ptr [rdx + r9 + 18], 14 - pinsrb xmm7, byte ptr [rdx + r15 + 18], 15 - pinsrb xmm5, byte ptr [rdx + r11 + 19], 3 - pinsrb xmm5, byte ptr [rdx + rdi + 19], 4 - pinsrb xmm5, byte ptr [rdx + rcx + 19], 5 - pinsrb xmm5, byte ptr [rdx + r12 + 19], 6 - pinsrb xmm5, byte ptr [rdx + r10 + 19], 7 - pinsrb xmm5, byte ptr [rdx + r14 + 19], 8 - pinsrb xmm5, byte ptr [rdx + rax + 19], 9 - pinsrb xmm5, byte ptr [rdx + rsi + 19], 10 - pinsrb xmm5, byte ptr [rdx + r13 + 19], 11 - pinsrb xmm5, byte ptr [rdx + rbx + 19], 12 - pinsrb xmm5, byte ptr [rdx + r8 + 19], 13 - pinsrb xmm5, byte ptr [rdx + r9 + 19], 14 - pinsrb xmm5, byte ptr [rdx + r15 + 19], 15 - pinsrb xmm3, byte ptr [rdx + r11 + 20], 3 - pinsrb xmm3, byte ptr [rdx + rdi + 20], 4 - pinsrb xmm3, byte ptr [rdx + rcx + 20], 5 - pinsrb xmm3, byte ptr [rdx + r12 + 20], 6 - pinsrb xmm3, byte ptr [rdx + r10 + 20], 7 - pinsrb xmm3, byte ptr [rdx + r14 + 20], 8 - pinsrb xmm3, byte ptr [rdx + rax + 20], 9 - pinsrb xmm3, byte ptr [rdx + rsi + 20], 10 - pinsrb xmm3, byte ptr [rdx + r13 + 20], 11 - pinsrb xmm3, byte ptr [rdx + rbx + 20], 12 - pinsrb xmm3, byte ptr [rdx + r8 + 20], 13 - pinsrb xmm3, byte ptr [rdx + r9 + 20], 14 + pinsrb xmm7, byte ptr [r13 + rsi + 18], 1 + pinsrb xmm5, byte ptr [r13 + rsi + 19], 1 + pinsrb xmm3, byte ptr [r13 + rsi + 20], 1 + pinsrb xmm2, byte ptr [r13 + rsi + 21], 1 + pinsrb xmm1, byte ptr [r13 + rsi + 22], 1 + pinsrb xmm8, byte ptr [r13 + rsi + 23], 1 + pinsrb xmm12, byte ptr [r13 + rsi + 24], 1 + pinsrb xmm13, byte ptr [r13 + rsi + 25], 1 + pinsrb xmm0, byte ptr [r13 + rsi + 26], 1 + pinsrb xmm11, byte ptr [r13 + rsi + 27], 1 + pinsrb xmm15, byte ptr [r13 + rsi + 28], 1 + pinsrb xmm9, byte ptr [r13 + rsi + 29], 1 + pinsrb xmm10, byte ptr [r13 + rsi + 30], 1 + movzx eax, byte ptr [r13 + rax + 31] + movd xmm6, eax + pinsrb xmm6, byte ptr [r13 + rsi + 31], 1 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 18], 2 + pinsrb xmm5, byte ptr [r13 + rax + 19], 2 + pinsrb xmm3, byte ptr [r13 + rax + 20], 2 + pinsrb xmm2, byte ptr [r13 + rax + 21], 2 + pinsrb xmm1, byte ptr [r13 + rax + 22], 2 + pinsrb xmm8, byte ptr [r13 + rax + 23], 2 + pinsrb xmm12, byte ptr [r13 + rax + 24], 2 + pinsrb xmm13, byte ptr [r13 + rax + 25], 2 + pinsrb xmm0, byte ptr [r13 + rax + 26], 2 + pinsrb xmm11, byte ptr [r13 + rax + 27], 2 + pinsrb xmm15, byte ptr [r13 + rax + 28], 2 + pinsrb xmm9, byte ptr [r13 + rax + 29], 2 + pinsrb xmm10, byte ptr [r13 + rax + 30], 2 + pinsrb xmm6, byte ptr [r13 + rax + 31], 2 + mov r11, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r11 + 18], 3 + mov r14, r12 + pinsrb xmm7, byte ptr [r13 + r12 + 18], 4 + mov r9, qword ptr [rsp + 112] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r9 + 18], 5 + mov rdi, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rdi + 18], 6 + pinsrb xmm7, byte ptr [r13 + r10 + 18], 7 + pinsrb xmm7, byte ptr [r13 + r8 + 18], 8 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rax + 18], 9 + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + rsi + 18], 10 + mov r15, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r15 + 18], 11 + pinsrb xmm7, byte ptr [r13 + rdx + 18], 12 + pinsrb xmm7, byte ptr [r13 + rcx + 18], 13 + pinsrb xmm7, byte ptr [r13 + rbx + 18], 14 + mov r12, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm7, byte ptr [r13 + r12 + 18], 15 + pinsrb xmm5, byte ptr [r13 + r11 + 19], 3 + pinsrb xmm5, byte ptr [r13 + r14 + 19], 4 + pinsrb xmm5, byte ptr [r13 + r9 + 19], 5 + pinsrb xmm5, byte ptr [r13 + rdi + 19], 6 + pinsrb xmm5, byte ptr [r13 + r10 + 19], 7 + pinsrb xmm5, byte ptr [r13 + r8 + 19], 8 + pinsrb xmm5, byte ptr [r13 + rax + 19], 9 + pinsrb xmm5, byte ptr [r13 + rsi + 19], 10 + pinsrb xmm5, byte ptr [r13 + r15 + 19], 11 + pinsrb xmm5, byte ptr [r13 + rdx + 19], 12 + pinsrb xmm5, byte ptr [r13 + rcx + 19], 13 + pinsrb xmm5, byte ptr [r13 + rbx + 19], 14 + pinsrb xmm5, byte ptr [r13 + r12 + 19], 15 + pinsrb xmm3, byte ptr [r13 + r11 + 20], 3 + pinsrb xmm3, byte ptr [r13 + r14 + 20], 4 + pinsrb xmm3, byte ptr [r13 + r9 + 20], 5 + pinsrb xmm3, byte ptr [r13 + rdi + 20], 6 + pinsrb xmm3, byte ptr [r13 + r10 + 20], 7 + pinsrb xmm3, byte ptr [r13 + r8 + 20], 8 + pinsrb xmm3, byte ptr [r13 + rax + 20], 9 + pinsrb xmm3, byte ptr [r13 + rsi + 20], 10 + pinsrb xmm3, byte ptr [r13 + r15 + 20], 11 + pinsrb xmm3, byte ptr [r13 + rdx + 20], 12 + pinsrb xmm3, byte ptr [r13 + rcx + 20], 13 + pinsrb xmm3, byte ptr [r13 + rbx + 20], 14 pcmpgtb xmm7, xmm14 movdqa xmm14, xmmword ptr [rip + .LCPI11_17] # xmm14 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] pandn xmm7, xmm14 - pcmpgtb xmm5, xmmword ptr [rsp + 144] # 16-byte Folded Reload + pcmpgtb xmm5, xmmword ptr [rsp + 160] # 16-byte Folded Reload movdqa xmm14, xmmword ptr [rip + .LCPI11_18] # xmm14 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] pandn xmm5, xmm14 por xmm5, xmm7 - pinsrb xmm3, byte ptr [rdx + r15 + 20], 15 - movdqa xmm14, xmmword ptr [rsp + 144] # 16-byte Reload + pinsrb xmm3, byte ptr [r13 + r12 + 20], 15 + movdqa xmm14, xmmword ptr [rsp + 160] # 16-byte Reload pcmpgtb xmm3, xmm14 movdqa xmm7, xmmword ptr [rip + .LCPI11_19] # xmm7 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] pandn xmm3, xmm7 @@ -59214,44 +61913,44 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr pcmpeqd xmm5, xmm5 psubb xmm4, xmm5 por xmm3, xmm4 - pinsrb xmm2, byte ptr [rdx + r11 + 21], 3 - pinsrb xmm2, byte ptr [rdx + rdi + 21], 4 - pinsrb xmm2, byte ptr [rdx + rcx + 21], 5 - pinsrb xmm2, byte ptr [rdx + r12 + 21], 6 - pinsrb xmm2, byte ptr [rdx + r10 + 21], 7 - pinsrb xmm2, byte ptr [rdx + r14 + 21], 8 - pinsrb xmm2, byte ptr [rdx + rax + 21], 9 - pinsrb xmm2, byte ptr [rdx + rsi + 21], 10 - pinsrb xmm2, byte ptr [rdx + r13 + 21], 11 - pinsrb xmm2, byte ptr [rdx + rbx + 21], 12 - pinsrb xmm2, byte ptr [rdx + r8 + 21], 13 - pinsrb xmm2, byte ptr [rdx + r9 + 21], 14 - pinsrb xmm2, byte ptr [rdx + r15 + 21], 15 - pinsrb xmm1, byte ptr [rdx + r11 + 22], 3 - pinsrb xmm1, byte ptr [rdx + rdi + 22], 4 - pinsrb xmm1, byte ptr [rdx + rcx + 22], 5 - pinsrb xmm1, byte ptr [rdx + r12 + 22], 6 - pinsrb xmm1, byte ptr [rdx + r10 + 22], 7 - pinsrb xmm1, byte ptr [rdx + r14 + 22], 8 - pinsrb xmm1, byte ptr [rdx + rax + 22], 9 - pinsrb xmm1, byte ptr [rdx + rsi + 22], 10 - pinsrb xmm1, byte ptr [rdx + r13 + 22], 11 - pinsrb xmm1, byte ptr [rdx + rbx + 22], 12 - pinsrb xmm1, byte ptr [rdx + r8 + 22], 13 - pinsrb xmm1, byte ptr [rdx + r9 + 22], 14 - pinsrb xmm1, byte ptr [rdx + r15 + 22], 15 - pinsrb xmm8, byte ptr [rdx + r11 + 23], 3 - pinsrb xmm8, byte ptr [rdx + rdi + 23], 4 - pinsrb xmm8, byte ptr [rdx + rcx + 23], 5 - pinsrb xmm8, byte ptr [rdx + r12 + 23], 6 - pinsrb xmm8, byte ptr [rdx + r10 + 23], 7 - pinsrb xmm8, byte ptr [rdx + r14 + 23], 8 - pinsrb xmm8, byte ptr [rdx + rax + 23], 9 - pinsrb xmm8, byte ptr [rdx + rsi + 23], 10 - pinsrb xmm8, byte ptr [rdx + r13 + 23], 11 - pinsrb xmm8, byte ptr [rdx + rbx + 23], 12 - pinsrb xmm8, byte ptr [rdx + r8 + 23], 13 - pinsrb xmm8, byte ptr [rdx + r9 + 23], 14 + pinsrb xmm2, byte ptr [r13 + r11 + 21], 3 + pinsrb xmm2, byte ptr [r13 + r14 + 21], 4 + pinsrb xmm2, byte ptr [r13 + r9 + 21], 5 + pinsrb xmm2, byte ptr [r13 + rdi + 21], 6 + pinsrb xmm2, byte ptr [r13 + r10 + 21], 7 + pinsrb xmm2, byte ptr [r13 + r8 + 21], 8 + pinsrb xmm2, byte ptr [r13 + rax + 21], 9 + pinsrb xmm2, byte ptr [r13 + rsi + 21], 10 + pinsrb xmm2, byte ptr [r13 + r15 + 21], 11 + pinsrb xmm2, byte ptr [r13 + rdx + 21], 12 + pinsrb xmm2, byte ptr [r13 + rcx + 21], 13 + pinsrb xmm2, byte ptr [r13 + rbx + 21], 14 + pinsrb xmm2, byte ptr [r13 + r12 + 21], 15 + pinsrb xmm1, byte ptr [r13 + r11 + 22], 3 + pinsrb xmm1, byte ptr [r13 + r14 + 22], 4 + pinsrb xmm1, byte ptr [r13 + r9 + 22], 5 + pinsrb xmm1, byte ptr [r13 + rdi + 22], 6 + pinsrb xmm1, byte ptr [r13 + r10 + 22], 7 + pinsrb xmm1, byte ptr [r13 + r8 + 22], 8 + pinsrb xmm1, byte ptr [r13 + rax + 22], 9 + pinsrb xmm1, byte ptr [r13 + rsi + 22], 10 + pinsrb xmm1, byte ptr [r13 + r15 + 22], 11 + pinsrb xmm1, byte ptr [r13 + rdx + 22], 12 + pinsrb xmm1, byte ptr [r13 + rcx + 22], 13 + pinsrb xmm1, byte ptr [r13 + rbx + 22], 14 + pinsrb xmm1, byte ptr [r13 + r12 + 22], 15 + pinsrb xmm8, byte ptr [r13 + r11 + 23], 3 + pinsrb xmm8, byte ptr [r13 + r14 + 23], 4 + pinsrb xmm8, byte ptr [r13 + r9 + 23], 5 + pinsrb xmm8, byte ptr [r13 + rdi + 23], 6 + pinsrb xmm8, byte ptr [r13 + r10 + 23], 7 + pinsrb xmm8, byte ptr [r13 + r8 + 23], 8 + pinsrb xmm8, byte ptr [r13 + rax + 23], 9 + pinsrb xmm8, byte ptr [r13 + rsi + 23], 10 + pinsrb xmm8, byte ptr [r13 + r15 + 23], 11 + pinsrb xmm8, byte ptr [r13 + rdx + 23], 12 + pinsrb xmm8, byte ptr [r13 + rcx + 23], 13 + pinsrb xmm8, byte ptr [r13 + rbx + 23], 14 pcmpgtb xmm2, xmm14 movdqa xmm5, xmmword ptr [rip + .LCPI11_20] # xmm5 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] pandn xmm2, xmm5 @@ -59259,136 +61958,138 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr movdqa xmm7, xmmword ptr [rip + .LCPI11_21] # xmm7 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] pandn xmm1, xmm7 por xmm1, xmm2 - pinsrb xmm8, byte ptr [rdx + r15 + 23], 15 + pinsrb xmm8, byte ptr [r13 + r12 + 23], 15 pcmpgtb xmm8, xmm14 movdqa xmm4, xmmword ptr [rip + .LCPI11_6] # xmm4 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] pandn xmm8, xmm4 por xmm8, xmm1 - pinsrb xmm12, byte ptr [rdx + r11 + 24], 3 - pinsrb xmm12, byte ptr [rdx + rdi + 24], 4 - pinsrb xmm12, byte ptr [rdx + rcx + 24], 5 - pinsrb xmm12, byte ptr [rdx + r12 + 24], 6 - pinsrb xmm12, byte ptr [rdx + r10 + 24], 7 - pinsrb xmm12, byte ptr [rdx + r14 + 24], 8 - pinsrb xmm12, byte ptr [rdx + rax + 24], 9 - pinsrb xmm12, byte ptr [rdx + rsi + 24], 10 - pinsrb xmm12, byte ptr [rdx + r13 + 24], 11 - pinsrb xmm12, byte ptr [rdx + rbx + 24], 12 - pinsrb xmm12, byte ptr [rdx + r8 + 24], 13 - pinsrb xmm12, byte ptr [rdx + r9 + 24], 14 - pinsrb xmm12, byte ptr [rdx + r15 + 24], 15 + pinsrb xmm12, byte ptr [r13 + r11 + 24], 3 + pinsrb xmm12, byte ptr [r13 + r14 + 24], 4 + pinsrb xmm12, byte ptr [r13 + r9 + 24], 5 + pinsrb xmm12, byte ptr [r13 + rdi + 24], 6 + pinsrb xmm12, byte ptr [r13 + r10 + 24], 7 + pinsrb xmm12, byte ptr [r13 + r8 + 24], 8 + pinsrb xmm12, byte ptr [r13 + rax + 24], 9 + pinsrb xmm12, byte ptr [r13 + rsi + 24], 10 + pinsrb xmm12, byte ptr [r13 + r15 + 24], 11 + pinsrb xmm12, byte ptr [r13 + rdx + 24], 12 + pinsrb xmm12, byte ptr [r13 + rcx + 24], 13 + pinsrb xmm12, byte ptr [r13 + rbx + 24], 14 + pinsrb xmm12, byte ptr [r13 + r12 + 24], 15 por xmm8, xmm3 pcmpgtb xmm12, xmm14 - pinsrb xmm13, byte ptr [rdx + r11 + 25], 3 - pinsrb xmm13, byte ptr [rdx + rdi + 25], 4 - pinsrb xmm13, byte ptr [rdx + rcx + 25], 5 - pinsrb xmm13, byte ptr [rdx + r12 + 25], 6 - pinsrb xmm13, byte ptr [rdx + r10 + 25], 7 - pinsrb xmm13, byte ptr [rdx + r14 + 25], 8 - pinsrb xmm13, byte ptr [rdx + rax + 25], 9 - pinsrb xmm13, byte ptr [rdx + rsi + 25], 10 - pinsrb xmm13, byte ptr [rdx + r13 + 25], 11 - pinsrb xmm13, byte ptr [rdx + rbx + 25], 12 - pinsrb xmm13, byte ptr [rdx + r8 + 25], 13 - pinsrb xmm13, byte ptr [rdx + r9 + 25], 14 - pinsrb xmm13, byte ptr [rdx + r15 + 25], 15 - pinsrb xmm0, byte ptr [rdx + r11 + 26], 3 - pinsrb xmm0, byte ptr [rdx + rdi + 26], 4 - pinsrb xmm0, byte ptr [rdx + rcx + 26], 5 - pinsrb xmm0, byte ptr [rdx + r12 + 26], 6 - pinsrb xmm0, byte ptr [rdx + r10 + 26], 7 - pinsrb xmm0, byte ptr [rdx + r14 + 26], 8 - pinsrb xmm0, byte ptr [rdx + rax + 26], 9 - pinsrb xmm0, byte ptr [rdx + rsi + 26], 10 - pinsrb xmm0, byte ptr [rdx + r13 + 26], 11 - pinsrb xmm0, byte ptr [rdx + rbx + 26], 12 - pinsrb xmm0, byte ptr [rdx + r8 + 26], 13 - pinsrb xmm0, byte ptr [rdx + r9 + 26], 14 - pinsrb xmm0, byte ptr [rdx + r15 + 26], 15 - pinsrb xmm11, byte ptr [rdx + r11 + 27], 3 - pinsrb xmm11, byte ptr [rdx + rdi + 27], 4 - pinsrb xmm11, byte ptr [rdx + rcx + 27], 5 - pinsrb xmm11, byte ptr [rdx + r12 + 27], 6 - pinsrb xmm11, byte ptr [rdx + r10 + 27], 7 - pinsrb xmm11, byte ptr [rdx + r14 + 27], 8 - pinsrb xmm11, byte ptr [rdx + rax + 27], 9 - pinsrb xmm11, byte ptr [rdx + rsi + 27], 10 - pinsrb xmm11, byte ptr [rdx + r13 + 27], 11 - pinsrb xmm11, byte ptr [rdx + rbx + 27], 12 - pinsrb xmm11, byte ptr [rdx + r8 + 27], 13 - pinsrb xmm11, byte ptr [rdx + r9 + 27], 14 + pinsrb xmm13, byte ptr [r13 + r11 + 25], 3 + pinsrb xmm13, byte ptr [r13 + r14 + 25], 4 + pinsrb xmm13, byte ptr [r13 + r9 + 25], 5 + pinsrb xmm13, byte ptr [r13 + rdi + 25], 6 + pinsrb xmm13, byte ptr [r13 + r10 + 25], 7 + pinsrb xmm13, byte ptr [r13 + r8 + 25], 8 + pinsrb xmm13, byte ptr [r13 + rax + 25], 9 + pinsrb xmm13, byte ptr [r13 + rsi + 25], 10 + pinsrb xmm13, byte ptr [r13 + r15 + 25], 11 + pinsrb xmm13, byte ptr [r13 + rdx + 25], 12 + pinsrb xmm13, byte ptr [r13 + rcx + 25], 13 + pinsrb xmm13, byte ptr [r13 + rbx + 25], 14 + pinsrb xmm13, byte ptr [r13 + r12 + 25], 15 + pinsrb xmm0, byte ptr [r13 + r11 + 26], 3 + pinsrb xmm0, byte ptr [r13 + r14 + 26], 4 + pinsrb xmm0, byte ptr [r13 + r9 + 26], 5 + pinsrb xmm0, byte ptr [r13 + rdi + 26], 6 + pinsrb xmm0, byte ptr [r13 + r10 + 26], 7 + pinsrb xmm0, byte ptr [r13 + r8 + 26], 8 + pinsrb xmm0, byte ptr [r13 + rax + 26], 9 + pinsrb xmm0, byte ptr [r13 + rsi + 26], 10 + pinsrb xmm0, byte ptr [r13 + r15 + 26], 11 + pinsrb xmm0, byte ptr [r13 + rdx + 26], 12 + pinsrb xmm0, byte ptr [r13 + rcx + 26], 13 + pinsrb xmm0, byte ptr [r13 + rbx + 26], 14 + pinsrb xmm0, byte ptr [r13 + r12 + 26], 15 + pinsrb xmm11, byte ptr [r13 + r11 + 27], 3 + pinsrb xmm11, byte ptr [r13 + r14 + 27], 4 + pinsrb xmm11, byte ptr [r13 + r9 + 27], 5 + pinsrb xmm11, byte ptr [r13 + rdi + 27], 6 + pinsrb xmm11, byte ptr [r13 + r10 + 27], 7 + pinsrb xmm11, byte ptr [r13 + r8 + 27], 8 + pinsrb xmm11, byte ptr [r13 + rax + 27], 9 + pinsrb xmm11, byte ptr [r13 + rsi + 27], 10 + pinsrb xmm11, byte ptr [r13 + r15 + 27], 11 + pinsrb xmm11, byte ptr [r13 + rdx + 27], 12 + pinsrb xmm11, byte ptr [r13 + rcx + 27], 13 + pinsrb xmm11, byte ptr [r13 + rbx + 27], 14 pcmpgtb xmm13, xmm14 pandn xmm13, xmmword ptr [rip + .LCPI11_16] paddb xmm13, xmm12 - pinsrb xmm11, byte ptr [rdx + r15 + 27], 15 + pinsrb xmm11, byte ptr [r13 + r12 + 27], 15 pcmpgtb xmm0, xmm14 pandn xmm0, xmmword ptr [rip + .LCPI11_17] pcmpgtb xmm11, xmm14 pandn xmm11, xmmword ptr [rip + .LCPI11_18] por xmm11, xmm0 - pinsrb xmm15, byte ptr [rdx + r11 + 28], 3 - pinsrb xmm9, byte ptr [rdx + r11 + 29], 3 - pinsrb xmm10, byte ptr [rdx + r11 + 30], 3 - pinsrb xmm6, byte ptr [rdx + r11 + 31], 3 - pinsrb xmm15, byte ptr [rdx + rdi + 28], 4 - pinsrb xmm9, byte ptr [rdx + rdi + 29], 4 - pinsrb xmm10, byte ptr [rdx + rdi + 30], 4 - pinsrb xmm6, byte ptr [rdx + rdi + 31], 4 - mov rdi, rcx - pinsrb xmm15, byte ptr [rdx + rcx + 28], 5 - pinsrb xmm9, byte ptr [rdx + rcx + 29], 5 - pinsrb xmm10, byte ptr [rdx + rcx + 30], 5 - pinsrb xmm6, byte ptr [rdx + rcx + 31], 5 - pinsrb xmm15, byte ptr [rdx + r12 + 28], 6 - pinsrb xmm9, byte ptr [rdx + r12 + 29], 6 - pinsrb xmm10, byte ptr [rdx + r12 + 30], 6 - pinsrb xmm6, byte ptr [rdx + r12 + 31], 6 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - mov rdi, r10 - pinsrb xmm15, byte ptr [rdx + r10 + 28], 7 - pinsrb xmm9, byte ptr [rdx + r10 + 29], 7 - pinsrb xmm10, byte ptr [rdx + r10 + 30], 7 - pinsrb xmm6, byte ptr [rdx + r10 + 31], 7 - mov rdi, r14 - pinsrb xmm15, byte ptr [rdx + r14 + 28], 8 - pinsrb xmm9, byte ptr [rdx + r14 + 29], 8 - pinsrb xmm10, byte ptr [rdx + r14 + 30], 8 - pinsrb xmm6, byte ptr [rdx + r14 + 31], 8 - pinsrb xmm15, byte ptr [rdx + rax + 28], 9 - pinsrb xmm9, byte ptr [rdx + rax + 29], 9 - pinsrb xmm10, byte ptr [rdx + rax + 30], 9 - pinsrb xmm6, byte ptr [rdx + rax + 31], 9 + pinsrb xmm15, byte ptr [r13 + r11 + 28], 3 + pinsrb xmm9, byte ptr [r13 + r11 + 29], 3 + pinsrb xmm10, byte ptr [r13 + r11 + 30], 3 + pinsrb xmm6, byte ptr [r13 + r11 + 31], 3 + pinsrb xmm15, byte ptr [r13 + r14 + 28], 4 + pinsrb xmm9, byte ptr [r13 + r14 + 29], 4 + pinsrb xmm10, byte ptr [r13 + r14 + 30], 4 + pinsrb xmm6, byte ptr [r13 + r14 + 31], 4 + mov rbx, r9 + pinsrb xmm15, byte ptr [r13 + r9 + 28], 5 + pinsrb xmm9, byte ptr [r13 + r9 + 29], 5 + pinsrb xmm10, byte ptr [r13 + r9 + 30], 5 + pinsrb xmm6, byte ptr [r13 + r9 + 31], 5 + pinsrb xmm15, byte ptr [r13 + rdi + 28], 6 + pinsrb xmm9, byte ptr [r13 + rdi + 29], 6 + pinsrb xmm10, byte ptr [r13 + rdi + 30], 6 + pinsrb xmm6, byte ptr [r13 + rdi + 31], 6 + mov rbx, r10 + pinsrb xmm15, byte ptr [r13 + r10 + 28], 7 + pinsrb xmm9, byte ptr [r13 + r10 + 29], 7 + pinsrb xmm10, byte ptr [r13 + r10 + 30], 7 + pinsrb xmm6, byte ptr [r13 + r10 + 31], 7 + mov r8, qword ptr [rsp + 136] # 8-byte Reload + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm15, byte ptr [r13 + rbx + 28], 8 + pinsrb xmm9, byte ptr [r13 + rbx + 29], 8 + pinsrb xmm10, byte ptr [r13 + rbx + 30], 8 + pinsrb xmm6, byte ptr [r13 + rbx + 31], 8 + pinsrb xmm15, byte ptr [r13 + rax + 28], 9 + pinsrb xmm9, byte ptr [r13 + rax + 29], 9 + pinsrb xmm10, byte ptr [r13 + rax + 30], 9 + pinsrb xmm6, byte ptr [r13 + rax + 31], 9 mov rax, rsi - pinsrb xmm15, byte ptr [rdx + rsi + 28], 10 - pinsrb xmm9, byte ptr [rdx + rsi + 29], 10 - pinsrb xmm10, byte ptr [rdx + rsi + 30], 10 - pinsrb xmm6, byte ptr [rdx + rsi + 31], 10 - pinsrb xmm15, byte ptr [rdx + r13 + 28], 11 - pinsrb xmm9, byte ptr [rdx + r13 + 29], 11 - pinsrb xmm10, byte ptr [rdx + r13 + 30], 11 - pinsrb xmm6, byte ptr [rdx + r13 + 31], 11 - pinsrb xmm15, byte ptr [rdx + rbx + 28], 12 - pinsrb xmm9, byte ptr [rdx + rbx + 29], 12 - pinsrb xmm10, byte ptr [rdx + rbx + 30], 12 - pinsrb xmm6, byte ptr [rdx + rbx + 31], 12 - mov rax, r8 - pinsrb xmm15, byte ptr [rdx + r8 + 28], 13 - pinsrb xmm9, byte ptr [rdx + r8 + 29], 13 - pinsrb xmm10, byte ptr [rdx + r8 + 30], 13 - pinsrb xmm6, byte ptr [rdx + r8 + 31], 13 - mov rax, r9 - pinsrb xmm15, byte ptr [rdx + r9 + 28], 14 - pinsrb xmm9, byte ptr [rdx + r9 + 29], 14 - pinsrb xmm10, byte ptr [rdx + r9 + 30], 14 - pinsrb xmm6, byte ptr [rdx + r9 + 31], 14 + pinsrb xmm15, byte ptr [r13 + rsi + 28], 10 + pinsrb xmm9, byte ptr [r13 + rsi + 29], 10 + pinsrb xmm10, byte ptr [r13 + rsi + 30], 10 + pinsrb xmm6, byte ptr [r13 + rsi + 31], 10 + mov rax, r15 + pinsrb xmm15, byte ptr [r13 + r15 + 28], 11 + pinsrb xmm9, byte ptr [r13 + r15 + 29], 11 + pinsrb xmm10, byte ptr [r13 + r15 + 30], 11 + pinsrb xmm6, byte ptr [r13 + r15 + 31], 11 + mov rax, rdx + pinsrb xmm15, byte ptr [r13 + rdx + 28], 12 + pinsrb xmm9, byte ptr [r13 + rdx + 29], 12 + pinsrb xmm10, byte ptr [r13 + rdx + 30], 12 + pinsrb xmm6, byte ptr [r13 + rdx + 31], 12 + mov rax, rcx + pinsrb xmm15, byte ptr [r13 + rcx + 28], 13 + pinsrb xmm9, byte ptr [r13 + rcx + 29], 13 + pinsrb xmm10, byte ptr [r13 + rcx + 30], 13 + pinsrb xmm6, byte ptr [r13 + rcx + 31], 13 mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rax + 28], 15 - pinsrb xmm9, byte ptr [rdx + rax + 29], 15 - pinsrb xmm10, byte ptr [rdx + rax + 30], 15 + pinsrb xmm15, byte ptr [r13 + rax + 28], 14 + pinsrb xmm9, byte ptr [r13 + rax + 29], 14 + pinsrb xmm10, byte ptr [r13 + rax + 30], 14 + pinsrb xmm6, byte ptr [r13 + rax + 31], 14 + mov rax, r12 + pinsrb xmm15, byte ptr [r13 + r12 + 28], 15 + pinsrb xmm9, byte ptr [r13 + r12 + 29], 15 + pinsrb xmm10, byte ptr [r13 + r12 + 30], 15 pcmpgtb xmm15, xmm14 pandn xmm15, xmmword ptr [rip + .LCPI11_19] por xmm15, xmm11 - pinsrb xmm6, byte ptr [rdx + rax + 31], 15 + pinsrb xmm6, byte ptr [r13 + r12 + 31], 15 psubb xmm13, xmmword ptr [rip + .LCPI11_22] por xmm15, xmm13 pcmpgtb xmm9, xmm14 @@ -59402,9 +62103,9 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr por xmm6, xmm15 movdqa xmm0, xmm8 punpcklbw xmm0, xmm6 # xmm0 = xmm0[0],xmm6[0],xmm0[1],xmm6[1],xmm0[2],xmm6[2],xmm0[3],xmm6[3],xmm0[4],xmm6[4],xmm0[5],xmm6[5],xmm0[6],xmm6[6],xmm0[7],xmm6[7] - movdqa xmm3, xmmword ptr [rsp + 192] # 16-byte Reload + movdqa xmm3, xmmword ptr [rsp + 224] # 16-byte Reload movdqa xmm1, xmm3 - movdqa xmm4, xmmword ptr [rsp + 160] # 16-byte Reload + movdqa xmm4, xmmword ptr [rsp + 192] # 16-byte Reload punpcklbw xmm1, xmm4 # xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7] movdqa xmm2, xmm1 punpcklwd xmm2, xmm0 # xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3] @@ -59414,222 +62115,218 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr movdqa xmm0, xmm3 punpcklwd xmm0, xmm8 # xmm0 = xmm0[0],xmm8[0],xmm0[1],xmm8[1],xmm0[2],xmm8[2],xmm0[3],xmm8[3] punpckhwd xmm3, xmm8 # xmm3 = xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7] - mov rcx, qword ptr [rsp + 224] # 8-byte Reload - movdqu xmmword ptr [r15 + 4*rcx + 48], xmm3 - movdqu xmmword ptr [r15 + 4*rcx + 32], xmm0 - movdqu xmmword ptr [r15 + 4*rcx + 16], xmm1 - movdqu xmmword ptr [r15 + 4*rcx], xmm2 + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + movdqu xmmword ptr [r8 + 4*rcx + 48], xmm3 + movdqu xmmword ptr [r8 + 4*rcx + 32], xmm0 + movdqu xmmword ptr [r8 + 4*rcx + 16], xmm1 + movdqu xmmword ptr [r8 + 4*rcx], xmm2 add rcx, 16 mov rax, rcx - cmp rcx, qword ptr [rsp + 256] # 8-byte Folded Reload - jne .LBB11_86 -# %bb.87: - mov r10, qword ptr [rsp + 248] # 8-byte Reload - cmp r10, qword ptr [rsp + 256] # 8-byte Folded Reload - mov r14b, byte ptr [rsp] # 1-byte Reload - mov r13, qword ptr [rsp + 288] # 8-byte Reload - mov rdx, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 136] # 8-byte Reload - jne .LBB11_88 - jmp .LBB11_91 -.LBB11_66: - and r10, -16 - mov rax, r10 + cmp rcx, qword ptr [rsp + 184] # 8-byte Folded Reload + jne .LBB11_223 +# %bb.224: + mov rcx, qword ptr [rsp + 272] # 8-byte Reload + cmp rcx, qword ptr [rsp + 184] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r14b, byte ptr [rsp + 8] # 1-byte Reload + mov r13, qword ptr [rsp + 264] # 8-byte Reload + mov rdi, qword ptr [rsp + 256] # 8-byte Reload + jne .LBB11_146 + jmp .LBB11_150 +.LBB11_225: + and rcx, -16 + mov rax, rcx shl rax, 5 - add rax, rdx - mov qword ptr [rsp + 280], rax # 8-byte Spill - mov qword ptr [rsp + 192], r10 # 8-byte Spill - lea rax, [r15 + 4*r10] - mov qword ptr [rsp + 288], rax # 8-byte Spill - movzx eax, r14b + add rax, r11 + mov qword ptr [rsp + 264], rax # 8-byte Spill + mov qword ptr [rsp + 184], rcx # 8-byte Spill + lea rax, [r12 + 4*rcx] + mov qword ptr [rsp + 112], rax # 8-byte Spill + movzx eax, r13b movd xmm1, eax pxor xmm0, xmm0 pshufb xmm1, xmm0 - movdqa xmmword ptr [rsp + 256], xmm1 # 16-byte Spill + movdqa xmmword ptr [rsp + 272], xmm1 # 16-byte Spill xor eax, eax - mov qword ptr [rsp + 120], r15 # 8-byte Spill - movdqa xmm8, xmmword ptr [rsp + 256] # 16-byte Reload + mov qword ptr [rsp + 136], r12 # 8-byte Spill + movdqa xmm8, xmmword ptr [rsp + 272] # 16-byte Reload .p2align 4, 0x90 -.LBB11_67: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 128], rax # 8-byte Spill +.LBB11_226: # =>This Inner Loop Header: Depth=1 + mov qword ptr [rsp + 144], rax # 8-byte Spill shl rax, 5 - mov r14, rax mov rbx, rax mov r15, rax - mov qword ptr [rsp + 32], rax # 8-byte Spill + mov r14, rax mov r12, rax + mov rdx, rax mov r8, rax - mov r11, rax + mov r13, rax + mov qword ptr [rsp + 104], rax # 8-byte Spill mov r9, rax - mov r10, rax mov rsi, rax mov rdi, rax - movzx ecx, byte ptr [rdx + rax] + movzx ecx, byte ptr [r11 + rax] movd xmm6, ecx - movzx ecx, byte ptr [rdx + rax + 1] + movzx ecx, byte ptr [r11 + rax + 1] movd xmm15, ecx - movzx ecx, byte ptr [rdx + rax + 2] + movzx ecx, byte ptr [r11 + rax + 2] movd xmm5, ecx - movzx ecx, byte ptr [rdx + rax + 3] + movzx ecx, byte ptr [r11 + rax + 3] movd xmm4, ecx - movzx ecx, byte ptr [rdx + rax + 4] + movzx ecx, byte ptr [r11 + rax + 4] movd xmm3, ecx - movzx ecx, byte ptr [rdx + rax + 5] + movzx ecx, byte ptr [r11 + rax + 5] movd xmm7, ecx - movzx ecx, byte ptr [rdx + rax + 6] + movzx ecx, byte ptr [r11 + rax + 6] movd xmm2, ecx - movzx ecx, byte ptr [rdx + rax + 7] + movzx ecx, byte ptr [r11 + rax + 7] movd xmm9, ecx - movzx ecx, byte ptr [rdx + rax + 8] + movzx ecx, byte ptr [r11 + rax + 8] movd xmm0, ecx - movdqa xmmword ptr [rsp + 224], xmm0 # 16-byte Spill - movzx ecx, byte ptr [rdx + rax + 9] + movdqa xmmword ptr [rsp + 240], xmm0 # 16-byte Spill + movzx ecx, byte ptr [r11 + rax + 9] movd xmm10, ecx - movzx ecx, byte ptr [rdx + rax + 10] + movzx ecx, byte ptr [r11 + rax + 10] movd xmm12, ecx - movzx ecx, byte ptr [rdx + rax + 11] + movzx ecx, byte ptr [r11 + rax + 11] movd xmm11, ecx - movzx ecx, byte ptr [rdx + rax + 12] + movzx ecx, byte ptr [r11 + rax + 12] movd xmm13, ecx - movzx ecx, byte ptr [rdx + rax + 13] + movzx ecx, byte ptr [r11 + rax + 13] movd xmm0, ecx - movzx ecx, byte ptr [rdx + rax + 14] + movzx ecx, byte ptr [r11 + rax + 14] movd xmm14, ecx - movzx ecx, byte ptr [rdx + rax + 15] + movzx ecx, byte ptr [r11 + rax + 15] movd xmm1, ecx - movdqa xmmword ptr [rsp + 176], xmm1 # 16-byte Spill + movdqa xmmword ptr [rsp + 208], xmm1 # 16-byte Spill mov qword ptr [rsp + 80], rax # 8-byte Spill - mov r13, rax - or r13, 32 - mov qword ptr [rsp + 40], r13 # 8-byte Spill - or r14, 64 - or rbx, 96 - or r15, 128 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - or rcx, 160 - mov qword ptr [rsp + 32], rcx # 8-byte Spill - or r12, 192 + mov rcx, rax + or rcx, 32 + mov qword ptr [rsp + 56], rcx # 8-byte Spill + or rbx, 64 + mov qword ptr [rsp + 64], rbx # 8-byte Spill + or r15, 96 + or r14, 128 + mov qword ptr [rsp + 160], r14 # 8-byte Spill + or r12, 160 + or rdx, 192 or r8, 224 - or r11, 256 - or r9, 288 - or r10, 320 + mov r10, rax + or r10, 256 + mov r13, qword ptr [rsp + 104] # 8-byte Reload + or r13, 288 + or r9, 320 or rsi, 352 - mov qword ptr [rsp + 88], rsi # 8-byte Spill + mov qword ptr [rsp + 24], rsi # 8-byte Spill mov rsi, rax or rsi, 384 - mov qword ptr [rsp + 112], rsi # 8-byte Spill - or rdi, 416 - mov qword ptr [rsp + 16], rdi # 8-byte Spill - mov rdi, rax + mov qword ptr [rsp + 48], rsi # 8-byte Spill + mov rcx, rax + or rcx, 416 + mov qword ptr [rsp + 16], rcx # 8-byte Spill or rdi, 448 - mov qword ptr [rsp + 24], rdi # 8-byte Spill - mov rdi, rax - or rdi, 480 - mov qword ptr [rsp + 8], rdi # 8-byte Spill - pinsrb xmm6, byte ptr [rdx + r13], 1 - pinsrb xmm6, byte ptr [rdx + r14], 2 - mov qword ptr [rsp + 104], rbx # 8-byte Spill - pinsrb xmm6, byte ptr [rdx + rbx], 3 - pinsrb xmm6, byte ptr [rdx + r15], 4 - pinsrb xmm6, byte ptr [rdx + rcx], 5 - pinsrb xmm6, byte ptr [rdx + r12], 6 - mov qword ptr [rsp + 56], r8 # 8-byte Spill - pinsrb xmm6, byte ptr [rdx + r8], 7 - mov qword ptr [rsp + 72], r11 # 8-byte Spill - pinsrb xmm6, byte ptr [rdx + r11], 8 - mov r11, r9 - mov qword ptr [rsp + 96], r9 # 8-byte Spill - pinsrb xmm6, byte ptr [rdx + r9], 9 - mov r9, r10 - pinsrb xmm6, byte ptr [rdx + r10], 10 - mov r10, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r10], 11 - pinsrb xmm6, byte ptr [rdx + rsi], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax], 13 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r13], 14 - pinsrb xmm6, byte ptr [rdx + rdi], 15 + or rax, 480 + mov qword ptr [rsp + 32], rax # 8-byte Spill + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rcx], 1 + pinsrb xmm6, byte ptr [r11 + rbx], 2 + mov qword ptr [rsp + 192], r15 # 8-byte Spill + pinsrb xmm6, byte ptr [r11 + r15], 3 + pinsrb xmm6, byte ptr [r11 + r14], 4 + mov rax, r12 + mov qword ptr [rsp + 128], r12 # 8-byte Spill + pinsrb xmm6, byte ptr [r11 + r12], 5 + pinsrb xmm6, byte ptr [r11 + rdx], 6 + mov rbx, r8 + pinsrb xmm6, byte ptr [r11 + r8], 7 + mov qword ptr [rsp + 72], r10 # 8-byte Spill + pinsrb xmm6, byte ptr [r11 + r10], 8 + pinsrb xmm6, byte ptr [r11 + r13], 9 + mov r8, r9 + pinsrb xmm6, byte ptr [r11 + r9], 10 + mov r9, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r9], 11 + pinsrb xmm6, byte ptr [r11 + rsi], 12 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r12], 13 + pinsrb xmm6, byte ptr [r11 + rdi], 14 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r14], 15 pmaxub xmm6, xmm8 pcmpeqb xmm6, xmm8 - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rdi + 1], 1 - pinsrb xmm15, byte ptr [rdx + r14 + 1], 2 - pinsrb xmm15, byte ptr [rdx + rbx + 1], 3 - pinsrb xmm15, byte ptr [rdx + r15 + 1], 4 - mov rbx, r15 - pinsrb xmm15, byte ptr [rdx + rcx + 1], 5 - pinsrb xmm15, byte ptr [rdx + r12 + 1], 6 - mov r15, r12 - pinsrb xmm15, byte ptr [rdx + r8 + 1], 7 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r13 + 1], 8 - pinsrb xmm15, byte ptr [rdx + r11 + 1], 9 - pinsrb xmm15, byte ptr [rdx + r9 + 1], 10 - mov qword ptr [rsp + 64], r9 # 8-byte Spill - pinsrb xmm15, byte ptr [rdx + r10 + 1], 11 - mov rcx, r10 - pinsrb xmm15, byte ptr [rdx + rsi + 1], 12 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r12 + 1], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rax + 1], 14 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rax + 1], 15 + pinsrb xmm15, byte ptr [r11 + rcx + 1], 1 + mov rcx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rcx + 1], 2 + pinsrb xmm15, byte ptr [r11 + r15 + 1], 3 + mov rcx, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rcx + 1], 4 + pinsrb xmm15, byte ptr [r11 + rax + 1], 5 + pinsrb xmm15, byte ptr [r11 + rdx + 1], 6 + mov rax, rdx + pinsrb xmm15, byte ptr [r11 + rbx + 1], 7 + pinsrb xmm15, byte ptr [r11 + r10 + 1], 8 + pinsrb xmm15, byte ptr [r11 + r13 + 1], 9 + mov r15, r13 + pinsrb xmm15, byte ptr [r11 + r8 + 1], 10 + mov qword ptr [rsp + 40], r8 # 8-byte Spill + pinsrb xmm15, byte ptr [r11 + r9 + 1], 11 + pinsrb xmm15, byte ptr [r11 + rsi + 1], 12 + pinsrb xmm15, byte ptr [r11 + r12 + 1], 13 + pinsrb xmm15, byte ptr [r11 + rdi + 1], 14 + mov qword ptr [rsp + 96], rdi # 8-byte Spill + pinsrb xmm15, byte ptr [r11 + r14 + 1], 15 pmaxub xmm15, xmm8 pcmpeqb xmm15, xmm8 movdqa xmm1, xmmword ptr [rip + .LCPI11_16] # xmm1 = [2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2] pand xmm15, xmm1 psubb xmm15, xmm6 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 16] + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [r11 + rdx + 16] movd xmm1, esi - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rdi + 2], 1 - mov r8, r14 - mov qword ptr [rsp + 48], r14 # 8-byte Spill - pinsrb xmm5, byte ptr [rdx + r14 + 2], 2 - mov r14, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r14 + 2], 3 - mov r10, rbx - pinsrb xmm5, byte ptr [rdx + rbx + 2], 4 - mov rax, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rax + 2], 5 - mov rbx, r15 - pinsrb xmm5, byte ptr [rdx + r15 + 2], 6 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rsi + 2], 7 - mov r11, r13 - pinsrb xmm5, byte ptr [rdx + r13 + 2], 8 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r15 + 2], 9 - pinsrb xmm5, byte ptr [rdx + r9 + 2], 10 - pinsrb xmm5, byte ptr [rdx + rcx + 2], 11 - mov rcx, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rcx + 2], 12 - mov r13, r12 - pinsrb xmm5, byte ptr [rdx + r12 + 2], 13 - mov r9, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r9 + 2], 14 - mov r12, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r12 + 2], 15 - pinsrb xmm4, byte ptr [rdx + rdi + 3], 1 - pinsrb xmm4, byte ptr [rdx + r8 + 3], 2 - pinsrb xmm4, byte ptr [rdx + r14 + 3], 3 - pinsrb xmm4, byte ptr [rdx + r10 + 3], 4 - pinsrb xmm4, byte ptr [rdx + rax + 3], 5 - pinsrb xmm4, byte ptr [rdx + rbx + 3], 6 - pinsrb xmm4, byte ptr [rdx + rsi + 3], 7 - pinsrb xmm4, byte ptr [rdx + r11 + 3], 8 - pinsrb xmm4, byte ptr [rdx + r15 + 3], 9 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r11 + 3], 10 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm4, byte ptr [rdx + r8 + 3], 11 - pinsrb xmm4, byte ptr [rdx + rcx + 3], 12 - pinsrb xmm4, byte ptr [rdx + r13 + 3], 13 - pinsrb xmm4, byte ptr [rdx + r9 + 3], 14 - pinsrb xmm4, byte ptr [rdx + r12 + 3], 15 + mov rdx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rdx + 2], 1 + mov r14, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r14 + 2], 2 + mov r9, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r9 + 2], 3 + mov r10, rcx + pinsrb xmm5, byte ptr [r11 + rcx + 2], 4 + mov r13, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r13 + 2], 5 + pinsrb xmm5, byte ptr [r11 + rax + 2], 6 + pinsrb xmm5, byte ptr [r11 + rbx + 2], 7 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rsi + 2], 8 + pinsrb xmm5, byte ptr [r11 + r15 + 2], 9 + pinsrb xmm5, byte ptr [r11 + r8 + 2], 10 + mov r8, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r8 + 2], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rcx + 2], 12 + pinsrb xmm5, byte ptr [r11 + r12 + 2], 13 + pinsrb xmm5, byte ptr [r11 + rdi + 2], 14 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rdi + 2], 15 + pinsrb xmm4, byte ptr [r11 + rdx + 3], 1 + pinsrb xmm4, byte ptr [r11 + r14 + 3], 2 + pinsrb xmm4, byte ptr [r11 + r9 + 3], 3 + pinsrb xmm4, byte ptr [r11 + r10 + 3], 4 + pinsrb xmm4, byte ptr [r11 + r13 + 3], 5 + pinsrb xmm4, byte ptr [r11 + rax + 3], 6 + pinsrb xmm4, byte ptr [r11 + rbx + 3], 7 + mov qword ptr [rsp + 88], rbx # 8-byte Spill + pinsrb xmm4, byte ptr [r11 + rsi + 3], 8 + pinsrb xmm4, byte ptr [r11 + r15 + 3], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdx + 3], 10 + pinsrb xmm4, byte ptr [r11 + r8 + 3], 11 + pinsrb xmm4, byte ptr [r11 + rcx + 3], 12 + mov r8, rcx + pinsrb xmm4, byte ptr [r11 + r12 + 3], 13 + mov rcx, r12 + mov rdx, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm4, byte ptr [r11 + rdx + 3], 14 + pinsrb xmm4, byte ptr [r11 + rdi + 3], 15 pmaxub xmm5, xmm8 pcmpeqb xmm5, xmm8 movdqa xmm6, xmmword ptr [rip + .LCPI11_17] # xmm6 = [4,4,4,4,4,4,4,4,4,4,4,4,4,4,4,4] @@ -59639,80 +62336,75 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr movdqa xmm6, xmmword ptr [rip + .LCPI11_18] # xmm6 = [8,8,8,8,8,8,8,8,8,8,8,8,8,8,8,8] pand xmm4, xmm6 por xmm4, xmm5 - mov rcx, qword ptr [rsp + 80] # 8-byte Reload - movzx esi, byte ptr [rdx + rcx + 17] + mov rdx, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [r11 + rdx + 17] movd xmm5, esi por xmm4, xmm15 - movzx esi, byte ptr [rdx + rcx + 18] + movzx esi, byte ptr [r11 + rdx + 18] movd xmm15, esi - mov r14, rdi - pinsrb xmm3, byte ptr [rdx + rdi + 4], 1 - mov r13, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r13 + 4], 2 - mov r12, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r12 + 4], 3 - mov qword ptr [rsp + 144], r10 # 8-byte Spill - pinsrb xmm3, byte ptr [rdx + r10 + 4], 4 - pinsrb xmm3, byte ptr [rdx + rax + 4], 5 - pinsrb xmm3, byte ptr [rdx + rbx + 4], 6 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rcx + 4], 7 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rcx + 4], 8 - pinsrb xmm3, byte ptr [rdx + r15 + 4], 9 - mov rsi, r11 - pinsrb xmm3, byte ptr [rdx + r11 + 4], 10 - pinsrb xmm3, byte ptr [rdx + r8 + 4], 11 - mov r9, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r9 + 4], 12 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rcx + 4], 13 - mov rdi, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rdi + 4], 14 - mov r11, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r11 + 4], 15 - pinsrb xmm7, byte ptr [rdx + r14 + 5], 1 - pinsrb xmm7, byte ptr [rdx + r13 + 5], 2 - pinsrb xmm7, byte ptr [rdx + r12 + 5], 3 - pinsrb xmm7, byte ptr [rdx + r10 + 5], 4 - pinsrb xmm7, byte ptr [rdx + rax + 5], 5 - pinsrb xmm7, byte ptr [rdx + rbx + 5], 6 - mov rcx, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rcx + 5], 7 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rcx + 5], 8 - pinsrb xmm7, byte ptr [rdx + r15 + 5], 9 - pinsrb xmm7, byte ptr [rdx + rsi + 5], 10 - pinsrb xmm7, byte ptr [rdx + r8 + 5], 11 - pinsrb xmm7, byte ptr [rdx + r9 + 5], 12 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm7, byte ptr [rdx + rcx + 5], 13 - pinsrb xmm7, byte ptr [rdx + rdi + 5], 14 - pinsrb xmm7, byte ptr [rdx + r11 + 5], 15 - pinsrb xmm2, byte ptr [rdx + r14 + 6], 1 - pinsrb xmm2, byte ptr [rdx + r13 + 6], 2 - pinsrb xmm2, byte ptr [rdx + r12 + 6], 3 - pinsrb xmm2, byte ptr [rdx + r10 + 6], 4 - pinsrb xmm2, byte ptr [rdx + rax + 6], 5 - mov r10, rax - pinsrb xmm2, byte ptr [rdx + rbx + 6], 6 - mov r13, rbx - mov qword ptr [rsp + 160], rbx # 8-byte Spill - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 6], 7 - mov r14, rax + mov r14, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + r14 + 4], 1 + mov rdx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rdx + 4], 2 + pinsrb xmm3, byte ptr [r11 + r9 + 4], 3 + pinsrb xmm3, byte ptr [r11 + r10 + 4], 4 + mov r12, r13 + pinsrb xmm3, byte ptr [r11 + r13 + 4], 5 + mov qword ptr [rsp + 120], rax # 8-byte Spill + pinsrb xmm3, byte ptr [r11 + rax + 4], 6 + pinsrb xmm3, byte ptr [r11 + rbx + 4], 7 mov rbx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rbx + 6], 8 - pinsrb xmm2, byte ptr [rdx + r15 + 6], 9 - mov r11, r15 - pinsrb xmm2, byte ptr [rdx + rsi + 6], 10 - pinsrb xmm2, byte ptr [rdx + r8 + 6], 11 - mov r12, r8 - pinsrb xmm2, byte ptr [rdx + r9 + 6], 12 - pinsrb xmm2, byte ptr [rdx + rcx + 6], 13 - pinsrb xmm2, byte ptr [rdx + rdi + 6], 14 - mov r15, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r15 + 6], 15 + pinsrb xmm3, byte ptr [r11 + rbx + 4], 8 + mov qword ptr [rsp + 104], r15 # 8-byte Spill + pinsrb xmm3, byte ptr [r11 + r15 + 4], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rsi + 4], 10 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rdx + 4], 11 + pinsrb xmm3, byte ptr [r11 + r8 + 4], 12 + pinsrb xmm3, byte ptr [r11 + rcx + 4], 13 + mov rdi, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rdi + 4], 14 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rcx + 4], 15 + pinsrb xmm7, byte ptr [r11 + r14 + 5], 1 + mov r10, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + r10 + 5], 2 + pinsrb xmm7, byte ptr [r11 + r9 + 5], 3 + mov r13, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + r13 + 5], 4 + pinsrb xmm7, byte ptr [r11 + r12 + 5], 5 + pinsrb xmm7, byte ptr [r11 + rax + 5], 6 + mov r13, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + r13 + 5], 7 + pinsrb xmm7, byte ptr [r11 + rbx + 5], 8 + pinsrb xmm7, byte ptr [r11 + r15 + 5], 9 + pinsrb xmm7, byte ptr [r11 + rsi + 5], 10 + pinsrb xmm7, byte ptr [r11 + rdx + 5], 11 + pinsrb xmm7, byte ptr [r11 + r8 + 5], 12 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm7, byte ptr [r11 + r12 + 5], 13 + pinsrb xmm7, byte ptr [r11 + rdi + 5], 14 + pinsrb xmm7, byte ptr [r11 + rcx + 5], 15 + pinsrb xmm2, byte ptr [r11 + r14 + 6], 1 + pinsrb xmm2, byte ptr [r11 + r10 + 6], 2 + pinsrb xmm2, byte ptr [r11 + r9 + 6], 3 + mov r10, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r10 + 6], 4 + mov r9, qword ptr [rsp + 128] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r9 + 6], 5 + pinsrb xmm2, byte ptr [r11 + rax + 6], 6 + pinsrb xmm2, byte ptr [r11 + r13 + 6], 7 + pinsrb xmm2, byte ptr [r11 + rbx + 6], 8 + pinsrb xmm2, byte ptr [r11 + r15 + 6], 9 + pinsrb xmm2, byte ptr [r11 + rsi + 6], 10 + pinsrb xmm2, byte ptr [r11 + rdx + 6], 11 + pinsrb xmm2, byte ptr [r11 + r8 + 6], 12 + mov r8, r12 + pinsrb xmm2, byte ptr [r11 + r12 + 6], 13 + pinsrb xmm2, byte ptr [r11 + rdi + 6], 14 + mov r14, rdi + pinsrb xmm2, byte ptr [r11 + rcx + 6], 15 pmaxub xmm3, xmm8 pcmpeqb xmm3, xmm8 movdqa xmm6, xmmword ptr [rip + .LCPI11_19] # xmm6 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] @@ -59723,1583 +62415,680 @@ comparison_greater_equal_scalar_arr_sse4: # @comparison_greater_equal_scalar_arr pand xmm7, xmm6 por xmm7, xmm3 mov rax, qword ptr [rsp + 80] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 19] + movzx esi, byte ptr [r11 + rax + 19] movd xmm3, esi pmaxub xmm2, xmm8 pcmpeqb xmm2, xmm8 movdqa xmm6, xmmword ptr [rip + .LCPI11_21] # xmm6 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] pand xmm2, xmm6 por xmm2, xmm7 - movzx esi, byte ptr [rdx + rax + 20] + movzx esi, byte ptr [r11 + rax + 20] movd xmm6, esi por xmm2, xmm4 - movzx esi, byte ptr [rdx + rax + 21] + movzx esi, byte ptr [r11 + rax + 21] movd xmm4, esi - mov rdi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rdi + 7], 1 - mov rax, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 7], 2 - mov rax, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + rax + 7], 3 - mov r8, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r8 + 7], 4 - pinsrb xmm9, byte ptr [rdx + r10 + 7], 5 - pinsrb xmm9, byte ptr [rdx + r13 + 7], 6 - pinsrb xmm9, byte ptr [rdx + r14 + 7], 7 - pinsrb xmm9, byte ptr [rdx + rbx + 7], 8 - pinsrb xmm9, byte ptr [rdx + r11 + 7], 9 - mov rcx, r11 - mov r11, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r11 + 7], 10 - pinsrb xmm9, byte ptr [rdx + r12 + 7], 11 - pinsrb xmm9, byte ptr [rdx + r9 + 7], 12 - mov r13, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r13 + 7], 13 - mov r12, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm9, byte ptr [rdx + r12 + 7], 14 - pinsrb xmm9, byte ptr [rdx + r15 + 7], 15 + mov rdi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rdi + 7], 1 + mov r15, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r15 + 7], 2 + mov rax, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rax + 7], 3 + pinsrb xmm9, byte ptr [r11 + r10 + 7], 4 + pinsrb xmm9, byte ptr [r11 + r9 + 7], 5 + mov r13, r9 + mov r12, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r12 + 7], 6 + mov rbx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rbx + 7], 7 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rcx + 7], 8 + mov r9, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r9 + 7], 9 + mov rdx, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rdx + 7], 10 + mov r10, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r10 + 7], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + rsi + 7], 12 + pinsrb xmm9, byte ptr [r11 + r8 + 7], 13 + pinsrb xmm9, byte ptr [r11 + r14 + 7], 14 + mov r14, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm9, byte ptr [r11 + r14 + 7], 15 pmaxub xmm9, xmm8 pcmpeqb xmm9, xmm8 movdqa xmm7, xmmword ptr [rip + .LCPI11_6] # xmm7 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] pand xmm9, xmm7 por xmm9, xmm2 - movdqa xmmword ptr [rsp + 208], xmm9 # 16-byte Spill - mov r9, qword ptr [rsp + 80] # 8-byte Reload - movzx esi, byte ptr [rdx + r9 + 22] + movdqa xmmword ptr [rsp + 224], xmm9 # 16-byte Spill + mov rsi, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [r11 + rsi + 22] movd xmm7, esi - movdqa xmm2, xmmword ptr [rsp + 224] # 16-byte Reload - pinsrb xmm2, byte ptr [rdx + rdi + 8], 1 - mov r14, rdi - mov rdi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rdi + 8], 2 - pinsrb xmm2, byte ptr [rdx + rax + 8], 3 - mov r15, rax - pinsrb xmm2, byte ptr [rdx + r8 + 8], 4 - pinsrb xmm2, byte ptr [rdx + r10 + 8], 5 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rax + 8], 6 - mov rsi, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rsi + 8], 7 - mov rbx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rbx + 8], 8 - pinsrb xmm2, byte ptr [rdx + rcx + 8], 9 - pinsrb xmm2, byte ptr [rdx + r11 + 8], 10 - mov rcx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + rcx + 8], 11 - mov r11, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r11 + 8], 12 - mov rsi, r13 - pinsrb xmm2, byte ptr [rdx + r13 + 8], 13 - pinsrb xmm2, byte ptr [rdx + r12 + 8], 14 - mov r13, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm2, byte ptr [rdx + r13 + 8], 15 - pmaxub xmm2, xmm8 - pcmpeqb xmm2, xmm8 - pinsrb xmm10, byte ptr [rdx + r14 + 9], 1 - pinsrb xmm10, byte ptr [rdx + rdi + 9], 2 - pinsrb xmm10, byte ptr [rdx + r15 + 9], 3 - mov r14, r15 - pinsrb xmm10, byte ptr [rdx + r8 + 9], 4 - mov r15, r8 - pinsrb xmm10, byte ptr [rdx + r10 + 9], 5 - pinsrb xmm10, byte ptr [rdx + rax + 9], 6 - mov r8, rax - mov rax, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rax + 9], 7 - pinsrb xmm10, byte ptr [rdx + rbx + 9], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rax + 9], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm10, byte ptr [rdx + rax + 9], 10 - pinsrb xmm10, byte ptr [rdx + rcx + 9], 11 - mov rcx, r11 - pinsrb xmm10, byte ptr [rdx + r11 + 9], 12 - pinsrb xmm10, byte ptr [rdx + rsi + 9], 13 - pinsrb xmm10, byte ptr [rdx + r12 + 9], 14 - pinsrb xmm10, byte ptr [rdx + r13 + 9], 15 - pmaxub xmm10, xmm8 - pcmpeqb xmm10, xmm8 - pand xmm10, xmmword ptr [rip + .LCPI11_16] - psubb xmm10, xmm2 - movzx esi, byte ptr [rdx + r9 + 23] - movd xmm2, esi - mov r11, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + r11 + 10], 1 - pinsrb xmm12, byte ptr [rdx + rdi + 10], 2 - mov r10, rdi - mov rsi, r14 - pinsrb xmm12, byte ptr [rdx + r14 + 10], 3 - pinsrb xmm12, byte ptr [rdx + r15 + 10], 4 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + r14 + 10], 5 - pinsrb xmm12, byte ptr [rdx + r8 + 10], 6 - mov rbx, r8 - mov r15, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + r15 + 10], 7 - mov r13, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + r13 + 10], 8 - mov rdi, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rdi + 10], 9 - pinsrb xmm12, byte ptr [rdx + rax + 10], 10 - mov r8, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + r8 + 10], 11 - mov r9, rcx - pinsrb xmm12, byte ptr [rdx + rcx + 10], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rax + 10], 13 - pinsrb xmm12, byte ptr [rdx + r12 + 10], 14 - mov rcx, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm12, byte ptr [rdx + rcx + 10], 15 - pinsrb xmm11, byte ptr [rdx + r11 + 11], 1 - pinsrb xmm11, byte ptr [rdx + r10 + 11], 2 - pinsrb xmm11, byte ptr [rdx + rsi + 11], 3 - mov r10, rsi - mov rsi, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rsi + 11], 4 - pinsrb xmm11, byte ptr [rdx + r14 + 11], 5 - pinsrb xmm11, byte ptr [rdx + rbx + 11], 6 - pinsrb xmm11, byte ptr [rdx + r15 + 11], 7 - mov r14, r15 - pinsrb xmm11, byte ptr [rdx + r13 + 11], 8 - pinsrb xmm11, byte ptr [rdx + rdi + 11], 9 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rbx + 11], 10 - pinsrb xmm11, byte ptr [rdx + r8 + 11], 11 - pinsrb xmm11, byte ptr [rdx + r9 + 11], 12 - pinsrb xmm11, byte ptr [rdx + rax + 11], 13 - pinsrb xmm11, byte ptr [rdx + r12 + 11], 14 - pinsrb xmm11, byte ptr [rdx + rcx + 11], 15 - pmaxub xmm12, xmm8 - pcmpeqb xmm12, xmm8 - pand xmm12, xmmword ptr [rip + .LCPI11_17] - pmaxub xmm11, xmm8 - pcmpeqb xmm11, xmm8 - pand xmm11, xmmword ptr [rip + .LCPI11_18] - por xmm11, xmm12 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 24] - movd xmm9, esi - por xmm11, xmm10 - movzx esi, byte ptr [rdx + rax + 25] - movd xmm12, esi - pinsrb xmm13, byte ptr [rdx + r11 + 12], 1 - mov r12, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + r12 + 12], 2 - mov r11, r10 - pinsrb xmm13, byte ptr [rdx + r10 + 12], 3 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rdi + 12], 4 - mov r15, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + r15 + 12], 5 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + r10 + 12], 6 - pinsrb xmm13, byte ptr [rdx + r14 + 12], 7 - pinsrb xmm13, byte ptr [rdx + r13 + 12], 8 - mov rcx, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rcx + 12], 9 - pinsrb xmm13, byte ptr [rdx + rbx + 12], 10 - pinsrb xmm13, byte ptr [rdx + r8 + 12], 11 - pinsrb xmm13, byte ptr [rdx + r9 + 12], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rax + 12], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rax + 12], 14 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm13, byte ptr [rdx + rsi + 12], 15 - mov rax, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 13], 1 - pinsrb xmm0, byte ptr [rdx + r12 + 13], 2 - pinsrb xmm0, byte ptr [rdx + r11 + 13], 3 - pinsrb xmm0, byte ptr [rdx + rdi + 13], 4 - pinsrb xmm0, byte ptr [rdx + r15 + 13], 5 - pinsrb xmm0, byte ptr [rdx + r10 + 13], 6 - pinsrb xmm0, byte ptr [rdx + r14 + 13], 7 - pinsrb xmm0, byte ptr [rdx + r13 + 13], 8 - pinsrb xmm0, byte ptr [rdx + rcx + 13], 9 - pinsrb xmm0, byte ptr [rdx + rbx + 13], 10 - pinsrb xmm0, byte ptr [rdx + r8 + 13], 11 - pinsrb xmm0, byte ptr [rdx + r9 + 13], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 13], 13 - mov rax, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 13], 14 - pinsrb xmm0, byte ptr [rdx + rsi + 13], 15 - mov rax, rsi - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rsi + 14], 1 - pinsrb xmm14, byte ptr [rdx + r12 + 14], 2 - pinsrb xmm14, byte ptr [rdx + r11 + 14], 3 - pinsrb xmm14, byte ptr [rdx + rdi + 14], 4 - pinsrb xmm14, byte ptr [rdx + r15 + 14], 5 - pinsrb xmm14, byte ptr [rdx + r10 + 14], 6 - pinsrb xmm14, byte ptr [rdx + r14 + 14], 7 - mov r15, r14 - pinsrb xmm14, byte ptr [rdx + r13 + 14], 8 - pinsrb xmm14, byte ptr [rdx + rcx + 14], 9 - mov r14, rcx - pinsrb xmm14, byte ptr [rdx + rbx + 14], 10 - pinsrb xmm14, byte ptr [rdx + r8 + 14], 11 - pinsrb xmm14, byte ptr [rdx + r9 + 14], 12 - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + rcx + 14], 13 - mov r13, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm14, byte ptr [rdx + r13 + 14], 14 - pinsrb xmm14, byte ptr [rdx + rax + 14], 15 - pmaxub xmm13, xmm8 - pcmpeqb xmm13, xmm8 - pand xmm13, xmmword ptr [rip + .LCPI11_19] - pmaxub xmm0, xmm8 - pcmpeqb xmm0, xmm8 - pand xmm0, xmmword ptr [rip + .LCPI11_20] - por xmm0, xmm13 - mov r12, qword ptr [rsp + 80] # 8-byte Reload - movzx esi, byte ptr [rdx + r12 + 26] - movd xmm13, esi - pmaxub xmm14, xmm8 - pcmpeqb xmm14, xmm8 - pand xmm14, xmmword ptr [rip + .LCPI11_21] - por xmm14, xmm0 - movzx esi, byte ptr [rdx + r12 + 27] - movd xmm10, esi - por xmm14, xmm11 - movzx esi, byte ptr [rdx + r12 + 28] - movd xmm11, esi - movdqa xmm0, xmmword ptr [rsp + 176] # 16-byte Reload - mov rcx, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rcx + 15], 1 + movdqa xmm2, xmmword ptr [rsp + 240] # 16-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 8], 1 + mov r8, rdi + pinsrb xmm2, byte ptr [r11 + r15 + 8], 2 + pinsrb xmm2, byte ptr [r11 + rax + 8], 3 + mov rdi, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 8], 4 + pinsrb xmm2, byte ptr [r11 + r13 + 8], 5 + pinsrb xmm2, byte ptr [r11 + r12 + 8], 6 + pinsrb xmm2, byte ptr [r11 + rbx + 8], 7 + pinsrb xmm2, byte ptr [r11 + rcx + 8], 8 + mov rcx, r9 + pinsrb xmm2, byte ptr [r11 + r9 + 8], 9 + pinsrb xmm2, byte ptr [r11 + rdx + 8], 10 + mov rdx, r10 + pinsrb xmm2, byte ptr [r11 + r10 + 8], 11 mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 15], 2 - mov rdi, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rdi + 15], 3 - mov r9, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r9 + 15], 4 - mov r10, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r10 + 15], 5 - mov rax, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 15], 6 - pinsrb xmm0, byte ptr [rdx + r15 + 15], 7 - mov rax, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rax + 15], 8 - pinsrb xmm0, byte ptr [rdx + r14 + 15], 9 - mov rbx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rbx + 15], 10 - pinsrb xmm0, byte ptr [rdx + r8 + 15], 11 - mov r8, qword ptr [rsp + 112] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r8 + 15], 12 + pinsrb xmm2, byte ptr [r11 + rsi + 8], 12 mov rsi, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + rsi + 15], 13 - pinsrb xmm0, byte ptr [rdx + r13 + 15], 14 - mov r11, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm0, byte ptr [rdx + r11 + 15], 15 - pmaxub xmm0, xmm8 - pcmpeqb xmm0, xmm8 - pand xmm0, xmmword ptr [rip + .LCPI11_6] - por xmm0, xmm14 - movdqa xmmword ptr [rsp + 176], xmm0 # 16-byte Spill - movzx esi, byte ptr [rdx + r12 + 29] - movd xmm14, esi - pinsrb xmm1, byte ptr [rdx + rcx + 16], 1 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rsi + 16], 2 - mov r12, rsi - pinsrb xmm1, byte ptr [rdx + rdi + 16], 3 - pinsrb xmm1, byte ptr [rdx + r9 + 16], 4 - pinsrb xmm1, byte ptr [rdx + r10 + 16], 5 - mov r9, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r9 + 16], 6 - pinsrb xmm1, byte ptr [rdx + r15 + 16], 7 - pinsrb xmm1, byte ptr [rdx + rax + 16], 8 - pinsrb xmm1, byte ptr [rdx + r14 + 16], 9 - pinsrb xmm1, byte ptr [rdx + rbx + 16], 10 - mov r14, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + r14 + 16], 11 - pinsrb xmm1, byte ptr [rdx + r8 + 16], 12 - mov r10, r8 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm1, byte ptr [rdx + rax + 16], 13 - pinsrb xmm1, byte ptr [rdx + r13 + 16], 14 - mov rsi, r11 - pinsrb xmm1, byte ptr [rdx + r11 + 16], 15 - pmaxub xmm1, xmm8 - pcmpeqb xmm1, xmm8 - pinsrb xmm5, byte ptr [rdx + rcx + 17], 1 - pinsrb xmm5, byte ptr [rdx + r12 + 17], 2 - mov r11, r12 - pinsrb xmm5, byte ptr [rdx + rdi + 17], 3 - mov rdi, qword ptr [rsp + 144] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rdi + 17], 4 - mov rcx, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rcx + 17], 5 - pinsrb xmm5, byte ptr [rdx + r9 + 17], 6 - pinsrb xmm5, byte ptr [rdx + r15 + 17], 7 - mov r9, r15 - mov rcx, qword ptr [rsp + 72] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + rcx + 17], 8 - mov r15, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm5, byte ptr [rdx + r15 + 17], 9 - pinsrb xmm5, byte ptr [rdx + rbx + 17], 10 - mov r8, r14 - pinsrb xmm5, byte ptr [rdx + r14 + 17], 11 - pinsrb xmm5, byte ptr [rdx + r10 + 17], 12 - mov r12, r10 - pinsrb xmm5, byte ptr [rdx + rax + 17], 13 - pinsrb xmm5, byte ptr [rdx + r13 + 17], 14 - pinsrb xmm5, byte ptr [rdx + rsi + 17], 15 - pmaxub xmm5, xmm8 - pcmpeqb xmm5, xmm8 - pand xmm5, xmmword ptr [rip + .LCPI11_16] - psubb xmm5, xmm1 - mov rax, qword ptr [rsp + 80] # 8-byte Reload - movzx esi, byte ptr [rdx + rax + 30] - movd xmm1, esi - mov rsi, qword ptr [rsp + 40] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rsi + 18], 1 - pinsrb xmm3, byte ptr [rdx + rsi + 19], 1 - pinsrb xmm6, byte ptr [rdx + rsi + 20], 1 - pinsrb xmm4, byte ptr [rdx + rsi + 21], 1 - pinsrb xmm7, byte ptr [rdx + rsi + 22], 1 - pinsrb xmm2, byte ptr [rdx + rsi + 23], 1 - pinsrb xmm9, byte ptr [rdx + rsi + 24], 1 - pinsrb xmm12, byte ptr [rdx + rsi + 25], 1 - pinsrb xmm13, byte ptr [rdx + rsi + 26], 1 - pinsrb xmm10, byte ptr [rdx + rsi + 27], 1 - pinsrb xmm11, byte ptr [rdx + rsi + 28], 1 - pinsrb xmm14, byte ptr [rdx + rsi + 29], 1 - pinsrb xmm1, byte ptr [rdx + rsi + 30], 1 - movzx eax, byte ptr [rdx + rax + 31] - movd xmm0, eax - pinsrb xmm0, byte ptr [rdx + rsi + 31], 1 - pinsrb xmm15, byte ptr [rdx + r11 + 18], 2 - mov r11, qword ptr [rsp + 104] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r11 + 18], 3 - pinsrb xmm15, byte ptr [rdx + rdi + 18], 4 - mov r14, qword ptr [rsp + 32] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r14 + 18], 5 - mov r10, qword ptr [rsp + 160] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r10 + 18], 6 - pinsrb xmm15, byte ptr [rdx + r9 + 18], 7 - mov rsi, rcx - pinsrb xmm15, byte ptr [rdx + rcx + 18], 8 - pinsrb xmm15, byte ptr [rdx + r15 + 18], 9 - mov rcx, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rcx + 18], 10 - pinsrb xmm15, byte ptr [rdx + r8 + 18], 11 - pinsrb xmm15, byte ptr [rdx + r12 + 18], 12 - mov rax, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rax + 18], 13 - mov rbx, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + rbx + 18], 14 - mov r13, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm15, byte ptr [rdx + r13 + 18], 15 - mov rbx, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rbx + 19], 2 - pinsrb xmm3, byte ptr [rdx + r11 + 19], 3 - pinsrb xmm3, byte ptr [rdx + rdi + 19], 4 - pinsrb xmm3, byte ptr [rdx + r14 + 19], 5 - pinsrb xmm3, byte ptr [rdx + r10 + 19], 6 - mov r13, r10 - pinsrb xmm3, byte ptr [rdx + r9 + 19], 7 - pinsrb xmm3, byte ptr [rdx + rsi + 19], 8 - mov r10, rsi - pinsrb xmm3, byte ptr [rdx + r15 + 19], 9 - pinsrb xmm3, byte ptr [rdx + rcx + 19], 10 - pinsrb xmm3, byte ptr [rdx + r8 + 19], 11 - mov rcx, r12 - pinsrb xmm3, byte ptr [rdx + r12 + 19], 12 - pinsrb xmm3, byte ptr [rdx + rax + 19], 13 - mov r8, qword ptr [rsp + 24] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + r8 + 19], 14 - mov rax, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm3, byte ptr [rdx + rax + 19], 15 - mov rsi, qword ptr [rsp + 48] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 20], 2 - pinsrb xmm4, byte ptr [rdx + rsi + 21], 2 - pinsrb xmm7, byte ptr [rdx + rsi + 22], 2 - pinsrb xmm2, byte ptr [rdx + rsi + 23], 2 - pinsrb xmm9, byte ptr [rdx + rsi + 24], 2 - pinsrb xmm12, byte ptr [rdx + rsi + 25], 2 - pinsrb xmm13, byte ptr [rdx + rsi + 26], 2 - pinsrb xmm10, byte ptr [rdx + rsi + 27], 2 - pinsrb xmm11, byte ptr [rdx + rsi + 28], 2 - pinsrb xmm14, byte ptr [rdx + rsi + 29], 2 - pinsrb xmm1, byte ptr [rdx + rsi + 30], 2 - pmaxub xmm15, xmm8 - pcmpeqb xmm15, xmm8 - pand xmm15, xmmword ptr [rip + .LCPI11_17] - pmaxub xmm3, xmm8 - pcmpeqb xmm3, xmm8 - pand xmm3, xmmword ptr [rip + .LCPI11_18] - por xmm3, xmm15 - pinsrb xmm0, byte ptr [rdx + rsi + 31], 2 - por xmm3, xmm5 - pinsrb xmm6, byte ptr [rdx + r11 + 20], 3 - pinsrb xmm6, byte ptr [rdx + rdi + 20], 4 - mov r9, r14 - pinsrb xmm6, byte ptr [rdx + r14 + 20], 5 - pinsrb xmm6, byte ptr [rdx + r13 + 20], 6 - mov r14, qword ptr [rsp + 56] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r14 + 20], 7 - pinsrb xmm6, byte ptr [rdx + r10 + 20], 8 - pinsrb xmm6, byte ptr [rdx + r15 + 20], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rax + 20], 10 - mov rbx, qword ptr [rsp + 88] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rbx + 20], 11 - pinsrb xmm6, byte ptr [rdx + r12 + 20], 12 - mov r12, qword ptr [rsp + 16] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + r12 + 20], 13 - pinsrb xmm6, byte ptr [rdx + r8 + 20], 14 - mov rsi, qword ptr [rsp + 8] # 8-byte Reload - pinsrb xmm6, byte ptr [rdx + rsi + 20], 15 - pinsrb xmm4, byte ptr [rdx + r11 + 21], 3 - pinsrb xmm4, byte ptr [rdx + rdi + 21], 4 - pinsrb xmm4, byte ptr [rdx + r9 + 21], 5 - pinsrb xmm4, byte ptr [rdx + r13 + 21], 6 - pinsrb xmm4, byte ptr [rdx + r14 + 21], 7 - pinsrb xmm4, byte ptr [rdx + r10 + 21], 8 - pinsrb xmm4, byte ptr [rdx + r15 + 21], 9 - pinsrb xmm4, byte ptr [rdx + rax + 21], 10 - pinsrb xmm4, byte ptr [rdx + rbx + 21], 11 - pinsrb xmm4, byte ptr [rdx + rcx + 21], 12 - pinsrb xmm4, byte ptr [rdx + r12 + 21], 13 - pinsrb xmm4, byte ptr [rdx + r8 + 21], 14 - pinsrb xmm4, byte ptr [rdx + rsi + 21], 15 - pinsrb xmm7, byte ptr [rdx + r11 + 22], 3 - pinsrb xmm7, byte ptr [rdx + rdi + 22], 4 - pinsrb xmm7, byte ptr [rdx + r9 + 22], 5 - pinsrb xmm7, byte ptr [rdx + r13 + 22], 6 - pinsrb xmm7, byte ptr [rdx + r14 + 22], 7 - pinsrb xmm7, byte ptr [rdx + r10 + 22], 8 - pinsrb xmm7, byte ptr [rdx + r15 + 22], 9 - pinsrb xmm7, byte ptr [rdx + rax + 22], 10 - pinsrb xmm7, byte ptr [rdx + rbx + 22], 11 - pinsrb xmm7, byte ptr [rdx + rcx + 22], 12 - pinsrb xmm7, byte ptr [rdx + r12 + 22], 13 - pinsrb xmm7, byte ptr [rdx + r8 + 22], 14 - pinsrb xmm7, byte ptr [rdx + rsi + 22], 15 - pmaxub xmm6, xmm8 - pcmpeqb xmm6, xmm8 - movdqa xmm5, xmmword ptr [rip + .LCPI11_19] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] - pand xmm6, xmm5 - pmaxub xmm4, xmm8 - pcmpeqb xmm4, xmm8 - movdqa xmm15, xmmword ptr [rip + .LCPI11_20] # xmm15 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] - pand xmm4, xmm15 - por xmm4, xmm6 - pmaxub xmm7, xmm8 - pcmpeqb xmm7, xmm8 - movdqa xmm6, xmmword ptr [rip + .LCPI11_21] # xmm6 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] - pand xmm7, xmm6 - por xmm7, xmm4 - por xmm7, xmm3 - pinsrb xmm2, byte ptr [rdx + r11 + 23], 3 - pinsrb xmm2, byte ptr [rdx + rdi + 23], 4 - pinsrb xmm2, byte ptr [rdx + r9 + 23], 5 - pinsrb xmm2, byte ptr [rdx + r13 + 23], 6 - pinsrb xmm2, byte ptr [rdx + r14 + 23], 7 - pinsrb xmm2, byte ptr [rdx + r10 + 23], 8 - pinsrb xmm2, byte ptr [rdx + r15 + 23], 9 - pinsrb xmm2, byte ptr [rdx + rax + 23], 10 - pinsrb xmm2, byte ptr [rdx + rbx + 23], 11 - pinsrb xmm2, byte ptr [rdx + rcx + 23], 12 - pinsrb xmm2, byte ptr [rdx + r12 + 23], 13 - pinsrb xmm2, byte ptr [rdx + r8 + 23], 14 - pinsrb xmm2, byte ptr [rdx + rsi + 23], 15 + pinsrb xmm2, byte ptr [r11 + rsi + 8], 13 + mov r10, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r10 + 8], 14 + pinsrb xmm2, byte ptr [r11 + r14 + 8], 15 pmaxub xmm2, xmm8 pcmpeqb xmm2, xmm8 - movdqa xmm3, xmmword ptr [rip + .LCPI11_6] # xmm3 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - pand xmm2, xmm3 - por xmm2, xmm7 - pinsrb xmm9, byte ptr [rdx + r11 + 24], 3 - pinsrb xmm9, byte ptr [rdx + rdi + 24], 4 - pinsrb xmm9, byte ptr [rdx + r9 + 24], 5 - pinsrb xmm9, byte ptr [rdx + r13 + 24], 6 - pinsrb xmm9, byte ptr [rdx + r14 + 24], 7 - pinsrb xmm9, byte ptr [rdx + r10 + 24], 8 - pinsrb xmm9, byte ptr [rdx + r15 + 24], 9 - pinsrb xmm9, byte ptr [rdx + rax + 24], 10 - pinsrb xmm9, byte ptr [rdx + rbx + 24], 11 - pinsrb xmm9, byte ptr [rdx + rcx + 24], 12 - pinsrb xmm9, byte ptr [rdx + r12 + 24], 13 - pinsrb xmm9, byte ptr [rdx + r8 + 24], 14 - pinsrb xmm9, byte ptr [rdx + rsi + 24], 15 - pmaxub xmm9, xmm8 - pcmpeqb xmm9, xmm8 - pinsrb xmm12, byte ptr [rdx + r11 + 25], 3 - pinsrb xmm12, byte ptr [rdx + rdi + 25], 4 - pinsrb xmm12, byte ptr [rdx + r9 + 25], 5 - pinsrb xmm12, byte ptr [rdx + r13 + 25], 6 - pinsrb xmm12, byte ptr [rdx + r14 + 25], 7 - pinsrb xmm12, byte ptr [rdx + r10 + 25], 8 - pinsrb xmm12, byte ptr [rdx + r15 + 25], 9 - pinsrb xmm12, byte ptr [rdx + rax + 25], 10 - pinsrb xmm12, byte ptr [rdx + rbx + 25], 11 - pinsrb xmm12, byte ptr [rdx + rcx + 25], 12 - pinsrb xmm12, byte ptr [rdx + r12 + 25], 13 - pinsrb xmm12, byte ptr [rdx + r8 + 25], 14 - pinsrb xmm12, byte ptr [rdx + rsi + 25], 15 - pmaxub xmm12, xmm8 - pcmpeqb xmm12, xmm8 - pand xmm12, xmmword ptr [rip + .LCPI11_16] - psubb xmm12, xmm9 - pinsrb xmm13, byte ptr [rdx + r11 + 26], 3 - pinsrb xmm13, byte ptr [rdx + rdi + 26], 4 - pinsrb xmm13, byte ptr [rdx + r9 + 26], 5 - pinsrb xmm13, byte ptr [rdx + r13 + 26], 6 - pinsrb xmm13, byte ptr [rdx + r14 + 26], 7 - pinsrb xmm13, byte ptr [rdx + r10 + 26], 8 - pinsrb xmm13, byte ptr [rdx + r15 + 26], 9 - pinsrb xmm13, byte ptr [rdx + rax + 26], 10 - pinsrb xmm13, byte ptr [rdx + rbx + 26], 11 - pinsrb xmm13, byte ptr [rdx + rcx + 26], 12 - pinsrb xmm13, byte ptr [rdx + r12 + 26], 13 - pinsrb xmm13, byte ptr [rdx + r8 + 26], 14 - pinsrb xmm13, byte ptr [rdx + rsi + 26], 15 - pinsrb xmm10, byte ptr [rdx + r11 + 27], 3 - pinsrb xmm10, byte ptr [rdx + rdi + 27], 4 - pinsrb xmm10, byte ptr [rdx + r9 + 27], 5 - pinsrb xmm10, byte ptr [rdx + r13 + 27], 6 - pinsrb xmm10, byte ptr [rdx + r14 + 27], 7 - pinsrb xmm10, byte ptr [rdx + r10 + 27], 8 - pinsrb xmm10, byte ptr [rdx + r15 + 27], 9 - pinsrb xmm10, byte ptr [rdx + rax + 27], 10 - pinsrb xmm10, byte ptr [rdx + rbx + 27], 11 - pinsrb xmm10, byte ptr [rdx + rcx + 27], 12 - pinsrb xmm10, byte ptr [rdx + r12 + 27], 13 - pinsrb xmm10, byte ptr [rdx + r8 + 27], 14 - pinsrb xmm10, byte ptr [rdx + rsi + 27], 15 - pmaxub xmm13, xmm8 - pcmpeqb xmm13, xmm8 - pand xmm13, xmmword ptr [rip + .LCPI11_17] + pinsrb xmm10, byte ptr [r11 + r8 + 9], 1 + pinsrb xmm10, byte ptr [r11 + r15 + 9], 2 + mov r9, r15 + pinsrb xmm10, byte ptr [r11 + rax + 9], 3 + pinsrb xmm10, byte ptr [r11 + rdi + 9], 4 + pinsrb xmm10, byte ptr [r11 + r13 + 9], 5 + pinsrb xmm10, byte ptr [r11 + r12 + 9], 6 + mov r15, r12 + pinsrb xmm10, byte ptr [r11 + rbx + 9], 7 + mov r12, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + r12 + 9], 8 + pinsrb xmm10, byte ptr [r11 + rcx + 9], 9 + mov rdi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rdi + 9], 10 + pinsrb xmm10, byte ptr [r11 + rdx + 9], 11 + mov rdx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm10, byte ptr [r11 + rdx + 9], 12 + pinsrb xmm10, byte ptr [r11 + rsi + 9], 13 + pinsrb xmm10, byte ptr [r11 + r10 + 9], 14 + mov rbx, r10 + pinsrb xmm10, byte ptr [r11 + r14 + 9], 15 pmaxub xmm10, xmm8 pcmpeqb xmm10, xmm8 - pand xmm10, xmmword ptr [rip + .LCPI11_18] - por xmm10, xmm13 - por xmm10, xmm12 - pinsrb xmm11, byte ptr [rdx + r11 + 28], 3 - pinsrb xmm14, byte ptr [rdx + r11 + 29], 3 - pinsrb xmm1, byte ptr [rdx + r11 + 30], 3 - pinsrb xmm0, byte ptr [rdx + r11 + 31], 3 - pinsrb xmm11, byte ptr [rdx + rdi + 28], 4 - pinsrb xmm14, byte ptr [rdx + rdi + 29], 4 - pinsrb xmm1, byte ptr [rdx + rdi + 30], 4 - pinsrb xmm0, byte ptr [rdx + rdi + 31], 4 - pinsrb xmm11, byte ptr [rdx + r9 + 28], 5 - pinsrb xmm14, byte ptr [rdx + r9 + 29], 5 - pinsrb xmm1, byte ptr [rdx + r9 + 30], 5 - pinsrb xmm0, byte ptr [rdx + r9 + 31], 5 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + r13 + 28], 6 - pinsrb xmm14, byte ptr [rdx + r13 + 29], 6 - pinsrb xmm1, byte ptr [rdx + r13 + 30], 6 - pinsrb xmm0, byte ptr [rdx + r13 + 31], 6 - mov rax, r14 - pinsrb xmm11, byte ptr [rdx + r14 + 28], 7 - pinsrb xmm14, byte ptr [rdx + r14 + 29], 7 - pinsrb xmm1, byte ptr [rdx + r14 + 30], 7 - pinsrb xmm0, byte ptr [rdx + r14 + 31], 7 - pinsrb xmm11, byte ptr [rdx + r10 + 28], 8 - pinsrb xmm14, byte ptr [rdx + r10 + 29], 8 - pinsrb xmm1, byte ptr [rdx + r10 + 30], 8 - pinsrb xmm0, byte ptr [rdx + r10 + 31], 8 - mov rax, qword ptr [rsp + 96] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rax + 28], 9 - pinsrb xmm14, byte ptr [rdx + rax + 29], 9 - pinsrb xmm1, byte ptr [rdx + rax + 30], 9 - pinsrb xmm0, byte ptr [rdx + rax + 31], 9 - mov rax, qword ptr [rsp + 64] # 8-byte Reload - pinsrb xmm11, byte ptr [rdx + rax + 28], 10 - pinsrb xmm14, byte ptr [rdx + rax + 29], 10 - pinsrb xmm1, byte ptr [rdx + rax + 30], 10 - pinsrb xmm0, byte ptr [rdx + rax + 31], 10 - mov rax, rbx - pinsrb xmm11, byte ptr [rdx + rbx + 28], 11 - pinsrb xmm14, byte ptr [rdx + rbx + 29], 11 - pinsrb xmm1, byte ptr [rdx + rbx + 30], 11 - pinsrb xmm0, byte ptr [rdx + rbx + 31], 11 - pinsrb xmm11, byte ptr [rdx + rcx + 28], 12 - pinsrb xmm14, byte ptr [rdx + rcx + 29], 12 - pinsrb xmm1, byte ptr [rdx + rcx + 30], 12 - pinsrb xmm0, byte ptr [rdx + rcx + 31], 12 - mov rax, r12 - pinsrb xmm11, byte ptr [rdx + r12 + 28], 13 - pinsrb xmm14, byte ptr [rdx + r12 + 29], 13 - pinsrb xmm1, byte ptr [rdx + r12 + 30], 13 - pinsrb xmm0, byte ptr [rdx + r12 + 31], 13 - mov rax, r8 - pinsrb xmm11, byte ptr [rdx + r8 + 28], 14 - pinsrb xmm14, byte ptr [rdx + r8 + 29], 14 - pinsrb xmm1, byte ptr [rdx + r8 + 30], 14 - pinsrb xmm0, byte ptr [rdx + r8 + 31], 14 - mov rax, rsi - pinsrb xmm11, byte ptr [rdx + rsi + 28], 15 - pinsrb xmm14, byte ptr [rdx + rsi + 29], 15 - pinsrb xmm1, byte ptr [rdx + rsi + 30], 15 - pinsrb xmm0, byte ptr [rdx + rsi + 31], 15 + pand xmm10, xmmword ptr [rip + .LCPI11_16] + psubb xmm10, xmm2 + mov r8, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [r11 + r8 + 23] + movd xmm2, esi + mov r10, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + r10 + 10], 1 + pinsrb xmm12, byte ptr [r11 + r9 + 10], 2 + pinsrb xmm12, byte ptr [r11 + rax + 10], 3 + mov r14, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + r14 + 10], 4 + pinsrb xmm12, byte ptr [r11 + r13 + 10], 5 + pinsrb xmm12, byte ptr [r11 + r15 + 10], 6 + mov rsi, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rsi + 10], 7 + pinsrb xmm12, byte ptr [r11 + r12 + 10], 8 + pinsrb xmm12, byte ptr [r11 + rcx + 10], 9 + mov r15, rcx + pinsrb xmm12, byte ptr [r11 + rdi + 10], 10 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rcx + 10], 11 + pinsrb xmm12, byte ptr [r11 + rdx + 10], 12 + mov rdx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rdx + 10], 13 + pinsrb xmm12, byte ptr [r11 + rbx + 10], 14 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm12, byte ptr [r11 + rdi + 10], 15 + pinsrb xmm11, byte ptr [r11 + r10 + 11], 1 + pinsrb xmm11, byte ptr [r11 + r9 + 11], 2 + pinsrb xmm11, byte ptr [r11 + rax + 11], 3 + pinsrb xmm11, byte ptr [r11 + r14 + 11], 4 + pinsrb xmm11, byte ptr [r11 + r13 + 11], 5 + mov rax, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rax + 11], 6 + pinsrb xmm11, byte ptr [r11 + rsi + 11], 7 + pinsrb xmm11, byte ptr [r11 + r12 + 11], 8 + pinsrb xmm11, byte ptr [r11 + r15 + 11], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rsi + 11], 10 + pinsrb xmm11, byte ptr [r11 + rcx + 11], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rcx + 11], 12 + pinsrb xmm11, byte ptr [r11 + rdx + 11], 13 + pinsrb xmm11, byte ptr [r11 + rbx + 11], 14 + pinsrb xmm11, byte ptr [r11 + rdi + 11], 15 + pmaxub xmm12, xmm8 + pcmpeqb xmm12, xmm8 + pand xmm12, xmmword ptr [rip + .LCPI11_17] pmaxub xmm11, xmm8 pcmpeqb xmm11, xmm8 - pand xmm11, xmm5 + pand xmm11, xmmword ptr [rip + .LCPI11_18] + por xmm11, xmm12 + movzx esi, byte ptr [r11 + r8 + 24] + movd xmm9, esi + por xmm11, xmm10 + movzx esi, byte ptr [r11 + r8 + 25] + movd xmm12, esi + pinsrb xmm13, byte ptr [r11 + r10 + 12], 1 + mov r12, r9 + pinsrb xmm13, byte ptr [r11 + r9 + 12], 2 + mov rdi, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rdi + 12], 3 + pinsrb xmm13, byte ptr [r11 + r14 + 12], 4 + mov rbx, r13 + pinsrb xmm13, byte ptr [r11 + r13 + 12], 5 + mov r15, rax + pinsrb xmm13, byte ptr [r11 + rax + 12], 6 + mov r10, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + r10 + 12], 7 + mov r13, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + r13 + 12], 8 + mov rcx, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rcx + 12], 9 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + r9 + 12], 10 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rdx + 12], 11 + mov r8, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + r8 + 12], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rax + 12], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rax + 12], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm13, byte ptr [r11 + rsi + 12], 15 + mov rax, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 13], 1 + pinsrb xmm0, byte ptr [r11 + r12 + 13], 2 + pinsrb xmm0, byte ptr [r11 + rdi + 13], 3 + pinsrb xmm0, byte ptr [r11 + r14 + 13], 4 + pinsrb xmm0, byte ptr [r11 + rbx + 13], 5 + pinsrb xmm0, byte ptr [r11 + r15 + 13], 6 + pinsrb xmm0, byte ptr [r11 + r10 + 13], 7 + pinsrb xmm0, byte ptr [r11 + r13 + 13], 8 + pinsrb xmm0, byte ptr [r11 + rcx + 13], 9 + pinsrb xmm0, byte ptr [r11 + r9 + 13], 10 + pinsrb xmm0, byte ptr [r11 + rdx + 13], 11 + pinsrb xmm0, byte ptr [r11 + r8 + 13], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 13], 13 + mov rax, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 13], 14 + pinsrb xmm0, byte ptr [r11 + rsi + 13], 15 + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + rsi + 14], 1 + pinsrb xmm14, byte ptr [r11 + r12 + 14], 2 + pinsrb xmm14, byte ptr [r11 + rdi + 14], 3 + pinsrb xmm14, byte ptr [r11 + r14 + 14], 4 + pinsrb xmm14, byte ptr [r11 + rbx + 14], 5 + pinsrb xmm14, byte ptr [r11 + r15 + 14], 6 + pinsrb xmm14, byte ptr [r11 + r10 + 14], 7 + mov rax, r10 + pinsrb xmm14, byte ptr [r11 + r13 + 14], 8 + pinsrb xmm14, byte ptr [r11 + rcx + 14], 9 + pinsrb xmm14, byte ptr [r11 + r9 + 14], 10 + pinsrb xmm14, byte ptr [r11 + rdx + 14], 11 + pinsrb xmm14, byte ptr [r11 + r8 + 14], 12 + mov rcx, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + rcx + 14], 13 + mov r13, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + r13 + 14], 14 + mov r8, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm14, byte ptr [r11 + r8 + 14], 15 + pmaxub xmm13, xmm8 + pcmpeqb xmm13, xmm8 + pand xmm13, xmmword ptr [rip + .LCPI11_19] + pmaxub xmm0, xmm8 + pcmpeqb xmm0, xmm8 + pand xmm0, xmmword ptr [rip + .LCPI11_20] + por xmm0, xmm13 + mov r9, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [r11 + r9 + 26] + movd xmm13, esi pmaxub xmm14, xmm8 pcmpeqb xmm14, xmm8 - pand xmm14, xmm15 + pand xmm14, xmmword ptr [rip + .LCPI11_21] + por xmm14, xmm0 + movzx esi, byte ptr [r11 + r9 + 27] + movd xmm10, esi por xmm14, xmm11 - pmaxub xmm1, xmm8 - pcmpeqb xmm1, xmm8 - pand xmm1, xmm6 - por xmm1, xmm14 - por xmm1, xmm10 - pmaxub xmm0, xmm8 - pcmpeqb xmm0, xmm8 - pand xmm0, xmm3 - por xmm0, xmm1 - movdqa xmm1, xmm2 - punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] - movdqa xmm5, xmmword ptr [rsp + 208] # 16-byte Reload - movdqa xmm3, xmm5 - movdqa xmm6, xmmword ptr [rsp + 176] # 16-byte Reload - punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] - movdqa xmm4, xmm3 - punpcklwd xmm4, xmm1 # xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3] - punpckhwd xmm3, xmm1 # xmm3 = xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7] - punpckhbw xmm2, xmm0 # xmm2 = xmm2[8],xmm0[8],xmm2[9],xmm0[9],xmm2[10],xmm0[10],xmm2[11],xmm0[11],xmm2[12],xmm0[12],xmm2[13],xmm0[13],xmm2[14],xmm0[14],xmm2[15],xmm0[15] - punpckhbw xmm5, xmm6 # xmm5 = xmm5[8],xmm6[8],xmm5[9],xmm6[9],xmm5[10],xmm6[10],xmm5[11],xmm6[11],xmm5[12],xmm6[12],xmm5[13],xmm6[13],xmm5[14],xmm6[14],xmm5[15],xmm6[15] - movdqa xmm0, xmm5 - punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] - punpckhwd xmm5, xmm2 # xmm5 = xmm5[4],xmm2[4],xmm5[5],xmm2[5],xmm5[6],xmm2[6],xmm5[7],xmm2[7] - mov rcx, qword ptr [rsp + 128] # 8-byte Reload - movdqu xmmword ptr [r15 + 4*rcx + 48], xmm5 - movdqu xmmword ptr [r15 + 4*rcx + 32], xmm0 - movdqu xmmword ptr [r15 + 4*rcx + 16], xmm3 - movdqu xmmword ptr [r15 + 4*rcx], xmm4 - add rcx, 16 - mov rax, rcx - cmp rcx, qword ptr [rsp + 192] # 8-byte Folded Reload - jne .LBB11_67 -# %bb.68: - mov r10, qword ptr [rsp + 248] # 8-byte Reload - cmp r10, qword ptr [rsp + 192] # 8-byte Folded Reload - mov r14b, byte ptr [rsp] # 1-byte Reload - mov r13, qword ptr [rsp + 288] # 8-byte Reload - mov rdx, qword ptr [rsp + 280] # 8-byte Reload - mov r11, qword ptr [rsp + 136] # 8-byte Reload - jne .LBB11_69 - jmp .LBB11_72 -.LBB11_124: - and r10, -8 - mov rax, r10 - shl rax, 6 - add rax, rdx - mov qword ptr [rsp + 48], rax # 8-byte Spill - mov qword ptr [rsp + 32], r10 # 8-byte Spill - lea rax, [r15 + 4*r10] - mov qword ptr [rsp + 56], rax # 8-byte Spill - movd xmm0, r14d - pshuflw xmm0, xmm0, 224 # xmm0 = xmm0[0,0,2,3,4,5,6,7] - pshufd xmm11, xmm0, 0 # xmm11 = xmm0[0,0,0,0] - xor r14d, r14d - mov qword ptr [rsp + 120], r15 # 8-byte Spill - pxor xmm15, xmm15 - .p2align 4, 0x90 -.LBB11_125: # =>This Inner Loop Header: Depth=1 - mov qword ptr [rsp + 16], r14 # 8-byte Spill - shl r14, 6 - mov rdi, r14 - mov r15, r14 - mov r12, r14 - mov r13, r14 - mov rbx, r14 - mov r9, r14 - movzx eax, word ptr [rdx + r14] - movd xmm5, eax - movzx eax, word ptr [rdx + r14 + 2] - movd xmm0, eax - movzx eax, word ptr [rdx + r14 + 4] - movd xmm1, eax - movzx eax, word ptr [rdx + r14 + 6] - movd xmm7, eax - movzx eax, word ptr [rdx + r14 + 8] - movd xmm8, eax - movzx eax, word ptr [rdx + r14 + 10] - movd xmm4, eax - movzx eax, word ptr [rdx + r14 + 12] - movzx esi, word ptr [rdx + r14 + 14] - movzx ecx, word ptr [rdx + r14 + 16] - mov dword ptr [rsp + 24], ecx # 4-byte Spill - movzx r10d, word ptr [rdx + r14 + 18] - movzx r11d, word ptr [rdx + r14 + 20] - mov rcx, r14 - or rcx, 64 - or rdi, 128 - or r15, 192 - or r12, 256 - or r13, 320 - or rbx, 384 - pinsrw xmm5, word ptr [rdx + rcx], 1 - pinsrw xmm5, word ptr [rdx + rdi], 2 - pinsrw xmm5, word ptr [rdx + r15], 3 - pinsrw xmm5, word ptr [rdx + r12], 4 - pinsrw xmm5, word ptr [rdx + r13], 5 - pinsrw xmm5, word ptr [rdx + rbx], 6 - pinsrw xmm0, word ptr [rdx + rcx + 2], 1 - pinsrw xmm0, word ptr [rdx + rdi + 2], 2 - pinsrw xmm0, word ptr [rdx + r15 + 2], 3 - pinsrw xmm0, word ptr [rdx + r12 + 2], 4 - pinsrw xmm0, word ptr [rdx + r13 + 2], 5 - pinsrw xmm0, word ptr [rdx + rbx + 2], 6 - or r9, 448 - pinsrw xmm0, word ptr [rdx + r9 + 2], 7 - movd xmm2, eax - movzx eax, word ptr [rdx + r14 + 22] - mov dword ptr [rsp + 8], eax # 4-byte Spill - pcmpgtw xmm0, xmm11 - pinsrw xmm1, word ptr [rdx + rcx + 4], 1 - pinsrw xmm1, word ptr [rdx + rdi + 4], 2 - pinsrw xmm1, word ptr [rdx + r15 + 4], 3 - pinsrw xmm1, word ptr [rdx + r12 + 4], 4 - pinsrw xmm1, word ptr [rdx + r13 + 4], 5 - pinsrw xmm1, word ptr [rdx + rbx + 4], 6 - pinsrw xmm1, word ptr [rdx + r9 + 4], 7 - packsswb xmm0, xmm0 - pcmpgtw xmm1, xmm11 - movdqa xmm9, xmmword ptr [rip + .LCPI11_8] # xmm9 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm3, xmm9 - pblendvb xmm3, xmm15, xmm0 - packsswb xmm1, xmm1 - movdqa xmm0, xmmword ptr [rip + .LCPI11_9] # xmm0 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm0 - movdqa xmm14, xmm0 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm15, xmm0 - movd xmm1, esi - movzx r8d, word ptr [rdx + r14 + 24] - pinsrw xmm5, word ptr [rdx + r9], 7 - pcmpgtw xmm5, xmm11 - pcmpeqd xmm0, xmm0 - pxor xmm5, xmm0 - packsswb xmm5, xmm5 - pinsrw xmm7, word ptr [rdx + rcx + 6], 1 - pinsrw xmm7, word ptr [rdx + rdi + 6], 2 - pinsrw xmm7, word ptr [rdx + r15 + 6], 3 - pinsrw xmm7, word ptr [rdx + r12 + 6], 4 - pinsrw xmm7, word ptr [rdx + r13 + 6], 5 - pinsrw xmm7, word ptr [rdx + rbx + 6], 6 - pinsrw xmm7, word ptr [rdx + r9 + 6], 7 - pcmpgtw xmm7, xmm11 - packsswb xmm7, xmm7 - pinsrw xmm8, word ptr [rdx + rcx + 8], 1 - pinsrw xmm8, word ptr [rdx + rdi + 8], 2 - pinsrw xmm8, word ptr [rdx + r15 + 8], 3 - pinsrw xmm8, word ptr [rdx + r12 + 8], 4 - pinsrw xmm8, word ptr [rdx + r13 + 8], 5 - pinsrw xmm8, word ptr [rdx + rbx + 8], 6 - pinsrw xmm8, word ptr [rdx + r9 + 8], 7 - psubb xmm3, xmm5 - movdqa xmm12, xmmword ptr [rip + .LCPI11_10] # xmm12 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm7 - pblendvb xmm12, xmm15, xmm0 - movd xmm7, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx eax, word ptr [rdx + r14 + 26] - pcmpgtw xmm8, xmm11 - packsswb xmm8, xmm8 - por xmm12, xmm6 - movdqa xmm13, xmmword ptr [rip + .LCPI11_11] # xmm13 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm8 - pblendvb xmm13, xmm15, xmm0 - movd xmm6, r10d - movzx r10d, word ptr [rdx + r14 + 28] - pinsrw xmm4, word ptr [rdx + rcx + 10], 1 - pinsrw xmm4, word ptr [rdx + rdi + 10], 2 - pinsrw xmm4, word ptr [rdx + r15 + 10], 3 - pinsrw xmm4, word ptr [rdx + r12 + 10], 4 - pinsrw xmm4, word ptr [rdx + r13 + 10], 5 - pinsrw xmm4, word ptr [rdx + rbx + 10], 6 - pinsrw xmm4, word ptr [rdx + r9 + 10], 7 - pcmpgtw xmm4, xmm11 - packsswb xmm4, xmm4 - pinsrw xmm2, word ptr [rdx + rcx + 12], 1 - pinsrw xmm2, word ptr [rdx + rdi + 12], 2 - pinsrw xmm2, word ptr [rdx + r15 + 12], 3 - pinsrw xmm2, word ptr [rdx + r12 + 12], 4 - pinsrw xmm2, word ptr [rdx + r13 + 12], 5 - pinsrw xmm2, word ptr [rdx + rbx + 12], 6 - por xmm12, xmm3 - movdqa xmm5, xmmword ptr [rip + .LCPI11_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm5, xmm15, xmm0 - movd xmm4, r11d - movzx esi, word ptr [rdx + r14 + 30] - mov dword ptr [rsp + 40], esi # 4-byte Spill - pinsrw xmm2, word ptr [rdx + r9 + 12], 7 - pcmpgtw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm13 - movdqa xmm13, xmmword ptr [rip + .LCPI11_13] # xmm13 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm13, xmm15, xmm0 - movd xmm3, dword ptr [rsp + 8] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx esi, word ptr [rdx + r14 + 32] - mov dword ptr [rsp + 24], esi # 4-byte Spill - pinsrw xmm1, word ptr [rdx + rcx + 14], 1 - pinsrw xmm1, word ptr [rdx + rdi + 14], 2 - pinsrw xmm1, word ptr [rdx + r15 + 14], 3 - pinsrw xmm1, word ptr [rdx + r12 + 14], 4 - pinsrw xmm1, word ptr [rdx + r13 + 14], 5 - pinsrw xmm1, word ptr [rdx + rbx + 14], 6 - por xmm13, xmm5 - movd xmm2, r8d - movzx esi, word ptr [rdx + r14 + 34] - mov dword ptr [rsp + 8], esi # 4-byte Spill - pinsrw xmm1, word ptr [rdx + r9 + 14], 7 - pcmpgtw xmm1, xmm11 - pinsrw xmm6, word ptr [rdx + rcx + 18], 1 - pinsrw xmm6, word ptr [rdx + rdi + 18], 2 - pinsrw xmm6, word ptr [rdx + r15 + 18], 3 - pinsrw xmm6, word ptr [rdx + r12 + 18], 4 - pinsrw xmm6, word ptr [rdx + r13 + 18], 5 - pinsrw xmm6, word ptr [rdx + rbx + 18], 6 - packsswb xmm1, xmm1 - pinsrw xmm6, word ptr [rdx + r9 + 18], 7 - pcmpgtw xmm6, xmm11 - packsswb xmm6, xmm6 - por xmm13, xmm12 - movdqa xmm12, xmmword ptr [rip + .LCPI11_14] # xmm12 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm12, xmm15, xmm0 - movdqa xmm8, xmm9 - movdqa xmm0, xmm6 - pblendvb xmm8, xmm15, xmm0 - movd xmm1, eax - movzx r11d, word ptr [rdx + r14 + 36] - pinsrw xmm7, word ptr [rdx + rcx + 16], 1 - pinsrw xmm7, word ptr [rdx + rdi + 16], 2 - pinsrw xmm7, word ptr [rdx + r15 + 16], 3 - pinsrw xmm7, word ptr [rdx + r12 + 16], 4 - pinsrw xmm7, word ptr [rdx + r13 + 16], 5 - pinsrw xmm7, word ptr [rdx + rbx + 16], 6 - pinsrw xmm4, word ptr [rdx + rcx + 20], 1 - pinsrw xmm4, word ptr [rdx + rdi + 20], 2 - pinsrw xmm4, word ptr [rdx + r15 + 20], 3 - pinsrw xmm4, word ptr [rdx + r12 + 20], 4 - pinsrw xmm4, word ptr [rdx + r13 + 20], 5 - pinsrw xmm4, word ptr [rdx + rbx + 20], 6 - pinsrw xmm4, word ptr [rdx + r9 + 20], 7 - pcmpgtw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm12, xmm13 - movdqa xmm5, xmm14 - movdqa xmm0, xmm4 - pblendvb xmm5, xmm15, xmm0 - movd xmm4, r10d - movzx esi, word ptr [rdx + r14 + 38] - pinsrw xmm7, word ptr [rdx + r9 + 16], 7 - pcmpgtw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI11_22] - packsswb xmm7, xmm7 - pinsrw xmm3, word ptr [rdx + rcx + 22], 1 - pinsrw xmm3, word ptr [rdx + rdi + 22], 2 - pinsrw xmm3, word ptr [rdx + r15 + 22], 3 - pinsrw xmm3, word ptr [rdx + r12 + 22], 4 - pinsrw xmm3, word ptr [rdx + r13 + 22], 5 - pinsrw xmm3, word ptr [rdx + rbx + 22], 6 - pinsrw xmm3, word ptr [rdx + r9 + 22], 7 - pcmpgtw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [rdx + rcx + 24], 1 - pinsrw xmm2, word ptr [rdx + rdi + 24], 2 - pinsrw xmm2, word ptr [rdx + r15 + 24], 3 - pinsrw xmm2, word ptr [rdx + r12 + 24], 4 - pinsrw xmm2, word ptr [rdx + r13 + 24], 5 - pinsrw xmm2, word ptr [rdx + rbx + 24], 6 - pinsrw xmm2, word ptr [rdx + r9 + 24], 7 - psubb xmm8, xmm7 - movdqa xmm10, xmmword ptr [rip + .LCPI11_10] # xmm10 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm14, xmm10 - movdqa xmm0, xmm3 - pblendvb xmm14, xmm15, xmm0 - movd xmm3, dword ptr [rsp + 40] # 4-byte Folded Reload - # xmm3 = mem[0],zero,zero,zero - movzx eax, word ptr [rdx + r14 + 40] - pcmpgtw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm14, xmm5 - movdqa xmm9, xmmword ptr [rip + .LCPI11_11] # xmm9 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm13, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm13, xmm15, xmm0 - movd xmm7, dword ptr [rsp + 24] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r10d, word ptr [rdx + r14 + 42] - pinsrw xmm1, word ptr [rdx + rcx + 26], 1 - pinsrw xmm1, word ptr [rdx + rdi + 26], 2 - pinsrw xmm1, word ptr [rdx + r15 + 26], 3 - pinsrw xmm1, word ptr [rdx + r12 + 26], 4 - pinsrw xmm1, word ptr [rdx + r13 + 26], 5 - pinsrw xmm1, word ptr [rdx + rbx + 26], 6 - pinsrw xmm1, word ptr [rdx + r9 + 26], 7 - pcmpgtw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm4, word ptr [rdx + rcx + 28], 1 - pinsrw xmm4, word ptr [rdx + rdi + 28], 2 - pinsrw xmm4, word ptr [rdx + r15 + 28], 3 - pinsrw xmm4, word ptr [rdx + r12 + 28], 4 - pinsrw xmm4, word ptr [rdx + r13 + 28], 5 - pinsrw xmm4, word ptr [rdx + rbx + 28], 6 - por xmm14, xmm8 - movdqa xmm5, xmmword ptr [rip + .LCPI11_12] # xmm5 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm5, xmm15, xmm0 - movd xmm2, dword ptr [rsp + 8] # 4-byte Folded Reload - # xmm2 = mem[0],zero,zero,zero - movzx r8d, word ptr [rdx + r14 + 44] - pinsrw xmm4, word ptr [rdx + r9 + 28], 7 - pcmpgtw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm5, xmm13 - movdqa xmm6, xmmword ptr [rip + .LCPI11_13] # xmm6 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm15, xmm0 - movd xmm4, r11d - movzx r11d, word ptr [rdx + r14 + 46] - pinsrw xmm3, word ptr [rdx + rcx + 30], 1 - pinsrw xmm3, word ptr [rdx + rdi + 30], 2 - pinsrw xmm3, word ptr [rdx + r15 + 30], 3 - pinsrw xmm3, word ptr [rdx + r12 + 30], 4 - pinsrw xmm3, word ptr [rdx + r13 + 30], 5 - pinsrw xmm3, word ptr [rdx + rbx + 30], 6 - por xmm6, xmm5 - movd xmm1, esi - movzx esi, word ptr [rdx + r14 + 48] - mov dword ptr [rsp + 8], esi # 4-byte Spill - pinsrw xmm3, word ptr [rdx + r9 + 30], 7 - pcmpgtw xmm3, xmm11 - pinsrw xmm2, word ptr [rdx + rcx + 34], 1 - pinsrw xmm2, word ptr [rdx + rdi + 34], 2 - pinsrw xmm2, word ptr [rdx + r15 + 34], 3 - pinsrw xmm2, word ptr [rdx + r12 + 34], 4 - pinsrw xmm2, word ptr [rdx + r13 + 34], 5 - pinsrw xmm2, word ptr [rdx + rbx + 34], 6 - packsswb xmm3, xmm3 - pinsrw xmm2, word ptr [rdx + r9 + 34], 7 - pcmpgtw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm6, xmm14 - movdqa xmm14, xmmword ptr [rip + .LCPI11_14] # xmm14 = <128,128,128,128,128,128,128,128,u,u,u,u,u,u,u,u> - movdqa xmm13, xmm14 - movdqa xmm0, xmm3 - pblendvb xmm13, xmm15, xmm0 - movdqa xmm8, xmmword ptr [rip + .LCPI11_8] # xmm8 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm8, xmm15, xmm0 - movd xmm2, eax - movzx esi, word ptr [rdx + r14 + 50] - pinsrw xmm7, word ptr [rdx + rcx + 32], 1 - pinsrw xmm7, word ptr [rdx + rdi + 32], 2 - pinsrw xmm7, word ptr [rdx + r15 + 32], 3 - pinsrw xmm7, word ptr [rdx + r12 + 32], 4 - pinsrw xmm7, word ptr [rdx + r13 + 32], 5 - pinsrw xmm7, word ptr [rdx + rbx + 32], 6 - pinsrw xmm4, word ptr [rdx + rcx + 36], 1 - pinsrw xmm4, word ptr [rdx + rdi + 36], 2 - pinsrw xmm4, word ptr [rdx + r15 + 36], 3 - pinsrw xmm4, word ptr [rdx + r12 + 36], 4 - pinsrw xmm4, word ptr [rdx + r13 + 36], 5 - pinsrw xmm4, word ptr [rdx + rbx + 36], 6 - pinsrw xmm4, word ptr [rdx + r9 + 36], 7 - pcmpgtw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm13, xmm6 - movdqa xmm6, xmmword ptr [rip + .LCPI11_9] # xmm6 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm4 - pblendvb xmm6, xmm15, xmm0 - movd xmm3, r10d - movzx r10d, word ptr [rdx + r14 + 52] - pinsrw xmm7, word ptr [rdx + r9 + 32], 7 - pcmpgtw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI11_22] - packsswb xmm7, xmm7 - pinsrw xmm1, word ptr [rdx + rcx + 38], 1 - pinsrw xmm1, word ptr [rdx + rdi + 38], 2 - pinsrw xmm1, word ptr [rdx + r15 + 38], 3 - pinsrw xmm1, word ptr [rdx + r12 + 38], 4 - pinsrw xmm1, word ptr [rdx + r13 + 38], 5 - pinsrw xmm1, word ptr [rdx + rbx + 38], 6 - pinsrw xmm1, word ptr [rdx + r9 + 38], 7 - pcmpgtw xmm1, xmm11 - packsswb xmm1, xmm1 - pinsrw xmm2, word ptr [rdx + rcx + 40], 1 - pinsrw xmm2, word ptr [rdx + rdi + 40], 2 - pinsrw xmm2, word ptr [rdx + r15 + 40], 3 - pinsrw xmm2, word ptr [rdx + r12 + 40], 4 - pinsrw xmm2, word ptr [rdx + r13 + 40], 5 - pinsrw xmm2, word ptr [rdx + rbx + 40], 6 - pinsrw xmm2, word ptr [rdx + r9 + 40], 7 - psubb xmm8, xmm7 - movdqa xmm5, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm5, xmm15, xmm0 - movd xmm1, r8d - movzx r8d, word ptr [rdx + r14 + 54] - pcmpgtw xmm2, xmm11 - packsswb xmm2, xmm2 - por xmm5, xmm6 - movdqa xmm6, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm6, xmm15, xmm0 - movd xmm4, r11d - movzx eax, word ptr [rdx + r14 + 56] - pinsrw xmm3, word ptr [rdx + rcx + 42], 1 - pinsrw xmm3, word ptr [rdx + rdi + 42], 2 - pinsrw xmm3, word ptr [rdx + r15 + 42], 3 - pinsrw xmm3, word ptr [rdx + r12 + 42], 4 - pinsrw xmm3, word ptr [rdx + r13 + 42], 5 - pinsrw xmm3, word ptr [rdx + rbx + 42], 6 - pinsrw xmm3, word ptr [rdx + r9 + 42], 7 - pcmpgtw xmm3, xmm11 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [rdx + rcx + 44], 1 - pinsrw xmm1, word ptr [rdx + rdi + 44], 2 - pinsrw xmm1, word ptr [rdx + r15 + 44], 3 - pinsrw xmm1, word ptr [rdx + r12 + 44], 4 - pinsrw xmm1, word ptr [rdx + r13 + 44], 5 - pinsrw xmm1, word ptr [rdx + rbx + 44], 6 - por xmm5, xmm8 - movdqa xmm9, xmmword ptr [rip + .LCPI11_12] # xmm9 = <32,32,32,32,32,32,32,32,u,u,u,u,u,u,u,u> - movdqa xmm2, xmm9 - movdqa xmm0, xmm3 - pblendvb xmm2, xmm15, xmm0 - movd xmm7, dword ptr [rsp + 8] # 4-byte Folded Reload - # xmm7 = mem[0],zero,zero,zero - movzx r11d, word ptr [rdx + r14 + 58] - pinsrw xmm1, word ptr [rdx + r9 + 44], 7 - pcmpgtw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm2, xmm6 - movdqa xmm10, xmmword ptr [rip + .LCPI11_13] # xmm10 = <64,64,64,64,64,64,64,64,u,u,u,u,u,u,u,u> - movdqa xmm6, xmm10 - movdqa xmm0, xmm1 - pblendvb xmm6, xmm15, xmm0 - movd xmm1, esi - movzx esi, word ptr [rdx + r14 + 60] - por xmm6, xmm2 - movd xmm2, r10d - pinsrw xmm4, word ptr [rdx + rcx + 46], 1 - pinsrw xmm4, word ptr [rdx + rdi + 46], 2 - pinsrw xmm4, word ptr [rdx + r15 + 46], 3 - pinsrw xmm4, word ptr [rdx + r12 + 46], 4 - pinsrw xmm4, word ptr [rdx + r13 + 46], 5 - pinsrw xmm4, word ptr [rdx + rbx + 46], 6 - pinsrw xmm4, word ptr [rdx + r9 + 46], 7 - pcmpgtw xmm4, xmm11 - packsswb xmm4, xmm4 - por xmm6, xmm5 - movdqa xmm8, xmm14 - movdqa xmm0, xmm4 - pblendvb xmm8, xmm15, xmm0 - movd xmm3, r8d - pinsrw xmm1, word ptr [rdx + rcx + 50], 1 - pinsrw xmm1, word ptr [rdx + rdi + 50], 2 - pinsrw xmm1, word ptr [rdx + r15 + 50], 3 - pinsrw xmm1, word ptr [rdx + r12 + 50], 4 - pinsrw xmm1, word ptr [rdx + r13 + 50], 5 - pinsrw xmm1, word ptr [rdx + rbx + 50], 6 - pinsrw xmm1, word ptr [rdx + r9 + 50], 7 - pcmpgtw xmm1, xmm11 - packsswb xmm1, xmm1 - por xmm8, xmm6 - movdqa xmm4, xmmword ptr [rip + .LCPI11_8] # xmm4 = <2,2,2,2,2,2,2,2,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm15, xmm0 - movd xmm1, eax - pinsrw xmm7, word ptr [rdx + rcx + 48], 1 - pinsrw xmm7, word ptr [rdx + rdi + 48], 2 - pinsrw xmm7, word ptr [rdx + r15 + 48], 3 - pinsrw xmm7, word ptr [rdx + r12 + 48], 4 - pinsrw xmm7, word ptr [rdx + r13 + 48], 5 - pinsrw xmm7, word ptr [rdx + rbx + 48], 6 - pinsrw xmm7, word ptr [rdx + r9 + 48], 7 - pcmpgtw xmm7, xmm11 - pxor xmm7, xmmword ptr [rip + .LCPI11_22] - pinsrw xmm2, word ptr [rdx + rcx + 52], 1 - pinsrw xmm2, word ptr [rdx + rdi + 52], 2 - pinsrw xmm2, word ptr [rdx + r15 + 52], 3 - pinsrw xmm2, word ptr [rdx + r12 + 52], 4 - pinsrw xmm2, word ptr [rdx + r13 + 52], 5 - pinsrw xmm2, word ptr [rdx + rbx + 52], 6 - packsswb xmm7, xmm7 - pinsrw xmm2, word ptr [rdx + r9 + 52], 7 - pcmpgtw xmm2, xmm11 - pinsrw xmm3, word ptr [rdx + rcx + 54], 1 - pinsrw xmm3, word ptr [rdx + rdi + 54], 2 - pinsrw xmm3, word ptr [rdx + r15 + 54], 3 - pinsrw xmm3, word ptr [rdx + r12 + 54], 4 - pinsrw xmm3, word ptr [rdx + r13 + 54], 5 - pinsrw xmm3, word ptr [rdx + rbx + 54], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [rdx + r9 + 54], 7 - pcmpgtw xmm3, xmm11 - pinsrw xmm1, word ptr [rdx + rcx + 56], 1 - pinsrw xmm1, word ptr [rdx + rdi + 56], 2 - pinsrw xmm1, word ptr [rdx + r15 + 56], 3 - pinsrw xmm1, word ptr [rdx + r12 + 56], 4 - pinsrw xmm1, word ptr [rdx + r13 + 56], 5 - pinsrw xmm1, word ptr [rdx + rbx + 56], 6 - packsswb xmm3, xmm3 - pinsrw xmm1, word ptr [rdx + r9 + 56], 7 - psubb xmm4, xmm7 - movdqa xmm5, xmmword ptr [rip + .LCPI11_9] # xmm5 = <4,4,4,4,4,4,4,4,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm2 - pblendvb xmm5, xmm15, xmm0 - movdqa xmm6, xmmword ptr [rip + .LCPI11_10] # xmm6 = <8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm3 - pblendvb xmm6, xmm15, xmm0 - movd xmm2, r11d - pcmpgtw xmm1, xmm11 - pinsrw xmm2, word ptr [rdx + rcx + 58], 1 - pinsrw xmm2, word ptr [rdx + rdi + 58], 2 - pinsrw xmm2, word ptr [rdx + r15 + 58], 3 - pinsrw xmm2, word ptr [rdx + r12 + 58], 4 - pinsrw xmm2, word ptr [rdx + r13 + 58], 5 - pinsrw xmm2, word ptr [rdx + rbx + 58], 6 - pinsrw xmm2, word ptr [rdx + r9 + 58], 7 - packsswb xmm1, xmm1 - pcmpgtw xmm2, xmm11 - por xmm6, xmm5 - movd xmm3, esi - pinsrw xmm3, word ptr [rdx + rcx + 60], 1 - pinsrw xmm3, word ptr [rdx + rdi + 60], 2 - pinsrw xmm3, word ptr [rdx + r15 + 60], 3 - pinsrw xmm3, word ptr [rdx + r12 + 60], 4 - pinsrw xmm3, word ptr [rdx + r13 + 60], 5 - pinsrw xmm3, word ptr [rdx + rbx + 60], 6 - packsswb xmm2, xmm2 - pinsrw xmm3, word ptr [rdx + r9 + 60], 7 - pcmpgtw xmm3, xmm11 - packsswb xmm3, xmm3 - por xmm6, xmm4 - movdqa xmm4, xmmword ptr [rip + .LCPI11_11] # xmm4 = <16,16,16,16,16,16,16,16,u,u,u,u,u,u,u,u> - movdqa xmm0, xmm1 - pblendvb xmm4, xmm15, xmm0 - movdqa xmm1, xmm9 - movdqa xmm0, xmm2 - pblendvb xmm1, xmm15, xmm0 - movdqa xmm0, xmm3 - pblendvb xmm10, xmm15, xmm0 - por xmm1, xmm4 - movzx eax, word ptr [rdx + r14 + 62] - por xmm10, xmm1 - movd xmm0, eax - pinsrw xmm0, word ptr [rdx + rcx + 62], 1 - pinsrw xmm0, word ptr [rdx + rdi + 62], 2 - pinsrw xmm0, word ptr [rdx + r15 + 62], 3 - mov r15, qword ptr [rsp + 120] # 8-byte Reload - pinsrw xmm0, word ptr [rdx + r12 + 62], 4 - pinsrw xmm0, word ptr [rdx + r13 + 62], 5 - pinsrw xmm0, word ptr [rdx + rbx + 62], 6 - pinsrw xmm0, word ptr [rdx + r9 + 62], 7 - pcmpgtw xmm0, xmm11 - packsswb xmm0, xmm0 - por xmm10, xmm6 - pblendvb xmm14, xmm15, xmm0 - por xmm14, xmm10 - movdqa xmm0, xmm12 - punpcklqdq xmm0, xmm13 # xmm0 = xmm0[0],xmm13[0] - movdqa xmm2, xmm8 - punpcklqdq xmm2, xmm14 # xmm2 = xmm2[0],xmm14[0] - movdqa xmm3, xmmword ptr [rip + .LCPI11_15] # xmm3 = <4,12,5,13,6,14,7,15,u,u,u,u,u,u,u,u> - pshufb xmm2, xmm3 - pshufb xmm0, xmm3 - punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] - punpcklbw xmm8, xmm14 # xmm8 = xmm8[0],xmm14[0],xmm8[1],xmm14[1],xmm8[2],xmm14[2],xmm8[3],xmm14[3],xmm8[4],xmm14[4],xmm8[5],xmm14[5],xmm8[6],xmm14[6],xmm8[7],xmm14[7] - punpcklbw xmm12, xmm13 # xmm12 = xmm12[0],xmm13[0],xmm12[1],xmm13[1],xmm12[2],xmm13[2],xmm12[3],xmm13[3],xmm12[4],xmm13[4],xmm12[5],xmm13[5],xmm12[6],xmm13[6],xmm12[7],xmm13[7] - punpcklwd xmm12, xmm8 # xmm12 = xmm12[0],xmm8[0],xmm12[1],xmm8[1],xmm12[2],xmm8[2],xmm12[3],xmm8[3] - mov rcx, qword ptr [rsp + 16] # 8-byte Reload - movdqu xmmword ptr [r15 + 4*rcx], xmm12 - movdqu xmmword ptr [r15 + 4*rcx + 16], xmm0 - add rcx, 8 - mov r14, rcx - cmp rcx, qword ptr [rsp + 32] # 8-byte Folded Reload - jne .LBB11_125 -# %bb.126: - mov r10, qword ptr [rsp + 256] # 8-byte Reload - cmp r10, qword ptr [rsp + 32] # 8-byte Folded Reload - mov r11, qword ptr [rsp + 136] # 8-byte Reload - mov r14d, dword ptr [rsp] # 4-byte Reload - mov r12, qword ptr [rsp + 56] # 8-byte Reload + movzx esi, byte ptr [r11 + r9 + 28] + movd xmm11, esi + movdqa xmm0, xmmword ptr [rsp + 208] # 16-byte Reload + mov rcx, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rcx + 15], 1 + pinsrb xmm0, byte ptr [r11 + r12 + 15], 2 + mov r10, r12 + mov rdx, qword ptr [rsp + 192] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rdx + 15], 3 + pinsrb xmm0, byte ptr [r11 + r14 + 15], 4 + pinsrb xmm0, byte ptr [r11 + rbx + 15], 5 + pinsrb xmm0, byte ptr [r11 + r15 + 15], 6 + pinsrb xmm0, byte ptr [r11 + rax + 15], 7 + mov rax, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rax + 15], 8 + mov r12, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + r12 + 15], 9 + mov rsi, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rsi + 15], 10 + mov rdi, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rdi + 15], 11 + mov rsi, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rsi + 15], 12 + mov rsi, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm0, byte ptr [r11 + rsi + 15], 13 + pinsrb xmm0, byte ptr [r11 + r13 + 15], 14 + pinsrb xmm0, byte ptr [r11 + r8 + 15], 15 + pmaxub xmm0, xmm8 + pcmpeqb xmm0, xmm8 + pand xmm0, xmmword ptr [rip + .LCPI11_6] + por xmm0, xmm14 + movdqa xmmword ptr [rsp + 208], xmm0 # 16-byte Spill + movzx esi, byte ptr [r11 + r9 + 29] + movd xmm14, esi + pinsrb xmm1, byte ptr [r11 + rcx + 16], 1 + pinsrb xmm1, byte ptr [r11 + r10 + 16], 2 + pinsrb xmm1, byte ptr [r11 + rdx + 16], 3 + pinsrb xmm1, byte ptr [r11 + r14 + 16], 4 + pinsrb xmm1, byte ptr [r11 + rbx + 16], 5 + mov r10, rbx + pinsrb xmm1, byte ptr [r11 + r15 + 16], 6 + mov r14, r15 + mov r9, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + r9 + 16], 7 + pinsrb xmm1, byte ptr [r11 + rax + 16], 8 + mov r8, r12 + pinsrb xmm1, byte ptr [r11 + r12 + 16], 9 + mov rax, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + rax + 16], 10 + mov r15, rax + pinsrb xmm1, byte ptr [r11 + rdi + 16], 11 mov rax, qword ptr [rsp + 48] # 8-byte Reload - jne .LBB11_127 - jmp .LBB11_130 -.LBB11_182: - mov r8, r10 - and r8, -4 - mov rbx, r8 - shl rbx, 7 - add rbx, rdx - lea r14, [r15 + 4*r8] - movaps xmm1, xmm0 - shufps xmm1, xmm0, 0 # xmm1 = xmm1[0,0],xmm0[0,0] - add rdx, 508 - xor ecx, ecx - movdqa xmm15, xmmword ptr [rip + .LCPI11_0] # xmm15 = <1,1,1,1,u,u,u,u,u,u,u,u,u,u,u,u> - movdqa xmm8, xmmword ptr [rip + .LCPI11_1] # xmm8 = [252,252,252,252,252,252,252,252,252,252,252,252,252,252,252,252] - movdqa xmm10, xmmword ptr [rip + .LCPI11_2] # xmm10 = [248,248,248,248,248,248,248,248,248,248,248,248,248,248,248,248] - movdqa xmm11, xmmword ptr [rip + .LCPI11_3] # xmm11 = [240,240,240,240,240,240,240,240,240,240,240,240,240,240,240,240] - movdqa xmm12, xmmword ptr [rip + .LCPI11_4] # xmm12 = [224,224,224,224,224,224,224,224,224,224,224,224,224,224,224,224] - movdqa xmm13, xmmword ptr [rip + .LCPI11_5] # xmm13 = [192,192,192,192,192,192,192,192,192,192,192,192,192,192,192,192] - movdqa xmm14, xmmword ptr [rip + .LCPI11_6] # xmm14 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] - movdqa xmm9, xmmword ptr [rip + .LCPI11_7] # xmm9 = [0,8,1,9,2,10,3,11,4,12,5,13,6,14,7,15] - .p2align 4, 0x90 -.LBB11_183: # =>This Inner Loop Header: Depth=1 - movss xmm6, dword ptr [rdx - 508] # xmm6 = mem[0],zero,zero,zero - movss xmm7, dword ptr [rdx - 504] # xmm7 = mem[0],zero,zero,zero - movss xmm5, dword ptr [rdx - 500] # xmm5 = mem[0],zero,zero,zero - movss xmm4, dword ptr [rdx - 496] # xmm4 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rdx - 380], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rdx - 252], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rdx - 124], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpleps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - insertps xmm7, dword ptr [rdx - 376], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rdx - 248], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rdx - 120], 48 # xmm7 = xmm7[0,1,2],mem[0] - insertps xmm5, dword ptr [rdx - 372], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rdx - 244], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rdx - 116], 48 # xmm5 = xmm5[0,1,2],mem[0] - insertps xmm4, dword ptr [rdx - 368], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] - insertps xmm4, dword ptr [rdx - 240], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] - insertps xmm4, dword ptr [rdx - 112], 48 # xmm4 = xmm4[0,1,2],mem[0] - cmpleps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - movdqa xmm2, xmm7 - pand xmm2, xmm15 - psubb xmm2, xmm7 - movss xmm7, dword ptr [rdx - 492] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rdx - 364], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rdx - 236], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rdx - 108], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm2, xmm6 - movss xmm6, dword ptr [rdx - 488] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rdx - 360], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rdx - 232], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rdx - 104], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpleps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 2 - pand xmm5, xmm8 - por xmm5, xmm2 - movss xmm3, dword ptr [rdx - 484] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rdx - 356], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rdx - 228], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [rdx - 100], 48 # xmm3 = xmm3[0,1,2],mem[0] - cmpleps xmm4, xmm1 - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 + pinsrb xmm1, byte ptr [r11 + rax + 16], 12 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + rax + 16], 13 + mov rdi, r13 + pinsrb xmm1, byte ptr [r11 + r13 + 16], 14 + mov rsi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm1, byte ptr [r11 + rsi + 16], 15 + pmaxub xmm1, xmm8 + pcmpeqb xmm1, xmm8 + pinsrb xmm5, byte ptr [r11 + rcx + 17], 1 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rbx + 17], 2 + pinsrb xmm5, byte ptr [r11 + rdx + 17], 3 + mov r13, rdx + mov rdx, qword ptr [rsp + 160] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rdx + 17], 4 + pinsrb xmm5, byte ptr [r11 + r10 + 17], 5 + mov r12, r10 + pinsrb xmm5, byte ptr [r11 + r14 + 17], 6 + pinsrb xmm5, byte ptr [r11 + r9 + 17], 7 + mov rcx, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rcx + 17], 8 + pinsrb xmm5, byte ptr [r11 + r8 + 17], 9 + pinsrb xmm5, byte ptr [r11 + r15 + 17], 10 + mov rcx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + rcx + 17], 11 + mov r10, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm5, byte ptr [r11 + r10 + 17], 12 + pinsrb xmm5, byte ptr [r11 + rax + 17], 13 + pinsrb xmm5, byte ptr [r11 + rdi + 17], 14 + pinsrb xmm5, byte ptr [r11 + rsi + 17], 15 + pmaxub xmm5, xmm8 + pcmpeqb xmm5, xmm8 + pand xmm5, xmmword ptr [rip + .LCPI11_16] + psubb xmm5, xmm1 + mov rax, qword ptr [rsp + 80] # 8-byte Reload + movzx esi, byte ptr [r11 + rax + 30] + movd xmm1, esi + mov rsi, qword ptr [rsp + 56] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rsi + 18], 1 + pinsrb xmm3, byte ptr [r11 + rsi + 19], 1 + pinsrb xmm6, byte ptr [r11 + rsi + 20], 1 + pinsrb xmm4, byte ptr [r11 + rsi + 21], 1 + pinsrb xmm7, byte ptr [r11 + rsi + 22], 1 + pinsrb xmm2, byte ptr [r11 + rsi + 23], 1 + pinsrb xmm9, byte ptr [r11 + rsi + 24], 1 + pinsrb xmm12, byte ptr [r11 + rsi + 25], 1 + pinsrb xmm13, byte ptr [r11 + rsi + 26], 1 + pinsrb xmm10, byte ptr [r11 + rsi + 27], 1 + pinsrb xmm11, byte ptr [r11 + rsi + 28], 1 + pinsrb xmm14, byte ptr [r11 + rsi + 29], 1 + pinsrb xmm1, byte ptr [r11 + rsi + 30], 1 + movzx eax, byte ptr [r11 + rax + 31] + movd xmm0, eax + pinsrb xmm0, byte ptr [r11 + rsi + 31], 1 + pinsrb xmm15, byte ptr [r11 + rbx + 18], 2 + mov rdi, r13 + pinsrb xmm15, byte ptr [r11 + r13 + 18], 3 + pinsrb xmm15, byte ptr [r11 + rdx + 18], 4 + mov r13, rdx + pinsrb xmm15, byte ptr [r11 + r12 + 18], 5 + mov rdx, r14 + pinsrb xmm15, byte ptr [r11 + r14 + 18], 6 + pinsrb xmm15, byte ptr [r11 + r9 + 18], 7 + mov r15, r9 + mov rsi, qword ptr [rsp + 72] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rsi + 18], 8 + pinsrb xmm15, byte ptr [r11 + r8 + 18], 9 + mov r8, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + r8 + 18], 10 + pinsrb xmm15, byte ptr [r11 + rcx + 18], 11 + pinsrb xmm15, byte ptr [r11 + r10 + 18], 12 + mov r14, r10 + mov rax, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rax + 18], 13 + mov r9, qword ptr [rsp + 96] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + r9 + 18], 14 + mov rcx, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm15, byte ptr [r11 + rcx + 18], 15 + mov rbx, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rbx + 19], 2 + pinsrb xmm3, byte ptr [r11 + rdi + 19], 3 + mov r10, rdi + pinsrb xmm3, byte ptr [r11 + r13 + 19], 4 + mov rbx, r13 + pinsrb xmm3, byte ptr [r11 + r12 + 19], 5 + pinsrb xmm3, byte ptr [r11 + rdx + 19], 6 + pinsrb xmm3, byte ptr [r11 + r15 + 19], 7 + pinsrb xmm3, byte ptr [r11 + rsi + 19], 8 + mov r15, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + r15 + 19], 9 + pinsrb xmm3, byte ptr [r11 + r8 + 19], 10 + mov rdx, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm3, byte ptr [r11 + rdx + 19], 11 + pinsrb xmm3, byte ptr [r11 + r14 + 19], 12 + pinsrb xmm3, byte ptr [r11 + rax + 19], 13 + pinsrb xmm3, byte ptr [r11 + r9 + 19], 14 + mov r13, r9 + pinsrb xmm3, byte ptr [r11 + rcx + 19], 15 + mov rdi, qword ptr [rsp + 64] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdi + 20], 2 + pinsrb xmm4, byte ptr [r11 + rdi + 21], 2 + pinsrb xmm7, byte ptr [r11 + rdi + 22], 2 + pinsrb xmm2, byte ptr [r11 + rdi + 23], 2 + pinsrb xmm9, byte ptr [r11 + rdi + 24], 2 + pinsrb xmm12, byte ptr [r11 + rdi + 25], 2 + pinsrb xmm13, byte ptr [r11 + rdi + 26], 2 + pinsrb xmm10, byte ptr [r11 + rdi + 27], 2 + pinsrb xmm11, byte ptr [r11 + rdi + 28], 2 + pinsrb xmm14, byte ptr [r11 + rdi + 29], 2 + pinsrb xmm1, byte ptr [r11 + rdi + 30], 2 + pmaxub xmm15, xmm8 + pcmpeqb xmm15, xmm8 + pand xmm15, xmmword ptr [rip + .LCPI11_17] + pmaxub xmm3, xmm8 + pcmpeqb xmm3, xmm8 + pand xmm3, xmmword ptr [rip + .LCPI11_18] + por xmm3, xmm15 + pinsrb xmm0, byte ptr [r11 + rdi + 31], 2 + por xmm3, xmm5 + pinsrb xmm6, byte ptr [r11 + r10 + 20], 3 + pinsrb xmm6, byte ptr [r11 + rbx + 20], 4 + pinsrb xmm6, byte ptr [r11 + r12 + 20], 5 + mov r9, r12 + mov r14, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r14 + 20], 6 + mov rdx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdx + 20], 7 + pinsrb xmm6, byte ptr [r11 + rsi + 20], 8 + mov r8, r15 + pinsrb xmm6, byte ptr [r11 + r15 + 20], 9 + mov r15, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r15 + 20], 10 + mov rax, qword ptr [rsp + 24] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rax + 20], 11 + mov rcx, qword ptr [rsp + 48] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rcx + 20], 12 + mov r12, qword ptr [rsp + 16] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + r12 + 20], 13 + pinsrb xmm6, byte ptr [r11 + r13 + 20], 14 + mov rdi, qword ptr [rsp + 32] # 8-byte Reload + pinsrb xmm6, byte ptr [r11 + rdi + 20], 15 + pinsrb xmm4, byte ptr [r11 + r10 + 21], 3 + pinsrb xmm4, byte ptr [r11 + rbx + 21], 4 + pinsrb xmm4, byte ptr [r11 + r9 + 21], 5 + pinsrb xmm4, byte ptr [r11 + r14 + 21], 6 + pinsrb xmm4, byte ptr [r11 + rdx + 21], 7 + pinsrb xmm4, byte ptr [r11 + rsi + 21], 8 + pinsrb xmm4, byte ptr [r11 + r8 + 21], 9 + pinsrb xmm4, byte ptr [r11 + r15 + 21], 10 + pinsrb xmm4, byte ptr [r11 + rax + 21], 11 + pinsrb xmm4, byte ptr [r11 + rcx + 21], 12 + pinsrb xmm4, byte ptr [r11 + r12 + 21], 13 + pinsrb xmm4, byte ptr [r11 + r13 + 21], 14 + pinsrb xmm4, byte ptr [r11 + rdi + 21], 15 + pinsrb xmm7, byte ptr [r11 + r10 + 22], 3 + pinsrb xmm7, byte ptr [r11 + rbx + 22], 4 + pinsrb xmm7, byte ptr [r11 + r9 + 22], 5 + pinsrb xmm7, byte ptr [r11 + r14 + 22], 6 + pinsrb xmm7, byte ptr [r11 + rdx + 22], 7 + pinsrb xmm7, byte ptr [r11 + rsi + 22], 8 + pinsrb xmm7, byte ptr [r11 + r8 + 22], 9 + mov rdx, r15 + pinsrb xmm7, byte ptr [r11 + r15 + 22], 10 + pinsrb xmm7, byte ptr [r11 + rax + 22], 11 + pinsrb xmm7, byte ptr [r11 + rcx + 22], 12 + mov rdx, rcx + pinsrb xmm7, byte ptr [r11 + r12 + 22], 13 + pinsrb xmm7, byte ptr [r11 + r13 + 22], 14 + pinsrb xmm7, byte ptr [r11 + rdi + 22], 15 + mov r15, rdi + pmaxub xmm6, xmm8 + pcmpeqb xmm6, xmm8 + movdqa xmm5, xmmword ptr [rip + .LCPI11_19] # xmm5 = [16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16] + pand xmm6, xmm5 + pmaxub xmm4, xmm8 + pcmpeqb xmm4, xmm8 + movdqa xmm15, xmmword ptr [rip + .LCPI11_20] # xmm15 = [32,32,32,32,32,32,32,32,32,32,32,32,32,32,32,32] pand xmm4, xmm15 - psllw xmm4, 3 - pand xmm4, xmm10 - cmpleps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 4 - pand xmm7, xmm11 + por xmm4, xmm6 + pmaxub xmm7, xmm8 + pcmpeqb xmm7, xmm8 + movdqa xmm6, xmmword ptr [rip + .LCPI11_21] # xmm6 = [64,64,64,64,64,64,64,64,64,64,64,64,64,64,64,64] + pand xmm7, xmm6 por xmm7, xmm4 - movss xmm4, dword ptr [rdx - 480] # xmm4 = mem[0],zero,zero,zero - insertps xmm4, dword ptr [rdx - 352], 16 # xmm4 = xmm4[0],mem[0],xmm4[2,3] - insertps xmm4, dword ptr [rdx - 224], 32 # xmm4 = xmm4[0,1],mem[0],xmm4[3] - insertps xmm4, dword ptr [rdx - 96], 48 # xmm4 = xmm4[0,1,2],mem[0] - por xmm7, xmm5 - movss xmm5, dword ptr [rdx - 476] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rdx - 348], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rdx - 220], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rdx - 92], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpleps xmm5, xmm1 - packssdw xmm5, xmm5 - cmpleps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - cmpleps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 6 - pand xmm3, xmm13 - por xmm3, xmm6 - movss xmm2, dword ptr [rdx - 472] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rdx - 344], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rdx - 216], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rdx - 88], 48 # xmm2 = xmm2[0,1,2],mem[0] - packsswb xmm5, xmm5 - cmpleps xmm4, xmm1 - packssdw xmm4, xmm4 - packsswb xmm4, xmm4 - psllw xmm4, 7 - pand xmm4, xmm14 - por xmm4, xmm3 - movss xmm3, dword ptr [rdx - 468] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rdx - 340], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rdx - 212], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - pand xmm5, xmm15 - insertps xmm3, dword ptr [rdx - 84], 48 # xmm3 = xmm3[0,1,2],mem[0] - por xmm4, xmm7 - cmpleps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm6, xmm2 - pand xmm6, xmm15 - psubb xmm6, xmm2 - movss xmm7, dword ptr [rdx - 464] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rdx - 336], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rdx - 208], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rdx - 80], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm6, xmm5 - movss xmm5, dword ptr [rdx - 460] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rdx - 332], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rdx - 204], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rdx - 76], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpleps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm6 - movss xmm6, dword ptr [rdx - 456] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rdx - 328], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rdx - 200], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rdx - 72], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpleps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 3 - pand xmm7, xmm10 - cmpleps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 4 - pand xmm5, xmm11 - por xmm5, xmm7 - movss xmm2, dword ptr [rdx - 452] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rdx - 324], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rdx - 196], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rdx - 68], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm5, xmm3 - movss xmm7, dword ptr [rdx - 448] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rdx - 320], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rdx - 192], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rdx - 64], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpleps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 5 - pand xmm6, xmm12 - cmpleps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm6 - movss xmm6, dword ptr [rdx - 444] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rdx - 316], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rdx - 188], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rdx - 60], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpleps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - cmpleps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - psllw xmm7, 7 - pand xmm7, xmm14 - por xmm7, xmm2 - movss xmm2, dword ptr [rdx - 440] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rdx - 312], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rdx - 184], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rdx - 56], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm7, xmm5 - movss xmm3, dword ptr [rdx - 436] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rdx - 308], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rdx - 180], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - pand xmm6, xmm15 - insertps xmm3, dword ptr [rdx - 52], 48 # xmm3 = xmm3[0,1,2],mem[0] - punpckldq xmm4, xmm7 # xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1] - cmpleps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm7, xmm2 - pand xmm7, xmm15 - psubb xmm7, xmm2 - movss xmm5, dword ptr [rdx - 432] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rdx - 304], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rdx - 176], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rdx - 48], 48 # xmm5 = xmm5[0,1,2],mem[0] - por xmm7, xmm6 - movss xmm6, dword ptr [rdx - 428] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rdx - 300], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rdx - 172], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rdx - 44], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpleps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm7 - movss xmm7, dword ptr [rdx - 424] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rdx - 296], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rdx - 168], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rdx - 40], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpleps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - pand xmm5, xmm15 - psllw xmm5, 3 - pand xmm5, xmm10 - cmpleps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 4 - pand xmm6, xmm11 - por xmm6, xmm5 - movss xmm2, dword ptr [rdx - 420] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rdx - 292], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rdx - 164], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rdx - 36], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm6, xmm3 - movss xmm5, dword ptr [rdx - 416] # xmm5 = mem[0],zero,zero,zero - insertps xmm5, dword ptr [rdx - 288], 16 # xmm5 = xmm5[0],mem[0],xmm5[2,3] - insertps xmm5, dword ptr [rdx - 160], 32 # xmm5 = xmm5[0,1],mem[0],xmm5[3] - insertps xmm5, dword ptr [rdx - 32], 48 # xmm5 = xmm5[0,1,2],mem[0] - cmpleps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 5 - pand xmm7, xmm12 - cmpleps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 - por xmm2, xmm7 - movss xmm7, dword ptr [rdx - 412] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rdx - 284], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rdx - 156], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rdx - 28], 48 # xmm7 = xmm7[0,1,2],mem[0] - cmpleps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - cmpleps xmm5, xmm1 - packssdw xmm5, xmm5 - packsswb xmm5, xmm5 - psllw xmm5, 7 - pand xmm5, xmm14 - por xmm5, xmm2 - movss xmm2, dword ptr [rdx - 408] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rdx - 280], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rdx - 152], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - pand xmm7, xmm15 - insertps xmm2, dword ptr [rdx - 24], 48 # xmm2 = xmm2[0,1,2],mem[0] - por xmm5, xmm6 - cmpleps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - movdqa xmm6, xmm2 - pand xmm6, xmm15 - psubb xmm6, xmm2 - movss xmm3, dword ptr [rdx - 404] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rdx - 276], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rdx - 148], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [rdx - 20], 48 # xmm3 = xmm3[0,1,2],mem[0] - por xmm6, xmm7 - movss xmm2, dword ptr [rdx - 400] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rdx - 272], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rdx - 144], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rdx - 16], 48 # xmm2 = xmm2[0,1,2],mem[0] - cmpleps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - pand xmm3, xmm15 - psllw xmm3, 2 - pand xmm3, xmm8 - por xmm3, xmm6 - movss xmm6, dword ptr [rdx - 396] # xmm6 = mem[0],zero,zero,zero - insertps xmm6, dword ptr [rdx - 268], 16 # xmm6 = xmm6[0],mem[0],xmm6[2,3] - insertps xmm6, dword ptr [rdx - 140], 32 # xmm6 = xmm6[0,1],mem[0],xmm6[3] - insertps xmm6, dword ptr [rdx - 12], 48 # xmm6 = xmm6[0,1,2],mem[0] - cmpleps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 3 - pand xmm2, xmm10 - cmpleps xmm6, xmm1 - packssdw xmm6, xmm6 - packsswb xmm6, xmm6 - pand xmm6, xmm15 - psllw xmm6, 4 - pand xmm6, xmm11 - por xmm6, xmm2 - movss xmm7, dword ptr [rdx - 392] # xmm7 = mem[0],zero,zero,zero - insertps xmm7, dword ptr [rdx - 264], 16 # xmm7 = xmm7[0],mem[0],xmm7[2,3] - insertps xmm7, dword ptr [rdx - 136], 32 # xmm7 = xmm7[0,1],mem[0],xmm7[3] - insertps xmm7, dword ptr [rdx - 8], 48 # xmm7 = xmm7[0,1,2],mem[0] - por xmm6, xmm3 - movss xmm2, dword ptr [rdx - 388] # xmm2 = mem[0],zero,zero,zero - insertps xmm2, dword ptr [rdx - 260], 16 # xmm2 = xmm2[0],mem[0],xmm2[2,3] - insertps xmm2, dword ptr [rdx - 132], 32 # xmm2 = xmm2[0,1],mem[0],xmm2[3] - insertps xmm2, dword ptr [rdx - 4], 48 # xmm2 = xmm2[0,1,2],mem[0] - cmpleps xmm7, xmm1 - packssdw xmm7, xmm7 - packsswb xmm7, xmm7 - pand xmm7, xmm15 - psllw xmm7, 5 - pand xmm7, xmm12 - cmpleps xmm2, xmm1 - packssdw xmm2, xmm2 - packsswb xmm2, xmm2 - pand xmm2, xmm15 - psllw xmm2, 6 - pand xmm2, xmm13 + por xmm7, xmm3 + pinsrb xmm2, byte ptr [r11 + r10 + 23], 3 + mov r14, rbx + pinsrb xmm2, byte ptr [r11 + rbx + 23], 4 + mov rbx, r9 + pinsrb xmm2, byte ptr [r11 + r9 + 23], 5 + mov rdi, qword ptr [rsp + 120] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rdi + 23], 6 + mov rcx, qword ptr [rsp + 88] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + rcx + 23], 7 + pinsrb xmm2, byte ptr [r11 + rsi + 23], 8 + pinsrb xmm2, byte ptr [r11 + r8 + 23], 9 + mov r9, qword ptr [rsp + 40] # 8-byte Reload + pinsrb xmm2, byte ptr [r11 + r9 + 23], 10 + pinsrb xmm2, byte ptr [r11 + rax + 23], 11 + pinsrb xmm2, byte ptr [r11 + rdx + 23], 12 + pinsrb xmm2, byte ptr [r11 + r12 + 23], 13 + pinsrb xmm2, byte ptr [r11 + r13 + 23], 14 + pinsrb xmm2, byte ptr [r11 + r15 + 23], 15 + pmaxub xmm2, xmm8 + pcmpeqb xmm2, xmm8 + movdqa xmm3, xmmword ptr [rip + .LCPI11_6] # xmm3 = [128,128,128,128,128,128,128,128,128,128,128,128,128,128,128,128] + pand xmm2, xmm3 por xmm2, xmm7 - movss xmm3, dword ptr [rdx - 384] # xmm3 = mem[0],zero,zero,zero - insertps xmm3, dword ptr [rdx - 256], 16 # xmm3 = xmm3[0],mem[0],xmm3[2,3] - insertps xmm3, dword ptr [rdx - 128], 32 # xmm3 = xmm3[0,1],mem[0],xmm3[3] - insertps xmm3, dword ptr [rdx], 48 # xmm3 = xmm3[0,1,2],mem[0] - cmpleps xmm3, xmm1 - packssdw xmm3, xmm3 - packsswb xmm3, xmm3 - psllw xmm3, 7 - pand xmm3, xmm14 - por xmm3, xmm2 - por xmm3, xmm6 - punpckldq xmm5, xmm3 # xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1] - punpcklbw xmm4, xmm5 # xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3],xmm4[4],xmm5[4],xmm4[5],xmm5[5],xmm4[6],xmm5[6],xmm4[7],xmm5[7] - pshufb xmm4, xmm9 - movdqu xmmword ptr [r15 + 4*rcx], xmm4 - add rcx, 4 - add rdx, 512 - cmp r8, rcx - jne .LBB11_183 -# %bb.184: - cmp r10, r8 - jne .LBB11_185 - jmp .LBB11_188 + pinsrb xmm9, byte ptr [r11 + r10 + 24], 3 + pinsrb xmm9, byte ptr [r11 + r14 + 24], 4 + pinsrb xmm9, byte ptr [r11 + rbx + 24], 5 + pinsrb xmm9, byte ptr [r11 + rdi + 24], 6 + pinsrb xmm9, byte ptr [r11 + rcx + 24], 7 + pinsrb xmm9, byte ptr [r11 + rsi + 24], 8 + pinsrb xmm9, byte ptr [r11 + r8 + 24], 9 + pinsrb xmm9, byte ptr [r11 + r9 + 24], 10 + pinsrb xmm9, byte ptr [r11 + rax + 24], 11 + pinsrb xmm9, byte ptr [r11 + rdx + 24], 12 + pinsrb xmm9, byte ptr [r11 + r12 + 24], 13 + pinsrb xmm9, byte ptr [r11 + r13 + 24], 14 + pinsrb xmm9, byte ptr [r11 + r15 + 24], 15 + pmaxub xmm9, xmm8 + pcmpeqb xmm9, xmm8 + pinsrb xmm12, byte ptr [r11 + r10 + 25], 3 + pinsrb xmm12, byte ptr [r11 + r14 + 25], 4 + pinsrb xmm12, byte ptr [r11 + rbx + 25], 5 + pinsrb xmm12, byte ptr [r11 + rdi + 25], 6 + pinsrb xmm12, byte ptr [r11 + rcx + 25], 7 + pinsrb xmm12, byte ptr [r11 + rsi + 25], 8 + pinsrb xmm12, byte ptr [r11 + r8 + 25], 9 + pinsrb xmm12, byte ptr [r11 + r9 + 25], 10 + pinsrb xmm12, byte ptr [r11 + rax + 25], 11 + pinsrb xmm12, byte ptr [r11 + rdx + 25], 12 + pinsrb xmm12, byte ptr [r11 + r12 + 25], 13 + pinsrb xmm12, byte ptr [r11 + r13 + 25], 14 + pinsrb xmm12, byte ptr [r11 + r15 + 25], 15 + pmaxub xmm12, xmm8 + pcmpeqb xmm12, xmm8 + pand xmm12, xmmword ptr [rip + .LCPI11_16] + psubb xmm12, xmm9 + pinsrb xmm13, byte ptr [r11 + r10 + 26], 3 + pinsrb xmm13, byte ptr [r11 + r14 + 26], 4 + pinsrb xmm13, byte ptr [r11 + rbx + 26], 5 + pinsrb xmm13, byte ptr [r11 + rdi + 26], 6 + pinsrb xmm13, byte ptr [r11 + rcx + 26], 7 + pinsrb xmm13, byte ptr [r11 + rsi + 26], 8 + pinsrb xmm13, byte ptr [r11 + r8 + 26], 9 + pinsrb xmm13, byte ptr [r11 + r9 + 26], 10 + pinsrb xmm13, byte ptr [r11 + rax + 26], 11 + pinsrb xmm13, byte ptr [r11 + rdx + 26], 12 + pinsrb xmm13, byte ptr [r11 + r12 + 26], 13 + pinsrb xmm13, byte ptr [r11 + r13 + 26], 14 + pinsrb xmm13, byte ptr [r11 + r15 + 26], 15 + pinsrb xmm10, byte ptr [r11 + r10 + 27], 3 + pinsrb xmm10, byte ptr [r11 + r14 + 27], 4 + pinsrb xmm10, byte ptr [r11 + rbx + 27], 5 + pinsrb xmm10, byte ptr [r11 + rdi + 27], 6 + pinsrb xmm10, byte ptr [r11 + rcx + 27], 7 + pinsrb xmm10, byte ptr [r11 + rsi + 27], 8 + pinsrb xmm10, byte ptr [r11 + r8 + 27], 9 + pinsrb xmm10, byte ptr [r11 + r9 + 27], 10 + pinsrb xmm10, byte ptr [r11 + rax + 27], 11 + mov r8, rax + pinsrb xmm10, byte ptr [r11 + rdx + 27], 12 + pinsrb xmm10, byte ptr [r11 + r12 + 27], 13 + pinsrb xmm10, byte ptr [r11 + r13 + 27], 14 + pinsrb xmm10, byte ptr [r11 + r15 + 27], 15 + pmaxub xmm13, xmm8 + pcmpeqb xmm13, xmm8 + pand xmm13, xmmword ptr [rip + .LCPI11_17] + pmaxub xmm10, xmm8 + pcmpeqb xmm10, xmm8 + pand xmm10, xmmword ptr [rip + .LCPI11_18] + por xmm10, xmm13 + por xmm10, xmm12 + pinsrb xmm11, byte ptr [r11 + r10 + 28], 3 + pinsrb xmm14, byte ptr [r11 + r10 + 29], 3 + pinsrb xmm1, byte ptr [r11 + r10 + 30], 3 + pinsrb xmm0, byte ptr [r11 + r10 + 31], 3 + pinsrb xmm11, byte ptr [r11 + r14 + 28], 4 + pinsrb xmm14, byte ptr [r11 + r14 + 29], 4 + pinsrb xmm1, byte ptr [r11 + r14 + 30], 4 + pinsrb xmm0, byte ptr [r11 + r14 + 31], 4 + mov rax, rbx + pinsrb xmm11, byte ptr [r11 + rbx + 28], 5 + pinsrb xmm14, byte ptr [r11 + rbx + 29], 5 + pinsrb xmm1, byte ptr [r11 + rbx + 30], 5 + pinsrb xmm0, byte ptr [r11 + rbx + 31], 5 + mov rax, rdi + pinsrb xmm11, byte ptr [r11 + rdi + 28], 6 + pinsrb xmm14, byte ptr [r11 + rdi + 29], 6 + pinsrb xmm1, byte ptr [r11 + rdi + 30], 6 + pinsrb xmm0, byte ptr [r11 + rdi + 31], 6 + mov rbx, qword ptr [rsp + 136] # 8-byte Reload + mov rax, rcx + pinsrb xmm11, byte ptr [r11 + rcx + 28], 7 + pinsrb xmm14, byte ptr [r11 + rcx + 29], 7 + pinsrb xmm1, byte ptr [r11 + rcx + 30], 7 + pinsrb xmm0, byte ptr [r11 + rcx + 31], 7 + mov rax, rsi + pinsrb xmm11, byte ptr [r11 + rsi + 28], 8 + pinsrb xmm14, byte ptr [r11 + rsi + 29], 8 + pinsrb xmm1, byte ptr [r11 + rsi + 30], 8 + pinsrb xmm0, byte ptr [r11 + rsi + 31], 8 + mov rax, qword ptr [rsp + 104] # 8-byte Reload + pinsrb xmm11, byte ptr [r11 + rax + 28], 9 + pinsrb xmm14, byte ptr [r11 + rax + 29], 9 + pinsrb xmm1, byte ptr [r11 + rax + 30], 9 + pinsrb xmm0, byte ptr [r11 + rax + 31], 9 + mov rax, r9 + pinsrb xmm11, byte ptr [r11 + r9 + 28], 10 + pinsrb xmm14, byte ptr [r11 + r9 + 29], 10 + pinsrb xmm1, byte ptr [r11 + r9 + 30], 10 + pinsrb xmm0, byte ptr [r11 + r9 + 31], 10 + mov rax, r8 + pinsrb xmm11, byte ptr [r11 + r8 + 28], 11 + pinsrb xmm14, byte ptr [r11 + r8 + 29], 11 + pinsrb xmm1, byte ptr [r11 + r8 + 30], 11 + pinsrb xmm0, byte ptr [r11 + r8 + 31], 11 + pinsrb xmm11, byte ptr [r11 + rdx + 28], 12 + pinsrb xmm14, byte ptr [r11 + rdx + 29], 12 + pinsrb xmm1, byte ptr [r11 + rdx + 30], 12 + pinsrb xmm0, byte ptr [r11 + rdx + 31], 12 + mov rax, r12 + pinsrb xmm11, byte ptr [r11 + r12 + 28], 13 + pinsrb xmm14, byte ptr [r11 + r12 + 29], 13 + pinsrb xmm1, byte ptr [r11 + r12 + 30], 13 + pinsrb xmm0, byte ptr [r11 + r12 + 31], 13 + mov rax, r13 + pinsrb xmm11, byte ptr [r11 + r13 + 28], 14 + pinsrb xmm14, byte ptr [r11 + r13 + 29], 14 + pinsrb xmm1, byte ptr [r11 + r13 + 30], 14 + pinsrb xmm0, byte ptr [r11 + r13 + 31], 14 + mov rax, r15 + pinsrb xmm11, byte ptr [r11 + r15 + 28], 15 + pinsrb xmm14, byte ptr [r11 + r15 + 29], 15 + pinsrb xmm1, byte ptr [r11 + r15 + 30], 15 + pinsrb xmm0, byte ptr [r11 + r15 + 31], 15 + pmaxub xmm11, xmm8 + pcmpeqb xmm11, xmm8 + pand xmm11, xmm5 + pmaxub xmm14, xmm8 + pcmpeqb xmm14, xmm8 + pand xmm14, xmm15 + por xmm14, xmm11 + pmaxub xmm1, xmm8 + pcmpeqb xmm1, xmm8 + pand xmm1, xmm6 + por xmm1, xmm14 + por xmm1, xmm10 + pmaxub xmm0, xmm8 + pcmpeqb xmm0, xmm8 + pand xmm0, xmm3 + por xmm0, xmm1 + movdqa xmm1, xmm2 + punpcklbw xmm1, xmm0 # xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7] + movdqa xmm5, xmmword ptr [rsp + 224] # 16-byte Reload + movdqa xmm3, xmm5 + movdqa xmm6, xmmword ptr [rsp + 208] # 16-byte Reload + punpcklbw xmm3, xmm6 # xmm3 = xmm3[0],xmm6[0],xmm3[1],xmm6[1],xmm3[2],xmm6[2],xmm3[3],xmm6[3],xmm3[4],xmm6[4],xmm3[5],xmm6[5],xmm3[6],xmm6[6],xmm3[7],xmm6[7] + movdqa xmm4, xmm3 + punpcklwd xmm4, xmm1 # xmm4 = xmm4[0],xmm1[0],xmm4[1],xmm1[1],xmm4[2],xmm1[2],xmm4[3],xmm1[3] + punpckhwd xmm3, xmm1 # xmm3 = xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7] + punpckhbw xmm2, xmm0 # xmm2 = xmm2[8],xmm0[8],xmm2[9],xmm0[9],xmm2[10],xmm0[10],xmm2[11],xmm0[11],xmm2[12],xmm0[12],xmm2[13],xmm0[13],xmm2[14],xmm0[14],xmm2[15],xmm0[15] + punpckhbw xmm5, xmm6 # xmm5 = xmm5[8],xmm6[8],xmm5[9],xmm6[9],xmm5[10],xmm6[10],xmm5[11],xmm6[11],xmm5[12],xmm6[12],xmm5[13],xmm6[13],xmm5[14],xmm6[14],xmm5[15],xmm6[15] + movdqa xmm0, xmm5 + punpcklwd xmm0, xmm2 # xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3] + punpckhwd xmm5, xmm2 # xmm5 = xmm5[4],xmm2[4],xmm5[5],xmm2[5],xmm5[6],xmm2[6],xmm5[7],xmm2[7] + mov rcx, qword ptr [rsp + 144] # 8-byte Reload + movdqu xmmword ptr [rbx + 4*rcx + 48], xmm5 + movdqu xmmword ptr [rbx + 4*rcx + 32], xmm0 + movdqu xmmword ptr [rbx + 4*rcx + 16], xmm3 + movdqu xmmword ptr [rbx + 4*rcx], xmm4 + add rcx, 16 + mov rax, rcx + cmp rcx, qword ptr [rsp + 184] # 8-byte Folded Reload + jne .LBB11_226 +# %bb.227: + mov rcx, qword ptr [rsp + 256] # 8-byte Reload + cmp rcx, qword ptr [rsp + 184] # 8-byte Folded Reload + mov r15, qword ptr [rsp + 152] # 8-byte Reload + mov r13b, byte ptr [rsp + 8] # 1-byte Reload + mov rbx, qword ptr [rsp + 264] # 8-byte Reload + jne .LBB11_160 + jmp .LBB11_164 .Lfunc_end11: .size comparison_greater_equal_scalar_arr_sse4, .Lfunc_end11-comparison_greater_equal_scalar_arr_sse4 # -- End function diff --git a/arrow/compute/internal/kernels/scalar_comparison_avx2_amd64.s b/arrow/compute/internal/kernels/scalar_comparison_avx2_amd64.s index 30246a225..b8a0c4cec 100644 --- a/arrow/compute/internal/kernels/scalar_comparison_avx2_amd64.s +++ b/arrow/compute/internal/kernels/scalar_comparison_avx2_amd64.s @@ -11,96 +11,110 @@ TEXT ·_comparison_equal_arr_arr_avx2(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x8944; BYTE $0xc8 // mov eax, r9d - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB0_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB0_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB0_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB0_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB0_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_22 - WORD $0x9848 // cdqe - -LBB0_20: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_20 - LONG $0x01c48349 // add r12, 1 - -LBB0_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_26 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB0_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB0_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB0_24: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_26: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_28: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_32 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_30: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5940f41 // sete r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3940f41 // sete r11b @@ -109,21 +123,21 @@ LBB0_24: LONG $0xd7940f41 // sete r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2940f41 // sete r10b @@ -134,143 +148,143 @@ LBB0_24: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4940f41 // sete r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1940f41 // sete r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_24 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_30 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_28: +LBB0_34: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -278,107 +292,123 @@ LBB0_28: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_28 - JMP LBB0_123 - -LBB0_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB0_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB0_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB0_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_50 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB0_48: - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xcb20 // and bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB0_48 - LONG $0x01c48349 // add r12, 1 - -LBB0_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_54 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB0_52: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_34 + JMP LBB0_153 + +LBB0_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB0_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB0_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB0_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + +LBB0_58: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x107ba1c4; WORD $0xf604 // vmovsd xmm0, qword [rsi + 8*r14] + LONG $0x2e79a1c4; WORD $0xf204 // vucomisd xmm0, qword [rdx + 8*r14] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x2044; BYTE $0xd3 // and bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xf8c38349 // add r11, -8 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB0_58 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB0_60: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_62: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_66 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_64: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] LONG $0x4610fbc5; BYTE $0x08 // vmovsd xmm0, qword [rsi + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x4610fbc5; BYTE $0x10 // vmovsd xmm0, qword [rsi + 16] LONG $0x422ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rdx + 16] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x4610fbc5; BYTE $0x18 // vmovsd xmm0, qword [rsi + 24] LONG $0x422ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rdx + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x4610fbc5; BYTE $0x20 // vmovsd xmm0, qword [rsi + 32] LONG $0x422ef9c5; BYTE $0x20 // vucomisd xmm0, qword [rdx + 32] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x4610fbc5; BYTE $0x28 // vmovsd xmm0, qword [rsi + 40] LONG $0x422ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rdx + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -394,13 +424,13 @@ LBB0_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x4610fbc5; BYTE $0x40 // vmovsd xmm0, qword [rsi + 64] LONG $0x422ef9c5; BYTE $0x40 // vucomisd xmm0, qword [rdx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x4610fbc5; BYTE $0x48 // vmovsd xmm0, qword [rsi + 72] LONG $0x422ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rdx + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -411,117 +441,116 @@ LBB0_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x4610fbc5; BYTE $0x58 // vmovsd xmm0, qword [rsi + 88] LONG $0x422ef9c5; BYTE $0x58 // vucomisd xmm0, qword [rdx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x4610fbc5; BYTE $0x60 // vmovsd xmm0, qword [rsi + 96] LONG $0x422ef9c5; BYTE $0x60 // vucomisd xmm0, qword [rdx + 96] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x4610fbc5; BYTE $0x68 // vmovsd xmm0, qword [rsi + 104] LONG $0x422ef9c5; BYTE $0x68 // vucomisd xmm0, qword [rdx + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x4610fbc5; BYTE $0x70 // vmovsd xmm0, qword [rsi + 112] LONG $0x422ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rdx + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x4610fbc5; BYTE $0x78 // vmovsd xmm0, qword [rsi + 120] LONG $0x422ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rdx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl QUAD $0x000000808610fbc5 // vmovsd xmm0, qword [rsi + 128] QUAD $0x00000080822ef9c5 // vucomisd xmm0, qword [rdx + 128] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl QUAD $0x000000888610fbc5 // vmovsd xmm0, qword [rsi + 136] QUAD $0x00000088822ef9c5 // vucomisd xmm0, qword [rdx + 136] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl QUAD $0x000000908610fbc5 // vmovsd xmm0, qword [rsi + 144] QUAD $0x00000090822ef9c5 // vucomisd xmm0, qword [rdx + 144] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl QUAD $0x000000988610fbc5 // vmovsd xmm0, qword [rsi + 152] QUAD $0x00000098822ef9c5 // vucomisd xmm0, qword [rdx + 152] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd6940f41 // sete r14b - WORD $0x2041; BYTE $0xc6 // and r14b, al + LONG $0xd7940f41 // sete r15b + WORD $0x2041; BYTE $0xc7 // and r15b, al QUAD $0x000000a08610fbc5 // vmovsd xmm0, qword [rsi + 160] QUAD $0x000000a0822ef9c5 // vucomisd xmm0, qword [rdx + 160] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl QUAD $0x000000a88610fbc5 // vmovsd xmm0, qword [rsi + 168] QUAD $0x000000a8822ef9c5 // vucomisd xmm0, qword [rdx + 168] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl QUAD $0x000000b08610fbc5 // vmovsd xmm0, qword [rsi + 176] QUAD $0x000000b0822ef9c5 // vucomisd xmm0, qword [rdx + 176] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl QUAD $0x000000b88610fbc5 // vmovsd xmm0, qword [rsi + 184] QUAD $0x000000b8822ef9c5 // vucomisd xmm0, qword [rdx + 184] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f41 // sete r15b - WORD $0x2041; BYTE $0xc7 // and r15b, al + LONG $0xd2940f41 // sete r10b + WORD $0x2041; BYTE $0xc2 // and r10b, al QUAD $0x000000c08610fbc5 // vmovsd xmm0, qword [rsi + 192] QUAD $0x000000c0822ef9c5 // vucomisd xmm0, qword [rdx + 192] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl QUAD $0x000000c88610fbc5 // vmovsd xmm0, qword [rsi + 200] QUAD $0x000000c8822ef9c5 // vucomisd xmm0, qword [rdx + 200] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4940f41 // sete r12b + WORD $0x2041; BYTE $0xc4 // and r12b, al QUAD $0x000000d08610fbc5 // vmovsd xmm0, qword [rsi + 208] QUAD $0x000000d0822ef9c5 // vucomisd xmm0, qword [rdx + 208] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd3940f41 // sete r11b - WORD $0x2041; BYTE $0xc3 // and r11b, al + LONG $0xd6940f41 // sete r14b + WORD $0x2041; BYTE $0xc6 // and r14b, al QUAD $0x000000d88610fbc5 // vmovsd xmm0, qword [rsi + 216] QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd2940f41 // sete r10b - WORD $0x2041; BYTE $0xc2 // and r10b, al + LONG $0xd3940f41 // sete r11b + WORD $0x2041; BYTE $0xc3 // and r11b, al QUAD $0x000000e08610fbc5 // vmovsd xmm0, qword [rsi + 224] QUAD $0x000000e0822ef9c5 // vucomisd xmm0, qword [rdx + 224] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl QUAD $0x000000e88610fbc5 // vmovsd xmm0, qword [rsi + 232] QUAD $0x000000e8822ef9c5 // vucomisd xmm0, qword [rdx + 232] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl QUAD $0x000000f08610fbc5 // vmovsd xmm0, qword [rsi + 240] QUAD $0x000000f0822ef9c5 // vucomisd xmm0, qword [rdx + 240] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -533,109 +562,107 @@ LBB0_52: WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd0940f41 // sete r8b WORD $0x2041; BYTE $0xc0 // and r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0841; BYTE $0xce // or r14b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x74b60f44; WORD $0x0324 // movzx r14d, byte [rsp + 3] - WORD $0x0845; BYTE $0xee // or r14b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xda // or r10b, bl + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xd1 // or cl, r10b - LONG $0x24348845 // mov byte [r12], r14b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB0_52 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_64 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_56: +LBB0_68: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x0410fbc5; BYTE $0xce // vmovsd xmm0, qword [rsi + 8*rcx] LONG $0x042ef9c5; BYTE $0xca // vucomisd xmm0, qword [rdx + 8*rcx] @@ -645,98 +672,122 @@ LBB0_56: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB0_56 - JMP LBB0_123 + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB0_68 + JMP LBB0_153 LBB0_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB0_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_8 - WORD $0x9848 // cdqe - -LBB0_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xfd // mov r13, r15 + JE LBB0_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB0_9 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB0_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4940f41 // sete r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_6 - LONG $0x01c48349 // add r12, 1 - -LBB0_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_12 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB0_10: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB0_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + +LBB0_9: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_11: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_15 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB0_13: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7940f41 // sete r15b + LONG $0xd6940f41 // sete r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7940f40 // sete dil @@ -748,19 +799,19 @@ LBB0_10: LONG $0xd3940f41 // sete r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6940f41 // sete r14b + LONG $0xd7940f41 // sete r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0940f41 // sete r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4940f41 // sete r12b @@ -769,147 +820,146 @@ LBB0_10: LONG $0xd5940f41 // sete r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1940f41 // sete r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB0_10 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - -LBB0_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB0_13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + +LBB0_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_14: +LBB0_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -917,101 +967,117 @@ LBB0_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_14 - JMP LBB0_123 - -LBB0_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB0_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_36 - WORD $0x9848 // cdqe - -LBB0_34: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_34 - LONG $0x01c48349 // add r12, 1 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_17 + JMP LBB0_153 LBB0_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_40 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB0_38: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB0_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB0_41: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_43: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_45: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_49 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_47: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5940f41 // sete r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3940f41 // sete r11b @@ -1020,21 +1086,21 @@ LBB0_38: LONG $0xd7940f41 // sete r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2940f41 // sete r10b @@ -1045,143 +1111,143 @@ LBB0_38: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4940f41 // sete r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1940f41 // sete r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_38 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_47 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_42: +LBB0_51: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -1189,97 +1255,113 @@ LBB0_42: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_42 - JMP LBB0_123 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_51 + JMP LBB0_153 -LBB0_68: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_72 - WORD $0x9848 // cdqe - -LBB0_70: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_70 - LONG $0x01c48349 // add r12, 1 +LBB0_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB0_86: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB0_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_76 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB0_88: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 -LBB0_74: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_90: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_94 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_92: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5940f41 // sete r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3940f41 // sete r11b @@ -1288,21 +1370,21 @@ LBB0_74: LONG $0xd7940f41 // sete r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2940f41 // sete r10b @@ -1313,143 +1395,143 @@ LBB0_74: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4940f41 // sete r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1940f41 // sete r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b - WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + WORD $0x0841; BYTE $0xdd // or r13b, bl + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_74 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_92 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_78: +LBB0_96: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -1457,97 +1539,113 @@ LBB0_78: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_78 - JMP LBB0_123 - -LBB0_79: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_83 - WORD $0x9848 // cdqe - -LBB0_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_81 - LONG $0x01c48349 // add r12, 1 - -LBB0_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_87 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_96 + JMP LBB0_153 + +LBB0_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB0_85: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_102: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_104: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_108 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_106: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5940f41 // sete r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3940f41 // sete r11b @@ -1556,21 +1654,21 @@ LBB0_85: LONG $0xd7940f41 // sete r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2940f41 // sete r10b @@ -1581,143 +1679,143 @@ LBB0_85: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4940f41 // sete r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1940f41 // sete r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_85 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB0_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_106 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB0_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_89: +LBB0_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -1725,97 +1823,113 @@ LBB0_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_89 - JMP LBB0_123 - -LBB0_101: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_105 - WORD $0x9848 // cdqe - -LBB0_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_103 - LONG $0x01c48349 // add r12, 1 - -LBB0_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_109 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB0_107: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_110 + JMP LBB0_153 + +LBB0_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB0_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_130: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_132: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_136 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_134: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5940f41 // sete r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3940f41 // sete r11b @@ -1824,21 +1938,21 @@ LBB0_107: LONG $0xd7940f41 // sete r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2940f41 // sete r10b @@ -1849,143 +1963,143 @@ LBB0_107: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4940f41 // sete r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1940f41 // sete r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_107 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_134 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_111: +LBB0_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -1993,99 +2107,115 @@ LBB0_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_111 - JMP LBB0_123 - -LBB0_112: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_116 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB0_114: - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xcb20 // and bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB0_114 - LONG $0x01c48349 // add r12, 1 - -LBB0_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_120 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB0_118: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_138 + JMP LBB0_153 + +LBB0_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + +LBB0_142: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x107aa1c4; WORD $0xb604 // vmovss xmm0, dword [rsi + 4*r14] + LONG $0x2e78a1c4; WORD $0xb204 // vucomiss xmm0, dword [rdx + 4*r14] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x2044; BYTE $0xd3 // and bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xfcc38349 // add r11, -4 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB0_142 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB0_144: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_146: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_150 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_148: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x0610fac5 // vmovss xmm0, dword [rsi] LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] LONG $0x4610fac5; BYTE $0x04 // vmovss xmm0, dword [rsi + 4] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x422ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rdx + 4] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x4610fac5; BYTE $0x08 // vmovss xmm0, dword [rsi + 8] LONG $0x422ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rdx + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x4610fac5; BYTE $0x0c // vmovss xmm0, dword [rsi + 12] LONG $0x422ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rdx + 12] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x4610fac5; BYTE $0x10 // vmovss xmm0, dword [rsi + 16] LONG $0x422ef8c5; BYTE $0x10 // vucomiss xmm0, dword [rdx + 16] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x4610fac5; BYTE $0x14 // vmovss xmm0, dword [rsi + 20] LONG $0x422ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rdx + 20] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2101,13 +2231,13 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x4610fac5; BYTE $0x20 // vmovss xmm0, dword [rsi + 32] LONG $0x422ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rdx + 32] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x4610fac5; BYTE $0x24 // vmovss xmm0, dword [rsi + 36] LONG $0x422ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rdx + 36] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2118,78 +2248,78 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x4610fac5; BYTE $0x2c // vmovss xmm0, dword [rsi + 44] LONG $0x422ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rdx + 44] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x4610fac5; BYTE $0x30 // vmovss xmm0, dword [rsi + 48] LONG $0x422ef8c5; BYTE $0x30 // vucomiss xmm0, dword [rdx + 48] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x4610fac5; BYTE $0x34 // vmovss xmm0, dword [rsi + 52] LONG $0x422ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rdx + 52] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x4610fac5; BYTE $0x38 // vmovss xmm0, dword [rsi + 56] LONG $0x422ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rdx + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x4610fac5; BYTE $0x3c // vmovss xmm0, dword [rsi + 60] LONG $0x422ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rdx + 60] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl LONG $0x4610fac5; BYTE $0x40 // vmovss xmm0, dword [rsi + 64] LONG $0x422ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rdx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl LONG $0x4610fac5; BYTE $0x44 // vmovss xmm0, dword [rsi + 68] LONG $0x422ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rdx + 68] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl LONG $0x4610fac5; BYTE $0x48 // vmovss xmm0, dword [rsi + 72] LONG $0x422ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rdx + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl LONG $0x4610fac5; BYTE $0x4c // vmovss xmm0, dword [rsi + 76] LONG $0x422ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rdx + 76] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd3940f41 // sete r11b - WORD $0x2041; BYTE $0xc3 // and r11b, al + LONG $0xd7940f41 // sete r15b + WORD $0x2041; BYTE $0xc7 // and r15b, al LONG $0x4610fac5; BYTE $0x50 // vmovss xmm0, dword [rsi + 80] LONG $0x422ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rdx + 80] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl LONG $0x4610fac5; BYTE $0x54 // vmovss xmm0, dword [rsi + 84] LONG $0x422ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rdx + 84] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl LONG $0x4610fac5; BYTE $0x58 // vmovss xmm0, dword [rsi + 88] LONG $0x422ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rdx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl LONG $0x4610fac5; BYTE $0x5c // vmovss xmm0, dword [rsi + 92] LONG $0x422ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rdx + 92] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2200,35 +2330,34 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl LONG $0x4610fac5; BYTE $0x64 // vmovss xmm0, dword [rsi + 100] LONG $0x422ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rdx + 100] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4940f41 // sete r12b + WORD $0x2041; BYTE $0xc4 // and r12b, al LONG $0x4610fac5; BYTE $0x68 // vmovss xmm0, dword [rsi + 104] LONG $0x422ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rdx + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f41 // sete r15b - WORD $0x2041; BYTE $0xc7 // and r15b, al + LONG $0xd6940f41 // sete r14b + WORD $0x2041; BYTE $0xc6 // and r14b, al LONG $0x4610fac5; BYTE $0x6c // vmovss xmm0, dword [rsi + 108] LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd6940f41 // sete r14b - WORD $0x2041; BYTE $0xc6 // and r14b, al + LONG $0xd3940f41 // sete r11b + WORD $0x2041; BYTE $0xc3 // and r11b, al LONG $0x4610fac5; BYTE $0x70 // vmovss xmm0, dword [rsi + 112] LONG $0x422ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rdx + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl LONG $0x4610fac5; BYTE $0x74 // vmovss xmm0, dword [rsi + 116] LONG $0x422ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rdx + 116] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x4610fac5; BYTE $0x78 // vmovss xmm0, dword [rsi + 120] LONG $0x422ef8c5; BYTE $0x78 // vucomiss xmm0, dword [rdx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2240,109 +2369,107 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd0940f41 // sete r8b WORD $0x2041; BYTE $0xc0 // and r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x5cb60f44; WORD $0x0324 // movzx r11d, byte [rsp + 3] - WORD $0x0845; BYTE $0xeb // or r11b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] LONG $0x07e2c041 // shl r10b, 7 WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xcf // or r15b, cl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x241c8845 // mov byte [r12], r11b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x24548845; BYTE $0x02 // mov byte [r12 + 2], r10b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB0_118 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_148 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_122: +LBB0_152: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x0410fac5; BYTE $0x8e // vmovss xmm0, dword [rsi + 4*rcx] LONG $0x042ef8c5; BYTE $0x8a // vucomiss xmm0, dword [rdx + 4*rcx] @@ -2352,94 +2479,117 @@ LBB0_122: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB0_122 - JMP LBB0_123 - -LBB0_57: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_61 - WORD $0x9848 // cdqe - -LBB0_59: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB0_152 + JMP LBB0_153 + +LBB0_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB0_74 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB0_72: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4940f41 // sete r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_59 - LONG $0x01c48349 // add r12, 1 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB0_72 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] -LBB0_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_65 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 +LBB0_74: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_76: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_80 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax -LBB0_63: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_78: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7940f41 // sete r15b + LONG $0xd6940f41 // sete r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7940f40 // sete dil @@ -2451,19 +2601,19 @@ LBB0_63: LONG $0xd3940f41 // sete r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6940f41 // sete r14b + LONG $0xd7940f41 // sete r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0940f41 // sete r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4940f41 // sete r12b @@ -2472,147 +2622,146 @@ LBB0_63: LONG $0xd5940f41 // sete r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1940f41 // sete r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB0_63 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB0_78 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] -LBB0_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_67: +LBB0_82: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -2620,97 +2769,113 @@ LBB0_67: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_67 - JMP LBB0_123 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_82 + JMP LBB0_153 -LBB0_90: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_94 - WORD $0x9848 // cdqe +LBB0_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB0_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_92 - LONG $0x01c48349 // add r12, 1 +LBB0_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB0_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_98 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB0_116: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 -LBB0_96: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_118: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_122 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_120: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5940f41 // sete r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3940f41 // sete r11b @@ -2719,21 +2884,21 @@ LBB0_96: LONG $0xd7940f41 // sete r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2940f41 // sete r10b @@ -2744,143 +2909,143 @@ LBB0_96: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4940f41 // sete r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1940f41 // sete r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_96 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_120 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_100: +LBB0_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -2888,19 +3053,20 @@ LBB0_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_100 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_124 -LBB0_123: +LBB0_153: SUBQ $8, SP RET @@ -2948,82 +3114,96 @@ TEXT ·_comparison_equal_arr_scalar_avx2(SB), $1320-48 MOVQ BP, 1280(SP) LEAQ LCDATA1<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB1_13 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB1_25 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB1_49 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB1_57 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB1_165 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_7: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_7 - LONG $0x01c38349 // add r11, 1 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB1_19 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB1_36 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB1_59 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB1_73 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB1_189 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_11 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_9 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_8: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_8 LBB1_9: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_101 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 LBB1_11: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_15 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB1_13: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000a82494940f // sete byte [rsp + 168] LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd2940f41 // sete r10b LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6940f41 // sete r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x940f; BYTE $0xd0 // sete al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x206e3944 // cmp dword [rsi + 32], r13d - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x246e3944 // cmp dword [rsi + 36], r13d LONG $0xd7940f40 // sete dil LONG $0x286e3944 // cmp dword [rsi + 40], r13d @@ -3035,33 +3215,33 @@ LBB1_11: LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4940f41 // sete r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x486e3944 // cmp dword [rsi + 72], r13d - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7940f41 // sete r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x646e3944 // cmp dword [rsi + 100], r13d LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x706e3944 // cmp dword [rsi + 112], r13d QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0x746e3944 // cmp dword [rsi + 116], r13d @@ -3069,178 +3249,233 @@ LBB1_11: LONG $0x786e3944 // cmp dword [rsi + 120], r13d LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x940f; BYTE $0xd1 // sete cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a824940244 // add r10b, byte [rsp + 168] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x68 // add dil, byte [rsp + 104] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + QUAD $0x0000009824bcb60f // movzx edi, byte [rsp + 152] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xc000 // add al, al - LONG $0x48244402 // add al, byte [rsp + 72] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x28244402 // add al, byte [rsp + 40] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_11 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_102 - JMP LBB1_165 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_13 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB1_13: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB1_39 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB1_65 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB1_73 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB1_165 - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fbc5 // vmovsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_21 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB1_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB1_129 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB1_19: - LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] +LBB1_18: + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB1_18 + JMP LBB1_179 + +LBB1_19: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB1_43 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB1_86 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB1_99 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB1_189 + WORD $0x8b4c; BYTE $0x22 // mov r12, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_29 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_27 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_26: + LONG $0x012ef9c5 // vucomisd xmm0, qword [rcx] + LONG $0x08718d48 // lea rsi, [rcx + 8] WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xca20 // and dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xcb20 // and bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_19 - LONG $0x01c38349 // add r11, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_26 -LBB1_21: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_105 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB1_27: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 -LBB1_23: +LBB1_29: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_33 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b824a4894c // mov qword [rsp + 184], r12 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + +LBB1_31: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x462ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rsi + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xc320 // and bl, al - LONG $0x462ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rsi + 16] - WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd5940f41 // sete r13b WORD $0x2041; BYTE $0xc5 // and r13b, al + LONG $0x462ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rsi + 16] + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x462ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rsi + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -3250,16 +3485,16 @@ LBB1_23: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x462ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rsi + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f40 // sete dil - WORD $0x2040; BYTE $0xc7 // and dil, al + LONG $0xd4940f41 // sete r12b + WORD $0x2041; BYTE $0xc4 // and r12b, al LONG $0x462ef9c5; BYTE $0x30 // vucomisd xmm0, qword [rsi + 48] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl LONG $0x462ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rsi + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -3269,519 +3504,355 @@ LBB1_23: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x462ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rsi + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl LONG $0x462ef9c5; BYTE $0x50 // vucomisd xmm0, qword [rsi + 80] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x462ef9c5; BYTE $0x58 // vucomisd xmm0, qword [rsi + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xc320 // and bl, al LONG $0x462ef9c5; BYTE $0x60 // vucomisd xmm0, qword [rsi + 96] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl LONG $0x462ef9c5; BYTE $0x68 // vucomisd xmm0, qword [rsi + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x462ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rsi + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xc220 // and dl, al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x58244c88 // mov byte [rsp + 88], cl LONG $0x462ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rsi + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl QUAD $0x00000080862ef9c5 // vucomisd xmm0, qword [rsi + 128] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl QUAD $0x00000088862ef9c5 // vucomisd xmm0, qword [rsi + 136] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl QUAD $0x00000090862ef9c5 // vucomisd xmm0, qword [rsi + 144] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al + LONG $0x40244c88 // mov byte [rsp + 64], cl QUAD $0x00000098862ef9c5 // vucomisd xmm0, qword [rsi + 152] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x80248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl QUAD $0x000000a0862ef9c5 // vucomisd xmm0, qword [rsi + 160] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x78244488 // mov byte [rsp + 120], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl QUAD $0x000000a8862ef9c5 // vucomisd xmm0, qword [rsi + 168] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x68244488 // mov byte [rsp + 104], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl QUAD $0x000000b0862ef9c5 // vucomisd xmm0, qword [rsi + 176] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd4940f41 // sete r12b - WORD $0x2041; BYTE $0xc4 // and r12b, al + LONG $0xd7940f41 // sete r15b + WORD $0x2041; BYTE $0xc7 // and r15b, al QUAD $0x000000b8862ef9c5 // vucomisd xmm0, qword [rsi + 184] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd2940f41 // sete r10b WORD $0x2041; BYTE $0xc2 // and r10b, al QUAD $0x000000c0862ef9c5 // vucomisd xmm0, qword [rsi + 192] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x70244488 // mov byte [rsp + 112], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl QUAD $0x000000c8862ef9c5 // vucomisd xmm0, qword [rsi + 200] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f41 // sete r15b - WORD $0x2041; BYTE $0xc7 // and r15b, al + LONG $0xd3940f41 // sete r11b + WORD $0x2041; BYTE $0xc3 // and r11b, al QUAD $0x000000d0862ef9c5 // vucomisd xmm0, qword [rsi + 208] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd6940f41 // sete r14b - WORD $0x2041; BYTE $0xc6 // and r14b, al + LONG $0xd1940f41 // sete r9b + WORD $0x2041; BYTE $0xc1 // and r9b, al QUAD $0x000000d8862ef9c5 // vucomisd xmm0, qword [rsi + 216] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd3940f41 // sete r11b - WORD $0x2041; BYTE $0xc3 // and r11b, al + LONG $0xd0940f41 // sete r8b + WORD $0x2041; BYTE $0xc0 // and r8b, al QUAD $0x000000e0862ef9c5 // vucomisd xmm0, qword [rsi + 224] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0xa0248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl QUAD $0x000000e8862ef9c5 // vucomisd xmm0, qword [rsi + 232] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x98248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl QUAD $0x000000f0862ef9c5 // vucomisd xmm0, qword [rsi + 240] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd1940f41 // sete r9b - WORD $0x2041; BYTE $0xc1 // and r9b, al + LONG $0xd7940f40 // sete dil + WORD $0x2040; BYTE $0xc7 // and dil, al QUAD $0x000000f8862ef9c5 // vucomisd xmm0, qword [rsi + 248] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd0940f41 // sete r8b - WORD $0x2041; BYTE $0xc0 // and r8b, al - WORD $0xdb00 // add bl, bl - LONG $0x20245c02 // add bl, byte [rsp + 32] - LONG $0x05e7c040 // shl dil, 5 - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xc220 // and dl, al + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x38 // add r13b, byte [rsp + 56] + WORD $0x8944; BYTE $0xe8 // mov eax, r13d + LONG $0x05e4c041 // shl r12b, 5 + QUAD $0x00008024acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 128] + LONG $0x06e5c041 // shl r13b, 6 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0xcb08 // or bl, cl + LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0841; BYTE $0xc5 // or r13b, al QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x74b60f44; WORD $0x5024 // movzx r14d, byte [rsp + 80] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0xcb08 // or bl, cl + QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0x8941; BYTE $0xcc // mov r12d, ecx + QUAD $0x00000110248c8b48 // mov rcx, qword [rsp + 272] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x247cb60f; BYTE $0x50 // movzx edi, byte [rsp + 80] - LONG $0x05e7c040 // shl dil, 5 - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0x0840; BYTE $0xfa // or dl, dil - LONG $0x6cb60f44; WORD $0x4824 // movzx r13d, byte [rsp + 72] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xd5 // or r13b, dl - QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] - WORD $0xd200 // add dl, dl - LONG $0x90249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 144] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0xca08 // or dl, cl - WORD $0xd189 // mov ecx, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xca08 // or dl, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e4c041 // shl r12b, 6 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0x0841; BYTE $0xdd // or r13b, bl + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c041 // shl r15b, 6 + WORD $0x0841; BYTE $0xdf // or r15b, bl + QUAD $0x0000012024b40a44 // or r14b, byte [rsp + 288] LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0845; BYTE $0xfa // or r10b, r15b WORD $0x0845; BYTE $0xe2 // or r10b, r12b - WORD $0x0841; BYTE $0xd2 // or r10b, dl - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x70 // add r15b, byte [rsp + 112] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xf3 // or r11b, r14b - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd8 // or al, r11b - WORD $0xc389 // mov ebx, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x0888 // mov byte [rax], cl - QUAD $0x000000982494b60f // movzx edx, byte [rsp + 152] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - LONG $0x06e1c041 // shl r9b, 6 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x000000a8249c0244 // add r11b, byte [rsp + 168] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0845; BYTE $0xc8 // or r8b, r9b - WORD $0x0841; BYTE $0xd8 // or r8b, bl - LONG $0x02508844 // mov byte [rax + 2], r10b - LONG $0x03408844 // mov byte [rax + 3], r8b + QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0x0188 // mov byte [rcx], al + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xdf // or dil, bl + LONG $0x01718844 // mov byte [rcx + 1], r14b + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x02518844 // mov byte [rcx + 2], r10b + WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_23 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_106 - JMP LBB1_165 - -LBB1_25: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB1_81 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB1_165 - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f6a8d4d // lea r13, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - WORD $0x894d; BYTE $0xd7 // mov r15, r10 - LONG $0xea490f4d // cmovns r13, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_31 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_29: - WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_29 - LONG $0x01c38349 // add r11, 1 + LONG $0x04c18348 // add rcx, 4 + WORD $0x8949; BYTE $0xce // mov r14, rcx + QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 + JNE LBB1_31 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] -LBB1_31: - LONG $0x05fdc149 // sar r13, 5 - LONG $0x20ff8349 // cmp r15, 32 - JL LBB1_108 - LONG $0x20fd8349 // cmp r13, 32 - LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d - QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 - QUAD $0x0000018824ac894c // mov qword [rsp + 392], r13 - JB LBB1_35 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 +LBB1_33: LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JAE LBB1_166 - LONG $0xab048d4b // lea rax, [r11 + 4*r13] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB1_166 - -LBB1_35: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x00000178249c894c // mov qword [rsp + 376], r11 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_160 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB1_162 LBB1_36: - QUAD $0x0000018024ac2b4c // sub r13, qword [rsp + 384] - QUAD $0x0000009824ac894c // mov qword [rsp + 152], r13 - -LBB1_37: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b - LONG $0xd0940f41 // sete r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd7940f41 // sete r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b - LONG $0xd5940f41 // sete r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b - LONG $0xd3940f41 // sete r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b - QUAD $0x000001402494940f // sete byte [rsp + 320] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b - WORD $0x940f; BYTE $0xd2 // sete dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b - LONG $0xd6940f40 // sete sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b - LONG $0xd7940f40 // sete dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b - LONG $0xd2940f41 // sete r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b - LONG $0xd4940f41 // sete r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b - LONG $0xd1940f41 // sete r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b - QUAD $0x000001202494940f // sete byte [rsp + 288] - LONG $0x11713844 // cmp byte [rcx + 17], r14b - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x13713844 // cmp byte [rcx + 19], r14b - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x14713844 // cmp byte [rcx + 20], r14b - QUAD $0x000000902494940f // sete byte [rsp + 144] - LONG $0x15713844 // cmp byte [rcx + 21], r14b - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd6940f41 // sete r14b - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x000001102494940f // sete byte [rsp + 272] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x30 // add r8b, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b - WORD $0xd200 // add dl, dl - LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xc000 // add al, al - LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000017824b48b48 // mov rsi, qword [rsp + 376] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x58 // movzx edi, byte [rsp + 88] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xc000 // add al, al - LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xd308 // or bl, dl - WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000017824b48948 // mov qword [rsp + 376], rsi - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB1_37 - QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] - QUAD $0x0000018824ac8b4c // mov r13, qword [rsp + 392] - JMP LBB1_109 - -LBB1_39: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB1_93 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB1_165 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_45 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB1_112 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB1_189 + WORD $0x8a44; BYTE $0x22 // mov r12b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_130 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_132 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB1_41: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_41 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB1_133 + JMP LBB1_189 LBB1_43: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB1_117 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB1_189 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_49 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_48: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_48 + +LBB1_49: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 + +LBB1_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_55 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB1_53: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_43 - LONG $0x01c38349 // add r11, 1 - -LBB1_45: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_112 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - -LBB1_47: - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000a82494940f // sete byte [rsp + 168] LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd2940f41 // sete r10b LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6940f41 // sete r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x206e394c // cmp qword [rsi + 32], r13 QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x206e394c // cmp qword [rsi + 32], r13 + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x940f; BYTE $0xd0 // sete al LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x406e394c // cmp qword [rsi + 64], r13 - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x486e394c // cmp qword [rsi + 72], r13 LONG $0xd7940f40 // sete dil LONG $0x506e394c // cmp qword [rsi + 80], r13 @@ -3793,33 +3864,33 @@ LBB1_47: LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4940f41 // sete r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7940f41 // sete r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 @@ -3827,153 +3898,206 @@ LBB1_47: LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x940f; BYTE $0xd1 // sete cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a824940244 // add r10b, byte [rsp + 168] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x68 // add dil, byte [rsp + 104] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + QUAD $0x0000009824bcb60f // movzx edi, byte [rsp + 152] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xc000 // add al, al - LONG $0x48244402 // add al, byte [rsp + 72] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl + LONG $0x01568841 // mov byte [r14 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc189 // mov ecx, eax + LONG $0x28244402 // add al, byte [rsp + 40] + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03538841 // mov byte [r11 + 3], dl + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c38349 // add r11, 4 - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_47 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_113 - JMP LBB1_165 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_53 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB1_49: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_53 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB1_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB1_98 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB1_51: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_51 - LONG $0x01c38349 // add r11, 1 +LBB1_58: + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0x10768d48 // lea rsi, [rsi + 16] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB1_58 + JMP LBB1_170 -LBB1_53: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_116 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB1_59: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_65 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_63 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_62: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_62 -LBB1_55: +LBB1_63: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 + +LBB1_65: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_69 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB1_67: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x940f; BYTE $0xd0 // sete al LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w @@ -3981,17 +4105,17 @@ LBB1_55: LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd6940f41 // sete r14b LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000a82494940f // sete byte [rsp + 168] LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w LONG $0xd7940f40 // sete dil LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w @@ -4003,33 +4127,33 @@ LBB1_55: LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd4940f41 // sete r12b LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w LONG $0xd7940f41 // sete r15b LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w @@ -4037,174 +4161,225 @@ LBB1_55: LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w - WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x940f; BYTE $0xd1 // sete cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b WORD $0x0841; BYTE $0xc2 // or r10b, al - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000009824bc0240 // add dil, byte [rsp + 152] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x68 // movzx edi, byte [rsp + 104] + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xc000 // add al, al - LONG $0x48244402 // add al, byte [rsp + 72] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x28244402 // add al, byte [rsp + 40] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x40c68348 // add rsi, 64 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_55 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_117 - JMP LBB1_165 - -LBB1_57: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_61 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_67 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB1_59: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_59 - LONG $0x01c38349 // add r11, 1 - -LBB1_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_120 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB1_69: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB1_85 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB1_63: +LBB1_72: + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w + LONG $0x04768d48 // lea rsi, [rsi + 4] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB1_72 + JMP LBB1_166 + +LBB1_73: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_79 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_77 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_76: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_76 + +LBB1_77: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 + +LBB1_79: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_83 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB1_81: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x2e394466 // cmp word [rsi], r13w - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000a82494940f // sete byte [rsp + 168] LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd2940f41 // sete r10b LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd6940f41 // sete r14b LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w WORD $0x940f; BYTE $0xd0 // sete al LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w LONG $0xd7940f40 // sete dil LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w @@ -4216,33 +4391,33 @@ LBB1_63: LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd4940f41 // sete r12b LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w LONG $0xd7940f41 // sete r15b LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w @@ -4250,173 +4425,193 @@ LBB1_63: LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w - WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x940f; BYTE $0xd1 // sete cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a824940244 // add r10b, byte [rsp + 168] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x68 // add dil, byte [rsp + 104] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + QUAD $0x0000009824bcb60f // movzx edi, byte [rsp + 152] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xc000 // add al, al - LONG $0x48244402 // add al, byte [rsp + 72] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x28244402 // add al, byte [rsp + 40] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x40c68348 // add rsi, 64 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_63 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_121 - JMP LBB1_165 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_81 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB1_65: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_69 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB1_83: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_164 -LBB1_67: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_67 - LONG $0x01c38349 // add r11, 1 +LBB1_85: + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB1_166 + +LBB1_86: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_92 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_90 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB1_69: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_123 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB1_71: +LBB1_89: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_89 + +LBB1_90: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 + +LBB1_92: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_96 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB1_94: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000a82494940f // sete byte [rsp + 168] LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd2940f41 // sete r10b LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6940f41 // sete r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x206e394c // cmp qword [rsi + 32], r13 QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x206e394c // cmp qword [rsi + 32], r13 + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x940f; BYTE $0xd0 // sete al LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x406e394c // cmp qword [rsi + 64], r13 - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x486e394c // cmp qword [rsi + 72], r13 LONG $0xd7940f40 // sete dil LONG $0x506e394c // cmp qword [rsi + 80], r13 @@ -4428,33 +4623,33 @@ LBB1_71: LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4940f41 // sete r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7940f41 // sete r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 @@ -4462,170 +4657,194 @@ LBB1_71: LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x940f; BYTE $0xd1 // sete cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a824940244 // add r10b, byte [rsp + 168] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x68 // add dil, byte [rsp + 104] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + QUAD $0x0000009824bcb60f // movzx edi, byte [rsp + 152] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xc000 // add al, al - LONG $0x48244402 // add al, byte [rsp + 72] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x28244402 // add al, byte [rsp + 40] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_71 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_124 - JMP LBB1_165 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_94 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB1_73: - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fac5 // vmovss xmm0, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_77 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_75: - LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] +LBB1_96: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_168 + +LBB1_98: + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB1_170 + +LBB1_99: + WORD $0x8b44; BYTE $0x22 // mov r12d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_105 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_103 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_102: + LONG $0x012ef8c5 // vucomiss xmm0, dword [rcx] + LONG $0x04718d48 // lea rsi, [rcx + 4] WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xca20 // and dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xcb20 // and bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_75 - LONG $0x01c38349 // add r11, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_102 -LBB1_77: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_126 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB1_103: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 -LBB1_79: +LBB1_105: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_109 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000c024a48944 // mov dword [rsp + 192], r12d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB1_107: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x462ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rsi + 4] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xc320 // and bl, al - LONG $0x462ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rsi + 8] - WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd5940f41 // sete r13b WORD $0x2041; BYTE $0xc5 // and r13b, al + LONG $0x462ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rsi + 8] + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x462ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rsi + 12] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -4635,16 +4854,16 @@ LBB1_79: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x462ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rsi + 20] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f40 // sete dil - WORD $0x2040; BYTE $0xc7 // and dil, al + LONG $0xd4940f41 // sete r12b + WORD $0x2041; BYTE $0xc4 // and r12b, al LONG $0x462ef8c5; BYTE $0x18 // vucomiss xmm0, dword [rsi + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl LONG $0x462ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rsi + 28] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -4654,510 +4873,341 @@ LBB1_79: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x462ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rsi + 36] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl LONG $0x462ef8c5; BYTE $0x28 // vucomiss xmm0, dword [rsi + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x462ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rsi + 44] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xc320 // and bl, al LONG $0x462ef8c5; BYTE $0x30 // vucomiss xmm0, dword [rsi + 48] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl LONG $0x462ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rsi + 52] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x462ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rsi + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xc220 // and dl, al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x58244c88 // mov byte [rsp + 88], cl LONG $0x462ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rsi + 60] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x462ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rsi + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl LONG $0x462ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rsi + 68] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x462ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rsi + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x462ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rsi + 76] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x80248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + LONG $0xd6940f41 // sete r14b + WORD $0x2041; BYTE $0xc6 // and r14b, al LONG $0x462ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rsi + 80] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x78244488 // mov byte [rsp + 120], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl LONG $0x462ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rsi + 84] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x68244488 // mov byte [rsp + 104], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl LONG $0x462ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rsi + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd4940f41 // sete r12b - WORD $0x2041; BYTE $0xc4 // and r12b, al + LONG $0xd7940f41 // sete r15b + WORD $0x2041; BYTE $0xc7 // and r15b, al LONG $0x462ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rsi + 92] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd2940f41 // sete r10b WORD $0x2041; BYTE $0xc2 // and r10b, al LONG $0x462ef8c5; BYTE $0x60 // vucomiss xmm0, dword [rsi + 96] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x70244488 // mov byte [rsp + 112], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl LONG $0x462ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rsi + 100] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f41 // sete r15b - WORD $0x2041; BYTE $0xc7 // and r15b, al + LONG $0xd3940f41 // sete r11b + WORD $0x2041; BYTE $0xc3 // and r11b, al LONG $0x462ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rsi + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd6940f41 // sete r14b - WORD $0x2041; BYTE $0xc6 // and r14b, al + LONG $0xd1940f41 // sete r9b + WORD $0x2041; BYTE $0xc1 // and r9b, al LONG $0x462ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rsi + 108] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd3940f41 // sete r11b - WORD $0x2041; BYTE $0xc3 // and r11b, al + LONG $0xd0940f41 // sete r8b + WORD $0x2041; BYTE $0xc0 // and r8b, al LONG $0x462ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rsi + 112] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0xa0248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl LONG $0x462ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rsi + 116] - LONG $0xd09b0f41 // setnp r8b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xc0 // and al, r8b - LONG $0x98248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], al + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl LONG $0x462ef8c5; BYTE $0x78 // vucomiss xmm0, dword [rsi + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd1940f41 // sete r9b - WORD $0x2041; BYTE $0xc1 // and r9b, al + LONG $0xd7940f40 // sete dil + WORD $0x2040; BYTE $0xc7 // and dil, al LONG $0x462ef8c5; BYTE $0x7c // vucomiss xmm0, dword [rsi + 124] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd0940f41 // sete r8b - WORD $0x2041; BYTE $0xc0 // and r8b, al - WORD $0xdb00 // add bl, bl - LONG $0x20245c02 // add bl, byte [rsp + 32] - LONG $0x05e7c040 // shl dil, 5 - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xc220 // and dl, al + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x38 // add r13b, byte [rsp + 56] + WORD $0x8944; BYTE $0xe8 // mov eax, r13d + LONG $0x05e4c041 // shl r12b, 5 + QUAD $0x00008024acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 128] + LONG $0x06e5c041 // shl r13b, 6 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0xcb08 // or bl, cl + LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0841; BYTE $0xc5 // or r13b, al QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x247cb60f; BYTE $0x50 // movzx edi, byte [rsp + 80] - LONG $0x05e7c040 // shl dil, 5 - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0x0840; BYTE $0xfa // or dl, dil - LONG $0x6cb60f44; WORD $0x4824 // movzx r13d, byte [rsp + 72] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xd5 // or r13b, dl - QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] - WORD $0xd200 // add dl, dl - LONG $0x90249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 144] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0xca08 // or dl, cl - WORD $0xd189 // mov ecx, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xca08 // or dl, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e4c041 // shl r12b, 6 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0x0841; BYTE $0xdd // or r13b, bl + WORD $0xd808 // or al, bl + LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0xcb08 // or bl, cl + LONG $0x03e6c041 // shl r14b, 3 + WORD $0x0841; BYTE $0xde // or r14b, bl + QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xf1 // or cl, r14b + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x64b60f44; WORD $0x1c24 // movzx r12d, byte [rsp + 28] + WORD $0x0845; BYTE $0xec // or r12b, r13b + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c041 // shl r15b, 6 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x2024840a; WORD $0x0001; BYTE $0x00 // or al, byte [rsp + 288] LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0845; BYTE $0xe2 // or r10b, r12b - WORD $0x0841; BYTE $0xd2 // or r10b, dl - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x70 // add r15b, byte [rsp + 112] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xf3 // or r11b, r14b - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd8 // or al, r11b - WORD $0xc389 // mov ebx, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x0888 // mov byte [rax], cl - QUAD $0x000000982494b60f // movzx edx, byte [rsp + 152] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - LONG $0x06e1c041 // shl r9b, 6 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xfa // or r10b, r15b + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x00000088249c0244 // add r11b, byte [rsp + 136] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0845; BYTE $0xc8 // or r8b, r9b - WORD $0x0841; BYTE $0xd8 // or r8b, bl - LONG $0x02508844 // mov byte [rax + 2], r10b - LONG $0x03408844 // mov byte [rax + 3], r8b + QUAD $0x000000a8248cb60f // movzx ecx, byte [rsp + 168] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x8845; BYTE $0x26 // mov byte [r14], r12b + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xdf // or dil, bl + LONG $0x01468841 // mov byte [r14 + 1], al + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xca08 // or dl, cl + LONG $0x02568845 // mov byte [r14 + 2], r10b + LONG $0x03568841 // mov byte [r14 + 3], dl LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax + LONG $0x04c68349 // add r14, 4 QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_79 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_127 - JMP LBB1_165 - -LBB1_81: - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_85 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_83: - WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_83 - LONG $0x01c38349 // add r11, 1 + JNE LBB1_107 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000c024a48b44 // mov r12d, dword [rsp + 192] + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] -LBB1_85: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_129 - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000018824bc894c // mov qword [rsp + 392], r15 - JB LBB1_89 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB1_109: LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JAE LBB1_169 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB1_169 - -LBB1_89: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x00000178249c894c // mov qword [rsp + 376], r11 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_172 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB1_174 -LBB1_90: - QUAD $0x0000018024bc2b4c // sub r15, qword [rsp + 384] - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 +LBB1_112: + WORD $0x8a44; BYTE $0x22 // mov r12b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_131 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_146 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 -LBB1_91: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b - LONG $0xd0940f41 // sete r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd7940f41 // sete r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b - LONG $0xd5940f41 // sete r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b - LONG $0xd3940f41 // sete r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b - QUAD $0x000001402494940f // sete byte [rsp + 320] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b - WORD $0x940f; BYTE $0xd2 // sete dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b - LONG $0xd6940f40 // sete sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b - LONG $0xd7940f40 // sete dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b - LONG $0xd2940f41 // sete r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b - LONG $0xd4940f41 // sete r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b - LONG $0xd1940f41 // sete r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b - QUAD $0x000001202494940f // sete byte [rsp + 288] - LONG $0x11713844 // cmp byte [rcx + 17], r14b - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x13713844 // cmp byte [rcx + 19], r14b - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x14713844 // cmp byte [rcx + 20], r14b - QUAD $0x000000902494940f // sete byte [rsp + 144] - LONG $0x15713844 // cmp byte [rcx + 21], r14b - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd6940f41 // sete r14b - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x000001102494940f // sete byte [rsp + 272] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x20 // add r8b, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b - WORD $0xd200 // add dl, dl - LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xc000 // add al, al - LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000017824b48b48 // mov rsi, qword [rsp + 376] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x50 // movzx edi, byte [rsp + 80] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xd308 // or bl, dl - WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000017824b48948 // mov qword [rsp + 376], rsi - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB1_91 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - JMP LBB1_130 - -LBB1_93: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_97 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_95: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_95 - LONG $0x01c38349 // add r11, 1 - -LBB1_97: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_133 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 +LBB1_115: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_115 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB1_147 + JMP LBB1_189 -LBB1_99: - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB1_117: + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_123 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_121 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_120: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_120 + +LBB1_121: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 + LONG $0x01c68349 // add r14, 1 + +LBB1_123: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_127 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB1_125: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000a82494940f // sete byte [rsp + 168] LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd2940f41 // sete r10b LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6940f41 // sete r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x940f; BYTE $0xd0 // sete al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x206e3944 // cmp dword [rsi + 32], r13d - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x246e3944 // cmp dword [rsi + 36], r13d LONG $0xd7940f40 // sete dil LONG $0x286e3944 // cmp dword [rsi + 40], r13d @@ -5169,33 +5219,33 @@ LBB1_99: LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4940f41 // sete r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x486e3944 // cmp dword [rsi + 72], r13d - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7940f41 // sete r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x646e3944 // cmp dword [rsi + 100], r13d LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x706e3944 // cmp dword [rsi + 112], r13d QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0x746e3944 // cmp dword [rsi + 116], r13d @@ -5203,194 +5253,376 @@ LBB1_99: LONG $0x786e3944 // cmp dword [rsi + 120], r13d LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x940f; BYTE $0xd1 // sete cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a824940244 // add r10b, byte [rsp + 168] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x68 // add dil, byte [rsp + 104] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + QUAD $0x0000009824bcb60f // movzx edi, byte [rsp + 152] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xc000 // add al, al - LONG $0x48244402 // add al, byte [rsp + 72] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl + LONG $0x01568841 // mov byte [r14 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc189 // mov ecx, eax + LONG $0x28244402 // add al, byte [rsp + 40] + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03538841 // mov byte [r11 + 3], dl + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c38349 // add r11, 4 - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB1_99 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB1_134 - JMP LBB1_165 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_125 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB1_101: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 +LBB1_127: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_177 -LBB1_102: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB1_135 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB1_129: WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 + JMP LBB1_179 -LBB1_104: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_104 - JMP LBB1_162 +LBB1_130: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB1_134 -LBB1_105: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 - -LBB1_106: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_136 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB1_138 +LBB1_131: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB1_148 -LBB1_108: - QUAD $0x00000178249c894c // mov qword [rsp + 376], r11 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi +LBB1_132: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 -LBB1_109: - LONG $0x05e5c149 // shl r13, 5 - WORD $0x394d; BYTE $0xfd // cmp r13, r15 - JGE LBB1_165 +LBB1_133: + LONG $0x01c68349 // add r14, 1 + +LBB1_134: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_142 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24648944; BYTE $0x1c // mov dword [rsp + 28], r12d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000188248c8948 // mov qword [rsp + 392], rcx + JB LBB1_138 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB1_190 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB1_190 + +LBB1_138: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + +LBB1_139: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx + +LBB1_140: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x01663844 // cmp byte [rsi + 1], r12b + LONG $0xd0940f41 // sete r8b + LONG $0x02663844 // cmp byte [rsi + 2], r12b + LONG $0xd6940f41 // sete r14b + LONG $0x03663844 // cmp byte [rsi + 3], r12b + LONG $0xd5940f41 // sete r13b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x04 // cmp byte [rsi + 4], al + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x05 // cmp byte [rsi + 5], al + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x06 // cmp byte [rsi + 6], al + QUAD $0x000000a82494940f // sete byte [rsp + 168] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x07 // cmp byte [rsi + 7], al + LONG $0xd3940f41 // sete r11b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x08 // cmp byte [rsi + 8], al + QUAD $0x000001402494940f // sete byte [rsp + 320] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x09 // cmp byte [rsi + 9], al + WORD $0x940f; BYTE $0xd2 // sete dl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x0a // cmp byte [rsi + 10], al + LONG $0xd6940f40 // sete sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd7940f40 // sete dil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd2940f41 // sete r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + LONG $0xd4940f41 // sete r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd1940f41 // sete r9b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000001202494940f // sete byte [rsp + 288] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + QUAD $0x000000982494940f // sete byte [rsp + 152] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd7940f41 // sete r15b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + QUAD $0x000001102494940f // sete byte [rsp + 272] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + LONG $0x24440244; BYTE $0x28 // add r8b, byte [rsp + 40] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xd200 // add dl, dl + LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x1c24448b // mov eax, dword [rsp + 28] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x0000008824b4b60f // movzx esi, byte [rsp + 136] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xd3 // or r11b, dl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + WORD $0x8941; BYTE $0xc4 // mov r12d, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xc000 // add al, al + LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] + QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + QUAD $0x000000982494b60f // movzx edx, byte [rsp + 152] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + QUAD $0x0000017824bc8b48 // mov rdi, qword [rsp + 376] + WORD $0x8844; BYTE $0x1f // mov byte [rdi], r11b + LONG $0x2474b60f; BYTE $0x78 // movzx esi, byte [rsp + 120] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014f8844 // mov byte [rdi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xc000 // add al, al + LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x027f8844 // mov byte [rdi + 2], r15b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000017824bc8948 // mov qword [rsp + 376], rdi + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_140 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + JMP LBB1_143 + +LBB1_142: + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + +LBB1_143: + LONG $0x05e1c148 // shl rcx, 5 WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xe8 // sub r8, r13 - WORD $0xf749; BYTE $0xd5 // not r13 - WORD $0x014d; BYTE $0xfd // add r13, r15 - JE LBB1_132 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB1_189 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB1_159 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d QUAD $0x00000178249c8b4c // mov r11, qword [rsp + 376] -LBB1_141: - LONG $0x34343845 // cmp byte [r12 + rsi], r14b +LBB1_183: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e243846 // cmp byte [rsi + r9], r12b WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl @@ -5399,8 +5631,8 @@ LBB1_141: WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743845; BYTE $0x01 // cmp byte [r12 + rsi + 1], r14b - LONG $0x02768d48 // lea rsi, [rsi + 2] + LONG $0x06643844; BYTE $0x01 // cmp byte [rsi + rax + 1], r12b + LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl WORD $0xd330 // xor bl, dl @@ -5410,197 +5642,262 @@ LBB1_141: WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB1_141 - JMP LBB1_157 + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB1_183 + JMP LBB1_186 -LBB1_112: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 - -LBB1_113: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB1_125 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 +LBB1_146: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_189 -LBB1_115: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0x10768d48 // lea rsi, [rsi + 16] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_115 - JMP LBB1_148 +LBB1_147: + LONG $0x01c68349 // add r14, 1 -LBB1_116: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 - -LBB1_117: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB1_122 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - -LBB1_119: - LONG $0x2e394466 // cmp word [rsi], r13w - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_119 - JMP LBB1_144 - -LBB1_120: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 - -LBB1_121: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_142 - -LBB1_122: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB1_144 - -LBB1_123: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 - -LBB1_124: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_146 - -LBB1_125: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB1_148 - -LBB1_126: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 - -LBB1_127: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_150 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB1_152 +LBB1_148: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_156 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24648944; BYTE $0x1c // mov dword [rsp + 28], r12d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000188248c8948 // mov qword [rsp + 392], rcx + JB LBB1_152 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB1_193 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB1_193 -LBB1_129: - QUAD $0x00000178249c894c // mov qword [rsp + 376], r11 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi +LBB1_152: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 -LBB1_130: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_155 +LBB1_153: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx -LBB1_132: - WORD $0xf631 // xor esi, esi - JMP LBB1_158 +LBB1_154: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x01663844 // cmp byte [rsi + 1], r12b + LONG $0xd0940f41 // sete r8b + LONG $0x02663844 // cmp byte [rsi + 2], r12b + LONG $0xd6940f41 // sete r14b + LONG $0x03663844 // cmp byte [rsi + 3], r12b + LONG $0xd5940f41 // sete r13b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x04 // cmp byte [rsi + 4], al + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x05 // cmp byte [rsi + 5], al + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x06 // cmp byte [rsi + 6], al + QUAD $0x000000a82494940f // sete byte [rsp + 168] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x07 // cmp byte [rsi + 7], al + LONG $0xd3940f41 // sete r11b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x08 // cmp byte [rsi + 8], al + QUAD $0x000001402494940f // sete byte [rsp + 320] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x09 // cmp byte [rsi + 9], al + WORD $0x940f; BYTE $0xd2 // sete dl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x0a // cmp byte [rsi + 10], al + LONG $0xd6940f40 // sete sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd7940f40 // sete dil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd2940f41 // sete r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + LONG $0xd4940f41 // sete r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd1940f41 // sete r9b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000001202494940f // sete byte [rsp + 288] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + QUAD $0x000000982494940f // sete byte [rsp + 152] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd7940f41 // sete r15b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + QUAD $0x000001102494940f // sete byte [rsp + 272] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + LONG $0x24440244; BYTE $0x28 // add r8b, byte [rsp + 40] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xd200 // add dl, dl + LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x1c24448b // mov eax, dword [rsp + 28] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x0000008824b4b60f // movzx esi, byte [rsp + 136] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xd3 // or r11b, dl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + WORD $0x8941; BYTE $0xc4 // mov r12d, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xc000 // add al, al + LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] + QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + QUAD $0x000000982494b60f // movzx edx, byte [rsp + 152] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + QUAD $0x0000017824bc8b48 // mov rdi, qword [rsp + 376] + WORD $0x8844; BYTE $0x1f // mov byte [rdi], r11b + LONG $0x2474b60f; BYTE $0x78 // movzx esi, byte [rsp + 120] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014f8844 // mov byte [rdi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xc000 // add al, al + LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x027f8844 // mov byte [rdi + 2], r15b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000017824bc8948 // mov qword [rsp + 376], rdi + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB1_154 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + JMP LBB1_157 -LBB1_133: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_165 +LBB1_156: + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB1_134: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_160 +LBB1_157: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB1_189 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB1_184 -LBB1_135: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB1_162 +LBB1_159: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB1_187 -LBB1_136: +LBB1_160: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB1_137: +LBB1_161: LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] WORD $0x9b0f; BYTE $0xd1 // setnp cl WORD $0x940f; BYTE $0xd0 // sete al @@ -5608,7 +5905,8 @@ LBB1_137: WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3f // movzx r10d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -5616,7 +5914,7 @@ LBB1_137: WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x462ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rsi + 8] LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -5630,29 +5928,29 @@ LBB1_137: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB1_137 + JNE LBB1_161 -LBB1_138: +LBB1_162: LONG $0x01c0f641 // test r8b, 1 - JE LBB1_165 + JE LBB1_189 LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] - JMP LBB1_154 + JMP LBB1_176 -LBB1_142: +LBB1_164: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB1_143: +LBB1_165: LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -5660,7 +5958,7 @@ LBB1_143: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] @@ -5672,29 +5970,29 @@ LBB1_143: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_143 + JNE LBB1_165 -LBB1_144: +LBB1_166: LONG $0x01c0f641 // test r8b, 1 - JE LBB1_165 + JE LBB1_189 LONG $0x2e394466 // cmp word [rsi], r13w - JMP LBB1_164 + JMP LBB1_181 -LBB1_146: +LBB1_168: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB1_147: +LBB1_169: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -5702,7 +6000,7 @@ LBB1_147: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -5714,23 +6012,22 @@ LBB1_147: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_147 + JNE LBB1_169 -LBB1_148: +LBB1_170: LONG $0x01c0f641 // test r8b, 1 - JE LBB1_165 + JE LBB1_189 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - JMP LBB1_164 + JMP LBB1_181 -LBB1_150: +LBB1_172: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB1_151: +LBB1_173: LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] WORD $0x9b0f; BYTE $0xd1 // setnp cl WORD $0x940f; BYTE $0xd0 // sete al @@ -5738,7 +6035,8 @@ LBB1_151: WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3f // movzx r10d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -5746,7 +6044,7 @@ LBB1_151: WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x462ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rsi + 4] LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -5760,16 +6058,16 @@ LBB1_151: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB1_151 + JNE LBB1_173 -LBB1_152: +LBB1_174: LONG $0x01c0f641 // test r8b, 1 - JE LBB1_165 + JE LBB1_189 LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] -LBB1_154: +LBB1_176: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd2 // sete dl WORD $0xc220 // and dl, al @@ -5785,79 +6083,21 @@ LBB1_154: WORD $0xd320 // and bl, dl WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x061c8841 // mov byte [r14 + rax], bl - JMP LBB1_165 - -LBB1_155: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - QUAD $0x00000178249c8b4c // mov r11, qword [rsp + 376] - -LBB1_156: - LONG $0x34343845 // cmp byte [r12 + rsi], r14b - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743845; BYTE $0x01 // cmp byte [r12 + rsi + 1], r14b - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB1_156 - -LBB1_157: - WORD $0x0149; BYTE $0xf4 // add r12, rsi + JMP LBB1_189 -LBB1_158: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_165 - LONG $0x24343845 // cmp byte [r12], r14b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - QUAD $0x0000017824848b4c // mov r8, qword [rsp + 376] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB1_165 - -LBB1_160: +LBB1_177: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB1_161: +LBB1_178: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -5865,7 +6105,7 @@ LBB1_161: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -5877,16 +6117,16 @@ LBB1_161: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_161 + JNE LBB1_178 -LBB1_162: +LBB1_179: LONG $0x01c0f641 // test r8b, 1 - JE LBB1_165 + JE LBB1_189 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d -LBB1_164: +LBB1_181: WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xda // mov rdx, r11 @@ -5900,108 +6140,167 @@ LBB1_164: WORD $0xc320 // and bl, al WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x161c8841 // mov byte [r14 + rdx], bl + JMP LBB1_189 -LBB1_165: +LBB1_184: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x00000178249c8b4c // mov r11, qword [rsp + 376] + +LBB1_185: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e243846 // cmp byte [rsi + r9], r12b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x06643844; BYTE $0x01 // cmp byte [rsi + rax + 1], r12b + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB1_185 + +LBB1_186: + WORD $0x014c; BYTE $0xce // add rsi, r9 + +LBB1_187: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_189 + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + QUAD $0x0000017824848b4c // mov r8, qword [rsp + 376] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + +LBB1_189: MOVQ 1280(SP), SP VZEROUPPER RET -LBB1_166: - LONG $0xe0e58349 // and r13, -32 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 +LBB1_190: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - QUAD $0x0000018024ac894c // mov qword [rsp + 384], r13 - LONG $0xab048d4b // lea rax, [r11 + 4*r13] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000017824848948 // mov qword [rsp + 376], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB1_167: +LBB1_191: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000019824848948 // mov qword [rsp + 408], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] - WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x1644b60f; BYTE $0x01 // movzx eax, byte [rsi + rdx + 1] + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] + WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x1644b60f; BYTE $0x02 // movzx eax, byte [rsi + rdx + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] QUAD $0x000000f024948948 // mov qword [rsp + 240], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax @@ -6010,1881 +6309,1882 @@ LBB1_167: QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02400d48; WORD $0x0000 // or rax, 576 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02600d48; WORD $0x0000 // or rax, 608 LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x80cf8149; WORD $0x0002; BYTE $0x00 // or r15, 640 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0xa0cb8149; WORD $0x0002; BYTE $0x00 // or r11, 672 - QUAD $0x000000c8249c894c // mov qword [rsp + 200], r11 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - LONG $0xc0c88149; WORD $0x0002; BYTE $0x00 // or r8, 704 - QUAD $0x000000b02484894c // mov qword [rsp + 176], r8 - WORD $0x8948; BYTE $0xda // mov rdx, rbx - LONG $0xe0ca8148; WORD $0x0002; BYTE $0x00 // or rdx, 736 - QUAD $0x000000c024948948 // mov qword [rsp + 192], rdx - WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0x00cc8149; WORD $0x0003; BYTE $0x00 // or r12, 768 - QUAD $0x000000d824a4894c // mov qword [rsp + 216], r12 - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x20ce8149; WORD $0x0003; BYTE $0x00 // or r14, 800 - QUAD $0x000000b824b4894c // mov qword [rsp + 184], r14 - WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x40cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 576 + QUAD $0x00000108249c8948 // mov qword [rsp + 264], rbx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x02600d48; WORD $0x0000 // or rax, 608 + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + WORD $0x8949; BYTE $0xce // mov r14, rcx + LONG $0x80ce8149; WORD $0x0002; BYTE $0x00 // or r14, 640 + LONG $0x2474894c; BYTE $0x70 // mov qword [rsp + 112], r14 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + WORD $0x8949; BYTE $0xcc // mov r12, rcx + LONG $0xc0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 704 + QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 + WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0xe0ce8148; WORD $0x0002; BYTE $0x00 // or rsi, 736 + QUAD $0x000000d024b48948 // mov qword [rsp + 208], rsi + WORD $0x8949; BYTE $0xcf // mov r15, rcx + LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 + QUAD $0x000000e024bc894c // mov qword [rsp + 224], r15 + WORD $0x8949; BYTE $0xcb // mov r11, rcx + LONG $0x20cb8149; WORD $0x0003; BYTE $0x00 // or r11, 800 + QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 + WORD $0x8949; BYTE $0xca // mov r10, rcx LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 - LONG $0x2454894c; BYTE $0x50 // mov qword [rsp + 80], r10 - WORD $0x8949; BYTE $0xd9 // mov r9, rbx + LONG $0x2454894c; BYTE $0x58 // mov qword [rsp + 88], r10 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 - LONG $0x244c894c; BYTE $0x48 // mov qword [rsp + 72], r9 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03800d48; WORD $0x0000 // or rax, 896 - QUAD $0x000000f824848948 // mov qword [rsp + 248], rax - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - LONG $0xa0cf8148; WORD $0x0003; BYTE $0x00 // or rdi, 928 - LONG $0x247c8948; BYTE $0x70 // mov qword [rsp + 112], rdi - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x00000100249c8948 // mov qword [rsp + 256], rbx + QUAD $0x000000d8248c894c // mov qword [rsp + 216], r9 + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 + LONG $0x2444894c; BYTE $0x50 // mov qword [rsp + 80], r8 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0xa0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 928 + LONG $0x24548948; BYTE $0x48 // mov qword [rsp + 72], rdx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - LONG $0x207923c4; WORD $0x2e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + r13], 1 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - LONG $0x2031e3c4; WORD $0x1e04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + rbx], 2 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 3 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + r15], 4 - LONG $0x2079a3c4; WORD $0x1e04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + r11], 5 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + r8], 6 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + rdx], 7 - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + r12], 8 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + r14], 9 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r10], 10 - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + r9], 11 - QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] - LONG $0x2079a3c4; WORD $0x2e04; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + r13], 12 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + rdi], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + r14], 1 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - LONG $0x2061a3c4; WORD $0x261c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r12], 2 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + r10], 3 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - LONG $0x2061a3c4; WORD $0x1e1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + r11], 4 - QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + r8], 5 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r9], 6 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + r15], 7 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + rbx], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rdx], 12 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rdx], 13 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + rdx], 14 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rdx], 15 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x010116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 1 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x020116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 2 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x030116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 3 + LONG $0x244c8948; BYTE $0x60 // mov qword [rsp + 96], rcx + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + LONG $0x207923c4; WORD $0x2f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r13], 1 + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r14], 4 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r12], 6 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rsi], 7 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r15], 8 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r11], 9 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r10], 10 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + r9], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rdx], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r14], 1 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r12], 2 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r8], 3 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r9], 4 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r10], 6 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r15], 7 QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x040116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 4 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x050116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 5 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x060116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x070116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 7 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x080116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 8 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x090116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 9 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0a0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 10 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0b0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 11 - QUAD $0x0c012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 12 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0d0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 13 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0e012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 14 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0f0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 15 - QUAD $0x0101366c2029a3c4 // vpinsrb xmm5, xmm10, byte [rsi + r14 + 1], 1 - QUAD $0x0201266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 1], 2 - QUAD $0x0301166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 1], 3 - QUAD $0x04011e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 1], 4 - QUAD $0x0501066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 5 - QUAD $0x06010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 6 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - QUAD $0x07013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 7 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0a011e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 1], 10 - QUAD $0x0b010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 12 + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rdx], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rbx], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rsi], 14 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rsi], 15 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x010137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 1 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x02012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x030137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 3 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x04012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 4 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x050137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 5 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x07012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 7 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x080137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 8 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x090137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 10 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0b0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 11 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0c0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 13 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0e0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 14 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0f0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 15 + QUAD $0x0101376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x0201276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 2 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x0301076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 3 + QUAD $0x04010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x0601176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 6 + QUAD $0x07013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 7 + QUAD $0x0801176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + QUAD $0x0a011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 10 + QUAD $0x0b010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 14 + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0106442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 1], 15 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xca6e79c5 // vmovd xmm9, edx LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xd26e79c5 // vmovd xmm10, edx + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x010216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 2], 1 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x02020e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 2], 2 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x030216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 2], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 4 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x050206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x060206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 6 + QUAD $0x010207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 1 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x02020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 2 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x070206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 7 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x080226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 2], 8 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x09022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 9 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0a020e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 2], 10 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x0b021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 11 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0c0236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 2], 12 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x0d023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x02023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 2 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x03023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 4 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x05023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 5 - QUAD $0x0602065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 2], 6 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x07023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 7 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x08021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 8 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x09021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 9 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0a021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 10 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x0b02065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 2], 11 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0c021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 12 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x010316642021e3c4 // vpinsrb xmm4, xmm11, byte [rsi + rdx + 3], 1 - QUAD $0x02030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 2 - QUAD $0x030316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 4 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x05030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 5 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x06030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 6 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - QUAD $0x070306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 7 - QUAD $0x080326642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 3], 8 - QUAD $0x09032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 9 - QUAD $0x0a030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 10 - QUAD $0x0b031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 11 - QUAD $0x0c0336642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 3], 12 - QUAD $0x0d033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 13 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0e0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0203066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 2 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0303166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 3], 3 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x04033e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 3], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0503066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 5 + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0603066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 6 - QUAD $0x07033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 7 - QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] - QUAD $0x08031e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 3], 8 + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x07022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 7 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x08020f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 2], 8 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x090227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 9 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0a022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 10 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x0b021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 11 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x0c0237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 12 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0d023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 14 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0903066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 9 + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] + QUAD $0x0102075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 1 + QUAD $0x0202375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0302175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0402175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0502175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0602175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x0702175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 7 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x08021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 8 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0902375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 10 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0b02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0c02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0d02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 13 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0e02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 14 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0f02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 15 + QUAD $0x010307642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r8 + 3], 1 + QUAD $0x02030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x050307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 5 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x060337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 6 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x07030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 7 + QUAD $0x08030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 8 + QUAD $0x090327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 9 + QUAD $0x0a032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 10 + QUAD $0x0b031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 11 + WORD $0x894d; BYTE $0xdc // mov r12, r11 + QUAD $0x0c0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 12 + QUAD $0x0d033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 13 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x0e031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 15 + QUAD $0x0103076c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rax + 3], 1 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0203076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0303076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0403076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 4 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 + QUAD $0x0503076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0603076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 6 + QUAD $0x0703176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 7 + QUAD $0x08031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 12 + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 14 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - QUAD $0x0f031e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 3], 15 + QUAD $0x0e0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 14 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xc26e79c5 // vmovd xmm8, edx + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0307442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xda6e79c5 // vmovd xmm11, edx + LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x010406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 1 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x020406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 2 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x030406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 3 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x04042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 4 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x05040e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 4], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x060406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 6 - QUAD $0x070406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 7 - QUAD $0x080426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 4], 8 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x090406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 9 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0a0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 11 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0c0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 12 - QUAD $0x0d0436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 4], 13 - QUAD $0x0e0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 14 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x0f0426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 4], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0104065c2011e3c4 // vpinsrb xmm3, xmm13, byte [rsi + rax + 4], 1 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0204165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 4], 2 - QUAD $0x0304165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 3 - QUAD $0x04043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 4 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0504165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06043e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 4], 6 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x0704365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 7 - QUAD $0x08041e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 4], 8 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x09041e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 4], 9 + QUAD $0x010437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 1 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x02043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 2 + QUAD $0x030417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 3 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x040437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 4 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + QUAD $0x050407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 5 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x06041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 6 + QUAD $0x07040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 7 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x08040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 8 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x090407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 10 + QUAD $0x0b0427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 13 + QUAD $0x0e041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 14 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0f0427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 15 + QUAD $0x01042f5c2011a3c4 // vpinsrb xmm3, xmm13, byte [rdi + r13 + 4], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0204175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0304175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0404175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 4 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 10 + QUAD $0x0504075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0604175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 6 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0804075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0904075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 10 QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0b041e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 4], 11 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0c04065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 4], 12 + QUAD $0x0b041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 11 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0c041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 13 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - QUAD $0x0e043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 14 - QUAD $0x0f040e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 4], 15 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x01050e642009a3c4 // vpinsrb xmm4, xmm14, byte [rsi + r9 + 5], 1 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x02053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 2 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x03050e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 5], 3 - QUAD $0x04052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 4 - QUAD $0x05050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 5 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x06050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 6 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x07050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 7 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x080506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 8 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x090506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 9 + QUAD $0x0d04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 14 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 15 + QUAD $0x010537642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r14 + 5], 1 + QUAD $0x02053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 2 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x030517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 3 + QUAD $0x040537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 4 + QUAD $0x05050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 5 + WORD $0x8949; BYTE $0xca // mov r10, rcx + QUAD $0x06051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x07053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 7 + QUAD $0x08050f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 5], 8 + QUAD $0x090507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 9 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0a0507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 11 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0a0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 10 + QUAD $0x0c0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 11 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0c0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 14 - QUAD $0x0f0526642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 5], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0105066c2049e3c4 // vpinsrb xmm5, xmm6, byte [rsi + rax + 5], 1 - QUAD $0x0205166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 2 + QUAD $0x0d0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 13 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0305066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 3 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0405166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 4 - QUAD $0x0505166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 5], 5 - QUAD $0x06053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 6 - WORD $0x8949; BYTE $0xfa // mov r10, rdi - QUAD $0x0705366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 7 - QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] - QUAD $0x0805366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 8 - QUAD $0x09051e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 5], 9 + QUAD $0x0e0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 14 + QUAD $0x0f0527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 15 + QUAD $0x01052f6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r13 + 5], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0205076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0405076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 4 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 10 - QUAD $0x0b051e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 5], 11 - QUAD $0x0c05066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 5], 12 + QUAD $0x0505076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 5 + QUAD $0x0605176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 6 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x07051f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 5], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0805076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0905076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0b052f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 5], 11 + QUAD $0x0c051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 12 + WORD $0x894d; BYTE $0xdc // mov r12, r11 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 13 + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 14 + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0506442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 5], 15 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0507442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 5], 15 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + LONG $0x0754b60f; BYTE $0x0a // movzx edx, byte [rdi + rax + 10] + LONG $0xda6ef9c5 // vmovd xmm3, edx LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x010606442019e3c4 // vpinsrb xmm0, xmm12, byte [rsi + rax + 6], 1 - QUAD $0x02063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 2 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x03060e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 6], 3 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x04061e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 6], 4 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x050616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 6], 5 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x06061e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 6], 6 - QUAD $0x07062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 7 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x08060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 8 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x09062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 9 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0a060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 11 - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x0c0626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 6], 12 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x0d0606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 6], 13 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0e060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 15 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x01060e6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rcx + 6], 1 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x02060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 2 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x03060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x04060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 4 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x05063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 5 - QUAD $0x0606166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 6], 6 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x07060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 7 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - QUAD $0x0806366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 8 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x09060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 10 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0b06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 12 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0d06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 13 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0e06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 14 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0f06366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 15 - QUAD $0x010706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 1 - QUAD $0x02073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 2 - QUAD $0x03070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 3 - QUAD $0x04071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 4 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x050736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 5 - QUAD $0x06071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x070716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 7 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x08071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 8 - QUAD $0x09072e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 7], 9 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0a0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 10 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x0a // movzx edx, byte [rdi + rdx + 10] + LONG $0xe26ef9c5 // vmovd xmm4, edx + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x010637442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rsi + 6], 1 + QUAD $0x020637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x040637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 4 + QUAD $0x050617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 5 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x060607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 6 + QUAD $0x07063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 7 + QUAD $0x08060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 8 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x090617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 9 + QUAD $0x0a0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 10 + QUAD $0x0b060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 11 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + QUAD $0x0c0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 12 LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0b070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 11 - QUAD $0x0c0726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 7], 12 - QUAD $0x0d0706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 7], 13 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0e0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 14 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0f0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 15 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0107164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 1 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0207164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 2 + QUAD $0x0d060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 13 LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0307164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 3 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0407164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 4 - QUAD $0x05073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 5 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0607164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 6 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x07073e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 7], 7 - QUAD $0x0807164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 7], 8 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0907164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 9 - QUAD $0x0a070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 10 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x0b072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 11 + QUAD $0x0e0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 14 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0f0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 15 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x01060f6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rcx + 6], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0206176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0306176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0406176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0506176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 5 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x06060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 6 + QUAD $0x07061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 7 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x08061f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 6], 8 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x09061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 10 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x0b062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 11 + QUAD $0x0c06276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 6], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 13 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0e060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 14 + QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] + QUAD $0x0f062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 15 + QUAD $0x010737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 1 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x02072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x030737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 3 + QUAD $0x040737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 4 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x050737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 5 + QUAD $0x060707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 7 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x08070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a0737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 10 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0b0737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 11 + QUAD $0x0c0707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 12 + QUAD $0x0d070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 13 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0e070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 14 + QUAD $0x0f0717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 15 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0107374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 1 LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0c070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 12 + QUAD $0x02070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 2 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x03070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 3 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x04070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 4 + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x06070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 6 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x07070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 7 + QUAD $0x08071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 8 + QUAD $0x09071f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 7], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 10 + QUAD $0x0b073f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 7], 11 + QUAD $0x0c07274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 12 LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 13 + QUAD $0x0d070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e070e442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rcx + 7], 14 + QUAD $0x0e070f442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rcx + 7], 14 QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0e7cb60f; BYTE $0x0b // movzx edi, byte [rsi + rcx + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f070e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 7], 15 + LONG $0x0f54b60f; BYTE $0x0b // movzx edx, byte [rdi + rcx + 11] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0f070f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x0b // movzx edi, byte [rsi + rcx + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x010806442031e3c4 // vpinsrb xmm0, xmm9, byte [rsi + rax + 8], 1 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x020826442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 8], 2 + LONG $0x0f54b60f; BYTE $0x0b // movzx edx, byte [rdi + rcx + 11] + LONG $0xd26ef9c5 // vmovd xmm2, edx LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x03080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 3 - QUAD $0x04081e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 8], 4 - WORD $0x894c; BYTE $0xf3 // mov rbx, r14 - QUAD $0x050836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 8], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x060806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x070816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 7 - QUAD $0x08081e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 8], 8 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x090806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 8], 9 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0a0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 10 - QUAD $0x0b080e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 8], 11 - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x0c081e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 8], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 13 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0e0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 14 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0f083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 15 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0108166c2029e3c4 // vpinsrb xmm5, xmm10, byte [rsi + rdx + 8], 1 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0208366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 8], 2 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x03083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 4 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0508166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 5 + QUAD $0x01080f442031e3c4 // vpinsrb xmm0, xmm9, byte [rdi + rcx + 8], 1 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x02082f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 8], 2 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x03080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x040817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 4 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x05082f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 8], 5 QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0608166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 6 - QUAD $0x07083e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 8], 7 - QUAD $0x0808166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 8], 8 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x09080e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 8], 9 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x0a083e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 8], 10 - QUAD $0x0b082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 12 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0d08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 13 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0e08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 14 - LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] - QUAD $0x0f082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 15 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x01092e742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r13 + 9], 1 - QUAD $0x020926742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r12 + 9], 2 - QUAD $0x03090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 4 - QUAD $0x05091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 5 - QUAD $0x060906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x070916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 7 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x080906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 8 - QUAD $0x090906742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r8 + 9], 9 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0a0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 11 - QUAD $0x0c091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0109067c2021e3c4 // vpinsrb xmm7, xmm11, byte [rsi + rax + 9], 1 - QUAD $0x0209367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 9], 2 + QUAD $0x060817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 6 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + QUAD $0x070807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 7 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x080837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 8], 8 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x090827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 8], 9 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0a081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 10 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x0b080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 11 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x0c0817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 13 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0309067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 3 - QUAD $0x04093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 4 - WORD $0x8949; BYTE $0xfe // mov r14, rdi + QUAD $0x0e0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 15 + QUAD $0x0108376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 8], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0208076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0308076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0408176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0508076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0608076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 6 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0708376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 7 + QUAD $0x08081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0908076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 14 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0509067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 5 + QUAD $0x0f08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x010907742039e3c4 // vpinsrb xmm6, xmm8, byte [rdi + rax + 9], 1 + QUAD $0x02093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 2 + QUAD $0x03090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 4 + QUAD $0x05092f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 9], 5 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0609067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0709067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 7 - QUAD $0x0809167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 9], 8 - QUAD $0x09090e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 9], 9 - QUAD $0x0a093e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 9], 10 + QUAD $0x060907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 6 + QUAD $0x070907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 7 + QUAD $0x080937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 8 + QUAD $0x090927742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 9], 9 + QUAD $0x0a091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 10 + QUAD $0x0b090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 11 + QUAD $0x0c0917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 12 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0d0917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0109077c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rax + 9], 1 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x02092f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 9], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0309077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 3 + QUAD $0x0409177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 4 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x05091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0609077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 6 + QUAD $0x0709377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 7 + QUAD $0x08091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 8 + WORD $0x894d; BYTE $0xde // mov r14, r11 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 10 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 12 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0d093e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 9], 13 + QUAD $0x0b09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 14 + QUAD $0x0e09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f09076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 9], 15 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi + LONG $0x0754b60f; BYTE $0x0c // movzx edx, byte [rdi + rax + 12] + LONG $0xc26ef9c5 // vmovd xmm0, edx LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x00044024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm5 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x010a2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 10], 1 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x020a1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 10], 2 + LONG $0x0754b60f; BYTE $0x0c // movzx edx, byte [rdi + rax + 12] + LONG $0xea6ef9c5 // vmovd xmm5, edx LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x030a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 3 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x040a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 4 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x050a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x060a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 6 - QUAD $0x070a165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 10], 7 - QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] - QUAD $0x080a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 8 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x090a265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 10], 9 + QUAD $0x010a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 1 + QUAD $0x020a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 2 + QUAD $0x030a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 3 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x040a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 4 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x050a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x060a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x070a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 7 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x080a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 8 + QUAD $0x090a275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 10], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 11 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0a0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 10 - QUAD $0x0b0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 11 - QUAD $0x0c0a1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 10], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e0a3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 10], 14 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0f0a3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 10], 15 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x010a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 1 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x020a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 2 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 - QUAD $0x040a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x050a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 5 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x060a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x070a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 7 - QUAD $0x080a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x090a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 9 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x0a0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 11 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0c0a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 12 - QUAD $0x0d0a3e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 10], 13 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - QUAD $0x0e0a3e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 10], 14 + QUAD $0x0c0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 12 + QUAD $0x0d0a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x010a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 1 + QUAD $0x020a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x030a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 3 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x040a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 4 + QUAD $0x050a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 5 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x060a17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 10], 6 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x070a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 7 + QUAD $0x080a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 8 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x090a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 9 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0a0a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 10 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0b0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 11 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 15 - QUAD $0x010b2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 11], 1 - QUAD $0x020b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 2 + QUAD $0x0c0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 12 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x0d0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 13 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0e0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 14 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0f0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 15 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x030b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 3 - QUAD $0x040b0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 11], 4 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x050b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 5 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x060b2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 11], 6 - QUAD $0x070b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 7 - WORD $0x8949; BYTE $0xd1 // mov r9, rdx - QUAD $0x080b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 8 - QUAD $0x090b264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 11], 9 + QUAD $0x010b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 1 + QUAD $0x020b3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 11], 2 + QUAD $0x030b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 3 + QUAD $0x040b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 4 + QUAD $0x050b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 5 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x060b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 7 + QUAD $0x080b0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 11], 8 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x090b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 11 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0a0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 10 + QUAD $0x0c0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 11 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0c0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 12 - QUAD $0x0d0b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 14 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x0f0b3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 11], 15 - QUAD $0x010b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 11], 1 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x020b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 2 - QUAD $0x030b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x040b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 4 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x050b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x060b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 6 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x070b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 7 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x080b26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 11], 8 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x090b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 9 - QUAD $0x0a0b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 11], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 11 - QUAD $0x0c0b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 11], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 13 + QUAD $0x0d0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 13 + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + QUAD $0x0e0b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x010b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 1 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x020b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 2 + QUAD $0x030b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 3 + QUAD $0x040b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x050b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 5 + QUAD $0x060b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 11], 6 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x070b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x080b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 8 + QUAD $0x090b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 9 + QUAD $0x0a0b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b0b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c0b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 12 + QUAD $0x0d0b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000420249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm3 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 14 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rcx + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 15 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0e0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 14 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x0d // movzx edx, byte [rdi + rdx + 13] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x0f0b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000400248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm1 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rcx + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x010c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 1 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x020c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x030c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 3 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x040c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 4 - QUAD $0x050c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 5 - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - QUAD $0x060c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 6 - QUAD $0x070c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 7 - QUAD $0x080c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 12], 8 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x090c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 9 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0a0c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b0c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 11 - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x0c0c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 12], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d0c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 13 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0e0c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 12], 14 - WORD $0x894d; BYTE $0xfa // mov r10, r15 - QUAD $0x0f0c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 12], 15 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x010c2e542051a3c4 // vpinsrb xmm2, xmm5, byte [rsi + r13 + 12], 1 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x020c3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 12], 2 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x030c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 3 - QUAD $0x040c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 4 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x0d // movzx edx, byte [rdi + rdx + 13] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x010c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 1 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x020c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x030c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x040c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 4 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x050c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 5 + QUAD $0x060c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x070c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x080c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 8 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + QUAD $0x090c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 9 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0a0c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 10 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x0b0c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 12], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 13 + QUAD $0x0e0c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 15 + QUAD $0x010c07542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rax + 12], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x020c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x040c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 4 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x050c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x060c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 6 + QUAD $0x070c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x080c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 8 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x090c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 9 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0a0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 12 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x0d0c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 13 + QUAD $0x0e0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 14 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x050c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x060c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 6 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x070c3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 12], 7 - QUAD $0x080c26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 12], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x090c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 10 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0b0c26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 12], 11 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0c0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 13 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 14 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 15 + QUAD $0x0f0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 15 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x010d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 13], 1 + QUAD $0x020d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 2 + QUAD $0x030d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 4 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x050d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 5 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x060d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 6 + QUAD $0x070d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 7 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x080d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 13], 8 + QUAD $0x090d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 9 + QUAD $0x0a0d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 10 + QUAD $0x0b0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 11 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 15 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x010d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 1 + QUAD $0x020d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 2 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x030d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 3 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x040d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 4 + QUAD $0x050d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 5 QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x010d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 1 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x020d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x030d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 3 - QUAD $0x040d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 4 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x050d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 5 - QUAD $0x060d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 6 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x070d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 7 - QUAD $0x080d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 13], 8 - QUAD $0x090d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 9 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0a0d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 11 - QUAD $0x0c0d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 12 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x0d0d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 13 - QUAD $0x0e0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 14 - QUAD $0x0f0d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 13], 15 - QUAD $0x010d2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 13], 1 - QUAD $0x020d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 2 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x030d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x040d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 4 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x050d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x060d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 6 - QUAD $0x070d3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 13], 7 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x080d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 8 - QUAD $0x090d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 10 - QUAD $0x0b0d264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 13], 11 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0c0d164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 13], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 14 + QUAD $0x060d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x070d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x080d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 8 + QUAD $0x090d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 9 + QUAD $0x0a0d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 12 + QUAD $0x0d0d3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 13], 13 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0e0d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0d06442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rax + 13], 15 - QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x0e2e // movzx edi, byte [rsi + r13 + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0d07442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x0e // movzx edx, byte [rdi + rax + 14] + LONG $0xca6ef9c5 // vmovd xmm1, edx LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x0e36 // movzx edi, byte [rsi + r14 + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x010e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 1 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x020e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 14], 2 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x030e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 14], 3 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x040e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 14], 4 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x0e // movzx edx, byte [rdi + rax + 14] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] + QUAD $0x020e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 2 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x050e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 5 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x060e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 6 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x070e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 7 + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 4 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x050e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 14], 5 + QUAD $0x060e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 14], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + QUAD $0x080e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 8 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x090e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x080e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 8 + QUAD $0x0b0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 12 + QUAD $0x0d0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 15 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x090e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 9 - QUAD $0x0a0e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 14], 10 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0b0e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 11 + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x020e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 2 + QUAD $0x030e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x040e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 4 + QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] + QUAD $0x050e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 14], 5 + QUAD $0x060e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 6 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0c0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 12 - QUAD $0x0d0e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 13 + QUAD $0x070e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 7 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x080e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 8 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x090e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0b0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c0e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 12 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0d0e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 13 + QUAD $0x0e0e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 14 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0f0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 15 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + LONG $0x54b60f42; WORD $0x0f37 // movzx edx, byte [rdi + r14 + 15] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x010f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 1 + QUAD $0x020f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x030f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 3 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x040f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 4 + QUAD $0x050f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 5 + QUAD $0x060f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x070f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x080f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 8 + QUAD $0x090f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 9 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x0a0f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x0f // movzx edx, byte [rdi + rax + 15] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x010f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 1 + QUAD $0x020f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x030f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x040f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 4 + QUAD $0x050f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x060f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x070f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 7 + QUAD $0x080f1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 15], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x090f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 15 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x010e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 14], 1 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x020e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x030e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 3 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x040e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 14], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x050e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 5 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x060e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 14], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x070e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 7 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x080e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 8 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x090e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 10 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0b0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 11 - QUAD $0x0c0e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 14], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0f0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 15 - LONG $0x7cb60f42; WORD $0x0f2e // movzx edi, byte [rsi + r13 + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x010f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 1 - QUAD $0x020f16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 15], 2 - QUAD $0x030f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 3 - QUAD $0x040f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 4 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x050f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 5 - QUAD $0x060f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x070f16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 15], 7 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x080f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 8 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x090f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 9 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0a0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 10 - QUAD $0x0b0f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 11 - QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] - QUAD $0x0c0f2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 15], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 13 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x0e0f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 15 - LONG $0x7cb60f42; WORD $0x0f36 // movzx edi, byte [rsi + r14 + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x010f0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 15], 1 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x020f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 2 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x030f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 3 - QUAD $0x040f1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 15], 4 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x050f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 5 - QUAD $0x060f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 6 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - QUAD $0x070f165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 15], 7 - QUAD $0x080f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x090f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 10 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0b0f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 13 + QUAD $0x0a0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 10 + QUAD $0x0b0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0d0f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 14 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x0f0f3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 15], 15 + QUAD $0x0e0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 14 + QUAD $0x0f0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x10 // movzx edi, byte [rsi + rax + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x011036442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 16], 1 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x021006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 2 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x03101e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 16], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 4 - QUAD $0x05101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 5 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x06100e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 16], 6 - QUAD $0x071016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 7 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x081016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 8 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x091006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 9 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0a101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 11 - QUAD $0x0c102e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 16], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 13 - QUAD $0x0e1006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x10 // movzx edi, byte [rsi + rdi + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x01103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 1 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x02103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 2 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x03103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 4 - QUAD $0x05100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x06100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 6 - QUAD $0x0710164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 16], 7 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x08100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 8 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x09103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 10 - QUAD $0x0b10264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 11 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0c103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 12 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0d10264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 13 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0e102e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 16], 14 - QUAD $0x0f103e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 16], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x11 // movzx edi, byte [rsi + rdi + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011136542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 17], 1 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x021106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 2 - QUAD $0x03111e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 17], 3 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x041116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 4 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x05113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 5 - QUAD $0x06110e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 17], 6 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x07113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 7 - QUAD $0x081116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 8 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x091116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 9 - QUAD $0x0a111e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 17], 10 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x0b111e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 17], 11 - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x0c1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 12 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0d1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 13 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0e1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 14 - QUAD $0x0f1106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x11 // movzx edi, byte [rsi + rax + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0111365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 17], 1 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x02113e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 17], 2 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x03110e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 17], 3 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0411165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0511065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 5 + LONG $0x54b60f42; WORD $0x1037 // movzx edx, byte [rdi + r14 + 16] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x01100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 1 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 3 + QUAD $0x041017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 4 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x051007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 5 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0611065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 6 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x07111e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 17], 7 - QUAD $0x08110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 8 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x09110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 11 + QUAD $0x061007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 6 + QUAD $0x07103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 7 + QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] + QUAD $0x08101f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 16], 8 + QUAD $0x09102f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 16], 9 + QUAD $0x0a1027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 13 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0e1037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 14 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0f1007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 15 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + LONG $0x1f54b60f; BYTE $0x10 // movzx edx, byte [rdi + rbx + 16] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x0110174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 16], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0210174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 2 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0310374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0410174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 4 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x05103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0610174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 6 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x07100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 7 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x08102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 8 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0910174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 10 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0b10274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 13 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0e10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x11 // movzx edx, byte [rdi + rdx + 17] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 1 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x02110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 2 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x03110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 3 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x05110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 5 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x06110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x07110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 7 + QUAD $0x08111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x09110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 11 + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 13 + QUAD $0x0e1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 14 + QUAD $0x0f1107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 15 + LONG $0x1f54b60f; BYTE $0x11 // movzx edx, byte [rdi + rbx + 17] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x0111175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 1 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 12 - QUAD $0x0d11265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 17], 13 - QUAD $0x0e112e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 17], 14 + QUAD $0x0211075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 2 + QUAD $0x0311375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0411375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 4 + QUAD $0x05113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 5 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x06113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 6 + QUAD $0x07110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 7 + QUAD $0x08112f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 17], 8 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0911075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 10 + QUAD $0x0b11275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 11 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x0c110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f1106442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rax + 17], 15 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f1107442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x12 // movzx edi, byte [rsi + rax + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x011206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 1 - QUAD $0x021206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 18], 2 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + LONG $0x1f54b60f; BYTE $0x12 // movzx edx, byte [rdi + rbx + 18] + LONG $0xc26ef9c5 // vmovd xmm0, edx LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x031206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 3 - QUAD $0x041216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 4 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x051206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 5 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x061206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 18], 6 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x071206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 7 + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x021237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 2 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x031217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x041207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 4 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x05121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 5 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 7 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x081207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 8 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x091207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 10 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x081206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 8 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x091206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 9 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0a1216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 10 - QUAD $0x0b121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 11 - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x0c1226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 18], 12 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x0d121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 14 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0f123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x12 // movzx edi, byte [rsi + rdi + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0112364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 18], 1 - QUAD $0x02123e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 18], 2 - QUAD $0x03120e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 18], 3 - QUAD $0x0412164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 4 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0512164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 5 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0612364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 18], 6 - QUAD $0x07121e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 18], 7 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - QUAD $0x0812164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 8 - QUAD $0x09120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 10 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x0b123e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 18], 11 + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 13 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0e1227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 14 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0f122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x12 // movzx edx, byte [rdi + rdx + 18] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0112174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 1 LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c12164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 13 - QUAD $0x0e122e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 18], 14 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0f121e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 18], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rdi + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 1 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x02133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x03133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 3 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x04133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 4 - QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] - QUAD $0x05132e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 19], 5 - QUAD $0x061306542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 19], 6 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x07133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x08133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 8 - QUAD $0x091306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 9 - QUAD $0x0a1316542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 19], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 11 - QUAD $0x0c1326542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 19], 12 - QUAD $0x0d131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 13 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0e130e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 19], 14 + QUAD $0x0212174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0312174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 3 + QUAD $0x0412374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0512174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 5 + QUAD $0x06123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 6 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x07123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0812174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 8 + QUAD $0x0912074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 9 + QUAD $0x0a120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0b120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 11 + QUAD $0x0c120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 13 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0e120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 14 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0f120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 15 + LONG $0x1f54b60f; BYTE $0x13 // movzx edx, byte [rdi + rbx + 19] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x01130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 1 + QUAD $0x021337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 2 + QUAD $0x031317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 3 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x04130f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 19], 4 + QUAD $0x05131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 5 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x06130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 6 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x071307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 7 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x081337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 8 + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + QUAD $0x091317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 10 + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 13 + QUAD $0x0e1327542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 19], 14 + QUAD $0x0f132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x13 // movzx edx, byte [rdi + rax + 19] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x01131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 15 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x1316 // movzx edi, byte [rsi + r10 + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0113065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 1 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0213065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0313065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 3 + QUAD $0x0313075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 3 + QUAD $0x0413375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0613375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 6 + QUAD $0x07133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0813075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 8 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0413065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0513065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 5 - QUAD $0x0613365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 19], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0713065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 7 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0813065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0913065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 9 - QUAD $0x0a130e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 19], 10 - QUAD $0x0b133e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 19], 11 - QUAD $0x0c13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 12 + QUAD $0x0913075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 13 + QUAD $0x0d13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 14 - QUAD $0x0f131e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 19], 15 + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x141e // movzx edi, byte [rsi + r11 + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x011406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 1 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x021416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x03143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 3 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x04143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 4 - QUAD $0x05142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x06143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 6 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x07142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 7 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - QUAD $0x08143e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 20], 8 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x09143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 9 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0a1426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 11 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x0c143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 13 - QUAD $0x0e140e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 20], 14 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x0f1436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 20], 15 - LONG $0x7cb60f42; WORD $0x1416 // movzx edi, byte [rsi + r10 + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x01141e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 20], 1 - QUAD $0x0214064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 20], 2 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0314064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 20], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 4 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x05143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 6 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - QUAD $0x0714164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 20], 7 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x08143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 8 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x09143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 10 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0b143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 11 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x0c140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0e143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 14 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0f143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 15 - LONG $0x7cb60f42; WORD $0x151e // movzx edi, byte [rsi + r11 + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 1 - QUAD $0x021516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 2 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x031516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 4 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x14 // movzx edx, byte [rdi + rax + 20] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x011427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 1 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x051506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x061506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 6 - QUAD $0x07152e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 21], 7 - QUAD $0x08153e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 21], 8 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x091506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 9 - QUAD $0x0a1526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 10 - QUAD $0x0b150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 11 - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x0c1526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 14 - QUAD $0x0f1536542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 21], 15 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x151e // movzx edi, byte [rsi + r11 + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01151e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 21], 1 + QUAD $0x031407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 3 + QUAD $0x04140f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 20], 4 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x06140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 6 + QUAD $0x071407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 7 + QUAD $0x081437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 8 + QUAD $0x091417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 9 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0215065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 2 - QUAD $0x0315065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 21], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x04150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0515065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0615065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 6 - QUAD $0x0715165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 7 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x08152e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 21], 8 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x09153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 9 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x0a153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 10 + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 11 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x0c142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 12 + QUAD $0x0d141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 13 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0e141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 15 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + LONG $0x54b60f42; WORD $0x140f // movzx edx, byte [rdi + r9 + 20] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 1 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x0214074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 2 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x03143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 3 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x04140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 4 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x05140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 5 + QUAD $0x0614374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x0714174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0814174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 8 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0914174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 9 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x0a14174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0d14374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 13 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0e14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 14 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0f14374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 20], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x15 // movzx edx, byte [rdi + rdx + 21] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x011527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 2 + QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] + QUAD $0x03151f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 21], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x041517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 4 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x051517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x081517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 8 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x091517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 9 + QUAD $0x0a1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 11 + QUAD $0x0c152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 13 + QUAD $0x0e151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 14 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0f152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 15 + LONG $0x54b60f42; WORD $0x150f // movzx edx, byte [rdi + r9 + 21] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0115075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 1 + QUAD $0x0215075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 2 + QUAD $0x03153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 3 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x04150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 4 + QUAD $0x05150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0715075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x0915275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 21], 9 + QUAD $0x0a15175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 10 QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0b151e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 21], 11 - QUAD $0x0c150e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 21], 12 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x0d15065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 21], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0e153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 14 + QUAD $0x0b151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0c150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 12 + QUAD $0x0d15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 13 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0e150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x0f1516442061a3c4 // vpinsrb xmm0, xmm3, byte [rsi + r10 + 21], 15 + QUAD $0x0f1537442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r14 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rdi + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 1 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x02163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 2 - QUAD $0x031616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 3 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x041616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 4 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x051616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 5 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x061616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x071616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 7 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x081616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 8 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x091616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 9 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0a1636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 22], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 11 - QUAD $0x0c1626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 22], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 13 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0e160e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 22], 14 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0f163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 15 - LONG $0x7cb60f42; WORD $0x161e // movzx edi, byte [rsi + r11 + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x01163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 1 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x02163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 2 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x0316264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 22], 3 - QUAD $0x04160e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 22], 4 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x05160e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 22], 5 - QUAD $0x0616064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 6 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - QUAD $0x07161e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 22], 7 - QUAD $0x08162e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 22], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0916064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 9 - QUAD $0x0a163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 10 - QUAD $0x0b161e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 22], 11 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x0c163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 12 - QUAD $0x0d16064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 22], 13 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e160e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 22], 14 - QUAD $0x0f16164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rdi + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x011716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 23], 1 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x021706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 23], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x03173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 3 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x04173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 4 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x05173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 5 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x06172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 6 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x07173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x08173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 8 - QUAD $0x091716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 9 - QUAD $0x0a1736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 10 + QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + LONG $0x54b60f42; WORD $0x1617 // movzx edx, byte [rdi + r10 + 22] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x01163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 1 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x021607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 2 + QUAD $0x03161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 3 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x04160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 4 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x05160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 5 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x061637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 6 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x07161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 7 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x081637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x09160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 12 LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0b1716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 11 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0c1736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 12 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x0d171e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 23], 13 - QUAD $0x0e170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 14 + QUAD $0x0d1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 14 + QUAD $0x0f162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x16 // movzx edx, byte [rdi + rdx + 22] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0116174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0216174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 2 LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0f1716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rdi + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x01170e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 23], 1 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x02173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 2 - QUAD $0x0317265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 4 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x05173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 6 - QUAD $0x07171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 7 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x0817265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 8 - QUAD $0x0917065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 9 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x0a171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 11 - QUAD $0x0c173e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 23], 12 + QUAD $0x0316174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 3 + QUAD $0x04160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 4 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x05162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0616174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 6 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x07160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 7 + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + QUAD $0x0916274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 10 + QUAD $0x0b161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 11 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x0c16274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 13 - QUAD $0x0e170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 14 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 15 + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 14 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 15 + LONG $0x54b60f42; WORD $0x1717 // movzx edx, byte [rdi + r10 + 23] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 1 + QUAD $0x021707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 23], 2 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x031717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x041707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 4 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x051707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 5 + QUAD $0x061737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 6 + QUAD $0x07171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 7 + QUAD $0x081737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 8 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x091737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 10 + QUAD $0x0b170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 13 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x0e171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 15 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + LONG $0x54b60f42; WORD $0x173f // movzx edx, byte [rdi + r15 + 23] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x01170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0317175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0417175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 4 + QUAD $0x05172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 5 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x06172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 6 + QUAD $0x07170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0817175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 8 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0917075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 11 + QUAD $0x0c17275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 13 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0e17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rcx + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 24], 1 - QUAD $0x021806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 24], 2 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x031816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 24], 3 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x04183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 4 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x05183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 5 - QUAD $0x06182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 6 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - QUAD $0x071806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 24], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x08183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 8 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x09182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 9 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0a183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 11 - QUAD $0x0c1836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 24], 12 - QUAD $0x0d181e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 24], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 14 - QUAD $0x0f1816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 24], 15 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x18 // movzx edi, byte [rsi + rdx + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x01180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 1 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x02180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 2 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x03183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 4 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x05183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 6 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x07183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 7 - QUAD $0x0818264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 8 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x09183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 9 - QUAD $0x0a181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 10 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0b183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 11 - QUAD $0x0c183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 12 - QUAD $0x0d18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 14 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0f181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 15 - LONG $0x0e7cb60f; BYTE $0x19 // movzx edi, byte [rsi + rcx + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x011906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 1 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x02191e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 25], 2 - QUAD $0x031916542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 25], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 4 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x051936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x061906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 6 - QUAD $0x071906542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 25], 7 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x08190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 8 - QUAD $0x09192e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 25], 9 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x0a193e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 25], 10 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0b1906542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 25], 11 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0c1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 14 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x18 // movzx edx, byte [rdi + rdx + 24] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x011817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 2 + QUAD $0x031817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x041817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 4 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x051817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x081817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 8 + QUAD $0x091837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 9 + QUAD $0x0a1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 10 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0b1837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 12 + QUAD $0x0d181f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 24], 13 + QUAD $0x0e181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 15 + LONG $0x54b60f42; WORD $0x183f // movzx edx, byte [rdi + r15 + 24] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 1 + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 15 - LONG $0x167cb60f; BYTE $0x19 // movzx edi, byte [rsi + rdx + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x0119265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 1 - QUAD $0x02190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0319065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0419065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0519065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 5 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x06192e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 25], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0719065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 7 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0819065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 8 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0919165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 25], 9 + QUAD $0x0318074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 3 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x0418274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 4 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 11 + QUAD $0x0518074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 5 + QUAD $0x06182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 6 + QUAD $0x07180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 7 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x08183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 8 + QUAD $0x0918074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 10 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0b18074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0c180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 12 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x0d18174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 13 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0e18374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 14 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0f181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x19 // movzx edx, byte [rdi + rax + 25] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x01192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x041917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 4 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x05191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x081917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 8 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x091917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 10 + QUAD $0x0b1937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x19 // movzx edx, byte [rdi + rdx + 25] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0119175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 1 LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c19165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 12 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0d19165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 13 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0e19165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 14 + QUAD $0x0219175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0319175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 3 + QUAD $0x0419275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0519175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0619175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 6 + QUAD $0x07190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 7 + QUAD $0x08193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 8 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x09193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 9 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x0a190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 10 + QUAD $0x0b19075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 25], 11 + QUAD $0x0c190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 12 + QUAD $0x0d19175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 25], 13 + QUAD $0x0e19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 14 LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 - QUAD $0x0f191e442061a3c4 // vpinsrb xmm0, xmm3, byte [rsi + r11 + 25], 15 + QUAD $0x0f191f442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rbx + 25], 15 LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x1a1e // movzx edi, byte [rsi + r11 + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x011a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 1 - QUAD $0x021a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 2 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x031a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 3 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x041a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 4 - QUAD $0x051a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 5 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x061a0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 26], 6 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x071a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 7 - QUAD $0x081a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 8 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x091a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 9 - QUAD $0x0a1a3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 26], 10 - QUAD $0x0b1a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 11 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0c1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 12 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x0d1a3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 26], 13 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0e1a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f1a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x1a // movzx edi, byte [rsi + rcx + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 1 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x021a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 2 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x031a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x041a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 4 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x051a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 5 - QUAD $0x061a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 6 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x071a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 7 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x081a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 8 - QUAD $0x091a164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 26], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a1a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 10 - QUAD $0x0b1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 12 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0d1a164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 26], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 14 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 15 - LONG $0x7cb60f42; WORD $0x1b1e // movzx edi, byte [rsi + r11 + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x011b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 27], 1 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x021b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 2 - QUAD $0x031b1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 27], 3 - QUAD $0x041b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 4 - QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - QUAD $0x051b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 5 - QUAD $0x061b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 27], 6 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x071b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 7 + LONG $0x0754b60f; BYTE $0x1a // movzx edx, byte [rdi + rax + 26] + LONG $0xc26ef9c5 // vmovd xmm0, edx + QUAD $0x011a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 1 + QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] + QUAD $0x021a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x041a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 4 + QUAD $0x051a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 5 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x061a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x071a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 7 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x081a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x091a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 10 QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x081b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 8 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x091b1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 27], 9 + QUAD $0x0b1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 11 LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0a1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 10 + QUAD $0x0c1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 12 LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0b1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 11 - QUAD $0x0c1b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 27], 12 - QUAD $0x0d1b3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 27], 13 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0e1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 14 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0f1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 15 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x1b // movzx edi, byte [rsi + rdx + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x011b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 1 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x021b0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 27], 2 + QUAD $0x0d1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 13 LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x031b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 3 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x041b365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 27], 4 - QUAD $0x051b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 5 - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - QUAD $0x061b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 6 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x071b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 7 - QUAD $0x081b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 8 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x091b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 9 - QUAD $0x0a1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 11 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0c1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 12 - QUAD $0x0d1b165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 27], 13 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0e1b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 14 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 15 + QUAD $0x0e1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3754b60f; BYTE $0x1a // movzx edx, byte [rdi + rsi + 26] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x011a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 1 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x021a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 2 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x031a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 3 + QUAD $0x041a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x051a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x061a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 6 + QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] + QUAD $0x071a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x081a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 8 + QUAD $0x091a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 9 + QUAD $0x0a1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 13 + QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] + QUAD $0x0e1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x1b // movzx edx, byte [rdi + rdx + 27] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x011b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 1 + QUAD $0x021b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 2 + WORD $0x894d; BYTE $0xd5 // mov r13, r10 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 3 + QUAD $0x041b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 4 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x051b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 5 + QUAD $0x061b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + QUAD $0x081b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 8 + QUAD $0x091b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 10 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0b1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 11 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0c1b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 14 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x0f1b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 15 + LONG $0x3754b60f; BYTE $0x1b // movzx edx, byte [rdi + rsi + 27] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x011b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 1 + QUAD $0x021b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 2 + QUAD $0x031b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 3 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x041b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 4 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x051b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 5 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x061b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 6 + QUAD $0x071b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x081b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 8 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x091b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 13 + QUAD $0x0e1b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0e7cb60f; BYTE $0x1c // movzx edi, byte [rsi + rcx + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 1 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x021c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x031c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 3 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x041c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 4 - QUAD $0x051c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x061c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 6 - QUAD $0x071c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 7 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x081c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 8 - QUAD $0x091c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 9 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0a1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 11 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - QUAD $0x0c1c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e1c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 14 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0f1c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 15 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x1c26 // movzx edi, byte [rsi + r12 + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x011c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 1 - QUAD $0x021c0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 28], 2 - QUAD $0x031c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 3 - QUAD $0x041c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 4 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - QUAD $0x051c0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 28], 5 - QUAD $0x061c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 6 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x071c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 7 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - QUAD $0x081c064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 28], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x091c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 9 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x0a1c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 10 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - QUAD $0x0b1c164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 28], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c1c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d1c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 13 - QUAD $0x0e1c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 14 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0f1c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x1d // movzx edi, byte [rsi + rdi + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x011d2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 29], 1 - QUAD $0x021d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x031d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 3 - QUAD $0x041d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 4 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x051d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x061d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 6 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x071d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x081d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 8 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x091d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 9 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0a1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 11 - QUAD $0x0c1d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 14 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0f1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 15 - LONG $0x7cb60f42; WORD $0x1d26 // movzx edi, byte [rsi + r12 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x011d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 29], 1 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x021d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 2 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x031d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 3 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x041d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 29], 4 - QUAD $0x051d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x061d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 6 - QUAD $0x071d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 29], 7 - QUAD $0x081d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 29], 8 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x091d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 9 - QUAD $0x0a1d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 10 - QUAD $0x0b1d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 29], 11 - QUAD $0x0c1d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 29], 12 - WORD $0x8949; BYTE $0xd6 // mov r14, rdx - QUAD $0x0d1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 13 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x0e1d16642061a3c4 // vpinsrb xmm4, xmm3, byte [rsi + r10 + 29], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0f1d16442059e3c4 // vpinsrb xmm0, xmm4, byte [rsi + rdx + 29], 15 - LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x1e06 // movzx edi, byte [rsi + r8 + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011e2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 30], 1 - LONG $0x7cb60f42; WORD $0x1f06 // movzx edi, byte [rsi + r8 + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 31], 1 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x021e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 2 - QUAD $0x021f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 2 - QUAD $0x031e0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 30], 3 - QUAD $0x031f0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 31], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 - QUAD $0x051e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 30], 5 - QUAD $0x051f1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 31], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x061e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 6 - QUAD $0x061f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 6 - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0a1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 10 - QUAD $0x0a1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 11 - QUAD $0x0b1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 11 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0c1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 12 - QUAD $0x0c1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 13 - QUAD $0x0d1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 14 - QUAD $0x0e1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 15 - QUAD $0x0f1f06542071e3c4 // vpinsrb xmm2, xmm1, byte [rsi + rax + 31], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e44b60f; BYTE $0x1e // movzx eax, byte [rsi + rcx + 30] - LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x011e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 30], 1 - LONG $0x0e44b60f; BYTE $0x1f // movzx eax, byte [rsi + rcx + 31] - LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f1e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 31], 1 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x021e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 2 - QUAD $0x021f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - QUAD $0x041e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 30], 4 - QUAD $0x041f267c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r12 + 31], 4 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 6 - QUAD $0x061f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 6 - QUAD $0x071e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 30], 7 - QUAD $0x071f3e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 31], 7 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x1c // movzx edx, byte [rdi + rdx + 28] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x011c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 1 + QUAD $0x021c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 3 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x041c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 4 + QUAD $0x051c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 6 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x071c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 7 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x081c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 8 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x091c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 10 + QUAD $0x0b1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 11 + QUAD $0x0c1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 12 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0d1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 13 + QUAD $0x0e1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 14 + QUAD $0x0f1c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 15 + QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] + LONG $0x54b60f42; WORD $0x1c1f // movzx edx, byte [rdi + r11 + 28] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x011c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x031c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 3 + QUAD $0x041c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 4 + QUAD $0x051c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 5 + QUAD $0x061c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 6 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x071c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 7 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x081c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 8 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x091c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0b1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0c1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 13 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0e1c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x1d // movzx edx, byte [rdi + rdx + 29] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x011d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 3 + QUAD $0x041d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 4 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x051d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 6 + QUAD $0x071d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 7 + QUAD $0x081d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 8 + QUAD $0x091d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 10 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + QUAD $0x0b1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 11 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0c1d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 12 + QUAD $0x0d1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e1d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 14 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0f1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 15 + LONG $0x54b60f42; WORD $0x1d1f // movzx edx, byte [rdi + r11 + 29] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x011d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x021d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 2 + QUAD $0x031d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 3 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x041d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 + QUAD $0x061d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 29], 6 + QUAD $0x071d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x081d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 8 + QUAD $0x091d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 9 + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 10 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0b1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 11 + QUAD $0x0c1d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d1d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 13 + QUAD $0x0e1d17642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r10 + 29], 14 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 + QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] + QUAD $0x0f1d17442059a3c4 // vpinsrb xmm0, xmm4, byte [rdi + r10 + 29], 15 + LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 + QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x1e // movzx edx, byte [rdi + rax + 30] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x011e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 30], 1 + LONG $0x0754b60f; BYTE $0x1f // movzx edx, byte [rdi + rax + 31] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x011f1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 31], 1 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x081e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 8 - QUAD $0x081f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 8 + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x091e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 30], 9 - QUAD $0x091f0e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 31], 9 + QUAD $0x051e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 5 + QUAD $0x051f0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 31], 5 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x00000110249c8b48 // mov rbx, qword [rsp + 272] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + QUAD $0x0b1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 11 + QUAD $0x0b1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 11 + QUAD $0x0c1e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 30], 12 + QUAD $0x0c1f274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 31], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x0f1e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 30], 15 + QUAD $0x0f1f37542071a3c4 // vpinsrb xmm2, xmm1, byte [rdi + r14 + 31], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1744b60f; BYTE $0x1e // movzx eax, byte [rdi + rdx + 30] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 1 + LONG $0x1744b60f; BYTE $0x1f // movzx eax, byte [rdi + rdx + 31] + LONG $0xf86ef9c5 // vmovd xmm7, eax + QUAD $0x011f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x041e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 4 + QUAD $0x041f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 4 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 11 - QUAD $0x0b1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 11 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - QUAD $0x0c1e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 30], 12 - QUAD $0x0c1f367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 31], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 13 - QUAD $0x0d1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 13 - QUAD $0x0e1e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 30], 14 - QUAD $0x0e1f167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 31], 14 - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - QUAD $0x0f1e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 30], 15 - QUAD $0x0f1f167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 31], 15 + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 30], 9 + QUAD $0x091f3f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 31], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0b1e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 11 + QUAD $0x0b1f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x0d1e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 30], 13 + QUAD $0x0d1f0f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 31], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 14 + QUAD $0x0e1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 14 + QUAD $0x0f1e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 15 + QUAD $0x0f1f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -8013,1993 +8313,2002 @@ LBB1_167: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x7f7ec1c4; WORD $0x8b44; BYTE $0x60 // vmovdqu yword [r11 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8b54; BYTE $0x40 // vmovdqu yword [r11 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8b64; BYTE $0x20 // vmovdqu yword [r11 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8b0c // vmovdqu yword [r11 + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608b // vmovdqu yword [rbx + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408b // vmovdqu yword [rbx + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208b // vmovdqu yword [rbx + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8b // vmovdqu yword [rbx + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB1_167 - QUAD $0x0000018824ac8b4c // mov r13, qword [rsp + 392] - QUAD $0x0000018024ac3b4c // cmp r13, qword [rsp + 384] + JNE LBB1_191 + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - QUAD $0x0000019024a48b4c // mov r12, qword [rsp + 400] - JNE LBB1_36 - JMP LBB1_109 - -LBB1_169: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 + LONG $0x24648b44; BYTE $0x1c // mov r12d, dword [rsp + 28] + QUAD $0x0000019024b48b48 // mov rsi, qword [rsp + 400] + JNE LBB1_139 + JMP LBB1_143 + +LBB1_193: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - QUAD $0x0000018024bc894c // mov qword [rsp + 384], r15 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000017824848948 // mov qword [rsp + 376], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB1_170: +LBB1_194: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000019824848948 // mov qword [rsp + 408], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000d824848948 // mov qword [rsp + 216], rax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rcx + 1] + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] + WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x0e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rcx + 2] - WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] - QUAD $0x000000f824948948 // mov qword [rsp + 248], rdx + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x000000f024948948 // mov qword [rsp + 240], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax LONG $0x40cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 576 - QUAD $0x00000100249c8948 // mov qword [rsp + 256], rbx + QUAD $0x00000108249c8948 // mov qword [rsp + 264], rbx WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x02600d48; WORD $0x0000 // or rax, 608 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - WORD $0x8949; BYTE $0xcc // mov r12, rcx - LONG $0x80cc8149; WORD $0x0002; BYTE $0x00 // or r12, 640 - QUAD $0x000000d024a4894c // mov qword [rsp + 208], r12 + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax WORD $0x8949; BYTE $0xce // mov r14, rcx - LONG $0xa0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 672 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + LONG $0x80ce8149; WORD $0x0002; BYTE $0x00 // or r14, 640 + LONG $0x2474894c; BYTE $0x70 // mov qword [rsp + 112], r14 WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x02c00d48; WORD $0x0000 // or rax, 704 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0xe0cf8148; WORD $0x0002; BYTE $0x00 // or rdi, 736 - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - LONG $0x00c98149; WORD $0x0003; BYTE $0x00 // or r9, 768 - QUAD $0x000000e0248c894c // mov qword [rsp + 224], r9 + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + WORD $0x8949; BYTE $0xcc // mov r12, rcx + LONG $0xc0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 704 + QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 + WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0xe0ce8148; WORD $0x0002; BYTE $0x00 // or rsi, 736 + QUAD $0x000000d024b48948 // mov qword [rsp + 208], rsi WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x20cf8149; WORD $0x0003; BYTE $0x00 // or r15, 800 - LONG $0x247c894c; BYTE $0x70 // mov qword [rsp + 112], r15 + LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 + QUAD $0x000000e024bc894c // mov qword [rsp + 224], r15 WORD $0x8949; BYTE $0xcb // mov r11, rcx - LONG $0x40cb8149; WORD $0x0003; BYTE $0x00 // or r11, 832 - QUAD $0x000000c0249c894c // mov qword [rsp + 192], r11 + LONG $0x20cb8149; WORD $0x0003; BYTE $0x00 // or r11, 800 + QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 WORD $0x8949; BYTE $0xca // mov r10, rcx - LONG $0x60ca8149; WORD $0x0003; BYTE $0x00 // or r10, 864 + LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 LONG $0x2454894c; BYTE $0x58 // mov qword [rsp + 88], r10 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 + QUAD $0x000000d8248c894c // mov qword [rsp + 216], r9 WORD $0x8949; BYTE $0xc8 // mov r8, rcx LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 - QUAD $0x000000802484894c // mov qword [rsp + 128], r8 + LONG $0x2444894c; BYTE $0x50 // mov qword [rsp + 80], r8 WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xa0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 928 - QUAD $0x000000f024948948 // mov qword [rsp + 240], rdx + LONG $0x24548948; BYTE $0x48 // mov qword [rsp + 72], rdx WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x00000108248c8948 // mov qword [rsp + 264], rcx + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x50 // mov qword [rsp + 80], rcx - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - LONG $0x207923c4; WORD $0x2e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + r13], 1 - LONG $0x2031e3c4; WORD $0x1e04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + rbx], 2 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 3 - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + r12], 4 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + r14], 5 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 6 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + rdi], 7 - WORD $0x8949; BYTE $0xfd // mov r13, rdi - QUAD $0x000000a024bc8948 // mov qword [rsp + 160], rdi - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + r9], 8 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + r15], 9 - LONG $0x2079a3c4; WORD $0x1e04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r11], 10 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + r10], 11 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + r8], 12 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + rdx], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + r14], 1 + LONG $0x244c8948; BYTE $0x60 // mov qword [rsp + 96], rcx + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + LONG $0x207923c4; WORD $0x2f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r13], 1 + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r14], 4 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r12], 6 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rsi], 7 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r15], 8 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r11], 9 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r10], 10 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + r9], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rdx], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r14], 1 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r12], 2 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r8], 3 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r9], 4 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r10], 2 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - LONG $0x2061a3c4; WORD $0x261c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + r12], 3 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + r8], 4 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - LONG $0x2061a3c4; WORD $0x1e1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + r11], 5 - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r9], 6 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + r15], 7 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r10], 6 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r15], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rdx], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + rbx], 10 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rdx], 12 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rdx], 13 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + rdx], 14 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rdx], 15 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x010116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 1 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - QUAD $0x020116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 2 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x030116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 3 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x040116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 4 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x050116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 5 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x060116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 6 - QUAD $0x07012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 7 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x08012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 8 + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rbx], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rsi], 14 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rsi], 15 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x010137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 1 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x02012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x030137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 3 LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x09012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 9 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x0a0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 10 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0b0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 12 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x0d0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 13 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0e0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 14 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0f0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 15 - QUAD $0x0101366c2029a3c4 // vpinsrb xmm5, xmm10, byte [rsi + r14 + 1], 1 - QUAD $0x0201166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 1], 2 - QUAD $0x0301266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 1], 3 - QUAD $0x0401066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 4 - QUAD $0x05011e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 1], 5 - QUAD $0x06010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 6 - QUAD $0x07013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 7 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0a011e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 1], 10 - QUAD $0x0b010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 12 + QUAD $0x04012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 4 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x050137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 5 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x07012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 7 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x080137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 8 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x090137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 10 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0b0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 11 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0c0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 13 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0e0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 14 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0f0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 15 + QUAD $0x0101376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x0201276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 2 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x0301076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 3 + QUAD $0x04010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x0601176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 6 + QUAD $0x07013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 7 + QUAD $0x0801176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + QUAD $0x0a011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 10 + QUAD $0x0b010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 14 - LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0106442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 1], 15 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 + LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xca6e79c5 // vmovd xmm9, edx LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xd26e79c5 // vmovd xmm10, edx + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x010206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 2], 1 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x02020e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 2], 2 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x030216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 2], 3 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x040206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 4 + QUAD $0x010207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 1 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x02020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 2 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x050206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 5 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x06020e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 2], 6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x070216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 2], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x080206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 8 - WORD $0x894d; BYTE $0xec // mov r12, r13 - QUAD $0x09022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 9 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x0a022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 10 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0b021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 11 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x0c0236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 2], 12 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x0d023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 13 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0e0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 15 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x07022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 7 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x08020f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 2], 8 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x090227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 9 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0a022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 10 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x0b021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 11 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x0c0237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 12 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0d023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x02023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x03023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x04023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x05023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 6 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x07023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 7 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x08021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x09021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0a021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 10 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x0b021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 12 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x010306642021a3c4 // vpinsrb xmm4, xmm11, byte [rsi + r8 + 3], 1 - QUAD $0x02030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 2 - QUAD $0x030316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 3 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x04031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 4 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x05030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 5 - QUAD $0x06030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 6 - QUAD $0x070316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 7 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x080316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 8 - QUAD $0x090326642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 3], 9 - QUAD $0x0a032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 10 - QUAD $0x0b031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 11 - QUAD $0x0c0336642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 3], 12 - QUAD $0x0d033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 13 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0e030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 14 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0f031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x02031e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 3], 2 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0303066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 3 + QUAD $0x0102075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 1 + QUAD $0x0202375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0302175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0402175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0502175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0602175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x0702175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 7 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x08021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 8 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0902375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 10 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0b02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0c02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0d02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 13 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0e02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 14 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0f02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 15 + QUAD $0x010307642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r8 + 3], 1 + QUAD $0x02030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x050307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 5 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x060337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 6 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x07030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 7 + QUAD $0x08030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 8 + QUAD $0x090327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 9 + QUAD $0x0a032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 10 + QUAD $0x0b031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 11 + WORD $0x894d; BYTE $0xdc // mov r12, r11 + QUAD $0x0c0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 12 + QUAD $0x0d033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 13 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x0e031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 15 + QUAD $0x0103076c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rax + 3], 1 + WORD $0x8949; BYTE $0xc5 // mov r13, rax LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0403066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 4 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x0503166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 3], 5 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x0603366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 3], 6 - QUAD $0x07033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 7 + QUAD $0x0203076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 2 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0803066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 8 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x09033e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 3], 9 + QUAD $0x0303076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0403076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0503076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0603076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 6 + QUAD $0x0703176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 7 + QUAD $0x08031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 12 + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 14 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0f0326442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 3], 15 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 14 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xc26e79c5 // vmovd xmm8, edx + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0307442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xda6e79c5 // vmovd xmm11, edx + LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x010406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 1 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x020406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x030406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 3 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x04042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 4 - QUAD $0x05040e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 4], 5 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x060406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 6 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x070406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 7 - QUAD $0x080416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x090406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 10 + QUAD $0x010437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 1 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x02043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 2 + QUAD $0x030417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 3 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x040437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 4 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + QUAD $0x050407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 5 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x06041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 6 + QUAD $0x07040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 7 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x08040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 8 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x090407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 9 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 12 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0d0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 13 - QUAD $0x0e040e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 4], 14 - QUAD $0x0f041e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 4], 15 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0104065c2011e3c4 // vpinsrb xmm3, xmm13, byte [rsi + rax + 4], 1 - QUAD $0x02041e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 4], 2 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x03041e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 4], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0404065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 4 - QUAD $0x0504165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 5 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - QUAD $0x0604365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 6 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0704165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 7 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x08040e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 4], 8 - QUAD $0x09043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0a041e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 4], 10 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0b04365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c041e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 4], 12 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0d041e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 4], 13 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x0e043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 14 - QUAD $0x0f04265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 4], 15 - QUAD $0x010506642009a3c4 // vpinsrb xmm4, xmm14, byte [rsi + r8 + 5], 1 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x02053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 2 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x03051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 3 - QUAD $0x04052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 4 - QUAD $0x05050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 5 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x06052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 6 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x07050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 7 - QUAD $0x080516642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 5], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x09050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 9 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0a050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 10 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0b0516642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 5], 11 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0c050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 12 - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - QUAD $0x0d0506642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 5], 13 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0e050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 14 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 15 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x0105266c2049a3c4 // vpinsrb xmm5, xmm6, byte [rsi + r12 + 5], 1 + QUAD $0x0a0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 10 + QUAD $0x0b0427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 13 + QUAD $0x0e041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 14 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0f0427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 15 + QUAD $0x01042f5c2011a3c4 // vpinsrb xmm3, xmm13, byte [rdi + r13 + 4], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0204175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0304175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0404175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0504075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 5 QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0205166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 2 - QUAD $0x03051e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 5], 3 - QUAD $0x0405066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0505066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 5 - QUAD $0x06053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 6 - QUAD $0x0705166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 5], 7 - QUAD $0x08050e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 5], 8 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x09050e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 5], 9 + QUAD $0x0604175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 6 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0804075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0904075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 10 - QUAD $0x0b05366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 11 + QUAD $0x0a04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 10 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x0b041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 11 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0c041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 14 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 12 + QUAD $0x0f04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 15 + QUAD $0x010537642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r14 + 5], 1 + QUAD $0x02053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 2 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x030517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 3 + QUAD $0x040537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 4 + QUAD $0x05050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 5 + WORD $0x8949; BYTE $0xca // mov r10, rcx + QUAD $0x06051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x07053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 7 + QUAD $0x08050f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 5], 8 + QUAD $0x090507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 9 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0a0507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 14 + QUAD $0x0f0527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 15 + QUAD $0x01052f6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r13 + 5], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0205076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0405076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0505076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 5 + QUAD $0x0605176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 6 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x07051f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 5], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0805076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0905076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0b052f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 5], 11 + QUAD $0x0c051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 12 + WORD $0x894d; BYTE $0xdc // mov r12, r11 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 14 - LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0506442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 5], 15 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 + LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0507442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 5], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x0a // movzx edx, byte [rdi + rax + 10] + LONG $0xda6ef9c5 // vmovd xmm3, edx LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x01061e442019a3c4 // vpinsrb xmm0, xmm12, byte [rsi + r11 + 6], 1 - QUAD $0x02063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 2 - QUAD $0x03061e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 6], 3 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x040606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 4 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x0a // movzx edx, byte [rdi + rdx + 10] + LONG $0xe26ef9c5 // vmovd xmm4, edx + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x010637442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rsi + 6], 1 + QUAD $0x020637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x040637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 4 + QUAD $0x050617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 5 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x050606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 5 - QUAD $0x06062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x070616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 6], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x080606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x090606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 9 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0a0636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 6], 10 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x0b0616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 6], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c0606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 12 - QUAD $0x0d0606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 6], 13 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0e063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 14 - QUAD $0x0f060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 15 - QUAD $0x0106266c2041a3c4 // vpinsrb xmm5, xmm7, byte [rsi + r12 + 6], 1 + QUAD $0x060607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 6 + QUAD $0x07063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 7 + QUAD $0x08060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 8 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x090617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 9 + QUAD $0x0a0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 10 + QUAD $0x0b060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 11 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + QUAD $0x0c0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 12 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x0d060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 14 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0f0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 15 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x01060f6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rcx + 6], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0206176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0306176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0406176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0506176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 5 QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x02060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 3 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x04060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x05063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 5 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x06061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 6 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x07060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 7 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x0806266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 6], 8 - QUAD $0x09060e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 6], 9 + QUAD $0x06060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 6 + QUAD $0x07061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 7 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x08061f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 6], 8 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x09061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 9 LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 10 - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x0b060e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 6], 11 - QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] - QUAD $0x0c06066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 6], 12 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0d062e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 6], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 14 + QUAD $0x0a060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 10 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x0b062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 11 + QUAD $0x0c06276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 6], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 13 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 15 - QUAD $0x01071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 1 - QUAD $0x02073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x03070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 3 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x04071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 4 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x05070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 5 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x06070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 6 - QUAD $0x070716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 7 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x080716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x09070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 9 - QUAD $0x0a0736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 10 - QUAD $0x0b0716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 7], 11 - QUAD $0x0c0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 12 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0d0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 13 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0e073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 14 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 15 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 1 + QUAD $0x0e060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 14 + QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] + QUAD $0x0f062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 15 + QUAD $0x010737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 1 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x02072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x030737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 3 + QUAD $0x040737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 4 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x050737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 5 + QUAD $0x060707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 7 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x08070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a0737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 10 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0b0737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 11 + QUAD $0x0c0707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 12 + QUAD $0x0d070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 13 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0e070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 14 + QUAD $0x0f0717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 15 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0107374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 1 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x02070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 2 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x03070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 3 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x04070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 4 + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x02070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 3 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0407164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 4 - QUAD $0x05073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 5 - QUAD $0x06071e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 7], 6 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x07072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 7 - QUAD $0x0807264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 7], 8 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0907164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 9 + QUAD $0x06070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 6 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x07070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 7 + QUAD $0x08071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 8 + QUAD $0x09071f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 7], 9 LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 10 - QUAD $0x0b070e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 7], 11 - QUAD $0x0c07064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 7], 12 + QUAD $0x0a070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 10 + QUAD $0x0b073f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 7], 11 + QUAD $0x0c07274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 12 LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 13 + QUAD $0x0d070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e070e442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rcx + 7], 14 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - LONG $0x0e7cb60f; BYTE $0x0b // movzx edi, byte [rsi + rcx + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f070e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 7], 15 + QUAD $0x0e070f442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rcx + 7], 14 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + LONG $0x0f54b60f; BYTE $0x0b // movzx edx, byte [rdi + rcx + 11] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0f070f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - LONG $0x0e7cb60f; BYTE $0x0b // movzx edi, byte [rsi + rcx + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x01080e442031e3c4 // vpinsrb xmm0, xmm9, byte [rsi + rcx + 8], 1 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - QUAD $0x020806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 8], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x03080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 3 - QUAD $0x04081e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 8], 4 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x05080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 5 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x06080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x070816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 7 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x080836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 8], 8 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x090816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 8], 9 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0a081e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 8], 10 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0b0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 11 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0c0826442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 8], 12 - QUAD $0x0d0806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 13 - QUAD $0x0e083e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 8], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f0806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 15 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0108066c2029e3c4 // vpinsrb xmm5, xmm10, byte [rsi + rax + 8], 1 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x02080e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 8], 2 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0308066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x04083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0508066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 5 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x06083e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 8], 6 - QUAD $0x07082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 7 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0808066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 8 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f54b60f; BYTE $0x0b // movzx edx, byte [rdi + rcx + 11] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x01080f442031e3c4 // vpinsrb xmm0, xmm9, byte [rdi + rcx + 8], 1 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x02082f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 8], 2 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x03080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x040817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 4 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x05082f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 8], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x060817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 6 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + QUAD $0x070807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 7 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x080837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 8], 8 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x090827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 8], 9 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0a081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 10 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x0b080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 11 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x0c0817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 13 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0908066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 9 + QUAD $0x0e0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 15 + QUAD $0x0108376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 8], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0208076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0308076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0408176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0508076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0608076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 6 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0708376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 7 + QUAD $0x08081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0908076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a08066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 10 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0b08066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0c08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 12 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0d08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 13 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0e08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 14 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0f08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 15 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x01092e742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r13 + 9], 1 - QUAD $0x020906742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r8 + 9], 2 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x030916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 3 - QUAD $0x04091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 4 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x050916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 5 - QUAD $0x06090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 6 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x07090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 7 - QUAD $0x080936742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r14 + 9], 8 - QUAD $0x090916742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r10 + 9], 9 - QUAD $0x0a091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 10 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0b090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 11 - QUAD $0x0c0926742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r12 + 9], 12 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x0d090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 13 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0e090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 14 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0f092e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r13 + 9], 15 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01090e7c2021e3c4 // vpinsrb xmm7, xmm11, byte [rsi + rcx + 9], 1 - QUAD $0x02090e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 9], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03090e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 9], 3 - QUAD $0x04093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 4 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x05091e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r11 + 9], 5 - QUAD $0x06093e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 9], 6 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x07091e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 9], 7 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x08090e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 9], 8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x09090e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 9], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a090e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 9], 10 - QUAD $0x0b09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 12 + QUAD $0x0a08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 13 + QUAD $0x0d08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 14 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x010907742039e3c4 // vpinsrb xmm6, xmm8, byte [rdi + rax + 9], 1 + QUAD $0x02093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 2 + QUAD $0x03090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 4 + QUAD $0x05092f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 9], 5 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x060907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 6 + QUAD $0x070907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 7 + QUAD $0x080937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 8 + QUAD $0x090927742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 9], 9 + QUAD $0x0a091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 10 + QUAD $0x0b090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 11 + QUAD $0x0c0917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 12 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0d0917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 14 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 14 + QUAD $0x0f0907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0109077c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rax + 9], 1 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x02092f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 9], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0309077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 3 + QUAD $0x0409177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 4 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x05091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0609077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 6 + QUAD $0x0709377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 7 + QUAD $0x08091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 8 + WORD $0x894d; BYTE $0xde // mov r14, r11 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f09076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 9], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x0c // movzx edx, byte [rdi + rax + 12] + LONG $0xc26ef9c5 // vmovd xmm0, edx LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x00044024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm5 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x010a165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 10], 1 - QUAD $0x020a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x030a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 3 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x040a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 4 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x050a265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 10], 5 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x060a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 6 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x070a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 7 - QUAD $0x080a365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 10], 8 - QUAD $0x090a165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 10], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 12 - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - QUAD $0x0d0a165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 10], 13 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0e0a3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 10], 14 - QUAD $0x0f0a2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 10], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x0c // movzx edx, byte [rdi + rax + 12] + LONG $0xea6ef9c5 // vmovd xmm5, edx LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 1 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x020a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x040a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 4 - QUAD $0x050a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 5 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x060a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 6 - QUAD $0x070a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 7 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x080a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 8 + QUAD $0x010a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 1 + QUAD $0x020a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 2 + QUAD $0x030a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 3 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x040a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 4 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x050a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x060a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x070a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 7 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x080a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 8 + QUAD $0x090a275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 10], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 12 + QUAD $0x0d0a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 13 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x090a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0a0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 10 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x0b0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 11 + QUAD $0x0e0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x010a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 1 + QUAD $0x020a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x030a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 3 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x040a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 4 + QUAD $0x050a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 5 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x060a17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 10], 6 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x070a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 7 + QUAD $0x080a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 8 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x090a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 9 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0a0a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 10 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0b0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 12 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x0d0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 13 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0e0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 14 QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 12 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0d0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 14 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0f0a2e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 10], 15 - QUAD $0x010b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 1 - QUAD $0x020b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 2 - QUAD $0x030b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 3 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x040b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 4 - QUAD $0x050b264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 11], 5 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x060b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 6 - QUAD $0x070b0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 11], 7 - WORD $0x894d; BYTE $0xcc // mov r12, r9 - QUAD $0x080b364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 11], 8 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x090b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 9 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x0a0b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 10 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0b0b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 11 + QUAD $0x0f0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x010b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 1 + QUAD $0x020b3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 11], 2 + QUAD $0x030b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 3 + QUAD $0x040b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 4 + QUAD $0x050b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 5 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x060b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 7 + QUAD $0x080b0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 11], 8 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x090b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 13 + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + QUAD $0x0e0b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x010b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 1 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x020b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 2 + QUAD $0x030b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 3 + QUAD $0x040b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x050b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 5 + QUAD $0x060b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 11], 6 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x070b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x080b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 8 + QUAD $0x090b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 9 + QUAD $0x0a0b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 10 QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c0b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 12 - QUAD $0x0d0b164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 11], 13 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x0e0b3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 11], 14 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0f0b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 15 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x010b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 11], 1 - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x020b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 11], 2 - QUAD $0x030b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x040b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x050b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 5 - QUAD $0x060b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 11], 6 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x070b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 11], 7 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x080b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 8 - QUAD $0x090b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 10 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0b0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 13 + QUAD $0x0b0b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c0b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 12 + QUAD $0x0d0b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000420249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm3 - QUAD $0x0e0b1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 11], 14 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x0d // movzx edi, byte [rsi + rax + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 15 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0e0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 14 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x0d // movzx edx, byte [rdi + rdx + 13] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x0f0b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000400248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0d // movzx edi, byte [rsi + rax + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x010c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 1 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x020c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 2 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x030c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 12], 3 - QUAD $0x040c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 4 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x050c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 12], 5 - QUAD $0x060c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 12], 6 - QUAD $0x070c26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 12], 7 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x080c26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 12], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x090c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 11 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0c0c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 12 - QUAD $0x0d0c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 13 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0e0c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 15 - QUAD $0x010c16542051e3c4 // vpinsrb xmm2, xmm5, byte [rsi + rdx + 12], 1 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - QUAD $0x020c36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 12], 2 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x030c1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 12], 3 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x0d // movzx edx, byte [rdi + rdx + 13] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x010c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 1 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x020c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x030c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x040c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 4 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x050c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 5 + QUAD $0x060c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x070c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x080c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 8 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + QUAD $0x090c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 9 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0a0c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 10 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x0b0c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 12], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 13 + QUAD $0x0e0c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 15 + QUAD $0x010c07542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rax + 12], 1 LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x040c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 4 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x050c36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 12], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x060c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 6 - QUAD $0x070c0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 12], 7 + QUAD $0x020c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 2 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x080c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x090c1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 12], 9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0a0c1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 12], 10 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x0b0c1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 12], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c0c1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 12], 12 - LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] - QUAD $0x0d0c0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 12], 13 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x0e0c06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 12], 14 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f0c1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 12], 15 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x010d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 1 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x020d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 2 - QUAD $0x030d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 13], 3 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x040d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 4 - QUAD $0x050d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 13], 5 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x060d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 13], 6 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x070d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 7 - QUAD $0x080d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 13], 8 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x090d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 13], 9 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0a0d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b0d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 11 - QUAD $0x0c0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 12 - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - QUAD $0x0d0d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 13], 13 - QUAD $0x0e0d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 13], 14 + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x040c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 4 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x050c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x060c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 6 + QUAD $0x070c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x080c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 8 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x090c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 9 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0a0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 12 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x0d0c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 13 + QUAD $0x0e0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 14 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 15 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x010d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 13], 1 + QUAD $0x020d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 2 + QUAD $0x030d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 4 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x050d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 5 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x060d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 6 + QUAD $0x070d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 7 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x080d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 13], 8 + QUAD $0x090d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 9 + QUAD $0x0a0d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 10 + QUAD $0x0b0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 11 LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 15 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x010d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 1 - QUAD $0x020d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 2 - QUAD $0x030d1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 13], 3 - QUAD $0x040d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 4 - QUAD $0x050d364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 13], 5 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x060d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 6 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x070d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 7 - QUAD $0x080d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 8 + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 13 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x090d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 10 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0b0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 12 - QUAD $0x0d0d0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 13], 13 - QUAD $0x0e0d064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 13], 14 + QUAD $0x0e0d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 15 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x010d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 1 + QUAD $0x020d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 2 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x030d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 3 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x040d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 4 + QUAD $0x050d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 5 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x060d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x070d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x080d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 8 + QUAD $0x090d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 9 + QUAD $0x0a0d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 12 + QUAD $0x0d0d3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 13], 13 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0e0d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0d06442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rax + 13], 15 - QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x0e2e // movzx edi, byte [rsi + r13 + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f0d07442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x0e // movzx edx, byte [rdi + rax + 14] + LONG $0xca6ef9c5 // vmovd xmm1, edx LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0e // movzx edi, byte [rsi + rax + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x010e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 1 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - QUAD $0x020e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x030e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 3 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x040e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 14], 4 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x050e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 14], 5 - QUAD $0x060e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 6 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x0e // movzx edx, byte [rdi + rax + 14] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] + QUAD $0x020e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x040e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 4 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x050e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 14], 5 + QUAD $0x060e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 14], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + QUAD $0x080e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 8 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x090e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 12 + QUAD $0x0d0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x020e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 2 + QUAD $0x030e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 3 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x040e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 4 + QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] + QUAD $0x050e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 14], 5 + QUAD $0x060e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 6 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x070e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 7 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x080e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 8 QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x070e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x080e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 8 - QUAD $0x090e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 14], 9 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0a0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 10 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0b0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c0e3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 14], 12 - QUAD $0x0d0e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 14], 13 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0e0e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 14], 14 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0f0e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 14], 15 + QUAD $0x090e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0b0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c0e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 12 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0d0e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 13 + QUAD $0x0e0e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 14 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0f0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 15 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + LONG $0x54b60f42; WORD $0x0f37 // movzx edx, byte [rdi + r14 + 15] + LONG $0xd26ef9c5 // vmovd xmm2, edx LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x010e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 14], 1 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x020e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 2 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x030e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 14], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x040e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 4 - QUAD $0x050e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 14], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x060e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 6 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x070e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 14], 7 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x080e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 8 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x090e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 14], 9 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0a0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 10 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0b0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 15 - LONG $0x7cb60f42; WORD $0x0f2e // movzx edi, byte [rsi + r13 + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x010f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 1 - QUAD $0x020f1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 15], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x030f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 3 - QUAD $0x040f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 4 - QUAD $0x050f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 5 - QUAD $0x060f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 6 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x070f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 7 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - QUAD $0x080f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x090f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 9 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0a0f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 10 - QUAD $0x0b0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 12 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0d0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 13 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0e0f2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 15], 14 - QUAD $0x0f0f0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 15], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0f // movzx edi, byte [rsi + rax + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x010f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 1 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x020f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 2 - QUAD $0x030f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x040f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 4 + QUAD $0x010f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 1 + QUAD $0x020f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x030f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 3 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x040f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 4 + QUAD $0x050f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 5 + QUAD $0x060f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x070f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x080f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 8 + QUAD $0x090f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 9 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x0a0f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x0f // movzx edx, byte [rdi + rax + 15] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x010f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 1 + QUAD $0x020f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x030f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 3 QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x050f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x060f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 6 - QUAD $0x070f165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 15], 7 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x080f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 8 - QUAD $0x090f365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 15], 9 + QUAD $0x040f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 4 + QUAD $0x050f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x060f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x070f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 7 + QUAD $0x080f1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 15], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x090f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 10 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0b0f365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 15], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d0f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 13 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0e0f1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 15], 14 - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0f0f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 15 + QUAD $0x0a0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 10 + QUAD $0x0b0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0d0f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 14 + QUAD $0x0f0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x1016 // movzx edi, byte [rsi + r10 + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x01100e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 16], 1 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x02100e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 16], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x03100e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 16], 3 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x04100e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 16], 4 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x05100e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 16], 5 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x06100e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 16], 6 - QUAD $0x07103e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 16], 7 - QUAD $0x081006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x09100e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 16], 9 - QUAD $0x0a101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 10 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 12 - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - QUAD $0x0d1006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 13 - QUAD $0x0e102e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 16], 14 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0f103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 15 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - LONG $0x1e7cb60f; BYTE $0x10 // movzx edi, byte [rsi + rbx + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x01103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 1 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x02103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x03103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 3 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x04102e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 16], 4 - QUAD $0x0510164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 5 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x0610164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 6 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x0710164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 7 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0810164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 8 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0910164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 9 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0a10164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 10 - QUAD $0x0b10364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 16], 11 - QUAD $0x0c10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 12 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0d103e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 16], 13 - QUAD $0x0e101e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 16], 14 - QUAD $0x0f10264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 15 - LONG $0x7cb60f42; WORD $0x1116 // movzx edi, byte [rsi + r10 + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x011106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 1 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - QUAD $0x021116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 2 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x031116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 3 - QUAD $0x04110e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 17], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x051106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 5 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x06111e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 17], 6 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x071106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 7 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x081136542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 17], 8 - QUAD $0x09110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 9 + LONG $0x54b60f42; WORD $0x1037 // movzx edx, byte [rdi + r14 + 16] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x01100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 1 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 3 + QUAD $0x041017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 4 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a1106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b1106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 11 + QUAD $0x051007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 5 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x061007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 6 + QUAD $0x07103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 7 + QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] + QUAD $0x08101f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 16], 8 + QUAD $0x09102f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 16], 9 + QUAD $0x0a1027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 13 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0e1037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 14 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0f1007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 15 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + LONG $0x1f54b60f; BYTE $0x10 // movzx edx, byte [rdi + rbx + 16] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x0110174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 16], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0210174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 2 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0310374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0410174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 4 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x05103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0610174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 6 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x07100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 7 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x08102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 8 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0910174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 10 QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0c1126542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 17], 12 - QUAD $0x0d1106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 13 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0e110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 14 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 15 - LONG $0x1e7cb60f; BYTE $0x11 // movzx edi, byte [rsi + rbx + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 1 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x02110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 2 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x0311065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 17], 3 - QUAD $0x04112e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 17], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x05113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 6 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x07113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 7 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x08113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x09113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 9 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0a110e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 17], 10 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0b113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 12 - QUAD $0x0d113e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 17], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 14 + QUAD $0x0b10274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 13 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0e10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x11 // movzx edx, byte [rdi + rdx + 17] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 1 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x02110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 2 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x03110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 3 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x05110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 5 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x06110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x07110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 7 + QUAD $0x08111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x09110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 11 + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 13 + QUAD $0x0e1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 14 + QUAD $0x0f1107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 15 + LONG $0x1f54b60f; BYTE $0x11 // movzx edx, byte [rdi + rbx + 17] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x0111175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0211075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 2 + QUAD $0x0311375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0411375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 4 + QUAD $0x05113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 5 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x06113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 6 + QUAD $0x07110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 7 + QUAD $0x08112f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 17], 8 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0911075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 10 + QUAD $0x0b11275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 11 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x0c110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f113e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rdi + 17], 15 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f1107442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - LONG $0x3e7cb60f; BYTE $0x12 // movzx edi, byte [rsi + rdi + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x01123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 1 - QUAD $0x021216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 2 - QUAD $0x031216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 3 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x04123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 4 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x05123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 5 - QUAD $0x06121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x071216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 7 - QUAD $0x081236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 18], 8 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x091216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 9 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x0a1216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 10 - QUAD $0x0b1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 11 - QUAD $0x0c1226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 18], 12 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0d1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 13 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0e1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 15 - LONG $0x1e7cb60f; BYTE $0x12 // movzx edi, byte [rsi + rbx + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x01122e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 18], 1 - QUAD $0x02120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 2 - QUAD $0x0312064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 18], 3 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0412164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 18], 4 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x0512364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 18], 5 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + LONG $0x1f54b60f; BYTE $0x12 // movzx edx, byte [rdi + rbx + 18] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x021237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 2 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x031217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x041207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 4 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x05121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 5 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 7 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x081207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 8 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0612064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 6 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x07121e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 18], 7 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x08120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0912064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 9 - QUAD $0x0a120e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 18], 10 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0b123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 15 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - LONG $0x3e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rdi + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x01133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 1 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - QUAD $0x021326542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 19], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x03133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 3 - QUAD $0x04133e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 19], 4 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x05133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 5 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x06133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 6 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x07133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x09133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 9 - QUAD $0x0a1316542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 19], 10 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 12 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x0d133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 13 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0e130e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 19], 14 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0f1306542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 19], 15 - LONG $0x1e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rbx + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01132e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 19], 1 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0213165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 2 + QUAD $0x091207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 13 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0e1227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 14 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0f122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x12 // movzx edx, byte [rdi + rdx + 18] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0112174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0212174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0312174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 3 + QUAD $0x0412374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0512174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 5 + QUAD $0x06123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 6 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x07123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 7 QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0313165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 3 - QUAD $0x0413165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 19], 4 - QUAD $0x0513365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 19], 5 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x06131e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 19], 6 - QUAD $0x07131e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 19], 7 - QUAD $0x08130e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 19], 8 - QUAD $0x0913065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 9 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x0a131e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 19], 10 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0b13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 11 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0c132e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 19], 12 + QUAD $0x0812174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 8 + QUAD $0x0912074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 9 + QUAD $0x0a120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0b120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 11 + QUAD $0x0c120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 13 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0e120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 14 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0f120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 15 + LONG $0x1f54b60f; BYTE $0x13 // movzx edx, byte [rdi + rbx + 19] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x01130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 1 + QUAD $0x021337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 2 + QUAD $0x031317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 3 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x04130f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 19], 4 + QUAD $0x05131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 5 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x06130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 6 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x071307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 7 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x081337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 8 + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + QUAD $0x091317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 10 + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 13 + QUAD $0x0e1327542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 19], 14 + QUAD $0x0f132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0754b60f; BYTE $0x13 // movzx edx, byte [rdi + rax + 19] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x01131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0313075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 3 + QUAD $0x0413375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0613375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 6 + QUAD $0x07133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0813075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 8 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0913075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0b13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 14 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - QUAD $0x0f13365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 19], 15 + QUAD $0x0d13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x143e // movzx edi, byte [rsi + r15 + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x01140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 1 - QUAD $0x021426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x031406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 3 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x041426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 4 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x051416442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 20], 5 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x061406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 6 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x071406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 12 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0d1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 13 - QUAD $0x0e140e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 20], 14 - QUAD $0x0f1406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 20], 15 + LONG $0x0754b60f; BYTE $0x14 // movzx edx, byte [rdi + rax + 20] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x011427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 1 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x14 // movzx edi, byte [rsi + rax + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0114064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 20], 1 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x0214064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 20], 2 - QUAD $0x0314164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 20], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0414064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 20], 4 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0514164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 20], 5 - QUAD $0x06141e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 20], 6 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x0714164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 20], 7 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0814164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 20], 8 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0914164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 20], 9 - QUAD $0x0a141e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 20], 10 + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 3 + QUAD $0x04140f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 20], 4 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x06140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 6 + QUAD $0x071407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 7 + QUAD $0x081437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 8 + QUAD $0x091417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 11 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x0c142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 12 + QUAD $0x0d141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 13 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0e141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 15 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + LONG $0x54b60f42; WORD $0x140f // movzx edx, byte [rdi + r9 + 20] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 1 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x0214074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 2 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x03143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 3 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x04140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 4 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x05140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 5 + QUAD $0x0614374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 6 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x0714174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0814174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 8 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0914174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 9 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x0a14174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0d14374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 13 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0e14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 14 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0f14374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 20], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x15 // movzx edx, byte [rdi + rdx + 21] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x011527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 2 QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x0b141e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 20], 11 - QUAD $0x0c142e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 20], 12 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0d142e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 20], 13 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x0e140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 14 - QUAD $0x0f14364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 20], 15 - LONG $0x7cb60f42; WORD $0x153e // movzx edi, byte [rsi + r15 + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x01150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 1 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x02150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x03150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 3 - QUAD $0x041526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 4 - QUAD $0x051516542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 21], 5 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x061516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 6 + QUAD $0x03151f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 21], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x041517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 4 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x051517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x081517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 8 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x091517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 9 + QUAD $0x0a1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 10 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0b1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 11 + QUAD $0x0c152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 13 + QUAD $0x0e151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 14 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0f152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 15 + LONG $0x54b60f42; WORD $0x150f // movzx edx, byte [rdi + r9 + 21] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0115075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 1 + QUAD $0x0215075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 2 + QUAD $0x03153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 3 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x04150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 4 + QUAD $0x05150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 5 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0715075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x071526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x08150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 8 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x091516542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 21], 9 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0a153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 10 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0b1536542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 21], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 12 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - QUAD $0x0d151e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 21], 13 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0e153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 14 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0f153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 15 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x3e7cb60f; BYTE $0x15 // movzx edi, byte [rsi + rdi + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x01153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 1 - QUAD $0x0215065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 21], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x03153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 3 - QUAD $0x0415065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0515065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 5 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x0615065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 21], 6 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - QUAD $0x07153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 7 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0815065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0915065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a15065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 10 - QUAD $0x0b151e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 21], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c15065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 12 - QUAD $0x0d152e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 21], 13 - QUAD $0x0e150e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 21], 14 + QUAD $0x0915275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 21], 9 + QUAD $0x0a15175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 10 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0b151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0c150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 12 + QUAD $0x0d15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 13 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0e150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1506442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rax + 21], 15 + QUAD $0x0f1537442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r14 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x16 // movzx edi, byte [rsi + rax + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x01163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 1 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x02163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x03163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 3 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x04163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 4 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x05162e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 22], 5 - QUAD $0x061616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 6 - QUAD $0x071626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 22], 7 - QUAD $0x08160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 8 - QUAD $0x091616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 22], 9 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x0a1626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 22], 10 - QUAD $0x0b1636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 22], 11 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0c161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 12 - QUAD $0x0d161e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 22], 13 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0e160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 14 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 15 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - LONG $0x1e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rbx + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0116164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 1 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x02160e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 22], 2 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0316164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 3 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0416164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 4 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0516164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 5 - QUAD $0x0616064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 22], 6 - QUAD $0x07163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 7 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0816164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 8 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0916364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 22], 9 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0a16164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 10 - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x0b160e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 22], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0c16164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 12 + QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + LONG $0x54b60f42; WORD $0x1617 // movzx edx, byte [rdi + r10 + 22] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x01163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 1 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x021607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 2 + QUAD $0x03161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 3 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x04160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 4 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x05160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 5 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x061637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 6 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x07161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 7 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x081637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x09160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 10 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0b160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 14 + QUAD $0x0f162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x16 // movzx edx, byte [rdi + rdx + 22] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0116174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0216174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0316174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 3 + QUAD $0x04160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 4 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x05162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0616174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 6 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x07160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 7 + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + QUAD $0x0916274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 10 + QUAD $0x0b161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 11 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x0c16274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0e16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 14 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0f16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 15 + LONG $0x54b60f42; WORD $0x1717 // movzx edx, byte [rdi + r10 + 23] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 1 + QUAD $0x021707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 23], 2 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x031717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x041707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 4 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x051707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 5 + QUAD $0x061737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 6 + QUAD $0x07171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 7 + QUAD $0x081737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 8 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x091737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 10 + QUAD $0x0b170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 13 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x0e171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 15 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + LONG $0x54b60f42; WORD $0x173f // movzx edx, byte [rdi + r15 + 23] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x01170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0317175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0417175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 4 + QUAD $0x05172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 5 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x06172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 6 + QUAD $0x07170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0817175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 8 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0917075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 11 + QUAD $0x0c17275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 12 LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0d16164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 13 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x0e163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 14 + QUAD $0x0d17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 13 QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0f16164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 22], 15 - LONG $0x067cb60f; BYTE $0x17 // movzx edi, byte [rsi + rax + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x011706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 1 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x021706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 2 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x031716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 3 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x041706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 4 - QUAD $0x05172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 5 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x06173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 6 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x07173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x09173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 9 - QUAD $0x0a1726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 23], 10 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 11 - QUAD $0x0c171e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 23], 12 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x0d173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 13 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0e173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 14 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0f172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 15 - LONG $0x1e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rbx + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0117165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 23], 1 - QUAD $0x02170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 3 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x04171e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 23], 4 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x0517165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 23], 5 - QUAD $0x0617065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 23], 6 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x07173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 7 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x0817065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 23], 8 - QUAD $0x0917365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 23], 9 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x0a17265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 10 - QUAD $0x0b170e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 23], 11 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - QUAD $0x0c171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 12 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x0d17365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 23], 13 - QUAD $0x0e173e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 23], 14 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x0f170e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 23], 15 + QUAD $0x0e17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - LONG $0x3e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rdi + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x01183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 1 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x02183e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 24], 2 - QUAD $0x031816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 24], 3 - QUAD $0x041806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x051806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 5 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x061806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x071816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 24], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a1806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b1806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c1806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 12 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0d1806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 13 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0e1806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 14 - QUAD $0x0f182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x18 // movzx edi, byte [rsi + rax + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0118064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 1 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0218064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 2 - QUAD $0x03180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 3 - QUAD $0x04181e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 24], 4 - QUAD $0x0518164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 24], 5 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x0618164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 24], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0718064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 7 - QUAD $0x0818064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 24], 8 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x09182e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 24], 9 - QUAD $0x0a18264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 10 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x0b18264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 11 - QUAD $0x0c181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 12 - QUAD $0x0d18364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 24], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 14 - QUAD $0x0f180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 15 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x1906 // movzx edi, byte [rsi + r8 + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x01190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 1 - QUAD $0x02193e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 25], 2 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x18 // movzx edx, byte [rdi + rdx + 24] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x011817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 2 + QUAD $0x031817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 3 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x041817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 4 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x051817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x081817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 8 + QUAD $0x091837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 9 + QUAD $0x0a1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 10 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0b1837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 12 + QUAD $0x0d181f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 24], 13 + QUAD $0x0e181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 15 + LONG $0x54b60f42; WORD $0x183f // movzx edx, byte [rdi + r15 + 24] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 1 + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0318074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 3 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x0418274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0518074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 5 + QUAD $0x06182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 6 + QUAD $0x07180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 7 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x08183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 8 + QUAD $0x0918074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 10 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0b18074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 11 LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x03190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 3 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x04193e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 25], 4 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x05190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 5 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x06190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 6 - QUAD $0x071916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 7 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x08190e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 25], 8 + QUAD $0x0c180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 12 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x0d18174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 13 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0e18374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 14 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0f181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x19 // movzx edx, byte [rdi + rax + 25] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x01192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 3 LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x091916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 9 + QUAD $0x041917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 4 QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x0a191e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 25], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b191e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 25], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c1916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 12 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x0d1936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 13 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0e1916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 14 + QUAD $0x05191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 7 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x081917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 8 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x091917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 10 + QUAD $0x0b1937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 11 LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0f1916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 15 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - LONG $0x167cb60f; BYTE $0x19 // movzx edi, byte [rsi + rdx + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0119165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 1 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x02193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x03193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x04193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x05193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 5 - QUAD $0x0619165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 25], 6 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x07193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 7 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x08193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 8 - QUAD $0x09192e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 25], 9 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0a192e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 25], 10 - QUAD $0x0b19265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 12 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0d19165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 25], 13 - QUAD $0x0e19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 14 + QUAD $0x0c1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1754b60f; BYTE $0x19 // movzx edx, byte [rdi + rdx + 25] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0119175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0219175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 2 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0319175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 3 + QUAD $0x0419275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0519175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0619175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 6 + QUAD $0x07190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 7 + QUAD $0x08193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 8 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x09193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 9 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x0a190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 10 + QUAD $0x0b19075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 25], 11 + QUAD $0x0c190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 12 + QUAD $0x0d19175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 25], 13 + QUAD $0x0e19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 14 LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f193e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rdi + 25], 15 + QUAD $0x0f191f442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rbx + 25], 15 LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 - LONG $0x7cb60f42; WORD $0x1a06 // movzx edi, byte [rsi + r8 + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x011a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 1 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x021a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x031a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 3 - QUAD $0x041a3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 26], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x051a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 5 - QUAD $0x061a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 6 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x071a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 7 - QUAD $0x081a0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 26], 8 + LONG $0x0754b60f; BYTE $0x1a // movzx edx, byte [rdi + rax + 26] + LONG $0xc26ef9c5 // vmovd xmm0, edx + QUAD $0x011a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 1 + QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] + QUAD $0x021a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 3 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 9 - QUAD $0x0a1a1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 26], 10 - QUAD $0x0b1a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 11 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0c1a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 12 - QUAD $0x0d1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 13 - WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x041a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 4 + QUAD $0x051a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 5 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x061a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x071a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 7 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x081a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 8 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x091a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 10 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0b1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f1a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3754b60f; BYTE $0x1a // movzx edx, byte [rdi + rsi + 26] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x011a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 1 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x021a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 2 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x031a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 3 + QUAD $0x041a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 4 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x051a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 5 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x061a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 6 + QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] + QUAD $0x071a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x081a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 8 + QUAD $0x091a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 9 + QUAD $0x0a1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 13 + QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] + QUAD $0x0e1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x1b // movzx edx, byte [rdi + rdx + 27] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x011b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 1 + QUAD $0x021b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 2 + WORD $0x894d; BYTE $0xd5 // mov r13, r10 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 3 + QUAD $0x041b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 4 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x051b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 5 + QUAD $0x061b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + QUAD $0x081b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 8 + QUAD $0x091b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 10 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0b1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 11 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0c1b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0e1a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f1a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 15 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x1a26 // movzx edi, byte [rsi + r12 + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 1 - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x021a364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 26], 2 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x031a3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 26], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x041a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x061a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x071a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 7 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x081a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 8 + QUAD $0x0d1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 13 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x091a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 9 - QUAD $0x0a1a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 10 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x0b1a1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 26], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 12 - QUAD $0x0d1a164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 26], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 14 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0f1a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 15 - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - LONG $0x167cb60f; BYTE $0x1b // movzx edi, byte [rsi + rdx + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 1 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - QUAD $0x021b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 2 + QUAD $0x0e1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 14 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x0f1b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 15 + LONG $0x3754b60f; BYTE $0x1b // movzx edx, byte [rdi + rsi + 27] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x011b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 1 + QUAD $0x021b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 2 + QUAD $0x031b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 3 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x041b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 4 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x051b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 5 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x061b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 6 + QUAD $0x071b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x081b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 8 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x091b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 10 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0b1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 11 LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x031b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 3 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x041b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 4 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x051b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 27], 5 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x061b2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 27], 6 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x071b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x081b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x091b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 9 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x0a1b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 27], 10 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b1b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 11 - QUAD $0x0c1b1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 27], 12 - QUAD $0x0d1b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 13 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0e1b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 14 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0f1b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 15 - LONG $0x7cb60f42; WORD $0x1b26 // movzx edi, byte [rsi + r12 + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x011b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 1 - QUAD $0x021b365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 27], 2 - QUAD $0x031b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x041b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x051b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 5 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x061b365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 27], 6 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - QUAD $0x071b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 7 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x081b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x091b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 9 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x0a1b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 10 - QUAD $0x0b1b1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 27], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c1b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d1b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 13 - QUAD $0x0e1b065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 27], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1b065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 27], 15 + QUAD $0x0c1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 13 + QUAD $0x0e1b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x1c // movzx edi, byte [rsi + rax + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x011c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 1 - QUAD $0x021c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 2 - QUAD $0x031c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 3 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x041c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 4 - QUAD $0x051c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 5 - QUAD $0x061c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 28], 6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x071c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 8 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x091c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 9 - QUAD $0x0a1c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 10 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0b1c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 12 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x0d1c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 13 - QUAD $0x0e1c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 14 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f1c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x1c // movzx edi, byte [rsi + rax + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x011c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 1 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x021c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 2 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x031c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x041c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 4 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x051c164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 28], 5 - QUAD $0x061c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 6 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x071c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 7 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x081c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x091c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 9 - QUAD $0x0a1c264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 28], 10 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x0b1c264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 28], 11 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0c1c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d1c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e1c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f1c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 15 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - LONG $0x3e7cb60f; BYTE $0x1d // movzx edi, byte [rsi + rdi + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 1 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x1c // movzx edx, byte [rdi + rdx + 28] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x011c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 1 + QUAD $0x021c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 3 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x041c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 4 + QUAD $0x051c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 6 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x071c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 7 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x081c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 8 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x091c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 10 + QUAD $0x0b1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 11 + QUAD $0x0c1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 12 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0d1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 13 + QUAD $0x0e1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 14 + QUAD $0x0f1c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 15 QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - QUAD $0x021d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x031d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 3 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x041d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 4 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x051d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 5 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x061d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 6 - QUAD $0x071d16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 29], 7 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x081d16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 29], 8 - QUAD $0x091d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 9 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0a1d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 10 - QUAD $0x0b1d06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 29], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c1d16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 29], 12 - QUAD $0x0d1d0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 29], 13 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0e1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 14 - QUAD $0x0f1d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 15 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x1d06 // movzx edi, byte [rsi + r8 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x011d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 1 - QUAD $0x021d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 2 - QUAD $0x031d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 29], 3 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x041d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 29], 4 - QUAD $0x051d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 29], 5 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x061d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 29], 6 - QUAD $0x071d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 7 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x081d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x091d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 9 + LONG $0x54b60f42; WORD $0x1c1f // movzx edx, byte [rdi + r11 + 28] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x011c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x031c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 3 + QUAD $0x041c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 4 + QUAD $0x051c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 5 + QUAD $0x061c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 6 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x071c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 7 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x081c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 8 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x091c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0b1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0c1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 13 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0e1c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 14 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0f1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + LONG $0x1754b60f; BYTE $0x1d // movzx edx, byte [rdi + rdx + 29] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x011d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 1 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x021d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x031d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 3 + QUAD $0x041d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 4 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x051d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 5 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x061d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 6 + QUAD $0x071d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 7 + QUAD $0x081d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 8 + QUAD $0x091d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 10 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + QUAD $0x0b1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 11 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0c1d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 12 + QUAD $0x0d1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 13 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0e1d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 14 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0f1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 15 + LONG $0x54b60f42; WORD $0x1d1f // movzx edx, byte [rdi + r11 + 29] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x011d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 1 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x021d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 2 + QUAD $0x031d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 3 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x041d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 + QUAD $0x061d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 29], 6 + QUAD $0x071d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x081d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 8 + QUAD $0x091d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 9 + WORD $0x8949; BYTE $0xdf // mov r15, rbx LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 10 - QUAD $0x0b1d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 29], 11 - QUAD $0x0c1d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 29], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 13 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x0e1d3e642061a3c4 // vpinsrb xmm4, xmm3, byte [rsi + r15 + 29], 14 + QUAD $0x0a1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 10 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0b1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 11 + QUAD $0x0c1d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d1d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 13 + QUAD $0x0e1d17642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r10 + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1d06442059e3c4 // vpinsrb xmm0, xmm4, byte [rsi + rax + 29], 15 + QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] + QUAD $0x0f1d17442059a3c4 // vpinsrb xmm0, xmm4, byte [rdi + r10 + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x067cb60f; BYTE $0x1e // movzx edi, byte [rsi + rax + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x011e0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 30], 1 - LONG $0x067cb60f; BYTE $0x1f // movzx edi, byte [rsi + rax + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 31], 1 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - QUAD $0x021e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 30], 2 - QUAD $0x021f1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 31], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x031e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 3 - QUAD $0x031f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 3 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x0754b60f; BYTE $0x1e // movzx edx, byte [rdi + rax + 30] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x011e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 30], 1 + LONG $0x0754b60f; BYTE $0x1f // movzx edx, byte [rdi + rax + 31] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x011f1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 31], 1 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + QUAD $0x051e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 5 + QUAD $0x051f0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 31], 5 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x051e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 5 - QUAD $0x051f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 5 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x061e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 6 - QUAD $0x061f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 6 - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x00000110249c8b48 // mov rbx, qword [rsp + 272] QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 - QUAD $0x0a1e1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 30], 10 - QUAD $0x0a1f1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 31], 10 + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 11 - QUAD $0x0b1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 11 - QUAD $0x0c1e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 30], 12 - QUAD $0x0c1f164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 31], 12 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0d1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 13 - QUAD $0x0d1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 13 + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + QUAD $0x0b1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 11 + QUAD $0x0b1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 11 + QUAD $0x0c1e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 30], 12 + QUAD $0x0c1f274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 31], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0e1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 14 - QUAD $0x0e1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 15 - QUAD $0x0f1f06542071e3c4 // vpinsrb xmm2, xmm1, byte [rsi + rax + 31], 15 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - LONG $0x44b60f42; WORD $0x1e06 // movzx eax, byte [rsi + r8 + 30] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x0f1e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 30], 15 + QUAD $0x0f1f37542071a3c4 // vpinsrb xmm2, xmm1, byte [rdi + r14 + 31], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1744b60f; BYTE $0x1e // movzx eax, byte [rdi + rdx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x011e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 30], 1 - LONG $0x44b60f42; WORD $0x1f06 // movzx eax, byte [rsi + r8 + 31] + QUAD $0x011e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 1 + LONG $0x1744b60f; BYTE $0x1f // movzx eax, byte [rdi + rdx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f0e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 31], 1 + QUAD $0x011f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 1 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x041e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 4 + QUAD $0x041f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x021e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 2 - QUAD $0x021f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 2 + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - QUAD $0x041e2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 30], 4 - QUAD $0x041f2e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r13 + 31], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 - QUAD $0x061e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 30], 6 - QUAD $0x061f167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 31], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x071e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 7 - QUAD $0x071f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 7 - QUAD $0x081e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 30], 8 - QUAD $0x081f367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 31], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x091e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 9 - QUAD $0x091f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 9 + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 30], 9 + QUAD $0x091f3f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 31], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 - WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x0b1e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 30], 11 - QUAD $0x0b1f267c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r12 + 31], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 12 - QUAD $0x0c1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 13 - QUAD $0x0d1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 13 - QUAD $0x0e1e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 30], 14 - QUAD $0x0e1f3e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 31], 14 + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0b1e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 11 + QUAD $0x0b1f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x0d1e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 30], 13 + QUAD $0x0d1f0f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 31], 13 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 15 - QUAD $0x0f1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 15 + QUAD $0x0e1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 14 + QUAD $0x0e1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 14 + QUAD $0x0f1e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 15 + QUAD $0x0f1f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -10128,21 +10437,21 @@ LBB1_170: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x7f7ec1c4; WORD $0x8b44; BYTE $0x60 // vmovdqu yword [r11 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8b54; BYTE $0x40 // vmovdqu yword [r11 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8b64; BYTE $0x20 // vmovdqu yword [r11 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8b0c // vmovdqu yword [r11 + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608b // vmovdqu yword [rbx + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408b // vmovdqu yword [rbx + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208b // vmovdqu yword [rbx + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8b // vmovdqu yword [rbx + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB1_170 - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - QUAD $0x0000018024bc3b4c // cmp r15, qword [rsp + 384] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - QUAD $0x0000019024a48b4c // mov r12, qword [rsp + 400] - JNE LBB1_90 - JMP LBB1_130 + JNE LBB1_194 + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + LONG $0x24648b44; BYTE $0x1c // mov r12d, dword [rsp + 28] + QUAD $0x0000019024b48b48 // mov rsi, qword [rsp + 400] + JNE LBB1_153 + JMP LBB1_157 DATA LCDATA2<>+0x000(SB)/8, $0x0101010101010101 DATA LCDATA2<>+0x008(SB)/8, $0x0101010101010101 @@ -10188,83 +10497,96 @@ TEXT ·_comparison_equal_scalar_arr_avx2(SB), $1320-48 MOVQ BP, 1280(SP) LEAQ LCDATA2<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB2_17 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB2_32 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB2_60 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB2_72 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB2_165 - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB2_7: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_7 - LONG $0x01c68349 // add r14, 1 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB2_19 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB2_36 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB2_59 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB2_73 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB2_189 + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_11 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_9 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_8: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_8 LBB2_9: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_13 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 LBB2_11: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_15 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB2_13: QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - QUAD $0x000000a02494940f // sete byte [rsp + 160] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] LONG $0xd2940f41 // sete r10b LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] LONG $0xd6940f41 // sete r14b LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] - QUAD $0x000000882494940f // sete byte [rsp + 136] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] LONG $0xd7940f40 // sete dil LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] LONG $0xd6940f40 // sete sil LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] @@ -10276,33 +10598,33 @@ LBB2_11: LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] LONG $0xd4940f41 // sete r12b LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] LONG $0xd7940f41 // sete r15b LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] @@ -10310,115 +10632,114 @@ LBB2_11: LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd0 // sete al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xdf // or dil, bl LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0844; BYTE $0xf3 // or bl, r14b WORD $0x8941; BYTE $0xda // mov r10d, ebx QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xd3 // or bl, r10b WORD $0xde89 // mov esi, ebx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000009824b4b60f // movzx esi, byte [rsp + 152] + QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xdb00 // add bl, bl - LONG $0x60245c02 // add bl, byte [rsp + 96] + LONG $0x70245c02 // add bl, byte [rsp + 112] WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0x8841; BYTE $0x3e // mov byte [r14], dil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x01468841 // mov byte [r14 + 1], al + LONG $0x014e8841 // mov byte [r14 + 1], cl WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd908 // or cl, bl LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xc108 // or cl, al + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x03468841 // mov byte [r14 + 3], al LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 LONG $0x04c68349 // add r14, 4 QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB2_11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + JNE LBB2_13 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] -LBB2_13: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB2_127 +LBB2_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB2_129 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi -LBB2_16: +LBB2_18: WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al @@ -10447,72 +10768,88 @@ LBB2_16: WORD $0xd830 // xor al, bl LONG $0x36048841 // mov byte [r14 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_16 - JMP LBB2_155 - -LBB2_17: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB2_46 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB2_83 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB2_94 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB2_165 - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_25 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB2_23: - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] + JNE LBB2_18 + JMP LBB2_179 + +LBB2_19: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB2_43 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB2_86 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB2_99 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB2_189 + WORD $0x8b4c; BYTE $0x26 // mov r12, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_29 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_27 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_26: + LONG $0x012ef9c5 // vucomisd xmm0, qword [rcx] + LONG $0x08518d48 // lea rdx, [rcx + 8] WORD $0x9b0f; BYTE $0xd1 // setnp cl WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xcb20 // and bl, cl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_23 - LONG $0x01c68349 // add r14, 1 - -LBB2_25: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_29 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000c0249c894c // mov qword [rsp + 192], r11 - QUAD $0x000000b8249c894c // mov qword [rsp + 184], r11 + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_26 LBB2_27: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 + +LBB2_29: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_33 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b824a4894c // mov qword [rsp + 184], r12 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + +LBB2_31: QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd5940f41 // sete r13b @@ -10521,7 +10858,7 @@ LBB2_27: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x422ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rdx + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -10531,7 +10868,7 @@ LBB2_27: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x58244c88 // mov byte [rsp + 88], cl LONG $0x422ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rdx + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd4940f41 // sete r12b @@ -10540,7 +10877,7 @@ LBB2_27: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x422ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rdx + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -10550,17 +10887,17 @@ LBB2_27: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x422ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rdx + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x422ef9c5; BYTE $0x50 // vucomisd xmm0, qword [rdx + 80] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x422ef9c5; BYTE $0x58 // vucomisd xmm0, qword [rdx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd3 // sete bl @@ -10574,72 +10911,72 @@ LBB2_27: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x422ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rdx + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl LONG $0x422ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rdx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl QUAD $0x00000080822ef9c5 // vucomisd xmm0, qword [rdx + 128] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl QUAD $0x00000088822ef9c5 // vucomisd xmm0, qword [rdx + 136] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl QUAD $0x00000090822ef9c5 // vucomisd xmm0, qword [rdx + 144] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl QUAD $0x00000098822ef9c5 // vucomisd xmm0, qword [rdx + 152] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl QUAD $0x000000a0822ef9c5 // vucomisd xmm0, qword [rdx + 160] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl QUAD $0x000000a8822ef9c5 // vucomisd xmm0, qword [rdx + 168] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl QUAD $0x000000b0822ef9c5 // vucomisd xmm0, qword [rdx + 176] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd7940f41 // sete r15b WORD $0x2041; BYTE $0xc7 // and r15b, al QUAD $0x000000b8822ef9c5 // vucomisd xmm0, qword [rdx + 184] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd0940f41 // sete r8b - WORD $0x2041; BYTE $0xc0 // and r8b, al + LONG $0xd2940f41 // sete r10b + WORD $0x2041; BYTE $0xc2 // and r10b, al QUAD $0x000000c0822ef9c5 // vucomisd xmm0, qword [rdx + 192] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl QUAD $0x000000c8822ef9c5 // vucomisd xmm0, qword [rdx + 200] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd3940f41 // sete r11b WORD $0x2041; BYTE $0xc3 // and r11b, al QUAD $0x000000d0822ef9c5 // vucomisd xmm0, qword [rdx + 208] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd2940f41 // sete r10b - WORD $0x2041; BYTE $0xc2 // and r10b, al - QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] - WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd1940f41 // sete r9b WORD $0x2041; BYTE $0xc1 // and r9b, al + QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] + WORD $0x9b0f; BYTE $0xd0 // setnp al + LONG $0xd0940f41 // sete r8b + WORD $0x2041; BYTE $0xc0 // and r8b, al QUAD $0x000000e0822ef9c5 // vucomisd xmm0, qword [rdx + 224] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -10659,23 +10996,23 @@ LBB2_27: LONG $0xd6940f40 // sete sil WORD $0x2040; BYTE $0xc6 // and sil, al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x38 // add r13b, byte [rsp + 56] + LONG $0x246c0244; BYTE $0x48 // add r13b, byte [rsp + 72] WORD $0x8944; BYTE $0xe8 // mov eax, r13d LONG $0x05e4c041 // shl r12b, 5 - QUAD $0x00008024acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 128] + LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] LONG $0x06e5c041 // shl r13b, 6 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] + LONG $0x64b60f44; WORD $0x5024 // movzx r12d, byte [rsp + 80] LONG $0x02e4c041 // shl r12b, 2 WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] WORD $0xc900 // add cl, cl - LONG $0x30244c02 // add cl, byte [rsp + 48] + LONG $0x40244c02 // add cl, byte [rsp + 64] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -10684,57 +11021,57 @@ LBB2_27: WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xcb08 // or bl, cl - LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] + LONG $0x6cb60f44; WORD $0x5824 // movzx r13d, byte [rsp + 88] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x74b60f44; WORD $0x5024 // movzx r14d, byte [rsp + 80] + LONG $0x74b60f44; WORD $0x6024 // movzx r14d, byte [rsp + 96] LONG $0x07e6c041 // shl r14b, 7 WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] WORD $0xc900 // add cl, cl - LONG $0x68244c02 // add cl, byte [rsp + 104] - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + LONG $0x20244c02 // add cl, byte [rsp + 32] + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xcb08 // or bl, cl - QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd908 // or cl, bl WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd908 // or cl, bl WORD $0x8941; BYTE $0xcc // mov r12d, ecx QUAD $0x00000110248c8b48 // mov rcx, qword [rsp + 272] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0x0844; BYTE $0xe8 // or al, r13b - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e7c041 // shl r15b, 6 WORD $0x0841; BYTE $0xdf // or r15b, bl QUAD $0x0000012024b40a44 // or r14b, byte [rsp + 288] - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf8 // or r8b, r15b - WORD $0x0845; BYTE $0xe0 // or r8b, r12b + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0845; BYTE $0xfa // or r10b, r15b + WORD $0x0845; BYTE $0xe2 // or r10b, r12b WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000a0249c0244 // add r11b, byte [rsp + 160] - LONG $0x02e2c041 // shl r10b, 2 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xd1 // or r9b, r10b + QUAD $0x00000098249c0244 // add r11b, byte [rsp + 152] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0845; BYTE $0xc8 // or r8b, r9b QUAD $0x000000a8249cb60f // movzx ebx, byte [rsp + 168] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x8941; BYTE $0xd9 // mov r9d, ebx + WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x8941; BYTE $0xd8 // mov r8d, ebx WORD $0x0188 // mov byte [rcx], al QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 @@ -10743,359 +11080,162 @@ LBB2_27: LONG $0x01718844 // mov byte [rcx + 1], r14b LONG $0x07e6c040 // shl sil, 7 WORD $0x0840; BYTE $0xfe // or sil, dil - WORD $0x0844; BYTE $0xce // or sil, r9b - LONG $0x02418844 // mov byte [rcx + 2], r8b + WORD $0x0844; BYTE $0xc6 // or sil, r8b + LONG $0x02518844 // mov byte [rcx + 2], r10b LONG $0x03718840 // mov byte [rcx + 3], sil LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 LONG $0x04c18348 // add rcx, 4 WORD $0x8949; BYTE $0xce // mov r14, rcx - QUAD $0x000000b824848348; BYTE $0xff // add qword [rsp + 184], -1 - JNE LBB2_27 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - -LBB2_29: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB2_136 - WORD $0xff31 // xor edi, edi - JMP LBB2_138 + QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 + JNE LBB2_31 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] -LBB2_32: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB2_105 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB2_165 - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_38 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB2_33: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_160 + WORD $0xff31 // xor edi, edi + JMP LBB2_162 LBB2_36: - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB2_112 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB2_189 + WORD $0x8a44; BYTE $0x26 // mov r12b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_130 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_132 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB2_41: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x22 // cmp r12b, byte [rdx] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB2_41 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB2_133 + JMP LBB2_189 + +LBB2_43: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB2_117 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB2_189 + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_49 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_48: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 WORD $0x894d; BYTE $0xf4 // mov r12, r14 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_36 - LONG $0x01c68349 // add r14, 1 - -LBB2_38: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_128 - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x245c8944; BYTE $0x1c // mov dword [rsp + 28], r11d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000018824bc894c // mov qword [rsp + 392], r15 - JB LBB2_42 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB2_166 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB2_166 - -LBB2_42: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xd4 // mov r12, rdx - QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 - -LBB2_43: - QUAD $0x0000018024bc2b4c // sub r15, qword [rsp + 384] - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - -LBB2_44: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x241c3a45 // cmp r11b, byte [r12] - QUAD $0x000001402494940f // sete byte [rsp + 320] - LONG $0x245c3a45; BYTE $0x01 // cmp r11b, byte [r12 + 1] - LONG $0xd1940f41 // sete r9b - LONG $0x245c3a45; BYTE $0x02 // cmp r11b, byte [r12 + 2] - LONG $0xd3940f41 // sete r11b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x03 // cmp al, byte [r12 + 3] - LONG $0xd5940f41 // sete r13b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x04 // cmp al, byte [r12 + 4] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x05 // cmp al, byte [r12 + 5] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x06 // cmp al, byte [r12 + 6] - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x07 // cmp al, byte [r12 + 7] - LONG $0xd4940f41 // sete r12b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x08 // cmp al, byte [rcx + 8] - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x09 // cmp al, byte [rcx + 9] - LONG $0xd6940f40 // sete sil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] - LONG $0xd7940f40 // sete dil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] - LONG $0xd0940f41 // sete r8b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] - LONG $0xd2940f41 // sete r10b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] - LONG $0xd7940f41 // sete r15b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] - QUAD $0x000000902494940f // sete byte [rsp + 144] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] - QUAD $0x000001202494940f // sete byte [rsp + 288] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] - QUAD $0x000000982494940f // sete byte [rsp + 152] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] - LONG $0xd6940f41 // sete r14b - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] - QUAD $0x000001102494940f // sete byte [rsp + 272] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0045; BYTE $0xc9 // add r9b, r9b - QUAD $0x00000140248c0244 // add r9b, byte [rsp + 320] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e4c041 // shl r12b, 7 - WORD $0x0841; BYTE $0xdc // or r12b, bl - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000008824b40240 // add sil, byte [rsp + 136] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xdd // or r13b, r11b - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xeb // or bl, r13b - WORD $0xde89 // mov esi, ebx - LONG $0x03e0c041 // shl r8b, 3 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xc2 // or r10b, r8b - LONG $0x05e7c041 // shl r15b, 5 - WORD $0x0845; BYTE $0xd7 // or r15b, r10b - QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x0841; BYTE $0xdc // or r12b, bl - WORD $0x0844; BYTE $0xf8 // or al, r15b - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xdb00 // add bl, bl - LONG $0x20249c02; WORD $0x0001; BYTE $0x00 // add bl, byte [rsp + 288] - WORD $0xde89 // mov esi, ebx - QUAD $0x00000098249cb60f // movzx ebx, byte [rsp + 152] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - QUAD $0x0000017824b48b48 // mov rsi, qword [rsp + 376] - WORD $0x8844; BYTE $0x26 // mov byte [rsi], r12b - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x4688; BYTE $0x01 // mov byte [rsi + 1], al - WORD $0x0841; BYTE $0xde // or r14b, bl - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xc000 // add al, al - LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - WORD $0x5688; BYTE $0x03 // mov byte [rsi + 3], dl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000017824b48948 // mov qword [rsp + 376], rsi - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB2_44 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - JMP LBB2_129 - -LBB2_46: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB2_117 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB2_165 - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_52 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB2_50: - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_50 - LONG $0x01c68349 // add r14, 1 - -LBB2_52: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_56 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - -LBB2_54: + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_48 + +LBB2_49: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 + +LBB2_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_55 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB2_53: QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - QUAD $0x000000a02494940f // sete byte [rsp + 160] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x086a3b4c // cmp r13, qword [rdx + 8] LONG $0xd2940f41 // sete r10b LONG $0x106a3b4c // cmp r13, qword [rdx + 16] LONG $0xd6940f41 // sete r14b LONG $0x186a3b4c // cmp r13, qword [rdx + 24] - QUAD $0x000000882494940f // sete byte [rsp + 136] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x286a3b4c // cmp r13, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x306a3b4c // cmp r13, qword [rdx + 48] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x386a3b4c // cmp r13, qword [rdx + 56] LONG $0xd7940f40 // sete dil LONG $0x406a3b4c // cmp r13, qword [rdx + 64] - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x486a3b4c // cmp r13, qword [rdx + 72] LONG $0xd6940f40 // sete sil LONG $0x506a3b4c // cmp r13, qword [rdx + 80] @@ -11107,33 +11247,33 @@ LBB2_54: LONG $0x686a3b4c // cmp r13, qword [rdx + 104] LONG $0xd4940f41 // sete r12b LONG $0x706a3b4c // cmp r13, qword [rdx + 112] - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] LONG $0xd7940f41 // sete r15b LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] @@ -11141,115 +11281,114 @@ LBB2_54: LONG $0xf0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 240] LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 248] - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd0 // sete al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xdf // or dil, bl LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0844; BYTE $0xf3 // or bl, r14b WORD $0x8941; BYTE $0xda // mov r10d, ebx QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xd3 // or bl, r10b WORD $0xde89 // mov esi, ebx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000009824b4b60f // movzx esi, byte [rsp + 152] + QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xdb00 // add bl, bl - LONG $0x60245c02 // add bl, byte [rsp + 96] + LONG $0x70245c02 // add bl, byte [rsp + 112] WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0x8841; BYTE $0x3e // mov byte [r14], dil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x01468841 // mov byte [r14 + 1], al + LONG $0x014e8841 // mov byte [r14 + 1], cl WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd908 // or cl, bl LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xc108 // or cl, al + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x03468841 // mov byte [r14 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 LONG $0x04c68349 // add r14, 4 QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB2_54 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + JNE LBB2_53 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] -LBB2_56: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB2_93 +LBB2_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB2_98 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi -LBB2_59: +LBB2_58: WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al @@ -11278,59 +11417,72 @@ LBB2_59: WORD $0xd830 // xor al, bl LONG $0x36048841 // mov byte [r14 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_59 - JMP LBB2_146 - -LBB2_60: - LONG $0x2eb70f44 // movzx r13d, word [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_64 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JNE LBB2_58 + JMP LBB2_170 + +LBB2_59: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_65 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_63 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx LBB2_62: - LONG $0x2a3b4466 // cmp r13w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 JNE LBB2_62 - LONG $0x01c68349 // add r14, 1 - -LBB2_64: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_68 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 -LBB2_66: +LBB2_63: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 + +LBB2_65: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_69 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB2_67: QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x2a3b4466 // cmp r13w, word [rdx] - QUAD $0x000000902494940f // sete byte [rsp + 144] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] LONG $0xd2940f41 // sete r10b LONG $0x6a3b4466; BYTE $0x04 // cmp r13w, word [rdx + 4] @@ -11338,15 +11490,15 @@ LBB2_66: LONG $0x6a3b4466; BYTE $0x06 // cmp r13w, word [rdx + 6] QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x6a3b4466; BYTE $0x08 // cmp r13w, word [rdx + 8] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x6a3b4466; BYTE $0x0a // cmp r13w, word [rdx + 10] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x6a3b4466; BYTE $0x0c // cmp r13w, word [rdx + 12] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x6a3b4466; BYTE $0x0e // cmp r13w, word [rdx + 14] LONG $0xd7940f40 // sete dil LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x6a3b4466; BYTE $0x12 // cmp r13w, word [rdx + 18] LONG $0xd6940f40 // sete sil LONG $0x6a3b4466; BYTE $0x14 // cmp r13w, word [rdx + 20] @@ -11358,33 +11510,33 @@ LBB2_66: LONG $0x6a3b4466; BYTE $0x1a // cmp r13w, word [rdx + 26] LONG $0xd4940f41 // sete r12b LONG $0x6a3b4466; BYTE $0x1c // cmp r13w, word [rdx + 28] - QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x6a3b4466; BYTE $0x1e // cmp r13w, word [rdx + 30] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x6a3b4466; BYTE $0x20 // cmp r13w, word [rdx + 32] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x6a3b4466; BYTE $0x22 // cmp r13w, word [rdx + 34] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x6a3b4466; BYTE $0x24 // cmp r13w, word [rdx + 36] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x6a3b4466; BYTE $0x26 // cmp r13w, word [rdx + 38] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x6a3b4466; BYTE $0x2a // cmp r13w, word [rdx + 42] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x6a3b4466; BYTE $0x2c // cmp r13w, word [rdx + 44] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x6a3b4466; BYTE $0x2e // cmp r13w, word [rdx + 46] LONG $0xd7940f41 // sete r15b LONG $0x6a3b4466; BYTE $0x30 // cmp r13w, word [rdx + 48] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x6a3b4466; BYTE $0x32 // cmp r13w, word [rdx + 50] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x6a3b4466; BYTE $0x36 // cmp r13w, word [rdx + 54] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x6a3b4466; BYTE $0x38 // cmp r13w, word [rdx + 56] QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0x6a3b4466; BYTE $0x3a // cmp r13w, word [rdx + 58] @@ -11392,16 +11544,16 @@ LBB2_66: LONG $0x6a3b4466; BYTE $0x3c // cmp r13w, word [rdx + 60] LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x6a3b4466; BYTE $0x3e // cmp r13w, word [rdx + 62] - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd0 // sete al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xdf // or dil, bl LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000009824b40240 // add sil, byte [rsp + 152] + QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0844; BYTE $0xf3 // or bl, r14b @@ -11409,98 +11561,97 @@ LBB2_66: QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xd3 // or bl, r10b WORD $0xde89 // mov esi, ebx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000008824b4b60f // movzx esi, byte [rsp + 136] + LONG $0x2474b60f; BYTE $0x78 // movzx esi, byte [rsp + 120] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xdb00 // add bl, bl - LONG $0x60245c02 // add bl, byte [rsp + 96] + LONG $0x70245c02 // add bl, byte [rsp + 112] WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0x8841; BYTE $0x3e // mov byte [r14], dil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x01468841 // mov byte [r14 + 1], al + LONG $0x014e8841 // mov byte [r14 + 1], cl WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd908 // or cl, bl LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xc108 // or cl, al + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x03468841 // mov byte [r14 + 3], al LONG $0x40c28348 // add rdx, 64 LONG $0x04c68349 // add r14, 4 QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB2_66 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - -LBB2_68: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB2_82 + JNE LBB2_67 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + +LBB2_69: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB2_85 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi -LBB2_71: +LBB2_72: LONG $0x2a3b4466 // cmp r13w, word [rdx] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al @@ -11529,75 +11680,88 @@ LBB2_71: WORD $0xd830 // xor al, bl LONG $0x36048841 // mov byte [r14 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_71 - JMP LBB2_142 - -LBB2_72: - LONG $0x2eb70f44 // movzx r13d, word [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_76 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB2_74: - LONG $0x2a3b4466 // cmp r13w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_74 - LONG $0x01c68349 // add r14, 1 + JNE LBB2_72 + JMP LBB2_166 + +LBB2_73: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_79 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_77 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx LBB2_76: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_80 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - -LBB2_78: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_76 + +LBB2_77: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 + +LBB2_79: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_83 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB2_81: QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x2a3b4466 // cmp r13w, word [rdx] - QUAD $0x000000a02494940f // sete byte [rsp + 160] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] LONG $0xd2940f41 // sete r10b LONG $0x6a3b4466; BYTE $0x04 // cmp r13w, word [rdx + 4] LONG $0xd6940f41 // sete r14b LONG $0x6a3b4466; BYTE $0x06 // cmp r13w, word [rdx + 6] - QUAD $0x000000882494940f // sete byte [rsp + 136] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x6a3b4466; BYTE $0x08 // cmp r13w, word [rdx + 8] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x6a3b4466; BYTE $0x0a // cmp r13w, word [rdx + 10] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x6a3b4466; BYTE $0x0c // cmp r13w, word [rdx + 12] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x6a3b4466; BYTE $0x0e // cmp r13w, word [rdx + 14] LONG $0xd7940f40 // sete dil LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x6a3b4466; BYTE $0x12 // cmp r13w, word [rdx + 18] LONG $0xd6940f40 // sete sil LONG $0x6a3b4466; BYTE $0x14 // cmp r13w, word [rdx + 20] @@ -11609,33 +11773,33 @@ LBB2_78: LONG $0x6a3b4466; BYTE $0x1a // cmp r13w, word [rdx + 26] LONG $0xd4940f41 // sete r12b LONG $0x6a3b4466; BYTE $0x1c // cmp r13w, word [rdx + 28] - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x6a3b4466; BYTE $0x1e // cmp r13w, word [rdx + 30] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x6a3b4466; BYTE $0x20 // cmp r13w, word [rdx + 32] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x6a3b4466; BYTE $0x22 // cmp r13w, word [rdx + 34] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x6a3b4466; BYTE $0x24 // cmp r13w, word [rdx + 36] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x6a3b4466; BYTE $0x26 // cmp r13w, word [rdx + 38] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x6a3b4466; BYTE $0x2a // cmp r13w, word [rdx + 42] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x6a3b4466; BYTE $0x2c // cmp r13w, word [rdx + 44] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x6a3b4466; BYTE $0x2e // cmp r13w, word [rdx + 46] LONG $0xd7940f41 // sete r15b LONG $0x6a3b4466; BYTE $0x30 // cmp r13w, word [rdx + 48] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x6a3b4466; BYTE $0x32 // cmp r13w, word [rdx + 50] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x6a3b4466; BYTE $0x36 // cmp r13w, word [rdx + 54] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x6a3b4466; BYTE $0x38 // cmp r13w, word [rdx + 56] QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0x6a3b4466; BYTE $0x3a // cmp r13w, word [rdx + 58] @@ -11643,181 +11807,193 @@ LBB2_78: LONG $0x6a3b4466; BYTE $0x3c // cmp r13w, word [rdx + 60] LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x6a3b4466; BYTE $0x3e // cmp r13w, word [rdx + 62] - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd0 // sete al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xdf // or dil, bl LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0844; BYTE $0xf3 // or bl, r14b WORD $0x8941; BYTE $0xda // mov r10d, ebx QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xd3 // or bl, r10b WORD $0xde89 // mov esi, ebx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000009824b4b60f // movzx esi, byte [rsp + 152] + QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xdb00 // add bl, bl - LONG $0x60245c02 // add bl, byte [rsp + 96] + LONG $0x70245c02 // add bl, byte [rsp + 112] WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0x8841; BYTE $0x3e // mov byte [r14], dil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x01468841 // mov byte [r14 + 1], al + LONG $0x014e8841 // mov byte [r14 + 1], cl WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd908 // or cl, bl LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xc108 // or cl, al + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x03468841 // mov byte [r14 + 3], al LONG $0x40c28348 // add rdx, 64 LONG $0x04c68349 // add r14, 4 QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB2_78 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - -LBB2_80: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB2_140 - -LBB2_82: - WORD $0xff31 // xor edi, edi - JMP LBB2_142 + JNE LBB2_81 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] LBB2_83: - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_87 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_164 LBB2_85: - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_85 - LONG $0x01c68349 // add r14, 1 - -LBB2_87: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_91 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 + WORD $0xff31 // xor edi, edi + JMP LBB2_166 + +LBB2_86: + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_92 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_90 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx LBB2_89: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_89 + +LBB2_90: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 + +LBB2_92: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_96 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB2_94: QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - QUAD $0x000000a02494940f // sete byte [rsp + 160] + QUAD $0x000000982494940f // sete byte [rsp + 152] LONG $0x086a3b4c // cmp r13, qword [rdx + 8] LONG $0xd2940f41 // sete r10b LONG $0x106a3b4c // cmp r13, qword [rdx + 16] LONG $0xd6940f41 // sete r14b LONG $0x186a3b4c // cmp r13, qword [rdx + 24] - QUAD $0x000000882494940f // sete byte [rsp + 136] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x286a3b4c // cmp r13, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x306a3b4c // cmp r13, qword [rdx + 48] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x386a3b4c // cmp r13, qword [rdx + 56] LONG $0xd7940f40 // sete dil LONG $0x406a3b4c // cmp r13, qword [rdx + 64] - QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x486a3b4c // cmp r13, qword [rdx + 72] LONG $0xd6940f40 // sete sil LONG $0x506a3b4c // cmp r13, qword [rdx + 80] @@ -11829,33 +12005,33 @@ LBB2_89: LONG $0x686a3b4c // cmp r13, qword [rdx + 104] LONG $0xd4940f41 // sete r12b LONG $0x706a3b4c // cmp r13, qword [rdx + 112] - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] LONG $0xd7940f41 // sete r15b LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] QUAD $0x000001402494940f // sete byte [rsp + 320] LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] @@ -11863,170 +12039,185 @@ LBB2_89: LONG $0xf0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 240] LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 248] - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd0 // sete al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xdf // or dil, bl LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0844; BYTE $0xf3 // or bl, r14b WORD $0x8941; BYTE $0xda // mov r10d, ebx QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xd3 // or bl, r10b WORD $0xde89 // mov esi, ebx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000009824b4b60f // movzx esi, byte [rsp + 152] + QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xdb00 // add bl, bl - LONG $0x60245c02 // add bl, byte [rsp + 96] + LONG $0x70245c02 // add bl, byte [rsp + 112] WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0x8841; BYTE $0x3e // mov byte [r14], dil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x01468841 // mov byte [r14 + 1], al + LONG $0x014e8841 // mov byte [r14 + 1], cl WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd908 // or cl, bl LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xc108 // or cl, al + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x03468841 // mov byte [r14 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 LONG $0x04c68349 // add r14, 4 QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB2_89 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + JNE LBB2_94 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] -LBB2_91: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB2_144 - -LBB2_93: - WORD $0xff31 // xor edi, edi - JMP LBB2_146 +LBB2_96: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_168 -LBB2_94: - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_98 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB2_98: + WORD $0xff31 // xor edi, edi + JMP LBB2_170 + +LBB2_99: + WORD $0x8b44; BYTE $0x26 // mov r12d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_105 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_103 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB2_96: - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] +LBB2_102: + LONG $0x012ef8c5 // vucomiss xmm0, dword [rcx] + LONG $0x04518d48 // lea rdx, [rcx + 4] WORD $0x9b0f; BYTE $0xd1 // setnp cl WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xcb20 // and bl, cl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_96 - LONG $0x01c68349 // add r14, 1 + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_102 -LBB2_98: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_102 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b8249c894c // mov qword [rsp + 184], r11 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - -LBB2_100: +LBB2_103: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 + +LBB2_105: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_109 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000c024a48944 // mov dword [rsp + 192], r12d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + +LBB2_107: QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x422ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rdx + 4] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd5940f41 // sete r13b @@ -12035,7 +12226,7 @@ LBB2_100: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x422ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rdx + 12] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -12045,7 +12236,7 @@ LBB2_100: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x58244c88 // mov byte [rsp + 88], cl LONG $0x422ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rdx + 20] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd4940f41 // sete r12b @@ -12054,7 +12245,7 @@ LBB2_100: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x422ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rdx + 28] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -12064,17 +12255,17 @@ LBB2_100: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x422ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rdx + 36] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x422ef8c5; BYTE $0x28 // vucomiss xmm0, dword [rdx + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x422ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rdx + 44] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd3 // sete bl @@ -12088,32 +12279,32 @@ LBB2_100: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x422ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rdx + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl LONG $0x422ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rdx + 60] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x422ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rdx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x422ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rdx + 68] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl LONG $0x422ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rdx + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl LONG $0x422ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rdx + 76] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd6940f41 // sete r14b @@ -12122,42 +12313,42 @@ LBB2_100: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl LONG $0x422ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rdx + 84] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl LONG $0x422ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rdx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd7940f41 // sete r15b WORD $0x2041; BYTE $0xc7 // and r15b, al LONG $0x422ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rdx + 92] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd0940f41 // sete r8b - WORD $0x2041; BYTE $0xc0 // and r8b, al + LONG $0xd2940f41 // sete r10b + WORD $0x2041; BYTE $0xc2 // and r10b, al LONG $0x422ef8c5; BYTE $0x60 // vucomiss xmm0, dword [rdx + 96] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl LONG $0x422ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rdx + 100] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd3940f41 // sete r11b WORD $0x2041; BYTE $0xc3 // and r11b, al LONG $0x422ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rdx + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd2940f41 // sete r10b - WORD $0x2041; BYTE $0xc2 // and r10b, al - LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] - WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd1940f41 // sete r9b WORD $0x2041; BYTE $0xc1 // and r9b, al + LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] + WORD $0x9b0f; BYTE $0xd0 // setnp al + LONG $0xd0940f41 // sete r8b + WORD $0x2041; BYTE $0xc0 // and r8b, al LONG $0x422ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rdx + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl LONG $0x422ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rdx + 116] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -12172,23 +12363,23 @@ LBB2_100: LONG $0xd6940f40 // sete sil WORD $0x2040; BYTE $0xc6 // and sil, al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x38 // add r13b, byte [rsp + 56] + LONG $0x246c0244; BYTE $0x48 // add r13b, byte [rsp + 72] WORD $0x8944; BYTE $0xe8 // mov eax, r13d LONG $0x05e4c041 // shl r12b, 5 - QUAD $0x00008024acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 128] + LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] LONG $0x06e5c041 // shl r13b, 6 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] + LONG $0x64b60f44; WORD $0x5024 // movzx r12d, byte [rsp + 80] LONG $0x02e4c041 // shl r12b, 2 WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] WORD $0xc900 // add cl, cl - LONG $0x30244c02 // add cl, byte [rsp + 48] + LONG $0x40244c02 // add cl, byte [rsp + 64] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -12197,53 +12388,53 @@ LBB2_100: WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xcb08 // or bl, cl - LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] + LONG $0x6cb60f44; WORD $0x5824 // movzx r13d, byte [rsp + 88] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] WORD $0xc900 // add cl, cl - LONG $0x68244c02 // add cl, byte [rsp + 104] - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + LONG $0x20244c02 // add cl, byte [rsp + 32] + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xcb08 // or bl, cl LONG $0x03e6c041 // shl r14b, 3 WORD $0x0841; BYTE $0xde // or r14b, bl - QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0844; BYTE $0xf1 // or cl, r14b QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x64b60f44; WORD $0x1c24 // movzx r12d, byte [rsp + 28] WORD $0x0845; BYTE $0xec // or r12b, r13b - QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e7c041 // shl r15b, 6 WORD $0x0841; BYTE $0xdf // or r15b, bl LONG $0x2024840a; WORD $0x0001; BYTE $0x00 // or al, byte [rsp + 288] - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf8 // or r8b, r15b - WORD $0x0841; BYTE $0xc8 // or r8b, cl + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0845; BYTE $0xfa // or r10b, r15b + WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x00000088249c0244 // add r11b, byte [rsp + 136] - LONG $0x02e2c041 // shl r10b, 2 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xd1 // or r9b, r10b - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + QUAD $0x000000a0249c0244 // add r11b, byte [rsp + 160] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0845; BYTE $0xc8 // or r8b, r9b + QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xc9 // or cl, r9b + WORD $0x0844; BYTE $0xc1 // or cl, r8b WORD $0x8845; BYTE $0x26 // mov byte [r14], r12b QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 @@ -12253,161 +12444,419 @@ LBB2_100: LONG $0x07e6c040 // shl sil, 7 WORD $0x0840; BYTE $0xfe // or sil, dil WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x02468845 // mov byte [r14 + 2], r8b + LONG $0x02568845 // mov byte [r14 + 2], r10b LONG $0x03768841 // mov byte [r14 + 3], sil LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 LONG $0x04c68349 // add r14, 4 QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB2_100 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + JNE LBB2_107 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000c024a48b44 // mov r12d, dword [rsp + 192] + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] -LBB2_102: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB2_148 - WORD $0xff31 // xor edi, edi - JMP LBB2_150 +LBB2_109: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_172 + WORD $0xff31 // xor edi, edi + JMP LBB2_174 + +LBB2_112: + WORD $0x8a44; BYTE $0x26 // mov r12b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_131 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_146 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 -LBB2_105: - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_109 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB2_115: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x22 // cmp r12b, byte [rdx] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB2_115 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB2_147 + JMP LBB2_189 -LBB2_107: - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] +LBB2_117: + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_123 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_121 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_120: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 WORD $0x894d; BYTE $0xf4 // mov r12, r14 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_107 - LONG $0x01c68349 // add r14, 1 - -LBB2_109: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_132 - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x245c8944; BYTE $0x1c // mov dword [rsp + 28], r11d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000018824bc894c // mov qword [rsp + 392], r15 - JB LBB2_113 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB2_169 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB2_169 + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_120 -LBB2_113: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xd4 // mov r12, rdx - QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 +LBB2_121: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + LONG $0x01c68349 // add r14, 1 -LBB2_114: - QUAD $0x0000018024bc2b4c // sub r15, qword [rsp + 384] - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 +LBB2_123: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_127 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax -LBB2_115: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x241c3a45 // cmp r11b, byte [r12] - QUAD $0x000001402494940f // sete byte [rsp + 320] - LONG $0x245c3a45; BYTE $0x01 // cmp r11b, byte [r12 + 1] - LONG $0xd1940f41 // sete r9b - LONG $0x245c3a45; BYTE $0x02 // cmp r11b, byte [r12 + 2] - LONG $0xd3940f41 // sete r11b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x03 // cmp al, byte [r12 + 3] - LONG $0xd5940f41 // sete r13b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x04 // cmp al, byte [r12 + 4] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x05 // cmp al, byte [r12 + 5] +LBB2_125: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] + QUAD $0x000000982494940f // sete byte [rsp + 152] + LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] + LONG $0xd2940f41 // sete r10b + LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] + LONG $0xd6940f41 // sete r14b + LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x06 // cmp al, byte [r12 + 6] + LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x1c24448b // mov eax, dword [rsp + 28] - LONG $0x24443a41; BYTE $0x07 // cmp al, byte [r12 + 7] - LONG $0xd4940f41 // sete r12b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x08 // cmp al, byte [rcx + 8] - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x09 // cmp al, byte [rcx + 9] - LONG $0xd6940f40 // sete sil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] + LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] LONG $0xd7940f40 // sete dil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] + LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] + LONG $0xd6940f40 // sete sil + LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] LONG $0xd0940f41 // sete r8b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] - LONG $0xd2940f41 // sete r10b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] - LONG $0xd7940f41 // sete r15b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] + LONG $0xd1940f41 // sete r9b + LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] + LONG $0xd3940f41 // sete r11b + LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] + LONG $0xd4940f41 // sete r12b + LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] + WORD $0x940f; BYTE $0xd1 // sete cl + LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] QUAD $0x000000902494940f // sete byte [rsp + 144] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] - QUAD $0x000001202494940f // sete byte [rsp + 288] - LONG $0x1c24548b // mov edx, dword [rsp + 28] - WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] + LONG $0xd7940f41 // sete r15b + LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] + QUAD $0x000001402494940f // sete byte [rsp + 320] + LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] + QUAD $0x000001202494940f // sete byte [rsp + 288] + LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] + LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xdf // or dil, bl + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0x0844; BYTE $0xf3 // or bl, r14b + WORD $0x8941; BYTE $0xda // mov r10d, ebx + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xd3 // or bl, r10b + WORD $0xde89 // mov esi, ebx + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0x0840; BYTE $0xf3 // or bl, sil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x06e6c040 // shl sil, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0x0840; BYTE $0xdf // or dil, bl + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + WORD $0xdb00 // add bl, bl + LONG $0x70245c02 // add bl, byte [rsp + 112] + WORD $0xde89 // mov esi, ebx + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x8841; BYTE $0x3e // mov byte [r14], dil + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014e8841 // mov byte [r14 + 1], cl + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd908 // or cl, bl + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 + JNE LBB2_125 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + +LBB2_127: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_177 + +LBB2_129: + WORD $0xff31 // xor edi, edi + JMP LBB2_179 + +LBB2_130: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB2_134 + +LBB2_131: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB2_148 + +LBB2_132: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 + +LBB2_133: + LONG $0x01c68349 // add r14, 1 + +LBB2_134: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_142 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24648944; BYTE $0x1c // mov dword [rsp + 28], r12d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000188248c8948 // mov qword [rsp + 392], rcx + JB LBB2_138 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB2_190 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB2_190 + +LBB2_138: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + +LBB2_139: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx + +LBB2_140: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3a44; BYTE $0x26 // cmp r12b, byte [rsi] + QUAD $0x000001402494940f // sete byte [rsp + 320] + LONG $0x01663a44 // cmp r12b, byte [rsi + 1] + LONG $0xd1940f41 // sete r9b + LONG $0x02663a44 // cmp r12b, byte [rsi + 2] + LONG $0xd3940f41 // sete r11b + LONG $0x03663a44 // cmp r12b, byte [rsi + 3] + LONG $0xd5940f41 // sete r13b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] + WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] + LONG $0xd4940f41 // sete r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] + LONG $0xd6940f40 // sete sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] + LONG $0xd7940f40 // sete dil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] + LONG $0xd0940f41 // sete r8b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] + LONG $0xd2940f41 // sete r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] + LONG $0xd7940f41 // sete r15b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + WORD $0x940f; BYTE $0xd0 // sete al + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + QUAD $0x000001202494940f // sete byte [rsp + 288] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] - QUAD $0x000000982494940f // sete byte [rsp + 152] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + QUAD $0x000000902494940f // sete byte [rsp + 144] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] LONG $0xd6940f41 // sete r14b @@ -12416,22 +12865,22 @@ LBB2_115: QUAD $0x000001102494940f // sete byte [rsp + 272] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x1c24548b // mov edx, dword [rsp + 28] WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] WORD $0x940f; BYTE $0xd2 // sete dl @@ -12443,348 +12892,129 @@ LBB2_115: LONG $0x02e3c041 // shl r11b, 2 WORD $0x0845; BYTE $0xcb // or r11b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000008824b40240 // add sil, byte [rsp + 136] + QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xdd // or r13b, r11b - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] LONG $0x02e7c040 // shl dil, 2 WORD $0x0840; BYTE $0xf7 // or dil, sil LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xeb // or bl, r13b - WORD $0xde89 // mov esi, ebx + WORD $0x8941; BYTE $0xd9 // mov r9d, ebx + LONG $0x1c24748b // mov esi, dword [rsp + 28] LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x0844; BYTE $0xcb // or bl, r9b LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e7c041 // shl r15b, 5 WORD $0x0845; BYTE $0xd7 // or r15b, r10b - QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] - LONG $0x06e6c040 // shl sil, 6 + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0x0841; BYTE $0xdc // or r12b, bl WORD $0x0844; BYTE $0xf8 // or al, r15b - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xdb00 // add bl, bl LONG $0x20249c02; WORD $0x0001; BYTE $0x00 // add bl, byte [rsp + 288] - WORD $0xde89 // mov esi, ebx - QUAD $0x00000098249cb60f // movzx ebx, byte [rsp + 152] + WORD $0xdf89 // mov edi, ebx + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - QUAD $0x0000017824b48b48 // mov rsi, qword [rsp + 376] - WORD $0x8844; BYTE $0x26 // mov byte [rsi], r12b - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] - LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xfb // or bl, dil + QUAD $0x0000017824bc8b48 // mov rdi, qword [rsp + 376] + WORD $0x8844; BYTE $0x27 // mov byte [rdi], r12b + WORD $0x8941; BYTE $0xf4 // mov r12d, esi + LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x4688; BYTE $0x01 // mov byte [rsi + 1], al + WORD $0x0841; BYTE $0xf6 // or r14b, sil + WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al WORD $0x0841; BYTE $0xde // or r14b, bl - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0xda08 // or dl, bl WORD $0xc208 // or dl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - WORD $0x5688; BYTE $0x03 // mov byte [rsi + 3], dl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000017824b48948 // mov qword [rsp + 376], rsi - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB2_115 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - JMP LBB2_133 - -LBB2_117: - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_121 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB2_119: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_119 - LONG $0x01c68349 // add r14, 1 - -LBB2_121: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_125 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - -LBB2_123: - QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] - LONG $0xd2940f41 // sete r10b - LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] - LONG $0xd6940f41 // sete r14b - LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] - LONG $0xd7940f40 // sete dil - LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] - QUAD $0x000000902494940f // sete byte [rsp + 144] - LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] - LONG $0xd6940f40 // sete sil - LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] - LONG $0xd0940f41 // sete r8b - LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] - LONG $0xd1940f41 // sete r9b - LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] - LONG $0xd3940f41 // sete r11b - LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] - LONG $0xd4940f41 // sete r12b - LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] - QUAD $0x000000982494940f // sete byte [rsp + 152] - LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] - LONG $0xd7940f41 // sete r15b - LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] - QUAD $0x000001402494940f // sete byte [rsp + 320] - LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] - QUAD $0x000001202494940f // sete byte [rsp + 288] - LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] - LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] - LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xdf // or dil, bl - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - WORD $0x8941; BYTE $0xda // mov r10d, ebx - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xd3 // or bl, r10b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000009824b4b60f // movzx esi, byte [rsp + 152] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xdb00 // add bl, bl - LONG $0x60245c02 // add bl, byte [rsp + 96] - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0x8841; BYTE $0x3e // mov byte [r14], dil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x01468841 // mov byte [r14 + 1], al - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xc108 // or cl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x034e8841 // mov byte [r14 + 3], cl - LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB2_123 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - -LBB2_125: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB2_153 - -LBB2_127: - WORD $0xff31 // xor edi, edi - JMP LBB2_155 + LONG $0x02778844 // mov byte [rdi + 2], r14b + WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000017824bc8948 // mov qword [rsp + 376], rdi + QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + JNE LBB2_140 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + JMP LBB2_143 -LBB2_128: +LBB2_142: QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 - WORD $0x8949; BYTE $0xd4 // mov r12, rdx + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB2_129: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB2_135 +LBB2_143: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB2_189 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB2_159 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - QUAD $0x0000017824b48b4c // mov r14, qword [rsp + 376] + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x00000178249c8b4c // mov r11, qword [rsp + 376] -LBB2_159: - LONG $0x341c3a45 // cmp r11b, byte [r12 + rsi] +LBB2_183: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e243a46 // cmp r12b, byte [rsi + r9] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x345c3a45; BYTE $0x01 // cmp r11b, byte [r12 + rsi + 1] - LONG $0x02768d48 // lea rsi, [rsi + 2] + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x06643a44; BYTE $0x01 // cmp r12b, byte [rsi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl WORD $0xd330 // xor bl, dl @@ -12793,98 +13023,326 @@ LBB2_159: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB2_159 - JMP LBB2_162 - -LBB2_132: - QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 - WORD $0x8949; BYTE $0xd4 // mov r12, rdx - -LBB2_133: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB2_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB2_160 + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB2_183 + JMP LBB2_186 -LBB2_135: - WORD $0xf631 // xor esi, esi - JMP LBB2_163 +LBB2_146: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_189 -LBB2_136: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xff31 // xor edi, edi +LBB2_147: + LONG $0x01c68349 // add r14, 1 -LBB2_137: - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xc820 // and al, cl - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x14b60f45; BYTE $0x36 // movzx r10d, byte [r14 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0xb341; BYTE $0x01 // mov r11b, 1 - WORD $0xd241; BYTE $0xe3 // shl r11b, cl - WORD $0x3044; BYTE $0xd0 // xor al, r10b - WORD $0x2041; BYTE $0xc3 // and r11b, al - WORD $0x3045; BYTE $0xd3 // xor r11b, r10b - LONG $0x361c8845 // mov byte [r14 + rsi], r11b - LONG $0x02c78348 // add rdi, 2 - LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] - LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd29b0f41 // setnp r10b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xd0 // and al, r10b - WORD $0xd8f6 // neg al - WORD $0x3044; BYTE $0xd8 // xor al, r11b - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xdb // xor bl, r11b - LONG $0x361c8841 // mov byte [r14 + rsi], bl - WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB2_137 +LBB2_148: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_156 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24648944; BYTE $0x1c // mov dword [rsp + 28], r12d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000188248c8948 // mov qword [rsp + 392], rcx + JB LBB2_152 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB2_193 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB2_193 -LBB2_138: - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_165 - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - JMP LBB2_152 +LBB2_152: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 -LBB2_140: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi +LBB2_153: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx -LBB2_141: - LONG $0x2a3b4466 // cmp r13w, word [rdx] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xf3 // mov r11, r14 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] +LBB2_154: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3a44; BYTE $0x26 // cmp r12b, byte [rsi] + QUAD $0x000001402494940f // sete byte [rsp + 320] + LONG $0x01663a44 // cmp r12b, byte [rsi + 1] + LONG $0xd1940f41 // sete r9b + LONG $0x02663a44 // cmp r12b, byte [rsi + 2] + LONG $0xd3940f41 // sete r11b + LONG $0x03663a44 // cmp r12b, byte [rsi + 3] + LONG $0xd5940f41 // sete r13b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] + WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] + LONG $0xd4940f41 // sete r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] + LONG $0xd6940f40 // sete sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] + LONG $0xd7940f40 // sete dil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] + LONG $0xd0940f41 // sete r8b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] + LONG $0xd2940f41 // sete r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] + LONG $0xd7940f41 // sete r15b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + WORD $0x940f; BYTE $0xd0 // sete al + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + QUAD $0x000001202494940f // sete byte [rsp + 288] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] + QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] + LONG $0xd6940f41 // sete r14b + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] + QUAD $0x000001102494940f // sete byte [rsp + 272] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x1c24548b // mov edx, dword [rsp + 28] + WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000140248c0244 // add r9b, byte [rsp + 320] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xdd // or r13b, r11b + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xeb // or bl, r13b + WORD $0x8941; BYTE $0xd9 // mov r9d, ebx + LONG $0x1c24748b // mov esi, dword [rsp + 28] + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0x0844; BYTE $0xcb // or bl, r9b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x05e7c041 // shl r15b, 5 + WORD $0x0845; BYTE $0xd7 // or r15b, r10b + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xdc // or r12b, bl + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + WORD $0xdb00 // add bl, bl + LONG $0x20249c02; WORD $0x0001; BYTE $0x00 // add bl, byte [rsp + 288] + WORD $0xdf89 // mov edi, ebx + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx + LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0x0840; BYTE $0xfb // or bl, dil + QUAD $0x0000017824bc8b48 // mov rdi, qword [rsp + 376] + WORD $0x8844; BYTE $0x27 // mov byte [rdi], r12b + WORD $0x8941; BYTE $0xf4 // mov r12d, esi + LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xf6 // or r14b, sil + WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd808 // or al, bl + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02778844 // mov byte [rdi + 2], r14b + WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000017824bc8948 // mov qword [rsp + 376], rdi + QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + JNE LBB2_154 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + JMP LBB2_157 + +LBB2_156: + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + +LBB2_157: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB2_189 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB2_184 + +LBB2_159: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB2_187 + +LBB2_160: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xff31 // xor edi, edi + +LBB2_161: + LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] + WORD $0x9b0f; BYTE $0xd1 // setnp cl + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xc820 // and al, cl + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x14b60f45; BYTE $0x36 // movzx r10d, byte [r14 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0xb341; BYTE $0x01 // mov r11b, 1 + WORD $0xd241; BYTE $0xe3 // shl r11b, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0x2041; BYTE $0xc3 // and r11b, al + WORD $0x3045; BYTE $0xd3 // xor r11b, r10b + LONG $0x361c8845 // mov byte [r14 + rsi], r11b + LONG $0x02c78348 // add rdi, 2 + LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd8f6 // neg al + WORD $0x3044; BYTE $0xd8 // xor al, r11b + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xdb // xor bl, r11b + LONG $0x361c8841 // mov byte [r14 + rsi], bl + WORD $0x3949; BYTE $0xf9 // cmp r9, rdi + JNE LBB2_161 + +LBB2_162: + LONG $0x01c0f641 // test r8b, 1 + JE LBB2_189 + LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] + JMP LBB2_176 + +LBB2_164: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0xff31 // xor edi, edi + +LBB2_165: + LONG $0x2a3b4466 // cmp r13w, word [rdx] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x361c8841 // mov byte [r14 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] LONG $0x04528d48 // lea rdx, [rdx + 4] LONG $0xd1940f41 // sete r9b WORD $0xf641; BYTE $0xd9 // neg r9b @@ -12896,20 +13354,20 @@ LBB2_141: WORD $0xd830 // xor al, bl LONG $0x36048841 // mov byte [r14 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_141 + JNE LBB2_165 -LBB2_142: +LBB2_166: LONG $0x01c0f641 // test r8b, 1 - JE LBB2_165 + JE LBB2_189 LONG $0x2a3b4466 // cmp r13w, word [rdx] - JMP LBB2_157 + JMP LBB2_181 -LBB2_144: +LBB2_168: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi -LBB2_145: +LBB2_169: WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al @@ -12938,20 +13396,20 @@ LBB2_145: WORD $0xd830 // xor al, bl LONG $0x36048841 // mov byte [r14 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_145 + JNE LBB2_169 -LBB2_146: +LBB2_170: LONG $0x01c0f641 // test r8b, 1 - JE LBB2_165 + JE LBB2_189 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - JMP LBB2_157 + JMP LBB2_181 -LBB2_148: +LBB2_172: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0xff31 // xor edi, edi -LBB2_149: +LBB2_173: LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] WORD $0x9b0f; BYTE $0xd1 // setnp cl WORD $0x940f; BYTE $0xd0 // sete al @@ -12984,14 +13442,14 @@ LBB2_149: WORD $0x3044; BYTE $0xdb // xor bl, r11b LONG $0x361c8841 // mov byte [r14 + rsi], bl WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB2_149 + JNE LBB2_173 -LBB2_150: +LBB2_174: LONG $0x01c0f641 // test r8b, 1 - JE LBB2_165 + JE LBB2_189 LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] -LBB2_152: +LBB2_176: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd2 // sete dl WORD $0xc220 // and dl, al @@ -13007,14 +13465,14 @@ LBB2_152: WORD $0xd320 // and bl, dl WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x061c8841 // mov byte [r14 + rax], bl - JMP LBB2_165 + JMP LBB2_189 -LBB2_153: +LBB2_177: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi -LBB2_154: +LBB2_178: WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al @@ -13043,14 +13501,14 @@ LBB2_154: WORD $0xd830 // xor al, bl LONG $0x36048841 // mov byte [r14 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_154 + JNE LBB2_178 -LBB2_155: +LBB2_179: LONG $0x01c0f641 // test r8b, 1 - JE LBB2_165 + JE LBB2_189 WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] -LBB2_157: +LBB2_181: WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfa // mov rdx, rdi @@ -13064,31 +13522,32 @@ LBB2_157: WORD $0xc320 // and bl, al WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x161c8841 // mov byte [r14 + rdx], bl - JMP LBB2_165 + JMP LBB2_189 -LBB2_160: +LBB2_184: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - QUAD $0x0000017824b48b4c // mov r14, qword [rsp + 376] + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x00000178249c8b4c // mov r11, qword [rsp + 376] -LBB2_161: - LONG $0x341c3a45 // cmp r11b, byte [r12 + rsi] +LBB2_185: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e243a46 // cmp r12b, byte [rsi + r9] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x345c3a45; BYTE $0x01 // cmp r11b, byte [r12 + rsi + 1] - LONG $0x02768d48 // lea rsi, [rsi + 2] + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x06643a44; BYTE $0x01 // cmp r12b, byte [rsi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl WORD $0xd330 // xor bl, dl @@ -13097,2019 +13556,2016 @@ LBB2_161: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB2_161 + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB2_185 -LBB2_162: - WORD $0x0149; BYTE $0xf4 // add r12, rsi +LBB2_186: + WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB2_163: +LBB2_187: LONG $0x01c0f641 // test r8b, 1 - JE LBB2_165 - LONG $0x241c3a45 // cmp r11b, byte [r12] + JE LBB2_189 + WORD $0x3a44; BYTE $0x26 // cmp r12b, byte [rsi] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 QUAD $0x0000017824848b4c // mov r8, qword [rsp + 376] LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al WORD $0x3040; BYTE $0xfb // xor bl, dil LONG $0x101c8841 // mov byte [r8 + rdx], bl -LBB2_165: +LBB2_189: MOVQ 1280(SP), SP VZEROUPPER RET -LBB2_166: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB2_190: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - QUAD $0x0000018024bc894c // mov qword [rsp + 384], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000017824848948 // mov qword [rsp + 376], rax - LONG $0x6e79c1c4; BYTE $0xc3 // vmovd xmm0, r11d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 WORD $0xc031 // xor eax, eax QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB2_167: +LBB2_191: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000019824848948 // mov qword [rsp + 408], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1a04b60f // movzx eax, byte [rdx + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] - WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] + WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xe06ef9c5 // vmovd xmm4, eax WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x3244b60f; BYTE $0x02 // movzx eax, byte [rdx + rsi + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x3244b60f; BYTE $0x03 // movzx eax, byte [rdx + rsi + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x3244b60f; BYTE $0x04 // movzx eax, byte [rdx + rsi + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x3244b60f; BYTE $0x05 // movzx eax, byte [rdx + rsi + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x3244b60f; BYTE $0x06 // movzx eax, byte [rdx + rsi + 6] - QUAD $0x000000f024b48948 // mov qword [rsp + 240], rsi + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x0000010024948948 // mov qword [rsp + 256], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x3244b60f; BYTE $0x07 // movzx eax, byte [rdx + rsi + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02400d48; WORD $0x0000 // or rax, 576 QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x40cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 576 + QUAD $0x000000f0249c8948 // mov qword [rsp + 240], rbx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x02600d48; WORD $0x0000 // or rax, 608 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0x80cb8149; WORD $0x0002; BYTE $0x00 // or r11, 640 - LONG $0x245c894c; BYTE $0x70 // mov qword [rsp + 112], r11 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + WORD $0x8949; BYTE $0xce // mov r14, rcx + LONG $0x80ce8149; WORD $0x0002; BYTE $0x00 // or r14, 640 + QUAD $0x000000a024b4894c // mov qword [rsp + 160], r14 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x02a00d48; WORD $0x0000 // or rax, 672 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0xc0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 704 - QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 - WORD $0x8948; BYTE $0xde // mov rsi, rbx + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + WORD $0x8949; BYTE $0xcd // mov r13, rcx + LONG $0xc0cd8149; WORD $0x0002; BYTE $0x00 // or r13, 704 + QUAD $0x000000e824ac894c // mov qword [rsp + 232], r13 + WORD $0x8948; BYTE $0xce // mov rsi, rcx LONG $0xe0ce8148; WORD $0x0002; BYTE $0x00 // or rsi, 736 - QUAD $0x000000d024b48948 // mov qword [rsp + 208], rsi - WORD $0x8949; BYTE $0xdf // mov r15, rbx + QUAD $0x000000c024b48948 // mov qword [rsp + 192], rsi + WORD $0x8949; BYTE $0xcf // mov r15, rcx LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 - QUAD $0x000000e024bc894c // mov qword [rsp + 224], r15 - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - LONG $0x20c98149; WORD $0x0003; BYTE $0x00 // or r9, 800 - QUAD $0x000000e8248c894c // mov qword [rsp + 232], r9 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - LONG $0x40c88149; WORD $0x0003; BYTE $0x00 // or r8, 832 - LONG $0x2444894c; BYTE $0x58 // mov qword [rsp + 88], r8 - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - LONG $0x60cf8148; WORD $0x0003; BYTE $0x00 // or rdi, 864 - QUAD $0x000000d824bc8948 // mov qword [rsp + 216], rdi - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x80ce8149; WORD $0x0003; BYTE $0x00 // or r14, 896 - LONG $0x2474894c; BYTE $0x50 // mov qword [rsp + 80], r14 - WORD $0x8949; BYTE $0xda // mov r10, rbx - LONG $0xa0ca8149; WORD $0x0003; BYTE $0x00 // or r10, 928 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x00000100249c8948 // mov qword [rsp + 256], rbx + LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 + WORD $0x8949; BYTE $0xcb // mov r11, rcx + LONG $0x20cb8149; WORD $0x0003; BYTE $0x00 // or r11, 800 + QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 + WORD $0x8949; BYTE $0xca // mov r10, rcx + LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 + QUAD $0x000001202494894c // mov qword [rsp + 288], r10 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 + QUAD $0x00000088248c894c // mov qword [rsp + 136], r9 + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 + QUAD $0x000000d02484894c // mov qword [rsp + 208], r8 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0xa0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 928 + QUAD $0x000000d824948948 // mov qword [rsp + 216], rdx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000c8248c8948 // mov qword [rsp + 200], rcx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x60 // mov qword [rsp + 96], rcx - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - LONG $0x207923c4; WORD $0x2a0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdx + r13], 1 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - LONG $0x2031e3c4; WORD $0x1a04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdx + rbx], 2 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 3 - LONG $0x2079a3c4; WORD $0x1a04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdx + r11], 4 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 5 - LONG $0x2079a3c4; WORD $0x2204; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdx + r12], 6 - LONG $0x2079e3c4; WORD $0x3204; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdx + rsi], 7 - LONG $0x2079a3c4; WORD $0x3a04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdx + r15], 8 - LONG $0x2079a3c4; WORD $0x0a04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdx + r9], 9 - LONG $0x2079a3c4; WORD $0x0204; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdx + r8], 10 - LONG $0x2079e3c4; WORD $0x3a04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdx + rdi], 11 - LONG $0x2079a3c4; WORD $0x3204; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdx + r14], 12 - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdx + r10], 13 - LONG $0x2079e3c4; WORD $0x0204; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdx + rax], 14 - LONG $0x2079e3c4; WORD $0x0a04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdx + rcx], 15 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdx + r14], 1 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - LONG $0x2061a3c4; WORD $0x221c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdx + r12], 2 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + r8], 3 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r9], 4 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r11], 5 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - LONG $0x2061a3c4; WORD $0x121c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + r10], 6 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + r15], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + rsi], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + rax], 9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + rbx], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + rcx], 11 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + rdi], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rdi], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rdi], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + rdi], 15 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x01013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 1 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x02012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x03013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 3 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x04012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x05013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 5 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x06012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 6 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x07012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 8 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x09013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 10 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0b013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 11 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0c013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 12 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0d013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 13 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0e013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 14 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0f013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 15 - QUAD $0x0101326c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r14 + 1], 1 - QUAD $0x0201226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 1], 2 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x0301026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 1], 3 - QUAD $0x04010a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 1], 4 - QUAD $0x05011a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 1], 5 - QUAD $0x0601126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 1], 6 - QUAD $0x07013a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 1], 7 - QUAD $0x0801326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 1], 8 - QUAD $0x0901026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 9 - QUAD $0x0a011a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 1], 10 - QUAD $0x0b010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 14 + LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + LONG $0x207923c4; WORD $0x270c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r12], 1 + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r14], 4 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r13], 6 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rsi], 7 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r15], 8 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r11], 9 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r10], 10 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + r9], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rdx], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r8], 2 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r9], 3 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r10], 4 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r15], 6 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r14], 7 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rsi], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rcx], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rdx], 12 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rdx], 13 + QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + r12], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rdx], 15 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x010117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 1 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x020117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 3 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x04012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x050117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 5 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x07012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 8 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x090117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 10 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0b0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 11 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0c0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 12 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0d0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0f0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 15 + QUAD $0x01011f6c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rbx + 1], 1 + QUAD $0x0201076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 2 + QUAD $0x03010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 3 + QUAD $0x0401176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x06013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 6 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x0701376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 1], 7 + QUAD $0x0801376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 10 + QUAD $0x0b010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + QUAD $0x0e01276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 14 LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0102442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 1], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xce6e79c5 // vmovd xmm9, esi LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xd66e79c5 // vmovd xmm10, esi - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x010202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 2], 1 - QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] - QUAD $0x02020a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 2], 2 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x030212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 2], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x050202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x060202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 6 - QUAD $0x07022a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 2], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x08020a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 2], 8 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x090222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 2], 9 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0a022a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 2], 10 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x0b021a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 2], 11 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0c0232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 2], 12 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0d023a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 2], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 1 - QUAD $0x02023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0302325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0402325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0502325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0602325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x0702325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 7 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x08021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 8 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x09023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 9 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0a023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 10 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0b023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 11 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0c023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0e023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 15 - QUAD $0x010302642021a3c4 // vpinsrb xmm4, xmm11, byte [rdx + r8 + 3], 1 - QUAD $0x02030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 2 - QUAD $0x030312642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 3], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x04033a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 3], 4 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x050302642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 3], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06033a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 3], 6 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x07030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 7 - QUAD $0x08030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 8 - QUAD $0x090322642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 3], 9 - QUAD $0x0a032a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 3], 10 - QUAD $0x0b031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 11 - WORD $0x894d; BYTE $0xdc // mov r12, r11 - QUAD $0x0c0332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 3], 12 - QUAD $0x0d033a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 3], 13 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0e031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 14 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0f030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 15 - QUAD $0x0103026c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdx + rax + 3], 1 - WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x010207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 1 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x02020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03020f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 2], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x07022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 7 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0203026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0303026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0403026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0503026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0603026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 6 - QUAD $0x0703326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 7 - QUAD $0x08031a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 3], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0903026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 9 + QUAD $0x080207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 8 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x090227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 9 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0a022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 10 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0b021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 11 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0c0237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 12 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x0d023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 13 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 12 + QUAD $0x0e0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 14 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x0f021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 15 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] + QUAD $0x0102075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0202375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0302375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0402375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0502375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 5 + QUAD $0x0602175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0702375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 7 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0802175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 8 + QUAD $0x0902175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x0d02175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 13 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x0e02175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 15 + QUAD $0x010307642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r8 + 3], 1 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x02030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x03030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x04030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x05030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x06030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 6 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x07030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x08030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 8 + QUAD $0x090327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 9 + QUAD $0x0a032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 10 + QUAD $0x0b031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 11 + QUAD $0x0c0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 12 + QUAD $0x0d033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 13 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0e030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 14 + QUAD $0x0f031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 15 + QUAD $0x0103076c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rax + 3], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 13 + QUAD $0x0203076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 2 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0303076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 3], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0403076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0503076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x06033f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 3], 6 + QUAD $0x0703376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e0302442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 3], 14 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a74b60f; BYTE $0x09 // movzx esi, byte [rdx + rcx + 9] + QUAD $0x0e0317442051a3c4 // vpinsrb xmm0, xmm5, byte [rdi + r10 + 3], 14 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x09 // movzx esi, byte [rdi + rcx + 9] LONG $0xc66e79c5 // vmovd xmm8, esi - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0302442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 3], 15 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0f0327442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a74b60f; BYTE $0x09 // movzx esi, byte [rdx + rcx + 9] + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f74b60f; BYTE $0x09 // movzx esi, byte [rdi + rcx + 9] LONG $0xde6e79c5 // vmovd xmm11, esi - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x010432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 4], 1 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x02043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 2 - QUAD $0x030412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 4], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x04043a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 4], 4 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - QUAD $0x050402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 5 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x06041a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 4], 6 - QUAD $0x07040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 7 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x08040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 8 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x090402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 10 - QUAD $0x0b0422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c0432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 4], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d0432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 4], 13 - QUAD $0x0e041a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 4], 14 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x0f0422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 15 - QUAD $0x01042a5c2011a3c4 // vpinsrb xmm3, xmm13, byte [rdx + r13 + 4], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0204325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0304325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0404325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0504025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0604325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 6 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0704025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0804025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0904025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 9 + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + QUAD $0x010417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x040417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x05040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 5 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x06042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 6 + QUAD $0x07040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x090407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 10 + QUAD $0x0b041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 11 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x0c041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 12 + QUAD $0x0d0437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 13 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 10 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0b041a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 4], 11 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0c041a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 4], 12 + QUAD $0x0e0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 15 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0104075c2011e3c4 // vpinsrb xmm3, xmm13, byte [rdi + rax + 4], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 14 + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x0304075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0404075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0504075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 5 + WORD $0x894c; BYTE $0xfe // mov rsi, r15 + QUAD $0x06043f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 4], 6 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 15 - QUAD $0x010532642009a3c4 // vpinsrb xmm4, xmm14, byte [rdx + r14 + 5], 1 - QUAD $0x02053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 2 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x030512642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 5], 3 - QUAD $0x04053a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 5], 4 - QUAD $0x05050a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 5], 5 - WORD $0x8949; BYTE $0xca // mov r10, rcx - QUAD $0x06051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 6 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x07053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 7 - QUAD $0x08050a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 5], 8 - QUAD $0x090502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 9 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0a0502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b050a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 5], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 12 + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x0804375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 4], 8 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0904075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 10 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 14 - QUAD $0x0f0522642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 5], 15 - QUAD $0x01052a6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdx + r13 + 5], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0205026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 2 + QUAD $0x0b04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 11 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0c040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 12 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0d043f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 4], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 14 + QUAD $0x0f04275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 15 + QUAD $0x010517642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r10 + 5], 1 + QUAD $0x02051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 2 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x03051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 3 + QUAD $0x040517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 4 + QUAD $0x05050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 5 + QUAD $0x06052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x08050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 8 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x090517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 10 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x0b0527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 11 + QUAD $0x0c051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 12 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x0d053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 14 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0305026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0405026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0505026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 5 - QUAD $0x0605326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 5], 6 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - QUAD $0x07051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0805026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0905026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 10 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x0b052a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 5], 11 - QUAD $0x0c051a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 5], 12 - WORD $0x894d; BYTE $0xdc // mov r12, r11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 14 + QUAD $0x0f0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 15 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0105176c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdi + rdx + 5], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0205176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0405076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 4 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0505176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 5 + QUAD $0x0605376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 6 + WORD $0x8949; BYTE $0xf5 // mov r13, rsi + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0705176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 7 + QUAD $0x0805376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 5], 8 + QUAD $0x0905076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a05176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x0c050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0502442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 5], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x0a // movzx esi, byte [rdx + rax + 10] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0507442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 5], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] LONG $0xde6ef9c5 // vmovd xmm3, esi LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x0a // movzx esi, byte [rdx + rsi + 10] - LONG $0xe66ef9c5 // vmovd xmm4, esi - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x01063a442019e3c4 // vpinsrb xmm0, xmm12, byte [rdx + rdi + 6], 1 - QUAD $0x020632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 6], 2 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x030602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 3 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x040632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 6], 4 - QUAD $0x050612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 6], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x060602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 6 - QUAD $0x07063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 7 - QUAD $0x08060a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 6], 8 - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x090632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 9 - QUAD $0x0a0602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 10 - QUAD $0x0b060a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 6], 11 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0c0602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 12 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0d060a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 6], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 14 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0f0612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 6], 15 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x01060a6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdx + rcx + 6], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0206326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0306326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0406326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0506326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 6 - QUAD $0x07061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 7 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x08061a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 6], 8 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x09061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 10 - WORD $0x894d; BYTE $0xef // mov r15, r13 - QUAD $0x0b062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 11 - QUAD $0x0c06226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 13 + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] + LONG $0xe66ef9c5 // vmovd xmm4, esi + QUAD $0x010617442019a3c4 // vpinsrb xmm0, xmm12, byte [rdi + r10 + 6], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02061f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 6], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x040617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 4 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x050637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 5 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + QUAD $0x06061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 6 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x070637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 7 + QUAD $0x08060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 8 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x09060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 9 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 14 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0f062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 15 - QUAD $0x01073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 1 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x02072a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 7], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x03073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 3 - QUAD $0x040732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 7], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x05073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 5 - QUAD $0x060702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x070702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x08070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x09070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 10 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0b073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 11 - QUAD $0x0c0702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 12 - QUAD $0x0d070a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 7], 13 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0e070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 14 - QUAD $0x0f0712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 7], 15 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0107324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 7], 1 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x02070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 2 + QUAD $0x0a060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 10 + QUAD $0x0b0627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 11 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0c060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 12 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x0d063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 13 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x0e0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 14 LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x03070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 4 - QUAD $0x0507324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 6 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x07070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 7 - QUAD $0x08071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 8 - QUAD $0x09071a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 7], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 10 - QUAD $0x0b073a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 7], 11 - QUAD $0x0c07224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 7], 12 + QUAD $0x0f060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 15 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x01063f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r15 + 6], 1 LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 13 + QUAD $0x02060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 2 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x03060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 3 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x04060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0506376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 5 + QUAD $0x06062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 6 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0706376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x08060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 8 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x09060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 9 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x0a06276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 6], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 12 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x0d062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 13 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0e060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 15 + QUAD $0x010717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 1 + QUAD $0x02071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 2 + WORD $0x8949; BYTE $0xda // mov r10, rbx + QUAD $0x030707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 3 + QUAD $0x040717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x050707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 5 + QUAD $0x06071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x090707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 10 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0b071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 11 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0c0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 12 + QUAD $0x0d070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 13 + QUAD $0x0e0707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 15 + QUAD $0x01073f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 7], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0207074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0307074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0407074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 4 + QUAD $0x0507374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0707374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x09070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 9 + QUAD $0x0a07274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 11 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0c07274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 12 + QUAD $0x0d072f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e070a442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rcx + 7], 14 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a74b60f; BYTE $0x0b // movzx esi, byte [rdx + rcx + 11] + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0e070f442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rcx + 7], 14 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x0b // movzx esi, byte [rdi + rcx + 11] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0f070a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 7], 15 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f070f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a74b60f; BYTE $0x0b // movzx esi, byte [rdx + rcx + 11] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01080a442031e3c4 // vpinsrb xmm0, xmm9, byte [rdx + rcx + 8], 1 - WORD $0x894d; BYTE $0xef // mov r15, r13 - QUAD $0x02082a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 8], 2 QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x03080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x040832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 4 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x05082a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 8], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x060832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 6 - WORD $0x8949; BYTE $0xc0 // mov r8, rax - QUAD $0x070802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 8 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x090822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 8], 9 + LONG $0x0f74b60f; BYTE $0x0b // movzx esi, byte [rdi + rcx + 11] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x010837442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r14 + 8], 1 + QUAD $0x020817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 3 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x04080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 4 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x050817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 5 + QUAD $0x06081f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 8], 6 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x07081f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 8], 7 + QUAD $0x080817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 8 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x09080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 10 + QUAD $0x0b081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 11 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x0c0807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 12 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0d0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 14 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x0f083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 15 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0108176c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rdx + 8], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0208376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0308376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0408376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 4 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x05081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 5 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x06081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 6 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x07081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 7 + QUAD $0x0808076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0908076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 9 LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0a081a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 8], 10 + QUAD $0x0a081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 10 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0b081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 11 + QUAD $0x0c08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 12 + QUAD $0x0d082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 13 + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + QUAD $0x0e082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010937742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r14 + 9], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 2 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x03091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 3 + QUAD $0x04090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 4 + QUAD $0x050917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 5 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x06091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 6 + QUAD $0x07091f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 9], 7 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x08091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 8 + QUAD $0x09090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 9 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0a090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 11 + QUAD $0x0c0907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 12 QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x0b080a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 8], 11 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0c0812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 12 + QUAD $0x0d090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 13 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0e0937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 14 + QUAD $0x0f093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 15 + QUAD $0x0109177c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rdx + 9], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0209077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 2 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x03090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 3 + QUAD $0x0409377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 4 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x05090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0609177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x08090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 8 + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 10 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 15 - QUAD $0x0108326c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r14 + 8], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0208026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0308026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0408326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0508026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0608026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 6 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0708326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 7 - QUAD $0x08081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0908026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 15 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010902742039e3c4 // vpinsrb xmm6, xmm8, byte [rdx + rax + 9], 1 - QUAD $0x02093a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 9], 2 - QUAD $0x03090a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 9], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 4 - QUAD $0x05092a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r13 + 9], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x060902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 6 - QUAD $0x070902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 7 - QUAD $0x08093a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 9], 8 - QUAD $0x090922742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 9], 9 - QUAD $0x0a091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 10 - QUAD $0x0b090a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 9], 11 - QUAD $0x0c0912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 12 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x0d0912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0109027c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdx + rax + 9], 1 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x02092a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 9], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0309027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 3 - QUAD $0x0409327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 9], 4 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x05091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0609027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 6 - QUAD $0x0709327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 9], 7 - QUAD $0x08091a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 9], 8 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0909027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 14 + QUAD $0x0b09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 11 + QUAD $0x0c09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 12 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0d093f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 9], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f09026c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdx + rax + 9], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x0c // movzx esi, byte [rdi + rax + 12] LONG $0xc66ef9c5 // vmovd xmm0, esi LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x00044024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm5 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x0c // movzx esi, byte [rdi + rax + 12] LONG $0xee6ef9c5 // vmovd xmm5, esi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 1 - QUAD $0x020a3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 10], 2 - QUAD $0x030a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x040a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 4 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x050a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x060a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x070a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 7 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x080a0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 10], 8 - QUAD $0x090a225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 10], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 11 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x010a275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 10], 1 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x020a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 2 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 12 - QUAD $0x0d0a125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 10], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x010a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 1 - QUAD $0x020a2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 10], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x030a32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 10], 3 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x040a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 4 - QUAD $0x050a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 5 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x060a12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 10], 6 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - QUAD $0x070a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 7 - QUAD $0x080a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 8 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x090a2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 10], 9 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0a0a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 10 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0b0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 11 + QUAD $0x030a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 3 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x040a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 4 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 12 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0d0a22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 10], 13 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0e0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 14 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0f0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 15 + QUAD $0x050a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 5 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x060a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x080a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x090a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 11 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x0c0a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 12 + QUAD $0x0d0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 13 + QUAD $0x0e0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 15 + QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] + QUAD $0x010a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 1 + QUAD $0x020a07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 10], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x030a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 3 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 1 - QUAD $0x020b3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 11], 2 - QUAD $0x030b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 3 - QUAD $0x040b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 4 - QUAD $0x050b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x060b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x070b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 7 - QUAD $0x080b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 8 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x090b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 12 + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x050a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 5 + QUAD $0x060a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x070a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x080a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 8 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x090a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 11 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0c0a07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 10], 12 + QUAD $0x0d0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 13 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x0e0a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 14 + LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + QUAD $0x0f0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 15 + QUAD $0x010b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 1 + QUAD $0x020b1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 11], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 3 + QUAD $0x040b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 4 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x050b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 5 + QUAD $0x060b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 6 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x070b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 7 + QUAD $0x080b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 8 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x090b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 9 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0a0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 11 + QUAD $0x0c0b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 12 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0d0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0f0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 15 + QUAD $0x010b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x020b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 2 + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x040b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 4 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x050b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 5 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x060b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x070b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 7 + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x0a0b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 10 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 13 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0e0b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x010b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 1 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x020b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 11], 2 - QUAD $0x030b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 3 - QUAD $0x040b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 11], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x050b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 5 - QUAD $0x060b12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 11], 6 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x070b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x080b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 8 - QUAD $0x090b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 9 - QUAD $0x0a0b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 11], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b0b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c0b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 12 - QUAD $0x0d0b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 11], 13 + QUAD $0x0b0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 11 + QUAD $0x0c0b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 11], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000420249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm3 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0e0b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 14 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x0d // movzx esi, byte [rdx + rsi + 13] + QUAD $0x0e0b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 14 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0f0b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 15 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000400248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm1 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x0d // movzx esi, byte [rdx + rsi + 13] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x010c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 1 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x020c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 12], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x030c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 12], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x040c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 4 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x050c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 5 - QUAD $0x060c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x070c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x080c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 8 - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - QUAD $0x090c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 12], 9 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0a0c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 12], 10 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x0b0c1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 12], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 13 - QUAD $0x0e0c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 12], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 15 - QUAD $0x010c02542051e3c4 // vpinsrb xmm2, xmm5, byte [rdx + rax + 12], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x020c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 2 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x010c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 1 + QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + QUAD $0x020c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 3 + QUAD $0x040c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 4 + QUAD $0x050c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 5 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x060c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 6 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x070c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 8 + QUAD $0x090c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 9 + QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] + QUAD $0x0a0c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 10 + QUAD $0x0b0c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 11 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0c0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 12 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0d0c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 14 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x030c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 4 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x050c12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 12], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x060c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 6 - QUAD $0x070c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x080c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 8 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x090c02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 12], 9 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x0a0c1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 12], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 12 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0d0c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 13 - QUAD $0x0e0c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 15 - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x010d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 13], 1 - QUAD $0x020d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 2 - QUAD $0x030d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 13], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x050d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 13], 5 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x060d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 6 - QUAD $0x070d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 7 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x080d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 13], 8 - QUAD $0x090d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 9 - QUAD $0x0a0d325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 13], 10 - QUAD $0x0b0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 11 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0c0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 12 + QUAD $0x0f0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 15 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x010c37542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rsi + 12], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x020c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 2 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x030c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 3 + QUAD $0x040c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 4 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x050c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 5 + QUAD $0x060c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 6 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x070c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 7 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x080c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 8 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x090c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 9 + QUAD $0x0a0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 10 LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0d0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 14 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0f0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 15 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x010d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 1 - QUAD $0x020d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 2 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x030d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x040d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 4 - QUAD $0x050d124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 13], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x060d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x070d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x080d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 8 - QUAD $0x090d024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 13], 9 - QUAD $0x0a0d1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 13], 10 + QUAD $0x0b0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 11 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0c0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 12 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0d0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 13 + QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] + QUAD $0x0e0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 14 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 15 + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + QUAD $0x010d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 1 + QUAD $0x020d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 2 + QUAD $0x030d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x040d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x050d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 5 + QUAD $0x060d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 6 + QUAD $0x070d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 8 + QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] + QUAD $0x090d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 9 + QUAD $0x0a0d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 10 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0b0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 11 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0c0d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 12 + QUAD $0x0d0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 13 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0e0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 14 + QUAD $0x0f0d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 15 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x010d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 1 + QUAD $0x020d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 2 + QUAD $0x030d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x040d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 4 + QUAD $0x050d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x060d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x070d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 7 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x080d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 8 + QUAD $0x090d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 12 - QUAD $0x0d0d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 13 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - QUAD $0x0e0d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 14 + QUAD $0x0c0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + QUAD $0x0e0d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0d02442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rax + 13], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x0e // movzx esi, byte [rdx + rax + 14] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0d07442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + LONG $0x74b60f42; WORD $0x0e3f // movzx esi, byte [rdi + r15 + 14] LONG $0xce6ef9c5 // vmovd xmm1, esi LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x0e // movzx esi, byte [rdx + rax + 14] - LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 1 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x020e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 2 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x030e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 4 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x050e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 5 - QUAD $0x060e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 14], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x070e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 7 - QUAD $0x080e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 8 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x090e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 12 - QUAD $0x0d0e1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 14], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x010e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 1 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x020e1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 14], 2 - QUAD $0x030e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 4 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x050e0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 14], 5 - QUAD $0x060e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 6 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x070e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 7 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x080e1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 14], 8 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x090e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 12 + LONG $0x0774b60f; BYTE $0x0e // movzx esi, byte [rdi + rax + 14] + LONG $0xc66ef9c5 // vmovd xmm0, esi + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x020e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x030e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x040e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x050e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x060e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 6 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x070e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x080e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 8 + QUAD $0x090e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 9 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0a0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 11 + QUAD $0x0c0e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 12 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0d0e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 14], 13 + QUAD $0x0e0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 15 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x010e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 14], 1 LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x0d0e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 14], 13 - QUAD $0x0e0e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 14], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f0e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 15 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - LONG $0x74b60f42; WORD $0x0f32 // movzx esi, byte [rdx + r14 + 15] - LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x020e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x030e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 3 LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x010f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 1 - QUAD $0x020f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 15], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x030f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 3 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x040f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 15], 4 - QUAD $0x050f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 15], 5 - QUAD $0x060f22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 15], 6 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x070f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 15], 7 + QUAD $0x040e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x050e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 5 QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x080f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 8 - QUAD $0x090f2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 15], 9 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0a0f22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 15], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x0f // movzx esi, byte [rdx + rax + 15] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x010f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 1 - QUAD $0x020f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x030f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x040f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 4 - QUAD $0x050f0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 15], 5 + QUAD $0x060e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 6 + QUAD $0x070e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 7 + QUAD $0x080e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 8 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x090e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a0e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 10 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0b0e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 11 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0c0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 12 QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x060f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x070f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 7 - QUAD $0x080f1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 15], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x090f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 10 - QUAD $0x0b0f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 11 + QUAD $0x0d0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 13 + QUAD $0x0e0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 15 + LONG $0x74b60f42; WORD $0x0f3f // movzx esi, byte [rdi + r15 + 15] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x010f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 1 + QUAD $0x020f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x030f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 3 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x040f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 4 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 12 - QUAD $0x0d0f025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 15], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 14 - QUAD $0x0f0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 15 + QUAD $0x050f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x060f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 7 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x080f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x090f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 9 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0a0f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 10 + QUAD $0x0b0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 11 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0c0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 12 + QUAD $0x0d0f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 13 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0e0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 14 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0f0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 15 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f74b60f; BYTE $0x0f // movzx esi, byte [rdi + rcx + 15] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x010f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 1 + QUAD $0x020f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 2 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x030f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x040f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 4 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x050f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 5 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x060f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x070f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 7 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x080f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x090f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 9 + QUAD $0x0a0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 10 + QUAD $0x0b0f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 11 + QUAD $0x0c0f1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 15], 12 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0d0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 13 + QUAD $0x0e0f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - LONG $0x74b60f42; WORD $0x1032 // movzx esi, byte [rdx + r14 + 16] + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1774b60f; BYTE $0x10 // movzx esi, byte [rdi + rdx + 16] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01100a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 16], 1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x021002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 3 - QUAD $0x041012442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 16], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 6 - QUAD $0x07103a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 16], 7 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - QUAD $0x08101a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 16], 8 - QUAD $0x09102a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 16], 9 - QUAD $0x0a1022442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 16], 10 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x011017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 1 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x021017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x031017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 3 + QUAD $0x04103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x051017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 5 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x061037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 6 + QUAD $0x071007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 7 + QUAD $0x08100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 8 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x09100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 9 + QUAD $0x0a1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0c101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 12 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 13 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0e1032442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 16], 14 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x0f1002442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 16], 15 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1a74b60f; BYTE $0x10 // movzx esi, byte [rdx + rbx + 16] + QUAD $0x0d1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 15 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + LONG $0x74b60f42; WORD $0x1017 // movzx esi, byte [rdi + r10 + 16] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x0110124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 16], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0210324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 2 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x03103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0410324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 4 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x05103a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 16], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0610324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 6 - QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] - QUAD $0x07100a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 16], 7 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x08102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 8 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0910324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 9 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0a10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 10 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0b10224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 16], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 13 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0e10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 14 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x11 // movzx esi, byte [rdx + rsi + 17] - LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x01110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 1 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x02110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 2 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x03110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 3 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x01101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0210074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 2 + QUAD $0x0310074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + QUAD $0x05102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x06103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 6 + QUAD $0x07100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 7 + QUAD $0x0810274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 8 LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x04110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 4 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x05110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x06110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x07110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 7 - QUAD $0x08111a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 17], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x09110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 9 + QUAD $0x09100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 9 LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 11 - QUAD $0x0c1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 13 - QUAD $0x0e1132542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 17], 14 - QUAD $0x0f1102542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 17], 15 - LONG $0x1a74b60f; BYTE $0x11 // movzx esi, byte [rdx + rbx + 17] + QUAD $0x0a100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 12 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0d10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 13 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x0e10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0f102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3774b60f; BYTE $0x11 // movzx esi, byte [rdi + rsi + 17] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x011137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 1 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x021137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x031137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 4 + QUAD $0x051117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 5 + QUAD $0x061137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 6 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x071117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 7 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x081127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 8 + QUAD $0x09110f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 17], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a1117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 10 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0b1117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 11 + QUAD $0x0c111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 12 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x0d110f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 17], 13 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x0e1107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 14 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0f1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 15 + LONG $0x74b60f42; WORD $0x1117 // movzx esi, byte [rdi + r10 + 17] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0111125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 17], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0211025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 2 - QUAD $0x03113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 3 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x04113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 4 - QUAD $0x05113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 5 + QUAD $0x01111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0211175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 2 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0311175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 3 + QUAD $0x0411075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + QUAD $0x06113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0711075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a11175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b11175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 11 + QUAD $0x0c110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 12 QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x06113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 6 - QUAD $0x07110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 7 - QUAD $0x08112a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 17], 8 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0911025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 17], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 10 - QUAD $0x0b11225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 17], 11 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x0c110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 14 + QUAD $0x0d113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 13 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0e110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f1102442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rax + 17], 15 + QUAD $0x0f112f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r13 + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - LONG $0x1a74b60f; BYTE $0x12 // movzx esi, byte [rdx + rbx + 18] + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1774b60f; BYTE $0x12 // movzx esi, byte [rdi + rdx + 18] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x011202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 1 - QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] - QUAD $0x021232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 18], 2 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x031212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 4 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x05121a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 18], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x071202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 8 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x091202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b1202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 13 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x0e1222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 18], 14 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0f122a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 18], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x12 // movzx esi, byte [rdx + rsi + 18] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0112324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0212324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0312324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 3 - QUAD $0x04123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0512324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 5 - QUAD $0x06123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 6 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x07123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0812324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 8 - QUAD $0x0912024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 9 - QUAD $0x0a120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 11 - QUAD $0x0c120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 13 + QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] + QUAD $0x01121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x04120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x05120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x06120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 6 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x071217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 7 + QUAD $0x081227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 8 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x091227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 9 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 14 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0f120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 15 - LONG $0x1a74b60f; BYTE $0x13 // movzx esi, byte [rdx + rbx + 19] - LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0a120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 11 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0c120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 12 + QUAD $0x0d120f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 18], 13 + QUAD $0x0e1207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 18], 14 + QUAD $0x0f1237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 15 + QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] + LONG $0x74b60f42; WORD $0x120f // movzx esi, byte [rdi + r9 + 18] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x01120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0212074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 2 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0312374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 3 LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 1 - QUAD $0x021332542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 19], 2 - QUAD $0x031312542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 19], 3 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x04130a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 19], 4 - QUAD $0x05131a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 19], 5 + QUAD $0x04120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 4 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x05122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 5 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x06120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 7 QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x06130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 6 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x071302542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 19], 7 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x081332542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 19], 8 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x091312542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 19], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1332542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 19], 10 - QUAD $0x0b1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 12 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0d131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 13 - QUAD $0x0e1322542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 19], 14 - QUAD $0x0f132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x13 // movzx esi, byte [rdx + rax + 19] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x01131a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 19], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0213025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0313025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 3 - QUAD $0x04133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0513025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 6 - QUAD $0x07133a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 19], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0813025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0913025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 10 + QUAD $0x08120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 8 + QUAD $0x0912074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 11 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 15 + QUAD $0x0c12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 12 + QUAD $0x0d123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 13 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0e123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 15 + LONG $0x1774b60f; BYTE $0x13 // movzx esi, byte [rdi + rdx + 19] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x01131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 1 + QUAD $0x02131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x031317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 4 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x051337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 5 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x061337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 6 + QUAD $0x071317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x081337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 8 + QUAD $0x091327542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 19], 9 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0a1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 11 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0c1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 15 + LONG $0x74b60f42; WORD $0x130f // movzx esi, byte [rdi + r9 + 19] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x01130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 1 + QUAD $0x0213075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 2 + QUAD $0x0313375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 3 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x04131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 4 + QUAD $0x05132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 5 + QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] + QUAD $0x0613075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0713375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 7 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0813175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 19], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0913375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a13375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 10 + QUAD $0x0b130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 12 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x0d13275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 13 + QUAD $0x0e133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 14 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x14 // movzx esi, byte [rdx + rax + 20] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x14 // movzx esi, byte [rdi + rcx + 20] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x011422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 20], 1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x021402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 2 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x01143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 1 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x02140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 2 + QUAD $0x031417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 3 + QUAD $0x041407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x061407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x071407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 7 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x081437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x091407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 11 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0c1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 12 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0d1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 15 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 3 - QUAD $0x04140a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 20], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 5 - QUAD $0x06140a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 20], 6 - QUAD $0x071402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 20], 7 - QUAD $0x081432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 20], 8 - QUAD $0x091412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 20], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b140a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 20], 11 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0c142a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 20], 12 - QUAD $0x0d141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 13 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0e141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 14 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0f140a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 20], 15 - QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] - LONG $0x74b60f42; WORD $0x140a // movzx esi, byte [rdx + r9 + 20] + LONG $0x0774b60f; BYTE $0x14 // movzx esi, byte [rdi + rax + 20] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x01141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 1 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0214024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 20], 2 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x03143a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 20], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 4 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x05140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 5 - QUAD $0x06143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x0714324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 7 + QUAD $0x01140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + QUAD $0x04141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 4 + QUAD $0x05142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 5 + QUAD $0x0614074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 6 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x07140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 7 + QUAD $0x0814174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0914074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 11 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x0c141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 12 + QUAD $0x0d14274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 20], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 + QUAD $0x0f141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3774b60f; BYTE $0x15 // movzx esi, byte [rdi + rsi + 21] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x01153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 1 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x021537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x031537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 3 QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0814324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 8 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0914324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 9 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x0a14124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b14324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c14324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 13 + QUAD $0x041537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 4 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x05153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 5 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x06151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 6 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x071537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 7 + QUAD $0x081537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 8 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x091517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 9 QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0e14324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 14 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0f14324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 20], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x15 // movzx esi, byte [rdx + rsi + 21] - LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x011522542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 21], 1 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 2 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x03151a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 21], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x041532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 4 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x051532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x071532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x081532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 8 - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x091532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 9 - QUAD $0x0a1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 11 - QUAD $0x0c152a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 21], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 13 - QUAD $0x0e151a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 21], 14 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0f152a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 21], 15 - LONG $0x74b60f42; WORD $0x150a // movzx esi, byte [rdx + r9 + 21] + QUAD $0x0a1537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 11 + QUAD $0x0c1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 12 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0d1527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0f1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 15 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + LONG $0x1774b60f; BYTE $0x15 // movzx esi, byte [rdi + rdx + 21] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0115025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 1 - QUAD $0x0215025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 21], 2 - QUAD $0x03153a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 21], 3 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x04150a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 21], 4 - QUAD $0x05150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0615025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 6 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0715025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0815025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 8 - QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] - QUAD $0x0915225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 21], 9 - QUAD $0x0a15125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 10 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0b151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 11 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0c150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 12 - QUAD $0x0d153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 13 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 14 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0115175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0215375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0315375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0415375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 4 + QUAD $0x05152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 5 + QUAD $0x0615075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 6 + QUAD $0x07150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 7 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0815375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0915375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 9 + QUAD $0x0a150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 11 + QUAD $0x0c151f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 21], 12 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x0d15375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 13 + QUAD $0x0e15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x0f1532442061a3c4 // vpinsrb xmm0, xmm3, byte [rdx + r14 + 21], 15 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f1507442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - LONG $0x74b60f42; WORD $0x1612 // movzx esi, byte [rdx + r10 + 22] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x16 // movzx esi, byte [rdi + rax + 22] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x01163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 1 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - QUAD $0x021602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 22], 2 - QUAD $0x03161a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 22], 3 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x04160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 4 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x05160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 5 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x061632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 22], 6 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x07161a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 22], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x09160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 12 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x01160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 1 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x021607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 2 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x03160f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 22], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 4 + QUAD $0x05163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 5 + QUAD $0x06161f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 22], 6 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x07163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 8 + QUAD $0x091617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0c1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 12 + QUAD $0x0d1627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x0e1627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 14 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x0f1617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x16 // movzx esi, byte [rdi + rax + 22] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x0116174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 1 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x02161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 2 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0316174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0416074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 4 + QUAD $0x05162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 5 + QUAD $0x0616074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 6 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x07161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0916074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 10 LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 13 + QUAD $0x0b16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 12 + QUAD $0x0d16374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 22], 13 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x0e16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 14 LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 14 - QUAD $0x0f162a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 22], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x16 // movzx esi, byte [rdx + rsi + 22] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0116324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0216324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0316324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 3 - QUAD $0x04160a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 22], 4 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x05162a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 22], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0616324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 6 - QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] - QUAD $0x07160a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 22], 7 - QUAD $0x0816024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 8 - QUAD $0x0916224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 22], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 10 - QUAD $0x0b161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 11 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x0c16224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 22], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 15 - LONG $0x74b60f42; WORD $0x1712 // movzx esi, byte [rdx + r10 + 23] + QUAD $0x0f16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 15 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + LONG $0x74b60f42; WORD $0x1737 // movzx esi, byte [rdi + r14 + 23] LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x01173a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 23], 1 - QUAD $0x021702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 23], 2 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x031712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 23], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 5 - QUAD $0x061732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 23], 6 - QUAD $0x07171a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 23], 7 - QUAD $0x08173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 8 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x091732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 23], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 10 - QUAD $0x0b170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c1702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 12 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0d171a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 23], 13 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0e171a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 23], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f1702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 15 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - LONG $0x74b60f42; WORD $0x173a // movzx esi, byte [rdx + r15 + 23] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x01170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0217025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 23], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0317325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 3 + QUAD $0x01170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 1 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x02170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 2 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + QUAD $0x03170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 3 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x04170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 4 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x051737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 5 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x061737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 6 + QUAD $0x07173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x081737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 8 QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0417325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 4 - QUAD $0x05172a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 23], 5 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x06172a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 23], 6 - QUAD $0x07170a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 23], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0817325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 8 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0917025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 23], 9 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0a17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 11 - QUAD $0x0c17225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 23], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 13 + QUAD $0x091737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 9 QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0e17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 14 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 15 + QUAD $0x0a1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 11 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0c1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 13 + QUAD $0x0e1727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 14 + QUAD $0x0f1717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x17 // movzx esi, byte [rdi + rsi + 23] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0117375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 1 + QUAD $0x02171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 2 + QUAD $0x0317175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 3 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x04173f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 23], 4 + QUAD $0x05172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0617175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 6 + QUAD $0x07171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 7 + QUAD $0x0817075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 8 + QUAD $0x0917075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c17375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 12 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x0d17175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 23], 13 + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + QUAD $0x0e172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 14 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x18 // movzx esi, byte [rdx + rsi + 24] + LONG $0x74b60f42; WORD $0x1837 // movzx esi, byte [rdi + r14 + 24] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x011832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 1 QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 2 - QUAD $0x031812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 24], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x041832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 4 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x051832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x071832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x081832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 8 - QUAD $0x091832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 9 - QUAD $0x0a183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 10 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0b1832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 12 - QUAD $0x0d181a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 24], 13 - QUAD $0x0e181a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 24], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 15 - LONG $0x74b60f42; WORD $0x183a // movzx esi, byte [rdx + r15 + 24] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x01180a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 24], 1 - QUAD $0x0218024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0318024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 3 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x0418224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 24], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0518024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 5 - QUAD $0x06182a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 24], 6 - QUAD $0x07180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 7 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x08183a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 24], 8 - QUAD $0x0918024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a18024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 10 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x0b18024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 11 + QUAD $0x011837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 1 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x02181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 2 + QUAD $0x03180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 3 + QUAD $0x04180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 4 LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0c180a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 24], 12 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0d18124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0e183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 14 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0f181a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 24], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x19 // movzx esi, byte [rdx + rax + 25] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x01192a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 25], 1 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x041932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 4 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x05191a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 25], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x071932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x081932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 8 + QUAD $0x05180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 5 QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x091932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 10 - QUAD $0x0b1932542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 25], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x19 // movzx esi, byte [rdx + rsi + 25] - LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x061837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 6 QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0119325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 1 + QUAD $0x071837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 7 LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0219325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0319325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 3 - QUAD $0x0419225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 25], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0519325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0619325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 6 - QUAD $0x07190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 7 - QUAD $0x08193a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 25], 8 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x09193a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 25], 9 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0a190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 10 - QUAD $0x0b19025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 11 - QUAD $0x0c190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 12 - QUAD $0x0d19125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 25], 13 - QUAD $0x0e193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 14 - LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 - QUAD $0x0f191a442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rbx + 25], 15 - LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 - LONG $0x0274b60f; BYTE $0x1a // movzx esi, byte [rdx + rax + 26] - LONG $0xc66ef9c5 // vmovd xmm0, esi - QUAD $0x011a2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 26], 1 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x021a12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 26], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 4 - QUAD $0x051a1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 26], 5 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x061a1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 26], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x071a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 7 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x081a32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 26], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x091a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 10 + QUAD $0x081837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x091837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 9 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0a1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 10 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0b1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 11 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x0c1827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 12 QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0b1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a74b60f; BYTE $0x1a // movzx esi, byte [rdx + rdi + 26] + QUAD $0x0d1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 14 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x0f180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x18 // movzx esi, byte [rdi + rsi + 24] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x011a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 1 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x021a024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 26], 2 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x031a1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 26], 3 - QUAD $0x041a224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 26], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x051a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x061a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 6 - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x071a224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 26], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x081a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 8 - QUAD $0x091a3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 26], 9 - QUAD $0x0a1a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 12 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0118374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 1 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 13 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x0e1a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 14 + QUAD $0x0218374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0318374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 3 + QUAD $0x04183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 4 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + QUAD $0x05183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x0618374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x1b // movzx esi, byte [rdx + rsi + 27] + QUAD $0x0718374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 7 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0818374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0918374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 9 + QUAD $0x0a18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 10 + QUAD $0x0b18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 12 + WORD $0x894d; BYTE $0xd6 // mov r14, r10 + QUAD $0x0d18174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 13 + QUAD $0x0e182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 14 + QUAD $0x0f181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x19 // movzx esi, byte [rdi + rax + 25] LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x011b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 27], 1 - QUAD $0x021b12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 27], 2 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 3 - QUAD $0x041b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 4 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x051b12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 27], 5 - QUAD $0x061b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 27], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x071b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 7 - QUAD $0x081b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 27], 8 - QUAD $0x091b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 10 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0b1b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 27], 11 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0c1b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 14 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0f1b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 27], 15 - LONG $0x3a74b60f; BYTE $0x1b // movzx esi, byte [rdx + rdi + 27] + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + QUAD $0x01191f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 25], 1 + QUAD $0x02191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 2 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x03191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 4 + QUAD $0x05190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 5 + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + QUAD $0x061917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x071907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x09192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 10 + QUAD $0x0b1907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 11 + QUAD $0x0c1927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 12 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0d1927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + QUAD $0x0f190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 15 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + LONG $0x1774b60f; BYTE $0x19 // movzx esi, byte [rdi + rdx + 25] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x011b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 1 - QUAD $0x021b025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 27], 2 - QUAD $0x031b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 3 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x041b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 4 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x051b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 5 - QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x061b3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 27], 6 - QUAD $0x071b225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 27], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x081b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 8 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x091b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 9 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0a1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0319075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0419075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 4 + QUAD $0x05193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x08190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0919075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 9 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x0a190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 10 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0b19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 11 QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 11 + QUAD $0x0c19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 12 + QUAD $0x0d19375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 25], 13 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0e193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 14 + LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0f1937442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r14 + 25], 15 + LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3774b60f; BYTE $0x1a // movzx esi, byte [rdi + rsi + 26] + LONG $0xc66ef9c5 // vmovd xmm0, esi + QUAD $0x011a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 1 + QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + QUAD $0x021a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 2 + QUAD $0x031a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 4 LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 13 - QUAD $0x0e1b0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 27], 14 + QUAD $0x051a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 5 + QUAD $0x061a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 6 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x071a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 7 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x081a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 8 + QUAD $0x091a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 9 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0a1a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 11 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0c1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 12 + QUAD $0x0d1a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 15 + LONG $0x1774b60f; BYTE $0x1a // movzx esi, byte [rdi + rdx + 26] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x011a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x021a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 2 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x031a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 3 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x041a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x051a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x061a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 15 + QUAD $0x071a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 7 + QUAD $0x081a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 8 + QUAD $0x091a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 9 + QUAD $0x0a1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 10 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x0b1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x0d1a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 13 + QUAD $0x0e1a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 14 + QUAD $0x0f1a374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 26], 15 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x1b // movzx esi, byte [rdi + rcx + 27] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x011b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 1 + QUAD $0x021b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 27], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x031b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x041b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x051b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 5 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x061b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 6 + QUAD $0x071b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 7 + QUAD $0x081b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 8 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x091b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 9 + QUAD $0x0a1b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 11 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x0c1b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x1b // movzx esi, byte [rdi + rsi + 27] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x011b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x021b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x031b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 3 + QUAD $0x041b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 4 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x051b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x061b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x071b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 7 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x081b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 8 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x091b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 9 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x0a1b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 10 + QUAD $0x0b1b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 11 + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x1c // movzx esi, byte [rdx + rsi + 28] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x1c // movzx esi, byte [rdi + rax + 28] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x011c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 1 - QUAD $0x021c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 3 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x041c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 28], 4 - QUAD $0x051c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 28], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 6 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x071c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 7 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x081c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 28], 8 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x091c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 10 - QUAD $0x0b1c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 28], 11 - QUAD $0x0c1c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 12 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0d1c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 28], 13 - QUAD $0x0e1c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 28], 14 - QUAD $0x0f1c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 28], 15 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x74b60f42; WORD $0x1c1a // movzx esi, byte [rdx + r11 + 28] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x011c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x021c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x031c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 3 - QUAD $0x041c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 4 - QUAD $0x051c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 5 - QUAD $0x061c3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 28], 6 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x071c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 7 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x081c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 8 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x091c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 9 + QUAD $0x011c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 1 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x021c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x031c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 3 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x041c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 4 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x051c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 5 + QUAD $0x061c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 6 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x071c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 7 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x081c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 8 + QUAD $0x091c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 9 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0a1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 11 + QUAD $0x0c1c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 12 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0d1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 13 LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 11 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0c1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 13 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x0e1c124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 28], 14 + QUAD $0x0e1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 14 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0f1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 15 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f74b60f; BYTE $0x1c // movzx esi, byte [rdi + rcx + 28] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x011c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 1 + QUAD $0x021c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 2 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x031c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 3 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x041c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x051c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x061c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x1d // movzx esi, byte [rdx + rsi + 29] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x011d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 1 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 3 - QUAD $0x041d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 4 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x051d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 5 + QUAD $0x071c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 7 QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 6 - QUAD $0x071d2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 29], 7 - QUAD $0x081d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 8 - QUAD $0x091d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 10 - QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] - QUAD $0x0b1d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 11 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0c1d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 12 - QUAD $0x0d1d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 13 + QUAD $0x081c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x091c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 9 + QUAD $0x0a1c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 10 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x0b1c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 11 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0c1c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 12 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0d1c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 13 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x0e1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 14 LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 14 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0f1d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 15 - LONG $0x74b60f42; WORD $0x1d1a // movzx esi, byte [rdx + r11 + 29] + QUAD $0x0f1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 15 + LONG $0x0774b60f; BYTE $0x1d // movzx esi, byte [rdi + rax + 29] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x011d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 1 + QUAD $0x021d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x031d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 3 + QUAD $0x041d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x051d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 5 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + QUAD $0x061d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 6 + QUAD $0x071d17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 29], 7 + QUAD $0x081d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x091d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 9 + QUAD $0x0a1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 10 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0b1d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 11 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0c1d17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 29], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 13 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0e1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x1d // movzx esi, byte [rdi + rsi + 29] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x011d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x021d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 2 - QUAD $0x031d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 3 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x041d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x051d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 5 - QUAD $0x061d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 29], 6 - QUAD $0x071d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x081d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 8 - QUAD $0x091d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 29], 9 - WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 10 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0b1d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 11 - QUAD $0x0c1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 13 - QUAD $0x0e1d12642061a3c4 // vpinsrb xmm4, xmm3, byte [rdx + r10 + 29], 14 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x011d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x021d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 2 + QUAD $0x031d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 3 + QUAD $0x041d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 29], 4 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x051d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 5 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x061d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x071d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x081d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 8 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x091d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a1d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 10 + QUAD $0x0b1d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 11 + QUAD $0x0c1d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 12 + QUAD $0x0d1d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 29], 13 + QUAD $0x0e1d1f642061e3c4 // vpinsrb xmm4, xmm3, byte [rdi + rbx + 29], 14 + WORD $0x8949; BYTE $0xdc // mov r12, rbx LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0f1d12442059a3c4 // vpinsrb xmm0, xmm4, byte [rdx + r10 + 29], 15 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f1d1f442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rbx + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x1e // movzx esi, byte [rdx + rax + 30] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x1e // movzx esi, byte [rdi + rcx + 30] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x011e1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 30], 1 - LONG $0x0274b60f; BYTE $0x1f // movzx esi, byte [rdx + rax + 31] + QUAD $0x011e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 1 + LONG $0x0f74b60f; BYTE $0x1f // movzx esi, byte [rdi + rcx + 31] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x011f1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 31], 1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x021e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 2 - QUAD $0x021f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 3 - QUAD $0x031f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 4 - QUAD $0x041f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 4 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x051e0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 30], 5 - QUAD $0x051f0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 31], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 6 - QUAD $0x061f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x071e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 7 - QUAD $0x071f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 7 - QUAD $0x00000110249c8b48 // mov rbx, qword [rsp + 272] - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 8 - QUAD $0x081f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 8 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x091e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 9 - QUAD $0x091f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 10 - QUAD $0x0a1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 10 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x0b1e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 30], 11 - QUAD $0x0b1f024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 31], 11 - QUAD $0x0c1e22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 30], 12 - QUAD $0x0c1f224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 31], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 13 - QUAD $0x0d1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 14 - QUAD $0x0e1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 14 - QUAD $0x0f1e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 30], 15 - QUAD $0x0f1f32542071a3c4 // vpinsrb xmm2, xmm1, byte [rdx + r14 + 31], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3244b60f; BYTE $0x1e // movzx eax, byte [rdx + rsi + 30] - LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x011e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 30], 1 - LONG $0x3244b60f; BYTE $0x1f // movzx eax, byte [rdx + rsi + 31] - LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f1a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 31], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x021e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 2 - QUAD $0x021f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x031e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 3 - QUAD $0x031f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 3 - QUAD $0x041e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 30], 4 - QUAD $0x041f2a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 31], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x051e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 5 - QUAD $0x051f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x061e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 6 - QUAD $0x061f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 6 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x071e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 7 - QUAD $0x071f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 7 + QUAD $0x011f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 1 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 8 - QUAD $0x091e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 30], 9 - QUAD $0x091f3a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r15 + 31], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 10 - QUAD $0x0b1e3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 30], 11 - QUAD $0x0b1f3a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rdi + 31], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 12 - QUAD $0x0c1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 12 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x0d1e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 30], 13 - QUAD $0x0d1f0a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 31], 13 + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + QUAD $0x051e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 30], 5 + QUAD $0x051f174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 31], 5 + QUAD $0x061e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 6 + QUAD $0x061f0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 31], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x0000011024b48b48 // mov rsi, qword [rsp + 272] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 14 - QUAD $0x0f1e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 30], 15 - QUAD $0x0f1f127c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r10 + 31], 15 + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x0b1e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 30], 11 + QUAD $0x0b1f1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 31], 11 + QUAD $0x0c1e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 30], 12 + QUAD $0x0c1f174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 31], 12 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + QUAD $0x0e1e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 30], 14 + QUAD $0x0e1f374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 31], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542071e3c4 // vpinsrb xmm2, xmm1, byte [rdi + rax + 31], 15 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x011e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] + LONG $0xf86ef9c5 // vmovd xmm7, eax + QUAD $0x011f077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 31], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x091e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 9 + QUAD $0x091f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0b1e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 11 + QUAD $0x0b1f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x0d1e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 30], 13 + QUAD $0x0d1f3f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 31], 13 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x0e1e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 14 + QUAD $0x0e1f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 14 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x0f1e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 15 + QUAD $0x0f1f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -15238,2002 +15694,2001 @@ LBB2_167: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x447ffec5; WORD $0x608b // vmovdqu yword [rbx + 4*rcx + 96], ymm0 - LONG $0x547ffec5; WORD $0x408b // vmovdqu yword [rbx + 4*rcx + 64], ymm2 - LONG $0x647ffec5; WORD $0x208b // vmovdqu yword [rbx + 4*rcx + 32], ymm4 - LONG $0x0c7ffec5; BYTE $0x8b // vmovdqu yword [rbx + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608e // vmovdqu yword [rsi + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408e // vmovdqu yword [rsi + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208e // vmovdqu yword [rsi + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8e // vmovdqu yword [rsi + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB2_167 - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - QUAD $0x0000018024bc3b4c // cmp r15, qword [rsp + 384] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - QUAD $0x0000019024a48b4c // mov r12, qword [rsp + 400] - JNE LBB2_43 - JMP LBB2_129 - -LBB2_169: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 + JNE LBB2_191 + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + LONG $0x24648b44; BYTE $0x1c // mov r12d, dword [rsp + 28] + QUAD $0x0000019024b48b48 // mov rsi, qword [rsp + 400] + JNE LBB2_139 + JMP LBB2_143 + +LBB2_193: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - QUAD $0x0000018024bc894c // mov qword [rsp + 384], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000017824848948 // mov qword [rsp + 376], rax - LONG $0x6e79c1c4; BYTE $0xc3 // vmovd xmm0, r11d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 WORD $0xc031 // xor eax, eax QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB2_170: +LBB2_194: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000019824848948 // mov qword [rsp + 408], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1a04b60f // movzx eax, byte [rdx + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] - WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] + WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xe06ef9c5 // vmovd xmm4, eax WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x3244b60f; BYTE $0x02 // movzx eax, byte [rdx + rsi + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x3244b60f; BYTE $0x03 // movzx eax, byte [rdx + rsi + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x3244b60f; BYTE $0x04 // movzx eax, byte [rdx + rsi + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x3244b60f; BYTE $0x05 // movzx eax, byte [rdx + rsi + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x3244b60f; BYTE $0x06 // movzx eax, byte [rdx + rsi + 6] - QUAD $0x000000f024b48948 // mov qword [rsp + 240], rsi + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x0000010024948948 // mov qword [rsp + 256], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x3244b60f; BYTE $0x07 // movzx eax, byte [rdx + rsi + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x0000010824848948 // mov qword [rsp + 264], rax LONG $0x40cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 576 - QUAD $0x00000108249c8948 // mov qword [rsp + 264], rbx + QUAD $0x000000f0249c8948 // mov qword [rsp + 240], rbx WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x02600d48; WORD $0x0000 // or rax, 608 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8949; BYTE $0xce // mov r14, rcx LONG $0x80ce8149; WORD $0x0002; BYTE $0x00 // or r14, 640 - LONG $0x2474894c; BYTE $0x70 // mov qword [rsp + 112], r14 + QUAD $0x000000a024b4894c // mov qword [rsp + 160], r14 WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x02a00d48; WORD $0x0000 // or rax, 672 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8949; BYTE $0xcc // mov r12, rcx - LONG $0xc0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 704 - QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0xe0cf8148; WORD $0x0002; BYTE $0x00 // or rdi, 736 - QUAD $0x000000d024bc8948 // mov qword [rsp + 208], rdi + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + WORD $0x8949; BYTE $0xcd // mov r13, rcx + LONG $0xc0cd8149; WORD $0x0002; BYTE $0x00 // or r13, 704 + QUAD $0x000000e824ac894c // mov qword [rsp + 232], r13 + WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0xe0ce8148; WORD $0x0002; BYTE $0x00 // or rsi, 736 + QUAD $0x000000c024b48948 // mov qword [rsp + 192], rsi WORD $0x8949; BYTE $0xcf // mov r15, rcx LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 - QUAD $0x000000e024bc894c // mov qword [rsp + 224], r15 + LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 WORD $0x8949; BYTE $0xcb // mov r11, rcx LONG $0x20cb8149; WORD $0x0003; BYTE $0x00 // or r11, 800 - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 + QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 WORD $0x8949; BYTE $0xca // mov r10, rcx LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 - LONG $0x2454894c; BYTE $0x58 // mov qword [rsp + 88], r10 + QUAD $0x000001202494894c // mov qword [rsp + 288], r10 WORD $0x8949; BYTE $0xc9 // mov r9, rcx LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 - QUAD $0x000000d8248c894c // mov qword [rsp + 216], r9 + QUAD $0x00000088248c894c // mov qword [rsp + 136], r9 WORD $0x8949; BYTE $0xc8 // mov r8, rcx LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 - LONG $0x2444894c; BYTE $0x50 // mov qword [rsp + 80], r8 - WORD $0x8948; BYTE $0xce // mov rsi, rcx - LONG $0xa0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 928 - LONG $0x24748948; BYTE $0x48 // mov qword [rsp + 72], rsi + QUAD $0x000000d02484894c // mov qword [rsp + 208], r8 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0xa0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 928 + QUAD $0x000000d824948948 // mov qword [rsp + 216], rdx WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + QUAD $0x000000c8248c8948 // mov qword [rsp + 200], rcx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x60 // mov qword [rsp + 96], rcx - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - LONG $0x207923c4; WORD $0x2a0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdx + r13], 1 - LONG $0x2031e3c4; WORD $0x1a04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdx + rbx], 2 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 3 - LONG $0x2079a3c4; WORD $0x3204; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdx + r14], 4 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 5 - LONG $0x2079a3c4; WORD $0x2204; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdx + r12], 6 - LONG $0x2079e3c4; WORD $0x3a04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdx + rdi], 7 - LONG $0x2079a3c4; WORD $0x3a04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdx + r15], 8 - LONG $0x2079a3c4; WORD $0x1a04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdx + r11], 9 - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdx + r10], 10 - LONG $0x2079a3c4; WORD $0x0a04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdx + r9], 11 - LONG $0x2079a3c4; WORD $0x0204; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdx + r8], 12 - LONG $0x2079e3c4; WORD $0x3204; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdx + rsi], 13 - LONG $0x2079e3c4; WORD $0x0204; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdx + rax], 14 - LONG $0x2079e3c4; WORD $0x0a04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdx + rcx], 15 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdx + r14], 1 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - LONG $0x2061a3c4; WORD $0x221c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdx + r12], 2 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + r8], 3 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r9], 4 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r11], 5 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - LONG $0x2061a3c4; WORD $0x121c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + r10], 6 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + r15], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + rsi], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + rax], 9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + rbx], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + rcx], 11 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + rdi], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rdi], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rdi], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + rdi], 15 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x01013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 1 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x02012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x03013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 3 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x04012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x05013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 5 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x06012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 6 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x07012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 8 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x09013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 10 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0b013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 11 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0c013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 12 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0d013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 13 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0e013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 14 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0f013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 15 - QUAD $0x0101326c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r14 + 1], 1 - QUAD $0x0201226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 1], 2 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x0301026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 1], 3 - QUAD $0x04010a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 1], 4 - QUAD $0x05011a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 1], 5 - QUAD $0x0601126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 1], 6 - QUAD $0x07013a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 1], 7 - QUAD $0x0801326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 1], 8 - QUAD $0x0901026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 9 - QUAD $0x0a011a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 1], 10 - QUAD $0x0b010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 14 + LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + LONG $0x207923c4; WORD $0x270c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r12], 1 + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r14], 4 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r13], 6 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rsi], 7 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r15], 8 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r11], 9 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r10], 10 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + r9], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rdx], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r8], 2 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r9], 3 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r10], 4 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r15], 6 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r14], 7 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rsi], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rcx], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rdx], 12 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rdx], 13 + QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + r12], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rdx], 15 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x010117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 1 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x020117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 3 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x04012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x050117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 5 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x07012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 8 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x090117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 10 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0b0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 11 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0c0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 12 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0d0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0f0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 15 + QUAD $0x01011f6c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rbx + 1], 1 + QUAD $0x0201076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 2 + QUAD $0x03010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 3 + QUAD $0x0401176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x06013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 6 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x0701376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 1], 7 + QUAD $0x0801376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 10 + QUAD $0x0b010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + QUAD $0x0e01276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 14 LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0102442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 1], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xce6e79c5 // vmovd xmm9, esi LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xd66e79c5 // vmovd xmm10, esi - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x010202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 2], 1 - QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] - QUAD $0x02020a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 2], 2 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x030212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 2], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x050202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x060202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 6 - QUAD $0x07022a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 2], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x08020a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 2], 8 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x090222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 2], 9 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0a022a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 2], 10 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x0b021a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 2], 11 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0c0232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 2], 12 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0d023a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 2], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 1 - QUAD $0x02023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0302325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0402325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0502325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0602325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x0702325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 7 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x08021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 8 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x09023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 9 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0a023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 10 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0b023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 11 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0c023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0e023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 15 - QUAD $0x010302642021a3c4 // vpinsrb xmm4, xmm11, byte [rdx + r8 + 3], 1 - QUAD $0x02030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 2 - QUAD $0x030312642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 3], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x04033a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 3], 4 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x050302642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 3], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06033a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 3], 6 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x07030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 7 - QUAD $0x08030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 8 - QUAD $0x090322642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 3], 9 - QUAD $0x0a032a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 3], 10 - QUAD $0x0b031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 11 - WORD $0x894d; BYTE $0xdc // mov r12, r11 - QUAD $0x0c0332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 3], 12 - QUAD $0x0d033a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 3], 13 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0e031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 14 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0f030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 15 - QUAD $0x0103026c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdx + rax + 3], 1 - WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x010207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 1 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x02020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03020f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 2], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x07022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 7 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0203026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0303026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0403026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0503026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0603026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 6 - QUAD $0x0703326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 7 - QUAD $0x08031a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 3], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0903026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 9 + QUAD $0x080207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 8 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x090227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 9 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0a022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 10 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0b021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 11 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0c0237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 12 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x0d023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 13 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 12 + QUAD $0x0e0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 14 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x0f021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 15 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] + QUAD $0x0102075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0202375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0302375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0402375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0502375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 5 + QUAD $0x0602175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0702375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 7 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0802175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 8 + QUAD $0x0902175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x0d02175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 13 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x0e02175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 15 + QUAD $0x010307642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r8 + 3], 1 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x02030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x03030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x04030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x05030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x06030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 6 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x07030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x08030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 8 + QUAD $0x090327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 9 + QUAD $0x0a032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 10 + QUAD $0x0b031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 11 + QUAD $0x0c0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 12 + QUAD $0x0d033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 13 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0e030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 14 + QUAD $0x0f031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 15 + QUAD $0x0103076c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rax + 3], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 13 + QUAD $0x0203076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 2 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0303076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 3], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0403076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0503076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x06033f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 3], 6 + QUAD $0x0703376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e0302442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 3], 14 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a74b60f; BYTE $0x09 // movzx esi, byte [rdx + rcx + 9] + QUAD $0x0e0317442051a3c4 // vpinsrb xmm0, xmm5, byte [rdi + r10 + 3], 14 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x09 // movzx esi, byte [rdi + rcx + 9] LONG $0xc66e79c5 // vmovd xmm8, esi - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0302442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 3], 15 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0f0327442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a74b60f; BYTE $0x09 // movzx esi, byte [rdx + rcx + 9] + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f74b60f; BYTE $0x09 // movzx esi, byte [rdi + rcx + 9] LONG $0xde6e79c5 // vmovd xmm11, esi - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x010432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 4], 1 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x02043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 2 - QUAD $0x030412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 4], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x04043a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 4], 4 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - QUAD $0x050402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 5 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x06041a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 4], 6 - QUAD $0x07040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 7 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x08040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 8 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x090402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 10 - QUAD $0x0b0422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c0432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 4], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d0432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 4], 13 - QUAD $0x0e041a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 4], 14 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x0f0422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 15 - QUAD $0x01042a5c2011a3c4 // vpinsrb xmm3, xmm13, byte [rdx + r13 + 4], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0204325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0304325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0404325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0504025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0604325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 6 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0704025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0804025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0904025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 9 + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + QUAD $0x010417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x040417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x05040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 5 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x06042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 6 + QUAD $0x07040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x090407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 10 + QUAD $0x0b041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 11 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x0c041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 12 + QUAD $0x0d0437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 13 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 10 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0b041a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 4], 11 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0c041a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 4], 12 + QUAD $0x0e0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 15 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0104075c2011e3c4 // vpinsrb xmm3, xmm13, byte [rdi + rax + 4], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 14 + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x0304075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0404075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0504075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 5 + WORD $0x894c; BYTE $0xfe // mov rsi, r15 + QUAD $0x06043f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 4], 6 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 15 - QUAD $0x010532642009a3c4 // vpinsrb xmm4, xmm14, byte [rdx + r14 + 5], 1 - QUAD $0x02053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 2 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x030512642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 5], 3 - QUAD $0x04053a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 5], 4 - QUAD $0x05050a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 5], 5 - WORD $0x8949; BYTE $0xca // mov r10, rcx - QUAD $0x06051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 6 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x07053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 7 - QUAD $0x08050a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 5], 8 - QUAD $0x090502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 9 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0a0502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b050a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 5], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 12 + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x0804375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 4], 8 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0904075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 10 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 14 - QUAD $0x0f0522642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 5], 15 - QUAD $0x01052a6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdx + r13 + 5], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0205026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 2 + QUAD $0x0b04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 11 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0c040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 12 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0d043f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 4], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 14 + QUAD $0x0f04275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 15 + QUAD $0x010517642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r10 + 5], 1 + QUAD $0x02051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 2 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x03051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 3 + QUAD $0x040517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 4 + QUAD $0x05050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 5 + QUAD $0x06052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x08050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 8 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x090517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 10 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x0b0527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 11 + QUAD $0x0c051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 12 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x0d053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 14 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0305026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0405026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0505026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 5 - QUAD $0x0605326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 5], 6 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - QUAD $0x07051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0805026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0905026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 10 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x0b052a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 5], 11 - QUAD $0x0c051a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 5], 12 - WORD $0x894d; BYTE $0xdc // mov r12, r11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 14 + QUAD $0x0f0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 15 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0105176c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdi + rdx + 5], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0205176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0405076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 4 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0505176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 5 + QUAD $0x0605376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 6 + WORD $0x8949; BYTE $0xf5 // mov r13, rsi + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0705176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 7 + QUAD $0x0805376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 5], 8 + QUAD $0x0905076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a05176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x0c050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0502442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 5], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x0a // movzx esi, byte [rdx + rax + 10] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0507442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 5], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] LONG $0xde6ef9c5 // vmovd xmm3, esi LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x0a // movzx esi, byte [rdx + rsi + 10] - LONG $0xe66ef9c5 // vmovd xmm4, esi - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x01063a442019e3c4 // vpinsrb xmm0, xmm12, byte [rdx + rdi + 6], 1 - QUAD $0x020632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 6], 2 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x030602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 3 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x040632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 6], 4 - QUAD $0x050612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 6], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x060602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 6 - QUAD $0x07063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 7 - QUAD $0x08060a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 6], 8 - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x090632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 9 - QUAD $0x0a0602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 10 - QUAD $0x0b060a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 6], 11 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0c0602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 12 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0d060a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 6], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 14 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0f0612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 6], 15 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x01060a6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdx + rcx + 6], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0206326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0306326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0406326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0506326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 6 - QUAD $0x07061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 7 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x08061a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 6], 8 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x09061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 10 - WORD $0x894d; BYTE $0xef // mov r15, r13 - QUAD $0x0b062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 11 - QUAD $0x0c06226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 13 + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] + LONG $0xe66ef9c5 // vmovd xmm4, esi + QUAD $0x010617442019a3c4 // vpinsrb xmm0, xmm12, byte [rdi + r10 + 6], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02061f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 6], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x040617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 4 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x050637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 5 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + QUAD $0x06061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 6 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x070637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 7 + QUAD $0x08060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 8 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x09060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 9 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 14 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0f062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 15 - QUAD $0x01073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 1 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x02072a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 7], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x03073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 3 - QUAD $0x040732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 7], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x05073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 5 - QUAD $0x060702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x070702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x08070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x09070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 10 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0b073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 11 - QUAD $0x0c0702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 12 - QUAD $0x0d070a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 7], 13 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0e070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 14 - QUAD $0x0f0712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 7], 15 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0107324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 7], 1 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x02070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 2 + QUAD $0x0a060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 10 + QUAD $0x0b0627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 11 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0c060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 12 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x0d063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 13 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x0e0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 14 LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x03070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 4 - QUAD $0x0507324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 6 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x07070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 7 - QUAD $0x08071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 8 - QUAD $0x09071a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 7], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 10 - QUAD $0x0b073a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 7], 11 - QUAD $0x0c07224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 7], 12 + QUAD $0x0f060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 15 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x01063f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r15 + 6], 1 LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 13 + QUAD $0x02060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 2 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x03060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 3 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x04060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0506376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 5 + QUAD $0x06062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 6 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0706376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x08060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 8 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x09060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 9 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x0a06276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 6], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 12 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x0d062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 13 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0e060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 15 + QUAD $0x010717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 1 + QUAD $0x02071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 2 + WORD $0x8949; BYTE $0xda // mov r10, rbx + QUAD $0x030707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 3 + QUAD $0x040717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x050707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 5 + QUAD $0x06071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x090707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 10 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0b071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 11 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0c0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 12 + QUAD $0x0d070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 13 + QUAD $0x0e0707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 15 + QUAD $0x01073f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 7], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0207074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0307074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0407074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 4 + QUAD $0x0507374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0707374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x09070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 9 + QUAD $0x0a07274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 11 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0c07274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 12 + QUAD $0x0d072f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e070a442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rcx + 7], 14 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a74b60f; BYTE $0x0b // movzx esi, byte [rdx + rcx + 11] + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0e070f442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rcx + 7], 14 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x0b // movzx esi, byte [rdi + rcx + 11] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0f070a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 7], 15 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f070f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a74b60f; BYTE $0x0b // movzx esi, byte [rdx + rcx + 11] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01080a442031e3c4 // vpinsrb xmm0, xmm9, byte [rdx + rcx + 8], 1 - WORD $0x894d; BYTE $0xef // mov r15, r13 - QUAD $0x02082a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 8], 2 QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x03080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x040832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 4 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x05082a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 8], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x060832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 6 - WORD $0x8949; BYTE $0xc0 // mov r8, rax - QUAD $0x070802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 8 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x090822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 8], 9 + LONG $0x0f74b60f; BYTE $0x0b // movzx esi, byte [rdi + rcx + 11] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x010837442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r14 + 8], 1 + QUAD $0x020817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 3 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x04080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 4 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x050817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 5 + QUAD $0x06081f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 8], 6 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x07081f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 8], 7 + QUAD $0x080817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 8 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x09080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 10 + QUAD $0x0b081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 11 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x0c0807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 12 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0d0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 14 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x0f083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 15 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0108176c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rdx + 8], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0208376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0308376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0408376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 4 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x05081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 5 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x06081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 6 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x07081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 7 + QUAD $0x0808076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0908076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 9 LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0a081a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 8], 10 + QUAD $0x0a081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 10 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0b081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 11 + QUAD $0x0c08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 12 + QUAD $0x0d082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 13 + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + QUAD $0x0e082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010937742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r14 + 9], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 2 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x03091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 3 + QUAD $0x04090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 4 + QUAD $0x050917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 5 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x06091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 6 + QUAD $0x07091f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 9], 7 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x08091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 8 + QUAD $0x09090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 9 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0a090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 11 + QUAD $0x0c0907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 12 QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x0b080a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 8], 11 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0c0812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 12 + QUAD $0x0d090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 13 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0e0937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 14 + QUAD $0x0f093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 15 + QUAD $0x0109177c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rdx + 9], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0209077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 2 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x03090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 3 + QUAD $0x0409377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 4 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x05090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0609177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x08090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 8 + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 10 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 15 - QUAD $0x0108326c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r14 + 8], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0208026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0308026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0408326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0508026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0608026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 6 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0708326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 7 - QUAD $0x08081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0908026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 15 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010902742039e3c4 // vpinsrb xmm6, xmm8, byte [rdx + rax + 9], 1 - QUAD $0x02093a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 9], 2 - QUAD $0x03090a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 9], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 4 - QUAD $0x05092a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r13 + 9], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x060902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 6 - QUAD $0x070902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 7 - QUAD $0x08093a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 9], 8 - QUAD $0x090922742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 9], 9 - QUAD $0x0a091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 10 - QUAD $0x0b090a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 9], 11 - QUAD $0x0c0912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 12 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x0d0912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0109027c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdx + rax + 9], 1 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x02092a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 9], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0309027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 3 - QUAD $0x0409327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 9], 4 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x05091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0609027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 6 - QUAD $0x0709327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 9], 7 - QUAD $0x08091a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 9], 8 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0909027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 14 + QUAD $0x0b09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 11 + QUAD $0x0c09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 12 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0d093f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 9], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f09026c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdx + rax + 9], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x0c // movzx esi, byte [rdi + rax + 12] LONG $0xc66ef9c5 // vmovd xmm0, esi LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x00044024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm5 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x0c // movzx esi, byte [rdi + rax + 12] LONG $0xee6ef9c5 // vmovd xmm5, esi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 1 - QUAD $0x020a3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 10], 2 - QUAD $0x030a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x040a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 4 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x050a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x060a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x070a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 7 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x080a0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 10], 8 - QUAD $0x090a225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 10], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 11 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x010a275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 10], 1 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x020a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 2 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 12 - QUAD $0x0d0a125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 10], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x010a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 1 - QUAD $0x020a2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 10], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x030a32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 10], 3 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x040a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 4 - QUAD $0x050a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 5 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x060a12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 10], 6 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - QUAD $0x070a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 7 - QUAD $0x080a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 8 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x090a2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 10], 9 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0a0a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 10 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0b0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 11 + QUAD $0x030a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 3 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x040a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 4 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 12 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0d0a22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 10], 13 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0e0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 14 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0f0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 15 + QUAD $0x050a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 5 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x060a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x080a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x090a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 11 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x0c0a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 12 + QUAD $0x0d0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 13 + QUAD $0x0e0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 15 + QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] + QUAD $0x010a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 1 + QUAD $0x020a07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 10], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x030a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 3 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 1 - QUAD $0x020b3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 11], 2 - QUAD $0x030b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 3 - QUAD $0x040b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 4 - QUAD $0x050b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x060b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x070b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 7 - QUAD $0x080b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 8 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x090b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 12 + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x050a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 5 + QUAD $0x060a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x070a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x080a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 8 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x090a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 11 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0c0a07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 10], 12 + QUAD $0x0d0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 13 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x0e0a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 14 + LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + QUAD $0x0f0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 15 + QUAD $0x010b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 1 + QUAD $0x020b1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 11], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 3 + QUAD $0x040b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 4 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x050b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 5 + QUAD $0x060b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 6 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x070b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 7 + QUAD $0x080b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 8 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x090b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 9 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0a0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 11 + QUAD $0x0c0b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 12 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0d0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0f0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 15 + QUAD $0x010b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x020b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 2 + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x040b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 4 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x050b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 5 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x060b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x070b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 7 + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x0a0b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 10 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 13 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0e0b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x010b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 1 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x020b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 11], 2 - QUAD $0x030b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 3 - QUAD $0x040b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 11], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x050b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 5 - QUAD $0x060b12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 11], 6 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x070b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x080b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 8 - QUAD $0x090b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 9 - QUAD $0x0a0b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 11], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b0b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c0b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 12 - QUAD $0x0d0b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 11], 13 + QUAD $0x0b0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 11 + QUAD $0x0c0b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 11], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000420249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm3 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0e0b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 14 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x0d // movzx esi, byte [rdx + rsi + 13] + QUAD $0x0e0b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 14 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0f0b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 15 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000400248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm1 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x0d // movzx esi, byte [rdx + rsi + 13] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x010c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 1 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x020c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 12], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x030c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 12], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x040c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 4 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x050c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 5 - QUAD $0x060c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x070c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x080c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 8 - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - QUAD $0x090c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 12], 9 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0a0c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 12], 10 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x0b0c1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 12], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 13 - QUAD $0x0e0c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 12], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 15 - QUAD $0x010c02542051e3c4 // vpinsrb xmm2, xmm5, byte [rdx + rax + 12], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x020c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 2 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x010c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 1 + QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + QUAD $0x020c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 3 + QUAD $0x040c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 4 + QUAD $0x050c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 5 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x060c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 6 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x070c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 8 + QUAD $0x090c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 9 + QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] + QUAD $0x0a0c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 10 + QUAD $0x0b0c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 11 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0c0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 12 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0d0c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 14 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x030c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 4 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x050c12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 12], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x060c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 6 - QUAD $0x070c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x080c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 8 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x090c02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 12], 9 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x0a0c1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 12], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 12 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0d0c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 13 - QUAD $0x0e0c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 15 - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x010d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 13], 1 - QUAD $0x020d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 2 - QUAD $0x030d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 13], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x050d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 13], 5 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x060d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 6 - QUAD $0x070d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 7 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x080d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 13], 8 - QUAD $0x090d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 9 - QUAD $0x0a0d325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 13], 10 - QUAD $0x0b0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 11 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0c0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 12 + QUAD $0x0f0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 15 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x010c37542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rsi + 12], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x020c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 2 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x030c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 3 + QUAD $0x040c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 4 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x050c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 5 + QUAD $0x060c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 6 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x070c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 7 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x080c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 8 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x090c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 9 + QUAD $0x0a0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 10 LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0d0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 14 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0f0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 15 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x010d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 1 - QUAD $0x020d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 2 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x030d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x040d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 4 - QUAD $0x050d124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 13], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x060d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x070d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x080d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 8 - QUAD $0x090d024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 13], 9 - QUAD $0x0a0d1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 13], 10 + QUAD $0x0b0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 11 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0c0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 12 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0d0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 13 + QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] + QUAD $0x0e0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 14 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 15 + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + QUAD $0x010d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 1 + QUAD $0x020d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 2 + QUAD $0x030d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x040d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x050d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 5 + QUAD $0x060d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 6 + QUAD $0x070d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 8 + QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] + QUAD $0x090d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 9 + QUAD $0x0a0d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 10 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0b0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 11 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0c0d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 12 + QUAD $0x0d0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 13 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0e0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 14 + QUAD $0x0f0d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 15 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x010d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 1 + QUAD $0x020d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 2 + QUAD $0x030d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x040d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 4 + QUAD $0x050d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x060d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x070d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 7 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x080d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 8 + QUAD $0x090d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 12 - QUAD $0x0d0d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 13 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - QUAD $0x0e0d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 14 + QUAD $0x0c0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + QUAD $0x0e0d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0d02442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rax + 13], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x0e // movzx esi, byte [rdx + rax + 14] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0d07442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + LONG $0x74b60f42; WORD $0x0e3f // movzx esi, byte [rdi + r15 + 14] LONG $0xce6ef9c5 // vmovd xmm1, esi LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x0e // movzx esi, byte [rdx + rax + 14] - LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x010e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 1 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x020e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 2 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x030e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x040e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 4 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x050e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 5 - QUAD $0x060e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 14], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x070e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 7 - QUAD $0x080e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 8 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x090e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 12 - QUAD $0x0d0e1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 14], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x010e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 1 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x020e1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 14], 2 - QUAD $0x030e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 4 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x050e0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 14], 5 - QUAD $0x060e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 6 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x070e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 7 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x080e1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 14], 8 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x090e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 12 + LONG $0x0774b60f; BYTE $0x0e // movzx esi, byte [rdi + rax + 14] + LONG $0xc66ef9c5 // vmovd xmm0, esi + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x020e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x030e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x040e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x050e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x060e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 6 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x070e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x080e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 8 + QUAD $0x090e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 9 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0a0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 11 + QUAD $0x0c0e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 12 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0d0e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 14], 13 + QUAD $0x0e0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 15 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x010e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 14], 1 LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x0d0e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 14], 13 - QUAD $0x0e0e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 14], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f0e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 15 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - LONG $0x74b60f42; WORD $0x0f32 // movzx esi, byte [rdx + r14 + 15] - LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x020e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x030e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 3 LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x010f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 1 - QUAD $0x020f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 15], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x030f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 3 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x040f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 15], 4 - QUAD $0x050f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 15], 5 - QUAD $0x060f22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 15], 6 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x070f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 15], 7 + QUAD $0x040e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x050e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 5 QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x080f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 8 - QUAD $0x090f2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 15], 9 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0a0f22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 15], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x0f // movzx esi, byte [rdx + rax + 15] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x010f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 1 - QUAD $0x020f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x030f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x040f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 4 - QUAD $0x050f0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 15], 5 + QUAD $0x060e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 6 + QUAD $0x070e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 7 + QUAD $0x080e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 8 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x090e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a0e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 10 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0b0e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 11 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0c0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 12 QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x060f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x070f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 7 - QUAD $0x080f1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 15], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x090f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 10 - QUAD $0x0b0f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 11 + QUAD $0x0d0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 13 + QUAD $0x0e0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 15 + LONG $0x74b60f42; WORD $0x0f3f // movzx esi, byte [rdi + r15 + 15] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x010f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 1 + QUAD $0x020f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x030f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 3 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x040f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 4 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 12 - QUAD $0x0d0f025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 15], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 14 - QUAD $0x0f0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 15 + QUAD $0x050f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x060f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x070f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 7 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x080f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x090f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 9 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0a0f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 10 + QUAD $0x0b0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 11 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0c0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 12 + QUAD $0x0d0f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 13 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0e0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 14 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0f0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 15 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f74b60f; BYTE $0x0f // movzx esi, byte [rdi + rcx + 15] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x010f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 1 + QUAD $0x020f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 2 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x030f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x040f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 4 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x050f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 5 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x060f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x070f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 7 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x080f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x090f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 9 + QUAD $0x0a0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 10 + QUAD $0x0b0f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 11 + QUAD $0x0c0f1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 15], 12 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0d0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 13 + QUAD $0x0e0f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - LONG $0x74b60f42; WORD $0x1032 // movzx esi, byte [rdx + r14 + 16] + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1774b60f; BYTE $0x10 // movzx esi, byte [rdi + rdx + 16] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01100a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 16], 1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x021002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 3 - QUAD $0x041012442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 16], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 6 - QUAD $0x07103a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 16], 7 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - QUAD $0x08101a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 16], 8 - QUAD $0x09102a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 16], 9 - QUAD $0x0a1022442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 16], 10 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x011017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 1 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x021017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x031017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 3 + QUAD $0x04103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x051017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 5 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x061037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 6 + QUAD $0x071007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 7 + QUAD $0x08100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 8 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x09100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 9 + QUAD $0x0a1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0c101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 12 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 13 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0e1032442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 16], 14 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x0f1002442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 16], 15 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1a74b60f; BYTE $0x10 // movzx esi, byte [rdx + rbx + 16] + QUAD $0x0d1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 15 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + LONG $0x74b60f42; WORD $0x1017 // movzx esi, byte [rdi + r10 + 16] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x0110124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 16], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0210324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 2 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x03103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 3 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0410324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 4 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x05103a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 16], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0610324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 6 - QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] - QUAD $0x07100a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 16], 7 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x08102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 8 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0910324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 9 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0a10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 10 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0b10224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 16], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 13 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0e10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 14 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x11 // movzx esi, byte [rdx + rsi + 17] - LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x01110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 1 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x02110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 2 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x03110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 3 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x01101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0210074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 2 + QUAD $0x0310074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + QUAD $0x05102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x06103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 6 + QUAD $0x07100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 7 + QUAD $0x0810274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 8 LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x04110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 4 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x05110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x06110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x07110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 7 - QUAD $0x08111a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 17], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x09110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 9 + QUAD $0x09100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 9 LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 11 - QUAD $0x0c1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 13 - QUAD $0x0e1132542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 17], 14 - QUAD $0x0f1102542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 17], 15 - LONG $0x1a74b60f; BYTE $0x11 // movzx esi, byte [rdx + rbx + 17] + QUAD $0x0a100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 12 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0d10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 13 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x0e10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0f102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3774b60f; BYTE $0x11 // movzx esi, byte [rdi + rsi + 17] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x011137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 1 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x021137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x031137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 4 + QUAD $0x051117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 5 + QUAD $0x061137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 6 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x071117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 7 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x081127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 8 + QUAD $0x09110f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 17], 9 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0a1117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 10 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0b1117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 11 + QUAD $0x0c111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 12 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x0d110f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 17], 13 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x0e1107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 14 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0f1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 15 + LONG $0x74b60f42; WORD $0x1117 // movzx esi, byte [rdi + r10 + 17] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0111125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 17], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0211025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 2 - QUAD $0x03113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 3 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x04113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 4 - QUAD $0x05113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 5 + QUAD $0x01111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0211175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 2 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0311175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 3 + QUAD $0x0411075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + QUAD $0x06113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0711075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a11175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b11175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 11 + QUAD $0x0c110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 12 QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x06113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 6 - QUAD $0x07110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 7 - QUAD $0x08112a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 17], 8 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0911025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 17], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 10 - QUAD $0x0b11225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 17], 11 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x0c110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 14 + QUAD $0x0d113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 13 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0e110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f1102442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rax + 17], 15 + QUAD $0x0f112f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r13 + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - LONG $0x1a74b60f; BYTE $0x12 // movzx esi, byte [rdx + rbx + 18] + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + LONG $0x1774b60f; BYTE $0x12 // movzx esi, byte [rdi + rdx + 18] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x011202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 1 - QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] - QUAD $0x021232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 18], 2 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x031212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 4 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x05121a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 18], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x071202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 8 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x091202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b1202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 13 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x0e1222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 18], 14 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0f122a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 18], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x12 // movzx esi, byte [rdx + rsi + 18] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0112324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0212324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0312324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 3 - QUAD $0x04123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0512324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 5 - QUAD $0x06123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 6 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x07123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0812324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 8 - QUAD $0x0912024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 9 - QUAD $0x0a120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 11 - QUAD $0x0c120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 13 + QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] + QUAD $0x01121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 1 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x02121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x04120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x05120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x06120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 6 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x071217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 7 + QUAD $0x081227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 8 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x091227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 9 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 14 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0f120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 15 - LONG $0x1a74b60f; BYTE $0x13 // movzx esi, byte [rdx + rbx + 19] - LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0a120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 11 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0c120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 12 + QUAD $0x0d120f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 18], 13 + QUAD $0x0e1207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 18], 14 + QUAD $0x0f1237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 15 + QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] + LONG $0x74b60f42; WORD $0x120f // movzx esi, byte [rdi + r9 + 18] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x01120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0212074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 2 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0312374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 3 LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x01130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 1 - QUAD $0x021332542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 19], 2 - QUAD $0x031312542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 19], 3 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x04130a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 19], 4 - QUAD $0x05131a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 19], 5 + QUAD $0x04120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 4 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x05122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 5 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x06120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 7 QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x06130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 6 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x071302542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 19], 7 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x081332542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 19], 8 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x091312542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 19], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1332542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 19], 10 - QUAD $0x0b1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 12 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0d131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 13 - QUAD $0x0e1322542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 19], 14 - QUAD $0x0f132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x0274b60f; BYTE $0x13 // movzx esi, byte [rdx + rax + 19] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x01131a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 19], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0213025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0313025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 3 - QUAD $0x04133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0513025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 6 - QUAD $0x07133a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 19], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0813025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 8 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0913025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 10 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 15 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 - QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x14 // movzx esi, byte [rdx + rax + 20] - LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x011422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 20], 1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x021402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 3 - QUAD $0x04140a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 20], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 5 - QUAD $0x06140a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 20], 6 - QUAD $0x071402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 20], 7 - QUAD $0x081432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 20], 8 - QUAD $0x091412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 20], 9 + QUAD $0x08120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 8 + QUAD $0x0912074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 9 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b140a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 20], 11 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0c142a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 20], 12 - QUAD $0x0d141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 13 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0e141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 14 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0f140a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 20], 15 - QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] - LONG $0x74b60f42; WORD $0x140a // movzx esi, byte [rdx + r9 + 20] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x01141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 1 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0214024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 20], 2 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x03143a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 20], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 4 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x05140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 5 - QUAD $0x06143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 6 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x0714324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0814324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 8 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0914324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 9 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x0a14124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b14324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 11 + QUAD $0x0a12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 12 + QUAD $0x0d123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 13 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0e123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 15 + LONG $0x1774b60f; BYTE $0x13 // movzx esi, byte [rdi + rdx + 19] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x01131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 1 + QUAD $0x02131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x031317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 4 LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c14324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 12 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0d143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 13 + QUAD $0x051337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 5 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x061337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 6 + QUAD $0x071317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x081337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 8 + QUAD $0x091327542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 19], 9 QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0e14324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 14 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0f14324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 20], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x15 // movzx esi, byte [rdx + rsi + 21] - LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x011522542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 21], 1 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 2 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x03151a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 21], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x041532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 4 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x051532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 6 + QUAD $0x0a1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 11 QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x071532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x081532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 8 - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x091532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 9 - QUAD $0x0a1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 11 - QUAD $0x0c152a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 21], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 13 - QUAD $0x0e151a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 21], 14 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0f152a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 21], 15 - LONG $0x74b60f42; WORD $0x150a // movzx esi, byte [rdx + r9 + 21] + QUAD $0x0c1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 15 + LONG $0x74b60f42; WORD $0x130f // movzx esi, byte [rdi + r9 + 19] LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x01130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 1 + QUAD $0x0213075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 2 + QUAD $0x0313375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 3 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x04131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 4 + QUAD $0x05132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 5 + QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] + QUAD $0x0613075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0713375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 7 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0813175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 19], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0913375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a13375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 10 + QUAD $0x0b130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 12 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x0d13275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 13 + QUAD $0x0e133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 14 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 15 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 + LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 + QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x14 // movzx esi, byte [rdi + rcx + 20] + LONG $0xc66ef9c5 // vmovd xmm0, esi + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x01143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 1 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x02140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 2 + QUAD $0x031417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 3 + QUAD $0x041407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x061407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 6 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0115025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 1 - QUAD $0x0215025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 21], 2 - QUAD $0x03153a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 21], 3 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x04150a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 21], 4 - QUAD $0x05150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0615025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 6 + QUAD $0x071407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 7 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x081437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x091407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 11 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0c1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 12 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0d1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x14 // movzx esi, byte [rdi + rax + 20] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x01140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + QUAD $0x04141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 4 + QUAD $0x05142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 5 + QUAD $0x0614074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 6 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x07140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 7 + QUAD $0x0814174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0914074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 11 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x0c141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 12 + QUAD $0x0d14274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 20], 13 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0715025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0815025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 8 - QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] - QUAD $0x0915225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 21], 9 - QUAD $0x0a15125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 10 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0b151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 11 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0c150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 12 - QUAD $0x0d153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 13 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0e150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 14 + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 + QUAD $0x0f141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3774b60f; BYTE $0x15 // movzx esi, byte [rdi + rsi + 21] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x01153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 1 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x021537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x031537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 4 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x05153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 5 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x06151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 6 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x071537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 7 + QUAD $0x081537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 8 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x091517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 9 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0a1537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 11 + QUAD $0x0c1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 12 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0d1527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0f1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 15 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + LONG $0x1774b60f; BYTE $0x15 // movzx esi, byte [rdi + rdx + 21] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0115175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0215375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0315375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0415375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 4 + QUAD $0x05152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 5 + QUAD $0x0615075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 6 + QUAD $0x07150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 7 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0815375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0915375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 9 + QUAD $0x0a150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 11 + QUAD $0x0c151f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 21], 12 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x0d15375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 13 + QUAD $0x0e15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x0f1532442061a3c4 // vpinsrb xmm0, xmm3, byte [rdx + r14 + 21], 15 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f1507442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - LONG $0x74b60f42; WORD $0x1612 // movzx esi, byte [rdx + r10 + 22] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x16 // movzx esi, byte [rdi + rax + 22] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x01163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 1 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - QUAD $0x021602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 22], 2 - QUAD $0x03161a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 22], 3 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x04160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 4 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x05160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 5 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x061632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 22], 6 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x07161a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 22], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x09160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 12 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x01160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 1 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x021607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 2 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x03160f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 22], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 4 + QUAD $0x05163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 5 + QUAD $0x06161f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 22], 6 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x07163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 8 + QUAD $0x091617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 10 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0c1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 12 + QUAD $0x0d1627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x0e1627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 14 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x0f1617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0774b60f; BYTE $0x16 // movzx esi, byte [rdi + rax + 22] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x0116174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 1 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x02161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 2 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0316174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0416074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 4 + QUAD $0x05162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 5 + QUAD $0x0616074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 6 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x07161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0916074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 9 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 10 LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 13 + QUAD $0x0b16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 12 + QUAD $0x0d16374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 22], 13 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x0e16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 14 LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 14 - QUAD $0x0f162a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 22], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x16 // movzx esi, byte [rdx + rsi + 22] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0116324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0216324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0316324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 3 - QUAD $0x04160a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 22], 4 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x05162a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 22], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0616324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 6 - QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] - QUAD $0x07160a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 22], 7 - QUAD $0x0816024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 8 - QUAD $0x0916224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 22], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 10 - QUAD $0x0b161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 11 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x0c16224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 22], 12 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 13 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 15 - LONG $0x74b60f42; WORD $0x1712 // movzx esi, byte [rdx + r10 + 23] + QUAD $0x0f16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 15 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + LONG $0x74b60f42; WORD $0x1737 // movzx esi, byte [rdi + r14 + 23] LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x01173a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 23], 1 - QUAD $0x021702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 23], 2 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x031712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 23], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 5 - QUAD $0x061732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 23], 6 - QUAD $0x07171a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 23], 7 - QUAD $0x08173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 8 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x091732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 23], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 10 - QUAD $0x0b170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 11 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c1702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 12 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0d171a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 23], 13 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0e171a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 23], 14 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0f1702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 15 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - LONG $0x74b60f42; WORD $0x173a // movzx esi, byte [rdx + r15 + 23] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x01170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0217025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 23], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0317325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 3 + QUAD $0x01170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 1 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x02170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 2 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + QUAD $0x03170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 3 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x04170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 4 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x051737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 5 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x061737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 6 + QUAD $0x07173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x081737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 8 QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0417325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 4 - QUAD $0x05172a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 23], 5 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x06172a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 23], 6 - QUAD $0x07170a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 23], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0817325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 8 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0917025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 23], 9 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0a17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 11 - QUAD $0x0c17225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 23], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 13 + QUAD $0x091737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 9 QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0e17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 14 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 15 + QUAD $0x0a1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 11 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0c1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 13 + QUAD $0x0e1727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 14 + QUAD $0x0f1717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x17 // movzx esi, byte [rdi + rsi + 23] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0117375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 1 + QUAD $0x02171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 2 + QUAD $0x0317175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 3 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x04173f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 23], 4 + QUAD $0x05172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0617175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 6 + QUAD $0x07171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 7 + QUAD $0x0817075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 8 + QUAD $0x0917075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 9 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c17375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 12 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x0d17175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 23], 13 + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + QUAD $0x0e172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 14 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x18 // movzx esi, byte [rdx + rsi + 24] + LONG $0x74b60f42; WORD $0x1837 // movzx esi, byte [rdi + r14 + 24] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x011832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 1 QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 2 - QUAD $0x031812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 24], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x041832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 4 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x051832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x071832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x081832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 8 - QUAD $0x091832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 9 - QUAD $0x0a183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 10 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0b1832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 12 - QUAD $0x0d181a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 24], 13 - QUAD $0x0e181a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 24], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 15 - LONG $0x74b60f42; WORD $0x183a // movzx esi, byte [rdx + r15 + 24] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x01180a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 24], 1 - QUAD $0x0218024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0318024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 3 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x0418224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 24], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0518024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 5 - QUAD $0x06182a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 24], 6 - QUAD $0x07180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 7 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x08183a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 24], 8 - QUAD $0x0918024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a18024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 10 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x0b18024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 11 + QUAD $0x011837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 1 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x02181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 2 + QUAD $0x03180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 3 + QUAD $0x04180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 4 LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0c180a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 24], 12 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0d18124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 13 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0e183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 14 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0f181a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 24], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x19 // movzx esi, byte [rdx + rax + 25] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x01192a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 25], 1 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x041932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 4 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x05191a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 25], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x071932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 7 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x081932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 8 + QUAD $0x05180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 5 QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x091932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 10 - QUAD $0x0b1932542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 25], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3274b60f; BYTE $0x19 // movzx esi, byte [rdx + rsi + 25] - LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x061837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 6 QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0119325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 1 + QUAD $0x071837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 7 LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0219325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0319325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 3 - QUAD $0x0419225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 25], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0519325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0619325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 6 - QUAD $0x07190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 7 - QUAD $0x08193a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 25], 8 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x09193a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 25], 9 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0a190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 10 - QUAD $0x0b19025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 11 - QUAD $0x0c190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 12 - QUAD $0x0d19125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 25], 13 - QUAD $0x0e193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 14 - LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 - QUAD $0x0f191a442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rbx + 25], 15 - LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 - LONG $0x0274b60f; BYTE $0x1a // movzx esi, byte [rdx + rax + 26] - LONG $0xc66ef9c5 // vmovd xmm0, esi - QUAD $0x011a2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 26], 1 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x021a12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 26], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 4 - QUAD $0x051a1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 26], 5 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x061a1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 26], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x071a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 7 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x081a32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 26], 8 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x091a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 10 + QUAD $0x081837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x091837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 9 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0a1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 10 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0b1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 11 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x0c1827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 12 QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0b1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 11 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0c1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 13 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 14 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0f1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a74b60f; BYTE $0x1a // movzx esi, byte [rdx + rdi + 26] + QUAD $0x0d1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 14 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x0f180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x18 // movzx esi, byte [rdi + rsi + 24] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x011a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 1 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x021a024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 26], 2 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x031a1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 26], 3 - QUAD $0x041a224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 26], 4 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x051a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x061a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 6 - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x071a224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 26], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x081a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 8 - QUAD $0x091a3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 26], 9 - QUAD $0x0a1a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 10 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 11 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 12 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0118374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 1 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 13 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x0e1a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 14 + QUAD $0x0218374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0318374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 3 + QUAD $0x04183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 4 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + QUAD $0x05183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x0618374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x1b // movzx esi, byte [rdx + rsi + 27] + QUAD $0x0718374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 7 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0818374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0918374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 9 + QUAD $0x0a18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 10 + QUAD $0x0b18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 12 + WORD $0x894d; BYTE $0xd6 // mov r14, r10 + QUAD $0x0d18174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 13 + QUAD $0x0e182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 14 + QUAD $0x0f181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x19 // movzx esi, byte [rdi + rax + 25] LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x011b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 27], 1 - QUAD $0x021b12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 27], 2 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 3 - QUAD $0x041b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 4 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x051b12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 27], 5 - QUAD $0x061b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 27], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x071b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 7 - QUAD $0x081b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 27], 8 - QUAD $0x091b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 10 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0b1b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 27], 11 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0c1b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 14 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0f1b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 27], 15 - LONG $0x3a74b60f; BYTE $0x1b // movzx esi, byte [rdx + rdi + 27] + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + QUAD $0x01191f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 25], 1 + QUAD $0x02191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 2 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x03191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 4 + QUAD $0x05190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 5 + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + QUAD $0x061917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x071907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x09192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0a1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 10 + QUAD $0x0b1907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 11 + QUAD $0x0c1927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 12 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0d1927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + QUAD $0x0f190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 15 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + LONG $0x1774b60f; BYTE $0x19 // movzx esi, byte [rdi + rdx + 25] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x011b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 1 - QUAD $0x021b025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 27], 2 - QUAD $0x031b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 3 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x041b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 4 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x051b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 5 - QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x061b3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 27], 6 - QUAD $0x071b225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 27], 7 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x081b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 8 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x091b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 9 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0a1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0319075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0419075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 4 + QUAD $0x05193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x08190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0919075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 9 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x0a190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 10 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0b19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 11 QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0b1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 11 + QUAD $0x0c19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 12 + QUAD $0x0d19375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 25], 13 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0e193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 14 + LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0f1937442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r14 + 25], 15 + LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + LONG $0x3774b60f; BYTE $0x1a // movzx esi, byte [rdi + rsi + 26] + LONG $0xc66ef9c5 // vmovd xmm0, esi + QUAD $0x011a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 1 + QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + QUAD $0x021a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 2 + QUAD $0x031a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 4 LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 13 - QUAD $0x0e1b0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 27], 14 + QUAD $0x051a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 5 + QUAD $0x061a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 6 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x071a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 7 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x081a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 8 + QUAD $0x091a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 9 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0a1a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 11 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0c1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 12 + QUAD $0x0d1a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 15 + LONG $0x1774b60f; BYTE $0x1a // movzx esi, byte [rdi + rdx + 26] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x011a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x021a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 2 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x031a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 3 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x041a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x051a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x061a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 15 + QUAD $0x071a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 7 + QUAD $0x081a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 8 + QUAD $0x091a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 9 + QUAD $0x0a1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 10 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x0b1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x0d1a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 13 + QUAD $0x0e1a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 14 + QUAD $0x0f1a374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 26], 15 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x1b // movzx esi, byte [rdi + rcx + 27] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x011b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 1 + QUAD $0x021b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 27], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x031b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x041b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 4 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x051b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 5 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x061b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 6 + QUAD $0x071b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 7 + QUAD $0x081b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 8 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x091b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 9 + QUAD $0x0a1b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 10 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0b1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 11 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x0c1b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x1b // movzx esi, byte [rdi + rsi + 27] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x011b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x021b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x031b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 3 + QUAD $0x041b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 4 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x051b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x061b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x071b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 7 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x081b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 8 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x091b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 9 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x0a1b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 10 + QUAD $0x0b1b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 11 + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0d1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0e1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x1c // movzx esi, byte [rdx + rsi + 28] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0774b60f; BYTE $0x1c // movzx esi, byte [rdi + rax + 28] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x011c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 1 - QUAD $0x021c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 3 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x041c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 28], 4 - QUAD $0x051c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 28], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 6 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x071c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 7 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x081c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 28], 8 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x091c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 10 - QUAD $0x0b1c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 28], 11 - QUAD $0x0c1c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 12 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0d1c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 28], 13 - QUAD $0x0e1c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 28], 14 - QUAD $0x0f1c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 28], 15 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x74b60f42; WORD $0x1c1a // movzx esi, byte [rdx + r11 + 28] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x011c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x021c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x031c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 3 - QUAD $0x041c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 4 - QUAD $0x051c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 5 - QUAD $0x061c3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 28], 6 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x071c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 7 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x081c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 8 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x091c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 9 + QUAD $0x011c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 1 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x021c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x031c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 3 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x041c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 4 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x051c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 5 + QUAD $0x061c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 6 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x071c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 7 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x081c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 8 + QUAD $0x091c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 9 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0a1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 10 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0b1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 11 + QUAD $0x0c1c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 12 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0d1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 13 LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 11 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0c1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 12 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0d1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 13 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x0e1c124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 28], 14 + QUAD $0x0e1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 14 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0f1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 15 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f74b60f; BYTE $0x1c // movzx esi, byte [rdi + rcx + 28] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x011c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 1 + QUAD $0x021c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 2 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x031c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 3 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x041c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 4 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x051c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x061c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0f1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x3274b60f; BYTE $0x1d // movzx esi, byte [rdx + rsi + 29] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x011d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 1 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x021d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 3 - QUAD $0x041d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 4 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x051d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 5 + QUAD $0x071c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 7 QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 6 - QUAD $0x071d2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 29], 7 - QUAD $0x081d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 8 - QUAD $0x091d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 10 - QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] - QUAD $0x0b1d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 11 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0c1d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 12 - QUAD $0x0d1d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 13 + QUAD $0x081c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x091c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 9 + QUAD $0x0a1c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 10 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x0b1c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 11 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0c1c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 12 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0d1c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 13 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x0e1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 14 LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0e1d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 14 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0f1d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 15 - LONG $0x74b60f42; WORD $0x1d1a // movzx esi, byte [rdx + r11 + 29] + QUAD $0x0f1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 15 + LONG $0x0774b60f; BYTE $0x1d // movzx esi, byte [rdi + rax + 29] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x011d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 1 + QUAD $0x021d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x031d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 3 + QUAD $0x041d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x051d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 5 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + QUAD $0x061d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 6 + QUAD $0x071d17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 29], 7 + QUAD $0x081d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x091d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 9 + QUAD $0x0a1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 10 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0b1d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 11 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0c1d17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 29], 12 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0d1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 13 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0e1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 14 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0f1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3774b60f; BYTE $0x1d // movzx esi, byte [rdi + rsi + 29] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x011d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 1 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x021d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 2 - QUAD $0x031d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 3 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x041d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x051d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 5 - QUAD $0x061d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 29], 6 - QUAD $0x071d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x081d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 8 - QUAD $0x091d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 29], 9 - WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 10 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0b1d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 11 - QUAD $0x0c1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0d1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 13 - QUAD $0x0e1d12642061a3c4 // vpinsrb xmm4, xmm3, byte [rdx + r10 + 29], 14 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x011d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x021d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 2 + QUAD $0x031d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 3 + QUAD $0x041d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 29], 4 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x051d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 5 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x061d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x071d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 7 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x081d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 8 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x091d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 9 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a1d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 10 + QUAD $0x0b1d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 11 + QUAD $0x0c1d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 12 + QUAD $0x0d1d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 29], 13 + QUAD $0x0e1d1f642061e3c4 // vpinsrb xmm4, xmm3, byte [rdi + rbx + 29], 14 + WORD $0x8949; BYTE $0xdc // mov r12, rbx LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0f1d12442059a3c4 // vpinsrb xmm0, xmm4, byte [rdx + r10 + 29], 15 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f1d1f442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rbx + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x0274b60f; BYTE $0x1e // movzx esi, byte [rdx + rax + 30] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f74b60f; BYTE $0x1e // movzx esi, byte [rdi + rcx + 30] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x011e1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 30], 1 - LONG $0x0274b60f; BYTE $0x1f // movzx esi, byte [rdx + rax + 31] + QUAD $0x011e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 1 + LONG $0x0f74b60f; BYTE $0x1f // movzx esi, byte [rdi + rcx + 31] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x011f1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 31], 1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x021e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 2 - QUAD $0x021f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 3 - QUAD $0x031f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x041e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 4 - QUAD $0x041f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 4 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x051e0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 30], 5 - QUAD $0x051f0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 31], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 6 - QUAD $0x061f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x071e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 7 - QUAD $0x071f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 7 - QUAD $0x00000110249c8b48 // mov rbx, qword [rsp + 272] - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 8 - QUAD $0x081f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 8 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x091e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 9 - QUAD $0x091f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 10 - QUAD $0x0a1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 10 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x0b1e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 30], 11 - QUAD $0x0b1f024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 31], 11 - QUAD $0x0c1e22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 30], 12 - QUAD $0x0c1f224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 31], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 13 - QUAD $0x0d1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0e1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 14 - QUAD $0x0e1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 14 - QUAD $0x0f1e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 30], 15 - QUAD $0x0f1f32542071a3c4 // vpinsrb xmm2, xmm1, byte [rdx + r14 + 31], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x3244b60f; BYTE $0x1e // movzx eax, byte [rdx + rsi + 30] - LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x011e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 30], 1 - LONG $0x3244b60f; BYTE $0x1f // movzx eax, byte [rdx + rsi + 31] - LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f1a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 31], 1 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x021e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 2 - QUAD $0x021f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x031e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 3 - QUAD $0x031f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 3 - QUAD $0x041e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 30], 4 - QUAD $0x041f2a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 31], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x051e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 5 - QUAD $0x051f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x061e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 6 - QUAD $0x061f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 6 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x071e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 7 - QUAD $0x071f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 7 + QUAD $0x011f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 1 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 8 - QUAD $0x091e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 30], 9 - QUAD $0x091f3a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r15 + 31], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 10 - QUAD $0x0b1e3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 30], 11 - QUAD $0x0b1f3a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rdi + 31], 11 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0c1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 12 - QUAD $0x0c1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 12 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x0d1e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 30], 13 - QUAD $0x0d1f0a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 31], 13 + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + QUAD $0x051e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 30], 5 + QUAD $0x051f174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 31], 5 + QUAD $0x061e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 6 + QUAD $0x061f0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 31], 6 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x0000011024b48b48 // mov rsi, qword [rsp + 272] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 14 - QUAD $0x0f1e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 30], 15 - QUAD $0x0f1f127c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r10 + 31], 15 + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x0b1e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 30], 11 + QUAD $0x0b1f1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 31], 11 + QUAD $0x0c1e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 30], 12 + QUAD $0x0c1f174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 31], 12 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + QUAD $0x0e1e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 30], 14 + QUAD $0x0e1f374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 31], 14 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0f1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542071e3c4 // vpinsrb xmm2, xmm1, byte [rdi + rax + 31], 15 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x011e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] + LONG $0xf86ef9c5 // vmovd xmm7, eax + QUAD $0x011f077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 31], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 4 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x091e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 9 + QUAD $0x091f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 9 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0b1e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 11 + QUAD $0x0b1f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x0d1e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 30], 13 + QUAD $0x0d1f3f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 31], 13 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x0e1e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 14 + QUAD $0x0e1f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 14 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x0f1e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 15 + QUAD $0x0f1f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -17362,21 +17817,21 @@ LBB2_170: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x447ffec5; WORD $0x608b // vmovdqu yword [rbx + 4*rcx + 96], ymm0 - LONG $0x547ffec5; WORD $0x408b // vmovdqu yword [rbx + 4*rcx + 64], ymm2 - LONG $0x647ffec5; WORD $0x208b // vmovdqu yword [rbx + 4*rcx + 32], ymm4 - LONG $0x0c7ffec5; BYTE $0x8b // vmovdqu yword [rbx + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608e // vmovdqu yword [rsi + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408e // vmovdqu yword [rsi + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208e // vmovdqu yword [rsi + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8e // vmovdqu yword [rsi + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB2_170 - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - QUAD $0x0000018024bc3b4c // cmp r15, qword [rsp + 384] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - QUAD $0x0000019024a48b4c // mov r12, qword [rsp + 400] - JNE LBB2_114 - JMP LBB2_133 + JNE LBB2_194 + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + LONG $0x24648b44; BYTE $0x1c // mov r12d, dword [rsp + 28] + QUAD $0x0000019024b48b48 // mov rsi, qword [rsp + 400] + JNE LBB2_153 + JMP LBB2_157 TEXT ·_comparison_not_equal_arr_arr_avx2(SB), $80-48 @@ -17388,96 +17843,110 @@ TEXT ·_comparison_not_equal_arr_arr_avx2(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x8944; BYTE $0xc8 // mov eax, r9d - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB3_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB3_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB3_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB3_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB3_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_22 - WORD $0x9848 // cdqe - -LBB3_20: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_20 - LONG $0x01c48349 // add r12, 1 - -LBB3_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_26 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB3_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB3_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB3_24: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_26: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_28: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_32 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_30: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5950f41 // setne r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3950f41 // setne r11b @@ -17486,21 +17955,21 @@ LBB3_24: LONG $0xd7950f41 // setne r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2950f41 // setne r10b @@ -17511,143 +17980,143 @@ LBB3_24: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4950f41 // setne r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1950f41 // setne r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_24 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_30 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_28: +LBB3_34: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -17655,107 +18124,123 @@ LBB3_28: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_28 - JMP LBB3_123 - -LBB3_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB3_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB3_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB3_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_50 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB3_48: - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xcb08 // or bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB3_48 - LONG $0x01c48349 // add r12, 1 - -LBB3_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_54 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB3_52: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_34 + JMP LBB3_153 + +LBB3_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB3_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB3_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB3_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + +LBB3_58: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x107ba1c4; WORD $0xf604 // vmovsd xmm0, qword [rsi + 8*r14] + LONG $0x2e79a1c4; WORD $0xf204 // vucomisd xmm0, qword [rdx + 8*r14] + LONG $0xd29a0f41 // setp r10b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0x0844; BYTE $0xd3 // or bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xf8c38349 // add r11, -8 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB3_58 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB3_60: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_62: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_66 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_64: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] LONG $0x4610fbc5; BYTE $0x08 // vmovsd xmm0, qword [rsi + 8] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x4610fbc5; BYTE $0x10 // vmovsd xmm0, qword [rsi + 16] LONG $0x422ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rdx + 16] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x4610fbc5; BYTE $0x18 // vmovsd xmm0, qword [rsi + 24] LONG $0x422ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rdx + 24] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x4610fbc5; BYTE $0x20 // vmovsd xmm0, qword [rsi + 32] LONG $0x422ef9c5; BYTE $0x20 // vucomisd xmm0, qword [rdx + 32] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x4610fbc5; BYTE $0x28 // vmovsd xmm0, qword [rsi + 40] LONG $0x422ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rdx + 40] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -17771,13 +18256,13 @@ LBB3_52: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x4610fbc5; BYTE $0x40 // vmovsd xmm0, qword [rsi + 64] LONG $0x422ef9c5; BYTE $0x40 // vucomisd xmm0, qword [rdx + 64] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x4610fbc5; BYTE $0x48 // vmovsd xmm0, qword [rsi + 72] LONG $0x422ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rdx + 72] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -17788,117 +18273,116 @@ LBB3_52: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x4610fbc5; BYTE $0x58 // vmovsd xmm0, qword [rsi + 88] LONG $0x422ef9c5; BYTE $0x58 // vucomisd xmm0, qword [rdx + 88] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x4610fbc5; BYTE $0x60 // vmovsd xmm0, qword [rsi + 96] LONG $0x422ef9c5; BYTE $0x60 // vucomisd xmm0, qword [rdx + 96] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x4610fbc5; BYTE $0x68 // vmovsd xmm0, qword [rsi + 104] LONG $0x422ef9c5; BYTE $0x68 // vucomisd xmm0, qword [rdx + 104] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x4610fbc5; BYTE $0x70 // vmovsd xmm0, qword [rsi + 112] LONG $0x422ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rdx + 112] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x4610fbc5; BYTE $0x78 // vmovsd xmm0, qword [rsi + 120] LONG $0x422ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rdx + 120] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl QUAD $0x000000808610fbc5 // vmovsd xmm0, qword [rsi + 128] QUAD $0x00000080822ef9c5 // vucomisd xmm0, qword [rdx + 128] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl QUAD $0x000000888610fbc5 // vmovsd xmm0, qword [rsi + 136] QUAD $0x00000088822ef9c5 // vucomisd xmm0, qword [rdx + 136] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl QUAD $0x000000908610fbc5 // vmovsd xmm0, qword [rsi + 144] QUAD $0x00000090822ef9c5 // vucomisd xmm0, qword [rdx + 144] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl QUAD $0x000000988610fbc5 // vmovsd xmm0, qword [rsi + 152] QUAD $0x00000098822ef9c5 // vucomisd xmm0, qword [rdx + 152] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al QUAD $0x000000a08610fbc5 // vmovsd xmm0, qword [rsi + 160] QUAD $0x000000a0822ef9c5 // vucomisd xmm0, qword [rdx + 160] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl QUAD $0x000000a88610fbc5 // vmovsd xmm0, qword [rsi + 168] QUAD $0x000000a8822ef9c5 // vucomisd xmm0, qword [rdx + 168] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl QUAD $0x000000b08610fbc5 // vmovsd xmm0, qword [rsi + 176] QUAD $0x000000b0822ef9c5 // vucomisd xmm0, qword [rdx + 176] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl QUAD $0x000000b88610fbc5 // vmovsd xmm0, qword [rsi + 184] QUAD $0x000000b8822ef9c5 // vucomisd xmm0, qword [rdx + 184] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al QUAD $0x000000c08610fbc5 // vmovsd xmm0, qword [rsi + 192] QUAD $0x000000c0822ef9c5 // vucomisd xmm0, qword [rdx + 192] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl QUAD $0x000000c88610fbc5 // vmovsd xmm0, qword [rsi + 200] QUAD $0x000000c8822ef9c5 // vucomisd xmm0, qword [rdx + 200] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al QUAD $0x000000d08610fbc5 // vmovsd xmm0, qword [rsi + 208] QUAD $0x000000d0822ef9c5 // vucomisd xmm0, qword [rdx + 208] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0xd6950f41 // setne r14b + WORD $0x0841; BYTE $0xc6 // or r14b, al QUAD $0x000000d88610fbc5 // vmovsd xmm0, qword [rsi + 216] QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al QUAD $0x000000e08610fbc5 // vmovsd xmm0, qword [rsi + 224] QUAD $0x000000e0822ef9c5 // vucomisd xmm0, qword [rdx + 224] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl QUAD $0x000000e88610fbc5 // vmovsd xmm0, qword [rsi + 232] QUAD $0x000000e8822ef9c5 // vucomisd xmm0, qword [rdx + 232] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl QUAD $0x000000f08610fbc5 // vmovsd xmm0, qword [rsi + 240] QUAD $0x000000f0822ef9c5 // vucomisd xmm0, qword [rdx + 240] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -17910,109 +18394,107 @@ LBB3_52: WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd0950f41 // setne r8b WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0841; BYTE $0xce // or r14b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x74b60f44; WORD $0x0324 // movzx r14d, byte [rsp + 3] - WORD $0x0845; BYTE $0xee // or r14b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xda // or r10b, bl + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xd1 // or cl, r10b - LONG $0x24348845 // mov byte [r12], r14b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB3_52 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_64 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_56: +LBB3_68: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x0410fbc5; BYTE $0xce // vmovsd xmm0, qword [rsi + 8*rcx] LONG $0x042ef9c5; BYTE $0xca // vucomisd xmm0, qword [rdx + 8*rcx] @@ -18022,98 +18504,122 @@ LBB3_56: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB3_56 - JMP LBB3_123 + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB3_68 + JMP LBB3_153 LBB3_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB3_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_8 - WORD $0x9848 // cdqe - -LBB3_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xfd // mov r13, r15 + JE LBB3_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB3_9 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB3_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4950f41 // setne r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_6 - LONG $0x01c48349 // add r12, 1 - -LBB3_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_12 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB3_10: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB3_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + +LBB3_9: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_11: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_15 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB3_13: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7950f41 // setne r15b + LONG $0xd6950f41 // setne r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7950f40 // setne dil @@ -18125,19 +18631,19 @@ LBB3_10: LONG $0xd3950f41 // setne r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6950f41 // setne r14b + LONG $0xd7950f41 // setne r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0950f41 // setne r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4950f41 // setne r12b @@ -18146,147 +18652,146 @@ LBB3_10: LONG $0xd5950f41 // setne r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1950f41 // setne r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB3_10 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - -LBB3_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB3_13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + +LBB3_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_14: +LBB3_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -18294,101 +18799,117 @@ LBB3_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_14 - JMP LBB3_123 - -LBB3_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB3_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_36 - WORD $0x9848 // cdqe - -LBB3_34: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_34 - LONG $0x01c48349 // add r12, 1 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_17 + JMP LBB3_153 LBB3_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_40 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB3_38: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB3_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB3_41: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_43: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_45: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_49 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_47: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5950f41 // setne r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3950f41 // setne r11b @@ -18397,21 +18918,21 @@ LBB3_38: LONG $0xd7950f41 // setne r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2950f41 // setne r10b @@ -18422,143 +18943,143 @@ LBB3_38: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4950f41 // setne r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1950f41 // setne r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_38 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_47 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_42: +LBB3_51: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -18566,97 +19087,113 @@ LBB3_42: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_42 - JMP LBB3_123 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_51 + JMP LBB3_153 -LBB3_68: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_72 - WORD $0x9848 // cdqe - -LBB3_70: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_70 - LONG $0x01c48349 // add r12, 1 +LBB3_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB3_86: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB3_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_76 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB3_88: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 -LBB3_74: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_90: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_94 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_92: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5950f41 // setne r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3950f41 // setne r11b @@ -18665,21 +19202,21 @@ LBB3_74: LONG $0xd7950f41 // setne r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2950f41 // setne r10b @@ -18690,143 +19227,143 @@ LBB3_74: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4950f41 // setne r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1950f41 // setne r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_74 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_92 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_78: +LBB3_96: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -18834,97 +19371,113 @@ LBB3_78: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_78 - JMP LBB3_123 - -LBB3_79: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_83 - WORD $0x9848 // cdqe - -LBB3_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_81 - LONG $0x01c48349 // add r12, 1 - -LBB3_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_87 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_96 + JMP LBB3_153 + +LBB3_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB3_85: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_102: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_104: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_108 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_106: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5950f41 // setne r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3950f41 // setne r11b @@ -18933,21 +19486,21 @@ LBB3_85: LONG $0xd7950f41 // setne r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2950f41 // setne r10b @@ -18958,143 +19511,143 @@ LBB3_85: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4950f41 // setne r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1950f41 // setne r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_85 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB3_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_106 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB3_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_89: +LBB3_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -19102,97 +19655,113 @@ LBB3_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_89 - JMP LBB3_123 - -LBB3_101: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_105 - WORD $0x9848 // cdqe - -LBB3_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_103 - LONG $0x01c48349 // add r12, 1 - -LBB3_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_109 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB3_107: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_110 + JMP LBB3_153 + +LBB3_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB3_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_130: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_132: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_136 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_134: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5950f41 // setne r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3950f41 // setne r11b @@ -19201,21 +19770,21 @@ LBB3_107: LONG $0xd7950f41 // setne r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2950f41 // setne r10b @@ -19226,143 +19795,143 @@ LBB3_107: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4950f41 // setne r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1950f41 // setne r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_107 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_134 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_111: +LBB3_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -19370,99 +19939,115 @@ LBB3_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_111 - JMP LBB3_123 - -LBB3_112: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_116 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB3_114: - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xcb08 // or bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB3_114 - LONG $0x01c48349 // add r12, 1 - -LBB3_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_120 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB3_118: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_138 + JMP LBB3_153 + +LBB3_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + +LBB3_142: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x107aa1c4; WORD $0xb604 // vmovss xmm0, dword [rsi + 4*r14] + LONG $0x2e78a1c4; WORD $0xb204 // vucomiss xmm0, dword [rdx + 4*r14] + LONG $0xd29a0f41 // setp r10b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0x0844; BYTE $0xd3 // or bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xfcc38349 // add r11, -4 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB3_142 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB3_144: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_146: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_150 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_148: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x0610fac5 // vmovss xmm0, dword [rsi] LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] LONG $0x4610fac5; BYTE $0x04 // vmovss xmm0, dword [rsi + 4] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x422ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rdx + 4] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x4610fac5; BYTE $0x08 // vmovss xmm0, dword [rsi + 8] LONG $0x422ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rdx + 8] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x4610fac5; BYTE $0x0c // vmovss xmm0, dword [rsi + 12] LONG $0x422ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rdx + 12] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x4610fac5; BYTE $0x10 // vmovss xmm0, dword [rsi + 16] LONG $0x422ef8c5; BYTE $0x10 // vucomiss xmm0, dword [rdx + 16] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x4610fac5; BYTE $0x14 // vmovss xmm0, dword [rsi + 20] LONG $0x422ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rdx + 20] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -19478,13 +20063,13 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x4610fac5; BYTE $0x20 // vmovss xmm0, dword [rsi + 32] LONG $0x422ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rdx + 32] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x4610fac5; BYTE $0x24 // vmovss xmm0, dword [rsi + 36] LONG $0x422ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rdx + 36] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -19495,78 +20080,78 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x4610fac5; BYTE $0x2c // vmovss xmm0, dword [rsi + 44] LONG $0x422ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rdx + 44] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x4610fac5; BYTE $0x30 // vmovss xmm0, dword [rsi + 48] LONG $0x422ef8c5; BYTE $0x30 // vucomiss xmm0, dword [rdx + 48] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x4610fac5; BYTE $0x34 // vmovss xmm0, dword [rsi + 52] LONG $0x422ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rdx + 52] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x4610fac5; BYTE $0x38 // vmovss xmm0, dword [rsi + 56] LONG $0x422ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rdx + 56] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x4610fac5; BYTE $0x3c // vmovss xmm0, dword [rsi + 60] LONG $0x422ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rdx + 60] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl LONG $0x4610fac5; BYTE $0x40 // vmovss xmm0, dword [rsi + 64] LONG $0x422ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rdx + 64] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl LONG $0x4610fac5; BYTE $0x44 // vmovss xmm0, dword [rsi + 68] LONG $0x422ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rdx + 68] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl LONG $0x4610fac5; BYTE $0x48 // vmovss xmm0, dword [rsi + 72] LONG $0x422ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rdx + 72] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl LONG $0x4610fac5; BYTE $0x4c // vmovss xmm0, dword [rsi + 76] LONG $0x422ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rdx + 76] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al LONG $0x4610fac5; BYTE $0x50 // vmovss xmm0, dword [rsi + 80] LONG $0x422ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rdx + 80] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl LONG $0x4610fac5; BYTE $0x54 // vmovss xmm0, dword [rsi + 84] LONG $0x422ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rdx + 84] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl LONG $0x4610fac5; BYTE $0x58 // vmovss xmm0, dword [rsi + 88] LONG $0x422ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rdx + 88] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl LONG $0x4610fac5; BYTE $0x5c // vmovss xmm0, dword [rsi + 92] LONG $0x422ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rdx + 92] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -19577,35 +20162,34 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl LONG $0x4610fac5; BYTE $0x64 // vmovss xmm0, dword [rsi + 100] LONG $0x422ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rdx + 100] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al LONG $0x4610fac5; BYTE $0x68 // vmovss xmm0, dword [rsi + 104] LONG $0x422ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rdx + 104] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0xd6950f41 // setne r14b + WORD $0x0841; BYTE $0xc6 // or r14b, al LONG $0x4610fac5; BYTE $0x6c // vmovss xmm0, dword [rsi + 108] LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x4610fac5; BYTE $0x70 // vmovss xmm0, dword [rsi + 112] LONG $0x422ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rdx + 112] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl LONG $0x4610fac5; BYTE $0x74 // vmovss xmm0, dword [rsi + 116] LONG $0x422ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rdx + 116] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x4610fac5; BYTE $0x78 // vmovss xmm0, dword [rsi + 120] LONG $0x422ef8c5; BYTE $0x78 // vucomiss xmm0, dword [rdx + 120] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -19617,109 +20201,107 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd0950f41 // setne r8b WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x5cb60f44; WORD $0x0324 // movzx r11d, byte [rsp + 3] - WORD $0x0845; BYTE $0xeb // or r11b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] LONG $0x07e2c041 // shl r10b, 7 WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xcf // or r15b, cl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x241c8845 // mov byte [r12], r11b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x24548845; BYTE $0x02 // mov byte [r12 + 2], r10b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB3_118 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_148 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_122: +LBB3_152: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x0410fac5; BYTE $0x8e // vmovss xmm0, dword [rsi + 4*rcx] LONG $0x042ef8c5; BYTE $0x8a // vucomiss xmm0, dword [rdx + 4*rcx] @@ -19729,94 +20311,117 @@ LBB3_122: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB3_122 - JMP LBB3_123 - -LBB3_57: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_61 - WORD $0x9848 // cdqe - -LBB3_59: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB3_152 + JMP LBB3_153 + +LBB3_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB3_74 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB3_72: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4950f41 // setne r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_59 - LONG $0x01c48349 // add r12, 1 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB3_72 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] -LBB3_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_65 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 +LBB3_74: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_76: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_80 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax -LBB3_63: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_78: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7950f41 // setne r15b + LONG $0xd6950f41 // setne r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7950f40 // setne dil @@ -19828,19 +20433,19 @@ LBB3_63: LONG $0xd3950f41 // setne r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6950f41 // setne r14b + LONG $0xd7950f41 // setne r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0950f41 // setne r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4950f41 // setne r12b @@ -19849,147 +20454,146 @@ LBB3_63: LONG $0xd5950f41 // setne r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1950f41 // setne r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB3_63 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB3_78 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] -LBB3_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_67: +LBB3_82: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -19997,97 +20601,113 @@ LBB3_67: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_67 - JMP LBB3_123 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_82 + JMP LBB3_153 -LBB3_90: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_94 - WORD $0x9848 // cdqe +LBB3_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB3_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_92 - LONG $0x01c48349 // add r12, 1 +LBB3_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB3_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_98 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB3_116: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 -LBB3_96: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_118: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_122 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_120: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5950f41 // setne r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3950f41 // setne r11b @@ -20096,21 +20716,21 @@ LBB3_96: LONG $0xd7950f41 // setne r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2950f41 // setne r10b @@ -20121,143 +20741,143 @@ LBB3_96: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4950f41 // setne r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1950f41 // setne r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_96 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_120 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_100: +LBB3_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -20265,19 +20885,20 @@ LBB3_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_100 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_124 -LBB3_123: +LBB3_153: SUBQ $8, SP RET @@ -20325,82 +20946,96 @@ TEXT ·_comparison_not_equal_arr_scalar_avx2(SB), $1320-48 MOVQ BP, 1280(SP) LEAQ LCDATA3<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB4_13 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB4_25 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB4_48 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB4_56 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB4_165 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_7: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_7 - LONG $0x01c38349 // add r11, 1 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB4_19 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB4_36 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB4_59 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB4_73 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB4_189 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_11 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_9 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_8: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_8 LBB4_9: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_100 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 LBB4_11: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_15 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + +LBB4_13: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd2950f41 // setne r10b LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6950f41 // setne r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] LONG $0x106e3944 // cmp dword [rsi + 16], r13d - QUAD $0x000000882494950f // setne byte [rsp + 136] + QUAD $0x000000902494950f // setne byte [rsp + 144] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x950f; BYTE $0xd0 // setne al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] LONG $0x246e3944 // cmp dword [rsi + 36], r13d LONG $0xd7950f40 // setne dil LONG $0x286e3944 // cmp dword [rsi + 40], r13d @@ -20412,199 +21047,253 @@ LBB4_11: LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4950f41 // setne r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0x950f; BYTE $0xd2 // setne dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + QUAD $0x000000a02494950f // setne byte [rsp + 160] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + QUAD $0x000000882494950f // setne byte [rsp + 136] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + QUAD $0x000000982494950f // setne byte [rsp + 152] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + QUAD $0x000000a82494950f // setne byte [rsp + 168] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x586e3944 // cmp dword [rsi + 88], r13d + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7950f41 // setne r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] LONG $0x686e3944 // cmp dword [rsi + 104], r13d - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] LONG $0x706e3944 // cmp dword [rsi + 112], r13d - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x746e3944 // cmp dword [rsi + 116], r13d + QUAD $0x000001202494950f // setne byte [rsp + 288] LONG $0x786e3944 // cmp dword [rsi + 120], r13d LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0x950f; BYTE $0xd1 // setne cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] + LONG $0x24540244; BYTE $0x60 // add r10b, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a024bc0240 // add dil, byte [rsp + 160] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB4_11 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_101 - JMP LBB4_165 + LONG $0x04c68349 // add r14, 4 + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 + JNE LBB4_13 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB4_13: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB4_38 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB4_64 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB4_72 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB4_165 - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fbc5 // vmovsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_21 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB4_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB4_129 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB4_19: - LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] +LBB4_18: + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB4_18 + JMP LBB4_179 + +LBB4_19: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB4_43 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB4_86 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB4_99 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB4_189 + WORD $0x8b4c; BYTE $0x22 // mov r12, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_29 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_27 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_26: + LONG $0x012ef9c5 // vucomisd xmm0, qword [rcx] + LONG $0x08718d48 // lea rsi, [rcx + 8] WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xca08 // or dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xcb08 // or bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_19 - LONG $0x01c38349 // add r11, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_26 + +LBB4_27: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 -LBB4_21: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_104 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB4_29: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_33 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b824a4894c // mov qword [rsp + 184], r12 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax -LBB4_23: +LBB4_31: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl @@ -20612,31 +21301,32 @@ LBB4_23: LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x462ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rsi + 8] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - LONG $0x462ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rsi + 16] - WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd5950f41 // setne r13b WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x462ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rsi + 16] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x462ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rsi + 24] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl + LONG $0x40248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 320], cl LONG $0x462ef9c5; BYTE $0x20 // vucomisd xmm0, qword [rsi + 32] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x40248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 320], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x462ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rsi + 40] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f40 // setne dil - WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al LONG $0x462ef9c5; BYTE $0x30 // vucomisd xmm0, qword [rsi + 48] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x462ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rsi + 56] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl @@ -20646,46 +21336,46 @@ LBB4_23: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x462ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rsi + 72] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x462ef9c5; BYTE $0x50 // vucomisd xmm0, qword [rsi + 80] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x462ef9c5; BYTE $0x58 // vucomisd xmm0, qword [rsi + 88] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xc308 // or bl, al LONG $0x462ef9c5; BYTE $0x60 // vucomisd xmm0, qword [rsi + 96] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl LONG $0x462ef9c5; BYTE $0x68 // vucomisd xmm0, qword [rsi + 104] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl LONG $0x462ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rsi + 112] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl LONG $0x462ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rsi + 120] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl QUAD $0x00000080862ef9c5 // vucomisd xmm0, qword [rsi + 128] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl QUAD $0x00000088862ef9c5 // vucomisd xmm0, qword [rsi + 136] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl @@ -20695,472 +21385,306 @@ LBB4_23: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl QUAD $0x00000098862ef9c5 // vucomisd xmm0, qword [rsi + 152] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x80248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], al + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x78244c88 // mov byte [rsp + 120], cl QUAD $0x000000a0862ef9c5 // vucomisd xmm0, qword [rsi + 160] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x78244488 // mov byte [rsp + 120], al + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x70244c88 // mov byte [rsp + 112], cl QUAD $0x000000a8862ef9c5 // vucomisd xmm0, qword [rsi + 168] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0xa0248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], al + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x68244c88 // mov byte [rsp + 104], cl QUAD $0x000000b0862ef9c5 // vucomisd xmm0, qword [rsi + 176] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd4950f41 // setne r12b - WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al QUAD $0x000000b8862ef9c5 // vucomisd xmm0, qword [rsi + 184] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd2950f41 // setne r10b WORD $0x0841; BYTE $0xc2 // or r10b, al QUAD $0x000000c0862ef9c5 // vucomisd xmm0, qword [rsi + 192] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x70244488 // mov byte [rsp + 112], al + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x60244c88 // mov byte [rsp + 96], cl QUAD $0x000000c8862ef9c5 // vucomisd xmm0, qword [rsi + 200] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al QUAD $0x000000d0862ef9c5 // vucomisd xmm0, qword [rsi + 208] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0xd1950f41 // setne r9b + WORD $0x0841; BYTE $0xc1 // or r9b, al QUAD $0x000000d8862ef9c5 // vucomisd xmm0, qword [rsi + 216] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0xd0950f41 // setne r8b + WORD $0x0841; BYTE $0xc0 // or r8b, al QUAD $0x000000e0862ef9c5 // vucomisd xmm0, qword [rsi + 224] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x98248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], al + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl QUAD $0x000000e8862ef9c5 // vucomisd xmm0, qword [rsi + 232] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x90248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], al + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x58244c88 // mov byte [rsp + 88], cl QUAD $0x000000f0862ef9c5 // vucomisd xmm0, qword [rsi + 240] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd1950f41 // setne r9b - WORD $0x0841; BYTE $0xc1 // or r9b, al + LONG $0xd7950f40 // setne dil + WORD $0x0840; BYTE $0xc7 // or dil, al QUAD $0x000000f8862ef9c5 // vucomisd xmm0, qword [rsi + 248] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd0950f41 // setne r8b - WORD $0x0841; BYTE $0xc0 // or r8b, al - WORD $0xdb00 // add bl, bl - LONG $0x20245c02 // add bl, byte [rsp + 32] - LONG $0x05e7c040 // shl dil, 5 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x38244402 // add al, byte [rsp + 56] - WORD $0xc389 // mov ebx, eax + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x20 // add r13b, byte [rsp + 32] + WORD $0x8944; BYTE $0xe8 // mov eax, r13d + LONG $0x05e4c041 // shl r12b, 5 + LONG $0x6cb60f44; WORD $0x4824 // movzx r13d, byte [rsp + 72] + LONG $0x06e5c041 // shl r13b, 6 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + LONG $0x64b60f44; WORD $0x2824 // movzx r12d, byte [rsp + 40] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x50244c02 // add cl, byte [rsp + 80] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0xcb08 // or bl, cl + LONG $0x6cb60f44; WORD $0x3024 // movzx r13d, byte [rsp + 48] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0841; BYTE $0xc5 // or r13b, al + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00009024b4b60f44; BYTE $0x00 // movzx r14d, byte [rsp + 144] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al + QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0xc900 // add cl, cl + LONG $0xa8248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 168] + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0xcb08 // or bl, cl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0x8941; BYTE $0xcc // mov r12d, ecx + QUAD $0x00000110248c8b48 // mov rcx, qword [rsp + 272] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x247cb60f; BYTE $0x58 // movzx edi, byte [rsp + 88] - LONG $0x05e7c040 // shl dil, 5 - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0x0840; BYTE $0xfa // or dl, dil - LONG $0x6cb60f44; WORD $0x5024 // movzx r13d, byte [rsp + 80] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xd5 // or r13b, dl - QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] - WORD $0xd200 // add dl, dl - LONG $0x48245402 // add dl, byte [rsp + 72] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0xca08 // or dl, cl - WORD $0xd189 // mov ecx, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xca08 // or dl, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xc108 // or cl, al - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e4c041 // shl r12b, 6 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0x0841; BYTE $0xdd // or r13b, bl + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c041 // shl r15b, 6 + WORD $0x0841; BYTE $0xdf // or r15b, bl + QUAD $0x0000012024b40a44 // or r14b, byte [rsp + 288] LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0845; BYTE $0xfa // or r10b, r15b WORD $0x0845; BYTE $0xe2 // or r10b, r12b - WORD $0x0841; BYTE $0xd2 // or r10b, dl - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x70 // add r15b, byte [rsp + 112] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xf3 // or r11b, r14b - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd8 // or al, r11b - WORD $0xc389 // mov ebx, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x0888 // mov byte [rax], cl - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - LONG $0x06e1c041 // shl r9b, 6 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0045; BYTE $0xdb // add r11b, r11b + LONG $0x245c0244; BYTE $0x60 // add r11b, byte [rsp + 96] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0845; BYTE $0xc8 // or r8b, r9b - WORD $0x0841; BYTE $0xd8 // or r8b, bl - LONG $0x02508844 // mov byte [rax + 2], r10b - LONG $0x03408844 // mov byte [rax + 3], r8b + QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0x0188 // mov byte [rcx], al + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xdf // or dil, bl + LONG $0x01718844 // mov byte [rcx + 1], r14b + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x02518844 // mov byte [rcx + 2], r10b + WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB4_23 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_105 - JMP LBB4_165 - -LBB4_25: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB4_80 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB4_165 - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_131 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - WORD $0x894d; BYTE $0xdd // mov r13, r11 - -LBB4_29: - WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_29 - LONG $0x01c58349 // add r13, 1 - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_132 + LONG $0x04c18348 // add rcx, 4 + WORD $0x8949; BYTE $0xce // mov r14, rcx + QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 + JNE LBB4_31 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] -LBB4_31: - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000018824bc894c // mov qword [rsp + 392], r15 - JB LBB4_34 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB4_33: LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc5 // cmp r13, rax - JAE LBB4_166 - QUAD $0x00000000bd048d4a // lea rax, [4*r15] - WORD $0x014c; BYTE $0xe8 // add rax, r13 - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB4_166 - -LBB4_34: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x0000017824ac894c // mov qword [rsp + 376], r13 - -LBB4_35: - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x0000018024ac2b4c // sub r13, qword [rsp + 384] - QUAD $0x0000009024ac894c // mov qword [rsp + 144], r13 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB4_160 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB4_162 LBB4_36: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b - LONG $0xd0950f41 // setne r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd7950f41 // setne r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b - LONG $0xd5950f41 // setne r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b - LONG $0xd3950f41 // setne r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b - LONG $0xd6950f40 // setne sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b - LONG $0xd7950f40 // setne dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b - LONG $0xd2950f41 // setne r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b - LONG $0xd4950f41 // setne r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b - LONG $0xd1950f41 // setne r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x11713844 // cmp byte [rcx + 17], r14b - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x13713844 // cmp byte [rcx + 19], r14b - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x14713844 // cmp byte [rcx + 20], r14b - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x15713844 // cmp byte [rcx + 21], r14b - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd6950f41 // setne r14b - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x000001102494950f // setne byte [rsp + 272] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x20 // add r8b, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b - WORD $0xd200 // add dl, dl - LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x0000009824b4b60f // movzx esi, byte [rsp + 152] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xc000 // add al, al - LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000017824b48b48 // mov rsi, qword [rsp + 376] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xd308 // or bl, dl - WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000017824b48948 // mov qword [rsp + 376], rsi - QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 - JNE LBB4_36 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - JMP LBB4_133 + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB4_112 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB4_189 + WORD $0x8a44; BYTE $0x22 // mov r12b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_130 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_132 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB4_41: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_41 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB4_133 + JMP LBB4_189 + +LBB4_43: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB4_117 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB4_189 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_49 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB4_38: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB4_92 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB4_165 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_44 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_42: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_42 - LONG $0x01c38349 // add r11, 1 - -LBB4_44: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_107 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - -LBB4_46: - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB4_48: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_48 + +LBB4_49: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 + +LBB4_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_55 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + +LBB4_53: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd2950f41 // setne r10b LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6950f41 // setne r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] LONG $0x206e394c // cmp qword [rsi + 32], r13 - QUAD $0x000000882494950f // setne byte [rsp + 136] + QUAD $0x000000902494950f // setne byte [rsp + 144] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x950f; BYTE $0xd0 // setne al LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] LONG $0x486e394c // cmp qword [rsi + 72], r13 LONG $0xd7950f40 // setne dil LONG $0x506e394c // cmp qword [rsi + 80], r13 @@ -21172,1749 +21696,1765 @@ LBB4_46: LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4950f41 // setne r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0x950f; BYTE $0xd2 // setne dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + QUAD $0x000000a02494950f // setne byte [rsp + 160] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + QUAD $0x000000882494950f // setne byte [rsp + 136] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + QUAD $0x000000982494950f // setne byte [rsp + 152] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + QUAD $0x000000a82494950f // setne byte [rsp + 168] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7950f41 // setne r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + QUAD $0x000001202494950f // setne byte [rsp + 288] LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0x950f; BYTE $0xd1 // setne cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] + LONG $0x24540244; BYTE $0x60 // add r10b, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a024bc0240 // add dil, byte [rsp + 160] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl + LONG $0x01568841 // mov byte [r14 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03538841 // mov byte [r11 + 3], dl + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c38349 // add r11, 4 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB4_46 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_108 - JMP LBB4_165 + LONG $0x04c68349 // add r14, 4 + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 + JNE LBB4_53 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB4_48: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_52 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_50: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_50 - LONG $0x01c38349 // add r11, 1 - -LBB4_52: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_111 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB4_54: - LONG $0x2e394466 // cmp word [rsi], r13w - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0xd2950f41 // setne r10b - LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w - LONG $0xd6950f41 // setne r14b - LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w - LONG $0xd7950f40 // setne dil - LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w - LONG $0xd0950f41 // setne r8b - LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w - LONG $0xd1950f41 // setne r9b - LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w - LONG $0xd3950f41 // setne r11b - LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w - LONG $0xd4950f41 // setne r12b - LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w - LONG $0xd7950f41 // setne r15b - LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w - LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a024bc0240 // add dil, byte [rsp + 160] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x40c68348 // add rsi, 64 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB4_54 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_112 - JMP LBB4_165 - -LBB4_56: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_60 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB4_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB4_98 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d LBB4_58: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0x10768d48 // lea rsi, [rsi + 16] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 JNE LBB4_58 - LONG $0x01c38349 // add r11, 1 - -LBB4_60: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_115 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 + JMP LBB4_170 + +LBB4_59: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_65 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_63 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi LBB4_62: - LONG $0x2e394466 // cmp word [rsi], r13w - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0xd2950f41 // setne r10b - LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w - LONG $0xd6950f41 // setne r14b - LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w - LONG $0xd7950f40 // setne dil - LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w - LONG $0xd0950f41 // setne r8b - LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w - LONG $0xd1950f41 // setne r9b - LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w - LONG $0xd3950f41 // setne r11b - LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w - LONG $0xd4950f41 // setne r12b - LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w - LONG $0xd7950f41 // setne r15b - LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w - LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a024bc0240 // add dil, byte [rsp + 160] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x40c68348 // add rsi, 64 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 JNE LBB4_62 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_116 - JMP LBB4_165 - -LBB4_64: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_68 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_66: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_66 - LONG $0x01c38349 // add r11, 1 - -LBB4_68: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_118 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB4_70: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x086e394c // cmp qword [rsi + 8], r13 + +LBB4_63: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 + +LBB4_65: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_69 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + +LBB4_67: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd2950f41 // setne r10b - LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd6950f41 // setne r14b - LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x206e394c // cmp qword [rsi + 32], r13 - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x286e394c // cmp qword [rsi + 40], r13 + LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x306e394c // cmp qword [rsi + 48], r13 - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x386e394c // cmp qword [rsi + 56], r13 + LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x486e394c // cmp qword [rsi + 72], r13 + LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w LONG $0xd7950f40 // setne dil - LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd0950f41 // setne r8b - LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w LONG $0xd1950f41 // setne r9b - LONG $0x606e394c // cmp qword [rsi + 96], r13 + LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w LONG $0xd3950f41 // setne r11b - LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd4950f41 // setne r12b - LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 + LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 + LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w LONG $0xd7950f41 // setne r15b - LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 + LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w + WORD $0x950f; BYTE $0xd1 // setne cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a024bc0240 // add dil, byte [rsp + 160] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB4_70 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_119 - JMP LBB4_165 - -LBB4_72: - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fac5 // vmovss xmm0, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_76 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_74: - LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xca08 // or dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_74 - LONG $0x01c38349 // add r11, 1 - -LBB4_76: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_121 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB4_78: - LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl - LONG $0x462ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rsi + 4] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - LONG $0x462ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rsi + 8] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd5950f41 // setne r13b - WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x462ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rsi + 12] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl - LONG $0x462ef8c5; BYTE $0x10 // vucomiss xmm0, dword [rsi + 16] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x40248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 320], cl - LONG $0x462ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rsi + 20] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f40 // setne dil - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x462ef8c5; BYTE $0x18 // vucomiss xmm0, dword [rsi + 24] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl - LONG $0x462ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rsi + 28] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x1c244c88 // mov byte [rsp + 28], cl - LONG $0x462ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rsi + 32] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl - LONG $0x462ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rsi + 36] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl - LONG $0x462ef8c5; BYTE $0x28 // vucomiss xmm0, dword [rsi + 40] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl - LONG $0x462ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rsi + 44] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl - LONG $0x462ef8c5; BYTE $0x30 // vucomiss xmm0, dword [rsi + 48] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl - LONG $0x462ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rsi + 52] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl - LONG $0x462ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rsi + 56] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - LONG $0x462ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rsi + 60] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl - LONG $0x462ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rsi + 64] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl - LONG $0x462ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rsi + 68] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl - LONG $0x462ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rsi + 72] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x462ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rsi + 76] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x80248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], al - LONG $0x462ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rsi + 80] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x78244488 // mov byte [rsp + 120], al - LONG $0x462ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rsi + 84] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0xa0248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], al - LONG $0x462ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rsi + 88] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd4950f41 // setne r12b - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x462ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rsi + 92] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - LONG $0x462ef8c5; BYTE $0x60 // vucomiss xmm0, dword [rsi + 96] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x70244488 // mov byte [rsp + 112], al - LONG $0x462ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rsi + 100] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b + LONG $0x01568841 // mov byte [r14 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x462ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rsi + 104] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x462ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rsi + 108] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x462ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rsi + 112] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x98248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], al - LONG $0x462ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rsi + 116] - LONG $0xd09a0f41 // setp r8b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x90248488; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], al - LONG $0x462ef8c5; BYTE $0x78 // vucomiss xmm0, dword [rsi + 120] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd1950f41 // setne r9b - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x462ef8c5; BYTE $0x7c // vucomiss xmm0, dword [rsi + 124] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd0950f41 // setne r8b - WORD $0x0841; BYTE $0xc0 // or r8b, al - WORD $0xdb00 // add bl, bl - LONG $0x20245c02 // add bl, byte [rsp + 32] - LONG $0x05e7c040 // shl dil, 5 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xc000 // add al, al - LONG $0x38244402 // add al, byte [rsp + 56] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x247cb60f; BYTE $0x58 // movzx edi, byte [rsp + 88] - LONG $0x05e7c040 // shl dil, 5 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0x0840; BYTE $0xfa // or dl, dil - LONG $0x6cb60f44; WORD $0x5024 // movzx r13d, byte [rsp + 80] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xd5 // or r13b, dl - QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] - WORD $0xd200 // add dl, dl - LONG $0x48245402 // add dl, byte [rsp + 72] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd108 // or cl, dl - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0xca08 // or dl, cl - WORD $0xd189 // mov ecx, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xca08 // or dl, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xc108 // or cl, al - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e4c041 // shl r12b, 6 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0845; BYTE $0xe2 // or r10b, r12b - WORD $0x0841; BYTE $0xd2 // or r10b, dl - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x70 // add r15b, byte [rsp + 112] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xf3 // or r11b, r14b - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd8 // or al, r11b - WORD $0xc389 // mov ebx, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x0888 // mov byte [rax], cl - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - LONG $0x06e1c041 // shl r9b, 6 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xc8 // or r8b, r9b - WORD $0x0841; BYTE $0xd8 // or r8b, bl - LONG $0x02508844 // mov byte [rax + 2], r10b - LONG $0x03408844 // mov byte [rax + 3], r8b - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB4_78 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_122 - JMP LBB4_165 - -LBB4_80: - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_84 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_82: - WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_82 - LONG $0x01c38349 // add r11, 1 - -LBB4_84: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_124 - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000018824bc894c // mov qword [rsp + 392], r15 - JB LBB4_88 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JAE LBB4_169 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB4_169 - -LBB4_88: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x00000178249c894c // mov qword [rsp + 376], r11 + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x40c68348 // add rsi, 64 + LONG $0x04c68349 // add r14, 4 + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 + JNE LBB4_67 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB4_89: - QUAD $0x0000018024bc2b4c // sub r15, qword [rsp + 384] - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 +LBB4_69: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB4_85 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB4_90: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b - LONG $0xd0950f41 // setne r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd7950f41 // setne r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b - LONG $0xd5950f41 // setne r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b - LONG $0xd3950f41 // setne r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b - LONG $0xd6950f40 // setne sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b - LONG $0xd7950f40 // setne dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b +LBB4_72: + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w + LONG $0x04768d48 // lea rsi, [rsi + 4] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB4_72 + JMP LBB4_166 + +LBB4_73: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_79 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_77 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_76: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_76 + +LBB4_77: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 + +LBB4_79: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_83 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + +LBB4_81: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + LONG $0x2e394466 // cmp word [rsi], r13w + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd2950f41 // setne r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w + LONG $0xd6950f41 // setne r14b + LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w + LONG $0xd7950f40 // setne dil + LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w + LONG $0xd0950f41 // setne r8b + LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w + LONG $0xd1950f41 // setne r9b + LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w + LONG $0xd3950f41 // setne r11b + LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd4950f41 // setne r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b + LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b - LONG $0xd1950f41 // setne r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x11713844 // cmp byte [rcx + 17], r14b + LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x13713844 // cmp byte [rcx + 19], r14b + LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x14713844 // cmp byte [rcx + 20], r14b + LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x15713844 // cmp byte [rcx + 21], r14b + LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w + LONG $0xd7950f41 // setne r15b + LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd6950f41 // setne r14b - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x000001102494950f // setne byte [rsp + 272] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x20 // add r8b, byte [rsp + 32] + LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] + LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + LONG $0x24540244; BYTE $0x60 // add r10b, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b - WORD $0xd200 // add dl, dl - LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - QUAD $0x000000982494b60f // movzx edx, byte [rsp + 152] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xd0 // or al, r10b + WORD $0xc789 // mov edi, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b + WORD $0x0845; BYTE $0xdc // or r12b, r11b + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xc308 // or bl, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xc000 // add al, al - LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000017824b48b48 // mov rsi, qword [rsp + 376] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] + WORD $0xc789 // mov edi, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xc000 // add al, al - LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xd308 // or bl, dl - WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000017824b48948 // mov qword [rsp + 376], rsi - QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 - JNE LBB4_90 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - JMP LBB4_125 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x40c68348 // add rsi, 64 + LONG $0x04c68349 // add r14, 4 + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 + JNE LBB4_81 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB4_92: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_96 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB4_83: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB4_164 -LBB4_94: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_94 - LONG $0x01c38349 // add r11, 1 +LBB4_85: + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB4_166 + +LBB4_86: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_92 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_90 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB4_96: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB4_128 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 +LBB4_89: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_89 -LBB4_98: - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x046e3944 // cmp dword [rsi + 4], r13d +LBB4_90: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 + +LBB4_92: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_96 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + +LBB4_94: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd2950f41 // setne r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6950f41 // setne r14b - LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x186e3944 // cmp dword [rsi + 24], r13d + LONG $0x186e394c // cmp qword [rsi + 24], r13 + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x206e394c // cmp qword [rsi + 32], r13 + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x286e394c // cmp qword [rsi + 40], r13 + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x246e3944 // cmp dword [rsi + 36], r13d + LONG $0x406e394c // cmp qword [rsi + 64], r13 + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x486e394c // cmp qword [rsi + 72], r13 LONG $0xd7950f40 // setne dil - LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0x506e394c // cmp qword [rsi + 80], r13 LONG $0xd0950f41 // setne r8b - LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0x586e394c // cmp qword [rsi + 88], r13 LONG $0xd1950f41 // setne r9b - LONG $0x306e3944 // cmp dword [rsi + 48], r13d + LONG $0x606e394c // cmp qword [rsi + 96], r13 LONG $0xd3950f41 // setne r11b - LONG $0x346e3944 // cmp dword [rsi + 52], r13d + LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4950f41 // setne r12b - LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d + LONG $0x706e394c // cmp qword [rsi + 112], r13 LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d + LONG $0x786e394c // cmp qword [rsi + 120], r13 + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7950f41 // setne r15b - LONG $0x606e3944 // cmp dword [rsi + 96], r13d + LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x706e3944 // cmp dword [rsi + 112], r13d - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d + LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x786e3944 // cmp dword [rsi + 120], r13d + LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 + WORD $0x950f; BYTE $0xd1 // setne cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] + LONG $0x24540244; BYTE $0x60 // add r10b, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a024bc0240 // add dil, byte [rsp + 160] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl + LONG $0x01568841 // mov byte [r14 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03538841 // mov byte [r11 + 3], dl - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c38349 // add r11, 4 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB4_98 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB4_129 - JMP LBB4_165 - -LBB4_100: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 - -LBB4_101: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB4_130 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - -LBB4_103: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_103 - JMP LBB4_157 - -LBB4_104: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0x04c68349 // add r14, 4 + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 + JNE LBB4_94 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB4_105: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB4_136 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB4_138 +LBB4_96: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB4_168 -LBB4_107: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 - -LBB4_108: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB4_120 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB4_98: WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - -LBB4_110: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al + JMP LBB4_170 + +LBB4_99: + WORD $0x8b44; BYTE $0x22 // mov r12d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_105 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_103 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_102: + LONG $0x012ef8c5 // vucomiss xmm0, dword [rcx] + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x9a0f; BYTE $0xd1 // setp cl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xcb08 // or bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0x10768d48 // lea rsi, [rsi + 16] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_110 - JMP LBB4_146 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_102 + +LBB4_103: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 + +LBB4_105: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_109 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000c024a48944 // mov dword [rsp + 192], r12d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB4_107: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x462ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rsi + 4] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd5950f41 // setne r13b + WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x462ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rsi + 8] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x462ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rsi + 12] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x40248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 320], cl + LONG $0x462ef8c5; BYTE $0x10 // vucomiss xmm0, dword [rsi + 16] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x462ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rsi + 20] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x462ef8c5; BYTE $0x18 // vucomiss xmm0, dword [rsi + 24] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x462ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rsi + 28] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x1c244c88 // mov byte [rsp + 28], cl + LONG $0x462ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rsi + 32] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x462ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rsi + 36] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x462ef8c5; BYTE $0x28 // vucomiss xmm0, dword [rsi + 40] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x462ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rsi + 44] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xc308 // or bl, al + LONG $0x462ef8c5; BYTE $0x30 // vucomiss xmm0, dword [rsi + 48] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x20248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], cl + LONG $0x462ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rsi + 52] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0x462ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rsi + 56] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl + LONG $0x462ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rsi + 60] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x462ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rsi + 64] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl + LONG $0x462ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rsi + 68] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0x462ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rsi + 72] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x462ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rsi + 76] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd6950f41 // setne r14b + WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0x462ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rsi + 80] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x462ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rsi + 84] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x462ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rsi + 88] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x462ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rsi + 92] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x462ef8c5; BYTE $0x60 // vucomiss xmm0, dword [rsi + 96] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x462ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rsi + 100] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x462ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rsi + 104] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd1950f41 // setne r9b + WORD $0x0841; BYTE $0xc1 // or r9b, al + LONG $0x462ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rsi + 108] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd0950f41 // setne r8b + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x462ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rsi + 112] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x462ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rsi + 116] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x462ef8c5; BYTE $0x78 // vucomiss xmm0, dword [rsi + 120] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f40 // setne dil + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x462ef8c5; BYTE $0x7c // vucomiss xmm0, dword [rsi + 124] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x20 // add r13b, byte [rsp + 32] + WORD $0x8944; BYTE $0xe8 // mov eax, r13d + LONG $0x05e4c041 // shl r12b, 5 + LONG $0x6cb60f44; WORD $0x4824 // movzx r13d, byte [rsp + 72] + LONG $0x06e5c041 // shl r13b, 6 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + LONG $0x64b60f44; WORD $0x2824 // movzx r12d, byte [rsp + 40] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x50244c02 // add cl, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x1c244488 // mov byte [rsp + 28], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0xcb08 // or bl, cl + LONG $0x6cb60f44; WORD $0x3024 // movzx r13d, byte [rsp + 48] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0841; BYTE $0xc5 // or r13b, al + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xc808 // or al, cl + QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0xc900 // add cl, cl + LONG $0xa8248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 168] + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0xcb08 // or bl, cl + LONG $0x03e6c041 // shl r14b, 3 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xf1 // or cl, r14b + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x64b60f44; WORD $0x1c24 // movzx r12d, byte [rsp + 28] + WORD $0x0845; BYTE $0xec // or r12b, r13b + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c041 // shl r15b, 6 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x2024840a; WORD $0x0001; BYTE $0x00 // or al, byte [rsp + 288] + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0845; BYTE $0xfa // or r10b, r15b + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + LONG $0x245c0244; BYTE $0x68 // add r11b, byte [rsp + 104] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0845; BYTE $0xc8 // or r8b, r9b + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x8845; BYTE $0x26 // mov byte [r14], r12b + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xdf // or dil, bl + LONG $0x01468841 // mov byte [r14 + 1], al + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xca08 // or dl, cl + LONG $0x02568845 // mov byte [r14 + 2], r10b + LONG $0x03568841 // mov byte [r14 + 3], dl + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 + JNE LBB4_107 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000c024a48b44 // mov r12d, dword [rsp + 192] + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] -LBB4_111: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 +LBB4_109: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB4_172 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB4_174 LBB4_112: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB4_117 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 + WORD $0x8a44; BYTE $0x22 // mov r12b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_131 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_146 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 -LBB4_114: - LONG $0x2e394466 // cmp word [rsi], r13w - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl +LBB4_115: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_115 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB4_147 + JMP LBB4_189 + +LBB4_117: + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_123 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_121 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_120: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_114 - JMP LBB4_142 + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_120 -LBB4_115: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 - -LBB4_116: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB4_140 +LBB4_121: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + LONG $0x01c68349 // add r14, 1 + +LBB4_123: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_127 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax -LBB4_117: +LBB4_125: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0xd2950f41 // setne r10b + LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0xd6950f41 // setne r14b + LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x146e3944 // cmp dword [rsi + 20], r13d + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x186e3944 // cmp dword [rsi + 24], r13d + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x206e3944 // cmp dword [rsi + 32], r13d + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x246e3944 // cmp dword [rsi + 36], r13d + LONG $0xd7950f40 // setne dil + LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0xd0950f41 // setne r8b + LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0xd1950f41 // setne r9b + LONG $0x306e3944 // cmp dword [rsi + 48], r13d + LONG $0xd3950f41 // setne r11b + LONG $0x346e3944 // cmp dword [rsi + 52], r13d + LONG $0xd4950f41 // setne r12b + LONG $0x386e3944 // cmp dword [rsi + 56], r13d + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x406e3944 // cmp dword [rsi + 64], r13d + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x446e3944 // cmp dword [rsi + 68], r13d + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x506e3944 // cmp dword [rsi + 80], r13d + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x546e3944 // cmp dword [rsi + 84], r13d + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x586e3944 // cmp dword [rsi + 88], r13d + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d + LONG $0xd7950f41 // setne r15b + LONG $0x606e3944 // cmp dword [rsi + 96], r13d + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x686e3944 // cmp dword [rsi + 104], r13d + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x706e3944 // cmp dword [rsi + 112], r13d + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x746e3944 // cmp dword [rsi + 116], r13d + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x786e3944 // cmp dword [rsi + 120], r13d + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] + LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + LONG $0x24540244; BYTE $0x60 // add r10b, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xd0 // or al, r10b + WORD $0xc789 // mov edi, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xc308 // or bl, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc000 // add al, al + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] + WORD $0xc789 // mov edi, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x04c68349 // add r14, 4 + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 + JNE LBB4_125 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB4_127: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_189 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB4_177 + +LBB4_129: WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB4_142 + JMP LBB4_179 -LBB4_118: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 +LBB4_130: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB4_134 -LBB4_119: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB4_144 +LBB4_131: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB4_148 -LBB4_120: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB4_146 +LBB4_132: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 -LBB4_121: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 - -LBB4_122: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB4_148 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB4_150 +LBB4_133: + LONG $0x01c68349 // add r14, 1 + +LBB4_134: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_142 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24648944; BYTE $0x1c // mov dword [rsp + 28], r12d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000188248c8948 // mov qword [rsp + 392], rcx + JB LBB4_138 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB4_190 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB4_190 -LBB4_124: - QUAD $0x00000178249c894c // mov qword [rsp + 376], r11 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi +LBB4_138: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 -LBB4_125: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB4_127 +LBB4_139: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + LONG $0x244c8948; BYTE $0x58 // mov qword [rsp + 88], rcx + +LBB4_140: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x01663844 // cmp byte [rsi + 1], r12b + LONG $0xd0950f41 // setne r8b + LONG $0x02663844 // cmp byte [rsi + 2], r12b + LONG $0xd6950f41 // setne r14b + LONG $0x03663844 // cmp byte [rsi + 3], r12b + LONG $0xd5950f41 // setne r13b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x04 // cmp byte [rsi + 4], al + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x05 // cmp byte [rsi + 5], al + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x06 // cmp byte [rsi + 6], al + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x07 // cmp byte [rsi + 7], al + LONG $0xd3950f41 // setne r11b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x08 // cmp byte [rsi + 8], al + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x09 // cmp byte [rsi + 9], al + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x0a // cmp byte [rsi + 10], al + LONG $0xd6950f40 // setne sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd7950f40 // setne dil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd2950f41 // setne r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + LONG $0xd4950f41 // setne r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd1950f41 // setne r9b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd7950f41 // setne r15b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + QUAD $0x000001102494950f // setne byte [rsp + 272] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + LONG $0x24440244; BYTE $0x30 // add r8b, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xd200 // add dl, dl + LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x1c24448b // mov eax, dword [rsp + 28] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xd3 // or r11b, dl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + WORD $0x8941; BYTE $0xc4 // mov r12d, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xc000 // add al, al + LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + QUAD $0x0000017824bc8b48 // mov rdi, qword [rsp + 376] + WORD $0x8844; BYTE $0x1f // mov byte [rdi], r11b + LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014f8844 // mov byte [rdi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xc000 // add al, al + LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + WORD $0xc289 // mov edx, eax + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x027f8844 // mov byte [rdi + 2], r15b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000017824bc8948 // mov qword [rsp + 376], rdi + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 + JNE LBB4_140 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + JMP LBB4_143 + +LBB4_142: + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + +LBB4_143: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB4_189 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB4_159 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d QUAD $0x00000178249c8b4c // mov r11, qword [rsp + 376] -LBB4_154: - LONG $0x34343845 // cmp byte [r12 + rsi], r14b +LBB4_183: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e243846 // cmp byte [rsi + r9], r12b WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl @@ -22923,8 +23463,8 @@ LBB4_154: WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743845; BYTE $0x01 // cmp byte [r12 + rsi + 1], r14b - LONG $0x02768d48 // lea rsi, [rsi + 2] + LONG $0x06643844; BYTE $0x01 // cmp byte [rsi + rax + 1], r12b + LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xdbf6 // neg bl WORD $0xd330 // xor bl, dl @@ -22934,58 +23474,262 @@ LBB4_154: WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB4_183 + JMP LBB4_186 + +LBB4_146: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB4_189 + +LBB4_147: + LONG $0x01c68349 // add r14, 1 + +LBB4_148: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB4_156 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24648944; BYTE $0x1c // mov dword [rsp + 28], r12d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000188248c8948 // mov qword [rsp + 392], rcx + JB LBB4_152 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB4_193 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB4_193 + +LBB4_152: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + +LBB4_153: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + LONG $0x244c8948; BYTE $0x58 // mov qword [rsp + 88], rcx + +LBB4_154: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x01663844 // cmp byte [rsi + 1], r12b + LONG $0xd0950f41 // setne r8b + LONG $0x02663844 // cmp byte [rsi + 2], r12b + LONG $0xd6950f41 // setne r14b + LONG $0x03663844 // cmp byte [rsi + 3], r12b + LONG $0xd5950f41 // setne r13b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x04 // cmp byte [rsi + 4], al + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x05 // cmp byte [rsi + 5], al + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x06 // cmp byte [rsi + 6], al + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x07 // cmp byte [rsi + 7], al + LONG $0xd3950f41 // setne r11b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x08 // cmp byte [rsi + 8], al + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x09 // cmp byte [rsi + 9], al + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x0a // cmp byte [rsi + 10], al + LONG $0xd6950f40 // setne sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd7950f40 // setne dil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd2950f41 // setne r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + LONG $0xd4950f41 // setne r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd1950f41 // setne r9b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd7950f41 // setne r15b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + QUAD $0x000001102494950f // setne byte [rsp + 272] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + LONG $0x24440244; BYTE $0x30 // add r8b, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xd200 // add dl, dl + LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x1c24448b // mov eax, dword [rsp + 28] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xd3 // or r11b, dl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + WORD $0x8941; BYTE $0xc4 // mov r12d, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xc000 // add al, al + LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + QUAD $0x0000017824bc8b48 // mov rdi, qword [rsp + 376] + WORD $0x8844; BYTE $0x1f // mov byte [rdi], r11b + LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014f8844 // mov byte [rdi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xc000 // add al, al + LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + WORD $0xc289 // mov edx, eax + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x027f8844 // mov byte [rdi + 2], r15b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000017824bc8948 // mov qword [rsp + 376], rdi + LONG $0x24448348; WORD $0xff58 // add qword [rsp + 88], -1 JNE LBB4_154 - JMP LBB4_162 - -LBB4_128: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 - -LBB4_129: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB4_155 - -LBB4_130: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] JMP LBB4_157 -LBB4_131: - WORD $0x894d; BYTE $0xdd // mov r13, r11 - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JGE LBB4_31 - -LBB4_132: - QUAD $0x0000017824ac894c // mov qword [rsp + 376], r13 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi +LBB4_156: + QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB4_133: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB4_165 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB4_160 +LBB4_157: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB4_189 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB4_184 -LBB4_127: - WORD $0xf631 // xor esi, esi - JMP LBB4_163 +LBB4_159: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB4_187 -LBB4_136: +LBB4_160: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB4_137: +LBB4_161: LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd0 // setne al @@ -22993,7 +23737,8 @@ LBB4_137: WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3f // movzx r10d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -23001,7 +23746,7 @@ LBB4_137: WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x462ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rsi + 8] LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -23015,29 +23760,29 @@ LBB4_137: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB4_137 + JNE LBB4_161 -LBB4_138: +LBB4_162: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_165 + JE LBB4_189 LONG $0x062ef9c5 // vucomisd xmm0, qword [rsi] - JMP LBB4_152 + JMP LBB4_176 -LBB4_140: +LBB4_164: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB4_141: +LBB4_165: LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -23045,7 +23790,7 @@ LBB4_141: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] @@ -23057,29 +23802,29 @@ LBB4_141: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_141 + JNE LBB4_165 -LBB4_142: +LBB4_166: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_165 + JE LBB4_189 LONG $0x2e394466 // cmp word [rsi], r13w - JMP LBB4_159 + JMP LBB4_181 -LBB4_144: +LBB4_168: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB4_145: +LBB4_169: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -23087,7 +23832,7 @@ LBB4_145: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -23099,23 +23844,22 @@ LBB4_145: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_145 + JNE LBB4_169 -LBB4_146: +LBB4_170: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_165 + JE LBB4_189 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - JMP LBB4_159 + JMP LBB4_181 -LBB4_148: +LBB4_172: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB4_149: +LBB4_173: LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd0 // setne al @@ -23123,7 +23867,8 @@ LBB4_149: WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3f // movzx r10d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -23131,7 +23876,7 @@ LBB4_149: WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x462ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rsi + 4] LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -23145,16 +23890,16 @@ LBB4_149: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB4_149 + JNE LBB4_173 -LBB4_150: +LBB4_174: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_165 + JE LBB4_189 LONG $0x062ef8c5 // vucomiss xmm0, dword [rsi] -LBB4_152: +LBB4_176: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd2 // setne dl WORD $0xc208 // or dl, al @@ -23170,21 +23915,21 @@ LBB4_152: WORD $0xd320 // and bl, dl WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x061c8841 // mov byte [r14 + rax], bl - JMP LBB4_165 + JMP LBB4_189 -LBB4_155: +LBB4_177: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB4_156: +LBB4_178: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -23192,7 +23937,7 @@ LBB4_156: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -23204,16 +23949,16 @@ LBB4_156: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_156 + JNE LBB4_178 -LBB4_157: +LBB4_179: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_165 + JE LBB4_189 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d -LBB4_159: +LBB4_181: WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xda // mov rdx, r11 @@ -23227,21 +23972,22 @@ LBB4_159: WORD $0xc320 // and bl, al WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x161c8841 // mov byte [r14 + rdx], bl - JMP LBB4_165 + JMP LBB4_189 -LBB4_160: +LBB4_184: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d QUAD $0x00000178249c8b4c // mov r11, qword [rsp + 376] -LBB4_161: - LONG $0x34343845 // cmp byte [r12 + rsi], r14b +LBB4_185: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e243846 // cmp byte [rsi + r9], r12b WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl @@ -23250,8 +23996,8 @@ LBB4_161: WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743845; BYTE $0x01 // cmp byte [r12 + rsi + 1], r14b - LONG $0x02768d48 // lea rsi, [rsi + 2] + LONG $0x06643844; BYTE $0x01 // cmp byte [rsi + rax + 1], r12b + LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xdbf6 // neg bl WORD $0xd330 // xor bl, dl @@ -23261,2021 +24007,2012 @@ LBB4_161: WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB4_161 + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB4_185 -LBB4_162: - WORD $0x0149; BYTE $0xf4 // add r12, rsi +LBB4_186: + WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB4_163: +LBB4_187: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_165 - LONG $0x24343845 // cmp byte [r12], r14b + JE LBB4_189 + WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 QUAD $0x0000017824848b4c // mov r8, qword [rsp + 376] LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al WORD $0x3040; BYTE $0xfb // xor bl, dil LONG $0x101c8841 // mov byte [r8 + rdx], bl -LBB4_165: +LBB4_189: MOVQ 1280(SP), SP VZEROUPPER RET -LBB4_166: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB4_190: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - QUAD $0x0000018024bc894c // mov qword [rsp + 384], r15 - QUAD $0x00000000bd048d4a // lea rax, [4*r15] - WORD $0x014c; BYTE $0xe8 // add rax, r13 + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000017824848948 // mov qword [rsp + 376], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB4_167: +LBB4_191: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000019824848948 // mov qword [rsp + 408], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 QUAD $0x000000c024848948 // mov qword [rsp + 192], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rcx + 1] + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xe06ef9c5 // vmovd xmm4, eax WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x1644b60f; BYTE $0x02 // movzx eax, byte [rsi + rdx + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] - QUAD $0x0000010024948948 // mov qword [rsp + 256], rdx + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x0000010824948948 // mov qword [rsp + 264], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax - WORD $0x8949; BYTE $0xdd // mov r13, rbx - LONG $0x20cd8149; WORD $0x0002; BYTE $0x00 // or r13, 544 - QUAD $0x000000f824ac894c // mov qword [rsp + 248], r13 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02400d48; WORD $0x0000 // or rax, 576 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02200d48; WORD $0x0000 // or rax, 544 + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0x40cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 576 + QUAD $0x000000c8249c8948 // mov qword [rsp + 200], rbx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x02600d48; WORD $0x0000 // or rax, 608 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - WORD $0x8949; BYTE $0xda // mov r10, rbx - LONG $0x80ca8149; WORD $0x0002; BYTE $0x00 // or r10, 640 - QUAD $0x000000802494894c // mov qword [rsp + 128], r10 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + WORD $0x8949; BYTE $0xce // mov r14, rcx + LONG $0x80ce8149; WORD $0x0002; BYTE $0x00 // or r14, 640 + QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x02a00d48; WORD $0x0000 // or rax, 672 - WORD $0x8949; BYTE $0xc4 // mov r12, rax - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - LONG $0xc0cf8148; WORD $0x0002; BYTE $0x00 // or rdi, 704 - QUAD $0x000000d824bc8948 // mov qword [rsp + 216], rdi - WORD $0x8948; BYTE $0xda // mov rdx, rbx - LONG $0xe0ca8148; WORD $0x0002; BYTE $0x00 // or rdx, 736 - QUAD $0x000000e024948948 // mov qword [rsp + 224], rdx - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03000d48; WORD $0x0000 // or rax, 768 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x20cf8149; WORD $0x0003; BYTE $0x00 // or r15, 800 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0x40cb8149; WORD $0x0003; BYTE $0x00 // or r11, 832 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - LONG $0x60c88149; WORD $0x0003; BYTE $0x00 // or r8, 864 - QUAD $0x000001082484894c // mov qword [rsp + 264], r8 - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x80ce8149; WORD $0x0003; BYTE $0x00 // or r14, 896 - LONG $0x2474894c; BYTE $0x78 // mov qword [rsp + 120], r14 - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - LONG $0xa0c98149; WORD $0x0003; BYTE $0x00 // or r9, 928 - LONG $0x244c894c; BYTE $0x58 // mov qword [rsp + 88], r9 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x000000f0249c8948 // mov qword [rsp + 240], rbx + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + WORD $0x8949; BYTE $0xcc // mov r12, rcx + LONG $0xc0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 704 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0xe0ce8148; WORD $0x0002; BYTE $0x00 // or rsi, 736 + QUAD $0x000000d024b48948 // mov qword [rsp + 208], rsi + WORD $0x8949; BYTE $0xcf // mov r15, rcx + LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 + QUAD $0x0000010024bc894c // mov qword [rsp + 256], r15 + WORD $0x8949; BYTE $0xcb // mov r11, rcx + LONG $0x20cb8149; WORD $0x0003; BYTE $0x00 // or r11, 800 + QUAD $0x000000f8249c894c // mov qword [rsp + 248], r11 + WORD $0x8949; BYTE $0xca // mov r10, rcx + LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 + QUAD $0x000000802494894c // mov qword [rsp + 128], r10 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 + LONG $0x244c894c; BYTE $0x70 // mov qword [rsp + 112], r9 + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 + QUAD $0x000000d82484894c // mov qword [rsp + 216], r8 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0xa0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 928 + QUAD $0x000000b024948948 // mov qword [rsp + 176], rdx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx - LONG $0x207923c4; WORD $0x2e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + r13], 1 - QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] - LONG $0x2031a3c4; WORD $0x2e04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + r13], 2 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 3 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + r10], 4 - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + r12], 5 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + rdi], 6 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + rdx], 7 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + rdx], 8 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + r15], 9 - LONG $0x2079a3c4; WORD $0x1e04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r11], 10 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + r8], 11 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + r14], 12 - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + r9], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + rbx], 1 + LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + LONG $0x207923c4; WORD $0x2f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r13], 1 + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r14], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r12], 6 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rsi], 7 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r15], 8 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r11], 9 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r10], 10 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + r9], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rdx], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r14], 1 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r12], 2 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r8], 3 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r9], 4 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r10], 6 QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r15], 2 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + r9], 3 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + r10], 4 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - LONG $0x2061a3c4; WORD $0x1e1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + r11], 5 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r8], 6 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + r14], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + rcx], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rdx], 12 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rdx], 13 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - LONG $0x2061a3c4; WORD $0x261c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + r12], 14 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rdx], 15 - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x010116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 1 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x020116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 2 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x030116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 3 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x04012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 4 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x050116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 5 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x060116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 6 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x07012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 7 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x08012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 8 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x090116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 9 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0a0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 10 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - QUAD $0x0b0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 12 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0d0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 13 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0e0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 15 - QUAD $0x01011e6c2029e3c4 // vpinsrb xmm5, xmm10, byte [rsi + rbx + 1], 1 - QUAD $0x02013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 2 - QUAD $0x03010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 3 - QUAD $0x0401166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 1], 4 - QUAD $0x05011e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 1], 5 - QUAD $0x0601066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 6 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - QUAD $0x0701366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 1], 7 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 10 - QUAD $0x0b010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 11 + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r15], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rdx], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rbx], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rsi], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rsi], 15 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x010137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 1 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x02012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 2 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x030137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 3 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x04012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x050137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 5 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x07012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 7 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x080137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 8 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x090137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 9 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0a0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 10 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0b0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 12 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0d0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 13 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0e0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 14 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0f0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 15 + QUAD $0x0101376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x0201276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 2 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x0301076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 3 + QUAD $0x04010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x0601176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 6 + QUAD $0x07013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 7 + QUAD $0x0801176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + QUAD $0x0a011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 10 + QUAD $0x0b010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 - QUAD $0x0e01266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 1], 14 + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0106442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 1], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xca6e79c5 // vmovd xmm9, edx LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xd26e79c5 // vmovd xmm10, edx + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x01020e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 2], 1 + QUAD $0x01020f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 2], 1 QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x02020e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 2], 2 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x030216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 2], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x040206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x050206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 5 + QUAD $0x02020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 2 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x07022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 7 + QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] + QUAD $0x080207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 8 + QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] + QUAD $0x090227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 9 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0a022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 10 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x0b021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 11 QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x060236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 2], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x070206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 7 - WORD $0x894d; BYTE $0xec // mov r12, r13 - QUAD $0x08022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 8 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x09022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 9 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x0a0206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 2], 10 - QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] - QUAD $0x0b021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c0216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 2], 12 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0d023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 13 + QUAD $0x0c0237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 12 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x0d023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 14 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 15 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x02023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x03023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 3 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x04023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 4 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x05023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 5 - QUAD $0x06021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 7 + QUAD $0x0102075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 1 + QUAD $0x0202375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0302175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0402175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0502175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0602175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0702175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 7 QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x08021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x09021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 9 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0a021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 10 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0b021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 12 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x01030e642021e3c4 // vpinsrb xmm4, xmm11, byte [rsi + rcx + 3], 1 - QUAD $0x02030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 2 - QUAD $0x030316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 3 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x04031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 4 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x050316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 5 - QUAD $0x060336642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 3], 6 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x07030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 7 - QUAD $0x080326642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 3], 8 - QUAD $0x09032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 9 - QUAD $0x0a0306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 10 - QUAD $0x0b031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 11 - QUAD $0x0c0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 12 - QUAD $0x0d033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 13 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0e0306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0203066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0303066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0403066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 4 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0503066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 5 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0603366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 3], 6 - QUAD $0x07033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0803066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 8 + QUAD $0x08021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 8 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0902375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 9 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0a02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 10 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0b02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0c02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 13 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0e02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0f02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 15 + QUAD $0x01030f642021e3c4 // vpinsrb xmm4, xmm11, byte [rdi + rcx + 3], 1 + QUAD $0x02030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x050337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 5 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x060337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 6 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x07030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 7 + QUAD $0x080307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 8 + QUAD $0x090327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 9 + QUAD $0x0a032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 10 + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + QUAD $0x0b031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 11 + QUAD $0x0c0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 12 + QUAD $0x0d033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 13 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x0e031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 15 + QUAD $0x0103076c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rax + 3], 1 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0903066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 12 + QUAD $0x0203076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0303076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0403076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 4 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 + QUAD $0x0503076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0603076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 6 + QUAD $0x0703176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 7 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x08031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 8 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x09030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 9 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0a030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 11 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0c030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0f0326442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 3], 15 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0e030f442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rcx + 3], 14 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xc26e79c5 // vmovd xmm8, edx + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0f030f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - LONG $0x167cb60f; BYTE $0x09 // movzx edi, byte [rsi + rdx + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xda6e79c5 // vmovd xmm11, edx + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x010406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 1 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x02041e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 4], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x030406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 3 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x04042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 4 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x050416442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 4], 5 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - QUAD $0x06043e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 4], 6 - QUAD $0x07040e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 4], 7 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x080416442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 4], 8 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x090416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 9 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0a0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 10 - QUAD $0x0b041e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 4], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 12 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0d0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 13 - QUAD $0x0e0406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 14 - QUAD $0x0f040e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 4], 15 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x01040e5c2001e3c4 // vpinsrb xmm3, xmm15, byte [rsi + rcx + 4], 1 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x0204165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 4], 2 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x03040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 3 + QUAD $0x010437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 1 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x02043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 2 + QUAD $0x030417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 4 QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x04040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 4 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x05040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 5 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - QUAD $0x0604365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 7 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x08040e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 4], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 9 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x0a04365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 11 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0c040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 12 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 13 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0e04365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 14 - QUAD $0x0f04265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 4], 15 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x010536642009a3c4 // vpinsrb xmm4, xmm14, byte [rsi + r14 + 5], 1 - QUAD $0x02051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 2 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x03051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 3 - QUAD $0x04052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 4 - QUAD $0x050506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 5 - QUAD $0x06053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x070506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 7 - WORD $0x8949; BYTE $0xc7 // mov r15, rax - QUAD $0x080516642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 5], 8 + QUAD $0x05040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 5 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x06042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 6 + QUAD $0x07040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 7 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x08040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 8 + QUAD $0x090427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 9 + QUAD $0x0a0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 10 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0b0427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 11 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x0c041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 12 + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x0d0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 13 + QUAD $0x0e041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 15 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0104175c2001e3c4 // vpinsrb xmm3, xmm15, byte [rdi + rdx + 4], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0204175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0304175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0404175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0504175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0604175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 6 + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0804075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0904075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 9 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x090506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 10 - QUAD $0x0b051e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 5], 11 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x0c052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 13 - QUAD $0x0e0506642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 5], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 15 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x01050e6c2049e3c4 // vpinsrb xmm5, xmm6, byte [rsi + rcx + 5], 1 - QUAD $0x0205166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0305066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0405066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 4 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0505066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 5 - QUAD $0x06053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 6 + QUAD $0x0a04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 10 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0b041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 11 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0c041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 13 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0705066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 7 - QUAD $0x08050e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 5], 8 + QUAD $0x0e04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 15 + QUAD $0x010537642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r14 + 5], 1 + QUAD $0x02053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 2 + QUAD $0x030517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 3 + QUAD $0x040537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 4 + QUAD $0x05050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 5 + QUAD $0x06052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 7 + QUAD $0x08050f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 5], 8 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x090517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 10 + QUAD $0x0b0527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 11 + QUAD $0x0c051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 12 + QUAD $0x0d0507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 14 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x0f052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 15 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x01051f6c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdi + rbx + 5], 1 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0905066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 12 + QUAD $0x0205076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0405076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 4 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 14 + QUAD $0x0505076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 5 + QUAD $0x0605176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 6 + WORD $0x8949; BYTE $0xd0 // mov r8, rdx + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0705076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 7 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x08050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 8 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x09050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0b05376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 5], 11 + QUAD $0x0c051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x0e053f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 5], 14 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - QUAD $0x0f0526442051a3c4 // vpinsrb xmm0, xmm5, byte [rsi + r12 + 5], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0507442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 5], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x0a // movzx edx, byte [rdi + rax + 10] + LONG $0xda6ef9c5 // vmovd xmm3, edx LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - WORD $0x894d; BYTE $0xf3 // mov r11, r14 - QUAD $0x010636442019a3c4 // vpinsrb xmm0, xmm12, byte [rsi + r14 + 6], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x020606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 2 - QUAD $0x03061e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 6], 3 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x040636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 6], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x050606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 5 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x060616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 6], 6 - QUAD $0x07063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x080606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 8 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x09063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 9 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x0a060e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 6], 10 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - QUAD $0x0b0606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 6], 11 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x0c062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 15 - QUAD $0x01060e6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rcx + 6], 1 - QUAD $0x0206166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 2 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x03060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 3 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x04060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 4 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x05063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 5 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x06062e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 6], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0706166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 7 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x08060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 10 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x0a // movzx edx, byte [rdi + rcx + 10] + LONG $0xe26ef9c5 // vmovd xmm4, edx + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x01060f442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rcx + 6], 1 + QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] + QUAD $0x020627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x040637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 5 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x060637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x080607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 8 + QUAD $0x090617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 10 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0b0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 14 + QUAD $0x0f062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 15 + QUAD $0x01061f6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rbx + 6], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0206176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0306176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0406176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0506176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 5 + QUAD $0x0606076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 6 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0706076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 7 + QUAD $0x08060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 8 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x09060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0a061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 10 + QUAD $0x0b06376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 11 + WORD $0x894d; BYTE $0xde // mov r14, r11 + QUAD $0x0c061f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 6], 12 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x0d061f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 6], 13 + QUAD $0x0e063f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 6], 14 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0f062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 15 + QUAD $0x01070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 1 + QUAD $0x020727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 2 LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0b061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 12 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0d061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 14 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0f06266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 6], 15 - QUAD $0x01071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 1 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x02071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 2 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x03071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 3 - QUAD $0x040736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 4 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x050736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 5 - QUAD $0x060716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 7], 6 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x07071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 7 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x080716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 7], 8 - QUAD $0x09073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 9 - QUAD $0x0a070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 10 - QUAD $0x0b0706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 7], 11 - QUAD $0x0c0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 13 + QUAD $0x03071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 3 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x04070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 5 + QUAD $0x060737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 6 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x070737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 7 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x080727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 8 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x090737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 9 + QUAD $0x0a0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 10 + QUAD $0x0b0717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 12 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0d0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 14 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 15 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0107064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 1 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x0207264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 7], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0307064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0407064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 4 - QUAD $0x05073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 5 - QUAD $0x06072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 6 - WORD $0x894d; BYTE $0xe8 // mov r8, r13 - QUAD $0x0707164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 7 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x08070e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 7], 8 + QUAD $0x0f0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0107074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 1 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0907064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 9 - QUAD $0x0a070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 10 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0b072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 13 + QUAD $0x0207074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0307074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0407074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 4 + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0707074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 7], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x09070f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 7], 9 + WORD $0x894d; BYTE $0xc8 // mov r8, r9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x0c07374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 12 + QUAD $0x0d071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0706442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rax + 7], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0706442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 7], 15 + QUAD $0x0e073f442071a3c4 // vpinsrb xmm0, xmm1, byte [rdi + r15 + 7], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x0b // movzx edx, byte [rdi + rax + 11] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0f072f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x01083e442031a3c4 // vpinsrb xmm0, xmm9, byte [rsi + r15 + 8], 1 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x02081e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 8], 2 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x03080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x040806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 4 - QUAD $0x050836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 8], 5 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x060806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 6 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - QUAD $0x07081e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 8], 7 - QUAD $0x080816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 8], 8 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x090816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 9 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0a0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 10 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0b083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 11 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x0b // movzx edx, byte [rdi + rax + 11] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x010837442031e3c4 // vpinsrb xmm0, xmm9, byte [rdi + rsi + 8], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x020807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 2 + QUAD $0x03081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x04083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 4 + QUAD $0x05080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 5 + QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] + QUAD $0x06080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 7 + QUAD $0x080827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 8], 8 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x090817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 9 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0a080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 13 LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 12 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0d0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 13 + QUAD $0x0e0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 14 LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0e0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 15 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0108166c2029e3c4 // vpinsrb xmm5, xmm10, byte [rsi + rdx + 8], 1 - QUAD $0x0208266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 8], 2 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0308166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 3 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x04083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 4 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0508166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 5 - QUAD $0x0608066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 8], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0708166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 7 - QUAD $0x08080e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 8], 8 + QUAD $0x0f0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 15 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0108176c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rdx + 8], 1 LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0908166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 9 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x0a08066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 8], 10 - QUAD $0x0b082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 11 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0c08266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 8], 12 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0d08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 13 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0e08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 14 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0f082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 15 - QUAD $0x01093e742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r15 + 9], 1 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x02091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 2 - QUAD $0x03090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 3 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x04091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 4 - QUAD $0x050936742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r14 + 9], 5 - QUAD $0x060906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 6 - WORD $0x8949; BYTE $0xc1 // mov r9, rax - QUAD $0x07091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 7 - QUAD $0x080916742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r10 + 9], 8 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x09090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 9 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x0a093e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r15 + 9], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 11 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x0c091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 15 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0109067c2021e3c4 // vpinsrb xmm7, xmm11, byte [rsi + rax + 9], 1 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x0209167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 9], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0309067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 3 - QUAD $0x04093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 4 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0509067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 5 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0609067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0709067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0809067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0909067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 9 - QUAD $0x0a09067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 9], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 11 - QUAD $0x0c09267c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r12 + 9], 12 + QUAD $0x0208176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0308176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0408176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 4 LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0d09367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 9], 13 - QUAD $0x0e09167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 9], 14 + QUAD $0x0508376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x0608276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 6 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x07081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 7 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x08081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 8 + QUAD $0x0908076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0a081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 10 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + QUAD $0x0b08076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 11 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0c081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 13 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0e08076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 14 + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010937742039e3c4 // vpinsrb xmm6, xmm8, byte [rdi + rsi + 9], 1 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x020937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x03091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 3 + QUAD $0x04093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 4 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x05093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 5 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x06090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 6 + QUAD $0x070907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x080907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 8 + QUAD $0x090917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 9 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0a090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 10 + QUAD $0x0b090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c0907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 12 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0d090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 13 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x0e093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 15 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x01090f7c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rcx + 9], 1 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x02090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 3 + QUAD $0x0409177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 4 + QUAD $0x0509377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 5 + QUAD $0x0609277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 6 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x07090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 7 + QUAD $0x08091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 8 + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x0909277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 9 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0a090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 11 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0c090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 13 + QUAD $0x0e09077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + LONG $0x0f54b60f; BYTE $0x0c // movzx edx, byte [rdi + rcx + 12] + LONG $0xc26ef9c5 // vmovd xmm0, edx LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x00046024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x010a2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 10], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x020a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x030a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 3 - QUAD $0x040a1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 10], 4 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x050a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 5 - QUAD $0x060a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x070a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 7 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x080a165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 10], 8 - QUAD $0x090a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 9 - QUAD $0x0a0a3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 10], 10 - QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] - QUAD $0x0b0a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 11 - QUAD $0x0c0a1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 10], 12 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0d0a3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 10], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x0c // movzx edx, byte [rdi + rcx + 12] + LONG $0xea6ef9c5 // vmovd xmm5, edx + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x010a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 1 + QUAD $0x020a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 2 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x030a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 3 QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x010a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 1 - QUAD $0x020a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x040a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 4 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x050a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 5 + QUAD $0x040a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 4 + QUAD $0x050a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 5 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x060a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x070a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 7 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x080a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 8 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x090a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 9 + QUAD $0x0a0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 10 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0b0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 11 + QUAD $0x0c0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 12 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0d0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 13 + QUAD $0x0e0a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 15 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x010a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 1 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x020a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x050a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 5 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x060a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 11 - QUAD $0x0c0a26642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 10], 12 - QUAD $0x0d0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 13 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0e0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 14 + QUAD $0x060a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 6 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x070a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 7 + QUAD $0x080a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 8 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + QUAD $0x090a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 9 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x0a0a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 11 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 15 - QUAD $0x010b2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 11], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x020b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x030b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 3 - QUAD $0x040b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 4 - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x050b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 5 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x060b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x070b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 7 - QUAD $0x080b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 8 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x090b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 10 - QUAD $0x0b0b0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 11], 11 + QUAD $0x0c0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 12 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x0d0a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 13 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0e0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 15 + QUAD $0x010b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 1 + QUAD $0x020b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 2 + QUAD $0x030b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 4 + QUAD $0x050b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 5 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x060b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 6 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x070b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 7 + QUAD $0x080b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 8 + QUAD $0x090b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 11 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0c0b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 12 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0d0b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 13 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 12 - QUAD $0x0d0b3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 11], 13 + QUAD $0x0e0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 14 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 15 - QUAD $0x010b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 1 + QUAD $0x0f0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 15 + QUAD $0x010b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 1 + QUAD $0x020b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 2 + QUAD $0x030b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 3 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x040b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 4 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x050b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 5 + QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] + QUAD $0x060b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 6 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 2 - QUAD $0x030b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 3 - QUAD $0x040b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 11], 4 - QUAD $0x050b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 11], 5 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x060b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 7 + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 11 - QUAD $0x0c0b26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 11], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 13 + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + QUAD $0x090b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 12 + QUAD $0x0d0b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000440249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm3 - QUAD $0x0e0b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 11], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0d // movzx edi, byte [rsi + rax + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x0d // movzx edx, byte [rdi + rax + 13] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f0b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000420248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm1 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rcx + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x010c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 12], 1 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x020c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 12], 2 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x030c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 12], 3 - QUAD $0x040c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 4 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x050c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 5 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x060c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 6 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x070c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 7 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x080c26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 12], 8 - QUAD $0x090c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 9 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x0a0c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 10 - QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] - QUAD $0x0b0c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 12], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 12 - QUAD $0x0d0c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 12], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 15 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x010c06542051e3c4 // vpinsrb xmm2, xmm5, byte [rsi + rax + 12], 1 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x020c3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 12], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x030c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x0d // movzx edx, byte [rdi + rax + 13] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x010c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 1 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x020c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x040c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 4 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x040c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 4 + QUAD $0x050c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 5 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x060c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 12], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x070c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 7 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x080c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 8 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x090c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 10 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x050c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 5 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x060c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 7 + QUAD $0x0b0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 11 + QUAD $0x0c0c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 12 + QUAD $0x0d0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 13 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x0e0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x010c07542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rax + 12], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x020c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + QUAD $0x040c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 4 + QUAD $0x050c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 5 + QUAD $0x060c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 6 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x070c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 7 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 9 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x0a0c2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 12], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0c0c3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 12], 12 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 14 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0f0c3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 12], 15 - QUAD $0x010d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 1 - WORD $0x894d; BYTE $0xdf // mov r15, r11 - QUAD $0x020d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 13], 2 - QUAD $0x030d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 13], 3 + QUAD $0x080c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x090c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 9 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x0a0c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 10 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0b0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0c0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 13 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0e0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 14 + QUAD $0x0f0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 15 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x010d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 1 + QUAD $0x020d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x030d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 3 + QUAD $0x040d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x050d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 5 + QUAD $0x060d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 13], 6 + QUAD $0x070d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 7 + QUAD $0x080d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 8 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x090d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 9 QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x040d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 4 - QUAD $0x050d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 5 + QUAD $0x0a0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 10 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0b0d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 11 QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x060d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 6 - QUAD $0x070d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 7 - QUAD $0x080d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 13], 8 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x090d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 9 - QUAD $0x0a0d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 10 - QUAD $0x0b0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 11 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x0c0d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 12 + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0d0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 13 + QUAD $0x0e0d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 13], 14 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0f0d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 13], 15 LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0d0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 13 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0e0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f0d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 15 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x010d164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 13], 1 - QUAD $0x020d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 2 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x030d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 3 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x040d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 4 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x050d064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 13], 5 + QUAD $0x010d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 1 + QUAD $0x020d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x030d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 3 + QUAD $0x040d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x050d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 5 QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x060d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x070d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x080d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 8 - QUAD $0x090d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 9 - QUAD $0x0a0d2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 13], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c0d1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 13], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 14 + QUAD $0x060d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 6 + QUAD $0x070d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x080d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 8 + QUAD $0x090d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 9 + QUAD $0x0a0d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0c0d1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 13], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + QUAD $0x0e0d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0d06442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rax + 13], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0e // movzx edi, byte [rsi + rax + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0f0d37442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rsi + 13], 15 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x0e3f // movzx edx, byte [rdi + r15 + 14] + LONG $0xca6ef9c5 // vmovd xmm1, edx LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 - QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x0e2e // movzx edi, byte [rsi + r13 + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x010e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 1 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x0e // movzx edx, byte [rdi + rax + 14] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x020e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 2 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x030e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 14], 3 + QUAD $0x020e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x040e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 4 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x050e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x080e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 8 + QUAD $0x090e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 9 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x040e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x050e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 5 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x060e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 14], 6 + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 + QUAD $0x0b0e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 11 + QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] + QUAD $0x0c0e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 12 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x0d0e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x020e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 2 + QUAD $0x030e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 3 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x070e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x080e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 8 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x090e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 11 - QUAD $0x0c0e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 12 - QUAD $0x0d0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 13 - QUAD $0x0e0e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 14], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 15 - QUAD $0x010e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 14], 1 + QUAD $0x040e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x050e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x060e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 6 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x030e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 3 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x040e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 14], 4 - QUAD $0x050e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 14], 5 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x060e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 14], 6 - QUAD $0x070e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 14], 7 + QUAD $0x070e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 7 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x090e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 14], 9 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x0a0e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 14], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 11 - QUAD $0x0c0e1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 14], 12 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0d0e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 14], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x0f // movzx edi, byte [rsi + rdi + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x010f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 1 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x020f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 2 - QUAD $0x030f0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 15], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x040f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x050f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 5 - QUAD $0x060f26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 15], 6 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x070f26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 15], 7 - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - QUAD $0x080f0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 15], 8 - QUAD $0x090f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 9 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x0a0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 10 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x0b0f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 11 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0c0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 14 - QUAD $0x0f0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 15 - LONG $0x7cb60f42; WORD $0x0f2e // movzx edi, byte [rsi + r13 + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x010f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 1 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x020f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 2 + QUAD $0x080e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 8 + QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + QUAD $0x090e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 9 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0a0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 10 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x030f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 3 - QUAD $0x040f165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 15], 4 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x050f2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 15], 5 - QUAD $0x060f365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 15], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x070f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 7 - QUAD $0x080f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 8 - QUAD $0x090f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 9 - QUAD $0x0a0f065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 15], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 12 - QUAD $0x0d0f1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 15], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e0f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 14 + QUAD $0x0b0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 11 + QUAD $0x0c0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 12 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x0d0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 14 + QUAD $0x0f0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 15 + LONG $0x54b60f42; WORD $0x0f3f // movzx edx, byte [rdi + r15 + 15] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x010f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x020f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x030f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 3 + QUAD $0x040f37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 15], 4 + QUAD $0x050f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 5 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x060f37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 15], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x070f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 7 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x080f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x090f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 10 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0b0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 11 + QUAD $0x0c0f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 12 + QUAD $0x0d0f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x0f // movzx edx, byte [rdi + rdx + 15] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x010f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x020f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x040f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 4 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x050f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 5 + QUAD $0x060f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x070f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 7 + QUAD $0x080f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 8 + QUAD $0x090f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 9 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x0a0f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 10 + QUAD $0x0b0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 11 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 15 + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0d0f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 13 + QUAD $0x0e0f1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 15], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x10 // movzx edi, byte [rsi + rax + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x011016442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 16], 1 - QUAD $0x02101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 3 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x041006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 4 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x05101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 5 + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + LONG $0x1f54b60f; BYTE $0x10 // movzx edx, byte [rdi + rbx + 16] + LONG $0xc26ef9c5 // vmovd xmm0, edx + QUAD $0x011037442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 16], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x03100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 5 + QUAD $0x061037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 6 + QUAD $0x07103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 7 + QUAD $0x081017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 8 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x091037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x061006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 6 - QUAD $0x071026442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 16], 7 - QUAD $0x08100e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 16], 8 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x091006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 10 - QUAD $0x0b103e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 16], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 15 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - LONG $0x167cb60f; BYTE $0x10 // movzx edi, byte [rsi + rdx + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0110364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 16], 1 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x02100e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 16], 2 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0310164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 3 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0410164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 4 - QUAD $0x05102e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 16], 5 + QUAD $0x0c1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 12 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0d1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e1017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 14 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0f1007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x10 // movzx edx, byte [rdi + rdx + 16] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0210374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0310174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 3 + QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] + QUAD $0x04101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 4 + QUAD $0x05100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 5 QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x0610164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0710164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 7 + QUAD $0x0610174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 6 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x07100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 7 QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0810164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 8 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x09101e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 16], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 12 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0d103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 13 - QUAD $0x0e100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 14 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0f100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 15 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x112e // movzx edi, byte [rsi + r13 + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x02113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 2 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x031116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 3 - QUAD $0x041106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 4 - QUAD $0x05111e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 17], 5 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x06110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 6 - QUAD $0x071126542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 17], 7 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x08110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 8 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x09113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 9 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x0a113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 10 - QUAD $0x0b113e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 17], 11 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0c113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0e111e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 17], 14 - QUAD $0x0f1106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x11 // movzx edi, byte [rsi + rax + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0111365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 17], 1 - QUAD $0x02110e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 17], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0311065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 3 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x0411065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 17], 4 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0511065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 5 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0611065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 6 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x07110e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 17], 7 - QUAD $0x0811165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 8 - QUAD $0x09111e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 17], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 10 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0b11365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 17], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 12 + QUAD $0x0810174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 8 + QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] + QUAD $0x09103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 9 + QUAD $0x0a10274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 10 + QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] + QUAD $0x0b10274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 14 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 15 + LONG $0x1f54b60f; BYTE $0x11 // movzx edx, byte [rdi + rbx + 17] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 1 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x02111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 2 + QUAD $0x03110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 3 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 5 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x06110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x07110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 7 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x08110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 8 + QUAD $0x091137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 9 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x0a1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 11 + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + QUAD $0x0d1117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 14 + QUAD $0x0f1107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x11 // movzx edx, byte [rdi + rax + 17] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x01112f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 17], 1 + QUAD $0x0211375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0311375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x04111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 4 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 14 + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0611075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 6 + QUAD $0x07110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + QUAD $0x09113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 9 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0a110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 10 + QUAD $0x0b11275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 11 + QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] + QUAD $0x0c11175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 12 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0d113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 13 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f1106442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rax + 17], 15 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0f1107442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r8 + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - LONG $0x7cb60f42; WORD $0x122e // movzx edi, byte [rsi + r13 + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x120f // movzx edx, byte [rdi + r9 + 18] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x01122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 1 + QUAD $0x02121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x07121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 7 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x081227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 8 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x021206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 2 - QUAD $0x031216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x041206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 5 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x061206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 6 - QUAD $0x071226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 18], 7 - QUAD $0x08120e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 18], 8 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x091206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a120e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 18], 10 - QUAD $0x0b123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 11 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0c1226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 18], 12 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0d121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 13 - QUAD $0x0e121e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 18], 14 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0f123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 15 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0e7cb60f; BYTE $0x12 // movzx edi, byte [rsi + rcx + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x01120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 1 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x02120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 2 + QUAD $0x091207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 9 + QUAD $0x0a1237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 14 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0f121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x12 // movzx edx, byte [rdi + rdx + 18] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0112174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0212174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 2 + QUAD $0x0312374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 3 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x0412374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0512174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0612174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0712174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0812174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0912174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 9 + QUAD $0x0a120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 10 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x03120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 3 - QUAD $0x0412064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 18], 4 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x05120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 5 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x06120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 6 - QUAD $0x07120e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 18], 7 - QUAD $0x0812164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 8 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x0912064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 18], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 10 - QUAD $0x0b12364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 18], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0c12164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 12 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0d12164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 18], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e121e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 18], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 15 - LONG $0x7cb60f42; WORD $0x132e // movzx edi, byte [rsi + r13 + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x02133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 2 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x03133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 3 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x04132e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 19], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x05133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 5 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x06133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 6 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x07133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 7 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x08133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 8 - QUAD $0x091306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 11 - QUAD $0x0c1326542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 19], 12 - QUAD $0x0d131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 14 - QUAD $0x0f133e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 19], 15 + QUAD $0x0b120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 11 + QUAD $0x0c12174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 12 + QUAD $0x0d123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 13 + LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] + QUAD $0x0e12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 14 + QUAD $0x0f12074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 15 + LONG $0x54b60f42; WORD $0x130f // movzx edx, byte [rdi + r9 + 19] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 1 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x02130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 2 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x03130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 3 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x04132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 5 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x06130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 6 + QUAD $0x07131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 7 + QUAD $0x081327542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 19], 8 + QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] + QUAD $0x091307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 10 + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0d1317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 14 + QUAD $0x0f131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 15 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + LONG $0x54b60f42; WORD $0x131f // movzx edx, byte [rdi + r11 + 19] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x01131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x03130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 3 + QUAD $0x0413375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0613375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 6 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x08133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 8 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x13 // movzx edi, byte [rsi + rax + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0113065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 1 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x0213365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 19], 2 + QUAD $0x0913075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 10 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0313065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0413065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 4 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x05133e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 19], 5 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x06130e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 19], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0713065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0813065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 8 - QUAD $0x0913065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 9 - QUAD $0x0a130e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 19], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 11 - QUAD $0x0c13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 12 - QUAD $0x0d13165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 19], 13 - QUAD $0x0e131e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 19], 14 + QUAD $0x0b13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 11 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 15 + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 13 + QUAD $0x0e13375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x141e // movzx edi, byte [rsi + r11 + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 1 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x021416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 2 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x03140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 3 - QUAD $0x04142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 4 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x05140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 5 - QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] - QUAD $0x061406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 20], 6 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x071426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 7 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x08143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 8 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x09143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 10 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x0b141e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 20], 11 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0c143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x14 // movzx edi, byte [rsi + rdi + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x0114164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 20], 1 - QUAD $0x0214364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 20], 2 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - QUAD $0x0314364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 20], 3 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x04142e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 20], 4 - QUAD $0x05143e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 20], 5 - QUAD $0x06140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x08143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 8 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x09143e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 20], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0d143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 13 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x0e140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 15 - LONG $0x7cb60f42; WORD $0x151e // movzx edi, byte [rsi + r11 + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 1 - QUAD $0x021516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 2 - WORD $0x8949; BYTE $0xd3 // mov r11, rdx - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x031516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x14 // movzx edx, byte [rdi + rax + 20] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x011407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 3 + QUAD $0x04142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 4 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x051427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 5 + QUAD $0x06140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x081407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 8 + QUAD $0x091407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 9 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x041506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 4 + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 11 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0c140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 12 + QUAD $0x0d1417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 13 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0e142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 14 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0f1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 15 + LONG $0x54b60f42; WORD $0x141f // movzx edx, byte [rdi + r11 + 20] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 1 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0214374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 20], 2 + QUAD $0x03140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 3 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x04140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 4 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x05140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 5 + QUAD $0x0614374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0714174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 7 + QUAD $0x08143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0914174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 9 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0a14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 10 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0b14174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 14 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x0f141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 15 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + LONG $0x1754b60f; BYTE $0x15 // movzx edx, byte [rdi + rdx + 21] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 3 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x041517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 4 + QUAD $0x051527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 5 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x061517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x07153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 7 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x081527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x091517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 9 + QUAD $0x0a1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c1537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 12 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 5 - QUAD $0x061506542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 21], 6 - QUAD $0x071526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 7 + QUAD $0x0d1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 13 + QUAD $0x0e152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 14 + QUAD $0x0f1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 15 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x081506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 8 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x091506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 9 - QUAD $0x0a150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 10 - QUAD $0x0b151e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 21], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 12 + LONG $0x0754b60f; BYTE $0x15 // movzx edx, byte [rdi + rax + 21] + LONG $0xda6ef9c5 // vmovd xmm3, edx LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x15 // movzx edi, byte [rsi + rax + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0115165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0215065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 2 - QUAD $0x0315365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 21], 3 - QUAD $0x04152e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 21], 4 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x0515365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 21], 5 + QUAD $0x0115075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 1 + QUAD $0x0215375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + QUAD $0x04150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 4 + QUAD $0x05150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 5 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0615065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 6 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0715165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 7 + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x07150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 7 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0815065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 8 - QUAD $0x09153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 9 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0a15265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 21], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b15065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0c153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 12 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 13 - QUAD $0x0e150e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 21], 14 + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0a15075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 10 + QUAD $0x0b15175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c15175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 12 + QUAD $0x0d151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e15175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0f151e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rbx + 21], 15 + QUAD $0x0f151f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r11 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rcx + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 1 - QUAD $0x02161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 2 - QUAD $0x031616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 4 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x051616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 5 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x06160e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 22], 6 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x07163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 7 + QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x1617 // movzx edx, byte [rdi + r10 + 22] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x01161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 2 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x03160f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 22], 3 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x041637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 4 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x051617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 5 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x06161f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 22], 6 + QUAD $0x07163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 7 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x081627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x091617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 9 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0a1627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 10 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0b1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 11 + QUAD $0x0c1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 12 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x0d162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 15 QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x081616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 8 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x091616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 9 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x0a161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 10 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0b163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 11 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0c1606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 22], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rdi + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x01163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 1 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x02162e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 22], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x03163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 3 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x04163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 4 - QUAD $0x0516364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 22], 5 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x06163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 6 - QUAD $0x0716164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 7 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x0816364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 22], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 9 - QUAD $0x0a16264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 22], 10 - QUAD $0x0b16064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 11 - QUAD $0x0c163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 12 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0d16164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e16064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 14 - QUAD $0x0f161e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 22], 15 - LONG $0x0e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rcx + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x02170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x041706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 5 - QUAD $0x06170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 6 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x07170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x081706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 8 - QUAD $0x091716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 9 - QUAD $0x0a171e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 23], 10 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x0b1726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 23], 11 - QUAD $0x0c1706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 23], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x17 // movzx edi, byte [rsi + rax + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0117065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 1 - QUAD $0x02172e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 23], 2 + LONG $0x1754b60f; BYTE $0x16 // movzx edx, byte [rdi + rdx + 22] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0116174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0216174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0316374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0416174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0516174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0616174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 6 + QUAD $0x07160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0816174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 8 + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a16074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 11 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0c160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 13 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0e160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 14 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0f160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 15 + LONG $0x54b60f42; WORD $0x1717 // movzx edx, byte [rdi + r10 + 23] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 1 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x021717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 2 + QUAD $0x03170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 3 + QUAD $0x041737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 5 + QUAD $0x06171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 6 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x071737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 7 + QUAD $0x08173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 8 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x09170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 9 + QUAD $0x0a1727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 11 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + QUAD $0x0c1707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 23], 12 + QUAD $0x0d172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 13 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0e172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x17 // movzx edx, byte [rdi + rcx + 23] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x01170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 1 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x02170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 2 + QUAD $0x0317375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 3 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x04170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 4 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0517275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 5 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x06170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 6 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x07170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0817175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 8 + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 10 QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0317165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 23], 3 - QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x04173e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 23], 4 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x05171e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 23], 5 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x06172e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 23], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0717065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 7 - QUAD $0x0817365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 23], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0917065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 9 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x0a17065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 23], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 12 - QUAD $0x0d17165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 23], 13 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0e17165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 23], 14 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - QUAD $0x0f171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 15 + QUAD $0x0b17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 12 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x0d171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 14 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x386563c4; WORD $0x01da // vinserti128 ymm11, ymm3, xmm2, 1 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rdi + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 1 - QUAD $0x02180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 2 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x03180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x04180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 4 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x05180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 5 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x061836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 24], 6 - QUAD $0x07180e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 24], 7 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x08180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 8 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x09180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 10 - QUAD $0x0b1826442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 24], 11 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0c180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 12 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0d180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 15 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + LONG $0x1754b60f; BYTE $0x18 // movzx edx, byte [rdi + rdx + 24] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 1 + QUAD $0x021817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 3 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x041817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x051837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 5 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x061817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 6 + QUAD $0x071837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 7 + QUAD $0x08183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 8 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x09183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 10 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0b1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 11 + QUAD $0x0c1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 12 + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x0d1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 13 + QUAD $0x0e182f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 24], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x18 // movzx edx, byte [rdi + rdx + 24] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0118174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0218174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0318174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 3 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x04182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 4 + QUAD $0x0518274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 5 + QUAD $0x06180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 6 + QUAD $0x07180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 7 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x08180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 8 QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rcx + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x01180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 1 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x0218264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 2 - QUAD $0x0318164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 3 - QUAD $0x04183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 4 - QUAD $0x05181e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 24], 5 - QUAD $0x06182e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 24], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 7 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x08183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 9 - QUAD $0x0a18064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 24], 10 - QUAD $0x0b18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 12 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 13 - QUAD $0x0e18164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 24], 14 - QUAD $0x0f181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 15 + QUAD $0x09180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 9 + QUAD $0x0a18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 10 + QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] + QUAD $0x0b18274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 12 + QUAD $0x0d181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 13 + QUAD $0x0e181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 15 + QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x191f // movzx edx, byte [rdi + r11 + 25] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x011907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 1 + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x021937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 4 + QUAD $0x051937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 5 + QUAD $0x061917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 6 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x07190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 7 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x19 // movzx edi, byte [rsi + rax + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x011916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 1 - QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - QUAD $0x021906542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 25], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x041906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 4 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x05191e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 25], 5 - QUAD $0x061936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 6 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x071906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x081906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 8 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x091916542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 25], 9 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0a1936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 10 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0b193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 11 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x0c191e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 25], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0f192e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 25], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3e7cb60f; BYTE $0x19 // movzx edi, byte [rsi + rdi + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 1 - QUAD $0x0219265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 2 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x03190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 3 - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - QUAD $0x0419265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 4 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x05193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 5 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x06193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 7 - QUAD $0x08193e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 25], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 10 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0b193e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 25], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 12 - QUAD $0x0d190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 14 + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + QUAD $0x09193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 9 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0a1937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 12 + QUAD $0x0d1907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 13 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x0e191f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 25], 14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x19 // movzx edx, byte [rdi + rcx + 25] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0119075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 25], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0219175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0319175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 3 + QUAD $0x04192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0519175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 5 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x06193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0719175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0819175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0919175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 9 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0a19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 10 + QUAD $0x0b19275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0f190e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rcx + 25], 15 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x0f1917442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r10 + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x1a // movzx edi, byte [rsi + rcx + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 1 - QUAD $0x021a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 2 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x031a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 3 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x041a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 4 - QUAD $0x051a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 5 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x061a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 6 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x071a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 7 - QUAD $0x081a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 8 - QUAD $0x091a16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 26], 9 - QUAD $0x0a1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b1a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 11 - QUAD $0x0c1a1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 26], 12 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0d1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 13 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0e1a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 14 - QUAD $0x0f1a2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 26], 15 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - LONG $0x167cb60f; BYTE $0x1a // movzx edi, byte [rsi + rdx + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + LONG $0x54b60f42; WORD $0x1a1f // movzx edx, byte [rdi + r11 + 26] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 1 + QUAD $0x021a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 3 QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x011a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 1 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x021a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 2 - QUAD $0x031a0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 26], 3 - QUAD $0x041a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 4 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x051a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 5 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x061a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 6 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x071a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 7 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x081a1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 26], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x091a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 9 + QUAD $0x041a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 4 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x051a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 5 QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x0a1a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 10 - QUAD $0x0b1a3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 26], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 12 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x0d1a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 14 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0f1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 15 - LONG $0x0e7cb60f; BYTE $0x1b // movzx edi, byte [rsi + rcx + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x011b3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 27], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x021b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 2 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x031b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 27], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x041b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 4 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x051b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 27], 5 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x061b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 6 + QUAD $0x061a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 6 + QUAD $0x071a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 7 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x081a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x091a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 9 + QUAD $0x0a1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 10 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x0b1a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 11 + QUAD $0x0c1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 12 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0d1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 13 + QUAD $0x0e1a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 15 + LONG $0x0f54b60f; BYTE $0x1a // movzx edx, byte [rdi + rcx + 26] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x011a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x021a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x031a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 3 QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x071b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 7 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x081b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 8 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x091b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 9 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x0a1b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 27], 10 - QUAD $0x0b1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 12 - QUAD $0x0d1b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 27], 13 - QUAD $0x0e1b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x067cb60f; BYTE $0x1b // movzx edi, byte [rsi + rax + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x011b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 1 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x021b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 2 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x031b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 3 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x041b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 4 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x051b365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 27], 5 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x061b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 6 - QUAD $0x071b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 7 - QUAD $0x081b1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 27], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x091b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 9 - QUAD $0x0a1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 10 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0b1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 11 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0c1b065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 27], 12 - QUAD $0x0d1b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 13 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0e1b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 14 + QUAD $0x041a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x051a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 5 + QUAD $0x061a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 6 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x071a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 7 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x081a1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 26], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x091a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 9 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0a1a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 10 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0b1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 11 QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0f1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 15 + QUAD $0x0c1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 12 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x0d1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e1a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 14 + QUAD $0x0f1a174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 26], 15 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x1b37 // movzx edx, byte [rdi + r14 + 27] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x041b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 4 + QUAD $0x051b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 5 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x061b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 7 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x081b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 8 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x091b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 10 + QUAD $0x0b1b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 13 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0e1b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x1b // movzx edx, byte [rdi + rdx + 27] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x011b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 1 + QUAD $0x021b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 2 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x031b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 3 + QUAD $0x041b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x051b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + QUAD $0x071b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 7 + QUAD $0x081b1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 27], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x091b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 9 + QUAD $0x0a1b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 10 + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x0d1b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 13 + QUAD $0x0e1b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x1c // movzx edi, byte [rsi + rdx + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 28], 1 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x021c26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 28], 2 - QUAD $0x031c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 3 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x041c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 4 - QUAD $0x051c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 5 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x061c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 6 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - QUAD $0x071c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 7 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x081c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 28], 8 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x091c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 9 - QUAD $0x0a1c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 10 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x0b1c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 11 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0c1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 12 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0d1c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 13 + LONG $0x54b60f42; WORD $0x1c37 // movzx edx, byte [rdi + r14 + 28] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x011c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 3 + QUAD $0x041c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 4 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x051c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x061c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 6 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x071c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 7 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + QUAD $0x081c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 8 + QUAD $0x091c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 11 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0c1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d1c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 13 + QUAD $0x0e1c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 14 LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0e1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 15 - LONG $0x067cb60f; BYTE $0x1c // movzx edi, byte [rsi + rax + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x011c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 1 + QUAD $0x0f1c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 15 + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + LONG $0x54b60f42; WORD $0x1c17 // movzx edx, byte [rdi + r10 + 28] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x011c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x021c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 2 + QUAD $0x031c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 3 + QUAD $0x041c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 4 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x051c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 5 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x061c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 6 QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x021c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 2 + QUAD $0x071c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 7 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x081c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x091c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 9 + QUAD $0x0a1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 10 QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x031c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 3 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x041c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 4 - QUAD $0x051c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 5 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x061c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x071c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x081c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 8 - QUAD $0x091c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a1c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 10 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0b1c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 11 - QUAD $0x0c1c064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 28], 12 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0d1c064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 28], 13 - QUAD $0x0e1c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 14 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0f1c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x1d // movzx edi, byte [rsi + rdi + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x011d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 1 - QUAD $0x021d26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 29], 2 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x031d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 3 - QUAD $0x041d0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 29], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x051d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 5 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x061d26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 29], 6 - QUAD $0x071d16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 29], 7 - QUAD $0x081d3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 29], 8 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x091d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 9 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x0a1d0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 29], 10 - QUAD $0x0b1d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 11 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0c1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 12 - QUAD $0x0d1d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 13 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x0e1d16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 29], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 15 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x1d3e // movzx edi, byte [rsi + r15 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x011d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x021d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x031d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 3 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x041d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 29], 4 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x051d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 5 - QUAD $0x061d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 29], 6 + QUAD $0x0b1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 13 LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x071d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 29], 7 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x081d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 29], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 9 - QUAD $0x0a1d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 29], 10 - QUAD $0x0b1d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 11 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0c1d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 12 - QUAD $0x0d1d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 29], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1d06642061e3c4 // vpinsrb xmm4, xmm3, byte [rsi + rax + 29], 14 + QUAD $0x0e1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 14 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 15 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + LONG $0x1754b60f; BYTE $0x1d // movzx edx, byte [rdi + rdx + 29] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 3 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x041d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 4 + QUAD $0x051d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 5 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x061d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 6 + QUAD $0x071d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 7 + QUAD $0x081d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 8 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x091d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 10 + QUAD $0x0b1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 11 + QUAD $0x0c1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 12 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0d1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 13 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x0e1d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 14 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0f1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 15 + LONG $0x54b60f42; WORD $0x1d17 // movzx edx, byte [rdi + r10 + 29] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x011d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 1 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x021d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 29], 2 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x031d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 3 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x041d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 4 + QUAD $0x051d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 5 + QUAD $0x061d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 6 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x071d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 7 + QUAD $0x081d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 8 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x091d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 9 + QUAD $0x0a1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0c1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 12 + QUAD $0x0d1d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e1d1f642061e3c4 // vpinsrb xmm4, xmm3, byte [rdi + rbx + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x0f1d2e442059a3c4 // vpinsrb xmm0, xmm4, byte [rsi + r13 + 29], 15 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f1d07442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rax + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x1e // movzx edi, byte [rsi + rax + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x011e0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 30], 1 - LONG $0x067cb60f; BYTE $0x1f // movzx edi, byte [rsi + rax + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 31], 1 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x1e // movzx edx, byte [rdi + rax + 30] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x011e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 30], 1 + LONG $0x0754b60f; BYTE $0x1f // movzx edx, byte [rdi + rax + 31] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x011f0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 31], 1 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x021e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 2 - QUAD $0x021f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 3 - QUAD $0x031f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 3 + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x0000011024948b48 // mov rdx, qword [rsp + 272] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + QUAD $0x091e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 30], 9 + QUAD $0x091f3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 31], 9 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 11 + QUAD $0x0b1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 5 - QUAD $0x051f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 5 - QUAD $0x061e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 30], 6 - QUAD $0x061f264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 31], 6 - QUAD $0x0000011024ac8b4c // mov r13, qword [rsp + 272] - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 - QUAD $0x0a1e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 30], 10 - QUAD $0x0a1f0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 31], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 11 - QUAD $0x0b1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 11 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0c1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 12 - QUAD $0x0c1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 13 - QUAD $0x0d1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 13 - QUAD $0x0e1e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 30], 14 - QUAD $0x0e1f164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 31], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 15 - QUAD $0x0f1f06542071e3c4 // vpinsrb xmm2, xmm1, byte [rsi + rax + 31], 15 - LONG $0x44b60f42; WORD $0x1e3e // movzx eax, byte [rsi + r15 + 30] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + QUAD $0x0e1e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 30], 14 + QUAD $0x0e1f1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 31], 14 + QUAD $0x0f1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 15 + QUAD $0x0f1f07542071a3c4 // vpinsrb xmm2, xmm1, byte [rdi + r8 + 31], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x011e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 30], 1 - LONG $0x44b60f42; WORD $0x1f3e // movzx eax, byte [rsi + r15 + 31] + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x011e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 31], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x021e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 2 - QUAD $0x021f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - QUAD $0x041e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 30], 4 - QUAD $0x041f1e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r11 + 31], 4 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x061e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 6 - QUAD $0x061f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 6 - QUAD $0x071e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 30], 7 - QUAD $0x071f167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 31], 7 - QUAD $0x081e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 30], 8 - QUAD $0x081f1e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 31], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 9 - QUAD $0x091f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 11 - QUAD $0x0b1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 11 - QUAD $0x0c1e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 30], 12 - QUAD $0x0c1f367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 31], 12 + QUAD $0x011f077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 31], 1 + QUAD $0x021e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 30], 2 + QUAD $0x021f377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 31], 2 + QUAD $0x031e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 3 + QUAD $0x031f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 3 + QUAD $0x041e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 4 + QUAD $0x041f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 4 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 13 - QUAD $0x0d1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 14 - QUAD $0x0e1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 14 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0f1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 15 - QUAD $0x0f1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 15 + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x071e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 7 + QUAD $0x071f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 30], 9 + QUAD $0x091f0f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r9 + 31], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x0c1e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 12 + QUAD $0x0c1f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 13 + QUAD $0x0d1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 13 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x0e1e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 14 + QUAD $0x0e1f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 - LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 + LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 + QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 QUAD $0x00020024946ffdc5; BYTE $0x00 // vmovdqa ymm2, yword [rsp + 512] LONG $0xc27495c5 // vpcmpeqb ymm0, ymm13, ymm2 QUAD $0x0004c024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1216] @@ -25372,10 +26109,10 @@ LBB4_167: LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 QUAD $0x0002c024a474edc5; BYTE $0x00 // vpcmpeqb ymm4, ymm2, yword [rsp + 704] LONG $0xe1dfddc5 // vpandn ymm4, ymm4, ymm1 - QUAD $0x000120248c74edc5; BYTE $0x00 // vpcmpeqb ymm1, ymm2, yword [rsp + 288] + QUAD $0x000140248c74edc5; BYTE $0x00 // vpcmpeqb ymm1, ymm2, yword [rsp + 320] LONG $0xdf75c1c4; BYTE $0xcd // vpandn ymm1, ymm1, ymm13 LONG $0xc9ebddc5 // vpor ymm1, ymm4, ymm1 - QUAD $0x000140249474edc5; BYTE $0x00 // vpcmpeqb ymm2, ymm2, yword [rsp + 320] + QUAD $0x000120249474edc5; BYTE $0x00 // vpcmpeqb ymm2, ymm2, yword [rsp + 288] LONG $0xdf6dc1c4; BYTE $0xd6 // vpandn ymm2, ymm2, ymm14 LONG $0xcaebf5c5 // vpor ymm1, ymm1, ymm2 LONG $0xc9ebe5c5 // vpor ymm1, ymm3, ymm1 @@ -25392,2011 +26129,1998 @@ LBB4_167: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x7f7ec1c4; WORD $0x8d44; BYTE $0x60 // vmovdqu yword [r13 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8d54; BYTE $0x40 // vmovdqu yword [r13 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8d64; BYTE $0x20 // vmovdqu yword [r13 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8d4c; BYTE $0x00 // vmovdqu yword [r13 + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608a // vmovdqu yword [rdx + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408a // vmovdqu yword [rdx + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208a // vmovdqu yword [rdx + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8a // vmovdqu yword [rdx + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB4_167 - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - QUAD $0x0000018024bc3b4c // cmp r15, qword [rsp + 384] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - QUAD $0x0000019024a48b4c // mov r12, qword [rsp + 400] - JNE LBB4_35 - JMP LBB4_133 - -LBB4_169: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 + JNE LBB4_191 + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + LONG $0x24648b44; BYTE $0x1c // mov r12d, dword [rsp + 28] + QUAD $0x0000019024b48b48 // mov rsi, qword [rsp + 400] + JNE LBB4_139 + JMP LBB4_143 + +LBB4_193: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - QUAD $0x0000018024bc894c // mov qword [rsp + 384], r15 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000017824848948 // mov qword [rsp + 376], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB4_170: +LBB4_194: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000019824848948 // mov qword [rsp + 408], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 QUAD $0x000000a024848948 // mov qword [rsp + 160], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rcx + 1] + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] + WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x0e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rcx + 2] - WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] - QUAD $0x0000010024948948 // mov qword [rsp + 256], rdx + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x0000010824948948 // mov qword [rsp + 264], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x02400d48; WORD $0x0000 // or rax, 576 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax - WORD $0x8949; BYTE $0xcc // mov r12, rcx - LONG $0x60cc8149; WORD $0x0002; BYTE $0x00 // or r12, 608 - QUAD $0x000000b824a4894c // mov qword [rsp + 184], r12 + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0x40cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 576 + QUAD $0x000000c8249c8948 // mov qword [rsp + 200], rbx WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x02800d48; WORD $0x0000 // or rax, 640 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - LONG $0xa0c98149; WORD $0x0002; BYTE $0x00 // or r9, 672 - QUAD $0x000000e0248c894c // mov qword [rsp + 224], r9 - WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0xc0cf8149; WORD $0x0002; BYTE $0x00 // or r15, 704 - QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0xe0cf8148; WORD $0x0002; BYTE $0x00 // or rdi, 736 - QUAD $0x0000009824bc8948 // mov qword [rsp + 152], rdi + LONG $0x02600d48; WORD $0x0000 // or rax, 608 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8949; BYTE $0xce // mov r14, rcx - LONG $0x00ce8149; WORD $0x0003; BYTE $0x00 // or r14, 768 - LONG $0x2474894c; BYTE $0x70 // mov qword [rsp + 112], r14 + LONG $0x80ce8149; WORD $0x0002; BYTE $0x00 // or r14, 640 + QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + WORD $0x8949; BYTE $0xcc // mov r12, rcx + LONG $0xc0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 704 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0xe0ce8148; WORD $0x0002; BYTE $0x00 // or rsi, 736 + QUAD $0x000000d024b48948 // mov qword [rsp + 208], rsi + WORD $0x8949; BYTE $0xcf // mov r15, rcx + LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 + QUAD $0x0000010024bc894c // mov qword [rsp + 256], r15 WORD $0x8949; BYTE $0xcb // mov r11, rcx LONG $0x20cb8149; WORD $0x0003; BYTE $0x00 // or r11, 800 - QUAD $0x000000d8249c894c // mov qword [rsp + 216], r11 + QUAD $0x000000f8249c894c // mov qword [rsp + 248], r11 WORD $0x8949; BYTE $0xca // mov r10, rcx LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 - QUAD $0x000000b02494894c // mov qword [rsp + 176], r10 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x03600d48; WORD $0x0000 // or rax, 864 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + QUAD $0x000000802494894c // mov qword [rsp + 128], r10 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 + LONG $0x244c894c; BYTE $0x70 // mov qword [rsp + 112], r9 WORD $0x8949; BYTE $0xc8 // mov r8, rcx LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 - QUAD $0x000000c82484894c // mov qword [rsp + 200], r8 + QUAD $0x000000d82484894c // mov qword [rsp + 216], r8 WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xa0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 928 - QUAD $0x000000a824948948 // mov qword [rsp + 168], rdx + QUAD $0x000000b024948948 // mov qword [rsp + 176], rdx WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx + QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x28 // mov qword [rsp + 40], rcx - LONG $0x207963c4; WORD $0x1e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + rbx], 1 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - LONG $0x2031e3c4; WORD $0x1e04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + rbx], 2 - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + r12], 3 - LONG $0x2079a3c4; WORD $0x2e04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + r13], 4 - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + r9], 5 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + r15], 6 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + rdi], 7 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + r14], 8 - LONG $0x2079a3c4; WORD $0x1e04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + r11], 9 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r10], 10 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - LONG $0x2079a3c4; WORD $0x2e04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + r13], 11 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + r8], 12 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + rdx], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + r14], 1 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r9], 2 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + r10], 3 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - LONG $0x2061a3c4; WORD $0x1e1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + r11], 4 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - LONG $0x2061a3c4; WORD $0x261c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + r12], 5 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r8], 6 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + r15], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + rbx], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rdx], 12 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rdx], 13 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + rdx], 14 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rdx], 15 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x010116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 1 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x020116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 2 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x030116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 3 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - QUAD $0x040116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 4 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x050116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 5 - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x060116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 6 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x070116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 7 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x080116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 8 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x090116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 9 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0a0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 10 - QUAD $0x0b012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 11 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x0c0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 12 + LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + LONG $0x207923c4; WORD $0x2f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r13], 1 + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r14], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r12], 6 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rsi], 7 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r15], 8 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r11], 9 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r10], 10 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + r9], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rdx], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r14], 1 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r12], 2 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r8], 3 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r9], 4 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r10], 6 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r15], 7 QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0d0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 13 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x0e0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 14 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0f012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 15 - QUAD $0x0101366c2029a3c4 // vpinsrb xmm5, xmm10, byte [rsi + r14 + 1], 1 - QUAD $0x02010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 2 - QUAD $0x0301166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 1], 3 - QUAD $0x04011e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 1], 4 - QUAD $0x0501266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 1], 5 - QUAD $0x0601066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 6 - QUAD $0x07013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 7 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - WORD $0x8949; BYTE $0xf9 // mov r9, rdi - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0a011e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 1], 10 - QUAD $0x0b010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 11 + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rdx], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rbx], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rsi], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rsi], 15 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x010137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 1 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x02012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 2 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x030137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 3 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x04012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x050137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 5 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x07012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 7 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x080137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 8 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x090137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 9 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0a0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 10 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0b0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 12 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0d0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 13 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0e0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 14 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0f0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 15 + QUAD $0x0101376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x0201276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 2 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x0301076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 3 + QUAD $0x04010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x0601176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 6 + QUAD $0x07013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 7 + QUAD $0x0801176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + QUAD $0x0a011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 10 + QUAD $0x0b010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 11 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 12 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 14 + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f0106442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 1], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xca6e79c5 // vmovd xmm9, edx LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x08 // movzx edx, byte [rdi + rax + 8] + LONG $0xd26e79c5 // vmovd xmm10, edx + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x010206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 2], 1 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x020216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 2], 2 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x030216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 2], 3 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x040206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 4 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x050206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 5 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x06020e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 2], 6 + QUAD $0x01020f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 2], 1 + QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] + QUAD $0x02020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 2 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x070206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 8 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x090226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 2], 9 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x0a022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 10 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0b021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 11 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0c0236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 2], 12 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x0d023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 13 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0e0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x03023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x04023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 4 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x05023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 5 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x06023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 7 - QUAD $0x08020e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 2], 8 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x09020e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 2], 9 - QUAD $0x0a021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 10 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0b021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 12 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x010306642021a3c4 // vpinsrb xmm4, xmm11, byte [rsi + r8 + 3], 1 - QUAD $0x020316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 2 - QUAD $0x030316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 3 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - QUAD $0x040316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 4 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - QUAD $0x050306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 5 - QUAD $0x06030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 6 - WORD $0x8949; BYTE $0xca // mov r10, rcx - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x07030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 7 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x080316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 8 - QUAD $0x090326642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 3], 9 - QUAD $0x0a032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 10 - QUAD $0x0b031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 11 - QUAD $0x0c0336642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 3], 12 - QUAD $0x0d033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 13 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x0e033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 14 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0203066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 2 - WORD $0x8949; BYTE $0xc4 // mov r12, rax - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0303066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 3 + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x07022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 7 + QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] + QUAD $0x080207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 8 + QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] + QUAD $0x090227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 9 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0a022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 10 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x0b021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 11 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0c0237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 12 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x0d023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 13 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0403066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 4 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0503066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 5 + QUAD $0x0e0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] + QUAD $0x0102075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 1 + QUAD $0x0202375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0302175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0402175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0502175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0602175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0702175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 7 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x08021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 8 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0902375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 9 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0a02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 10 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0b02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0c02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 13 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0e02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0f02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 15 + QUAD $0x01030f642021e3c4 // vpinsrb xmm4, xmm11, byte [rdi + rcx + 3], 1 + QUAD $0x02030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x050337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 5 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x060337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 6 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x07030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 7 + QUAD $0x080307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 8 + QUAD $0x090327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 9 + QUAD $0x0a032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 10 + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + QUAD $0x0b031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 11 + QUAD $0x0c0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 12 + QUAD $0x0d033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 13 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x0e031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 15 + QUAD $0x0103076c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rax + 3], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0203076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0303076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0403076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 4 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0603066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 6 - QUAD $0x07033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 7 - WORD $0x8949; BYTE $0xfb // mov r11, rdi - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0803066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 8 - QUAD $0x09030e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 3], 9 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 12 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 + QUAD $0x0503076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0603076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 6 + QUAD $0x0703176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 7 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x08031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 8 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x09030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 9 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0a030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 11 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0c030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 14 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x09 // movzx edi, byte [rsi + rcx + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - QUAD $0x0f031e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 3], 15 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0e030f442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rcx + 3], 14 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xc26e79c5 // vmovd xmm8, edx + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0f030f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x09 // movzx edx, byte [rdi + rcx + 9] + LONG $0xda6e79c5 // vmovd xmm11, edx + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x01040e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 4], 1 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x020406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 2 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x030436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 4], 3 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x04042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 4 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - QUAD $0x050406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 5 - QUAD $0x060416442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 4], 6 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x070416442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 4], 7 - QUAD $0x080416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 8 - QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] - QUAD $0x090406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 9 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0a0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 11 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x0c041e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 4], 12 + QUAD $0x010437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 1 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x02043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 2 + QUAD $0x030417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 5 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x06042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 6 + QUAD $0x07040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 7 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x08040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 8 + QUAD $0x090427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 9 + QUAD $0x0a0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 10 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0b0427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 11 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x0c041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 12 + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x0d0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 13 + QUAD $0x0e041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 15 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0104175c2001e3c4 // vpinsrb xmm3, xmm15, byte [rdi + rdx + 4], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0204175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0304175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0404175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0504175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0604175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 6 + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 13 - QUAD $0x0e043e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 4], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0104065c2001e3c4 // vpinsrb xmm3, xmm15, byte [rsi + rax + 4], 1 - QUAD $0x0204265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 4], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0304065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0404065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 4 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0504065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 5 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x06043e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 4], 6 - QUAD $0x07041e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 4], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0804065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 8 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x09041e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 4], 9 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x0a043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 10 + QUAD $0x0804075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0904075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 10 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0b041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 11 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0c041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 11 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0c043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 12 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x0d04265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 4], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 14 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 15 - QUAD $0x01050e642009a3c4 // vpinsrb xmm4, xmm14, byte [rsi + r9 + 5], 1 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x02050e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 5], 2 - QUAD $0x030536642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 5], 3 - QUAD $0x04052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 4 - WORD $0x894d; BYTE $0xee // mov r14, r13 - QUAD $0x05050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 5 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x06050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 6 - QUAD $0x070516642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 5], 7 - QUAD $0x080516642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 5], 8 - QUAD $0x090506642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 5], 9 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0a050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 10 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0b052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 11 - QUAD $0x0c051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 12 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0d050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 13 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0e0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 15 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x0105266c2049a3c4 // vpinsrb xmm5, xmm6, byte [rsi + r12 + 5], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0205066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0305066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 3 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x04051e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 5], 4 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x05050e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 5], 5 - QUAD $0x06053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 6 + QUAD $0x0d04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 13 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0705066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0805066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 8 - QUAD $0x09051e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 5], 9 + QUAD $0x0e04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 15 + QUAD $0x010537642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r14 + 5], 1 + QUAD $0x02053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 2 + QUAD $0x030517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 3 + QUAD $0x040537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 4 + QUAD $0x05050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 5 + QUAD $0x06052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 7 + QUAD $0x08050f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 5], 8 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x090517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 10 + QUAD $0x0b0527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 11 + QUAD $0x0c051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 12 + QUAD $0x0d0507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 14 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x0f052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 15 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x01051f6c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdi + rbx + 5], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0205076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0405076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0505076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 5 + QUAD $0x0605176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 6 + WORD $0x8949; BYTE $0xd0 // mov r8, rdx + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0705076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 7 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x08050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 8 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x09050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 9 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0a05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 10 + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0b05376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 5], 11 + QUAD $0x0c051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 11 - QUAD $0x0c053e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 5], 12 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0d05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 14 + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x0e053f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 5], 14 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f0506442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 5], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0507442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 5], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x0a // movzx edx, byte [rdi + rax + 10] + LONG $0xda6ef9c5 // vmovd xmm3, edx LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - QUAD $0x010606442019a3c4 // vpinsrb xmm0, xmm12, byte [rsi + r8 + 6], 1 - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - QUAD $0x02060e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 6], 2 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x03063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 3 - QUAD $0x040636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 6], 4 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x050636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 6], 5 - QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] - QUAD $0x06060e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 6], 6 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x070616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 6], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 8 - QUAD $0x090616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 6], 9 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x0a0616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 6], 10 - QUAD $0x0b062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 11 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x0c061e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 6], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d0606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 13 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0e063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 14 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0f063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 15 - QUAD $0x0106266c2041a3c4 // vpinsrb xmm5, xmm7, byte [rsi + r12 + 6], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x03063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 3 - QUAD $0x04061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 4 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x05063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 5 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x06061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 6 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x07061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 7 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x08061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x09061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 9 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x0a06266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 6], 10 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0b061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 12 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x0d062e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 6], 13 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0e061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 14 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0f061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 15 - QUAD $0x010706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 7], 1 - QUAD $0x02070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 2 - WORD $0x8948; BYTE $0xcb // mov rbx, rcx - QUAD $0x03073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 3 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x04073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 4 - QUAD $0x050736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 5 - QUAD $0x06070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 6 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - QUAD $0x070716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x08070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 8 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x09070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 9 - QUAD $0x0a0716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 7], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 11 - QUAD $0x0c071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 12 - QUAD $0x0d0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 13 QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x0e070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 14 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x0f0716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 7], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0107064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 1 + LONG $0x0f54b60f; BYTE $0x0a // movzx edx, byte [rdi + rcx + 10] + LONG $0xe26ef9c5 // vmovd xmm4, edx + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x01060f442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rcx + 6], 1 + QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] + QUAD $0x020627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x040637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 5 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x060637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x080607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 8 + QUAD $0x090617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 10 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0b0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 14 + QUAD $0x0f062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 15 + QUAD $0x01061f6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rbx + 6], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0206176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0306176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0406176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0506176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 5 + QUAD $0x0606076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 6 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0706076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 7 + QUAD $0x08060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 8 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x09060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0a061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 10 + QUAD $0x0b06376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 11 + WORD $0x894d; BYTE $0xde // mov r14, r11 + QUAD $0x0c061f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 6], 12 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x0d061f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 6], 13 + QUAD $0x0e063f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 6], 14 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0f062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 15 + QUAD $0x01070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 1 + QUAD $0x020727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x03071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 3 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x04070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 5 + QUAD $0x060737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 6 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x070737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 7 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x080727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 8 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x090737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 9 + QUAD $0x0a0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 10 + QUAD $0x0b0717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 12 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0d0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 14 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0207064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 2 + QUAD $0x0f0707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 7], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0107074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0207074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0307074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0407074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 4 + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0707074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 7], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x09070f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 7], 9 + WORD $0x894d; BYTE $0xc8 // mov r8, r9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0307064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 3 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0407064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 7], 4 - QUAD $0x05073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 5 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0607064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0707064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0807064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0907164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 9 - QUAD $0x0a07264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 7], 10 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0b07264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 7], 11 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - QUAD $0x0c071e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 7], 12 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0d07164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 13 + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x0c07374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 12 + QUAD $0x0d071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0e0716442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rdx + 7], 14 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x0b // movzx edi, byte [rsi + rdx + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0f0716442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 7], 15 + QUAD $0x0e073f442071a3c4 // vpinsrb xmm0, xmm1, byte [rdi + r15 + 7], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x0b // movzx edx, byte [rdi + rax + 11] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0f072f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - LONG $0x167cb60f; BYTE $0x0b // movzx edi, byte [rsi + rdx + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x010816442031e3c4 // vpinsrb xmm0, xmm9, byte [rsi + rdx + 8], 1 - QUAD $0x02081e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 8], 2 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x030816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 3 - WORD $0x894c; BYTE $0xfa // mov rdx, r15 - QUAD $0x04083e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 8], 4 - QUAD $0x050836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 8], 5 - QUAD $0x06082e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 8], 6 - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x070836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 8], 7 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x08083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 8 - QUAD $0x09080e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 8], 9 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0a083e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 8], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 11 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x0c081e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 8], 12 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x0d080e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 8], 13 - QUAD $0x0e080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 14 - QUAD $0x0f0816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 8], 15 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x0108166c2029a3c4 // vpinsrb xmm5, xmm10, byte [rsi + r10 + 8], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x03083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 3 - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - QUAD $0x0408066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 8], 4 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x0b // movzx edx, byte [rdi + rax + 11] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x010837442031e3c4 // vpinsrb xmm0, xmm9, byte [rdi + rsi + 8], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x020807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 2 + QUAD $0x03081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x04083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 4 + QUAD $0x05080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 5 + QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] + QUAD $0x06080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 7 + QUAD $0x080827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 8], 8 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x090817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 8], 9 QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x05080e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 8], 5 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x06080e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 8], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07080e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 8], 7 - QUAD $0x0808066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0908066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 9 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x0a080e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 8], 10 - WORD $0x894d; BYTE $0xe0 // mov r8, r12 - QUAD $0x0b08266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 8], 11 - QUAD $0x0c081e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 8], 12 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x0d081e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 8], 13 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0e08266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 8], 14 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0f080e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 8], 15 - QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] - QUAD $0x010926742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r12 + 9], 1 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x02090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 2 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x03090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 3 - QUAD $0x040916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 4 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x050916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 5 - QUAD $0x06092e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r13 + 9], 6 - WORD $0x894c; BYTE $0xe9 // mov rcx, r13 - QUAD $0x070936742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r14 + 9], 7 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x080916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 8 + QUAD $0x0a080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 11 QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x090916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 9 - QUAD $0x0a093e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r15 + 9], 10 + QUAD $0x0c0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 15 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0108176c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rdx + 8], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0208176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 2 LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0b0916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 11 - QUAD $0x0c091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 12 - QUAD $0x0d090e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r9 + 9], 13 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x0e0926742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r12 + 9], 14 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0f0936742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r14 + 9], 15 - QUAD $0x0109167c2021a3c4 // vpinsrb xmm7, xmm11, byte [rsi + r10 + 9], 1 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x02091e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 9], 2 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0309167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 9], 3 - QUAD $0x04093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 4 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0509167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 9], 5 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0609167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 9], 6 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x07093e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 9], 7 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0809167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 9], 8 - QUAD $0x0909067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 9 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0a09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 10 - QUAD $0x0b09067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 9], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 12 - QUAD $0x0d091e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r11 + 9], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 14 - LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 - QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 - QUAD $0x00046024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] - QUAD $0x010a2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 10], 1 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x020a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 2 + QUAD $0x0308176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0408176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 4 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0508376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x0608276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 6 QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x030a1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 10], 3 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - QUAD $0x040a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 4 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x050a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 5 - WORD $0x8948; BYTE $0xca // mov rdx, rcx - QUAD $0x060a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 6 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x070a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 8 + QUAD $0x07081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 7 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x08081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 8 + QUAD $0x0908076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0a081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 10 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + QUAD $0x0b08076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 11 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0c081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 13 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0e08076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 14 + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010937742039e3c4 // vpinsrb xmm6, xmm8, byte [rdi + rsi + 9], 1 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x020937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x03091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 3 + QUAD $0x04093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 4 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x05093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 5 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x06090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 6 + QUAD $0x070907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x080907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 8 + QUAD $0x090917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 9 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0a090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 10 + QUAD $0x0b090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 11 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x090a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 9 + QUAD $0x0c0907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 12 QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0a0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 11 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x0c0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 12 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0d0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 13 - QUAD $0x0e0a265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 10], 14 - QUAD $0x0f0a365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 10], 15 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x010a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 1 + QUAD $0x0d090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 13 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x0e093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 14 LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x020a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x040a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 4 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x050a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 5 - QUAD $0x060a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 6 - QUAD $0x070a3e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 10], 7 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x080a3e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 10], 8 + QUAD $0x0f090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 15 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x01090f7c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rcx + 9], 1 LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x090a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 9 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x0a0a26642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 10], 10 + QUAD $0x02090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 3 + QUAD $0x0409177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 4 + QUAD $0x0509377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 5 + QUAD $0x0609277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 6 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x07090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 7 + QUAD $0x08091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 8 + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x0909277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 9 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0a090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 11 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0c090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 12 LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b0a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 11 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0c0a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 12 - QUAD $0x0d0a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e0a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 14 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0f0a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 15 - QUAD $0x010b2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 11], 1 - WORD $0x894c; BYTE $0xe9 // mov rcx, r13 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x020b1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 11], 2 - QUAD $0x030b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 3 - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x040b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 4 - QUAD $0x050b0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 11], 5 - QUAD $0x060b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 6 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x070b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 7 + QUAD $0x0d090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 13 + QUAD $0x0e09077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 14 + LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 + QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + LONG $0x0f54b60f; BYTE $0x0c // movzx edx, byte [rdi + rcx + 12] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 + QUAD $0x00046024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x0c // movzx edx, byte [rdi + rcx + 12] + LONG $0xea6ef9c5 // vmovd xmm5, edx + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x010a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 1 + QUAD $0x020a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 2 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x030a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 3 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x040a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 4 + QUAD $0x050a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 5 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x060a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x070a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 7 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x080a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 8 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x090a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 9 + QUAD $0x0a0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 10 LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x080b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 8 - QUAD $0x090b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 9 - WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x0b0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 11 + QUAD $0x0c0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 12 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0a0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 11 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0c0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 13 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0e0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 15 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x010b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 1 + QUAD $0x0d0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 13 + QUAD $0x0e0a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 14 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x020b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 2 - QUAD $0x030b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 3 - QUAD $0x040b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 11], 4 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x050b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 5 + QUAD $0x0f0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 15 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x010a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 1 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x020a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x060b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 7 - QUAD $0x080b3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 11], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 9 - QUAD $0x0a0b26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 11], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 11 - QUAD $0x0c0b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 11], 12 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0d0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 13 + QUAD $0x050a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 6 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x070a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 7 + QUAD $0x080a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 8 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + QUAD $0x090a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 9 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x0a0a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 12 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x0d0a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 13 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0e0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 15 + QUAD $0x010b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 1 + QUAD $0x020b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 2 + QUAD $0x030b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 4 + QUAD $0x050b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 5 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x060b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 6 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x070b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 7 + QUAD $0x080b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 8 + QUAD $0x090b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 11 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0c0b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 12 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0d0b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 15 + QUAD $0x010b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 1 + QUAD $0x020b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 2 + QUAD $0x030b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 3 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x040b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 4 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x050b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 5 + QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] + QUAD $0x060b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 6 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + QUAD $0x090b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 12 + QUAD $0x0d0b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000440249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0d // movzx edi, byte [rsi + rax + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x0d // movzx edx, byte [rdi + rax + 13] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f0b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 15 + LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 + QUAD $0x000420248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm1 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x0d // movzx edx, byte [rdi + rax + 13] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x010c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 1 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x020c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x040c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 5 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x060c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 12], 6 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x070c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 7 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x080c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 8 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x090c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 11 + QUAD $0x0c0c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 12 + QUAD $0x0d0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 13 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x0e0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 15 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 15 - LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 - QUAD $0x000420248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm1 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x0d // movzx edi, byte [rsi + rax + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x010c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 1 - QUAD $0x020c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 12], 2 - WORD $0x894c; BYTE $0xe9 // mov rcx, r13 - QUAD $0x030c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 3 - QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] - QUAD $0x040c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 4 - QUAD $0x050c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 5 + QUAD $0x010c07542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rax + 12], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x020c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + QUAD $0x040c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 4 + QUAD $0x050c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 5 + QUAD $0x060c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 6 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x070c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x080c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x090c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 9 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x0a0c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 10 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0b0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0c0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 13 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0e0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 14 + QUAD $0x0f0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 15 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x010d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 1 + QUAD $0x020d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x030d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 3 + QUAD $0x040d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x050d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 5 + QUAD $0x060d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 13], 6 + QUAD $0x070d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 7 + QUAD $0x080d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 8 QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] - QUAD $0x060c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 6 - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - QUAD $0x070c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 12], 7 - QUAD $0x080c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 8 - QUAD $0x090c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 9 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x0a0c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 10 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0b0c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 12], 11 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x0c0c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 12 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x0d0c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 12], 13 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x0e0c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 14 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0f0c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 15 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x010c36542051a3c4 // vpinsrb xmm2, xmm5, byte [rsi + r14 + 12], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x020c3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 12], 2 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x030c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 3 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x040c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 4 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x050c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 5 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x060c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 6 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x070c16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 12], 7 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x080c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 8 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x090c26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 12], 9 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0a0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 10 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0b0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0c0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 12 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0d0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 13 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0e0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 14 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0f0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 15 - QUAD $0x010d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 1 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x020d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 2 - QUAD $0x030d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 3 - QUAD $0x040d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 13], 4 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x050d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 5 - QUAD $0x060d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 6 - QUAD $0x070d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x080d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 8 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x090d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 9 - QUAD $0x0a0d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 10 - QUAD $0x0b0d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 13], 11 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x0c0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 12 - QUAD $0x0d0d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 13], 13 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x0e0d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 14 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 15 - QUAD $0x010d364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 13], 1 - QUAD $0x020d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 2 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x030d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 3 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x040d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 4 + QUAD $0x090d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 9 QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x050d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 5 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x060d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 6 - QUAD $0x070d164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 13], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x080d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 8 - QUAD $0x090d264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 13], 9 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x0a0d2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 13], 10 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0b0d064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 13], 11 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0c0d364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 13], 12 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x0d0d1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 13], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e0d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 14 + QUAD $0x0a0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 10 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0b0d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 11 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0d0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 13 + QUAD $0x0e0d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 13], 14 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0f0d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 13], 15 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x010d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 1 + QUAD $0x020d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x030d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 3 + QUAD $0x040d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x050d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x060d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 6 + QUAD $0x070d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x080d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 8 + QUAD $0x090d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 9 + QUAD $0x0a0d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0c0d1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 13], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + QUAD $0x0e0d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0f0d26442071a3c4 // vpinsrb xmm0, xmm1, byte [rsi + r12 + 13], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x0e // movzx edi, byte [rsi + rcx + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0f0d37442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rsi + 13], 15 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x0e3f // movzx edx, byte [rdi + r15 + 14] + LONG $0xca6ef9c5 // vmovd xmm1, edx LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e7cb60f; BYTE $0x0e // movzx edi, byte [rsi + rcx + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x010e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 1 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x020e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 14], 2 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x030e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 3 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x040e3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 14], 4 - QUAD $0x050e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 5 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x060e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 6 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x070e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 8 - QUAD $0x090e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 14], 9 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0a0e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 10 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0b0e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 14], 11 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0c0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d0e3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 14], 13 - QUAD $0x0e0e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 14], 14 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0f0e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 14], 15 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x010e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 1 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x020e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 14], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x030e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x040e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 4 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x050e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 5 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x060e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x070e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x080e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x090e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 9 - QUAD $0x0a0e2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 14], 10 - QUAD $0x0b0e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 14], 11 - QUAD $0x0c0e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 14], 12 - QUAD $0x0d0e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 14], 13 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - QUAD $0x0f0e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 14], 15 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x0f1e // movzx edi, byte [rsi + r11 + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x010f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 1 - QUAD $0x020f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 2 - QUAD $0x030f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 3 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x040f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 4 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x050f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 5 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x060f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 6 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x070f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 7 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x080f26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 15], 8 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x090f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 9 - QUAD $0x0a0f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 10 - QUAD $0x0b0f16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 15], 11 - QUAD $0x0c0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 12 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0d0f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 13 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0e0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 14 - QUAD $0x0f0f16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 15], 15 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x0f36 // movzx edi, byte [rsi + r14 + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x010f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 1 - QUAD $0x020f0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 15], 2 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x030f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 3 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x040f165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 15], 4 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x050f3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 15], 5 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x060f2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 15], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x070f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x080f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x090f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 9 + LONG $0x0754b60f; BYTE $0x0e // movzx edx, byte [rdi + rax + 14] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x020e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x040e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 4 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x050e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x080e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 8 + QUAD $0x090e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 + QUAD $0x0b0e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 11 + QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] + QUAD $0x0c0e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 12 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x0d0e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x020e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 2 + QUAD $0x030e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x040e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x050e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x060e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 6 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x070e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x080e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 8 + QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + QUAD $0x090e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 9 QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x0a0f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 10 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0b0f0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 15], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0c0f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 12 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0d0f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 13 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0e0f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 14 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0f0f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 15 + QUAD $0x0a0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b0e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 11 + QUAD $0x0c0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 12 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x0d0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 14 + QUAD $0x0f0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 15 + LONG $0x54b60f42; WORD $0x0f3f // movzx edx, byte [rdi + r15 + 15] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x010f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x020f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x030f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 3 + QUAD $0x040f37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 15], 4 + QUAD $0x050f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 5 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x060f37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 15], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x070f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 7 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x080f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x090f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 10 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0b0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 11 + QUAD $0x0c0f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 12 + QUAD $0x0d0f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f0f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x0f // movzx edx, byte [rdi + rdx + 15] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x010f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x020f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x040f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 4 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x050f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 5 + QUAD $0x060f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x070f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 7 + QUAD $0x080f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 8 + QUAD $0x090f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 9 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x0a0f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 10 + QUAD $0x0b0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0d0f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 13 + QUAD $0x0e0f1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 15], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - LONG $0x7cb60f42; WORD $0x101e // movzx edi, byte [rsi + r11 + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x011016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 1 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x021016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 2 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x031016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 3 - QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] - QUAD $0x04101e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 16], 4 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x051016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 5 - QUAD $0x061006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 6 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x071006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 7 - QUAD $0x081026442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 16], 8 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x091016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 9 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0a103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 11 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0c103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 12 - QUAD $0x0d101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 13 - QUAD $0x0e1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 15 - LONG $0x7cb60f42; WORD $0x1036 // movzx edi, byte [rsi + r14 + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x0110264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0210064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0310064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 3 - QUAD $0x0410164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 16], 4 - QUAD $0x05103e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 16], 5 - QUAD $0x06102e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 16], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0710064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0810064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0910064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 9 - QUAD $0x0a100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 10 - QUAD $0x0b100e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 16], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 12 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x0d102e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 16], 13 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0e10164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 16], 14 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 15 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1e7cb60f; BYTE $0x11 // movzx edi, byte [rsi + rbx + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x011106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 1 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x021106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 2 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x03110e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 17], 3 - QUAD $0x04111e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 17], 4 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x05113e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 17], 5 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x061106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 6 - QUAD $0x071106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 7 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x081136542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 17], 8 - QUAD $0x091116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 9 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0a1106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 11 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x0c110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 12 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x0d111e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 17], 13 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x0e1106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 14 + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + LONG $0x1f54b60f; BYTE $0x10 // movzx edx, byte [rdi + rbx + 16] + LONG $0xc26ef9c5 // vmovd xmm0, edx + QUAD $0x011037442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 16], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 15 + QUAD $0x03100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 5 + QUAD $0x061037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 6 + QUAD $0x07103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 7 + QUAD $0x081017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 8 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x091037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 12 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0d1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e1017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 14 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0f1007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x10 // movzx edx, byte [rdi + rdx + 16] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0210374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0310174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 3 + QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] + QUAD $0x04101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 4 + QUAD $0x05100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0610174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 6 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x07100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0810174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 8 + QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] + QUAD $0x09103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 9 + QUAD $0x0a10274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 10 + QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] + QUAD $0x0b10274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 14 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 15 + LONG $0x1f54b60f; BYTE $0x11 // movzx edx, byte [rdi + rbx + 17] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 1 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x02111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 2 + QUAD $0x03110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 3 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 5 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x06110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 6 QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e7cb60f; BYTE $0x11 // movzx edi, byte [rsi + rcx + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0111265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 17], 1 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x02110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 2 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0311165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 3 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x04110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 4 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x05110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 5 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x06110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x08110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 9 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0a113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 12 - QUAD $0x0d112e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 17], 13 - QUAD $0x0e11165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 17], 14 + QUAD $0x07110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 7 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x08110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 8 + QUAD $0x091137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 9 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x0a1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 11 + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + QUAD $0x0d1117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 14 + QUAD $0x0f1107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x11 // movzx edx, byte [rdi + rax + 17] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x01112f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 17], 1 + QUAD $0x0211375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0311375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x04111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0611075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 6 + QUAD $0x07110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + QUAD $0x09113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 9 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0a110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 10 + QUAD $0x0b11275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 11 + QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] + QUAD $0x0c11175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 12 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0d113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 13 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0f112e442061a3c4 // vpinsrb xmm0, xmm3, byte [rsi + r13 + 17], 15 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0f1107442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r8 + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - LONG $0x1e7cb60f; BYTE $0x12 // movzx edi, byte [rsi + rbx + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x01123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 1 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x02123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 2 - QUAD $0x03120e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 18], 3 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x04123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 4 - QUAD $0x05123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 5 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x06123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 6 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x07123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 7 - QUAD $0x081236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 18], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x09123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 9 - QUAD $0x0a1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 11 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0c1236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 18], 12 - QUAD $0x0d121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 13 - QUAD $0x0e1206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 18], 14 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0f120e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 18], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x12 // movzx edi, byte [rsi + rax + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - WORD $0x894d; BYTE $0xe0 // mov r8, r12 - QUAD $0x0112264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 18], 1 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x120f // movzx edx, byte [rdi + r9 + 18] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x01122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 1 + QUAD $0x02121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x07121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 7 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x081227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 8 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x091207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 9 + QUAD $0x0a1237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 14 LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x02121e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 18], 2 - QUAD $0x0312164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 3 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x04121e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 18], 4 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0512264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 18], 5 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0612164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 18], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0712064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 7 - QUAD $0x08120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0912064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 9 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x0a120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 12 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x0d120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 13 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0e12164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 14 - QUAD $0x0f122e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 18], 15 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x132e // movzx edi, byte [rsi + r13 + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x01130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 1 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x02130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 2 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x03130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 3 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x04133e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 19], 4 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x05130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 5 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x06130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 6 + QUAD $0x0f121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x12 // movzx edx, byte [rdi + rdx + 18] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0112174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0212174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 2 + QUAD $0x0312374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 3 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x0412374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0512174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0612174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0712174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0812174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0912174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 9 + QUAD $0x0a120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 11 + QUAD $0x0c12174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 12 + QUAD $0x0d123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 13 + LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] + QUAD $0x0e12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 14 + QUAD $0x0f12074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 15 + LONG $0x54b60f42; WORD $0x130f // movzx edx, byte [rdi + r9 + 19] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 1 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x02130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 2 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x03130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 3 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x04132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 4 QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x07130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x08130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 8 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x09130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 9 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0a133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 11 - QUAD $0x0c1336542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 19], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 13 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0e133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 14 - QUAD $0x0f130e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 19], 15 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - LONG $0x3e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rdi + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0113065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 1 - QUAD $0x02131e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 19], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x03133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 3 - QUAD $0x04131e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 19], 4 - QUAD $0x0513265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 19], 5 - QUAD $0x0613165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 19], 6 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x07131e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 19], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x08133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 8 - QUAD $0x0913065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 9 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x0a13165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 19], 10 + QUAD $0x05130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 5 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x06130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 6 + QUAD $0x07131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 7 + QUAD $0x081327542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 19], 8 + QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] + QUAD $0x091307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 10 + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0d1317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 14 + QUAD $0x0f131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 15 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + LONG $0x54b60f42; WORD $0x131f // movzx edx, byte [rdi + r11 + 19] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x01131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x03130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 3 + QUAD $0x0413375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0613375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 6 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x08133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0913075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 11 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - QUAD $0x0c131e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 19], 12 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0d13065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 13 - QUAD $0x0e13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 14 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 15 + QUAD $0x0d13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 13 + QUAD $0x0e13375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - LONG $0x7cb60f42; WORD $0x142e // movzx edi, byte [rsi + r13 + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] - QUAD $0x01142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 1 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x021416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 2 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x031436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 20], 3 - QUAD $0x04143e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 20], 4 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x05143e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 20], 5 - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x061416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 6 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x071416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 7 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x081416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 8 - QUAD $0x09140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 9 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0a140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 10 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0b140e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 20], 11 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x0c140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 12 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0d140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 13 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x0e1426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 14 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 15 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e7cb60f; BYTE $0x14 // movzx edi, byte [rsi + rcx + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x01140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 1 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x02140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 2 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x03140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 3 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x04140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 4 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0514164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 20], 5 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x06140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 6 - QUAD $0x07141e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 20], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x08140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 9 - QUAD $0x0a14164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 20], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 11 - QUAD $0x0c141e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 20], 12 - QUAD $0x0d14064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 20], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 14 - QUAD $0x0f14064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 20], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0754b60f; BYTE $0x14 // movzx edx, byte [rdi + rax + 20] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x011407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 3 + QUAD $0x04142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 4 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x051427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 5 + QUAD $0x06140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 7 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x15 // movzx edi, byte [rsi + rax + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x01152e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 21], 1 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x02151e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 21], 2 - QUAD $0x031536542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 21], 3 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x04150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 4 - QUAD $0x05153e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 21], 5 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x061506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 6 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x07153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 7 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x08153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x09153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 9 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0a153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 10 - QUAD $0x0b150e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 21], 11 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x0c1516542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 21], 12 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x0d1506542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 21], 13 - QUAD $0x0e1526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 14 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0f153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 15 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - LONG $0x3e7cb60f; BYTE $0x15 // movzx edi, byte [rsi + rdi + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x01151e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 21], 1 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0215365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 21], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x03153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x04153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 4 - QUAD $0x0515165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 21], 5 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0615165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 21], 6 + QUAD $0x081407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 8 + QUAD $0x091407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 11 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0c140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 12 + QUAD $0x0d1417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 13 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0e142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 14 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0f1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 15 + LONG $0x54b60f42; WORD $0x141f // movzx edx, byte [rdi + r11 + 20] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x01141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 1 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0214374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 20], 2 + QUAD $0x03140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 3 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x04140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 4 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x05140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 5 + QUAD $0x0614374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0714174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 7 + QUAD $0x08143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0914174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 9 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0a14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 10 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0b14174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 13 LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0715165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 21], 7 + QUAD $0x0e14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 14 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x0f141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 15 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + LONG $0x1754b60f; BYTE $0x15 // movzx edx, byte [rdi + rdx + 21] + LONG $0xd26ef9c5 // vmovd xmm2, edx LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0815165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 21], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0915165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 21], 9 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x0a15265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 21], 10 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0b150e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 21], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0c15165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 21], 12 + QUAD $0x011517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 3 QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0d15165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 21], 13 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0e152e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 21], 14 + QUAD $0x041517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 4 + QUAD $0x051527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 5 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x061517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 6 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x07153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 7 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x081527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x091517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 9 + QUAD $0x0a1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c1537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 12 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0d1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 13 + QUAD $0x0e152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 14 + QUAD $0x0f1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0754b60f; BYTE $0x15 // movzx edx, byte [rdi + rax + 21] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0115075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 1 + QUAD $0x0215375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + QUAD $0x04150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 4 + QUAD $0x05150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x07150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0a15075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 10 + QUAD $0x0b15175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c15175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 12 + QUAD $0x0d151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e15175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0f1516442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rdx + 21], 15 + QUAD $0x0f151f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r11 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x16 // movzx edi, byte [rsi + rdx + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x011616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 1 - QUAD $0x02161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 2 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x031616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 3 - QUAD $0x04160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 4 - QUAD $0x05163e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 22], 5 - QUAD $0x061606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 22], 6 - QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x07163e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 22], 7 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x08161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 8 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x09160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 9 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0a1616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 22], 11 - QUAD $0x0c1616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 22], 12 - QUAD $0x0d1606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 22], 13 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0e1606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 22], 14 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x0f1616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 22], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x16 // movzx edi, byte [rsi + rax + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x01161e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 22], 1 - QUAD $0x0216364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 22], 2 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x03161e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 22], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0416064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 4 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0516064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 5 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0616064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 6 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - QUAD $0x0716364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 22], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x08163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 9 - QUAD $0x0a16264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 22], 10 - QUAD $0x0b160e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 22], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 12 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0d163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 13 - QUAD $0x0e162e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 22], 14 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0f163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 15 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x172e // movzx edi, byte [rsi + r13 + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x01170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 1 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x02173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 2 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x03173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 3 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - QUAD $0x041706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 23], 4 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x05173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 5 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x06173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 6 - QUAD $0x07173e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 23], 7 - QUAD $0x08171e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 23], 8 - QUAD $0x09170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 9 - QUAD $0x0a1716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 11 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x0c1726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 23], 12 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0d170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 13 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x0e173e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 23], 14 - QUAD $0x0f1716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 23], 15 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x171e // movzx edi, byte [rsi + r11 + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x01170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 1 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x02170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 2 - QUAD $0x03171e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 23], 3 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x04170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 4 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x05171e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 23], 5 - QUAD $0x0617065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 6 - QUAD $0x0717365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 23], 7 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0817365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 23], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0917065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 9 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0a17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 11 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0c17165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 23], 12 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0d17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 13 + QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x1617 // movzx edx, byte [rdi + r10 + 22] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x01161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 2 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x03160f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 22], 3 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x041637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 4 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x051617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 5 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x06161f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 22], 6 + QUAD $0x07163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 7 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x081627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x091617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 9 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0a1627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 10 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0b1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 11 + QUAD $0x0c1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 12 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x0d162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x16 // movzx edx, byte [rdi + rdx + 22] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0116174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0216174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0316374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 3 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0416174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0516174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0616174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 6 + QUAD $0x07160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0816174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 8 + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a16074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 10 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0b160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 11 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0c160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 13 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0e160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 14 LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 14 + QUAD $0x0f160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 15 + LONG $0x54b60f42; WORD $0x1717 // movzx edx, byte [rdi + r10 + 23] + LONG $0xd26ef9c5 // vmovd xmm2, edx + QUAD $0x01171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 1 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x021717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 2 + QUAD $0x03170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 3 + QUAD $0x041737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 5 + QUAD $0x06171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 6 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x071737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 7 + QUAD $0x08173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 8 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x09170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 9 + QUAD $0x0a1727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 10 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0b170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 11 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + QUAD $0x0c1707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 23], 12 + QUAD $0x0d172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 13 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0e172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x17 // movzx edx, byte [rdi + rcx + 23] + LONG $0xda6ef9c5 // vmovd xmm3, edx LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0f170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 15 + QUAD $0x01170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 1 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x02170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 2 + QUAD $0x0317375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 3 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x04170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 4 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0517275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 5 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x06170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 6 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x07170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0817175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 8 + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0a17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 10 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0b17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 12 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x0d171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 14 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x386563c4; WORD $0x01da // vinserti128 ymm11, ymm3, xmm2, 1 - LONG $0x7cb60f42; WORD $0x182e // movzx edi, byte [rsi + r13 + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x01180e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 24], 1 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x02182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 2 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x03180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 3 - QUAD $0x041806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 24], 4 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x05180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 5 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x06180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 6 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x07180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 7 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + LONG $0x1754b60f; BYTE $0x18 // movzx edx, byte [rdi + rdx + 24] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 1 + QUAD $0x021817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 3 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x041817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x051837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 5 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x061817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 6 + QUAD $0x071837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 7 + QUAD $0x08183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 8 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x09183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 10 LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x081816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 24], 8 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x091816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 24], 9 + QUAD $0x0b1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 11 + QUAD $0x0c1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 12 QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0a1806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 24], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 11 - QUAD $0x0c1826442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 24], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 13 - QUAD $0x0e183e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 24], 14 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0f183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 15 - LONG $0x7cb60f42; WORD $0x181e // movzx edi, byte [rsi + r11 + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x01183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 2 - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0318264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 3 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x04183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 4 - QUAD $0x05181e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 24], 5 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x06181e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 24], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 7 - QUAD $0x0818364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 24], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 9 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x0a181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 11 - QUAD $0x0c18164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 24], 12 - QUAD $0x0d18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 13 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0e18164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 24], 14 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0f18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x19 // movzx edi, byte [rsi + rax + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x01190e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 25], 1 - QUAD $0x02192e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 25], 2 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x031906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 3 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x04193e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 25], 4 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x051906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 5 - QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] - QUAD $0x06192e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 25], 6 - QUAD $0x07190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x081906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 8 - QUAD $0x091916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 9 - QUAD $0x0a1906542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 25], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 11 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x0c1916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 13 - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - QUAD $0x0e190e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 25], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 15 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x1936 // movzx edi, byte [rsi + r14 + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0119065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 1 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0219065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 25], 2 - QUAD $0x0319265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0419065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 4 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0519265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 5 - QUAD $0x06191e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 25], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0719065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 7 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x08191e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 25], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0919065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 9 - QUAD $0x0a191e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 25], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 11 + QUAD $0x0d1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 13 + QUAD $0x0e182f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 24], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x18 // movzx edx, byte [rdi + rdx + 24] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0118174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0218174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0318174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 3 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x04182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 4 + QUAD $0x0518274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 5 + QUAD $0x06180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 6 + QUAD $0x07180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 7 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x08180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 8 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x09180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 9 + QUAD $0x0a18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 10 + QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] + QUAD $0x0b18274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 11 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 12 + QUAD $0x0c18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 12 + QUAD $0x0d181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 13 + QUAD $0x0e181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 15 + QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x191f // movzx edx, byte [rdi + r11 + 25] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x011907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 1 + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x021937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 3 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0d19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 13 - QUAD $0x0e19165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 25], 14 + QUAD $0x041907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 4 + QUAD $0x051937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 5 + QUAD $0x061917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 6 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x07190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + QUAD $0x09193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 9 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0a1937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 12 + QUAD $0x0d1907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 13 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x0e191f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 25], 14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f54b60f; BYTE $0x19 // movzx edx, byte [rdi + rcx + 25] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0119075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 25], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0219175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0319175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 3 + QUAD $0x04192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0519175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 5 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x06193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0719175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 7 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0819175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0919175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 9 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0a19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 10 + QUAD $0x0b19275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0f191e442061a3c4 // vpinsrb xmm0, xmm3, byte [rsi + r11 + 25], 15 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x0f1917442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r10 + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x1a // movzx edi, byte [rsi + rax + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x011a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 1 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x021a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 2 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x031a16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 26], 3 - QUAD $0x041a3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 26], 4 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x051a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 5 - QUAD $0x061a2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 26], 6 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x071a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 7 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x081a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x091a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 9 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0a1a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 10 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0b1a2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 26], 11 - QUAD $0x0c1a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 12 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0d1a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 13 - QUAD $0x0e1a0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 26], 14 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0f1a0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 26], 15 - LONG $0x7cb60f42; WORD $0x1a36 // movzx edi, byte [rsi + r14 + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x011a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 1 - QUAD $0x021a064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 26], 2 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x031a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 3 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x041a064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 26], 4 - QUAD $0x051a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 5 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x061a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x071a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 7 - QUAD $0x081a1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 26], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x091a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 9 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0a1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 10 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0b1a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 12 - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - QUAD $0x0d1a3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 26], 13 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0e1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 14 - QUAD $0x0f1a1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 26], 15 - LONG $0x067cb60f; BYTE $0x1b // movzx edi, byte [rsi + rax + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 1 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x021b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 2 - QUAD $0x031b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 27], 3 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x041b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 27], 4 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x051b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 5 - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x061b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 27], 6 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x071b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 7 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x081b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 27], 8 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x091b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 9 + LONG $0x54b60f42; WORD $0x1a1f // movzx edx, byte [rdi + r11 + 26] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 1 + QUAD $0x021a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 3 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x041a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 4 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x051a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 5 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x061a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 6 + QUAD $0x071a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 7 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x081a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 8 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x091a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 9 + QUAD $0x0a1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 10 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x0b1a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 11 + QUAD $0x0c1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 12 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0a1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 10 - QUAD $0x0b1b2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 27], 11 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0c1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d1b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 13 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x0e1b2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 27], 14 - QUAD $0x0f1b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 27], 15 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x1b0e // movzx edi, byte [rsi + r9 + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x011b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 1 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x021b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 2 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x031b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 3 - QUAD $0x041b065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 27], 4 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x051b1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 27], 5 + QUAD $0x0d1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 13 + QUAD $0x0e1a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 15 + LONG $0x0f54b60f; BYTE $0x1a // movzx edx, byte [rdi + rcx + 26] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x011a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x021a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x031a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 3 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x041a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 4 LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x061b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x071b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 7 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x081b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x091b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 9 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0a1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 10 - QUAD $0x0b1b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 11 + QUAD $0x051a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 5 + QUAD $0x061a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 6 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x071a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 7 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x081a1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 26], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x091a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 9 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0a1a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 10 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0b1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 11 QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0c1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 12 - QUAD $0x0d1b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 13 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0e1b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 14 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0f1b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 15 + QUAD $0x0c1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 12 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x0d1a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e1a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 14 + QUAD $0x0f1a174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 26], 15 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + LONG $0x54b60f42; WORD $0x1b37 // movzx edx, byte [rdi + r14 + 27] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x041b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 4 + QUAD $0x051b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 5 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x061b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 6 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x071b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 7 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x081b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 8 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + QUAD $0x091b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 10 + QUAD $0x0b1b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 13 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0e1b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1754b60f; BYTE $0x1b // movzx edx, byte [rdi + rdx + 27] + LONG $0xda6ef9c5 // vmovd xmm3, edx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x011b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 1 + QUAD $0x021b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 2 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x031b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 3 + QUAD $0x041b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x051b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + QUAD $0x071b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 7 + QUAD $0x081b1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 27], 8 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x091b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 9 + QUAD $0x0a1b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 10 + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x0d1b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 13 + QUAD $0x0e1b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x1c // movzx edi, byte [rsi + rdx + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x011c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 1 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x021c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 2 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x031c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 3 - QUAD $0x041c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 4 - QUAD $0x051c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 5 - QUAD $0x061c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 6 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x071c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 7 - QUAD $0x081c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 28], 8 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x091c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 9 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0a1c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b1c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 11 - QUAD $0x0c1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 12 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x0d1c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 28], 13 - QUAD $0x0e1c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 28], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 15 - LONG $0x7cb60f42; WORD $0x1c0e // movzx edi, byte [rsi + r9 + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x011c1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 28], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x021c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 2 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x031c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x041c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 4 - QUAD $0x051c1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 28], 5 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x061c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 6 - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x071c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 7 + LONG $0x54b60f42; WORD $0x1c37 // movzx edx, byte [rdi + r14 + 28] + LONG $0xc26ef9c5 // vmovd xmm0, edx LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x081c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x091c1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 28], 9 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0a1c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 10 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0b1c0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 28], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c1c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 12 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x0d1c164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 28], 13 - QUAD $0x0e1c264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 28], 14 - QUAD $0x0f1c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x1d // movzx edi, byte [rsi + rax + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] - QUAD $0x011d26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 29], 1 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x021d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 2 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x031d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 3 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x041d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 4 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x051d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 5 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x061d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 6 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x071d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x081d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 8 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x091d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 9 - QUAD $0x0a1d06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 29], 10 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0b1d06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 29], 11 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0c1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 12 - QUAD $0x0d1d36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 29], 13 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x0e1d36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 29], 14 + QUAD $0x011c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 2 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x1d // movzx edi, byte [rsi + rax + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x011d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 29], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x021d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 2 - QUAD $0x031d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 29], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x041d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 4 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x051d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 29], 5 - QUAD $0x061d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 29], 6 - QUAD $0x071d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 29], 7 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x081d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 29], 8 - QUAD $0x091d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 29], 9 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0a1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 10 - QUAD $0x0b1d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 12 - QUAD $0x0d1d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 29], 13 - LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] - QUAD $0x0e1d0e642061a3c4 // vpinsrb xmm4, xmm3, byte [rsi + r9 + 29], 14 + QUAD $0x031c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 3 + QUAD $0x041c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 4 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x051c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x061c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 6 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x071c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 7 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + QUAD $0x081c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 8 + QUAD $0x091c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 10 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 11 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0c1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 12 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0d1c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 13 + QUAD $0x0e1c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 15 + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + LONG $0x54b60f42; WORD $0x1c17 // movzx edx, byte [rdi + r10 + 28] + LONG $0xca6ef9c5 // vmovd xmm1, edx + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x011c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x021c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 2 + QUAD $0x031c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 3 + QUAD $0x041c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 4 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x051c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 5 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x061c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 6 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x071c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 7 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x081c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 8 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x091c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 9 + QUAD $0x0a1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 10 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0b1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 11 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0c1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 13 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0e1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 14 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 15 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + LONG $0x1754b60f; BYTE $0x1d // movzx edx, byte [rdi + rdx + 29] + LONG $0xd26ef9c5 // vmovd xmm2, edx + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x011d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 3 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x041d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 4 + QUAD $0x051d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 5 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x061d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 6 + QUAD $0x071d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 7 + QUAD $0x081d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 8 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x091d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 9 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0a1d17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 29], 10 + QUAD $0x0b1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 11 + QUAD $0x0c1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 12 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0d1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 13 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x0e1d1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 29], 14 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0f1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 15 + LONG $0x54b60f42; WORD $0x1d17 // movzx edx, byte [rdi + r10 + 29] + LONG $0xda6ef9c5 // vmovd xmm3, edx + QUAD $0x011d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 1 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x021d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 29], 2 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x031d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 3 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x041d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 4 + QUAD $0x051d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 5 + QUAD $0x061d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 6 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x071d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 7 + QUAD $0x081d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 8 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x091d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 9 + QUAD $0x0a1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 11 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0c1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 12 + QUAD $0x0d1d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 13 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0e1d1f642061e3c4 // vpinsrb xmm4, xmm3, byte [rdi + rbx + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x0f1d3e442059a3c4 // vpinsrb xmm0, xmm4, byte [rsi + r15 + 29], 15 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f1d07442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rax + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1e7cb60f; BYTE $0x1e // movzx edi, byte [rsi + rbx + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 30], 1 - LONG $0x1e7cb60f; BYTE $0x1f // movzx edi, byte [rsi + rbx + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 31], 1 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x021e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 2 - QUAD $0x021f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 2 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x031e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 3 - QUAD $0x031f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 3 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x051e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 5 - QUAD $0x051f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 5 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x061e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 6 - QUAD $0x061f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 6 - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] + LONG $0x0754b60f; BYTE $0x1e // movzx edx, byte [rdi + rax + 30] + LONG $0xc26ef9c5 // vmovd xmm0, edx + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x011e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 30], 1 + LONG $0x0754b60f; BYTE $0x1f // movzx edx, byte [rdi + rax + 31] + LONG $0xca6ef9c5 // vmovd xmm1, edx + QUAD $0x011f0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 31], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x0000011024948b48 // mov rdx, qword [rsp + 272] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + QUAD $0x091e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 30], 9 + QUAD $0x091f3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 31], 9 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 + QUAD $0x0b1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 11 + QUAD $0x0b1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 11 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0a1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 10 - QUAD $0x0a1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 10 - QUAD $0x0b1e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 30], 11 - QUAD $0x0b1f064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 31], 11 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0c1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 12 - QUAD $0x0c1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 13 - QUAD $0x0d1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 13 - QUAD $0x0e1e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 30], 14 - QUAD $0x0e1f364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 31], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 15 - QUAD $0x0f1f06542071e3c4 // vpinsrb xmm2, xmm1, byte [rsi + rax + 31], 15 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e44b60f; BYTE $0x1e // movzx eax, byte [rsi + rcx + 30] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + QUAD $0x0e1e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 30], 14 + QUAD $0x0e1f1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 31], 14 + QUAD $0x0f1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 15 + QUAD $0x0f1f07542071a3c4 // vpinsrb xmm2, xmm1, byte [rdi + r8 + 31], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - QUAD $0x011e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 30], 1 - LONG $0x0e44b60f; BYTE $0x1f // movzx eax, byte [rsi + rcx + 31] + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x011e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 31], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x021e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 2 - QUAD $0x021f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 2 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x041e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 4 - QUAD $0x041f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 4 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 + QUAD $0x011f077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 31], 1 + QUAD $0x021e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 30], 2 + QUAD $0x021f377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 31], 2 + QUAD $0x031e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 3 + QUAD $0x031f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 3 + QUAD $0x041e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 4 + QUAD $0x041f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 4 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x061e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 6 - QUAD $0x061f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x071e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 7 - QUAD $0x071f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 7 - QUAD $0x081e2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 30], 8 - QUAD $0x081f2e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r13 + 31], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 9 - QUAD $0x091f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 9 + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x071e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 7 + QUAD $0x071f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 7 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 30], 9 + QUAD $0x091f0f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r9 + 31], 9 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x0c1e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 12 + QUAD $0x0c1f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 11 - QUAD $0x0b1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 12 - QUAD $0x0c1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 12 - QUAD $0x0d1e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 30], 13 - QUAD $0x0d1f167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 31], 13 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x0e1e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 30], 14 - QUAD $0x0e1f0e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 31], 14 - QUAD $0x0f1e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 30], 15 - QUAD $0x0f1f3e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 31], 15 + QUAD $0x0d1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 13 + QUAD $0x0d1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 13 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x0e1e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 14 + QUAD $0x0e1f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 - LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 + LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 + QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 QUAD $0x00020024946ffdc5; BYTE $0x00 // vmovdqa ymm2, yword [rsp + 512] LONG $0xc27495c5 // vpcmpeqb ymm0, ymm13, ymm2 QUAD $0x0004c024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1216] @@ -27493,10 +28217,10 @@ LBB4_170: LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 QUAD $0x0002c024a474edc5; BYTE $0x00 // vpcmpeqb ymm4, ymm2, yword [rsp + 704] LONG $0xe1dfddc5 // vpandn ymm4, ymm4, ymm1 - QUAD $0x000120248c74edc5; BYTE $0x00 // vpcmpeqb ymm1, ymm2, yword [rsp + 288] + QUAD $0x000140248c74edc5; BYTE $0x00 // vpcmpeqb ymm1, ymm2, yword [rsp + 320] LONG $0xdf75c1c4; BYTE $0xcd // vpandn ymm1, ymm1, ymm13 LONG $0xc9ebddc5 // vpor ymm1, ymm4, ymm1 - QUAD $0x000140249474edc5; BYTE $0x00 // vpcmpeqb ymm2, ymm2, yword [rsp + 320] + QUAD $0x000120249474edc5; BYTE $0x00 // vpcmpeqb ymm2, ymm2, yword [rsp + 288] LONG $0xdf6dc1c4; BYTE $0xd6 // vpandn ymm2, ymm2, ymm14 LONG $0xcaebf5c5 // vpor ymm1, ymm1, ymm2 LONG $0xc9ebe5c5 // vpor ymm1, ymm3, ymm1 @@ -27513,21 +28237,21 @@ LBB4_170: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x7f7ec1c4; WORD $0x8b44; BYTE $0x60 // vmovdqu yword [r11 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8b54; BYTE $0x40 // vmovdqu yword [r11 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8b64; BYTE $0x20 // vmovdqu yword [r11 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8b0c // vmovdqu yword [r11 + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608a // vmovdqu yword [rdx + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408a // vmovdqu yword [rdx + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208a // vmovdqu yword [rdx + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8a // vmovdqu yword [rdx + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB4_170 - QUAD $0x0000018824bc8b4c // mov r15, qword [rsp + 392] - QUAD $0x0000018024bc3b4c // cmp r15, qword [rsp + 384] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - QUAD $0x0000019024a48b4c // mov r12, qword [rsp + 400] - JNE LBB4_89 - JMP LBB4_125 + JNE LBB4_194 + QUAD $0x00000188248c8b48 // mov rcx, qword [rsp + 392] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + LONG $0x24648b44; BYTE $0x1c // mov r12d, dword [rsp + 28] + QUAD $0x0000019024b48b48 // mov rsi, qword [rsp + 400] + JNE LBB4_153 + JMP LBB4_157 DATA LCDATA4<>+0x000(SB)/8, $0x0202020202020202 DATA LCDATA4<>+0x008(SB)/8, $0x0202020202020202 @@ -27559,7 +28283,7 @@ DATA LCDATA4<>+0x0d0(SB)/8, $0x8080808080808080 DATA LCDATA4<>+0x0d8(SB)/8, $0x8080808080808080 GLOBL LCDATA4<>(SB), 8, $224 -TEXT ·_comparison_not_equal_scalar_arr_avx2(SB), $1320-48 +TEXT ·_comparison_not_equal_scalar_arr_avx2(SB), $1288-48 MOVQ typ+0(FP), DI MOVQ left+8(FP), SI @@ -27570,335 +28294,363 @@ TEXT ·_comparison_not_equal_scalar_arr_avx2(SB), $1320-48 MOVQ SP, BP ADDQ $32, SP ANDQ $-32, SP - MOVQ BP, 1280(SP) + MOVQ BP, 1248(SP) LEAQ LCDATA4<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB5_17 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB5_32 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB5_63 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB5_75 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB5_164 - WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB5_7: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - LONG $0x44b60f45; WORD $0x0035 // movzx r8d, byte [r13 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_7 - LONG $0x01c58349 // add r13, 1 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x8949; BYTE $0xcd // mov r13, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB5_19 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB5_36 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB5_59 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB5_73 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB5_188 + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_11 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_9 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_8: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_8 LBB5_9: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_13 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 LBB5_11: - QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 - LONG $0x7c723b44 // cmp r14d, dword [rdx + 124] - LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0x78723b44 // cmp r14d, dword [rdx + 120] - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x74723b44 // cmp r14d, dword [rdx + 116] - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x70723b44 // cmp r14d, dword [rdx + 112] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6c723b44 // cmp r14d, dword [rdx + 108] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x68723b44 // cmp r14d, dword [rdx + 104] - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x64723b44 // cmp r14d, dword [rdx + 100] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x5c723b44 // cmp r14d, dword [rdx + 92] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x58723b44 // cmp r14d, dword [rdx + 88] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x54723b44 // cmp r14d, dword [rdx + 84] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x50723b44 // cmp r14d, dword [rdx + 80] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x4c723b44 // cmp r14d, dword [rdx + 76] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x48723b44 // cmp r14d, dword [rdx + 72] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x44723b44 // cmp r14d, dword [rdx + 68] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x3c723b44 // cmp r14d, dword [rdx + 60] - LONG $0xd0950f41 // setne r8b - LONG $0x38723b44 // cmp r14d, dword [rdx + 56] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x34723b44 // cmp r14d, dword [rdx + 52] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x30723b44 // cmp r14d, dword [rdx + 48] - LONG $0xd3950f41 // setne r11b - LONG $0x2c723b44 // cmp r14d, dword [rdx + 44] - LONG $0xd2950f41 // setne r10b - LONG $0x28723b44 // cmp r14d, dword [rdx + 40] - LONG $0xd1950f41 // setne r9b - LONG $0x24723b44 // cmp r14d, dword [rdx + 36] - LONG $0xd7950f40 // setne dil - LONG $0x1c723b44 // cmp r14d, dword [rdx + 28] - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x18723b44 // cmp r14d, dword [rdx + 24] - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x14723b44 // cmp r14d, dword [rdx + 20] - LONG $0xd6950f40 // setne sil - LONG $0x10723b44 // cmp r14d, dword [rdx + 16] - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x0c723b44 // cmp r14d, dword [rdx + 12] - LONG $0xd4950f41 // setne r12b - LONG $0x08723b44 // cmp r14d, dword [rdx + 8] - LONG $0xd5950f41 // setne r13b - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] - LONG $0xd7950f41 // setne r15b - LONG $0x20723b44 // cmp r14d, dword [rdx + 32] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x40723b44 // cmp r14d, dword [rdx + 64] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x60723b44 // cmp r14d, dword [rdx + 96] - QUAD $0x000000802494950f // setne byte [rsp + 128] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000b024bc0244 // add r15b, byte [rsp + 176] - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xec // or r12b, r13b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000009824bc0240 // add dil, byte [rsp + 152] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] - WORD $0xc189 // mov ecx, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x80ea8348 // sub rdx, -128 - LONG $0x04c78349 // add r15, 4 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_15 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax LBB5_13: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB5_133 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 + QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] + LONG $0xd7950f40 // setne dil + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] + LONG $0xd3950f41 // setne r11b + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] + LONG $0xd2950f41 // setne r10b + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] + LONG $0xd1950f41 // setne r9b + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] + LONG $0xd6950f40 // setne sil + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] + WORD $0x950f; BYTE $0xd1 // setne cl + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] + LONG $0xd4950f41 // setne r12b + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] + LONG $0xd5950f41 // setne r13b + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] + LONG $0xd7950f41 // setne r15b + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd6950f41 // setne r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xfd // or r13b, r15b + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x06 // mov byte [r14], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x40 // add sil, byte [rsp + 64] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017e8841 // mov byte [r14 + 1], dil + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x48244402 // add al, byte [rsp + 72] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02468841 // mov byte [r14 + 2], al + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xc000 // add al, al + LONG $0x60244402 // add al, byte [rsp + 96] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x80ea8348 // sub rdx, -128 + LONG $0x04c68349 // add r14, 4 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB5_13 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB5_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_188 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JE LBB5_129 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB5_16: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] +LBB5_18: + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + WORD $0x894d; BYTE $0xee // mov r14, r13 + LONG $0x54b60f45; WORD $0x0035 // movzx r10d, byte [r13 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0x3044; BYTE $0xd3 // xor bl, r10b LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB5_16 - JMP LBB5_160 - -LBB5_17: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB5_49 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_18 + JMP LBB5_177 + +LBB5_19: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB5_43 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 JE LBB5_86 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB5_97 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB5_164 - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_25 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB5_23: - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB5_99 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB5_188 + WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_29 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_27 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6ef9c1c4; BYTE $0xc6 // vmovq xmm0, r14 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_26: + LONG $0x012ef9c5 // vucomisd xmm0, qword [rcx] + LONG $0x08518d48 // lea rdx, [rcx + 8] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xcb08 // or bl, cl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xee // mov r14, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x0005 // movzx r9d, byte [r13 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_23 - LONG $0x01c58349 // add r13, 1 - -LBB5_25: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_29 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000c0249c894c // mov qword [rsp + 192], r11 - QUAD $0x000000b8249c894c // mov qword [rsp + 184], r11 + LONG $0x057c8841; BYTE $0x00 // mov byte [r13 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_26 LBB5_27: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 + +LBB5_29: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_33 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b824b4894c // mov qword [rsp + 184], r14 + LONG $0x6ef9c1c4; BYTE $0xc6 // vmovq xmm0, r14 + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + +LBB5_31: QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd5950f41 // setne r13b @@ -27907,7 +28659,7 @@ LBB5_27: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x422ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rdx + 24] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl @@ -27917,7 +28669,7 @@ LBB5_27: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x422ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rdx + 40] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd4950f41 // setne r12b @@ -27926,7 +28678,7 @@ LBB5_27: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl LONG $0x422ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rdx + 56] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl @@ -27936,17 +28688,17 @@ LBB5_27: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x422ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rdx + 72] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl LONG $0x422ef9c5; BYTE $0x50 // vucomisd xmm0, qword [rdx + 80] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl LONG $0x422ef9c5; BYTE $0x58 // vucomisd xmm0, qword [rdx + 88] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd3 // setne bl @@ -27960,82 +28712,82 @@ LBB5_27: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl LONG $0x422ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rdx + 112] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x422ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rdx + 120] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl QUAD $0x00000080822ef9c5 // vucomisd xmm0, qword [rdx + 128] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl QUAD $0x00000088822ef9c5 // vucomisd xmm0, qword [rdx + 136] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl QUAD $0x00000090822ef9c5 // vucomisd xmm0, qword [rdx + 144] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x58244c88 // mov byte [rsp + 88], cl QUAD $0x00000098822ef9c5 // vucomisd xmm0, qword [rdx + 152] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl QUAD $0x000000a0822ef9c5 // vucomisd xmm0, qword [rdx + 160] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl QUAD $0x000000a8822ef9c5 // vucomisd xmm0, qword [rdx + 168] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl + LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl QUAD $0x000000b0822ef9c5 // vucomisd xmm0, qword [rdx + 176] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd7950f41 // setne r15b WORD $0x0841; BYTE $0xc7 // or r15b, al QUAD $0x000000b8822ef9c5 // vucomisd xmm0, qword [rdx + 184] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd0950f41 // setne r8b - WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al QUAD $0x000000c0822ef9c5 // vucomisd xmm0, qword [rdx + 192] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl QUAD $0x000000c8822ef9c5 // vucomisd xmm0, qword [rdx + 200] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd3950f41 // setne r11b WORD $0x0841; BYTE $0xc3 // or r11b, al QUAD $0x000000d0822ef9c5 // vucomisd xmm0, qword [rdx + 208] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] - WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd1950f41 // setne r9b WORD $0x0841; BYTE $0xc1 // or r9b, al + QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd0950f41 // setne r8b + WORD $0x0841; BYTE $0xc0 // or r8b, al QUAD $0x000000e0822ef9c5 // vucomisd xmm0, qword [rdx + 224] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl QUAD $0x000000e8822ef9c5 // vucomisd xmm0, qword [rdx + 232] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl QUAD $0x000000f0822ef9c5 // vucomisd xmm0, qword [rdx + 240] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd7950f40 // setne dil @@ -28045,23 +28797,23 @@ LBB5_27: LONG $0xd6950f40 // setne sil WORD $0x0840; BYTE $0xc6 // or sil, al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] + LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] WORD $0x8944; BYTE $0xe8 // mov eax, r13d LONG $0x05e4c041 // shl r12b, 5 - LONG $0x6cb60f44; WORD $0x4824 // movzx r13d, byte [rsp + 72] + QUAD $0x00009824acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 152] LONG $0x06e5c041 // shl r13b, 6 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x64b60f44; WORD $0x3824 // movzx r12d, byte [rsp + 56] + LONG $0x64b60f44; WORD $0x3024 // movzx r12d, byte [rsp + 48] LONG $0x02e4c041 // shl r12b, 2 WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x20244c02 // add cl, byte [rsp + 32] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -28070,1066 +28822,339 @@ LBB5_27: WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xcb08 // or bl, cl - LONG $0x6cb60f44; WORD $0x2024 // movzx r13d, byte [rsp + 32] + LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - QUAD $0x00008824b4b60f44; BYTE $0x00 // movzx r14d, byte [rsp + 136] + LONG $0x74b60f44; WORD $0x6824 // movzx r14d, byte [rsp + 104] LONG $0x07e6c041 // shl r14b, 7 WORD $0x0841; BYTE $0xc6 // or r14b, al - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xc900 // add cl, cl - LONG $0x58244c02 // add cl, byte [rsp + 88] - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + LONG $0x80248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 128] + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xcb08 // or bl, cl - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd908 // or cl, bl WORD $0x8941; BYTE $0xcc // mov r12d, ecx QUAD $0x00000110248c8b48 // mov rcx, qword [rsp + 272] - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xe3 // or bl, r12b LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0x0844; BYTE $0xe8 // or al, r13b - QUAD $0x0000b024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 176] + QUAD $0x0000a824a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 168] LONG $0x05e4c041 // shl r12b, 5 LONG $0x06e7c041 // shl r15b, 6 WORD $0x0845; BYTE $0xe7 // or r15b, r12b QUAD $0x0000012024b40a44 // or r14b, byte [rsp + 288] - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf8 // or r8b, r15b - WORD $0x0841; BYTE $0xd8 // or r8b, bl + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0845; BYTE $0xfa // or r10b, r15b + WORD $0x0841; BYTE $0xda // or r10b, bl WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x00000098249c0244 // add r11b, byte [rsp + 152] - LONG $0x02e2c041 // shl r10b, 2 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xd1 // or r9b, r10b - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] + LONG $0x245c0244; BYTE $0x40 // add r11b, byte [rsp + 64] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0845; BYTE $0xc8 // or r8b, r9b + QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x8941; BYTE $0xd9 // mov r9d, ebx + WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x8941; BYTE $0xd8 // mov r8d, ebx WORD $0x0188 // mov byte [rcx], al - QUAD $0x000000a8249cb60f // movzx ebx, byte [rsp + 168] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e7c040 // shl dil, 6 WORD $0x0840; BYTE $0xdf // or dil, bl LONG $0x01718844 // mov byte [rcx + 1], r14b LONG $0x07e6c040 // shl sil, 7 WORD $0x0840; BYTE $0xfe // or sil, dil - WORD $0x0844; BYTE $0xce // or sil, r9b - LONG $0x02418844 // mov byte [rcx + 2], r8b + WORD $0x0844; BYTE $0xc6 // or sil, r8b + LONG $0x02518844 // mov byte [rcx + 2], r10b LONG $0x03718840 // mov byte [rcx + 3], sil LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 LONG $0x04c18348 // add rcx, 4 WORD $0x8949; BYTE $0xcd // mov r13, rcx - QUAD $0x000000b824848348; BYTE $0xff // add qword [rsp + 184], -1 - JNE LBB5_27 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - -LBB5_29: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB5_134 - WORD $0xff31 // xor edi, edi - JMP LBB5_136 - -LBB5_32: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB5_108 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB5_164 - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_38 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB5_36: - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xef // mov r15, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_36 - LONG $0x01c58349 // add r13, 1 - -LBB5_38: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_46 - LONG $0x20fe8349 // cmp r14, 32 - LONG $0x245c8944; BYTE $0x1c // mov dword [rsp + 28], r11d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000018024b4894c // mov qword [rsp + 384], r14 - JB LBB5_42 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc5 // cmp r13, rax - JAE LBB5_165 - QUAD $0x00000000b5048d4a // lea rax, [4*r14] - WORD $0x014c; BYTE $0xe8 // add rax, r13 - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB5_165 - -LBB5_42: - WORD $0xc031 // xor eax, eax - QUAD $0x0000017824848948 // mov qword [rsp + 376], rax - -LBB5_43: - QUAD $0x0000017824b42b4c // sub r14, qword [rsp + 376] - QUAD $0x000000a024b4894c // mov qword [rsp + 160], r14 - -LBB5_44: - LONG $0x1f5a3a44 // cmp r11b, byte [rdx + 31] - QUAD $0x000001102494950f // setne byte [rsp + 272] - LONG $0x1e5a3a44 // cmp r11b, byte [rdx + 30] - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x1d5a3a44 // cmp r11b, byte [rdx + 29] - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x1c5a3a44 // cmp r11b, byte [rdx + 28] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x1b5a3a44 // cmp r11b, byte [rdx + 27] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x1a5a3a44 // cmp r11b, byte [rdx + 26] - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x195a3a44 // cmp r11b, byte [rdx + 25] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x175a3a44 // cmp r11b, byte [rdx + 23] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x165a3a44 // cmp r11b, byte [rdx + 22] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x155a3a44 // cmp r11b, byte [rdx + 21] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x145a3a44 // cmp r11b, byte [rdx + 20] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x135a3a44 // cmp r11b, byte [rdx + 19] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x125a3a44 // cmp r11b, byte [rdx + 18] - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x115a3a44 // cmp r11b, byte [rdx + 17] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x0f5a3a44 // cmp r11b, byte [rdx + 15] - LONG $0xd6950f41 // setne r14b - LONG $0x0e5a3a44 // cmp r11b, byte [rdx + 14] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x0d5a3a44 // cmp r11b, byte [rdx + 13] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x0c5a3a44 // cmp r11b, byte [rdx + 12] - LONG $0xd4950f41 // setne r12b - LONG $0x0b5a3a44 // cmp r11b, byte [rdx + 11] - LONG $0xd7950f41 // setne r15b - LONG $0x0a5a3a44 // cmp r11b, byte [rdx + 10] - LONG $0xd3950f41 // setne r11b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] - LONG $0xd2950f41 // setne r10b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7950f40 // setne dil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0xd1950f41 // setne r9b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0xd0950f41 // setne r8b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0xd6950f40 // setne sil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x023a // cmp al, byte [rdx] - QUAD $0x000000a82494950f // setne byte [rsp + 168] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x01 // cmp al, byte [rdx + 1] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] - LONG $0x086a3a44 // cmp r13b, byte [rdx + 8] - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5a3a; BYTE $0x10 // cmp bl, byte [rdx + 16] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5a3a; BYTE $0x18 // cmp bl, byte [rdx + 24] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - WORD $0xc000 // add al, al - LONG $0xa8248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 168] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al - LONG $0x03e6c040 // shl sil, 3 - WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x04e0c041 // shl r8b, 4 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x05e1c041 // shl r9b, 5 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xc7 // or dil, al - WORD $0x0844; BYTE $0xcf // or dil, r9b - LONG $0x007d8841 // mov byte [r13], dil - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xce // or r14b, cl - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x01758845 // mov byte [r13 + 1], r14b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] - WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x40244402 // add al, byte [rsp + 64] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x20c28348 // add rdx, 32 - LONG $0x04c58349 // add r13, 4 - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB5_44 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000018024b48b4c // mov r14, qword [rsp + 384] - -LBB5_46: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JE LBB5_122 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - -LBB5_139: - LONG $0x321c3a44 // cmp r11b, byte [rdx + rsi] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl - LONG $0x325c3a44; BYTE $0x01 // cmp r11b, byte [rdx + rsi + 1] - LONG $0x02768d48 // lea rsi, [rsi + 2] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB5_139 - JMP LBB5_155 - -LBB5_49: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB5_123 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB5_164 - WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_55 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB5_53: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - LONG $0x44b60f45; WORD $0x0035 // movzx r8d, byte [r13 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_53 - LONG $0x01c58349 // add r13, 1 - -LBB5_55: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_59 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - -LBB5_57: - QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 - LONG $0xf8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 248] - LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0xf0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 240] - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0xe8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 232] - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0xe0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 224] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0xd8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 216] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0xd0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 208] - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0xc8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 200] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0xb8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 184] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0xb0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 176] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0xa8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 168] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0xa0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 160] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x98b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 152] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x90b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 144] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x88b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 136] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x78723b4c // cmp r14, qword [rdx + 120] - LONG $0xd0950f41 // setne r8b - LONG $0x70723b4c // cmp r14, qword [rdx + 112] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x68723b4c // cmp r14, qword [rdx + 104] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x60723b4c // cmp r14, qword [rdx + 96] - LONG $0xd3950f41 // setne r11b - LONG $0x58723b4c // cmp r14, qword [rdx + 88] - LONG $0xd2950f41 // setne r10b - LONG $0x50723b4c // cmp r14, qword [rdx + 80] - LONG $0xd1950f41 // setne r9b - LONG $0x48723b4c // cmp r14, qword [rdx + 72] - LONG $0xd7950f40 // setne dil - LONG $0x38723b4c // cmp r14, qword [rdx + 56] - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x30723b4c // cmp r14, qword [rdx + 48] - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x28723b4c // cmp r14, qword [rdx + 40] - LONG $0xd6950f40 // setne sil - LONG $0x20723b4c // cmp r14, qword [rdx + 32] - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x18723b4c // cmp r14, qword [rdx + 24] - LONG $0xd4950f41 // setne r12b - LONG $0x10723b4c // cmp r14, qword [rdx + 16] - LONG $0xd5950f41 // setne r13b - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x08723b4c // cmp r14, qword [rdx + 8] - LONG $0xd7950f41 // setne r15b - LONG $0x40723b4c // cmp r14, qword [rdx + 64] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x80b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 128] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xc0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 192] - QUAD $0x000000802494950f // setne byte [rsp + 128] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000b024bc0244 // add r15b, byte [rsp + 176] - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xec // or r12b, r13b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000009824bc0240 // add dil, byte [rsp + 152] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] - WORD $0xc189 // mov ecx, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c78349 // add r15, 4 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_57 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - -LBB5_59: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB5_96 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi - -LBB5_62: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x08723b4c // cmp r14, qword [rdx + 8] - LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB5_62 - JMP LBB5_146 - -LBB5_63: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_67 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB5_65: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - LONG $0x44b60f45; WORD $0x0035 // movzx r8d, byte [r13 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_65 - LONG $0x01c58349 // add r13, 1 - -LBB5_67: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_71 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - -LBB5_69: - QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 - LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] - LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] - QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] - QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] - LONG $0xd0950f41 // setne r8b - LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] - LONG $0xd3950f41 // setne r11b - LONG $0x723b4466; BYTE $0x16 // cmp r14w, word [rdx + 22] - LONG $0xd2950f41 // setne r10b - LONG $0x723b4466; BYTE $0x14 // cmp r14w, word [rdx + 20] - LONG $0xd1950f41 // setne r9b - LONG $0x723b4466; BYTE $0x12 // cmp r14w, word [rdx + 18] - LONG $0xd7950f40 // setne dil - LONG $0x723b4466; BYTE $0x0e // cmp r14w, word [rdx + 14] - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x723b4466; BYTE $0x0c // cmp r14w, word [rdx + 12] - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x723b4466; BYTE $0x0a // cmp r14w, word [rdx + 10] - LONG $0xd6950f40 // setne sil - LONG $0x723b4466; BYTE $0x08 // cmp r14w, word [rdx + 8] - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x723b4466; BYTE $0x06 // cmp r14w, word [rdx + 6] - LONG $0xd4950f41 // setne r12b - LONG $0x723b4466; BYTE $0x04 // cmp r14w, word [rdx + 4] - LONG $0xd5950f41 // setne r13b - LONG $0x323b4466 // cmp r14w, word [rdx] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] - LONG $0xd7950f41 // setne r15b - LONG $0x723b4466; BYTE $0x10 // cmp r14w, word [rdx + 16] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x723b4466; BYTE $0x20 // cmp r14w, word [rdx + 32] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x723b4466; BYTE $0x30 // cmp r14w, word [rdx + 48] - QUAD $0x000000802494950f // setne byte [rsp + 128] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000b024bc0244 // add r15b, byte [rsp + 176] - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xec // or r12b, r13b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000009824bc0240 // add dil, byte [rsp + 152] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] - WORD $0xc189 // mov ecx, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x40c28348 // add rdx, 64 - LONG $0x04c78349 // add r15, 4 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_69 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 + JNE LBB5_31 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] -LBB5_71: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB5_85 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi +LBB5_33: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB5_188 + LONG $0x6ef9c1c4; BYTE $0xc6 // vmovq xmm0, r14 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB5_158 + WORD $0xff31 // xor edi, edi + JMP LBB5_160 -LBB5_74: - LONG $0x323b4466 // cmp r14w, word [rdx] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl +LBB5_36: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB5_112 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB5_188 + WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_130 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_132 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB5_41: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x001d // movzx r9d, byte [r13 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB5_74 - JMP LBB5_142 + LONG $0x1d448841; BYTE $0x00 // mov byte [r13 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB5_41 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JNE LBB5_133 + JMP LBB5_188 -LBB5_75: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_79 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB5_43: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB5_117 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB5_188 + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_51 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_49 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB5_77: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - LONG $0x44b60f45; WORD $0x0035 // movzx r8d, byte [r13 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_77 - LONG $0x01c58349 // add r13, 1 +LBB5_48: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_48 -LBB5_79: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_83 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 +LBB5_49: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 + +LBB5_51: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_55 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax -LBB5_81: +LBB5_53: QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 - LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] - LONG $0xd0950f41 // setne r8b - LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] + LONG $0xd7950f40 // setne dil + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] LONG $0xd3950f41 // setne r11b - LONG $0x723b4466; BYTE $0x16 // cmp r14w, word [rdx + 22] + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd2950f41 // setne r10b - LONG $0x723b4466; BYTE $0x14 // cmp r14w, word [rdx + 20] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd1950f41 // setne r9b - LONG $0x723b4466; BYTE $0x12 // cmp r14w, word [rdx + 18] - LONG $0xd7950f40 // setne dil - LONG $0x723b4466; BYTE $0x0e // cmp r14w, word [rdx + 14] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] + LONG $0xd6950f40 // setne sil + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x723b4466; BYTE $0x0c // cmp r14w, word [rdx + 12] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x723b4466; BYTE $0x0a // cmp r14w, word [rdx + 10] - LONG $0xd6950f40 // setne sil - LONG $0x723b4466; BYTE $0x08 // cmp r14w, word [rdx + 8] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x723b4466; BYTE $0x06 // cmp r14w, word [rdx + 6] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] LONG $0xd4950f41 // setne r12b - LONG $0x723b4466; BYTE $0x04 // cmp r14w, word [rdx + 4] + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd5950f41 // setne r13b - LONG $0x323b4466 // cmp r14w, word [rdx] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] LONG $0xd7950f41 // setne r15b - LONG $0x723b4466; BYTE $0x10 // cmp r14w, word [rdx + 16] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x723b4466; BYTE $0x20 // cmp r14w, word [rdx + 32] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x723b4466; BYTE $0x30 // cmp r14w, word [rdx + 48] - QUAD $0x000000802494950f // setne byte [rsp + 128] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000b024bc0244 // add r15b, byte [rsp + 176] - LONG $0x02e5c041 // shl r13b, 2 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0xd6950f41 // setne r14b + LONG $0x40423b4c // cmp r8, qword [rdx + 64] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xfd // or r13b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e4c041 // shl r12b, 3 + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x04e4c041 // shl r12b, 4 WORD $0x0845; BYTE $0xec // or r12b, r13b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000009824bc0240 // add dil, byte [rsp + 152] + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x06 // mov byte [r14], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x40 // add sil, byte [rsp + 64] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017e8841 // mov byte [r14 + 1], dil + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] + LONG $0x48244402 // add al, byte [rsp + 72] WORD $0xc189 // mov ecx, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x02468841 // mov byte [r14 + 2], al + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -29143,214 +29168,754 @@ LBB5_81: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x40c28348 // add rdx, 64 - LONG $0x04c78349 // add r15, 4 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c68349 // add r14, 4 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB5_53 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB5_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_188 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JE LBB5_98 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 + WORD $0xff31 // xor edi, edi + +LBB5_58: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xee // mov r14, r13 + LONG $0x54b60f45; WORD $0x0035 // movzx r10d, byte [r13 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_58 + JMP LBB5_168 + +LBB5_59: + LONG $0x06b70f44 // movzx r8d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_65 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_63 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_62: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x013b4466 // cmp r8w, word [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_62 + +LBB5_63: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 + +LBB5_65: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_69 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB5_67: + QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 + LONG $0x423b4466; BYTE $0x3e // cmp r8w, word [rdx + 62] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] + LONG $0x423b4466; BYTE $0x3c // cmp r8w, word [rdx + 60] + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x423b4466; BYTE $0x3a // cmp r8w, word [rdx + 58] + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x423b4466; BYTE $0x38 // cmp r8w, word [rdx + 56] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x423b4466; BYTE $0x36 // cmp r8w, word [rdx + 54] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x423b4466; BYTE $0x34 // cmp r8w, word [rdx + 52] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x423b4466; BYTE $0x32 // cmp r8w, word [rdx + 50] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x423b4466; BYTE $0x2e // cmp r8w, word [rdx + 46] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x423b4466; BYTE $0x2c // cmp r8w, word [rdx + 44] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x423b4466; BYTE $0x2a // cmp r8w, word [rdx + 42] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x423b4466; BYTE $0x28 // cmp r8w, word [rdx + 40] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x423b4466; BYTE $0x26 // cmp r8w, word [rdx + 38] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x423b4466; BYTE $0x24 // cmp r8w, word [rdx + 36] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x423b4466; BYTE $0x22 // cmp r8w, word [rdx + 34] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x423b4466; BYTE $0x1e // cmp r8w, word [rdx + 30] + LONG $0xd7950f40 // setne dil + LONG $0x423b4466; BYTE $0x1c // cmp r8w, word [rdx + 28] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x423b4466; BYTE $0x1a // cmp r8w, word [rdx + 26] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x423b4466; BYTE $0x18 // cmp r8w, word [rdx + 24] + LONG $0xd3950f41 // setne r11b + LONG $0x423b4466; BYTE $0x16 // cmp r8w, word [rdx + 22] + LONG $0xd2950f41 // setne r10b + LONG $0x423b4466; BYTE $0x14 // cmp r8w, word [rdx + 20] + LONG $0xd1950f41 // setne r9b + LONG $0x423b4466; BYTE $0x12 // cmp r8w, word [rdx + 18] + LONG $0xd6950f40 // setne sil + LONG $0x423b4466; BYTE $0x0e // cmp r8w, word [rdx + 14] + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x423b4466; BYTE $0x0c // cmp r8w, word [rdx + 12] + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x423b4466; BYTE $0x0a // cmp r8w, word [rdx + 10] + WORD $0x950f; BYTE $0xd1 // setne cl + LONG $0x423b4466; BYTE $0x08 // cmp r8w, word [rdx + 8] + LONG $0xd4950f41 // setne r12b + LONG $0x423b4466; BYTE $0x06 // cmp r8w, word [rdx + 6] + LONG $0xd5950f41 // setne r13b + LONG $0x423b4466; BYTE $0x04 // cmp r8w, word [rdx + 4] + LONG $0xd7950f41 // setne r15b + LONG $0x023b4466 // cmp r8w, word [rdx] + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] + LONG $0xd6950f41 // setne r14b + LONG $0x423b4466; BYTE $0x10 // cmp r8w, word [rdx + 16] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x423b4466; BYTE $0x20 // cmp r8w, word [rdx + 32] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x423b4466; BYTE $0x30 // cmp r8w, word [rdx + 48] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xfd // or r13b, r15b + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x06 // mov byte [r14], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x40 // add sil, byte [rsp + 64] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017e8841 // mov byte [r14 + 1], dil + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x48244402 // add al, byte [rsp + 72] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02468841 // mov byte [r14 + 2], al + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xc000 // add al, al + LONG $0x60244402 // add al, byte [rsp + 96] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c68349 // add r14, 4 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB5_67 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB5_69: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_188 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JE LBB5_85 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 + WORD $0xff31 // xor edi, edi + +LBB5_72: + LONG $0x023b4466 // cmp r8w, word [rdx] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xee // mov r14, r13 + LONG $0x54b60f45; WORD $0x0035 // movzx r10d, byte [r13 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] + LONG $0x04528d48 // lea rdx, [rdx + 4] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_72 + JMP LBB5_164 + +LBB5_73: + LONG $0x06b70f44 // movzx r8d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_79 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_77 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_76: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x013b4466 // cmp r8w, word [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_76 + +LBB5_77: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 + +LBB5_79: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_83 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB5_81: + QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 + LONG $0x423b4466; BYTE $0x3e // cmp r8w, word [rdx + 62] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] + LONG $0x423b4466; BYTE $0x3c // cmp r8w, word [rdx + 60] + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x423b4466; BYTE $0x3a // cmp r8w, word [rdx + 58] + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x423b4466; BYTE $0x38 // cmp r8w, word [rdx + 56] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x423b4466; BYTE $0x36 // cmp r8w, word [rdx + 54] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x423b4466; BYTE $0x34 // cmp r8w, word [rdx + 52] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x423b4466; BYTE $0x32 // cmp r8w, word [rdx + 50] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x423b4466; BYTE $0x2e // cmp r8w, word [rdx + 46] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x423b4466; BYTE $0x2c // cmp r8w, word [rdx + 44] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x423b4466; BYTE $0x2a // cmp r8w, word [rdx + 42] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x423b4466; BYTE $0x28 // cmp r8w, word [rdx + 40] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x423b4466; BYTE $0x26 // cmp r8w, word [rdx + 38] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x423b4466; BYTE $0x24 // cmp r8w, word [rdx + 36] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x423b4466; BYTE $0x22 // cmp r8w, word [rdx + 34] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x423b4466; BYTE $0x1e // cmp r8w, word [rdx + 30] + LONG $0xd7950f40 // setne dil + LONG $0x423b4466; BYTE $0x1c // cmp r8w, word [rdx + 28] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x423b4466; BYTE $0x1a // cmp r8w, word [rdx + 26] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x423b4466; BYTE $0x18 // cmp r8w, word [rdx + 24] + LONG $0xd3950f41 // setne r11b + LONG $0x423b4466; BYTE $0x16 // cmp r8w, word [rdx + 22] + LONG $0xd2950f41 // setne r10b + LONG $0x423b4466; BYTE $0x14 // cmp r8w, word [rdx + 20] + LONG $0xd1950f41 // setne r9b + LONG $0x423b4466; BYTE $0x12 // cmp r8w, word [rdx + 18] + LONG $0xd6950f40 // setne sil + LONG $0x423b4466; BYTE $0x0e // cmp r8w, word [rdx + 14] + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x423b4466; BYTE $0x0c // cmp r8w, word [rdx + 12] + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x423b4466; BYTE $0x0a // cmp r8w, word [rdx + 10] + WORD $0x950f; BYTE $0xd1 // setne cl + LONG $0x423b4466; BYTE $0x08 // cmp r8w, word [rdx + 8] + LONG $0xd4950f41 // setne r12b + LONG $0x423b4466; BYTE $0x06 // cmp r8w, word [rdx + 6] + LONG $0xd5950f41 // setne r13b + LONG $0x423b4466; BYTE $0x04 // cmp r8w, word [rdx + 4] + LONG $0xd7950f41 // setne r15b + LONG $0x023b4466 // cmp r8w, word [rdx] + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] + LONG $0xd6950f41 // setne r14b + LONG $0x423b4466; BYTE $0x10 // cmp r8w, word [rdx + 16] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x423b4466; BYTE $0x20 // cmp r8w, word [rdx + 32] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x423b4466; BYTE $0x30 // cmp r8w, word [rdx + 48] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xfd // or r13b, r15b + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x06 // mov byte [r14], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x40 // add sil, byte [rsp + 64] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017e8841 // mov byte [r14 + 1], dil + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x48244402 // add al, byte [rsp + 72] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02468841 // mov byte [r14 + 2], al + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xc000 // add al, al + LONG $0x60244402 // add al, byte [rsp + 96] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c68349 // add r14, 4 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 JNE LBB5_81 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] LBB5_83: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB5_140 + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_188 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB5_162 LBB5_85: WORD $0xff31 // xor edi, edi - JMP LBB5_142 + JMP LBB5_164 LBB5_86: - WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_90 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB5_88: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - LONG $0x44b60f45; WORD $0x0035 // movzx r8d, byte [r13 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_88 - LONG $0x01c58349 // add r13, 1 + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_92 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_90 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_89: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_89 LBB5_90: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_94 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 LBB5_92: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_96 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB5_94: QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 - LONG $0xf8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 248] + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0xf0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 240] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0xe8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 232] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0xe0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 224] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0xd8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 216] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0xd0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 208] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0xc8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 200] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0xb8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 184] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0xb0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 176] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0xa8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 168] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0xa0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 160] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x98b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 152] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x90b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 144] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x88b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 136] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x78723b4c // cmp r14, qword [rdx + 120] - LONG $0xd0950f41 // setne r8b - LONG $0x70723b4c // cmp r14, qword [rdx + 112] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x68723b4c // cmp r14, qword [rdx + 104] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x60723b4c // cmp r14, qword [rdx + 96] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] + LONG $0xd7950f40 // setne dil + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] LONG $0xd3950f41 // setne r11b - LONG $0x58723b4c // cmp r14, qword [rdx + 88] + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd2950f41 // setne r10b - LONG $0x50723b4c // cmp r14, qword [rdx + 80] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd1950f41 // setne r9b - LONG $0x48723b4c // cmp r14, qword [rdx + 72] - LONG $0xd7950f40 // setne dil - LONG $0x38723b4c // cmp r14, qword [rdx + 56] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] + LONG $0xd6950f40 // setne sil + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x30723b4c // cmp r14, qword [rdx + 48] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x28723b4c // cmp r14, qword [rdx + 40] - LONG $0xd6950f40 // setne sil - LONG $0x20723b4c // cmp r14, qword [rdx + 32] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x18723b4c // cmp r14, qword [rdx + 24] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] LONG $0xd4950f41 // setne r12b - LONG $0x10723b4c // cmp r14, qword [rdx + 16] + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd5950f41 // setne r13b - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] LONG $0xd7950f41 // setne r15b - LONG $0x40723b4c // cmp r14, qword [rdx + 64] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x80b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 128] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xc0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 192] - QUAD $0x000000802494950f // setne byte [rsp + 128] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000b024bc0244 // add r15b, byte [rsp + 176] - LONG $0x02e5c041 // shl r13b, 2 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0xd6950f41 // setne r14b + LONG $0x40423b4c // cmp r8, qword [rdx + 64] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xfd // or r13b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e4c041 // shl r12b, 3 + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x04e4c041 // shl r12b, 4 WORD $0x0845; BYTE $0xec // or r12b, r13b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000009824bc0240 // add dil, byte [rsp + 152] + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x06 // mov byte [r14], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x40 // add sil, byte [rsp + 64] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017e8841 // mov byte [r14 + 1], dil + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] + LONG $0x48244402 // add al, byte [rsp + 72] WORD $0xc189 // mov ecx, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x02468841 // mov byte [r14 + 2], al + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -29364,84 +29929,99 @@ LBB5_92: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x03468841 // mov byte [r14 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c78349 // add r15, 4 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_92 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - -LBB5_94: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB5_144 + LONG $0x04c68349 // add r14, 4 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB5_94 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] LBB5_96: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_188 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB5_166 + +LBB5_98: WORD $0xff31 // xor edi, edi - JMP LBB5_146 - -LBB5_97: - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_101 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JMP LBB5_168 LBB5_99: - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] + WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_105 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_103 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_102: + LONG $0x012ef8c5 // vucomiss xmm0, dword [rcx] + LONG $0x04518d48 // lea rdx, [rcx + 4] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xcb08 // or bl, cl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xee // mov r14, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x0005 // movzx r9d, byte [r13 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_99 - LONG $0x01c58349 // add r13, 1 - -LBB5_101: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_105 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b8249c894c // mov qword [rsp + 184], r11 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 + LONG $0x057c8841; BYTE $0x00 // mov byte [r13 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_102 LBB5_103: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 + +LBB5_105: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_109 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000c024b48944 // mov dword [rsp + 192], r14d + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + +LBB5_107: QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x422ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rdx + 4] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd5950f41 // setne r13b @@ -29450,7 +30030,7 @@ LBB5_103: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x422ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rdx + 12] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl @@ -29460,7 +30040,7 @@ LBB5_103: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x422ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rdx + 20] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd4950f41 // setne r12b @@ -29469,7 +30049,7 @@ LBB5_103: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl LONG $0x422ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rdx + 28] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl @@ -29479,17 +30059,17 @@ LBB5_103: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x422ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rdx + 36] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl LONG $0x422ef8c5; BYTE $0x28 // vucomiss xmm0, dword [rdx + 40] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl LONG $0x422ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rdx + 44] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd3 // setne bl @@ -29503,27 +30083,27 @@ LBB5_103: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl LONG $0x422ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rdx + 56] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x422ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rdx + 60] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl LONG $0x422ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rdx + 64] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl LONG $0x422ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rdx + 68] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x422ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rdx + 72] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd7950f41 // setne r15b @@ -29532,52 +30112,52 @@ LBB5_103: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x58244c88 // mov byte [rsp + 88], cl LONG $0x422ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rdx + 80] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x422ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rdx + 84] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x422ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rdx + 88] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd6950f41 // setne r14b WORD $0x0841; BYTE $0xc6 // or r14b, al LONG $0x422ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rdx + 92] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd0950f41 // setne r8b - WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al LONG $0x422ef8c5; BYTE $0x60 // vucomiss xmm0, dword [rdx + 96] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x422ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rdx + 100] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd3950f41 // setne r11b WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x422ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rdx + 104] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] - WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd1950f41 // setne r9b WORD $0x0841; BYTE $0xc1 // or r9b, al + LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd0950f41 // setne r8b + WORD $0x0841; BYTE $0xc0 // or r8b, al LONG $0x422ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rdx + 112] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl + LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl LONG $0x422ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rdx + 116] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl LONG $0x422ef8c5; BYTE $0x78 // vucomiss xmm0, dword [rdx + 120] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd7950f40 // setne dil @@ -29587,23 +30167,23 @@ LBB5_103: LONG $0xd6950f40 // setne sil WORD $0x0840; BYTE $0xc6 // or sil, al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] + LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] WORD $0x8944; BYTE $0xe8 // mov eax, r13d LONG $0x05e4c041 // shl r12b, 5 - LONG $0x6cb60f44; WORD $0x4824 // movzx r13d, byte [rsp + 72] + QUAD $0x00009824acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 152] LONG $0x06e5c041 // shl r13b, 6 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x64b60f44; WORD $0x3824 // movzx r12d, byte [rsp + 56] + LONG $0x64b60f44; WORD $0x3024 // movzx r12d, byte [rsp + 48] LONG $0x02e4c041 // shl r12b, 2 WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x20244c02 // add cl, byte [rsp + 32] LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x1c244488 // mov byte [rsp + 28], al - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -29612,56 +30192,56 @@ LBB5_103: WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xcb08 // or bl, cl - LONG $0x6cb60f44; WORD $0x2024 // movzx r13d, byte [rsp + 32] + LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl LONG $0x20248488; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 288], al - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xc808 // or al, cl - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xc900 // add cl, cl - LONG $0x58244c02 // add cl, byte [rsp + 88] + LONG $0x80248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 128] LONG $0x02e7c041 // shl r15b, 2 WORD $0x0841; BYTE $0xcf // or r15b, cl - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0x0844; BYTE $0xf9 // or cl, r15b WORD $0xcb89 // mov ebx, ecx QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd908 // or cl, bl LONG $0x64b60f44; WORD $0x1c24 // movzx r12d, byte [rsp + 28] WORD $0x0845; BYTE $0xec // or r12b, r13b - QUAD $0x00000098249cb60f // movzx ebx, byte [rsp + 152] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e6c041 // shl r14b, 6 WORD $0x0841; BYTE $0xde // or r14b, bl LONG $0x2024840a; WORD $0x0001; BYTE $0x00 // or al, byte [rsp + 288] - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf0 // or r8b, r14b - WORD $0x0841; BYTE $0xc8 // or r8b, cl + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0845; BYTE $0xf2 // or r10b, r14b + WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0045; BYTE $0xdb // add r11b, r11b - LONG $0x245c0244; BYTE $0x68 // add r11b, byte [rsp + 104] - LONG $0x02e2c041 // shl r10b, 2 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xd1 // or r9b, r10b - QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + LONG $0x245c0244; BYTE $0x48 // add r11b, byte [rsp + 72] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0845; BYTE $0xd9 // or r9b, r11b + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0845; BYTE $0xc8 // or r8b, r9b + QUAD $0x000000a8248cb60f // movzx ecx, byte [rsp + 168] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xc9 // or cl, r9b + WORD $0x0844; BYTE $0xc1 // or cl, r8b WORD $0x8845; BYTE $0x27 // mov byte [r15], r12b - QUAD $0x000000a8249cb60f // movzx ebx, byte [rsp + 168] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e7c040 // shl dil, 6 WORD $0x0840; BYTE $0xdf // or dil, bl @@ -29669,246 +30249,508 @@ LBB5_103: LONG $0x07e6c040 // shl sil, 7 WORD $0x0840; BYTE $0xfe // or sil, dil WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x02478845 // mov byte [r15 + 2], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b LONG $0x03778841 // mov byte [r15 + 3], sil LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 LONG $0x04c78349 // add r15, 4 WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB5_103 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 + JNE LBB5_107 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000c024b48b44 // mov r14d, dword [rsp + 192] + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] -LBB5_105: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB5_148 - WORD $0xff31 // xor edi, edi - JMP LBB5_150 - -LBB5_108: - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_112 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB5_109: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB5_188 + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB5_170 + WORD $0xff31 // xor edi, edi + JMP LBB5_172 + +LBB5_112: + WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_131 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_145 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB5_115: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x4cb60f45; WORD $0x001d // movzx r9d, byte [r13 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1d448841; BYTE $0x00 // mov byte [r13 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB5_115 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JNE LBB5_146 + JMP LBB5_188 + +LBB5_117: + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_123 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_121 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB5_110: - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] +LBB5_120: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 WORD $0x894d; BYTE $0xef // mov r15, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_110 - LONG $0x01c58349 // add r13, 1 + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_120 -LBB5_112: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_120 - LONG $0x20fe8349 // cmp r14, 32 - LONG $0x245c8944; BYTE $0x1c // mov dword [rsp + 28], r11d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000018024b4894c // mov qword [rsp + 384], r14 - JB LBB5_116 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 +LBB5_121: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB5_188 + LONG $0x01c58349 // add r13, 1 + +LBB5_123: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_127 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB5_125: + QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] + QUAD $0x000001202494950f // setne byte [rsp + 288] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + QUAD $0x000001402494950f // setne byte [rsp + 320] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] + LONG $0xd7950f40 // setne dil + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] + LONG $0xd3950f41 // setne r11b + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] + LONG $0xd2950f41 // setne r10b + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] + LONG $0xd1950f41 // setne r9b + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] + LONG $0xd6950f40 // setne sil + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] + WORD $0x950f; BYTE $0xd1 // setne cl + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] + LONG $0xd4950f41 // setne r12b + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] + LONG $0xd5950f41 // setne r13b + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] + LONG $0xd7950f41 // setne r15b + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd6950f41 // setne r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xfd // or r13b, r15b + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x06 // mov byte [r14], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x40 // add sil, byte [rsp + 64] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017e8841 // mov byte [r14 + 1], dil + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x48244402 // add al, byte [rsp + 72] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02468841 // mov byte [r14 + 2], al + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xc000 // add al, al + LONG $0x60244402 // add al, byte [rsp + 96] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x80ea8348 // sub rdx, -128 + LONG $0x04c68349 // add r14, 4 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB5_125 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB5_127: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_188 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB5_175 + +LBB5_129: + WORD $0xff31 // xor edi, edi + JMP LBB5_177 + +LBB5_130: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB5_134 + +LBB5_131: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB5_147 + +LBB5_132: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB5_188 + +LBB5_133: + LONG $0x01c58349 // add r13, 1 + +LBB5_134: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_142 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + JB LBB5_138 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x0148; BYTE $0xf8 // add rax, rdi WORD $0x3949; BYTE $0xc5 // cmp r13, rax - JAE LBB5_168 - QUAD $0x00000000b5048d4a // lea rax, [4*r14] + JAE LBB5_189 + QUAD $0x000000008d048d48 // lea rax, [4*rcx] WORD $0x014c; BYTE $0xe8 // add rax, r13 - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB5_168 + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB5_189 -LBB5_116: +LBB5_138: WORD $0xc031 // xor eax, eax QUAD $0x0000017824848948 // mov qword [rsp + 376], rax -LBB5_117: - QUAD $0x0000017824b42b4c // sub r14, qword [rsp + 376] - QUAD $0x000000a024b4894c // mov qword [rsp + 160], r14 +LBB5_139: + QUAD $0x00000178248c2b48 // sub rcx, qword [rsp + 376] + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx -LBB5_118: - LONG $0x1f5a3a44 // cmp r11b, byte [rdx + 31] +LBB5_140: + LONG $0x1f773a44 // cmp r14b, byte [rdi + 31] QUAD $0x000001102494950f // setne byte [rsp + 272] - LONG $0x1e5a3a44 // cmp r11b, byte [rdx + 30] + LONG $0x1e773a44 // cmp r14b, byte [rdi + 30] QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x1d5a3a44 // cmp r11b, byte [rdx + 29] + LONG $0x1d773a44 // cmp r14b, byte [rdi + 29] QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x1c5a3a44 // cmp r11b, byte [rdx + 28] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x1b5a3a44 // cmp r11b, byte [rdx + 27] + LONG $0x1c773a44 // cmp r14b, byte [rdi + 28] LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x1a5a3a44 // cmp r11b, byte [rdx + 26] + LONG $0x1b773a44 // cmp r14b, byte [rdi + 27] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x195a3a44 // cmp r11b, byte [rdx + 25] + LONG $0x1a773a44 // cmp r14b, byte [rdi + 26] LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x175a3a44 // cmp r11b, byte [rdx + 23] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x165a3a44 // cmp r11b, byte [rdx + 22] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x155a3a44 // cmp r11b, byte [rdx + 21] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x145a3a44 // cmp r11b, byte [rdx + 20] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x135a3a44 // cmp r11b, byte [rdx + 19] + LONG $0x19773a44 // cmp r14b, byte [rdi + 25] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x17773a44 // cmp r14b, byte [rdi + 23] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x16773a44 // cmp r14b, byte [rdi + 22] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x15773a44 // cmp r14b, byte [rdi + 21] QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x125a3a44 // cmp r11b, byte [rdx + 18] + LONG $0x14773a44 // cmp r14b, byte [rdi + 20] QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x115a3a44 // cmp r11b, byte [rdx + 17] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x0f5a3a44 // cmp r11b, byte [rdx + 15] - LONG $0xd6950f41 // setne r14b - LONG $0x0e5a3a44 // cmp r11b, byte [rdx + 14] + LONG $0x13773a44 // cmp r14b, byte [rdi + 19] LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x0d5a3a44 // cmp r11b, byte [rdx + 13] + LONG $0x12773a44 // cmp r14b, byte [rdi + 18] LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x0c5a3a44 // cmp r11b, byte [rdx + 12] + LONG $0x11773a44 // cmp r14b, byte [rdi + 17] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x0f773a44 // cmp r14b, byte [rdi + 15] + LONG $0xd3950f41 // setne r11b + LONG $0x0e773a44 // cmp r14b, byte [rdi + 14] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x0d773a44 // cmp r14b, byte [rdi + 13] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x0c773a44 // cmp r14b, byte [rdi + 12] LONG $0xd4950f41 // setne r12b - LONG $0x0b5a3a44 // cmp r11b, byte [rdx + 11] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x0b // cmp al, byte [rdi + 11] LONG $0xd7950f41 // setne r15b - LONG $0x0a5a3a44 // cmp r11b, byte [rdx + 10] - LONG $0xd3950f41 // setne r11b LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] + WORD $0x473a; BYTE $0x0a // cmp al, byte [rdi + 10] + LONG $0xd6950f41 // setne r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x09 // cmp al, byte [rdi + 9] LONG $0xd2950f41 // setne r10b LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7950f40 // setne dil + WORD $0x473a; BYTE $0x07 // cmp al, byte [rdi + 7] + LONG $0xd6950f40 // setne sil LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - QUAD $0x000000b02494950f // setne byte [rsp + 176] + WORD $0x473a; BYTE $0x06 // cmp al, byte [rdi + 6] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] + WORD $0x473a; BYTE $0x05 // cmp al, byte [rdi + 5] LONG $0xd1950f41 // setne r9b LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] + WORD $0x473a; BYTE $0x04 // cmp al, byte [rdi + 4] LONG $0xd0950f41 // setne r8b LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0xd6950f40 // setne sil + WORD $0x473a; BYTE $0x03 // cmp al, byte [rdi + 3] + WORD $0x950f; BYTE $0xd2 // setne dl LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] + WORD $0x473a; BYTE $0x02 // cmp al, byte [rdi + 2] WORD $0x950f; BYTE $0xd1 // setne cl LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x023a // cmp al, byte [rdx] + WORD $0x073a // cmp al, byte [rdi] QUAD $0x000000a82494950f // setne byte [rsp + 168] LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x01 // cmp al, byte [rdx + 1] + WORD $0x473a; BYTE $0x01 // cmp al, byte [rdi + 1] WORD $0x950f; BYTE $0xd0 // setne al WORD $0x894c; BYTE $0xeb // mov rbx, r13 LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] - LONG $0x086a3a44 // cmp r13b, byte [rdx + 8] + LONG $0x086f3a44 // cmp r13b, byte [rdi + 8] WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5a3a; BYTE $0x10 // cmp bl, byte [rdx + 16] - QUAD $0x000000902494950f // setne byte [rsp + 144] + WORD $0x5f3a; BYTE $0x10 // cmp bl, byte [rdi + 16] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5a3a; BYTE $0x18 // cmp bl, byte [rdx + 24] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + WORD $0x5f3a; BYTE $0x18 // cmp bl, byte [rdi + 24] + WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xc000 // add al, al LONG $0xa8248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 168] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al - LONG $0x03e6c040 // shl sil, 3 - WORD $0x0840; BYTE $0xce // or sil, cl + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0xca08 // or dl, cl LONG $0x04e0c041 // shl r8b, 4 - WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xd0 // or r8b, dl LONG $0x05e1c041 // shl r9b, 5 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xc7 // or dil, al - WORD $0x0844; BYTE $0xcf // or dil, r9b - LONG $0x007d8841 // mov byte [r13], dil + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xc6 // or sil, al + WORD $0x0844; BYTE $0xce // or sil, r9b + LONG $0x00758841 // mov byte [r13], sil WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x24540244; BYTE $0x48 // add r10b, byte [rsp + 72] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] + WORD $0x0845; BYTE $0xf7 // or r15b, r14b LONG $0x04e4c041 // shl r12b, 4 WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xce // or r14b, cl - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x01758845 // mov byte [r13 + 1], r14b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x015d8845 // mov byte [r13 + 1], r11b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0x78244402 // add al, byte [rsp + 120] WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl + WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xc000 // add al, al - LONG $0x58244402 // add al, byte [rsp + 88] + WORD $0xd808 // or al, bl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -29916,219 +30758,256 @@ LBB5_118: WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x000001202494b60f // movzx edx, byte [rsp + 288] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl + WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x20c28348 // add rdx, 32 + LONG $0x20c78348 // add rdi, 32 LONG $0x04c58349 // add r13, 4 QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB5_118 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000018024b48b4c // mov r14, qword [rsp + 384] + JNE LBB5_140 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x00000180248c8b48 // mov rcx, qword [rsp + 384] -LBB5_120: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB5_153 +LBB5_142: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB5_188 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JE LBB5_157 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d -LBB5_122: - WORD $0xf631 // xor esi, esi - JMP LBB5_156 +LBB5_181: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0f343a46 // cmp r14b, byte [rdi + r9] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xce // mov rsi, r9 + LONG $0x03eec148 // shr rsi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x35548841; BYTE $0x00 // mov byte [r13 + rsi], dl + LONG $0x07743a44; BYTE $0x01 // cmp r14b, byte [rdi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB5_181 + JMP LBB5_184 -LBB5_123: - WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_127 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB5_145: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB5_188 -LBB5_125: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - LONG $0x44b60f45; WORD $0x0035 // movzx r8d, byte [r13 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x357c8841; BYTE $0x00 // mov byte [r13 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_125 - LONG $0x01c58349 // add r13, 1 +LBB5_146: + LONG $0x01c58349 // add r13, 1 + +LBB5_147: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB5_155 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + JB LBB5_151 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc5 // cmp r13, rax + JAE LBB5_192 + QUAD $0x000000008d048d48 // lea rax, [4*rcx] + WORD $0x014c; BYTE $0xe8 // add rax, r13 + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB5_192 -LBB5_127: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB5_131 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 +LBB5_151: + WORD $0xc031 // xor eax, eax + QUAD $0x0000017824848948 // mov qword [rsp + 376], rax -LBB5_129: - QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 - LONG $0x7c723b44 // cmp r14d, dword [rdx + 124] - LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] - LONG $0x78723b44 // cmp r14d, dword [rdx + 120] +LBB5_152: + QUAD $0x00000178248c2b48 // sub rcx, qword [rsp + 376] + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx + +LBB5_153: + LONG $0x1f773a44 // cmp r14b, byte [rdi + 31] + QUAD $0x000001102494950f // setne byte [rsp + 272] + LONG $0x1e773a44 // cmp r14b, byte [rdi + 30] QUAD $0x000001202494950f // setne byte [rsp + 288] - LONG $0x74723b44 // cmp r14d, dword [rdx + 116] + LONG $0x1d773a44 // cmp r14b, byte [rdi + 29] QUAD $0x000001402494950f // setne byte [rsp + 320] - LONG $0x70723b44 // cmp r14d, dword [rdx + 112] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6c723b44 // cmp r14d, dword [rdx + 108] + LONG $0x1c773a44 // cmp r14b, byte [rdi + 28] LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x68723b44 // cmp r14d, dword [rdx + 104] + LONG $0x1b773a44 // cmp r14b, byte [rdi + 27] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x64723b44 // cmp r14d, dword [rdx + 100] + LONG $0x1a773a44 // cmp r14b, byte [rdi + 26] LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x5c723b44 // cmp r14d, dword [rdx + 92] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x58723b44 // cmp r14d, dword [rdx + 88] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x54723b44 // cmp r14d, dword [rdx + 84] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x50723b44 // cmp r14d, dword [rdx + 80] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x4c723b44 // cmp r14d, dword [rdx + 76] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x48723b44 // cmp r14d, dword [rdx + 72] + LONG $0x19773a44 // cmp r14b, byte [rdi + 25] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x17773a44 // cmp r14b, byte [rdi + 23] + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x16773a44 // cmp r14b, byte [rdi + 22] QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x44723b44 // cmp r14d, dword [rdx + 68] + LONG $0x15773a44 // cmp r14b, byte [rdi + 21] QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x3c723b44 // cmp r14d, dword [rdx + 60] - LONG $0xd0950f41 // setne r8b - LONG $0x38723b44 // cmp r14d, dword [rdx + 56] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x34723b44 // cmp r14d, dword [rdx + 52] + LONG $0x14773a44 // cmp r14b, byte [rdi + 20] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x13773a44 // cmp r14b, byte [rdi + 19] LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x30723b44 // cmp r14d, dword [rdx + 48] + LONG $0x12773a44 // cmp r14b, byte [rdi + 18] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x11773a44 // cmp r14b, byte [rdi + 17] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x0f773a44 // cmp r14b, byte [rdi + 15] LONG $0xd3950f41 // setne r11b - LONG $0x2c723b44 // cmp r14d, dword [rdx + 44] + LONG $0x0e773a44 // cmp r14b, byte [rdi + 14] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x0d773a44 // cmp r14b, byte [rdi + 13] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x0c773a44 // cmp r14b, byte [rdi + 12] + LONG $0xd4950f41 // setne r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x0b // cmp al, byte [rdi + 11] + LONG $0xd7950f41 // setne r15b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x0a // cmp al, byte [rdi + 10] + LONG $0xd6950f41 // setne r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x09 // cmp al, byte [rdi + 9] LONG $0xd2950f41 // setne r10b - LONG $0x28723b44 // cmp r14d, dword [rdx + 40] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x07 // cmp al, byte [rdi + 7] + LONG $0xd6950f40 // setne sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x06 // cmp al, byte [rdi + 6] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x05 // cmp al, byte [rdi + 5] LONG $0xd1950f41 // setne r9b - LONG $0x24723b44 // cmp r14d, dword [rdx + 36] - LONG $0xd7950f40 // setne dil - LONG $0x1c723b44 // cmp r14d, dword [rdx + 28] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x04 // cmp al, byte [rdi + 4] + LONG $0xd0950f41 // setne r8b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x03 // cmp al, byte [rdi + 3] + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x02 // cmp al, byte [rdi + 2] + WORD $0x950f; BYTE $0xd1 // setne cl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x073a // cmp al, byte [rdi] + QUAD $0x000000a82494950f // setne byte [rsp + 168] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x01 // cmp al, byte [rdi + 1] WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x18723b44 // cmp r14d, dword [rdx + 24] + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] + LONG $0x086f3a44 // cmp r13b, byte [rdi + 8] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5f3a; BYTE $0x10 // cmp bl, byte [rdi + 16] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5f3a; BYTE $0x18 // cmp bl, byte [rdi + 24] WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x14723b44 // cmp r14d, dword [rdx + 20] - LONG $0xd6950f40 // setne sil - LONG $0x10723b44 // cmp r14d, dword [rdx + 16] - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x0c723b44 // cmp r14d, dword [rdx + 12] - LONG $0xd4950f41 // setne r12b - LONG $0x08723b44 // cmp r14d, dword [rdx + 8] - LONG $0xd5950f41 // setne r13b - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] - LONG $0xd7950f41 // setne r15b - LONG $0x20723b44 // cmp r14d, dword [rdx + 32] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x40723b44 // cmp r14d, dword [rdx + 64] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x60723b44 // cmp r14d, dword [rdx + 96] - QUAD $0x000000802494950f // setne byte [rsp + 128] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000b024bc0244 // add r15b, byte [rsp + 176] - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xec // or r12b, r13b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000009824bc0240 // add dil, byte [rsp + 152] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0xa8248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 168] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0xca08 // or dl, cl + LONG $0x04e0c041 // shl r8b, 4 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + LONG $0x05e1c041 // shl r9b, 5 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xc6 // or sil, al + WORD $0x0844; BYTE $0xce // or sil, r9b + LONG $0x00758841 // mov byte [r13], sil + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + LONG $0x24540244; BYTE $0x48 // add r10b, byte [rsp + 72] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x015d8845 // mov byte [r13 + 1], r11b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] + LONG $0x78244402 // add al, byte [rsp + 120] WORD $0xc189 // mov ecx, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl + WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x02458841 // mov byte [r13 + 2], al + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + WORD $0xd808 // or al, bl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -30136,41 +31015,39 @@ LBB5_129: WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + QUAD $0x000001202494b60f // movzx edx, byte [rsp + 288] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl + WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x80ea8348 // sub rdx, -128 - LONG $0x04c78349 // add r15, 4 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_129 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - -LBB5_131: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB5_164 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB5_158 + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x20c78348 // add rdi, 32 + LONG $0x04c58349 // add r13, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB5_153 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x00000180248c8b48 // mov rcx, qword [rsp + 384] -LBB5_133: - WORD $0xff31 // xor edi, edi - JMP LBB5_160 +LBB5_155: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB5_188 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JNE LBB5_182 + +LBB5_157: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB5_185 -LBB5_134: +LBB5_158: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0xff31 // xor edi, edi -LBB5_135: +LBB5_159: LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd0 // setne al @@ -30203,104 +31080,104 @@ LBB5_135: WORD $0x3044; BYTE $0xdb // xor bl, r11b LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB5_135 + JNE LBB5_159 -LBB5_136: +LBB5_160: LONG $0x01c0f641 // test r8b, 1 - JE LBB5_164 + JE LBB5_188 LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - JMP LBB5_152 + JMP LBB5_174 -LBB5_140: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB5_162: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB5_141: - LONG $0x323b4466 // cmp r14w, word [rdx] +LBB5_163: + LONG $0x023b4466 // cmp r8w, word [rdx] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + WORD $0x894d; BYTE $0xee // mov r14, r13 + LONG $0x54b60f45; WORD $0x0035 // movzx r10d, byte [r13 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0x3044; BYTE $0xd3 // xor bl, r10b LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB5_141 + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_163 -LBB5_142: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_164 - LONG $0x323b4466 // cmp r14w, word [rdx] - JMP LBB5_162 +LBB5_164: + LONG $0x01c1f641 // test r9b, 1 + JE LBB5_188 + LONG $0x023b4466 // cmp r8w, word [rdx] + JMP LBB5_179 -LBB5_144: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB5_166: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB5_145: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] +LBB5_167: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + WORD $0x894d; BYTE $0xee // mov r14, r13 + LONG $0x54b60f45; WORD $0x0035 // movzx r10d, byte [r13 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0x3044; BYTE $0xd3 // xor bl, r10b LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x08423b4c // cmp r8, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB5_145 + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_167 -LBB5_146: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_164 - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - JMP LBB5_162 +LBB5_168: + LONG $0x01c1f641 // test r9b, 1 + JE LBB5_188 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + JMP LBB5_179 -LBB5_148: +LBB5_170: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0xff31 // xor edi, edi -LBB5_149: +LBB5_171: LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd0 // setne al @@ -30333,14 +31210,14 @@ LBB5_149: WORD $0x3044; BYTE $0xdb // xor bl, r11b LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB5_149 + JNE LBB5_171 -LBB5_150: +LBB5_172: LONG $0x01c0f641 // test r8b, 1 - JE LBB5_164 + JE LBB5_188 LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] -LBB5_152: +LBB5_174: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd2 // setne dl WORD $0xc208 // or dl, al @@ -30356,2105 +31233,2108 @@ LBB5_152: WORD $0xd320 // and bl, dl WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x055c8841; BYTE $0x00 // mov byte [r13 + rax], bl - JMP LBB5_164 + JMP LBB5_188 -LBB5_153: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi +LBB5_175: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 + WORD $0xff31 // xor edi, edi -LBB5_154: - LONG $0x321c3a44 // cmp r11b, byte [rdx + rsi] +LBB5_176: + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xee // mov r14, r13 + LONG $0x54b60f45; WORD $0x0035 // movzx r10d, byte [r13 + rsi] + WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl - LONG $0x325c3a44; BYTE $0x01 // cmp r11b, byte [rdx + rsi + 1] - LONG $0x02768d48 // lea rsi, [rsi + 2] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0x08528d48 // lea rdx, [rdx + 8] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl - LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB5_154 + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_176 -LBB5_155: - WORD $0x0148; BYTE $0xf2 // add rdx, rsi +LBB5_177: + LONG $0x01c1f641 // test r9b, 1 + JE LBB5_188 + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] -LBB5_156: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_164 - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] +LBB5_179: WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x8948; BYTE $0xfa // mov rdx, rdi LONG $0x03eac148 // shr rdx, 3 - LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] - LONG $0x07e68040 // and sil, 7 + LONG $0x15748a41; BYTE $0x00 // mov sil, byte [r13 + rdx] + LONG $0x07e78040 // and dil, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi + WORD $0xf989 // mov ecx, edi WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - JMP LBB5_163 + WORD $0x3040; BYTE $0xf3 // xor bl, sil + JMP LBB5_187 -LBB5_158: +LBB5_182: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d -LBB5_159: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi +LBB5_183: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0f343a46 // cmp r14b, byte [rdi + r9] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xce // mov rsi, r9 LONG $0x03eec148 // shr rsi, 3 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] - WORD $0xf989 // mov ecx, edi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x355c8841; BYTE $0x00 // mov byte [r13 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd1950f41 // setne r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x35548841; BYTE $0x00 // mov byte [r13 + rsi], dl + LONG $0x07743a44; BYTE $0x01 // cmp r14b, byte [rdi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB5_159 + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB5_183 -LBB5_160: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_164 - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] +LBB5_184: + WORD $0x014c; BYTE $0xcf // add rdi, r9 -LBB5_162: +LBB5_185: + LONG $0x01c0f641 // test r8b, 1 + JE LBB5_188 + WORD $0x3a44; BYTE $0x37 // cmp r14b, byte [rdi] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfa // mov rdx, rdi + WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 - LONG $0x15748a41; BYTE $0x00 // mov sil, byte [r13 + rdx] - LONG $0x07e78040 // and dil, 7 + LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf989 // mov ecx, edi + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil + WORD $0x3040; BYTE $0xfb // xor bl, dil -LBB5_163: +LBB5_187: LONG $0x155c8841; BYTE $0x00 // mov byte [r13 + rdx], bl -LBB5_164: - MOVQ 1280(SP), SP +LBB5_188: + MOVQ 1248(SP), SP VZEROUPPER RET -LBB5_165: - LONG $0xe0e68349 // and r14, -32 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 +LBB5_189: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000018824848948 // mov qword [rsp + 392], rax - QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 - QUAD $0x00000000b5048d4a // lea rax, [4*r14] - WORD $0x014c; BYTE $0xe8 // add rax, r13 + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - LONG $0x6e79c1c4; BYTE $0xc3 // vmovd xmm0, r11d + QUAD $0x00000178248c8948 // mov qword [rsp + 376], rcx + QUAD $0x000000008d048d48 // lea rax, [4*rcx] + WORD $0x014c; BYTE $0xe8 // add rax, r13 + QUAD $0x0000018824848948 // mov qword [rsp + 392], rax + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 - WORD $0xf631 // xor esi, esi + WORD $0xc031 // xor eax, eax QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 -LBB5_166: - QUAD $0x0000019824b48948 // mov qword [rsp + 408], rsi - LONG $0x05e6c148 // shl rsi, 5 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi +LBB5_190: + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x0000019824848948 // mov qword [rsp + 408], rax + LONG $0x05e3c148 // shl rbx, 5 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x000000d824848948 // mov qword [rsp + 216], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x01000d48; WORD $0x0000 // or rax, 256 QUAD $0x0000012024848948 // mov qword [rsp + 288], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x01000d48; WORD $0x0000 // or rax, 256 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - QUAD $0x0000010824b48948 // mov qword [rsp + 264], rsi + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x3204b60f // movzx eax, byte [rdx + rsi] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] + LONG $0x1744b60f; BYTE $0x01 // movzx eax, byte [rdi + rdx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x3244b60f; BYTE $0x01 // movzx eax, byte [rdx + rsi + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x0a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rcx + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x3244b60f; BYTE $0x02 // movzx eax, byte [rdx + rsi + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x0a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rcx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x3244b60f; BYTE $0x03 // movzx eax, byte [rdx + rsi + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x0a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rcx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x3244b60f; BYTE $0x04 // movzx eax, byte [rdx + rsi + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x0a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rcx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x3244b60f; BYTE $0x05 // movzx eax, byte [rdx + rsi + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x0a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rcx + 6] - QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x000000e824948948 // mov qword [rsp + 232], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x3244b60f; BYTE $0x06 // movzx eax, byte [rdx + rsi + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x0a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rcx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x3244b60f; BYTE $0x07 // movzx eax, byte [rdx + rsi + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x01800d48; WORD $0x0000 // or rax, 384 QUAD $0x0000014024848948 // mov qword [rsp + 320], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x01800d48; WORD $0x0000 // or rax, 384 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x02200d48; WORD $0x0000 // or rax, 544 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - LONG $0x40cc8149; WORD $0x0002; BYTE $0x00 // or r12, 576 + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + WORD $0x8949; BYTE $0xdc // mov r12, rbx + LONG $0x20cc8149; WORD $0x0002; BYTE $0x00 // or r12, 544 QUAD $0x000000e024a4894c // mov qword [rsp + 224], r12 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x02600d48; WORD $0x0000 // or rax, 608 - WORD $0x8949; BYTE $0xc6 // mov r14, rax - QUAD $0x000000f824848948 // mov qword [rsp + 248], rax - WORD $0x8949; BYTE $0xf7 // mov r15, rsi - LONG $0x80cf8149; WORD $0x0002; BYTE $0x00 // or r15, 640 - QUAD $0x0000010024bc894c // mov qword [rsp + 256], r15 - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - LONG $0xa0ca8149; WORD $0x0002; BYTE $0x00 // or r10, 672 - LONG $0x2454894c; BYTE $0x68 // mov qword [rsp + 104], r10 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x02c00d48; WORD $0x0000 // or rax, 704 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax - WORD $0x8949; BYTE $0xf0 // mov r8, rsi - LONG $0xe0c88149; WORD $0x0002; BYTE $0x00 // or r8, 736 - LONG $0x2444894c; BYTE $0x70 // mov qword [rsp + 112], r8 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x03000d48; WORD $0x0000 // or rax, 768 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0x40cf8149; WORD $0x0002; BYTE $0x00 // or r15, 576 + LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x60cb8149; WORD $0x0002; BYTE $0x00 // or r11, 608 + QUAD $0x000000d8249c894c // mov qword [rsp + 216], r11 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x80ca8149; WORD $0x0002; BYTE $0x00 // or r10, 640 + QUAD $0x000000c82494894c // mov qword [rsp + 200], r10 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0xc0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 704 + QUAD $0x000000c024b4894c // mov qword [rsp + 192], r14 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02e00d48; WORD $0x0000 // or rax, 736 + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + WORD $0x8949; BYTE $0xdd // mov r13, rbx + LONG $0x00cd8149; WORD $0x0003; BYTE $0x00 // or r13, 768 + LONG $0x246c894c; BYTE $0x28 // mov qword [rsp + 40], r13 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x03200d48; WORD $0x0000 // or rax, 800 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - WORD $0x8949; BYTE $0xf1 // mov r9, rsi + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + WORD $0x8949; BYTE $0xd9 // mov r9, rbx LONG $0x40c98149; WORD $0x0003; BYTE $0x00 // or r9, 832 QUAD $0x000000d0248c894c // mov qword [rsp + 208], r9 - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x60cf8148; WORD $0x0003; BYTE $0x00 // or rdi, 864 - LONG $0x247c8948; BYTE $0x60 // mov qword [rsp + 96], rdi - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - LONG $0x80c98148; WORD $0x0003; BYTE $0x00 // or rcx, 896 - QUAD $0x00000088248c8948 // mov qword [rsp + 136], rcx - WORD $0x8949; BYTE $0xf3 // mov r11, rsi - LONG $0xa0cb8149; WORD $0x0003; BYTE $0x00 // or r11, 928 - QUAD $0x000000c0249c894c // mov qword [rsp + 192], r11 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x60c98148; WORD $0x0003; BYTE $0x00 // or rcx, 864 + QUAD $0x000000b8248c8948 // mov qword [rsp + 184], rcx + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 + QUAD $0x000000b02484894c // mov qword [rsp + 176], r8 + WORD $0x8948; BYTE $0xde // mov rsi, rbx + LONG $0xa0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 928 + QUAD $0x0000010024b48948 // mov qword [rsp + 256], rsi + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x000000f8249c8948 // mov qword [rsp + 248], rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax - LONG $0xe0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 992 - LONG $0x24748948; BYTE $0x50 // mov qword [rsp + 80], rsi - LONG $0x207923c4; WORD $0x2a0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdx + r13], 1 - LONG $0x2031a3c4; WORD $0x2204; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdx + r12], 2 - LONG $0x2079a3c4; WORD $0x3204; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdx + r14], 3 - LONG $0x2079a3c4; WORD $0x3a04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdx + r15], 4 - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdx + r10], 5 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 6 - LONG $0x2079a3c4; WORD $0x0204; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdx + r8], 7 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 8 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 9 - LONG $0x2079a3c4; WORD $0x0a04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdx + r9], 10 - LONG $0x2079e3c4; WORD $0x3a04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdx + rdi], 11 - LONG $0x2079e3c4; WORD $0x0a04; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdx + rcx], 12 - LONG $0x2079a3c4; WORD $0x1a04; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdx + r11], 13 - LONG $0x2079e3c4; WORD $0x0204; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdx + rax], 14 - LONG $0x2079e3c4; WORD $0x3204; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdx + rsi], 15 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - LONG $0x2061a3c4; WORD $0x221c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdx + r12], 1 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdx + r14], 2 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + r11], 3 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r8], 4 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r9], 5 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + rbx], 6 + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + LONG $0xe0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 992 + QUAD $0x0000010824948948 // mov qword [rsp + 264], rdx + LONG $0x207923c4; WORD $0x270c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r12], 1 + LONG $0x2031a3c4; WORD $0x3f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + r15], 2 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + r11], 3 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r10], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r14], 6 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 7 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r13], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 9 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r9], 10 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + rcx], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rsi], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rdx], 15 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r14], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 2 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r12], 3 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r8], 4 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r10], 5 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r9], 6 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r11], 7 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + r15], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rcx], 10 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rdx], 11 QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + rsi], 7 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + r15], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + rdi], 9 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + rax], 10 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - LONG $0x2061a3c4; WORD $0x121c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + r10], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + rcx], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rcx], 13 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rcx], 14 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - LONG $0x2061a3c4; WORD $0x2a1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + r13], 15 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x01010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 2 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x03010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 3 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x04010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 4 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x05010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 5 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x06010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 6 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x07010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 7 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x08010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x09010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 10 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0b010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 11 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0c010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 12 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0d010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 14 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0f012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 15 - QUAD $0x0101226c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r12 + 1], 1 - QUAD $0x0201326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 1], 2 - WORD $0x894c; BYTE $0xf1 // mov rcx, r14 - QUAD $0x03011a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 1], 3 - QUAD $0x0401026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 1], 4 - QUAD $0x05010a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 1], 5 - QUAD $0x06011a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 1], 6 - QUAD $0x0701326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 1], 7 - QUAD $0x08013a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 1], 8 - QUAD $0x09013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 9 - QUAD $0x0a01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 10 - WORD $0x8949; BYTE $0xc3 // mov r11, rax - QUAD $0x0b01126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 1], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 13 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0e01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 14 + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rsi], 14 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rsi], 15 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x01012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x020137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 2 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x030137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 4 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x050137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 5 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x070137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 7 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x080137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 8 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x090137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 9 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0a0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 10 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0b0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 11 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0c0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 12 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0d0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 13 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0e0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 14 + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x0f0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 15 + QUAD $0x0101376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x02011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 2 + QUAD $0x0301276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 3 + QUAD $0x0401076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 4 + QUAD $0x0501176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 5 + QUAD $0x06010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 6 + QUAD $0x07011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 7 + QUAD $0x08013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + QUAD $0x0a010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 10 + QUAD $0x0b01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0f0102442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 1], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 - QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xd06e79c5 // vmovd xmm10, eax QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x010232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 2], 1 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x02021a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 2], 2 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x030202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 2], 3 - QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] - QUAD $0x04020a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 2], 4 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x05023a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 2], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x010207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 2 + QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040237442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 2], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x05021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 5 + QUAD $0x06022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 6 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x07021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 7 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x08020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 8 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + QUAD $0x090207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 12 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0d0227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 13 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x0e023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] + QUAD $0x0102375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 2], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0202075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0302075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x060202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 6 + QUAD $0x0402075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 4 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x0502375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 2], 5 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x070202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 7 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x080202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 8 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x090202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 9 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x0a0222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 2], 10 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0b022a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 2], 11 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x0c0232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 2], 12 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x0d0212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 2], 13 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 15 - QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0102025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 1 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x02020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x03020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 3 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x04020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x05020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 5 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x06020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 6 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x07023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x08023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x09020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 9 - QUAD $0x0a021a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 2], 10 + QUAD $0x0602075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0702075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0802075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 8 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0902175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 9 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0a02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 10 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0d022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 13 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0e02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 14 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0f02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 15 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x01032f642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r13 + 3], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x020317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + QUAD $0x05031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 5 + WORD $0x8949; BYTE $0xda // mov r10, rbx + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x06032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 6 + QUAD $0x07031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 7 + QUAD $0x08030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 8 + QUAD $0x090307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 9 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x0a030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 10 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0b031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 11 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0c0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 12 + QUAD $0x0d0327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 13 + QUAD $0x0e033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 14 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x0f0307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 15 + QUAD $0x01030f6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rcx + 3], 1 LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0b020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 13 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0e020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 14 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x0f021a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 2], 15 - QUAD $0x010332642021e3c4 // vpinsrb xmm4, xmm11, byte [rdx + rsi + 3], 1 - QUAD $0x02031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 2 - QUAD $0x030302642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 3], 3 - QUAD $0x04030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 4 - QUAD $0x05033a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 3], 5 + QUAD $0x02030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 2 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x03030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 3 QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x06030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 6 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x07033a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 3], 7 - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x08030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 8 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x09031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 9 - QUAD $0x0a0322642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 3], 10 - QUAD $0x0b032a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 3], 11 - QUAD $0x0c0332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 3], 12 - QUAD $0x0d0312642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 3], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 14 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0f0312642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 3], 15 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x01030a6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdx + rcx + 3], 1 - QUAD $0x0203026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0303026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 3 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x04030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x05030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 5 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0603326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 6 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0703326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 7 - QUAD $0x08033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 8 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0903326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 9 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0a033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 13 + QUAD $0x04030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 4 + QUAD $0x0503376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 3], 5 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0603276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 3], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x07030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 7 + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0e033a442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rdi + 3], 14 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x09 // movzx edi, byte [rdx + rdi + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x0f032a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 3], 15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f0307442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x3a7cb60f; BYTE $0x09 // movzx edi, byte [rdx + rdi + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x010422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 1 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - QUAD $0x020402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 2 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - QUAD $0x03041a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 4], 3 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x04043a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 4], 4 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x05043a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 4], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x06043a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 4], 6 - QUAD $0x07043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 7 - QUAD $0x08040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 8 - QUAD $0x09041a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 4], 9 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x0a043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 10 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0b041a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 4], 11 - QUAD $0x0c0432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 4], 12 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0d040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 13 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x0e0432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 4], 14 - QUAD $0x0f0412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 4], 15 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x0104125c2001a3c4 // vpinsrb xmm3, xmm15, byte [rdx + r10 + 4], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x02043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 2 - QUAD $0x0304025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0404025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 4 - QUAD $0x05040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0604025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 6 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x07043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 7 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0804025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 8 - QUAD $0x0904325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 9 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0a04325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 10 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x010437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x030407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x040407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 4 + QUAD $0x050417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 5 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x06042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 6 + QUAD $0x07041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 9 + QUAD $0x0a040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 10 + QUAD $0x0b041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 11 + QUAD $0x0c0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 13 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x0e042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 14 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + QUAD $0x0f0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 15 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x0104375c2001a3c4 // vpinsrb xmm3, xmm15, byte [rdi + r14 + 4], 1 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 13 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0e040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 14 - QUAD $0x0f042a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 4], 15 - QUAD $0x010522642009a3c4 // vpinsrb xmm4, xmm14, byte [rdx + r12 + 5], 1 - QUAD $0x020502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 2 - QUAD $0x03051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 3 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - QUAD $0x040522642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 5], 4 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x050502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 5 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x06051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 6 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x07051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 7 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x08051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 8 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x09051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 9 - QUAD $0x0a053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 10 - QUAD $0x0b051a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 5], 11 - WORD $0x894d; BYTE $0xdf // mov r15, r11 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0c051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 12 - QUAD $0x0d050a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 5], 13 - QUAD $0x0e0532642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 5], 14 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0f051a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 5], 15 - QUAD $0x0105126c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdx + r10 + 5], 1 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x02051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 2 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x03051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 3 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x04051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 4 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x05050a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 5], 5 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x06051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 6 - QUAD $0x07053a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 5], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x08053a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 5], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x09053a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 5], 9 - QUAD $0x0a05326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 5], 10 - QUAD $0x0b05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 11 + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] + QUAD $0x03040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 3 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0404075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 4 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x0504175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 5 + QUAD $0x0604275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x08041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 8 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x0904275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 9 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x0a041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 10 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0b041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 11 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x0c041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 12 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0d041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 13 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0e041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 14 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0f041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 15 + QUAD $0x010537642009e3c4 // vpinsrb xmm4, xmm14, byte [rdi + rsi + 5], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x020537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 2 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x030537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 4 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x050537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 5 + QUAD $0x06053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 6 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x070537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 7 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x08053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 8 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x090537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 9 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0a0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 10 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0b0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 11 + QUAD $0x0c0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 12 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0d0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 13 + QUAD $0x0e052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 14 + QUAD $0x0f050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 15 + QUAD $0x0105376c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r14 + 5], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 2 + QUAD $0x03050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 3 + QUAD $0x0405076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 4 + QUAD $0x0505176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 5 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0605176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 6 + QUAD $0x0705076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 7 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x08051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 8 + QUAD $0x0905276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 5], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 13 - QUAD $0x0e050a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 5], 14 + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 + WORD $0x8949; BYTE $0xc0 // mov r8, rax LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - QUAD $0x0f052a442051a3c4 // vpinsrb xmm0, xmm5, byte [rdx + r13 + 5], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + QUAD $0x0f051f442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rbx + 5], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xd86ef9c5 // vmovd xmm3, eax LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x01061a442019a3c4 // vpinsrb xmm0, xmm12, byte [rdx + r11 + 6], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x020602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 2 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x030602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 3 - QUAD $0x040622442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 6], 4 - QUAD $0x050602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 5 + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x01060f442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rcx + 6], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x020617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 2 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x030637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 3 + QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] + QUAD $0x04061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 5 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x06060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x070607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 7 + QUAD $0x08063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 9 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x0a063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 10 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0b061f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 6], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 12 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0d0627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 13 + QUAD $0x0e062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0106076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 6], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0206076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0306076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x060602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 6 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x07060a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 6], 7 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x080602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 8 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x090602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a0602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 10 - QUAD $0x0b063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 11 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x0c063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 12 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0d0632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 6], 13 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0e061a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 6], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f0602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 15 - QUAD $0x0106126c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdx + r10 + 6], 1 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0206026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 2 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0306026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 6], 3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0406026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 4 - QUAD $0x05060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x06063a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 6], 6 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0706026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 7 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x08062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0906026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 9 + QUAD $0x0406076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0506076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 5 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x0606176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 6 + QUAD $0x0706376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 7 LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0a06326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 10 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x0b060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 11 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0c06226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 12 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0d06326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 13 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0e06326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 14 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x0f06226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 15 - QUAD $0x01071a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 7], 1 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x020732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 2 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x030732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 3 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x040732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 4 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x050732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 5 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x060732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 6 - QUAD $0x07070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 7 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x080722542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 7], 8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x09070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 10 + QUAD $0x0806376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 8 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x0906176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 10 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0b06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 11 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0c06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0d06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 13 + QUAD $0x0e06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 14 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0f06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 15 + QUAD $0x01070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 1 + QUAD $0x020717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 2 + QUAD $0x030737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 3 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + QUAD $0x04071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 4 LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0b070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 11 - QUAD $0x0c073a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 7], 12 - QUAD $0x0d0732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 7], 13 - QUAD $0x0e071a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 7], 14 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x0f073a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 7], 15 - QUAD $0x0107124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 7], 1 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x02071a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 7], 2 - QUAD $0x0307024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 7], 3 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x04070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 4 + QUAD $0x05070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 5 + QUAD $0x06070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 6 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x07070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 7 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x08070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 8 LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x05070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 5 - QUAD $0x06073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 6 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x07070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 7 - QUAD $0x08072a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 7], 8 - QUAD $0x0907024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 9 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x0a07324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 7], 10 - QUAD $0x0b070a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 7], 11 + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + QUAD $0x0a073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 10 + QUAD $0x0b071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 11 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x0c070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 12 + QUAD $0x0d0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 13 + QUAD $0x0e072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 14 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x0f070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 15 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x01071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 2 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x0307274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x04070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 4 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x0907174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c07024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d07024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 13 + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 12 + QUAD $0x0d07374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0e0702442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rax + 7], 14 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x0b // movzx edi, byte [rdx + rax + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x0f071a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 7], 15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0707442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 7], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0f072f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x027cb60f; BYTE $0x0b // movzx edi, byte [rdx + rax + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi + QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x010837442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r14 + 8], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x020817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 2 + QUAD $0x030807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x040807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x05081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 6 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x070807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 8 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x09083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 10 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x010802442031e3c4 // vpinsrb xmm0, xmm9, byte [rdx + rax + 8], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x020802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 2 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x03080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 3 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - QUAD $0x040812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 4 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x050802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 5 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x060832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 6 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x070802442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 8], 7 - QUAD $0x080822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 8], 8 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x090802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 9 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x0a0822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 8], 10 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0b083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 11 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0c083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 12 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0d083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 14 - QUAD $0x0f083a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 8], 15 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x01083a6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r15 + 8], 1 - QUAD $0x02081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03083a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 8], 3 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x04083a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 8], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05083a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 8], 5 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x06080a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 8], 6 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x07082a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 8], 7 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x08081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x09081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 9 - QUAD $0x0a08326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 10 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0b08326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 12 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0d081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 13 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0e08326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 14 - QUAD $0x0f081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 15 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x01091a742039a3c4 // vpinsrb xmm6, xmm8, byte [rdx + r11 + 9], 1 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x02091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 2 - QUAD $0x03090a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 9], 3 - WORD $0x8948; BYTE $0xcb // mov rbx, rcx - QUAD $0x040912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 4 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x050912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 5 - QUAD $0x060932742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 9], 6 - QUAD $0x070902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 7 - QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - QUAD $0x080902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 8 - QUAD $0x090902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 9 - QUAD $0x0a0922742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 9], 10 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0b0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 11 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0c0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 12 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0d090a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 9], 13 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 15 - QUAD $0x01093a7c2021a3c4 // vpinsrb xmm7, xmm11, byte [rdx + r15 + 9], 1 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0209027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 2 + QUAD $0x0b0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 11 + QUAD $0x0c080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 13 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0309027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0409027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 4 - QUAD $0x05093a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rdi + 9], 5 - QUAD $0x06090a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r9 + 9], 6 - QUAD $0x07092a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 9], 7 + QUAD $0x0e0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 15 + QUAD $0x01081f6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r11 + 8], 1 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0208376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 2 + QUAD $0x0308276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 3 + QUAD $0x04080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0508076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 5 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x06080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x07080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 7 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x08080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x09080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 9 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0a081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 10 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0b080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 11 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x0c08176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 8], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 13 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0e08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 14 + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010937742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r14 + 9], 1 + QUAD $0x020917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 2 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x030937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 3 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x040917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 4 + QUAD $0x05091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x060917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 6 + QUAD $0x070907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 7 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x080917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 8 + QUAD $0x09093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 9 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0a091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 10 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0b0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 11 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0c0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 12 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x0d0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 13 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0e0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 14 + QUAD $0x0f090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0109177c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rdx + 9], 1 + QUAD $0x0209377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 2 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0309177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 3 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0409177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 4 + QUAD $0x0509077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0609077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0809027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 8 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x09093a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r15 + 9], 9 + QUAD $0x0709077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0a09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 10 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 13 - QUAD $0x0e09327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 9], 14 + QUAD $0x0809077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + QUAD $0x0a091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 10 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0b091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 11 + QUAD $0x0c09177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 9], 12 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + QUAD $0x0d090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 13 + QUAD $0x0e09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 - QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0f09026c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdx + rax + 9], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xc06ef9c5 // vmovd xmm0, eax LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 - QUAD $0x00046024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm5 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x010a1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 10], 1 + QUAD $0x00044024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm5 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x020a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 2 - QUAD $0x030a1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 10], 3 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - QUAD $0x040a2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 10], 4 - QUAD $0x050a125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 10], 5 - QUAD $0x060a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x070a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 7 - QUAD $0x080a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 8 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x090a125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 10], 9 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x0a0a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 10 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x0b0a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 11 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x0c0a0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 10], 12 - QUAD $0x0d0a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e0a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 14 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0f0a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 15 - QUAD $0x010a22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 10], 1 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x020a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x030a3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 10], 3 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x040a3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 10], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x050a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 5 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x060a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 6 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x070a22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 10], 7 + QUAD $0x010a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 2 + QUAD $0x030a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 3 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x040a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 4 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x050a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 5 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x060a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 9 + QUAD $0x0a0a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 10 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0b0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 11 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0c0a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 13 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x0e0a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 14 + QUAD $0x0f0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 15 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x010a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 1 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x020a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x050a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 5 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x060a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 6 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x080a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 8 - QUAD $0x090a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 9 + QUAD $0x070a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 7 LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0a0a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 10 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x0b0a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c0a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d0a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 13 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0e0a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 14 + QUAD $0x080a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x090a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 9 QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x0f0a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 15 - QUAD $0x010b1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 11], 1 - QUAD $0x020b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 2 - QUAD $0x030b1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 11], 3 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x040b2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 11], 4 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x050b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 5 - QUAD $0x060b324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 11], 6 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x070b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 7 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x080b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 8 - QUAD $0x090b124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 11], 9 + QUAD $0x0a0a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 10 + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + QUAD $0x0b0a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 11 + QUAD $0x0c0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 12 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x0d0a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 13 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x0e0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 14 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x0f0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 15 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x010b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 1 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x020b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 2 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x030b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 3 + QUAD $0x040b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 4 + QUAD $0x050b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 5 + QUAD $0x060b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 6 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x070b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 7 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x080b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x090b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 9 QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - QUAD $0x0a0b124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 11], 10 - QUAD $0x0b0b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 11 - QUAD $0x0c0b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 12 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0d0b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e0b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 14 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f0b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 15 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x010b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 1 - QUAD $0x020b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 11], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x030b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 3 - QUAD $0x040b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 11], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x050b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 5 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x060b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 6 - QUAD $0x070b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 11], 7 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x080b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x090b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 9 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0a0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 10 - QUAD $0x0b0b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 13 + QUAD $0x0a0b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 10 + QUAD $0x0b0b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 11 + QUAD $0x0c0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 12 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x0d0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 13 + QUAD $0x0e0b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 14 + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x0f0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 15 + QUAD $0x010b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 1 + QUAD $0x020b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 2 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + QUAD $0x040b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 4 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x050b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x060b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 10 + QUAD $0x0b0b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 11], 11 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x0c0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 12 + QUAD $0x0d0b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 - QUAD $0x000440249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm3 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0e0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 14 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a7cb60f; BYTE $0x0d // movzx edi, byte [rdx + rcx + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x0f0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 15 + QUAD $0x000420249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm3 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0f0b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 - QUAD $0x000420248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm1 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - LONG $0x0a7cb60f; BYTE $0x0d // movzx edi, byte [rdx + rcx + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x010c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 1 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x020c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 2 - QUAD $0x030c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 3 - QUAD $0x040c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 12], 4 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x050c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 12], 5 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x060c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 12], 6 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x070c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 12], 7 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x080c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 8 - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x090c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 12], 9 - QUAD $0x0a0c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 12], 10 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0b0c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 12], 11 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0c0c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 12], 12 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0d0c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 12], 13 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0e0c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 12], 14 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0f0c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 12], 15 - QUAD $0x010c1a542051e3c4 // vpinsrb xmm2, xmm5, byte [rdx + rbx + 12], 1 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - QUAD $0x020c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x030c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 3 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x040c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 4 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x050c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 5 - QUAD $0x060c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 6 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x070c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 7 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x080c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x090c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 9 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0a0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 10 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0b0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 12 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0d0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 13 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0e0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 14 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x0f0c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 15 - QUAD $0x010d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 1 - QUAD $0x020d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 13], 2 - WORD $0x8949; BYTE $0xf5 // mov r13, rsi - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x030d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 13], 3 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x040d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 4 - QUAD $0x050d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 5 - QUAD $0x060d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 6 - QUAD $0x070d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 13], 7 - QUAD $0x080d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 8 - QUAD $0x090d325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 13], 9 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x0a0d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 10 + QUAD $0x000400248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm1 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x010c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x020c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 2 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x030c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 3 + QUAD $0x040c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0b0d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 11 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0c0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 12 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0d0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 13 - QUAD $0x0e0d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 13], 14 - QUAD $0x0f0d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 15 - WORD $0x894d; BYTE $0xe6 // mov r14, r12 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x010d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 1 - QUAD $0x020d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 2 - QUAD $0x030d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 3 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x040d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x050d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x060d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 6 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x070d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 7 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x080d124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 13], 8 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x090d224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 13], 9 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0a0d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b0d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c0d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d0d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 13 - WORD $0x8949; BYTE $0xdf // mov r15, rbx - QUAD $0x0e0d1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 13], 14 - LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 - QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0f0d3a442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rdi + 13], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x0e // movzx edi, byte [rdx + rdi + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 - QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x3a7cb60f; BYTE $0x0e // movzx edi, byte [rdx + rdi + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x010e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 14], 1 - QUAD $0x020e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 2 - QUAD $0x030e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 3 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x040e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 4 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x050e3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 14], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x060e3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 14], 6 - QUAD $0x070e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 14], 7 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x080e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 14], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x090e3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 14], 9 - QUAD $0x0a0e024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 14], 10 - QUAD $0x0b0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 11 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0c0e1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 14], 12 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x0d0e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e0e3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 14], 14 - QUAD $0x0f0e324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 14], 15 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x010e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 14], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x020e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 2 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x030e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 14], 3 - QUAD $0x040e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x050e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 5 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x060e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 6 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x070e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 7 - QUAD $0x080e12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 14], 8 - QUAD $0x090e22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 14], 9 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0a0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 10 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0b0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d0e0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 14], 13 - QUAD $0x0e0e3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 14], 14 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0f0e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x0f // movzx edi, byte [rdx + rdi + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x010f0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 15], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x020f3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 15], 2 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x030f3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 15], 3 - QUAD $0x040f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 4 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x050f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 5 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x060f22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 15], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x070f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 7 - QUAD $0x080f1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 15], 8 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x090f1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 15], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 10 - QUAD $0x0b0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 11 - QUAD $0x0c0f1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 15], 12 - QUAD $0x0d0f2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 15], 13 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0e0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 15 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x0f12 // movzx edi, byte [rdx + r10 + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x010f025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 15], 1 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x020f2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 15], 2 - QUAD $0x030f325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 15], 3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x040f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 4 + QUAD $0x050c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 6 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x070c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 7 + QUAD $0x080c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 8 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x050f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 5 + QUAD $0x090c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 9 + QUAD $0x0a0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 11 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x060f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 6 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x070f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x080f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x090f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 9 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x0a0f3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 15], 10 + QUAD $0x0c0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 12 + QUAD $0x0d0c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 12], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f0c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 15 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x010c1f542051a3c4 // vpinsrb xmm2, xmm5, byte [rdi + r11 + 12], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x020c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x040c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 4 + QUAD $0x050c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 5 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x060c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x070c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 7 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x080c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x090c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 9 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0a0c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 10 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0b0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 11 + QUAD $0x0c0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 13 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0e0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 14 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0f0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 15 + QUAD $0x010d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 1 + QUAD $0x020d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 2 + QUAD $0x030d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 4 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x050d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 5 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x060d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 6 + QUAD $0x070d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 7 + QUAD $0x080d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 8 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x090d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 9 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0a0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 10 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0b0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 11 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x0d0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 13 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0e0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 14 + QUAD $0x0f0d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 15 + QUAD $0x010d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 1 LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0b0f1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 15], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 12 - QUAD $0x0d0f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 13 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0e0f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 14 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0f0f325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 15], 15 - LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 - QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 - QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x100a // movzx edi, byte [rdx + r9 + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x01100a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 16], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02100a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 16], 2 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x031002442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 16], 3 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x04103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 4 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x05103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 5 - QUAD $0x061022442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 16], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x07103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 7 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x08103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 8 - QUAD $0x09101a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 16], 9 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x0a1022442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 16], 10 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0b103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 11 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0c103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 12 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0d103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 13 - QUAD $0x0e1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 14 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0f1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 15 - LONG $0x7cb60f42; WORD $0x1012 // movzx edi, byte [rdx + r10 + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x0110324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 1 - QUAD $0x02102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0310324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 3 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0410324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 4 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0510324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 5 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x06101a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 16], 6 - QUAD $0x0710024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 7 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0810024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0910024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 9 - QUAD $0x0a103a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 16], 10 - QUAD $0x0b101a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 16], 11 + QUAD $0x020d1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 13], 2 + QUAD $0x030d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x040d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x050d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 5 + QUAD $0x060d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 6 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + QUAD $0x070d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 7 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x080d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x090d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 9 + QUAD $0x0a0d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c10024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 12 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0d101a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 16], 13 + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x0c0d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 14 + LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 + QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0e10024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 14 - QUAD $0x0f10324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 16], 15 - LONG $0x7cb60f42; WORD $0x110a // movzx edi, byte [rdx + r9 + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x011102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 1 - QUAD $0x02110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 2 - QUAD $0x031102542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 17], 3 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x041102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 4 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - QUAD $0x051132542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 17], 5 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x061132542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 17], 6 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x071102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 7 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x08113a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 17], 8 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x091102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 9 - QUAD $0x0a1122542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 17], 10 + QUAD $0x0f0d07442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x0e2f // movzx eax, byte [rdi + r13 + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 + QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x0e3f // movzx eax, byte [rdi + r15 + 14] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x010e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + QUAD $0x040e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0b1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 11 + QUAD $0x050e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 8 + QUAD $0x090e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 9 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0a0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 10 + QUAD $0x0b0e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 11 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0c0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 12 + QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] + QUAD $0x0d0e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x020e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 2 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0c1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 12 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x0d112a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 17], 13 + QUAD $0x030e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x040e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 14 + QUAD $0x050e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 5 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x060e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 6 + QUAD $0x070e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 7 + QUAD $0x080e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x090e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 11 + QUAD $0x0c0e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 12 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x0d0e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 13 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f1102542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 17], 15 - LONG $0x7cb60f42; WORD $0x1112 // movzx edi, byte [rdx + r10 + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x0111225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 17], 1 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x02110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 2 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0311025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 17], 3 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x04110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x05110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 5 - QUAD $0x06111a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 17], 6 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x07110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 7 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x08110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x09110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 9 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0a110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 12 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - QUAD $0x0d111a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 17], 13 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0e113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x0e0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 15 + LONG $0x44b60f42; WORD $0x0f2f // movzx eax, byte [rdi + r13 + 15] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x010f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x030f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 3 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x040f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 15], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x070f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x090f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 9 + QUAD $0x0a0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 11 + QUAD $0x0c0f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 12 + QUAD $0x0d0f1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 15], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 14 + QUAD $0x0f0f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 15 + LONG $0x44b60f42; WORD $0x0f3f // movzx eax, byte [rdi + r15 + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x010f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 1 + QUAD $0x020f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x030f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x050f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 5 + QUAD $0x060f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x070f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 7 + QUAD $0x080f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 8 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x090f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 9 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x0a0f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0d0f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 13 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0e0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 14 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x0f0f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 15 + LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x0f111a442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rbx + 17], 15 - LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x12 // movzx edi, byte [rdx + rdi + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x01123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x02123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 2 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x03123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 3 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x04123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 4 - QUAD $0x051232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 18], 5 - QUAD $0x061232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x071232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 7 - QUAD $0x08123a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 18], 8 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x091232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 10 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0b1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 11 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0c1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 12 - QUAD $0x0d122a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 18], 13 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0e1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 14 - QUAD $0x0f1202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 15 - LONG $0x7cb60f42; WORD $0x1212 // movzx edi, byte [rdx + r10 + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0112224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 18], 1 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0212124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 18], 2 - QUAD $0x0312024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 3 - WORD $0x894d; BYTE $0xc4 // mov r12, r8 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0412324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 4 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0512324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 18], 5 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0612024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 6 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x07122a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 18], 7 - QUAD $0x08120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 8 + LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 + QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x011017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 1 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0912024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 9 - QUAD $0x0a120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 10 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0b120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 12 - QUAD $0x0d121a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 18], 13 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0e120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 14 - QUAD $0x0f121a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 18], 15 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x133a // movzx edi, byte [rdx + r15 + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x01130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 1 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x02130a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 19], 2 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x03130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 3 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x04131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 4 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x05130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 5 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x06130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 6 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x07130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 7 + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x03100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 3 + QUAD $0x041007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 4 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x051007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 6 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x071027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 8 + QUAD $0x09101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 10 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + QUAD $0x0b103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 13 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x0e1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0110074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0210074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0310074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + QUAD $0x05101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0610074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0710074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0810074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 8 + QUAD $0x0910374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 9 + QUAD $0x0a102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 10 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0b10374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 13 + QUAD $0x0e10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 14 + QUAD $0x0f100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 15 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x110f // movzx eax, byte [rdi + r9 + 17] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 1 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x02111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 2 + QUAD $0x03110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 3 QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x08130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 8 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x09131a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 19], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 10 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0b130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 11 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0c130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 12 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0d130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 14 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 15 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - LONG $0x0a7cb60f; BYTE $0x13 // movzx edi, byte [rdx + rcx + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x01133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 1 - QUAD $0x0213125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 19], 2 - QUAD $0x0313225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 19], 3 - QUAD $0x0413325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 4 - QUAD $0x0513325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 19], 5 - QUAD $0x0613025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 19], 6 - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - QUAD $0x07132a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 19], 7 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0813325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 8 - QUAD $0x0913025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 9 + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + QUAD $0x051107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 6 + QUAD $0x071127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 7 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x081117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 8 + QUAD $0x09111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 10 + QUAD $0x0b113f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 17], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0d1127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 13 + QUAD $0x0e1117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 14 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x0f112f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 17], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x11 // movzx eax, byte [rdi + rax + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0111075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 1 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0211075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 2 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0311375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0411075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0611075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 6 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0711175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0a13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 10 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 11 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0c13125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 19], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 13 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0e132a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 19], 14 + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0f13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 15 + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + QUAD $0x0b11375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 11 + QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] + QUAD $0x0c11375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 + QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1107442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 17], 15 + LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - LONG $0x7cb60f42; WORD $0x143a // movzx edi, byte [rdx + r15 + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x011402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 20], 1 - QUAD $0x02140a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 20], 2 - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x03143a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 20], 3 - QUAD $0x04141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 4 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x051432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 5 + LONG $0x44b60f42; WORD $0x120f // movzx eax, byte [rdi + r9 + 18] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 + QUAD $0x02121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 2 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x03123f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 18], 3 + QUAD $0x04120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 7 + QUAD $0x081217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 8 + QUAD $0x09121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 12 + QUAD $0x0d1227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 14 + QUAD $0x0f122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x0112274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 1 + QUAD $0x0212074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 2 + QUAD $0x0312374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x061402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 6 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x07140a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 20], 7 + QUAD $0x0412074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0512074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 5 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0612374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 6 + QUAD $0x0712174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 7 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x08120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 8 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x09122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 9 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0a12074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 10 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0b121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 11 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x0c12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 12 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0d121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 13 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x0e12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 14 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0f12174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 2 + QUAD $0x03133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 3 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x081402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 8 - QUAD $0x09141a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 20], 9 + QUAD $0x041307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 5 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x06133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 6 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + QUAD $0x071317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 9 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 10 + QUAD $0x0a1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0113275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0313075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0413075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x0613375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x08130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 8 + QUAD $0x09132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 9 + QUAD $0x0a13075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 10 + QUAD $0x0b131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 11 + QUAD $0x0c130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 12 + QUAD $0x0d131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 13 + QUAD $0x0e13375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 14 + QUAD $0x0f13175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 19], 15 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 + LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 + QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x140f // movzx eax, byte [rdi + r9 + 20] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x011427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x03141f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 20], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0b1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 11 + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x06143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 6 + QUAD $0x071417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 9 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0a1437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 10 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0b1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 11 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x0c143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 12 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x0d140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 13 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0e141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 14 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x0f1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 15 + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x142f // movzx eax, byte [rdi + r13 + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0114374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0c1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 12 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0d1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 13 + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0414074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 14 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0f143a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 20], 15 - LONG $0x0a7cb60f; BYTE $0x14 // movzx edi, byte [rdx + rcx + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x01140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 1 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x02140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 2 - QUAD $0x0314224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 20], 3 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x04143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 4 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x05141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 5 - QUAD $0x0614324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 20], 6 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x07143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x08143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x09141a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 20], 9 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0a143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 11 - QUAD $0x0c14124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 13 - QUAD $0x0e142a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 20], 14 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x0f14224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 20], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x15 // movzx edi, byte [rdx + rdi + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011502542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 21], 1 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x02152a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 21], 2 - QUAD $0x03153a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 21], 3 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x04153a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 21], 4 - QUAD $0x051532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 5 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x061532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 6 - QUAD $0x07150a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 21], 7 - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x08150a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 21], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x09153a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 21], 9 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x0a153a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 21], 10 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0b1512542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 21], 11 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x0c1502542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 21], 12 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0d153a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 21], 13 - QUAD $0x0e1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x027cb60f; BYTE $0x15 // movzx edi, byte [rdx + rax + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0115025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 1 - QUAD $0x02150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0315025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0415025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 4 - QUAD $0x05151a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 21], 5 - QUAD $0x0615325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 21], 6 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0715025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 7 + QUAD $0x0514074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0614074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0815025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 8 - QUAD $0x09151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 9 + QUAD $0x0714074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0a15025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 10 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0b151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 11 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0c15325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 21], 12 + QUAD $0x0814074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0914074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 15 + LONG $0x44b60f42; WORD $0x150f // movzx eax, byte [rdi + r9 + 21] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 1 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x021517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 2 + QUAD $0x03151f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 21], 3 + QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] + QUAD $0x041527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 7 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d15025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 13 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0e150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 14 + QUAD $0x081507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 9 + QUAD $0x0a1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 10 + QUAD $0x0b1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 11 + QUAD $0x0c153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 12 + QUAD $0x0d150f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 21], 13 + QUAD $0x0e151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 14 + QUAD $0x0f1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 15 + LONG $0x44b60f42; WORD $0x152f // movzx eax, byte [rdi + r13 + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0115375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x04153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 4 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x05151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x07152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] + QUAD $0x0a150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 13 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0e15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x0f1522442061a3c4 // vpinsrb xmm0, xmm3, byte [rdx + r12 + 21], 15 + QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x0f151f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r11 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x16 // movzx edi, byte [rdx + rax + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 1 + QUAD $0x021617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x031607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 3 + QUAD $0x041627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 4 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x051617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 5 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x061617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 8 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x091627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 9 + QUAD $0x0a1637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 10 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x011602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 22], 1 - QUAD $0x02162a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 22], 2 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x031602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 22], 3 - QUAD $0x04163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 4 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x05163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 5 - QUAD $0x061632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x071632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 7 - QUAD $0x08160a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 22], 8 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x091632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a1632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 22], 10 - QUAD $0x0b1612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 22], 11 - QUAD $0x0c1602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 22], 12 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x0d162a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 22], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 14 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0f1612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 22], 15 - QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x161a // movzx edi, byte [rdx + r11 + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x01163a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 22], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x02163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 3 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x04163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x06163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 6 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x0716224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 22], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x08163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x09163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 9 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0a163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 10 - QUAD $0x0b161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 11 - QUAD $0x0c16324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 22], 12 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x0d16024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 22], 13 - QUAD $0x0e160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 14 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x0f160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 15 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - LONG $0x1a7cb60f; BYTE $0x17 // movzx edi, byte [rdx + rbx + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x01173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x02173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 2 - QUAD $0x031702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 3 + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 12 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x041702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 4 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x05173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 5 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x061732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 23], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x07173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 7 - QUAD $0x08170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 8 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x09170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 9 - QUAD $0x0a1732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 10 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0b1732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 11 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0c1732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 12 - QUAD $0x0d172a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 23], 13 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x0e172a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 23], 14 - QUAD $0x0f1712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 23], 15 - LONG $0x7cb60f42; WORD $0x171a // movzx edi, byte [rdx + r11 + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01173a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 23], 1 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0217325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 3 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x04173a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 23], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x06173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 6 - QUAD $0x0717225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 23], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x08173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x09173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 9 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0a173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 11 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0c17225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 23], 12 - QUAD $0x0d17025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 23], 13 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0e173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 14 - QUAD $0x0f170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 15 - LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 - LONG $0x386563c4; WORD $0x01da // vinserti128 ymm11, ymm3, xmm2, 1 - LONG $0x1a7cb60f; BYTE $0x18 // movzx edi, byte [rdx + rbx + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x01180a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 24], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02180a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 24], 2 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x031812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 24], 3 - QUAD $0x041802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 4 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x051802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 5 - QUAD $0x061832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 6 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x07181a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 24], 7 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x081832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 8 - QUAD $0x09180a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 24], 9 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x0a180a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 24], 10 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0b180a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 24], 11 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0c183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 12 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0d183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 13 - QUAD $0x0e182a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 24], 14 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0f183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 15 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x3a7cb60f; BYTE $0x18 // movzx edi, byte [rdx + rdi + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x01181a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 24], 1 - QUAD $0x0218324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 2 + QUAD $0x0d1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 14 + QUAD $0x0f1607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0116074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 1 + QUAD $0x02160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 2 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0316074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 3 + QUAD $0x04163f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 22], 4 + QUAD $0x05161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0616074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 6 + QUAD $0x07162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 11 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x0c160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + QUAD $0x0e16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 14 + QUAD $0x0f161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x01171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 2 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x03173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 4 + QUAD $0x051717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 5 + QUAD $0x061717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 6 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x07172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 8 + QUAD $0x091727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 9 + QUAD $0x0a1737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 10 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x0b171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 11 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0c170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 12 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x0d1717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 13 QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0318324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 3 - QUAD $0x04183a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 24], 4 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0518324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 5 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0618324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 6 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x0718024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 7 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0818324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 8 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0918324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 9 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0a18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 10 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0b18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 11 - QUAD $0x0c18224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 24], 12 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0d18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 13 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0e182a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 24], 14 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x0f18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x327cb60f; BYTE $0x19 // movzx edi, byte [rdx + rsi + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x011922542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 25], 1 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x021932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 2 - QUAD $0x031912542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 25], 3 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x04193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 4 - QUAD $0x051902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 5 + QUAD $0x0e1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 14 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x0f1727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x0117375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + QUAD $0x0317075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x061902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 6 - QUAD $0x07191a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 25], 7 - QUAD $0x081932542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 25], 8 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x091912542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 25], 9 - QUAD $0x0a190a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 25], 10 - QUAD $0x0b190a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 25], 11 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x0c190a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 25], 12 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0d190a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 25], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e190a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 25], 14 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0f191a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 25], 15 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - LONG $0x0a7cb60f; BYTE $0x19 // movzx edi, byte [rdx + rcx + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01191a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 25], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x02193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 3 - QUAD $0x04193a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 25], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 5 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x06193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 6 - QUAD $0x0719025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x08193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x09193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 9 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x0a19325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 25], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c191a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 25], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 13 - QUAD $0x0e192a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 25], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0f193a442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rdi + 25], 15 + QUAD $0x0417075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0517075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0617075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0717075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0817075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 11 + QUAD $0x0c170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 15 + LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 + LONG $0x386563c4; WORD $0x01da // vinserti128 ymm11, ymm3, xmm2, 1 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x01181f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 24], 1 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x02180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 2 + QUAD $0x03183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 3 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x041807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 6 + QUAD $0x07182f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 24], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 8 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x09183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 10 + QUAD $0x0b181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 11 + QUAD $0x0c180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 12 + QUAD $0x0d1817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 13 + QUAD $0x0e1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 14 + QUAD $0x0f1827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0118374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x0318174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 3 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x04181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0518074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0618074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0718074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 7 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x08180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0918074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 11 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x0c181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 12 + QUAD $0x0d18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 13 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0e18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x01192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 1 + QUAD $0x02190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 2 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x031927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 3 + QUAD $0x041907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 4 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x051907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 5 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x061937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 6 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x07190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + QUAD $0x09193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 12 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x0d1937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x0f193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + QUAD $0x0319175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 25], 3 + QUAD $0x04191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0519075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x08190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x09190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 11 + QUAD $0x0c191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 13 + QUAD $0x0e19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 14 + LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0f1917442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rdx + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x1a // movzx edi, byte [rdx + rdi + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011a22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 26], 1 - QUAD $0x021a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 2 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x031a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 3 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - QUAD $0x041a22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 26], 4 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x051a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 5 - QUAD $0x061a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 6 + QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x1a // movzx eax, byte [rdi + rax + 26] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 1 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x021a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 2 + QUAD $0x031a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 4 + QUAD $0x051a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 5 + QUAD $0x061a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 6 + QUAD $0x071a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 7 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x081a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 11 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x0c1a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 12 + QUAD $0x0d1a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 14 + QUAD $0x0f1a3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 26], 15 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x1a17 // movzx eax, byte [rdi + r10 + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x011a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 1 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x021a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x031a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 3 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x041a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 4 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x051a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 5 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x071a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 7 + QUAD $0x061a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x081a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 8 + QUAD $0x091a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a1a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 13 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x0e1a2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 26], 14 + QUAD $0x0f1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1744b60f; BYTE $0x1b // movzx eax, byte [rdi + rdx + 27] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x011b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 1 + QUAD $0x021b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x031b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 3 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x081a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 8 - QUAD $0x091a12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 26], 9 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x0a1a02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 26], 10 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0b1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 11 - QUAD $0x0c1a0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 26], 12 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0d1a0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 26], 13 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0e1a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 14 - QUAD $0x0f1a1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 26], 15 - LONG $0x0a7cb60f; BYTE $0x1a // movzx edi, byte [rdx + rcx + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x011a0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 26], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x021a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 2 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x031a124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 26], 3 - QUAD $0x041a3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 26], 4 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x051a3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 26], 5 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x061a1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 26], 6 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x071a2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 26], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x081a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x091a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 9 - QUAD $0x0a1a324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 26], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 11 - QUAD $0x0c1a1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 26], 12 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0d1a324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 26], 13 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0e1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 14 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0f1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x1b // movzx edi, byte [rdx + rdi + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x011b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 27], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x021b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 2 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x031b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 3 - QUAD $0x041b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 27], 4 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x051b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x061b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x071b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 7 - QUAD $0x081b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 8 - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - QUAD $0x091b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 27], 9 - QUAD $0x0a1b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 27], 10 + QUAD $0x041b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0b1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 11 + QUAD $0x051b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + QUAD $0x081b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 9 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x0a1b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 10 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0b1b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 11 + QUAD $0x0c1b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 12 + QUAD $0x0d1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f1b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 15 + LONG $0x44b60f42; WORD $0x1b17 // movzx eax, byte [rdi + r10 + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + QUAD $0x011b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 1 + QUAD $0x021b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 2 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0c1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 12 - QUAD $0x0d1b0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 27], 13 - QUAD $0x0e1b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0f1b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 27], 15 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - LONG $0x327cb60f; BYTE $0x1b // movzx edi, byte [rdx + rsi + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x011b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 1 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x021b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 2 - QUAD $0x031b125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 27], 3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x041b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 4 - QUAD $0x051b3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 27], 5 - QUAD $0x061b1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 27], 6 - QUAD $0x071b2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 27], 7 + QUAD $0x031b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 3 + QUAD $0x041b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 4 + QUAD $0x051b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x081b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x091b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 9 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0a1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 10 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0b1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 11 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - QUAD $0x0c1b1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 27], 12 - QUAD $0x0d1b325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 27], 13 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0e1b3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 27], 14 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0f1b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 15 + QUAD $0x071b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x081b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x091b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 9 + QUAD $0x0a1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 13 + QUAD $0x0e1b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 + QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 - QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x1c // movzx edi, byte [rdx + rdi + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 28], 1 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x021c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 28], 2 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x031c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 28], 3 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - QUAD $0x041c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 28], 4 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x051c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 28], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x061c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 28], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x071c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 28], 7 + QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 + LONG $0x1744b60f; BYTE $0x1c // movzx eax, byte [rdi + rdx + 28] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 2 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x031c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 3 QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - QUAD $0x081c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 8 - QUAD $0x091c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 28], 9 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0a1c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 28], 10 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0b1c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 28], 11 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0c1c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 28], 12 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x0d1c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e1c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 28], 14 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0f1c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 28], 15 - LONG $0x327cb60f; BYTE $0x1c // movzx edi, byte [rdx + rsi + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x011c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 1 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x021c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x031c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 3 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x041c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x051c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 5 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x061c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 6 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x071c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x081c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 8 - QUAD $0x091c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 9 + QUAD $0x041c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 4 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x051c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x061c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 9 + QUAD $0x0a1c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 10 + QUAD $0x0b1c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 28], 11 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x0c1c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 12 + QUAD $0x0d1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 14 + QUAD $0x0f1c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 15 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + LONG $0x1744b60f; BYTE $0x1c // movzx eax, byte [rdi + rdx + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x031c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x041c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x051c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 5 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x061c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0a1c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 10 - QUAD $0x0b1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 11 - QUAD $0x0c1c1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 28], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 13 - QUAD $0x0e1c3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 28], 14 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x0f1c1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 28], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x1d // movzx edi, byte [rdx + rax + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x011d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 1 - QUAD $0x021d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 2 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x031d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 3 - QUAD $0x041d12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 29], 4 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x051d12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 29], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x061d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 6 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x071d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 7 - QUAD $0x081d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x091d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 9 - QUAD $0x0a1d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 10 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0b1d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 11 - QUAD $0x0c1d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 12 - QUAD $0x0d1d2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 29], 13 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x0e1d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 14 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0f1d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 15 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x3a7cb60f; BYTE $0x1d // movzx edi, byte [rdx + rdi + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x011d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 1 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x021d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 2 - QUAD $0x031d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 3 + QUAD $0x081c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 8 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x091c374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 28], 9 + QUAD $0x0a1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 10 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0b1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 11 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x0c1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x1d // movzx eax, byte [rdi + rax + 29] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x011d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 2 + QUAD $0x031d0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 29], 3 + QUAD $0x041d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 4 + QUAD $0x051d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 5 + QUAD $0x061d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 9 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0a1d0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 29], 10 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0b1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 11 + QUAD $0x0c1d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 12 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + QUAD $0x0d1d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 14 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x0f1d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 15 + LONG $0x1744b60f; BYTE $0x1d // movzx eax, byte [rdi + rdx + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] + QUAD $0x011d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 2 + QUAD $0x031d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 3 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x041d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 + QUAD $0x061d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x081d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 8 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + QUAD $0x091d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 29], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 10 + QUAD $0x0b1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 11 + QUAD $0x0c1d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 12 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x041d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 4 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x051d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 29], 5 - QUAD $0x061d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 29], 6 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x071d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 7 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x081d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x091d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 9 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0a1d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b1d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c1d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 29], 12 - QUAD $0x0d1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 13 - QUAD $0x0e1d3a642061a3c4 // vpinsrb xmm4, xmm3, byte [rdx + r15 + 29], 14 + QUAD $0x0d1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 13 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x0e1d37642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r14 + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x0f1d1a442059a3c4 // vpinsrb xmm0, xmm4, byte [rdx + r11 + 29], 15 + QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1d07442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rax + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - LONG $0x027cb60f; BYTE $0x1e // movzx edi, byte [rdx + rax + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x011e3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 30], 1 - LONG $0x027cb60f; BYTE $0x1f // movzx edi, byte [rdx + rax + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 31], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x021e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 2 - QUAD $0x021f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 2 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x031e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 3 - QUAD $0x031f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 3 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x041e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 4 - QUAD $0x041f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 4 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x051e12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 30], 5 - QUAD $0x051f124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 31], 5 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x061e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 6 - QUAD $0x061f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 6 - QUAD $0x071e0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 30], 7 - QUAD $0x071f0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 31], 7 - QUAD $0x00000110248c8b4c // mov r9, qword [rsp + 272] + QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + LONG $0x1f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rbx + 30] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 1 + LONG $0x1f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rbx + 31] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011f0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 31], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x081e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 8 - QUAD $0x081f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 8 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x091e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 9 - QUAD $0x091f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 10 - QUAD $0x0a1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 10 + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0b1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 11 - QUAD $0x0b1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 11 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0c1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 12 - QUAD $0x0c1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 12 + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0d1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 13 - QUAD $0x0d1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 13 - QUAD $0x0e1e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 30], 14 - QUAD $0x0e1f324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 31], 14 - QUAD $0x0f1e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 30], 15 - QUAD $0x0f1f02542071a3c4 // vpinsrb xmm2, xmm1, byte [rdx + r8 + 31], 15 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x3a44b60f; BYTE $0x1e // movzx eax, byte [rdx + rdi + 30] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x00000110249c8b48 // mov rbx, qword [rsp + 272] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + QUAD $0x0a1e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 30], 10 + QUAD $0x0a1f0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 31], 10 + QUAD $0x0b1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 11 + QUAD $0x0b1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 + QUAD $0x0d1e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 30], 13 + QUAD $0x0d1f3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 31], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x0f1e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 30], 15 + QUAD $0x0f1f27542071a3c4 // vpinsrb xmm2, xmm1, byte [rdi + r12 + 31], 15 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x011e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 30], 1 - LONG $0x3a44b60f; BYTE $0x1f // movzx eax, byte [rdx + rdi + 31] + QUAD $0x011e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f127c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r10 + 31], 1 - QUAD $0x021e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 30], 2 - QUAD $0x021f2a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 31], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x031e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 3 - QUAD $0x031f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x041e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 4 - QUAD $0x041f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 4 - QUAD $0x051e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 30], 5 - QUAD $0x051f227c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r12 + 31], 5 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x061e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 6 - QUAD $0x061f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 6 - QUAD $0x071e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 30], 7 - QUAD $0x071f327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 31], 7 + QUAD $0x011f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 1 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x021e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 2 + QUAD $0x021f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x041e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 4 + QUAD $0x041f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x091e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 9 - QUAD $0x091f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 9 + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 10 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 11 - QUAD $0x0b1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 11 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x0c1e1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 30], 12 - QUAD $0x0c1f1a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 31], 12 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x0d1e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 30], 13 - QUAD $0x0d1f0a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 31], 13 + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 9 + QUAD $0x091f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + QUAD $0x0d1e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 13 + QUAD $0x0d1f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 13 + QUAD $0x0e1e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 30], 14 + QUAD $0x0e1f377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 31], 14 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 14 - QUAD $0x0f1e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 30], 15 - QUAD $0x0f1f1a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 31], 15 + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 QUAD $0x00020024946ffdc5; BYTE $0x00 // vmovdqa ymm2, yword [rsp + 512] LONG $0xc27495c5 // vpcmpeqb ymm0, ymm13, ymm2 - QUAD $0x0004c024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1216] + QUAD $0x0004a024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1184] LONG $0x6d6ffdc5; BYTE $0x00 // vmovdqa ymm5, yword 0[rbp] /* [rip + .LCPI5_0] */ LONG $0xfddfc5c5 // vpandn ymm7, ymm7, ymm5 LONG $0xc0fcc5c5 // vpaddb ymm0, ymm7, ymm0 @@ -32466,12 +33346,12 @@ LBB5_166: LONG $0xe3df1dc5 // vpandn ymm12, ymm12, ymm3 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0xe2740dc5 // vpcmpeqb ymm12, ymm14, ymm2 - LONG $0x456f7dc5; BYTE $0x60 // vmovdqa ymm8, yword 96[rbp] /* [rip + .LCPI5_3] */ - LONG $0xdf1d41c4; BYTE $0xe0 // vpandn ymm12, ymm12, ymm8 + LONG $0x656ffdc5; BYTE $0x60 // vmovdqa ymm4, yword 96[rbp] /* [rip + .LCPI5_3] */ + LONG $0xe4df1dc5 // vpandn ymm12, ymm12, ymm4 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0xc976f5c5 // vpcmpeqd ymm1, ymm1, ymm1 LONG $0xc1f8fdc5 // vpsubb ymm0, ymm0, ymm1 - LONG $0xe476ddc5 // vpcmpeqd ymm4, ymm4, ymm4 + LONG $0x763d41c4; BYTE $0xc0 // vpcmpeqd ymm8, ymm8, ymm8 LONG $0xc7ebfdc5 // vpor ymm0, ymm0, ymm7 LONG $0xfa7485c5 // vpcmpeqb ymm7, ymm15, ymm2 QUAD $0x000000808d6ffdc5 // vmovdqa ymm1, yword 128[rbp] /* [rip + .LCPI5_4] */ @@ -32480,73 +33360,75 @@ LBB5_166: QUAD $0x000000a0ad6f7dc5 // vmovdqa ymm13, yword 160[rbp] /* [rip + .LCPI5_5] */ LONG $0xdf1d41c4; BYTE $0xe5 // vpandn ymm12, ymm12, ymm13 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 - QUAD $0x0004a024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1184] - QUAD $0x000000c08d6f7dc5 // vmovdqa ymm9, yword 192[rbp] /* [rip + .LCPI5_6] */ - LONG $0xdf1d41c4; BYTE $0xe1 // vpandn ymm12, ymm12, ymm9 + QUAD $0x00048024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1152] + QUAD $0x000000c0b56f7dc5 // vmovdqa ymm14, yword 192[rbp] /* [rip + .LCPI5_6] */ + LONG $0xdf1d41c4; BYTE $0xe6 // vpandn ymm12, ymm12, ymm14 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0xc7ebfdc5 // vpor ymm0, ymm0, ymm7 - QUAD $0x00048024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1152] - QUAD $0x00046024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1120] + QUAD $0x00046024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1120] + QUAD $0x00044024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1088] LONG $0xe5df1dc5 // vpandn ymm12, ymm12, ymm5 LONG $0xfffc9dc5 // vpaddb ymm7, ymm12, ymm7 - QUAD $0x00044024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1088] + QUAD $0x00042024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1056] LONG $0xe6df1dc5 // vpandn ymm12, ymm12, ymm6 - QUAD $0x00042024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 1056] + QUAD $0x00040024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 1024] LONG $0xfbdf05c5 // vpandn ymm15, ymm15, ymm3 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 - QUAD $0x0003e024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 992] - LONG $0xdf0541c4; BYTE $0xf8 // vpandn ymm15, ymm15, ymm8 + QUAD $0x0003c024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 960] + LONG $0xfcdf05c5 // vpandn ymm15, ymm15, ymm4 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 - LONG $0xfcf8c5c5 // vpsubb ymm7, ymm7, ymm4 + LONG $0xf845c1c4; BYTE $0xf8 // vpsubb ymm7, ymm7, ymm8 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 - QUAD $0x00040024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1024] + QUAD $0x0003e024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 992] LONG $0xe1df1dc5 // vpandn ymm12, ymm12, ymm1 - QUAD $0x0003a024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 928] + QUAD $0x00038024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 896] LONG $0xdf0541c4; BYTE $0xfd // vpandn ymm15, ymm15, ymm13 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 - QUAD $0x0003c024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 960] - LONG $0xdf0541c4; BYTE $0xf9 // vpandn ymm15, ymm15, ymm9 + QUAD $0x0003a024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 928] + LONG $0xdf0541c4; BYTE $0xfe // vpandn ymm15, ymm15, ymm14 + LONG $0x6f7d41c4; BYTE $0xc6 // vmovdqa ymm8, ymm14 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 LONG $0xe7eb1dc5 // vpor ymm12, ymm12, ymm7 - QUAD $0x00038024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 896] - QUAD $0x00036024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 864] + QUAD $0x00036024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 864] + QUAD $0x00034024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 832] LONG $0xfddf05c5 // vpandn ymm15, ymm15, ymm5 LONG $0xfffc85c5 // vpaddb ymm7, ymm15, ymm7 - QUAD $0x00032024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 800] + QUAD $0x00030024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 768] LONG $0xfedf05c5 // vpandn ymm15, ymm15, ymm6 - QUAD $0x00034024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 832] + QUAD $0x00032024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 800] LONG $0xf3df0dc5 // vpandn ymm14, ymm14, ymm3 LONG $0xeb0541c4; BYTE $0xf6 // vpor ymm14, ymm15, ymm14 - QUAD $0x0002e024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 736] - LONG $0xdf0541c4; BYTE $0xf8 // vpandn ymm15, ymm15, ymm8 + QUAD $0x0002c024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 704] + LONG $0xfcdf05c5 // vpandn ymm15, ymm15, ymm4 LONG $0xeb0d41c4; BYTE $0xf7 // vpor ymm14, ymm14, ymm15 - LONG $0xfcf8c5c5 // vpsubb ymm7, ymm7, ymm4 + LONG $0x760541c4; BYTE $0xff // vpcmpeqd ymm15, ymm15, ymm15 + LONG $0xf845c1c4; BYTE $0xff // vpsubb ymm7, ymm7, ymm15 LONG $0xffeb8dc5 // vpor ymm7, ymm14, ymm7 - QUAD $0x00030024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 768] + QUAD $0x0002e024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 736] LONG $0xf1df0dc5 // vpandn ymm14, ymm14, ymm1 LONG $0xd2742dc5 // vpcmpeqb ymm10, ymm10, ymm2 LONG $0xdf2d41c4; BYTE $0xd5 // vpandn ymm10, ymm10, ymm13 LONG $0xeb0d41c4; BYTE $0xd2 // vpor ymm10, ymm14, ymm10 LONG $0xda7425c5 // vpcmpeqb ymm11, ymm11, ymm2 - LONG $0x6f7d41c4; BYTE $0xf1 // vmovdqa ymm14, ymm9 - LONG $0xdf2541c4; BYTE $0xd9 // vpandn ymm11, ymm11, ymm9 + LONG $0xdf2541c4; BYTE $0xd8 // vpandn ymm11, ymm11, ymm8 + LONG $0x6f7d41c4; BYTE $0xf0 // vmovdqa ymm14, ymm8 LONG $0xeb2d41c4; BYTE $0xd3 // vpor ymm10, ymm10, ymm11 LONG $0xffebadc5 // vpor ymm7, ymm10, ymm7 - QUAD $0x000220248c746dc5; BYTE $0x00 // vpcmpeqb ymm9, ymm2, yword [rsp + 544] - QUAD $0x0002402484746dc5; BYTE $0x00 // vpcmpeqb ymm8, ymm2, yword [rsp + 576] + LONG $0xca7435c5 // vpcmpeqb ymm9, ymm9, ymm2 + QUAD $0x0002202484746dc5; BYTE $0x00 // vpcmpeqb ymm8, ymm2, yword [rsp + 544] LONG $0xc5df3dc5 // vpandn ymm8, ymm8, ymm5 LONG $0xfc3d41c4; BYTE $0xc1 // vpaddb ymm8, ymm8, ymm9 - QUAD $0x00026024ac74edc5; BYTE $0x00 // vpcmpeqb ymm5, ymm2, yword [rsp + 608] + QUAD $0x00024024ac74edc5; BYTE $0x00 // vpcmpeqb ymm5, ymm2, yword [rsp + 576] LONG $0xeedfd5c5 // vpandn ymm5, ymm5, ymm6 - QUAD $0x00028024b474edc5; BYTE $0x00 // vpcmpeqb ymm6, ymm2, yword [rsp + 640] + QUAD $0x00026024b474edc5; BYTE $0x00 // vpcmpeqb ymm6, ymm2, yword [rsp + 608] LONG $0xf3dfcdc5 // vpandn ymm6, ymm6, ymm3 LONG $0xeeebd5c5 // vpor ymm5, ymm5, ymm6 - QUAD $0x0002a0249c74edc5; BYTE $0x00 // vpcmpeqb ymm3, ymm2, yword [rsp + 672] - LONG $0x5ddfe5c5; BYTE $0x60 // vpandn ymm3, ymm3, yword 96[rbp] /* [rip + .LCPI5_3] */ + QUAD $0x000280249c74edc5; BYTE $0x00 // vpcmpeqb ymm3, ymm2, yword [rsp + 640] + LONG $0xdcdfe5c5 // vpandn ymm3, ymm3, ymm4 LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 - LONG $0xecf8bdc5 // vpsubb ymm5, ymm8, ymm4 + LONG $0xf83dc1c4; BYTE $0xef // vpsubb ymm5, ymm8, ymm15 LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 - QUAD $0x0002c024a474edc5; BYTE $0x00 // vpcmpeqb ymm4, ymm2, yword [rsp + 704] + QUAD $0x0002a024a474edc5; BYTE $0x00 // vpcmpeqb ymm4, ymm2, yword [rsp + 672] LONG $0xe1dfddc5 // vpandn ymm4, ymm4, ymm1 QUAD $0x000140248c74edc5; BYTE $0x00 // vpcmpeqb ymm1, ymm2, yword [rsp + 320] LONG $0xdf75c1c4; BYTE $0xcd // vpandn ymm1, ymm1, ymm13 @@ -32568,2002 +33450,2004 @@ LBB5_166: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x7f7ec1c4; WORD $0x8944; BYTE $0x60 // vmovdqu yword [r9 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8954; BYTE $0x40 // vmovdqu yword [r9 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8964; BYTE $0x20 // vmovdqu yword [r9 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x890c // vmovdqu yword [r9 + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608b // vmovdqu yword [rbx + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408b // vmovdqu yword [rbx + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208b // vmovdqu yword [rbx + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8b // vmovdqu yword [rbx + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 - WORD $0x8948; BYTE $0xce // mov rsi, rcx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000178248c3b48 // cmp rcx, qword [rsp + 376] - JNE LBB5_166 - QUAD $0x0000018024b48b4c // mov r14, qword [rsp + 384] - QUAD $0x0000017824b43b4c // cmp r14, qword [rsp + 376] - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - QUAD $0x0000019024ac8b4c // mov r13, qword [rsp + 400] - QUAD $0x0000018824948b48 // mov rdx, qword [rsp + 392] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - JNE LBB5_43 - JMP LBB5_46 + JNE LBB5_190 + QUAD $0x00000180248c8b48 // mov rcx, qword [rsp + 384] + QUAD $0x00000178248c3b48 // cmp rcx, qword [rsp + 376] + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + QUAD $0x0000018824ac8b4c // mov r13, qword [rsp + 392] + QUAD $0x0000019024bc8b48 // mov rdi, qword [rsp + 400] + JNE LBB5_139 + JMP LBB5_142 -LBB5_168: - LONG $0xe0e68349 // and r14, -32 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 +LBB5_192: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000018824848948 // mov qword [rsp + 392], rax - QUAD $0x0000017824b4894c // mov qword [rsp + 376], r14 - QUAD $0x00000000b5048d4a // lea rax, [4*r14] - WORD $0x014c; BYTE $0xe8 // add rax, r13 + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - LONG $0x6e79c1c4; BYTE $0xc3 // vmovd xmm0, r11d + QUAD $0x00000178248c8948 // mov qword [rsp + 376], rcx + QUAD $0x000000008d048d48 // lea rax, [4*rcx] + WORD $0x014c; BYTE $0xe8 // add rax, r13 + QUAD $0x0000018824848948 // mov qword [rsp + 392], rax + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 - WORD $0xdb31 // xor ebx, ebx + WORD $0xc031 // xor eax, eax QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 -LBB5_169: - QUAD $0x00000198249c8948 // mov qword [rsp + 408], rbx +LBB5_193: + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x0000019824848948 // mov qword [rsp + 408], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1a04b60f // movzx eax, byte [rdx + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] + LONG $0x1744b60f; BYTE $0x01 // movzx eax, byte [rdi + rdx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x0a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rcx + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x0a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rcx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x0a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rcx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - QUAD $0x00000100249c8948 // mov qword [rsp + 256], rbx - LONG $0x1a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x0a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rcx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x0a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rcx + 6] - QUAD $0x000000d8248c8948 // mov qword [rsp + 216], rcx + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x000000e824948948 // mov qword [rsp + 232], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x0a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rcx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x20ce8149; WORD $0x0002; BYTE $0x00 // or r14, 544 - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x40c98148; WORD $0x0002; BYTE $0x00 // or rcx, 576 - QUAD $0x000000b8248c8948 // mov qword [rsp + 184], rcx - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02600d48; WORD $0x0000 // or rax, 608 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02800d48; WORD $0x0000 // or rax, 640 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax - WORD $0x8949; BYTE $0xda // mov r10, rbx - LONG $0xa0ca8149; WORD $0x0002; BYTE $0x00 // or r10, 672 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - LONG $0xc0c98149; WORD $0x0002; BYTE $0x00 // or r9, 704 - QUAD $0x000000e8248c894c // mov qword [rsp + 232], r9 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0xe0cb8149; WORD $0x0002; BYTE $0x00 // or r11, 736 - LONG $0x245c894c; BYTE $0x68 // mov qword [rsp + 104], r11 + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0x00cc8149; WORD $0x0003; BYTE $0x00 // or r12, 768 - LONG $0x2464894c; BYTE $0x70 // mov qword [rsp + 112], r12 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - LONG $0x20c88149; WORD $0x0003; BYTE $0x00 // or r8, 800 - LONG $0x2444894c; BYTE $0x30 // mov qword [rsp + 48], r8 + LONG $0x20cc8149; WORD $0x0002; BYTE $0x00 // or r12, 544 + QUAD $0x000000e024a4894c // mov qword [rsp + 224], r12 WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x40cf8149; WORD $0x0003; BYTE $0x00 // or r15, 832 - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03600d48; WORD $0x0000 // or rax, 864 - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + LONG $0x40cf8149; WORD $0x0002; BYTE $0x00 // or r15, 576 + LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x60cb8149; WORD $0x0002; BYTE $0x00 // or r11, 608 + QUAD $0x000000d8249c894c // mov qword [rsp + 216], r11 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x80ca8149; WORD $0x0002; BYTE $0x00 // or r10, 640 + QUAD $0x000000c82494894c // mov qword [rsp + 200], r10 WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03800d48; WORD $0x0000 // or rax, 896 - WORD $0x8948; BYTE $0xc7 // mov rdi, rax + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0xc0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 704 + QUAD $0x000000c024b4894c // mov qword [rsp + 192], r14 WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03a00d48; WORD $0x0000 // or rax, 928 - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + LONG $0x02e00d48; WORD $0x0000 // or rax, 736 + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + WORD $0x8949; BYTE $0xdd // mov r13, rbx + LONG $0x00cd8149; WORD $0x0003; BYTE $0x00 // or r13, 768 + LONG $0x246c894c; BYTE $0x28 // mov qword [rsp + 40], r13 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03200d48; WORD $0x0000 // or rax, 800 + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + LONG $0x40c98149; WORD $0x0003; BYTE $0x00 // or r9, 832 + QUAD $0x000000d0248c894c // mov qword [rsp + 208], r9 + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x60c98148; WORD $0x0003; BYTE $0x00 // or rcx, 864 + QUAD $0x000000b8248c8948 // mov qword [rsp + 184], rcx + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 + QUAD $0x000000b02484894c // mov qword [rsp + 176], r8 + WORD $0x8948; BYTE $0xde // mov rsi, rbx + LONG $0xa0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 928 + QUAD $0x0000010024b48948 // mov qword [rsp + 256], rsi WORD $0x8948; BYTE $0xd8 // mov rax, rbx + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x000000f8249c8948 // mov qword [rsp + 248], rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - LONG $0xe0cb8148; WORD $0x0003; BYTE $0x00 // or rbx, 992 - LONG $0x207923c4; WORD $0x320c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdx + r14], 1 - LONG $0x2031e3c4; WORD $0x0a04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdx + rcx], 2 - LONG $0x2079a3c4; WORD $0x2a04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdx + r13], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - LONG $0x2079e3c4; WORD $0x0a04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdx + rcx], 4 - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdx + r10], 5 - LONG $0x2079a3c4; WORD $0x0a04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdx + r9], 6 - LONG $0x2079a3c4; WORD $0x1a04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdx + r11], 7 - LONG $0x2079a3c4; WORD $0x2204; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdx + r12], 8 - LONG $0x2079a3c4; WORD $0x0204; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdx + r8], 9 - LONG $0x2079a3c4; WORD $0x3a04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdx + r15], 10 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdx + r10], 11 - LONG $0x2079e3c4; WORD $0x3a04; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdx + rdi], 12 - LONG $0x2079e3c4; WORD $0x3204; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdx + rsi], 13 - LONG $0x2079e3c4; WORD $0x0204; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdx + rax], 14 - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdx + rbx], 15 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x000000b0249c8948 // mov qword [rsp + 176], rbx - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdx + r11], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdx + rax], 2 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + rax], 3 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r8], 4 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r9], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + rax], 6 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + rsi], 7 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + r15], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + rdi], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + rax], 10 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + rbx], 11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + rbx], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rbx], 13 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rbx], 14 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + r14], 15 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x01011a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 1], 1 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x02011a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 1], 2 - QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] - QUAD $0x03012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 3 - QUAD $0x04010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 4 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x05010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 5 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x06010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x08010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 8 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x09010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 9 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0a010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 10 - QUAD $0x0b0112642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 1], 11 + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + LONG $0xe0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 992 + QUAD $0x0000010824948948 // mov qword [rsp + 264], rdx + LONG $0x207923c4; WORD $0x270c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r12], 1 + LONG $0x2031a3c4; WORD $0x3f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + r15], 2 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + r11], 3 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r10], 4 LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0c011a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 1], 12 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x0d0112642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 1], 13 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0e010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 14 - QUAD $0x0f0122642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 1], 15 - QUAD $0x01011a6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r11 + 1], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x02010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 2 + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r14], 6 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 7 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r13], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 9 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r9], 10 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + rcx], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rsi], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rdx], 15 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r14], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 2 QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0301226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 1], 3 - QUAD $0x0401026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 1], 4 - QUAD $0x05010a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 1], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 6 - QUAD $0x0701326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 1], 7 - QUAD $0x08013a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 1], 8 - QUAD $0x09013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 9 - WORD $0x8949; BYTE $0xfd // mov r13, rdi - QUAD $0x0a01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 11 + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r12], 3 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r8], 4 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r10], 5 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r9], 6 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r11], 7 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + r15], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rcx], 10 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rdx], 11 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rsi], 14 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rsi], 15 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x01012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x020137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 2 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x030137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 4 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x050137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 5 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x070137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 7 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x080137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 8 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x090137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 9 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0a0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 10 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0b0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 11 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0c0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 12 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0d0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 13 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0e0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 14 + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x0f0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 15 + QUAD $0x0101376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x02011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 2 + QUAD $0x0301276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 3 + QUAD $0x0401076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 4 + QUAD $0x0501176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 5 + QUAD $0x06010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 6 + QUAD $0x07011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 7 + QUAD $0x08013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + QUAD $0x0a010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 10 + QUAD $0x0b01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 14 + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 - QUAD $0x0f0132442051a3c4 // vpinsrb xmm0, xmm5, byte [rdx + r14 + 1], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 - QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi + QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xd06e79c5 // vmovd xmm10, eax QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x01023a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 2], 1 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x010207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 2 + QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040237442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 2], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x05021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 5 + QUAD $0x06022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 6 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x07021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 7 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x08020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 8 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + QUAD $0x090207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 10 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 2 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x030202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x040202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 4 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x050202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 5 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x060202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 2], 6 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x07020a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 2], 7 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x08021a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 2], 8 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x090202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 9 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0a0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 11 - QUAD $0x0c021a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 2], 12 - QUAD $0x0d0212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 2], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 14 + QUAD $0x0b0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 11 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0f0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 15 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + QUAD $0x0c0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 12 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0d0227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 13 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x0e023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 2], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0202025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 2 - QUAD $0x0302225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 2], 3 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0402325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 2], 4 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0502225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 2], 5 - QUAD $0x06020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 6 - QUAD $0x0702325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 7 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x08023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 8 - WORD $0x894c; BYTE $0xe9 // mov rcx, r13 - QUAD $0x09022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 9 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0a02325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 10 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x0b022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0c021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0e021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 14 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0f022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 15 - QUAD $0x01033a642021a3c4 // vpinsrb xmm4, xmm11, byte [rdx + r15 + 3], 1 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x02031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 2 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - QUAD $0x03031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 3 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x04031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 4 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - QUAD $0x05031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 5 - QUAD $0x060302642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 3], 6 - QUAD $0x07030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 7 - QUAD $0x08031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 8 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x09030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 9 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0a031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 11 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0c031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 12 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x0d032a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 3], 13 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0e031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 14 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x0f031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 15 - QUAD $0x0103126c2039a3c4 // vpinsrb xmm5, xmm8, byte [rdx + r10 + 3], 1 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - QUAD $0x0203026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 2 + QUAD $0x0102375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 2], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0202075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 2 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0303026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 3 - QUAD $0x0403326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 3], 4 - QUAD $0x0503226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 3], 5 + QUAD $0x0302075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0402075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 4 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x0502375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 2], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0602075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0702075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0802075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 8 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0902175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 9 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0a02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 10 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0d022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 13 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0e02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 14 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0f02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 15 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x01032f642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r13 + 3], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x020317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + QUAD $0x05031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 5 + WORD $0x8949; BYTE $0xda // mov r10, rbx + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x06032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 6 + QUAD $0x07031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 7 + QUAD $0x08030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 8 + QUAD $0x090307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 9 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x0a030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 10 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0b031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 11 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0c0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 12 + QUAD $0x0d0327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 13 + QUAD $0x0e033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 14 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x0f0307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 15 + QUAD $0x01030f6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rcx + 3], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 2 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x03030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x04030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 4 + QUAD $0x0503376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 3], 5 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0603276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 3], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x07030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 7 + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0603026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 6 + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0703026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 7 - QUAD $0x08033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 8 - QUAD $0x09030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 9 - QUAD $0x0a03326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 12 + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 13 + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e0302442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 3], 14 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x09 // movzx edi, byte [rdx + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0302442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 3], 15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f0307442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x09 // movzx edi, byte [rdx + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - QUAD $0x01043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 1 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x02043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 2 - QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] - QUAD $0x030422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x040432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 4], 4 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x050402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x010437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x030407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x040407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 4 + QUAD $0x050417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 5 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x06042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 6 + QUAD $0x07041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 9 + QUAD $0x0a040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 10 + QUAD $0x0b041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 11 + QUAD $0x0c0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 13 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x0e042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 14 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + QUAD $0x0f0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 15 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x0104375c2001a3c4 // vpinsrb xmm3, xmm15, byte [rdi + r14 + 4], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] + QUAD $0x03040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 3 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0404075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 4 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x0504175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 5 + QUAD $0x0604275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x08041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 8 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x0904275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 9 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x0a041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 10 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0b041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 11 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x0c041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 12 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0d041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 13 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0e041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 14 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0f041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 15 + QUAD $0x010537642009e3c4 // vpinsrb xmm4, xmm14, byte [rdi + rsi + 5], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x020537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 2 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x030537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 4 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x050537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 5 + QUAD $0x06053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 6 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x070537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 7 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x08053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 8 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x090537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 9 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0a0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 10 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0b0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 11 + QUAD $0x0c0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 12 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0d0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 13 + QUAD $0x0e052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 14 + QUAD $0x0f050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 15 + QUAD $0x0105376c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r14 + 5], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 2 + QUAD $0x03050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 3 + QUAD $0x0405076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 4 + QUAD $0x0505176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 5 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0605176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 6 + QUAD $0x0705076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 7 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x08051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 8 + QUAD $0x0905276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 5], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 + QUAD $0x0f051f442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rbx + 5], 15 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x060402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 6 + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x01060f442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rcx + 6], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x020617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 2 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x030637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 3 + QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] + QUAD $0x04061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 5 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x06060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 6 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 7 - QUAD $0x08041a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 4], 8 - QUAD $0x09040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 9 + QUAD $0x070607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 7 + QUAD $0x08063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 9 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x0a063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 10 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0b061f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 6], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 12 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0d0627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 13 + QUAD $0x0e062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0106076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 6], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0206076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0306076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0406076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0a0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 10 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x0b040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 11 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 12 - QUAD $0x0d042a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 4], 13 + QUAD $0x0506076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 5 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x0606176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 6 + QUAD $0x0706376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 7 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0806376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 8 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x0906176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 10 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0b06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 11 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0c06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0d06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 13 + QUAD $0x0e06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 14 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0f06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 15 + QUAD $0x01070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 1 + QUAD $0x020717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 2 + QUAD $0x030737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 3 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + QUAD $0x04071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 4 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x05070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 5 + QUAD $0x06070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 6 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x07070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 7 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x08070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 8 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + QUAD $0x0a073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 10 + QUAD $0x0b071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 11 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x0c070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 12 + QUAD $0x0d0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 13 + QUAD $0x0e072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 14 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x0f070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 15 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x01071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 2 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x0307274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x04070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 4 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x0907174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 12 + QUAD $0x0d07374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 13 + LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 + QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 14 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x0f0412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 4], 15 - QUAD $0x01041a5c2001e3c4 // vpinsrb xmm3, xmm15, byte [rdx + rbx + 4], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x02043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 2 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x03042a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 4], 3 - QUAD $0x0404325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 4], 4 + QUAD $0x0e0707442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 7], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0f072f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 7], 15 + LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 + QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x010837442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r14 + 8], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x020817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 2 + QUAD $0x030807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x040807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x05081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 6 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x070807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 8 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x09083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 11 + QUAD $0x0c080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 15 + QUAD $0x01081f6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r11 + 8], 1 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0208376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 2 + QUAD $0x0308276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 3 + QUAD $0x04080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0508076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 5 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x06080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x07080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 7 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x08080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x09080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 9 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0a081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 10 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0b080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 11 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x0c08176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 8], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 13 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0e08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 14 + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010937742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r14 + 9], 1 + QUAD $0x020917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 2 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x030937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 3 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x040917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 4 + QUAD $0x05091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x060917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 6 + QUAD $0x070907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 7 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x080917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 8 + QUAD $0x09093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 9 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0a091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 10 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0b0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 11 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0c0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 12 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x0d0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 13 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0e0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 14 + QUAD $0x0f090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 15 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0109177c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rdx + 9], 1 + QUAD $0x0209377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 2 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0309177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 3 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0409177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 4 + QUAD $0x0509077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0609077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0709077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0809077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + QUAD $0x0a091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 10 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0b091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 11 + QUAD $0x0c09177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 9], 12 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + QUAD $0x0d090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 13 + QUAD $0x0e09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 14 + LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 + QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 + QUAD $0x00044024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm5 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x010a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 2 + QUAD $0x030a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 3 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x040a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 4 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x050a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 5 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x060a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 9 + QUAD $0x0a0a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 10 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0b0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 11 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0c0a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 13 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x0e0a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 14 + QUAD $0x0f0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 15 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x010a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 1 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x020a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x050a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 5 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x060a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x070a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 7 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x080a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x090a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 9 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x0a0a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 10 + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + QUAD $0x0b0a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 11 + QUAD $0x0c0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 12 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x0d0a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 13 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x0e0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 14 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x0f0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 15 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x010b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 1 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x020b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 2 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x030b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 3 + QUAD $0x040b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 4 + QUAD $0x050b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 5 + QUAD $0x060b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 6 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x070b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 7 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x080b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x090b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 9 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0a0b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 10 + QUAD $0x0b0b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 11 + QUAD $0x0c0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 12 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x0d0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 13 + QUAD $0x0e0b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 14 + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x0f0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 15 + QUAD $0x010b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 1 + QUAD $0x020b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 2 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + QUAD $0x040b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 4 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x050b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x060b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 10 + QUAD $0x0b0b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 11], 11 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x0c0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 12 + QUAD $0x0d0b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 13 + LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 + QUAD $0x000420249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm3 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0f0b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 15 + LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 + QUAD $0x000400248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm1 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x010c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x020c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 2 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x030c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 3 + QUAD $0x040c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 6 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x070c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 7 + QUAD $0x080c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 8 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0504025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 6 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x07043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 7 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0804025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 8 - QUAD $0x09040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 10 + QUAD $0x090c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 9 + QUAD $0x0a0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 12 + QUAD $0x0d0c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 12], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f0c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 15 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x010c1f542051a3c4 // vpinsrb xmm2, xmm5, byte [rdi + r11 + 12], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x020c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x040c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 4 + QUAD $0x050c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 5 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x060c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x070c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 7 LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0b040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 15 + QUAD $0x080c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x090c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 9 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0a0c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 10 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0b0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 11 + QUAD $0x0c0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 13 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0e0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 14 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0f0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 15 + QUAD $0x010d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 1 + QUAD $0x020d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 2 + QUAD $0x030d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 3 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x040d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 4 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x050d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 5 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x060d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 6 + QUAD $0x070d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 7 + QUAD $0x080d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 8 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x090d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 9 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0a0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 10 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0b0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 11 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x0d0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 13 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0e0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 14 + QUAD $0x0f0d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 15 + QUAD $0x010d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x020d1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 13], 2 + QUAD $0x030d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x010502642009e3c4 // vpinsrb xmm4, xmm14, byte [rdx + rax + 5], 1 - QUAD $0x02053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 2 - QUAD $0x030522642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 5], 3 - QUAD $0x040532642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 5], 4 - QUAD $0x050502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x060502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 6 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x07053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 7 - QUAD $0x08051a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 5], 8 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x090502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 9 + QUAD $0x040d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0a0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 10 - QUAD $0x0b050a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 5], 11 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0c051a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 5], 12 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0d0532642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 5], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 14 - QUAD $0x0f0512642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 5], 15 - QUAD $0x01051a6c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdx + rbx + 5], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0205026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 2 - QUAD $0x03052a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 5], 3 - QUAD $0x0405326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 5], 4 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0505026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 5 + QUAD $0x050d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 5 + QUAD $0x060d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 6 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + QUAD $0x070d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 7 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x080d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 8 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0605026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 6 - QUAD $0x07053a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 5], 7 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0805326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 5], 8 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x0905226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 5], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 10 - QUAD $0x0b050a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 5], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 12 + QUAD $0x090d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 9 + QUAD $0x0a0d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 14 - LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0502442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 5], 15 + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x0c0d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 14 + LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 + QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f0d07442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x0e2f // movzx eax, byte [rdi + r13 + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 + QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x0e3f // movzx eax, byte [rdi + r15 + 14] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x010e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 2 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + QUAD $0x040e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 8 + QUAD $0x090e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 9 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0a0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 10 + QUAD $0x0b0e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 11 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0c0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 12 + QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] + QUAD $0x0d0e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 15 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x020e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x030e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x010602442019e3c4 // vpinsrb xmm0, xmm12, byte [rdx + rax + 6], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 2 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - QUAD $0x03061a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 6], 3 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x040602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 4 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x050612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 6], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x060602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 6 - QUAD $0x07063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 8 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x09063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 9 + QUAD $0x040e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0a0602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 10 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0b060a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 6], 11 - QUAD $0x0c061a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 6], 12 - QUAD $0x0d0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 13 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0e0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 14 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x0f062a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 6], 15 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - QUAD $0x01061a6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdx + r11 + 6], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x02060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 2 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x03060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 3 - QUAD $0x04060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x05060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06063a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 6], 6 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x07060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 7 - QUAD $0x0806326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 6], 8 - QUAD $0x0906226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 9 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0a060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 10 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x0b06326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 6], 11 - LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] - QUAD $0x0c060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 13 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0e060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 14 - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0f06226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 15 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x01070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 1 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x02070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 2 - QUAD $0x03071a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 7], 3 - QUAD $0x040702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 4 - QUAD $0x050712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 7], 5 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x060702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 7 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x080712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 7], 8 - QUAD $0x09073a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 7], 9 - QUAD $0x0a0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 10 + QUAD $0x050e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 5 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x060e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 6 + QUAD $0x070e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 7 + QUAD $0x080e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x090e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 11 + QUAD $0x0c0e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 12 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x0d0e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 14 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 11 + QUAD $0x0f0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 15 + LONG $0x44b60f42; WORD $0x0f2f // movzx eax, byte [rdi + r13 + 15] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x010f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x020f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x030f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 3 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x040f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 15], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 12 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0d071a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 7], 13 - QUAD $0x0e0732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 14 - QUAD $0x0f072a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 7], 15 - QUAD $0x01071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 1 - WORD $0x894d; BYTE $0xdd // mov r13, r11 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x0207324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 2 + QUAD $0x050f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x070f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x090f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 9 + QUAD $0x0a0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 11 + QUAD $0x0c0f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 12 + QUAD $0x0d0f1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 15], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 14 + QUAD $0x0f0f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 15 + LONG $0x44b60f42; WORD $0x0f3f // movzx eax, byte [rdi + r15 + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x010f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 1 + QUAD $0x020f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 2 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0307024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 3 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x04070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 4 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0507224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 7], 5 - QUAD $0x06073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 6 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x07073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 7 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x08071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 8 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x09070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 9 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0a070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 10 - QUAD $0x0b07324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 7], 11 - QUAD $0x0c070a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 7], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 13 - LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 - QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e073a442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rdi + 7], 14 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - LONG $0x0a7cb60f; BYTE $0x0b // movzx edi, byte [rdx + rcx + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f070a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 7], 15 - LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a7cb60f; BYTE $0x0b // movzx edi, byte [rdx + rcx + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x01083a442031e3c4 // vpinsrb xmm0, xmm9, byte [rdx + rdi + 8], 1 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x02083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 2 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x03083a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 8], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x04080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 4 - QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] - QUAD $0x05080a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 8], 5 - QUAD $0x060802442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 8], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 7 - QUAD $0x080812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 8 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x09080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 9 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0a080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 10 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x0b0812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 11 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0c080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 12 - QUAD $0x0d081a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 8], 13 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0e080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 14 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0f080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 15 - QUAD $0x01082a6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r13 + 8], 1 - WORD $0x8949; BYTE $0xf6 // mov r14, rsi - QUAD $0x0208326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 2 - QUAD $0x0308026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 3 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x04080a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 8], 4 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x0508226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 8], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0608326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 6 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x0708226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 8], 7 - QUAD $0x08081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 8 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0908026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 9 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0a081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 10 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0b081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0c081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 13 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0e081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 14 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 15 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x01091a742039e3c4 // vpinsrb xmm6, xmm8, byte [rdx + rbx + 9], 1 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x02091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 2 - QUAD $0x03093a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 9], 3 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x04091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 4 - QUAD $0x05090a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 9], 5 - QUAD $0x060902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 6 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x07093a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 9], 7 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x08091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 8 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x09091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 9 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0a091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 10 - QUAD $0x0b0912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 11 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0c091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 12 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x0d0902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 13 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0e091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 14 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x0f091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 15 - QUAD $0x01092a7c2021a3c4 // vpinsrb xmm7, xmm11, byte [rdx + r13 + 9], 1 - QUAD $0x0209327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 9], 2 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x03091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 3 - QUAD $0x04090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 4 - QUAD $0x05093a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rdi + 9], 5 - QUAD $0x0609327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 9], 6 - WORD $0x8949; BYTE $0xf6 // mov r14, rsi - QUAD $0x0709227c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r12 + 9], 7 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x08090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 8 - QUAD $0x0909027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 9 - QUAD $0x0a091a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 9], 10 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x0b091a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 9], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 12 + QUAD $0x030f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x050f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 5 + QUAD $0x060f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x070f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 7 + QUAD $0x080f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 8 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x090f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 9 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x0a0f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 13 + QUAD $0x0b0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0d0f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 13 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0e0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 14 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x0f0f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 15 + LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 + QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 + LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 + QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x011017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x03100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 3 + QUAD $0x041007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 4 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x051007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 6 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x071027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 7 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 14 - LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 - QUAD $0x00048024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f09026c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdx + rax + 9], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 - QUAD $0x00046024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm5 + QUAD $0x081007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 8 + QUAD $0x09101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 10 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + QUAD $0x0b103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 12 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x010a2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 10], 1 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x020a225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 10], 2 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x030a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 3 + QUAD $0x0d1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 13 QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x040a125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 10], 4 - QUAD $0x050a0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 10], 5 - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - QUAD $0x060a0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 10], 6 - QUAD $0x070a3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 10], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 8 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x090a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 9 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0a0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 11 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 12 - QUAD $0x0d0a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 14 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0f0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x010a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x020a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 2 - QUAD $0x030a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x040a3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 10], 4 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x050a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 5 - QUAD $0x060a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 6 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x070a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 7 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x080a02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 10], 8 + QUAD $0x0e1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 14 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x090a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 10 - QUAD $0x0b0a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 12 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - QUAD $0x0d0a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 13 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0e0a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 15 - QUAD $0x010b2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 11], 1 - QUAD $0x020b224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 11], 2 + QUAD $0x0f1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x030b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 3 - QUAD $0x040b124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 11], 4 - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x050b224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 11], 5 - QUAD $0x060b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 8 + QUAD $0x0110074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 1 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x090b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 9 - QUAD $0x0a0b324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 11], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 11 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 13 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0e0b2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 11], 14 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0f0b324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 11], 15 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x010b0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 11], 1 - QUAD $0x020b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 2 + QUAD $0x0210074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 2 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x030b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 3 - QUAD $0x040b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 11], 4 - QUAD $0x050b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x060b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 6 - QUAD $0x070b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 7 - QUAD $0x080b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 11], 8 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x090b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 10 + QUAD $0x0310074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + QUAD $0x05101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0610074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0710074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 11 + QUAD $0x0810074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 8 + QUAD $0x0910374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 9 + QUAD $0x0a102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 10 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0b10374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 12 - QUAD $0x0d0b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 11], 13 - LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 - QUAD $0x000440249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm3 - QUAD $0x0e0b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 11], 14 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x0d // movzx edi, byte [rdx + rax + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 15 - LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 - QUAD $0x000420248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm1 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0d // movzx edi, byte [rdx + rax + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x010c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 1 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x020c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 12], 2 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x030c3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 12], 3 - QUAD $0x040c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 12], 4 - QUAD $0x050c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 12], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x060c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x080c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 8 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x090c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 9 + QUAD $0x0d10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 13 + QUAD $0x0e10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 14 + QUAD $0x0f100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 15 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x110f // movzx eax, byte [rdi + r9 + 17] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 1 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x02111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 2 + QUAD $0x03110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 3 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + QUAD $0x051107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 6 + QUAD $0x071127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 7 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x081117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 8 + QUAD $0x09111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 10 + QUAD $0x0b113f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 17], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0d1127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 13 + QUAD $0x0e1117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 14 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x0f112f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 17], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x11 // movzx eax, byte [rdi + rax + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0111075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 1 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0211075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 2 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0311375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0411075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0a0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 10 + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0611075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 6 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0711175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + QUAD $0x0b11375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 11 + QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] + QUAD $0x0c11375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 11 + QUAD $0x0f1107442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 17], 15 + LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 + QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 + LONG $0x44b60f42; WORD $0x120f // movzx eax, byte [rdi + r9 + 18] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 + QUAD $0x02121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 2 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x03123f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 18], 3 + QUAD $0x04120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 13 - QUAD $0x0e0c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 12], 14 - QUAD $0x0f0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 15 - QUAD $0x010c0a542051a3c4 // vpinsrb xmm2, xmm5, byte [rdx + r9 + 12], 1 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x020c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 2 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x030c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 3 + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x040c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 4 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x050c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 5 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x060c0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 12], 6 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x070c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 7 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x080c1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 12], 8 - QUAD $0x090c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 10 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0b0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0c0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 13 - QUAD $0x0e0c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 12], 14 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 15 - QUAD $0x010d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 1 - QUAD $0x020d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 2 - QUAD $0x030d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 13], 3 - QUAD $0x040d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 13], 4 - QUAD $0x050d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 5 - WORD $0x894d; BYTE $0xe2 // mov r10, r12 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x060d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 6 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x070d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 7 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x080d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 8 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x090d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 9 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0a0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 11 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x0c0d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 13], 12 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0d0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 13 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0e0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 14 - QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] - QUAD $0x0f0d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 15 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x010d1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 13], 1 - QUAD $0x020d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 2 - QUAD $0x030d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 3 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x040d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 4 - QUAD $0x050d2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 13], 5 - QUAD $0x060d0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 13], 6 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x070d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 7 - QUAD $0x080d1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 13], 8 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x090d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 9 - QUAD $0x0a0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 13 - QUAD $0x0e0d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 14 - LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 - QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0d02442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rax + 13], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x0e // movzx edi, byte [rdx + rax + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 - QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0e // movzx edi, byte [rdx + rax + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x010e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 1 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x020e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 14], 2 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x030e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 3 + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 7 + QUAD $0x081217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 8 + QUAD $0x09121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 12 + QUAD $0x0d1227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 13 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x040e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 4 - QUAD $0x050e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 5 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x060e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 6 - QUAD $0x070e024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 14], 7 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x080e1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 14], 8 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x090e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 9 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0a0e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 10 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0b0e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 14], 11 - QUAD $0x0c0e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 12 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x0d0e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 13 + QUAD $0x0e1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 14 + QUAD $0x0f122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x0112274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 1 + QUAD $0x0212074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 2 + QUAD $0x0312374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0412074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0512074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 5 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0612374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 6 + QUAD $0x0712174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 7 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x08120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 8 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x09122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 9 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0a12074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 10 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0b121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 11 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x0c12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 12 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0d121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 13 LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0e0e324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 14], 14 - QUAD $0x0f0e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 14], 15 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x010e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x020e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 2 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x030e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x040e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x050e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x060e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 6 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x070e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 7 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x080e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 8 - QUAD $0x090e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 9 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0a0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 10 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0b0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 11 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0c0e22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 14], 12 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e0e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f0e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 15 - QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] - LONG $0x7cb60f42; WORD $0x0f02 // movzx edi, byte [rdx + r8 + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x010f3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 15], 1 - QUAD $0x020f0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 15], 2 - QUAD $0x030f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x040f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 4 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x050f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 5 - QUAD $0x060f2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 15], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x070f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 7 - QUAD $0x080f1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 15], 8 - QUAD $0x090f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 9 - QUAD $0x0a0f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 15], 10 - QUAD $0x0b0f1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 15], 11 + QUAD $0x0e12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 14 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0f12174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 2 + QUAD $0x03133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 12 - QUAD $0x0d0f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 15], 13 - QUAD $0x0e0f32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 15], 14 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x0f0f0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 15], 15 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1a7cb60f; BYTE $0x0f // movzx edi, byte [rdx + rbx + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - QUAD $0x010f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x020f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 2 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x030f125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 15], 3 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x040f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x050f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x060f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 6 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x070f325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 15], 7 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x080f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x090f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 9 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0a0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 11 - QUAD $0x0c0f225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 15], 12 - QUAD $0x0d0f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 13 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0e0f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 14 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - QUAD $0x0f0f3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 15], 15 - LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 - QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 - QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - LONG $0x7cb60f42; WORD $0x1002 // movzx edi, byte [rdx + r8 + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x011032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 1 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x021032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 2 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x031032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x041032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 4 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x051032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 5 - QUAD $0x06102a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 16], 6 - WORD $0x894d; BYTE $0xec // mov r12, r13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x071032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 7 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x081032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 8 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x091032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 9 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0a1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 10 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0b1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 11 - QUAD $0x0c1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 13 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0e1002442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 16], 14 - QUAD $0x0f100a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 16], 15 - LONG $0x1a7cb60f; BYTE $0x10 // movzx edi, byte [rdx + rbx + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x01101a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 16], 1 - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x02100a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 16], 2 - QUAD $0x0310124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 16], 3 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0410024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 4 + QUAD $0x051307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 5 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x06133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 6 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + QUAD $0x071317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 8 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0510024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 5 - QUAD $0x06100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 6 - QUAD $0x0710324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 16], 7 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0810324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 8 + QUAD $0x091307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 14 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0910024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 9 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x0a102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 13 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0e10324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 16], 14 - QUAD $0x0f103a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 16], 15 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - LONG $0x3a7cb60f; BYTE $0x11 // movzx edi, byte [rdx + rdi + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x01113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 1 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x02110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 2 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x03113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 4 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x051112542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 17], 5 - QUAD $0x061122542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 17], 6 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x071122542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 17], 7 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x08113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 8 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x09113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 9 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0a111a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 17], 10 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 11 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0c113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 12 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x0d111a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 17], 13 - QUAD $0x0e1102542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 17], 14 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0f113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a7cb60f; BYTE $0x11 // movzx edi, byte [rdx + rdi + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x01113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 1 - QUAD $0x02110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 2 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x03113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 5 - QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x06113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 6 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0711025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 17], 7 - QUAD $0x0811325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 8 - QUAD $0x0911025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 9 - QUAD $0x0a112a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 17], 10 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x0b110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 11 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0c11325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 13 - QUAD $0x0e11325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 17], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 + QUAD $0x0f1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0113275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0313075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0413075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x0613375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1102442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rax + 17], 15 - LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x12 // movzx edi, byte [rdx + rax + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x08130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 8 + QUAD $0x09132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 9 + QUAD $0x0a13075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 10 + QUAD $0x0b131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 11 + QUAD $0x0c130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 12 + QUAD $0x0d131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 13 + QUAD $0x0e13375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 14 + QUAD $0x0f13175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 19], 15 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 + LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 + QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x140f // movzx eax, byte [rdi + r9 + 20] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x011427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x03141f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 20], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x06143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 6 + QUAD $0x071417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 9 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0a1437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 10 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0b1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 11 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x0c143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 12 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x0d140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 13 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0e141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 14 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x0f1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 15 + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x142f // movzx eax, byte [rdi + r13 + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0114374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x011202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 1 - QUAD $0x02120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 2 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x03120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 3 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x04122a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 18], 4 - QUAD $0x051212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 5 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x06120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 6 - QUAD $0x071222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 18], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x08120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 8 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x091212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 9 - QUAD $0x0a121a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 18], 10 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 11 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0c123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 12 - QUAD $0x0d121a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 18], 13 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0e123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 14 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0f123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 15 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x121a // movzx edi, byte [rdx + r11 + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x01123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 1 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0212324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 18], 2 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0312224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 18], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 5 - QUAD $0x06123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 6 - QUAD $0x0712024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 7 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x08123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x09123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 9 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0a123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 10 - QUAD $0x0b120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 11 - QUAD $0x0c12324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 12 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - QUAD $0x0d120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 14 - QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] - QUAD $0x0f12024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 15 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - LONG $0x3a7cb60f; BYTE $0x13 // movzx edi, byte [rdx + rdi + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x021302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 2 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x03133a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 19], 3 - QUAD $0x04132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 4 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x051302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x061302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x071302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 7 - QUAD $0x08130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 8 - QUAD $0x091312542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 19], 9 - QUAD $0x0a131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 11 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0c132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 12 + QUAD $0x0414074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0514074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0614074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0714074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0814074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0914074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 11 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 13 + QUAD $0x0c14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 13 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 14 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0f1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 15 - LONG $0x7cb60f42; WORD $0x131a // movzx edi, byte [rdx + r11 + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x01130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 1 - QUAD $0x0213325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 19], 2 - QUAD $0x0313225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 19], 3 + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 15 + LONG $0x44b60f42; WORD $0x150f // movzx eax, byte [rdi + r9 + 21] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 1 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x021517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 2 + QUAD $0x03151f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 21], 3 + QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] + QUAD $0x041527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 5 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0413025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 4 + QUAD $0x061507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 8 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0513025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 5 - QUAD $0x06133a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 19], 6 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0713025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 7 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x08130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 8 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0913025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 9 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0a13125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 19], 10 + QUAD $0x091507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 9 + QUAD $0x0a1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 10 + QUAD $0x0b1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 11 + QUAD $0x0c153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 12 + QUAD $0x0d150f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 21], 13 + QUAD $0x0e151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 14 + QUAD $0x0f1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 15 + LONG $0x44b60f42; WORD $0x152f // movzx eax, byte [rdi + r13 + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0115375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x04153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 4 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x05151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x07152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 11 - QUAD $0x0c13325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 12 - QUAD $0x0d130a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 19], 13 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0e130a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 19], 14 - QUAD $0x0f13025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 19], 15 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 - QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x14 // movzx edi, byte [rdx + rax + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x011432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 1 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x02141a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 20], 2 - QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] - QUAD $0x031422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 20], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x041432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 4 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x051402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 20], 5 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x06143a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 20], 6 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x071432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 7 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x081432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 8 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x091432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 9 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0a1432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 10 - QUAD $0x0b141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 11 - QUAD $0x0c142a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 20], 12 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x0d1432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 20], 13 + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] + QUAD $0x0a150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 13 LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0e1432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 14 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0f1432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a7cb60f; BYTE $0x14 // movzx edi, byte [rdx + rdi + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x01143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x02143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 2 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x03141a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 20], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 6 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x07143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 7 - QUAD $0x08140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 8 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x09140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 9 - QUAD $0x0a14124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 10 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0b140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 11 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0c140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 13 - QUAD $0x0e140a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 20], 14 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x0f140a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 20], 15 - LONG $0x027cb60f; BYTE $0x15 // movzx edi, byte [rdx + rax + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x011502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 1 - QUAD $0x02151a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 21], 2 - QUAD $0x031522542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 21], 3 - WORD $0x894d; BYTE $0xe5 // mov r13, r12 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x041502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 4 - QUAD $0x051502542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 21], 5 - QUAD $0x06153a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 21], 6 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x071502542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 21], 7 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x08153a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 21], 8 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x091502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 9 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0a1522542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 21], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 11 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 12 - QUAD $0x0d1532542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 21], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 14 - QUAD $0x0f1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 15 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x151a // movzx edi, byte [rdx + r11 + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x0115325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 21], 1 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x0215125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 2 - QUAD $0x03151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 3 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x04151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x05150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0615325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 6 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x0715325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 7 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0815325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 8 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0915325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 9 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0a153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 14 + QUAD $0x0e15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x0f150a442061a3c4 // vpinsrb xmm0, xmm3, byte [rdx + r9 + 21], 15 + QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x0f151f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r11 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - LONG $0x3a7cb60f; BYTE $0x16 // movzx edi, byte [rdx + rdi + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x01163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 1 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x02163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 2 - QUAD $0x03162a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 22], 3 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x04160a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 22], 4 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x05163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 6 - QUAD $0x071602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 22], 7 - QUAD $0x08163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 8 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x09163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 9 - QUAD $0x0a1622442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 22], 10 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 11 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0c163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 13 - QUAD $0x0e1602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 22], 14 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0f163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 15 - LONG $0x7cb60f42; WORD $0x161a // movzx edi, byte [rdx + r11 + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0116324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 22], 1 - QUAD $0x0216124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 22], 2 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0316024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 3 - QUAD $0x04161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 4 - QUAD $0x05160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 5 - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - QUAD $0x0616224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 22], 6 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x07161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 7 - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - QUAD $0x0816124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 22], 8 - QUAD $0x0916324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 10 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x0b16024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 22], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 15 + QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 1 + QUAD $0x021617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 2 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x17 // movzx edi, byte [rdx + rax + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x011702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 1 + QUAD $0x031607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 3 + QUAD $0x041627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 4 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x051617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 5 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x061617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 8 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x091627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 9 + QUAD $0x0a1637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 10 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x021702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 2 - WORD $0x894d; BYTE $0xee // mov r14, r13 - QUAD $0x03172a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 23], 3 - QUAD $0x04170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 4 - QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] - QUAD $0x05172a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 23], 5 - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x061732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 6 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x07170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 7 + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 14 + QUAD $0x0f1607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0116074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 1 + QUAD $0x02160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 2 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0316074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 3 + QUAD $0x04163f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 22], 4 + QUAD $0x05161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 5 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x081702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 8 + QUAD $0x0616074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 6 + QUAD $0x07162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 11 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x0c160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + QUAD $0x0e16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 14 + QUAD $0x0f161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x01171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 2 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x03173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 4 + QUAD $0x051717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 5 + QUAD $0x061717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 6 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x07172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 8 + QUAD $0x091727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 9 + QUAD $0x0a1737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 10 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x0b171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 11 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0c170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 12 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x0d1717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 13 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0e1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 14 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x0f1727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x0117375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 1 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x091702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 9 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0a170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 10 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0b170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 11 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0c170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 12 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x0d171a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 23], 13 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0e173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 14 - QUAD $0x0f173a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 23], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a7cb60f; BYTE $0x17 // movzx edi, byte [rdx + rdi + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x01173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x02173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 2 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x03173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x05173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 5 - QUAD $0x0617225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 23], 6 - QUAD $0x07171a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 23], 7 - QUAD $0x0817125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 23], 8 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x09171a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 23], 9 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0a173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 10 - QUAD $0x0b17025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 23], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 15 + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + QUAD $0x0317075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0417075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0517075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0617075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0717075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0817075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 11 + QUAD $0x0c170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 12 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x386563c4; WORD $0x01da // vinserti128 ymm11, ymm3, xmm2, 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - LONG $0x3a7cb60f; BYTE $0x18 // movzx edi, byte [rdx + rdi + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x01183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 1 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x02183a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 24], 2 - QUAD $0x031832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 4 - QUAD $0x05182a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 24], 5 - QUAD $0x061832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 6 - QUAD $0x07180a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 24], 7 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x081832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 8 - QUAD $0x091802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 9 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x01181f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 24], 1 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x02180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 2 + QUAD $0x03183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 3 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x041807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 6 + QUAD $0x07182f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 24], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 8 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x09183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 10 + QUAD $0x0b181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 11 + QUAD $0x0c180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 12 + QUAD $0x0d1817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 13 + QUAD $0x0e1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 14 + QUAD $0x0f1827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0118374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x0318174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 3 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x04181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0a1802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 10 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0b1822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 24], 11 - QUAD $0x0c180a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 24], 12 - QUAD $0x0d181a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 24], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e1802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 14 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0f1802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 15 - QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x1832 // movzx edi, byte [rdx + r14 + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x01180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0218024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 2 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0318024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 3 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x04181a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 24], 4 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0518024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 5 + QUAD $0x0518074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0618074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0718074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 7 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x08180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 8 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0618024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 6 + QUAD $0x0918074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 9 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0718024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 7 - QUAD $0x0818124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 8 - WORD $0x8949; BYTE $0xda // mov r10, rbx - QUAD $0x09181a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 24], 9 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x0a182a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 24], 10 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0b180a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 24], 11 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0c18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 12 + QUAD $0x0a18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d18024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 13 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0e181a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 24], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f18024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x027cb60f; BYTE $0x19 // movzx edi, byte [rdx + rax + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x011902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 1 - QUAD $0x02193a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 25], 2 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x031902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 3 + QUAD $0x0b18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 11 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x0c181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 12 + QUAD $0x0d18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 13 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0e18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + QUAD $0x01192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 1 + QUAD $0x02190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 2 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x031927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 3 + QUAD $0x041907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 4 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x051907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 5 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x061937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 6 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x07190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + QUAD $0x09193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 11 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0c1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 12 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x0d1937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 13 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x041902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 4 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x05193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 7 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x08193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 8 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x09193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 9 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0a193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 10 - QUAD $0x0b1922542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 25], 11 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0c193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 13 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0e193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 14 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0f193a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 25], 15 - LONG $0x7cb60f42; WORD $0x1932 // movzx edi, byte [rdx + r14 + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 1 - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x02190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 2 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x03193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 3 - QUAD $0x04191a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 25], 4 - QUAD $0x0519025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 6 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x07193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 7 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x08193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 8 - QUAD $0x0919125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 25], 9 - QUAD $0x0a192a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 25], 10 - QUAD $0x0b190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 11 - QUAD $0x0c19325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 12 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0d192a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 25], 13 - QUAD $0x0e191a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 25], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f190a442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rcx + 25], 15 + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x0f193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + QUAD $0x0319175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 25], 3 + QUAD $0x04191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0519075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x08190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x09190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 11 + QUAD $0x0c191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 13 + QUAD $0x0e19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 14 + LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0f1917442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rdx + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - LONG $0x7cb60f42; WORD $0x1a1a // movzx edi, byte [rdx + r11 + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x011a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 1 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x021a02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 26], 2 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x031a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 3 - QUAD $0x041a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 4 - QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] - QUAD $0x051a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 5 + QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x061a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x071a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 7 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x081a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 8 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x091a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 9 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0a1a22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 26], 10 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0b1a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 11 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c1a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d1a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 13 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0e1a32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 26], 14 - QUAD $0x0f1a3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 26], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x1a // movzx edi, byte [rdx + rax + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x011a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 1 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x021a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 2 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x031a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x041a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x051a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x061a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 6 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x071a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 7 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x081a3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 26], 8 - QUAD $0x091a124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 26], 9 + LONG $0x0744b60f; BYTE $0x1a // movzx eax, byte [rdi + rax + 26] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 1 LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0a1a1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 26], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 12 - QUAD $0x0d1a2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 26], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 15 - LONG $0x7cb60f42; WORD $0x1b1a // movzx edi, byte [rdx + r11 + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x011b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 27], 1 - QUAD $0x021b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 27], 2 - QUAD $0x031b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x041b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 4 - QUAD $0x051b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 5 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x061b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 27], 6 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x071b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 27], 7 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x081b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 8 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x091b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 9 - QUAD $0x0a1b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 27], 10 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0b1b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 11 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0c1b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d1b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 13 - QUAD $0x0e1b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 27], 14 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0f1b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 27], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a7cb60f; BYTE $0x1b // movzx edi, byte [rdx + rdi + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x011b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 1 - QUAD $0x021b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 2 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x031b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 3 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x041b325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 27], 4 + QUAD $0x021a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 2 + QUAD $0x031a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 4 + QUAD $0x051a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 5 + QUAD $0x061a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 6 + QUAD $0x071a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 7 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x081a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 8 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x051b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x061b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 6 - QUAD $0x071b0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 27], 7 - QUAD $0x081b3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 27], 8 - QUAD $0x091b125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 27], 9 - QUAD $0x0a1b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 10 + QUAD $0x091a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 10 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0b1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 11 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x0c1a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 12 + QUAD $0x0d1a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 14 + QUAD $0x0f1a3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 26], 15 + QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x1a17 // movzx eax, byte [rdi + r10 + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x011a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 1 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x021a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x031a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 3 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x041a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 4 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x051a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x061a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 11 + QUAD $0x081a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 8 + QUAD $0x091a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a1a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 12 + QUAD $0x0d1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 13 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x0e1a2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 26], 14 + QUAD $0x0f1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1744b60f; BYTE $0x1b // movzx eax, byte [rdi + rdx + 27] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x011b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 1 + QUAD $0x021b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x031b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + QUAD $0x081b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 9 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x0a1b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 10 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0b1b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 11 + QUAD $0x0c1b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 12 + QUAD $0x0d1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f1b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 15 + LONG $0x44b60f42; WORD $0x1b17 // movzx eax, byte [rdi + r10 + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + QUAD $0x011b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 1 + QUAD $0x021b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x031b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 3 + QUAD $0x041b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 4 + QUAD $0x051b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x081b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x091b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 9 + QUAD $0x0a1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0e1b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f1b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 15 + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 13 + QUAD $0x0e1b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 + QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 - QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - LONG $0x7cb60f42; WORD $0x1c0a // movzx edi, byte [rdx + r9 + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 28], 1 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x021c3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 28], 2 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x031c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 28], 3 - QUAD $0x041c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 4 - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x051c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 28], 5 - QUAD $0x061c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 6 - QUAD $0x071c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 7 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x081c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 8 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x091c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 28], 9 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0a1c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 10 - QUAD $0x0b1c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 11 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0c1c1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 28], 12 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0d1c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 13 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0e1c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 14 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0f1c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 15 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - LONG $0x327cb60f; BYTE $0x1c // movzx edi, byte [rdx + rsi + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x011c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 1 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x021c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 2 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x031c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 3 - QUAD $0x041c324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 28], 4 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x051c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 5 + QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 + LONG $0x1744b60f; BYTE $0x1c // movzx eax, byte [rdi + rdx + 28] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 2 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x031c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 3 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x041c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 4 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x051c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x061c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 9 + QUAD $0x0a1c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 10 + QUAD $0x0b1c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 28], 11 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x0c1c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 12 + QUAD $0x0d1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 14 + QUAD $0x0f1c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 15 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + LONG $0x1744b60f; BYTE $0x1c // movzx eax, byte [rdi + rdx + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x031c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x041c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x051c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 5 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x061c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x081c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 8 QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x061c324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 28], 6 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x071c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 7 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x081c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x091c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 9 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0a1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 10 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x0b1c2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 28], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 12 - QUAD $0x0d1c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 13 + QUAD $0x091c374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 28], 9 + QUAD $0x0a1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 10 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0b1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 11 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x0c1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x1d // movzx eax, byte [rdi + rax + 29] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x011d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 2 + QUAD $0x031d0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 29], 3 + QUAD $0x041d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 4 + QUAD $0x051d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 5 + QUAD $0x061d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 7 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e1c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 15 - LONG $0x7cb60f42; WORD $0x1d0a // movzx edi, byte [rdx + r9 + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x011d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 1 - QUAD $0x021d3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 29], 2 - QUAD $0x031d1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 29], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x041d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 4 - QUAD $0x051d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 5 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x061d3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 29], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x071d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 7 - QUAD $0x081d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 8 - QUAD $0x091d12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 29], 9 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x0a1d1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 29], 10 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0b1d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 11 - QUAD $0x0c1d1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 29], 12 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0d1d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 13 - QUAD $0x0e1d0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 29], 14 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0f1d0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 29], 15 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1a7cb60f; BYTE $0x1d // movzx edi, byte [rdx + rbx + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x011d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 29], 1 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x021d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 29], 2 - QUAD $0x031d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 3 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x041d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x051d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 5 - QUAD $0x061d325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 29], 6 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x071d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 7 + QUAD $0x081d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 9 QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x081d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 8 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x091d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 9 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0a1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 10 - QUAD $0x0b1d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 11 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0c1d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 13 - QUAD $0x0e1d02642061e3c4 // vpinsrb xmm4, xmm3, byte [rdx + rax + 29], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1d02442059e3c4 // vpinsrb xmm0, xmm4, byte [rdx + rax + 29], 15 - LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - LONG $0x0a7cb60f; BYTE $0x1e // movzx edi, byte [rdx + rcx + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011e0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 30], 1 - LONG $0x0a7cb60f; BYTE $0x1f // movzx edi, byte [rdx + rcx + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 31], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x021e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 2 - QUAD $0x021f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 2 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x031e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 3 - QUAD $0x031f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 3 + QUAD $0x0a1d0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 29], 10 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0b1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 11 + QUAD $0x0c1d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 12 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + QUAD $0x0d1d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 13 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x041e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 4 - QUAD $0x041f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 4 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x051e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 5 - QUAD $0x051f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 5 - QUAD $0x061e3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 30], 6 - QUAD $0x061f3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 31], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x071e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 7 - QUAD $0x071f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 7 - QUAD $0x0000011024bc8b48 // mov rdi, qword [rsp + 272] - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x081e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 8 - QUAD $0x081f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 8 + QUAD $0x0e1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 14 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x0f1d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 15 + LONG $0x1744b60f; BYTE $0x1d // movzx eax, byte [rdi + rdx + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] + QUAD $0x011d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 1 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x091e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 9 - QUAD $0x091f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 9 - QUAD $0x0a1e1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 30], 10 - QUAD $0x0a1f1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 31], 10 - QUAD $0x0b1e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 30], 11 - QUAD $0x0b1f024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 31], 11 + QUAD $0x021d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 2 + QUAD $0x031d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 3 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x041d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 + QUAD $0x061d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x081d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 8 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + QUAD $0x091d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 29], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 10 + QUAD $0x0b1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 11 + QUAD $0x0c1d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0d1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 13 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x0e1d37642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r14 + 29], 14 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1d07442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rax + 29], 15 + LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 + QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + LONG $0x1f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rbx + 30] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 1 + LONG $0x1f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rbx + 31] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011f0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 31], 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0c1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 12 - QUAD $0x0c1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 12 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0d1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 13 - QUAD $0x0d1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 14 - QUAD $0x0e1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 14 + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x00000110249c8b48 // mov rbx, qword [rsp + 272] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + QUAD $0x0a1e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 30], 10 + QUAD $0x0a1f0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 31], 10 + QUAD $0x0b1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 11 + QUAD $0x0b1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 11 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0f1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 15 - QUAD $0x0f1f02542071e3c4 // vpinsrb xmm2, xmm1, byte [rdx + rax + 31], 15 - LONG $0x1a44b60f; BYTE $0x1e // movzx eax, byte [rdx + rbx + 30] + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 + QUAD $0x0d1e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 30], 13 + QUAD $0x0d1f3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 31], 13 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x0f1e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 30], 15 + QUAD $0x0f1f27542071a3c4 // vpinsrb xmm2, xmm1, byte [rdi + r12 + 31], 15 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x011e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 30], 1 - LONG $0x1a44b60f; BYTE $0x1f // movzx eax, byte [rdx + rbx + 31] + QUAD $0x011e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f227c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r12 + 31], 1 - QUAD $0x021e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 30], 2 - QUAD $0x021f127c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r10 + 31], 2 + QUAD $0x011f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 1 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x021e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 2 + QUAD $0x021f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 2 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x031e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 3 - QUAD $0x031f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 3 - QUAD $0x041e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 30], 4 - QUAD $0x041f327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 31], 4 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x051e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 5 - QUAD $0x051f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x061e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 6 - QUAD $0x061f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 6 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x071e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 7 - QUAD $0x071f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 7 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 8 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x091e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 9 - QUAD $0x091f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 10 + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x041e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 4 + QUAD $0x041f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 11 - QUAD $0x0b1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 11 - QUAD $0x0c1e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 30], 12 - QUAD $0x0c1f2a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 31], 12 + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 9 + QUAD $0x091f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 13 - QUAD $0x0d1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 15 - QUAD $0x0f1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 15 + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + QUAD $0x0d1e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 13 + QUAD $0x0d1f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 13 + QUAD $0x0e1e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 30], 14 + QUAD $0x0e1f377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 31], 14 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 QUAD $0x00020024946ffdc5; BYTE $0x00 // vmovdqa ymm2, yword [rsp + 512] LONG $0xc27495c5 // vpcmpeqb ymm0, ymm13, ymm2 - QUAD $0x0004c024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1216] + QUAD $0x0004a024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1184] LONG $0x6d6ffdc5; BYTE $0x00 // vmovdqa ymm5, yword 0[rbp] /* [rip + .LCPI5_0] */ LONG $0xfddfc5c5 // vpandn ymm7, ymm7, ymm5 LONG $0xc0fcc5c5 // vpaddb ymm0, ymm7, ymm0 @@ -34575,12 +35459,12 @@ LBB5_169: LONG $0xe3df1dc5 // vpandn ymm12, ymm12, ymm3 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0xe2740dc5 // vpcmpeqb ymm12, ymm14, ymm2 - LONG $0x456f7dc5; BYTE $0x60 // vmovdqa ymm8, yword 96[rbp] /* [rip + .LCPI5_3] */ - LONG $0xdf1d41c4; BYTE $0xe0 // vpandn ymm12, ymm12, ymm8 + LONG $0x656ffdc5; BYTE $0x60 // vmovdqa ymm4, yword 96[rbp] /* [rip + .LCPI5_3] */ + LONG $0xe4df1dc5 // vpandn ymm12, ymm12, ymm4 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0xc976f5c5 // vpcmpeqd ymm1, ymm1, ymm1 LONG $0xc1f8fdc5 // vpsubb ymm0, ymm0, ymm1 - LONG $0xe476ddc5 // vpcmpeqd ymm4, ymm4, ymm4 + LONG $0x763d41c4; BYTE $0xc0 // vpcmpeqd ymm8, ymm8, ymm8 LONG $0xc7ebfdc5 // vpor ymm0, ymm0, ymm7 LONG $0xfa7485c5 // vpcmpeqb ymm7, ymm15, ymm2 QUAD $0x000000808d6ffdc5 // vmovdqa ymm1, yword 128[rbp] /* [rip + .LCPI5_4] */ @@ -34589,73 +35473,75 @@ LBB5_169: QUAD $0x000000a0ad6f7dc5 // vmovdqa ymm13, yword 160[rbp] /* [rip + .LCPI5_5] */ LONG $0xdf1d41c4; BYTE $0xe5 // vpandn ymm12, ymm12, ymm13 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 - QUAD $0x0004a024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1184] - QUAD $0x000000c08d6f7dc5 // vmovdqa ymm9, yword 192[rbp] /* [rip + .LCPI5_6] */ - LONG $0xdf1d41c4; BYTE $0xe1 // vpandn ymm12, ymm12, ymm9 + QUAD $0x00048024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1152] + QUAD $0x000000c0b56f7dc5 // vmovdqa ymm14, yword 192[rbp] /* [rip + .LCPI5_6] */ + LONG $0xdf1d41c4; BYTE $0xe6 // vpandn ymm12, ymm12, ymm14 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0xc7ebfdc5 // vpor ymm0, ymm0, ymm7 - QUAD $0x00048024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1152] - QUAD $0x00046024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1120] + QUAD $0x00046024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 1120] + QUAD $0x00044024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1088] LONG $0xe5df1dc5 // vpandn ymm12, ymm12, ymm5 LONG $0xfffc9dc5 // vpaddb ymm7, ymm12, ymm7 - QUAD $0x00044024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1088] + QUAD $0x00042024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1056] LONG $0xe6df1dc5 // vpandn ymm12, ymm12, ymm6 - QUAD $0x00042024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 1056] + QUAD $0x00040024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 1024] LONG $0xfbdf05c5 // vpandn ymm15, ymm15, ymm3 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 - QUAD $0x0003e024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 992] - LONG $0xdf0541c4; BYTE $0xf8 // vpandn ymm15, ymm15, ymm8 + QUAD $0x0003c024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 960] + LONG $0xfcdf05c5 // vpandn ymm15, ymm15, ymm4 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 - LONG $0xfcf8c5c5 // vpsubb ymm7, ymm7, ymm4 + LONG $0xf845c1c4; BYTE $0xf8 // vpsubb ymm7, ymm7, ymm8 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 - QUAD $0x00040024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 1024] + QUAD $0x0003e024a4746dc5; BYTE $0x00 // vpcmpeqb ymm12, ymm2, yword [rsp + 992] LONG $0xe1df1dc5 // vpandn ymm12, ymm12, ymm1 - QUAD $0x0003a024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 928] + QUAD $0x00038024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 896] LONG $0xdf0541c4; BYTE $0xfd // vpandn ymm15, ymm15, ymm13 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 - QUAD $0x0003c024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 960] - LONG $0xdf0541c4; BYTE $0xf9 // vpandn ymm15, ymm15, ymm9 + QUAD $0x0003a024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 928] + LONG $0xdf0541c4; BYTE $0xfe // vpandn ymm15, ymm15, ymm14 + LONG $0x6f7d41c4; BYTE $0xc6 // vmovdqa ymm8, ymm14 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 LONG $0xe7eb1dc5 // vpor ymm12, ymm12, ymm7 - QUAD $0x00038024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 896] - QUAD $0x00036024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 864] + QUAD $0x00036024bc74edc5; BYTE $0x00 // vpcmpeqb ymm7, ymm2, yword [rsp + 864] + QUAD $0x00034024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 832] LONG $0xfddf05c5 // vpandn ymm15, ymm15, ymm5 LONG $0xfffc85c5 // vpaddb ymm7, ymm15, ymm7 - QUAD $0x00032024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 800] + QUAD $0x00030024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 768] LONG $0xfedf05c5 // vpandn ymm15, ymm15, ymm6 - QUAD $0x00034024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 832] + QUAD $0x00032024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 800] LONG $0xf3df0dc5 // vpandn ymm14, ymm14, ymm3 LONG $0xeb0541c4; BYTE $0xf6 // vpor ymm14, ymm15, ymm14 - QUAD $0x0002e024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 736] - LONG $0xdf0541c4; BYTE $0xf8 // vpandn ymm15, ymm15, ymm8 + QUAD $0x0002c024bc746dc5; BYTE $0x00 // vpcmpeqb ymm15, ymm2, yword [rsp + 704] + LONG $0xfcdf05c5 // vpandn ymm15, ymm15, ymm4 LONG $0xeb0d41c4; BYTE $0xf7 // vpor ymm14, ymm14, ymm15 - LONG $0xfcf8c5c5 // vpsubb ymm7, ymm7, ymm4 + LONG $0x760541c4; BYTE $0xff // vpcmpeqd ymm15, ymm15, ymm15 + LONG $0xf845c1c4; BYTE $0xff // vpsubb ymm7, ymm7, ymm15 LONG $0xffeb8dc5 // vpor ymm7, ymm14, ymm7 - QUAD $0x00030024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 768] + QUAD $0x0002e024b4746dc5; BYTE $0x00 // vpcmpeqb ymm14, ymm2, yword [rsp + 736] LONG $0xf1df0dc5 // vpandn ymm14, ymm14, ymm1 LONG $0xd2742dc5 // vpcmpeqb ymm10, ymm10, ymm2 LONG $0xdf2d41c4; BYTE $0xd5 // vpandn ymm10, ymm10, ymm13 LONG $0xeb0d41c4; BYTE $0xd2 // vpor ymm10, ymm14, ymm10 LONG $0xda7425c5 // vpcmpeqb ymm11, ymm11, ymm2 - LONG $0x6f7d41c4; BYTE $0xf1 // vmovdqa ymm14, ymm9 - LONG $0xdf2541c4; BYTE $0xd9 // vpandn ymm11, ymm11, ymm9 + LONG $0xdf2541c4; BYTE $0xd8 // vpandn ymm11, ymm11, ymm8 + LONG $0x6f7d41c4; BYTE $0xf0 // vmovdqa ymm14, ymm8 LONG $0xeb2d41c4; BYTE $0xd3 // vpor ymm10, ymm10, ymm11 LONG $0xffebadc5 // vpor ymm7, ymm10, ymm7 - QUAD $0x000220248c746dc5; BYTE $0x00 // vpcmpeqb ymm9, ymm2, yword [rsp + 544] - QUAD $0x0002402484746dc5; BYTE $0x00 // vpcmpeqb ymm8, ymm2, yword [rsp + 576] + LONG $0xca7435c5 // vpcmpeqb ymm9, ymm9, ymm2 + QUAD $0x0002202484746dc5; BYTE $0x00 // vpcmpeqb ymm8, ymm2, yword [rsp + 544] LONG $0xc5df3dc5 // vpandn ymm8, ymm8, ymm5 LONG $0xfc3d41c4; BYTE $0xc1 // vpaddb ymm8, ymm8, ymm9 - QUAD $0x00026024ac74edc5; BYTE $0x00 // vpcmpeqb ymm5, ymm2, yword [rsp + 608] + QUAD $0x00024024ac74edc5; BYTE $0x00 // vpcmpeqb ymm5, ymm2, yword [rsp + 576] LONG $0xeedfd5c5 // vpandn ymm5, ymm5, ymm6 - QUAD $0x00028024b474edc5; BYTE $0x00 // vpcmpeqb ymm6, ymm2, yword [rsp + 640] + QUAD $0x00026024b474edc5; BYTE $0x00 // vpcmpeqb ymm6, ymm2, yword [rsp + 608] LONG $0xf3dfcdc5 // vpandn ymm6, ymm6, ymm3 LONG $0xeeebd5c5 // vpor ymm5, ymm5, ymm6 - QUAD $0x0002a0249c74edc5; BYTE $0x00 // vpcmpeqb ymm3, ymm2, yword [rsp + 672] - LONG $0x5ddfe5c5; BYTE $0x60 // vpandn ymm3, ymm3, yword 96[rbp] /* [rip + .LCPI5_3] */ + QUAD $0x000280249c74edc5; BYTE $0x00 // vpcmpeqb ymm3, ymm2, yword [rsp + 640] + LONG $0xdcdfe5c5 // vpandn ymm3, ymm3, ymm4 LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 - LONG $0xecf8bdc5 // vpsubb ymm5, ymm8, ymm4 + LONG $0xf83dc1c4; BYTE $0xef // vpsubb ymm5, ymm8, ymm15 LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 - QUAD $0x0002c024a474edc5; BYTE $0x00 // vpcmpeqb ymm4, ymm2, yword [rsp + 704] + QUAD $0x0002a024a474edc5; BYTE $0x00 // vpcmpeqb ymm4, ymm2, yword [rsp + 672] LONG $0xe1dfddc5 // vpandn ymm4, ymm4, ymm1 QUAD $0x000140248c74edc5; BYTE $0x00 // vpcmpeqb ymm1, ymm2, yword [rsp + 320] LONG $0xdf75c1c4; BYTE $0xcd // vpandn ymm1, ymm1, ymm13 @@ -34677,22 +35563,22 @@ LBB5_169: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000198248c8b48 // mov rcx, qword [rsp + 408] - LONG $0x447ffec5; WORD $0x608f // vmovdqu yword [rdi + 4*rcx + 96], ymm0 - LONG $0x547ffec5; WORD $0x408f // vmovdqu yword [rdi + 4*rcx + 64], ymm2 - LONG $0x647ffec5; WORD $0x208f // vmovdqu yword [rdi + 4*rcx + 32], ymm4 - LONG $0x0c7ffec5; BYTE $0x8f // vmovdqu yword [rdi + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608b // vmovdqu yword [rbx + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408b // vmovdqu yword [rbx + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208b // vmovdqu yword [rbx + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8b // vmovdqu yword [rbx + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 - WORD $0x8948; BYTE $0xcb // mov rbx, rcx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000178248c3b48 // cmp rcx, qword [rsp + 376] - JNE LBB5_169 - QUAD $0x0000018024b48b4c // mov r14, qword [rsp + 384] - QUAD $0x0000017824b43b4c // cmp r14, qword [rsp + 376] - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - QUAD $0x0000019024ac8b4c // mov r13, qword [rsp + 400] - QUAD $0x0000018824948b48 // mov rdx, qword [rsp + 392] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - JNE LBB5_117 - JMP LBB5_120 + JNE LBB5_193 + QUAD $0x00000180248c8b48 // mov rcx, qword [rsp + 384] + QUAD $0x00000178248c3b48 // cmp rcx, qword [rsp + 376] + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + QUAD $0x0000018824ac8b4c // mov r13, qword [rsp + 392] + QUAD $0x0000019024bc8b48 // mov rdi, qword [rsp + 400] + JNE LBB5_152 + JMP LBB5_155 TEXT ·_comparison_greater_arr_arr_avx2(SB), $80-48 @@ -34704,68 +35590,82 @@ TEXT ·_comparison_greater_arr_arr_avx2(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB6_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB6_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB6_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB6_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB6_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_22 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_20: - WORD $0x0a8b // mov ecx, dword [rdx] - LONG $0x04c28348 // add rdx, 4 - WORD $0x0e3b // cmp ecx, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_20 - LONG $0x01c68349 // add r14, 1 - -LBB6_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_26 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB6_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB6_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB6_24: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x82 // mov ebx, dword [rdx + 4*rax] + WORD $0x1c3b; BYTE $0x86 // cmp ebx, dword [rsi + 4*rax] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_26: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_28: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_32 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_30: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] LONG $0xd5970f41 // seta r13b @@ -34786,7 +35686,7 @@ LBB6_24: WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] @@ -34800,7 +35700,7 @@ LBB6_24: WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] LONG $0xd1970f41 // seta r9b WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] @@ -34816,7 +35716,7 @@ LBB6_24: LONG $0x405a3b44 // cmp r11d, dword [rdx + 64] LONG $0x2454970f; BYTE $0x0a // seta byte [rsp + 10] WORD $0x4a3b; BYTE $0x44 // cmp ecx, dword [rdx + 68] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b WORD $0x423b; BYTE $0x48 // cmp eax, dword [rdx + 72] WORD $0x468b; BYTE $0x4c // mov eax, dword [rsi + 76] LONG $0x2454970f; BYTE $0x06 // seta byte [rsp + 6] @@ -34860,11 +35760,11 @@ LBB6_24: WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x970f; BYTE $0xd0 // seta al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] + LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0844; BYTE $0xe9 // or cl, r13b @@ -34884,23 +35784,23 @@ LBB6_24: LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xcc // or r12b, r9b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0845; BYTE $0xc2 // or r10b, r8b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0a // add r14b, byte [rsp + 10] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0a // add r12b, byte [rsp + 10] LONG $0x244cb60f; BYTE $0x06 // movzx ecx, byte [rsp + 6] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe1 // or cl, r12b LONG $0x03e3c041 // shl r11b, 3 WORD $0x0841; BYTE $0xcb // or r11b, cl LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] @@ -34910,12 +35810,12 @@ LBB6_24: LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd908 // or cl, bl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x44b60f44; WORD $0x0d24 // movzx r8d, byte [rsp + 13] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0844; BYTE $0xc7 // or dil, r8b - LONG $0x01568845 // mov byte [r14 + 1], r10b + LONG $0x01578845 // mov byte [r15 + 1], r10b WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xc900 // add cl, cl @@ -34939,98 +35839,111 @@ LBB6_24: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x027e8841 // mov byte [r14 + 2], dil - LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x027f8841 // mov byte [r15 + 2], dil + LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_24 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_30 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] -LBB6_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_28: +LBB6_34: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8a // mov edi, dword [rdx + 4*rcx] WORD $0x3c3b; BYTE $0x8e // cmp edi, dword [rsi + 4*rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_28 - JMP LBB6_123 - -LBB6_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB6_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB6_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB6_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_50 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_48: - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0xd2970f41 // seta r10b - LONG $0x08c28348 // add rdx, 8 - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_48 - LONG $0x01c68349 // add r14, 1 - -LBB6_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_54 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB6_52: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_34 + JMP LBB6_153 + +LBB6_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB6_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB6_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB6_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_58: + LONG $0x0410fbc5; BYTE $0xc6 // vmovsd xmm0, qword [rsi + 8*rax] + LONG $0x042ef9c5; BYTE $0xc2 // vucomisd xmm0, qword [rdx + 8*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xd3970f41 // seta r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_58 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_60: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_62: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_66 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB6_64: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] LONG $0x2454970f; BYTE $0x04 // seta byte [rsp + 4] @@ -35054,7 +35967,7 @@ LBB6_52: WORD $0x970f; BYTE $0xd0 // seta al LONG $0x4610fbc5; BYTE $0x38 // vmovsd xmm0, qword [rsi + 56] LONG $0x422ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rdx + 56] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x4610fbc5; BYTE $0x40 // vmovsd xmm0, qword [rsi + 64] LONG $0x422ef9c5; BYTE $0x40 // vucomisd xmm0, qword [rdx + 64] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] @@ -35069,7 +35982,7 @@ LBB6_52: LONG $0xd3970f41 // seta r11b LONG $0x4610fbc5; BYTE $0x60 // vmovsd xmm0, qword [rsi + 96] LONG $0x422ef9c5; BYTE $0x60 // vucomisd xmm0, qword [rdx + 96] - LONG $0xd6970f41 // seta r14b + LONG $0xd7970f41 // seta r15b LONG $0x4610fbc5; BYTE $0x68 // vmovsd xmm0, qword [rsi + 104] LONG $0x422ef9c5; BYTE $0x68 // vucomisd xmm0, qword [rdx + 104] LONG $0x2454970f; BYTE $0x05 // seta byte [rsp + 5] @@ -35131,8 +36044,8 @@ LBB6_52: WORD $0xc900 // add cl, cl LONG $0x04244c02 // add cl, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl @@ -35153,26 +36066,26 @@ LBB6_52: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -35180,12 +36093,12 @@ LBB6_52: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -35211,23 +36124,22 @@ LBB6_52: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB6_52 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB6_64 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB6_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_56: +LBB6_68: LONG $0x0410fbc5; BYTE $0xce // vmovsd xmm0, qword [rsi + 8*rcx] LONG $0x042ef9c5; BYTE $0xca // vucomisd xmm0, qword [rdx + 8*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -35235,75 +36147,95 @@ LBB6_56: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_56 - JMP LBB6_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_68 + JMP LBB6_153 LBB6_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB6_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + JE LBB6_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB6_9 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB6_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd49f0f41 // setg r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_6 - LONG $0x01c68349 // add r14, 1 - -LBB6_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_12 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB6_10: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + LONG $0x38048841 // mov byte [r8 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB6_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB6_9: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_11: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_15 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_13: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x0246b60f // movzx eax, byte [rsi + 2] @@ -35323,7 +36255,7 @@ LBB6_10: LONG $0x24549f0f; BYTE $0x04 // setg byte [rsp + 4] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd79f0f41 // setg r15b + LONG $0xd69f0f41 // setg r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x24549f0f; BYTE $0x07 // setg byte [rsp + 7] @@ -35338,7 +36270,7 @@ LBB6_10: LONG $0xd39f0f41 // setg r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd69f0f41 // setg r14b + LONG $0xd79f0f41 // setg r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] LONG $0x24549f0f; BYTE $0x05 // setg byte [rsp + 5] @@ -35398,12 +36330,12 @@ LBB6_10: WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] LONG $0xd09f0f41 // setg r8b WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x30244c02 // add cl, byte [rsp + 48] WORD $0xc889 // mov eax, ecx LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al @@ -35425,26 +36357,26 @@ LBB6_10: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x06 // movzx edi, byte [rsp + 6] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0d // add r12b, byte [rsp + 13] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -35452,12 +36384,12 @@ LBB6_10: LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al @@ -35483,23 +36415,22 @@ LBB6_10: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_10 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB6_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_13 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB6_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_14: +LBB6_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -35507,74 +36438,88 @@ LBB6_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_14 - JMP LBB6_123 - -LBB6_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB6_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_36 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_34: - WORD $0x8b48; BYTE $0x0a // mov rcx, qword [rdx] - LONG $0x08c28348 // add rdx, 8 - WORD $0x3b48; BYTE $0x0e // cmp rcx, qword [rsi] - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_34 - LONG $0x01c68349 // add r14, 1 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_17 + JMP LBB6_153 LBB6_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_40 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB6_38: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB6_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_41: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc21c8b48 // mov rbx, qword [rdx + 8*rax] + LONG $0xc61c3b48 // cmp rbx, qword [rsi + 8*rax] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_43: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_45: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_49 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_47: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0xd5970f41 // seta r13b @@ -35595,7 +36540,7 @@ LBB6_38: LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0x40468b48 // mov rax, qword [rsi + 64] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x40423b48 // cmp rax, qword [rdx + 64] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] @@ -35609,7 +36554,7 @@ LBB6_38: LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0xd1970f41 // seta r9b LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] LONG $0x70468b48 // mov rax, qword [rsi + 112] @@ -35625,7 +36570,7 @@ LBB6_38: LONG $0x809a3b4c; WORD $0x0000; BYTE $0x00 // cmp r11, qword [rdx + 128] LONG $0x2454970f; BYTE $0x0a // seta byte [rsp + 10] LONG $0x888a3b48; WORD $0x0000; BYTE $0x00 // cmp rcx, qword [rdx + 136] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b LONG $0x90823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 144] LONG $0x98868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 152] LONG $0x2454970f; BYTE $0x06 // seta byte [rsp + 6] @@ -35669,11 +36614,11 @@ LBB6_38: LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x970f; BYTE $0xd0 // seta al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] + LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0844; BYTE $0xe9 // or cl, r13b @@ -35693,23 +36638,23 @@ LBB6_38: LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xcc // or r12b, r9b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0845; BYTE $0xc2 // or r10b, r8b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0a // add r14b, byte [rsp + 10] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0a // add r12b, byte [rsp + 10] LONG $0x244cb60f; BYTE $0x06 // movzx ecx, byte [rsp + 6] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe1 // or cl, r12b LONG $0x03e3c041 // shl r11b, 3 WORD $0x0841; BYTE $0xcb // or r11b, cl LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] @@ -35719,12 +36664,12 @@ LBB6_38: LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd908 // or cl, bl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x44b60f44; WORD $0x0d24 // movzx r8d, byte [rsp + 13] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0844; BYTE $0xc7 // or dil, r8b - LONG $0x01568845 // mov byte [r14 + 1], r10b + LONG $0x01578845 // mov byte [r15 + 1], r10b WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xc900 // add cl, cl @@ -35748,93 +36693,106 @@ LBB6_38: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x027e8841 // mov byte [r14 + 2], dil - LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x027f8841 // mov byte [r15 + 2], dil + LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_38 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_47 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] -LBB6_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_42: +LBB6_51: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xca3c8b48 // mov rdi, qword [rdx + 8*rcx] LONG $0xce3c3b48 // cmp rdi, qword [rsi + 8*rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_42 - JMP LBB6_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_51 + JMP LBB6_153 -LBB6_68: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_72 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_70: - WORD $0xb70f; BYTE $0x0a // movzx ecx, word [rdx] - LONG $0x02c28348 // add rdx, 2 - WORD $0x3b66; BYTE $0x0e // cmp cx, word [rsi] - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_70 - LONG $0x01c68349 // add r14, 1 +LBB6_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_86: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x421cb70f // movzx ebx, word [rdx + 2*rax] + LONG $0x461c3b66 // cmp bx, word [rsi + 2*rax] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB6_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_76 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB6_88: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 -LBB6_74: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_90: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_94 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_92: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0xd5970f41 // seta r13b @@ -35855,7 +36813,7 @@ LBB6_74: LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0x1046b70f // movzx eax, word [rsi + 16] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x10423b66 // cmp ax, word [rdx + 16] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] @@ -35869,7 +36827,7 @@ LBB6_74: LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0xd1970f41 // seta r9b LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] LONG $0x1c46b70f // movzx eax, word [rsi + 28] @@ -35885,7 +36843,7 @@ LBB6_74: LONG $0x5a3b4466; BYTE $0x20 // cmp r11w, word [rdx + 32] LONG $0x2454970f; BYTE $0x0a // seta byte [rsp + 10] LONG $0x224a3b66 // cmp cx, word [rdx + 34] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b LONG $0x24423b66 // cmp ax, word [rdx + 36] LONG $0x2646b70f // movzx eax, word [rsi + 38] LONG $0x2454970f; BYTE $0x06 // seta byte [rsp + 6] @@ -35929,11 +36887,11 @@ LBB6_74: LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x970f; BYTE $0xd0 // seta al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] + LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0844; BYTE $0xe9 // or cl, r13b @@ -35953,23 +36911,23 @@ LBB6_74: LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xcc // or r12b, r9b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0845; BYTE $0xc2 // or r10b, r8b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0a // add r14b, byte [rsp + 10] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0a // add r12b, byte [rsp + 10] LONG $0x244cb60f; BYTE $0x06 // movzx ecx, byte [rsp + 6] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe1 // or cl, r12b LONG $0x03e3c041 // shl r11b, 3 WORD $0x0841; BYTE $0xcb // or r11b, cl LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] @@ -35979,12 +36937,12 @@ LBB6_74: LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd908 // or cl, bl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x44b60f44; WORD $0x0d24 // movzx r8d, byte [rsp + 13] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0844; BYTE $0xc7 // or dil, r8b - LONG $0x01568845 // mov byte [r14 + 1], r10b + LONG $0x01578845 // mov byte [r15 + 1], r10b WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xc900 // add cl, cl @@ -36008,96 +36966,109 @@ LBB6_74: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x027e8841 // mov byte [r14 + 2], dil - LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x027f8841 // mov byte [r15 + 2], dil + LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_74 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_92 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] -LBB6_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_78: +LBB6_96: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4a3cb70f // movzx edi, word [rdx + 2*rcx] LONG $0x4e3c3b66 // cmp di, word [rsi + 2*rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_78 - JMP LBB6_123 - -LBB6_79: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_83 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_81 - LONG $0x01c68349 // add r14, 1 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_96 + JMP LBB6_153 + +LBB6_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB6_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_87 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB6_85: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd39f0f41 // setg r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_102: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_104: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_108 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB6_106: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] LONG $0x24549f0f; BYTE $0x14 // setg byte [rsp + 20] @@ -36121,7 +37092,7 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x09 // setg byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd09f0f41 // setg r8b + LONG $0xd79f0f40 // setg dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd39f0f41 // setg r11b @@ -36161,7 +37132,7 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x0b // setg byte [rsp + 11] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] + LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd19f0f41 // setg r9b @@ -36170,10 +37141,10 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x13 // setg byte [rsp + 19] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] + LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] + LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] LONG $0x24549f0f; BYTE $0x0f // setg byte [rsp + 15] @@ -36188,10 +37159,10 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x11 // setg byte [rsp + 17] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] - LONG $0xd79f0f40 // setg dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09f0f41 // setg r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -36200,34 +37171,34 @@ LBB6_85: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -36240,22 +37211,23 @@ LBB6_85: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -36272,26 +37244,25 @@ LBB6_85: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB6_85 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - -LBB6_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + JNE LBB6_106 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB6_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_89: +LBB6_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -36299,73 +37270,87 @@ LBB6_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_89 - JMP LBB6_123 - -LBB6_101: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_105 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_103 - LONG $0x01c68349 // add r14, 1 - -LBB6_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_109 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB6_107: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_110 + JMP LBB6_153 + +LBB6_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd39f0f41 // setg r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_130: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_132: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_136 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB6_134: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] LONG $0x24549f0f; BYTE $0x14 // setg byte [rsp + 20] @@ -36389,7 +37374,7 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x09 // setg byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd09f0f41 // setg r8b + LONG $0xd79f0f40 // setg dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd39f0f41 // setg r11b @@ -36429,7 +37414,7 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x0b // setg byte [rsp + 11] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] + LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd19f0f41 // setg r9b @@ -36438,10 +37423,10 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x13 // setg byte [rsp + 19] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] + LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] + LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] LONG $0x24549f0f; BYTE $0x0f // setg byte [rsp + 15] @@ -36456,10 +37441,10 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x11 // setg byte [rsp + 17] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] - LONG $0xd79f0f40 // setg dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09f0f41 // setg r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -36468,34 +37453,34 @@ LBB6_107: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -36508,22 +37493,23 @@ LBB6_107: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -36540,26 +37526,25 @@ LBB6_107: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB6_107 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB6_134 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB6_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_111: +LBB6_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -36567,67 +37552,81 @@ LBB6_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_111 - JMP LBB6_123 - -LBB6_112: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_116 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_114: - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0xd2970f41 // seta r10b - LONG $0x04c28348 // add rdx, 4 - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_114 - LONG $0x01c68349 // add r14, 1 - -LBB6_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_120 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_138 + JMP LBB6_153 + +LBB6_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_142: + LONG $0x0410fac5; BYTE $0x86 // vmovss xmm0, dword [rsi + 4*rax] + LONG $0x042ef8c5; BYTE $0x82 // vucomiss xmm0, dword [rdx + 4*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xd3970f41 // seta r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_142 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_144: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_146: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_150 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax -LBB6_118: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_148: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x0610fac5 // vmovss xmm0, dword [rsi] LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] LONG $0x2454970f; BYTE $0x04 // seta byte [rsp + 4] @@ -36651,7 +37650,7 @@ LBB6_118: WORD $0x970f; BYTE $0xd0 // seta al LONG $0x4610fac5; BYTE $0x1c // vmovss xmm0, dword [rsi + 28] LONG $0x422ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rdx + 28] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x4610fac5; BYTE $0x20 // vmovss xmm0, dword [rsi + 32] LONG $0x422ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rdx + 32] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] @@ -36666,7 +37665,7 @@ LBB6_118: LONG $0xd3970f41 // seta r11b LONG $0x4610fac5; BYTE $0x30 // vmovss xmm0, dword [rsi + 48] LONG $0x422ef8c5; BYTE $0x30 // vucomiss xmm0, dword [rdx + 48] - LONG $0xd6970f41 // seta r14b + LONG $0xd7970f41 // seta r15b LONG $0x4610fac5; BYTE $0x34 // vmovss xmm0, dword [rsi + 52] LONG $0x422ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rdx + 52] LONG $0x2454970f; BYTE $0x05 // seta byte [rsp + 5] @@ -36728,8 +37727,8 @@ LBB6_118: WORD $0xc900 // add cl, cl LONG $0x04244c02 // add cl, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl @@ -36750,26 +37749,26 @@ LBB6_118: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -36777,12 +37776,12 @@ LBB6_118: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -36808,23 +37807,22 @@ LBB6_118: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB6_118 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB6_148 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB6_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_122: +LBB6_152: LONG $0x0410fac5; BYTE $0x8e // vmovss xmm0, dword [rsi + 4*rcx] LONG $0x042ef8c5; BYTE $0x8a // vucomiss xmm0, dword [rdx + 4*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -36832,66 +37830,85 @@ LBB6_122: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_122 - JMP LBB6_123 - -LBB6_57: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_61 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_59: - WORD $0xb60f; BYTE $0x0a // movzx ecx, byte [rdx] - LONG $0x01c28348 // add rdx, 1 - WORD $0x0e3a // cmp cl, byte [rsi] - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_152 + JMP LBB6_153 + +LBB6_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_59 - LONG $0x01c68349 // add r14, 1 - -LBB6_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_65 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB6_63: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + JLE LBB6_74 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xe4 // xor r12d, r12d + +LBB6_72: + LONG $0x0cb60f42; BYTE $0x22 // movzx ecx, byte [rdx + r12] + LONG $0x260c3a42 // cmp cl, byte [rsi + r12] + WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf2 // xor r10b, r14b + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + LONG $0x38048841 // mov byte [r8 + rdi], al + LONG $0x01c48349 // add r12, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc38349 // add r11, -1 + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB6_72 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB6_74: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_76: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_80 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_78: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] @@ -36913,9 +37930,9 @@ LBB6_63: LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] LONG $0x0746b60f // movzx eax, byte [rsi + 7] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x0946b60f // movzx eax, byte [rsi + 9] @@ -36945,11 +37962,11 @@ LBB6_63: LONG $0x1146b60f // movzx eax, byte [rsi + 17] LONG $0x2454970f; BYTE $0x0c // seta byte [rsp + 12] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b LONG $0x1246b60f // movzx eax, byte [rsi + 18] WORD $0x423a; BYTE $0x12 // cmp al, byte [rdx + 18] LONG $0x1346b60f // movzx eax, byte [rsi + 19] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] LONG $0x1446b60f // movzx eax, byte [rsi + 20] @@ -36992,10 +38009,10 @@ LBB6_63: WORD $0x0045; BYTE $0xed // add r13b, r13b LONG $0x246c0244; BYTE $0x04 // add r13b, byte [rsp + 4] WORD $0x8944; BYTE $0xe8 // mov eax, r13d - LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] + LONG $0x6cb60f44; WORD $0x3024 // movzx r13d, byte [rsp + 48] LONG $0x06e5c041 // shl r13b, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0845; BYTE $0xef // or r15b, r13b + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0845; BYTE $0xee // or r14b, r13b LONG $0x6cb60f44; WORD $0x1424 // movzx r13d, byte [rsp + 20] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0841; BYTE $0xc5 // or r13b, al @@ -37025,28 +38042,28 @@ LBB6_63: LONG $0x06e1c041 // shl r9b, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al - WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0c // add r12b, byte [rsp + 12] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xe6 // or r14b, r12b + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x0c // add r15b, byte [rsp + 12] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe0 // or al, r12b LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0a // movzx ecx, byte [rsp + 10] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc0 // or r8b, al LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xc000 // add al, al @@ -37069,96 +38086,109 @@ LBB6_63: LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xc7 // or dil, al WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x02468845 // mov byte [r14 + 2], r8b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x02478845 // mov byte [r15 + 2], r8b + LONG $0x037f8841 // mov byte [r15 + 3], dil LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_63 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB6_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_78 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB6_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_67: +LBB6_82: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0a1cb60f // movzx ebx, byte [rdx + rcx] WORD $0x1c3a; BYTE $0x0e // cmp bl, byte [rsi + rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_67 - JMP LBB6_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_82 + JMP LBB6_153 -LBB6_90: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_94 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB6_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB6_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_92 - LONG $0x01c68349 // add r14, 1 +LBB6_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd39f0f41 // setg r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB6_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_98 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 +LBB6_116: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 -LBB6_96: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_118: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_122 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB6_120: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] LONG $0x24549f0f; BYTE $0x14 // setg byte [rsp + 20] @@ -37182,7 +38212,7 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x09 // setg byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd09f0f41 // setg r8b + LONG $0xd79f0f40 // setg dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd39f0f41 // setg r11b @@ -37222,7 +38252,7 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x0b // setg byte [rsp + 11] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] + LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd19f0f41 // setg r9b @@ -37231,10 +38261,10 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x13 // setg byte [rsp + 19] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] + LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] + LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] LONG $0x24549f0f; BYTE $0x0f // setg byte [rsp + 15] @@ -37249,10 +38279,10 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x11 // setg byte [rsp + 17] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] - LONG $0xd79f0f40 // setg dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09f0f41 // setg r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -37261,34 +38291,34 @@ LBB6_96: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -37301,22 +38331,23 @@ LBB6_96: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -37333,26 +38364,25 @@ LBB6_96: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB6_96 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB6_120 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB6_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_100: +LBB6_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -37360,19 +38390,19 @@ LBB6_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_100 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_124 -LBB6_123: +LBB6_153: SUBQ $8, SP RET @@ -37420,83 +38450,96 @@ TEXT ·_comparison_greater_arr_scalar_avx2(SB), $1384-48 MOVQ BP, 1344(SP) LEAQ LCDATA5<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB7_19 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB7_24 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB7_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB7_84 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB7_102 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB7_191 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_17 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB7_112 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB7_130 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB7_210 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_15 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_13 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_12: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc08348 // add rax, -1 + JNE LBB7_12 + +LBB7_13: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 LBB7_15: - WORD $0x3b44; BYTE $0x2e // cmp r13d, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0xd219 // sbb edx, edx - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_15 - LONG $0x01c38349 // add r11, 1 + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_19 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax LBB7_17: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_18 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - -LBB7_120: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + QUAD $0x000000882494970f // seta byte [rsp + 136] LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd7970f40 // seta dil LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6970f41 // seta r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000802494970f // seta byte [rsp + 128] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x106e3944 // cmp dword [rsi + 16], r13d - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x970f; BYTE $0xd0 // seta al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d WORD $0x970f; BYTE $0xd3 // seta bl LONG $0x206e3944 // cmp dword [rsi + 32], r13d - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x246e3944 // cmp dword [rsi + 36], r13d - WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x286e3944 // cmp dword [rsi + 40], r13d LONG $0xd1970f41 // seta r9b LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d @@ -37506,33 +38549,33 @@ LBB7_120: LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4970f41 // seta r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x970f; BYTE $0xd1 // seta cl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x486e3944 // cmp dword [rsi + 72], r13d - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7970f41 // seta r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0x706e3944 // cmp dword [rsi + 112], r13d QUAD $0x000001202494970f // seta byte [rsp + 288] LONG $0x746e3944 // cmp dword [rsi + 116], r13d @@ -37542,167 +38585,185 @@ LBB7_120: LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d LONG $0xd0970f41 // seta r8b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x78 // add dil, byte [rsp + 120] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0xd200 // add dl, dl - LONG $0x68245402 // add dl, byte [rsp + 104] - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x60 // movzx edi, byte [rsp + 96] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xd308 // or bl, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xd200 // add dl, dl - LONG $0x40245402 // add dl, byte [rsp + 64] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - WORD $0x1a88 // mov byte [rdx], bl - LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x40244c02 // add cl, byte [rsp + 64] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4a88; BYTE $0x01 // mov byte [rdx + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xc900 // add cl, cl LONG $0x40248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 320] - WORD $0xcb89 // mov ebx, ecx + WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xd108 // or cl, dl + LONG $0x2454b60f; BYTE $0x04 // movzx edx, byte [rsp + 4] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xd8 // or r8b, bl + WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8844 // mov byte [rdx + 2], r15b - LONG $0x03428844 // mov byte [rdx + 3], r8b + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x03468845 // mov byte [r14 + 3], r8b LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c28348 // add rdx, 4 - QUAD $0x000000f024948948 // mov qword [rsp + 240], rdx - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB7_120 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB7_123 - JMP LBB7_191 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_17 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] LBB7_19: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB7_20 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB7_155 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB7_171 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB7_191 - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fbc5 // vmovsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_35 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_148 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB7_22 -LBB7_33: +LBB7_24: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB7_25 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB7_169 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB7_186 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB7_210 + WORD $0x8b4c; BYTE $0x22 // mov r12, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_49 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB7_48: LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] LONG $0x08c68348 // add rsi, 8 LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_33 - LONG $0x01c38349 // add r11, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB7_48 -LBB7_35: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_39 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - LONG $0x2474894c; BYTE $0x78 // mov qword [rsp + 120], r14 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 +LBB7_49: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 + +LBB7_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_55 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax -LBB7_37: +LBB7_53: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] LONG $0x5610fbc5; BYTE $0x08 // vmovsd xmm2, qword [rsi + 8] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 QUAD $0x000001202494970f // seta byte [rsp + 288] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 - WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x4e10fbc5; BYTE $0x10 // vmovsd xmm1, qword [rsi + 16] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0x4e10fbc5; BYTE $0x18 // vmovsd xmm1, qword [rsi + 24] @@ -37712,15 +38773,15 @@ LBB7_37: LONG $0x4e10fbc5; BYTE $0x20 // vmovsd xmm1, qword [rsi + 32] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0x4e10fbc5; BYTE $0x28 // vmovsd xmm1, qword [rsi + 40] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x4e10fbc5; BYTE $0x30 // vmovsd xmm1, qword [rsi + 48] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0x4e10fbc5; BYTE $0x38 // vmovsd xmm1, qword [rsi + 56] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x4e10fbc5; BYTE $0x40 // vmovsd xmm1, qword [rsi + 64] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0x4e10fbc5; BYTE $0x48 // vmovsd xmm1, qword [rsi + 72] @@ -37730,7 +38791,7 @@ LBB7_37: LONG $0x4e10fbc5; BYTE $0x50 // vmovsd xmm1, qword [rsi + 80] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0x4e10fbc5; BYTE $0x58 // vmovsd xmm1, qword [rsi + 88] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x4e10fbc5; BYTE $0x60 // vmovsd xmm1, qword [rsi + 96] @@ -37738,19 +38799,19 @@ LBB7_37: LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0x6e10fbc5; BYTE $0x70 // vmovsd xmm5, qword [rsi + 112] LONG $0x7610fbc5; BYTE $0x78 // vmovsd xmm6, qword [rsi + 120] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] QUAD $0x0000008086107bc5 // vmovsd xmm8, qword [rsi + 128] QUAD $0x000000888e107bc5 // vmovsd xmm9, qword [rsi + 136] LONG $0xd82ef9c5 // vucomisd xmm3, xmm0 QUAD $0x0000009096107bc5 // vmovsd xmm10, qword [rsi + 144] QUAD $0x000000989e107bc5 // vmovsd xmm11, qword [rsi + 152] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] QUAD $0x000000a0a6107bc5 // vmovsd xmm12, qword [rsi + 160] QUAD $0x000000a8ae107bc5 // vmovsd xmm13, qword [rsi + 168] LONG $0xe82ef9c5 // vucomisd xmm5, xmm0 QUAD $0x000000b0b6107bc5 // vmovsd xmm14, qword [rsi + 176] QUAD $0x000000b89610fbc5 // vmovsd xmm2, qword [rsi + 184] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] QUAD $0x000000c09e10fbc5 // vmovsd xmm3, qword [rsi + 192] QUAD $0x000000c8a610fbc5 // vmovsd xmm4, qword [rsi + 200] LONG $0xf02ef9c5 // vucomisd xmm6, xmm0 @@ -37760,7 +38821,7 @@ LBB7_37: QUAD $0x000000e08e10fbc5 // vmovsd xmm1, qword [rsi + 224] QUAD $0x000000e8ae10fbc5 // vmovsd xmm5, qword [rsi + 232] LONG $0xc02e79c5 // vucomisd xmm8, xmm0 - QUAD $0x000000802494970f // seta byte [rsp + 128] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0xc82e79c5 // vucomisd xmm9, xmm0 WORD $0x970f; BYTE $0xd1 // seta cl LONG $0xd02e79c5 // vucomisd xmm10, xmm0 @@ -37772,437 +38833,260 @@ LBB7_37: LONG $0xe82e79c5 // vucomisd xmm13, xmm0 LONG $0xd6970f41 // seta r14b LONG $0xf02e79c5 // vucomisd xmm14, xmm0 - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 LONG $0xd1970f41 // seta r9b LONG $0xd82ef9c5 // vucomisd xmm3, xmm0 - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0xe02ef9c5 // vucomisd xmm4, xmm0 - LONG $0xd7970f41 // seta r15b - LONG $0xf02ef9c5 // vucomisd xmm6, xmm0 - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0xf82ef9c5 // vucomisd xmm7, xmm0 - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] - LONG $0xe82ef9c5 // vucomisd xmm5, xmm0 - QUAD $0x000000f08e10fbc5 // vmovsd xmm1, qword [rsi + 240] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x04 // seta byte [rsp + 4] - QUAD $0x000000f88e10fbc5 // vmovsd xmm1, qword [rsi + 248] - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdb00 // add bl, bl - LONG $0x20249c02; WORD $0x0001; BYTE $0x00 // add bl, byte [rsp + 288] - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xec // or r12b, r13b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - WORD $0x8941; BYTE $0xdc // mov r12d, ebx - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - LONG $0x64b60f44; WORD $0x3024 // movzx r12d, byte [rsp + 48] - LONG $0x06e4c041 // shl r12b, 6 - LONG $0x6cb60f44; WORD $0x1824 // movzx r13d, byte [rsp + 24] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xc000 // add al, al - LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] - LONG $0x64b60f44; WORD $0x1024 // movzx r12d, byte [rsp + 16] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0x8944; BYTE $0xe0 // mov eax, r12d - QUAD $0x00014024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 320] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0xc308 // or bl, al - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0xc900 // add cl, cl - LONG $0x80248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 128] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x03e0c041 // shl r8b, 3 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xc2 // or r10b, r8b - LONG $0x05e6c041 // shl r14b, 5 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0841; BYTE $0xdb // or r11b, bl - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - WORD $0x8844; BYTE $0x28 // mov byte [rax], r13b - WORD $0x0845; BYTE $0xf1 // or r9b, r14b - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x58 // add r15b, byte [rsp + 88] - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf9 // or cl, r15b - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x01588844 // mov byte [rax + 1], r11b - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - LONG $0x02488844 // mov byte [rax + 2], r9b - WORD $0xca08 // or dl, cl - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x04c08348 // add rax, 4 - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - LONG $0x24448348; WORD $0xff78 // add qword [rsp + 120], -1 - JNE LBB7_37 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - -LBB7_39: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB7_191 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB7_186 - WORD $0x3145; BYTE $0xd2 // xor r10d, r10d - JMP LBB7_188 - -LBB7_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB7_42 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB7_191 - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f6a8d4d // lea r13, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - WORD $0x894d; BYTE $0xd7 // mov r15, r10 - LONG $0xea490f4d // cmovns r13, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB7_6: - WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_6 - LONG $0x01c38349 // add r11, 1 - -LBB7_8: - LONG $0x05fdc149 // sar r13, 5 - LONG $0x20ff8349 // cmp r15, 32 - JL LBB7_9 - LONG $0x20fd8349 // cmp r13, 32 - LONG $0x24748944; BYTE $0x04 // mov dword [rsp + 4], r14d - QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 - QUAD $0x0000016824ac894c // mov qword [rsp + 360], r13 - JB LBB7_67 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JAE LBB7_70 - LONG $0xab048d4b // lea rax, [r11 + 4*r13] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB7_70 - -LBB7_67: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x00000160249c894c // mov qword [rsp + 352], r11 - -LBB7_73: - QUAD $0x0000018024ac2b4c // sub r13, qword [rsp + 384] - LONG $0x246c894c; BYTE $0x78 // mov qword [rsp + 120], r13 - -LBB7_74: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b - QUAD $0x0000014024949f0f // setg byte [rsp + 320] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b - LONG $0xd09f0f41 // setg r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd79f0f41 // setg r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b - LONG $0xd59f0f41 // setg r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - QUAD $0x0000008024949f0f // setg byte [rsp + 128] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b - LONG $0xd39f0f41 // setg r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b - QUAD $0x0000012024949f0f // setg byte [rsp + 288] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b - WORD $0x9f0f; BYTE $0xd2 // setg dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b - LONG $0xd69f0f40 // setg sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b - LONG $0xd79f0f40 // setg dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b - LONG $0xd29f0f41 // setg r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b - LONG $0xd49f0f41 // setg r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b - LONG $0xd19f0f41 // setg r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b - QUAD $0x0000010024949f0f // setg byte [rsp + 256] - LONG $0x11713844 // cmp byte [rcx + 17], r14b - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x13713844 // cmp byte [rcx + 19], r14b - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x14713844 // cmp byte [rcx + 20], r14b - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x15713844 // cmp byte [rcx + 21], r14b - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd69f0f41 // setg r14b - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x000000f024949f0f // setg byte [rsp + 240] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - QUAD $0x0000014024840244 // add r8b, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0xe02ef9c5 // vucomisd xmm4, xmm0 + LONG $0xd7970f41 // seta r15b + LONG $0xf02ef9c5 // vucomisd xmm6, xmm0 + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0xf82ef9c5 // vucomisd xmm7, xmm0 + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0xe82ef9c5 // vucomisd xmm5, xmm0 + QUAD $0x000000f08e10fbc5 // vmovsd xmm1, qword [rsi + 240] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + LONG $0x2454970f; BYTE $0x04 // seta byte [rsp + 4] + QUAD $0x000000f88e10fbc5 // vmovsd xmm1, qword [rsi + 248] + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + WORD $0x970f; BYTE $0xd3 // seta bl WORD $0xd200 // add dl, dl LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + LONG $0x02e5c041 // shl r13b, 2 + WORD $0x0841; BYTE $0xd5 // or r13b, dl + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xec // or r12b, r13b + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + WORD $0x8941; BYTE $0xd4 // mov r12d, edx + LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] + LONG $0x06e4c041 // shl r12b, 6 + LONG $0x6cb60f44; WORD $0x3024 // movzx r13d, byte [rsp + 48] + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b WORD $0xc000 // add al, al LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + LONG $0x64b60f44; WORD $0x0824 // movzx r12d, byte [rsp + 8] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + WORD $0x8944; BYTE $0xe0 // mov eax, r12d + QUAD $0x00014024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 320] + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0x0841; BYTE $0xd5 // or r13b, dl + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000016024b48b48 // mov rsi, qword [rsp + 352] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x18 // movzx edi, byte [rsp + 24] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc208 // or dl, al + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0xc900 // add cl, cl + LONG $0x50244c02 // add cl, byte [rsp + 80] + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x05e6c041 // shl r14b, 5 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0841; BYTE $0xd3 // or r11b, dl + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xc1 // or r9b, al + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + WORD $0x8844; BYTE $0x28 // mov byte [rax], r13b + WORD $0x0845; BYTE $0xf1 // or r9b, r14b + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x78 // add r15b, byte [rsp + 120] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0x0844; BYTE $0xf8 // or al, r15b + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xc808 // or al, cl + LONG $0x015e8845 // mov byte [r14 + 1], r11b + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xd308 // or bl, dl + WORD $0xcb08 // or bl, cl + LONG $0x024e8845 // mov byte [r14 + 2], r9b WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000016024b48948 // mov qword [rsp + 352], rsi - LONG $0x24448348; WORD $0xff78 // add qword [rsp + 120], -1 - JNE LBB7_74 + LONG $0x035e8841 // mov byte [r14 + 3], bl + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 + JNE LBB7_53 QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x0000016824ac8b4c // mov r13, qword [rsp + 360] - JMP LBB7_76 - -LBB7_20: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB7_129 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB7_191 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_26 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] -LBB7_24: - WORD $0x3b4c; BYTE $0x2e // cmp r13, qword [rsi] - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0xd219 // sbb edx, edx - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_24 - LONG $0x01c38349 // add r11, 1 - -LBB7_26: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_27 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 +LBB7_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_203 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + JMP LBB7_205 -LBB7_146: - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 +LBB7_2: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB7_58 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB7_210 + WORD $0x8a44; BYTE $0x2a // mov r13b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_5 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_87 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB7_93: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB7_93 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB7_89 + JMP LBB7_210 + +LBB7_25: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB7_150 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB7_210 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_33 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_31 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_30: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc08348 // add rax, -1 + JNE LBB7_30 + +LBB7_31: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 + +LBB7_33: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_37 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + +LBB7_35: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + QUAD $0x000000882494970f // seta byte [rsp + 136] LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd7970f40 // seta dil LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6970f41 // seta r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000802494970f // seta byte [rsp + 128] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x206e394c // cmp qword [rsi + 32], r13 - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x970f; BYTE $0xd0 // seta al LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x970f; BYTE $0xd3 // seta bl LONG $0x406e394c // cmp qword [rsi + 64], r13 - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x486e394c // cmp qword [rsi + 72], r13 - WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x506e394c // cmp qword [rsi + 80], r13 LONG $0xd1970f41 // seta r9b LONG $0x586e394c // cmp qword [rsi + 88], r13 @@ -38212,33 +39096,33 @@ LBB7_146: LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4970f41 // seta r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x970f; BYTE $0xd1 // seta cl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7970f41 // seta r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 QUAD $0x000001202494970f // seta byte [rsp + 288] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 @@ -38248,66 +39132,66 @@ LBB7_146: LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 LONG $0xd0970f41 // seta r8b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x78 // add dil, byte [rsp + 120] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0xd200 // add dl, dl - LONG $0x68245402 // add dl, byte [rsp + 104] - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x60 // movzx edi, byte [rsp + 96] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xd308 // or bl, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xd200 // add dl, dl - LONG $0x40245402 // add dl, byte [rsp + 64] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x40244c02 // add cl, byte [rsp + 64] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl - WORD $0x0841; BYTE $0xd7 // or r15b, dl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xc900 // add cl, cl LONG $0x40248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 320] WORD $0xca89 // mov edx, ecx @@ -38315,7 +39199,7 @@ LBB7_146: WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx @@ -38331,86 +39215,105 @@ LBB7_146: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03438845 // mov byte [r11 + 3], r8b + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x03468845 // mov byte [r14 + 3], r8b LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c38349 // add r11, 4 - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB7_146 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB7_149 - JMP LBB7_191 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_35 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] -LBB7_84: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_88 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB7_86: - LONG $0x2e3b4466 // cmp r13w, word [rsi] - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0xd219 // sbb edx, edx - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_86 - LONG $0x01c38349 // add r11, 1 - -LBB7_88: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_89 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 +LBB7_37: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_167 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB7_40 -LBB7_91: +LBB7_112: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_116 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_115: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc08348 // add rax, -1 + JNE LBB7_115 + +LBB7_116: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 + +LBB7_118: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_122 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + +LBB7_120: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 LONG $0x2e394466 // cmp word [rsi], r13w - WORD $0x970f; BYTE $0xd0 // seta al + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd7970f40 // seta dil LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd6970f41 // seta r14b LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000000802494970f // seta byte [rsp + 128] + QUAD $0x000000882494970f // seta byte [rsp + 136] LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + WORD $0x970f; BYTE $0xd0 // seta al LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w WORD $0x970f; BYTE $0xd3 // seta bl LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w - WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd1970f41 // seta r9b LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w @@ -38420,33 +39323,33 @@ LBB7_91: LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd4970f41 // seta r12b LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x970f; BYTE $0xd1 // seta cl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w LONG $0xd7970f41 // seta r15b LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w QUAD $0x000001202494970f // seta byte [rsp + 288] LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w @@ -38456,173 +39359,189 @@ LBB7_91: LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w LONG $0xd0970f41 // seta r8b WORD $0x0040; BYTE $0xff // add dil, dil - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x247c0240; BYTE $0x50 // add dil, byte [rsp + 80] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0xd200 // add dl, dl - LONG $0x48245402 // add dl, byte [rsp + 72] - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x68 // movzx edi, byte [rsp + 104] + LONG $0x247cb60f; BYTE $0x60 // movzx edi, byte [rsp + 96] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xd308 // or bl, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xd200 // add dl, dl - LONG $0x40245402 // add dl, byte [rsp + 64] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - WORD $0x1a88 // mov byte [rdx], bl - LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x40244c02 // add cl, byte [rsp + 64] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4a88; BYTE $0x01 // mov byte [rdx + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xc900 // add cl, cl LONG $0x40248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 320] - WORD $0xcb89 // mov ebx, ecx + WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xd108 // or cl, dl + LONG $0x2454b60f; BYTE $0x04 // movzx edx, byte [rsp + 4] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xd8 // or r8b, bl + WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8844 // mov byte [rdx + 2], r15b - LONG $0x03428844 // mov byte [rdx + 3], r8b + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x03468845 // mov byte [r14 + 3], r8b LONG $0x40c68348 // add rsi, 64 - LONG $0x04c28348 // add rdx, 4 - QUAD $0x000000f024948948 // mov qword [rsp + 240], rdx - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB7_91 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB7_94 - JMP LBB7_191 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_120 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] -LBB7_102: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_106 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB7_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_128 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB7_125 -LBB7_104: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_104 - LONG $0x01c38349 // add r11, 1 - -LBB7_106: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_107 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - -LBB7_109: +LBB7_130: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_136 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_134 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_133: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB7_133 + +LBB7_134: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 + +LBB7_136: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_140 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + +LBB7_138: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + QUAD $0x0000008824949f0f // setg byte [rsp + 136] LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd79f0f40 // setg dil LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd69f0f41 // setg r14b LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x0000008024949f0f // setg byte [rsp + 128] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w WORD $0x9f0f; BYTE $0xd0 // setg al LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w WORD $0x9f0f; BYTE $0xd3 // setg bl LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w - WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd19f0f41 // setg r9b LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w @@ -38632,33 +39551,33 @@ LBB7_109: LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd49f0f41 // setg r12b LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x9f0f; BYTE $0xd1 // setg cl + WORD $0x9f0f; BYTE $0xd2 // setg dl LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w LONG $0xd79f0f41 // setg r15b LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w QUAD $0x0000014024949f0f // setg byte [rsp + 320] LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w QUAD $0x0000012024949f0f // setg byte [rsp + 288] LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w @@ -38668,172 +39587,189 @@ LBB7_109: LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w LONG $0xd09f0f41 // setg r8b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x78 // add dil, byte [rsp + 120] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0xd200 // add dl, dl - LONG $0x68245402 // add dl, byte [rsp + 104] - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x60 // movzx edi, byte [rsp + 96] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xd308 // or bl, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xd200 // add dl, dl - LONG $0x40245402 // add dl, byte [rsp + 64] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - WORD $0x1a88 // mov byte [rdx], bl - LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x40244c02 // add cl, byte [rsp + 64] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4a88; BYTE $0x01 // mov byte [rdx + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xc900 // add cl, cl LONG $0x40248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 320] - WORD $0xcb89 // mov ebx, ecx + WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xd108 // or cl, dl + LONG $0x2454b60f; BYTE $0x04 // movzx edx, byte [rsp + 4] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xd8 // or r8b, bl + WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8844 // mov byte [rdx + 2], r15b - LONG $0x03428844 // mov byte [rdx + 3], r8b + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x03468845 // mov byte [r14 + 3], r8b LONG $0x40c68348 // add rsi, 64 - LONG $0x04c28348 // add rdx, 4 - QUAD $0x000000f024948948 // mov qword [rsp + 240], rdx - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB7_109 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB7_112 - JMP LBB7_191 - -LBB7_155: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_159 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB7_157: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_157 - LONG $0x01c38349 // add r11, 1 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_138 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] -LBB7_159: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_160 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 +LBB7_140: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_146 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB7_143 + +LBB7_169: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_175 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_173 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_172: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB7_172 + +LBB7_173: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 + +LBB7_175: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_179 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax -LBB7_162: +LBB7_177: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + QUAD $0x0000008824949f0f // setg byte [rsp + 136] LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd79f0f40 // setg dil LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd69f0f41 // setg r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x0000008024949f0f // setg byte [rsp + 128] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] LONG $0x206e394c // cmp qword [rsi + 32], r13 - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x9f0f; BYTE $0xd0 // setg al LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x9f0f; BYTE $0xd3 // setg bl LONG $0x406e394c // cmp qword [rsi + 64], r13 - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] LONG $0x486e394c // cmp qword [rsi + 72], r13 - WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x506e394c // cmp qword [rsi + 80], r13 LONG $0xd19f0f41 // setg r9b LONG $0x586e394c // cmp qword [rsi + 88], r13 @@ -38843,33 +39779,33 @@ LBB7_162: LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd49f0f41 // setg r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x9f0f; BYTE $0xd1 // setg cl + WORD $0x9f0f; BYTE $0xd2 // setg dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd79f0f41 // setg r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 QUAD $0x0000014024949f0f // setg byte [rsp + 320] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 QUAD $0x0000012024949f0f // setg byte [rsp + 288] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 @@ -38879,159 +39815,177 @@ LBB7_162: LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 LONG $0xd09f0f41 // setg r8b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x78 // add dil, byte [rsp + 120] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0xd200 // add dl, dl - LONG $0x68245402 // add dl, byte [rsp + 104] - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x60 // movzx edi, byte [rsp + 96] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xd308 // or bl, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xd200 // add dl, dl - LONG $0x40245402 // add dl, byte [rsp + 64] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - WORD $0x1a88 // mov byte [rdx], bl - LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x40244c02 // add cl, byte [rsp + 64] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4a88; BYTE $0x01 // mov byte [rdx + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xc900 // add cl, cl LONG $0x40248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 320] - WORD $0xcb89 // mov ebx, ecx + WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xd108 // or cl, dl + LONG $0x2454b60f; BYTE $0x04 // movzx edx, byte [rsp + 4] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xd8 // or r8b, bl + WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8844 // mov byte [rdx + 2], r15b - LONG $0x03428844 // mov byte [rdx + 3], r8b + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x03468845 // mov byte [r14 + 3], r8b LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c28348 // add rdx, 4 - QUAD $0x000000f024948948 // mov qword [rsp + 240], rdx - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB7_162 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB7_165 - JMP LBB7_191 - -LBB7_171: - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fac5 // vmovss xmm0, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_175 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_177 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] -LBB7_173: +LBB7_179: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_184 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB7_182 + +LBB7_186: + WORD $0x8b44; BYTE $0x22 // mov r12d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_192 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_190 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB7_189: LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] LONG $0x04c68348 // add rsi, 4 LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_173 - LONG $0x01c38349 // add r11, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB7_189 -LBB7_175: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_179 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - LONG $0x2474894c; BYTE $0x78 // mov qword [rsp + 120], r14 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 +LBB7_190: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 + +LBB7_192: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_196 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000008024a48944 // mov dword [rsp + 128], r12d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax -LBB7_177: +LBB7_194: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] LONG $0x5610fac5; BYTE $0x04 // vmovss xmm2, dword [rsi + 4] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 QUAD $0x000001202494970f // seta byte [rsp + 288] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 - WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x4e10fac5; BYTE $0x08 // vmovss xmm1, dword [rsi + 8] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x0c // vmovss xmm1, dword [rsi + 12] @@ -39041,15 +39995,15 @@ LBB7_177: LONG $0x4e10fac5; BYTE $0x10 // vmovss xmm1, dword [rsi + 16] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x14 // vmovss xmm1, dword [rsi + 20] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x4e10fac5; BYTE $0x18 // vmovss xmm1, dword [rsi + 24] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x1c // vmovss xmm1, dword [rsi + 28] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x4e10fac5; BYTE $0x20 // vmovss xmm1, dword [rsi + 32] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x24 // vmovss xmm1, dword [rsi + 36] @@ -39059,7 +40013,7 @@ LBB7_177: LONG $0x4e10fac5; BYTE $0x28 // vmovss xmm1, dword [rsi + 40] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x2c // vmovss xmm1, dword [rsi + 44] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x4e10fac5; BYTE $0x30 // vmovss xmm1, dword [rsi + 48] @@ -39067,19 +40021,19 @@ LBB7_177: LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x6e10fac5; BYTE $0x38 // vmovss xmm5, dword [rsi + 56] LONG $0x7610fac5; BYTE $0x3c // vmovss xmm6, dword [rsi + 60] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x46107ac5; BYTE $0x40 // vmovss xmm8, dword [rsi + 64] LONG $0x4e107ac5; BYTE $0x44 // vmovss xmm9, dword [rsi + 68] LONG $0xd82ef8c5 // vucomiss xmm3, xmm0 LONG $0x56107ac5; BYTE $0x48 // vmovss xmm10, dword [rsi + 72] LONG $0x5e107ac5; BYTE $0x4c // vmovss xmm11, dword [rsi + 76] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x66107ac5; BYTE $0x50 // vmovss xmm12, dword [rsi + 80] LONG $0x6e107ac5; BYTE $0x54 // vmovss xmm13, dword [rsi + 84] LONG $0xe82ef8c5 // vucomiss xmm5, xmm0 LONG $0x76107ac5; BYTE $0x58 // vmovss xmm14, dword [rsi + 88] LONG $0x5610fac5; BYTE $0x5c // vmovss xmm2, dword [rsi + 92] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x5e10fac5; BYTE $0x60 // vmovss xmm3, dword [rsi + 96] LONG $0x6610fac5; BYTE $0x64 // vmovss xmm4, dword [rsi + 100] LONG $0xf02ef8c5 // vucomiss xmm6, xmm0 @@ -39089,7 +40043,7 @@ LBB7_177: LONG $0x4e10fac5; BYTE $0x70 // vmovss xmm1, dword [rsi + 112] LONG $0x6e10fac5; BYTE $0x74 // vmovss xmm5, dword [rsi + 116] LONG $0xc02e78c5 // vucomiss xmm8, xmm0 - QUAD $0x000000802494970f // seta byte [rsp + 128] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0xc82e78c5 // vucomiss xmm9, xmm0 WORD $0x970f; BYTE $0xd1 // seta cl LONG $0xd02e78c5 // vucomiss xmm10, xmm0 @@ -39101,68 +40055,68 @@ LBB7_177: LONG $0xe82e78c5 // vucomiss xmm13, xmm0 LONG $0xd6970f41 // seta r14b LONG $0xf02e78c5 // vucomiss xmm14, xmm0 - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 LONG $0xd1970f41 // seta r9b LONG $0xd82ef8c5 // vucomiss xmm3, xmm0 - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0xe02ef8c5 // vucomiss xmm4, xmm0 LONG $0xd7970f41 // seta r15b LONG $0xf02ef8c5 // vucomiss xmm6, xmm0 - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0xf82ef8c5 // vucomiss xmm7, xmm0 LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0xe82ef8c5 // vucomiss xmm5, xmm0 LONG $0x4e10fac5; BYTE $0x78 // vmovss xmm1, dword [rsi + 120] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x2454970f; BYTE $0x04 // seta byte [rsp + 4] LONG $0x4e10fac5; BYTE $0x7c // vmovss xmm1, dword [rsi + 124] LONG $0x80ee8348 // sub rsi, -128 LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdb00 // add bl, bl - LONG $0x20249c02; WORD $0x0001; BYTE $0x00 // add bl, byte [rsp + 288] + WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0xd200 // add dl, dl + LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl + WORD $0x0841; BYTE $0xd5 // or r13b, dl LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xec // or r12b, r13b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - WORD $0x8941; BYTE $0xdc // mov r12d, ebx - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - LONG $0x64b60f44; WORD $0x3024 // movzx r12d, byte [rsp + 48] + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xe2 // or dl, r12b + WORD $0x8941; BYTE $0xd4 // mov r12d, edx + LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] LONG $0x06e4c041 // shl r12b, 6 - LONG $0x6cb60f44; WORD $0x1824 // movzx r13d, byte [rsp + 24] + LONG $0x6cb60f44; WORD $0x3024 // movzx r13d, byte [rsp + 48] LONG $0x07e5c041 // shl r13b, 7 WORD $0x0845; BYTE $0xe5 // or r13b, r12b WORD $0xc000 // add al, al LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] - LONG $0x64b60f44; WORD $0x1024 // movzx r12d, byte [rsp + 16] + LONG $0x64b60f44; WORD $0x0824 // movzx r12d, byte [rsp + 8] LONG $0x02e4c041 // shl r12b, 2 WORD $0x0841; BYTE $0xc4 // or r12b, al WORD $0x8944; BYTE $0xe0 // mov eax, r12d QUAD $0x00014024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 320] LONG $0x03e4c041 // shl r12b, 3 WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0xc308 // or bl, al - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0x0841; BYTE $0xd5 // or r13b, dl + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xc208 // or dl, al + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e3c041 // shl r11b, 7 WORD $0x0841; BYTE $0xc3 // or r11b, al WORD $0xc900 // add cl, cl - LONG $0x80248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 128] + LONG $0x50244c02 // add cl, byte [rsp + 80] LONG $0x02e7c040 // shl dil, 2 WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x03e0c041 // shl r8b, 3 @@ -39170,359 +40124,183 @@ LBB7_177: LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e6c041 // shl r14b, 5 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0841; BYTE $0xdb // or r11b, bl - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - WORD $0x8844; BYTE $0x28 // mov byte [rax], r13b - WORD $0x0845; BYTE $0xf1 // or r9b, r14b - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x58 // add r15b, byte [rsp + 88] - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf9 // or cl, r15b - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x01588844 // mov byte [rax + 1], r11b - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - LONG $0x02488844 // mov byte [rax + 2], r9b - WORD $0xca08 // or dl, cl - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x04c08348 // add rax, 4 - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - LONG $0x24448348; WORD $0xff78 // add qword [rsp + 120], -1 - JNE LBB7_177 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - -LBB7_179: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB7_191 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB7_184 - WORD $0x3145; BYTE $0xd2 // xor r10d, r10d - JMP LBB7_182 - -LBB7_42: - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_46 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB7_44: - WORD $0x3a44; BYTE $0x36 // cmp r14b, byte [rsi] - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0xd219 // sbb edx, edx - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_44 - LONG $0x01c38349 // add r11, 1 - -LBB7_46: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_47 - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x24748944; BYTE $0x04 // mov dword [rsp + 4], r14d - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000017824bc894c // mov qword [rsp + 376], r15 - JB LBB7_49 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JAE LBB7_52 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB7_52 - -LBB7_49: - WORD $0xc031 // xor eax, eax - QUAD $0x0000016824848948 // mov qword [rsp + 360], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x00000160249c894c // mov qword [rsp + 352], r11 - -LBB7_55: - QUAD $0x0000016824bc2b4c // sub r15, qword [rsp + 360] - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - -LBB7_56: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b - QUAD $0x000001402494970f // seta byte [rsp + 320] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b - LONG $0xd0970f41 // seta r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd7970f41 // seta r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b - LONG $0xd5970f41 // seta r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x970f; BYTE $0xd0 // seta al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b - LONG $0xd3970f41 // seta r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b - QUAD $0x000001202494970f // seta byte [rsp + 288] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b - WORD $0x970f; BYTE $0xd2 // seta dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b - LONG $0xd6970f40 // seta sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b - LONG $0xd7970f40 // seta dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b - LONG $0xd2970f41 // seta r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b - LONG $0xd4970f41 // seta r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b - QUAD $0x000000802494970f // seta byte [rsp + 128] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b - LONG $0xd1970f41 // seta r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b - QUAD $0x000001002494970f // seta byte [rsp + 256] - LONG $0x11713844 // cmp byte [rcx + 17], r14b - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0x13713844 // cmp byte [rcx + 19], r14b - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0x14713844 // cmp byte [rcx + 20], r14b - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x15713844 // cmp byte [rcx + 21], r14b - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd6970f41 // seta r14b - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x000000f02494970f // seta byte [rsp + 240] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x04245c8b // mov ebx, dword [rsp + 4] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x970f; BYTE $0xd3 // seta bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - QUAD $0x0000014024840244 // add r8b, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b - WORD $0xd200 // add dl, dl - LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xc000 // add al, al - LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000016024b48b48 // mov rsi, qword [rsp + 352] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x18 // movzx edi, byte [rsp + 24] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0841; BYTE $0xd3 // or r11b, dl + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xc1 // or r9b, al + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + WORD $0x8844; BYTE $0x28 // mov byte [rax], r13b + WORD $0x0845; BYTE $0xf1 // or r9b, r14b + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x78 // add r15b, byte [rsp + 120] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0x0844; BYTE $0xf8 // or al, r15b + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x10 // movzx edx, byte [rsp + 16] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xc808 // or al, cl + LONG $0x015e8845 // mov byte [r14 + 1], r11b + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xd308 // or bl, dl + WORD $0xcb08 // or bl, cl + LONG $0x024e8845 // mov byte [r14 + 2], r9b WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000016024b48948 // mov qword [rsp + 352], rsi - LONG $0x24448348; WORD $0xff78 // add qword [rsp + 120], -1 - JNE LBB7_56 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000017824bc8b4c // mov r15, qword [rsp + 376] - JMP LBB7_58 + LONG $0x035e8841 // mov byte [r14 + 3], bl + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 + JNE LBB7_194 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0000008024a48b44 // mov r12d, dword [rsp + 128] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] -LBB7_129: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_133 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB7_131: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_131 - LONG $0x01c38349 // add r11, 1 +LBB7_196: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_201 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + JMP LBB7_199 -LBB7_133: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB7_134 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 +LBB7_58: + WORD $0x8a44; BYTE $0x2a // mov r13b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_59 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_61 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 -LBB7_136: - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 +LBB7_67: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3a44; BYTE $0x2e // cmp r13b, byte [rsi] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x075a8d48 // lea rbx, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xda490f48 // cmovns rbx, rdx + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001be; BYTE $0x00 // mov esi, 1 + WORD $0xe6d3 // shl esi, cl + WORD $0x2044; BYTE $0xde // and sil, r11b + WORD $0x3044; BYTE $0xce // xor sil, r9b + LONG $0x1e348841 // mov byte [r14 + rbx], sil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc08348 // add rax, -1 + JNE LBB7_67 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB7_63 + JMP LBB7_210 + +LBB7_150: + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_156 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_154 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_153: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB7_153 + +LBB7_154: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 + LONG $0x01c68349 // add r14, 1 + +LBB7_156: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_160 + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + +LBB7_158: + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + QUAD $0x0000008824949f0f // setg byte [rsp + 136] LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd79f0f40 // setg dil LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd69f0f41 // setg r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x0000008024949f0f // setg byte [rsp + 128] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] LONG $0x106e3944 // cmp dword [rsi + 16], r13d - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x9f0f; BYTE $0xd0 // setg al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d WORD $0x9f0f; BYTE $0xd3 // setg bl LONG $0x206e3944 // cmp dword [rsi + 32], r13d - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] LONG $0x246e3944 // cmp dword [rsi + 36], r13d - WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x286e3944 // cmp dword [rsi + 40], r13d LONG $0xd19f0f41 // setg r9b LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d @@ -39532,33 +40310,33 @@ LBB7_136: LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd49f0f41 // setg r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x9f0f; BYTE $0xd1 // setg cl + WORD $0x9f0f; BYTE $0xd2 // setg dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] LONG $0x486e3944 // cmp dword [rsi + 72], r13d - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd79f0f41 // setg r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d QUAD $0x0000014024949f0f // setg byte [rsp + 320] LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] LONG $0x706e3944 // cmp dword [rsi + 112], r13d QUAD $0x0000012024949f0f // setg byte [rsp + 288] LONG $0x746e3944 // cmp dword [rsi + 116], r13d @@ -39568,66 +40346,66 @@ LBB7_136: LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d LONG $0xd09f0f41 // setg r8b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x78 // add dil, byte [rsp + 120] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0xd200 // add dl, dl - LONG $0x68245402 // add dl, byte [rsp + 104] - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + LONG $0x247cb60f; BYTE $0x60 // movzx edi, byte [rsp + 96] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xd308 // or bl, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xd200 // add dl, dl - LONG $0x40245402 // add dl, byte [rsp + 64] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x40244c02 // add cl, byte [rsp + 64] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl - WORD $0x0841; BYTE $0xd7 // or r15b, dl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xc900 // add cl, cl LONG $0x40248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 320] WORD $0xca89 // mov edx, ecx @@ -39635,7 +40413,7 @@ LBB7_136: WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx @@ -39651,259 +40429,531 @@ LBB7_136: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03438845 // mov byte [r11 + 3], r8b + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x03468845 // mov byte [r14 + 3], r8b LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c38349 // add r11, 4 - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB7_136 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB7_139 - JMP LBB7_191 - -LBB7_18: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB7_191 - -LBB7_123: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB7_127 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_158 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + +LBB7_160: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_210 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_165 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_125 + JMP LBB7_163 -LBB7_9: - QUAD $0x00000160249c894c // mov qword [rsp + 352], r11 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi +LBB7_5: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB7_90 -LBB7_76: - LONG $0x05e5c149 // shl r13, 5 - WORD $0x394d; BYTE $0xfd // cmp r13, r15 - JGE LBB7_191 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xe8 // sub r8, r13 - WORD $0xf749; BYTE $0xd5 // not r13 - WORD $0x014d; BYTE $0xfd // add r13, r15 - JNE LBB7_79 - WORD $0xf631 // xor esi, esi - JMP LBB7_82 - -LBB7_27: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB7_191 +LBB7_59: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB7_64 -LBB7_149: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB7_153 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_151 +LBB7_87: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 LBB7_89: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB7_191 - -LBB7_94: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB7_100 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_96 + LONG $0x01c68349 // add r14, 1 -LBB7_107: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB7_191 +LBB7_90: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_91 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x246c8944; BYTE $0x04 // mov dword [rsp + 4], r13d + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x00000168248c8948 // mov qword [rsp + 360], rcx + JB LBB7_95 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB7_98 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB7_98 -LBB7_112: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB7_117 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_114 +LBB7_95: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 -LBB7_160: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB7_191 +LBB7_101: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x00000080248c8948 // mov qword [rsp + 128], rcx -LBB7_165: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB7_169 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_167 +LBB7_102: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + QUAD $0x0000014024949f0f // setg byte [rsp + 320] + LONG $0x016e3844 // cmp byte [rsi + 1], r13b + LONG $0xd09f0f41 // setg r8b + LONG $0x026e3844 // cmp byte [rsi + 2], r13b + LONG $0xd69f0f41 // setg r14b + LONG $0x036e3844 // cmp byte [rsi + 3], r13b + LONG $0xd59f0f41 // setg r13b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4638; BYTE $0x04 // cmp byte [rsi + 4], al + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4638; BYTE $0x05 // cmp byte [rsi + 5], al + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4638; BYTE $0x06 // cmp byte [rsi + 6], al + QUAD $0x0000008824949f0f // setg byte [rsp + 136] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4638; BYTE $0x07 // cmp byte [rsi + 7], al + LONG $0xd39f0f41 // setg r11b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4638; BYTE $0x08 // cmp byte [rsi + 8], al + QUAD $0x0000012024949f0f // setg byte [rsp + 288] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4638; BYTE $0x09 // cmp byte [rsi + 9], al + WORD $0x9f0f; BYTE $0xd2 // setg dl + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4638; BYTE $0x0a // cmp byte [rsi + 10], al + LONG $0xd69f0f40 // setg sil + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd79f0f40 // setg dil + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd29f0f41 // setg r10b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + LONG $0xd49f0f41 // setg r12b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd19f0f41 // setg r9b + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x0000010024949f0f // setg byte [rsp + 256] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd79f0f41 // setg r15b + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + QUAD $0x000000f024949f0f // setg byte [rsp + 240] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + QUAD $0x0000014024840244 // add r8b, byte [rsp + 320] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xd200 // add dl, dl + LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x246c8b44; BYTE $0x04 // mov r13d, dword [rsp + 4] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2454b60f; BYTE $0x18 // movzx edx, byte [rsp + 24] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xd3 // or r11b, dl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc000 // add al, al + LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + QUAD $0x0000016024bc8b48 // mov rdi, qword [rsp + 352] + WORD $0x8844; BYTE $0x1f // mov byte [rdi], r11b + LONG $0x2474b60f; BYTE $0x28 // movzx esi, byte [rsp + 40] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014f8844 // mov byte [rdi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x10 // movzx edx, byte [rsp + 16] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x027f8844 // mov byte [rdi + 2], r15b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000016024bc8948 // mov qword [rsp + 352], rdi + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_102 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x00000168248c8b48 // mov rcx, qword [rsp + 360] + JMP LBB7_104 -LBB7_47: - QUAD $0x00000160249c894c // mov qword [rsp + 352], r11 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi +LBB7_91: + QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB7_58: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB7_191 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB7_61 - WORD $0xc031 // xor eax, eax - JMP LBB7_64 +LBB7_104: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB7_210 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB7_107 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB7_110 -LBB7_134: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB7_191 - -LBB7_139: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB7_143 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_141 +LBB7_61: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_210 -LBB7_186: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xd2 // xor r10d, r10d - WORD $0x894d; BYTE $0xde // mov r14, r11 +LBB7_63: + LONG $0x01c68349 // add r14, 1 -LBB7_187: - LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] - LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xd7 // mov rdi, r10 - LONG $0x03efc148 // shr rdi, 3 - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - LONG $0x14b60f41; BYTE $0x3e // movzx edx, byte [r14 + rdi] - WORD $0xd030 // xor al, dl - WORD $0xc320 // and bl, al - WORD $0xd330 // xor bl, dl - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c28349 // add r10, 2 - LONG $0x4e10fbc5; BYTE $0x08 // vmovsd xmm1, qword [rsi + 8] - LONG $0x10c68348 // add rsi, 16 - LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl - WORD $0x394d; BYTE $0xd1 // cmp r9, r10 - JNE LBB7_187 +LBB7_64: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_65 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x246c8944; BYTE $0x04 // mov dword [rsp + 4], r13d + QUAD $0x000000f824bc894c // mov qword [rsp + 248], r15 + QUAD $0x00000178248c8948 // mov qword [rsp + 376], rcx + JB LBB7_69 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB7_72 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB7_72 -LBB7_188: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 - LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] - LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - JMP LBB7_190 +LBB7_69: + WORD $0xc031 // xor eax, eax + QUAD $0x0000016824848948 // mov qword [rsp + 360], rax + WORD $0x8949; BYTE $0xfb // mov r11, rdi + QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 -LBB7_184: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xd2 // xor r10d, r10d - WORD $0x894d; BYTE $0xde // mov r14, r11 +LBB7_75: + QUAD $0x00000168248c2b48 // sub rcx, qword [rsp + 360] + QUAD $0x00000080248c8948 // mov qword [rsp + 128], rcx -LBB7_185: - LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] - LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xd7 // mov rdi, r10 - LONG $0x03efc148 // shr rdi, 3 - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - LONG $0x14b60f41; BYTE $0x3e // movzx edx, byte [r14 + rdi] - WORD $0xd030 // xor al, dl - WORD $0xc320 // and bl, al - WORD $0xd330 // xor bl, dl - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c28349 // add r10, 2 - LONG $0x4e10fac5; BYTE $0x04 // vmovss xmm1, dword [rsi + 4] - LONG $0x08c68348 // add rsi, 8 - LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl - WORD $0x394d; BYTE $0xd1 // cmp r9, r10 - JNE LBB7_185 +LBB7_76: + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + WORD $0x3845; BYTE $0x2b // cmp byte [r11], r13b + QUAD $0x000001402494970f // seta byte [rsp + 320] + LONG $0x016b3845 // cmp byte [r11 + 1], r13b + LONG $0xd0970f41 // seta r8b + LONG $0x026b3845 // cmp byte [r11 + 2], r13b + LONG $0xd6970f41 // seta r14b + LONG $0x036b3845 // cmp byte [r11 + 3], r13b + LONG $0xd5970f41 // seta r13b + LONG $0x0424448b // mov eax, dword [rsp + 4] + LONG $0x04433841 // cmp byte [r11 + 4], al + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x0424448b // mov eax, dword [rsp + 4] + LONG $0x05433841 // cmp byte [r11 + 5], al + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0x0424448b // mov eax, dword [rsp + 4] + LONG $0x06433841 // cmp byte [r11 + 6], al + QUAD $0x000000882494970f // seta byte [rsp + 136] + LONG $0x0424448b // mov eax, dword [rsp + 4] + LONG $0x07433841 // cmp byte [r11 + 7], al + LONG $0xd3970f41 // seta r11b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + QUAD $0x000001202494970f // seta byte [rsp + 288] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al + WORD $0x970f; BYTE $0xd2 // seta dl + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0xd6970f40 // seta sil + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd7970f40 // seta dil + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd2970f41 // seta r10b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + LONG $0xd4970f41 // seta r12b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd1970f41 // seta r9b + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000001002494970f // seta byte [rsp + 256] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd7970f41 // seta r15b + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + QUAD $0x000000f02494970f // seta byte [rsp + 240] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x04245c8b // mov ebx, dword [rsp + 4] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + QUAD $0x0000014024840244 // add r8b, byte [rsp + 320] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xd200 // add dl, dl + LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x246c8b44; BYTE $0x04 // mov r13d, dword [rsp + 4] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2454b60f; BYTE $0x10 // movzx edx, byte [rsp + 16] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xd3 // or r11b, dl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc000 // add al, al + LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + QUAD $0x0000016024b48b48 // mov rsi, qword [rsp + 352] + WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b + LONG $0x247cb60f; BYTE $0x28 // movzx edi, byte [rsp + 40] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xff // or r15b, dil + LONG $0x014e8844 // mov byte [rsi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x18 // movzx edx, byte [rsp + 24] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x027e8844 // mov byte [rsi + 2], r15b + WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl + LONG $0x20598d4c // lea r11, [rcx + 32] + LONG $0x04c68348 // add rsi, 4 + QUAD $0x0000016024b48948 // mov qword [rsp + 352], rsi + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB7_76 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] + JMP LBB7_78 -LBB7_182: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 - LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] - LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 +LBB7_65: + QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 + WORD $0x8949; BYTE $0xfb // mov r11, rdi -LBB7_190: - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xd2 // mov rdx, r10 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x13348a41 // mov sil, byte [r11 + rdx] - LONG $0x07e28041 // and r10b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x131c8841 // mov byte [r11 + rdx], bl - JMP LBB7_191 +LBB7_78: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB7_210 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB7_81 + WORD $0xc031 // xor eax, eax + JMP LBB7_84 -LBB7_127: +LBB7_148: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB7_128: +LBB7_149: WORD $0x3b44; BYTE $0x2e // cmp r13d, dword [rsi] WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x17 // movzx r10d, byte [r15 + rdx] + LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 @@ -39911,7 +40961,7 @@ LBB7_128: WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x17048841 // mov byte [r15 + rdx], al + LONG $0x16048841 // mov byte [r14 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x046e3b44 // cmp r13d, dword [rsi + 4] LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -39922,84 +40972,71 @@ LBB7_128: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x171c8841 // mov byte [r15 + rdx], bl + LONG $0x161c8841 // mov byte [r14 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB7_128 + JNE LBB7_149 -LBB7_125: +LBB7_22: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 + JE LBB7_210 WORD $0x3b44; BYTE $0x2e // cmp r13d, dword [rsi] - JMP LBB7_98 + JMP LBB7_127 -LBB7_79: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - QUAD $0x00000160249c8b4c // mov r11, qword [rsp + 352] +LBB7_203: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d -LBB7_80: - LONG $0x34343845 // cmp byte [r12 + rsi], r14b - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi +LBB7_204: + LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] + LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xd7 // mov rdi, r10 LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0x8944; BYTE $0xd1 // mov ecx, r10d WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743845; BYTE $0x01 // cmp byte [r12 + rsi + 1], r14b - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + LONG $0x14b60f41; BYTE $0x3e // movzx edx, byte [r14 + rdi] + WORD $0xd030 // xor al, dl + WORD $0xc320 // and bl, al WORD $0xd330 // xor bl, dl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c28349 // add r10, 2 + LONG $0x4e10fbc5; BYTE $0x08 // vmovsd xmm1, qword [rsi + 8] + LONG $0x10c68348 // add rsi, 16 + LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB7_80 - WORD $0x0149; BYTE $0xf4 // add r12, rsi + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB7_204 -LBB7_82: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 - LONG $0x24343845 // cmp byte [r12], r14b - WORD $0x9f0f; BYTE $0xd0 // setg al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - QUAD $0x0000016024848b4c // mov r8, qword [rsp + 352] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB7_191 +LBB7_205: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_210 + LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] + LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + JMP LBB7_207 -LBB7_153: +LBB7_167: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB7_154: +LBB7_168: WORD $0x3b4c; BYTE $0x2e // cmp r13, qword [rsi] WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x17 // movzx r10d, byte [r15 + rdx] + LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 @@ -40007,7 +41044,7 @@ LBB7_154: WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x17048841 // mov byte [r15 + rdx], al + LONG $0x16048841 // mov byte [r14 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x086e3b4c // cmp r13, qword [rsi + 8] LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -40018,28 +41055,27 @@ LBB7_154: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x171c8841 // mov byte [r15 + rdx], bl + LONG $0x161c8841 // mov byte [r14 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB7_154 + JNE LBB7_168 -LBB7_151: +LBB7_40: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 + JE LBB7_210 WORD $0x3b4c; BYTE $0x2e // cmp r13, qword [rsi] - JMP LBB7_98 + JMP LBB7_127 -LBB7_100: +LBB7_128: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB7_101: +LBB7_129: LONG $0x2e3b4466 // cmp r13w, word [rsi] WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x17 // movzx r10d, byte [r15 + rdx] + LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 @@ -40047,7 +41083,7 @@ LBB7_101: WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x17048841 // mov byte [r15 + rdx], al + LONG $0x16048841 // mov byte [r14 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] LONG $0x04768d48 // lea rsi, [rsi + 4] @@ -40058,16 +41094,16 @@ LBB7_101: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x171c8841 // mov byte [r15 + rdx], bl + LONG $0x161c8841 // mov byte [r14 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB7_101 + JNE LBB7_129 -LBB7_96: +LBB7_125: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 + JE LBB7_210 LONG $0x2e3b4466 // cmp r13w, word [rsi] -LBB7_98: +LBB7_127: WORD $0xc019 // sbb eax, eax WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 @@ -40078,21 +41114,20 @@ LBB7_98: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - JMP LBB7_99 + JMP LBB7_209 -LBB7_117: +LBB7_146: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB7_118: +LBB7_147: LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -40100,7 +41135,7 @@ LBB7_118: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] @@ -40112,29 +41147,28 @@ LBB7_118: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB7_118 + JNE LBB7_147 -LBB7_114: +LBB7_143: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 + JE LBB7_210 LONG $0x2e394466 // cmp word [rsi], r13w - JMP LBB7_116 + JMP LBB7_145 -LBB7_169: +LBB7_184: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB7_170: +LBB7_185: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -40142,7 +41176,7 @@ LBB7_170: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -40154,82 +41188,82 @@ LBB7_170: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB7_170 + JNE LBB7_185 -LBB7_167: +LBB7_182: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 + JE LBB7_210 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - JMP LBB7_116 + JMP LBB7_145 -LBB7_61: +LBB7_201: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 - WORD $0xc031 // xor eax, eax - QUAD $0x0000016024948b4c // mov r10, qword [rsp + 352] + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d -LBB7_62: - LONG $0x04343a45 // cmp r14b, byte [r12 + rax] - WORD $0xf619 // sbb esi, esi - WORD $0x8948; BYTE $0xc7 // mov rdi, rax +LBB7_202: + LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] + LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xd7 // mov rdi, r10 LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax + WORD $0x8944; BYTE $0xd1 // mov ecx, r10d WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x1cb60f41; BYTE $0x3a // movzx ebx, byte [r10 + rdi] - WORD $0x3040; BYTE $0xde // xor sil, bl - WORD $0x2040; BYTE $0xf2 // and dl, sil - WORD $0xda30 // xor dl, bl - LONG $0x3a148841 // mov byte [r10 + rdi], dl - LONG $0x04743a45; BYTE $0x01 // cmp r14b, byte [r12 + rax + 1] - LONG $0x02408d48 // lea rax, [rax + 2] - WORD $0xf619 // sbb esi, esi - WORD $0x3040; BYTE $0xd6 // xor sil, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil + LONG $0x14b60f41; BYTE $0x3e // movzx edx, byte [r14 + rdi] + WORD $0xd030 // xor al, dl + WORD $0xc320 // and bl, al WORD $0xd330 // xor bl, dl - LONG $0x3a1c8841 // mov byte [r10 + rdi], bl - WORD $0x3949; BYTE $0xc1 // cmp r9, rax - JNE LBB7_62 - WORD $0x0149; BYTE $0xc4 // add r12, rax + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x02c28349 // add r10, 2 + LONG $0x4e10fac5; BYTE $0x04 // vmovss xmm1, dword [rsi + 4] + LONG $0x08c68348 // add rsi, 8 + LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB7_202 -LBB7_64: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 - LONG $0x24343a45 // cmp r14b, byte [r12] - WORD $0xd219 // sbb edx, edx - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - LONG $0x03eec148 // shr rsi, 3 - QUAD $0x0000016024848b4c // mov r8, qword [rsp + 352] - LONG $0x303c8a41 // mov dil, byte [r8 + rsi] - WORD $0x0724 // and al, 7 +LBB7_199: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_210 + LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] + LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 + +LBB7_207: + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x16348a41 // mov sil, byte [r14 + rdx] + LONG $0x07e28041 // and r10b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xc189 // mov ecx, eax - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xfa // xor dl, dil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x301c8841 // mov byte [r8 + rsi], bl - JMP LBB7_191 + WORD $0x8944; BYTE $0xd1 // mov ecx, r10d + JMP LBB7_208 -LBB7_143: +LBB7_165: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB7_144: +LBB7_166: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -40237,7 +41271,7 @@ LBB7_144: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -40249,16 +41283,16 @@ LBB7_144: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB7_144 + JNE LBB7_166 -LBB7_141: +LBB7_163: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_191 + JE LBB7_210 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d -LBB7_116: +LBB7_145: WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xda // mov rdx, r11 @@ -40267,1998 +41301,2106 @@ LBB7_116: LONG $0x07e38041 // and r11b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + +LBB7_208: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al -LBB7_99: +LBB7_209: WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x161c8841 // mov byte [r14 + rdx], bl -LBB7_191: +LBB7_210: MOVQ 1344(SP), SP VZEROUPPER RET -LBB7_70: - LONG $0xe0e58349 // and r13, -32 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 +LBB7_107: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x00000160249c8b4c // mov r11, qword [rsp + 352] + +LBB7_108: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e2c3846 // cmp byte [rsi + r9], r13b + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x066c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r13b + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB7_108 + WORD $0x014c; BYTE $0xce // add rsi, r9 + +LBB7_110: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_210 + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + WORD $0x9f0f; BYTE $0xd0 // setg al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + QUAD $0x0000016024848b4c // mov r8, qword [rsp + 352] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + JMP LBB7_210 + +LBB7_81: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xc031 // xor eax, eax + QUAD $0x0000016024948b4c // mov r10, qword [rsp + 352] + +LBB7_82: + LONG $0x032c3a45 // cmp r13b, byte [r11 + rax] + WORD $0xf619 // sbb esi, esi + WORD $0x8948; BYTE $0xc7 // mov rdi, rax + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x1cb60f41; BYTE $0x3a // movzx ebx, byte [r10 + rdi] + WORD $0x3040; BYTE $0xde // xor sil, bl + WORD $0x2040; BYTE $0xf2 // and dl, sil + WORD $0xda30 // xor dl, bl + LONG $0x3a148841 // mov byte [r10 + rdi], dl + LONG $0x036c3a45; BYTE $0x01 // cmp r13b, byte [r11 + rax + 1] + LONG $0x02408d48 // lea rax, [rax + 2] + WORD $0xf619 // sbb esi, esi + WORD $0x3040; BYTE $0xd6 // xor sil, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x2040; BYTE $0xf3 // and bl, sil + WORD $0xd330 // xor bl, dl + LONG $0x3a1c8841 // mov byte [r10 + rdi], bl + WORD $0x3949; BYTE $0xc1 // cmp r9, rax + JNE LBB7_82 + WORD $0x0149; BYTE $0xc3 // add r11, rax + +LBB7_84: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_210 + WORD $0x3a45; BYTE $0x2b // cmp r13b, byte [r11] + WORD $0xd219 // sbb edx, edx + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + LONG $0x03eec148 // shr rsi, 3 + QUAD $0x0000016024848b4c // mov r8, qword [rsp + 352] + LONG $0x303c8a41 // mov dil, byte [r8 + rsi] + WORD $0x0724 // and al, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xc189 // mov ecx, eax + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xfa // xor dl, dil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x301c8841 // mov byte [r8 + rsi], bl + JMP LBB7_210 + +LBB7_98: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000024024848948 // mov qword [rsp + 576], rax - QUAD $0x0000018024ac894c // mov qword [rsp + 384], r13 - LONG $0xab048d4b // lea rax, [r11 + 4*r13] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000016024848948 // mov qword [rsp + 352], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc5 // vmovd xmm0, r13d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 -LBB7_71: +LBB7_99: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000017024848948 // mov qword [rsp + 368], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + QUAD $0x000000e824848948 // mov qword [rsp + 232], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] - WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x1644b60f; BYTE $0x01 // movzx eax, byte [rsi + rdx + 1] + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x1644b60f; BYTE $0x02 // movzx eax, byte [rsi + rdx + 2] + LONG $0x0f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rcx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000220248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 544], xmm1 - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x0f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rcx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x0f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rcx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x0f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rcx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] - QUAD $0x000000d024948948 // mov qword [rsp + 208], rdx + LONG $0x0f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rcx + 6] + QUAD $0x000000c0248c8948 // mov qword [rsp + 192], rcx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x0f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rcx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02400d48; WORD $0x0000 // or rax, 576 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + WORD $0x8949; BYTE $0xdc // mov r12, rbx + LONG $0x40cc8149; WORD $0x0002; BYTE $0x00 // or r12, 576 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02600d48; WORD $0x0000 // or rax, 608 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02800d48; WORD $0x0000 // or rax, 640 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x80cf8149; WORD $0x0002; BYTE $0x00 // or r15, 640 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0xa0cb8149; WORD $0x0002; BYTE $0x00 // or r11, 672 - QUAD $0x000000b8249c894c // mov qword [rsp + 184], r11 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - LONG $0xc0c88149; WORD $0x0002; BYTE $0x00 // or r8, 704 - QUAD $0x000000882484894c // mov qword [rsp + 136], r8 - WORD $0x8948; BYTE $0xda // mov rdx, rbx - LONG $0xe0ca8148; WORD $0x0002; BYTE $0x00 // or rdx, 736 - QUAD $0x000000b024948948 // mov qword [rsp + 176], rdx - WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0x00cc8149; WORD $0x0003; BYTE $0x00 // or r12, 768 - QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 + LONG $0xa0cf8149; WORD $0x0002; BYTE $0x00 // or r15, 672 + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x20ce8149; WORD $0x0003; BYTE $0x00 // or r14, 800 - QUAD $0x000000a824b4894c // mov qword [rsp + 168], r14 + LONG $0xc0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 704 + LONG $0x2474894c; BYTE $0x60 // mov qword [rsp + 96], r14 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02e00d48; WORD $0x0000 // or rax, 736 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x00cb8149; WORD $0x0003; BYTE $0x00 // or r11, 768 + QUAD $0x000000d8249c894c // mov qword [rsp + 216], r11 WORD $0x8949; BYTE $0xda // mov r10, rbx - LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 - LONG $0x2454894c; BYTE $0x28 // mov qword [rsp + 40], r10 + LONG $0x20ca8149; WORD $0x0003; BYTE $0x00 // or r10, 800 + LONG $0x2454894c; BYTE $0x58 // mov qword [rsp + 88], r10 WORD $0x8949; BYTE $0xd9 // mov r9, rbx - LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 - LONG $0x244c894c; BYTE $0x40 // mov qword [rsp + 64], r9 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03800d48; WORD $0x0000 // or rax, 896 - QUAD $0x000000d824848948 // mov qword [rsp + 216], rax - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - LONG $0xa0cf8148; WORD $0x0003; BYTE $0x00 // or rdi, 928 - LONG $0x247c8948; BYTE $0x70 // mov qword [rsp + 112], rdi - WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x40c98149; WORD $0x0003; BYTE $0x00 // or r9, 832 + LONG $0x244c894c; BYTE $0x38 // mov qword [rsp + 56], r9 + WORD $0x8948; BYTE $0xda // mov rdx, rbx + LONG $0x60ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 864 + LONG $0x24548948; BYTE $0x40 // mov qword [rsp + 64], rdx + WORD $0x8948; BYTE $0xde // mov rsi, rbx + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx QUAD $0x000000e0249c8948 // mov qword [rsp + 224], rbx + LONG $0x80ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 896 + LONG $0x24748948; BYTE $0x50 // mov qword [rsp + 80], rsi + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0xa0c88149; WORD $0x0003; BYTE $0x00 // or r8, 928 + LONG $0x2444894c; BYTE $0x48 // mov qword [rsp + 72], r8 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - LONG $0x207923c4; WORD $0x2e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + r13], 1 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - LONG $0x2031e3c4; WORD $0x1e04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + rbx], 2 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 3 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + r15], 4 - LONG $0x2079a3c4; WORD $0x1e04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + r11], 5 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + r8], 6 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + rdx], 7 - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + r12], 8 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + r14], 9 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r10], 10 - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + r9], 11 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - LONG $0x2079a3c4; WORD $0x2e04; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + r13], 12 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + rdi], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + r14], 1 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2061a3c4; WORD $0x261c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r12], 2 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + r10], 3 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - LONG $0x2061a3c4; WORD $0x1e1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + r11], 4 - QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + r8], 5 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r9], 6 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + r15], 7 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + rbx], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rdx], 12 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rdx], 13 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + rdx], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rdx], 15 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x010116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 1 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x020116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 2 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x030116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 3 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x040116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 4 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x050116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 5 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x060116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 6 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x070116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 7 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x080116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 8 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x090116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 9 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0a0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 10 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0b0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 11 - QUAD $0x0c012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 12 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0d0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 13 - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] - QUAD $0x0e012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 15 - QUAD $0x0101366c2029a3c4 // vpinsrb xmm5, xmm10, byte [rsi + r14 + 1], 1 - QUAD $0x0201266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 1], 2 - QUAD $0x0301166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 1], 3 - QUAD $0x04011e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 1], 4 - QUAD $0x0501066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 5 - QUAD $0x06010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 6 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - QUAD $0x07013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 7 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0a011e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 1], 10 - QUAD $0x0b010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 14 - LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0106442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 1], 15 + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + LONG $0x207963c4; WORD $0x1f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + rbx], 1 + QUAD $0x000000b824a4894c // mov qword [rsp + 184], r12 + LONG $0x2031a3c4; WORD $0x2704; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + r12], 2 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 4 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + r15], 5 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r14], 6 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + r13], 7 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r11], 8 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r10], 9 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r9], 10 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + rdx], 11 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + rsi], 12 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + r8], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r15], 1 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r10], 2 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r8], 3 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r14], 4 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r9], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + rax], 7 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi - LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 - QUAD $0x00050024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1280], ymm0 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rax], 8 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rcx], 9 LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x00022024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 544] - QUAD $0x010216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 2], 1 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x02020e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 2], 2 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x030216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 2], 3 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x040206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x050206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 5 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x060206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x070206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 7 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x080226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 2], 8 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x09022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 9 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0a020e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 2], 10 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0b021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 11 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0c0236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 2], 12 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x0d023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 13 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 15 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 2 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x03023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 5 - QUAD $0x0602065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 2], 6 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x07023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 7 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x08021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x09021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 9 + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rdx], 10 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rsi], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rbx], 12 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rbx], 13 + LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + LONG $0x2061a3c4; WORD $0x2f1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + r13], 14 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rbx], 15 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x01011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 1 + QUAD $0x020127642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 1], 2 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x030127642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 1], 3 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x04011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 4 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x050127642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 1], 5 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x06011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 6 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x07011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 7 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x08011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 8 LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0a021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 10 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0b02065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 2], 11 + QUAD $0x09011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 9 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x0a011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 10 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0b0127642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 1], 11 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0c011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 12 LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x010316642021e3c4 // vpinsrb xmm4, xmm11, byte [rsi + rdx + 3], 1 - QUAD $0x02030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 2 - QUAD $0x030316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 3 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x04030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 4 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x05030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 5 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x06030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 6 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x070306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 7 - QUAD $0x080326642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 3], 8 - QUAD $0x09032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 9 - QUAD $0x0a030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 10 - QUAD $0x0b031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 11 - QUAD $0x0c0336642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 3], 12 - QUAD $0x0d033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 13 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0e0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 14 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0f030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0203066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 2 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x0303166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 3], 3 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x04033e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 3], 4 + QUAD $0x0d011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 13 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0e011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 14 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0f011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 15 + QUAD $0x01013f6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r15 + 1], 1 + QUAD $0x0201176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 2 + QUAD $0x0301076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 3 + QUAD $0x0401376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x06010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 6 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x07011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 7 + QUAD $0x0801076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 8 + QUAD $0x09010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 9 + QUAD $0x0a01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 10 + QUAD $0x0b01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0503066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 5 + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + QUAD $0x0e012f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 1], 14 + LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax + LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 + QUAD $0x00050024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1280], ymm0 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xd06e79c5 // vmovd xmm10, eax + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x00022024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 544] + QUAD $0x010217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 1 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x02021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x030207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0603066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 6 - QUAD $0x07033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 7 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x08031e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 3], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0903066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x070237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 7 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x080207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 8 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x090227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 9 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x0a021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 11 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x0c020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 12 + QUAD $0x0d0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 13 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x0e023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] + QUAD $0x01020f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 2], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0202075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0302075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 3 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x0402075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 2], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0502075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 5 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 + QUAD $0x0602075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0702075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 7 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0802175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 8 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0902175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 9 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0a022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 10 + QUAD $0x0b02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 11 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0c02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 12 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x0d02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 13 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x0e02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 14 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0f02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 15 + QUAD $0x010317642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r10 + 3], 1 + QUAD $0x02031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 2 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x030337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x050337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 5 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x060337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 6 + QUAD $0x070337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 7 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x080337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 8 + QUAD $0x090327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 9 + QUAD $0x0a031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 10 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0b031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 11 + QUAD $0x0c030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 12 + WORD $0x894d; BYTE $0xcc // mov r12, r9 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 13 + QUAD $0x0e033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 14 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0f0337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 15 + QUAD $0x01030f6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rcx + 3], 1 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x02030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 2 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x03030f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 3], 3 + QUAD $0x0403076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 3], 4 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0503176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 5 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x06030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 6 + QUAD $0x0703076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 7 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0a032f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 3], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 14 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - QUAD $0x0f031e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 3], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 14 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f0307442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x010406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 1 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x020406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 2 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x030406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 3 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x04042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 4 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x05040e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 4], 5 + QUAD $0x010417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 1 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x02041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x030407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x040407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x050407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 5 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x06043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 6 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x060406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 6 - QUAD $0x070406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 7 - QUAD $0x080426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 4], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x090406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 10 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 11 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0c0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 12 - QUAD $0x0d0436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 4], 13 - QUAD $0x0e0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 14 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x0f0426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 4], 15 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0104065c2011e3c4 // vpinsrb xmm3, xmm13, byte [rsi + rax + 4], 1 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0204165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 4], 2 - QUAD $0x0304165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 3 - QUAD $0x04043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 4 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x0504165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 5 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x06043e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 4], 6 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0704365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 7 - QUAD $0x08041e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 4], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x09041e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 4], 9 + QUAD $0x070407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 7 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x080437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 10 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0b041e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 4], 11 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0c04065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 4], 12 + QUAD $0x090407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 10 + QUAD $0x0b041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 11 + QUAD $0x0c0427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 13 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0e0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 14 + QUAD $0x0f0437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 15 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x01041f5c2011e3c4 // vpinsrb xmm3, xmm13, byte [rdi + rbx + 4], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x03040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0404075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 4 + QUAD $0x0504175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 5 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 13 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x0e043e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 4], 14 - QUAD $0x0f040e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 4], 15 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x01050e642009a3c4 // vpinsrb xmm4, xmm14, byte [rsi + r9 + 5], 1 - QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] - QUAD $0x02053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 2 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x03050e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 5], 3 - QUAD $0x04052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 4 - QUAD $0x05050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 5 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x06050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 6 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x07050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 7 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x080506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x090506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 10 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 11 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0c0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 13 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 14 - QUAD $0x0f0526642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 5], 15 + QUAD $0x0604075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 6 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0704175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 7 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x08040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 8 + QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] + QUAD $0x0904375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 4], 9 + QUAD $0x0a042f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 4], 10 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0b04375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 11 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0c042f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 4], 12 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0d04375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 13 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x0e04275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 14 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x0f04275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 15 + QUAD $0x010517642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r10 + 5], 1 + QUAD $0x02051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 2 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x030537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 3 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x040517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 4 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x05051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 5 + QUAD $0x06053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 6 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x070537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 7 + QUAD $0x08050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 8 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x09050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 9 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0a050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 10 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0b050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 11 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0c050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 13 + QUAD $0x0e0507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 14 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0f050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 15 + QUAD $0x01051f6c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdi + rbx + 5], 1 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x02053f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 5], 2 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0305376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 3 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x0405376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 4 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x05051f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 5], 5 + QUAD $0x0605076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 6 + QUAD $0x0705176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 7 + QUAD $0x08050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 8 + QUAD $0x0905376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 5], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0105066c2049e3c4 // vpinsrb xmm5, xmm6, byte [rsi + rax + 5], 1 - QUAD $0x0205166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 2 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0305066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 3 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0405166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 4 - QUAD $0x0505166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 5], 5 - QUAD $0x06053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 6 - WORD $0x8949; BYTE $0xfa // mov r10, rdi - QUAD $0x0705366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 7 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x0805366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 8 - QUAD $0x09051e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 5], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 10 - QUAD $0x0b051e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 5], 11 - QUAD $0x0c05066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 5], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 13 + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x0c052f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 5], 12 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 14 + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0506442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 5], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + QUAD $0x0f0527442051a3c4 // vpinsrb xmm0, xmm5, byte [rdi + r12 + 5], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xd86ef9c5 // vmovd xmm3, eax LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x010606442019e3c4 // vpinsrb xmm0, xmm12, byte [rsi + rax + 6], 1 - QUAD $0x02063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 2 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x03060e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 6], 3 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x04061e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 6], 4 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x050616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 6], 5 + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x01060f442019a3c4 // vpinsrb xmm0, xmm12, byte [rdi + r9 + 6], 1 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x020607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x040617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 4 + QUAD $0x05061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x060607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 6 QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x06061e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 6], 6 - QUAD $0x07062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 7 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x08060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 8 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x09062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 10 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0b060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 11 + QUAD $0x07061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 7 QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x0c0626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 6], 12 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x0d0606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 6], 13 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0e060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 14 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0f060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 15 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x01060e6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rcx + 6], 1 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x02060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 2 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x03060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x04060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 5 - QUAD $0x0606166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 6], 6 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x07060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 7 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - QUAD $0x0806366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 10 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0b06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0c06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 12 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0d06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 13 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - QUAD $0x0e06166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 14 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x0f06366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 15 - QUAD $0x010706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 1 - QUAD $0x02073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 2 - QUAD $0x03070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 3 - QUAD $0x04071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 4 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x050736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 5 - QUAD $0x06071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 6 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x070716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 7 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x08071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 8 - QUAD $0x09072e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 7], 9 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0a0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 10 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x0b070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 11 - QUAD $0x0c0726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 7], 12 - QUAD $0x0d0706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 7], 13 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0e0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 15 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0107164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 1 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0207164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 2 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0307164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 3 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0407164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 4 - QUAD $0x05073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 5 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0607164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 6 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x07073e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 7], 7 - QUAD $0x0807164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 7], 8 + QUAD $0x080627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 8 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x09061f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 6], 9 LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0907164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 9 - QUAD $0x0a070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 10 + QUAD $0x0a0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 11 LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0b072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 11 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0c070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 13 + QUAD $0x0c062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 12 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0d0637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 14 + QUAD $0x0f060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 15 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x01060f6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rcx + 6], 1 + QUAD $0x02063f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 6], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0306076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 3 + QUAD $0x0406376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0506076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 5 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0606376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 6 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x0706176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 7 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0806376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0906376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 9 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0a06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 10 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0b06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 11 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0c06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 12 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0d06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 13 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x0e06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 14 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x0f063f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 6], 15 + QUAD $0x01070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 1 + QUAD $0x020707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 2 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x030737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 3 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x040707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 4 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x050737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 5 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x060737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 6 + QUAD $0x07071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 7 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + QUAD $0x080727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 8 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x09071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 9 + QUAD $0x0a0717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 10 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0b0717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 11 + QUAD $0x0c072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 12 + QUAD $0x0d0737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 13 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0e070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 14 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0f0717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 15 + QUAD $0x01070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 1 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x02072f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 7], 2 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x03070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 3 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x04071f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 7], 4 + QUAD $0x0507074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0707174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 7 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x0807274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0907074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e070e442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rcx + 7], 14 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e7cb60f; BYTE $0x0b // movzx edi, byte [rsi + rcx + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f070e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 7], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e0707442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 7], 14 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f0707442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0004e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1248], ymm0 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0e7cb60f; BYTE $0x0b // movzx edi, byte [rsi + rcx + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x010806442031e3c4 // vpinsrb xmm0, xmm9, byte [rsi + rax + 8], 1 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x020826442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 8], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x03080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 3 - QUAD $0x04081e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 8], 4 - WORD $0x894c; BYTE $0xf3 // mov rbx, r14 - QUAD $0x050836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 8], 5 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x060806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 6 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x070816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 7 - QUAD $0x08081e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 8], 8 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x090806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 8], 9 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0a0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 10 - QUAD $0x0b080e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 8], 11 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x0c081e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 8], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 13 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0e0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0f083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 15 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0108166c2029e3c4 // vpinsrb xmm5, xmm10, byte [rsi + rdx + 8], 1 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0208366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 8], 2 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x03083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 4 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0508166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 5 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0608166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 6 - QUAD $0x07083e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 8], 7 - QUAD $0x0808166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 8], 8 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x09080e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 8], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0a083e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 8], 10 - QUAD $0x0b082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0c08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 12 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0d08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 13 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - QUAD $0x0e08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0f082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 15 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x01092e742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r13 + 9], 1 - QUAD $0x020926742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r12 + 9], 2 - QUAD $0x03090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 3 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x04090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 4 - QUAD $0x05091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 5 - QUAD $0x060906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 6 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x070916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x080906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 8 - QUAD $0x090906742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r8 + 9], 9 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x010817442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r10 + 8], 1 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x02080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 2 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x030817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 3 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + QUAD $0x040807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 4 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x050807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 5 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x060837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 8], 6 + QUAD $0x070837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 8], 7 + QUAD $0x08083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x090807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 13 + QUAD $0x0e080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 14 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x0f080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 15 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0108076c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rax + 8], 1 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x02082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 2 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 10 + QUAD $0x0308076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 3 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x04081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 4 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x05082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 5 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x06081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 6 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x07081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 7 + QUAD $0x0808276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 8 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x09081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 9 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0a08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 10 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0b081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0c081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 12 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x0d081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 13 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x0e08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 14 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0f081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 15 + QUAD $0x010917742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r10 + 9], 1 + QUAD $0x02090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 2 + QUAD $0x030917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 3 + QUAD $0x04091f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 9], 4 + QUAD $0x050907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 5 + QUAD $0x060937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 6 + QUAD $0x070937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 7 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x08090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 8 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x090917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 9 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0a090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 10 LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0b090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 11 - QUAD $0x0c091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 13 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 15 + QUAD $0x0b090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 11 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0c0937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 12 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0d0917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 13 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0e0937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 14 + QUAD $0x0f090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 15 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0109377c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rsi + 9], 1 + QUAD $0x02093f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 9], 2 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0309377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 3 + QUAD $0x0409077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 4 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x05092f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 9], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0609077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 6 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x0709377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 7 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x08091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 10 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0109067c2021e3c4 // vpinsrb xmm7, xmm11, byte [rsi + rax + 9], 1 - QUAD $0x0209367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 9], 2 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0309067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 3 - QUAD $0x04093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 4 - WORD $0x8949; BYTE $0xfe // mov r14, rdi + QUAD $0x0b09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0509067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0609067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 6 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0709067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 7 - QUAD $0x0809167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 9], 8 - QUAD $0x09090e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 9], 9 - QUAD $0x0a093e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 9], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 12 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0d093e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 9], 13 + QUAD $0x0c09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 12 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 14 + QUAD $0x0d09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 13 + QUAD $0x0e09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f09076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 9], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xc06ef9c5 // vmovd xmm0, eax LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x0004a024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm5 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x010a2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 10], 1 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x020a1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 10], 2 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x030a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 3 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x040a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x050a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 5 + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x010a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 1 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x020a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 2 + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + QUAD $0x030a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x040a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x050a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 5 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x060a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 6 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x060a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 6 - QUAD $0x070a165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 10], 7 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x080a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 8 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x090a265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 10], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 10 - QUAD $0x0b0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 11 - QUAD $0x0c0a1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 10], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d0a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 13 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0e0a3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 10], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0f0a3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 10], 15 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x010a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x020a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 2 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 - QUAD $0x040a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 5 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x060a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 6 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x070a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 7 - QUAD $0x080a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 8 + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x080a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 8 + QUAD $0x090a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 9 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 9 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0a0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 10 + QUAD $0x0a0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 10 + QUAD $0x0b0a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 11 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 11 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x0c0a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 12 - QUAD $0x0d0a3e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 10], 13 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x0e0a3e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 10], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 15 - QUAD $0x010b2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 11], 1 - QUAD $0x020b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 2 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x030b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 3 - QUAD $0x040b0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 11], 4 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x050b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 5 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x060b2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 11], 6 - QUAD $0x070b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 7 - WORD $0x8949; BYTE $0xd1 // mov r9, rdx - QUAD $0x080b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 8 - QUAD $0x090b264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 11], 9 + QUAD $0x0c0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 12 + QUAD $0x0d0a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 13 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0e0a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 14 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0f0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 15 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x010a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 1 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x020a17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 10], 2 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 10 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 11 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0c0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 12 - QUAD $0x0d0b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 13 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 14 - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x0f0b3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 11], 15 - QUAD $0x010b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 11], 1 + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 + QUAD $0x040a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 4 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x050a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 5 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x060a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 6 + QUAD $0x070a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 7 + QUAD $0x080a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 8 + QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] + QUAD $0x090a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 9 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0a0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 10 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0b0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0c0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 12 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x0d0a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 13 + QUAD $0x0e0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 14 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x0f0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 15 + QUAD $0x010b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 1 + QUAD $0x020b1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 11], 2 + QUAD $0x030b0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 11], 3 + QUAD $0x040b3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 11], 4 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x050b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 5 + QUAD $0x060b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 6 + WORD $0x894d; BYTE $0xe9 // mov r9, r13 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x070b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 7 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x080b1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 11], 8 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x090b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 9 + LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] + QUAD $0x0a0b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 10 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0b0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 11 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0c0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 13 + WORD $0x8949; BYTE $0xdf // mov r15, rbx + QUAD $0x0e0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 14 + QUAD $0x0f0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 15 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x010b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 1 + QUAD $0x020b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 11], 2 + QUAD $0x030b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 3 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x040b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x050b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x060b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 6 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x020b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 2 - QUAD $0x030b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x040b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x050b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 5 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x060b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 6 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x070b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 7 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x080b26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 11], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x090b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 9 - QUAD $0x0a0b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 11], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 11 - QUAD $0x0c0b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 11], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 13 + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + QUAD $0x090b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 9 + QUAD $0x0a0b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000480249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm3 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 14 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rcx + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f0b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000460248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rcx + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x010c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 1 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x020c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x030c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 3 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x040c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 4 - QUAD $0x050c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 5 - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - QUAD $0x060c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 6 - QUAD $0x070c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 7 - QUAD $0x080c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 12], 8 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x090c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a0c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 10 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0b0c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 11 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x0c0c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 12], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d0c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 12], 13 - LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] - QUAD $0x0e0c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 12], 14 - WORD $0x894d; BYTE $0xfa // mov r10, r15 - QUAD $0x0f0c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 12], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x010c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x020c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x030c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x040c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 4 + QUAD $0x050c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 5 + QUAD $0x060c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 6 + QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] + QUAD $0x070c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 7 + QUAD $0x080c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 12], 8 + QUAD $0x090c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 9 + QUAD $0x0a0c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 12], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 11 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0c0c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 12 + QUAD $0x0d0c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 13 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0e0c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 14 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x0f0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 15 + QUAD $0x010c17542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rdx + 12], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x020c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 2 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x030c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 3 + QUAD $0x040c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 4 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x050c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 5 + QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] + QUAD $0x060c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 6 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x070c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 7 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x080c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 8 + QUAD $0x090c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 9 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x0a0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 10 QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x010c2e542051a3c4 // vpinsrb xmm2, xmm5, byte [rsi + r13 + 12], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x020c3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 12], 2 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x030c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 3 - QUAD $0x040c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x060c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 6 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x070c3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 12], 7 - QUAD $0x080c26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 12], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 10 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0b0c26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 12], 11 + QUAD $0x0b0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0c0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 12 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x0d0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 13 + LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] + QUAD $0x0e0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 14 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0f0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 15 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x010d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 1 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x020d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 2 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x030d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 3 + QUAD $0x040d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 4 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x050d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 5 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x060d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 6 + QUAD $0x070d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 7 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x080d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 8 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x090d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 9 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0a0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 10 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0b0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 11 + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0c0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 13 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 15 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x010d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 1 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x020d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x030d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 3 - QUAD $0x040d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 4 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x050d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 5 - QUAD $0x060d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 6 + QUAD $0x0d0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 13 + QUAD $0x0e0d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 14 + QUAD $0x0f0d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 13], 15 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x010d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 1 + QUAD $0x020d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 2 + QUAD $0x030d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 3 + QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] + QUAD $0x040d0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 13], 4 + QUAD $0x050d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 5 + QUAD $0x060d3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 13], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x070d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 7 + QUAD $0x080d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 8 + QUAD $0x090d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 9 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x0a0d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 10 + QUAD $0x0b0d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 11 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0c0d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 12 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0d0d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 13 + LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] + QUAD $0x0e0d1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 13], 14 + LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 + QUAD $0x00044024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm0 + LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] + QUAD $0x0f0d1f442071a3c4 // vpinsrb xmm0, xmm1, byte [rdi + r11 + 13], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 + QUAD $0x00042024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm0 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xc06ef9c5 // vmovd xmm0, eax QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x070d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 7 - QUAD $0x080d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 13], 8 - QUAD $0x090d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 9 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0a0d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 10 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0b0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 11 - QUAD $0x0c0d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 12 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x0d0d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 13 - QUAD $0x0e0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 14 - QUAD $0x0f0d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 13], 15 - QUAD $0x010d2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 13], 1 - QUAD $0x020d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 2 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x030d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x040d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x050d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 5 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x060d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 6 - QUAD $0x070d3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 13], 7 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x080d0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 13], 8 - QUAD $0x090d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 9 + QUAD $0x010e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 1 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x020e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 2 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x030e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x040e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x050e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x080e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x090e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 12 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0d0e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 14], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 15 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x010e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x020e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 3 + QUAD $0x040e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 14], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x050e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x060e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x070e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 7 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x080e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x090e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 9 + QUAD $0x0a0e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 10 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x0b0e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 11 + QUAD $0x0c0e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 14], 12 + QUAD $0x0d0e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 13 + QUAD $0x0e0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 14 + QUAD $0x0f0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x0f // movzx eax, byte [rdi + rax + 15] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x010f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 1 + QUAD $0x020f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 2 + QUAD $0x030f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 15], 3 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x040f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 4 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x050f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x060f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 6 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x070f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 7 + QUAD $0x080f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 10 - QUAD $0x0b0d264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 13], 11 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x0c0d164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 13], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 14 - LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 - QUAD $0x00044024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm0 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0d06442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rax + 13], 15 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x0e2e // movzx edi, byte [rsi + r13 + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 - QUAD $0x00042024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm0 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - LONG $0x7cb60f42; WORD $0x0e36 // movzx edi, byte [rsi + r14 + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x010e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 1 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x020e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 14], 2 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x030e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 14], 3 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x040e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 14], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x050e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 5 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x060e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x070e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 7 + QUAD $0x090f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 9 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x0a0f1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 15], 10 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x0b0f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 12 + QUAD $0x0d0f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 14 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x080e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 8 + QUAD $0x0f0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0f // movzx eax, byte [rdi + rax + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x010f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 1 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x020f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x030f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x050f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 5 + QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] + QUAD $0x060f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 6 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x070f3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 15], 7 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x080f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 8 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x090e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 9 - QUAD $0x0a0e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 14], 10 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x0b0e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 11 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0c0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 12 - QUAD $0x0d0e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 13 + QUAD $0x090f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 9 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x0a0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 10 + QUAD $0x0b0f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 11 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0c0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 13 LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 14 + QUAD $0x0e0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 14 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 15 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x010e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 14], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x020e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 2 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x030e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 3 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x040e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 14], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 5 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x060e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 14], 6 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x070e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x080e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x090e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 11 - QUAD $0x0c0e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 14], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 13 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 15 - LONG $0x7cb60f42; WORD $0x0f2e // movzx edi, byte [rsi + r13 + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x010f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 1 - QUAD $0x020f16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 15], 2 - QUAD $0x030f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 3 - QUAD $0x040f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 4 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x050f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 5 - QUAD $0x060f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 6 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x070f16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 15], 7 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x080f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 8 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x090f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 9 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0a0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 10 - QUAD $0x0b0f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 11 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x0c0f2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 15], 12 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0d0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 13 - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - QUAD $0x0e0f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 14 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0f0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 15 - LONG $0x7cb60f42; WORD $0x0f36 // movzx edi, byte [rsi + r14 + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x010f0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 15], 1 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x020f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 2 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x030f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 3 - QUAD $0x040f1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 15], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x050f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 5 - QUAD $0x060f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 6 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x070f165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 15], 7 - QUAD $0x080f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 10 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0b0f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 14 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0f0f3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 15], 15 + QUAD $0x0f0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x10 // movzx edi, byte [rsi + rax + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x011036442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 16], 1 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x021006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 2 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x03101e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 16], 3 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x041006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 4 - QUAD $0x05101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 5 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x06100e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 16], 6 - QUAD $0x071016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 7 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x081016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x091006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0a101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 10 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 11 - QUAD $0x0c102e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 16], 12 + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x011007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x031007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 3 + QUAD $0x041027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 4 + QUAD $0x05101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x061007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 6 + QUAD $0x07102f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 16], 7 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x081007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 9 + QUAD $0x0a101f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 16], 10 + QUAD $0x0b100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 11 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0c1027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 13 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0e100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 15 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + LONG $0x1f44b60f; BYTE $0x10 // movzx eax, byte [rdi + rbx + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 13 - QUAD $0x0e1006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 14 + QUAD $0x0110074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 1 + QUAD $0x0210174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 16], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0310074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 3 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + QUAD $0x04101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0510074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 5 + QUAD $0x0610074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 6 + QUAD $0x07103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 7 + QUAD $0x0810374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0910374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 9 + QUAD $0x0a100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 10 + QUAD $0x0b10374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 11 + QUAD $0x0c10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 14 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 15 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - LONG $0x3e7cb60f; BYTE $0x10 // movzx edi, byte [rsi + rdi + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 2 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x03103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 4 - QUAD $0x05100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 5 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x06100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 6 - QUAD $0x0710164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 16], 7 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x08100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 10 - QUAD $0x0b10264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 12 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0d10264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 13 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - QUAD $0x0e102e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 16], 14 - QUAD $0x0f103e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 16], 15 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - LONG $0x3e7cb60f; BYTE $0x11 // movzx edi, byte [rsi + rdi + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011136542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 17], 1 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - QUAD $0x021106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 2 - QUAD $0x03111e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 17], 3 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x041116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x05113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 5 - QUAD $0x06110e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 17], 6 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x07113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 7 - QUAD $0x081116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 8 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x091116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 9 - QUAD $0x0a111e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 17], 10 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0b111e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 17], 11 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x0c1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 12 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0d1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 13 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0e1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 14 - QUAD $0x0f1106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x067cb60f; BYTE $0x11 // movzx edi, byte [rsi + rax + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x0111365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 17], 1 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x02113e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 17], 2 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x03110e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 17], 3 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0411165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0511065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 5 + QUAD $0x0f10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 15 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + LONG $0x1744b60f; BYTE $0x11 // movzx eax, byte [rdi + rdx + 17] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x01112f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 17], 1 + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x021117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x031107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 5 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0611065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 6 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x07111e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 17], 7 - QUAD $0x08110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 9 + QUAD $0x061107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 6 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x071107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 7 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x081107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 11 + QUAD $0x091107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 11 + QUAD $0x0c1127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 12 - QUAD $0x0d11265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 17], 13 - QUAD $0x0e112e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 17], 14 + QUAD $0x0d1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 13 + QUAD $0x0e110f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 17], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 15 + LONG $0x1f44b60f; BYTE $0x11 // movzx eax, byte [rdi + rbx + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0111075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 1 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x02113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x03111f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 17], 3 + QUAD $0x04111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 4 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0511275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 5 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x06110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0711075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 7 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + QUAD $0x0911375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + QUAD $0x0b11375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1106442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rax + 17], 15 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f1107442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 + LONG $0x1744b60f; BYTE $0x12 // movzx eax, byte [rdi + rdx + 18] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x01122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 1 + QUAD $0x021217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x031207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 3 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x041237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x06122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 6 + QUAD $0x071207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 18], 7 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x08120f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 18], 8 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x091237442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 18], 9 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + QUAD $0x0a1207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 18], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x0c121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 14 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0f1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0112174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 1 + QUAD $0x02123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 2 + QUAD $0x03121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 3 + QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] + QUAD $0x04123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 4 + QUAD $0x0512274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 5 + QUAD $0x06120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0712074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 7 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x067cb60f; BYTE $0x12 // movzx edi, byte [rsi + rax + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0812074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 8 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x0912274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 9 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x011206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 1 - QUAD $0x021206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 18], 2 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x031206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 3 - QUAD $0x041216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 5 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x061206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 18], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x071206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x081206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x091206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 9 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x0a1216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 10 - QUAD $0x0b121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 11 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x0c1226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 18], 12 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x0d121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 13 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0e123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0f123e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 18], 15 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - LONG $0x3e7cb60f; BYTE $0x12 // movzx edi, byte [rsi + rdi + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0112364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 18], 1 - QUAD $0x02123e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 18], 2 - QUAD $0x03120e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 18], 3 - QUAD $0x0412164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 4 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0512164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 5 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0612364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 18], 6 - QUAD $0x07121e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 18], 7 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x0812164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 8 - QUAD $0x09120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 10 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x0b123e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 18], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0c12164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 13 - QUAD $0x0e122e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 18], 14 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0f121e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 18], 15 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - LONG $0x3e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rdi + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x01133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 1 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x02133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x03133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 3 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x04133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 4 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x05132e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 19], 5 - QUAD $0x061306542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 19], 6 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x07133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 7 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x08133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 8 - QUAD $0x091306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 9 - QUAD $0x0a1316542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 19], 10 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 11 - QUAD $0x0c1326542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 19], 12 - QUAD $0x0d131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 13 - LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] - QUAD $0x0e130e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 19], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 15 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - LONG $0x7cb60f42; WORD $0x1316 // movzx edi, byte [rsi + r10 + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + QUAD $0x0a12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 10 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0113065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 1 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0213065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 2 + QUAD $0x0b12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 14 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0f121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x011307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 2 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0313065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0413065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 4 + QUAD $0x031307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 3 + QUAD $0x041337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 5 + QUAD $0x06132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x071307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 7 + QUAD $0x08130f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 19], 8 + QUAD $0x091337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 9 + QUAD $0x0a1307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 10 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0b1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 11 + QUAD $0x0c131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 12 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x0d132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 13 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0e130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 14 + QUAD $0x0f1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0113175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 19], 1 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x0213075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0313075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 3 + QUAD $0x04133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] + QUAD $0x06133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x08131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 8 + QUAD $0x0913275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 9 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0a13275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 10 + QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] + QUAD $0x0b130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0513065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 5 - QUAD $0x0613365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 19], 6 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0713065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0813065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0913065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 9 - QUAD $0x0a130e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 19], 10 - QUAD $0x0b133e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 19], 11 - QUAD $0x0c13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 13 + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 14 - QUAD $0x0f131e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 19], 15 + QUAD $0x0d13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 + QUAD $0x0f131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x141e // movzx edi, byte [rsi + r11 + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x011406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 1 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x021416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x03143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 3 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x04143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 4 - QUAD $0x05142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 5 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x06143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 6 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x07142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 7 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x08143e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 20], 8 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x09143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 9 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x0a1426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 10 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0b140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 11 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0c143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 13 - QUAD $0x0e140e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 20], 14 - LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] - QUAD $0x0f1436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 20], 15 - LONG $0x7cb60f42; WORD $0x1416 // movzx edi, byte [rsi + r10 + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x01141e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 20], 1 - QUAD $0x0214064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 20], 2 - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x0314064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 20], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 5 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x06143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 6 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x0714164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 20], 7 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x08143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 11 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0c140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 13 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0e143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 15 - LONG $0x7cb60f42; WORD $0x151e // movzx edi, byte [rsi + r11 + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 1 - QUAD $0x021516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 2 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x031516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x14 // movzx eax, byte [rdi + rax + 20] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x011407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 1 + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x021417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x031407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 3 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x041506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 4 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x051506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 5 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x061506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 6 - QUAD $0x07152e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 21], 7 - QUAD $0x08153e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 21], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x091506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 9 - QUAD $0x0a1526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 10 - QUAD $0x0b150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 11 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x0c1526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 12 + QUAD $0x041407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 4 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x051437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x061407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 6 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x071417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 7 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x081407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + QUAD $0x0b1437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 20], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 12 + QUAD $0x0d142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 13 + QUAD $0x0e140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 15 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + LONG $0x1f44b60f; BYTE $0x14 // movzx eax, byte [rdi + rbx + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 13 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 14 - QUAD $0x0f1536542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 21], 15 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - LONG $0x7cb60f42; WORD $0x151e // movzx edi, byte [rsi + r11 + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01151e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 21], 1 + QUAD $0x0114074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 1 + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 + QUAD $0x0214074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x0414074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 4 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x05140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 5 + QUAD $0x06143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 6 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0215065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 2 - QUAD $0x0315065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 21], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x04150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0515065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 5 + QUAD $0x0714074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 7 + QUAD $0x08141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 8 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x09142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 9 + QUAD $0x0a14274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 20], 10 + QUAD $0x0b140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 11 + QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] + QUAD $0x0c140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 13 + LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] + QUAD $0x0e143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 14 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 15 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + LONG $0x44b60f42; WORD $0x1527 // movzx eax, byte [rdi + r12 + 21] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x011507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 1 + QUAD $0x021517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x031507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 4 + QUAD $0x051537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 5 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0615065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 6 - QUAD $0x0715165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 7 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x08152e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 21], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0a153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 10 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0b151e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 21], 11 - QUAD $0x0c150e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 21], 12 - QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] - QUAD $0x0d15065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 21], 13 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0e153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 14 + QUAD $0x061507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 6 + QUAD $0x071517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 7 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x081507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 14 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x0f1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 15 + LONG $0x1f44b60f; BYTE $0x15 // movzx eax, byte [rdi + rbx + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0115075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 1 + QUAD $0x0215375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 2 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x03151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 3 + QUAD $0x0415075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 4 + QUAD $0x05150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 5 + WORD $0x8948; BYTE $0xce // mov rsi, rcx + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x0715175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 7 + QUAD $0x08151f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 21], 8 + QUAD $0x09152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 11 + QUAD $0x0c150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 13 + QUAD $0x0e153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0f1516442061a3c4 // vpinsrb xmm0, xmm3, byte [rsi + r10 + 21], 15 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f1507442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - LONG $0x3e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rdi + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x01163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 1 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x02163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 2 - QUAD $0x031616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 3 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x041616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 4 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x051616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 5 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x061616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 6 + LONG $0x44b60f42; WORD $0x1627 // movzx eax, byte [rdi + r12 + 22] + LONG $0xc06ef9c5 // vmovd xmm0, eax QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x071616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 7 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x081616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 8 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x091616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 9 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0a1636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 22], 10 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0b163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 11 - QUAD $0x0c1626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 22], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 13 - LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] - QUAD $0x0e160e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 22], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0f163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 15 - LONG $0x7cb60f42; WORD $0x161e // movzx edi, byte [rsi + r11 + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 2 - LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] - QUAD $0x0316264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 22], 3 - QUAD $0x04160e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 22], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x05160e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 22], 5 - QUAD $0x0616064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 6 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x07161e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 22], 7 - QUAD $0x08162e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 22], 8 + QUAD $0x011617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 2 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x03160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 3 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x041627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 5 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x06162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x071607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 7 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + QUAD $0x081607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 9 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0916064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 9 - QUAD $0x0a163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 10 - QUAD $0x0b161e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 22], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0c163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 12 - QUAD $0x0d16064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 22], 13 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e160e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 22], 14 - QUAD $0x0f16164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 15 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - LONG $0x3e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rdi + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x011716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 23], 1 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - QUAD $0x021706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 23], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x03173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 3 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x04173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x05173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 5 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x06172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 6 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x07173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 7 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x08173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 8 - QUAD $0x091716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 9 - QUAD $0x0a1736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 10 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0b1716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 11 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0c1736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 12 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x0d171e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 23], 13 - QUAD $0x0e170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f1716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 15 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - LONG $0x3e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rdi + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x01170e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 23], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 2 - QUAD $0x0317265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 5 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x06173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 6 - QUAD $0x07171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 7 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x0817265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 8 - QUAD $0x0917065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 9 + QUAD $0x0a1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x0c160f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 22], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 13 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x0e163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 14 + QUAD $0x0f1637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0116074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0216074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 2 + QUAD $0x03161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0416074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 4 + QUAD $0x0516374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 5 + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0616374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 6 + QUAD $0x0716174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 22], 7 + QUAD $0x08161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 14 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 1 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x021737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 2 + QUAD $0x03170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 3 + QUAD $0x041727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 5 + QUAD $0x06172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x071707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 7 + QUAD $0x081707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 23], 8 LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0a171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 11 - QUAD $0x0c173e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 23], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 13 - QUAD $0x0e170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 15 + QUAD $0x09171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 9 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0a1717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 11 + QUAD $0x0c170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 13 + QUAD $0x0e173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 14 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x0f170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 15 + QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x1717 // movzx eax, byte [rdi + r10 + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0117075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 1 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x02172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 2 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x0317075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0417075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 4 + QUAD $0x05171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 5 + QUAD $0x0617375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0717075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 7 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x08171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0a17275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 10 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0b17375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 14 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x0f173f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rcx + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 24], 1 - QUAD $0x021806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 24], 2 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x031816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 24], 3 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x04183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 4 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x05183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 5 - QUAD $0x06182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 6 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x071806442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 24], 7 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x08183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 8 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x09182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 9 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0a183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 10 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0b183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 11 - QUAD $0x0c1836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 24], 12 - QUAD $0x0d181e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 24], 13 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0e183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 14 - QUAD $0x0f1816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 24], 15 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - LONG $0x167cb60f; BYTE $0x18 // movzx edi, byte [rsi + rdx + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x01180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 1 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x02180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 2 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x03183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 5 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x06183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 6 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x07183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 7 - QUAD $0x0818264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 9 - QUAD $0x0a181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 11 - QUAD $0x0c183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 12 - QUAD $0x0d18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 14 - LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] - QUAD $0x0f181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 15 - LONG $0x0e7cb60f; BYTE $0x19 // movzx edi, byte [rsi + rcx + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x011906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 1 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x02191e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 25], 2 - QUAD $0x031916542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 25], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x011807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 1 + QUAD $0x021837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x031807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 3 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x041906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 4 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x051936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 5 + QUAD $0x041807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x061807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 6 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x061906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 6 - QUAD $0x071906542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 25], 7 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x08190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 8 - QUAD $0x09192e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 25], 9 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0a193e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 25], 10 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0b1906542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 25], 11 + QUAD $0x071807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 7 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0c1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 13 + QUAD $0x081807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 8 + QUAD $0x09181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 9 + QUAD $0x0a1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 10 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0b1837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 12 + QUAD $0x0d180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 14 + QUAD $0x0f180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 15 + LONG $0x44b60f42; WORD $0x1817 // movzx eax, byte [rdi + r10 + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x01181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 1 + QUAD $0x02182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 2 + QUAD $0x0318074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 3 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x04180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0518074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0618074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 6 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0718174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 7 + QUAD $0x08181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 8 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x09181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 9 + QUAD $0x0a18274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 10 + QUAD $0x0b18374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 11 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + QUAD $0x0c18074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0d18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 13 LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 15 - LONG $0x167cb60f; BYTE $0x19 // movzx edi, byte [rsi + rdx + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - QUAD $0x0119265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 1 - QUAD $0x02190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 2 + QUAD $0x0e18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 14 + QUAD $0x0f183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 15 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x011907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 2 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0319065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0419065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0519065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 5 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x06192e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 25], 6 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0719065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 7 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0819065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 8 - LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] - QUAD $0x0919165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 25], 9 + QUAD $0x031907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 3 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x04193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 4 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x051917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 5 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + QUAD $0x06190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 6 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x07192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 7 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 10 + QUAD $0x091907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 10 + QUAD $0x0b1937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 11 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b19065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0c19165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 12 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0d19165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 13 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - QUAD $0x0e19165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 14 + QUAD $0x0c1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x01191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0319075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 3 + QUAD $0x04190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0519075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 + QUAD $0x0719175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 7 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0819075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 8 + QUAD $0x09191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 9 + QUAD $0x0a19275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 10 + QUAD $0x0b19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 11 + QUAD $0x0c19075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 25], 12 + QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] + QUAD $0x0d19075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 25], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 14 LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 - QUAD $0x0f191e442061a3c4 // vpinsrb xmm0, xmm3, byte [rsi + r11 + 25], 15 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x0f1927442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r12 + 25], 15 LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x1a1e // movzx edi, byte [rsi + r11 + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x011a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 1 - QUAD $0x021a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 2 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x031a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 3 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x041a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 4 - QUAD $0x051a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 5 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x061a0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 26], 6 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x071a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 7 - QUAD $0x081a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 8 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x091a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 9 - QUAD $0x0a1a3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 26], 10 - QUAD $0x0b1a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 11 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0c1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 12 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x0d1a3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 26], 13 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0e1a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 14 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0f1a0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 26], 15 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0e7cb60f; BYTE $0x1a // movzx edi, byte [rsi + rcx + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 1 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x021a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 2 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x031a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x041a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 4 - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x051a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 5 - QUAD $0x061a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 6 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x071a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 7 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x081a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 8 - QUAD $0x091a164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 26], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a1a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 10 - QUAD $0x0b1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 11 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + LONG $0x1744b60f; BYTE $0x1a // movzx eax, byte [rdi + rdx + 26] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x011a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 2 + LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] + QUAD $0x031a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 3 + QUAD $0x041a3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 26], 4 + QUAD $0x051a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 5 + QUAD $0x061a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 6 + QUAD $0x071a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 7 + QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] + QUAD $0x081a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 8 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x091a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 9 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0a1a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 10 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0b1a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 12 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0d1a164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 26], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 14 + QUAD $0x0d1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 13 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0e1a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 15 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + LONG $0x3744b60f; BYTE $0x1a // movzx eax, byte [rdi + rsi + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x011a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 1 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x021a174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 26], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x041a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x051a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x061a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x071a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 7 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x081a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 8 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x091a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 + QUAD $0x0d1a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 14 + QUAD $0x0f1a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 15 + LONG $0x1744b60f; BYTE $0x1b // movzx eax, byte [rdi + rdx + 27] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x011b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 27], 1 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x021b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 2 + QUAD $0x031b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 4 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 15 - LONG $0x7cb60f42; WORD $0x1b1e // movzx edi, byte [rsi + r11 + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x011b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 27], 1 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x021b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 2 - QUAD $0x031b1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 27], 3 - QUAD $0x041b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 4 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x051b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 5 - QUAD $0x061b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 27], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x071b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 7 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x081b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 8 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x091b1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 27], 9 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0a1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 10 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0b1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 11 - QUAD $0x0c1b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 27], 12 - QUAD $0x0d1b3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 27], 13 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0e1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 15 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - LONG $0x167cb60f; BYTE $0x1b // movzx edi, byte [rsi + rdx + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x011b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 1 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x021b0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 27], 2 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x031b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 3 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x041b365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 27], 4 - QUAD $0x051b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 5 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x061b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 6 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x071b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 7 - QUAD $0x081b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x091b3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 27], 9 - QUAD $0x0a1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 11 + QUAD $0x051b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x061b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + QUAD $0x081b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 8 + QUAD $0x091b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 9 + QUAD $0x0a1b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 10 + QUAD $0x0b1b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 12 LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0c1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 12 - QUAD $0x0d1b165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 27], 13 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - QUAD $0x0e1b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 15 + QUAD $0x0d1b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 13 + QUAD $0x0e1b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 14 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0f1b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 15 + LONG $0x3744b60f; BYTE $0x1b // movzx eax, byte [rdi + rsi + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x011b1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 27], 1 + QUAD $0x021b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 2 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x031b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 3 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x041b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x051b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x071b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 7 + QUAD $0x081b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 8 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x091b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x0d1b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 13 + LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] + QUAD $0x0e1b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 14 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - LONG $0x0e7cb60f; BYTE $0x1c // movzx edi, byte [rsi + rcx + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 1 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x021c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x031c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 3 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x041c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 4 - QUAD $0x051c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 5 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x061c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 6 - QUAD $0x071c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x081c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 8 - QUAD $0x091c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 10 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x0744b60f; BYTE $0x1c // movzx eax, byte [rdi + rax + 28] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 1 + QUAD $0x021c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 2 + QUAD $0x031c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 3 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x041c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 4 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x051c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x061c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x071c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 7 + QUAD $0x081c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 8 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x091c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 10 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 11 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x0c1c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 13 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0e1c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0f1c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 15 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - LONG $0x7cb60f42; WORD $0x1c26 // movzx edi, byte [rsi + r12 + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x011c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 1 - QUAD $0x021c0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 28], 2 - QUAD $0x031c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 3 - QUAD $0x041c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 4 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x051c0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 28], 5 - QUAD $0x061c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 6 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x071c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 7 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - QUAD $0x081c064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 28], 8 + QUAD $0x0b1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 12 + QUAD $0x0d1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 14 + QUAD $0x0f1c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 15 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x0f44b60f; BYTE $0x1c // movzx eax, byte [rdi + rcx + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + QUAD $0x031c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 3 + QUAD $0x041c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x051c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 5 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x061c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 6 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x071c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 7 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x081c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 8 + QUAD $0x091c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 9 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x0a1c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 10 + QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] + QUAD $0x0b1c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 12 + QUAD $0x0d1c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 13 + QUAD $0x0e1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 14 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0f1c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 15 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + LONG $0x44b60f42; WORD $0x1d17 // movzx eax, byte [rdi + r10 + 29] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x011d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 2 + QUAD $0x031d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 3 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x041d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 4 + QUAD $0x051d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 5 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x061d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x071d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 7 + QUAD $0x081d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 8 + QUAD $0x091d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 9 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 9 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0a1c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 10 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0b1c164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 28], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0c1c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 12 + QUAD $0x0a1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 10 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0b1d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 11 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + QUAD $0x0c1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 15 + LONG $0x0f44b60f; BYTE $0x1d // movzx eax, byte [rdi + rcx + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x011d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x041d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d1c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 13 - QUAD $0x0e1c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f1c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 15 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - LONG $0x3e7cb60f; BYTE $0x1d // movzx edi, byte [rsi + rdi + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x011d2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 29], 1 - QUAD $0x021d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x031d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 3 - QUAD $0x041d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 4 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x051d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 5 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x061d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 6 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x071d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 7 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x081d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 8 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x091d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 9 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0a1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 10 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0b1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 11 - QUAD $0x0c1d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 12 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0d1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 13 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0e1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0f1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 15 - LONG $0x7cb60f42; WORD $0x1d26 // movzx edi, byte [rsi + r12 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x011d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 29], 1 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x021d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 2 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x031d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 3 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x041d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 29], 4 - QUAD $0x051d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 5 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x061d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 6 - QUAD $0x071d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 29], 7 - QUAD $0x081d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 29], 8 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x091d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 9 - QUAD $0x0a1d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 10 - QUAD $0x0b1d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 29], 11 - QUAD $0x0c1d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 29], 12 - WORD $0x8949; BYTE $0xd6 // mov r14, rdx - QUAD $0x0d1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 13 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - QUAD $0x0e1d16642061a3c4 // vpinsrb xmm4, xmm3, byte [rsi + r10 + 29], 14 + QUAD $0x061d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 6 + QUAD $0x071d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 7 + QUAD $0x081d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 8 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x091d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 9 + QUAD $0x0a1d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 10 + QUAD $0x0b1d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 11 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0c1d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 12 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x0d1d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 13 + LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] + QUAD $0x0e1d0f642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r9 + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f1d16442059e3c4 // vpinsrb xmm0, xmm4, byte [rsi + rdx + 29], 15 + QUAD $0x0f1d1f442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rbx + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - LONG $0x7cb60f42; WORD $0x1e06 // movzx edi, byte [rsi + r8 + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011e2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 30], 1 - LONG $0x7cb60f42; WORD $0x1f06 // movzx edi, byte [rsi + r8 + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 31], 1 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x021e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 2 - QUAD $0x021f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 2 - QUAD $0x031e0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 30], 3 - QUAD $0x031f0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 31], 3 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 - QUAD $0x051e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 30], 5 - QUAD $0x051f1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 31], 5 + WORD $0x894c; BYTE $0xd1 // mov rcx, r10 + LONG $0x44b60f42; WORD $0x1e17 // movzx eax, byte [rdi + r10 + 30] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 30], 1 + LONG $0x44b60f42; WORD $0x1f17 // movzx eax, byte [rdi + r10 + 31] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011f3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 31], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + QUAD $0x041e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 30], 4 + QUAD $0x041f374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 31], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 + QUAD $0x061e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 30], 6 + QUAD $0x061f274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 31], 6 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x061e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 6 - QUAD $0x061f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 6 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 10 - QUAD $0x0a1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 10 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 11 - QUAD $0x0b1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 11 + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0c1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 12 - QUAD $0x0c1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 12 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0d1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 13 - QUAD $0x0d1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 13 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 14 - QUAD $0x0e1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 15 - QUAD $0x0f1f06542071e3c4 // vpinsrb xmm2, xmm1, byte [rsi + rax + 31], 15 + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + QUAD $0x0b1e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 30], 11 + QUAD $0x0b1f2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 31], 11 + QUAD $0x0c1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 12 + QUAD $0x0c1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542071e3c4 // vpinsrb xmm2, xmm1, byte [rdi + rax + 31], 15 QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0e44b60f; BYTE $0x1e // movzx eax, byte [rsi + rcx + 30] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x011e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 30], 1 - LONG $0x0e44b60f; BYTE $0x1f // movzx eax, byte [rsi + rcx + 31] + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x011e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f1e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 31], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x021e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 2 - QUAD $0x021f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 2 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - QUAD $0x041e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 30], 4 - QUAD $0x041f267c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r12 + 31], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x061e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 6 - QUAD $0x061f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 6 - QUAD $0x071e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 30], 7 - QUAD $0x071f3e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 31], 7 + QUAD $0x011f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x081e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 8 - QUAD $0x081f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 8 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x091e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 30], 9 - QUAD $0x091f0e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 31], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 11 - QUAD $0x0b1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 11 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - QUAD $0x0c1e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 30], 12 - QUAD $0x0c1f367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 31], 12 + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 4 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 13 - QUAD $0x0d1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 13 - QUAD $0x0e1e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 30], 14 - QUAD $0x0e1f167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 31], 14 - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - QUAD $0x0f1e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 30], 15 - QUAD $0x0f1f167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 31], 15 + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x091e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 9 + QUAD $0x091f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x0c1e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 12 + QUAD $0x0c1f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 12 + QUAD $0x0d1e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 13 + QUAD $0x0d1f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 13 + QUAD $0x0e1e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 30], 14 + QUAD $0x0e1f0f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r9 + 31], 14 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x0f1e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 15 + QUAD $0x0f1f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -42412,2011 +43554,2001 @@ LBB7_71: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000170248c8b48 // mov rcx, qword [rsp + 368] - LONG $0x7f7ec1c4; WORD $0x8b44; BYTE $0x60 // vmovdqu yword [r11 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8b54; BYTE $0x40 // vmovdqu yword [r11 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8b64; BYTE $0x20 // vmovdqu yword [r11 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8b0c // vmovdqu yword [r11 + 4*rcx], ymm1 + LONG $0x7f7ec1c4; WORD $0x8e44; BYTE $0x60 // vmovdqu yword [r14 + 4*rcx + 96], ymm0 + LONG $0x7f7ec1c4; WORD $0x8e54; BYTE $0x40 // vmovdqu yword [r14 + 4*rcx + 64], ymm2 + LONG $0x7f7ec1c4; WORD $0x8e64; BYTE $0x20 // vmovdqu yword [r14 + 4*rcx + 32], ymm4 + LONG $0x7f7ec1c4; WORD $0x8e0c // vmovdqu yword [r14 + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB7_71 - QUAD $0x0000016824ac8b4c // mov r13, qword [rsp + 360] - QUAD $0x0000018024ac3b4c // cmp r13, qword [rsp + 384] + JNE LBB7_99 + QUAD $0x00000168248c8b48 // mov rcx, qword [rsp + 360] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] - QUAD $0x0000024024a48b4c // mov r12, qword [rsp + 576] - JNE LBB7_73 - JMP LBB7_76 + LONG $0x246c8b44; BYTE $0x04 // mov r13d, dword [rsp + 4] + QUAD $0x0000024024b48b48 // mov rsi, qword [rsp + 576] + JNE LBB7_101 + JMP LBB7_104 -LBB7_52: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB7_72: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x000001f824848948 // mov qword [rsp + 504], rax - QUAD $0x0000016824bc894c // mov qword [rsp + 360], r15 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] + QUAD $0x00000168248c8948 // mov qword [rsp + 360], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000016024848948 // mov qword [rsp + 352], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc5 // vmovd xmm0, r13d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 QUAD $0x00024024b46f7dc5; BYTE $0x00 // vmovdqa ymm14, yword [rsp + 576] -LBB7_53: +LBB7_73: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000017024848948 // mov qword [rsp + 368], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + QUAD $0x000000d824848948 // mov qword [rsp + 216], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000d824848948 // mov qword [rsp + 216], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rcx + 1] + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x0e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rcx + 2] - WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0x0f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rcx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x0f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rcx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x0f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rcx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000200248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 512], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x0f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rcx + 5] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] - QUAD $0x000000b824948948 // mov qword [rsp + 184], rdx + LONG $0x0f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rcx + 6] + QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x0f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rcx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - WORD $0x8949; BYTE $0xdd // mov r13, rbx - LONG $0x20cd8149; WORD $0x0002; BYTE $0x00 // or r13, 544 - LONG $0x246c894c; BYTE $0x38 // mov qword [rsp + 56], r13 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0x40cb8149; WORD $0x0002; BYTE $0x00 // or r11, 576 - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x60ce8149; WORD $0x0002; BYTE $0x00 // or r14, 608 - LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02200d48; WORD $0x0000 // or rax, 544 + LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02400d48; WORD $0x0000 // or rax, 576 + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xdc // mov r12, rbx + LONG $0x60cc8149; WORD $0x0002; BYTE $0x00 // or r12, 608 + LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 WORD $0x8949; BYTE $0xdf // mov r15, rbx LONG $0x80cf8149; WORD $0x0002; BYTE $0x00 // or r15, 640 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - LONG $0xa0cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 672 - QUAD $0x00000090249c8948 // mov qword [rsp + 144], rbx - WORD $0x8949; BYTE $0xcc // mov r12, rcx - LONG $0xc0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 704 - QUAD $0x000000c824a4894c // mov qword [rsp + 200], r12 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000b824bc894c // mov qword [rsp + 184], r15 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0xc0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 704 + QUAD $0x000000c024b4894c // mov qword [rsp + 192], r14 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02e00d48; WORD $0x0000 // or rax, 736 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - LONG $0x00c88149; WORD $0x0003; BYTE $0x00 // or r8, 768 - LONG $0x2444894c; BYTE $0x78 // mov qword [rsp + 120], r8 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x03200d48; WORD $0x0000 // or rax, 800 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x00cb8149; WORD $0x0003; BYTE $0x00 // or r11, 768 + QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x20ca8149; WORD $0x0003; BYTE $0x00 // or r10, 800 + QUAD $0x000001002494894c // mov qword [rsp + 256], r10 + WORD $0x8949; BYTE $0xd9 // mov r9, rbx LONG $0x40c98149; WORD $0x0003; BYTE $0x00 // or r9, 832 - LONG $0x244c894c; BYTE $0x58 // mov qword [rsp + 88], r9 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0x60cf8148; WORD $0x0003; BYTE $0x00 // or rdi, 864 - QUAD $0x000000b024bc8948 // mov qword [rsp + 176], rdi - WORD $0x8948; BYTE $0xca // mov rdx, rcx - LONG $0x80ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 896 - QUAD $0x000000a024948948 // mov qword [rsp + 160], rdx - WORD $0x8949; BYTE $0xca // mov r10, rcx - LONG $0xa0ca8149; WORD $0x0003; BYTE $0x00 // or r10, 928 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx + LONG $0x244c894c; BYTE $0x28 // mov qword [rsp + 40], r9 + WORD $0x8948; BYTE $0xda // mov rdx, rbx + LONG $0x60ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 864 + QUAD $0x000000d024948948 // mov qword [rsp + 208], rdx + WORD $0x8948; BYTE $0xde // mov rsi, rbx + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + QUAD $0x000000e0249c8948 // mov qword [rsp + 224], rbx + LONG $0x80ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 896 + QUAD $0x000000c824b48948 // mov qword [rsp + 200], rsi + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0xa0c88149; WORD $0x0003; BYTE $0x00 // or r8, 928 + LONG $0x2444894c; BYTE $0x58 // mov qword [rsp + 88], r8 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx - LONG $0x207923c4; WORD $0x2e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + r13], 1 - LONG $0x245c894c; BYTE $0x50 // mov qword [rsp + 80], r11 - LONG $0x2031a3c4; WORD $0x1e04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + r11], 2 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + r14], 3 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + r15], 4 - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 5 - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + r12], 6 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + r12], 7 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + r8], 8 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - LONG $0x2079a3c4; WORD $0x2e04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + r13], 9 - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r9], 10 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + rdi], 11 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + rdx], 12 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + r10], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + r10], 1 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r9], 2 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + r15], 3 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + r8], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + rax], 5 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r14], 6 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + rdx], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + rcx], 10 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rcx], 12 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rbx], 13 + LONG $0x244c8948; BYTE $0x60 // mov qword [rsp + 96], rcx LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + rbx], 14 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rbx], 15 + LONG $0x207963c4; WORD $0x1f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + rbx], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + r12], 3 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r15], 4 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + r13], 5 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r14], 6 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 7 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r11], 8 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r10], 9 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r9], 10 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + rdx], 11 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + rsi], 12 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + r8], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r15], 1 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r14], 2 + QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r10], 3 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r8], 4 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r9], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + rax], 6 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r11], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rax], 8 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rcx], 9 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rdx], 10 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + r12], 11 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rbx], 13 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rbx], 14 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rbx], 15 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 LONG $0xd8da8dc5 // vpminub ymm3, ymm14, ymm0 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x01011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 1 - QUAD $0x02011e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 1], 2 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x03011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 3 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x04011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 4 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x05011e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 1], 5 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x06011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 6 - QUAD $0x070126642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 1], 7 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x08011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 8 - QUAD $0x09012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 9 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0a011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 10 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x0b011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 11 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x01011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x02011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 2 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x03011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 3 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x04011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 4 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x05012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 5 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x06011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 6 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x07011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 7 QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x0c011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 12 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0d011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 13 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0e012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 14 + QUAD $0x08011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 8 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x09011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 9 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0a011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 10 QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x0f011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 15 - QUAD $0x0101166c2029a3c4 // vpinsrb xmm5, xmm10, byte [rsi + r10 + 1], 1 - QUAD $0x02010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 2 - QUAD $0x03013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 3 - WORD $0x894d; BYTE $0xfa // mov r10, r15 - QUAD $0x0401066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 4 - WORD $0x894d; BYTE $0xc5 // mov r13, r8 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x05011e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 1], 5 - QUAD $0x0601366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 1], 6 - QUAD $0x0701166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 1], 7 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 11 - QUAD $0x0c010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 + QUAD $0x0b011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 11 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0c011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 12 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0d011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 13 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x0e012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 14 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0f011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 15 + QUAD $0x01013f6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r15 + 1], 1 + QUAD $0x0201376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 1], 2 + QUAD $0x0301176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 3 + QUAD $0x0401076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 4 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + QUAD $0x05010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 5 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x06011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 6 + QUAD $0x07011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 7 + QUAD $0x0801076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 8 + QUAD $0x09010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 9 + QUAD $0x0a01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 10 + QUAD $0x0b01276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 11 + QUAD $0x0c01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 LONG $0xc374fdc5 // vpcmpeqb ymm0, ymm0, ymm3 QUAD $0x00050024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1280], ymm0 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e0106442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 1], 14 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0106442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 1], 15 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f0107442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 1], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xd06e79c5 // vmovd xmm10, eax + LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] QUAD $0x0001c024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 448] - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x010206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 2], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x020206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 2 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x030206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 3 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x040226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 2], 4 - QUAD $0x05021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 5 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x060216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 2], 6 + QUAD $0x010237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 1 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x02023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 2 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x030207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x07020e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 2], 7 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x080206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 8 - QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x09023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 10 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0b0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 11 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x0c021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 12 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 14 + QUAD $0x06020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 6 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x07021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x080207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x090207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 10 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0f0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 15 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 13 + QUAD $0x0e022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 14 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0f022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 15 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] QUAD $0x0001a0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 416] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x0202365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 2], 2 - QUAD $0x0302165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 2], 3 - QUAD $0x04022e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 2], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x05020e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 2], 5 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x06023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 6 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0702165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 2], 7 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x08020e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 2], 8 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x09020e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 2], 9 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x0a021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 10 - LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x0b021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 11 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0c022e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 2], 12 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x010306642021a3c4 // vpinsrb xmm4, xmm11, byte [rsi + r8 + 3], 1 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x02031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 2 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x03031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 3 - QUAD $0x040326642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 3], 4 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x05032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 5 - QUAD $0x060316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 6 - QUAD $0x07030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 7 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x080316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 8 - QUAD $0x09033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 9 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0a0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 10 + QUAD $0x01020f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 2], 1 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0202375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0302075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 3 + QUAD $0x0402175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 4 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0502075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 5 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x06021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 6 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x0702175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 2], 7 QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0b0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 11 - QUAD $0x0c031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 12 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x0d0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 13 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0e0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 14 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0f0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - QUAD $0x0203366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 3], 2 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0303166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 3], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0403066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0503066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 5 - QUAD $0x06033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 6 - QUAD $0x0703166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 3], 7 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0803166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 3], 8 - QUAD $0x09030e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 3], 9 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 + QUAD $0x0802175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 8 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x09021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 9 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0a021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 10 + QUAD $0x0b02275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 2], 11 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x0c02275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 2], 12 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0d021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 13 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0e021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 14 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x0f02275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 2], 15 + QUAD $0x010337642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r14 + 3], 1 + QUAD $0x02033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 2 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x030307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 3 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + QUAD $0x04033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 4 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x05031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 5 + QUAD $0x06030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 6 + QUAD $0x07031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 7 + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x08031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 8 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x09031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 9 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x0a030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 10 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0b031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 11 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0c031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 12 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0d031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 13 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0e0307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 14 + QUAD $0x0f032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 15 + QUAD $0x01030f6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rcx + 3], 1 + QUAD $0x0203376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 2 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0303376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 3 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x04031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 4 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x05030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 5 + QUAD $0x0603076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 6 + QUAD $0x0703176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 3], 7 + QUAD $0x0803176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 8 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0903176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 9 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x0a032f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 3], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 14 + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 14 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 15 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi + QUAD $0x0f0327442051a3c4 // vpinsrb xmm0, xmm5, byte [rdi + r12 + 3], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x00020024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 512] - QUAD $0x010406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 1 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x020426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 4], 2 - QUAD $0x03041e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 4], 3 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x04041e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 4], 4 - QUAD $0x05042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 5 - QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - QUAD $0x060406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 6 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x07040e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 4], 7 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x08042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 8 - QUAD $0x09043e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 4], 9 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x0a040e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 4], 10 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0b043e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 4], 11 - QUAD $0x0c041e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 4], 12 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x0d041e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 4], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 14 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x010427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 1 + QUAD $0x020437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x030407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 3 + QUAD $0x04043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 4 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x05040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 5 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x06043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x070407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 7 + QUAD $0x08041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 8 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x090437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 9 + QUAD $0x0a040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 10 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0f0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 15 + QUAD $0x0b0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 12 + LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] + QUAD $0x0d0417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 13 + QUAD $0x0e0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 15 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x01040f5c2011a3c4 // vpinsrb xmm3, xmm13, byte [rdi + r9 + 4], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x0304375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 3 + QUAD $0x04041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 4 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0504375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 5 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + QUAD $0x0604075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 6 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x07041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 7 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x08041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 8 + QUAD $0x0904175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 9 + QUAD $0x0a042f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 4], 10 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0104065c2011e3c4 // vpinsrb xmm3, xmm13, byte [rsi + rax + 4], 1 - QUAD $0x0204365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 2 - QUAD $0x0304165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 4], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0404065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05043e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 4], 5 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0604165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 4], 6 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x07040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 7 - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x0804165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 8 + QUAD $0x0b04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 11 + LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + QUAD $0x0c042f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 4], 12 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0d041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 13 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0e04175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 14 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 15 + QUAD $0x010527642001a3c4 // vpinsrb xmm4, xmm15, byte [rdi + r12 + 5], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0904065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 9 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 11 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0c04165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 12 + QUAD $0x020507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 2 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x030527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 3 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x040527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 4 + QUAD $0x05050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 5 + QUAD $0x06053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 6 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x07053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 7 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x08050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 8 + QUAD $0x090537642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 5], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 13 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x0e04165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 4], 14 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 15 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x010506642001e3c4 // vpinsrb xmm4, xmm15, byte [rsi + rax + 5], 1 - QUAD $0x020526642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 5], 2 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x030526642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 5], 3 - QUAD $0x04051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 4 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x05051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 5 - QUAD $0x060506642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 5], 6 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x070506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 7 - QUAD $0x08052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 8 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x090506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 9 - QUAD $0x0a050e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 5], 10 - QUAD $0x0b053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 11 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x0c053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 12 - QUAD $0x0d051e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 5], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 14 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0f0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 15 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - QUAD $0x01051e6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rsi + r11 + 5], 1 - QUAD $0x0205366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 2 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x0305366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0405066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 4 - QUAD $0x05053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 5 - QUAD $0x0605166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 6 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0705166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 7 - QUAD $0x08050e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 5], 8 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x09050e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 5], 9 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0a050e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 5], 10 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0b050e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 5], 11 + QUAD $0x0a0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 10 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0b050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 12 + QUAD $0x0d0517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 15 + QUAD $0x01050f6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r9 + 5], 1 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x02050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 2 QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c050e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 5], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 13 + QUAD $0x03050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x04050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 4 + QUAD $0x0505376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 5 + QUAD $0x0605076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 6 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x0705376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 5], 7 + QUAD $0x08051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0905076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x0c052f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 5], 12 + QUAD $0x0d051f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 5], 13 LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 - QUAD $0x0e0516442051a3c4 // vpinsrb xmm0, xmm5, byte [rsi + r10 + 5], 14 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - LONG $0x0e7cb60f; BYTE $0x0a // movzx edi, byte [rsi + rcx + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] - QUAD $0x0f052e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 5], 15 + QUAD $0x0e0517442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rdx + 5], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f0507442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 5], 15 LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - LONG $0x0e7cb60f; BYTE $0x0a // movzx edi, byte [rsi + rcx + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x010606442019e3c4 // vpinsrb xmm0, xmm12, byte [rsi + rax + 6], 1 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x020616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 6], 2 - WORD $0x894d; BYTE $0xe0 // mov r8, r12 - QUAD $0x030626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 6], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 4 - QUAD $0x05061e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 6], 5 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x06060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 6 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x070626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 6], 7 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x08060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 8 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x09061e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 6], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 10 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0b060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 11 - QUAD $0x0c063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 12 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x0d063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 14 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0f060e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 6], 15 - QUAD $0x01061e6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rsi + r11 + 6], 1 - QUAD $0x02060e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 6], 2 - WORD $0x894d; BYTE $0xf3 // mov r11, r14 - QUAD $0x0306366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0506066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 5 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x06060e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 6], 6 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0706366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 7 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0806166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 6], 8 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0906066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 9 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a06066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b06066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c06066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d06066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 13 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e06066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 14 - QUAD $0x0f062e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 6], 15 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x010706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 1 - QUAD $0x020716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 2 - QUAD $0x030706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 7], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x050706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 5 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x060716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 6 - QUAD $0x070726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 7], 7 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x080716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 8 - QUAD $0x09071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 9 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0a0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 10 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0b0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 11 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0c0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 12 - QUAD $0x0d073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 13 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0e0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 14 - QUAD $0x0f070e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 7], 15 - LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] - QUAD $0x01073e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 7], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 2 - QUAD $0x03071e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 7], 3 - QUAD $0x04073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 4 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0507164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 5 - QUAD $0x06070e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 7], 6 - QUAD $0x0707364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 7], 7 - QUAD $0x0807164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 7], 8 - WORD $0x894d; BYTE $0xd6 // mov r14, r10 + QUAD $0x010607442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rax + 6], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0907064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 9 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 11 + QUAD $0x020607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 2 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x03062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 3 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + QUAD $0x040627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x050607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 5 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x060617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 6 + QUAD $0x07063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 7 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x080627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 8 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x09060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a0637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 10 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0b0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 11 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x0c0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 12 + QUAD $0x0d0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 14 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0f0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 15 + QUAD $0x01060f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r9 + 6], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0206076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 2 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 14 + QUAD $0x0306076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0406076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 4 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x05061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 5 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x06061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 6 + QUAD $0x0706376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 7 + QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] + QUAD $0x0806376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 8 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x09061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 9 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0a061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 10 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x0b061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 11 + LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] + QUAD $0x0c061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 12 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0d061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 13 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0e061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 14 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x0f061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 15 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x01071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x02071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 2 + QUAD $0x03072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 3 + QUAD $0x04071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 4 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x05072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 5 + QUAD $0x060717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 6 + QUAD $0x07073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 7 + QUAD $0x080727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 8 + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + QUAD $0x0a0737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 7], 10 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x0b073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 11 + QUAD $0x0c0707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 12 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0d070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 13 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x0e070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 14 + QUAD $0x0f0717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 15 + QUAD $0x01070f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 7], 1 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x02070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 2 + QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] + QUAD $0x0307074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 7], 3 + QUAD $0x0407074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 4 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0507274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 + QUAD $0x0807374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0907074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] + QUAD $0x0c071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 - QUAD $0x0f072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 15 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc06ef9c5 // vmovd xmm0, eax LONG $0x3875e3c4; WORD $0x01ca // vinserti128 ymm1, ymm1, xmm2, 1 QUAD $0x0004e0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1248], ymm1 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x010806542031a3c4 // vpinsrb xmm2, xmm9, byte [rsi + r8 + 8], 1 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x02080e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 8], 2 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x030806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x050806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 5 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x060816542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 8], 6 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - QUAD $0x070826542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 8], 7 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x080826542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 8], 8 - QUAD $0x09081e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 8], 9 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0a082e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 8], 10 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x0b081e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 8], 11 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] + QUAD $0x010817542031a3c4 // vpinsrb xmm2, xmm9, byte [rdi + r10 + 8], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x02081f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 8], 2 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x030817542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 8], 3 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x040837542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 8], 4 + QUAD $0x05082f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 8], 5 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x06082f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 8], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x070807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 7 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0c0806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 12 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d0806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 13 + QUAD $0x080807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x090807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a0807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 10 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x0b083f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 8], 11 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x0c083f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 8], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d0807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e0807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 14 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 14 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0f080e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 8], 15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 - QUAD $0x01083e6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rsi + r15 + 8], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x02083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 2 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x03083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 4 - QUAD $0x0508166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 5 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x06083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 6 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x07083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 7 - QUAD $0x0808366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 8], 8 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x0908366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 8], 9 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - QUAD $0x0a08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 10 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0b08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 11 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0c083e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 8], 12 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0d08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 13 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0e08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 14 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x0f083e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 8], 15 + QUAD $0x0f0807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0108076c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rax + 8], 1 + QUAD $0x02080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 2 + QUAD $0x0308076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 3 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0408076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 4 + QUAD $0x0508276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0608076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0708076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 7 + QUAD $0x0808376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 8 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0908376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 9 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x0a08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 10 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0b080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 11 + QUAD $0x0c081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 12 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0d080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 13 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x0e080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 14 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x0f081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 15 LONG $0x3855e3c4; WORD $0x01d2 // vinserti128 ymm2, ymm5, xmm2, 1 LONG $0xeada8dc5 // vpminub ymm5, ymm14, ymm2 - QUAD $0x010906742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r8 + 9], 1 - QUAD $0x02090e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r9 + 9], 2 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x030916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 3 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x04093e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r15 + 9], 4 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x050916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 5 - QUAD $0x060916742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r10 + 9], 6 - QUAD $0x07091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 7 - QUAD $0x080926742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r12 + 9], 8 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x090916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 9 - QUAD $0x0a092e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r13 + 9], 10 - QUAD $0x0b091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 11 + QUAD $0x010917742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r10 + 9], 1 + QUAD $0x02091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 2 + QUAD $0x030917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 3 + QUAD $0x040937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 4 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x050917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 5 + QUAD $0x06092f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 9], 6 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x070917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 7 QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0c0916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 12 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x0d090e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r9 + 9], 13 - QUAD $0x0e0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 14 - WORD $0x8949; BYTE $0xc4 // mov r12, rax - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0f0916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 15 - QUAD $0x01090e7c2021e3c4 // vpinsrb xmm7, xmm11, byte [rsi + rcx + 9], 1 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - QUAD $0x0209067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 9], 2 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0309067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0409067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0509067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 5 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x06091e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 9], 6 - QUAD $0x07093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 7 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0809067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 8 - QUAD $0x0909367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 9], 9 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 10 + QUAD $0x080917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 8 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x090917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 10 + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + QUAD $0x0b090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 11 + QUAD $0x0c093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 12 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0d0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 13 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x0e093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0f0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 15 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0109377c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rsi + 9], 1 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0209377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 2 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x03091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 3 + QUAD $0x0409077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 4 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0509377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 5 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0609377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 6 + QUAD $0x0709077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0809077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 8 + QUAD $0x0909377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 9 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x0a09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 11 LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 14 + QUAD $0x0c09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 12 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0d09077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 13 + QUAD $0x0e090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 14 + WORD $0x8949; BYTE $0xcc // mov r12, rcx LONG $0xd574edc5 // vpcmpeqb ymm2, ymm2, ymm5 QUAD $0x0004c024947ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xd76ef9c5 // vmovd xmm2, edi + QUAD $0x0f091f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r11 + 9], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xd06ef9c5 // vmovd xmm2, eax LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x0004a024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x010a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 1 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax + LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] + QUAD $0x010a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x020a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 2 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x030a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x040a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 4 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x050a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 5 + QUAD $0x060a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 6 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x020a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 2 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x030a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 3 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x040a3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 10], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x050a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 5 - WORD $0x894d; BYTE $0xd6 // mov r14, r10 - QUAD $0x060a165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 10], 6 - QUAD $0x070a1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 10], 7 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x080a1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 10], 8 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x090a165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 10], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a0a3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 10], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b0a3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 10], 11 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0c0a3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 10], 12 - QUAD $0x0d0a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 13 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - QUAD $0x0e0a265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 10], 14 - QUAD $0x0f0a165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 10], 15 + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x080a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x090a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 9 + QUAD $0x0a0a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 10 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0b0a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 13 + QUAD $0x0e0a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 14 + QUAD $0x0f0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x010a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x020a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x040a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 4 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x050a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 5 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x060a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 6 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x070a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 7 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x080a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 8 + LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + QUAD $0x090a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 9 + QUAD $0x0a0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 10 LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x010a16642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 10], 1 - QUAD $0x020a06642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 10], 2 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x040a16642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 10], 4 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x050a16642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 10], 5 - QUAD $0x060a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 6 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x070a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 7 - QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] - QUAD $0x080a06642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 10], 8 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x090a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 9 + QUAD $0x0b0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 11 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x0c0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 12 + QUAD $0x0d0a07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 10], 13 + QUAD $0x0e0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 14 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x0f0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 15 + QUAD $0x010b1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 11], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x020b17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 11], 2 + QUAD $0x030b0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 11], 3 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x040b17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 11], 4 + QUAD $0x050b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 5 + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + QUAD $0x060b2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 11], 6 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x070b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 7 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x080b2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 11], 8 QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x0a0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 10 - LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x0b0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 11 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0c0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 12 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0d0a3e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 10], 13 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x0e0a26642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 10], 14 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0f0a1e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 10], 15 - QUAD $0x010b0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 11], 1 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x020b0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 11], 2 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x030b0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 11], 3 - QUAD $0x040b2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 11], 4 - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - QUAD $0x050b06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 11], 5 - QUAD $0x060b36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 11], 6 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x070b36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 11], 7 - QUAD $0x080b1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 11], 8 - QUAD $0x090b16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 11], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a0b0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 11], 10 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x0b0b2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 11], 11 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0c0b06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 11], 12 + QUAD $0x090b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 9 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0a0b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 10 + QUAD $0x0b0b17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 11], 11 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0c0b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 12 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0d0b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 13 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0e0b1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 11], 14 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0f0b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 15 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x010b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 1 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x020b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 2 + QUAD $0x030b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x040b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 4 + QUAD $0x050b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 5 + QUAD $0x060b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 6 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x070b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x080b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 8 + QUAD $0x090b3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 11], 9 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d0b06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 11], 13 - QUAD $0x0e0b0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 11], 14 - WORD $0x894d; BYTE $0xca // mov r10, r9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0f0b06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 11], 15 + QUAD $0x0a0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 10 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x010b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x020b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 2 - QUAD $0x030b3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 11], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x040b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 4 - QUAD $0x050b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 5 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x060b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 6 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x070b3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 11], 7 - QUAD $0x080b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 8 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x090b3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 11], 9 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - QUAD $0x0a0b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 10 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0b0b3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 11], 11 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0c0b264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 11], 12 - QUAD $0x0d0b3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 11], 13 + QUAD $0x0b0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 11 + QUAD $0x0c0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 12 + QUAD $0x0d0b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000480249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm3 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e0b3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 11], 14 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - LONG $0x3e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rdi + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0f0b3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 11], 15 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0f0b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x3e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rdi + 13] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x010c3e4c2069e3c4 // vpinsrb xmm1, xmm2, byte [rsi + rdi + 12], 1 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x020c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 12], 2 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x030c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 12], 3 - QUAD $0x040c1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 12], 4 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x050c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 12], 5 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x060c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 12], 6 - QUAD $0x070c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 12], 7 - QUAD $0x080c1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 12], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x090c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 12], 9 - QUAD $0x0a0c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 12], 10 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - QUAD $0x0b0c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 12], 11 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x0c0c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 12], 12 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0d0c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 12], 13 - QUAD $0x0e0c164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 12], 14 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0f0c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 12], 15 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x010c0e542051e3c4 // vpinsrb xmm2, xmm5, byte [rsi + rcx + 12], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x020c3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 12], 2 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x030c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 3 - QUAD $0x040c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x050c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 5 - QUAD $0x060c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 6 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x070c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 7 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x080c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 8 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x010c3f4c2069a3c4 // vpinsrb xmm1, xmm2, byte [rdi + r15 + 12], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x090c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 9 - QUAD $0x0a0c06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 12], 10 - LONG $0x24548b4c; BYTE $0x08 // mov r10, qword [rsp + 8] - QUAD $0x0b0c16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 12], 11 - QUAD $0x0c0c26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 12], 12 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x0d0c06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 12], 13 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x0e0c26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 12], 14 + QUAD $0x020c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 2 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 15 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x010d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x020d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 2 - QUAD $0x030d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 13], 3 - QUAD $0x040d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x050d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 5 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x060d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 13], 6 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x070d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 7 - QUAD $0x080d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 8 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x090d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 9 + QUAD $0x030c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 3 + QUAD $0x040c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 12], 4 + QUAD $0x050c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 12], 5 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x060c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 12], 6 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x070c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 12], 7 + QUAD $0x080c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 12], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x090c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a0c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 10 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0b0c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 12], 11 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x0c0c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 12], 12 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 10 - QUAD $0x0b0d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 11 - QUAD $0x0c0d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 13], 12 - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d0d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 13 + QUAD $0x0d0c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 13 + QUAD $0x0e0c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 12], 14 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 14 - QUAD $0x0f0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 15 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x010d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 1 - QUAD $0x020d3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 13], 2 + QUAD $0x0f0c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x010c07542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rax + 12], 1 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x020c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 2 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x030c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x030d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x040d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 4 - QUAD $0x050d0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 13], 5 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x060d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 6 - QUAD $0x070d16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 13], 7 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x080d2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 13], 8 + QUAD $0x040c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 4 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x050c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x060c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 6 + QUAD $0x070c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 7 + QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] + QUAD $0x080c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 8 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x090c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 9 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0a0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 10 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x0b0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 12 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0d0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 13 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0e0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 14 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 15 + QUAD $0x010d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x090d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 9 + QUAD $0x020d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x030d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x040d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 4 + QUAD $0x050d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 5 + QUAD $0x060d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 6 + QUAD $0x070d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 7 + QUAD $0x080d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 13], 8 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a0d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 10 - QUAD $0x0b0d16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 13], 11 - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c0d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 12 - QUAD $0x0d0d06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 13], 13 - QUAD $0x0e0d26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 13], 14 + QUAD $0x090d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 10 + QUAD $0x0b0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 11 + QUAD $0x0c0d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 13], 12 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0d0d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e0d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 14 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0f0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x010d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 1 + QUAD $0x020d0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 13], 2 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x030d37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 13], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x040d0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 13], 4 + QUAD $0x050d1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 13], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x060d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x070d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 7 + QUAD $0x080d37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 13], 8 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + QUAD $0x090d27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 13], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a0d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 10 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x0b0d2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 13], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c0d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d0d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 13 + QUAD $0x0e0d1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 13], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000440248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 15 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - LONG $0x067cb60f; BYTE $0x0e // movzx edi, byte [rsi + rax + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x0f0d27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 13], 15 + QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x0e3f // movzx eax, byte [rdi + r15 + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x00042024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm0 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x0e // movzx edi, byte [rsi + rax + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x010e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x020e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 2 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x030e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 14], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x040e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 4 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x050e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 14], 5 - QUAD $0x060e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 6 - QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] - QUAD $0x070e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 7 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x080e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 8 - QUAD $0x090e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 9 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0a0e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 10 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0b0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 11 - QUAD $0x0c0e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 14], 12 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0d0e3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 14], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e0e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 14], 14 - QUAD $0x0f0e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 14], 15 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x010e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x020e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 2 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x030e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 3 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - QUAD $0x040e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 14], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x050e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 5 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x060e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 6 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x070e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 7 - QUAD $0x080e2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 14], 8 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x090e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 14], 9 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0a0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 10 - QUAD $0x0b0e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 14], 11 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - QUAD $0x0c0e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 14], 12 - QUAD $0x0d0e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 14], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0f0e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 14], 15 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - LONG $0x3e7cb60f; BYTE $0x0f // movzx edi, byte [rsi + rdi + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x010f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 1 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x020f2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 15], 2 - QUAD $0x030f16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 15], 3 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x040f16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 15], 4 - QUAD $0x050f16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 15], 5 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x060f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 6 - QUAD $0x070f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 7 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x080f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x090f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 9 - QUAD $0x0a0f1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 15], 10 - QUAD $0x0b0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 11 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x020e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x040e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 4 + QUAD $0x050e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x070e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 7 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0c0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 12 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 13 - QUAD $0x0e0f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 14 + QUAD $0x080e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x090e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 9 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0a0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 10 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0f0f06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 15], 15 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x0f // movzx edi, byte [rsi + rax + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x010f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x020f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 2 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x030f1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 15], 3 - QUAD $0x040f365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 15], 4 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - QUAD $0x050f365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 15], 5 + QUAD $0x0b0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 11 + QUAD $0x0c0e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 12 + QUAD $0x0d0e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 13 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0e0e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x020e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 2 + QUAD $0x030e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 3 + QUAD $0x040e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 4 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + QUAD $0x050e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 5 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x060e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x070e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 7 + QUAD $0x080e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x090e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 9 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0a0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 10 + QUAD $0x0b0e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 14], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 14 + QUAD $0x0f0e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 15 + LONG $0x44b60f42; WORD $0x0f3f // movzx eax, byte [rdi + r15 + 15] + LONG $0xd06ef9c5 // vmovd xmm2, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x010f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 1 + QUAD $0x020f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x030f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x040f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 4 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x060f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 6 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x070f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 7 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x080f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 8 - QUAD $0x090f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 9 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - QUAD $0x0a0f265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 15], 10 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0b0f3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 15], 11 - QUAD $0x0c0f0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 15], 12 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0d0f0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 15], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e0f3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 15], 14 - QUAD $0x0f0f065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 15], 15 + QUAD $0x050f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x060f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 6 + QUAD $0x070f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 7 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x080f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 8 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x090f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 9 + QUAD $0x0a0f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 10 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x0b0f3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 15], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 12 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x0d0f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 13 + QUAD $0x0e0f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 14 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0f0f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0f // movzx eax, byte [rdi + rax + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x010f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x020f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x030f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 3 + QUAD $0x040f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 4 + QUAD $0x050f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 5 + QUAD $0x060f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x070f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 7 + QUAD $0x080f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x090f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 9 + QUAD $0x0a0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 10 + QUAD $0x0b0f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0d0f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 14 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - LONG $0x3e7cb60f; BYTE $0x10 // movzx edi, byte [rsi + rdi + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x01103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 1 - QUAD $0x02102e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 16], 2 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x03103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 3 - QUAD $0x041016442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 16], 4 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x051016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 5 - QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] - QUAD $0x06102e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 16], 6 - QUAD $0x07103e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 16], 7 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x081016442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 16], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x09103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 11 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0c103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 12 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0d103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 13 - QUAD $0x0e101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 14 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x0f1006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 15 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x3e7cb60f; BYTE $0x10 // movzx edi, byte [rsi + rdi + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x01103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 1 - QUAD $0x02100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 2 - QUAD $0x03101e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 16], 3 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x04100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 4 - QUAD $0x0510364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 16], 5 - QUAD $0x0610064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 6 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0710364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 16], 7 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + LONG $0x3744b60f; BYTE $0x10 // movzx eax, byte [rdi + rsi + 16] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x011007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 1 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x02101f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 16], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 3 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x04100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x071007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 7 + QUAD $0x081017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 8 + QUAD $0x09100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 9 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x0a1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 10 + QUAD $0x0b103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 11 + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x0c1037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 12 + QUAD $0x0d1027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 14 + QUAD $0x0f101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 15 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x100f // movzx eax, byte [rdi + r9 + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0110074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 1 + QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] + QUAD $0x02103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0310074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0810064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 8 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x09101e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 16], 9 - QUAD $0x0a10264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 10 + QUAD $0x0510074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 5 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0610174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 6 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x07101f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 16], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0810074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0910074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 9 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x0a10274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 10 + QUAD $0x0b102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 11 LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 12 - QUAD $0x0d100e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 16], 13 + QUAD $0x0c10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 12 + QUAD $0x0d10074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 14 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x0f102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 15 + LONG $0x3744b60f; BYTE $0x11 // movzx eax, byte [rdi + rsi + 17] + LONG $0xd06ef9c5 // vmovd xmm2, eax LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 14 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0f101e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 16], 15 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - LONG $0x7cb60f42; WORD $0x113e // movzx edi, byte [rsi + r15 + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x01110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 1 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x02110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 2 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x03110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 3 - QUAD $0x041116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 4 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x05110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 5 - QUAD $0x06112e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 17], 6 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x07110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 7 - QUAD $0x081116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 8 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x09110e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 17], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 10 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x0b112e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 17], 11 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x0c1116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 12 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x0d1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 13 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0e1116542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 17], 14 - QUAD $0x0f1106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 15 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - LONG $0x7cb60f42; WORD $0x1126 // movzx edi, byte [rsi + r12 + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0111165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 1 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x0211165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 2 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0311165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 3 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0411165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 4 - QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] - QUAD $0x0511065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 17], 5 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x06113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 6 - QUAD $0x0711365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 17], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x08113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 8 - QUAD $0x09111e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 17], 9 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0a113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 10 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0b113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 13 - QUAD $0x0e11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 14 + QUAD $0x011107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 1 + QUAD $0x02111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 3 + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 6 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x07111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 7 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x081137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 9 + QUAD $0x0a1117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 10 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0b1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 11 + QUAD $0x0c1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 12 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0d1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 15 + LONG $0x44b60f42; WORD $0x110f // movzx eax, byte [rdi + r9 + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x0111175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 1 + QUAD $0x02113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0311075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0411075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 4 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + QUAD $0x0611175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 6 + QUAD $0x07111f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 17], 7 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x08110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + QUAD $0x0a11275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 11 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x0c11275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 12 + QUAD $0x0d11075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 13 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x0e11075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x0f111e4c2061a3c4 // vpinsrb xmm1, xmm3, byte [rsi + r11 + 17], 15 + QUAD $0x0f112f4c2061a3c4 // vpinsrb xmm1, xmm3, byte [rdi + r13 + 17], 15 LONG $0xd8da8dc5 // vpminub ymm3, ymm14, ymm0 LONG $0xc374fdc5 // vpcmpeqb ymm0, ymm0, ymm3 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 LONG $0x3875e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm1, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - LONG $0x7cb60f42; WORD $0x123e // movzx edi, byte [rsi + r15 + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x011206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 1 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x02121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 2 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x031236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 18], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 4 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x05121e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 18], 5 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x061206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 6 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f44b60f; BYTE $0x12 // movzx eax, byte [rdi + rcx + 18] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x01123f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 18], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 2 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x03122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x041207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x071206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 7 + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + QUAD $0x07121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 7 + QUAD $0x081237442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 18], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 10 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0b121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 12 + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + QUAD $0x0d1237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 13 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x0e1237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 14 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0f1237442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 18], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0112174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0212074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 2 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x03121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0412074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 4 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0512074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 5 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0612174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 6 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x081206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 8 - QUAD $0x09120e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 18], 9 - QUAD $0x0a120e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 18], 10 - QUAD $0x0b122e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 18], 11 - QUAD $0x0c1216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 12 + QUAD $0x0712074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 7 + QUAD $0x08120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 8 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x09120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 9 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 14 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0f1206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 15 - LONG $0x7cb60f42; WORD $0x1226 // movzx edi, byte [rsi + r12 + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + QUAD $0x0a12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 10 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0112064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 1 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x0212264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 18], 2 + QUAD $0x0b12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 11 + QUAD $0x0c12274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 13 + QUAD $0x0e12074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 14 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 15 + LONG $0x0f44b60f; BYTE $0x13 // movzx eax, byte [rdi + rcx + 19] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x01133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 2 + QUAD $0x03132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 3 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x041307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 5 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x06132f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 19], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x071307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x081307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 10 + QUAD $0x0b131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + QUAD $0x0d1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 13 + QUAD $0x0e1337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 14 + QUAD $0x0f1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 15 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x133f // movzx eax, byte [rdi + r15 + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0113075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 + QUAD $0x03131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0312064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 3 - QUAD $0x0412164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 4 - QUAD $0x0512064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 18], 5 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x0612064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 18], 6 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0712064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 7 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0812164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 18], 8 + QUAD $0x0413075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 4 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0513275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 5 + QUAD $0x0613175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 19], 6 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x0713175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 19], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0813075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 8 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + QUAD $0x09130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 11 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x0c13375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 12 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x0d130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x0f130f442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rcx + 19], 15 + LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 + QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x14 // movzx eax, byte [rdi + rax + 20] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x011407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0912064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 9 + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 3 + QUAD $0x041407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x06142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x071407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x081407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 8 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x091417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 9 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0a1437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 10 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x0b1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 11 + QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] + QUAD $0x0c141f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 20], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 13 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x0e142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 15 + LONG $0x44b60f42; WORD $0x143f // movzx eax, byte [rdi + r15 + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0114074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0414074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 4 + QUAD $0x0514274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 20], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0614074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 6 + QUAD $0x0714174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0814074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 8 + QUAD $0x09141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 11 + QUAD $0x0c14374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 12 + QUAD $0x0d140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 13 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0e141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 14 + QUAD $0x0f140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x15 // movzx eax, byte [rdi + rax + 21] + LONG $0xd06ef9c5 // vmovd xmm2, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x011507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 1 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x02153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 3 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x04150f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 21], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 6 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x071527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x081507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 8 + QUAD $0x091517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 9 + QUAD $0x0a1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 10 + QUAD $0x0b1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 11 + QUAD $0x0c151f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 21], 12 + WORD $0x894d; BYTE $0xde // mov r14, r11 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 13 + QUAD $0x0e152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 14 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0f1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 15 + QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x151f // movzx eax, byte [rdi + r11 + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0115075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 1 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0215375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0415175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 4 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x05150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0715075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x0a15175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 13 + QUAD $0x0e151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 14 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 15 + LONG $0x387563c4; WORD $0x01d8 // vinserti128 ymm11, ymm1, xmm0, 1 + LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 + QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x011607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 1 + QUAD $0x02163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 2 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x03163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 3 + QUAD $0x04160f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 22], 4 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x05161f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 22], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 6 + QUAD $0x071627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 7 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x08162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 8 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a12064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 10 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0b12164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 11 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - QUAD $0x0c120e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 18], 12 + QUAD $0x091607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d12064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 18], 13 - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x0e123e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 18], 14 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 15 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - LONG $0x3e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rdi + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x01133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 1 - QUAD $0x02131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 2 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - QUAD $0x031336542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 19], 3 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x04131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 4 - QUAD $0x05131e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 19], 5 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x06131e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 19], 6 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x07133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 7 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x08133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x09133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 11 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x0c1336542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 19], 12 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0d133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 14 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x0f133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 15 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x3e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rdi + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x01133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 1 - QUAD $0x0213265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 19], 2 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x03133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 5 - QUAD $0x0613065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 6 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x07133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 7 - QUAD $0x0813165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 19], 8 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x09133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 9 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0a133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 10 - QUAD $0x0b13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 11 - QUAD $0x0c130e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 19], 12 - QUAD $0x0d13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 13 - QUAD $0x0e133e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 19], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x0f130e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rcx + 19], 15 - LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 + QUAD $0x0a1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 10 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + QUAD $0x0c1637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 12 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0d1637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 14 + QUAD $0x0f1607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 15 + LONG $0x44b60f42; WORD $0x161f // movzx eax, byte [rdi + r11 + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x01160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 1 + QUAD $0x0216374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 2 + QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] + QUAD $0x0316074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 3 + QUAD $0x0416174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 4 + QUAD $0x05160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0616074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0716074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 7 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x0816274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a16174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 22], 10 + LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] + QUAD $0x0b16174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 22], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] + QUAD $0x0e161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 14 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 15 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + LONG $0x3744b60f; BYTE $0x17 // movzx eax, byte [rdi + rsi + 23] + LONG $0xd06ef9c5 // vmovd xmm2, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x011707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x021717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 2 + QUAD $0x03173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 3 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - LONG $0x067cb60f; BYTE $0x14 // movzx edi, byte [rsi + rax + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x011416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 1 + QUAD $0x041707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 4 + QUAD $0x05171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 5 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x06170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 6 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x021406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 2 - QUAD $0x03142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 3 - QUAD $0x04141e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 20], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x051406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 5 - QUAD $0x06141e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 20], 6 - QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] - QUAD $0x07143e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 20], 7 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x08141e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 20], 8 - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - QUAD $0x091426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 10 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x0b140e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 20], 11 - QUAD $0x0c1436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 20], 12 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x0d1436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 20], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 14 + QUAD $0x071707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 7 + QUAD $0x08172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 9 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x0a173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 10 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0f1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 15 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - LONG $0x7cb60f42; WORD $0x1406 // movzx edi, byte [rsi + r8 + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x0114164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 20], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 2 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x03141e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 20], 3 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x04140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x05140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 5 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x06140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 6 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x07140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x08143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 8 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x09143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 9 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0a143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 10 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0b143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 14 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0f143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 15 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - LONG $0x3e7cb60f; BYTE $0x15 // movzx edi, byte [rsi + rdi + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 1 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x02152e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 21], 2 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x031516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 3 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x041516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 4 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x051516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 5 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x06153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 6 - QUAD $0x07153e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 21], 7 - QUAD $0x08151e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 21], 8 - QUAD $0x091526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0a153e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 21], 10 - QUAD $0x0b150e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 21], 11 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0c153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 12 - QUAD $0x0d1536542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 21], 13 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0e151e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 21], 14 - QUAD $0x0f1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 15 - WORD $0x8949; BYTE $0xc1 // mov r9, rax - LONG $0x7cb60f42; WORD $0x1506 // movzx edi, byte [rsi + r8 + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0115165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 1 + QUAD $0x0b1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 12 + QUAD $0x0d1737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 14 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0f171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 15 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0215065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 2 - QUAD $0x03151e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 21], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0415065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 5 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x06153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 6 - QUAD $0x07150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 7 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x0815265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 21], 8 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x09150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 9 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x0a151e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 21], 10 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0b150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 13 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 14 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 15 - LONG $0x387563c4; WORD $0x01d8 // vinserti128 ymm11, ymm1, xmm0, 1 - LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 - QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - LONG $0x0e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rcx + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x01163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 1 - QUAD $0x02162e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 22], 2 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x03163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 3 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x04163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 4 - QUAD $0x051616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 5 - QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] - QUAD $0x06162e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 22], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x071616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 7 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x081606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 22], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x09163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 9 - QUAD $0x0a163e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 22], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 11 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x0c1616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 22], 12 - QUAD $0x0d1636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 22], 13 - QUAD $0x0e161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 14 - QUAD $0x0f160e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 22], 15 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x3e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rdi + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x01163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 1 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x02163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 2 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x03160e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 22], 3 - QUAD $0x0416064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 4 + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x01170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 1 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0516064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 5 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0616064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 6 + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + QUAD $0x0317075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0417075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 4 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0517375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 5 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x06172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 6 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x0717075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 7 + QUAD $0x0817275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 8 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0716064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 7 - QUAD $0x0816264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 22], 8 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0916064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 9 - QUAD $0x0a161e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 22], 10 - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - QUAD $0x0b16264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 22], 11 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c16064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d16064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 14 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0f163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 15 - LONG $0x0e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rcx + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x01171e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 23], 1 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x02170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 2 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x03170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 4 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x05170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 5 - QUAD $0x06172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 6 - QUAD $0x071716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 7 - QUAD $0x081706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 23], 8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x09170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 10 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x0b172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 11 - QUAD $0x0c1716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 23], 12 - QUAD $0x0d1736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 14 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0f1736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 15 - QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - LONG $0x7cb60f42; WORD $0x1716 // movzx edi, byte [rsi + r10 + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x01170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 1 - QUAD $0x02173e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 23], 2 - QUAD $0x03170e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 23], 3 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0417165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 23], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x05170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 5 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x06173e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 23], 6 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0717065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 23], 7 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x08171e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 23], 8 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x09170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 9 - QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] - QUAD $0x0a170e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 23], 10 - QUAD $0x0b17265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 11 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0c170e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 23], 12 - QUAD $0x0d17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 13 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x0e17265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 14 + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 10 + QUAD $0x0b17175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 23], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 12 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x0d170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 13 + QUAD $0x0e171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f1706442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rax + 23], 15 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f1707442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 23], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - LONG $0x0e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rcx + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x01181e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 24], 1 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x02183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 2 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x03180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 3 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x04180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 4 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x05183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 5 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x06180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 6 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x07181e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 24], 7 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x08183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x09180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 10 - QUAD $0x0b182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 11 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0c183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 12 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0d183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 14 - QUAD $0x0f1836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 24], 15 - LONG $0x7cb60f42; WORD $0x1816 // movzx edi, byte [rsi + r10 + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x01183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 1 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x02182e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 24], 2 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x03183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 3 - QUAD $0x0418164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 4 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0518164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 5 - QUAD $0x06183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 6 - QUAD $0x0718064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 24], 7 - QUAD $0x08181e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 24], 8 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0918164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 9 - QUAD $0x0a180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 10 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0b18164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 11 - QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] - QUAD $0x0c18064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 24], 12 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0d183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 13 - QUAD $0x0e18264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 14 - QUAD $0x0f18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 15 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - LONG $0x7cb60f42; WORD $0x190e // movzx edi, byte [rsi + r9 + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x011906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x021906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 2 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x031906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 4 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x051916542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 25], 5 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x06191e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 25], 6 - QUAD $0x07191e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 25], 7 + LONG $0x3744b60f; BYTE $0x18 // movzx eax, byte [rdi + rsi + 24] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] + QUAD $0x01181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 1 + QUAD $0x021817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 3 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x041827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 5 + QUAD $0x06180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 6 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x07180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x081807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 8 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x091817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 9 + QUAD $0x0a183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 10 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0b1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 11 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0c1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 14 + QUAD $0x0f181f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 24], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0118374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0318074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0418074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 4 + QUAD $0x0518374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 5 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + QUAD $0x06182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 6 + QUAD $0x0718074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 7 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x08182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0918074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 9 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0a183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 10 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0b18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 12 + QUAD $0x0d180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 13 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x0e18374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 14 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x0f180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x01191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 3 + QUAD $0x041927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 6 + QUAD $0x07190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 7 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x08190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 8 + QUAD $0x091917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 10 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0b1917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 11 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x0c1907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 15 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x1927 // movzx eax, byte [rdi + r12 + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0119375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 1 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0219375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0319075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 3 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x04191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 4 + QUAD $0x05191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 5 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x06191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 6 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x081906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 8 - QUAD $0x09190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 9 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0a1926542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 25], 10 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0b1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 11 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0c193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 12 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x0d1936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e190e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 25], 14 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x0f193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 15 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - LONG $0x0e7cb60f; BYTE $0x19 // movzx edi, byte [rsi + rcx + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x01190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 1 - QUAD $0x02192e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 25], 2 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x03193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x05190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 5 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x06192e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 25], 6 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x07193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 7 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x08191e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 25], 8 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x09193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 9 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0a193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 10 - QUAD $0x0b19165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 25], 11 - QUAD $0x0c19065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 25], 12 - QUAD $0x0d193e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 25], 13 + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x08192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 8 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x09192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 9 + QUAD $0x0a193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 10 + QUAD $0x0b19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 11 + LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] + QUAD $0x0c193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 13 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e190e4c2061e3c4 // vpinsrb xmm1, xmm3, byte [rsi + rcx + 25], 14 + QUAD $0x0e19374c2061a3c4 // vpinsrb xmm1, xmm3, byte [rdi + r14 + 25], 14 LONG $0xd8da8dc5 // vpminub ymm3, ymm14, ymm0 LONG $0xc374fdc5 // vpcmpeqb ymm0, ymm0, ymm3 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f190e442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rcx + 25], 15 + WORD $0x894c; BYTE $0xca // mov rdx, r9 + QUAD $0x0f190f442071a3c4 // vpinsrb xmm0, xmm1, byte [rdi + r9 + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00018024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 384], ymm0 - LONG $0x7cb60f42; WORD $0x1a0e // movzx edi, byte [rsi + r9 + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x011a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 1 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x021a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 2 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x031a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 3 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x041a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 4 - QUAD $0x051a16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 26], 5 - QUAD $0x061a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x071a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 7 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x081a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 8 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x091a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 9 - QUAD $0x0a1a26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 26], 10 - QUAD $0x0b1a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 11 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x0c1a0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 26], 12 - QUAD $0x0d1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 14 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0f1a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 15 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x1a // movzx edi, byte [rsi + rax + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + LONG $0x0744b60f; BYTE $0x1a // movzx eax, byte [rdi + rax + 26] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x011a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 1 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x021a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 2 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x031a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x041a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x071a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 7 + QUAD $0x081a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 10 + QUAD $0x0b1a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 11 + QUAD $0x0c1a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 13 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0e1a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 15 + LONG $0x44b60f42; WORD $0x1a27 // movzx eax, byte [rdi + r12 + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x011a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 1 + QUAD $0x021a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x031a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 3 + QUAD $0x041a1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 26], 4 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x051a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 5 + QUAD $0x061a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x081a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 8 + QUAD $0x091a2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 26], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 10 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x011a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 1 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - QUAD $0x021a164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 26], 2 + QUAD $0x0b1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 11 + QUAD $0x0c1a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 12 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0d1a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 14 + QUAD $0x0f1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 15 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x1b27 // movzx eax, byte [rdi + r12 + 27] + LONG $0xd06ef9c5 // vmovd xmm2, eax + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x011b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 1 + QUAD $0x021b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 2 + QUAD $0x031b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 3 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x041b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 4 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x051b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 5 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x061b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 6 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x071b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 7 + QUAD $0x081b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 10 + QUAD $0x0b1b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 11 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x0c1b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 12 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x0d1b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 13 + QUAD $0x0e1b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 27], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 15 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x0f44b60f; BYTE $0x1b // movzx eax, byte [rdi + rcx + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x011b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 1 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x021b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 2 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x031b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x031a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x041a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x051a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 5 - QUAD $0x061a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 6 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x071a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 7 - QUAD $0x081a1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 26], 8 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x091a3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 26], 9 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0a1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 10 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0b1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 11 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0c1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 14 - QUAD $0x0f1a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 15 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - LONG $0x7cb60f42; WORD $0x1b26 // movzx edi, byte [rsi + r12 + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x011b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 1 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x021b1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 27], 2 - QUAD $0x031b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 3 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x041b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 4 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x051b2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 27], 5 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x061b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 6 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x071b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 7 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x081b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 8 - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x091b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 27], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a1b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 10 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0b1b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 11 - QUAD $0x0c1b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 27], 12 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0d1b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e1b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 14 - QUAD $0x0f1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 15 - WORD $0x8949; BYTE $0xd1 // mov r9, rdx - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - LONG $0x167cb60f; BYTE $0x1b // movzx edi, byte [rsi + rdx + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x011b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 1 - QUAD $0x021b165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 27], 2 - QUAD $0x031b065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 27], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x041b065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 27], 4 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x051b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 5 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x061b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 6 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x071b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 7 - QUAD $0x081b1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 27], 8 - QUAD $0x091b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 9 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x0a1b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 10 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0b1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 11 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0c1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 12 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0d1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 13 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0e1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 14 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0f1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 15 + QUAD $0x041b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 4 + QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] + QUAD $0x051b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x081b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x091b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 9 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0a1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x0d1b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 14 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - LONG $0x7cb60f42; WORD $0x1c26 // movzx edi, byte [rsi + r12 + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x011c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 1 - QUAD $0x021c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 2 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x031c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 3 - QUAD $0x041c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 4 - QUAD $0x051c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 28], 5 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x061c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 6 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x071c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 7 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x081c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 28], 8 - QUAD $0x091c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 28], 9 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0a1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 10 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0b1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 11 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x0c1c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 28], 12 - QUAD $0x0d1c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 13 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x0e1c26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 28], 14 - QUAD $0x0f1c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 15 - QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] - LONG $0x7cb60f42; WORD $0x1c06 // movzx edi, byte [rsi + r8 + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x011c0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 28], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x021c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 2 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x031c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 3 - QUAD $0x041c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x051c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 5 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x061c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 6 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x071c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 7 - QUAD $0x081c1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 28], 8 - LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] - QUAD $0x091c1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 28], 9 - QUAD $0x0a1c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 10 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0b1c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 11 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0c1c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 28], 12 + LONG $0x44b60f42; WORD $0x1c27 // movzx eax, byte [rdi + r12 + 28] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 3 + QUAD $0x041c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 28], 4 + QUAD $0x051c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 5 + QUAD $0x061c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 6 + QUAD $0x071c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x081c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 8 + QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] + QUAD $0x091c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 9 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d1c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 13 + QUAD $0x0a1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 10 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0b1c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 11 + QUAD $0x0c1c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 12 + QUAD $0x0d1c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 14 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0f1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 15 + LONG $0x0f44b60f; BYTE $0x1c // movzx eax, byte [rdi + rcx + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x011c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 1 + QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] + QUAD $0x021c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 2 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x031c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 3 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x041c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 4 + QUAD $0x051c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x061c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 6 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x071c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x081c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x091c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 9 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0a1c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 10 + LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] + QUAD $0x0b1c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 11 + LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + QUAD $0x0c1c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 12 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0d1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 13 + QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] + QUAD $0x0e1c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 14 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x0f1c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x1d // movzx eax, byte [rdi + rax + 29] + LONG $0xd06ef9c5 // vmovd xmm2, eax LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e1c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 14 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x0f1c164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 28], 15 + QUAD $0x011d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 3 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - LONG $0x067cb60f; BYTE $0x1d // movzx edi, byte [rsi + rax + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x011d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 1 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x021d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 2 + QUAD $0x041d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 5 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x061d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x071d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 7 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x081d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 8 + QUAD $0x091d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 10 + QUAD $0x0b1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 11 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x0c1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 13 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0e1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 14 + QUAD $0x0f1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x1d // movzx eax, byte [rdi + rax + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x011d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 1 + QUAD $0x021d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 2 + QUAD $0x031d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 3 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x041d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 4 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x051d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 5 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x031d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 4 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x051d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 5 - QUAD $0x061d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 6 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x071d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 7 - QUAD $0x081d2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 29], 8 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x091d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 9 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0a1d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 10 - QUAD $0x0b1d16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 29], 11 - QUAD $0x0c1d36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 29], 12 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x0d1d16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 29], 13 - QUAD $0x0e1d26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 29], 14 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0f1d36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 29], 15 - LONG $0x7cb60f42; WORD $0x1d06 // movzx edi, byte [rsi + r8 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x011d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 1 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x021d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 29], 2 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x031d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 3 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x041d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 29], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x051d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 5 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x061d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 6 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x071d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 29], 7 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x081d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 8 - QUAD $0x091d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 29], 9 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0a1d3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 29], 10 - QUAD $0x0b1d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 29], 11 - QUAD $0x0c1d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 29], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d1d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 29], 13 - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x0e1d3e642061a3c4 // vpinsrb xmm4, xmm3, byte [rsi + r15 + 29], 14 + QUAD $0x061d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 6 + QUAD $0x071d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x081d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 8 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x091d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 9 + QUAD $0x0a1d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 10 + QUAD $0x0b1d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 11 + QUAD $0x0c1d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 12 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x0d1d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 13 + QUAD $0x0e1d0f642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r9 + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x0f1d16442059a3c4 // vpinsrb xmm0, xmm4, byte [rsi + r10 + 29], 15 + QUAD $0x0f1d3f442059a3c4 // vpinsrb xmm0, xmm4, byte [rdi + r15 + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - LONG $0x7cb60f42; WORD $0x1e1e // movzx edi, byte [rsi + r11 + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x011e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 1 - LONG $0x7cb60f42; WORD $0x1f1e // movzx edi, byte [rsi + r11 + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x021e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 2 - QUAD $0x021f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 2 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x031e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 3 - QUAD $0x031f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 3 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x051e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 5 - QUAD $0x051f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 5 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x061e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 6 - QUAD $0x061f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 6 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x1e17 // movzx eax, byte [rdi + r10 + 30] + LONG $0xc06ef9c5 // vmovd xmm0, eax + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x011e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 30], 1 + LONG $0x44b60f42; WORD $0x1f17 // movzx eax, byte [rdi + r10 + 31] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011f0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 31], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x0a1e1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 30], 10 - QUAD $0x0a1f1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 31], 10 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0b1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 11 - QUAD $0x0b1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 11 + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0c1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 12 - QUAD $0x0c1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 12 - QUAD $0x0d1e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 30], 13 - QUAD $0x0d1f164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 31], 13 + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0b1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 11 + QUAD $0x0b1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 11 + QUAD $0x0c1e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 30], 12 + QUAD $0x0c1f374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 31], 12 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + QUAD $0x0e1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 14 + QUAD $0x0e1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 14 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 14 - QUAD $0x0e1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 14 - QUAD $0x0f1e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 30], 15 - QUAD $0x0f1f36542071a3c4 // vpinsrb xmm2, xmm1, byte [rsi + r14 + 31], 15 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - LONG $0x44b60f42; WORD $0x1e06 // movzx eax, byte [rsi + r8 + 30] + QUAD $0x0f1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542071e3c4 // vpinsrb xmm2, xmm1, byte [rdi + rax + 31], 15 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x011e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 30], 1 - LONG $0x1644b60f; BYTE $0x1f // movzx eax, byte [rsi + rdx + 31] + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x011e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 31], 1 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x021e2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 30], 2 - QUAD $0x021f2e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r13 + 31], 2 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - QUAD $0x041e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 30], 4 - QUAD $0x041f0e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 31], 4 + QUAD $0x011f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 1 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x061e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 6 - QUAD $0x061f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 6 - QUAD $0x071e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 30], 7 - QUAD $0x071f267c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r12 + 31], 7 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x081e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 8 - QUAD $0x081f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 8 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x091e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 9 - QUAD $0x091f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 9 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0b1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 11 - QUAD $0x0b1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 11 + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0c1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 12 - QUAD $0x0c1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 12 - QUAD $0x0d1e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 30], 13 - QUAD $0x0d1f0e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 31], 13 - QUAD $0x0e1e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 30], 14 - QUAD $0x0e1f3e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 31], 14 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 15 - QUAD $0x0f1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 15 + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x041e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 4 + QUAD $0x041f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 4 + QUAD $0x051e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 5 + QUAD $0x051f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 5 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 9 + QUAD $0x091f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 9 + QUAD $0x0a1e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 10 + QUAD $0x0a1f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + WORD $0x894c; BYTE $0xe8 // mov rax, r13 + QUAD $0x0d1e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 13 + QUAD $0x0d1f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 13 + QUAD $0x0e1e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 30], 14 + QUAD $0x0e1f0f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r9 + 31], 14 + QUAD $0x0f1e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 30], 15 + QUAD $0x0f1f3f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -44609,21 +45741,21 @@ LBB7_53: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000170248c8b48 // mov rcx, qword [rsp + 368] - LONG $0x7f7ec1c4; WORD $0x8b44; BYTE $0x60 // vmovdqu yword [r11 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8b54; BYTE $0x40 // vmovdqu yword [r11 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8b64; BYTE $0x20 // vmovdqu yword [r11 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8b0c // vmovdqu yword [r11 + 4*rcx], ymm1 + LONG $0x7f7ec1c4; WORD $0x8e44; BYTE $0x60 // vmovdqu yword [r14 + 4*rcx + 96], ymm0 + LONG $0x7f7ec1c4; WORD $0x8e54; BYTE $0x40 // vmovdqu yword [r14 + 4*rcx + 64], ymm2 + LONG $0x7f7ec1c4; WORD $0x8e64; BYTE $0x20 // vmovdqu yword [r14 + 4*rcx + 32], ymm4 + LONG $0x7f7ec1c4; WORD $0x8e0c // vmovdqu yword [r14 + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000168248c3b48 // cmp rcx, qword [rsp + 360] - JNE LBB7_53 - QUAD $0x0000017824bc8b4c // mov r15, qword [rsp + 376] - QUAD $0x0000016824bc3b4c // cmp r15, qword [rsp + 360] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] - QUAD $0x000001f824a48b4c // mov r12, qword [rsp + 504] - JNE LBB7_55 - JMP LBB7_58 + JNE LBB7_73 + QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] + QUAD $0x00000168248c3b48 // cmp rcx, qword [rsp + 360] + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + LONG $0x246c8b44; BYTE $0x04 // mov r13d, dword [rsp + 4] + QUAD $0x000001f8249c8b4c // mov r11, qword [rsp + 504] + JNE LBB7_75 + JMP LBB7_78 DATA LCDATA6<>+0x000(SB)/8, $0x0101010101010101 DATA LCDATA6<>+0x008(SB)/8, $0x0101010101010101 @@ -44669,63 +45801,77 @@ TEXT ·_comparison_greater_scalar_arr_avx2(SB), $1352-48 MOVQ BP, 1312(SP) LEAQ LCDATA6<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB8_13 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB8_28 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB8_51 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB8_59 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB8_179 - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_7: - WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0xf619 // sbb esi, esi - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_7 - LONG $0x01c38349 // add r11, 1 + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB8_18 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB8_35 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB8_57 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB8_70 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB8_194 + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_11 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_9 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_8: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc08348 // add rax, -1 + JNE LBB8_8 LBB8_9: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_115 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 LBB8_11: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_15 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB8_13: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] QUAD $0x000000802494970f // seta byte [rsp + 128] LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] @@ -44733,21 +45879,21 @@ LBB8_11: LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] LONG $0xd6970f41 // seta r14b LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] WORD $0x970f; BYTE $0xd0 // seta al LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] LONG $0xd3970f41 // seta r11b LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] - LONG $0xd0970f41 // seta r8b + LONG $0xd6970f40 // seta sil LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] LONG $0xd1970f41 // seta r9b LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] @@ -44755,31 +45901,31 @@ LBB8_11: LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] LONG $0xd4970f41 // seta r12b LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd0970f41 // seta r8b LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] LONG $0xd7970f41 // seta r15b LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] @@ -44797,65 +45943,64 @@ LBB8_11: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x48 // add sil, byte [rsp + 72] - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x20 // movzx edi, byte [rsp + 32] - LONG $0x06e7c040 // shl dil, 6 + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4e88; BYTE $0x01 // mov byte [rsi + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -44866,86 +46011,109 @@ LBB8_11: QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl - QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc189 // mov ecx, eax + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al WORD $0xcb08 // or bl, cl - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68348 // add rsi, 4 - QUAD $0x000000e824b48948 // mov qword [rsp + 232], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB8_11 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB8_116 - JMP LBB8_179 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB8_13 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] -LBB8_13: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB8_41 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB8_70 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB8_81 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB8_179 - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_21 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_19: - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] +LBB8_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_157 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB8_159 + +LBB8_18: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB8_42 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB8_83 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB8_96 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB8_194 + WORD $0x8b4c; BYTE $0x3e // mov r15, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_26 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6ef9c1c4; BYTE $0xc7 // vmovq xmm0, r15 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_25: + LONG $0x012ef9c5 // vucomisd xmm0, qword [rcx] WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x08c28348 // add rdx, 8 + LONG $0x08518d48 // lea rdx, [rcx + 8] WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_19 - LONG $0x01c38349 // add r11, 1 + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_25 -LBB8_21: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_25 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 +LBB8_26: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 -LBB8_23: +LBB8_28: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_32 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 + LONG $0x6ef9c1c4; BYTE $0xc7 // vmovq xmm0, r15 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + +LBB8_30: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] LONG $0xd0970f41 // seta r8b LONG $0x422ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rdx + 16] @@ -44953,19 +46121,19 @@ LBB8_23: LONG $0x422ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rdx + 24] LONG $0xd5970f41 // seta r13b LONG $0x422ef9c5; BYTE $0x20 // vucomisd xmm0, qword [rdx + 32] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x422ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rdx + 40] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x422ef9c5; BYTE $0x30 // vucomisd xmm0, qword [rdx + 48] WORD $0x970f; BYTE $0xd0 // seta al LONG $0x422ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rdx + 56] LONG $0xd3970f41 // seta r11b LONG $0x422ef9c5; BYTE $0x40 // vucomisd xmm0, qword [rdx + 64] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x422ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rdx + 72] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x422ef9c5; BYTE $0x50 // vucomisd xmm0, qword [rdx + 80] - LONG $0xd7970f40 // seta dil + LONG $0xd6970f40 // seta sil LONG $0x422ef9c5; BYTE $0x58 // vucomisd xmm0, qword [rdx + 88] LONG $0xd1970f41 // seta r9b LONG $0x422ef9c5; BYTE $0x60 // vucomisd xmm0, qword [rdx + 96] @@ -44973,31 +46141,31 @@ LBB8_23: LONG $0x422ef9c5; BYTE $0x68 // vucomisd xmm0, qword [rdx + 104] LONG $0xd4970f41 // seta r12b LONG $0x422ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rdx + 112] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x422ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rdx + 120] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd7970f40 // seta dil QUAD $0x00000080822ef9c5 // vucomisd xmm0, qword [rdx + 128] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] QUAD $0x00000088822ef9c5 // vucomisd xmm0, qword [rdx + 136] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] QUAD $0x00000090822ef9c5 // vucomisd xmm0, qword [rdx + 144] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] QUAD $0x00000098822ef9c5 // vucomisd xmm0, qword [rdx + 152] - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] QUAD $0x000000a0822ef9c5 // vucomisd xmm0, qword [rdx + 160] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] QUAD $0x000000a8822ef9c5 // vucomisd xmm0, qword [rdx + 168] - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] QUAD $0x000000b0822ef9c5 // vucomisd xmm0, qword [rdx + 176] - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] QUAD $0x000000b8822ef9c5 // vucomisd xmm0, qword [rdx + 184] LONG $0xd7970f41 // seta r15b QUAD $0x000000c0822ef9c5 // vucomisd xmm0, qword [rdx + 192] QUAD $0x000001402494970f // seta byte [rsp + 320] QUAD $0x000000c8822ef9c5 // vucomisd xmm0, qword [rdx + 200] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - QUAD $0x000000d0822ef9c5 // vucomisd xmm0, qword [rdx + 208] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + QUAD $0x000000d0822ef9c5 // vucomisd xmm0, qword [rdx + 208] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] QUAD $0x000000e0822ef9c5 // vucomisd xmm0, qword [rdx + 224] @@ -45009,69 +46177,68 @@ LBB8_23: QUAD $0x000000f8822ef9c5 // vucomisd xmm0, qword [rdx + 248] WORD $0x970f; BYTE $0xd3 // seta bl WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x78 // add r8b, byte [rsp + 120] + LONG $0x24440244; BYTE $0x60 // add r8b, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e3c041 // shl r11b, 7 WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xc6 // or r14b, r8b - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x50 // add sil, byte [rsp + 80] + WORD $0xc900 // add cl, cl + LONG $0x70244c02 // add cl, byte [rsp + 112] LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x58 // movzx esi, byte [rsp + 88] + LONG $0x2474b60f; BYTE $0x78 // movzx esi, byte [rsp + 120] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xf7 // or dil, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0844; BYTE $0xe7 // or dil, r12b + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x20 // movzx edi, byte [rsp + 32] - LONG $0x06e7c040 // shl dil, 6 + LONG $0x30244402 // add al, byte [rsp + 48] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4e88; BYTE $0x01 // mov byte [rsi + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x017e8841 // mov byte [r14 + 1], dil + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -45082,325 +46249,151 @@ LBB8_23: QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl - QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc189 // mov ecx, eax + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al WORD $0xcb08 // or bl, cl - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl + WORD $0xc308 // or bl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x035e8841 // mov byte [r14 + 3], bl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68348 // add rsi, 4 - QUAD $0x000000e824b48948 // mov qword [rsp + 232], rsi + LONG $0x04c68349 // add r14, 4 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 - JNE LBB8_23 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - -LBB8_25: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB8_179 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB8_133 - WORD $0xff31 // xor edi, edi - JMP LBB8_135 - -LBB8_28: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB8_92 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB8_179 - WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] - LONG $0x1f6a8d4d // lea r13, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xea490f4d // cmovns r13, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_128 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - WORD $0x894d; BYTE $0xdf // mov r15, r11 + JNE LBB8_30 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] LBB8_32: - WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_32 - LONG $0x01c78349 // add r15, 1 - LONG $0x05fdc149 // sar r13, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_129 - -LBB8_34: - LONG $0x20fd8349 // cmp r13, 32 - LONG $0x24748944; BYTE $0x04 // mov dword [rsp + 4], r14d - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000016824ac894c // mov qword [rsp + 360], r13 - JB LBB8_37 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc7 // cmp r15, rax - JAE LBB8_180 - LONG $0xaf048d4b // lea rax, [r15 + 4*r13] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB8_180 - -LBB8_37: - WORD $0xc031 // xor eax, eax - QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xd4 // mov r12, rdx - QUAD $0x0000016024bc894c // mov qword [rsp + 352], r15 - -LBB8_38: - QUAD $0x0000018024ac2b4c // sub r13, qword [rsp + 384] - QUAD $0x0000008024ac894c // mov qword [rsp + 128], r13 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x6ef9c1c4; BYTE $0xc7 // vmovq xmm0, r15 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_161 + WORD $0xff31 // xor edi, edi + JMP LBB8_163 + +LBB8_35: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB8_109 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB8_194 + WORD $0x8a44; BYTE $0x3e // mov r15b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_127 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_129 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB8_40: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x3a // cmp r15b, byte [rdx] + WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1c048841 // mov byte [r12 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB8_40 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JNE LBB8_130 + JMP LBB8_194 + +LBB8_42: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB8_114 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB8_194 + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_50 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_48 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB8_39: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343a45 // cmp r14b, byte [r12] - QUAD $0x0000012024949f0f // setg byte [rsp + 288] - LONG $0x24743a45; BYTE $0x01 // cmp r14b, byte [r12 + 1] - LONG $0xd29f0f41 // setg r10b - LONG $0x24743a45; BYTE $0x02 // cmp r14b, byte [r12 + 2] - WORD $0x9f0f; BYTE $0xd3 // setg bl - LONG $0x24743a45; BYTE $0x03 // cmp r14b, byte [r12 + 3] - LONG $0xd59f0f41 // setg r13b - LONG $0x24743a45; BYTE $0x04 // cmp r14b, byte [r12 + 4] - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x24743a45; BYTE $0x05 // cmp r14b, byte [r12 + 5] - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x24743a45; BYTE $0x06 // cmp r14b, byte [r12 + 6] - WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x24743a45; BYTE $0x07 // cmp r14b, byte [r12 + 7] - LONG $0xd49f0f41 // setg r12b - LONG $0x08713a44 // cmp r14b, byte [rcx + 8] - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0x09713a44 // cmp r14b, byte [rcx + 9] - LONG $0xd69f0f40 // setg sil - LONG $0x0a713a44 // cmp r14b, byte [rcx + 10] - LONG $0xd79f0f40 // setg dil - LONG $0x0b713a44 // cmp r14b, byte [rcx + 11] - LONG $0xd19f0f41 // setg r9b - LONG $0x0c713a44 // cmp r14b, byte [rcx + 12] - LONG $0xd39f0f41 // setg r11b - LONG $0x0d713a44 // cmp r14b, byte [rcx + 13] - LONG $0xd79f0f41 // setg r15b - LONG $0x0e713a44 // cmp r14b, byte [rcx + 14] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0x0f713a44 // cmp r14b, byte [rcx + 15] - LONG $0xd09f0f41 // setg r8b - LONG $0x10713a44 // cmp r14b, byte [rcx + 16] - QUAD $0x0000010024949f0f // setg byte [rsp + 256] - LONG $0x11713a44 // cmp r14b, byte [rcx + 17] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x12713a44 // cmp r14b, byte [rcx + 18] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x13713a44 // cmp r14b, byte [rcx + 19] - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x14713a44 // cmp r14b, byte [rcx + 20] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x15713a44 // cmp r14b, byte [rcx + 21] - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0x16713a44 // cmp r14b, byte [rcx + 22] - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x17713a44 // cmp r14b, byte [rcx + 23] - LONG $0xd69f0f41 // setg r14b - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] - QUAD $0x000000e824949f0f // setg byte [rsp + 232] - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - QUAD $0x0000014024949f0f // setg byte [rsp + 320] - LONG $0x0424548b // mov edx, dword [rsp + 4] - WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000012024940244 // add r10b, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e4c041 // shl r12b, 7 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xd3 // or bl, r10b - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xeb // or bl, r13b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e7c041 // shl r15b, 5 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - WORD $0x0841; BYTE $0xdc // or r12b, bl - WORD $0x0845; BYTE $0xf8 // or r8b, r15b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xc000 // add al, al - LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0xc308 // or bl, al - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - QUAD $0x0000016024b48b48 // mov rsi, qword [rsp + 352] - WORD $0x8844; BYTE $0x26 // mov byte [rsi], r12b - LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x01468844 // mov byte [rsi + 1], r8b - WORD $0x0841; BYTE $0xde // or r14b, bl - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xc000 // add al, al - LONG $0xe8248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 232] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - QUAD $0x00000140249cb60f // movzx ebx, byte [rsp + 320] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] - WORD $0x5688; BYTE $0x03 // mov byte [rsi + 3], dl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000016024b48948 // mov qword [rsp + 352], rsi - QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 - JNE LBB8_39 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000016824ac8b4c // mov r13, qword [rsp + 360] - JMP LBB8_130 +LBB8_47: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc08348 // add rax, -1 + JNE LBB8_47 -LBB8_41: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB8_104 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB8_179 - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_47 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_45: - WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x1945; BYTE $0xc9 // sbb r9d, r9d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3045; BYTE $0xc1 // xor r9b, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xcf // and dil, r9b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_45 - LONG $0x01c38349 // add r11, 1 +LBB8_48: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 -LBB8_47: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_118 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - -LBB8_49: - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 +LBB8_50: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_54 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB8_52: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] QUAD $0x000000802494970f // seta byte [rsp + 128] LONG $0x086a3b4c // cmp r13, qword [rdx + 8] @@ -45408,21 +46401,21 @@ LBB8_49: LONG $0x106a3b4c // cmp r13, qword [rdx + 16] LONG $0xd6970f41 // seta r14b LONG $0x186a3b4c // cmp r13, qword [rdx + 24] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x286a3b4c // cmp r13, qword [rdx + 40] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x306a3b4c // cmp r13, qword [rdx + 48] WORD $0x970f; BYTE $0xd0 // seta al LONG $0x386a3b4c // cmp r13, qword [rdx + 56] LONG $0xd3970f41 // seta r11b LONG $0x406a3b4c // cmp r13, qword [rdx + 64] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x486a3b4c // cmp r13, qword [rdx + 72] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x506a3b4c // cmp r13, qword [rdx + 80] - LONG $0xd0970f41 // seta r8b + LONG $0xd6970f40 // seta sil LONG $0x586a3b4c // cmp r13, qword [rdx + 88] LONG $0xd1970f41 // seta r9b LONG $0x606a3b4c // cmp r13, qword [rdx + 96] @@ -45430,31 +46423,31 @@ LBB8_49: LONG $0x686a3b4c // cmp r13, qword [rdx + 104] LONG $0xd4970f41 // seta r12b LONG $0x706a3b4c // cmp r13, qword [rdx + 112] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd0970f41 // seta r8b LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] LONG $0xd7970f41 // seta r15b LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] @@ -45472,67 +46465,64 @@ LBB8_49: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x48 // add sil, byte [rsp + 72] - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc789 // mov edi, eax - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - WORD $0x8844; BYTE $0x18 // mov byte [rax], r11b - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x014b8841 // mov byte [r11 + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -45552,66 +46542,86 @@ LBB8_49: WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xcb08 // or bl, cl WORD $0xc308 // or bl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x035b8841 // mov byte [r11 + 3], bl + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c38349 // add r11, 4 - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB8_49 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB8_119 - JMP LBB8_179 - -LBB8_51: - LONG $0x2eb70f44 // movzx r13d, word [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_55 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_53: - LONG $0x2a394466 // cmp word [rdx], r13w - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0xf619 // sbb esi, esi - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_53 - LONG $0x01c38349 // add r11, 1 - -LBB8_55: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_121 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024bc894c // mov qword [rsp + 144], r15 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB8_52 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + +LBB8_54: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_165 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB8_167 + +LBB8_57: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_63 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_61 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_60: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc78349 // add r15, -1 + JNE LBB8_60 -LBB8_57: +LBB8_61: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 + +LBB8_63: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_67 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB8_65: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 LONG $0x2a3b4466 // cmp r13w, word [rdx] WORD $0x970f; BYTE $0xd0 // seta al LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] @@ -45619,21 +46629,21 @@ LBB8_57: LONG $0x6a3b4466; BYTE $0x04 // cmp r13w, word [rdx + 4] LONG $0xd6970f41 // seta r14b LONG $0x6a3b4466; BYTE $0x06 // cmp r13w, word [rdx + 6] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + QUAD $0x000000802494970f // seta byte [rsp + 128] LONG $0x6a3b4466; BYTE $0x08 // cmp r13w, word [rdx + 8] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x6a3b4466; BYTE $0x0a // cmp r13w, word [rdx + 10] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x6a3b4466; BYTE $0x0c // cmp r13w, word [rdx + 12] - QUAD $0x000000802494970f // seta byte [rsp + 128] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x6a3b4466; BYTE $0x0e // cmp r13w, word [rdx + 14] LONG $0xd3970f41 // seta r11b LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x6a3b4466; BYTE $0x12 // cmp r13w, word [rdx + 18] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x6a3b4466; BYTE $0x14 // cmp r13w, word [rdx + 20] - LONG $0xd0970f41 // seta r8b + LONG $0xd6970f40 // seta sil LONG $0x6a3b4466; BYTE $0x16 // cmp r13w, word [rdx + 22] LONG $0xd1970f41 // seta r9b LONG $0x6a3b4466; BYTE $0x18 // cmp r13w, word [rdx + 24] @@ -45641,31 +46651,31 @@ LBB8_57: LONG $0x6a3b4466; BYTE $0x1a // cmp r13w, word [rdx + 26] LONG $0xd4970f41 // seta r12b LONG $0x6a3b4466; BYTE $0x1c // cmp r13w, word [rdx + 28] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x6a3b4466; BYTE $0x1e // cmp r13w, word [rdx + 30] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd0970f41 // seta r8b LONG $0x6a3b4466; BYTE $0x20 // cmp r13w, word [rdx + 32] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x6a3b4466; BYTE $0x22 // cmp r13w, word [rdx + 34] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x6a3b4466; BYTE $0x24 // cmp r13w, word [rdx + 36] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x6a3b4466; BYTE $0x26 // cmp r13w, word [rdx + 38] - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x6a3b4466; BYTE $0x2a // cmp r13w, word [rdx + 42] - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x6a3b4466; BYTE $0x2c // cmp r13w, word [rdx + 44] - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x6a3b4466; BYTE $0x2e // cmp r13w, word [rdx + 46] LONG $0xd7970f41 // seta r15b LONG $0x6a3b4466; BYTE $0x30 // cmp r13w, word [rdx + 48] QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x6a3b4466; BYTE $0x32 // cmp r13w, word [rdx + 50] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x6a3b4466; BYTE $0x36 // cmp r13w, word [rdx + 54] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x6a3b4466; BYTE $0x38 // cmp r13w, word [rdx + 56] @@ -45678,71 +46688,70 @@ LBB8_57: WORD $0x970f; BYTE $0xd3 // seta bl WORD $0x0040; BYTE $0xff // add dil, dil WORD $0x0840; BYTE $0xc7 // or dil, al - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e3c041 // shl r11b, 7 WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x48 // add sil, byte [rsp + 72] - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x78244c02 // add cl, byte [rsp + 120] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x20 // movzx edi, byte [rsp + 32] - LONG $0x06e7c040 // shl dil, 6 + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4e88; BYTE $0x01 // mov byte [rsi + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -45753,76 +46762,96 @@ LBB8_57: QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl - QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc189 // mov ecx, eax + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al WORD $0xcb08 // or bl, cl - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68348 // add rsi, 4 - QUAD $0x000000e824b48948 // mov qword [rsp + 232], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB8_57 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB8_122 - JMP LBB8_179 - -LBB8_59: - LONG $0x2eb70f44 // movzx r13d, word [rsi] - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_63 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB8_65 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] -LBB8_61: - LONG $0x2a3b4466 // cmp r13w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x33 // movzx r8d, byte [r11 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_61 - LONG $0x01c38349 // add r11, 1 +LBB8_67: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_169 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB8_171 -LBB8_63: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_67 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 +LBB8_70: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_76 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_74 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_73: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_73 -LBB8_65: +LBB8_74: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 + +LBB8_76: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_80 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB8_78: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 LONG $0x2a3b4466 // cmp r13w, word [rdx] QUAD $0x0000008024949f0f // setg byte [rsp + 128] LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] @@ -45830,21 +46859,21 @@ LBB8_65: LONG $0x6a3b4466; BYTE $0x04 // cmp r13w, word [rdx + 4] LONG $0xd69f0f41 // setg r14b LONG $0x6a3b4466; BYTE $0x06 // cmp r13w, word [rdx + 6] - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] LONG $0x6a3b4466; BYTE $0x08 // cmp r13w, word [rdx + 8] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] LONG $0x6a3b4466; BYTE $0x0a // cmp r13w, word [rdx + 10] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] LONG $0x6a3b4466; BYTE $0x0c // cmp r13w, word [rdx + 12] WORD $0x9f0f; BYTE $0xd0 // setg al LONG $0x6a3b4466; BYTE $0x0e // cmp r13w, word [rdx + 14] LONG $0xd39f0f41 // setg r11b LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] LONG $0x6a3b4466; BYTE $0x12 // cmp r13w, word [rdx + 18] - LONG $0xd69f0f40 // setg sil + WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x6a3b4466; BYTE $0x14 // cmp r13w, word [rdx + 20] - LONG $0xd09f0f41 // setg r8b + LONG $0xd69f0f40 // setg sil LONG $0x6a3b4466; BYTE $0x16 // cmp r13w, word [rdx + 22] LONG $0xd19f0f41 // setg r9b LONG $0x6a3b4466; BYTE $0x18 // cmp r13w, word [rdx + 24] @@ -45852,31 +46881,31 @@ LBB8_65: LONG $0x6a3b4466; BYTE $0x1a // cmp r13w, word [rdx + 26] LONG $0xd49f0f41 // setg r12b LONG $0x6a3b4466; BYTE $0x1c // cmp r13w, word [rdx + 28] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] LONG $0x6a3b4466; BYTE $0x1e // cmp r13w, word [rdx + 30] - WORD $0x9f0f; BYTE $0xd1 // setg cl + LONG $0xd09f0f41 // setg r8b LONG $0x6a3b4466; BYTE $0x20 // cmp r13w, word [rdx + 32] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x6a3b4466; BYTE $0x22 // cmp r13w, word [rdx + 34] - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] LONG $0x6a3b4466; BYTE $0x24 // cmp r13w, word [rdx + 36] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] LONG $0x6a3b4466; BYTE $0x26 // cmp r13w, word [rdx + 38] - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] LONG $0x6a3b4466; BYTE $0x2a // cmp r13w, word [rdx + 42] - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] LONG $0x6a3b4466; BYTE $0x2c // cmp r13w, word [rdx + 44] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] LONG $0x6a3b4466; BYTE $0x2e // cmp r13w, word [rdx + 46] LONG $0xd79f0f41 // setg r15b LONG $0x6a3b4466; BYTE $0x30 // cmp r13w, word [rdx + 48] QUAD $0x0000014024949f0f // setg byte [rsp + 320] LONG $0x6a3b4466; BYTE $0x32 // cmp r13w, word [rdx + 50] - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] LONG $0x6a3b4466; BYTE $0x36 // cmp r13w, word [rdx + 54] LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] LONG $0x6a3b4466; BYTE $0x38 // cmp r13w, word [rdx + 56] @@ -45894,65 +46923,64 @@ LBB8_65: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x48 // add sil, byte [rsp + 72] - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x20 // movzx edi, byte [rsp + 32] - LONG $0x06e7c040 // shl dil, 6 + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4e88; BYTE $0x01 // mov byte [rsi + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -45963,84 +46991,96 @@ LBB8_65: QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl - QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc189 // mov ecx, eax + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al WORD $0xcb08 // or bl, cl - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68348 // add rsi, 4 - QUAD $0x000000e824b48948 // mov qword [rsp + 232], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB8_65 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB8_78 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] -LBB8_67: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB8_179 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB8_137 +LBB8_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_174 WORD $0xff31 // xor edi, edi - JMP LBB8_139 + JMP LBB8_176 -LBB8_70: - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_74 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_72: - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x33 // movzx r8d, byte [r11 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_72 - LONG $0x01c38349 // add r11, 1 +LBB8_83: + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_89 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_87 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_86: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_86 -LBB8_74: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_78 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 +LBB8_87: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 -LBB8_76: +LBB8_89: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_93 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB8_91: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] QUAD $0x0000008024949f0f // setg byte [rsp + 128] LONG $0x086a3b4c // cmp r13, qword [rdx + 8] @@ -46048,21 +47088,21 @@ LBB8_76: LONG $0x106a3b4c // cmp r13, qword [rdx + 16] LONG $0xd69f0f41 // setg r14b LONG $0x186a3b4c // cmp r13, qword [rdx + 24] - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] LONG $0x286a3b4c // cmp r13, qword [rdx + 40] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] LONG $0x306a3b4c // cmp r13, qword [rdx + 48] WORD $0x9f0f; BYTE $0xd0 // setg al LONG $0x386a3b4c // cmp r13, qword [rdx + 56] LONG $0xd39f0f41 // setg r11b LONG $0x406a3b4c // cmp r13, qword [rdx + 64] - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] LONG $0x486a3b4c // cmp r13, qword [rdx + 72] - LONG $0xd69f0f40 // setg sil + WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x506a3b4c // cmp r13, qword [rdx + 80] - LONG $0xd09f0f41 // setg r8b + LONG $0xd69f0f40 // setg sil LONG $0x586a3b4c // cmp r13, qword [rdx + 88] LONG $0xd19f0f41 // setg r9b LONG $0x606a3b4c // cmp r13, qword [rdx + 96] @@ -46070,31 +47110,31 @@ LBB8_76: LONG $0x686a3b4c // cmp r13, qword [rdx + 104] LONG $0xd49f0f41 // setg r12b LONG $0x706a3b4c // cmp r13, qword [rdx + 112] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x9f0f; BYTE $0xd1 // setg cl + LONG $0xd09f0f41 // setg r8b LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] LONG $0xd79f0f41 // setg r15b LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] QUAD $0x0000014024949f0f // setg byte [rsp + 320] LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] @@ -46112,65 +47152,64 @@ LBB8_76: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x48 // add sil, byte [rsp + 72] - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x20 // movzx edi, byte [rsp + 32] - LONG $0x06e7c040 // shl dil, 6 + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4e88; BYTE $0x01 // mov byte [rsi + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -46181,138 +47220,153 @@ LBB8_76: QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl - QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc189 // mov ecx, eax + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al WORD $0xcb08 // or bl, cl - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68348 // add rsi, 4 - QUAD $0x000000e824b48948 // mov qword [rsp + 232], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB8_76 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB8_91 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] -LBB8_78: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB8_179 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB8_141 +LBB8_93: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_178 WORD $0xff31 // xor edi, edi - JMP LBB8_143 - -LBB8_81: - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_85 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JMP LBB8_180 -LBB8_83: - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] +LBB8_96: + WORD $0x8b44; BYTE $0x3e // mov r15d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_102 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_100 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e79c1c4; BYTE $0xc7 // vmovd xmm0, r15d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_99: + LONG $0x012ef8c5 // vucomiss xmm0, dword [rcx] WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x04c28348 // add rdx, 4 + LONG $0x04518d48 // lea rdx, [rcx + 4] WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_83 - LONG $0x01c38349 // add r11, 1 + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_99 -LBB8_85: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_89 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 +LBB8_100: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 -LBB8_87: +LBB8_102: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_106 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000009024bc8944 // mov dword [rsp + 144], r15d + LONG $0x6e79c1c4; BYTE $0xc7 // vmovd xmm0, r15d + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + +LBB8_104: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x422ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rdx + 4] LONG $0xd0970f41 // seta r8b LONG $0x422ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rdx + 8] LONG $0xd6970f41 // seta r14b LONG $0x422ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rdx + 12] - LONG $0xd5970f41 // seta r13b + LONG $0xd4970f41 // seta r12b LONG $0x422ef8c5; BYTE $0x10 // vucomiss xmm0, dword [rdx + 16] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x422ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rdx + 20] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x422ef8c5; BYTE $0x18 // vucomiss xmm0, dword [rdx + 24] WORD $0x970f; BYTE $0xd0 // seta al LONG $0x422ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rdx + 28] LONG $0xd3970f41 // seta r11b LONG $0x422ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rdx + 32] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x422ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rdx + 36] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x422ef8c5; BYTE $0x28 // vucomiss xmm0, dword [rdx + 40] - LONG $0xd7970f40 // seta dil + LONG $0xd6970f40 // seta sil LONG $0x422ef8c5; BYTE $0x2c // vucomiss xmm0, dword [rdx + 44] LONG $0xd1970f41 // seta r9b LONG $0x422ef8c5; BYTE $0x30 // vucomiss xmm0, dword [rdx + 48] LONG $0xd2970f41 // seta r10b LONG $0x422ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rdx + 52] - LONG $0xd4970f41 // seta r12b + LONG $0xd5970f41 // seta r13b LONG $0x422ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rdx + 56] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x422ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rdx + 60] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd7970f40 // seta dil LONG $0x422ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rdx + 64] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x422ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rdx + 68] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x422ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rdx + 72] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x422ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rdx + 76] - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x422ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rdx + 80] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x422ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rdx + 84] - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x422ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rdx + 88] - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x422ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rdx + 92] LONG $0xd7970f41 // seta r15b LONG $0x422ef8c5; BYTE $0x60 // vucomiss xmm0, dword [rdx + 96] QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x422ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rdx + 100] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x422ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rdx + 104] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x422ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rdx + 104] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x422ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rdx + 112] @@ -46324,69 +47378,343 @@ LBB8_87: LONG $0x422ef8c5; BYTE $0x7c // vucomiss xmm0, dword [rdx + 124] WORD $0x970f; BYTE $0xd3 // seta bl WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x78 // add r8b, byte [rsp + 120] + LONG $0x24440244; BYTE $0x60 // add r8b, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e3c041 // shl r11b, 7 WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xc6 // or r14b, r8b - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x50 // add sil, byte [rsp + 80] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc900 // add cl, cl + LONG $0x70244c02 // add cl, byte [rsp + 112] + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xf4 // or r12b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x58 // movzx esi, byte [rsp + 88] + LONG $0x05e5c041 // shl r13b, 5 + WORD $0x0845; BYTE $0xd5 // or r13b, r10b + LONG $0x2474b60f; BYTE $0x78 // movzx esi, byte [rsp + 120] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xf7 // or dil, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0844; BYTE $0xef // or dil, r13b + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x20 // movzx edi, byte [rsp + 32] - LONG $0x06e7c040 // shl dil, 6 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl + LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB8_104 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000009024bc8b44 // mov r15d, dword [rsp + 144] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + +LBB8_106: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x6e79c1c4; BYTE $0xc7 // vmovd xmm0, r15d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_182 + WORD $0xff31 // xor edi, edi + JMP LBB8_184 + +LBB8_109: + WORD $0x8a44; BYTE $0x3e // mov r15b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_128 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_143 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + +LBB8_112: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3844; BYTE $0x3a // cmp byte [rdx], r15b + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0x2044; BYTE $0xda // and dl, r11b + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x1c148841 // mov byte [r12 + rbx], dl + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc08348 // add rax, -1 + JNE LBB8_112 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JNE LBB8_144 + JMP LBB8_194 + +LBB8_114: + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_120 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_118 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_117: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_117 + +LBB8_118: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + LONG $0x01c48349 // add r12, 1 + +LBB8_120: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_124 + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB8_122: + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 + WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] + QUAD $0x0000008024949f0f // setg byte [rsp + 128] + LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] + LONG $0xd79f0f40 // setg dil + LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] + LONG $0xd69f0f41 // setg r14b + LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] + WORD $0x9f0f; BYTE $0xd0 // setg al + LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] + LONG $0xd39f0f41 // setg r11b + LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] + WORD $0x9f0f; BYTE $0xd1 // setg cl + LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] + LONG $0xd69f0f40 // setg sil + LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] + LONG $0xd19f0f41 // setg r9b + LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] + LONG $0xd29f0f41 // setg r10b + LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] + LONG $0xd49f0f41 // setg r12b + LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] + LONG $0xd09f0f41 // setg r8b + LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] + LONG $0xd79f0f41 // setg r15b + LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] + QUAD $0x0000014024949f0f // setg byte [rsp + 320] + LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] + QUAD $0x0000012024949f0f // setg byte [rsp + 288] + LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] + QUAD $0x0000010024949f0f // setg byte [rsp + 256] + LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] + LONG $0x24549f0f; BYTE $0x04 // setg byte [rsp + 4] + LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4e88; BYTE $0x01 // mov byte [rsi + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xc000 // add al, al LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -46397,215 +47725,441 @@ LBB8_87: QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl - QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xc108 // or cl, al - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc189 // mov ecx, eax + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al WORD $0xcb08 // or bl, cl - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68348 // add rsi, 4 - QUAD $0x000000e824b48948 // mov qword [rsp + 232], rsi - QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 - JNE LBB8_87 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB8_122 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] -LBB8_89: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB8_179 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB8_145 +LBB8_124: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_194 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB8_187 WORD $0xff31 // xor edi, edi - JMP LBB8_147 - -LBB8_92: - WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_96 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JMP LBB8_189 -LBB8_94: - WORD $0x3844; BYTE $0x32 // cmp byte [rdx], r14b - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0xf619 // sbb esi, esi - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_94 - LONG $0x01c38349 // add r11, 1 +LBB8_127: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB8_131 -LBB8_96: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_124 - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x24748944; BYTE $0x04 // mov dword [rsp + 4], r14d - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000017024bc894c // mov qword [rsp + 368], r15 - JB LBB8_100 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB8_128: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB8_145 + +LBB8_129: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + +LBB8_130: + LONG $0x01c48349 // add r12, 1 + +LBB8_131: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_139 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x247c8944; BYTE $0x04 // mov dword [rsp + 4], r15d + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x00000168248c8948 // mov qword [rsp + 360], rcx + JB LBB8_135 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JAE LBB8_183 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB8_183 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB8_205 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB8_205 -LBB8_100: +LBB8_135: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000016024a4894c // mov qword [rsp + 352], r12 + +LBB8_136: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x00000080248c8948 // mov qword [rsp + 128], rcx + +LBB8_137: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3a44; BYTE $0x3e // cmp r15b, byte [rsi] + QUAD $0x0000012024949f0f // setg byte [rsp + 288] + LONG $0x017e3a44 // cmp r15b, byte [rsi + 1] + LONG $0xd19f0f41 // setg r9b + LONG $0x027e3a44 // cmp r15b, byte [rsi + 2] + LONG $0xd39f0f41 // setg r11b + LONG $0x037e3a44 // cmp r15b, byte [rsi + 3] + LONG $0xd59f0f41 // setg r13b + LONG $0x047e3a44 // cmp r15b, byte [rsi + 4] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x057e3a44 // cmp r15b, byte [rsi + 5] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x067e3a44 // cmp r15b, byte [rsi + 6] + WORD $0x9f0f; BYTE $0xd3 // setg bl + LONG $0x077e3a44 // cmp r15b, byte [rsi + 7] + LONG $0xd49f0f41 // setg r12b + LONG $0x087e3a44 // cmp r15b, byte [rsi + 8] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x097e3a44 // cmp r15b, byte [rsi + 9] + LONG $0xd69f0f40 // setg sil + LONG $0x0a793a44 // cmp r15b, byte [rcx + 10] + LONG $0xd79f0f40 // setg dil + LONG $0x0b793a44 // cmp r15b, byte [rcx + 11] + LONG $0xd09f0f41 // setg r8b + LONG $0x0c793a44 // cmp r15b, byte [rcx + 12] + LONG $0xd29f0f41 // setg r10b + LONG $0x0d793a44 // cmp r15b, byte [rcx + 13] + LONG $0xd79f0f41 // setg r15b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + WORD $0x9f0f; BYTE $0xd0 // setg al + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + QUAD $0x0000010024949f0f // setg byte [rsp + 256] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] + LONG $0xd69f0f41 // setg r14b + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] + QUAD $0x000000f024949f0f // setg byte [rsp + 240] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] + QUAD $0x0000014024949f0f // setg byte [rsp + 320] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] + WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000120248c0244 // add r9b, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x60 // add sil, byte [rsp + 96] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xdd // or r13b, r11b + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xeb // or bl, r13b + WORD $0xde89 // mov esi, ebx + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0x0840; BYTE $0xf3 // or bl, sil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x05e7c041 // shl r15b, 5 + WORD $0x0845; BYTE $0xd7 // or r15b, r10b + LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] + LONG $0x06e6c040 // shl sil, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0x0841; BYTE $0xdc // or r12b, bl + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247c8b44; BYTE $0x04 // mov r15d, dword [rsp + 4] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xdb00 // add bl, bl + LONG $0x00249c02; WORD $0x0001; BYTE $0x00 // add bl, byte [rsp + 256] + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0x0840; BYTE $0xf3 // or bl, sil + QUAD $0x0000016024bc8b48 // mov rdi, qword [rsp + 352] + WORD $0x8844; BYTE $0x27 // mov byte [rdi], r12b + LONG $0x2474b60f; BYTE $0x18 // movzx esi, byte [rsp + 24] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xf6 // or r14b, sil + WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xc000 // add al, al + LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd808 // or al, bl + QUAD $0x00000140249cb60f // movzx ebx, byte [rsp + 320] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02778844 // mov byte [rdi + 2], r14b + WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000016024bc8948 // mov qword [rsp + 352], rdi + QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 + JNE LBB8_137 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x00000168248c8b48 // mov rcx, qword [rsp + 360] + JMP LBB8_140 + +LBB8_139: + QUAD $0x0000016024a4894c // mov qword [rsp + 352], r12 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + +LBB8_140: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB8_194 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB8_195 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB8_198 + +LBB8_143: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB8_194 + +LBB8_144: + LONG $0x01c48349 // add r12, 1 + +LBB8_145: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB8_153 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x247c8944; BYTE $0x04 // mov dword [rsp + 4], r15d + QUAD $0x000000f824b4894c // mov qword [rsp + 248], r14 + QUAD $0x00000170248c8948 // mov qword [rsp + 368], rcx + JB LBB8_149 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB8_208 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB8_208 + +LBB8_149: WORD $0xc031 // xor eax, eax QUAD $0x0000016824848948 // mov qword [rsp + 360], rax - WORD $0x8949; BYTE $0xd4 // mov r12, rdx - QUAD $0x00000160249c894c // mov qword [rsp + 352], r11 + WORD $0x8949; BYTE $0xfb // mov r11, rdi + QUAD $0x0000016024a4894c // mov qword [rsp + 352], r12 -LBB8_101: - QUAD $0x0000016824bc2b4c // sub r15, qword [rsp + 360] - QUAD $0x0000008024bc894c // mov qword [rsp + 128], r15 +LBB8_150: + QUAD $0x00000168248c2b48 // sub rcx, qword [rsp + 360] + QUAD $0x00000080248c8948 // mov qword [rsp + 128], rcx -LBB8_102: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343a45 // cmp r14b, byte [r12] - QUAD $0x000001402494970f // seta byte [rsp + 320] - LONG $0x24743a45; BYTE $0x01 // cmp r14b, byte [r12 + 1] - LONG $0xd2970f41 // seta r10b - LONG $0x24743a45; BYTE $0x02 // cmp r14b, byte [r12 + 2] - WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x24743a45; BYTE $0x03 // cmp r14b, byte [r12 + 3] +LBB8_151: + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + WORD $0x3a45; BYTE $0x3b // cmp r15b, byte [r11] + QUAD $0x000001202494970f // seta byte [rsp + 288] + LONG $0x017b3a45 // cmp r15b, byte [r11 + 1] + LONG $0xd1970f41 // seta r9b + LONG $0x027b3a45 // cmp r15b, byte [r11 + 2] + LONG $0xd3970f41 // seta r11b + LONG $0x03793a44 // cmp r15b, byte [rcx + 3] LONG $0xd5970f41 // seta r13b - LONG $0x24743a45; BYTE $0x04 // cmp r14b, byte [r12 + 4] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0x24743a45; BYTE $0x05 // cmp r14b, byte [r12 + 5] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0x24743a45; BYTE $0x06 // cmp r14b, byte [r12 + 6] - WORD $0x970f; BYTE $0xd0 // seta al - LONG $0x24743a45; BYTE $0x07 // cmp r14b, byte [r12 + 7] + LONG $0x04793a44 // cmp r15b, byte [rcx + 4] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x05793a44 // cmp r15b, byte [rcx + 5] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x06793a44 // cmp r15b, byte [rcx + 6] + WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0x07793a44 // cmp r15b, byte [rcx + 7] LONG $0xd4970f41 // seta r12b - LONG $0x08713a44 // cmp r14b, byte [rcx + 8] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] - LONG $0x09713a44 // cmp r14b, byte [rcx + 9] + LONG $0x08793a44 // cmp r15b, byte [rcx + 8] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x09793a44 // cmp r15b, byte [rcx + 9] LONG $0xd6970f40 // seta sil - LONG $0x0a713a44 // cmp r14b, byte [rcx + 10] + LONG $0x0a793a44 // cmp r15b, byte [rcx + 10] LONG $0xd7970f40 // seta dil - LONG $0x0b713a44 // cmp r14b, byte [rcx + 11] - LONG $0xd1970f41 // seta r9b - LONG $0x0c713a44 // cmp r14b, byte [rcx + 12] - LONG $0xd3970f41 // seta r11b - LONG $0x0d713a44 // cmp r14b, byte [rcx + 13] - LONG $0xd7970f41 // seta r15b - LONG $0x0e713a44 // cmp r14b, byte [rcx + 14] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0x0f713a44 // cmp r14b, byte [rcx + 15] + LONG $0x0b793a44 // cmp r15b, byte [rcx + 11] LONG $0xd0970f41 // seta r8b - LONG $0x10713a44 // cmp r14b, byte [rcx + 16] + LONG $0x0c793a44 // cmp r15b, byte [rcx + 12] + LONG $0xd2970f41 // seta r10b + LONG $0x0d793a44 // cmp r15b, byte [rcx + 13] + LONG $0xd7970f41 // seta r15b + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x0424448b // mov eax, dword [rsp + 4] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + WORD $0x970f; BYTE $0xd0 // seta al + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] QUAD $0x000001002494970f // seta byte [rsp + 256] - LONG $0x11713a44 // cmp r14b, byte [rcx + 17] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] - LONG $0x12713a44 // cmp r14b, byte [rcx + 18] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x13713a44 // cmp r14b, byte [rcx + 19] - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0x14713a44 // cmp r14b, byte [rcx + 20] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x15713a44 // cmp r14b, byte [rcx + 21] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] - LONG $0x16713a44 // cmp r14b, byte [rcx + 22] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x17713a44 // cmp r14b, byte [rcx + 23] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x0424548b // mov edx, dword [rsp + 4] + WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] LONG $0xd6970f41 // seta r14b LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] - QUAD $0x000000e82494970f // seta byte [rsp + 232] + QUAD $0x000000f02494970f // seta byte [rsp + 240] LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - QUAD $0x000001202494970f // seta byte [rsp + 288] + QUAD $0x000001402494970f // seta byte [rsp + 320] LONG $0x0424548b // mov edx, dword [rsp + 4] WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000014024940244 // add r10b, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000120248c0244 // add r9b, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e4c041 // shl r12b, 7 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xd3 // or bl, r10b + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0845; BYTE $0xcb // or r11b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + LONG $0x24740240; BYTE $0x60 // add sil, byte [rsp + 96] LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0841; BYTE $0xdd // or r13b, bl + WORD $0x0845; BYTE $0xdd // or r13b, r11b LONG $0x02e7c040 // shl dil, 2 WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xeb // or bl, r13b WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e7c041 // shl r15b, 5 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x2474b60f; BYTE $0x48 // movzx esi, byte [rsp + 72] + WORD $0x0845; BYTE $0xd7 // or r15b, r10b + LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0840; BYTE $0xf0 // or al, sil WORD $0x0841; BYTE $0xdc // or r12b, bl - WORD $0x0845; BYTE $0xf8 // or r8b, r15b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xc000 // add al, al - LONG $0x00248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 256] - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247c8b44; BYTE $0x04 // mov r15d, dword [rsp + 4] + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] + WORD $0xdb00 // add bl, bl + LONG $0x00249c02; WORD $0x0001; BYTE $0x00 // add bl, byte [rsp + 256] + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0xc308 // or bl, al + WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx @@ -46613,368 +48167,120 @@ LBB8_102: WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil QUAD $0x0000016024b48b48 // mov rsi, qword [rsp + 352] WORD $0x8844; BYTE $0x26 // mov byte [rsi], r12b - LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] + LONG $0x247cb60f; BYTE $0x18 // movzx edi, byte [rsp + 24] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e6c041 // shl r14b, 7 WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x01468844 // mov byte [rsi + 1], r8b + WORD $0x4688; BYTE $0x01 // mov byte [rsi + 1], al WORD $0x0841; BYTE $0xde // or r14b, bl - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xc000 // add al, al - LONG $0xe8248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 232] + LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + QUAD $0x00000140249cb60f // movzx ebx, byte [rsp + 320] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0xda08 // or dl, bl WORD $0xc208 // or dl, al LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] WORD $0x5688; BYTE $0x03 // mov byte [rsi + 3], dl - LONG $0x20618d4c // lea r12, [rcx + 32] + LONG $0x20598d4c // lea r11, [rcx + 32] LONG $0x04c68348 // add rsi, 4 QUAD $0x0000016024b48948 // mov qword [rsp + 352], rsi QUAD $0x0000008024848348; BYTE $0xff // add qword [rsp + 128], -1 - JNE LBB8_102 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000017024bc8b4c // mov r15, qword [rsp + 368] - JMP LBB8_125 - -LBB8_104: - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_108 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_106: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x33 // movzx r8d, byte [r11 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_106 - LONG $0x01c38349 // add r11, 1 - -LBB8_108: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_112 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - -LBB8_110: - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - QUAD $0x0000008024949f0f // setg byte [rsp + 128] - LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] - LONG $0xd79f0f40 // setg dil - LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] - LONG $0xd69f0f41 // setg r14b - LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] - WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] - LONG $0xd39f0f41 // setg r11b - LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] - LONG $0xd69f0f40 // setg sil - LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] - LONG $0xd09f0f41 // setg r8b - LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] - LONG $0xd19f0f41 // setg r9b - LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] - LONG $0xd29f0f41 // setg r10b - LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] - LONG $0xd49f0f41 // setg r12b - LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x9f0f; BYTE $0xd1 // setg cl - LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] - LONG $0xd79f0f41 // setg r15b - LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] - QUAD $0x0000014024949f0f // setg byte [rsp + 320] - LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] - QUAD $0x0000012024949f0f // setg byte [rsp + 288] - LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] - QUAD $0x0000010024949f0f // setg byte [rsp + 256] - LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] - LONG $0x24549f0f; BYTE $0x04 // setg byte [rsp + 4] - LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x48 // add sil, byte [rsp + 72] - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - WORD $0x8844; BYTE $0x18 // mov byte [rax], r11b - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x014b8841 // mov byte [r11 + 1], cl - WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xc000 // add al, al - LONG $0x40248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 320] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xcb08 // or bl, cl - WORD $0xc308 // or bl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x035b8841 // mov byte [r11 + 3], bl - LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c38349 // add r11, 4 - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB8_110 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - -LBB8_112: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB8_179 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB8_150 - WORD $0xff31 // xor edi, edi - JMP LBB8_152 - -LBB8_115: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB8_179 - -LBB8_116: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB8_156 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB8_158 - -LBB8_118: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB8_179 - -LBB8_119: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB8_160 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB8_162 - -LBB8_121: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB8_179 + JNE LBB8_151 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x00000170248c8b48 // mov rcx, qword [rsp + 368] + JMP LBB8_154 -LBB8_122: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB8_164 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB8_166 +LBB8_153: + QUAD $0x0000016024a4894c // mov qword [rsp + 352], r12 + WORD $0x8949; BYTE $0xfb // mov r11, rdi -LBB8_124: - QUAD $0x00000160249c894c // mov qword [rsp + 352], r11 - WORD $0x8949; BYTE $0xd4 // mov r12, rdx - -LBB8_125: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB8_179 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB8_169 +LBB8_154: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB8_194 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB8_200 WORD $0xc031 // xor eax, eax - JMP LBB8_172 + JMP LBB8_203 -LBB8_128: - WORD $0x894d; BYTE $0xdf // mov r15, r11 - LONG $0x05fdc149 // sar r13, 5 - LONG $0x20fa8349 // cmp r10, 32 - JGE LBB8_34 +LBB8_157: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB8_129: - QUAD $0x0000016024bc894c // mov qword [rsp + 352], r15 - WORD $0x8949; BYTE $0xd4 // mov r12, rdx +LBB8_158: + WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d + WORD $0xff19 // sbb edi, edi + WORD $0x894c; BYTE $0xde // mov rsi, r11 + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x3044; BYTE $0xd7 // xor dil, r10b + WORD $0x2040; BYTE $0xf8 // and al, dil + WORD $0x3044; BYTE $0xd0 // xor al, r10b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x02c38349 // add r11, 2 + LONG $0x046a3944 // cmp dword [rdx + 4], r13d + LONG $0x08528d48 // lea rdx, [rdx + 8] + WORD $0xff19 // sbb edi, edi + WORD $0x3040; BYTE $0xc7 // xor dil, al + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x2040; BYTE $0xfb // and bl, dil + WORD $0xc330 // xor bl, al + LONG $0x341c8841 // mov byte [r12 + rsi], bl + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB8_158 -LBB8_130: - LONG $0x05e5c149 // shl r13, 5 - WORD $0x394d; BYTE $0xd5 // cmp r13, r10 - JGE LBB8_179 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xe8 // sub r8, r13 - WORD $0xf749; BYTE $0xd5 // not r13 - WORD $0x014d; BYTE $0xd5 // add r13, r10 - JNE LBB8_174 - WORD $0xf631 // xor esi, esi - JMP LBB8_177 +LBB8_159: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_194 + WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d + JMP LBB8_173 -LBB8_133: +LBB8_161: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi - WORD $0x894d; BYTE $0xde // mov r14, r11 -LBB8_134: +LBB8_162: LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] WORD $0x970f; BYTE $0xd0 // seta al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -46982,7 +48288,7 @@ LBB8_134: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] LONG $0xd1970f41 // seta r9b @@ -46994,29 +48300,121 @@ LBB8_134: WORD $0xe0d2 // shl al, cl WORD $0x2044; BYTE $0xc8 // and al, r9b WORD $0xd830 // xor al, bl - LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x34048841 // mov byte [r12 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_134 + JNE LBB8_162 -LBB8_135: +LBB8_163: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 + JE LBB8_194 LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - JMP LBB8_149 + JMP LBB8_186 -LBB8_137: +LBB8_165: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB8_166: + WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 + WORD $0xff19 // sbb edi, edi + WORD $0x894c; BYTE $0xde // mov rsi, r11 + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x3044; BYTE $0xd7 // xor dil, r10b + WORD $0x2040; BYTE $0xf8 // and al, dil + WORD $0x3044; BYTE $0xd0 // xor al, r10b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x02c38349 // add r11, 2 + LONG $0x086a394c // cmp qword [rdx + 8], r13 + LONG $0x10528d48 // lea rdx, [rdx + 16] + WORD $0xff19 // sbb edi, edi + WORD $0x3040; BYTE $0xc7 // xor dil, al + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x2040; BYTE $0xfb // and bl, dil + WORD $0xc330 // xor bl, al + LONG $0x341c8841 // mov byte [r12 + rsi], bl + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB8_166 + +LBB8_167: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_194 + WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 + JMP LBB8_173 + +LBB8_169: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB8_170: + LONG $0x2a394466 // cmp word [rdx], r13w + WORD $0xff19 // sbb edi, edi + WORD $0x894c; BYTE $0xde // mov rsi, r11 + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x3044; BYTE $0xd7 // xor dil, r10b + WORD $0x2040; BYTE $0xf8 // and al, dil + WORD $0x3044; BYTE $0xd0 // xor al, r10b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x02c38349 // add r11, 2 + LONG $0x6a394466; BYTE $0x02 // cmp word [rdx + 2], r13w + LONG $0x04528d48 // lea rdx, [rdx + 4] + WORD $0xff19 // sbb edi, edi + WORD $0x3040; BYTE $0xc7 // xor dil, al + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x2040; BYTE $0xfb // and bl, dil + WORD $0xc330 // xor bl, al + LONG $0x341c8841 // mov byte [r12 + rsi], bl + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB8_170 + +LBB8_171: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_194 + LONG $0x2a394466 // cmp word [rdx], r13w + +LBB8_173: + WORD $0xc019 // sbb eax, eax + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x14348a41 // mov sil, byte [r12 + rdx] + LONG $0x07e38041 // and r11b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0xc320 // and bl, al + JMP LBB8_193 + +LBB8_174: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi - WORD $0x894d; BYTE $0xde // mov r14, r11 -LBB8_138: +LBB8_175: LONG $0x2a3b4466 // cmp r13w, word [rdx] WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -47024,7 +48422,7 @@ LBB8_138: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] LONG $0x04528d48 // lea rdx, [rdx + 4] @@ -47036,29 +48434,29 @@ LBB8_138: WORD $0xe0d2 // shl al, cl WORD $0x2044; BYTE $0xc8 // and al, r9b WORD $0xd830 // xor al, bl - LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x34048841 // mov byte [r12 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_138 + JNE LBB8_175 -LBB8_139: +LBB8_176: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 + JE LBB8_194 LONG $0x2a3b4466 // cmp r13w, word [rdx] - JMP LBB8_154 + JMP LBB8_191 -LBB8_141: +LBB8_178: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi - WORD $0x894d; BYTE $0xde // mov r14, r11 -LBB8_142: +LBB8_179: WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -47066,7 +48464,7 @@ LBB8_142: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 LONG $0x086a3b4c // cmp r13, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] @@ -47078,29 +48476,29 @@ LBB8_142: WORD $0xe0d2 // shl al, cl WORD $0x2044; BYTE $0xc8 // and al, r9b WORD $0xd830 // xor al, bl - LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x34048841 // mov byte [r12 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_142 + JNE LBB8_179 -LBB8_143: +LBB8_180: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 + JE LBB8_194 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - JMP LBB8_154 + JMP LBB8_191 -LBB8_145: +LBB8_182: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi - WORD $0x894d; BYTE $0xde // mov r14, r11 -LBB8_146: +LBB8_183: LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] WORD $0x970f; BYTE $0xd0 // seta al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -47108,7 +48506,7 @@ LBB8_146: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 LONG $0x422ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rdx + 4] LONG $0xd1970f41 // seta r9b @@ -47120,220 +48518,149 @@ LBB8_146: WORD $0xe0d2 // shl al, cl WORD $0x2044; BYTE $0xc8 // and al, r9b WORD $0xd830 // xor al, bl - LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x34048841 // mov byte [r12 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_146 + JNE LBB8_183 -LBB8_147: +LBB8_184: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 + JE LBB8_194 LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] -LBB8_149: +LBB8_186: WORD $0x970f; BYTE $0xd0 // seta al - JMP LBB8_155 + JMP LBB8_192 -LBB8_150: +LBB8_187: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi - WORD $0x894d; BYTE $0xde // mov r14, r11 -LBB8_151: +LBB8_188: WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd19f0f41 // setg r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x36048841 // mov byte [r14 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_151 - -LBB8_152: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - -LBB8_154: - WORD $0x9f0f; BYTE $0xd0 // setg al - -LBB8_155: - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x13348a41 // mov sil, byte [r11 + rdx] - LONG $0x07e78040 // and dil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf989 // mov ecx, edi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x131c8841 // mov byte [r11 + rdx], bl - JMP LBB8_179 - -LBB8_156: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - -LBB8_157: - WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d - WORD $0xff19 // sbb edi, edi - WORD $0x894c; BYTE $0xde // mov rsi, r11 - LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x046a3944 // cmp dword [rdx + 4], r13d - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0xff19 // sbb edi, edi - WORD $0x3040; BYTE $0xc7 // xor dil, al - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB8_157 - -LBB8_158: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 - WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d - JMP LBB8_168 - -LBB8_160: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - -LBB8_161: - WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 - WORD $0xff19 // sbb edi, edi - WORD $0x894c; BYTE $0xde // mov rsi, r11 - LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x086a394c // cmp qword [rdx + 8], r13 - LONG $0x10528d48 // lea rdx, [rdx + 16] - WORD $0xff19 // sbb edi, edi - WORD $0x3040; BYTE $0xc7 // xor dil, al - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB8_161 + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x341c8841 // mov byte [r12 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] + LONG $0x08528d48 // lea rdx, [rdx + 8] + LONG $0xd19f0f41 // setg r9b + WORD $0xf641; BYTE $0xd9 // neg r9b + WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0xd830 // xor al, bl + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfa // cmp r10, rdi + JNE LBB8_188 -LBB8_162: +LBB8_189: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 - WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 - JMP LBB8_168 + JE LBB8_194 + WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] -LBB8_164: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 +LBB8_191: + WORD $0x9f0f; BYTE $0xd0 // setg al -LBB8_165: - LONG $0x2a394466 // cmp word [rdx], r13w - WORD $0xff19 // sbb edi, edi - WORD $0x894c; BYTE $0xde // mov rsi, r11 - LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d +LBB8_192: + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0x03eac148 // shr rdx, 3 + LONG $0x14348a41 // mov sil, byte [r12 + rdx] + LONG $0x07e78040 // and dil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf989 // mov ecx, edi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0xc320 // and bl, al + +LBB8_193: + WORD $0x3040; BYTE $0xf3 // xor bl, sil + LONG $0x141c8841 // mov byte [r12 + rdx], bl + +LBB8_194: + MOVQ 1312(SP), SP + VZEROUPPER + RET + +LBB8_195: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x00000160249c8b4c // mov r11, qword [rsp + 352] + +LBB8_196: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e3c3a46 // cmp r15b, byte [rsi + r9] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x067c3a44; BYTE $0x01 // cmp r15b, byte [rsi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x6a394466; BYTE $0x02 // cmp word [rdx + 2], r13w - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0xff19 // sbb edi, edi - WORD $0x3040; BYTE $0xc7 // xor dil, al - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB8_165 - -LBB8_166: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 - LONG $0x2a394466 // cmp word [rdx], r13w + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB8_196 + WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB8_168: - WORD $0xc019 // sbb eax, eax - WORD $0x894c; BYTE $0xda // mov rdx, r11 +LBB8_198: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_194 + WORD $0x3a44; BYTE $0x3e // cmp r15b, byte [rsi] + WORD $0x9f0f; BYTE $0xd0 // setg al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 - LONG $0x16348a41 // mov sil, byte [r14 + rdx] - LONG $0x07e38041 // and r11b, 7 + QUAD $0x0000016024848b4c // mov r8, qword [rsp + 352] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x161c8841 // mov byte [r14 + rdx], bl - JMP LBB8_179 + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + JMP LBB8_194 -LBB8_169: +LBB8_200: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0xc031 // xor eax, eax QUAD $0x0000016024948b4c // mov r10, qword [rsp + 352] -LBB8_170: - LONG $0x04343845 // cmp byte [r12 + rax], r14b +LBB8_201: + LONG $0x033c3845 // cmp byte [r11 + rax], r15b WORD $0xf619 // sbb esi, esi WORD $0x8948; BYTE $0xc7 // mov rdi, rax LONG $0x03efc148 // shr rdi, 3 @@ -47346,7 +48673,7 @@ LBB8_170: WORD $0x2040; BYTE $0xf2 // and dl, sil WORD $0xda30 // xor dl, bl LONG $0x3a148841 // mov byte [r10 + rdi], dl - LONG $0x04743845; BYTE $0x01 // cmp byte [r12 + rax + 1], r14b + LONG $0x037c3845; BYTE $0x01 // cmp byte [r11 + rax + 1], r15b LONG $0x02408d48 // lea rax, [rax + 2] WORD $0xf619 // sbb esi, esi WORD $0x3040; BYTE $0xd6 // xor sil, dl @@ -47357,13 +48684,13 @@ LBB8_170: WORD $0xd330 // xor bl, dl LONG $0x3a1c8841 // mov byte [r10 + rdi], bl WORD $0x3949; BYTE $0xc1 // cmp r9, rax - JNE LBB8_170 - WORD $0x0149; BYTE $0xc4 // add r12, rax + JNE LBB8_201 + WORD $0x0149; BYTE $0xc3 // add r11, rax -LBB8_172: +LBB8_203: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 - LONG $0x24343845 // cmp byte [r12], r14b + JE LBB8_194 + WORD $0x3845; BYTE $0x3b // cmp byte [r11], r15b WORD $0xd219 // sbb edx, edx WORD $0x8948; BYTE $0xc6 // mov rsi, rax LONG $0x03eec148 // shr rsi, 3 @@ -47377,2043 +48704,1987 @@ LBB8_172: WORD $0xd320 // and bl, dl WORD $0x3040; BYTE $0xfb // xor bl, dil LONG $0x301c8841 // mov byte [r8 + rsi], bl - JMP LBB8_179 - -LBB8_174: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - QUAD $0x00000160249c8b4c // mov r11, qword [rsp + 352] - -LBB8_175: - LONG $0x34343a45 // cmp r14b, byte [r12 + rsi] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743a45; BYTE $0x01 // cmp r14b, byte [r12 + rsi + 1] - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB8_175 - WORD $0x0149; BYTE $0xf4 // add r12, rsi - -LBB8_177: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_179 - LONG $0x24343a45 // cmp r14b, byte [r12] - WORD $0x9f0f; BYTE $0xd0 // setg al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - QUAD $0x0000016024848b4c // mov r8, qword [rsp + 352] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - -LBB8_179: - MOVQ 1312(SP), SP - VZEROUPPER - RET + JMP LBB8_194 -LBB8_180: - LONG $0xe0e58349 // and r13, -32 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 +LBB8_205: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000017024848948 // mov qword [rsp + 368], rax - QUAD $0x0000018024ac894c // mov qword [rsp + 384], r13 - LONG $0xaf048d4b // lea rax, [r15 + 4*r13] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] QUAD $0x0000016024848948 // mov qword [rsp + 352], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc7 // vmovd xmm0, r15d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 -LBB8_181: +LBB8_206: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000017824848948 // mov qword [rsp + 376], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] + WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1a04b60f // movzx eax, byte [rdx + rbx] + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] - WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0x1744b60f; BYTE $0x01 // movzx eax, byte [rdi + rdx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x3244b60f; BYTE $0x02 // movzx eax, byte [rdx + rsi + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000220248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 544], xmm1 - LONG $0x1a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x3244b60f; BYTE $0x03 // movzx eax, byte [rdx + rsi + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x3244b60f; BYTE $0x04 // movzx eax, byte [rdx + rsi + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x1a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x3244b60f; BYTE $0x05 // movzx eax, byte [rdx + rsi + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x3244b60f; BYTE $0x06 // movzx eax, byte [rdx + rsi + 6] - QUAD $0x000000d824b48948 // mov qword [rsp + 216], rsi + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x000000d024948948 // mov qword [rsp + 208], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x3244b60f; BYTE $0x07 // movzx eax, byte [rdx + rsi + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - LONG $0x40cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 576 - QUAD $0x00000090249c8948 // mov qword [rsp + 144], rbx - WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02400d48; WORD $0x0000 // or rax, 576 + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02600d48; WORD $0x0000 // or rax, 608 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - WORD $0x8949; BYTE $0xcc // mov r12, rcx - LONG $0x80cc8149; WORD $0x0002; BYTE $0x00 // or r12, 640 - WORD $0x8949; BYTE $0xce // mov r14, rcx - LONG $0xa0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 672 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - WORD $0x8949; BYTE $0xca // mov r10, rcx - LONG $0xc0ca8149; WORD $0x0002; BYTE $0x00 // or r10, 704 - LONG $0x2454894c; BYTE $0x68 // mov qword [rsp + 104], r10 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0xe0cf8148; WORD $0x0002; BYTE $0x00 // or rdi, 736 - QUAD $0x000000b024bc8948 // mov qword [rsp + 176], rdi - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x03000d48; WORD $0x0000 // or rax, 768 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x20cf8149; WORD $0x0003; BYTE $0x00 // or r15, 800 - LONG $0x247c894c; BYTE $0x70 // mov qword [rsp + 112], r15 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - LONG $0x40cb8149; WORD $0x0003; BYTE $0x00 // or r11, 832 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 - LONG $0x244c894c; BYTE $0x48 // mov qword [rsp + 72], r9 - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 - QUAD $0x000000a82484894c // mov qword [rsp + 168], r8 - WORD $0x8948; BYTE $0xce // mov rsi, rcx - LONG $0xa0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 928 - QUAD $0x000000c824b48948 // mov qword [rsp + 200], rsi + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x80cb8149; WORD $0x0002; BYTE $0x00 // or r11, 640 + QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 + WORD $0x8949; BYTE $0xdc // mov r12, rbx + LONG $0xa0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 672 + QUAD $0x0000009824a4894c // mov qword [rsp + 152], r12 + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0xc0cf8149; WORD $0x0002; BYTE $0x00 // or r15, 704 + QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0xe0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 736 + QUAD $0x000000e024b4894c // mov qword [rsp + 224], r14 + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0x00c88149; WORD $0x0003; BYTE $0x00 // or r8, 768 + LONG $0x2444894c; BYTE $0x10 // mov qword [rsp + 16], r8 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03200d48; WORD $0x0000 // or rax, 800 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03400d48; WORD $0x0000 // or rax, 832 + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x60ca8149; WORD $0x0003; BYTE $0x00 // or r10, 864 + QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + LONG $0x80c98149; WORD $0x0003; BYTE $0x00 // or r9, 896 + QUAD $0x00000080248c894c // mov qword [rsp + 128], r9 + LONG $0xa0cb8148; WORD $0x0003; BYTE $0x00 // or rbx, 928 + QUAD $0x000000a0249c8948 // mov qword [rsp + 160], rbx WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + QUAD $0x000000d8248c8948 // mov qword [rsp + 216], rcx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - LONG $0x207923c4; WORD $0x2a0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdx + r13], 1 - LONG $0x2031e3c4; WORD $0x1a04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdx + rbx], 2 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdx + rbx], 3 - LONG $0x2079a3c4; WORD $0x2204; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdx + r12], 4 - WORD $0x894d; BYTE $0xe5 // mov r13, r12 - QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 - LONG $0x2079a3c4; WORD $0x3204; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdx + r14], 5 - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdx + r10], 6 - LONG $0x2079e3c4; WORD $0x3a04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdx + rdi], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - LONG $0x2079e3c4; WORD $0x3a04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdx + rdi], 8 - LONG $0x2079a3c4; WORD $0x3a04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdx + r15], 9 - LONG $0x2079a3c4; WORD $0x1a04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdx + r11], 10 - LONG $0x2079a3c4; WORD $0x0a04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdx + r9], 11 - LONG $0x2079a3c4; WORD $0x0204; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdx + r8], 12 - LONG $0x2079e3c4; WORD $0x3204; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdx + rsi], 13 - LONG $0x2079e3c4; WORD $0x0204; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdx + rax], 14 - LONG $0x2079e3c4; WORD $0x0a04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdx + rcx], 15 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdx + r14], 1 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdx + r11], 2 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - LONG $0x2061a3c4; WORD $0x221c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + r12], 3 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r8], 4 + QUAD $0x00000120248c8948 // mov qword [rsp + 288], rcx + LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + LONG $0x207923c4; WORD $0x2f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r13], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + LONG $0x2031e3c4; WORD $0x1704; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rdx], 2 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rdx], 3 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r11], 4 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + r12], 5 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r15], 6 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + r14], 7 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r8], 8 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + rsi], 9 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r12], 10 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + r10], 11 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r9], 12 + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rbx], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r8], 2 LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r9], 5 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - LONG $0x2061a3c4; WORD $0x121c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + r10], 6 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + r15], 7 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + rsi], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + rax], 9 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + rbx], 10 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + rcx], 11 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + rdi], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rdi], 13 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rdi], 14 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + rdi], 15 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x01013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x02013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 2 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x03013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 3 - QUAD $0x04012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 4 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x05012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 5 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x06013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 6 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x07013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x08013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x09013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 11 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0c013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 12 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0d013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e013a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 1], 14 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x0f012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 15 - QUAD $0x0101326c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r14 + 1], 1 - QUAD $0x02011a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 1], 2 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - QUAD $0x0301226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 1], 3 - QUAD $0x0401026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 1], 4 - QUAD $0x05010a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 1], 5 - QUAD $0x0601126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 1], 6 - QUAD $0x07013a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 1], 7 - QUAD $0x0801326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 1], 8 - QUAD $0x0901026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 9 - QUAD $0x0a011a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 1], 10 - QUAD $0x0b010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 11 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0c01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 13 + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r9], 3 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r10], 4 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r15], 6 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r14], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rsi], 8 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 14 - LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rcx], 10 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rdx], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rdx], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rdx], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + LONG $0x2061a3c4; WORD $0x2f1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + r13], 15 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x010117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x020117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 2 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x030117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 3 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x040117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 4 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x050117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 5 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x060117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 6 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x070117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x080117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 8 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x090117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 9 + QUAD $0x0a0127642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 1], 10 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0b0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0c0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 12 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0d0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 13 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0e0117642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 1], 14 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0f012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 15 + QUAD $0x01011f6c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rbx + 1], 1 + QUAD $0x0201076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 2 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x03010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 3 + QUAD $0x0401176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x06013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 6 + QUAD $0x0701376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 1], 7 + QUAD $0x0801376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0a01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 10 + QUAD $0x0b010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f0102442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 1], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 + LONG $0x386563c4; WORD $0x01f8 // vinserti128 ymm15, ymm3, xmm0, 1 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xce6e79c5 // vmovd xmm9, esi LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1248], ymm0 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xd66e79c5 // vmovd xmm10, esi - LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] QUAD $0x00022024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 544] - QUAD $0x010202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 2], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x02020a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 2], 2 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x030212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 2], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x040202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 4 + QUAD $0x01020f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 2], 1 + QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] + QUAD $0x02020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 2 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x050227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 5 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x06022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 6 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x070237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x080207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x090207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 9 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0a0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 10 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x0b021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 11 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0c021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 12 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x0d023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 13 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x050202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 5 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x060202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x070202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 7 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x080222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 2], 8 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x09022a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 2], 9 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x0a020a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 2], 10 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x0b021a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 2], 11 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x0c0232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 2], 12 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x0d023a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 2], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 14 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0f0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 15 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 1 - QUAD $0x02023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 2 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0302325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 3 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0402325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 4 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0502325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 5 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0602325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0702325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 7 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x08021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 9 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0a023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 10 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0b023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 11 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0c023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 13 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0e023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 14 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0f023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 15 - QUAD $0x010302642021a3c4 // vpinsrb xmm4, xmm11, byte [rdx + r8 + 3], 1 - QUAD $0x02030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 2 - QUAD $0x030312642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 3], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x04030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 4 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x05033a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 3], 5 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x06033a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 3], 6 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x07030a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 3], 7 - QUAD $0x080322642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 3], 8 - QUAD $0x09032a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 3], 9 - QUAD $0x0a030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 10 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - QUAD $0x0b031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 11 - QUAD $0x0c0332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 3], 12 - QUAD $0x0d033a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 3], 13 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0e031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 14 - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x0f0332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 3], 15 - QUAD $0x0103026c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdx + rax + 3], 1 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x02030a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 3], 2 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0303026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 3 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0403026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 4 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0503026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0603026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 6 - QUAD $0x0703326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 7 - QUAD $0x08031a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 3], 8 + QUAD $0x0102075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 2], 1 + QUAD $0x0202175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0302175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 3 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0402175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 4 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0502175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 5 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0602175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0702375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0802175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 8 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x0902175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 9 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0a02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 10 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 15 + QUAD $0x01030f642021e3c4 // vpinsrb xmm4, xmm11, byte [rdi + rcx + 3], 1 + QUAD $0x02030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x040317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 4 + QUAD $0x050327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 5 + QUAD $0x06032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 6 + QUAD $0x070337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 7 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x08030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 8 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0903026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 9 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 10 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0b03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 11 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0c03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 13 + QUAD $0x090307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 3], 9 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0a032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 10 + QUAD $0x0b031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 11 + QUAD $0x0c031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 12 + QUAD $0x0d033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e0307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 3], 14 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0f030f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 3], 15 + QUAD $0x0103076c2039a3c4 // vpinsrb xmm5, xmm8, byte [rdi + r8 + 3], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0203076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 2 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0303276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 3], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0403076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0503076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 5 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0603076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 6 + QUAD $0x0703376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e0302442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 3], 14 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x0274b60f; BYTE $0x09 // movzx esi, byte [rdx + rax + 9] + QUAD $0x0e0317442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rdx + 3], 14 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x0f74b60f; BYTE $0x09 // movzx esi, byte [rdi + rcx + 9] LONG $0xc66e79c5 // vmovd xmm8, esi - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f0302442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 3], 15 + LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + QUAD $0x0f033f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x09 // movzx esi, byte [rdx + rax + 9] + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + LONG $0x1774b60f; BYTE $0x09 // movzx esi, byte [rdi + rdx + 9] LONG $0xde6e79c5 // vmovd xmm11, esi QUAD $0x0001a024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 416] + LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] + QUAD $0x010407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 1 + QUAD $0x02040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 2 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x03041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 3 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + QUAD $0x040417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 5 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x06041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 6 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x070437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 7 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x010402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 1 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x020402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 2 - QUAD $0x030412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 4], 3 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x04042a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 4], 4 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x050402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 5 - WORD $0x8949; BYTE $0xff // mov r15, rdi - QUAD $0x06043a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 4], 6 - QUAD $0x07040a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 4], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x08043a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 4], 8 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x090432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 4], 9 - QUAD $0x0a0402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 10 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0b0402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 11 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0c040a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 4], 12 - QUAD $0x0d0422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 13 - QUAD $0x0e041a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 4], 14 - QUAD $0x0f0432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 4], 15 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0104325c2011e3c4 // vpinsrb xmm3, xmm13, byte [rdx + rsi + 4], 1 - QUAD $0x02040a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 4], 2 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x03041a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 4], 3 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0404225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 4], 4 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x05040a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 4], 5 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0604325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 6 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x07041a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 4], 7 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x08040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 9 + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x090417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 9 + QUAD $0x0a042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 10 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x0b040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 12 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0d040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 13 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0e040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 14 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0a040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 10 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0b04325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 4], 11 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0c040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 13 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - QUAD $0x0e04125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 4], 14 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 15 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x010512642009a3c4 // vpinsrb xmm4, xmm14, byte [rdx + r10 + 5], 1 + QUAD $0x0f040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 15 QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x02050a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 5], 2 + QUAD $0x01040f5c2011e3c4 // vpinsrb xmm3, xmm13, byte [rdi + rcx + 4], 1 LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x03050a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 5], 3 - QUAD $0x04052a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 5], 4 - QUAD $0x050502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 5 - QUAD $0x06053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 6 + QUAD $0x02040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 2 + QUAD $0x0304275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 3 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x04040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 4 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x05040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 5 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0604375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 7 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0804275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 8 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x09040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 9 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0a040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 10 QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x07050a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 5], 7 - QUAD $0x08053a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 5], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x090502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 9 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x0a052a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 5], 10 - QUAD $0x0b0502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 11 - QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] - QUAD $0x0c0502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 12 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0d0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 14 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0f0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 15 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0105026c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdx + rax + 5], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0205026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 2 - QUAD $0x03051a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 5], 3 - QUAD $0x0405226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 5], 4 - QUAD $0x05050a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 5], 5 - QUAD $0x0605326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 5], 6 - QUAD $0x07051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 7 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x08050a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 5], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0905026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 9 + QUAD $0x0b040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 11 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x0c040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 12 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x0d042f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 4], 13 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0e040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 14 + QUAD $0x0f043f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 4], 15 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 + QUAD $0x010507642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r8 + 5], 1 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x02052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 2 + QUAD $0x03051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 3 + QUAD $0x040517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 4 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x050507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 5 + QUAD $0x06051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 6 + QUAD $0x070537642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 5], 7 + QUAD $0x080507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 8 + QUAD $0x090517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 9 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0a0517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 10 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0b0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 12 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0d0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 14 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 10 - QUAD $0x0b05326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 5], 11 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0c05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 12 + QUAD $0x0f0507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 5], 15 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0105076c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdi + rax + 5], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0205076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x04053f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 5], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0505076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 5 + QUAD $0x0605376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 6 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 13 + QUAD $0x0705076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 7 + QUAD $0x0805276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 5], 8 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 14 - LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 + QUAD $0x0905076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 9 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x0c050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f0502442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 5], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x0274b60f; BYTE $0x0a // movzx esi, byte [rdx + rax + 10] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 + LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 + QUAD $0x0f050f442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rcx + 5], 15 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] LONG $0xde6ef9c5 // vmovd xmm3, esi LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x0a // movzx esi, byte [rdx + rax + 10] + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] LONG $0xe66ef9c5 // vmovd xmm4, esi - QUAD $0x010612442019a3c4 // vpinsrb xmm0, xmm12, byte [rdx + r10 + 6], 1 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x020632442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 6], 2 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x030602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x040602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 4 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x050632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 5 - QUAD $0x06063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 6 - QUAD $0x07060a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 6], 7 - QUAD $0x08063a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 6], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x09060a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 6], 9 - QUAD $0x0a062a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 6], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 11 - QUAD $0x0c0602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 12 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x0d0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 14 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 15 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0106126c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdx + r10 + 6], 1 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x02061a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 6], 2 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0306326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 3 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x010607442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rax + 6], 1 + WORD $0x894d; BYTE $0xe9 // mov r9, r13 + QUAD $0x02062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 2 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x04061f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 6], 4 + QUAD $0x050607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 5 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x060637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 6 + QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] + QUAD $0x07061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x080607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 8 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x09060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 9 + QUAD $0x0a0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 10 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x0b0627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 11 + QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] + QUAD $0x0c0617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 6], 12 + QUAD $0x0d0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 15 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0106076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 6], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0206176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0306176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 3 + QUAD $0x04063f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 6], 4 LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0406326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 4 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0506326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 5 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x06061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 6 - QUAD $0x0706226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 7 - QUAD $0x08060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 8 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x09063a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 6], 9 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0a061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 10 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0b060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 11 - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - QUAD $0x0c06226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 12 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0d062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 13 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x0e061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 14 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0f061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 15 + QUAD $0x0506376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 5 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x06062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0706176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0806176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 8 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x0906176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 9 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0a06176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 10 + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x0b06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c06176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d06176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e06176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f06176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 15 + LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] + QUAD $0x01073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 1 + QUAD $0x02070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 2 + WORD $0x894d; BYTE $0xcf // mov r15, r9 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x03070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 3 + QUAD $0x04071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x05071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 5 + QUAD $0x060737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 6 + QUAD $0x07071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 7 LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x01071a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 7], 1 - QUAD $0x020732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 7], 2 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x03071a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 7], 3 - QUAD $0x040702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 4 - WORD $0x8949; BYTE $0xc6 // mov r14, rax - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x050702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 5 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x060702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x070702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 7 - QUAD $0x08073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 8 - QUAD $0x09070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 9 + QUAD $0x08071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 8 + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x0a071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 10 + QUAD $0x0b0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 11 + QUAD $0x0c0717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 7], 12 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0d071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 13 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x0e0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 14 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0f070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 15 + QUAD $0x0107074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0207074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0307074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 3 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 10 + QUAD $0x0407074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 4 + QUAD $0x0507374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 5 + QUAD $0x06072f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 7], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0907074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 9 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 + QUAD $0x0b07074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 7], 11 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 12 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 11 - QUAD $0x0c0702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 12 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0d0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 14 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x0f070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 15 - QUAD $0x0107124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 7], 1 - QUAD $0x02071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 2 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x03070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 3 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x04070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 4 - QUAD $0x0507324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 5 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x06070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x07070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 7 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x08070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 8 - QUAD $0x09073a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 7], 9 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0a070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 10 - QUAD $0x0b070a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 7], 11 - QUAD $0x0c07224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 7], 12 - QUAD $0x0d072a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 7], 13 + QUAD $0x0d07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e070a442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rcx + 7], 14 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - LONG $0x0a74b60f; BYTE $0x0b // movzx esi, byte [rdx + rcx + 11] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e0707442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 7], 14 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0774b60f; BYTE $0x0b // movzx esi, byte [rdi + rax + 11] LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f070a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 7], 15 + QUAD $0x0f0717442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a74b60f; BYTE $0x0b // movzx esi, byte [rdx + rcx + 11] + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + LONG $0x0774b60f; BYTE $0x0b // movzx esi, byte [rdi + rax + 11] LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x01080a442031e3c4 // vpinsrb xmm0, xmm9, byte [rdx + rcx + 8], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x02080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 2 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x03082a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 8], 3 - QUAD $0x040832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 8], 4 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x05080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 5 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x060832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 6 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x070832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 7 - QUAD $0x08083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 8 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x090802442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 8], 9 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x0a0812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b0832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 8], 11 - QUAD $0x0c081a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 8], 12 - QUAD $0x0d0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 8], 14 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x0f080a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 8], 15 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x01081a6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r11 + 8], 1 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x0208326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 2 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0308326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 3 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0408326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 4 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x05081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 5 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x06083a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 8], 6 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x0708226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 8], 7 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0808326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x09081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 9 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0a081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 10 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0b081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 11 - LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x0c081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 12 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0d08326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 13 - QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] - QUAD $0x0e08326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 14 + LONG $0x24548b4c; BYTE $0x08 // mov r10, qword [rsp + 8] + QUAD $0x010817442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r10 + 8], 1 + QUAD $0x02083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 2 + QUAD $0x03080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 3 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x04080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 4 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x05083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 5 + QUAD $0x060837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 8], 6 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x070807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x080807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 8 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x09080f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 8], 9 + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x0a081f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 8], 10 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0b0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 11 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x0c081f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 8], 12 + QUAD $0x0d081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 13 + QUAD $0x0e0827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 8], 14 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0f0817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 15 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0108176c2029e3c4 // vpinsrb xmm5, xmm10, byte [rdi + rdx + 8], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0208176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0308176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 3 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0408376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 4 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0508176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 5 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0608076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 6 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x07081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0808176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 8 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x09081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 9 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x0a081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 10 + QUAD $0x0b082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 11 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x0c08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 13 LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0f081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 15 + QUAD $0x0e081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010917742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r10 + 9], 1 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x02091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 2 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x03091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 3 + QUAD $0x04090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 4 + QUAD $0x05093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 5 + QUAD $0x060937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 6 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x070937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 7 LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x01091a742039e3c4 // vpinsrb xmm6, xmm8, byte [rdx + rbx + 9], 1 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x02091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 2 - QUAD $0x03092a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r13 + 9], 3 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x04091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 4 - QUAD $0x05090a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 9], 5 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x06090a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 9], 6 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x07091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 7 - QUAD $0x08093a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 9], 8 - QUAD $0x090902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 9 - QUAD $0x0a0912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 10 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0b091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 11 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0c093a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 9], 12 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0d093a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 9], 13 - QUAD $0x0e0902742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 9], 14 - QUAD $0x0f090a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 9], 15 - QUAD $0x01091a7c2021a3c4 // vpinsrb xmm7, xmm11, byte [rdx + r11 + 9], 1 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x02090a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r9 + 9], 2 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0309027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 3 - QUAD $0x0409327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 9], 4 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0509027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 5 - QUAD $0x06093a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r15 + 9], 6 - QUAD $0x0709227c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r12 + 9], 7 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x08093a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r15 + 9], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0909027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 9 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 10 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x0b09227c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r12 + 9], 11 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0c09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 13 - QUAD $0x0e09327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 9], 14 + QUAD $0x08091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 8 + QUAD $0x09090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 9 + QUAD $0x0a0907742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 9], 10 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x0b090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 11 + QUAD $0x0c091f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 9], 12 + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x0d091f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 9], 13 + LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] + QUAD $0x0e0917742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 9], 14 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0f090f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 9], 15 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0109077c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rax + 9], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 3 + QUAD $0x0409377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0509077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 5 + QUAD $0x0609077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 7 + QUAD $0x0809177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 8 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x09090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 9 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0a090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 10 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0b090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 11 + QUAD $0x0c09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 12 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0d090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 13 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0e090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0f09326c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdx + r14 + 9], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x0f74b60f; BYTE $0x0c // movzx esi, byte [rdi + rcx + 12] LONG $0xc66ef9c5 // vmovd xmm0, esi LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x00048024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm5 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + LONG $0x0f74b60f; BYTE $0x0c // movzx esi, byte [rdi + rcx + 12] LONG $0xee6ef9c5 // vmovd xmm5, esi - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x010a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 1 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x020a2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 10], 2 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x030a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 3 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x040a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 4 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x050a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 5 - QUAD $0x060a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x070a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 7 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x080a125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 10], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x090a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a0a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 10 - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - QUAD $0x0b0a1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 10], 11 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x0c0a1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 10], 12 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x0d0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 14 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 15 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x010a32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 10], 1 - QUAD $0x020a0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 10], 2 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x030a32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 10], 3 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x040a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 4 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x050a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 5 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x060a0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 10], 6 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x070a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 7 - QUAD $0x080a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 8 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x090a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 9 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0a0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 10 - QUAD $0x0b0a22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 10], 11 - LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x0c0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 13 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - QUAD $0x0e0a22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 10], 14 - QUAD $0x0f0a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 15 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - QUAD $0x010b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 1 - QUAD $0x020b2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 11], 2 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x030b2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 11], 3 - QUAD $0x040b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 4 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x050b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 5 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x060b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 6 - QUAD $0x070b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 7 - QUAD $0x080b124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 11], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x090b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 10 - QUAD $0x0b0b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 11 - QUAD $0x0c0b1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 11], 12 - QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - QUAD $0x0d0b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e0b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 14 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x0f0b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 15 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x010b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 1 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x020b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 2 - QUAD $0x030b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 3 - WORD $0x8949; BYTE $0xf6 // mov r14, rsi - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x040b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 4 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x050b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 5 - QUAD $0x060b0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 11], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x070b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 7 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x080b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 8 - QUAD $0x090b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 9 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - QUAD $0x0a0b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 10 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0b0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 11 LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0c0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 12 - QUAD $0x0d0b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 13 + QUAD $0x010a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 1 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x020a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 2 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x030a0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 10], 3 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x040a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 4 + QUAD $0x050a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 5 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x060a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 6 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + QUAD $0x070a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x080a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 8 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x090a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 9 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0a0a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 10 + QUAD $0x0b0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 11 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0c0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 12 + QUAD $0x0d0a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 13 + QUAD $0x0e0a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 14 + QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] + QUAD $0x0f0a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 15 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x010a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x020a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x030a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 3 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x040a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 4 + QUAD $0x050a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 5 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x060a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x070a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 8 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x090a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 9 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0a0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 12 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0d0a17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 10], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0f0a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x010b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 1 + QUAD $0x020b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 2 + QUAD $0x030b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x040b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x060b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 6 + QUAD $0x070b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 7 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x080b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 8 + QUAD $0x090b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 9 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0a0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 10 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x0b0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 11 + QUAD $0x0c0b0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 11], 12 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0d0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 13 + LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] + QUAD $0x0e0b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 14 + QUAD $0x0f0b3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 11], 15 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x010b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x020b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 2 + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x040b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x050b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 5 + QUAD $0x060b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + QUAD $0x0a0b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 10 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x0b0b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 11 + QUAD $0x0c0b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 12 + QUAD $0x0d0b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000460249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm3 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 14 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - LONG $0x0a74b60f; BYTE $0x0d // movzx esi, byte [rdx + rcx + 13] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0f0b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 11], 15 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000440248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a74b60f; BYTE $0x0d // movzx esi, byte [rdx + rcx + 13] + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x010c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x020c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 2 - QUAD $0x030c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 12], 3 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x040c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 12], 4 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x050c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 5 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x060c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 6 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x070c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 12], 7 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x080c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 12], 8 - QUAD $0x090c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 12], 9 - QUAD $0x0a0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 11 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0c0c3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 12], 12 - QUAD $0x0d0c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 12], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 14 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 15 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x010c02542051a3c4 // vpinsrb xmm2, xmm5, byte [rdx + r8 + 12], 1 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x020c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 2 - QUAD $0x030c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 12], 3 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x040c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 12], 4 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x050c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 5 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x060c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 6 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x070c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 7 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x010c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 1 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x020c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 2 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x030c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 3 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x040c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 4 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x050c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 5 + QUAD $0x060c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 6 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x070c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 7 + QUAD $0x080c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 12], 8 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x090c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 9 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0a0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 10 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x0b0c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0c0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 12 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x0d0c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 12], 13 + QUAD $0x0e0c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 14 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0f0c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 15 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x010c37542051a3c4 // vpinsrb xmm2, xmm5, byte [rdi + r14 + 12], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x020c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x030c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 3 + QUAD $0x040c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 4 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x050c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 5 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x060c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x070c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 8 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x090c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 9 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0a0c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 10 + QUAD $0x0b0c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 11 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0c0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 12 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x0d0c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 13 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0e0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 14 LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x080c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x090c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 9 - QUAD $0x0a0c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 10 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0b0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 11 - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] - QUAD $0x0c0c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 13 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - QUAD $0x0e0c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 14 - QUAD $0x0f0c22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 12], 15 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x010d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 1 - QUAD $0x020d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 2 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x030d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 3 - QUAD $0x040d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 4 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x050d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 5 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x060d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 6 - QUAD $0x070d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 13], 7 - QUAD $0x080d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 13], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x090d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 9 - QUAD $0x0a0d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 11 - QUAD $0x0c0d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 13], 12 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0d0d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 13], 14 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x0f0d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 13], 15 - QUAD $0x010d024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 13], 1 - QUAD $0x020d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 2 - WORD $0x8949; BYTE $0xf0 // mov r8, rsi - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x030d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 3 - QUAD $0x040d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 4 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x050d1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 13], 5 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x060d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 6 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x070d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 7 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x080d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 8 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x090d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 9 - QUAD $0x0a0d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 10 - QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] - QUAD $0x0b0d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 11 - LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] - QUAD $0x0c0d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 12 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d0d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 13 - QUAD $0x0e0d2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 13], 14 + QUAD $0x0f0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 15 + QUAD $0x010d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 1 + QUAD $0x020d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 2 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x030d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 3 + QUAD $0x040d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 4 + QUAD $0x050d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 13], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x060d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 6 + QUAD $0x070d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 7 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x080d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 8 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x090d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 9 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0a0d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 13], 10 + QUAD $0x0b0d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x0d0d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 13], 13 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x0e0d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 14 + QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] + QUAD $0x0f0d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 15 + QUAD $0x010d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 1 + QUAD $0x020d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x030d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 3 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x040d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 4 + QUAD $0x050d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 5 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x060d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 6 + QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] + QUAD $0x070d3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 13], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x080d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 8 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x090d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 9 + QUAD $0x0a0d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 10 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x0b0d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 11 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0c0d1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 13], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d0d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e0d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x00042024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm0 - QUAD $0x0f0d22442071a3c4 // vpinsrb xmm0, xmm1, byte [rdx + r12 + 13], 15 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - LONG $0x3274b60f; BYTE $0x0e // movzx esi, byte [rdx + rsi + 14] + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f0d17442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rdx + 13], 15 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + LONG $0x1774b60f; BYTE $0x0e // movzx esi, byte [rdi + rdx + 14] LONG $0xce6ef9c5 // vmovd xmm1, esi LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x0e // movzx esi, byte [rdx + rsi + 14] + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + LONG $0x1774b60f; BYTE $0x0e // movzx esi, byte [rdi + rdx + 14] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x010e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 1 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x020e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 2 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x030e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 3 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x010e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 1 + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x020e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 2 + QUAD $0x030e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 3 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x040e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 4 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x050e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 5 + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x070e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x080e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x090e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 9 + QUAD $0x0a0e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 10 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0b0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 11 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0c0e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 12 QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x040e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 4 - QUAD $0x050e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 14], 5 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x060e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 6 - QUAD $0x070e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 7 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x080e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 8 - QUAD $0x090e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a0e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 10 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0b0e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 14], 11 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0c0e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 12 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x0d0e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 13 - QUAD $0x0e0e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 14 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x0f0e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 14], 15 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x010e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 1 - QUAD $0x020e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 14], 2 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x030e02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 14], 3 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x040e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 4 - QUAD $0x050e1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 14], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x060e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 14], 6 - QUAD $0x070e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 7 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x080e1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 14], 8 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x090e2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 14], 9 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0a0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 10 - QUAD $0x0b0e3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 14], 11 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - QUAD $0x0c0e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 14], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d0e1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 14], 13 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0e0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 14 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0f0e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 14], 15 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - LONG $0x3274b60f; BYTE $0x0f // movzx esi, byte [rdx + rsi + 15] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x010f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 1 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x020f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 2 + QUAD $0x0d0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 13 + QUAD $0x0e0e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 14], 14 + QUAD $0x0f0e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 15 + QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] + QUAD $0x010e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 14], 1 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x030f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x040f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 4 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x050f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 5 + QUAD $0x020e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x030e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 3 + QUAD $0x040e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 4 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x050e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 5 + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x060e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 6 + QUAD $0x070e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 14], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x080e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 8 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x090e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 14], 9 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x0a0e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 14], 10 + QUAD $0x0b0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 11 + QUAD $0x0c0e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 13 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0e0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f0e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 15 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + LONG $0x1f74b60f; BYTE $0x0f // movzx esi, byte [rdi + rbx + 15] + LONG $0xd66ef9c5 // vmovd xmm2, esi + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x010f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 1 + QUAD $0x020f37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 15], 2 LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x060f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 6 - QUAD $0x070f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 15], 7 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x080f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 8 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x090f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 9 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 10 - QUAD $0x0b0f22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 15], 11 + QUAD $0x030f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 3 QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0c0f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 15], 12 - QUAD $0x0d0f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e0f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 14 - QUAD $0x0f0f0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 15], 15 + QUAD $0x040f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 4 + QUAD $0x050f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 15], 5 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x060f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 6 QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x0f // movzx esi, byte [rdx + rsi + 15] - LONG $0xde6ef9c5 // vmovd xmm3, esi - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x010f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 1 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x020f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 2 - QUAD $0x030f025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 15], 3 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x040f125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 15], 4 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x050f025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 15], 5 - QUAD $0x060f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x070f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 7 - QUAD $0x080f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 8 - QUAD $0x090f2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 15], 9 + QUAD $0x070f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 7 + QUAD $0x080f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 8 + QUAD $0x090f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 9 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0a0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 10 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0b0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 11 + QUAD $0x0c0f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 12 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0d0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 14 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 10 - QUAD $0x0b0f3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 15], 11 - QUAD $0x0c0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 12 - QUAD $0x0d0f1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 15], 13 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - QUAD $0x0e0f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 14 - QUAD $0x0f0f325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 15], 15 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 + QUAD $0x0f0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 15 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + LONG $0x74b60f42; WORD $0x0f07 // movzx esi, byte [rdi + r8 + 15] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x010f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 1 + LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] + QUAD $0x020f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 2 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x030f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x050f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 5 + QUAD $0x060f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x070f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 7 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x080f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 8 + QUAD $0x090f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 9 + QUAD $0x0a0f3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 15], 10 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0b0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c0f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 12 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0d0f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 13 + QUAD $0x0e0f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - LONG $0x74b60f42; WORD $0x103a // movzx esi, byte [rdx + r15 + 16] + LONG $0x1f74b60f; BYTE $0x10 // movzx esi, byte [rdi + rbx + 16] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x011002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 1 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x021032442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 16], 2 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x03103a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 16], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x041002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 4 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x051002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 5 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x061002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x071002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 7 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x081002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 11 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0c1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 12 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x0d101a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 16], 13 - QUAD $0x0e100a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 16], 14 - QUAD $0x0f100a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 16], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x10 // movzx esi, byte [rdx + rax + 16] - LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x01100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 1 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x02100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 2 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x03100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 3 - QUAD $0x0410124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 16], 4 - QUAD $0x0510024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 16], 5 + LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] + QUAD $0x01101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 1 + QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] + QUAD $0x02101f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 16], 2 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x03100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 3 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x04100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 5 + QUAD $0x061027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 6 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x07100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 7 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x08102f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 16], 8 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x09100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 9 LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x06100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x07100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 7 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x08100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 8 - QUAD $0x09102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 9 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x0a100a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 16], 10 + QUAD $0x0a100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 10 QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0b100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 11 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0c100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 13 - QUAD $0x0e101a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 16], 14 - WORD $0x894d; BYTE $0xe5 // mov r13, r12 - QUAD $0x0f10224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 16], 15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 - LONG $0x74b60f42; WORD $0x113a // movzx esi, byte [rdx + r15 + 17] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x01113a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 17], 1 - QUAD $0x021132542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 17], 2 - QUAD $0x03113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 4 + QUAD $0x0b100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 12 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0d100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 13 LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x051132542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 17], 5 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x061112542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 17], 6 + QUAD $0x0e1037442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 16], 14 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0f1037442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 16], 15 + LONG $0x74b60f42; WORD $0x1007 // movzx esi, byte [rdi + r8 + 16] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x01103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 1 + QUAD $0x02100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 2 + QUAD $0x0310374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 3 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0410374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 4 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0510374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 5 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0610374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 6 + QUAD $0x0710074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0810074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 8 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0910374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 9 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0a10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 10 QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x071132542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 17], 7 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x081102542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 17], 8 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x09111a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 17], 9 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x0a1132542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 17], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b1132542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 17], 11 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0c1132542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 17], 12 - QUAD $0x0d111a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 17], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0e111a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 17], 14 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f1132542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 17], 15 - LONG $0x0274b60f; BYTE $0x11 // movzx esi, byte [rdx + rax + 17] + QUAD $0x0b10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 11 + QUAD $0x0c10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 12 + QUAD $0x0d10174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 16], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 15 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + LONG $0x1774b60f; BYTE $0x11 // movzx esi, byte [rdi + rdx + 17] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x01111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 1 + QUAD $0x02111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 2 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x031117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 3 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x041117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 4 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x051117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 5 + QUAD $0x061127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 6 + QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] + QUAD $0x071107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 7 + QUAD $0x08112f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 17], 8 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x09111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 9 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0a1117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 10 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x0b1127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c1137542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 17], 12 + QUAD $0x0d110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 13 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0e110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 14 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0f111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 15 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + LONG $0x0f74b60f; BYTE $0x11 // movzx esi, byte [rdi + rcx + 17] LONG $0xde6ef9c5 // vmovd xmm3, esi - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0111225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 17], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0211025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 2 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0311025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 3 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0411025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 4 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0511025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0611025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0711025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 7 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0811025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 8 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0911325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 9 - QUAD $0x0a110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 10 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0b11325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 11 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0c11325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 12 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d11325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 13 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0e11325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 14 + QUAD $0x01113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 1 + QUAD $0x02110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 2 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x03110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 3 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x04113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 4 + QUAD $0x0511375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 5 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x06110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 7 + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - QUAD $0x0f112a442061a3c4 // vpinsrb xmm0, xmm3, byte [rdx + r13 + 17], 15 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0f1137442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r14 + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 - LONG $0x0a74b60f; BYTE $0x12 // movzx esi, byte [rdx + rcx + 18] + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + LONG $0x74b60f42; WORD $0x122f // movzx esi, byte [rdi + r13 + 18] LONG $0xc66ef9c5 // vmovd xmm0, esi - QUAD $0x01123a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 18], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x02120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 2 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x03122a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 18], 3 - QUAD $0x04123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 4 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x05120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 5 - QUAD $0x061212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 6 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x071232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 7 - QUAD $0x081202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 18], 8 - QUAD $0x09121a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 18], 9 - QUAD $0x0a1232442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 18], 10 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0b1202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 18], 11 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x0c120a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 18], 12 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x0d1212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 13 - QUAD $0x0e121a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 18], 14 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f1232442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 18], 15 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x12 // movzx esi, byte [rdx + rsi + 18] - LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0112224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 18], 1 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x02121a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 18], 2 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0312224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 18], 3 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x04123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 4 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0512324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 5 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x06123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0712324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 7 - QUAD $0x0812024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0912024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 9 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a12024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 10 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0b12324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 18], 11 LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0c12024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d12024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e12024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f12024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x0274b60f; BYTE $0x13 // movzx esi, byte [rdx + rax + 19] - LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 2 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x031207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 3 + QUAD $0x041217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 4 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x051217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + QUAD $0x071207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 18], 7 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x011302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 1 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x021332542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 19], 2 - QUAD $0x03132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x041332542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 19], 4 - QUAD $0x05130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 5 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x06130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 6 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x07132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 7 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x08130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x09130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 10 - QUAD $0x0b1302542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 19], 11 - QUAD $0x0c130a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 19], 12 - QUAD $0x0d1312542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 19], 13 - QUAD $0x0e131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 14 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x0f131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 15 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a74b60f; BYTE $0x13 // movzx esi, byte [rdx + rcx + 19] - LONG $0xde6ef9c5 // vmovd xmm3, esi - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0113125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 19], 1 - QUAD $0x02131a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 19], 2 - WORD $0x894d; BYTE $0xe0 // mov r8, r12 - QUAD $0x0313225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 19], 3 - QUAD $0x04133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 4 - WORD $0x8949; BYTE $0xfb // mov r11, rdi - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0513225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 19], 5 - QUAD $0x06133a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 19], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x07130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 7 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x08133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 8 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x09130a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 19], 9 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0a13325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 10 - QUAD $0x0b13325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 19], 11 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0c13325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 12 + QUAD $0x081207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 8 + QUAD $0x09121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 9 + QUAD $0x0a1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 10 + QUAD $0x0b1227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 11 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0c120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 12 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0d1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 14 + QUAD $0x0f121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 15 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + LONG $0x1f74b60f; BYTE $0x12 // movzx esi, byte [rdi + rbx + 18] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0112074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0212074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 2 + QUAD $0x03120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 3 + QUAD $0x04123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0512074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 5 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0612174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d13325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 13 + QUAD $0x0712374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 7 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0812274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 8 QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0e13325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 14 + QUAD $0x0912374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 9 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0a12374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 10 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x0b121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0c12374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 12 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d12374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 13 LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0f13325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 15 + QUAD $0x0e12374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 14 + QUAD $0x0f12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 15 + LONG $0x74b60f42; WORD $0x132f // movzx esi, byte [rdi + r13 + 19] + LONG $0xd66ef9c5 // vmovd xmm2, esi + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x011337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 1 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x021337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 2 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x031307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 3 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x04130f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 19], 4 + QUAD $0x051317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 5 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x061337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 6 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x071337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 7 + LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] + QUAD $0x081317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 8 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x09133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 9 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0a1337542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 19], 10 + QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] + QUAD $0x0b1337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 11 + QUAD $0x0c130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 12 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0d130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 13 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0e130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 14 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0f130f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 19], 15 + LONG $0x1f74b60f; BYTE $0x13 // movzx esi, byte [rdi + rbx + 19] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x01130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 3 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x04130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 4 + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x0613175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 19], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x0813275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0913075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 9 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x0a131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 10 + QUAD $0x0b131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0d13175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 19], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - LONG $0x74b60f42; WORD $0x143a // movzx esi, byte [rdx + r15 + 20] + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x0f74b60f; BYTE $0x14 // movzx esi, byte [rdi + rcx + 20] LONG $0xc66ef9c5 // vmovd xmm0, esi - QUAD $0x011402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 1 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x021402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 2 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x031402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x041402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 4 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x051402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 5 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x061402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 6 - QUAD $0x07142a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 20], 7 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x081402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 11 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0c1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 12 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0d1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 20], 14 - QUAD $0x0f141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 15 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - LONG $0x1a74b60f; BYTE $0x14 // movzx esi, byte [rdx + rbx + 20] + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] + QUAD $0x01140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 1 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x02140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 2 + QUAD $0x031407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 3 + QUAD $0x04140f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 20], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 5 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x06140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 6 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x07140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 7 + QUAD $0x081417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 8 + QUAD $0x09143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 9 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0a1437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 20], 10 + QUAD $0x0b1437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c1437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 20], 12 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x0d1427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 13 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x0e1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 14 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0f1437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 20], 15 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + LONG $0x74b60f42; WORD $0x140f // movzx esi, byte [rdi + r9 + 20] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0114124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 1 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x0214324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 20], 2 - QUAD $0x0314024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 20], 3 - QUAD $0x04141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 4 - QUAD $0x0514224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 20], 5 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0614124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 6 - QUAD $0x07140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 7 - QUAD $0x08143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 8 - QUAD $0x09140a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 20], 9 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0a140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 10 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x0b14224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 20], 11 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0c143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d14024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 20], 13 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - QUAD $0x0e141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 14 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0f140a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 20], 15 - LONG $0x74b60f42; WORD $0x153a // movzx esi, byte [rdx + r15 + 21] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x011532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 1 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x021502542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 21], 2 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x03152a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 21], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x041532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 4 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x051532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 5 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x06153a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 21], 6 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x071532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 7 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x081532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 8 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x091532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0114374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 1 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x0214374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 20], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0314374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 3 QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 11 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0c1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 12 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x0d1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 13 + QUAD $0x0414374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 4 + QUAD $0x05142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 5 + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x0614174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0714374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 7 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x08143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 8 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0914374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 9 + QUAD $0x0a141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 10 + QUAD $0x0b141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 11 LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 14 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 15 - LONG $0x1a74b60f; BYTE $0x15 // movzx esi, byte [rdx + rbx + 21] + QUAD $0x0c14374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 12 + QUAD $0x0d14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 13 + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x0f141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 15 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0774b60f; BYTE $0x15 // movzx esi, byte [rdi + rax + 21] + LONG $0xd66ef9c5 // vmovd xmm2, esi + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x011507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 2 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x031507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 5 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x061507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 6 + QUAD $0x07150f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 21], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x081507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 9 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0a1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 10 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0b1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 12 + QUAD $0x0d1527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 13 + QUAD $0x0e1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 14 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + QUAD $0x0f1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 15 + LONG $0x74b60f42; WORD $0x150f // movzx esi, byte [rdi + r9 + 21] LONG $0xde6ef9c5 // vmovd xmm3, esi - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0115325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 1 - QUAD $0x0215325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 21], 2 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0315325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 3 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0415325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 4 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0515325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 5 - QUAD $0x0615125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 6 - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - QUAD $0x0715125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 7 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0815325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 8 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0915325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 9 - QUAD $0x0a150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 10 - QUAD $0x0b15225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 21], 11 - QUAD $0x0c153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 12 - QUAD $0x0d15025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 13 - QUAD $0x0e151a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 21], 14 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x01152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 1 + QUAD $0x0215375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0415075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0515075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 5 + QUAD $0x0615175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 6 + QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] + QUAD $0x0715275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 21], 7 + QUAD $0x08153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 8 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x09150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 9 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0a15175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 10 + QUAD $0x0b151f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 21], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 12 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0d153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 13 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0e15375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x0f150a442061a3c4 // vpinsrb xmm0, xmm3, byte [rdx + r9 + 21], 15 + QUAD $0x0f151f442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rbx + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x0274b60f; BYTE $0x16 // movzx esi, byte [rdx + rax + 22] + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + LONG $0x3774b60f; BYTE $0x16 // movzx esi, byte [rdi + rsi + 22] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x011602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 22], 1 - QUAD $0x021602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 22], 2 - QUAD $0x03162a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 22], 3 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x04160a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 22], 4 - LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] - QUAD $0x051622442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 22], 5 - QUAD $0x06163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 6 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x07161a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 22], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x08163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 22], 9 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x0a1602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 22], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 11 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0c160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 12 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x0d160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e160a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 22], 14 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x0f161a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 22], 15 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a74b60f; BYTE $0x16 // movzx esi, byte [rdx + rcx + 22] - LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x01160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 1 - QUAD $0x0216324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 22], 2 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x03160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 3 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x04160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 4 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x05160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 5 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x06160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 6 - QUAD $0x0716124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 22], 7 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x08160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 9 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0a160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 10 - QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] - QUAD $0x0b163a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 22], 11 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0c160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 12 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 13 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0e16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 14 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0f162a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 22], 15 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - LONG $0x3274b60f; BYTE $0x17 // movzx esi, byte [rdx + rsi + 23] - LONG $0xd66ef9c5 // vmovd xmm2, esi + LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] + QUAD $0x01161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 1 + QUAD $0x021617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 2 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x031617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 3 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x04160f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 22], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x05161f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 22], 5 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x061617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 6 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x071637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 7 LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x011732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 1 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x021732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 2 + QUAD $0x081637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 8 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x091637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 9 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0a1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 10 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0b1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 12 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0d1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0e1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 14 + QUAD $0x0f1607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 15 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + LONG $0x3774b60f; BYTE $0x16 // movzx esi, byte [rdi + rsi + 22] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x01162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 1 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x031732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 3 - QUAD $0x04170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 4 - QUAD $0x051722542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 23], 5 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x06170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 6 - QUAD $0x07171a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 23], 7 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x08173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 8 - QUAD $0x091702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 9 - QUAD $0x0a1702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 23], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 11 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0c1702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 12 + QUAD $0x0216374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 2 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0316374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 3 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x04162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 4 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0516374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 5 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0616374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 6 + QUAD $0x0716274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 7 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0816274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 8 + QUAD $0x09160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 9 + QUAD $0x0a16174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 22], 10 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0b160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 11 + QUAD $0x0c16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 12 + QUAD $0x0d163f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 22], 13 + QUAD $0x0e16374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 22], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 15 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0774b60f; BYTE $0x17 // movzx esi, byte [rdi + rax + 23] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x01171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 1 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0d1702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0e171a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 23], 14 - QUAD $0x0f171a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 23], 15 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - LONG $0x74b60f42; WORD $0x1702 // movzx esi, byte [rdx + r8 + 23] + QUAD $0x021707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 2 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x03171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 3 + QUAD $0x04170f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 23], 4 + QUAD $0x05171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 5 + QUAD $0x061717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 6 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x07173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x081707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 9 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0a1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 10 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x0b1707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 23], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0c1717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 12 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0d1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 15 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + LONG $0x0774b60f; BYTE $0x17 // movzx esi, byte [rdi + rax + 23] LONG $0xde6ef9c5 // vmovd xmm3, esi - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0117025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 23], 1 - QUAD $0x0217325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 23], 2 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x0317325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 23], 3 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x04171a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 23], 4 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x05173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 5 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0617325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 6 - QUAD $0x0717125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 23], 7 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0817325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 8 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0917325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 9 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0a17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 10 - QUAD $0x0b173a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 23], 11 - QUAD $0x0c170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0117075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x03170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 3 + QUAD $0x04172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 4 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x05170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 5 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x06170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 6 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0717375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 7 + QUAD $0x0817275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 8 QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 14 - QUAD $0x0f172a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 23], 15 + QUAD $0x09170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 9 + QUAD $0x0a17175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 23], 10 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x0b170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0c17375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 12 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0d171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 13 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x0e17175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 23], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f17375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - LONG $0x0a74b60f; BYTE $0x18 // movzx esi, byte [rdx + rcx + 24] + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + LONG $0x3774b60f; BYTE $0x18 // movzx esi, byte [rdi + rsi + 24] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x01182a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 24], 1 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x021832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 2 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x031832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x041832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 4 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x051832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 5 - QUAD $0x06180a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 24], 6 - QUAD $0x071822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 24], 7 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x081832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 8 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x091822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 24], 9 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 11 + LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + QUAD $0x01182f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 24], 1 + QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] + QUAD $0x021827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 2 + QUAD $0x03181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 3 QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0c1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 12 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x0d1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 13 - QUAD $0x0e181a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 24], 14 + QUAD $0x041837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 4 QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f1832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 15 - LONG $0x74b60f42; WORD $0x1802 // movzx esi, byte [rdx + r8 + 24] + QUAD $0x051837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 5 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + QUAD $0x06181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 6 + QUAD $0x07183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x081837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 8 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x091837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 9 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0a1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 10 + QUAD $0x0b1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 11 + QUAD $0x0c1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 12 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + QUAD $0x0d1807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 13 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0e1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 14 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0f1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 15 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + LONG $0x3774b60f; BYTE $0x18 // movzx esi, byte [rdi + rsi + 24] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0118024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 1 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x02180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 2 - QUAD $0x0318324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 24], 3 - QUAD $0x04181a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 24], 4 - QUAD $0x05183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0618024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 6 - QUAD $0x0718124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 7 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0818024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 8 - LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] - QUAD $0x0918124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 9 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - QUAD $0x0a183a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 24], 10 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0b18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 11 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0c18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 12 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 13 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - QUAD $0x0e18024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 14 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0f18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 15 - LONG $0x0a74b60f; BYTE $0x19 // movzx esi, byte [rdx + rcx + 25] + QUAD $0x0118074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0318074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 3 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x04183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 4 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0518374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 5 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0618374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 6 + QUAD $0x0718374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0818374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 8 + QUAD $0x09180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 9 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0a180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 10 + QUAD $0x0b180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0c180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 12 + QUAD $0x0d181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 13 + QUAD $0x0e18174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 15 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x0f74b60f; BYTE $0x19 // movzx esi, byte [rdi + rcx + 25] LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x01192a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 25], 1 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x02192a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 25], 2 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x03191a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 25], 3 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x04191a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 25], 4 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x05190a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 25], 5 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x06190a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 25], 6 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x071932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 7 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x081932542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 25], 8 - QUAD $0x091922542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 25], 9 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 10 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0b1922542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 25], 11 + QUAD $0x01192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 1 + QUAD $0x021927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 2 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x031937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 3 QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0c1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 12 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x0d193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 14 + QUAD $0x041937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 4 QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0f1932542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 25], 15 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x19 // movzx esi, byte [rdx + rsi + 25] + QUAD $0x051937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 5 + QUAD $0x06191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 6 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x071937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 7 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x08191f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 25], 8 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x091937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 9 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x0a191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 10 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0b1937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 11 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0c190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 12 + QUAD $0x0d1907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 13 + QUAD $0x0e1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 14 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0f1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 15 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + LONG $0x74b60f42; WORD $0x1927 // movzx esi, byte [rdi + r12 + 25] LONG $0xde6ef9c5 // vmovd xmm3, esi - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0119325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 1 - QUAD $0x02190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 2 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0319325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 3 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0419325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 4 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0519325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 5 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0619325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0719325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 7 - QUAD $0x0819025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 8 - QUAD $0x0919125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 25], 9 - QUAD $0x0a193a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 25], 10 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0b190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 11 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0c19025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d19025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 13 - QUAD $0x0e19025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 14 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0119175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 25], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0219175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 2 + QUAD $0x0319075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 3 + QUAD $0x04193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0519075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 5 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 + QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] + QUAD $0x0719075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 25], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0819075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0919075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 9 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x0a192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 12 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0d19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0e19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 14 LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1902442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rax + 25], 15 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f1907442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 25], 15 LONG $0x387d63c4; WORD $0x01c2 // vinserti128 ymm8, ymm0, xmm2, 1 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - LONG $0x74b60f42; WORD $0x1a3a // movzx esi, byte [rdx + r15 + 26] + LONG $0x0f74b60f; BYTE $0x1a // movzx esi, byte [rdi + rcx + 26] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x011a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 1 - QUAD $0x021a2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 26], 2 - QUAD $0x031a1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 26], 3 - QUAD $0x041a1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 26], 4 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x051a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 5 - QUAD $0x061a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 6 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x071a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 7 - QUAD $0x081a32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 26], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 10 - QUAD $0x0b1a22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 26], 11 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0c1a1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 26], 12 - QUAD $0x0d1a3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 26], 13 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x0e1a22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 26], 14 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x0f1a02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 26], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x1a // movzx esi, byte [rdx + rax + 26] - LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x011a1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 26], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x021a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 2 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x031a0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 26], 3 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x041a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 4 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x051a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 5 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x061a124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 26], 6 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x071a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 7 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x081a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 8 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x091a324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 26], 9 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x011a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 2 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x031a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 3 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x041a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x051a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 5 + QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] + QUAD $0x061a3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 26], 6 + QUAD $0x071a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 7 + QUAD $0x081a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 8 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x091a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 9 + QUAD $0x0a1a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 10 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x0b1a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 11 + QUAD $0x0c1a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 12 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x0d1a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0e1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 14 QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0a1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 10 - QUAD $0x0b1a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 11 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0c1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 12 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - QUAD $0x0d1a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 13 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0e1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 14 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0f1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 15 - LONG $0x74b60f42; WORD $0x1b3a // movzx esi, byte [rdx + r15 + 27] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x011b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 27], 1 - QUAD $0x021b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 27], 2 + QUAD $0x0f1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 15 + LONG $0x74b60f42; WORD $0x1a27 // movzx esi, byte [rdi + r12 + 26] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x011a174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 26], 1 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x031b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 3 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x041b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 4 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x051b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 5 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x061b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 6 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x071b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 7 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x081b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 8 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x091b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 9 + QUAD $0x021a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 2 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x031a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 3 QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a1b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b1b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 11 - QUAD $0x0c1b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 27], 12 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x0d1b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 27], 13 - QUAD $0x0e1b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 27], 14 - QUAD $0x0f1b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 27], 15 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - LONG $0x74b60f42; WORD $0x1b22 // movzx esi, byte [rdx + r12 + 27] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x011b1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 27], 1 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x021b1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 27], 2 - QUAD $0x031b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 3 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x041b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 4 - QUAD $0x051b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 5 - QUAD $0x061b125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 27], 6 - QUAD $0x071b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 7 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x081b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 8 - QUAD $0x091b325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 27], 9 + QUAD $0x041a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 4 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x051a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 5 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x061a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 6 + QUAD $0x071a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 7 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x081a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 8 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x091a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 9 + QUAD $0x0a1a2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 26], 10 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0b1a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0c1a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 12 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0d1a174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 26], 13 + QUAD $0x0e1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0f1a2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 26], 15 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + LONG $0x74b60f42; WORD $0x1b1f // movzx esi, byte [rdi + r11 + 27] + LONG $0xd66ef9c5 // vmovd xmm2, esi + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x011b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 1 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x021b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 27], 2 + QUAD $0x031b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 3 + QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] + QUAD $0x041b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 27], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 5 + QUAD $0x061b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 6 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x071b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x081b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 9 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0a1b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 10 + QUAD $0x0b1b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 12 + QUAD $0x0d1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 14 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0a1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 10 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0b1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 11 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0c1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 12 - QUAD $0x0d1b0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 27], 13 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x0e1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 14 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 15 + QUAD $0x0f1b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 15 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + LONG $0x0774b60f; BYTE $0x1b // movzx esi, byte [rdi + rax + 27] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x011b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x021b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 2 + QUAD $0x031b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 3 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x041b375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 27], 4 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x051b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 5 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x061b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x071b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 7 + QUAD $0x081b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 8 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x091b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 9 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0a1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 10 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0b1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0c1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 12 + QUAD $0x0d1b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 13 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0e1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 14 + QUAD $0x0f1b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - LONG $0x0a74b60f; BYTE $0x1c // movzx esi, byte [rdx + rcx + 28] + LONG $0x74b60f42; WORD $0x1c1f // movzx esi, byte [rdi + r11 + 28] LONG $0xc66ef9c5 // vmovd xmm0, esi - QUAD $0x011c3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 28], 1 - QUAD $0x021c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 2 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x031c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x041c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 4 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x051c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 5 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x061c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 6 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x071c32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 28], 7 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x081c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x091c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 9 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x0a1c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 28], 10 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0b1c3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 28], 11 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0c1c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 12 - QUAD $0x0d1c1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 28], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e1c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 28], 14 - QUAD $0x0f1c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 15 - LONG $0x74b60f42; WORD $0x1c22 // movzx esi, byte [rdx + r12 + 28] - LONG $0xce6ef9c5 // vmovd xmm1, esi - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x011c224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 28], 1 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - QUAD $0x021c1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 28], 2 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x031c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 3 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x041c0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 28], 4 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x051c1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 28], 5 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x061c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x071c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 7 - QUAD $0x081c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x091c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 9 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0a1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 10 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0b1c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 11 LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0c1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 12 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 13 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0e1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 14 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0f1c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 15 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x0274b60f; BYTE $0x1d // movzx esi, byte [rdx + rax + 29] - LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x011c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 1 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x021c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 2 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x031c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 3 + QUAD $0x041c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 4 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x051c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 5 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x061c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 6 + QUAD $0x071c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 7 LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x011d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 1 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x021d02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 29], 2 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x031d02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 29], 3 + QUAD $0x081c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 8 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x091c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 9 + QUAD $0x0a1c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 10 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0b1c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c1c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 12 QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x041d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 4 - QUAD $0x051d2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 29], 5 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x061d02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 29], 6 - QUAD $0x071d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 7 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x081d02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 29], 8 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x091d32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 29], 9 - QUAD $0x0a1d12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 29], 10 - QUAD $0x0b1d3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 29], 11 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x0c1d32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 29], 12 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x0d1d12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 29], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1d02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 29], 14 - QUAD $0x0f1d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 15 + QUAD $0x0d1c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0e1c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 14 + QUAD $0x0f1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 15 + LONG $0x0774b60f; BYTE $0x1c // movzx esi, byte [rdi + rax + 28] + LONG $0xce6ef9c5 // vmovd xmm1, esi + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x011c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 1 + QUAD $0x021c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x031c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 3 + QUAD $0x041c374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 28], 4 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x051c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 5 + QUAD $0x061c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x071c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 7 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x081c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x091c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 9 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x0a1c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 10 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0b1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 11 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x0c1c374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 28], 12 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0d1c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x0e1c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 15 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0774b60f; BYTE $0x1d // movzx esi, byte [rdi + rax + 29] + LONG $0xd66ef9c5 // vmovd xmm2, esi + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x011d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 1 + QUAD $0x021d17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 29], 2 + QUAD $0x031d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 3 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x041d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 4 + QUAD $0x051d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 5 + QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] + QUAD $0x061d17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 29], 6 QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - LONG $0x74b60f42; WORD $0x1d2a // movzx esi, byte [rdx + r13 + 29] + QUAD $0x071d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x081d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 8 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x091d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 9 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0a1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 10 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x0b1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 11 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0c1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 12 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0d1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0e1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 14 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0f1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 15 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + LONG $0x3774b60f; BYTE $0x1d // movzx esi, byte [rdi + rsi + 29] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x011d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 29], 1 - QUAD $0x021d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 2 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x031d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 29], 3 - QUAD $0x041d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 29], 4 - QUAD $0x051d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 5 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x061d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 29], 6 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x071d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 7 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x081d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 8 - QUAD $0x091d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 9 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a1d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 10 - QUAD $0x0b1d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 29], 11 - LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x0c1d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 29], 12 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x011d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x021d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 2 + QUAD $0x031d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 3 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x041d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 4 + QUAD $0x051d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 5 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x061d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 6 QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d1d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e1d02642061e3c4 // vpinsrb xmm4, xmm3, byte [rdx + rax + 29], 14 + QUAD $0x071d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 29], 7 + QUAD $0x081d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 8 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x091d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 9 + QUAD $0x0a1d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 10 + QUAD $0x0b1d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 11 + QUAD $0x0c1d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 29], 12 + QUAD $0x0d1d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 29], 13 + QUAD $0x0e1d27642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r12 + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1d02442059e3c4 // vpinsrb xmm0, xmm4, byte [rdx + rax + 29], 15 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f1d17442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rdx + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - LONG $0x74b60f42; WORD $0x1e3a // movzx esi, byte [rdx + r15 + 30] + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x0f74b60f; BYTE $0x1e // movzx esi, byte [rdi + rcx + 30] LONG $0xc66ef9c5 // vmovd xmm0, esi - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x011e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 1 - LONG $0x74b60f42; WORD $0x1f3a // movzx esi, byte [rdx + r15 + 31] + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x011e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 1 + LONG $0x0f74b60f; BYTE $0x1f // movzx esi, byte [rdi + rcx + 31] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x011f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 1 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x021e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 2 - QUAD $0x021f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 2 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x031e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 3 - QUAD $0x031f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x041e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 4 - QUAD $0x041f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 4 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x051e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 5 - QUAD $0x051f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 5 + QUAD $0x011f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 1 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x061e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 6 - QUAD $0x061f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 6 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x071e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 7 - QUAD $0x071f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 7 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x081e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 8 - QUAD $0x081f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 9 - QUAD $0x091f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 10 - QUAD $0x0a1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 11 - QUAD $0x0b1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 11 - QUAD $0x0c1e32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 30], 12 - QUAD $0x0c1f324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 31], 12 - QUAD $0x0d1e12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 30], 13 - QUAD $0x0d1f124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 31], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 14 - QUAD $0x0e1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 14 + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0f1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 15 - QUAD $0x0f1f02542071e3c4 // vpinsrb xmm2, xmm1, byte [rdx + rax + 31], 15 - LONG $0x44b60f42; WORD $0x1e2a // movzx eax, byte [rdx + r13 + 30] + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x061e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 30], 6 + QUAD $0x061f174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 31], 6 + QUAD $0x071e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 30], 7 + QUAD $0x071f2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 31], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + QUAD $0x0b1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 11 + QUAD $0x0b1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542071e3c4 // vpinsrb xmm2, xmm1, byte [rdi + rax + 31], 15 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x011e024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 30], 1 - LONG $0x44b60f42; WORD $0x1f2a // movzx eax, byte [rdx + r13 + 31] + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x011e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f027c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r8 + 31], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x021e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 2 - QUAD $0x021f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 2 - QUAD $0x031e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 30], 3 - QUAD $0x031f227c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r12 + 31], 3 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x041e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 4 - QUAD $0x041f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 4 + QUAD $0x011f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x051e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 5 - QUAD $0x051f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 5 - QUAD $0x061e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 30], 6 - QUAD $0x061f0a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r9 + 31], 6 - QUAD $0x071e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 30], 7 - QUAD $0x071f1a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 31], 7 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 9 - QUAD $0x091f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 9 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 10 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0b1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 11 - QUAD $0x0b1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 11 - QUAD $0x0c1e1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 30], 12 - QUAD $0x0c1f1a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 31], 12 - QUAD $0x0d1e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 30], 13 - QUAD $0x0d1f0a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 31], 13 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 15 - QUAD $0x0f1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 15 + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 4 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + QUAD $0x061e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 6 + QUAD $0x061f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 30], 9 + QUAD $0x091f0f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r9 + 31], 9 + QUAD $0x0a1e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 10 + QUAD $0x0a1f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + QUAD $0x0c1e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 30], 12 + QUAD $0x0c1f377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 31], 12 + QUAD $0x0d1e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 30], 13 + QUAD $0x0d1f3f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 31], 13 + QUAD $0x0e1e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 14 + QUAD $0x0e1f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 14 + QUAD $0x0f1e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 15 + QUAD $0x0f1f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00012024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -49542,2007 +50813,2001 @@ LBB8_181: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] - LONG $0x7f7ec1c4; WORD $0x8f44; BYTE $0x60 // vmovdqu yword [r15 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8f54; BYTE $0x40 // vmovdqu yword [r15 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8f64; BYTE $0x20 // vmovdqu yword [r15 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8f0c // vmovdqu yword [r15 + 4*rcx], ymm1 + LONG $0x447ffec5; WORD $0x608e // vmovdqu yword [rsi + 4*rcx + 96], ymm0 + LONG $0x547ffec5; WORD $0x408e // vmovdqu yword [rsi + 4*rcx + 64], ymm2 + LONG $0x647ffec5; WORD $0x208e // vmovdqu yword [rsi + 4*rcx + 32], ymm4 + LONG $0x0c7ffec5; BYTE $0x8e // vmovdqu yword [rsi + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB8_181 - QUAD $0x0000016824ac8b4c // mov r13, qword [rsp + 360] - QUAD $0x0000018024ac3b4c // cmp r13, qword [rsp + 384] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] - QUAD $0x0000017024a48b4c // mov r12, qword [rsp + 368] - JNE LBB8_38 - JMP LBB8_130 - -LBB8_183: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 + JNE LBB8_206 + QUAD $0x00000168248c8b48 // mov rcx, qword [rsp + 360] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + LONG $0x247c8b44; BYTE $0x04 // mov r15d, dword [rsp + 4] + QUAD $0x0000017024b48b48 // mov rsi, qword [rsp + 368] + JNE LBB8_136 + JMP LBB8_140 + +LBB8_208: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x000001f824848948 // mov qword [rsp + 504], rax - QUAD $0x0000016824bc894c // mov qword [rsp + 360], r15 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] + QUAD $0x00000168248c8948 // mov qword [rsp + 360], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] QUAD $0x0000016024848948 // mov qword [rsp + 352], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc7 // vmovd xmm0, r15d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 WORD $0xc031 // xor eax, eax - QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 + QUAD $0x000000f024a4894c // mov qword [rsp + 240], r12 -LBB8_184: +LBB8_209: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000017824848948 // mov qword [rsp + 376], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] + WORD $0x8948; BYTE $0xca // mov rdx, rcx LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x1a04b60f // movzx eax, byte [rdx + rbx] + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] - WORD $0x8948; BYTE $0xcf // mov rdi, rcx + LONG $0x1744b60f; BYTE $0x01 // movzx eax, byte [rdi + rdx + 1] LONG $0xe86ef9c5 // vmovd xmm5, eax - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x3a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rdi + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001a0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 416], xmm1 - LONG $0x3a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rdi + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x3a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rdi + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000200248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 512], xmm1 - LONG $0x1a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x3a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rdi + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x3a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rdi + 6] - QUAD $0x000000c824bc8948 // mov qword [rsp + 200], rdi + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x000000e024948948 // mov qword [rsp + 224], rdx LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x1a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x3a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rdi + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02200d48; WORD $0x0000 // or rax, 544 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02400d48; WORD $0x0000 // or rax, 576 - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02600d48; WORD $0x0000 // or rax, 608 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax - WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02800d48; WORD $0x0000 // or rax, 640 - WORD $0x8949; BYTE $0xc6 // mov r14, rax - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - LONG $0xa0c98149; WORD $0x0002; BYTE $0x00 // or r9, 672 - LONG $0x244c894c; BYTE $0x28 // mov qword [rsp + 40], r9 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x02c00d48; WORD $0x0000 // or rax, 704 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x02e00d48; WORD $0x0000 // or rax, 736 - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x03000d48; WORD $0x0000 // or rax, 768 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x0000010024848948 // mov qword [rsp + 256], rax - WORD $0x8949; BYTE $0xcb // mov r11, rcx - LONG $0x20cb8149; WORD $0x0003; BYTE $0x00 // or r11, 800 - LONG $0x245c894c; BYTE $0x78 // mov qword [rsp + 120], r11 - WORD $0x8949; BYTE $0xca // mov r10, rcx - LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - LONG $0x60c88149; WORD $0x0003; BYTE $0x00 // or r8, 864 - QUAD $0x000000d82484894c // mov qword [rsp + 216], r8 - WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x80cf8149; WORD $0x0003; BYTE $0x00 // or r15, 896 - LONG $0x247c894c; BYTE $0x58 // mov qword [rsp + 88], r15 - WORD $0x8948; BYTE $0xce // mov rsi, rcx - LONG $0xa0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 928 - QUAD $0x0000008824b48948 // mov qword [rsp + 136], rsi - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xdc // mov r12, rbx + LONG $0xa0cc8149; WORD $0x0002; BYTE $0x00 // or r12, 672 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0xc0cf8149; WORD $0x0002; BYTE $0x00 // or r15, 704 + QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0xe0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 736 + QUAD $0x0000014024b4894c // mov qword [rsp + 320], r14 + WORD $0x8948; BYTE $0xda // mov rdx, rbx + LONG $0x00ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 768 + LONG $0x24548948; BYTE $0x10 // mov qword [rsp + 16], rdx + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0x20c88149; WORD $0x0003; BYTE $0x00 // or r8, 800 + QUAD $0x000000b02484894c // mov qword [rsp + 176], r8 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03400d48; WORD $0x0000 // or rax, 832 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 + LONG $0x244c894c; BYTE $0x50 // mov qword [rsp + 80], r9 + WORD $0x8948; BYTE $0xde // mov rsi, rbx + LONG $0x80ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 896 + QUAD $0x000000d824b48948 // mov qword [rsp + 216], rsi + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0xa0cb8149; WORD $0x0003; BYTE $0x00 // or r11, 928 + QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x000000e8249c8948 // mov qword [rsp + 232], rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - LONG $0x206123c4; WORD $0x220c; BYTE $0x01 // vpinsrb xmm9, xmm3, byte [rdx + r12], 1 - LONG $0x2031e3c4; WORD $0x1a1c; BYTE $0x02 // vpinsrb xmm3, xmm9, byte [rdx + rbx], 2 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + rbx], 3 - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r14], 4 - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r9], 5 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + rbx], 6 - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + rdi], 7 - LONG $0x2061a3c4; WORD $0x2a1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + r13], 8 - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + r11], 9 - LONG $0x2061a3c4; WORD $0x121c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + r10], 10 - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + r8], 11 - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + r15], 12 - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rsi], 13 - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rax], 14 - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + rcx], 15 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - LONG $0x2059a3c4; WORD $0x3224; BYTE $0x01 // vpinsrb xmm4, xmm4, byte [rdx + r14], 1 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - LONG $0x2059a3c4; WORD $0x1224; BYTE $0x02 // vpinsrb xmm4, xmm4, byte [rdx + r10], 2 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - LONG $0x2059a3c4; WORD $0x1a24; BYTE $0x03 // vpinsrb xmm4, xmm4, byte [rdx + r11], 3 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2059a3c4; WORD $0x2224; BYTE $0x04 // vpinsrb xmm4, xmm4, byte [rdx + r12], 4 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - LONG $0x2059a3c4; WORD $0x0224; BYTE $0x05 // vpinsrb xmm4, xmm4, byte [rdx + r8], 5 - LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] - LONG $0x2059a3c4; WORD $0x0a24; BYTE $0x06 // vpinsrb xmm4, xmm4, byte [rdx + r9], 6 - LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] - LONG $0x2059a3c4; WORD $0x3a24; BYTE $0x07 // vpinsrb xmm4, xmm4, byte [rdx + r15], 7 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - LONG $0x2059e3c4; WORD $0x3224; BYTE $0x08 // vpinsrb xmm4, xmm4, byte [rdx + rsi], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - LONG $0x2059e3c4; WORD $0x0224; BYTE $0x09 // vpinsrb xmm4, xmm4, byte [rdx + rax], 9 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - LONG $0x2059e3c4; WORD $0x1a24; BYTE $0x0a // vpinsrb xmm4, xmm4, byte [rdx + rbx], 10 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - LONG $0x2059e3c4; WORD $0x0a24; BYTE $0x0b // vpinsrb xmm4, xmm4, byte [rdx + rcx], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - LONG $0x2059e3c4; WORD $0x3a24; BYTE $0x0c // vpinsrb xmm4, xmm4, byte [rdx + rdi], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - LONG $0x2059e3c4; WORD $0x3a24; BYTE $0x0d // vpinsrb xmm4, xmm4, byte [rdx + rdi], 13 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - LONG $0x2059e3c4; WORD $0x3a24; BYTE $0x0e // vpinsrb xmm4, xmm4, byte [rdx + rdi], 14 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - LONG $0x2059e3c4; WORD $0x3a24; BYTE $0x0f // vpinsrb xmm4, xmm4, byte [rdx + rdi], 15 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 1 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x02013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 3 + LONG $0x244c8948; BYTE $0x40 // mov qword [rsp + 64], rcx QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x04012a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 1], 4 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x05013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 5 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x06013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x07013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 7 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x08013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 8 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x09012a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 1], 9 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x0a012a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 1], 10 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0b013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 11 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0c013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 12 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0d013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 13 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0e013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 14 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0f013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 15 - QUAD $0x010132742029a3c4 // vpinsrb xmm6, xmm10, byte [rdx + r14 + 1], 1 - QUAD $0x020112742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 1], 2 - QUAD $0x03011a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r11 + 1], 3 - QUAD $0x040122742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 1], 4 - QUAD $0x050102742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 1], 5 - QUAD $0x06010a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 1], 6 - QUAD $0x07013a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 1], 7 - QUAD $0x080132742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 1], 8 - QUAD $0x090102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 9 - QUAD $0x0a011a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 1], 10 - QUAD $0x0b010a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 1], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c0102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 12 + LONG $0x206123c4; WORD $0x2f0c; BYTE $0x01 // vpinsrb xmm9, xmm3, byte [rdi + r13], 1 + LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] + LONG $0x2031e3c4; WORD $0x1f1c; BYTE $0x02 // vpinsrb xmm3, xmm9, byte [rdi + rbx], 2 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + LONG $0x2061a3c4; WORD $0x2f1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r13], 3 + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r10], 4 + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r12], 5 + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r15], 6 + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r14], 7 + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rdx], 8 + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + r8], 9 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + r12], 10 + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + r9], 11 + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + r11], 13 + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rax], 14 + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rcx], 15 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + LONG $0x2059a3c4; WORD $0x0f24; BYTE $0x01 // vpinsrb xmm4, xmm4, byte [rdi + r9], 1 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + LONG $0x2059e3c4; WORD $0x1f24; BYTE $0x02 // vpinsrb xmm4, xmm4, byte [rdi + rbx], 2 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x2059e3c4; WORD $0x0724; BYTE $0x03 // vpinsrb xmm4, xmm4, byte [rdi + rax], 3 + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + LONG $0x2059a3c4; WORD $0x1f24; BYTE $0x04 // vpinsrb xmm4, xmm4, byte [rdi + r11], 4 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + LONG $0x2059a3c4; WORD $0x0724; BYTE $0x05 // vpinsrb xmm4, xmm4, byte [rdi + r8], 5 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + LONG $0x2059a3c4; WORD $0x3f24; BYTE $0x06 // vpinsrb xmm4, xmm4, byte [rdi + r15], 6 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + LONG $0x2059a3c4; WORD $0x3724; BYTE $0x07 // vpinsrb xmm4, xmm4, byte [rdi + r14], 7 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + LONG $0x2059e3c4; WORD $0x3724; BYTE $0x08 // vpinsrb xmm4, xmm4, byte [rdi + rsi], 8 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x2059e3c4; WORD $0x0724; BYTE $0x09 // vpinsrb xmm4, xmm4, byte [rdi + rax], 9 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + LONG $0x2059a3c4; WORD $0x1724; BYTE $0x0a // vpinsrb xmm4, xmm4, byte [rdi + r10], 10 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + LONG $0x2059e3c4; WORD $0x0f24; BYTE $0x0b // vpinsrb xmm4, xmm4, byte [rdi + rcx], 11 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + LONG $0x2059e3c4; WORD $0x1724; BYTE $0x0c // vpinsrb xmm4, xmm4, byte [rdi + rdx], 12 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + LONG $0x2059e3c4; WORD $0x1724; BYTE $0x0d // vpinsrb xmm4, xmm4, byte [rdi + rdx], 13 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + LONG $0x2059e3c4; WORD $0x1724; BYTE $0x0e // vpinsrb xmm4, xmm4, byte [rdi + rdx], 14 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + LONG $0x2059e3c4; WORD $0x1724; BYTE $0x0f // vpinsrb xmm4, xmm4, byte [rdi + rdx], 15 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0101176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 1 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0201176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 2 + QUAD $0x03012f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 1], 3 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x04012f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 1], 4 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0501176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 5 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x06012f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 1], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0701176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0801176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 8 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0901176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 9 + QUAD $0x0a01276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 10 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0b01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 12 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0d01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 13 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0e01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 15 + QUAD $0x01010f742029a3c4 // vpinsrb xmm6, xmm10, byte [rdi + r9 + 1], 1 + QUAD $0x02011f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 1], 2 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x030117742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 1], 3 + QUAD $0x04011f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 1], 4 + QUAD $0x050107742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 1], 5 + QUAD $0x06013f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 1], 6 + QUAD $0x070137742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 1], 7 + QUAD $0x080137742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 1], 8 + QUAD $0x090107742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 1], 9 + QUAD $0x0a0117742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 1], 10 + QUAD $0x0b010f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 1], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0107742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 1], 12 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 13 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e0102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 14 + QUAD $0x0d0107742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 1], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e0107742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 1], 14 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x0004e0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1248], ymm3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0f01025c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdx + rax + 1], 15 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f01075c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdi + rax + 1], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xce6e79c5 // vmovd xmm9, esi LONG $0x3865e3c4; WORD $0x01dd // vinserti128 ymm3, ymm3, xmm5, 1 QUAD $0x000220249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm3 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x08 // movzx esi, byte [rdx + rax + 8] + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0774b60f; BYTE $0x08 // movzx esi, byte [rdi + rax + 8] LONG $0xd66e79c5 // vmovd xmm10, esi - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x01021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 1 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x02020a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 2], 2 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0302025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 2], 3 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0402025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0502025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 5 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x06020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 6 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0702025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0802025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 8 + QUAD $0x0102075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 2], 1 + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] + QUAD $0x02020f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 2], 2 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x03021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 3 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0402075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 4 LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0902225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 2], 9 - QUAD $0x0a022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 10 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x0b021a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 2], 11 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0c02325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 2], 12 + QUAD $0x0502275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 2], 5 + WORD $0x894d; BYTE $0xea // mov r10, r13 + QUAD $0x06022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 6 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x07020f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 2], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0802075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 8 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0902075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 10 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x0b021f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 2], 11 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0c02375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 2], 12 QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x0d023a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 2], 13 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0e02125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 2], 14 - QUAD $0x0f023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0d023f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 2], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] QUAD $0x0001a024a46ff9c5; BYTE $0x00 // vmovdqa xmm4, oword [rsp + 416] - QUAD $0x010202642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 2], 1 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x020232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 2 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x030232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 3 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x040232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 4 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x050232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 5 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x060232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 6 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x070232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 7 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x08023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 8 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x09023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 9 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0a023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 10 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0b023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 13 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0e023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 14 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0f023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 15 - QUAD $0x01031a6c2021e3c4 // vpinsrb xmm5, xmm11, byte [rdx + rbx + 3], 1 - QUAD $0x02030a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 3], 2 - QUAD $0x0303026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 3], 3 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x04033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 4 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x0503026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 3], 5 - QUAD $0x06030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x07033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 7 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x08030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 8 - QUAD $0x0903226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 3], 9 - QUAD $0x0a032a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 3], 10 - QUAD $0x0b031a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 3], 11 - QUAD $0x0c03326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 3], 12 - QUAD $0x0d033a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 3], 13 - QUAD $0x0e03126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 3], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 15 - QUAD $0x010302742039e3c4 // vpinsrb xmm6, xmm8, byte [rdx + rax + 3], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x020302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 2 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x030312742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 3], 3 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x04030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 4 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x05030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 5 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x06030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 6 - QUAD $0x070332742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 3], 7 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x080332742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r14 + 3], 8 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x09030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 9 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0a030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 10 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0b030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 11 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0c030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 12 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0d030a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 3], 13 + QUAD $0x010207642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 2], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x020237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 2 + QUAD $0x030217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 3 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x04022f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 2], 4 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x050217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x060237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 6 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x070237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 7 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x080217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 8 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x090217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 9 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0a0217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 10 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0b0217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 11 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0c0217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 12 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0d0217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 13 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0e0217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 14 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0f0217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 15 + QUAD $0x0103076c2021a3c4 // vpinsrb xmm5, xmm11, byte [rdi + r8 + 3], 1 + QUAD $0x02030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 2 + QUAD $0x03031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 3 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0403176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 4 + QUAD $0x0503276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 3], 5 + QUAD $0x0603176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 3], 6 + QUAD $0x07030f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 3], 7 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x08031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 8 + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x0903076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 3], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a03176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 10 + QUAD $0x0b031f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 3], 11 + QUAD $0x0c03376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 3], 12 + WORD $0x894d; BYTE $0xf2 // mov r10, r14 + QUAD $0x0d033f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 3], 13 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0e03176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f03176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 3], 15 + QUAD $0x010307742039e3c4 // vpinsrb xmm6, xmm8, byte [rdi + rax + 3], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x020307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 2 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x030307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 3 + QUAD $0x04032f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 3], 4 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x05033f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 3], 5 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x060307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 6 + QUAD $0x070337742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 3], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x080307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 8 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x090327742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 3], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 10 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0b031f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 3], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 12 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0d0307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x0001c0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm3 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0e030a5c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdx + rcx + 3], 14 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - LONG $0x0a74b60f; BYTE $0x09 // movzx esi, byte [rdx + rcx + 9] + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e03075c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdi + rax + 3], 14 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0774b60f; BYTE $0x09 // movzx esi, byte [rdi + rax + 9] LONG $0xc66e79c5 // vmovd xmm8, esi - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0f03225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 3], 15 + LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] + QUAD $0x0f03375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 3], 15 LONG $0x3865e3c4; WORD $0x01dd // vinserti128 ymm3, ymm3, xmm5, 1 QUAD $0x0001a0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm3 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a74b60f; BYTE $0x09 // movzx esi, byte [rdx + rcx + 9] + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1774b60f; BYTE $0x09 // movzx esi, byte [rdi + rdx + 9] LONG $0xde6e79c5 // vmovd xmm11, esi - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] QUAD $0x000200249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 512] - QUAD $0x01041a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 4], 1 - WORD $0x894d; BYTE $0xcb // mov r11, r9 - QUAD $0x02040a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 4], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x03040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 3 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x04042a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 4], 4 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - QUAD $0x0504025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 4], 5 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0604325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 6 - QUAD $0x07043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 7 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x08043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 8 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0904325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 9 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x0a040a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 4], 10 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0b04325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 11 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0c04325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 12 - QUAD $0x0d043a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 4], 13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0e04325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 14 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0f04325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 4], 15 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x010432642001e3c4 // vpinsrb xmm4, xmm15, byte [rdx + rsi + 4], 1 - QUAD $0x020402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 2 - QUAD $0x030412642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 4], 3 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x040402642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 4], 4 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x050412642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 4], 5 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x060432642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 4], 6 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x070402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 7 - QUAD $0x080432642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 4], 8 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x09043a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 4], 9 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a0402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 10 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0b0432642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 4], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c0402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 13 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0e0432642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 4], 14 - QUAD $0x0f0422642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 4], 15 - WORD $0x894d; BYTE $0xe6 // mov r14, r12 - QUAD $0x01051a6c2009e3c4 // vpinsrb xmm5, xmm14, byte [rdx + rbx + 5], 1 - QUAD $0x02051a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 5], 2 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x03051a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 5], 3 - QUAD $0x04052a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 5], 4 - QUAD $0x05050a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 5], 5 + QUAD $0x01040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 1 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0304075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 3 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0404175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0504075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0604075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 6 + QUAD $0x07040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 7 + QUAD $0x08041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 8 + QUAD $0x0904075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a04375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0b04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 11 + WORD $0x894d; BYTE $0xd5 // mov r13, r10 + QUAD $0x0c04175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 12 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x0d04175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0e04375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 14 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0605026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 6 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0705026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 7 - QUAD $0x08053a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 5], 8 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x09051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 9 - QUAD $0x0a050a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 5], 10 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 12 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0d050a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 5], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 14 + QUAD $0x0f04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x010437642001e3c4 // vpinsrb xmm4, xmm15, byte [rdi + rsi + 4], 1 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x010502742019e3c4 // vpinsrb xmm6, xmm12, byte [rdx + rax + 5], 1 + QUAD $0x020407642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 4], 2 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x03041f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 4], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x040407642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 4], 4 + QUAD $0x05043f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 4], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x060437642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 4], 6 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x07043f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 4], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x080407642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 4], 8 + QUAD $0x090427642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 4], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0407642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 4], 10 + QUAD $0x0b041f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 4], 11 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x0c041f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 4], 12 + QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] + QUAD $0x0d0427642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 4], 13 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x0e0427642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 4], 14 + QUAD $0x0f0437642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 4], 15 + QUAD $0x01050f6c2009a3c4 // vpinsrb xmm5, xmm14, byte [rdi + r9 + 5], 1 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0205076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0305076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 3 + QUAD $0x0405176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0505076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0605076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 6 + QUAD $0x07050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0805176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 8 + QUAD $0x0905076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 9 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0a050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 10 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x020502742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 5], 2 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x03050a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 5], 3 - QUAD $0x040502742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 5], 4 - QUAD $0x050512742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 5], 5 - QUAD $0x060532742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 5], 6 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x07050a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 5], 7 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x080512742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 5], 8 - QUAD $0x09053a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 5], 9 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a0502742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 5], 10 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x0b0522742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 5], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c0502742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 5], 12 + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x0c052f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 5], 12 + QUAD $0x0d05176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 13 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + QUAD $0x0e050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 15 + QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] + QUAD $0x010507742019a3c4 // vpinsrb xmm6, xmm12, byte [rdi + r8 + 5], 1 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x020517742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 5], 2 + QUAD $0x03051f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 5], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x040507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 4 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x05051f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 5], 5 + QUAD $0x060537742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 5], 6 + QUAD $0x07053f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 5], 7 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x08053f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 5], 8 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x090507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 10 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x0b0537742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 5], 11 + QUAD $0x0c051f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 5], 12 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0502742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 5], 13 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e0502742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 5], 14 + QUAD $0x0d0507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 13 + QUAD $0x0e0527742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 5], 14 LONG $0x385d63c4; WORD $0x01fb // vinserti128 ymm15, ymm4, xmm3, 1 - QUAD $0x0f0532642049a3c4 // vpinsrb xmm4, xmm6, byte [rdx + r14 + 5], 15 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x0274b60f; BYTE $0x0a // movzx esi, byte [rdx + rax + 10] + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f0507642049e3c4 // vpinsrb xmm4, xmm6, byte [rdi + rax + 5], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] LONG $0xe66e79c5 // vmovd xmm12, esi LONG $0x385de3c4; WORD $0x01dd // vinserti128 ymm3, ymm4, xmm5, 1 QUAD $0x000200249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm3 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x0a // movzx esi, byte [rdx + rax + 10] + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0774b60f; BYTE $0x0a // movzx esi, byte [rdi + rax + 10] LONG $0xe66ef9c5 // vmovd xmm4, esi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0106026c2011e3c4 // vpinsrb xmm5, xmm13, byte [rdx + rax + 6], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0206026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 2 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x03061a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 6], 3 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x04060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0506026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 5 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0606026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 6], 6 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x07063a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 6], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0806326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 8 - QUAD $0x09061a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 6], 9 - QUAD $0x0a062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b06026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c06026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 12 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0d06326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 6], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e06026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 14 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x0f063a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 6], 15 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x01062a742041a3c4 // vpinsrb xmm6, xmm7, byte [rdx + r13 + 6], 1 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x020632742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 6], 2 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x030632742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 6], 3 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x040632742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 6], 4 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x050632742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 6], 5 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0106076c2011e3c4 // vpinsrb xmm5, xmm13, byte [rdi + rax + 6], 1 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0206076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0306076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 3 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0406076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0506076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0606076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0706076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 7 + QUAD $0x0806176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 8 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0906076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 9 + QUAD $0x0a060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0b06076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 11 + WORD $0x894d; BYTE $0xec // mov r12, r13 + QUAD $0x0c062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 12 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0d06076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 13 + QUAD $0x0e060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 15 + QUAD $0x010607742041a3c4 // vpinsrb xmm6, xmm7, byte [rdi + r8 + 6], 1 + WORD $0x894d; BYTE $0xd5 // mov r13, r10 + QUAD $0x020617742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 6], 2 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x03060f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 6], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x040617742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 6], 4 + WORD $0x8948; BYTE $0xde // mov rsi, rbx + QUAD $0x05061f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 6], 5 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x060607742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 6], 6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x070607742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 6], 7 + WORD $0x894d; BYTE $0xfa // mov r10, r15 + QUAD $0x08063f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 6], 8 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x09061f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 6], 9 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0a061f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 6], 10 + QUAD $0x0b0637742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 6], 11 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x0c063f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 6], 12 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0d0637742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 6], 13 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0e061f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 6], 14 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0f061f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 6], 15 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x01071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 1 LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x06061a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 6], 6 - QUAD $0x07060a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 6], 7 - QUAD $0x080612742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 6], 8 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x09060a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 6], 9 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x0a0612742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 6], 10 - QUAD $0x0b0622742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 6], 11 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x0c061a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r11 + 6], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0602742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 6], 13 + QUAD $0x02071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 2 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x03071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 3 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x04071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 4 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x05071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 5 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x06071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 6 QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0e061a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 6], 14 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0f061a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 6], 15 - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - QUAD $0x010722542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 7], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x020702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 2 - QUAD $0x030732542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 7], 3 - QUAD $0x04070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 4 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x05070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 5 - QUAD $0x060702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 6 - QUAD $0x07073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x080702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 8 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x090702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 11 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0c073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 12 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0d0722542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 7], 13 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0e073a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 7], 14 - QUAD $0x0f073a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 7], 15 - QUAD $0x01072a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 7], 1 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x02073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 2 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0307024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 7], 3 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x04073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 4 - QUAD $0x0507324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 5 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0607324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 6 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x0707324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 7 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0807324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 8 - QUAD $0x09070a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 7], 9 - QUAD $0x0a07124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 7], 10 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0b07324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 7], 11 - QUAD $0x0c071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 12 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0d07324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 13 + QUAD $0x07071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 7 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x08071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 8 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x09071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 9 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0a071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 10 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0b071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 11 + QUAD $0x0c0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 12 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0d071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 13 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0e071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 14 + QUAD $0x0f070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 15 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x01070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 1 + QUAD $0x02072f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 7], 2 + QUAD $0x03070f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 7], 3 + QUAD $0x0407174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 4 + QUAD $0x0507374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 5 + QUAD $0x0607074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 7], 6 + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 + QUAD $0x0807174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 8 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x0907274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 9 + QUAD $0x0a071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 10 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x0b072f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 7], 11 + QUAD $0x0c073f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 7], 12 + QUAD $0x0d07374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 13 LONG $0x384de3c4; WORD $0x01dd // vinserti128 ymm3, ymm6, xmm5, 1 QUAD $0x0004c0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm3 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0e07326c2071e3c4 // vpinsrb xmm5, xmm1, byte [rdx + rsi + 7], 14 - WORD $0x8949; BYTE $0xf5 // mov r13, rsi - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - LONG $0x3274b60f; BYTE $0x0b // movzx esi, byte [rdx + rsi + 11] + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e07076c2071e3c4 // vpinsrb xmm5, xmm1, byte [rdi + rax + 7], 14 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x0f74b60f; BYTE $0x0b // movzx esi, byte [rdi + rcx + 11] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0f071a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 7], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f07076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 7], 15 LONG $0x3855e3c4; WORD $0x01d2 // vinserti128 ymm2, ymm5, xmm2, 1 QUAD $0x0004a024947ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm2 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x0b // movzx esi, byte [rdx + rsi + 11] + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f74b60f; BYTE $0x0b // movzx esi, byte [rdi + rcx + 11] LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01083a6c2031e3c4 // vpinsrb xmm5, xmm9, byte [rdx + rdi + 8], 1 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - QUAD $0x02081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0308326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 3 QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x04083a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 8], 4 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0508326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 5 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0608326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0708326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0808326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 8 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x09080a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 8], 9 - QUAD $0x0a080a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 8], 10 - QUAD $0x0b08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 12 - WORD $0x894d; BYTE $0xe2 // mov r10, r12 - QUAD $0x0d08226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 8], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e08026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f080a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 8], 15 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x01080a742029e3c4 // vpinsrb xmm6, xmm10, byte [rdx + rcx + 8], 1 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x02080a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 8], 2 - WORD $0x894d; BYTE $0xc4 // mov r12, r8 - QUAD $0x030802742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 8], 3 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x040832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 4 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x05080a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 8], 5 + QUAD $0x01083f6c2031a3c4 // vpinsrb xmm5, xmm9, byte [rdi + r15 + 8], 1 LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x06080a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 8], 6 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x07080a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 8], 7 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x080802742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 8], 8 + QUAD $0x02080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 2 + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x0308376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 3 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x0408076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 4 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0508176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 5 QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x09081a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r11 + 8], 9 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0a080a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 8], 10 - QUAD $0x0b0832742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r14 + 8], 11 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0c0832742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r14 + 8], 12 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0d080a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rcx + 8], 13 - QUAD $0x0e082a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r13 + 8], 14 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x0f082a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r13 + 8], 15 - QUAD $0x01093a7c2039e3c4 // vpinsrb xmm7, xmm8, byte [rdx + rdi + 9], 1 - QUAD $0x02091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x03090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 3 - QUAD $0x04093a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r15 + 9], 4 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x05093a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rdi + 9], 5 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x06091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 6 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x07091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 7 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x08091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 8 - QUAD $0x09090a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r9 + 9], 9 + QUAD $0x06081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0708076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0808176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 8 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x09080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a08176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 10 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0b08176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 11 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x0c081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 12 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0d08176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 13 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0e08176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 8], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f08176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x010817742029e3c4 // vpinsrb xmm6, xmm10, byte [rdi + rdx + 8], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x020817742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 8], 2 + QUAD $0x03080f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 8], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x040837742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 8], 4 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x050817742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 8], 5 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x06080f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 8], 6 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x070817742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 8], 7 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x080817742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 8], 8 + QUAD $0x090827742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 8], 9 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x0a0827742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 8], 10 + QUAD $0x0b082f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 8], 11 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x0c082f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 8], 12 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0d0817742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 8], 13 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x0e082f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 8], 14 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0f0817742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 8], 15 + QUAD $0x01093f7c2039a3c4 // vpinsrb xmm7, xmm8, byte [rdi + r15 + 9], 1 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0209177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 2 + QUAD $0x0309377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 3 + QUAD $0x0409077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 4 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x05093f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 9], 5 + QUAD $0x06091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 6 + QUAD $0x0709077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0809177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 8 + QUAD $0x09090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 9 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0a091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0b09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 11 + QUAD $0x0c091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 12 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x0d09377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 9], 13 + QUAD $0x0e09177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 9], 14 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x0f09177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 9], 15 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x01090f5c2021e3c4 // vpinsrb xmm3, xmm11, byte [rdi + rcx + 9], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0209075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 2 QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 11 + QUAD $0x03090f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 9], 3 + QUAD $0x0409375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 9], 4 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x05090f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 9], 5 + QUAD $0x06090f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 9], 6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0709075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0809075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 8 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0909075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 9 + QUAD $0x0a09275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 9], 10 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0b09075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c09075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 12 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0d09075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 13 + QUAD $0x0e092f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 9], 14 + LONG $0x384de3c4; WORD $0x01ed // vinserti128 ymm5, ymm6, xmm5, 1 + QUAD $0x00048024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm5 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f09075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0774b60f; BYTE $0x0c // movzx esi, byte [rdi + rax + 12] + LONG $0xee6ef9c5 // vmovd xmm5, esi + LONG $0x3865e3c4; WORD $0x01df // vinserti128 ymm3, ymm3, xmm7, 1 + QUAD $0x000460249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0774b60f; BYTE $0x0c // movzx esi, byte [rdi + rax + 12] + LONG $0xf66ef9c5 // vmovd xmm6, esi + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x010a075c2019e3c4 // vpinsrb xmm3, xmm12, byte [rdi + rax + 10], 1 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x020a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 2 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x030a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 3 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x040a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 4 + QUAD $0x050a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 5 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x060a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x070a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 7 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x080a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 8 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x090a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 9 + QUAD $0x0a0a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 10 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0b0a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 11 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x0c0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 12 + QUAD $0x0d0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 13 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0e0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 14 + QUAD $0x0f0a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x010a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x020a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 2 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x030a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 3 + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x040a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 4 + QUAD $0x050a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 5 LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0c090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 12 - QUAD $0x0d09127c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r10 + 9], 13 - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x0e09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 14 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0f091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 15 + QUAD $0x060a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 6 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x070a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x080a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 8 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0109025c2021e3c4 // vpinsrb xmm3, xmm11, byte [rdx + rax + 9], 1 - WORD $0x8949; BYTE $0xc2 // mov r10, rax - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0209025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 2 - QUAD $0x0309225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 9], 3 - QUAD $0x0409325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 9], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0509025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 5 - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] - QUAD $0x06093a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 9], 6 + QUAD $0x090a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 9 + QUAD $0x0a0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 10 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0b0a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 11 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0c0a17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 10], 12 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0d0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 13 + WORD $0x894c; BYTE $0xea // mov rdx, r13 + QUAD $0x0e0a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 14 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x0f0a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 15 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x010b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 1 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x020b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 2 + QUAD $0x030b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 3 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0709025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 7 - QUAD $0x0809025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 9], 8 - QUAD $0x09091a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 9], 9 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 10 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x0b092a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 9], 11 - QUAD $0x0c09325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 9], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 13 + QUAD $0x040b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 4 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x050b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x060b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 6 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 14 - LONG $0x384de3c4; WORD $0x01ed // vinserti128 ymm5, ymm6, xmm5, 1 - QUAD $0x00048024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm5 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0f09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 15 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] - LONG $0xee6ef9c5 // vmovd xmm5, esi - LONG $0x3865e3c4; WORD $0x01df // vinserti128 ymm3, ymm3, xmm7, 1 - QUAD $0x000460249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm3 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x0c // movzx esi, byte [rdx + rax + 12] - LONG $0xf66ef9c5 // vmovd xmm6, esi - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x010a0a5c2019a3c4 // vpinsrb xmm3, xmm12, byte [rdx + r9 + 10], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x020a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 2 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x030a325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 10], 3 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x040a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 4 - QUAD $0x050a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 5 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x060a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 6 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x070a1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 10], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x080a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 8 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x090a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 10 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x0b0a225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 10], 11 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0c0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 12 - QUAD $0x0d0a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 13 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0e0a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 14 - QUAD $0x0f0a1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 10], 15 - QUAD $0x010a12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 10], 1 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x020a32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 10], 2 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x030a32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 10], 3 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x040a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 4 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x050a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 5 - QUAD $0x060a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 6 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x070a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 7 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x080a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 8 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x090a12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 10], 9 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0a0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 10 - QUAD $0x0b0a2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 10], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 12 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0d0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 13 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0e0a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 14 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x0f0a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 15 - QUAD $0x010b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 1 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x020b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 2 - QUAD $0x030b324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 11], 3 - QUAD $0x040b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 4 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x050b1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 11], 5 - QUAD $0x060b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 6 - QUAD $0x070b1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 11], 7 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x080b3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 11], 8 - QUAD $0x090b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 10 - QUAD $0x0b0b224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 11], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 12 + QUAD $0x070b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 7 + QUAD $0x080b3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 11], 8 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x090b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 9 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 10 + QUAD $0x0b0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 11 + QUAD $0x0c0b0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 11], 12 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 13 - QUAD $0x0e0b0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 11], 14 + QUAD $0x0d0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 13 + QUAD $0x0e0b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 15 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x010b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 1 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 15 + QUAD $0x020b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 2 + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + QUAD $0x040b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x050b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 5 + QUAD $0x060b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 11], 6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x080b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 8 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x010b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x020b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 2 - QUAD $0x030b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 3 + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + QUAD $0x0a0b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 10 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x040b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x050b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 5 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x060b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 6 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x070b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 7 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x080b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 8 - QUAD $0x090b12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 11], 9 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0a0b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 11], 10 - QUAD $0x0b0b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 11 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0c0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 12 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0d0b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 13 + QUAD $0x0b0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 11 + QUAD $0x0c0b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 11], 12 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0d0b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000440249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm3 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0e0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 14 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - LONG $0x0a74b60f; BYTE $0x0d // movzx esi, byte [rdx + rcx + 13] + QUAD $0x0e0b17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 11], 14 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0f0b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000420248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a74b60f; BYTE $0x0d // movzx esi, byte [rdx + rcx + 13] + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1774b60f; BYTE $0x0d // movzx esi, byte [rdi + rdx + 13] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x010c1a542051a3c4 // vpinsrb xmm2, xmm5, byte [rdx + r11 + 12], 1 - WORD $0x894d; BYTE $0xca // mov r10, r9 - QUAD $0x020c0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 12], 2 - WORD $0x894c; BYTE $0xf1 // mov rcx, r14 - QUAD $0x030c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 12], 3 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x040c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 12], 4 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x050c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 5 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x060c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 6 - QUAD $0x070c02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 12], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x080c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 8 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x090c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a0c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 10 - WORD $0x894d; BYTE $0xe0 // mov r8, r12 - QUAD $0x0b0c22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 12], 11 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0c0c22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 12], 12 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x0d0c0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 12], 13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0e0c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 14 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0f0c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 15 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x010c32642049e3c4 // vpinsrb xmm4, xmm6, byte [rdx + rsi + 12], 1 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x020c32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 12], 2 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x030c1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 12], 3 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x040c1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 12], 4 - QUAD $0x050c02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 12], 5 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x010c1f542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rbx + 12], 1 LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x060c02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 12], 6 + QUAD $0x020c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 2 + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x030c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 3 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x070c02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 12], 7 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x080c1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 12], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x090c02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 12], 9 - QUAD $0x0a0c3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 12], 10 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0b0c3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 12], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c0c3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 12], 12 - QUAD $0x0d0c2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 12], 13 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0e0c2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 12], 14 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x0f0c2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 12], 15 - QUAD $0x010d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 13], 1 - QUAD $0x020d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 13], 2 - QUAD $0x030d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 3 - QUAD $0x040d325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 13], 4 - QUAD $0x050d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 13], 5 + QUAD $0x040c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 4 + QUAD $0x050c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 5 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x060c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 6 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x070c0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 12], 7 + LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] + QUAD $0x080c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 8 + QUAD $0x090c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 9 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x0a0c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 10 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0b0c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 11 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0c0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 12 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0d0c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 13 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0e0c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 14 LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x060d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 6 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x070d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 13], 7 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x080d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 8 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x090d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 9 + QUAD $0x0f0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x010c37642049e3c4 // vpinsrb xmm4, xmm6, byte [rdi + rsi + 12], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x020c37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 12], 2 QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 10 - QUAD $0x0b0d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 11 - QUAD $0x0c0d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 12 - QUAD $0x0d0d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 13 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0e0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 15 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x010d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 1 - QUAD $0x020d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 2 - WORD $0x8949; BYTE $0xf1 // mov r9, rsi + QUAD $0x030c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x040c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 4 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x050c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 5 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x060c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 6 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x070c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 7 + QUAD $0x080c2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 12], 8 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x090c27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 12], 9 QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x030d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 3 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x040d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 4 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x050d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 5 + QUAD $0x0a0c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 10 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0b0c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 11 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x0c0c2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 12], 12 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0d0c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 13 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x0e0c2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 12], 14 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0f0c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 15 + QUAD $0x010d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 1 LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x060d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 6 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x070d0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 13], 7 - QUAD $0x080d1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 13], 8 - QUAD $0x090d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 9 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 10 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0b0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 11 - QUAD $0x0c0d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 13 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 14 + QUAD $0x020d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 2 + QUAD $0x030d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 3 + QUAD $0x040d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 4 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x050d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 5 + QUAD $0x060d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 6 + QUAD $0x070d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 7 + QUAD $0x080d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 13], 8 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x090d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 9 + QUAD $0x0a0d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 10 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x0b0d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c0d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 12 + QUAD $0x0d0d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 13 + QUAD $0x0e0d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 13], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 13], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x010d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 1 + QUAD $0x020d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 2 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x030d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x040d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x050d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 5 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x060d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x070d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 7 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x080d3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 13], 8 + QUAD $0x090d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 9 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0a0d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 10 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0b0d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 12 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0d0d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 13 + QUAD $0x0e0d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 14 LONG $0x385de3c4; WORD $0x01d2 // vinserti128 ymm2, ymm4, xmm2, 1 QUAD $0x00040024947ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm2 - WORD $0x894d; BYTE $0xec // mov r12, r13 - QUAD $0x0f0d2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 13], 15 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - LONG $0x74b60f42; WORD $0x0e32 // movzx esi, byte [rdx + r14 + 14] + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0774b60f; BYTE $0x0e // movzx esi, byte [rdi + rax + 14] LONG $0xd66ef9c5 // vmovd xmm2, esi LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x0003e0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x0e // movzx esi, byte [rdx + rax + 14] + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + LONG $0x1f74b60f; BYTE $0x0e // movzx esi, byte [rdi + rbx + 14] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x010e02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 14], 1 - QUAD $0x020e12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 14], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x030e0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 14], 3 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x040e12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 14], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x050e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 5 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x060e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 6 - QUAD $0x070e1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 14], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x080e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 8 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x090e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a0e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 10 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x0b0e1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 14], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 12 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d0e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 13 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0e0e3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 14], 14 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0f0e1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 14], 15 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x010e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 1 - QUAD $0x020e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 14], 2 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x030e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 14], 3 - QUAD $0x040e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x050e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 5 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x060e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 6 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x010e27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 14], 1 + QUAD $0x020e0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 14], 2 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x030e2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 14], 3 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x070e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 7 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x080e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 8 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x090e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 9 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0a0e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 10 - QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] - QUAD $0x0b0e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 11 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0c0e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 12 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0d0e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 13 + QUAD $0x040e07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 14], 4 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x050e37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 14], 5 + QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] + QUAD $0x060e37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 14], 6 QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0e0e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 14], 14 - QUAD $0x0f0e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 14], 15 - LONG $0x74b60f42; WORD $0x0f32 // movzx esi, byte [rdx + r14 + 15] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x010f025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 15], 1 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x020f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 2 - QUAD $0x030f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 3 - QUAD $0x040f125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 15], 4 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x050f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 5 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x060f225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 15], 6 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x070f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 7 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x080f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 8 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x090f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 9 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x0a0f025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 15], 10 - QUAD $0x0b0f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 11 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0c0f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 12 + QUAD $0x070e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x080e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 8 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x090e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a0e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 10 + QUAD $0x0b0e0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 14], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c0e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 12 QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0d0f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 13 - QUAD $0x0e0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 14 - QUAD $0x0f0f1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 15], 15 + QUAD $0x0d0e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0e0e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 14 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x0f0e0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 14], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x010e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x020e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 2 + QUAD $0x030e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x040e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 4 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x050e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x060e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 6 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x070e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 7 + QUAD $0x080e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 14], 8 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x090e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 9 + QUAD $0x0a0e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 14], 10 + QUAD $0x0b0e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 11 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x0c0e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 14], 12 + QUAD $0x0d0e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 13 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0e0e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 14 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0f0e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 15 QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x0f // movzx esi, byte [rdx + rsi + 15] + LONG $0x3774b60f; BYTE $0x0f // movzx esi, byte [rdi + rsi + 15] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x010f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 1 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x020f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 2 + QUAD $0x030f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 3 + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + QUAD $0x050f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 5 + QUAD $0x060f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x070f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 7 + LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] + QUAD $0x080f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 8 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x090f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 10 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x0b0f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0d0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 13 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0e0f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 14 + QUAD $0x0f0f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 15 + LONG $0x1f74b60f; BYTE $0x0f // movzx esi, byte [rdi + rbx + 15] LONG $0xe66ef9c5 // vmovd xmm4, esi - QUAD $0x010f2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 15], 1 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x020f32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 15], 2 - QUAD $0x030f0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 15], 3 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x040f1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 15], 4 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x050f0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 15], 5 - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] - QUAD $0x060f2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 15], 6 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x070f32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 15], 7 - QUAD $0x080f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 8 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x090f12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 15], 9 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0a0f3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 15], 10 - QUAD $0x0b0f3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 15], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c0f1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 15], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 13 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0e0f32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 15], 14 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0f0f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x010f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x020f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 2 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x030f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x040f0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 15], 4 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x050f1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 15], 5 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x060f1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 15], 6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x070f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x080f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 8 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x090f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a0f37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 15], 10 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0b0f37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 15], 11 + QUAD $0x0c0f3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 15], 12 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0d0f37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 15], 13 + QUAD $0x0e0f17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 15], 14 + QUAD $0x0f0f07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 15], 15 LONG $0x3875e3c4; WORD $0x01ca // vinserti128 ymm1, ymm1, xmm2, 1 QUAD $0x0003a0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm1 LONG $0x385de3c4; WORD $0x01cb // vinserti128 ymm1, ymm4, xmm3, 1 QUAD $0x0003c0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x0274b60f; BYTE $0x10 // movzx esi, byte [rdx + rax + 16] + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + LONG $0x1774b60f; BYTE $0x10 // movzx esi, byte [rdi + rdx + 16] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0110024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 1 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x02103a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 16], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0310024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 3 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0410024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0510024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 5 - QUAD $0x0610224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 16], 6 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0710024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 7 - QUAD $0x08100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 8 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0910024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 9 - QUAD $0x0a10024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 16], 10 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x0b10224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 16], 11 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0c100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 12 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d10024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0e10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 14 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0f10324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 15 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x10 // movzx esi, byte [rdx + rsi + 16] + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0110074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 1 + LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] + QUAD $0x02100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 2 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x0310174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 3 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0410174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 4 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0510174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 5 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0610174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0710374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 7 + QUAD $0x0810374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 8 + QUAD $0x0910274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 10 + QUAD $0x0b10174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 16], 11 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x0c103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 12 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0d10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 13 + QUAD $0x0e102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f10174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 15 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + LONG $0x74b60f42; WORD $0x1037 // movzx esi, byte [rdi + r14 + 16] LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x011032542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 16], 1 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x021032542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 16], 2 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x031032542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 16], 3 - QUAD $0x04101a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 16], 4 - QUAD $0x05100a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 16], 5 - QUAD $0x06102a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 16], 6 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x07100a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 16], 7 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x08102a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 16], 8 - QUAD $0x091012542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 16], 9 - QUAD $0x0a103a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 16], 10 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0b1032542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 16], 11 - QUAD $0x0c101a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 16], 12 - QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] - QUAD $0x0d101a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 16], 13 - QUAD $0x0e1032542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 16], 14 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0f1032542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 16], 15 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - LONG $0x3a74b60f; BYTE $0x11 // movzx esi, byte [rdx + rdi + 17] - LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x0111025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 17], 1 - QUAD $0x02113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0311325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 3 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x04111a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 17], 4 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x05113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 5 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0611125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 17], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0711325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0811325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 8 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0911325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a11325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 10 - QUAD $0x0b11225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 17], 11 - QUAD $0x0c110a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 17], 12 - QUAD $0x0d11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x11 // movzx esi, byte [rdx + rax + 17] - LONG $0xe66ef9c5 // vmovd xmm4, esi - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x011102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 1 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x021122642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 17], 2 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x031132642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 17], 3 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x011017542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 16], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x021017542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 16], 2 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x03102f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 16], 3 + QUAD $0x04100f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 16], 4 + QUAD $0x05101f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 16], 5 + QUAD $0x06101f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 16], 6 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x07100f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 16], 7 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x08100f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 16], 8 + QUAD $0x091007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 10 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x041102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x051102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 5 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x061102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 6 - QUAD $0x07110a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 17], 7 - QUAD $0x08112a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 17], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x091102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 9 + QUAD $0x0b1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 11 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0c1017542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 16], 12 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0d1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 14 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 15 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + LONG $0x74b60f42; WORD $0x1127 // movzx esi, byte [rdi + r12 + 17] + LONG $0xde6ef9c5 // vmovd xmm3, esi + QUAD $0x0111075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 1 + QUAD $0x02110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 2 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x0311075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 3 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0411075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 4 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x05110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 5 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x06111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0711075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 7 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a1102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 10 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0b1102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 11 + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a11175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0b11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 11 + QUAD $0x0c113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 12 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0d111f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 17], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 15 + LONG $0x74b60f42; WORD $0x1137 // movzx esi, byte [rdi + r14 + 17] + LONG $0xe66ef9c5 // vmovd xmm4, esi + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + QUAD $0x01113f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 17], 1 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x021137642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 17], 2 + QUAD $0x03112f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 17], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 5 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x061107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 6 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c1102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 12 - QUAD $0x0d111a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 17], 13 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e1102642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 17], 14 + QUAD $0x071107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x081107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 8 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x091137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 17], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a1137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 17], 10 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0b1137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 17], 11 + QUAD $0x0c1117642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 17], 12 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0d1117642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 17], 13 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0e1137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 17], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000380248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm1 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0f11024c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdx + rax + 17], 15 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0f11374c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdi + rsi + 17], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x000360248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm1 - LONG $0x3a74b60f; BYTE $0x12 // movzx esi, byte [rdx + rdi + 18] + LONG $0x74b60f42; WORD $0x1227 // movzx esi, byte [rdi + r12 + 18] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0112024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0212024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 2 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0312024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 3 - QUAD $0x04121a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 18], 4 - QUAD $0x05123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 5 - QUAD $0x0612124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 18], 6 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x07122a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 18], 7 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x08120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 8 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x09120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 9 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x0a120a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 18], 10 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x0b121a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 18], 11 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0c12324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 12 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0d12324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 13 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0e12124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 18], 14 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0f12324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 15 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - LONG $0x74b60f42; WORD $0x120a // movzx esi, byte [rdx + r9 + 18] - LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x01123a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 18], 1 - QUAD $0x021222542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 18], 2 - QUAD $0x031232542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 18], 3 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x041232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 4 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x051232542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 18], 5 + QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] + QUAD $0x0112274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 1 LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x061232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 6 - LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] - QUAD $0x071222542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 18], 7 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x081232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 8 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x091232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 9 + QUAD $0x0212374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 2 + QUAD $0x0312074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 3 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0412374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 4 + QUAD $0x05120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 5 + QUAD $0x06121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 6 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x07120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 7 LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0a1232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 10 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0b1232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 11 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0c1232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 12 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0d1232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 13 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0e123a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 18], 14 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0f121a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 18], 15 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - LONG $0x3274b60f; BYTE $0x13 // movzx esi, byte [rdx + rsi + 19] + QUAD $0x0812374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 8 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0912374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 9 + QUAD $0x0a12174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 10 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0b12174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 11 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0c12174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 12 + QUAD $0x0d121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 13 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0e121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 14 + QUAD $0x0f120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 15 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f74b60f; BYTE $0x12 // movzx esi, byte [rdi + rcx + 18] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x01123f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 18], 1 + QUAD $0x021237542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 18], 2 + QUAD $0x03122f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 18], 3 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x04122f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 18], 4 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x051217542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 18], 5 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x06120f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 18], 6 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x07123f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 18], 7 + QUAD $0x081207542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 18], 8 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x091207542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 18], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1207542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 18], 10 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0b120f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 18], 11 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0c120f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 18], 12 + QUAD $0x0d1217542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 18], 13 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x0e1217542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 18], 14 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x0f121f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 18], 15 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + LONG $0x3774b60f; BYTE $0x13 // movzx esi, byte [rdi + rsi + 19] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0113325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 1 - QUAD $0x0213025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 2 - QUAD $0x0313025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 19], 3 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0413025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0513025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 5 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0613025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 6 - QUAD $0x07132a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 19], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0813025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 8 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0913025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 9 - QUAD $0x0a130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 10 - QUAD $0x0b131a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 19], 11 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0c131a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 19], 12 + QUAD $0x0113275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 1 + LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] + QUAD $0x0213075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 2 + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x0313375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 3 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0413375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 4 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0513375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x06130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 6 + QUAD $0x07130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0813375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 8 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0913375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 9 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x0a130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 10 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0b13375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c13375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 12 QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0d130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 13 - QUAD $0x0e13125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 19], 14 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0f130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 15 - LONG $0x74b60f42; WORD $0x130a // movzx esi, byte [rdx + r9 + 19] + QUAD $0x0d130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 13 + QUAD $0x0e131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f13375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 15 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + LONG $0x74b60f42; WORD $0x1327 // movzx esi, byte [rdi + r12 + 19] LONG $0xe66ef9c5 // vmovd xmm4, esi - QUAD $0x01133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 1 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x02132a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 19], 2 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x03133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 3 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x041302642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 19], 4 - QUAD $0x051332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 19], 5 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x061332642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 19], 6 - QUAD $0x071322642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 19], 7 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x08130a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 19], 8 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x091332642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 19], 9 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0a1332642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 19], 10 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x0b1332642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 19], 11 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0c1332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 19], 12 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0d1332642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 19], 13 - QUAD $0x0e133a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 19], 14 - QUAD $0x0f131a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 19], 15 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x011337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 19], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x021337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 19], 2 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x031337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 19], 3 + QUAD $0x04132f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 19], 4 + QUAD $0x051317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 19], 5 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x061317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 19], 6 + QUAD $0x07133f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 19], 7 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x08132f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 19], 8 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x091317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 19], 9 + QUAD $0x0a1307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 10 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0b1307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 11 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x0c133f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 19], 12 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0d1307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 13 + QUAD $0x0e1317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 19], 14 + QUAD $0x0f131f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 19], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000320248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm1 LONG $0x385de3c4; WORD $0x01cb // vinserti128 ymm1, ymm4, xmm3, 1 QUAD $0x000340248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm1 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - LONG $0x3274b60f; BYTE $0x14 // movzx esi, byte [rdx + rsi + 20] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0774b60f; BYTE $0x14 // movzx esi, byte [rdi + rax + 20] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0114324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 1 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x0214324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0314324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 3 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x0414324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 4 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x0514224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 20], 5 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0614324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0714324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0814324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 8 - QUAD $0x0914024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 20], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a14024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 20], 10 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0b14324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 11 - QUAD $0x0c141a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 20], 12 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x0d14124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 13 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x0e141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 14 - QUAD $0x0f140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 15 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - LONG $0x74b60f42; WORD $0x143a // movzx esi, byte [rdx + r15 + 20] + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x01141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 1 + QUAD $0x0214074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 2 + QUAD $0x0314374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 20], 3 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0414074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 4 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0514074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 5 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x0614174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0714074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0814074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 8 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x09141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 9 + QUAD $0x0a140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0b14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 12 + QUAD $0x0d140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 15 + LONG $0x74b60f42; WORD $0x1427 // movzx esi, byte [rdi + r12 + 20] LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x011432542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 20], 1 - QUAD $0x02142a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 20], 2 - QUAD $0x03143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 3 - QUAD $0x041402542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 20], 4 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x05142a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 20], 5 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x06140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 6 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x07140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 7 - QUAD $0x08140a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 20], 8 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x09140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 9 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0a140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 10 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0b140a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 20], 11 - QUAD $0x0c1432542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 20], 12 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x011407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 1 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x02140f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 20], 2 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x031427542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 20], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 5 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x061407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 6 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x071437542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 20], 7 + QUAD $0x08142f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 20], 8 + QUAD $0x091417542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 20], 9 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x0a140f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 20], 10 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0b140f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 20], 11 + QUAD $0x0c143f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 20], 12 QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0d140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 13 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0e140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 14 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0f140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 15 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - LONG $0x0a74b60f; BYTE $0x15 // movzx esi, byte [rdx + rcx + 21] + QUAD $0x0d140f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 20], 13 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x0e1437542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 20], 14 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0f1407542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 20], 15 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + LONG $0x74b60f42; WORD $0x153f // movzx esi, byte [rdi + r15 + 21] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 1 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x02150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 2 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0315025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 21], 3 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x0415325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 4 - QUAD $0x0515225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 21], 5 + QUAD $0x01151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 1 + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] + QUAD $0x02150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 2 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x03152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 3 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x04151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 4 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0515175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 5 + QUAD $0x0615175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 6 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0715175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 7 + LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] + QUAD $0x0815175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 8 + QUAD $0x09151f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 21], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0a15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 10 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0b15175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 12 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0d15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0e15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 14 LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0615325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0715325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0815325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 8 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0915325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 9 - QUAD $0x0a15025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 10 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0b15025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 11 - QUAD $0x0c151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 12 - QUAD $0x0d15125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 13 - QUAD $0x0e151a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 21], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f15025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 15 - LONG $0x74b60f42; WORD $0x153a // movzx esi, byte [rdx + r15 + 21] - WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x0f15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 15 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + LONG $0x3774b60f; BYTE $0x15 // movzx esi, byte [rdi + rsi + 21] LONG $0xe66ef9c5 // vmovd xmm4, esi + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x011537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 21], 1 + QUAD $0x02150f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 21], 2 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + QUAD $0x031527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 21], 3 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x041527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 21], 4 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x051537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 21], 5 + QUAD $0x061507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x071507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x081507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 8 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x011502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 1 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x021532642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 21], 2 + QUAD $0x091507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 9 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x031502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 3 + QUAD $0x0a1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 10 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x041502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 4 - QUAD $0x05152a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 21], 5 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x061502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 6 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x07152a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 21], 7 - QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] - QUAD $0x081522642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 21], 8 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x09153a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 21], 9 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x0a1512642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 21], 10 - QUAD $0x0b150a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 21], 11 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0c150a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 21], 12 + QUAD $0x0b1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 12 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d1502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 13 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e1502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 14 + QUAD $0x0d1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 13 + QUAD $0x0e1537642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 21], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x0002e0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm1 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0f15024c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdx + rax + 21], 15 + QUAD $0x0f15074c2059a3c4 // vpinsrb xmm1, xmm4, byte [rdi + r8 + 21], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x000300248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x0274b60f; BYTE $0x16 // movzx esi, byte [rdx + rax + 22] + LONG $0x74b60f42; WORD $0x163f // movzx esi, byte [rdi + r15 + 22] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x01163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 1 - QUAD $0x02160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 2 - QUAD $0x0316024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 22], 3 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0416024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 4 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x05160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 5 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x06160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 6 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x07160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0816324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 8 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x09163a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 22], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 10 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0b16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 11 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0c161a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 22], 12 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0d16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 13 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x0e16024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 22], 14 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0f16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 15 - LONG $0x1a74b60f; BYTE $0x16 // movzx esi, byte [rdx + rbx + 22] + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0116374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 22], 1 + QUAD $0x02160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 2 + QUAD $0x03162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 3 + QUAD $0x04161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 4 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x05160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x06160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x07160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 7 + QUAD $0x0816174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 22], 8 + WORD $0x894c; BYTE $0xdb // mov rbx, r11 + QUAD $0x09161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 9 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0a161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 10 + QUAD $0x0b16174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 11 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0c160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 12 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0d16174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 13 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x0e163f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 22], 14 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0f16174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1774b60f; BYTE $0x16 // movzx esi, byte [rdi + rdx + 22] LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x011617542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 22], 1 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x021617542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 22], 2 + QUAD $0x03160f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 22], 3 + QUAD $0x041627542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 22], 4 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x05160f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 22], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x061637542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 22], 6 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x071637542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 22], 7 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x081637542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 22], 8 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x011632542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 22], 1 - QUAD $0x021632542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 22], 2 + QUAD $0x091637542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 22], 9 QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x031632542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 22], 3 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x041632542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 22], 4 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x051632542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 22], 5 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x061632542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 22], 6 - QUAD $0x07162a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 22], 7 - QUAD $0x081622542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 22], 8 - QUAD $0x09163a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 22], 9 - QUAD $0x0a1612542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 22], 10 - QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] - QUAD $0x0b1622542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 22], 11 - QUAD $0x0c160a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 22], 12 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0d162a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 22], 13 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0e1612542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 22], 14 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0f1632542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 22], 15 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - LONG $0x74b60f42; WORD $0x173a // movzx esi, byte [rdx + r15 + 23] + QUAD $0x0a1637542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 22], 10 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x0b1617542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 22], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c1637542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 22], 12 + QUAD $0x0d1607542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 22], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e1607542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 22], 14 + QUAD $0x0f1607542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 22], 15 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + LONG $0x74b60f42; WORD $0x172f // movzx esi, byte [rdi + r13 + 23] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x01170a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 23], 1 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x0217325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 23], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0317325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 3 - QUAD $0x0417025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 23], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0517025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 23], 5 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0617025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 23], 6 - QUAD $0x07170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x0817025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 23], 8 - QUAD $0x09173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 9 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x0a173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 10 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0b170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 11 - QUAD $0x0c171a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 23], 12 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0d17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 13 - QUAD $0x0e17025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 23], 14 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0f17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 15 - LONG $0x1a74b60f; BYTE $0x17 // movzx esi, byte [rdx + rbx + 23] + QUAD $0x0117375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 1 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0317075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 3 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0417075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 4 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0517275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0617075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0717075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0817075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 8 + QUAD $0x09171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 9 + QUAD $0x0a171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 10 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x0b171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 11 + QUAD $0x0c170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 12 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x0d17375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 13 + QUAD $0x0e173f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 23], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0774b60f; BYTE $0x17 // movzx esi, byte [rdi + rax + 23] LONG $0xe66ef9c5 // vmovd xmm4, esi + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x011737642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 23], 1 + QUAD $0x021717642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 23], 2 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x031717642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 23], 3 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x04171f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 23], 4 + QUAD $0x05170f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 23], 5 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x06173f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 23], 6 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x071717642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 23], 7 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x081717642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 23], 8 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x011732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 1 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x021732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 2 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x03171a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 23], 3 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x041732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 4 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x051732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 5 - LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x06171a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 23], 6 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x071732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 7 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x081732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 8 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x091732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 9 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0a1732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 10 - QUAD $0x0b1722642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 23], 11 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0c1732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 12 - QUAD $0x0d172a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 23], 13 - QUAD $0x0e1712642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 23], 14 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0f1722642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 23], 15 + QUAD $0x091737642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 23], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a1737642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 23], 10 + QUAD $0x0b1717642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 23], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c1737642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 23], 12 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0d1717642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 23], 13 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0e1737642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 23], 14 + QUAD $0x0f1707642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 23], 15 LONG $0x386d63c4; WORD $0x01d9 // vinserti128 ymm11, ymm2, xmm1, 1 LONG $0x385d63c4; WORD $0x01e3 // vinserti128 ymm12, ymm4, xmm3, 1 - LONG $0x74b60f42; WORD $0x183a // movzx esi, byte [rdx + r15 + 24] + LONG $0x74b60f42; WORD $0x182f // movzx esi, byte [rdi + r13 + 24] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x01180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 1 - QUAD $0x0218324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 24], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0318324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 3 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x0418024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 4 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0518324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 5 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x06183a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 24], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0718324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 7 - QUAD $0x0818024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 8 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x0918324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 24], 9 - QUAD $0x0a183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 10 - QUAD $0x0b180a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 24], 11 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x0c180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 12 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d18024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 13 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0e18124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 14 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x0f182a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 24], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x18 // movzx esi, byte [rdx + rax + 24] + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0118374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 1 + LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] + QUAD $0x02180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x0318374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 3 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x04182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 4 + QUAD $0x0518274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 5 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0618374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0718374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0818374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 8 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0918374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 9 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x0a18274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 24], 10 + QUAD $0x0b181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 11 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x0c181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 12 + QUAD $0x0d18374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0e18374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 14 + QUAD $0x0f180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 15 + LONG $0x0774b60f; BYTE $0x18 // movzx esi, byte [rdi + rax + 24] LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x011802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x021802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 2 - QUAD $0x03181a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 24], 3 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x041802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 4 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x05181a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 24], 5 - QUAD $0x06181a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 24], 6 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x071802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 7 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x081802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x091802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 9 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0a181a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 24], 10 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0b180a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 24], 11 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x011807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x021807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 2 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x031807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 3 + QUAD $0x04181f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 24], 4 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x051837542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 24], 5 + QUAD $0x06183f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 24], 6 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c1802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d183a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 24], 13 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e1802542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 24], 14 - QUAD $0x0f1822542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 24], 15 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x0274b60f; BYTE $0x19 // movzx esi, byte [rdx + rax + 25] + QUAD $0x071807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 7 + QUAD $0x081817542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 24], 8 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x091807542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 24], 9 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x0a181f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 24], 10 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0b180f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 24], 11 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0c180f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 24], 12 + QUAD $0x0d1817542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 24], 13 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x0e180f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 24], 14 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0f180f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 24], 15 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x0f74b60f; BYTE $0x19 // movzx esi, byte [rdi + rcx + 25] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0119025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x0219025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0319025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 3 - QUAD $0x0419025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0519025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 5 - QUAD $0x06193a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 25], 6 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0719025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x0819325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 8 - QUAD $0x0919325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 25], 9 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x0a19025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 10 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0b19325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 11 - QUAD $0x0c190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 12 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0d19325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 13 - QUAD $0x0e19125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 25], 14 - QUAD $0x0f192a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 25], 15 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - LONG $0x74b60f42; WORD $0x1912 // movzx esi, byte [rdx + r10 + 25] - LONG $0xe66ef9c5 // vmovd xmm4, esi - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x011932642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 25], 1 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x02190a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 25], 2 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x031932642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 25], 3 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x04193a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 25], 4 - QUAD $0x05191a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 25], 5 - LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] - QUAD $0x06191a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 25], 6 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x071932642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 25], 7 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x01190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 1 + QUAD $0x02190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 2 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x03190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 3 + QUAD $0x04192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 4 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0519175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 5 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0619175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0719375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0819375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 8 QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x081932642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 25], 8 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x091932642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 25], 9 - QUAD $0x0a191a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 25], 10 - QUAD $0x0b190a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 25], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c191a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 25], 12 - QUAD $0x0d193a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 25], 13 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0e1922642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 25], 14 + QUAD $0x0919375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 9 + QUAD $0x0a19275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 10 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0b19275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 11 + QUAD $0x0c191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 12 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0d193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0e19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 14 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x0f19175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 25], 15 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + LONG $0x74b60f42; WORD $0x191f // movzx esi, byte [rdi + r11 + 25] + LONG $0xe66ef9c5 // vmovd xmm4, esi + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x011937642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 25], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x021937642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 25], 2 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x031937642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 25], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041937642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 25], 4 + QUAD $0x051937642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 25], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x061937642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 25], 6 + QUAD $0x071907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 7 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x08190f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 25], 8 + QUAD $0x091907642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 25], 9 + QUAD $0x0a191f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 25], 10 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0b1907642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 25], 11 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x0c1937642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 25], 12 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0d1907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 13 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0e1907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000180248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 384], ymm1 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0f190a4c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdx + rcx + 25], 15 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x0f192f4c2059a3c4 // vpinsrb xmm1, xmm4, byte [rdi + r13 + 25], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x000240248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - LONG $0x0a74b60f; BYTE $0x1a // movzx esi, byte [rdx + rcx + 26] + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + LONG $0x1f74b60f; BYTE $0x1a // movzx esi, byte [rdi + rbx + 26] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x011a0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 26], 1 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x021a0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 26], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x031a0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 26], 3 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x041a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 4 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x051a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 5 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x061a2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 26], 6 - QUAD $0x071a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x081a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 8 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x091a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 9 - QUAD $0x0a1a024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 26], 10 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0b1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c1a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 12 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x0d1a024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 26], 13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0e1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 14 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0f1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 15 - LONG $0x74b60f42; WORD $0x1a12 // movzx esi, byte [rdx + r10 + 26] + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x011a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 1 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x021a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 2 + QUAD $0x031a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 3 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x041a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 4 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x051a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 5 + QUAD $0x061a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 6 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x071a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 7 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x081a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 8 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x091a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 10 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + QUAD $0x0b1a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 11 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0c1a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 12 + QUAD $0x0d1a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0e1a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 14 + QUAD $0x0f1a174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 26], 15 + LONG $0x74b60f42; WORD $0x1a1f // movzx esi, byte [rdi + r11 + 26] LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x011a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 1 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x021a3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 26], 2 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x031a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 4 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x051a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x061a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 6 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x071a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 7 + QUAD $0x081a0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 26], 8 LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x011a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 1 - QUAD $0x021a0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 26], 2 + QUAD $0x091a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 9 QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x031a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 3 - QUAD $0x041a3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 26], 4 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x051a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 5 - QUAD $0x061a1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 26], 6 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x071a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 7 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x081a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 8 - QUAD $0x091a32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 26], 9 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0a1a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 10 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0b1a0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 26], 11 - QUAD $0x0c1a1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 26], 12 + QUAD $0x0a1a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 10 + QUAD $0x0b1a07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 26], 11 + QUAD $0x0c1a37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 26], 12 QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x0d1a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 13 - QUAD $0x0e1a22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 26], 14 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0f1a32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 26], 15 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - LONG $0x74b60f42; WORD $0x1b3a // movzx esi, byte [rdx + r15 + 27] + QUAD $0x0d1a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 13 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0e1a37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 26], 14 + QUAD $0x0f1a2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 26], 15 + LONG $0x1f74b60f; BYTE $0x1b // movzx esi, byte [rdi + rbx + 27] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x011b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 1 - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - QUAD $0x021b125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 27], 2 - QUAD $0x031b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 3 - QUAD $0x041b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 4 + QUAD $0x011b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 1 + LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] + QUAD $0x021b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 2 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x031b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 3 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x041b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 4 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x051b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 5 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x061b1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 27], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x071b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 7 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x081b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 8 + QUAD $0x091b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 9 LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x051b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 5 - QUAD $0x061b2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 27], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x071b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 7 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - QUAD $0x081b1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 27], 8 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x091b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 9 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0a1b325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 27], 10 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x0b1b225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 27], 11 - QUAD $0x0c1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 12 - QUAD $0x0d1b025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 27], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x0274b60f; BYTE $0x1b // movzx esi, byte [rdx + rax + 27] + QUAD $0x0a1b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 10 + QUAD $0x0b1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 11 + QUAD $0x0c1b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 12 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x0d1b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 13 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0e1b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0f1b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 15 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + LONG $0x1774b60f; BYTE $0x1b // movzx esi, byte [rdi + rdx + 27] LONG $0xe66ef9c5 // vmovd xmm4, esi - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x011b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 1 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x021b02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 27], 2 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x031b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 3 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x041b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 4 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x051b3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 27], 5 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x061b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 6 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x071b2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 27], 7 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x081b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 8 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x091b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 9 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a1b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 10 - QUAD $0x0b1b0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 27], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c1b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d1b02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 27], 13 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0e1b32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 27], 14 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x011b37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 27], 1 + QUAD $0x021b3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 27], 2 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x031b3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 27], 3 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x041b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 4 QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x0f1b32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 27], 15 + QUAD $0x051b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x061b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 6 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x071b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 7 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x081b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 8 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x091b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a1b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 10 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0b1b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c1b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 12 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0d1b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 13 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0e1b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 14 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0f1b37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 27], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000260248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm1 LONG $0x385de3c4; WORD $0x01cb // vinserti128 ymm1, ymm4, xmm3, 1 QUAD $0x000280248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm1 - LONG $0x74b60f42; WORD $0x1c3a // movzx esi, byte [rdx + r15 + 28] + LONG $0x1f74b60f; BYTE $0x1c // movzx esi, byte [rdi + rbx + 28] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x011c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 1 - QUAD $0x021c124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 28], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x031c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 3 QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x041c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 4 - QUAD $0x051c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 5 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x061c3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 28], 6 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x071c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 7 - QUAD $0x081c1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 28], 8 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x091c1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 28], 9 - QUAD $0x0a1c324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 28], 10 - QUAD $0x0b1c224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 28], 11 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0c1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 12 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0d1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 13 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0e1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 14 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x0f1c0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 28], 15 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a74b60f; BYTE $0x1c // movzx esi, byte [rdx + rcx + 28] + QUAD $0x011c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 1 + QUAD $0x021c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 2 + QUAD $0x031c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 3 + QUAD $0x041c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 4 + QUAD $0x051c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 5 + QUAD $0x061c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x071c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 7 + QUAD $0x081c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 28], 8 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x091c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0b1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 12 + QUAD $0x0d1c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 13 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0e1c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 14 + QUAD $0x0f1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 15 + LONG $0x1774b60f; BYTE $0x1c // movzx esi, byte [rdi + rdx + 28] LONG $0xd66ef9c5 // vmovd xmm2, esi - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x011c0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 28], 1 - QUAD $0x021c02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 28], 2 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x031c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 28], 3 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x041c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 28], 4 - QUAD $0x051c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 28], 5 - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - QUAD $0x061c02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 28], 6 - QUAD $0x071c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 28], 7 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x081c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 28], 8 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x091c12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 28], 9 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x0a1c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 28], 10 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0b1c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 28], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c1c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 28], 12 - QUAD $0x0d1c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 13 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0e1c22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 28], 14 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0f1c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 15 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - LONG $0x3274b60f; BYTE $0x1d // movzx esi, byte [rdx + rsi + 29] + QUAD $0x011c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 28], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x021c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 2 + QUAD $0x031c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 28], 3 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x041c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 28], 4 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x051c0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 28], 5 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x061c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x071c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 7 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x081c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 28], 8 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x091c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 28], 9 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x0a1c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 28], 10 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0b1c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 28], 11 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x0c1c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 28], 12 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0d1c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 28], 13 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x0e1c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 28], 14 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x0f1c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 28], 15 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + LONG $0x3774b60f; BYTE $0x1d // movzx esi, byte [rdi + rsi + 29] LONG $0xde6ef9c5 // vmovd xmm3, esi - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x011d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 1 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x021d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 2 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x031d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 3 QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x041d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 4 + QUAD $0x011d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 1 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x021d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 2 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x031d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 3 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x041d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 4 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x051d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 5 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x061d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 6 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x071d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x081d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 8 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x091d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 9 LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x051d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 5 - QUAD $0x061d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 29], 6 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x071d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 7 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x081d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 8 - QUAD $0x091d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 9 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0a1d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 10 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - QUAD $0x0b1d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 29], 11 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0c1d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 12 + QUAD $0x0a1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 10 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0b1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 11 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0c1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 12 QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0d1d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0e1d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 14 - QUAD $0x0f1d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 29], 15 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3274b60f; BYTE $0x1d // movzx esi, byte [rdx + rsi + 29] + QUAD $0x0d1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 13 + QUAD $0x0e1d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 15 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + LONG $0x74b60f42; WORD $0x1d27 // movzx esi, byte [rdi + r12 + 29] LONG $0xe66ef9c5 // vmovd xmm4, esi - QUAD $0x011d0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 29], 1 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x021d0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 29], 2 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x031d0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 29], 3 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x041d0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 29], 4 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x051d32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 29], 5 - QUAD $0x061d02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 29], 6 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x071d32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 29], 7 - QUAD $0x081d32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 29], 8 - QUAD $0x091d12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 29], 9 - QUAD $0x0a1d2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 29], 10 - QUAD $0x0b1d3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 29], 11 - WORD $0x8949; BYTE $0xfd // mov r13, rdi - QUAD $0x0c1d1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 29], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d1d3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 29], 13 - QUAD $0x0e1d22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 29], 14 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x011d37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 29], 1 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x021d37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 29], 2 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x031d37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 29], 3 + QUAD $0x041d17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 29], 4 + QUAD $0x051d0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 29], 5 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x061d17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 29], 6 + QUAD $0x071d07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 29], 7 + WORD $0x8949; BYTE $0xc1 // mov r9, rax + QUAD $0x081d07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 29], 8 + QUAD $0x091d1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 29], 9 + QUAD $0x0a1d37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 29], 10 + QUAD $0x0b1d0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 29], 11 + QUAD $0x0c1d2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 29], 12 + QUAD $0x0d1d17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 29], 13 + QUAD $0x0e1d1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 29], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x0002a0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm1 - QUAD $0x0f1d024c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdx + rax + 29], 15 - WORD $0x8949; BYTE $0xc4 // mov r12, rax + QUAD $0x0f1d3f4c2059a3c4 // vpinsrb xmm1, xmm4, byte [rdi + r15 + 29], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x0002c0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm1 - QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - LONG $0x74b60f42; WORD $0x1e02 // movzx esi, byte [rdx + r8 + 30] + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x0f74b60f; BYTE $0x1e // movzx esi, byte [rdi + rcx + 30] LONG $0xce6ef9c5 // vmovd xmm1, esi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x011e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 1 - LONG $0x74b60f42; WORD $0x1f02 // movzx esi, byte [rdx + r8 + 31] - LONG $0xd66ef9c5 // vmovd xmm2, esi - QUAD $0x011f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x021e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 2 - QUAD $0x021f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x031e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 3 - QUAD $0x031f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 3 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x041e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 4 - QUAD $0x041f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x051e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 5 - QUAD $0x051f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 5 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x061e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 6 - QUAD $0x061f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 6 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x071e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 7 - QUAD $0x071f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 7 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 8 + QUAD $0x011e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 1 + LONG $0x0f74b60f; BYTE $0x1f // movzx esi, byte [rdi + rcx + 31] + LONG $0xd66ef9c5 // vmovd xmm2, esi + QUAD $0x011f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 1 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 2 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 3 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 4 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x091e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 9 - QUAD $0x091f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 9 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 10 - QUAD $0x0b1e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 30], 11 - QUAD $0x0b1f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 31], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 12 - QUAD $0x0c1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 12 + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 6 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 8 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x091e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 9 + QUAD $0x091f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 9 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 11 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 12 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0d1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 13 - QUAD $0x0d1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0f1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 15 - QUAD $0x0f1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 15 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - LONG $0x3244b60f; BYTE $0x1e // movzx eax, byte [rdx + rsi + 30] + QUAD $0x0d1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 13 + QUAD $0x0d1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 14 + QUAD $0x0e1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 15 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + LONG $0x44b60f42; WORD $0x1e27 // movzx eax, byte [rdi + r12 + 30] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x011e025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 30], 1 - LONG $0x3244b60f; BYTE $0x1f // movzx eax, byte [rdx + rsi + 31] + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x011e175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 30], 1 + LONG $0x44b60f42; WORD $0x1f27 // movzx eax, byte [rdi + r12 + 31] LONG $0xe06ef9c5 // vmovd xmm4, eax - QUAD $0x011f02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 31], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x021e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 2 - QUAD $0x021f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 2 - QUAD $0x031e0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 30], 3 - QUAD $0x031f0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 31], 3 - QUAD $0x041e0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 30], 4 - QUAD $0x041f0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 31], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x051e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 5 - QUAD $0x051f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 5 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x061e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 6 - QUAD $0x061f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 6 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x071e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 7 - QUAD $0x071f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 7 - QUAD $0x081e325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 30], 8 - QUAD $0x081f32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 31], 8 - QUAD $0x091e125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 30], 9 - QUAD $0x091f12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 31], 9 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a1e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 10 - QUAD $0x0a1f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 10 - QUAD $0x0b1e2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 30], 11 - QUAD $0x0b1f2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 31], 11 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x0c1e1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 30], 12 - QUAD $0x0c1f1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 31], 12 - QUAD $0x0d1e3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 30], 13 - QUAD $0x0d1f3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 31], 13 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0e1e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 14 - QUAD $0x0e1f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 14 - QUAD $0x0f1e225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 30], 15 - QUAD $0x0f1f22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 31], 15 + QUAD $0x011f17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 31], 1 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x021e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 2 + QUAD $0x021f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 2 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x031e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 3 + QUAD $0x031f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 3 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x041e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 4 + QUAD $0x041f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 5 + QUAD $0x051f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 5 + QUAD $0x061e175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 30], 6 + QUAD $0x061f17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 31], 6 + QUAD $0x071e0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 30], 7 + QUAD $0x071f0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 31], 7 + QUAD $0x081e075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 30], 8 + QUAD $0x081f07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 31], 8 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x091e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 9 + QUAD $0x091f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 9 + QUAD $0x0a1e375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 30], 10 + QUAD $0x0a1f37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 31], 10 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0b1e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 11 + QUAD $0x0b1f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 11 + QUAD $0x0c1e2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 30], 12 + QUAD $0x0c1f2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 31], 12 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0d1e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 13 + QUAD $0x0d1f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 13 + QUAD $0x0e1e1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 30], 14 + QUAD $0x0e1f1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 31], 14 + QUAD $0x0f1e3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 30], 15 + QUAD $0x0f1f3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 31], 15 LONG $0x3865e3c4; WORD $0x01c9 // vinserti128 ymm1, ymm3, xmm1, 1 QUAD $0x000120248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 288], ymm1 LONG $0x385de3c4; WORD $0x01ca // vinserti128 ymm1, ymm4, xmm2, 1 @@ -51715,21 +52980,21 @@ LBB8_184: LONG $0x385de3c4; WORD $0x01e9 // vinserti128 ymm5, ymm4, xmm1, 1 LONG $0x465de3c4; WORD $0x31c9 // vperm2i128 ymm1, ymm4, ymm1, 49 QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] - LONG $0x7f7ec1c4; WORD $0x8b4c; BYTE $0x60 // vmovdqu yword [r11 + 4*rcx + 96], ymm1 - LONG $0x7f7ec1c4; WORD $0x8b54; BYTE $0x40 // vmovdqu yword [r11 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8b6c; BYTE $0x20 // vmovdqu yword [r11 + 4*rcx + 32], ymm5 - LONG $0x7f7ec1c4; WORD $0x8b1c // vmovdqu yword [r11 + 4*rcx], ymm3 + LONG $0x4c7ffec5; WORD $0x608e // vmovdqu yword [rsi + 4*rcx + 96], ymm1 + LONG $0x547ffec5; WORD $0x408e // vmovdqu yword [rsi + 4*rcx + 64], ymm2 + LONG $0x6c7ffec5; WORD $0x208e // vmovdqu yword [rsi + 4*rcx + 32], ymm5 + LONG $0x1c7ffec5; BYTE $0x8e // vmovdqu yword [rsi + 4*rcx], ymm3 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000168248c3b48 // cmp rcx, qword [rsp + 360] - JNE LBB8_184 - QUAD $0x0000017024bc8b4c // mov r15, qword [rsp + 368] - QUAD $0x0000016824bc3b4c // cmp r15, qword [rsp + 360] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - LONG $0x24748b44; BYTE $0x04 // mov r14d, dword [rsp + 4] - QUAD $0x000001f824a48b4c // mov r12, qword [rsp + 504] - JNE LBB8_101 - JMP LBB8_125 + JNE LBB8_209 + QUAD $0x00000170248c8b48 // mov rcx, qword [rsp + 368] + QUAD $0x00000168248c3b48 // cmp rcx, qword [rsp + 360] + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + LONG $0x247c8b44; BYTE $0x04 // mov r15d, dword [rsp + 4] + QUAD $0x000001f8249c8b4c // mov r11, qword [rsp + 504] + JNE LBB8_150 + JMP LBB8_154 TEXT ·_comparison_greater_equal_arr_arr_avx2(SB), $80-48 @@ -51741,71 +53006,85 @@ TEXT ·_comparison_greater_equal_arr_arr_avx2(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB9_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB9_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB9_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB9_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB9_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_22 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_20: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_20 - LONG $0x01c68349 // add r14, 1 - -LBB9_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_26 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB9_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB9_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB9_24: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x0c8b; BYTE $0x86 // mov ecx, dword [rsi + 4*rax] + WORD $0x0c3b; BYTE $0x82 // cmp ecx, dword [rdx + 4*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_26: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_28: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_32 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_30: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] LONG $0x2454930f; BYTE $0x14 // setae byte [rsp + 20] @@ -51829,7 +53108,7 @@ LBB9_24: LONG $0x2454930f; BYTE $0x09 // setae byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3930f41 // setae r11b @@ -51869,7 +53148,7 @@ LBB9_24: LONG $0x2454930f; BYTE $0x0b // setae byte [rsp + 11] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] + LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1930f41 // setae r9b @@ -51878,10 +53157,10 @@ LBB9_24: LONG $0x2454930f; BYTE $0x13 // setae byte [rsp + 19] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] + LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] + LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] LONG $0x2454930f; BYTE $0x0f // setae byte [rsp + 15] @@ -51896,10 +53175,10 @@ LBB9_24: LONG $0x2454930f; BYTE $0x11 // setae byte [rsp + 17] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] - LONG $0xd7930f40 // setae dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd0930f41 // setae r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -51908,34 +53187,34 @@ LBB9_24: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -51948,22 +53227,23 @@ LBB9_24: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -51980,26 +53260,25 @@ LBB9_24: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_24 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_30 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_28: +LBB9_34: WORD $0x048b; BYTE $0x8e // mov eax, dword [rsi + 4*rcx] WORD $0x043b; BYTE $0x8a // cmp eax, dword [rdx + 4*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -52007,75 +53286,89 @@ LBB9_28: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_28 - JMP LBB9_123 - -LBB9_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB9_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB9_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB9_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_50 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_48: - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_48 - LONG $0x01c68349 // add r14, 1 - -LBB9_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_54 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB9_52: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_34 + JMP LBB9_153 + +LBB9_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB9_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB9_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB9_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_58: + LONG $0x0410fbc5; BYTE $0xc6 // vmovsd xmm0, qword [rsi + 8*rax] + LONG $0x042ef9c5; BYTE $0xc2 // vucomisd xmm0, qword [rdx + 8*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_58 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_60: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_62: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_66 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB9_64: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] LONG $0x4e10fbc5; BYTE $0x08 // vmovsd xmm1, qword [rsi + 8] LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] @@ -52099,7 +53392,7 @@ LBB9_52: LONG $0x4610fbc5; BYTE $0x38 // vmovsd xmm0, qword [rsi + 56] LONG $0xd5930f41 // setae r13b LONG $0x422ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rdx + 56] - LONG $0xd7930f41 // setae r15b + LONG $0xd6930f41 // setae r14b LONG $0x4610fbc5; BYTE $0x40 // vmovsd xmm0, qword [rsi + 64] LONG $0x422ef9c5; BYTE $0x40 // vucomisd xmm0, qword [rdx + 64] LONG $0x4610fbc5; BYTE $0x48 // vmovsd xmm0, qword [rsi + 72] @@ -52130,7 +53423,7 @@ LBB9_52: LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] QUAD $0x00000088822ef9c5 // vucomisd xmm0, qword [rdx + 136] QUAD $0x000000908610fbc5 // vmovsd xmm0, qword [rsi + 144] - LONG $0xd6930f41 // setae r14b + LONG $0xd7930f41 // setae r15b QUAD $0x00000090822ef9c5 // vucomisd xmm0, qword [rdx + 144] QUAD $0x000000988610fbc5 // vmovsd xmm0, qword [rsi + 152] LONG $0xd4930f41 // setae r12b @@ -52176,8 +53469,8 @@ LBB9_52: WORD $0xc000 // add al, al LONG $0x04244402 // add al, byte [rsp + 4] LONG $0x06e5c041 // shl r13b, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0845; BYTE $0xef // or r15b, r13b + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0845; BYTE $0xee // or r14b, r13b LONG $0x6cb60f44; WORD $0x0524 // movzx r13d, byte [rsp + 5] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0841; BYTE $0xc5 // or r13b, al @@ -52207,17 +53500,17 @@ LBB9_52: LONG $0x06e1c041 // shl r9b, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0e // add r14b, byte [rsp + 14] + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x0e // add r15b, byte [rsp + 14] LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0845; BYTE $0xfc // or r12b, r15b LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -52225,12 +53518,12 @@ LBB9_52: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc0 // or r8b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -52255,23 +53548,22 @@ LBB9_52: LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xc7 // or dil, al WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x02468845 // mov byte [r14 + 2], r8b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x02478845 // mov byte [r15 + 2], r8b + LONG $0x037f8841 // mov byte [r15 + 3], dil LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB9_52 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB9_64 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB9_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_56: +LBB9_68: LONG $0x0410fbc5; BYTE $0xce // vmovsd xmm0, qword [rsi + 8*rcx] LONG $0x042ef9c5; BYTE $0xca // vucomisd xmm0, qword [rdx + 8*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -52279,75 +53571,95 @@ LBB9_56: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_56 - JMP LBB9_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_68 + JMP LBB9_153 LBB9_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB9_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + JE LBB9_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB9_9 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB9_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd49d0f41 // setge r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_6 - LONG $0x01c68349 // add r14, 1 - -LBB9_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_12 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB9_10: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + LONG $0x38048841 // mov byte [r8 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB9_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB9_9: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_11: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_15 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB9_13: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x9d0f; BYTE $0xd1 // setge cl LONG $0x0246b60f // movzx eax, byte [rsi + 2] @@ -52367,7 +53679,7 @@ LBB9_10: LONG $0x24549d0f; BYTE $0x04 // setge byte [rsp + 4] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd79d0f41 // setge r15b + LONG $0xd69d0f41 // setge r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x24549d0f; BYTE $0x07 // setge byte [rsp + 7] @@ -52382,7 +53694,7 @@ LBB9_10: LONG $0xd39d0f41 // setge r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd69d0f41 // setge r14b + LONG $0xd79d0f41 // setge r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] LONG $0x24549d0f; BYTE $0x05 // setge byte [rsp + 5] @@ -52442,12 +53754,12 @@ LBB9_10: WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] LONG $0xd09d0f41 // setge r8b WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x30244c02 // add cl, byte [rsp + 48] WORD $0xc889 // mov eax, ecx LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al @@ -52469,26 +53781,26 @@ LBB9_10: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x06 // movzx edi, byte [rsp + 6] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0d // add r12b, byte [rsp + 13] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -52496,12 +53808,12 @@ LBB9_10: LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al @@ -52527,23 +53839,22 @@ LBB9_10: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB9_10 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB9_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB9_13 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB9_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_14: +LBB9_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -52551,77 +53862,91 @@ LBB9_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_14 - JMP LBB9_123 - -LBB9_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB9_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_36 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_34: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_34 - LONG $0x01c68349 // add r14, 1 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_17 + JMP LBB9_153 LBB9_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_40 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB9_38: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB9_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_41: + LONG $0xc60c8b48 // mov rcx, qword [rsi + 8*rax] + LONG $0xc20c3b48 // cmp rcx, qword [rdx + 8*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_43: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_45: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_49 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_47: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] LONG $0x2454930f; BYTE $0x14 // setae byte [rsp + 20] @@ -52645,7 +53970,7 @@ LBB9_38: LONG $0x2454930f; BYTE $0x09 // setae byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3930f41 // setae r11b @@ -52685,7 +54010,7 @@ LBB9_38: LONG $0x2454930f; BYTE $0x0b // setae byte [rsp + 11] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] + LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1930f41 // setae r9b @@ -52694,10 +54019,10 @@ LBB9_38: LONG $0x2454930f; BYTE $0x13 // setae byte [rsp + 19] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] + LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] + LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] LONG $0x2454930f; BYTE $0x0f // setae byte [rsp + 15] @@ -52712,10 +54037,10 @@ LBB9_38: LONG $0x2454930f; BYTE $0x11 // setae byte [rsp + 17] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] - LONG $0xd7930f40 // setae dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd0930f41 // setae r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -52724,34 +54049,34 @@ LBB9_38: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -52764,22 +54089,23 @@ LBB9_38: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -52796,26 +54122,25 @@ LBB9_38: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_38 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_47 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_42: +LBB9_51: LONG $0xce048b48 // mov rax, qword [rsi + 8*rcx] LONG $0xca043b48 // cmp rax, qword [rdx + 8*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -52823,73 +54148,87 @@ LBB9_42: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_42 - JMP LBB9_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_51 + JMP LBB9_153 -LBB9_68: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_72 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_70: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_70 - LONG $0x01c68349 // add r14, 1 +LBB9_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_86: + LONG $0x460cb70f // movzx ecx, word [rsi + 2*rax] + LONG $0x420c3b66 // cmp cx, word [rdx + 2*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB9_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_76 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 +LBB9_88: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 -LBB9_74: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_90: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_94 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_92: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] LONG $0x2454930f; BYTE $0x14 // setae byte [rsp + 20] @@ -52913,7 +54252,7 @@ LBB9_74: LONG $0x2454930f; BYTE $0x09 // setae byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3930f41 // setae r11b @@ -52953,7 +54292,7 @@ LBB9_74: LONG $0x2454930f; BYTE $0x0b // setae byte [rsp + 11] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] + LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1930f41 // setae r9b @@ -52962,10 +54301,10 @@ LBB9_74: LONG $0x2454930f; BYTE $0x13 // setae byte [rsp + 19] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] + LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] + LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] LONG $0x2454930f; BYTE $0x0f // setae byte [rsp + 15] @@ -52980,10 +54319,10 @@ LBB9_74: LONG $0x2454930f; BYTE $0x11 // setae byte [rsp + 17] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] - LONG $0xd7930f40 // setae dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd0930f41 // setae r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -52992,34 +54331,34 @@ LBB9_74: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -53032,22 +54371,23 @@ LBB9_74: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -53064,26 +54404,25 @@ LBB9_74: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_74 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_92 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_78: +LBB9_96: LONG $0x4e04b70f // movzx eax, word [rsi + 2*rcx] LONG $0x4a043b66 // cmp ax, word [rdx + 2*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -53091,73 +54430,87 @@ LBB9_78: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_78 - JMP LBB9_123 - -LBB9_79: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_83 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_96 + JMP LBB9_153 + +LBB9_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB9_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_81 - LONG $0x01c68349 // add r14, 1 +LBB9_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd39d0f41 // setge r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_102: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_104: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_108 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax -LBB9_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_87 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB9_85: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_106: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] LONG $0x24549d0f; BYTE $0x14 // setge byte [rsp + 20] @@ -53181,7 +54534,7 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x09 // setge byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd09d0f41 // setge r8b + LONG $0xd79d0f40 // setge dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd39d0f41 // setge r11b @@ -53221,7 +54574,7 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x0b // setge byte [rsp + 11] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] + LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd19d0f41 // setge r9b @@ -53230,10 +54583,10 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x13 // setge byte [rsp + 19] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] + LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] + LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] LONG $0x24549d0f; BYTE $0x0f // setge byte [rsp + 15] @@ -53248,10 +54601,10 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x11 // setge byte [rsp + 17] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] - LONG $0xd79d0f40 // setge dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09d0f41 // setge r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -53260,34 +54613,34 @@ LBB9_85: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -53300,22 +54653,23 @@ LBB9_85: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -53332,26 +54686,25 @@ LBB9_85: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_85 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - -LBB9_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + JNE LBB9_106 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB9_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_89: +LBB9_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -53359,73 +54712,87 @@ LBB9_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_89 - JMP LBB9_123 - -LBB9_101: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_105 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_103 - LONG $0x01c68349 // add r14, 1 - -LBB9_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_109 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB9_107: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_110 + JMP LBB9_153 + +LBB9_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd39d0f41 // setge r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_130: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_132: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_136 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_134: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] LONG $0x24549d0f; BYTE $0x14 // setge byte [rsp + 20] @@ -53449,7 +54816,7 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x09 // setge byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd09d0f41 // setge r8b + LONG $0xd79d0f40 // setge dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd39d0f41 // setge r11b @@ -53489,7 +54856,7 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x0b // setge byte [rsp + 11] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] + LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd19d0f41 // setge r9b @@ -53498,10 +54865,10 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x13 // setge byte [rsp + 19] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] + LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] + LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] LONG $0x24549d0f; BYTE $0x0f // setge byte [rsp + 15] @@ -53516,10 +54883,10 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x11 // setge byte [rsp + 17] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] - LONG $0xd79d0f40 // setge dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09d0f41 // setge r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -53528,34 +54895,34 @@ LBB9_107: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -53568,22 +54935,23 @@ LBB9_107: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -53600,26 +54968,25 @@ LBB9_107: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_107 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_134 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_111: +LBB9_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -53627,67 +54994,81 @@ LBB9_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_111 - JMP LBB9_123 - -LBB9_112: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_116 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_114: - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_114 - LONG $0x01c68349 // add r14, 1 - -LBB9_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_120 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_138 + JMP LBB9_153 + +LBB9_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_142: + LONG $0x0410fac5; BYTE $0x86 // vmovss xmm0, dword [rsi + 4*rax] + LONG $0x042ef8c5; BYTE $0x82 // vucomiss xmm0, dword [rdx + 4*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_142 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_144: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_146: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_150 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax -LBB9_118: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_148: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x0610fac5 // vmovss xmm0, dword [rsi] LONG $0x4e10fac5; BYTE $0x04 // vmovss xmm1, dword [rsi + 4] LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] @@ -53711,7 +55092,7 @@ LBB9_118: LONG $0x4610fac5; BYTE $0x1c // vmovss xmm0, dword [rsi + 28] LONG $0xd5930f41 // setae r13b LONG $0x422ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rdx + 28] - LONG $0xd7930f41 // setae r15b + LONG $0xd6930f41 // setae r14b LONG $0x4610fac5; BYTE $0x20 // vmovss xmm0, dword [rsi + 32] LONG $0x422ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rdx + 32] LONG $0x4610fac5; BYTE $0x24 // vmovss xmm0, dword [rsi + 36] @@ -53742,7 +55123,7 @@ LBB9_118: LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] LONG $0x422ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rdx + 68] LONG $0x4610fac5; BYTE $0x48 // vmovss xmm0, dword [rsi + 72] - LONG $0xd6930f41 // setae r14b + LONG $0xd7930f41 // setae r15b LONG $0x422ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rdx + 72] LONG $0x4610fac5; BYTE $0x4c // vmovss xmm0, dword [rsi + 76] LONG $0xd4930f41 // setae r12b @@ -53788,8 +55169,8 @@ LBB9_118: WORD $0xc000 // add al, al LONG $0x04244402 // add al, byte [rsp + 4] LONG $0x06e5c041 // shl r13b, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0845; BYTE $0xef // or r15b, r13b + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0845; BYTE $0xee // or r14b, r13b LONG $0x6cb60f44; WORD $0x0524 // movzx r13d, byte [rsp + 5] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0841; BYTE $0xc5 // or r13b, al @@ -53819,17 +55200,17 @@ LBB9_118: LONG $0x06e1c041 // shl r9b, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0e // add r14b, byte [rsp + 14] + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x0e // add r15b, byte [rsp + 14] LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0845; BYTE $0xfc // or r12b, r15b LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -53837,12 +55218,12 @@ LBB9_118: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc0 // or r8b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -53867,23 +55248,22 @@ LBB9_118: LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xc7 // or dil, al WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x02468845 // mov byte [r14 + 2], r8b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x02478845 // mov byte [r15 + 2], r8b + LONG $0x037f8841 // mov byte [r15 + 3], dil LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB9_118 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB9_148 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB9_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_122: +LBB9_152: LONG $0x0410fac5; BYTE $0x8e // vmovss xmm0, dword [rsi + 4*rcx] LONG $0x042ef8c5; BYTE $0x8a // vucomiss xmm0, dword [rdx + 4*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -53891,71 +55271,90 @@ LBB9_122: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_122 - JMP LBB9_123 - -LBB9_57: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_61 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_59: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_59 - LONG $0x01c68349 // add r14, 1 - -LBB9_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_65 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB9_63: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_152 + JMP LBB9_153 + +LBB9_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 + WORD $0x8548; BYTE $0xc0 // test rax, rax + JLE LBB9_74 + WORD $0x634d; BYTE $0xe1 // movsxd r12, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB9_72: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0x000000bf; BYTE $0x00 // mov edi, 0 + LONG $0xffd78040 // adc dil, -1 + LONG $0x24448d49; BYTE $0x07 // lea rax, [r12 + 7] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x03f8c148 // sar rax, 3 + LONG $0x34b60f45; BYTE $0x07 // movzx r14d, byte [r15 + rax] + QUAD $0x00000000c53c8d44 // lea r15d, [8*rax] + WORD $0x8944; BYTE $0xe1 // mov ecx, r12d + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x3044; BYTE $0xf7 // xor dil, r14b + WORD $0x2040; BYTE $0xfb // and bl, dil + WORD $0x3044; BYTE $0xf3 // xor bl, r14b + LONG $0x001c8841 // mov byte [r8 + rax], bl + LONG $0x01c38349 // add r11, 1 + LONG $0x01c48349 // add r12, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB9_72 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB9_74: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_76: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_80 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB9_78: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x0246b60f // movzx eax, byte [rsi + 2] @@ -53975,7 +55374,7 @@ LBB9_63: LONG $0x2454930f; BYTE $0x04 // setae byte [rsp + 4] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7930f41 // setae r15b + LONG $0xd6930f41 // setae r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x2454930f; BYTE $0x07 // setae byte [rsp + 7] @@ -53990,7 +55389,7 @@ LBB9_63: LONG $0xd3930f41 // setae r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6930f41 // setae r14b + LONG $0xd7930f41 // setae r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] LONG $0x2454930f; BYTE $0x05 // setae byte [rsp + 5] @@ -54050,12 +55449,12 @@ LBB9_63: WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] LONG $0xd0930f41 // setae r8b WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x30244c02 // add cl, byte [rsp + 48] WORD $0xc889 // mov eax, ecx LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al @@ -54077,26 +55476,26 @@ LBB9_63: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x06 // movzx edi, byte [rsp + 6] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0d // add r12b, byte [rsp + 13] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -54104,12 +55503,12 @@ LBB9_63: LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al @@ -54135,23 +55534,22 @@ LBB9_63: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB9_63 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB9_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB9_78 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB9_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_67: +LBB9_82: LONG $0x0e04b60f // movzx eax, byte [rsi + rcx] WORD $0x043a; BYTE $0x0a // cmp al, byte [rdx + rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -54159,73 +55557,87 @@ LBB9_67: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_67 - JMP LBB9_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_82 + JMP LBB9_153 -LBB9_90: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_94 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB9_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB9_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_92 - LONG $0x01c68349 // add r14, 1 +LBB9_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd39d0f41 // setge r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB9_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_98 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 +LBB9_116: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 -LBB9_96: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_118: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_122 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_120: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] LONG $0x24549d0f; BYTE $0x14 // setge byte [rsp + 20] @@ -54249,7 +55661,7 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x09 // setge byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd09d0f41 // setge r8b + LONG $0xd79d0f40 // setge dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd39d0f41 // setge r11b @@ -54289,7 +55701,7 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x0b // setge byte [rsp + 11] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] + LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd19d0f41 // setge r9b @@ -54298,10 +55710,10 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x13 // setge byte [rsp + 19] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] + LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] + LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] LONG $0x24549d0f; BYTE $0x0f // setge byte [rsp + 15] @@ -54316,10 +55728,10 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x11 // setge byte [rsp + 17] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] - LONG $0xd79d0f40 // setge dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09d0f41 // setge r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -54328,34 +55740,34 @@ LBB9_96: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -54368,22 +55780,23 @@ LBB9_96: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -54400,26 +55813,25 @@ LBB9_96: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_96 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_120 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_100: +LBB9_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -54427,19 +55839,19 @@ LBB9_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_100 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_124 -LBB9_123: +LBB9_153: SUBQ $8, SP RET @@ -54487,82 +55899,95 @@ TEXT ·_comparison_greater_equal_arr_scalar_avx2(SB), $1384-48 MOVQ BP, 1344(SP) LEAQ LCDATA7<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB10_15 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB10_24 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB10_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB10_81 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB10_97 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB10_194 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_13 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_11: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_11 - LONG $0x01c38349 // add r11, 1 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB10_113 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB10_130 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB10_209 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_15 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_13 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_12: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_12 LBB10_13: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_14 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB10_115: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 + +LBB10_15: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_19 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + +LBB10_17: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000982494930f // setae byte [rsp + 152] + QUAD $0x000000a02494930f // setae byte [rsp + 160] LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd2930f41 // setae r10b LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6930f41 // setae r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000a02494930f // setae byte [rsp + 160] + QUAD $0x000000a82494930f // setae byte [rsp + 168] LONG $0x106e3944 // cmp dword [rsi + 16], r13d - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x930f; BYTE $0xd0 // setae al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d WORD $0x930f; BYTE $0xd3 // setae bl LONG $0x206e3944 // cmp dword [rsi + 32], r13d - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + QUAD $0x000000882494930f // setae byte [rsp + 136] LONG $0x246e3944 // cmp dword [rsi + 36], r13d LONG $0xd7930f40 // setae dil LONG $0x286e3944 // cmp dword [rsi + 40], r13d @@ -54574,33 +55999,33 @@ LBB10_115: LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4930f41 // setae r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x930f; BYTE $0xd1 // setae cl + WORD $0x930f; BYTE $0xd2 // setae dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x446e3944 // cmp dword [rsi + 68], r13d + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0x486e3944 // cmp dword [rsi + 72], r13d - QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7930f41 // setae r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] LONG $0x706e3944 // cmp dword [rsi + 112], r13d QUAD $0x000001402494930f // setae byte [rsp + 320] LONG $0x746e3944 // cmp dword [rsi + 116], r13d @@ -54608,168 +56033,186 @@ LBB10_115: LONG $0x786e3944 // cmp dword [rsi + 120], r13d LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x930f; BYTE $0xd2 // setae dl + WORD $0x930f; BYTE $0xd1 // setae cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] WORD $0xc789 // mov edi, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB10_115 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_118 - JMP LBB10_194 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + JNE LBB10_17 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB10_15: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB10_16 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB10_150 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB10_166 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB10_194 - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fbc5 // vmovsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_31 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_29: +LBB10_19: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_148 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_22 + +LBB10_24: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB10_25 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB10_169 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB10_186 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB10_209 + WORD $0x8b4c; BYTE $0x22 // mov r12, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_49 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB10_48: LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] LONG $0x08c68348 // add rsi, 8 LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_29 - LONG $0x01c38349 // add r11, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB10_48 -LBB10_31: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_32 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB10_183: +LBB10_49: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 + +LBB10_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_55 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x0000009824a4894c // mov qword [rsp + 152], r12 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB10_53: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] LONG $0x5610fbc5; BYTE $0x08 // vmovsd xmm2, qword [rsi + 8] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 WORD $0x930f; BYTE $0xd2 // setae dl LONG $0x4e10fbc5; BYTE $0x10 // vmovsd xmm1, qword [rsi + 16] @@ -54783,16 +56226,16 @@ LBB10_183: LONG $0xd1930f41 // setae r9b LONG $0x4e10fbc5; BYTE $0x28 // vmovsd xmm1, qword [rsi + 40] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - QUAD $0x000000a02494930f // setae byte [rsp + 160] + QUAD $0x000000a82494930f // setae byte [rsp + 168] LONG $0x4e10fbc5; BYTE $0x30 // vmovsd xmm1, qword [rsi + 48] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0x4e10fbc5; BYTE $0x38 // vmovsd xmm1, qword [rsi + 56] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + QUAD $0x000000882494930f // setae byte [rsp + 136] LONG $0x4e10fbc5; BYTE $0x40 // vmovsd xmm1, qword [rsi + 64] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x4e10fbc5; BYTE $0x48 // vmovsd xmm1, qword [rsi + 72] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0xd2930f41 // setae r10b @@ -54804,21 +56247,21 @@ LBB10_183: LONG $0xd7930f41 // setae r15b LONG $0x4e10fbc5; BYTE $0x60 // vmovsd xmm1, qword [rsi + 96] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - WORD $0x930f; BYTE $0xd0 // setae al + WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x4e10fbc5; BYTE $0x68 // vmovsd xmm1, qword [rsi + 104] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0x4e10fbc5; BYTE $0x70 // vmovsd xmm1, qword [rsi + 112] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] LONG $0x4e10fbc5; BYTE $0x78 // vmovsd xmm1, qword [rsi + 120] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] QUAD $0x000000808e10fbc5 // vmovsd xmm1, qword [rsi + 128] QUAD $0x000000889610fbc5 // vmovsd xmm2, qword [rsi + 136] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 QUAD $0x000000908e10fbc5 // vmovsd xmm1, qword [rsi + 144] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 QUAD $0x000000989610fbc5 // vmovsd xmm2, qword [rsi + 152] LONG $0xd3930f41 // setae r11b @@ -54830,13 +56273,13 @@ LBB10_183: LONG $0xd4930f41 // setae r12b LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 QUAD $0x000000b08e10fbc5 // vmovsd xmm1, qword [rsi + 176] - QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 QUAD $0x000000b89610fbc5 // vmovsd xmm2, qword [rsi + 184] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + QUAD $0x000000802494930f // setae byte [rsp + 128] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 QUAD $0x000000c08e10fbc5 // vmovsd xmm1, qword [rsi + 192] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 QUAD $0x000000c89610fbc5 // vmovsd xmm2, qword [rsi + 200] LONG $0xd5930f41 // setae r13b @@ -54845,1061 +56288,943 @@ LBB10_183: QUAD $0x000001202494930f // setae byte [rsp + 288] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 QUAD $0x000000d89610fbc5 // vmovsd xmm2, qword [rsi + 216] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 QUAD $0x000000e08e10fbc5 // vmovsd xmm1, qword [rsi + 224] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 QUAD $0x000000e89610fbc5 // vmovsd xmm2, qword [rsi + 232] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 QUAD $0x000000f08e10fbc5 // vmovsd xmm1, qword [rsi + 240] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 QUAD $0x000000f89610fbc5 // vmovsd xmm2, qword [rsi + 248] QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 + LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 + WORD $0x930f; BYTE $0xd0 // setae al + WORD $0xd200 // add dl, dl + LONG $0x90249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 144] + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xd7 // or dil, dl + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x04e1c041 // shl r9b, 4 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000a82494b60f // movzx edx, byte [rsp + 168] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xca // or dl, r9b + WORD $0xd789 // mov edi, edx + LONG $0x44b60f44; WORD $0x6024 // movzx r8d, byte [rsp + 96] + LONG $0x06e0c041 // shl r8b, 6 + QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + LONG $0x24540244; BYTE $0x50 // add r10b, byte [rsp + 80] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0x0844; BYTE $0xd3 // or bl, r10b + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xf9 // or cl, r15b + WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xcb08 // or bl, cl + WORD $0xdf89 // mov edi, ebx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + LONG $0x245c0244; BYTE $0x30 // add r11b, byte [rsp + 48] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xf4 // or r12b, r14b + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x247cb60f; BYTE $0x58 // movzx edi, byte [rsp + 88] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xfd // or r13b, dil + WORD $0x8841; BYTE $0x16 // mov byte [r14], dl + WORD $0x0841; BYTE $0xcd // or r13b, cl + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xc900 // add cl, cl + LONG $0x20248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 288] + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd108 // or cl, dl + QUAD $0x000001402494b60f // movzx edx, byte [rsp + 320] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xca08 // or dl, cl + LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + LONG $0x026e8845 // mov byte [r14 + 2], r13b + WORD $0xd008 // or al, dl + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB10_53 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB10_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x6ef9c1c4; BYTE $0xc4 // vmovq xmm0, r12 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_203 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_205 + +LBB10_2: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB10_58 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB10_209 + WORD $0x8a44; BYTE $0x2a // mov r13b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_5 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_88 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB10_94: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_94 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB10_90 + JMP LBB10_209 + +LBB10_25: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB10_150 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB10_209 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_33 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_31 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_30: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_30 + +LBB10_31: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 + +LBB10_33: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_37 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + +LBB10_35: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + QUAD $0x000000a02494930f // setae byte [rsp + 160] + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0xd2930f41 // setae r10b + LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0xd6930f41 // setae r14b + LONG $0x186e394c // cmp qword [rsi + 24], r13 + QUAD $0x000000a82494930f // setae byte [rsp + 168] + LONG $0x206e394c // cmp qword [rsi + 32], r13 + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x286e394c // cmp qword [rsi + 40], r13 + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x306e394c // cmp qword [rsi + 48], r13 + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x386e394c // cmp qword [rsi + 56], r13 + WORD $0x930f; BYTE $0xd3 // setae bl + LONG $0x406e394c // cmp qword [rsi + 64], r13 + QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x486e394c // cmp qword [rsi + 72], r13 + LONG $0xd7930f40 // setae dil + LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0xd0930f41 // setae r8b + LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0xd1930f41 // setae r9b + LONG $0x606e394c // cmp qword [rsi + 96], r13 + LONG $0xd3930f41 // setae r11b + LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0xd4930f41 // setae r12b + LONG $0x706e394c // cmp qword [rsi + 112], r13 + QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x786e394c // cmp qword [rsi + 120], r13 + WORD $0x930f; BYTE $0xd2 // setae dl + LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 + LONG $0xd7930f41 // setae r15b + LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 + LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 + QUAD $0x000001402494930f // setae byte [rsp + 320] + LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + QUAD $0x000001202494930f // setae byte [rsp + 288] + LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0xd02ef9c5 // vucomisd xmm2, xmm0 + LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 WORD $0x930f; BYTE $0xd1 // setae cl - WORD $0xd200 // add dl, dl - LONG $0x78245402 // add dl, byte [rsp + 120] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl - LONG $0x03e0c041 // shl r8b, 3 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x04e1c041 // shl r9b, 4 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xca // or dl, r9b - QUAD $0x0000802484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 128] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x60 // add r10b, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xd3 // or bl, r10b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x0840; BYTE $0xd7 // or dil, dl - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al - WORD $0x0045; BYTE $0xdb // add r11b, r11b - LONG $0x245c0244; BYTE $0x28 // add r11b, byte [rsp + 40] LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0x0844; BYTE $0xd0 // or al, r10b + WORD $0xc789 // mov edi, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - WORD $0xd308 // or bl, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xd5 // or r13b, dl - QUAD $0x0000011024948b48 // mov rdx, qword [rsp + 272] - WORD $0x8840; BYTE $0x3a // mov byte [rdx], dil - WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xc308 // or bl, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x5a88; BYTE $0x01 // mov byte [rdx + 1], bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - LONG $0x026a8844 // mov byte [rdx + 2], r13b - WORD $0xc108 // or cl, al - WORD $0x4a88; BYTE $0x03 // mov byte [rdx + 3], cl - LONG $0x04c28348 // add rdx, 4 - QUAD $0x0000011024948948 // mov qword [rsp + 272], rdx - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB10_183 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_186 - JMP LBB10_194 - -LBB10_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB10_33 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB10_194 - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_5 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - WORD $0x894d; BYTE $0xdd // mov r13, r11 - -LBB10_59: - WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_59 - LONG $0x01c58349 // add r13, 1 - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_62 - -LBB10_63: - LONG $0x20ff8349 // cmp r15, 32 - LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000026024bc894c // mov qword [rsp + 608], r15 - JB LBB10_64 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc5 // cmp r13, rax - JAE LBB10_67 - QUAD $0x00000000bd048d4a // lea rax, [4*r15] - WORD $0x014c; BYTE $0xe8 // add rax, r13 - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB10_67 - -LBB10_64: - WORD $0xc031 // xor eax, eax - QUAD $0x000001a024848948 // mov qword [rsp + 416], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x0000016824ac894c // mov qword [rsp + 360], r13 - -LBB10_70: - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x000001a024ac2b4c // sub r13, qword [rsp + 416] - QUAD $0x0000009824ac894c // mov qword [rsp + 152], r13 - -LBB10_71: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b - LONG $0xd09d0f41 // setge r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd79d0f41 // setge r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b - LONG $0xd59d0f41 // setge r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b - LONG $0xd39d0f41 // setge r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b - QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b - WORD $0x9d0f; BYTE $0xd2 // setge dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b - LONG $0xd69d0f40 // setge sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b - LONG $0xd79d0f40 // setge dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b - LONG $0xd29d0f41 // setge r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b - LONG $0xd49d0f41 // setge r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b - LONG $0xd19d0f41 // setge r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b - QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x11713844 // cmp byte [rcx + 17], r14b - QUAD $0x0000008824949d0f // setge byte [rsp + 136] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x13713844 // cmp byte [rcx + 19], r14b - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x14713844 // cmp byte [rcx + 20], r14b - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x15713844 // cmp byte [rcx + 21], r14b - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd69d0f41 // setge r14b - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x0000011024949d0f // setge byte [rsp + 272] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x20 // add r8b, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b - WORD $0xd200 // add dl, dl - LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xc000 // add al, al - LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000016824b48b48 // mov rsi, qword [rsp + 360] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + LONG $0x20244402 // add al, byte [rsp + 32] WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xd308 // or bl, dl - WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000016824b48948 // mov qword [rsp + 360], rsi + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0x04c68349 // add r14, 4 QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB10_71 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000026024bc8b4c // mov r15, qword [rsp + 608] - JMP LBB10_73 - -LBB10_16: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB10_124 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB10_194 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_22 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_20: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_20 - LONG $0x01c38349 // add r11, 1 + JNE LBB10_35 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB10_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_23 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - -LBB10_141: - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000982494930f // setae byte [rsp + 152] - LONG $0x086e394c // cmp qword [rsi + 8], r13 +LBB10_37: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_167 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_40 + +LBB10_113: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_119 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_117 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_116: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_116 + +LBB10_117: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 + +LBB10_119: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_123 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + +LBB10_121: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd2930f41 // setae r10b - LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd6930f41 // setae r14b - LONG $0x186e394c // cmp qword [rsi + 24], r13 + LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w + QUAD $0x000000a82494930f // setae byte [rsp + 168] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x206e394c // cmp qword [rsi + 32], r13 - QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x306e394c // cmp qword [rsi + 48], r13 - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x386e394c // cmp qword [rsi + 56], r13 + LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x406e394c // cmp qword [rsi + 64], r13 - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x486e394c // cmp qword [rsi + 72], r13 + LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w + QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w LONG $0xd7930f40 // setae dil - LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd0930f41 // setae r8b - LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w LONG $0xd1930f41 // setae r9b - LONG $0x606e394c // cmp qword [rsi + 96], r13 + LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w LONG $0xd3930f41 // setae r11b - LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd4930f41 // setae r12b - LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w QUAD $0x000000882494930f // setae byte [rsp + 136] - LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w + WORD $0x930f; BYTE $0xd2 // setae dl + LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 + LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 + LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w LONG $0xd7930f41 // setae r15b - LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 + LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 + LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] - LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x930f; BYTE $0xd2 // setae dl + LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w + WORD $0x930f; BYTE $0xd1 // setae cl + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xd0 // or al, r10b + WORD $0xc789 // mov edi, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000008824bcb60f // movzx edi, byte [rsp + 136] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xc308 // or bl, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xc000 // add al, al + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x40c68348 // add rsi, 64 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + JNE LBB10_121 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB10_123: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_128 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_126 + +LBB10_130: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_136 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_134 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_133: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_133 + +LBB10_134: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 + +LBB10_136: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_140 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + +LBB10_138: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + LONG $0x2e394466 // cmp word [rsi], r13w + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w + LONG $0xd29d0f41 // setge r10b + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w + LONG $0xd69d0f41 // setge r14b + LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w + QUAD $0x000000a824949d0f // setge byte [rsp + 168] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w + WORD $0x9d0f; BYTE $0xd0 // setge al + LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w + WORD $0x9d0f; BYTE $0xd3 // setge bl + LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w + LONG $0xd79d0f40 // setge dil + LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w + LONG $0xd09d0f41 // setge r8b + LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w + LONG $0xd19d0f41 // setge r9b + LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w + LONG $0xd39d0f41 // setge r11b + LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w + LONG $0xd49d0f41 // setge r12b + LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w + LONG $0xd79d0f41 // setge r15b + LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w + QUAD $0x0000012024949d0f // setge byte [rsp + 288] + LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w + LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] + LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w + WORD $0x9d0f; BYTE $0xd1 // setge cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] WORD $0xc789 // mov edi, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl + LONG $0x01568841 // mov byte [r14 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03538841 // mov byte [r11 + 3], dl - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c38349 // add r11, 4 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB10_141 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_144 - JMP LBB10_194 - -LBB10_81: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_85 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_83: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_83 - LONG $0x01c38349 // add r11, 1 - -LBB10_85: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_86 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB10_88: - LONG $0x2e394466 // cmp word [rsi], r13w - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0xd2930f41 // setae r10b - LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w - LONG $0xd6930f41 // setae r14b - LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w - QUAD $0x000000982494930f // setae byte [rsp + 152] - LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w - WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w - LONG $0xd7930f40 // setae dil - LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w - LONG $0xd0930f41 // setae r8b - LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w - LONG $0xd1930f41 // setae r9b - LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w - LONG $0xd3930f41 // setae r11b - LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w - LONG $0xd4930f41 // setae r12b - LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - QUAD $0x000000882494930f // setae byte [rsp + 136] - LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w - LONG $0xd7930f41 // setae r15b - LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w - QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w - QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w - LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] - LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w - WORD $0x930f; BYTE $0xd2 // setae dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x40c68348 // add rsi, 64 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB10_88 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_91 - JMP LBB10_194 - -LBB10_97: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_101 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_99: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_99 - LONG $0x01c38349 // add r11, 1 - -LBB10_101: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_102 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB10_104: - LONG $0x2e394466 // cmp word [rsi], r13w - QUAD $0x0000009824949d0f // setge byte [rsp + 152] - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0xd29d0f41 // setge r10b - LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w - LONG $0xd69d0f41 // setge r14b - LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w - WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w - LONG $0xd79d0f40 // setge dil - LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w - LONG $0xd09d0f41 // setge r8b - LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w - LONG $0xd19d0f41 // setge r9b - LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w - LONG $0xd39d0f41 // setge r11b - LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w - LONG $0xd49d0f41 // setge r12b - LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - QUAD $0x0000008824949d0f // setge byte [rsp + 136] - LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w - LONG $0xd79d0f41 // setge r15b - LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w - QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w - QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w - LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] - LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x40c68348 // add rsi, 64 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB10_104 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_107 - JMP LBB10_194 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x40c68348 // add rsi, 64 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + JNE LBB10_138 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB10_150: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_154 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_152: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_152 - LONG $0x01c38349 // add r11, 1 +LBB10_140: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_146 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_143 + +LBB10_169: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_175 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_173 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_172: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_172 -LBB10_154: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_155 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - -LBB10_157: +LBB10_173: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 + +LBB10_175: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_179 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + +LBB10_177: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x0000009824949d0f // setge byte [rsp + 152] + QUAD $0x000000a024949d0f // setge byte [rsp + 160] LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd29d0f41 // setge r10b LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd69d0f41 // setge r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000a024949d0f // setge byte [rsp + 160] + QUAD $0x000000a824949d0f // setge byte [rsp + 168] LONG $0x206e394c // cmp qword [rsi + 32], r13 - QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x9d0f; BYTE $0xd0 // setge al LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x9d0f; BYTE $0xd3 // setge bl LONG $0x406e394c // cmp qword [rsi + 64], r13 - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + QUAD $0x0000008824949d0f // setge byte [rsp + 136] LONG $0x486e394c // cmp qword [rsi + 72], r13 LONG $0xd79d0f40 // setge dil LONG $0x506e394c // cmp qword [rsi + 80], r13 @@ -55911,33 +57236,33 @@ LBB10_157: LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd49d0f41 // setge r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + QUAD $0x0000009024949d0f // setge byte [rsp + 144] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x9d0f; BYTE $0xd1 // setge cl + WORD $0x9d0f; BYTE $0xd2 // setge dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd79d0f41 // setge r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 QUAD $0x0000014024949d0f // setge byte [rsp + 320] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 @@ -55945,160 +57270,178 @@ LBB10_157: LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x9d0f; BYTE $0xd2 // setge dl + WORD $0x9d0f; BYTE $0xd1 // setge cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xc789 // mov edi, eax LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] WORD $0xc789 // mov edi, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] - WORD $0x1888 // mov byte [rax], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0x4888; BYTE $0x01 // mov byte [rax + 1], cl - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xca08 // or dl, cl - LONG $0x02788844 // mov byte [rax + 2], r15b - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB10_157 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_160 - JMP LBB10_194 + LONG $0x04c68349 // add r14, 4 + QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + JNE LBB10_177 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB10_166: - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0210fac5 // vmovss xmm0, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_170 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB10_179: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_184 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_182 -LBB10_168: +LBB10_186: + WORD $0x8b44; BYTE $0x22 // mov r12d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_192 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_190 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB10_189: LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] LONG $0x04c68348 // add rsi, 4 LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_168 - LONG $0x01c38349 // add r11, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB10_189 -LBB10_170: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_171 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 +LBB10_190: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 -LBB10_173: +LBB10_192: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_196 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x0000009824a48944 // mov dword [rsp + 152], r12d + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB10_194: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] LONG $0x5610fac5; BYTE $0x04 // vmovss xmm2, dword [rsi + 4] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 WORD $0x930f; BYTE $0xd2 // setae dl LONG $0x4e10fac5; BYTE $0x08 // vmovss xmm1, dword [rsi + 8] @@ -56112,16 +57455,16 @@ LBB10_173: LONG $0xd1930f41 // setae r9b LONG $0x4e10fac5; BYTE $0x14 // vmovss xmm1, dword [rsi + 20] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - QUAD $0x000000a02494930f // setae byte [rsp + 160] + QUAD $0x000000a82494930f // setae byte [rsp + 168] LONG $0x4e10fac5; BYTE $0x18 // vmovss xmm1, dword [rsi + 24] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0x4e10fac5; BYTE $0x1c // vmovss xmm1, dword [rsi + 28] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + QUAD $0x000000882494930f // setae byte [rsp + 136] LONG $0x4e10fac5; BYTE $0x20 // vmovss xmm1, dword [rsi + 32] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x4e10fac5; BYTE $0x24 // vmovss xmm1, dword [rsi + 36] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0xd2930f41 // setae r10b @@ -56133,21 +57476,21 @@ LBB10_173: LONG $0xd7930f41 // setae r15b LONG $0x4e10fac5; BYTE $0x30 // vmovss xmm1, dword [rsi + 48] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - WORD $0x930f; BYTE $0xd0 // setae al + WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x4e10fac5; BYTE $0x34 // vmovss xmm1, dword [rsi + 52] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0x4e10fac5; BYTE $0x38 // vmovss xmm1, dword [rsi + 56] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] LONG $0x4e10fac5; BYTE $0x3c // vmovss xmm1, dword [rsi + 60] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] LONG $0x4e10fac5; BYTE $0x40 // vmovss xmm1, dword [rsi + 64] LONG $0x5610fac5; BYTE $0x44 // vmovss xmm2, dword [rsi + 68] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x48 // vmovss xmm1, dword [rsi + 72] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 LONG $0x5610fac5; BYTE $0x4c // vmovss xmm2, dword [rsi + 76] LONG $0xd3930f41 // setae r11b @@ -56159,13 +57502,13 @@ LBB10_173: LONG $0xd4930f41 // setae r12b LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x58 // vmovss xmm1, dword [rsi + 88] - QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 LONG $0x5610fac5; BYTE $0x5c // vmovss xmm2, dword [rsi + 92] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + QUAD $0x000000802494930f // setae byte [rsp + 128] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x60 // vmovss xmm1, dword [rsi + 96] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 LONG $0x5610fac5; BYTE $0x64 // vmovss xmm2, dword [rsi + 100] LONG $0xd5930f41 // setae r13b @@ -56174,13 +57517,13 @@ LBB10_173: QUAD $0x000001202494930f // setae byte [rsp + 288] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 LONG $0x5610fac5; BYTE $0x6c // vmovss xmm2, dword [rsi + 108] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x70 // vmovss xmm1, dword [rsi + 112] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 LONG $0x5610fac5; BYTE $0x74 // vmovss xmm2, dword [rsi + 116] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x4e10fac5; BYTE $0x78 // vmovss xmm1, dword [rsi + 120] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] @@ -56191,227 +57534,753 @@ LBB10_173: LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] LONG $0x80ee8348 // sub rsi, -128 LONG $0xd02ef8c5 // vucomiss xmm2, xmm0 - WORD $0x930f; BYTE $0xd1 // setae cl + WORD $0x930f; BYTE $0xd0 // setae al WORD $0xd200 // add dl, dl - LONG $0x78245402 // add dl, byte [rsp + 120] + LONG $0x90249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 144] LONG $0x02e7c040 // shl dil, 2 WORD $0x0840; BYTE $0xd7 // or dil, dl LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil LONG $0x04e1c041 // shl r9b, 4 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] + QUAD $0x000000a82494b60f // movzx edx, byte [rsp + 168] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 WORD $0x0844; BYTE $0xca // or dl, r9b - QUAD $0x0000802484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 128] + WORD $0xd789 // mov edi, edx + LONG $0x44b60f44; WORD $0x6024 // movzx r8d, byte [rsp + 96] LONG $0x06e0c041 // shl r8b, 6 - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0844; BYTE $0xc2 // or dl, r8b WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x60 // add r10b, byte [rsp + 96] + LONG $0x24540244; BYTE $0x50 // add r10b, byte [rsp + 80] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0844; BYTE $0xd3 // or bl, r10b LONG $0x03e7c041 // shl r15b, 3 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x0840; BYTE $0xd7 // or dil, dl - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xf9 // or cl, r15b + WORD $0x0840; BYTE $0xfa // or dl, dil + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xcb08 // or bl, cl + WORD $0xdf89 // mov edi, ebx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + WORD $0xcb08 // or bl, cl WORD $0x0045; BYTE $0xdb // add r11b, r11b - LONG $0x245c0244; BYTE $0x28 // add r11b, byte [rsp + 40] + LONG $0x245c0244; BYTE $0x30 // add r11b, byte [rsp + 48] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xde // or r14b, r11b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x247cb60f; BYTE $0x58 // movzx edi, byte [rsp + 88] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xfd // or r13b, dil + WORD $0x8841; BYTE $0x16 // mov byte [r14], dl + WORD $0x0841; BYTE $0xcd // or r13b, cl + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xc900 // add cl, cl + LONG $0x20248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 288] + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd108 // or cl, dl + QUAD $0x000001402494b60f // movzx edx, byte [rsp + 320] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xca08 // or dl, cl + LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + LONG $0x026e8845 // mov byte [r14 + 2], r13b + WORD $0xd008 // or al, dl + LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB10_194 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x0000009824a48b44 // mov r12d, dword [rsp + 152] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB10_196: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x6e79c1c4; BYTE $0xc4 // vmovd xmm0, r12d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_201 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_199 + +LBB10_58: + WORD $0x8a44; BYTE $0x2a // mov r13b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_59 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_61 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB10_67: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + LONG $0x000000be; BYTE $0x00 // mov esi, 0 + LONG $0xffd68040 // adc sil, -1 + LONG $0x075a8d48 // lea rbx, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xda490f48 // cmovns rbx, rdx + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + WORD $0x3044; BYTE $0xce // xor sil, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x2040; BYTE $0xf0 // and al, sil + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_67 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB10_63 + JMP LBB10_209 + +LBB10_150: + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_156 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_154 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_153: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_153 + +LBB10_154: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + LONG $0x01c68349 // add r14, 1 + +LBB10_156: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_160 + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + +LBB10_158: + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0xd29d0f41 // setge r10b + LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0xd69d0f41 // setge r14b + LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d + QUAD $0x000000a824949d0f // setge byte [rsp + 168] + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x146e3944 // cmp dword [rsi + 20], r13d + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x186e3944 // cmp dword [rsi + 24], r13d + WORD $0x9d0f; BYTE $0xd0 // setge al + LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + WORD $0x9d0f; BYTE $0xd3 // setge bl + LONG $0x206e3944 // cmp dword [rsi + 32], r13d + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x246e3944 // cmp dword [rsi + 36], r13d + LONG $0xd79d0f40 // setge dil + LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0xd09d0f41 // setge r8b + LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0xd19d0f41 // setge r9b + LONG $0x306e3944 // cmp dword [rsi + 48], r13d + LONG $0xd39d0f41 // setge r11b + LONG $0x346e3944 // cmp dword [rsi + 52], r13d + LONG $0xd49d0f41 // setge r12b + LONG $0x386e3944 // cmp dword [rsi + 56], r13d + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x406e3944 // cmp dword [rsi + 64], r13d + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x446e3944 // cmp dword [rsi + 68], r13d + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x506e3944 // cmp dword [rsi + 80], r13d + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x546e3944 // cmp dword [rsi + 84], r13d + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x586e3944 // cmp dword [rsi + 88], r13d + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d + LONG $0xd79d0f41 // setge r15b + LONG $0x606e3944 // cmp dword [rsi + 96], r13d + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x686e3944 // cmp dword [rsi + 104], r13d + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x706e3944 // cmp dword [rsi + 112], r13d + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x746e3944 // cmp dword [rsi + 116], r13d + QUAD $0x0000012024949d0f // setge byte [rsp + 288] + LONG $0x786e3944 // cmp dword [rsi + 120], r13d + LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] + LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d + WORD $0x9d0f; BYTE $0xd1 // setge cl + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + QUAD $0x000000a024940244 // add r10b, byte [rsp + 160] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] + QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc2 // mov r10d, eax + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0x0844; BYTE $0xd0 // or al, r10b + WORD $0xc789 // mov edi, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - WORD $0xd308 // or bl, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xd5 // or r13b, dl - QUAD $0x0000011024948b48 // mov rdx, qword [rsp + 272] - WORD $0x8840; BYTE $0x3a // mov byte [rdx], dil - WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xc308 // or bl, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x5a88; BYTE $0x01 // mov byte [rdx + 1], bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] + WORD $0x8841; BYTE $0x1e // mov byte [r14], bl + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x01568841 // mov byte [r14 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x1c // movzx edx, byte [rsp + 28] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - LONG $0x026a8844 // mov byte [rdx + 2], r13b + WORD $0xd108 // or cl, dl WORD $0xc108 // or cl, al - WORD $0x4a88; BYTE $0x03 // mov byte [rdx + 3], cl - LONG $0x04c28348 // add rdx, 4 - QUAD $0x0000011024948948 // mov qword [rsp + 272], rdx + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x034e8841 // mov byte [r14 + 3], cl + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x04c68349 // add r14, 4 QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB10_173 - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_176 - JMP LBB10_194 + JNE LBB10_158 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB10_160: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_209 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB10_165 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_163 + +LBB10_5: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB10_91 + +LBB10_59: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB10_64 + +LBB10_88: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 + +LBB10_90: + LONG $0x01c68349 // add r14, 1 + +LBB10_91: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB10_92 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x246c8944; BYTE $0x1c // mov dword [rsp + 28], r13d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000260248c8948 // mov qword [rsp + 608], rcx + JB LBB10_96 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB10_99 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB10_99 + +LBB10_96: + WORD $0xc031 // xor eax, eax + QUAD $0x000001a024848948 // mov qword [rsp + 416], rax + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000016824b4894c // mov qword [rsp + 360], r14 + +LBB10_102: + QUAD $0x000001a0248c2b48 // sub rcx, qword [rsp + 416] + QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx + +LBB10_103: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x016e3844 // cmp byte [rsi + 1], r13b + LONG $0xd09d0f41 // setge r8b + LONG $0x026e3844 // cmp byte [rsi + 2], r13b + LONG $0xd69d0f41 // setge r14b + LONG $0x036e3844 // cmp byte [rsi + 3], r13b + LONG $0xd59d0f41 // setge r13b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x04 // cmp byte [rsi + 4], al + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x05 // cmp byte [rsi + 5], al + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x06 // cmp byte [rsi + 6], al + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x07 // cmp byte [rsi + 7], al + LONG $0xd39d0f41 // setge r11b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x08 // cmp byte [rsi + 8], al + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x09 // cmp byte [rsi + 9], al + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x0a // cmp byte [rsi + 10], al + LONG $0xd69d0f40 // setge sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd79d0f40 // setge dil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd29d0f41 // setge r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + LONG $0xd49d0f41 // setge r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000000a824949d0f // setge byte [rsp + 168] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd19d0f41 // setge r9b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x0000012024949d0f // setge byte [rsp + 288] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd79d0f41 // setge r15b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + QUAD $0x0000011024949d0f // setge byte [rsp + 272] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + LONG $0x24440244; BYTE $0x20 // add r8b, byte [rsp + 32] + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xd200 // add dl, dl + LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000a824b4b60f // movzx esi, byte [rsp + 168] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xd3 // or r11b, dl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] + QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + QUAD $0x0000016824bc8b48 // mov rdi, qword [rsp + 360] + WORD $0x8844; BYTE $0x1f // mov byte [rdi], r11b + QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014f8844 // mov byte [rdi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xc000 // add al, al + LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x027f8844 // mov byte [rdi + 2], r15b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000016824bc8948 // mov qword [rsp + 360], rdi + QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + JNE LBB10_103 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000260248c8b48 // mov rcx, qword [rsp + 608] + JMP LBB10_105 + +LBB10_92: + QUAD $0x0000016824b4894c // mov qword [rsp + 360], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB10_33: - WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_37 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB10_105: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB10_209 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB10_108 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB10_111 -LBB10_35: - WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b - LONG $0x01768d48 // lea rsi, [rsi + 1] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_35 - LONG $0x01c38349 // add r11, 1 +LBB10_61: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB10_209 -LBB10_37: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_38 +LBB10_63: + LONG $0x01c68349 // add r14, 1 + +LBB10_64: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 LONG $0x20ff8349 // cmp r15, 32 - LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000017024bc894c // mov qword [rsp + 368], r15 - JB LBB10_40 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 + JL LBB10_65 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x246c8944; BYTE $0x1c // mov dword [rsp + 28], r13d + QUAD $0x0000011824bc894c // mov qword [rsp + 280], r15 + QUAD $0x00000170248c8948 // mov qword [rsp + 368], rcx + JB LBB10_69 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JAE LBB10_43 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB10_43 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB10_72 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB10_72 -LBB10_40: +LBB10_69: WORD $0xc031 // xor eax, eax QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x00000168249c894c // mov qword [rsp + 360], r11 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x0000016824b4894c // mov qword [rsp + 360], r14 -LBB10_46: - QUAD $0x0000018024bc2b4c // sub r15, qword [rsp + 384] - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 +LBB10_75: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx -LBB10_47: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24343845 // cmp byte [r12], r14b +LBB10_76: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x24743845; BYTE $0x01 // cmp byte [r12 + 1], r14b + LONG $0x016e3844 // cmp byte [rsi + 1], r13b LONG $0xd0930f41 // setae r8b - LONG $0x24743845; BYTE $0x02 // cmp byte [r12 + 2], r14b - LONG $0xd7930f41 // setae r15b - LONG $0x24743845; BYTE $0x03 // cmp byte [r12 + 3], r14b + LONG $0x026e3844 // cmp byte [rsi + 2], r13b + LONG $0xd6930f41 // setae r14b + LONG $0x036e3844 // cmp byte [rsi + 3], r13b LONG $0xd5930f41 // setae r13b - LONG $0x24743845; BYTE $0x04 // cmp byte [r12 + 4], r14b - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x24743845; BYTE $0x05 // cmp byte [r12 + 5], r14b - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x24743845; BYTE $0x06 // cmp byte [r12 + 6], r14b - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x24743845; BYTE $0x07 // cmp byte [r12 + 7], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x04 // cmp byte [rsi + 4], al + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x05 // cmp byte [rsi + 5], al + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x06 // cmp byte [rsi + 6], al + QUAD $0x000000a02494930f // setae byte [rsp + 160] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x07 // cmp byte [rsi + 7], al LONG $0xd3930f41 // setae r11b - LONG $0x24743845; BYTE $0x08 // cmp byte [r12 + 8], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x08 // cmp byte [rsi + 8], al QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0x24743845; BYTE $0x09 // cmp byte [r12 + 9], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x09 // cmp byte [rsi + 9], al WORD $0x930f; BYTE $0xd2 // setae dl - LONG $0x24743845; BYTE $0x0a // cmp byte [r12 + 10], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4638; BYTE $0x0a // cmp byte [rsi + 10], al LONG $0xd6930f40 // setae sil - LONG $0x24743845; BYTE $0x0b // cmp byte [r12 + 11], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al LONG $0xd7930f40 // setae dil - LONG $0x24743845; BYTE $0x0c // cmp byte [r12 + 12], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al LONG $0xd2930f41 // setae r10b - LONG $0x24743845; BYTE $0x0d // cmp byte [r12 + 13], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al LONG $0xd4930f41 // setae r12b - LONG $0x0e713844 // cmp byte [rcx + 14], r14b - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x0f713844 // cmp byte [rcx + 15], r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000000a82494930f // setae byte [rsp + 168] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al LONG $0xd1930f41 // setae r9b - LONG $0x10713844 // cmp byte [rcx + 16], r14b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0x11713844 // cmp byte [rcx + 17], r14b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl QUAD $0x000000882494930f // setae byte [rsp + 136] - LONG $0x12713844 // cmp byte [rcx + 18], r14b - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x13713844 // cmp byte [rcx + 19], r14b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x14713844 // cmp byte [rcx + 20], r14b - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x15713844 // cmp byte [rcx + 21], r14b - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x16713844 // cmp byte [rcx + 22], r14b - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x17713844 // cmp byte [rcx + 23], r14b - LONG $0xd6930f41 // setae r14b + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd7930f41 // setae r15b LONG $0x1c245c8b // mov ebx, dword [rsp + 28] WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl QUAD $0x000001102494930f // setae byte [rsp + 272] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] @@ -56426,40 +58295,42 @@ LBB10_47: WORD $0x930f; BYTE $0xd3 // setae bl WORD $0x0045; BYTE $0xc0 // add r8b, r8b LONG $0x24440244; BYTE $0x20 // add r8b, byte [rsp + 32] + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e3c041 // shl r11b, 7 WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0845; BYTE $0xc7 // or r15b, r8b + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b WORD $0xd200 // add dl, dl LONG $0x40249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 320] LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b + WORD $0x0845; BYTE $0xf5 // or r13b, r14b LONG $0x02e6c040 // shl sil, 2 WORD $0x0840; BYTE $0xd6 // or sil, dl - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] WORD $0xe2c0; BYTE $0x04 // shl dl, 4 WORD $0x0844; BYTE $0xea // or dl, r13b WORD $0x8941; BYTE $0xd0 // mov r8d, edx + LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] LONG $0x03e7c040 // shl dil, 3 WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 WORD $0x0844; BYTE $0xc2 // or dl, r8b LONG $0x04e2c041 // shl r10b, 4 WORD $0x0841; BYTE $0xfa // or r10b, dil LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + QUAD $0x000000a824b4b60f // movzx esi, byte [rsp + 168] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xf1 // or r9b, sil WORD $0x0841; BYTE $0xd3 // or r11b, dl WORD $0x0845; BYTE $0xe1 // or r9b, r12b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xc000 // add al, al LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + QUAD $0x000000882494b60f // movzx edx, byte [rsp + 136] WORD $0xe2c0; BYTE $0x02 // shl dl, 2 WORD $0xc208 // or dl, al WORD $0xd689 // mov esi, edx @@ -56467,30 +58338,30 @@ LBB10_47: WORD $0xe2c0; BYTE $0x03 // shl dl, 3 WORD $0x0840; BYTE $0xf2 // or dl, sil WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] WORD $0xe2c0; BYTE $0x04 // shl dl, 4 WORD $0x0840; BYTE $0xf2 // or dl, sil WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 WORD $0x0840; BYTE $0xf2 // or dl, sil - QUAD $0x0000016824b48b48 // mov rsi, qword [rsp + 360] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xfe // or r14b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd6 // or r14b, dl - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x0000016824bc8b48 // mov rdi, qword [rsp + 360] + WORD $0x8844; BYTE $0x1f // mov byte [rdi], r11b + QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x014f8844 // mov byte [rdi + 1], r9b + WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xc000 // add al, al LONG $0x10248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 272] WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax @@ -56506,399 +58377,44 @@ LBB10_47: WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xd308 // or bl, dl WORD $0xc308 // or bl, al - LONG $0x02768844 // mov byte [rsi + 2], r14b - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - WORD $0x5e88; BYTE $0x03 // mov byte [rsi + 3], bl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - QUAD $0x0000016824b48948 // mov qword [rsp + 360], rsi + LONG $0x027f8844 // mov byte [rdi + 2], r15b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000016824bc8948 // mov qword [rsp + 360], rdi QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB10_47 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000017024bc8b4c // mov r15, qword [rsp + 368] - JMP LBB10_49 - -LBB10_124: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_128 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_126: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1b // movzx r8d, byte [r11 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1b3c8841 // mov byte [r11 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_126 - LONG $0x01c38349 // add r11, 1 - -LBB10_128: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_129 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x000000a824bc894c // mov qword [rsp + 168], r15 - -LBB10_131: - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x0000009824949d0f // setge byte [rsp + 152] - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd29d0f41 // setge r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d - LONG $0xd69d0f41 // setge r14b - LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x186e3944 // cmp dword [rsi + 24], r13d - WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x206e3944 // cmp dword [rsi + 32], r13d - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x246e3944 // cmp dword [rsi + 36], r13d - LONG $0xd79d0f40 // setge dil - LONG $0x286e3944 // cmp dword [rsi + 40], r13d - LONG $0xd09d0f41 // setge r8b - LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd19d0f41 // setge r9b - LONG $0x306e3944 // cmp dword [rsi + 48], r13d - LONG $0xd39d0f41 // setge r11b - LONG $0x346e3944 // cmp dword [rsi + 52], r13d - LONG $0xd49d0f41 // setge r12b - LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d - QUAD $0x0000008824949d0f // setge byte [rsp + 136] - LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d - LONG $0xd79d0f41 // setge r15b - LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x706e3944 // cmp dword [rsi + 112], r13d - QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d - QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x786e3944 // cmp dword [rsi + 120], r13d - LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] - LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x70 // add dil, byte [rsp + 112] - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1b // mov byte [r11], bl - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014b8841 // mov byte [r11 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001202484b60f // movzx eax, byte [rsp + 288] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027b8845 // mov byte [r11 + 2], r15b - LONG $0x03538841 // mov byte [r11 + 3], dl - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c38349 // add r11, 4 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB10_131 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JL LBB10_134 - JMP LBB10_194 - -LBB10_14: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_118: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_122 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_120 - -LBB10_32: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_186: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_188 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_190 - -LBB10_23: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_144: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_148 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_146 - -LBB10_86: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_91: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_95 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_93 - -LBB10_102: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_107: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_112 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_109 - -LBB10_155: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_160: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_164 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_162 - -LBB10_171: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_176: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_180 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_178 - -LBB10_38: - QUAD $0x00000168249c894c // mov qword [rsp + 360], r11 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - -LBB10_49: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_52 - WORD $0xf631 // xor esi, esi - JMP LBB10_55 - -LBB10_129: - WORD $0x894d; BYTE $0xde // mov r14, r11 - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - -LBB10_134: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_138 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_136 - -LBB10_5: - WORD $0x894d; BYTE $0xdd // mov r13, r11 - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JGE LBB10_63 + JNE LBB10_76 + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + QUAD $0x00000170248c8b48 // mov rcx, qword [rsp + 368] + JMP LBB10_78 -LBB10_62: - QUAD $0x0000016824ac894c // mov qword [rsp + 360], r13 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi +LBB10_65: + QUAD $0x0000016824b4894c // mov qword [rsp + 360], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB10_73: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_194 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_76 - WORD $0xf631 // xor esi, esi - JMP LBB10_79 +LBB10_78: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB10_209 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB10_81 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB10_84 -LBB10_122: +LBB10_148: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_123: +LBB10_149: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x17 // movzx r10d, byte [r15 + rdx] + LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 @@ -56906,7 +58422,7 @@ LBB10_123: WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x17048841 // mov byte [r15 + rdx], al + LONG $0x16048841 // mov byte [r14 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -56918,31 +58434,30 @@ LBB10_123: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x171c8841 // mov byte [r15 + rdx], bl + LONG $0x161c8841 // mov byte [r14 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB10_123 + JNE LBB10_149 -LBB10_120: +LBB10_22: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 WORD $0xc031 // xor eax, eax WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - JMP LBB10_192 + JMP LBB10_207 -LBB10_188: +LBB10_203: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_189: +LBB10_204: LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 LONG $0x000000b8; BYTE $0x00 // mov eax, 0 WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 @@ -56950,7 +58465,7 @@ LBB10_189: WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x4e10fbc5; BYTE $0x08 // vmovsd xmm1, qword [rsi + 8] LONG $0x10c68348 // add rsi, 16 @@ -56963,31 +58478,30 @@ LBB10_189: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_189 + JNE LBB10_204 -LBB10_190: +LBB10_205: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 LONG $0x0e10fbc5 // vmovsd xmm1, qword [rsi] WORD $0xc031 // xor eax, eax LONG $0xc82ef9c5 // vucomisd xmm1, xmm0 - JMP LBB10_192 + JMP LBB10_207 -LBB10_148: +LBB10_167: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_149: +LBB10_168: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x17 // movzx r10d, byte [r15 + rdx] + LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 @@ -56995,7 +58509,7 @@ LBB10_149: WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x17048841 // mov byte [r15 + rdx], al + LONG $0x16048841 // mov byte [r14 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -57007,30 +58521,29 @@ LBB10_149: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x171c8841 // mov byte [r15 + rdx], bl + LONG $0x161c8841 // mov byte [r14 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB10_149 + JNE LBB10_168 -LBB10_146: +LBB10_40: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 WORD $0xc031 // xor eax, eax WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - JMP LBB10_192 + JMP LBB10_207 -LBB10_95: +LBB10_128: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_96: +LBB10_129: LONG $0x2e394466 // cmp word [rsi], r13w LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x17 // movzx r10d, byte [r15 + rdx] + LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 @@ -57038,7 +58551,7 @@ LBB10_96: WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x17048841 // mov byte [r15 + rdx], al + LONG $0x16048841 // mov byte [r14 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] @@ -57050,30 +58563,29 @@ LBB10_96: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x171c8841 // mov byte [r15 + rdx], bl + LONG $0x161c8841 // mov byte [r14 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB10_96 + JNE LBB10_129 -LBB10_93: +LBB10_126: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 WORD $0xc031 // xor eax, eax LONG $0x2e394466 // cmp word [rsi], r13w - JMP LBB10_192 + JMP LBB10_207 -LBB10_112: +LBB10_146: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_113: +LBB10_147: LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -57081,7 +58593,7 @@ LBB10_113: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] @@ -57093,29 +58605,28 @@ LBB10_113: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_113 + JNE LBB10_147 -LBB10_109: +LBB10_143: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 LONG $0x2e394466 // cmp word [rsi], r13w - JMP LBB10_111 + JMP LBB10_145 -LBB10_164: +LBB10_184: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_165: +LBB10_185: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -57123,7 +58634,7 @@ LBB10_165: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -57135,30 +58646,29 @@ LBB10_165: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_165 + JNE LBB10_185 -LBB10_162: +LBB10_182: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - JMP LBB10_111 + JMP LBB10_145 -LBB10_180: +LBB10_201: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_181: +LBB10_202: LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 LONG $0x000000b8; BYTE $0x00 // mov eax, 0 WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 @@ -57166,7 +58676,7 @@ LBB10_181: WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x4e10fac5; BYTE $0x04 // vmovss xmm1, dword [rsi + 4] LONG $0x08c68348 // add rsi, 8 @@ -57179,18 +58689,18 @@ LBB10_181: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_181 + JNE LBB10_202 -LBB10_178: +LBB10_199: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 LONG $0x0e10fac5 // vmovss xmm1, dword [rsi] WORD $0xc031 // xor eax, eax LONG $0xc82ef8c5 // vucomiss xmm1, xmm0 -LBB10_192: +LBB10_207: WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 @@ -57201,75 +58711,20 @@ LBB10_192: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - JMP LBB10_193 - -LBB10_52: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - QUAD $0x00000168249c8b4c // mov r11, qword [rsp + 360] - -LBB10_53: - LONG $0x34343845 // cmp byte [r12 + rsi], r14b - LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 - WORD $0xd380; BYTE $0xff // adc bl, -1 - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0xf189 // mov ecx, esi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743845; BYTE $0x01 // cmp byte [r12 + rsi + 1], r14b - LONG $0x02768d48 // lea rsi, [rsi + 2] - LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 - WORD $0xd380; BYTE $0xff // adc bl, -1 - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB10_53 - WORD $0x0149; BYTE $0xf4 // add r12, rsi - -LBB10_55: - LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 - WORD $0xc031 // xor eax, eax - LONG $0x24343845 // cmp byte [r12], r14b - WORD $0xff14 // adc al, -1 - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - QUAD $0x0000016824848b4c // mov r8, qword [rsp + 360] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - JMP LBB10_57 + JMP LBB10_208 -LBB10_138: +LBB10_165: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB10_139: +LBB10_166: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -57277,7 +58732,7 @@ LBB10_139: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -57289,16 +58744,16 @@ LBB10_139: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3f148841 // mov byte [r15 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_139 + JNE LBB10_166 -LBB10_136: +LBB10_163: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 + JE LBB10_209 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d -LBB10_111: +LBB10_145: WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xda // mov rdx, r11 @@ -57311,28 +58766,29 @@ LBB10_111: WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al -LBB10_193: +LBB10_208: WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x161c8841 // mov byte [r14 + rdx], bl -LBB10_194: +LBB10_209: MOVQ 1344(SP), SP VZEROUPPER RET -LBB10_76: +LBB10_108: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d QUAD $0x00000168249c8b4c // mov r11, qword [rsp + 360] -LBB10_77: - LONG $0x34343845 // cmp byte [r12 + rsi], r14b +LBB10_109: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e2c3846 // cmp byte [rsi + r9], r13b WORD $0x9d0f; BYTE $0xd3 // setge bl WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl @@ -57341,8 +58797,8 @@ LBB10_77: WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x34743845; BYTE $0x01 // cmp byte [r12 + rsi + 1], r14b - LONG $0x02768d48 // lea rsi, [rsi + 2] + LONG $0x066c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r13b + LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x9d0f; BYTE $0xd3 // setge bl WORD $0xdbf6 // neg bl WORD $0xd330 // xor bl, dl @@ -57352,2012 +58808,2066 @@ LBB10_77: WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB10_77 - WORD $0x0149; BYTE $0xf4 // add r12, rsi + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB10_109 + WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB10_79: +LBB10_111: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_194 - LONG $0x24343845 // cmp byte [r12], r14b + JE LBB10_209 + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + QUAD $0x0000016824848b4c // mov r8, qword [rsp + 360] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + JMP LBB10_86 + +LBB10_81: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x00000168249c8b4c // mov r11, qword [rsp + 360] + +LBB10_82: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e2c3846 // cmp byte [rsi + r9], r13b + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x066c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r13b + LONG $0x02488d4c // lea r9, [rax + 2] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB10_82 + WORD $0x014c; BYTE $0xce // add rsi, r9 + +LBB10_84: + LONG $0x01c0f641 // test r8b, 1 + JE LBB10_209 + WORD $0xc031 // xor eax, eax + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 QUAD $0x0000016824848b4c // mov r8, qword [rsp + 360] LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al -LBB10_57: +LBB10_86: WORD $0x3040; BYTE $0xfb // xor bl, dil LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB10_194 + JMP LBB10_209 -LBB10_67: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB10_99: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000017024848948 // mov qword [rsp + 368], rax - QUAD $0x000001a024bc894c // mov qword [rsp + 416], r15 - QUAD $0x00000000bd048d4a // lea rax, [4*r15] - WORD $0x014c; BYTE $0xe8 // add rax, r13 + QUAD $0x000001a0248c8948 // mov qword [rsp + 416], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000016824848948 // mov qword [rsp + 360], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc5 // vmovd xmm0, r13d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00018024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 384], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x0000011024ac894c // mov qword [rsp + 272], r13 + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB10_68: +LBB10_100: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000017824848948 // mov qword [rsp + 376], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + QUAD $0x000000d824848948 // mov qword [rsp + 216], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rcx + 1] - WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x1644b60f; BYTE $0x02 // movzx eax, byte [rsi + rdx + 2] + LONG $0x0f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rcx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000240248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 576], xmm1 - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x0f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rcx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x0f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rcx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x0f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rcx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] - QUAD $0x0000010024948948 // mov qword [rsp + 256], rdx + LONG $0x0f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rcx + 6] + QUAD $0x000000c8248c8948 // mov qword [rsp + 200], rcx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x0f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rcx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax - LONG $0x20cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 544 - QUAD $0x000000f8249c8948 // mov qword [rsp + 248], rbx - WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02200d48; WORD $0x0000 // or rax, 544 + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02400d48; WORD $0x0000 // or rax, 576 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x02600d48; WORD $0x0000 // or rax, 608 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - WORD $0x8949; BYTE $0xcb // mov r11, rcx - LONG $0x80cb8149; WORD $0x0002; BYTE $0x00 // or r11, 640 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + WORD $0x8949; BYTE $0xdd // mov r13, rbx + LONG $0x60cd8149; WORD $0x0002; BYTE $0x00 // or r13, 608 + QUAD $0x0000009824ac894c // mov qword [rsp + 152], r13 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02800d48; WORD $0x0000 // or rax, 640 + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02a00d48; WORD $0x0000 // or rax, 672 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02c00d48; WORD $0x0000 // or rax, 704 + WORD $0x8949; BYTE $0xc6 // mov r14, rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02e00d48; WORD $0x0000 // or rax, 736 WORD $0x8949; BYTE $0xc4 // mov r12, rax - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0xc0cf8148; WORD $0x0002; BYTE $0x00 // or rdi, 704 - QUAD $0x000000f024bc8948 // mov qword [rsp + 240], rdi - WORD $0x8948; BYTE $0xca // mov rdx, rcx - LONG $0xe0ca8148; WORD $0x0002; BYTE $0x00 // or rdx, 736 - QUAD $0x000000d824948948 // mov qword [rsp + 216], rdx - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x03000d48; WORD $0x0000 // or rax, 768 - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax - WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x20cf8149; WORD $0x0003; BYTE $0x00 // or r15, 800 - LONG $0x247c894c; BYTE $0x70 // mov qword [rsp + 112], r15 - WORD $0x8949; BYTE $0xce // mov r14, rcx - LONG $0x40ce8149; WORD $0x0003; BYTE $0x00 // or r14, 832 - QUAD $0x000000c024b4894c // mov qword [rsp + 192], r14 - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - LONG $0x60c98149; WORD $0x0003; BYTE $0x00 // or r9, 864 - QUAD $0x00000108248c894c // mov qword [rsp + 264], r9 - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 - QUAD $0x000000802484894c // mov qword [rsp + 128], r8 - WORD $0x8949; BYTE $0xca // mov r10, rcx - LONG $0xa0ca8149; WORD $0x0003; BYTE $0x00 // or r10, 928 - LONG $0x2454894c; BYTE $0x58 // mov qword [rsp + 88], r10 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0x00c88149; WORD $0x0003; BYTE $0x00 // or r8, 768 + QUAD $0x000000f82484894c // mov qword [rsp + 248], r8 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x20ca8149; WORD $0x0003; BYTE $0x00 // or r10, 800 + LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + LONG $0x40c98149; WORD $0x0003; BYTE $0x00 // or r9, 832 + QUAD $0x00000090248c894c // mov qword [rsp + 144], r9 + WORD $0x8948; BYTE $0xda // mov rdx, rbx + LONG $0x60ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 864 + QUAD $0x0000010824948948 // mov qword [rsp + 264], rdx + WORD $0x8948; BYTE $0xde // mov rsi, rbx + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + QUAD $0x00000100249c8948 // mov qword [rsp + 256], rbx + LONG $0x80ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 896 + LONG $0x24748948; BYTE $0x70 // mov qword [rsp + 112], rsi + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0xa0cb8149; WORD $0x0003; BYTE $0x00 // or r11, 928 + QUAD $0x000000b8249c894c // mov qword [rsp + 184], r11 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx - LONG $0x207963c4; WORD $0x1e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + rbx], 1 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - LONG $0x2031a3c4; WORD $0x2e04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + r13], 2 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 3 - LONG $0x2079a3c4; WORD $0x1e04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + r11], 4 - LONG $0x2079a3c4; WORD $0x2604; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + r12], 5 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + rdi], 6 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + rdx], 7 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + rdx], 8 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + r15], 9 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r14], 10 - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + r9], 11 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + r8], 12 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + r10], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + rbx], 1 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r15], 2 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + r9], 3 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + r10], 4 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - LONG $0x2061a3c4; WORD $0x1e1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + r11], 5 - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r8], 6 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + r14], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + rcx], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rdx], 12 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rdx], 13 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - LONG $0x2061a3c4; WORD $0x261c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + r12], 14 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rdx], 15 - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x010116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 1 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x020116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 2 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x030116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 3 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x04012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 4 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x050116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 5 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x060116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 6 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x07012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 7 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x08012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 8 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x090116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 9 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x0a0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 10 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - QUAD $0x0b0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 12 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0d0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 13 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0e0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f0116642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 1], 15 - QUAD $0x01011e6c2029e3c4 // vpinsrb xmm5, xmm10, byte [rsi + rbx + 1], 1 - QUAD $0x02013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 2 - QUAD $0x03010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 3 - QUAD $0x0401166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 1], 4 - QUAD $0x05011e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 1], 5 - QUAD $0x0601066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 6 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - QUAD $0x0701366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 1], 7 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0a01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 10 - QUAD $0x0b010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 - QUAD $0x0e01266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 1], 14 - LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 + QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + LONG $0x207963c4; WORD $0x1f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + rbx], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + LONG $0x2031e3c4; WORD $0x1f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + rbx], 2 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + r13], 3 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 4 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + r15], 5 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r14], 6 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + r12], 7 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r8], 8 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r10], 9 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r9], 10 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + rdx], 11 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + rsi], 12 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + r11], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r12], 1 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r11], 2 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r10], 3 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r8], 4 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x2061a3c4; WORD $0x2f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r13], 5 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r9], 6 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r14], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rax], 8 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rcx], 9 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rdx], 10 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rsi], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rbx], 12 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rbx], 13 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rbx], 14 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rbx], 15 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x01011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x02011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 2 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x03013f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 1], 3 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x04011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x05011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 5 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x06011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 6 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x07011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 7 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x08011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 8 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x09013f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 1], 9 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x0a011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 10 + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + QUAD $0x0b011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 11 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x0c011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 12 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0d011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 13 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x0e011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 14 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x0f011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 15 + QUAD $0x0101276c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r12 + 1], 1 + QUAD $0x02011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 2 + QUAD $0x0301176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 3 + QUAD $0x0401076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 4 + QUAD $0x05012f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 1], 5 + QUAD $0x06010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 6 + QUAD $0x0701376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 1], 7 + WORD $0x894d; BYTE $0xf1 // mov r9, r14 + QUAD $0x0801076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 8 + WORD $0x8949; BYTE $0xc3 // mov r11, rax + QUAD $0x09010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 9 + QUAD $0x0a01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 10 + QUAD $0x0b01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0106442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 1], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 + LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x00050024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1280], ymm0 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xd06e79c5 // vmovd xmm10, eax + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] QUAD $0x00024024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 576] - QUAD $0x01020e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 2], 1 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x02020e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 2], 2 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x030216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 2], 3 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x040206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x050206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 5 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x060236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 2], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x070206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 7 - WORD $0x894d; BYTE $0xec // mov r12, r13 - QUAD $0x08022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 8 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x09022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 9 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - QUAD $0x0a0206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 2], 10 - QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] - QUAD $0x0b021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c0216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 2], 12 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0d023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 15 + QUAD $0x010217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 1 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x020237442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 2], 2 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x030207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x050207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 5 + QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] + QUAD $0x06023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x070207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 7 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x080237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0b0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 12 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0d0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 13 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x0e022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 14 + QUAD $0x0f021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 15 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 QUAD $0x0001e0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 480] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x02023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 2 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x03023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 4 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x05023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 5 - QUAD $0x06021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 7 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x08021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x09021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 9 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x0a021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 10 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0b021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 12 + QUAD $0x0102275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 2], 1 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0202275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 2], 2 LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x01030e642021e3c4 // vpinsrb xmm4, xmm11, byte [rsi + rcx + 3], 1 - QUAD $0x02030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 2 - QUAD $0x030316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 3 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x04031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 4 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x050316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 5 - QUAD $0x060336642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 3], 6 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x07030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 7 - QUAD $0x080326642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 3], 8 - QUAD $0x09032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 9 - QUAD $0x0a0306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 10 - QUAD $0x0b031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 11 - QUAD $0x0c0316642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 3], 12 - QUAD $0x0d033e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 3], 13 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0e0306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0203066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0303066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0403066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 4 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0503066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 5 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0603366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 3], 6 - QUAD $0x07033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0803066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 8 + QUAD $0x03021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 3 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0903066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 9 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 + QUAD $0x0402075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0502075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0602075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 6 + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + QUAD $0x07020f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 2], 7 + QUAD $0x08021f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 2], 8 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x09021f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 2], 9 + WORD $0x8949; BYTE $0xd1 // mov r9, rdx + QUAD $0x0a02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 10 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0d02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 13 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0e02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 14 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0f02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 15 + QUAD $0x010317642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r10 + 3], 1 + QUAD $0x020337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 2 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x030317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 3 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x040317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 4 + QUAD $0x050307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 5 + QUAD $0x06033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 6 + WORD $0x894c; BYTE $0xfe // mov rsi, r15 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x07033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 7 + QUAD $0x080337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 8 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x090317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 9 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0a0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 10 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x0b0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 11 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0c0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 12 + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x0d0317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 13 + QUAD $0x0e032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 14 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x0f0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 15 + QUAD $0x01030f6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rcx + 3], 1 + QUAD $0x0203276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 3], 2 + QUAD $0x03031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 3 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x04030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 4 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x05030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x06030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 6 + QUAD $0x0703076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 + QUAD $0x09031f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 3], 9 + QUAD $0x0a030f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 3], 10 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0f0326442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 3], 15 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 14 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0f032f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - LONG $0x167cb60f; BYTE $0x09 // movzx edi, byte [rsi + rdx + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x0001c024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 448] + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x01040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x020407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 2 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x030407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x040407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 5 + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + QUAD $0x060437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 6 + QUAD $0x07043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 7 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x010406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 1 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x02041e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 4], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x030406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 3 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x04042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 4 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x050416442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 4], 5 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x06043e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 4], 6 - QUAD $0x07040e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 4], 7 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - QUAD $0x080416442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 4], 8 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x090416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 9 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x0a0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 10 - QUAD $0x0b041e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 4], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 12 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0d0416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 13 - QUAD $0x0e0406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 4], 14 - QUAD $0x0f040e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 4], 15 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x01040e5c2001e3c4 // vpinsrb xmm3, xmm15, byte [rsi + rcx + 4], 1 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x0204165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 4], 2 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x03040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 3 + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x09041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a0437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 10 + QUAD $0x0b0437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 12 + QUAD $0x0d0417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 13 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0e0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 14 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x0f0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 15 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x01043f5c2001a3c4 // vpinsrb xmm3, xmm15, byte [rdi + r15 + 4], 1 + QUAD $0x0204275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0304075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0404075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0504075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0604075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 6 QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x04040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 4 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x05040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 5 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - QUAD $0x0604365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 7 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x08040e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 4], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 9 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0a04365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 10 + QUAD $0x07040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 7 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x08040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 8 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x0904175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 9 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0a040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 10 LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 11 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0c040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 12 + QUAD $0x0b040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 11 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0c04175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 12 + QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] + QUAD $0x0d04275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 13 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0e040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 14 + QUAD $0x0f042f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 4], 15 + WORD $0x894d; BYTE $0xec // mov r12, r13 + QUAD $0x01050f642009a3c4 // vpinsrb xmm4, xmm14, byte [rdi + r9 + 5], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 2 + QUAD $0x030507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 3 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x04052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 4 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + QUAD $0x05050f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 5], 5 + QUAD $0x06051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 6 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x07050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 7 + QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] + QUAD $0x08051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 8 + QUAD $0x09051f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 5], 9 + QUAD $0x0a0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 10 + QUAD $0x0b0537642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 5], 11 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x0c0537642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 5], 12 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x0d050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 13 + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x0e0507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 14 + QUAD $0x0f0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 15 + QUAD $0x01053f6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r15 + 5], 1 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0205376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 2 LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d040e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 4], 13 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0e04365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 4], 14 - QUAD $0x0f04265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 4], 15 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x010536642009a3c4 // vpinsrb xmm4, xmm14, byte [rsi + r14 + 5], 1 - QUAD $0x02051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 2 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x03051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 3 - QUAD $0x04052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 4 - QUAD $0x050506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 5 - QUAD $0x06053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x070506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 7 - WORD $0x8949; BYTE $0xc7 // mov r15, rax - QUAD $0x080516642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 5], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x090506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 10 - QUAD $0x0b051e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 5], 11 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x0c052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 13 - QUAD $0x0e0506642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 5], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 15 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x01050e6c2049e3c4 // vpinsrb xmm5, xmm6, byte [rsi + rcx + 5], 1 - QUAD $0x0205166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0305066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 3 + QUAD $0x03050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 3 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x04050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 4 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x05050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 5 + QUAD $0x0605076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 6 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0405066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 4 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0505066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 5 - QUAD $0x06053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0705066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 7 - QUAD $0x08050e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 5], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0905066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 9 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0a05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 10 + QUAD $0x0705076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0805076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0905076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e05066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 14 + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x0c05176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - QUAD $0x0f0526442051a3c4 // vpinsrb xmm0, xmm5, byte [rsi + r12 + 5], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + QUAD $0x0f0527442051a3c4 // vpinsrb xmm0, xmm5, byte [rdi + r12 + 5], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xd86ef9c5 // vmovd xmm3, eax LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x0a // movzx edi, byte [rsi + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - WORD $0x894d; BYTE $0xf3 // mov r11, r14 - QUAD $0x010636442019a3c4 // vpinsrb xmm0, xmm12, byte [rsi + r14 + 6], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 2 - QUAD $0x03061e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 6], 3 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x040636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 6], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x050606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 5 - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - QUAD $0x060616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 6], 6 - QUAD $0x07063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x010607442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rax + 6], 1 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x020627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x04062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 4 + QUAD $0x05060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x060607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 6 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x07060f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 6], 7 + WORD $0x894d; BYTE $0xdf // mov r15, r11 + QUAD $0x08061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 9 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0a061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0b0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 11 + QUAD $0x0c0637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 12 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0d0637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 13 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x0e0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 14 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x0f0607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 6], 15 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x080606442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 6], 8 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x09063e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 6], 9 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0a060e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 6], 10 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - QUAD $0x0b0606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 6], 11 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x0c062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 15 - QUAD $0x01060e6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rcx + 6], 1 - QUAD $0x0206166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 2 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x03060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x04060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 4 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x05063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 5 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x06062e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 6], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0706166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 6], 7 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x08060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 9 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x0a060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 10 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0b061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 12 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0d061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 13 + QUAD $0x0106076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 6], 1 + QUAD $0x0206376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0306076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0406076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0506076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 5 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0606376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 6 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x07061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 7 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x08061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 8 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x09060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 9 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0a06176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 10 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x0b062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0c061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 12 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0d061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 13 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x0e062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 14 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x0f061f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 6], 15 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x01071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 1 + QUAD $0x020727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 2 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x03071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 3 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x04071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 4 LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 14 - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0f06266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 6], 15 - QUAD $0x01071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 1 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x02071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 2 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x03071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 3 - QUAD $0x040736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 4 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x050736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 7], 5 - QUAD $0x060716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 7], 6 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x07071e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 7], 7 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - QUAD $0x080716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 7], 8 - QUAD $0x09073e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 7], 9 - QUAD $0x0a070e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 7], 10 - QUAD $0x0b0706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 7], 11 - QUAD $0x0c0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 12 + QUAD $0x05071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 5 + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x060727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 6 + QUAD $0x07070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 7 + QUAD $0x08073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x09071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 9 + QUAD $0x0a071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 10 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x0b070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 11 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0c070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 12 + QUAD $0x0d0737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 13 + QUAD $0x0e0717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 14 + QUAD $0x0f0707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 15 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x01070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 1 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x02071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 2 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x03070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 3 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0407174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 4 + QUAD $0x0507074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 5 + QUAD $0x0607374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 6 + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 7], 15 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0107064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 1 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x0207264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 7], 2 + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x09070f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 7], 9 + QUAD $0x0a07174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 12 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0307064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0407064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 4 - QUAD $0x05073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 5 - QUAD $0x06072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 6 - WORD $0x894d; BYTE $0xe8 // mov r8, r13 - QUAD $0x0707164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 7 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x08070e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 7], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0907064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 9 - QUAD $0x0a070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 10 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0b072e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 7], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 13 + QUAD $0x0d07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0706442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rax + 7], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0706442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 7], 15 + QUAD $0x0e072f442071a3c4 // vpinsrb xmm0, xmm1, byte [rdi + r13 + 7], 14 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f0707442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x01083e442031a3c4 // vpinsrb xmm0, xmm9, byte [rsi + r15 + 8], 1 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x02081e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 8], 2 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x03080e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 8], 3 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x040806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 4 - QUAD $0x050836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 8], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x060806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 8], 6 - QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] - QUAD $0x07081e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 8], 7 - QUAD $0x080816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 8], 8 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x090816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 9 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x0a0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 10 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0b083e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 8], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 12 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0d0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 13 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0e0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f0816442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 8], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x010807442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r8 + 8], 1 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x020837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 8], 2 QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0108166c2029e3c4 // vpinsrb xmm5, xmm10, byte [rsi + rdx + 8], 1 - QUAD $0x0208266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 8], 2 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0308166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 4 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0508166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 5 - QUAD $0x0608066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 8], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0708166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 7 - QUAD $0x08080e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 8], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0908166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 9 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0a08066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 8], 10 - QUAD $0x0b082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 11 + QUAD $0x030817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x040807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 5 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + QUAD $0x060827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 8], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x070807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 7 + QUAD $0x08083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 8 LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0c08266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 8], 12 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0d08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 13 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0e08166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 8], 14 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0f082e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r13 + 8], 15 - QUAD $0x01093e742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r15 + 9], 1 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - QUAD $0x02091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 2 - QUAD $0x03090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 3 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x04091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 4 - QUAD $0x050936742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r14 + 9], 5 - QUAD $0x060906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 6 - WORD $0x8949; BYTE $0xc1 // mov r9, rax - QUAD $0x07091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 7 - QUAD $0x080916742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r10 + 9], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x09090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 9 - QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] - QUAD $0x0a093e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r15 + 9], 10 + QUAD $0x090827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 8], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 10 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 11 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0c091e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r11 + 9], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 14 + QUAD $0x0b0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 11 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x0c080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 12 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0d0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 13 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0e0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 15 + QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + QUAD $0x0108176c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r10 + 8], 1 + QUAD $0x02081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 2 + QUAD $0x03080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0408076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 4 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x05080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 5 + QUAD $0x06081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 6 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x07080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 7 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x08081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 8 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x09081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 9 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0a081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 10 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0b081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0c081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 12 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0d081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 13 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x0e082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 14 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010907742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r8 + 9], 1 + QUAD $0x020937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 2 + QUAD $0x030917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x040937742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 9], 4 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x050917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 5 + QUAD $0x060937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 6 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x070917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 7 + QUAD $0x08093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 8 + QUAD $0x090927742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 9], 9 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0a0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 10 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x0b0937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 11 + QUAD $0x0c090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 12 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0d0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 13 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x0e0927742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 9], 14 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x0f0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 15 + QUAD $0x0109177c2021a3c4 // vpinsrb xmm7, xmm11, byte [rdi + r10 + 9], 1 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x02093f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 9], 2 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0309177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 3 + QUAD $0x0409077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 4 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0906742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rax + 9], 15 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0109067c2021e3c4 // vpinsrb xmm7, xmm11, byte [rsi + rax + 9], 1 - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x0209167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 9], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0309067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 3 - QUAD $0x04093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 4 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0509067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 5 + QUAD $0x0509077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 5 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x06092f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 9], 6 + QUAD $0x07090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0809077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0609067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0709067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0809067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0909067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 9 - QUAD $0x0a09067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 9], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 11 - QUAD $0x0c09267c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r12 + 9], 12 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0d09367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 9], 13 - QUAD $0x0e09167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 9], 14 + QUAD $0x0a09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 10 + QUAD $0x0b091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 13 + QUAD $0x0e091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1248], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f09076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 9], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xc06ef9c5 // vmovd xmm0, eax LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x0004c024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x010a2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 10], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x030a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 3 - QUAD $0x040a1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 10], 4 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x050a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 5 - QUAD $0x060a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x070a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 7 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x080a165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 10], 8 - QUAD $0x090a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 9 - QUAD $0x0a0a3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 10], 10 - QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] - QUAD $0x0b0a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 11 - QUAD $0x0c0a1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 10], 12 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0d0a3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 10], 13 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax + QUAD $0x010a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 1 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 15 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x010a0e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 10], 1 - QUAD $0x020a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 2 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x040a16642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 10], 4 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x050a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x060a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 9 + QUAD $0x020a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 2 + QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] + QUAD $0x030a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 3 + QUAD $0x040a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x050a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 5 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x060a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x080a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 8 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x090a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 9 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0a0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 11 - QUAD $0x0c0a26642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 10], 12 - QUAD $0x0d0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 13 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0e0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 15 - QUAD $0x010b2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 11], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x030b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 3 - QUAD $0x040b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 4 - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x050b064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 11], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x060b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x070b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 7 - QUAD $0x080b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 8 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x090b1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 11], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 10 - QUAD $0x0b0b0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 11], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 12 - QUAD $0x0d0b3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 11], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 14 + QUAD $0x0a0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 10 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x0b0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 12 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0d0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 13 + QUAD $0x0e0a275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 10], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x010a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 1 + QUAD $0x020a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x040a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 4 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x050a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 5 + QUAD $0x060a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 6 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x070a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 7 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x080a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 8 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x090a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 9 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0a0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 10 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x0b0a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 11 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0c0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 12 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0d0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 13 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x0e0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 14 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0f0a37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 10], 15 + QUAD $0x010b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 1 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x020b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 2 + QUAD $0x030b1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 11], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x040b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 4 + QUAD $0x050b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 5 + QUAD $0x060b0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 11], 6 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x070b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 7 + QUAD $0x080b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 8 + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + QUAD $0x090b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 9 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0a0b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 10 + QUAD $0x0b0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 11 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0c0b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 12 + QUAD $0x0d0b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 13 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0e0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 14 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x0f0b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 15 + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x010b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 1 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x020b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 11], 2 + QUAD $0x030b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x040b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 4 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 15 - QUAD $0x010b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 11], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x020b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 2 - QUAD $0x030b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 11], 3 - QUAD $0x040b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 11], 4 - QUAD $0x050b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 11], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x060b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 7 + QUAD $0x050b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 5 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 9 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0a0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 11 - QUAD $0x0c0b26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 11], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 13 + QUAD $0x060b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 6 + QUAD $0x070b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 7 + QUAD $0x080b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0a0b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 11], 10 + QUAD $0x0b0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 11 + QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] + QUAD $0x0c0b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 12 + QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] + QUAD $0x0d0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x0004a0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm3 - QUAD $0x0e0b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 11], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0d // movzx edi, byte [rsi + rax + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 11], 15 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000480248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm1 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - LONG $0x0e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rcx + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x010c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 12], 1 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x020c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 12], 2 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x030c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 12], 3 - QUAD $0x040c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 12], 4 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x050c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 12], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x060c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 6 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x070c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 12], 7 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x080c26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 12], 8 - QUAD $0x090c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 9 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x0a0c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 12], 10 - QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] - QUAD $0x0b0c36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 12], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 12 - QUAD $0x0d0c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 12], 13 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x010c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 1 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 14 + QUAD $0x020c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 2 + QUAD $0x030c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 12], 3 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x040c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 4 + QUAD $0x050c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 12], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x060c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 6 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x070c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 12], 7 + QUAD $0x080c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 8 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x090c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 9 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x0a0c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 12], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0b0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 11 + QUAD $0x0c0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 12 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x0d0c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 12], 13 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0e0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 14 + QUAD $0x0f0c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 15 + QUAD $0x010c0f542051a3c4 // vpinsrb xmm2, xmm5, byte [rdi + r9 + 12], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x020c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 2 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x030c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 3 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x040c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 4 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x050c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 5 + QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] + QUAD $0x060c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 6 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x070c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 7 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x080c0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 12], 8 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x090c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 9 + QUAD $0x0a0c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 10 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0b0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 11 + QUAD $0x0c0c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 12], 12 + QUAD $0x0d0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 13 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x0e0c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 14 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0f0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 15 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x010d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x020d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 2 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x030d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 3 + QUAD $0x040d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 4 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x050d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 5 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x060d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 6 + QUAD $0x070d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 7 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x080d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 8 + QUAD $0x090d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 9 + QUAD $0x0a0d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 10 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x0b0d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 11 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x0d0d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 13], 13 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0e0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 14 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x0f0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 15 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x010d174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 13], 1 + QUAD $0x020d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 2 + QUAD $0x030d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 3 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x040d3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 13], 4 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 12], 15 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x010c06542051e3c4 // vpinsrb xmm2, xmm5, byte [rsi + rax + 12], 1 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x020c3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 12], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x030c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 3 + QUAD $0x050d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 5 + QUAD $0x060d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 6 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x040c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 4 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x050c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 5 + QUAD $0x070d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 7 + QUAD $0x080d0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 13], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x090d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 9 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x060c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x070c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090c06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 12], 9 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x0a0c2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 12], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0c0c3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 12], 12 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e0c0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 12], 14 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - QUAD $0x0f0c3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 12], 15 - QUAD $0x010d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 1 - WORD $0x894d; BYTE $0xdf // mov r15, r11 - QUAD $0x020d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 13], 2 - QUAD $0x030d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 13], 3 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x040d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 4 - QUAD $0x050d0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 13], 5 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x060d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 6 - QUAD $0x070d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 7 - QUAD $0x080d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 13], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x090d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 9 - QUAD $0x0a0d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 10 - QUAD $0x0b0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 11 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0c0d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 13], 12 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0d0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 13 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0e0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f0d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 15 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x010d164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 13], 1 - QUAD $0x020d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 2 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x030d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 3 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x040d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 4 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x050d064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 13], 5 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x060d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x070d164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 13], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x080d3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 13], 8 - QUAD $0x090d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 9 - QUAD $0x0a0d2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 13], 10 + QUAD $0x0a0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 10 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 11 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0c0d1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 13], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e0d064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 13], 14 + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + QUAD $0x0e0d374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x00044024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0d06442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rax + 13], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0e // movzx edi, byte [rsi + rax + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + QUAD $0x0f0d2f442071a3c4 // vpinsrb xmm0, xmm1, byte [rdi + r13 + 13], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - LONG $0x7cb60f42; WORD $0x0e2e // movzx edi, byte [rsi + r13 + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x010e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 1 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x020e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 2 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x030e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 14], 3 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x040e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x050e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 5 - QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] - QUAD $0x060e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 14], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x070e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x010e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 1 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x020e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 2 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x030e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 3 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x040e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x050e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x070e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 7 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x080e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x090e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 + WORD $0x894d; BYTE $0xe2 // mov r10, r12 + QUAD $0x0b0e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 14], 11 + QUAD $0x0c0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 12 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x0d0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 13 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x0e0e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 14], 14 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x0f0e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 14], 15 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x080e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 8 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x090e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 14], 9 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 11 - QUAD $0x0c0e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 12 - QUAD $0x0d0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 13 - QUAD $0x0e0e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 14], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 15 - QUAD $0x010e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 14], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x020e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x030e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 3 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x040e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 14], 4 - QUAD $0x050e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 14], 5 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x060e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 14], 6 - QUAD $0x070e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 14], 7 + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x020e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x030e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 3 + QUAD $0x040e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 14], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x050e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 5 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x080e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x090e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 14], 9 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0a0e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 14], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 11 - QUAD $0x0c0e1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 14], 12 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0d0e1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 14], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x0f // movzx edi, byte [rsi + rdi + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x010f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 1 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x020f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 2 - QUAD $0x030f0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 15], 3 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x040f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x050f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 5 - QUAD $0x060f26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 15], 6 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x070f26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 15], 7 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x080f0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 15], 8 - QUAD $0x090f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 9 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0a0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 10 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x0b0f3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 15], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 14 - QUAD $0x0f0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 15 - LONG $0x7cb60f42; WORD $0x0f2e // movzx edi, byte [rsi + r13 + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x010f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x020f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 2 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x030f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 3 - QUAD $0x040f165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 15], 4 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x050f2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 15], 5 - QUAD $0x060f365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 15], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x070f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 7 - QUAD $0x080f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 8 - QUAD $0x090f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 9 - QUAD $0x0a0f065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 15], 10 + QUAD $0x060e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 6 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x070e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x080e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x090e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 9 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x0a0e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 14], 10 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 11 + QUAD $0x0b0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 14 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x0f // movzx eax, byte [rdi + rax + 15] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x010f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 1 + QUAD $0x020f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 2 + QUAD $0x030f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 3 + QUAD $0x040f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 4 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x050f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 5 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x060f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 6 + QUAD $0x070f1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 15], 7 + QUAD $0x080f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 8 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 12 - QUAD $0x0d0f1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 15], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e0f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 14 + QUAD $0x090f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 9 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0a0f1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 15], 10 + QUAD $0x0b0f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 12 + QUAD $0x0d0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 13 + QUAD $0x0e0f27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 15], 14 + QUAD $0x0f0f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 15], 15 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + LONG $0x44b60f42; WORD $0x0f17 // movzx eax, byte [rdi + r10 + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x010f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 1 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x020f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x030f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x050f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x060f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 6 + QUAD $0x070f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x080f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 8 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x090f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 9 + QUAD $0x0a0f3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 15], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 15 + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0d0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 14 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00042024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x10 // movzx edi, byte [rsi + rax + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x011016442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 16], 1 - QUAD $0x02101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 3 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x041006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 4 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x05101e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 16], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x061006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 6 - QUAD $0x071026442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 16], 7 - QUAD $0x08100e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 16], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 9 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc06ef9c5 // vmovd xmm0, eax QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 10 - QUAD $0x0b103e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 16], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1006442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 16], 15 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - LONG $0x167cb60f; BYTE $0x10 // movzx edi, byte [rsi + rdx + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] - QUAD $0x0110364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 16], 1 - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x02100e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 16], 2 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0310164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 3 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0410164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 4 - QUAD $0x05102e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 16], 5 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0610164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0710164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 7 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0810164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 8 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x09101e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 16], 9 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0a103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 12 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0d103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 13 - QUAD $0x0e100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 14 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 15 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x112e // movzx edi, byte [rsi + r13 + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 1 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x02113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 2 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x031116542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 17], 3 - QUAD $0x041106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 4 - QUAD $0x05111e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 17], 5 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x06110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 6 - QUAD $0x071126542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 17], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x08110e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 17], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x09113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 9 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x0a113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 10 - QUAD $0x0b113e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 17], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0e111e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 17], 14 - QUAD $0x0f1106542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 17], 15 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x11 // movzx edi, byte [rsi + rax + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0111365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 17], 1 - QUAD $0x02110e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 17], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0311065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 3 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0411065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 17], 4 + QUAD $0x011007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 1 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x021017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x031007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 4 + QUAD $0x05101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 5 + QUAD $0x06100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 6 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0511065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0611065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 6 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x07110e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 17], 7 - QUAD $0x0811165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 8 - QUAD $0x09111e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 17], 9 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0a11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 10 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0b11365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 17], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 12 + QUAD $0x071007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 7 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x081007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x09101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 9 + QUAD $0x0a101f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 16], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x0c1037442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 16], 12 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0d1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 13 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0e1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 14 + QUAD $0x0f1007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 15 + LONG $0x44b60f42; WORD $0x1017 // movzx eax, byte [rdi + r10 + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0110374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 1 + QUAD $0x0210274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 2 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e11065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 17], 14 - LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 + QUAD $0x0310074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0510074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 5 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x06101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 6 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0710074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 7 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x08100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 8 + QUAD $0x09102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 9 + QUAD $0x0a103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 10 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x0b103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1106442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rax + 17], 15 - LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 - QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 - LONG $0x7cb60f42; WORD $0x122e // movzx edi, byte [rsi + r13 + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0c10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 12 + QUAD $0x0d100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 14 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 15 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3744b60f; BYTE $0x11 // movzx eax, byte [rdi + rsi + 17] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x011107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 1 + QUAD $0x021117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x031107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 3 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x04112f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 17], 4 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x05110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x061107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 6 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x071127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 7 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 1 + QUAD $0x081107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 8 + QUAD $0x09111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0b1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 11 + QUAD $0x0c1137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 12 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x021206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 2 - QUAD $0x031216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 3 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x041206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 4 + QUAD $0x0d1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 13 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x061206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 6 - QUAD $0x071226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 18], 7 - QUAD $0x08120e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 18], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 18], 9 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0a120e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 18], 10 - QUAD $0x0b123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 11 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x0c1226442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 18], 12 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0d121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 13 - QUAD $0x0e121e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 18], 14 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0f123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 15 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - LONG $0x0e7cb60f; BYTE $0x12 // movzx edi, byte [rsi + rcx + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x01120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x02120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 2 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x03120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 3 - QUAD $0x0412064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 18], 4 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x05120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 5 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x06120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 6 - QUAD $0x07120e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 18], 7 - QUAD $0x0812164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 8 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x0912064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 18], 9 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x0a120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 10 - QUAD $0x0b12364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 18], 11 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0c12164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 12 + QUAD $0x0e1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 15 + LONG $0x44b60f42; WORD $0x1117 // movzx eax, byte [rdi + r10 + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x01111f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 17], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0211075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 2 LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0d12164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 18], 13 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0e121e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 18], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 15 - LONG $0x7cb60f42; WORD $0x132e // movzx edi, byte [rsi + r13 + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 1 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x02133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 2 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x03133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 3 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x04132e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 19], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x05133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 5 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x06133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 6 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x07133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 8 - QUAD $0x091306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 9 + QUAD $0x0311175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 3 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0411375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 4 + QUAD $0x0511075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 5 + QUAD $0x06111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 6 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0711075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 7 + QUAD $0x08110f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 17], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + QUAD $0x0b113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0e111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 14 + LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 + QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x0f113f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r15 + 17], 15 + LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 + QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 + LONG $0x3744b60f; BYTE $0x12 // movzx eax, byte [rdi + rsi + 18] + LONG $0xc06ef9c5 // vmovd xmm0, eax QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0a1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 11 - QUAD $0x0c1326542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 19], 12 - QUAD $0x0d131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 13 + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 14 - QUAD $0x0f133e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 19], 15 + QUAD $0x021207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 2 + QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] + QUAD $0x03120f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 18], 3 + QUAD $0x04122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 4 + QUAD $0x05120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 5 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x061217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 6 + QUAD $0x071227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 7 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x081207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 12 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0d1207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 18], 13 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0e1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 14 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x13 // movzx edi, byte [rsi + rax + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0113065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 1 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0213365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 19], 2 + QUAD $0x0f1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x01121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 1 + QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] + QUAD $0x02122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 2 + QUAD $0x0312174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 3 + QUAD $0x0412374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0512074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x06120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 6 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x0712174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0812074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 8 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0912274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 11 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0c12374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 12 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0313065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 3 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0413065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 4 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x05133e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 19], 5 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x06130e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 19], 6 + QUAD $0x0d12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 13 + QUAD $0x0e121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 14 + QUAD $0x0f123f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 18], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x01131f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 19], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 2 + QUAD $0x03130f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 19], 3 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0713065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 7 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0813065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 8 - QUAD $0x0913065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 9 - QUAD $0x0a130e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 19], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 11 - QUAD $0x0c13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 12 - QUAD $0x0d13165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 19], 13 - QUAD $0x0e131e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 19], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f13065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 19], 15 + QUAD $0x041307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 5 + QUAD $0x061317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 7 + QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] + QUAD $0x08131f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 19], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 10 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x0b1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + QUAD $0x0d1307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 13 + QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] + QUAD $0x0e1337542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 19], 14 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x0f1307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] + QUAD $0x01130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 1 + QUAD $0x02132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0313075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0413075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x06130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 6 + QUAD $0x0713175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 19], 7 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x08133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 8 + QUAD $0x0913275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 10 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0b130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 11 + QUAD $0x0c13375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x141e // movzx edi, byte [rsi + r11 + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x14 // movzx eax, byte [rdi + rax + 20] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x01141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x031417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 3 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x041427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] + QUAD $0x06142f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 20], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 7 + QUAD $0x08141f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 20], 8 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x09141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a1437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 20], 10 + QUAD $0x0b1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 11 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0c1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 12 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0d1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 13 + QUAD $0x0e1437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 14 + QUAD $0x0f1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 15 + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x14 // movzx eax, byte [rdi + rax + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x01140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0414074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 4 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0514074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0614074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 6 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0714074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 7 + QUAD $0x08143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0914074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 10 + QUAD $0x0b140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 11 + QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] + QUAD $0x0c143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 12 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0d140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 13 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0e141f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 20], 14 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x0f140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x15 // movzx eax, byte [rdi + rax + 21] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x011507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 2 + QUAD $0x031517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 3 + QUAD $0x041527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 5 + QUAD $0x06152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 7 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 1 + QUAD $0x081507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 8 + QUAD $0x09151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 9 + QUAD $0x0a1537542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 21], 10 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x0b152f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 21], 11 + QUAD $0x0c1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 12 QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x021416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 2 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x03140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 3 - QUAD $0x04142e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 20], 4 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x05140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 5 - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - QUAD $0x061406442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 20], 6 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x071426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 7 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x08143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x09143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 9 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0a140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 10 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x0b141e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 20], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 15 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x3e7cb60f; BYTE $0x14 // movzx edi, byte [rsi + rdi + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x0114164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 20], 1 - QUAD $0x0214364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 20], 2 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0314364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 20], 3 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x04142e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 20], 4 - QUAD $0x05143e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 20], 5 - QUAD $0x06140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x08143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 8 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x09143e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 20], 9 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0a143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0d143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 13 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x0e140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 15 - LONG $0x7cb60f42; WORD $0x151e // movzx edi, byte [rsi + r11 + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 1 - QUAD $0x021516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 2 - WORD $0x8949; BYTE $0xd3 // mov r11, rdx - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x031516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 3 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x041506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 4 + QUAD $0x0d1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 13 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 5 - QUAD $0x061506542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 21], 6 - QUAD $0x071526542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 21], 7 + QUAD $0x0e1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 14 + QUAD $0x0f1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 15 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + LONG $0x44b60f42; WORD $0x1537 // movzx eax, byte [rdi + r14 + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 9 - QUAD $0x0a150e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 21], 10 - QUAD $0x0b151e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 21], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 15 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x15 // movzx edi, byte [rsi + rax + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0115165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0215065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 2 - QUAD $0x0315365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 21], 3 - QUAD $0x04152e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 21], 4 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x0515365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 21], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0615065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 6 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0715165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 7 + QUAD $0x0115075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 1 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0215375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0415075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 4 + QUAD $0x0515075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 5 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0815065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 8 - QUAD $0x09153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 9 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x0a15265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 21], 10 + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x0715275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 21], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x0a15075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 10 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b15065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0c153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 12 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 13 - QUAD $0x0e150e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 21], 14 + QUAD $0x0b15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 11 + QUAD $0x0c153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 12 + QUAD $0x0d150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 13 + QUAD $0x0e151f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f151e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rbx + 21], 15 + QUAD $0x0f150f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r9 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rcx + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 1 - QUAD $0x02161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 2 - QUAD $0x031616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 3 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x04163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 4 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x051616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 5 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x06160e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 22], 6 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x07163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 7 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x081616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 8 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x091616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 9 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x0a161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 10 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0b163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 11 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x0c1606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 22], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 15 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x3e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rdi + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x01163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 1 - QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] - QUAD $0x02162e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 22], 2 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x03163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 3 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x04163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 4 - QUAD $0x0516364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 22], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x06163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 6 - QUAD $0x0716164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 7 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x0816364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 22], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 9 - QUAD $0x0a16264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 22], 10 - QUAD $0x0b16064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 11 - QUAD $0x0c163e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 22], 12 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0d16164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e16064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 14 - QUAD $0x0f161e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 22], 15 - LONG $0x0e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rcx + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + LONG $0x44b60f42; WORD $0x1617 // movzx eax, byte [rdi + r10 + 22] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x01161f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 22], 1 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x02160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x031607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 4 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x05163f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 22], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x061607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 6 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x07161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 7 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 1 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x02170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 2 + QUAD $0x081607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 10 + QUAD $0x0b162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 12 + QUAD $0x0d1617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 13 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x0e162f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 22], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 15 + LONG $0x44b60f42; WORD $0x1637 // movzx eax, byte [rdi + r14 + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0116074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 1 + QUAD $0x0216374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0316074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 3 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0416174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 22], 4 + LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] + QUAD $0x05160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0616074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 6 + QUAD $0x0716274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 3 + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a16074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x041706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 4 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 5 - QUAD $0x06170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 6 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x07170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 8 - QUAD $0x091716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 9 - QUAD $0x0a171e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 23], 10 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x0b1726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 23], 11 - QUAD $0x0c1706542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 23], 12 + QUAD $0x0e16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 14 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0f16274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 15 + LONG $0x44b60f42; WORD $0x1717 // movzx eax, byte [rdi + r10 + 23] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x01171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 1 + QUAD $0x02170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 2 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x031707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 23], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 4 + QUAD $0x05173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 5 + QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] + QUAD $0x06173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 6 + QUAD $0x07171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 7 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x081707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 9 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x0a1737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0b1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 12 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0d1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 13 + QUAD $0x0e172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 14 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + QUAD $0x0f171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 15 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + LONG $0x1f44b60f; BYTE $0x17 // movzx eax, byte [rdi + rbx + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x0117375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0317075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 3 + QUAD $0x0417175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 4 + QUAD $0x05170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x06170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 6 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0717075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 7 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1706542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 23], 15 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x17 // movzx edi, byte [rsi + rax + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0117065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 1 - QUAD $0x02172e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 23], 2 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0317165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 23], 3 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x04173e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 23], 4 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x05171e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 23], 5 + QUAD $0x0817075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 8 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0917175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 9 QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x06172e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 23], 6 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0717065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 7 - QUAD $0x0817365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 23], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0917065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 9 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0a17065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 23], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c173e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 23], 12 - QUAD $0x0d17165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 23], 13 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0e17165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 23], 14 - QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] - QUAD $0x0f171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 15 + QUAD $0x0a172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 10 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x0b17175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 23], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 14 + QUAD $0x0f17275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x386563c4; WORD $0x01da // vinserti128 ymm11, ymm3, xmm2, 1 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rdi + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 1 - QUAD $0x02180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 2 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x03180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 3 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x04180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 4 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x05180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 5 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x061836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 24], 6 - QUAD $0x07180e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 24], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x08180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x09180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 9 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x0a180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 10 - QUAD $0x0b1826442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 24], 11 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0c180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 12 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0d180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 14 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f180e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 24], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x01180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 2 + QUAD $0x031807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 5 + QUAD $0x06183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 6 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x07183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 7 + QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] + QUAD $0x081807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 8 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x091827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 9 + QUAD $0x0a1837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 10 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x0b1837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 12 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0d1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 13 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0e1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 14 + QUAD $0x0f181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 15 + LONG $0x1f44b60f; BYTE $0x18 // movzx eax, byte [rdi + rbx + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0118374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0318074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0418074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 4 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x05181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 5 + QUAD $0x06180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 6 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0718074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 7 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x08181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 8 + QUAD $0x0918174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 9 + QUAD $0x0a182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 10 + QUAD $0x0b18174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 12 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0d18374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 13 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x0e182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 14 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x01190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x031907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 3 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x041917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x061907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 6 + QUAD $0x07193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 7 + QUAD $0x081907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 8 + QUAD $0x091927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 9 + QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] + QUAD $0x0a190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 10 + QUAD $0x0b1937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 11 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0c1917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 12 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0d1907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 13 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - LONG $0x0e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rcx + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x01180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 1 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x0218264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 2 - QUAD $0x0318164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 3 - QUAD $0x04183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 4 - QUAD $0x05181e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 24], 5 - QUAD $0x06182e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 24], 6 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x07180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 7 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x08183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 9 - QUAD $0x0a18064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 24], 10 - QUAD $0x0b18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 11 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0c18064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 24], 12 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0d180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 13 - QUAD $0x0e18164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 24], 14 - QUAD $0x0f181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 15 + QUAD $0x0f190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 15 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x19 // movzx edi, byte [rsi + rax + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x011916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 1 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x021906542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 25], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 3 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x041906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 4 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x05191e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 25], 5 - QUAD $0x061936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 6 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x071906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 7 + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 8 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x091916542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 25], 9 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0a1936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 10 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0b193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 11 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0c191e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 25], 12 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0d193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e193e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 25], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0f192e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 25], 15 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - LONG $0x3e7cb60f; BYTE $0x19 // movzx edi, byte [rsi + rdi + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 1 - QUAD $0x0219265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 2 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - QUAD $0x03190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 3 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x0419265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 4 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x05193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x06193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x07193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 7 - QUAD $0x08193e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 25], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 9 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0a193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 10 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0b193e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 25], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 12 - QUAD $0x0d190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 13 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0e190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 14 + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0219275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0319075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 3 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0419075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 4 + QUAD $0x05191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x07191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 7 + QUAD $0x08191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0919075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 12 + QUAD $0x0d19375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 25], 13 + QUAD $0x0e192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f190e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rcx + 25], 15 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x0f191f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r11 + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x1a // movzx edi, byte [rsi + rcx + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 1 - QUAD $0x021a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 2 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x031a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 3 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x041a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 4 - QUAD $0x051a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 5 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x061a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 6 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x071a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 7 - QUAD $0x081a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 8 - QUAD $0x091a16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 26], 9 - QUAD $0x0a1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b1a06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 26], 11 - QUAD $0x0c1a1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 26], 12 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x0d1a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 13 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0e1a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 14 - QUAD $0x0f1a2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 26], 15 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - LONG $0x167cb60f; BYTE $0x1a // movzx edi, byte [rsi + rdx + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x011a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 1 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x021a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 2 - QUAD $0x031a0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 26], 3 - QUAD $0x041a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 4 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x051a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 5 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x061a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 6 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x071a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 7 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x081a1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 26], 8 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x091a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 9 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0a1a164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 26], 10 - QUAD $0x0b1a3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 26], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 12 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x0d1a2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 26], 13 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0e1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f1a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 15 - LONG $0x0e7cb60f; BYTE $0x1b // movzx edi, byte [rsi + rcx + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x011b3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 27], 1 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x021b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 2 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x031b0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 27], 3 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x041b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 4 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + LONG $0x44b60f42; WORD $0x1a2f // movzx eax, byte [rdi + r13 + 26] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x011a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x031a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 3 + QUAD $0x041a17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 26], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 5 + QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] + QUAD $0x061a3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 26], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 7 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x081a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 9 + QUAD $0x0a1a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 10 + QUAD $0x0b1a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 11 + QUAD $0x0c1a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 12 + QUAD $0x0d1a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 13 QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x051b16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 27], 5 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x061b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 6 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x071b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 7 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x081b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 8 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x091b0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 27], 9 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x0a1b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 27], 10 - QUAD $0x0b1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 12 - QUAD $0x0d1b36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 27], 13 - QUAD $0x0e1b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1b06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 27], 15 + QUAD $0x0e1a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 14 + QUAD $0x0f1a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x1a // movzx eax, byte [rdi + rax + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 1 + QUAD $0x021a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x031a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 3 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + QUAD $0x041a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 4 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x051a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 6 + QUAD $0x071a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x081a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 8 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x091a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 9 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0a1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0d1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 14 + QUAD $0x0f1a1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 26], 15 + LONG $0x44b60f42; WORD $0x1b2f // movzx eax, byte [rdi + r13 + 27] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x011b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 27], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x021b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x031b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 3 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x041b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 5 + QUAD $0x061b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] + QUAD $0x081b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 9 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x0a1b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 27], 10 + QUAD $0x0b1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 12 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0d1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 13 + QUAD $0x0e1b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 27], 14 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - LONG $0x067cb60f; BYTE $0x1b // movzx edi, byte [rsi + rax + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x011b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 1 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x021b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 2 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x031b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 3 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x041b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 4 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x051b365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 27], 5 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x061b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 6 - QUAD $0x071b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 7 - QUAD $0x081b1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 27], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x091b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 9 - QUAD $0x0a1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 10 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0b1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 11 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0c1b065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 27], 12 - QUAD $0x0d1b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 13 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0e1b2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 27], 14 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0f1b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 15 + QUAD $0x0f1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 15 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + LONG $0x44b60f42; WORD $0x1b17 // movzx eax, byte [rdi + r10 + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x011b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x021b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 2 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x031b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 3 + QUAD $0x041b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 4 + QUAD $0x051b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x071b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x081b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 8 + QUAD $0x091b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 9 + QUAD $0x0a1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] + QUAD $0x0d1b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 13 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0e1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 14 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x1c // movzx edi, byte [rsi + rdx + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 28], 1 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x021c26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 28], 2 - QUAD $0x031c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 3 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x041c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 4 - QUAD $0x051c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 5 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x061c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 6 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x071c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 7 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x081c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 28], 8 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x091c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 9 - QUAD $0x0a1c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 10 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x0b1c1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 28], 11 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x0c1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 12 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0d1c1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 28], 13 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0e1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 15 - LONG $0x067cb60f; BYTE $0x1c // movzx edi, byte [rsi + rax + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x011c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 1 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x021c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 2 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x031c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 3 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x041c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 4 - QUAD $0x051c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 5 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x061c164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 28], 6 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x071c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 7 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x081c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 8 - QUAD $0x091c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 9 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x0a1c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 28], 10 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0b1c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 11 - QUAD $0x0c1c064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 28], 12 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0d1c064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 28], 13 - QUAD $0x0e1c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 14 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0f1c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x1d // movzx edi, byte [rsi + rdi + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x011d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 1 - QUAD $0x021d26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 29], 2 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x031d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 3 - QUAD $0x041d0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 29], 4 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x051d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 5 - QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] - QUAD $0x061d26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 29], 6 - QUAD $0x071d16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 29], 7 - QUAD $0x081d3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 29], 8 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x091d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 9 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0a1d0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 29], 10 - QUAD $0x0b1d1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 29], 11 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x0c1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 12 - QUAD $0x0d1d1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 29], 13 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x0e1d16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 29], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f1d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 15 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - LONG $0x7cb60f42; WORD $0x1d3e // movzx edi, byte [rsi + r15 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x011d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 1 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x021d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x031d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 3 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x041d1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 29], 4 + LONG $0x0744b60f; BYTE $0x1c // movzx eax, byte [rdi + rax + 28] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 1 + QUAD $0x021c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 28], 2 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x031c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 3 + QUAD $0x041c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x061c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 6 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x051d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 5 - QUAD $0x061d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 29], 6 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x071d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 29], 7 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x081d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 29], 8 + QUAD $0x071c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 7 + QUAD $0x081c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 9 + QUAD $0x0a1c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 10 + QUAD $0x0b1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 12 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x0d1c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 13 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0e1c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 14 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x0f1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 15 + LONG $0x44b60f42; WORD $0x1c17 // movzx eax, byte [rdi + r10 + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + QUAD $0x011c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 1 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x031c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 28], 3 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 9 - QUAD $0x0a1d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 29], 10 - QUAD $0x0b1d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 11 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0c1d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 12 - QUAD $0x0d1d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 29], 13 + QUAD $0x041c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 5 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x061c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 6 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x071c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 7 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x081c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 8 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x091c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 9 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0a1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 11 + QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] + QUAD $0x0c1c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 12 + QUAD $0x0d1c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 13 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0e1c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 14 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + QUAD $0x0f1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 15 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + LONG $0x0744b60f; BYTE $0x1d // movzx eax, byte [rdi + rax + 29] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x011d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 2 + QUAD $0x031d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 4 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1d06642061e3c4 // vpinsrb xmm4, xmm3, byte [rsi + rax + 29], 14 + QUAD $0x051d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x061d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 7 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x081d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 10 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x0b1d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 12 + QUAD $0x0d1d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 13 + QUAD $0x0e1d0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 29], 14 + QUAD $0x0f1d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 15 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f44b60f; BYTE $0x1d // movzx eax, byte [rdi + rcx + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x011d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 1 + QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] + QUAD $0x021d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 29], 2 + QUAD $0x031d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 3 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x041d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 + QUAD $0x061d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 6 + QUAD $0x071d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 7 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x081d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 8 + QUAD $0x091d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 9 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0a1d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 10 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0b1d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 11 + QUAD $0x0c1d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 12 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x0d1d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 13 + QUAD $0x0e1d07642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r8 + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x0f1d2e442059a3c4 // vpinsrb xmm0, xmm4, byte [rsi + r13 + 29], 15 + QUAD $0x0f1d37442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rsi + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x1e // movzx edi, byte [rsi + rax + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x011e0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 30], 1 - LONG $0x067cb60f; BYTE $0x1f // movzx edi, byte [rsi + rax + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 31], 1 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + LONG $0x3744b60f; BYTE $0x1e // movzx eax, byte [rdi + rsi + 30] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] + QUAD $0x011e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 30], 1 + LONG $0x3744b60f; BYTE $0x1f // movzx eax, byte [rdi + rsi + 31] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011f374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 31], 1 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x051e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 5 + QUAD $0x051f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 5 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + QUAD $0x0b1e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 30], 11 + QUAD $0x0b1f3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 31], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x021e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 2 - QUAD $0x021f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 2 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x031e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 3 - QUAD $0x031f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 3 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x051e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 5 - QUAD $0x051f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 5 - QUAD $0x061e26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 30], 6 - QUAD $0x061f264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 31], 6 - QUAD $0x0000011024ac8b4c // mov r13, qword [rsp + 272] - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 - QUAD $0x0a1e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 30], 10 - QUAD $0x0a1f0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 31], 10 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0b1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 11 - QUAD $0x0b1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 11 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0c1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 12 - QUAD $0x0c1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 13 - QUAD $0x0d1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 13 - QUAD $0x0e1e16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 30], 14 - QUAD $0x0e1f164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 31], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 15 - QUAD $0x0f1f06542071e3c4 // vpinsrb xmm2, xmm1, byte [rsi + rax + 31], 15 - LONG $0x44b60f42; WORD $0x1e3e // movzx eax, byte [rsi + r15 + 30] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542071e3c4 // vpinsrb xmm2, xmm1, byte [rdi + rax + 31], 15 + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x011e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 30], 1 - LONG $0x44b60f42; WORD $0x1f3e // movzx eax, byte [rsi + r15 + 31] + QUAD $0x011e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 31], 1 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x021e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 2 - QUAD $0x021f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 2 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - QUAD $0x041e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 30], 4 - QUAD $0x041f1e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r11 + 31], 4 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x061e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 6 - QUAD $0x061f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 6 - QUAD $0x071e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 30], 7 - QUAD $0x071f167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 31], 7 - QUAD $0x081e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 30], 8 - QUAD $0x081f1e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 31], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 9 - QUAD $0x091f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 9 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 11 - QUAD $0x0b1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 11 - QUAD $0x0c1e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 30], 12 - QUAD $0x0c1f367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 31], 12 + QUAD $0x011f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 1 + QUAD $0x021e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 30], 2 + QUAD $0x021f2f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 31], 2 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 13 - QUAD $0x0d1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 13 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0e1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 14 - QUAD $0x0e1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 14 + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x041e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 4 + QUAD $0x041f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 4 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + QUAD $0x081e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 8 + QUAD $0x081f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 8 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x091e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 9 + QUAD $0x091f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 9 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x0a1e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 10 + QUAD $0x0a1f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 10 + QUAD $0x0b1e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 11 + QUAD $0x0b1f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 15 - QUAD $0x0f1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 15 + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 12 + QUAD $0x0d1e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 30], 13 + QUAD $0x0d1f0f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r9 + 31], 13 + QUAD $0x0e1e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 30], 14 + QUAD $0x0e1f077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 31], 14 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -59478,2004 +60988,2007 @@ LBB10_68: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] - LONG $0x7f7ec1c4; WORD $0x8d44; BYTE $0x60 // vmovdqu yword [r13 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8d54; BYTE $0x40 // vmovdqu yword [r13 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8d64; BYTE $0x20 // vmovdqu yword [r13 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8d4c; BYTE $0x00 // vmovdqu yword [r13 + 4*rcx], ymm1 + LONG $0x7f7ec1c4; WORD $0x8e44; BYTE $0x60 // vmovdqu yword [r14 + 4*rcx + 96], ymm0 + LONG $0x7f7ec1c4; WORD $0x8e54; BYTE $0x40 // vmovdqu yword [r14 + 4*rcx + 64], ymm2 + LONG $0x7f7ec1c4; WORD $0x8e64; BYTE $0x20 // vmovdqu yword [r14 + 4*rcx + 32], ymm4 + LONG $0x7f7ec1c4; WORD $0x8e0c // vmovdqu yword [r14 + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x000001a0248c3b48 // cmp rcx, qword [rsp + 416] - JNE LBB10_68 - QUAD $0x0000026024bc8b4c // mov r15, qword [rsp + 608] - QUAD $0x000001a024bc3b4c // cmp r15, qword [rsp + 416] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - QUAD $0x0000017024a48b4c // mov r12, qword [rsp + 368] - JNE LBB10_70 - JMP LBB10_73 + JNE LBB10_100 + QUAD $0x00000260248c8b48 // mov rcx, qword [rsp + 608] + QUAD $0x000001a0248c3b48 // cmp rcx, qword [rsp + 416] + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] + QUAD $0x0000017024b48b48 // mov rsi, qword [rsp + 368] + JNE LBB10_102 + JMP LBB10_105 -LBB10_43: - LONG $0xe0e78349 // and r15, -32 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB10_72: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000021824848948 // mov qword [rsp + 536], rax - QUAD $0x0000018024bc894c // mov qword [rsp + 384], r15 - LONG $0xbb048d4b // lea rax, [r11 + 4*r15] + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] QUAD $0x0000016824848948 // mov qword [rsp + 360], rax - LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x6e79c1c4; BYTE $0xc5 // vmovd xmm0, r13d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 WORD $0xc031 // xor eax, eax - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 + QUAD $0x0000011024b4894c // mov qword [rsp + 272], r14 -LBB10_44: +LBB10_73: WORD $0x8948; BYTE $0xc3 // mov rbx, rax QUAD $0x0000017824848948 // mov qword [rsp + 376], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x000000d824848948 // mov qword [rsp + 216], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0604b60f // movzx eax, byte [rsi + rax] - WORD $0x8948; BYTE $0xca // mov rdx, rcx + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x1e04b60f // movzx eax, byte [rsi + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x1644b60f; BYTE $0x01 // movzx eax, byte [rsi + rdx + 1] + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1e44b60f; BYTE $0x01 // movzx eax, byte [rsi + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xe86ef9c5 // vmovd xmm5, eax - LONG $0x1644b60f; BYTE $0x02 // movzx eax, byte [rsi + rdx + 2] + LONG $0x0f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rcx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1e44b60f; BYTE $0x02 // movzx eax, byte [rsi + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x1644b60f; BYTE $0x03 // movzx eax, byte [rsi + rdx + 3] + LONG $0x0f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rcx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1e44b60f; BYTE $0x03 // movzx eax, byte [rsi + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x1644b60f; BYTE $0x04 // movzx eax, byte [rsi + rdx + 4] + LONG $0x0f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rcx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000220248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 544], xmm1 - LONG $0x1e44b60f; BYTE $0x04 // movzx eax, byte [rsi + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x1644b60f; BYTE $0x05 // movzx eax, byte [rsi + rdx + 5] + LONG $0x0f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rcx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1e44b60f; BYTE $0x05 // movzx eax, byte [rsi + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x1644b60f; BYTE $0x06 // movzx eax, byte [rsi + rdx + 6] - QUAD $0x0000010824948948 // mov qword [rsp + 264], rdx + LONG $0x0f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rcx + 6] + QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1e44b60f; BYTE $0x06 // movzx eax, byte [rsi + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x1644b60f; BYTE $0x07 // movzx eax, byte [rsi + rdx + 7] + LONG $0x0f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rcx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1e44b60f; BYTE $0x07 // movzx eax, byte [rsi + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax - WORD $0x8949; BYTE $0xdd // mov r13, rbx - LONG $0x20cd8149; WORD $0x0002; BYTE $0x00 // or r13, 544 + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02200d48; WORD $0x0000 // or rax, 544 + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02400d48; WORD $0x0000 // or rax, 576 - WORD $0x8949; BYTE $0xc4 // mov r12, rax - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x60ce8149; WORD $0x0002; BYTE $0x00 // or r14, 608 - QUAD $0x000000c024b4894c // mov qword [rsp + 192], r14 - LONG $0x80cb8148; WORD $0x0002; BYTE $0x00 // or rbx, 640 - QUAD $0x000000f0249c8948 // mov qword [rsp + 240], rbx - WORD $0x8949; BYTE $0xc9 // mov r9, rcx + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02600d48; WORD $0x0000 // or rax, 608 + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x80cb8149; WORD $0x0002; BYTE $0x00 // or r11, 640 + QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 + WORD $0x8949; BYTE $0xd9 // mov r9, rbx LONG $0xa0c98149; WORD $0x0002; BYTE $0x00 // or r9, 672 - QUAD $0x00000088248c894c // mov qword [rsp + 136], r9 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x02c00d48; WORD $0x0000 // or rax, 704 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax - WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x244c894c; BYTE $0x28 // mov qword [rsp + 40], r9 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0xc0ca8149; WORD $0x0002; BYTE $0x00 // or r10, 704 + QUAD $0x000000e02494894c // mov qword [rsp + 224], r10 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02e00d48; WORD $0x0000 // or rax, 736 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax - WORD $0x8949; BYTE $0xcb // mov r11, rcx - LONG $0x00cb8149; WORD $0x0003; BYTE $0x00 // or r11, 768 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0x20cf8148; WORD $0x0003; BYTE $0x00 // or rdi, 800 - LONG $0x247c8948; BYTE $0x58 // mov qword [rsp + 88], rdi - WORD $0x8949; BYTE $0xca // mov r10, rcx - LONG $0x40ca8149; WORD $0x0003; BYTE $0x00 // or r10, 832 - LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - LONG $0x60c88149; WORD $0x0003; BYTE $0x00 // or r8, 864 - QUAD $0x000000a82484894c // mov qword [rsp + 168], r8 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x03800d48; WORD $0x0000 // or rax, 896 + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0x00ce8149; WORD $0x0003; BYTE $0x00 // or r14, 768 + LONG $0x2474894c; BYTE $0x78 // mov qword [rsp + 120], r14 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03200d48; WORD $0x0000 // or rax, 800 + WORD $0x8949; BYTE $0xc4 // mov r12, rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03400d48; WORD $0x0000 // or rax, 832 WORD $0x8949; BYTE $0xc7 // mov r15, rax - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax - WORD $0x8948; BYTE $0xca // mov rdx, rcx - LONG $0xa0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 928 - LONG $0x24548948; BYTE $0x28 // mov qword [rsp + 40], rdx - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + WORD $0x8948; BYTE $0xda // mov rdx, rbx + LONG $0x60ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 864 + QUAD $0x000000c824948948 // mov qword [rsp + 200], rdx + WORD $0x8948; BYTE $0xde // mov rsi, rbx + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + QUAD $0x00000108249c8948 // mov qword [rsp + 264], rbx + LONG $0x80ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 896 + QUAD $0x0000008824b48948 // mov qword [rsp + 136], rsi + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0xa0c88149; WORD $0x0003; BYTE $0x00 // or r8, 928 + LONG $0x2444894c; BYTE $0x70 // mov qword [rsp + 112], r8 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax LONG $0xe0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 992 - QUAD $0x000000d8248c8948 // mov qword [rsp + 216], rcx - QUAD $0x000000f824ac894c // mov qword [rsp + 248], r13 - LONG $0x207923c4; WORD $0x2e0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rsi + r13], 1 - LONG $0x2031a3c4; WORD $0x2604; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rsi + r12], 2 - LONG $0x2079a3c4; WORD $0x3604; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rsi + r14], 3 - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 4 - LONG $0x2079a3c4; WORD $0x0e04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rsi + r9], 5 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 6 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - LONG $0x2079e3c4; WORD $0x1e04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rsi + rbx], 7 - LONG $0x2079a3c4; WORD $0x1e04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rsi + r11], 8 - LONG $0x2079e3c4; WORD $0x3e04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rsi + rdi], 9 - LONG $0x2079a3c4; WORD $0x1604; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rsi + r10], 10 - LONG $0x2079a3c4; WORD $0x0604; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rsi + r8], 11 - LONG $0x2079a3c4; WORD $0x3e04; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rsi + r15], 12 - LONG $0x2079e3c4; WORD $0x1604; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rsi + rdx], 13 - LONG $0x2079e3c4; WORD $0x0604; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rsi + rax], 14 - LONG $0x2079e3c4; WORD $0x0e04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rsi + rcx], 15 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - LONG $0x2061a3c4; WORD $0x061c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rsi + r8], 1 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - LONG $0x2061a3c4; WORD $0x161c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rsi + r10], 2 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - LONG $0x2061e3c4; WORD $0x161c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rsi + rdx], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rsi + rax], 4 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - LONG $0x2061a3c4; WORD $0x0e1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rsi + r9], 5 - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - LONG $0x2061a3c4; WORD $0x361c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rsi + r14], 6 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - LONG $0x2061a3c4; WORD $0x3e1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rsi + r15], 7 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - LONG $0x2061e3c4; WORD $0x3e1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rsi + rdi], 8 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - LONG $0x2061e3c4; WORD $0x061c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rsi + rax], 9 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - LONG $0x2061a3c4; WORD $0x1e1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rsi + r11], 10 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rsi + rcx], 11 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x2061e3c4; WORD $0x0e1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rsi + rcx], 12 + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + LONG $0x207963c4; WORD $0x1f0c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + rbx], 1 + LONG $0x2031a3c4; WORD $0x2f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + r13], 2 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 3 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r11], 4 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + r9], 5 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r10], 6 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + r13], 7 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r14], 8 + LONG $0x2079a3c4; WORD $0x2704; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + r12], 9 + LONG $0x2079a3c4; WORD $0x3f04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r15], 10 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + rdx], 11 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + rsi], 12 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + r8], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rcx], 15 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r15], 1 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + r10], 2 + QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r8], 3 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r9], 4 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r11], 5 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r14], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + rax], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + rax], 8 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rcx], 9 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rdx], 10 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + r12], 11 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rbx], 13 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rbx], 14 QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rsi + rbx], 13 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - LONG $0x2061a3c4; WORD $0x261c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rsi + r12], 14 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - LONG $0x2061e3c4; WORD $0x1e1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rsi + rbx], 15 + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rbx], 15 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x00026024946f7dc5; BYTE $0x00 // vmovdqa ymm10, yword [rsp + 608] LONG $0xd8deadc5 // vpmaxub ymm3, ymm10, ymm0 - QUAD $0x01012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 1 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x02011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 2 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x03012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 3 - QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] - QUAD $0x04012e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 1], 4 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x05011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 5 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x06011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 6 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x07011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 7 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x08011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 8 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x09011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 9 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x0a011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 10 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x01011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 1 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x02011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 2 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x03011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 3 QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0b011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 11 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x0c011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 12 + QUAD $0x04011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 4 LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0d011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 13 + QUAD $0x05011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 5 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x06011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 6 + QUAD $0x07012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 7 LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0e011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 14 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x0f011e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 1], 15 - QUAD $0x0101066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 1], 1 - QUAD $0x0201166c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r10 + 1], 2 - QUAD $0x0301166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 1], 3 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0401166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 1], 4 - QUAD $0x05010e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 1], 5 - QUAD $0x0601366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 1], 6 - QUAD $0x07013e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 1], 7 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x08013e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 1], 8 - QUAD $0x0901066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 9 - QUAD $0x0a011e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 1], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 11 - QUAD $0x0c010e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 1], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d01066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 1], 13 - WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x08011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 8 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x09011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 9 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0a011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 10 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0b011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 11 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0c011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 12 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x0d011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 13 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x0e011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 14 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0f011f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 1], 15 + QUAD $0x01013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 1 + QUAD $0x0201176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 2 + QUAD $0x0301076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 3 + QUAD $0x04010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 4 + QUAD $0x05011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 5 + QUAD $0x0601376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 1], 6 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x07011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 7 + QUAD $0x0801076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 8 + QUAD $0x09010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 9 + QUAD $0x0a01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 10 + QUAD $0x0b01276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 11 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + QUAD $0x0c01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 LONG $0xc374fdc5 // vpcmpeqb ymm0, ymm0, ymm3 QUAD $0x00050024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1280], ymm0 - QUAD $0x0e0126442051a3c4 // vpinsrb xmm0, xmm5, byte [rsi + r12 + 1], 14 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0f0106442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 1], 15 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0e012f442051a3c4 // vpinsrb xmm0, xmm5, byte [rdi + r13 + 1], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f0107442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 1], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x08 // movzx edi, byte [rsi + rax + 8] - LONG $0xf76ef9c5 // vmovd xmm6, edi + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xf06ef9c5 // vmovd xmm6, eax QUAD $0x0001e024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 480] - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x01023e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 2], 1 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x020206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 2 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x030206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 3 - QUAD $0x04022e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 2], 4 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x05021e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 2], 5 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x06020e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 2], 6 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x070206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 2], 7 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x080206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 8 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x090206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 9 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0a0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 10 + QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] + QUAD $0x010217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 1 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x020207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 2 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x03021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 3 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0b0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 11 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0c0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 12 + QUAD $0x040207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 4 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d0206442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 2], 13 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0e0216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 2], 14 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0f020e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 2], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] - QUAD $0x0102065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 2], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x02023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 3 - QUAD $0x0402165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 2], 4 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0502165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 2], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06023e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 2], 6 - QUAD $0x0702365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 2], 7 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0802365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 2], 8 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x0902265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 2], 9 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0a02165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 2], 10 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0b02165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 2], 11 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0c02165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 2], 12 - QUAD $0x0d021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0e021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 14 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0f021e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 2], 15 - QUAD $0x01033e642021a3c4 // vpinsrb xmm4, xmm11, byte [rsi + r15 + 3], 1 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x02031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 2 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x03031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 3 - QUAD $0x04032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 4 - QUAD $0x05031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 5 - QUAD $0x06030e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 3], 6 - QUAD $0x070306642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r8 + 3], 7 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x08032e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 3], 8 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x09031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 9 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x0a031e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 3], 10 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0b031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 11 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x0c031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 12 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0d031e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 3], 13 - QUAD $0x0e0316642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 3], 14 - QUAD $0x0f030e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 3], 15 - QUAD $0x0103066c2039e3c4 // vpinsrb xmm5, xmm8, byte [rsi + rax + 3], 1 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0203066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 3], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0303066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 3 + QUAD $0x050207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x060207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 6 + QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] + QUAD $0x07020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 7 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x08023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x090207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 9 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0403066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0503066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 5 - QUAD $0x06033e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 3], 6 + QUAD $0x0a0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 11 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0c0207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 13 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x0e0237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 2], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0001c0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 448] + QUAD $0x01020f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 2], 1 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0703066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 7 - QUAD $0x0803366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 3], 8 - QUAD $0x0903266c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r12 + 3], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 11 - QUAD $0x0c03166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 3], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 13 + QUAD $0x0202075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 2 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0302075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 3 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x04021f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 2], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0502075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0602075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 6 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0702375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 7 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x0802275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 2], 8 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0902375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 9 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0a02375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 2], 10 + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0d02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 13 + QUAD $0x0e022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 14 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0f022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 15 + QUAD $0x010317642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r10 + 3], 1 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x020317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 2 + QUAD $0x03031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 3 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x040317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 4 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x050317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x060317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 6 + QUAD $0x07030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 7 + QUAD $0x08033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 8 + LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] + QUAD $0x09032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 9 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0a0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 10 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x0b033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 11 + QUAD $0x0c0307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 12 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0d0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 13 + QUAD $0x0e0337642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 3], 14 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0f0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 15 + QUAD $0x01030f6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rcx + 3], 1 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x02031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 2 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x03030f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 3], 3 + QUAD $0x04031f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 3], 4 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x05030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 5 + QUAD $0x0603076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0703076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 7 + QUAD $0x0803276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 3], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + QUAD $0x0a03376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e03066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 3], 14 + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 14 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0f0306442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rax + 3], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x09 // movzx edi, byte [rsi + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x00022024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 544] - QUAD $0x01040e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 4], 1 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x020416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 4], 2 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x03040e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 4], 3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x040406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x050406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 5 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x060436442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 4], 6 - QUAD $0x07043e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 4], 7 - WORD $0x894d; BYTE $0xec // mov r12, r13 - QUAD $0x08042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 8 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x09042e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 4], 9 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x0a041e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 4], 10 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x0b041e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 4], 11 - QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] - QUAD $0x0c041e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 4], 12 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0d043e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 4], 13 + QUAD $0x010417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 1 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x02040f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 4], 2 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x030437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 3 + QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] + QUAD $0x040437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 4], 4 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x050407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 5 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x060427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 4], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x070407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 7 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 14 + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 + QUAD $0x09042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 9 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + QUAD $0x0a0417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 10 + QUAD $0x0b043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 11 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0c043f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 4], 12 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x0d041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 14 + QUAD $0x0f0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0104075c2001e3c4 // vpinsrb xmm3, xmm15, byte [rdi + rax + 4], 1 + QUAD $0x02041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 2 + QUAD $0x03040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 3 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0f0406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 4], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0104065c2001e3c4 // vpinsrb xmm3, xmm15, byte [rsi + rax + 4], 1 - QUAD $0x0204065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 4], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0304065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0404065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 4 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x05043e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 4], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0604065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0704065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 7 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0804065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 8 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0904065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 10 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x0b04065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 4], 11 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x0c04065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 4], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 14 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0f04065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 4], 15 - QUAD $0x01050e642009e3c4 // vpinsrb xmm4, xmm14, byte [rsi + rcx + 5], 1 - QUAD $0x020516642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 5], 2 - QUAD $0x03050e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 5], 3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x040506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 4 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x05050e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rcx + 5], 5 - QUAD $0x060536642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 5], 6 + QUAD $0x0404075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0504075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 5 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0604175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 6 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0704175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 7 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0804175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 8 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0904175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 9 QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x07050e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r9 + 5], 7 - QUAD $0x080526642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r12 + 5], 8 - QUAD $0x09052e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 5], 9 - QUAD $0x0a0516642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 5], 10 - QUAD $0x0b051e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 5], 11 - QUAD $0x0c051e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rbx + 5], 12 - QUAD $0x0d053e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r15 + 5], 13 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e0506642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 5], 14 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0f0516642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r10 + 5], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0105066c2011e3c4 // vpinsrb xmm5, xmm13, byte [rsi + rax + 5], 1 + QUAD $0x0a040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b04175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 11 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0c041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 12 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0d041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 13 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0e041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 14 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0f041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 15 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x01051f642009e3c4 // vpinsrb xmm4, xmm14, byte [rdi + rbx + 5], 1 + QUAD $0x02050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 2 + QUAD $0x030537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 3 + QUAD $0x040537642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 5], 4 + QUAD $0x050507642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 5], 5 + QUAD $0x060527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 6 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x070527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 5], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x080537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 8 + QUAD $0x09052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 9 + QUAD $0x0a0517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 5], 10 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x0b0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 11 + QUAD $0x0c053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 12 + QUAD $0x0d051f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 5], 13 QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x02050e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 5], 2 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x0305366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 5], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0405066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 4 - QUAD $0x05053e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 5], 5 - QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x06051e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 5], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0705066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 5], 7 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0805166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 8 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x0905166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 9 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0a05166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 10 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0b05166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 11 - QUAD $0x0c05066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 5], 12 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0d05166c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdx + 5], 13 + QUAD $0x0e050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 14 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x0f052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 15 + QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] + QUAD $0x0105376c2011a3c4 // vpinsrb xmm5, xmm13, byte [rdi + r14 + 5], 1 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x02050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 2 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x03051f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 5], 3 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x04051f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 5], 4 + QUAD $0x0505076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0605076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 6 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0705176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0805076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0905076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 9 + QUAD $0x0a050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 10 + QUAD $0x0b05176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 11 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0c05076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0e0516442051e3c4 // vpinsrb xmm0, xmm5, byte [rsi + rdx + 5], 14 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - LONG $0x167cb60f; BYTE $0x0a // movzx edi, byte [rsi + rdx + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x0f053e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 5], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e0507442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 5], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f0507442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 5], 15 LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x0a // movzx edi, byte [rsi + rdx + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x010626442019a3c4 // vpinsrb xmm0, xmm12, byte [rsi + r12 + 6], 1 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x02062e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 6], 2 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x030616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 6], 3 - QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] - QUAD $0x040616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 6], 4 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x05061e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 6], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x06063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 6 - QUAD $0x07060e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 6], 7 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x08063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 8 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x09063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 9 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0a063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 10 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0b063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 11 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x0c063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e063e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 6], 14 - QUAD $0x0f0616442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 6], 15 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x01063e6c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rdi + 6], 1 - QUAD $0x02060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 2 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - QUAD $0x0306366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04063e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 6], 4 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x05060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 5 - QUAD $0x06061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 6 - QUAD $0x0706066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 7 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0806066c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r8 + 6], 8 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x0906366c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r14 + 6], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a06066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b06066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 6], 11 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x0c061e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 6], 12 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x0d060e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 6], 13 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0e060e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rcx + 6], 14 - QUAD $0x0f063e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r15 + 6], 15 - QUAD $0x010726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 7], 1 - QUAD $0x02072e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 7], 2 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x03072e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 7], 3 - QUAD $0x040716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 4 - QUAD $0x05071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 5 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x060716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 6 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x070716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 7 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x080716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 8 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x09071e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 7], 9 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0a0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 10 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0b0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 11 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x0c0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 12 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0d0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 13 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0e0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 14 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x0f0716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 7], 15 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0107164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 1 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x01061f442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rbx + 6], 1 + QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] + QUAD $0x02061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x030607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x040607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x050607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x06063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 6 + QUAD $0x070627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 8 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x090627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 10 + QUAD $0x0b0637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 6], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 13 QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0207164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 2 - QUAD $0x0307164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 7], 3 - QUAD $0x04073e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 7], 4 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0507164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 5 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x0607164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 6 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0707164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 7 - QUAD $0x0807064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 7], 8 - QUAD $0x0907364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 7], 9 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0a07164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 7], 10 - QUAD $0x0b07064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 7], 11 - QUAD $0x0c071e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 7], 12 - QUAD $0x0d070e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 7], 13 - QUAD $0x0e070e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 7], 14 + QUAD $0x0e0617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 14 + QUAD $0x0f062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 15 + QUAD $0x0106376c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r14 + 6], 1 + QUAD $0x02060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 2 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0306376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 3 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0406076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 4 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x0506376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 5 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x06060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 6 + QUAD $0x0706176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 7 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x0806176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 8 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x09060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 9 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x0a060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 11 + QUAD $0x0c06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 12 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x0d062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 13 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0e06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 14 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0f060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 15 + QUAD $0x01071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 1 + QUAD $0x02071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 2 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x03070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 3 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x04070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 4 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x05070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 5 + QUAD $0x06073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 6 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x07070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 7 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x08070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 8 + QUAD $0x090727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 9 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0a0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 10 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0b071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 11 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0c070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 12 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x0d073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 13 + QUAD $0x0e0717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 14 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0f0717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 15 + QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] + QUAD $0x01073f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 7], 1 + QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] + QUAD $0x02071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 2 + QUAD $0x0307374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 3 + QUAD $0x0407074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 4 + QUAD $0x0507374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 5 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0607374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 + QUAD $0x0807174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 8 + QUAD $0x09070f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 7], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0c07374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 7], 12 + QUAD $0x0d072f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 7], 13 + QUAD $0x0e07074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 7], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - QUAD $0x0f073e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 7], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc06ef9c5 // vmovd xmm0, eax LONG $0x3875e3c4; WORD $0x01ca // vinserti128 ymm1, ymm1, xmm2, 1 QUAD $0x0004e0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1248], ymm1 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x010807542031e3c4 // vpinsrb xmm2, xmm9, byte [rdi + rax + 8], 1 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0b // movzx edi, byte [rsi + rax + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x010826542031a3c4 // vpinsrb xmm2, xmm9, byte [rsi + r12 + 8], 1 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x020806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 2 - WORD $0x894d; BYTE $0xe8 // mov r8, r13 - QUAD $0x03082e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 8], 3 + QUAD $0x020807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x030807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 3 + QUAD $0x000000a824848b4c // mov r8, qword [rsp + 168] + QUAD $0x040807542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 8], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x050807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x060807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x070807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x090807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 8], 9 + QUAD $0x0a0827542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 8], 10 + QUAD $0x0b081f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 8], 11 + QUAD $0x0c080f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 8], 12 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0d0827542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 8], 13 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0e081f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 8], 14 + QUAD $0x0f0817542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 8], 15 + QUAD $0x01083f6c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r15 + 8], 1 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x02080f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 8], 2 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x040806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 4 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x05082e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 8], 5 + QUAD $0x0308076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 3 + QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] + QUAD $0x0408176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 8], 4 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x060806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 6 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x070816542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 8], 7 + QUAD $0x0508076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 5 + QUAD $0x0608376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 6 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x080806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 8 - QUAD $0x09081e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 8], 9 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0a0806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 10 - QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] - QUAD $0x0b0816542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 8], 11 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x0c0836542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 8], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d080e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 8], 13 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e0806542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 8], 14 - QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] - QUAD $0x0f083e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 8], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0108066c2049e3c4 // vpinsrb xmm5, xmm6, byte [rsi + rax + 8], 1 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0208066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0308066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0408066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 4 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x05080e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r9 + 8], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0608066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 6 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x07083e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rdi + 8], 7 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0808066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 8 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0908066c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rax + 8], 9 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0a081e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 8], 10 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0b081e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 8], 11 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x0c081e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 8], 12 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0d081e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 8], 13 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0e081e6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rsi + rbx + 8], 14 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0f081e6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rsi + r11 + 8], 15 + QUAD $0x0708076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 7 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x08080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 8 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x09080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 9 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0a08176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 10 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0b08376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 11 + QUAD $0x0c08376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 12 + QUAD $0x0d082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 13 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0e082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 14 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0f08376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 8], 15 LONG $0x3855e3c4; WORD $0x01d2 // vinserti128 ymm2, ymm5, xmm2, 1 LONG $0xeadeadc5 // vpmaxub ymm5, ymm10, ymm2 - QUAD $0x010926742039a3c4 // vpinsrb xmm6, xmm8, byte [rsi + r12 + 9], 1 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x02091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 2 - QUAD $0x030906742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r8 + 9], 3 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x01091f742039e3c4 // vpinsrb xmm6, xmm8, byte [rdi + rbx + 9], 1 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + QUAD $0x02091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 2 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x03091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 3 + QUAD $0x040907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 4 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x050907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 5 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x06091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 6 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x07091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 7 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x08091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 8 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x09091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 9 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0a091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 10 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0b091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 11 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x0c091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 12 + QUAD $0x0d0927742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 9], 13 + QUAD $0x0e091f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 9], 14 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x0f091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 15 + QUAD $0x01093f7c2021a3c4 // vpinsrb xmm7, xmm11, byte [rdi + r15 + 9], 1 + QUAD $0x02090f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r9 + 9], 2 QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - QUAD $0x04091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 4 - QUAD $0x05092e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r13 + 9], 5 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x06091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 6 - QUAD $0x070916742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r10 + 9], 7 - WORD $0x894d; BYTE $0xd4 // mov r12, r10 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x08091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 8 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x090916742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r10 + 9], 9 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x0a091e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rbx + 9], 10 - QUAD $0x0b0916742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rdx + 9], 11 - QUAD $0x0c0936742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r14 + 9], 12 - QUAD $0x0d090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e090e742049e3c4 // vpinsrb xmm6, xmm6, byte [rsi + rcx + 9], 14 - QUAD $0x0f093e742049a3c4 // vpinsrb xmm6, xmm6, byte [rsi + r15 + 9], 15 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x01090e7c2021e3c4 // vpinsrb xmm7, xmm11, byte [rsi + rcx + 9], 1 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x02091e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r11 + 9], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x03090e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 9], 3 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x04090e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 9], 4 - QUAD $0x05090e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r9 + 9], 5 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x0609167c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdx + 9], 6 - QUAD $0x07093e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rdi + 9], 7 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x08090e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rcx + 9], 8 - QUAD $0x0909067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 9 - QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] - QUAD $0x0a09367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 9], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 11 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x0c092e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r13 + 9], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 13 + QUAD $0x03091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 3 + QUAD $0x0409177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 9], 4 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0509277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 5 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x06091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 6 + QUAD $0x0709077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0809077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 8 + QUAD $0x09090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 9 + QUAD $0x0a09177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 10 + QUAD $0x0b09377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 12 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e09067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 9], 14 + QUAD $0x0d09077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 13 + QUAD $0x0e092f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r13 + 9], 14 LONG $0xd574edc5 // vpcmpeqb ymm2, ymm2, ymm5 QUAD $0x0004c024947ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0f09066c2041e3c4 // vpinsrb xmm5, xmm7, byte [rsi + rax + 9], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xd76ef9c5 // vmovd xmm2, edi + QUAD $0x0f09376c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r14 + 9], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xd06ef9c5 // vmovd xmm2, eax LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x0004a024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm5 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0c // movzx edi, byte [rsi + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x000000f824bc8b4c // mov r15, qword [rsp + 248] - QUAD $0x010a3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 10], 1 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x020a1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 10], 2 - QUAD $0x030a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 3 - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - QUAD $0x040a065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 10], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x050a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 5 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x060a0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 10], 6 - QUAD $0x070a265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 10], 7 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x080a0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 10], 8 - QUAD $0x090a165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 10], 9 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x0a0a265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 10], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax + QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] + QUAD $0x010a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 1 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x020a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 2 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x030a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 3 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0b0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 11 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0c0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 13 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e0a065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 10], 14 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0f0a165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 10], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x010a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 1 - QUAD $0x020a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x030a3e642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdi + 10], 3 + QUAD $0x040a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 4 + QUAD $0x050a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 5 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x060a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 6 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x070a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 7 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x080a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x090a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 9 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x040a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x050a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 5 - QUAD $0x060a16642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 10], 6 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x070a1e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r11 + 10], 7 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x080a06642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rax + 10], 8 - QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] - QUAD $0x090a16642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 10], 9 - QUAD $0x0a0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 10 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x0b0a36642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r14 + 10], 11 - QUAD $0x0c0a2e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 10], 12 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0d0a16642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 10], 13 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0e0a16642059e3c4 // vpinsrb xmm4, xmm4, byte [rsi + rdx + 10], 14 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x0f0a2e642059a3c4 // vpinsrb xmm4, xmm4, byte [rsi + r13 + 10], 15 - QUAD $0x010b3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 11], 1 - QUAD $0x020b1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 11], 2 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x030b1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 11], 3 - QUAD $0x040b06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 11], 4 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x050b1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 11], 5 - QUAD $0x060b0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 11], 6 - QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] - QUAD $0x070b1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 11], 7 - QUAD $0x080b0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 11], 8 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x090b0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 11], 9 - QUAD $0x0a0b26442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 11], 10 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x0b0b2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 11], 11 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x0c0b3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 11], 12 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0d0b0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 11], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e0b0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 11], 14 - QUAD $0x0f0b16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 11], 15 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x010b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x020b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 2 - QUAD $0x030b3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 11], 3 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x040b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 4 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x050b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 5 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x060b0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 11], 6 - QUAD $0x070b1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 11], 7 - QUAD $0x080b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 8 + QUAD $0x0a0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 10 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x090b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 10 - QUAD $0x0b0b364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 11], 11 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0c0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 13 + QUAD $0x0b0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 11 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0c0a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x010a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x020a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 2 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x040a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 4 + QUAD $0x050a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 5 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x060a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 6 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x070a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 7 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x080a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 8 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x090a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 9 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0a0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 10 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 11 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0c0a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 12 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0d0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 13 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0e0a17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 10], 14 + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] + QUAD $0x0f0a37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 10], 15 + QUAD $0x010b2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 11], 1 + QUAD $0x020b0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 11], 2 + QUAD $0x030b17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 11], 3 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x040b0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 11], 4 + QUAD $0x050b07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 11], 5 + QUAD $0x060b37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 11], 6 + QUAD $0x070b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 7 + QUAD $0x080b3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 11], 8 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x090b17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 11], 9 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x0a0b2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 11], 10 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x0b0b07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 11], 11 + QUAD $0x0c0b1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 11], 12 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0d0b17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 11], 13 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x0e0b1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 11], 14 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x0f0b17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 11], 15 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x010b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 1 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x020b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 2 + QUAD $0x030b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 3 + WORD $0x8949; BYTE $0xc3 // mov r11, rax + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x040b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x050b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 5 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x060b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 6 + QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] + QUAD $0x070b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 7 + QUAD $0x080b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x090b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 11 + QUAD $0x0c0b274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 11], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000480249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm3 - QUAD $0x0e0b164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 11], 14 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - LONG $0x0e7cb60f; BYTE $0x0d // movzx edi, byte [rsi + rcx + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0f0b064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 11], 15 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f0b074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 11], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00046024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0d // movzx edi, byte [rsi + rax + 13] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] - QUAD $0x010c264c2069a3c4 // vpinsrb xmm1, xmm2, byte [rsi + r12 + 12], 1 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x020c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 12], 2 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x030c0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 12], 3 - QUAD $0x040c064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 12], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x050c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 12], 5 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x060c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 12], 6 - QUAD $0x070c1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 12], 7 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x080c1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 12], 8 - QUAD $0x090c0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 12], 9 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0a0c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 12], 10 - QUAD $0x0b0c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 12], 11 - QUAD $0x0c0c3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 12], 12 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x010c074c2069e3c4 // vpinsrb xmm1, xmm2, byte [rdi + rax + 12], 1 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + QUAD $0x020c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 12], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x030c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 3 + QUAD $0x040c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 12], 4 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d0c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 12], 13 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x0e0c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 12], 14 - QUAD $0x0f0c164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 12], 15 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x010c16542051a3c4 // vpinsrb xmm2, xmm5, byte [rsi + r10 + 12], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x020c3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 12], 2 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x030c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 3 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x040c1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 12], 4 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x050c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 5 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x060c3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 12], 6 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x070c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 7 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x080c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 8 - QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] - QUAD $0x090c2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 12], 9 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0a0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 10 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0b0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 11 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0c0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 12 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0d0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 13 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0e0c0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 12], 14 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0f0c16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 12], 15 - QUAD $0x010d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 13], 1 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x020d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 2 - QUAD $0x030d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 3 - QUAD $0x040d065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 13], 4 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x050d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 5 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x060d165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 13], 6 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x070d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 7 - QUAD $0x080d1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 13], 8 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x090d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 9 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x0a0d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 13], 10 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0b0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 11 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x0c0d0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 13], 12 - QUAD $0x0d0d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 13 - QUAD $0x0e0d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 13], 14 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0f0d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 13], 15 - QUAD $0x010d16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 13], 1 - QUAD $0x020d3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 13], 2 + QUAD $0x050c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 5 + QUAD $0x060c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 12], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x070c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 7 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x080c274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 12], 8 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x090c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 12], 9 + QUAD $0x0a0c2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 12], 10 + QUAD $0x0b0c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 12], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c0c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 12 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0d0c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 12], 13 + QUAD $0x0e0c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 12], 14 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x030d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 3 - QUAD $0x040d1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 13], 4 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x050d36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 13], 5 - QUAD $0x060d3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 13], 6 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x070d3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 13], 7 + QUAD $0x0f0c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 12], 15 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + QUAD $0x010c17542051e3c4 // vpinsrb xmm2, xmm5, byte [rdi + rdx + 12], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x020c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 2 + QUAD $0x030c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 3 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x040c0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 12], 4 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x050c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 5 + QUAD $0x060c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 6 + QUAD $0x070c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 7 + QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] + QUAD $0x080c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 12], 8 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x090c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 9 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0a0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 10 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0b0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 11 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0c0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 12 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x0d0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 13 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0e0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 14 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0f0c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 15 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x010d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 1 + QUAD $0x020d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 2 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x030d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 3 + QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] + QUAD $0x040d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 4 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x050d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 5 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x060d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 6 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x070d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 7 + QUAD $0x080d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 13], 8 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x090d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 9 + QUAD $0x0a0d2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 13], 10 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0b0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 11 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x0d0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 13 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x0e0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 14 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0f0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 15 + QUAD $0x010d17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 13], 1 + QUAD $0x020d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 2 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x030d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 3 + QUAD $0x040d0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 13], 4 + QUAD $0x050d07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 13], 5 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x080d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 8 - QUAD $0x090d2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 13], 9 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0a0d2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 13], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b0d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 11 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0c0d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d0d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 13 - QUAD $0x0e0d0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 13], 14 + QUAD $0x060d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x070d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 7 + QUAD $0x080d37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 13], 8 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x090d27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 13], 9 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x0a0d0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 13], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b0d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c0d07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 13], 12 + QUAD $0x0d0d1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 13], 13 + LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] + QUAD $0x0e0d17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 13], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000440248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0f0d06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 13], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x0e // movzx edi, byte [rsi + rax + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x0f0d1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 13], 15 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x0e07 // movzx eax, byte [rdi + r8 + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x00042024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm0 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x0e // movzx edi, byte [rsi + rax + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x010e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 14], 1 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x020e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 14], 2 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x030e0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 14], 3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x040e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 4 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x050e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 5 - QUAD $0x060e164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 14], 6 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x070e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 7 - QUAD $0x080e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 14], 8 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x090e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 9 - QUAD $0x0a0e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 14], 10 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] + QUAD $0x020e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0b0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 11 - QUAD $0x0c0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d0e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 14], 13 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x0e0e1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 14], 14 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x0f0e0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 14], 15 + QUAD $0x040e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 4 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x050e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x060e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + QUAD $0x080e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 14], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x090e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 + QUAD $0x0b0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x020e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 2 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x030e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 14], 3 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x040e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 14], 4 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x050e1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 14], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x060e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x070e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x080e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 8 + QUAD $0x090e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 9 + QUAD $0x0a0e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 14], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 12 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0d0e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 13 + QUAD $0x0e0e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 14 + QUAD $0x0f0e1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 14], 15 + LONG $0x44b60f42; WORD $0x0f07 // movzx eax, byte [rdi + r8 + 15] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x010f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 1 + QUAD $0x020f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 2 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x010e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 1 + QUAD $0x030f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x040f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 4 + QUAD $0x050f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 5 + QUAD $0x060f17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 15], 6 + QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] + QUAD $0x070f2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 15], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x080f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x090f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 11 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0c0f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 15], 12 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0d0f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 15], 13 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x020e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 2 + QUAD $0x0e0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 14 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x030e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x040e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 4 - QUAD $0x050e36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 14], 5 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x060e16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 14], 6 - QUAD $0x070e3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 14], 7 + QUAD $0x0f0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x0f // movzx eax, byte [rdi + rax + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] + QUAD $0x010f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 1 + QUAD $0x020f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 2 + QUAD $0x030f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 3 + QUAD $0x040f3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 15], 4 + QUAD $0x050f1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 15], 5 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x080e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 8 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x090e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 14], 9 - QUAD $0x0a0e2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 14], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 11 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x0c0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 13 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0e0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 14 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0f0e3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 14], 15 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x0f3e // movzx edi, byte [rsi + r15 + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x010f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 1 - QUAD $0x020f16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 15], 2 - QUAD $0x030f0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 15], 3 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x040f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 4 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x050f16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 15], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x060f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 6 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x070f06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 15], 7 - QUAD $0x080f1e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 15], 8 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x090f2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 15], 9 - QUAD $0x0a0f26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 15], 10 - QUAD $0x000000a824b48b4c // mov r14, qword [rsp + 168] - QUAD $0x0b0f36542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 15], 11 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x0c0f26542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 15], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d0f3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 15], 13 - QUAD $0x0e0f1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 15], 14 - QUAD $0x0f0f0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 15], 15 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1e7cb60f; BYTE $0x0f // movzx edi, byte [rsi + rbx + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x010f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x020f0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 15], 2 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x030f0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 15], 3 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x040f1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 15], 4 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x050f3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 15], 5 - QUAD $0x060f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 6 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x070f165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 15], 7 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x080f3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 15], 8 - QUAD $0x090f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 11 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0c0f065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 15], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d0f3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 15], 13 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0e0f3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 15], 14 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0f0f3e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 15], 15 + QUAD $0x060f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 6 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x070f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x080f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x090f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 10 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0b0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 11 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0c0f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 12 + QUAD $0x0d0f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - LONG $0x7cb60f42; WORD $0x103e // movzx edi, byte [rsi + r15 + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 1 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x02103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x03103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 3 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x04103e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 16], 4 - QUAD $0x051016442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 16], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x06103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 6 - QUAD $0x071006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 7 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x08103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 8 - QUAD $0x09102e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 16], 9 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0a103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 10 - QUAD $0x0b1036442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 16], 11 - QUAD $0x0c1026442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 16], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d103e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 16], 13 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0e1006442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 16], 14 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x0f102e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 16], 15 - LONG $0x1e7cb60f; BYTE $0x10 // movzx edi, byte [rsi + rbx + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x01101e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 16], 1 - QUAD $0x02100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 2 - QUAD $0x03100e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 16], 3 - QUAD $0x04101e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 16], 4 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x05100e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 16], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06103e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 16], 6 - QUAD $0x0710164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 7 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x08101e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 16], 8 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x0910264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 16], 9 - QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] - QUAD $0x0a10164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 16], 10 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0b10164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 16], 11 - QUAD $0x0c10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 12 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x01100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 1 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x031007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 3 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x041017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 5 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x06103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 6 + QUAD $0x07102f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 16], 7 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x08100f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 16], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 9 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x0a102f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 16], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 11 + QUAD $0x0c1007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 12 + QUAD $0x0d1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 13 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x0e101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x01101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0210074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 2 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x03101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 3 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0510074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0610074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 6 + QUAD $0x07100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 7 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x0810274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 16], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0910074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 10 + QUAD $0x0b10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 11 + QUAD $0x0c10374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 13 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0e10074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 14 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 13 + QUAD $0x0f10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x11 // movzx eax, byte [rdi + rax + 17] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 1 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x021107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 2 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x031137542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 17], 3 + QUAD $0x041117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 5 + QUAD $0x06113f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 17], 6 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x071117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 7 + QUAD $0x08110f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 17], 8 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x091117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 9 + QUAD $0x0a112f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 17], 10 + QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] + QUAD $0x0b110f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 17], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 13 + QUAD $0x0e111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 14 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x0f110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 15 + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + LONG $0x1f44b60f; BYTE $0x11 // movzx eax, byte [rdi + rbx + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0111075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0211075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 2 + QUAD $0x03111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 3 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x04111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0611375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 6 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x07112f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 17], 7 + QUAD $0x0811275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 8 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0911275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 12 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e10064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 16], 14 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x0f100e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 16], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x11 // movzx edi, byte [rsi + rax + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 1 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x02113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x03113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 3 - QUAD $0x04113e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 17], 4 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x05113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 5 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x06113e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 17], 6 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x07113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 7 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x08113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 8 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x09113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 9 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0a113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 10 - QUAD $0x0b1136542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 17], 11 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x0c113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d113e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 17], 13 - QUAD $0x0e1106542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 17], 14 - QUAD $0x0f112e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 17], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x11 // movzx edi, byte [rsi + rdi + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01111e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 17], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x02113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04113e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 17], 4 - QUAD $0x05110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 5 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x06112e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 17], 6 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x07110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 7 - QUAD $0x08111e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 17], 8 - QUAD $0x0911265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 17], 9 - QUAD $0x0a11165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 17], 10 - QUAD $0x0b11165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 17], 11 - QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] - QUAD $0x0c11265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 17], 12 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0d110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 13 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0e110e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 17], 14 + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + QUAD $0x0e11075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - QUAD $0x0f110e4c2061a3c4 // vpinsrb xmm1, xmm3, byte [rsi + r9 + 17], 15 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f11074c2061e3c4 // vpinsrb xmm1, xmm3, byte [rdi + rax + 17], 15 LONG $0xd8deadc5 // vpmaxub ymm3, ymm10, ymm0 LONG $0xc374fdc5 // vpcmpeqb ymm0, ymm0, ymm3 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 LONG $0x3875e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm1, xmm2, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - LONG $0x067cb60f; BYTE $0x12 // movzx edi, byte [rsi + rax + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x01121e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 18], 1 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x021216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 2 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - QUAD $0x031206442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 18], 3 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - QUAD $0x04121e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 18], 4 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x051216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 5 - QUAD $0x06123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 6 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x07120e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 18], 7 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x081216442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 18], 8 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x091216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 9 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x0a1236442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 18], 10 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x0b123e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 18], 11 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x0c1216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 12 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0d1216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 13 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0e1216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 14 - QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] - QUAD $0x0f1216442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 18], 15 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x12 // movzx edi, byte [rsi + rdx + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0112164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 1 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x0212164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 2 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0312164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 3 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 + QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] + QUAD $0x02123f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 18], 2 + QUAD $0x031237442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 18], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + QUAD $0x071217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 7 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x081207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 18], 8 + QUAD $0x091217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 18], 9 LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0412164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 18], 4 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x05123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 5 - QUAD $0x06122e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 18], 6 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x07123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 7 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x08123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 8 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x09123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 9 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0a123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 11 - QUAD $0x0c12264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 18], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d123e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 18], 13 - QUAD $0x0e120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 14 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0f120e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 18], 15 - LONG $0x067cb60f; BYTE $0x13 // movzx edi, byte [rsi + rax + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x01131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 1 + QUAD $0x0a1217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 10 + QUAD $0x0b120f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 18], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 14 + QUAD $0x0f120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 15 + LONG $0x1f44b60f; BYTE $0x12 // movzx eax, byte [rdi + rbx + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0112074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 1 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0212174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 2 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x03120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 3 + QUAD $0x04121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 4 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x0512374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 5 + QUAD $0x0612374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 6 + QUAD $0x07122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0812074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 8 + QUAD $0x0912274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 9 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x0a120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 10 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x021306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 2 - QUAD $0x031306542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 19], 3 - QUAD $0x04131e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 19], 4 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x051326542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 19], 5 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x06130e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 19], 6 - QUAD $0x07130e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 19], 7 - QUAD $0x081316542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 19], 8 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x09131e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 19], 9 - QUAD $0x0a1336542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 19], 10 - QUAD $0x0b133e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 19], 11 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - QUAD $0x0c131e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 19], 12 + QUAD $0x0b12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 12 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0d12274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 14 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0f12374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 1 + QUAD $0x02133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x031307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 4 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d1306542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 19], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 14 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0f133e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 19], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x13 // movzx edi, byte [rsi + rdi + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x01133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x02133e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 19], 2 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0313065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 19], 3 - QUAD $0x0413165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 4 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0513165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 19], 5 - QUAD $0x06132e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 19], 6 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x0713365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 19], 7 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0813165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 8 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x09133e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 19], 9 - QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] - QUAD $0x0a13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 10 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0b13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 11 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0c13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 12 - QUAD $0x0000012024948b48 // mov rdx, qword [rsp + 288] - QUAD $0x0d13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 13 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0e13165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 19], 14 + QUAD $0x051307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x061307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x071307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 7 + QUAD $0x081307542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 19], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 9 + QUAD $0x0a1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0c1317542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 19], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 15 + LONG $0x1f44b60f; BYTE $0x13 // movzx eax, byte [rdi + rbx + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + QUAD $0x01132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 1 + QUAD $0x0213175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 19], 2 + QUAD $0x03130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 3 + QUAD $0x04131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 4 + QUAD $0x0513375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0613075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x08130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 8 + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + QUAD $0x0913075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 9 + QUAD $0x0a130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 10 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0b133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 + QUAD $0x0d13275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x0f130e442061a3c4 // vpinsrb xmm0, xmm3, byte [rsi + r9 + 19], 15 + QUAD $0x0f1337442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rsi + 19], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 - QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] - LONG $0x167cb60f; BYTE $0x14 // movzx edi, byte [rsi + rdx + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x011416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 1 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x021416442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 20], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x03143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 3 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x04143e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 20], 4 - QUAD $0x051426442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 20], 5 - QUAD $0x06140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 6 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x07140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 7 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x08140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 8 - QUAD $0x09141e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 20], 9 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0a140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 10 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0b140e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 20], 11 - QUAD $0x0c141e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 20], 12 - QUAD $0x0d1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 13 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e1406442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 20], 14 - QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] - QUAD $0x0f141e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 20], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x14 // movzx edi, byte [rsi + rcx + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x01140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x02140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 2 - QUAD $0x0314064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 20], 3 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x04140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 4 - QUAD $0x0514164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 20], 5 - QUAD $0x06142e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 20], 6 - WORD $0x894d; BYTE $0xea // mov r10, r13 - QUAD $0x0714364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 20], 7 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x08140e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 20], 8 - QUAD $0x09143e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 20], 9 - QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] - QUAD $0x0a143e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 20], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 11 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x0c143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 12 - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0d14264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 20], 13 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0e143e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 20], 14 - QUAD $0x0f140e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 20], 15 - QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x1536 // movzx edi, byte [rsi + r14 + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 1 - QUAD $0x021516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 2 - QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] - QUAD $0x031516542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 21], 3 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x04153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 4 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x05153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 5 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x06151e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 21], 6 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x07152e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 21], 7 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x081506542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 21], 8 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x09153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 9 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0a153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 10 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0b153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 11 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x0c153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d153e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 21], 13 - QUAD $0x0e1506542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 21], 14 - QUAD $0x0f151e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 21], 15 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - LONG $0x1e7cb60f; BYTE $0x15 // movzx edi, byte [rsi + rbx + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x14 // movzx eax, byte [rdi + rax + 20] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 1 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x021417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 2 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0115065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 21], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x02153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 2 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x03153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 4 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x05153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 5 - QUAD $0x0615165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 6 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x07153e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 21], 7 - QUAD $0x08150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 8 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x09150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 9 - QUAD $0x0a153e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 21], 10 - LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] - QUAD $0x0b15165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 21], 11 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x0c150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 12 - QUAD $0x0d15265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 21], 13 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0e150e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 21], 14 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x0f150e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 21], 15 + QUAD $0x031407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 3 + QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] + QUAD $0x04141f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 20], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x061427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x071407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 7 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x08140f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 20], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 10 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0b141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 11 + QUAD $0x0c1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 12 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x0d1437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x14 // movzx eax, byte [rdi + rax + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x01142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 + QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] + QUAD $0x03142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 3 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0414074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0514074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0614074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0714074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 7 + QUAD $0x08140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 8 + QUAD $0x0914074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 10 + QUAD $0x0b143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 11 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0c14374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 12 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0d14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 15 + QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x153f // movzx eax, byte [rdi + r15 + 21] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 1 + QUAD $0x021517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x031507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 3 + QUAD $0x04151f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 21], 4 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x051507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 5 + QUAD $0x061527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 6 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x071527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 7 + QUAD $0x08150f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 21], 8 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 10 + QUAD $0x0b151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c1507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 12 + QUAD $0x0d1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 13 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x0e150f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 21], 14 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x0f1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x15 // movzx eax, byte [rdi + rax + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + QUAD $0x01150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0215075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 2 + QUAD $0x03152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 3 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0415075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0515075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x07152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 11 + QUAD $0x0c15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 12 + QUAD $0x0d15175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 13 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0e151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 15 LONG $0x387563c4; WORD $0x01d8 // vinserti128 ymm11, ymm1, xmm0, 1 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 - LONG $0x7cb60f42; WORD $0x1636 // movzx edi, byte [rsi + r14 + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x01160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 1 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x02160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 2 - WORD $0x8949; BYTE $0xd7 // mov r15, rdx - QUAD $0x031616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 3 - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - QUAD $0x041636442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 22], 4 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x051616442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 22], 5 - QUAD $0x06161e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 22], 6 - QUAD $0x07162e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 22], 7 - QUAD $0x081606442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 22], 8 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x09160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 9 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0a160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 10 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0b160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 11 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x0c1626442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r12 + 22], 12 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0d162e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 22], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e160e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 22], 14 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0f163e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 22], 15 - LONG $0x1e7cb60f; BYTE $0x16 // movzx edi, byte [rsi + rbx + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0116064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 1 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0216064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 22], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0316064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 22], 3 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x04161e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 22], 4 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x05163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 6 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x07163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 7 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x08163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 8 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x09163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 9 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0a163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 10 - QUAD $0x0b16164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 22], 11 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x0c163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 13 - QUAD $0x0e160e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 22], 14 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0f163e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 22], 15 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x3e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rdi + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x01173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 1 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x02173e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 23], 2 - QUAD $0x03173e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 23], 3 - QUAD $0x041736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 4 - QUAD $0x051716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 5 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x061716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 6 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x071716542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 23], 7 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x08170e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 23], 8 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x09173e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 23], 9 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x0a1736542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 23], 10 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x0b1716542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 23], 11 - QUAD $0x0c1726542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r12 + 23], 12 - QUAD $0x0d172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 13 - QUAD $0x0e170e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 23], 14 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x0f172e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 23], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0e7cb60f; BYTE $0x17 // movzx edi, byte [rsi + rcx + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0117165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 23], 1 - QUAD $0x0217065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 23], 2 - QUAD $0x0317065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 3 - QUAD $0x04171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 4 + LONG $0x44b60f42; WORD $0x163f // movzx eax, byte [rdi + r15 + 22] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 1 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + QUAD $0x021617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 2 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x031617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 4 + QUAD $0x051607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x061607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 6 + QUAD $0x071627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 7 + QUAD $0x08161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 8 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x09161f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 22], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 12 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0d1637442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 22], 13 + QUAD $0x0e160f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 22], 14 + QUAD $0x0f1637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 15 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + LONG $0x0f44b60f; BYTE $0x16 // movzx eax, byte [rdi + rcx + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x01160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 1 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x02163f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 22], 2 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x03160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 3 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x0416274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 22], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0516074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 5 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x0616374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 22], 6 + QUAD $0x07162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + QUAD $0x0916074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 11 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0517065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 5 + QUAD $0x0c16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + QUAD $0x0e161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 15 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0617065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 6 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0717165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 23], 7 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0817065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 8 - QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] - QUAD $0x09171e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 23], 9 - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - QUAD $0x0a17265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 23], 10 - QUAD $0x0b171e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 23], 11 + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 1 + QUAD $0x021717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 2 + QUAD $0x031717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 3 + QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] + QUAD $0x041717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 5 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x061717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 6 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0c17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 12 - QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] - QUAD $0x0d17065c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r8 + 23], 13 + QUAD $0x071707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 8 + QUAD $0x09171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 10 + QUAD $0x000000c8249c8b4c // mov r11, qword [rsp + 200] + QUAD $0x0b171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 12 + QUAD $0x0d1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 15 + LONG $0x0f44b60f; BYTE $0x17 // movzx eax, byte [rdi + rcx + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + QUAD $0x01171f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 23], 1 + QUAD $0x02173f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 23], 2 + QUAD $0x03170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 3 + QUAD $0x0417275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 23], 4 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x05170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 5 + QUAD $0x0617375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 6 + WORD $0x894c; BYTE $0xee // mov rsi, r13 + QUAD $0x07172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 7 + QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] + QUAD $0x08172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 8 + QUAD $0x0917075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 9 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0a17075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 10 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x0b170f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 23], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 12 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e17065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 23], 14 + QUAD $0x0d17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 14 LONG $0x387563c4; WORD $0x01c8 // vinserti128 ymm9, ymm1, xmm0, 1 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0f171e442061e3c4 // vpinsrb xmm0, xmm3, byte [rsi + rbx + 23], 15 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f1707442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 23], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x18 // movzx edi, byte [rsi + rax + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 1 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x021806442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 24], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x03183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 3 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x04183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 4 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x05183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x06183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 6 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x07183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 7 - QUAD $0x08180e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 24], 8 - QUAD $0x09183e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 24], 9 - QUAD $0x0a1836442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 24], 10 - QUAD $0x0b1816442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 24], 11 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x0c183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e183e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 24], 14 - QUAD $0x0f182e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 24], 15 - LONG $0x0e7cb60f; BYTE $0x18 // movzx edi, byte [rsi + rcx + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0118164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 24], 1 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x02180e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 24], 2 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x03183e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 24], 3 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x04183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 4 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x05180e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 24], 5 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x06183e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 24], 6 - QUAD $0x0718164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 7 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0818164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 8 - QUAD $0x09181e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 24], 9 - QUAD $0x0a18264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 10 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x0b18264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 24], 11 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x0c18164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 12 - QUAD $0x0d18064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 24], 13 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0e18164c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdx + 24], 14 - QUAD $0x0f181e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 24], 15 - QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x1906 // movzx edi, byte [rsi + r8 + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] - QUAD $0x011916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 1 - QUAD $0x021906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 2 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x031936542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r14 + 25], 3 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - QUAD $0x04191e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 25], 4 - QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] - QUAD $0x051916542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 25], 5 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x06191e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rbx + 25], 6 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x071906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 7 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x081906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 8 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x091906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 9 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0a1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 10 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0b1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 11 - QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] - QUAD $0x0c192e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 25], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 13 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x1827 // movzx eax, byte [rdi + r12 + 24] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 1 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x021807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x031807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 3 + QUAD $0x041817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 4 + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x051837442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 24], 5 + QUAD $0x061817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x071807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 7 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0e1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 14 + QUAD $0x081807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 9 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0a1817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 24], 10 + QUAD $0x0b181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 11 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x0c181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x01181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 1 + QUAD $0x02183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 2 + QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] + QUAD $0x03183f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 24], 3 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0f1906542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 25], 15 + QUAD $0x0418074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 4 + QUAD $0x05180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 5 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0618074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 6 + QUAD $0x0718374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 7 + QUAD $0x08182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0918074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 9 + QUAD $0x0a18074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 10 + QUAD $0x0b180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 11 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0c182f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 24], 12 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x0d180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 13 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0e18074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 24], 14 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0f181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 15 + LONG $0x44b60f42; WORD $0x1927 // movzx eax, byte [rdi + r12 + 25] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x01190f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 25], 1 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x067cb60f; BYTE $0x19 // movzx edi, byte [rsi + rax + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0119165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 25], 1 - QUAD $0x02190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 2 - QUAD $0x03193e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 25], 3 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x04190e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 25], 4 - QUAD $0x05190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0619065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 6 + QUAD $0x021907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 2 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x031927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 3 + QUAD $0x041917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 4 + QUAD $0x051937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x061907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 6 + QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] + QUAD $0x071917542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 25], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 9 + QUAD $0x0a1917542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 25], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 11 + QUAD $0x0c191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 12 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x0d191f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 25], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x0f1937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 15 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0719065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 7 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0819065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 25], 8 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x09193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 9 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0a193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 10 - QUAD $0x0b19265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 25], 11 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x0c190e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 25], 12 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0d193e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdi + 25], 13 + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + QUAD $0x03193f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 25], 3 + QUAD $0x000000d824948b48 // mov rdx, qword [rsp + 216] + QUAD $0x0419175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0519075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 5 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x0619375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 25], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0819075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0919075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 9 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0a19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 11 + QUAD $0x0c192f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 25], 12 + QUAD $0x0d190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 13 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0e19164c2061a3c4 // vpinsrb xmm1, xmm3, byte [rsi + r10 + 25], 14 + QUAD $0x0e19074c2061a3c4 // vpinsrb xmm1, xmm3, byte [rdi + r8 + 25], 14 LONG $0xd8deadc5 // vpmaxub ymm3, ymm10, ymm0 LONG $0xc374fdc5 // vpcmpeqb ymm0, ymm0, ymm3 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x0f193e442071e3c4 // vpinsrb xmm0, xmm1, byte [rsi + rdi + 25], 15 + QUAD $0x0f191f442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rbx + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0001a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm0 - LONG $0x7cb60f42; WORD $0x1a06 // movzx edi, byte [rsi + r8 + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x011a06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 26], 1 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x021a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 2 - QUAD $0x031a36442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r14 + 26], 3 - QUAD $0x041a1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 26], 4 - QUAD $0x051a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 5 - QUAD $0x061a1e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rbx + 26], 6 - QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] - QUAD $0x071a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 7 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x081a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 8 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x091a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 9 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0a1a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 10 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x0b1a1e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r11 + 26], 11 - QUAD $0x0c1a2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 26], 12 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0d1a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 13 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0e1a16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 26], 14 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x0f1a3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 26], 15 - QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x1a36 // movzx edi, byte [rsi + r14 + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x011a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x021a3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 26], 2 - QUAD $0x031a3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 26], 3 - QUAD $0x041a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 4 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x051a3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 26], 5 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x061a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 6 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x071a264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 26], 7 - QUAD $0x081a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 8 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x091a1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 26], 9 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0a1a0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 26], 10 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x1a // movzx eax, byte [rdi + rax + 26] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011a0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 26], 1 + QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] + QUAD $0x021a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 2 + QUAD $0x031a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 5 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x061a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 6 + QUAD $0x071a17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 26], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 8 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0b1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 11 - QUAD $0x0c1a0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 26], 12 + QUAD $0x091a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 10 + QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] + QUAD $0x0b1a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 12 + QUAD $0x0d1a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 13 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x0e1a3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 26], 14 + QUAD $0x0f1a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 15 + QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] + LONG $0x44b60f42; WORD $0x1a1f // movzx eax, byte [rdi + r11 + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + QUAD $0x011a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 1 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x021a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 2 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x031a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 3 + QUAD $0x041a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 4 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x051a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 5 + QUAD $0x061a374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 26], 6 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x071a174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 26], 7 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x081a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x091a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 9 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x0a1a2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 26], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 14 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d1a064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 26], 13 - QUAD $0x0e1a164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 26], 14 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x0f1a0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 26], 15 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x1b // movzx edi, byte [rsi + rax + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - QUAD $0x011b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 1 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x021b06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 27], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x031b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 3 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x041b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 4 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x051b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 5 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x061b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 6 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x071b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 7 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x081b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 8 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x091b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 9 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0a1b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 10 - QUAD $0x0b1b1e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r11 + 27], 11 - QUAD $0x0c1b2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 27], 12 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0d1b3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 27], 13 - QUAD $0x0e1b16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 27], 14 - QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] - QUAD $0x0f1b2e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r13 + 27], 15 - LONG $0x7cb60f42; WORD $0x1b36 // movzx edi, byte [rsi + r14 + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x011b365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 27], 1 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x021b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 2 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x031b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 3 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x041b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 4 - QUAD $0x051b3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 27], 5 - QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] - QUAD $0x061b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 6 - QUAD $0x071b265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 27], 7 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x081b165c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rdx + 27], 8 - QUAD $0x091b1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 27], 9 - QUAD $0x0a1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 10 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0b1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 11 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x0c1b1e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r11 + 27], 12 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0d1b1e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rbx + 27], 13 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0e1b0e5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rcx + 27], 14 - QUAD $0x0f1b0e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r9 + 27], 15 + QUAD $0x0f1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 15 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + LONG $0x44b60f42; WORD $0x1b37 // movzx eax, byte [rdi + r14 + 27] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x011b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 1 + QUAD $0x021b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 27], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x031b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 5 + QUAD $0x061b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 8 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + QUAD $0x091b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 27], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 10 + QUAD $0x0b1b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 27], 11 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0c1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 12 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0d1b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 13 + QUAD $0x0e1b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 14 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x0f1b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 27], 15 + LONG $0x44b60f42; WORD $0x1b1f // movzx eax, byte [rdi + r11 + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x011b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 1 + QUAD $0x021b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 2 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x031b1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 27], 3 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x041b1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 27], 4 + QUAD $0x051b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 5 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x061b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 6 + QUAD $0x071b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 7 + QUAD $0x081b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x091b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 9 + QUAD $0x0a1b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 10 + WORD $0x894c; BYTE $0xea // mov rdx, r13 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - LONG $0x067cb60f; BYTE $0x1c // movzx edi, byte [rsi + rax + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 1 - QUAD $0x021c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 2 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x031c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 3 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x041c0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 28], 4 + LONG $0x44b60f42; WORD $0x1c37 // movzx eax, byte [rdi + r14 + 28] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] + QUAD $0x011c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 1 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x021c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x031c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 3 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x041c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 5 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x061c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 6 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x071c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 8 + QUAD $0x091c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 9 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0a1c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 28], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 11 QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x051c06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 28], 5 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x061c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 6 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x071c0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 28], 7 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x081c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 8 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x091c06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 28], 9 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0a1c16442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdx + 28], 10 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x0b1c16442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r10 + 28], 11 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x0c1c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 12 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0d1c3e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r15 + 28], 13 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x0e1c3e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rdi + 28], 14 - QUAD $0x0f1c2e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r13 + 28], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3e7cb60f; BYTE $0x1c // movzx edi, byte [rsi + rdi + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 1 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x021c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 2 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x031c364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 28], 3 - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x041c2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 28], 4 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x051c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 5 - QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] - QUAD $0x061c264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 28], 6 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x071c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 7 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x081c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 8 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x091c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a1c064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 28], 10 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b1c3e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rdi + 28], 11 - QUAD $0x0c1c1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 28], 12 - QUAD $0x0d1c1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 28], 13 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0e1c1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 28], 14 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x0f1c1e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r11 + 28], 15 + QUAD $0x0c1c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 28], 12 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0d1c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 28], 13 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0e1c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 14 + QUAD $0x0f1c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 15 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - LONG $0x067cb60f; BYTE $0x1d // movzx edi, byte [rsi + rax + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x011d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 1 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x021d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x031d3e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdi + 29], 3 - QUAD $0x041d0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 29], 4 - QUAD $0x051d06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 29], 5 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x061d06542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r8 + 29], 6 - QUAD $0x071d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 7 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x081d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 8 + LONG $0x0744b60f; BYTE $0x1c // movzx eax, byte [rdi + rax + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + QUAD $0x011c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + QUAD $0x031c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 3 + QUAD $0x041c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 5 + QUAD $0x061c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 6 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x071c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x081c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 8 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x091c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 9 + QUAD $0x0a1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 10 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0b1c3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 28], 11 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0c1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0d1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 13 LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x091d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 9 - QUAD $0x0a1d16542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rdx + 29], 10 - QUAD $0x0b1d16542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r10 + 29], 11 - QUAD $0x000000e0248c8b4c // mov r9, qword [rsp + 224] - QUAD $0x0c1d0e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r9 + 29], 12 - QUAD $0x0d1d3e542069a3c4 // vpinsrb xmm2, xmm2, byte [rsi + r15 + 29], 13 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0e1d0e542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rcx + 29], 14 + QUAD $0x0e1c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 14 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + LONG $0x0744b60f; BYTE $0x1d // movzx eax, byte [rdi + rax + 29] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 1 + QUAD $0x021d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 2 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x031d37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 29], 3 + QUAD $0x041d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 4 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x051d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 5 + QUAD $0x061d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 6 + QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] + QUAD $0x071d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 7 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 9 + QUAD $0x0a1d37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 29], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 11 + QUAD $0x0c1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 12 + QUAD $0x0d1d17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 29], 13 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0e1d07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 29], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 15 + QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] + LONG $0x44b60f42; WORD $0x1d17 // movzx eax, byte [rdi + r10 + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000f824a48b4c // mov r12, qword [rsp + 248] + QUAD $0x011d275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 29], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x021d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 2 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x031d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 3 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0f1d06542069e3c4 // vpinsrb xmm2, xmm2, byte [rsi + rax + 29], 15 - QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] - LONG $0x167cb60f; BYTE $0x1d // movzx edi, byte [rsi + rdx + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x011d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 1 - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - QUAD $0x021d3e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r15 + 29], 2 - QUAD $0x031d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 3 - QUAD $0x041d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 29], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x051d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 5 - QUAD $0x061d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 29], 6 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x071d265c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r12 + 29], 7 + QUAD $0x041d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x081d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 8 - QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] - QUAD $0x091d365c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r14 + 29], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 10 - LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] - QUAD $0x0b1d165c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r10 + 29], 11 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x0c1d2e5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rsi + r13 + 29], 12 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d1d065c2061e3c4 // vpinsrb xmm3, xmm3, byte [rsi + rax + 29], 13 - QUAD $0x0e1d1e642061e3c4 // vpinsrb xmm4, xmm3, byte [rsi + rbx + 29], 14 + QUAD $0x061d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 6 + QUAD $0x071d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 7 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x081d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 8 + QUAD $0x091d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 9 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0a1d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 10 + QUAD $0x0b1d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 29], 11 + QUAD $0x0c1d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 12 + WORD $0x8949; BYTE $0xd7 // mov r15, rdx + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0d1d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 13 + QUAD $0x0e1d0f642061e3c4 // vpinsrb xmm4, xmm3, byte [rdi + rcx + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x0f1d1e442059a3c4 // vpinsrb xmm0, xmm4, byte [rsi + r11 + 29], 15 - WORD $0x894c; BYTE $0xdb // mov rbx, r11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0f1d07442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rax + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] - LONG $0x7cb60f42; WORD $0x1e1e // movzx edi, byte [rsi + r11 + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x011e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 1 - LONG $0x7cb60f42; WORD $0x1f1e // movzx edi, byte [rsi + r11 + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 1 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x021e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 2 - QUAD $0x021f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 2 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x031e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 3 - QUAD $0x031f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x041e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 4 - QUAD $0x041f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 4 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x011e37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011f374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 31], 1 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + WORD $0x894c; BYTE $0xf0 // mov rax, r14 + QUAD $0x031e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 30], 3 + QUAD $0x031f374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 31], 3 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + QUAD $0x051e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 30], 5 + QUAD $0x051f2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 31], 5 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + QUAD $0x071e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 7 + QUAD $0x071f0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 31], 7 + QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 10 + QUAD $0x0a1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 11 + QUAD $0x0b1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 11 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x051e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 5 - QUAD $0x051f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 5 - QUAD $0x061e06442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r8 + 30], 6 - QUAD $0x061f064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 31], 6 - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x071e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 7 - QUAD $0x071f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 7 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x081e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 8 - QUAD $0x081f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 8 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x091e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 9 - QUAD $0x091f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 9 + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0a1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 10 - QUAD $0x0a1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 10 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0b1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 11 - QUAD $0x0b1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 11 - QUAD $0x0c1e0e442079a3c4 // vpinsrb xmm0, xmm0, byte [rsi + r9 + 30], 12 - QUAD $0x0c1f0e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r9 + 31], 12 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0d1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 13 - QUAD $0x0d1f064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 31], 13 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x0e1e0e442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rcx + 30], 14 - QUAD $0x0e1f0e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rcx + 31], 14 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0f1e06442079e3c4 // vpinsrb xmm0, xmm0, byte [rsi + rax + 30], 15 - QUAD $0x0f1f06542071e3c4 // vpinsrb xmm2, xmm1, byte [rsi + rax + 31], 15 - LONG $0x1644b60f; BYTE $0x1e // movzx eax, byte [rsi + rdx + 30] + QUAD $0x0d1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 13 + QUAD $0x0d1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 13 + QUAD $0x0e1e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 30], 14 + QUAD $0x0e1f074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 31], 14 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542071e3c4 // vpinsrb xmm2, xmm1, byte [rdi + rax + 31], 15 + WORD $0x894c; BYTE $0xd1 // mov rcx, r10 + LONG $0x44b60f42; WORD $0x1e17 // movzx eax, byte [rdi + r10 + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x011e064c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r8 + 30], 1 - LONG $0x1644b60f; BYTE $0x1f // movzx eax, byte [rsi + rdx + 31] + QUAD $0x011e274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 30], 1 + LONG $0x44b60f42; WORD $0x1f17 // movzx eax, byte [rdi + r10 + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f067c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r8 + 31], 1 - QUAD $0x021e3e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r15 + 30], 2 - QUAD $0x021f3e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r15 + 31], 2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x031e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x041e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 4 - QUAD $0x041f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 4 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x051e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 5 - QUAD $0x051f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 5 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x061e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 6 - QUAD $0x061f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 6 - QUAD $0x071e264c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r12 + 30], 7 - QUAD $0x071f267c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r12 + 31], 7 + QUAD $0x011f277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 31], 1 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 2 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x081e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 8 - QUAD $0x081f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 8 - QUAD $0x091e364c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r14 + 30], 9 - QUAD $0x091f367c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r14 + 31], 9 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0a1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 10 - QUAD $0x0a1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 10 - QUAD $0x0b1e164c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r10 + 30], 11 - QUAD $0x0b1f167c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r10 + 31], 11 - QUAD $0x0c1e2e4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rsi + r13 + 30], 12 - QUAD $0x0c1f2e7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rsi + r13 + 31], 12 + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x081e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 8 + QUAD $0x081f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x091e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 9 + QUAD $0x091f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 9 + QUAD $0x0a1e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 10 + QUAD $0x0a1f1f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 31], 10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x0c1e3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 30], 12 + QUAD $0x0c1f3f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 31], 12 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x0d1e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 13 + QUAD $0x0d1f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 13 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0e1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 14 + QUAD $0x0e1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 14 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0d1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 13 - QUAD $0x0d1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 13 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e1e064c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rax + 30], 14 - QUAD $0x0e1f067c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rax + 31], 14 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x0f1e1e4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rsi + rbx + 30], 15 - QUAD $0x0f1f1e7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rsi + rbx + 31], 15 + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -61639,21 +63152,21 @@ LBB10_44: LONG $0x3865e3c4; WORD $0x01e0 // vinserti128 ymm4, ymm3, xmm0, 1 LONG $0x4665e3c4; WORD $0x31c0 // vperm2i128 ymm0, ymm3, ymm0, 49 QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] - LONG $0x7f7ec1c4; WORD $0x8b44; BYTE $0x60 // vmovdqu yword [r11 + 4*rcx + 96], ymm0 - LONG $0x7f7ec1c4; WORD $0x8b54; BYTE $0x40 // vmovdqu yword [r11 + 4*rcx + 64], ymm2 - LONG $0x7f7ec1c4; WORD $0x8b64; BYTE $0x20 // vmovdqu yword [r11 + 4*rcx + 32], ymm4 - LONG $0x7f7ec1c4; WORD $0x8b0c // vmovdqu yword [r11 + 4*rcx], ymm1 + LONG $0x7f7ec1c4; WORD $0x8e44; BYTE $0x60 // vmovdqu yword [r14 + 4*rcx + 96], ymm0 + LONG $0x7f7ec1c4; WORD $0x8e54; BYTE $0x40 // vmovdqu yword [r14 + 4*rcx + 64], ymm2 + LONG $0x7f7ec1c4; WORD $0x8e64; BYTE $0x20 // vmovdqu yword [r14 + 4*rcx + 32], ymm4 + LONG $0x7f7ec1c4; WORD $0x8e0c // vmovdqu yword [r14 + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB10_44 - QUAD $0x0000017024bc8b4c // mov r15, qword [rsp + 368] - QUAD $0x0000018024bc3b4c // cmp r15, qword [rsp + 384] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] - QUAD $0x0000021824a48b4c // mov r12, qword [rsp + 536] - JNE LBB10_46 - JMP LBB10_49 + JNE LBB10_73 + QUAD $0x00000170248c8b48 // mov rcx, qword [rsp + 368] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x0000011824bc8b4c // mov r15, qword [rsp + 280] + LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] + QUAD $0x0000021824b48b48 // mov rsi, qword [rsp + 536] + JNE LBB10_75 + JMP LBB10_78 DATA LCDATA8<>+0x000(SB)/8, $0x0202020202020202 DATA LCDATA8<>+0x008(SB)/8, $0x0202020202020202 @@ -61683,11 +63196,7 @@ DATA LCDATA8<>+0x0c0(SB)/8, $0x8080808080808080 DATA LCDATA8<>+0x0c8(SB)/8, $0x8080808080808080 DATA LCDATA8<>+0x0d0(SB)/8, $0x8080808080808080 DATA LCDATA8<>+0x0d8(SB)/8, $0x8080808080808080 -DATA LCDATA8<>+0x0e0(SB)/8, $0xffffffffffffffff -DATA LCDATA8<>+0x0e8(SB)/8, $0xffffffffffffffff -DATA LCDATA8<>+0x0f0(SB)/8, $0xffffffffffffffff -DATA LCDATA8<>+0x0f8(SB)/8, $0xffffffffffffffff -GLOBL LCDATA8<>(SB), 8, $256 +GLOBL LCDATA8<>(SB), 8, $224 TEXT ·_comparison_greater_equal_scalar_arr_avx2(SB), $1320-48 @@ -61703,291 +63212,319 @@ TEXT ·_comparison_greater_equal_scalar_arr_avx2(SB), $1320-48 MOVQ BP, 1280(SP) LEAQ LCDATA8<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xcf // mov r15, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB11_26 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB11_24 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB11_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB11_99 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB11_114 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB11_185 - WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_17 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB11_113 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB11_131 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB11_211 + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_15 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_13 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_12: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_12 + +LBB11_13: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 LBB11_15: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1f // movzx r8d, byte [r15 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1f3c8841 // mov byte [r15 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_15 - LONG $0x01c78349 // add r15, 1 + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_19 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax LBB11_17: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_21 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 + QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] + LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] + QUAD $0x000001202494930f // setae byte [rsp + 288] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + QUAD $0x000001402494930f // setae byte [rsp + 320] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] + LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] + QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] + LONG $0xd7930f40 // setae dil + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] + LONG $0xd3930f41 // setae r11b + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] + LONG $0xd2930f41 // setae r10b + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] + LONG $0xd1930f41 // setae r9b + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] + LONG $0xd6930f40 // setae sil + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] + WORD $0x930f; BYTE $0xd3 // setae bl + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] + WORD $0x930f; BYTE $0xd1 // setae cl + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] + LONG $0xd5930f41 // setae r13b + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] + LONG $0xd4930f41 // setae r12b + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] + LONG $0xd7930f41 // setae r15b + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + QUAD $0x000000a82494930f // setae byte [rsp + 168] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd6930f41 // setae r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] + QUAD $0x000000982494930f // setae byte [rsp + 152] + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000009824b40240 // add sil, byte [rsp + 152] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017f8841 // mov byte [r15 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x50244402 // add al, byte [rsp + 80] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02478841 // mov byte [r15 + 2], al + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xc000 // add al, al + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x80ea8348 // sub rdx, -128 + LONG $0x04c78349 // add r15, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB11_17 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] LBB11_19: - QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 - LONG $0x7c723b44 // cmp r14d, dword [rdx + 124] - LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] - LONG $0x78723b44 // cmp r14d, dword [rdx + 120] - QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0x74723b44 // cmp r14d, dword [rdx + 116] - QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0x70723b44 // cmp r14d, dword [rdx + 112] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x6c723b44 // cmp r14d, dword [rdx + 108] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x68723b44 // cmp r14d, dword [rdx + 104] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x64723b44 // cmp r14d, dword [rdx + 100] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x5c723b44 // cmp r14d, dword [rdx + 92] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x58723b44 // cmp r14d, dword [rdx + 88] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x54723b44 // cmp r14d, dword [rdx + 84] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x50723b44 // cmp r14d, dword [rdx + 80] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x4c723b44 // cmp r14d, dword [rdx + 76] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x48723b44 // cmp r14d, dword [rdx + 72] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x44723b44 // cmp r14d, dword [rdx + 68] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x3c723b44 // cmp r14d, dword [rdx + 60] - LONG $0xd0930f41 // setae r8b - LONG $0x38723b44 // cmp r14d, dword [rdx + 56] - QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x34723b44 // cmp r14d, dword [rdx + 52] - QUAD $0x000000882494930f // setae byte [rsp + 136] - LONG $0x30723b44 // cmp r14d, dword [rdx + 48] - LONG $0xd3930f41 // setae r11b - LONG $0x2c723b44 // cmp r14d, dword [rdx + 44] - LONG $0xd2930f41 // setae r10b - LONG $0x28723b44 // cmp r14d, dword [rdx + 40] - LONG $0xd1930f41 // setae r9b - LONG $0x24723b44 // cmp r14d, dword [rdx + 36] - LONG $0xd7930f40 // setae dil - LONG $0x1c723b44 // cmp r14d, dword [rdx + 28] - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x18723b44 // cmp r14d, dword [rdx + 24] - WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x14723b44 // cmp r14d, dword [rdx + 20] - LONG $0xd6930f40 // setae sil - LONG $0x10723b44 // cmp r14d, dword [rdx + 16] - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x0c723b44 // cmp r14d, dword [rdx + 12] - LONG $0xd5930f41 // setae r13b - LONG $0x08723b44 // cmp r14d, dword [rdx + 8] - LONG $0xd4930f41 // setae r12b - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] - LONG $0xd7930f41 // setae r15b - LONG $0x20723b44 // cmp r14d, dword [rdx + 32] - QUAD $0x000000a82494930f // setae byte [rsp + 168] - LONG $0x40723b44 // cmp r14d, dword [rdx + 64] - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x60723b44 // cmp r14d, dword [rdx + 96] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000a024bc0244 // add r15b, byte [rsp + 160] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a824bc0240 // add dil, byte [rsp + 168] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x80ea8348 // sub rdx, -128 - LONG $0x04c78349 // add r15, 4 - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB11_19 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_211 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_149 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB11_22 -LBB11_21: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_130 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_24 - -LBB11_26: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB11_27 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB11_149 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB11_164 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB11_185 - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fbc5 // vmovsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_49 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_47: - LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil +LBB11_24: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB11_25 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB11_170 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB11_187 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB11_211 + WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_49 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6ef9c1c4; BYTE $0xc6 // vmovq xmm0, r14 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_48: + LONG $0x08518d48 // lea rdx, [rcx + 8] + LONG $0x012ef9c5 // vucomisd xmm0, qword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x07 // movzx r9d, byte [r15 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_47 - LONG $0x01c78349 // add r15, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x073c8841 // mov byte [r15 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_48 LBB11_49: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_53 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 LBB11_51: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_55 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000a024b4894c // mov qword [rsp + 160], r14 + LONG $0x6ef9c1c4; BYTE $0xc6 // vmovq xmm0, r14 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + +LBB11_53: QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - QUAD $0x000000a82494930f // setae byte [rsp + 168] + QUAD $0x000000982494930f // setae byte [rsp + 152] LONG $0x422ef9c5; BYTE $0x08 // vucomisd xmm0, qword [rdx + 8] LONG $0xd1930f41 // setae r9b LONG $0x422ef9c5; BYTE $0x10 // vucomisd xmm0, qword [rdx + 16] @@ -61995,15 +63532,15 @@ LBB11_51: LONG $0x422ef9c5; BYTE $0x18 // vucomisd xmm0, qword [rdx + 24] LONG $0xd5930f41 // setae r13b LONG $0x422ef9c5; BYTE $0x20 // vucomisd xmm0, qword [rdx + 32] - QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x422ef9c5; BYTE $0x28 // vucomisd xmm0, qword [rdx + 40] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0x422ef9c5; BYTE $0x30 // vucomisd xmm0, qword [rdx + 48] WORD $0x930f; BYTE $0xd3 // setae bl LONG $0x422ef9c5; BYTE $0x38 // vucomisd xmm0, qword [rdx + 56] LONG $0xd4930f41 // setae r12b LONG $0x422ef9c5; BYTE $0x40 // vucomisd xmm0, qword [rdx + 64] - QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] LONG $0x422ef9c5; BYTE $0x48 // vucomisd xmm0, qword [rdx + 72] LONG $0xd6930f40 // setae sil LONG $0x422ef9c5; BYTE $0x50 // vucomisd xmm0, qword [rdx + 80] @@ -62015,21 +63552,21 @@ LBB11_51: LONG $0x422ef9c5; BYTE $0x68 // vucomisd xmm0, qword [rdx + 104] LONG $0xd7930f41 // setae r15b LONG $0x422ef9c5; BYTE $0x70 // vucomisd xmm0, qword [rdx + 112] - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0x422ef9c5; BYTE $0x78 // vucomisd xmm0, qword [rdx + 120] WORD $0x930f; BYTE $0xd1 // setae cl QUAD $0x00000080822ef9c5 // vucomisd xmm0, qword [rdx + 128] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + QUAD $0x000000802494930f // setae byte [rsp + 128] QUAD $0x00000088822ef9c5 // vucomisd xmm0, qword [rdx + 136] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] QUAD $0x00000090822ef9c5 // vucomisd xmm0, qword [rdx + 144] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] QUAD $0x00000098822ef9c5 // vucomisd xmm0, qword [rdx + 152] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] QUAD $0x000000a0822ef9c5 // vucomisd xmm0, qword [rdx + 160] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + QUAD $0x000000882494930f // setae byte [rsp + 136] QUAD $0x000000a8822ef9c5 // vucomisd xmm0, qword [rdx + 168] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] QUAD $0x000000b0822ef9c5 // vucomisd xmm0, qword [rdx + 176] LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] QUAD $0x000000b8822ef9c5 // vucomisd xmm0, qword [rdx + 184] @@ -62037,11 +63574,11 @@ LBB11_51: QUAD $0x000000c0822ef9c5 // vucomisd xmm0, qword [rdx + 192] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] QUAD $0x000000c8822ef9c5 // vucomisd xmm0, qword [rdx + 200] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] QUAD $0x000000d0822ef9c5 // vucomisd xmm0, qword [rdx + 208] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + QUAD $0x000000d8822ef9c5 // vucomisd xmm0, qword [rdx + 216] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] QUAD $0x000000e0822ef9c5 // vucomisd xmm0, qword [rdx + 224] QUAD $0x000001402494930f // setae byte [rsp + 320] QUAD $0x000000e8822ef9c5 // vucomisd xmm0, qword [rdx + 232] @@ -62051,536 +63588,355 @@ LBB11_51: QUAD $0x000000f8822ef9c5 // vucomisd xmm0, qword [rdx + 248] WORD $0x930f; BYTE $0xd0 // setae al WORD $0x0045; BYTE $0xc9 // add r9b, r9b - QUAD $0x000000a8248c0244 // add r9b, byte [rsp + 168] + QUAD $0x00000098248c0244 // add r9b, byte [rsp + 152] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e4c041 // shl r12b, 7 WORD $0x0841; BYTE $0xdc // or r12b, bl LONG $0x02e3c041 // shl r11b, 2 WORD $0x0845; BYTE $0xcb // or r11b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000008824b40240 // add sil, byte [rsp + 136] + LONG $0x24740240; BYTE $0x58 // add sil, byte [rsp + 88] LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xdd // or r13b, r11b LONG $0x02e7c040 // shl dil, 2 WORD $0x0840; BYTE $0xf7 // or dil, sil - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xeb // or bl, r13b WORD $0xde89 // mov esi, ebx LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e7c041 // shl r15b, 5 WORD $0x0845; BYTE $0xd7 // or r15b, r10b - QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] + LONG $0x2474b60f; BYTE $0x60 // movzx esi, byte [rsp + 96] LONG $0x06e6c040 // shl sil, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xdc // or r12b, bl - WORD $0x0844; BYTE $0xf9 // or cl, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xdb00 // add bl, bl - LONG $0x48245c02 // add bl, byte [rsp + 72] - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0x8845; BYTE $0x27 // mov byte [r15], r12b - LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xf6 // or r14b, sil - LONG $0x014f8841 // mov byte [r15 + 1], cl - WORD $0x0841; BYTE $0xde // or r14b, bl - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02778845 // mov byte [r15 + 2], r14b - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c78349 // add r15, 4 - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB11_51 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - -LBB11_53: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_179 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_181 - -LBB11_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB11_56 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB11_185 - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_6: - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_6 - LONG $0x01c78349 // add r15, 1 - -LBB11_8: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_9 - LONG $0x20fe8349 // cmp r14, 32 - LONG $0x245c8944; BYTE $0x1c // mov dword [rsp + 28], r11d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 - JB LBB11_82 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc7 // cmp r15, rax - JAE LBB11_85 - LONG $0xb7048d4b // lea rax, [r15 + 4*r14] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB11_85 - -LBB11_82: - WORD $0xc031 // xor eax, eax - QUAD $0x000001a024848948 // mov qword [rsp + 416], rax - WORD $0x894d; BYTE $0xfd // mov r13, r15 - -LBB11_88: - QUAD $0x000001a024b42b4c // sub r14, qword [rsp + 416] - QUAD $0x000000b024b4894c // mov qword [rsp + 176], r14 - -LBB11_89: - LONG $0x1f5a3a44 // cmp r11b, byte [rdx + 31] - QUAD $0x0000011024949d0f // setge byte [rsp + 272] - LONG $0x1e5a3a44 // cmp r11b, byte [rdx + 30] - QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x1d5a3a44 // cmp r11b, byte [rdx + 29] - QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0x1c5a3a44 // cmp r11b, byte [rdx + 28] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x1b5a3a44 // cmp r11b, byte [rdx + 27] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x1a5a3a44 // cmp r11b, byte [rdx + 26] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x195a3a44 // cmp r11b, byte [rdx + 25] - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x175a3a44 // cmp r11b, byte [rdx + 23] - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x165a3a44 // cmp r11b, byte [rdx + 22] - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x155a3a44 // cmp r11b, byte [rdx + 21] - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x145a3a44 // cmp r11b, byte [rdx + 20] - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x135a3a44 // cmp r11b, byte [rdx + 19] - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x125a3a44 // cmp r11b, byte [rdx + 18] - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x115a3a44 // cmp r11b, byte [rdx + 17] - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x0f5a3a44 // cmp r11b, byte [rdx + 15] - LONG $0xd69d0f41 // setge r14b - LONG $0x0e5a3a44 // cmp r11b, byte [rdx + 14] - QUAD $0x0000008824949d0f // setge byte [rsp + 136] - LONG $0x0d5a3a44 // cmp r11b, byte [rdx + 13] - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x0c5a3a44 // cmp r11b, byte [rdx + 12] - LONG $0xd49d0f41 // setge r12b - LONG $0x0b5a3a44 // cmp r11b, byte [rdx + 11] - LONG $0xd79d0f41 // setge r15b - LONG $0x0a5a3a44 // cmp r11b, byte [rdx + 10] - LONG $0xd39d0f41 // setge r11b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] - LONG $0xd29d0f41 // setge r10b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd79d0f40 // setge dil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0xd19d0f41 // setge r9b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0xd09d0f41 // setge r8b - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0xd69d0f40 // setge sil - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x023a // cmp al, byte [rdx] - QUAD $0x0000009824949d0f // setge byte [rsp + 152] - LONG $0x1c24448b // mov eax, dword [rsp + 28] - WORD $0x423a; BYTE $0x01 // cmp al, byte [rdx + 1] - WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] - LONG $0x086a3a44 // cmp r13b, byte [rdx + 8] - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x000000a824949d0f // setge byte [rsp + 168] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5a3a; BYTE $0x10 // cmp bl, byte [rdx + 16] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x1c245c8b // mov ebx, dword [rsp + 28] - WORD $0x5a3a; BYTE $0x18 // cmp bl, byte [rdx + 24] - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - WORD $0xc000 // add al, al - LONG $0x98248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 152] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al - LONG $0x03e6c040 // shl sil, 3 - WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x04e0c041 // shl r8b, 4 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x05e1c041 // shl r9b, 5 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xc7 // or dil, al - WORD $0x0844; BYTE $0xcf // or dil, r9b - LONG $0x007d8841 // mov byte [r13], dil - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000a824940244 // add r10b, byte [rsp + 168] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xe0 // or al, r12b - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xce // or r14b, cl - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x01758845 // mov byte [r13 + 1], r14b - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x60244402 // add al, byte [rsp + 96] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0x0841; BYTE $0xdc // or r12b, bl + WORD $0x0844; BYTE $0xf9 // or cl, r15b + QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + WORD $0xdb00 // add bl, bl + LONG $0x80249c02; WORD $0x0000; BYTE $0x00 // add bl, byte [rsp + 128] + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x8845; BYTE $0x27 // mov byte [r15], r12b + LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xf6 // or r14b, sil + LONG $0x014f8841 // mov byte [r15 + 1], cl + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xc900 // add cl, cl + LONG $0x20244c02 // add cl, byte [rsp + 32] + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000140248cb60f // movzx ecx, byte [rsp + 320] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd908 // or cl, bl + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x20c28348 // add rdx, 32 - LONG $0x04c58349 // add r13, 4 - QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 - JNE LBB11_89 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - JMP LBB11_91 + LONG $0x02778845 // mov byte [r15 + 2], r14b + LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c78349 // add r15, 4 + QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 + JNE LBB11_53 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB11_27: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB11_132 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB11_185 - WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax +LBB11_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB11_211 + LONG $0x6ef9c1c4; BYTE $0xc6 // vmovq xmm0, r14 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_204 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB11_206 + +LBB11_2: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB11_58 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB11_211 + WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_5 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_88 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB11_94: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + WORD $0x9d0f; BYTE $0xd2 // setge dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1f048841 // mov byte [r15 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB11_94 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JNE LBB11_90 + JMP LBB11_211 + +LBB11_25: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB11_151 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB11_211 + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax JE LBB11_33 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_31 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_30: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_30 LBB11_31: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1f // movzx r8d, byte [r15 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1f3c8841 // mov byte [r15 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_31 - LONG $0x01c78349 // add r15, 1 + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 LBB11_33: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 JL LBB11_37 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax LBB11_35: QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 - LONG $0xf8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 248] + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] - LONG $0xf0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 240] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0xe8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 232] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0xe0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 224] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0xd8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 216] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0xd0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 208] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0xc8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 200] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0xb8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 184] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0xb0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 176] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0xa8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 168] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0xa0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 160] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x98b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 152] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x90b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 144] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x88b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 136] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x78723b4c // cmp r14, qword [rdx + 120] - LONG $0xd0930f41 // setae r8b - LONG $0x70723b4c // cmp r14, qword [rdx + 112] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x68723b4c // cmp r14, qword [rdx + 104] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] QUAD $0x000000882494930f // setae byte [rsp + 136] - LONG $0x60723b4c // cmp r14, qword [rdx + 96] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] + LONG $0xd7930f40 // setae dil + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] LONG $0xd3930f41 // setae r11b - LONG $0x58723b4c // cmp r14, qword [rdx + 88] + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd2930f41 // setae r10b - LONG $0x50723b4c // cmp r14, qword [rdx + 80] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd1930f41 // setae r9b - LONG $0x48723b4c // cmp r14, qword [rdx + 72] - LONG $0xd7930f40 // setae dil - LONG $0x38723b4c // cmp r14, qword [rdx + 56] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] + LONG $0xd6930f40 // setae sil + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x30723b4c // cmp r14, qword [rdx + 48] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x28723b4c // cmp r14, qword [rdx + 40] - LONG $0xd6930f40 // setae sil - LONG $0x20723b4c // cmp r14, qword [rdx + 32] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x18723b4c // cmp r14, qword [rdx + 24] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] LONG $0xd5930f41 // setae r13b - LONG $0x10723b4c // cmp r14, qword [rdx + 16] + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd4930f41 // setae r12b - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] LONG $0xd7930f41 // setae r15b - LONG $0x40723b4c // cmp r14, qword [rdx + 64] + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] QUAD $0x000000a82494930f // setae byte [rsp + 168] - LONG $0x80b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 128] - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0xc0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 192] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000a024bc0244 // add r15b, byte [rsp + 160] - LONG $0x02e4c041 // shl r12b, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0xd6930f41 // setae r14b + LONG $0x40423b4c // cmp r8, qword [rdx + 64] + QUAD $0x000000982494930f // setae byte [rsp + 152] + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e5c041 // shl r13b, 3 + LONG $0x04e5c041 // shl r13b, 4 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc808 // or al, cl WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a824bc0240 // add dil, byte [rsp + 168] + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000009824b40240 // add sil, byte [rsp + 152] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017f8841 // mov byte [r15 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + LONG $0x50244402 // add al, byte [rsp + 80] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] + LONG $0x68244402 // add al, byte [rsp + 104] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -62601,637 +63957,673 @@ LBB11_35: LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 LONG $0x04c78349 // add r15, 4 - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 JNE LBB11_35 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] LBB11_37: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_147 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_211 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_168 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d JMP LBB11_40 -LBB11_99: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_103 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_101: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1f // movzx r8d, byte [r15 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1f3c8841 // mov byte [r15 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_101 - LONG $0x01c78349 // add r15, 1 - -LBB11_103: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_107 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - -LBB11_105: - QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 - LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] - LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] - LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] - QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] - QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] - LONG $0xd0930f41 // setae r8b - LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] - QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] - QUAD $0x000000882494930f // setae byte [rsp + 136] - LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] - LONG $0xd3930f41 // setae r11b - LONG $0x723b4466; BYTE $0x16 // cmp r14w, word [rdx + 22] - LONG $0xd2930f41 // setae r10b - LONG $0x723b4466; BYTE $0x14 // cmp r14w, word [rdx + 20] - LONG $0xd1930f41 // setae r9b - LONG $0x723b4466; BYTE $0x12 // cmp r14w, word [rdx + 18] - LONG $0xd7930f40 // setae dil - LONG $0x723b4466; BYTE $0x0e // cmp r14w, word [rdx + 14] - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x723b4466; BYTE $0x0c // cmp r14w, word [rdx + 12] - WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x723b4466; BYTE $0x0a // cmp r14w, word [rdx + 10] - LONG $0xd6930f40 // setae sil - LONG $0x723b4466; BYTE $0x08 // cmp r14w, word [rdx + 8] - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x723b4466; BYTE $0x06 // cmp r14w, word [rdx + 6] - LONG $0xd5930f41 // setae r13b - LONG $0x723b4466; BYTE $0x04 // cmp r14w, word [rdx + 4] - LONG $0xd4930f41 // setae r12b - LONG $0x323b4466 // cmp r14w, word [rdx] - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] - LONG $0xd7930f41 // setae r15b - LONG $0x723b4466; BYTE $0x10 // cmp r14w, word [rdx + 16] - QUAD $0x000000a82494930f // setae byte [rsp + 168] - LONG $0x723b4466; BYTE $0x20 // cmp r14w, word [rdx + 32] - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x723b4466; BYTE $0x30 // cmp r14w, word [rdx + 48] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000a024bc0244 // add r15b, byte [rsp + 160] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a824bc0240 // add dil, byte [rsp + 168] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x40c28348 // add rdx, 64 - LONG $0x04c78349 // add r15, 4 - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB11_105 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - -LBB11_107: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_112 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_110 - -LBB11_114: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_118 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB11_113: + LONG $0x06b70f44 // movzx r8d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_119 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_117 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx LBB11_116: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x37 // movzx r8d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x013b4466 // cmp r8w, word [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 JNE LBB11_116 - LONG $0x01c78349 // add r15, 1 -LBB11_118: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_122 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 +LBB11_117: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 + +LBB11_119: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_123 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB11_121: + QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 + LONG $0x423b4466; BYTE $0x3e // cmp r8w, word [rdx + 62] + LONG $0x2454930f; BYTE $0x1c // setae byte [rsp + 28] + LONG $0x423b4466; BYTE $0x3c // cmp r8w, word [rdx + 60] + QUAD $0x000001202494930f // setae byte [rsp + 288] + LONG $0x423b4466; BYTE $0x3a // cmp r8w, word [rdx + 58] + QUAD $0x000001402494930f // setae byte [rsp + 320] + LONG $0x423b4466; BYTE $0x38 // cmp r8w, word [rdx + 56] + LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x423b4466; BYTE $0x36 // cmp r8w, word [rdx + 54] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x423b4466; BYTE $0x34 // cmp r8w, word [rdx + 52] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x423b4466; BYTE $0x32 // cmp r8w, word [rdx + 50] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x423b4466; BYTE $0x2e // cmp r8w, word [rdx + 46] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x423b4466; BYTE $0x2c // cmp r8w, word [rdx + 44] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x423b4466; BYTE $0x2a // cmp r8w, word [rdx + 42] + QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x423b4466; BYTE $0x28 // cmp r8w, word [rdx + 40] + QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x423b4466; BYTE $0x26 // cmp r8w, word [rdx + 38] + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x423b4466; BYTE $0x24 // cmp r8w, word [rdx + 36] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x423b4466; BYTE $0x22 // cmp r8w, word [rdx + 34] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x423b4466; BYTE $0x1e // cmp r8w, word [rdx + 30] + LONG $0xd7930f40 // setae dil + LONG $0x423b4466; BYTE $0x1c // cmp r8w, word [rdx + 28] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x423b4466; BYTE $0x1a // cmp r8w, word [rdx + 26] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x423b4466; BYTE $0x18 // cmp r8w, word [rdx + 24] + LONG $0xd3930f41 // setae r11b + LONG $0x423b4466; BYTE $0x16 // cmp r8w, word [rdx + 22] + LONG $0xd2930f41 // setae r10b + LONG $0x423b4466; BYTE $0x14 // cmp r8w, word [rdx + 20] + LONG $0xd1930f41 // setae r9b + LONG $0x423b4466; BYTE $0x12 // cmp r8w, word [rdx + 18] + LONG $0xd6930f40 // setae sil + LONG $0x423b4466; BYTE $0x0e // cmp r8w, word [rdx + 14] + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x423b4466; BYTE $0x0c // cmp r8w, word [rdx + 12] + WORD $0x930f; BYTE $0xd3 // setae bl + LONG $0x423b4466; BYTE $0x0a // cmp r8w, word [rdx + 10] + WORD $0x930f; BYTE $0xd1 // setae cl + LONG $0x423b4466; BYTE $0x08 // cmp r8w, word [rdx + 8] + LONG $0xd5930f41 // setae r13b + LONG $0x423b4466; BYTE $0x06 // cmp r8w, word [rdx + 6] + LONG $0xd4930f41 // setae r12b + LONG $0x423b4466; BYTE $0x04 // cmp r8w, word [rdx + 4] + LONG $0xd7930f41 // setae r15b + LONG $0x023b4466 // cmp r8w, word [rdx] + QUAD $0x000000a82494930f // setae byte [rsp + 168] + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] + LONG $0xd6930f41 // setae r14b + LONG $0x423b4466; BYTE $0x10 // cmp r8w, word [rdx + 16] + QUAD $0x000000982494930f // setae byte [rsp + 152] + LONG $0x423b4466; BYTE $0x20 // cmp r8w, word [rdx + 32] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x423b4466; BYTE $0x30 // cmp r8w, word [rdx + 48] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000009824b40240 // add sil, byte [rsp + 152] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017f8841 // mov byte [r15 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x60244402 // add al, byte [rsp + 96] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02478841 // mov byte [r15 + 2], al + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xc000 // add al, al + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c78349 // add r15, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB11_121 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB11_123: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_211 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_129 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB11_126 -LBB11_120: - QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 - LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] - LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] - LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] - QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] - QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] - LONG $0xd09d0f41 // setge r8b - LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] - QUAD $0x0000008824949d0f // setge byte [rsp + 136] - LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] - LONG $0xd39d0f41 // setge r11b - LONG $0x723b4466; BYTE $0x16 // cmp r14w, word [rdx + 22] - LONG $0xd29d0f41 // setge r10b - LONG $0x723b4466; BYTE $0x14 // cmp r14w, word [rdx + 20] - LONG $0xd19d0f41 // setge r9b - LONG $0x723b4466; BYTE $0x12 // cmp r14w, word [rdx + 18] - LONG $0xd79d0f40 // setge dil - LONG $0x723b4466; BYTE $0x0e // cmp r14w, word [rdx + 14] - WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x723b4466; BYTE $0x0c // cmp r14w, word [rdx + 12] - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x723b4466; BYTE $0x0a // cmp r14w, word [rdx + 10] - LONG $0xd69d0f40 // setge sil - LONG $0x723b4466; BYTE $0x08 // cmp r14w, word [rdx + 8] - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x723b4466; BYTE $0x06 // cmp r14w, word [rdx + 6] - LONG $0xd59d0f41 // setge r13b - LONG $0x723b4466; BYTE $0x04 // cmp r14w, word [rdx + 4] - LONG $0xd49d0f41 // setge r12b - LONG $0x323b4466 // cmp r14w, word [rdx] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] - LONG $0xd79d0f41 // setge r15b - LONG $0x723b4466; BYTE $0x10 // cmp r14w, word [rdx + 16] - QUAD $0x000000a824949d0f // setge byte [rsp + 168] - LONG $0x723b4466; BYTE $0x20 // cmp r14w, word [rdx + 32] - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x723b4466; BYTE $0x30 // cmp r14w, word [rdx + 48] - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000a024bc0244 // add r15b, byte [rsp + 160] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a824bc0240 // add dil, byte [rsp + 168] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x40c28348 // add rdx, 64 - LONG $0x04c78349 // add r15, 4 - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB11_120 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] +LBB11_131: + LONG $0x06b70f44 // movzx r8d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_137 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_135 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_134: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x013b4466 // cmp r8w, word [rcx] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_134 -LBB11_122: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_128 +LBB11_135: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 + +LBB11_137: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_141 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB11_139: + QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 + LONG $0x423b4466; BYTE $0x3e // cmp r8w, word [rdx + 62] + LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] + LONG $0x423b4466; BYTE $0x3c // cmp r8w, word [rdx + 60] + QUAD $0x0000012024949d0f // setge byte [rsp + 288] + LONG $0x423b4466; BYTE $0x3a // cmp r8w, word [rdx + 58] + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x423b4466; BYTE $0x38 // cmp r8w, word [rdx + 56] + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x423b4466; BYTE $0x36 // cmp r8w, word [rdx + 54] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x423b4466; BYTE $0x34 // cmp r8w, word [rdx + 52] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x423b4466; BYTE $0x32 // cmp r8w, word [rdx + 50] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x423b4466; BYTE $0x2e // cmp r8w, word [rdx + 46] + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x423b4466; BYTE $0x2c // cmp r8w, word [rdx + 44] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x423b4466; BYTE $0x2a // cmp r8w, word [rdx + 42] + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x423b4466; BYTE $0x28 // cmp r8w, word [rdx + 40] + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x423b4466; BYTE $0x26 // cmp r8w, word [rdx + 38] + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x423b4466; BYTE $0x24 // cmp r8w, word [rdx + 36] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x423b4466; BYTE $0x22 // cmp r8w, word [rdx + 34] + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x423b4466; BYTE $0x1e // cmp r8w, word [rdx + 30] + LONG $0xd79d0f40 // setge dil + LONG $0x423b4466; BYTE $0x1c // cmp r8w, word [rdx + 28] + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x423b4466; BYTE $0x1a // cmp r8w, word [rdx + 26] + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x423b4466; BYTE $0x18 // cmp r8w, word [rdx + 24] + LONG $0xd39d0f41 // setge r11b + LONG $0x423b4466; BYTE $0x16 // cmp r8w, word [rdx + 22] + LONG $0xd29d0f41 // setge r10b + LONG $0x423b4466; BYTE $0x14 // cmp r8w, word [rdx + 20] + LONG $0xd19d0f41 // setge r9b + LONG $0x423b4466; BYTE $0x12 // cmp r8w, word [rdx + 18] + LONG $0xd69d0f40 // setge sil + LONG $0x423b4466; BYTE $0x0e // cmp r8w, word [rdx + 14] + WORD $0x9d0f; BYTE $0xd0 // setge al + LONG $0x423b4466; BYTE $0x0c // cmp r8w, word [rdx + 12] + WORD $0x9d0f; BYTE $0xd3 // setge bl + LONG $0x423b4466; BYTE $0x0a // cmp r8w, word [rdx + 10] + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x423b4466; BYTE $0x08 // cmp r8w, word [rdx + 8] + LONG $0xd59d0f41 // setge r13b + LONG $0x423b4466; BYTE $0x06 // cmp r8w, word [rdx + 6] + LONG $0xd49d0f41 // setge r12b + LONG $0x423b4466; BYTE $0x04 // cmp r8w, word [rdx + 4] + LONG $0xd79d0f41 // setge r15b + LONG $0x023b4466 // cmp r8w, word [rdx] + QUAD $0x000000a824949d0f // setge byte [rsp + 168] + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] + LONG $0xd69d0f41 // setge r14b + LONG $0x423b4466; BYTE $0x10 // cmp r8w, word [rdx + 16] + QUAD $0x0000009824949d0f // setge byte [rsp + 152] + LONG $0x423b4466; BYTE $0x20 // cmp r8w, word [rdx + 32] + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x423b4466; BYTE $0x30 // cmp r8w, word [rdx + 48] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000009824b40240 // add sil, byte [rsp + 152] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017f8841 // mov byte [r15 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x50244402 // add al, byte [rsp + 80] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02478841 // mov byte [r15 + 2], al + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xc000 // add al, al + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c78349 // add r15, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB11_139 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB11_141: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_211 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_147 WORD $0xff31 // xor edi, edi - JMP LBB11_125 - -LBB11_149: - WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_153 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JMP LBB11_144 -LBB11_151: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x37 // movzx r8d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_151 - LONG $0x01c78349 // add r15, 1 - -LBB11_153: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_157 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 +LBB11_170: + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_176 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_174 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_173: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_173 + +LBB11_174: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 + +LBB11_176: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_180 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax -LBB11_155: +LBB11_178: QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 - LONG $0xf8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 248] + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] - LONG $0xf0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 240] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0xe8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 232] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0xe0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 224] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0xd8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 216] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0xd0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 208] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0xc8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 200] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0xb8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 184] - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0xb0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 176] - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0xa8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 168] - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0xa0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 160] - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x98b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 152] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x90b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 144] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x88b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 136] - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x78723b4c // cmp r14, qword [rdx + 120] - LONG $0xd09d0f41 // setge r8b - LONG $0x70723b4c // cmp r14, qword [rdx + 112] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x68723b4c // cmp r14, qword [rdx + 104] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] QUAD $0x0000008824949d0f // setge byte [rsp + 136] - LONG $0x60723b4c // cmp r14, qword [rdx + 96] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] + LONG $0xd79d0f40 // setge dil + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] LONG $0xd39d0f41 // setge r11b - LONG $0x58723b4c // cmp r14, qword [rdx + 88] + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd29d0f41 // setge r10b - LONG $0x50723b4c // cmp r14, qword [rdx + 80] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd19d0f41 // setge r9b - LONG $0x48723b4c // cmp r14, qword [rdx + 72] - LONG $0xd79d0f40 // setge dil - LONG $0x38723b4c // cmp r14, qword [rdx + 56] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] + LONG $0xd69d0f40 // setge sil + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x30723b4c // cmp r14, qword [rdx + 48] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x28723b4c // cmp r14, qword [rdx + 40] - LONG $0xd69d0f40 // setge sil - LONG $0x20723b4c // cmp r14, qword [rdx + 32] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x18723b4c // cmp r14, qword [rdx + 24] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] LONG $0xd59d0f41 // setge r13b - LONG $0x10723b4c // cmp r14, qword [rdx + 16] + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd49d0f41 // setge r12b - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] LONG $0xd79d0f41 // setge r15b - LONG $0x40723b4c // cmp r14, qword [rdx + 64] + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] QUAD $0x000000a824949d0f // setge byte [rsp + 168] - LONG $0x80b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 128] - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0xc0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 192] - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000a024bc0244 // add r15b, byte [rsp + 160] - LONG $0x02e4c041 // shl r12b, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0xd69d0f41 // setge r14b + LONG $0x40423b4c // cmp r8, qword [rdx + 64] + QUAD $0x0000009824949d0f // setge byte [rsp + 152] + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e5c041 // shl r13b, 3 + LONG $0x04e5c041 // shl r13b, 4 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc808 // or al, cl WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a824bc0240 // add dil, byte [rsp + 168] + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000009824b40240 // add sil, byte [rsp + 152] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017f8841 // mov byte [r15 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + LONG $0x50244402 // add al, byte [rsp + 80] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] + LONG $0x68244402 // add al, byte [rsp + 104] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -63252,72 +64644,87 @@ LBB11_155: LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 LONG $0x04c78349 // add r15, 4 - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB11_155 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB11_178 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB11_157: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_162 +LBB11_180: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_211 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_185 WORD $0xff31 // xor edi, edi - JMP LBB11_160 - -LBB11_164: - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x0610fac5 // vmovss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_168 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JMP LBB11_183 -LBB11_166: - LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil +LBB11_187: + WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_193 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_191 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_190: + LONG $0x04518d48 // lea rdx, [rcx + 4] + LONG $0x012ef8c5 // vucomiss xmm0, dword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x07 // movzx r9d, byte [r15 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_166 - LONG $0x01c78349 // add r15, 1 - -LBB11_168: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_172 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x073c8841 // mov byte [r15 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_190 + +LBB11_191: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 + +LBB11_193: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_197 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000a024b48944 // mov dword [rsp + 160], r14d + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax -LBB11_170: +LBB11_195: QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] - QUAD $0x000000a82494930f // setae byte [rsp + 168] + QUAD $0x000000982494930f // setae byte [rsp + 152] LONG $0x422ef8c5; BYTE $0x04 // vucomiss xmm0, dword [rdx + 4] LONG $0xd1930f41 // setae r9b LONG $0x422ef8c5; BYTE $0x08 // vucomiss xmm0, dword [rdx + 8] @@ -63325,15 +64732,15 @@ LBB11_170: LONG $0x422ef8c5; BYTE $0x0c // vucomiss xmm0, dword [rdx + 12] LONG $0xd5930f41 // setae r13b LONG $0x422ef8c5; BYTE $0x10 // vucomiss xmm0, dword [rdx + 16] - QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x422ef8c5; BYTE $0x14 // vucomiss xmm0, dword [rdx + 20] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0x422ef8c5; BYTE $0x18 // vucomiss xmm0, dword [rdx + 24] WORD $0x930f; BYTE $0xd3 // setae bl LONG $0x422ef8c5; BYTE $0x1c // vucomiss xmm0, dword [rdx + 28] LONG $0xd4930f41 // setae r12b LONG $0x422ef8c5; BYTE $0x20 // vucomiss xmm0, dword [rdx + 32] - QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] LONG $0x422ef8c5; BYTE $0x24 // vucomiss xmm0, dword [rdx + 36] LONG $0xd6930f40 // setae sil LONG $0x422ef8c5; BYTE $0x28 // vucomiss xmm0, dword [rdx + 40] @@ -63345,21 +64752,21 @@ LBB11_170: LONG $0x422ef8c5; BYTE $0x34 // vucomiss xmm0, dword [rdx + 52] LONG $0xd7930f41 // setae r15b LONG $0x422ef8c5; BYTE $0x38 // vucomiss xmm0, dword [rdx + 56] - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0x422ef8c5; BYTE $0x3c // vucomiss xmm0, dword [rdx + 60] WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x422ef8c5; BYTE $0x40 // vucomiss xmm0, dword [rdx + 64] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + QUAD $0x000000802494930f // setae byte [rsp + 128] LONG $0x422ef8c5; BYTE $0x44 // vucomiss xmm0, dword [rdx + 68] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] LONG $0x422ef8c5; BYTE $0x48 // vucomiss xmm0, dword [rdx + 72] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0x422ef8c5; BYTE $0x4c // vucomiss xmm0, dword [rdx + 76] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] LONG $0x422ef8c5; BYTE $0x50 // vucomiss xmm0, dword [rdx + 80] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + QUAD $0x000000882494930f // setae byte [rsp + 136] LONG $0x422ef8c5; BYTE $0x54 // vucomiss xmm0, dword [rdx + 84] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] LONG $0x422ef8c5; BYTE $0x58 // vucomiss xmm0, dword [rdx + 88] LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] LONG $0x422ef8c5; BYTE $0x5c // vucomiss xmm0, dword [rdx + 92] @@ -63367,11 +64774,11 @@ LBB11_170: LONG $0x422ef8c5; BYTE $0x60 // vucomiss xmm0, dword [rdx + 96] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] LONG $0x422ef8c5; BYTE $0x64 // vucomiss xmm0, dword [rdx + 100] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] LONG $0x422ef8c5; BYTE $0x68 // vucomiss xmm0, dword [rdx + 104] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x422ef8c5; BYTE $0x6c // vucomiss xmm0, dword [rdx + 108] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0x422ef8c5; BYTE $0x70 // vucomiss xmm0, dword [rdx + 112] QUAD $0x000001402494930f // setae byte [rsp + 320] LONG $0x422ef8c5; BYTE $0x74 // vucomiss xmm0, dword [rdx + 116] @@ -63381,55 +64788,55 @@ LBB11_170: LONG $0x422ef8c5; BYTE $0x7c // vucomiss xmm0, dword [rdx + 124] WORD $0x930f; BYTE $0xd0 // setae al WORD $0x0045; BYTE $0xc9 // add r9b, r9b - QUAD $0x000000a8248c0244 // add r9b, byte [rsp + 168] + QUAD $0x00000098248c0244 // add r9b, byte [rsp + 152] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e4c041 // shl r12b, 7 WORD $0x0841; BYTE $0xdc // or r12b, bl LONG $0x02e3c041 // shl r11b, 2 WORD $0x0845; BYTE $0xcb // or r11b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000008824b40240 // add sil, byte [rsp + 136] + LONG $0x24740240; BYTE $0x58 // add sil, byte [rsp + 88] LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xdd // or r13b, r11b LONG $0x02e7c040 // shl dil, 2 WORD $0x0840; BYTE $0xf7 // or dil, sil - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xeb // or bl, r13b WORD $0xde89 // mov esi, ebx LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e7c041 // shl r15b, 5 WORD $0x0845; BYTE $0xd7 // or r15b, r10b - QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] + LONG $0x2474b60f; BYTE $0x60 // movzx esi, byte [rsp + 96] LONG $0x06e6c040 // shl sil, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x0841; BYTE $0xdc // or r12b, bl WORD $0x0844; BYTE $0xf9 // or cl, r15b QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xdb00 // add bl, bl - LONG $0x48245c02 // add bl, byte [rsp + 72] + LONG $0x80249c02; WORD $0x0000; BYTE $0x00 // add bl, byte [rsp + 128] WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xf3 // or bl, sil WORD $0x8845; BYTE $0x27 // mov byte [r15], r12b @@ -63439,15 +64846,15 @@ LBB11_170: WORD $0x0841; BYTE $0xf6 // or r14b, sil LONG $0x014f8841 // mov byte [r15 + 1], cl WORD $0x0841; BYTE $0xde // or r14b, bl - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] WORD $0xc900 // add cl, cl LONG $0x20244c02 // add cl, byte [rsp + 32] WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd908 // or cl, bl WORD $0xcb89 // mov ebx, ecx @@ -63461,135 +64868,621 @@ LBB11_170: LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02778845 // mov byte [r15 + 2], r14b + LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 + LONG $0x04c78349 // add r15, 4 + QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 + JNE LBB11_195 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000a024b48b44 // mov r14d, dword [rsp + 160] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB11_197: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB11_211 + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_202 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB11_200 + +LBB11_58: + WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_59 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_61 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB11_67: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + LONG $0x000000ba; BYTE $0x00 // mov edx, 0 + WORD $0xd280; BYTE $0xff // adc dl, -1 + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1f048841 // mov byte [r15 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB11_67 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JNE LBB11_63 + JMP LBB11_211 + +LBB11_151: + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_157 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xe6 // cmp r14, r12 + LONG $0xf44f0f4d // cmovg r14, r12 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_155 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_154: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_154 + +LBB11_155: + WORD $0x294d; BYTE $0xf4 // sub r12, r14 + JE LBB11_211 + LONG $0x01c78349 // add r15, 1 + +LBB11_157: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_161 + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + +LBB11_159: + QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] + LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] + QUAD $0x0000012024949d0f // setge byte [rsp + 288] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] + LONG $0xd79d0f40 // setge dil + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] + LONG $0xd39d0f41 // setge r11b + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] + LONG $0xd29d0f41 // setge r10b + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] + LONG $0xd19d0f41 // setge r9b + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] + LONG $0xd69d0f40 // setge sil + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] + WORD $0x9d0f; BYTE $0xd0 // setge al + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] + WORD $0x9d0f; BYTE $0xd3 // setge bl + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] + LONG $0xd59d0f41 // setge r13b + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] + LONG $0xd49d0f41 // setge r12b + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] + LONG $0xd79d0f41 // setge r15b + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + QUAD $0x000000a824949d0f // setge byte [rsp + 168] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd69d0f41 // setge r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] + QUAD $0x0000009824949d0f // setge byte [rsp + 152] + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a824b40244 // add r14b, byte [rsp + 168] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000009824b40240 // add sil, byte [rsp + 152] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x017f8841 // mov byte [r15 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x50244402 // add al, byte [rsp + 80] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02478841 // mov byte [r15 + 2], al + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xc000 // add al, al + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x80ea8348 // sub rdx, -128 + LONG $0x04c78349 // add r15, 4 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB11_159 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB11_161: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_211 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB11_166 + WORD $0xff31 // xor edi, edi + JMP LBB11_164 + +LBB11_5: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB11_91 + +LBB11_59: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB11_64 + +LBB11_88: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB11_211 + +LBB11_90: + LONG $0x01c78349 // add r15, 1 + +LBB11_91: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_92 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x00000160248c8948 // mov qword [rsp + 352], rcx + JB LBB11_96 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JAE LBB11_99 + LONG $0x8f048d49 // lea rax, [r15 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB11_99 + +LBB11_96: + WORD $0xc031 // xor eax, eax + QUAD $0x000001a024848948 // mov qword [rsp + 416], rax + WORD $0x894d; BYTE $0xfd // mov r13, r15 + +LBB11_102: + QUAD $0x000001a0248c2b48 // sub rcx, qword [rsp + 416] + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx + +LBB11_103: + LONG $0x1f773a44 // cmp r14b, byte [rdi + 31] + QUAD $0x0000011024949d0f // setge byte [rsp + 272] + LONG $0x1e773a44 // cmp r14b, byte [rdi + 30] + QUAD $0x0000012024949d0f // setge byte [rsp + 288] + LONG $0x1d773a44 // cmp r14b, byte [rdi + 29] + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x1c773a44 // cmp r14b, byte [rdi + 28] + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x1b773a44 // cmp r14b, byte [rdi + 27] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x1a773a44 // cmp r14b, byte [rdi + 26] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x19773a44 // cmp r14b, byte [rdi + 25] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x17773a44 // cmp r14b, byte [rdi + 23] + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x16773a44 // cmp r14b, byte [rdi + 22] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x15773a44 // cmp r14b, byte [rdi + 21] + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x14773a44 // cmp r14b, byte [rdi + 20] + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x13773a44 // cmp r14b, byte [rdi + 19] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x12773a44 // cmp r14b, byte [rdi + 18] + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x11773a44 // cmp r14b, byte [rdi + 17] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x0f773a44 // cmp r14b, byte [rdi + 15] + LONG $0xd39d0f41 // setge r11b + LONG $0x0e773a44 // cmp r14b, byte [rdi + 14] + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x0d773a44 // cmp r14b, byte [rdi + 13] + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x0c773a44 // cmp r14b, byte [rdi + 12] + LONG $0xd49d0f41 // setge r12b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x0b // cmp al, byte [rdi + 11] + LONG $0xd79d0f41 // setge r15b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x0a // cmp al, byte [rdi + 10] + LONG $0xd69d0f41 // setge r14b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x09 // cmp al, byte [rdi + 9] + LONG $0xd29d0f41 // setge r10b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x07 // cmp al, byte [rdi + 7] + LONG $0xd69d0f40 // setge sil + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x06 // cmp al, byte [rdi + 6] + QUAD $0x0000009824949d0f // setge byte [rsp + 152] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x05 // cmp al, byte [rdi + 5] + LONG $0xd19d0f41 // setge r9b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x04 // cmp al, byte [rdi + 4] + LONG $0xd09d0f41 // setge r8b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x03 // cmp al, byte [rdi + 3] + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x02 // cmp al, byte [rdi + 2] + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x073a // cmp al, byte [rdi] + QUAD $0x000000a824949d0f // setge byte [rsp + 168] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x01 // cmp al, byte [rdi + 1] + WORD $0x9d0f; BYTE $0xd0 // setge al + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] + LONG $0x086f3a44 // cmp r13b, byte [rdi + 8] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5f3a; BYTE $0x10 // cmp bl, byte [rdi + 16] + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x1c245c8b // mov ebx, dword [rsp + 28] + WORD $0x5f3a; BYTE $0x18 // cmp bl, byte [rdi + 24] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xc000 // add al, al + LONG $0xa8248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 168] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0xca08 // or dl, cl + LONG $0x04e0c041 // shl r8b, 4 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + LONG $0x05e1c041 // shl r9b, 5 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xc6 // or sil, al + WORD $0x0844; BYTE $0xce // or sil, r9b + LONG $0x00758841 // mov byte [r13], sil + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + LONG $0x24540244; BYTE $0x50 // add r10b, byte [rsp + 80] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x015d8845 // mov byte [r13 + 1], r11b + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd008 // or al, dl + WORD $0xc808 // or al, cl + LONG $0x02458841 // mov byte [r13 + 2], al + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xc000 // add al, al + WORD $0xd808 // or al, bl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000001202494b60f // movzx edx, byte [rsp + 288] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl - LONG $0x02778845 // mov byte [r15 + 2], r14b - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c78349 // add r15, 4 + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x20c78348 // add rdi, 32 + LONG $0x04c58349 // add r13, 4 QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB11_170 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] + JNE LBB11_103 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x00000160248c8b48 // mov rcx, qword [rsp + 352] + JMP LBB11_105 -LBB11_172: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_177 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_175 - -LBB11_56: - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_60 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB11_92: + WORD $0x894d; BYTE $0xfd // mov r13, r15 -LBB11_58: - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_58 - LONG $0x01c78349 // add r15, 1 - -LBB11_60: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_61 - LONG $0x20fe8349 // cmp r14, 32 - LONG $0x245c8944; BYTE $0x1c // mov dword [rsp + 28], r11d - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 - JB LBB11_63 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 +LBB11_105: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB11_211 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JNE LBB11_108 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB11_111 + +LBB11_61: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB11_211 + +LBB11_63: + LONG $0x01c78349 // add r15, 1 + +LBB11_64: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB11_65 + LONG $0x20f98348 // cmp rcx, 32 + LONG $0x24748944; BYTE $0x1c // mov dword [rsp + 28], r14d + QUAD $0x0000011824a4894c // mov qword [rsp + 280], r12 + QUAD $0x00000160248c8948 // mov qword [rsp + 352], rcx + JB LBB11_69 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x0148; BYTE $0xf8 // add rax, rdi WORD $0x3949; BYTE $0xc7 // cmp r15, rax - JAE LBB11_66 - LONG $0xb7048d4b // lea rax, [r15 + 4*r14] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB11_66 + JAE LBB11_72 + LONG $0x8f048d49 // lea rax, [r15 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB11_72 -LBB11_63: +LBB11_69: WORD $0xc031 // xor eax, eax QUAD $0x0000018024848948 // mov qword [rsp + 384], rax - WORD $0x8948; BYTE $0xd7 // mov rdi, rdx WORD $0x894d; BYTE $0xfd // mov r13, r15 -LBB11_69: - QUAD $0x0000018024b42b4c // sub r14, qword [rsp + 384] - QUAD $0x0000009824b4894c // mov qword [rsp + 152], r14 +LBB11_75: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx -LBB11_70: - LONG $0x1f5f3a44 // cmp r11b, byte [rdi + 31] +LBB11_76: + LONG $0x1f773a44 // cmp r14b, byte [rdi + 31] QUAD $0x000001102494930f // setae byte [rsp + 272] - LONG $0x1e5f3a44 // cmp r11b, byte [rdi + 30] + LONG $0x1e773a44 // cmp r14b, byte [rdi + 30] QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0x1d5f3a44 // cmp r11b, byte [rdi + 29] + LONG $0x1d773a44 // cmp r14b, byte [rdi + 29] QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0x1c5f3a44 // cmp r11b, byte [rdi + 28] + LONG $0x1c773a44 // cmp r14b, byte [rdi + 28] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x1b5f3a44 // cmp r11b, byte [rdi + 27] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x1a5f3a44 // cmp r11b, byte [rdi + 26] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x195f3a44 // cmp r11b, byte [rdi + 25] + LONG $0x1b773a44 // cmp r14b, byte [rdi + 27] LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x175f3a44 // cmp r11b, byte [rdi + 23] + LONG $0x1a773a44 // cmp r14b, byte [rdi + 26] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x19773a44 // cmp r14b, byte [rdi + 25] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x17773a44 // cmp r14b, byte [rdi + 23] LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x165f3a44 // cmp r11b, byte [rdi + 22] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x155f3a44 // cmp r11b, byte [rdi + 21] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x145f3a44 // cmp r11b, byte [rdi + 20] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x135f3a44 // cmp r11b, byte [rdi + 19] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x125f3a44 // cmp r11b, byte [rdi + 18] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x115f3a44 // cmp r11b, byte [rdi + 17] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x0f5f3a44 // cmp r11b, byte [rdi + 15] - LONG $0xd6930f41 // setae r14b - LONG $0x0e5f3a44 // cmp r11b, byte [rdi + 14] + LONG $0x16773a44 // cmp r14b, byte [rdi + 22] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x15773a44 // cmp r14b, byte [rdi + 21] QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x0d5f3a44 // cmp r11b, byte [rdi + 13] + LONG $0x14773a44 // cmp r14b, byte [rdi + 20] QUAD $0x000000882494930f // setae byte [rsp + 136] - LONG $0x0c5f3a44 // cmp r11b, byte [rdi + 12] + LONG $0x13773a44 // cmp r14b, byte [rdi + 19] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x12773a44 // cmp r14b, byte [rdi + 18] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x11773a44 // cmp r14b, byte [rdi + 17] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x0f773a44 // cmp r14b, byte [rdi + 15] + LONG $0xd3930f41 // setae r11b + LONG $0x0e773a44 // cmp r14b, byte [rdi + 14] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x0d773a44 // cmp r14b, byte [rdi + 13] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x0c773a44 // cmp r14b, byte [rdi + 12] LONG $0xd4930f41 // setae r12b - LONG $0x0b5f3a44 // cmp r11b, byte [rdi + 11] + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x0b // cmp al, byte [rdi + 11] LONG $0xd7930f41 // setae r15b - LONG $0x0a5f3a44 // cmp r11b, byte [rdi + 10] - LONG $0xd3930f41 // setae r11b + LONG $0x1c24448b // mov eax, dword [rsp + 28] + WORD $0x473a; BYTE $0x0a // cmp al, byte [rdi + 10] + LONG $0xd6930f41 // setae r14b LONG $0x1c24448b // mov eax, dword [rsp + 28] WORD $0x473a; BYTE $0x09 // cmp al, byte [rdi + 9] LONG $0xd2930f41 // setae r10b @@ -63598,7 +65491,7 @@ LBB11_70: LONG $0xd6930f40 // setae sil LONG $0x1c24448b // mov eax, dword [rsp + 28] WORD $0x473a; BYTE $0x06 // cmp al, byte [rdi + 6] - QUAD $0x000000a82494930f // setae byte [rsp + 168] + QUAD $0x000000982494930f // setae byte [rsp + 152] LONG $0x1c24448b // mov eax, dword [rsp + 28] WORD $0x473a; BYTE $0x05 // cmp al, byte [rdi + 5] LONG $0xd1930f41 // setae r9b @@ -63613,7 +65506,7 @@ LBB11_70: WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x1c24448b // mov eax, dword [rsp + 28] WORD $0x073a // cmp al, byte [rdi] - QUAD $0x000000a02494930f // setae byte [rsp + 160] + QUAD $0x000000a82494930f // setae byte [rsp + 168] LONG $0x1c24448b // mov eax, dword [rsp + 28] WORD $0x473a; BYTE $0x01 // cmp al, byte [rdi + 1] WORD $0x930f; BYTE $0xd0 // setae al @@ -63621,15 +65514,15 @@ LBB11_70: LONG $0x246c8b44; BYTE $0x1c // mov r13d, dword [rsp + 28] LONG $0x086f3a44 // cmp r13b, byte [rdi + 8] WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] WORD $0x5f3a; BYTE $0x10 // cmp bl, byte [rdi + 16] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + QUAD $0x000000802494930f // setae byte [rsp + 128] LONG $0x1c245c8b // mov ebx, dword [rsp + 28] WORD $0x5f3a; BYTE $0x18 // cmp bl, byte [rdi + 24] WORD $0x930f; BYTE $0xd3 // setae bl WORD $0xc000 // add al, al - LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] + LONG $0xa8248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 168] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xe2c0; BYTE $0x03 // shl dl, 3 @@ -63638,66 +65531,66 @@ LBB11_70: WORD $0x0841; BYTE $0xd0 // or r8b, dl LONG $0x05e1c041 // shl r9b, 5 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000a82484b60f // movzx eax, byte [rsp + 168] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e6c040 // shl sil, 7 WORD $0x0840; BYTE $0xc6 // or sil, al WORD $0x0844; BYTE $0xce // or sil, r9b LONG $0x00758841 // mov byte [r13], sil WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000008024940244 // add r10b, byte [rsp + 128] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x24540244; BYTE $0x50 // add r10b, byte [rsp + 80] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] + WORD $0x0845; BYTE $0xf7 // or r15b, r14b LONG $0x04e4c041 // shl r12b, 4 WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xe0 // or al, r12b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xce // or r14b, cl - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x01758845 // mov byte [r13 + 1], r14b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x015d8845 // mov byte [r13 + 1], r11b + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xc000 // add al, al - LONG $0x48244402 // add al, byte [rsp + 72] + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xc000 // add al, al WORD $0xd808 // or al, bl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -63718,282 +65611,48 @@ LBB11_70: LONG $0x03458841 // mov byte [r13 + 3], al LONG $0x20c78348 // add rdi, 32 LONG $0x04c58349 // add r13, 4 - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB11_70 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - JMP LBB11_72 - -LBB11_132: - WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_136 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_134: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x37 // movzx r8d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_134 - LONG $0x01c78349 // add r15, 1 - -LBB11_136: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB11_140 - QUAD $0x000001182494894c // mov qword [rsp + 280], r10 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - -LBB11_138: - QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 - LONG $0x7c723b44 // cmp r14d, dword [rdx + 124] - LONG $0x24549d0f; BYTE $0x1c // setge byte [rsp + 28] - LONG $0x78723b44 // cmp r14d, dword [rdx + 120] - QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x74723b44 // cmp r14d, dword [rdx + 116] - QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0x70723b44 // cmp r14d, dword [rdx + 112] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x6c723b44 // cmp r14d, dword [rdx + 108] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x68723b44 // cmp r14d, dword [rdx + 104] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x64723b44 // cmp r14d, dword [rdx + 100] - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x5c723b44 // cmp r14d, dword [rdx + 92] - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x58723b44 // cmp r14d, dword [rdx + 88] - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x54723b44 // cmp r14d, dword [rdx + 84] - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x50723b44 // cmp r14d, dword [rdx + 80] - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x4c723b44 // cmp r14d, dword [rdx + 76] - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x48723b44 // cmp r14d, dword [rdx + 72] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x44723b44 // cmp r14d, dword [rdx + 68] - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x3c723b44 // cmp r14d, dword [rdx + 60] - LONG $0xd09d0f41 // setge r8b - LONG $0x38723b44 // cmp r14d, dword [rdx + 56] - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x34723b44 // cmp r14d, dword [rdx + 52] - QUAD $0x0000008824949d0f // setge byte [rsp + 136] - LONG $0x30723b44 // cmp r14d, dword [rdx + 48] - LONG $0xd39d0f41 // setge r11b - LONG $0x2c723b44 // cmp r14d, dword [rdx + 44] - LONG $0xd29d0f41 // setge r10b - LONG $0x28723b44 // cmp r14d, dword [rdx + 40] - LONG $0xd19d0f41 // setge r9b - LONG $0x24723b44 // cmp r14d, dword [rdx + 36] - LONG $0xd79d0f40 // setge dil - LONG $0x1c723b44 // cmp r14d, dword [rdx + 28] - WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x18723b44 // cmp r14d, dword [rdx + 24] - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x14723b44 // cmp r14d, dword [rdx + 20] - LONG $0xd69d0f40 // setge sil - LONG $0x10723b44 // cmp r14d, dword [rdx + 16] - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x0c723b44 // cmp r14d, dword [rdx + 12] - LONG $0xd59d0f41 // setge r13b - LONG $0x08723b44 // cmp r14d, dword [rdx + 8] - LONG $0xd49d0f41 // setge r12b - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] - LONG $0xd79d0f41 // setge r15b - LONG $0x20723b44 // cmp r14d, dword [rdx + 32] - QUAD $0x000000a824949d0f // setge byte [rsp + 168] - LONG $0x40723b44 // cmp r14d, dword [rdx + 64] - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x60723b44 // cmp r14d, dword [rdx + 96] - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000a024bc0244 // add r15b, byte [rsp + 160] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000a824bc0240 // add dil, byte [rsp + 168] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - QUAD $0x00000120249cb60f // movzx ebx, byte [rsp + 288] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x80ea8348 // sub rdx, -128 - LONG $0x04c78349 // add r15, 4 - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB11_138 - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - -LBB11_140: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB11_145 - WORD $0xff31 // xor edi, edi - JMP LBB11_143 - -LBB11_9: - WORD $0x894d; BYTE $0xfd // mov r13, r15 - -LBB11_91: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB11_94 - WORD $0xf631 // xor esi, esi - JMP LBB11_97 + QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + JNE LBB11_76 + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + QUAD $0x00000160248c8b48 // mov rcx, qword [rsp + 352] + JMP LBB11_78 -LBB11_61: +LBB11_65: WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x8948; BYTE $0xd7 // mov rdi, rdx -LBB11_72: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB11_185 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB11_75 +LBB11_78: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB11_211 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JNE LBB11_81 WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB11_78 + JMP LBB11_84 -LBB11_130: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d +LBB11_149: + WORD $0x894d; BYTE $0xca // mov r10, r9 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB11_131: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] +LBB11_150: + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xde // mov rsi, r11 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + LONG $0x1cb60f45; BYTE $0x37 // movzx r11d, byte [r15 + rsi] + WORD $0x3044; BYTE $0xdf // xor dil, r11b + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0x3044; BYTE $0xd8 // xor al, r11b LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] + LONG $0x02c68349 // add r14, 2 + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] LONG $0x08528d48 // lea rdx, [rdx + 8] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 @@ -64004,22 +65663,22 @@ LBB11_131: WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB11_131 + WORD $0x394d; BYTE $0xf2 // cmp r10, r14 + JNE LBB11_150 -LBB11_24: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 +LBB11_22: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_211 WORD $0xc031 // xor eax, eax - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - JMP LBB11_183 + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + JMP LBB11_128 -LBB11_179: +LBB11_204: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB11_180: +LBB11_205: LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] LONG $0x000000b8; BYTE $0x00 // mov eax, 0 WORD $0xff14 // adc al, -1 @@ -64047,37 +65706,37 @@ LBB11_180: WORD $0xd830 // xor al, bl LONG $0x37048841 // mov byte [r15 + rsi], al WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB11_180 + JNE LBB11_205 -LBB11_181: +LBB11_206: LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 + JE LBB11_211 WORD $0xc031 // xor eax, eax LONG $0x022ef9c5 // vucomisd xmm0, qword [rdx] - JMP LBB11_183 + JMP LBB11_208 -LBB11_147: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d +LBB11_168: + WORD $0x894d; BYTE $0xca // mov r10, r9 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB11_148: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] +LBB11_169: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xde // mov rsi, r11 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + LONG $0x1cb60f45; BYTE $0x37 // movzx r11d, byte [r15 + rsi] + WORD $0x3044; BYTE $0xdf // xor dil, r11b + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0x3044; BYTE $0xd8 // xor al, r11b LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x02c68349 // add r14, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 @@ -64088,38 +65747,38 @@ LBB11_148: WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB11_148 + WORD $0x394d; BYTE $0xf2 // cmp r10, r14 + JNE LBB11_169 LBB11_40: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_211 WORD $0xc031 // xor eax, eax - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - JMP LBB11_183 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + JMP LBB11_128 -LBB11_112: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d +LBB11_129: + WORD $0x894d; BYTE $0xca // mov r10, r9 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB11_113: - LONG $0x323b4466 // cmp r14w, word [rdx] +LBB11_130: + LONG $0x023b4466 // cmp r8w, word [rdx] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xde // mov rsi, r11 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + LONG $0x1cb60f45; BYTE $0x37 // movzx r11d, byte [r15 + rsi] + WORD $0x3044; BYTE $0xdf // xor dil, r11b + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0x3044; BYTE $0xd8 // xor al, r11b LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] + LONG $0x02c68349 // add r14, 2 + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] LONG $0x04528d48 // lea rdx, [rdx + 4] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 @@ -64130,104 +65789,113 @@ LBB11_113: WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB11_113 + WORD $0x394d; BYTE $0xf2 // cmp r10, r14 + JNE LBB11_130 -LBB11_110: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 +LBB11_126: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_211 WORD $0xc031 // xor eax, eax - LONG $0x323b4466 // cmp r14w, word [rdx] - JMP LBB11_183 + LONG $0x023b4466 // cmp r8w, word [rdx] LBB11_128: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x17348a41 // mov sil, byte [r15 + rdx] + LONG $0x07e68041 // and r14b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + JMP LBB11_209 + +LBB11_147: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB11_129: - LONG $0x323b4466 // cmp r14w, word [rdx] +LBB11_148: + LONG $0x023b4466 // cmp r8w, word [rdx] WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] + LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0x3044; BYTE $0xd3 // xor bl, r10b LONG $0x371c8841 // mov byte [r15 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd19d0f41 // setge r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd29d0f41 // setge r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl LONG $0x37048841 // mov byte [r15 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB11_129 + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB11_148 -LBB11_125: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 - LONG $0x323b4466 // cmp r14w, word [rdx] - JMP LBB11_127 +LBB11_144: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_211 + LONG $0x023b4466 // cmp r8w, word [rdx] + JMP LBB11_146 -LBB11_162: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB11_185: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB11_163: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] +LBB11_186: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] + LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0x3044; BYTE $0xd3 // xor bl, r10b LONG $0x371c8841 // mov byte [r15 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x08423b4c // cmp r8, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd19d0f41 // setge r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd29d0f41 // setge r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl LONG $0x37048841 // mov byte [r15 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB11_163 + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB11_186 -LBB11_160: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - JMP LBB11_127 +LBB11_183: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_211 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + JMP LBB11_146 -LBB11_177: +LBB11_202: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB11_178: +LBB11_203: LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] LONG $0x000000b8; BYTE $0x00 // mov eax, 0 WORD $0xff14 // adc al, -1 @@ -64255,15 +65923,15 @@ LBB11_178: WORD $0xd830 // xor al, bl LONG $0x37048841 // mov byte [r15 + rsi], al WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB11_178 + JNE LBB11_203 -LBB11_175: +LBB11_200: LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 + JE LBB11_211 WORD $0xc031 // xor eax, eax LONG $0x022ef8c5 // vucomiss xmm0, dword [rdx] -LBB11_183: +LBB11_208: WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 @@ -64271,52 +65939,54 @@ LBB11_183: LONG $0x07e38041 // and r11b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + +LBB11_209: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - JMP LBB11_184 + JMP LBB11_210 -LBB11_145: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB11_166: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB11_146: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] +LBB11_167: + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] + LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0x3044; BYTE $0xd3 // xor bl, r10b LONG $0x371c8841 // mov byte [r15 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd19d0f41 // setge r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd29d0f41 // setge r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl LONG $0x37048841 // mov byte [r15 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB11_146 + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB11_167 -LBB11_143: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] +LBB11_164: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_211 + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] -LBB11_127: +LBB11_146: WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfa // mov rdx, rdi @@ -64329,75 +65999,76 @@ LBB11_127: WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al -LBB11_184: +LBB11_210: WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x171c8841 // mov byte [r15 + rdx], bl -LBB11_185: +LBB11_211: MOVQ 1280(SP), SP VZEROUPPER RET -LBB11_94: +LBB11_108: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d -LBB11_95: - LONG $0x321c3a44 // cmp r11b, byte [rdx + rsi] - WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi +LBB11_109: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0f343a46 // cmp r14b, byte [rdi + r9] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xce // mov rsi, r9 + LONG $0x03eec148 // shr rsi, 3 + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl - LONG $0x325c3a44; BYTE $0x01 // cmp r11b, byte [rdx + rsi + 1] - LONG $0x02768d48 // lea rsi, [rsi + 2] - LONG $0xd19d0f41 // setge r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x35548841; BYTE $0x00 // mov byte [r13 + rsi], dl + LONG $0x07743a44; BYTE $0x01 // cmp r14b, byte [rdi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB11_95 - WORD $0x0148; BYTE $0xf2 // add rdx, rsi + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB11_109 + WORD $0x014c; BYTE $0xcf // add rdi, r9 -LBB11_97: +LBB11_111: LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] + JE LBB11_211 + WORD $0x3a44; BYTE $0x37 // cmp r14b, byte [rdi] WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] - LONG $0x07e68040 // and sil, 7 + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al - JMP LBB11_80 + JMP LBB11_86 -LBB11_75: +LBB11_81: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xc9 // xor r9d, r9d -LBB11_76: +LBB11_82: WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0f1c3a46 // cmp r11b, byte [rdi + r9] + LONG $0x0f343a46 // cmp r14b, byte [rdi + r9] LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 WORD $0xd380; BYTE $0xff // adc bl, -1 WORD $0x894c; BYTE $0xce // mov rsi, r9 @@ -64411,7 +66082,7 @@ LBB11_76: WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b LONG $0x35548841; BYTE $0x00 // mov byte [r13 + rsi], dl - LONG $0x075c3a44; BYTE $0x01 // cmp r11b, byte [rdi + rax + 1] + LONG $0x07743a44; BYTE $0x01 // cmp r14b, byte [rdi + rax + 1] LONG $0x02488d4c // lea r9, [rax + 2] LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 WORD $0xd380; BYTE $0xff // adc bl, -1 @@ -64423,14 +66094,14 @@ LBB11_76: WORD $0xd030 // xor al, dl LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB11_76 + JNE LBB11_82 WORD $0x014c; BYTE $0xcf // add rdi, r9 -LBB11_78: +LBB11_84: LONG $0x01c0f641 // test r8b, 1 - JE LBB11_185 + JE LBB11_211 WORD $0xc031 // xor eax, eax - WORD $0x3a44; BYTE $0x1f // cmp r11b, byte [rdi] + WORD $0x3a44; BYTE $0x37 // cmp r14b, byte [rdi] WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 @@ -64442,1984 +66113,1985 @@ LBB11_78: WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al -LBB11_80: +LBB11_86: WORD $0x3040; BYTE $0xfb // xor bl, dil LONG $0x155c8841; BYTE $0x00 // mov byte [r13 + rdx], bl - JMP LBB11_185 + JMP LBB11_211 -LBB11_85: - LONG $0xe0e68349 // and r14, -32 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 +LBB11_99: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000016824848948 // mov qword [rsp + 360], rax - QUAD $0x000001a024b4894c // mov qword [rsp + 416], r14 - LONG $0xb7048d4b // lea rax, [r15 + 4*r14] + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000017024848948 // mov qword [rsp + 368], rax - LONG $0x6e79c1c4; BYTE $0xc3 // vmovd xmm0, r11d + QUAD $0x000001a0248c8948 // mov qword [rsp + 416], rcx + LONG $0x8f048d49 // lea rax, [r15 + 4*rcx] + QUAD $0x0000016824848948 // mov qword [rsp + 360], rax + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 QUAD $0x00018024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 384], ymm0 - WORD $0xdb31 // xor ebx, ebx + WORD $0xc031 // xor eax, eax QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 -LBB11_86: - QUAD $0x00000178249c8948 // mov qword [rsp + 376], rbx +LBB11_100: + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x0000017824848948 // mov qword [rsp + 376], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - QUAD $0x000000d824848948 // mov qword [rsp + 216], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 - LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xc06ef9c5 // vmovd xmm0, eax - LONG $0x1a04b60f // movzx eax, byte [rdx + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] + LONG $0x1744b60f; BYTE $0x01 // movzx eax, byte [rdi + rdx + 1] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x1a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x0a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rcx + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000220248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 544], xmm1 - LONG $0x1a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x0a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rcx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x0a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rcx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - QUAD $0x000000f8249c8948 // mov qword [rsp + 248], rbx - LONG $0x1a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x0a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rcx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xf06ef9c5 // vmovd xmm6, eax - LONG $0x0a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rcx + 6] - QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x000000f824948948 // mov qword [rsp + 248], rdx LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x1a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x0a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rcx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x20ce8149; WORD $0x0002; BYTE $0x00 // or r14, 544 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0x40c98148; WORD $0x0002; BYTE $0x00 // or rcx, 576 - QUAD $0x000000b0248c8948 // mov qword [rsp + 176], rcx - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02600d48; WORD $0x0000 // or rax, 608 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x000000c824848948 // mov qword [rsp + 200], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + WORD $0x8949; BYTE $0xdc // mov r12, rbx + LONG $0x20cc8149; WORD $0x0002; BYTE $0x00 // or r12, 544 + QUAD $0x000000c824a4894c // mov qword [rsp + 200], r12 + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0x40cf8149; WORD $0x0002; BYTE $0x00 // or r15, 576 + LONG $0x247c894c; BYTE $0x50 // mov qword [rsp + 80], r15 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x60cb8149; WORD $0x0002; BYTE $0x00 // or r11, 608 + QUAD $0x000000e8249c894c // mov qword [rsp + 232], r11 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x80ca8149; WORD $0x0002; BYTE $0x00 // or r10, 640 + QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02800d48; WORD $0x0000 // or rax, 640 + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - WORD $0x8949; BYTE $0xda // mov r10, rbx - LONG $0xa0ca8149; WORD $0x0002; BYTE $0x00 // or r10, 672 - QUAD $0x000001002494894c // mov qword [rsp + 256], r10 - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - LONG $0xc0c98149; WORD $0x0002; BYTE $0x00 // or r9, 704 - QUAD $0x000000f0248c894c // mov qword [rsp + 240], r9 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0xe0cb8149; WORD $0x0002; BYTE $0x00 // or r11, 736 - LONG $0x245c894c; BYTE $0x50 // mov qword [rsp + 80], r11 - WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 - QUAD $0x0000008024bc894c // mov qword [rsp + 128], r15 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - LONG $0x20c88149; WORD $0x0003; BYTE $0x00 // or r8, 800 - LONG $0x2444894c; BYTE $0x38 // mov qword [rsp + 56], r8 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0x40cc8149; WORD $0x0003; BYTE $0x00 // or r12, 832 - QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0xc0ce8149; WORD $0x0002; BYTE $0x00 // or r14, 704 + QUAD $0x000000a024b4894c // mov qword [rsp + 160], r14 WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03600d48; WORD $0x0000 // or rax, 864 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + LONG $0x02e00d48; WORD $0x0000 // or rax, 736 + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + WORD $0x8949; BYTE $0xdd // mov r13, rbx + LONG $0x00cd8149; WORD $0x0003; BYTE $0x00 // or r13, 768 + LONG $0x246c894c; BYTE $0x30 // mov qword [rsp + 48], r13 WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03800d48; WORD $0x0000 // or rax, 896 - WORD $0x8948; BYTE $0xc7 // mov rdi, rax + LONG $0x03200d48; WORD $0x0000 // or rax, 800 LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + LONG $0x40c98149; WORD $0x0003; BYTE $0x00 // or r9, 832 + QUAD $0x000000d8248c894c // mov qword [rsp + 216], r9 + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x60c98148; WORD $0x0003; BYTE $0x00 // or rcx, 864 + QUAD $0x000000b0248c8948 // mov qword [rsp + 176], rcx + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0x80c88149; WORD $0x0003; BYTE $0x00 // or r8, 896 + QUAD $0x000000a82484894c // mov qword [rsp + 168], r8 + WORD $0x8948; BYTE $0xde // mov rsi, rbx + LONG $0xa0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 928 + QUAD $0x000000f024b48948 // mov qword [rsp + 240], rsi WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03a00d48; WORD $0x0000 // or rax, 928 - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax - WORD $0x8948; BYTE $0xd8 // mov rax, rbx + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x000000e0249c8948 // mov qword [rsp + 224], rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - LONG $0xe0cb8148; WORD $0x0003; BYTE $0x00 // or rbx, 992 - LONG $0x207923c4; WORD $0x320c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdx + r14], 1 - LONG $0x2031e3c4; WORD $0x0a04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdx + rcx], 2 - LONG $0x2079a3c4; WORD $0x2a04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdx + r13], 3 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x2079e3c4; WORD $0x0a04; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdx + rcx], 4 - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdx + r10], 5 - LONG $0x2079a3c4; WORD $0x0a04; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdx + r9], 6 - LONG $0x2079a3c4; WORD $0x1a04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdx + r11], 7 - LONG $0x2079a3c4; WORD $0x3a04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdx + r15], 8 - LONG $0x2079a3c4; WORD $0x0204; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdx + r8], 9 - LONG $0x2079a3c4; WORD $0x2204; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdx + r12], 10 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - LONG $0x2079a3c4; WORD $0x1204; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdx + r10], 11 - LONG $0x2079e3c4; WORD $0x3a04; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdx + rdi], 12 - LONG $0x2079e3c4; WORD $0x3204; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdx + rsi], 13 - LONG $0x2079e3c4; WORD $0x0204; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdx + rax], 14 - LONG $0x2079e3c4; WORD $0x1a04; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdx + rbx], 15 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x000000a8249c8948 // mov qword [rsp + 168], rbx - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdx + r11], 1 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdx + rax], 2 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + rax], 3 - QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r8], 4 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r9], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + rax], 6 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + rsi], 7 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + r15], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + rdi], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + rax], 10 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + rbx], 11 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + LONG $0xe0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 992 + QUAD $0x0000010824948948 // mov qword [rsp + 264], rdx + LONG $0x207923c4; WORD $0x270c; BYTE $0x01 // vpinsrb xmm9, xmm0, byte [rdi + r12], 1 + LONG $0x2031a3c4; WORD $0x3f04; BYTE $0x02 // vpinsrb xmm0, xmm9, byte [rdi + r15], 2 + LONG $0x2079a3c4; WORD $0x1f04; BYTE $0x03 // vpinsrb xmm0, xmm0, byte [rdi + r11], 3 + LONG $0x2079a3c4; WORD $0x1704; BYTE $0x04 // vpinsrb xmm0, xmm0, byte [rdi + r10], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x05 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 5 + LONG $0x2079a3c4; WORD $0x3704; BYTE $0x06 // vpinsrb xmm0, xmm0, byte [rdi + r14], 6 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x07 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 7 + LONG $0x2079a3c4; WORD $0x2f04; BYTE $0x08 // vpinsrb xmm0, xmm0, byte [rdi + r13], 8 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + LONG $0x2079e3c4; WORD $0x1f04; BYTE $0x09 // vpinsrb xmm0, xmm0, byte [rdi + rbx], 9 + LONG $0x2079a3c4; WORD $0x0f04; BYTE $0x0a // vpinsrb xmm0, xmm0, byte [rdi + r9], 10 + LONG $0x2079e3c4; WORD $0x0f04; BYTE $0x0b // vpinsrb xmm0, xmm0, byte [rdi + rcx], 11 + LONG $0x2079a3c4; WORD $0x0704; BYTE $0x0c // vpinsrb xmm0, xmm0, byte [rdi + r8], 12 + LONG $0x2079e3c4; WORD $0x3704; BYTE $0x0d // vpinsrb xmm0, xmm0, byte [rdi + rsi], 13 + LONG $0x2079e3c4; WORD $0x0704; BYTE $0x0e // vpinsrb xmm0, xmm0, byte [rdi + rax], 14 + LONG $0x2079e3c4; WORD $0x1704; BYTE $0x0f // vpinsrb xmm0, xmm0, byte [rdi + rdx], 15 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + LONG $0x2061a3c4; WORD $0x371c; BYTE $0x01 // vpinsrb xmm3, xmm3, byte [rdi + r14], 1 LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + rbx], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rbx], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rbx], 14 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + r14], 15 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x01011a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 1], 1 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x02011a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 1], 2 - QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] - QUAD $0x03012a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 1], 3 - QUAD $0x04010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 4 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x05010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 5 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x06010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 6 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x07010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 7 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x08010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 8 + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x02 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 2 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r12], 3 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r8], 4 + QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + r10], 5 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r9], 6 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + r11], 7 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + LONG $0x2061a3c4; WORD $0x3f1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + r15], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + rax], 9 LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 10 - QUAD $0x0b0112642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 1], 11 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0c011a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 1], 12 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x0d0112642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 1], 13 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0e010a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 1], 14 - QUAD $0x0f0122642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 1], 15 - QUAD $0x01011a6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r11 + 1], 1 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x02010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 2 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x0301226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 1], 3 - QUAD $0x0401026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 1], 4 - QUAD $0x05010a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 1], 5 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x06010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 6 - QUAD $0x0701326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 1], 7 - QUAD $0x08013a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 1], 8 - QUAD $0x09013a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 1], 9 - WORD $0x8949; BYTE $0xfd // mov r13, rdi - QUAD $0x0a01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 10 + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + rcx], 10 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rdx], 11 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rsi], 12 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rsi], 14 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rsi], 15 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x01012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 1 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x020137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 2 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x030137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 3 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x040137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x050137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 5 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x06012f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 1], 6 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x070137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 7 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x080137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 8 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x090137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 9 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0a0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 10 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0b0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 11 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0c0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 12 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0d0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 13 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0e0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 14 + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x0f0137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 1], 15 + QUAD $0x0101376c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x02011f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 1], 2 + QUAD $0x0301276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 1], 3 + QUAD $0x0401076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 1], 4 + QUAD $0x0501176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 1], 5 + QUAD $0x06010f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 1], 6 + QUAD $0x07011f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 1], 7 + QUAD $0x08013f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 1], 8 + QUAD $0x0901076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 9 + QUAD $0x0a010f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 1], 10 + QUAD $0x0b01176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 1], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 12 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e01026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 1], 14 + QUAD $0x0d01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e01076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 1], 14 LONG $0x386563c4; WORD $0x01e8 // vinserti128 ymm13, ymm3, xmm0, 1 - QUAD $0x0f0132442051a3c4 // vpinsrb xmm0, xmm5, byte [rdx + r14 + 1], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f0107442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 1], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0004c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm0 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xd06e79c5 // vmovd xmm10, eax QUAD $0x00022024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 544] - QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] - QUAD $0x01023a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 2], 1 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x020202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 2 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x030202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x040202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 4 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x050202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 5 - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - QUAD $0x060202442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 2], 6 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x07020a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 2], 7 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x08021a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 2], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 11 - QUAD $0x0c021a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 2], 12 - QUAD $0x0d0212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 2], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 14 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0f0202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 2], 15 + QUAD $0x010207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x020207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 2 QUAD $0x000000e824948b4c // mov r10, qword [rsp + 232] - QUAD $0x0001e0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 480] - QUAD $0x0102125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 2], 1 + QUAD $0x030217442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 2], 3 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x040237442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 2], 4 + QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] + QUAD $0x05021f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 2], 5 + QUAD $0x06022f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 2], 6 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x07021f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 2], 7 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x08020f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 2], 8 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x090207442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 2], 9 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0202025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 2 - QUAD $0x0302225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 2], 3 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x0402325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 2], 4 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x0502225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 2], 5 - QUAD $0x06020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 6 - QUAD $0x0702325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x08023a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 2], 8 - WORD $0x894c; BYTE $0xe9 // mov rcx, r13 - QUAD $0x09022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 9 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0a02325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 2], 10 + QUAD $0x0a0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 12 + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x0d0227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 2], 13 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x0e023f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 2], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f0207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 2], 15 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x0001e0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 480] + QUAD $0x0102375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 2], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0202075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0302075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0402075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 4 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x0502375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 2], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0602075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0702075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0802075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 8 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x0902175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 9 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0a02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 10 + QUAD $0x0000014024948b48 // mov rdx, qword [rsp + 320] + QUAD $0x0b02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 11 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0c02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 12 LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0b022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0c021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0e021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 14 - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0f022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 15 - QUAD $0x01033a642021a3c4 // vpinsrb xmm4, xmm11, byte [rdx + r15 + 3], 1 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x02031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 2 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x03031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 3 - QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x04031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 4 - QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] - QUAD $0x05031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 5 - QUAD $0x060302642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 3], 6 - QUAD $0x07030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 7 - QUAD $0x08031a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 3], 8 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x09030a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 3], 9 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0a031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 10 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0b031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 11 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0c031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 12 + QUAD $0x0d022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 13 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0e02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 14 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0f02175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 2], 15 + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x01032f642021a3c4 // vpinsrb xmm4, xmm11, byte [rdi + r13 + 3], 1 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x020317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 2 + QUAD $0x030317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 3], 3 + QUAD $0x040337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 3], 4 + QUAD $0x05031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 5 + WORD $0x8949; BYTE $0xda // mov r10, rbx QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x0d032a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 3], 13 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x0e031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 14 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0f031a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 3], 15 - QUAD $0x0103126c2039a3c4 // vpinsrb xmm5, xmm8, byte [rdx + r10 + 3], 1 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - QUAD $0x0203026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 2 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0303026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 3 - QUAD $0x0403326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 3], 4 - QUAD $0x0503226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 3], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0603026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 6 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0703026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 7 - QUAD $0x08033a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 3], 8 - QUAD $0x09030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 9 - QUAD $0x0a03326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 12 + QUAD $0x06032f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 3], 6 + QUAD $0x07031f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 3], 7 + QUAD $0x08030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 8 + QUAD $0x090307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 9 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x0a030f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 3], 10 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x0b031f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 3], 11 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0c0317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 3], 12 + QUAD $0x0d0327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 3], 13 + QUAD $0x0e033f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 3], 14 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x0f0307642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 3], 15 + QUAD $0x01030f6c2039e3c4 // vpinsrb xmm5, xmm8, byte [rdi + rcx + 3], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 2 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x03030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 3 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x04030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 4 + QUAD $0x0503376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 3], 5 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0603276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 3], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x07030f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 3], 7 + QUAD $0x0803076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0903076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d03026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 3], 13 + QUAD $0x0b03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d03076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 3], 13 LONG $0x3865e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm3, xmm0, 1 QUAD $0x00022024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm0 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0302442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 3], 14 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x09 // movzx edi, byte [rdx + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0302442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 3], 15 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e0307442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rax + 3], 14 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f0307442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 3], 15 LONG $0x387de3c4; WORD $0x01c4 // vinserti128 ymm0, ymm0, xmm4, 1 QUAD $0x0001e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm0 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x09 // movzx edi, byte [rdx + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x0001c024846ff9c5; BYTE $0x00 // vmovdqa xmm0, oword [rsp + 448] - QUAD $0x01043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 1 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x02043a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 4], 2 - QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x030422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 4], 3 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x040432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 4], 4 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - QUAD $0x050402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 4], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x060402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 6 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x010437442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 4], 1 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x070402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 7 - QUAD $0x08041a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 4], 8 - QUAD $0x09040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 10 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0b040a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 4], 11 + QUAD $0x020407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 2 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x030407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x040407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 4 + QUAD $0x050417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 4], 5 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x06042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 6 + QUAD $0x07041f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 4], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x080407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 12 - QUAD $0x0d042a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 4], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e0402442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 4], 14 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x0f0412442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 4], 15 - QUAD $0x01041a5c2001e3c4 // vpinsrb xmm3, xmm15, byte [rdx + rbx + 4], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x02043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 2 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x03042a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 4], 3 - QUAD $0x0404325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 4], 4 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0504025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x06043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x07043a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 4], 7 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0804025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 8 - QUAD $0x09040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b040a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 4], 11 + QUAD $0x090407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 9 + QUAD $0x0a040f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 4], 10 + QUAD $0x0b041f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 4], 11 + QUAD $0x0c0417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 4], 12 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0d0407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 4], 13 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x0e042f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 4], 14 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + QUAD $0x0f0407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 4], 15 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x0104375c2001a3c4 // vpinsrb xmm3, xmm15, byte [rdi + r14 + 4], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 14 + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] + QUAD $0x03040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 3 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + QUAD $0x0404075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 4 + QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] + QUAD $0x0504175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 5 + QUAD $0x0604275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 15 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x010502642009e3c4 // vpinsrb xmm4, xmm14, byte [rdx + rax + 5], 1 - QUAD $0x02053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 2 - QUAD $0x030522642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 5], 3 - QUAD $0x040532642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 5], 4 - QUAD $0x050502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 5], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x060502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 6 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x07053a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 5], 7 - QUAD $0x08051a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 5], 8 + QUAD $0x0704075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 7 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x08041f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 4], 8 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0904275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 4], 9 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x0a041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 10 + QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] + QUAD $0x0b041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 11 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x0c041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 12 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0d041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 13 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0e041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 14 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0f041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 15 + QUAD $0x010537642009e3c4 // vpinsrb xmm4, xmm14, byte [rdi + rsi + 5], 1 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x020537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 2 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x030537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 3 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x040537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 4 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x050537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 5 + QUAD $0x06053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 6 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x070537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 7 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x08053f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 5], 8 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x090537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 9 + QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] + QUAD $0x0a0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 10 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0b0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 11 + QUAD $0x0c0517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 5], 12 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0d0537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 5], 13 + QUAD $0x0e052f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 5], 14 + QUAD $0x0f050f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 5], 15 + QUAD $0x0105376c2049a3c4 // vpinsrb xmm5, xmm6, byte [rdi + r14 + 5], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 2 + QUAD $0x03050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 3 + QUAD $0x0405076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 4 + QUAD $0x0505176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 5 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x0605176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 6 + QUAD $0x0705076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 7 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x08051f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 5], 8 + QUAD $0x0905276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 5], 9 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 10 - QUAD $0x0b050a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 5], 11 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0c051a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 5], 12 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0d0532642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 5], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e0502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 5], 14 - QUAD $0x0f0512642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 5], 15 - QUAD $0x01051a6c2049e3c4 // vpinsrb xmm5, xmm6, byte [rdx + rbx + 5], 1 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0205026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 2 - QUAD $0x03052a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 5], 3 - QUAD $0x0405326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 5], 4 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0505026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0605026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 6 - QUAD $0x07053a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 5], 7 - QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] - QUAD $0x0805326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 5], 8 - QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] - QUAD $0x0905226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 5], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 10 - QUAD $0x0b050a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 5], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 12 + QUAD $0x0a05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e05026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 5], 14 + QUAD $0x0b05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e05076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 5], 14 + WORD $0x8949; BYTE $0xc0 // mov r8, rax LONG $0x386563c4; WORD $0x01f0 // vinserti128 ymm14, ymm3, xmm0, 1 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0502442051e3c4 // vpinsrb xmm0, xmm5, byte [rdx + rax + 5], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 + QUAD $0x0f051f442051e3c4 // vpinsrb xmm0, xmm5, byte [rdi + rbx + 5], 15 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x387d63c4; WORD $0x01fc // vinserti128 ymm15, ymm0, xmm4, 1 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x01060f442019e3c4 // vpinsrb xmm0, xmm12, byte [rdi + rcx + 6], 1 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x020617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 6], 2 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x030637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 6], 3 + QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] + QUAD $0x04061f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 6], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 5 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x06060f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 6], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x070607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 7 + QUAD $0x08063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x090607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 9 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x0a063f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 6], 10 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x0b061f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 6], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 12 + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x0d0627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 6], 13 + QUAD $0x0e062f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 6], 14 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x0f0607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 6], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0106076c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdi + rax + 6], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0206076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 2 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x010602442019e3c4 // vpinsrb xmm0, xmm12, byte [rdx + rax + 6], 1 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x020602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 2 - QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] - QUAD $0x03061a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 6], 3 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x040602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 6], 4 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - QUAD $0x050612442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 6], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x060602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 6 - QUAD $0x07063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 7 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x080602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 8 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x09063a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 6], 9 + QUAD $0x0306076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 3 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 6], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b060a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 6], 11 - QUAD $0x0c061a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 6], 12 - QUAD $0x0d0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0e0632442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 6], 14 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x0f062a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 6], 15 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x01061a6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdx + r11 + 6], 1 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x02060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 2 + QUAD $0x0406076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0506076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 5 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x0606176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 6 + QUAD $0x0706376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 7 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0806376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 8 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x0906176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 6], 9 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0a06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 10 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0b06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 11 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0c06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 12 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0d06376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 13 + QUAD $0x0e06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 14 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0f06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 15 + QUAD $0x01070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 1 + QUAD $0x020717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 2 + QUAD $0x030737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 3 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + QUAD $0x04071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x05070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 5 + QUAD $0x06070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 6 LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x03060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 3 - QUAD $0x04060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 4 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x05060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x06063a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rdi + 6], 6 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x07060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 7 - QUAD $0x0806326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 6], 8 - QUAD $0x0906226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 9 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0a060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 10 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0b06326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 6], 11 - LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] - QUAD $0x0c060a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 6], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 13 + QUAD $0x07070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 7 LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 14 - QUAD $0x0000012024a48b4c // mov r12, qword [rsp + 288] - QUAD $0x0f06226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 6], 15 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x01070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 1 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x02070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 2 - QUAD $0x03071a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 7], 3 - QUAD $0x040702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 4 - QUAD $0x050712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 7], 5 - QUAD $0x000000f024848b4c // mov r8, qword [rsp + 240] - QUAD $0x060702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 6 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x07070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 7 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - QUAD $0x080712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 7], 8 - QUAD $0x09073a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 7], 9 - QUAD $0x0a0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 7], 12 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x0d071a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 7], 13 - QUAD $0x0e0732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 14 - QUAD $0x0f072a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 7], 15 - QUAD $0x01071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 1 - WORD $0x894d; BYTE $0xdd // mov r13, r11 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x0207324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 7], 2 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0307024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 3 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x04070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 4 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x0507224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 7], 5 - QUAD $0x06073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x07073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 7 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x08071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 8 + QUAD $0x08070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 8 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + QUAD $0x0a073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 10 + QUAD $0x0b071f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 7], 11 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x0c070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 12 + QUAD $0x0d0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 13 + QUAD $0x0e072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 14 QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x09070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 9 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0a070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 10 - QUAD $0x0b07324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 7], 11 - QUAD $0x0c070a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 7], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 13 + QUAD $0x0f070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 15 + QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] + QUAD $0x01071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 2 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x0307274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 7], 3 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x04070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 4 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0707074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x0907174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 12 + QUAD $0x0d07374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 13 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0001c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm0 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e073a442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rdi + 7], 14 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a7cb60f; BYTE $0x0b // movzx edi, byte [rdx + rcx + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f070a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 7], 15 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e0707442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 7], 14 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x0f072f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 7], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00020024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm0 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - LONG $0x0a7cb60f; BYTE $0x0b // movzx edi, byte [rdx + rcx + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x01083a442031e3c4 // vpinsrb xmm0, xmm9, byte [rdx + rdi + 8], 1 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x02083a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 8], 2 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x03083a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 8], 3 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x04080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 4 - QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] - QUAD $0x05080a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 8], 5 - QUAD $0x060802442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 8], 6 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x07080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 7 - QUAD $0x080812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x09080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 10 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x0b0812442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 8], 11 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0c080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 12 - QUAD $0x0d081a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 8], 13 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0e080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 14 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0f080a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 8], 15 - QUAD $0x01082a6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdx + r13 + 8], 1 - WORD $0x8949; BYTE $0xf6 // mov r14, rsi - QUAD $0x0208326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 2 - QUAD $0x0308026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 3 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x04080a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 8], 4 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x0508226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 8], 5 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0608326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 6 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0708226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 8], 7 - QUAD $0x08081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 8 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0908026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 9 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0a081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 10 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0b081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0c081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0e081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 14 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 15 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x01091a742039e3c4 // vpinsrb xmm6, xmm8, byte [rdx + rbx + 9], 1 - QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] - QUAD $0x02091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 2 - QUAD $0x03093a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 9], 3 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c824b48b4c // mov r14, qword [rsp + 200] + QUAD $0x010837442031a3c4 // vpinsrb xmm0, xmm9, byte [rdi + r14 + 8], 1 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x020817442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 8], 2 + QUAD $0x030807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x040807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 4 QUAD $0x00000098249c8b48 // mov rbx, qword [rsp + 152] - QUAD $0x04091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 4 - QUAD $0x05090a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 9], 5 - QUAD $0x060902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 6 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x07093a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 9], 7 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x08091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x09091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 9 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0a091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 10 - QUAD $0x0b0912742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 9], 11 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0c091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 12 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0d0902742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 9], 13 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x0e091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 14 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x0f091a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 9], 15 - QUAD $0x01092a7c2021a3c4 // vpinsrb xmm7, xmm11, byte [rdx + r13 + 9], 1 - QUAD $0x0209327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 9], 2 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x03091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 3 - QUAD $0x04090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 4 - QUAD $0x05093a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rdi + 9], 5 - QUAD $0x0609327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 9], 6 - WORD $0x8949; BYTE $0xf6 // mov r14, rsi - QUAD $0x0709227c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r12 + 9], 7 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x08090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 8 - QUAD $0x0909027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 9 - QUAD $0x0a091a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 9], 10 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x0b091a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 9], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 13 + QUAD $0x05081f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 8], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x060807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 6 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x070807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 8], 7 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 14 + QUAD $0x080807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 8 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x09083f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 8], 9 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0a0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 11 + QUAD $0x0c080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 12 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0d0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e0807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 8], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f080f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 8], 15 + QUAD $0x01081f6c2029a3c4 // vpinsrb xmm5, xmm10, byte [rdi + r11 + 8], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0208376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 8], 2 + QUAD $0x0308276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 3 + QUAD $0x04080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0508076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 5 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x06080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x07080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 7 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x08080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 8 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x09080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 9 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x0a081f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 8], 10 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0b080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 11 + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x0c08176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 8], 12 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0d080f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 8], 13 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0e08276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 14 + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x010937742039a3c4 // vpinsrb xmm6, xmm8, byte [rdi + r14 + 9], 1 + QUAD $0x020917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 2 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x030937742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 9], 3 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x040917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 4 + QUAD $0x05091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 5 + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x060917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 6 + QUAD $0x070907742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 9], 7 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x080917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 8 + QUAD $0x09093f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 9], 9 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x0a091f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 9], 10 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0b0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 11 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x0c0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 12 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0d0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 13 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0e0917742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 9], 14 + QUAD $0x0f090f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 9], 15 + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x0109177c2021e3c4 // vpinsrb xmm7, xmm11, byte [rdi + rdx + 9], 1 + QUAD $0x0209377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 9], 2 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0309177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 3 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x0409177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 4 + QUAD $0x0509077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0609077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0709077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0809077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0909077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 9], 9 + QUAD $0x0a091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 10 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0b091f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 9], 11 + QUAD $0x0c09177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 9], 12 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + QUAD $0x0d090f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rcx + 9], 13 + QUAD $0x0e09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 14 LONG $0x3855e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm5, xmm0, 1 QUAD $0x0004a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f09026c2041e3c4 // vpinsrb xmm5, xmm7, byte [rdx + rax + 9], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xc76ef9c5 // vmovd xmm0, edi + QUAD $0x0f092f6c2041a3c4 // vpinsrb xmm5, xmm7, byte [rdi + r13 + 9], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xc06ef9c5 // vmovd xmm0, eax LONG $0x3855e3c4; WORD $0x01ee // vinserti128 ymm5, ymm5, xmm6, 1 QUAD $0x00048024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm5 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x010a2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 10], 1 - QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] - QUAD $0x020a225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 10], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x030a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 3 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x040a125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 10], 4 - QUAD $0x050a0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 10], 5 - QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] - QUAD $0x060a0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 10], 6 - QUAD $0x070a3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 10], 7 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x080a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 9 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a0a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 12 - QUAD $0x0d0a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 14 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0f0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 15 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x010a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 1 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x020a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 2 - QUAD $0x030a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x040a3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 10], 4 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x050a3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 10], 5 - QUAD $0x060a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 6 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x070a1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 10], 7 - QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] - QUAD $0x080a02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 10], 8 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x090a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 10 - QUAD $0x0b0a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 12 - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - QUAD $0x0d0a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 13 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0e0a32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 10], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 15 - QUAD $0x010b2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 11], 1 - QUAD $0x020b224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 11], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x030b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 3 - QUAD $0x040b124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 11], 4 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - QUAD $0x050b224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 11], 5 - QUAD $0x060b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 6 + QUAD $0x010a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 1 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x070b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 7 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x080b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 9 - QUAD $0x0a0b324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 11], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 11 + QUAD $0x020a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 2 + QUAD $0x030a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 3 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x040a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 4 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x050a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 5 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x060a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x070a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x080a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 12 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0d0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 13 - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x0e0b2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 11], 14 + QUAD $0x090a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 9 + QUAD $0x0a0a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 10 + QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] + QUAD $0x0b0a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 11 QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0f0b324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 11], 15 - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - QUAD $0x010b0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 11], 1 - QUAD $0x020b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 2 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x030b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 3 - QUAD $0x040b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 11], 4 - QUAD $0x050b3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 11], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x060b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 6 - QUAD $0x070b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 7 - QUAD $0x080b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 11], 8 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x090b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 12 - QUAD $0x0d0b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 11], 13 - LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 - QUAD $0x000460249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm3 - QUAD $0x0e0b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 11], 14 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x0d // movzx edi, byte [rdx + rax + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 15 - LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 - QUAD $0x000440248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm1 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x0d // movzx edi, byte [rdx + rax + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x010c0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 12], 1 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x020c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 12], 2 - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x030c3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 12], 3 - QUAD $0x040c12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 12], 4 - QUAD $0x050c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 12], 5 + QUAD $0x0c0a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 12 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x060c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 6 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x070c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 7 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x080c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 9 + QUAD $0x0d0a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 13 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x0e0a2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 10], 14 + QUAD $0x0f0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 15 + QUAD $0x00000100248c8b4c // mov r9, qword [rsp + 256] + QUAD $0x010a0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 10], 1 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x020a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 12 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0d0c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 12], 13 - QUAD $0x0e0c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 12], 14 - QUAD $0x0f0c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 12], 15 - QUAD $0x010c0a542051a3c4 // vpinsrb xmm2, xmm5, byte [rdx + r9 + 12], 1 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x020c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 2 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x030c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 3 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x040c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 4 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x050c2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 12], 5 - QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] - QUAD $0x060c0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 12], 6 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x070c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 7 - QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] - QUAD $0x080c1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 12], 8 - QUAD $0x090c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a0c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 12], 10 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0b0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0c0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 12 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x0d0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 13 - QUAD $0x0e0c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 12], 14 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x0f0c1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 12], 15 - QUAD $0x010d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 1 - QUAD $0x020d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 2 - QUAD $0x030d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 13], 3 - QUAD $0x040d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 13], 4 - QUAD $0x050d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 5 - WORD $0x894d; BYTE $0xe2 // mov r10, r12 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - QUAD $0x060d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 6 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x070d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 7 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x080d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 8 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x090d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 9 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0a0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 10 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0b0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 11 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0c0d3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 13], 12 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x0d0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 13 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x0e0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 14 - QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] - QUAD $0x0f0d225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 13], 15 + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x050a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 5 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x060a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x070a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 7 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x080a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 8 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x090a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 9 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0a0a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 10 + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + QUAD $0x0b0a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 11 + QUAD $0x0c0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 12 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0d0a1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 10], 13 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x0e0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 14 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x0f0a3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 10], 15 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x010b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 1 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x020b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 2 QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] - QUAD $0x010d1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 13], 1 - QUAD $0x020d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 2 - QUAD $0x030d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 3 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x040d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 4 - QUAD $0x050d2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 13], 5 - QUAD $0x060d0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 13], 6 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x070d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 7 - QUAD $0x080d1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 13], 8 + QUAD $0x030b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 3 + QUAD $0x040b074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 11], 4 + QUAD $0x050b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 5 + QUAD $0x060b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 6 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x070b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 7 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x080b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 8 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x090b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 9 + QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] + QUAD $0x0a0b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 10 + QUAD $0x0b0b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 11 + QUAD $0x0c0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 12 + QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] + QUAD $0x0d0b1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 11], 13 + QUAD $0x0e0b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 14 QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x090d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 9 - QUAD $0x0a0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 11 + QUAD $0x0f0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 15 + QUAD $0x010b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 1 + QUAD $0x020b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 2 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + QUAD $0x040b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 4 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x050b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x060b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x090b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 10 + QUAD $0x0b0b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 11], 11 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x0c0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 12 + QUAD $0x0d0b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 11], 13 + LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 + QUAD $0x000460249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm3 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0f0b3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 11], 15 + LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 + QUAD $0x000440248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm1 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x010c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 12], 1 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x020c37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 12], 2 + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x030c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 12], 3 + QUAD $0x040c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x060c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 6 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x070c07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 12], 7 + QUAD $0x080c17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 12], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x090c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 9 + QUAD $0x0a0c17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 12], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 12 + QUAD $0x0d0c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 12], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e0c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 12], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f0c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 12], 15 + QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] + QUAD $0x010c1f542051a3c4 // vpinsrb xmm2, xmm5, byte [rdi + r11 + 12], 1 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 12 + QUAD $0x020c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x040c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 4 + QUAD $0x050c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 5 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x060c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 12], 6 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x070c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 7 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x080c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 8 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x090c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 9 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x0a0c17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 12], 10 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x0b0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 11 + QUAD $0x0c0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 12 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0d0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 13 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0e0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 14 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + QUAD $0x0f0c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 12], 15 + QUAD $0x010d3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 13], 1 + QUAD $0x020d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 2 + QUAD $0x030d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 3 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x040d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 4 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x050d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 5 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x060d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 6 + QUAD $0x070d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 7 + QUAD $0x080d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 8 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x090d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 9 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0a0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 10 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0b0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 11 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x0c0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 12 + QUAD $0x0d0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 13 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0e0d0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 13], 14 + QUAD $0x0f0d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 13], 15 + QUAD $0x010d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x020d1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 13], 2 + QUAD $0x030d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x040d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x050d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 5 + QUAD $0x060d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 6 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + QUAD $0x070d074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 13], 7 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x080d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x090d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 9 + QUAD $0x0a0d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 13 - QUAD $0x0e0d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 14 + QUAD $0x0b0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 11 + QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] + QUAD $0x0c0d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 14 LONG $0x386de3c4; WORD $0x01c0 // vinserti128 ymm0, ymm2, xmm0, 1 QUAD $0x00040024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f0d02442071e3c4 // vpinsrb xmm0, xmm1, byte [rdx + rax + 13], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x0e // movzx edi, byte [rdx + rax + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f0d07442071e3c4 // vpinsrb xmm0, xmm1, byte [rdi + rax + 13], 15 + QUAD $0x000000f824ac8b4c // mov r13, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x0e2f // movzx eax, byte [rdi + r13 + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax LONG $0x387de3c4; WORD $0x01c3 // vinserti128 ymm0, ymm0, xmm3, 1 QUAD $0x00042024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm0 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x0e // movzx edi, byte [rdx + rax + 14] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x010e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 1 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x020e0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 14], 2 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x030e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 3 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x0e3f // movzx eax, byte [rdi + r15 + 14] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x010e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x020e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 2 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + QUAD $0x040e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 4 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x040e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 4 - QUAD $0x050e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 5 - QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] - QUAD $0x060e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 14], 6 - QUAD $0x070e024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 14], 7 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x080e1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 14], 8 + QUAD $0x050e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x060e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x070e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x080e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 8 + QUAD $0x090e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 9 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0a0e0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 14], 10 + QUAD $0x0b0e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 11 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x0c0e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 14], 12 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x0d0e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 14], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x010e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 1 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x020e37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 14], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x030e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x040e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x050e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 5 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x060e17442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 14], 6 + QUAD $0x070e07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 14], 7 + QUAD $0x080e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 14], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x090e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 9 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 14], 9 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x0a0e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 10 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x0b0e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 14], 11 - QUAD $0x0c0e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 12 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x0d0e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 13 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - QUAD $0x0e0e324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 14], 14 - QUAD $0x0f0e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 14], 15 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x010e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x020e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 2 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x030e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x040e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 4 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x050e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x060e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x070e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x080e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 8 - QUAD $0x090e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 9 + QUAD $0x0a0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 11 + QUAD $0x0c0e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 12 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x0d0e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 14], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 14 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f0e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 14], 15 + LONG $0x44b60f42; WORD $0x0f2f // movzx eax, byte [rdi + r13 + 15] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x010f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x020f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 2 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x030f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 3 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x040f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 15], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x050f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x060f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x070f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x080f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 8 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x090f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 15], 9 + QUAD $0x0a0f0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 15], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 11 + QUAD $0x0c0f37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 15], 12 + QUAD $0x0d0f1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 15], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e0f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 15], 14 + QUAD $0x0f0f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 15], 15 + LONG $0x44b60f42; WORD $0x0f3f // movzx eax, byte [rdi + r15 + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x010f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 1 + QUAD $0x020f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x030f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x050f1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 15], 5 + QUAD $0x060f175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 15], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x070f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 7 + QUAD $0x080f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 8 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x090f375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 15], 9 + LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] + QUAD $0x0a0f2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 15], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 12 + QUAD $0x0d0f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 13 LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0a0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 10 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0b0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 11 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0c0e22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 14], 12 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0d0e32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 14], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e0e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f0e3a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 14], 15 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - LONG $0x7cb60f42; WORD $0x0f02 // movzx edi, byte [rdx + r8 + 15] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x010f3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 15], 1 - QUAD $0x020f0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 15], 2 - QUAD $0x030f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 3 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x040f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 4 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - QUAD $0x050f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 5 - QUAD $0x060f2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 15], 6 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x070f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 15], 7 - QUAD $0x080f1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 15], 8 - QUAD $0x090f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 9 - QUAD $0x0a0f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 15], 10 - QUAD $0x0b0f1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 15], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c0f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 15], 12 - QUAD $0x0d0f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 15], 13 - QUAD $0x0e0f32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 15], 14 - QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] - QUAD $0x0f0f0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 15], 15 - QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] - LONG $0x1a7cb60f; BYTE $0x0f // movzx edi, byte [rdx + rbx + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x010f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 1 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x020f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 2 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x030f125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 15], 3 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x040f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 4 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x050f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 5 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x060f0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 15], 6 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x070f325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 15], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x080f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x090f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 9 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0a0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b0f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 11 - QUAD $0x0c0f225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 15], 12 - QUAD $0x0d0f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e0f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 14 - QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] - QUAD $0x0f0f3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 15], 15 + QUAD $0x0e0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 14 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x0f0f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 15 LONG $0x387de3c4; WORD $0x01c1 // vinserti128 ymm0, ymm0, xmm1, 1 QUAD $0x0003c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0003e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm0 - LONG $0x7cb60f42; WORD $0x1002 // movzx edi, byte [rdx + r8 + 16] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x011032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 1 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x021032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 2 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x031032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 3 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x041032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 4 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x051032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 5 - QUAD $0x06102a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 16], 6 - WORD $0x894d; BYTE $0xec // mov r12, r13 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x071032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 7 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x081032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 8 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x091032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 9 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b1032442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 16], 11 - QUAD $0x0c1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 12 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x011017442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 16], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x021007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 2 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x03100f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 16], 3 + QUAD $0x041007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 4 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x051007442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 16], 5 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0d1002442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 16], 13 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x0e1002442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 16], 14 - QUAD $0x0f100a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 16], 15 - LONG $0x1a7cb60f; BYTE $0x10 // movzx edi, byte [rdx + rbx + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x01101a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 16], 1 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x02100a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 16], 2 - QUAD $0x0310124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 16], 3 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0410024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 4 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0510024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 5 - QUAD $0x06100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 6 - QUAD $0x0710324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 16], 7 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x0810324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 16], 8 + QUAD $0x061007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 6 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x071027442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 16], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 8 + QUAD $0x09101f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 16], 9 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0a1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 10 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x0b103f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 16], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 12 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0d1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 13 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x0e1017442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 16], 14 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0910024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 16], 9 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0a102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d103a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 16], 13 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0e10324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 16], 14 - QUAD $0x0f103a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 16], 15 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - LONG $0x3a7cb60f; BYTE $0x11 // movzx edi, byte [rdx + rdi + 17] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x01113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 1 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x02110a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 17], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x03113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 3 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x04113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 4 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - QUAD $0x051112542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 17], 5 - QUAD $0x061122542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 17], 6 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x071122542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 17], 7 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x08113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 9 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x0a111a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 17], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 11 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0c113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 12 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x0d111a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 17], 13 - QUAD $0x0e1102542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 17], 14 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0f113a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 17], 15 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - LONG $0x3a7cb60f; BYTE $0x11 // movzx edi, byte [rdx + rdi + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x01113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 1 - QUAD $0x02110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 2 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x03113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 4 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x05113a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 17], 5 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x06113a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 17], 6 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0711025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 17], 7 - QUAD $0x0811325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 8 - QUAD $0x0911025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 9 - QUAD $0x0a112a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 17], 10 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x0b110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 11 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0c11325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 17], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 13 - QUAD $0x0e11325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 17], 14 + QUAD $0x0f1007442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 16], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0110074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0210074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0310074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + QUAD $0x05101f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 16], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0610074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0710074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0810074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 8 + QUAD $0x0910374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 9 + QUAD $0x0a102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 10 + QUAD $0x0000014024b48b4c // mov r14, qword [rsp + 320] + QUAD $0x0b10374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 16], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 13 + QUAD $0x0e10374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 16], 14 + QUAD $0x0f100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 15 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x110f // movzx eax, byte [rdi + r9 + 17] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 1 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x02111f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 17], 2 + QUAD $0x03110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 3 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x04110f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 17], 4 + QUAD $0x051107542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 17], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x061107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 6 + QUAD $0x071127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 7 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x081117542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 17], 8 + QUAD $0x09111f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 17], 9 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0a1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 10 + QUAD $0x0b113f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 17], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1107542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 17], 12 + QUAD $0x000000f024a48b4c // mov r12, qword [rsp + 240] + QUAD $0x0d1127542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 17], 13 + QUAD $0x0e1117542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 17], 14 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x0f112f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 17], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x11 // movzx eax, byte [rdi + rax + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0111075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0211075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 2 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0311375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0411075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0511075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0611075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 6 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0711175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0811075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0911075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + QUAD $0x0b11375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 11 + QUAD $0x000000b824b48b4c // mov r14, qword [rsp + 184] + QUAD $0x0c11375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 17], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0003a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1102442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rax + 17], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f1107442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rax + 17], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00038024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm0 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x12 // movzx edi, byte [rdx + rax + 18] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x011202442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 18], 1 - QUAD $0x02120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 2 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x03120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 3 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x04122a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 18], 4 - QUAD $0x051212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 5 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - QUAD $0x06120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 6 - QUAD $0x071222442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 18], 7 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x08120a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 18], 8 - LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] - QUAD $0x091212442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 18], 9 - QUAD $0x0a121a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 18], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 11 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0c123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 12 - QUAD $0x0d121a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 18], 13 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0e123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 14 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0f123a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 18], 15 - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x121a // movzx edi, byte [rdx + r11 + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x01123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 1 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x0212324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 18], 2 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x0312224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 18], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 4 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x05123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 5 - QUAD $0x06123a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 18], 6 - QUAD $0x0712024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x08123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x09123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 9 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0a123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 10 - QUAD $0x0b120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 11 - QUAD $0x0c12324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 18], 12 - QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] - QUAD $0x0d120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 14 - QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] - QUAD $0x0f12024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 18], 15 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - LONG $0x3a7cb60f; BYTE $0x13 // movzx edi, byte [rdx + rdi + 19] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 1 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x021302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x03133a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 19], 3 - QUAD $0x04132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 4 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x051302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x061302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 6 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x071302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 7 - QUAD $0x08130a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 19], 8 - QUAD $0x091312542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 19], 9 - QUAD $0x0a131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 10 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0b131a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 19], 11 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0c132a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 19], 12 + LONG $0x44b60f42; WORD $0x120f // movzx eax, byte [rdi + r9 + 18] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x011207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 1 + QUAD $0x02121f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 18], 2 + QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] + QUAD $0x03123f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 18], 3 + QUAD $0x04120f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 18], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 5 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0d1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 14 + QUAD $0x061207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x071207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 7 + QUAD $0x081217442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 18], 8 + QUAD $0x09121f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 18], 9 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0a1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 11 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0f1302542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 19], 15 - LONG $0x7cb60f42; WORD $0x131a // movzx edi, byte [rdx + r11 + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x01130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 1 - QUAD $0x0213325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 19], 2 - QUAD $0x0313225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 19], 3 + QUAD $0x0c1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 12 + QUAD $0x0d1227442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 18], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e1207442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 18], 14 + QUAD $0x0f122f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 18], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + QUAD $0x0112274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 1 + QUAD $0x0212074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 2 + QUAD $0x0312374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0412074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0512074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 5 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0612374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 18], 6 + QUAD $0x0712174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 7 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x08120f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 18], 8 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x09122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 9 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + QUAD $0x0a12074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 18], 10 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x0b121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 11 + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + QUAD $0x0c12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 12 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0d121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 13 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0e12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 14 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0f12174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x011307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x021307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 2 + QUAD $0x03133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 3 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0413025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 4 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0513025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 5 - QUAD $0x06133a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 19], 6 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0713025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 7 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x08130a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 19], 8 + QUAD $0x041307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 5 + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x06133f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 19], 6 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x071317542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 19], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 9 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0a1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 12 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0d1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 14 QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0913025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 9 - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x0a13125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 19], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b13025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 19], 11 - QUAD $0x0c13325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 12 - QUAD $0x0d130a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 19], 13 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x0e130a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 19], 14 - QUAD $0x0f13025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 19], 15 + QUAD $0x0f1307542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 19], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0113275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 19], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0213075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0313075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0413075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + QUAD $0x0613375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 19], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0713075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 7 + QUAD $0x08130f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 19], 8 + QUAD $0x09132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 9 + QUAD $0x0a13075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 10 + QUAD $0x0b131f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 19], 11 + QUAD $0x0c130f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 19], 12 + QUAD $0x0d131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 13 + QUAD $0x0e13375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 14 + QUAD $0x0f13175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 19], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00034024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x00036024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm0 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x14 // movzx edi, byte [rdx + rax + 20] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x011432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 1 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x02141a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 20], 2 + QUAD $0x000000f8248c8b4c // mov r9, qword [rsp + 248] + LONG $0x44b60f42; WORD $0x140f // movzx eax, byte [rdi + r9 + 20] + LONG $0xc06ef9c5 // vmovd xmm0, eax QUAD $0x000000c824a48b4c // mov r12, qword [rsp + 200] - QUAD $0x031422442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 20], 3 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x041432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 4 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - QUAD $0x051402442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 20], 5 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x06143a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 20], 6 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x071432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 7 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x081432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 8 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x091432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 9 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0a1432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 10 - QUAD $0x0b141a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 20], 11 - QUAD $0x0c142a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 20], 12 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x0d1432442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 20], 13 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0e1432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 14 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0f1432442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 20], 15 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - LONG $0x3a7cb60f; BYTE $0x14 // movzx edi, byte [rdx + rdi + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x01143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x02143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 2 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x03141a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 20], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 4 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x05143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x06143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x07143a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 20], 7 - QUAD $0x08140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 8 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x09140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 9 - QUAD $0x0a14124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 11 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0c140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d140a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 20], 13 - QUAD $0x0e140a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 20], 14 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x0f140a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 20], 15 - LONG $0x027cb60f; BYTE $0x15 // movzx edi, byte [rdx + rax + 21] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x011502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 1 - QUAD $0x02151a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 21], 2 - QUAD $0x031522542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 21], 3 - WORD $0x894d; BYTE $0xe5 // mov r13, r12 + QUAD $0x011427442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 20], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x021407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 2 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + QUAD $0x03141f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 20], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x041407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 4 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x041502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 4 - QUAD $0x051502542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 21], 5 - QUAD $0x06153a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 21], 6 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x071502542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 21], 7 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x08153a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 21], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 9 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0a1522542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 21], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 11 + QUAD $0x051407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 5 + QUAD $0x06143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 6 + QUAD $0x071417442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 20], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 12 - QUAD $0x0d1532542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 21], 13 + QUAD $0x091407442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 20], 9 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x0a1437442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 20], 10 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0b1417442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 20], 11 + QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] + QUAD $0x0c143f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 20], 12 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x0d140f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 20], 13 + QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] + QUAD $0x0e141f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 20], 14 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + QUAD $0x0f1407442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 20], 15 + QUAD $0x000000e024ac8b4c // mov r13, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x142f // movzx eax, byte [rdi + r13 + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x0114374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0214074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0414074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0514074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0614074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0714074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0814074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0914074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 14 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e1502542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 21], 14 - QUAD $0x0f1532542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 21], 15 - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x151a // movzx edi, byte [rdx + r11 + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] - QUAD $0x0115325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 21], 1 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x0215125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 2 - QUAD $0x03151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 3 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x04151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 4 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x05150a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 21], 5 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x0615325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 6 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0715325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 7 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x0815325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 8 - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0915325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 9 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0a153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 14 + QUAD $0x0f14074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 15 + LONG $0x44b60f42; WORD $0x150f // movzx eax, byte [rdi + r9 + 21] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 1 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x021517542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 21], 2 + QUAD $0x03151f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 21], 3 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x041527542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 21], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x061507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x071507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091507542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 21], 9 + QUAD $0x0a1537542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 21], 10 + QUAD $0x0b1517542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 21], 11 + QUAD $0x0c153f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 21], 12 + QUAD $0x0d150f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 21], 13 + QUAD $0x0e151f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 21], 14 + QUAD $0x0f1507542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 21], 15 + LONG $0x44b60f42; WORD $0x152f // movzx eax, byte [rdi + r13 + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0115375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0315075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 3 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x04153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 4 + QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] + QUAD $0x05151f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 21], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x07152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0915075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 9 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x0a150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d15075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0e15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00030024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm0 - QUAD $0x0f150a442061a3c4 // vpinsrb xmm0, xmm3, byte [rdx + r9 + 21], 15 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x0f151f442061a3c4 // vpinsrb xmm0, xmm3, byte [rdi + r11 + 21], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00032024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm0 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - LONG $0x3a7cb60f; BYTE $0x16 // movzx edi, byte [rdx + rdi + 22] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x01163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 1 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x02163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 2 - QUAD $0x03162a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 22], 3 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x04160a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 22], 4 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x05163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 5 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x06163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 6 - QUAD $0x071602442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 22], 7 - QUAD $0x08163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 9 - QUAD $0x0a1622442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 22], 10 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0b163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 11 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0c163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 12 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0d163a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 22], 13 - QUAD $0x0e1602442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 22], 14 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x0f163a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 22], 15 - LONG $0x7cb60f42; WORD $0x161a // movzx edi, byte [rdx + r11 + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0116324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 22], 1 - QUAD $0x0216124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 22], 2 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x011607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 1 + QUAD $0x021617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 2 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x031607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 3 + QUAD $0x041627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 4 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x051617442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rdx + 22], 5 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x061617442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 22], 6 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0316024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 3 - QUAD $0x04161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 4 - QUAD $0x05160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 5 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x0616224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 22], 6 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x07161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 7 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x0816124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 22], 8 - QUAD $0x0916324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 10 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x0b16024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 22], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 12 + QUAD $0x071607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 8 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x091627442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 22], 9 + QUAD $0x0a1637442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 22], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 12 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0d1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e1607442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 22], 14 + QUAD $0x0f1607442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 22], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0116074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 1 + QUAD $0x02160f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 22], 2 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0316074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 3 + QUAD $0x04163f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 22], 4 + QUAD $0x05161f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 22], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0616074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 6 + QUAD $0x07162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 10 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 13 + QUAD $0x0b16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 11 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x0c160f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 22], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 13 + QUAD $0x0e16374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 22], 14 + QUAD $0x0f161f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 22], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x01171f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 23], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x021707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 2 + QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] + QUAD $0x03173f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 23], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x041707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 4 + QUAD $0x051717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 23], 5 + QUAD $0x061717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 6 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x07172f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 23], 7 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f16024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 22], 15 + QUAD $0x081707542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 23], 8 + QUAD $0x091727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 9 + QUAD $0x0a1737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 23], 10 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x0b171f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 23], 11 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x0c170f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 23], 12 + QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + QUAD $0x0d1717542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 23], 13 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0e1737542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 23], 14 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x0f1727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 23], 15 QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x17 // movzx edi, byte [rdx + rax + 23] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x011702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 1 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x021702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 2 - WORD $0x894d; BYTE $0xee // mov r14, r13 - QUAD $0x03172a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 23], 3 - QUAD $0x04170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 4 - QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] - QUAD $0x05172a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 23], 5 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x061732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 23], 6 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x07170a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 23], 7 + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x0117375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0217075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 2 + QUAD $0x0317075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x0417075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 4 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x081702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 8 + QUAD $0x0517075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0617075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0717075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0817075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091702542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 23], 9 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x0a170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0b170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 11 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0c170a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 23], 12 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x0d171a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 23], 13 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0e173a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 23], 14 - QUAD $0x0f173a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 23], 15 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - LONG $0x3a7cb60f; BYTE $0x17 // movzx edi, byte [rdx + rdi + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x01173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 1 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x02173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 2 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x03173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x04173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 4 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x05173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 5 - QUAD $0x0617225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 23], 6 - QUAD $0x07171a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 23], 7 - QUAD $0x0817125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 23], 8 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x09171a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 23], 9 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0a173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 10 - QUAD $0x0b17025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 23], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 12 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x0d173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 15 + QUAD $0x0a17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 11 + QUAD $0x0c170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 12 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0d17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 14 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 15 LONG $0x387563c4; WORD $0x01d0 // vinserti128 ymm10, ymm1, xmm0, 1 LONG $0x386563c4; WORD $0x01da // vinserti128 ymm11, ymm3, xmm2, 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - LONG $0x3a7cb60f; BYTE $0x18 // movzx edi, byte [rdx + rdi + 24] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x01183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 1 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x02183a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 24], 2 - QUAD $0x031832442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 24], 3 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x04183a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rdi + 24], 4 - QUAD $0x05182a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 24], 5 - QUAD $0x061832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 6 - QUAD $0x07180a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 24], 7 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x081832442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 24], 8 - QUAD $0x091802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 10 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0b1822442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 24], 11 - QUAD $0x0c180a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 24], 12 - QUAD $0x0d181a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 24], 13 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x01181f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 24], 1 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x02180f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 24], 2 + QUAD $0x03183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 3 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x041807442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 24], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x061807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 6 + QUAD $0x07182f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 24], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 8 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x09183f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 24], 9 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0a1807442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 24], 10 + QUAD $0x0b181f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 24], 11 + QUAD $0x0c180f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 24], 12 + QUAD $0x0d1817442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 24], 13 + QUAD $0x0e1837442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 24], 14 + QUAD $0x0f1827442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 24], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0118374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0218074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 2 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0318174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 3 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x04181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0518074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0618074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0718074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 7 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x08180f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 24], 8 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0918074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 11 + QUAD $0x000000b8249c8b4c // mov r11, qword [rsp + 184] + QUAD $0x0c181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 12 + QUAD $0x0d18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 13 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0e18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 14 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e1802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 14 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0f1802442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 24], 15 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x1832 // movzx edi, byte [rdx + r14 + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e8248c8b4c // mov r9, qword [rsp + 232] - QUAD $0x01180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 1 + QUAD $0x0f18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c824ac8b4c // mov r13, qword [rsp + 200] + QUAD $0x01192f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 25], 1 + QUAD $0x02190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 2 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x031927542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 25], 3 + QUAD $0x041907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 4 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x051907542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 25], 5 + QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] + QUAD $0x061937542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 25], 6 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x07190f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 25], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 8 + QUAD $0x09193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 9 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0218024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 2 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0318024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 3 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x04181a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 24], 4 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0518024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 5 + QUAD $0x0a1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 11 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0c1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 12 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x0d1937542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 25], 13 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0618024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 6 + QUAD $0x0e1907542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 25], 14 + QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] + QUAD $0x0f193f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 25], 15 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + QUAD $0x0319175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 25], 3 + QUAD $0x04191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0519075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 5 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0718024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 7 - QUAD $0x0818124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 8 - WORD $0x8949; BYTE $0xda // mov r10, rbx - QUAD $0x09181a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 24], 9 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0a182a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 24], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b180a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 24], 11 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0c18324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 24], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d18024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 13 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0e181a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 24], 14 + QUAD $0x0619075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f18024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 15 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - LONG $0x027cb60f; BYTE $0x19 // movzx edi, byte [rdx + rax + 25] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x011902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 1 - QUAD $0x02193a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 25], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x041902542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 25], 4 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x05193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 5 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - QUAD $0x06193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 6 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x07193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 7 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x08193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 8 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x09193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 9 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x0a193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 10 - QUAD $0x0b1922542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 25], 11 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0c193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 12 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0d193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 13 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0e193a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 25], 14 - QUAD $0x000000a824bc8b4c // mov r15, qword [rsp + 168] - QUAD $0x0f193a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 25], 15 - LONG $0x7cb60f42; WORD $0x1932 // movzx edi, byte [rdx + r14 + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x01190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 1 - QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] - QUAD $0x02190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 2 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x03193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 3 - QUAD $0x04191a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 25], 4 - QUAD $0x0519025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 25], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x06193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x07193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x08193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 8 - QUAD $0x0919125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 25], 9 - QUAD $0x0a192a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 25], 10 - QUAD $0x0b190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 11 - QUAD $0x0c19325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 12 - QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] - QUAD $0x0d192a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 25], 13 - QUAD $0x0e191a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 25], 14 + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x08190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 8 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x09190f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 25], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 11 + QUAD $0x0c191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 13 + QUAD $0x0e19175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 25], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00024024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm0 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x0f190a442061e3c4 // vpinsrb xmm0, xmm3, byte [rdx + rcx + 25], 15 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0f1917442061e3c4 // vpinsrb xmm0, xmm3, byte [rdi + rdx + 25], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x00026024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm0 - QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] - LONG $0x7cb60f42; WORD $0x1a1a // movzx edi, byte [rdx + r11 + 26] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x011a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 1 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x021a02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 26], 2 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x031a0a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rcx + 26], 3 - QUAD $0x041a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 4 - QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] - QUAD $0x051a32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 26], 5 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - QUAD $0x061a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 6 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x071a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 7 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x081a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 9 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0a1a22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 26], 10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0b1a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 11 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c1a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 12 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0d1a02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 26], 13 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - QUAD $0x0e1a32442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r14 + 26], 14 - QUAD $0x0f1a3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 26], 15 QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x1a // movzx edi, byte [rdx + rax + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + LONG $0x0744b60f; BYTE $0x1a // movzx eax, byte [rdi + rax + 26] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011a2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 26], 1 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x021a1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 26], 2 + QUAD $0x031a27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 26], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x041a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 4 + QUAD $0x051a07442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r8 + 26], 5 + QUAD $0x061a37442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rsi + 26], 6 + QUAD $0x071a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 7 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x081a1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 26], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 9 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x0a1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0b1a07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 26], 11 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x0c1a0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 26], 12 + QUAD $0x0d1a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 13 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0e1a37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 26], 14 + QUAD $0x0f1a3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 26], 15 + QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + LONG $0x44b60f42; WORD $0x1a17 // movzx eax, byte [rdi + r10 + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x011a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x021a074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 26], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x031a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 3 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x041a2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 26], 4 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x051a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x061a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x081a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 8 + QUAD $0x091a0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 26], 9 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0a1a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 13 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0e1a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 14 + QUAD $0x0f1a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 15 + QUAD $0x000000f824948b48 // mov rdx, qword [rsp + 248] + LONG $0x1744b60f; BYTE $0x1b // movzx eax, byte [rdi + rdx + 27] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x011b0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 27], 1 + QUAD $0x021b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 2 QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x011a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 1 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x021a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 2 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x031a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 3 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x041a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 4 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x051a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 5 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x061a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 6 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x071a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 7 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x081a3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 26], 8 - QUAD $0x091a124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 26], 9 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0a1a1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 26], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 12 - QUAD $0x0d1a2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 26], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0e1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f1a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 15 - LONG $0x7cb60f42; WORD $0x1b1a // movzx edi, byte [rdx + r11 + 27] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x011b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 27], 1 - QUAD $0x021b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 27], 2 - QUAD $0x031b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 3 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x041b02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 27], 4 - QUAD $0x051b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 5 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - QUAD $0x061b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 27], 6 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x071b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 7 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x081b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 8 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x091b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 9 - QUAD $0x0a1b22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 27], 10 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0b1b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 27], 11 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0c1b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 12 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x0d1b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 13 - QUAD $0x0e1b32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 27], 14 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x0f1b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 27], 15 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - LONG $0x0a7cb60f; BYTE $0x1b // movzx edi, byte [rdx + rcx + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x011b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 1 - QUAD $0x021b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 2 + QUAD $0x031b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x041b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 4 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x051b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x061b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 6 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x031b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 3 - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - QUAD $0x041b325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 27], 4 + QUAD $0x071b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 7 + QUAD $0x081b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 27], 9 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x0a1b1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 27], 10 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x0b1b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 27], 11 + QUAD $0x0c1b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 12 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x0d1b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 27], 13 + QUAD $0x0e1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 14 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x0f1b37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 27], 15 + LONG $0x44b60f42; WORD $0x1b17 // movzx eax, byte [rdi + r10 + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + QUAD $0x011b175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 27], 1 + QUAD $0x021b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x031b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 3 + QUAD $0x041b2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 27], 4 + QUAD $0x051b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 7 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + QUAD $0x081b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 8 LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x051b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 5 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x061b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 6 - QUAD $0x071b0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 27], 7 - QUAD $0x081b3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 27], 8 - QUAD $0x091b125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 27], 9 - QUAD $0x0a1b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 10 + QUAD $0x091b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 9 + QUAD $0x0a1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 11 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 11 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 12 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x0d1b0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 27], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 14 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 15 + QUAD $0x0d1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 13 + QUAD $0x0e1b275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 27], 14 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00028024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm0 LONG $0x3865e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm3, xmm2, 1 QUAD $0x0002a024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm0 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - LONG $0x7cb60f42; WORD $0x1c12 // movzx edi, byte [rdx + r10 + 28] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 28], 1 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x021c3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 28], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 28], 3 - QUAD $0x041c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 4 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - QUAD $0x051c22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 28], 5 - QUAD $0x061c32442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rsi + 28], 6 + LONG $0x1744b60f; BYTE $0x1c // movzx eax, byte [rdi + rdx + 28] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x011c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 1 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x071c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 28], 7 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x081c0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 28], 8 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x091c02442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r8 + 28], 9 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x0a1c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 28], 10 - QUAD $0x0b1c2a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r13 + 28], 11 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0c1c1a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r11 + 28], 12 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0d1c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 28], 13 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x0e1c1a442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rbx + 28], 14 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0f1c02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 28], 15 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - LONG $0x027cb60f; BYTE $0x1c // movzx edi, byte [rdx + rax + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x011c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 1 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x021c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 2 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x031c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 3 - QUAD $0x041c324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 28], 4 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x051c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 5 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x061c324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 28], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x071c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 7 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x081c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 8 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x091c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 9 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0a1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 10 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0b1c2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 28], 11 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 12 - QUAD $0x0d1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 13 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0e1c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 14 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x0f1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 15 - LONG $0x7cb60f42; WORD $0x1d12 // movzx edi, byte [rdx + r10 + 29] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x011d12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 29], 1 - QUAD $0x021d3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 29], 2 - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x031d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 3 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x041d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 4 - QUAD $0x051d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 5 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - QUAD $0x061d3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 29], 6 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x071d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 7 - QUAD $0x081d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 8 - QUAD $0x091d02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 29], 9 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x0a1d22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 29], 10 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0b1d0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 29], 11 - QUAD $0x0c1d1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 29], 12 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0d1d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 13 - QUAD $0x0e1d1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 29], 14 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x0f1d3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 29], 15 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - LONG $0x7cb60f42; WORD $0x1d02 // movzx edi, byte [rdx + r8 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x011d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 1 - QUAD $0x021d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 2 - QUAD $0x031d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 3 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x041d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 4 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x051d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 5 - QUAD $0x061d325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 29], 6 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x071d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 7 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x081d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 8 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x091d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 9 + QUAD $0x021c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 2 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x031c0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 28], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x041c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 4 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x051c3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 28], 5 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x061c27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 28], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x071c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091c07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 28], 9 + QUAD $0x0a1c1f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r11 + 28], 10 + QUAD $0x0b1c1f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rbx + 28], 11 + QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] + QUAD $0x0c1c2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 28], 12 + QUAD $0x0d1c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 13 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x0e1c0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 28], 14 + QUAD $0x0f1c37442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r14 + 28], 15 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + LONG $0x1744b60f; BYTE $0x1c // movzx eax, byte [rdi + rdx + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 2 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x031c1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 28], 3 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x041c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 5 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x061c1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 28], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 7 + QUAD $0x081c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 8 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x091c374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 28], 9 + QUAD $0x0a1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 10 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x0b1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 11 + QUAD $0x000000b824848b4c // mov r8, qword [rsp + 184] + QUAD $0x0c1c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 13 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a1d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 10 - QUAD $0x0b1d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 11 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0c1d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d1d025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 29], 13 - QUAD $0x0e1d0a642061e3c4 // vpinsrb xmm4, xmm3, byte [rdx + rcx + 29], 14 + QUAD $0x0e1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 14 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x1d // movzx eax, byte [rdi + rax + 29] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x011d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x021d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 2 + QUAD $0x031d0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 29], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x041d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 4 + QUAD $0x051d3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 29], 5 + QUAD $0x061d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x071d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 7 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x091d07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 29], 9 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x0a1d0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 29], 10 + QUAD $0x000000b024a48b4c // mov r12, qword [rsp + 176] + QUAD $0x0b1d27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 29], 11 + QUAD $0x0c1d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 12 + QUAD $0x000000f024ac8b4c // mov r13, qword [rsp + 240] + QUAD $0x0d1d2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 29], 13 + QUAD $0x0e1d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 14 + QUAD $0x00000108248c8b4c // mov r9, qword [rsp + 264] + QUAD $0x0f1d0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 29], 15 + LONG $0x1744b60f; BYTE $0x1d // movzx eax, byte [rdi + rdx + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0000010024948b48 // mov rdx, qword [rsp + 256] + QUAD $0x011d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 29], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x021d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 2 + QUAD $0x031d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 3 + QUAD $0x041d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 + QUAD $0x061d1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 29], 6 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x071d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x081d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 8 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + QUAD $0x091d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 29], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 10 + QUAD $0x0b1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 11 + QUAD $0x0c1d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 29], 12 + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0d1d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 29], 13 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0e1d07642061a3c4 // vpinsrb xmm4, xmm3, byte [rdi + r8 + 29], 14 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x0002c024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm0 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1d02442059e3c4 // vpinsrb xmm0, xmm4, byte [rdx + rax + 29], 15 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f1d07442059e3c4 // vpinsrb xmm0, xmm4, byte [rdi + rax + 29], 15 LONG $0x387de3c4; WORD $0x01c2 // vinserti128 ymm0, ymm0, xmm2, 1 QUAD $0x0002e024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm0 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x0a7cb60f; BYTE $0x1e // movzx edi, byte [rdx + rcx + 30] - LONG $0xc76ef9c5 // vmovd xmm0, edi - QUAD $0x011e12442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r10 + 30], 1 - LONG $0x0a7cb60f; BYTE $0x1f // movzx edi, byte [rdx + rcx + 31] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011f124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 31], 1 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x021e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 2 - QUAD $0x021f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 2 - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x031e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 3 - QUAD $0x031f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x041e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 4 - QUAD $0x041f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 4 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - QUAD $0x051e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 5 - QUAD $0x051f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 5 - QUAD $0x061e3a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r15 + 30], 6 - QUAD $0x061f3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 31], 6 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + LONG $0x1f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rbx + 30] + LONG $0xc06ef9c5 // vmovd xmm0, eax + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x011e17442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r10 + 30], 1 + LONG $0x1f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rbx + 31] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011f174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 31], 1 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x071e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 7 - QUAD $0x071f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 7 + QUAD $0x021e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 2 + QUAD $0x021f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 2 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x031e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 3 + QUAD $0x031f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 3 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x041e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 4 + QUAD $0x041f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 4 + QUAD $0x051e3f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r15 + 30], 5 + QUAD $0x051f3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 31], 5 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x061e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 6 + QUAD $0x061f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x071e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 7 + QUAD $0x071f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 7 QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x081e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 8 - QUAD $0x081f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 8 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x091e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 9 - QUAD $0x091f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 9 - QUAD $0x0a1e22442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r12 + 30], 10 - QUAD $0x0a1f224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 31], 10 - QUAD $0x0b1e0a442079a3c4 // vpinsrb xmm0, xmm0, byte [rdx + r9 + 30], 11 - QUAD $0x0b1f0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 31], 11 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x081e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 8 + QUAD $0x081f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 8 LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0c1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 12 - QUAD $0x0c1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 12 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0d1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 13 - QUAD $0x0d1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0e1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 14 - QUAD $0x0e1f024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 31], 14 + QUAD $0x091e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 9 + QUAD $0x091f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 9 + QUAD $0x0a1e0f442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rcx + 30], 10 + QUAD $0x0a1f0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 31], 10 + QUAD $0x0b1e27442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r12 + 30], 11 + QUAD $0x0b1f274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 31], 11 QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0f1e02442079e3c4 // vpinsrb xmm0, xmm0, byte [rdx + rax + 30], 15 - QUAD $0x0f1f02542071e3c4 // vpinsrb xmm2, xmm1, byte [rdx + rax + 31], 15 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - LONG $0x44b60f42; WORD $0x1e02 // movzx eax, byte [rdx + r8 + 30] + QUAD $0x0c1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 12 + QUAD $0x0c1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 12 + QUAD $0x0d1e2f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r13 + 30], 13 + QUAD $0x0d1f2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 31], 13 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0e1e07442079e3c4 // vpinsrb xmm0, xmm0, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 31], 14 + QUAD $0x0f1e0f442079a3c4 // vpinsrb xmm0, xmm0, byte [rdi + r9 + 30], 15 + QUAD $0x0f1f0f542071a3c4 // vpinsrb xmm2, xmm1, byte [rdi + r9 + 31], 15 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xc86ef9c5 // vmovd xmm1, eax - QUAD $0x011e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 30], 1 - LONG $0x44b60f42; WORD $0x1f02 // movzx eax, byte [rdx + r8 + 31] + QUAD $0x011e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xf86ef9c5 // vmovd xmm7, eax - QUAD $0x011f1a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 31], 1 - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] - QUAD $0x021e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 30], 2 - QUAD $0x021f127c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r10 + 31], 2 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x031e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 3 - QUAD $0x031f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 3 - QUAD $0x041e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 30], 4 - QUAD $0x041f327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 31], 4 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x051e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 5 - QUAD $0x051f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 5 - QUAD $0x061e324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 30], 6 - QUAD $0x061f327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 31], 6 + QUAD $0x011f177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 31], 1 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x021e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 2 + QUAD $0x021f177c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r10 + 31], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 4 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 5 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x071e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 7 - QUAD $0x071f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 7 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 8 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x091e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 9 - QUAD $0x091f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 9 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 11 - QUAD $0x0b1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 11 - QUAD $0x0c1e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 30], 12 - QUAD $0x0c1f2a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 31], 12 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0d1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 13 - QUAD $0x0d1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 14 + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 6 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0f1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 15 - QUAD $0x0f1f027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 31], 15 + QUAD $0x071e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 7 + QUAD $0x071f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 8 + QUAD $0x091e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 30], 9 + QUAD $0x091f1f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r11 + 31], 9 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0a1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 10 + QUAD $0x0a1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 10 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 11 + WORD $0x894c; BYTE $0xf0 // mov rax, r14 + QUAD $0x0c1e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 30], 12 + QUAD $0x0c1f377c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r14 + 31], 12 + QUAD $0x0d1e374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 30], 13 + QUAD $0x0d1f377c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rsi + 31], 13 + QUAD $0x0e1e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 30], 14 + QUAD $0x0e1f077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 31], 14 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f077c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rax + 31], 15 LONG $0x3875e3c4; WORD $0x01c0 // vinserti128 ymm0, ymm1, xmm0, 1 QUAD $0x00014024847ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm0 LONG $0x3845e3c4; WORD $0x01c2 // vinserti128 ymm0, ymm7, xmm2, 1 @@ -66437,20 +68109,20 @@ LBB11_86: LONG $0xdf45c1c4; BYTE $0xfd // vpandn ymm7, ymm7, ymm13 QUAD $0x0001e0249c6ffdc5; BYTE $0x00 // vmovdqa ymm3, yword [rsp + 480] LONG $0xe26465c5 // vpcmpgtb ymm12, ymm3, ymm2 - LONG $0x4d6f7dc5; BYTE $0x40 // vmovdqa ymm9, yword 64[rbp] /* [rip + .LCPI11_2] */ - LONG $0xdf1d41c4; BYTE $0xe1 // vpandn ymm12, ymm12, ymm9 + LONG $0x456f7dc5; BYTE $0x40 // vmovdqa ymm8, yword 64[rbp] /* [rip + .LCPI11_2] */ + LONG $0xdf1d41c4; BYTE $0xe0 // vpandn ymm12, ymm12, ymm8 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0xe2640dc5 // vpcmpgtb ymm12, ymm14, ymm2 - LONG $0x656ffdc5; BYTE $0x60 // vmovdqa ymm4, yword 96[rbp] /* [rip + .LCPI11_3] */ - LONG $0xe4df1dc5 // vpandn ymm12, ymm12, ymm4 + LONG $0x4d6f7dc5; BYTE $0x60 // vmovdqa ymm9, yword 96[rbp] /* [rip + .LCPI11_3] */ + LONG $0xdf1d41c4; BYTE $0xe1 // vpandn ymm12, ymm12, ymm9 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 LONG $0x761d41c4; BYTE $0xe4 // vpcmpeqd ymm12, ymm12, ymm12 LONG $0xf87dc1c4; BYTE $0xc4 // vpsubb ymm0, ymm0, ymm12 - LONG $0x763d41c4; BYTE $0xc0 // vpcmpeqd ymm8, ymm8, ymm8 + LONG $0xf676cdc5 // vpcmpeqd ymm6, ymm6, ymm6 LONG $0xc7ebfdc5 // vpor ymm0, ymm0, ymm7 LONG $0xfa6485c5 // vpcmpgtb ymm7, ymm15, ymm2 - QUAD $0x00000080b56ffdc5 // vmovdqa ymm6, yword 128[rbp] /* [rip + .LCPI11_4] */ - LONG $0xfedfc5c5 // vpandn ymm7, ymm7, ymm6 + QUAD $0x00000080a56ffdc5 // vmovdqa ymm4, yword 128[rbp] /* [rip + .LCPI11_4] */ + LONG $0xfcdfc5c5 // vpandn ymm7, ymm7, ymm4 QUAD $0x0001c024a46f7dc5; BYTE $0x00 // vmovdqa ymm12, yword [rsp + 448] LONG $0xe2641dc5 // vpcmpgtb ymm12, ymm12, ymm2 QUAD $0x000000a09d6ffdc5 // vmovdqa ymm3, yword 160[rbp] /* [rip + .LCPI11_5] */ @@ -66473,17 +68145,17 @@ LBB11_86: LONG $0xdf1d41c4; BYTE $0xe5 // vpandn ymm12, ymm12, ymm13 QUAD $0x00044024b46f7dc5; BYTE $0x00 // vmovdqa ymm14, yword [rsp + 1088] LONG $0xfa640dc5 // vpcmpgtb ymm15, ymm14, ymm2 - LONG $0xdf0541c4; BYTE $0xf9 // vpandn ymm15, ymm15, ymm9 + LONG $0xdf0541c4; BYTE $0xf8 // vpandn ymm15, ymm15, ymm8 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 QUAD $0x00040024b46f7dc5; BYTE $0x00 // vmovdqa ymm14, yword [rsp + 1024] LONG $0xfa640dc5 // vpcmpgtb ymm15, ymm14, ymm2 - LONG $0xfcdf05c5 // vpandn ymm15, ymm15, ymm4 + LONG $0xdf0541c4; BYTE $0xf9 // vpandn ymm15, ymm15, ymm9 LONG $0xeb1d41c4; BYTE $0xe7 // vpor ymm12, ymm12, ymm15 - LONG $0xf845c1c4; BYTE $0xf8 // vpsubb ymm7, ymm7, ymm8 + LONG $0xfef8c5c5 // vpsubb ymm7, ymm7, ymm6 LONG $0xffeb9dc5 // vpor ymm7, ymm12, ymm7 QUAD $0x00042024a46f7dc5; BYTE $0x00 // vmovdqa ymm12, yword [rsp + 1056] LONG $0xe2641dc5 // vpcmpgtb ymm12, ymm12, ymm2 - LONG $0xe6df1dc5 // vpandn ymm12, ymm12, ymm6 + LONG $0xe4df1dc5 // vpandn ymm12, ymm12, ymm4 QUAD $0x0003c024b46f7dc5; BYTE $0x00 // vmovdqa ymm14, yword [rsp + 960] LONG $0xfa640dc5 // vpcmpgtb ymm15, ymm14, ymm2 LONG $0xfbdf05c5 // vpandn ymm15, ymm15, ymm3 @@ -66504,18 +68176,18 @@ LBB11_86: LONG $0xdf0541c4; BYTE $0xfd // vpandn ymm15, ymm15, ymm13 QUAD $0x00036024b46f7dc5; BYTE $0x00 // vmovdqa ymm14, yword [rsp + 864] LONG $0xf2640dc5 // vpcmpgtb ymm14, ymm14, ymm2 - LONG $0xdf0d41c4; BYTE $0xf1 // vpandn ymm14, ymm14, ymm9 + LONG $0xdf0d41c4; BYTE $0xf0 // vpandn ymm14, ymm14, ymm8 LONG $0xeb0541c4; BYTE $0xf6 // vpor ymm14, ymm15, ymm14 QUAD $0x00030024bc6f7dc5; BYTE $0x00 // vmovdqa ymm15, yword [rsp + 768] LONG $0xfa6405c5 // vpcmpgtb ymm15, ymm15, ymm2 - LONG $0xfcdf05c5 // vpandn ymm15, ymm15, ymm4 + LONG $0xdf0541c4; BYTE $0xf9 // vpandn ymm15, ymm15, ymm9 LONG $0xeb0d41c4; BYTE $0xf7 // vpor ymm14, ymm14, ymm15 - LONG $0xf845c1c4; BYTE $0xf8 // vpsubb ymm7, ymm7, ymm8 + LONG $0x760541c4; BYTE $0xff // vpcmpeqd ymm15, ymm15, ymm15 + LONG $0xf845c1c4; BYTE $0xff // vpsubb ymm7, ymm7, ymm15 LONG $0xffeb8dc5 // vpor ymm7, ymm14, ymm7 QUAD $0x00032024b46f7dc5; BYTE $0x00 // vmovdqa ymm14, yword [rsp + 800] LONG $0xf2640dc5 // vpcmpgtb ymm14, ymm14, ymm2 - LONG $0xfe6f7dc5 // vmovdqa ymm15, ymm6 - LONG $0xf6df0dc5 // vpandn ymm14, ymm14, ymm6 + LONG $0xf4df0dc5 // vpandn ymm14, ymm14, ymm4 LONG $0xd2642dc5 // vpcmpgtb ymm10, ymm10, ymm2 LONG $0xd3df2dc5 // vpandn ymm10, ymm10, ymm3 LONG $0xeb0d41c4; BYTE $0xd2 // vpor ymm10, ymm14, ymm10 @@ -66539,13 +68211,13 @@ LBB11_86: LONG $0xeeebd5c5 // vpor ymm5, ymm5, ymm6 QUAD $0x0002c0248c6ffdc5; BYTE $0x00 // vmovdqa ymm1, yword [rsp + 704] LONG $0xda64f5c5 // vpcmpgtb ymm3, ymm1, ymm2 - LONG $0xdcdfe5c5 // vpandn ymm3, ymm3, ymm4 + LONG $0x5ddfe5c5; BYTE $0x60 // vpandn ymm3, ymm3, yword 96[rbp] /* [rip + .LCPI11_3] */ LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 - QUAD $0x000000e0adf8bdc5 // vpsubb ymm5, ymm8, yword 224[rbp] /* [rip + .LCPI11_7] */ + LONG $0xf83dc1c4; BYTE $0xef // vpsubb ymm5, ymm8, ymm15 LONG $0xdbebd5c5 // vpor ymm3, ymm5, ymm3 QUAD $0x0002e0248c6ffdc5; BYTE $0x00 // vmovdqa ymm1, yword [rsp + 736] LONG $0xe264f5c5 // vpcmpgtb ymm4, ymm1, ymm2 - LONG $0xdf5dc1c4; BYTE $0xe7 // vpandn ymm4, ymm4, ymm15 + QUAD $0x00000080a5dfddc5 // vpandn ymm4, ymm4, yword 128[rbp] /* [rip + .LCPI11_4] */ QUAD $0x000140248c6ffdc5; BYTE $0x00 // vmovdqa ymm1, yword [rsp + 320] LONG $0xca64f5c5 // vpcmpgtb ymm1, ymm1, ymm2 QUAD $0x000000a08ddff5c5 // vpandn ymm1, ymm1, yword 160[rbp] /* [rip + .LCPI11_5] */ @@ -66573,1988 +68245,1989 @@ LBB11_86: LONG $0x7f7ec1c4; WORD $0x8f64; BYTE $0x20 // vmovdqu yword [r15 + 4*rcx + 32], ymm4 LONG $0x7f7ec1c4; WORD $0x8f0c // vmovdqu yword [r15 + 4*rcx], ymm1 LONG $0x20c18348 // add rcx, 32 - WORD $0x8948; BYTE $0xcb // mov rbx, rcx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x000001a0248c3b48 // cmp rcx, qword [rsp + 416] - JNE LBB11_86 - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - QUAD $0x000001a024b43b4c // cmp r14, qword [rsp + 416] - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - QUAD $0x0000017024ac8b4c // mov r13, qword [rsp + 368] - QUAD $0x0000016824948b48 // mov rdx, qword [rsp + 360] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - JNE LBB11_88 - JMP LBB11_91 + JNE LBB11_100 + QUAD $0x00000160248c8b48 // mov rcx, qword [rsp + 352] + QUAD $0x000001a0248c3b48 // cmp rcx, qword [rsp + 416] + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + QUAD $0x0000016824ac8b4c // mov r13, qword [rsp + 360] + QUAD $0x0000017024bc8b48 // mov rdi, qword [rsp + 368] + JNE LBB11_102 + JMP LBB11_105 -LBB11_66: - LONG $0xe0e68349 // and r14, -32 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 +LBB11_72: + LONG $0xe0e18348 // and rcx, -32 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000016824848948 // mov qword [rsp + 360], rax - QUAD $0x0000018024b4894c // mov qword [rsp + 384], r14 - LONG $0xb7048d4b // lea rax, [r15 + 4*r14] + WORD $0x0148; BYTE $0xf8 // add rax, rdi QUAD $0x0000017024848948 // mov qword [rsp + 368], rax - LONG $0x6e79c1c4; BYTE $0xc3 // vmovd xmm0, r11d + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8f048d49 // lea rax, [r15 + 4*rcx] + QUAD $0x0000016824848948 // mov qword [rsp + 360], rax + LONG $0x6e79c1c4; BYTE $0xc6 // vmovd xmm0, r14d LONG $0x787de2c4; BYTE $0xc0 // vpbroadcastb ymm0, xmm0 - WORD $0xdb31 // xor ebx, ebx + WORD $0xc031 // xor eax, eax QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 -LBB11_67: - QUAD $0x00000178249c8948 // mov qword [rsp + 376], rbx +LBB11_73: + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x0000017824848948 // mov qword [rsp + 376], rax LONG $0x05e3c148 // shl rbx, 5 WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x20c88348 // or rax, 32 - QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x40c88348 // or rax, 64 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x60c88348 // or rax, 96 LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00800d48; WORD $0x0000 // or rax, 128 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + QUAD $0x0000010824848948 // mov qword [rsp + 264], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00a00d48; WORD $0x0000 // or rax, 160 - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x00e00d48; WORD $0x0000 // or rax, 224 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01000d48; WORD $0x0000 // or rax, 256 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01200d48; WORD $0x0000 // or rax, 288 QUAD $0x000000d824848948 // mov qword [rsp + 216], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x000000f0249c8948 // mov qword [rsp + 240], rbx LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x02000d48; WORD $0x0000 // or rax, 512 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x0204b60f // movzx eax, byte [rdx + rax] + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x0704b60f // movzx eax, byte [rdi + rax] LONG $0xd86ef9c5 // vmovd xmm3, eax - LONG $0x1a04b60f // movzx eax, byte [rdx + rbx] + LONG $0x1f04b60f // movzx eax, byte [rdi + rbx] LONG $0xe06ef9c5 // vmovd xmm4, eax - LONG $0x0a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rcx + 1] + LONG $0x1744b60f; BYTE $0x01 // movzx eax, byte [rdi + rdx + 1] LONG $0xe86ef9c5 // vmovd xmm5, eax - LONG $0x1a44b60f; BYTE $0x01 // movzx eax, byte [rdx + rbx + 1] + LONG $0x1f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rbx + 1] LONG $0xd06e79c5 // vmovd xmm10, eax - LONG $0x0a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rcx + 2] + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001e0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 480], xmm1 - LONG $0x1a44b60f; BYTE $0x02 // movzx eax, byte [rdx + rbx + 2] + LONG $0x1f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rbx + 2] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x0001c0248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 448], xmm1 - LONG $0x0a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rcx + 3] + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] LONG $0xd86e79c5 // vmovd xmm11, eax - LONG $0x1a44b60f; BYTE $0x03 // movzx eax, byte [rdx + rbx + 3] + LONG $0x1f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rbx + 3] LONG $0xc06e79c5 // vmovd xmm8, eax - LONG $0x0a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rcx + 4] + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] LONG $0xc86ef9c5 // vmovd xmm1, eax QUAD $0x000200248c7ff9c5; BYTE $0x00 // vmovdqa oword [rsp + 512], xmm1 - LONG $0x1a44b60f; BYTE $0x04 // movzx eax, byte [rdx + rbx + 4] + LONG $0x1f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rbx + 4] LONG $0xf86e79c5 // vmovd xmm15, eax - LONG $0x0a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rcx + 5] + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] LONG $0xf06e79c5 // vmovd xmm14, eax - LONG $0x1a44b60f; BYTE $0x05 // movzx eax, byte [rdx + rbx + 5] + LONG $0x1f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rbx + 5] LONG $0xe06e79c5 // vmovd xmm12, eax - LONG $0x0a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rcx + 6] - QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + QUAD $0x000000f824948948 // mov qword [rsp + 248], rdx LONG $0xe86e79c5 // vmovd xmm13, eax - LONG $0x1a44b60f; BYTE $0x06 // movzx eax, byte [rdx + rbx + 6] + LONG $0x1f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rbx + 6] LONG $0xf86ef9c5 // vmovd xmm7, eax - LONG $0x0a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rcx + 7] + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] LONG $0xd06ef9c5 // vmovd xmm2, eax - LONG $0x1a44b60f; BYTE $0x07 // movzx eax, byte [rdx + rbx + 7] + LONG $0x1f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rbx + 7] LONG $0xc86ef9c5 // vmovd xmm1, eax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01600d48; WORD $0x0000 // or rax, 352 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax WORD $0x8948; BYTE $0xd8 // mov rax, rbx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - LONG $0x20cf8148; WORD $0x0002; BYTE $0x00 // or rdi, 544 - QUAD $0x000000c824bc8948 // mov qword [rsp + 200], rdi - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02400d48; WORD $0x0000 // or rax, 576 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000e824848948 // mov qword [rsp + 232], rax + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0x20cf8149; WORD $0x0002; BYTE $0x00 // or r15, 544 + LONG $0x247c894c; BYTE $0x58 // mov qword [rsp + 88], r15 + WORD $0x8949; BYTE $0xde // mov r14, rbx + LONG $0x40ce8149; WORD $0x0002; BYTE $0x00 // or r14, 576 + QUAD $0x000000b824b4894c // mov qword [rsp + 184], r14 WORD $0x8949; BYTE $0xdb // mov r11, rbx LONG $0x60cb8149; WORD $0x0002; BYTE $0x00 // or r11, 608 - QUAD $0x000000a8249c894c // mov qword [rsp + 168], r11 - WORD $0x8949; BYTE $0xde // mov r14, rbx - LONG $0x80ce8149; WORD $0x0002; BYTE $0x00 // or r14, 640 - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 + QUAD $0x000000e0249c894c // mov qword [rsp + 224], r11 WORD $0x8949; BYTE $0xda // mov r10, rbx - LONG $0xa0ca8149; WORD $0x0002; BYTE $0x00 // or r10, 672 - QUAD $0x000000a02494894c // mov qword [rsp + 160], r10 + LONG $0x80ca8149; WORD $0x0002; BYTE $0x00 // or r10, 640 + LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x02c00d48; WORD $0x0000 // or rax, 704 + LONG $0x02a00d48; WORD $0x0000 // or rax, 672 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + LONG $0xc0c98149; WORD $0x0002; BYTE $0x00 // or r9, 704 + LONG $0x244c894c; BYTE $0x38 // mov qword [rsp + 56], r9 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x02e00d48; WORD $0x0000 // or rax, 736 + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03000d48; WORD $0x0000 // or rax, 768 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x03200d48; WORD $0x0000 // or rax, 800 + WORD $0x8949; BYTE $0xc4 // mov r12, rax QUAD $0x0000009824848948 // mov qword [rsp + 152], rax WORD $0x8949; BYTE $0xd8 // mov r8, rbx - LONG $0xe0c88149; WORD $0x0002; BYTE $0x00 // or r8, 736 - LONG $0x2444894c; BYTE $0x78 // mov qword [rsp + 120], r8 - WORD $0x8949; BYTE $0xdf // mov r15, rbx - LONG $0x00cf8149; WORD $0x0003; BYTE $0x00 // or r15, 768 - QUAD $0x000000c024bc894c // mov qword [rsp + 192], r15 + LONG $0x40c88149; WORD $0x0003; BYTE $0x00 // or r8, 832 + QUAD $0x000000f02484894c // mov qword [rsp + 240], r8 + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + LONG $0x60c98148; WORD $0x0003; BYTE $0x00 // or rcx, 864 + QUAD $0x000000c8248c8948 // mov qword [rsp + 200], rcx WORD $0x8948; BYTE $0xd8 // mov rax, rbx - LONG $0x03200d48; WORD $0x0000 // or rax, 800 - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - LONG $0x40c98149; WORD $0x0003; BYTE $0x00 // or r9, 832 - QUAD $0x000000b8248c894c // mov qword [rsp + 184], r9 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0x60cc8149; WORD $0x0003; BYTE $0x00 // or r12, 864 - QUAD $0x000000b024a4894c // mov qword [rsp + 176], r12 + LONG $0x03800d48; WORD $0x0000 // or rax, 896 + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax WORD $0x8948; BYTE $0xde // mov rsi, rbx - LONG $0x80ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 896 - QUAD $0x0000010824b48948 // mov qword [rsp + 264], rsi - WORD $0x8948; BYTE $0xd9 // mov rcx, rbx - LONG $0xa0c98148; WORD $0x0003; BYTE $0x00 // or rcx, 928 - QUAD $0x000000e8248c8948 // mov qword [rsp + 232], rcx + LONG $0xa0ce8148; WORD $0x0003; BYTE $0x00 // or rsi, 928 + QUAD $0x000000d024b48948 // mov qword [rsp + 208], rsi WORD $0x8948; BYTE $0xd8 // mov rax, rbx + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x00000100249c8948 // mov qword [rsp + 256], rbx LONG $0x03c00d48; WORD $0x0000 // or rax, 960 - LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax - LONG $0xe0cb8148; WORD $0x0003; BYTE $0x00 // or rbx, 992 - QUAD $0x000000f8249c8948 // mov qword [rsp + 248], rbx - LONG $0x206163c4; WORD $0x3a0c; BYTE $0x01 // vpinsrb xmm9, xmm3, byte [rdx + rdi], 1 - LONG $0x2031a3c4; WORD $0x2a1c; BYTE $0x02 // vpinsrb xmm3, xmm9, byte [rdx + r13], 2 - LONG $0x2061a3c4; WORD $0x1a1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdx + r11], 3 - LONG $0x2061a3c4; WORD $0x321c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdx + r14], 4 - LONG $0x2061a3c4; WORD $0x121c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdx + r10], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdx + rdi], 6 - LONG $0x2061a3c4; WORD $0x021c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdx + r8], 7 - LONG $0x2061a3c4; WORD $0x3a1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdx + r15], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - LONG $0x2061e3c4; WORD $0x3a1c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdx + rdi], 9 - LONG $0x2061a3c4; WORD $0x0a1c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdx + r9], 10 - LONG $0x2061a3c4; WORD $0x221c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdx + r12], 11 - LONG $0x2061e3c4; WORD $0x321c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdx + rsi], 12 - LONG $0x2061e3c4; WORD $0x0a1c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdx + rcx], 13 - LONG $0x2061e3c4; WORD $0x021c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdx + rax], 14 - LONG $0x2061e3c4; WORD $0x1a1c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdx + rbx], 15 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - LONG $0x2059a3c4; WORD $0x2224; BYTE $0x01 // vpinsrb xmm4, xmm4, byte [rdx + r12], 1 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - LONG $0x2059a3c4; WORD $0x3224; BYTE $0x02 // vpinsrb xmm4, xmm4, byte [rdx + r14], 2 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - LONG $0x2059a3c4; WORD $0x1a24; BYTE $0x03 // vpinsrb xmm4, xmm4, byte [rdx + r11], 3 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - LONG $0x2059a3c4; WORD $0x0224; BYTE $0x04 // vpinsrb xmm4, xmm4, byte [rdx + r8], 4 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - LONG $0x2059a3c4; WORD $0x0a24; BYTE $0x05 // vpinsrb xmm4, xmm4, byte [rdx + r9], 5 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - LONG $0x2059e3c4; WORD $0x1a24; BYTE $0x06 // vpinsrb xmm4, xmm4, byte [rdx + rbx], 6 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - LONG $0x2059e3c4; WORD $0x3224; BYTE $0x07 // vpinsrb xmm4, xmm4, byte [rdx + rsi], 7 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - LONG $0x2059a3c4; WORD $0x3a24; BYTE $0x08 // vpinsrb xmm4, xmm4, byte [rdx + r15], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - LONG $0x2059e3c4; WORD $0x3a24; BYTE $0x09 // vpinsrb xmm4, xmm4, byte [rdx + rdi], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - LONG $0x2059e3c4; WORD $0x0224; BYTE $0x0a // vpinsrb xmm4, xmm4, byte [rdx + rax], 10 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - LONG $0x2059a3c4; WORD $0x1224; BYTE $0x0b // vpinsrb xmm4, xmm4, byte [rdx + r10], 11 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x2059e3c4; WORD $0x0a24; BYTE $0x0c // vpinsrb xmm4, xmm4, byte [rdx + rcx], 12 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - LONG $0x2059e3c4; WORD $0x0a24; BYTE $0x0d // vpinsrb xmm4, xmm4, byte [rdx + rcx], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - LONG $0x2059e3c4; WORD $0x0a24; BYTE $0x0e // vpinsrb xmm4, xmm4, byte [rdx + rcx], 14 - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - LONG $0x2059a3c4; WORD $0x2a24; BYTE $0x0f // vpinsrb xmm4, xmm4, byte [rdx + r13], 15 - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x01010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x04010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 4 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x05010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 6 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x07010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 7 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x08012a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 1], 8 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x09010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 9 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x0a010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 10 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0b010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 11 - QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] - QUAD $0x0c010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 12 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x0d010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 13 + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + LONG $0xe0ca8148; WORD $0x0003; BYTE $0x00 // or rdx, 992 + LONG $0x24548948; BYTE $0x60 // mov qword [rsp + 96], rdx + LONG $0x206123c4; WORD $0x3f0c; BYTE $0x01 // vpinsrb xmm9, xmm3, byte [rdi + r15], 1 + LONG $0x2031a3c4; WORD $0x371c; BYTE $0x02 // vpinsrb xmm3, xmm9, byte [rdi + r14], 2 + LONG $0x2061a3c4; WORD $0x1f1c; BYTE $0x03 // vpinsrb xmm3, xmm3, byte [rdi + r11], 3 + LONG $0x2061a3c4; WORD $0x171c; BYTE $0x04 // vpinsrb xmm3, xmm3, byte [rdi + r10], 4 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x05 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 5 + LONG $0x2061a3c4; WORD $0x0f1c; BYTE $0x06 // vpinsrb xmm3, xmm3, byte [rdi + r9], 6 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + LONG $0x2061e3c4; WORD $0x1f1c; BYTE $0x07 // vpinsrb xmm3, xmm3, byte [rdi + rbx], 7 + LONG $0x2061a3c4; WORD $0x2f1c; BYTE $0x08 // vpinsrb xmm3, xmm3, byte [rdi + r13], 8 + LONG $0x2061a3c4; WORD $0x271c; BYTE $0x09 // vpinsrb xmm3, xmm3, byte [rdi + r12], 9 + LONG $0x2061a3c4; WORD $0x071c; BYTE $0x0a // vpinsrb xmm3, xmm3, byte [rdi + r8], 10 + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0b // vpinsrb xmm3, xmm3, byte [rdi + rcx], 11 LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0e010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 14 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x0f010a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 1], 15 - QUAD $0x010122742029a3c4 // vpinsrb xmm6, xmm10, byte [rdx + r12 + 1], 1 - QUAD $0x020132742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r14 + 1], 2 - QUAD $0x03011a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r11 + 1], 3 - QUAD $0x040102742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r8 + 1], 4 - QUAD $0x05010a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 1], 5 - QUAD $0x06011a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 1], 6 - QUAD $0x070132742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 1], 7 - QUAD $0x08013a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 1], 8 - QUAD $0x09013a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 1], 9 - QUAD $0x0a0102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 10 - QUAD $0x0b0112742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r10 + 1], 11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c0102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 13 - WORD $0x8949; BYTE $0xc3 // mov r11, rax - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e0102742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 1], 14 + LONG $0x2061e3c4; WORD $0x0f1c; BYTE $0x0c // vpinsrb xmm3, xmm3, byte [rdi + rcx], 12 + LONG $0x2061e3c4; WORD $0x371c; BYTE $0x0d // vpinsrb xmm3, xmm3, byte [rdi + rsi], 13 + LONG $0x2061e3c4; WORD $0x071c; BYTE $0x0e // vpinsrb xmm3, xmm3, byte [rdi + rax], 14 + LONG $0x2061e3c4; WORD $0x171c; BYTE $0x0f // vpinsrb xmm3, xmm3, byte [rdi + rdx], 15 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + LONG $0x2059a3c4; WORD $0x3724; BYTE $0x01 // vpinsrb xmm4, xmm4, byte [rdi + r14], 1 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + LONG $0x2059a3c4; WORD $0x1724; BYTE $0x02 // vpinsrb xmm4, xmm4, byte [rdi + r10], 2 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + LONG $0x2059a3c4; WORD $0x2724; BYTE $0x03 // vpinsrb xmm4, xmm4, byte [rdi + r12], 3 + QUAD $0x0000010824848b4c // mov r8, qword [rsp + 264] + LONG $0x2059a3c4; WORD $0x0724; BYTE $0x04 // vpinsrb xmm4, xmm4, byte [rdi + r8], 4 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + LONG $0x2059e3c4; WORD $0x1f24; BYTE $0x05 // vpinsrb xmm4, xmm4, byte [rdi + rbx], 5 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + LONG $0x2059a3c4; WORD $0x0f24; BYTE $0x06 // vpinsrb xmm4, xmm4, byte [rdi + r9], 6 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + LONG $0x2059a3c4; WORD $0x1f24; BYTE $0x07 // vpinsrb xmm4, xmm4, byte [rdi + r11], 7 + QUAD $0x0000014024bc8b4c // mov r15, qword [rsp + 320] + LONG $0x2059a3c4; WORD $0x3f24; BYTE $0x08 // vpinsrb xmm4, xmm4, byte [rdi + r15], 8 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + LONG $0x2059e3c4; WORD $0x0724; BYTE $0x09 // vpinsrb xmm4, xmm4, byte [rdi + rax], 9 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + LONG $0x2059e3c4; WORD $0x0f24; BYTE $0x0a // vpinsrb xmm4, xmm4, byte [rdi + rcx], 10 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + LONG $0x2059e3c4; WORD $0x1724; BYTE $0x0b // vpinsrb xmm4, xmm4, byte [rdi + rdx], 11 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + LONG $0x2059e3c4; WORD $0x3724; BYTE $0x0c // vpinsrb xmm4, xmm4, byte [rdi + rsi], 12 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + LONG $0x2059a3c4; WORD $0x2f24; BYTE $0x0d // vpinsrb xmm4, xmm4, byte [rdi + r13], 13 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + LONG $0x2059e3c4; WORD $0x3724; BYTE $0x0e // vpinsrb xmm4, xmm4, byte [rdi + rsi], 14 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + LONG $0x2059e3c4; WORD $0x3724; BYTE $0x0f // vpinsrb xmm4, xmm4, byte [rdi + rsi], 15 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0101376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 1 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0201376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 2 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x0301376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 3 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0401376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 4 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x0501376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 5 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0601376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 6 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0701376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 7 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0801376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 8 + QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] + QUAD $0x0901376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 9 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0a01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 10 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x0b01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 12 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0d01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 13 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0e01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 14 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0f01376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 1], 15 + QUAD $0x010137742029a3c4 // vpinsrb xmm6, xmm10, byte [rdi + r14 + 1], 1 + QUAD $0x020117742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 1], 2 + WORD $0x894d; BYTE $0xd6 // mov r14, r10 + QUAD $0x030127742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 1], 3 + QUAD $0x040107742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r8 + 1], 4 + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 + QUAD $0x05011f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 1], 5 + QUAD $0x06010f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 1], 6 + WORD $0x894d; BYTE $0xca // mov r10, r9 + QUAD $0x07011f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 1], 7 + QUAD $0x08013f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r15 + 1], 8 + QUAD $0x090107742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 1], 9 + QUAD $0x0a010f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 1], 10 + QUAD $0x0b0117742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 1], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c0107742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 1], 12 + QUAD $0x0d012f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r13 + 1], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0107742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 1], 14 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x0004c0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1216], ymm3 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0f01025c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdx + rax + 1], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xcf6e79c5 // vmovd xmm9, edi + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f01075c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdi + rax + 1], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xc86e79c5 // vmovd xmm9, eax LONG $0x3865e3c4; WORD $0x01dd // vinserti128 ymm3, ymm3, xmm5, 1 QUAD $0x000220249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 544], ymm3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x08 // movzx edi, byte [rdx + rax + 8] - LONG $0xd76e79c5 // vmovd xmm10, edi - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x08 // movzx eax, byte [rdi + rax + 8] + LONG $0xd06e79c5 // vmovd xmm10, eax QUAD $0x0001e0249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 480] - QUAD $0x01020a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 2], 1 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x0202325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 2], 2 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0302025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 3 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x04023a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 2], 4 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0502025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 5 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x0602125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 2], 6 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0102075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0202075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 2 + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x03023f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 2], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0402075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 4 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x05021f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 2], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0602075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 6 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x07021f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 2], 7 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x08020f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 2], 8 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x0902075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 2], 9 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0a02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 12 + QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + QUAD $0x0d022f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 2], 13 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0702025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 7 - QUAD $0x08022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 8 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0902025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 9 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x0a02225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 2], 10 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x0b022a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 2], 11 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x0c021a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 2], 12 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x0d020a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 2], 13 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x0e02025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 2], 14 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0f02025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 2], 15 + QUAD $0x0e02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f02075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 2], 15 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] QUAD $0x0001c024a46ff9c5; BYTE $0x00 // vmovdqa xmm4, oword [rsp + 448] - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x010202642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 2], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x020202642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 2], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x03023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 3 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x04023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 6 - QUAD $0x070232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x08023a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 2], 8 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x090232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a0232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 10 + QUAD $0x01020f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 2], 1 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + QUAD $0x020237642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 2], 2 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x030237642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 2], 3 + QUAD $0x040237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 4 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x050217642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 2], 5 + QUAD $0x060217642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 2], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x070207642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 2], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x080207642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 2], 8 + QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] + QUAD $0x090217642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 2], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a0237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 10 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0b0237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 11 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0c0237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 12 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0d0237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 13 LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0b0232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 11 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0c0232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 12 - QUAD $0x0d021a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 2], 13 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0e0232642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 2], 14 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x0f021a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 2], 15 - QUAD $0x01030a6c2021a3c4 // vpinsrb xmm5, xmm11, byte [rdx + r9 + 3], 1 - QUAD $0x0203326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 3], 2 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x0303326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 3 - QUAD $0x04033a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 3], 4 - WORD $0x894d; BYTE $0xfb // mov r11, r15 - QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] - QUAD $0x0503326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 3], 5 - QUAD $0x0603126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 3], 6 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0703326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 7 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x08030a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 3], 8 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x0903326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 3], 9 - QUAD $0x0a03226c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r12 + 3], 10 - QUAD $0x0b032a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 3], 11 - QUAD $0x0c031a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 3], 12 - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x0d030a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 3], 13 - QUAD $0x0e03026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 3], 14 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0f03126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 3], 15 - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x01030a742039e3c4 // vpinsrb xmm6, xmm8, byte [rdx + rcx + 3], 1 - QUAD $0x020302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x030302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 3 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x040302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 4 + QUAD $0x0e0237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 14 + QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] + QUAD $0x0f0237642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 2], 15 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0103376c2021e3c4 // vpinsrb xmm5, xmm11, byte [rdi + rsi + 3], 1 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0203376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 2 + QUAD $0x03033f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 3], 3 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0403376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 4 + QUAD $0x05031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 5 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x06033f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 3], 6 + QUAD $0x07031f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r11 + 3], 7 + QUAD $0x08030f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 3], 8 + QUAD $0x0903076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 3], 9 + QUAD $0x000000f0248c8b4c // mov r9, qword [rsp + 240] + QUAD $0x0a030f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 3], 10 + QUAD $0x000000c8249c8b48 // mov rbx, qword [rsp + 200] + QUAD $0x0b031f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 3], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c03376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 12 + QUAD $0x0d032f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 3], 13 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0e032f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 3], 14 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0f03376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 3], 15 + QUAD $0x01030f742039e3c4 // vpinsrb xmm6, xmm8, byte [rdi + rcx + 3], 1 + QUAD $0x020327742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 3], 2 + QUAD $0x030337742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 3], 3 + QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] + QUAD $0x04031f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 3], 4 + QUAD $0x050317742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rdx + 3], 5 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x060327742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r12 + 3], 6 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x07030f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 3], 7 + QUAD $0x080307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 8 + QUAD $0x090317742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 3], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b0307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 5 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x060322742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 3], 6 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x070302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 7 - QUAD $0x08033a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 3], 8 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x090332742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 3], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b0302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c0302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0302742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 3], 13 + QUAD $0x0c0307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d0307742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 3], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x0001e0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 480], ymm3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e03025c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdx + rax + 3], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x09 // movzx edi, byte [rdx + rax + 9] - LONG $0xc76e79c5 // vmovd xmm8, edi - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0f030a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 3], 15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e03075c2049e3c4 // vpinsrb xmm3, xmm6, byte [rdi + rax + 3], 14 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xc06e79c5 // vmovd xmm8, eax + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f03075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 3], 15 LONG $0x3865e3c4; WORD $0x01dd // vinserti128 ymm3, ymm3, xmm5, 1 QUAD $0x0001c0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 448], ymm3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x09 // movzx edi, byte [rdx + rax + 9] - LONG $0xdf6e79c5 // vmovd xmm11, edi + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x09 // movzx eax, byte [rdi + rax + 9] + LONG $0xd86e79c5 // vmovd xmm11, eax QUAD $0x000200249c6ff9c5; BYTE $0x00 // vmovdqa xmm3, oword [rsp + 512] - QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] - QUAD $0x0104025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 4], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0204025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 2 - QUAD $0x000000a8249c8b48 // mov rbx, qword [rsp + 168] - QUAD $0x03041a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 4], 3 - QUAD $0x04043a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 4], 4 - QUAD $0x0504325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 4], 5 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0104075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0204075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 2 + QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + QUAD $0x0304175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 4], 3 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0404175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 4], 4 + QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] + QUAD $0x0504075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 4], 5 + QUAD $0x06043f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 4], 6 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0704375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 4], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0804075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 8 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0604025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 6 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x07041a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 4], 7 - QUAD $0x08040a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 4], 8 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0904025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 9 - QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] - QUAD $0x0a043a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 4], 10 - QUAD $0x000000b024b48b4c // mov r14, qword [rsp + 176] - QUAD $0x0b04325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 4], 11 - QUAD $0x0c042a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 4], 12 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0d04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 13 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0e04025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 4], 14 - QUAD $0x0f04125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 4], 15 - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - QUAD $0x010412642001a3c4 // vpinsrb xmm4, xmm15, byte [rdx + r10 + 4], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x020402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 2 + QUAD $0x0904075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 9 + QUAD $0x0a040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 10 + QUAD $0x0b041f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 4], 11 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x0c040f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 4], 12 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0d04075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 4], 13 + QUAD $0x0e042f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 4], 14 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0f040f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 4], 15 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x01042f642001a3c4 // vpinsrb xmm4, xmm15, byte [rdi + r13 + 4], 1 + QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] + QUAD $0x020437642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 4], 2 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x030402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 3 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x040402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 4 + QUAD $0x030407642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 4], 3 + QUAD $0x04041f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 4], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x050407642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 4], 5 + QUAD $0x060427642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 4], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x070407642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 4], 7 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x08041f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 4], 8 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x09041f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 4], 9 + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + QUAD $0x0a0427642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 4], 10 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x0b041f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 4], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0c041f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 4], 12 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0d0427642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 4], 13 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0e041f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 4], 14 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x0f0427642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 4], 15 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x01051f6c2009e3c4 // vpinsrb xmm5, xmm14, byte [rdi + rbx + 5], 1 + QUAD $0x000000b8249c8b48 // mov rbx, qword [rsp + 184] + QUAD $0x02051f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 5], 2 + QUAD $0x0305176c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r10 + 5], 3 + QUAD $0x0405176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 4 + QUAD $0x0505076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 5], 5 + QUAD $0x06053f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 5], 6 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + QUAD $0x0705376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 7 + QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] + QUAD $0x0805376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 5], 8 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x09053f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 5], 9 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0a05176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 10 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x0b05176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 11 + QUAD $0x0c050f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 5], 12 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0d05176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e05176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 5], 14 + QUAD $0x0f050f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 5], 15 + QUAD $0x01052f742019a3c4 // vpinsrb xmm6, xmm12, byte [rdi + r13 + 5], 1 + QUAD $0x020537742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 5], 2 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x030517742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 5], 3 + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + QUAD $0x04051f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 5], 4 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x05050f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 5], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x06050f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 5], 6 + QUAD $0x070507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 7 + QUAD $0x08051f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 5], 8 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x090507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b0507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 5 - QUAD $0x060422642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 4], 6 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x07043a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 4], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x080402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 8 - QUAD $0x090432642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 4], 9 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0a0422642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 4], 10 + QUAD $0x0c0507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d0507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 13 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b0402642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 4], 11 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0c0432642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 4], 12 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0d040a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 4], 13 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0e0432642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 4], 14 - QUAD $0x0f040a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 4], 15 - QUAD $0x0105026c2009a3c4 // vpinsrb xmm5, xmm14, byte [rdx + r8 + 5], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02050a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 5], 2 - QUAD $0x03051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 3 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x04051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 4 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0505026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 5], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06050a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 5], 6 - QUAD $0x07051a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 5], 7 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x08051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 8 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x09051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 9 - QUAD $0x0a053a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 5], 10 - QUAD $0x0b05326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 5], 11 - QUAD $0x0c052a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 5], 12 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x0d051a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 5], 13 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x0e051a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 5], 14 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0f05326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 5], 15 - QUAD $0x010512742019a3c4 // vpinsrb xmm6, xmm12, byte [rdx + r10 + 5], 1 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x02051a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 5], 2 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x03051a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 5], 3 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x04051a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 5], 4 - QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] - QUAD $0x05051a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 5], 5 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x06051a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 5], 6 - QUAD $0x07053a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 5], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x08053a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 5], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x09053a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 5], 9 - QUAD $0x0a0522742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 5], 10 - QUAD $0x0b0502742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 5], 11 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x0c0522742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 5], 12 - QUAD $0x0d050a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 5], 13 - QUAD $0x0e0532742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 5], 14 + QUAD $0x0e0507742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 5], 14 LONG $0x385d63c4; WORD $0x01f3 // vinserti128 ymm14, ymm4, xmm3, 1 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0f0502642049e3c4 // vpinsrb xmm4, xmm6, byte [rdx + rax + 5], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xe76e79c5 // vmovd xmm12, edi + QUAD $0x0f0527642049a3c4 // vpinsrb xmm4, xmm6, byte [rdi + r12 + 5], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06e79c5 // vmovd xmm12, eax LONG $0x385de3c4; WORD $0x01dd // vinserti128 ymm3, ymm4, xmm5, 1 QUAD $0x000200249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 512], ymm3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x0a // movzx edi, byte [rdx + rax + 10] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x01063a6c2011a3c4 // vpinsrb xmm5, xmm13, byte [rdx + r15 + 6], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0206026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 2 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0306026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0406026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 4 - QUAD $0x0506026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 6], 5 - QUAD $0x06060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 6 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x07060a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 6], 7 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0806026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 8 - QUAD $0x0000014024848b4c // mov r8, qword [rsp + 320] - QUAD $0x0906026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 6], 9 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0a06026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 10 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0a // movzx eax, byte [rdi + rax + 10] + LONG $0xe06ef9c5 // vmovd xmm4, eax + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x01061f6c2011a3c4 // vpinsrb xmm5, xmm13, byte [rdi + r11 + 6], 1 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x02060f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rcx + 6], 2 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0306176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 6], 3 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0406376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 6], 4 QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0b06026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 6], 11 - QUAD $0x0c062a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 6], 12 - QUAD $0x0d061a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 6], 13 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x0e06126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 6], 14 - QUAD $0x0f06326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 6], 15 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x01061a742041a3c4 // vpinsrb xmm6, xmm7, byte [rdx + r11 + 6], 1 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x020632742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r14 + 6], 2 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x03061a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rbx + 6], 3 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x040602742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 6], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050602742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 6], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06063a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 6], 6 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x070602742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 6], 7 + QUAD $0x0506076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 5 + QUAD $0x0606076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0706076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 7 + QUAD $0x0806376c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rsi + 6], 8 + QUAD $0x09063f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 6], 9 + QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] + QUAD $0x0a063f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r15 + 6], 10 + QUAD $0x000000c824848b4c // mov r8, qword [rsp + 200] + QUAD $0x0b06076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 6], 11 + QUAD $0x0c060f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r9 + 6], 12 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x0d06276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 6], 13 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x0e062f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 6], 14 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x080602742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 6], 8 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x090602742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rax + 6], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a0632742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 6], 10 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0b060a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r9 + 6], 11 - QUAD $0x0c0622742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 6], 12 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0d0622742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 6], 13 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0e0632742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 6], 14 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0f0632742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 6], 15 - QUAD $0x01073a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 7], 1 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x020732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 2 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x030732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 3 + QUAD $0x0f06076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 6], 15 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x010607742041e3c4 // vpinsrb xmm6, xmm7, byte [rdi + rax + 6], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x020607742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 6], 2 + QUAD $0x030617742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 6], 3 + QUAD $0x04061f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 6], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x050607742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 6], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x060607742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 6], 6 QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x040732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 4 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x050732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 5 - QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - QUAD $0x06073a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 7], 6 - QUAD $0x07070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 7 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x08070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 8 - QUAD $0x090702542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 7], 9 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x0a0732542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 7], 10 + QUAD $0x070637742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 6], 7 + QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] + QUAD $0x080637742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 6], 8 + QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] + QUAD $0x090617742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 6], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a0637742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 6], 10 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0b0637742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 6], 11 + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + QUAD $0x0c0637742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 6], 12 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0d0637742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 6], 13 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0e061f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 6], 14 + QUAD $0x000000e8249c8b48 // mov rbx, qword [rsp + 232] + QUAD $0x0f061f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rbx + 6], 15 + QUAD $0x01071f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 7], 1 + WORD $0x894c; BYTE $0xdb // mov rbx, r11 + QUAD $0x02070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 2 + QUAD $0x030717542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 7], 3 + QUAD $0x040737542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 7], 4 QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0b070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 11 - QUAD $0x0c072a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 7], 12 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x0d072a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 7], 13 - QUAD $0x0e0712542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 7], 14 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x0f070a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 7], 15 - QUAD $0x01071a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 7], 1 - QUAD $0x0207324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 7], 2 - QUAD $0x03071a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 7], 3 + QUAD $0x05070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 5 LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x04070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x05070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 5 - QUAD $0x06073a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 7], 6 + QUAD $0x06070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 6 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x07070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 7 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x08070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + QUAD $0x09070f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 7], 9 + QUAD $0x0a073f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 7], 10 + QUAD $0x0b0707542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 7], 11 + QUAD $0x0c070f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 7], 12 + QUAD $0x0d0727542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 7], 13 + QUAD $0x0e072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 14 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0f072f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 7], 15 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x01070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 1 QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x07070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x08070a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 7], 8 - QUAD $0x0907024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a07024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 10 - QUAD $0x0b070a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 7], 11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c07024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 7], 12 - QUAD $0x0d07224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 7], 13 + QUAD $0x02070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 2 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x03071f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 7], 3 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x04070f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 7], 4 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0507174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 7], 5 + QUAD $0x0607074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 6 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x07070f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 7], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0807074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 8 + QUAD $0x0907174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 9 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0a07174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 7], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c07074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 7], 12 + QUAD $0x0d07374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 7], 13 LONG $0x384de3c4; WORD $0x01dd // vinserti128 ymm3, ymm6, xmm5, 1 QUAD $0x0004a0249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1184], ymm3 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e07026c2071e3c4 // vpinsrb xmm5, xmm1, byte [rdx + rax + 7], 14 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0b // movzx edi, byte [rdx + rax + 11] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0f07026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 7], 15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e07076c2071e3c4 // vpinsrb xmm5, xmm1, byte [rdi + rax + 7], 14 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x000000e824b48b4c // mov r14, qword [rsp + 232] + QUAD $0x0f07376c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r14 + 7], 15 LONG $0x3855e3c4; WORD $0x01d2 // vinserti128 ymm2, ymm5, xmm2, 1 QUAD $0x00048024947ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1152], ymm2 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0b // movzx eax, byte [rdi + rax + 11] + LONG $0xd06ef9c5 // vmovd xmm2, eax + WORD $0x8949; BYTE $0xdf // mov r15, rbx + QUAD $0x01081f6c2031e3c4 // vpinsrb xmm5, xmm9, byte [rdi + rbx + 8], 1 + QUAD $0x000000b824948b48 // mov rdx, qword [rsp + 184] + QUAD $0x0208176c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rdx + 8], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0308076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 3 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + QUAD $0x0408076c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r8 + 8], 4 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x05081f6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rbx + 8], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0608076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0708076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0808076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 8 + QUAD $0x0000009824a48b4c // mov r12, qword [rsp + 152] + QUAD $0x0908276c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r12 + 8], 9 QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x0b // movzx edi, byte [rdx + rax + 11] - LONG $0xd76ef9c5 // vmovd xmm2, edi + QUAD $0x0a08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 10 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0108026c2031e3c4 // vpinsrb xmm5, xmm9, byte [rdx + rax + 8], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x0208026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03080a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rcx + 8], 3 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - QUAD $0x0408126c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r10 + 8], 4 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - QUAD $0x05081a6c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rbx + 8], 5 - QUAD $0x06083a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r15 + 8], 6 + QUAD $0x0b08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 12 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0d08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 13 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0708026c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rax + 8], 7 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x08080a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r9 + 8], 8 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x0908026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 8], 9 - QUAD $0x0a08326c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdx + rsi + 8], 10 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x0b08026c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r8 + 8], 11 - QUAD $0x00000108249c8b4c // mov r11, qword [rsp + 264] - QUAD $0x0c081a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r11 + 8], 12 - QUAD $0x0d082a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 8], 13 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x0e082a6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r13 + 8], 14 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0f08326c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdx + r14 + 8], 15 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x010832742029e3c4 // vpinsrb xmm6, xmm10, byte [rdx + rsi + 8], 1 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x020832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 2 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x030832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 3 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x04083a742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r15 + 8], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05083a742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rdi + 8], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x060832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 6 + QUAD $0x0e08076c2051e3c4 // vpinsrb xmm5, xmm5, byte [rdi + rax + 8], 14 + QUAD $0x0f082f6c2051a3c4 // vpinsrb xmm5, xmm5, byte [rdi + r13 + 8], 15 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x01082f742029a3c4 // vpinsrb xmm6, xmm10, byte [rdi + r13 + 8], 1 QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x070832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 7 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x080832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 8 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x090832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a0832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 10 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x0b0832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 11 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0c0832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 12 - QUAD $0x0d0822742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 8], 13 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x0e0822742049a3c4 // vpinsrb xmm6, xmm6, byte [rdx + r12 + 8], 14 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0f0832742049e3c4 // vpinsrb xmm6, xmm6, byte [rdx + rsi + 8], 15 - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x0109327c2039e3c4 // vpinsrb xmm7, xmm8, byte [rdx + rsi + 9], 1 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x0209327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 9], 2 - QUAD $0x03090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 3 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - QUAD $0x0409127c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r10 + 9], 4 - QUAD $0x05091a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rbx + 9], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0609327c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rsi + 9], 6 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x07090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 7 - QUAD $0x08090a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r9 + 9], 8 - QUAD $0x0909027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 9 - QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] - QUAD $0x0a090a7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rcx + 9], 10 - QUAD $0x0b09027c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r8 + 9], 11 - QUAD $0x0c091a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r11 + 9], 12 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0d09027c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdx + rax + 9], 13 - QUAD $0x0e092a7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r13 + 9], 14 - QUAD $0x0f09327c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdx + r14 + 9], 15 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] - QUAD $0x01092a5c2021a3c4 // vpinsrb xmm3, xmm11, byte [rdx + r13 + 9], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0209025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0309025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 3 - QUAD $0x04093a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 9], 4 - QUAD $0x05093a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 9], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0609025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 6 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x07091a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 9], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0809025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 8 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x0909025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 11 + QUAD $0x020837742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rsi + 8], 2 + QUAD $0x03081f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 8], 3 + QUAD $0x04080f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 8], 4 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 14 + QUAD $0x050807742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rax + 8], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x06080f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 8], 6 + QUAD $0x07080f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r9 + 8], 7 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x08080f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 8], 8 + QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] + QUAD $0x09080f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 8], 9 + WORD $0x894d; BYTE $0xd1 // mov r9, r10 + QUAD $0x0a0817742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 8], 10 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x0b081f742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r11 + 8], 11 + QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] + QUAD $0x0c0817742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r10 + 8], 12 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0d080f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 8], 13 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0e080f742049e3c4 // vpinsrb xmm6, xmm6, byte [rdi + rcx + 8], 14 + QUAD $0x0f0837742049a3c4 // vpinsrb xmm6, xmm6, byte [rdi + r14 + 8], 15 + QUAD $0x01093f7c2039a3c4 // vpinsrb xmm7, xmm8, byte [rdi + r15 + 9], 1 + QUAD $0x0209177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 2 + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0309177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 3 + QUAD $0x0409077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 4 + QUAD $0x05091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 5 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0609177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 6 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x07091f7c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rbx + 9], 7 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x0809077c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r8 + 9], 8 + QUAD $0x0909277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 9 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0a09177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 10 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x0b093f7c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r15 + 9], 11 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0c09177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 12 + QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] + QUAD $0x0d09177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e09177c2041e3c4 // vpinsrb xmm7, xmm7, byte [rdi + rdx + 9], 14 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0f09277c2041a3c4 // vpinsrb xmm7, xmm7, byte [rdi + r12 + 9], 15 + QUAD $0x01092f5c2021a3c4 // vpinsrb xmm3, xmm11, byte [rdi + r13 + 9], 1 + QUAD $0x0209375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 9], 2 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0309175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 9], 3 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x0409175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 9], 4 + QUAD $0x0509075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x0609075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0709075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x0809075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 8 + QUAD $0x000000d824ac8b4c // mov r13, qword [rsp + 216] + QUAD $0x09092f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 9], 9 + QUAD $0x0a090f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 9], 10 + QUAD $0x0b091f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 9], 11 + QUAD $0x0c09175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 9], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d09075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 9], 13 + QUAD $0x0e090f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 9], 14 LONG $0x384de3c4; WORD $0x01ed // vinserti128 ymm5, ymm6, xmm5, 1 QUAD $0x00046024ac7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1120], ymm5 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0f09025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 9], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xef6ef9c5 // vmovd xmm5, edi + QUAD $0x0f09375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 9], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xe86ef9c5 // vmovd xmm5, eax LONG $0x3865e3c4; WORD $0x01df // vinserti128 ymm3, ymm3, xmm7, 1 QUAD $0x000440249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1088], ymm3 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x0c // movzx edi, byte [rdx + rax + 12] - LONG $0xf76ef9c5 // vmovd xmm6, edi - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x010a125c2019a3c4 // vpinsrb xmm3, xmm12, byte [rdx + r10 + 10], 1 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - QUAD $0x020a025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 10], 2 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - QUAD $0x030a225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 10], 3 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x040a1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 10], 4 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x050a225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 10], 5 - QUAD $0x060a325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 10], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x070a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 7 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x080a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x090a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 9 - QUAD $0x0a0a0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 10], 10 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0b0a3a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 10], 11 - QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] - QUAD $0x0c0a325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 10], 12 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0d0a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 13 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0e0a025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 10], 14 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x0f0a3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 10], 15 - QUAD $0x010a2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 10], 1 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x020a3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 10], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x030a3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 10], 3 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x040a3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 10], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x050a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 5 - QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] - QUAD $0x060a2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 10], 6 - QUAD $0x070a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x080a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 8 - QUAD $0x000000d8248c8b48 // mov rcx, qword [rsp + 216] - QUAD $0x090a0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 10], 9 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0c // movzx eax, byte [rdi + rax + 12] + LONG $0xf06ef9c5 // vmovd xmm6, eax LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 10 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0b0a1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 10], 11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 14 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0f0a02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 10], 15 - QUAD $0x010b124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 11], 1 - QUAD $0x020b024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 11], 2 - QUAD $0x030b0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 11], 3 - QUAD $0x040b1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 11], 4 - QUAD $0x050b224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 11], 5 - QUAD $0x060b324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 11], 6 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x070b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 7 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x080b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 8 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x090b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 9 + QUAD $0x010a075c2019e3c4 // vpinsrb xmm3, xmm12, byte [rdi + rax + 10], 1 QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0a0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 10 - QUAD $0x0b0b3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 11], 11 - QUAD $0x0c0b324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 11], 12 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0d0b024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 11], 13 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x0e0b3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 11], 14 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0f0b324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 11], 15 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x010b1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 11], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x020b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 2 + QUAD $0x020a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x030a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x040a075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 10], 4 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x050a175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 10], 5 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x060a175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 10], 6 + QUAD $0x070a1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 10], 7 + QUAD $0x080a075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 10], 8 + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x090a375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 10], 9 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x0a0a1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 10], 10 + QUAD $0x0b0a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c0a375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 10], 12 + QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] + QUAD $0x0d0a3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 10], 13 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x0e0a0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 10], 14 + QUAD $0x0f0a275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 10], 15 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x010a1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 10], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x020a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 2 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x030b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 3 - QUAD $0x040b3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 11], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050b02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 11], 5 - QUAD $0x060b2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 11], 6 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x070b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 7 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x080b32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 11], 8 - QUAD $0x090b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 9 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 10 - QUAD $0x0b0b1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 11], 11 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0c0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 12 + QUAD $0x030a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x040a07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 10], 4 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x050a27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 10], 5 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + QUAD $0x060a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 6 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x070a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 7 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x080a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 8 + QUAD $0x090a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 9 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x0a0a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 10 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x0b0a07642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 10], 11 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0c0a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 12 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0d0a2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 10], 13 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0e0a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 14 + QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] + QUAD $0x0f0a0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 10], 15 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x010b2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 11], 1 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + QUAD $0x020b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 2 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x030b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 3 LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0d0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 13 + QUAD $0x040b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 4 + QUAD $0x050b174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 11], 5 + QUAD $0x060b174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 11], 6 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x070b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 7 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x080b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 8 + QUAD $0x090b374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 11], 9 + QUAD $0x0a0b1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 11], 10 + QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] + QUAD $0x0b0b0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 11], 11 + QUAD $0x0c0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 12 + QUAD $0x0d0b3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 11], 13 + QUAD $0x0e0b0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 11], 14 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0f0b374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 11], 15 + QUAD $0x010b1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 11], 1 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x020b17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 11], 2 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x030b37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 11], 3 + QUAD $0x040b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 4 + QUAD $0x050b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 5 + QUAD $0x000000a824a48b4c // mov r12, qword [rsp + 168] + QUAD $0x060b27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 11], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x070b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 7 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x080b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 8 + QUAD $0x000000d8248c8b4c // mov r9, qword [rsp + 216] + QUAD $0x090b0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 11], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 10 + QUAD $0x0b0b07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 11], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 12 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0d0b2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 11], 13 LONG $0x385de3c4; WORD $0x01db // vinserti128 ymm3, ymm4, xmm3, 1 QUAD $0x000420249c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1056], ymm3 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 14 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a7cb60f; BYTE $0x0d // movzx edi, byte [rdx + rcx + 13] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0f0b0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 11], 15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 14 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f0b07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 11], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000400248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 1024], ymm1 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a7cb60f; BYTE $0x0d // movzx edi, byte [rdx + rcx + 13] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x010c12542051a3c4 // vpinsrb xmm2, xmm5, byte [rdx + r10 + 12], 1 - QUAD $0x020c02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 12], 2 - QUAD $0x030c0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 12], 3 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x040c02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 12], 4 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x050c0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 12], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x060c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 6 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x070c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 7 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x080c32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 12], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x090c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 9 - QUAD $0x000000b824948b4c // mov r10, qword [rsp + 184] - QUAD $0x0a0c12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 12], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b0c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 11 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0c0c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 12 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0d0c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 12], 13 - QUAD $0x0e0c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 12], 14 - QUAD $0x0f0c32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 12], 15 - QUAD $0x010c1a642049e3c4 // vpinsrb xmm4, xmm6, byte [rdx + rbx + 12], 1 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x020c3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 12], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x030c3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 12], 3 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x040c1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 12], 4 - QUAD $0x050c02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 12], 5 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x060c32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 12], 6 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x070c22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 12], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x080c02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 12], 8 - QUAD $0x090c2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 12], 9 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0a0c1a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r11 + 12], 10 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x0b0c1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 12], 11 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0c0c1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 12], 12 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0d0c2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 12], 13 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0e0c1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 12], 14 - LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] - QUAD $0x0f0c2a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 12], 15 - QUAD $0x010d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x020d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x030d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 3 - QUAD $0x040d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 4 - QUAD $0x050d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x060d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 6 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x070d0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 13], 7 - QUAD $0x080d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 13], 8 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0d // movzx eax, byte [rdi + rax + 13] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x010c37542051a3c4 // vpinsrb xmm2, xmm5, byte [rdi + r14 + 12], 1 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x020c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 12], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x030c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x040c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 4 + QUAD $0x050c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x060c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 6 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x070c07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 12], 7 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x080c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 12], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x090c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 9 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0a0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 10 + QUAD $0x0b0c0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 12], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 12 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0d0c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 12], 13 + QUAD $0x0e0c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 12], 14 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0f0c1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 12], 15 + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x010c1f642049a3c4 // vpinsrb xmm4, xmm6, byte [rdi + r11 + 12], 1 + QUAD $0x020c17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 12], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x030c07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 12], 3 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x040c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 4 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x050c17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 12], 5 + QUAD $0x060c27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 12], 6 + QUAD $0x070c3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 12], 7 QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x090d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 9 - QUAD $0x0a0d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 13], 10 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0b0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 11 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x0c0d1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 13], 12 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x0d0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 13 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0e0d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 13], 14 - QUAD $0x000000f824848b4c // mov r8, qword [rsp + 248] - QUAD $0x0f0d025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 13], 15 - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - QUAD $0x010d124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 13], 1 - QUAD $0x020d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 2 - QUAD $0x030d3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 13], 3 + QUAD $0x080c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 8 + QUAD $0x090c0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 12], 9 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + QUAD $0x0a0c0f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 12], 10 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x0b0c0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 12], 11 + QUAD $0x0000012024bc8b4c // mov r15, qword [rsp + 288] + QUAD $0x0c0c3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 12], 12 + QUAD $0x0d0c2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 12], 13 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x0e0c3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 12], 14 + QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] + QUAD $0x0f0c2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 12], 15 + QUAD $0x010d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 1 + QUAD $0x020d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 2 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x030d375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 13], 3 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x040d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 4 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x050d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 5 LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x040d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 4 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x050d324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 13], 5 - QUAD $0x060d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 6 - QUAD $0x070d224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 13], 7 - QUAD $0x080d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 8 - QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] - QUAD $0x090d324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 13], 9 - QUAD $0x0a0d1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 13], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0d024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 13], 13 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0e0d3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 13], 14 + QUAD $0x060d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 6 + QUAD $0x070d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 7 + QUAD $0x080d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 8 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x090d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 13], 9 + QUAD $0x000000f024948b48 // mov rdx, qword [rsp + 240] + QUAD $0x0a0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 10 + QUAD $0x000000c824948b48 // mov rdx, qword [rsp + 200] + QUAD $0x0b0d175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 13], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 12 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x0d0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 13 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x0e0d375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 13], 14 + QUAD $0x0f0d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 13], 15 + QUAD $0x010d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 1 + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] + QUAD $0x020d374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 13], 2 + QUAD $0x030d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x040d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 4 + QUAD $0x050d174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 13], 5 + QUAD $0x060d274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 13], 6 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x070d1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 13], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x080d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 8 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x090d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 9 + QUAD $0x0a0d0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 13], 10 + QUAD $0x0b0d0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 13], 11 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d0d074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 13], 13 + QUAD $0x0e0d3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 13], 14 LONG $0x385de3c4; WORD $0x01d2 // vinserti128 ymm2, ymm4, xmm2, 1 QUAD $0x0003e024947ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 992], ymm2 - QUAD $0x0f0d2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 13], 15 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x0e // movzx edi, byte [rdx + rax + 14] - LONG $0xd76ef9c5 // vmovd xmm2, edi + QUAD $0x0f0d2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 13], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xd06ef9c5 // vmovd xmm2, eax LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x0003c0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 960], ymm1 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x0e // movzx edi, byte [rdx + rax + 14] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] - QUAD $0x010e32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 14], 1 - QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] - QUAD $0x020e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 2 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x030e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x040e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 4 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x0e // movzx eax, byte [rdi + rax + 14] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x010e07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 14], 1 + QUAD $0x000000b824bc8b4c // mov r15, qword [rsp + 184] + QUAD $0x020e3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 14], 2 + QUAD $0x030e37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 14], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x040e07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 14], 4 + QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] + QUAD $0x050e0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 14], 5 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x060e17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 14], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x070e07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 14], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x080e07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 14], 8 + QUAD $0x090e07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 14], 9 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x0a0e0f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 14], 10 + QUAD $0x0b0e17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 14], 11 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0c0e37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 14], 12 + QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] + QUAD $0x0d0e27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 14], 13 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x0e0e07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 14], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f0e07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 14], 15 QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x050e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 5 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x060e1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 14], 6 - QUAD $0x070e0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 14], 7 + QUAD $0x010e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x020e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x030e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 3 + QUAD $0x0000010824b48b4c // mov r14, qword [rsp + 264] + QUAD $0x040e374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 14], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x050e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 5 + QUAD $0x000000a824948b48 // mov rdx, qword [rsp + 168] + QUAD $0x060e174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 14], 6 + QUAD $0x070e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 7 + QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] + QUAD $0x080e1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 14], 8 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x090e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 10 + QUAD $0x0b0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 11 + QUAD $0x00000120249c8b48 // mov rbx, qword [rsp + 288] + QUAD $0x0c0e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 14], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 14], 14 + QUAD $0x0f0e2f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 14], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x0f // movzx eax, byte [rdi + rax + 15] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x010f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 1 + QUAD $0x020f3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 15], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x030f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x040f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 4 + QUAD $0x050f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 5 + QUAD $0x060f175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 15], 6 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x070f3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 15], 7 QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x080e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 8 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x090e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 9 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0a0e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 10 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0b0e02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 14], 11 - QUAD $0x0c0e1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 14], 12 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x0d0e2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 14], 13 - QUAD $0x0e0e0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 14], 14 - QUAD $0x0f0e02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 14], 15 - QUAD $0x010e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 14], 1 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x020e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x030e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 3 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x040e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x050e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 5 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x060e224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 14], 6 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x070e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x080e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 8 - QUAD $0x090e324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 14], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a0e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b0e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 11 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0c0e324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 14], 12 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0d0e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 14], 13 - QUAD $0x0e0e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 14], 14 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x0f0e024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 14], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a7cb60f; BYTE $0x0f // movzx edi, byte [rdx + rcx + 15] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x010f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 1 - QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] - QUAD $0x020f125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 15], 2 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x030f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 3 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x040f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 4 + QUAD $0x080f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x090f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 9 + QUAD $0x0a0f0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 15], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b0f075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 15], 11 + QUAD $0x0c0f375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 15], 12 + QUAD $0x0d0f275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 15], 13 + QUAD $0x0e0f075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 15], 14 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + QUAD $0x0f0f0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 15], 15 + QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] + LONG $0x44b60f42; WORD $0x0f17 // movzx eax, byte [rdi + r10 + 15] + LONG $0xe06ef9c5 // vmovd xmm4, eax QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x050f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 5 - QUAD $0x060f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 6 - QUAD $0x070f0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 15], 7 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x080f1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 15], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x090f3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 15], 9 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x0a0f325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 15], 10 - QUAD $0x0b0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 11 - QUAD $0x0c0f1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 15], 12 - QUAD $0x0d0f2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 15], 13 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0e0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 14 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0f0f025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 15], 15 - QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] - LONG $0x327cb60f; BYTE $0x0f // movzx edi, byte [rdx + rsi + 15] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x010f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x020f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 2 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x030f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 3 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x040f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x050f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 5 - QUAD $0x060f22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 15], 6 + QUAD $0x010f37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 15], 1 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x070f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 15], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x080f3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 15], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x090f3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 15], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a0f3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 15], 10 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x0b0f3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 15], 11 - QUAD $0x0c0f32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 15], 12 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0d0f0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 15], 13 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0e0f3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 15], 14 - QUAD $0x0f0f02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 15], 15 + QUAD $0x020f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x030f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 3 + QUAD $0x040f37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 15], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x050f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 5 + QUAD $0x060f17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 15], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x070f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 7 + QUAD $0x080f1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 15], 8 + QUAD $0x000000d824b48b4c // mov r14, qword [rsp + 216] + QUAD $0x090f37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 15], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a0f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 15], 10 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0b0f27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 15], 11 + QUAD $0x0c0f1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 15], 12 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x0d0f1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 15], 13 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0e0f1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 15], 14 + QUAD $0x0f0f2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 15], 15 LONG $0x3875e3c4; WORD $0x01ca // vinserti128 ymm1, ymm1, xmm2, 1 QUAD $0x000380248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 896], ymm1 LONG $0x385de3c4; WORD $0x01cb // vinserti128 ymm1, ymm4, xmm3, 1 QUAD $0x0003a0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 928], ymm1 - LONG $0x0a7cb60f; BYTE $0x10 // movzx edi, byte [rdx + rcx + 16] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x01100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 1 - QUAD $0x0210124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 16], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x04100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 4 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x05100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 6 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x07100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 7 - QUAD $0x08101a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 16], 8 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x09100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 9 - QUAD $0x000000b824a48b4c // mov r12, qword [rsp + 184] - QUAD $0x0a10224c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r12 + 16], 10 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0b100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 11 - QUAD $0x0c101a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 16], 12 - QUAD $0x0d102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 13 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x0e102a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 16], 14 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x0f100a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 16], 15 - LONG $0x327cb60f; BYTE $0x10 // movzx edi, byte [rdx + rsi + 16] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x01100a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 16], 1 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x02101a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 16], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x03100a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 16], 3 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x04100a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 16], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x05100a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 16], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x06100a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 16], 6 - QUAD $0x071002542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 16], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x081002542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 16], 8 - QUAD $0x000000d824b48b48 // mov rsi, qword [rsp + 216] - QUAD $0x091032542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 16], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1002542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 16], 10 - QUAD $0x0b103a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 16], 11 - QUAD $0x0c1032542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 16], 12 - QUAD $0x0d100a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 16], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e1002542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 16], 14 - QUAD $0x0f1002542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 16], 15 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x1102 // movzx edi, byte [rdx + r8 + 17] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0111025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 1 - QUAD $0x0211125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 17], 2 - QUAD $0x000000a8249c8b4c // mov r11, qword [rsp + 168] - QUAD $0x03111a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 17], 3 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x04110a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 17], 4 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x0511025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 5 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x10 // movzx eax, byte [rdi + rax + 16] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0110174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 16], 1 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x02102f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 16], 2 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x03100f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 16], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0410074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0510074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0610074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 6 + QUAD $0x07103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 7 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x08103f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 16], 8 QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x0611025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 6 + QUAD $0x0910074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 9 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0a10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 12 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x0d10074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 16], 13 LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x0711025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 7 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0811025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 8 + QUAD $0x0e10074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 16], 14 + QUAD $0x0f100f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 16], 15 + LONG $0x44b60f42; WORD $0x1017 // movzx eax, byte [rdi + r10 + 16] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011037542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 16], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x021007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 2 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x03100f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 16], 3 + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x041037542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 16], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x071007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 8 + QUAD $0x091037542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 16], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 10 + QUAD $0x0b1027542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 16], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 12 + QUAD $0x0d101f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 16], 13 + QUAD $0x0e101f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 16], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f1007542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 16], 15 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + LONG $0x1f44b60f; BYTE $0x11 // movzx eax, byte [rdi + rbx + 17] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0111175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 1 + WORD $0x894d; BYTE $0xee // mov r14, r13 + QUAD $0x02112f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 17], 2 + QUAD $0x03110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 3 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x04110f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 17], 4 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x05112f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 17], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0611075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0711075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 7 + QUAD $0x08113f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 17], 8 + QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] + QUAD $0x0911175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 17], 9 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0a11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 10 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x0b11175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 17], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c11075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 17], 12 + QUAD $0x0d11075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 17], 13 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0e11275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 17], 14 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x0f111f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 17], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x11 // movzx eax, byte [rdi + rax + 17] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x01113f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 17], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x021107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 2 + QUAD $0x03110f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 17], 3 + QUAD $0x041137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 17], 4 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x051107642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 17], 5 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x06110f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 17], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x071107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 7 QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0911025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 9 - QUAD $0x0a11225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 17], 10 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x0b11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 11 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0c11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 12 - QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] - QUAD $0x0d11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 13 - QUAD $0x0e112a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 17], 14 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0f11025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 17], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x11 // movzx edi, byte [rdx + rdi + 17] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x01113a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 17], 1 - QUAD $0x02111a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 17], 2 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x03111a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 17], 3 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x04113a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 17], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05113a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 17], 5 - QUAD $0x06110a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 17], 6 - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - QUAD $0x071132642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 17], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x08110a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 17], 8 - QUAD $0x091132642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 17], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a1132642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 17], 10 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0b1122642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 17], 11 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x0c112a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 17], 12 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0d1132642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 17], 13 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0e113a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 17], 14 + QUAD $0x081107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 8 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x091107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0a1137642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 17], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b1107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d1107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e1107642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 17], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000360248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 864], ymm1 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x0f11324c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdx + rsi + 17], 15 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f11074c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdi + rax + 17], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x000340248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 832], ymm1 - LONG $0x7cb60f42; WORD $0x1202 // movzx edi, byte [rdx + r8 + 18] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x01123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 1 - QUAD $0x0212124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 18], 2 - QUAD $0x03121a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 18], 3 - QUAD $0x04120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 4 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x05121a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 18], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x07123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 7 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x08120a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 18], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x09123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 9 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x0a123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 11 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0c123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 12 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0d123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 13 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0e123a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 18], 14 - QUAD $0x0f12024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 18], 15 - QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] - LONG $0x027cb60f; BYTE $0x12 // movzx edi, byte [rdx + rax + 18] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x01123a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 18], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x021202542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 18], 2 - QUAD $0x03121a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 18], 3 + LONG $0x1f44b60f; BYTE $0x12 // movzx eax, byte [rdi + rbx + 18] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0112074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 1 + QUAD $0x0212374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 2 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x03121f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 18], 3 + QUAD $0x04120f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 18], 4 + QUAD $0x05122f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 18], 5 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x041202542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 18], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x051202542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 18], 5 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x06121a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 18], 6 - QUAD $0x071232542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 18], 7 - QUAD $0x08120a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 18], 8 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x091202542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 18], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0a123a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 18], 10 - QUAD $0x0b1222542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 18], 11 - QUAD $0x0c122a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 18], 12 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0d1232542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 18], 13 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x0e1202542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 18], 14 - QUAD $0x0f1232542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 18], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a7cb60f; BYTE $0x13 // movzx edi, byte [rdx + rcx + 19] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] - QUAD $0x0113125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 19], 1 - QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] - QUAD $0x0213325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 19], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x03133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 4 - QUAD $0x05131a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 19], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x06133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 6 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x07131a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 19], 7 - QUAD $0x08130a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 19], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x09133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 9 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x0a133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 10 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x0b130a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 19], 11 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0c133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 12 - QUAD $0x000000e824ac8b4c // mov r13, qword [rsp + 232] - QUAD $0x0d132a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 19], 13 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0e133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 14 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x0f133a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 19], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x13 // movzx edi, byte [rdx + rdi + 19] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x01133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 1 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x02133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x03133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 3 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x041322642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 19], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 5 - QUAD $0x06131a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 19], 6 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x07133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x08133a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 19], 8 - QUAD $0x091302642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 19], 9 - QUAD $0x0a133a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 19], 10 + QUAD $0x0612074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0712074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0812074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 8 + QUAD $0x0912174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 18], 9 + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x0a12374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 18], 10 + QUAD $0x0b12174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 18], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 12 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0d12074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 18], 13 + QUAD $0x0e12274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 18], 14 + QUAD $0x0f121f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 18], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x12 // movzx eax, byte [rdi + rax + 18] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x01123f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 18], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x021207542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 18], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031207542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 18], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x041207542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 18], 4 + QUAD $0x051207542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 18], 5 + QUAD $0x06120f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 18], 6 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x07120f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 18], 7 + QUAD $0x0000014024948b4c // mov r10, qword [rsp + 320] + QUAD $0x081217542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 18], 8 + QUAD $0x000000d8249c8b4c // mov r11, qword [rsp + 216] + QUAD $0x09121f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 18], 9 + QUAD $0x0a1237542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 18], 10 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0b1227542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 18], 11 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0c120f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 18], 12 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0d1237542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 18], 13 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1302642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 19], 11 + QUAD $0x0e1207542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 18], 14 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x0f1217542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 18], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0113075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 1 + QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] + QUAD $0x02132f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 19], 2 + QUAD $0x03131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 3 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x04133f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 19], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0513075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0613075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 6 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0713075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 19], 7 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x08131f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 19], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0913075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 9 + QUAD $0x0a13375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 19], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 12 + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + QUAD $0x0d13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f13075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 19], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x13 // movzx eax, byte [rdi + rax + 19] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x011307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x021307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x041307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 4 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c1302642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 19], 12 - QUAD $0x0d1332642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 19], 13 - QUAD $0x0e1302642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 19], 14 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0f1302642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 19], 15 + QUAD $0x051307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 6 + QUAD $0x07130f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 19], 7 + QUAD $0x081317642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 19], 8 + QUAD $0x09131f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 19], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1307642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 19], 10 + QUAD $0x0b1327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 19], 11 + QUAD $0x0c130f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 19], 12 + QUAD $0x0d1337642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 19], 13 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0e1327642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 19], 14 + QUAD $0x0f1317642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 19], 15 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000300248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 768], ymm1 LONG $0x385de3c4; WORD $0x01cb // vinserti128 ymm1, ymm4, xmm3, 1 QUAD $0x000320248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 800], ymm1 - LONG $0x0a7cb60f; BYTE $0x14 // movzx edi, byte [rdx + rcx + 20] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x0114124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 1 - QUAD $0x0214324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 2 - QUAD $0x000000a824948b4c // mov r10, qword [rsp + 168] - QUAD $0x0314124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 20], 3 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x04143a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 20], 4 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x0514324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 20], 5 - QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] - QUAD $0x0614024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 20], 6 - QUAD $0x07141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 7 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0814024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 20], 8 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x09141a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 20], 9 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0a14024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 20], 10 - QUAD $0x0b140a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 20], 11 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0c14024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 20], 12 - QUAD $0x0d142a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 20], 13 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0e14024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 20], 14 QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x0f141a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 20], 15 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a7cb60f; BYTE $0x14 // movzx edi, byte [rdx + rcx + 20] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x01140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 1 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x02140a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 20], 2 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x03140a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 20], 3 - QUAD $0x041422542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 20], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 6 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x07143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 7 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x081432542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 20], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x09143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 11 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0c143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 12 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0d143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 13 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0e143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 14 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0f143a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 20], 15 - QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x1522 // movzx edi, byte [rdx + r12 + 21] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x01153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x02153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 2 - QUAD $0x0315125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 21], 3 - QUAD $0x04153a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 21], 4 - QUAD $0x0515325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 5 - QUAD $0x0615025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 21], 6 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x07152a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 21], 7 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x08153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 8 - QUAD $0x09151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 9 - QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] - QUAD $0x0a15325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 21], 10 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0b153a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r15 + 21], 11 - QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] - QUAD $0x0c151a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 21], 12 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0d153a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 21], 13 - QUAD $0x0e15025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 21], 14 - QUAD $0x0f151a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 21], 15 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x151a // movzx edi, byte [rdx + r11 + 21] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x011502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 1 - QUAD $0x02150a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 21], 2 - QUAD $0x03150a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 21], 3 + LONG $0x44b60f42; WORD $0x141f // movzx eax, byte [rdi + r11 + 20] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0114374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 20], 1 + QUAD $0x02142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0314074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 3 + QUAD $0x04143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 4 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x05142f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 20], 5 LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x041502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 4 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x051512642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 21], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 6 + QUAD $0x0614074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 20], 6 + QUAD $0x0714074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 7 + QUAD $0x08141f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 20], 8 + QUAD $0x0000009824848b4c // mov r8, qword [rsp + 152] + QUAD $0x0914074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 20], 9 + QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + QUAD $0x0a14174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 20], 10 + QUAD $0x000000c824b48b48 // mov rsi, qword [rsp + 200] + QUAD $0x0b14374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 20], 11 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x0c140f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 20], 12 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x0d140f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 20], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e14174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 20], 14 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x0f143f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 20], 15 + QUAD $0x00000100249c8b48 // mov rbx, qword [rsp + 256] + LONG $0x1f44b60f; BYTE $0x14 // movzx eax, byte [rdi + rbx + 20] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x011407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 1 QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x071502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 7 - QUAD $0x081532642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 21], 8 + QUAD $0x021407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x041407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x071407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 8 QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x091502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 9 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0a1502642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 21], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 11 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0c1532642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 21], 12 + QUAD $0x091407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b1407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d1407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 13 + QUAD $0x0e1427542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 20], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f1407542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 20], 15 + LONG $0x44b60f42; WORD $0x151f // movzx eax, byte [rdi + r11 + 21] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x0115375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0215075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 2 + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x0315375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 21], 3 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 13 + QUAD $0x0415075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 4 + QUAD $0x05152f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 21], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0615075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 6 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e1502642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 21], 14 + QUAD $0x0715075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0815075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 21], 8 + QUAD $0x0915075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 21], 9 + QUAD $0x0a15175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 21], 10 + QUAD $0x0b15375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 21], 11 + QUAD $0x0c150f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 21], 12 + WORD $0x894d; BYTE $0xc8 // mov r8, r9 + QUAD $0x0d150f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 21], 13 + QUAD $0x0e15175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 21], 14 + QUAD $0x0f153f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 21], 15 + LONG $0x1f44b60f; BYTE $0x15 // movzx eax, byte [rdi + rbx + 21] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x011517642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 21], 1 + QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] + QUAD $0x02150f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 21], 2 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x031537642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 21], 3 + QUAD $0x0000010824948b48 // mov rdx, qword [rsp + 264] + QUAD $0x041517642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 21], 4 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x05151f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 21], 5 + QUAD $0x000000a8248c8b4c // mov r9, qword [rsp + 168] + QUAD $0x06150f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 21], 6 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x071527642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 21], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 8 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x091507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 9 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x0a153f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 21], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 13 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e1507642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 21], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x0002c0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 704], ymm1 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0f150a4c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdx + rcx + 21], 15 + QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] + QUAD $0x0f151f4c2059a3c4 // vpinsrb xmm1, xmm4, byte [rdi + r11 + 21], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x0002e0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 736], ymm1 - LONG $0x7cb60f42; WORD $0x1622 // movzx edi, byte [rdx + r12 + 22] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x01160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 2 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - QUAD $0x03160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x04160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 4 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x05160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 5 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x06160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 6 - QUAD $0x07162a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 22], 7 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x08160a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 22], 8 - QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] - QUAD $0x09160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 9 - QUAD $0x0a16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 10 - QUAD $0x0b163a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 22], 11 - QUAD $0x0c161a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 22], 12 - QUAD $0x000000e824b48b48 // mov rsi, qword [rsp + 232] - QUAD $0x0d16324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 22], 13 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0e160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 14 - QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] - QUAD $0x0f160a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 22], 15 - LONG $0x7cb60f42; WORD $0x161a // movzx edi, byte [rdx + r11 + 22] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x01161a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 22], 1 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x02163a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 22], 2 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x03163a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 22], 3 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0116074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0216074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 2 + QUAD $0x0316374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 22], 3 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0416374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 22], 4 + QUAD $0x05162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 5 LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x04162a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 22], 4 - QUAD $0x051612542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 22], 5 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x061622542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 22], 6 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x07163a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 22], 7 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x08163a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 22], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x09163a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 22], 9 - QUAD $0x0a1602542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 22], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b163a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 22], 11 - QUAD $0x0c1632542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 22], 12 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0d163a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 22], 13 - QUAD $0x0e1602542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 22], 14 + QUAD $0x06162f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r13 + 22], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0716074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x0816074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0916074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 9 + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + QUAD $0x0a16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 11 + QUAD $0x0c16074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 12 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x0d16074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 22], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f16074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 22], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x16 // movzx eax, byte [rdi + rax + 22] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011617542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 22], 1 + QUAD $0x02160f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 22], 2 + QUAD $0x031637542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 22], 3 + QUAD $0x041617542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 22], 4 + QUAD $0x05161f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 22], 5 + QUAD $0x06160f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 22], 6 + QUAD $0x071627542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 22], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081607542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 22], 8 + QUAD $0x000000d8249c8b48 // mov rbx, qword [rsp + 216] + QUAD $0x09161f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 22], 9 + QUAD $0x0a163f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 22], 10 LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0f1602542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 22], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a7cb60f; BYTE $0x17 // movzx edi, byte [rdx + rdi + 23] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x01173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 1 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] - QUAD $0x0217025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 23], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x03173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x04173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 4 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x0517125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 23], 5 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x06171a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 23], 6 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x0717325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 23], 7 - QUAD $0x08170a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 23], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x09173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 9 - QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] - QUAD $0x0a170a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 23], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 11 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0c173a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 23], 12 - QUAD $0x0d17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 13 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0e17325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 23], 14 - QUAD $0x0f170a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 23], 15 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a7cb60f; BYTE $0x17 // movzx edi, byte [rdx + rcx + 23] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x01171a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 23], 1 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x02170a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 23], 2 - QUAD $0x03173a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 23], 3 - QUAD $0x04172a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 23], 4 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x051732642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 23], 5 - QUAD $0x061722642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 23], 6 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x07173a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 23], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x08170a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 23], 8 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x091722642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 23], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a170a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 23], 10 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0b172a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r13 + 23], 11 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0c170a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 23], 12 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0d170a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 23], 13 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0e173a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 23], 14 - QUAD $0x0f1702642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 23], 15 + QUAD $0x0b1607542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 22], 11 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x0c160f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 22], 12 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0d1627542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 22], 13 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x0e163f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 22], 14 + QUAD $0x0f161f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 22], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0117075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 1 + QUAD $0x000000b824b48b48 // mov rsi, qword [rsp + 184] + QUAD $0x0217375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 23], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x0317075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 3 + QUAD $0x0417375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 23], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0517075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 5 + QUAD $0x06172f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 23], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0717075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 7 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x08170f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 23], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0917075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 9 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x0a171f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 23], 10 + QUAD $0x000000c824948b4c // mov r10, qword [rsp + 200] + QUAD $0x0b17175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 23], 11 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0c17175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 23], 12 + QUAD $0x0d17075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 23], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f17075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 23], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x17 // movzx eax, byte [rdi + rax + 23] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x011707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x021707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 2 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x031707642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 23], 3 + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x04172f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 23], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x071707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 8 + QUAD $0x09171f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 23], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b1707642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 23], 11 + QUAD $0x0c170f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 23], 12 + QUAD $0x0d1727642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 23], 13 + QUAD $0x0e173f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 23], 14 + QUAD $0x000000e824a48b4c // mov r12, qword [rsp + 232] + QUAD $0x0f1727642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 23], 15 LONG $0x386d63c4; WORD $0x01d9 // vinserti128 ymm11, ymm2, xmm1, 1 LONG $0x385d63c4; WORD $0x01e3 // vinserti128 ymm12, ymm4, xmm3, 1 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0118074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 1 + QUAD $0x0218374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 24], 2 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x03181f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 24], 3 + QUAD $0x0418374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0518074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 5 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0618374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 24], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0718074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 7 + QUAD $0x08180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0918074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 9 + QUAD $0x0a181f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 24], 10 + QUAD $0x0b18174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 24], 11 + QUAD $0x0c18174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 24], 12 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x0d180f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 24], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f18074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 24], 15 QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x18 // movzx edi, byte [rdx + rax + 24] - LONG $0xcf6ef9c5 // vmovd xmm1, edi + LONG $0x0744b60f; BYTE $0x18 // movzx eax, byte [rdi + rax + 24] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x011807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 1 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x02183f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 24], 2 + QUAD $0x031807542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 24], 3 + QUAD $0x04182f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 24], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 5 + QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] + QUAD $0x061837542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 24], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x071807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 7 + QUAD $0x00000140248c8b48 // mov rcx, qword [rsp + 320] + QUAD $0x08180f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rcx + 24], 8 + QUAD $0x000000d824848b4c // mov r8, qword [rsp + 216] + QUAD $0x091807542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 24], 9 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0a1817542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 24], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b1807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d1807542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 24], 13 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0e1817542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 24], 14 + QUAD $0x0f1827542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 24], 15 + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x0119075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x0219075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 2 + QUAD $0x03191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0419075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x0519075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 5 + QUAD $0x0619375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 25], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0719075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 7 + QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] + QUAD $0x08191f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 25], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x0919075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 9 + QUAD $0x0a191f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 25], 10 QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] - QUAD $0x0118024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 1 - QUAD $0x0218024c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r8 + 24], 2 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x0318024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 3 + QUAD $0x0b19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 12 + QUAD $0x0d190f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 25], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e19075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 25], 14 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0f19275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 25], 15 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + LONG $0x0744b60f; BYTE $0x19 // movzx eax, byte [rdi + rax + 25] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x011937642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 25], 1 + QUAD $0x02193f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 25], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 3 + QUAD $0x04192f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 25], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 5 + QUAD $0x061937642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 25], 6 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0418024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 4 - QUAD $0x0518124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 24], 5 - QUAD $0x06181a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 24], 6 - QUAD $0x0718324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 24], 7 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0818024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 24], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x09183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 9 - QUAD $0x0a180a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 24], 10 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x0b181a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 24], 11 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0c183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 12 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0d183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 13 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0e183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 14 - QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] - QUAD $0x0f183a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 24], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x18 // movzx edi, byte [rdx + rdi + 24] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x01181a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 24], 1 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x02183a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 24], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x03183a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 24], 3 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x04183a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 24], 4 - QUAD $0x051832542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 24], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061832542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 24], 6 - QUAD $0x07183a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 24], 7 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x081832542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 24], 8 - QUAD $0x091822542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 24], 9 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0a1802542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 24], 10 - QUAD $0x0b182a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 24], 11 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0c1832542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 24], 12 - QUAD $0x0d180a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 24], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e180a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 24], 14 + QUAD $0x071907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 7 + QUAD $0x08190f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rcx + 25], 8 + QUAD $0x091907642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r8 + 25], 9 + QUAD $0x0a1917642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 25], 10 LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0f1812542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 24], 15 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x0a7cb60f; BYTE $0x19 // movzx edi, byte [rdx + rcx + 25] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c8248c8b4c // mov r9, qword [rsp + 200] - QUAD $0x01190a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 25], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x02190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 2 - QUAD $0x000000a824ac8b4c // mov r13, qword [rsp + 168] - QUAD $0x03192a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 25], 3 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x04190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 4 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x05190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 5 - QUAD $0x0000009824b48b48 // mov rsi, qword [rsp + 152] - QUAD $0x0619325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 25], 6 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x07190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 7 - QUAD $0x0819025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 8 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x0919025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 9 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0a19025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 10 - QUAD $0x0b191a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 25], 11 - QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] - QUAD $0x0c19025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 25], 12 - QUAD $0x000000e8248c8b48 // mov rcx, qword [rsp + 232] - QUAD $0x0d190a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 25], 13 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0e193a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 25], 14 - QUAD $0x000000f8249c8b4c // mov r11, qword [rsp + 248] - QUAD $0x0f191a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 25], 15 - QUAD $0x000000f024bc8b48 // mov rdi, qword [rsp + 240] - LONG $0x3a7cb60f; BYTE $0x19 // movzx edi, byte [rdx + rdi + 25] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x01191a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 25], 1 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x02193a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 25], 2 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x03193a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 25], 3 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x04193a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 25], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x05193a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 25], 5 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x06193a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 25], 6 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x07193a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 25], 7 - QUAD $0x081932642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 25], 8 - QUAD $0x091922642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 25], 9 - QUAD $0x0a1902642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 25], 10 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x0b1922642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 25], 11 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0c193a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 25], 12 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0d1932642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 25], 13 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0e191a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 25], 14 + QUAD $0x0b1917642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 25], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d1907642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 25], 13 + QUAD $0x0e1917642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 25], 14 LONG $0x386d63c4; WORD $0x01d1 // vinserti128 ymm10, ymm2, xmm1, 1 - QUAD $0x0f19124c2059a3c4 // vpinsrb xmm1, xmm4, byte [rdx + r10 + 25], 15 + QUAD $0x000000e824848b4c // mov r8, qword [rsp + 232] + QUAD $0x0f19074c2059a3c4 // vpinsrb xmm1, xmm4, byte [rdi + r8 + 25], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x0001a0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 416], ymm1 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a7cb60f; BYTE $0x1a // movzx edi, byte [rdx + rdi + 26] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x011a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 1 - QUAD $0x000000e024bc8b48 // mov rdi, qword [rsp + 224] - QUAD $0x021a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 2 - QUAD $0x031a2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 26], 3 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - QUAD $0x041a0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 26], 4 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x051a3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 26], 5 - QUAD $0x061a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 6 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x071a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 7 - QUAD $0x000000c024b48b48 // mov rsi, qword [rsp + 192] - QUAD $0x081a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 8 - QUAD $0x0000014024b48b48 // mov rsi, qword [rsp + 320] - QUAD $0x091a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 9 - QUAD $0x000000b824ac8b4c // mov r13, qword [rsp + 184] - QUAD $0x0a1a2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 26], 10 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0b1a324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 26], 11 - QUAD $0x0c1a024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 26], 12 - QUAD $0x0d1a0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 26], 13 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0e1a0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 26], 14 - WORD $0x894c; BYTE $0xde // mov rsi, r11 - QUAD $0x0f1a1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 26], 15 - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - LONG $0x7cb60f42; WORD $0x1a1a // movzx edi, byte [rdx + r11 + 26] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] - QUAD $0x011a0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 26], 1 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x021a02542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r8 + 26], 2 - QUAD $0x031a3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 26], 3 - LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] - QUAD $0x041a12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 26], 4 - QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] - QUAD $0x051a0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 26], 5 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x061a0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 26], 6 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x071a3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 26], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x081a0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 26], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x091a3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 26], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0a1a3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 26], 10 - QUAD $0x0b1a22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 26], 11 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0c1a3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 26], 12 - QUAD $0x0d1a32542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r14 + 26], 13 - QUAD $0x0e1a1a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rbx + 26], 14 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0f1a3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 26], 15 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - LONG $0x3a7cb60f; BYTE $0x1b // movzx edi, byte [rdx + rdi + 27] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x000000c824bc8b48 // mov rdi, qword [rsp + 200] - QUAD $0x011b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 1 - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] - QUAD $0x021b325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 27], 2 - QUAD $0x000000a824bc8b48 // mov rdi, qword [rsp + 168] - QUAD $0x031b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 3 - QUAD $0x041b0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 27], 4 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x051b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 5 - QUAD $0x0000009824bc8b48 // mov rdi, qword [rsp + 152] - QUAD $0x061b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x071b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 7 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x081b0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 27], 8 - QUAD $0x00000140249c8b48 // mov rbx, qword [rsp + 320] - QUAD $0x091b1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 27], 9 - QUAD $0x0a1b2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 27], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b1b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 11 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0c1b3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 27], 12 - QUAD $0x0d1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 13 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + LONG $0x0f44b60f; BYTE $0x1a // movzx eax, byte [rdi + rcx + 26] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x011a174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 26], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 2 + QUAD $0x000000e024b48b48 // mov rsi, qword [rsp + 224] + QUAD $0x031a374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 26], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x041a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x051a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x061a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x071a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 7 + QUAD $0x081a1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 26], 8 + QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] + QUAD $0x091a0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 26], 9 + QUAD $0x0a1a1f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r11 + 26], 10 + QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] + QUAD $0x0b1a3f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r15 + 26], 11 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0e1b025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 27], 14 - QUAD $0x0f1b325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 27], 15 - LONG $0x7cb60f42; WORD $0x1b1a // movzx edi, byte [rdx + r11 + 27] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x011b32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 27], 1 - QUAD $0x021b02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 27], 2 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x031b32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 27], 3 - QUAD $0x041b12642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r10 + 27], 4 - QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] - QUAD $0x051b32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 27], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x061b32642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rsi + 27], 6 - QUAD $0x071b3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 27], 7 - QUAD $0x081b0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 27], 8 - QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] - QUAD $0x091b22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 27], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0a1b3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 27], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b1b0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 27], 11 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0c1b0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 27], 12 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x0d1b0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 27], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e1b0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 27], 14 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0f1b0a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rcx + 27], 15 - LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 - QUAD $0x000240248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm1 - LONG $0x385de3c4; WORD $0x01cb // vinserti128 ymm1, ymm4, xmm3, 1 - QUAD $0x000260248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm1 - QUAD $0x0000010024848b4c // mov r8, qword [rsp + 256] - LONG $0x7cb60f42; WORD $0x1c02 // movzx edi, byte [rdx + r8 + 28] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c8248c8b48 // mov rcx, qword [rsp + 200] - QUAD $0x011c0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 28], 1 - QUAD $0x021c324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 28], 2 - QUAD $0x000000a824b48b48 // mov rsi, qword [rsp + 168] - QUAD $0x031c324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 28], 3 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - QUAD $0x041c124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 28], 4 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x051c1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 28], 5 - QUAD $0x0000009824ac8b4c // mov r13, qword [rsp + 152] - QUAD $0x061c2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 28], 6 - LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] - QUAD $0x071c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 7 - QUAD $0x081c0a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r9 + 28], 8 - QUAD $0x091c1a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rbx + 28], 9 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x0a1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 10 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0b1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 11 - QUAD $0x0000010824bc8b48 // mov rdi, qword [rsp + 264] - QUAD $0x0c1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 12 - QUAD $0x000000e824bc8b48 // mov rdi, qword [rsp + 232] - QUAD $0x0d1c3a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rdi + 28], 13 - QUAD $0x0e1c024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 28], 14 - QUAD $0x000000f824b48b4c // mov r14, qword [rsp + 248] - QUAD $0x0f1c324c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r14 + 28], 15 - QUAD $0x000000f0249c8b48 // mov rbx, qword [rsp + 240] - LONG $0x1a7cb60f; BYTE $0x1c // movzx edi, byte [rdx + rbx + 28] - LONG $0xd76ef9c5 // vmovd xmm2, edi + QUAD $0x0c1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 12 QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x011c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x021c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 2 + QUAD $0x0d1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e1a074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 26], 14 + QUAD $0x0f1a274c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r12 + 26], 15 + QUAD $0x0000010024a48b4c // mov r12, qword [rsp + 256] + LONG $0x44b60f42; WORD $0x1a27 // movzx eax, byte [rdi + r12 + 26] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011a37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 26], 1 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + QUAD $0x021a1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 26], 2 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x031c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 3 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x041c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 4 + QUAD $0x031a07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 26], 3 + QUAD $0x041a2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 26], 4 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x051a07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 26], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061a07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 26], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x071a07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 26], 7 + QUAD $0x0000014024ac8b4c // mov r13, qword [rsp + 320] + QUAD $0x081a2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 26], 8 + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] + QUAD $0x091a07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 26], 9 + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + QUAD $0x0a1a1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 26], 10 + QUAD $0x0b1a17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 26], 11 QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x051c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x061c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 6 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x071c0a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r9 + 28], 7 + QUAD $0x0c1a07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 26], 12 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0d1a07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 26], 13 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x0e1a17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 26], 14 + QUAD $0x0f1a07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 26], 15 + LONG $0x0f44b60f; BYTE $0x1b // movzx eax, byte [rdi + rcx + 27] + LONG $0xd86ef9c5 // vmovd xmm3, eax + QUAD $0x011b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 2 + QUAD $0x031b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x041b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 4 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x051b0f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rcx + 27], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x061b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 6 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x071b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 7 + QUAD $0x000000c024848b4c // mov r8, qword [rsp + 192] + QUAD $0x081b075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 27], 8 + QUAD $0x091b0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 27], 9 + QUAD $0x000000f024b48b48 // mov rsi, qword [rsp + 240] + QUAD $0x0a1b375c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rsi + 27], 10 + QUAD $0x0b1b3f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r15 + 27], 11 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 12 + QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] + QUAD $0x0d1b375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 27], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x0e1b175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 27], 14 LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x081c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 8 - QUAD $0x091c22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 28], 9 - QUAD $0x0a1c3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 28], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 11 + QUAD $0x0f1b075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 27], 15 + LONG $0x44b60f42; WORD $0x1b27 // movzx eax, byte [rdi + r12 + 27] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x011b07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 27], 1 + QUAD $0x021b1f642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rbx + 27], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031b07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 27], 3 + QUAD $0x0000010824a48b4c // mov r12, qword [rsp + 264] + QUAD $0x041b27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 27], 4 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c1c02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 28], 12 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0d1c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 28], 13 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0e1c3a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rdi + 28], 14 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x0f1c22542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r12 + 28], 15 - LONG $0x7cb60f42; WORD $0x1d02 // movzx edi, byte [rdx + r8 + 29] - LONG $0xdf6ef9c5 // vmovd xmm3, edi - QUAD $0x011d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 1 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x021d0a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rcx + 29], 2 - QUAD $0x031d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 3 - QUAD $0x041d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 29], 4 - QUAD $0x051d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 5 - QUAD $0x061d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 6 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x071d325c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rsi + 29], 7 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x081d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 8 - QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] - QUAD $0x091d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 9 - QUAD $0x000000b824bc8b48 // mov rdi, qword [rsp + 184] - QUAD $0x0a1d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 10 - QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] - QUAD $0x0b1d2a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r13 + 29], 11 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x0c1d125c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r10 + 29], 12 - QUAD $0x000000e8249c8b4c // mov r11, qword [rsp + 232] - QUAD $0x0d1d1a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r11 + 29], 13 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0e1d3a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rdi + 29], 14 - QUAD $0x0f1d325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 29], 15 - LONG $0x1a7cb60f; BYTE $0x1d // movzx edi, byte [rdx + rbx + 29] - LONG $0xe76ef9c5 // vmovd xmm4, edi - QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] - QUAD $0x011d02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 29], 1 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x021d3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 29], 2 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x031d3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 29], 3 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x041d32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 29], 4 - QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] - QUAD $0x051d3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 29], 5 - QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] - QUAD $0x061d1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 29], 6 - QUAD $0x071d0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 29], 7 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x081d0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 29], 8 - QUAD $0x000000d824bc8b48 // mov rdi, qword [rsp + 216] - QUAD $0x091d3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 29], 9 - QUAD $0x0a1d3a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r15 + 29], 10 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x0b1d3a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rdi + 29], 11 - QUAD $0x0c1d02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 29], 12 + QUAD $0x051b07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 27], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061b07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 27], 6 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x071b07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 27], 7 + QUAD $0x081b2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 27], 8 + QUAD $0x000000d824bc8b4c // mov r15, qword [rsp + 216] + QUAD $0x091b3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 27], 9 + QUAD $0x0a1b1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 27], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b1b07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 27], 11 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x0c1b2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 27], 12 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x0d1b1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 27], 13 + QUAD $0x0e1b17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 27], 14 + QUAD $0x000000e824848b48 // mov rax, qword [rsp + 232] + QUAD $0x0f1b07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 27], 15 + LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 + QUAD $0x000240248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 576], ymm1 + LONG $0x385de3c4; WORD $0x01cb // vinserti128 ymm1, ymm4, xmm3, 1 + QUAD $0x000260248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 608], ymm1 + QUAD $0x000000f8249c8b48 // mov rbx, qword [rsp + 248] + LONG $0x1f44b60f; BYTE $0x1c // movzx eax, byte [rdi + rbx + 28] + LONG $0xc86ef9c5 // vmovd xmm1, eax + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x011c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 1 + QUAD $0x000000b8248c8b4c // mov r9, qword [rsp + 184] + QUAD $0x021c0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 28], 2 + QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + QUAD $0x031c174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 28], 3 LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1d02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 29], 13 + QUAD $0x041c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 4 + QUAD $0x051c0f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rcx + 28], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x061c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 6 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e1d02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 29], 14 + QUAD $0x071c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 7 + QUAD $0x081c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x091c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 9 + QUAD $0x0a1c374c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rsi + 28], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 11 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0c1c074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 28], 12 + QUAD $0x0d1c374c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r14 + 28], 13 + QUAD $0x0e1c174c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rdx + 28], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1c074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 28], 15 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f44b60f; BYTE $0x1c // movzx eax, byte [rdi + rcx + 28] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x011c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x021c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 3 + QUAD $0x041c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 28], 4 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x051c27542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r12 + 28], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 6 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x071c37542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r14 + 28], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081c07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 28], 8 + QUAD $0x091c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 28], 9 + QUAD $0x0000009024bc8b4c // mov r15, qword [rsp + 144] + QUAD $0x0a1c3f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r15 + 28], 10 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0b1c37542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rsi + 28], 11 + QUAD $0x0c1c2f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r13 + 28], 12 + QUAD $0x0d1c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 28], 13 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x0e1c1f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r11 + 28], 14 + QUAD $0x000000e824948b48 // mov rdx, qword [rsp + 232] + QUAD $0x0f1c17542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rdx + 28], 15 + LONG $0x1f44b60f; BYTE $0x1d // movzx eax, byte [rdi + rbx + 29] + LONG $0xd86ef9c5 // vmovd xmm3, eax + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x011d1f5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rbx + 29], 1 + QUAD $0x021d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 2 + QUAD $0x031d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x041d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x051d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x061d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 6 + LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] + QUAD $0x071d0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 29], 7 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x081d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x091d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 9 + QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + QUAD $0x0a1d175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 29], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 11 + QUAD $0x0c1d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 29], 12 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x0d1d075c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r8 + 29], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1d075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 29], 15 + LONG $0x0f44b60f; BYTE $0x1d // movzx eax, byte [rdi + rcx + 29] + LONG $0xe06ef9c5 // vmovd xmm4, eax + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x011d07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 29], 1 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x021d07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 29], 2 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x031d07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 29], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x041d07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 29], 4 + QUAD $0x051d27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 29], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061d07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 29], 6 + QUAD $0x071d37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 29], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081d07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 29], 8 + QUAD $0x000000d824a48b4c // mov r12, qword [rsp + 216] + QUAD $0x091d27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 29], 9 + QUAD $0x0a1d3f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r15 + 29], 10 + QUAD $0x0b1d37642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rsi + 29], 11 + QUAD $0x0c1d2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 29], 12 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0d1d2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 29], 13 + QUAD $0x0e1d1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 29], 14 LONG $0x386de3c4; WORD $0x01c9 // vinserti128 ymm1, ymm2, xmm1, 1 QUAD $0x000280248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 640], ymm1 - QUAD $0x0f1d224c2059a3c4 // vpinsrb xmm1, xmm4, byte [rdx + r12 + 29], 15 + QUAD $0x0f1d174c2059e3c4 // vpinsrb xmm1, xmm4, byte [rdi + rdx + 29], 15 LONG $0x3875e3c4; WORD $0x01cb // vinserti128 ymm1, ymm1, xmm3, 1 QUAD $0x0002a0248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 672], ymm1 - QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] - LONG $0x027cb60f; BYTE $0x1e // movzx edi, byte [rdx + rax + 30] - LONG $0xcf6ef9c5 // vmovd xmm1, edi - QUAD $0x000000c824bc8b4c // mov r15, qword [rsp + 200] - QUAD $0x011e3a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r15 + 30], 1 - LONG $0x027cb60f; BYTE $0x1f // movzx edi, byte [rdx + rax + 31] - LONG $0xd76ef9c5 // vmovd xmm2, edi - QUAD $0x011f3a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r15 + 31], 1 - QUAD $0x021e0a4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rcx + 30], 2 - QUAD $0x021f0a542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rcx + 31], 2 - QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] - QUAD $0x031e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 3 - QUAD $0x031f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x041e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 4 - QUAD $0x041f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 4 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x051e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 5 - QUAD $0x051f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 5 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x061e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 6 - QUAD $0x061f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 6 - QUAD $0x071e324c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rsi + 30], 7 - QUAD $0x071f32542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rsi + 31], 7 + QUAD $0x000000f824b48b48 // mov rsi, qword [rsp + 248] + LONG $0x3744b60f; BYTE $0x1e // movzx eax, byte [rdi + rsi + 30] + LONG $0xc86ef9c5 // vmovd xmm1, eax + QUAD $0x011e1f4c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rbx + 30], 1 + LONG $0x3744b60f; BYTE $0x1f // movzx eax, byte [rdi + rsi + 31] + LONG $0xd06ef9c5 // vmovd xmm2, eax + QUAD $0x011f1f542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rbx + 31], 1 + QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] + QUAD $0x021e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 2 + QUAD $0x021f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 2 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x031e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 3 + QUAD $0x031f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 3 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x041e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 4 + QUAD $0x041f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 4 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x051e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 5 + QUAD $0x051f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x061e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 6 + QUAD $0x061f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 6 + QUAD $0x071e0f4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r9 + 30], 7 + QUAD $0x071f0f542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r9 + 31], 7 QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x081e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 8 - QUAD $0x081f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 8 - QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] - QUAD $0x091e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 9 - QUAD $0x091f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 9 - QUAD $0x000000b824848b48 // mov rax, qword [rsp + 184] - QUAD $0x0a1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 10 - QUAD $0x0b1e2a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r13 + 30], 11 - QUAD $0x0b1f2a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r13 + 31], 11 - QUAD $0x0c1e124c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r10 + 30], 12 - QUAD $0x0c1f12542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r10 + 31], 12 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - QUAD $0x0d1e1a4c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdx + r11 + 30], 13 - QUAD $0x0d1f1a542069a3c4 // vpinsrb xmm2, xmm2, byte [rdx + r11 + 31], 13 + QUAD $0x081e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 8 + QUAD $0x081f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 8 + QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] + QUAD $0x091e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 9 + QUAD $0x091f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 9 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x0a1e174c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r10 + 30], 10 + QUAD $0x0a1f17542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r10 + 31], 10 + QUAD $0x000000c824848b48 // mov rax, qword [rsp + 200] + QUAD $0x0b1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 11 + QUAD $0x0b1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 11 LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0e1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 14 - QUAD $0x0e1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 14 - QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] - QUAD $0x0f1e024c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdx + rax + 30], 15 - QUAD $0x0f1f02542069e3c4 // vpinsrb xmm2, xmm2, byte [rdx + rax + 31], 15 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x0a44b60f; BYTE $0x1e // movzx eax, byte [rdx + rcx + 30] + QUAD $0x0c1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 12 + QUAD $0x0c1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 12 + QUAD $0x0d1e074c2071a3c4 // vpinsrb xmm1, xmm1, byte [rdi + r8 + 30], 13 + QUAD $0x0d1f07542069a3c4 // vpinsrb xmm2, xmm2, byte [rdi + r8 + 31], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0e1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 14 + QUAD $0x0e1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 14 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0f1e074c2071e3c4 // vpinsrb xmm1, xmm1, byte [rdi + rax + 30], 15 + QUAD $0x0f1f07542069e3c4 // vpinsrb xmm2, xmm2, byte [rdi + rax + 31], 15 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x0f44b60f; BYTE $0x1e // movzx eax, byte [rdi + rcx + 30] LONG $0xd86ef9c5 // vmovd xmm3, eax - QUAD $0x011e025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 30], 1 - LONG $0x0a44b60f; BYTE $0x1f // movzx eax, byte [rdx + rcx + 31] + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x011e0f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r9 + 30], 1 + LONG $0x0f44b60f; BYTE $0x1f // movzx eax, byte [rdi + rcx + 31] LONG $0xe06ef9c5 // vmovd xmm4, eax - QUAD $0x011f02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 31], 1 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x021e025c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r8 + 30], 2 - QUAD $0x021f02642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r8 + 31], 2 + QUAD $0x011f0f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r9 + 31], 1 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x021e175c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r10 + 30], 2 + QUAD $0x021f17642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r10 + 31], 2 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x031e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 3 - QUAD $0x031f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 3 - QUAD $0x041e325c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r14 + 30], 4 - QUAD $0x041f32642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r14 + 31], 4 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x051e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 5 - QUAD $0x051f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 5 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x061e1a5c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rbx + 30], 6 - QUAD $0x061f1a642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rbx + 31], 6 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x071e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 7 - QUAD $0x071f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 7 - QUAD $0x081e0a5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r9 + 30], 8 - QUAD $0x081f0a642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r9 + 31], 8 - QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] - QUAD $0x091e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 9 - QUAD $0x091f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 9 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0a1e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 10 - QUAD $0x0a1f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b1e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 11 - QUAD $0x0b1f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 11 + QUAD $0x031e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 3 + QUAD $0x031f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 3 + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + QUAD $0x041e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 4 + QUAD $0x041f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 4 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c1e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 12 - QUAD $0x0c1f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 12 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d1e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 13 - QUAD $0x0d1f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e1e025c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdx + rax + 30], 14 - QUAD $0x0e1f02642059e3c4 // vpinsrb xmm4, xmm4, byte [rdx + rax + 31], 14 - QUAD $0x0f1e225c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdx + r12 + 30], 15 - QUAD $0x0f1f22642059a3c4 // vpinsrb xmm4, xmm4, byte [rdx + r12 + 31], 15 + QUAD $0x051e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 5 + QUAD $0x051f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 5 + QUAD $0x000000a824848b48 // mov rax, qword [rsp + 168] + QUAD $0x061e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 6 + QUAD $0x061f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 6 + QUAD $0x071e375c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r14 + 30], 7 + QUAD $0x071f37642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r14 + 31], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x081e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 8 + QUAD $0x081f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 8 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x091e275c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r12 + 30], 9 + QUAD $0x091f27642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r12 + 31], 9 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0a1e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 10 + QUAD $0x0a1f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0b1e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 11 + QUAD $0x0b1f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 11 + QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] + QUAD $0x0c1e075c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rax + 30], 12 + QUAD $0x0c1f07642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rax + 31], 12 + WORD $0x894c; BYTE $0xe8 // mov rax, r13 + QUAD $0x0d1e2f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r13 + 30], 13 + QUAD $0x0d1f2f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r13 + 31], 13 + QUAD $0x0e1e1f5c2061a3c4 // vpinsrb xmm3, xmm3, byte [rdi + r11 + 30], 14 + QUAD $0x0e1f1f642059a3c4 // vpinsrb xmm4, xmm4, byte [rdi + r11 + 31], 14 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x0f1e175c2061e3c4 // vpinsrb xmm3, xmm3, byte [rdi + rdx + 30], 15 + QUAD $0x0f1f17642059e3c4 // vpinsrb xmm4, xmm4, byte [rdi + rdx + 31], 15 LONG $0x3865e3c4; WORD $0x01c9 // vinserti128 ymm1, ymm3, xmm1, 1 QUAD $0x000140248c7ffdc5; BYTE $0x00 // vmovdqa yword [rsp + 320], ymm1 LONG $0x385de3c4; WORD $0x01ca // vinserti128 ymm1, ymm4, xmm2, 1 @@ -68705,14 +70378,14 @@ LBB11_67: LONG $0x7f7ec1c4; WORD $0x8f6c; BYTE $0x20 // vmovdqu yword [r15 + 4*rcx + 32], ymm5 LONG $0x7f7ec1c4; WORD $0x8f1c // vmovdqu yword [r15 + 4*rcx], ymm3 LONG $0x20c18348 // add rcx, 32 - WORD $0x8948; BYTE $0xcb // mov rbx, rcx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] - JNE LBB11_67 - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - QUAD $0x0000018024b43b4c // cmp r14, qword [rsp + 384] - LONG $0x245c8b44; BYTE $0x1c // mov r11d, dword [rsp + 28] - QUAD $0x0000017024ac8b4c // mov r13, qword [rsp + 368] - QUAD $0x0000016824bc8b48 // mov rdi, qword [rsp + 360] - QUAD $0x0000011824948b4c // mov r10, qword [rsp + 280] - JNE LBB11_69 - JMP LBB11_72 + JNE LBB11_73 + QUAD $0x00000160248c8b48 // mov rcx, qword [rsp + 352] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + QUAD $0x0000011824a48b4c // mov r12, qword [rsp + 280] + LONG $0x24748b44; BYTE $0x1c // mov r14d, dword [rsp + 28] + QUAD $0x0000016824ac8b4c // mov r13, qword [rsp + 360] + QUAD $0x0000017024bc8b48 // mov rdi, qword [rsp + 368] + JNE LBB11_75 + JMP LBB11_78 diff --git a/arrow/compute/internal/kernels/scalar_comparison_sse4_amd64.s b/arrow/compute/internal/kernels/scalar_comparison_sse4_amd64.s index 635738a7c..6dd0cb95a 100644 --- a/arrow/compute/internal/kernels/scalar_comparison_sse4_amd64.s +++ b/arrow/compute/internal/kernels/scalar_comparison_sse4_amd64.s @@ -11,96 +11,110 @@ TEXT ·_comparison_equal_arr_arr_sse4(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x8944; BYTE $0xc8 // mov eax, r9d - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB0_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB0_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB0_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB0_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB0_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_22 - WORD $0x9848 // cdqe - -LBB0_20: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_20 - LONG $0x01c48349 // add r12, 1 - -LBB0_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_26 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB0_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB0_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB0_24: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_26: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_28: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_32 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_30: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5940f41 // sete r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3940f41 // sete r11b @@ -109,21 +123,21 @@ LBB0_24: LONG $0xd7940f41 // sete r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2940f41 // sete r10b @@ -134,143 +148,143 @@ LBB0_24: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4940f41 // sete r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1940f41 // sete r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_24 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_30 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_28: +LBB0_34: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -278,107 +292,123 @@ LBB0_28: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_28 - JMP LBB0_123 - -LBB0_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB0_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB0_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB0_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_50 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB0_48: - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xcb20 // and bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB0_48 - LONG $0x01c48349 // add r12, 1 - -LBB0_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_54 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_34 + JMP LBB0_153 + +LBB0_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB0_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB0_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB0_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB0_52: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_58: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x100f42f2; WORD $0xf604 // movsd xmm0, qword [rsi + 8*r14] + LONG $0x2e0f4266; WORD $0xf204 // ucomisd xmm0, qword [rdx + 8*r14] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x2044; BYTE $0xd3 // and bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xf8c38349 // add r11, -8 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB0_58 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB0_60: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_62: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_66 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_64: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x06100ff2 // movsd xmm0, qword [rsi] LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] LONG $0x46100ff2; BYTE $0x08 // movsd xmm0, qword [rsi + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x46100ff2; BYTE $0x10 // movsd xmm0, qword [rsi + 16] LONG $0x422e0f66; BYTE $0x10 // ucomisd xmm0, qword [rdx + 16] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x46100ff2; BYTE $0x18 // movsd xmm0, qword [rsi + 24] LONG $0x422e0f66; BYTE $0x18 // ucomisd xmm0, qword [rdx + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x46100ff2; BYTE $0x20 // movsd xmm0, qword [rsi + 32] LONG $0x422e0f66; BYTE $0x20 // ucomisd xmm0, qword [rdx + 32] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x46100ff2; BYTE $0x28 // movsd xmm0, qword [rsi + 40] LONG $0x422e0f66; BYTE $0x28 // ucomisd xmm0, qword [rdx + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -394,13 +424,13 @@ LBB0_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x46100ff2; BYTE $0x40 // movsd xmm0, qword [rsi + 64] LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x46100ff2; BYTE $0x48 // movsd xmm0, qword [rsi + 72] LONG $0x422e0f66; BYTE $0x48 // ucomisd xmm0, qword [rdx + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -411,117 +441,116 @@ LBB0_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x46100ff2; BYTE $0x58 // movsd xmm0, qword [rsi + 88] LONG $0x422e0f66; BYTE $0x58 // ucomisd xmm0, qword [rdx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x46100ff2; BYTE $0x60 // movsd xmm0, qword [rsi + 96] LONG $0x422e0f66; BYTE $0x60 // ucomisd xmm0, qword [rdx + 96] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x46100ff2; BYTE $0x68 // movsd xmm0, qword [rsi + 104] LONG $0x422e0f66; BYTE $0x68 // ucomisd xmm0, qword [rdx + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x46100ff2; BYTE $0x70 // movsd xmm0, qword [rsi + 112] LONG $0x422e0f66; BYTE $0x70 // ucomisd xmm0, qword [rdx + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x46100ff2; BYTE $0x78 // movsd xmm0, qword [rsi + 120] LONG $0x422e0f66; BYTE $0x78 // ucomisd xmm0, qword [rdx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl QUAD $0x0000008086100ff2 // movsd xmm0, qword [rsi + 128] QUAD $0x00000080822e0f66 // ucomisd xmm0, qword [rdx + 128] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl QUAD $0x0000008886100ff2 // movsd xmm0, qword [rsi + 136] QUAD $0x00000088822e0f66 // ucomisd xmm0, qword [rdx + 136] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl QUAD $0x0000009086100ff2 // movsd xmm0, qword [rsi + 144] QUAD $0x00000090822e0f66 // ucomisd xmm0, qword [rdx + 144] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl QUAD $0x0000009886100ff2 // movsd xmm0, qword [rsi + 152] QUAD $0x00000098822e0f66 // ucomisd xmm0, qword [rdx + 152] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd6940f41 // sete r14b - WORD $0x2041; BYTE $0xc6 // and r14b, al + LONG $0xd7940f41 // sete r15b + WORD $0x2041; BYTE $0xc7 // and r15b, al QUAD $0x000000a086100ff2 // movsd xmm0, qword [rsi + 160] QUAD $0x000000a0822e0f66 // ucomisd xmm0, qword [rdx + 160] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl QUAD $0x000000a886100ff2 // movsd xmm0, qword [rsi + 168] QUAD $0x000000a8822e0f66 // ucomisd xmm0, qword [rdx + 168] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl QUAD $0x000000b086100ff2 // movsd xmm0, qword [rsi + 176] QUAD $0x000000b0822e0f66 // ucomisd xmm0, qword [rdx + 176] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl QUAD $0x000000b886100ff2 // movsd xmm0, qword [rsi + 184] QUAD $0x000000b8822e0f66 // ucomisd xmm0, qword [rdx + 184] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f41 // sete r15b - WORD $0x2041; BYTE $0xc7 // and r15b, al + LONG $0xd2940f41 // sete r10b + WORD $0x2041; BYTE $0xc2 // and r10b, al QUAD $0x000000c086100ff2 // movsd xmm0, qword [rsi + 192] QUAD $0x000000c0822e0f66 // ucomisd xmm0, qword [rdx + 192] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl QUAD $0x000000c886100ff2 // movsd xmm0, qword [rsi + 200] QUAD $0x000000c8822e0f66 // ucomisd xmm0, qword [rdx + 200] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4940f41 // sete r12b + WORD $0x2041; BYTE $0xc4 // and r12b, al QUAD $0x000000d086100ff2 // movsd xmm0, qword [rsi + 208] QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd3940f41 // sete r11b - WORD $0x2041; BYTE $0xc3 // and r11b, al + LONG $0xd6940f41 // sete r14b + WORD $0x2041; BYTE $0xc6 // and r14b, al QUAD $0x000000d886100ff2 // movsd xmm0, qword [rsi + 216] QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd2940f41 // sete r10b - WORD $0x2041; BYTE $0xc2 // and r10b, al + LONG $0xd3940f41 // sete r11b + WORD $0x2041; BYTE $0xc3 // and r11b, al QUAD $0x000000e086100ff2 // movsd xmm0, qword [rsi + 224] QUAD $0x000000e0822e0f66 // ucomisd xmm0, qword [rdx + 224] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl QUAD $0x000000e886100ff2 // movsd xmm0, qword [rsi + 232] QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl QUAD $0x000000f086100ff2 // movsd xmm0, qword [rsi + 240] QUAD $0x000000f0822e0f66 // ucomisd xmm0, qword [rdx + 240] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -533,109 +562,107 @@ LBB0_52: WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd0940f41 // sete r8b WORD $0x2041; BYTE $0xc0 // and r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0841; BYTE $0xce // or r14b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x74b60f44; WORD $0x0324 // movzx r14d, byte [rsp + 3] - WORD $0x0845; BYTE $0xee // or r14b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xda // or r10b, bl + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xd1 // or cl, r10b - LONG $0x24348845 // mov byte [r12], r14b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB0_52 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_64 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_56: +LBB0_68: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x04100ff2; BYTE $0xce // movsd xmm0, qword [rsi + 8*rcx] LONG $0x042e0f66; BYTE $0xca // ucomisd xmm0, qword [rdx + 8*rcx] @@ -645,98 +672,122 @@ LBB0_56: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB0_56 - JMP LBB0_123 + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB0_68 + JMP LBB0_153 LBB0_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB0_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_8 - WORD $0x9848 // cdqe - -LBB0_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xfd // mov r13, r15 + JE LBB0_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB0_9 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB0_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4940f41 // sete r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_6 - LONG $0x01c48349 // add r12, 1 - -LBB0_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_12 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB0_10: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB0_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + +LBB0_9: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_11: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_15 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB0_13: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7940f41 // sete r15b + LONG $0xd6940f41 // sete r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7940f40 // sete dil @@ -748,19 +799,19 @@ LBB0_10: LONG $0xd3940f41 // sete r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6940f41 // sete r14b + LONG $0xd7940f41 // sete r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0940f41 // sete r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4940f41 // sete r12b @@ -769,147 +820,146 @@ LBB0_10: LONG $0xd5940f41 // sete r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1940f41 // sete r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB0_10 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB0_13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] -LBB0_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_14: +LBB0_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -917,101 +967,117 @@ LBB0_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_14 - JMP LBB0_123 - -LBB0_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB0_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB0_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_36 - WORD $0x9848 // cdqe - -LBB0_34: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_34 - LONG $0x01c48349 // add r12, 1 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_17 + JMP LBB0_153 LBB0_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_40 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB0_38: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB0_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB0_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB0_41: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_43: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_45: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_49 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_47: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5940f41 // sete r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3940f41 // sete r11b @@ -1020,21 +1086,21 @@ LBB0_38: LONG $0xd7940f41 // sete r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2940f41 // sete r10b @@ -1045,143 +1111,143 @@ LBB0_38: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4940f41 // sete r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1940f41 // sete r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_38 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_47 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_42: +LBB0_51: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -1189,97 +1255,113 @@ LBB0_42: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_42 - JMP LBB0_123 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_51 + JMP LBB0_153 -LBB0_68: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_72 - WORD $0x9848 // cdqe - -LBB0_70: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_70 - LONG $0x01c48349 // add r12, 1 +LBB0_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB0_86: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB0_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_76 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB0_88: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 -LBB0_74: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_90: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_94 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_92: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5940f41 // sete r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3940f41 // sete r11b @@ -1288,21 +1370,21 @@ LBB0_74: LONG $0xd7940f41 // sete r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2940f41 // sete r10b @@ -1313,143 +1395,143 @@ LBB0_74: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4940f41 // sete r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1940f41 // sete r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_74 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_92 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_78: +LBB0_96: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -1457,97 +1539,113 @@ LBB0_78: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_78 - JMP LBB0_123 - -LBB0_79: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_83 - WORD $0x9848 // cdqe - -LBB0_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_81 - LONG $0x01c48349 // add r12, 1 - -LBB0_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_87 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_96 + JMP LBB0_153 + +LBB0_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB0_85: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_102: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_104: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_108 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_106: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5940f41 // sete r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3940f41 // sete r11b @@ -1556,21 +1654,21 @@ LBB0_85: LONG $0xd7940f41 // sete r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2940f41 // sete r10b @@ -1581,143 +1679,143 @@ LBB0_85: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4940f41 // sete r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1940f41 // sete r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_85 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB0_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_106 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB0_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_89: +LBB0_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -1725,97 +1823,113 @@ LBB0_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_89 - JMP LBB0_123 - -LBB0_101: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_105 - WORD $0x9848 // cdqe - -LBB0_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_103 - LONG $0x01c48349 // add r12, 1 - -LBB0_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_109 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB0_107: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_110 + JMP LBB0_153 + +LBB0_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB0_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB0_130: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_132: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_136 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_134: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5940f41 // sete r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3940f41 // sete r11b @@ -1824,21 +1938,21 @@ LBB0_107: LONG $0xd7940f41 // sete r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2940f41 // sete r10b @@ -1849,143 +1963,143 @@ LBB0_107: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4940f41 // sete r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1940f41 // sete r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_107 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_134 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_111: +LBB0_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -1993,99 +2107,115 @@ LBB0_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_111 - JMP LBB0_123 - -LBB0_112: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_116 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB0_114: - LONG $0x06100ff3 // movss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xcb20 // and bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB0_114 - LONG $0x01c48349 // add r12, 1 - -LBB0_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_120 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_138 + JMP LBB0_153 + +LBB0_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB0_118: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_142: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x100f42f3; WORD $0xb604 // movss xmm0, dword [rsi + 4*r14] + LONG $0x042e0f42; BYTE $0xb2 // ucomiss xmm0, dword [rdx + 4*r14] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x2044; BYTE $0xd3 // and bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xfcc38349 // add r11, -4 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB0_142 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB0_144: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_146: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_150 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_148: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x06100ff3 // movss xmm0, dword [rsi] WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] LONG $0x46100ff3; BYTE $0x04 // movss xmm0, dword [rsi + 4] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x04422e0f // ucomiss xmm0, dword [rdx + 4] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x46100ff3; BYTE $0x08 // movss xmm0, dword [rsi + 8] LONG $0x08422e0f // ucomiss xmm0, dword [rdx + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x46100ff3; BYTE $0x0c // movss xmm0, dword [rsi + 12] LONG $0x0c422e0f // ucomiss xmm0, dword [rdx + 12] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x46100ff3; BYTE $0x10 // movss xmm0, dword [rsi + 16] LONG $0x10422e0f // ucomiss xmm0, dword [rdx + 16] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x46100ff3; BYTE $0x14 // movss xmm0, dword [rsi + 20] LONG $0x14422e0f // ucomiss xmm0, dword [rdx + 20] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2101,13 +2231,13 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x46100ff3; BYTE $0x20 // movss xmm0, dword [rsi + 32] LONG $0x20422e0f // ucomiss xmm0, dword [rdx + 32] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x46100ff3; BYTE $0x24 // movss xmm0, dword [rsi + 36] LONG $0x24422e0f // ucomiss xmm0, dword [rdx + 36] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2118,78 +2248,78 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x46100ff3; BYTE $0x2c // movss xmm0, dword [rsi + 44] LONG $0x2c422e0f // ucomiss xmm0, dword [rdx + 44] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x46100ff3; BYTE $0x30 // movss xmm0, dword [rsi + 48] LONG $0x30422e0f // ucomiss xmm0, dword [rdx + 48] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x46100ff3; BYTE $0x34 // movss xmm0, dword [rsi + 52] LONG $0x34422e0f // ucomiss xmm0, dword [rdx + 52] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x46100ff3; BYTE $0x38 // movss xmm0, dword [rsi + 56] LONG $0x38422e0f // ucomiss xmm0, dword [rdx + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x46100ff3; BYTE $0x3c // movss xmm0, dword [rsi + 60] LONG $0x3c422e0f // ucomiss xmm0, dword [rdx + 60] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl LONG $0x46100ff3; BYTE $0x40 // movss xmm0, dword [rsi + 64] LONG $0x40422e0f // ucomiss xmm0, dword [rdx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl LONG $0x46100ff3; BYTE $0x44 // movss xmm0, dword [rsi + 68] LONG $0x44422e0f // ucomiss xmm0, dword [rdx + 68] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl LONG $0x46100ff3; BYTE $0x48 // movss xmm0, dword [rsi + 72] LONG $0x48422e0f // ucomiss xmm0, dword [rdx + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl LONG $0x46100ff3; BYTE $0x4c // movss xmm0, dword [rsi + 76] LONG $0x4c422e0f // ucomiss xmm0, dword [rdx + 76] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd3940f41 // sete r11b - WORD $0x2041; BYTE $0xc3 // and r11b, al + LONG $0xd7940f41 // sete r15b + WORD $0x2041; BYTE $0xc7 // and r15b, al LONG $0x46100ff3; BYTE $0x50 // movss xmm0, dword [rsi + 80] LONG $0x50422e0f // ucomiss xmm0, dword [rdx + 80] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl LONG $0x46100ff3; BYTE $0x54 // movss xmm0, dword [rsi + 84] LONG $0x54422e0f // ucomiss xmm0, dword [rdx + 84] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl LONG $0x46100ff3; BYTE $0x58 // movss xmm0, dword [rsi + 88] LONG $0x58422e0f // ucomiss xmm0, dword [rdx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl LONG $0x46100ff3; BYTE $0x5c // movss xmm0, dword [rsi + 92] LONG $0x5c422e0f // ucomiss xmm0, dword [rdx + 92] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2200,35 +2330,34 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl LONG $0x46100ff3; BYTE $0x64 // movss xmm0, dword [rsi + 100] LONG $0x64422e0f // ucomiss xmm0, dword [rdx + 100] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4940f41 // sete r12b + WORD $0x2041; BYTE $0xc4 // and r12b, al LONG $0x46100ff3; BYTE $0x68 // movss xmm0, dword [rsi + 104] LONG $0x68422e0f // ucomiss xmm0, dword [rdx + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f41 // sete r15b - WORD $0x2041; BYTE $0xc7 // and r15b, al + LONG $0xd6940f41 // sete r14b + WORD $0x2041; BYTE $0xc6 // and r14b, al LONG $0x46100ff3; BYTE $0x6c // movss xmm0, dword [rsi + 108] LONG $0x6c422e0f // ucomiss xmm0, dword [rdx + 108] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd6940f41 // sete r14b - WORD $0x2041; BYTE $0xc6 // and r14b, al + LONG $0xd3940f41 // sete r11b + WORD $0x2041; BYTE $0xc3 // and r11b, al LONG $0x46100ff3; BYTE $0x70 // movss xmm0, dword [rsi + 112] LONG $0x70422e0f // ucomiss xmm0, dword [rdx + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl LONG $0x46100ff3; BYTE $0x74 // movss xmm0, dword [rsi + 116] LONG $0x74422e0f // ucomiss xmm0, dword [rdx + 116] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x46100ff3; BYTE $0x78 // movss xmm0, dword [rsi + 120] LONG $0x78422e0f // ucomiss xmm0, dword [rdx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al @@ -2240,109 +2369,107 @@ LBB0_118: WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd0940f41 // sete r8b WORD $0x2041; BYTE $0xc0 // and r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x5cb60f44; WORD $0x0324 // movzx r11d, byte [rsp + 3] - WORD $0x0845; BYTE $0xeb // or r11b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] LONG $0x07e2c041 // shl r10b, 7 WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xcf // or r15b, cl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x241c8845 // mov byte [r12], r11b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x24548845; BYTE $0x02 // mov byte [r12 + 2], r10b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB0_118 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_148 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_122: +LBB0_152: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x04100ff3; BYTE $0x8e // movss xmm0, dword [rsi + 4*rcx] LONG $0x8a042e0f // ucomiss xmm0, dword [rdx + 4*rcx] @@ -2352,94 +2479,117 @@ LBB0_122: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB0_122 - JMP LBB0_123 + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB0_152 + JMP LBB0_153 -LBB0_57: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_61 - WORD $0x9848 // cdqe - -LBB0_59: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] +LBB0_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB0_74 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB0_72: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4940f41 // sete r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_59 - LONG $0x01c48349 // add r12, 1 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB0_72 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] -LBB0_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_65 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 +LBB0_74: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 -LBB0_63: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_76: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_80 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB0_78: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7940f41 // sete r15b + LONG $0xd6940f41 // sete r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7940f40 // sete dil @@ -2451,19 +2601,19 @@ LBB0_63: LONG $0xd3940f41 // sete r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6940f41 // sete r14b + LONG $0xd7940f41 // sete r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0940f41 // sete r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4940f41 // sete r12b @@ -2472,147 +2622,146 @@ LBB0_63: LONG $0xd5940f41 // sete r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1940f41 // sete r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB0_63 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB0_78 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] -LBB0_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_67: +LBB0_82: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -2620,97 +2769,113 @@ LBB0_67: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_67 - JMP LBB0_123 - -LBB0_90: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB0_94 - WORD $0x9848 // cdqe + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_82 + JMP LBB0_153 -LBB0_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2940f41 // sete r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB0_92 - LONG $0x01c48349 // add r12, 1 +LBB0_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB0_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB0_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB0_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB0_98 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB0_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3940f41 // sete r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB0_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB0_96: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB0_116: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB0_153 + LONG $0x01c78349 // add r15, 1 + +LBB0_118: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB0_122 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB0_120: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] + LONG $0x2454940f; BYTE $0x1e // sete byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] + LONG $0x2454940f; BYTE $0x1f // sete byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] + LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x03 // sete byte [rsp + 3] + LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454940f; BYTE $0x05 // sete byte [rsp + 5] + LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5940f41 // sete r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454940f; BYTE $0x0a // sete byte [rsp + 10] + LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3940f41 // sete r11b @@ -2719,21 +2884,21 @@ LBB0_96: LONG $0xd7940f41 // sete r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454940f; BYTE $0x06 // sete byte [rsp + 6] + LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454940f; BYTE $0x07 // sete byte [rsp + 7] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7940f40 // sete dil + LONG $0xd0940f41 // sete r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454940f; BYTE $0x0b // sete byte [rsp + 11] + LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2940f41 // sete r10b @@ -2744,143 +2909,143 @@ LBB0_96: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4940f41 // sete r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454940f; BYTE $0x09 // sete byte [rsp + 9] + LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454940f; BYTE $0x0c // sete byte [rsp + 12] + LONG $0x2454940f; BYTE $0x15 // sete byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454940f; BYTE $0x0d // sete byte [rsp + 13] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1940f41 // sete r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454940f; BYTE $0x14 // sete byte [rsp + 20] + LONG $0x2454940f; BYTE $0x1d // sete byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454940f; BYTE $0x0e // sete byte [rsp + 14] + LONG $0x2454940f; BYTE $0x16 // sete byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454940f; BYTE $0x0f // sete byte [rsp + 15] + LONG $0x2454940f; BYTE $0x17 // sete byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x19 // sete byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454940f; BYTE $0x11 // sete byte [rsp + 17] + LONG $0x2454940f; BYTE $0x1a // sete byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454940f; BYTE $0x13 // sete byte [rsp + 19] + LONG $0x2454940f; BYTE $0x1c // sete byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454940f; BYTE $0x12 // sete byte [rsp + 18] + LONG $0x2454940f; BYTE $0x1b // sete byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB0_96 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB0_120 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB0_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB0_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB0_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB0_153 WORD $0xc931 // xor ecx, ecx -LBB0_100: +LBB0_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -2888,19 +3053,20 @@ LBB0_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB0_100 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB0_124 -LBB0_123: +LBB0_153: SUBQ $8, SP RET @@ -2938,7 +3104,7 @@ DATA LCDATA1<>+0x0f0(SB)/8, $0x4040404040404040 DATA LCDATA1<>+0x0f8(SB)/8, $0x4040404040404040 GLOBL LCDATA1<>(SB), 8, $256 -TEXT ·_comparison_equal_arr_scalar_sse4(SB), $328-48 +TEXT ·_comparison_equal_arr_scalar_sse4(SB), $344-48 MOVQ typ+0(FP), DI MOVQ left+8(FP), SI @@ -2949,247 +3115,257 @@ TEXT ·_comparison_equal_arr_scalar_sse4(SB), $328-48 MOVQ SP, BP ADDQ $16, SP ANDQ $-16, SP - MOVQ BP, 304(SP) + MOVQ BP, 320(SP) LEAQ LCDATA1<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB1_27 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB1_25 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB1_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB1_101 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB1_124 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB1_199 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_17 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB1_114 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB1_139 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB1_222 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB1_15 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_13 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_12: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_12 + +LBB1_13: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 LBB1_15: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_15 - LONG $0x01c68349 // add r14, 1 + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_19 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax LBB1_17: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_21 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - -LBB1_19: - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000d02494940f // sete byte [rsp + 208] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd2940f41 // sete r10b + LONG $0xd1940f41 // sete r9b LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6940f41 // sete r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000b02494940f // sete byte [rsp + 176] + QUAD $0x000000c02494940f // sete byte [rsp + 192] LONG $0x106e3944 // cmp dword [rsi + 16], r13d - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x940f; BYTE $0xd0 // sete al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0xd3940f41 // sete r11b LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x000000c02494940f // sete byte [rsp + 192] + QUAD $0x000000e02494940f // sete byte [rsp + 224] LONG $0x246e3944 // cmp dword [rsi + 36], r13d - LONG $0xd7940f40 // sete dil + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x286e3944 // cmp dword [rsi + 40], r13d - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd1940f41 // sete r9b + LONG $0xd0940f41 // sete r8b LONG $0x306e3944 // cmp dword [rsi + 48], r13d - LONG $0xd3940f41 // sete r11b + LONG $0xd2940f41 // sete r10b LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4940f41 // sete r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000d02494940f // sete byte [rsp + 208] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x486e3944 // cmp dword [rsi + 72], r13d - QUAD $0x000000802494940f // sete byte [rsp + 128] + QUAD $0x000000b02494940f // sete byte [rsp + 176] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x506e3944 // cmp dword [rsi + 80], r13d LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7940f41 // sete r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x686e3944 // cmp dword [rsi + 104], r13d - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x706e3944 // cmp dword [rsi + 112], r13d - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x746e3944 // cmp dword [rsi + 116], r13d - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x786e3944 // cmp dword [rsi + 120], r13d - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000080248c0244 // add r9b, byte [rsp + 128] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - LONG $0x02e0c041 // shl r8b, 2 + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x10244402 // add al, byte [rsp + 16] + LONG $0x28244402 // add al, byte [rsp + 40] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB1_19 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 + JNE LBB1_17 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] -LBB1_21: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB1_23 +LBB1_19: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_222 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB1_21 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB1_145: +LBB1_162: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -3197,7 +3373,7 @@ LBB1_145: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -3209,74 +3385,90 @@ LBB1_145: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_145 - JMP LBB1_24 - -LBB1_27: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB1_28 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB1_160 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB1_172 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB1_199 - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x02100ff2 // movsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_50 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_48: - LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] - LONG $0x08768d48 // lea rsi, [rsi + 8] + JNE LBB1_162 + JMP LBB1_22 + +LBB1_25: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB1_26 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB1_179 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB1_193 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB1_222 + WORD $0x8b4c; BYTE $0x32 // mov r14, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_52 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_50 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_49: + LONG $0x012e0f66 // ucomisd xmm0, qword [rcx] + LONG $0x08718d48 // lea rsi, [rcx + 8] WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xca20 // and dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xcb20 // and bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_48 - LONG $0x01c68349 // add r14, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_49 LBB1_50: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_54 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000110249c894c // mov qword [rsp + 272], r11 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 LBB1_52: - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_56 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x0000009824b4894c // mov qword [rsp + 152], r14 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + +LBB1_54: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x462e0f66; BYTE $0x08 // ucomisd xmm0, qword [rsi + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd5940f41 // sete r13b @@ -3285,17 +3477,17 @@ LBB1_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x18244c88 // mov byte [rsp + 24], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x462e0f66; BYTE $0x18 // ucomisd xmm0, qword [rsi + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl LONG $0x462e0f66; BYTE $0x20 // ucomisd xmm0, qword [rsi + 32] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x462e0f66; BYTE $0x28 // ucomisd xmm0, qword [rsi + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd4940f41 // sete r12b @@ -3304,27 +3496,27 @@ LBB1_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x462e0f66; BYTE $0x38 // ucomisd xmm0, qword [rsi + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x08244c88 // mov byte [rsp + 8], cl LONG $0x462e0f66; BYTE $0x40 // ucomisd xmm0, qword [rsi + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x462e0f66; BYTE $0x48 // ucomisd xmm0, qword [rsi + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x462e0f66; BYTE $0x50 // ucomisd xmm0, qword [rsi + 80] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x462e0f66; BYTE $0x58 // ucomisd xmm0, qword [rsi + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd3 // sete bl @@ -3333,22 +3525,22 @@ LBB1_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x462e0f66; BYTE $0x68 // ucomisd xmm0, qword [rsi + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl LONG $0x462e0f66; BYTE $0x70 // ucomisd xmm0, qword [rsi + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x462e0f66; BYTE $0x78 // ucomisd xmm0, qword [rsi + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl QUAD $0x00000080862e0f66 // ucomisd xmm0, qword [rsi + 128] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -3358,27 +3550,27 @@ LBB1_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl QUAD $0x00000090862e0f66 // ucomisd xmm0, qword [rsi + 144] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl QUAD $0x00000098862e0f66 // ucomisd xmm0, qword [rsi + 152] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl QUAD $0x000000a0862e0f66 // ucomisd xmm0, qword [rsi + 160] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl QUAD $0x000000a8862e0f66 // ucomisd xmm0, qword [rsi + 168] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl QUAD $0x000000b0862e0f66 // ucomisd xmm0, qword [rsi + 176] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd7940f41 // sete r15b @@ -3391,7 +3583,7 @@ LBB1_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl QUAD $0x000000c8862e0f66 // ucomisd xmm0, qword [rsi + 200] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd3940f41 // sete r11b @@ -3408,12 +3600,12 @@ LBB1_52: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl + LONG $0xf0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 240], cl QUAD $0x000000e8862e0f66 // ucomisd xmm0, qword [rsi + 232] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0x00248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 256], cl QUAD $0x000000f0862e0f66 // ucomisd xmm0, qword [rsi + 240] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd7940f40 // sete dil @@ -3423,605 +3615,402 @@ LBB1_52: WORD $0x940f; BYTE $0xd2 // sete dl WORD $0xc220 // and dl, al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] + LONG $0x246c0244; BYTE $0x20 // add r13b, byte [rsp + 32] WORD $0x8944; BYTE $0xe8 // mov eax, r13d LONG $0x05e4c041 // shl r12b, 5 - LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] + LONG $0x6cb60f44; WORD $0x4024 // movzx r13d, byte [rsp + 64] LONG $0x06e5c041 // shl r13b, 6 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x64b60f44; WORD $0x1824 // movzx r12d, byte [rsp + 24] + LONG $0x64b60f44; WORD $0x3024 // movzx r12d, byte [rsp + 48] LONG $0x02e4c041 // shl r12b, 2 WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] + LONG $0x38244c02 // add cl, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x04244488 // mov byte [rsp + 4], al - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x08244488 // mov byte [rsp + 8], al + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xcb08 // or bl, cl - LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] + LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - LONG $0x08244488 // mov byte [rsp + 8], al - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x18244488 // mov byte [rsp + 24], al + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x74b60f44; WORD $0x6024 // movzx r14d, byte [rsp + 96] + LONG $0x74b60f44; WORD $0x7024 // movzx r14d, byte [rsp + 112] LONG $0x07e6c041 // shl r14b, 7 WORD $0x0841; BYTE $0xc6 // or r14b, al - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] WORD $0xc900 // add cl, cl LONG $0x58244c02 // add cl, byte [rsp + 88] - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xcb08 // or bl, cl - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd908 // or cl, bl WORD $0xcb89 // mov ebx, ecx - QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd908 // or cl, bl - WORD $0x8941; BYTE $0xcc // mov r12d, ecx - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x0844; BYTE $0xe8 // or al, r13b - QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e7c041 // shl r15b, 6 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x24740a44; BYTE $0x08 // or r14b, byte [rsp + 8] + LONG $0x24740a44; BYTE $0x18 // or r14b, byte [rsp + 24] LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xf8 // or r8b, r15b - WORD $0x0845; BYTE $0xe0 // or r8b, r12b + WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000d0249c0244 // add r11b, byte [rsp + 208] + QUAD $0x000000c0249c0244 // add r11b, byte [rsp + 192] LONG $0x02e2c041 // shl r10b, 2 WORD $0x0845; BYTE $0xda // or r10b, r11b LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xd1 // or r9b, r10b - QUAD $0x00000098249cb60f // movzx ebx, byte [rsp + 152] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x8941; BYTE $0xd9 // mov r9d, ebx - WORD $0x0188 // mov byte [rcx], al - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + QUAD $0x000000f0248cb60f // movzx ecx, byte [rsp + 240] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xc9 // or cl, r9b + WORD $0xcb89 // mov ebx, ecx + LONG $0x24048841 // mov byte [r12], al + QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 LONG $0x06e7c040 // shl dil, 6 - WORD $0x0840; BYTE $0xdf // or dil, bl - LONG $0x01718844 // mov byte [rcx + 1], r14b + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x24748845; BYTE $0x01 // mov byte [r12 + 1], r14b WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x0844; BYTE $0xca // or dl, r9b - LONG $0x02418844 // mov byte [rcx + 2], r8b - WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl + WORD $0xda08 // or dl, bl + LONG $0x24448845; BYTE $0x02 // mov byte [r12 + 2], r8b + LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c18348 // add rcx, 4 - WORD $0x8949; BYTE $0xce // mov r14, rcx - QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB1_52 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000012024848348; BYTE $0xff // add qword [rsp + 288], -1 + JNE LBB1_54 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0000009824b48b4c // mov r14, qword [rsp + 152] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] -LBB1_54: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB1_195 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB1_197 +LBB1_56: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_222 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_218 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB1_220 LBB1_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB1_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB1_199 - WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_6: - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB1_59 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB1_222 + WORD $0x8a44; BYTE $0x32 // mov r14b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_5 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_89 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + +LBB1_95: + LONG $0x015e8d4c // lea r11, [rsi + 1] + WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_6 - LONG $0x01c68349 // add r14, 1 - -LBB1_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_9 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x245c8844; BYTE $0x04 // mov byte [rsp + 4], r11b - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x0000010024bc894c // mov qword [rsp + 256], r15 - JB LBB1_84 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB1_87 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB1_87 + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x343c8841 // mov byte [r12 + rsi], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + LONG $0xffc58349 // add r13, -1 + JNE LBB1_95 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB1_91 + JMP LBB1_222 -LBB1_84: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - LONG $0x2474894c; BYTE $0x58 // mov qword [rsp + 88], r14 +LBB1_26: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB1_163 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB1_222 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB1_34 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_32 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_31: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_31 -LBB1_90: - QUAD $0x000000e824bc2b4c // sub r15, qword [rsp + 232] - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 - -LBB1_91: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x015e3844 // cmp byte [rsi + 1], r11b - LONG $0xd6940f40 // sete sil - LONG $0x02593844 // cmp byte [rcx + 2], r11b - LONG $0xd7940f41 // sete r15b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al - LONG $0xd4940f41 // sete r12b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al - QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al - LONG $0xd1940f41 // sete r9b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al - WORD $0x940f; BYTE $0xd2 // sete dl - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al - LONG $0xd7940f40 // sete dil - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al - LONG $0xd2940f41 // sete r10b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al - LONG $0xd6940f41 // sete r14b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al - LONG $0xd5940f41 // sete r13b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al - LONG $0xd0940f41 // sete r8b - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl - LONG $0xd3940f41 // sete r11b - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - WORD $0xd200 // add dl, dl - LONG $0xc0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 192] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x7cb60f44; WORD $0x0424 // movzx r15d, byte [rsp + 4] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - WORD $0x0841; BYTE $0xd1 // or r9b, dl - WORD $0x0845; BYTE $0xe8 // or r8b, r13b - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xd200 // add dl, dl - LONG $0x78245402 // add dl, byte [rsp + 120] - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - WORD $0x8844; BYTE $0x0a // mov byte [rdx], r9b - LONG $0x247cb60f; BYTE $0x48 // movzx edi, byte [rsp + 72] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xfb // or r11b, dil - LONG $0x01428844 // mov byte [rdx + 1], r8b - WORD $0x0841; BYTE $0xf3 // or r11b, sil - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x0000008824b4b60f // movzx esi, byte [rsp + 136] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xc308 // or bl, al - LONG $0x025a8844 // mov byte [rdx + 2], r11b - WORD $0x8945; BYTE $0xfb // mov r11d, r15d - WORD $0x5a88; BYTE $0x03 // mov byte [rdx + 3], bl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c28348 // add rdx, 4 - LONG $0x24548948; BYTE $0x58 // mov qword [rsp + 88], rdx - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB1_91 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - JMP LBB1_93 - -LBB1_28: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB1_146 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB1_199 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_34 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_32: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_32 - LONG $0x01c68349 // add r14, 1 +LBB1_32: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 LBB1_34: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 JL LBB1_38 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax LBB1_36: - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000d02494940f // sete byte [rsp + 208] + QUAD $0x000000802494940f // sete byte [rsp + 128] LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0xd2940f41 // sete r10b + LONG $0xd1940f41 // sete r9b LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6940f41 // sete r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000b02494940f // sete byte [rsp + 176] + QUAD $0x000000c02494940f // sete byte [rsp + 192] LONG $0x206e394c // cmp qword [rsi + 32], r13 - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x940f; BYTE $0xd0 // sete al LONG $0x386e394c // cmp qword [rsi + 56], r13 - WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0xd3940f41 // sete r11b LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x000000c02494940f // sete byte [rsp + 192] + QUAD $0x000000e02494940f // sete byte [rsp + 224] LONG $0x486e394c // cmp qword [rsi + 72], r13 - LONG $0xd7940f40 // sete dil + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x506e394c // cmp qword [rsi + 80], r13 - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x586e394c // cmp qword [rsi + 88], r13 - LONG $0xd1940f41 // sete r9b + LONG $0xd0940f41 // sete r8b LONG $0x606e394c // cmp qword [rsi + 96], r13 - LONG $0xd3940f41 // sete r11b + LONG $0xd2940f41 // sete r10b LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4940f41 // sete r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000d02494940f // sete byte [rsp + 208] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - QUAD $0x000000802494940f // sete byte [rsp + 128] + QUAD $0x000000b02494940f // sete byte [rsp + 176] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7940f41 // sete r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000080248c0244 // add r9b, byte [rsp + 128] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - LONG $0x02e0c041 // shl r8b, 2 + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x10244402 // add al, byte [rsp + 16] + LONG $0x28244402 // add al, byte [rsp + 40] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 JNE LBB1_36 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] LBB1_38: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_222 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax JE LBB1_40 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB1_159: +LBB1_178: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -4029,7 +4018,7 @@ LBB1_159: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -4041,695 +4030,200 @@ LBB1_159: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_159 + JNE LBB1_178 JMP LBB1_41 -LBB1_57: - WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_61 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB1_114: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_120 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_118 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB1_59: - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl +LBB1_117: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_59 - LONG $0x01c68349 // add r14, 1 - -LBB1_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_62 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x245c8844; BYTE $0x04 // mov byte [rsp + 4], r11b - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x0000010024bc894c // mov qword [rsp + 256], r15 - JB LBB1_64 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB1_67 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB1_67 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_117 -LBB1_64: +LBB1_118: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 + +LBB1_120: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_121 + LONG $0x08f98348 // cmp rcx, 8 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + JB LBB1_123 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB1_126 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JBE LBB1_126 + +LBB1_123: WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - LONG $0x2474894c; BYTE $0x38 // mov qword [rsp + 56], r14 + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB1_70: - QUAD $0x000000e824bc2b4c // sub r15, qword [rsp + 232] - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 +LBB1_129: + LONG $0x244c2b48; BYTE $0x20 // sub rcx, qword [rsp + 32] + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx -LBB1_71: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x015e3844 // cmp byte [rsi + 1], r11b +LBB1_130: + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + LONG $0x2e394466 // cmp word [rsi], r13w + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w + LONG $0xd0940f41 // sete r8b + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w + LONG $0xd6940f41 // sete r14b + LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w + WORD $0x940f; BYTE $0xd0 // sete al + LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w + WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w + QUAD $0x000000e02494940f // sete byte [rsp + 224] + LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w + WORD $0x940f; BYTE $0xd1 // sete cl + LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd6940f40 // sete sil - LONG $0x02593844 // cmp byte [rcx + 2], r11b - LONG $0xd7940f41 // sete r15b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al + LONG $0x6b394566; BYTE $0x16 // cmp word [r11 + 22], r13w + LONG $0xd1940f41 // sete r9b + LONG $0x6b394566; BYTE $0x18 // cmp word [r11 + 24], r13w + LONG $0xd2940f41 // sete r10b + LONG $0x6b394566; BYTE $0x1a // cmp word [r11 + 26], r13w LONG $0xd4940f41 // sete r12b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al - QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al + LONG $0x6b394566; BYTE $0x1c // cmp word [r11 + 28], r13w QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al - LONG $0xd1940f41 // sete r9b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al - WORD $0x940f; BYTE $0xd2 // sete dl - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0x6b394566; BYTE $0x1e // cmp word [r11 + 30], r13w LONG $0xd7940f40 // sete dil - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al - LONG $0xd2940f41 // sete r10b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al - LONG $0xd6940f41 // sete r14b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al - LONG $0xd5940f41 // sete r13b - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] - WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al - LONG $0xd0940f41 // sete r8b - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x6b394566; BYTE $0x20 // cmp word [r11 + 32], r13w LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x6b394566; BYTE $0x22 // cmp word [r11 + 34], r13w + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x6b394566; BYTE $0x24 // cmp word [r11 + 36], r13w + QUAD $0x000000b02494940f // sete byte [rsp + 176] + LONG $0x6b394566; BYTE $0x26 // cmp word [r11 + 38], r13w + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x6b394566; BYTE $0x28 // cmp word [r11 + 40], r13w LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl - LONG $0xd3940f41 // sete r11b - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + LONG $0x6b394566; BYTE $0x2a // cmp word [r11 + 42], r13w + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x6b394566; BYTE $0x2c // cmp word [r11 + 44], r13w + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x6b394566; BYTE $0x2e // cmp word [r11 + 46], r13w + LONG $0xd7940f41 // sete r15b + LONG $0x6b394566; BYTE $0x30 // cmp word [r11 + 48], r13w + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x6b394566; BYTE $0x32 // cmp word [r11 + 50], r13w + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x6b394566; BYTE $0x34 // cmp word [r11 + 52], r13w LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x6b394566; BYTE $0x38 // cmp word [r11 + 56], r13w LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x245cb60f; BYTE $0x04 // movzx ebx, byte [rsp + 4] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - WORD $0xd200 // add dl, dl - LONG $0xc0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 192] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x7cb60f44; WORD $0x0424 // movzx r15d, byte [rsp + 4] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - WORD $0x0841; BYTE $0xd1 // or r9b, dl - WORD $0x0845; BYTE $0xe8 // or r8b, r13b - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xd200 // add dl, dl - LONG $0x78245402 // add dl, byte [rsp + 120] - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - WORD $0x8844; BYTE $0x0a // mov byte [rdx], r9b - LONG $0x247cb60f; BYTE $0x58 // movzx edi, byte [rsp + 88] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xfb // or r11b, dil - LONG $0x01428844 // mov byte [rdx + 1], r8b - WORD $0x0841; BYTE $0xf3 // or r11b, sil - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x0000008824b4b60f // movzx esi, byte [rsp + 136] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xc308 // or bl, al - LONG $0x025a8844 // mov byte [rdx + 2], r11b - WORD $0x8945; BYTE $0xfb // mov r11d, r15d - WORD $0x5a88; BYTE $0x03 // mov byte [rdx + 3], bl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c28348 // add rdx, 4 - LONG $0x24548948; BYTE $0x38 // mov qword [rsp + 56], rdx - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB1_71 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - JMP LBB1_73 - -LBB1_146: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_150 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_148: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_148 - LONG $0x01c68349 // add r14, 1 - -LBB1_150: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_154 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 - -LBB1_152: - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd2940f41 // sete r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d - LONG $0xd6940f41 // sete r14b - LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x186e3944 // cmp dword [rsi + 24], r13d - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x246e3944 // cmp dword [rsi + 36], r13d - LONG $0xd7940f40 // sete dil - LONG $0x286e3944 // cmp dword [rsi + 40], r13d - LONG $0xd0940f41 // sete r8b - LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd1940f41 // sete r9b - LONG $0x306e3944 // cmp dword [rsi + 48], r13d - LONG $0xd3940f41 // sete r11b - LONG $0x346e3944 // cmp dword [rsi + 52], r13d - LONG $0xd4940f41 // sete r12b - LONG $0x386e3944 // cmp dword [rsi + 56], r13d - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d - LONG $0xd7940f41 // sete r15b - LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x706e3944 // cmp dword [rsi + 112], r13d - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] - LONG $0x786e3944 // cmp dword [rsi + 120], r13d - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] - LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xc000 // add al, al - LONG $0x10244402 // add al, byte [rsp + 16] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB1_152 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - -LBB1_154: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB1_156 - -LBB1_23: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB1_24 - -LBB1_101: - LONG $0x1ab70f44 // movzx r11d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_105 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_103: - LONG $0x1e394466 // cmp word [rsi], r11w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_103 - LONG $0x01c68349 // add r14, 1 - -LBB1_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_106 - LONG $0x08ff8349 // cmp r15, 8 - LONG $0x245c8944; BYTE $0x04 // mov dword [rsp + 4], r11d - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x000000f024bc894c // mov qword [rsp + 240], r15 - JB LBB1_108 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB1_111 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB1_111 - -LBB1_108: - WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - LONG $0x2474894c; BYTE $0x08 // mov qword [rsp + 8], r14 - -LBB1_114: - LONG $0x247c2b4c; BYTE $0x20 // sub r15, qword [rsp + 32] - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 - -LBB1_115: - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - LONG $0x1e394466 // cmp word [rsi], r11w - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x5e394466; BYTE $0x02 // cmp word [rsi + 2], r11w - LONG $0xd0940f41 // sete r8b - LONG $0x5e394466; BYTE $0x04 // cmp word [rsi + 4], r11w - LONG $0xd6940f41 // sete r14b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x06463966 // cmp word [rsi + 6], ax - LONG $0xd5940f41 // sete r13b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x08463966 // cmp word [rsi + 8], ax - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x0a463966 // cmp word [rsi + 10], ax - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x0c463966 // cmp word [rsi + 12], ax - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x0e463966 // cmp word [rsi + 14], ax - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x10463966 // cmp word [rsi + 16], ax - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x12463966 // cmp word [rsi + 18], ax - WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x14463966 // cmp word [rsi + 20], ax - LONG $0xd6940f40 // sete sil - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x16 // cmp word [r10 + 22], ax - LONG $0xd1940f41 // sete r9b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x18 // cmp word [r10 + 24], ax - LONG $0xd3940f41 // sete r11b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x1a // cmp word [r10 + 26], ax - LONG $0xd4940f41 // sete r12b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x1c // cmp word [r10 + 28], ax - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x1e // cmp word [r10 + 30], ax - LONG $0xd7940f40 // sete dil - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x20 // cmp word [r10 + 32], dx - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x22 // cmp word [r10 + 34], dx - QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x24 // cmp word [r10 + 36], dx - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x26 // cmp word [r10 + 38], dx - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x28 // cmp word [r10 + 40], dx - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x2a // cmp word [r10 + 42], dx - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x2c // cmp word [r10 + 44], dx - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x2e // cmp word [r10 + 46], dx - LONG $0xd7940f41 // sete r15b - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x30 // cmp word [r10 + 48], dx - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x32 // cmp word [r10 + 50], dx - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x34 // cmp word [r10 + 52], dx - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x36 // cmp word [r10 + 54], dx - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x38 // cmp word [r10 + 56], dx - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x3a // cmp word [r10 + 58], dx - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x3c // cmp word [r10 + 60], dx - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x3e // cmp word [r10 + 62], dx - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - QUAD $0x000000a024840244 // add r8b, byte [rsp + 160] - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + LONG $0x6b394566; BYTE $0x3a // cmp word [r11 + 58], r13w + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x6b394566; BYTE $0x3c // cmp word [r11 + 60], r13w + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x6b394566; BYTE $0x3e // cmp word [r11 + 62], r13w + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + QUAD $0x0000008024840244 // add r8b, byte [rsp + 128] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xc6 // or r14b, r8b WORD $0xc900 // add cl, cl - LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x0424448b // mov eax, dword [rsp + 4] + LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e6c040 // shl sil, 2 WORD $0x0840; BYTE $0xce // or sil, cl - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xc108 // or cl, al WORD $0x8941; BYTE $0xc8 // mov r8d, ecx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0841; BYTE $0xf1 // or r9b, sil - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - WORD $0x8941; BYTE $0xc3 // mov r11d, eax - LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000d024b4b60f // movzx esi, byte [rsp + 208] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xf7 // or dil, sil WORD $0xcb08 // or bl, cl WORD $0x0844; BYTE $0xe7 // or dil, r12b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + WORD $0xce89 // mov esi, ecx + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx @@ -4747,7 +4241,7 @@ LBB1_115: WORD $0x0841; BYTE $0xf7 // or r15b, sil LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] + LONG $0x28244402 // add al, byte [rsp + 40] WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 @@ -4761,232 +4255,214 @@ LBB1_115: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0xda08 // or dl, bl WORD $0xc208 // or dl, al LONG $0x02798844 // mov byte [rcx + 2], r15b WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl - LONG $0x40728d49 // lea rsi, [r10 + 64] + LONG $0x40738d49 // lea rsi, [r11 + 64] LONG $0x04c18348 // add rcx, 4 LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB1_115 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - JMP LBB1_117 - -LBB1_124: - LONG $0x1ab70f44 // movzx r11d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_128 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 + JNE LBB1_130 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + JMP LBB1_132 + +LBB1_139: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_145 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_143 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB1_126: - LONG $0x1e394466 // cmp word [rsi], r11w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl +LBB1_142: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_126 - LONG $0x01c68349 // add r14, 1 - -LBB1_128: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_129 - LONG $0x08ff8349 // cmp r15, 8 - LONG $0x245c8944; BYTE $0x04 // mov dword [rsp + 4], r11d - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x000000f024bc894c // mov qword [rsp + 240], r15 - JB LBB1_131 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB1_134 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB1_134 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_142 + +LBB1_143: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 + +LBB1_145: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_146 + LONG $0x08f98348 // cmp rcx, 8 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + JB LBB1_148 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB1_151 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JBE LBB1_151 -LBB1_131: +LBB1_148: WORD $0xc031 // xor eax, eax LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - LONG $0x2474894c; BYTE $0x08 // mov qword [rsp + 8], r14 + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB1_137: - LONG $0x247c2b4c; BYTE $0x20 // sub r15, qword [rsp + 32] - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 +LBB1_154: + LONG $0x244c2b48; BYTE $0x20 // sub rcx, qword [rsp + 32] + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx -LBB1_138: - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - LONG $0x1e394466 // cmp word [rsi], r11w - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x5e394466; BYTE $0x02 // cmp word [rsi + 2], r11w +LBB1_155: + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + LONG $0x2e394466 // cmp word [rsi], r13w + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd0940f41 // sete r8b - LONG $0x5e394466; BYTE $0x04 // cmp word [rsi + 4], r11w + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd6940f41 // sete r14b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x06463966 // cmp word [rsi + 6], ax - LONG $0xd5940f41 // sete r13b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x08463966 // cmp word [rsi + 8], ax - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x0a463966 // cmp word [rsi + 10], ax - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x0c463966 // cmp word [rsi + 12], ax - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x0e463966 // cmp word [rsi + 14], ax - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x10463966 // cmp word [rsi + 16], ax + LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x12463966 // cmp word [rsi + 18], ax + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w + WORD $0x940f; BYTE $0xd0 // sete al + LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w + WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w + QUAD $0x000000e02494940f // sete byte [rsp + 224] + LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x14463966 // cmp word [rsi + 20], ax + LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd6940f40 // sete sil - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x16 // cmp word [r10 + 22], ax + LONG $0x6b394566; BYTE $0x16 // cmp word [r11 + 22], r13w LONG $0xd1940f41 // sete r9b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x18 // cmp word [r10 + 24], ax - LONG $0xd3940f41 // sete r11b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x1a // cmp word [r10 + 26], ax + LONG $0x6b394566; BYTE $0x18 // cmp word [r11 + 24], r13w + LONG $0xd2940f41 // sete r10b + LONG $0x6b394566; BYTE $0x1a // cmp word [r11 + 26], r13w LONG $0xd4940f41 // sete r12b - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x1c // cmp word [r10 + 28], ax - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x0424448b // mov eax, dword [rsp + 4] - LONG $0x42394166; BYTE $0x1e // cmp word [r10 + 30], ax + LONG $0x6b394566; BYTE $0x1c // cmp word [r11 + 28], r13w + QUAD $0x000000d02494940f // sete byte [rsp + 208] + LONG $0x6b394566; BYTE $0x1e // cmp word [r11 + 30], r13w LONG $0xd7940f40 // sete dil - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x20 // cmp word [r10 + 32], dx + LONG $0x6b394566; BYTE $0x20 // cmp word [r11 + 32], r13w LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x22 // cmp word [r10 + 34], dx + LONG $0x6b394566; BYTE $0x22 // cmp word [r11 + 34], r13w + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x6b394566; BYTE $0x24 // cmp word [r11 + 36], r13w QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x24 // cmp word [r10 + 36], dx - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x26 // cmp word [r10 + 38], dx + LONG $0x6b394566; BYTE $0x26 // cmp word [r11 + 38], r13w LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x28 // cmp word [r10 + 40], dx - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x2a // cmp word [r10 + 42], dx + LONG $0x6b394566; BYTE $0x28 // cmp word [r11 + 40], r13w + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x6b394566; BYTE $0x2a // cmp word [r11 + 42], r13w LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x2c // cmp word [r10 + 44], dx + LONG $0x6b394566; BYTE $0x2c // cmp word [r11 + 44], r13w LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x2e // cmp word [r10 + 46], dx + LONG $0x6b394566; BYTE $0x2e // cmp word [r11 + 46], r13w LONG $0xd7940f41 // sete r15b - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x30 // cmp word [r10 + 48], dx - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x32 // cmp word [r10 + 50], dx + LONG $0x6b394566; BYTE $0x30 // cmp word [r11 + 48], r13w + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x6b394566; BYTE $0x32 // cmp word [r11 + 50], r13w LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x34 // cmp word [r10 + 52], dx + LONG $0x6b394566; BYTE $0x34 // cmp word [r11 + 52], r13w LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x36 // cmp word [r10 + 54], dx + LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x38 // cmp word [r10 + 56], dx + LONG $0x6b394566; BYTE $0x38 // cmp word [r11 + 56], r13w LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x3a // cmp word [r10 + 58], dx - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x3c // cmp word [r10 + 60], dx - QUAD $0x000000882494940f // sete byte [rsp + 136] - LONG $0x0424548b // mov edx, dword [rsp + 4] - LONG $0x52394166; BYTE $0x3e // cmp word [r10 + 62], dx + LONG $0x6b394566; BYTE $0x3a // cmp word [r11 + 58], r13w + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x6b394566; BYTE $0x3c // cmp word [r11 + 60], r13w + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x6b394566; BYTE $0x3e // cmp word [r11 + 62], r13w WORD $0x940f; BYTE $0xd2 // sete dl WORD $0x0045; BYTE $0xc0 // add r8b, r8b - QUAD $0x000000a024840244 // add r8b, byte [rsp + 160] - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + QUAD $0x0000008024840244 // add r8b, byte [rsp + 128] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xc308 // or bl, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xc6 // or r14b, r8b WORD $0xc900 // add cl, cl - LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x0424448b // mov eax, dword [rsp + 4] + LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e6c040 // shl sil, 2 WORD $0x0840; BYTE $0xce // or sil, cl - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xc108 // or cl, al WORD $0x8941; BYTE $0xc8 // mov r8d, ecx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0841; BYTE $0xf1 // or r9b, sil - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - WORD $0x8941; BYTE $0xc3 // mov r11d, eax - LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000d024b4b60f // movzx esi, byte [rsp + 208] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xf7 // or dil, sil WORD $0xcb08 // or bl, cl WORD $0x0844; BYTE $0xe7 // or dil, r12b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x68244402 // add al, byte [rsp + 104] - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + WORD $0xce89 // mov esi, ecx + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx @@ -5004,7 +4480,7 @@ LBB1_138: WORD $0x0841; BYTE $0xf7 // or r15b, sil LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] + LONG $0x28244402 // add al, byte [rsp + 40] WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 @@ -5018,313 +4494,339 @@ LBB1_138: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0xda08 // or dl, bl WORD $0xc208 // or dl, al LONG $0x02798844 // mov byte [rcx + 2], r15b WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl - LONG $0x40728d49 // lea rsi, [r10 + 64] + LONG $0x40738d49 // lea rsi, [r11 + 64] LONG $0x04c18348 // add rcx, 4 LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB1_138 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - JMP LBB1_140 + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 + JNE LBB1_155 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + JMP LBB1_157 -LBB1_160: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_164 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB1_179: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB1_185 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_183 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB1_162: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_162 - LONG $0x01c68349 // add r14, 1 +LBB1_182: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_182 -LBB1_164: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_168 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x000000a0249c894c // mov qword [rsp + 160], r11 +LBB1_183: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 -LBB1_166: - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0xd2940f41 // sete r10b +LBB1_185: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_189 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + +LBB1_187: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0xd1940f41 // sete r9b LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6940f41 // sete r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000b02494940f // sete byte [rsp + 176] + QUAD $0x000000c02494940f // sete byte [rsp + 192] LONG $0x206e394c // cmp qword [rsi + 32], r13 - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x940f; BYTE $0xd0 // sete al LONG $0x386e394c // cmp qword [rsi + 56], r13 - WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0xd3940f41 // sete r11b LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x000000c02494940f // sete byte [rsp + 192] + QUAD $0x000000e02494940f // sete byte [rsp + 224] LONG $0x486e394c // cmp qword [rsi + 72], r13 - LONG $0xd7940f40 // sete dil + WORD $0x940f; BYTE $0xd1 // sete cl LONG $0x506e394c // cmp qword [rsi + 80], r13 - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x586e394c // cmp qword [rsi + 88], r13 - LONG $0xd1940f41 // sete r9b + LONG $0xd0940f41 // sete r8b LONG $0x606e394c // cmp qword [rsi + 96], r13 - LONG $0xd3940f41 // sete r11b + LONG $0xd2940f41 // sete r10b LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4940f41 // sete r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + QUAD $0x000000d02494940f // sete byte [rsp + 208] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x940f; BYTE $0xd2 // sete dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - QUAD $0x000000802494940f // sete byte [rsp + 128] + QUAD $0x000000b02494940f // sete byte [rsp + 176] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7940f41 // sete r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 - LONG $0x2454940f; BYTE $0x04 // sete byte [rsp + 4] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000080248c0244 // add r9b, byte [rsp + 128] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000008824b48b4c // mov r14, qword [rsp + 136] - LONG $0x02e0c041 // shl r8b, 2 + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] WORD $0xc000 // add al, al - LONG $0x50244402 // add al, byte [rsp + 80] - WORD $0xc789 // mov edi, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x10244402 // add al, byte [rsp + 16] + LONG $0x28244402 // add al, byte [rsp + 40] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000a024848348; BYTE $0xff // add qword [rsp + 160], -1 - JNE LBB1_166 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - -LBB1_168: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB1_170 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 + JNE LBB1_187 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] + +LBB1_189: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_222 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_191 LBB1_40: WORD $0x3145; BYTE $0xdb // xor r11d, r11d JMP LBB1_41 -LBB1_172: - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x02100ff3 // movss xmm0, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB1_176 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB1_174: - WORD $0x2e0f; BYTE $0x06 // ucomiss xmm0, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] +LBB1_193: + WORD $0x8b44; BYTE $0x32 // mov r14d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_199 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_197 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB1_196: + WORD $0x2e0f; BYTE $0x01 // ucomiss xmm0, dword [rcx] + LONG $0x04718d48 // lea rsi, [rcx + 4] WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xca20 // and dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xcb20 // and bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB1_174 - LONG $0x01c68349 // add r14, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_196 -LBB1_176: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB1_177 - LONG $0x04fb8349 // cmp r11, 4 - JB LBB1_179 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB1_182 - LONG $0x9e048d4b // lea rax, [r14 + 4*r11] - WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB1_182 +LBB1_197: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 -LBB1_179: - WORD $0x3145; BYTE $0xc0 // xor r8d, r8d +LBB1_199: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_200 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x04f98348 // cmp rcx, 4 + JB LBB1_202 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB1_205 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JBE LBB1_205 + +LBB1_202: + WORD $0xc031 // xor eax, eax WORD $0x8948; BYTE $0xf3 // mov rbx, rsi - WORD $0x894d; BYTE $0xf7 // mov r15, r14 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB1_185: - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - WORD $0x294d; BYTE $0xc3 // sub r11, r8 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 +LBB1_208: + LONG $0x246c894c; BYTE $0x78 // mov qword [rsp + 120], r13 + QUAD $0x0000012024b48944 // mov dword [rsp + 288], r14d + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx + WORD $0x2948; BYTE $0xc1 // sub rcx, rax + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx -LBB1_186: +LBB1_209: WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -5338,52 +4840,52 @@ LBB1_186: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x08244c88 // mov byte [rsp + 8], cl LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x18244c88 // mov byte [rsp + 24], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -5393,22 +4895,22 @@ LBB1_186: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd4940f41 // sete r12b @@ -5417,22 +4919,22 @@ LBB1_186: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd6940f41 // sete r14b @@ -5445,7 +4947,7 @@ LBB1_186: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd3940f41 // sete r11b @@ -5466,7 +4968,7 @@ LBB1_186: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0x00248c88; WORD $0x0001; BYTE $0x00 // mov byte [rsp + 256], cl LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd7940f40 // sete dil @@ -5478,65 +4980,65 @@ LBB1_186: WORD $0xd200 // add dl, dl WORD $0x0844; BYTE $0xea // or dl, r13b WORD $0x8941; BYTE $0xd5 // mov r13d, edx - LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] + LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] WORD $0xc900 // add cl, cl - LONG $0x18244c02 // add cl, byte [rsp + 24] - LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] + LONG $0x30244c02 // add cl, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd008 // or al, dl - LONG $0x04244488 // mov byte [rsp + 4], al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x08244488 // mov byte [rsp + 8], al + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe8 // or al, r13b LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] WORD $0xe2c0; BYTE $0x04 // shl dl, 4 WORD $0xca08 // or dl, cl - LONG $0x6cb60f44; WORD $0x6824 // movzx r13d, byte [rsp + 104] + LONG $0x6cb60f44; WORD $0x6024 // movzx r13d, byte [rsp + 96] LONG $0x05e5c041 // shl r13b, 5 - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x6cb60f44; WORD $0x6024 // movzx r13d, byte [rsp + 96] + LONG $0x6cb60f44; WORD $0x7024 // movzx r13d, byte [rsp + 112] LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x50 // add r12b, byte [rsp + 80] + LONG $0x24640244; BYTE $0x68 // add r12b, byte [rsp + 104] WORD $0x8944; BYTE $0xe1 // mov ecx, r12d - LONG $0x64b60f44; WORD $0x7824 // movzx r12d, byte [rsp + 120] + QUAD $0x0000a024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 160] LONG $0x02e4c041 // shl r12b, 2 WORD $0x0841; BYTE $0xcc // or r12b, cl - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0x0844; BYTE $0xe1 // or cl, r12b WORD $0x8941; BYTE $0xcc // mov r12d, ecx - QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x64b60f44; WORD $0x0424 // movzx r12d, byte [rsp + 4] + LONG $0x64b60f44; WORD $0x0824 // movzx r12d, byte [rsp + 8] WORD $0x0841; BYTE $0xc4 // or r12b, al - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x05 // shl al, 5 LONG $0x06e6c041 // shl r14b, 6 WORD $0x0841; BYTE $0xc6 // or r14b, al @@ -5545,16 +5047,16 @@ LBB1_186: WORD $0x0845; BYTE $0xf0 // or r8b, r14b WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000b0249c0244 // add r11b, byte [rsp + 176] + QUAD $0x000000c0249c0244 // add r11b, byte [rsp + 192] LONG $0x02e2c041 // shl r10b, 2 WORD $0x0845; BYTE $0xda // or r10b, r11b LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xd1 // or r9b, r10b LONG $0x04e7c041 // shl r15b, 4 WORD $0x0845; BYTE $0xcf // or r15b, r9b - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] WORD $0x8844; BYTE $0x20 // mov byte [rax], r12b - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 LONG $0x06e7c040 // shl dil, 6 WORD $0x0840; BYTE $0xcf // or dil, cl @@ -5566,412 +5068,328 @@ LBB1_186: LONG $0x03708840 // mov byte [rax + 3], sil LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 LONG $0x04c08348 // add rax, 4 - QUAD $0x0000008824848948 // mov qword [rsp + 136], rax - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB1_186 + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB1_209 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - JMP LBB1_188 - -LBB1_9: - LONG $0x2474894c; BYTE $0x58 // mov qword [rsp + 88], r14 - -LBB1_93: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_96 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB1_99 - -LBB1_62: - LONG $0x2474894c; BYTE $0x38 // mov qword [rsp + 56], r14 - -LBB1_73: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_76 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB1_79 - -LBB1_106: - LONG $0x2474894c; BYTE $0x08 // mov qword [rsp + 8], r14 - -LBB1_117: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB1_119 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xff // xor r15d, r15d - LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] - -LBB1_123: - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x1e394466 // cmp word [rsi], r11w - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xff // mov rdi, r15 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c78349 // add r15, 2 - LONG $0x5e394466; BYTE $0x02 // cmp word [rsi + 2], r11w - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - WORD $0xda30 // xor dl, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0xd830 // xor al, bl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x394d; BYTE $0xf9 // cmp r9, r15 - JNE LBB1_123 - JMP LBB1_120 - -LBB1_129: - LONG $0x2474894c; BYTE $0x08 // mov qword [rsp + 8], r14 - -LBB1_140: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB1_142 - -LBB1_119: - WORD $0x3145; BYTE $0xff // xor r15d, r15d - JMP LBB1_120 - -LBB1_177: - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - WORD $0x8948; BYTE $0xf3 // mov rbx, rsi - -LBB1_188: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB1_199 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB1_193 - WORD $0xf631 // xor esi, esi - JMP LBB1_191 - -LBB1_156: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - -LBB1_157: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_157 - -LBB1_24: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_199 - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - JMP LBB1_26 + QUAD $0x0000012024b48b44 // mov r14d, dword [rsp + 288] + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + JMP LBB1_211 -LBB1_96: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] +LBB1_59: + WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB1_60 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_62 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 -LBB1_97: - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b +LBB1_68: + LONG $0x01768d4c // lea r14, [rsi + 1] + WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b - LONG $0x02488d4c // lea r9, [rax + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB1_97 - WORD $0x014c; BYTE $0xce // add rsi, r9 - -LBB1_99: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_199 - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xca // mov rdx, r9 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - JMP LBB1_81 - -LBB1_76: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x343c8841 // mov byte [r12 + rsi], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + LONG $0xffc08348 // add rax, -1 + JNE LBB1_68 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB1_64 + JMP LBB1_222 + +LBB1_163: + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB1_169 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB1_167 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB1_77: - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b +LBB1_166: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b - LONG $0x02488d4c // lea r9, [rax + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB1_77 - WORD $0x014c; BYTE $0xce // add rsi, r9 - -LBB1_79: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_199 - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xca // mov rdx, r9 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB1_166 -LBB1_81: - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e18041 // and r9b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xc9 // mov ecx, r9d - JMP LBB1_82 +LBB1_167: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + LONG $0x01c48349 // add r12, 1 -LBB1_195: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d +LBB1_169: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_173 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax -LBB1_196: - LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xc820 // and al, cl - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd0 // xor al, r10b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x462e0f66; BYTE $0x08 // ucomisd xmm0, qword [rsi + 8] - LONG $0x10768d48 // lea rsi, [rsi + 16] - LONG $0xd29b0f41 // setnp r10b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xd0 // and al, r10b - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB1_196 +LBB1_171: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0xd1940f41 // sete r9b + LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0xd6940f41 // sete r14b + LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x146e3944 // cmp dword [rsi + 20], r13d + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x186e3944 // cmp dword [rsi + 24], r13d + WORD $0x940f; BYTE $0xd0 // sete al + LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + LONG $0xd3940f41 // sete r11b + LONG $0x206e3944 // cmp dword [rsi + 32], r13d + QUAD $0x000000e02494940f // sete byte [rsp + 224] + LONG $0x246e3944 // cmp dword [rsi + 36], r13d + WORD $0x940f; BYTE $0xd1 // sete cl + LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0xd7940f40 // sete dil + LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0xd0940f41 // sete r8b + LONG $0x306e3944 // cmp dword [rsi + 48], r13d + LONG $0xd2940f41 // sete r10b + LONG $0x346e3944 // cmp dword [rsi + 52], r13d + LONG $0xd4940f41 // sete r12b + LONG $0x386e3944 // cmp dword [rsi + 56], r13d + QUAD $0x000000d02494940f // sete byte [rsp + 208] + LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d + WORD $0x940f; BYTE $0xd2 // sete dl + LONG $0x406e3944 // cmp dword [rsi + 64], r13d + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x446e3944 // cmp dword [rsi + 68], r13d + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + QUAD $0x000000b02494940f // sete byte [rsp + 176] + LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x506e3944 // cmp dword [rsi + 80], r13d + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x546e3944 // cmp dword [rsi + 84], r13d + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x586e3944 // cmp dword [rsi + 88], r13d + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d + LONG $0xd7940f41 // sete r15b + LONG $0x606e3944 // cmp dword [rsi + 96], r13d + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x686e3944 // cmp dword [rsi + 104], r13d + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x706e3944 // cmp dword [rsi + 112], r13d + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x746e3944 // cmp dword [rsi + 116], r13d + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x786e3944 // cmp dword [rsi + 120], r13d + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000080248c0244 // add r9b, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + WORD $0xc000 // add al, al + LONG $0x68244402 // add al, byte [rsp + 104] + WORD $0xc189 // mov ecx, eax + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x28244402 // add al, byte [rsp + 40] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 + JNE LBB1_171 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x000000f024848b48 // mov rax, qword [rsp + 240] -LBB1_197: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_199 - LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] - WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xc220 // and dl, al - WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - LONG $0x03e8c148 // shr rax, 3 - LONG $0x06348a41 // mov sil, byte [r14 + rax] - LONG $0x07e38041 // and r11b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf2 // xor dl, sil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x061c8841 // mov byte [r14 + rax], bl - JMP LBB1_199 +LBB1_173: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB1_222 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB1_175 -LBB1_170: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB1_21: WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB1_22 -LBB1_171: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0x10768d48 // lea rsi, [rsi + 16] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB1_171 - -LBB1_41: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_199 - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 +LBB1_5: + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + JMP LBB1_92 -LBB1_26: - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xda // mov rdx, r11 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x16348a41 // mov sil, byte [r14 + rdx] - LONG $0x07e38041 // and r11b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x161c8841 // mov byte [r14 + rdx], bl - JMP LBB1_199 +LBB1_121: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB1_142: +LBB1_132: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB1_222 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB1_134 WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xff // xor r15d, r15d - LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] -LBB1_143: +LBB1_138: WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x1e394466 // cmp word [rsi], r11w + LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x940f; BYTE $0xd2 // sete dl WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xff // mov rdi, r15 + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d + LONG $0x14b60f45; BYTE $0x3b // movzx r10d, byte [r11 + rdi] + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0x3044; BYTE $0xd2 // xor dl, r10b WORD $0xd320 // and bl, dl WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c78349 // add r15, 2 - LONG $0x5e394466; BYTE $0x02 // cmp word [rsi + 2], r11w + LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + LONG $0x02c68349 // add r14, 2 + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] WORD $0x940f; BYTE $0xd2 // sete dl WORD $0xdaf6 // neg dl @@ -5981,1912 +5399,943 @@ LBB1_143: WORD $0xe0d2 // shl al, cl WORD $0xd020 // and al, dl WORD $0xd830 // xor al, bl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x394d; BYTE $0xf9 // cmp r9, r15 - JNE LBB1_143 + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB1_138 + JMP LBB1_135 -LBB1_120: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_199 - LONG $0x1e394466 // cmp word [rsi], r11w - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xfa // mov rdx, r15 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e78041 // and r15b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d +LBB1_146: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB1_82: - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl +LBB1_157: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB1_222 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB1_159 -LBB1_199: - MOVQ 304(SP), SP - RET +LBB1_134: + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB1_135 -LBB1_193: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xf631 // xor esi, esi +LBB1_200: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi -LBB1_194: - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xca20 // and dl, cl - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3f // movzx r10d, byte [r15 + rdi] - WORD $0xf189 // mov ecx, esi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0xb341; BYTE $0x01 // mov r11b, 1 - WORD $0xd241; BYTE $0xe3 // shl r11b, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0x2041; BYTE $0xd3 // and r11b, dl - WORD $0x3045; BYTE $0xd3 // xor r11b, r10b - LONG $0x3f1c8845 // mov byte [r15 + rdi], r11b - LONG $0x02c68348 // add rsi, 2 - LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] - LONG $0x085b8d48 // lea rbx, [rbx + 8] - LONG $0xd29b0f41 // setnp r10b - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x2044; BYTE $0xd2 // and dl, r10b - WORD $0x894d; BYTE $0xfa // mov r10, r15 - WORD $0xdaf6 // neg dl - WORD $0x3044; BYTE $0xda // xor dl, r11b - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0x3044; BYTE $0xd8 // xor al, r11b - LONG $0x3f048841 // mov byte [r15 + rdi], al - WORD $0x3949; BYTE $0xf1 // cmp r9, rsi - JNE LBB1_194 +LBB1_211: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB1_222 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB1_216 + WORD $0xf631 // xor esi, esi + JMP LBB1_214 -LBB1_191: - LONG $0x01c0f641 // test r8b, 1 - JE LBB1_199 - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xc220 // and dl, al - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x03e8c148 // shr rax, 3 - LONG $0x073c8a41 // mov dil, byte [r15 + rax] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xfa // xor dl, dil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x071c8841 // mov byte [r15 + rax], bl - JMP LBB1_199 +LBB1_60: + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + JMP LBB1_65 -LBB1_87: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax - LONG $0xc3b60f41 // movzx eax, r11b - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 - WORD $0xc031 // xor eax, eax - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 +LBB1_89: + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 -LBB1_88: - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - LONG $0x05e7c148 // shl rdi, 5 - WORD $0x8949; BYTE $0xfb // mov r11, rdi - WORD $0x8949; BYTE $0xff // mov r15, rdi - WORD $0x8948; BYTE $0xfb // mov rbx, rdi - WORD $0x8949; BYTE $0xfc // mov r12, rdi - WORD $0x8949; BYTE $0xfa // mov r10, rdi - WORD $0x8949; BYTE $0xfe // mov r14, rdi - WORD $0x8949; BYTE $0xf8 // mov r8, rdi - WORD $0x8949; BYTE $0xf9 // mov r9, rdi - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - LONG $0x247c8948; BYTE $0x68 // mov qword [rsp + 104], rdi - LONG $0x3e0cb60f // movzx ecx, byte [rsi + rdi] - LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x3e4cb60f; BYTE $0x01 // movzx ecx, byte [rsi + rdi + 1] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x3e4cb60f; BYTE $0x02 // movzx ecx, byte [rsi + rdi + 2] - LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x3e4cb60f; BYTE $0x03 // movzx ecx, byte [rsi + rdi + 3] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x3e4cb60f; BYTE $0x04 // movzx ecx, byte [rsi + rdi + 4] - LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x3e4cb60f; BYTE $0x05 // movzx ecx, byte [rsi + rdi + 5] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x3e4cb60f; BYTE $0x06 // movzx ecx, byte [rsi + rdi + 6] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x3e4cb60f; BYTE $0x07 // movzx ecx, byte [rsi + rdi + 7] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 - LONG $0x3e4cb60f; BYTE $0x08 // movzx ecx, byte [rsi + rdi + 8] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 - LONG $0x3e4cb60f; BYTE $0x09 // movzx ecx, byte [rsi + rdi + 9] - LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x3e4cb60f; BYTE $0x0a // movzx ecx, byte [rsi + rdi + 10] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 - LONG $0x3e4cb60f; BYTE $0x0b // movzx ecx, byte [rsi + rdi + 11] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x3e4cb60f; BYTE $0x0c // movzx ecx, byte [rsi + rdi + 12] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x3e4cb60f; BYTE $0x0d // movzx ecx, byte [rsi + rdi + 13] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x3e4cb60f; BYTE $0x0e // movzx ecx, byte [rsi + rdi + 14] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x247c8948; BYTE $0x28 // mov qword [rsp + 40], rdi - WORD $0x8949; BYTE $0xfd // mov r13, rdi - LONG $0x20cd8349 // or r13, 32 - LONG $0x246c894c; BYTE $0x08 // mov qword [rsp + 8], r13 - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - LONG $0x40c98348 // or rcx, 64 - LONG $0x244c8948; BYTE $0x50 // mov qword [rsp + 80], rcx - LONG $0x60cb8349 // or r11, 96 - LONG $0x80cb8148; WORD $0x0000; BYTE $0x00 // or rbx, 128 - LONG $0xa0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 160 - LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0xe0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 224 - LONG $0x00ce8149; WORD $0x0001; BYTE $0x00 // or r14, 256 - LONG $0x20c98149; WORD $0x0001; BYTE $0x00 // or r9, 288 - LONG $0x244c894c; BYTE $0x78 // mov qword [rsp + 120], r9 - LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - LONG $0x60ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 352 - QUAD $0x000000d024948948 // mov qword [rsp + 208], rdx - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - LONG $0x80c88149; WORD $0x0001; BYTE $0x00 // or r8, 384 - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x012e3c203a0f4666 // pinsrb xmm15, byte [rsi + r13], 1 - QUAD $0x020e3c203a0f4466 // pinsrb xmm15, byte [rsi + rcx], 2 - QUAD $0x031e3c203a0f4666 // pinsrb xmm15, byte [rsi + r11], 3 - LONG $0x245c8948; BYTE $0x30 // mov qword [rsp + 48], rbx - QUAD $0x041e3c203a0f4466 // pinsrb xmm15, byte [rsi + rbx], 4 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - QUAD $0x053e3c203a0f4666 // pinsrb xmm15, byte [rsi + r15], 5 - QUAD $0x06263c203a0f4666 // pinsrb xmm15, byte [rsi + r12], 6 - WORD $0x894c; BYTE $0xd7 // mov rdi, r10 - QUAD $0x000000802494894c // mov qword [rsp + 128], r10 - QUAD $0x07163c203a0f4666 // pinsrb xmm15, byte [rsi + r10], 7 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - QUAD $0x08363c203a0f4666 // pinsrb xmm15, byte [rsi + r14], 8 - QUAD $0x090e3c203a0f4666 // pinsrb xmm15, byte [rsi + r9], 9 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x0a2e3c203a0f4666 // pinsrb xmm15, byte [rsi + r13], 10 - QUAD $0x0b163c203a0f4466 // pinsrb xmm15, byte [rsi + rdx], 11 - QUAD $0x0c063c203a0f4666 // pinsrb xmm15, byte [rsi + r8], 12 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - QUAD $0x0d363c203a0f4666 // pinsrb xmm15, byte [rsi + r14], 13 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x0e0e3c203a0f4666 // pinsrb xmm15, byte [rsi + r9], 14 - QUAD $0x0f063c203a0f4466 // pinsrb xmm15, byte [rsi + rax], 15 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x01010e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 1], 1 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x02010e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 1], 2 - QUAD $0x011e6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r11 + 1], 3 - WORD $0x894c; BYTE $0xd9 // mov rcx, r11 - QUAD $0x04011e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 1], 4 - QUAD $0x013e6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r15 + 1], 5 - QUAD $0x01266c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r12 + 1], 6 - LONG $0x2464894c; BYTE $0x70 // mov qword [rsp + 112], r12 - QUAD $0x07013e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 1], 7 - QUAD $0x01166c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r10 + 1], 8 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - LONG $0x2454894c; BYTE $0x38 // mov qword [rsp + 56], r10 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x013e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r15 + 1], 9 - QUAD $0x012e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r13 + 1], 10 - QUAD $0x0b01166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 1], 11 - QUAD $0x01066c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r8 + 1], 12 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0x2444894c; BYTE $0x68 // mov qword [rsp + 104], r8 - QUAD $0x01366c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r14 + 1], 13 - QUAD $0x010e6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rsi + r9 + 1], 14 - WORD $0x894d; BYTE $0xce // mov r14, r9 - QUAD $0x0f01066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 1], 15 - WORD $0x8949; BYTE $0xc1 // mov r9, rax - QUAD $0x00c0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 192] - LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 - LONG $0xfd6f0f66 // movdqa xmm7, xmm5 - QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI1_10] */ - LONG $0xfcdb0f66 // pand xmm7, xmm4 - LONG $0xfdf80f66 // psubb xmm7, xmm5 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - LONG $0x54b60f42; WORD $0x0f06 // movzx edx, byte [rsi + r8 + 15] - LONG $0x6e0f4466; BYTE $0xf2 // movd xmm14, edx - LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 - LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] - QUAD $0x021e74203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r11 + 2], 1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x02020674203a0f66 // pinsrb xmm6, byte [rsi + rax + 2], 2 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - QUAD $0x03020e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 2], 3 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x04020e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 2], 4 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x05023e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 2], 5 - QUAD $0x022674203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r12 + 2], 6 - QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x07021674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 2], 7 - QUAD $0x08021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 8 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - QUAD $0x023e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r15 + 2], 9 - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x023e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r15 + 2], 10 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x022674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r12 + 2], 11 - QUAD $0x021674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r10 + 2], 12 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x021674203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r10 + 2], 13 - QUAD $0x023674203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r14 + 2], 14 - LONG $0x244c894c; BYTE $0x40 // mov qword [rsp + 64], r9 - QUAD $0x020e74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r9 + 2], 15 - LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 - LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 - QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xf0db0f66 // pand xmm6, xmm0 - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x54b60f42; WORD $0x1006 // movzx edx, byte [rsi + r8 + 16] - LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - WORD $0x894c; BYTE $0xda // mov rdx, r11 - QUAD $0x031e54203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r11 + 3], 1 - QUAD $0x02030654203a0f66 // pinsrb xmm2, byte [rsi + rax + 3], 2 - QUAD $0x032e54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r13 + 3], 3 - QUAD $0x04030e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 3], 4 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - QUAD $0x05033e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 3], 5 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x06030e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 3], 6 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x07033e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 3], 7 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x030654203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r8 + 3], 8 - QUAD $0x09031e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 3], 9 - QUAD $0x033e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r15 + 3], 10 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - QUAD $0x032654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r12 + 3], 11 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x032654203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r12 + 3], 12 - QUAD $0x031654203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r10 + 3], 13 - QUAD $0x033654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r14 + 3], 14 - QUAD $0x030e54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r9 + 3], 15 - QUAD $0x0104164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 4], 1 - QUAD $0x0204064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 4], 2 - QUAD $0x042e4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rsi + r13 + 4], 3 - QUAD $0x041e4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r11 + 4], 4 - LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] - QUAD $0x041e4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r11 + 4], 5 - QUAD $0x06040e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 4], 6 - QUAD $0x07043e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 4], 7 - QUAD $0x04064c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r8 + 4], 8 - QUAD $0x09041e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 4], 9 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0a040e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 4], 10 - QUAD $0x043e4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r15 + 4], 11 - QUAD $0x04264c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r12 + 4], 12 - QUAD $0x04164c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r10 + 4], 13 - QUAD $0x04364c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r14 + 4], 14 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - QUAD $0x040e4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r9 + 4], 15 - LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - LONG $0x3e54b60f; BYTE $0x11 // movzx edx, byte [rsi + rdi + 17] - LONG $0xc26e0f66 // movd xmm0, edx - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0xd5db0f66 // pand xmm2, xmm5 - LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 - QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xcddb0f66 // pand xmm1, xmm5 - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0x3e54b60f; BYTE $0x12 // movzx edx, byte [rsi + rdi + 18] - LONG $0xea6e0f66 // movd xmm5, edx - LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] - QUAD $0x050e44203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rsi + r9 + 5], 1 - QUAD $0x050644203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rax + 5], 2 - QUAD $0x052e44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rsi + r13 + 5], 3 - LONG $0x246c894c; BYTE $0x60 // mov qword [rsp + 96], r13 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x051644203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rdx + 5], 4 - QUAD $0x051e44203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r11 + 5], 5 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x053e44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rdi + 5], 6 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x052644203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rsi + r12 + 5], 7 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x051644203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rsi + rdx + 5], 8 - QUAD $0x051e44203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rsi + rbx + 5], 9 - QUAD $0x050e44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rsi + rcx + 5], 10 - QUAD $0x053e44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r15 + 5], 11 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x050e44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rsi + rcx + 5], 12 - QUAD $0x051644203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r10 + 5], 13 - WORD $0x894d; BYTE $0xd6 // mov r14, r10 - QUAD $0x050644203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r8 + 5], 14 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x051644203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r10 + 5], 15 - LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 - QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI1_14] */ - LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x0e54b60f; BYTE $0x13 // movzx edx, byte [rsi + rcx + 19] - LONG $0xfa6e0f66 // movd xmm7, edx - LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - LONG $0x0e54b60f; BYTE $0x14 // movzx edx, byte [rsi + rcx + 20] - LONG $0xf26e0f66 // movd xmm6, edx - QUAD $0x060e5c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r9 + 6], 1 - QUAD $0x0206065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 6], 2 - QUAD $0x062e5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r13 + 6], 3 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x061e5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r11 + 6], 4 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x06065c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r8 + 6], 5 - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - QUAD $0x06063e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 6], 6 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x06265c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r12 + 6], 7 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0806165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 6], 8 - QUAD $0x09061e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 6], 9 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0a06165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 6], 10 - QUAD $0x063e5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r15 + 6], 11 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x06265c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r12 + 6], 12 - QUAD $0x06365c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r14 + 6], 13 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x06365c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rsi + r14 + 6], 14 - QUAD $0x06165c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r10 + 6], 15 - QUAD $0x0000b024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 176] - QUAD $0x070e54203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r9 + 7], 1 - WORD $0x8949; BYTE $0xc2 // mov r10, rax - QUAD $0x02070654203a0f66 // pinsrb xmm2, byte [rsi + rax + 7], 2 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x03070654203a0f66 // pinsrb xmm2, byte [rsi + rax + 7], 3 - QUAD $0x071e54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r11 + 7], 4 - QUAD $0x070654203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r8 + 7], 5 - QUAD $0x06070e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 7], 6 - QUAD $0x07073e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 7], 7 - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x070654203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r8 + 7], 8 - QUAD $0x09071e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 7], 9 - QUAD $0x0a071654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 7], 10 - QUAD $0x073e54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r15 + 7], 11 - QUAD $0x072654203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r12 + 7], 12 - QUAD $0x072e54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r13 + 7], 13 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - QUAD $0x073654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r14 + 7], 14 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x070e54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r9 + 7], 15 - LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 - QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI1_15] */ - LONG $0xd9db0f66 // pand xmm3, xmm1 - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 - LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI1_6] */ - LONG $0xd1db0f66 // pand xmm2, xmm1 - LONG $0xd3eb0f66 // por xmm2, xmm3 - LONG $0xca6f0f66 // movdqa xmm1, xmm2 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - LONG $0x1e54b60f; BYTE $0x15 // movzx edx, byte [rsi + rbx + 21] - LONG $0xd26e0f66 // movd xmm2, edx - LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] - QUAD $0x091e54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r11 + 9], 1 - QUAD $0x091654203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r10 + 9], 2 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x090e54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rcx + 9], 3 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x090e54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rcx + 9], 4 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x091654203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rsi + rdx + 9], 5 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x093654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r14 + 9], 6 - QUAD $0x090654203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rax + 9], 7 - QUAD $0x090654203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r8 + 9], 8 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x090654203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rax + 9], 9 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x091654203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r10 + 9], 10 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x091654203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rsi + rdx + 9], 11 - QUAD $0x092654203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r12 + 9], 12 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x092e54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r13 + 9], 13 - QUAD $0x093e54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rdi + 9], 14 - QUAD $0x090e54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r9 + 9], 15 - LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 - LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 - LONG $0xccdb0f66 // pand xmm1, xmm4 - LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 - LONG $0x1e54b60f; BYTE $0x16 // movzx edx, byte [rsi + rbx + 22] - LONG $0xda6e0f66 // movd xmm3, edx - QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] - QUAD $0x081e64203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r11 + 8], 1 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x082e64203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r13 + 8], 2 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x080664203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r8 + 8], 3 - QUAD $0x04080e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 8], 4 - LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] - QUAD $0x080e64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r9 + 8], 5 - QUAD $0x083664203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r14 + 8], 6 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x083664203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r14 + 8], 7 - QUAD $0x083e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r15 + 8], 8 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x09081664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 8], 9 - QUAD $0x081664203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r10 + 8], 10 - QUAD $0x000000d024bc8b4c // mov r15, qword [rsp + 208] - QUAD $0x083e64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r15 + 8], 11 - QUAD $0x082664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r12 + 8], 12 - QUAD $0x0d080664203a0f66 // pinsrb xmm4, byte [rsi + rax + 8], 13 - QUAD $0x0e083e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 8], 14 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0f080664203a0f66 // pinsrb xmm4, byte [rsi + rax + 8], 15 - LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 - LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 - QUAD $0x00a024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 160] - QUAD $0x0a1e54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r11 + 10], 1 - QUAD $0x0a2e54203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r13 + 10], 2 - QUAD $0x0a0654203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r8 + 10], 3 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - QUAD $0x0a0e54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rcx + 10], 4 - QUAD $0x0a0e54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r9 + 10], 5 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0a0e54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rcx + 10], 6 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - QUAD $0x0a3654203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r14 + 10], 7 - QUAD $0x0a1e54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rsi + rbx + 10], 8 - QUAD $0x0a1654203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rdx + 10], 9 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0a1654203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rdx + 10], 10 - WORD $0x8948; BYTE $0xd3 // mov rbx, rdx - QUAD $0x0a3e54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r15 + 10], 11 - QUAD $0x0a2654203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r12 + 10], 12 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - QUAD $0x0a3654203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r14 + 10], 13 - QUAD $0x0a3e54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rdi + 10], 14 - QUAD $0x0a0654203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rsi + rax + 10], 15 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - LONG $0x0654b60f; BYTE $0x17 // movzx edx, byte [rsi + rax + 23] - LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - QUAD $0x00a024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm10 - LONG $0x0654b60f; BYTE $0x18 // movzx edx, byte [rsi + rax + 24] - LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - QUAD $0x0b1e5c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rsi + r11 + 11], 1 - QUAD $0x0b2e5c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rsi + r13 + 11], 2 - QUAD $0x0b165c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r10 + 11], 3 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b065c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rsi + rax + 11], 4 - QUAD $0x0b0e5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r9 + 11], 5 - QUAD $0x0b0e5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rsi + rcx + 11], 6 - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - QUAD $0x0b065c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r8 + 11], 7 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x0b065c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r8 + 11], 8 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x0b0e5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r9 + 11], 9 - QUAD $0x0b1e5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rsi + rbx + 11], 10 - QUAD $0x0b3e5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r15 + 11], 11 - QUAD $0x0b265c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r12 + 11], 12 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - QUAD $0x0b365c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rsi + r14 + 11], 13 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0b365c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rsi + r14 + 11], 14 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0b165c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rsi + rdx + 11], 15 - QUAD $0x0c1e6c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rsi + r11 + 12], 1 - QUAD $0x0c2e6c203a0f4666; BYTE $0x02 // pinsrb xmm13, byte [rsi + r13 + 12], 2 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0c1e6c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rsi + rbx + 12], 3 - QUAD $0x0c066c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rsi + rax + 12], 4 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c066c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rsi + rax + 12], 5 - QUAD $0x0c0e6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rsi + rcx + 12], 6 - QUAD $0x0c3e6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rsi + rdi + 12], 7 - QUAD $0x0c066c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r8 + 12], 8 - QUAD $0x0c0e6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r9 + 12], 9 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0c1e6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rsi + rbx + 12], 10 - QUAD $0x0c3e6c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r15 + 12], 11 - QUAD $0x0c266c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r12 + 12], 12 - QUAD $0x0c166c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rsi + r10 + 12], 13 - WORD $0x894d; BYTE $0xd3 // mov r11, r10 - QUAD $0x0c366c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r14 + 12], 14 - QUAD $0x0c166c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rsi + rdx + 12], 15 - LONG $0x24548b4c; BYTE $0x08 // mov r10, qword [rsp + 8] - QUAD $0x0d1664203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rsi + r10 + 13], 1 - QUAD $0x0d2e64203a0f4666; BYTE $0x02 // pinsrb xmm12, byte [rsi + r13 + 13], 2 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0d2e64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rsi + r13 + 13], 3 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0d1e64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rsi + rbx + 13], 4 - QUAD $0x0d0664203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rsi + rax + 13], 5 - QUAD $0x0d0e64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rcx + 13], 6 - QUAD $0x0d3e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rdi + 13], 7 - QUAD $0x0d0664203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r8 + 13], 8 - QUAD $0x0d0e64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r9 + 13], 9 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0d1e64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rsi + rbx + 13], 10 - QUAD $0x0d3e64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r15 + 13], 11 - QUAD $0x0d2664203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r12 + 13], 12 - QUAD $0x0d1e64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rsi + r11 + 13], 13 - QUAD $0x0d3664203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r14 + 13], 14 - QUAD $0x0d1664203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rsi + rdx + 13], 15 - LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 - QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 - QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - LONG $0x0654b60f; BYTE $0x19 // movzx edx, byte [rsi + rax + 25] - LONG $0xca6e0f66 // movd xmm1, edx - LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 - QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI1_14] */ - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0x0654b60f; BYTE $0x1a // movzx edx, byte [rsi + rax + 26] - LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx - QUAD $0x0000f024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 240] - QUAD $0x0e1664203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r10 + 14], 1 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0e3664203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r14 + 14], 2 - WORD $0x894d; BYTE $0xea // mov r10, r13 - QUAD $0x0e2e64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r13 + 14], 3 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0e1e64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r11 + 14], 4 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x050e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 14], 5 - QUAD $0x060e0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 14], 6 - QUAD $0x070e3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 14], 7 - QUAD $0x0e0664203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r8 + 14], 8 - QUAD $0x0e0e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r9 + 14], 9 - QUAD $0x0a0e1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 14], 10 - QUAD $0x0e3e64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r15 + 14], 11 - QUAD $0x0e2664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r12 + 14], 12 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0d0e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 14], 13 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0e2e64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r13 + 14], 14 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0f0e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 14], 15 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0f1674203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rsi + rdx + 15], 1 - QUAD $0x0f3674203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rsi + r14 + 15], 2 - QUAD $0x0f1674203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rsi + r10 + 15], 3 - QUAD $0x0f1e74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rsi + r11 + 15], 4 - QUAD $0x0f0674203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rsi + rax + 15], 5 - QUAD $0x0f0e74203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rsi + rcx + 15], 6 - QUAD $0x0f3e74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rsi + rdi + 15], 7 - QUAD $0x0f0674203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r8 + 15], 8 - QUAD $0x0f0e74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r9 + 15], 9 - QUAD $0x0f1e74203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rsi + rbx + 15], 10 - QUAD $0x0f3e74203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rsi + r15 + 15], 11 - QUAD $0x0f2674203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rsi + r12 + 15], 12 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0f1674203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rsi + rdx + 15], 13 - QUAD $0x0f2e74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rsi + r13 + 15], 14 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0f1674203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rsi + rdx + 15], 15 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x10167c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rdx + 16], 1 - QUAD $0x10367c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rsi + r14 + 16], 2 - QUAD $0x10167c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rsi + r10 + 16], 3 - QUAD $0x101e7c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rsi + r11 + 16], 4 - QUAD $0x10067c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rax + 16], 5 - QUAD $0x100e7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rcx + 16], 6 - QUAD $0x103e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rdi + 16], 7 - QUAD $0x10067c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r8 + 16], 8 - QUAD $0x100e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r9 + 16], 9 - QUAD $0x101e7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rsi + rbx + 16], 10 - QUAD $0x103e7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r15 + 16], 11 - QUAD $0x10267c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r12 + 16], 12 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x10167c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rsi + rdx + 16], 13 - QUAD $0x102e7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r13 + 16], 14 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x01111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 1 - QUAD $0x113644203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r14 + 17], 2 - QUAD $0x111644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r10 + 17], 3 - QUAD $0x111e44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r11 + 17], 4 - QUAD $0x05110644203a0f66 // pinsrb xmm0, byte [rsi + rax + 17], 5 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x06110e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 17], 6 - QUAD $0x07113e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 17], 7 - QUAD $0x110644203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r8 + 17], 8 - QUAD $0x110e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r9 + 17], 9 - QUAD $0x0a111e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 17], 10 - QUAD $0x113e44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r15 + 17], 11 - QUAD $0x112644203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r12 + 17], 12 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0d110644203a0f66 // pinsrb xmm0, byte [rsi + rax + 17], 13 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0e111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 14 - QUAD $0x00a024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 160] - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - LONG $0x54b60f42; WORD $0x1b36 // movzx edx, byte [rsi + r14 + 27] - LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx - QUAD $0x00c024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 192] - LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 - QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI1_15] */ - LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 - LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 - LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI1_6] */ - LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 - LONG $0x54b60f42; WORD $0x1c36 // movzx edx, byte [rsi + r14 + 28] - LONG $0xe26e0f66 // movd xmm4, edx - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x110644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r8 + 17], 15 - LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 - LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 - LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 - QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI1_10] */ - LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 - LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 - QUAD $0x00a024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm13 - LONG $0x54b60f42; WORD $0x1d36 // movzx edx, byte [rsi + r14 + 29] - LONG $0x6e0f4466; BYTE $0xea // movd xmm13, edx - QUAD $0x10067c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r8 + 16], 15 - QUAD $0x0000c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 192] - LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 - LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] - QUAD $0x12366c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rsi + r14 + 18], 1 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0212166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 18], 2 - QUAD $0x12166c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r10 + 18], 3 - QUAD $0x121e6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r11 + 18], 4 - QUAD $0x122e6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r13 + 18], 5 - QUAD $0x06120e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 18], 6 - QUAD $0x07123e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 18], 7 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0812166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 18], 8 - QUAD $0x120e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r9 + 18], 9 - QUAD $0x0a121e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 18], 10 - QUAD $0x123e6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r15 + 18], 11 - QUAD $0x12266c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r12 + 18], 12 - QUAD $0x0d12066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 18], 13 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0e12066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 18], 14 - LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 - QUAD $0x12066c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r8 + 18], 15 - LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 - QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - LONG $0x0654b60f; BYTE $0x1e // movzx edx, byte [rsi + rax + 30] - LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx - QUAD $0x13367c203a0f4266; BYTE $0x01 // pinsrb xmm7, byte [rsi + r14 + 19], 1 - QUAD $0x143674203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r14 + 20], 1 - QUAD $0x153654203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r14 + 21], 1 - QUAD $0x16365c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r14 + 22], 1 - QUAD $0x173644203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rsi + r14 + 23], 1 - QUAD $0x183654203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r14 + 24], 1 - QUAD $0x19364c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rsi + r14 + 25], 1 - QUAD $0x1a365c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rsi + r14 + 26], 1 - QUAD $0x1b364c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rsi + r14 + 27], 1 - QUAD $0x1c3664203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r14 + 28], 1 - QUAD $0x1d366c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rsi + r14 + 29], 1 - QUAD $0x1e3664203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rsi + r14 + 30], 1 - LONG $0x0654b60f; BYTE $0x1f // movzx edx, byte [rsi + rax + 31] - LONG $0xc26e0f66 // movd xmm0, edx - QUAD $0x1f3644203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rsi + r14 + 31], 1 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0213167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 19], 2 - QUAD $0x02141674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 20], 2 - QUAD $0x02151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 2 - QUAD $0x0216165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 22], 2 - QUAD $0x171644203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rdx + 23], 2 - QUAD $0x181654203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rdx + 24], 2 - QUAD $0x0219164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 25], 2 - QUAD $0x1a165c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rdx + 26], 2 - QUAD $0x1b164c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rdx + 27], 2 - QUAD $0x021c1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 28], 2 - QUAD $0x1d166c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rdx + 29], 2 - QUAD $0x1e1664203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rdx + 30], 2 - QUAD $0x021f1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 31], 2 - QUAD $0x13167c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rsi + r10 + 19], 3 - QUAD $0x131e7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r11 + 19], 4 - QUAD $0x132e7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r13 + 19], 5 - QUAD $0x06130e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 19], 6 - QUAD $0x07133e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 19], 7 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x13367c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r14 + 19], 8 - QUAD $0x130e7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r9 + 19], 9 - QUAD $0x0a131e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 19], 10 - QUAD $0x133e7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r15 + 19], 11 - QUAD $0x13267c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r12 + 19], 12 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0d13167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 19], 13 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0e13067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 19], 14 - QUAD $0x13067c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r8 + 19], 15 - QUAD $0x141674203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r10 + 20], 3 - QUAD $0x141e74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r11 + 20], 4 - QUAD $0x142e74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r13 + 20], 5 - QUAD $0x06140e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 20], 6 - QUAD $0x07143e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 20], 7 - QUAD $0x143674203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r14 + 20], 8 - QUAD $0x140e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r9 + 20], 9 - QUAD $0x0a141e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 20], 10 - QUAD $0x143e74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r15 + 20], 11 - QUAD $0x142674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r12 + 20], 12 - QUAD $0x0d141674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 20], 13 - QUAD $0x0e140674203a0f66 // pinsrb xmm6, byte [rsi + rax + 20], 14 - QUAD $0x0000a024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 160] - QUAD $0x140674203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r8 + 20], 15 - QUAD $0x00c024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 192] - LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 - QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 - QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0x151654203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r10 + 21], 3 - QUAD $0x151e54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r11 + 21], 4 - QUAD $0x152e54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r13 + 21], 5 - QUAD $0x06150e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 21], 6 - QUAD $0x07153e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 21], 7 - QUAD $0x153654203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r14 + 21], 8 - QUAD $0x150e54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r9 + 21], 9 - QUAD $0x0a151e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 21], 10 - QUAD $0x153e54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r15 + 21], 11 - QUAD $0x152654203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r12 + 21], 12 - QUAD $0x0d151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 13 - QUAD $0x0e150654203a0f66 // pinsrb xmm2, byte [rsi + rax + 21], 14 - QUAD $0x150654203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r8 + 21], 15 - LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 - QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI1_14] */ - LONG $0xd7db0f66 // pand xmm2, xmm7 - LONG $0xd6eb0f66 // por xmm2, xmm6 - LONG $0xd5eb0f66 // por xmm2, xmm5 - QUAD $0x16165c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r10 + 22], 3 - QUAD $0x161e5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r11 + 22], 4 - QUAD $0x162e5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r13 + 22], 5 - QUAD $0x06160e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 22], 6 - QUAD $0x07163e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 22], 7 - QUAD $0x16365c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r14 + 22], 8 - QUAD $0x160e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r9 + 22], 9 - QUAD $0x0a161e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 22], 10 - QUAD $0x163e5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r15 + 22], 11 - QUAD $0x16265c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r12 + 22], 12 - QUAD $0x0d16165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 22], 13 - QUAD $0x0e16065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 22], 14 - QUAD $0x16065c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r8 + 22], 15 - QUAD $0x171644203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rsi + r10 + 23], 3 - QUAD $0x171e44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r11 + 23], 4 - QUAD $0x172e44203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r13 + 23], 5 - QUAD $0x170e44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rcx + 23], 6 - QUAD $0x173e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rdi + 23], 7 - QUAD $0x173644203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r14 + 23], 8 - QUAD $0x170e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r9 + 23], 9 - QUAD $0x171e44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rsi + rbx + 23], 10 - QUAD $0x173e44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r15 + 23], 11 - QUAD $0x172644203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r12 + 23], 12 - QUAD $0x171644203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rdx + 23], 13 - QUAD $0x170644203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rax + 23], 14 - QUAD $0x170644203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r8 + 23], 15 - LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 - QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI1_15] */ - LONG $0xdddb0f66 // pand xmm3, xmm5 - LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 - LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 - LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI1_6] */ - LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 - LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - QUAD $0x19164c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rsi + r10 + 25], 3 - QUAD $0x191e4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r11 + 25], 4 - QUAD $0x192e4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r13 + 25], 5 - QUAD $0x06190e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 25], 6 - QUAD $0x07193e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 25], 7 - QUAD $0x19364c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r14 + 25], 8 - QUAD $0x190e4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r9 + 25], 9 - QUAD $0x0a191e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 25], 10 - QUAD $0x193e4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r15 + 25], 11 - QUAD $0x19264c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r12 + 25], 12 - QUAD $0x0d19164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 25], 13 - QUAD $0x0e19064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 25], 14 - QUAD $0x19064c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r8 + 25], 15 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 - LONG $0xd16f0f66 // movdqa xmm2, xmm1 - QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI1_10] */ - LONG $0xd3db0f66 // pand xmm2, xmm3 - LONG $0xd1f80f66 // psubb xmm2, xmm1 - QUAD $0x181654203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r10 + 24], 3 - QUAD $0x181e54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r11 + 24], 4 - QUAD $0x182e54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r13 + 24], 5 - QUAD $0x180e54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rcx + 24], 6 - QUAD $0x183e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rdi + 24], 7 - QUAD $0x183654203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r14 + 24], 8 - QUAD $0x180e54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r9 + 24], 9 - QUAD $0x181e54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rbx + 24], 10 - QUAD $0x183e54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r15 + 24], 11 - QUAD $0x182654203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r12 + 24], 12 - QUAD $0x181654203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rsi + rdx + 24], 13 - QUAD $0x180654203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rax + 24], 14 - QUAD $0x180654203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r8 + 24], 15 - LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 - LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 - QUAD $0x1a165c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r10 + 26], 3 - QUAD $0x1a1e5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r11 + 26], 4 - QUAD $0x1a2e5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r13 + 26], 5 - QUAD $0x1a0e5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rsi + rcx + 26], 6 - QUAD $0x1a3e5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rsi + rdi + 26], 7 - QUAD $0x1a365c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r14 + 26], 8 - QUAD $0x1a0e5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r9 + 26], 9 - QUAD $0x1a1e5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rsi + rbx + 26], 10 - QUAD $0x1a3e5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r15 + 26], 11 - QUAD $0x1a265c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r12 + 26], 12 - QUAD $0x1a165c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rdx + 26], 13 - QUAD $0x1a065c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rsi + rax + 26], 14 - QUAD $0x1a065c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rsi + r8 + 26], 15 - LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 - QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 - LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 - QUAD $0x1b164c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r10 + 27], 3 - QUAD $0x1b1e4c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rsi + r11 + 27], 4 - QUAD $0x1b2e4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r13 + 27], 5 - QUAD $0x1b0e4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rcx + 27], 6 - QUAD $0x1b3e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rdi + 27], 7 - QUAD $0x1b364c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r14 + 27], 8 - QUAD $0x1b0e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r9 + 27], 9 - QUAD $0x1b1e4c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rsi + rbx + 27], 10 - QUAD $0x1b3e4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r15 + 27], 11 - QUAD $0x1b264c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r12 + 27], 12 - QUAD $0x1b164c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rsi + rdx + 27], 13 - QUAD $0x1b064c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rsi + rax + 27], 14 - QUAD $0x1b064c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r8 + 27], 15 - QUAD $0x1c1664203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r10 + 28], 3 - QUAD $0x1c1e64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r11 + 28], 4 - QUAD $0x1c2e64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r13 + 28], 5 - QUAD $0x061c0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 28], 6 - QUAD $0x071c3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 28], 7 - QUAD $0x1c3664203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r14 + 28], 8 - QUAD $0x1c0e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r9 + 28], 9 - QUAD $0x0a1c1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 28], 10 - QUAD $0x1c3e64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r15 + 28], 11 - QUAD $0x1c2664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r12 + 28], 12 - QUAD $0x0d1c1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 28], 13 - QUAD $0x0e1c0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 28], 14 - QUAD $0x1c0664203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r8 + 28], 15 - QUAD $0x1d166c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rsi + r10 + 29], 3 - QUAD $0x1d1e6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r11 + 29], 4 - QUAD $0x1d2e6c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rsi + r13 + 29], 5 - QUAD $0x1d0e6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rsi + rcx + 29], 6 - QUAD $0x1d3e6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rsi + rdi + 29], 7 - QUAD $0x1d366c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r14 + 29], 8 - QUAD $0x1d0e6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r9 + 29], 9 - QUAD $0x1d1e6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rsi + rbx + 29], 10 - QUAD $0x1d3e6c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r15 + 29], 11 - QUAD $0x1d266c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r12 + 29], 12 - QUAD $0x1d166c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rdx + 29], 13 - QUAD $0x1d066c203a0f4466; BYTE $0x0e // pinsrb xmm13, byte [rsi + rax + 29], 14 - LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 - LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 - QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 - QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 - QUAD $0x1d066c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rsi + r8 + 29], 15 - LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 - LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 - LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 - QUAD $0x1e1664203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rsi + r10 + 30], 3 - QUAD $0x1f1644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r10 + 31], 3 - QUAD $0x1e1e64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rsi + r11 + 30], 4 - QUAD $0x1f1e44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r11 + 31], 4 - QUAD $0x1e2e64203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r13 + 30], 5 - QUAD $0x1f2e44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r13 + 31], 5 - QUAD $0x1e0e64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rcx + 30], 6 - QUAD $0x061f0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 31], 6 - QUAD $0x1e3e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rdi + 30], 7 - QUAD $0x071f3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 31], 7 - QUAD $0x1e3664203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r14 + 30], 8 - QUAD $0x1f3644203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r14 + 31], 8 - QUAD $0x1e0e64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r9 + 30], 9 - QUAD $0x1f0e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r9 + 31], 9 - QUAD $0x1e1e64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rsi + rbx + 30], 10 - QUAD $0x0a1f1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 31], 10 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x1e3e64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r15 + 30], 11 - QUAD $0x1f3e44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r15 + 31], 11 - QUAD $0x1e2664203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r12 + 30], 12 - QUAD $0x1f2644203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r12 + 31], 12 - QUAD $0x1e1664203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rsi + rdx + 30], 13 - QUAD $0x0d1f1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 31], 13 - QUAD $0x1e0664203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rsi + rax + 30], 14 - QUAD $0x0e1f0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 31], 14 - QUAD $0x1e0664203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rsi + r8 + 30], 15 - QUAD $0x1f0644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r8 + 31], 15 - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 - LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 - LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0xc6db0f66 // pand xmm0, xmm6 - LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 - LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 - LONG $0xc8600f66 // punpcklbw xmm1, xmm0 - QUAD $0x0000b024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 176] - LONG $0xd46f0f66 // movdqa xmm2, xmm4 - LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 - LONG $0xda6f0f66 // movdqa xmm3, xmm2 - LONG $0xd9610f66 // punpcklwd xmm3, xmm1 - LONG $0xd1690f66 // punpckhwd xmm2, xmm1 - LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 - LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x647f0ff3; WORD $0x308f // movdqu oword [rdi + 4*rcx + 48], xmm4 - LONG $0x447f0ff3; WORD $0x208f // movdqu oword [rdi + 4*rcx + 32], xmm0 - LONG $0x547f0ff3; WORD $0x108f // movdqu oword [rdi + 4*rcx + 16], xmm2 - LONG $0x1c7f0ff3; BYTE $0x8f // movdqu oword [rdi + 4*rcx], xmm3 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB1_88 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x000000e824bc3b4c // cmp r15, qword [rsp + 232] - LONG $0x245c8a44; BYTE $0x04 // mov r11b, byte [rsp + 4] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - JNE LBB1_90 - JMP LBB1_93 +LBB1_91: + LONG $0x01c48349 // add r12, 1 -LBB1_67: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0xc3b60f41 // movzx eax, r11b - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 - WORD $0xc031 // xor eax, eax - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 +LBB1_92: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_93 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x24748844; BYTE $0x08 // mov byte [rsp + 8], r14b + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x00000118248c8948 // mov qword [rsp + 280], rcx + JB LBB1_97 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xd8 // add rax, r11 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB1_100 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc3 // cmp r11, rax + JAE LBB1_100 -LBB1_68: - WORD $0x8949; BYTE $0xc7 // mov r15, rax - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - LONG $0x05e7c149 // shl r15, 5 - WORD $0x894c; BYTE $0xff // mov rdi, r15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 - WORD $0x894d; BYTE $0xfa // mov r10, r15 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - WORD $0x894d; BYTE $0xfb // mov r11, r15 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x247c894c; BYTE $0x68 // mov qword [rsp + 104], r15 - LONG $0x14b60f42; BYTE $0x3e // movzx edx, byte [rsi + r15] - LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - LONG $0x54b60f42; WORD $0x013e // movzx edx, byte [rsi + r15 + 1] - LONG $0xea6e0f66 // movd xmm5, edx - LONG $0x54b60f42; WORD $0x023e // movzx edx, byte [rsi + r15 + 2] - LONG $0xf26e0f66 // movd xmm6, edx - LONG $0x54b60f42; WORD $0x033e // movzx edx, byte [rsi + r15 + 3] - LONG $0xd26e0f66 // movd xmm2, edx - LONG $0x54b60f42; WORD $0x043e // movzx edx, byte [rsi + r15 + 4] - LONG $0xca6e0f66 // movd xmm1, edx - LONG $0x54b60f42; WORD $0x053e // movzx edx, byte [rsi + r15 + 5] - LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - LONG $0x54b60f42; WORD $0x063e // movzx edx, byte [rsi + r15 + 6] - LONG $0xda6e0f66 // movd xmm3, edx - LONG $0x54b60f42; WORD $0x073e // movzx edx, byte [rsi + r15 + 7] - LONG $0xc26e0f66 // movd xmm0, edx - QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 - LONG $0x54b60f42; WORD $0x083e // movzx edx, byte [rsi + r15 + 8] - LONG $0xc26e0f66 // movd xmm0, edx - QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x54b60f42; WORD $0x093e // movzx edx, byte [rsi + r15 + 9] - LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - LONG $0x54b60f42; WORD $0x0a3e // movzx edx, byte [rsi + r15 + 10] - LONG $0xc26e0f66 // movd xmm0, edx - QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 - LONG $0x54b60f42; WORD $0x0b3e // movzx edx, byte [rsi + r15 + 11] - LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx - LONG $0x54b60f42; WORD $0x0c3e // movzx edx, byte [rsi + r15 + 12] - LONG $0x6e0f4466; BYTE $0xea // movd xmm13, edx - LONG $0x54b60f42; WORD $0x0d3e // movzx edx, byte [rsi + r15 + 13] - LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx - LONG $0x54b60f42; WORD $0x0e3e // movzx edx, byte [rsi + r15 + 14] - LONG $0xc26e0f66 // movd xmm0, edx - QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 - LONG $0x247c894c; BYTE $0x30 // mov qword [rsp + 48], r15 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - LONG $0x20cd8349 // or r13, 32 - LONG $0x246c894c; BYTE $0x28 // mov qword [rsp + 40], r13 - LONG $0x40cf8348 // or rdi, 64 - LONG $0x60c98348 // or rcx, 96 - LONG $0x244c8948; BYTE $0x78 // mov qword [rsp + 120], rcx - LONG $0x80ca8149; WORD $0x0000; BYTE $0x00 // or r10, 128 - LONG $0xa0c88149; WORD $0x0000; BYTE $0x00 // or r8, 160 - LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0xe0c98149; WORD $0x0000; BYTE $0x00 // or r9, 224 - LONG $0x00cb8149; WORD $0x0001; BYTE $0x00 // or r11, 256 - LONG $0x20cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 288 - LONG $0x40ce8149; WORD $0x0001; BYTE $0x00 // or r14, 320 - LONG $0x01600d48; WORD $0x0000 // or rax, 352 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - LONG $0x80ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 384 - LONG $0x24548948; BYTE $0x68 // mov qword [rsp + 104], rdx - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - QUAD $0x012e3c203a0f4666 // pinsrb xmm15, byte [rsi + r13], 1 - QUAD $0x023e3c203a0f4466 // pinsrb xmm15, byte [rsi + rdi], 2 - QUAD $0x030e3c203a0f4466 // pinsrb xmm15, byte [rsi + rcx], 3 - QUAD $0x04163c203a0f4666 // pinsrb xmm15, byte [rsi + r10], 4 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 - LONG $0x2444894c; BYTE $0x48 // mov qword [rsp + 72], r8 - QUAD $0x05063c203a0f4666 // pinsrb xmm15, byte [rsi + r8], 5 - LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 - QUAD $0x06263c203a0f4666 // pinsrb xmm15, byte [rsi + r12], 6 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - QUAD $0x070e3c203a0f4666 // pinsrb xmm15, byte [rsi + r9], 7 - WORD $0x894d; BYTE $0xd9 // mov r9, r11 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - QUAD $0x081e3c203a0f4666 // pinsrb xmm15, byte [rsi + r11], 8 - LONG $0x245c8948; BYTE $0x40 // mov qword [rsp + 64], rbx - QUAD $0x091e3c203a0f4466 // pinsrb xmm15, byte [rsi + rbx], 9 - LONG $0x2474894c; BYTE $0x58 // mov qword [rsp + 88], r14 - QUAD $0x0a363c203a0f4666 // pinsrb xmm15, byte [rsi + r14], 10 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x0b2e3c203a0f4666 // pinsrb xmm15, byte [rsi + r13], 11 - QUAD $0x0c163c203a0f4466 // pinsrb xmm15, byte [rsi + rdx], 12 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0d0e3c203a0f4466 // pinsrb xmm15, byte [rsi + rcx], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0e0e3c203a0f4466 // pinsrb xmm15, byte [rsi + rcx], 14 - QUAD $0x0f063c203a0f4466 // pinsrb xmm15, byte [rsi + rax], 15 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x011e6c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rsi + r11 + 1], 1 - QUAD $0x02013e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 1], 2 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x011e6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r11 + 1], 3 - QUAD $0x01166c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r10 + 1], 4 - LONG $0x2454894c; BYTE $0x50 // mov qword [rsp + 80], r10 - QUAD $0x013e6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r15 + 1], 5 - QUAD $0x01266c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r12 + 1], 6 - QUAD $0x01066c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r8 + 1], 7 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 - QUAD $0x010e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r9 + 1], 8 - QUAD $0x09011e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 1], 9 - QUAD $0x01366c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r14 + 1], 10 - QUAD $0x012e6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r13 + 1], 11 - WORD $0x894d; BYTE $0xe8 // mov r8, r13 - QUAD $0x0c01166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 1], 12 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0d01166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 1], 13 - QUAD $0x0e010e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 1], 14 - QUAD $0x0f01066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 1], 15 - QUAD $0x00c0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 192] - LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 - LONG $0xfd6f0f66 // movdqa xmm7, xmm5 - QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI1_10] */ - LONG $0xfcdb0f66 // pand xmm7, xmm4 - LONG $0xfdf80f66 // psubb xmm7, xmm5 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - LONG $0x0654b60f; BYTE $0x0f // movzx edx, byte [rsi + rax + 15] - LONG $0x6e0f4466; BYTE $0xf2 // movd xmm14, edx - LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x01021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 1 - QUAD $0x02023e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 2], 2 - WORD $0x894d; BYTE $0xdc // mov r12, r11 - QUAD $0x021e74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r11 + 2], 3 - QUAD $0x021674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r10 + 2], 4 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x05020e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 2], 5 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x021e74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r11 + 2], 6 - LONG $0x247c894c; BYTE $0x70 // mov qword [rsp + 112], r15 - QUAD $0x023e74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r15 + 2], 7 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x022e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r13 + 2], 8 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x023674203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r14 + 2], 9 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x020e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r9 + 2], 10 - QUAD $0x020674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r8 + 2], 11 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0c021674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 2], 12 - LONG $0x24548b4c; BYTE $0x08 // mov r10, qword [rsp + 8] - QUAD $0x021674203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r10 + 2], 13 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0e021674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 2], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f021674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 2], 15 - LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 - LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 - QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xf0db0f66 // pand xmm6, xmm0 - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x0654b60f; BYTE $0x10 // movzx edx, byte [rsi + rax + 16] - LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - QUAD $0x01031e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 3], 1 - QUAD $0x02033e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 3], 2 - WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x032654203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r12 + 3], 3 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x032654203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r12 + 3], 4 - QUAD $0x05030e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 3], 5 - QUAD $0x031e54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r11 + 3], 6 - QUAD $0x033e54203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rsi + r15 + 3], 7 - QUAD $0x032e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r13 + 3], 8 - QUAD $0x033654203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r14 + 3], 9 - QUAD $0x030e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r9 + 3], 10 - WORD $0x894d; BYTE $0xce // mov r14, r9 - QUAD $0x030654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r8 + 3], 11 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x033e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r15 + 3], 12 - QUAD $0x031654203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r10 + 3], 13 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x032e54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r13 + 3], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f031654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 3], 15 - QUAD $0x01041e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 4], 1 - QUAD $0x02043e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 4], 2 - QUAD $0x0304064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 4], 3 - QUAD $0x04264c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r12 + 4], 4 - QUAD $0x05040e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 4], 5 - WORD $0x894c; BYTE $0xd9 // mov rcx, r11 - QUAD $0x041e4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rsi + r11 + 4], 6 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x041e4c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rsi + r11 + 4], 7 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x040e4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r9 + 4], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x09041e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 4], 9 - QUAD $0x04364c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r14 + 4], 10 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - QUAD $0x04064c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r8 + 4], 11 - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - QUAD $0x043e4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r15 + 4], 12 - QUAD $0x04164c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r10 + 4], 13 - QUAD $0x042e4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r13 + 4], 14 - QUAD $0x0f04164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 4], 15 - WORD $0x8949; BYTE $0xd2 // mov r10, rdx - LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - LONG $0x1e54b60f; BYTE $0x11 // movzx edx, byte [rsi + rbx + 17] - LONG $0xc26e0f66 // movd xmm0, edx - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0xd5db0f66 // pand xmm2, xmm5 - LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 - QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xcddb0f66 // pand xmm1, xmm5 - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0x1e54b60f; BYTE $0x12 // movzx edx, byte [rsi + rbx + 18] - LONG $0xea6e0f66 // movd xmm5, edx - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x050644203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rsi + r8 + 5], 1 - QUAD $0x053e44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rdi + 5], 2 - QUAD $0x050644203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rax + 5], 3 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x051644203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rdx + 5], 4 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x051644203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rsi + rdx + 5], 5 - QUAD $0x050e44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rcx + 5], 6 - QUAD $0x051e44203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rsi + r11 + 5], 7 - QUAD $0x050e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r9 + 5], 8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x050e44203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rsi + rcx + 5], 9 - QUAD $0x052644203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r12 + 5], 10 - QUAD $0x053644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r14 + 5], 11 - QUAD $0x053e44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r15 + 5], 12 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x050e44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rcx + 5], 13 - QUAD $0x052e44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r13 + 5], 14 - QUAD $0x051644203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r10 + 5], 15 - LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 - QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI1_14] */ - LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0x1e54b60f; BYTE $0x13 // movzx edx, byte [rsi + rbx + 19] - LONG $0xfa6e0f66 // movd xmm7, edx - LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - LONG $0x1e54b60f; BYTE $0x14 // movzx edx, byte [rsi + rbx + 20] - LONG $0xf26e0f66 // movd xmm6, edx - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - QUAD $0x06065c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r8 + 6], 1 - QUAD $0x02063e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 6], 2 - QUAD $0x0306065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 6], 3 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x061e5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r11 + 6], 4 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x060e5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r9 + 6], 5 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x06065c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r8 + 6], 6 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x06265c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r12 + 6], 7 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0806065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 6], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x09061e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 6], 9 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x06365c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r14 + 6], 10 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0b060e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 6], 11 - QUAD $0x063e5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r15 + 6], 12 - LONG $0x24548b4c; BYTE $0x08 // mov r10, qword [rsp + 8] - QUAD $0x06165c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r10 + 6], 13 - QUAD $0x062e5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rsi + r13 + 6], 14 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0f060e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 6], 15 - QUAD $0x0000d024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 208] - QUAD $0x01071654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 7], 1 - QUAD $0x02073e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 7], 2 - QUAD $0x000000a024bc8948 // mov qword [rsp + 160], rdi - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x03070e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 7], 3 - QUAD $0x071e54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r11 + 7], 4 - QUAD $0x070e54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r9 + 7], 5 - QUAD $0x070654203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r8 + 7], 6 - QUAD $0x072654203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rsi + r12 + 7], 7 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - QUAD $0x08070654203a0f66 // pinsrb xmm2, byte [rsi + rax + 7], 8 - QUAD $0x09071e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 7], 9 - QUAD $0x073654203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r14 + 7], 10 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b070654203a0f66 // pinsrb xmm2, byte [rsi + rax + 7], 11 - QUAD $0x073e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r15 + 7], 12 - QUAD $0x071654203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r10 + 7], 13 - QUAD $0x072e54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r13 + 7], 14 - LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] - QUAD $0x073654203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r14 + 7], 15 - LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 - QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI1_15] */ - LONG $0xd9db0f66 // pand xmm3, xmm1 - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 - LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI1_6] */ - LONG $0xd1db0f66 // pand xmm2, xmm1 - LONG $0xd3eb0f66 // por xmm2, xmm3 - LONG $0xca6f0f66 // movdqa xmm1, xmm2 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - LONG $0x1e54b60f; BYTE $0x15 // movzx edx, byte [rsi + rbx + 21] - LONG $0xd26e0f66 // movd xmm2, edx - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x091654203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rdx + 9], 1 - QUAD $0x093e54203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rdi + 9], 2 - QUAD $0x090e54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rcx + 9], 3 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x093e54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rdi + 9], 4 - QUAD $0x090e54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r9 + 9], 5 - QUAD $0x090654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r8 + 9], 6 - QUAD $0x091e54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r11 + 9], 7 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x090e54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rsi + rcx + 9], 8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x090e54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rcx + 9], 9 - QUAD $0x092654203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r12 + 9], 10 - QUAD $0x090654203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rsi + rax + 9], 11 - QUAD $0x093e54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r15 + 9], 12 - QUAD $0x091654203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r10 + 9], 13 - QUAD $0x092e54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r13 + 9], 14 - QUAD $0x093654203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r14 + 9], 15 - LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 - LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 - LONG $0xccdb0f66 // pand xmm1, xmm4 - LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 - LONG $0x1e54b60f; BYTE $0x16 // movzx edx, byte [rsi + rbx + 22] - LONG $0xda6e0f66 // movd xmm3, edx - QUAD $0x0000f024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 240] - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x081664203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r10 + 8], 1 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x082664203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r12 + 8], 2 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x03080664203a0f66 // pinsrb xmm4, byte [rsi + rax + 8], 3 - QUAD $0x04083e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 8], 4 - QUAD $0x080e64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r9 + 8], 5 - QUAD $0x080664203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r8 + 8], 6 - WORD $0x894c; BYTE $0xdb // mov rbx, r11 - QUAD $0x081e64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r11 + 8], 7 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x08081664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 8], 8 - QUAD $0x09080e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 8], 9 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a080e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 8], 10 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x083664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r14 + 8], 11 - QUAD $0x083e64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r15 + 8], 12 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0d083e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 8], 13 - QUAD $0x082e64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r13 + 8], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0f083e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 8], 15 - LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 - LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 - QUAD $0x00b024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 176] - QUAD $0x0a1654203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r10 + 10], 1 - QUAD $0x0a2654203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r12 + 10], 2 - QUAD $0x0a0654203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rax + 10], 3 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0a1e54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r11 + 10], 4 - QUAD $0x0a0e54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r9 + 10], 5 - QUAD $0x0a0654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r8 + 10], 6 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - QUAD $0x0a1e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rbx + 10], 7 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - QUAD $0x0a1654203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rsi + rdx + 10], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0a1e54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rbx + 10], 9 - QUAD $0x0a0e54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rcx + 10], 10 - QUAD $0x0a3654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r14 + 10], 11 - QUAD $0x0a3e54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r15 + 10], 12 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0a0e54203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rsi + rcx + 10], 13 - QUAD $0x0a2e54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r13 + 10], 14 - QUAD $0x0a3e54203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rsi + rdi + 10], 15 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - LONG $0x3e54b60f; BYTE $0x17 // movzx edx, byte [rsi + rdi + 23] - LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - QUAD $0x00b024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 176], xmm10 - LONG $0x3e54b60f; BYTE $0x18 // movzx edx, byte [rsi + rdi + 24] - LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0b165c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rdx + 11], 1 - QUAD $0x0b265c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rsi + r12 + 11], 2 - QUAD $0x0b065c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rsi + rax + 11], 3 - QUAD $0x0b1e5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r11 + 11], 4 - QUAD $0x0b0e5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r9 + 11], 5 - QUAD $0x0b165c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rsi + r10 + 11], 6 - QUAD $0x0b065c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r8 + 11], 7 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x0b0e5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r9 + 11], 8 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - QUAD $0x0b1e5c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rsi + rbx + 11], 9 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x0b3e5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rsi + rdi + 11], 10 - QUAD $0x0b365c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r14 + 11], 11 - QUAD $0x0b3e5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r15 + 11], 12 - QUAD $0x0b0e5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rcx + 11], 13 - QUAD $0x0b2e5c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rsi + r13 + 11], 14 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0b1e5c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rsi + rbx + 11], 15 - QUAD $0x0c166c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rsi + rdx + 12], 1 - QUAD $0x0c266c203a0f4666; BYTE $0x02 // pinsrb xmm13, byte [rsi + r12 + 12], 2 - QUAD $0x0c066c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rsi + rax + 12], 3 - QUAD $0x0c1e6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r11 + 12], 4 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0c2e6c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rsi + r13 + 12], 5 - QUAD $0x0c166c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rsi + r10 + 12], 6 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x0c1e6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rsi + rbx + 12], 7 - QUAD $0x0c0e6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r9 + 12], 8 - WORD $0x894d; BYTE $0xca // mov r10, r9 - QUAD $0x0c066c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r8 + 12], 9 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - QUAD $0x0c3e6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rsi + rdi + 12], 10 - WORD $0x8949; BYTE $0xf8 // mov r8, rdi - QUAD $0x0c366c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r14 + 12], 11 - QUAD $0x0c3e6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r15 + 12], 12 - QUAD $0x0c0e6c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rcx + 12], 13 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0c2e6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r13 + 12], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0c3e6c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rsi + rdi + 12], 15 - QUAD $0x0d1664203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rdx + 13], 1 - QUAD $0x0d2664203a0f4666; BYTE $0x02 // pinsrb xmm12, byte [rsi + r12 + 13], 2 - QUAD $0x0d0664203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rsi + rax + 13], 3 - QUAD $0x0d1e64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rsi + r11 + 13], 4 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0d0664203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rsi + rax + 13], 5 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0d1664203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rdx + 13], 6 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x0d1e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rbx + 13], 7 - QUAD $0x0d1664203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r10 + 13], 8 - QUAD $0x0d0e64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r9 + 13], 9 - QUAD $0x0d0664203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r8 + 13], 10 - QUAD $0x0d3664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r14 + 13], 11 - QUAD $0x0d3e64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r15 + 13], 12 - QUAD $0x0d0e64203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rsi + rcx + 13], 13 - QUAD $0x0d2e64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r13 + 13], 14 - QUAD $0x0d3e64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rsi + rdi + 13], 15 - LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 - QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 - QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - LONG $0x0e54b60f; BYTE $0x19 // movzx edx, byte [rsi + rcx + 25] - LONG $0xca6e0f66 // movd xmm1, edx - LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 - QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI1_14] */ - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0x0e54b60f; BYTE $0x1a // movzx edx, byte [rsi + rcx + 26] - LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx - QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x010e0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 14], 1 - QUAD $0x0e2664203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r12 + 14], 2 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0e1664203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r10 + 14], 3 - QUAD $0x0e1e64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r11 + 14], 4 - QUAD $0x050e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 14], 5 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x060e0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 14], 6 - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - QUAD $0x070e1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 14], 7 - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x0e0664203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r8 + 14], 8 - QUAD $0x0e0e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r9 + 14], 9 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0a0e1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 14], 10 - QUAD $0x0e3664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r14 + 14], 11 - QUAD $0x0e3e64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r15 + 14], 12 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0d0e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 14], 13 - QUAD $0x0e2e64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r13 + 14], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f0e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 14], 15 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0f1674203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rsi + rdx + 15], 1 - QUAD $0x0f2674203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rsi + r12 + 15], 2 - QUAD $0x0f1674203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rsi + r10 + 15], 3 - QUAD $0x0f1e74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rsi + r11 + 15], 4 - QUAD $0x0f0674203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rsi + rax + 15], 5 - QUAD $0x0f0e74203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rsi + rcx + 15], 6 - QUAD $0x0f3e74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rsi + rdi + 15], 7 - QUAD $0x0f0674203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r8 + 15], 8 - QUAD $0x0f0e74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r9 + 15], 9 - QUAD $0x0f1e74203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rsi + rbx + 15], 10 - QUAD $0x0f3674203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rsi + r14 + 15], 11 - QUAD $0x0f3e74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rsi + r15 + 15], 12 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0f1674203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rsi + rdx + 15], 13 - QUAD $0x0f2e74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rsi + r13 + 15], 14 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0f1674203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rsi + rdx + 15], 15 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x10167c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rdx + 16], 1 - QUAD $0x10267c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rsi + r12 + 16], 2 - QUAD $0x10167c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rsi + r10 + 16], 3 - QUAD $0x101e7c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rsi + r11 + 16], 4 - QUAD $0x10067c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rax + 16], 5 - QUAD $0x100e7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rcx + 16], 6 - QUAD $0x103e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rdi + 16], 7 - QUAD $0x10067c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r8 + 16], 8 - QUAD $0x100e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r9 + 16], 9 - QUAD $0x101e7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rsi + rbx + 16], 10 - QUAD $0x10367c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r14 + 16], 11 - QUAD $0x103e7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r15 + 16], 12 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x10167c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rsi + rdx + 16], 13 - QUAD $0x102e7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r13 + 16], 14 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x01111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 1 - QUAD $0x112644203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r12 + 17], 2 - QUAD $0x111644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r10 + 17], 3 - QUAD $0x111e44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r11 + 17], 4 - QUAD $0x05110644203a0f66 // pinsrb xmm0, byte [rsi + rax + 17], 5 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x06110e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 17], 6 - QUAD $0x07113e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 17], 7 - QUAD $0x110644203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r8 + 17], 8 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x110e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r9 + 17], 9 - QUAD $0x0a111e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 17], 10 - QUAD $0x113644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r14 + 17], 11 - QUAD $0x113e44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r15 + 17], 12 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0d111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 13 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0e111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 14 - QUAD $0x00b024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 176] - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x54b60f42; WORD $0x1b26 // movzx edx, byte [rsi + r12 + 27] - LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx - QUAD $0x00c024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 192] - LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 - QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI1_15] */ - LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 - LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 - LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI1_6] */ - LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 - LONG $0x54b60f42; WORD $0x1c26 // movzx edx, byte [rsi + r12 + 28] - LONG $0xe26e0f66 // movd xmm4, edx - LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] - QUAD $0x110644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r8 + 17], 15 - LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 - LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 - LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 - QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI1_10] */ - LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 - LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 - QUAD $0x00b024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 176], xmm13 - LONG $0x54b60f42; WORD $0x1d26 // movzx edx, byte [rsi + r12 + 29] - LONG $0x6e0f4466; BYTE $0xea // movd xmm13, edx - QUAD $0x10067c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r8 + 16], 15 - QUAD $0x0000c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 192] - LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x12266c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rsi + r12 + 18], 1 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0212166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 18], 2 - QUAD $0x12166c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r10 + 18], 3 - QUAD $0x121e6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r11 + 18], 4 - QUAD $0x122e6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r13 + 18], 5 - QUAD $0x06120e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 18], 6 - QUAD $0x07123e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 18], 7 - QUAD $0x0812066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 18], 8 - QUAD $0x120e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r9 + 18], 9 - QUAD $0x0a121e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 18], 10 - QUAD $0x12366c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r14 + 18], 11 - QUAD $0x123e6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r15 + 18], 12 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0d12166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 18], 13 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0e12166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 18], 14 - LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 - QUAD $0x12066c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r8 + 18], 15 - LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 - QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - LONG $0x0654b60f; BYTE $0x1e // movzx edx, byte [rsi + rax + 30] - LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx - QUAD $0x13267c203a0f4266; BYTE $0x01 // pinsrb xmm7, byte [rsi + r12 + 19], 1 - QUAD $0x142674203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r12 + 20], 1 - QUAD $0x152654203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r12 + 21], 1 - QUAD $0x16265c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r12 + 22], 1 - QUAD $0x172644203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rsi + r12 + 23], 1 - QUAD $0x182654203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r12 + 24], 1 - QUAD $0x19264c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rsi + r12 + 25], 1 - QUAD $0x1a265c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rsi + r12 + 26], 1 - QUAD $0x1b264c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rsi + r12 + 27], 1 - QUAD $0x1c2664203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r12 + 28], 1 - QUAD $0x1d266c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rsi + r12 + 29], 1 - QUAD $0x1e2664203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rsi + r12 + 30], 1 - LONG $0x0654b60f; BYTE $0x1f // movzx edx, byte [rsi + rax + 31] - LONG $0xc26e0f66 // movd xmm0, edx - QUAD $0x1f2644203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rsi + r12 + 31], 1 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x0213167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 19], 2 - QUAD $0x02141674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 20], 2 - QUAD $0x02151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 2 - QUAD $0x0216165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 22], 2 - QUAD $0x171644203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rdx + 23], 2 - QUAD $0x181654203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rdx + 24], 2 - QUAD $0x0219164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 25], 2 - QUAD $0x1a165c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rdx + 26], 2 - QUAD $0x1b164c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rdx + 27], 2 - QUAD $0x021c1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 28], 2 - QUAD $0x1d166c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rdx + 29], 2 - QUAD $0x1e1664203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rdx + 30], 2 - QUAD $0x021f1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 31], 2 - QUAD $0x13167c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rsi + r10 + 19], 3 - QUAD $0x131e7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r11 + 19], 4 - QUAD $0x132e7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r13 + 19], 5 - QUAD $0x06130e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 19], 6 - QUAD $0x07133e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 19], 7 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0813067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 19], 8 - QUAD $0x130e7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r9 + 19], 9 - QUAD $0x0a131e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 19], 10 - QUAD $0x13367c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r14 + 19], 11 - QUAD $0x133e7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r15 + 19], 12 - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - QUAD $0x0d13167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 19], 13 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x13267c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rsi + r12 + 19], 14 - QUAD $0x13067c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r8 + 19], 15 - QUAD $0x141674203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r10 + 20], 3 - QUAD $0x141e74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r11 + 20], 4 - QUAD $0x142e74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r13 + 20], 5 - QUAD $0x06140e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 20], 6 - QUAD $0x07143e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 20], 7 - QUAD $0x08140674203a0f66 // pinsrb xmm6, byte [rsi + rax + 20], 8 - QUAD $0x140e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r9 + 20], 9 - QUAD $0x0a141e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 20], 10 - QUAD $0x143674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r14 + 20], 11 - QUAD $0x143e74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r15 + 20], 12 - QUAD $0x0d141674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 20], 13 - QUAD $0x142674203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r12 + 20], 14 - QUAD $0x0000b024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 176] - QUAD $0x140674203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r8 + 20], 15 - QUAD $0x00c024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 192] - LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 - QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 - QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0x151654203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r10 + 21], 3 - QUAD $0x151e54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r11 + 21], 4 - QUAD $0x152e54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r13 + 21], 5 - QUAD $0x06150e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 21], 6 - QUAD $0x07153e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 21], 7 - QUAD $0x08150654203a0f66 // pinsrb xmm2, byte [rsi + rax + 21], 8 - QUAD $0x150e54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r9 + 21], 9 - QUAD $0x0a151e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 21], 10 - QUAD $0x153654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r14 + 21], 11 - QUAD $0x153e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r15 + 21], 12 - QUAD $0x0d151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 13 - QUAD $0x152654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r12 + 21], 14 - QUAD $0x150654203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r8 + 21], 15 - LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 - QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI1_14] */ - LONG $0xd7db0f66 // pand xmm2, xmm7 - LONG $0xd6eb0f66 // por xmm2, xmm6 - LONG $0xd5eb0f66 // por xmm2, xmm5 - QUAD $0x16165c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r10 + 22], 3 - QUAD $0x161e5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r11 + 22], 4 - QUAD $0x162e5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r13 + 22], 5 - QUAD $0x06160e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 22], 6 - QUAD $0x07163e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 22], 7 - QUAD $0x0816065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 22], 8 - QUAD $0x160e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r9 + 22], 9 - QUAD $0x0a161e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 22], 10 - QUAD $0x16365c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r14 + 22], 11 - QUAD $0x163e5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r15 + 22], 12 - QUAD $0x0d16165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 22], 13 - QUAD $0x16265c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rsi + r12 + 22], 14 - QUAD $0x16065c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r8 + 22], 15 - QUAD $0x171644203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rsi + r10 + 23], 3 - QUAD $0x171e44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r11 + 23], 4 - QUAD $0x172e44203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r13 + 23], 5 - QUAD $0x170e44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rcx + 23], 6 - QUAD $0x173e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rdi + 23], 7 - QUAD $0x170644203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rsi + rax + 23], 8 - QUAD $0x170e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r9 + 23], 9 - QUAD $0x171e44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rsi + rbx + 23], 10 - QUAD $0x173644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r14 + 23], 11 - QUAD $0x173e44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r15 + 23], 12 - QUAD $0x171644203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rdx + 23], 13 - QUAD $0x172644203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r12 + 23], 14 - QUAD $0x170644203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r8 + 23], 15 - LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 - QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI1_15] */ - LONG $0xdddb0f66 // pand xmm3, xmm5 - LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 - LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 - LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI1_6] */ - LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 - LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - QUAD $0x19164c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rsi + r10 + 25], 3 - QUAD $0x191e4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r11 + 25], 4 - QUAD $0x192e4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r13 + 25], 5 - QUAD $0x06190e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 25], 6 - QUAD $0x07193e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 25], 7 - QUAD $0x0819064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 25], 8 - QUAD $0x190e4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r9 + 25], 9 - QUAD $0x0a191e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 25], 10 - QUAD $0x19364c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r14 + 25], 11 - QUAD $0x193e4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r15 + 25], 12 - QUAD $0x0d19164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 25], 13 - QUAD $0x19264c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r12 + 25], 14 - QUAD $0x19064c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r8 + 25], 15 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 - LONG $0xd16f0f66 // movdqa xmm2, xmm1 - QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI1_10] */ - LONG $0xd3db0f66 // pand xmm2, xmm3 - LONG $0xd1f80f66 // psubb xmm2, xmm1 - QUAD $0x181654203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r10 + 24], 3 - QUAD $0x181e54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r11 + 24], 4 - QUAD $0x182e54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r13 + 24], 5 - QUAD $0x180e54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rcx + 24], 6 - QUAD $0x183e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rdi + 24], 7 - QUAD $0x180654203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rsi + rax + 24], 8 - QUAD $0x180e54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r9 + 24], 9 - QUAD $0x181e54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rbx + 24], 10 - QUAD $0x183654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r14 + 24], 11 - QUAD $0x183e54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r15 + 24], 12 - QUAD $0x181654203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rsi + rdx + 24], 13 - QUAD $0x182654203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r12 + 24], 14 - QUAD $0x180654203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r8 + 24], 15 - LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 - LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 - QUAD $0x1a165c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r10 + 26], 3 - QUAD $0x1a1e5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r11 + 26], 4 - QUAD $0x1a2e5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r13 + 26], 5 - QUAD $0x1a0e5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rsi + rcx + 26], 6 - QUAD $0x1a3e5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rsi + rdi + 26], 7 - QUAD $0x1a065c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rsi + rax + 26], 8 - QUAD $0x1a0e5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r9 + 26], 9 - QUAD $0x1a1e5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rsi + rbx + 26], 10 - QUAD $0x1a365c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r14 + 26], 11 - QUAD $0x1a3e5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r15 + 26], 12 - QUAD $0x1a165c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rdx + 26], 13 - QUAD $0x1a265c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rsi + r12 + 26], 14 - QUAD $0x1a065c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rsi + r8 + 26], 15 - LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 - QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI1_11] */ - LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 - LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 - QUAD $0x1b164c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r10 + 27], 3 - QUAD $0x1b1e4c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rsi + r11 + 27], 4 - QUAD $0x1b2e4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r13 + 27], 5 - QUAD $0x1b0e4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rcx + 27], 6 - QUAD $0x1b3e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rdi + 27], 7 - QUAD $0x1b064c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rsi + rax + 27], 8 - QUAD $0x1b0e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r9 + 27], 9 - QUAD $0x1b1e4c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rsi + rbx + 27], 10 - QUAD $0x1b364c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r14 + 27], 11 - QUAD $0x1b3e4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r15 + 27], 12 - QUAD $0x1b164c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rsi + rdx + 27], 13 - QUAD $0x1b264c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r12 + 27], 14 - QUAD $0x1b064c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r8 + 27], 15 - QUAD $0x1c1664203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r10 + 28], 3 - QUAD $0x1c1e64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r11 + 28], 4 - QUAD $0x1c2e64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r13 + 28], 5 - QUAD $0x061c0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 28], 6 - QUAD $0x071c3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 28], 7 - QUAD $0x081c0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 28], 8 - QUAD $0x1c0e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r9 + 28], 9 - QUAD $0x0a1c1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 28], 10 - QUAD $0x1c3664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r14 + 28], 11 - QUAD $0x1c3e64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r15 + 28], 12 - QUAD $0x0d1c1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 28], 13 - QUAD $0x1c2664203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r12 + 28], 14 - QUAD $0x1c0664203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r8 + 28], 15 - QUAD $0x1d166c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rsi + r10 + 29], 3 - QUAD $0x1d1e6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r11 + 29], 4 - QUAD $0x1d2e6c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rsi + r13 + 29], 5 - QUAD $0x1d0e6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rsi + rcx + 29], 6 - QUAD $0x1d3e6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rsi + rdi + 29], 7 - QUAD $0x1d066c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rsi + rax + 29], 8 - QUAD $0x1d0e6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r9 + 29], 9 - QUAD $0x1d1e6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rsi + rbx + 29], 10 - QUAD $0x1d366c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r14 + 29], 11 - QUAD $0x1d3e6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r15 + 29], 12 - QUAD $0x1d166c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rdx + 29], 13 - QUAD $0x1d266c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r12 + 29], 14 - LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 - LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 - QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI1_12] */ - LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 - QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI1_13] */ - LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 - QUAD $0x1d066c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rsi + r8 + 29], 15 - LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 - LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 - LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 - QUAD $0x1e1664203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rsi + r10 + 30], 3 - QUAD $0x1f1644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r10 + 31], 3 - QUAD $0x1e1e64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rsi + r11 + 30], 4 - QUAD $0x1f1e44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r11 + 31], 4 - QUAD $0x1e2e64203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r13 + 30], 5 - QUAD $0x1f2e44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r13 + 31], 5 - QUAD $0x1e0e64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rcx + 30], 6 - QUAD $0x061f0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 31], 6 - QUAD $0x1e3e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rdi + 30], 7 - QUAD $0x071f3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 31], 7 - QUAD $0x1e0664203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rsi + rax + 30], 8 - QUAD $0x081f0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 31], 8 - QUAD $0x1e0e64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r9 + 30], 9 - QUAD $0x1f0e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r9 + 31], 9 - QUAD $0x1e1e64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rsi + rbx + 30], 10 - QUAD $0x0a1f1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 31], 10 - QUAD $0x1e3664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r14 + 30], 11 - QUAD $0x1f3644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r14 + 31], 11 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x1e3e64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r15 + 30], 12 - QUAD $0x1f3e44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r15 + 31], 12 - QUAD $0x1e1664203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rsi + rdx + 30], 13 - QUAD $0x0d1f1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 31], 13 - QUAD $0x1e2664203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r12 + 30], 14 - QUAD $0x1f2644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r12 + 31], 14 - QUAD $0x1e0664203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rsi + r8 + 30], 15 - QUAD $0x1f0644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r8 + 31], 15 - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 - LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 - LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0xc6db0f66 // pand xmm0, xmm6 - LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 - LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 - LONG $0xc8600f66 // punpcklbw xmm1, xmm0 - QUAD $0x0000d024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 208] - LONG $0xd46f0f66 // movdqa xmm2, xmm4 - LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 - LONG $0xda6f0f66 // movdqa xmm3, xmm2 - LONG $0xd9610f66 // punpcklwd xmm3, xmm1 - LONG $0xd1690f66 // punpckhwd xmm2, xmm1 - LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 - LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x647f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm4 - LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 - LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 - LONG $0x1c7f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm3 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB1_68 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x000000e824bc3b4c // cmp r15, qword [rsp + 232] - LONG $0x245c8a44; BYTE $0x04 // mov r11b, byte [rsp + 4] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - JNE LBB1_70 - JMP LBB1_73 +LBB1_97: + WORD $0xc031 // xor eax, eax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + +LBB1_103: + QUAD $0x00000098248c2b48 // sub rcx, qword [rsp + 152] + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] + +LBB1_104: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x01763844 // cmp byte [rsi + 1], r14b + LONG $0xd6940f40 // sete sil + LONG $0x02713844 // cmp byte [rcx + 2], r14b + LONG $0xd3940f41 // sete r11b + LONG $0x03713844 // cmp byte [rcx + 3], r14b + LONG $0xd7940f41 // sete r15b + LONG $0x04713844 // cmp byte [rcx + 4], r14b + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al + LONG $0xd5940f41 // sete r13b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al + LONG $0xd0940f41 // sete r8b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + QUAD $0x000000e02494940f // sete byte [rsp + 224] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al + WORD $0x940f; BYTE $0xd2 // sete dl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0xd7940f40 // sete dil + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd1940f41 // sete r9b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd6940f41 // sete r14b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000000d02494940f // sete byte [rsp + 208] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + WORD $0x940f; BYTE $0xd0 // sete al + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + QUAD $0x000000b02494940f // sete byte [rsp + 176] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd2940f41 // sete r10b + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] + LONG $0x06e5c041 // shl r13b, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xe8 // or r8b, r13b + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0841; BYTE $0xf3 // or r11b, sil + WORD $0xd200 // add dl, dl + LONG $0xe0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 224] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xd7 // or dil, dl + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xfa // or dl, r15b + WORD $0xd689 // mov esi, edx + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0841; BYTE $0xf9 // or r9b, dil + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x247cb60f; BYTE $0x08 // movzx edi, byte [rsp + 8] + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xce // or r14b, r9b + QUAD $0x000000c02494b60f // movzx edx, byte [rsp + 192] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xf2 // or dl, r14b + WORD $0x8941; BYTE $0xd1 // mov r9d, edx + WORD $0x8941; BYTE $0xfe // mov r14d, edi + QUAD $0x000000d02494b60f // movzx edx, byte [rsp + 208] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd008 // or al, dl + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0844; BYTE $0xc8 // or al, r9b + QUAD $0x000000b02494b60f // movzx edx, byte [rsp + 176] + WORD $0xd200 // add dl, dl + LONG $0xa0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 160] + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x24048845 // mov byte [r12], r8b + LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xf2 // or r10b, sil + LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + WORD $0x0841; BYTE $0xd2 // or r10b, dl + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xc000 // add al, al + LONG $0x40244402 // add al, byte [rsp + 64] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x24548845; BYTE $0x02 // mov byte [r12 + 2], r10b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 + JNE LBB1_104 + QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x00000118248c8b48 // mov rcx, qword [rsp + 280] + JMP LBB1_106 + +LBB1_93: + QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + +LBB1_106: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB1_222 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB1_109 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB1_112 + +LBB1_62: + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB1_222 + +LBB1_64: + LONG $0x01c48349 // add r12, 1 + +LBB1_65: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB1_66 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x245c8844; BYTE $0x08 // mov byte [rsp + 8], r11b + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x00000118248c8948 // mov qword [rsp + 280], rcx + JB LBB1_70 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB1_73 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB1_73 + +LBB1_70: + WORD $0xc031 // xor eax, eax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + +LBB1_76: + QUAD $0x00000098248c2b48 // sub rcx, qword [rsp + 152] + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] + +LBB1_77: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b + QUAD $0x000001002494940f // sete byte [rsp + 256] + LONG $0x015e3844 // cmp byte [rsi + 1], r11b + LONG $0xd6940f40 // sete sil + LONG $0x02593844 // cmp byte [rcx + 2], r11b + LONG $0xd7940f41 // sete r15b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al + LONG $0xd5940f41 // sete r13b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al + LONG $0xd1940f41 // sete r9b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + QUAD $0x000000e02494940f // sete byte [rsp + 224] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al + WORD $0x940f; BYTE $0xd2 // sete dl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0xd0940f41 // sete r8b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd2940f41 // sete r10b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd6940f41 // sete r14b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000000d02494940f // sete byte [rsp + 208] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd4940f41 // sete r12b + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + QUAD $0x000000b02494940f // sete byte [rsp + 176] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd3940f41 // sete r11b + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000010024b40240 // add sil, byte [rsp + 256] + LONG $0x06e5c041 // shl r13b, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0845; BYTE $0xe9 // or r9b, r13b + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + WORD $0xd200 // add dl, dl + LONG $0xe0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 224] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x7cb60f44; WORD $0x0824 // movzx r15d, byte [rsp + 8] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000d024b4b60f // movzx esi, byte [rsp + 208] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xf4 // or r12b, sil + WORD $0x0841; BYTE $0xd1 // or r9b, dl + WORD $0x0841; BYTE $0xc4 // or r12b, al + QUAD $0x000000b02494b60f // movzx edx, byte [rsp + 176] + WORD $0xd200 // add dl, dl + LONG $0xa0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 160] + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0x8844; BYTE $0x0f // mov byte [rdi], r9b + LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xf3 // or r11b, sil + LONG $0x01678844 // mov byte [rdi + 1], r12b + WORD $0x0841; BYTE $0xd3 // or r11b, dl + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xc000 // add al, al + LONG $0x38244402 // add al, byte [rsp + 56] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x025f8844 // mov byte [rdi + 2], r11b + WORD $0x8945; BYTE $0xfb // mov r11d, r15d + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB1_77 + QUAD $0x0000009024bc8948 // mov qword [rsp + 144], rdi + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x00000118248c8b48 // mov rcx, qword [rsp + 280] + JMP LBB1_79 + +LBB1_66: + QUAD $0x0000009024a4894c // mov qword [rsp + 144], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + +LBB1_79: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB1_222 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB1_82 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB1_85 + +LBB1_175: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB1_176: + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0x08768d48 // lea rsi, [rsi + 8] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3c148841 // mov byte [r12 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB1_176 + +LBB1_22: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_222 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + JMP LBB1_24 + +LBB1_109: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] + +LBB1_110: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e343846 // cmp byte [rsi + r9], r14b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x06743844; BYTE $0x01 // cmp byte [rsi + rax + 1], r14b + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB1_110 + WORD $0x014c; BYTE $0xce // add rsi, r9 + +LBB1_112: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_222 + WORD $0x3844; BYTE $0x36 // cmp byte [rsi], r14b + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + LONG $0x163c8a41 // mov dil, byte [r14 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x161c8841 // mov byte [r14 + rdx], bl + JMP LBB1_222 + +LBB1_82: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + +LBB1_83: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3e048841 // mov byte [r14 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB1_83 + WORD $0x014c; BYTE $0xce // add rsi, r9 + +LBB1_85: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_222 + WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + JMP LBB1_87 + +LBB1_218: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB1_219: + LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] + WORD $0x9b0f; BYTE $0xd1 // setnp cl + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xc820 // and al, cl + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x3c // movzx r10d, byte [r12 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x462e0f66; BYTE $0x08 // ucomisd xmm0, qword [rsi + 8] + LONG $0x10768d48 // lea rsi, [rsi + 16] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3c148841 // mov byte [r12 + rdi], dl + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB1_219 + +LBB1_220: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_222 + LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xc220 // and dl, al + WORD $0xdaf6 // neg dl + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + LONG $0x03e8c148 // shr rax, 3 + LONG $0x04348a41 // mov sil, byte [r12 + rax] + LONG $0x07e38041 // and r11b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf2 // xor dl, sil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xf3 // xor bl, sil + LONG $0x041c8841 // mov byte [r12 + rax], bl + JMP LBB1_222 + +LBB1_191: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB1_192: + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0x10768d48 // lea rsi, [rsi + 16] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3c148841 // mov byte [r12 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB1_192 + +LBB1_41: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_222 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + +LBB1_24: + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x14348a41 // mov sil, byte [r12 + rdx] + LONG $0x07e38041 // and r11b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xf3 // xor bl, sil + LONG $0x141c8841 // mov byte [r12 + rdx], bl + JMP LBB1_222 + +LBB1_159: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] + +LBB1_160: + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x14b60f45; BYTE $0x3b // movzx r10d, byte [r11 + rdi] + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + LONG $0x02c68349 // add r14, 2 + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w + LONG $0x04768d48 // lea rsi, [rsi + 4] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + WORD $0xda30 // xor dl, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd020 // and al, dl + WORD $0xd830 // xor al, bl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB1_160 + +LBB1_135: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_222 + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e68041 // and r14b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + +LBB1_87: + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + JMP LBB1_222 + +LBB1_216: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xf631 // xor esi, esi + WORD $0x894d; BYTE $0xee // mov r14, r13 + +LBB1_217: + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x9b0f; BYTE $0xd1 // setnp cl + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xca20 // and dl, cl + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x03efc148 // shr rdi, 3 + LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] + WORD $0xf189 // mov ecx, esi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0xb341; BYTE $0x01 // mov r11b, 1 + WORD $0xd241; BYTE $0xe3 // shl r11b, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0x2041; BYTE $0xd3 // and r11b, dl + WORD $0x3045; BYTE $0xd3 // xor r11b, r10b + LONG $0x3e1c8845 // mov byte [r14 + rdi], r11b + LONG $0x02c68348 // add rsi, 2 + LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] + LONG $0x085b8d48 // lea rbx, [rbx + 8] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x2044; BYTE $0xd2 // and dl, r10b + WORD $0xdaf6 // neg dl + WORD $0x3044; BYTE $0xda // xor dl, r11b + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xd8 // xor al, r11b + LONG $0x3e048841 // mov byte [r14 + rdi], al + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB1_217 + +LBB1_214: + LONG $0x01c0f641 // test r8b, 1 + JE LBB1_222 + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xc220 // and dl, al + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x03e8c148 // shr rax, 3 + LONG $0x057c8a41; BYTE $0x00 // mov dil, byte [r13 + rax] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xfa // xor dl, dil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x055c8841; BYTE $0x00 // mov byte [r13 + rax], bl + +LBB1_222: + MOVQ 320(SP), SP + RET -LBB1_111: - LONG $0xf8e78349 // and r15, -8 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB1_126: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - LONG $0x6e0f4166; BYTE $0xc3 // movd xmm0, r11d + LONG $0x246c8944; BYTE $0x38 // mov dword [rsp + 56], r13d + LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 WORD $0x3145; BYTE $0xff // xor r15d, r15d @@ -7897,99 +6346,99 @@ LBB1_111: LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI1_4] */ LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI1_5] */ LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI1_6] */ - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 -LBB1_112: - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 +LBB1_127: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06e7c149 // shl r15, 6 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xfa // mov rdx, r15 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 LONG $0x34b70f46; BYTE $0x3e // movzx r14d, word [rsi + r15] - LONG $0x44b70f42; WORD $0x023e // movzx eax, word [rsi + r15 + 2] - LONG $0x54b70f46; WORD $0x043e // movzx r10d, word [rsi + r15 + 4] - LONG $0x7cb70f42; WORD $0x063e // movzx edi, word [rsi + r15 + 6] - LONG $0x5cb70f46; WORD $0x083e // movzx r11d, word [rsi + r15 + 8] - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - LONG $0x40c88349 // or r8, 64 - LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + LONG $0x7cb70f42; WORD $0x023e // movzx edi, word [rsi + r15 + 2] + LONG $0x5cb70f46; WORD $0x043e // movzx r11d, word [rsi + r15 + 4] + LONG $0x6cb70f46; WORD $0x063e // movzx r13d, word [rsi + r15 + 6] + LONG $0x54b70f46; WORD $0x083e // movzx r10d, word [rsi + r15 + 8] + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + LONG $0x40c98349 // or r9, 64 + LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 + LONG $0x00ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 256 LONG $0x40c98148; WORD $0x0001; BYTE $0x00 // or rcx, 320 - LONG $0x80ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 384 - LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 + LONG $0x01c00d48; WORD $0x0000 // or rax, 448 LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d - LONG $0xc40f4266; WORD $0x0624; BYTE $0x01 // pinsrw xmm4, word [rsi + r8], 1 - LONG $0xc40f4266; WORD $0x0e24; BYTE $0x02 // pinsrw xmm4, word [rsi + r9], 2 + LONG $0xc40f4266; WORD $0x0e24; BYTE $0x01 // pinsrw xmm4, word [rsi + r9], 1 + LONG $0xc40f4266; WORD $0x0624; BYTE $0x02 // pinsrw xmm4, word [rsi + r8], 2 LONG $0xc40f4266; WORD $0x2624; BYTE $0x03 // pinsrw xmm4, word [rsi + r12], 3 - LONG $0xc40f4266; WORD $0x2e24; BYTE $0x04 // pinsrw xmm4, word [rsi + r13], 4 + LONG $0x24c40f66; WORD $0x0416 // pinsrw xmm4, word [rsi + rdx], 4 LONG $0x24c40f66; WORD $0x050e // pinsrw xmm4, word [rsi + rcx], 5 - LONG $0x24c40f66; WORD $0x0616 // pinsrw xmm4, word [rsi + rdx], 6 - LONG $0x24c40f66; WORD $0x071e // pinsrw xmm4, word [rsi + rbx], 7 + LONG $0x24c40f66; WORD $0x061e // pinsrw xmm4, word [rsi + rbx], 6 + LONG $0x24c40f66; WORD $0x0706 // pinsrw xmm4, word [rsi + rax], 7 LONG $0x74b70f46; WORD $0x0a3e // movzx r14d, word [rsi + r15 + 10] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x01020674c40f4266 // pinsrw xmm6, word [rsi + r8 + 2], 1 - QUAD $0x02020e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 2], 2 + LONG $0xf76e0f66 // movd xmm6, edi + QUAD $0x01020e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 2], 1 + QUAD $0x02020674c40f4266 // pinsrw xmm6, word [rsi + r8 + 2], 2 QUAD $0x03022674c40f4266 // pinsrw xmm6, word [rsi + r12 + 2], 3 - LONG $0x44b70f42; WORD $0x0c3e // movzx eax, word [rsi + r15 + 12] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x04022e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 2], 4 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x44b70f42; WORD $0x0e3e // movzx eax, word [rsi + r15 + 14] - LONG $0x10244489 // mov dword [rsp + 16], eax + LONG $0x7cb70f42; WORD $0x0c3e // movzx edi, word [rsi + r15 + 12] + LONG $0x10247c89 // mov dword [rsp + 16], edi + LONG $0x74c40f66; WORD $0x0216; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 2], 4 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x5cb70f46; WORD $0x0e3e // movzx r11d, word [rsi + r15 + 14] LONG $0x74c40f66; WORD $0x020e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 2], 5 - LONG $0xef6e0f66 // movd xmm5, edi + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d LONG $0x7cb70f42; WORD $0x103e // movzx edi, word [rsi + r15 + 16] - LONG $0x74c40f66; WORD $0x0216; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 2], 6 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x44b70f42; WORD $0x123e // movzx eax, word [rsi + r15 + 18] - LONG $0x30244489 // mov dword [rsp + 48], eax - LONG $0x74c40f66; WORD $0x021e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 2], 7 + LONG $0x28247c89 // mov dword [rsp + 40], edi + LONG $0x74c40f66; WORD $0x021e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 2], 6 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x7cb70f42; WORD $0x123e // movzx edi, word [rsi + r15 + 18] + LONG $0x30247c89 // mov dword [rsp + 48], edi + LONG $0x74c40f66; WORD $0x0206; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 2], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xce6f0f66 // movdqa xmm1, xmm6 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xcef80f66 // psubb xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d - LONG $0x54b70f46; WORD $0x143e // movzx r10d, word [rsi + r15 + 20] + LONG $0x6cb70f46; WORD $0x143e // movzx r13d, word [rsi + r15 + 20] LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - QUAD $0x01040654c40f4266 // pinsrw xmm2, word [rsi + r8 + 4], 1 - QUAD $0x02040e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 4], 2 + QUAD $0x01040e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 4], 1 + QUAD $0x02040654c40f4266 // pinsrw xmm2, word [rsi + r8 + 4], 2 QUAD $0x03042654c40f4266 // pinsrw xmm2, word [rsi + r12 + 4], 3 - QUAD $0x04042e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 4], 4 + LONG $0x54c40f66; WORD $0x0416; BYTE $0x04 // pinsrw xmm2, word [rsi + rdx + 4], 4 LONG $0x54c40f66; WORD $0x040e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 4], 5 - LONG $0x54c40f66; WORD $0x0416; BYTE $0x06 // pinsrw xmm2, word [rsi + rdx + 4], 6 - LONG $0x54c40f66; WORD $0x041e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 4], 7 - QUAD $0x0106066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 6], 1 - QUAD $0x02060e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 6], 2 + LONG $0x54c40f66; WORD $0x041e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 4], 6 + LONG $0x54c40f66; WORD $0x0406; BYTE $0x07 // pinsrw xmm2, word [rsi + rax + 4], 7 + QUAD $0x01060e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 6], 1 + QUAD $0x0206066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 6], 2 QUAD $0x0306266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 6], 3 - QUAD $0x04062e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 6], 4 + LONG $0x6cc40f66; WORD $0x0616; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 6], 4 LONG $0x6cc40f66; WORD $0x060e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 6], 5 - LONG $0x6cc40f66; WORD $0x0616; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 6], 6 - LONG $0x6cc40f66; WORD $0x061e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 6], 7 - QUAD $0x0108065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 8], 1 - QUAD $0x02080e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 8], 2 + LONG $0x6cc40f66; WORD $0x061e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 6], 6 + LONG $0x6cc40f66; WORD $0x0606; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 6], 7 + QUAD $0x01080e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 8], 1 + QUAD $0x0208065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 8], 2 QUAD $0x0308265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 8], 3 - QUAD $0x04082e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 8], 4 + LONG $0x5cc40f66; WORD $0x0816; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 8], 4 LONG $0x5cc40f66; WORD $0x080e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 8], 5 - LONG $0x5cc40f66; WORD $0x0816; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 8], 6 - LONG $0x5cc40f66; WORD $0x081e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 8], 7 + LONG $0x5cc40f66; WORD $0x081e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 8], 6 + LONG $0x5cc40f66; WORD $0x0806; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 8], 7 LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x7c6e0f66; WORD $0x1824 // movd xmm7, dword [rsp + 24] - LONG $0x44b70f42; WORD $0x163e // movzx eax, word [rsi + r15 + 22] + LONG $0x7c6e0f66; WORD $0x1024 // movd xmm7, dword [rsp + 16] + LONG $0x74b70f46; WORD $0x163e // movzx r14d, word [rsi + r15 + 22] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 LONG $0xf2710f66; BYTE $0x02 // psllw xmm2, 2 LONG $0xdb0f4166; BYTE $0xd1 // pand xmm2, xmm9 LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0x646e0f66; WORD $0x1024 // movd xmm4, dword [rsp + 16] - LONG $0x5cb70f46; WORD $0x183e // movzx r11d, word [rsi + r15 + 24] + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x7cb70f42; WORD $0x183e // movzx edi, word [rsi + r15 + 24] LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 @@ -8001,25 +6450,25 @@ LBB1_112: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xcf6e0f66 // movd xmm1, edi - LONG $0x7cb70f42; WORD $0x1a3e // movzx edi, word [rsi + r15 + 26] - QUAD $0x010a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 10], 1 - QUAD $0x020a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 10], 2 + LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] + LONG $0x54b70f46; WORD $0x1a3e // movzx r10d, word [rsi + r15 + 26] + QUAD $0x010a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 10], 1 + QUAD $0x020a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 10], 2 QUAD $0x030a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 10], 3 - QUAD $0x040a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 10], 4 + LONG $0x74c40f66; WORD $0x0a16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 10], 4 LONG $0x74c40f66; WORD $0x0a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 10], 5 - LONG $0x74c40f66; WORD $0x0a16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 10], 6 - LONG $0x74c40f66; WORD $0x0a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 10], 7 - QUAD $0x010c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 12], 1 - QUAD $0x020c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 12], 2 + LONG $0x74c40f66; WORD $0x0a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 10], 6 + LONG $0x74c40f66; WORD $0x0a06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 10], 7 + QUAD $0x010c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 12], 1 + QUAD $0x020c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 12], 2 QUAD $0x030c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 12], 3 - QUAD $0x040c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 12], 4 + LONG $0x7cc40f66; WORD $0x0c16; BYTE $0x04 // pinsrw xmm7, word [rsi + rdx + 12], 4 LONG $0x7cc40f66; WORD $0x0c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 12], 5 - LONG $0x7cc40f66; WORD $0x0c16; BYTE $0x06 // pinsrw xmm7, word [rsi + rdx + 12], 6 - LONG $0x7cc40f66; WORD $0x0c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 12], 7 + LONG $0x7cc40f66; WORD $0x0c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 12], 6 + LONG $0x7cc40f66; WORD $0x0c06; BYTE $0x07 // pinsrw xmm7, word [rsi + rax + 12], 7 LONG $0xdaeb0f66 // por xmm3, xmm2 LONG $0x6e0f4466; WORD $0x2444; BYTE $0x30 // movd xmm8, dword [rsp + 48] - LONG $0x74b70f46; WORD $0x1c3e // movzx r14d, word [rsi + r15 + 28] + LONG $0x5cb70f46; WORD $0x1c3e // movzx r11d, word [rsi + r15 + 28] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8031,81 +6480,81 @@ LBB1_112: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d - LONG $0x54b70f46; WORD $0x1e3e // movzx r10d, word [rsi + r15 + 30] - QUAD $0x010e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 14], 1 - QUAD $0x020e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 14], 2 + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d + LONG $0x6cb70f46; WORD $0x1e3e // movzx r13d, word [rsi + r15 + 30] + QUAD $0x010e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 14], 1 + QUAD $0x020e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 14], 2 QUAD $0x030e2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 14], 3 - QUAD $0x040e2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 14], 4 + LONG $0x64c40f66; WORD $0x0e16; BYTE $0x04 // pinsrw xmm4, word [rsi + rdx + 14], 4 LONG $0x64c40f66; WORD $0x0e0e; BYTE $0x05 // pinsrw xmm4, word [rsi + rcx + 14], 5 - LONG $0x64c40f66; WORD $0x0e16; BYTE $0x06 // pinsrw xmm4, word [rsi + rdx + 14], 6 - LONG $0x64c40f66; WORD $0x0e1e; BYTE $0x07 // pinsrw xmm4, word [rsi + rbx + 14], 7 - QUAD $0x01120644c40f4666 // pinsrw xmm8, word [rsi + r8 + 18], 1 - QUAD $0x02120e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 18], 2 + LONG $0x64c40f66; WORD $0x0e1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 14], 6 + LONG $0x64c40f66; WORD $0x0e06; BYTE $0x07 // pinsrw xmm4, word [rsi + rax + 14], 7 + QUAD $0x01120e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 18], 1 + QUAD $0x02120644c40f4666 // pinsrw xmm8, word [rsi + r8 + 18], 2 QUAD $0x03122644c40f4666 // pinsrw xmm8, word [rsi + r12 + 18], 3 - QUAD $0x04122e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 18], 4 + QUAD $0x04121644c40f4466 // pinsrw xmm8, word [rsi + rdx + 18], 4 QUAD $0x05120e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 18], 5 - QUAD $0x06121644c40f4466 // pinsrw xmm8, word [rsi + rdx + 18], 6 - QUAD $0x07121e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 18], 7 + QUAD $0x06121e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 18], 6 + QUAD $0x07120644c40f4466 // pinsrw xmm8, word [rsi + rax + 18], 7 LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f42; WORD $0x203e // movzx eax, word [rsi + r15 + 32] + LONG $0x6e0f4166; BYTE $0xd6 // movd xmm2, r14d + LONG $0x74b70f46; WORD $0x203e // movzx r14d, word [rsi + r15 + 32] LONG $0xe3eb0f66 // por xmm4, xmm3 LONG $0x750f4466; BYTE $0xc0 // pcmpeqw xmm8, xmm0 LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf80f4166; BYTE $0xf8 // psubb xmm7, xmm8 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x5cb70f46; WORD $0x223e // movzx r11d, word [rsi + r15 + 34] - QUAD $0x0110064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 16], 1 - QUAD $0x02100e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 16], 2 + LONG $0xdf6e0f66 // movd xmm3, edi + LONG $0x7cb70f42; WORD $0x223e // movzx edi, word [rsi + r15 + 34] + LONG $0x28247c89 // mov dword [rsp + 40], edi + QUAD $0x01100e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 16], 1 + QUAD $0x0210064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 16], 2 QUAD $0x0310264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 16], 3 - QUAD $0x04102e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 16], 4 + LONG $0x4cc40f66; WORD $0x1016; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 16], 4 LONG $0x4cc40f66; WORD $0x100e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 16], 5 - LONG $0x4cc40f66; WORD $0x1016; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 16], 6 - LONG $0x4cc40f66; WORD $0x101e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 16], 7 + LONG $0x4cc40f66; WORD $0x101e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 16], 6 + LONG $0x4cc40f66; WORD $0x1006; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 16], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0xf76e0f66 // movd xmm6, edi - LONG $0x7cb70f42; WORD $0x243e // movzx edi, word [rsi + r15 + 36] - LONG $0x30247c89 // mov dword [rsp + 48], edi - QUAD $0x0114066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 20], 1 - QUAD $0x02140e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 20], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x243e // movzx r10d, word [rsi + r15 + 36] + QUAD $0x01140e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 20], 1 + QUAD $0x0214066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 20], 2 QUAD $0x0314266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 20], 3 - QUAD $0x04142e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 20], 4 + LONG $0x6cc40f66; WORD $0x1416; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 20], 4 LONG $0x6cc40f66; WORD $0x140e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 20], 5 - LONG $0x6cc40f66; WORD $0x1416; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 20], 6 - LONG $0x6cc40f66; WORD $0x141e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 20], 7 + LONG $0x6cc40f66; WORD $0x141e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 20], 6 + LONG $0x6cc40f66; WORD $0x1406; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 20], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 LONG $0xefeb0f66 // por xmm5, xmm7 - LONG $0x6e0f4166; BYTE $0xfe // movd xmm7, r14d + LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d LONG $0x7cb70f42; WORD $0x263e // movzx edi, word [rsi + r15 + 38] LONG $0x10247c89 // mov dword [rsp + 16], edi - QUAD $0x01160654c40f4266 // pinsrw xmm2, word [rsi + r8 + 22], 1 - QUAD $0x02160e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 22], 2 + QUAD $0x01160e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 22], 1 + QUAD $0x02160654c40f4266 // pinsrw xmm2, word [rsi + r8 + 22], 2 QUAD $0x03162654c40f4266 // pinsrw xmm2, word [rsi + r12 + 22], 3 - QUAD $0x04162e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 22], 4 + LONG $0x54c40f66; WORD $0x1616; BYTE $0x04 // pinsrw xmm2, word [rsi + rdx + 22], 4 LONG $0x54c40f66; WORD $0x160e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 22], 5 - LONG $0x54c40f66; WORD $0x1616; BYTE $0x06 // pinsrw xmm2, word [rsi + rdx + 22], 6 - LONG $0x54c40f66; WORD $0x161e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 22], 7 - QUAD $0x0118065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 24], 1 - QUAD $0x02180e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 24], 2 + LONG $0x54c40f66; WORD $0x161e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 22], 6 + LONG $0x54c40f66; WORD $0x1606; BYTE $0x07 // pinsrw xmm2, word [rsi + rax + 22], 7 + QUAD $0x01180e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 24], 1 + QUAD $0x0218065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 24], 2 QUAD $0x0318265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 24], 3 - QUAD $0x04182e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 24], 4 + LONG $0x5cc40f66; WORD $0x1816; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 24], 4 LONG $0x5cc40f66; WORD $0x180e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 24], 5 - LONG $0x5cc40f66; WORD $0x1816; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 24], 6 - LONG $0x5cc40f66; WORD $0x181e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 24], 7 + LONG $0x5cc40f66; WORD $0x181e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 24], 6 + LONG $0x5cc40f66; WORD $0x1806; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 24], 7 LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 @@ -8117,33 +6566,32 @@ LBB1_112: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x7cb70f42; WORD $0x283e // movzx edi, word [rsi + r15 + 40] + LONG $0x6e0f4166; BYTE $0xd5 // movd xmm2, r13d + LONG $0x5cb70f46; WORD $0x283e // movzx r11d, word [rsi + r15 + 40] LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f42; WORD $0x2a3e // movzx eax, word [rsi + r15 + 42] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x011a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 26], 1 - QUAD $0x021a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 26], 2 + LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d + LONG $0x74b70f46; WORD $0x2a3e // movzx r14d, word [rsi + r15 + 42] + QUAD $0x011a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 26], 1 + QUAD $0x021a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 26], 2 QUAD $0x031a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 26], 3 - QUAD $0x041a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 26], 4 + LONG $0x74c40f66; WORD $0x1a16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 26], 4 LONG $0x74c40f66; WORD $0x1a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 26], 5 - LONG $0x74c40f66; WORD $0x1a16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 26], 6 - LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 26], 7 - QUAD $0x011c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 28], 1 - QUAD $0x021c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 28], 2 + LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 26], 6 + LONG $0x74c40f66; WORD $0x1a06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 26], 7 + QUAD $0x011c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 28], 1 + QUAD $0x021c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 28], 2 QUAD $0x031c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 28], 3 - QUAD $0x041c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 28], 4 + LONG $0x7cc40f66; WORD $0x1c16; BYTE $0x04 // pinsrw xmm7, word [rsi + rdx + 28], 4 LONG $0x7cc40f66; WORD $0x1c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 28], 5 - LONG $0x7cc40f66; WORD $0x1c16; BYTE $0x06 // pinsrw xmm7, word [rsi + rdx + 28], 6 - LONG $0x7cc40f66; WORD $0x1c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 28], 7 - QUAD $0x011e0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 30], 1 - QUAD $0x021e0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 30], 2 + LONG $0x7cc40f66; WORD $0x1c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 28], 6 + LONG $0x7cc40f66; WORD $0x1c06; BYTE $0x07 // pinsrw xmm7, word [rsi + rax + 28], 7 + QUAD $0x011e0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 30], 1 + QUAD $0x021e0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 30], 2 QUAD $0x031e2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 30], 3 - QUAD $0x041e2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 30], 4 + LONG $0x54c40f66; WORD $0x1e16; BYTE $0x04 // pinsrw xmm2, word [rsi + rdx + 30], 4 LONG $0x54c40f66; WORD $0x1e0e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 30], 5 - LONG $0x54c40f66; WORD $0x1e16; BYTE $0x06 // pinsrw xmm2, word [rsi + rdx + 30], 6 - LONG $0x54c40f66; WORD $0x1e1e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 30], 7 + LONG $0x54c40f66; WORD $0x1e1e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 30], 6 + LONG $0x54c40f66; WORD $0x1e06; BYTE $0x07 // pinsrw xmm2, word [rsi + rax + 30], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8155,28 +6603,28 @@ LBB1_112: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d - LONG $0x54b70f46; WORD $0x2c3e // movzx r10d, word [rsi + r15 + 44] + LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] + LONG $0x6cb70f46; WORD $0x2c3e // movzx r13d, word [rsi + r15 + 44] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 LONG $0xdb0f4166; BYTE $0xd6 // pand xmm2, xmm14 LONG $0xd7eb0f66 // por xmm2, xmm7 - LONG $0x746e0f66; WORD $0x3024 // movd xmm6, dword [rsp + 48] - LONG $0x74b70f46; WORD $0x2e3e // movzx r14d, word [rsi + r15 + 46] - QUAD $0x0120066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 32], 1 - QUAD $0x02200e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 32], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x2e3e // movzx r10d, word [rsi + r15 + 46] + QUAD $0x01200e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 32], 1 + QUAD $0x0220066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 32], 2 QUAD $0x0320266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 32], 3 - QUAD $0x04202e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 32], 4 + LONG $0x6cc40f66; WORD $0x2016; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 32], 4 LONG $0x6cc40f66; WORD $0x200e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 32], 5 - LONG $0x6cc40f66; WORD $0x2016; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 32], 6 - QUAD $0x0122064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 34], 1 - QUAD $0x02220e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 34], 2 + LONG $0x6cc40f66; WORD $0x201e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 32], 6 + QUAD $0x01220e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 34], 1 + QUAD $0x0222064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 34], 2 QUAD $0x0322264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 34], 3 - QUAD $0x04222e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 34], 4 + LONG $0x4cc40f66; WORD $0x2216; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 34], 4 LONG $0x4cc40f66; WORD $0x220e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 34], 5 - LONG $0x4cc40f66; WORD $0x2216; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 34], 6 - LONG $0x4cc40f66; WORD $0x221e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 34], 7 + LONG $0x4cc40f66; WORD $0x221e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 34], 6 + LONG $0x4cc40f66; WORD $0x2206; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 34], 7 LONG $0xd3eb0f66 // por xmm2, xmm3 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 @@ -8184,45 +6632,44 @@ LBB1_112: LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf9f80f66 // psubb xmm7, xmm1 LONG $0x5c6e0f66; WORD $0x1024 // movd xmm3, dword [rsp + 16] - LONG $0x44b70f42; WORD $0x303e // movzx eax, word [rsi + r15 + 48] - LONG $0x10244489 // mov dword [rsp + 16], eax - LONG $0x6cc40f66; WORD $0x201e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 32], 7 + LONG $0x7cb70f42; WORD $0x303e // movzx edi, word [rsi + r15 + 48] + LONG $0x10247c89 // mov dword [rsp + 16], edi + LONG $0x6cc40f66; WORD $0x2006; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 32], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - QUAD $0x01240674c40f4266 // pinsrw xmm6, word [rsi + r8 + 36], 1 - QUAD $0x02240e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 36], 2 + QUAD $0x01240e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 36], 1 + QUAD $0x02240674c40f4266 // pinsrw xmm6, word [rsi + r8 + 36], 2 QUAD $0x03242674c40f4266 // pinsrw xmm6, word [rsi + r12 + 36], 3 - QUAD $0x04242e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 36], 4 + LONG $0x74c40f66; WORD $0x2416; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 36], 4 LONG $0x74c40f66; WORD $0x240e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 36], 5 - LONG $0x74c40f66; WORD $0x2416; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 36], 6 - LONG $0x74c40f66; WORD $0x241e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 36], 7 - QUAD $0x0126065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 38], 1 - QUAD $0x02260e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 38], 2 + LONG $0x74c40f66; WORD $0x241e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 36], 6 + LONG $0x74c40f66; WORD $0x2406; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 36], 7 + QUAD $0x01260e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 38], 1 + QUAD $0x0226065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 38], 2 QUAD $0x0326265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 38], 3 - QUAD $0x04262e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 38], 4 + LONG $0x5cc40f66; WORD $0x2616; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 38], 4 LONG $0x5cc40f66; WORD $0x260e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 38], 5 - LONG $0x5cc40f66; WORD $0x2616; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 38], 6 - LONG $0x5cc40f66; WORD $0x261e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 38], 7 + LONG $0x5cc40f66; WORD $0x261e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 38], 6 + LONG $0x5cc40f66; WORD $0x2606; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 38], 7 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0xef6e0f66 // movd xmm5, edi - QUAD $0x0128066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 40], 1 - QUAD $0x02280e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 40], 2 + LONG $0x6e0f4166; BYTE $0xeb // movd xmm5, r11d + QUAD $0x01280e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 40], 1 + QUAD $0x0228066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 40], 2 QUAD $0x0328266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 40], 3 - QUAD $0x04282e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 40], 4 + LONG $0x6cc40f66; WORD $0x2816; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 40], 4 LONG $0x6cc40f66; WORD $0x280e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 40], 5 - LONG $0x6cc40f66; WORD $0x2816; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 40], 6 - LONG $0x44b70f42; WORD $0x323e // movzx eax, word [rsi + r15 + 50] + LONG $0x6cc40f66; WORD $0x281e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 40], 6 + LONG $0x7cb70f42; WORD $0x323e // movzx edi, word [rsi + r15 + 50] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] - LONG $0x7cb70f42; WORD $0x343e // movzx edi, word [rsi + r15 + 52] - LONG $0x18247c89 // mov dword [rsp + 24], edi - LONG $0x6cc40f66; WORD $0x281e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 40], 7 + LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d + LONG $0x5cb70f46; WORD $0x343e // movzx r11d, word [rsi + r15 + 52] + LONG $0x6cc40f66; WORD $0x2806; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 40], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 @@ -8234,25 +6681,25 @@ LBB1_112: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xebeb0f66 // por xmm5, xmm3 - LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d - LONG $0x5cb70f46; WORD $0x363e // movzx r11d, word [rsi + r15 + 54] - QUAD $0x012a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 42], 1 - QUAD $0x022a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 42], 2 + LONG $0x6e0f4166; BYTE $0xfd // movd xmm7, r13d + LONG $0x74b70f46; WORD $0x363e // movzx r14d, word [rsi + r15 + 54] + QUAD $0x012a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 42], 1 + QUAD $0x022a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 42], 2 QUAD $0x032a264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 42], 3 - QUAD $0x042a2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 42], 4 + LONG $0x4cc40f66; WORD $0x2a16; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 42], 4 LONG $0x4cc40f66; WORD $0x2a0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 42], 5 - LONG $0x4cc40f66; WORD $0x2a16; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 42], 6 - LONG $0x4cc40f66; WORD $0x2a1e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 42], 7 - QUAD $0x012c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 44], 1 - QUAD $0x022c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 44], 2 + LONG $0x4cc40f66; WORD $0x2a1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 42], 6 + LONG $0x4cc40f66; WORD $0x2a06; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 42], 7 + QUAD $0x012c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 44], 1 + QUAD $0x022c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 44], 2 QUAD $0x032c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 44], 3 - QUAD $0x042c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 44], 4 + LONG $0x7cc40f66; WORD $0x2c16; BYTE $0x04 // pinsrw xmm7, word [rsi + rdx + 44], 4 LONG $0x7cc40f66; WORD $0x2c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 44], 5 - LONG $0x7cc40f66; WORD $0x2c16; BYTE $0x06 // pinsrw xmm7, word [rsi + rdx + 44], 6 + LONG $0x7cc40f66; WORD $0x2c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 44], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xde // movd xmm3, r14d + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d LONG $0x54b70f46; WORD $0x383e // movzx r10d, word [rsi + r15 + 56] - LONG $0x7cc40f66; WORD $0x2c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 44], 7 + LONG $0x7cc40f66; WORD $0x2c06; BYTE $0x07 // pinsrw xmm7, word [rsi + rax + 44], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 @@ -8265,56 +6712,55 @@ LBB1_112: LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xf9eb0f66 // por xmm7, xmm1 LONG $0x746e0f66; WORD $0x1024 // movd xmm6, dword [rsp + 16] - LONG $0x74b70f46; WORD $0x3a3e // movzx r14d, word [rsi + r15 + 58] - QUAD $0x012e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 46], 1 - QUAD $0x022e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 46], 2 + LONG $0x6cb70f46; WORD $0x3a3e // movzx r13d, word [rsi + r15 + 58] + QUAD $0x012e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 46], 1 + QUAD $0x022e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 46], 2 QUAD $0x032e265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 46], 3 - QUAD $0x042e2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 46], 4 + LONG $0x5cc40f66; WORD $0x2e16; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 46], 4 LONG $0x5cc40f66; WORD $0x2e0e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 46], 5 - LONG $0x5cc40f66; WORD $0x2e16; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 46], 6 - LONG $0x5cc40f66; WORD $0x2e1e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 46], 7 + LONG $0x5cc40f66; WORD $0x2e1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 46], 6 + LONG $0x5cc40f66; WORD $0x2e06; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 46], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 LONG $0xdfeb0f66 // por xmm3, xmm7 - LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xcf6e0f66 // movd xmm1, edi LONG $0x7cb70f42; WORD $0x3c3e // movzx edi, word [rsi + r15 + 60] LONG $0x7cb70f46; WORD $0x3e3e // movzx r15d, word [rsi + r15 + 62] - QUAD $0x0132064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 1 - QUAD $0x02320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 2 + QUAD $0x01320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 1 + QUAD $0x0232064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 2 QUAD $0x0332264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 50], 3 - QUAD $0x04322e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 50], 4 + LONG $0x4cc40f66; WORD $0x3216; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 50], 4 LONG $0x4cc40f66; WORD $0x320e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 50], 5 - LONG $0x4cc40f66; WORD $0x3216; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 50], 6 - LONG $0x4cc40f66; WORD $0x321e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 50], 7 + LONG $0x4cc40f66; WORD $0x321e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 50], 6 + LONG $0x4cc40f66; WORD $0x3206; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 50], 7 LONG $0xddeb0f66 // por xmm3, xmm5 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xe96f0f66 // movdqa xmm5, xmm1 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xe9f80f66 // psubb xmm5, xmm1 - LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x01300674c40f4266 // pinsrw xmm6, word [rsi + r8 + 48], 1 - QUAD $0x02300e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 48], 2 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + QUAD $0x01300e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 48], 1 + QUAD $0x02300674c40f4266 // pinsrw xmm6, word [rsi + r8 + 48], 2 QUAD $0x03302674c40f4266 // pinsrw xmm6, word [rsi + r12 + 48], 3 - QUAD $0x04302e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 48], 4 + LONG $0x74c40f66; WORD $0x3016; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 48], 4 LONG $0x74c40f66; WORD $0x300e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 48], 5 - LONG $0x74c40f66; WORD $0x3016; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 48], 6 - LONG $0x74c40f66; WORD $0x301e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 48], 7 + LONG $0x74c40f66; WORD $0x301e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 48], 6 + LONG $0x74c40f66; WORD $0x3006; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 48], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 - QUAD $0x0134064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 52], 1 - QUAD $0x02340e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 52], 2 + QUAD $0x01340e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 52], 1 + QUAD $0x0234064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 52], 2 QUAD $0x0334264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 52], 3 - QUAD $0x04342e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 52], 4 + LONG $0x4cc40f66; WORD $0x3416; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 52], 4 LONG $0x4cc40f66; WORD $0x340e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 52], 5 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0x4cc40f66; WORD $0x3416; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 52], 6 + LONG $0x4cc40f66; WORD $0x341e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 52], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - LONG $0x4cc40f66; WORD $0x341e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 52], 7 + LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d + LONG $0x4cc40f66; WORD $0x3406; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 52], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 @@ -8322,20 +6768,20 @@ LBB1_112: LONG $0xdb0f4166; BYTE $0xc9 // pand xmm1, xmm9 LONG $0xcdeb0f66 // por xmm1, xmm5 LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d - QUAD $0x01360674c40f4266 // pinsrw xmm6, word [rsi + r8 + 54], 1 - QUAD $0x02360e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 54], 2 + QUAD $0x01360e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 54], 1 + QUAD $0x02360674c40f4266 // pinsrw xmm6, word [rsi + r8 + 54], 2 QUAD $0x03362674c40f4266 // pinsrw xmm6, word [rsi + r12 + 54], 3 - QUAD $0x04362e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 54], 4 + LONG $0x74c40f66; WORD $0x3616; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 54], 4 LONG $0x74c40f66; WORD $0x360e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 54], 5 - LONG $0x74c40f66; WORD $0x3616; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 54], 6 - LONG $0x74c40f66; WORD $0x361e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 54], 7 - QUAD $0x0138066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 56], 1 - QUAD $0x02380e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 56], 2 + LONG $0x74c40f66; WORD $0x361e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 54], 6 + LONG $0x74c40f66; WORD $0x3606; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 54], 7 + QUAD $0x01380e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 56], 1 + QUAD $0x0238066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 56], 2 QUAD $0x0338266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 56], 3 - QUAD $0x04382e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 56], 4 + LONG $0x6cc40f66; WORD $0x3816; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 56], 4 LONG $0x6cc40f66; WORD $0x380e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 56], 5 - LONG $0x6cc40f66; WORD $0x3816; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 56], 6 - LONG $0x6cc40f66; WORD $0x381e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 56], 7 + LONG $0x6cc40f66; WORD $0x381e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 56], 6 + LONG $0x6cc40f66; WORD $0x3806; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 56], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8347,23 +6793,23 @@ LBB1_112: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d - QUAD $0x013a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 58], 1 - QUAD $0x023a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 58], 2 + LONG $0x6e0f4166; BYTE $0xf5 // movd xmm6, r13d + QUAD $0x013a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 58], 1 + QUAD $0x023a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 58], 2 QUAD $0x033a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 58], 3 - QUAD $0x043a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 58], 4 + LONG $0x74c40f66; WORD $0x3a16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 58], 4 LONG $0x74c40f66; WORD $0x3a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 58], 5 - LONG $0x74c40f66; WORD $0x3a16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 58], 6 - LONG $0x74c40f66; WORD $0x3a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 58], 7 + LONG $0x74c40f66; WORD $0x3a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 58], 6 + LONG $0x74c40f66; WORD $0x3a06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 58], 7 LONG $0xe9eb0f66 // por xmm5, xmm1 LONG $0xcf6e0f66 // movd xmm1, edi - QUAD $0x013c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 60], 1 - QUAD $0x023c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 60], 2 + QUAD $0x013c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 60], 1 + QUAD $0x023c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 60], 2 QUAD $0x033c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 60], 3 - QUAD $0x043c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 60], 4 + LONG $0x4cc40f66; WORD $0x3c16; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 60], 4 LONG $0x4cc40f66; WORD $0x3c0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 60], 5 - LONG $0x4cc40f66; WORD $0x3c16; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 60], 6 - LONG $0x4cc40f66; WORD $0x3c1e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 60], 7 + LONG $0x4cc40f66; WORD $0x3c1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 60], 6 + LONG $0x4cc40f66; WORD $0x3c06; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 60], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8376,13 +6822,14 @@ LBB1_112: LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 LONG $0xceeb0f66 // por xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf7 // movd xmm6, r15d - QUAD $0x013e0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 62], 1 - QUAD $0x023e0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 62], 2 + QUAD $0x013e0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 62], 1 + QUAD $0x023e0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 62], 2 QUAD $0x033e2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 62], 3 - QUAD $0x043e2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 62], 4 + LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] + LONG $0x74c40f66; WORD $0x3e16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 62], 4 LONG $0x74c40f66; WORD $0x3e0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 62], 5 - LONG $0x74c40f66; WORD $0x3e16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 62], 6 - LONG $0x74c40f66; WORD $0x3e1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 62], 7 + LONG $0x74c40f66; WORD $0x3e1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 62], 6 + LONG $0x74c40f66; WORD $0x3e06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 62], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 @@ -8400,31 +6847,32 @@ LBB1_112: LONG $0xde600f66 // punpcklbw xmm3, xmm6 LONG $0xe2600f66 // punpcklbw xmm4, xmm2 LONG $0xe3610f66 // punpcklwd xmm4, xmm3 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x247f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm4 - LONG $0x4c7f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm1 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + LONG $0x247f0ff3; BYTE $0x8f // movdqu oword [rdi + 4*rcx], xmm4 + LONG $0x4c7f0ff3; WORD $0x108f // movdqu oword [rdi + 4*rcx + 16], xmm1 LONG $0x08c18348 // add rcx, 8 WORD $0x8949; BYTE $0xcf // mov r15, rcx LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB1_112 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - LONG $0x247c3b4c; BYTE $0x20 // cmp r15, qword [rsp + 32] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - LONG $0x245c8b44; BYTE $0x04 // mov r11d, dword [rsp + 4] - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - JNE LBB1_114 - JMP LBB1_117 + JNE LBB1_127 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x246c8b44; BYTE $0x38 // mov r13d, dword [rsp + 56] + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + JNE LBB1_129 + JMP LBB1_132 -LBB1_134: - LONG $0xf8e78349 // and r15, -8 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB1_151: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - LONG $0x6e0f4166; BYTE $0xc3 // movd xmm0, r11d + LONG $0x246c8944; BYTE $0x38 // mov dword [rsp + 56], r13d + LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 WORD $0x3145; BYTE $0xff // xor r15d, r15d @@ -8435,99 +6883,99 @@ LBB1_134: LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI1_4] */ LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI1_5] */ LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI1_6] */ - QUAD $0x0000008824b4894c // mov qword [rsp + 136], r14 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 -LBB1_135: - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 +LBB1_152: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06e7c149 // shl r15, 6 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xfa // mov rdx, r15 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 LONG $0x34b70f46; BYTE $0x3e // movzx r14d, word [rsi + r15] - LONG $0x44b70f42; WORD $0x023e // movzx eax, word [rsi + r15 + 2] - LONG $0x54b70f46; WORD $0x043e // movzx r10d, word [rsi + r15 + 4] - LONG $0x7cb70f42; WORD $0x063e // movzx edi, word [rsi + r15 + 6] - LONG $0x5cb70f46; WORD $0x083e // movzx r11d, word [rsi + r15 + 8] - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - LONG $0x40c88349 // or r8, 64 - LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + LONG $0x7cb70f42; WORD $0x023e // movzx edi, word [rsi + r15 + 2] + LONG $0x5cb70f46; WORD $0x043e // movzx r11d, word [rsi + r15 + 4] + LONG $0x6cb70f46; WORD $0x063e // movzx r13d, word [rsi + r15 + 6] + LONG $0x54b70f46; WORD $0x083e // movzx r10d, word [rsi + r15 + 8] + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + LONG $0x40c98349 // or r9, 64 + LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 + LONG $0x00ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 256 LONG $0x40c98148; WORD $0x0001; BYTE $0x00 // or rcx, 320 - LONG $0x80ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 384 - LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 + LONG $0x01c00d48; WORD $0x0000 // or rax, 448 LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d - LONG $0xc40f4266; WORD $0x0624; BYTE $0x01 // pinsrw xmm4, word [rsi + r8], 1 - LONG $0xc40f4266; WORD $0x0e24; BYTE $0x02 // pinsrw xmm4, word [rsi + r9], 2 + LONG $0xc40f4266; WORD $0x0e24; BYTE $0x01 // pinsrw xmm4, word [rsi + r9], 1 + LONG $0xc40f4266; WORD $0x0624; BYTE $0x02 // pinsrw xmm4, word [rsi + r8], 2 LONG $0xc40f4266; WORD $0x2624; BYTE $0x03 // pinsrw xmm4, word [rsi + r12], 3 - LONG $0xc40f4266; WORD $0x2e24; BYTE $0x04 // pinsrw xmm4, word [rsi + r13], 4 + LONG $0x24c40f66; WORD $0x0416 // pinsrw xmm4, word [rsi + rdx], 4 LONG $0x24c40f66; WORD $0x050e // pinsrw xmm4, word [rsi + rcx], 5 - LONG $0x24c40f66; WORD $0x0616 // pinsrw xmm4, word [rsi + rdx], 6 - LONG $0x24c40f66; WORD $0x071e // pinsrw xmm4, word [rsi + rbx], 7 + LONG $0x24c40f66; WORD $0x061e // pinsrw xmm4, word [rsi + rbx], 6 + LONG $0x24c40f66; WORD $0x0706 // pinsrw xmm4, word [rsi + rax], 7 LONG $0x74b70f46; WORD $0x0a3e // movzx r14d, word [rsi + r15 + 10] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x01020674c40f4266 // pinsrw xmm6, word [rsi + r8 + 2], 1 - QUAD $0x02020e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 2], 2 + LONG $0xf76e0f66 // movd xmm6, edi + QUAD $0x01020e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 2], 1 + QUAD $0x02020674c40f4266 // pinsrw xmm6, word [rsi + r8 + 2], 2 QUAD $0x03022674c40f4266 // pinsrw xmm6, word [rsi + r12 + 2], 3 - LONG $0x44b70f42; WORD $0x0c3e // movzx eax, word [rsi + r15 + 12] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x04022e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 2], 4 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x44b70f42; WORD $0x0e3e // movzx eax, word [rsi + r15 + 14] - LONG $0x10244489 // mov dword [rsp + 16], eax + LONG $0x7cb70f42; WORD $0x0c3e // movzx edi, word [rsi + r15 + 12] + LONG $0x10247c89 // mov dword [rsp + 16], edi + LONG $0x74c40f66; WORD $0x0216; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 2], 4 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x5cb70f46; WORD $0x0e3e // movzx r11d, word [rsi + r15 + 14] LONG $0x74c40f66; WORD $0x020e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 2], 5 - LONG $0xef6e0f66 // movd xmm5, edi + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d LONG $0x7cb70f42; WORD $0x103e // movzx edi, word [rsi + r15 + 16] - LONG $0x74c40f66; WORD $0x0216; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 2], 6 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x44b70f42; WORD $0x123e // movzx eax, word [rsi + r15 + 18] - LONG $0x30244489 // mov dword [rsp + 48], eax - LONG $0x74c40f66; WORD $0x021e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 2], 7 + LONG $0x28247c89 // mov dword [rsp + 40], edi + LONG $0x74c40f66; WORD $0x021e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 2], 6 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x7cb70f42; WORD $0x123e // movzx edi, word [rsi + r15 + 18] + LONG $0x30247c89 // mov dword [rsp + 48], edi + LONG $0x74c40f66; WORD $0x0206; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 2], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xce6f0f66 // movdqa xmm1, xmm6 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xcef80f66 // psubb xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d - LONG $0x54b70f46; WORD $0x143e // movzx r10d, word [rsi + r15 + 20] + LONG $0x6cb70f46; WORD $0x143e // movzx r13d, word [rsi + r15 + 20] LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - QUAD $0x01040654c40f4266 // pinsrw xmm2, word [rsi + r8 + 4], 1 - QUAD $0x02040e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 4], 2 + QUAD $0x01040e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 4], 1 + QUAD $0x02040654c40f4266 // pinsrw xmm2, word [rsi + r8 + 4], 2 QUAD $0x03042654c40f4266 // pinsrw xmm2, word [rsi + r12 + 4], 3 - QUAD $0x04042e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 4], 4 + LONG $0x54c40f66; WORD $0x0416; BYTE $0x04 // pinsrw xmm2, word [rsi + rdx + 4], 4 LONG $0x54c40f66; WORD $0x040e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 4], 5 - LONG $0x54c40f66; WORD $0x0416; BYTE $0x06 // pinsrw xmm2, word [rsi + rdx + 4], 6 - LONG $0x54c40f66; WORD $0x041e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 4], 7 - QUAD $0x0106066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 6], 1 - QUAD $0x02060e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 6], 2 + LONG $0x54c40f66; WORD $0x041e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 4], 6 + LONG $0x54c40f66; WORD $0x0406; BYTE $0x07 // pinsrw xmm2, word [rsi + rax + 4], 7 + QUAD $0x01060e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 6], 1 + QUAD $0x0206066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 6], 2 QUAD $0x0306266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 6], 3 - QUAD $0x04062e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 6], 4 + LONG $0x6cc40f66; WORD $0x0616; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 6], 4 LONG $0x6cc40f66; WORD $0x060e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 6], 5 - LONG $0x6cc40f66; WORD $0x0616; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 6], 6 - LONG $0x6cc40f66; WORD $0x061e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 6], 7 - QUAD $0x0108065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 8], 1 - QUAD $0x02080e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 8], 2 + LONG $0x6cc40f66; WORD $0x061e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 6], 6 + LONG $0x6cc40f66; WORD $0x0606; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 6], 7 + QUAD $0x01080e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 8], 1 + QUAD $0x0208065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 8], 2 QUAD $0x0308265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 8], 3 - QUAD $0x04082e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 8], 4 + LONG $0x5cc40f66; WORD $0x0816; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 8], 4 LONG $0x5cc40f66; WORD $0x080e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 8], 5 - LONG $0x5cc40f66; WORD $0x0816; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 8], 6 - LONG $0x5cc40f66; WORD $0x081e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 8], 7 + LONG $0x5cc40f66; WORD $0x081e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 8], 6 + LONG $0x5cc40f66; WORD $0x0806; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 8], 7 LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x7c6e0f66; WORD $0x1824 // movd xmm7, dword [rsp + 24] - LONG $0x44b70f42; WORD $0x163e // movzx eax, word [rsi + r15 + 22] + LONG $0x7c6e0f66; WORD $0x1024 // movd xmm7, dword [rsp + 16] + LONG $0x74b70f46; WORD $0x163e // movzx r14d, word [rsi + r15 + 22] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 LONG $0xf2710f66; BYTE $0x02 // psllw xmm2, 2 LONG $0xdb0f4166; BYTE $0xd1 // pand xmm2, xmm9 LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0x646e0f66; WORD $0x1024 // movd xmm4, dword [rsp + 16] - LONG $0x5cb70f46; WORD $0x183e // movzx r11d, word [rsi + r15 + 24] + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x7cb70f42; WORD $0x183e // movzx edi, word [rsi + r15 + 24] LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 @@ -8539,25 +6987,25 @@ LBB1_135: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xcf6e0f66 // movd xmm1, edi - LONG $0x7cb70f42; WORD $0x1a3e // movzx edi, word [rsi + r15 + 26] - QUAD $0x010a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 10], 1 - QUAD $0x020a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 10], 2 + LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] + LONG $0x54b70f46; WORD $0x1a3e // movzx r10d, word [rsi + r15 + 26] + QUAD $0x010a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 10], 1 + QUAD $0x020a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 10], 2 QUAD $0x030a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 10], 3 - QUAD $0x040a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 10], 4 + LONG $0x74c40f66; WORD $0x0a16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 10], 4 LONG $0x74c40f66; WORD $0x0a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 10], 5 - LONG $0x74c40f66; WORD $0x0a16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 10], 6 - LONG $0x74c40f66; WORD $0x0a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 10], 7 - QUAD $0x010c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 12], 1 - QUAD $0x020c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 12], 2 + LONG $0x74c40f66; WORD $0x0a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 10], 6 + LONG $0x74c40f66; WORD $0x0a06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 10], 7 + QUAD $0x010c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 12], 1 + QUAD $0x020c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 12], 2 QUAD $0x030c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 12], 3 - QUAD $0x040c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 12], 4 + LONG $0x7cc40f66; WORD $0x0c16; BYTE $0x04 // pinsrw xmm7, word [rsi + rdx + 12], 4 LONG $0x7cc40f66; WORD $0x0c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 12], 5 - LONG $0x7cc40f66; WORD $0x0c16; BYTE $0x06 // pinsrw xmm7, word [rsi + rdx + 12], 6 - LONG $0x7cc40f66; WORD $0x0c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 12], 7 + LONG $0x7cc40f66; WORD $0x0c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 12], 6 + LONG $0x7cc40f66; WORD $0x0c06; BYTE $0x07 // pinsrw xmm7, word [rsi + rax + 12], 7 LONG $0xdaeb0f66 // por xmm3, xmm2 LONG $0x6e0f4466; WORD $0x2444; BYTE $0x30 // movd xmm8, dword [rsp + 48] - LONG $0x74b70f46; WORD $0x1c3e // movzx r14d, word [rsi + r15 + 28] + LONG $0x5cb70f46; WORD $0x1c3e // movzx r11d, word [rsi + r15 + 28] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8569,81 +7017,81 @@ LBB1_135: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d - LONG $0x54b70f46; WORD $0x1e3e // movzx r10d, word [rsi + r15 + 30] - QUAD $0x010e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 14], 1 - QUAD $0x020e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 14], 2 + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d + LONG $0x6cb70f46; WORD $0x1e3e // movzx r13d, word [rsi + r15 + 30] + QUAD $0x010e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 14], 1 + QUAD $0x020e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 14], 2 QUAD $0x030e2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 14], 3 - QUAD $0x040e2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 14], 4 + LONG $0x64c40f66; WORD $0x0e16; BYTE $0x04 // pinsrw xmm4, word [rsi + rdx + 14], 4 LONG $0x64c40f66; WORD $0x0e0e; BYTE $0x05 // pinsrw xmm4, word [rsi + rcx + 14], 5 - LONG $0x64c40f66; WORD $0x0e16; BYTE $0x06 // pinsrw xmm4, word [rsi + rdx + 14], 6 - LONG $0x64c40f66; WORD $0x0e1e; BYTE $0x07 // pinsrw xmm4, word [rsi + rbx + 14], 7 - QUAD $0x01120644c40f4666 // pinsrw xmm8, word [rsi + r8 + 18], 1 - QUAD $0x02120e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 18], 2 + LONG $0x64c40f66; WORD $0x0e1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 14], 6 + LONG $0x64c40f66; WORD $0x0e06; BYTE $0x07 // pinsrw xmm4, word [rsi + rax + 14], 7 + QUAD $0x01120e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 18], 1 + QUAD $0x02120644c40f4666 // pinsrw xmm8, word [rsi + r8 + 18], 2 QUAD $0x03122644c40f4666 // pinsrw xmm8, word [rsi + r12 + 18], 3 - QUAD $0x04122e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 18], 4 + QUAD $0x04121644c40f4466 // pinsrw xmm8, word [rsi + rdx + 18], 4 QUAD $0x05120e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 18], 5 - QUAD $0x06121644c40f4466 // pinsrw xmm8, word [rsi + rdx + 18], 6 - QUAD $0x07121e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 18], 7 + QUAD $0x06121e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 18], 6 + QUAD $0x07120644c40f4466 // pinsrw xmm8, word [rsi + rax + 18], 7 LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f42; WORD $0x203e // movzx eax, word [rsi + r15 + 32] + LONG $0x6e0f4166; BYTE $0xd6 // movd xmm2, r14d + LONG $0x74b70f46; WORD $0x203e // movzx r14d, word [rsi + r15 + 32] LONG $0xe3eb0f66 // por xmm4, xmm3 LONG $0x750f4466; BYTE $0xc0 // pcmpeqw xmm8, xmm0 LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf80f4166; BYTE $0xf8 // psubb xmm7, xmm8 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x5cb70f46; WORD $0x223e // movzx r11d, word [rsi + r15 + 34] - QUAD $0x0110064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 16], 1 - QUAD $0x02100e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 16], 2 + LONG $0xdf6e0f66 // movd xmm3, edi + LONG $0x7cb70f42; WORD $0x223e // movzx edi, word [rsi + r15 + 34] + LONG $0x28247c89 // mov dword [rsp + 40], edi + QUAD $0x01100e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 16], 1 + QUAD $0x0210064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 16], 2 QUAD $0x0310264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 16], 3 - QUAD $0x04102e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 16], 4 + LONG $0x4cc40f66; WORD $0x1016; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 16], 4 LONG $0x4cc40f66; WORD $0x100e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 16], 5 - LONG $0x4cc40f66; WORD $0x1016; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 16], 6 - LONG $0x4cc40f66; WORD $0x101e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 16], 7 + LONG $0x4cc40f66; WORD $0x101e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 16], 6 + LONG $0x4cc40f66; WORD $0x1006; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 16], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0xf76e0f66 // movd xmm6, edi - LONG $0x7cb70f42; WORD $0x243e // movzx edi, word [rsi + r15 + 36] - LONG $0x30247c89 // mov dword [rsp + 48], edi - QUAD $0x0114066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 20], 1 - QUAD $0x02140e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 20], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x243e // movzx r10d, word [rsi + r15 + 36] + QUAD $0x01140e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 20], 1 + QUAD $0x0214066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 20], 2 QUAD $0x0314266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 20], 3 - QUAD $0x04142e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 20], 4 + LONG $0x6cc40f66; WORD $0x1416; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 20], 4 LONG $0x6cc40f66; WORD $0x140e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 20], 5 - LONG $0x6cc40f66; WORD $0x1416; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 20], 6 - LONG $0x6cc40f66; WORD $0x141e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 20], 7 + LONG $0x6cc40f66; WORD $0x141e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 20], 6 + LONG $0x6cc40f66; WORD $0x1406; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 20], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 LONG $0xefeb0f66 // por xmm5, xmm7 - LONG $0x6e0f4166; BYTE $0xfe // movd xmm7, r14d + LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d LONG $0x7cb70f42; WORD $0x263e // movzx edi, word [rsi + r15 + 38] LONG $0x10247c89 // mov dword [rsp + 16], edi - QUAD $0x01160654c40f4266 // pinsrw xmm2, word [rsi + r8 + 22], 1 - QUAD $0x02160e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 22], 2 + QUAD $0x01160e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 22], 1 + QUAD $0x02160654c40f4266 // pinsrw xmm2, word [rsi + r8 + 22], 2 QUAD $0x03162654c40f4266 // pinsrw xmm2, word [rsi + r12 + 22], 3 - QUAD $0x04162e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 22], 4 + LONG $0x54c40f66; WORD $0x1616; BYTE $0x04 // pinsrw xmm2, word [rsi + rdx + 22], 4 LONG $0x54c40f66; WORD $0x160e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 22], 5 - LONG $0x54c40f66; WORD $0x1616; BYTE $0x06 // pinsrw xmm2, word [rsi + rdx + 22], 6 - LONG $0x54c40f66; WORD $0x161e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 22], 7 - QUAD $0x0118065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 24], 1 - QUAD $0x02180e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 24], 2 + LONG $0x54c40f66; WORD $0x161e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 22], 6 + LONG $0x54c40f66; WORD $0x1606; BYTE $0x07 // pinsrw xmm2, word [rsi + rax + 22], 7 + QUAD $0x01180e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 24], 1 + QUAD $0x0218065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 24], 2 QUAD $0x0318265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 24], 3 - QUAD $0x04182e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 24], 4 + LONG $0x5cc40f66; WORD $0x1816; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 24], 4 LONG $0x5cc40f66; WORD $0x180e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 24], 5 - LONG $0x5cc40f66; WORD $0x1816; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 24], 6 - LONG $0x5cc40f66; WORD $0x181e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 24], 7 + LONG $0x5cc40f66; WORD $0x181e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 24], 6 + LONG $0x5cc40f66; WORD $0x1806; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 24], 7 LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 @@ -8655,33 +7103,32 @@ LBB1_135: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x7cb70f42; WORD $0x283e // movzx edi, word [rsi + r15 + 40] + LONG $0x6e0f4166; BYTE $0xd5 // movd xmm2, r13d + LONG $0x5cb70f46; WORD $0x283e // movzx r11d, word [rsi + r15 + 40] LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f42; WORD $0x2a3e // movzx eax, word [rsi + r15 + 42] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x011a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 26], 1 - QUAD $0x021a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 26], 2 + LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d + LONG $0x74b70f46; WORD $0x2a3e // movzx r14d, word [rsi + r15 + 42] + QUAD $0x011a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 26], 1 + QUAD $0x021a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 26], 2 QUAD $0x031a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 26], 3 - QUAD $0x041a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 26], 4 + LONG $0x74c40f66; WORD $0x1a16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 26], 4 LONG $0x74c40f66; WORD $0x1a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 26], 5 - LONG $0x74c40f66; WORD $0x1a16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 26], 6 - LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 26], 7 - QUAD $0x011c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 28], 1 - QUAD $0x021c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 28], 2 + LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 26], 6 + LONG $0x74c40f66; WORD $0x1a06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 26], 7 + QUAD $0x011c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 28], 1 + QUAD $0x021c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 28], 2 QUAD $0x031c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 28], 3 - QUAD $0x041c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 28], 4 + LONG $0x7cc40f66; WORD $0x1c16; BYTE $0x04 // pinsrw xmm7, word [rsi + rdx + 28], 4 LONG $0x7cc40f66; WORD $0x1c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 28], 5 - LONG $0x7cc40f66; WORD $0x1c16; BYTE $0x06 // pinsrw xmm7, word [rsi + rdx + 28], 6 - LONG $0x7cc40f66; WORD $0x1c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 28], 7 - QUAD $0x011e0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 30], 1 - QUAD $0x021e0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 30], 2 + LONG $0x7cc40f66; WORD $0x1c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 28], 6 + LONG $0x7cc40f66; WORD $0x1c06; BYTE $0x07 // pinsrw xmm7, word [rsi + rax + 28], 7 + QUAD $0x011e0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 30], 1 + QUAD $0x021e0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 30], 2 QUAD $0x031e2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 30], 3 - QUAD $0x041e2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 30], 4 + LONG $0x54c40f66; WORD $0x1e16; BYTE $0x04 // pinsrw xmm2, word [rsi + rdx + 30], 4 LONG $0x54c40f66; WORD $0x1e0e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 30], 5 - LONG $0x54c40f66; WORD $0x1e16; BYTE $0x06 // pinsrw xmm2, word [rsi + rdx + 30], 6 - LONG $0x54c40f66; WORD $0x1e1e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 30], 7 + LONG $0x54c40f66; WORD $0x1e1e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 30], 6 + LONG $0x54c40f66; WORD $0x1e06; BYTE $0x07 // pinsrw xmm2, word [rsi + rax + 30], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8693,28 +7140,28 @@ LBB1_135: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d - LONG $0x54b70f46; WORD $0x2c3e // movzx r10d, word [rsi + r15 + 44] + LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] + LONG $0x6cb70f46; WORD $0x2c3e // movzx r13d, word [rsi + r15 + 44] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 LONG $0xdb0f4166; BYTE $0xd6 // pand xmm2, xmm14 LONG $0xd7eb0f66 // por xmm2, xmm7 - LONG $0x746e0f66; WORD $0x3024 // movd xmm6, dword [rsp + 48] - LONG $0x74b70f46; WORD $0x2e3e // movzx r14d, word [rsi + r15 + 46] - QUAD $0x0120066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 32], 1 - QUAD $0x02200e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 32], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x2e3e // movzx r10d, word [rsi + r15 + 46] + QUAD $0x01200e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 32], 1 + QUAD $0x0220066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 32], 2 QUAD $0x0320266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 32], 3 - QUAD $0x04202e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 32], 4 + LONG $0x6cc40f66; WORD $0x2016; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 32], 4 LONG $0x6cc40f66; WORD $0x200e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 32], 5 - LONG $0x6cc40f66; WORD $0x2016; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 32], 6 - QUAD $0x0122064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 34], 1 - QUAD $0x02220e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 34], 2 + LONG $0x6cc40f66; WORD $0x201e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 32], 6 + QUAD $0x01220e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 34], 1 + QUAD $0x0222064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 34], 2 QUAD $0x0322264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 34], 3 - QUAD $0x04222e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 34], 4 + LONG $0x4cc40f66; WORD $0x2216; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 34], 4 LONG $0x4cc40f66; WORD $0x220e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 34], 5 - LONG $0x4cc40f66; WORD $0x2216; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 34], 6 - LONG $0x4cc40f66; WORD $0x221e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 34], 7 + LONG $0x4cc40f66; WORD $0x221e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 34], 6 + LONG $0x4cc40f66; WORD $0x2206; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 34], 7 LONG $0xd3eb0f66 // por xmm2, xmm3 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 @@ -8722,45 +7169,44 @@ LBB1_135: LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf9f80f66 // psubb xmm7, xmm1 LONG $0x5c6e0f66; WORD $0x1024 // movd xmm3, dword [rsp + 16] - LONG $0x44b70f42; WORD $0x303e // movzx eax, word [rsi + r15 + 48] - LONG $0x10244489 // mov dword [rsp + 16], eax - LONG $0x6cc40f66; WORD $0x201e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 32], 7 + LONG $0x7cb70f42; WORD $0x303e // movzx edi, word [rsi + r15 + 48] + LONG $0x10247c89 // mov dword [rsp + 16], edi + LONG $0x6cc40f66; WORD $0x2006; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 32], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - QUAD $0x01240674c40f4266 // pinsrw xmm6, word [rsi + r8 + 36], 1 - QUAD $0x02240e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 36], 2 + QUAD $0x01240e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 36], 1 + QUAD $0x02240674c40f4266 // pinsrw xmm6, word [rsi + r8 + 36], 2 QUAD $0x03242674c40f4266 // pinsrw xmm6, word [rsi + r12 + 36], 3 - QUAD $0x04242e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 36], 4 + LONG $0x74c40f66; WORD $0x2416; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 36], 4 LONG $0x74c40f66; WORD $0x240e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 36], 5 - LONG $0x74c40f66; WORD $0x2416; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 36], 6 - LONG $0x74c40f66; WORD $0x241e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 36], 7 - QUAD $0x0126065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 38], 1 - QUAD $0x02260e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 38], 2 + LONG $0x74c40f66; WORD $0x241e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 36], 6 + LONG $0x74c40f66; WORD $0x2406; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 36], 7 + QUAD $0x01260e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 38], 1 + QUAD $0x0226065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 38], 2 QUAD $0x0326265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 38], 3 - QUAD $0x04262e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 38], 4 + LONG $0x5cc40f66; WORD $0x2616; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 38], 4 LONG $0x5cc40f66; WORD $0x260e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 38], 5 - LONG $0x5cc40f66; WORD $0x2616; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 38], 6 - LONG $0x5cc40f66; WORD $0x261e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 38], 7 + LONG $0x5cc40f66; WORD $0x261e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 38], 6 + LONG $0x5cc40f66; WORD $0x2606; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 38], 7 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0xef6e0f66 // movd xmm5, edi - QUAD $0x0128066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 40], 1 - QUAD $0x02280e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 40], 2 + LONG $0x6e0f4166; BYTE $0xeb // movd xmm5, r11d + QUAD $0x01280e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 40], 1 + QUAD $0x0228066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 40], 2 QUAD $0x0328266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 40], 3 - QUAD $0x04282e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 40], 4 + LONG $0x6cc40f66; WORD $0x2816; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 40], 4 LONG $0x6cc40f66; WORD $0x280e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 40], 5 - LONG $0x6cc40f66; WORD $0x2816; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 40], 6 - LONG $0x44b70f42; WORD $0x323e // movzx eax, word [rsi + r15 + 50] + LONG $0x6cc40f66; WORD $0x281e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 40], 6 + LONG $0x7cb70f42; WORD $0x323e // movzx edi, word [rsi + r15 + 50] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] - LONG $0x7cb70f42; WORD $0x343e // movzx edi, word [rsi + r15 + 52] - LONG $0x18247c89 // mov dword [rsp + 24], edi - LONG $0x6cc40f66; WORD $0x281e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 40], 7 + LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d + LONG $0x5cb70f46; WORD $0x343e // movzx r11d, word [rsi + r15 + 52] + LONG $0x6cc40f66; WORD $0x2806; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 40], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 @@ -8772,25 +7218,25 @@ LBB1_135: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xebeb0f66 // por xmm5, xmm3 - LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d - LONG $0x5cb70f46; WORD $0x363e // movzx r11d, word [rsi + r15 + 54] - QUAD $0x012a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 42], 1 - QUAD $0x022a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 42], 2 + LONG $0x6e0f4166; BYTE $0xfd // movd xmm7, r13d + LONG $0x74b70f46; WORD $0x363e // movzx r14d, word [rsi + r15 + 54] + QUAD $0x012a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 42], 1 + QUAD $0x022a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 42], 2 QUAD $0x032a264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 42], 3 - QUAD $0x042a2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 42], 4 + LONG $0x4cc40f66; WORD $0x2a16; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 42], 4 LONG $0x4cc40f66; WORD $0x2a0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 42], 5 - LONG $0x4cc40f66; WORD $0x2a16; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 42], 6 - LONG $0x4cc40f66; WORD $0x2a1e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 42], 7 - QUAD $0x012c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 44], 1 - QUAD $0x022c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 44], 2 + LONG $0x4cc40f66; WORD $0x2a1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 42], 6 + LONG $0x4cc40f66; WORD $0x2a06; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 42], 7 + QUAD $0x012c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 44], 1 + QUAD $0x022c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 44], 2 QUAD $0x032c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 44], 3 - QUAD $0x042c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 44], 4 + LONG $0x7cc40f66; WORD $0x2c16; BYTE $0x04 // pinsrw xmm7, word [rsi + rdx + 44], 4 LONG $0x7cc40f66; WORD $0x2c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 44], 5 - LONG $0x7cc40f66; WORD $0x2c16; BYTE $0x06 // pinsrw xmm7, word [rsi + rdx + 44], 6 + LONG $0x7cc40f66; WORD $0x2c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 44], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xde // movd xmm3, r14d + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d LONG $0x54b70f46; WORD $0x383e // movzx r10d, word [rsi + r15 + 56] - LONG $0x7cc40f66; WORD $0x2c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 44], 7 + LONG $0x7cc40f66; WORD $0x2c06; BYTE $0x07 // pinsrw xmm7, word [rsi + rax + 44], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 @@ -8803,56 +7249,55 @@ LBB1_135: LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xf9eb0f66 // por xmm7, xmm1 LONG $0x746e0f66; WORD $0x1024 // movd xmm6, dword [rsp + 16] - LONG $0x74b70f46; WORD $0x3a3e // movzx r14d, word [rsi + r15 + 58] - QUAD $0x012e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 46], 1 - QUAD $0x022e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 46], 2 + LONG $0x6cb70f46; WORD $0x3a3e // movzx r13d, word [rsi + r15 + 58] + QUAD $0x012e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 46], 1 + QUAD $0x022e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 46], 2 QUAD $0x032e265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 46], 3 - QUAD $0x042e2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 46], 4 + LONG $0x5cc40f66; WORD $0x2e16; BYTE $0x04 // pinsrw xmm3, word [rsi + rdx + 46], 4 LONG $0x5cc40f66; WORD $0x2e0e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 46], 5 - LONG $0x5cc40f66; WORD $0x2e16; BYTE $0x06 // pinsrw xmm3, word [rsi + rdx + 46], 6 - LONG $0x5cc40f66; WORD $0x2e1e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 46], 7 + LONG $0x5cc40f66; WORD $0x2e1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 46], 6 + LONG $0x5cc40f66; WORD $0x2e06; BYTE $0x07 // pinsrw xmm3, word [rsi + rax + 46], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 LONG $0xdfeb0f66 // por xmm3, xmm7 - LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xcf6e0f66 // movd xmm1, edi LONG $0x7cb70f42; WORD $0x3c3e // movzx edi, word [rsi + r15 + 60] LONG $0x7cb70f46; WORD $0x3e3e // movzx r15d, word [rsi + r15 + 62] - QUAD $0x0132064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 1 - QUAD $0x02320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 2 + QUAD $0x01320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 1 + QUAD $0x0232064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 2 QUAD $0x0332264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 50], 3 - QUAD $0x04322e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 50], 4 + LONG $0x4cc40f66; WORD $0x3216; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 50], 4 LONG $0x4cc40f66; WORD $0x320e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 50], 5 - LONG $0x4cc40f66; WORD $0x3216; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 50], 6 - LONG $0x4cc40f66; WORD $0x321e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 50], 7 + LONG $0x4cc40f66; WORD $0x321e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 50], 6 + LONG $0x4cc40f66; WORD $0x3206; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 50], 7 LONG $0xddeb0f66 // por xmm3, xmm5 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xe96f0f66 // movdqa xmm5, xmm1 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xe9f80f66 // psubb xmm5, xmm1 - LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x01300674c40f4266 // pinsrw xmm6, word [rsi + r8 + 48], 1 - QUAD $0x02300e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 48], 2 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + QUAD $0x01300e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 48], 1 + QUAD $0x02300674c40f4266 // pinsrw xmm6, word [rsi + r8 + 48], 2 QUAD $0x03302674c40f4266 // pinsrw xmm6, word [rsi + r12 + 48], 3 - QUAD $0x04302e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 48], 4 + LONG $0x74c40f66; WORD $0x3016; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 48], 4 LONG $0x74c40f66; WORD $0x300e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 48], 5 - LONG $0x74c40f66; WORD $0x3016; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 48], 6 - LONG $0x74c40f66; WORD $0x301e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 48], 7 + LONG $0x74c40f66; WORD $0x301e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 48], 6 + LONG $0x74c40f66; WORD $0x3006; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 48], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 - QUAD $0x0134064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 52], 1 - QUAD $0x02340e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 52], 2 + QUAD $0x01340e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 52], 1 + QUAD $0x0234064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 52], 2 QUAD $0x0334264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 52], 3 - QUAD $0x04342e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 52], 4 + LONG $0x4cc40f66; WORD $0x3416; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 52], 4 LONG $0x4cc40f66; WORD $0x340e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 52], 5 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0x4cc40f66; WORD $0x3416; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 52], 6 + LONG $0x4cc40f66; WORD $0x341e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 52], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - LONG $0x4cc40f66; WORD $0x341e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 52], 7 + LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d + LONG $0x4cc40f66; WORD $0x3406; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 52], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 @@ -8860,20 +7305,20 @@ LBB1_135: LONG $0xdb0f4166; BYTE $0xc9 // pand xmm1, xmm9 LONG $0xcdeb0f66 // por xmm1, xmm5 LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d - QUAD $0x01360674c40f4266 // pinsrw xmm6, word [rsi + r8 + 54], 1 - QUAD $0x02360e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 54], 2 + QUAD $0x01360e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 54], 1 + QUAD $0x02360674c40f4266 // pinsrw xmm6, word [rsi + r8 + 54], 2 QUAD $0x03362674c40f4266 // pinsrw xmm6, word [rsi + r12 + 54], 3 - QUAD $0x04362e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 54], 4 + LONG $0x74c40f66; WORD $0x3616; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 54], 4 LONG $0x74c40f66; WORD $0x360e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 54], 5 - LONG $0x74c40f66; WORD $0x3616; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 54], 6 - LONG $0x74c40f66; WORD $0x361e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 54], 7 - QUAD $0x0138066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 56], 1 - QUAD $0x02380e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 56], 2 + LONG $0x74c40f66; WORD $0x361e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 54], 6 + LONG $0x74c40f66; WORD $0x3606; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 54], 7 + QUAD $0x01380e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 56], 1 + QUAD $0x0238066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 56], 2 QUAD $0x0338266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 56], 3 - QUAD $0x04382e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 56], 4 + LONG $0x6cc40f66; WORD $0x3816; BYTE $0x04 // pinsrw xmm5, word [rsi + rdx + 56], 4 LONG $0x6cc40f66; WORD $0x380e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 56], 5 - LONG $0x6cc40f66; WORD $0x3816; BYTE $0x06 // pinsrw xmm5, word [rsi + rdx + 56], 6 - LONG $0x6cc40f66; WORD $0x381e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 56], 7 + LONG $0x6cc40f66; WORD $0x381e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 56], 6 + LONG $0x6cc40f66; WORD $0x3806; BYTE $0x07 // pinsrw xmm5, word [rsi + rax + 56], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8885,23 +7330,23 @@ LBB1_135: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d - QUAD $0x013a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 58], 1 - QUAD $0x023a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 58], 2 + LONG $0x6e0f4166; BYTE $0xf5 // movd xmm6, r13d + QUAD $0x013a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 58], 1 + QUAD $0x023a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 58], 2 QUAD $0x033a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 58], 3 - QUAD $0x043a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 58], 4 + LONG $0x74c40f66; WORD $0x3a16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 58], 4 LONG $0x74c40f66; WORD $0x3a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 58], 5 - LONG $0x74c40f66; WORD $0x3a16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 58], 6 - LONG $0x74c40f66; WORD $0x3a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 58], 7 + LONG $0x74c40f66; WORD $0x3a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 58], 6 + LONG $0x74c40f66; WORD $0x3a06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 58], 7 LONG $0xe9eb0f66 // por xmm5, xmm1 LONG $0xcf6e0f66 // movd xmm1, edi - QUAD $0x013c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 60], 1 - QUAD $0x023c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 60], 2 + QUAD $0x013c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 60], 1 + QUAD $0x023c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 60], 2 QUAD $0x033c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 60], 3 - QUAD $0x043c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 60], 4 + LONG $0x4cc40f66; WORD $0x3c16; BYTE $0x04 // pinsrw xmm1, word [rsi + rdx + 60], 4 LONG $0x4cc40f66; WORD $0x3c0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 60], 5 - LONG $0x4cc40f66; WORD $0x3c16; BYTE $0x06 // pinsrw xmm1, word [rsi + rdx + 60], 6 - LONG $0x4cc40f66; WORD $0x3c1e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 60], 7 + LONG $0x4cc40f66; WORD $0x3c1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 60], 6 + LONG $0x4cc40f66; WORD $0x3c06; BYTE $0x07 // pinsrw xmm1, word [rsi + rax + 60], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -8914,13 +7359,14 @@ LBB1_135: LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 LONG $0xceeb0f66 // por xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf7 // movd xmm6, r15d - QUAD $0x013e0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 62], 1 - QUAD $0x023e0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 62], 2 + QUAD $0x013e0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 62], 1 + QUAD $0x023e0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 62], 2 QUAD $0x033e2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 62], 3 - QUAD $0x043e2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 62], 4 + LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] + LONG $0x74c40f66; WORD $0x3e16; BYTE $0x04 // pinsrw xmm6, word [rsi + rdx + 62], 4 LONG $0x74c40f66; WORD $0x3e0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 62], 5 - LONG $0x74c40f66; WORD $0x3e16; BYTE $0x06 // pinsrw xmm6, word [rsi + rdx + 62], 6 - LONG $0x74c40f66; WORD $0x3e1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 62], 7 + LONG $0x74c40f66; WORD $0x3e1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 62], 6 + LONG $0x74c40f66; WORD $0x3e06; BYTE $0x07 // pinsrw xmm6, word [rsi + rax + 62], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 @@ -8938,32 +7384,32 @@ LBB1_135: LONG $0xde600f66 // punpcklbw xmm3, xmm6 LONG $0xe2600f66 // punpcklbw xmm4, xmm2 LONG $0xe3610f66 // punpcklwd xmm4, xmm3 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x247f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm4 - LONG $0x4c7f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm1 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + LONG $0x247f0ff3; BYTE $0x8f // movdqu oword [rdi + 4*rcx], xmm4 + LONG $0x4c7f0ff3; WORD $0x108f // movdqu oword [rdi + 4*rcx + 16], xmm1 LONG $0x08c18348 // add rcx, 8 WORD $0x8949; BYTE $0xcf // mov r15, rcx LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB1_135 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - LONG $0x247c3b4c; BYTE $0x20 // cmp r15, qword [rsp + 32] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - LONG $0x245c8b44; BYTE $0x04 // mov r11d, dword [rsp + 4] - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - JNE LBB1_137 - JMP LBB1_140 + JNE LBB1_152 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x246c8b44; BYTE $0x38 // mov r13d, dword [rsp + 56] + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + JNE LBB1_154 + JMP LBB1_157 -LBB1_182: - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - LONG $0xfce08349 // and r8, -4 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 +LBB1_205: + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0xfce08348 // and rax, -4 + WORD $0x8948; BYTE $0xc3 // mov rbx, rax LONG $0x07e3c148 // shl rbx, 7 WORD $0x0148; BYTE $0xf3 // add rbx, rsi - LONG $0x863c8d4f // lea r15, [r14 + 4*r8] - WORD $0x280f; BYTE $0xc8 // movaps xmm1, xmm0 + LONG $0x842c8d4d // lea r13, [r12 + 4*rax] + LONG $0xc86f0f66 // movdqa xmm1, xmm0 LONG $0x00c8c60f // shufps xmm1, xmm0, 0 LONG $0xfcc68148; WORD $0x0001; BYTE $0x00 // add rsi, 508 - WORD $0xc931 // xor ecx, ecx + WORD $0xd231 // xor edx, edx LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI1_0] */ LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI1_1] */ LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI1_2] */ @@ -8973,7 +7419,7 @@ LBB1_182: LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI1_6] */ LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI1_7] */ -LBB1_183: +LBB1_206: QUAD $0xfffffe04b6100ff3 // movss xmm6, dword [rsi - 508] QUAD $0xfffffe08be100ff3 // movss xmm7, dword [rsi - 504] QUAD $0xfffffe0cae100ff3 // movss xmm5, dword [rsi - 500] @@ -9250,78 +7696,1899 @@ LBB1_183: QUAD $0xffff6c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 148], 32 LONG $0x213a0f66; WORD $0xec5e; BYTE $0x30 // insertps xmm3, dword [rsi - 20], 48 LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0xfffffe7096100ff3 // movss xmm2, dword [rsi - 400] - QUAD $0xfffef096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 272], 16 - QUAD $0xffff7096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 144], 32 - LONG $0x213a0f66; WORD $0xf056; BYTE $0x30 // insertps xmm2, dword [rsi - 16], 48 - LONG $0x00d9c20f // cmpeqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] - QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 - QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 - LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 - LONG $0x00d1c20f // cmpeqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0x00f1c20f // cmpeqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf2eb0f66 // por xmm6, xmm2 - QUAD $0xfffffe78be100ff3 // movss xmm7, dword [rsi - 392] - QUAD $0xfffef8be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 264], 16 - QUAD $0xffff78be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 136], 32 - LONG $0x213a0f66; WORD $0xf87e; BYTE $0x30 // insertps xmm7, dword [rsi - 8], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffffe7c96100ff3 // movss xmm2, dword [rsi - 388] - QUAD $0xfffefc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 260], 16 - QUAD $0xffff7c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 132], 32 - LONG $0x213a0f66; WORD $0xfc56; BYTE $0x30 // insertps xmm2, dword [rsi - 4], 48 - LONG $0x00f9c20f // cmpeqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x00d1c20f // cmpeqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffffe809e100ff3 // movss xmm3, dword [rsi - 384] - QUAD $0xffff009e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 256], 16 - LONG $0x213a0f66; WORD $0x805e; BYTE $0x20 // insertps xmm3, dword [rsi - 128], 32 - LONG $0x213a0f66; WORD $0x301e // insertps xmm3, dword [rsi], 48 - LONG $0x00d9c20f // cmpeqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0xdeeb0f66 // por xmm3, xmm6 - LONG $0xeb620f66 // punpckldq xmm5, xmm3 - LONG $0xe5600f66 // punpcklbw xmm4, xmm5 - LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 - LONG $0x7f0f41f3; WORD $0x8e24 // movdqu oword [r14 + 4*rcx], xmm4 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 - WORD $0x3949; BYTE $0xc8 // cmp r8, rcx - JNE LBB1_183 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB1_185 - JMP LBB1_188 + QUAD $0xfffffe7096100ff3 // movss xmm2, dword [rsi - 400] + QUAD $0xfffef096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 272], 16 + QUAD $0xffff7096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 144], 32 + LONG $0x213a0f66; WORD $0xf056; BYTE $0x30 // insertps xmm2, dword [rsi - 16], 48 + LONG $0x00d9c20f // cmpeqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] + QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 + QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 + LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 + LONG $0x00d1c20f // cmpeqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0x00f1c20f // cmpeqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf2eb0f66 // por xmm6, xmm2 + QUAD $0xfffffe78be100ff3 // movss xmm7, dword [rsi - 392] + QUAD $0xfffef8be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 264], 16 + QUAD $0xffff78be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 136], 32 + LONG $0x213a0f66; WORD $0xf87e; BYTE $0x30 // insertps xmm7, dword [rsi - 8], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe7c96100ff3 // movss xmm2, dword [rsi - 388] + QUAD $0xfffefc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 260], 16 + QUAD $0xffff7c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 132], 32 + LONG $0x213a0f66; WORD $0xfc56; BYTE $0x30 // insertps xmm2, dword [rsi - 4], 48 + LONG $0x00f9c20f // cmpeqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x00d1c20f // cmpeqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe809e100ff3 // movss xmm3, dword [rsi - 384] + QUAD $0xffff009e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 256], 16 + LONG $0x213a0f66; WORD $0x805e; BYTE $0x20 // insertps xmm3, dword [rsi - 128], 32 + LONG $0x213a0f66; WORD $0x301e // insertps xmm3, dword [rsi], 48 + LONG $0x00d9c20f // cmpeqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0xdeeb0f66 // por xmm3, xmm6 + LONG $0xeb620f66 // punpckldq xmm5, xmm3 + LONG $0xe5600f66 // punpcklbw xmm4, xmm5 + LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 + LONG $0x7f0f41f3; WORD $0x9424 // movdqu oword [r12 + 4*rdx], xmm4 + LONG $0x04c28348 // add rdx, 4 + LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JNE LBB1_206 + WORD $0x3948; BYTE $0xc1 // cmp rcx, rax + JNE LBB1_208 + JMP LBB1_211 + +LBB1_100: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xd8 // add rax, r11 + QUAD $0x0000013024848948 // mov qword [rsp + 304], rax + QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + LONG $0xc6b60f41 // movzx eax, r14b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + WORD $0xc031 // xor eax, eax + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + +LBB1_101: + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + LONG $0x05e6c148 // shl rsi, 5 + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x8949; BYTE $0xf0 // mov r8, rsi + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8949; BYTE $0xf5 // mov r13, rsi + WORD $0x8949; BYTE $0xf1 // mov r9, rsi + WORD $0x8949; BYTE $0xf2 // mov r10, rsi + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + WORD $0x8949; BYTE $0xf7 // mov r15, rsi + LONG $0x24748948; BYTE $0x40 // mov qword [rsp + 64], rsi + LONG $0x0cb60f41; BYTE $0x33 // movzx ecx, byte [r11 + rsi] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x4cb60f41; WORD $0x0133 // movzx ecx, byte [r11 + rsi + 1] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x4cb60f41; WORD $0x0233 // movzx ecx, byte [r11 + rsi + 2] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x4cb60f41; WORD $0x0333 // movzx ecx, byte [r11 + rsi + 3] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x4cb60f41; WORD $0x0433 // movzx ecx, byte [r11 + rsi + 4] + LONG $0xc96e0f66 // movd xmm1, ecx + LONG $0x4cb60f41; WORD $0x0533 // movzx ecx, byte [r11 + rsi + 5] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x4cb60f41; WORD $0x0633 // movzx ecx, byte [r11 + rsi + 6] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x4cb60f41; WORD $0x0733 // movzx ecx, byte [r11 + rsi + 7] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 + LONG $0x4cb60f41; WORD $0x0833 // movzx ecx, byte [r11 + rsi + 8] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x00010024847f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm0 + LONG $0x4cb60f41; WORD $0x0933 // movzx ecx, byte [r11 + rsi + 9] + LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx + LONG $0x4cb60f41; WORD $0x0a33 // movzx ecx, byte [r11 + rsi + 10] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 + LONG $0x4cb60f41; WORD $0x0b33 // movzx ecx, byte [r11 + rsi + 11] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x4cb60f41; WORD $0x0c33 // movzx ecx, byte [r11 + rsi + 12] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x4cb60f41; WORD $0x0d33 // movzx ecx, byte [r11 + rsi + 13] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x4cb60f41; WORD $0x0e33 // movzx ecx, byte [r11 + rsi + 14] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + LONG $0x20cc8349 // or r12, 32 + LONG $0x2464894c; BYTE $0x20 // mov qword [rsp + 32], r12 + LONG $0x40cb8348 // or rbx, 64 + LONG $0x245c8948; BYTE $0x30 // mov qword [rsp + 48], rbx + LONG $0x60ca8348 // or rdx, 96 + LONG $0x24548948; BYTE $0x70 // mov qword [rsp + 112], rdx + LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 + LONG $0xa0cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 160 + LONG $0x247c8948; BYTE $0x60 // mov qword [rsp + 96], rdi + LONG $0x00c00d48; WORD $0x0000 // or rax, 192 + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + LONG $0xe0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 224 + LONG $0x00c98149; WORD $0x0001; BYTE $0x00 // or r9, 256 + QUAD $0x000000c0248c894c // mov qword [rsp + 192], r9 + LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 + LONG $0x40ce8149; WORD $0x0001; BYTE $0x00 // or r14, 320 + LONG $0x60cf8149; WORD $0x0001; BYTE $0x00 // or r15, 352 + LONG $0x247c894c; BYTE $0x50 // mov qword [rsp + 80], r15 + LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] + LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 + LONG $0x247c8948; BYTE $0x40 // mov qword [rsp + 64], rdi + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x01a00d48; WORD $0x0000 // or rax, 416 + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0x24748948; BYTE $0x38 // mov qword [rsp + 56], rsi + LONG $0x01c00d48; WORD $0x0000 // or rax, 448 + LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 + LONG $0x244c8948; BYTE $0x28 // mov qword [rsp + 40], rcx + QUAD $0x01233c203a0f4766 // pinsrb xmm15, byte [r11 + r12], 1 + QUAD $0x021b3c203a0f4566 // pinsrb xmm15, byte [r11 + rbx], 2 + QUAD $0x03133c203a0f4566 // pinsrb xmm15, byte [r11 + rdx], 3 + QUAD $0x04033c203a0f4766 // pinsrb xmm15, byte [r11 + r8], 4 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x05233c203a0f4766 // pinsrb xmm15, byte [r11 + r12], 5 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x061b3c203a0f4566 // pinsrb xmm15, byte [r11 + rbx], 6 + LONG $0x246c894c; BYTE $0x48 // mov qword [rsp + 72], r13 + QUAD $0x072b3c203a0f4766 // pinsrb xmm15, byte [r11 + r13], 7 + QUAD $0x080b3c203a0f4766 // pinsrb xmm15, byte [r11 + r9], 8 + QUAD $0x09133c203a0f4766 // pinsrb xmm15, byte [r11 + r10], 9 + QUAD $0x0a333c203a0f4766 // pinsrb xmm15, byte [r11 + r14], 10 + QUAD $0x0b3b3c203a0f4766 // pinsrb xmm15, byte [r11 + r15], 11 + QUAD $0x0c3b3c203a0f4566 // pinsrb xmm15, byte [r11 + rdi], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0d333c203a0f4566 // pinsrb xmm15, byte [r11 + rsi], 13 + QUAD $0x0e033c203a0f4566 // pinsrb xmm15, byte [r11 + rax], 14 + QUAD $0x0f0b3c203a0f4566 // pinsrb xmm15, byte [r11 + rcx], 15 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x01336c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r11 + rsi + 1], 1 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x013b6c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r11 + r15 + 1], 2 + QUAD $0x01136c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r11 + rdx + 1], 3 + QUAD $0x01036c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r11 + r8 + 1], 4 + QUAD $0x01236c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r11 + r12 + 1], 5 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + QUAD $0x011b6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r11 + rbx + 1], 6 + QUAD $0x012b6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r11 + r13 + 1], 7 + QUAD $0x010b6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r11 + r9 + 1], 8 + QUAD $0x01136c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r11 + r10 + 1], 9 + WORD $0x894d; BYTE $0xd4 // mov r12, r10 + QUAD $0x01336c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r11 + r14 + 1], 10 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + QUAD $0x000000e024b4894c // mov qword [rsp + 224], r14 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x01336c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r11 + rsi + 1], 11 + QUAD $0x013b6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r11 + rdi + 1], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x01336c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r11 + rsi + 1], 13 + QUAD $0x01036c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r11 + rax + 1], 14 + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax + QUAD $0x010b6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r11 + rcx + 1], 15 + QUAD $0x00b0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 + LONG $0xfd6f0f66 // movdqa xmm7, xmm5 + QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI1_10] */ + LONG $0xfcdb0f66 // pand xmm7, xmm4 + LONG $0xfdf80f66 // psubb xmm7, xmm5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x7cb60f41; WORD $0x0f03 // movzx edi, byte [r11 + rax + 15] + LONG $0x6e0f4466; BYTE $0xf7 // movd xmm14, edi + LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x020b74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r11 + rcx + 2], 1 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x022b74203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r11 + r13 + 2], 2 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x023374203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r11 + r14 + 2], 3 + QUAD $0x020374203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r11 + r8 + 2], 4 + QUAD $0x021374203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r11 + rdx + 2], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x023374203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r11 + rsi + 2], 6 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x020b74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r11 + r9 + 2], 7 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x021374203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r11 + r10 + 2], 8 + QUAD $0x022374203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r11 + r12 + 2], 9 + QUAD $0x023b74203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r11 + r15 + 2], 10 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x023b74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r11 + r15 + 2], 11 + LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] + QUAD $0x023b74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r11 + rdi + 2], 12 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x023b74203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r11 + rdi + 2], 13 + QUAD $0x021b74203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r11 + rbx + 2], 14 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x023b74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r11 + rdi + 2], 15 + LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 + LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 + QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xf0db0f66 // pand xmm6, xmm0 + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x7cb60f41; WORD $0x1003 // movzx edi, byte [r11 + rax + 16] + LONG $0x6e0f4466; BYTE $0xff // movd xmm15, edi + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x030b54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rcx + 3], 1 + QUAD $0x032b54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r11 + r13 + 3], 2 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + QUAD $0x033354203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r14 + 3], 3 + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + LONG $0x2444894c; BYTE $0x68 // mov qword [rsp + 104], r8 + QUAD $0x030354203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r11 + r8 + 3], 4 + QUAD $0x031354203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r11 + rdx + 3], 5 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + QUAD $0x033354203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r11 + rsi + 3], 6 + WORD $0x894c; BYTE $0xce // mov rsi, r9 + QUAD $0x030b54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r11 + r9 + 3], 7 + WORD $0x894d; BYTE $0xd0 // mov r8, r10 + QUAD $0x031354203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r11 + r10 + 3], 8 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + QUAD $0x032354203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r12 + 3], 9 + QUAD $0x000000e024948b4c // mov r10, qword [rsp + 224] + QUAD $0x031354203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r11 + r10 + 3], 10 + QUAD $0x033b54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r11 + r15 + 3], 11 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x032354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r12 + 3], 12 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x033b54203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rdi + 3], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x033b54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r11 + rdi + 3], 14 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x033b54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r11 + rdi + 3], 15 + QUAD $0x04034c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r11 + rax + 4], 1 + QUAD $0x042b4c203a0f4366; BYTE $0x02 // pinsrb xmm1, byte [r11 + r13 + 4], 2 + QUAD $0x041b4c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r11 + rbx + 4], 3 + QUAD $0x04334c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r11 + r14 + 4], 4 + QUAD $0x04134c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r11 + rdx + 4], 5 + QUAD $0x040b4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r11 + rcx + 4], 6 + WORD $0x8948; BYTE $0xcb // mov rbx, rcx + QUAD $0x04334c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r11 + rsi + 4], 7 + QUAD $0x04034c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r11 + r8 + 4], 8 + QUAD $0x040b4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r11 + r9 + 4], 9 + WORD $0x894d; BYTE $0xcd // mov r13, r9 + QUAD $0x00000120248c894c // mov qword [rsp + 288], r9 + QUAD $0x04134c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r11 + r10 + 4], 10 + QUAD $0x043b4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r11 + r15 + 4], 11 + QUAD $0x04234c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r11 + r12 + 4], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x04334c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r11 + rsi + 4], 13 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x04134c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r11 + rdx + 4], 14 + QUAD $0x043b4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r11 + rdi + 4], 15 + LONG $0xf7eb0f66 // por xmm6, xmm7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x7cb60f41; WORD $0x1103 // movzx edi, byte [r11 + rax + 17] + LONG $0xc76e0f66 // movd xmm0, edi + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0xd5db0f66 // pand xmm2, xmm5 + LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 + QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xcddb0f66 // pand xmm1, xmm5 + LONG $0xcaeb0f66 // por xmm1, xmm2 + LONG $0x7cb60f41; WORD $0x1203 // movzx edi, byte [r11 + rax + 18] + LONG $0xef6e0f66 // movd xmm5, edi + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x050344203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r11 + r8 + 5], 1 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x050b44203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r11 + r9 + 5], 2 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x053344203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r11 + r14 + 5], 3 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + QUAD $0x051344203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r11 + r10 + 5], 4 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x050b44203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r11 + rcx + 5], 5 + QUAD $0x051b44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r11 + rbx + 5], 6 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x051b44203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r11 + rbx + 5], 7 + QUAD $0x000000c024bc8b4c // mov r15, qword [rsp + 192] + QUAD $0x053b44203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r11 + r15 + 5], 8 + QUAD $0x052b44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r11 + r13 + 5], 9 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x052344203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r11 + r12 + 5], 10 + LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] + QUAD $0x053b44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r11 + rdi + 5], 11 + LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] + QUAD $0x053b44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r11 + rdi + 5], 12 + QUAD $0x053344203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r11 + rsi + 5], 13 + QUAD $0x051344203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r11 + rdx + 5], 14 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x053344203a0f4566; BYTE $0x0f // pinsrb xmm8, byte [r11 + rsi + 5], 15 + LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 + QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI1_14] */ + LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + LONG $0x7cb60f41; WORD $0x1303 // movzx edi, byte [r11 + rax + 19] + LONG $0xff6e0f66 // movd xmm7, edi + LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 + LONG $0x7cb60f41; WORD $0x1403 // movzx edi, byte [r11 + rax + 20] + LONG $0xf76e0f66 // movd xmm6, edi + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x06035c203a0f4366; BYTE $0x01 // pinsrb xmm3, byte [r11 + r8 + 6], 1 + WORD $0x894d; BYTE $0xc8 // mov r8, r9 + QUAD $0x060b5c203a0f4366; BYTE $0x02 // pinsrb xmm3, byte [r11 + r9 + 6], 2 + QUAD $0x06335c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r11 + r14 + 6], 3 + QUAD $0x06135c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r11 + r10 + 6], 4 + QUAD $0x060b5c203a0f4166; BYTE $0x05 // pinsrb xmm3, byte [r11 + rcx + 6], 5 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x060b5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r11 + rcx + 6], 6 + QUAD $0x061b5c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r11 + rbx + 6], 7 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x063b5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r11 + r15 + 6], 8 + QUAD $0x062b5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r11 + r13 + 6], 9 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x06235c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r11 + r12 + 6], 10 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x06035c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r11 + rax + 6], 11 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x06235c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r11 + r12 + 6], 12 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x061b5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r11 + rbx + 6], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x063b5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r11 + rdi + 6], 14 + QUAD $0x06335c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r11 + rsi + 6], 15 + QUAD $0x0000d024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 208] + QUAD $0x071354203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rdx + 7], 1 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x070354203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r11 + r8 + 7], 2 + QUAD $0x073354203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r14 + 7], 3 + QUAD $0x071354203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r11 + r10 + 7], 4 + WORD $0x894d; BYTE $0xd0 // mov r8, r10 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x073354203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r11 + rsi + 7], 5 + QUAD $0x070b54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r11 + rcx + 7], 6 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x073354203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r11 + r14 + 7], 7 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + QUAD $0x070b54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r11 + r9 + 7], 8 + QUAD $0x072b54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r13 + 7], 9 + QUAD $0x073b54203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r11 + r15 + 7], 10 + QUAD $0x070354203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r11 + rax + 7], 11 + QUAD $0x072354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r12 + 7], 12 + QUAD $0x071b54203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rbx + 7], 13 + QUAD $0x073b54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r11 + rdi + 7], 14 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x071354203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r11 + rdx + 7], 15 + LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 + QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI1_15] */ + LONG $0xd9db0f66 // pand xmm3, xmm1 + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 + LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI1_6] */ + LONG $0xd1db0f66 // pand xmm2, xmm1 + LONG $0xd3eb0f66 // por xmm2, xmm3 + LONG $0xca6f0f66 // movdqa xmm1, xmm2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x7cb60f41; WORD $0x1503 // movzx edi, byte [r11 + rax + 21] + LONG $0xd76e0f66 // movd xmm2, edi + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x092b54203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r11 + r13 + 9], 1 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x091b54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r11 + rbx + 9], 2 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x091354203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r11 + r10 + 9], 3 + QUAD $0x090354203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r11 + r8 + 9], 4 + QUAD $0x093354203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r11 + rsi + 9], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x093354203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r11 + rsi + 9], 6 + WORD $0x894d; BYTE $0xf1 // mov r9, r14 + QUAD $0x093354203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r11 + r14 + 9], 7 + WORD $0x8949; BYTE $0xce // mov r14, rcx + QUAD $0x090b54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r11 + rcx + 9], 8 + QUAD $0x00000120248c8b48 // mov rcx, qword [rsp + 288] + QUAD $0x090b54203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r11 + rcx + 9], 9 + QUAD $0x093b54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r11 + r15 + 9], 10 + LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] + QUAD $0x093b54203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r11 + rdi + 9], 11 + QUAD $0x092354203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r11 + r12 + 9], 12 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x093b54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r11 + rdi + 9], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x093b54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r11 + rdi + 9], 14 + QUAD $0x091354203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r11 + rdx + 9], 15 + LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 + LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 + LONG $0xccdb0f66 // pand xmm1, xmm4 + LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 + LONG $0x7cb60f41; WORD $0x1603 // movzx edi, byte [r11 + rax + 22] + LONG $0xdf6e0f66 // movd xmm3, edi + QUAD $0x00010024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 256] + QUAD $0x082b64203a0f4366; BYTE $0x01 // pinsrb xmm4, byte [r11 + r13 + 8], 1 + QUAD $0x081b64203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r11 + rbx + 8], 2 + QUAD $0x081364203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r11 + r10 + 8], 3 + QUAD $0x080364203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r11 + r8 + 8], 4 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x081364203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r11 + rdx + 8], 5 + QUAD $0x083364203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r11 + rsi + 8], 6 + QUAD $0x080b64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r11 + r9 + 8], 7 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + QUAD $0x083364203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r11 + r14 + 8], 8 + WORD $0x8949; BYTE $0xcd // mov r13, rcx + QUAD $0x080b64203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r11 + rcx + 8], 9 + QUAD $0x083b64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r11 + r15 + 8], 10 + WORD $0x894d; BYTE $0xfc // mov r12, r15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x080364203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r11 + rax + 8], 11 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x081364203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r11 + r10 + 8], 12 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x080b64203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r11 + rcx + 8], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x083b64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r11 + rdi + 8], 14 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x083b64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r11 + r15 + 8], 15 + LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 + LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 + QUAD $0x00a024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 160] + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0a3354203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r11 + rsi + 10], 1 + QUAD $0x0a1b54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r11 + rbx + 10], 2 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x0a1b54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r11 + rbx + 10], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0a3354203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r11 + rsi + 10], 4 + QUAD $0x0a1354203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r11 + rdx + 10], 5 + WORD $0x8949; BYTE $0xd6 // mov r14, rdx + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0a1354203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r11 + rdx + 10], 6 + QUAD $0x0a0b54203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r11 + r9 + 10], 7 + QUAD $0x0a0354203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r11 + r8 + 10], 8 + QUAD $0x0a2b54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r11 + r13 + 10], 9 + WORD $0x894d; BYTE $0xe9 // mov r9, r13 + QUAD $0x0a2354203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r11 + r12 + 10], 10 + QUAD $0x0a0354203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r11 + rax + 10], 11 + QUAD $0x0a1354203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r11 + r10 + 10], 12 + WORD $0x894c; BYTE $0xd6 // mov rsi, r10 + QUAD $0x0a0b54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r11 + rcx + 10], 13 + QUAD $0x0a3b54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r11 + rdi + 10], 14 + QUAD $0x0a3b54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r11 + r15 + 10], 15 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + LONG $0x7cb60f41; WORD $0x170b // movzx edi, byte [r11 + rcx + 23] + LONG $0x6e0f4466; BYTE $0xc7 // movd xmm8, edi + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + QUAD $0x00a024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm10 + LONG $0x7cb60f41; WORD $0x180b // movzx edi, byte [r11 + rcx + 24] + LONG $0x6e0f4466; BYTE $0xd7 // movd xmm10, edi + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0b135c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r11 + rdx + 11], 1 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x0b2b5c203a0f4766; BYTE $0x02 // pinsrb xmm11, byte [r11 + r13 + 11], 2 + QUAD $0x0b1b5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r11 + rbx + 11], 3 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0b0b5c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r11 + rcx + 11], 4 + QUAD $0x0b335c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r11 + r14 + 11], 5 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0b0b5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r11 + rcx + 11], 6 + LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] + QUAD $0x0b3b5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r11 + rdi + 11], 7 + QUAD $0x0b035c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r11 + r8 + 11], 8 + QUAD $0x0b0b5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r11 + r9 + 11], 9 + WORD $0x894d; BYTE $0xe2 // mov r10, r12 + QUAD $0x0b235c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r11 + r12 + 11], 10 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + QUAD $0x0b035c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r11 + rax + 11], 11 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + QUAD $0x0b335c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r11 + rsi + 11], 12 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b035c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r11 + rax + 11], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x0b3b5c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r11 + rdi + 11], 14 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0b335c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r11 + rsi + 11], 15 + QUAD $0x0c136c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r11 + rdx + 12], 1 + QUAD $0x0c2b6c203a0f4766; BYTE $0x02 // pinsrb xmm13, byte [r11 + r13 + 12], 2 + QUAD $0x0c1b6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r11 + rbx + 12], 3 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x0c336c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r11 + rsi + 12], 4 + QUAD $0x0c336c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r11 + r14 + 12], 5 + QUAD $0x0c0b6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r11 + rcx + 12], 6 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x0c2b6c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r11 + r13 + 12], 7 + QUAD $0x0c036c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r11 + r8 + 12], 8 + QUAD $0x0c0b6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r11 + r9 + 12], 9 + QUAD $0x0c136c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r11 + r10 + 12], 10 + QUAD $0x0c3b6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r11 + r15 + 12], 11 + QUAD $0x0c236c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r11 + r12 + 12], 12 + QUAD $0x0c036c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r11 + rax + 12], 13 + QUAD $0x0c3b6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r11 + rdi + 12], 14 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0c036c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r11 + rax + 12], 15 + QUAD $0x0d1364203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r11 + rdx + 13], 1 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x0d2b64203a0f4766; BYTE $0x02 // pinsrb xmm12, byte [r11 + r13 + 13], 2 + QUAD $0x0d1b64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r11 + rbx + 13], 3 + QUAD $0x0d3364203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r11 + rsi + 13], 4 + QUAD $0x0d3364203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r11 + r14 + 13], 5 + QUAD $0x0d0b64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r11 + rcx + 13], 6 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d3364203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r11 + rsi + 13], 7 + QUAD $0x0d0364203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r11 + r8 + 13], 8 + QUAD $0x0d0b64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r11 + r9 + 13], 9 + QUAD $0x0d1364203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r11 + r10 + 13], 10 + QUAD $0x0d3b64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r11 + r15 + 13], 11 + QUAD $0x0d2364203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r11 + r12 + 13], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0d3364203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r11 + rsi + 13], 13 + QUAD $0x0d3b64203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r11 + rdi + 13], 14 + QUAD $0x0d0364203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r11 + rax + 13], 15 + LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 + QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 + QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x7cb60f41; WORD $0x1903 // movzx edi, byte [r11 + rax + 25] + LONG $0xcf6e0f66 // movd xmm1, edi + LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 + QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI1_14] */ + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x7cb60f41; WORD $0x1a03 // movzx edi, byte [r11 + rax + 26] + LONG $0x6e0f4466; BYTE $0xdf // movd xmm11, edi + QUAD $0x0000f024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 240] + QUAD $0x0e1364203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r11 + rdx + 14], 1 + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0e3364203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r11 + rsi + 14], 2 + QUAD $0x0e1b64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r11 + rbx + 14], 3 + LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] + QUAD $0x0e3364203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r11 + r14 + 14], 4 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0e0364203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r11 + rax + 14], 5 + QUAD $0x0e0b64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r11 + rcx + 14], 6 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0e1364203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r11 + rdx + 14], 7 + QUAD $0x0e0364203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r11 + r8 + 14], 8 + QUAD $0x0e0b64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r11 + r9 + 14], 9 + QUAD $0x0e1364203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r11 + r10 + 14], 10 + QUAD $0x0e3b64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r11 + r15 + 14], 11 + QUAD $0x0e2364203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r11 + r12 + 14], 12 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x0e3b64203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r11 + rdi + 14], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x0e3b64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r11 + rdi + 14], 14 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x0e3b64203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r11 + rdi + 14], 15 + QUAD $0x0f2b74203a0f4766; BYTE $0x01 // pinsrb xmm14, byte [r11 + r13 + 15], 1 + QUAD $0x0f3374203a0f4566; BYTE $0x02 // pinsrb xmm14, byte [r11 + rsi + 15], 2 + QUAD $0x0f1b74203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r11 + rbx + 15], 3 + QUAD $0x0f3374203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r11 + r14 + 15], 4 + QUAD $0x0f0374203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r11 + rax + 15], 5 + QUAD $0x0f0b74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r11 + rcx + 15], 6 + QUAD $0x0f1374203a0f4566; BYTE $0x07 // pinsrb xmm14, byte [r11 + rdx + 15], 7 + QUAD $0x0f0374203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r11 + r8 + 15], 8 + QUAD $0x0f0b74203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r11 + r9 + 15], 9 + QUAD $0x0f1374203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r11 + r10 + 15], 10 + QUAD $0x0f3b74203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r11 + r15 + 15], 11 + QUAD $0x0f2374203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r11 + r12 + 15], 12 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x0f2b74203a0f4766; BYTE $0x0d // pinsrb xmm14, byte [r11 + r13 + 15], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x0f3b74203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r11 + rdi + 15], 14 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x0f3b74203a0f4566; BYTE $0x0f // pinsrb xmm14, byte [r11 + rdi + 15], 15 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x102b7c203a0f4766; BYTE $0x01 // pinsrb xmm15, byte [r11 + r13 + 16], 1 + QUAD $0x10337c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r11 + rsi + 16], 2 + QUAD $0x101b7c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r11 + rbx + 16], 3 + QUAD $0x10337c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r11 + r14 + 16], 4 + QUAD $0x10037c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r11 + rax + 16], 5 + QUAD $0x100b7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r11 + rcx + 16], 6 + QUAD $0x10137c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r11 + rdx + 16], 7 + QUAD $0x10037c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r11 + r8 + 16], 8 + QUAD $0x100b7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r11 + r9 + 16], 9 + QUAD $0x10137c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r11 + r10 + 16], 10 + QUAD $0x103b7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r11 + r15 + 16], 11 + QUAD $0x10237c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r11 + r12 + 16], 12 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x103b7c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r11 + rdi + 16], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x103b7c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r11 + rdi + 16], 14 + QUAD $0x112b44203a0f4366; BYTE $0x01 // pinsrb xmm0, byte [r11 + r13 + 17], 1 + QUAD $0x113344203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r11 + rsi + 17], 2 + QUAD $0x111b44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r11 + rbx + 17], 3 + QUAD $0x113344203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r11 + r14 + 17], 4 + QUAD $0x110344203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r11 + rax + 17], 5 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x110b44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r11 + rcx + 17], 6 + QUAD $0x111344203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r11 + rdx + 17], 7 + QUAD $0x110344203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r11 + r8 + 17], 8 + QUAD $0x110b44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r11 + r9 + 17], 9 + QUAD $0x111344203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r11 + r10 + 17], 10 + QUAD $0x113b44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r11 + r15 + 17], 11 + QUAD $0x112344203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r11 + r12 + 17], 12 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x110344203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r11 + rax + 17], 13 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x113344203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r11 + rsi + 17], 14 + QUAD $0x00a024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 160] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x7cb60f41; WORD $0x1b03 // movzx edi, byte [r11 + rax + 27] + LONG $0x6e0f4466; BYTE $0xcf // movd xmm9, edi + QUAD $0x00b024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 + QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI1_15] */ + LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 + LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 + LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI1_6] */ + LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 + LONG $0x7cb60f41; WORD $0x1c03 // movzx edi, byte [r11 + rax + 28] + LONG $0xe76e0f66 // movd xmm4, edi + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x111344203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r11 + r10 + 17], 15 + LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 + LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 + LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 + QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI1_10] */ + LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 + LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 + QUAD $0x00a024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm13 + LONG $0x7cb60f41; WORD $0x1d03 // movzx edi, byte [r11 + rax + 29] + LONG $0x6e0f4466; BYTE $0xef // movd xmm13, edi + QUAD $0x10137c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r11 + r10 + 16], 15 + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x123b6c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r11 + rdi + 18], 1 + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x123b6c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r11 + rdi + 18], 2 + QUAD $0x121b6c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r11 + rbx + 18], 3 + QUAD $0x12336c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r11 + r14 + 18], 4 + QUAD $0x122b6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r11 + r13 + 18], 5 + QUAD $0x120b6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r11 + rcx + 18], 6 + QUAD $0x12136c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r11 + rdx + 18], 7 + QUAD $0x12036c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r11 + r8 + 18], 8 + QUAD $0x120b6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r11 + r9 + 18], 9 + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + QUAD $0x12036c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r11 + rax + 18], 10 + QUAD $0x123b6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r11 + r15 + 18], 11 + QUAD $0x12236c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r11 + r12 + 18], 12 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x123b6c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r11 + rdi + 18], 13 + QUAD $0x12336c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r11 + rsi + 18], 14 + LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 + QUAD $0x12136c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r11 + r10 + 18], 15 + LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 + QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + LONG $0x7cb60f41; WORD $0x1e33 // movzx edi, byte [r11 + rsi + 30] + LONG $0x6e0f4466; BYTE $0xe7 // movd xmm12, edi + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x133b7c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r11 + rdi + 19], 1 + QUAD $0x143b74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r11 + rdi + 20], 1 + QUAD $0x153b54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rdi + 21], 1 + QUAD $0x163b5c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r11 + rdi + 22], 1 + QUAD $0x173b44203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r11 + rdi + 23], 1 + QUAD $0x183b54203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r11 + rdi + 24], 1 + QUAD $0x193b4c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r11 + rdi + 25], 1 + QUAD $0x1a3b5c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r11 + rdi + 26], 1 + QUAD $0x1b3b4c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r11 + rdi + 27], 1 + QUAD $0x1c3b64203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r11 + rdi + 28], 1 + QUAD $0x1d3b6c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r11 + rdi + 29], 1 + QUAD $0x1e3b64203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r11 + rdi + 30], 1 + LONG $0x74b60f41; WORD $0x1f33 // movzx esi, byte [r11 + rsi + 31] + LONG $0xc66e0f66 // movd xmm0, esi + QUAD $0x1f3b44203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r11 + rdi + 31], 1 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x13337c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r11 + rsi + 19], 2 + QUAD $0x143374203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r11 + rsi + 20], 2 + QUAD $0x153354203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r11 + rsi + 21], 2 + QUAD $0x16335c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r11 + rsi + 22], 2 + QUAD $0x173344203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r11 + rsi + 23], 2 + QUAD $0x183354203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r11 + rsi + 24], 2 + QUAD $0x19334c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r11 + rsi + 25], 2 + QUAD $0x1a335c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r11 + rsi + 26], 2 + QUAD $0x1b334c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r11 + rsi + 27], 2 + QUAD $0x1c3364203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r11 + rsi + 28], 2 + QUAD $0x1d336c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r11 + rsi + 29], 2 + QUAD $0x1e3364203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r11 + rsi + 30], 2 + QUAD $0x1f3344203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r11 + rsi + 31], 2 + QUAD $0x131b7c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r11 + rbx + 19], 3 + QUAD $0x13337c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r11 + r14 + 19], 4 + QUAD $0x132b7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r11 + r13 + 19], 5 + QUAD $0x130b7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r11 + rcx + 19], 6 + QUAD $0x13137c203a0f4166; BYTE $0x07 // pinsrb xmm7, byte [r11 + rdx + 19], 7 + QUAD $0x13037c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r11 + r8 + 19], 8 + QUAD $0x130b7c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r11 + r9 + 19], 9 + QUAD $0x13037c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r11 + rax + 19], 10 + QUAD $0x133b7c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r11 + r15 + 19], 11 + QUAD $0x13237c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r11 + r12 + 19], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x13337c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r11 + rsi + 19], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x133b7c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r11 + rdi + 19], 14 + QUAD $0x13137c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r11 + r10 + 19], 15 + QUAD $0x141b74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r11 + rbx + 20], 3 + QUAD $0x143374203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r11 + r14 + 20], 4 + QUAD $0x142b74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r11 + r13 + 20], 5 + QUAD $0x140b74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r11 + rcx + 20], 6 + QUAD $0x141374203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r11 + rdx + 20], 7 + QUAD $0x140374203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r11 + r8 + 20], 8 + QUAD $0x140b74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r11 + r9 + 20], 9 + QUAD $0x140374203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r11 + rax + 20], 10 + QUAD $0x143b74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r11 + r15 + 20], 11 + QUAD $0x142374203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r11 + r12 + 20], 12 + QUAD $0x143374203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r11 + rsi + 20], 13 + QUAD $0x143b74203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r11 + rdi + 20], 14 + QUAD $0x0000a024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 160] + QUAD $0x141374203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r11 + r10 + 20], 15 + QUAD $0x00b024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 + QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 + QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xf7eb0f66 // por xmm6, xmm7 + QUAD $0x151b54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r11 + rbx + 21], 3 + QUAD $0x153354203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r11 + r14 + 21], 4 + QUAD $0x152b54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r11 + r13 + 21], 5 + QUAD $0x150b54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r11 + rcx + 21], 6 + QUAD $0x151354203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r11 + rdx + 21], 7 + QUAD $0x150354203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r11 + r8 + 21], 8 + QUAD $0x150b54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r9 + 21], 9 + QUAD $0x150354203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r11 + rax + 21], 10 + QUAD $0x153b54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r11 + r15 + 21], 11 + QUAD $0x152354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r12 + 21], 12 + QUAD $0x153354203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rsi + 21], 13 + QUAD $0x153b54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r11 + rdi + 21], 14 + QUAD $0x151354203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r11 + r10 + 21], 15 + LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 + QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI1_14] */ + LONG $0xd7db0f66 // pand xmm2, xmm7 + LONG $0xd6eb0f66 // por xmm2, xmm6 + LONG $0xd5eb0f66 // por xmm2, xmm5 + QUAD $0x161b5c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r11 + rbx + 22], 3 + QUAD $0x16335c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r11 + r14 + 22], 4 + QUAD $0x162b5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r11 + r13 + 22], 5 + QUAD $0x160b5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r11 + rcx + 22], 6 + QUAD $0x16135c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r11 + rdx + 22], 7 + QUAD $0x16035c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r11 + r8 + 22], 8 + QUAD $0x160b5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r11 + r9 + 22], 9 + QUAD $0x16035c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r11 + rax + 22], 10 + QUAD $0x163b5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r11 + r15 + 22], 11 + QUAD $0x16235c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r11 + r12 + 22], 12 + QUAD $0x16335c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r11 + rsi + 22], 13 + QUAD $0x163b5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r11 + rdi + 22], 14 + QUAD $0x16135c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r11 + r10 + 22], 15 + QUAD $0x171b44203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r11 + rbx + 23], 3 + QUAD $0x173344203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r11 + r14 + 23], 4 + QUAD $0x172b44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r11 + r13 + 23], 5 + QUAD $0x170b44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r11 + rcx + 23], 6 + QUAD $0x171344203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r11 + rdx + 23], 7 + QUAD $0x170344203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r11 + r8 + 23], 8 + QUAD $0x170b44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r11 + r9 + 23], 9 + QUAD $0x170344203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r11 + rax + 23], 10 + QUAD $0x173b44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r11 + r15 + 23], 11 + QUAD $0x172344203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r11 + r12 + 23], 12 + QUAD $0x173344203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r11 + rsi + 23], 13 + QUAD $0x173b44203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r11 + rdi + 23], 14 + QUAD $0x171344203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r11 + r10 + 23], 15 + LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 + QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI1_15] */ + LONG $0xdddb0f66 // pand xmm3, xmm5 + LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 + LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 + LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI1_6] */ + LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 + LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 + QUAD $0x191b4c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r11 + rbx + 25], 3 + QUAD $0x19334c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r11 + r14 + 25], 4 + QUAD $0x192b4c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r11 + r13 + 25], 5 + QUAD $0x190b4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r11 + rcx + 25], 6 + QUAD $0x19134c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r11 + rdx + 25], 7 + QUAD $0x19034c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r11 + r8 + 25], 8 + QUAD $0x190b4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r11 + r9 + 25], 9 + QUAD $0x19034c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r11 + rax + 25], 10 + QUAD $0x193b4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r11 + r15 + 25], 11 + QUAD $0x19234c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r11 + r12 + 25], 12 + QUAD $0x19334c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r11 + rsi + 25], 13 + QUAD $0x193b4c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r11 + rdi + 25], 14 + QUAD $0x19134c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r11 + r10 + 25], 15 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 + LONG $0xd16f0f66 // movdqa xmm2, xmm1 + QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI1_10] */ + LONG $0xd3db0f66 // pand xmm2, xmm3 + LONG $0xd1f80f66 // psubb xmm2, xmm1 + QUAD $0x181b54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r11 + rbx + 24], 3 + QUAD $0x183354203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r11 + r14 + 24], 4 + QUAD $0x182b54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r11 + r13 + 24], 5 + QUAD $0x180b54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r11 + rcx + 24], 6 + QUAD $0x181354203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r11 + rdx + 24], 7 + QUAD $0x180354203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r11 + r8 + 24], 8 + QUAD $0x180b54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r11 + r9 + 24], 9 + QUAD $0x180354203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r11 + rax + 24], 10 + QUAD $0x183b54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r11 + r15 + 24], 11 + QUAD $0x182354203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r11 + r12 + 24], 12 + QUAD $0x183354203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r11 + rsi + 24], 13 + QUAD $0x183b54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r11 + rdi + 24], 14 + QUAD $0x181354203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r11 + r10 + 24], 15 + LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 + LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 + QUAD $0x1a1b5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r11 + rbx + 26], 3 + QUAD $0x1a335c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r11 + r14 + 26], 4 + QUAD $0x1a2b5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r11 + r13 + 26], 5 + QUAD $0x1a0b5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r11 + rcx + 26], 6 + QUAD $0x1a135c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r11 + rdx + 26], 7 + QUAD $0x1a035c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r11 + r8 + 26], 8 + QUAD $0x1a0b5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r11 + r9 + 26], 9 + QUAD $0x1a035c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r11 + rax + 26], 10 + QUAD $0x1a3b5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r11 + r15 + 26], 11 + QUAD $0x1a235c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r11 + r12 + 26], 12 + QUAD $0x1a335c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r11 + rsi + 26], 13 + QUAD $0x1a3b5c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r11 + rdi + 26], 14 + QUAD $0x1a135c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r11 + r10 + 26], 15 + LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 + QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 + LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 + QUAD $0x1b1b4c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r11 + rbx + 27], 3 + QUAD $0x1b334c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r11 + r14 + 27], 4 + QUAD $0x1b2b4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r11 + r13 + 27], 5 + QUAD $0x1b0b4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r11 + rcx + 27], 6 + QUAD $0x1b134c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r11 + rdx + 27], 7 + QUAD $0x1b034c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r11 + r8 + 27], 8 + QUAD $0x1b0b4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r11 + r9 + 27], 9 + QUAD $0x1b034c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r11 + rax + 27], 10 + QUAD $0x1b3b4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r11 + r15 + 27], 11 + QUAD $0x1b234c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r11 + r12 + 27], 12 + QUAD $0x1b334c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r11 + rsi + 27], 13 + QUAD $0x1b3b4c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r11 + rdi + 27], 14 + QUAD $0x1b134c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r11 + r10 + 27], 15 + QUAD $0x1c1b64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r11 + rbx + 28], 3 + QUAD $0x1c3364203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r11 + r14 + 28], 4 + QUAD $0x1c2b64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r11 + r13 + 28], 5 + QUAD $0x1c0b64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r11 + rcx + 28], 6 + QUAD $0x1c1364203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r11 + rdx + 28], 7 + QUAD $0x1c0364203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r11 + r8 + 28], 8 + QUAD $0x1c0b64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r11 + r9 + 28], 9 + QUAD $0x1c0364203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r11 + rax + 28], 10 + QUAD $0x1c3b64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r11 + r15 + 28], 11 + QUAD $0x1c2364203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r11 + r12 + 28], 12 + QUAD $0x1c3364203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r11 + rsi + 28], 13 + QUAD $0x1c3b64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r11 + rdi + 28], 14 + QUAD $0x1c1364203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r11 + r10 + 28], 15 + QUAD $0x1d1b6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r11 + rbx + 29], 3 + QUAD $0x1d336c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r11 + r14 + 29], 4 + QUAD $0x1d2b6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r11 + r13 + 29], 5 + QUAD $0x1d0b6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r11 + rcx + 29], 6 + QUAD $0x1d136c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r11 + rdx + 29], 7 + QUAD $0x1d036c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r11 + r8 + 29], 8 + QUAD $0x1d0b6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r11 + r9 + 29], 9 + QUAD $0x1d036c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r11 + rax + 29], 10 + QUAD $0x1d3b6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r11 + r15 + 29], 11 + QUAD $0x1d236c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r11 + r12 + 29], 12 + QUAD $0x1d336c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r11 + rsi + 29], 13 + QUAD $0x1d3b6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r11 + rdi + 29], 14 + LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 + LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 + QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 + QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 + QUAD $0x1d136c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r11 + r10 + 29], 15 + LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 + LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 + LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 + QUAD $0x1e1b64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r11 + rbx + 30], 3 + QUAD $0x1f1b44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r11 + rbx + 31], 3 + QUAD $0x1e3364203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r11 + r14 + 30], 4 + QUAD $0x1f3344203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r11 + r14 + 31], 4 + QUAD $0x1e2b64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r11 + r13 + 30], 5 + QUAD $0x1f2b44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r11 + r13 + 31], 5 + QUAD $0x1e0b64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r11 + rcx + 30], 6 + QUAD $0x1f0b44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r11 + rcx + 31], 6 + QUAD $0x1e1364203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r11 + rdx + 30], 7 + QUAD $0x1f1344203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r11 + rdx + 31], 7 + QUAD $0x1e0364203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r11 + r8 + 30], 8 + QUAD $0x1f0344203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r11 + r8 + 31], 8 + QUAD $0x1e0b64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r11 + r9 + 30], 9 + QUAD $0x1f0b44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r11 + r9 + 31], 9 + QUAD $0x1e0364203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r11 + rax + 30], 10 + QUAD $0x1f0344203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r11 + rax + 31], 10 + QUAD $0x1e3b64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r11 + r15 + 30], 11 + QUAD $0x1f3b44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r11 + r15 + 31], 11 + QUAD $0x1e2364203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r11 + r12 + 30], 12 + QUAD $0x1f2344203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r11 + r12 + 31], 12 + QUAD $0x1e3364203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r11 + rsi + 30], 13 + QUAD $0x1f3344203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r11 + rsi + 31], 13 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x1e3b64203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r11 + rdi + 30], 14 + QUAD $0x1f3b44203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r11 + rdi + 31], 14 + QUAD $0x1e1364203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r11 + r10 + 30], 15 + QUAD $0x1f1344203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r11 + r10 + 31], 15 + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 + LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 + LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0xc6db0f66 // pand xmm0, xmm6 + LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 + LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 + LONG $0xc8600f66 // punpcklbw xmm1, xmm0 + QUAD $0x0000d024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 208] + LONG $0xd46f0f66 // movdqa xmm2, xmm4 + LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 + LONG $0xda6f0f66 // movdqa xmm3, xmm2 + LONG $0xd9610f66 // punpcklwd xmm3, xmm1 + LONG $0xd1690f66 // punpckhwd xmm2, xmm1 + LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 + LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + LONG $0x647f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm4 + LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 + LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 + LONG $0x1c7f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm3 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x00000098248c3b48 // cmp rcx, qword [rsp + 152] + JNE LBB1_101 + QUAD $0x00000118248c8b48 // mov rcx, qword [rsp + 280] + QUAD $0x00000098248c3b48 // cmp rcx, qword [rsp + 152] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x24748a44; BYTE $0x08 // mov r14b, byte [rsp + 8] + QUAD $0x0000013024b48b48 // mov rsi, qword [rsp + 304] + JNE LBB1_103 + JMP LBB1_106 + +LBB1_73: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + QUAD $0x0000013024848948 // mov qword [rsp + 304], rax + QUAD $0x00000098248c8948 // mov qword [rsp + 152], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + LONG $0xc3b60f41 // movzx eax, r11b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 + WORD $0xc031 // xor eax, eax + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + +LBB1_74: + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + LONG $0x05e6c148 // shl rsi, 5 + LONG $0x24748948; BYTE $0x18 // mov qword [rsp + 24], rsi + WORD $0x8949; BYTE $0xf2 // mov r10, rsi + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + WORD $0x8949; BYTE $0xf5 // mov r13, rsi + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + WORD $0x8949; BYTE $0xf0 // mov r8, rsi + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x8949; BYTE $0xf1 // mov r9, rsi + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + LONG $0x24748948; BYTE $0x48 // mov qword [rsp + 72], rsi + LONG $0x0cb60f41; BYTE $0x36 // movzx ecx, byte [r14 + rsi] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x4cb60f41; WORD $0x0136 // movzx ecx, byte [r14 + rsi + 1] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x4cb60f41; WORD $0x0236 // movzx ecx, byte [r14 + rsi + 2] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x4cb60f41; WORD $0x0336 // movzx ecx, byte [r14 + rsi + 3] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x4cb60f41; WORD $0x0436 // movzx ecx, byte [r14 + rsi + 4] + LONG $0xc96e0f66 // movd xmm1, ecx + LONG $0x4cb60f41; WORD $0x0536 // movzx ecx, byte [r14 + rsi + 5] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x4cb60f41; WORD $0x0636 // movzx ecx, byte [r14 + rsi + 6] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x4cb60f41; WORD $0x0736 // movzx ecx, byte [r14 + rsi + 7] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 + LONG $0x4cb60f41; WORD $0x0836 // movzx ecx, byte [r14 + rsi + 8] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x00012024847f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm0 + LONG $0x4cb60f41; WORD $0x0936 // movzx ecx, byte [r14 + rsi + 9] + LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx + LONG $0x4cb60f41; WORD $0x0a36 // movzx ecx, byte [r14 + rsi + 10] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 + LONG $0x4cb60f41; WORD $0x0b36 // movzx ecx, byte [r14 + rsi + 11] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x4cb60f41; WORD $0x0c36 // movzx ecx, byte [r14 + rsi + 12] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x4cb60f41; WORD $0x0d36 // movzx ecx, byte [r14 + rsi + 13] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x4cb60f41; WORD $0x0e36 // movzx ecx, byte [r14 + rsi + 14] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 + LONG $0x24748948; BYTE $0x50 // mov qword [rsp + 80], rsi + WORD $0x8949; BYTE $0xf7 // mov r15, rsi + LONG $0x20cf8349 // or r15, 32 + LONG $0x247c894c; BYTE $0x30 // mov qword [rsp + 48], r15 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + LONG $0x40c88348 // or rax, 64 + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + LONG $0x60ca8349 // or r10, 96 + LONG $0x80cb8149; WORD $0x0000; BYTE $0x00 // or r11, 128 + LONG $0xa0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 160 + LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + LONG $0xe0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 224 + LONG $0x00cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 256 + LONG $0x247c8948; BYTE $0x20 // mov qword [rsp + 32], rdi + LONG $0x20c88149; WORD $0x0001; BYTE $0x00 // or r8, 288 + LONG $0x2444894c; BYTE $0x68 // mov qword [rsp + 104], r8 + LONG $0x40c98149; WORD $0x0001; BYTE $0x00 // or r9, 320 + QUAD $0x000000a0248c894c // mov qword [rsp + 160], r9 + LONG $0x60ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 352 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + LONG $0x80c98148; WORD $0x0001; BYTE $0x00 // or rcx, 384 + LONG $0x244c8948; BYTE $0x48 // mov qword [rsp + 72], rcx + LONG $0xa0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 416 + LONG $0x245c8948; BYTE $0x10 // mov qword [rsp + 16], rbx + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 + LONG $0x245c8948; BYTE $0x28 // mov qword [rsp + 40], rbx + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + LONG $0xe0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 480 + QUAD $0x013e3c203a0f4766 // pinsrb xmm15, byte [r14 + r15], 1 + QUAD $0x02063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 2 + LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 + QUAD $0x03163c203a0f4766 // pinsrb xmm15, byte [r14 + r10], 3 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + LONG $0x245c894c; BYTE $0x58 // mov qword [rsp + 88], r11 + QUAD $0x041e3c203a0f4766 // pinsrb xmm15, byte [r14 + r11], 4 + LONG $0x246c894c; BYTE $0x40 // mov qword [rsp + 64], r13 + QUAD $0x052e3c203a0f4766 // pinsrb xmm15, byte [r14 + r13], 5 + QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + QUAD $0x063e3c203a0f4766 // pinsrb xmm15, byte [r14 + r15], 6 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + QUAD $0x000000b024a4894c // mov qword [rsp + 176], r12 + QUAD $0x07263c203a0f4766 // pinsrb xmm15, byte [r14 + r12], 7 + QUAD $0x083e3c203a0f4566 // pinsrb xmm15, byte [r14 + rdi], 8 + QUAD $0x09063c203a0f4766 // pinsrb xmm15, byte [r14 + r8], 9 + QUAD $0x0a0e3c203a0f4766 // pinsrb xmm15, byte [r14 + r9], 10 + QUAD $0x0b163c203a0f4566 // pinsrb xmm15, byte [r14 + rdx], 11 + QUAD $0x0c0e3c203a0f4566 // pinsrb xmm15, byte [r14 + rcx], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 14 + QUAD $0x0f1e3c203a0f4566 // pinsrb xmm15, byte [r14 + rbx], 15 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x01266c203a0f4366; BYTE $0x01 // pinsrb xmm5, byte [r14 + r12 + 1], 1 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x01066c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rax + 1], 2 + QUAD $0x01166c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r10 + 1], 3 + QUAD $0x01366c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rsi + 1], 4 + QUAD $0x012e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r13 + 1], 5 + QUAD $0x013e6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r15 + 1], 6 + QUAD $0x011e6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r11 + 1], 7 + QUAD $0x013e6c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r14 + rdi + 1], 8 + QUAD $0x01066c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r8 + 1], 9 + QUAD $0x010e6c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r9 + 1], 10 + QUAD $0x01166c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r14 + rdx + 1], 11 + WORD $0x8949; BYTE $0xd4 // mov r12, rdx + LONG $0x24548948; BYTE $0x60 // mov qword [rsp + 96], rdx + QUAD $0x010e6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rcx + 1], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x01066c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rax + 1], 13 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x01066c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r14 + r8 + 1], 14 + QUAD $0x011e6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r14 + rbx + 1], 15 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x245c8948; BYTE $0x38 // mov qword [rsp + 56], rbx + QUAD $0x00d0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 208] + LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 + LONG $0xfd6f0f66 // movdqa xmm7, xmm5 + QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI1_10] */ + LONG $0xfcdb0f66 // pand xmm7, xmm4 + LONG $0xfdf80f66 // psubb xmm7, xmm5 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + LONG $0x54b60f41; WORD $0x0f06 // movzx edx, byte [r14 + rax + 15] + LONG $0x6e0f4466; BYTE $0xf2 // movd xmm14, edx + LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x023e74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rdi + 2], 1 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x023674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rsi + 2], 2 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x020e74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rcx + 2], 3 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x022e74203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r14 + r13 + 2], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x021674203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r14 + rdx + 2], 5 + QUAD $0x023e74203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r15 + 2], 6 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x023e74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r15 + 2], 7 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x021e74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r11 + 2], 8 + LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] + QUAD $0x021e74203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r14 + rbx + 2], 9 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x020e74203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r9 + 2], 10 + QUAD $0x022674203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r12 + 2], 11 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x021674203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rdx + 2], 12 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x022674203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r12 + 2], 13 + QUAD $0x020674203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r14 + r8 + 2], 14 + QUAD $0x021674203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r14 + r10 + 2], 15 + LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 + LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 + QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xf0db0f66 // pand xmm6, xmm0 + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x54b60f41; WORD $0x1006 // movzx edx, byte [r14 + rax + 16] + LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + QUAD $0x033e54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rdi + 3], 1 + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + QUAD $0x033654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rsi + 3], 2 + QUAD $0x030e54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rcx + 3], 3 + WORD $0x8949; BYTE $0xca // mov r10, rcx + QUAD $0x032e54203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r14 + r13 + 3], 4 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x031654203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r14 + rdx + 3], 5 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x030e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 3], 6 + WORD $0x894c; BYTE $0xfe // mov rsi, r15 + QUAD $0x033e54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r15 + 3], 7 + QUAD $0x031e54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r11 + 3], 8 + QUAD $0x031e54203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r14 + rbx + 3], 9 + QUAD $0x030e54203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r9 + 3], 10 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x031e54203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rbx + 3], 11 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x033e54203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r15 + 3], 12 + QUAD $0x032654203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r14 + r12 + 3], 13 + QUAD $0x030654203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r8 + 3], 14 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x030e54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r9 + 3], 15 + QUAD $0x04064c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rax + 4], 1 + QUAD $0x043e4c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rdi + 4], 2 + QUAD $0x04164c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r14 + r10 + 4], 3 + QUAD $0x042e4c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r14 + r13 + 4], 4 + QUAD $0x04164c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r14 + rdx + 4], 5 + QUAD $0x040e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 4], 6 + QUAD $0x04364c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r14 + rsi + 4], 7 + QUAD $0x041e4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r11 + 4], 8 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x04364c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r14 + rsi + 4], 9 + QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] + QUAD $0x043e4c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r14 + rdi + 4], 10 + QUAD $0x041e4c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r14 + rbx + 4], 11 + QUAD $0x043e4c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r15 + 4], 12 + QUAD $0x04264c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r14 + r12 + 4], 13 + QUAD $0x04064c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r14 + r8 + 4], 14 + QUAD $0x040e4c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r14 + r9 + 4], 15 + LONG $0xf7eb0f66 // por xmm6, xmm7 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + LONG $0x54b60f41; WORD $0x111e // movzx edx, byte [r14 + rbx + 17] + LONG $0xc26e0f66 // movd xmm0, edx + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0xd5db0f66 // pand xmm2, xmm5 + LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 + QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xcddb0f66 // pand xmm1, xmm5 + LONG $0xcaeb0f66 // por xmm1, xmm2 + LONG $0x54b60f41; WORD $0x121e // movzx edx, byte [r14 + rbx + 18] + LONG $0xea6e0f66 // movd xmm5, edx + QUAD $0x050644203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rax + 5], 1 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x050e44203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rcx + 5], 2 + WORD $0x894d; BYTE $0xd0 // mov r8, r10 + QUAD $0x051644203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r14 + r10 + 5], 3 + QUAD $0x052e44203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r14 + r13 + 5], 4 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x050e44203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r14 + rcx + 5], 5 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x051e44203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r14 + r11 + 5], 6 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x051644203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r14 + rdx + 5], 7 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x051644203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r14 + rdx + 5], 8 + QUAD $0x053644203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r14 + rsi + 5], 9 + QUAD $0x053e44203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rdi + 5], 10 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x051644203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rdx + 5], 11 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x051644203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rdx + 5], 12 + QUAD $0x052644203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r14 + r12 + 5], 13 + WORD $0x894d; BYTE $0xe2 // mov r10, r12 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x053e44203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rdi + 5], 14 + QUAD $0x050e44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r9 + 5], 15 + LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 + QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI1_14] */ + LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + LONG $0x54b60f41; WORD $0x131e // movzx edx, byte [r14 + rbx + 19] + LONG $0xfa6e0f66 // movd xmm7, edx + LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 + LONG $0x54b60f41; WORD $0x141e // movzx edx, byte [r14 + rbx + 20] + LONG $0xf26e0f66 // movd xmm6, edx + QUAD $0x06065c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rax + 6], 1 + WORD $0x8949; BYTE $0xc1 // mov r9, rax + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x062e5c203a0f4366; BYTE $0x02 // pinsrb xmm3, byte [r14 + r13 + 6], 2 + QUAD $0x06065c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r14 + r8 + 6], 3 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x06265c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r14 + r12 + 6], 4 + QUAD $0x060e5c203a0f4166; BYTE $0x05 // pinsrb xmm3, byte [r14 + rcx + 6], 5 + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + QUAD $0x061e5c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r14 + r11 + 6], 6 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x06365c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r14 + rsi + 6], 7 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x06065c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r14 + rax + 6], 8 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x06165c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r14 + rdx + 6], 9 + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x061e5c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r14 + r11 + 6], 10 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x061e5c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rbx + 6], 11 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x063e5c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r15 + 6], 12 + QUAD $0x06165c203a0f4366; BYTE $0x0d // pinsrb xmm3, byte [r14 + r10 + 6], 13 + QUAD $0x063e5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r14 + rdi + 6], 14 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x06165c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r14 + r10 + 6], 15 + QUAD $0x0000e024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 224] + QUAD $0x070e54203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r14 + r9 + 7], 1 + WORD $0x894c; BYTE $0xef // mov rdi, r13 + QUAD $0x072e54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r13 + 7], 2 + QUAD $0x070654203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r8 + 7], 3 + QUAD $0x072654203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r14 + r12 + 7], 4 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x070e54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r9 + 7], 5 + QUAD $0x070e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 7], 6 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + QUAD $0x073654203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rsi + 7], 7 + QUAD $0x070654203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r14 + rax + 7], 8 + QUAD $0x071654203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r14 + rdx + 7], 9 + QUAD $0x071e54203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r11 + 7], 10 + WORD $0x894d; BYTE $0xdd // mov r13, r11 + QUAD $0x071e54203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rbx + 7], 11 + QUAD $0x073e54203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r15 + 7], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x073654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rsi + 7], 13 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x070e54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rcx + 7], 14 + QUAD $0x071654203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r10 + 7], 15 + LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 + QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI1_15] */ + LONG $0xd9db0f66 // pand xmm3, xmm1 + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 + LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI1_6] */ + LONG $0xd1db0f66 // pand xmm2, xmm1 + LONG $0xd3eb0f66 // por xmm2, xmm3 + LONG $0xca6f0f66 // movdqa xmm1, xmm2 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + LONG $0x54b60f41; WORD $0x1506 // movzx edx, byte [r14 + rax + 21] + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x091654203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r10 + 9], 1 + QUAD $0x093e54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rdi + 9], 2 + QUAD $0x090654203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r14 + r8 + 9], 3 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x091e54203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r14 + rbx + 9], 4 + QUAD $0x090e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r9 + 9], 5 + QUAD $0x092654203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r12 + 9], 6 + QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] + QUAD $0x091e54203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r14 + r11 + 9], 7 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x091654203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rdx + 9], 8 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x091654203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r14 + rdx + 9], 9 + QUAD $0x092e54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r13 + 9], 10 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x092e54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r13 + 9], 11 + QUAD $0x093e54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r15 + 9], 12 + QUAD $0x093654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rsi + 9], 13 + QUAD $0x090e54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rcx + 9], 14 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x090e54203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rcx + 9], 15 + LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 + QUAD $0x0000e0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm1 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 + LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 + LONG $0xccdb0f66 // pand xmm1, xmm4 + LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 + LONG $0x54b60f41; WORD $0x1606 // movzx edx, byte [r14 + rax + 22] + LONG $0xda6e0f66 // movd xmm3, edx + QUAD $0x00012024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 288] + QUAD $0x081664203a0f4366; BYTE $0x01 // pinsrb xmm4, byte [r14 + r10 + 8], 1 + QUAD $0x083e64203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rdi + 8], 2 + QUAD $0x080664203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r14 + r8 + 8], 3 + QUAD $0x081e64203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rbx + 8], 4 + QUAD $0x080e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r9 + 8], 5 + QUAD $0x082664203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r14 + r12 + 8], 6 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + QUAD $0x081e64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r11 + 8], 7 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x080664203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r14 + rax + 8], 8 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x080e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r9 + 8], 9 + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + QUAD $0x081e64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r11 + 8], 10 + QUAD $0x082e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r13 + 8], 11 + QUAD $0x083e64203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r15 + 8], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x081664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 8], 13 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x083e64203a0f4366; BYTE $0x0e // pinsrb xmm4, byte [r14 + r15 + 8], 14 + QUAD $0x080e64203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r14 + rcx + 8], 15 + WORD $0x8948; BYTE $0xcb // mov rbx, rcx + LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 + LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 + QUAD $0x00c024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 192] + QUAD $0x0a1654203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r10 + 10], 1 + QUAD $0x0a3e54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rdi + 10], 2 + WORD $0x8949; BYTE $0xfa // mov r10, rdi + QUAD $0x0a0654203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r14 + r8 + 10], 3 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0a0654203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r8 + 10], 4 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0a0e54203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r14 + rcx + 10], 5 + QUAD $0x0a2654203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r12 + 10], 6 + QUAD $0x0a3654203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rsi + 10], 7 + QUAD $0x0a0654203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rax + 10], 8 + QUAD $0x0a0e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r9 + 10], 9 + QUAD $0x0a1e54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r11 + 10], 10 + QUAD $0x0a2e54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r13 + 10], 11 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x0a2e54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r13 + 10], 12 + QUAD $0x0a1654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rdx + 10], 13 + QUAD $0x0a3e54203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r14 + r15 + 10], 14 + QUAD $0x0a1e54203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rbx + 10], 15 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + LONG $0x54b60f41; WORD $0x1706 // movzx edx, byte [r14 + rax + 23] + LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + QUAD $0x00c024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 192], xmm10 + LONG $0x54b60f41; WORD $0x1806 // movzx edx, byte [r14 + rax + 24] + LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x0b3e5c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rdi + 11], 1 + QUAD $0x0b165c203a0f4766; BYTE $0x02 // pinsrb xmm11, byte [r14 + r10 + 11], 2 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0b165c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r14 + r10 + 11], 3 + QUAD $0x0b065c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r14 + r8 + 11], 4 + QUAD $0x0b0e5c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r14 + rcx + 11], 5 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + QUAD $0x0b265c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r12 + 11], 6 + QUAD $0x0b365c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rsi + 11], 7 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0b065c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r8 + 11], 8 + QUAD $0x0b0e5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r9 + 11], 9 + QUAD $0x0b1e5c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r14 + r11 + 11], 10 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x0b1e5c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r14 + rbx + 11], 11 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x0b2e5c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r13 + 11], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0b065c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rax + 11], 13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x0b265c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r12 + 11], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0b165c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r14 + rdx + 11], 15 + QUAD $0x0c3e6c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rdi + 12], 1 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x0c3e6c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rdi + 12], 2 + QUAD $0x0c166c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r14 + r10 + 12], 3 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0c2e6c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r14 + r13 + 12], 4 + LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] + QUAD $0x0c3e6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r14 + rdi + 12], 5 + QUAD $0x0c0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 12], 6 + QUAD $0x0c366c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r14 + rsi + 12], 7 + QUAD $0x0c066c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r8 + 12], 8 + QUAD $0x0c0e6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r9 + 12], 9 + QUAD $0x0c1e6c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r14 + r11 + 12], 10 + QUAD $0x0c1e6c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r14 + rbx + 12], 11 + QUAD $0x0c3e6c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r15 + 12], 12 + QUAD $0x0c066c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rax + 12], 13 + WORD $0x8949; BYTE $0xc2 // mov r10, rax + QUAD $0x0c266c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r14 + r12 + 12], 14 + QUAD $0x0c166c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r14 + rdx + 12], 15 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0d0664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rax + 13], 1 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0d1664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rdx + 13], 2 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0d1664203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rdx + 13], 3 + QUAD $0x0d2e64203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r14 + r13 + 13], 4 + QUAD $0x0d3e64203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r14 + rdi + 13], 5 + QUAD $0x0d0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 13], 6 + QUAD $0x0d3664203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r14 + rsi + 13], 7 + QUAD $0x0d0664203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r8 + 13], 8 + QUAD $0x0d0e64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r9 + 13], 9 + QUAD $0x0d1e64203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r14 + r11 + 13], 10 + QUAD $0x0d1e64203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r14 + rbx + 13], 11 + QUAD $0x0d3e64203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r15 + 13], 12 + QUAD $0x0d1664203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r14 + r10 + 13], 13 + QUAD $0x0d2664203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r14 + r12 + 13], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0d1664203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r14 + rdx + 13], 15 + LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 + QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 + QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] + LONG $0x54b60f41; WORD $0x193e // movzx edx, byte [r14 + rdi + 25] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 + QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI1_14] */ + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x54b60f41; WORD $0x1a3e // movzx edx, byte [r14 + rdi + 26] + LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx + QUAD $0x0000f024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 240] + QUAD $0x0e0664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rax + 14], 1 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x0e2664203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r14 + r12 + 14], 2 + LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] + QUAD $0x0e3e64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdi + 14], 3 + WORD $0x894d; BYTE $0xea // mov r10, r13 + QUAD $0x0e2e64203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r13 + 14], 4 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e0664203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r14 + rax + 14], 5 + QUAD $0x0e0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 14], 6 + QUAD $0x0e3664203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r14 + rsi + 14], 7 + QUAD $0x0e0664203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r8 + 14], 8 + QUAD $0x0e0e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r9 + 14], 9 + QUAD $0x0e1e64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r11 + 14], 10 + QUAD $0x0e1e64203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r14 + rbx + 14], 11 + QUAD $0x0e3e64203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r15 + 14], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0e1664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 14], 13 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x0e2e64203a0f4366; BYTE $0x0e // pinsrb xmm4, byte [r14 + r13 + 14], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0e1664203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r14 + rdx + 14], 15 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0f1674203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r14 + rdx + 15], 1 + QUAD $0x0f2674203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r14 + r12 + 15], 2 + QUAD $0x0f3e74203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r14 + rdi + 15], 3 + QUAD $0x0f1674203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r14 + r10 + 15], 4 + QUAD $0x0f0674203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r14 + rax + 15], 5 + QUAD $0x0f0e74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r14 + rcx + 15], 6 + QUAD $0x0f3674203a0f4566; BYTE $0x07 // pinsrb xmm14, byte [r14 + rsi + 15], 7 + QUAD $0x0f0674203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r14 + r8 + 15], 8 + QUAD $0x0f0e74203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r14 + r9 + 15], 9 + QUAD $0x0f1e74203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r14 + r11 + 15], 10 + QUAD $0x0f1e74203a0f4566; BYTE $0x0b // pinsrb xmm14, byte [r14 + rbx + 15], 11 + QUAD $0x0f3e74203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r14 + r15 + 15], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0f1674203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r14 + rdx + 15], 13 + QUAD $0x0f2e74203a0f4766; BYTE $0x0e // pinsrb xmm14, byte [r14 + r13 + 15], 14 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0f1674203a0f4566; BYTE $0x0f // pinsrb xmm14, byte [r14 + rdx + 15], 15 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x10167c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rdx + 16], 1 + QUAD $0x10267c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r14 + r12 + 16], 2 + QUAD $0x103e7c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r14 + rdi + 16], 3 + QUAD $0x10167c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r14 + r10 + 16], 4 + QUAD $0x10067c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r14 + rax + 16], 5 + QUAD $0x100e7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r14 + rcx + 16], 6 + QUAD $0x10367c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r14 + rsi + 16], 7 + QUAD $0x10067c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r8 + 16], 8 + QUAD $0x100e7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r14 + r9 + 16], 9 + QUAD $0x101e7c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r14 + r11 + 16], 10 + QUAD $0x101e7c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r14 + rbx + 16], 11 + QUAD $0x103e7c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r14 + r15 + 16], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x10167c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r14 + rdx + 16], 13 + QUAD $0x102e7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r14 + r13 + 16], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x111644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rdx + 17], 1 + QUAD $0x112644203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r14 + r12 + 17], 2 + QUAD $0x113e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdi + 17], 3 + QUAD $0x111644203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r10 + 17], 4 + QUAD $0x110644203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rax + 17], 5 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x110e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 17], 6 + QUAD $0x113644203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r14 + rsi + 17], 7 + QUAD $0x110644203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r8 + 17], 8 + QUAD $0x110e44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r9 + 17], 9 + QUAD $0x111e44203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r11 + 17], 10 + QUAD $0x111e44203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r14 + rbx + 17], 11 + QUAD $0x113e44203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r15 + 17], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x110644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rax + 17], 13 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x111644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rdx + 17], 14 + QUAD $0x00c024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 192] + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + LONG $0x54b60f43; WORD $0x1b26 // movzx edx, byte [r14 + r12 + 27] + LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx + QUAD $0x00d024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 208] + LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 + QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI1_15] */ + LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 + LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 + LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI1_6] */ + LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 + LONG $0x54b60f43; WORD $0x1c26 // movzx edx, byte [r14 + r12 + 28] + LONG $0xe26e0f66 // movd xmm4, edx + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + QUAD $0x110644203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r8 + 17], 15 + LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 + LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 + LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 + QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI1_10] */ + LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 + LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 + QUAD $0x00c024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 192], xmm13 + LONG $0x54b60f43; WORD $0x1d26 // movzx edx, byte [r14 + r12 + 29] + LONG $0x6e0f4466; BYTE $0xea // movd xmm13, edx + QUAD $0x10067c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r14 + r8 + 16], 15 + QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] + LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x12266c203a0f4366; BYTE $0x01 // pinsrb xmm5, byte [r14 + r12 + 18], 1 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x12166c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rdx + 18], 2 + QUAD $0x123e6c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r14 + rdi + 18], 3 + QUAD $0x12166c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r14 + r10 + 18], 4 + QUAD $0x122e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r13 + 18], 5 + QUAD $0x120e6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r14 + rcx + 18], 6 + QUAD $0x12366c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r14 + rsi + 18], 7 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x12166c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r14 + rdx + 18], 8 + QUAD $0x120e6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r9 + 18], 9 + QUAD $0x121e6c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r11 + 18], 10 + QUAD $0x121e6c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r14 + rbx + 18], 11 + QUAD $0x123e6c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r14 + r15 + 18], 12 + QUAD $0x12066c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rax + 18], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x12066c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rax + 18], 14 + LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 + QUAD $0x12066c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r8 + 18], 15 + LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 + QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + LONG $0x54b60f41; WORD $0x1e06 // movzx edx, byte [r14 + rax + 30] + LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx + QUAD $0x13267c203a0f4366; BYTE $0x01 // pinsrb xmm7, byte [r14 + r12 + 19], 1 + QUAD $0x142674203a0f4366; BYTE $0x01 // pinsrb xmm6, byte [r14 + r12 + 20], 1 + QUAD $0x152654203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r14 + r12 + 21], 1 + QUAD $0x16265c203a0f4366; BYTE $0x01 // pinsrb xmm3, byte [r14 + r12 + 22], 1 + QUAD $0x172644203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r14 + r12 + 23], 1 + QUAD $0x182654203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r12 + 24], 1 + QUAD $0x19264c203a0f4366; BYTE $0x01 // pinsrb xmm1, byte [r14 + r12 + 25], 1 + QUAD $0x1a265c203a0f4766; BYTE $0x01 // pinsrb xmm11, byte [r14 + r12 + 26], 1 + QUAD $0x1b264c203a0f4766; BYTE $0x01 // pinsrb xmm9, byte [r14 + r12 + 27], 1 + QUAD $0x1c2664203a0f4366; BYTE $0x01 // pinsrb xmm4, byte [r14 + r12 + 28], 1 + QUAD $0x1d266c203a0f4766; BYTE $0x01 // pinsrb xmm13, byte [r14 + r12 + 29], 1 + QUAD $0x1e2664203a0f4766; BYTE $0x01 // pinsrb xmm12, byte [r14 + r12 + 30], 1 + LONG $0x54b60f41; WORD $0x1f06 // movzx edx, byte [r14 + rax + 31] + LONG $0xc26e0f66 // movd xmm0, edx + QUAD $0x1f2644203a0f4366; BYTE $0x01 // pinsrb xmm0, byte [r14 + r12 + 31], 1 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x13167c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rdx + 19], 2 + QUAD $0x141674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rdx + 20], 2 + QUAD $0x151654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rdx + 21], 2 + QUAD $0x16165c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rdx + 22], 2 + QUAD $0x171644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rdx + 23], 2 + QUAD $0x181654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rdx + 24], 2 + QUAD $0x19164c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rdx + 25], 2 + QUAD $0x1a165c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rdx + 26], 2 + QUAD $0x1b164c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rdx + 27], 2 + QUAD $0x1c1664203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rdx + 28], 2 + QUAD $0x1d166c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rdx + 29], 2 + QUAD $0x1e1664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rdx + 30], 2 + QUAD $0x1f1644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rdx + 31], 2 + QUAD $0x133e7c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r14 + rdi + 19], 3 + QUAD $0x13167c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r14 + r10 + 19], 4 + QUAD $0x132e7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r13 + 19], 5 + QUAD $0x130e7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r14 + rcx + 19], 6 + QUAD $0x13367c203a0f4166; BYTE $0x07 // pinsrb xmm7, byte [r14 + rsi + 19], 7 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x13267c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r12 + 19], 8 + QUAD $0x130e7c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r9 + 19], 9 + QUAD $0x131e7c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r14 + r11 + 19], 10 + QUAD $0x131e7c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r14 + rbx + 19], 11 + QUAD $0x133e7c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r14 + r15 + 19], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x13167c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rdx + 19], 13 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x13067c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r14 + rax + 19], 14 + QUAD $0x13067c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r14 + r8 + 19], 15 + QUAD $0x143e74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rdi + 20], 3 + QUAD $0x141674203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r14 + r10 + 20], 4 + QUAD $0x142e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r13 + 20], 5 + QUAD $0x140e74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rcx + 20], 6 + QUAD $0x143674203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r14 + rsi + 20], 7 + QUAD $0x142674203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r12 + 20], 8 + QUAD $0x140e74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r9 + 20], 9 + QUAD $0x141e74203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r11 + 20], 10 + QUAD $0x141e74203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r14 + rbx + 20], 11 + QUAD $0x143e74203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r15 + 20], 12 + QUAD $0x141674203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r14 + rdx + 20], 13 + QUAD $0x140674203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rax + 20], 14 + QUAD $0x0000c024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 192] + QUAD $0x140674203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r14 + r8 + 20], 15 + QUAD $0x00d024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 208] + LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 + QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 + QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xf7eb0f66 // por xmm6, xmm7 + QUAD $0x153e54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdi + 21], 3 + QUAD $0x151654203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r14 + r10 + 21], 4 + QUAD $0x152e54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r13 + 21], 5 + QUAD $0x150e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 21], 6 + QUAD $0x153654203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rsi + 21], 7 + QUAD $0x152654203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r12 + 21], 8 + QUAD $0x150e54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r9 + 21], 9 + QUAD $0x151e54203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r11 + 21], 10 + QUAD $0x151e54203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rbx + 21], 11 + QUAD $0x153e54203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r15 + 21], 12 + QUAD $0x151654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rdx + 21], 13 + QUAD $0x150654203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rax + 21], 14 + QUAD $0x150654203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r8 + 21], 15 + LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 + QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI1_14] */ + LONG $0xd7db0f66 // pand xmm2, xmm7 + LONG $0xd6eb0f66 // por xmm2, xmm6 + LONG $0xd5eb0f66 // por xmm2, xmm5 + QUAD $0x163e5c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r14 + rdi + 22], 3 + QUAD $0x16165c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r14 + r10 + 22], 4 + QUAD $0x162e5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r13 + 22], 5 + QUAD $0x160e5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r14 + rcx + 22], 6 + QUAD $0x16365c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r14 + rsi + 22], 7 + QUAD $0x16265c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r12 + 22], 8 + QUAD $0x160e5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r9 + 22], 9 + QUAD $0x161e5c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r14 + r11 + 22], 10 + QUAD $0x161e5c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rbx + 22], 11 + QUAD $0x163e5c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r15 + 22], 12 + QUAD $0x16165c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rdx + 22], 13 + QUAD $0x16065c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r14 + rax + 22], 14 + QUAD $0x16065c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r14 + r8 + 22], 15 + QUAD $0x173e44203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rdi + 23], 3 + QUAD $0x171644203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r14 + r10 + 23], 4 + QUAD $0x172e44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r13 + 23], 5 + QUAD $0x170e44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r14 + rcx + 23], 6 + QUAD $0x173644203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r14 + rsi + 23], 7 + QUAD $0x172644203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r12 + 23], 8 + QUAD $0x170e44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r9 + 23], 9 + QUAD $0x171e44203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r14 + r11 + 23], 10 + QUAD $0x171e44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rbx + 23], 11 + QUAD $0x173e44203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r14 + r15 + 23], 12 + QUAD $0x171644203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rdx + 23], 13 + QUAD $0x170644203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rax + 23], 14 + QUAD $0x170644203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r8 + 23], 15 + LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 + QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI1_15] */ + LONG $0xdddb0f66 // pand xmm3, xmm5 + LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 + LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 + LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI1_6] */ + LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 + LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 + QUAD $0x193e4c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r14 + rdi + 25], 3 + QUAD $0x19164c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r14 + r10 + 25], 4 + QUAD $0x192e4c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r14 + r13 + 25], 5 + QUAD $0x190e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 25], 6 + QUAD $0x19364c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r14 + rsi + 25], 7 + QUAD $0x19264c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r12 + 25], 8 + QUAD $0x190e4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r9 + 25], 9 + QUAD $0x191e4c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r14 + r11 + 25], 10 + QUAD $0x191e4c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r14 + rbx + 25], 11 + QUAD $0x193e4c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r15 + 25], 12 + QUAD $0x19164c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r14 + rdx + 25], 13 + QUAD $0x19064c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r14 + rax + 25], 14 + QUAD $0x19064c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r14 + r8 + 25], 15 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 + LONG $0xd16f0f66 // movdqa xmm2, xmm1 + QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI1_10] */ + LONG $0xd3db0f66 // pand xmm2, xmm3 + LONG $0xd1f80f66 // psubb xmm2, xmm1 + QUAD $0x183e54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rdi + 24], 3 + QUAD $0x181654203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r10 + 24], 4 + QUAD $0x182e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r13 + 24], 5 + QUAD $0x180e54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r14 + rcx + 24], 6 + QUAD $0x183654203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rsi + 24], 7 + QUAD $0x182654203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r14 + r12 + 24], 8 + QUAD $0x180e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r9 + 24], 9 + QUAD $0x181e54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r11 + 24], 10 + QUAD $0x181e54203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r14 + rbx + 24], 11 + QUAD $0x183e54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r15 + 24], 12 + QUAD $0x181654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rdx + 24], 13 + QUAD $0x180654203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rax + 24], 14 + QUAD $0x180654203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r8 + 24], 15 + LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 + LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 + QUAD $0x1a3e5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r14 + rdi + 26], 3 + QUAD $0x1a165c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r14 + r10 + 26], 4 + QUAD $0x1a2e5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r13 + 26], 5 + QUAD $0x1a0e5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r14 + rcx + 26], 6 + QUAD $0x1a365c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rsi + 26], 7 + QUAD $0x1a265c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r12 + 26], 8 + QUAD $0x1a0e5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r9 + 26], 9 + QUAD $0x1a1e5c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r14 + r11 + 26], 10 + QUAD $0x1a1e5c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r14 + rbx + 26], 11 + QUAD $0x1a3e5c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r15 + 26], 12 + QUAD $0x1a165c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rdx + 26], 13 + QUAD $0x1a065c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r14 + rax + 26], 14 + QUAD $0x1a065c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r8 + 26], 15 + LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 + QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI1_11] */ + LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 + LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 + QUAD $0x1b3e4c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r14 + rdi + 27], 3 + QUAD $0x1b164c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r14 + r10 + 27], 4 + QUAD $0x1b2e4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r13 + 27], 5 + QUAD $0x1b0e4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r14 + rcx + 27], 6 + QUAD $0x1b364c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r14 + rsi + 27], 7 + QUAD $0x1b264c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r12 + 27], 8 + QUAD $0x1b0e4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r14 + r9 + 27], 9 + QUAD $0x1b1e4c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r14 + r11 + 27], 10 + QUAD $0x1b1e4c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rbx + 27], 11 + QUAD $0x1b3e4c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r14 + r15 + 27], 12 + QUAD $0x1b164c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r14 + rdx + 27], 13 + QUAD $0x1b064c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rax + 27], 14 + QUAD $0x1b064c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r14 + r8 + 27], 15 + QUAD $0x1c3e64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdi + 28], 3 + QUAD $0x1c1664203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r10 + 28], 4 + QUAD $0x1c2e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r13 + 28], 5 + QUAD $0x1c0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 28], 6 + QUAD $0x1c3664203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r14 + rsi + 28], 7 + QUAD $0x1c2664203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r12 + 28], 8 + QUAD $0x1c0e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r9 + 28], 9 + QUAD $0x1c1e64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r11 + 28], 10 + QUAD $0x1c1e64203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r14 + rbx + 28], 11 + QUAD $0x1c3e64203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r15 + 28], 12 + QUAD $0x1c1664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 28], 13 + QUAD $0x1c0664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rax + 28], 14 + QUAD $0x1c0664203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r8 + 28], 15 + QUAD $0x1d3e6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r14 + rdi + 29], 3 + QUAD $0x1d166c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r14 + r10 + 29], 4 + QUAD $0x1d2e6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r14 + r13 + 29], 5 + QUAD $0x1d0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 29], 6 + QUAD $0x1d366c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r14 + rsi + 29], 7 + QUAD $0x1d266c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r12 + 29], 8 + QUAD $0x1d0e6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r9 + 29], 9 + QUAD $0x1d1e6c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r14 + r11 + 29], 10 + QUAD $0x1d1e6c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r14 + rbx + 29], 11 + QUAD $0x1d3e6c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r15 + 29], 12 + QUAD $0x1d166c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rdx + 29], 13 + QUAD $0x1d066c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r14 + rax + 29], 14 + LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 + LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 + QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI1_12] */ + LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 + QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI1_13] */ + LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 + QUAD $0x1d066c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r14 + r8 + 29], 15 + LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 + LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 + LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 + QUAD $0x1e3e64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rdi + 30], 3 + QUAD $0x1f3e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdi + 31], 3 + QUAD $0x1e1664203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r14 + r10 + 30], 4 + QUAD $0x1f1644203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r10 + 31], 4 + QUAD $0x1e2e64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r14 + r13 + 30], 5 + QUAD $0x1f2e44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r13 + 31], 5 + QUAD $0x1e0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 30], 6 + QUAD $0x1f0e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 31], 6 + QUAD $0x1e3664203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r14 + rsi + 30], 7 + QUAD $0x1f3644203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r14 + rsi + 31], 7 + QUAD $0x1e2664203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r12 + 30], 8 + QUAD $0x1f2644203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r12 + 31], 8 + QUAD $0x1e0e64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r9 + 30], 9 + QUAD $0x1f0e44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r9 + 31], 9 + QUAD $0x1e1e64203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r14 + r11 + 30], 10 + QUAD $0x1f1e44203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r11 + 31], 10 + QUAD $0x1e1e64203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r14 + rbx + 30], 11 + QUAD $0x1f1e44203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r14 + rbx + 31], 11 + QUAD $0x1e3e64203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r15 + 30], 12 + QUAD $0x1f3e44203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r15 + 31], 12 + QUAD $0x1e1664203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rdx + 30], 13 + QUAD $0x1f1644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rdx + 31], 13 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x1e0664203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r14 + rax + 30], 14 + QUAD $0x1f0644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rax + 31], 14 + QUAD $0x1e0664203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r14 + r8 + 30], 15 + QUAD $0x1f0644203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r8 + 31], 15 + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 + LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 + LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0xc6db0f66 // pand xmm0, xmm6 + LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 + LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 + LONG $0xc8600f66 // punpcklbw xmm1, xmm0 + QUAD $0x0000e024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 224] + LONG $0xd46f0f66 // movdqa xmm2, xmm4 + LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 + LONG $0xda6f0f66 // movdqa xmm3, xmm2 + LONG $0xd9610f66 // punpcklwd xmm3, xmm1 + LONG $0xd1690f66 // punpckhwd xmm2, xmm1 + LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 + LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x647f0ff3; WORD $0x308a // movdqu oword [rdx + 4*rcx + 48], xmm4 + LONG $0x447f0ff3; WORD $0x208a // movdqu oword [rdx + 4*rcx + 32], xmm0 + LONG $0x547f0ff3; WORD $0x108a // movdqu oword [rdx + 4*rcx + 16], xmm2 + LONG $0x1c7f0ff3; BYTE $0x8a // movdqu oword [rdx + 4*rcx], xmm3 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x00000098248c3b48 // cmp rcx, qword [rsp + 152] + JNE LBB1_74 + QUAD $0x00000118248c8b48 // mov rcx, qword [rsp + 280] + QUAD $0x00000098248c3b48 // cmp rcx, qword [rsp + 152] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x245c8a44; BYTE $0x08 // mov r11b, byte [rsp + 8] + QUAD $0x0000013024b48b48 // mov rsi, qword [rsp + 304] + JNE LBB1_76 + JMP LBB1_79 DATA LCDATA2<>+0x000(SB)/8, $0x0000000001010101 DATA LCDATA2<>+0x008(SB)/8, $0x0000000000000000 @@ -9371,194 +9638,208 @@ TEXT ·_comparison_equal_scalar_arr_sse4(SB), $328-48 MOVQ BP, 304(SP) LEAQ LCDATA2<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0x240c8948 // mov qword [rsp], rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB2_17 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB2_32 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB2_83 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB2_95 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB2_177 - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] - -LBB2_7: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x31 // movzx r8d, byte [r9 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x313c8841 // mov byte [r9 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_7 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB2_19 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB2_36 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB2_59 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB2_73 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB2_200 + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB2_11 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_9 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_8: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001be; BYTE $0x00 // mov esi, 1 + WORD $0xe6d3 // shl esi, cl + WORD $0x2040; BYTE $0xde // and sil, bl + WORD $0x3044; BYTE $0xce // xor sil, r9b + LONG $0x04348841 // mov byte [r12 + rax], sil + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_8 LBB2_9: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_13 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 LBB2_11: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_15 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB2_13: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - QUAD $0x000000c02494940f // sete byte [rsp + 192] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] - LONG $0xd2940f41 // sete r10b + LONG $0xd1940f41 // sete r9b LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] LONG $0xd6940f41 // sete r14b LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] - QUAD $0x000000a02494940f // sete byte [rsp + 160] + QUAD $0x000000c02494940f // sete byte [rsp + 192] LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] - WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x940f; BYTE $0xd0 // sete al LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] - LONG $0xd7940f40 // sete dil + LONG $0xd3940f41 // sete r11b LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] - QUAD $0x000000d02494940f // sete byte [rsp + 208] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] LONG $0xd6940f40 // sete sil LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] - LONG $0xd1940f41 // sete r9b + LONG $0xd0940f41 // sete r8b LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] - LONG $0xd3940f41 // sete r11b + LONG $0xd2940f41 // sete r10b LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] LONG $0xd4940f41 // sete r12b LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] QUAD $0x000000b02494940f // sete byte [rsp + 176] LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] LONG $0xd7940f41 // sete r15b LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2414940f // sete byte [rsp] LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000c024940244 // add r10b, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xdf // or dil, bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000088248c0244 // add r9b, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0845; BYTE $0xce // or r14b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000d024b40240 // add sil, byte [rsp + 208] - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - WORD $0x8941; BYTE $0xda // mov r10d, ebx - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xd3 // or bl, r10b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc1 // mov r9d, eax + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xc8 // or al, r9b + WORD $0xc689 // mov esi, eax + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x24348b48 // mov rsi, qword [rsp] - QUAD $0x0000b02484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 176] - LONG $0x06e0c041 // shl r8b, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0844; BYTE $0xc0 // or al, r8b - WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xdb00 // add bl, bl - LONG $0x48245c02 // add bl, byte [rsp + 72] - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8840; BYTE $0x3e // mov byte [rsi], dil - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + LONG $0x06e6c040 // shl sil, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe3 // or bl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x58244402 // add al, byte [rsp + 88] + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4688; BYTE $0x01 // mov byte [rsi + 1], al - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x245c8841; BYTE $0x01 // mov byte [r12 + 1], bl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] + LONG $0x20244402 // add al, byte [rsp + 32] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax @@ -9566,49 +9847,47 @@ LBB2_11: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x241cb60f // movzx ebx, byte [rsp] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x4e88; BYTE $0x03 // mov byte [rsi + 3], cl + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68348 // add rsi, 4 - LONG $0x24348948 // mov qword [rsp], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_11 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB2_13 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB2_13: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB2_82 +LBB2_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB2_131 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi - LONG $0x241c8b4c // mov r11, qword [rsp] -LBB2_16: +LBB2_18: WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -9616,7 +9895,7 @@ LBB2_16: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x331c8841 // mov byte [r11 + rsi], bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] LONG $0x08528d48 // lea rdx, [rdx + 8] @@ -9628,68 +9907,85 @@ LBB2_16: WORD $0xe0d2 // shl al, cl WORD $0x2044; BYTE $0xc8 // and al, r9b WORD $0xd830 // xor al, bl - LONG $0x33048841 // mov byte [r11 + rsi], al + LONG $0x34048841 // mov byte [r12 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_16 - JMP LBB2_153 - -LBB2_17: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB2_46 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB2_107 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB2_118 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB2_177 - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_25 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x241c8b4c // mov r11, qword [rsp] + JNE LBB2_18 + JMP LBB2_177 -LBB2_23: - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] +LBB2_19: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB2_43 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB2_87 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB2_100 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB2_200 + WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_29 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_27 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_26: + LONG $0x012e0f66 // ucomisd xmm0, qword [rcx] + LONG $0x08518d48 // lea rdx, [rcx + 8] WORD $0x9b0f; BYTE $0xd1 // setnp cl WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xcb20 // and bl, cl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_23 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB2_25: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_29 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 - QUAD $0x0000009824b4894c // mov qword [rsp + 152], r14 + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_26 LBB2_27: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 + +LBB2_29: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_33 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x0000010024b4894c // mov qword [rsp + 256], r14 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + QUAD $0x000000d824848948 // mov qword [rsp + 216], rax + QUAD $0x0000011024848948 // mov qword [rsp + 272], rax + +LBB2_31: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -9697,26 +9993,27 @@ LBB2_27: LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xc320 // and bl, al - LONG $0x422e0f66; BYTE $0x10 // ucomisd xmm0, qword [rdx + 16] - WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd5940f41 // sete r13b WORD $0x2041; BYTE $0xc5 // and r13b, al + LONG $0x422e0f66; BYTE $0x10 // ucomisd xmm0, qword [rdx + 16] + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0x28244c88 // mov byte [rsp + 40], cl LONG $0x422e0f66; BYTE $0x18 // ucomisd xmm0, qword [rdx + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x08244c88 // mov byte [rsp + 8], cl LONG $0x422e0f66; BYTE $0x20 // ucomisd xmm0, qword [rdx + 32] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x422e0f66; BYTE $0x28 // ucomisd xmm0, qword [rdx + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd7940f40 // sete dil - WORD $0x2040; BYTE $0xc7 // and dil, al + LONG $0xd4940f41 // sete r12b + WORD $0x2041; BYTE $0xc4 // and r12b, al LONG $0x422e0f66; BYTE $0x30 // ucomisd xmm0, qword [rdx + 48] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -9726,17 +10023,17 @@ LBB2_27: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + WORD $0x0c88; BYTE $0x24 // mov byte [rsp], cl LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x422e0f66; BYTE $0x48 // ucomisd xmm0, qword [rdx + 72] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x422e0f66; BYTE $0x50 // ucomisd xmm0, qword [rdx + 80] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -9744,44 +10041,43 @@ LBB2_27: LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x422e0f66; BYTE $0x58 // ucomisd xmm0, qword [rdx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0xc120 // and cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xc320 // and bl, al LONG $0x422e0f66; BYTE $0x60 // ucomisd xmm0, qword [rdx + 96] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl LONG $0x422e0f66; BYTE $0x68 // ucomisd xmm0, qword [rdx + 104] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x58244c88 // mov byte [rsp + 88], cl LONG $0x422e0f66; BYTE $0x70 // ucomisd xmm0, qword [rdx + 112] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x422e0f66; BYTE $0x78 // ucomisd xmm0, qword [rdx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl QUAD $0x00000080822e0f66 // ucomisd xmm0, qword [rdx + 128] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl QUAD $0x00000088822e0f66 // ucomisd xmm0, qword [rdx + 136] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl QUAD $0x00000090822e0f66 // ucomisd xmm0, qword [rdx + 144] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl QUAD $0x00000098822e0f66 // ucomisd xmm0, qword [rdx + 152] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -9791,593 +10087,406 @@ LBB2_27: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl QUAD $0x000000a8822e0f66 // ucomisd xmm0, qword [rdx + 168] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl QUAD $0x000000b0822e0f66 // ucomisd xmm0, qword [rdx + 176] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd7940f41 // sete r15b WORD $0x2041; BYTE $0xc7 // and r15b, al QUAD $0x000000b8822e0f66 // ucomisd xmm0, qword [rdx + 184] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd1940f41 // sete r9b - WORD $0x2041; BYTE $0xc1 // and r9b, al + LONG $0xd0940f41 // sete r8b + WORD $0x2041; BYTE $0xc0 // and r8b, al QUAD $0x000000c0822e0f66 // ucomisd xmm0, qword [rdx + 192] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl QUAD $0x000000c8822e0f66 // ucomisd xmm0, qword [rdx + 200] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd6940f41 // sete r14b - WORD $0x2041; BYTE $0xc6 // and r14b, al - QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] - WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd3940f41 // sete r11b WORD $0x2041; BYTE $0xc3 // and r11b, al - QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] + QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd2940f41 // sete r10b WORD $0x2041; BYTE $0xc2 // and r10b, al + QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] + WORD $0x9b0f; BYTE $0xd0 // setnp al + LONG $0xd1940f41 // sete r9b + WORD $0x2041; BYTE $0xc1 // and r9b, al QUAD $0x000000e0822e0f66 // ucomisd xmm0, qword [rdx + 224] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd4940f41 // sete r12b - WORD $0x2041; BYTE $0xc4 // and r12b, al + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0xc120 // and cl, al + LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl QUAD $0x000000f0822e0f66 // ucomisd xmm0, qword [rdx + 240] WORD $0x9b0f; BYTE $0xd0 // setnp al - LONG $0xd0940f41 // sete r8b - WORD $0x2041; BYTE $0xc0 // and r8b, al + LONG $0xd7940f40 // sete dil + WORD $0x2040; BYTE $0xc7 // and dil, al QUAD $0x000000f8822e0f66 // ucomisd xmm0, qword [rdx + 248] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd6940f40 // sete sil WORD $0x2040; BYTE $0xc6 // and sil, al - WORD $0xdb00 // add bl, bl - LONG $0x18245c02 // add bl, byte [rsp + 24] - LONG $0x05e7c040 // shl dil, 5 - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x18 // add r13b, byte [rsp + 24] + WORD $0x8944; BYTE $0xe8 // mov eax, r13d + LONG $0x05e4c041 // shl r12b, 5 + LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] + LONG $0x06e5c041 // shl r13b, 6 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + LONG $0x64b60f44; WORD $0x2824 // movzx r12d, byte [rsp + 40] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xc900 // add cl, cl + LONG $0x30244c02 // add cl, byte [rsp + 48] + LONG $0x2404b60f // movzx eax, byte [rsp] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x08244488 // mov byte [rsp + 8], al + WORD $0x0844; BYTE $0xe8 // or al, r13b + WORD $0x0488; BYTE $0x24 // mov byte [rsp], al LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0xcb08 // or bl, cl + LONG $0x6cb60f44; WORD $0x2024 // movzx r13d, byte [rsp + 32] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0841; BYTE $0xc5 // or r13b, al LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x247cb60f; BYTE $0x48 // movzx edi, byte [rsp + 72] - LONG $0x05e7c040 // shl dil, 5 - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x6cb60f44; WORD $0x7024 // movzx r13d, byte [rsp + 112] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xcd // or r13b, cl - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + WORD $0xd808 // or al, bl + LONG $0x10244488 // mov byte [rsp + 16], al + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x74b60f44; WORD $0x7824 // movzx r14d, byte [rsp + 120] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xc900 // add cl, cl - LONG $0x50244c02 // add cl, byte [rsp + 80] - LONG $0x247cb60f; BYTE $0x78 // movzx edi, byte [rsp + 120] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x48244c02 // add cl, byte [rsp + 72] + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0xcb08 // or bl, cl + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xcf89 // mov edi, ecx - QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x247cb60f; BYTE $0x08 // movzx edi, byte [rsp + 8] - WORD $0x0840; BYTE $0xc7 // or dil, al - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd908 // or cl, bl + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x0844; BYTE $0xe8 // or al, r13b + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e7c041 // shl r15b, 6 - WORD $0x0841; BYTE $0xc7 // or r15b, al - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0845; BYTE $0xf9 // or r9b, r15b - LONG $0x24048b48 // mov rax, qword [rsp] - WORD $0x0841; BYTE $0xc9 // or r9b, cl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - QUAD $0x000000a024b40244 // add r14b, byte [rsp + 160] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xf3 // or r11b, r14b - LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x24740a44; BYTE $0x10 // or r14b, byte [rsp + 16] + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xf8 // or r8b, r15b + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x000000c0249c0244 // add r11b, byte [rsp + 192] + LONG $0x02e2c041 // shl r10b, 2 WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - WORD $0x8840; BYTE $0x38 // mov byte [rax], dil - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xd1 // or r9b, r10b + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xc9 // or cl, r9b + WORD $0xcb89 // mov ebx, ecx + LONG $0x24048841 // mov byte [r12], al + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x06e0c041 // shl r8b, 6 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x01688844 // mov byte [rax + 1], r13b + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x24748845; BYTE $0x01 // mov byte [r12 + 1], r14b LONG $0x07e6c040 // shl sil, 7 - WORD $0x0844; BYTE $0xc6 // or sil, r8b - WORD $0x0844; BYTE $0xe6 // or sil, r12b - LONG $0x02488844 // mov byte [rax + 2], r9b - LONG $0x03708840 // mov byte [rax + 3], sil + WORD $0x0840; BYTE $0xfe // or sil, dil + WORD $0x0840; BYTE $0xde // or sil, bl + LONG $0x24448845; BYTE $0x02 // mov byte [r12 + 2], r8b + LONG $0x24748841; BYTE $0x03 // mov byte [r12 + 3], sil LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c08348 // add rax, 4 - LONG $0x24048948 // mov qword [rsp], rax - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB2_27 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000011024848348; BYTE $0xff // add qword [rsp + 272], -1 + JNE LBB2_31 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x000000d824848b48 // mov rax, qword [rsp + 216] -LBB2_29: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB2_162 - WORD $0xff31 // xor edi, edi - JMP LBB2_164 - -LBB2_32: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB2_60 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB2_177 - WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_38 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x241c8b4c // mov r11, qword [rsp] +LBB2_33: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_200 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_186 + WORD $0xff31 // xor edi, edi + JMP LBB2_188 LBB2_36: - WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB2_114 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB2_200 + WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_147 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + +LBB2_41: + LONG $0x01728d4c // lea r14, [rdx + 1] + WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x2040; BYTE $0xd7 // and dil, dl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_36 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB2_38: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_130 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x24748844; BYTE $0x08 // mov byte [rsp + 8], r14b - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 - JB LBB2_42 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB2_182 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB2_182 - -LBB2_42: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + LONG $0x1c3c8841 // mov byte [r12 + rbx], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0xffc58349 // add r13, -1 + JNE LBB2_41 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB2_148 + JMP LBB2_200 LBB2_43: - QUAD $0x000000e024bc2b4c // sub r15, qword [rsp + 224] - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB2_119 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB2_200 + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB2_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_49 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_48: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001be; BYTE $0x00 // mov esi, 1 + WORD $0xe6d3 // shl esi, cl + WORD $0x2040; BYTE $0xde // and sil, bl + WORD $0x3044; BYTE $0xce // xor sil, r9b + LONG $0x04348841 // mov byte [r12 + rax], sil + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_48 + +LBB2_49: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 + +LBB2_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_55 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax -LBB2_44: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3a44; BYTE $0x36 // cmp r14b, byte [rsi] - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x01763a44 // cmp r14b, byte [rsi + 1] - LONG $0xd7940f40 // sete dil - LONG $0x02763a44 // cmp r14b, byte [rsi + 2] - LONG $0xd3940f41 // sete r11b - LONG $0x03763a44 // cmp r14b, byte [rsi + 3] - LONG $0xd7940f41 // sete r15b - LONG $0x04763a44 // cmp r14b, byte [rsi + 4] - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x05763a44 // cmp r14b, byte [rsi + 5] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x06763a44 // cmp r14b, byte [rsi + 6] - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x07763a44 // cmp r14b, byte [rsi + 7] - LONG $0xd5940f41 // sete r13b - LONG $0x08763a44 // cmp r14b, byte [rsi + 8] - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x09763a44 // cmp r14b, byte [rsi + 9] - LONG $0xd6940f40 // sete sil - LONG $0x0a713a44 // cmp r14b, byte [rcx + 10] - LONG $0xd0940f41 // sete r8b - LONG $0x0b713a44 // cmp r14b, byte [rcx + 11] - LONG $0xd1940f41 // sete r9b - LONG $0x0c713a44 // cmp r14b, byte [rcx + 12] - LONG $0xd6940f41 // sete r14b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] - LONG $0xd4940f41 // sete r12b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] - QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] - LONG $0xd2940f41 // sete r10b - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - LONG $0x2414940f // sete byte [rsp] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xfb // or r11b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000d024b40240 // add sil, byte [rsp + 208] - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xfb // or bl, r15b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xce // or r14b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x74b60f44; WORD $0x0824 // movzx r14d, byte [rsp + 8] - QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xdb00 // add bl, bl - LONG $0x78245c02 // add bl, byte [rsp + 120] - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xf2 // or r10b, sil - WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al - WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - LONG $0x241cb60f // movzx ebx, byte [rsp] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02578844 // mov byte [rdi + 2], r10b - WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c78348 // add rdi, 4 - LONG $0x247c8948; BYTE $0x68 // mov qword [rsp + 104], rdi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_44 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - JMP LBB2_131 - -LBB2_46: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB2_72 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB2_177 - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_52 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] - -LBB2_50: - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x31 // movzx r8d, byte [r9 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x313c8841 // mov byte [r9 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_50 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB2_52: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_56 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - -LBB2_54: +LBB2_53: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - QUAD $0x000000c02494940f // sete byte [rsp + 192] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x086a3b4c // cmp r13, qword [rdx + 8] - LONG $0xd2940f41 // sete r10b + LONG $0xd1940f41 // sete r9b LONG $0x106a3b4c // cmp r13, qword [rdx + 16] LONG $0xd6940f41 // sete r14b LONG $0x186a3b4c // cmp r13, qword [rdx + 24] - QUAD $0x000000a02494940f // sete byte [rsp + 160] + QUAD $0x000000c02494940f // sete byte [rsp + 192] LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x286a3b4c // cmp r13, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x306a3b4c // cmp r13, qword [rdx + 48] - WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x940f; BYTE $0xd0 // sete al LONG $0x386a3b4c // cmp r13, qword [rdx + 56] - LONG $0xd7940f40 // sete dil + LONG $0xd3940f41 // sete r11b LONG $0x406a3b4c // cmp r13, qword [rdx + 64] - QUAD $0x000000d02494940f // sete byte [rsp + 208] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x486a3b4c // cmp r13, qword [rdx + 72] LONG $0xd6940f40 // sete sil LONG $0x506a3b4c // cmp r13, qword [rdx + 80] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x586a3b4c // cmp r13, qword [rdx + 88] - LONG $0xd1940f41 // sete r9b + LONG $0xd0940f41 // sete r8b LONG $0x606a3b4c // cmp r13, qword [rdx + 96] - LONG $0xd3940f41 // sete r11b + LONG $0xd2940f41 // sete r10b LONG $0x686a3b4c // cmp r13, qword [rdx + 104] LONG $0xd4940f41 // sete r12b LONG $0x706a3b4c // cmp r13, qword [rdx + 112] QUAD $0x000000b02494940f // sete byte [rsp + 176] LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] LONG $0xd7940f41 // sete r15b LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0xf0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 240] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2414940f // sete byte [rsp] LONG $0xf8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 248] WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000c024940244 // add r10b, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xdf // or dil, bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000088248c0244 // add r9b, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0845; BYTE $0xce // or r14b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000d024b40240 // add sil, byte [rsp + 208] - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - WORD $0x8941; BYTE $0xda // mov r10d, ebx - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xd3 // or bl, r10b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc1 // mov r9d, eax + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xc8 // or al, r9b + WORD $0xc689 // mov esi, eax + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x24348b48 // mov rsi, qword [rsp] - QUAD $0x0000b02484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 176] - LONG $0x06e0c041 // shl r8b, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0844; BYTE $0xc0 // or al, r8b - WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xdb00 // add bl, bl - LONG $0x48245c02 // add bl, byte [rsp + 72] - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8840; BYTE $0x3e // mov byte [rsi], dil - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + LONG $0x06e6c040 // shl sil, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe3 // or bl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x58244402 // add al, byte [rsp + 88] + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4688; BYTE $0x01 // mov byte [rsi + 1], al - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x245c8841; BYTE $0x01 // mov byte [r12 + 1], bl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] + LONG $0x20244402 // add al, byte [rsp + 32] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax @@ -10385,49 +10494,47 @@ LBB2_54: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x241cb60f // movzx ebx, byte [rsp] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x4e88; BYTE $0x03 // mov byte [rsi + 3], cl + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68348 // add rsi, 4 - LONG $0x24348948 // mov qword [rsp], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_54 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - -LBB2_56: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JE LBB2_117 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB2_53 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + +LBB2_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB2_99 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi - LONG $0x241c8b4c // mov r11, qword [rsp] -LBB2_59: +LBB2_58: WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] WORD $0x940f; BYTE $0xd0 // sete al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -10435,7 +10542,7 @@ LBB2_59: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x331c8841 // mov byte [r11 + rsi], bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 LONG $0x086a3b4c // cmp r13, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] @@ -10447,641 +10554,176 @@ LBB2_59: WORD $0xe0d2 // shl al, cl WORD $0x2044; BYTE $0xc8 // and al, r9b WORD $0xd830 // xor al, bl - LONG $0x33048841 // mov byte [r11 + rsi], al + LONG $0x34048841 // mov byte [r12 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_59 - JMP LBB2_168 - -LBB2_60: - WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_64 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x241c8b4c // mov r11, qword [rsp] + JNE LBB2_58 + JMP LBB2_192 + +LBB2_59: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_65 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_63 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx LBB2_62: - WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 JNE LBB2_62 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 -LBB2_64: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_134 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x24748844; BYTE $0x08 // mov byte [rsp + 8], r14b - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 - JB LBB2_68 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB2_185 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB2_185 - -LBB2_68: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax +LBB2_63: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 + +LBB2_65: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_133 + LONG $0x08f98348 // cmp rcx, 8 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + JB LBB2_69 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB2_205 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB2_205 LBB2_69: - QUAD $0x000000e024bc2b4c // sub r15, qword [rsp + 224] - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + WORD $0xc031 // xor eax, eax + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + LONG $0x2424894c // mov qword [rsp], r12 LBB2_70: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3a44; BYTE $0x36 // cmp r14b, byte [rsi] - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x01763a44 // cmp r14b, byte [rsi + 1] - LONG $0xd7940f40 // sete dil - LONG $0x02763a44 // cmp r14b, byte [rsi + 2] - LONG $0xd3940f41 // sete r11b - LONG $0x03763a44 // cmp r14b, byte [rsi + 3] - LONG $0xd7940f41 // sete r15b - LONG $0x04763a44 // cmp r14b, byte [rsi + 4] - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x05763a44 // cmp r14b, byte [rsi + 5] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x06763a44 // cmp r14b, byte [rsi + 6] - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x07763a44 // cmp r14b, byte [rsi + 7] - LONG $0xd5940f41 // sete r13b - LONG $0x08763a44 // cmp r14b, byte [rsi + 8] - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x09763a44 // cmp r14b, byte [rsi + 9] - LONG $0xd6940f40 // sete sil - LONG $0x0a713a44 // cmp r14b, byte [rcx + 10] - LONG $0xd0940f41 // sete r8b - LONG $0x0b713a44 // cmp r14b, byte [rcx + 11] - LONG $0xd1940f41 // sete r9b - LONG $0x0c713a44 // cmp r14b, byte [rcx + 12] - LONG $0xd6940f41 // sete r14b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] - LONG $0xd4940f41 // sete r12b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] - QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] - LONG $0xd2940f41 // sete r10b - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - LONG $0x2414940f // sete byte [rsp] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xfb // or r11b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000d024b40240 // add sil, byte [rsp + 208] - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xfb // or bl, r15b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xce // or r14b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x74b60f44; WORD $0x0824 // movzx r14d, byte [rsp + 8] - QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xdb00 // add bl, bl - LONG $0x78245c02 // add bl, byte [rsp + 120] - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xf2 // or r10b, sil - WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al - WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - LONG $0x241cb60f // movzx ebx, byte [rsp] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02578844 // mov byte [rdi + 2], r10b - WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c78348 // add rdi, 4 - LONG $0x247c8948; BYTE $0x68 // mov qword [rsp + 104], rdi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_70 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - JMP LBB2_135 - -LBB2_72: - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_76 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] - -LBB2_74: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x31 // movzx r8d, byte [r9 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x313c8841 // mov byte [r9 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_74 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + LONG $0x244c2b48; BYTE $0x18 // sub rcx, qword [rsp + 24] + QUAD $0x00000090248c8948 // mov qword [rsp + 144], rcx -LBB2_76: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_80 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - -LBB2_78: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] - LONG $0xd2940f41 // sete r10b - LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] - LONG $0xd6940f41 // sete r14b - LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] - WORD $0x940f; BYTE $0xd3 // sete bl - LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] +LBB2_71: + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + LONG $0x2e3b4466 // cmp r13w, word [rsi] + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] LONG $0xd7940f40 // sete dil - LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] - LONG $0xd6940f40 // sete sil - LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] - LONG $0xd0940f41 // sete r8b - LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] - LONG $0xd1940f41 // sete r9b - LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] - LONG $0xd3940f41 // sete r11b - LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] - LONG $0xd4940f41 // sete r12b - LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] - QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] + LONG $0x6e3b4466; BYTE $0x04 // cmp r13w, word [rsi + 4] + LONG $0xd6940f41 // sete r14b + LONG $0x6e3b4466; BYTE $0x06 // cmp r13w, word [rsi + 6] + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x6e3b4466; BYTE $0x08 // cmp r13w, word [rsi + 8] LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] + LONG $0x6e3b4466; BYTE $0x0a // cmp r13w, word [rsi + 10] LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] - LONG $0xd7940f41 // sete r15b - LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] - LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] - LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] - LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] - WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000c024940244 // add r10b, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xdf // or dil, bl - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000d024b40240 // add sil, byte [rsp + 208] - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - WORD $0x8941; BYTE $0xda // mov r10d, ebx - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xd3 // or bl, r10b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x24348b48 // mov rsi, qword [rsp] - QUAD $0x0000b02484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 176] - LONG $0x06e0c041 // shl r8b, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0844; BYTE $0xc0 // or al, r8b - WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xdb00 // add bl, bl - LONG $0x48245c02 // add bl, byte [rsp + 72] - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8840; BYTE $0x3e // mov byte [rsi], dil - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4688; BYTE $0x01 // mov byte [rsi + 1], al - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xc108 // or cl, al - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x4e88; BYTE $0x03 // mov byte [rsi + 3], cl - LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68348 // add rsi, 4 - LONG $0x24348948 // mov qword [rsp], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_78 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - -LBB2_80: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB2_151 - -LBB2_82: - WORD $0xff31 // xor edi, edi - JMP LBB2_153 - -LBB2_83: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_87 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x241c8b4c // mov r11, qword [rsp] - -LBB2_85: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_85 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB2_87: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_138 - LONG $0x08ff8349 // cmp r15, 8 - LONG $0x24748944; BYTE $0x08 // mov dword [rsp + 8], r14d - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 - JB LBB2_91 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB2_188 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - WORD $0x3948; BYTE $0xd0 // cmp rax, rdx - JBE LBB2_188 - -LBB2_91: - WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - -LBB2_92: - LONG $0x247c2b4c; BYTE $0x20 // sub r15, qword [rsp + 32] - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - -LBB2_93: - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - LONG $0x363b4466 // cmp r14w, word [rsi] - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x763b4466; BYTE $0x02 // cmp r14w, word [rsi + 2] - LONG $0xd7940f40 // sete dil - LONG $0x763b4466; BYTE $0x04 // cmp r14w, word [rsi + 4] - LONG $0xd7940f41 // sete r15b - LONG $0x763b4466; BYTE $0x06 // cmp r14w, word [rsi + 6] - LONG $0xd5940f41 // sete r13b - LONG $0x763b4466; BYTE $0x08 // cmp r14w, word [rsi + 8] - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x763b4466; BYTE $0x0a // cmp r14w, word [rsi + 10] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x763b4466; BYTE $0x0c // cmp r14w, word [rsi + 12] + LONG $0x6e3b4466; BYTE $0x0c // cmp r13w, word [rsi + 12] WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x763b4466; BYTE $0x0e // cmp r14w, word [rsi + 14] - LONG $0xd3940f41 // sete r11b - LONG $0x763b4466; BYTE $0x10 // cmp r14w, word [rsi + 16] - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x763b4466; BYTE $0x12 // cmp r14w, word [rsi + 18] + LONG $0x6e3b4466; BYTE $0x0e // cmp r13w, word [rsi + 14] + LONG $0xd2940f41 // sete r10b + LONG $0x6e3b4466; BYTE $0x10 // cmp r13w, word [rsi + 16] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x6e3b4466; BYTE $0x12 // cmp r13w, word [rsi + 18] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x763b4466; BYTE $0x14 // cmp r14w, word [rsi + 20] + LONG $0x6e3b4466; BYTE $0x14 // cmp r13w, word [rsi + 20] WORD $0x940f; BYTE $0xd2 // sete dl - LONG $0x763b4466; BYTE $0x16 // cmp r14w, word [rsi + 22] + LONG $0x6e3b4466; BYTE $0x16 // cmp r13w, word [rsi + 22] LONG $0xd6940f40 // sete sil - LONG $0x723b4566; BYTE $0x18 // cmp r14w, word [r10 + 24] + LONG $0x6b3b4566; BYTE $0x18 // cmp r13w, word [r11 + 24] LONG $0xd1940f41 // sete r9b - LONG $0x723b4566; BYTE $0x1a // cmp r14w, word [r10 + 26] + LONG $0x6b3b4566; BYTE $0x1a // cmp r13w, word [r11 + 26] LONG $0xd4940f41 // sete r12b - LONG $0x723b4566; BYTE $0x1c // cmp r14w, word [r10 + 28] + LONG $0x6b3b4566; BYTE $0x1c // cmp r13w, word [r11 + 28] QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x723b4566; BYTE $0x1e // cmp r14w, word [r10 + 30] + LONG $0x6b3b4566; BYTE $0x1e // cmp r13w, word [r11 + 30] LONG $0xd0940f41 // sete r8b - LONG $0x723b4566; BYTE $0x20 // cmp r14w, word [r10 + 32] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x723b4566; BYTE $0x22 // cmp r14w, word [r10 + 34] - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x723b4566; BYTE $0x24 // cmp r14w, word [r10 + 36] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x723b4566; BYTE $0x26 // cmp r14w, word [r10 + 38] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x723b4566; BYTE $0x28 // cmp r14w, word [r10 + 40] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x723b4566; BYTE $0x2a // cmp r14w, word [r10 + 42] + LONG $0x6b3b4566; BYTE $0x20 // cmp r13w, word [r11 + 32] LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x723b4566; BYTE $0x2c // cmp r14w, word [r10 + 44] + LONG $0x6b3b4566; BYTE $0x22 // cmp r13w, word [r11 + 34] LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x723b4566; BYTE $0x2e // cmp r14w, word [r10 + 46] - LONG $0xd6940f41 // sete r14b - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x30 // cmp bx, word [r10 + 48] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x32 // cmp bx, word [r10 + 50] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x34 // cmp bx, word [r10 + 52] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x36 // cmp bx, word [r10 + 54] + LONG $0x6b3b4566; BYTE $0x24 // cmp r13w, word [r11 + 36] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x6b3b4566; BYTE $0x26 // cmp r13w, word [r11 + 38] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x6b3b4566; BYTE $0x28 // cmp r13w, word [r11 + 40] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x6b3b4566; BYTE $0x2a // cmp r13w, word [r11 + 42] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x6b3b4566; BYTE $0x2c // cmp r13w, word [r11 + 44] LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x38 // cmp bx, word [r10 + 56] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x3a // cmp bx, word [r10 + 58] + LONG $0x6b3b4566; BYTE $0x2e // cmp r13w, word [r11 + 46] + LONG $0xd7940f41 // sete r15b + LONG $0x6b3b4566; BYTE $0x30 // cmp r13w, word [r11 + 48] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x6b3b4566; BYTE $0x32 // cmp r13w, word [r11 + 50] LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x3c // cmp bx, word [r10 + 60] - LONG $0x2414940f // sete byte [rsp] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x3e // cmp bx, word [r10 + 62] + LONG $0x6b3b4566; BYTE $0x34 // cmp r13w, word [r11 + 52] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x6b3b4566; BYTE $0x36 // cmp r13w, word [r11 + 54] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x6b3b4566; BYTE $0x38 // cmp r13w, word [r11 + 56] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x6b3b4566; BYTE $0x3a // cmp r13w, word [r11 + 58] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x6b3b4566; BYTE $0x3c // cmp r13w, word [r11 + 60] + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x6b3b4566; BYTE $0x3e // cmp r13w, word [r11 + 62] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xff // or r15b, dil + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil WORD $0xc900 // add cl, cl - LONG $0xd0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 208] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b + LONG $0xa0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 160] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0xe2c0; BYTE $0x02 // shl dl, 2 WORD $0xca08 // or dl, cl - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xc108 // or cl, al WORD $0xcf89 // mov edi, ecx LONG $0x03e6c040 // shl sil, 3 WORD $0x0840; BYTE $0xd6 // or sil, dl - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e1c041 // shl r9b, 4 @@ -11092,16 +10734,17 @@ LBB2_93: WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl - WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0845; BYTE $0xe0 // or r8b, r12b - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xc000 // add al, al - LONG $0x60244402 // add al, byte [rsp + 96] - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx @@ -11109,216 +10752,218 @@ LBB2_93: WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd108 // or cl, dl WORD $0xce89 // mov esi, ecx - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - WORD $0x8844; BYTE $0x19 // mov byte [rcx], r11b - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + LONG $0x240c8b48 // mov rcx, qword [rsp] + WORD $0x8844; BYTE $0x11 // mov byte [rcx], r10b + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xd6 // or r14b, dl + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xd7 // or r15b, dl LONG $0x01418844 // mov byte [rcx + 1], r8b - WORD $0x0841; BYTE $0xf6 // or r14b, sil - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x20244402 // add al, byte [rsp + 32] WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd008 // or al, dl - LONG $0x2414b60f // movzx edx, byte [rsp] + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xd308 // or bl, dl WORD $0xc308 // or bl, al - LONG $0x02718844 // mov byte [rcx + 2], r14b - LONG $0x24748b44; BYTE $0x08 // mov r14d, dword [rsp + 8] + LONG $0x02798844 // mov byte [rcx + 2], r15b WORD $0x5988; BYTE $0x03 // mov byte [rcx + 3], bl - LONG $0x40728d49 // lea rsi, [r10 + 64] + LONG $0x40738d49 // lea rsi, [r11 + 64] LONG $0x04c18348 // add rcx, 4 - LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_93 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + LONG $0x240c8948 // mov qword [rsp], rcx + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB2_71 QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - JMP LBB2_139 - -LBB2_95: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_99 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x241c8b4c // mov r11, qword [rsp] + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + JMP LBB2_134 + +LBB2_73: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_79 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_77 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB2_97: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] +LBB2_76: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_97 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB2_99: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_143 - LONG $0x08ff8349 // cmp r15, 8 - LONG $0x24748944; BYTE $0x08 // mov dword [rsp + 8], r14d - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 - JB LBB2_103 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB2_191 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - WORD $0x3948; BYTE $0xd0 // cmp rax, rdx - JBE LBB2_191 + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_76 + +LBB2_77: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 + +LBB2_79: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_138 + LONG $0x08f98348 // cmp rcx, 8 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + JB LBB2_83 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB2_208 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB2_208 -LBB2_103: +LBB2_83: WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax + LONG $0x2424894c // mov qword [rsp], r12 -LBB2_104: - LONG $0x247c2b4c; BYTE $0x20 // sub r15, qword [rsp + 32] - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 +LBB2_84: + LONG $0x244c2b48; BYTE $0x18 // sub rcx, qword [rsp + 24] + QUAD $0x00000090248c8948 // mov qword [rsp + 144], rcx -LBB2_105: - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - LONG $0x363b4466 // cmp r14w, word [rsi] - QUAD $0x000000c02494940f // sete byte [rsp + 192] - LONG $0x763b4466; BYTE $0x02 // cmp r14w, word [rsi + 2] +LBB2_85: + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + LONG $0x2e3b4466 // cmp r13w, word [rsi] + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] LONG $0xd7940f40 // sete dil - LONG $0x763b4466; BYTE $0x04 // cmp r14w, word [rsi + 4] - LONG $0xd7940f41 // sete r15b - LONG $0x763b4466; BYTE $0x06 // cmp r14w, word [rsi + 6] - LONG $0xd5940f41 // sete r13b - LONG $0x763b4466; BYTE $0x08 // cmp r14w, word [rsi + 8] - QUAD $0x000000802494940f // sete byte [rsp + 128] - LONG $0x763b4466; BYTE $0x0a // cmp r14w, word [rsi + 10] - LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] - LONG $0x763b4466; BYTE $0x0c // cmp r14w, word [rsi + 12] + LONG $0x6e3b4466; BYTE $0x04 // cmp r13w, word [rsi + 4] + LONG $0xd6940f41 // sete r14b + LONG $0x6e3b4466; BYTE $0x06 // cmp r13w, word [rsi + 6] + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x6e3b4466; BYTE $0x08 // cmp r13w, word [rsi + 8] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x6e3b4466; BYTE $0x0a // cmp r13w, word [rsi + 10] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x6e3b4466; BYTE $0x0c // cmp r13w, word [rsi + 12] WORD $0x940f; BYTE $0xd0 // sete al - LONG $0x763b4466; BYTE $0x0e // cmp r14w, word [rsi + 14] - LONG $0xd3940f41 // sete r11b - LONG $0x763b4466; BYTE $0x10 // cmp r14w, word [rsi + 16] - QUAD $0x000000d02494940f // sete byte [rsp + 208] - LONG $0x763b4466; BYTE $0x12 // cmp r14w, word [rsi + 18] + LONG $0x6e3b4466; BYTE $0x0e // cmp r13w, word [rsi + 14] + LONG $0xd2940f41 // sete r10b + LONG $0x6e3b4466; BYTE $0x10 // cmp r13w, word [rsi + 16] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x6e3b4466; BYTE $0x12 // cmp r13w, word [rsi + 18] WORD $0x940f; BYTE $0xd1 // sete cl - LONG $0x763b4466; BYTE $0x14 // cmp r14w, word [rsi + 20] + LONG $0x6e3b4466; BYTE $0x14 // cmp r13w, word [rsi + 20] WORD $0x940f; BYTE $0xd2 // sete dl - LONG $0x763b4466; BYTE $0x16 // cmp r14w, word [rsi + 22] + LONG $0x6e3b4466; BYTE $0x16 // cmp r13w, word [rsi + 22] LONG $0xd6940f40 // sete sil - LONG $0x723b4566; BYTE $0x18 // cmp r14w, word [r10 + 24] + LONG $0x6b3b4566; BYTE $0x18 // cmp r13w, word [r11 + 24] LONG $0xd1940f41 // sete r9b - LONG $0x723b4566; BYTE $0x1a // cmp r14w, word [r10 + 26] + LONG $0x6b3b4566; BYTE $0x1a // cmp r13w, word [r11 + 26] LONG $0xd4940f41 // sete r12b - LONG $0x723b4566; BYTE $0x1c // cmp r14w, word [r10 + 28] + LONG $0x6b3b4566; BYTE $0x1c // cmp r13w, word [r11 + 28] QUAD $0x000000b02494940f // sete byte [rsp + 176] - LONG $0x723b4566; BYTE $0x1e // cmp r14w, word [r10 + 30] + LONG $0x6b3b4566; BYTE $0x1e // cmp r13w, word [r11 + 30] LONG $0xd0940f41 // sete r8b - LONG $0x723b4566; BYTE $0x20 // cmp r14w, word [r10 + 32] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0x723b4566; BYTE $0x22 // cmp r14w, word [r10 + 34] - QUAD $0x000000a02494940f // sete byte [rsp + 160] - LONG $0x723b4566; BYTE $0x24 // cmp r14w, word [r10 + 36] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] - LONG $0x723b4566; BYTE $0x26 // cmp r14w, word [r10 + 38] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] - LONG $0x723b4566; BYTE $0x28 // cmp r14w, word [r10 + 40] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] - LONG $0x723b4566; BYTE $0x2a // cmp r14w, word [r10 + 42] + LONG $0x6b3b4566; BYTE $0x20 // cmp r13w, word [r11 + 32] LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] - LONG $0x723b4566; BYTE $0x2c // cmp r14w, word [r10 + 44] + LONG $0x6b3b4566; BYTE $0x22 // cmp r13w, word [r11 + 34] LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] - LONG $0x723b4566; BYTE $0x2e // cmp r14w, word [r10 + 46] - LONG $0xd6940f41 // sete r14b - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x30 // cmp bx, word [r10 + 48] - LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x32 // cmp bx, word [r10 + 50] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x34 // cmp bx, word [r10 + 52] - LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x36 // cmp bx, word [r10 + 54] + LONG $0x6b3b4566; BYTE $0x24 // cmp r13w, word [r11 + 36] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x6b3b4566; BYTE $0x26 // cmp r13w, word [r11 + 38] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x6b3b4566; BYTE $0x28 // cmp r13w, word [r11 + 40] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x6b3b4566; BYTE $0x2a // cmp r13w, word [r11 + 42] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x6b3b4566; BYTE $0x2c // cmp r13w, word [r11 + 44] LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x38 // cmp bx, word [r10 + 56] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x3a // cmp bx, word [r10 + 58] + LONG $0x6b3b4566; BYTE $0x2e // cmp r13w, word [r11 + 46] + LONG $0xd7940f41 // sete r15b + LONG $0x6b3b4566; BYTE $0x30 // cmp r13w, word [r11 + 48] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x6b3b4566; BYTE $0x32 // cmp r13w, word [r11 + 50] LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x3c // cmp bx, word [r10 + 60] - LONG $0x2414940f // sete byte [rsp] - LONG $0x08245c8b // mov ebx, dword [rsp + 8] - LONG $0x5a3b4166; BYTE $0x3e // cmp bx, word [r10 + 62] + LONG $0x6b3b4566; BYTE $0x34 // cmp r13w, word [r11 + 52] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x6b3b4566; BYTE $0x36 // cmp r13w, word [r11 + 54] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x6b3b4566; BYTE $0x38 // cmp r13w, word [r11 + 56] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x6b3b4566; BYTE $0x3a // cmp r13w, word [r11 + 58] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x6b3b4566; BYTE $0x3c // cmp r13w, word [r11 + 60] + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x6b3b4566; BYTE $0x3e // cmp r13w, word [r11 + 62] WORD $0x940f; BYTE $0xd3 // sete bl WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] + QUAD $0x0000008824bc0240 // add dil, byte [rsp + 136] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xff // or r15b, dil + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil WORD $0xc900 // add cl, cl - LONG $0xd0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 208] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xfd // or r13b, r15b + LONG $0xa0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 160] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0xe2c0; BYTE $0x02 // shl dl, 2 WORD $0xca08 // or dl, cl - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xc108 // or cl, al WORD $0xcf89 // mov edi, ecx LONG $0x03e6c040 // shl sil, 3 WORD $0x0840; BYTE $0xd6 // or sil, dl - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e1c041 // shl r9b, 4 @@ -11329,16 +10974,17 @@ LBB2_105: WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl - WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0845; BYTE $0xe0 // or r8b, r12b - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xc000 // add al, al - LONG $0x60244402 // add al, byte [rsp + 96] - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx @@ -11346,231 +10992,244 @@ LBB2_105: WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd108 // or cl, dl WORD $0xce89 // mov esi, ecx - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - WORD $0x8844; BYTE $0x19 // mov byte [rcx], r11b - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + LONG $0x240c8b48 // mov rcx, qword [rsp] + WORD $0x8844; BYTE $0x11 // mov byte [rcx], r10b + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xd6 // or r14b, dl + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xd7 // or r15b, dl LONG $0x01418844 // mov byte [rcx + 1], r8b - WORD $0x0841; BYTE $0xf6 // or r14b, sil - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x20244402 // add al, byte [rsp + 32] WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd008 // or al, dl - LONG $0x2414b60f // movzx edx, byte [rsp] + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0xd308 // or bl, dl WORD $0xc308 // or bl, al - LONG $0x02718844 // mov byte [rcx + 2], r14b - LONG $0x24748b44; BYTE $0x08 // mov r14d, dword [rsp + 8] + LONG $0x02798844 // mov byte [rcx + 2], r15b WORD $0x5988; BYTE $0x03 // mov byte [rcx + 3], bl - LONG $0x40728d49 // lea rsi, [r10 + 64] + LONG $0x40738d49 // lea rsi, [r11 + 64] LONG $0x04c18348 // add rcx, 4 - LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_105 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + LONG $0x240c8948 // mov qword [rsp], rcx + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB2_85 QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - JMP LBB2_144 - -LBB2_107: - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_111 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] - -LBB2_109: - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x31 // movzx r8d, byte [r9 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x313c8841 // mov byte [r9 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_109 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + JMP LBB2_139 -LBB2_111: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_115 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x00000098249c894c // mov qword [rsp + 152], r11 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - -LBB2_113: +LBB2_87: + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB2_93 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_91 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_90: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001be; BYTE $0x00 // mov esi, 1 + WORD $0xe6d3 // shl esi, cl + WORD $0x2040; BYTE $0xde // and sil, bl + WORD $0x3044; BYTE $0xce // xor sil, r9b + LONG $0x04348841 // mov byte [r12 + rax], sil + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_90 + +LBB2_91: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 + +LBB2_93: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_97 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB2_95: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - QUAD $0x000000c02494940f // sete byte [rsp + 192] + QUAD $0x000000882494940f // sete byte [rsp + 136] LONG $0x086a3b4c // cmp r13, qword [rdx + 8] - LONG $0xd2940f41 // sete r10b + LONG $0xd1940f41 // sete r9b LONG $0x106a3b4c // cmp r13, qword [rdx + 16] LONG $0xd6940f41 // sete r14b LONG $0x186a3b4c // cmp r13, qword [rdx + 24] - QUAD $0x000000a02494940f // sete byte [rsp + 160] + QUAD $0x000000c02494940f // sete byte [rsp + 192] LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] LONG $0x286a3b4c // cmp r13, qword [rdx + 40] - LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] LONG $0x306a3b4c // cmp r13, qword [rdx + 48] - WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0x940f; BYTE $0xd0 // sete al LONG $0x386a3b4c // cmp r13, qword [rdx + 56] - LONG $0xd7940f40 // sete dil + LONG $0xd3940f41 // sete r11b LONG $0x406a3b4c // cmp r13, qword [rdx + 64] - QUAD $0x000000d02494940f // sete byte [rsp + 208] + QUAD $0x000000a02494940f // sete byte [rsp + 160] LONG $0x486a3b4c // cmp r13, qword [rdx + 72] LONG $0xd6940f40 // sete sil LONG $0x506a3b4c // cmp r13, qword [rdx + 80] - LONG $0xd0940f41 // sete r8b + LONG $0xd7940f40 // sete dil LONG $0x586a3b4c // cmp r13, qword [rdx + 88] - LONG $0xd1940f41 // sete r9b + LONG $0xd0940f41 // sete r8b LONG $0x606a3b4c // cmp r13, qword [rdx + 96] - LONG $0xd3940f41 // sete r11b + LONG $0xd2940f41 // sete r10b LONG $0x686a3b4c // cmp r13, qword [rdx + 104] LONG $0xd4940f41 // sete r12b LONG $0x706a3b4c // cmp r13, qword [rdx + 112] QUAD $0x000000b02494940f // sete byte [rsp + 176] LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x940f; BYTE $0xd3 // sete bl LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] - LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] - LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] - LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] - LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] - LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] LONG $0xd7940f41 // sete r15b LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] - LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] - LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] - LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] - LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] LONG $0xf0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 240] - LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2414940f // sete byte [rsp] LONG $0xf8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 248] WORD $0x940f; BYTE $0xd1 // sete cl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000c024940244 // add r10b, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xdf // or dil, bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000088248c0244 // add r9b, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0845; BYTE $0xce // or r14b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000d024b40240 // add sil, byte [rsp + 208] - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - WORD $0x8941; BYTE $0xda // mov r10d, ebx - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xd3 // or bl, r10b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc1 // mov r9d, eax + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xc8 // or al, r9b + WORD $0xc689 // mov esi, eax + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - LONG $0x24348b48 // mov rsi, qword [rsp] - QUAD $0x0000b02484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 176] - LONG $0x06e0c041 // shl r8b, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0844; BYTE $0xc0 // or al, r8b - WORD $0x0840; BYTE $0xdf // or dil, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xdb00 // add bl, bl - LONG $0x48245c02 // add bl, byte [rsp + 72] - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - WORD $0x8840; BYTE $0x3e // mov byte [rsi], dil - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + LONG $0x06e6c040 // shl sil, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe3 // or bl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x58244402 // add al, byte [rsp + 88] + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - WORD $0x4688; BYTE $0x01 // mov byte [rsi + 1], al - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x245c8841; BYTE $0x01 // mov byte [r12 + 1], bl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] + LONG $0x20244402 // add al, byte [rsp + 32] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax @@ -11578,111 +11237,124 @@ LBB2_113: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x241cb60f // movzx ebx, byte [rsp] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x4e88; BYTE $0x03 // mov byte [rsi + 3], cl + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68348 // add rsi, 4 - LONG $0x24348948 // mov qword [rsp], rsi - QUAD $0x0000008824848348; BYTE $0xff // add qword [rsp + 136], -1 - JNE LBB2_113 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - -LBB2_115: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB2_166 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB2_95 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB2_117: +LBB2_97: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_190 + +LBB2_99: WORD $0xff31 // xor edi, edi - JMP LBB2_168 - -LBB2_118: - LONG $0x1f728d4d // lea r14, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xf2490f4d // cmovns r14, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff3 // movss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB2_122 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x241c8b4c // mov r11, qword [rsp] + JMP LBB2_192 + +LBB2_100: + WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_106 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_104 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB2_120: - WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] +LBB2_103: + WORD $0x2e0f; BYTE $0x01 // ucomiss xmm0, dword [rcx] + LONG $0x04518d48 // lea rdx, [rcx + 4] WORD $0x9b0f; BYTE $0xd1 // setnp cl WORD $0x940f; BYTE $0xd3 // sete bl WORD $0xcb20 // and bl, cl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x333c8841 // mov byte [r11 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB2_120 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_103 -LBB2_122: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB2_147 - LONG $0x04fe8349 // cmp r14, 4 - JB LBB2_126 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB2_194 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb0048d4a // lea rax, [rax + 4*r14] - WORD $0x3948; BYTE $0xd0 // cmp rax, rdx - JBE LBB2_194 +LBB2_104: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 + +LBB2_106: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_142 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x04f98348 // cmp rcx, 4 + JB LBB2_110 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB2_211 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB2_211 -LBB2_126: - WORD $0x3145; BYTE $0xc0 // xor r8d, r8d +LBB2_110: + WORD $0xc031 // xor eax, eax WORD $0x8948; BYTE $0xd3 // mov rbx, rdx - LONG $0x243c8b4c // mov r15, qword [rsp] + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB2_127: - LONG $0x247c894c; BYTE $0x08 // mov qword [rsp + 8], r15 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 - WORD $0x294d; BYTE $0xc6 // sub r14, r8 - QUAD $0x0000009824b4894c // mov qword [rsp + 152], r14 +LBB2_111: + QUAD $0x0000008024ac894c // mov qword [rsp + 128], r13 + QUAD $0x0000011024b48944 // mov dword [rsp + 272], r14d + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + WORD $0x2948; BYTE $0xc1 // sub rcx, rax + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx -LBB2_128: +LBB2_112: WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -11696,12 +11368,12 @@ LBB2_128: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x18244c88 // mov byte [rsp + 24], cl + LONG $0x20244c88 // mov byte [rsp + 32], cl LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x08244c88 // mov byte [rsp + 8], cl LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -11711,12 +11383,12 @@ LBB2_128: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x30244c88 // mov byte [rsp + 48], cl LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -11731,42 +11403,42 @@ LBB2_128: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x60244c88 // mov byte [rsp + 96], cl LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x40244c88 // mov byte [rsp + 64], cl LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x48244c88 // mov byte [rsp + 72], cl LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x50244c88 // mov byte [rsp + 80], cl LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x70244c88 // mov byte [rsp + 112], cl LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x78244c88 // mov byte [rsp + 120], cl LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x58244c88 // mov byte [rsp + 88], cl LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd4940f41 // sete r12b @@ -11775,7 +11447,7 @@ LBB2_128: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x68244c88 // mov byte [rsp + 104], cl LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl @@ -11785,12 +11457,12 @@ LBB2_128: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd6940f41 // sete r14b @@ -11803,7 +11475,7 @@ LBB2_128: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd3940f41 // sete r11b @@ -11824,7 +11496,7 @@ LBB2_128: WORD $0x9b0f; BYTE $0xd0 // setnp al WORD $0x940f; BYTE $0xd1 // sete cl WORD $0xc120 // and cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] WORD $0x9b0f; BYTE $0xd0 // setnp al LONG $0xd7940f40 // sete dil @@ -11836,201 +11508,410 @@ LBB2_128: WORD $0xd200 // add dl, dl WORD $0x0844; BYTE $0xea // or dl, r13b WORD $0x8941; BYTE $0xd5 // mov r13d, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + LONG $0x2454b60f; BYTE $0x18 // movzx edx, byte [rsp + 24] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] WORD $0xc900 // add cl, cl LONG $0x28244c02 // add cl, byte [rsp + 40] LONG $0x2404b60f // movzx eax, byte [rsp] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd008 // or al, dl WORD $0x0488; BYTE $0x24 // mov byte [rsp], al - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xca08 // or dl, cl + LONG $0x6cb60f44; WORD $0x5024 // movzx r13d, byte [rsp + 80] + LONG $0x05e5c041 // shl r13b, 5 + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + LONG $0x6cb60f44; WORD $0x7824 // movzx r13d, byte [rsp + 120] + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xcd // or r13b, cl + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x58 // add r12b, byte [rsp + 88] + WORD $0x8944; BYTE $0xe1 // mov ecx, r12d + LONG $0x64b60f44; WORD $0x6824 // movzx r12d, byte [rsp + 104] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xcc // or r12b, cl + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0x8941; BYTE $0xcc // mov r12d, ecx + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x24b60f44; BYTE $0x24 // movzx r12d, byte [rsp] + WORD $0x0841; BYTE $0xc4 // or r12b, al + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + LONG $0x06e6c041 // shl r14b, 6 + WORD $0x0841; BYTE $0xc6 // or r14b, al + WORD $0x0841; BYTE $0xd5 // or r13b, dl + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xf0 // or r8b, r14b + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x000000c0249c0244 // add r11b, byte [rsp + 192] + LONG $0x02e2c041 // shl r10b, 2 + WORD $0x0845; BYTE $0xda // or r10b, r11b + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xd1 // or r9b, r10b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + WORD $0x8844; BYTE $0x20 // mov byte [rax], r12b + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x01688844 // mov byte [rax + 1], r13b + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xfe // or sil, dil + WORD $0x0844; BYTE $0xfe // or sil, r15b + LONG $0x02408844 // mov byte [rax + 2], r8b + LONG $0x03708840 // mov byte [rax + 3], sil + LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 + LONG $0x04c08348 // add rax, 4 + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB2_112 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x0000011024b48b44 // mov r14d, dword [rsp + 272] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + JMP LBB2_143 + +LBB2_114: + WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB2_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_161 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + +LBB2_117: + LONG $0x01728d4c // lea r14, [rdx + 1] + WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xd7 // and dil, dl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x1c3c8841 // mov byte [r12 + rbx], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0xffc08348 // add rax, -1 + JNE LBB2_117 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB2_162 + JMP LBB2_200 + +LBB2_119: + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB2_125 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB2_123 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB2_122: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001be; BYTE $0x00 // mov esi, 1 + WORD $0xe6d3 // shl esi, cl + WORD $0x2040; BYTE $0xde // and sil, bl + WORD $0x3044; BYTE $0xce // xor sil, r9b + LONG $0x04348841 // mov byte [r12 + rax], sil + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB2_122 + +LBB2_123: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 + LONG $0x01c48349 // add r12, 1 + +LBB2_125: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_129 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB2_127: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] + LONG $0xd1940f41 // sete r9b + LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] + LONG $0xd6940f41 // sete r14b + LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] + WORD $0x940f; BYTE $0xd0 // sete al + LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] + LONG $0xd3940f41 // sete r11b + LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] + LONG $0xd6940f40 // sete sil + LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] + LONG $0xd7940f40 // sete dil + LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] + LONG $0xd0940f41 // sete r8b + LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] + LONG $0xd2940f41 // sete r10b + LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] + LONG $0xd4940f41 // sete r12b + LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] + QUAD $0x000000b02494940f // sete byte [rsp + 176] + LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] + WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] + LONG $0x2454940f; BYTE $0x60 // sete byte [rsp + 96] + LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] + LONG $0xd7940f41 // sete r15b + LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] + LONG $0x2414940f // sete byte [rsp] + LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] + WORD $0x940f; BYTE $0xd1 // sete cl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000088248c0244 // add r9b, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x000000a024b40240 // add sil, byte [rsp + 160] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc1 // mov r9d, eax + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xc8 // or al, r9b + WORD $0xc689 // mov esi, eax + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + LONG $0x06e6c040 // shl sil, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe3 // or bl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0x58244402 // add al, byte [rsp + 88] + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0xc689 // mov esi, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x241c8845 // mov byte [r12], r11b + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x245c8841; BYTE $0x01 // mov byte [r12 + 1], bl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xca08 // or dl, cl - LONG $0x6cb60f44; WORD $0x6024 // movzx r13d, byte [rsp + 96] - LONG $0x05e5c041 // shl r13b, 5 - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x6cb60f44; WORD $0x7024 // movzx r13d, byte [rsp + 112] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xcd // or r13b, cl - WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x48 // add r12b, byte [rsp + 72] - WORD $0x8944; BYTE $0xe1 // mov ecx, r12d - LONG $0x64b60f44; WORD $0x7824 // movzx r12d, byte [rsp + 120] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0841; BYTE $0xcc // or r12b, cl - QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - WORD $0x8941; BYTE $0xcc // mov r12d, ecx - QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x24b60f44; BYTE $0x24 // movzx r12d, byte [rsp] - WORD $0x0841; BYTE $0xc4 // or r12b, al - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e6c041 // shl r14b, 6 - WORD $0x0841; BYTE $0xc6 // or r14b, al - WORD $0x0841; BYTE $0xd5 // or r13b, dl - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf0 // or r8b, r14b - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000a0249c0244 // add r11b, byte [rsp + 160] - LONG $0x02e2c041 // shl r10b, 2 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xd1 // or r9b, r10b - LONG $0x04e7c041 // shl r15b, 4 - WORD $0x0845; BYTE $0xcf // or r15b, r9b - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - WORD $0x8844; BYTE $0x20 // mov byte [rax], r12b - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x06e7c040 // shl dil, 6 - WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e6c040 // shl sil, 7 - WORD $0x0840; BYTE $0xfe // or sil, dil - WORD $0x0844; BYTE $0xfe // or sil, r15b - LONG $0x02408844 // mov byte [rax + 2], r8b - LONG $0x03708840 // mov byte [rax + 3], sil - LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 - LONG $0x04c08348 // add rax, 4 - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - QUAD $0x0000009824848348; BYTE $0xff // add qword [rsp + 152], -1 - JNE LBB2_128 - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] - JMP LBB2_148 + WORD $0xd808 // or al, bl + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd908 // or cl, bl + WORD $0xc108 // or cl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB2_127 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB2_130: - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx +LBB2_129: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB2_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB2_175 LBB2_131: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB2_137 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + WORD $0xff31 // xor edi, edi + JMP LBB2_177 -LBB2_156: - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e343a46 // cmp r14b, byte [rsi + r9] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x06743a44; BYTE $0x01 // cmp r14b, byte [rsi + rax + 1] - LONG $0x02488d4c // lea r9, [rax + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB2_156 - JMP LBB2_159 +LBB2_132: + WORD $0x8949; BYTE $0xd6 // mov r14, rdx + JMP LBB2_149 -LBB2_134: - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx +LBB2_133: + LONG $0x2424894c // mov qword [rsp], r12 + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx -LBB2_135: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB2_157 +LBB2_134: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB2_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB2_141 + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + LONG $0x241c8b4c // mov r11, qword [rsp] LBB2_137: - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_177 - JMP LBB2_161 - -LBB2_138: - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - -LBB2_139: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JE LBB2_146 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xff // xor r15d, r15d - LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] - -LBB2_142: WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x363b4466 // cmp r14w, word [rsi] + LONG $0x2e3b4466 // cmp r13w, word [rsi] WORD $0x940f; BYTE $0xd2 // sete dl WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xff // mov rdi, r15 + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 LONG $0x03efc148 // shr rdi, 3 LONG $0x14b60f45; BYTE $0x3b // movzx r10d, byte [r11 + rdi] - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl @@ -12038,8 +11919,8 @@ LBB2_142: WORD $0xd320 // and bl, dl WORD $0x3044; BYTE $0xd3 // xor bl, r10b LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x02c78349 // add r15, 2 - LONG $0x763b4466; BYTE $0x02 // cmp r14w, word [rsi + 2] + LONG $0x02c68349 // add r14, 2 + LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] LONG $0x04768d48 // lea rsi, [rsi + 4] WORD $0x940f; BYTE $0xd2 // sete dl WORD $0xdaf6 // neg dl @@ -12050,2219 +11931,918 @@ LBB2_142: WORD $0xd020 // and al, dl WORD $0xd830 // xor al, bl LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x394d; BYTE $0xf9 // cmp r9, r15 - JNE LBB2_142 - JMP LBB2_173 + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB2_137 + JMP LBB2_197 -LBB2_143: - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx +LBB2_138: + LONG $0x2424894c // mov qword [rsp], r12 + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx -LBB2_144: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB2_171 +LBB2_139: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB2_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB2_195 -LBB2_146: - WORD $0x3145; BYTE $0xff // xor r15d, r15d - JMP LBB2_173 +LBB2_141: + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB2_197 -LBB2_147: - LONG $0x243c8b4c // mov r15, qword [rsp] +LBB2_142: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 WORD $0x8948; BYTE $0xd3 // mov rbx, rdx -LBB2_148: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xd6 // cmp r14, r10 - JGE LBB2_177 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xd6 // add r14, r10 - JNE LBB2_178 - WORD $0xf631 // xor esi, esi - JMP LBB2_180 - -LBB2_151: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi - LONG $0x241c8b4c // mov r11, qword [rsp] - -LBB2_152: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x331c8841 // mov byte [r11 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd1940f41 // sete r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x33048841 // mov byte [r11 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_152 - -LBB2_153: - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_177 - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - JMP LBB2_170 - -LBB2_157: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - -LBB2_158: - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e343a46 // cmp r14b, byte [rsi + r9] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x06743a44; BYTE $0x01 // cmp r14b, byte [rsi + rax + 1] - LONG $0x02488d4c // lea r9, [rax + 2] - WORD $0x940f; BYTE $0xd3 // sete bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB2_158 - -LBB2_159: - WORD $0x014c; BYTE $0xce // add rsi, r9 - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_177 - -LBB2_161: - WORD $0x3a44; BYTE $0x36 // cmp r14b, byte [rsi] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xca // mov rdx, r9 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e18041 // and r9b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xc9 // mov ecx, r9d - JMP LBB2_175 - -LBB2_162: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xff31 // xor edi, edi - LONG $0x24348b4c // mov r14, qword [rsp] - -LBB2_163: - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xc820 // and al, cl - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x36 // movzx r10d, byte [r14 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0xb341; BYTE $0x01 // mov r11b, 1 - WORD $0xd241; BYTE $0xe3 // shl r11b, cl - WORD $0x3044; BYTE $0xd0 // xor al, r10b - WORD $0x2041; BYTE $0xc3 // and r11b, al - WORD $0x3045; BYTE $0xd3 // xor r11b, r10b - LONG $0x361c8845 // mov byte [r14 + rsi], r11b - LONG $0x02c78348 // add rdi, 2 - LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] - LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd29b0f41 // setnp r10b - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0x2044; BYTE $0xd0 // and al, r10b - WORD $0xd8f6 // neg al - WORD $0x3044; BYTE $0xd8 // xor al, r11b - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xdb // xor bl, r11b - LONG $0x361c8841 // mov byte [r14 + rsi], bl - WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB2_163 - -LBB2_164: - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_177 - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xc220 // and dl, al - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x03e8c148 // shr rax, 3 - LONG $0x24048b4c // mov r8, qword [rsp] - LONG $0x00348a41 // mov sil, byte [r8 + rax] - LONG $0x07e78040 // and dil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf989 // mov ecx, edi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf2 // xor dl, sil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x001c8841 // mov byte [r8 + rax], bl - JMP LBB2_177 - -LBB2_166: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi - LONG $0x241c8b4c // mov r11, qword [rsp] - -LBB2_167: - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x33 // movzx r9d, byte [r11 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x331c8841 // mov byte [r11 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x086a3b4c // cmp r13, qword [rdx + 8] - LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd1940f41 // sete r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x33048841 // mov byte [r11 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB2_167 +LBB2_143: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB2_200 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB2_201 + WORD $0xf631 // xor esi, esi + JMP LBB2_203 -LBB2_168: - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_177 - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] +LBB2_146: + WORD $0x8949; BYTE $0xd6 // mov r14, rdx + JMP LBB2_163 -LBB2_170: - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24048b4c // mov r8, qword [rsp] - LONG $0x10348a41 // mov sil, byte [r8 + rdx] - LONG $0x07e78040 // and dil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf989 // mov ecx, edi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - JMP LBB2_176 +LBB2_147: + WORD $0x8949; BYTE $0xd6 // mov r14, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 -LBB2_171: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xff // xor r15d, r15d - LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] +LBB2_148: + LONG $0x01c48349 // add r12, 1 -LBB2_172: - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x363b4466 // cmp r14w, word [rsi] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xff // mov rdi, r15 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3b // movzx r10d, byte [r11 + rdi] - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl - LONG $0x02c78349 // add r15, 2 - LONG $0x763b4466; BYTE $0x02 // cmp r14w, word [rsi + 2] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xdaf6 // neg dl - WORD $0xda30 // xor dl, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0xd830 // xor al, bl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x394d; BYTE $0xf9 // cmp r9, r15 - JNE LBB2_172 +LBB2_149: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_157 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x241c8844 // mov byte [rsp], r11b + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000f8248c8948 // mov qword [rsp + 248], rcx + JB LBB2_153 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB2_214 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB2_214 -LBB2_173: - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_177 - LONG $0x363b4466 // cmp r14w, word [rsi] - WORD $0x940f; BYTE $0xd0 // sete al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xfa // mov rdx, r15 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e78041 // and r15b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d +LBB2_153: + WORD $0xc031 // xor eax, eax + QUAD $0x000000d824848948 // mov qword [rsp + 216], rax + LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 -LBB2_175: - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil +LBB2_154: + QUAD $0x000000d8248c2b48 // sub rcx, qword [rsp + 216] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx -LBB2_176: - LONG $0x101c8841 // mov byte [r8 + rdx], bl +LBB2_155: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3a44; BYTE $0x1e // cmp r11b, byte [rsi] + QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x015e3a44 // cmp r11b, byte [rsi + 1] + LONG $0xd7940f40 // sete dil + LONG $0x025e3a44 // cmp r11b, byte [rsi + 2] + LONG $0xd3940f41 // sete r11b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x03 // cmp al, byte [rsi + 3] + LONG $0xd7940f41 // sete r15b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] + WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] + LONG $0xd4940f41 // sete r12b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] + LONG $0xd6940f40 // sete sil + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] + LONG $0xd0940f41 // sete r8b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] + LONG $0xd1940f41 // sete r9b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] + LONG $0xd6940f41 // sete r14b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + LONG $0xd5940f41 // sete r13b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + QUAD $0x000000b02494940f // sete byte [rsp + 176] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] + LONG $0xd2940f41 // sete r10b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0841; BYTE $0xfb // or r11b, dil + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x000000c024b40240 // add sil, byte [rsp + 192] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x1cb60f44; BYTE $0x24 // movzx r11d, byte [rsp] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xfb // or bl, r15b + WORD $0xd889 // mov eax, ebx + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xce // or r14b, r9b + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xf5 // or r13b, sil + WORD $0x0841; BYTE $0xdc // or r12b, bl + WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] + WORD $0x8844; BYTE $0x27 // mov byte [rdi], r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x016f8844 // mov byte [rdi + 1], r13b + WORD $0x0841; BYTE $0xda // or r10b, bl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd808 // or al, bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02578844 // mov byte [rdi + 2], r10b + WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + LONG $0x247c8948; BYTE $0x60 // mov qword [rsp + 96], rdi + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB2_155 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + JMP LBB2_158 -LBB2_177: - MOVQ 304(SP), SP - RET +LBB2_157: + LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 -LBB2_178: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xf631 // xor esi, esi - WORD $0x894d; BYTE $0xfe // mov r14, r15 +LBB2_158: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB2_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB2_174 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] -LBB2_179: - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9b0f; BYTE $0xd1 // setnp cl - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xca20 // and dl, cl - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi +LBB2_180: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e1c3a46 // cmp r11b, byte [rsi + r9] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] - WORD $0xf189 // mov ecx, esi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0xb341; BYTE $0x01 // mov r11b, 1 - WORD $0xd241; BYTE $0xe3 // shl r11b, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0x2041; BYTE $0xd3 // and r11b, dl - WORD $0x3045; BYTE $0xd3 // xor r11b, r10b - LONG $0x3e1c8845 // mov byte [r14 + rdi], r11b - LONG $0x02c68348 // add rsi, 2 - LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] - LONG $0x085b8d48 // lea rbx, [rbx + 8] - LONG $0xd29b0f41 // setnp r10b - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0x2044; BYTE $0xd2 // and dl, r10b - WORD $0xdaf6 // neg dl - WORD $0x3044; BYTE $0xda // xor dl, r11b + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x065c3a44; BYTE $0x01 // cmp r11b, byte [rsi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0x3044; BYTE $0xd8 // xor al, r11b + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x3949; BYTE $0xf1 // cmp r9, rsi - JNE LBB2_179 - -LBB2_180: - LONG $0x01c0f641 // test r8b, 1 - JE LBB2_177 - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9b0f; BYTE $0xd0 // setnp al - WORD $0x940f; BYTE $0xd2 // sete dl - WORD $0xc220 // and dl, al - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x03e8c148 // shr rax, 3 - LONG $0x073c8a41 // mov dil, byte [r15 + rax] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xfa // xor dl, dil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x071c8841 // mov byte [r15 + rax], bl - JMP LBB2_177 + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB2_180 + JMP LBB2_183 -LBB2_182: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000e024bc894c // mov qword [rsp + 224], r15 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - LONG $0xc6b60f41 // movzx eax, r14b - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 - WORD $0xc031 // xor eax, eax +LBB2_161: + WORD $0x8949; BYTE $0xd6 // mov r14, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB2_200 -LBB2_183: - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - LONG $0x05e7c148 // shl rdi, 5 - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - WORD $0x8949; BYTE $0xfa // mov r10, rdi - WORD $0x8949; BYTE $0xfe // mov r14, rdi - WORD $0x8949; BYTE $0xff // mov r15, rdi - WORD $0x8949; BYTE $0xfc // mov r12, rdi - WORD $0x8949; BYTE $0xfb // mov r11, rdi - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - WORD $0x8949; BYTE $0xf9 // mov r9, rdi - WORD $0x8948; BYTE $0xfb // mov rbx, rdi - LONG $0x247c8948; BYTE $0x50 // mov qword [rsp + 80], rdi - LONG $0x247c8948; BYTE $0x60 // mov qword [rsp + 96], rdi - LONG $0x3a0cb60f // movzx ecx, byte [rdx + rdi] - LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x3a4cb60f; BYTE $0x01 // movzx ecx, byte [rdx + rdi + 1] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x3a4cb60f; BYTE $0x02 // movzx ecx, byte [rdx + rdi + 2] - LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x3a4cb60f; BYTE $0x03 // movzx ecx, byte [rdx + rdi + 3] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x3a4cb60f; BYTE $0x04 // movzx ecx, byte [rdx + rdi + 4] - LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x3a4cb60f; BYTE $0x05 // movzx ecx, byte [rdx + rdi + 5] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x3a4cb60f; BYTE $0x06 // movzx ecx, byte [rdx + rdi + 6] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x3a4cb60f; BYTE $0x07 // movzx ecx, byte [rdx + rdi + 7] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 - LONG $0x3a4cb60f; BYTE $0x08 // movzx ecx, byte [rdx + rdi + 8] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 - LONG $0x3a4cb60f; BYTE $0x09 // movzx ecx, byte [rdx + rdi + 9] - LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x3a4cb60f; BYTE $0x0a // movzx ecx, byte [rdx + rdi + 10] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 - LONG $0x3a4cb60f; BYTE $0x0b // movzx ecx, byte [rdx + rdi + 11] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x3a4cb60f; BYTE $0x0c // movzx ecx, byte [rdx + rdi + 12] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x3a4cb60f; BYTE $0x0d // movzx ecx, byte [rdx + rdi + 13] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x3a4cb60f; BYTE $0x0e // movzx ecx, byte [rdx + rdi + 14] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x247c8948; BYTE $0x40 // mov qword [rsp + 64], rdi - WORD $0x8949; BYTE $0xfd // mov r13, rdi - LONG $0x20cd8349 // or r13, 32 - LONG $0x246c894c; BYTE $0x18 // mov qword [rsp + 24], r13 - LONG $0x40ce8348 // or rsi, 64 - LONG $0x24748948; BYTE $0x28 // mov qword [rsp + 40], rsi - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - LONG $0x60c98348 // or rcx, 96 - LONG $0x80ce8149; WORD $0x0000; BYTE $0x00 // or r14, 128 - LONG $0xa0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 160 - LONG $0xc0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 192 - LONG $0xe0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 224 - LONG $0x00cc8149; WORD $0x0001; BYTE $0x00 // or r12, 256 - LONG $0x20c98149; WORD $0x0001; BYTE $0x00 // or r9, 288 - LONG $0x244c894c; BYTE $0x48 // mov qword [rsp + 72], r9 - LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 - LONG $0x245c8948; BYTE $0x78 // mov qword [rsp + 120], rbx - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - LONG $0x60cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 352 - LONG $0x245c8948; BYTE $0x50 // mov qword [rsp + 80], rbx - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - LONG $0x80c88149; WORD $0x0001; BYTE $0x00 // or r8, 384 - LONG $0x2444894c; BYTE $0x60 // mov qword [rsp + 96], r8 - LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - QUAD $0x012a3c203a0f4666 // pinsrb xmm15, byte [rdx + r13], 1 - QUAD $0x02323c203a0f4466 // pinsrb xmm15, byte [rdx + rsi], 2 - LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx - QUAD $0x030a3c203a0f4466 // pinsrb xmm15, byte [rdx + rcx], 3 - LONG $0x2474894c; BYTE $0x70 // mov qword [rsp + 112], r14 - QUAD $0x04323c203a0f4666 // pinsrb xmm15, byte [rdx + r14], 4 - QUAD $0x0000008024bc894c // mov qword [rsp + 128], r15 - QUAD $0x053a3c203a0f4666 // pinsrb xmm15, byte [rdx + r15], 5 - WORD $0x894c; BYTE $0xd7 // mov rdi, r10 - QUAD $0x06123c203a0f4666 // pinsrb xmm15, byte [rdx + r10], 6 - WORD $0x894d; BYTE $0xda // mov r10, r11 - LONG $0x245c894c; BYTE $0x58 // mov qword [rsp + 88], r11 - QUAD $0x071a3c203a0f4666 // pinsrb xmm15, byte [rdx + r11], 7 - QUAD $0x08223c203a0f4666 // pinsrb xmm15, byte [rdx + r12], 8 - QUAD $0x090a3c203a0f4666 // pinsrb xmm15, byte [rdx + r9], 9 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x0a2a3c203a0f4666 // pinsrb xmm15, byte [rdx + r13], 10 - QUAD $0x0b1a3c203a0f4466 // pinsrb xmm15, byte [rdx + rbx], 11 - QUAD $0x0c023c203a0f4666 // pinsrb xmm15, byte [rdx + r8], 12 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0d323c203a0f4466 // pinsrb xmm15, byte [rdx + rsi], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e323c203a0f4466 // pinsrb xmm15, byte [rdx + rsi], 14 - QUAD $0x0f023c203a0f4466 // pinsrb xmm15, byte [rdx + rax], 15 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - QUAD $0x011a6c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdx + r11 + 1], 1 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0201326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 1], 2 - QUAD $0x03010a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 1], 3 - QUAD $0x01326c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdx + r14 + 1], 4 - QUAD $0x013a6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rdx + r15 + 1], 5 - QUAD $0x06013a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 1], 6 - QUAD $0x01126c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r10 + 1], 7 - QUAD $0x01226c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r12 + 1], 8 - WORD $0x894d; BYTE $0xe6 // mov r14, r12 - QUAD $0x000000c024a4894c // mov qword [rsp + 192], r12 - QUAD $0x010a6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r9 + 1], 9 - QUAD $0x012a6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r13 + 1], 10 - WORD $0x894d; BYTE $0xef // mov r15, r13 - QUAD $0x0b011a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 1], 11 - QUAD $0x01026c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r8 + 1], 12 - LONG $0x244c8b4c; BYTE $0x10 // mov r9, qword [rsp + 16] - QUAD $0x010a6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdx + r9 + 1], 13 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x011a6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdx + r11 + 1], 14 - QUAD $0x0f01026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 1], 15 - QUAD $0x00b0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 - LONG $0xfd6f0f66 // movdqa xmm7, xmm5 - QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI2_10] */ - LONG $0xfcdb0f66 // pand xmm7, xmm4 - LONG $0xfdf80f66 // psubb xmm7, xmm5 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - LONG $0x74b60f42; WORD $0x0f22 // movzx esi, byte [rdx + r12 + 15] - LONG $0x6e0f4466; BYTE $0xf6 // movd xmm14, esi - LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x020274203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdx + r8 + 2], 1 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x021274203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdx + r10 + 2], 2 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x03020a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 2], 3 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x04021a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 2], 4 - QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] - QUAD $0x05023274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 2], 5 - QUAD $0x06023a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 2], 6 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x07023274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 2], 7 - QUAD $0x023274203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r14 + 2], 8 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x022a74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r13 + 2], 9 - QUAD $0x023a74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r15 + 2], 10 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x023274203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r14 + 2], 11 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x023a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r15 + 2], 12 - QUAD $0x020a74203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdx + r9 + 2], 13 - QUAD $0x021a74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdx + r11 + 2], 14 - WORD $0x8949; BYTE $0xc1 // mov r9, rax - QUAD $0x0f020274203a0f66 // pinsrb xmm6, byte [rdx + rax + 2], 15 - LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 - LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 - QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xf0db0f66 // pand xmm6, xmm0 - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x74b60f42; WORD $0x1022 // movzx esi, byte [rdx + r12 + 16] - LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - WORD $0x894c; BYTE $0xc6 // mov rsi, r8 - QUAD $0x030254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r8 + 3], 1 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x031254203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r10 + 3], 2 - QUAD $0x03030a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 3], 3 - QUAD $0x04031a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 3], 4 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x05030a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 3], 5 - QUAD $0x0000008824bc8948 // mov qword [rsp + 136], rdi - QUAD $0x06033a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 3], 6 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x030254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r8 + 3], 7 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x031254203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r10 + 3], 8 - QUAD $0x032a54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r13 + 3], 9 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0a031a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 3], 10 - QUAD $0x033254203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r14 + 3], 11 - QUAD $0x033a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r15 + 3], 12 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x032254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r12 + 3], 13 - QUAD $0x031a54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r11 + 3], 14 - QUAD $0x030a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r9 + 3], 15 - QUAD $0x0104324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 4], 1 - QUAD $0x0204024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 4], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0304324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 4], 3 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0404324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 4], 4 - QUAD $0x05040a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 4], 5 - QUAD $0x06043a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 4], 6 - QUAD $0x04024c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r8 + 4], 7 - QUAD $0x04124c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r10 + 4], 8 - QUAD $0x042a4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdx + r13 + 4], 9 - QUAD $0x0a041a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 4], 10 - QUAD $0x04324c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdx + r14 + 4], 11 - QUAD $0x043a4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r15 + 4], 12 - QUAD $0x04224c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdx + r12 + 4], 13 - QUAD $0x041a4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r11 + 4], 14 - QUAD $0x040a4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r9 + 4], 15 - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - LONG $0x244c894c; BYTE $0x20 // mov qword [rsp + 32], r9 - LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - LONG $0x74b60f42; WORD $0x110a // movzx esi, byte [rdx + r9 + 17] - LONG $0xc66e0f66 // movd xmm0, esi - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0xd5db0f66 // pand xmm2, xmm5 - LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 - QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xcddb0f66 // pand xmm1, xmm5 - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0x74b60f42; WORD $0x120a // movzx esi, byte [rdx + r9 + 18] - LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x052a44203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rdx + r13 + 5], 1 - QUAD $0x050244203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdx + rax + 5], 2 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x051a44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r11 + 5], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x050244203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rdx + rax + 5], 4 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x053a44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdx + rdi + 5], 5 - QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] - QUAD $0x050244203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdx + r8 + 5], 6 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x051244203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdx + r10 + 5], 7 - QUAD $0x000000c0249c8b48 // mov rbx, qword [rsp + 192] - QUAD $0x051a44203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rdx + rbx + 5], 8 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x053244203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdx + rsi + 5], 9 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x053244203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdx + r14 + 5], 10 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x053a44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r15 + 5], 11 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x052244203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdx + r12 + 5], 12 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x053244203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdx + rsi + 5], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x053244203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdx + rsi + 5], 14 - QUAD $0x050a44203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rdx + rcx + 5], 15 - LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 - QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI2_14] */ - LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0x74b60f42; WORD $0x130a // movzx esi, byte [rdx + r9 + 19] - LONG $0xfe6e0f66 // movd xmm7, esi - LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - LONG $0x74b60f42; WORD $0x140a // movzx esi, byte [rdx + r9 + 20] - LONG $0xf66e0f66 // movd xmm6, esi - QUAD $0x062a5c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdx + r13 + 6], 1 - LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] - QUAD $0x060a5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdx + r9 + 6], 2 - QUAD $0x061a5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r11 + 6], 3 - QUAD $0x0406025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 6], 4 - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - QUAD $0x05063a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 6], 5 - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - QUAD $0x06025c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdx + r8 + 6], 6 - QUAD $0x06125c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdx + r10 + 6], 7 - WORD $0x8949; BYTE $0xda // mov r10, rbx - QUAD $0x08061a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 6], 8 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0906025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 6], 9 - WORD $0x894c; BYTE $0xf3 // mov rbx, r14 - QUAD $0x06325c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r14 + 6], 10 - WORD $0x894c; BYTE $0xfe // mov rsi, r15 - QUAD $0x063a5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r15 + 6], 11 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - QUAD $0x06225c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r12 + 6], 12 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x06225c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdx + r12 + 6], 13 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x06325c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdx + r14 + 6], 14 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x06025c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r8 + 6], 15 - QUAD $0x0000d024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 208] - QUAD $0x072a54203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r13 + 7], 1 - QUAD $0x070a54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r9 + 7], 2 - QUAD $0x071a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r11 + 7], 3 - WORD $0x894d; BYTE $0xdd // mov r13, r11 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x070a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r9 + 7], 4 - QUAD $0x05070a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 7], 5 - QUAD $0x06073a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 7], 6 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x07070a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 7], 7 - QUAD $0x071254203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r10 + 7], 8 - QUAD $0x09070254203a0f66 // pinsrb xmm2, byte [rdx + rax + 7], 9 - QUAD $0x0a071a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 7], 10 - QUAD $0x0b073254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 7], 11 - QUAD $0x073a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r15 + 7], 12 - QUAD $0x072254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r12 + 7], 13 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - QUAD $0x073254203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r14 + 7], 14 - QUAD $0x070254203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r8 + 7], 15 - LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 - QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI2_15] */ - LONG $0xd9db0f66 // pand xmm3, xmm1 - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 - LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI2_6] */ - LONG $0xd1db0f66 // pand xmm2, xmm1 - LONG $0xd3eb0f66 // por xmm2, xmm3 - LONG $0xca6f0f66 // movdqa xmm1, xmm2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - LONG $0x0274b60f; BYTE $0x15 // movzx esi, byte [rdx + rax + 21] - LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x090a54203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdx + rcx + 9], 1 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x091a54203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdx + r11 + 9], 2 - QUAD $0x092a54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r13 + 9], 3 - QUAD $0x090a54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r9 + 9], 4 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x092a54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdx + r13 + 9], 5 - QUAD $0x093a54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rdx + rdi + 9], 6 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x090254203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdx + r8 + 9], 7 - QUAD $0x091254203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r10 + 9], 8 - WORD $0x894d; BYTE $0xd6 // mov r14, r10 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x093254203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rsi + 9], 9 - QUAD $0x091a54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdx + rbx + 9], 10 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x091254203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdx + r10 + 9], 11 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x091a54203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdx + rbx + 9], 12 - QUAD $0x093a54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdx + r15 + 9], 13 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x093a54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rdx + rdi + 9], 14 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x093254203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdx + rsi + 9], 15 - LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 - LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 - LONG $0xccdb0f66 // pand xmm1, xmm4 - LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 - LONG $0x0274b60f; BYTE $0x16 // movzx esi, byte [rdx + rax + 22] - LONG $0xde6e0f66 // movd xmm3, esi - QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] - QUAD $0x01080a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 8], 1 - QUAD $0x081a64203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdx + r11 + 8], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x03080264203a0f66 // pinsrb xmm4, byte [rdx + rax + 8], 3 - QUAD $0x080a64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r9 + 8], 4 - QUAD $0x082a64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdx + r13 + 8], 5 - QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] - QUAD $0x083a64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdx + r15 + 8], 6 - QUAD $0x080264203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r8 + 8], 7 - QUAD $0x083264203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r14 + 8], 8 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x09083264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 8], 9 - QUAD $0x082264203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdx + r12 + 8], 10 - QUAD $0x081264203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r10 + 8], 11 - QUAD $0x0c081a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 8], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0d081a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 8], 13 - QUAD $0x0e083a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 8], 14 - WORD $0x8949; BYTE $0xfa // mov r10, rdi - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0f080a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 8], 15 - LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 - LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 - QUAD $0x00a024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 160] - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x0a3a54203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdx + rdi + 10], 1 - QUAD $0x0a1a54203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdx + r11 + 10], 2 - QUAD $0x0a0254203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdx + rax + 10], 3 - QUAD $0x0a0a54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r9 + 10], 4 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - QUAD $0x0a2a54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdx + r13 + 10], 5 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - QUAD $0x0a3a54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r15 + 10], 6 - QUAD $0x0a0254203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdx + r8 + 10], 7 - QUAD $0x0a3254203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r14 + 10], 8 - QUAD $0x0a3254203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rsi + 10], 9 - QUAD $0x0a2254203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdx + r12 + 10], 10 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0a3254203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdx + r14 + 10], 11 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x0a3a54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdx + r15 + 10], 12 - QUAD $0x0a1a54203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdx + rbx + 10], 13 - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x0a1254203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r10 + 10], 14 - QUAD $0x0a0a54203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdx + rcx + 10], 15 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - LONG $0x0a74b60f; BYTE $0x17 // movzx esi, byte [rdx + rcx + 23] - LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi - LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - QUAD $0x00a024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm10 - LONG $0x0a74b60f; BYTE $0x18 // movzx esi, byte [rdx + rcx + 24] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - QUAD $0x0b3a5c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdx + rdi + 11], 1 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0b0a5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rcx + 11], 2 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0b0a5c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rdx + rcx + 11], 3 - QUAD $0x0b025c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdx + rax + 11], 4 - WORD $0x894c; BYTE $0xd9 // mov rcx, r11 - QUAD $0x0b1a5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdx + r11 + 11], 5 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - QUAD $0x0b0a5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r9 + 11], 6 - QUAD $0x0b025c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdx + r8 + 11], 7 - QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] - QUAD $0x0b0a5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r9 + 11], 8 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x0b1a5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdx + r11 + 11], 9 - QUAD $0x0b225c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdx + r12 + 11], 10 - QUAD $0x0b325c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r14 + 11], 11 - QUAD $0x0b3a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r15 + 11], 12 - WORD $0x8949; BYTE $0xda // mov r10, rbx - QUAD $0x0b1a5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdx + rbx + 11], 13 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x0b225c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r12 + 11], 14 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0b325c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdx + rsi + 11], 15 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x0c2a6c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rdx + r13 + 12], 1 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0c1a6c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rbx + 12], 2 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0c1a6c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rdx + rbx + 12], 3 - QUAD $0x0c026c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdx + rax + 12], 4 - QUAD $0x0c0a6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdx + rcx + 12], 5 - QUAD $0x0c3a6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rdx + rdi + 12], 6 - QUAD $0x0c026c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdx + r8 + 12], 7 - QUAD $0x0c0a6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r9 + 12], 8 - QUAD $0x0c1a6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdx + r11 + 12], 9 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x0c1a6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdx + rbx + 12], 10 - QUAD $0x0c326c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdx + r14 + 12], 11 - QUAD $0x0c3a6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r15 + 12], 12 - QUAD $0x0c126c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdx + r10 + 12], 13 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x0c226c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r12 + 12], 14 - QUAD $0x0c326c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdx + rsi + 12], 15 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x0d1264203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdx + r10 + 13], 1 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0d3264203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rsi + 13], 2 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0d3264203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdx + rsi + 13], 3 - QUAD $0x0d0264203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdx + rax + 13], 4 - QUAD $0x0d0a64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdx + rcx + 13], 5 - QUAD $0x0d3a64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rdx + rdi + 13], 6 - QUAD $0x0d0264203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdx + r8 + 13], 7 - QUAD $0x0d0a64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r9 + 13], 8 - QUAD $0x0d1a64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdx + r11 + 13], 9 - QUAD $0x0d1a64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdx + rbx + 13], 10 - QUAD $0x0d3264203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdx + r14 + 13], 11 - QUAD $0x0d3a64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdx + r15 + 13], 12 - QUAD $0x0d2a64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdx + r13 + 13], 13 - QUAD $0x0d2264203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r12 + 13], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d0264203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdx + rax + 13], 15 - LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 - QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 - QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - LONG $0x0274b60f; BYTE $0x19 // movzx esi, byte [rdx + rax + 25] - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 - QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI2_14] */ - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0x0274b60f; BYTE $0x1a // movzx esi, byte [rdx + rax + 26] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - QUAD $0x0000f024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 240] - QUAD $0x0e1264203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdx + r10 + 14], 1 - WORD $0x894c; BYTE $0xd6 // mov rsi, r10 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x0e2264203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdx + r12 + 14], 2 - LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] - QUAD $0x0e1264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r10 + 14], 3 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x0e2a64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r13 + 14], 4 - QUAD $0x050e0a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 14], 5 - QUAD $0x060e3a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 14], 6 - QUAD $0x0e0264203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r8 + 14], 7 - QUAD $0x0e0a64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r9 + 14], 8 - QUAD $0x0e1a64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r11 + 14], 9 - QUAD $0x0a0e1a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 14], 10 - QUAD $0x0e3264203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r14 + 14], 11 - QUAD $0x0e3a64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r15 + 14], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d0e0264203a0f66 // pinsrb xmm4, byte [rdx + rax + 14], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0e0e0264203a0f66 // pinsrb xmm4, byte [rdx + rax + 14], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0e0264203a0f66 // pinsrb xmm4, byte [rdx + rax + 14], 15 - QUAD $0x0f3274203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdx + rsi + 15], 1 - QUAD $0x0f2274203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdx + r12 + 15], 2 - QUAD $0x0f1274203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdx + r10 + 15], 3 - QUAD $0x0f2a74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rdx + r13 + 15], 4 - QUAD $0x0f0a74203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdx + rcx + 15], 5 - QUAD $0x0f3a74203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rdx + rdi + 15], 6 - QUAD $0x0f0274203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdx + r8 + 15], 7 - QUAD $0x0f0a74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdx + r9 + 15], 8 - QUAD $0x0f1a74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rdx + r11 + 15], 9 - QUAD $0x0f1a74203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdx + rbx + 15], 10 - QUAD $0x0f3274203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdx + r14 + 15], 11 - QUAD $0x0f3a74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdx + r15 + 15], 12 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0f3274203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdx + rsi + 15], 13 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0274203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rdx + rax + 15], 14 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0f3274203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdx + rsi + 15], 15 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x10327c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rsi + 16], 1 - QUAD $0x10227c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rdx + r12 + 16], 2 - QUAD $0x10127c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r10 + 16], 3 - QUAD $0x102a7c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdx + r13 + 16], 4 - QUAD $0x100a7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdx + rcx + 16], 5 - QUAD $0x103a7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rdx + rdi + 16], 6 - QUAD $0x10027c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r8 + 16], 7 - QUAD $0x100a7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdx + r9 + 16], 8 - QUAD $0x101a7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdx + r11 + 16], 9 - QUAD $0x101a7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdx + rbx + 16], 10 - QUAD $0x10327c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdx + r14 + 16], 11 - QUAD $0x103a7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdx + r15 + 16], 12 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x10327c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdx + rsi + 16], 13 - QUAD $0x10027c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdx + rax + 16], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x01110244203a0f66 // pinsrb xmm0, byte [rdx + rax + 17], 1 - QUAD $0x112244203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdx + r12 + 17], 2 - QUAD $0x111244203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r10 + 17], 3 - QUAD $0x112a44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdx + r13 + 17], 4 - QUAD $0x05110a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 17], 5 - QUAD $0x06113a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 17], 6 - QUAD $0x110244203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r8 + 17], 7 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x110a44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r9 + 17], 8 - QUAD $0x111a44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdx + r11 + 17], 9 - QUAD $0x0a111a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 17], 10 - QUAD $0x113244203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r14 + 17], 11 - QUAD $0x113a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r15 + 17], 12 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0d113244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 17], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e113244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 17], 14 - QUAD $0x00a024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 160] - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - LONG $0x74b60f42; WORD $0x1b22 // movzx esi, byte [rdx + r12 + 27] - LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - QUAD $0x00b024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 - QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI2_15] */ - LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 - LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 - LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI2_6] */ - LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 - LONG $0x74b60f42; WORD $0x1c22 // movzx esi, byte [rdx + r12 + 28] - LONG $0xe66e0f66 // movd xmm4, esi - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x110244203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r8 + 17], 15 - LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 - LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 - LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 - QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI2_10] */ - LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 - LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 - QUAD $0x00a024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm13 - LONG $0x74b60f42; WORD $0x1d22 // movzx esi, byte [rdx + r12 + 29] - LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi - QUAD $0x10027c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdx + r8 + 16], 15 - QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] - LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 - LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] - QUAD $0x12226c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdx + r12 + 18], 1 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0212326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 18], 2 - QUAD $0x12126c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r10 + 18], 3 - QUAD $0x122a6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdx + r13 + 18], 4 - QUAD $0x05120a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 18], 5 - QUAD $0x06123a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 18], 6 - QUAD $0x0712026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 18], 7 - QUAD $0x120a6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r9 + 18], 8 - QUAD $0x121a6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r11 + 18], 9 - QUAD $0x0a121a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 18], 10 - QUAD $0x12326c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdx + r14 + 18], 11 - QUAD $0x123a6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r15 + 18], 12 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0d12326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 18], 13 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0e12326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 18], 14 - LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 - QUAD $0x12026c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdx + r8 + 18], 15 - LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 - QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - LONG $0x0274b60f; BYTE $0x1e // movzx esi, byte [rdx + rax + 30] - LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - QUAD $0x13227c203a0f4266; BYTE $0x01 // pinsrb xmm7, byte [rdx + r12 + 19], 1 - QUAD $0x142274203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdx + r12 + 20], 1 - QUAD $0x152254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r12 + 21], 1 - QUAD $0x16225c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdx + r12 + 22], 1 - QUAD $0x172244203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rdx + r12 + 23], 1 - QUAD $0x182254203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdx + r12 + 24], 1 - QUAD $0x19224c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rdx + r12 + 25], 1 - QUAD $0x1a225c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdx + r12 + 26], 1 - QUAD $0x1b224c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rdx + r12 + 27], 1 - QUAD $0x1c2264203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdx + r12 + 28], 1 - QUAD $0x1d226c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rdx + r12 + 29], 1 - QUAD $0x1e2264203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdx + r12 + 30], 1 - LONG $0x0274b60f; BYTE $0x1f // movzx esi, byte [rdx + rax + 31] - LONG $0xc66e0f66 // movd xmm0, esi - QUAD $0x1f2244203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdx + r12 + 31], 1 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0213327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 19], 2 - QUAD $0x02143274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 20], 2 - QUAD $0x02153254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 21], 2 - QUAD $0x0216325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 22], 2 - QUAD $0x173244203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdx + rsi + 23], 2 - QUAD $0x183254203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdx + rsi + 24], 2 - QUAD $0x0219324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 25], 2 - QUAD $0x1a325c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rsi + 26], 2 - QUAD $0x1b324c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rsi + 27], 2 - QUAD $0x021c3264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 28], 2 - QUAD $0x1d326c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rsi + 29], 2 - QUAD $0x1e3264203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rsi + 30], 2 - QUAD $0x021f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 31], 2 - QUAD $0x13127c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r10 + 19], 3 - QUAD $0x132a7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdx + r13 + 19], 4 - QUAD $0x05130a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 19], 5 - QUAD $0x06133a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 19], 6 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0713027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 19], 7 - QUAD $0x130a7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdx + r9 + 19], 8 - QUAD $0x131a7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdx + r11 + 19], 9 - QUAD $0x0a131a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 19], 10 - QUAD $0x13327c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdx + r14 + 19], 11 - QUAD $0x133a7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r15 + 19], 12 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0d13327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 19], 13 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x13227c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdx + r12 + 19], 14 - QUAD $0x13027c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdx + r8 + 19], 15 - QUAD $0x141274203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r10 + 20], 3 - QUAD $0x142a74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdx + r13 + 20], 4 - QUAD $0x05140a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 20], 5 - QUAD $0x06143a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 20], 6 - QUAD $0x07140274203a0f66 // pinsrb xmm6, byte [rdx + rax + 20], 7 - QUAD $0x140a74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r9 + 20], 8 - QUAD $0x141a74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r11 + 20], 9 - QUAD $0x0a141a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 20], 10 - QUAD $0x143274203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r14 + 20], 11 - QUAD $0x143a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r15 + 20], 12 - QUAD $0x0d143274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 20], 13 - QUAD $0x142274203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdx + r12 + 20], 14 - QUAD $0x0000a024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 160] - QUAD $0x140274203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdx + r8 + 20], 15 - QUAD $0x00b024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 - QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 - QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0x151254203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r10 + 21], 3 - QUAD $0x152a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r13 + 21], 4 - QUAD $0x05150a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 21], 5 - QUAD $0x06153a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 21], 6 - QUAD $0x07150254203a0f66 // pinsrb xmm2, byte [rdx + rax + 21], 7 - QUAD $0x150a54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r9 + 21], 8 - QUAD $0x151a54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r11 + 21], 9 - QUAD $0x0a151a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 21], 10 - QUAD $0x153254203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r14 + 21], 11 - QUAD $0x153a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r15 + 21], 12 - QUAD $0x0d153254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 21], 13 - QUAD $0x152254203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r12 + 21], 14 - QUAD $0x150254203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r8 + 21], 15 - LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 - QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI2_14] */ - LONG $0xd7db0f66 // pand xmm2, xmm7 - LONG $0xd6eb0f66 // por xmm2, xmm6 - LONG $0xd5eb0f66 // por xmm2, xmm5 - QUAD $0x16125c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r10 + 22], 3 - QUAD $0x162a5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdx + r13 + 22], 4 - QUAD $0x05160a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 22], 5 - QUAD $0x06163a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 22], 6 - QUAD $0x0716025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 22], 7 - QUAD $0x160a5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdx + r9 + 22], 8 - QUAD $0x161a5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdx + r11 + 22], 9 - QUAD $0x0a161a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 22], 10 - QUAD $0x16325c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r14 + 22], 11 - QUAD $0x163a5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r15 + 22], 12 - QUAD $0x0d16325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 22], 13 - QUAD $0x16225c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdx + r12 + 22], 14 - QUAD $0x16025c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r8 + 22], 15 - QUAD $0x171244203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r10 + 23], 3 - QUAD $0x172a44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdx + r13 + 23], 4 - QUAD $0x170a44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdx + rcx + 23], 5 - QUAD $0x173a44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rdx + rdi + 23], 6 - QUAD $0x170244203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rdx + rax + 23], 7 - QUAD $0x170a44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdx + r9 + 23], 8 - QUAD $0x171a44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdx + r11 + 23], 9 - QUAD $0x171a44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdx + rbx + 23], 10 - QUAD $0x173244203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r14 + 23], 11 - QUAD $0x173a44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdx + r15 + 23], 12 - QUAD $0x173244203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdx + rsi + 23], 13 - QUAD $0x172244203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdx + r12 + 23], 14 - QUAD $0x170244203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdx + r8 + 23], 15 - LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 - QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI2_15] */ - LONG $0xdddb0f66 // pand xmm3, xmm5 - LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 - LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 - LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI2_6] */ - LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 - LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - QUAD $0x19124c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r10 + 25], 3 - QUAD $0x192a4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdx + r13 + 25], 4 - QUAD $0x05190a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 25], 5 - QUAD $0x06193a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 25], 6 - QUAD $0x0719024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 25], 7 - QUAD $0x190a4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r9 + 25], 8 - QUAD $0x191a4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdx + r11 + 25], 9 - QUAD $0x0a191a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 25], 10 - QUAD $0x19324c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdx + r14 + 25], 11 - QUAD $0x193a4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r15 + 25], 12 - QUAD $0x0d19324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 25], 13 - QUAD $0x19224c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r12 + 25], 14 - QUAD $0x19024c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r8 + 25], 15 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 - LONG $0xd16f0f66 // movdqa xmm2, xmm1 - QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI2_10] */ - LONG $0xd3db0f66 // pand xmm2, xmm3 - LONG $0xd1f80f66 // psubb xmm2, xmm1 - QUAD $0x181254203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r10 + 24], 3 - QUAD $0x182a54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r13 + 24], 4 - QUAD $0x180a54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdx + rcx + 24], 5 - QUAD $0x183a54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rdx + rdi + 24], 6 - QUAD $0x180254203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rdx + rax + 24], 7 - QUAD $0x180a54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r9 + 24], 8 - QUAD $0x181a54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdx + r11 + 24], 9 - QUAD $0x181a54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdx + rbx + 24], 10 - QUAD $0x183254203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdx + r14 + 24], 11 - QUAD $0x183a54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdx + r15 + 24], 12 - QUAD $0x183254203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdx + rsi + 24], 13 - QUAD $0x182254203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r12 + 24], 14 - QUAD $0x180254203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdx + r8 + 24], 15 - LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 - LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 - QUAD $0x1a125c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r10 + 26], 3 - QUAD $0x1a2a5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdx + r13 + 26], 4 - QUAD $0x1a0a5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdx + rcx + 26], 5 - QUAD $0x1a3a5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rdx + rdi + 26], 6 - QUAD $0x1a025c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rdx + rax + 26], 7 - QUAD $0x1a0a5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r9 + 26], 8 - QUAD $0x1a1a5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdx + r11 + 26], 9 - QUAD $0x1a1a5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdx + rbx + 26], 10 - QUAD $0x1a325c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r14 + 26], 11 - QUAD $0x1a3a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r15 + 26], 12 - QUAD $0x1a325c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdx + rsi + 26], 13 - QUAD $0x1a225c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r12 + 26], 14 - QUAD $0x1a025c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdx + r8 + 26], 15 - LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 - QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 - LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 - QUAD $0x1b124c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdx + r10 + 27], 3 - QUAD $0x1b2a4c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdx + r13 + 27], 4 - QUAD $0x1b0a4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdx + rcx + 27], 5 - QUAD $0x1b3a4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rdx + rdi + 27], 6 - QUAD $0x1b024c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rdx + rax + 27], 7 - QUAD $0x1b0a4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r9 + 27], 8 - QUAD $0x1b1a4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdx + r11 + 27], 9 - QUAD $0x1b1a4c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rdx + rbx + 27], 10 - QUAD $0x1b324c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdx + r14 + 27], 11 - QUAD $0x1b3a4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdx + r15 + 27], 12 - QUAD $0x1b324c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdx + rsi + 27], 13 - QUAD $0x1b224c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r12 + 27], 14 - QUAD $0x1b024c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdx + r8 + 27], 15 - QUAD $0x1c1264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r10 + 28], 3 - QUAD $0x1c2a64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r13 + 28], 4 - QUAD $0x051c0a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 28], 5 - QUAD $0x061c3a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 28], 6 - QUAD $0x071c0264203a0f66 // pinsrb xmm4, byte [rdx + rax + 28], 7 - QUAD $0x1c0a64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r9 + 28], 8 - QUAD $0x1c1a64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r11 + 28], 9 - QUAD $0x0a1c1a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 28], 10 - QUAD $0x1c3264203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r14 + 28], 11 - QUAD $0x1c3a64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r15 + 28], 12 - QUAD $0x0d1c3264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 28], 13 - QUAD $0x1c2264203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdx + r12 + 28], 14 - QUAD $0x1c0264203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdx + r8 + 28], 15 - QUAD $0x1d126c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdx + r10 + 29], 3 - QUAD $0x1d2a6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdx + r13 + 29], 4 - QUAD $0x1d0a6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdx + rcx + 29], 5 - QUAD $0x1d3a6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rdx + rdi + 29], 6 - QUAD $0x1d026c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rdx + rax + 29], 7 - QUAD $0x1d0a6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r9 + 29], 8 - QUAD $0x1d1a6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdx + r11 + 29], 9 - QUAD $0x1d1a6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdx + rbx + 29], 10 - QUAD $0x1d326c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdx + r14 + 29], 11 - QUAD $0x1d3a6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r15 + 29], 12 - QUAD $0x1d326c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rdx + rsi + 29], 13 - QUAD $0x1d226c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r12 + 29], 14 - LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 - LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 - QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 - QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 - QUAD $0x1d026c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdx + r8 + 29], 15 - LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 - LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 - LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 - QUAD $0x1e1264203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r10 + 30], 3 - QUAD $0x1f1244203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r10 + 31], 3 - QUAD $0x1e2a64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdx + r13 + 30], 4 - QUAD $0x1f2a44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdx + r13 + 31], 4 - QUAD $0x1e0a64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdx + rcx + 30], 5 - QUAD $0x051f0a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 31], 5 - QUAD $0x1e3a64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rdx + rdi + 30], 6 - QUAD $0x061f3a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 31], 6 - QUAD $0x1e0264203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rdx + rax + 30], 7 - QUAD $0x071f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 31], 7 - QUAD $0x1e0a64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r9 + 30], 8 - QUAD $0x1f0a44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r9 + 31], 8 - QUAD $0x1e1a64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdx + r11 + 30], 9 - QUAD $0x1f1a44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdx + r11 + 31], 9 - QUAD $0x1e1a64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdx + rbx + 30], 10 - QUAD $0x0a1f1a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 31], 10 - QUAD $0x1e3264203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdx + r14 + 30], 11 - QUAD $0x1f3244203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r14 + 31], 11 - QUAD $0x1e3a64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdx + r15 + 30], 12 - QUAD $0x1f3a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r15 + 31], 12 - QUAD $0x1e3264203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdx + rsi + 30], 13 - QUAD $0x0d1f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 31], 13 - QUAD $0x1e2264203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r12 + 30], 14 - QUAD $0x1f2244203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdx + r12 + 31], 14 - QUAD $0x1e0264203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdx + r8 + 30], 15 - QUAD $0x1f0244203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r8 + 31], 15 - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 - LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 - LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0xc6db0f66 // pand xmm0, xmm6 - LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 - LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 - LONG $0xc8600f66 // punpcklbw xmm1, xmm0 - QUAD $0x0000d024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 208] - LONG $0xd46f0f66 // movdqa xmm2, xmm4 - LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 - LONG $0xda6f0f66 // movdqa xmm3, xmm2 - LONG $0xd9610f66 // punpcklwd xmm3, xmm1 - LONG $0xd1690f66 // punpckhwd xmm2, xmm1 - LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 - LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x647f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm4 - LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 - LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 - LONG $0x1c7f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm3 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e0248c3b48 // cmp rcx, qword [rsp + 224] - JNE LBB2_183 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x000000e024bc3b4c // cmp r15, qword [rsp + 224] - LONG $0x24748a44; BYTE $0x08 // mov r14b, byte [rsp + 8] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - JNE LBB2_43 - JMP LBB2_131 +LBB2_162: + LONG $0x01c48349 // add r12, 1 -LBB2_185: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000e024bc894c // mov qword [rsp + 224], r15 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - LONG $0xc6b60f41 // movzx eax, r14b - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 - WORD $0xc031 // xor eax, eax +LBB2_163: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB2_171 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x241c8844 // mov byte [rsp], r11b + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000f8248c8948 // mov qword [rsp + 248], rcx + JB LBB2_167 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB2_217 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB2_217 -LBB2_186: - WORD $0x8949; BYTE $0xc7 // mov r15, rax - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - LONG $0x05e7c149 // shl r15, 5 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 - WORD $0x894c; BYTE $0xff // mov rdi, r15 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - WORD $0x894d; BYTE $0xfb // mov r11, r15 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x894d; BYTE $0xfa // mov r10, r15 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x34b60f42; BYTE $0x3a // movzx esi, byte [rdx + r15] - LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - LONG $0x74b60f42; WORD $0x013a // movzx esi, byte [rdx + r15 + 1] - LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x74b60f42; WORD $0x023a // movzx esi, byte [rdx + r15 + 2] - LONG $0xf66e0f66 // movd xmm6, esi - LONG $0x74b60f42; WORD $0x033a // movzx esi, byte [rdx + r15 + 3] - LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x74b60f42; WORD $0x043a // movzx esi, byte [rdx + r15 + 4] - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x74b60f42; WORD $0x053a // movzx esi, byte [rdx + r15 + 5] - LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi - LONG $0x74b60f42; WORD $0x063a // movzx esi, byte [rdx + r15 + 6] - LONG $0xde6e0f66 // movd xmm3, esi - LONG $0x74b60f42; WORD $0x073a // movzx esi, byte [rdx + r15 + 7] - LONG $0xc66e0f66 // movd xmm0, esi - QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 - LONG $0x74b60f42; WORD $0x083a // movzx esi, byte [rdx + r15 + 8] - LONG $0xc66e0f66 // movd xmm0, esi - QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x74b60f42; WORD $0x093a // movzx esi, byte [rdx + r15 + 9] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0x74b60f42; WORD $0x0a3a // movzx esi, byte [rdx + r15 + 10] - LONG $0xc66e0f66 // movd xmm0, esi - QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 - LONG $0x74b60f42; WORD $0x0b3a // movzx esi, byte [rdx + r15 + 11] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - LONG $0x74b60f42; WORD $0x0c3a // movzx esi, byte [rdx + r15 + 12] - LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi - LONG $0x74b60f42; WORD $0x0d3a // movzx esi, byte [rdx + r15 + 13] - LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - LONG $0x74b60f42; WORD $0x0e3a // movzx esi, byte [rdx + r15 + 14] - LONG $0xc66e0f66 // movd xmm0, esi - QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - LONG $0x20ce8349 // or r14, 32 - LONG $0x2474894c; BYTE $0x10 // mov qword [rsp + 16], r14 - LONG $0x40cb8348 // or rbx, 64 - LONG $0x245c8948; BYTE $0x48 // mov qword [rsp + 72], rbx - LONG $0x60c88348 // or rax, 96 - LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax - LONG $0x80c98148; WORD $0x0000; BYTE $0x00 // or rcx, 128 - LONG $0xa0cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 160 - LONG $0xc0c88149; WORD $0x0000; BYTE $0x00 // or r8, 192 - LONG $0xe0c98149; WORD $0x0000; BYTE $0x00 // or r9, 224 - LONG $0x00cb8149; WORD $0x0001; BYTE $0x00 // or r11, 256 - LONG $0x20cc8149; WORD $0x0001; BYTE $0x00 // or r12, 288 - LONG $0x2464894c; BYTE $0x40 // mov qword [rsp + 64], r12 - LONG $0x40ca8149; WORD $0x0001; BYTE $0x00 // or r10, 320 - LONG $0x2454894c; BYTE $0x58 // mov qword [rsp + 88], r10 - WORD $0x894d; BYTE $0xfa // mov r10, r15 - LONG $0x60ca8149; WORD $0x0001; BYTE $0x00 // or r10, 352 - LONG $0x2454894c; BYTE $0x50 // mov qword [rsp + 80], r10 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - LONG $0x80cc8149; WORD $0x0001; BYTE $0x00 // or r12, 384 - WORD $0x894c; BYTE $0xfe // mov rsi, r15 - LONG $0xa0ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 416 - LONG $0x24748948; BYTE $0x30 // mov qword [rsp + 48], rsi - LONG $0xc0cd8149; WORD $0x0001; BYTE $0x00 // or r13, 448 - LONG $0x246c894c; BYTE $0x18 // mov qword [rsp + 24], r13 - WORD $0x894c; BYTE $0xfe // mov rsi, r15 - LONG $0xe0ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 480 - LONG $0x24748948; BYTE $0x28 // mov qword [rsp + 40], rsi - QUAD $0x01323c203a0f4666 // pinsrb xmm15, byte [rdx + r14], 1 - QUAD $0x021a3c203a0f4466 // pinsrb xmm15, byte [rdx + rbx], 2 - QUAD $0x03023c203a0f4466 // pinsrb xmm15, byte [rdx + rax], 3 - QUAD $0x00000080248c8948 // mov qword [rsp + 128], rcx - QUAD $0x040a3c203a0f4466 // pinsrb xmm15, byte [rdx + rcx], 4 - QUAD $0x053a3c203a0f4466 // pinsrb xmm15, byte [rdx + rdi], 5 - LONG $0x2444894c; BYTE $0x60 // mov qword [rsp + 96], r8 - QUAD $0x06023c203a0f4666 // pinsrb xmm15, byte [rdx + r8], 6 - QUAD $0x000000d0248c894c // mov qword [rsp + 208], r9 - QUAD $0x070a3c203a0f4666 // pinsrb xmm15, byte [rdx + r9], 7 - LONG $0x245c894c; BYTE $0x78 // mov qword [rsp + 120], r11 - QUAD $0x081a3c203a0f4666 // pinsrb xmm15, byte [rdx + r11], 8 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x09323c203a0f4666 // pinsrb xmm15, byte [rdx + r14], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0a3a3c203a0f4666 // pinsrb xmm15, byte [rdx + r15], 10 - QUAD $0x0b123c203a0f4666 // pinsrb xmm15, byte [rdx + r10], 11 - LONG $0x2464894c; BYTE $0x38 // mov qword [rsp + 56], r12 - QUAD $0x0c223c203a0f4666 // pinsrb xmm15, byte [rdx + r12], 12 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x0d123c203a0f4666 // pinsrb xmm15, byte [rdx + r10], 13 - QUAD $0x0e2a3c203a0f4666 // pinsrb xmm15, byte [rdx + r13], 14 - QUAD $0x0f323c203a0f4466 // pinsrb xmm15, byte [rdx + rsi], 15 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x01011a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 1], 1 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x02011a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 1], 2 - QUAD $0x0301026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 1], 3 - QUAD $0x04010a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 1], 4 - QUAD $0x05013a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 1], 5 - QUAD $0x01026c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r8 + 1], 6 - QUAD $0x010a6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r9 + 1], 7 - QUAD $0x011a6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r11 + 1], 8 - QUAD $0x01326c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r14 + 1], 9 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - QUAD $0x013a6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r15 + 1], 10 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0b010a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 1], 11 - QUAD $0x01226c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r12 + 1], 12 - QUAD $0x01126c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdx + r10 + 1], 13 - QUAD $0x012a6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdx + r13 + 1], 14 - QUAD $0x0f01326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 1], 15 - QUAD $0x00b0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 - LONG $0xfd6f0f66 // movdqa xmm7, xmm5 - QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI2_10] */ - LONG $0xfcdb0f66 // pand xmm7, xmm4 - LONG $0xfdf80f66 // psubb xmm7, xmm5 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - LONG $0x74b60f42; WORD $0x0f2a // movzx esi, byte [rdx + r13 + 15] - LONG $0x6e0f4466; BYTE $0xf6 // movd xmm14, esi - LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x01020a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 2], 1 - QUAD $0x02021a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 2], 2 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x021a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r11 + 2], 3 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x020274203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdx + r8 + 2], 4 - QUAD $0x05023a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 2], 5 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x022274203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r12 + 2], 6 - QUAD $0x000000d024b48b4c // mov r14, qword [rsp + 208] - QUAD $0x023274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r14 + 2], 7 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x023a74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r15 + 2], 8 - QUAD $0x09020274203a0f66 // pinsrb xmm6, byte [rdx + rax + 2], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x0a023274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 2], 10 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x021274203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r10 + 2], 11 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x020a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r9 + 2], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0d023274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 2], 13 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x0e023274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 2], 14 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0f023274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 2], 15 - LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 - LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 - QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xf0db0f66 // pand xmm6, xmm0 - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x74b60f42; WORD $0x102a // movzx esi, byte [rdx + r13 + 16] - LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - QUAD $0x01030a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 3], 1 - QUAD $0x02031a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 3], 2 - WORD $0x894c; BYTE $0xd9 // mov rcx, r11 - QUAD $0x031a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r11 + 3], 3 - QUAD $0x030254203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r8 + 3], 4 - QUAD $0x0000008824bc8948 // mov qword [rsp + 136], rdi - QUAD $0x05033a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 3], 5 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - QUAD $0x032254203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r12 + 3], 6 - QUAD $0x033254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r14 + 3], 7 - WORD $0x894c; BYTE $0xfe // mov rsi, r15 - QUAD $0x033a54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r15 + 3], 8 - QUAD $0x09030254203a0f66 // pinsrb xmm2, byte [rdx + rax + 3], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x033a54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r15 + 3], 10 - QUAD $0x031254203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r10 + 3], 11 - QUAD $0x030a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r9 + 3], 12 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x032254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r12 + 3], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e030254203a0f66 // pinsrb xmm2, byte [rdx + rax + 3], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0f030254203a0f66 // pinsrb xmm2, byte [rdx + rax + 3], 15 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x042a4c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rdx + r13 + 4], 1 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x02041a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 4], 2 - QUAD $0x03040a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 4], 3 - QUAD $0x04024c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdx + r8 + 4], 4 - QUAD $0x05043a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 4], 5 - QUAD $0x041a4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r11 + 4], 6 - QUAD $0x04324c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r14 + 4], 7 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - QUAD $0x0804324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 4], 8 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x0904324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 4], 9 - QUAD $0x043a4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdx + r15 + 4], 10 - QUAD $0x04124c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdx + r10 + 4], 11 - WORD $0x894d; BYTE $0xd7 // mov r15, r10 - QUAD $0x040a4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r9 + 4], 12 - QUAD $0x04224c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdx + r12 + 4], 13 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x0e041a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 4], 14 - QUAD $0x0f04024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 4], 15 - WORD $0x8949; BYTE $0xc2 // mov r10, rax - LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - LONG $0x3a74b60f; BYTE $0x11 // movzx esi, byte [rdx + rdi + 17] - LONG $0xc66e0f66 // movd xmm0, esi - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0xd5db0f66 // pand xmm2, xmm5 - LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 - QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xcddb0f66 // pand xmm1, xmm5 - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0x3a74b60f; BYTE $0x12 // movzx esi, byte [rdx + rdi + 18] - LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x052a44203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rdx + r13 + 5], 1 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x051a44203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rdx + r11 + 5], 2 - QUAD $0x050a44203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rdx + rcx + 5], 3 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x053244203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdx + r14 + 5], 4 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x050a44203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rdx + r9 + 5], 5 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x050244203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rdx + rax + 5], 6 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - QUAD $0x050244203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdx + r8 + 5], 7 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x050244203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdx + r8 + 5], 8 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x053244203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdx + rsi + 5], 9 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x053244203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdx + rsi + 5], 10 - QUAD $0x053a44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r15 + 5], 11 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x052244203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdx + r12 + 5], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x053244203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdx + rsi + 5], 13 - QUAD $0x051a44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdx + rbx + 5], 14 - QUAD $0x051244203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdx + r10 + 5], 15 - LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 - QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI2_14] */ - LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0x3a74b60f; BYTE $0x13 // movzx esi, byte [rdx + rdi + 19] - LONG $0xfe6e0f66 // movd xmm7, esi - LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - LONG $0x3a74b60f; BYTE $0x14 // movzx esi, byte [rdx + rdi + 20] - LONG $0xf66e0f66 // movd xmm6, esi - QUAD $0x062a5c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdx + r13 + 6], 1 - WORD $0x894c; BYTE $0xde // mov rsi, r11 - QUAD $0x061a5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdx + r11 + 6], 2 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x06125c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r10 + 6], 3 - WORD $0x894d; BYTE $0xf3 // mov r11, r14 - QUAD $0x06325c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdx + r14 + 6], 4 - QUAD $0x060a5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdx + r9 + 6], 5 - QUAD $0x0606025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 6], 6 - QUAD $0x07060a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 6], 7 - WORD $0x8949; BYTE $0xce // mov r14, rcx - QUAD $0x06025c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdx + r8 + 6], 8 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x09063a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 6], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x063a5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r15 + 6], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b06025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 6], 11 - WORD $0x894c; BYTE $0xe3 // mov rbx, r12 - QUAD $0x06225c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r12 + 6], 12 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x06225c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdx + r12 + 6], 13 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x0e060a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 6], 14 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f060a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 6], 15 - QUAD $0x0000c024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 192] - QUAD $0x072a54203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r13 + 7], 1 - QUAD $0x02073254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 7], 2 - WORD $0x8949; BYTE $0xf5 // mov r13, rsi - QUAD $0x071254203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r10 + 7], 3 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x071a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r11 + 7], 4 - QUAD $0x070a54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdx + r9 + 7], 5 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x06070a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 7], 6 - QUAD $0x073254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r14 + 7], 7 - QUAD $0x070254203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r8 + 7], 8 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - QUAD $0x09073a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 7], 9 - QUAD $0x073a54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r15 + 7], 10 - QUAD $0x0b070254203a0f66 // pinsrb xmm2, byte [rdx + rax + 7], 11 - QUAD $0x0c071a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 7], 12 - QUAD $0x072254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r12 + 7], 13 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] - QUAD $0x072254203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r12 + 7], 14 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0f071a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 7], 15 - LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 - QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI2_15] */ - LONG $0xd9db0f66 // pand xmm3, xmm1 - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 - LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI2_6] */ - LONG $0xd1db0f66 // pand xmm2, xmm1 - LONG $0xd3eb0f66 // por xmm2, xmm3 - LONG $0xca6f0f66 // movdqa xmm1, xmm2 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - LONG $0x0274b60f; BYTE $0x15 // movzx esi, byte [rdx + rax + 21] - LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x244c8b4c; BYTE $0x10 // mov r9, qword [rsp + 16] - QUAD $0x090a54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdx + r9 + 9], 1 - QUAD $0x092a54203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdx + r13 + 9], 2 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x090254203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r8 + 9], 3 - QUAD $0x091254203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r10 + 9], 4 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x093a54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdx + rdi + 9], 5 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x092a54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r13 + 9], 6 - QUAD $0x093254203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdx + r14 + 9], 7 - QUAD $0x090a54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rdx + rcx + 9], 8 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x093254203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rsi + 9], 9 - QUAD $0x093a54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdx + r15 + 9], 10 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x093254203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rdx + rsi + 9], 11 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x093254203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdx + rsi + 9], 12 - QUAD $0x091a54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdx + r11 + 9], 13 - QUAD $0x092254203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r12 + 9], 14 - QUAD $0x091a54203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdx + rbx + 9], 15 - LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 - LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 - LONG $0xccdb0f66 // pand xmm1, xmm4 - LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 - LONG $0x0274b60f; BYTE $0x16 // movzx esi, byte [rdx + rax + 22] - LONG $0xde6e0f66 // movd xmm3, esi - QUAD $0x0000f024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 240] - QUAD $0x080a64203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdx + r9 + 8], 1 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x082264203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdx + r12 + 8], 2 - QUAD $0x080264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r8 + 8], 3 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - QUAD $0x081264203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r10 + 8], 4 - QUAD $0x05083a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 8], 5 - QUAD $0x082a64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdx + r13 + 8], 6 - QUAD $0x083264203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r14 + 8], 7 - QUAD $0x08080a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 8], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x09081a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 8], 9 - QUAD $0x083a64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdx + r15 + 8], 10 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0b080264203a0f66 // pinsrb xmm4, byte [rdx + rax + 8], 11 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0c083264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 8], 12 - QUAD $0x081a64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdx + r11 + 8], 13 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x081264203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdx + r10 + 8], 14 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x0f080a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 8], 15 - LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 - LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 - QUAD $0x00a024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 160] - QUAD $0x0a0a54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdx + r9 + 10], 1 - QUAD $0x0a2254203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdx + r12 + 10], 2 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x0a0a54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r9 + 10], 3 - QUAD $0x0a0254203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r8 + 10], 4 - QUAD $0x0a3a54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdx + rdi + 10], 5 - QUAD $0x0a2a54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r13 + 10], 6 - WORD $0x894d; BYTE $0xe8 // mov r8, r13 - QUAD $0x0a3254203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdx + r14 + 10], 7 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] - QUAD $0x0a3254203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r14 + 10], 8 - QUAD $0x0a1a54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rbx + 10], 9 - QUAD $0x0a3a54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdx + r15 + 10], 10 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - QUAD $0x0a0254203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rdx + rax + 10], 11 - QUAD $0x0a3254203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdx + rsi + 10], 12 - QUAD $0x0a1a54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdx + r11 + 10], 13 - QUAD $0x0a1254203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r10 + 10], 14 - QUAD $0x0a0a54203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdx + rcx + 10], 15 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - LONG $0x0a74b60f; BYTE $0x17 // movzx esi, byte [rdx + rcx + 23] - LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi - LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - QUAD $0x00a024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm10 - LONG $0x0a74b60f; BYTE $0x18 // movzx esi, byte [rdx + rcx + 24] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x0b125c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdx + r10 + 11], 1 - QUAD $0x0b225c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rdx + r12 + 11], 2 - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - QUAD $0x0b0a5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r9 + 11], 3 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x0b1a5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdx + r11 + 11], 4 - QUAD $0x0b3a5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdx + rdi + 11], 5 - QUAD $0x0b025c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r8 + 11], 6 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 - QUAD $0x0b2a5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdx + r13 + 11], 7 - QUAD $0x0b325c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r14 + 11], 8 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x0b025c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdx + r8 + 11], 9 - QUAD $0x0b1a5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdx + rbx + 11], 10 - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - QUAD $0x0b025c203a0f4466; BYTE $0x0b // pinsrb xmm11, byte [rdx + rax + 11], 11 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x0b2a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r13 + 11], 12 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x0b0a5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdx + r9 + 11], 13 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x0b325c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rdx + rsi + 11], 14 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b025c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdx + rax + 11], 15 - QUAD $0x0c126c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rdx + r10 + 12], 1 - QUAD $0x0c226c203a0f4666; BYTE $0x02 // pinsrb xmm13, byte [rdx + r12 + 12], 2 - QUAD $0x0c0a6c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rdx + rcx + 12], 3 - QUAD $0x0c1a6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdx + r11 + 12], 4 - QUAD $0x0c3a6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdx + rdi + 12], 5 - QUAD $0x0c3a6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdx + r15 + 12], 6 - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - QUAD $0x0c1a6c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdx + r11 + 12], 7 - QUAD $0x0c326c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r14 + 12], 8 - QUAD $0x0c026c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdx + r8 + 12], 9 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x0c3a6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rdx + r15 + 12], 10 - QUAD $0x0c1a6c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rdx + rbx + 12], 11 - QUAD $0x0c2a6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r13 + 12], 12 - QUAD $0x0c0a6c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdx + r9 + 12], 13 - QUAD $0x0c326c203a0f4466; BYTE $0x0e // pinsrb xmm13, byte [rdx + rsi + 12], 14 - QUAD $0x0c026c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdx + rax + 12], 15 - QUAD $0x0d1264203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdx + r10 + 13], 1 - QUAD $0x0d2264203a0f4666; BYTE $0x02 // pinsrb xmm12, byte [rdx + r12 + 13], 2 - QUAD $0x0d0a64203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdx + rcx + 13], 3 - WORD $0x8949; BYTE $0xca // mov r10, rcx - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0d0a64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdx + rcx + 13], 4 - QUAD $0x0d3a64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdx + rdi + 13], 5 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0d3a64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rdx + rdi + 13], 6 - QUAD $0x0d1a64203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdx + r11 + 13], 7 - QUAD $0x0d3264203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r14 + 13], 8 - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - QUAD $0x0d0264203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdx + r8 + 13], 9 - QUAD $0x0d3a64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdx + r15 + 13], 10 - QUAD $0x0d1a64203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rdx + rbx + 13], 11 - QUAD $0x0d2a64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdx + r13 + 13], 12 - QUAD $0x0d0a64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdx + r9 + 13], 13 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - QUAD $0x0d3264203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rdx + rsi + 13], 14 - QUAD $0x0d0264203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdx + rax + 13], 15 - LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 - QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 - QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - LONG $0x1a74b60f; BYTE $0x19 // movzx esi, byte [rdx + rbx + 25] - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 - QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI2_14] */ - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0x1a74b60f; BYTE $0x1a // movzx esi, byte [rdx + rbx + 26] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x010e0264203a0f66 // pinsrb xmm4, byte [rdx + rax + 14], 1 - QUAD $0x0e2264203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdx + r12 + 14], 2 - QUAD $0x0e1264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r10 + 14], 3 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x040e0a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 14], 4 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x050e0a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 14], 5 - QUAD $0x060e3a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 14], 6 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - QUAD $0x0e1a64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r11 + 14], 7 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x0e0a64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r9 + 14], 8 - WORD $0x894c; BYTE $0xf3 // mov rbx, r14 - QUAD $0x0e3264203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r14 + 14], 9 - WORD $0x894d; BYTE $0xfb // mov r11, r15 - QUAD $0x0e3a64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdx + r15 + 14], 10 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0e3264203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r14 + 14], 11 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x0e3a64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r15 + 14], 12 - QUAD $0x0e2a64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdx + r13 + 14], 13 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x0e2a64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdx + r13 + 14], 14 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0f0e3264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 14], 15 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0f3274203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdx + rsi + 15], 1 - QUAD $0x0f2274203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdx + r12 + 15], 2 - QUAD $0x0f1274203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdx + r10 + 15], 3 - QUAD $0x0f0274203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rdx + rax + 15], 4 - QUAD $0x0f0a74203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdx + rcx + 15], 5 - QUAD $0x0f3a74203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rdx + rdi + 15], 6 - QUAD $0x0f0274203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdx + r8 + 15], 7 - QUAD $0x0f0a74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdx + r9 + 15], 8 - QUAD $0x0f1a74203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdx + rbx + 15], 9 - QUAD $0x0f1a74203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rdx + r11 + 15], 10 - QUAD $0x0f3274203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdx + r14 + 15], 11 - QUAD $0x0f3a74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdx + r15 + 15], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0f3274203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdx + rsi + 15], 13 - QUAD $0x0f2a74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdx + r13 + 15], 14 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0f3274203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdx + rsi + 15], 15 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x10327c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rsi + 16], 1 - QUAD $0x10227c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rdx + r12 + 16], 2 - QUAD $0x10127c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r10 + 16], 3 - QUAD $0x10027c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdx + rax + 16], 4 - QUAD $0x100a7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdx + rcx + 16], 5 - QUAD $0x103a7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rdx + rdi + 16], 6 - QUAD $0x10027c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r8 + 16], 7 - QUAD $0x100a7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdx + r9 + 16], 8 - QUAD $0x101a7c203a0f4466; BYTE $0x09 // pinsrb xmm15, byte [rdx + rbx + 16], 9 - QUAD $0x101a7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdx + r11 + 16], 10 - QUAD $0x10327c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdx + r14 + 16], 11 - QUAD $0x103a7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdx + r15 + 16], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x10327c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdx + rsi + 16], 13 - QUAD $0x102a7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdx + r13 + 16], 14 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x01113244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 17], 1 - QUAD $0x112244203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdx + r12 + 17], 2 - QUAD $0x111244203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r10 + 17], 3 - QUAD $0x04110244203a0f66 // pinsrb xmm0, byte [rdx + rax + 17], 4 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x05110a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 17], 5 - QUAD $0x06113a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 17], 6 - QUAD $0x110244203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r8 + 17], 7 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x110a44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r9 + 17], 8 - QUAD $0x09111a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 17], 9 - QUAD $0x111a44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdx + r11 + 17], 10 - QUAD $0x113244203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r14 + 17], 11 - QUAD $0x113a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r15 + 17], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0d113244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 17], 13 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x0e113244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 17], 14 - QUAD $0x00a024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 160] - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - LONG $0x74b60f42; WORD $0x1b22 // movzx esi, byte [rdx + r12 + 27] - LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - QUAD $0x00b024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 - QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI2_15] */ - LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 - LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 - LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI2_6] */ - LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 - LONG $0x74b60f42; WORD $0x1c22 // movzx esi, byte [rdx + r12 + 28] - LONG $0xe66e0f66 // movd xmm4, esi - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x110244203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r8 + 17], 15 - LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 - LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 - LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 - QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI2_10] */ - LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 - LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 - QUAD $0x00a024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm13 - LONG $0x74b60f42; WORD $0x1d22 // movzx esi, byte [rdx + r12 + 29] - LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi - QUAD $0x10027c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdx + r8 + 16], 15 - QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] - LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x12226c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdx + r12 + 18], 1 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0212326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 18], 2 - QUAD $0x12126c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r10 + 18], 3 - QUAD $0x122a6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdx + r13 + 18], 4 - QUAD $0x05120a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 18], 5 - QUAD $0x06123a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 18], 6 - QUAD $0x0712026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 18], 7 - QUAD $0x120a6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r9 + 18], 8 - QUAD $0x09121a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 18], 9 - QUAD $0x121a6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r11 + 18], 10 - QUAD $0x12326c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdx + r14 + 18], 11 - QUAD $0x123a6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r15 + 18], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0d12326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 18], 13 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x0e12326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 18], 14 - LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 - QUAD $0x12026c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdx + r8 + 18], 15 - LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 - QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - LONG $0x0274b60f; BYTE $0x1e // movzx esi, byte [rdx + rax + 30] - LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - QUAD $0x13227c203a0f4266; BYTE $0x01 // pinsrb xmm7, byte [rdx + r12 + 19], 1 - QUAD $0x142274203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdx + r12 + 20], 1 - QUAD $0x152254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r12 + 21], 1 - QUAD $0x16225c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdx + r12 + 22], 1 - QUAD $0x172244203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rdx + r12 + 23], 1 - QUAD $0x182254203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdx + r12 + 24], 1 - QUAD $0x19224c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rdx + r12 + 25], 1 - QUAD $0x1a225c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdx + r12 + 26], 1 - QUAD $0x1b224c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rdx + r12 + 27], 1 - QUAD $0x1c2264203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdx + r12 + 28], 1 - QUAD $0x1d226c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rdx + r12 + 29], 1 - QUAD $0x1e2264203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdx + r12 + 30], 1 - LONG $0x0274b60f; BYTE $0x1f // movzx esi, byte [rdx + rax + 31] - LONG $0xc66e0f66 // movd xmm0, esi - QUAD $0x1f2244203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdx + r12 + 31], 1 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0213327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 19], 2 - QUAD $0x02143274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 20], 2 - QUAD $0x02153254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 21], 2 - QUAD $0x0216325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 22], 2 - QUAD $0x173244203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdx + rsi + 23], 2 - QUAD $0x183254203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdx + rsi + 24], 2 - QUAD $0x0219324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 25], 2 - QUAD $0x1a325c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rsi + 26], 2 - QUAD $0x1b324c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rsi + 27], 2 - QUAD $0x021c3264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 28], 2 - QUAD $0x1d326c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rsi + 29], 2 - QUAD $0x1e3264203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rsi + 30], 2 - QUAD $0x021f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 31], 2 - QUAD $0x13127c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r10 + 19], 3 - QUAD $0x132a7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdx + r13 + 19], 4 - QUAD $0x05130a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 19], 5 - QUAD $0x06133a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 19], 6 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x0713027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 19], 7 - QUAD $0x130a7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdx + r9 + 19], 8 - QUAD $0x09131a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 19], 9 - QUAD $0x131a7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdx + r11 + 19], 10 - QUAD $0x13327c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdx + r14 + 19], 11 - QUAD $0x133a7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r15 + 19], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0d13327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 19], 13 - LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] - QUAD $0x13227c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdx + r12 + 19], 14 - QUAD $0x13027c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdx + r8 + 19], 15 - QUAD $0x141274203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r10 + 20], 3 - QUAD $0x142a74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdx + r13 + 20], 4 - QUAD $0x05140a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 20], 5 - QUAD $0x06143a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 20], 6 - QUAD $0x07140274203a0f66 // pinsrb xmm6, byte [rdx + rax + 20], 7 - QUAD $0x140a74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r9 + 20], 8 - QUAD $0x09141a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 20], 9 - QUAD $0x141a74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r11 + 20], 10 - QUAD $0x143274203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r14 + 20], 11 - QUAD $0x143a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r15 + 20], 12 - QUAD $0x0d143274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 20], 13 - QUAD $0x142274203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdx + r12 + 20], 14 - QUAD $0x0000a024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 160] - QUAD $0x140274203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdx + r8 + 20], 15 - QUAD $0x00b024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 - QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 - QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0x151254203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r10 + 21], 3 - QUAD $0x152a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r13 + 21], 4 - QUAD $0x05150a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 21], 5 - QUAD $0x06153a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 21], 6 - QUAD $0x07150254203a0f66 // pinsrb xmm2, byte [rdx + rax + 21], 7 - QUAD $0x150a54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r9 + 21], 8 - QUAD $0x09151a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 21], 9 - QUAD $0x151a54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r11 + 21], 10 - QUAD $0x153254203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r14 + 21], 11 - QUAD $0x153a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r15 + 21], 12 - QUAD $0x0d153254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 21], 13 - QUAD $0x152254203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r12 + 21], 14 - QUAD $0x150254203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r8 + 21], 15 - LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 - QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI2_14] */ - LONG $0xd7db0f66 // pand xmm2, xmm7 - LONG $0xd6eb0f66 // por xmm2, xmm6 - LONG $0xd5eb0f66 // por xmm2, xmm5 - QUAD $0x16125c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r10 + 22], 3 - QUAD $0x162a5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdx + r13 + 22], 4 - QUAD $0x05160a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 22], 5 - QUAD $0x06163a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 22], 6 - QUAD $0x0716025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 22], 7 - QUAD $0x160a5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdx + r9 + 22], 8 - QUAD $0x09161a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 22], 9 - QUAD $0x161a5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r11 + 22], 10 - QUAD $0x16325c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r14 + 22], 11 - QUAD $0x163a5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r15 + 22], 12 - QUAD $0x0d16325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 22], 13 - QUAD $0x16225c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdx + r12 + 22], 14 - QUAD $0x16025c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r8 + 22], 15 - QUAD $0x171244203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r10 + 23], 3 - QUAD $0x172a44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdx + r13 + 23], 4 - QUAD $0x170a44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdx + rcx + 23], 5 - QUAD $0x173a44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rdx + rdi + 23], 6 - QUAD $0x170244203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rdx + rax + 23], 7 - QUAD $0x170a44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdx + r9 + 23], 8 - QUAD $0x171a44203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdx + rbx + 23], 9 - QUAD $0x171a44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdx + r11 + 23], 10 - QUAD $0x173244203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r14 + 23], 11 - QUAD $0x173a44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdx + r15 + 23], 12 - QUAD $0x173244203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdx + rsi + 23], 13 - QUAD $0x172244203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdx + r12 + 23], 14 - QUAD $0x170244203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdx + r8 + 23], 15 - LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 - QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI2_15] */ - LONG $0xdddb0f66 // pand xmm3, xmm5 - LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 - LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 - LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI2_6] */ - LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 - LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - QUAD $0x19124c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r10 + 25], 3 - QUAD $0x192a4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdx + r13 + 25], 4 - QUAD $0x05190a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 25], 5 - QUAD $0x06193a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 25], 6 - QUAD $0x0719024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 25], 7 - QUAD $0x190a4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r9 + 25], 8 - QUAD $0x09191a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 25], 9 - QUAD $0x191a4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdx + r11 + 25], 10 - QUAD $0x19324c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdx + r14 + 25], 11 - QUAD $0x193a4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r15 + 25], 12 - QUAD $0x0d19324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 25], 13 - QUAD $0x19224c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r12 + 25], 14 - QUAD $0x19024c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r8 + 25], 15 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 - LONG $0xd16f0f66 // movdqa xmm2, xmm1 - QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI2_10] */ - LONG $0xd3db0f66 // pand xmm2, xmm3 - LONG $0xd1f80f66 // psubb xmm2, xmm1 - QUAD $0x181254203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r10 + 24], 3 - QUAD $0x182a54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r13 + 24], 4 - QUAD $0x180a54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdx + rcx + 24], 5 - QUAD $0x183a54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rdx + rdi + 24], 6 - QUAD $0x180254203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rdx + rax + 24], 7 - QUAD $0x180a54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r9 + 24], 8 - QUAD $0x181a54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rbx + 24], 9 - QUAD $0x181a54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdx + r11 + 24], 10 - QUAD $0x183254203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdx + r14 + 24], 11 - QUAD $0x183a54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdx + r15 + 24], 12 - QUAD $0x183254203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdx + rsi + 24], 13 - QUAD $0x182254203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r12 + 24], 14 - QUAD $0x180254203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdx + r8 + 24], 15 - LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 - LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 - QUAD $0x1a125c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r10 + 26], 3 - QUAD $0x1a2a5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdx + r13 + 26], 4 - QUAD $0x1a0a5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdx + rcx + 26], 5 - QUAD $0x1a3a5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rdx + rdi + 26], 6 - QUAD $0x1a025c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rdx + rax + 26], 7 - QUAD $0x1a0a5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r9 + 26], 8 - QUAD $0x1a1a5c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdx + rbx + 26], 9 - QUAD $0x1a1a5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdx + r11 + 26], 10 - QUAD $0x1a325c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r14 + 26], 11 - QUAD $0x1a3a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r15 + 26], 12 - QUAD $0x1a325c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdx + rsi + 26], 13 - QUAD $0x1a225c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r12 + 26], 14 - QUAD $0x1a025c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdx + r8 + 26], 15 - LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 - QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI2_11] */ - LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 - LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 - QUAD $0x1b124c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdx + r10 + 27], 3 - QUAD $0x1b2a4c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdx + r13 + 27], 4 - QUAD $0x1b0a4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdx + rcx + 27], 5 - QUAD $0x1b3a4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rdx + rdi + 27], 6 - QUAD $0x1b024c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rdx + rax + 27], 7 - QUAD $0x1b0a4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r9 + 27], 8 - QUAD $0x1b1a4c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdx + rbx + 27], 9 - QUAD $0x1b1a4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdx + r11 + 27], 10 - QUAD $0x1b324c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdx + r14 + 27], 11 - QUAD $0x1b3a4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdx + r15 + 27], 12 - QUAD $0x1b324c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdx + rsi + 27], 13 - QUAD $0x1b224c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r12 + 27], 14 - QUAD $0x1b024c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdx + r8 + 27], 15 - QUAD $0x1c1264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r10 + 28], 3 - QUAD $0x1c2a64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r13 + 28], 4 - QUAD $0x051c0a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 28], 5 - QUAD $0x061c3a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 28], 6 - QUAD $0x071c0264203a0f66 // pinsrb xmm4, byte [rdx + rax + 28], 7 - QUAD $0x1c0a64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r9 + 28], 8 - QUAD $0x091c1a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 28], 9 - QUAD $0x1c1a64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdx + r11 + 28], 10 - QUAD $0x1c3264203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r14 + 28], 11 - QUAD $0x1c3a64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r15 + 28], 12 - QUAD $0x0d1c3264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 28], 13 - QUAD $0x1c2264203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdx + r12 + 28], 14 - QUAD $0x1c0264203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdx + r8 + 28], 15 - QUAD $0x1d126c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdx + r10 + 29], 3 - QUAD $0x1d2a6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdx + r13 + 29], 4 - QUAD $0x1d0a6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdx + rcx + 29], 5 - QUAD $0x1d3a6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rdx + rdi + 29], 6 - QUAD $0x1d026c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rdx + rax + 29], 7 - QUAD $0x1d0a6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r9 + 29], 8 - QUAD $0x1d1a6c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rdx + rbx + 29], 9 - QUAD $0x1d1a6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rdx + r11 + 29], 10 - QUAD $0x1d326c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdx + r14 + 29], 11 - QUAD $0x1d3a6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r15 + 29], 12 - QUAD $0x1d326c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rdx + rsi + 29], 13 - QUAD $0x1d226c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r12 + 29], 14 - LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 - LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 - QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI2_12] */ - LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 - QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI2_13] */ - LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 - QUAD $0x1d026c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdx + r8 + 29], 15 - LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 - LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 - LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 - QUAD $0x1e1264203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r10 + 30], 3 - QUAD $0x1f1244203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r10 + 31], 3 - QUAD $0x1e2a64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdx + r13 + 30], 4 - QUAD $0x1f2a44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdx + r13 + 31], 4 - QUAD $0x1e0a64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdx + rcx + 30], 5 - QUAD $0x051f0a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 31], 5 - QUAD $0x1e3a64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rdx + rdi + 30], 6 - QUAD $0x061f3a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 31], 6 - QUAD $0x1e0264203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rdx + rax + 30], 7 - QUAD $0x071f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 31], 7 - QUAD $0x1e0a64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r9 + 30], 8 - QUAD $0x1f0a44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r9 + 31], 8 - QUAD $0x1e1a64203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rdx + rbx + 30], 9 - QUAD $0x091f1a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 31], 9 - QUAD $0x1e1a64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdx + r11 + 30], 10 - QUAD $0x1f1a44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdx + r11 + 31], 10 - QUAD $0x1e3264203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdx + r14 + 30], 11 - QUAD $0x1f3244203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r14 + 31], 11 - QUAD $0x1e3a64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdx + r15 + 30], 12 - QUAD $0x1f3a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r15 + 31], 12 - QUAD $0x1e3264203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdx + rsi + 30], 13 - QUAD $0x0d1f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 31], 13 - QUAD $0x1e2264203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r12 + 30], 14 - QUAD $0x1f2244203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdx + r12 + 31], 14 - QUAD $0x1e0264203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdx + r8 + 30], 15 - QUAD $0x1f0244203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r8 + 31], 15 - LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 - LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 - LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0xc6db0f66 // pand xmm0, xmm6 - LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 - LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 - LONG $0xc8600f66 // punpcklbw xmm1, xmm0 - QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] - LONG $0xd46f0f66 // movdqa xmm2, xmm4 - LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 - LONG $0xda6f0f66 // movdqa xmm3, xmm2 - LONG $0xd9610f66 // punpcklwd xmm3, xmm1 - LONG $0xd1690f66 // punpckhwd xmm2, xmm1 - LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 - LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x647f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm4 - LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 - LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 - LONG $0x1c7f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm3 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e0248c3b48 // cmp rcx, qword [rsp + 224] - JNE LBB2_186 - QUAD $0x000000e824bc8b4c // mov r15, qword [rsp + 232] - QUAD $0x000000e024bc3b4c // cmp r15, qword [rsp + 224] - LONG $0x24748a44; BYTE $0x08 // mov r14b, byte [rsp + 8] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - JNE LBB2_69 - JMP LBB2_135 +LBB2_167: + WORD $0xc031 // xor eax, eax + QUAD $0x000000d824848948 // mov qword [rsp + 216], rax + LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + +LBB2_168: + QUAD $0x000000d8248c2b48 // sub rcx, qword [rsp + 216] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + +LBB2_169: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3a44; BYTE $0x1e // cmp r11b, byte [rsi] + QUAD $0x000000902494940f // sete byte [rsp + 144] + LONG $0x015e3a44 // cmp r11b, byte [rsi + 1] + LONG $0xd7940f40 // sete dil + LONG $0x025e3a44 // cmp r11b, byte [rsi + 2] + LONG $0xd3940f41 // sete r11b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x03 // cmp al, byte [rsi + 3] + LONG $0xd7940f41 // sete r15b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] + QUAD $0x000000882494940f // sete byte [rsp + 136] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] + LONG $0x2454940f; BYTE $0x70 // sete byte [rsp + 112] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] + WORD $0x940f; BYTE $0xd3 // sete bl + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] + LONG $0xd4940f41 // sete r12b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] + QUAD $0x000000c02494940f // sete byte [rsp + 192] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] + LONG $0xd6940f40 // sete sil + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] + LONG $0xd0940f41 // sete r8b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] + LONG $0xd1940f41 // sete r9b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] + LONG $0xd6940f41 // sete r14b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] + LONG $0x2454940f; BYTE $0x48 // sete byte [rsp + 72] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + QUAD $0x000000a02494940f // sete byte [rsp + 160] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + LONG $0xd5940f41 // sete r13b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + QUAD $0x000000b02494940f // sete byte [rsp + 176] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + LONG $0x2454940f; BYTE $0x68 // sete byte [rsp + 104] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] + LONG $0x2454940f; BYTE $0x78 // sete byte [rsp + 120] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] + LONG $0x2454940f; BYTE $0x50 // sete byte [rsp + 80] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] + LONG $0x2454940f; BYTE $0x58 // sete byte [rsp + 88] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] + LONG $0x2454940f; BYTE $0x38 // sete byte [rsp + 56] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x2454940f; BYTE $0x40 // sete byte [rsp + 64] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] + LONG $0xd2940f41 // sete r10b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] + LONG $0x2454940f; BYTE $0x30 // sete byte [rsp + 48] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] + LONG $0x2454940f; BYTE $0x18 // sete byte [rsp + 24] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] + LONG $0x2454940f; BYTE $0x28 // sete byte [rsp + 40] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] + LONG $0x2454940f; BYTE $0x20 // sete byte [rsp + 32] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] + LONG $0x2454940f; BYTE $0x08 // sete byte [rsp + 8] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] + LONG $0x2454940f; BYTE $0x10 // sete byte [rsp + 16] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] + QUAD $0x000000802494940f // sete byte [rsp + 128] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000009024bc0240 // add dil, byte [rsp + 144] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0841; BYTE $0xfb // or r11b, dil + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x000000c024b40240 // add sil, byte [rsp + 192] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x1cb60f44; BYTE $0x24 // movzx r11d, byte [rsp] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + QUAD $0x00000088249cb60f // movzx ebx, byte [rsp + 136] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xfb // or bl, r15b + WORD $0xd889 // mov eax, ebx + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xce // or r14b, r9b + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xf5 // or r13b, sil + WORD $0x0841; BYTE $0xdc // or r12b, bl + WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xc000 // add al, al + LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] + WORD $0x8844; BYTE $0x27 // mov byte [rdi], r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x016f8844 // mov byte [rdi + 1], r13b + WORD $0x0841; BYTE $0xda // or r10b, bl + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd808 // or al, bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02578844 // mov byte [rdi + 2], r10b + WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + LONG $0x247c8948; BYTE $0x60 // mov qword [rsp + 96], rdi + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB2_169 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + JMP LBB2_172 + +LBB2_171: + LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + +LBB2_172: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB2_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB2_181 + +LBB2_174: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB2_184 + +LBB2_175: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0xff31 // xor edi, edi + +LBB2_176: + WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x341c8841 // mov byte [r12 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] + LONG $0x08528d48 // lea rdx, [rdx + 8] + LONG $0xd1940f41 // sete r9b + WORD $0xf641; BYTE $0xd9 // neg r9b + WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0xd830 // xor al, bl + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfa // cmp r10, rdi + JNE LBB2_176 + +LBB2_177: + LONG $0x01c0f641 // test r8b, 1 + JE LBB2_200 + WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] + JMP LBB2_194 + +LBB2_181: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + +LBB2_182: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e1c3a46 // cmp r11b, byte [rsi + r9] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x065c3a44; BYTE $0x01 // cmp r11b, byte [rsi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x940f; BYTE $0xd3 // sete bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3e048841 // mov byte [r14 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB2_182 + +LBB2_183: + WORD $0x014c; BYTE $0xce // add rsi, r9 + +LBB2_184: + LONG $0x01c0f641 // test r8b, 1 + JE LBB2_200 + WORD $0x3a44; BYTE $0x1e // cmp r11b, byte [rsi] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + JMP LBB2_199 + +LBB2_186: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xff31 // xor edi, edi + +LBB2_187: + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0x9b0f; BYTE $0xd1 // setnp cl + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xc820 // and al, cl + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0xb341; BYTE $0x01 // mov r11b, 1 + WORD $0xd241; BYTE $0xe3 // shl r11b, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0x2041; BYTE $0xc3 // and r11b, al + WORD $0x3045; BYTE $0xd3 // xor r11b, r10b + LONG $0x341c8845 // mov byte [r12 + rsi], r11b + LONG $0x02c78348 // add rdi, 2 + LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd8f6 // neg al + WORD $0x3044; BYTE $0xd8 // xor al, r11b + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xdb // xor bl, r11b + LONG $0x341c8841 // mov byte [r12 + rsi], bl + WORD $0x3949; BYTE $0xf9 // cmp r9, rdi + JNE LBB2_187 LBB2_188: - LONG $0xf8e78349 // and r15, -8 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 + LONG $0x01c0f641 // test r8b, 1 + JE LBB2_200 + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xc220 // and dl, al + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + LONG $0x03e8c148 // shr rax, 3 + LONG $0x04348a41 // mov sil, byte [r12 + rax] + LONG $0x07e78040 // and dil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf989 // mov ecx, edi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf2 // xor dl, sil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xf3 // xor bl, sil + LONG $0x041c8841 // mov byte [r12 + rax], bl + JMP LBB2_200 + +LBB2_190: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0xff31 // xor edi, edi + +LBB2_191: + WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x341c8841 // mov byte [r12 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x086a3b4c // cmp r13, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd1940f41 // sete r9b + WORD $0xf641; BYTE $0xd9 // neg r9b + WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0xd830 // xor al, bl + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfa // cmp r10, rdi + JNE LBB2_191 + +LBB2_192: + LONG $0x01c0f641 // test r8b, 1 + JE LBB2_200 + WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] + +LBB2_194: + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0x03eac148 // shr rdx, 3 + LONG $0x14348a41 // mov sil, byte [r12 + rdx] + LONG $0x07e78040 // and dil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf989 // mov ecx, edi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xf3 // xor bl, sil + LONG $0x141c8841 // mov byte [r12 + rdx], bl + JMP LBB2_200 + +LBB2_195: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + LONG $0x241c8b4c // mov r11, qword [rsp] + +LBB2_196: + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x2e3b4466 // cmp r13w, word [rsi] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x14b60f45; BYTE $0x3b // movzx r10d, byte [r11 + rdi] + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + LONG $0x02c68349 // add r14, 2 + LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] + LONG $0x04768d48 // lea rsi, [rsi + 4] + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xdaf6 // neg dl + WORD $0xda30 // xor dl, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd020 // and al, dl + WORD $0xd830 // xor al, bl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB2_196 + +LBB2_197: + LONG $0x01c0f641 // test r8b, 1 + JE LBB2_200 + LONG $0x2e3b4466 // cmp r13w, word [rsi] + WORD $0x940f; BYTE $0xd0 // sete al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x24048b4c // mov r8, qword [rsp] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e68041 // and r14b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + +LBB2_199: + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + +LBB2_200: + MOVQ 304(SP), SP + RET + +LBB2_201: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xf631 // xor esi, esi + WORD $0x894d; BYTE $0xee // mov r14, r13 + +LBB2_202: + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x9b0f; BYTE $0xd1 // setnp cl + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xca20 // and dl, cl + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x03efc148 // shr rdi, 3 + LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] + WORD $0xf189 // mov ecx, esi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0xb341; BYTE $0x01 // mov r11b, 1 + WORD $0xd241; BYTE $0xe3 // shl r11b, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0x2041; BYTE $0xd3 // and r11b, dl + WORD $0x3045; BYTE $0xd3 // xor r11b, r10b + LONG $0x3e1c8845 // mov byte [r14 + rdi], r11b + LONG $0x02c68348 // add rsi, 2 + LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] + LONG $0x085b8d48 // lea rbx, [rbx + 8] + LONG $0xd29b0f41 // setnp r10b + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0x2044; BYTE $0xd2 // and dl, r10b + WORD $0xdaf6 // neg dl + WORD $0x3044; BYTE $0xda // xor dl, r11b + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xd8 // xor al, r11b + LONG $0x3e048841 // mov byte [r14 + rdi], al + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB2_202 + +LBB2_203: + LONG $0x01c0f641 // test r8b, 1 + JE LBB2_200 + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x9b0f; BYTE $0xd0 // setnp al + WORD $0x940f; BYTE $0xd2 // sete dl + WORD $0xc220 // and dl, al + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x03e8c148 // shr rax, 3 + LONG $0x057c8a41; BYTE $0x00 // mov dil, byte [r13 + rax] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xfa // xor dl, dil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x055c8841; BYTE $0x00 // mov byte [r13 + rax], bl + JMP LBB2_200 + +LBB2_205: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x244c8948; BYTE $0x18 // mov qword [rsp + 24], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24048948 // mov qword [rsp], rax + LONG $0x246c8944; BYTE $0x30 // mov dword [rsp + 48], r13d + LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 WORD $0x3145; BYTE $0xff // xor r15d, r15d @@ -14273,98 +12853,99 @@ LBB2_188: LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI2_4] */ LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI2_5] */ LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI2_6] */ + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 -LBB2_189: - LONG $0x247c894c; BYTE $0x30 // mov qword [rsp + 48], r15 +LBB2_206: + LONG $0x247c894c; BYTE $0x10 // mov qword [rsp + 16], r15 LONG $0x06e7c149 // shl r15, 6 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xff // mov rdi, r15 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 LONG $0x34b70f46; BYTE $0x3a // movzx r14d, word [rdx + r15] - LONG $0x44b70f42; WORD $0x023a // movzx eax, word [rdx + r15 + 2] - LONG $0x54b70f46; WORD $0x043a // movzx r10d, word [rdx + r15 + 4] - LONG $0x74b70f42; WORD $0x063a // movzx esi, word [rdx + r15 + 6] - LONG $0x5cb70f46; WORD $0x083a // movzx r11d, word [rdx + r15 + 8] - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - LONG $0x40c88349 // or r8, 64 - LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + LONG $0x74b70f42; WORD $0x023a // movzx esi, word [rdx + r15 + 2] + LONG $0x5cb70f46; WORD $0x043a // movzx r11d, word [rdx + r15 + 4] + LONG $0x6cb70f46; WORD $0x063a // movzx r13d, word [rdx + r15 + 6] + LONG $0x54b70f46; WORD $0x083a // movzx r10d, word [rdx + r15 + 8] + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + LONG $0x40c98349 // or r9, 64 + LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 + LONG $0x00cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 256 LONG $0x40c98148; WORD $0x0001; BYTE $0x00 // or rcx, 320 - LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 - LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 + LONG $0x01c00d48; WORD $0x0000 // or rax, 448 LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d - LONG $0xc40f4266; WORD $0x0224; BYTE $0x01 // pinsrw xmm4, word [rdx + r8], 1 - LONG $0xc40f4266; WORD $0x0a24; BYTE $0x02 // pinsrw xmm4, word [rdx + r9], 2 + LONG $0xc40f4266; WORD $0x0a24; BYTE $0x01 // pinsrw xmm4, word [rdx + r9], 1 + LONG $0xc40f4266; WORD $0x0224; BYTE $0x02 // pinsrw xmm4, word [rdx + r8], 2 LONG $0xc40f4266; WORD $0x2224; BYTE $0x03 // pinsrw xmm4, word [rdx + r12], 3 - LONG $0xc40f4266; WORD $0x2a24; BYTE $0x04 // pinsrw xmm4, word [rdx + r13], 4 + LONG $0x24c40f66; WORD $0x043a // pinsrw xmm4, word [rdx + rdi], 4 LONG $0x24c40f66; WORD $0x050a // pinsrw xmm4, word [rdx + rcx], 5 - LONG $0x24c40f66; WORD $0x063a // pinsrw xmm4, word [rdx + rdi], 6 - LONG $0x24c40f66; WORD $0x071a // pinsrw xmm4, word [rdx + rbx], 7 + LONG $0x24c40f66; WORD $0x061a // pinsrw xmm4, word [rdx + rbx], 6 + LONG $0x24c40f66; WORD $0x0702 // pinsrw xmm4, word [rdx + rax], 7 LONG $0x74b70f46; WORD $0x0a3a // movzx r14d, word [rdx + r15 + 10] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x01020274c40f4266 // pinsrw xmm6, word [rdx + r8 + 2], 1 - QUAD $0x02020a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 2], 2 + LONG $0xf66e0f66 // movd xmm6, esi + QUAD $0x01020a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 2], 1 + QUAD $0x02020274c40f4266 // pinsrw xmm6, word [rdx + r8 + 2], 2 QUAD $0x03022274c40f4266 // pinsrw xmm6, word [rdx + r12 + 2], 3 - LONG $0x44b70f42; WORD $0x0c3a // movzx eax, word [rdx + r15 + 12] - LONG $0x28244489 // mov dword [rsp + 40], eax - QUAD $0x04022a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 2], 4 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x44b70f42; WORD $0x0e3a // movzx eax, word [rdx + r15 + 14] - LONG $0x18244489 // mov dword [rsp + 24], eax + LONG $0x74b70f42; WORD $0x0c3a // movzx esi, word [rdx + r15 + 12] + LONG $0x08247489 // mov dword [rsp + 8], esi + LONG $0x74c40f66; WORD $0x023a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 2], 4 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x5cb70f46; WORD $0x0e3a // movzx r11d, word [rdx + r15 + 14] LONG $0x74c40f66; WORD $0x020a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 2], 5 - LONG $0xee6e0f66 // movd xmm5, esi + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d LONG $0x74b70f42; WORD $0x103a // movzx esi, word [rdx + r15 + 16] - LONG $0x74c40f66; WORD $0x023a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 2], 6 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x44b70f42; WORD $0x123a // movzx eax, word [rdx + r15 + 18] - LONG $0x38244489 // mov dword [rsp + 56], eax - LONG $0x74c40f66; WORD $0x021a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 2], 7 + LONG $0x20247489 // mov dword [rsp + 32], esi + LONG $0x74c40f66; WORD $0x021a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 2], 6 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x74b70f42; WORD $0x123a // movzx esi, word [rdx + r15 + 18] + LONG $0x28247489 // mov dword [rsp + 40], esi + LONG $0x74c40f66; WORD $0x0202; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 2], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xce6f0f66 // movdqa xmm1, xmm6 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xcef80f66 // psubb xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d - LONG $0x54b70f46; WORD $0x143a // movzx r10d, word [rdx + r15 + 20] + LONG $0x6cb70f46; WORD $0x143a // movzx r13d, word [rdx + r15 + 20] LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - QUAD $0x01040254c40f4266 // pinsrw xmm2, word [rdx + r8 + 4], 1 - QUAD $0x02040a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 4], 2 + QUAD $0x01040a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 4], 1 + QUAD $0x02040254c40f4266 // pinsrw xmm2, word [rdx + r8 + 4], 2 QUAD $0x03042254c40f4266 // pinsrw xmm2, word [rdx + r12 + 4], 3 - QUAD $0x04042a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 4], 4 + LONG $0x54c40f66; WORD $0x043a; BYTE $0x04 // pinsrw xmm2, word [rdx + rdi + 4], 4 LONG $0x54c40f66; WORD $0x040a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 4], 5 - LONG $0x54c40f66; WORD $0x043a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 4], 6 - LONG $0x54c40f66; WORD $0x041a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 4], 7 - QUAD $0x0106026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 6], 1 - QUAD $0x02060a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 6], 2 + LONG $0x54c40f66; WORD $0x041a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 4], 6 + LONG $0x54c40f66; WORD $0x0402; BYTE $0x07 // pinsrw xmm2, word [rdx + rax + 4], 7 + QUAD $0x01060a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 6], 1 + QUAD $0x0206026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 6], 2 QUAD $0x0306226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 6], 3 - QUAD $0x04062a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 6], 4 + LONG $0x6cc40f66; WORD $0x063a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 6], 4 LONG $0x6cc40f66; WORD $0x060a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 6], 5 - LONG $0x6cc40f66; WORD $0x063a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 6], 6 - LONG $0x6cc40f66; WORD $0x061a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 6], 7 - QUAD $0x0108025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 8], 1 - QUAD $0x02080a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 8], 2 + LONG $0x6cc40f66; WORD $0x061a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 6], 6 + LONG $0x6cc40f66; WORD $0x0602; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 6], 7 + QUAD $0x01080a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 8], 1 + QUAD $0x0208025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 8], 2 QUAD $0x0308225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 8], 3 - QUAD $0x04082a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 8], 4 + LONG $0x5cc40f66; WORD $0x083a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 8], 4 LONG $0x5cc40f66; WORD $0x080a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 8], 5 - LONG $0x5cc40f66; WORD $0x083a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 8], 6 - LONG $0x5cc40f66; WORD $0x081a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 8], 7 + LONG $0x5cc40f66; WORD $0x081a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 8], 6 + LONG $0x5cc40f66; WORD $0x0802; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 8], 7 LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x7c6e0f66; WORD $0x2824 // movd xmm7, dword [rsp + 40] - LONG $0x44b70f42; WORD $0x163a // movzx eax, word [rdx + r15 + 22] + LONG $0x7c6e0f66; WORD $0x0824 // movd xmm7, dword [rsp + 8] + LONG $0x74b70f46; WORD $0x163a // movzx r14d, word [rdx + r15 + 22] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 LONG $0xf2710f66; BYTE $0x02 // psllw xmm2, 2 LONG $0xdb0f4166; BYTE $0xd1 // pand xmm2, xmm9 LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0x646e0f66; WORD $0x1824 // movd xmm4, dword [rsp + 24] - LONG $0x5cb70f46; WORD $0x183a // movzx r11d, word [rdx + r15 + 24] + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x74b70f42; WORD $0x183a // movzx esi, word [rdx + r15 + 24] LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 @@ -14376,25 +12957,25 @@ LBB2_189: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x74b70f42; WORD $0x1a3a // movzx esi, word [rdx + r15 + 26] - QUAD $0x010a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 10], 1 - QUAD $0x020a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 10], 2 + LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] + LONG $0x54b70f46; WORD $0x1a3a // movzx r10d, word [rdx + r15 + 26] + QUAD $0x010a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 10], 1 + QUAD $0x020a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 10], 2 QUAD $0x030a2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 10], 3 - QUAD $0x040a2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 10], 4 + LONG $0x74c40f66; WORD $0x0a3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 10], 4 LONG $0x74c40f66; WORD $0x0a0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 10], 5 - LONG $0x74c40f66; WORD $0x0a3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 10], 6 - LONG $0x74c40f66; WORD $0x0a1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 10], 7 - QUAD $0x010c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 12], 1 - QUAD $0x020c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 12], 2 + LONG $0x74c40f66; WORD $0x0a1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 10], 6 + LONG $0x74c40f66; WORD $0x0a02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 10], 7 + QUAD $0x010c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 12], 1 + QUAD $0x020c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 12], 2 QUAD $0x030c227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 12], 3 - QUAD $0x040c2a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 12], 4 + LONG $0x7cc40f66; WORD $0x0c3a; BYTE $0x04 // pinsrw xmm7, word [rdx + rdi + 12], 4 LONG $0x7cc40f66; WORD $0x0c0a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 12], 5 - LONG $0x7cc40f66; WORD $0x0c3a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 12], 6 - LONG $0x7cc40f66; WORD $0x0c1a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 12], 7 + LONG $0x7cc40f66; WORD $0x0c1a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 12], 6 + LONG $0x7cc40f66; WORD $0x0c02; BYTE $0x07 // pinsrw xmm7, word [rdx + rax + 12], 7 LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4466; WORD $0x2444; BYTE $0x38 // movd xmm8, dword [rsp + 56] - LONG $0x74b70f46; WORD $0x1c3a // movzx r14d, word [rdx + r15 + 28] + LONG $0x6e0f4466; WORD $0x2444; BYTE $0x28 // movd xmm8, dword [rsp + 40] + LONG $0x5cb70f46; WORD $0x1c3a // movzx r11d, word [rdx + r15 + 28] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -14406,81 +12987,81 @@ LBB2_189: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d - LONG $0x54b70f46; WORD $0x1e3a // movzx r10d, word [rdx + r15 + 30] - QUAD $0x010e0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 14], 1 - QUAD $0x020e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 14], 2 + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d + LONG $0x6cb70f46; WORD $0x1e3a // movzx r13d, word [rdx + r15 + 30] + QUAD $0x010e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 14], 1 + QUAD $0x020e0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 14], 2 QUAD $0x030e2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 14], 3 - QUAD $0x040e2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 14], 4 + LONG $0x64c40f66; WORD $0x0e3a; BYTE $0x04 // pinsrw xmm4, word [rdx + rdi + 14], 4 LONG $0x64c40f66; WORD $0x0e0a; BYTE $0x05 // pinsrw xmm4, word [rdx + rcx + 14], 5 - LONG $0x64c40f66; WORD $0x0e3a; BYTE $0x06 // pinsrw xmm4, word [rdx + rdi + 14], 6 - LONG $0x64c40f66; WORD $0x0e1a; BYTE $0x07 // pinsrw xmm4, word [rdx + rbx + 14], 7 - QUAD $0x01120244c40f4666 // pinsrw xmm8, word [rdx + r8 + 18], 1 - QUAD $0x02120a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 18], 2 + LONG $0x64c40f66; WORD $0x0e1a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 14], 6 + LONG $0x64c40f66; WORD $0x0e02; BYTE $0x07 // pinsrw xmm4, word [rdx + rax + 14], 7 + QUAD $0x01120a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 18], 1 + QUAD $0x02120244c40f4666 // pinsrw xmm8, word [rdx + r8 + 18], 2 QUAD $0x03122244c40f4666 // pinsrw xmm8, word [rdx + r12 + 18], 3 - QUAD $0x04122a44c40f4666 // pinsrw xmm8, word [rdx + r13 + 18], 4 + QUAD $0x04123a44c40f4466 // pinsrw xmm8, word [rdx + rdi + 18], 4 QUAD $0x05120a44c40f4466 // pinsrw xmm8, word [rdx + rcx + 18], 5 - QUAD $0x06123a44c40f4466 // pinsrw xmm8, word [rdx + rdi + 18], 6 - QUAD $0x07121a44c40f4466 // pinsrw xmm8, word [rdx + rbx + 18], 7 + QUAD $0x06121a44c40f4466 // pinsrw xmm8, word [rdx + rbx + 18], 6 + QUAD $0x07120244c40f4466 // pinsrw xmm8, word [rdx + rax + 18], 7 LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f42; WORD $0x203a // movzx eax, word [rdx + r15 + 32] + LONG $0x6e0f4166; BYTE $0xd6 // movd xmm2, r14d + LONG $0x74b70f46; WORD $0x203a // movzx r14d, word [rdx + r15 + 32] LONG $0xe3eb0f66 // por xmm4, xmm3 LONG $0x750f4466; BYTE $0xc0 // pcmpeqw xmm8, xmm0 LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf80f4166; BYTE $0xf8 // psubb xmm7, xmm8 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x5cb70f46; WORD $0x223a // movzx r11d, word [rdx + r15 + 34] - QUAD $0x0110024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 16], 1 - QUAD $0x02100a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 16], 2 + LONG $0xde6e0f66 // movd xmm3, esi + LONG $0x74b70f42; WORD $0x223a // movzx esi, word [rdx + r15 + 34] + LONG $0x20247489 // mov dword [rsp + 32], esi + QUAD $0x01100a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 16], 1 + QUAD $0x0210024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 16], 2 QUAD $0x0310224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 16], 3 - QUAD $0x04102a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 16], 4 + LONG $0x4cc40f66; WORD $0x103a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 16], 4 LONG $0x4cc40f66; WORD $0x100a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 16], 5 - LONG $0x4cc40f66; WORD $0x103a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 16], 6 - LONG $0x4cc40f66; WORD $0x101a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 16], 7 + LONG $0x4cc40f66; WORD $0x101a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 16], 6 + LONG $0x4cc40f66; WORD $0x1002; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 16], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0xf66e0f66 // movd xmm6, esi - LONG $0x74b70f42; WORD $0x243a // movzx esi, word [rdx + r15 + 36] - LONG $0x38247489 // mov dword [rsp + 56], esi - QUAD $0x0114026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 20], 1 - QUAD $0x02140a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 20], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x243a // movzx r10d, word [rdx + r15 + 36] + QUAD $0x01140a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 20], 1 + QUAD $0x0214026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 20], 2 QUAD $0x0314226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 20], 3 - QUAD $0x04142a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 20], 4 + LONG $0x6cc40f66; WORD $0x143a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 20], 4 LONG $0x6cc40f66; WORD $0x140a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 20], 5 - LONG $0x6cc40f66; WORD $0x143a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 20], 6 - LONG $0x6cc40f66; WORD $0x141a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 20], 7 + LONG $0x6cc40f66; WORD $0x141a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 20], 6 + LONG $0x6cc40f66; WORD $0x1402; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 20], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 LONG $0xefeb0f66 // por xmm5, xmm7 - LONG $0x6e0f4166; BYTE $0xfe // movd xmm7, r14d + LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d LONG $0x74b70f42; WORD $0x263a // movzx esi, word [rdx + r15 + 38] - LONG $0x18247489 // mov dword [rsp + 24], esi - QUAD $0x01160254c40f4266 // pinsrw xmm2, word [rdx + r8 + 22], 1 - QUAD $0x02160a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 22], 2 + LONG $0x08247489 // mov dword [rsp + 8], esi + QUAD $0x01160a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 22], 1 + QUAD $0x02160254c40f4266 // pinsrw xmm2, word [rdx + r8 + 22], 2 QUAD $0x03162254c40f4266 // pinsrw xmm2, word [rdx + r12 + 22], 3 - QUAD $0x04162a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 22], 4 + LONG $0x54c40f66; WORD $0x163a; BYTE $0x04 // pinsrw xmm2, word [rdx + rdi + 22], 4 LONG $0x54c40f66; WORD $0x160a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 22], 5 - LONG $0x54c40f66; WORD $0x163a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 22], 6 - LONG $0x54c40f66; WORD $0x161a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 22], 7 - QUAD $0x0118025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 24], 1 - QUAD $0x02180a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 24], 2 + LONG $0x54c40f66; WORD $0x161a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 22], 6 + LONG $0x54c40f66; WORD $0x1602; BYTE $0x07 // pinsrw xmm2, word [rdx + rax + 22], 7 + QUAD $0x01180a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 24], 1 + QUAD $0x0218025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 24], 2 QUAD $0x0318225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 24], 3 - QUAD $0x04182a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 24], 4 + LONG $0x5cc40f66; WORD $0x183a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 24], 4 LONG $0x5cc40f66; WORD $0x180a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 24], 5 - LONG $0x5cc40f66; WORD $0x183a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 24], 6 - LONG $0x5cc40f66; WORD $0x181a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 24], 7 + LONG $0x5cc40f66; WORD $0x181a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 24], 6 + LONG $0x5cc40f66; WORD $0x1802; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 24], 7 LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 @@ -14492,33 +13073,32 @@ LBB2_189: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x74b70f46; WORD $0x283a // movzx r14d, word [rdx + r15 + 40] + LONG $0x6e0f4166; BYTE $0xd5 // movd xmm2, r13d + LONG $0x5cb70f46; WORD $0x283a // movzx r11d, word [rdx + r15 + 40] LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f42; WORD $0x2a3a // movzx eax, word [rdx + r15 + 42] - LONG $0x28244489 // mov dword [rsp + 40], eax - QUAD $0x011a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 26], 1 - QUAD $0x021a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 26], 2 + LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d + LONG $0x74b70f46; WORD $0x2a3a // movzx r14d, word [rdx + r15 + 42] + QUAD $0x011a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 26], 1 + QUAD $0x021a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 26], 2 QUAD $0x031a2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 26], 3 - QUAD $0x041a2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 26], 4 + LONG $0x74c40f66; WORD $0x1a3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 26], 4 LONG $0x74c40f66; WORD $0x1a0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 26], 5 - LONG $0x74c40f66; WORD $0x1a3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 26], 6 - LONG $0x74c40f66; WORD $0x1a1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 26], 7 - QUAD $0x011c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 28], 1 - QUAD $0x021c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 28], 2 + LONG $0x74c40f66; WORD $0x1a1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 26], 6 + LONG $0x74c40f66; WORD $0x1a02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 26], 7 + QUAD $0x011c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 28], 1 + QUAD $0x021c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 28], 2 QUAD $0x031c227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 28], 3 - QUAD $0x041c2a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 28], 4 + LONG $0x7cc40f66; WORD $0x1c3a; BYTE $0x04 // pinsrw xmm7, word [rdx + rdi + 28], 4 LONG $0x7cc40f66; WORD $0x1c0a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 28], 5 - LONG $0x7cc40f66; WORD $0x1c3a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 28], 6 - LONG $0x7cc40f66; WORD $0x1c1a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 28], 7 - QUAD $0x011e0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 30], 1 - QUAD $0x021e0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 30], 2 + LONG $0x7cc40f66; WORD $0x1c1a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 28], 6 + LONG $0x7cc40f66; WORD $0x1c02; BYTE $0x07 // pinsrw xmm7, word [rdx + rax + 28], 7 + QUAD $0x011e0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 30], 1 + QUAD $0x021e0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 30], 2 QUAD $0x031e2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 30], 3 - QUAD $0x041e2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 30], 4 + LONG $0x54c40f66; WORD $0x1e3a; BYTE $0x04 // pinsrw xmm2, word [rdx + rdi + 30], 4 LONG $0x54c40f66; WORD $0x1e0a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 30], 5 - LONG $0x54c40f66; WORD $0x1e3a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 30], 6 - LONG $0x54c40f66; WORD $0x1e1a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 30], 7 + LONG $0x54c40f66; WORD $0x1e1a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 30], 6 + LONG $0x54c40f66; WORD $0x1e02; BYTE $0x07 // pinsrw xmm2, word [rdx + rax + 30], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -14530,72 +13110,73 @@ LBB2_189: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d - LONG $0x54b70f46; WORD $0x2c3a // movzx r10d, word [rdx + r15 + 44] + LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] + LONG $0x6cb70f46; WORD $0x2c3a // movzx r13d, word [rdx + r15 + 44] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 LONG $0xdb0f4166; BYTE $0xd6 // pand xmm2, xmm14 LONG $0xd7eb0f66 // por xmm2, xmm7 - LONG $0x746e0f66; WORD $0x3824 // movd xmm6, dword [rsp + 56] - LONG $0x74b70f42; WORD $0x2e3a // movzx esi, word [rdx + r15 + 46] - QUAD $0x0120026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 32], 1 - QUAD $0x02200a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 32], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x2e3a // movzx r10d, word [rdx + r15 + 46] + QUAD $0x01200a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 32], 1 + QUAD $0x0220026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 32], 2 QUAD $0x0320226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 32], 3 - QUAD $0x04202a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 32], 4 + LONG $0x6cc40f66; WORD $0x203a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 32], 4 LONG $0x6cc40f66; WORD $0x200a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 32], 5 - LONG $0x6cc40f66; WORD $0x203a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 32], 6 - QUAD $0x0122024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 34], 1 - QUAD $0x02220a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 34], 2 + LONG $0x6cc40f66; WORD $0x201a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 32], 6 + QUAD $0x01220a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 34], 1 + QUAD $0x0222024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 34], 2 QUAD $0x0322224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 34], 3 - QUAD $0x04222a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 34], 4 + LONG $0x4cc40f66; WORD $0x223a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 34], 4 LONG $0x4cc40f66; WORD $0x220a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 34], 5 - LONG $0x4cc40f66; WORD $0x223a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 34], 6 - LONG $0x4cc40f66; WORD $0x221a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 34], 7 + LONG $0x4cc40f66; WORD $0x221a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 34], 6 + LONG $0x4cc40f66; WORD $0x2202; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 34], 7 LONG $0xd3eb0f66 // por xmm2, xmm3 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xf96f0f66 // movdqa xmm7, xmm1 LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf9f80f66 // psubb xmm7, xmm1 - LONG $0x5c6e0f66; WORD $0x1824 // movd xmm3, dword [rsp + 24] - LONG $0x5cb70f46; WORD $0x303a // movzx r11d, word [rdx + r15 + 48] - LONG $0x6cc40f66; WORD $0x201a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 32], 7 + LONG $0x5c6e0f66; WORD $0x0824 // movd xmm3, dword [rsp + 8] + LONG $0x74b70f42; WORD $0x303a // movzx esi, word [rdx + r15 + 48] + LONG $0x08247489 // mov dword [rsp + 8], esi + LONG $0x6cc40f66; WORD $0x2002; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 32], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - QUAD $0x01240274c40f4266 // pinsrw xmm6, word [rdx + r8 + 36], 1 - QUAD $0x02240a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 36], 2 + QUAD $0x01240a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 36], 1 + QUAD $0x02240274c40f4266 // pinsrw xmm6, word [rdx + r8 + 36], 2 QUAD $0x03242274c40f4266 // pinsrw xmm6, word [rdx + r12 + 36], 3 - QUAD $0x04242a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 36], 4 + LONG $0x74c40f66; WORD $0x243a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 36], 4 LONG $0x74c40f66; WORD $0x240a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 36], 5 - LONG $0x74c40f66; WORD $0x243a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 36], 6 - LONG $0x74c40f66; WORD $0x241a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 36], 7 - QUAD $0x0126025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 38], 1 - QUAD $0x02260a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 38], 2 + LONG $0x74c40f66; WORD $0x241a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 36], 6 + LONG $0x74c40f66; WORD $0x2402; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 36], 7 + QUAD $0x01260a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 38], 1 + QUAD $0x0226025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 38], 2 QUAD $0x0326225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 38], 3 - QUAD $0x04262a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 38], 4 + LONG $0x5cc40f66; WORD $0x263a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 38], 4 LONG $0x5cc40f66; WORD $0x260a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 38], 5 - LONG $0x5cc40f66; WORD $0x263a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 38], 6 - LONG $0x5cc40f66; WORD $0x261a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 38], 7 + LONG $0x5cc40f66; WORD $0x261a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 38], 6 + LONG $0x5cc40f66; WORD $0x2602; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 38], 7 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d - QUAD $0x0128026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 40], 1 - QUAD $0x02280a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 40], 2 + LONG $0x6e0f4166; BYTE $0xeb // movd xmm5, r11d + QUAD $0x01280a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 40], 1 + QUAD $0x0228026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 40], 2 QUAD $0x0328226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 40], 3 - QUAD $0x04282a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 40], 4 + LONG $0x6cc40f66; WORD $0x283a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 40], 4 LONG $0x6cc40f66; WORD $0x280a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 40], 5 - LONG $0x6cc40f66; WORD $0x283a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 40], 6 - LONG $0x44b70f42; WORD $0x323a // movzx eax, word [rdx + r15 + 50] + LONG $0x6cc40f66; WORD $0x281a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 40], 6 + LONG $0x74b70f42; WORD $0x323a // movzx esi, word [rdx + r15 + 50] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] - LONG $0x74b70f46; WORD $0x343a // movzx r14d, word [rdx + r15 + 52] - LONG $0x6cc40f66; WORD $0x281a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 40], 7 + LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d + LONG $0x5cb70f46; WORD $0x343a // movzx r11d, word [rdx + r15 + 52] + LONG $0x6cc40f66; WORD $0x2802; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 40], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 @@ -14607,25 +13188,25 @@ LBB2_189: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xebeb0f66 // por xmm5, xmm3 - LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d - LONG $0x54b70f46; WORD $0x363a // movzx r10d, word [rdx + r15 + 54] - QUAD $0x012a024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 42], 1 - QUAD $0x022a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 42], 2 + LONG $0x6e0f4166; BYTE $0xfd // movd xmm7, r13d + LONG $0x74b70f46; WORD $0x363a // movzx r14d, word [rdx + r15 + 54] + QUAD $0x012a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 42], 1 + QUAD $0x022a024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 42], 2 QUAD $0x032a224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 42], 3 - QUAD $0x042a2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 42], 4 + LONG $0x4cc40f66; WORD $0x2a3a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 42], 4 LONG $0x4cc40f66; WORD $0x2a0a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 42], 5 - LONG $0x4cc40f66; WORD $0x2a3a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 42], 6 - LONG $0x4cc40f66; WORD $0x2a1a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 42], 7 - QUAD $0x012c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 44], 1 - QUAD $0x022c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 44], 2 + LONG $0x4cc40f66; WORD $0x2a1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 42], 6 + LONG $0x4cc40f66; WORD $0x2a02; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 42], 7 + QUAD $0x012c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 44], 1 + QUAD $0x022c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 44], 2 QUAD $0x032c227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 44], 3 - QUAD $0x042c2a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 44], 4 + LONG $0x7cc40f66; WORD $0x2c3a; BYTE $0x04 // pinsrw xmm7, word [rdx + rdi + 44], 4 LONG $0x7cc40f66; WORD $0x2c0a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 44], 5 - LONG $0x7cc40f66; WORD $0x2c3a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 44], 6 + LONG $0x7cc40f66; WORD $0x2c1a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 44], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0xde6e0f66 // movd xmm3, esi - LONG $0x74b70f42; WORD $0x383a // movzx esi, word [rdx + r15 + 56] - LONG $0x7cc40f66; WORD $0x2c1a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 44], 7 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x54b70f46; WORD $0x383a // movzx r10d, word [rdx + r15 + 56] + LONG $0x7cc40f66; WORD $0x2c02; BYTE $0x07 // pinsrw xmm7, word [rdx + rax + 44], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 @@ -14637,77 +13218,77 @@ LBB2_189: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - LONG $0x5cb70f46; WORD $0x3a3a // movzx r11d, word [rdx + r15 + 58] - QUAD $0x012e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 46], 1 - QUAD $0x022e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 46], 2 + LONG $0x746e0f66; WORD $0x0824 // movd xmm6, dword [rsp + 8] + LONG $0x6cb70f46; WORD $0x3a3a // movzx r13d, word [rdx + r15 + 58] + QUAD $0x012e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 46], 1 + QUAD $0x022e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 46], 2 QUAD $0x032e225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 46], 3 - QUAD $0x042e2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 46], 4 + LONG $0x5cc40f66; WORD $0x2e3a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 46], 4 LONG $0x5cc40f66; WORD $0x2e0a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 46], 5 - LONG $0x5cc40f66; WORD $0x2e3a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 46], 6 - LONG $0x5cc40f66; WORD $0x2e1a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 46], 7 + LONG $0x5cc40f66; WORD $0x2e1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 46], 6 + LONG $0x5cc40f66; WORD $0x2e02; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 46], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 LONG $0xdfeb0f66 // por xmm3, xmm7 - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x44b70f42; WORD $0x3c3a // movzx eax, word [rdx + r15 + 60] + LONG $0xce6e0f66 // movd xmm1, esi + LONG $0x74b70f42; WORD $0x3c3a // movzx esi, word [rdx + r15 + 60] LONG $0x7cb70f46; WORD $0x3e3a // movzx r15d, word [rdx + r15 + 62] - QUAD $0x0132024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 50], 1 - QUAD $0x02320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 2 + QUAD $0x01320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 1 + QUAD $0x0232024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 50], 2 QUAD $0x0332224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 50], 3 - QUAD $0x04322a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 50], 4 + LONG $0x4cc40f66; WORD $0x323a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 50], 4 LONG $0x4cc40f66; WORD $0x320a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 50], 5 - LONG $0x4cc40f66; WORD $0x323a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 50], 6 - LONG $0x4cc40f66; WORD $0x321a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 50], 7 + LONG $0x4cc40f66; WORD $0x321a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 50], 6 + LONG $0x4cc40f66; WORD $0x3202; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 50], 7 LONG $0xddeb0f66 // por xmm3, xmm5 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xe96f0f66 // movdqa xmm5, xmm1 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xe9f80f66 // psubb xmm5, xmm1 - LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d - QUAD $0x01300274c40f4266 // pinsrw xmm6, word [rdx + r8 + 48], 1 - QUAD $0x02300a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 48], 2 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + QUAD $0x01300a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 48], 1 + QUAD $0x02300274c40f4266 // pinsrw xmm6, word [rdx + r8 + 48], 2 QUAD $0x03302274c40f4266 // pinsrw xmm6, word [rdx + r12 + 48], 3 - QUAD $0x04302a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 48], 4 + LONG $0x74c40f66; WORD $0x303a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 48], 4 LONG $0x74c40f66; WORD $0x300a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 48], 5 - LONG $0x74c40f66; WORD $0x303a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 48], 6 - LONG $0x74c40f66; WORD $0x301a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 48], 7 + LONG $0x74c40f66; WORD $0x301a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 48], 6 + LONG $0x74c40f66; WORD $0x3002; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 48], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 - QUAD $0x0134024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 52], 1 - QUAD $0x02340a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 52], 2 + QUAD $0x01340a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 52], 1 + QUAD $0x0234024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 52], 2 QUAD $0x0334224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 52], 3 - QUAD $0x04342a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 52], 4 + LONG $0x4cc40f66; WORD $0x343a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 52], 4 LONG $0x4cc40f66; WORD $0x340a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 52], 5 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0x4cc40f66; WORD $0x343a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 52], 6 + LONG $0x4cc40f66; WORD $0x341a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 52], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d - LONG $0x4cc40f66; WORD $0x341a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 52], 7 + LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d + LONG $0x4cc40f66; WORD $0x3402; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 52], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xf1710f66; BYTE $0x02 // psllw xmm1, 2 LONG $0xdb0f4166; BYTE $0xc9 // pand xmm1, xmm9 LONG $0xcdeb0f66 // por xmm1, xmm5 - LONG $0xee6e0f66 // movd xmm5, esi - QUAD $0x01360274c40f4266 // pinsrw xmm6, word [rdx + r8 + 54], 1 - QUAD $0x02360a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 54], 2 + LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d + QUAD $0x01360a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 54], 1 + QUAD $0x02360274c40f4266 // pinsrw xmm6, word [rdx + r8 + 54], 2 QUAD $0x03362274c40f4266 // pinsrw xmm6, word [rdx + r12 + 54], 3 - QUAD $0x04362a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 54], 4 + LONG $0x74c40f66; WORD $0x363a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 54], 4 LONG $0x74c40f66; WORD $0x360a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 54], 5 - LONG $0x74c40f66; WORD $0x363a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 54], 6 - LONG $0x74c40f66; WORD $0x361a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 54], 7 - QUAD $0x0138026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 56], 1 - QUAD $0x02380a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 56], 2 + LONG $0x74c40f66; WORD $0x361a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 54], 6 + LONG $0x74c40f66; WORD $0x3602; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 54], 7 + QUAD $0x01380a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 56], 1 + QUAD $0x0238026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 56], 2 QUAD $0x0338226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 56], 3 - QUAD $0x04382a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 56], 4 + LONG $0x6cc40f66; WORD $0x383a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 56], 4 LONG $0x6cc40f66; WORD $0x380a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 56], 5 - LONG $0x6cc40f66; WORD $0x383a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 56], 6 - LONG $0x6cc40f66; WORD $0x381a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 56], 7 + LONG $0x6cc40f66; WORD $0x381a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 56], 6 + LONG $0x6cc40f66; WORD $0x3802; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 56], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -14719,24 +13300,23 @@ LBB2_189: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - LONG $0x24348b48 // mov rsi, qword [rsp] - QUAD $0x013a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 58], 1 - QUAD $0x023a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 58], 2 + LONG $0x6e0f4166; BYTE $0xf5 // movd xmm6, r13d + QUAD $0x013a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 58], 1 + QUAD $0x023a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 58], 2 QUAD $0x033a2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 58], 3 - QUAD $0x043a2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 58], 4 + LONG $0x74c40f66; WORD $0x3a3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 58], 4 LONG $0x74c40f66; WORD $0x3a0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 58], 5 - LONG $0x74c40f66; WORD $0x3a3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 58], 6 - LONG $0x74c40f66; WORD $0x3a1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 58], 7 + LONG $0x74c40f66; WORD $0x3a1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 58], 6 + LONG $0x74c40f66; WORD $0x3a02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 58], 7 LONG $0xe9eb0f66 // por xmm5, xmm1 - LONG $0xc86e0f66 // movd xmm1, eax - QUAD $0x013c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 60], 1 - QUAD $0x023c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 60], 2 + LONG $0xce6e0f66 // movd xmm1, esi + QUAD $0x013c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 60], 1 + QUAD $0x023c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 60], 2 QUAD $0x033c224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 60], 3 - QUAD $0x043c2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 60], 4 + LONG $0x4cc40f66; WORD $0x3c3a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 60], 4 LONG $0x4cc40f66; WORD $0x3c0a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 60], 5 - LONG $0x4cc40f66; WORD $0x3c3a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 60], 6 - LONG $0x4cc40f66; WORD $0x3c1a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 60], 7 + LONG $0x4cc40f66; WORD $0x3c1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 60], 6 + LONG $0x4cc40f66; WORD $0x3c02; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 60], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -14749,13 +13329,14 @@ LBB2_189: LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 LONG $0xceeb0f66 // por xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf7 // movd xmm6, r15d - QUAD $0x013e0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 62], 1 - QUAD $0x023e0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 62], 2 + QUAD $0x013e0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 62], 1 + QUAD $0x023e0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 62], 2 QUAD $0x033e2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 62], 3 - QUAD $0x043e2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 62], 4 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + LONG $0x74c40f66; WORD $0x3e3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 62], 4 LONG $0x74c40f66; WORD $0x3e0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 62], 5 - LONG $0x74c40f66; WORD $0x3e3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 62], 6 - LONG $0x74c40f66; WORD $0x3e1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 62], 7 + LONG $0x74c40f66; WORD $0x3e1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 62], 6 + LONG $0x74c40f66; WORD $0x3e02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 62], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 @@ -14773,33 +13354,32 @@ LBB2_189: LONG $0xde600f66 // punpcklbw xmm3, xmm6 LONG $0xe2600f66 // punpcklbw xmm4, xmm2 LONG $0xe3610f66 // punpcklwd xmm4, xmm3 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] LONG $0x247f0ff3; BYTE $0x8e // movdqu oword [rsi + 4*rcx], xmm4 - LONG $0x24348948 // mov qword [rsp], rsi LONG $0x4c7f0ff3; WORD $0x108e // movdqu oword [rsi + 4*rcx + 16], xmm1 LONG $0x08c18348 // add rcx, 8 WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB2_189 + LONG $0x244c3b48; BYTE $0x18 // cmp rcx, qword [rsp + 24] + JNE LBB2_206 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x244c3b48; BYTE $0x18 // cmp rcx, qword [rsp + 24] QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - LONG $0x247c3b4c; BYTE $0x20 // cmp r15, qword [rsp + 32] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - LONG $0x24748b44; BYTE $0x08 // mov r14d, dword [rsp + 8] - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - JNE LBB2_92 - JMP LBB2_139 + LONG $0x246c8b44; BYTE $0x30 // mov r13d, dword [rsp + 48] + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + JNE LBB2_70 + JMP LBB2_134 -LBB2_191: - LONG $0xf8e78349 // and r15, -8 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB2_208: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x244c8948; BYTE $0x18 // mov qword [rsp + 24], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24048948 // mov qword [rsp], rax + LONG $0x246c8944; BYTE $0x30 // mov dword [rsp + 48], r13d + LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 WORD $0x3145; BYTE $0xff // xor r15d, r15d @@ -14810,98 +13390,99 @@ LBB2_191: LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI2_4] */ LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI2_5] */ LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI2_6] */ + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 -LBB2_192: - LONG $0x247c894c; BYTE $0x30 // mov qword [rsp + 48], r15 +LBB2_209: + LONG $0x247c894c; BYTE $0x10 // mov qword [rsp + 16], r15 LONG $0x06e7c149 // shl r15, 6 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xff // mov rdi, r15 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 LONG $0x34b70f46; BYTE $0x3a // movzx r14d, word [rdx + r15] - LONG $0x44b70f42; WORD $0x023a // movzx eax, word [rdx + r15 + 2] - LONG $0x54b70f46; WORD $0x043a // movzx r10d, word [rdx + r15 + 4] - LONG $0x74b70f42; WORD $0x063a // movzx esi, word [rdx + r15 + 6] - LONG $0x5cb70f46; WORD $0x083a // movzx r11d, word [rdx + r15 + 8] - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - LONG $0x40c88349 // or r8, 64 - LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + LONG $0x74b70f42; WORD $0x023a // movzx esi, word [rdx + r15 + 2] + LONG $0x5cb70f46; WORD $0x043a // movzx r11d, word [rdx + r15 + 4] + LONG $0x6cb70f46; WORD $0x063a // movzx r13d, word [rdx + r15 + 6] + LONG $0x54b70f46; WORD $0x083a // movzx r10d, word [rdx + r15 + 8] + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + LONG $0x40c98349 // or r9, 64 + LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 + LONG $0x00cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 256 LONG $0x40c98148; WORD $0x0001; BYTE $0x00 // or rcx, 320 - LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 - LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 + LONG $0x01c00d48; WORD $0x0000 // or rax, 448 LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d - LONG $0xc40f4266; WORD $0x0224; BYTE $0x01 // pinsrw xmm4, word [rdx + r8], 1 - LONG $0xc40f4266; WORD $0x0a24; BYTE $0x02 // pinsrw xmm4, word [rdx + r9], 2 + LONG $0xc40f4266; WORD $0x0a24; BYTE $0x01 // pinsrw xmm4, word [rdx + r9], 1 + LONG $0xc40f4266; WORD $0x0224; BYTE $0x02 // pinsrw xmm4, word [rdx + r8], 2 LONG $0xc40f4266; WORD $0x2224; BYTE $0x03 // pinsrw xmm4, word [rdx + r12], 3 - LONG $0xc40f4266; WORD $0x2a24; BYTE $0x04 // pinsrw xmm4, word [rdx + r13], 4 + LONG $0x24c40f66; WORD $0x043a // pinsrw xmm4, word [rdx + rdi], 4 LONG $0x24c40f66; WORD $0x050a // pinsrw xmm4, word [rdx + rcx], 5 - LONG $0x24c40f66; WORD $0x063a // pinsrw xmm4, word [rdx + rdi], 6 - LONG $0x24c40f66; WORD $0x071a // pinsrw xmm4, word [rdx + rbx], 7 + LONG $0x24c40f66; WORD $0x061a // pinsrw xmm4, word [rdx + rbx], 6 + LONG $0x24c40f66; WORD $0x0702 // pinsrw xmm4, word [rdx + rax], 7 LONG $0x74b70f46; WORD $0x0a3a // movzx r14d, word [rdx + r15 + 10] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x01020274c40f4266 // pinsrw xmm6, word [rdx + r8 + 2], 1 - QUAD $0x02020a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 2], 2 + LONG $0xf66e0f66 // movd xmm6, esi + QUAD $0x01020a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 2], 1 + QUAD $0x02020274c40f4266 // pinsrw xmm6, word [rdx + r8 + 2], 2 QUAD $0x03022274c40f4266 // pinsrw xmm6, word [rdx + r12 + 2], 3 - LONG $0x44b70f42; WORD $0x0c3a // movzx eax, word [rdx + r15 + 12] - LONG $0x28244489 // mov dword [rsp + 40], eax - QUAD $0x04022a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 2], 4 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x44b70f42; WORD $0x0e3a // movzx eax, word [rdx + r15 + 14] - LONG $0x18244489 // mov dword [rsp + 24], eax + LONG $0x74b70f42; WORD $0x0c3a // movzx esi, word [rdx + r15 + 12] + LONG $0x08247489 // mov dword [rsp + 8], esi + LONG $0x74c40f66; WORD $0x023a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 2], 4 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x5cb70f46; WORD $0x0e3a // movzx r11d, word [rdx + r15 + 14] LONG $0x74c40f66; WORD $0x020a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 2], 5 - LONG $0xee6e0f66 // movd xmm5, esi + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d LONG $0x74b70f42; WORD $0x103a // movzx esi, word [rdx + r15 + 16] - LONG $0x74c40f66; WORD $0x023a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 2], 6 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x44b70f42; WORD $0x123a // movzx eax, word [rdx + r15 + 18] - LONG $0x38244489 // mov dword [rsp + 56], eax - LONG $0x74c40f66; WORD $0x021a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 2], 7 + LONG $0x20247489 // mov dword [rsp + 32], esi + LONG $0x74c40f66; WORD $0x021a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 2], 6 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x74b70f42; WORD $0x123a // movzx esi, word [rdx + r15 + 18] + LONG $0x28247489 // mov dword [rsp + 40], esi + LONG $0x74c40f66; WORD $0x0202; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 2], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xce6f0f66 // movdqa xmm1, xmm6 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xcef80f66 // psubb xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d - LONG $0x54b70f46; WORD $0x143a // movzx r10d, word [rdx + r15 + 20] + LONG $0x6cb70f46; WORD $0x143a // movzx r13d, word [rdx + r15 + 20] LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - QUAD $0x01040254c40f4266 // pinsrw xmm2, word [rdx + r8 + 4], 1 - QUAD $0x02040a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 4], 2 + QUAD $0x01040a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 4], 1 + QUAD $0x02040254c40f4266 // pinsrw xmm2, word [rdx + r8 + 4], 2 QUAD $0x03042254c40f4266 // pinsrw xmm2, word [rdx + r12 + 4], 3 - QUAD $0x04042a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 4], 4 + LONG $0x54c40f66; WORD $0x043a; BYTE $0x04 // pinsrw xmm2, word [rdx + rdi + 4], 4 LONG $0x54c40f66; WORD $0x040a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 4], 5 - LONG $0x54c40f66; WORD $0x043a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 4], 6 - LONG $0x54c40f66; WORD $0x041a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 4], 7 - QUAD $0x0106026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 6], 1 - QUAD $0x02060a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 6], 2 + LONG $0x54c40f66; WORD $0x041a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 4], 6 + LONG $0x54c40f66; WORD $0x0402; BYTE $0x07 // pinsrw xmm2, word [rdx + rax + 4], 7 + QUAD $0x01060a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 6], 1 + QUAD $0x0206026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 6], 2 QUAD $0x0306226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 6], 3 - QUAD $0x04062a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 6], 4 + LONG $0x6cc40f66; WORD $0x063a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 6], 4 LONG $0x6cc40f66; WORD $0x060a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 6], 5 - LONG $0x6cc40f66; WORD $0x063a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 6], 6 - LONG $0x6cc40f66; WORD $0x061a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 6], 7 - QUAD $0x0108025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 8], 1 - QUAD $0x02080a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 8], 2 + LONG $0x6cc40f66; WORD $0x061a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 6], 6 + LONG $0x6cc40f66; WORD $0x0602; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 6], 7 + QUAD $0x01080a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 8], 1 + QUAD $0x0208025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 8], 2 QUAD $0x0308225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 8], 3 - QUAD $0x04082a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 8], 4 + LONG $0x5cc40f66; WORD $0x083a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 8], 4 LONG $0x5cc40f66; WORD $0x080a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 8], 5 - LONG $0x5cc40f66; WORD $0x083a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 8], 6 - LONG $0x5cc40f66; WORD $0x081a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 8], 7 + LONG $0x5cc40f66; WORD $0x081a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 8], 6 + LONG $0x5cc40f66; WORD $0x0802; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 8], 7 LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x7c6e0f66; WORD $0x2824 // movd xmm7, dword [rsp + 40] - LONG $0x44b70f42; WORD $0x163a // movzx eax, word [rdx + r15 + 22] + LONG $0x7c6e0f66; WORD $0x0824 // movd xmm7, dword [rsp + 8] + LONG $0x74b70f46; WORD $0x163a // movzx r14d, word [rdx + r15 + 22] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 LONG $0xf2710f66; BYTE $0x02 // psllw xmm2, 2 LONG $0xdb0f4166; BYTE $0xd1 // pand xmm2, xmm9 LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0x646e0f66; WORD $0x1824 // movd xmm4, dword [rsp + 24] - LONG $0x5cb70f46; WORD $0x183a // movzx r11d, word [rdx + r15 + 24] + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x74b70f42; WORD $0x183a // movzx esi, word [rdx + r15 + 24] LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 @@ -14913,25 +13494,25 @@ LBB2_192: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x74b70f42; WORD $0x1a3a // movzx esi, word [rdx + r15 + 26] - QUAD $0x010a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 10], 1 - QUAD $0x020a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 10], 2 + LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] + LONG $0x54b70f46; WORD $0x1a3a // movzx r10d, word [rdx + r15 + 26] + QUAD $0x010a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 10], 1 + QUAD $0x020a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 10], 2 QUAD $0x030a2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 10], 3 - QUAD $0x040a2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 10], 4 + LONG $0x74c40f66; WORD $0x0a3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 10], 4 LONG $0x74c40f66; WORD $0x0a0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 10], 5 - LONG $0x74c40f66; WORD $0x0a3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 10], 6 - LONG $0x74c40f66; WORD $0x0a1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 10], 7 - QUAD $0x010c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 12], 1 - QUAD $0x020c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 12], 2 + LONG $0x74c40f66; WORD $0x0a1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 10], 6 + LONG $0x74c40f66; WORD $0x0a02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 10], 7 + QUAD $0x010c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 12], 1 + QUAD $0x020c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 12], 2 QUAD $0x030c227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 12], 3 - QUAD $0x040c2a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 12], 4 + LONG $0x7cc40f66; WORD $0x0c3a; BYTE $0x04 // pinsrw xmm7, word [rdx + rdi + 12], 4 LONG $0x7cc40f66; WORD $0x0c0a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 12], 5 - LONG $0x7cc40f66; WORD $0x0c3a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 12], 6 - LONG $0x7cc40f66; WORD $0x0c1a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 12], 7 + LONG $0x7cc40f66; WORD $0x0c1a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 12], 6 + LONG $0x7cc40f66; WORD $0x0c02; BYTE $0x07 // pinsrw xmm7, word [rdx + rax + 12], 7 LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4466; WORD $0x2444; BYTE $0x38 // movd xmm8, dword [rsp + 56] - LONG $0x74b70f46; WORD $0x1c3a // movzx r14d, word [rdx + r15 + 28] + LONG $0x6e0f4466; WORD $0x2444; BYTE $0x28 // movd xmm8, dword [rsp + 40] + LONG $0x5cb70f46; WORD $0x1c3a // movzx r11d, word [rdx + r15 + 28] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -14943,81 +13524,81 @@ LBB2_192: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d - LONG $0x54b70f46; WORD $0x1e3a // movzx r10d, word [rdx + r15 + 30] - QUAD $0x010e0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 14], 1 - QUAD $0x020e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 14], 2 + LONG $0x6e0f4166; BYTE $0xed // movd xmm5, r13d + LONG $0x6cb70f46; WORD $0x1e3a // movzx r13d, word [rdx + r15 + 30] + QUAD $0x010e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 14], 1 + QUAD $0x020e0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 14], 2 QUAD $0x030e2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 14], 3 - QUAD $0x040e2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 14], 4 + LONG $0x64c40f66; WORD $0x0e3a; BYTE $0x04 // pinsrw xmm4, word [rdx + rdi + 14], 4 LONG $0x64c40f66; WORD $0x0e0a; BYTE $0x05 // pinsrw xmm4, word [rdx + rcx + 14], 5 - LONG $0x64c40f66; WORD $0x0e3a; BYTE $0x06 // pinsrw xmm4, word [rdx + rdi + 14], 6 - LONG $0x64c40f66; WORD $0x0e1a; BYTE $0x07 // pinsrw xmm4, word [rdx + rbx + 14], 7 - QUAD $0x01120244c40f4666 // pinsrw xmm8, word [rdx + r8 + 18], 1 - QUAD $0x02120a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 18], 2 + LONG $0x64c40f66; WORD $0x0e1a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 14], 6 + LONG $0x64c40f66; WORD $0x0e02; BYTE $0x07 // pinsrw xmm4, word [rdx + rax + 14], 7 + QUAD $0x01120a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 18], 1 + QUAD $0x02120244c40f4666 // pinsrw xmm8, word [rdx + r8 + 18], 2 QUAD $0x03122244c40f4666 // pinsrw xmm8, word [rdx + r12 + 18], 3 - QUAD $0x04122a44c40f4666 // pinsrw xmm8, word [rdx + r13 + 18], 4 + QUAD $0x04123a44c40f4466 // pinsrw xmm8, word [rdx + rdi + 18], 4 QUAD $0x05120a44c40f4466 // pinsrw xmm8, word [rdx + rcx + 18], 5 - QUAD $0x06123a44c40f4466 // pinsrw xmm8, word [rdx + rdi + 18], 6 - QUAD $0x07121a44c40f4466 // pinsrw xmm8, word [rdx + rbx + 18], 7 + QUAD $0x06121a44c40f4466 // pinsrw xmm8, word [rdx + rbx + 18], 6 + QUAD $0x07120244c40f4466 // pinsrw xmm8, word [rdx + rax + 18], 7 LONG $0xe0750f66 // pcmpeqw xmm4, xmm0 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f42; WORD $0x203a // movzx eax, word [rdx + r15 + 32] + LONG $0x6e0f4166; BYTE $0xd6 // movd xmm2, r14d + LONG $0x74b70f46; WORD $0x203a // movzx r14d, word [rdx + r15 + 32] LONG $0xe3eb0f66 // por xmm4, xmm3 LONG $0x750f4466; BYTE $0xc0 // pcmpeqw xmm8, xmm0 LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf80f4166; BYTE $0xf8 // psubb xmm7, xmm8 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x5cb70f46; WORD $0x223a // movzx r11d, word [rdx + r15 + 34] - QUAD $0x0110024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 16], 1 - QUAD $0x02100a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 16], 2 + LONG $0xde6e0f66 // movd xmm3, esi + LONG $0x74b70f42; WORD $0x223a // movzx esi, word [rdx + r15 + 34] + LONG $0x20247489 // mov dword [rsp + 32], esi + QUAD $0x01100a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 16], 1 + QUAD $0x0210024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 16], 2 QUAD $0x0310224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 16], 3 - QUAD $0x04102a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 16], 4 + LONG $0x4cc40f66; WORD $0x103a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 16], 4 LONG $0x4cc40f66; WORD $0x100a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 16], 5 - LONG $0x4cc40f66; WORD $0x103a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 16], 6 - LONG $0x4cc40f66; WORD $0x101a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 16], 7 + LONG $0x4cc40f66; WORD $0x101a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 16], 6 + LONG $0x4cc40f66; WORD $0x1002; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 16], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0xf66e0f66 // movd xmm6, esi - LONG $0x74b70f42; WORD $0x243a // movzx esi, word [rdx + r15 + 36] - LONG $0x38247489 // mov dword [rsp + 56], esi - QUAD $0x0114026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 20], 1 - QUAD $0x02140a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 20], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x243a // movzx r10d, word [rdx + r15 + 36] + QUAD $0x01140a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 20], 1 + QUAD $0x0214026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 20], 2 QUAD $0x0314226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 20], 3 - QUAD $0x04142a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 20], 4 + LONG $0x6cc40f66; WORD $0x143a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 20], 4 LONG $0x6cc40f66; WORD $0x140a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 20], 5 - LONG $0x6cc40f66; WORD $0x143a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 20], 6 - LONG $0x6cc40f66; WORD $0x141a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 20], 7 + LONG $0x6cc40f66; WORD $0x141a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 20], 6 + LONG $0x6cc40f66; WORD $0x1402; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 20], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 LONG $0xefeb0f66 // por xmm5, xmm7 - LONG $0x6e0f4166; BYTE $0xfe // movd xmm7, r14d + LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d LONG $0x74b70f42; WORD $0x263a // movzx esi, word [rdx + r15 + 38] - LONG $0x18247489 // mov dword [rsp + 24], esi - QUAD $0x01160254c40f4266 // pinsrw xmm2, word [rdx + r8 + 22], 1 - QUAD $0x02160a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 22], 2 + LONG $0x08247489 // mov dword [rsp + 8], esi + QUAD $0x01160a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 22], 1 + QUAD $0x02160254c40f4266 // pinsrw xmm2, word [rdx + r8 + 22], 2 QUAD $0x03162254c40f4266 // pinsrw xmm2, word [rdx + r12 + 22], 3 - QUAD $0x04162a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 22], 4 + LONG $0x54c40f66; WORD $0x163a; BYTE $0x04 // pinsrw xmm2, word [rdx + rdi + 22], 4 LONG $0x54c40f66; WORD $0x160a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 22], 5 - LONG $0x54c40f66; WORD $0x163a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 22], 6 - LONG $0x54c40f66; WORD $0x161a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 22], 7 - QUAD $0x0118025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 24], 1 - QUAD $0x02180a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 24], 2 + LONG $0x54c40f66; WORD $0x161a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 22], 6 + LONG $0x54c40f66; WORD $0x1602; BYTE $0x07 // pinsrw xmm2, word [rdx + rax + 22], 7 + QUAD $0x01180a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 24], 1 + QUAD $0x0218025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 24], 2 QUAD $0x0318225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 24], 3 - QUAD $0x04182a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 24], 4 + LONG $0x5cc40f66; WORD $0x183a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 24], 4 LONG $0x5cc40f66; WORD $0x180a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 24], 5 - LONG $0x5cc40f66; WORD $0x183a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 24], 6 - LONG $0x5cc40f66; WORD $0x181a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 24], 7 + LONG $0x5cc40f66; WORD $0x181a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 24], 6 + LONG $0x5cc40f66; WORD $0x1802; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 24], 7 LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 @@ -15029,33 +13610,32 @@ LBB2_192: LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x74b70f46; WORD $0x283a // movzx r14d, word [rdx + r15 + 40] + LONG $0x6e0f4166; BYTE $0xd5 // movd xmm2, r13d + LONG $0x5cb70f46; WORD $0x283a // movzx r11d, word [rdx + r15 + 40] LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f42; WORD $0x2a3a // movzx eax, word [rdx + r15 + 42] - LONG $0x28244489 // mov dword [rsp + 40], eax - QUAD $0x011a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 26], 1 - QUAD $0x021a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 26], 2 + LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d + LONG $0x74b70f46; WORD $0x2a3a // movzx r14d, word [rdx + r15 + 42] + QUAD $0x011a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 26], 1 + QUAD $0x021a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 26], 2 QUAD $0x031a2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 26], 3 - QUAD $0x041a2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 26], 4 + LONG $0x74c40f66; WORD $0x1a3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 26], 4 LONG $0x74c40f66; WORD $0x1a0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 26], 5 - LONG $0x74c40f66; WORD $0x1a3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 26], 6 - LONG $0x74c40f66; WORD $0x1a1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 26], 7 - QUAD $0x011c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 28], 1 - QUAD $0x021c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 28], 2 + LONG $0x74c40f66; WORD $0x1a1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 26], 6 + LONG $0x74c40f66; WORD $0x1a02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 26], 7 + QUAD $0x011c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 28], 1 + QUAD $0x021c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 28], 2 QUAD $0x031c227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 28], 3 - QUAD $0x041c2a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 28], 4 + LONG $0x7cc40f66; WORD $0x1c3a; BYTE $0x04 // pinsrw xmm7, word [rdx + rdi + 28], 4 LONG $0x7cc40f66; WORD $0x1c0a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 28], 5 - LONG $0x7cc40f66; WORD $0x1c3a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 28], 6 - LONG $0x7cc40f66; WORD $0x1c1a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 28], 7 - QUAD $0x011e0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 30], 1 - QUAD $0x021e0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 30], 2 + LONG $0x7cc40f66; WORD $0x1c1a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 28], 6 + LONG $0x7cc40f66; WORD $0x1c02; BYTE $0x07 // pinsrw xmm7, word [rdx + rax + 28], 7 + QUAD $0x011e0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 30], 1 + QUAD $0x021e0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 30], 2 QUAD $0x031e2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 30], 3 - QUAD $0x041e2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 30], 4 + LONG $0x54c40f66; WORD $0x1e3a; BYTE $0x04 // pinsrw xmm2, word [rdx + rdi + 30], 4 LONG $0x54c40f66; WORD $0x1e0a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 30], 5 - LONG $0x54c40f66; WORD $0x1e3a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 30], 6 - LONG $0x54c40f66; WORD $0x1e1a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 30], 7 + LONG $0x54c40f66; WORD $0x1e1a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 30], 6 + LONG $0x54c40f66; WORD $0x1e02; BYTE $0x07 // pinsrw xmm2, word [rdx + rax + 30], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -15067,72 +13647,73 @@ LBB2_192: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d - LONG $0x54b70f46; WORD $0x2c3a // movzx r10d, word [rdx + r15 + 44] + LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] + LONG $0x6cb70f46; WORD $0x2c3a // movzx r13d, word [rdx + r15 + 44] LONG $0xd0750f66 // pcmpeqw xmm2, xmm0 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 LONG $0xdb0f4166; BYTE $0xd6 // pand xmm2, xmm14 LONG $0xd7eb0f66 // por xmm2, xmm7 - LONG $0x746e0f66; WORD $0x3824 // movd xmm6, dword [rsp + 56] - LONG $0x74b70f42; WORD $0x2e3a // movzx esi, word [rdx + r15 + 46] - QUAD $0x0120026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 32], 1 - QUAD $0x02200a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 32], 2 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x54b70f46; WORD $0x2e3a // movzx r10d, word [rdx + r15 + 46] + QUAD $0x01200a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 32], 1 + QUAD $0x0220026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 32], 2 QUAD $0x0320226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 32], 3 - QUAD $0x04202a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 32], 4 + LONG $0x6cc40f66; WORD $0x203a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 32], 4 LONG $0x6cc40f66; WORD $0x200a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 32], 5 - LONG $0x6cc40f66; WORD $0x203a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 32], 6 - QUAD $0x0122024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 34], 1 - QUAD $0x02220a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 34], 2 + LONG $0x6cc40f66; WORD $0x201a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 32], 6 + QUAD $0x01220a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 34], 1 + QUAD $0x0222024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 34], 2 QUAD $0x0322224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 34], 3 - QUAD $0x04222a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 34], 4 + LONG $0x4cc40f66; WORD $0x223a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 34], 4 LONG $0x4cc40f66; WORD $0x220a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 34], 5 - LONG $0x4cc40f66; WORD $0x223a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 34], 6 - LONG $0x4cc40f66; WORD $0x221a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 34], 7 + LONG $0x4cc40f66; WORD $0x221a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 34], 6 + LONG $0x4cc40f66; WORD $0x2202; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 34], 7 LONG $0xd3eb0f66 // por xmm2, xmm3 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xf96f0f66 // movdqa xmm7, xmm1 LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 LONG $0xf9f80f66 // psubb xmm7, xmm1 - LONG $0x5c6e0f66; WORD $0x1824 // movd xmm3, dword [rsp + 24] - LONG $0x5cb70f46; WORD $0x303a // movzx r11d, word [rdx + r15 + 48] - LONG $0x6cc40f66; WORD $0x201a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 32], 7 + LONG $0x5c6e0f66; WORD $0x0824 // movd xmm3, dword [rsp + 8] + LONG $0x74b70f42; WORD $0x303a // movzx esi, word [rdx + r15 + 48] + LONG $0x08247489 // mov dword [rsp + 8], esi + LONG $0x6cc40f66; WORD $0x2002; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 32], 7 LONG $0xe8750f66 // pcmpeqw xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - QUAD $0x01240274c40f4266 // pinsrw xmm6, word [rdx + r8 + 36], 1 - QUAD $0x02240a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 36], 2 + QUAD $0x01240a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 36], 1 + QUAD $0x02240274c40f4266 // pinsrw xmm6, word [rdx + r8 + 36], 2 QUAD $0x03242274c40f4266 // pinsrw xmm6, word [rdx + r12 + 36], 3 - QUAD $0x04242a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 36], 4 + LONG $0x74c40f66; WORD $0x243a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 36], 4 LONG $0x74c40f66; WORD $0x240a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 36], 5 - LONG $0x74c40f66; WORD $0x243a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 36], 6 - LONG $0x74c40f66; WORD $0x241a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 36], 7 - QUAD $0x0126025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 38], 1 - QUAD $0x02260a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 38], 2 + LONG $0x74c40f66; WORD $0x241a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 36], 6 + LONG $0x74c40f66; WORD $0x2402; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 36], 7 + QUAD $0x01260a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 38], 1 + QUAD $0x0226025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 38], 2 QUAD $0x0326225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 38], 3 - QUAD $0x04262a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 38], 4 + LONG $0x5cc40f66; WORD $0x263a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 38], 4 LONG $0x5cc40f66; WORD $0x260a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 38], 5 - LONG $0x5cc40f66; WORD $0x263a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 38], 6 - LONG $0x5cc40f66; WORD $0x261a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 38], 7 + LONG $0x5cc40f66; WORD $0x261a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 38], 6 + LONG $0x5cc40f66; WORD $0x2602; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 38], 7 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d - QUAD $0x0128026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 40], 1 - QUAD $0x02280a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 40], 2 + LONG $0x6e0f4166; BYTE $0xeb // movd xmm5, r11d + QUAD $0x01280a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 40], 1 + QUAD $0x0228026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 40], 2 QUAD $0x0328226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 40], 3 - QUAD $0x04282a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 40], 4 + LONG $0x6cc40f66; WORD $0x283a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 40], 4 LONG $0x6cc40f66; WORD $0x280a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 40], 5 - LONG $0x6cc40f66; WORD $0x283a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 40], 6 - LONG $0x44b70f42; WORD $0x323a // movzx eax, word [rdx + r15 + 50] + LONG $0x6cc40f66; WORD $0x281a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 40], 6 + LONG $0x74b70f42; WORD $0x323a // movzx esi, word [rdx + r15 + 50] LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] - LONG $0x74b70f46; WORD $0x343a // movzx r14d, word [rdx + r15 + 52] - LONG $0x6cc40f66; WORD $0x281a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 40], 7 + LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d + LONG $0x5cb70f46; WORD $0x343a // movzx r11d, word [rdx + r15 + 52] + LONG $0x6cc40f66; WORD $0x2802; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 40], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 @@ -15144,25 +13725,25 @@ LBB2_192: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xebeb0f66 // por xmm5, xmm3 - LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d - LONG $0x54b70f46; WORD $0x363a // movzx r10d, word [rdx + r15 + 54] - QUAD $0x012a024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 42], 1 - QUAD $0x022a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 42], 2 + LONG $0x6e0f4166; BYTE $0xfd // movd xmm7, r13d + LONG $0x74b70f46; WORD $0x363a // movzx r14d, word [rdx + r15 + 54] + QUAD $0x012a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 42], 1 + QUAD $0x022a024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 42], 2 QUAD $0x032a224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 42], 3 - QUAD $0x042a2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 42], 4 + LONG $0x4cc40f66; WORD $0x2a3a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 42], 4 LONG $0x4cc40f66; WORD $0x2a0a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 42], 5 - LONG $0x4cc40f66; WORD $0x2a3a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 42], 6 - LONG $0x4cc40f66; WORD $0x2a1a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 42], 7 - QUAD $0x012c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 44], 1 - QUAD $0x022c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 44], 2 + LONG $0x4cc40f66; WORD $0x2a1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 42], 6 + LONG $0x4cc40f66; WORD $0x2a02; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 42], 7 + QUAD $0x012c0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 44], 1 + QUAD $0x022c027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 44], 2 QUAD $0x032c227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 44], 3 - QUAD $0x042c2a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 44], 4 + LONG $0x7cc40f66; WORD $0x2c3a; BYTE $0x04 // pinsrw xmm7, word [rdx + rdi + 44], 4 LONG $0x7cc40f66; WORD $0x2c0a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 44], 5 - LONG $0x7cc40f66; WORD $0x2c3a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 44], 6 + LONG $0x7cc40f66; WORD $0x2c1a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 44], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0xde6e0f66 // movd xmm3, esi - LONG $0x74b70f42; WORD $0x383a // movzx esi, word [rdx + r15 + 56] - LONG $0x7cc40f66; WORD $0x2c1a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 44], 7 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x54b70f46; WORD $0x383a // movzx r10d, word [rdx + r15 + 56] + LONG $0x7cc40f66; WORD $0x2c02; BYTE $0x07 // pinsrw xmm7, word [rdx + rax + 44], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 @@ -15174,77 +13755,77 @@ LBB2_192: LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - LONG $0x5cb70f46; WORD $0x3a3a // movzx r11d, word [rdx + r15 + 58] - QUAD $0x012e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 46], 1 - QUAD $0x022e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 46], 2 + LONG $0x746e0f66; WORD $0x0824 // movd xmm6, dword [rsp + 8] + LONG $0x6cb70f46; WORD $0x3a3a // movzx r13d, word [rdx + r15 + 58] + QUAD $0x012e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 46], 1 + QUAD $0x022e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 46], 2 QUAD $0x032e225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 46], 3 - QUAD $0x042e2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 46], 4 + LONG $0x5cc40f66; WORD $0x2e3a; BYTE $0x04 // pinsrw xmm3, word [rdx + rdi + 46], 4 LONG $0x5cc40f66; WORD $0x2e0a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 46], 5 - LONG $0x5cc40f66; WORD $0x2e3a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 46], 6 - LONG $0x5cc40f66; WORD $0x2e1a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 46], 7 + LONG $0x5cc40f66; WORD $0x2e1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 46], 6 + LONG $0x5cc40f66; WORD $0x2e02; BYTE $0x07 // pinsrw xmm3, word [rdx + rax + 46], 7 LONG $0xd8750f66 // pcmpeqw xmm3, xmm0 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 LONG $0xdfeb0f66 // por xmm3, xmm7 - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x44b70f42; WORD $0x3c3a // movzx eax, word [rdx + r15 + 60] + LONG $0xce6e0f66 // movd xmm1, esi + LONG $0x74b70f42; WORD $0x3c3a // movzx esi, word [rdx + r15 + 60] LONG $0x7cb70f46; WORD $0x3e3a // movzx r15d, word [rdx + r15 + 62] - QUAD $0x0132024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 50], 1 - QUAD $0x02320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 2 + QUAD $0x01320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 1 + QUAD $0x0232024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 50], 2 QUAD $0x0332224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 50], 3 - QUAD $0x04322a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 50], 4 + LONG $0x4cc40f66; WORD $0x323a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 50], 4 LONG $0x4cc40f66; WORD $0x320a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 50], 5 - LONG $0x4cc40f66; WORD $0x323a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 50], 6 - LONG $0x4cc40f66; WORD $0x321a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 50], 7 + LONG $0x4cc40f66; WORD $0x321a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 50], 6 + LONG $0x4cc40f66; WORD $0x3202; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 50], 7 LONG $0xddeb0f66 // por xmm3, xmm5 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xe96f0f66 // movdqa xmm5, xmm1 LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 LONG $0xe9f80f66 // psubb xmm5, xmm1 - LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d - QUAD $0x01300274c40f4266 // pinsrw xmm6, word [rdx + r8 + 48], 1 - QUAD $0x02300a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 48], 2 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + QUAD $0x01300a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 48], 1 + QUAD $0x02300274c40f4266 // pinsrw xmm6, word [rdx + r8 + 48], 2 QUAD $0x03302274c40f4266 // pinsrw xmm6, word [rdx + r12 + 48], 3 - QUAD $0x04302a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 48], 4 + LONG $0x74c40f66; WORD $0x303a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 48], 4 LONG $0x74c40f66; WORD $0x300a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 48], 5 - LONG $0x74c40f66; WORD $0x303a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 48], 6 - LONG $0x74c40f66; WORD $0x301a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 48], 7 + LONG $0x74c40f66; WORD $0x301a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 48], 6 + LONG $0x74c40f66; WORD $0x3002; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 48], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 - QUAD $0x0134024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 52], 1 - QUAD $0x02340a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 52], 2 + QUAD $0x01340a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 52], 1 + QUAD $0x0234024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 52], 2 QUAD $0x0334224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 52], 3 - QUAD $0x04342a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 52], 4 + LONG $0x4cc40f66; WORD $0x343a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 52], 4 LONG $0x4cc40f66; WORD $0x340a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 52], 5 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0x4cc40f66; WORD $0x343a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 52], 6 + LONG $0x4cc40f66; WORD $0x341a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 52], 6 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d - LONG $0x4cc40f66; WORD $0x341a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 52], 7 + LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d + LONG $0x4cc40f66; WORD $0x3402; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 52], 7 LONG $0xc8750f66 // pcmpeqw xmm1, xmm0 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 LONG $0xf1710f66; BYTE $0x02 // psllw xmm1, 2 LONG $0xdb0f4166; BYTE $0xc9 // pand xmm1, xmm9 LONG $0xcdeb0f66 // por xmm1, xmm5 - LONG $0xee6e0f66 // movd xmm5, esi - QUAD $0x01360274c40f4266 // pinsrw xmm6, word [rdx + r8 + 54], 1 - QUAD $0x02360a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 54], 2 + LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d + QUAD $0x01360a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 54], 1 + QUAD $0x02360274c40f4266 // pinsrw xmm6, word [rdx + r8 + 54], 2 QUAD $0x03362274c40f4266 // pinsrw xmm6, word [rdx + r12 + 54], 3 - QUAD $0x04362a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 54], 4 + LONG $0x74c40f66; WORD $0x363a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 54], 4 LONG $0x74c40f66; WORD $0x360a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 54], 5 - LONG $0x74c40f66; WORD $0x363a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 54], 6 - LONG $0x74c40f66; WORD $0x361a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 54], 7 - QUAD $0x0138026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 56], 1 - QUAD $0x02380a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 56], 2 + LONG $0x74c40f66; WORD $0x361a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 54], 6 + LONG $0x74c40f66; WORD $0x3602; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 54], 7 + QUAD $0x01380a6cc40f4266 // pinsrw xmm5, word [rdx + r9 + 56], 1 + QUAD $0x0238026cc40f4266 // pinsrw xmm5, word [rdx + r8 + 56], 2 QUAD $0x0338226cc40f4266 // pinsrw xmm5, word [rdx + r12 + 56], 3 - QUAD $0x04382a6cc40f4266 // pinsrw xmm5, word [rdx + r13 + 56], 4 + LONG $0x6cc40f66; WORD $0x383a; BYTE $0x04 // pinsrw xmm5, word [rdx + rdi + 56], 4 LONG $0x6cc40f66; WORD $0x380a; BYTE $0x05 // pinsrw xmm5, word [rdx + rcx + 56], 5 - LONG $0x6cc40f66; WORD $0x383a; BYTE $0x06 // pinsrw xmm5, word [rdx + rdi + 56], 6 - LONG $0x6cc40f66; WORD $0x381a; BYTE $0x07 // pinsrw xmm5, word [rdx + rbx + 56], 7 + LONG $0x6cc40f66; WORD $0x381a; BYTE $0x06 // pinsrw xmm5, word [rdx + rbx + 56], 6 + LONG $0x6cc40f66; WORD $0x3802; BYTE $0x07 // pinsrw xmm5, word [rdx + rax + 56], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -15256,24 +13837,23 @@ LBB2_192: LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - LONG $0x24348b48 // mov rsi, qword [rsp] - QUAD $0x013a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 58], 1 - QUAD $0x023a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 58], 2 + LONG $0x6e0f4166; BYTE $0xf5 // movd xmm6, r13d + QUAD $0x013a0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 58], 1 + QUAD $0x023a0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 58], 2 QUAD $0x033a2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 58], 3 - QUAD $0x043a2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 58], 4 + LONG $0x74c40f66; WORD $0x3a3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 58], 4 LONG $0x74c40f66; WORD $0x3a0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 58], 5 - LONG $0x74c40f66; WORD $0x3a3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 58], 6 - LONG $0x74c40f66; WORD $0x3a1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 58], 7 + LONG $0x74c40f66; WORD $0x3a1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 58], 6 + LONG $0x74c40f66; WORD $0x3a02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 58], 7 LONG $0xe9eb0f66 // por xmm5, xmm1 - LONG $0xc86e0f66 // movd xmm1, eax - QUAD $0x013c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 60], 1 - QUAD $0x023c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 60], 2 + LONG $0xce6e0f66 // movd xmm1, esi + QUAD $0x013c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 60], 1 + QUAD $0x023c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 60], 2 QUAD $0x033c224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 60], 3 - QUAD $0x043c2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 60], 4 + LONG $0x4cc40f66; WORD $0x3c3a; BYTE $0x04 // pinsrw xmm1, word [rdx + rdi + 60], 4 LONG $0x4cc40f66; WORD $0x3c0a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 60], 5 - LONG $0x4cc40f66; WORD $0x3c3a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 60], 6 - LONG $0x4cc40f66; WORD $0x3c1a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 60], 7 + LONG $0x4cc40f66; WORD $0x3c1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 60], 6 + LONG $0x4cc40f66; WORD $0x3c02; BYTE $0x07 // pinsrw xmm1, word [rdx + rax + 60], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 @@ -15286,13 +13866,14 @@ LBB2_192: LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 LONG $0xceeb0f66 // por xmm1, xmm6 LONG $0x6e0f4166; BYTE $0xf7 // movd xmm6, r15d - QUAD $0x013e0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 62], 1 - QUAD $0x023e0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 62], 2 + QUAD $0x013e0a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 62], 1 + QUAD $0x023e0274c40f4266 // pinsrw xmm6, word [rdx + r8 + 62], 2 QUAD $0x033e2274c40f4266 // pinsrw xmm6, word [rdx + r12 + 62], 3 - QUAD $0x043e2a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 62], 4 + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + LONG $0x74c40f66; WORD $0x3e3a; BYTE $0x04 // pinsrw xmm6, word [rdx + rdi + 62], 4 LONG $0x74c40f66; WORD $0x3e0a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 62], 5 - LONG $0x74c40f66; WORD $0x3e3a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 62], 6 - LONG $0x74c40f66; WORD $0x3e1a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 62], 7 + LONG $0x74c40f66; WORD $0x3e1a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 62], 6 + LONG $0x74c40f66; WORD $0x3e02; BYTE $0x07 // pinsrw xmm6, word [rdx + rax + 62], 7 LONG $0xf0750f66 // pcmpeqw xmm6, xmm0 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 @@ -15310,34 +13891,32 @@ LBB2_192: LONG $0xde600f66 // punpcklbw xmm3, xmm6 LONG $0xe2600f66 // punpcklbw xmm4, xmm2 LONG $0xe3610f66 // punpcklwd xmm4, xmm3 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] LONG $0x247f0ff3; BYTE $0x8e // movdqu oword [rsi + 4*rcx], xmm4 - LONG $0x24348948 // mov qword [rsp], rsi LONG $0x4c7f0ff3; WORD $0x108e // movdqu oword [rsi + 4*rcx + 16], xmm1 LONG $0x08c18348 // add rcx, 8 WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB2_192 + LONG $0x244c3b48; BYTE $0x18 // cmp rcx, qword [rsp + 24] + JNE LBB2_209 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x244c3b48; BYTE $0x18 // cmp rcx, qword [rsp + 24] QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] - LONG $0x247c3b4c; BYTE $0x20 // cmp r15, qword [rsp + 32] - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - LONG $0x24748b44; BYTE $0x08 // mov r14d, dword [rsp + 8] - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - JNE LBB2_104 - JMP LBB2_144 + LONG $0x246c8b44; BYTE $0x30 // mov r13d, dword [rsp + 48] + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + JNE LBB2_84 + JMP LBB2_139 -LBB2_194: - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - LONG $0xfce08349 // and r8, -4 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 +LBB2_211: + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0xfce08348 // and rax, -4 + WORD $0x8948; BYTE $0xc3 // mov rbx, rax LONG $0x07e3c148 // shl rbx, 7 WORD $0x0148; BYTE $0xd3 // add rbx, rdx - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x803c8d4e // lea r15, [rax + 4*r8] - WORD $0x280f; BYTE $0xc8 // movaps xmm1, xmm0 + LONG $0x842c8d4d // lea r13, [r12 + 4*rax] + LONG $0xc86f0f66 // movdqa xmm1, xmm0 LONG $0x00c8c60f // shufps xmm1, xmm0, 0 LONG $0xfcc28148; WORD $0x0001; BYTE $0x00 // add rdx, 508 - WORD $0xc931 // xor ecx, ecx + WORD $0xf631 // xor esi, esi LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI2_0] */ LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI2_1] */ LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI2_2] */ @@ -15346,9 +13925,8 @@ LBB2_194: LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI2_5] */ LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI2_6] */ LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI2_7] */ - LONG $0x24048b48 // mov rax, qword [rsp] -LBB2_195: +LBB2_212: QUAD $0xfffffe04b2100ff3 // movss xmm6, dword [rdx - 508] QUAD $0xfffffe08ba100ff3 // movss xmm7, dword [rdx - 504] QUAD $0xfffffe0caa100ff3 // movss xmm5, dword [rdx - 500] @@ -15625,78 +14203,1902 @@ LBB2_195: QUAD $0xffff6c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 148], 32 LONG $0x213a0f66; WORD $0xec5a; BYTE $0x30 // insertps xmm3, dword [rdx - 20], 48 LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0xfffffe7092100ff3 // movss xmm2, dword [rdx - 400] - QUAD $0xfffef092213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 272], 16 - QUAD $0xffff7092213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 144], 32 - LONG $0x213a0f66; WORD $0xf052; BYTE $0x30 // insertps xmm2, dword [rdx - 16], 48 - LONG $0x00d9c20f // cmpeqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe74b2100ff3 // movss xmm6, dword [rdx - 396] - QUAD $0xfffef4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 268], 16 - QUAD $0xffff74b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 140], 32 - LONG $0x213a0f66; WORD $0xf472; BYTE $0x30 // insertps xmm6, dword [rdx - 12], 48 - LONG $0x00d1c20f // cmpeqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0x00f1c20f // cmpeqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf2eb0f66 // por xmm6, xmm2 - QUAD $0xfffffe78ba100ff3 // movss xmm7, dword [rdx - 392] - QUAD $0xfffef8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 264], 16 - QUAD $0xffff78ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 136], 32 - LONG $0x213a0f66; WORD $0xf87a; BYTE $0x30 // insertps xmm7, dword [rdx - 8], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffffe7c92100ff3 // movss xmm2, dword [rdx - 388] - QUAD $0xfffefc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 260], 16 - QUAD $0xffff7c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 132], 32 - LONG $0x213a0f66; WORD $0xfc52; BYTE $0x30 // insertps xmm2, dword [rdx - 4], 48 - LONG $0x00f9c20f // cmpeqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x00d1c20f // cmpeqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffffe809a100ff3 // movss xmm3, dword [rdx - 384] - QUAD $0xffff009a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 256], 16 - LONG $0x213a0f66; WORD $0x805a; BYTE $0x20 // insertps xmm3, dword [rdx - 128], 32 - LONG $0x213a0f66; WORD $0x301a // insertps xmm3, dword [rdx], 48 - LONG $0x00d9c20f // cmpeqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0xdeeb0f66 // por xmm3, xmm6 - LONG $0xeb620f66 // punpckldq xmm5, xmm3 - LONG $0xe5600f66 // punpcklbw xmm4, xmm5 - LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 - LONG $0x247f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm4 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c28148; WORD $0x0002; BYTE $0x00 // add rdx, 512 - WORD $0x3949; BYTE $0xc8 // cmp r8, rcx - JNE LBB2_195 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB2_127 - JMP LBB2_148 + QUAD $0xfffffe7092100ff3 // movss xmm2, dword [rdx - 400] + QUAD $0xfffef092213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 272], 16 + QUAD $0xffff7092213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 144], 32 + LONG $0x213a0f66; WORD $0xf052; BYTE $0x30 // insertps xmm2, dword [rdx - 16], 48 + LONG $0x00d9c20f // cmpeqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe74b2100ff3 // movss xmm6, dword [rdx - 396] + QUAD $0xfffef4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 268], 16 + QUAD $0xffff74b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 140], 32 + LONG $0x213a0f66; WORD $0xf472; BYTE $0x30 // insertps xmm6, dword [rdx - 12], 48 + LONG $0x00d1c20f // cmpeqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0x00f1c20f // cmpeqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf2eb0f66 // por xmm6, xmm2 + QUAD $0xfffffe78ba100ff3 // movss xmm7, dword [rdx - 392] + QUAD $0xfffef8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 264], 16 + QUAD $0xffff78ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 136], 32 + LONG $0x213a0f66; WORD $0xf87a; BYTE $0x30 // insertps xmm7, dword [rdx - 8], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe7c92100ff3 // movss xmm2, dword [rdx - 388] + QUAD $0xfffefc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 260], 16 + QUAD $0xffff7c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 132], 32 + LONG $0x213a0f66; WORD $0xfc52; BYTE $0x30 // insertps xmm2, dword [rdx - 4], 48 + LONG $0x00f9c20f // cmpeqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x00d1c20f // cmpeqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe809a100ff3 // movss xmm3, dword [rdx - 384] + QUAD $0xffff009a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 256], 16 + LONG $0x213a0f66; WORD $0x805a; BYTE $0x20 // insertps xmm3, dword [rdx - 128], 32 + LONG $0x213a0f66; WORD $0x301a // insertps xmm3, dword [rdx], 48 + LONG $0x00d9c20f // cmpeqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0xdeeb0f66 // por xmm3, xmm6 + LONG $0xeb620f66 // punpckldq xmm5, xmm3 + LONG $0xe5600f66 // punpcklbw xmm4, xmm5 + LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 + LONG $0x7f0f41f3; WORD $0xb424 // movdqu oword [r12 + 4*rsi], xmm4 + LONG $0x04c68348 // add rsi, 4 + LONG $0x00c28148; WORD $0x0002; BYTE $0x00 // add rdx, 512 + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JNE LBB2_212 + WORD $0x3948; BYTE $0xc1 // cmp rcx, rax + JNE LBB2_111 + JMP LBB2_143 + +LBB2_214: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + QUAD $0x000000d8248c8948 // mov qword [rsp + 216], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0xc3b60f41 // movzx eax, r11b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + WORD $0xc031 // xor eax, eax + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + +LBB2_215: + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + LONG $0x05e2c148 // shl rdx, 5 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + WORD $0x8949; BYTE $0xd0 // mov r8, rdx + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + LONG $0x24548948; BYTE $0x30 // mov qword [rsp + 48], rdx + WORD $0x8949; BYTE $0xd1 // mov r9, rdx + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x8949; BYTE $0xd7 // mov r15, rdx + LONG $0x24548948; BYTE $0x40 // mov qword [rsp + 64], rdx + LONG $0x0cb60f41; BYTE $0x16 // movzx ecx, byte [r14 + rdx] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x4cb60f41; WORD $0x0116 // movzx ecx, byte [r14 + rdx + 1] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x4cb60f41; WORD $0x0216 // movzx ecx, byte [r14 + rdx + 2] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x4cb60f41; WORD $0x0316 // movzx ecx, byte [r14 + rdx + 3] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x4cb60f41; WORD $0x0416 // movzx ecx, byte [r14 + rdx + 4] + LONG $0xc96e0f66 // movd xmm1, ecx + LONG $0x4cb60f41; WORD $0x0516 // movzx ecx, byte [r14 + rdx + 5] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x4cb60f41; WORD $0x0616 // movzx ecx, byte [r14 + rdx + 6] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x4cb60f41; WORD $0x0716 // movzx ecx, byte [r14 + rdx + 7] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 + LONG $0x4cb60f41; WORD $0x0816 // movzx ecx, byte [r14 + rdx + 8] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 + LONG $0x4cb60f41; WORD $0x0916 // movzx ecx, byte [r14 + rdx + 9] + LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx + LONG $0x4cb60f41; WORD $0x0a16 // movzx ecx, byte [r14 + rdx + 10] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 + LONG $0x4cb60f41; WORD $0x0b16 // movzx ecx, byte [r14 + rdx + 11] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x4cb60f41; WORD $0x0c16 // movzx ecx, byte [r14 + rdx + 12] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x4cb60f41; WORD $0x0d16 // movzx ecx, byte [r14 + rdx + 13] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x4cb60f41; WORD $0x0e16 // movzx ecx, byte [r14 + rdx + 14] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 + WORD $0x8949; BYTE $0xd4 // mov r12, rdx + LONG $0x20cc8349 // or r12, 32 + LONG $0x2464894c; BYTE $0x20 // mov qword [rsp + 32], r12 + LONG $0x40c88348 // or rax, 64 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x60c88349 // or r8, 96 + LONG $0x80cb8149; WORD $0x0000; BYTE $0x00 // or r11, 128 + LONG $0xa0ce8148; WORD $0x0000; BYTE $0x00 // or rsi, 160 + LONG $0x24748948; BYTE $0x48 // mov qword [rsp + 72], rsi + LONG $0xc0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 192 + QUAD $0x0000e030244c8148; BYTE $0x00 // or qword [rsp + 48], 224 + LONG $0x00c98149; WORD $0x0001; BYTE $0x00 // or r9, 256 + LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 + LONG $0x245c8948; BYTE $0x78 // mov qword [rsp + 120], rbx + LONG $0x60cf8149; WORD $0x0001; BYTE $0x00 // or r15, 352 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 + LONG $0x24748948; BYTE $0x40 // mov qword [rsp + 64], rsi + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0x24548948; BYTE $0x38 // mov qword [rsp + 56], rdx + LONG $0xc0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 448 + LONG $0x247c8948; BYTE $0x08 // mov qword [rsp + 8], rdi + LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 + LONG $0x244c8948; BYTE $0x18 // mov qword [rsp + 24], rcx + QUAD $0x01263c203a0f4766 // pinsrb xmm15, byte [r14 + r12], 1 + QUAD $0x02063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 2 + QUAD $0x03063c203a0f4766 // pinsrb xmm15, byte [r14 + r8], 3 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + QUAD $0x041e3c203a0f4766 // pinsrb xmm15, byte [r14 + r11], 4 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x05263c203a0f4766 // pinsrb xmm15, byte [r14 + r12], 5 + QUAD $0x062e3c203a0f4766 // pinsrb xmm15, byte [r14 + r13], 6 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x07063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 7 + QUAD $0x080e3c203a0f4766 // pinsrb xmm15, byte [r14 + r9], 8 + QUAD $0x09163c203a0f4766 // pinsrb xmm15, byte [r14 + r10], 9 + QUAD $0x0a1e3c203a0f4566 // pinsrb xmm15, byte [r14 + rbx], 10 + QUAD $0x0b3e3c203a0f4766 // pinsrb xmm15, byte [r14 + r15], 11 + QUAD $0x0c363c203a0f4566 // pinsrb xmm15, byte [r14 + rsi], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 13 + QUAD $0x0e3e3c203a0f4566 // pinsrb xmm15, byte [r14 + rdi], 14 + QUAD $0x0f0e3c203a0f4566 // pinsrb xmm15, byte [r14 + rcx], 15 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x011e6c203a0f4366; BYTE $0x01 // pinsrb xmm5, byte [r14 + r11 + 1], 1 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x01066c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rax + 1], 2 + QUAD $0x01066c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r8 + 1], 3 + QUAD $0x01166c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rdx + 1], 4 + QUAD $0x01266c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r12 + 1], 5 + QUAD $0x012e6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r13 + 1], 6 + WORD $0x894d; BYTE $0xec // mov r12, r13 + LONG $0x246c894c; BYTE $0x58 // mov qword [rsp + 88], r13 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x01066c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r14 + rax + 1], 7 + QUAD $0x010e6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r9 + 1], 8 + QUAD $0x01166c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r10 + 1], 9 + QUAD $0x011e6c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r14 + rbx + 1], 10 + QUAD $0x013e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r15 + 1], 11 + QUAD $0x01366c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rsi + 1], 12 + LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] + QUAD $0x011e6c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r14 + r11 + 1], 13 + QUAD $0x013e6c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rdi + 1], 14 + QUAD $0x010e6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r14 + rcx + 1], 15 + QUAD $0x00b0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 + LONG $0xfd6f0f66 // movdqa xmm7, xmm5 + QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI2_10] */ + LONG $0xfcdb0f66 // pand xmm7, xmm4 + LONG $0xfdf80f66 // psubb xmm7, xmm5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x74b60f41; WORD $0x0f06 // movzx esi, byte [r14 + rax + 15] + LONG $0x6e0f4466; BYTE $0xf6 // movd xmm14, esi + LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x020e74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rcx + 2], 1 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x022e74203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r14 + r13 + 2], 2 + WORD $0x894c; BYTE $0xc7 // mov rdi, r8 + QUAD $0x020674203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r8 + 2], 3 + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + QUAD $0x021674203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rdx + 2], 4 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x021674203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r14 + rdx + 2], 5 + QUAD $0x022674203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r12 + 2], 6 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x020674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r8 + 2], 7 + QUAD $0x020e74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r9 + 2], 8 + LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 + QUAD $0x021674203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r10 + 2], 9 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x022674203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r12 + 2], 10 + LONG $0x247c894c; BYTE $0x68 // mov qword [rsp + 104], r15 + QUAD $0x023e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r15 + 2], 11 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x023674203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rsi + 2], 12 + QUAD $0x021e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r11 + 2], 13 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x023674203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rsi + 2], 14 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x023674203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rsi + 2], 15 + LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 + LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 + QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xf0db0f66 // pand xmm6, xmm0 + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x74b60f41; WORD $0x1006 // movzx esi, byte [r14 + rax + 16] + LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x030e54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rcx + 3], 1 + QUAD $0x032e54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r13 + 3], 2 + LONG $0x247c8948; BYTE $0x50 // mov qword [rsp + 80], rdi + QUAD $0x033e54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdi + 3], 3 + QUAD $0x031e54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rbx + 3], 4 + QUAD $0x031654203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r14 + rdx + 3], 5 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x030e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 3], 6 + QUAD $0x030654203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r8 + 3], 7 + QUAD $0x030e54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r9 + 3], 8 + QUAD $0x031654203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r10 + 3], 9 + QUAD $0x032654203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r12 + 3], 10 + QUAD $0x033e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 3], 11 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x032654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 3], 12 + QUAD $0x031e54203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r14 + r11 + 3], 13 + LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] + QUAD $0x033e54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r15 + 3], 14 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x033654203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rsi + 3], 15 + QUAD $0x04064c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rax + 4], 1 + QUAD $0x042e4c203a0f4366; BYTE $0x02 // pinsrb xmm1, byte [r14 + r13 + 4], 2 + QUAD $0x043e4c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r14 + rdi + 4], 3 + QUAD $0x041e4c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r14 + rbx + 4], 4 + QUAD $0x04164c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r14 + rdx + 4], 5 + QUAD $0x040e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 4], 6 + QUAD $0x04064c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r14 + r8 + 4], 7 + QUAD $0x040e4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r9 + 4], 8 + QUAD $0x04164c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r10 + 4], 9 + LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] + QUAD $0x04164c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r14 + r10 + 4], 10 + LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] + QUAD $0x043e4c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r14 + rdi + 4], 11 + QUAD $0x04264c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r12 + 4], 12 + QUAD $0x041e4c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r14 + r11 + 4], 13 + WORD $0x894d; BYTE $0xdc // mov r12, r11 + QUAD $0x043e4c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r14 + r15 + 4], 14 + QUAD $0x04364c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rsi + 4], 15 + LONG $0xf7eb0f66 // por xmm6, xmm7 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x74b60f41; WORD $0x1106 // movzx esi, byte [r14 + rax + 17] + LONG $0xc66e0f66 // movd xmm0, esi + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0xd5db0f66 // pand xmm2, xmm5 + LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 + QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xcddb0f66 // pand xmm1, xmm5 + LONG $0xcaeb0f66 // por xmm1, xmm2 + LONG $0x74b60f41; WORD $0x1206 // movzx esi, byte [r14 + rax + 18] + LONG $0xee6e0f66 // movd xmm5, esi + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x053e44203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r14 + r15 + 5], 1 + QUAD $0x052e44203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r14 + r13 + 5], 2 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x050e44203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rcx + 5], 3 + QUAD $0x051e44203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r14 + rbx + 5], 4 + QUAD $0x051644203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r14 + rdx + 5], 5 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x053644203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r14 + rsi + 5], 6 + LONG $0x2444894c; BYTE $0x30 // mov qword [rsp + 48], r8 + QUAD $0x050644203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r8 + 5], 7 + QUAD $0x050e44203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r9 + 5], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x053644203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r14 + rsi + 5], 9 + WORD $0x894d; BYTE $0xd3 // mov r11, r10 + QUAD $0x051644203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r14 + r10 + 5], 10 + QUAD $0x053e44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rdi + 5], 11 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x053644203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rsi + 5], 12 + QUAD $0x052644203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r14 + r12 + 5], 13 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x053644203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rsi + 5], 14 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x053644203a0f4566; BYTE $0x0f // pinsrb xmm8, byte [r14 + rsi + 5], 15 + LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 + QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI2_14] */ + LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + LONG $0x74b60f41; WORD $0x1306 // movzx esi, byte [r14 + rax + 19] + LONG $0xfe6e0f66 // movd xmm7, esi + LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 + LONG $0x74b60f41; WORD $0x1406 // movzx esi, byte [r14 + rax + 20] + LONG $0xf66e0f66 // movd xmm6, esi + QUAD $0x063e5c203a0f4366; BYTE $0x01 // pinsrb xmm3, byte [r14 + r15 + 6], 1 + WORD $0x894d; BYTE $0xfa // mov r10, r15 + QUAD $0x062e5c203a0f4366; BYTE $0x02 // pinsrb xmm3, byte [r14 + r13 + 6], 2 + QUAD $0x060e5c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r14 + rcx + 6], 3 + WORD $0x8948; BYTE $0xcf // mov rdi, rcx + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x061e5c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r14 + rbx + 6], 4 + QUAD $0x06165c203a0f4166; BYTE $0x05 // pinsrb xmm3, byte [r14 + rdx + 6], 5 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x060e5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r14 + rcx + 6], 6 + QUAD $0x06065c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r8 + 6], 7 + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + QUAD $0x060e5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r9 + 6], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x06365c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r14 + rsi + 6], 9 + QUAD $0x061e5c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r14 + r11 + 6], 10 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x063e5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r14 + r15 + 6], 11 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x06265c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r12 + 6], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x061e5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rbx + 6], 13 + LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] + QUAD $0x060e5c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r14 + r9 + 6], 14 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x06065c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r14 + r8 + 6], 15 + QUAD $0x0000c024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 192] + QUAD $0x071654203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r14 + r10 + 7], 1 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x071e54203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rbx + 7], 2 + QUAD $0x073e54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdi + 7], 3 + QUAD $0x072e54203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r14 + r13 + 7], 4 + WORD $0x894d; BYTE $0xea // mov r10, r13 + QUAD $0x0000008824ac894c // mov qword [rsp + 136], r13 + QUAD $0x071654203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r14 + rdx + 7], 5 + QUAD $0x070e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 7], 6 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x070e54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rcx + 7], 7 + QUAD $0x070654203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r14 + rax + 7], 8 + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x073654203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r14 + rsi + 7], 9 + QUAD $0x071e54203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r11 + 7], 10 + QUAD $0x073e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 7], 11 + WORD $0x894d; BYTE $0xfb // mov r11, r15 + QUAD $0x072654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 7], 12 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x073e54203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rdi + 7], 13 + QUAD $0x070e54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r9 + 7], 14 + QUAD $0x070654203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r8 + 7], 15 + LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 + QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI2_15] */ + LONG $0xd9db0f66 // pand xmm3, xmm1 + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 + LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI2_6] */ + LONG $0xd1db0f66 // pand xmm2, xmm1 + LONG $0xd3eb0f66 // por xmm2, xmm3 + LONG $0xca6f0f66 // movdqa xmm1, xmm2 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x74b60f41; WORD $0x1506 // movzx esi, byte [r14 + rax + 21] + LONG $0xd66e0f66 // movd xmm2, esi + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x090e54203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rcx + 9], 1 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x091654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rdx + 9], 2 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x091654203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rdx + 9], 3 + QUAD $0x091654203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r10 + 9], 4 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x091654203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r10 + 9], 5 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x090e54203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r9 + 9], 6 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x093654203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rsi + 9], 7 + QUAD $0x091e54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rbx + 9], 8 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x093e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r15 + 9], 9 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x092654203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r12 + 9], 10 + QUAD $0x091e54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r11 + 9], 11 + QUAD $0x092e54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r13 + 9], 12 + QUAD $0x093e54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rdi + 9], 13 + LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] + QUAD $0x093e54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rdi + 9], 14 + QUAD $0x090654203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r8 + 9], 15 + LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 + QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 + LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 + LONG $0xccdb0f66 // pand xmm1, xmm4 + LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 + LONG $0x74b60f41; WORD $0x1606 // movzx esi, byte [r14 + rax + 22] + LONG $0xde6e0f66 // movd xmm3, esi + QUAD $0x0000e024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 224] + QUAD $0x080e64203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rcx + 8], 1 + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x081e64203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rbx + 8], 2 + QUAD $0x081664203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdx + 8], 3 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x080664203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rax + 8], 4 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + QUAD $0x081664203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r10 + 8], 5 + QUAD $0x080e64203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r14 + r9 + 8], 6 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x081e64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r11 + 8], 7 + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + QUAD $0x080664203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r14 + rax + 8], 8 + WORD $0x894c; BYTE $0xfe // mov rsi, r15 + QUAD $0x083e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r15 + 8], 9 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x082664203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r12 + 8], 10 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x080e64203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r14 + rcx + 8], 11 + QUAD $0x082e64203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r13 + 8], 12 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x080e64203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rcx + 8], 13 + QUAD $0x083e64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rdi + 8], 14 + WORD $0x8949; BYTE $0xfa // mov r10, rdi + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + QUAD $0x080e64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r9 + 8], 15 + LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 + LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 + QUAD $0x00a024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 160] + QUAD $0x0a0654203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r8 + 10], 1 + QUAD $0x0a1e54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rbx + 10], 2 + LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] + QUAD $0x0a3e54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rdi + 10], 3 + WORD $0x8948; BYTE $0xfb // mov rbx, rdi + QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] + QUAD $0x0a3e54203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r14 + rdi + 10], 4 + QUAD $0x0a1654203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r14 + rdx + 10], 5 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x0a2654203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r12 + 10], 6 + WORD $0x894d; BYTE $0xd8 // mov r8, r11 + QUAD $0x0a1e54203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r14 + r11 + 10], 7 + QUAD $0x0a0654203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rax + 10], 8 + WORD $0x8949; BYTE $0xc3 // mov r11, rax + QUAD $0x0a3654203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r14 + rsi + 10], 9 + QUAD $0x0a3e54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r15 + 10], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0a0654203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r14 + rax + 10], 11 + QUAD $0x0a2e54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r13 + 10], 12 + QUAD $0x0a0e54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rcx + 10], 13 + QUAD $0x0a1654203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r14 + r10 + 10], 14 + QUAD $0x0a0e54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r9 + 10], 15 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + LONG $0x74b60f41; WORD $0x170e // movzx esi, byte [r14 + rcx + 23] + LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + QUAD $0x00a024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm10 + LONG $0x74b60f41; WORD $0x180e // movzx esi, byte [r14 + rcx + 24] + LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0b165c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rdx + 11], 1 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0b0e5c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rcx + 11], 2 + QUAD $0x0b1e5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r14 + rbx + 11], 3 + QUAD $0x0b3e5c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rdi + 11], 4 + LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] + QUAD $0x0b3e5c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r14 + rdi + 11], 5 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + QUAD $0x0b265c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r12 + 11], 6 + QUAD $0x0b065c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r14 + r8 + 11], 7 + WORD $0x894d; BYTE $0xd9 // mov r9, r11 + QUAD $0x0b1e5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r11 + 11], 8 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x0b165c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r10 + 11], 9 + WORD $0x894d; BYTE $0xfb // mov r11, r15 + QUAD $0x0b3e5c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r14 + r15 + 11], 10 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + QUAD $0x0b065c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r14 + rax + 11], 11 + WORD $0x894d; BYTE $0xec // mov r12, r13 + QUAD $0x0b2e5c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r13 + 11], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0b065c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rax + 11], 13 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x0b365c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r14 + rsi + 11], 14 + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x0b1e5c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r14 + rbx + 11], 15 + QUAD $0x0c166c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rdx + 12], 1 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x0c2e6c203a0f4766; BYTE $0x02 // pinsrb xmm13, byte [r14 + r13 + 12], 2 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x0c1e6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r14 + rbx + 12], 3 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x0c2e6c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r14 + r13 + 12], 4 + QUAD $0x0c3e6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r14 + rdi + 12], 5 + QUAD $0x0c0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 12], 6 + QUAD $0x0c066c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r14 + r8 + 12], 7 + QUAD $0x0c0e6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r9 + 12], 8 + QUAD $0x0c166c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r10 + 12], 9 + QUAD $0x0c1e6c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r14 + r11 + 12], 10 + QUAD $0x0c3e6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r14 + r15 + 12], 11 + QUAD $0x0c266c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r12 + 12], 12 + QUAD $0x0c066c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rax + 12], 13 + QUAD $0x0c366c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r14 + rsi + 12], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0c066c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r14 + rax + 12], 15 + QUAD $0x0d1664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rdx + 13], 1 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0d1664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rdx + 13], 2 + QUAD $0x0d1e64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rbx + 13], 3 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x0d2e64203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r14 + r13 + 13], 4 + QUAD $0x0d3e64203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r14 + rdi + 13], 5 + QUAD $0x0d0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 13], 6 + QUAD $0x0d0664203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r14 + r8 + 13], 7 + QUAD $0x0d0e64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r9 + 13], 8 + QUAD $0x0d1664203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r10 + 13], 9 + QUAD $0x0d1e64203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r14 + r11 + 13], 10 + QUAD $0x0d3e64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r14 + r15 + 13], 11 + QUAD $0x0d2664203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r12 + 13], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0d1664203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rdx + 13], 13 + QUAD $0x0d3664203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r14 + rsi + 13], 14 + QUAD $0x0d0664203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r14 + rax + 13], 15 + LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 + QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 + QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x74b60f41; WORD $0x1906 // movzx esi, byte [r14 + rax + 25] + LONG $0xce6e0f66 // movd xmm1, esi + LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 + QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI2_14] */ + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x74b60f41; WORD $0x1a06 // movzx esi, byte [r14 + rax + 26] + LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi + QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0e0664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rax + 14], 1 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x0e2e64203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r14 + r13 + 14], 2 + LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] + QUAD $0x0e3e64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdi + 14], 3 + QUAD $0x0e1e64203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rbx + 14], 4 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0e0664203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r14 + rax + 14], 5 + QUAD $0x0e0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 14], 6 + QUAD $0x0e0664203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r8 + 14], 7 + QUAD $0x0e0e64203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r9 + 14], 8 + QUAD $0x0e1664203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r10 + 14], 9 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + QUAD $0x0e1e64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r11 + 14], 10 + QUAD $0x0e3e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r15 + 14], 11 + QUAD $0x0e2664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r12 + 14], 12 + QUAD $0x0e1664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 14], 13 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0e1664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rdx + 14], 14 + LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] + QUAD $0x0e1e64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r11 + 14], 15 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f1674203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r14 + rdx + 15], 1 + QUAD $0x0f2e74203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r14 + r13 + 15], 2 + QUAD $0x0f3e74203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r14 + rdi + 15], 3 + QUAD $0x0f1e74203a0f4566; BYTE $0x04 // pinsrb xmm14, byte [r14 + rbx + 15], 4 + QUAD $0x0f0674203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r14 + rax + 15], 5 + QUAD $0x0f0e74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r14 + rcx + 15], 6 + QUAD $0x0f0674203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r14 + r8 + 15], 7 + QUAD $0x0f0e74203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r14 + r9 + 15], 8 + QUAD $0x0f1674203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r14 + r10 + 15], 9 + QUAD $0x0f3674203a0f4566; BYTE $0x0a // pinsrb xmm14, byte [r14 + rsi + 15], 10 + QUAD $0x0f3e74203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r14 + r15 + 15], 11 + QUAD $0x0f2674203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r14 + r12 + 15], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0f1674203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r14 + rdx + 15], 13 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0f1674203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r14 + rdx + 15], 14 + QUAD $0x0f1e74203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r14 + r11 + 15], 15 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x10167c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rdx + 16], 1 + QUAD $0x102e7c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r14 + r13 + 16], 2 + QUAD $0x103e7c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r14 + rdi + 16], 3 + QUAD $0x101e7c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r14 + rbx + 16], 4 + QUAD $0x10067c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r14 + rax + 16], 5 + QUAD $0x100e7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r14 + rcx + 16], 6 + QUAD $0x10067c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r14 + r8 + 16], 7 + QUAD $0x100e7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r9 + 16], 8 + QUAD $0x10167c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r14 + r10 + 16], 9 + QUAD $0x10367c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r14 + rsi + 16], 10 + QUAD $0x103e7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r14 + r15 + 16], 11 + QUAD $0x10267c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r14 + r12 + 16], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x10167c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r14 + rdx + 16], 13 + LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] + QUAD $0x101e7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r14 + r11 + 16], 14 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x111644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rdx + 17], 1 + QUAD $0x112e44203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r14 + r13 + 17], 2 + QUAD $0x113e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdi + 17], 3 + QUAD $0x111e44203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rbx + 17], 4 + QUAD $0x110644203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rax + 17], 5 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x110e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 17], 6 + QUAD $0x110644203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r8 + 17], 7 + QUAD $0x110e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r9 + 17], 8 + QUAD $0x111644203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r10 + 17], 9 + QUAD $0x113644203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rsi + 17], 10 + QUAD $0x113e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r15 + 17], 11 + QUAD $0x112644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r12 + 17], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x110644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rax + 17], 13 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x111644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rdx + 17], 14 + QUAD $0x00a024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 160] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + LONG $0x74b60f41; WORD $0x1b06 // movzx esi, byte [r14 + rax + 27] + LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi + QUAD $0x00b024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 + QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI2_15] */ + LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 + LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 + LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI2_6] */ + LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 + LONG $0x74b60f41; WORD $0x1c06 // movzx esi, byte [r14 + rax + 28] + LONG $0xe66e0f66 // movd xmm4, esi + LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] + QUAD $0x111e44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r11 + 17], 15 + LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 + LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 + LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 + QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI2_10] */ + LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 + LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 + QUAD $0x00a024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm13 + LONG $0x74b60f41; WORD $0x1d06 // movzx esi, byte [r14 + rax + 29] + LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi + QUAD $0x101e7c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r14 + r11 + 16], 15 + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x12366c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rsi + 18], 1 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x12366c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rsi + 18], 2 + QUAD $0x123e6c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r14 + rdi + 18], 3 + QUAD $0x121e6c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rbx + 18], 4 + QUAD $0x122e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r13 + 18], 5 + QUAD $0x120e6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r14 + rcx + 18], 6 + QUAD $0x12066c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r8 + 18], 7 + QUAD $0x120e6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r9 + 18], 8 + QUAD $0x12166c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r10 + 18], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x12066c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r14 + rax + 18], 10 + QUAD $0x123e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r15 + 18], 11 + QUAD $0x12266c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r14 + r12 + 18], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x12366c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rsi + 18], 13 + QUAD $0x12166c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rdx + 18], 14 + LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 + QUAD $0x121e6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r11 + 18], 15 + LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 + QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + LONG $0x74b60f41; WORD $0x1e16 // movzx esi, byte [r14 + rdx + 30] + LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x13367c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rsi + 19], 1 + QUAD $0x143674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rsi + 20], 1 + QUAD $0x153654203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rsi + 21], 1 + QUAD $0x16365c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rsi + 22], 1 + QUAD $0x173644203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rsi + 23], 1 + QUAD $0x183654203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rsi + 24], 1 + QUAD $0x19364c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rsi + 25], 1 + QUAD $0x1a365c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rsi + 26], 1 + QUAD $0x1b364c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rsi + 27], 1 + QUAD $0x1c3664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rsi + 28], 1 + QUAD $0x1d366c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rsi + 29], 1 + QUAD $0x1e3664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rsi + 30], 1 + LONG $0x54b60f41; WORD $0x1f16 // movzx edx, byte [r14 + rdx + 31] + LONG $0xc26e0f66 // movd xmm0, edx + QUAD $0x1f3644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rsi + 31], 1 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x13167c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rdx + 19], 2 + QUAD $0x141674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rdx + 20], 2 + QUAD $0x151654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rdx + 21], 2 + QUAD $0x16165c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rdx + 22], 2 + QUAD $0x171644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rdx + 23], 2 + QUAD $0x181654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rdx + 24], 2 + QUAD $0x19164c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rdx + 25], 2 + QUAD $0x1a165c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rdx + 26], 2 + QUAD $0x1b164c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rdx + 27], 2 + QUAD $0x1c1664203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rdx + 28], 2 + QUAD $0x1d166c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rdx + 29], 2 + QUAD $0x1e1664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rdx + 30], 2 + QUAD $0x1f1644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rdx + 31], 2 + QUAD $0x133e7c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r14 + rdi + 19], 3 + QUAD $0x131e7c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r14 + rbx + 19], 4 + QUAD $0x132e7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r13 + 19], 5 + QUAD $0x130e7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r14 + rcx + 19], 6 + QUAD $0x13067c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r14 + r8 + 19], 7 + QUAD $0x130e7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r9 + 19], 8 + QUAD $0x13167c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r10 + 19], 9 + QUAD $0x13067c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r14 + rax + 19], 10 + QUAD $0x133e7c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r14 + r15 + 19], 11 + QUAD $0x13267c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r14 + r12 + 19], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x13167c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rdx + 19], 13 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x13367c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r14 + rsi + 19], 14 + QUAD $0x131e7c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r14 + r11 + 19], 15 + QUAD $0x143e74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rdi + 20], 3 + QUAD $0x141e74203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rbx + 20], 4 + QUAD $0x142e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r13 + 20], 5 + QUAD $0x140e74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rcx + 20], 6 + QUAD $0x140674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r8 + 20], 7 + QUAD $0x140e74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r9 + 20], 8 + QUAD $0x141674203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r10 + 20], 9 + QUAD $0x140674203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r14 + rax + 20], 10 + QUAD $0x143e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r15 + 20], 11 + QUAD $0x142674203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r12 + 20], 12 + QUAD $0x141674203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r14 + rdx + 20], 13 + QUAD $0x143674203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rsi + 20], 14 + QUAD $0x0000a024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 160] + QUAD $0x141e74203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r14 + r11 + 20], 15 + QUAD $0x00b024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 + QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 + QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xf7eb0f66 // por xmm6, xmm7 + QUAD $0x153e54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdi + 21], 3 + QUAD $0x151e54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rbx + 21], 4 + QUAD $0x152e54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r13 + 21], 5 + QUAD $0x150e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 21], 6 + QUAD $0x150654203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r8 + 21], 7 + QUAD $0x150e54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r9 + 21], 8 + QUAD $0x151654203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r10 + 21], 9 + QUAD $0x150654203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r14 + rax + 21], 10 + QUAD $0x153e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 21], 11 + QUAD $0x152654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 21], 12 + QUAD $0x151654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rdx + 21], 13 + QUAD $0x153654203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rsi + 21], 14 + QUAD $0x151e54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r11 + 21], 15 + LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 + QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI2_14] */ + LONG $0xd7db0f66 // pand xmm2, xmm7 + LONG $0xd6eb0f66 // por xmm2, xmm6 + LONG $0xd5eb0f66 // por xmm2, xmm5 + QUAD $0x163e5c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r14 + rdi + 22], 3 + QUAD $0x161e5c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r14 + rbx + 22], 4 + QUAD $0x162e5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r13 + 22], 5 + QUAD $0x160e5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r14 + rcx + 22], 6 + QUAD $0x16065c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r8 + 22], 7 + QUAD $0x160e5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r9 + 22], 8 + QUAD $0x16165c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r10 + 22], 9 + QUAD $0x16065c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r14 + rax + 22], 10 + QUAD $0x163e5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r14 + r15 + 22], 11 + QUAD $0x16265c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r12 + 22], 12 + QUAD $0x16165c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rdx + 22], 13 + QUAD $0x16365c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r14 + rsi + 22], 14 + QUAD $0x161e5c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r14 + r11 + 22], 15 + QUAD $0x173e44203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rdi + 23], 3 + QUAD $0x171e44203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r14 + rbx + 23], 4 + QUAD $0x172e44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r13 + 23], 5 + QUAD $0x170e44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r14 + rcx + 23], 6 + QUAD $0x170644203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r8 + 23], 7 + QUAD $0x170e44203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r9 + 23], 8 + QUAD $0x171644203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r10 + 23], 9 + QUAD $0x170644203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rax + 23], 10 + QUAD $0x173e44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r14 + r15 + 23], 11 + QUAD $0x172644203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r14 + r12 + 23], 12 + QUAD $0x171644203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rdx + 23], 13 + QUAD $0x173644203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rsi + 23], 14 + QUAD $0x171e44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r11 + 23], 15 + LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 + QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI2_15] */ + LONG $0xdddb0f66 // pand xmm3, xmm5 + LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 + LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 + LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI2_6] */ + LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 + LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 + QUAD $0x193e4c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r14 + rdi + 25], 3 + QUAD $0x191e4c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r14 + rbx + 25], 4 + QUAD $0x192e4c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r14 + r13 + 25], 5 + QUAD $0x190e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 25], 6 + QUAD $0x19064c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r14 + r8 + 25], 7 + QUAD $0x190e4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r9 + 25], 8 + QUAD $0x19164c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r10 + 25], 9 + QUAD $0x19064c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r14 + rax + 25], 10 + QUAD $0x193e4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r14 + r15 + 25], 11 + QUAD $0x19264c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r12 + 25], 12 + QUAD $0x19164c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r14 + rdx + 25], 13 + QUAD $0x19364c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r14 + rsi + 25], 14 + QUAD $0x191e4c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r14 + r11 + 25], 15 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 + LONG $0xd16f0f66 // movdqa xmm2, xmm1 + QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI2_10] */ + LONG $0xd3db0f66 // pand xmm2, xmm3 + LONG $0xd1f80f66 // psubb xmm2, xmm1 + QUAD $0x183e54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rdi + 24], 3 + QUAD $0x181e54203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r14 + rbx + 24], 4 + QUAD $0x182e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r13 + 24], 5 + QUAD $0x180e54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r14 + rcx + 24], 6 + QUAD $0x180654203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r14 + r8 + 24], 7 + QUAD $0x180e54203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r14 + r9 + 24], 8 + QUAD $0x181654203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r10 + 24], 9 + QUAD $0x180654203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r14 + rax + 24], 10 + QUAD $0x183e54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r15 + 24], 11 + QUAD $0x182654203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r12 + 24], 12 + QUAD $0x181654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rdx + 24], 13 + QUAD $0x183654203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rsi + 24], 14 + QUAD $0x181e54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r11 + 24], 15 + LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 + LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 + QUAD $0x1a3e5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r14 + rdi + 26], 3 + QUAD $0x1a1e5c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rbx + 26], 4 + QUAD $0x1a2e5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r13 + 26], 5 + QUAD $0x1a0e5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r14 + rcx + 26], 6 + QUAD $0x1a065c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r14 + r8 + 26], 7 + QUAD $0x1a0e5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r9 + 26], 8 + QUAD $0x1a165c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r10 + 26], 9 + QUAD $0x1a065c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r14 + rax + 26], 10 + QUAD $0x1a3e5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r14 + r15 + 26], 11 + QUAD $0x1a265c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r12 + 26], 12 + QUAD $0x1a165c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rdx + 26], 13 + QUAD $0x1a365c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r14 + rsi + 26], 14 + QUAD $0x1a1e5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r11 + 26], 15 + LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 + QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 + LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 + QUAD $0x1b3e4c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r14 + rdi + 27], 3 + QUAD $0x1b1e4c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r14 + rbx + 27], 4 + QUAD $0x1b2e4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r13 + 27], 5 + QUAD $0x1b0e4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r14 + rcx + 27], 6 + QUAD $0x1b064c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r8 + 27], 7 + QUAD $0x1b0e4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r9 + 27], 8 + QUAD $0x1b164c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r14 + r10 + 27], 9 + QUAD $0x1b064c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r14 + rax + 27], 10 + QUAD $0x1b3e4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r14 + r15 + 27], 11 + QUAD $0x1b264c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r14 + r12 + 27], 12 + QUAD $0x1b164c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r14 + rdx + 27], 13 + QUAD $0x1b364c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rsi + 27], 14 + QUAD $0x1b1e4c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r14 + r11 + 27], 15 + QUAD $0x1c3e64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdi + 28], 3 + QUAD $0x1c1e64203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rbx + 28], 4 + QUAD $0x1c2e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r13 + 28], 5 + QUAD $0x1c0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 28], 6 + QUAD $0x1c0664203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r8 + 28], 7 + QUAD $0x1c0e64203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r9 + 28], 8 + QUAD $0x1c1664203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r10 + 28], 9 + QUAD $0x1c0664203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r14 + rax + 28], 10 + QUAD $0x1c3e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r15 + 28], 11 + QUAD $0x1c2664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r12 + 28], 12 + QUAD $0x1c1664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 28], 13 + QUAD $0x1c3664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rsi + 28], 14 + QUAD $0x1c1e64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r11 + 28], 15 + QUAD $0x1d3e6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r14 + rdi + 29], 3 + QUAD $0x1d1e6c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r14 + rbx + 29], 4 + QUAD $0x1d2e6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r14 + r13 + 29], 5 + QUAD $0x1d0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 29], 6 + QUAD $0x1d066c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r14 + r8 + 29], 7 + QUAD $0x1d0e6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r9 + 29], 8 + QUAD $0x1d166c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r10 + 29], 9 + QUAD $0x1d066c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r14 + rax + 29], 10 + QUAD $0x1d3e6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r14 + r15 + 29], 11 + QUAD $0x1d266c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r12 + 29], 12 + QUAD $0x1d166c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rdx + 29], 13 + QUAD $0x1d366c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r14 + rsi + 29], 14 + LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 + LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 + QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 + QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 + QUAD $0x1d1e6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r14 + r11 + 29], 15 + LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 + LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 + LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 + QUAD $0x1e3e64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rdi + 30], 3 + QUAD $0x1f3e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdi + 31], 3 + QUAD $0x1e1e64203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r14 + rbx + 30], 4 + QUAD $0x1f1e44203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rbx + 31], 4 + QUAD $0x1e2e64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r14 + r13 + 30], 5 + QUAD $0x1f2e44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r13 + 31], 5 + QUAD $0x1e0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 30], 6 + QUAD $0x1f0e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 31], 6 + QUAD $0x1e0664203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r14 + r8 + 30], 7 + QUAD $0x1f0644203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r8 + 31], 7 + QUAD $0x1e0e64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r9 + 30], 8 + QUAD $0x1f0e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r9 + 31], 8 + QUAD $0x1e1664203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r10 + 30], 9 + QUAD $0x1f1644203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r10 + 31], 9 + QUAD $0x1e0664203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r14 + rax + 30], 10 + QUAD $0x1f0644203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rax + 31], 10 + QUAD $0x1e3e64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r14 + r15 + 30], 11 + QUAD $0x1f3e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r15 + 31], 11 + QUAD $0x1e2664203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r12 + 30], 12 + QUAD $0x1f2644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r12 + 31], 12 + QUAD $0x1e1664203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rdx + 30], 13 + QUAD $0x1f1644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rdx + 31], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x1e3664203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r14 + rsi + 30], 14 + QUAD $0x1f3644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rsi + 31], 14 + QUAD $0x1e1e64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r14 + r11 + 30], 15 + QUAD $0x1f1e44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r11 + 31], 15 + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 + LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 + LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0xc6db0f66 // pand xmm0, xmm6 + LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 + LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 + LONG $0xc8600f66 // punpcklbw xmm1, xmm0 + QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] + LONG $0xd46f0f66 // movdqa xmm2, xmm4 + LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 + LONG $0xda6f0f66 // movdqa xmm3, xmm2 + LONG $0xd9610f66 // punpcklwd xmm3, xmm1 + LONG $0xd1690f66 // punpckhwd xmm2, xmm1 + LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 + LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + LONG $0x647f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm4 + LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 + LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 + LONG $0x1c7f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm3 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000d8248c3b48 // cmp rcx, qword [rsp + 216] + JNE LBB2_215 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x000000d8248c3b48 // cmp rcx, qword [rsp + 216] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x241c8a44 // mov r11b, byte [rsp] + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + JNE LBB2_154 + JMP LBB2_158 + +LBB2_217: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + QUAD $0x000000d8248c8948 // mov qword [rsp + 216], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0xc3b60f41 // movzx eax, r11b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + WORD $0xc031 // xor eax, eax + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + +LBB2_218: + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + LONG $0x05e2c148 // shl rdx, 5 + WORD $0x8949; BYTE $0xd0 // mov r8, rdx + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + LONG $0x24548948; BYTE $0x38 // mov qword [rsp + 56], rdx + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + WORD $0x8949; BYTE $0xd7 // mov r15, rdx + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x8949; BYTE $0xd1 // mov r9, rdx + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + LONG $0x0cb60f41; BYTE $0x16 // movzx ecx, byte [r14 + rdx] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x4cb60f41; WORD $0x0116 // movzx ecx, byte [r14 + rdx + 1] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x4cb60f41; WORD $0x0216 // movzx ecx, byte [r14 + rdx + 2] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x4cb60f41; WORD $0x0316 // movzx ecx, byte [r14 + rdx + 3] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x4cb60f41; WORD $0x0416 // movzx ecx, byte [r14 + rdx + 4] + LONG $0xc96e0f66 // movd xmm1, ecx + LONG $0x4cb60f41; WORD $0x0516 // movzx ecx, byte [r14 + rdx + 5] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x4cb60f41; WORD $0x0616 // movzx ecx, byte [r14 + rdx + 6] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x4cb60f41; WORD $0x0716 // movzx ecx, byte [r14 + rdx + 7] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 + LONG $0x4cb60f41; WORD $0x0816 // movzx ecx, byte [r14 + rdx + 8] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 + LONG $0x4cb60f41; WORD $0x0916 // movzx ecx, byte [r14 + rdx + 9] + LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx + LONG $0x4cb60f41; WORD $0x0a16 // movzx ecx, byte [r14 + rdx + 10] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 + LONG $0x4cb60f41; WORD $0x0b16 // movzx ecx, byte [r14 + rdx + 11] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x4cb60f41; WORD $0x0c16 // movzx ecx, byte [r14 + rdx + 12] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x4cb60f41; WORD $0x0d16 // movzx ecx, byte [r14 + rdx + 13] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x4cb60f41; WORD $0x0e16 // movzx ecx, byte [r14 + rdx + 14] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x00010024847f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm0 + WORD $0x8949; BYTE $0xd4 // mov r12, rdx + LONG $0x20cc8349 // or r12, 32 + LONG $0x2464894c; BYTE $0x20 // mov qword [rsp + 32], r12 + LONG $0x40c88349 // or r8, 64 + LONG $0x60c88348 // or rax, 96 + LONG $0x80ca8149; WORD $0x0000; BYTE $0x00 // or r10, 128 + LONG $0xa0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 160 + LONG $0x246c894c; BYTE $0x50 // mov qword [rsp + 80], r13 + LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] + LONG $0xc0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 192 + LONG $0xe0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 224 + LONG $0x245c894c; BYTE $0x58 // mov qword [rsp + 88], r11 + LONG $0x00cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 256 + LONG $0x20cf8149; WORD $0x0001; BYTE $0x00 // or r15, 288 + LONG $0x40cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 320 + LONG $0x247c8948; BYTE $0x30 // mov qword [rsp + 48], rdi + LONG $0x60c98149; WORD $0x0001; BYTE $0x00 // or r9, 352 + LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 + LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0x24548948; BYTE $0x18 // mov qword [rsp + 24], rdx + LONG $0xc0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 448 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 + LONG $0x244c8948; BYTE $0x28 // mov qword [rsp + 40], rcx + QUAD $0x01263c203a0f4766 // pinsrb xmm15, byte [r14 + r12], 1 + QUAD $0x02063c203a0f4766 // pinsrb xmm15, byte [r14 + r8], 2 + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + QUAD $0x03063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 3 + QUAD $0x04163c203a0f4766 // pinsrb xmm15, byte [r14 + r10], 4 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x05263c203a0f4766 // pinsrb xmm15, byte [r14 + r12], 5 + LONG $0x246c894c; BYTE $0x38 // mov qword [rsp + 56], r13 + QUAD $0x062e3c203a0f4766 // pinsrb xmm15, byte [r14 + r13], 6 + QUAD $0x071e3c203a0f4766 // pinsrb xmm15, byte [r14 + r11], 7 + QUAD $0x081e3c203a0f4566 // pinsrb xmm15, byte [r14 + rbx], 8 + QUAD $0x093e3c203a0f4766 // pinsrb xmm15, byte [r14 + r15], 9 + QUAD $0x0a3e3c203a0f4566 // pinsrb xmm15, byte [r14 + rdi], 10 + QUAD $0x0b0e3c203a0f4766 // pinsrb xmm15, byte [r14 + r9], 11 + QUAD $0x0c363c203a0f4566 // pinsrb xmm15, byte [r14 + rsi], 12 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0d063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0e063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 14 + QUAD $0x0f0e3c203a0f4566 // pinsrb xmm15, byte [r14 + rcx], 15 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x012e6c203a0f4366; BYTE $0x01 // pinsrb xmm5, byte [r14 + r13 + 1], 1 + QUAD $0x01066c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r14 + r8 + 1], 2 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + QUAD $0x01166c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r14 + rdx + 1], 3 + QUAD $0x01166c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r14 + r10 + 1], 4 + QUAD $0x01266c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r12 + 1], 5 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + QUAD $0x01066c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r8 + 1], 6 + QUAD $0x011e6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r11 + 1], 7 + QUAD $0x011e6c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r14 + rbx + 1], 8 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + QUAD $0x013e6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r15 + 1], 9 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x013e6c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r14 + rdi + 1], 10 + QUAD $0x010e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r9 + 1], 11 + WORD $0x894d; BYTE $0xcf // mov r15, r9 + QUAD $0x01366c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rsi + 1], 12 + WORD $0x8949; BYTE $0xf1 // mov r9, rsi + LONG $0x24748948; BYTE $0x78 // mov qword [rsp + 120], rsi + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x01066c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rax + 1], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x01066c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rax + 1], 14 + QUAD $0x010e6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r14 + rcx + 1], 15 + QUAD $0x00b0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xe9 // pcmpeqb xmm5, xmm9 + LONG $0xfd6f0f66 // movdqa xmm7, xmm5 + QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI2_10] */ + LONG $0xfcdb0f66 // pand xmm7, xmm4 + LONG $0xfdf80f66 // psubb xmm7, xmm5 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + LONG $0x74b60f41; WORD $0x0f06 // movzx esi, byte [r14 + rax + 15] + LONG $0x6e0f4466; BYTE $0xf6 // movd xmm14, esi + LONG $0x740f4566; BYTE $0xf9 // pcmpeqb xmm15, xmm9 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x020e74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rcx + 2], 1 + LONG $0x246c894c; BYTE $0x40 // mov qword [rsp + 64], r13 + QUAD $0x022e74203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r14 + r13 + 2], 2 + QUAD $0x021674203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rdx + 2], 3 + WORD $0x894c; BYTE $0xd7 // mov rdi, r10 + LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 + QUAD $0x021674203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r14 + r10 + 2], 4 + QUAD $0x022674203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r12 + 2], 5 + QUAD $0x020674203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r8 + 2], 6 + LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] + QUAD $0x021674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r10 + 2], 7 + QUAD $0x00000090249c894c // mov qword [rsp + 144], r11 + QUAD $0x021e74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r11 + 2], 8 + LONG $0x245c8948; BYTE $0x70 // mov qword [rsp + 112], rbx + QUAD $0x021e74203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r14 + rbx + 2], 9 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x020674203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r8 + 2], 10 + QUAD $0x023e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r15 + 2], 11 + QUAD $0x020e74203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r9 + 2], 12 + LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] + QUAD $0x020e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r9 + 2], 13 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x023674203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rsi + 2], 14 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x023674203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rsi + 2], 15 + LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 + LONG $0x740f4166; BYTE $0xf1 // pcmpeqb xmm6, xmm9 + QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xf0db0f66 // pand xmm6, xmm0 + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x74b60f41; WORD $0x1006 // movzx esi, byte [r14 + rax + 16] + LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi + QUAD $0x030e54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rcx + 3], 1 + QUAD $0x032e54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r13 + 3], 2 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x031654203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdx + 3], 3 + QUAD $0x033e54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rdi + 3], 4 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + QUAD $0x032654203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r12 + 3], 5 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x030e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 3], 6 + QUAD $0x031654203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r10 + 3], 7 + QUAD $0x031e54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r11 + 3], 8 + QUAD $0x031e54203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r14 + rbx + 3], 9 + QUAD $0x030654203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r8 + 3], 10 + QUAD $0x033e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 3], 11 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x032654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 3], 12 + QUAD $0x030e54203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r14 + r9 + 3], 13 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x033654203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rsi + 3], 14 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x033e54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rdi + 3], 15 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x042e4c203a0f4366; BYTE $0x01 // pinsrb xmm1, byte [r14 + r13 + 4], 1 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x042e4c203a0f4366; BYTE $0x02 // pinsrb xmm1, byte [r14 + r13 + 4], 2 + QUAD $0x04064c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r14 + rax + 4], 3 + LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] + QUAD $0x043e4c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r14 + rdi + 4], 4 + QUAD $0x04164c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r14 + rdx + 4], 5 + QUAD $0x040e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 4], 6 + QUAD $0x04164c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r14 + r10 + 4], 7 + QUAD $0x041e4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r11 + 4], 8 + QUAD $0x041e4c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r14 + rbx + 4], 9 + QUAD $0x04064c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r14 + r8 + 4], 10 + QUAD $0x043e4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r14 + r15 + 4], 11 + LONG $0x247c894c; BYTE $0x68 // mov qword [rsp + 104], r15 + QUAD $0x04264c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r12 + 4], 12 + QUAD $0x040e4c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r14 + r9 + 4], 13 + QUAD $0x04364c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r14 + rsi + 4], 14 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x04064c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r14 + r8 + 4], 15 + LONG $0xf7eb0f66 // por xmm6, xmm7 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + LONG $0x74b60f41; WORD $0x113e // movzx esi, byte [r14 + rdi + 17] + LONG $0xc66e0f66 // movd xmm0, esi + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0xd5db0f66 // pand xmm2, xmm5 + LONG $0x740f4166; BYTE $0xc9 // pcmpeqb xmm1, xmm9 + QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xcddb0f66 // pand xmm1, xmm5 + LONG $0xcaeb0f66 // por xmm1, xmm2 + LONG $0x74b60f41; WORD $0x123e // movzx esi, byte [r14 + rdi + 18] + LONG $0xee6e0f66 // movd xmm5, esi + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x051644203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r14 + r10 + 5], 1 + QUAD $0x052e44203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r14 + r13 + 5], 2 + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax + QUAD $0x050644203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rax + 5], 3 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x051644203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r14 + rdx + 5], 4 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x050e44203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r14 + rcx + 5], 5 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x050e44203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r14 + r9 + 5], 6 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x051e44203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r11 + 5], 7 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x051e44203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r14 + rbx + 5], 8 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x052644203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r12 + 5], 9 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x053644203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rsi + 5], 10 + QUAD $0x053e44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r14 + r15 + 5], 11 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + QUAD $0x053644203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rsi + 5], 12 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x053644203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rsi + 5], 13 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x053e44203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r14 + r15 + 5], 14 + QUAD $0x050644203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r8 + 5], 15 + LONG $0x740f4566; BYTE $0xc1 // pcmpeqb xmm8, xmm9 + QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI2_14] */ + LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + LONG $0x74b60f41; WORD $0x133e // movzx esi, byte [r14 + rdi + 19] + LONG $0xfe6e0f66 // movd xmm7, esi + LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 + LONG $0x74b60f41; WORD $0x143e // movzx esi, byte [r14 + rdi + 20] + LONG $0xf66e0f66 // movd xmm6, esi + WORD $0x894d; BYTE $0xd0 // mov r8, r10 + QUAD $0x06165c203a0f4366; BYTE $0x01 // pinsrb xmm3, byte [r14 + r10 + 6], 1 + QUAD $0x062e5c203a0f4366; BYTE $0x02 // pinsrb xmm3, byte [r14 + r13 + 6], 2 + QUAD $0x06065c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r14 + rax + 6], 3 + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + QUAD $0x06165c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r14 + rdx + 6], 4 + QUAD $0x060e5c203a0f4166; BYTE $0x05 // pinsrb xmm3, byte [r14 + rcx + 6], 5 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + QUAD $0x060e5c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r14 + r9 + 6], 6 + WORD $0x894d; BYTE $0xd9 // mov r9, r11 + QUAD $0x061e5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r11 + 6], 7 + QUAD $0x061e5c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r14 + rbx + 6], 8 + QUAD $0x06265c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r12 + 6], 9 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x063e5c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r14 + rdi + 6], 10 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x06165c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rdx + 6], 11 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x06265c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r12 + 6], 12 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x06365c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rsi + 6], 13 + QUAD $0x063e5c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r14 + r15 + 6], 14 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x06065c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r14 + rax + 6], 15 + QUAD $0x0000c024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 192] + QUAD $0x070654203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r14 + r8 + 7], 1 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + QUAD $0x072e54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r13 + 7], 2 + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + QUAD $0x0000008824948b48 // mov rdx, qword [rsp + 136] + QUAD $0x071654203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdx + 7], 3 + QUAD $0x071654203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r14 + r10 + 7], 4 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x071654203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r14 + rdx + 7], 5 + QUAD $0x070e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 7], 6 + WORD $0x8949; BYTE $0xca // mov r10, rcx + QUAD $0x070e54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r9 + 7], 7 + QUAD $0x071e54203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r14 + rbx + 7], 8 + QUAD $0x071e54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r11 + 7], 9 + QUAD $0x073e54203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r14 + rdi + 7], 10 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x070e54203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rcx + 7], 11 + QUAD $0x072654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 7], 12 + QUAD $0x073654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rsi + 7], 13 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x073e54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rdi + 7], 14 + QUAD $0x070654203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rax + 7], 15 + LONG $0x740f4166; BYTE $0xd9 // pcmpeqb xmm3, xmm9 + QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI2_15] */ + LONG $0xd9db0f66 // pand xmm3, xmm1 + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 + LONG $0x4d6f0f66; BYTE $0x60 // movdqa xmm1, oword 96[rbp] /* [rip + .LCPI2_6] */ + LONG $0xd1db0f66 // pand xmm2, xmm1 + LONG $0xd3eb0f66 // por xmm2, xmm3 + LONG $0xca6f0f66 // movdqa xmm1, xmm2 + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + LONG $0x74b60f43; WORD $0x150e // movzx esi, byte [r14 + r9 + 21] + LONG $0xd66e0f66 // movd xmm2, esi + QUAD $0x093e54203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r15 + 9], 1 + QUAD $0x092e54203a0f4766; BYTE $0x02 // pinsrb xmm10, byte [r14 + r13 + 9], 2 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x090654203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rax + 9], 3 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x092e54203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r13 + 9], 4 + QUAD $0x091654203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r14 + rdx + 9], 5 + QUAD $0x091654203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r10 + 9], 6 + LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] + QUAD $0x091e54203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r14 + r11 + 9], 7 + QUAD $0x091e54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rbx + 9], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x093654203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r14 + rsi + 9], 9 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x093654203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r14 + rsi + 9], 10 + QUAD $0x090e54203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r14 + rcx + 9], 11 + QUAD $0x092654203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r12 + 9], 12 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x091654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rdx + 9], 13 + QUAD $0x093e54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rdi + 9], 14 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x091654203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r10 + 9], 15 + LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 + QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 + LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 + LONG $0xccdb0f66 // pand xmm1, xmm4 + LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 + LONG $0x74b60f43; WORD $0x160e // movzx esi, byte [r14 + r9 + 22] + LONG $0xde6e0f66 // movd xmm3, esi + QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x083e64203a0f4366; BYTE $0x01 // pinsrb xmm4, byte [r14 + r15 + 8], 1 + QUAD $0x080664203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r14 + r8 + 8], 2 + QUAD $0x080664203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rax + 8], 3 + WORD $0x8949; BYTE $0xc4 // mov r12, rax + QUAD $0x082e64203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r13 + 8], 4 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x083e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r15 + 8], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x080664203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rax + 8], 6 + WORD $0x894d; BYTE $0xd8 // mov r8, r11 + QUAD $0x081e64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r11 + 8], 7 + WORD $0x8948; BYTE $0xdf // mov rdi, rbx + QUAD $0x081e64203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r14 + rbx + 8], 8 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x081e64203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r14 + rbx + 8], 9 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x083664203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r14 + rsi + 8], 10 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x081e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r11 + 8], 11 + QUAD $0x080e64203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r14 + rcx + 8], 12 + QUAD $0x081664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 8], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x080664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rax + 8], 14 + QUAD $0x081664203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r10 + 8], 15 + LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 + LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 + QUAD $0x00a024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 160] + QUAD $0x0a0e54203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r9 + 10], 1 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x0a0e54203a0f4766; BYTE $0x02 // pinsrb xmm10, byte [r14 + r9 + 10], 2 + QUAD $0x0a2654203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r14 + r12 + 10], 3 + QUAD $0x0a2e54203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r13 + 10], 4 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x0a3e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r15 + 10], 5 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x0a3e54203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r15 + 10], 6 + QUAD $0x0a0654203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r14 + r8 + 10], 7 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + QUAD $0x0a3e54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rdi + 10], 8 + QUAD $0x0a1e54203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r14 + rbx + 10], 9 + QUAD $0x0a3654203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r14 + rsi + 10], 10 + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + QUAD $0x0a1e54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r11 + 10], 11 + QUAD $0x0a0e54203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r14 + rcx + 10], 12 + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x0a3654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rsi + 10], 13 + QUAD $0x0a0654203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rax + 10], 14 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0a1e54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r11 + 10], 15 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + LONG $0x74b60f41; WORD $0x1706 // movzx esi, byte [r14 + rax + 23] + LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + QUAD $0x00a024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm10 + LONG $0x74b60f41; WORD $0x1806 // movzx esi, byte [r14 + rax + 24] + LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0b065c203a0f4766; BYTE $0x01 // pinsrb xmm11, byte [r14 + r8 + 11], 1 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + QUAD $0x0b0e5c203a0f4766; BYTE $0x02 // pinsrb xmm11, byte [r14 + r9 + 11], 2 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x0b265c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r14 + r12 + 11], 3 + QUAD $0x0b2e5c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r14 + r13 + 11], 4 + QUAD $0x0b165c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r14 + rdx + 11], 5 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 + QUAD $0x0b3e5c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r15 + 11], 6 + QUAD $0x0b165c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r14 + r10 + 11], 7 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0b165c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r10 + 11], 8 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x0b2e5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r13 + 11], 9 + QUAD $0x0b3e5c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r14 + rdi + 11], 10 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x0b3e5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r14 + r15 + 11], 11 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x0b265c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r12 + 11], 12 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0b065c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rax + 11], 13 + LONG $0x244c8b4c; BYTE $0x10 // mov r9, qword [rsp + 16] + QUAD $0x0b0e5c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r9 + 11], 14 + QUAD $0x0b1e5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r11 + 11], 15 + QUAD $0x0c066c203a0f4766; BYTE $0x01 // pinsrb xmm13, byte [r14 + r8 + 12], 1 + QUAD $0x0c1e6c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rbx + 12], 2 + QUAD $0x0c366c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r14 + rsi + 12], 3 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0c1e6c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r14 + rbx + 12], 4 + QUAD $0x0c166c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r14 + rdx + 12], 5 + QUAD $0x0c0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 12], 6 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0c1e6c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r14 + rbx + 12], 7 + QUAD $0x0c166c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r10 + 12], 8 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x0c2e6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r13 + 12], 9 + QUAD $0x0c3e6c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r14 + rdi + 12], 10 + QUAD $0x0c3e6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r14 + r15 + 12], 11 + QUAD $0x0c266c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r12 + 12], 12 + QUAD $0x0c066c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rax + 12], 13 + QUAD $0x0c0e6c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r14 + r9 + 12], 14 + QUAD $0x0c1e6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r14 + r11 + 12], 15 + QUAD $0x0d0664203a0f4766; BYTE $0x01 // pinsrb xmm12, byte [r14 + r8 + 13], 1 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0d2e64203a0f4766; BYTE $0x02 // pinsrb xmm12, byte [r14 + r13 + 13], 2 + QUAD $0x0d3664203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rsi + 13], 3 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0d3664203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r14 + rsi + 13], 4 + QUAD $0x0d1664203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r14 + rdx + 13], 5 + QUAD $0x0d0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 13], 6 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0d1664203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r14 + rdx + 13], 7 + WORD $0x894d; BYTE $0xd5 // mov r13, r10 + QUAD $0x0d1664203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r10 + 13], 8 + QUAD $0x0d1e64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r14 + rbx + 13], 9 + QUAD $0x0d3e64203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r14 + rdi + 13], 10 + QUAD $0x0d3e64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r14 + r15 + 13], 11 + QUAD $0x0d2664203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r12 + 13], 12 + QUAD $0x0d0664203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rax + 13], 13 + QUAD $0x0d0e64203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r14 + r9 + 13], 14 + QUAD $0x0d1e64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r14 + r11 + 13], 15 + LONG $0x740f4566; BYTE $0xd9 // pcmpeqb xmm11, xmm9 + QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0x740f4566; BYTE $0xe9 // pcmpeqb xmm13, xmm9 + QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + LONG $0x74b60f41; WORD $0x1906 // movzx esi, byte [r14 + rax + 25] + LONG $0xce6e0f66 // movd xmm1, esi + LONG $0x740f4566; BYTE $0xe1 // pcmpeqb xmm12, xmm9 + QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI2_14] */ + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x74b60f41; WORD $0x1a06 // movzx esi, byte [r14 + rax + 26] + LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi + QUAD $0x00010024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 256] + QUAD $0x0e0664203a0f4366; BYTE $0x01 // pinsrb xmm4, byte [r14 + r8 + 14], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0e3664203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rsi + 14], 2 + QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] + QUAD $0x0e3e64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdi + 14], 3 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x0e1664203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r10 + 14], 4 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0e0664203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r14 + rax + 14], 5 + QUAD $0x0e0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 14], 6 + WORD $0x8949; BYTE $0xd0 // mov r8, rdx + QUAD $0x0e1664203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r14 + rdx + 14], 7 + WORD $0x894d; BYTE $0xe9 // mov r9, r13 + QUAD $0x0e2e64203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r13 + 14], 8 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + QUAD $0x0e1e64203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r14 + rbx + 14], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0e1e64203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r14 + rbx + 14], 10 + QUAD $0x0e3e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r15 + 14], 11 + QUAD $0x0e2664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r12 + 14], 12 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0e1664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 14], 13 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0e1664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rdx + 14], 14 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x0e2e64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r13 + 14], 15 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0f1674203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r14 + rdx + 15], 1 + QUAD $0x0f3674203a0f4566; BYTE $0x02 // pinsrb xmm14, byte [r14 + rsi + 15], 2 + QUAD $0x0f3e74203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r14 + rdi + 15], 3 + QUAD $0x0f1674203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r14 + r10 + 15], 4 + QUAD $0x0f0674203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r14 + rax + 15], 5 + QUAD $0x0f0e74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r14 + rcx + 15], 6 + QUAD $0x0f0674203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r14 + r8 + 15], 7 + QUAD $0x0f0e74203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r14 + r9 + 15], 8 + QUAD $0x0f1e74203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r14 + r11 + 15], 9 + QUAD $0x0f1e74203a0f4566; BYTE $0x0a // pinsrb xmm14, byte [r14 + rbx + 15], 10 + QUAD $0x0f3e74203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r14 + r15 + 15], 11 + QUAD $0x0f2674203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r14 + r12 + 15], 12 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0f1674203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r14 + rdx + 15], 13 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0f1674203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r14 + rdx + 15], 14 + QUAD $0x0f2e74203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r14 + r13 + 15], 15 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x102e7c203a0f4766; BYTE $0x01 // pinsrb xmm15, byte [r14 + r13 + 16], 1 + QUAD $0x10367c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r14 + rsi + 16], 2 + QUAD $0x103e7c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r14 + rdi + 16], 3 + QUAD $0x10167c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r14 + r10 + 16], 4 + QUAD $0x10067c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r14 + rax + 16], 5 + QUAD $0x100e7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r14 + rcx + 16], 6 + QUAD $0x10067c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r14 + r8 + 16], 7 + QUAD $0x100e7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r9 + 16], 8 + QUAD $0x101e7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r14 + r11 + 16], 9 + QUAD $0x101e7c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r14 + rbx + 16], 10 + QUAD $0x103e7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r14 + r15 + 16], 11 + QUAD $0x10267c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r14 + r12 + 16], 12 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x10167c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r14 + rdx + 16], 13 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x10167c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r14 + rdx + 16], 14 + QUAD $0x112e44203a0f4366; BYTE $0x01 // pinsrb xmm0, byte [r14 + r13 + 17], 1 + QUAD $0x113644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rsi + 17], 2 + QUAD $0x113e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdi + 17], 3 + QUAD $0x111644203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r10 + 17], 4 + QUAD $0x110644203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rax + 17], 5 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x110e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 17], 6 + QUAD $0x110644203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r8 + 17], 7 + QUAD $0x110e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r9 + 17], 8 + QUAD $0x111e44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r11 + 17], 9 + QUAD $0x111e44203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rbx + 17], 10 + QUAD $0x113e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r15 + 17], 11 + QUAD $0x112644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r12 + 17], 12 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x111644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rdx + 17], 13 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x113644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rsi + 17], 14 + QUAD $0x00a024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 160] + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + LONG $0x74b60f41; WORD $0x1b1e // movzx esi, byte [r14 + rbx + 27] + LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi + QUAD $0x00b024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xe5 // pcmpeqb xmm4, xmm13 + QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI2_15] */ + LONG $0x740f4566; BYTE $0xf5 // pcmpeqb xmm14, xmm13 + LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 + LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI2_6] */ + LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 + LONG $0x74b60f41; WORD $0x1c1e // movzx esi, byte [r14 + rbx + 28] + LONG $0xe66e0f66 // movd xmm4, esi + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x110644203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rax + 17], 15 + LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 + LONG $0x740f4166; BYTE $0xc5 // pcmpeqb xmm0, xmm13 + LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 + QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI2_10] */ + LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 + LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 + QUAD $0x00a024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm13 + LONG $0x74b60f41; WORD $0x1d1e // movzx esi, byte [r14 + rbx + 29] + LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x10067c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r14 + rax + 16], 15 + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x12366c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rsi + 18], 1 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x12366c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rsi + 18], 2 + QUAD $0x123e6c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r14 + rdi + 18], 3 + QUAD $0x12166c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r14 + r10 + 18], 4 + QUAD $0x122e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r13 + 18], 5 + QUAD $0x120e6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r14 + rcx + 18], 6 + QUAD $0x12066c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r8 + 18], 7 + QUAD $0x120e6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r9 + 18], 8 + QUAD $0x121e6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r11 + 18], 9 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x12066c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r14 + rax + 18], 10 + QUAD $0x123e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r15 + 18], 11 + QUAD $0x12266c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r14 + r12 + 18], 12 + QUAD $0x12166c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rdx + 18], 13 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x12166c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rdx + 18], 14 + LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 + QUAD $0x121e6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r14 + rbx + 18], 15 + LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 + QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + LONG $0x74b60f41; WORD $0x1e16 // movzx esi, byte [r14 + rdx + 30] + LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x13367c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rsi + 19], 1 + QUAD $0x143674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rsi + 20], 1 + QUAD $0x153654203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rsi + 21], 1 + QUAD $0x16365c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rsi + 22], 1 + QUAD $0x173644203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rsi + 23], 1 + QUAD $0x183654203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rsi + 24], 1 + QUAD $0x19364c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rsi + 25], 1 + QUAD $0x1a365c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rsi + 26], 1 + QUAD $0x1b364c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rsi + 27], 1 + QUAD $0x1c3664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rsi + 28], 1 + QUAD $0x1d366c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rsi + 29], 1 + QUAD $0x1e3664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rsi + 30], 1 + LONG $0x54b60f41; WORD $0x1f16 // movzx edx, byte [r14 + rdx + 31] + LONG $0xc26e0f66 // movd xmm0, edx + QUAD $0x1f3644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rsi + 31], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x13167c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rdx + 19], 2 + QUAD $0x141674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rdx + 20], 2 + QUAD $0x151654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rdx + 21], 2 + QUAD $0x16165c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rdx + 22], 2 + QUAD $0x171644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rdx + 23], 2 + QUAD $0x181654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rdx + 24], 2 + QUAD $0x19164c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rdx + 25], 2 + QUAD $0x1a165c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rdx + 26], 2 + QUAD $0x1b164c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rdx + 27], 2 + QUAD $0x1c1664203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rdx + 28], 2 + QUAD $0x1d166c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rdx + 29], 2 + QUAD $0x1e1664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rdx + 30], 2 + QUAD $0x1f1644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rdx + 31], 2 + QUAD $0x133e7c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r14 + rdi + 19], 3 + QUAD $0x13167c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r14 + r10 + 19], 4 + QUAD $0x132e7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r13 + 19], 5 + QUAD $0x130e7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r14 + rcx + 19], 6 + QUAD $0x13067c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r14 + r8 + 19], 7 + QUAD $0x130e7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r9 + 19], 8 + QUAD $0x131e7c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r11 + 19], 9 + QUAD $0x13067c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r14 + rax + 19], 10 + QUAD $0x133e7c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r14 + r15 + 19], 11 + QUAD $0x13267c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r14 + r12 + 19], 12 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x13167c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rdx + 19], 13 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x13367c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r14 + rsi + 19], 14 + QUAD $0x131e7c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r14 + rbx + 19], 15 + QUAD $0x143e74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rdi + 20], 3 + QUAD $0x141674203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r14 + r10 + 20], 4 + QUAD $0x142e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r13 + 20], 5 + QUAD $0x140e74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rcx + 20], 6 + QUAD $0x140674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r8 + 20], 7 + QUAD $0x140e74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r9 + 20], 8 + QUAD $0x141e74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r11 + 20], 9 + QUAD $0x140674203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r14 + rax + 20], 10 + QUAD $0x143e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r15 + 20], 11 + QUAD $0x142674203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r12 + 20], 12 + QUAD $0x141674203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r14 + rdx + 20], 13 + QUAD $0x143674203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rsi + 20], 14 + QUAD $0x0000a024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 160] + QUAD $0x141e74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rbx + 20], 15 + QUAD $0x00b024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 + QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0x740f4166; BYTE $0xf7 // pcmpeqb xmm6, xmm15 + QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xf7eb0f66 // por xmm6, xmm7 + QUAD $0x153e54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdi + 21], 3 + QUAD $0x151654203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r14 + r10 + 21], 4 + QUAD $0x152e54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r13 + 21], 5 + QUAD $0x150e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 21], 6 + QUAD $0x150654203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r8 + 21], 7 + QUAD $0x150e54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r9 + 21], 8 + QUAD $0x151e54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r11 + 21], 9 + QUAD $0x150654203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r14 + rax + 21], 10 + QUAD $0x153e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 21], 11 + QUAD $0x152654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 21], 12 + QUAD $0x151654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rdx + 21], 13 + QUAD $0x153654203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rsi + 21], 14 + QUAD $0x151e54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rbx + 21], 15 + LONG $0x740f4166; BYTE $0xd7 // pcmpeqb xmm2, xmm15 + QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI2_14] */ + LONG $0xd7db0f66 // pand xmm2, xmm7 + LONG $0xd6eb0f66 // por xmm2, xmm6 + LONG $0xd5eb0f66 // por xmm2, xmm5 + QUAD $0x163e5c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r14 + rdi + 22], 3 + QUAD $0x16165c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r14 + r10 + 22], 4 + QUAD $0x162e5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r13 + 22], 5 + QUAD $0x160e5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r14 + rcx + 22], 6 + QUAD $0x16065c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r8 + 22], 7 + QUAD $0x160e5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r9 + 22], 8 + QUAD $0x161e5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r11 + 22], 9 + QUAD $0x16065c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r14 + rax + 22], 10 + QUAD $0x163e5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r14 + r15 + 22], 11 + QUAD $0x16265c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r12 + 22], 12 + QUAD $0x16165c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rdx + 22], 13 + QUAD $0x16365c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r14 + rsi + 22], 14 + QUAD $0x161e5c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r14 + rbx + 22], 15 + QUAD $0x173e44203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rdi + 23], 3 + QUAD $0x171644203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r14 + r10 + 23], 4 + QUAD $0x172e44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r13 + 23], 5 + QUAD $0x170e44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r14 + rcx + 23], 6 + QUAD $0x170644203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r8 + 23], 7 + QUAD $0x170e44203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r9 + 23], 8 + QUAD $0x171e44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r11 + 23], 9 + QUAD $0x170644203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rax + 23], 10 + QUAD $0x173e44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r14 + r15 + 23], 11 + QUAD $0x172644203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r14 + r12 + 23], 12 + QUAD $0x171644203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rdx + 23], 13 + QUAD $0x173644203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rsi + 23], 14 + QUAD $0x171e44203a0f4566; BYTE $0x0f // pinsrb xmm8, byte [r14 + rbx + 23], 15 + LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 + QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI2_15] */ + LONG $0xdddb0f66 // pand xmm3, xmm5 + LONG $0x740f4566; BYTE $0xc7 // pcmpeqb xmm8, xmm15 + LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 + LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI2_6] */ + LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 + LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 + QUAD $0x193e4c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r14 + rdi + 25], 3 + QUAD $0x19164c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r14 + r10 + 25], 4 + QUAD $0x192e4c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r14 + r13 + 25], 5 + QUAD $0x190e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 25], 6 + QUAD $0x19064c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r14 + r8 + 25], 7 + QUAD $0x190e4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r9 + 25], 8 + QUAD $0x191e4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r11 + 25], 9 + QUAD $0x19064c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r14 + rax + 25], 10 + QUAD $0x193e4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r14 + r15 + 25], 11 + QUAD $0x19264c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r12 + 25], 12 + QUAD $0x19164c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r14 + rdx + 25], 13 + QUAD $0x19364c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r14 + rsi + 25], 14 + QUAD $0x191e4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rbx + 25], 15 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + LONG $0x740f4166; BYTE $0xcf // pcmpeqb xmm1, xmm15 + LONG $0xd16f0f66 // movdqa xmm2, xmm1 + QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI2_10] */ + LONG $0xd3db0f66 // pand xmm2, xmm3 + LONG $0xd1f80f66 // psubb xmm2, xmm1 + QUAD $0x183e54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rdi + 24], 3 + QUAD $0x181654203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r10 + 24], 4 + QUAD $0x182e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r13 + 24], 5 + QUAD $0x180e54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r14 + rcx + 24], 6 + QUAD $0x180654203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r14 + r8 + 24], 7 + QUAD $0x180e54203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r14 + r9 + 24], 8 + QUAD $0x181e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r11 + 24], 9 + QUAD $0x180654203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r14 + rax + 24], 10 + QUAD $0x183e54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r15 + 24], 11 + QUAD $0x182654203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r12 + 24], 12 + QUAD $0x181654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rdx + 24], 13 + QUAD $0x183654203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rsi + 24], 14 + QUAD $0x181e54203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rbx + 24], 15 + LONG $0x740f4566; BYTE $0xd7 // pcmpeqb xmm10, xmm15 + LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 + QUAD $0x1a3e5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r14 + rdi + 26], 3 + QUAD $0x1a165c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r14 + r10 + 26], 4 + QUAD $0x1a2e5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r13 + 26], 5 + QUAD $0x1a0e5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r14 + rcx + 26], 6 + QUAD $0x1a065c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r14 + r8 + 26], 7 + QUAD $0x1a0e5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r9 + 26], 8 + QUAD $0x1a1e5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r11 + 26], 9 + QUAD $0x1a065c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r14 + rax + 26], 10 + QUAD $0x1a3e5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r14 + r15 + 26], 11 + QUAD $0x1a265c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r12 + 26], 12 + QUAD $0x1a165c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rdx + 26], 13 + QUAD $0x1a365c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r14 + rsi + 26], 14 + QUAD $0x1a1e5c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r14 + rbx + 26], 15 + LONG $0x740f4566; BYTE $0xdf // pcmpeqb xmm11, xmm15 + QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI2_11] */ + LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 + LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 + QUAD $0x1b3e4c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r14 + rdi + 27], 3 + QUAD $0x1b164c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r14 + r10 + 27], 4 + QUAD $0x1b2e4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r13 + 27], 5 + QUAD $0x1b0e4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r14 + rcx + 27], 6 + QUAD $0x1b064c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r8 + 27], 7 + QUAD $0x1b0e4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r9 + 27], 8 + QUAD $0x1b1e4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r14 + r11 + 27], 9 + QUAD $0x1b064c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r14 + rax + 27], 10 + QUAD $0x1b3e4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r14 + r15 + 27], 11 + QUAD $0x1b264c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r14 + r12 + 27], 12 + QUAD $0x1b164c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r14 + rdx + 27], 13 + QUAD $0x1b364c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rsi + 27], 14 + QUAD $0x1b1e4c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r14 + rbx + 27], 15 + QUAD $0x1c3e64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdi + 28], 3 + QUAD $0x1c1664203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r10 + 28], 4 + QUAD $0x1c2e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r13 + 28], 5 + QUAD $0x1c0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 28], 6 + QUAD $0x1c0664203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r8 + 28], 7 + QUAD $0x1c0e64203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r9 + 28], 8 + QUAD $0x1c1e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r11 + 28], 9 + QUAD $0x1c0664203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r14 + rax + 28], 10 + QUAD $0x1c3e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r15 + 28], 11 + QUAD $0x1c2664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r12 + 28], 12 + QUAD $0x1c1664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rdx + 28], 13 + QUAD $0x1c3664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rsi + 28], 14 + QUAD $0x1c1e64203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r14 + rbx + 28], 15 + QUAD $0x1d3e6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r14 + rdi + 29], 3 + QUAD $0x1d166c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r14 + r10 + 29], 4 + QUAD $0x1d2e6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r14 + r13 + 29], 5 + QUAD $0x1d0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 29], 6 + QUAD $0x1d066c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r14 + r8 + 29], 7 + QUAD $0x1d0e6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r9 + 29], 8 + QUAD $0x1d1e6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r11 + 29], 9 + QUAD $0x1d066c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r14 + rax + 29], 10 + QUAD $0x1d3e6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r14 + r15 + 29], 11 + QUAD $0x1d266c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r12 + 29], 12 + QUAD $0x1d166c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rdx + 29], 13 + QUAD $0x1d366c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r14 + rsi + 29], 14 + LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 + LONG $0x740f4566; BYTE $0xcf // pcmpeqb xmm9, xmm15 + QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI2_12] */ + LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 + QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI2_13] */ + LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 + QUAD $0x1d1e6c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r14 + rbx + 29], 15 + LONG $0x740f4566; BYTE $0xef // pcmpeqb xmm13, xmm15 + LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 + LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 + QUAD $0x1e3e64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rdi + 30], 3 + QUAD $0x1f3e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdi + 31], 3 + QUAD $0x1e1664203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r14 + r10 + 30], 4 + QUAD $0x1f1644203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r10 + 31], 4 + QUAD $0x1e2e64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r14 + r13 + 30], 5 + QUAD $0x1f2e44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r13 + 31], 5 + QUAD $0x1e0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 30], 6 + QUAD $0x1f0e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 31], 6 + QUAD $0x1e0664203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r14 + r8 + 30], 7 + QUAD $0x1f0644203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r8 + 31], 7 + QUAD $0x1e0e64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r9 + 30], 8 + QUAD $0x1f0e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r9 + 31], 8 + QUAD $0x1e1e64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r11 + 30], 9 + QUAD $0x1f1e44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r11 + 31], 9 + QUAD $0x1e0664203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r14 + rax + 30], 10 + QUAD $0x1f0644203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rax + 31], 10 + QUAD $0x1e3e64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r14 + r15 + 30], 11 + QUAD $0x1f3e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r15 + 31], 11 + QUAD $0x1e2664203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r12 + 30], 12 + QUAD $0x1f2644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r12 + 31], 12 + QUAD $0x1e1664203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rdx + 30], 13 + QUAD $0x1f1644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rdx + 31], 13 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x1e3664203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r14 + rsi + 30], 14 + QUAD $0x1f3644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rsi + 31], 14 + QUAD $0x1e1e64203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r14 + rbx + 30], 15 + QUAD $0x1f1e44203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rbx + 31], 15 + LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 + LONG $0x740f4566; BYTE $0xe7 // pcmpeqb xmm12, xmm15 + LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 + LONG $0x740f4166; BYTE $0xc7 // pcmpeqb xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0xc6db0f66 // pand xmm0, xmm6 + LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 + LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 + LONG $0xc8600f66 // punpcklbw xmm1, xmm0 + QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] + LONG $0xd46f0f66 // movdqa xmm2, xmm4 + LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 + LONG $0xda6f0f66 // movdqa xmm3, xmm2 + LONG $0xd9610f66 // punpcklwd xmm3, xmm1 + LONG $0xd1690f66 // punpckhwd xmm2, xmm1 + LONG $0x680f4466; BYTE $0xc0 // punpckhbw xmm8, xmm0 + LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x647f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm4 + LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 + LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 + LONG $0x1c7f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm3 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000d8248c3b48 // cmp rcx, qword [rsp + 216] + JNE LBB2_218 + QUAD $0x000000f8248c8b48 // mov rcx, qword [rsp + 248] + QUAD $0x000000d8248c3b48 // cmp rcx, qword [rsp + 216] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x241c8a44 // mov r11b, byte [rsp] + QUAD $0x0000012024b48b48 // mov rsi, qword [rsp + 288] + JNE LBB2_168 + JMP LBB2_172 TEXT ·_comparison_not_equal_arr_arr_sse4(SB), $80-48 @@ -15708,96 +16110,110 @@ TEXT ·_comparison_not_equal_arr_arr_sse4(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x8944; BYTE $0xc8 // mov eax, r9d - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB3_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB3_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB3_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB3_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB3_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_22 - WORD $0x9848 // cdqe - -LBB3_20: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_20 - LONG $0x01c48349 // add r12, 1 - -LBB3_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_26 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB3_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB3_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB3_24: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_26: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_28: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_32 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_30: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5950f41 // setne r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3950f41 // setne r11b @@ -15806,21 +16222,21 @@ LBB3_24: LONG $0xd7950f41 // setne r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2950f41 // setne r10b @@ -15831,143 +16247,143 @@ LBB3_24: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4950f41 // setne r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1950f41 // setne r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_24 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_30 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_28: +LBB3_34: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -15975,107 +16391,123 @@ LBB3_28: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_28 - JMP LBB3_123 - -LBB3_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB3_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB3_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB3_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_50 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB3_48: - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xcb08 // or bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB3_48 - LONG $0x01c48349 // add r12, 1 - -LBB3_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_54 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_34 + JMP LBB3_153 + +LBB3_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB3_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB3_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB3_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB3_52: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_58: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x100f42f2; WORD $0xf604 // movsd xmm0, qword [rsi + 8*r14] + LONG $0x2e0f4266; WORD $0xf204 // ucomisd xmm0, qword [rdx + 8*r14] + LONG $0xd29a0f41 // setp r10b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0x0844; BYTE $0xd3 // or bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xf8c38349 // add r11, -8 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB3_58 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB3_60: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_62: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_66 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_64: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x06100ff2 // movsd xmm0, qword [rsi] LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] LONG $0x46100ff2; BYTE $0x08 // movsd xmm0, qword [rsi + 8] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x46100ff2; BYTE $0x10 // movsd xmm0, qword [rsi + 16] LONG $0x422e0f66; BYTE $0x10 // ucomisd xmm0, qword [rdx + 16] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x46100ff2; BYTE $0x18 // movsd xmm0, qword [rsi + 24] LONG $0x422e0f66; BYTE $0x18 // ucomisd xmm0, qword [rdx + 24] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x46100ff2; BYTE $0x20 // movsd xmm0, qword [rsi + 32] LONG $0x422e0f66; BYTE $0x20 // ucomisd xmm0, qword [rdx + 32] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x46100ff2; BYTE $0x28 // movsd xmm0, qword [rsi + 40] LONG $0x422e0f66; BYTE $0x28 // ucomisd xmm0, qword [rdx + 40] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -16091,13 +16523,13 @@ LBB3_52: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x46100ff2; BYTE $0x40 // movsd xmm0, qword [rsi + 64] LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x46100ff2; BYTE $0x48 // movsd xmm0, qword [rsi + 72] LONG $0x422e0f66; BYTE $0x48 // ucomisd xmm0, qword [rdx + 72] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -16108,117 +16540,116 @@ LBB3_52: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x46100ff2; BYTE $0x58 // movsd xmm0, qword [rsi + 88] LONG $0x422e0f66; BYTE $0x58 // ucomisd xmm0, qword [rdx + 88] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x46100ff2; BYTE $0x60 // movsd xmm0, qword [rsi + 96] LONG $0x422e0f66; BYTE $0x60 // ucomisd xmm0, qword [rdx + 96] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x46100ff2; BYTE $0x68 // movsd xmm0, qword [rsi + 104] LONG $0x422e0f66; BYTE $0x68 // ucomisd xmm0, qword [rdx + 104] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x46100ff2; BYTE $0x70 // movsd xmm0, qword [rsi + 112] LONG $0x422e0f66; BYTE $0x70 // ucomisd xmm0, qword [rdx + 112] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x46100ff2; BYTE $0x78 // movsd xmm0, qword [rsi + 120] LONG $0x422e0f66; BYTE $0x78 // ucomisd xmm0, qword [rdx + 120] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl QUAD $0x0000008086100ff2 // movsd xmm0, qword [rsi + 128] QUAD $0x00000080822e0f66 // ucomisd xmm0, qword [rdx + 128] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl QUAD $0x0000008886100ff2 // movsd xmm0, qword [rsi + 136] QUAD $0x00000088822e0f66 // ucomisd xmm0, qword [rdx + 136] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl QUAD $0x0000009086100ff2 // movsd xmm0, qword [rsi + 144] QUAD $0x00000090822e0f66 // ucomisd xmm0, qword [rdx + 144] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl QUAD $0x0000009886100ff2 // movsd xmm0, qword [rsi + 152] QUAD $0x00000098822e0f66 // ucomisd xmm0, qword [rdx + 152] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al QUAD $0x000000a086100ff2 // movsd xmm0, qword [rsi + 160] QUAD $0x000000a0822e0f66 // ucomisd xmm0, qword [rdx + 160] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl QUAD $0x000000a886100ff2 // movsd xmm0, qword [rsi + 168] QUAD $0x000000a8822e0f66 // ucomisd xmm0, qword [rdx + 168] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl QUAD $0x000000b086100ff2 // movsd xmm0, qword [rsi + 176] QUAD $0x000000b0822e0f66 // ucomisd xmm0, qword [rdx + 176] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl QUAD $0x000000b886100ff2 // movsd xmm0, qword [rsi + 184] QUAD $0x000000b8822e0f66 // ucomisd xmm0, qword [rdx + 184] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al QUAD $0x000000c086100ff2 // movsd xmm0, qword [rsi + 192] QUAD $0x000000c0822e0f66 // ucomisd xmm0, qword [rdx + 192] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl QUAD $0x000000c886100ff2 // movsd xmm0, qword [rsi + 200] QUAD $0x000000c8822e0f66 // ucomisd xmm0, qword [rdx + 200] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al QUAD $0x000000d086100ff2 // movsd xmm0, qword [rsi + 208] QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0xd6950f41 // setne r14b + WORD $0x0841; BYTE $0xc6 // or r14b, al QUAD $0x000000d886100ff2 // movsd xmm0, qword [rsi + 216] QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al QUAD $0x000000e086100ff2 // movsd xmm0, qword [rsi + 224] QUAD $0x000000e0822e0f66 // ucomisd xmm0, qword [rdx + 224] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl QUAD $0x000000e886100ff2 // movsd xmm0, qword [rsi + 232] QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl QUAD $0x000000f086100ff2 // movsd xmm0, qword [rsi + 240] QUAD $0x000000f0822e0f66 // ucomisd xmm0, qword [rdx + 240] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -16230,109 +16661,107 @@ LBB3_52: WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd0950f41 // setne r8b WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0841; BYTE $0xce // or r14b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xf3 // or bl, r14b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x74b60f44; WORD $0x0324 // movzx r14d, byte [rsp + 3] - WORD $0x0845; BYTE $0xee // or r14b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xda // or r10b, bl + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xd1 // or cl, r10b - LONG $0x24348845 // mov byte [r12], r14b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB3_52 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_64 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_56: +LBB3_68: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x04100ff2; BYTE $0xce // movsd xmm0, qword [rsi + 8*rcx] LONG $0x042e0f66; BYTE $0xca // ucomisd xmm0, qword [rdx + 8*rcx] @@ -16342,98 +16771,122 @@ LBB3_56: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB3_56 - JMP LBB3_123 + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB3_68 + JMP LBB3_153 LBB3_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB3_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_8 - WORD $0x9848 // cdqe - -LBB3_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xfd // mov r13, r15 + JE LBB3_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB3_9 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB3_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4950f41 // setne r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_6 - LONG $0x01c48349 // add r12, 1 - -LBB3_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_12 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB3_10: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB3_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + +LBB3_9: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_11: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_15 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB3_13: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7950f41 // setne r15b + LONG $0xd6950f41 // setne r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7950f40 // setne dil @@ -16445,19 +16898,19 @@ LBB3_10: LONG $0xd3950f41 // setne r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6950f41 // setne r14b + LONG $0xd7950f41 // setne r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0950f41 // setne r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4950f41 // setne r12b @@ -16466,147 +16919,146 @@ LBB3_10: LONG $0xd5950f41 // setne r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1950f41 // setne r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB3_10 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB3_13 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] -LBB3_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_14: +LBB3_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -16614,101 +17066,117 @@ LBB3_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_14 - JMP LBB3_123 - -LBB3_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB3_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB3_123 - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_36 - WORD $0x9848 // cdqe - -LBB3_34: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_34 - LONG $0x01c48349 // add r12, 1 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_17 + JMP LBB3_153 LBB3_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_40 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB3_38: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB3_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB3_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB3_41: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_43: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_45: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_49 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_47: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5950f41 // setne r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3950f41 // setne r11b @@ -16717,21 +17185,21 @@ LBB3_38: LONG $0xd7950f41 // setne r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2950f41 // setne r10b @@ -16742,143 +17210,143 @@ LBB3_38: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4950f41 // setne r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1950f41 // setne r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_38 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_47 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_42: +LBB3_51: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -16886,97 +17354,113 @@ LBB3_42: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_42 - JMP LBB3_123 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_51 + JMP LBB3_153 -LBB3_68: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_72 - WORD $0x9848 // cdqe - -LBB3_70: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_70 - LONG $0x01c48349 // add r12, 1 +LBB3_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB3_86: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB3_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_76 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB3_88: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 -LBB3_74: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_90: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_94 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_92: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5950f41 // setne r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3950f41 // setne r11b @@ -16985,21 +17469,21 @@ LBB3_74: LONG $0xd7950f41 // setne r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2950f41 // setne r10b @@ -17010,143 +17494,143 @@ LBB3_74: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4950f41 // setne r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1950f41 // setne r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_74 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_92 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_78: +LBB3_96: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -17154,97 +17638,113 @@ LBB3_78: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xe180; BYTE $0x07 // and cl, 7 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_78 - JMP LBB3_123 - -LBB3_79: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_83 - WORD $0x9848 // cdqe - -LBB3_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_81 - LONG $0x01c48349 // add r12, 1 - -LBB3_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_87 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xe180; BYTE $0x07 // and cl, 7 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3f048841 // mov byte [r15 + rdi], al + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_96 + JMP LBB3_153 + +LBB3_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB3_85: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_102: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_104: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_108 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_106: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0646b70f // movzx eax, word [rsi + 6] LONG $0x06423b66 // cmp ax, word [rdx + 6] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0846b70f // movzx eax, word [rsi + 8] LONG $0x08423b66 // cmp ax, word [rdx + 8] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0a46b70f // movzx eax, word [rsi + 10] LONG $0x0a423b66 // cmp ax, word [rdx + 10] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0c46b70f // movzx eax, word [rsi + 12] LONG $0x0c423b66 // cmp ax, word [rdx + 12] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd5950f41 // setne r13b LONG $0x1046b70f // movzx eax, word [rsi + 16] LONG $0x10423b66 // cmp ax, word [rdx + 16] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3950f41 // setne r11b @@ -17253,21 +17753,21 @@ LBB3_85: LONG $0xd7950f41 // setne r15b LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x1c46b70f // movzx eax, word [rsi + 28] LONG $0x1c423b66 // cmp ax, word [rdx + 28] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x1e46b70f // movzx eax, word [rsi + 30] LONG $0x1e423b66 // cmp ax, word [rdx + 30] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x2046b70f // movzx eax, word [rsi + 32] LONG $0x225eb70f // movzx ebx, word [rsi + 34] LONG $0x20423b66 // cmp ax, word [rdx + 32] LONG $0x2446b70f // movzx eax, word [rsi + 36] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x225a3b66 // cmp bx, word [rdx + 34] LONG $0x265eb70f // movzx ebx, word [rsi + 38] LONG $0xd2950f41 // setne r10b @@ -17278,143 +17778,143 @@ LBB3_85: LONG $0x2a5eb70f // movzx ebx, word [rsi + 42] LONG $0xd4950f41 // setne r12b LONG $0x28423b66 // cmp ax, word [rdx + 40] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x2a5a3b66 // cmp bx, word [rdx + 42] LONG $0x2c46b70f // movzx eax, word [rsi + 44] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1950f41 // setne r9b LONG $0x30423b66 // cmp ax, word [rdx + 48] LONG $0x3246b70f // movzx eax, word [rsi + 50] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x38423b66 // cmp ax, word [rdx + 56] LONG $0x3a46b70f // movzx eax, word [rsi + 58] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x3a423b66 // cmp ax, word [rdx + 58] LONG $0x3c46b70f // movzx eax, word [rsi + 60] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x3c423b66 // cmp ax, word [rdx + 60] LONG $0x3e46b70f // movzx eax, word [rsi + 62] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x40c28348 // add rdx, 64 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_85 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB3_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_106 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB3_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_89: +LBB3_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -17422,97 +17922,113 @@ LBB3_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_89 - JMP LBB3_123 - -LBB3_101: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_105 - WORD $0x9848 // cdqe - -LBB3_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_103 - LONG $0x01c48349 // add r12, 1 - -LBB3_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_109 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB3_107: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_110 + JMP LBB3_153 + +LBB3_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB3_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB3_130: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_132: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_136 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_134: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x18468b48 // mov rax, qword [rsi + 24] LONG $0x18423b48 // cmp rax, qword [rdx + 24] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x20468b48 // mov rax, qword [rsi + 32] LONG $0x20423b48 // cmp rax, qword [rdx + 32] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x28468b48 // mov rax, qword [rsi + 40] LONG $0x28423b48 // cmp rax, qword [rdx + 40] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x30468b48 // mov rax, qword [rsi + 48] LONG $0x30423b48 // cmp rax, qword [rdx + 48] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0xd5950f41 // setne r13b LONG $0x40468b48 // mov rax, qword [rsi + 64] LONG $0x40423b48 // cmp rax, qword [rdx + 64] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3950f41 // setne r11b @@ -17521,21 +18037,21 @@ LBB3_107: LONG $0xd7950f41 // setne r15b LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x70468b48 // mov rax, qword [rsi + 112] LONG $0x70423b48 // cmp rax, qword [rdx + 112] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x78468b48 // mov rax, qword [rsi + 120] LONG $0x78423b48 // cmp rax, qword [rdx + 120] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x80868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 128] LONG $0x889e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 136] LONG $0x80823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 128] LONG $0x90868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 144] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x889a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 136] LONG $0x989e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 152] LONG $0xd2950f41 // setne r10b @@ -17546,143 +18062,143 @@ LBB3_107: LONG $0xa89e8b48; WORD $0x0000; BYTE $0x00 // mov rbx, qword [rsi + 168] LONG $0xd4950f41 // setne r12b LONG $0xa0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 160] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0xa89a3b48; WORD $0x0000; BYTE $0x00 // cmp rbx, qword [rdx + 168] LONG $0xb0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 176] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1950f41 // setne r9b LONG $0xc0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 192] LONG $0xc8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 200] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0xe0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 224] LONG $0xe8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 232] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0xe8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 232] LONG $0xf0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 240] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0xf0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 240] LONG $0xf8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 248] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_107 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_134 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_111: +LBB3_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -17690,99 +18206,115 @@ LBB3_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_111 - JMP LBB3_123 - -LBB3_112: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_116 - WORD $0x634c; BYTE $0xd0 // movsxd r10, eax - -LBB3_114: - LONG $0x06100ff3 // movss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xcb08 // or bl, cl - WORD $0xdbf6 // neg bl - LONG $0x077a8d49 // lea rdi, [r10 + 7] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f49 // cmovns rdi, r10 - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001b8; BYTE $0x00 // mov eax, 1 - WORD $0xe0d3 // shl eax, cl - WORD $0xd820 // and al, bl - WORD $0x3044; BYTE $0xc0 // xor al, r8b - LONG $0x3c048841 // mov byte [r12 + rdi], al - LONG $0x01c28349 // add r10, 1 - LONG $0x08fa8349 // cmp r10, 8 - JNE LBB3_114 - LONG $0x01c48349 // add r12, 1 - -LBB3_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_120 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_138 + JMP LBB3_153 + +LBB3_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB3_118: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_142: + LONG $0x310c8d4b // lea rcx, [r9 + r14] + LONG $0x100f42f3; WORD $0xb604 // movss xmm0, dword [rsi + 4*r14] + LONG $0x042e0f42; BYTE $0xb2 // ucomiss xmm0, dword [rdx + 4*r14] + LONG $0xd29a0f41 // setp r10b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0x0844; BYTE $0xd3 // or bl, r10b + WORD $0xdbf6 // neg bl + LONG $0x313c8d4b // lea rdi, [r9 + r14] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd048d; WORD $0x0000; BYTE $0x00 // lea eax, [8*rdi] + WORD $0xc129 // sub ecx, eax + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0xcb30 // xor bl, cl + WORD $0xd820 // and al, bl + WORD $0xc830 // xor al, cl + LONG $0x3f048841 // mov byte [r15 + rdi], al + LONG $0x01c68349 // add r14, 1 + LONG $0xfcc38349 // add r11, -4 + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + JNE LBB3_142 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + +LBB3_144: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 + +LBB3_146: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_150 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_148: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 LONG $0x06100ff3 // movss xmm0, dword [rsi] WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] LONG $0x46100ff3; BYTE $0x04 // movss xmm0, dword [rsi + 4] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x15244c88 // mov byte [rsp + 21], cl + LONG $0x1d244c88 // mov byte [rsp + 29], cl LONG $0x04422e0f // ucomiss xmm0, dword [rdx + 4] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0d244c88 // mov byte [rsp + 13], cl + LONG $0x16244c88 // mov byte [rsp + 22], cl LONG $0x46100ff3; BYTE $0x08 // movss xmm0, dword [rsi + 8] LONG $0x08422e0f // ucomiss xmm0, dword [rdx + 8] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x14244c88 // mov byte [rsp + 20], cl + LONG $0x1c244c88 // mov byte [rsp + 28], cl LONG $0x46100ff3; BYTE $0x0c // movss xmm0, dword [rsi + 12] LONG $0x0c422e0f // ucomiss xmm0, dword [rdx + 12] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x17244c88 // mov byte [rsp + 23], cl + LONG $0x1f244c88 // mov byte [rsp + 31], cl LONG $0x46100ff3; BYTE $0x10 // movss xmm0, dword [rsi + 16] LONG $0x10422e0f // ucomiss xmm0, dword [rdx + 16] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x16244c88 // mov byte [rsp + 22], cl + LONG $0x1e244c88 // mov byte [rsp + 30], cl LONG $0x46100ff3; BYTE $0x14 // movss xmm0, dword [rsi + 20] LONG $0x14422e0f // ucomiss xmm0, dword [rdx + 20] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -17798,13 +18330,13 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x03244c88 // mov byte [rsp + 3], cl + LONG $0x0c244c88 // mov byte [rsp + 12], cl LONG $0x46100ff3; BYTE $0x20 // movss xmm0, dword [rsi + 32] LONG $0x20422e0f // ucomiss xmm0, dword [rdx + 32] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x13244c88 // mov byte [rsp + 19], cl + LONG $0x1b244c88 // mov byte [rsp + 27], cl LONG $0x46100ff3; BYTE $0x24 // movss xmm0, dword [rsi + 36] LONG $0x24422e0f // ucomiss xmm0, dword [rdx + 36] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -17815,78 +18347,78 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x12244c88 // mov byte [rsp + 18], cl + LONG $0x1a244c88 // mov byte [rsp + 26], cl LONG $0x46100ff3; BYTE $0x2c // movss xmm0, dword [rsi + 44] LONG $0x2c422e0f // ucomiss xmm0, dword [rdx + 44] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x11244c88 // mov byte [rsp + 17], cl + LONG $0x19244c88 // mov byte [rsp + 25], cl LONG $0x46100ff3; BYTE $0x30 // movss xmm0, dword [rsi + 48] LONG $0x30422e0f // ucomiss xmm0, dword [rdx + 48] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0b244c88 // mov byte [rsp + 11], cl LONG $0x46100ff3; BYTE $0x34 // movss xmm0, dword [rsi + 52] LONG $0x34422e0f // ucomiss xmm0, dword [rdx + 52] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0f244c88 // mov byte [rsp + 15], cl + LONG $0x18244c88 // mov byte [rsp + 24], cl LONG $0x46100ff3; BYTE $0x38 // movss xmm0, dword [rsi + 56] LONG $0x38422e0f // ucomiss xmm0, dword [rdx + 56] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x15244c88 // mov byte [rsp + 21], cl LONG $0x46100ff3; BYTE $0x3c // movss xmm0, dword [rsi + 60] LONG $0x3c422e0f // ucomiss xmm0, dword [rdx + 60] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0b244c88 // mov byte [rsp + 11], cl + LONG $0x14244c88 // mov byte [rsp + 20], cl LONG $0x46100ff3; BYTE $0x40 // movss xmm0, dword [rsi + 64] LONG $0x40422e0f // ucomiss xmm0, dword [rdx + 64] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0e244c88 // mov byte [rsp + 14], cl + LONG $0x17244c88 // mov byte [rsp + 23], cl LONG $0x46100ff3; BYTE $0x44 // movss xmm0, dword [rsi + 68] LONG $0x44422e0f // ucomiss xmm0, dword [rdx + 68] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x0a244c88 // mov byte [rsp + 10], cl + LONG $0x13244c88 // mov byte [rsp + 19], cl LONG $0x46100ff3; BYTE $0x48 // movss xmm0, dword [rsi + 72] LONG $0x48422e0f // ucomiss xmm0, dword [rdx + 72] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x09244c88 // mov byte [rsp + 9], cl + LONG $0x12244c88 // mov byte [rsp + 18], cl LONG $0x46100ff3; BYTE $0x4c // movss xmm0, dword [rsi + 76] LONG $0x4c422e0f // ucomiss xmm0, dword [rdx + 76] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al LONG $0x46100ff3; BYTE $0x50 // movss xmm0, dword [rsi + 80] LONG $0x50422e0f // ucomiss xmm0, dword [rdx + 80] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x11244c88 // mov byte [rsp + 17], cl LONG $0x46100ff3; BYTE $0x54 // movss xmm0, dword [rsi + 84] LONG $0x54422e0f // ucomiss xmm0, dword [rdx + 84] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x07244c88 // mov byte [rsp + 7], cl + LONG $0x10244c88 // mov byte [rsp + 16], cl LONG $0x46100ff3; BYTE $0x58 // movss xmm0, dword [rsi + 88] LONG $0x58422e0f // ucomiss xmm0, dword [rdx + 88] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x05244c88 // mov byte [rsp + 5], cl + LONG $0x0e244c88 // mov byte [rsp + 14], cl LONG $0x46100ff3; BYTE $0x5c // movss xmm0, dword [rsi + 92] LONG $0x5c422e0f // ucomiss xmm0, dword [rdx + 92] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -17897,35 +18429,34 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x06244c88 // mov byte [rsp + 6], cl + LONG $0x0f244c88 // mov byte [rsp + 15], cl LONG $0x46100ff3; BYTE $0x64 // movss xmm0, dword [rsi + 100] LONG $0x64422e0f // ucomiss xmm0, dword [rdx + 100] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al LONG $0x46100ff3; BYTE $0x68 // movss xmm0, dword [rsi + 104] LONG $0x68422e0f // ucomiss xmm0, dword [rdx + 104] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0xd6950f41 // setne r14b + WORD $0x0841; BYTE $0xc6 // or r14b, al LONG $0x46100ff3; BYTE $0x6c // movss xmm0, dword [rsi + 108] LONG $0x6c422e0f // ucomiss xmm0, dword [rdx + 108] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x46100ff3; BYTE $0x70 // movss xmm0, dword [rsi + 112] LONG $0x70422e0f // ucomiss xmm0, dword [rdx + 112] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x04244c88 // mov byte [rsp + 4], cl + LONG $0x0d244c88 // mov byte [rsp + 13], cl LONG $0x46100ff3; BYTE $0x74 // movss xmm0, dword [rsi + 116] LONG $0x74422e0f // ucomiss xmm0, dword [rdx + 116] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x38244c88 // mov byte [rsp + 56], cl LONG $0x46100ff3; BYTE $0x78 // movss xmm0, dword [rsi + 120] LONG $0x78422e0f // ucomiss xmm0, dword [rdx + 120] WORD $0x9a0f; BYTE $0xd0 // setp al @@ -17937,109 +18468,107 @@ LBB3_118: WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd0950f41 // setne r8b WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x15244402 // add al, byte [rsp + 21] + LONG $0x1d244402 // add al, byte [rsp + 29] LONG $0x05e7c040 // shl dil, 5 LONG $0x06e5c041 // shl r13b, 6 WORD $0x0841; BYTE $0xfd // or r13b, dil WORD $0x8944; BYTE $0xef // mov edi, r13d - LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] + LONG $0x244cb60f; BYTE $0x1c // movzx ecx, byte [rsp + 28] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al WORD $0xd889 // mov eax, ebx WORD $0xd800 // add al, bl - LONG $0x13244402 // add al, byte [rsp + 19] + LONG $0x1b244402 // add al, byte [rsp + 27] WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x03 // movzx eax, byte [rsp + 3] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x03244488 // mov byte [rsp + 3], al - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] + LONG $0x2444b60f; BYTE $0x1f // movzx eax, byte [rsp + 31] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x19 // movzx ebx, byte [rsp + 25] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x6cb60f44; WORD $0x1624 // movzx r13d, byte [rsp + 22] + LONG $0x6cb60f44; WORD $0x1e24 // movzx r13d, byte [rsp + 30] LONG $0x04e5c041 // shl r13b, 4 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc789 // mov edi, eax - LONG $0x245cb60f; BYTE $0x0f // movzx ebx, byte [rsp + 15] + LONG $0x0b244488 // mov byte [rsp + 11], al + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x0a // movzx ebx, byte [rsp + 10] + LONG $0x247cb60f; BYTE $0x14 // movzx edi, byte [rsp + 20] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] WORD $0xdb00 // add bl, bl - LONG $0x0e245c02 // add bl, byte [rsp + 14] - LONG $0x244cb60f; BYTE $0x09 // movzx ecx, byte [rsp + 9] + LONG $0x17245c02 // add bl, byte [rsp + 23] + LONG $0x244cb60f; BYTE $0x12 // movzx ecx, byte [rsp + 18] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0841; BYTE $0xcb // or r11b, cl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x245cb60f; BYTE $0x11 // movzx ebx, byte [rsp + 17] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x5cb60f44; WORD $0x0324 // movzx r11d, byte [rsp + 3] - WORD $0x0845; BYTE $0xeb // or r11b, r13b - LONG $0x6cb60f44; WORD $0x0724 // movzx r13d, byte [rsp + 7] + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x05 // movzx ecx, byte [rsp + 5] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0x0844; BYTE $0xe9 // or cl, r13b - WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247c0a40; BYTE $0x0b // or dil, byte [rsp + 11] LONG $0x07e2c041 // shl r10b, 7 WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xc900 // add cl, cl - LONG $0x06244c02 // add cl, byte [rsp + 6] - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xcf // or r15b, cl - LONG $0x03e6c041 // shl r14b, 3 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0f // add r12b, byte [rsp + 15] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xe6 // or r14b, r12b + LONG $0x03e3c041 // shl r11b, 3 + WORD $0x0845; BYTE $0xf3 // or r11b, r14b + LONG $0x244cb60f; BYTE $0x0d // movzx ecx, byte [rsp + 13] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x241c8845 // mov byte [r12], r11b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0x0844; BYTE $0xd9 // or cl, r11b + WORD $0x8841; BYTE $0x07 // mov byte [r15], al + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 LONG $0x06e1c041 // shl r9b, 6 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448841; BYTE $0x01 // mov byte [r12 + 1], al + LONG $0x017f8841 // mov byte [r15 + 1], dil LONG $0x07e0c041 // shl r8b, 7 WORD $0x0845; BYTE $0xc8 // or r8b, r9b WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x24548845; BYTE $0x02 // mov byte [r12 + 2], r10b - LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x02578845 // mov byte [r15 + 2], r10b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB3_118 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_148 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_122: +LBB3_152: LONG $0x01498d4c // lea r9, [rcx + 1] LONG $0x04100ff3; BYTE $0x8e // movss xmm0, dword [rsi + 4*rcx] LONG $0x8a042e0f // ucomiss xmm0, dword [rdx + 4*rcx] @@ -18049,94 +18578,117 @@ LBB3_122: WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x04b60f45; BYTE $0x3f // movzx r8d, byte [r15 + rdi] WORD $0x3044; BYTE $0xc0 // xor al, r8b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x394d; BYTE $0xce // cmp r14, r9 - JNE LBB3_122 - JMP LBB3_123 + WORD $0x394d; BYTE $0xcc // cmp r12, r9 + JNE LBB3_152 + JMP LBB3_153 -LBB3_57: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_61 - WORD $0x9848 // cdqe - -LBB3_59: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] +LBB3_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe0 // cmp rax, r12 + LONG $0xc44f0f49 // cmovg rax, r12 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB3_74 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB3_72: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd4950f41 // setne r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_59 - LONG $0x01c48349 // add r12, 1 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB3_72 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] -LBB3_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_65 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 +LBB3_74: + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 -LBB3_63: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_76: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_80 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB3_78: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x0246b60f // movzx eax, byte [rsi + 2] WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] LONG $0x0346b60f // movzx eax, byte [rsi + 3] WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] LONG $0x0446b60f // movzx eax, byte [rsi + 4] WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] LONG $0x0546b60f // movzx eax, byte [rsi + 5] WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7950f41 // setne r15b + LONG $0xd6950f41 // setne r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] LONG $0x0946b60f // movzx eax, byte [rsi + 9] WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] LONG $0xd7950f40 // setne dil @@ -18148,19 +18700,19 @@ LBB3_63: LONG $0xd3950f41 // setne r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6950f41 // setne r14b + LONG $0xd7950f41 // setne r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] LONG $0x0e46b60f // movzx eax, byte [rsi + 14] WORD $0x423a; BYTE $0x0e // cmp al, byte [rdx + 14] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x0f46b60f // movzx eax, byte [rsi + 15] WORD $0x423a; BYTE $0x0f // cmp al, byte [rdx + 15] LONG $0xd0950f41 // setne r8b LONG $0x1046b60f // movzx eax, byte [rsi + 16] WORD $0x423a; BYTE $0x10 // cmp al, byte [rdx + 16] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] LONG $0x1146b60f // movzx eax, byte [rsi + 17] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] LONG $0xd4950f41 // setne r12b @@ -18169,147 +18721,146 @@ LBB3_63: LONG $0xd5950f41 // setne r13b LONG $0x1346b60f // movzx eax, byte [rsi + 19] WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] LONG $0x1446b60f // movzx eax, byte [rsi + 20] WORD $0x423a; BYTE $0x14 // cmp al, byte [rdx + 20] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] LONG $0x1546b60f // movzx eax, byte [rsi + 21] WORD $0x423a; BYTE $0x15 // cmp al, byte [rdx + 21] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] LONG $0x1646b60f // movzx eax, byte [rsi + 22] WORD $0x423a; BYTE $0x16 // cmp al, byte [rdx + 22] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] LONG $0x1746b60f // movzx eax, byte [rsi + 23] WORD $0x423a; BYTE $0x17 // cmp al, byte [rdx + 23] LONG $0xd1950f41 // setne r9b LONG $0x1846b60f // movzx eax, byte [rsi + 24] WORD $0x423a; BYTE $0x18 // cmp al, byte [rdx + 24] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] LONG $0x1946b60f // movzx eax, byte [rsi + 25] WORD $0x423a; BYTE $0x19 // cmp al, byte [rdx + 25] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] LONG $0x1a46b60f // movzx eax, byte [rsi + 26] WORD $0x423a; BYTE $0x1a // cmp al, byte [rdx + 26] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x1b46b60f // movzx eax, byte [rsi + 27] WORD $0x423a; BYTE $0x1b // cmp al, byte [rdx + 27] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] LONG $0x1c46b60f // movzx eax, byte [rsi + 28] WORD $0x423a; BYTE $0x1c // cmp al, byte [rdx + 28] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] LONG $0x1d46b60f // movzx eax, byte [rsi + 29] WORD $0x423a; BYTE $0x1d // cmp al, byte [rdx + 29] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x1e46b60f // movzx eax, byte [rsi + 30] WORD $0x423a; BYTE $0x1e // cmp al, byte [rdx + 30] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] LONG $0x1f46b60f // movzx eax, byte [rsi + 31] LONG $0x20c68348 // add rsi, 32 WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xdb00 // add bl, bl - LONG $0x04245c02 // add bl, byte [rsp + 4] + LONG $0x0d245c02 // add bl, byte [rsp + 13] WORD $0xd889 // mov eax, ebx - LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] + LONG $0x245cb60f; BYTE $0x0e // movzx ebx, byte [rsp + 14] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xde // or r14b, bl + LONG $0x245cb60f; BYTE $0x1e // movzx ebx, byte [rsp + 30] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x08 // add dil, byte [rsp + 8] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + LONG $0x247c0240; BYTE $0x11 // add dil, byte [rsp + 17] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e2c041 // shl r10b, 2 WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al WORD $0xdf89 // mov edi, ebx LONG $0x03e3c041 // shl r11b, 3 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x247cb60f; BYTE $0x10 // movzx edi, byte [rsp + 16] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xf8 // or r8b, dil - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0841; BYTE $0xde // or r14b, bl WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] + LONG $0x24640244; BYTE $0x17 // add r12b, byte [rsp + 23] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] + LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x243c8845 // mov byte [r12], r15b - LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b + LONG $0x245cb60f; BYTE $0x15 // movzx ebx, byte [rsp + 21] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x24448845; BYTE $0x01 // mov byte [r12 + 1], r8b + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] + LONG $0x2444b60f; BYTE $0x1b // movzx eax, byte [rsp + 27] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x13 // movzx ebx, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1c // movzx ebx, byte [rsp + 28] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x20c28348 // add rdx, 32 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB3_63 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 + JNE LBB3_78 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] -LBB3_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_67: +LBB3_82: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -18317,97 +18868,113 @@ LBB3_67: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_67 - JMP LBB3_123 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_82 + JMP LBB3_153 -LBB3_90: - LONG $0x1f7e8d4d // lea r15, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xfe490f4d // cmovns r15, r14 - WORD $0x488d; BYTE $0x07 // lea ecx, [rax + 7] - WORD $0xc085 // test eax, eax - WORD $0x490f; BYTE $0xc8 // cmovns ecx, eax - WORD $0xe183; BYTE $0xf8 // and ecx, -8 - WORD $0xc829 // sub eax, ecx - JE LBB3_94 - WORD $0x9848 // cdqe +LBB3_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB3_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB3_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB3_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd2950f41 // setne r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3c // movzx r8d, byte [r12 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB3_92 - LONG $0x01c48349 // add r12, 1 +LBB3_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd3950f41 // setne r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB3_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB3_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB3_98 - LONG $0x2474894c; BYTE $0x18 // mov qword [rsp + 24], r14 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB3_116: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB3_153 + LONG $0x01c78349 // add r15, 1 -LBB3_96: - LONG $0x2464894c; BYTE $0x30 // mov qword [rsp + 48], r12 +LBB3_118: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB3_122 + LONG $0x2464894c; BYTE $0x28 // mov qword [rsp + 40], r12 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB3_120: + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454950f; BYTE $0x04 // setne byte [rsp + 4] + LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] - LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] + LONG $0x2454950f; BYTE $0x1e // setne byte [rsp + 30] WORD $0x468b; BYTE $0x0c // mov eax, dword [rsi + 12] WORD $0x423b; BYTE $0x0c // cmp eax, dword [rdx + 12] - LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] + LONG $0x2454950f; BYTE $0x1f // setne byte [rsp + 31] WORD $0x468b; BYTE $0x10 // mov eax, dword [rsi + 16] WORD $0x423b; BYTE $0x10 // cmp eax, dword [rdx + 16] - LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] + LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] WORD $0x468b; BYTE $0x14 // mov eax, dword [rsi + 20] WORD $0x423b; BYTE $0x14 // cmp eax, dword [rdx + 20] - LONG $0x2454950f; BYTE $0x03 // setne byte [rsp + 3] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] WORD $0x468b; BYTE $0x18 // mov eax, dword [rsi + 24] WORD $0x423b; BYTE $0x18 // cmp eax, dword [rdx + 24] - LONG $0x2454950f; BYTE $0x05 // setne byte [rsp + 5] + LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] LONG $0xd5950f41 // setne r13b WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] - LONG $0x2454950f; BYTE $0x0a // setne byte [rsp + 10] + LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0950f41 // setne r8b + LONG $0xd7950f40 // setne dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3950f41 // setne r11b @@ -18416,21 +18983,21 @@ LBB3_96: LONG $0xd7950f41 // setne r15b WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0x2454950f; BYTE $0x06 // setne byte [rsp + 6] + LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] - LONG $0x2454950f; BYTE $0x07 // setne byte [rsp + 7] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] WORD $0x423b; BYTE $0x38 // cmp eax, dword [rdx + 56] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] WORD $0x468b; BYTE $0x3c // mov eax, dword [rsi + 60] WORD $0x423b; BYTE $0x3c // cmp eax, dword [rdx + 60] - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b WORD $0x468b; BYTE $0x40 // mov eax, dword [rsi + 64] WORD $0x5e8b; BYTE $0x44 // mov ebx, dword [rsi + 68] WORD $0x423b; BYTE $0x40 // cmp eax, dword [rdx + 64] WORD $0x468b; BYTE $0x48 // mov eax, dword [rsi + 72] - LONG $0x2454950f; BYTE $0x0b // setne byte [rsp + 11] + LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] WORD $0x5a3b; BYTE $0x44 // cmp ebx, dword [rdx + 68] WORD $0x5e8b; BYTE $0x4c // mov ebx, dword [rsi + 76] LONG $0xd2950f41 // setne r10b @@ -18441,143 +19008,143 @@ LBB3_96: WORD $0x5e8b; BYTE $0x54 // mov ebx, dword [rsi + 84] LONG $0xd4950f41 // setne r12b WORD $0x423b; BYTE $0x50 // cmp eax, dword [rdx + 80] - LONG $0x2454950f; BYTE $0x09 // setne byte [rsp + 9] + LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] WORD $0x5a3b; BYTE $0x54 // cmp ebx, dword [rdx + 84] WORD $0x468b; BYTE $0x58 // mov eax, dword [rsi + 88] - LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x2454950f; BYTE $0x15 // setne byte [rsp + 21] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454950f; BYTE $0x0d // setne byte [rsp + 13] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1950f41 // setne r9b WORD $0x423b; BYTE $0x60 // cmp eax, dword [rdx + 96] WORD $0x468b; BYTE $0x64 // mov eax, dword [rsi + 100] - LONG $0x2454950f; BYTE $0x14 // setne byte [rsp + 20] + LONG $0x2454950f; BYTE $0x1d // setne byte [rsp + 29] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454950f; BYTE $0x0e // setne byte [rsp + 14] + LONG $0x2454950f; BYTE $0x16 // setne byte [rsp + 22] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454950f; BYTE $0x0f // setne byte [rsp + 15] + LONG $0x2454950f; BYTE $0x17 // setne byte [rsp + 23] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x2454950f; BYTE $0x19 // setne byte [rsp + 25] WORD $0x423b; BYTE $0x70 // cmp eax, dword [rdx + 112] WORD $0x468b; BYTE $0x74 // mov eax, dword [rsi + 116] - LONG $0x2454950f; BYTE $0x11 // setne byte [rsp + 17] + LONG $0x2454950f; BYTE $0x1a // setne byte [rsp + 26] WORD $0x423b; BYTE $0x74 // cmp eax, dword [rdx + 116] WORD $0x468b; BYTE $0x78 // mov eax, dword [rsi + 120] - LONG $0x2454950f; BYTE $0x13 // setne byte [rsp + 19] + LONG $0x2454950f; BYTE $0x1c // setne byte [rsp + 28] WORD $0x423b; BYTE $0x78 // cmp eax, dword [rdx + 120] WORD $0x468b; BYTE $0x7c // mov eax, dword [rsi + 124] - LONG $0x2454950f; BYTE $0x12 // setne byte [rsp + 18] + LONG $0x2454950f; BYTE $0x1b // setne byte [rsp + 27] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x04244402 // add al, byte [rsp + 4] + LONG $0x0d244402 // add al, byte [rsp + 13] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] + LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] + LONG $0x2444b60f; BYTE $0x1e // movzx eax, byte [rsp + 30] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x0a // add r8b, byte [rsp + 10] - LONG $0x245cb60f; BYTE $0x16 // movzx ebx, byte [rsp + 22] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x13 // add dil, byte [rsp + 19] + LONG $0x245cb60f; BYTE $0x1f // movzx ebx, byte [rsp + 31] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 WORD $0xc308 // or bl, al WORD $0xd889 // mov eax, ebx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b - LONG $0x245cb60f; BYTE $0x17 // movzx ebx, byte [rsp + 23] + WORD $0x0841; BYTE $0xfb // or r11b, dil + LONG $0x245cb60f; BYTE $0x0b // movzx ebx, byte [rsp + 11] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0xc308 // or bl, al - WORD $0x8941; BYTE $0xd8 // mov r8d, ebx + WORD $0xdf89 // mov edi, ebx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245cb60f; BYTE $0x03 // movzx ebx, byte [rsp + 3] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xc3 // or bl, r8b - LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] + WORD $0x0840; BYTE $0xfb // or bl, dil + LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - LONG $0x2444b60f; BYTE $0x07 // movzx eax, byte [rsp + 7] + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0824 // movzx r8d, byte [rsp + 8] - LONG $0x06e0c041 // shl r8b, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0844; BYTE $0xc7 // or dil, r8b + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x11 // movzx edi, byte [rsp + 17] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf8 // or r8b, dil WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0841; BYTE $0xc0 // or r8b, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x0b // add r10b, byte [rsp + 11] + LONG $0x24540244; BYTE $0x14 // add r10b, byte [rsp + 20] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] + LONG $0x2444b60f; BYTE $0x12 // movzx eax, byte [rsp + 18] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc389 // mov ebx, eax - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + LONG $0x2444b60f; BYTE $0x15 // movzx eax, byte [rsp + 21] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x242c8845 // mov byte [r12], r13b - LONG $0x245cb60f; BYTE $0x0d // movzx ebx, byte [rsp + 13] + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xd9 // or r9b, bl - LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x01478845 // mov byte [r15 + 1], r8b WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x16 // movzx eax, byte [rsp + 22] WORD $0xc000 // add al, al - LONG $0x14244402 // add al, byte [rsp + 20] + LONG $0x1d244402 // add al, byte [rsp + 29] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x0f // movzx eax, byte [rsp + 15] + LONG $0x2444b60f; BYTE $0x17 // movzx eax, byte [rsp + 23] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x19 // movzx eax, byte [rsp + 25] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x11 // movzx eax, byte [rsp + 17] + LONG $0x2444b60f; BYTE $0x1a // movzx eax, byte [rsp + 26] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x13 // movzx eax, byte [rsp + 19] + LONG $0x2444b60f; BYTE $0x1c // movzx eax, byte [rsp + 28] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - LONG $0x245cb60f; BYTE $0x12 // movzx ebx, byte [rsp + 18] + LONG $0x245cb60f; BYTE $0x1b // movzx ebx, byte [rsp + 27] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 WORD $0xd908 // or cl, bl WORD $0xc108 // or cl, al - LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x034f8841 // mov byte [r15 + 3], cl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c48349 // add r12, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB3_96 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB3_120 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB3_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xf7 // cmp r15, r14 - JGE LBB3_123 - WORD $0x294d; BYTE $0xfe // sub r14, r15 +LBB3_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc4 // sub r12, rax + JLE LBB3_153 WORD $0xc931 // xor ecx, ecx -LBB3_100: +LBB3_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -18585,19 +19152,20 @@ LBB3_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x894d; BYTE $0xfa // mov r10, r15 + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc6 // cmp r14, r8 - JNE LBB3_100 + WORD $0x394d; BYTE $0xc4 // cmp r12, r8 + JNE LBB3_124 -LBB3_123: +LBB3_153: SUBQ $8, SP RET @@ -18649,143 +19217,803 @@ DATA LCDATA3<>+0x160(SB)/8, $0xffffffffffffffff DATA LCDATA3<>+0x168(SB)/8, $0xffffffffffffffff GLOBL LCDATA3<>(SB), 8, $368 -TEXT ·_comparison_not_equal_arr_scalar_sse4(SB), $344-48 +TEXT ·_comparison_not_equal_arr_scalar_sse4(SB), $312-48 + + MOVQ typ+0(FP), DI + MOVQ left+8(FP), SI + MOVQ right+16(FP), DX + MOVQ out+24(FP), CX + MOVQ length+32(FP), R8 + MOVQ offset+40(FP), R9 + MOVQ SP, BP + ADDQ $16, SP + ANDQ $-16, SP + MOVQ BP, 288(SP) + LEAQ LCDATA3<>(SB), BP + + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB4_19 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB4_36 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB4_59 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB4_64 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB4_208 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_11 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_9 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_8: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_8 + +LBB4_9: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 + LONG $0x01c48349 // add r12, 1 + +LBB4_11: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB4_15 + QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + +LBB4_13: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0xd2950f41 // setne r10b + LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0xd6950f41 // setne r14b + LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x146e3944 // cmp dword [rsi + 20], r13d + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x186e3944 // cmp dword [rsi + 24], r13d + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x206e3944 // cmp dword [rsi + 32], r13d + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x246e3944 // cmp dword [rsi + 36], r13d + LONG $0xd7950f40 // setne dil + LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0xd0950f41 // setne r8b + LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0xd1950f41 // setne r9b + LONG $0x306e3944 // cmp dword [rsi + 48], r13d + LONG $0xd3950f41 // setne r11b + LONG $0x346e3944 // cmp dword [rsi + 52], r13d + LONG $0xd4950f41 // setne r12b + LONG $0x386e3944 // cmp dword [rsi + 56], r13d + QUAD $0x000000e02494950f // setne byte [rsp + 224] + LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x406e3944 // cmp dword [rsi + 64], r13d + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x446e3944 // cmp dword [rsi + 68], r13d + QUAD $0x000000d02494950f // setne byte [rsp + 208] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x506e3944 // cmp dword [rsi + 80], r13d + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x546e3944 // cmp dword [rsi + 84], r13d + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x586e3944 // cmp dword [rsi + 88], r13d + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d + LONG $0xd7950f41 // setne r15b + LONG $0x606e3944 // cmp dword [rsi + 96], r13d + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x686e3944 // cmp dword [rsi + 104], r13d + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x706e3944 // cmp dword [rsi + 112], r13d + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x746e3944 // cmp dword [rsi + 116], r13d + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0x786e3944 // cmp dword [rsi + 120], r13d + LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc2 // mov r10d, eax + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xd0 // or al, r10b + WORD $0xc789 // mov edi, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x000000e024bcb60f // movzx edi, byte [rsp + 224] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xc308 // or bl, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + WORD $0xc000 // add al, al + LONG $0x60244402 // add al, byte [rsp + 96] + WORD $0xc789 // mov edi, eax + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x241c8841 // mov byte [r12], bl + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB4_13 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB4_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_208 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JE LBB4_113 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB4_18: + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x02c38349 // add r11, 2 + LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0x08768d48 // lea rsi, [rsi + 8] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0xd830 // xor al, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3c148841 // mov byte [r12 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB4_18 + JMP LBB4_177 + +LBB4_19: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB4_43 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB4_69 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB4_82 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB4_208 + WORD $0x8b4c; BYTE $0x3a // mov r15, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_29 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_27 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_26: + LONG $0x012e0f66 // ucomisd xmm0, qword [rcx] + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x9a0f; BYTE $0xd1 // setp cl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xcb08 // or bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_26 + +LBB4_27: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 + LONG $0x01c48349 // add r12, 1 + +LBB4_29: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB4_33 + QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + QUAD $0x0000010824848948 // mov qword [rsp + 264], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + +LBB4_31: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x462e0f66; BYTE $0x08 // ucomisd xmm0, qword [rsi + 8] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd5950f41 // setne r13b + WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x462e0f66; BYTE $0x10 // ucomisd xmm0, qword [rsi + 16] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x462e0f66; BYTE $0x18 // ucomisd xmm0, qword [rsi + 24] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x462e0f66; BYTE $0x20 // ucomisd xmm0, qword [rsi + 32] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x462e0f66; BYTE $0x28 // ucomisd xmm0, qword [rsi + 40] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x462e0f66; BYTE $0x30 // ucomisd xmm0, qword [rsi + 48] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x462e0f66; BYTE $0x38 // ucomisd xmm0, qword [rsi + 56] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x08244c88 // mov byte [rsp + 8], cl + LONG $0x462e0f66; BYTE $0x40 // ucomisd xmm0, qword [rsi + 64] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x462e0f66; BYTE $0x48 // ucomisd xmm0, qword [rsi + 72] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x462e0f66; BYTE $0x50 // ucomisd xmm0, qword [rsi + 80] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x462e0f66; BYTE $0x58 // ucomisd xmm0, qword [rsi + 88] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xc308 // or bl, al + LONG $0x462e0f66; BYTE $0x60 // ucomisd xmm0, qword [rsi + 96] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x18244c88 // mov byte [rsp + 24], cl + LONG $0x462e0f66; BYTE $0x68 // ucomisd xmm0, qword [rsi + 104] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x462e0f66; BYTE $0x70 // ucomisd xmm0, qword [rsi + 112] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x462e0f66; BYTE $0x78 // ucomisd xmm0, qword [rsi + 120] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x70244c88 // mov byte [rsp + 112], cl + QUAD $0x00000080862e0f66 // ucomisd xmm0, qword [rsi + 128] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x68244c88 // mov byte [rsp + 104], cl + QUAD $0x00000088862e0f66 // ucomisd xmm0, qword [rsi + 136] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + QUAD $0x00000090862e0f66 // ucomisd xmm0, qword [rsi + 144] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl + QUAD $0x00000098862e0f66 // ucomisd xmm0, qword [rsi + 152] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl + QUAD $0x000000a0862e0f66 // ucomisd xmm0, qword [rsi + 160] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + QUAD $0x000000a8862e0f66 // ucomisd xmm0, qword [rsi + 168] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl + QUAD $0x000000b0862e0f66 // ucomisd xmm0, qword [rsi + 176] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al + QUAD $0x000000b8862e0f66 // ucomisd xmm0, qword [rsi + 184] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd0950f41 // setne r8b + WORD $0x0841; BYTE $0xc0 // or r8b, al + QUAD $0x000000c0862e0f66 // ucomisd xmm0, qword [rsi + 192] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl + QUAD $0x000000c8862e0f66 // ucomisd xmm0, qword [rsi + 200] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al + QUAD $0x000000d0862e0f66 // ucomisd xmm0, qword [rsi + 208] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al + QUAD $0x000000d8862e0f66 // ucomisd xmm0, qword [rsi + 216] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd1950f41 // setne r9b + WORD $0x0841; BYTE $0xc1 // or r9b, al + QUAD $0x000000e0862e0f66 // ucomisd xmm0, qword [rsi + 224] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl + QUAD $0x000000e8862e0f66 // ucomisd xmm0, qword [rsi + 232] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xf0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 240], cl + QUAD $0x000000f0862e0f66 // ucomisd xmm0, qword [rsi + 240] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f40 // setne dil + WORD $0x0840; BYTE $0xc7 // or dil, al + QUAD $0x000000f8862e0f66 // ucomisd xmm0, qword [rsi + 248] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] + WORD $0x8944; BYTE $0xe8 // mov eax, r13d + LONG $0x05e4c041 // shl r12b, 5 + LONG $0x6cb60f44; WORD $0x4024 // movzx r13d, byte [rsp + 64] + LONG $0x06e5c041 // shl r13b, 6 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + LONG $0x64b60f44; WORD $0x3024 // movzx r12d, byte [rsp + 48] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xc900 // add cl, cl + LONG $0x38244c02 // add cl, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x08244488 // mov byte [rsp + 8], al + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0xcb08 // or bl, cl + LONG $0x6cb60f44; WORD $0x2024 // movzx r13d, byte [rsp + 32] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x18244488 // mov byte [rsp + 24], al + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x74b60f44; WORD $0x7024 // movzx r14d, byte [rsp + 112] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + WORD $0xc900 // add cl, cl + LONG $0x68244c02 // add cl, byte [rsp + 104] + QUAD $0x000000d0249cb60f // movzx ebx, byte [rsp + 208] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0xcb08 // or bl, cl + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x0844; BYTE $0xe8 // or al, r13b + QUAD $0x00000098249cb60f // movzx ebx, byte [rsp + 152] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c041 // shl r15b, 6 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x24740a44; BYTE $0x18 // or r14b, byte [rsp + 24] + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xf8 // or r8b, r15b + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x00000088249c0244 // add r11b, byte [rsp + 136] + LONG $0x02e2c041 // shl r10b, 2 + WORD $0x0845; BYTE $0xda // or r10b, r11b + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xd1 // or r9b, r10b + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xc9 // or cl, r9b + WORD $0xcb89 // mov ebx, ecx + LONG $0x24048841 // mov byte [r12], al + QUAD $0x000000f0248cb60f // movzx ecx, byte [rsp + 240] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x24748845; BYTE $0x01 // mov byte [r12 + 1], r14b + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xda08 // or dl, bl + LONG $0x24448845; BYTE $0x02 // mov byte [r12 + 2], r8b + LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 + JNE LBB4_31 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] + QUAD $0x0000010824848b48 // mov rax, qword [rsp + 264] + +LBB4_33: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_208 + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB4_190 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB4_192 - MOVQ typ+0(FP), DI - MOVQ left+8(FP), SI - MOVQ right+16(FP), DX - MOVQ out+24(FP), CX - MOVQ length+32(FP), R8 - MOVQ offset+40(FP), R9 - MOVQ SP, BP - ADDQ $16, SP - ANDQ $-16, SP - MOVQ BP, 320(SP) - LEAQ LCDATA3<>(SB), BP +LBB4_36: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB4_96 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB4_208 + WORD $0x8a44; BYTE $0x3a // mov r15b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_114 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_120 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB4_41: + LONG $0x016e8d4c // lea r13, [rsi + 1] + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894c; BYTE $0xe7 // mov rdi, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x894c; BYTE $0xee // mov rsi, r13 + LONG $0xffc38349 // add r11, -1 + JNE LBB4_41 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JNE LBB4_121 + JMP LBB4_208 - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB4_17 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB4_32 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB4_83 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB4_99 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB4_174 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_7: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - LONG $0x04b60f45; BYTE $0x1c // movzx r8d, byte [r12 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1c3c8841 // mov byte [r12 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_7 - LONG $0x01c48349 // add r12, 1 +LBB4_43: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB4_101 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB4_208 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_49 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_48: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_48 -LBB4_9: - LONG $0x05fac149 // sar r10, 5 +LBB4_49: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 + LONG $0x01c48349 // add r12, 1 + +LBB4_51: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_13 + JL LBB4_55 QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax -LBB4_11: - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d +LBB4_53: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0xd2950f41 // setne r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6950f41 // setne r14b - LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d + LONG $0x186e394c // cmp qword [rsi + 24], r13 QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d + LONG $0x206e394c // cmp qword [rsi + 32], r13 LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x146e3944 // cmp dword [rsi + 20], r13d + LONG $0x286e394c // cmp qword [rsi + 40], r13 LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x186e3944 // cmp dword [rsi + 24], r13d + LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + LONG $0x386e394c // cmp qword [rsi + 56], r13 WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x000000e02494950f // setne byte [rsp + 224] - LONG $0x246e3944 // cmp dword [rsi + 36], r13d + LONG $0x406e394c // cmp qword [rsi + 64], r13 + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x486e394c // cmp qword [rsi + 72], r13 LONG $0xd7950f40 // setne dil - LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0x506e394c // cmp qword [rsi + 80], r13 LONG $0xd0950f41 // setne r8b - LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0x586e394c // cmp qword [rsi + 88], r13 LONG $0xd1950f41 // setne r9b - LONG $0x306e3944 // cmp dword [rsi + 48], r13d + LONG $0x606e394c // cmp qword [rsi + 96], r13 LONG $0xd3950f41 // setne r11b - LONG $0x346e3944 // cmp dword [rsi + 52], r13d + LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4950f41 // setne r12b - LONG $0x386e3944 // cmp dword [rsi + 56], r13d - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x406e3944 // cmp dword [rsi + 64], r13d + LONG $0x706e394c // cmp qword [rsi + 112], r13 + QUAD $0x000000e02494950f // setne byte [rsp + 224] + LONG $0x786e394c // cmp qword [rsi + 120], r13 + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d + LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 + QUAD $0x000000d02494950f // setne byte [rsp + 208] + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x546e3944 // cmp dword [rsi + 84], r13d + LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d - LONG $0xd7950f41 // setne r15b - LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d + LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 + LONG $0xd7950f41 // setne r15b + LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x706e3944 // cmp dword [rsi + 112], r13d + LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d + LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x786e3944 // cmp dword [rsi + 120], r13d + LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 + WORD $0x950f; BYTE $0xd1 // setne cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -18794,7 +20022,7 @@ LBB4_11: LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000e024bc0240 // add dil, byte [rsp + 224] + QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b @@ -18814,18 +20042,18 @@ LBB4_11: WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] + QUAD $0x000000e024bcb60f // movzx edi, byte [rsp + 224] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xc000 // add al, al LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax @@ -18833,68 +20061,67 @@ LBB4_11: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x241c8841 // mov byte [r12], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244c8841; BYTE $0x01 // mov byte [r12 + 1], cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0x04c48349 // add r12, 4 QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB4_11 + JNE LBB4_53 QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB4_13: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 +LBB4_55: + LONG $0x05e0c148 // shl rax, 5 WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JE LBB4_82 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_208 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JE LBB4_81 WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB4_16: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d +LBB4_58: + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 @@ -18910,8 +20137,8 @@ LBB4_16: WORD $0x3044; BYTE $0xcb // xor bl, r9b LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0x08768d48 // lea rsi, [rsi + 8] + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0x10768d48 // lea rsi, [rsi + 16] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0xd830 // xor al, bl @@ -18922,282 +20149,637 @@ LBB4_16: WORD $0xda30 // xor dl, bl LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_16 - JMP LBB4_151 + JNE LBB4_58 + JMP LBB4_196 -LBB4_17: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB4_46 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB4_114 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB4_125 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB4_174 - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x02100ff2 // movsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_25 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_23: - LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xca08 // or dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax +LBB4_59: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_136 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_134 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x8945; BYTE $0xef // mov r15d, r13d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_62: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x39394466 // cmp word [rcx], r15w + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_62 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JNE LBB4_135 + JMP LBB4_208 + +LBB4_64: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_150 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_148 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x8945; BYTE $0xef // mov r15d, r13d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_67: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x39394466 // cmp word [rcx], r15w + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_67 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JNE LBB4_149 + JMP LBB4_208 + +LBB4_69: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_75 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_73 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_72: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_23 - LONG $0x01c48349 // add r12, 1 + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_72 -LBB4_25: - LONG $0x05fac149 // sar r10, 5 +LBB4_73: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 + LONG $0x01c48349 // add r12, 1 + +LBB4_75: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_29 + JL LBB4_79 QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000000d82494894c // mov qword [rsp + 216], r10 - QUAD $0x000001102494894c // mov qword [rsp + 272], r10 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax -LBB4_27: - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 - LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] +LBB4_77: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0xd2950f41 // setne r10b + LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0xd6950f41 // setne r14b + LONG $0x186e394c // cmp qword [rsi + 24], r13 + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x206e394c // cmp qword [rsi + 32], r13 + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x286e394c // cmp qword [rsi + 40], r13 + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x306e394c // cmp qword [rsi + 48], r13 + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x386e394c // cmp qword [rsi + 56], r13 + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x406e394c // cmp qword [rsi + 64], r13 + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x486e394c // cmp qword [rsi + 72], r13 + LONG $0xd7950f40 // setne dil + LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0xd0950f41 // setne r8b + LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0xd1950f41 // setne r9b + LONG $0x606e394c // cmp qword [rsi + 96], r13 + LONG $0xd3950f41 // setne r11b + LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0xd4950f41 // setne r12b + LONG $0x706e394c // cmp qword [rsi + 112], r13 + QUAD $0x000000e02494950f // setne byte [rsp + 224] + LONG $0x786e394c // cmp qword [rsi + 120], r13 + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 + QUAD $0x000000d02494950f // setne byte [rsp + 208] + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 + LONG $0xd7950f41 // setne r15b + LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] + LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x8941; BYTE $0xc2 // mov r10d, eax + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xd0 // or al, r10b + WORD $0xc789 // mov edi, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x000000e024bcb60f // movzx edi, byte [rsp + 224] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xc308 // or bl, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + WORD $0xc000 // add al, al + LONG $0x60244402 // add al, byte [rsp + 96] + WORD $0xc789 // mov edi, eax + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0xc789 // mov edi, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x241c8841 // mov byte [r12], bl + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB4_77 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + +LBB4_79: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_208 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB4_194 + +LBB4_81: + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB4_196 + +LBB4_82: + WORD $0x8b44; BYTE $0x3a // mov r15d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_88 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_86 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_85: + WORD $0x2e0f; BYTE $0x01 // ucomiss xmm0, dword [rcx] + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x9a0f; BYTE $0xd1 // setp cl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xcb08 // or bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_85 + +LBB4_86: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 + LONG $0x01c48349 // add r12, 1 + +LBB4_88: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB4_115 + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + LONG $0x04f98348 // cmp rcx, 4 + JB LBB4_92 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB4_209 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JBE LBB4_209 + +LBB4_92: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + +LBB4_93: + LONG $0x246c894c; BYTE $0x78 // mov qword [rsp + 120], r13 + QUAD $0x000000a824bc8944 // mov dword [rsp + 168], r15d + QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + QUAD $0x000000a0248c8948 // mov qword [rsp + 160], rcx + WORD $0x294c; BYTE $0xc9 // sub rcx, r9 + QUAD $0x000000b0248c8948 // mov qword [rsp + 176], rcx + +LBB4_94: + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl - LONG $0x462e0f66; BYTE $0x08 // ucomisd xmm0, qword [rsi + 8] + WORD $0x8941; BYTE $0xcd // mov r13d, ecx + LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd5950f41 // setne r13b - WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x462e0f66; BYTE $0x10 // ucomisd xmm0, qword [rsi + 16] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + LONG $0x08432e0f // ucomiss xmm0, dword [rbx + 8] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl - LONG $0x462e0f66; BYTE $0x18 // ucomisd xmm0, qword [rsi + 24] + LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x10244c88 // mov byte [rsp + 16], cl - LONG $0x462e0f66; BYTE $0x20 // ucomisd xmm0, qword [rsi + 32] + LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl - LONG $0x462e0f66; BYTE $0x28 // ucomisd xmm0, qword [rsi + 40] + LONG $0x18244c88 // mov byte [rsp + 24], cl + LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd4950f41 // setne r12b - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x462e0f66; BYTE $0x30 // ucomisd xmm0, qword [rsi + 48] + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x38244c88 // mov byte [rsp + 56], cl - LONG $0x462e0f66; BYTE $0x38 // ucomisd xmm0, qword [rsi + 56] + LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x08244c88 // mov byte [rsp + 8], cl - LONG $0x462e0f66; BYTE $0x40 // ucomisd xmm0, qword [rsi + 64] + LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x40244c88 // mov byte [rsp + 64], cl - LONG $0x462e0f66; BYTE $0x48 // ucomisd xmm0, qword [rsi + 72] + LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl - LONG $0x462e0f66; BYTE $0x50 // ucomisd xmm0, qword [rsi + 80] + LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x48244c88 // mov byte [rsp + 72], cl - LONG $0x462e0f66; BYTE $0x58 // ucomisd xmm0, qword [rsi + 88] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - LONG $0x462e0f66; BYTE $0x60 // ucomisd xmm0, qword [rsi + 96] + LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x18244c88 // mov byte [rsp + 24], cl - LONG $0x462e0f66; BYTE $0x68 // ucomisd xmm0, qword [rsi + 104] + LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl - LONG $0x462e0f66; BYTE $0x70 // ucomisd xmm0, qword [rsi + 112] + LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl - LONG $0x462e0f66; BYTE $0x78 // ucomisd xmm0, qword [rsi + 120] + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x70244c88 // mov byte [rsp + 112], cl - QUAD $0x00000080862e0f66 // ucomisd xmm0, qword [rsi + 128] + LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl - QUAD $0x00000088862e0f66 // ucomisd xmm0, qword [rsi + 136] + LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl - QUAD $0x00000090862e0f66 // ucomisd xmm0, qword [rsi + 144] + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x48432e0f // ucomiss xmm0, dword [rbx + 72] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl - QUAD $0x00000098862e0f66 // ucomisd xmm0, qword [rsi + 152] + LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl + LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl - QUAD $0x000000a0862e0f66 // ucomisd xmm0, qword [rsi + 160] + LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl + LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al - LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl - QUAD $0x000000a8862e0f66 // ucomisd xmm0, qword [rsi + 168] + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl - QUAD $0x000000b0862e0f66 // ucomisd xmm0, qword [rsi + 176] + LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al - QUAD $0x000000b8862e0f66 // ucomisd xmm0, qword [rsi + 184] + LONG $0xd6950f41 // setne r14b + WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0x5c432e0f // ucomiss xmm0, dword [rbx + 92] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd0950f41 // setne r8b WORD $0x0841; BYTE $0xc0 // or r8b, al - QUAD $0x000000c0862e0f66 // ucomisd xmm0, qword [rsi + 192] + LONG $0x60432e0f // ucomiss xmm0, dword [rbx + 96] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl - QUAD $0x000000c8862e0f66 // ucomisd xmm0, qword [rsi + 200] + LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd3950f41 // setne r11b WORD $0x0841; BYTE $0xc3 // or r11b, al - QUAD $0x000000d0862e0f66 // ucomisd xmm0, qword [rsi + 208] + LONG $0x68432e0f // ucomiss xmm0, dword [rbx + 104] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd2950f41 // setne r10b WORD $0x0841; BYTE $0xc2 // or r10b, al - QUAD $0x000000d8862e0f66 // ucomisd xmm0, qword [rsi + 216] + LONG $0x6c432e0f // ucomiss xmm0, dword [rbx + 108] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd1950f41 // setne r9b WORD $0x0841; BYTE $0xc1 // or r9b, al - QUAD $0x000000e0862e0f66 // ucomisd xmm0, qword [rsi + 224] + LONG $0x70432e0f // ucomiss xmm0, dword [rbx + 112] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl - QUAD $0x000000e8862e0f66 // ucomisd xmm0, qword [rsi + 232] + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl WORD $0xc108 // or cl, al LONG $0xf0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 240], cl - QUAD $0x000000f0862e0f66 // ucomisd xmm0, qword [rsi + 240] + LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd7950f40 // setne dil WORD $0x0840; BYTE $0xc7 // or dil, al - QUAD $0x000000f8862e0f66 // ucomisd xmm0, qword [rsi + 248] + LONG $0x7c432e0f // ucomiss xmm0, dword [rbx + 124] WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x20 // add r13b, byte [rsp + 32] - WORD $0x8944; BYTE $0xe8 // mov eax, r13d - LONG $0x05e4c041 // shl r12b, 5 - LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] - LONG $0x06e5c041 // shl r13b, 6 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x64b60f44; WORD $0x3024 // movzx r12d, byte [rsp + 48] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + LONG $0xd6950f40 // setne sil + WORD $0x0840; BYTE $0xc6 // or sil, al + WORD $0xd200 // add dl, dl + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd5 // mov r13d, edx + LONG $0x2454b60f; BYTE $0x28 // movzx edx, byte [rsp + 40] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0844; BYTE $0xe8 // or al, r13b + WORD $0x8941; BYTE $0xc5 // mov r13d, eax + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] WORD $0xc900 // add cl, cl - LONG $0x40244c02 // add cl, byte [rsp + 64] + LONG $0x30244c02 // add cl, byte [rsp + 48] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0844; BYTE $0xe8 // or al, r13b + WORD $0xd008 // or al, dl LONG $0x08244488 // mov byte [rsp + 8], al - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0xcb08 // or bl, cl - LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] - LONG $0x04e5c041 // shl r13b, 4 - WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - LONG $0x18244488 // mov byte [rsp + 24], al - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0x0844; BYTE $0xe8 // or al, r13b + WORD $0x8941; BYTE $0xc5 // mov r13d, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x74b60f44; WORD $0x7024 // movzx r14d, byte [rsp + 112] - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xc900 // add cl, cl - LONG $0x50244c02 // add cl, byte [rsp + 80] - QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0xcb08 // or bl, cl - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xca08 // or dl, cl + LONG $0x6cb60f44; WORD $0x5824 // movzx r13d, byte [rsp + 88] + LONG $0x05e5c041 // shl r13b, 5 + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + LONG $0x6cb60f44; WORD $0x7024 // movzx r13d, byte [rsp + 112] + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xcd // or r13b, cl + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x60 // add r12b, byte [rsp + 96] + WORD $0x8944; BYTE $0xe1 // mov ecx, r12d + QUAD $0x0000d024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 208] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xcc // or r12b, cl QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0x8941; BYTE $0xcc // mov r12d, ecx + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x0844; BYTE $0xe8 // or al, r13b - QUAD $0x00000098249cb60f // movzx ebx, byte [rsp + 152] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x06e7c041 // shl r15b, 6 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x24740a44; BYTE $0x18 // or r14b, byte [rsp + 24] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x64b60f44; WORD $0x0824 // movzx r12d, byte [rsp + 8] + WORD $0x0841; BYTE $0xc4 // or r12b, al + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + LONG $0x06e6c041 // shl r14b, 6 + WORD $0x0841; BYTE $0xc6 // or r14b, al + WORD $0x0841; BYTE $0xd5 // or r13b, dl LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf8 // or r8b, r15b + WORD $0x0845; BYTE $0xf0 // or r8b, r14b WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0045; BYTE $0xdb // add r11b, r11b QUAD $0x00000088249c0244 // add r11b, byte [rsp + 136] @@ -19205,417 +20787,201 @@ LBB4_27: WORD $0x0845; BYTE $0xda // or r10b, r11b LONG $0x03e1c041 // shl r9b, 3 WORD $0x0845; BYTE $0xd1 // or r9b, r10b - QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xc9 // or cl, r9b - WORD $0xcb89 // mov ebx, ecx - LONG $0x24048841 // mov byte [r12], al + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + WORD $0x8844; BYTE $0x20 // mov byte [rax], r12b QUAD $0x000000f0248cb60f // movzx ecx, byte [rsp + 240] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 LONG $0x06e7c040 // shl dil, 6 WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x24748845; BYTE $0x01 // mov byte [r12 + 1], r14b - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xda08 // or dl, bl - LONG $0x24448845; BYTE $0x02 // mov byte [r12 + 2], r8b - LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c48349 // add r12, 4 - QUAD $0x0000011024848348; BYTE $0xff // add qword [rsp + 272], -1 - JNE LBB4_27 + LONG $0x01688844 // mov byte [rax + 1], r13b + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xfe // or sil, dil + WORD $0x0844; BYTE $0xfe // or sil, r15b + LONG $0x02408844 // mov byte [rax + 2], r8b + LONG $0x03708840 // mov byte [rax + 3], sil + LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 + LONG $0x04c08348 // add rax, 4 + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 + JNE LBB4_94 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x000000d824948b4c // mov r10, qword [rsp + 216] + QUAD $0x000000a824bc8b44 // mov r15d, dword [rsp + 168] + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + JMP LBB4_116 + +LBB4_96: + WORD $0x8a44; BYTE $0x3a // mov r15b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_119 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_161 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 -LBB4_29: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JNE LBB4_160 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB4_162 - -LBB4_32: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB4_60 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB4_174 - WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_38 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB4_99: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_99 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JNE LBB4_162 + JMP LBB4_208 -LBB4_36: - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax +LBB4_101: + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB4_107 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB4_105 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB4_104: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx LONG $0x03ffc148 // sar rdi, 3 WORD $0x894d; BYTE $0xe7 // mov r15, r12 LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_36 - LONG $0x01c48349 // add r12, 1 - -LBB4_38: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_137 - LONG $0x10fa8349 // cmp r10, 16 - LONG $0x245c8844; BYTE $0x08 // mov byte [rsp + 8], r11b - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000001082494894c // mov qword [rsp + 264], r10 - JB LBB4_42 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc4 // cmp r12, rax - JAE LBB4_179 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB4_179 - -LBB4_42: - WORD $0xc031 // xor eax, eax - QUAD $0x000000d824848948 // mov qword [rsp + 216], rax - LONG $0x2464894c; BYTE $0x68 // mov qword [rsp + 104], r12 + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB4_104 -LBB4_43: - QUAD $0x000000d824942b4c // sub r10, qword [rsp + 216] - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 +LBB4_105: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 + LONG $0x01c48349 // add r12, 1 -LBB4_44: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - QUAD $0x000000f02494950f // setne byte [rsp + 240] - LONG $0x015e3844 // cmp byte [rsi + 1], r11b - LONG $0xd6950f40 // setne sil - LONG $0x02593844 // cmp byte [rcx + 2], r11b - LONG $0xd7950f41 // setne r15b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al - LONG $0xd4950f41 // setne r12b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al - LONG $0xd1950f41 // setne r9b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al - QUAD $0x000000e02494950f // setne byte [rsp + 224] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al - LONG $0xd7950f40 // setne dil - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al - LONG $0xd2950f41 // setne r10b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al - LONG $0xd6950f41 // setne r14b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al - LONG $0xd5950f41 // setne r13b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al - LONG $0xd0950f41 // setne r8b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl - LONG $0xd3950f41 // setne r11b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000f024b40240 // add sil, byte [rsp + 240] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - WORD $0xd200 // add dl, dl - LONG $0xe0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 224] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x7cb60f44; WORD $0x0824 // movzx r15d, byte [rsp + 8] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - WORD $0x0841; BYTE $0xd1 // or r9b, dl - WORD $0x0845; BYTE $0xe8 // or r8b, r13b - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xd200 // add dl, dl - LONG $0xb0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 176] - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - WORD $0x8844; BYTE $0x0a // mov byte [rdx], r9b - LONG $0x247cb60f; BYTE $0x50 // movzx edi, byte [rsp + 80] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xfb // or r11b, dil - LONG $0x01428844 // mov byte [rdx + 1], r8b - WORD $0x0841; BYTE $0xf3 // or r11b, sil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xc000 // add al, al - LONG $0x40244402 // add al, byte [rsp + 64] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xc308 // or bl, al - LONG $0x025a8844 // mov byte [rdx + 2], r11b - WORD $0x8945; BYTE $0xfb // mov r11d, r15d - WORD $0x5a88; BYTE $0x03 // mov byte [rdx + 3], bl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c28348 // add rdx, 4 - LONG $0x24548948; BYTE $0x68 // mov qword [rsp + 104], rdx - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB4_44 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - JMP LBB4_138 - -LBB4_46: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB4_72 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB4_174 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] +LBB4_107: + LONG $0x1f468d49 // lea rax, [r14 + 31] WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_52 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_50: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - LONG $0x04b60f45; BYTE $0x1c // movzx r8d, byte [r12 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1c3c8841 // mov byte [r12 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_50 - LONG $0x01c48349 // add r12, 1 - -LBB4_52: - LONG $0x05fac149 // sar r10, 5 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_56 + JL LBB4_111 QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 + QUAD $0x000000b024848948 // mov qword [rsp + 176], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax -LBB4_54: - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 +LBB4_109: + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd2950f41 // setne r10b - LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6950f41 // setne r14b - LONG $0x186e394c // cmp qword [rsi + 24], r13 + LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x206e394c // cmp qword [rsi + 32], r13 + LONG $0x106e3944 // cmp dword [rsi + 16], r13d LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x286e394c // cmp qword [rsi + 40], r13 + LONG $0x146e3944 // cmp dword [rsi + 20], r13d LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x306e394c // cmp qword [rsi + 48], r13 + LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x386e394c // cmp qword [rsi + 56], r13 + LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x000000e02494950f // setne byte [rsp + 224] - LONG $0x486e394c // cmp qword [rsi + 72], r13 + LONG $0x206e3944 // cmp dword [rsi + 32], r13d + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x246e3944 // cmp dword [rsi + 36], r13d LONG $0xd7950f40 // setne dil - LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0x286e3944 // cmp dword [rsi + 40], r13d LONG $0xd0950f41 // setne r8b - LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d LONG $0xd1950f41 // setne r9b - LONG $0x606e394c // cmp qword [rsi + 96], r13 + LONG $0x306e3944 // cmp dword [rsi + 48], r13d LONG $0xd3950f41 // setne r11b - LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4950f41 // setne r12b - LONG $0x706e394c // cmp qword [rsi + 112], r13 - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 + LONG $0x386e3944 // cmp dword [rsi + 56], r13d + QUAD $0x000000e02494950f // setne byte [rsp + 224] + LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x406e3944 // cmp dword [rsi + 64], r13d LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + LONG $0x446e3944 // cmp dword [rsi + 68], r13d + QUAD $0x000000d02494950f // setne byte [rsp + 208] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 + LONG $0x506e3944 // cmp dword [rsi + 80], r13d LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 - LONG $0xd7950f41 // setne r15b - LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x546e3944 // cmp dword [rsi + 84], r13d + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x586e3944 // cmp dword [rsi + 88], r13d LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d + LONG $0xd7950f41 // setne r15b + LONG $0x606e3944 // cmp dword [rsi + 96], r13d LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x686e3944 // cmp dword [rsi + 104], r13d + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 + LONG $0x706e3944 // cmp dword [rsi + 112], r13d LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + LONG $0x746e3944 // cmp dword [rsi + 116], r13d LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x786e3944 // cmp dword [rsi + 120], r13d LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d + WORD $0x950f; BYTE $0xd1 // setne cl WORD $0x0045; BYTE $0xd2 // add r10b, r10b QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -19624,7 +20990,7 @@ LBB4_54: LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000e024bc0240 // add dil, byte [rsp + 224] + QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b @@ -19644,18 +21010,18 @@ LBB4_54: WORD $0x0845; BYTE $0xcb // or r11b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] + QUAD $0x000000e024bcb60f // movzx edi, byte [rsp + 224] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xc000 // add al, al LONG $0x60244402 // add al, byte [rsp + 96] WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax @@ -19663,195 +21029,161 @@ LBB4_54: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0840; BYTE $0xf8 // or al, dil WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0840; BYTE $0xf8 // or al, dil LONG $0x241c8841 // mov byte [r12], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244c8841; BYTE $0x01 // mov byte [r12 + 1], cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0xc108 // or cl, al LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 LONG $0x04c48349 // add r12, 4 QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB4_54 + JNE LBB4_109 QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] -LBB4_56: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 +LBB4_111: + LONG $0x05e0c148 // shl rax, 5 WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JE LBB4_124 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB4_208 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB4_175 + +LBB4_113: WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB4_177 -LBB4_59: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0x03efc148 // shr rdi, 3 - WORD $0x894d; BYTE $0xe6 // mov r14, r12 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x02c38349 // add r11, 2 - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0x10768d48 // lea rsi, [rsi + 16] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0xd830 // xor al, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0xc220 // and dl, al - WORD $0xda30 // xor dl, bl - LONG $0x3c148841 // mov byte [r12 + rdi], dl - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_59 - JMP LBB4_170 +LBB4_114: + WORD $0x8949; BYTE $0xf5 // mov r13, rsi + JMP LBB4_122 -LBB4_60: - WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_64 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB4_115: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi -LBB4_62: - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_62 - LONG $0x01c48349 // add r12, 1 +LBB4_116: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB4_208 + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB4_199 + WORD $0xf631 // xor esi, esi + JMP LBB4_201 -LBB4_64: - LONG $0x05fac149 // sar r10, 5 +LBB4_119: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB4_163 + +LBB4_120: + WORD $0x8949; BYTE $0xf5 // mov r13, rsi + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 + +LBB4_121: + LONG $0x01c48349 // add r12, 1 + +LBB4_122: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_141 - LONG $0x10fa8349 // cmp r10, 16 - LONG $0x245c8844; BYTE $0x08 // mov byte [rsp + 8], r11b + JL LBB4_130 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x247c8844; BYTE $0x08 // mov byte [rsp + 8], r15b QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000001202494894c // mov qword [rsp + 288], r10 - JB LBB4_68 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x00000108248c8948 // mov qword [rsp + 264], rcx + JB LBB4_126 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x014c; BYTE $0xe8 // add rax, r13 WORD $0x3949; BYTE $0xc4 // cmp r12, rax - JAE LBB4_182 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB4_182 + JAE LBB4_212 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc5 // cmp r13, rax + JAE LBB4_212 -LBB4_68: - WORD $0xc031 // xor eax, eax - QUAD $0x000000d824848948 // mov qword [rsp + 216], rax - LONG $0x2464894c; BYTE $0x68 // mov qword [rsp + 104], r12 +LBB4_126: + WORD $0xc031 // xor eax, eax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 -LBB4_69: - QUAD $0x000000d824942b4c // sub r10, qword [rsp + 216] - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 +LBB4_127: + QUAD $0x000000a8248c2b48 // sub rcx, qword [rsp + 168] + QUAD $0x000000b0248c8948 // mov qword [rsp + 176], rcx + QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] -LBB4_70: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b +LBB4_128: + WORD $0x894c; BYTE $0xe9 // mov rcx, r13 + LONG $0x007d3845 // cmp byte [r13], r15b QUAD $0x000000f02494950f // setne byte [rsp + 240] - LONG $0x015e3844 // cmp byte [rsi + 1], r11b + LONG $0x017d3845 // cmp byte [r13 + 1], r15b LONG $0xd6950f40 // setne sil - LONG $0x02593844 // cmp byte [rcx + 2], r11b + LONG $0x027d3845 // cmp byte [r13 + 2], r15b + WORD $0x8944; BYTE $0xf8 // mov eax, r15d LONG $0xd7950f41 // setne r15b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al - LONG $0xd4950f41 // setne r12b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al + LONG $0x03453841 // cmp byte [r13 + 3], al QUAD $0x000000882494950f // setne byte [rsp + 136] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x04453841 // cmp byte [r13 + 4], al + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al - QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x05453841 // cmp byte [r13 + 5], al + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x06453841 // cmp byte [r13 + 6], al + LONG $0xd5950f41 // setne r13b LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al LONG $0xd1950f41 // setne r9b LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al - QUAD $0x000000e02494950f // setne byte [rsp + 224] + QUAD $0x000000802494950f // setne byte [rsp + 128] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al WORD $0x950f; BYTE $0xd2 // setne dl LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al - LONG $0xd7950f40 // setne dil + LONG $0xd0950f41 // setne r8b LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al LONG $0xd2950f41 // setne r10b @@ -19860,49 +21192,49 @@ LBB4_70: LONG $0xd6950f41 // setne r14b LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al - LONG $0xd5950f41 // setne r13b + QUAD $0x000000982494950f // setne byte [rsp + 152] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al - QUAD $0x000000a02494950f // setne byte [rsp + 160] + QUAD $0x000000e02494950f // setne byte [rsp + 224] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al - LONG $0xd0950f41 // setne r8b + LONG $0xd4950f41 // setne r12b LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl - QUAD $0x000000b02494950f // setne byte [rsp + 176] + QUAD $0x000000d02494950f // setne byte [rsp + 208] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + QUAD $0x000000c02494950f // setne byte [rsp + 192] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl LONG $0xd3950f41 // setne r11b LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] @@ -19911,392 +21243,159 @@ LBB4_70: LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl WORD $0x950f; BYTE $0xd3 // setne bl WORD $0x0040; BYTE $0xf6 // add sil, sil QUAD $0x000000f024b40240 // add sil, byte [rsp + 240] - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x06e5c041 // shl r13b, 6 LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al + WORD $0x0845; BYTE $0xe9 // or r9b, r13b LONG $0x02e7c041 // shl r15b, 2 WORD $0x0841; BYTE $0xf7 // or r15b, sil WORD $0xd200 // add dl, dl - LONG $0xe0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 224] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x7cb60f44; WORD $0x0824 // movzx r15d, byte [rsp + 8] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl + LONG $0x80249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 128] QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x7cb60f44; WORD $0x0824 // movzx r15d, byte [rsp + 8] LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al + WORD $0x0840; BYTE $0xf2 // or dl, sil LONG $0x04e6c041 // shl r14b, 4 WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000e024b4b60f // movzx esi, byte [rsp + 224] LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xf4 // or r12b, sil WORD $0x0841; BYTE $0xd1 // or r9b, dl - WORD $0x0845; BYTE $0xe8 // or r8b, r13b - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0x0841; BYTE $0xc4 // or r12b, al + QUAD $0x000000c02494b60f // movzx edx, byte [rsp + 192] WORD $0xd200 // add dl, dl - LONG $0xb0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 176] + LONG $0xd0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 208] WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] WORD $0xe2c0; BYTE $0x02 // shl dl, 2 WORD $0x0840; BYTE $0xf2 // or dl, sil WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] WORD $0xe2c0; BYTE $0x03 // shl dl, 3 WORD $0x0840; BYTE $0xf2 // or dl, sil WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] WORD $0xe2c0; BYTE $0x04 // shl dl, 4 WORD $0x0840; BYTE $0xf2 // or dl, sil WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - WORD $0x8844; BYTE $0x0a // mov byte [rdx], r9b - LONG $0x247cb60f; BYTE $0x50 // movzx edi, byte [rsp + 80] - LONG $0x06e7c040 // shl dil, 6 + WORD $0x8844; BYTE $0x0f // mov byte [rdi], r9b + LONG $0x2474b60f; BYTE $0x48 // movzx esi, byte [rsp + 72] + LONG $0x06e6c040 // shl sil, 6 LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xfb // or r11b, dil - LONG $0x01428844 // mov byte [rdx + 1], r8b WORD $0x0841; BYTE $0xf3 // or r11b, sil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x01678844 // mov byte [rdi + 1], r12b + WORD $0x0841; BYTE $0xd3 // or r11b, dl + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x40244402 // add al, byte [rsp + 64] - WORD $0xc689 // mov esi, eax + LONG $0x38244402 // add al, byte [rsp + 56] + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x0000008024b4b60f // movzx esi, byte [rsp + 128] - LONG $0x06e6c040 // shl sil, 6 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xd308 // or bl, dl WORD $0xc308 // or bl, al - LONG $0x025a8844 // mov byte [rdx + 2], r11b - WORD $0x8945; BYTE $0xfb // mov r11d, r15d - WORD $0x5a88; BYTE $0x03 // mov byte [rdx + 3], bl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c28348 // add rdx, 4 - LONG $0x24548948; BYTE $0x68 // mov qword [rsp + 104], rdx - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB4_70 + LONG $0x025f8844 // mov byte [rdi + 2], r11b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20698d4c // lea r13, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 + JNE LBB4_128 + QUAD $0x000000a024bc8948 // mov qword [rsp + 160], rdi QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - JMP LBB4_142 - -LBB4_72: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_76 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_74: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - LONG $0x04b60f45; BYTE $0x1c // movzx r8d, byte [r12 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1c3c8841 // mov byte [r12 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_74 - LONG $0x01c48349 // add r12, 1 - -LBB4_76: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_80 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + JMP LBB4_131 -LBB4_78: - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd2950f41 // setne r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d - LONG $0xd6950f41 // setne r14b - LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x186e3944 // cmp dword [rsi + 24], r13d - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x000000e02494950f // setne byte [rsp + 224] - LONG $0x246e3944 // cmp dword [rsi + 36], r13d - LONG $0xd7950f40 // setne dil - LONG $0x286e3944 // cmp dword [rsi + 40], r13d - LONG $0xd0950f41 // setne r8b - LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd1950f41 // setne r9b - LONG $0x306e3944 // cmp dword [rsi + 48], r13d - LONG $0xd3950f41 // setne r11b - LONG $0x346e3944 // cmp dword [rsi + 52], r13d - LONG $0xd4950f41 // setne r12b - LONG $0x386e3944 // cmp dword [rsi + 56], r13d - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d - LONG $0xd7950f41 // setne r15b - LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x706e3944 // cmp dword [rsi + 112], r13d - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x786e3944 // cmp dword [rsi + 120], r13d - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000e024bc0240 // add dil, byte [rsp + 224] - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x60244402 // add al, byte [rsp + 96] - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x241c8841 // mov byte [r12], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244c8841; BYTE $0x01 // mov byte [r12 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c48349 // add r12, 4 - QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB4_78 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] +LBB4_130: + QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 -LBB4_80: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 +LBB4_131: + LONG $0x05e1c148 // shl rcx, 5 WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JNE LBB4_149 - -LBB4_82: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB4_151 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB4_208 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB4_179 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB4_182 -LBB4_83: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_87 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB4_134: + WORD $0x8945; BYTE $0xef // mov r15d, r13d + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 -LBB4_85: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_85 - LONG $0x01c48349 // add r12, 1 +LBB4_135: + WORD $0x8945; BYTE $0xfd // mov r13d, r15d + LONG $0x01c48349 // add r12, 1 -LBB4_87: - LONG $0x05fac149 // sar r10, 5 +LBB4_136: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_95 - LONG $0x08fa8349 // cmp r10, 8 + JL LBB4_144 + LONG $0x08f98348 // cmp rcx, 8 QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - JB LBB4_91 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x000000b0248c8948 // mov qword [rsp + 176], rcx + JB LBB4_140 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xf0 // add rax, rsi WORD $0x3949; BYTE $0xc4 // cmp r12, rax - JAE LBB4_185 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] + JAE LBB4_215 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB4_185 + JBE LBB4_215 -LBB4_91: +LBB4_140: WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax -LBB4_92: +LBB4_141: LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 - LONG $0x24542b4c; BYTE $0x20 // sub r10, qword [rsp + 32] - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 + LONG $0x244c2b48; BYTE $0x28 // sub rcx, qword [rsp + 40] + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx -LBB4_93: +LBB4_142: WORD $0x8949; BYTE $0xf3 // mov r11, rsi LONG $0x2e394466 // cmp word [rsi], r13w QUAD $0x000000982494950f // setne byte [rsp + 152] @@ -20307,7 +21406,7 @@ LBB4_93: LONG $0x6b394566; BYTE $0x06 // cmp word [r11 + 6], r13w LONG $0xd4950f41 // setne r12b LONG $0x6b394566; BYTE $0x08 // cmp word [r11 + 8], r13w - QUAD $0x000000b02494950f // setne byte [rsp + 176] + QUAD $0x000000d02494950f // setne byte [rsp + 208] LONG $0x6b394566; BYTE $0x0a // cmp word [r11 + 10], r13w LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] LONG $0x6b394566; BYTE $0x0c // cmp word [r11 + 12], r13w @@ -20315,7 +21414,7 @@ LBB4_93: LONG $0x6b394566; BYTE $0x0e // cmp word [r11 + 14], r13w WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x6b394566; BYTE $0x10 // cmp word [r11 + 16], r13w - QUAD $0x000000e02494950f // setne byte [rsp + 224] + QUAD $0x000000802494950f // setne byte [rsp + 128] LONG $0x6b394566; BYTE $0x12 // cmp word [r11 + 18], r13w WORD $0x950f; BYTE $0xd1 // setne cl LONG $0x6b394566; BYTE $0x14 // cmp word [r11 + 20], r13w @@ -20327,13 +21426,13 @@ LBB4_93: LONG $0x6b394566; BYTE $0x1a // cmp word [r11 + 26], r13w QUAD $0x000000882494950f // setne byte [rsp + 136] LONG $0x6b394566; BYTE $0x1c // cmp word [r11 + 28], r13w - QUAD $0x000000a02494950f // setne byte [rsp + 160] + QUAD $0x000000e02494950f // setne byte [rsp + 224] LONG $0x6b394566; BYTE $0x1e // cmp word [r11 + 30], r13w LONG $0xd7950f40 // setne dil LONG $0x6b394566; BYTE $0x20 // cmp word [r11 + 32], r13w - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] LONG $0x6b394566; BYTE $0x22 // cmp word [r11 + 34], r13w - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + QUAD $0x000000c02494950f // setne byte [rsp + 192] LONG $0x6b394566; BYTE $0x24 // cmp word [r11 + 36], r13w LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] LONG $0x6b394566; BYTE $0x26 // cmp word [r11 + 38], r13w @@ -20341,25 +21440,25 @@ LBB4_93: LONG $0x6b394566; BYTE $0x28 // cmp word [r11 + 40], r13w LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] LONG $0x6b394566; BYTE $0x2a // cmp word [r11 + 42], r13w - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] LONG $0x6b394566; BYTE $0x2c // cmp word [r11 + 44], r13w - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] LONG $0x6b394566; BYTE $0x2e // cmp word [r11 + 46], r13w LONG $0xd2950f41 // setne r10b LONG $0x6b394566; BYTE $0x30 // cmp word [r11 + 48], r13w LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] LONG $0x6b394566; BYTE $0x32 // cmp word [r11 + 50], r13w - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x6b394566; BYTE $0x34 // cmp word [r11 + 52], r13w - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x6b394566; BYTE $0x34 // cmp word [r11 + 52], r13w LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] LONG $0x6b394566; BYTE $0x38 // cmp word [r11 + 56], r13w LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x6b394566; BYTE $0x3a // cmp word [r11 + 58], r13w LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x6b394566; BYTE $0x3c // cmp word [r11 + 60], r13w - QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] LONG $0x6b394566; BYTE $0x3e // cmp word [r11 + 62], r13w WORD $0x950f; BYTE $0xd2 // setne dl WORD $0x0040; BYTE $0xf6 // add sil, sil @@ -20370,12 +21469,12 @@ LBB4_93: LONG $0x02e7c041 // shl r15b, 2 WORD $0x0841; BYTE $0xf7 // or r15b, sil WORD $0xc900 // add cl, cl - LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + LONG $0x80248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 128] LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xc8 // or r8b, cl - QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0844; BYTE $0xe1 // or cl, r12b WORD $0xce89 // mov esi, ecx @@ -20389,15 +21488,15 @@ LBB4_93: QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xf0 // or al, r14b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + QUAD $0x000000e024b4b60f // movzx esi, byte [rsp + 224] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xf7 // or dil, sil WORD $0xcb08 // or bl, cl WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] WORD $0xc900 // add cl, cl - LONG $0x50244c02 // add cl, byte [rsp + 80] + LONG $0x68244c02 // add cl, byte [rsp + 104] WORD $0xce89 // mov esi, ecx LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 @@ -20411,27 +21510,27 @@ LBB4_93: WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx - LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] WORD $0x1988 // mov byte [rcx], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0841; BYTE $0xda // or r10b, bl LONG $0x01798840 // mov byte [rcx + 1], dil WORD $0x0841; BYTE $0xf2 // or r10b, sil - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd808 // or al, bl WORD $0xc389 // mov ebx, eax @@ -20442,7 +21541,7 @@ LBB4_93: LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd808 // or al, bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0xda08 // or dl, bl @@ -20453,25 +21552,24 @@ LBB4_93: LONG $0x04c18348 // add rcx, 4 LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB4_93 + JNE LBB4_142 QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] -LBB4_95: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 +LBB4_144: + LONG $0x05e1c148 // shl rcx, 5 WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JE LBB4_113 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB4_208 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JE LBB4_160 WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB4_98: +LBB4_147: WORD $0x8948; BYTE $0xf0 // mov rax, rsi LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x950f; BYTE $0xd2 // setne dl @@ -20500,74 +21598,48 @@ LBB4_98: WORD $0xd830 // xor al, bl LONG $0x3c048841 // mov byte [r12 + rdi], al WORD $0x394d; BYTE $0xf1 // cmp r9, r14 - JNE LBB4_98 - JMP LBB4_166 + JNE LBB4_147 + JMP LBB4_205 -LBB4_99: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_103 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB4_148: + WORD $0x8945; BYTE $0xef // mov r15d, r13d + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 -LBB4_101: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_101 - LONG $0x01c48349 // add r12, 1 +LBB4_149: + WORD $0x8945; BYTE $0xfd // mov r13d, r15d + LONG $0x01c48349 // add r12, 1 -LBB4_103: - LONG $0x05fac149 // sar r10, 5 +LBB4_150: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_111 - LONG $0x08fa8349 // cmp r10, 8 + JL LBB4_158 + LONG $0x08f98348 // cmp rcx, 8 QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - JB LBB4_107 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x000000b0248c8948 // mov qword [rsp + 176], rcx + JB LBB4_154 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xf0 // add rax, rsi WORD $0x3949; BYTE $0xc4 // cmp r12, rax - JAE LBB4_191 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] + JAE LBB4_218 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB4_191 + JBE LBB4_218 -LBB4_107: +LBB4_154: WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax -LBB4_108: +LBB4_155: LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 - LONG $0x24542b4c; BYTE $0x20 // sub r10, qword [rsp + 32] - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 + LONG $0x244c2b48; BYTE $0x28 // sub rcx, qword [rsp + 40] + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx -LBB4_109: +LBB4_156: WORD $0x8949; BYTE $0xf3 // mov r11, rsi LONG $0x2e394466 // cmp word [rsi], r13w QUAD $0x000000982494950f // setne byte [rsp + 152] @@ -20578,7 +21650,7 @@ LBB4_109: LONG $0x6b394566; BYTE $0x06 // cmp word [r11 + 6], r13w LONG $0xd4950f41 // setne r12b LONG $0x6b394566; BYTE $0x08 // cmp word [r11 + 8], r13w - QUAD $0x000000b02494950f // setne byte [rsp + 176] + QUAD $0x000000d02494950f // setne byte [rsp + 208] LONG $0x6b394566; BYTE $0x0a // cmp word [r11 + 10], r13w LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] LONG $0x6b394566; BYTE $0x0c // cmp word [r11 + 12], r13w @@ -20586,7 +21658,7 @@ LBB4_109: LONG $0x6b394566; BYTE $0x0e // cmp word [r11 + 14], r13w WORD $0x950f; BYTE $0xd3 // setne bl LONG $0x6b394566; BYTE $0x10 // cmp word [r11 + 16], r13w - QUAD $0x000000e02494950f // setne byte [rsp + 224] + QUAD $0x000000802494950f // setne byte [rsp + 128] LONG $0x6b394566; BYTE $0x12 // cmp word [r11 + 18], r13w WORD $0x950f; BYTE $0xd1 // setne cl LONG $0x6b394566; BYTE $0x14 // cmp word [r11 + 20], r13w @@ -20598,13 +21670,13 @@ LBB4_109: LONG $0x6b394566; BYTE $0x1a // cmp word [r11 + 26], r13w QUAD $0x000000882494950f // setne byte [rsp + 136] LONG $0x6b394566; BYTE $0x1c // cmp word [r11 + 28], r13w - QUAD $0x000000a02494950f // setne byte [rsp + 160] + QUAD $0x000000e02494950f // setne byte [rsp + 224] LONG $0x6b394566; BYTE $0x1e // cmp word [r11 + 30], r13w LONG $0xd7950f40 // setne dil LONG $0x6b394566; BYTE $0x20 // cmp word [r11 + 32], r13w - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] LONG $0x6b394566; BYTE $0x22 // cmp word [r11 + 34], r13w - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + QUAD $0x000000c02494950f // setne byte [rsp + 192] LONG $0x6b394566; BYTE $0x24 // cmp word [r11 + 36], r13w LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] LONG $0x6b394566; BYTE $0x26 // cmp word [r11 + 38], r13w @@ -20612,25 +21684,25 @@ LBB4_109: LONG $0x6b394566; BYTE $0x28 // cmp word [r11 + 40], r13w LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] LONG $0x6b394566; BYTE $0x2a // cmp word [r11 + 42], r13w - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] LONG $0x6b394566; BYTE $0x2c // cmp word [r11 + 44], r13w - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] LONG $0x6b394566; BYTE $0x2e // cmp word [r11 + 46], r13w LONG $0xd2950f41 // setne r10b LONG $0x6b394566; BYTE $0x30 // cmp word [r11 + 48], r13w LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] LONG $0x6b394566; BYTE $0x32 // cmp word [r11 + 50], r13w - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] LONG $0x6b394566; BYTE $0x34 // cmp word [r11 + 52], r13w - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] LONG $0x6b394566; BYTE $0x38 // cmp word [r11 + 56], r13w LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] LONG $0x6b394566; BYTE $0x3a // cmp word [r11 + 58], r13w LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] LONG $0x6b394566; BYTE $0x3c // cmp word [r11 + 60], r13w - QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] LONG $0x6b394566; BYTE $0x3e // cmp word [r11 + 62], r13w WORD $0x950f; BYTE $0xd2 // setne dl WORD $0x0040; BYTE $0xf6 // add sil, sil @@ -20641,12 +21713,12 @@ LBB4_109: LONG $0x02e7c041 // shl r15b, 2 WORD $0x0841; BYTE $0xf7 // or r15b, sil WORD $0xc900 // add cl, cl - LONG $0xe0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 224] + LONG $0x80248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 128] LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b LONG $0x02e0c041 // shl r8b, 2 WORD $0x0841; BYTE $0xc8 // or r8b, cl - QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0844; BYTE $0xe1 // or cl, r12b WORD $0xce89 // mov esi, ecx @@ -20660,15 +21732,15 @@ LBB4_109: QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xf0 // or al, r14b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + QUAD $0x000000e024b4b60f // movzx esi, byte [rsp + 224] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xf7 // or dil, sil WORD $0xcb08 // or bl, cl WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] WORD $0xc900 // add cl, cl - LONG $0x50244c02 // add cl, byte [rsp + 80] + LONG $0x68244c02 // add cl, byte [rsp + 104] WORD $0xce89 // mov esi, ecx LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 @@ -20679,696 +21751,321 @@ LBB4_109: WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0xce89 // mov esi, ecx - LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0xce89 // mov esi, ecx - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - WORD $0x1988 // mov byte [rcx], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x01798840 // mov byte [rcx + 1], dil - WORD $0x0841; BYTE $0xf2 // or r10b, sil - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xc000 // add al, al - LONG $0x30244402 // add al, byte [rsp + 48] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02518844 // mov byte [rcx + 2], r10b - WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl - LONG $0x40738d49 // lea rsi, [r11 + 64] - LONG $0x04c18348 // add rcx, 4 - LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx - QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB4_109 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - -LBB4_111: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JNE LBB4_164 - -LBB4_113: - WORD $0x3145; BYTE $0xf6 // xor r14d, r14d - JMP LBB4_166 - -LBB4_114: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_118 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_116: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - LONG $0x04b60f45; BYTE $0x1c // movzx r8d, byte [r12 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1c3c8841 // mov byte [r12 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_116 - LONG $0x01c48349 // add r12, 1 - -LBB4_118: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_122 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - -LBB4_120: - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0xd2950f41 // setne r10b - LONG $0x106e394c // cmp qword [rsi + 16], r13 - LONG $0xd6950f41 // setne r14b - LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x206e394c // cmp qword [rsi + 32], r13 - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x306e394c // cmp qword [rsi + 48], r13 - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x386e394c // cmp qword [rsi + 56], r13 - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x000000e02494950f // setne byte [rsp + 224] - LONG $0x486e394c // cmp qword [rsi + 72], r13 - LONG $0xd7950f40 // setne dil - LONG $0x506e394c // cmp qword [rsi + 80], r13 - LONG $0xd0950f41 // setne r8b - LONG $0x586e394c // cmp qword [rsi + 88], r13 - LONG $0xd1950f41 // setne r9b - LONG $0x606e394c // cmp qword [rsi + 96], r13 - LONG $0xd3950f41 // setne r11b - LONG $0x686e394c // cmp qword [rsi + 104], r13 - LONG $0xd4950f41 // setne r12b - LONG $0x706e394c // cmp qword [rsi + 112], r13 - QUAD $0x000000a02494950f // setne byte [rsp + 160] - LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 - LONG $0xd7950f41 // setne r15b - LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009824940244 // add r10b, byte [rsp + 152] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000e024bc0240 // add dil, byte [rsp + 224] - QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x60244402 // add al, byte [rsp + 96] - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x241c8841 // mov byte [r12], bl - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x244c8841; BYTE $0x01 // mov byte [r12 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b - LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c48349 // add r12, 4 - QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB4_120 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - -LBB4_122: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JNE LBB4_168 - -LBB4_124: - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB4_170 - -LBB4_125: - LONG $0x1f568d4d // lea r10, [r14 + 31] - WORD $0x854d; BYTE $0xf6 // test r14, r14 - LONG $0xd6490f4d // cmovns r10, r14 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x02100ff3 // movss xmm0, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB4_129 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB4_127: - WORD $0x2e0f; BYTE $0x06 // ucomiss xmm0, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xca08 // or dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB4_127 - LONG $0x01c48349 // add r12, 1 - -LBB4_129: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fe8349 // cmp r14, 32 - JL LBB4_145 - LONG $0x04fa8349 // cmp r10, 4 - JB LBB4_133 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc4 // cmp r12, rax - JAE LBB4_188 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] - WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB4_188 - -LBB4_133: - WORD $0x3145; BYTE $0xc0 // xor r8d, r8d - WORD $0x8948; BYTE $0xf3 // mov rbx, rsi - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - -LBB4_134: - QUAD $0x0000008024bc894c // mov qword [rsp + 128], r15 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x000001102494894c // mov qword [rsp + 272], r10 - WORD $0x294d; BYTE $0xc2 // sub r10, r8 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - -LBB4_135: - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xcd // mov r13d, ecx - LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - LONG $0x08432e0f // ucomiss xmm0, dword [rbx + 8] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl - LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl - LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x18244c88 // mov byte [rsp + 24], cl - LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl - LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl - LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl - LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl - LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl - LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl - LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl - LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl - LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl - LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl - LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl - LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl - LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd4950f41 // setne r12b - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x48432e0f // ucomiss xmm0, dword [rbx + 72] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl - LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl - LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl - LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl - LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x5c432e0f // ucomiss xmm0, dword [rbx + 92] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd0950f41 // setne r8b - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x60432e0f // ucomiss xmm0, dword [rbx + 96] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl - LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x68432e0f // ucomiss xmm0, dword [rbx + 104] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - LONG $0x6c432e0f // ucomiss xmm0, dword [rbx + 108] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd1950f41 // setne r9b - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x70432e0f // ucomiss xmm0, dword [rbx + 112] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xf0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 240], cl - LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f40 // setne dil - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x7c432e0f // ucomiss xmm0, dword [rbx + 124] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f40 // setne sil - WORD $0x0840; BYTE $0xc6 // or sil, al - WORD $0xd200 // add dl, dl - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd5 // mov r13d, edx - LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] + WORD $0x1988 // mov byte [rcx], bl + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xda // or r10b, bl + LONG $0x01798840 // mov byte [rcx + 1], dil + WORD $0x0841; BYTE $0xf2 // or r10b, sil + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xc900 // add cl, cl - LONG $0x30244c02 // add cl, byte [rsp + 48] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl - LONG $0x08244488 // mov byte [rsp + 8], al - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xca08 // or dl, cl - LONG $0x6cb60f44; WORD $0x5824 // movzx r13d, byte [rsp + 88] - LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x6cb60f44; WORD $0x7024 // movzx r13d, byte [rsp + 112] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xcd // or r13b, cl - WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x60 // add r12b, byte [rsp + 96] - WORD $0x8944; BYTE $0xe1 // mov ecx, r12d - QUAD $0x0000b024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 176] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0841; BYTE $0xcc // or r12b, cl - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - WORD $0x8941; BYTE $0xcc // mov r12d, ecx - QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x64b60f44; WORD $0x0824 // movzx r12d, byte [rsp + 8] - WORD $0x0841; BYTE $0xc4 // or r12b, al - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e6c041 // shl r14b, 6 - WORD $0x0841; BYTE $0xc6 // or r14b, al - WORD $0x0841; BYTE $0xd5 // or r13b, dl - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf0 // or r8b, r14b - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x00000088249c0244 // add r11b, byte [rsp + 136] - LONG $0x02e2c041 // shl r10b, 2 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xd1 // or r9b, r10b - LONG $0x04e7c041 // shl r15b, 4 - WORD $0x0845; BYTE $0xcf // or r15b, r9b - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - WORD $0x8844; BYTE $0x20 // mov byte [rax], r12b - QUAD $0x000000f0248cb60f // movzx ecx, byte [rsp + 240] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x06e7c040 // shl dil, 6 - WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e6c040 // shl sil, 7 - WORD $0x0840; BYTE $0xfe // or sil, dil - WORD $0x0844; BYTE $0xfe // or sil, r15b - LONG $0x02408844 // mov byte [rax + 2], r8b - LONG $0x03708840 // mov byte [rax + 3], sil - LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 - LONG $0x04c08348 // add rax, 4 - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB4_135 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] + WORD $0xd808 // or al, bl + LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02518844 // mov byte [rcx + 2], r10b + WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl + LONG $0x40738d49 // lea rsi, [r11 + 64] + LONG $0x04c18348 // add rcx, 4 + LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB4_156 QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0000011024948b4c // mov r10, qword [rsp + 272] - JMP LBB4_146 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] -LBB4_137: - LONG $0x2464894c; BYTE $0x68 // mov qword [rsp + 104], r12 +LBB4_158: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB4_208 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB4_203 -LBB4_138: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JE LBB4_144 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] +LBB4_160: + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB4_205 -LBB4_154: - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b - LONG $0x02488d4c // lea r9, [rax + 2] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB4_154 - JMP LBB4_157 +LBB4_161: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB4_208 -LBB4_141: - LONG $0x2464894c; BYTE $0x68 // mov qword [rsp + 104], r12 +LBB4_162: + LONG $0x01c48349 // add r12, 1 -LBB4_142: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JNE LBB4_155 +LBB4_163: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB4_171 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x247c8844; BYTE $0x08 // mov byte [rsp + 8], r15b + QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + QUAD $0x00000108248c8948 // mov qword [rsp + 264], rcx + JB LBB4_167 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB4_221 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB4_221 -LBB4_144: - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x01c0f641 // test r8b, 1 - JE LBB4_174 - JMP LBB4_159 +LBB4_167: + WORD $0xc031 // xor eax, eax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB4_145: - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - WORD $0x8948; BYTE $0xf3 // mov rbx, rsi +LBB4_168: + QUAD $0x000000a8248c2b48 // sub rcx, qword [rsp + 168] + QUAD $0x000000b0248c8948 // mov qword [rsp + 176], rcx + QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] + +LBB4_169: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b + QUAD $0x000000f02494950f // setne byte [rsp + 240] + LONG $0x017e3844 // cmp byte [rsi + 1], r15b + LONG $0xd6950f40 // setne sil + LONG $0x02793844 // cmp byte [rcx + 2], r15b + WORD $0x8944; BYTE $0xf8 // mov eax, r15d + LONG $0xd7950f41 // setne r15b + WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al + LONG $0xd5950f41 // setne r13b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al + LONG $0xd1950f41 // setne r9b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0xd0950f41 // setne r8b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd2950f41 // setne r10b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd6950f41 // setne r14b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + QUAD $0x000000982494950f // setne byte [rsp + 152] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000000e02494950f // setne byte [rsp + 224] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd4950f41 // setne r12b + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000000d02494950f // setne byte [rsp + 208] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd3950f41 // setne r11b + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x000000f024b40240 // add sil, byte [rsp + 240] + LONG $0x06e5c041 // shl r13b, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0845; BYTE $0xe9 // or r9b, r13b + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + WORD $0xd200 // add dl, dl + LONG $0x80249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 128] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x7cb60f44; WORD $0x0824 // movzx r15d, byte [rsp + 8] + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x000000e024b4b60f // movzx esi, byte [rsp + 224] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xf4 // or r12b, sil + WORD $0x0841; BYTE $0xd1 // or r9b, dl + WORD $0x0841; BYTE $0xc4 // or r12b, al + QUAD $0x000000c02494b60f // movzx edx, byte [rsp + 192] + WORD $0xd200 // add dl, dl + LONG $0xd0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 208] + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0x8844; BYTE $0x0f // mov byte [rdi], r9b + LONG $0x2474b60f; BYTE $0x48 // movzx esi, byte [rsp + 72] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xf3 // or r11b, sil + LONG $0x01678844 // mov byte [rdi + 1], r12b + WORD $0x0841; BYTE $0xd3 // or r11b, dl + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xc000 // add al, al + LONG $0x38244402 // add al, byte [rsp + 56] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x025f8844 // mov byte [rdi + 2], r11b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x000000b024848348; BYTE $0xff // add qword [rsp + 176], -1 + JNE LBB4_169 + QUAD $0x000000a024bc8948 // mov qword [rsp + 160], rdi + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + JMP LBB4_172 + +LBB4_171: + QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB4_146: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xf2 // cmp r10, r14 - JGE LBB4_174 +LBB4_172: + LONG $0x05e1c148 // shl rcx, 5 WORD $0x894d; BYTE $0xf0 // mov r8, r14 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xf2 // add r10, r14 - JNE LBB4_175 - WORD $0xf631 // xor esi, esi - JMP LBB4_177 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB4_208 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB4_184 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB4_187 -LBB4_149: +LBB4_175: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB4_150: +LBB4_176: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al @@ -21397,23 +22094,23 @@ LBB4_150: WORD $0xda30 // xor dl, bl LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_150 + JNE LBB4_176 -LBB4_151: +LBB4_177: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_174 + JE LBB4_208 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - JMP LBB4_172 + JMP LBB4_198 -LBB4_155: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] +LBB4_179: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] -LBB4_156: +LBB4_180: WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b + LONG $0x0d7c3847; BYTE $0x00 // cmp byte [r13 + r9], r15b WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xdbf6 // neg bl WORD $0x894c; BYTE $0xcf // mov rdi, r9 @@ -21422,12 +22119,12 @@ LBB4_156: WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x057c3845; BYTE $0x01 // cmp byte [r13 + rax + 1], r15b LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xdbf6 // neg bl @@ -21437,39 +22134,82 @@ LBB4_156: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3b048841 // mov byte [r11 + rdi], al WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB4_156 + JNE LBB4_180 + WORD $0x014d; BYTE $0xcd // add r13, r9 -LBB4_157: - WORD $0x014c; BYTE $0xce // add rsi, r9 +LBB4_182: + LONG $0x01c0f641 // test r8b, 1 + JE LBB4_208 + LONG $0x007d3845 // cmp byte [r13], r15b + JMP LBB4_189 + +LBB4_184: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] + +LBB4_185: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0e3c3846 // cmp byte [rsi + r9], r15b + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xcf // mov rdi, r9 + LONG $0x03efc148 // shr rdi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x067c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r15b + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB4_185 + WORD $0x014c; BYTE $0xce // add rsi, r9 + +LBB4_187: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_174 + JE LBB4_208 + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b -LBB4_159: - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xca // mov rdx, r9 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e18041 // and r9b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xc9 // mov ecx, r9d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB4_174 +LBB4_189: + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + JMP LBB4_208 -LBB4_160: +LBB4_190: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB4_161: +LBB4_191: LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd0 // setne al @@ -21502,11 +22242,11 @@ LBB4_161: WORD $0xda30 // xor dl, bl LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB4_161 + JNE LBB4_191 -LBB4_162: +LBB4_192: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_174 + JE LBB4_208 LONG $0x062e0f66 // ucomisd xmm0, qword [rsi] WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd2 // setne dl @@ -21523,68 +22263,14 @@ LBB4_162: WORD $0xd320 // and bl, dl WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x041c8841 // mov byte [r12 + rax], bl - JMP LBB4_174 - -LBB4_164: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xf6 // xor r14d, r14d - -LBB4_165: - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x2e394466 // cmp word [rsi], r13w - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3c // movzx r10d, byte [r12 + rdi] - WORD $0x8944; BYTE $0xf1 // mov ecx, r14d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x02c68349 // add r14, 2 - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - WORD $0xda30 // xor dl, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0xd830 // xor al, bl - LONG $0x3c048841 // mov byte [r12 + rdi], al - WORD $0x394d; BYTE $0xf1 // cmp r9, r14 - JNE LBB4_165 - -LBB4_166: - LONG $0x01c0f641 // test r8b, 1 - JE LBB4_174 - LONG $0x2e394466 // cmp word [rsi], r13w - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xf2 // mov rdx, r14 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x143c8a41 // mov dil, byte [r12 + rdx] - LONG $0x07e68041 // and r14b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xf1 // mov ecx, r14d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - JMP LBB4_173 + JMP LBB4_208 -LBB4_168: +LBB4_194: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB4_169: +LBB4_195: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al @@ -21613,14 +22299,14 @@ LBB4_169: WORD $0xda30 // xor dl, bl LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB4_169 + JNE LBB4_195 -LBB4_170: +LBB4_196: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_174 + JE LBB4_208 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 -LBB4_172: +LBB4_198: WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xda // mov rdx, r11 @@ -21631,23 +22317,17 @@ LBB4_172: WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - -LBB4_173: - LONG $0x141c8841 // mov byte [r12 + rdx], bl - -LBB4_174: - MOVQ 320(SP), SP - RET + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xf3 // xor bl, sil + JMP LBB4_207 -LBB4_175: +LBB4_199: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0xf631 // xor esi, esi - WORD $0x894d; BYTE $0xfe // mov r14, r15 + WORD $0x894d; BYTE $0xee // mov r14, r13 -LBB4_176: +LBB4_200: WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd2 // setne dl @@ -21679,1138 +22359,672 @@ LBB4_176: WORD $0x3044; BYTE $0xd8 // xor al, r11b LONG $0x3e048841 // mov byte [r14 + rdi], al WORD $0x3949; BYTE $0xf1 // cmp r9, rsi - JNE LBB4_176 + JNE LBB4_200 -LBB4_177: +LBB4_201: + LONG $0x01c0f641 // test r8b, 1 + JE LBB4_208 + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x03e8c148 // shr rax, 3 + LONG $0x057c8a41; BYTE $0x00 // mov dil, byte [r13 + rax] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xfa // xor dl, dil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x055c8841; BYTE $0x00 // mov byte [r13 + rax], bl + JMP LBB4_208 + +LBB4_203: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + +LBB4_204: + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x14b60f45; BYTE $0x3c // movzx r10d, byte [r12 + rdi] + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x02c68349 // add r14, 2 + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w + LONG $0x04768d48 // lea rsi, [rsi + 4] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + WORD $0xda30 // xor dl, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd020 // and al, dl + WORD $0xd830 // xor al, bl + LONG $0x3c048841 // mov byte [r12 + rdi], al + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB4_204 + +LBB4_205: LONG $0x01c0f641 // test r8b, 1 - JE LBB4_174 - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x03e8c148 // shr rax, 3 - LONG $0x073c8a41 // mov dil, byte [r15 + rax] - LONG $0x07e68040 // and sil, 7 + JE LBB4_208 + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x143c8a41 // mov dil, byte [r12 + rdx] + LONG $0x07e68041 // and r14b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xfa // xor dl, dil - WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x071c8841 // mov byte [r15 + rax], bl - JMP LBB4_174 -LBB4_179: - LONG $0xf0e28349 // and r10, -16 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000013024848948 // mov qword [rsp + 304], rax - QUAD $0x000000d82494894c // mov qword [rsp + 216], r10 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - LONG $0xc3b60f41 // movzx eax, r11b - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000120248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm1 - WORD $0xc031 // xor eax, eax - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 +LBB4_207: + LONG $0x141c8841 // mov byte [r12 + rdx], bl -LBB4_180: - WORD $0x8949; BYTE $0xc1 // mov r9, rax - QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x05e1c148 // shl rcx, 5 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0x8949; BYTE $0xcd // mov r13, rcx - WORD $0x8948; BYTE $0xcb // mov rbx, rcx - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0x8949; BYTE $0xcf // mov r15, rcx - WORD $0x8948; BYTE $0xcf // mov rdi, rcx +LBB4_208: + MOVQ 288(SP), SP + RET + +LBB4_209: WORD $0x8949; BYTE $0xc9 // mov r9, rcx - LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - WORD $0x8948; BYTE $0xca // mov rdx, rcx - LONG $0x0e0cb60f // movzx ecx, byte [rsi + rcx] - LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x164cb60f; BYTE $0x01 // movzx ecx, byte [rsi + rdx + 1] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x164cb60f; BYTE $0x02 // movzx ecx, byte [rsi + rdx + 2] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x164cb60f; BYTE $0x03 // movzx ecx, byte [rsi + rdx + 3] - LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x164cb60f; BYTE $0x04 // movzx ecx, byte [rsi + rdx + 4] - LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x164cb60f; BYTE $0x05 // movzx ecx, byte [rsi + rdx + 5] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x164cb60f; BYTE $0x06 // movzx ecx, byte [rsi + rdx + 6] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x164cb60f; BYTE $0x07 // movzx ecx, byte [rsi + rdx + 7] - LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x164cb60f; BYTE $0x08 // movzx ecx, byte [rsi + rdx + 8] - LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x164cb60f; BYTE $0x09 // movzx ecx, byte [rsi + rdx + 9] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 - LONG $0x164cb60f; BYTE $0x0a // movzx ecx, byte [rsi + rdx + 10] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x164cb60f; BYTE $0x0b // movzx ecx, byte [rsi + rdx + 11] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x164cb60f; BYTE $0x0c // movzx ecx, byte [rsi + rdx + 12] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x164cb60f; BYTE $0x0d // movzx ecx, byte [rsi + rdx + 13] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x164cb60f; BYTE $0x0e // movzx ecx, byte [rsi + rdx + 14] - LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x164cb60f; BYTE $0x0f // movzx ecx, byte [rsi + rdx + 15] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 - LONG $0x24548948; BYTE $0x20 // mov qword [rsp + 32], rdx - WORD $0x8948; BYTE $0xd1 // mov rcx, rdx - LONG $0x20c98348 // or rcx, 32 - LONG $0x244c8948; BYTE $0x18 // mov qword [rsp + 24], rcx - LONG $0x40cb8349 // or r11, 64 - LONG $0x245c894c; BYTE $0x70 // mov qword [rsp + 112], r11 - LONG $0x60c88349 // or r8, 96 - LONG $0x2444894c; BYTE $0x40 // mov qword [rsp + 64], r8 - LONG $0x80ce8149; WORD $0x0000; BYTE $0x00 // or r14, 128 - LONG $0xa0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 160 - WORD $0x8949; BYTE $0xda // mov r10, rbx - LONG $0xc0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 192 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - LONG $0xe0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 224 - LONG $0x00cf8149; WORD $0x0001; BYTE $0x00 // or r15, 256 - LONG $0x20cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 288 - QUAD $0x000000e024bc8948 // mov qword [rsp + 224], rdi - LONG $0x40c98149; WORD $0x0001; BYTE $0x00 // or r9, 320 - LONG $0x244c894c; BYTE $0x28 // mov qword [rsp + 40], r9 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - LONG $0x60cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 352 - LONG $0x245c8948; BYTE $0x30 // mov qword [rsp + 48], rbx - LONG $0x01800d48; WORD $0x0000 // or rax, 384 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - WORD $0x8948; BYTE $0xd1 // mov rcx, rdx - LONG $0xc0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 448 - LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx - WORD $0x8948; BYTE $0xd1 // mov rcx, rdx - LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 - LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - LONG $0x203a0f66; WORD $0x1624; BYTE $0x01 // pinsrb xmm4, byte [rsi + rdx], 1 - QUAD $0x021e24203a0f4266 // pinsrb xmm4, byte [rsi + r11], 2 - QUAD $0x030624203a0f4266 // pinsrb xmm4, byte [rsi + r8], 3 - QUAD $0x043624203a0f4266 // pinsrb xmm4, byte [rsi + r14], 4 - QUAD $0x052e24203a0f4266 // pinsrb xmm4, byte [rsi + r13], 5 - QUAD $0x061624203a0f4266 // pinsrb xmm4, byte [rsi + r10], 6 - QUAD $0x072624203a0f4266 // pinsrb xmm4, byte [rsi + r12], 7 - QUAD $0x083e24203a0f4266 // pinsrb xmm4, byte [rsi + r15], 8 - LONG $0x203a0f66; WORD $0x3e24; BYTE $0x09 // pinsrb xmm4, byte [rsi + rdi], 9 - QUAD $0x0a0e24203a0f4266 // pinsrb xmm4, byte [rsi + r9], 10 - LONG $0x203a0f66; WORD $0x1e24; BYTE $0x0b // pinsrb xmm4, byte [rsi + rbx], 11 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - LONG $0x203a0f66; WORD $0x1624; BYTE $0x0c // pinsrb xmm4, byte [rsi + rdx], 12 - LONG $0x203a0f66; WORD $0x0624; BYTE $0x0d // pinsrb xmm4, byte [rsi + rax], 13 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - LONG $0x203a0f66; WORD $0x1e24; BYTE $0x0e // pinsrb xmm4, byte [rsi + rbx], 14 - LONG $0x203a0f66; WORD $0x0e24; BYTE $0x0f // pinsrb xmm4, byte [rsi + rcx], 15 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x01011e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 1], 1 - QUAD $0x011e5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rsi + r11 + 1], 2 - QUAD $0x01065c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r8 + 1], 3 - QUAD $0x01365c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r14 + 1], 4 - QUAD $0x012e5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r13 + 1], 5 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - QUAD $0x01165c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r10 + 1], 6 - QUAD $0x01265c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r12 + 1], 7 - WORD $0x894d; BYTE $0xe5 // mov r13, r12 - QUAD $0x013e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r15 + 1], 8 - QUAD $0x09013e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 1], 9 - QUAD $0x010e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r9 + 1], 10 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x01265c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r12 + 1], 11 - QUAD $0x0c01165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 1], 12 - QUAD $0x0d01065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 1], 13 - WORD $0x8949; BYTE $0xc0 // mov r8, rax - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e01065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 1], 14 - QUAD $0x00012024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 288] - LONG $0xe6740f66 // pcmpeqb xmm4, xmm6 - QUAD $0x0f010e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 1], 15 - LONG $0xde740f66 // pcmpeqb xmm3, xmm6 - QUAD $0x00000100856f0f66 // movdqa xmm0, oword 256[rbp] /* [rip + .LCPI4_16] */ - LONG $0xd8df0f66 // pandn xmm3, xmm0 - LONG $0xdcfc0f66 // paddb xmm3, xmm4 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - LONG $0x0654b60f; BYTE $0x10 // movzx edx, byte [rsi + rax + 16] - LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0102066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 2], 1 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x02166c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rsi + r10 + 2], 2 - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x03023e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 2], 3 - QUAD $0x02366c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r14 + 2], 4 - QUAD $0x021e6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r11 + 2], 5 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x020e6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r9 + 2], 6 - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - QUAD $0x022e6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r13 + 2], 7 - QUAD $0x023e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r15 + 2], 8 - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - QUAD $0x0902166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 2], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a02066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 2], 10 - QUAD $0x02266c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r12 + 2], 11 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0c020e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 2], 12 - QUAD $0x02066c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r8 + 2], 13 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x022e6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rsi + r13 + 2], 14 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x02066c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r8 + 2], 15 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0103067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 3], 1 - QUAD $0x03167c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rsi + r10 + 3], 2 - QUAD $0x03033e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 3], 3 - QUAD $0x03367c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r14 + 3], 4 - QUAD $0x031e7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r11 + 3], 5 - QUAD $0x030e7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rsi + r9 + 3], 6 - QUAD $0x07031e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 3], 7 - QUAD $0x033e7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r15 + 3], 8 - QUAD $0x0903167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 3], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a03067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 3], 10 - QUAD $0x03267c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r12 + 3], 11 - QUAD $0x0c030e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 3], 12 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0d03067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 3], 13 - QUAD $0x032e7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rsi + r13 + 3], 14 - QUAD $0x03067c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r8 + 3], 15 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0104064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 4], 1 - QUAD $0x04164c203a0f4266; BYTE $0x02 // pinsrb xmm1, byte [rsi + r10 + 4], 2 - QUAD $0x03043e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 4], 3 - QUAD $0x04364c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r14 + 4], 4 - QUAD $0x041e4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r11 + 4], 5 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x040e4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rsi + r9 + 4], 6 - QUAD $0x07041e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 4], 7 - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - QUAD $0x043e4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r15 + 4], 8 - QUAD $0x0904164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 4], 9 - WORD $0x8948; BYTE $0xd3 // mov rbx, rdx - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0a04164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 4], 10 - QUAD $0x04264c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r12 + 4], 11 - QUAD $0x0c040e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 4], 12 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x041e4c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r11 + 4], 13 - QUAD $0x042e4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r13 + 4], 14 - QUAD $0x04064c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r8 + 4], 15 - LONG $0xee740f66 // pcmpeqb xmm5, xmm6 - QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI4_17] */ - LONG $0xe8df0f66 // pandn xmm5, xmm0 - LONG $0xfe740f66 // pcmpeqb xmm7, xmm6 - QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI4_18] */ - LONG $0xf8df0f66 // pandn xmm7, xmm0 + LONG $0xfce18349 // and r9, -4 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + LONG $0x07e3c148 // shl rbx, 7 + WORD $0x0148; BYTE $0xf3 // add rbx, rsi + LONG $0x8c2c8d4f // lea r13, [r12 + 4*r9] + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0x00c8c60f // shufps xmm1, xmm0, 0 + LONG $0xfcc68148; WORD $0x0001; BYTE $0x00 // add rsi, 508 + WORD $0xd231 // xor edx, edx + LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI4_0] */ + LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI4_1] */ + LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI4_2] */ + LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI4_3] */ + LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI4_4] */ + LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI4_5] */ + LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI4_6] */ + LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI4_7] */ + +LBB4_210: + QUAD $0xfffffe04b6100ff3 // movss xmm6, dword [rsi - 508] + QUAD $0xfffffe08be100ff3 // movss xmm7, dword [rsi - 504] + QUAD $0xfffffe0cae100ff3 // movss xmm5, dword [rsi - 500] + QUAD $0xfffffe10a6100ff3 // movss xmm4, dword [rsi - 496] + QUAD $0xfffe84b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 380], 16 + QUAD $0xffff04b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 252], 32 + LONG $0x213a0f66; WORD $0x8476; BYTE $0x30 // insertps xmm6, dword [rsi - 124], 48 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + QUAD $0xfffe88be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 376], 16 + QUAD $0xffff08be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 248], 32 + LONG $0x213a0f66; WORD $0x887e; BYTE $0x30 // insertps xmm7, dword [rsi - 120], 48 + QUAD $0xfffe8cae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 372], 16 + QUAD $0xffff0cae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 244], 32 + LONG $0x213a0f66; WORD $0x8c6e; BYTE $0x30 // insertps xmm5, dword [rsi - 116], 48 + QUAD $0xfffe90a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 368], 16 + QUAD $0xffff10a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 240], 32 + LONG $0x213a0f66; WORD $0x9066; BYTE $0x30 // insertps xmm4, dword [rsi - 112], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xd76f0f66 // movdqa xmm2, xmm7 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xd7f80f66 // psubb xmm2, xmm7 + QUAD $0xfffffe14be100ff3 // movss xmm7, dword [rsi - 492] + QUAD $0xfffe94be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 364], 16 + QUAD $0xffff14be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 236], 32 + LONG $0x213a0f66; WORD $0x947e; BYTE $0x30 // insertps xmm7, dword [rsi - 108], 48 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe18b6100ff3 // movss xmm6, dword [rsi - 488] + QUAD $0xfffe98b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 360], 16 + QUAD $0xffff18b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 232], 32 + LONG $0x213a0f66; WORD $0x9876; BYTE $0x30 // insertps xmm6, dword [rsi - 104], 48 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 + LONG $0xeaeb0f66 // por xmm5, xmm2 + QUAD $0xfffffe1c9e100ff3 // movss xmm3, dword [rsi - 484] + QUAD $0xfffe9c9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 356], 16 + QUAD $0xffff1c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 228], 32 + LONG $0x213a0f66; WORD $0x9c5e; BYTE $0x30 // insertps xmm3, dword [rsi - 100], 48 + LONG $0x04e1c20f // cmpneqps xmm4, xmm1 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + LONG $0xf4710f66; BYTE $0x03 // psllw xmm4, 3 + LONG $0xdb0f4166; BYTE $0xe2 // pand xmm4, xmm10 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x04 // psllw xmm7, 4 + LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 + LONG $0xfceb0f66 // por xmm7, xmm4 + QUAD $0xfffffe20a6100ff3 // movss xmm4, dword [rsi - 480] + QUAD $0xfffea0a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 352], 16 + QUAD $0xffff20a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 224], 32 + LONG $0x213a0f66; WORD $0xa066; BYTE $0x30 // insertps xmm4, dword [rsi - 96], 48 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - LONG $0x0e54b60f; BYTE $0x11 // movzx edx, byte [rsi + rcx + 17] - LONG $0xe26e0f66 // movd xmm4, edx - LONG $0xce740f66 // pcmpeqb xmm1, xmm6 - QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI4_19] */ - LONG $0xc8df0f66 // pandn xmm1, xmm0 - LONG $0xcfeb0f66 // por xmm1, xmm7 - LONG $0x0e54b60f; BYTE $0x12 // movzx edx, byte [rsi + rcx + 18] - LONG $0xfa6e0f66 // movd xmm7, edx - LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 - LONG $0xd8f80f66 // psubb xmm3, xmm0 - LONG $0xcbeb0f66 // por xmm1, xmm3 - LONG $0x0e54b60f; BYTE $0x13 // movzx edx, byte [rsi + rcx + 19] - LONG $0xea6e0f66 // movd xmm5, edx - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x01051654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 5], 1 - QUAD $0x051654203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rsi + r10 + 5], 2 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x03050e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 5], 3 - LONG $0x2474894c; BYTE $0x78 // mov qword [rsp + 120], r14 - QUAD $0x053654203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r14 + 5], 4 - QUAD $0x05050654203a0f66 // pinsrb xmm2, byte [rsi + rax + 5], 5 - WORD $0x894d; BYTE $0xcc // mov r12, r9 - QUAD $0x050e54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r9 + 5], 6 - QUAD $0x000000a024bc8948 // mov qword [rsp + 160], rdi - QUAD $0x07053e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 5], 7 - QUAD $0x053e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r15 + 5], 8 - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - QUAD $0x09051e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 5], 9 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a050654203a0f66 // pinsrb xmm2, byte [rsi + rax + 5], 10 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0b050e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 5], 11 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x052e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r13 + 5], 12 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - QUAD $0x051e54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r11 + 5], 13 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e050e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 5], 14 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x051e54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r11 + 5], 15 - QUAD $0x061644203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rdx + 6], 1 - QUAD $0x061644203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rsi + r10 + 6], 2 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x061e44203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rbx + 6], 3 - QUAD $0x063644203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r14 + 6], 4 - QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] - QUAD $0x061e44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rsi + rbx + 6], 5 - QUAD $0x062644203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rsi + r12 + 6], 6 - QUAD $0x063e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rdi + 6], 7 - QUAD $0x063e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r15 + 6], 8 - QUAD $0x060e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r9 + 6], 9 - QUAD $0x060644203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rsi + rax + 6], 10 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x061e44203a0f4466; BYTE $0x0b // pinsrb xmm8, byte [rsi + rbx + 6], 11 - QUAD $0x062e44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r13 + 6], 12 - QUAD $0x060644203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r8 + 6], 13 - QUAD $0x060e44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rcx + 6], 14 - QUAD $0x061e44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r11 + 6], 15 - WORD $0x894c; BYTE $0xd9 // mov rcx, r11 - QUAD $0x071674203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rsi + rdx + 7], 1 - QUAD $0x071674203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rsi + r10 + 7], 2 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x071674203a0f4466; BYTE $0x03 // pinsrb xmm14, byte [rsi + rdx + 7], 3 - QUAD $0x073674203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rsi + r14 + 7], 4 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x071e74203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rsi + r11 + 7], 5 - QUAD $0x072674203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rsi + r12 + 7], 6 - QUAD $0x073e74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rsi + rdi + 7], 7 - QUAD $0x073e74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r15 + 7], 8 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - LONG $0x247c894c; BYTE $0x60 // mov qword [rsp + 96], r15 - QUAD $0x070e74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r9 + 7], 9 - QUAD $0x070674203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rsi + rax + 7], 10 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x071e74203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rsi + rbx + 7], 11 - QUAD $0x072e74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rsi + r13 + 7], 12 - WORD $0x894d; BYTE $0xee // mov r14, r13 - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - QUAD $0x070674203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rsi + r8 + 7], 13 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x072e74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rsi + r13 + 7], 14 - LONG $0xd6740f66 // pcmpeqb xmm2, xmm6 - QUAD $0x00000140856f0f66 // movdqa xmm0, oword 320[rbp] /* [rip + .LCPI4_20] */ - LONG $0xd0df0f66 // pandn xmm2, xmm0 - LONG $0x740f4466; BYTE $0xc6 // pcmpeqb xmm8, xmm6 - QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI4_21] */ - LONG $0xdf0f4466; BYTE $0xc0 // pandn xmm8, xmm0 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] - LONG $0x54b60f42; WORD $0x140e // movzx edx, byte [rsi + r9 + 20] - LONG $0xda6e0f66 // movd xmm3, edx - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x070e74203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rsi + rcx + 7], 15 - LONG $0x740f4466; BYTE $0xf6 // pcmpeqb xmm14, xmm6 - LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI4_6] */ - LONG $0xdf0f4466; BYTE $0xf0 // pandn xmm14, xmm0 - LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 - LONG $0x54b60f42; WORD $0x150e // movzx edx, byte [rsi + r9 + 21] - LONG $0xd26e0f66 // movd xmm2, edx - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x080e4c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rcx + 8], 1 - QUAD $0x08164c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rsi + r10 + 8], 2 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x08064c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r8 + 8], 3 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x08164c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rsi + rdx + 8], 4 - QUAD $0x081e4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r11 + 8], 5 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x08164c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rdx + 8], 6 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x083e4c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rsi + r15 + 8], 7 - QUAD $0x08264c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r12 + 8], 8 - QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] - QUAD $0x08264c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r12 + 8], 9 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x08164c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rsi + rdx + 8], 10 - QUAD $0x081e4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rsi + rbx + 8], 11 - QUAD $0x08364c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r14 + 8], 12 - QUAD $0x083e4c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rsi + rdi + 8], 13 - QUAD $0x082e4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r13 + 8], 14 - QUAD $0x08064c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rsi + rax + 8], 15 - LONG $0xeb0f4466; BYTE $0xf1 // por xmm14, xmm1 - QUAD $0x011024b47f0f4466; WORD $0x0000 // movdqa oword [rsp + 272], xmm14 - LONG $0x54b60f42; WORD $0x160e // movzx edx, byte [rsi + r9 + 22] - LONG $0xca6e0f66 // movd xmm1, edx - LONG $0xc66f0f66 // movdqa xmm0, xmm6 - LONG $0x740f4466; BYTE $0xce // pcmpeqb xmm9, xmm6 - QUAD $0x00c024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 192] - QUAD $0x090e74203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rsi + rcx + 9], 1 - QUAD $0x091674203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rsi + r10 + 9], 2 - QUAD $0x090674203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rsi + r8 + 9], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x090674203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rsi + rax + 9], 4 - QUAD $0x091e74203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rsi + r11 + 9], 5 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x091674203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rsi + rdx + 9], 6 - WORD $0x894c; BYTE $0xff // mov rdi, r15 - QUAD $0x093e74203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rsi + r15 + 9], 7 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x093e74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r15 + 9], 8 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - QUAD $0x092674203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r12 + 9], 9 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x092e74203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rsi + r13 + 9], 10 - QUAD $0x091e74203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rsi + rbx + 9], 11 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - QUAD $0x093674203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rsi + r14 + 9], 12 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x093674203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rsi + r14 + 9], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x090674203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rsi + rax + 9], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090674203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rsi + rax + 9], 15 - WORD $0x8949; BYTE $0xca // mov r10, rcx - QUAD $0x0a0e64203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rcx + 10], 1 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0a0e64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rcx + 10], 2 - QUAD $0x0a0664203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rsi + r8 + 10], 3 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x0a0e64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rsi + rcx + 10], 4 - QUAD $0x0a1e64203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r11 + 10], 5 - QUAD $0x0a1664203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rdx + 10], 6 - QUAD $0x0a3e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rdi + 10], 7 - QUAD $0x0a3e64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r15 + 10], 8 - QUAD $0x0a0e64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r9 + 10], 9 - QUAD $0x0a2e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r13 + 10], 10 - QUAD $0x0a1e64203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rsi + rbx + 10], 11 - QUAD $0x0a2664203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r12 + 10], 12 - QUAD $0x0a3664203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rsi + r14 + 10], 13 - LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] - QUAD $0x0a3664203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r14 + 10], 14 - QUAD $0x0a0664203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rsi + rax + 10], 15 - QUAD $0x0b166c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rsi + r10 + 11], 1 - LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] - QUAD $0x0b166c203a0f4666; BYTE $0x02 // pinsrb xmm13, byte [rsi + r10 + 11], 2 - QUAD $0x0b066c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rsi + r8 + 11], 3 - QUAD $0x0b0e6c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rsi + rcx + 11], 4 - QUAD $0x0b1e6c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rsi + r11 + 11], 5 - QUAD $0x0b166c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rsi + rdx + 11], 6 - QUAD $0x0b3e6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rsi + rdi + 11], 7 - QUAD $0x0b3e6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r15 + 11], 8 - QUAD $0x0b0e6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r9 + 11], 9 - QUAD $0x0b2e6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rsi + r13 + 11], 10 - QUAD $0x0b1e6c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rsi + rbx + 11], 11 - WORD $0x8949; BYTE $0xdf // mov r15, rbx - QUAD $0x0b266c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r12 + 11], 12 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0b2e6c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rsi + r13 + 11], 13 - QUAD $0x0b366c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r14 + 11], 14 - QUAD $0x0b066c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rsi + rax + 11], 15 - LONG $0x740f4466; BYTE $0xf6 // pcmpeqb xmm14, xmm6 - QUAD $0x000100b5df0f4466; BYTE $0x00 // pandn xmm14, oword 256[rbp] /* [rip + .LCPI4_16] */ - LONG $0xfc0f4566; BYTE $0xf1 // paddb xmm14, xmm9 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - LONG $0x0654b60f; BYTE $0x17 // movzx edx, byte [rsi + rax + 23] - LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - LONG $0x740f4466; BYTE $0xe6 // pcmpeqb xmm12, xmm6 - QUAD $0x000110a5df0f4466; BYTE $0x00 // pandn xmm12, oword 272[rbp] /* [rip + .LCPI4_17] */ - LONG $0x740f4466; BYTE $0xee // pcmpeqb xmm13, xmm6 - QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI4_18] */ - LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - LONG $0x0654b60f; BYTE $0x18 // movzx edx, byte [rsi + rax + 24] - LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx - QUAD $0x00f0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 240] - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0c064c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rax + 12], 1 - QUAD $0x0c164c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rsi + r10 + 12], 2 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x0c064c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r8 + 12], 3 - WORD $0x8949; BYTE $0xce // mov r14, rcx - QUAD $0x0c0e4c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rsi + rcx + 12], 4 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - QUAD $0x0c1e4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r11 + 12], 5 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x0c1e4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rsi + r11 + 12], 6 - WORD $0x8948; BYTE $0xfb // mov rbx, rdi - QUAD $0x0c3e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rdi + 12], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0c0e4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rsi + rcx + 12], 8 - QUAD $0x0c0e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r9 + 12], 9 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0c3e4c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rsi + rdi + 12], 10 - QUAD $0x0c3e4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r15 + 12], 11 - QUAD $0x0c264c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r12 + 12], 12 - QUAD $0x0c2e4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r13 + 12], 13 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0c164c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rsi + rdx + 12], 14 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0c164c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rsi + rdx + 12], 15 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0d165c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rdx + 13], 1 - QUAD $0x0d165c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rsi + r10 + 13], 2 - QUAD $0x0d065c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rsi + rax + 13], 3 - QUAD $0x0d365c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r14 + 13], 4 - QUAD $0x0d065c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r8 + 13], 5 - QUAD $0x0d1e5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rsi + r11 + 13], 6 - QUAD $0x0d1e5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rsi + rbx + 13], 7 - QUAD $0x0d0e5c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rsi + rcx + 13], 8 - QUAD $0x0d0e5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r9 + 13], 9 - QUAD $0x0d3e5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rsi + rdi + 13], 10 - QUAD $0x0d3e5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r15 + 13], 11 - QUAD $0x0d265c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r12 + 13], 12 - QUAD $0x0d2e5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rsi + r13 + 13], 13 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0d165c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rsi + rdx + 13], 14 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0d165c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rsi + rdx + 13], 15 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0e167c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rdx + 14], 1 - QUAD $0x0e167c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rsi + r10 + 14], 2 - QUAD $0x0e067c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rsi + rax + 14], 3 - QUAD $0x0e367c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rsi + r14 + 14], 4 - QUAD $0x0e067c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rsi + r8 + 14], 5 - QUAD $0x0e1e7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rsi + r11 + 14], 6 - QUAD $0x0e1e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rbx + 14], 7 - QUAD $0x0e0e7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rsi + rcx + 14], 8 - QUAD $0x0e0e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r9 + 14], 9 - QUAD $0x0e3e7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rsi + rdi + 14], 10 - QUAD $0x0e3e7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r15 + 14], 11 - QUAD $0x0e267c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r12 + 14], 12 - QUAD $0x0e2e7c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rsi + r13 + 14], 13 - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x0e3e7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r15 + 14], 14 - LONG $0x740f4466; BYTE $0xce // pcmpeqb xmm9, xmm6 - QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI4_19] */ - LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - LONG $0x0e54b60f; BYTE $0x19 // movzx edx, byte [rsi + rcx + 25] - LONG $0x6e0f4466; BYTE $0xea // movd xmm13, edx - QUAD $0x000160b5f80f4466; BYTE $0x00 // psubb xmm14, oword 352[rbp] /* [rip + .LCPI4_22] */ - LONG $0xeb0f4566; BYTE $0xce // por xmm9, xmm14 - LONG $0x0e54b60f; BYTE $0x1a // movzx edx, byte [rsi + rcx + 26] - LONG $0xc26e0f66 // movd xmm0, edx - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0e067c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rsi + rax + 14], 15 - LONG $0x740f4466; BYTE $0xde // pcmpeqb xmm11, xmm6 - QUAD $0x0001409ddf0f4466; BYTE $0x00 // pandn xmm11, oword 320[rbp] /* [rip + .LCPI4_20] */ - LONG $0x740f4466; BYTE $0xfe // pcmpeqb xmm15, xmm6 - LONG $0x6f0f4466; BYTE $0xf6 // movdqa xmm14, xmm6 - QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI4_21] */ - LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 - LONG $0x0e54b60f; BYTE $0x1b // movzx edx, byte [rsi + rcx + 27] - LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx - QUAD $0x0000b024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 176] - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - QUAD $0x0f1e74203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r11 + 15], 1 - QUAD $0x0f1674203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rsi + r10 + 15], 2 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x030f1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 15], 3 - QUAD $0x0f3674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r14 + 15], 4 - QUAD $0x0f0674203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r8 + 15], 5 - LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] - QUAD $0x0f2674203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r12 + 15], 6 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x070f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 15], 7 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x080f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 15], 8 - QUAD $0x0f0e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r9 + 15], 9 - QUAD $0x0a0f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 15], 10 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0b0f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 15], 11 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0f3674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r14 + 15], 12 - QUAD $0x0f2e74203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r13 + 15], 13 - QUAD $0x0f3e74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r15 + 15], 14 - QUAD $0x0f0f0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 15], 15 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI4_6] */ - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - LONG $0x0654b60f; BYTE $0x1c // movzx edx, byte [rsi + rax + 28] - LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 - QUAD $0x0000b024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm6 - LONG $0x0654b60f; BYTE $0x1d // movzx edx, byte [rsi + rax + 29] - LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx - QUAD $0x101e54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r11 + 16], 1 - QUAD $0x101654203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r10 + 16], 2 - QUAD $0x101e54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rbx + 16], 3 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x102e54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r13 + 16], 4 - QUAD $0x100654203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r8 + 16], 5 - QUAD $0x102654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r12 + 16], 6 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x102654203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r12 + 16], 7 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x101654203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rsi + rdx + 16], 8 - QUAD $0x100e54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r9 + 16], 9 - QUAD $0x103e54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rdi + 16], 10 - QUAD $0x100e54203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rsi + rcx + 16], 11 - QUAD $0x103654203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r14 + 16], 12 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x103654203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r14 + 16], 13 - QUAD $0x103e54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r15 + 16], 14 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x100654203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rsi + rax + 16], 15 - QUAD $0x111e64203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r11 + 17], 1 - QUAD $0x111664203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r10 + 17], 2 - QUAD $0x03111e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 17], 3 - WORD $0x894d; BYTE $0xea // mov r10, r13 - QUAD $0x112e64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r13 + 17], 4 - QUAD $0x110664203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r8 + 17], 5 - LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] - QUAD $0x111e64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r11 + 17], 6 - WORD $0x894c; BYTE $0xe3 // mov rbx, r12 - QUAD $0x112664203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r12 + 17], 7 - QUAD $0x08111664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 17], 8 - QUAD $0x110e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r9 + 17], 9 - QUAD $0x0a113e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 17], 10 - QUAD $0x0b110e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 17], 11 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0c110e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 17], 12 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - QUAD $0x113664203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r14 + 17], 13 - QUAD $0x113e64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r15 + 17], 14 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - QUAD $0x0f110664203a0f66 // pinsrb xmm4, byte [rsi + rax + 17], 15 - WORD $0x8949; BYTE $0xc7 // mov r15, rax - LONG $0x6f0f4166; BYTE $0xf6 // movdqa xmm6, xmm14 - LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 - LONG $0x740f4166; BYTE $0xe6 // pcmpeqb xmm4, xmm14 - QUAD $0x00000100a5df0f66 // pandn xmm4, oword 256[rbp] /* [rip + .LCPI4_16] */ - LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - LONG $0x3e54b60f; BYTE $0x1e // movzx edx, byte [rsi + rdi + 30] - LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0112067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 18], 1 - QUAD $0x0113066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 1 - QUAD $0x0114065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 20], 1 - QUAD $0x01150654203a0f66 // pinsrb xmm2, byte [rsi + rax + 21], 1 - QUAD $0x0116064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 22], 1 - QUAD $0x170644203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rax + 23], 1 - QUAD $0x180664203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rax + 24], 1 - QUAD $0x19066c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rsi + rax + 25], 1 - QUAD $0x011a0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 26], 1 - QUAD $0x1b065c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rax + 27], 1 - QUAD $0x1c067c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rax + 28], 1 - QUAD $0x1d064c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rax + 29], 1 - QUAD $0x1e0654203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rax + 30], 1 - LONG $0x3e54b60f; BYTE $0x1f // movzx edx, byte [rsi + rdi + 31] - LONG $0xf26e0f66 // movd xmm6, edx - QUAD $0x011f0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 31], 1 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0212167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 18], 2 - QUAD $0x0213166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 19], 2 - QUAD $0x0214165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 20], 2 - QUAD $0x02151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 2 - QUAD $0x0216164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 22], 2 - QUAD $0x171644203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rdx + 23], 2 - QUAD $0x181664203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rdx + 24], 2 - QUAD $0x19166c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rdx + 25], 2 - QUAD $0x021a1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 26], 2 - QUAD $0x1b165c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rdx + 27], 2 - QUAD $0x1c167c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rsi + rdx + 28], 2 - QUAD $0x1d164c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rdx + 29], 2 - QUAD $0x1e1654203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rdx + 30], 2 - QUAD $0x021f1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 31], 2 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x0312167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 18], 3 - WORD $0x894d; BYTE $0xd6 // mov r14, r10 - QUAD $0x12167c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r10 + 18], 4 - QUAD $0x12067c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r8 + 18], 5 - QUAD $0x121e7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rsi + r11 + 18], 6 - QUAD $0x07121e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 18], 7 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0812067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 18], 8 - QUAD $0x120e7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r9 + 18], 9 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0a123e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 18], 10 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x12167c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r10 + 18], 11 - QUAD $0x0c120e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 18], 12 - QUAD $0x122e7c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r13 + 18], 13 - QUAD $0x12267c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rsi + r12 + 18], 14 - QUAD $0x123e7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r15 + 18], 15 - QUAD $0x0313166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 19], 3 - QUAD $0x13366c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r14 + 19], 4 - QUAD $0x13066c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r8 + 19], 5 - QUAD $0x131e6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r11 + 19], 6 - QUAD $0x07131e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 19], 7 - QUAD $0x0813066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 8 - QUAD $0x130e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r9 + 19], 9 - QUAD $0x0a133e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 19], 10 - QUAD $0x13166c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r10 + 19], 11 - QUAD $0x0c130e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 19], 12 - QUAD $0x132e6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r13 + 19], 13 - QUAD $0x13266c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rsi + r12 + 19], 14 - QUAD $0x133e6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r15 + 19], 15 - QUAD $0x0314165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 20], 3 - QUAD $0x14365c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r14 + 20], 4 - QUAD $0x14065c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r8 + 20], 5 - QUAD $0x141e5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r11 + 20], 6 - QUAD $0x07141e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 20], 7 - QUAD $0x0814065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 20], 8 - QUAD $0x140e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r9 + 20], 9 - QUAD $0x0a143e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 20], 10 - QUAD $0x14165c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r10 + 20], 11 - QUAD $0x0c140e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 20], 12 - QUAD $0x142e5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r13 + 20], 13 - QUAD $0x14265c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rsi + r12 + 20], 14 - LONG $0x740f4166; BYTE $0xfe // pcmpeqb xmm7, xmm14 - QUAD $0x00000110bddf0f66 // pandn xmm7, oword 272[rbp] /* [rip + .LCPI4_17] */ - LONG $0x740f4166; BYTE $0xee // pcmpeqb xmm5, xmm14 - QUAD $0x00000120addf0f66 // pandn xmm5, oword 288[rbp] /* [rip + .LCPI4_18] */ - LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0x143e5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r15 + 20], 15 - LONG $0x740f4166; BYTE $0xde // pcmpeqb xmm3, xmm14 - QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI4_19] */ - LONG $0xdfdf0f66 // pandn xmm3, xmm7 - LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xed760f66 // pcmpeqd xmm5, xmm5 - LONG $0xe5f80f66 // psubb xmm4, xmm5 - LONG $0xdceb0f66 // por xmm3, xmm4 - QUAD $0x03151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 3 - QUAD $0x153654203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r14 + 21], 4 - QUAD $0x150654203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r8 + 21], 5 - QUAD $0x151e54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r11 + 21], 6 - QUAD $0x07151e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 21], 7 - QUAD $0x08150654203a0f66 // pinsrb xmm2, byte [rsi + rax + 21], 8 - QUAD $0x150e54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r9 + 21], 9 - QUAD $0x0a153e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 21], 10 - QUAD $0x151654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r10 + 21], 11 - QUAD $0x0c150e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 21], 12 - QUAD $0x152e54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r13 + 21], 13 - QUAD $0x152654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r12 + 21], 14 - QUAD $0x153e54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r15 + 21], 15 - QUAD $0x0316164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 22], 3 - QUAD $0x16364c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r14 + 22], 4 - QUAD $0x16064c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r8 + 22], 5 - QUAD $0x161e4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rsi + r11 + 22], 6 - QUAD $0x07161e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 22], 7 - QUAD $0x0816064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 22], 8 - QUAD $0x160e4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r9 + 22], 9 - QUAD $0x0a163e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 22], 10 - QUAD $0x16164c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r10 + 22], 11 - QUAD $0x0c160e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 22], 12 - QUAD $0x162e4c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r13 + 22], 13 - QUAD $0x16264c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r12 + 22], 14 - QUAD $0x163e4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r15 + 22], 15 - QUAD $0x171644203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rdx + 23], 3 - QUAD $0x173644203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r14 + 23], 4 - QUAD $0x170644203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r8 + 23], 5 - QUAD $0x171e44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rsi + r11 + 23], 6 - QUAD $0x171e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rbx + 23], 7 - QUAD $0x170644203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rsi + rax + 23], 8 - QUAD $0x170e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r9 + 23], 9 - QUAD $0x173e44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rsi + rdi + 23], 10 - QUAD $0x171644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r10 + 23], 11 - QUAD $0x170e44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rsi + rcx + 23], 12 - QUAD $0x172e44203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r13 + 23], 13 - QUAD $0x172644203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r12 + 23], 14 - LONG $0x6f0f4166; BYTE $0xe6 // movdqa xmm4, xmm14 - LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 - QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI4_20] */ - LONG $0xd5df0f66 // pandn xmm2, xmm5 - LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 - QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI4_21] */ - LONG $0xcfdf0f66 // pandn xmm1, xmm7 - LONG $0xcaeb0f66 // por xmm1, xmm2 - QUAD $0x173e44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r15 + 23], 15 - LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 - LONG $0x6f0f4166; BYTE $0xd6 // movdqa xmm2, xmm14 - LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI4_6] */ - LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - QUAD $0x181664203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rsi + rdx + 24], 3 - QUAD $0x183664203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rsi + r14 + 24], 4 - QUAD $0x180664203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r8 + 24], 5 - QUAD $0x181e64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rsi + r11 + 24], 6 - QUAD $0x181e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rbx + 24], 7 - QUAD $0x180664203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rsi + rax + 24], 8 - QUAD $0x180e64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r9 + 24], 9 - QUAD $0x183e64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rsi + rdi + 24], 10 - QUAD $0x181664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r10 + 24], 11 - QUAD $0x180e64203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rsi + rcx + 24], 12 - QUAD $0x182e64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rsi + r13 + 24], 13 - QUAD $0x182664203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r12 + 24], 14 - QUAD $0x183e64203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rsi + r15 + 24], 15 - LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 - QUAD $0x19166c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rsi + rdx + 25], 3 - QUAD $0x19366c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r14 + 25], 4 - QUAD $0x19066c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rsi + r8 + 25], 5 - QUAD $0x191e6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rsi + r11 + 25], 6 - QUAD $0x191e6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rsi + rbx + 25], 7 - QUAD $0x19066c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rsi + rax + 25], 8 - QUAD $0x190e6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r9 + 25], 9 - QUAD $0x193e6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rsi + rdi + 25], 10 - QUAD $0x19166c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r10 + 25], 11 - QUAD $0x190e6c203a0f4466; BYTE $0x0c // pinsrb xmm13, byte [rsi + rcx + 25], 12 - QUAD $0x192e6c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rsi + r13 + 25], 13 - QUAD $0x19266c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r12 + 25], 14 - QUAD $0x193e6c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rsi + r15 + 25], 15 - QUAD $0x031a1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 26], 3 - QUAD $0x1a3644203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r14 + 26], 4 - QUAD $0x1a0644203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r8 + 26], 5 - QUAD $0x1a1e44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rsi + r11 + 26], 6 - QUAD $0x071a1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 26], 7 - QUAD $0x081a0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 26], 8 - QUAD $0x1a0e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r9 + 26], 9 - QUAD $0x0a1a3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 26], 10 - QUAD $0x1a1644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r10 + 26], 11 - QUAD $0x0c1a0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 26], 12 - QUAD $0x1a2e44203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r13 + 26], 13 - QUAD $0x1a2644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r12 + 26], 14 - QUAD $0x1a3e44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r15 + 26], 15 - QUAD $0x1b165c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rsi + rdx + 27], 3 - QUAD $0x1b365c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r14 + 27], 4 - QUAD $0x1b065c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r8 + 27], 5 - QUAD $0x1b1e5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rsi + r11 + 27], 6 - QUAD $0x1b1e5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rsi + rbx + 27], 7 - QUAD $0x1b065c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rsi + rax + 27], 8 - QUAD $0x1b0e5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r9 + 27], 9 - QUAD $0x1b3e5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rsi + rdi + 27], 10 - QUAD $0x1b165c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r10 + 27], 11 - QUAD $0x1b0e5c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rsi + rcx + 27], 12 - QUAD $0x1b2e5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rsi + r13 + 27], 13 - QUAD $0x1b265c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rsi + r12 + 27], 14 - LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 - QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI4_16] */ - LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 - QUAD $0x1b3e5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rsi + r15 + 27], 15 - LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 - QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI4_17] */ - LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 - QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI4_18] */ - LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 - QUAD $0x1c167c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rsi + rdx + 28], 3 - QUAD $0x1d164c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rsi + rdx + 29], 3 - QUAD $0x1e1654203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rdx + 30], 3 - QUAD $0x031f1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 31], 3 - QUAD $0x1c367c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rsi + r14 + 28], 4 - QUAD $0x1d364c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rsi + r14 + 29], 4 - QUAD $0x1e3654203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r14 + 30], 4 - QUAD $0x1f3674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r14 + 31], 4 - QUAD $0x1c067c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rsi + r8 + 28], 5 - QUAD $0x1d064c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r8 + 29], 5 - QUAD $0x1e0654203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r8 + 30], 5 - QUAD $0x1f0674203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r8 + 31], 5 - WORD $0x894c; BYTE $0xda // mov rdx, r11 - QUAD $0x1c1e7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rsi + r11 + 28], 6 - QUAD $0x1d1e4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rsi + r11 + 29], 6 - QUAD $0x1e1e54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r11 + 30], 6 - QUAD $0x1f1e74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r11 + 31], 6 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - WORD $0x8948; BYTE $0xda // mov rdx, rbx - QUAD $0x1c1e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rbx + 28], 7 - QUAD $0x1d1e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rbx + 29], 7 - QUAD $0x1e1e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rbx + 30], 7 - QUAD $0x071f1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 31], 7 - QUAD $0x1c067c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rsi + rax + 28], 8 - QUAD $0x1d064c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rsi + rax + 29], 8 - QUAD $0x1e0654203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rsi + rax + 30], 8 - QUAD $0x081f0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 31], 8 - QUAD $0x1c0e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r9 + 28], 9 - QUAD $0x1d0e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r9 + 29], 9 - QUAD $0x1e0e54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r9 + 30], 9 - QUAD $0x1f0e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r9 + 31], 9 - QUAD $0x1c3e7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rsi + rdi + 28], 10 - QUAD $0x1d3e4c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rsi + rdi + 29], 10 - QUAD $0x1e3e54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rdi + 30], 10 - QUAD $0x0a1f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 31], 10 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x1c167c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r10 + 28], 11 - QUAD $0x1d164c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r10 + 29], 11 - QUAD $0x1e1654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r10 + 30], 11 - QUAD $0x1f1674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r10 + 31], 11 - QUAD $0x1c0e7c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rsi + rcx + 28], 12 - QUAD $0x1d0e4c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rsi + rcx + 29], 12 - QUAD $0x1e0e54203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rsi + rcx + 30], 12 - QUAD $0x0c1f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 31], 12 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x1c2e7c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rsi + r13 + 28], 13 - QUAD $0x1d2e4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r13 + 29], 13 - QUAD $0x1e2e54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r13 + 30], 13 - QUAD $0x1f2e74203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r13 + 31], 13 - WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x1c267c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r12 + 28], 14 - QUAD $0x1d264c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r12 + 29], 14 - QUAD $0x1e2654203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r12 + 30], 14 - QUAD $0x1f2674203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r12 + 31], 14 - QUAD $0x1c3e7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r15 + 28], 15 - QUAD $0x1d3e4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r15 + 29], 15 - QUAD $0x1e3e54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r15 + 30], 15 - LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 - QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI4_19] */ - LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 - QUAD $0x1f3e74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r15 + 31], 15 - QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI4_22] */ - LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 - LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 - LONG $0xdf0f4466; BYTE $0xcd // pandn xmm9, xmm5 - LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 - LONG $0xdf0f4466; BYTE $0xd7 // pandn xmm10, xmm7 - LONG $0xeb0f4566; BYTE $0xd1 // por xmm10, xmm9 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - LONG $0xf4df0f66 // pandn xmm6, xmm4 - LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0xc6600f66 // punpcklbw xmm0, xmm6 - QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] - LONG $0xcc6f0f66 // movdqa xmm1, xmm4 - QUAD $0x0000b0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 176] - LONG $0xcb600f66 // punpcklbw xmm1, xmm3 - LONG $0xd16f0f66 // movdqa xmm2, xmm1 - LONG $0xd0610f66 // punpcklwd xmm2, xmm0 - LONG $0xc8690f66 // punpckhwd xmm1, xmm0 - LONG $0x680f4466; BYTE $0xc6 // punpckhbw xmm8, xmm6 - LONG $0xe3680f66 // punpckhbw xmm4, xmm3 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x7f0f41f3; WORD $0x8864; BYTE $0x30 // movdqu oword [r8 + 4*rcx + 48], xmm4 - LONG $0x7f0f41f3; WORD $0x8844; BYTE $0x20 // movdqu oword [r8 + 4*rcx + 32], xmm0 - LONG $0x7f0f41f3; WORD $0x884c; BYTE $0x10 // movdqu oword [r8 + 4*rcx + 16], xmm1 - LONG $0x7f0f41f3; WORD $0x8814 // movdqu oword [r8 + 4*rcx], xmm2 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000d8248c3b48 // cmp rcx, qword [rsp + 216] - JNE LBB4_180 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x000000d824943b4c // cmp r10, qword [rsp + 216] - LONG $0x245c8a44; BYTE $0x08 // mov r11b, byte [rsp + 8] - QUAD $0x0000013024b48b48 // mov rsi, qword [rsp + 304] - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - JNE LBB4_43 - JMP LBB4_138 + QUAD $0xfffffe24ae100ff3 // movss xmm5, dword [rsi - 476] + QUAD $0xfffea4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 348], 16 + QUAD $0xffff24ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 220], 32 + LONG $0x213a0f66; WORD $0xa46e; BYTE $0x30 // insertps xmm5, dword [rsi - 92], 48 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 + LONG $0xdb0f4166; BYTE $0xdd // pand xmm3, xmm13 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe2896100ff3 // movss xmm2, dword [rsi - 472] + QUAD $0xfffea896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 344], 16 + QUAD $0xffff2896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 216], 32 + LONG $0x213a0f66; WORD $0xa856; BYTE $0x30 // insertps xmm2, dword [rsi - 88], 48 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0x04e1c20f // cmpneqps xmm4, xmm1 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 + LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 + LONG $0xe3eb0f66 // por xmm4, xmm3 + QUAD $0xfffffe2c9e100ff3 // movss xmm3, dword [rsi - 468] + QUAD $0xfffeac9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 340], 16 + QUAD $0xffff2c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 212], 32 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0x213a0f66; WORD $0xac5e; BYTE $0x30 // insertps xmm3, dword [rsi - 84], 48 + LONG $0xe7eb0f66 // por xmm4, xmm7 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf26f0f66 // movdqa xmm6, xmm2 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf2f80f66 // psubb xmm6, xmm2 + QUAD $0xfffffe30be100ff3 // movss xmm7, dword [rsi - 464] + QUAD $0xfffeb0be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 336], 16 + QUAD $0xffff30be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 208], 32 + LONG $0x213a0f66; WORD $0xb07e; BYTE $0x30 // insertps xmm7, dword [rsi - 80], 48 + LONG $0xf5eb0f66 // por xmm6, xmm5 + QUAD $0xfffffe34ae100ff3 // movss xmm5, dword [rsi - 460] + QUAD $0xfffeb4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 332], 16 + QUAD $0xffff34ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 204], 32 + LONG $0x213a0f66; WORD $0xb46e; BYTE $0x30 // insertps xmm5, dword [rsi - 76], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe38b6100ff3 // movss xmm6, dword [rsi - 456] + QUAD $0xfffeb8b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 328], 16 + QUAD $0xffff38b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 200], 32 + LONG $0x213a0f66; WORD $0xb876; BYTE $0x30 // insertps xmm6, dword [rsi - 72], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x03 // psllw xmm7, 3 + LONG $0xdb0f4166; BYTE $0xfa // pand xmm7, xmm10 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 + LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 + LONG $0xefeb0f66 // por xmm5, xmm7 + QUAD $0xfffffe3c96100ff3 // movss xmm2, dword [rsi - 452] + QUAD $0xfffebc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 324], 16 + QUAD $0xffff3c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 196], 32 + LONG $0x213a0f66; WORD $0xbc56; BYTE $0x30 // insertps xmm2, dword [rsi - 68], 48 + LONG $0xebeb0f66 // por xmm5, xmm3 + QUAD $0xfffffe40be100ff3 // movss xmm7, dword [rsi - 448] + QUAD $0xfffec0be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 320], 16 + QUAD $0xffff40be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 192], 32 + LONG $0x213a0f66; WORD $0xc07e; BYTE $0x30 // insertps xmm7, dword [rsi - 64], 48 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe44b6100ff3 // movss xmm6, dword [rsi - 444] + QUAD $0xfffec4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 316], 16 + QUAD $0xffff44b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 188], 32 + LONG $0x213a0f66; WORD $0xc476; BYTE $0x30 // insertps xmm6, dword [rsi - 60], 48 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xf7710f66; BYTE $0x07 // psllw xmm7, 7 + LONG $0xdb0f4166; BYTE $0xfe // pand xmm7, xmm14 + LONG $0xfaeb0f66 // por xmm7, xmm2 + QUAD $0xfffffe4896100ff3 // movss xmm2, dword [rsi - 440] + QUAD $0xfffec896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 312], 16 + QUAD $0xffff4896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 184], 32 + LONG $0x213a0f66; WORD $0xc856; BYTE $0x30 // insertps xmm2, dword [rsi - 56], 48 + LONG $0xfdeb0f66 // por xmm7, xmm5 + QUAD $0xfffffe4c9e100ff3 // movss xmm3, dword [rsi - 436] + QUAD $0xfffecc9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 308], 16 + QUAD $0xffff4c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 180], 32 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0x213a0f66; WORD $0xcc5e; BYTE $0x30 // insertps xmm3, dword [rsi - 52], 48 + LONG $0xe7620f66 // punpckldq xmm4, xmm7 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xfa6f0f66 // movdqa xmm7, xmm2 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xfaf80f66 // psubb xmm7, xmm2 + QUAD $0xfffffe50ae100ff3 // movss xmm5, dword [rsi - 432] + QUAD $0xfffed0ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 304], 16 + QUAD $0xffff50ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 176], 32 + LONG $0x213a0f66; WORD $0xd06e; BYTE $0x30 // insertps xmm5, dword [rsi - 48], 48 + LONG $0xfeeb0f66 // por xmm7, xmm6 + QUAD $0xfffffe54b6100ff3 // movss xmm6, dword [rsi - 428] + QUAD $0xfffed4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 300], 16 + QUAD $0xffff54b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 172], 32 + LONG $0x213a0f66; WORD $0xd476; BYTE $0x30 // insertps xmm6, dword [rsi - 44], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdfeb0f66 // por xmm3, xmm7 + QUAD $0xfffffe58be100ff3 // movss xmm7, dword [rsi - 424] + QUAD $0xfffed8be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 296], 16 + QUAD $0xffff58be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 168], 32 + LONG $0x213a0f66; WORD $0xd87e; BYTE $0x30 // insertps xmm7, dword [rsi - 40], 48 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 + LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf5eb0f66 // por xmm6, xmm5 + QUAD $0xfffffe5c96100ff3 // movss xmm2, dword [rsi - 420] + QUAD $0xfffedc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 292], 16 + QUAD $0xffff5c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 164], 32 + LONG $0x213a0f66; WORD $0xdc56; BYTE $0x30 // insertps xmm2, dword [rsi - 36], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe60ae100ff3 // movss xmm5, dword [rsi - 416] + QUAD $0xfffee0ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 288], 16 + QUAD $0xffff60ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 160], 32 + LONG $0x213a0f66; WORD $0xe06e; BYTE $0x30 // insertps xmm5, dword [rsi - 32], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe64be100ff3 // movss xmm7, dword [rsi - 412] + QUAD $0xfffee4be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 284], 16 + QUAD $0xffff64be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 156], 32 + LONG $0x213a0f66; WORD $0xe47e; BYTE $0x30 // insertps xmm7, dword [rsi - 28], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xf5710f66; BYTE $0x07 // psllw xmm5, 7 + LONG $0xdb0f4166; BYTE $0xee // pand xmm5, xmm14 + LONG $0xeaeb0f66 // por xmm5, xmm2 + QUAD $0xfffffe6896100ff3 // movss xmm2, dword [rsi - 408] + QUAD $0xfffee896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 280], 16 + QUAD $0xffff6896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 152], 32 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0x213a0f66; WORD $0xe856; BYTE $0x30 // insertps xmm2, dword [rsi - 24], 48 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf26f0f66 // movdqa xmm6, xmm2 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf2f80f66 // psubb xmm6, xmm2 + QUAD $0xfffffe6c9e100ff3 // movss xmm3, dword [rsi - 404] + QUAD $0xfffeec9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 276], 16 + QUAD $0xffff6c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 148], 32 + LONG $0x213a0f66; WORD $0xec5e; BYTE $0x30 // insertps xmm3, dword [rsi - 20], 48 + LONG $0xf7eb0f66 // por xmm6, xmm7 + QUAD $0xfffffe7096100ff3 // movss xmm2, dword [rsi - 400] + QUAD $0xfffef096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 272], 16 + QUAD $0xffff7096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 144], 32 + LONG $0x213a0f66; WORD $0xf056; BYTE $0x30 // insertps xmm2, dword [rsi - 16], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] + QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 + QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 + LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf2eb0f66 // por xmm6, xmm2 + QUAD $0xfffffe78be100ff3 // movss xmm7, dword [rsi - 392] + QUAD $0xfffef8be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 264], 16 + QUAD $0xffff78be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 136], 32 + LONG $0x213a0f66; WORD $0xf87e; BYTE $0x30 // insertps xmm7, dword [rsi - 8], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe7c96100ff3 // movss xmm2, dword [rsi - 388] + QUAD $0xfffefc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 260], 16 + QUAD $0xffff7c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 132], 32 + LONG $0x213a0f66; WORD $0xfc56; BYTE $0x30 // insertps xmm2, dword [rsi - 4], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe809e100ff3 // movss xmm3, dword [rsi - 384] + QUAD $0xffff009e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 256], 16 + LONG $0x213a0f66; WORD $0x805e; BYTE $0x20 // insertps xmm3, dword [rsi - 128], 32 + LONG $0x213a0f66; WORD $0x301e // insertps xmm3, dword [rsi], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0xdeeb0f66 // por xmm3, xmm6 + LONG $0xeb620f66 // punpckldq xmm5, xmm3 + LONG $0xe5600f66 // punpcklbw xmm4, xmm5 + LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 + LONG $0x7f0f41f3; WORD $0x9424 // movdqu oword [r12 + 4*rdx], xmm4 + LONG $0x04c28348 // add rdx, 4 + LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 + WORD $0x3949; BYTE $0xd1 // cmp r9, rdx + JNE LBB4_210 + WORD $0x394c; BYTE $0xc9 // cmp rcx, r9 + JNE LBB4_93 + JMP LBB4_116 -LBB4_182: - LONG $0xf0e28349 // and r10, -16 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 +LBB4_212: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000d82494894c // mov qword [rsp + 216], r10 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - LONG $0xc3b60f41 // movzx eax, r11b + WORD $0x014c; BYTE $0xe8 // add rax, r13 + QUAD $0x0000011024848948 // mov qword [rsp + 272], rax + QUAD $0x000000a8248c8948 // mov qword [rsp + 168], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + LONG $0xc7b60f41 // movzx eax, r15b LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x0000a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm1 + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 WORD $0xc031 // xor eax, eax - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 -LBB4_183: - WORD $0x8949; BYTE $0xc1 // mov r9, rax +LBB4_213: QUAD $0x0000009824848948 // mov qword [rsp + 152], rax - LONG $0x05e1c149 // shl r9, 5 - WORD $0x894d; BYTE $0xcc // mov r12, r9 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - WORD $0x894d; BYTE $0xca // mov r10, r9 - LONG $0x244c894c; BYTE $0x40 // mov qword [rsp + 64], r9 - WORD $0x894d; BYTE $0xcf // mov r15, r9 - WORD $0x894d; BYTE $0xcb // mov r11, r9 - WORD $0x894d; BYTE $0xce // mov r14, r9 - WORD $0x894c; BYTE $0xca // mov rdx, r9 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - WORD $0x894c; BYTE $0xcb // mov rbx, r9 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0x04b60f42; BYTE $0x0e // movzx eax, byte [rsi + r9] - LONG $0xe06e0f66 // movd xmm4, eax - LONG $0x44b60f42; WORD $0x010e // movzx eax, byte [rsi + r9 + 1] - LONG $0xd86e0f66 // movd xmm3, eax - LONG $0x44b60f42; WORD $0x020e // movzx eax, byte [rsi + r9 + 2] - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b60f42; WORD $0x030e // movzx eax, byte [rsi + r9 + 3] - LONG $0xf86e0f66 // movd xmm7, eax - LONG $0x44b60f42; WORD $0x040e // movzx eax, byte [rsi + r9 + 4] - LONG $0x6e0f4466; BYTE $0xc8 // movd xmm9, eax - LONG $0x44b60f42; WORD $0x050e // movzx eax, byte [rsi + r9 + 5] - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b60f42; WORD $0x060e // movzx eax, byte [rsi + r9 + 6] - LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax - LONG $0x44b60f42; WORD $0x070e // movzx eax, byte [rsi + r9 + 7] - LONG $0x6e0f4466; BYTE $0xf0 // movd xmm14, eax - LONG $0x44b60f42; WORD $0x080e // movzx eax, byte [rsi + r9 + 8] - LONG $0xc06e0f66 // movd xmm0, eax - QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 - LONG $0x44b60f42; WORD $0x090e // movzx eax, byte [rsi + r9 + 9] - LONG $0x6e0f4466; BYTE $0xd8 // movd xmm11, eax - LONG $0x44b60f42; WORD $0x0a0e // movzx eax, byte [rsi + r9 + 10] - LONG $0x6e0f4466; BYTE $0xe0 // movd xmm12, eax - LONG $0x44b60f42; WORD $0x0b0e // movzx eax, byte [rsi + r9 + 11] - LONG $0x6e0f4466; BYTE $0xe8 // movd xmm13, eax - LONG $0x44b60f42; WORD $0x0c0e // movzx eax, byte [rsi + r9 + 12] - LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x05e0c148 // shl rax, 5 + WORD $0x8949; BYTE $0xc6 // mov r14, rax + WORD $0x8949; BYTE $0xc3 // mov r11, rax + WORD $0x8949; BYTE $0xc0 // mov r8, rax + WORD $0x8949; BYTE $0xc4 // mov r12, rax + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + WORD $0x8949; BYTE $0xc2 // mov r10, rax + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + WORD $0x8949; BYTE $0xc7 // mov r15, rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x4cb60f41; WORD $0x0005 // movzx ecx, byte [r13 + rax] + LONG $0xe16e0f66 // movd xmm4, ecx + LONG $0x4cb60f41; WORD $0x0105 // movzx ecx, byte [r13 + rax + 1] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x4cb60f41; WORD $0x0205 // movzx ecx, byte [r13 + rax + 2] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x4cb60f41; WORD $0x0305 // movzx ecx, byte [r13 + rax + 3] + LONG $0xf96e0f66 // movd xmm7, ecx + LONG $0x4cb60f41; WORD $0x0405 // movzx ecx, byte [r13 + rax + 4] + LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx + LONG $0x4cb60f41; WORD $0x0505 // movzx ecx, byte [r13 + rax + 5] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x4cb60f41; WORD $0x0605 // movzx ecx, byte [r13 + rax + 6] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x4cb60f41; WORD $0x0705 // movzx ecx, byte [r13 + rax + 7] + LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx + LONG $0x4cb60f41; WORD $0x0805 // movzx ecx, byte [r13 + rax + 8] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 + LONG $0x4cb60f41; WORD $0x0905 // movzx ecx, byte [r13 + rax + 9] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x4cb60f41; WORD $0x0a05 // movzx ecx, byte [r13 + rax + 10] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x4cb60f41; WORD $0x0b05 // movzx ecx, byte [r13 + rax + 11] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x4cb60f41; WORD $0x0c05 // movzx ecx, byte [r13 + rax + 12] + LONG $0xc16e0f66 // movd xmm0, ecx QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x44b60f42; WORD $0x0d0e // movzx eax, byte [rsi + r9 + 13] - LONG $0xf06e0f66 // movd xmm6, eax - LONG $0x44b60f42; WORD $0x0e0e // movzx eax, byte [rsi + r9 + 14] - LONG $0x6e0f4466; BYTE $0xf8 // movd xmm15, eax - LONG $0x44b60f42; WORD $0x0f0e // movzx eax, byte [rsi + r9 + 15] - LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x4cb60f41; WORD $0x0d05 // movzx ecx, byte [r13 + rax + 13] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x4cb60f41; WORD $0x0e05 // movzx ecx, byte [r13 + rax + 14] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x4cb60f41; WORD $0x0f05 // movzx ecx, byte [r13 + rax + 15] + LONG $0xc16e0f66 // movd xmm0, ecx QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 - LONG $0x244c894c; BYTE $0x48 // mov qword [rsp + 72], r9 - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - LONG $0x20c98348 // or rcx, 32 - LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx - LONG $0x40cc8349 // or r12, 64 - LONG $0x60cd8349 // or r13, 96 - LONG $0x80ca8149; WORD $0x0000; BYTE $0x00 // or r10, 128 - LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - LONG $0xa0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 160 - LONG $0x2454894c; BYTE $0x40 // mov qword [rsp + 64], r10 - LONG $0xc0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 192 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0xe0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 224 - LONG $0x00ce8149; WORD $0x0001; BYTE $0x00 // or r14, 256 - QUAD $0x000000b024b4894c // mov qword [rsp + 176], r14 - LONG $0x20ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 288 - LONG $0x40c88149; WORD $0x0001; BYTE $0x00 // or r8, 320 - LONG $0x2444894c; BYTE $0x78 // mov qword [rsp + 120], r8 - LONG $0x60cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 352 - LONG $0x245c8948; BYTE $0x58 // mov qword [rsp + 88], rbx - LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 - LONG $0x247c8948; BYTE $0x28 // mov qword [rsp + 40], rdi - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x01c00d48; WORD $0x0000 // or rax, 448 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + WORD $0x8948; BYTE $0xc7 // mov rdi, rax + LONG $0x20cf8348 // or rdi, 32 + LONG $0x40ce8349 // or r14, 64 + LONG $0x2474894c; BYTE $0x70 // mov qword [rsp + 112], r14 + LONG $0x60cb8349 // or r11, 96 + LONG $0x245c894c; BYTE $0x60 // mov qword [rsp + 96], r11 + LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 + LONG $0x2444894c; BYTE $0x50 // mov qword [rsp + 80], r8 + LONG $0xa0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 160 + LONG $0xc0ca8148; WORD $0x0000; BYTE $0x00 // or rdx, 192 + QUAD $0x000000c024948948 // mov qword [rsp + 192], rdx + LONG $0xe0ce8148; WORD $0x0000; BYTE $0x00 // or rsi, 224 + LONG $0x24748948; BYTE $0x28 // mov qword [rsp + 40], rsi + LONG $0x00ca8149; WORD $0x0001; BYTE $0x00 // or r10, 256 + LONG $0x2454894c; BYTE $0x68 // mov qword [rsp + 104], r10 + LONG $0x20cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 288 + LONG $0x245c8948; BYTE $0x48 // mov qword [rsp + 72], rbx + LONG $0x40cf8149; WORD $0x0001; BYTE $0x00 // or r15, 320 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + LONG $0x60c98149; WORD $0x0001; BYTE $0x00 // or r9, 352 + LONG $0x244c894c; BYTE $0x58 // mov qword [rsp + 88], r9 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 + LONG $0x245c8948; BYTE $0x38 // mov qword [rsp + 56], rbx + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0xc0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 448 + LONG $0x24548948; BYTE $0x30 // mov qword [rsp + 48], rdx + LONG $0x01e00d48; WORD $0x0000 // or rax, 480 LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0xe0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 480 - LONG $0x203a0f66; WORD $0x0e24; BYTE $0x01 // pinsrb xmm4, byte [rsi + rcx], 1 - LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 - QUAD $0x022624203a0f4266 // pinsrb xmm4, byte [rsi + r12], 2 - QUAD $0x032e24203a0f4266 // pinsrb xmm4, byte [rsi + r13], 3 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - LONG $0x203a0f66; WORD $0x0e24; BYTE $0x04 // pinsrb xmm4, byte [rsi + rcx], 4 - QUAD $0x051624203a0f4266 // pinsrb xmm4, byte [rsi + r10], 5 - QUAD $0x063e24203a0f4266 // pinsrb xmm4, byte [rsi + r15], 6 - QUAD $0x071e24203a0f4266 // pinsrb xmm4, byte [rsi + r11], 7 - QUAD $0x083624203a0f4266 // pinsrb xmm4, byte [rsi + r14], 8 - LONG $0x203a0f66; WORD $0x1624; BYTE $0x09 // pinsrb xmm4, byte [rsi + rdx], 9 - QUAD $0x0a0624203a0f4266 // pinsrb xmm4, byte [rsi + r8], 10 - LONG $0x203a0f66; WORD $0x1e24; BYTE $0x0b // pinsrb xmm4, byte [rsi + rbx], 11 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - LONG $0x203a0f66; WORD $0x0e24; BYTE $0x0c // pinsrb xmm4, byte [rsi + rcx], 12 - LONG $0x244c8b4c; BYTE $0x10 // mov r9, qword [rsp + 16] - QUAD $0x0d0e24203a0f4266 // pinsrb xmm4, byte [rsi + r9], 13 - LONG $0x203a0f66; WORD $0x0624; BYTE $0x0e // pinsrb xmm4, byte [rsi + rax], 14 - LONG $0x203a0f66; WORD $0x3e24; BYTE $0x0f // pinsrb xmm4, byte [rsi + rdi], 15 - LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] - QUAD $0x010e5c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r9 + 1], 1 - QUAD $0x01265c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rsi + r12 + 1], 2 - QUAD $0x012e5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r13 + 1], 3 - WORD $0x894d; BYTE $0xec // mov r12, r13 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x012e5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r13 + 1], 4 - QUAD $0x01165c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r10 + 1], 5 - QUAD $0x013e5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r15 + 1], 6 - QUAD $0x011e5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r11 + 1], 7 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x01365c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r14 + 1], 8 - QUAD $0x0901165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 1], 9 - WORD $0x8949; BYTE $0xd6 // mov r14, rdx - QUAD $0x01065c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r8 + 1], 10 - QUAD $0x0b011e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 1], 11 - QUAD $0x0c010e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 1], 12 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0d01165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 1], 13 - QUAD $0x0e01065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 1], 14 - QUAD $0x0000a0248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 160] + QUAD $0x003d64203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r13 + rdi], 1 + QUAD $0x003564203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r13 + r14], 2 + QUAD $0x001d64203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r13 + r11], 3 + QUAD $0x000564203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r13 + r8], 4 + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + QUAD $0x002564203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r13 + r12], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x002564203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r13 + r12], 6 + QUAD $0x003564203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r13 + rsi], 7 + QUAD $0x001564203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r13 + r10], 8 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x001564203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r13 + rdx], 9 + QUAD $0x003d64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r13 + r15], 10 + QUAD $0x000d64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r13 + r9], 11 + QUAD $0x001d64203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r13 + rbx], 12 + QUAD $0x000d64203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r13 + rcx], 13 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x000564203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r13 + rax], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x000564203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r13 + rax], 15 + QUAD $0x013d5c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r13 + rdi + 1], 1 + LONG $0x247c8948; BYTE $0x20 // mov qword [rsp + 32], rdi + QUAD $0x01355c203a0f4366; BYTE $0x02 // pinsrb xmm3, byte [r13 + r14 + 1], 2 + QUAD $0x011d5c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r13 + r11 + 1], 3 + QUAD $0x01055c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r13 + r8 + 1], 4 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x011d5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r13 + r11 + 1], 5 + QUAD $0x01255c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r13 + r12 + 1], 6 + QUAD $0x01355c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r13 + rsi + 1], 7 + QUAD $0x01155c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r13 + r10 + 1], 8 + QUAD $0x01155c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r13 + rdx + 1], 9 + QUAD $0x013d5c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r13 + r15 + 1], 10 + QUAD $0x010d5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r13 + r9 + 1], 11 + QUAD $0x011d5c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r13 + rbx + 1], 12 + QUAD $0x010d5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r13 + rcx + 1], 13 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x01355c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r13 + r14 + 1], 14 + QUAD $0x0000d0248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 208] LONG $0xe1740f66 // pcmpeqb xmm4, xmm1 - QUAD $0x0f013e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 1], 15 - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x01055c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r13 + r8 + 1], 15 LONG $0xd9740f66 // pcmpeqb xmm3, xmm1 QUAD $0x00000100856f0f66 // movdqa xmm0, oword 256[rbp] /* [rip + .LCPI4_16] */ LONG $0xd8df0f66 // pandn xmm3, xmm0 LONG $0xdcfc0f66 // paddb xmm3, xmm4 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - LONG $0x0654b60f; BYTE $0x10 // movzx edx, byte [rsi + rax + 16] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x54b60f41; WORD $0x1005 // movzx edx, byte [r13 + rax + 16] LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - WORD $0x894c; BYTE $0xca // mov rdx, r9 - QUAD $0x020e6c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rsi + r9 + 2], 1 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x02023e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 2], 2 - LONG $0x2464894c; BYTE $0x38 // mov qword [rsp + 56], r12 - QUAD $0x02266c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r12 + 2], 3 - WORD $0x894d; BYTE $0xe8 // mov r8, r13 - QUAD $0x022e6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r13 + 2], 4 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x021e6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r11 + 2], 5 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x022e6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r13 + 2], 6 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - QUAD $0x02166c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r10 + 2], 7 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x023e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r15 + 2], 8 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - QUAD $0x02366c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r14 + 2], 9 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x02166c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r10 + 2], 10 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x02366c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r14 + 2], 11 + QUAD $0x023d6c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r13 + rdi + 2], 1 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x020d6c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r13 + r9 + 2], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x02356c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r13 + rsi + 2], 3 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x02156c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r13 + r10 + 2], 4 + QUAD $0x021d6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r13 + r11 + 2], 5 + WORD $0x894c; BYTE $0xe3 // mov rbx, r12 + QUAD $0x02256c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r13 + r12 + 2], 6 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c02066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 2], 12 + QUAD $0x02056c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r13 + rax + 2], 7 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x020d6c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r13 + rcx + 2], 8 + LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] + QUAD $0x023d6c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r13 + rdi + 2], 9 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x023d6c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r13 + r15 + 2], 10 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x023d6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r13 + r15 + 2], 11 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x02256c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r13 + r12 + 2], 12 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d02066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 2], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e02066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 2], 14 - LONG $0x244c8948; BYTE $0x50 // mov qword [rsp + 80], rcx - QUAD $0x0f020e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 2], 15 - QUAD $0x0103167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 3], 1 - QUAD $0x02033e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 3], 2 - QUAD $0x03267c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rsi + r12 + 3], 3 - QUAD $0x03067c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r8 + 3], 4 - QUAD $0x031e7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r11 + 3], 5 - QUAD $0x032e7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rsi + r13 + 3], 6 - QUAD $0x07031e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 3], 7 - QUAD $0x033e7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r15 + 3], 8 - QUAD $0x030e7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r9 + 3], 9 - QUAD $0x03167c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r10 + 3], 10 - QUAD $0x03367c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r14 + 3], 11 + QUAD $0x02056c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r13 + rax + 2], 13 + QUAD $0x02356c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r13 + r14 + 2], 14 + QUAD $0x02056c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r13 + r8 + 2], 15 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x03057c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r13 + rax + 3], 1 + QUAD $0x030d7c203a0f4366; BYTE $0x02 // pinsrb xmm7, byte [r13 + r9 + 3], 2 + QUAD $0x03357c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r13 + rsi + 3], 3 + QUAD $0x03157c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r13 + r10 + 3], 4 + QUAD $0x031d7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r13 + r11 + 3], 5 + QUAD $0x031d7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r13 + rbx + 3], 6 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c03067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 3], 12 + QUAD $0x03057c203a0f4166; BYTE $0x07 // pinsrb xmm7, byte [r13 + rax + 3], 7 + QUAD $0x030d7c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r13 + rcx + 3], 8 + QUAD $0x033d7c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r13 + rdi + 3], 9 + QUAD $0x03157c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r13 + rdx + 3], 10 + QUAD $0x033d7c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r13 + r15 + 3], 11 + QUAD $0x03257c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r13 + r12 + 3], 12 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d03067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 3], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e03067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 3], 14 - QUAD $0x0f030e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 3], 15 - QUAD $0x04164c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rdx + 4], 1 - QUAD $0x043e4c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rdi + 4], 2 - QUAD $0x04264c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r12 + 4], 3 - QUAD $0x04064c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rsi + r8 + 4], 4 - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - QUAD $0x041e4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r11 + 4], 5 - QUAD $0x042e4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rsi + r13 + 4], 6 - QUAD $0x041e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rbx + 4], 7 - QUAD $0x043e4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r15 + 4], 8 - QUAD $0x040e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r9 + 4], 9 - QUAD $0x04164c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r10 + 4], 10 - QUAD $0x04364c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r14 + 4], 11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x04064c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rsi + rax + 4], 12 - LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] - QUAD $0x04064c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r8 + 4], 13 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x04164c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rsi + rdx + 4], 14 - QUAD $0x040e4c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rsi + rcx + 4], 15 + QUAD $0x03057c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r13 + rax + 3], 13 + QUAD $0x03357c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r13 + r14 + 3], 14 + QUAD $0x03057c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r13 + r8 + 3], 15 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x04054c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r13 + rax + 4], 1 + QUAD $0x040d4c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r13 + r9 + 4], 2 + QUAD $0x04354c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r13 + rsi + 4], 3 + QUAD $0x04154c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r10 + 4], 4 + QUAD $0x041d4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r13 + r11 + 4], 5 + QUAD $0x041d4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r13 + rbx + 4], 6 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x04354c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r13 + rsi + 4], 7 + QUAD $0x040d4c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r13 + rcx + 4], 8 + QUAD $0x043d4c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r13 + rdi + 4], 9 + WORD $0x8949; BYTE $0xfa // mov r10, rdi + QUAD $0x04154c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r13 + rdx + 4], 10 + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + QUAD $0x0000008824948948 // mov qword [rsp + 136], rdx + QUAD $0x043d4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r13 + r15 + 4], 11 + QUAD $0x04254c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r13 + r12 + 4], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x04154c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r13 + rdx + 4], 13 + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + QUAD $0x04354c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r13 + r14 + 4], 14 + QUAD $0x04054c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r13 + r8 + 4], 15 LONG $0xe9740f66 // pcmpeqb xmm5, xmm1 QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI4_17] */ LONG $0xe8df0f66 // pandn xmm5, xmm0 @@ -22818,87 +23032,79 @@ LBB4_183: QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI4_18] */ LONG $0xf8df0f66 // pandn xmm7, xmm0 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - LONG $0x0e54b60f; BYTE $0x11 // movzx edx, byte [rsi + rcx + 17] + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + LONG $0x54b60f43; WORD $0x1105 // movzx edx, byte [r13 + r8 + 17] LONG $0xe26e0f66 // movd xmm4, edx LONG $0x740f4466; BYTE $0xc9 // pcmpeqb xmm9, xmm1 QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI4_19] */ LONG $0xdf0f4466; BYTE $0xc8 // pandn xmm9, xmm0 LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 - LONG $0x0e54b60f; BYTE $0x12 // movzx edx, byte [rsi + rcx + 18] + LONG $0x54b60f43; WORD $0x1205 // movzx edx, byte [r13 + r8 + 18] LONG $0xfa6e0f66 // movd xmm7, edx LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 LONG $0xd8f80f66 // psubb xmm3, xmm0 LONG $0xeb0f4466; BYTE $0xcb // por xmm9, xmm3 - LONG $0x0e54b60f; BYTE $0x13 // movzx edx, byte [rsi + rcx + 19] + LONG $0x54b60f43; WORD $0x1305 // movzx edx, byte [r13 + r8 + 19] LONG $0xea6e0f66 // movd xmm5, edx - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x052654203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r12 + 5], 1 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x052e54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rsi + r13 + 5], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x03050654203a0f66 // pinsrb xmm2, byte [rsi + rax + 5], 3 - QUAD $0x04053e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 5], 4 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - QUAD $0x051e54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r11 + 5], 5 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x06050654203a0f66 // pinsrb xmm2, byte [rsi + rax + 5], 6 - QUAD $0x00000110249c8948 // mov qword [rsp + 272], rbx - QUAD $0x07051e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 5], 7 - QUAD $0x053e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r15 + 5], 8 - QUAD $0x00000088248c894c // mov qword [rsp + 136], r9 - QUAD $0x050e54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r9 + 5], 9 - QUAD $0x051654203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r10 + 5], 10 - QUAD $0x053654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r14 + 5], 11 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0c051654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 5], 12 - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - QUAD $0x050654203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r8 + 5], 13 - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x050654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r8 + 5], 14 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x051e54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r11 + 5], 15 - QUAD $0x062644203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rsi + r12 + 6], 1 - QUAD $0x062e44203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rsi + r13 + 6], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x060644203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rax + 6], 3 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x062e44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r13 + 6], 4 - QUAD $0x063e44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rsi + rdi + 6], 5 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x060644203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rax + 6], 6 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - QUAD $0x061e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rbx + 6], 7 - QUAD $0x063e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r15 + 6], 8 - QUAD $0x060e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r9 + 6], 9 - QUAD $0x061644203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r10 + 6], 10 - QUAD $0x063644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r14 + 6], 11 - QUAD $0x061644203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rsi + rdx + 6], 12 - QUAD $0x060e44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rcx + 6], 13 - QUAD $0x060644203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r8 + 6], 14 - QUAD $0x061e44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r11 + 6], 15 - QUAD $0x072674203a0f4666; BYTE $0x01 // pinsrb xmm14, byte [rsi + r12 + 7], 1 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x072674203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rsi + r12 + 7], 2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x070674203a0f4466; BYTE $0x03 // pinsrb xmm14, byte [rsi + rax + 7], 3 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x071e74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rsi + r11 + 7], 4 - QUAD $0x073e74203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rsi + rdi + 7], 5 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x072e74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rsi + r13 + 7], 6 - QUAD $0x071e74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rsi + rbx + 7], 7 - QUAD $0x073e74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r15 + 7], 8 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - QUAD $0x070e74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r9 + 7], 9 - QUAD $0x071674203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rsi + r10 + 7], 10 - QUAD $0x073674203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rsi + r14 + 7], 11 - QUAD $0x071674203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rsi + rdx + 7], 12 - QUAD $0x070e74203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rsi + rcx + 7], 13 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - QUAD $0x070674203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rsi + r8 + 7], 14 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + QUAD $0x050554203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r13 + rax + 5], 1 + QUAD $0x050d54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r13 + r9 + 5], 2 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x051554203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r13 + rdx + 5], 3 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x053554203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r13 + r14 + 5], 4 + QUAD $0x051d54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r13 + r11 + 5], 5 + QUAD $0x051d54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r13 + rbx + 5], 6 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x050554203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r13 + rax + 5], 7 + QUAD $0x050d54203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r13 + rcx + 5], 8 + QUAD $0x051554203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r13 + r10 + 5], 9 + QUAD $0x053d54203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r13 + rdi + 5], 10 + QUAD $0x053d54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r13 + r15 + 5], 11 + WORD $0x894c; BYTE $0xe7 // mov rdi, r12 + QUAD $0x052554203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r13 + r12 + 5], 12 + QUAD $0x053554203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r13 + rsi + 5], 13 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x053554203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r13 + rsi + 5], 14 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x052554203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r13 + r12 + 5], 15 + QUAD $0x060544203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r13 + r8 + 6], 1 + QUAD $0x060d44203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r13 + r9 + 6], 2 + QUAD $0x061544203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r13 + rdx + 6], 3 + QUAD $0x063544203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r13 + r14 + 6], 4 + QUAD $0x061d44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r13 + r11 + 6], 5 + QUAD $0x061d44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r13 + rbx + 6], 6 + QUAD $0x060544203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r13 + rax + 6], 7 + QUAD $0x060d44203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r13 + rcx + 6], 8 + QUAD $0x061544203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r13 + r10 + 6], 9 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + QUAD $0x061d44203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r13 + r11 + 6], 10 + QUAD $0x063d44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r13 + r15 + 6], 11 + QUAD $0x063d44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r13 + rdi + 6], 12 + LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] + QUAD $0x061544203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r13 + r10 + 6], 13 + QUAD $0x063544203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r13 + rsi + 6], 14 + QUAD $0x062544203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r13 + r12 + 6], 15 + QUAD $0x070574203a0f4766; BYTE $0x01 // pinsrb xmm14, byte [r13 + r8 + 7], 1 + QUAD $0x070d74203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r13 + r9 + 7], 2 + QUAD $0x071574203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r13 + rdx + 7], 3 + QUAD $0x073574203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r13 + r14 + 7], 4 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x071574203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r13 + rdx + 7], 5 + QUAD $0x071d74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r13 + rbx + 7], 6 + QUAD $0x070574203a0f4566; BYTE $0x07 // pinsrb xmm14, byte [r13 + rax + 7], 7 + QUAD $0x070d74203a0f4566; BYTE $0x08 // pinsrb xmm14, byte [r13 + rcx + 7], 8 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x072574203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r13 + r12 + 7], 9 + QUAD $0x071d74203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r13 + r11 + 7], 10 + WORD $0x894d; BYTE $0xda // mov r10, r11 + QUAD $0x073d74203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r13 + r15 + 7], 11 + QUAD $0x073d74203a0f4566; BYTE $0x0c // pinsrb xmm14, byte [r13 + rdi + 7], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x070574203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r13 + rax + 7], 13 + QUAD $0x073574203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r13 + rsi + 7], 14 LONG $0x6f0f4166; BYTE $0xce // movdqa xmm1, xmm14 - QUAD $0x00a024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 160] + QUAD $0x00d024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 208] LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 QUAD $0x00000140856f0f66 // movdqa xmm0, oword 320[rbp] /* [rip + .LCPI4_20] */ LONG $0xd0df0f66 // pandn xmm2, xmm0 @@ -22906,373 +23112,378 @@ LBB4_183: QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI4_21] */ LONG $0xdf0f4466; BYTE $0xc0 // pandn xmm8, xmm0 LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - LONG $0x3e54b60f; BYTE $0x14 // movzx edx, byte [rsi + rdi + 20] + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + LONG $0x54b60f43; WORD $0x1405 // movzx edx, byte [r13 + r8 + 20] LONG $0xda6e0f66 // movd xmm3, edx - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0f070e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 7], 15 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x070d4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r13 + rcx + 7], 15 LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI4_6] */ LONG $0xc8df0f66 // pandn xmm1, xmm0 LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - LONG $0x3e54b60f; BYTE $0x15 // movzx edx, byte [rsi + rdi + 21] + LONG $0x54b60f43; WORD $0x1505 // movzx edx, byte [r13 + r8 + 21] LONG $0xd26e0f66 // movd xmm2, edx - QUAD $0x0000c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 192] - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x01080644203a0f66 // pinsrb xmm0, byte [rsi + rax + 8], 1 - QUAD $0x082644203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r12 + 8], 2 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x082644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r12 + 8], 3 - QUAD $0x081e44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r11 + 8], 4 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x083644203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r14 + 8], 5 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x06081644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 8], 6 - QUAD $0x00000110249c8b4c // mov r11, qword [rsp + 272] - QUAD $0x081e44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r11 + 8], 7 - QUAD $0x083e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r15 + 8], 8 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x081644203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r10 + 8], 9 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x083e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r15 + 8], 10 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0b081644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 8], 11 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0c081644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 8], 12 - QUAD $0x082e44203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r13 + 8], 13 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0e081644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 8], 14 - QUAD $0x0f080e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 8], 15 + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x080544203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r13 + rax + 8], 1 + QUAD $0x080d44203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r13 + r9 + 8], 2 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x081d44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r13 + rbx + 8], 3 + QUAD $0x083544203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r13 + r14 + 8], 4 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x081d44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r13 + r11 + 8], 5 + QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] + QUAD $0x083544203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r13 + r14 + 8], 6 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x083d44203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r13 + rdi + 8], 7 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x083d44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r13 + r15 + 8], 8 + QUAD $0x082544203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r13 + r12 + 8], 9 + QUAD $0x081544203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r13 + r10 + 8], 10 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x082544203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r13 + r12 + 8], 11 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x081544203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r13 + rdx + 8], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x081544203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r13 + rdx + 8], 13 + QUAD $0x083544203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r13 + rsi + 8], 14 + QUAD $0x080d44203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r13 + rcx + 8], 15 LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 - QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 - LONG $0x3e54b60f; BYTE $0x16 // movzx edx, byte [rsi + rdi + 22] + QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + LONG $0x54b60f43; WORD $0x1605 // movzx edx, byte [r13 + r8 + 22] LONG $0xca6e0f66 // movd xmm1, edx LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 - QUAD $0x09065c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rax + 9], 1 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x093e5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rdi + 9], 2 - QUAD $0x09265c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r12 + 9], 3 - QUAD $0x09065c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r8 + 9], 4 - QUAD $0x09365c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r14 + 9], 5 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x092e5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rsi + r13 + 9], 6 - QUAD $0x091e5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r11 + 9], 7 - QUAD $0x091e5c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rsi + rbx + 9], 8 - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x09165c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r10 + 9], 9 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - QUAD $0x093e5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rsi + r15 + 9], 10 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x09165c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r10 + 9], 11 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x093e5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r15 + 9], 12 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x09165c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rdx + 9], 13 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x09165c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rsi + rdx + 9], 14 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x09165c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rsi + rdx + 9], 15 + QUAD $0x09055c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r13 + rax + 9], 1 + QUAD $0x090d5c203a0f4766; BYTE $0x02 // pinsrb xmm11, byte [r13 + r9 + 9], 2 + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + QUAD $0x091d5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r13 + rbx + 9], 3 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x09055c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r13 + rax + 9], 4 + QUAD $0x091d5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r13 + r11 + 9], 5 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + QUAD $0x09355c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r13 + r14 + 9], 6 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + QUAD $0x093d5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r13 + rdi + 9], 7 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 + QUAD $0x093d5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r13 + r15 + 9], 8 + LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] + QUAD $0x093d5c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r13 + rdi + 9], 9 + QUAD $0x09155c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r13 + r10 + 9], 10 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x09255c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r13 + r12 + 9], 11 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x09255c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r13 + r12 + 9], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x09355c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r13 + rsi + 9], 13 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0a0664203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rax + 10], 1 - QUAD $0x0a3e64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rdi + 10], 2 - QUAD $0x0a2664203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rsi + r12 + 10], 3 - QUAD $0x0a0664203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rsi + r8 + 10], 4 - QUAD $0x0a3664203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r14 + 10], 5 - QUAD $0x0a2e64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rsi + r13 + 10], 6 - QUAD $0x0a1e64203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rsi + r11 + 10], 7 - QUAD $0x0a1e64203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rsi + rbx + 10], 8 - QUAD $0x0a0e64203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rsi + rcx + 10], 9 - QUAD $0x0a0e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r9 + 10], 10 - QUAD $0x0a1664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r10 + 10], 11 - QUAD $0x0a3e64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r15 + 10], 12 - LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] - QUAD $0x0a3664203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rsi + r14 + 10], 13 + QUAD $0x09055c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r13 + rax + 9], 14 LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0a0664203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rsi + rax + 10], 14 - QUAD $0x0a1664203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rsi + rdx + 10], 15 + QUAD $0x09055c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r13 + rax + 9], 15 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x0a3564203a0f4766; BYTE $0x01 // pinsrb xmm12, byte [r13 + r14 + 10], 1 + QUAD $0x0a0d64203a0f4766; BYTE $0x02 // pinsrb xmm12, byte [r13 + r9 + 10], 2 + QUAD $0x0a0564203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r13 + r8 + 10], 3 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x0a3564203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r13 + r14 + 10], 4 + QUAD $0x0a1d64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r13 + r11 + 10], 5 + QUAD $0x0a1d64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r13 + rbx + 10], 6 + QUAD $0x0a1564203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r13 + rdx + 10], 7 + QUAD $0x0a0d64203a0f4566; BYTE $0x08 // pinsrb xmm12, byte [r13 + rcx + 10], 8 + QUAD $0x0a3d64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r13 + rdi + 10], 9 + QUAD $0x0a1564203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r13 + r10 + 10], 10 + QUAD $0x0a3d64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r13 + r15 + 10], 11 + QUAD $0x0a2564203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r13 + r12 + 10], 12 + QUAD $0x0a3564203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r13 + rsi + 10], 13 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b066c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rsi + rax + 11], 1 - QUAD $0x0b3e6c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rdi + 11], 2 - WORD $0x8949; BYTE $0xfe // mov r14, rdi - QUAD $0x0b266c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rsi + r12 + 11], 3 - QUAD $0x0b066c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r8 + 11], 4 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b066c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rsi + rax + 11], 5 - QUAD $0x0b2e6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rsi + r13 + 11], 6 - QUAD $0x0b1e6c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rsi + r11 + 11], 7 - WORD $0x894d; BYTE $0xdc // mov r12, r11 - QUAD $0x0b1e6c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rsi + rbx + 11], 8 - QUAD $0x0b0e6c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rsi + rcx + 11], 9 - QUAD $0x0b0e6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rsi + r9 + 11], 10 - QUAD $0x0b166c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r10 + 11], 11 - QUAD $0x0b3e6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r15 + 11], 12 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0b3e6c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rdi + 11], 13 - WORD $0x8949; BYTE $0xfd // mov r13, rdi - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x0b0e6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r9 + 11], 14 - QUAD $0x0b166c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rsi + rdx + 11], 15 + QUAD $0x0a0564203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r13 + rax + 10], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0a0564203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r13 + rax + 10], 15 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0b056c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r13 + rax + 11], 1 + QUAD $0x0b0d6c203a0f4766; BYTE $0x02 // pinsrb xmm13, byte [r13 + r9 + 11], 2 + QUAD $0x0b056c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r13 + r8 + 11], 3 + QUAD $0x0b356c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r13 + r14 + 11], 4 + QUAD $0x0b1d6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r13 + r11 + 11], 5 + QUAD $0x0b1d6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r13 + rbx + 11], 6 + QUAD $0x0b156c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r13 + rdx + 11], 7 + QUAD $0x0b0d6c203a0f4566; BYTE $0x08 // pinsrb xmm13, byte [r13 + rcx + 11], 8 + QUAD $0x0b3d6c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r13 + rdi + 11], 9 + QUAD $0x0b156c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r13 + r10 + 11], 10 + QUAD $0x0b3d6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r13 + r15 + 11], 11 + QUAD $0x0b256c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r13 + r12 + 11], 12 + QUAD $0x0b356c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r13 + rsi + 11], 13 + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0b056c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r13 + rax + 11], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b056c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r13 + rax + 11], 15 LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 QUAD $0x0001009ddf0f4466; BYTE $0x00 // pandn xmm11, oword 256[rbp] /* [rip + .LCPI4_16] */ LONG $0xfc0f4466; BYTE $0xd8 // paddb xmm11, xmm0 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - LONG $0x3e54b60f; BYTE $0x17 // movzx edx, byte [rsi + rdi + 23] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x54b60f41; WORD $0x1705 // movzx edx, byte [r13 + rax + 23] LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 QUAD $0x000110a5df0f4466; BYTE $0x00 // pandn xmm12, oword 272[rbp] /* [rip + .LCPI4_17] */ LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI4_18] */ LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - LONG $0x3e54b60f; BYTE $0x18 // movzx edx, byte [rsi + rdi + 24] + LONG $0x54b60f41; WORD $0x1805 // movzx edx, byte [r13 + rax + 24] LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx QUAD $0x00f0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 240] - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0c1e4c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rsi + r11 + 12], 1 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - QUAD $0x0c364c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rsi + r14 + 12], 2 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0c3e4c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rsi + rdi + 12], 3 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x0c364c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rsi + r14 + 12], 4 - QUAD $0x0c064c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rsi + rax + 12], 5 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0c164c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rdx + 12], 6 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - QUAD $0x0c264c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rsi + r12 + 12], 7 - QUAD $0x0c1e4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rsi + rbx + 12], 8 - QUAD $0x0c0e4c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rsi + rcx + 12], 9 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0c264c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r12 + 12], 10 - QUAD $0x0c164c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r10 + 12], 11 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x0c164c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r10 + 12], 12 - QUAD $0x0c2e4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r13 + 12], 13 - QUAD $0x0c0e4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r9 + 12], 14 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0c2e4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r13 + 12], 15 - QUAD $0x0d1e74203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r11 + 13], 1 - QUAD $0x0d0674203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rsi + r8 + 13], 2 - QUAD $0x030d3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 13], 3 - QUAD $0x0d3674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r14 + 13], 4 - QUAD $0x050d0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 13], 5 - QUAD $0x060d1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 13], 6 - QUAD $0x0d3e74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r15 + 13], 7 - QUAD $0x080d1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 13], 8 - QUAD $0x090d0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 13], 9 - QUAD $0x0d2674203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r12 + 13], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b0d1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 13], 11 - QUAD $0x0d1674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r10 + 13], 12 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x0d1674203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r10 + 13], 13 - QUAD $0x0d0e74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r9 + 13], 14 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0d0e74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r9 + 13], 15 - QUAD $0x0e1e7c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rsi + r11 + 14], 1 - QUAD $0x0e067c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rsi + r8 + 14], 2 - QUAD $0x0e3e7c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rsi + rdi + 14], 3 - QUAD $0x0e367c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rsi + r14 + 14], 4 - QUAD $0x0e067c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rax + 14], 5 - QUAD $0x0e167c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rdx + 14], 6 - QUAD $0x0e3e7c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rsi + r15 + 14], 7 - QUAD $0x000000b024bc8b48 // mov rdi, qword [rsp + 176] - QUAD $0x0e3e7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rsi + rdi + 14], 8 - QUAD $0x0e0e7c203a0f4466; BYTE $0x09 // pinsrb xmm15, byte [rsi + rcx + 14], 9 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - QUAD $0x0e267c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r12 + 14], 10 - QUAD $0x0e1e7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rsi + rbx + 14], 11 - WORD $0x894d; BYTE $0xec // mov r12, r13 - QUAD $0x0e2e7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r13 + 14], 12 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x0e167c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rsi + r10 + 14], 13 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x0e167c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r10 + 14], 14 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0c054c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r13 + rax + 12], 1 + QUAD $0x0c0d4c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r13 + r9 + 12], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0c354c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r13 + rsi + 12], 3 + QUAD $0x0c354c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r14 + 12], 4 + WORD $0x894d; BYTE $0xd8 // mov r8, r11 + QUAD $0x0c1d4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r13 + r11 + 12], 5 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + QUAD $0x0c1d4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r13 + rbx + 12], 6 + LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] + QUAD $0x0c1d4c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r13 + rbx + 12], 7 + QUAD $0x0c0d4c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r13 + rcx + 12], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0c054c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r13 + rax + 12], 9 + QUAD $0x0c154c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r13 + r10 + 12], 10 + QUAD $0x0c3d4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r13 + r15 + 12], 11 + QUAD $0x0c254c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r13 + r12 + 12], 12 + QUAD $0x0c3d4c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r13 + rdi + 12], 13 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0c154c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r13 + rdx + 12], 14 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x0c3d4c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r13 + rdi + 12], 15 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x0d3d74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r13 + rdi + 13], 1 + QUAD $0x0d0d74203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r13 + r9 + 13], 2 + QUAD $0x0d3574203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r13 + rsi + 13], 3 + QUAD $0x0d3574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r14 + 13], 4 + QUAD $0x0d0574203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r13 + r8 + 13], 5 + QUAD $0x0d1d74203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r13 + r11 + 13], 6 + QUAD $0x0d1d74203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r13 + rbx + 13], 7 + QUAD $0x0d0d74203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r13 + rcx + 13], 8 + QUAD $0x0d0574203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r13 + rax + 13], 9 + QUAD $0x0d1574203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r13 + r10 + 13], 10 + QUAD $0x0d3d74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r13 + r15 + 13], 11 + QUAD $0x0d2574203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r13 + r12 + 13], 12 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x0d3d74203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r13 + rdi + 13], 13 + QUAD $0x0d1574203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r13 + rdx + 13], 14 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x0d3d74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r13 + rdi + 13], 15 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x0e3d7c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r13 + rdi + 14], 1 + QUAD $0x0e0d7c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r13 + r9 + 14], 2 + QUAD $0x0e357c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r13 + rsi + 14], 3 + WORD $0x8949; BYTE $0xf1 // mov r9, rsi + QUAD $0x0e357c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r13 + r14 + 14], 4 + QUAD $0x0e057c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r13 + r8 + 14], 5 + QUAD $0x0e1d7c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r13 + r11 + 14], 6 + QUAD $0x0e1d7c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r13 + rbx + 14], 7 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + QUAD $0x0e0d7c203a0f4566; BYTE $0x08 // pinsrb xmm15, byte [r13 + rcx + 14], 8 + QUAD $0x0e057c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r13 + rax + 14], 9 + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x0e157c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r13 + r10 + 14], 10 + WORD $0x894c; BYTE $0xd7 // mov rdi, r10 + QUAD $0x0e3d7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r13 + r15 + 14], 11 + QUAD $0x0e257c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r13 + r12 + 14], 12 + LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] + QUAD $0x0e357c203a0f4766; BYTE $0x0d // pinsrb xmm15, byte [r13 + r14 + 14], 13 + QUAD $0x0e157c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r13 + rdx + 14], 14 + WORD $0x8949; BYTE $0xd7 // mov r15, rdx LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI4_19] */ LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - LONG $0x0654b60f; BYTE $0x19 // movzx edx, byte [rsi + rax + 25] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x54b60f41; WORD $0x1905 // movzx edx, byte [r13 + rax + 25] LONG $0x6e0f4466; BYTE $0xea // movd xmm13, edx QUAD $0x0001609df80f4466; BYTE $0x00 // psubb xmm11, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0xeb0f4566; BYTE $0xcb // por xmm9, xmm11 - LONG $0x0654b60f; BYTE $0x1a // movzx edx, byte [rsi + rax + 26] + LONG $0x54b60f41; WORD $0x1a05 // movzx edx, byte [r13 + rax + 26] LONG $0xc26e0f66 // movd xmm0, edx - QUAD $0x0e0e7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r9 + 14], 15 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0e0d7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r13 + rcx + 14], 15 LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 QUAD $0x00000140b5df0f66 // pandn xmm6, oword 320[rbp] /* [rip + .LCPI4_20] */ LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI4_21] */ LONG $0xeb0f4466; BYTE $0xfe // por xmm15, xmm6 - LONG $0x0654b60f; BYTE $0x1b // movzx edx, byte [rsi + rax + 27] + LONG $0x54b60f41; WORD $0x1b05 // movzx edx, byte [r13 + rax + 27] LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx QUAD $0x0000e024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 224] - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x010f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 15], 1 - QUAD $0x0f0674203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rsi + r8 + 15], 2 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - QUAD $0x0f0e74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r9 + 15], 3 - QUAD $0x0f3674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r14 + 15], 4 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x050f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 15], 5 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x060f1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 15], 6 - QUAD $0x0f3e74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r15 + 15], 7 - QUAD $0x080f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 15], 8 - QUAD $0x0000008824bc8b48 // mov rdi, qword [rsp + 136] - QUAD $0x090f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 15], 9 - QUAD $0x0f1e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r11 + 15], 10 - QUAD $0x0b0f1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 15], 11 - QUAD $0x0f2674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r12 + 15], 12 - QUAD $0x0f2e74203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r13 + 15], 13 - QUAD $0x0f1674203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r10 + 15], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0f3574203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r13 + rsi + 15], 1 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0f1574203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r13 + rdx + 15], 2 + QUAD $0x0f0d74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r13 + r9 + 15], 3 LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x0f1674203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r10 + 15], 15 + QUAD $0x0f1574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r10 + 15], 4 + QUAD $0x0f0574203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r13 + r8 + 15], 5 + QUAD $0x000000c024a48b4c // mov r12, qword [rsp + 192] + QUAD $0x0f2574203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r13 + r12 + 15], 6 + QUAD $0x0f1d74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r13 + r11 + 15], 7 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0f1574203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r13 + rdx + 15], 8 + QUAD $0x0f1d74203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r13 + rbx + 15], 9 + QUAD $0x0f3d74203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r13 + rdi + 15], 10 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x0f1d74203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r13 + rbx + 15], 11 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x0f1d74203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r13 + r11 + 15], 12 + QUAD $0x0f3574203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r13 + r14 + 15], 13 + QUAD $0x0f3d74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r13 + r15 + 15], 14 + QUAD $0x0f0d74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r13 + rcx + 15], 15 LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI4_6] */ LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x0654b60f; BYTE $0x1c // movzx edx, byte [rsi + rax + 28] + LONG $0x54b60f41; WORD $0x1c05 // movzx edx, byte [r13 + rax + 28] LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 QUAD $0x0000e024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm6 - LONG $0x0654b60f; BYTE $0x1d // movzx edx, byte [rsi + rax + 29] + LONG $0x54b60f41; WORD $0x1d05 // movzx edx, byte [r13 + rax + 29] LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x101654203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rdx + 16], 1 - QUAD $0x100654203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r8 + 16], 2 - QUAD $0x100e54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r9 + 16], 3 - QUAD $0x103654203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r14 + 16], 4 - QUAD $0x100e54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rsi + rcx + 16], 5 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x102654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r12 + 16], 6 - QUAD $0x103e54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r15 + 16], 7 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x100e54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rsi + rcx + 16], 8 - QUAD $0x103e54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rdi + 16], 9 - QUAD $0x101e54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r11 + 16], 10 - QUAD $0x101e54203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rsi + rbx + 16], 11 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x100654203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rsi + rax + 16], 12 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x102e54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r13 + 16], 13 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x102e54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r13 + 16], 14 - QUAD $0x101654203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r10 + 16], 15 - QUAD $0x01111664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 17], 1 - QUAD $0x110664203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r8 + 17], 2 - QUAD $0x110e64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r9 + 17], 3 - QUAD $0x113664203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r14 + 17], 4 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x110664203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r8 + 17], 5 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - QUAD $0x112664203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r12 + 17], 6 - QUAD $0x113e64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r15 + 17], 7 - QUAD $0x08110e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 17], 8 - QUAD $0x09113e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 17], 9 - QUAD $0x111e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r11 + 17], 10 - QUAD $0x0b111e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 17], 11 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x112664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r12 + 17], 12 - QUAD $0x0d110664203a0f66 // pinsrb xmm4, byte [rsi + rax + 17], 13 - QUAD $0x112e64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r13 + 17], 14 - QUAD $0x111664203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r10 + 17], 15 - WORD $0x894c; BYTE $0xd7 // mov rdi, r10 + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + QUAD $0x103554203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r13 + rsi + 16], 1 + LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] + QUAD $0x103d54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r13 + rdi + 16], 2 + WORD $0x894c; BYTE $0xce // mov rsi, r9 + QUAD $0x100d54203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r13 + r9 + 16], 3 + QUAD $0x101554203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r13 + r10 + 16], 4 + QUAD $0x100554203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r13 + r8 + 16], 5 + QUAD $0x102554203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r13 + r12 + 16], 6 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x100d54203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r13 + r9 + 16], 7 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x100d54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r13 + rcx + 16], 8 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x103d54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r13 + r15 + 16], 9 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x102554203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r13 + r12 + 16], 10 + QUAD $0x101d54203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r13 + rbx + 16], 11 + QUAD $0x101d54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r13 + r11 + 16], 12 + QUAD $0x103554203a0f4766; BYTE $0x0d // pinsrb xmm10, byte [r13 + r14 + 16], 13 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x101d54203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r13 + r11 + 16], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x100554203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r13 + rax + 16], 15 + QUAD $0x111564203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r13 + rdx + 17], 1 + QUAD $0x113d64203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r13 + rdi + 17], 2 + QUAD $0x113564203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r13 + rsi + 17], 3 + QUAD $0x111564203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r13 + r10 + 17], 4 + QUAD $0x110564203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r13 + r8 + 17], 5 + QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] + QUAD $0x113d64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r13 + rdi + 17], 6 + QUAD $0x110d64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r13 + r9 + 17], 7 + QUAD $0x110d64203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r13 + rcx + 17], 8 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 + QUAD $0x113d64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r13 + r15 + 17], 9 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x112564203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r13 + r12 + 17], 10 + QUAD $0x111d64203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r13 + rbx + 17], 11 + WORD $0x8949; BYTE $0xda // mov r10, rbx + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x112564203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r13 + r12 + 17], 12 + QUAD $0x113564203a0f4366; BYTE $0x0d // pinsrb xmm4, byte [r13 + r14 + 17], 13 + WORD $0x894d; BYTE $0xdf // mov r15, r11 + QUAD $0x111d64203a0f4366; BYTE $0x0e // pinsrb xmm4, byte [r13 + r11 + 17], 14 + QUAD $0x110564203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r13 + rax + 17], 15 LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 LONG $0x740f4166; BYTE $0xe6 // pcmpeqb xmm4, xmm14 QUAD $0x00000100b56f0f66 // movdqa xmm6, oword 256[rbp] /* [rip + .LCPI4_16] */ LONG $0xe6df0f66 // pandn xmm4, xmm6 LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - LONG $0x0e54b60f; BYTE $0x1e // movzx edx, byte [rsi + rcx + 30] + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + LONG $0x54b60f41; WORD $0x1e1d // movzx edx, byte [r13 + rbx + 30] LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0112067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 18], 1 - QUAD $0x0113066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 1 - QUAD $0x0114065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 20], 1 - QUAD $0x01150654203a0f66 // pinsrb xmm2, byte [rsi + rax + 21], 1 - QUAD $0x0116064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 22], 1 - QUAD $0x170644203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rax + 23], 1 - QUAD $0x180664203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rax + 24], 1 - QUAD $0x19066c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rsi + rax + 25], 1 - QUAD $0x011a0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 26], 1 - QUAD $0x1b065c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rax + 27], 1 - QUAD $0x1c067c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rax + 28], 1 - QUAD $0x1d064c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rax + 29], 1 - QUAD $0x1e0654203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rax + 30], 1 - LONG $0x0e54b60f; BYTE $0x1f // movzx edx, byte [rsi + rcx + 31] + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x12057c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r13 + rax + 18], 1 + QUAD $0x13056c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r13 + rax + 19], 1 + QUAD $0x14055c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r13 + rax + 20], 1 + QUAD $0x150554203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r13 + rax + 21], 1 + QUAD $0x16054c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r13 + rax + 22], 1 + QUAD $0x170544203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r13 + rax + 23], 1 + QUAD $0x180564203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r13 + rax + 24], 1 + QUAD $0x19056c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r13 + rax + 25], 1 + QUAD $0x1a0544203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r13 + rax + 26], 1 + QUAD $0x1b055c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r13 + rax + 27], 1 + QUAD $0x1c057c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r13 + rax + 28], 1 + QUAD $0x1d054c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r13 + rax + 29], 1 + QUAD $0x1e0554203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r13 + rax + 30], 1 + LONG $0x54b60f41; WORD $0x1f1d // movzx edx, byte [r13 + rbx + 31] LONG $0xf26e0f66 // movd xmm6, edx - QUAD $0x011f0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 31], 1 + QUAD $0x1f0574203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r13 + rax + 31], 1 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x12157c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r13 + rdx + 18], 2 + QUAD $0x13156c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r13 + rdx + 19], 2 + QUAD $0x14155c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r13 + rdx + 20], 2 + QUAD $0x151554203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r13 + rdx + 21], 2 + QUAD $0x16154c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r13 + rdx + 22], 2 + QUAD $0x171544203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r13 + rdx + 23], 2 + QUAD $0x181564203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r13 + rdx + 24], 2 + QUAD $0x19156c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r13 + rdx + 25], 2 + QUAD $0x1a1544203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r13 + rdx + 26], 2 + QUAD $0x1b155c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r13 + rdx + 27], 2 + QUAD $0x1c157c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r13 + rdx + 28], 2 + QUAD $0x1d154c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r13 + rdx + 29], 2 + QUAD $0x1e1554203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r13 + rdx + 30], 2 + QUAD $0x1f1574203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r13 + rdx + 31], 2 LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0212167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 18], 2 - QUAD $0x0213166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 19], 2 - QUAD $0x0214165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 20], 2 - QUAD $0x02151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 2 - QUAD $0x0216164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 22], 2 - QUAD $0x171644203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rdx + 23], 2 - QUAD $0x181664203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rdx + 24], 2 - QUAD $0x19166c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rdx + 25], 2 - QUAD $0x021a1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 26], 2 - QUAD $0x1b165c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rdx + 27], 2 - QUAD $0x1c167c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rsi + rdx + 28], 2 - QUAD $0x1d164c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rdx + 29], 2 - QUAD $0x1e1654203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rdx + 30], 2 - QUAD $0x021f1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 31], 2 - LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] - QUAD $0x0312167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 18], 3 - QUAD $0x12367c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r14 + 18], 4 - QUAD $0x12067c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r8 + 18], 5 + QUAD $0x12157c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r13 + rdx + 18], 3 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x12357c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r13 + r14 + 18], 4 + QUAD $0x12057c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r13 + r8 + 18], 5 + QUAD $0x123d7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r13 + rdi + 18], 6 WORD $0x894c; BYTE $0xcb // mov rbx, r9 - QUAD $0x120e7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rsi + r9 + 18], 6 - QUAD $0x123e7c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rsi + r15 + 18], 7 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x121e7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r11 + 18], 8 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x09120e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 18], 9 - LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] - QUAD $0x120e7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r9 + 18], 10 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x12167c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r10 + 18], 11 - WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x12267c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r12 + 18], 12 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x12267c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r12 + 18], 13 - QUAD $0x122e7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rsi + r13 + 18], 14 - QUAD $0x0f123e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 18], 15 - QUAD $0x0313166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 19], 3 - QUAD $0x13366c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r14 + 19], 4 - QUAD $0x13066c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r8 + 19], 5 - QUAD $0x06131e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 19], 6 - QUAD $0x133e6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r15 + 19], 7 - QUAD $0x131e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r11 + 19], 8 - QUAD $0x09130e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 19], 9 - QUAD $0x130e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r9 + 19], 10 - QUAD $0x13166c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r10 + 19], 11 - QUAD $0x0c13066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 12 - QUAD $0x13266c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r12 + 19], 13 - QUAD $0x132e6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rsi + r13 + 19], 14 - QUAD $0x0f133e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 19], 15 - QUAD $0x0314165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 20], 3 - QUAD $0x14365c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r14 + 20], 4 - QUAD $0x14065c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r8 + 20], 5 - QUAD $0x06141e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 20], 6 - QUAD $0x143e5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r15 + 20], 7 - QUAD $0x141e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r11 + 20], 8 - QUAD $0x09140e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 20], 9 - QUAD $0x140e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r9 + 20], 10 - QUAD $0x14165c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r10 + 20], 11 - QUAD $0x0c14065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 20], 12 - QUAD $0x14265c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r12 + 20], 13 - QUAD $0x142e5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rsi + r13 + 20], 14 + QUAD $0x120d7c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r13 + r9 + 18], 7 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x120d7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r13 + r9 + 18], 8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x120d7c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r13 + rcx + 18], 9 + QUAD $0x12357c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r13 + rsi + 18], 10 + QUAD $0x12157c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r13 + r10 + 18], 11 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + QUAD $0x12257c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r13 + r12 + 18], 12 + LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] + QUAD $0x121d7c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r13 + r11 + 18], 13 + QUAD $0x123d7c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r13 + r15 + 18], 14 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x12257c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r13 + r12 + 18], 15 + QUAD $0x13156c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r13 + rdx + 19], 3 + QUAD $0x13356c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r13 + r14 + 19], 4 + QUAD $0x13056c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r13 + r8 + 19], 5 + QUAD $0x133d6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r13 + rdi + 19], 6 + QUAD $0x131d6c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r13 + rbx + 19], 7 + QUAD $0x130d6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r13 + r9 + 19], 8 + QUAD $0x13056c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r13 + rax + 19], 9 + QUAD $0x13356c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r13 + rsi + 19], 10 + QUAD $0x13156c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r13 + r10 + 19], 11 + QUAD $0x130d6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r13 + rcx + 19], 12 + QUAD $0x131d6c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r13 + r11 + 19], 13 + QUAD $0x133d6c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r13 + r15 + 19], 14 + QUAD $0x13256c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r13 + r12 + 19], 15 + QUAD $0x14155c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r13 + rdx + 20], 3 + QUAD $0x14355c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r13 + r14 + 20], 4 + QUAD $0x14055c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r13 + r8 + 20], 5 + QUAD $0x143d5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r13 + rdi + 20], 6 + QUAD $0x141d5c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r13 + rbx + 20], 7 + QUAD $0x140d5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r13 + r9 + 20], 8 + QUAD $0x14055c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r13 + rax + 20], 9 + QUAD $0x14355c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r13 + rsi + 20], 10 + QUAD $0x14155c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r13 + r10 + 20], 11 + QUAD $0x140d5c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r13 + rcx + 20], 12 + QUAD $0x141d5c203a0f4366; BYTE $0x0d // pinsrb xmm3, byte [r13 + r11 + 20], 13 + QUAD $0x143d5c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r13 + r15 + 20], 14 LONG $0x740f4166; BYTE $0xfe // pcmpeqb xmm7, xmm14 QUAD $0x000110b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 272[rbp] /* [rip + .LCPI4_17] */ LONG $0xdf0f4166; BYTE $0xfe // pandn xmm7, xmm14 - QUAD $0x0000a024ac740f66; BYTE $0x00 // pcmpeqb xmm5, oword [rsp + 160] + QUAD $0x0000d024ac740f66; BYTE $0x00 // pcmpeqb xmm5, oword [rsp + 208] QUAD $0x000120b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 288[rbp] /* [rip + .LCPI4_18] */ LONG $0xdf0f4166; BYTE $0xee // pandn xmm5, xmm14 LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0x0f143e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 20], 15 - QUAD $0x00a024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 160] + QUAD $0x14255c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r13 + r12 + 20], 15 + QUAD $0x00d024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 208] LONG $0x740f4166; BYTE $0xde // pcmpeqb xmm3, xmm14 QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI4_19] */ LONG $0xdfdf0f66 // pandn xmm3, xmm7 @@ -23280,44 +23491,44 @@ LBB4_183: LONG $0xed760f66 // pcmpeqd xmm5, xmm5 LONG $0xe5f80f66 // psubb xmm4, xmm5 LONG $0xdceb0f66 // por xmm3, xmm4 - QUAD $0x03151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 3 - QUAD $0x153654203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r14 + 21], 4 - QUAD $0x150654203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r8 + 21], 5 - QUAD $0x06151e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 21], 6 - QUAD $0x153e54203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rsi + r15 + 21], 7 - QUAD $0x151e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r11 + 21], 8 - QUAD $0x09150e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 21], 9 - QUAD $0x150e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r9 + 21], 10 - QUAD $0x151654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r10 + 21], 11 - QUAD $0x0c150654203a0f66 // pinsrb xmm2, byte [rsi + rax + 21], 12 - QUAD $0x152654203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r12 + 21], 13 - QUAD $0x152e54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r13 + 21], 14 - QUAD $0x0f153e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 21], 15 - QUAD $0x0316164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 22], 3 - QUAD $0x16364c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r14 + 22], 4 - QUAD $0x16064c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r8 + 22], 5 - QUAD $0x06161e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 22], 6 - QUAD $0x163e4c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rsi + r15 + 22], 7 - QUAD $0x161e4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r11 + 22], 8 - QUAD $0x09160e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 22], 9 - QUAD $0x160e4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r9 + 22], 10 - QUAD $0x16164c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r10 + 22], 11 - QUAD $0x0c16064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 22], 12 - QUAD $0x16264c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r12 + 22], 13 - QUAD $0x162e4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r13 + 22], 14 - QUAD $0x0f163e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 22], 15 - QUAD $0x171644203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rdx + 23], 3 - QUAD $0x173644203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r14 + 23], 4 - QUAD $0x170644203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r8 + 23], 5 - QUAD $0x171e44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rbx + 23], 6 - QUAD $0x173e44203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rsi + r15 + 23], 7 - QUAD $0x171e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r11 + 23], 8 - QUAD $0x170e44203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rsi + rcx + 23], 9 - QUAD $0x170e44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r9 + 23], 10 - QUAD $0x171644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r10 + 23], 11 - QUAD $0x170644203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rsi + rax + 23], 12 - QUAD $0x172644203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r12 + 23], 13 - QUAD $0x172e44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r13 + 23], 14 + QUAD $0x151554203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r13 + rdx + 21], 3 + QUAD $0x153554203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r13 + r14 + 21], 4 + QUAD $0x150554203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r13 + r8 + 21], 5 + QUAD $0x153d54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r13 + rdi + 21], 6 + QUAD $0x151d54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r13 + rbx + 21], 7 + QUAD $0x150d54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r13 + r9 + 21], 8 + QUAD $0x150554203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r13 + rax + 21], 9 + QUAD $0x153554203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r13 + rsi + 21], 10 + QUAD $0x151554203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r13 + r10 + 21], 11 + QUAD $0x150d54203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r13 + rcx + 21], 12 + QUAD $0x151d54203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r13 + r11 + 21], 13 + QUAD $0x153d54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r13 + r15 + 21], 14 + QUAD $0x152554203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r13 + r12 + 21], 15 + QUAD $0x16154c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r13 + rdx + 22], 3 + QUAD $0x16354c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r13 + r14 + 22], 4 + QUAD $0x16054c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r13 + r8 + 22], 5 + QUAD $0x163d4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r13 + rdi + 22], 6 + QUAD $0x161d4c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r13 + rbx + 22], 7 + QUAD $0x160d4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r13 + r9 + 22], 8 + QUAD $0x16054c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r13 + rax + 22], 9 + QUAD $0x16354c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r13 + rsi + 22], 10 + QUAD $0x16154c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r13 + r10 + 22], 11 + QUAD $0x160d4c203a0f4166; BYTE $0x0c // pinsrb xmm1, byte [r13 + rcx + 22], 12 + QUAD $0x161d4c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r13 + r11 + 22], 13 + QUAD $0x163d4c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r13 + r15 + 22], 14 + QUAD $0x16254c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r13 + r12 + 22], 15 + QUAD $0x171544203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r13 + rdx + 23], 3 + QUAD $0x173544203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r13 + r14 + 23], 4 + QUAD $0x170544203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r13 + r8 + 23], 5 + QUAD $0x173d44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r13 + rdi + 23], 6 + QUAD $0x171d44203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r13 + rbx + 23], 7 + QUAD $0x170d44203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r13 + r9 + 23], 8 + QUAD $0x170544203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r13 + rax + 23], 9 + QUAD $0x173544203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r13 + rsi + 23], 10 + QUAD $0x171544203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r13 + r10 + 23], 11 + QUAD $0x170d44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r13 + rcx + 23], 12 + QUAD $0x171d44203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r13 + r11 + 23], 13 + QUAD $0x173d44203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r13 + r15 + 23], 14 LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI4_20] */ LONG $0xd5df0f66 // pandn xmm2, xmm5 @@ -23325,134 +23536,136 @@ LBB4_183: QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI4_21] */ LONG $0xcfdf0f66 // pandn xmm1, xmm7 LONG $0xcaeb0f66 // por xmm1, xmm2 - QUAD $0x173e44203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rsi + rdi + 23], 15 + QUAD $0x172544203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r13 + r12 + 23], 15 LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI4_6] */ LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - QUAD $0x181664203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rsi + rdx + 24], 3 - QUAD $0x183664203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rsi + r14 + 24], 4 - QUAD $0x180664203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r8 + 24], 5 - QUAD $0x181e64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rbx + 24], 6 - QUAD $0x183e64203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rsi + r15 + 24], 7 - QUAD $0x181e64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r11 + 24], 8 - QUAD $0x180e64203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rsi + rcx + 24], 9 - QUAD $0x180e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r9 + 24], 10 - QUAD $0x181664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r10 + 24], 11 - QUAD $0x180664203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rsi + rax + 24], 12 - QUAD $0x182664203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rsi + r12 + 24], 13 - QUAD $0x182e64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r13 + 24], 14 - QUAD $0x183e64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rsi + rdi + 24], 15 + QUAD $0x181564203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r13 + rdx + 24], 3 + QUAD $0x183564203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r13 + r14 + 24], 4 + QUAD $0x180564203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r13 + r8 + 24], 5 + QUAD $0x183d64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r13 + rdi + 24], 6 + QUAD $0x181d64203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r13 + rbx + 24], 7 + QUAD $0x180d64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r13 + r9 + 24], 8 + QUAD $0x180564203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r13 + rax + 24], 9 + QUAD $0x183564203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r13 + rsi + 24], 10 + QUAD $0x181564203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r13 + r10 + 24], 11 + QUAD $0x180d64203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r13 + rcx + 24], 12 + QUAD $0x181d64203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r13 + r11 + 24], 13 + QUAD $0x183d64203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r13 + r15 + 24], 14 + QUAD $0x182564203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r13 + r12 + 24], 15 LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 - QUAD $0x19166c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rsi + rdx + 25], 3 - QUAD $0x19366c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r14 + 25], 4 - QUAD $0x19066c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rsi + r8 + 25], 5 - QUAD $0x191e6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rsi + rbx + 25], 6 - QUAD $0x193e6c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rsi + r15 + 25], 7 - QUAD $0x191e6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r11 + 25], 8 - QUAD $0x190e6c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rsi + rcx + 25], 9 - QUAD $0x190e6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rsi + r9 + 25], 10 - QUAD $0x19166c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r10 + 25], 11 - QUAD $0x19066c203a0f4466; BYTE $0x0c // pinsrb xmm13, byte [rsi + rax + 25], 12 - QUAD $0x19266c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rsi + r12 + 25], 13 - QUAD $0x192e6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r13 + 25], 14 - QUAD $0x193e6c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rsi + rdi + 25], 15 - QUAD $0x031a1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 26], 3 - QUAD $0x1a3644203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r14 + 26], 4 - QUAD $0x1a0644203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r8 + 26], 5 - QUAD $0x061a1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 26], 6 - QUAD $0x1a3e44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r15 + 26], 7 - QUAD $0x1a1e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r11 + 26], 8 - QUAD $0x091a0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 26], 9 - QUAD $0x1a0e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r9 + 26], 10 - QUAD $0x1a1644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r10 + 26], 11 - QUAD $0x0c1a0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 26], 12 - QUAD $0x1a2644203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r12 + 26], 13 - QUAD $0x1a2e44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r13 + 26], 14 - QUAD $0x0f1a3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 26], 15 - QUAD $0x1b165c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rsi + rdx + 27], 3 - QUAD $0x1b365c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r14 + 27], 4 - QUAD $0x1b065c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r8 + 27], 5 - QUAD $0x1b1e5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rsi + rbx + 27], 6 - QUAD $0x1b3e5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r15 + 27], 7 - QUAD $0x1b1e5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r11 + 27], 8 - QUAD $0x1b0e5c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rsi + rcx + 27], 9 - QUAD $0x1b0e5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rsi + r9 + 27], 10 - QUAD $0x1b165c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r10 + 27], 11 - QUAD $0x1b065c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rsi + rax + 27], 12 - QUAD $0x1b265c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rsi + r12 + 27], 13 - QUAD $0x1b2e5c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rsi + r13 + 27], 14 + QUAD $0x19156c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r13 + rdx + 25], 3 + QUAD $0x19356c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r13 + r14 + 25], 4 + QUAD $0x19056c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r13 + r8 + 25], 5 + QUAD $0x193d6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r13 + rdi + 25], 6 + QUAD $0x191d6c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r13 + rbx + 25], 7 + QUAD $0x190d6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r13 + r9 + 25], 8 + QUAD $0x19056c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r13 + rax + 25], 9 + QUAD $0x19356c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r13 + rsi + 25], 10 + QUAD $0x19156c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r13 + r10 + 25], 11 + QUAD $0x190d6c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r13 + rcx + 25], 12 + QUAD $0x191d6c203a0f4766; BYTE $0x0d // pinsrb xmm13, byte [r13 + r11 + 25], 13 + QUAD $0x193d6c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r13 + r15 + 25], 14 + QUAD $0x19256c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r13 + r12 + 25], 15 + QUAD $0x1a1544203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r13 + rdx + 26], 3 + QUAD $0x1a3544203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r13 + r14 + 26], 4 + QUAD $0x1a0544203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r13 + r8 + 26], 5 + QUAD $0x1a3d44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r13 + rdi + 26], 6 + QUAD $0x1a1d44203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r13 + rbx + 26], 7 + QUAD $0x1a0d44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r13 + r9 + 26], 8 + QUAD $0x1a0544203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r13 + rax + 26], 9 + QUAD $0x1a3544203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r13 + rsi + 26], 10 + QUAD $0x1a1544203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r13 + r10 + 26], 11 + QUAD $0x1a0d44203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r13 + rcx + 26], 12 + QUAD $0x1a1d44203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r13 + r11 + 26], 13 + QUAD $0x1a3d44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r13 + r15 + 26], 14 + QUAD $0x1a2544203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r13 + r12 + 26], 15 + QUAD $0x1b155c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r13 + rdx + 27], 3 + QUAD $0x1b355c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r13 + r14 + 27], 4 + QUAD $0x1b055c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r13 + r8 + 27], 5 + QUAD $0x1b3d5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r13 + rdi + 27], 6 + QUAD $0x1b1d5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r13 + rbx + 27], 7 + QUAD $0x1b0d5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r13 + r9 + 27], 8 + QUAD $0x1b055c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r13 + rax + 27], 9 + QUAD $0x1b355c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r13 + rsi + 27], 10 + QUAD $0x1b155c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r13 + r10 + 27], 11 + QUAD $0x1b0d5c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r13 + rcx + 27], 12 + QUAD $0x1b1d5c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r13 + r11 + 27], 13 + QUAD $0x1b3d5c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r13 + r15 + 27], 14 LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI4_16] */ LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 - QUAD $0x1b3e5c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rsi + rdi + 27], 15 + QUAD $0x1b255c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r13 + r12 + 27], 15 LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI4_17] */ LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI4_18] */ LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 - QUAD $0x1c167c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rsi + rdx + 28], 3 - QUAD $0x1d164c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rsi + rdx + 29], 3 - QUAD $0x1e1654203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rdx + 30], 3 - QUAD $0x031f1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 31], 3 - QUAD $0x1c367c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rsi + r14 + 28], 4 - QUAD $0x1d364c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rsi + r14 + 29], 4 - QUAD $0x1e3654203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r14 + 30], 4 - QUAD $0x1f3674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r14 + 31], 4 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - QUAD $0x1c067c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rsi + r8 + 28], 5 - QUAD $0x1d064c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r8 + 29], 5 - QUAD $0x1e0654203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r8 + 30], 5 - QUAD $0x1f0674203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r8 + 31], 5 - QUAD $0x1c1e7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rbx + 28], 6 - QUAD $0x1d1e4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rbx + 29], 6 - QUAD $0x1e1e54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rbx + 30], 6 - QUAD $0x061f1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 31], 6 - QUAD $0x1c3e7c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rsi + r15 + 28], 7 - QUAD $0x1d3e4c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rsi + r15 + 29], 7 - QUAD $0x1e3e54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r15 + 30], 7 - QUAD $0x1f3e74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r15 + 31], 7 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x1c1e7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r11 + 28], 8 - QUAD $0x1d1e4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r11 + 29], 8 - QUAD $0x1e1e54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r11 + 30], 8 - QUAD $0x1f1e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r11 + 31], 8 - QUAD $0x1c0e7c203a0f4466; BYTE $0x09 // pinsrb xmm15, byte [rsi + rcx + 28], 9 - QUAD $0x1d0e4c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rsi + rcx + 29], 9 - QUAD $0x1e0e54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rcx + 30], 9 - QUAD $0x091f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 31], 9 + QUAD $0x1c157c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r13 + rdx + 28], 3 + QUAD $0x1d154c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r13 + rdx + 29], 3 + QUAD $0x1e1554203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r13 + rdx + 30], 3 + QUAD $0x1f1574203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r13 + rdx + 31], 3 + QUAD $0x1c357c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r13 + r14 + 28], 4 + QUAD $0x1d354c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r14 + 29], 4 + QUAD $0x1e3554203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r13 + r14 + 30], 4 + QUAD $0x1f3574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r14 + 31], 4 + QUAD $0x1c057c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r13 + r8 + 28], 5 + QUAD $0x1d054c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r13 + r8 + 29], 5 + QUAD $0x1e0554203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r13 + r8 + 30], 5 + QUAD $0x1f0574203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r13 + r8 + 31], 5 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + QUAD $0x1c3d7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r13 + rdi + 28], 6 + QUAD $0x1d3d4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r13 + rdi + 29], 6 + QUAD $0x1e3d54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r13 + rdi + 30], 6 + QUAD $0x1f3d74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r13 + rdi + 31], 6 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x1c1d7c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r13 + rbx + 28], 7 + QUAD $0x1d1d4c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r13 + rbx + 29], 7 + QUAD $0x1e1d54203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r13 + rbx + 30], 7 + QUAD $0x1f1d74203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r13 + rbx + 31], 7 WORD $0x894c; BYTE $0xca // mov rdx, r9 - QUAD $0x1c0e7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r9 + 28], 10 - QUAD $0x1d0e4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r9 + 29], 10 - QUAD $0x1e0e54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r9 + 30], 10 - QUAD $0x1f0e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r9 + 31], 10 - WORD $0x894c; BYTE $0xd2 // mov rdx, r10 - QUAD $0x1c167c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r10 + 28], 11 - QUAD $0x1d164c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r10 + 29], 11 - QUAD $0x1e1654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r10 + 30], 11 - QUAD $0x1f1674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r10 + 31], 11 - QUAD $0x1c067c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rsi + rax + 28], 12 - QUAD $0x1d064c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rsi + rax + 29], 12 - QUAD $0x1e0654203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rsi + rax + 30], 12 - QUAD $0x0c1f0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 31], 12 + QUAD $0x1c0d7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r13 + r9 + 28], 8 + QUAD $0x1d0d4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r13 + r9 + 29], 8 + QUAD $0x1e0d54203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r13 + r9 + 30], 8 + QUAD $0x1f0d74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r13 + r9 + 31], 8 + QUAD $0x1c057c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r13 + rax + 28], 9 + QUAD $0x1d054c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r13 + rax + 29], 9 + QUAD $0x1e0554203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r13 + rax + 30], 9 + QUAD $0x1f0574203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r13 + rax + 31], 9 + QUAD $0x1c357c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r13 + rsi + 28], 10 + QUAD $0x1d354c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r13 + rsi + 29], 10 + QUAD $0x1e3554203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r13 + rsi + 30], 10 + QUAD $0x1f3574203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r13 + rsi + 31], 10 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x1c157c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r13 + r10 + 28], 11 + QUAD $0x1d154c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r13 + r10 + 29], 11 + QUAD $0x1e1554203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r13 + r10 + 30], 11 + QUAD $0x1f1574203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r13 + r10 + 31], 11 + QUAD $0x1c0d7c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r13 + rcx + 28], 12 + QUAD $0x1d0d4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r13 + rcx + 29], 12 + QUAD $0x1e0d54203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r13 + rcx + 30], 12 + QUAD $0x1f0d74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r13 + rcx + 31], 12 + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x1c1d7c203a0f4766; BYTE $0x0d // pinsrb xmm15, byte [r13 + r11 + 28], 13 + QUAD $0x1d1d4c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r13 + r11 + 29], 13 + QUAD $0x1e1d54203a0f4766; BYTE $0x0d // pinsrb xmm10, byte [r13 + r11 + 30], 13 + QUAD $0x1f1d74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r13 + r11 + 31], 13 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x1c3d7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r13 + r15 + 28], 14 + QUAD $0x1d3d4c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r13 + r15 + 29], 14 + QUAD $0x1e3d54203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r13 + r15 + 30], 14 + QUAD $0x1f3d74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r13 + r15 + 31], 14 WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x1c267c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rsi + r12 + 28], 13 - QUAD $0x1d264c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r12 + 29], 13 - QUAD $0x1e2654203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r12 + 30], 13 - QUAD $0x1f2674203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r12 + 31], 13 - QUAD $0x1c2e7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r13 + 28], 14 - QUAD $0x1d2e4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r13 + 29], 14 - QUAD $0x1e2e54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r13 + 30], 14 - QUAD $0x1f2e74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r13 + 31], 14 - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - QUAD $0x1c3e7c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rsi + rdi + 28], 15 - QUAD $0x1d3e4c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rsi + rdi + 29], 15 - QUAD $0x1e3e54203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rsi + rdi + 30], 15 + QUAD $0x1c257c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r13 + r12 + 28], 15 + QUAD $0x1d254c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r13 + r12 + 29], 15 + QUAD $0x1e2554203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r13 + r12 + 30], 15 LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI4_19] */ LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 - QUAD $0x0f1f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 31], 15 + QUAD $0x1f2574203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r13 + r12 + 31], 15 QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 @@ -23466,7 +23679,7 @@ LBB4_183: LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 LONG $0xc6600f66 // punpcklbw xmm0, xmm6 - QUAD $0x0000c0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 192] + QUAD $0x0000b0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 176] LONG $0xcb6f0f66 // movdqa xmm1, xmm3 QUAD $0x0000e024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 224] LONG $0xcc600f66 // punpcklbw xmm1, xmm4 @@ -23479,48 +23692,48 @@ LBB4_183: LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 LONG $0x690f4166; BYTE $0xd8 // punpckhwd xmm3, xmm8 QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - LONG $0x5c7f0ff3; WORD $0x308b // movdqu oword [rbx + 4*rcx + 48], xmm3 - LONG $0x447f0ff3; WORD $0x208b // movdqu oword [rbx + 4*rcx + 32], xmm0 - LONG $0x4c7f0ff3; WORD $0x108b // movdqu oword [rbx + 4*rcx + 16], xmm1 - LONG $0x147f0ff3; BYTE $0x8b // movdqu oword [rbx + 4*rcx], xmm2 + LONG $0x7f0f41f3; WORD $0x885c; BYTE $0x30 // movdqu oword [r8 + 4*rcx + 48], xmm3 + LONG $0x7f0f41f3; WORD $0x8844; BYTE $0x20 // movdqu oword [r8 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x884c; BYTE $0x10 // movdqu oword [r8 + 4*rcx + 16], xmm1 + LONG $0x7f0f41f3; WORD $0x8814 // movdqu oword [r8 + 4*rcx], xmm2 LONG $0x10c18348 // add rcx, 16 WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000d8248c3b48 // cmp rcx, qword [rsp + 216] - JNE LBB4_183 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x000000d824943b4c // cmp r10, qword [rsp + 216] - LONG $0x245c8a44; BYTE $0x08 // mov r11b, byte [rsp + 8] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + JNE LBB4_213 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + LONG $0x247c8a44; BYTE $0x08 // mov r15b, byte [rsp + 8] + QUAD $0x0000011024ac8b4c // mov r13, qword [rsp + 272] QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - JNE LBB4_69 - JMP LBB4_142 + JNE LBB4_127 + JMP LBB4_131 -LBB4_185: - LONG $0xf8e28349 // and r10, -8 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 +LBB4_215: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x2454894c; BYTE $0x20 // mov qword [rsp + 32], r10 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x244c8948; BYTE $0x28 // mov qword [rsp + 40], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - LONG $0x246c8944; BYTE $0x40 // mov dword [rsp + 64], r13d + LONG $0x246c8944; BYTE $0x38 // mov dword [rsp + 56], r13d LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 WORD $0x3145; BYTE $0xff // xor r15d, r15d - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 LONG $0xef0f4566; BYTE $0xff // pxor xmm15, xmm15 -LBB4_186: +LBB4_216: LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06e7c149 // shl r15, 6 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 WORD $0x894d; BYTE $0xfc // mov r12, r15 WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 WORD $0x894c; BYTE $0xff // mov rdi, r15 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 LONG $0x04b70f42; BYTE $0x3e // movzx eax, word [rsi + r15] LONG $0xe86e0f66 // movd xmm5, eax LONG $0x44b70f42; WORD $0x023e // movzx eax, word [rsi + r15 + 2] @@ -23540,36 +23753,36 @@ LBB4_186: LONG $0x74b70f46; WORD $0x143e // movzx r14d, word [rsi + r15 + 20] WORD $0x894c; BYTE $0xf9 // mov rcx, r15 LONG $0x40c98348 // or rcx, 64 - LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 - LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 - LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 + LONG $0x40cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 320 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 LONG $0x2cc40f66; WORD $0x010e // pinsrw xmm5, word [rsi + rcx], 1 - LONG $0xc40f4266; WORD $0x062c; BYTE $0x02 // pinsrw xmm5, word [rsi + r8], 2 + LONG $0xc40f4266; WORD $0x0e2c; BYTE $0x02 // pinsrw xmm5, word [rsi + r9], 2 LONG $0xc40f4266; WORD $0x262c; BYTE $0x03 // pinsrw xmm5, word [rsi + r12], 3 LONG $0xc40f4266; WORD $0x2e2c; BYTE $0x04 // pinsrw xmm5, word [rsi + r13], 4 - LONG $0x2cc40f66; WORD $0x051e // pinsrw xmm5, word [rsi + rbx], 5 - LONG $0x2cc40f66; WORD $0x063e // pinsrw xmm5, word [rsi + rdi], 6 + LONG $0x2cc40f66; WORD $0x053e // pinsrw xmm5, word [rsi + rdi], 5 + LONG $0x2cc40f66; WORD $0x061e // pinsrw xmm5, word [rsi + rbx], 6 LONG $0x44c40f66; WORD $0x020e; BYTE $0x01 // pinsrw xmm0, word [rsi + rcx + 2], 1 - QUAD $0x02020644c40f4266 // pinsrw xmm0, word [rsi + r8 + 2], 2 + QUAD $0x02020e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 2], 2 QUAD $0x03022644c40f4266 // pinsrw xmm0, word [rsi + r12 + 2], 3 QUAD $0x04022e44c40f4266 // pinsrw xmm0, word [rsi + r13 + 2], 4 - LONG $0x44c40f66; WORD $0x021e; BYTE $0x05 // pinsrw xmm0, word [rsi + rbx + 2], 5 - LONG $0x44c40f66; WORD $0x023e; BYTE $0x06 // pinsrw xmm0, word [rsi + rdi + 2], 6 - LONG $0xc0c98149; WORD $0x0001; BYTE $0x00 // or r9, 448 - QUAD $0x07020e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 2], 7 + LONG $0x44c40f66; WORD $0x023e; BYTE $0x05 // pinsrw xmm0, word [rsi + rdi + 2], 5 + LONG $0x44c40f66; WORD $0x021e; BYTE $0x06 // pinsrw xmm0, word [rsi + rbx + 2], 6 + LONG $0xc0c88149; WORD $0x0001; BYTE $0x00 // or r8, 448 + QUAD $0x07020644c40f4266 // pinsrw xmm0, word [rsi + r8 + 2], 7 LONG $0xd06e0f66 // movd xmm2, eax LONG $0x44b70f42; WORD $0x163e // movzx eax, word [rsi + r15 + 22] LONG $0x10244489 // mov dword [rsp + 16], eax LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 LONG $0x4cc40f66; WORD $0x040e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 4], 1 - QUAD $0x0204064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 4], 2 + QUAD $0x02040e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 4], 2 QUAD $0x0304264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 4], 3 QUAD $0x04042e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 4], 4 - LONG $0x4cc40f66; WORD $0x041e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 4], 5 - LONG $0x4cc40f66; WORD $0x043e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 4], 6 - QUAD $0x07040e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 4], 7 + LONG $0x4cc40f66; WORD $0x043e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 4], 5 + LONG $0x4cc40f66; WORD $0x041e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 4], 6 + QUAD $0x0704064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 4], 7 LONG $0xc0630f66 // packsswb xmm0, xmm0 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 QUAD $0x0000808d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 128[rbp] /* [rip + .LCPI4_8] */ @@ -23583,27 +23796,27 @@ LBB4_186: LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xca // movd xmm1, r10d LONG $0x54b70f46; WORD $0x183e // movzx r10d, word [rsi + r15 + 24] - LONG $0xc40f4266; WORD $0x0e2c; BYTE $0x07 // pinsrw xmm5, word [rsi + r9], 7 + LONG $0xc40f4266; WORD $0x062c; BYTE $0x07 // pinsrw xmm5, word [rsi + r8], 7 LONG $0x750f4166; BYTE $0xeb // pcmpeqw xmm5, xmm11 LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 LONG $0xe8ef0f66 // pxor xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0x7cc40f66; WORD $0x060e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 6], 1 - QUAD $0x0206067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 6], 2 + QUAD $0x02060e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 6], 2 QUAD $0x0306267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 6], 3 QUAD $0x04062e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 6], 4 - LONG $0x7cc40f66; WORD $0x061e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 6], 5 - LONG $0x7cc40f66; WORD $0x063e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 6], 6 - QUAD $0x07060e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 6], 7 + LONG $0x7cc40f66; WORD $0x063e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 6], 5 + LONG $0x7cc40f66; WORD $0x061e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 6], 6 + QUAD $0x0706067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 6], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 LONG $0xff630f66 // packsswb xmm7, xmm7 QUAD $0x01080e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 8], 1 - QUAD $0x02080644c40f4666 // pinsrw xmm8, word [rsi + r8 + 8], 2 + QUAD $0x02080e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 8], 2 QUAD $0x03082644c40f4666 // pinsrw xmm8, word [rsi + r12 + 8], 3 QUAD $0x04082e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 8], 4 - QUAD $0x05081e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 8], 5 - QUAD $0x06083e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 8], 6 - QUAD $0x07080e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 8], 7 + QUAD $0x05083e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 8], 5 + QUAD $0x06081e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 8], 6 + QUAD $0x07080644c40f4666 // pinsrw xmm8, word [rsi + r8 + 8], 7 LONG $0xddf80f66 // psubb xmm3, xmm5 QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI4_10] */ LONG $0xc76f0f66 // movdqa xmm0, xmm7 @@ -23619,20 +23832,20 @@ LBB4_186: LONG $0xf26e0f66 // movd xmm6, edx LONG $0x5cb70f46; WORD $0x1c3e // movzx r11d, word [rsi + r15 + 28] LONG $0x64c40f66; WORD $0x0a0e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 10], 1 - QUAD $0x020a0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 10], 2 + QUAD $0x020a0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 10], 2 QUAD $0x030a2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 10], 3 QUAD $0x040a2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 10], 4 - LONG $0x64c40f66; WORD $0x0a1e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 10], 5 - LONG $0x64c40f66; WORD $0x0a3e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 10], 6 - QUAD $0x070a0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 10], 7 + LONG $0x64c40f66; WORD $0x0a3e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 10], 5 + LONG $0x64c40f66; WORD $0x0a1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 10], 6 + QUAD $0x070a0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 10], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0x54c40f66; WORD $0x0c0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 12], 1 - QUAD $0x020c0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 12], 2 + QUAD $0x020c0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 12], 2 QUAD $0x030c2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 12], 3 QUAD $0x040c2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 12], 4 - LONG $0x54c40f66; WORD $0x0c1e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 12], 5 - LONG $0x54c40f66; WORD $0x0c3e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 12], 6 + LONG $0x54c40f66; WORD $0x0c3e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 12], 5 + LONG $0x54c40f66; WORD $0x0c1e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 12], 6 LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI4_12] */ LONG $0xc46f0f66 // movdqa xmm0, xmm4 @@ -23640,7 +23853,7 @@ LBB4_186: LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d LONG $0x54b70f42; WORD $0x1e3e // movzx edx, word [rsi + r15 + 30] LONG $0x30245489 // mov dword [rsp + 48], edx - QUAD $0x070c0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 12], 7 + QUAD $0x070c0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 12], 7 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 @@ -23649,27 +23862,27 @@ LBB4_186: LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 LONG $0x5c6e0f66; WORD $0x1024 // movd xmm3, dword [rsp + 16] LONG $0x54b70f42; WORD $0x203e // movzx edx, word [rsi + r15 + 32] - LONG $0x28245489 // mov dword [rsp + 40], edx + LONG $0x20245489 // mov dword [rsp + 32], edx LONG $0x4cc40f66; WORD $0x0e0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 14], 1 - QUAD $0x020e064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 14], 2 + QUAD $0x020e0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 14], 2 QUAD $0x030e264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 14], 3 QUAD $0x040e2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 14], 4 - LONG $0x4cc40f66; WORD $0x0e1e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 14], 5 - LONG $0x4cc40f66; WORD $0x0e3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 14], 6 + LONG $0x4cc40f66; WORD $0x0e3e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 14], 5 + LONG $0x4cc40f66; WORD $0x0e1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 14], 6 LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d LONG $0x54b70f42; WORD $0x223e // movzx edx, word [rsi + r15 + 34] LONG $0x10245489 // mov dword [rsp + 16], edx - QUAD $0x070e0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 14], 7 + QUAD $0x070e064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 14], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0x74c40f66; WORD $0x120e; BYTE $0x01 // pinsrw xmm6, word [rsi + rcx + 18], 1 - QUAD $0x02120674c40f4266 // pinsrw xmm6, word [rsi + r8 + 18], 2 + QUAD $0x02120e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 18], 2 QUAD $0x03122674c40f4266 // pinsrw xmm6, word [rsi + r12 + 18], 3 QUAD $0x04122e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 18], 4 - LONG $0x74c40f66; WORD $0x121e; BYTE $0x05 // pinsrw xmm6, word [rsi + rbx + 18], 5 - LONG $0x74c40f66; WORD $0x123e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 18], 6 + LONG $0x74c40f66; WORD $0x123e; BYTE $0x05 // pinsrw xmm6, word [rsi + rdi + 18], 5 + LONG $0x74c40f66; WORD $0x121e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 18], 6 LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x07120e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 18], 7 + QUAD $0x07120674c40f4266 // pinsrw xmm6, word [rsi + r8 + 18], 7 LONG $0x750f4166; BYTE $0xf3 // pcmpeqw xmm6, xmm11 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 @@ -23682,18 +23895,18 @@ LBB4_186: LONG $0xc86e0f66 // movd xmm1, eax LONG $0x74b70f46; WORD $0x243e // movzx r14d, word [rsi + r15 + 36] LONG $0x7cc40f66; WORD $0x100e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 16], 1 - QUAD $0x0210067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 16], 2 + QUAD $0x02100e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 16], 2 QUAD $0x0310267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 16], 3 QUAD $0x04102e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 16], 4 - LONG $0x7cc40f66; WORD $0x101e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 16], 5 - LONG $0x7cc40f66; WORD $0x103e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 16], 6 + LONG $0x7cc40f66; WORD $0x103e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 16], 5 + LONG $0x7cc40f66; WORD $0x101e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 16], 6 LONG $0x64c40f66; WORD $0x140e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 20], 1 - QUAD $0x02140664c40f4266 // pinsrw xmm4, word [rsi + r8 + 20], 2 + QUAD $0x02140e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 20], 2 QUAD $0x03142664c40f4266 // pinsrw xmm4, word [rsi + r12 + 20], 3 QUAD $0x04142e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 20], 4 - LONG $0x64c40f66; WORD $0x141e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 20], 5 - LONG $0x64c40f66; WORD $0x143e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 20], 6 - QUAD $0x07140e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 20], 7 + LONG $0x64c40f66; WORD $0x143e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 20], 5 + LONG $0x64c40f66; WORD $0x141e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 20], 6 + QUAD $0x07140664c40f4266 // pinsrw xmm4, word [rsi + r8 + 20], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 @@ -23702,26 +23915,26 @@ LBB4_186: LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d LONG $0x5cb70f46; WORD $0x263e // movzx r11d, word [rsi + r15 + 38] - QUAD $0x07100e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 16], 7 + QUAD $0x0710067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 16], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0xff630f66 // packsswb xmm7, xmm7 LONG $0x5cc40f66; WORD $0x160e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 22], 1 - QUAD $0x0216065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 22], 2 + QUAD $0x02160e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 22], 2 QUAD $0x0316265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 22], 3 QUAD $0x04162e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 22], 4 - LONG $0x5cc40f66; WORD $0x161e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 22], 5 - LONG $0x5cc40f66; WORD $0x163e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 22], 6 - QUAD $0x07160e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 22], 7 + LONG $0x5cc40f66; WORD $0x163e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 22], 5 + LONG $0x5cc40f66; WORD $0x161e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 22], 6 + QUAD $0x0716065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 22], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0x54c40f66; WORD $0x180e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 24], 1 - QUAD $0x02180654c40f4266 // pinsrw xmm2, word [rsi + r8 + 24], 2 + QUAD $0x02180e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 24], 2 QUAD $0x03182654c40f4266 // pinsrw xmm2, word [rsi + r12 + 24], 3 QUAD $0x04182e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 24], 4 - LONG $0x54c40f66; WORD $0x181e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 24], 5 - LONG $0x54c40f66; WORD $0x183e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 24], 6 - QUAD $0x07180e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 24], 7 + LONG $0x54c40f66; WORD $0x183e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 24], 5 + LONG $0x54c40f66; WORD $0x181e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 24], 6 + QUAD $0x07180654c40f4266 // pinsrw xmm2, word [rsi + r8 + 24], 7 LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI4_10] */ LONG $0x6f0f4566; BYTE $0xf2 // movdqa xmm14, xmm10 @@ -23736,31 +23949,31 @@ LBB4_186: LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 LONG $0xc26f0f66 // movdqa xmm0, xmm2 LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 - LONG $0x7c6e0f66; WORD $0x2824 // movd xmm7, dword [rsp + 40] + LONG $0x7c6e0f66; WORD $0x2024 // movd xmm7, dword [rsp + 32] LONG $0x54b70f46; WORD $0x2a3e // movzx r10d, word [rsi + r15 + 42] LONG $0x4cc40f66; WORD $0x1a0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 26], 1 - QUAD $0x021a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 26], 2 + QUAD $0x021a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 26], 2 QUAD $0x031a264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 26], 3 QUAD $0x041a2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 26], 4 - LONG $0x4cc40f66; WORD $0x1a1e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 26], 5 - LONG $0x4cc40f66; WORD $0x1a3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 26], 6 - QUAD $0x071a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 26], 7 + LONG $0x4cc40f66; WORD $0x1a3e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 26], 5 + LONG $0x4cc40f66; WORD $0x1a1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 26], 6 + QUAD $0x071a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 26], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0x64c40f66; WORD $0x1c0e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 28], 1 - QUAD $0x021c0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 28], 2 + QUAD $0x021c0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 28], 2 QUAD $0x031c2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 28], 3 QUAD $0x041c2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 28], 4 - LONG $0x64c40f66; WORD $0x1c1e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 28], 5 - LONG $0x64c40f66; WORD $0x1c3e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 28], 6 + LONG $0x64c40f66; WORD $0x1c3e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 28], 5 + LONG $0x64c40f66; WORD $0x1c1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 28], 6 LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI4_12] */ LONG $0xc16f0f66 // movdqa xmm0, xmm1 LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 LONG $0x546e0f66; WORD $0x1024 // movd xmm2, dword [rsp + 16] LONG $0x54b70f42; WORD $0x2c3e // movzx edx, word [rsi + r15 + 44] - LONG $0x28245489 // mov dword [rsp + 40], edx - QUAD $0x071c0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 28], 7 + LONG $0x20245489 // mov dword [rsp + 32], edx + QUAD $0x071c0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 28], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 @@ -23771,24 +23984,24 @@ LBB4_186: LONG $0x54b70f42; WORD $0x2e3e // movzx edx, word [rsi + r15 + 46] LONG $0x10245489 // mov dword [rsp + 16], edx LONG $0x5cc40f66; WORD $0x1e0e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 30], 1 - QUAD $0x021e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 30], 2 + QUAD $0x021e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 30], 2 QUAD $0x031e265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 30], 3 QUAD $0x041e2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 30], 4 - LONG $0x5cc40f66; WORD $0x1e1e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 30], 5 - LONG $0x5cc40f66; WORD $0x1e3e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 30], 6 + LONG $0x5cc40f66; WORD $0x1e3e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 30], 5 + LONG $0x5cc40f66; WORD $0x1e1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 30], 6 LONG $0xf5eb0f66 // por xmm6, xmm5 LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d LONG $0x5cb70f46; WORD $0x303e // movzx r11d, word [rsi + r15 + 48] - QUAD $0x071e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 30], 7 + QUAD $0x071e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 30], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0x54c40f66; WORD $0x220e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 34], 1 - QUAD $0x02220654c40f4266 // pinsrw xmm2, word [rsi + r8 + 34], 2 + QUAD $0x02220e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 34], 2 QUAD $0x03222654c40f4266 // pinsrw xmm2, word [rsi + r12 + 34], 3 QUAD $0x04222e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 34], 4 - LONG $0x54c40f66; WORD $0x221e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 34], 5 - LONG $0x54c40f66; WORD $0x223e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 34], 6 + LONG $0x54c40f66; WORD $0x223e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 34], 5 + LONG $0x54c40f66; WORD $0x221e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 34], 6 LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07220e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 34], 7 + QUAD $0x07220654c40f4266 // pinsrw xmm2, word [rsi + r8 + 34], 7 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 @@ -23802,18 +24015,18 @@ LBB4_186: LONG $0xd06e0f66 // movd xmm2, eax LONG $0x74b70f46; WORD $0x323e // movzx r14d, word [rsi + r15 + 50] LONG $0x7cc40f66; WORD $0x200e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 32], 1 - QUAD $0x0220067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 32], 2 + QUAD $0x02200e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 32], 2 QUAD $0x0320267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 32], 3 QUAD $0x04202e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 32], 4 - LONG $0x7cc40f66; WORD $0x201e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 32], 5 - LONG $0x7cc40f66; WORD $0x203e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 32], 6 + LONG $0x7cc40f66; WORD $0x203e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 32], 5 + LONG $0x7cc40f66; WORD $0x201e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 32], 6 LONG $0x64c40f66; WORD $0x240e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 36], 1 - QUAD $0x02240664c40f4266 // pinsrw xmm4, word [rsi + r8 + 36], 2 + QUAD $0x02240e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 36], 2 QUAD $0x03242664c40f4266 // pinsrw xmm4, word [rsi + r12 + 36], 3 QUAD $0x04242e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 36], 4 - LONG $0x64c40f66; WORD $0x241e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 36], 5 - LONG $0x64c40f66; WORD $0x243e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 36], 6 - QUAD $0x07240e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 36], 7 + LONG $0x64c40f66; WORD $0x243e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 36], 5 + LONG $0x64c40f66; WORD $0x241e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 36], 6 + QUAD $0x07240664c40f4266 // pinsrw xmm4, word [rsi + r8 + 36], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 @@ -23822,31 +24035,31 @@ LBB4_186: LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d LONG $0x54b70f42; WORD $0x343e // movzx edx, word [rsi + r15 + 52] - QUAD $0x07200e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 32], 7 + QUAD $0x0720067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 32], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0xff630f66 // packsswb xmm7, xmm7 LONG $0x4cc40f66; WORD $0x260e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 38], 1 - QUAD $0x0226064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 38], 2 + QUAD $0x02260e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 38], 2 QUAD $0x0326264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 38], 3 QUAD $0x04262e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 38], 4 - LONG $0x4cc40f66; WORD $0x261e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 38], 5 - LONG $0x4cc40f66; WORD $0x263e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 38], 6 - QUAD $0x07260e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 38], 7 + LONG $0x4cc40f66; WORD $0x263e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 38], 5 + LONG $0x4cc40f66; WORD $0x261e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 38], 6 + QUAD $0x0726064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 38], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0x54c40f66; WORD $0x280e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 40], 1 - QUAD $0x02280654c40f4266 // pinsrw xmm2, word [rsi + r8 + 40], 2 + QUAD $0x02280e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 40], 2 QUAD $0x03282654c40f4266 // pinsrw xmm2, word [rsi + r12 + 40], 3 QUAD $0x04282e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 40], 4 - LONG $0x54c40f66; WORD $0x281e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 40], 5 - LONG $0x54c40f66; WORD $0x283e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 40], 6 - QUAD $0x07280e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 40], 7 + LONG $0x54c40f66; WORD $0x283e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 40], 5 + LONG $0x54c40f66; WORD $0x281e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 40], 6 + QUAD $0x07280654c40f4266 // pinsrw xmm2, word [rsi + r8 + 40], 7 LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 LONG $0x6f0f4166; BYTE $0xea // movdqa xmm5, xmm10 LONG $0xc16f0f66 // movdqa xmm0, xmm1 LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 - LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] + LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] LONG $0x54b70f46; WORD $0x363e // movzx r10d, word [rsi + r15 + 54] LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xd2630f66 // packsswb xmm2, xmm2 @@ -23857,20 +24070,20 @@ LBB4_186: LONG $0x646e0f66; WORD $0x1024 // movd xmm4, dword [rsp + 16] LONG $0x44b70f42; WORD $0x383e // movzx eax, word [rsi + r15 + 56] LONG $0x5cc40f66; WORD $0x2a0e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 42], 1 - QUAD $0x022a065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 42], 2 + QUAD $0x022a0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 42], 2 QUAD $0x032a265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 42], 3 QUAD $0x042a2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 42], 4 - LONG $0x5cc40f66; WORD $0x2a1e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 42], 5 - LONG $0x5cc40f66; WORD $0x2a3e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 42], 6 - QUAD $0x072a0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 42], 7 + LONG $0x5cc40f66; WORD $0x2a3e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 42], 5 + LONG $0x5cc40f66; WORD $0x2a1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 42], 6 + QUAD $0x072a065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 42], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0x4cc40f66; WORD $0x2c0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 44], 1 - QUAD $0x022c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 44], 2 + QUAD $0x022c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 44], 2 QUAD $0x032c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 44], 3 QUAD $0x042c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 44], 4 - LONG $0x4cc40f66; WORD $0x2c1e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 44], 5 - LONG $0x4cc40f66; WORD $0x2c3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 44], 6 + LONG $0x4cc40f66; WORD $0x2c3e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 44], 5 + LONG $0x4cc40f66; WORD $0x2c1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 44], 6 LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 QUAD $0x0000c08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 192[rbp] /* [rip + .LCPI4_12] */ LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 @@ -23878,7 +24091,7 @@ LBB4_186: LONG $0x380f4166; WORD $0xd710 // pblendvb xmm2, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d LONG $0x5cb70f46; WORD $0x3a3e // movzx r11d, word [rsi + r15 + 58] - QUAD $0x072c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 44], 7 + QUAD $0x072c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 44], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xd6eb0f66 // por xmm2, xmm6 @@ -23891,12 +24104,12 @@ LBB4_186: LONG $0xf2eb0f66 // por xmm6, xmm2 LONG $0xd26e0f66 // movd xmm2, edx LONG $0x64c40f66; WORD $0x2e0e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 46], 1 - QUAD $0x022e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 46], 2 + QUAD $0x022e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 46], 2 QUAD $0x032e2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 46], 3 QUAD $0x042e2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 46], 4 - LONG $0x64c40f66; WORD $0x2e1e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 46], 5 - LONG $0x64c40f66; WORD $0x2e3e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 46], 6 - QUAD $0x072e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 46], 7 + LONG $0x64c40f66; WORD $0x2e3e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 46], 5 + LONG $0x64c40f66; WORD $0x2e1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 46], 6 + QUAD $0x072e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 46], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xf5eb0f66 // por xmm6, xmm5 @@ -23905,12 +24118,12 @@ LBB4_186: LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d LONG $0x4cc40f66; WORD $0x320e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 50], 1 - QUAD $0x0232064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 2 + QUAD $0x02320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 2 QUAD $0x0332264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 50], 3 QUAD $0x04322e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 50], 4 - LONG $0x4cc40f66; WORD $0x321e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 50], 5 - LONG $0x4cc40f66; WORD $0x323e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 50], 6 - QUAD $0x07320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 7 + LONG $0x4cc40f66; WORD $0x323e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 50], 5 + LONG $0x4cc40f66; WORD $0x321e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 50], 6 + QUAD $0x0732064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 @@ -23919,40 +24132,40 @@ LBB4_186: LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 LONG $0xc86e0f66 // movd xmm1, eax LONG $0x7cc40f66; WORD $0x300e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 48], 1 - QUAD $0x0230067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 48], 2 + QUAD $0x02300e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 48], 2 QUAD $0x0330267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 48], 3 QUAD $0x04302e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 48], 4 - LONG $0x7cc40f66; WORD $0x301e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 48], 5 - LONG $0x7cc40f66; WORD $0x303e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 48], 6 - QUAD $0x07300e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 48], 7 + LONG $0x7cc40f66; WORD $0x303e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 48], 5 + LONG $0x7cc40f66; WORD $0x301e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 48], 6 + QUAD $0x0730067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 48], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0x54c40f66; WORD $0x340e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 52], 1 - QUAD $0x02340654c40f4266 // pinsrw xmm2, word [rsi + r8 + 52], 2 + QUAD $0x02340e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 52], 2 QUAD $0x03342654c40f4266 // pinsrw xmm2, word [rsi + r12 + 52], 3 QUAD $0x04342e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 52], 4 - LONG $0x54c40f66; WORD $0x341e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 52], 5 - LONG $0x54c40f66; WORD $0x343e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 52], 6 + LONG $0x54c40f66; WORD $0x343e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 52], 5 + LONG $0x54c40f66; WORD $0x341e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 52], 6 LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x07340e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 52], 7 + QUAD $0x07340654c40f4266 // pinsrw xmm2, word [rsi + r8 + 52], 7 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0x5cc40f66; WORD $0x360e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 54], 1 - QUAD $0x0236065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 54], 2 + QUAD $0x02360e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 54], 2 QUAD $0x0336265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 54], 3 QUAD $0x04362e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 54], 4 - LONG $0x5cc40f66; WORD $0x361e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 54], 5 - LONG $0x5cc40f66; WORD $0x363e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 54], 6 + LONG $0x5cc40f66; WORD $0x363e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 54], 5 + LONG $0x5cc40f66; WORD $0x361e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 54], 6 LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x07360e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 54], 7 + QUAD $0x0736065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 54], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0x4cc40f66; WORD $0x380e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 56], 1 - QUAD $0x0238064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 56], 2 + QUAD $0x02380e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 56], 2 QUAD $0x0338264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 56], 3 QUAD $0x04382e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 56], 4 - LONG $0x4cc40f66; WORD $0x381e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 56], 5 - LONG $0x4cc40f66; WORD $0x383e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 56], 6 + LONG $0x4cc40f66; WORD $0x383e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 56], 5 + LONG $0x4cc40f66; WORD $0x381e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 56], 6 LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07380e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 56], 7 + QUAD $0x0738064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 56], 7 LONG $0xe7f80f66 // psubb xmm4, xmm7 QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI4_9] */ LONG $0xc26f0f66 // movdqa xmm0, xmm2 @@ -23963,24 +24176,24 @@ LBB4_186: LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0x54c40f66; WORD $0x3a0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 58], 1 - QUAD $0x023a0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 58], 2 + QUAD $0x023a0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 58], 2 QUAD $0x033a2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 58], 3 QUAD $0x043a2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 58], 4 - LONG $0x54c40f66; WORD $0x3a1e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 58], 5 - LONG $0x54c40f66; WORD $0x3a3e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 58], 6 - QUAD $0x073a0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 58], 7 + LONG $0x54c40f66; WORD $0x3a3e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 58], 5 + LONG $0x54c40f66; WORD $0x3a1e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 58], 6 + QUAD $0x073a0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 58], 7 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xf5eb0f66 // por xmm6, xmm5 LONG $0x6e0f4166; BYTE $0xde // movd xmm3, r14d LONG $0x5cc40f66; WORD $0x3c0e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 60], 1 - QUAD $0x023c065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 60], 2 + QUAD $0x023c0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 60], 2 QUAD $0x033c265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 60], 3 QUAD $0x043c2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 60], 4 - LONG $0x5cc40f66; WORD $0x3c1e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 60], 5 - LONG $0x5cc40f66; WORD $0x3c3e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 60], 6 + LONG $0x5cc40f66; WORD $0x3c3e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 60], 5 + LONG $0x5cc40f66; WORD $0x3c1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 60], 6 LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x073c0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 60], 7 + QUAD $0x073c065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 60], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xf4eb0f66 // por xmm6, xmm4 @@ -23997,441 +24210,71 @@ LBB4_186: LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 LONG $0xc06e0f66 // movd xmm0, eax LONG $0x44c40f66; WORD $0x3e0e; BYTE $0x01 // pinsrw xmm0, word [rsi + rcx + 62], 1 - QUAD $0x023e0644c40f4266 // pinsrw xmm0, word [rsi + r8 + 62], 2 + QUAD $0x023e0e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 62], 2 QUAD $0x033e2644c40f4266 // pinsrw xmm0, word [rsi + r12 + 62], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] QUAD $0x043e2e44c40f4266 // pinsrw xmm0, word [rsi + r13 + 62], 4 - LONG $0x44c40f66; WORD $0x3e1e; BYTE $0x05 // pinsrw xmm0, word [rsi + rbx + 62], 5 - LONG $0x44c40f66; WORD $0x3e3e; BYTE $0x06 // pinsrw xmm0, word [rsi + rdi + 62], 6 - QUAD $0x073e0e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 62], 7 + LONG $0x44c40f66; WORD $0x3e3e; BYTE $0x05 // pinsrw xmm0, word [rsi + rdi + 62], 5 + LONG $0x44c40f66; WORD $0x3e1e; BYTE $0x06 // pinsrw xmm0, word [rsi + rbx + 62], 6 + QUAD $0x073e0644c40f4266 // pinsrw xmm0, word [rsi + r8 + 62], 7 LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xeb0f4466; BYTE $0xd6 // por xmm10, xmm6 - LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 - LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 - LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 - LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 - LONG $0x6c0f4166; BYTE $0xd6 // punpcklqdq xmm2, xmm14 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI4_15] */ - LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 - LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 - LONG $0xc2610f66 // punpcklwd xmm0, xmm2 - LONG $0x600f4566; BYTE $0xc6 // punpcklbw xmm8, xmm14 - LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 - LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - LONG $0x7f0f44f3; WORD $0x8824 // movdqu oword [rax + 4*rcx], xmm12 - LONG $0x447f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm0 - LONG $0x08c18348 // add rcx, 8 - WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB4_186 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - LONG $0x24543b4c; BYTE $0x20 // cmp r10, qword [rsp + 32] - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - LONG $0x246c8b44; BYTE $0x40 // mov r13d, dword [rsp + 64] - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - JNE LBB4_92 - JMP LBB4_95 - -LBB4_188: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - LONG $0xfce08349 // and r8, -4 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - LONG $0x07e3c148 // shl rbx, 7 - WORD $0x0148; BYTE $0xf3 // add rbx, rsi - LONG $0x843c8d4f // lea r15, [r12 + 4*r8] - WORD $0x280f; BYTE $0xc8 // movaps xmm1, xmm0 - LONG $0x00c8c60f // shufps xmm1, xmm0, 0 - LONG $0xfcc68148; WORD $0x0001; BYTE $0x00 // add rsi, 508 - WORD $0xc931 // xor ecx, ecx - LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI4_0] */ - LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI4_1] */ - LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI4_2] */ - LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI4_3] */ - LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI4_4] */ - LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI4_5] */ - LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI4_6] */ - LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI4_7] */ - -LBB4_189: - QUAD $0xfffffe04b6100ff3 // movss xmm6, dword [rsi - 508] - QUAD $0xfffffe08be100ff3 // movss xmm7, dword [rsi - 504] - QUAD $0xfffffe0cae100ff3 // movss xmm5, dword [rsi - 500] - QUAD $0xfffffe10a6100ff3 // movss xmm4, dword [rsi - 496] - QUAD $0xfffe84b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 380], 16 - QUAD $0xffff04b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 252], 32 - LONG $0x213a0f66; WORD $0x8476; BYTE $0x30 // insertps xmm6, dword [rsi - 124], 48 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - QUAD $0xfffe88be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 376], 16 - QUAD $0xffff08be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 248], 32 - LONG $0x213a0f66; WORD $0x887e; BYTE $0x30 // insertps xmm7, dword [rsi - 120], 48 - QUAD $0xfffe8cae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 372], 16 - QUAD $0xffff0cae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 244], 32 - LONG $0x213a0f66; WORD $0x8c6e; BYTE $0x30 // insertps xmm5, dword [rsi - 116], 48 - QUAD $0xfffe90a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 368], 16 - QUAD $0xffff10a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 240], 32 - LONG $0x213a0f66; WORD $0x9066; BYTE $0x30 // insertps xmm4, dword [rsi - 112], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xd76f0f66 // movdqa xmm2, xmm7 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xd7f80f66 // psubb xmm2, xmm7 - QUAD $0xfffffe14be100ff3 // movss xmm7, dword [rsi - 492] - QUAD $0xfffe94be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 364], 16 - QUAD $0xffff14be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 236], 32 - LONG $0x213a0f66; WORD $0x947e; BYTE $0x30 // insertps xmm7, dword [rsi - 108], 48 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffffe18b6100ff3 // movss xmm6, dword [rsi - 488] - QUAD $0xfffe98b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 360], 16 - QUAD $0xffff18b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 232], 32 - LONG $0x213a0f66; WORD $0x9876; BYTE $0x30 // insertps xmm6, dword [rsi - 104], 48 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 - LONG $0xeaeb0f66 // por xmm5, xmm2 - QUAD $0xfffffe1c9e100ff3 // movss xmm3, dword [rsi - 484] - QUAD $0xfffe9c9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 356], 16 - QUAD $0xffff1c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 228], 32 - LONG $0x213a0f66; WORD $0x9c5e; BYTE $0x30 // insertps xmm3, dword [rsi - 100], 48 - LONG $0x04e1c20f // cmpneqps xmm4, xmm1 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xf4710f66; BYTE $0x03 // psllw xmm4, 3 - LONG $0xdb0f4166; BYTE $0xe2 // pand xmm4, xmm10 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x04 // psllw xmm7, 4 - LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 - LONG $0xfceb0f66 // por xmm7, xmm4 - QUAD $0xfffffe20a6100ff3 // movss xmm4, dword [rsi - 480] - QUAD $0xfffea0a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 352], 16 - QUAD $0xffff20a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 224], 32 - LONG $0x213a0f66; WORD $0xa066; BYTE $0x30 // insertps xmm4, dword [rsi - 96], 48 - LONG $0xfdeb0f66 // por xmm7, xmm5 - QUAD $0xfffffe24ae100ff3 // movss xmm5, dword [rsi - 476] - QUAD $0xfffea4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 348], 16 - QUAD $0xffff24ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 220], 32 - LONG $0x213a0f66; WORD $0xa46e; BYTE $0x30 // insertps xmm5, dword [rsi - 92], 48 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 - LONG $0xdb0f4166; BYTE $0xdd // pand xmm3, xmm13 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe2896100ff3 // movss xmm2, dword [rsi - 472] - QUAD $0xfffea896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 344], 16 - QUAD $0xffff2896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 216], 32 - LONG $0x213a0f66; WORD $0xa856; BYTE $0x30 // insertps xmm2, dword [rsi - 88], 48 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0x04e1c20f // cmpneqps xmm4, xmm1 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 - LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 - LONG $0xe3eb0f66 // por xmm4, xmm3 - QUAD $0xfffffe2c9e100ff3 // movss xmm3, dword [rsi - 468] - QUAD $0xfffeac9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 340], 16 - QUAD $0xffff2c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 212], 32 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0x213a0f66; WORD $0xac5e; BYTE $0x30 // insertps xmm3, dword [rsi - 84], 48 - LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf26f0f66 // movdqa xmm6, xmm2 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf2f80f66 // psubb xmm6, xmm2 - QUAD $0xfffffe30be100ff3 // movss xmm7, dword [rsi - 464] - QUAD $0xfffeb0be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 336], 16 - QUAD $0xffff30be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 208], 32 - LONG $0x213a0f66; WORD $0xb07e; BYTE $0x30 // insertps xmm7, dword [rsi - 80], 48 - LONG $0xf5eb0f66 // por xmm6, xmm5 - QUAD $0xfffffe34ae100ff3 // movss xmm5, dword [rsi - 460] - QUAD $0xfffeb4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 332], 16 - QUAD $0xffff34ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 204], 32 - LONG $0x213a0f66; WORD $0xb46e; BYTE $0x30 // insertps xmm5, dword [rsi - 76], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe38b6100ff3 // movss xmm6, dword [rsi - 456] - QUAD $0xfffeb8b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 328], 16 - QUAD $0xffff38b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 200], 32 - LONG $0x213a0f66; WORD $0xb876; BYTE $0x30 // insertps xmm6, dword [rsi - 72], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x03 // psllw xmm7, 3 - LONG $0xdb0f4166; BYTE $0xfa // pand xmm7, xmm10 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 - LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 - LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0xfffffe3c96100ff3 // movss xmm2, dword [rsi - 452] - QUAD $0xfffebc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 324], 16 - QUAD $0xffff3c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 196], 32 - LONG $0x213a0f66; WORD $0xbc56; BYTE $0x30 // insertps xmm2, dword [rsi - 68], 48 - LONG $0xebeb0f66 // por xmm5, xmm3 - QUAD $0xfffffe40be100ff3 // movss xmm7, dword [rsi - 448] - QUAD $0xfffec0be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 320], 16 - QUAD $0xffff40be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 192], 32 - LONG $0x213a0f66; WORD $0xc07e; BYTE $0x30 // insertps xmm7, dword [rsi - 64], 48 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffffe44b6100ff3 // movss xmm6, dword [rsi - 444] - QUAD $0xfffec4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 316], 16 - QUAD $0xffff44b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 188], 32 - LONG $0x213a0f66; WORD $0xc476; BYTE $0x30 // insertps xmm6, dword [rsi - 60], 48 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xf7710f66; BYTE $0x07 // psllw xmm7, 7 - LONG $0xdb0f4166; BYTE $0xfe // pand xmm7, xmm14 - LONG $0xfaeb0f66 // por xmm7, xmm2 - QUAD $0xfffffe4896100ff3 // movss xmm2, dword [rsi - 440] - QUAD $0xfffec896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 312], 16 - QUAD $0xffff4896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 184], 32 - LONG $0x213a0f66; WORD $0xc856; BYTE $0x30 // insertps xmm2, dword [rsi - 56], 48 - LONG $0xfdeb0f66 // por xmm7, xmm5 - QUAD $0xfffffe4c9e100ff3 // movss xmm3, dword [rsi - 436] - QUAD $0xfffecc9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 308], 16 - QUAD $0xffff4c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 180], 32 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0x213a0f66; WORD $0xcc5e; BYTE $0x30 // insertps xmm3, dword [rsi - 52], 48 - LONG $0xe7620f66 // punpckldq xmm4, xmm7 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xfa6f0f66 // movdqa xmm7, xmm2 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xfaf80f66 // psubb xmm7, xmm2 - QUAD $0xfffffe50ae100ff3 // movss xmm5, dword [rsi - 432] - QUAD $0xfffed0ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 304], 16 - QUAD $0xffff50ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 176], 32 - LONG $0x213a0f66; WORD $0xd06e; BYTE $0x30 // insertps xmm5, dword [rsi - 48], 48 - LONG $0xfeeb0f66 // por xmm7, xmm6 - QUAD $0xfffffe54b6100ff3 // movss xmm6, dword [rsi - 428] - QUAD $0xfffed4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 300], 16 - QUAD $0xffff54b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 172], 32 - LONG $0x213a0f66; WORD $0xd476; BYTE $0x30 // insertps xmm6, dword [rsi - 44], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdfeb0f66 // por xmm3, xmm7 - QUAD $0xfffffe58be100ff3 // movss xmm7, dword [rsi - 424] - QUAD $0xfffed8be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 296], 16 - QUAD $0xffff58be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 168], 32 - LONG $0x213a0f66; WORD $0xd87e; BYTE $0x30 // insertps xmm7, dword [rsi - 40], 48 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 - LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf5eb0f66 // por xmm6, xmm5 - QUAD $0xfffffe5c96100ff3 // movss xmm2, dword [rsi - 420] - QUAD $0xfffedc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 292], 16 - QUAD $0xffff5c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 164], 32 - LONG $0x213a0f66; WORD $0xdc56; BYTE $0x30 // insertps xmm2, dword [rsi - 36], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffffe60ae100ff3 // movss xmm5, dword [rsi - 416] - QUAD $0xfffee0ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 288], 16 - QUAD $0xffff60ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 160], 32 - LONG $0x213a0f66; WORD $0xe06e; BYTE $0x30 // insertps xmm5, dword [rsi - 32], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffffe64be100ff3 // movss xmm7, dword [rsi - 412] - QUAD $0xfffee4be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 284], 16 - QUAD $0xffff64be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 156], 32 - LONG $0x213a0f66; WORD $0xe47e; BYTE $0x30 // insertps xmm7, dword [rsi - 28], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xf5710f66; BYTE $0x07 // psllw xmm5, 7 - LONG $0xdb0f4166; BYTE $0xee // pand xmm5, xmm14 - LONG $0xeaeb0f66 // por xmm5, xmm2 - QUAD $0xfffffe6896100ff3 // movss xmm2, dword [rsi - 408] - QUAD $0xfffee896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 280], 16 - QUAD $0xffff6896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 152], 32 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0x213a0f66; WORD $0xe856; BYTE $0x30 // insertps xmm2, dword [rsi - 24], 48 - LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf26f0f66 // movdqa xmm6, xmm2 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf2f80f66 // psubb xmm6, xmm2 - QUAD $0xfffffe6c9e100ff3 // movss xmm3, dword [rsi - 404] - QUAD $0xfffeec9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 276], 16 - QUAD $0xffff6c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 148], 32 - LONG $0x213a0f66; WORD $0xec5e; BYTE $0x30 // insertps xmm3, dword [rsi - 20], 48 - LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0xfffffe7096100ff3 // movss xmm2, dword [rsi - 400] - QUAD $0xfffef096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 272], 16 - QUAD $0xffff7096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 144], 32 - LONG $0x213a0f66; WORD $0xf056; BYTE $0x30 // insertps xmm2, dword [rsi - 16], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] - QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 - QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 - LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf2eb0f66 // por xmm6, xmm2 - QUAD $0xfffffe78be100ff3 // movss xmm7, dword [rsi - 392] - QUAD $0xfffef8be213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 264], 16 - QUAD $0xffff78be213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 136], 32 - LONG $0x213a0f66; WORD $0xf87e; BYTE $0x30 // insertps xmm7, dword [rsi - 8], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffffe7c96100ff3 // movss xmm2, dword [rsi - 388] - QUAD $0xfffefc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 260], 16 - QUAD $0xffff7c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 132], 32 - LONG $0x213a0f66; WORD $0xfc56; BYTE $0x30 // insertps xmm2, dword [rsi - 4], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffffe809e100ff3 // movss xmm3, dword [rsi - 384] - QUAD $0xffff009e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 256], 16 - LONG $0x213a0f66; WORD $0x805e; BYTE $0x20 // insertps xmm3, dword [rsi - 128], 32 - LONG $0x213a0f66; WORD $0x301e // insertps xmm3, dword [rsi], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0xdeeb0f66 // por xmm3, xmm6 - LONG $0xeb620f66 // punpckldq xmm5, xmm3 - LONG $0xe5600f66 // punpcklbw xmm4, xmm5 - LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 - LONG $0x7f0f41f3; WORD $0x8c24 // movdqu oword [r12 + 4*rcx], xmm4 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 - WORD $0x3949; BYTE $0xc8 // cmp r8, rcx - JNE LBB4_189 - WORD $0x394d; BYTE $0xc2 // cmp r10, r8 - JNE LBB4_134 - JMP LBB4_146 + LONG $0xeb0f4466; BYTE $0xd6 // por xmm10, xmm6 + LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 + LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 + LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 + LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 + LONG $0x6c0f4166; BYTE $0xd6 // punpcklqdq xmm2, xmm14 + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI4_15] */ + LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 + LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 + LONG $0xc2610f66 // punpcklwd xmm0, xmm2 + LONG $0x600f4566; BYTE $0xc6 // punpcklbw xmm8, xmm14 + LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 + LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + LONG $0x7f0f44f3; WORD $0x8824 // movdqu oword [rax + 4*rcx], xmm12 + LONG $0x447f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm0 + LONG $0x08c18348 // add rcx, 8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] + JNE LBB4_216 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + LONG $0x246c8b44; BYTE $0x38 // mov r13d, dword [rsp + 56] + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + JNE LBB4_141 + JMP LBB4_144 -LBB4_191: - LONG $0xf8e28349 // and r10, -8 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 +LBB4_218: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x2454894c; BYTE $0x20 // mov qword [rsp + 32], r10 - LONG $0x94048d4b // lea rax, [r12 + 4*r10] + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x244c8948; BYTE $0x28 // mov qword [rsp + 40], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - LONG $0x246c8944; BYTE $0x40 // mov dword [rsp + 64], r13d + LONG $0x246c8944; BYTE $0x38 // mov dword [rsp + 56], r13d LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 WORD $0x3145; BYTE $0xff // xor r15d, r15d - QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 LONG $0xef0f4566; BYTE $0xff // pxor xmm15, xmm15 -LBB4_192: +LBB4_219: LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06e7c149 // shl r15, 6 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 WORD $0x894d; BYTE $0xfc // mov r12, r15 WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 WORD $0x894c; BYTE $0xff // mov rdi, r15 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 LONG $0x04b70f42; BYTE $0x3e // movzx eax, word [rsi + r15] LONG $0xe86e0f66 // movd xmm5, eax LONG $0x44b70f42; WORD $0x023e // movzx eax, word [rsi + r15 + 2] @@ -24451,36 +24294,36 @@ LBB4_192: LONG $0x74b70f46; WORD $0x143e // movzx r14d, word [rsi + r15 + 20] WORD $0x894c; BYTE $0xf9 // mov rcx, r15 LONG $0x40c98348 // or rcx, 64 - LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 - LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 - LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 + LONG $0x40cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 320 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 LONG $0x2cc40f66; WORD $0x010e // pinsrw xmm5, word [rsi + rcx], 1 - LONG $0xc40f4266; WORD $0x062c; BYTE $0x02 // pinsrw xmm5, word [rsi + r8], 2 + LONG $0xc40f4266; WORD $0x0e2c; BYTE $0x02 // pinsrw xmm5, word [rsi + r9], 2 LONG $0xc40f4266; WORD $0x262c; BYTE $0x03 // pinsrw xmm5, word [rsi + r12], 3 LONG $0xc40f4266; WORD $0x2e2c; BYTE $0x04 // pinsrw xmm5, word [rsi + r13], 4 - LONG $0x2cc40f66; WORD $0x051e // pinsrw xmm5, word [rsi + rbx], 5 - LONG $0x2cc40f66; WORD $0x063e // pinsrw xmm5, word [rsi + rdi], 6 + LONG $0x2cc40f66; WORD $0x053e // pinsrw xmm5, word [rsi + rdi], 5 + LONG $0x2cc40f66; WORD $0x061e // pinsrw xmm5, word [rsi + rbx], 6 LONG $0x44c40f66; WORD $0x020e; BYTE $0x01 // pinsrw xmm0, word [rsi + rcx + 2], 1 - QUAD $0x02020644c40f4266 // pinsrw xmm0, word [rsi + r8 + 2], 2 + QUAD $0x02020e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 2], 2 QUAD $0x03022644c40f4266 // pinsrw xmm0, word [rsi + r12 + 2], 3 QUAD $0x04022e44c40f4266 // pinsrw xmm0, word [rsi + r13 + 2], 4 - LONG $0x44c40f66; WORD $0x021e; BYTE $0x05 // pinsrw xmm0, word [rsi + rbx + 2], 5 - LONG $0x44c40f66; WORD $0x023e; BYTE $0x06 // pinsrw xmm0, word [rsi + rdi + 2], 6 - LONG $0xc0c98149; WORD $0x0001; BYTE $0x00 // or r9, 448 - QUAD $0x07020e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 2], 7 + LONG $0x44c40f66; WORD $0x023e; BYTE $0x05 // pinsrw xmm0, word [rsi + rdi + 2], 5 + LONG $0x44c40f66; WORD $0x021e; BYTE $0x06 // pinsrw xmm0, word [rsi + rbx + 2], 6 + LONG $0xc0c88149; WORD $0x0001; BYTE $0x00 // or r8, 448 + QUAD $0x07020644c40f4266 // pinsrw xmm0, word [rsi + r8 + 2], 7 LONG $0xd06e0f66 // movd xmm2, eax LONG $0x44b70f42; WORD $0x163e // movzx eax, word [rsi + r15 + 22] LONG $0x10244489 // mov dword [rsp + 16], eax LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 LONG $0x4cc40f66; WORD $0x040e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 4], 1 - QUAD $0x0204064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 4], 2 + QUAD $0x02040e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 4], 2 QUAD $0x0304264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 4], 3 QUAD $0x04042e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 4], 4 - LONG $0x4cc40f66; WORD $0x041e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 4], 5 - LONG $0x4cc40f66; WORD $0x043e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 4], 6 - QUAD $0x07040e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 4], 7 + LONG $0x4cc40f66; WORD $0x043e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 4], 5 + LONG $0x4cc40f66; WORD $0x041e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 4], 6 + QUAD $0x0704064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 4], 7 LONG $0xc0630f66 // packsswb xmm0, xmm0 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 QUAD $0x0000808d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 128[rbp] /* [rip + .LCPI4_8] */ @@ -24494,27 +24337,27 @@ LBB4_192: LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xca // movd xmm1, r10d LONG $0x54b70f46; WORD $0x183e // movzx r10d, word [rsi + r15 + 24] - LONG $0xc40f4266; WORD $0x0e2c; BYTE $0x07 // pinsrw xmm5, word [rsi + r9], 7 + LONG $0xc40f4266; WORD $0x062c; BYTE $0x07 // pinsrw xmm5, word [rsi + r8], 7 LONG $0x750f4166; BYTE $0xeb // pcmpeqw xmm5, xmm11 LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 LONG $0xe8ef0f66 // pxor xmm5, xmm0 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0x7cc40f66; WORD $0x060e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 6], 1 - QUAD $0x0206067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 6], 2 + QUAD $0x02060e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 6], 2 QUAD $0x0306267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 6], 3 QUAD $0x04062e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 6], 4 - LONG $0x7cc40f66; WORD $0x061e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 6], 5 - LONG $0x7cc40f66; WORD $0x063e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 6], 6 - QUAD $0x07060e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 6], 7 + LONG $0x7cc40f66; WORD $0x063e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 6], 5 + LONG $0x7cc40f66; WORD $0x061e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 6], 6 + QUAD $0x0706067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 6], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 LONG $0xff630f66 // packsswb xmm7, xmm7 QUAD $0x01080e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 8], 1 - QUAD $0x02080644c40f4666 // pinsrw xmm8, word [rsi + r8 + 8], 2 + QUAD $0x02080e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 8], 2 QUAD $0x03082644c40f4666 // pinsrw xmm8, word [rsi + r12 + 8], 3 QUAD $0x04082e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 8], 4 - QUAD $0x05081e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 8], 5 - QUAD $0x06083e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 8], 6 - QUAD $0x07080e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 8], 7 + QUAD $0x05083e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 8], 5 + QUAD $0x06081e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 8], 6 + QUAD $0x07080644c40f4666 // pinsrw xmm8, word [rsi + r8 + 8], 7 LONG $0xddf80f66 // psubb xmm3, xmm5 QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI4_10] */ LONG $0xc76f0f66 // movdqa xmm0, xmm7 @@ -24530,20 +24373,20 @@ LBB4_192: LONG $0xf26e0f66 // movd xmm6, edx LONG $0x5cb70f46; WORD $0x1c3e // movzx r11d, word [rsi + r15 + 28] LONG $0x64c40f66; WORD $0x0a0e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 10], 1 - QUAD $0x020a0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 10], 2 + QUAD $0x020a0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 10], 2 QUAD $0x030a2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 10], 3 QUAD $0x040a2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 10], 4 - LONG $0x64c40f66; WORD $0x0a1e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 10], 5 - LONG $0x64c40f66; WORD $0x0a3e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 10], 6 - QUAD $0x070a0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 10], 7 + LONG $0x64c40f66; WORD $0x0a3e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 10], 5 + LONG $0x64c40f66; WORD $0x0a1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 10], 6 + QUAD $0x070a0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 10], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0x54c40f66; WORD $0x0c0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 12], 1 - QUAD $0x020c0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 12], 2 + QUAD $0x020c0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 12], 2 QUAD $0x030c2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 12], 3 QUAD $0x040c2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 12], 4 - LONG $0x54c40f66; WORD $0x0c1e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 12], 5 - LONG $0x54c40f66; WORD $0x0c3e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 12], 6 + LONG $0x54c40f66; WORD $0x0c3e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 12], 5 + LONG $0x54c40f66; WORD $0x0c1e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 12], 6 LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI4_12] */ LONG $0xc46f0f66 // movdqa xmm0, xmm4 @@ -24551,7 +24394,7 @@ LBB4_192: LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d LONG $0x54b70f42; WORD $0x1e3e // movzx edx, word [rsi + r15 + 30] LONG $0x30245489 // mov dword [rsp + 48], edx - QUAD $0x070c0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 12], 7 + QUAD $0x070c0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 12], 7 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 @@ -24560,27 +24403,27 @@ LBB4_192: LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 LONG $0x5c6e0f66; WORD $0x1024 // movd xmm3, dword [rsp + 16] LONG $0x54b70f42; WORD $0x203e // movzx edx, word [rsi + r15 + 32] - LONG $0x28245489 // mov dword [rsp + 40], edx + LONG $0x20245489 // mov dword [rsp + 32], edx LONG $0x4cc40f66; WORD $0x0e0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 14], 1 - QUAD $0x020e064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 14], 2 + QUAD $0x020e0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 14], 2 QUAD $0x030e264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 14], 3 QUAD $0x040e2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 14], 4 - LONG $0x4cc40f66; WORD $0x0e1e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 14], 5 - LONG $0x4cc40f66; WORD $0x0e3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 14], 6 + LONG $0x4cc40f66; WORD $0x0e3e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 14], 5 + LONG $0x4cc40f66; WORD $0x0e1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 14], 6 LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d LONG $0x54b70f42; WORD $0x223e // movzx edx, word [rsi + r15 + 34] LONG $0x10245489 // mov dword [rsp + 16], edx - QUAD $0x070e0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 14], 7 + QUAD $0x070e064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 14], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0x74c40f66; WORD $0x120e; BYTE $0x01 // pinsrw xmm6, word [rsi + rcx + 18], 1 - QUAD $0x02120674c40f4266 // pinsrw xmm6, word [rsi + r8 + 18], 2 + QUAD $0x02120e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 18], 2 QUAD $0x03122674c40f4266 // pinsrw xmm6, word [rsi + r12 + 18], 3 QUAD $0x04122e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 18], 4 - LONG $0x74c40f66; WORD $0x121e; BYTE $0x05 // pinsrw xmm6, word [rsi + rbx + 18], 5 - LONG $0x74c40f66; WORD $0x123e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 18], 6 + LONG $0x74c40f66; WORD $0x123e; BYTE $0x05 // pinsrw xmm6, word [rsi + rdi + 18], 5 + LONG $0x74c40f66; WORD $0x121e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 18], 6 LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x07120e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 18], 7 + QUAD $0x07120674c40f4266 // pinsrw xmm6, word [rsi + r8 + 18], 7 LONG $0x750f4166; BYTE $0xf3 // pcmpeqw xmm6, xmm11 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 @@ -24593,18 +24436,18 @@ LBB4_192: LONG $0xc86e0f66 // movd xmm1, eax LONG $0x74b70f46; WORD $0x243e // movzx r14d, word [rsi + r15 + 36] LONG $0x7cc40f66; WORD $0x100e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 16], 1 - QUAD $0x0210067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 16], 2 + QUAD $0x02100e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 16], 2 QUAD $0x0310267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 16], 3 QUAD $0x04102e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 16], 4 - LONG $0x7cc40f66; WORD $0x101e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 16], 5 - LONG $0x7cc40f66; WORD $0x103e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 16], 6 + LONG $0x7cc40f66; WORD $0x103e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 16], 5 + LONG $0x7cc40f66; WORD $0x101e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 16], 6 LONG $0x64c40f66; WORD $0x140e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 20], 1 - QUAD $0x02140664c40f4266 // pinsrw xmm4, word [rsi + r8 + 20], 2 + QUAD $0x02140e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 20], 2 QUAD $0x03142664c40f4266 // pinsrw xmm4, word [rsi + r12 + 20], 3 QUAD $0x04142e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 20], 4 - LONG $0x64c40f66; WORD $0x141e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 20], 5 - LONG $0x64c40f66; WORD $0x143e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 20], 6 - QUAD $0x07140e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 20], 7 + LONG $0x64c40f66; WORD $0x143e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 20], 5 + LONG $0x64c40f66; WORD $0x141e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 20], 6 + QUAD $0x07140664c40f4266 // pinsrw xmm4, word [rsi + r8 + 20], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 @@ -24613,26 +24456,26 @@ LBB4_192: LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d LONG $0x5cb70f46; WORD $0x263e // movzx r11d, word [rsi + r15 + 38] - QUAD $0x07100e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 16], 7 + QUAD $0x0710067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 16], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0xff630f66 // packsswb xmm7, xmm7 LONG $0x5cc40f66; WORD $0x160e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 22], 1 - QUAD $0x0216065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 22], 2 + QUAD $0x02160e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 22], 2 QUAD $0x0316265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 22], 3 QUAD $0x04162e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 22], 4 - LONG $0x5cc40f66; WORD $0x161e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 22], 5 - LONG $0x5cc40f66; WORD $0x163e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 22], 6 - QUAD $0x07160e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 22], 7 + LONG $0x5cc40f66; WORD $0x163e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 22], 5 + LONG $0x5cc40f66; WORD $0x161e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 22], 6 + QUAD $0x0716065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 22], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0x54c40f66; WORD $0x180e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 24], 1 - QUAD $0x02180654c40f4266 // pinsrw xmm2, word [rsi + r8 + 24], 2 + QUAD $0x02180e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 24], 2 QUAD $0x03182654c40f4266 // pinsrw xmm2, word [rsi + r12 + 24], 3 QUAD $0x04182e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 24], 4 - LONG $0x54c40f66; WORD $0x181e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 24], 5 - LONG $0x54c40f66; WORD $0x183e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 24], 6 - QUAD $0x07180e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 24], 7 + LONG $0x54c40f66; WORD $0x183e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 24], 5 + LONG $0x54c40f66; WORD $0x181e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 24], 6 + QUAD $0x07180654c40f4266 // pinsrw xmm2, word [rsi + r8 + 24], 7 LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI4_10] */ LONG $0x6f0f4566; BYTE $0xf2 // movdqa xmm14, xmm10 @@ -24647,31 +24490,31 @@ LBB4_192: LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 LONG $0xc26f0f66 // movdqa xmm0, xmm2 LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 - LONG $0x7c6e0f66; WORD $0x2824 // movd xmm7, dword [rsp + 40] + LONG $0x7c6e0f66; WORD $0x2024 // movd xmm7, dword [rsp + 32] LONG $0x54b70f46; WORD $0x2a3e // movzx r10d, word [rsi + r15 + 42] LONG $0x4cc40f66; WORD $0x1a0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 26], 1 - QUAD $0x021a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 26], 2 + QUAD $0x021a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 26], 2 QUAD $0x031a264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 26], 3 QUAD $0x041a2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 26], 4 - LONG $0x4cc40f66; WORD $0x1a1e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 26], 5 - LONG $0x4cc40f66; WORD $0x1a3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 26], 6 - QUAD $0x071a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 26], 7 + LONG $0x4cc40f66; WORD $0x1a3e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 26], 5 + LONG $0x4cc40f66; WORD $0x1a1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 26], 6 + QUAD $0x071a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 26], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0x64c40f66; WORD $0x1c0e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 28], 1 - QUAD $0x021c0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 28], 2 + QUAD $0x021c0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 28], 2 QUAD $0x031c2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 28], 3 QUAD $0x041c2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 28], 4 - LONG $0x64c40f66; WORD $0x1c1e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 28], 5 - LONG $0x64c40f66; WORD $0x1c3e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 28], 6 + LONG $0x64c40f66; WORD $0x1c3e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 28], 5 + LONG $0x64c40f66; WORD $0x1c1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 28], 6 LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI4_12] */ LONG $0xc16f0f66 // movdqa xmm0, xmm1 LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 LONG $0x546e0f66; WORD $0x1024 // movd xmm2, dword [rsp + 16] LONG $0x54b70f42; WORD $0x2c3e // movzx edx, word [rsi + r15 + 44] - LONG $0x28245489 // mov dword [rsp + 40], edx - QUAD $0x071c0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 28], 7 + LONG $0x20245489 // mov dword [rsp + 32], edx + QUAD $0x071c0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 28], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 @@ -24682,24 +24525,24 @@ LBB4_192: LONG $0x54b70f42; WORD $0x2e3e // movzx edx, word [rsi + r15 + 46] LONG $0x10245489 // mov dword [rsp + 16], edx LONG $0x5cc40f66; WORD $0x1e0e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 30], 1 - QUAD $0x021e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 30], 2 + QUAD $0x021e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 30], 2 QUAD $0x031e265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 30], 3 QUAD $0x041e2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 30], 4 - LONG $0x5cc40f66; WORD $0x1e1e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 30], 5 - LONG $0x5cc40f66; WORD $0x1e3e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 30], 6 + LONG $0x5cc40f66; WORD $0x1e3e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 30], 5 + LONG $0x5cc40f66; WORD $0x1e1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 30], 6 LONG $0xf5eb0f66 // por xmm6, xmm5 LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d LONG $0x5cb70f46; WORD $0x303e // movzx r11d, word [rsi + r15 + 48] - QUAD $0x071e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 30], 7 + QUAD $0x071e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 30], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0x54c40f66; WORD $0x220e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 34], 1 - QUAD $0x02220654c40f4266 // pinsrw xmm2, word [rsi + r8 + 34], 2 + QUAD $0x02220e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 34], 2 QUAD $0x03222654c40f4266 // pinsrw xmm2, word [rsi + r12 + 34], 3 QUAD $0x04222e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 34], 4 - LONG $0x54c40f66; WORD $0x221e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 34], 5 - LONG $0x54c40f66; WORD $0x223e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 34], 6 + LONG $0x54c40f66; WORD $0x223e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 34], 5 + LONG $0x54c40f66; WORD $0x221e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 34], 6 LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07220e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 34], 7 + QUAD $0x07220654c40f4266 // pinsrw xmm2, word [rsi + r8 + 34], 7 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 @@ -24713,18 +24556,18 @@ LBB4_192: LONG $0xd06e0f66 // movd xmm2, eax LONG $0x74b70f46; WORD $0x323e // movzx r14d, word [rsi + r15 + 50] LONG $0x7cc40f66; WORD $0x200e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 32], 1 - QUAD $0x0220067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 32], 2 + QUAD $0x02200e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 32], 2 QUAD $0x0320267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 32], 3 QUAD $0x04202e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 32], 4 - LONG $0x7cc40f66; WORD $0x201e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 32], 5 - LONG $0x7cc40f66; WORD $0x203e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 32], 6 + LONG $0x7cc40f66; WORD $0x203e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 32], 5 + LONG $0x7cc40f66; WORD $0x201e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 32], 6 LONG $0x64c40f66; WORD $0x240e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 36], 1 - QUAD $0x02240664c40f4266 // pinsrw xmm4, word [rsi + r8 + 36], 2 + QUAD $0x02240e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 36], 2 QUAD $0x03242664c40f4266 // pinsrw xmm4, word [rsi + r12 + 36], 3 QUAD $0x04242e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 36], 4 - LONG $0x64c40f66; WORD $0x241e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 36], 5 - LONG $0x64c40f66; WORD $0x243e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 36], 6 - QUAD $0x07240e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 36], 7 + LONG $0x64c40f66; WORD $0x243e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 36], 5 + LONG $0x64c40f66; WORD $0x241e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 36], 6 + QUAD $0x07240664c40f4266 // pinsrw xmm4, word [rsi + r8 + 36], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 @@ -24733,31 +24576,31 @@ LBB4_192: LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d LONG $0x54b70f42; WORD $0x343e // movzx edx, word [rsi + r15 + 52] - QUAD $0x07200e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 32], 7 + QUAD $0x0720067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 32], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0xff630f66 // packsswb xmm7, xmm7 LONG $0x4cc40f66; WORD $0x260e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 38], 1 - QUAD $0x0226064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 38], 2 + QUAD $0x02260e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 38], 2 QUAD $0x0326264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 38], 3 QUAD $0x04262e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 38], 4 - LONG $0x4cc40f66; WORD $0x261e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 38], 5 - LONG $0x4cc40f66; WORD $0x263e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 38], 6 - QUAD $0x07260e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 38], 7 + LONG $0x4cc40f66; WORD $0x263e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 38], 5 + LONG $0x4cc40f66; WORD $0x261e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 38], 6 + QUAD $0x0726064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 38], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0x54c40f66; WORD $0x280e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 40], 1 - QUAD $0x02280654c40f4266 // pinsrw xmm2, word [rsi + r8 + 40], 2 + QUAD $0x02280e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 40], 2 QUAD $0x03282654c40f4266 // pinsrw xmm2, word [rsi + r12 + 40], 3 QUAD $0x04282e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 40], 4 - LONG $0x54c40f66; WORD $0x281e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 40], 5 - LONG $0x54c40f66; WORD $0x283e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 40], 6 - QUAD $0x07280e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 40], 7 + LONG $0x54c40f66; WORD $0x283e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 40], 5 + LONG $0x54c40f66; WORD $0x281e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 40], 6 + QUAD $0x07280654c40f4266 // pinsrw xmm2, word [rsi + r8 + 40], 7 LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 LONG $0x6f0f4166; BYTE $0xea // movdqa xmm5, xmm10 LONG $0xc16f0f66 // movdqa xmm0, xmm1 LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 - LONG $0x4c6e0f66; WORD $0x2824 // movd xmm1, dword [rsp + 40] + LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] LONG $0x54b70f46; WORD $0x363e // movzx r10d, word [rsi + r15 + 54] LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xd2630f66 // packsswb xmm2, xmm2 @@ -24768,20 +24611,20 @@ LBB4_192: LONG $0x646e0f66; WORD $0x1024 // movd xmm4, dword [rsp + 16] LONG $0x44b70f42; WORD $0x383e // movzx eax, word [rsi + r15 + 56] LONG $0x5cc40f66; WORD $0x2a0e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 42], 1 - QUAD $0x022a065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 42], 2 + QUAD $0x022a0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 42], 2 QUAD $0x032a265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 42], 3 QUAD $0x042a2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 42], 4 - LONG $0x5cc40f66; WORD $0x2a1e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 42], 5 - LONG $0x5cc40f66; WORD $0x2a3e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 42], 6 - QUAD $0x072a0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 42], 7 + LONG $0x5cc40f66; WORD $0x2a3e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 42], 5 + LONG $0x5cc40f66; WORD $0x2a1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 42], 6 + QUAD $0x072a065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 42], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0x4cc40f66; WORD $0x2c0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 44], 1 - QUAD $0x022c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 44], 2 + QUAD $0x022c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 44], 2 QUAD $0x032c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 44], 3 QUAD $0x042c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 44], 4 - LONG $0x4cc40f66; WORD $0x2c1e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 44], 5 - LONG $0x4cc40f66; WORD $0x2c3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 44], 6 + LONG $0x4cc40f66; WORD $0x2c3e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 44], 5 + LONG $0x4cc40f66; WORD $0x2c1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 44], 6 LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 QUAD $0x0000c08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 192[rbp] /* [rip + .LCPI4_12] */ LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 @@ -24789,7 +24632,7 @@ LBB4_192: LONG $0x380f4166; WORD $0xd710 // pblendvb xmm2, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d LONG $0x5cb70f46; WORD $0x3a3e // movzx r11d, word [rsi + r15 + 58] - QUAD $0x072c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 44], 7 + QUAD $0x072c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 44], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xd6eb0f66 // por xmm2, xmm6 @@ -24802,12 +24645,12 @@ LBB4_192: LONG $0xf2eb0f66 // por xmm6, xmm2 LONG $0xd26e0f66 // movd xmm2, edx LONG $0x64c40f66; WORD $0x2e0e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 46], 1 - QUAD $0x022e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 46], 2 + QUAD $0x022e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 46], 2 QUAD $0x032e2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 46], 3 QUAD $0x042e2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 46], 4 - LONG $0x64c40f66; WORD $0x2e1e; BYTE $0x05 // pinsrw xmm4, word [rsi + rbx + 46], 5 - LONG $0x64c40f66; WORD $0x2e3e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 46], 6 - QUAD $0x072e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 46], 7 + LONG $0x64c40f66; WORD $0x2e3e; BYTE $0x05 // pinsrw xmm4, word [rsi + rdi + 46], 5 + LONG $0x64c40f66; WORD $0x2e1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 46], 6 + QUAD $0x072e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 46], 7 LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xf5eb0f66 // por xmm6, xmm5 @@ -24816,12 +24659,12 @@ LBB4_192: LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d LONG $0x4cc40f66; WORD $0x320e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 50], 1 - QUAD $0x0232064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 2 + QUAD $0x02320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 2 QUAD $0x0332264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 50], 3 QUAD $0x04322e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 50], 4 - LONG $0x4cc40f66; WORD $0x321e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 50], 5 - LONG $0x4cc40f66; WORD $0x323e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 50], 6 - QUAD $0x07320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 7 + LONG $0x4cc40f66; WORD $0x323e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 50], 5 + LONG $0x4cc40f66; WORD $0x321e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 50], 6 + QUAD $0x0732064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 7 LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 @@ -24830,40 +24673,40 @@ LBB4_192: LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 LONG $0xc86e0f66 // movd xmm1, eax LONG $0x7cc40f66; WORD $0x300e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 48], 1 - QUAD $0x0230067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 48], 2 + QUAD $0x02300e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 48], 2 QUAD $0x0330267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 48], 3 QUAD $0x04302e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 48], 4 - LONG $0x7cc40f66; WORD $0x301e; BYTE $0x05 // pinsrw xmm7, word [rsi + rbx + 48], 5 - LONG $0x7cc40f66; WORD $0x303e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 48], 6 - QUAD $0x07300e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 48], 7 + LONG $0x7cc40f66; WORD $0x303e; BYTE $0x05 // pinsrw xmm7, word [rsi + rdi + 48], 5 + LONG $0x7cc40f66; WORD $0x301e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 48], 6 + QUAD $0x0730067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 48], 7 LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI4_22] */ LONG $0x54c40f66; WORD $0x340e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 52], 1 - QUAD $0x02340654c40f4266 // pinsrw xmm2, word [rsi + r8 + 52], 2 + QUAD $0x02340e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 52], 2 QUAD $0x03342654c40f4266 // pinsrw xmm2, word [rsi + r12 + 52], 3 QUAD $0x04342e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 52], 4 - LONG $0x54c40f66; WORD $0x341e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 52], 5 - LONG $0x54c40f66; WORD $0x343e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 52], 6 + LONG $0x54c40f66; WORD $0x343e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 52], 5 + LONG $0x54c40f66; WORD $0x341e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 52], 6 LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x07340e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 52], 7 + QUAD $0x07340654c40f4266 // pinsrw xmm2, word [rsi + r8 + 52], 7 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0x5cc40f66; WORD $0x360e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 54], 1 - QUAD $0x0236065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 54], 2 + QUAD $0x02360e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 54], 2 QUAD $0x0336265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 54], 3 QUAD $0x04362e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 54], 4 - LONG $0x5cc40f66; WORD $0x361e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 54], 5 - LONG $0x5cc40f66; WORD $0x363e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 54], 6 + LONG $0x5cc40f66; WORD $0x363e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 54], 5 + LONG $0x5cc40f66; WORD $0x361e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 54], 6 LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x07360e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 54], 7 + QUAD $0x0736065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 54], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0x4cc40f66; WORD $0x380e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 56], 1 - QUAD $0x0238064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 56], 2 + QUAD $0x02380e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 56], 2 QUAD $0x0338264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 56], 3 QUAD $0x04382e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 56], 4 - LONG $0x4cc40f66; WORD $0x381e; BYTE $0x05 // pinsrw xmm1, word [rsi + rbx + 56], 5 - LONG $0x4cc40f66; WORD $0x383e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 56], 6 + LONG $0x4cc40f66; WORD $0x383e; BYTE $0x05 // pinsrw xmm1, word [rsi + rdi + 56], 5 + LONG $0x4cc40f66; WORD $0x381e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 56], 6 LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07380e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 56], 7 + QUAD $0x0738064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 56], 7 LONG $0xe7f80f66 // psubb xmm4, xmm7 QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI4_9] */ LONG $0xc26f0f66 // movdqa xmm0, xmm2 @@ -24874,24 +24717,24 @@ LBB4_192: LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 LONG $0x54c40f66; WORD $0x3a0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 58], 1 - QUAD $0x023a0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 58], 2 + QUAD $0x023a0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 58], 2 QUAD $0x033a2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 58], 3 QUAD $0x043a2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 58], 4 - LONG $0x54c40f66; WORD $0x3a1e; BYTE $0x05 // pinsrw xmm2, word [rsi + rbx + 58], 5 - LONG $0x54c40f66; WORD $0x3a3e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 58], 6 - QUAD $0x073a0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 58], 7 + LONG $0x54c40f66; WORD $0x3a3e; BYTE $0x05 // pinsrw xmm2, word [rsi + rdi + 58], 5 + LONG $0x54c40f66; WORD $0x3a1e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 58], 6 + QUAD $0x073a0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 58], 7 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 LONG $0xf5eb0f66 // por xmm6, xmm5 LONG $0x6e0f4166; BYTE $0xde // movd xmm3, r14d LONG $0x5cc40f66; WORD $0x3c0e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 60], 1 - QUAD $0x023c065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 60], 2 + QUAD $0x023c0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 60], 2 QUAD $0x033c265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 60], 3 QUAD $0x043c2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 60], 4 - LONG $0x5cc40f66; WORD $0x3c1e; BYTE $0x05 // pinsrw xmm3, word [rsi + rbx + 60], 5 - LONG $0x5cc40f66; WORD $0x3c3e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 60], 6 + LONG $0x5cc40f66; WORD $0x3c3e; BYTE $0x05 // pinsrw xmm3, word [rsi + rdi + 60], 5 + LONG $0x5cc40f66; WORD $0x3c1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 60], 6 LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x073c0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 60], 7 + QUAD $0x073c065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 60], 7 LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xf4eb0f66 // por xmm6, xmm4 @@ -24908,13 +24751,13 @@ LBB4_192: LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 LONG $0xc06e0f66 // movd xmm0, eax LONG $0x44c40f66; WORD $0x3e0e; BYTE $0x01 // pinsrw xmm0, word [rsi + rcx + 62], 1 - QUAD $0x023e0644c40f4266 // pinsrw xmm0, word [rsi + r8 + 62], 2 + QUAD $0x023e0e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 62], 2 QUAD $0x033e2644c40f4266 // pinsrw xmm0, word [rsi + r12 + 62], 3 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] QUAD $0x043e2e44c40f4266 // pinsrw xmm0, word [rsi + r13 + 62], 4 - LONG $0x44c40f66; WORD $0x3e1e; BYTE $0x05 // pinsrw xmm0, word [rsi + rbx + 62], 5 - LONG $0x44c40f66; WORD $0x3e3e; BYTE $0x06 // pinsrw xmm0, word [rsi + rdi + 62], 6 - QUAD $0x073e0e44c40f4266 // pinsrw xmm0, word [rsi + r9 + 62], 7 + LONG $0x44c40f66; WORD $0x3e3e; BYTE $0x05 // pinsrw xmm0, word [rsi + rdi + 62], 5 + LONG $0x44c40f66; WORD $0x3e1e; BYTE $0x06 // pinsrw xmm0, word [rsi + rbx + 62], 6 + QUAD $0x073e0644c40f4266 // pinsrw xmm0, word [rsi + r8 + 62], 7 LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 LONG $0xc0630f66 // packsswb xmm0, xmm0 LONG $0xeb0f4466; BYTE $0xd6 // por xmm10, xmm6 @@ -24936,16 +24779,922 @@ LBB4_192: LONG $0x447f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm0 LONG $0x08c18348 // add rcx, 8 WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB4_192 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - LONG $0x24543b4c; BYTE $0x20 // cmp r10, qword [rsp + 32] + LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] + JNE LBB4_219 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - LONG $0x246c8b44; BYTE $0x40 // mov r13d, dword [rsp + 64] + LONG $0x246c8b44; BYTE $0x38 // mov r13d, dword [rsp + 56] LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - JNE LBB4_108 - JMP LBB4_111 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + JNE LBB4_155 + JMP LBB4_158 + +LBB4_221: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + QUAD $0x0000011024848948 // mov qword [rsp + 272], rax + QUAD $0x000000a8248c8948 // mov qword [rsp + 168], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + LONG $0xc7b60f41 // movzx eax, r15b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 + WORD $0xc031 // xor eax, eax + LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 + +LBB4_222: + WORD $0x8949; BYTE $0xc1 // mov r9, rax + QUAD $0x0000009824848948 // mov qword [rsp + 152], rax + LONG $0x05e0c148 // shl rax, 5 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + WORD $0x8949; BYTE $0xc7 // mov r15, rax + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + WORD $0x8949; BYTE $0xc6 // mov r14, rax + WORD $0x8949; BYTE $0xc2 // mov r10, rax + WORD $0x8949; BYTE $0xc3 // mov r11, rax + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x0704b60f // movzx eax, byte [rdi + rax] + LONG $0xe06e0f66 // movd xmm4, eax + LONG $0x1744b60f; BYTE $0x01 // movzx eax, byte [rdi + rdx + 1] + LONG $0xd86e0f66 // movd xmm3, eax + LONG $0x1744b60f; BYTE $0x02 // movzx eax, byte [rdi + rdx + 2] + LONG $0xe86e0f66 // movd xmm5, eax + LONG $0x1744b60f; BYTE $0x03 // movzx eax, byte [rdi + rdx + 3] + LONG $0xf86e0f66 // movd xmm7, eax + LONG $0x1744b60f; BYTE $0x04 // movzx eax, byte [rdi + rdx + 4] + LONG $0x6e0f4466; BYTE $0xc8 // movd xmm9, eax + LONG $0x1744b60f; BYTE $0x05 // movzx eax, byte [rdi + rdx + 5] + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x1744b60f; BYTE $0x06 // movzx eax, byte [rdi + rdx + 6] + LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax + LONG $0x1744b60f; BYTE $0x07 // movzx eax, byte [rdi + rdx + 7] + LONG $0x6e0f4466; BYTE $0xf0 // movd xmm14, eax + LONG $0x1744b60f; BYTE $0x08 // movzx eax, byte [rdi + rdx + 8] + LONG $0xc06e0f66 // movd xmm0, eax + QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 + LONG $0x1744b60f; BYTE $0x09 // movzx eax, byte [rdi + rdx + 9] + LONG $0x6e0f4466; BYTE $0xd8 // movd xmm11, eax + LONG $0x1744b60f; BYTE $0x0a // movzx eax, byte [rdi + rdx + 10] + LONG $0x6e0f4466; BYTE $0xe0 // movd xmm12, eax + LONG $0x1744b60f; BYTE $0x0b // movzx eax, byte [rdi + rdx + 11] + LONG $0x6e0f4466; BYTE $0xe8 // movd xmm13, eax + LONG $0x1744b60f; BYTE $0x0c // movzx eax, byte [rdi + rdx + 12] + LONG $0xc06e0f66 // movd xmm0, eax + QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 + LONG $0x1744b60f; BYTE $0x0d // movzx eax, byte [rdi + rdx + 13] + LONG $0xf06e0f66 // movd xmm6, eax + LONG $0x1744b60f; BYTE $0x0e // movzx eax, byte [rdi + rdx + 14] + LONG $0x6e0f4466; BYTE $0xf8 // movd xmm15, eax + LONG $0x1744b60f; BYTE $0x0f // movzx eax, byte [rdi + rdx + 15] + LONG $0xc06e0f66 // movd xmm0, eax + QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 + LONG $0x24548948; BYTE $0x68 // mov qword [rsp + 104], rdx + WORD $0x8949; BYTE $0xd4 // mov r12, rdx + LONG $0x20cc8349 // or r12, 32 + LONG $0x2464894c; BYTE $0x18 // mov qword [rsp + 24], r12 + LONG $0x40c88349 // or r8, 64 + LONG $0x2444894c; BYTE $0x20 // mov qword [rsp + 32], r8 + LONG $0x60c98348 // or rcx, 96 + LONG $0x244c8948; BYTE $0x60 // mov qword [rsp + 96], rcx + LONG $0x80cf8149; WORD $0x0000; BYTE $0x00 // or r15, 128 + LONG $0xa0ce8148; WORD $0x0000; BYTE $0x00 // or rsi, 160 + LONG $0xc0ce8149; WORD $0x0000; BYTE $0x00 // or r14, 192 + LONG $0xe0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 224 + LONG $0x00cb8149; WORD $0x0001; BYTE $0x00 // or r11, 256 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + LONG $0x20c98149; WORD $0x0001; BYTE $0x00 // or r9, 288 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 + LONG $0x60cd8149; WORD $0x0001; BYTE $0x00 // or r13, 352 + QUAD $0x00018050244c8148; BYTE $0x00 // or qword [rsp + 80], 384 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + LONG $0x01a00d48; WORD $0x0000 // or rax, 416 + LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + LONG $0x01c00d48; WORD $0x0000 // or rax, 448 + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + LONG $0xe0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 480 + LONG $0x24548948; BYTE $0x40 // mov qword [rsp + 64], rdx + QUAD $0x012724203a0f4266 // pinsrb xmm4, byte [rdi + r12], 1 + QUAD $0x020724203a0f4266 // pinsrb xmm4, byte [rdi + r8], 2 + LONG $0x203a0f66; WORD $0x0f24; BYTE $0x03 // pinsrb xmm4, byte [rdi + rcx], 3 + LONG $0x247c894c; BYTE $0x70 // mov qword [rsp + 112], r15 + QUAD $0x043f24203a0f4266 // pinsrb xmm4, byte [rdi + r15], 4 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x203a0f66; WORD $0x3724; BYTE $0x05 // pinsrb xmm4, byte [rdi + rsi], 5 + QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 + QUAD $0x063724203a0f4266 // pinsrb xmm4, byte [rdi + r14], 6 + QUAD $0x071724203a0f4266 // pinsrb xmm4, byte [rdi + r10], 7 + QUAD $0x000000e0249c894c // mov qword [rsp + 224], r11 + QUAD $0x081f24203a0f4266 // pinsrb xmm4, byte [rdi + r11], 8 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + QUAD $0x090f24203a0f4266 // pinsrb xmm4, byte [rdi + r9], 9 + LONG $0x245c8948; BYTE $0x38 // mov qword [rsp + 56], rbx + LONG $0x203a0f66; WORD $0x1f24; BYTE $0x0a // pinsrb xmm4, byte [rdi + rbx], 10 + LONG $0x246c894c; BYTE $0x28 // mov qword [rsp + 40], r13 + QUAD $0x0b2f24203a0f4266 // pinsrb xmm4, byte [rdi + r13], 11 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x0c2724203a0f4266 // pinsrb xmm4, byte [rdi + r12], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + LONG $0x203a0f66; WORD $0x3724; BYTE $0x0d // pinsrb xmm4, byte [rdi + rsi], 13 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x0e0f24203a0f4266 // pinsrb xmm4, byte [rdi + r9], 14 + LONG $0x203a0f66; WORD $0x1724; BYTE $0x0f // pinsrb xmm4, byte [rdi + rdx], 15 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0101375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 1], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x01075c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdi + r8 + 1], 2 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0301375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 1], 3 + QUAD $0x013f5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r15 + 1], 4 + QUAD $0x0501075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 1], 5 + QUAD $0x01375c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r14 + 1], 6 + QUAD $0x01175c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r10 + 1], 7 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + QUAD $0x011f5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdi + r11 + 1], 8 + QUAD $0x09010f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 1], 9 + WORD $0x8949; BYTE $0xca // mov r10, rcx + QUAD $0x0a011f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 1], 10 + QUAD $0x012f5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r13 + 1], 11 + QUAD $0x01275c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r12 + 1], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0d01375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 1], 13 + QUAD $0x010f5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdi + r9 + 1], 14 + QUAD $0x0000c0248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 192] + LONG $0xe1740f66 // pcmpeqb xmm4, xmm1 + QUAD $0x0f01175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 1], 15 + LONG $0xd9740f66 // pcmpeqb xmm3, xmm1 + QUAD $0x00000100856f0f66 // movdqa xmm0, oword 256[rbp] /* [rip + .LCPI4_16] */ + LONG $0xd8df0f66 // pandn xmm3, xmm0 + LONG $0xdcfc0f66 // paddb xmm3, xmm4 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + LONG $0x0f54b60f; BYTE $0x10 // movzx edx, byte [rdi + rcx + 16] + LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x01020f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 2], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x02076c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rdi + r8 + 2], 2 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x022f6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r13 + 2], 3 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x02376c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdi + r14 + 2], 4 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + QUAD $0x0502076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 2], 5 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x021f6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r11 + 2], 6 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x023f6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r15 + 2], 7 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x08020f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 2], 8 + WORD $0x894d; BYTE $0xd1 // mov r9, r10 + LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 + QUAD $0x02176c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r10 + 2], 9 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x02176c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r10 + 2], 10 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x023f6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdi + r15 + 2], 11 + QUAD $0x02276c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdi + r12 + 2], 12 + QUAD $0x0d02376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 2], 13 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0e02176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 2], 14 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0f02376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 2], 15 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0103077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 3], 1 + QUAD $0x03077c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rdi + r8 + 3], 2 + QUAD $0x032f7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r13 + 3], 3 + QUAD $0x03377c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdi + r14 + 3], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0503077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 3], 5 + QUAD $0x031f7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r11 + 3], 6 + QUAD $0x07031f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 3], 7 + QUAD $0x08030f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 3], 8 + QUAD $0x030f7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdi + r9 + 3], 9 + QUAD $0x03177c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdi + r10 + 3], 10 + QUAD $0x033f7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdi + r15 + 3], 11 + QUAD $0x03277c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdi + r12 + 3], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d03077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 3], 13 + QUAD $0x0e03177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 3], 14 + QUAD $0x0f03377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 3], 15 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x04074c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdi + rax + 4], 1 + QUAD $0x04074c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rdi + r8 + 4], 2 + QUAD $0x042f4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdi + r13 + 4], 3 + QUAD $0x04374c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdi + r14 + 4], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x04074c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdi + rax + 4], 5 + QUAD $0x041f4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r11 + 4], 6 + QUAD $0x041f4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rdi + rbx + 4], 7 + QUAD $0x040f4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rdi + rcx + 4], 8 + QUAD $0x040f4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdi + r9 + 4], 9 + QUAD $0x04174c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdi + r10 + 4], 10 + QUAD $0x043f4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdi + r15 + 4], 11 + QUAD $0x04274c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdi + r12 + 4], 12 + LONG $0x244c8b4c; BYTE $0x10 // mov r9, qword [rsp + 16] + QUAD $0x040f4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rdi + r9 + 4], 13 + QUAD $0x04174c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdi + rdx + 4], 14 + QUAD $0x04374c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rdi + rsi + 4], 15 + LONG $0xe9740f66 // pcmpeqb xmm5, xmm1 + QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI4_17] */ + LONG $0xe8df0f66 // pandn xmm5, xmm0 + LONG $0xf9740f66 // pcmpeqb xmm7, xmm1 + QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI4_18] */ + LONG $0xf8df0f66 // pandn xmm7, xmm0 + LONG $0xfdeb0f66 // por xmm7, xmm5 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + LONG $0x3754b60f; BYTE $0x11 // movzx edx, byte [rdi + rsi + 17] + LONG $0xe26e0f66 // movd xmm4, edx + LONG $0x740f4466; BYTE $0xc9 // pcmpeqb xmm9, xmm1 + QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI4_19] */ + LONG $0xdf0f4466; BYTE $0xc8 // pandn xmm9, xmm0 + LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 + LONG $0x3754b60f; BYTE $0x12 // movzx edx, byte [rdi + rsi + 18] + LONG $0xfa6e0f66 // movd xmm7, edx + LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 + LONG $0xd8f80f66 // psubb xmm3, xmm0 + LONG $0xeb0f4466; BYTE $0xcb // por xmm9, xmm3 + LONG $0x3754b60f; BYTE $0x13 // movzx edx, byte [rdi + rsi + 19] + LONG $0xea6e0f66 // movd xmm5, edx + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x01051754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 5], 1 + QUAD $0x050754203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdi + r8 + 5], 2 + QUAD $0x052f54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdi + r13 + 5], 3 + QUAD $0x053754203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdi + r14 + 5], 4 + QUAD $0x05050754203a0f66 // pinsrb xmm2, byte [rdi + rax + 5], 5 + QUAD $0x051f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r11 + 5], 6 + QUAD $0x07051f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 5], 7 + QUAD $0x08050f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 5], 8 + LONG $0x245c8b4c; BYTE $0x48 // mov r11, qword [rsp + 72] + QUAD $0x051f54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r11 + 5], 9 + QUAD $0x051754203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r10 + 5], 10 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0b053754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 5], 11 + QUAD $0x052754203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdi + r12 + 5], 12 + WORD $0x894c; BYTE $0xce // mov rsi, r9 + QUAD $0x050f54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdi + r9 + 5], 13 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x050f54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdi + r9 + 5], 14 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x051754203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r10 + 5], 15 + QUAD $0x061744203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdi + rdx + 6], 1 + QUAD $0x060744203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rdi + r8 + 6], 2 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x062f44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdi + r13 + 6], 3 + QUAD $0x063744203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdi + r14 + 6], 4 + QUAD $0x060744203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdi + rax + 6], 5 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x062f44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r13 + 6], 6 + QUAD $0x061f44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rdi + rbx + 6], 7 + QUAD $0x060f44203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rdi + rcx + 6], 8 + QUAD $0x061f44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdi + r11 + 6], 9 + QUAD $0x063f44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdi + r15 + 6], 10 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x061f44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdi + r11 + 6], 11 + QUAD $0x062744203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdi + r12 + 6], 12 + QUAD $0x063744203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdi + rsi + 6], 13 + QUAD $0x060f44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdi + r9 + 6], 14 + QUAD $0x061744203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdi + r10 + 6], 15 + QUAD $0x071774203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdi + rdx + 7], 1 + QUAD $0x070774203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdi + r8 + 7], 2 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x073f74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdi + r15 + 7], 3 + QUAD $0x073774203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rdi + r14 + 7], 4 + QUAD $0x070774203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdi + rax + 7], 5 + WORD $0x894d; BYTE $0xe8 // mov r8, r13 + QUAD $0x072f74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdi + r13 + 7], 6 + QUAD $0x071f74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rdi + rbx + 7], 7 + QUAD $0x070f74203a0f4466; BYTE $0x08 // pinsrb xmm14, byte [rdi + rcx + 7], 8 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x073774203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rdi + r14 + 7], 9 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x071774203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rdi + r10 + 7], 10 + QUAD $0x071f74203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdi + r11 + 7], 11 + QUAD $0x072774203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdi + r12 + 7], 12 + QUAD $0x073774203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdi + rsi + 7], 13 + QUAD $0x070f74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdi + r9 + 7], 14 + LONG $0x6f0f4166; BYTE $0xce // movdqa xmm1, xmm14 + QUAD $0x00c024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 192] + LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 + QUAD $0x00000140856f0f66 // movdqa xmm0, oword 320[rbp] /* [rip + .LCPI4_20] */ + LONG $0xd0df0f66 // pandn xmm2, xmm0 + LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 + QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI4_21] */ + LONG $0xdf0f4466; BYTE $0xc0 // pandn xmm8, xmm0 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + LONG $0x54b60f42; WORD $0x141f // movzx edx, byte [rdi + r11 + 20] + LONG $0xda6e0f66 // movd xmm3, edx + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x070f4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdi + r9 + 7], 15 + LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 + LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI4_6] */ + LONG $0xc8df0f66 // pandn xmm1, xmm0 + LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 + LONG $0x54b60f42; WORD $0x151f // movzx edx, byte [rdi + r11 + 21] + LONG $0xd26e0f66 // movd xmm2, edx + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x01083744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 8], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02080f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 8], 2 + QUAD $0x083f44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdi + r15 + 8], 3 + WORD $0x894d; BYTE $0xfd // mov r13, r15 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x04080744203a0f66 // pinsrb xmm0, byte [rdi + rax + 8], 4 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x05081744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 8], 5 + QUAD $0x080744203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r8 + 8], 6 + QUAD $0x07081f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 8], 7 + QUAD $0x000000e024a48b4c // mov r12, qword [rsp + 224] + QUAD $0x082744203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdi + r12 + 8], 8 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + QUAD $0x083744203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdi + r14 + 8], 9 + QUAD $0x081744203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdi + r10 + 8], 10 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0b081744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 8], 11 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0c081744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 8], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d080744203a0f66 // pinsrb xmm0, byte [rdi + rax + 8], 13 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x083744203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdi + r14 + 8], 14 + QUAD $0x080f44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdi + r9 + 8], 15 + LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 + QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + LONG $0x54b60f42; WORD $0x161f // movzx edx, byte [rdi + r11 + 22] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 + QUAD $0x09375c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdi + rsi + 9], 1 + QUAD $0x090f5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdi + rcx + 9], 2 + QUAD $0x092f5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdi + r13 + 9], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x09075c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdi + rax + 9], 4 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x09075c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdi + r8 + 9], 5 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x091f5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdi + r11 + 9], 6 + QUAD $0x091f5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rdi + rbx + 9], 7 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + QUAD $0x09275c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdi + r12 + 9], 8 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x093f5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdi + r15 + 9], 9 + QUAD $0x09175c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdi + r10 + 9], 10 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x093f5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdi + r15 + 9], 11 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x09275c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdi + r12 + 9], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x09375c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdi + rsi + 9], 13 + QUAD $0x09375c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdi + r14 + 9], 14 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x090f5c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdi + rcx + 9], 15 + LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] + QUAD $0x0a3764203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdi + r14 + 10], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0a0764203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdi + rax + 10], 2 + QUAD $0x0a2f64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdi + r13 + 10], 3 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0a0764203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdi + rax + 10], 4 + QUAD $0x0a0764203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdi + r8 + 10], 5 + QUAD $0x0a1f64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdi + r11 + 10], 6 + QUAD $0x0a1f64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rdi + rbx + 10], 7 + QUAD $0x0a1764203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rdi + rdx + 10], 8 + QUAD $0x0a0f64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdi + r9 + 10], 9 + QUAD $0x0a1764203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdi + r10 + 10], 10 + QUAD $0x0a3f64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdi + r15 + 10], 11 + QUAD $0x0a2764203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdi + r12 + 10], 12 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x0a3764203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdi + rsi + 10], 13 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0a3764203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdi + r14 + 10], 14 + QUAD $0x0a0f64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdi + rcx + 10], 15 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0b076c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdi + rax + 11], 1 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0b376c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdi + rsi + 11], 2 + QUAD $0x0b2f6c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdi + r13 + 11], 3 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x0b376c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdi + rsi + 11], 4 + QUAD $0x0b076c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rdi + r8 + 11], 5 + QUAD $0x0b1f6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdi + r11 + 11], 6 + QUAD $0x0b1f6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rdi + rbx + 11], 7 + QUAD $0x0b176c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rdi + rdx + 11], 8 + QUAD $0x0b0f6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdi + r9 + 11], 9 + QUAD $0x0b176c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rdi + r10 + 11], 10 + QUAD $0x0b3f6c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdi + r15 + 11], 11 + QUAD $0x0b276c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdi + r12 + 11], 12 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x0b2f6c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdi + r13 + 11], 13 + QUAD $0x0b376c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdi + r14 + 11], 14 + QUAD $0x0b0f6c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdi + rcx + 11], 15 + LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 + QUAD $0x0001009ddf0f4466; BYTE $0x00 // pandn xmm11, oword 256[rbp] /* [rip + .LCPI4_16] */ + LONG $0xfc0f4466; BYTE $0xd8 // paddb xmm11, xmm0 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + LONG $0x0f54b60f; BYTE $0x17 // movzx edx, byte [rdi + rcx + 23] + LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx + LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 + QUAD $0x000110a5df0f4466; BYTE $0x00 // pandn xmm12, oword 272[rbp] /* [rip + .LCPI4_17] */ + LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 + QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI4_18] */ + LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 + LONG $0x0f54b60f; BYTE $0x18 // movzx edx, byte [rdi + rcx + 24] + LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx + QUAD $0x00f0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 240] + QUAD $0x0c074c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdi + rax + 12], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0c074c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rdi + r8 + 12], 2 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x0c0f4c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rdi + rcx + 12], 3 + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + QUAD $0x0c374c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdi + rsi + 12], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c074c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdi + rax + 12], 5 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + QUAD $0x0c1f4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r11 + 12], 6 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + QUAD $0x0c1f4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rdi + rbx + 12], 7 + QUAD $0x000000e0249c8b48 // mov rbx, qword [rsp + 224] + QUAD $0x0c1f4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rdi + rbx + 12], 8 + QUAD $0x0c0f4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdi + r9 + 12], 9 + QUAD $0x0c174c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdi + r10 + 12], 10 + QUAD $0x0c3f4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdi + r15 + 12], 11 + QUAD $0x0c274c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdi + r12 + 12], 12 + QUAD $0x0c2f4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rdi + r13 + 12], 13 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0c174c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdi + rdx + 12], 14 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x0c2f4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdi + r13 + 12], 15 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x010d0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 13], 1 + QUAD $0x0d0774203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdi + r8 + 13], 2 + QUAD $0x030d0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 13], 3 + QUAD $0x0d3774203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r14 + 13], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x050d0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 13], 5 + QUAD $0x060d3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 13], 6 + QUAD $0x0d1f74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r11 + 13], 7 + QUAD $0x080d1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 13], 8 + QUAD $0x0d0f74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r9 + 13], 9 + QUAD $0x0d1774203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdi + r10 + 13], 10 + QUAD $0x0d3f74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r15 + 13], 11 + QUAD $0x0d2774203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r12 + 13], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d0d0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 13], 13 + QUAD $0x0e0d1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 13], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0d0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 13], 15 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e077c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdi + rax + 14], 1 + QUAD $0x0e077c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rdi + r8 + 14], 2 + QUAD $0x0e0f7c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rdi + rcx + 14], 3 + QUAD $0x0e377c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdi + r14 + 14], 4 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0e077c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdi + rax + 14], 5 + QUAD $0x0e377c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rdi + rsi + 14], 6 + WORD $0x8949; BYTE $0xf5 // mov r13, rsi + QUAD $0x0e1f7c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r11 + 14], 7 + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 + QUAD $0x0e1f7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdi + rbx + 14], 8 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + QUAD $0x0e0f7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r9 + 14], 9 + QUAD $0x0e177c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdi + r10 + 14], 10 + QUAD $0x0e3f7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdi + r15 + 14], 11 + QUAD $0x0e277c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdi + r12 + 14], 12 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + LONG $0x2464894c; BYTE $0x50 // mov qword [rsp + 80], r12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0e377c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdi + rsi + 14], 13 + QUAD $0x0e177c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdi + rdx + 14], 14 + WORD $0x8949; BYTE $0xd7 // mov r15, rdx + LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 + QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI4_19] */ + LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + LONG $0x0754b60f; BYTE $0x19 // movzx edx, byte [rdi + rax + 25] + LONG $0x6e0f4466; BYTE $0xea // movd xmm13, edx + QUAD $0x0001609df80f4466; BYTE $0x00 // psubb xmm11, oword 352[rbp] /* [rip + .LCPI4_22] */ + LONG $0xeb0f4566; BYTE $0xcb // por xmm9, xmm11 + LONG $0x0754b60f; BYTE $0x1a // movzx edx, byte [rdi + rax + 26] + LONG $0xc26e0f66 // movd xmm0, edx + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x0e277c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r12 + 14], 15 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + QUAD $0x00000140b5df0f66 // pandn xmm6, oword 320[rbp] /* [rip + .LCPI4_20] */ + LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 + QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI4_21] */ + LONG $0xeb0f4466; BYTE $0xfe // por xmm15, xmm6 + LONG $0x0754b60f; BYTE $0x1b // movzx edx, byte [rdi + rax + 27] + LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx + QUAD $0x0000d024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 208] + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x0f0774203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdi + r8 + 15], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x020f1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 15], 2 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x030f1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 15], 3 + QUAD $0x0f3774203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r14 + 15], 4 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x0f1774203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdi + r10 + 15], 5 + QUAD $0x0f2f74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r13 + 15], 6 + QUAD $0x070f0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 15], 7 + QUAD $0x0f1f74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdi + r11 + 15], 8 + WORD $0x894d; BYTE $0xde // mov r14, r11 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x090f0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 15], 9 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0a0f1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 15], 10 + LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] + QUAD $0x0f1f74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r11 + 15], 11 + QUAD $0x0f0f74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r9 + 15], 12 + QUAD $0x0d0f3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 15], 13 + QUAD $0x0f3f74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdi + r15 + 15], 14 + QUAD $0x0f2774203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdi + r12 + 15], 15 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI4_6] */ + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x0754b60f; BYTE $0x1c // movzx edx, byte [rdi + rax + 28] + LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx + LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 + QUAD $0x0000d024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm6 + LONG $0x0754b60f; BYTE $0x1d // movzx edx, byte [rdi + rax + 29] + LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x100754203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdi + r8 + 16], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x100754203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdi + r8 + 16], 2 + QUAD $0x101f54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdi + rbx + 16], 3 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x100f54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdi + r9 + 16], 4 + QUAD $0x101754203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdi + r10 + 16], 5 + QUAD $0x102f54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r13 + 16], 6 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x100754203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rdi + rax + 16], 7 + QUAD $0x103754203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdi + r14 + 16], 8 + QUAD $0x100f54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdi + rcx + 16], 9 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x100f54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdi + rcx + 16], 10 + QUAD $0x101f54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r11 + 16], 11 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x103754203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdi + rsi + 16], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x100754203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdi + rax + 16], 13 + QUAD $0x103f54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdi + r15 + 16], 14 + QUAD $0x102754203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdi + r12 + 16], 15 + QUAD $0x01111764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 17], 1 + QUAD $0x110764203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdi + r8 + 17], 2 + QUAD $0x03111f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 17], 3 + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + QUAD $0x110f64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdi + r9 + 17], 4 + QUAD $0x111764203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdi + r10 + 17], 5 + QUAD $0x112f64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r13 + 17], 6 + QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] + QUAD $0x111764203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r10 + 17], 7 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + QUAD $0x113764203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdi + r14 + 17], 8 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x09111764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 17], 9 + QUAD $0x0a110f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 17], 10 + QUAD $0x111f64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r11 + 17], 11 + QUAD $0x0c113764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 17], 12 + QUAD $0x0d110764203a0f66 // pinsrb xmm4, byte [rdi + rax + 17], 13 + QUAD $0x113f64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdi + r15 + 17], 14 + WORD $0x894c; BYTE $0xe6 // mov rsi, r12 + QUAD $0x112764203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdi + r12 + 17], 15 + LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 + LONG $0x740f4166; BYTE $0xe6 // pcmpeqb xmm4, xmm14 + QUAD $0x00000100b56f0f66 // movdqa xmm6, oword 256[rbp] /* [rip + .LCPI4_16] */ + LONG $0xe6df0f66 // pandn xmm4, xmm6 + LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + LONG $0x0f54b60f; BYTE $0x1e // movzx edx, byte [rdi + rcx + 30] + LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0112077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 18], 1 + QUAD $0x0113076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 19], 1 + QUAD $0x0114075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 20], 1 + QUAD $0x01150754203a0f66 // pinsrb xmm2, byte [rdi + rax + 21], 1 + QUAD $0x0116074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 22], 1 + QUAD $0x170744203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdi + rax + 23], 1 + QUAD $0x180764203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdi + rax + 24], 1 + QUAD $0x19076c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdi + rax + 25], 1 + QUAD $0x011a0744203a0f66 // pinsrb xmm0, byte [rdi + rax + 26], 1 + QUAD $0x1b075c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdi + rax + 27], 1 + QUAD $0x1c077c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdi + rax + 28], 1 + QUAD $0x1d074c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdi + rax + 29], 1 + QUAD $0x1e0754203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdi + rax + 30], 1 + LONG $0x0f54b60f; BYTE $0x1f // movzx edx, byte [rdi + rcx + 31] + LONG $0xf26e0f66 // movd xmm6, edx + QUAD $0x011f0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 31], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0212177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 18], 2 + QUAD $0x0213176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 19], 2 + QUAD $0x0214175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 20], 2 + QUAD $0x02151754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 21], 2 + QUAD $0x0216174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 22], 2 + QUAD $0x171744203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdi + rdx + 23], 2 + QUAD $0x181764203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdi + rdx + 24], 2 + QUAD $0x19176c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdi + rdx + 25], 2 + QUAD $0x021a1744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 26], 2 + QUAD $0x1b175c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdi + rdx + 27], 2 + QUAD $0x1c177c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rdx + 28], 2 + QUAD $0x1d174c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdi + rdx + 29], 2 + QUAD $0x1e1754203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdi + rdx + 30], 2 + QUAD $0x021f1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 31], 2 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x12077c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r8 + 18], 3 + WORD $0x894d; BYTE $0xce // mov r14, r9 + QUAD $0x120f7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdi + r9 + 18], 4 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x12077c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdi + r8 + 18], 5 + QUAD $0x122f7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r13 + 18], 6 + WORD $0x894d; BYTE $0xd3 // mov r11, r10 + QUAD $0x12177c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r10 + 18], 7 + QUAD $0x08121f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 18], 8 + LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] + QUAD $0x120f7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdi + r9 + 18], 9 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0a120f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 18], 10 + LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] + QUAD $0x12177c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdi + r10 + 18], 11 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0c12077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 18], 12 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x12277c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rdi + r12 + 18], 13 + QUAD $0x123f7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdi + r15 + 18], 14 + QUAD $0x0f12377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 18], 15 + QUAD $0x0313176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 19], 3 + QUAD $0x13376c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdi + r14 + 19], 4 + QUAD $0x13076c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rdi + r8 + 19], 5 + QUAD $0x132f6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r13 + 19], 6 + QUAD $0x131f6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r11 + 19], 7 + QUAD $0x08131f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 19], 8 + QUAD $0x130f6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r9 + 19], 9 + QUAD $0x0a130f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 19], 10 + QUAD $0x13176c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdi + r10 + 19], 11 + QUAD $0x0c13076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 19], 12 + QUAD $0x13276c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdi + r12 + 19], 13 + QUAD $0x133f6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdi + r15 + 19], 14 + QUAD $0x0f13376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 19], 15 + QUAD $0x0314175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 20], 3 + QUAD $0x14375c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r14 + 20], 4 + QUAD $0x14075c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdi + r8 + 20], 5 + QUAD $0x142f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r13 + 20], 6 + QUAD $0x141f5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r11 + 20], 7 + QUAD $0x08141f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 20], 8 + QUAD $0x140f5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdi + r9 + 20], 9 + QUAD $0x0a140f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 20], 10 + QUAD $0x14175c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r10 + 20], 11 + QUAD $0x0c14075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 20], 12 + QUAD $0x14275c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdi + r12 + 20], 13 + QUAD $0x143f5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdi + r15 + 20], 14 + LONG $0x740f4166; BYTE $0xfe // pcmpeqb xmm7, xmm14 + QUAD $0x000110b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 272[rbp] /* [rip + .LCPI4_17] */ + LONG $0xdf0f4166; BYTE $0xfe // pandn xmm7, xmm14 + QUAD $0x0000c024ac740f66; BYTE $0x00 // pcmpeqb xmm5, oword [rsp + 192] + QUAD $0x000120b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 288[rbp] /* [rip + .LCPI4_18] */ + LONG $0xdf0f4166; BYTE $0xee // pandn xmm5, xmm14 + LONG $0xefeb0f66 // por xmm5, xmm7 + QUAD $0x0f14375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 20], 15 + QUAD $0x00c024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 192] + LONG $0x740f4166; BYTE $0xde // pcmpeqb xmm3, xmm14 + QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI4_19] */ + LONG $0xdfdf0f66 // pandn xmm3, xmm7 + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xed760f66 // pcmpeqd xmm5, xmm5 + LONG $0xe5f80f66 // psubb xmm4, xmm5 + LONG $0xdceb0f66 // por xmm3, xmm4 + QUAD $0x03151754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 21], 3 + QUAD $0x153754203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdi + r14 + 21], 4 + QUAD $0x150754203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdi + r8 + 21], 5 + QUAD $0x152f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r13 + 21], 6 + QUAD $0x151f54203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r11 + 21], 7 + QUAD $0x08151f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 21], 8 + QUAD $0x150f54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r9 + 21], 9 + QUAD $0x0a150f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 21], 10 + QUAD $0x151754203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdi + r10 + 21], 11 + QUAD $0x0c150754203a0f66 // pinsrb xmm2, byte [rdi + rax + 21], 12 + QUAD $0x152754203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdi + r12 + 21], 13 + QUAD $0x153f54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdi + r15 + 21], 14 + QUAD $0x0f153754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 21], 15 + QUAD $0x0316174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 22], 3 + QUAD $0x16374c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdi + r14 + 22], 4 + QUAD $0x16074c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdi + r8 + 22], 5 + QUAD $0x162f4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdi + r13 + 22], 6 + QUAD $0x161f4c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdi + r11 + 22], 7 + QUAD $0x08161f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 22], 8 + QUAD $0x160f4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdi + r9 + 22], 9 + QUAD $0x0a160f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 22], 10 + QUAD $0x16174c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdi + r10 + 22], 11 + QUAD $0x0c16074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 22], 12 + QUAD $0x16274c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdi + r12 + 22], 13 + QUAD $0x163f4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdi + r15 + 22], 14 + QUAD $0x0f16374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 22], 15 + QUAD $0x171744203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rdi + rdx + 23], 3 + QUAD $0x173744203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdi + r14 + 23], 4 + QUAD $0x170744203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rdi + r8 + 23], 5 + QUAD $0x172f44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r13 + 23], 6 + QUAD $0x171f44203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r11 + 23], 7 + QUAD $0x171f44203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rdi + rbx + 23], 8 + QUAD $0x170f44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdi + r9 + 23], 9 + QUAD $0x170f44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdi + rcx + 23], 10 + QUAD $0x171744203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdi + r10 + 23], 11 + QUAD $0x170744203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rdi + rax + 23], 12 + QUAD $0x172744203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rdi + r12 + 23], 13 + QUAD $0x173f44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdi + r15 + 23], 14 + LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 + QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI4_20] */ + LONG $0xd5df0f66 // pandn xmm2, xmm5 + LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 + QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI4_21] */ + LONG $0xcfdf0f66 // pandn xmm1, xmm7 + LONG $0xcaeb0f66 // por xmm1, xmm2 + QUAD $0x173744203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rdi + rsi + 23], 15 + LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 + LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI4_6] */ + LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + QUAD $0x181764203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdi + rdx + 24], 3 + QUAD $0x183764203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdi + r14 + 24], 4 + QUAD $0x180764203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdi + r8 + 24], 5 + QUAD $0x182f64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdi + r13 + 24], 6 + QUAD $0x181f64203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdi + r11 + 24], 7 + QUAD $0x181f64203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rdi + rbx + 24], 8 + QUAD $0x180f64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdi + r9 + 24], 9 + QUAD $0x180f64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdi + rcx + 24], 10 + QUAD $0x181764203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdi + r10 + 24], 11 + QUAD $0x180764203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdi + rax + 24], 12 + QUAD $0x182764203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdi + r12 + 24], 13 + QUAD $0x183f64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdi + r15 + 24], 14 + QUAD $0x183764203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdi + rsi + 24], 15 + LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 + LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 + QUAD $0x19176c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rdi + rdx + 25], 3 + QUAD $0x19376c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdi + r14 + 25], 4 + QUAD $0x19076c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rdi + r8 + 25], 5 + QUAD $0x192f6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdi + r13 + 25], 6 + QUAD $0x191f6c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdi + r11 + 25], 7 + QUAD $0x191f6c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rdi + rbx + 25], 8 + QUAD $0x190f6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdi + r9 + 25], 9 + QUAD $0x190f6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdi + rcx + 25], 10 + QUAD $0x19176c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdi + r10 + 25], 11 + QUAD $0x19076c203a0f4466; BYTE $0x0c // pinsrb xmm13, byte [rdi + rax + 25], 12 + QUAD $0x19276c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdi + r12 + 25], 13 + QUAD $0x193f6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdi + r15 + 25], 14 + QUAD $0x19376c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdi + rsi + 25], 15 + QUAD $0x031a1744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 26], 3 + QUAD $0x1a3744203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdi + r14 + 26], 4 + QUAD $0x1a0744203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdi + r8 + 26], 5 + QUAD $0x1a2f44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r13 + 26], 6 + QUAD $0x1a1f44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r11 + 26], 7 + QUAD $0x081a1f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 26], 8 + QUAD $0x1a0f44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdi + r9 + 26], 9 + QUAD $0x0a1a0f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 26], 10 + QUAD $0x1a1744203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdi + r10 + 26], 11 + QUAD $0x0c1a0744203a0f66 // pinsrb xmm0, byte [rdi + rax + 26], 12 + QUAD $0x1a2744203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdi + r12 + 26], 13 + QUAD $0x1a3f44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdi + r15 + 26], 14 + QUAD $0x0f1a3744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 26], 15 + QUAD $0x1b175c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rdi + rdx + 27], 3 + QUAD $0x1b375c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdi + r14 + 27], 4 + QUAD $0x1b075c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdi + r8 + 27], 5 + QUAD $0x1b2f5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdi + r13 + 27], 6 + QUAD $0x1b1f5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdi + r11 + 27], 7 + QUAD $0x1b1f5c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rdi + rbx + 27], 8 + QUAD $0x1b0f5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdi + r9 + 27], 9 + QUAD $0x1b0f5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdi + rcx + 27], 10 + QUAD $0x1b175c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdi + r10 + 27], 11 + QUAD $0x1b075c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rdi + rax + 27], 12 + QUAD $0x1b275c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdi + r12 + 27], 13 + QUAD $0x1b3f5c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdi + r15 + 27], 14 + LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 + QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI4_16] */ + LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 + QUAD $0x1b375c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdi + rsi + 27], 15 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 + QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI4_17] */ + LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 + QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI4_18] */ + LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 + QUAD $0x1c177c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rdi + rdx + 28], 3 + QUAD $0x1d174c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rdi + rdx + 29], 3 + QUAD $0x1e1754203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdi + rdx + 30], 3 + QUAD $0x031f1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 31], 3 + QUAD $0x1c377c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdi + r14 + 28], 4 + QUAD $0x1d374c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdi + r14 + 29], 4 + QUAD $0x1e3754203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdi + r14 + 30], 4 + QUAD $0x1f3774203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r14 + 31], 4 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x1c077c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rdi + r8 + 28], 5 + QUAD $0x1d074c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdi + r8 + 29], 5 + QUAD $0x1e0754203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdi + r8 + 30], 5 + QUAD $0x1f0774203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdi + r8 + 31], 5 + QUAD $0x1c2f7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r13 + 28], 6 + QUAD $0x1d2f4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r13 + 29], 6 + QUAD $0x1e2f54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r13 + 30], 6 + QUAD $0x1f2f74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r13 + 31], 6 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + QUAD $0x1c1f7c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r11 + 28], 7 + QUAD $0x1d1f4c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r11 + 29], 7 + QUAD $0x1e1f54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r11 + 30], 7 + QUAD $0x1f1f74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r11 + 31], 7 + LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x1c1f7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdi + rbx + 28], 8 + QUAD $0x1d1f4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rdi + rbx + 29], 8 + QUAD $0x1e1f54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rdi + rbx + 30], 8 + QUAD $0x081f1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 31], 8 + WORD $0x894c; BYTE $0xca // mov rdx, r9 + QUAD $0x1c0f7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r9 + 28], 9 + QUAD $0x1d0f4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdi + r9 + 29], 9 + QUAD $0x1e0f54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdi + r9 + 30], 9 + QUAD $0x1f0f74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r9 + 31], 9 + QUAD $0x1c0f7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdi + rcx + 28], 10 + QUAD $0x1d0f4c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rdi + rcx + 29], 10 + QUAD $0x1e0f54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdi + rcx + 30], 10 + QUAD $0x0a1f0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 31], 10 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + QUAD $0x1c177c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdi + r10 + 28], 11 + QUAD $0x1d174c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdi + r10 + 29], 11 + QUAD $0x1e1754203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r10 + 30], 11 + QUAD $0x1f1774203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r10 + 31], 11 + QUAD $0x1c077c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rdi + rax + 28], 12 + QUAD $0x1d074c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rdi + rax + 29], 12 + QUAD $0x1e0754203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdi + rax + 30], 12 + QUAD $0x0c1f0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 31], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x1c077c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdi + rax + 28], 13 + QUAD $0x1d074c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdi + rax + 29], 13 + QUAD $0x1e0754203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdi + rax + 30], 13 + QUAD $0x0d1f0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 31], 13 + QUAD $0x1c3f7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdi + r15 + 28], 14 + QUAD $0x1d3f4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdi + r15 + 29], 14 + QUAD $0x1e3f54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdi + r15 + 30], 14 + QUAD $0x1f3f74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdi + r15 + 31], 14 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x1c277c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r12 + 28], 15 + QUAD $0x1d274c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdi + r12 + 29], 15 + QUAD $0x1e2754203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdi + r12 + 30], 15 + LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 + QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI4_19] */ + LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 + QUAD $0x1f2774203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdi + r12 + 31], 15 + QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI4_22] */ + LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 + LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 + LONG $0xdf0f4466; BYTE $0xcd // pandn xmm9, xmm5 + LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 + LONG $0xdf0f4466; BYTE $0xd7 // pandn xmm10, xmm7 + LONG $0xeb0f4566; BYTE $0xd1 // por xmm10, xmm9 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + LONG $0xf4df0f66 // pandn xmm6, xmm4 + LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 + LONG $0xc6600f66 // punpcklbw xmm0, xmm6 + QUAD $0x0000b0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 176] + LONG $0xcb6f0f66 // movdqa xmm1, xmm3 + QUAD $0x0000d024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 208] + LONG $0xcc600f66 // punpcklbw xmm1, xmm4 + LONG $0xd16f0f66 // movdqa xmm2, xmm1 + LONG $0xd0610f66 // punpcklwd xmm2, xmm0 + LONG $0xc8690f66 // punpckhwd xmm1, xmm0 + LONG $0x680f4466; BYTE $0xc6 // punpckhbw xmm8, xmm6 + LONG $0xdc680f66 // punpckhbw xmm3, xmm4 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xd8 // punpckhwd xmm3, xmm8 + QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] + LONG $0x5c7f0ff3; WORD $0x308e // movdqu oword [rsi + 4*rcx + 48], xmm3 + LONG $0x447f0ff3; WORD $0x208e // movdqu oword [rsi + 4*rcx + 32], xmm0 + LONG $0x4c7f0ff3; WORD $0x108e // movdqu oword [rsi + 4*rcx + 16], xmm1 + LONG $0x147f0ff3; BYTE $0x8e // movdqu oword [rsi + 4*rcx], xmm2 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + JNE LBB4_222 + QUAD $0x00000108248c8b48 // mov rcx, qword [rsp + 264] + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + LONG $0x247c8a44; BYTE $0x08 // mov r15b, byte [rsp + 8] + QUAD $0x0000011024b48b48 // mov rsi, qword [rsp + 272] + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + JNE LBB4_168 + JMP LBB4_172 DATA LCDATA4<>+0x000(SB)/8, $0x0000000001010101 DATA LCDATA4<>+0x008(SB)/8, $0x0000000000000000 @@ -24995,3005 +25744,3154 @@ DATA LCDATA4<>+0x160(SB)/8, $0xffffffffffffffff DATA LCDATA4<>+0x168(SB)/8, $0xffffffffffffffff GLOBL LCDATA4<>(SB), 8, $368 -TEXT ·_comparison_not_equal_scalar_arr_sse4(SB), $312-48 +TEXT ·_comparison_not_equal_scalar_arr_sse4(SB), $296-48 + + MOVQ typ+0(FP), DI + MOVQ left+8(FP), SI + MOVQ right+16(FP), DX + MOVQ out+24(FP), CX + MOVQ length+32(FP), R8 + MOVQ offset+40(FP), R9 + MOVQ SP, BP + ADDQ $16, SP + ANDQ $-16, SP + MOVQ BP, 272(SP) + LEAQ LCDATA4<>(SB), BP + + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB5_19 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB5_36 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB5_59 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB5_73 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB5_200 + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_11 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_9 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_8: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_8 + +LBB5_9: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 + +LBB5_11: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB5_15 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + +LBB5_13: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] + LONG $0xd7950f40 // setne dil + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + QUAD $0x000000b02494950f // setne byte [rsp + 176] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] + LONG $0xd3950f41 // setne r11b + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] + LONG $0xd2950f41 // setne r10b + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] + LONG $0xd1950f41 // setne r9b + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] + LONG $0xd6950f40 // setne sil + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] + WORD $0x950f; BYTE $0xd0 // setne al + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] + WORD $0x950f; BYTE $0xd3 // setne bl + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] + WORD $0x950f; BYTE $0xd1 // setne cl + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] + LONG $0xd4950f41 // setne r12b + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] + LONG $0xd5950f41 // setne r13b + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] + LONG $0xd7950f41 // setne r15b + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd6950f41 // setne r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a024b40244 // add r14b, byte [rsp + 160] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xfd // or r13b, r15b + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x24048841 // mov byte [r12], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xc000 // add al, al + LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x78244402 // add al, byte [rsp + 120] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al + LONG $0x80ea8348 // sub rdx, -128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB5_13 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + +LBB5_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB5_131 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 + WORD $0xff31 // xor edi, edi - MOVQ typ+0(FP), DI - MOVQ left+8(FP), SI - MOVQ right+16(FP), DX - MOVQ out+24(FP), CX - MOVQ length+32(FP), R8 - MOVQ offset+40(FP), R9 - MOVQ SP, BP - ADDQ $16, SP - ANDQ $-16, SP - MOVQ BP, 288(SP) - LEAQ LCDATA4<>(SB), BP +LBB5_18: + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x341c8841 // mov byte [r12 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0x08528d48 // lea rdx, [rdx + 8] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_18 + JMP LBB5_177 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 - LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx - WORD $0x8949; BYTE $0xd6 // mov r14, rdx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB5_27 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB5_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 +LBB5_19: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB5_43 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB5_87 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 JE LBB5_100 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB5_123 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB5_198 - WORD $0x8b44; BYTE $0x1e // mov r11d, dword [rsi] - LONG $0x1f578d4d // lea r10, [r15 + 31] + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB5_200 + WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_29 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_27 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_26: + LONG $0x012e0f66 // ucomisd xmm0, qword [rcx] + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x9a0f; BYTE $0xd1 // setp cl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xcb08 // or bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_26 + +LBB5_27: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 + +LBB5_29: + LONG $0x1f478d49 // lea rax, [r15 + 31] WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_17 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB5_33 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax -LBB5_15: - WORD $0x3b45; BYTE $0x1e // cmp r11d, dword [r14] - LONG $0x04768d4d // lea r14, [r14 + 4] +LBB5_31: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd5950f41 // setne r13b + WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x422e0f66; BYTE $0x10 // ucomisd xmm0, qword [rdx + 16] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x422e0f66; BYTE $0x18 // ucomisd xmm0, qword [rdx + 24] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x18244c88 // mov byte [rsp + 24], cl + LONG $0x422e0f66; BYTE $0x20 // ucomisd xmm0, qword [rdx + 32] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x422e0f66; BYTE $0x28 // ucomisd xmm0, qword [rdx + 40] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd4950f41 // setne r12b + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x422e0f66; BYTE $0x30 // ucomisd xmm0, qword [rdx + 48] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x422e0f66; BYTE $0x38 // ucomisd xmm0, qword [rdx + 56] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x422e0f66; BYTE $0x48 // ucomisd xmm0, qword [rdx + 72] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x422e0f66; BYTE $0x50 // ucomisd xmm0, qword [rdx + 80] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x422e0f66; BYTE $0x58 // ucomisd xmm0, qword [rdx + 88] + WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f44; BYTE $0x32 // movzx r8d, byte [rdx + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x323c8840 // mov byte [rdx + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_15 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 + WORD $0xc308 // or bl, al + LONG $0x422e0f66; BYTE $0x60 // ucomisd xmm0, qword [rdx + 96] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x422e0f66; BYTE $0x68 // ucomisd xmm0, qword [rdx + 104] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x422e0f66; BYTE $0x70 // ucomisd xmm0, qword [rdx + 112] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x422e0f66; BYTE $0x78 // ucomisd xmm0, qword [rdx + 120] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x60244c88 // mov byte [rsp + 96], cl + QUAD $0x00000080822e0f66 // ucomisd xmm0, qword [rdx + 128] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x50244c88 // mov byte [rsp + 80], cl + QUAD $0x00000088822e0f66 // ucomisd xmm0, qword [rdx + 136] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x78244c88 // mov byte [rsp + 120], cl + QUAD $0x00000090822e0f66 // ucomisd xmm0, qword [rdx + 144] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + QUAD $0x00000098822e0f66 // ucomisd xmm0, qword [rdx + 152] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl + QUAD $0x000000a0822e0f66 // ucomisd xmm0, qword [rdx + 160] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + QUAD $0x000000a8822e0f66 // ucomisd xmm0, qword [rdx + 168] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + QUAD $0x000000b0822e0f66 // ucomisd xmm0, qword [rdx + 176] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al + QUAD $0x000000b8822e0f66 // ucomisd xmm0, qword [rdx + 184] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd0950f41 // setne r8b + WORD $0x0841; BYTE $0xc0 // or r8b, al + QUAD $0x000000c0822e0f66 // ucomisd xmm0, qword [rdx + 192] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + QUAD $0x000000c8822e0f66 // ucomisd xmm0, qword [rdx + 200] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd3950f41 // setne r11b + WORD $0x0841; BYTE $0xc3 // or r11b, al + QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al + QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd1950f41 // setne r9b + WORD $0x0841; BYTE $0xc1 // or r9b, al + QUAD $0x000000e0822e0f66 // ucomisd xmm0, qword [rdx + 224] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xd0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 208], cl + QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl + QUAD $0x000000f0822e0f66 // ucomisd xmm0, qword [rdx + 240] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f40 // setne dil + WORD $0x0840; BYTE $0xc7 // or dil, al + QUAD $0x000000f8822e0f66 // ucomisd xmm0, qword [rdx + 248] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd6950f40 // setne sil + WORD $0x0840; BYTE $0xc6 // or sil, al + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] + WORD $0x8944; BYTE $0xe8 // mov eax, r13d + LONG $0x05e4c041 // shl r12b, 5 + LONG $0x6cb60f44; WORD $0x4824 // movzx r13d, byte [rsp + 72] + LONG $0x06e5c041 // shl r13b, 6 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xc900 // add cl, cl + LONG $0x38244c02 // add cl, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0xcb08 // or bl, cl + LONG $0x6cb60f44; WORD $0x1024 // movzx r13d, byte [rsp + 16] + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0841; BYTE $0xc5 // or r13b, al + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x28244488 // mov byte [rsp + 40], al + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x74b60f44; WORD $0x6024 // movzx r14d, byte [rsp + 96] + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xc900 // add cl, cl + LONG $0x50244c02 // add cl, byte [rsp + 80] + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0xcb08 // or bl, cl + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd908 // or cl, bl + WORD $0xcb89 // mov ebx, ecx + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd908 // or cl, bl + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x0844; BYTE $0xe8 // or al, r13b + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + LONG $0x06e7c041 // shl r15b, 6 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x24740a44; BYTE $0x28 // or r14b, byte [rsp + 40] + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xf8 // or r8b, r15b + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x00000090249c0244 // add r11b, byte [rsp + 144] + LONG $0x02e2c041 // shl r10b, 2 + WORD $0x0845; BYTE $0xda // or r10b, r11b + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xd1 // or r9b, r10b + QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xc9 // or cl, r9b + WORD $0xcb89 // mov ebx, ecx + LONG $0x24048841 // mov byte [r12], al + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x24748845; BYTE $0x01 // mov byte [r12 + 1], r14b + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xfe // or sil, dil + WORD $0x0840; BYTE $0xde // or sil, bl + LONG $0x24448845; BYTE $0x02 // mov byte [r12 + 2], r8b + LONG $0x24748841; BYTE $0x03 // mov byte [r12 + 3], sil + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 + JNE LBB5_31 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x000000f824848b48 // mov rax, qword [rsp + 248] + +LBB5_33: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB5_200 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB5_186 + WORD $0xff31 // xor edi, edi + JMP LBB5_188 + +LBB5_36: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB5_114 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB5_200 + WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_147 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB5_41: + LONG $0x016a8d4c // lea r13, [rdx + 1] + WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894c; BYTE $0xe7 // mov rdi, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1c048841 // mov byte [r12 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x894c; BYTE $0xea // mov rdx, r13 + LONG $0xffc38349 // add r11, -1 + JNE LBB5_41 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB5_148 + JMP LBB5_200 + +LBB5_43: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB5_119 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB5_200 + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_51 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_49 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_48: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_48 + +LBB5_49: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 -LBB5_17: - LONG $0x05fac149 // sar r10, 5 +LBB5_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_21 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - QUAD $0x000000a82494894c // mov qword [rsp + 168], r10 + JL LBB5_55 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax -LBB5_19: - LONG $0x7c5e3b45 // cmp r11d, dword [r14 + 124] +LBB5_53: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0x785e3b45 // cmp r11d, dword [r14 + 120] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x745e3b45 // cmp r11d, dword [r14 + 116] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x705e3b45 // cmp r11d, dword [r14 + 112] - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x6c5e3b45 // cmp r11d, dword [r14 + 108] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x685e3b45 // cmp r11d, dword [r14 + 104] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x645e3b45 // cmp r11d, dword [r14 + 100] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x5c5e3b45 // cmp r11d, dword [r14 + 92] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x585e3b45 // cmp r11d, dword [r14 + 88] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x545e3b45 // cmp r11d, dword [r14 + 84] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x505e3b45 // cmp r11d, dword [r14 + 80] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x4c5e3b45 // cmp r11d, dword [r14 + 76] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x485e3b45 // cmp r11d, dword [r14 + 72] - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x445e3b45 // cmp r11d, dword [r14 + 68] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x3c5e3b45 // cmp r11d, dword [r14 + 60] - LONG $0xd0950f41 // setne r8b - LONG $0x385e3b45 // cmp r11d, dword [r14 + 56] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x345e3b45 // cmp r11d, dword [r14 + 52] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x305e3b45 // cmp r11d, dword [r14 + 48] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] LONG $0xd7950f40 // setne dil - LONG $0x2c5e3b45 // cmp r11d, dword [r14 + 44] + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + QUAD $0x000000b02494950f // setne byte [rsp + 176] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] + LONG $0xd3950f41 // setne r11b + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd2950f41 // setne r10b - LONG $0x285e3b45 // cmp r11d, dword [r14 + 40] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd1950f41 // setne r9b - LONG $0x245e3b45 // cmp r11d, dword [r14 + 36] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] LONG $0xd6950f40 // setne sil - LONG $0x1c5e3b45 // cmp r11d, dword [r14 + 28] + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x185e3b45 // cmp r11d, dword [r14 + 24] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x145e3b45 // cmp r11d, dword [r14 + 20] - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x105e3b45 // cmp r11d, dword [r14 + 16] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x0c5e3b45 // cmp r11d, dword [r14 + 12] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] + LONG $0xd4950f41 // setne r12b + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd5950f41 // setne r13b - LONG $0x085e3b45 // cmp r11d, dword [r14 + 8] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] LONG $0xd7950f41 // setne r15b - WORD $0x3b45; BYTE $0x1e // cmp r11d, dword [r14] - QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x045e3b45 // cmp r11d, dword [r14 + 4] - WORD $0x894d; BYTE $0xf4 // mov r12, r14 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x08423b4c // cmp r8, qword [rdx + 8] LONG $0xd6950f41 // setne r14b - LONG $0x245c3b45; BYTE $0x20 // cmp r11d, dword [r12 + 32] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x245c3b45; BYTE $0x40 // cmp r11d, dword [r12 + 64] + LONG $0x40423b4c // cmp r8, qword [rdx + 64] QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x245c3b45; BYTE $0x60 // cmp r11d, dword [r12 + 96] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] WORD $0x0045; BYTE $0xf6 // add r14b, r14b - QUAD $0x000000c024b40244 // add r14b, byte [rsp + 192] + QUAD $0x000000a024b40244 // add r14b, byte [rsp + 160] LONG $0x02e7c041 // shl r15b, 2 WORD $0x0845; BYTE $0xf7 // or r15b, r14b - WORD $0x894d; BYTE $0xe6 // mov r14, r12 LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xfd // or r13b, r15b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xca08 // or dl, cl + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0xd008 // or al, dl - WORD $0x8841; BYTE $0x07 // mov byte [r15], al + WORD $0xc808 // or al, cl + LONG $0x24048841 // mov byte [r12], al WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000b024b40240 // add sil, byte [rsp + 176] + QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] LONG $0x02e1c041 // shl r9b, 2 WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e7c040 // shl dil, 4 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0x0844; BYTE $0xd8 // or al, r11b + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl + WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] + LONG $0x78244402 // add al, byte [rsp + 120] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl + WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x80ee8349 // sub r14, -128 - LONG $0x04c78349 // add r15, 4 - LONG $0x247c894c; BYTE $0x08 // mov qword [rsp + 8], r15 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_19 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB5_53 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB5_21: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JE LBB5_23 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xff31 // xor edi, edi - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] +LBB5_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JE LBB5_99 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 + WORD $0xff31 // xor edi, edi -LBB5_144: - WORD $0x3b45; BYTE $0x1e // cmp r11d, dword [r14] +LBB5_58: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0x3044; BYTE $0xd0 // xor al, r10b - WORD $0xc220 // and dl, al - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - LONG $0x37148841 // mov byte [r15 + rsi], dl - LONG $0x02c78348 // add rdi, 2 - LONG $0x045e3b45 // cmp r11d, dword [r14 + 4] - LONG $0x08768d4d // lea r14, [r14 + 8] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0xd030 // xor al, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0xd330 // xor bl, dl - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB5_144 - JMP LBB5_24 + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x341c8841 // mov byte [r12 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_58 + JMP LBB5_192 -LBB5_27: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB5_28 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB5_159 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB5_171 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB5_198 - LONG $0x1f578d4d // lea r10, [r15 + 31] +LBB5_59: + LONG $0x36b70f44 // movzx r14d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_65 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_63 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_62: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x313b4466 // cmp r14w, word [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_62 + +LBB5_63: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 + +LBB5_65: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_50 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB5_133 + LONG $0x08f98348 // cmp rcx, 8 + LONG $0x24748944; BYTE $0x0c // mov dword [rsp + 12], r14d + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000a8248c8948 // mov qword [rsp + 168], rcx + JB LBB5_69 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB5_205 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB5_205 -LBB5_48: - LONG $0x2e0f4166; BYTE $0x06 // ucomisd xmm0, qword [r14] - LONG $0x08768d4d // lea r14, [r14 + 8] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xca08 // or dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x1cb60f41; BYTE $0x30 // movzx ebx, byte [r8 + rsi] - WORD $0xda30 // xor dl, bl - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3040; BYTE $0xdf // xor dil, bl - LONG $0x303c8841 // mov byte [r8 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_48 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 +LBB5_69: + WORD $0xc031 // xor eax, eax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB5_50: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_54 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 +LBB5_70: + LONG $0x244c2b48; BYTE $0x20 // sub rcx, qword [rsp + 32] + QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx -LBB5_52: - WORD $0x894c; BYTE $0xf2 // mov rdx, r14 - LONG $0x2e0f4166; BYTE $0x06 // ucomisd xmm0, qword [r14] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x18244c88 // mov byte [rsp + 24], cl - LONG $0x2e0f4166; WORD $0x0846 // ucomisd xmm0, qword [r14 + 8] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x2e0f4166; WORD $0x1046 // ucomisd xmm0, qword [r14 + 16] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl - LONG $0x2e0f4166; WORD $0x1846 // ucomisd xmm0, qword [r14 + 24] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl - LONG $0x2e0f4166; WORD $0x2046 // ucomisd xmm0, qword [r14 + 32] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x10244c88 // mov byte [rsp + 16], cl - LONG $0x2e0f4166; WORD $0x2846 // ucomisd xmm0, qword [r14 + 40] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd1950f41 // setne r9b - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2e0f4166; WORD $0x3046 // ucomisd xmm0, qword [r14 + 48] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl - LONG $0x2e0f4166; WORD $0x3846 // ucomisd xmm0, qword [r14 + 56] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl - LONG $0x2e0f4166; WORD $0x4046 // ucomisd xmm0, qword [r14 + 64] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl - LONG $0x2e0f4166; WORD $0x4846 // ucomisd xmm0, qword [r14 + 72] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl - LONG $0x2e0f4166; WORD $0x5046 // ucomisd xmm0, qword [r14 + 80] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - LONG $0x50245c88 // mov byte [rsp + 80], bl - LONG $0x2e0f4166; WORD $0x5846 // ucomisd xmm0, qword [r14 + 88] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - LONG $0x48245c88 // mov byte [rsp + 72], bl - LONG $0x2e0f4166; WORD $0x6046 // ucomisd xmm0, qword [r14 + 96] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - LONG $0x68245c88 // mov byte [rsp + 104], bl - LONG $0x2e0f4166; WORD $0x6846 // ucomisd xmm0, qword [r14 + 104] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - LONG $0x60245c88 // mov byte [rsp + 96], bl - LONG $0x2e0f4166; WORD $0x7046 // ucomisd xmm0, qword [r14 + 112] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd5950f41 // setne r13b - WORD $0x0841; BYTE $0xc5 // or r13b, al - LONG $0x2e0f4166; WORD $0x7846 // ucomisd xmm0, qword [r14 + 120] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl - QUAD $0x000080862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 128] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl - QUAD $0x000088862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 136] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl - QUAD $0x000090862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 144] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc308 // or bl, al - QUAD $0x000098862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 152] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl - QUAD $0x0000a0862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 160] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl - QUAD $0x0000a8862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 168] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl - QUAD $0x0000b0862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 176] - WORD $0x9a0f; BYTE $0xd0 // setp al +LBB5_71: + LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] + LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] + LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] + LONG $0xd2950f41 // setne r10b + LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] + QUAD $0x000000b02494950f // setne byte [rsp + 176] + LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] LONG $0xd4950f41 // setne r12b - WORD $0x0841; BYTE $0xc4 // or r12b, al - QUAD $0x0000b8862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 184] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd0950f41 // setne r8b - WORD $0x0841; BYTE $0xc0 // or r8b, al - QUAD $0x0000c0862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 192] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl - QUAD $0x0000c8862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 200] - WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x16423b66 // cmp ax, word [rdx + 22] LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al - QUAD $0x0000d0862e0f4166; BYTE $0x00 // ucomisd xmm0, qword [r14 + 208] - WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al - QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - QUAD $0x000000e0822e0f66 // ucomisd xmm0, qword [rdx + 224] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl - QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] - WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x12423b66 // cmp ax, word [rdx + 18] + LONG $0xd3950f41 // setne r11b + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x0e423b66 // cmp ax, word [rdx + 14] + LONG $0xd6950f40 // setne sil + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x0c423b66 // cmp ax, word [rdx + 12] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x0a423b66 // cmp ax, word [rdx + 10] + LONG $0xd1950f41 // setne r9b + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x08423b66 // cmp ax, word [rdx + 8] + LONG $0xd0950f41 // setne r8b + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x06423b66 // cmp ax, word [rdx + 6] + LONG $0xd7950f40 // setne dil + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x04423b66 // cmp ax, word [rdx + 4] WORD $0x950f; BYTE $0xd1 // setne cl + LONG $0x0c24448b // mov eax, dword [rsp + 12] + WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] + QUAD $0x000000e02494950f // setne byte [rsp + 224] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x02423b66 // cmp ax, word [rdx + 2] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x246c8b44; BYTE $0x0c // mov r13d, dword [rsp + 12] + LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x0c245c8b // mov ebx, dword [rsp + 12] + LONG $0x205a3b66 // cmp bx, word [rdx + 32] + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x0c245c8b // mov ebx, dword [rsp + 12] + LONG $0x305a3b66 // cmp bx, word [rdx + 48] + QUAD $0x000000802494950f // setne byte [rsp + 128] + WORD $0xc000 // add al, al + LONG $0xe0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al - LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl - QUAD $0x000000f0822e0f66 // ucomisd xmm0, qword [rdx + 240] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f40 // setne dil - WORD $0x0840; BYTE $0xc7 // or dil, al - QUAD $0x000000f8822e0f66 // ucomisd xmm0, qword [rdx + 248] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f40 // setne sil - WORD $0x0840; BYTE $0xc6 // or sil, al - WORD $0x0045; BYTE $0xdb // add r11b, r11b - LONG $0x245c0244; BYTE $0x18 // add r11b, byte [rsp + 24] + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x04e0c041 // shl r8b, 4 + WORD $0x0841; BYTE $0xf8 // or r8b, dil LONG $0x05e1c041 // shl r9b, 5 - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0x0844; BYTE $0xc8 // or al, r9b - WORD $0x8941; BYTE $0xc1 // mov r9d, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xc6 // or sil, al + WORD $0x0844; BYTE $0xce // or sil, r9b + LONG $0x00758841 // mov byte [r13], sil + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x000000a0249c0244 // add r11b, byte [rsp + 160] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x24748b44; BYTE $0x0c // mov r14d, dword [rsp + 12] + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x01558845 // mov byte [r13 + 1], r10b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xc000 // add al, al + LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0844; BYTE $0xd8 // or al, r11b - WORD $0x8941; BYTE $0xc3 // mov r11d, eax - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] - WORD $0xc900 // add cl, cl - LONG $0x30244c02 // add cl, byte [rsp + 48] - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0844; BYTE $0xc8 // or al, r9b - WORD $0x8941; BYTE $0xc1 // mov r9d, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xd8 // or al, r11b - WORD $0x8941; BYTE $0xc3 // mov r11d, eax + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02458841 // mov byte [r13 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x10244488 // mov byte [rsp + 16], al - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl - WORD $0x8941; BYTE $0xc3 // mov r11d, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e5c041 // shl r13b, 6 - WORD $0x0841; BYTE $0xc5 // or r13b, al - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xc900 // add cl, cl - LONG $0x78244c02 // add cl, byte [rsp + 120] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0xcb08 // or bl, cl - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - LONG $0x244c0a44; BYTE $0x10 // or r9b, byte [rsp + 16] - QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x06e4c041 // shl r12b, 6 - WORD $0x0841; BYTE $0xdc // or r12b, bl - WORD $0x0845; BYTE $0xdd // or r13b, r11b - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xe0 // or r8b, r12b - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x0000009024bc0244 // add r15b, byte [rsp + 144] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xfe // or r14b, r15b - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xf2 // or r10b, r14b - QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xd1 // or cl, r10b - WORD $0x8844; BYTE $0x08 // mov byte [rax], r9b - QUAD $0x000000a8249cb60f // movzx ebx, byte [rsp + 168] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - LONG $0x06e7c040 // shl dil, 6 - WORD $0x0840; BYTE $0xdf // or dil, bl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e6c040 // shl sil, 7 - WORD $0x0840; BYTE $0xfe // or sil, dil - WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x02408844 // mov byte [rax + 2], r8b - LONG $0x03708840 // mov byte [rax + 3], sil - LONG $0x00b28d4c; WORD $0x0001; BYTE $0x00 // lea r14, [rdx + 256] - LONG $0x04c08348 // add rax, 4 - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c58349 // add r13, 4 QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB5_52 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + JNE LBB5_71 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + JMP LBB5_134 -LBB5_54: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JNE LBB5_194 - WORD $0xff31 // xor edi, edi - JMP LBB5_196 +LBB5_73: + LONG $0x36b70f44 // movzx r14d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_79 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_77 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB5_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB5_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB5_198 - WORD $0x068a // mov al, byte [rsi] - LONG $0x10244488 // mov byte [rsp + 16], al - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] - -LBB5_6: - LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] - WORD $0x3a41; BYTE $0x0e // cmp cl, byte [r14] - LONG $0x01768d4d // lea r14, [r14 + 1] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f44; BYTE $0x32 // movzx r9d, byte [rdx + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x323c8840 // mov byte [rdx + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_6 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 +LBB5_76: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x313b4466 // cmp r14w, word [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_76 -LBB5_8: - LONG $0x05fac149 // sar r10, 5 +LBB5_77: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 + +LBB5_79: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_9 - LONG $0x10fa8349 // cmp r10, 16 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000001082494894c // mov qword [rsp + 264], r10 + JL LBB5_138 + LONG $0x08f98348 // cmp rcx, 8 + LONG $0x24748944; BYTE $0x0c // mov dword [rsp + 12], r14d + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000a8248c8948 // mov qword [rsp + 168], rcx JB LBB5_83 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - LONG $0x24443948; BYTE $0x08 // cmp qword [rsp + 8], rax - JAE LBB5_86 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB5_86 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB5_208 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB5_208 LBB5_83: WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB5_89: - QUAD $0x000000e824942b4c // sub r10, qword [rsp + 232] - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 +LBB5_84: + LONG $0x244c2b48; BYTE $0x20 // sub rcx, qword [rsp + 32] + QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx -LBB5_90: - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - LONG $0x1f463a41 // cmp al, byte [r14 + 31] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0x1e463a41 // cmp al, byte [r14 + 30] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x1d463a41 // cmp al, byte [r14 + 29] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x1c463a41 // cmp al, byte [r14 + 28] +LBB5_85: + LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x1b463a41 // cmp al, byte [r14 + 27] + LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x1a463a41 // cmp al, byte [r14 + 26] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x19463a41 // cmp al, byte [r14 + 25] + LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x17463a41 // cmp al, byte [r14 + 23] + LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x16463a41 // cmp al, byte [r14 + 22] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x15463a41 // cmp al, byte [r14 + 21] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x14463a41 // cmp al, byte [r14 + 20] + LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x13463a41 // cmp al, byte [r14 + 19] - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x12463a41 // cmp al, byte [r14 + 18] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x11463a41 // cmp al, byte [r14 + 17] + LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x0f463a41 // cmp al, byte [r14 + 15] + LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] + LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] + LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] + LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] + LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] LONG $0xd2950f41 // setne r10b - LONG $0x0e463a41 // cmp al, byte [r14 + 14] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x0d463a41 // cmp al, byte [r14 + 13] - LONG $0xd5950f41 // setne r13b - LONG $0x0c463a41 // cmp al, byte [r14 + 12] + LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] + QUAD $0x000000b02494950f // setne byte [rsp + 176] + LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] LONG $0xd4950f41 // setne r12b - LONG $0x0b463a41 // cmp al, byte [r14 + 11] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x16423b66 // cmp ax, word [rdx + 22] LONG $0xd7950f41 // setne r15b - LONG $0x0a463a41 // cmp al, byte [r14 + 10] - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x09463a41 // cmp al, byte [r14 + 9] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x14423b66 // cmp ax, word [rdx + 20] + LONG $0xd6950f41 // setne r14b + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x12423b66 // cmp ax, word [rdx + 18] LONG $0xd3950f41 // setne r11b - LONG $0x07463a41 // cmp al, byte [r14 + 7] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd6950f40 // setne sil - LONG $0x06463a41 // cmp al, byte [r14 + 6] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x05463a41 // cmp al, byte [r14 + 5] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x0c423b66 // cmp ax, word [rdx + 12] + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x0a423b66 // cmp ax, word [rdx + 10] LONG $0xd1950f41 // setne r9b - LONG $0x04463a41 // cmp al, byte [r14 + 4] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x08423b66 // cmp ax, word [rdx + 8] LONG $0xd0950f41 // setne r8b - LONG $0x03463a41 // cmp al, byte [r14 + 3] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x06423b66 // cmp ax, word [rdx + 6] LONG $0xd7950f40 // setne dil - LONG $0x02463a41 // cmp al, byte [r14 + 2] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0x3a41; BYTE $0x06 // cmp al, byte [r14] - QUAD $0x000000a82494950f // setne byte [rsp + 168] - LONG $0x01463a41 // cmp al, byte [r14 + 1] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x04423b66 // cmp ax, word [rdx + 4] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x08463a41 // cmp al, byte [r14 + 8] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] + QUAD $0x000000e02494950f // setne byte [rsp + 224] + LONG $0x0c24448b // mov eax, dword [rsp + 12] + LONG $0x02423b66 // cmp ax, word [rdx + 2] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x246c8b44; BYTE $0x0c // mov r13d, dword [rsp + 12] + LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x0c245c8b // mov ebx, dword [rsp + 12] + LONG $0x205a3b66 // cmp bx, word [rdx + 32] QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x10463a41 // cmp al, byte [r14 + 16] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x18463a41 // cmp al, byte [r14 + 24] - QUAD $0x000000882494950f // setne byte [rsp + 136] - WORD $0xc900 // add cl, cl - LONG $0xa8248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 168] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xca08 // or dl, cl + LONG $0x0c245c8b // mov ebx, dword [rsp + 12] + LONG $0x305a3b66 // cmp bx, word [rdx + 48] + QUAD $0x000000802494950f // setne byte [rsp + 128] + WORD $0xc000 // add al, al + LONG $0xe0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xd7 // or dil, dl + WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x04e0c041 // shl r8b, 4 WORD $0x0841; BYTE $0xf8 // or r8b, dil LONG $0x05e1c041 // shl r9b, 5 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e6c040 // shl sil, 7 WORD $0x0840; BYTE $0xc6 // or sil, al WORD $0x0844; BYTE $0xce // or sil, r9b - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - WORD $0x8840; BYTE $0x30 // mov byte [rax], sil + LONG $0x00758841 // mov byte [r13], sil WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000c0249c0244 // add r11b, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xdb // or bl, r11b + QUAD $0x000000a0249c0244 // add r11b, byte [rsp + 160] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xde // or r14b, r11b LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x0845; BYTE $0xf7 // or r15b, r14b LONG $0x04e4c041 // shl r12b, 4 WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x24748b44; BYTE $0x0c // mov r14d, dword [rsp + 12] + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0841; BYTE $0xca // or r10b, cl - WORD $0x0845; BYTE $0xea // or r10b, r13b - LONG $0x01508844 // mov byte [rax + 1], r10b - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xc900 // add cl, cl - LONG $0x90248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 144] - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xd108 // or cl, dl - WORD $0x4888; BYTE $0x02 // mov byte [rax + 2], cl - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xc900 // add cl, cl - LONG $0x88248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 136] - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x01558845 // mov byte [r13 + 1], r10b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xc000 // add al, al + LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xd108 // or cl, dl - WORD $0x4888; BYTE $0x03 // mov byte [rax + 3], cl - LONG $0x20c68349 // add r14, 32 - LONG $0x04c08348 // add rax, 4 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02458841 // mov byte [r13 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c58349 // add r13, 4 QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 + JNE LBB5_85 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + JMP LBB5_139 + +LBB5_87: + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_93 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_91 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB5_90: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 JNE LBB5_90 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - JMP LBB5_92 - -LBB5_28: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB5_145 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB5_198 - WORD $0x8b4c; BYTE $0x1e // mov r11, qword [rsi] - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_34 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] -LBB5_32: - WORD $0x3b4d; BYTE $0x1e // cmp r11, qword [r14] - LONG $0x08768d4d // lea r14, [r14 + 8] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x1cb60f41; BYTE $0x30 // movzx ebx, byte [r8 + rsi] - WORD $0xda30 // xor dl, bl - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3040; BYTE $0xdf // xor dil, bl - LONG $0x303c8841 // mov byte [r8 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_32 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 +LBB5_91: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 -LBB5_34: - LONG $0x05fac149 // sar r10, 5 +LBB5_93: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_38 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - QUAD $0x000000a82494894c // mov qword [rsp + 168], r10 + JL LBB5_97 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax -LBB5_36: - LONG $0xf89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 248] +LBB5_95: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0xf09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 240] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0xe89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 232] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0xe09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 224] - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0xd89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 216] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0xd09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 208] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0xc89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 200] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0xb89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 184] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0xb09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 176] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0xa89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 168] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xa09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 160] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x989e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 152] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x909e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 144] - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x889e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 136] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x785e3b4d // cmp r11, qword [r14 + 120] - LONG $0xd0950f41 // setne r8b - LONG $0x705e3b4d // cmp r11, qword [r14 + 112] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x685e3b4d // cmp r11, qword [r14 + 104] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x605e3b4d // cmp r11, qword [r14 + 96] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] LONG $0xd7950f40 // setne dil - LONG $0x585e3b4d // cmp r11, qword [r14 + 88] + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + QUAD $0x000000b02494950f // setne byte [rsp + 176] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] + LONG $0xd3950f41 // setne r11b + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd2950f41 // setne r10b - LONG $0x505e3b4d // cmp r11, qword [r14 + 80] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd1950f41 // setne r9b - LONG $0x485e3b4d // cmp r11, qword [r14 + 72] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] LONG $0xd6950f40 // setne sil - LONG $0x385e3b4d // cmp r11, qword [r14 + 56] + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x305e3b4d // cmp r11, qword [r14 + 48] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x285e3b4d // cmp r11, qword [r14 + 40] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x205e3b4d // cmp r11, qword [r14 + 32] - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x185e3b4d // cmp r11, qword [r14 + 24] - LONG $0xd7950f41 // setne r15b - LONG $0x105e3b4d // cmp r11, qword [r14 + 16] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] LONG $0xd4950f41 // setne r12b - WORD $0x3b4d; BYTE $0x1e // cmp r11, qword [r14] - QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x085e3b4d // cmp r11, qword [r14 + 8] + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd5950f41 // setne r13b - LONG $0x405e3b4d // cmp r11, qword [r14 + 64] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x809e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 128] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] + LONG $0xd7950f41 // setne r15b + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0xd6950f41 // setne r14b + LONG $0x40423b4c // cmp r8, qword [rdx + 64] QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0xc09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 192] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - WORD $0x0045; BYTE $0xed // add r13b, r13b - QUAD $0x000000c024ac0244 // add r13b, byte [rsp + 192] - LONG $0x02e4c041 // shl r12b, 2 + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a024b40244 // add r14b, byte [rsp + 160] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xfd // or r13b, r15b + LONG $0x04e4c041 // shl r12b, 4 WORD $0x0845; BYTE $0xec // or r12b, r13b - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xe7 // or r15b, r12b - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xfa // or dl, r15b WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x00458841 // mov byte [r13], al + LONG $0x24048841 // mov byte [r12], al WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000b024b40240 // add sil, byte [rsp + 176] + QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] LONG $0x02e1c041 // shl r9b, 2 WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e7c040 // shl dil, 4 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0x0844; BYTE $0xd8 // or al, r11b + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01458845 // mov byte [r13 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl + WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] + LONG $0x78244402 // add al, byte [rsp + 120] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl + WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x00c68149; WORD $0x0001; BYTE $0x00 // add r14, 256 - LONG $0x04c58349 // add r13, 4 - LONG $0x246c894c; BYTE $0x08 // mov qword [rsp + 8], r13 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_36 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB5_95 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB5_38: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JE LBB5_40 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xff31 // xor edi, edi - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] +LBB5_97: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB5_190 -LBB5_158: - WORD $0x3b4d; BYTE $0x1e // cmp r11, qword [r14] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0x3044; BYTE $0xd0 // xor al, r10b - WORD $0xc220 // and dl, al - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - LONG $0x37148841 // mov byte [r15 + rsi], dl - LONG $0x02c78348 // add rdi, 2 - LONG $0x085e3b4d // cmp r11, qword [r14 + 8] - LONG $0x10768d4d // lea r14, [r14 + 16] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0xd030 // xor al, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0xc320 // and bl, al - WORD $0xd330 // xor bl, dl - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB5_158 - JMP LBB5_41 +LBB5_99: + WORD $0xff31 // xor edi, edi + JMP LBB5_192 -LBB5_57: - WORD $0x068a // mov al, byte [rsi] - LONG $0x40244488 // mov byte [rsp + 64], al - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_61 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] +LBB5_100: + WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_106 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_104 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB5_59: - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] - WORD $0x3a41; BYTE $0x0e // cmp cl, byte [r14] - LONG $0x01768d4d // lea r14, [r14 + 1] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f44; BYTE $0x32 // movzx r9d, byte [rdx + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x323c8840 // mov byte [rdx + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_59 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 - -LBB5_61: - LONG $0x05fac149 // sar r10, 5 +LBB5_103: + WORD $0x2e0f; BYTE $0x01 // ucomiss xmm0, dword [rcx] + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x9a0f; BYTE $0xd1 // setp cl + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xcb08 // or bl, cl + WORD $0xdbf6 // neg bl + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_103 + +LBB5_104: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 + +LBB5_106: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_62 - LONG $0x10fa8349 // cmp r10, 16 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000001082494894c // mov qword [rsp + 264], r10 - JB LBB5_64 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - LONG $0x24443948; BYTE $0x08 // cmp qword [rsp + 8], rax - JAE LBB5_67 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB5_67 + JL LBB5_142 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x04f98348 // cmp rcx, 4 + JB LBB5_110 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB5_211 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB5_211 -LBB5_64: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax +LBB5_110: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB5_70: - QUAD $0x000000e824942b4c // sub r10, qword [rsp + 232] - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 +LBB5_111: + QUAD $0x0000008824ac894c // mov qword [rsp + 136], r13 + QUAD $0x000000a824b48944 // mov dword [rsp + 168], r14d + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + WORD $0x294c; BYTE $0xc9 // sub rcx, r9 + QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx -LBB5_71: - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - LONG $0x1f463a41 // cmp al, byte [r14 + 31] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0x1e463a41 // cmp al, byte [r14 + 30] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0x1d463a41 // cmp al, byte [r14 + 29] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x1c463a41 // cmp al, byte [r14 + 28] - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x1b463a41 // cmp al, byte [r14 + 27] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x1a463a41 // cmp al, byte [r14 + 26] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x19463a41 // cmp al, byte [r14 + 25] - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x17463a41 // cmp al, byte [r14 + 23] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x16463a41 // cmp al, byte [r14 + 22] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x15463a41 // cmp al, byte [r14 + 21] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x14463a41 // cmp al, byte [r14 + 20] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x13463a41 // cmp al, byte [r14 + 19] - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x12463a41 // cmp al, byte [r14 + 18] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x11463a41 // cmp al, byte [r14 + 17] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x0f463a41 // cmp al, byte [r14 + 15] - LONG $0xd2950f41 // setne r10b - LONG $0x0e463a41 // cmp al, byte [r14 + 14] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x0d463a41 // cmp al, byte [r14 + 13] - LONG $0xd5950f41 // setne r13b - LONG $0x0c463a41 // cmp al, byte [r14 + 12] +LBB5_112: + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + WORD $0x8941; BYTE $0xcd // mov r13d, ecx + LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + LONG $0x08432e0f // ucomiss xmm0, dword [rbx + 8] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x10244c88 // mov byte [rsp + 16], cl + LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x18244c88 // mov byte [rsp + 24], cl + LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x28244c88 // mov byte [rsp + 40], cl + LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x30244c88 // mov byte [rsp + 48], cl + LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x38244c88 // mov byte [rsp + 56], cl + LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x0c244c88 // mov byte [rsp + 12], cl + LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x20244c88 // mov byte [rsp + 32], cl + LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x48244c88 // mov byte [rsp + 72], cl + LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x40244c88 // mov byte [rsp + 64], cl + LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x58244c88 // mov byte [rsp + 88], cl + LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x50244c88 // mov byte [rsp + 80], cl + LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x68244c88 // mov byte [rsp + 104], cl + LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x78244c88 // mov byte [rsp + 120], cl + LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x60244c88 // mov byte [rsp + 96], cl + LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x70244c88 // mov byte [rsp + 112], cl + LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] + WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd4950f41 // setne r12b - LONG $0x0b463a41 // cmp al, byte [r14 + 11] - LONG $0xd7950f41 // setne r15b - LONG $0x0a463a41 // cmp al, byte [r14 + 10] - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x09463a41 // cmp al, byte [r14 + 9] + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x48432e0f // ucomiss xmm0, dword [rbx + 72] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl + LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl + LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl + LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0xa0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 160], cl + LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd6950f41 // setne r14b + WORD $0x0841; BYTE $0xc6 // or r14b, al + LONG $0x5c432e0f // ucomiss xmm0, dword [rbx + 92] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd0950f41 // setne r8b + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x60432e0f // ucomiss xmm0, dword [rbx + 96] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd1 // setne cl + WORD $0xc108 // or cl, al + LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl + LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] + WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd3950f41 // setne r11b - LONG $0x07463a41 // cmp al, byte [r14 + 7] - LONG $0xd6950f40 // setne sil - LONG $0x06463a41 // cmp al, byte [r14 + 6] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x05463a41 // cmp al, byte [r14 + 5] + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x68432e0f // ucomiss xmm0, dword [rbx + 104] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd2950f41 // setne r10b + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x6c432e0f // ucomiss xmm0, dword [rbx + 108] + WORD $0x9a0f; BYTE $0xd0 // setp al LONG $0xd1950f41 // setne r9b - LONG $0x04463a41 // cmp al, byte [r14 + 4] - LONG $0xd0950f41 // setne r8b - LONG $0x03463a41 // cmp al, byte [r14 + 3] - LONG $0xd7950f40 // setne dil - LONG $0x02463a41 // cmp al, byte [r14 + 2] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0x3a41; BYTE $0x06 // cmp al, byte [r14] - QUAD $0x000000a82494950f // setne byte [rsp + 168] - LONG $0x01463a41 // cmp al, byte [r14 + 1] + WORD $0x0841; BYTE $0xc1 // or r9b, al + LONG $0x70432e0f // ucomiss xmm0, dword [rbx + 112] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f41 // setne r15b + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] + WORD $0x9a0f; BYTE $0xd0 // setp al WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x08463a41 // cmp al, byte [r14 + 8] - QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x10463a41 // cmp al, byte [r14 + 16] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x18463a41 // cmp al, byte [r14 + 24] - QUAD $0x000000882494950f // setne byte [rsp + 136] - WORD $0xc900 // add cl, cl - LONG $0xa8248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 168] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xca08 // or dl, cl - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xd7 // or dil, dl - LONG $0x04e0c041 // shl r8b, 4 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x05e1c041 // shl r9b, 5 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c040 // shl sil, 7 + WORD $0xc108 // or cl, al + LONG $0xe0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 224], cl + LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd7950f40 // setne dil + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x7c432e0f // ucomiss xmm0, dword [rbx + 124] + WORD $0x9a0f; BYTE $0xd0 // setp al + LONG $0xd6950f40 // setne sil WORD $0x0840; BYTE $0xc6 // or sil, al - WORD $0x0844; BYTE $0xce // or sil, r9b - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - WORD $0x8840; BYTE $0x30 // mov byte [rax], sil - WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000c0249c0244 // add r11b, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0844; BYTE $0xdb // or bl, r11b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xca // or r10b, cl - WORD $0x0845; BYTE $0xea // or r10b, r13b - LONG $0x01508844 // mov byte [rax + 1], r10b - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xc900 // add cl, cl - LONG $0x90248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 144] - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xd108 // or cl, dl - WORD $0x4888; BYTE $0x02 // mov byte [rax + 2], cl - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xc900 // add cl, cl - LONG $0x88248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 136] - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xd200 // add dl, dl + WORD $0x0844; BYTE $0xea // or dl, r13b + WORD $0x8941; BYTE $0xd5 // mov r13d, edx + LONG $0x2454b60f; BYTE $0x30 // movzx edx, byte [rsp + 48] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0x0844; BYTE $0xe8 // or al, r13b + WORD $0x8941; BYTE $0xc5 // mov r13d, eax + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xc900 // add cl, cl + LONG $0x20244c02 // add cl, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd008 // or al, dl + LONG $0x0c244488 // mov byte [rsp + 12], al + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xe8 // or al, r13b + WORD $0x8941; BYTE $0xc5 // mov r13d, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xe8 // or al, r13b + LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xca08 // or dl, cl + LONG $0x6cb60f44; WORD $0x6824 // movzx r13d, byte [rsp + 104] + LONG $0x05e5c041 // shl r13b, 5 + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + LONG $0x6cb60f44; WORD $0x6024 // movzx r13d, byte [rsp + 96] + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xcd // or r13b, cl + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x70 // add r12b, byte [rsp + 112] + WORD $0x8944; BYTE $0xe1 // mov ecx, r12d + QUAD $0x00008024a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 128] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xcc // or r12b, cl + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0x8941; BYTE $0xcc // mov r12d, ecx + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x64b60f44; WORD $0x0c24 // movzx r12d, byte [rsp + 12] + WORD $0x0841; BYTE $0xc4 // or r12b, al + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + LONG $0x06e6c041 // shl r14b, 6 + WORD $0x0841; BYTE $0xc6 // or r14b, al + WORD $0x0841; BYTE $0xd5 // or r13b, dl + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xf0 // or r8b, r14b + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x00000090249c0244 // add r11b, byte [rsp + 144] + LONG $0x02e2c041 // shl r10b, 2 + WORD $0x0845; BYTE $0xda // or r10b, r11b + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xd1 // or r9b, r10b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + WORD $0x8844; BYTE $0x20 // mov byte [rax], r12b + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xd108 // or cl, dl - WORD $0x4888; BYTE $0x03 // mov byte [rax + 3], cl - LONG $0x20c68349 // add r14, 32 + LONG $0x06e7c040 // shl dil, 6 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x01688844 // mov byte [rax + 1], r13b + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xfe // or sil, dil + WORD $0x0844; BYTE $0xfe // or sil, r15b + LONG $0x02408844 // mov byte [rax + 2], r8b + LONG $0x03708840 // mov byte [rax + 3], sil + LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 LONG $0x04c08348 // add rax, 4 - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + QUAD $0x0000008824848948 // mov qword [rsp + 136], rax QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB5_71 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - JMP LBB5_73 + JNE LBB5_112 + QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000a824b48b44 // mov r14d, dword [rsp + 168] + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + JMP LBB5_143 -LBB5_145: - WORD $0x8b44; BYTE $0x1e // mov r11d, dword [rsi] - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_149 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] +LBB5_114: + WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB5_161 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB5_117: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1c048841 // mov byte [r12 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB5_117 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB5_162 + JMP LBB5_200 -LBB5_147: - WORD $0x3b45; BYTE $0x1e // cmp r11d, dword [r14] - LONG $0x04768d4d // lea r14, [r14 + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x1cb60f41; BYTE $0x30 // movzx ebx, byte [r8 + rsi] - WORD $0xda30 // xor dl, bl - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3040; BYTE $0xdf // xor dil, bl - LONG $0x303c8841 // mov byte [r8 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_147 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 +LBB5_119: + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB5_125 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB5_123 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB5_149: - LONG $0x05fac149 // sar r10, 5 +LBB5_122: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB5_122 + +LBB5_123: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB5_200 + LONG $0x01c48349 // add r12, 1 + +LBB5_125: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_153 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - QUAD $0x000000a82494894c // mov qword [rsp + 168], r10 + JL LBB5_129 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax -LBB5_151: - LONG $0x7c5e3b45 // cmp r11d, dword [r14 + 124] +LBB5_127: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] + LONG $0x2454950f; BYTE $0x0c // setne byte [rsp + 12] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] + LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0x785e3b45 // cmp r11d, dword [r14 + 120] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x745e3b45 // cmp r11d, dword [r14 + 116] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x705e3b45 // cmp r11d, dword [r14 + 112] - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x6c5e3b45 // cmp r11d, dword [r14 + 108] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x685e3b45 // cmp r11d, dword [r14 + 104] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x645e3b45 // cmp r11d, dword [r14 + 100] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x5c5e3b45 // cmp r11d, dword [r14 + 92] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x585e3b45 // cmp r11d, dword [r14 + 88] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x545e3b45 // cmp r11d, dword [r14 + 84] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x505e3b45 // cmp r11d, dword [r14 + 80] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x4c5e3b45 // cmp r11d, dword [r14 + 76] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x485e3b45 // cmp r11d, dword [r14 + 72] - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x445e3b45 // cmp r11d, dword [r14 + 68] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x3c5e3b45 // cmp r11d, dword [r14 + 60] - LONG $0xd0950f41 // setne r8b - LONG $0x385e3b45 // cmp r11d, dword [r14 + 56] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x345e3b45 // cmp r11d, dword [r14 + 52] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x305e3b45 // cmp r11d, dword [r14 + 48] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] LONG $0xd7950f40 // setne dil - LONG $0x2c5e3b45 // cmp r11d, dword [r14 + 44] + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + QUAD $0x000000802494950f // setne byte [rsp + 128] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + QUAD $0x000000b02494950f // setne byte [rsp + 176] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] + LONG $0xd3950f41 // setne r11b + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] LONG $0xd2950f41 // setne r10b - LONG $0x285e3b45 // cmp r11d, dword [r14 + 40] + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] LONG $0xd1950f41 // setne r9b - LONG $0x245e3b45 // cmp r11d, dword [r14 + 36] + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] LONG $0xd6950f40 // setne sil - LONG $0x1c5e3b45 // cmp r11d, dword [r14 + 28] + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x185e3b45 // cmp r11d, dword [r14 + 24] + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x145e3b45 // cmp r11d, dword [r14 + 20] + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x105e3b45 // cmp r11d, dword [r14 + 16] - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x0c5e3b45 // cmp r11d, dword [r14 + 12] - LONG $0xd7950f41 // setne r15b - LONG $0x085e3b45 // cmp r11d, dword [r14 + 8] + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] LONG $0xd4950f41 // setne r12b - WORD $0x3b45; BYTE $0x1e // cmp r11d, dword [r14] - QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x045e3b45 // cmp r11d, dword [r14 + 4] + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] LONG $0xd5950f41 // setne r13b - LONG $0x205e3b45 // cmp r11d, dword [r14 + 32] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x405e3b45 // cmp r11d, dword [r14 + 64] + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] + LONG $0xd7950f41 // setne r15b + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd6950f41 // setne r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x605e3b45 // cmp r11d, dword [r14 + 96] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - WORD $0x0045; BYTE $0xed // add r13b, r13b - QUAD $0x000000c024ac0244 // add r13b, byte [rsp + 192] - LONG $0x02e4c041 // shl r12b, 2 + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x000000a024b40244 // add r14b, byte [rsp + 160] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xfd // or r13b, r15b + LONG $0x04e4c041 // shl r12b, 4 WORD $0x0845; BYTE $0xec // or r12b, r13b - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xe7 // or r15b, r12b - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xfa // or dl, r15b WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl + WORD $0x0844; BYTE $0xe1 // or cl, r12b + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x00458841 // mov byte [r13], al + LONG $0x24048841 // mov byte [r12], al WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000b024b40240 // add sil, byte [rsp + 176] + QUAD $0x0000009024b40240 // add sil, byte [rsp + 144] LONG $0x02e1c041 // shl r9b, 2 WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e7c040 // shl dil, 4 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0x0844; BYTE $0xd8 // or al, r11b + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01458845 // mov byte [r13 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl + WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] + LONG $0x78244402 // add al, byte [rsp + 120] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl + WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x80ee8349 // sub r14, -128 - LONG $0x04c58349 // add r13, 4 - LONG $0x246c894c; BYTE $0x08 // mov qword [rsp + 8], r13 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_151 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al + LONG $0x80ea8348 // sub rdx, -128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB5_127 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB5_153: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 +LBB5_129: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB5_200 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB5_175 + +LBB5_131: + WORD $0xff31 // xor edi, edi + JMP LBB5_177 + +LBB5_132: + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + JMP LBB5_149 + +LBB5_133: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + +LBB5_134: + LONG $0x05e1c148 // shl rcx, 5 WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JNE LBB5_155 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB5_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB5_141 + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xf631 // xor esi, esi -LBB5_23: - WORD $0xff31 // xor edi, edi - JMP LBB5_24 +LBB5_137: + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + LONG $0x323b4466 // cmp r14w, word [rdx] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x03efc148 // shr rdi, 3 + LONG $0x54b60f45; WORD $0x003d // movzx r10d, byte [r13 + rdi] + WORD $0xf189 // mov ecx, esi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl + LONG $0x02c68348 // add rsi, 2 + LONG $0x703b4466; BYTE $0x02 // cmp r14w, word [rax + 2] + LONG $0x04508d48 // lea rdx, [rax + 4] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB5_137 + JMP LBB5_197 -LBB5_100: - LONG $0x1eb70f44 // movzx r11d, word [rsi] - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_104 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] +LBB5_138: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB5_102: - LONG $0x1e3b4566 // cmp r11w, word [r14] - LONG $0x02768d4d // lea r14, [r14 + 2] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f44; BYTE $0x32 // movzx r9d, byte [rdx + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x323c8840 // mov byte [rdx + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_102 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 +LBB5_139: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB5_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB5_195 -LBB5_104: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_105 - LONG $0x08fa8349 // cmp r10, 8 - LONG $0x245c8944; BYTE $0x10 // mov dword [rsp + 16], r11d - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - JB LBB5_107 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - LONG $0x24443948; BYTE $0x08 // cmp qword [rsp + 8], rax - JAE LBB5_110 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - WORD $0x394c; BYTE $0xf0 // cmp rax, r14 - JBE LBB5_110 - -LBB5_107: - WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] +LBB5_141: + WORD $0xf631 // xor esi, esi + JMP LBB5_197 -LBB5_113: - LONG $0x24542b4c; BYTE $0x28 // sub r10, qword [rsp + 40] - QUAD $0x000000a82494894c // mov qword [rsp + 168], r10 +LBB5_142: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx -LBB5_114: - LONG $0x5e3b4566; BYTE $0x3e // cmp r11w, word [r14 + 62] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0x5e3b4566; BYTE $0x3c // cmp r11w, word [r14 + 60] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x5e3b4566; BYTE $0x3a // cmp r11w, word [r14 + 58] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x5e3b4566; BYTE $0x38 // cmp r11w, word [r14 + 56] - LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x5e3b4566; BYTE $0x36 // cmp r11w, word [r14 + 54] - LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x5e3b4566; BYTE $0x34 // cmp r11w, word [r14 + 52] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x5e3b4566; BYTE $0x32 // cmp r11w, word [r14 + 50] - LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x5e3b4566; BYTE $0x2e // cmp r11w, word [r14 + 46] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x5e3b4566; BYTE $0x2c // cmp r11w, word [r14 + 44] - LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x5e3b4566; BYTE $0x2a // cmp r11w, word [r14 + 42] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x5e3b4566; BYTE $0x28 // cmp r11w, word [r14 + 40] - LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x5e3b4566; BYTE $0x26 // cmp r11w, word [r14 + 38] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x5e3b4566; BYTE $0x24 // cmp r11w, word [r14 + 36] - QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x5e3b4566; BYTE $0x22 // cmp r11w, word [r14 + 34] - LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x5e3b4566; BYTE $0x1e // cmp r11w, word [r14 + 30] - LONG $0xd1950f41 // setne r9b - LONG $0x5e3b4566; BYTE $0x1c // cmp r11w, word [r14 + 28] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x5e3b4566; BYTE $0x1a // cmp r11w, word [r14 + 26] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x5e3b4566; BYTE $0x18 // cmp r11w, word [r14 + 24] - LONG $0xd5950f41 // setne r13b - LONG $0x5e3b4566; BYTE $0x16 // cmp r11w, word [r14 + 22] - LONG $0xd7950f41 // setne r15b - LONG $0x5e3b4566; BYTE $0x14 // cmp r11w, word [r14 + 20] - LONG $0xd3950f41 // setne r11b - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x12 // cmp ax, word [r14 + 18] - LONG $0xd2950f41 // setne r10b - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x0e // cmp ax, word [r14 + 14] - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x0c // cmp ax, word [r14 + 12] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x0a // cmp ax, word [r14 + 10] - LONG $0xd0950f41 // setne r8b - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x08 // cmp ax, word [r14 + 8] - LONG $0xd7950f40 // setne dil - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x06 // cmp ax, word [r14 + 6] - LONG $0xd6950f40 // setne sil - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x04 // cmp ax, word [r14 + 4] - WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x063b4166 // cmp ax, word [r14] - QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x02 // cmp ax, word [r14 + 2] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x894c; BYTE $0xe3 // mov rbx, r12 - LONG $0x24648b44; BYTE $0x10 // mov r12d, dword [rsp + 16] - LONG $0x663b4566; BYTE $0x10 // cmp r12w, word [r14 + 16] - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x10245c8b // mov ebx, dword [rsp + 16] - LONG $0x5e3b4166; BYTE $0x20 // cmp bx, word [r14 + 32] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x10245c8b // mov ebx, dword [rsp + 16] - LONG $0x5e3b4166; BYTE $0x30 // cmp bx, word [r14 + 48] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xc000 // add al, al - LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al - LONG $0x03e6c040 // shl sil, 3 - WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x04e7c040 // shl dil, 4 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x05e0c041 // shl r8b, 5 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xc208 // or dl, al - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x24148841 // mov byte [r12], dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000b024940244 // add r10b, byte [rsp + 176] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245c8b44; BYTE $0x10 // mov r11d, dword [rsp + 16] - LONG $0x04e5c041 // shl r13b, 4 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xe8 // or al, r13b - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc9 // or r9b, cl - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x244c8845; BYTE $0x01 // mov byte [r12 + 1], r9b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xc000 // add al, al - LONG $0x98248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 152] - WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl - WORD $0xc808 // or al, cl - LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - WORD $0xd808 // or al, bl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl - WORD $0xc808 // or al, cl - LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al - LONG $0x40c68349 // add r14, 64 - LONG $0x04c48349 // add r12, 4 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_114 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - JMP LBB5_116 +LBB5_143: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB5_200 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB5_201 + WORD $0xf631 // xor esi, esi + JMP LBB5_203 -LBB5_123: - LONG $0x1eb70f44 // movzx r11d, word [rsi] - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_127 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] +LBB5_146: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB5_163 -LBB5_125: - LONG $0x1e3b4566 // cmp r11w, word [r14] - LONG $0x02768d4d // lea r14, [r14 + 2] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f44; BYTE $0x32 // movzx r9d, byte [rdx + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x323c8840 // mov byte [rdx + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_125 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 +LBB5_147: + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB5_200 -LBB5_127: - LONG $0x05fac149 // sar r10, 5 +LBB5_148: + LONG $0x01c48349 // add r12, 1 + +LBB5_149: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_128 - LONG $0x08fa8349 // cmp r10, 8 - LONG $0x245c8944; BYTE $0x10 // mov dword [rsp + 16], r11d - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - JB LBB5_130 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - LONG $0x24443948; BYTE $0x08 // cmp qword [rsp + 8], rax - JAE LBB5_133 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - WORD $0x394c; BYTE $0xf0 // cmp rax, r14 - JBE LBB5_133 - -LBB5_130: - WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + JL LBB5_157 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x24748844; BYTE $0x0c // mov byte [rsp + 12], r14b + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + JB LBB5_153 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xe8 // add rax, r13 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB5_214 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc5 // cmp r13, rax + JAE LBB5_214 -LBB5_136: - LONG $0x24542b4c; BYTE $0x28 // sub r10, qword [rsp + 40] - QUAD $0x000000a82494894c // mov qword [rsp + 168], r10 +LBB5_153: + WORD $0xc031 // xor eax, eax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + WORD $0x894c; BYTE $0xef // mov rdi, r13 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB5_137: - LONG $0x5e3b4566; BYTE $0x3e // cmp r11w, word [r14 + 62] - LONG $0x2454950f; BYTE $0x08 // setne byte [rsp + 8] - LONG $0x5e3b4566; BYTE $0x3c // cmp r11w, word [r14 + 60] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0x5e3b4566; BYTE $0x3a // cmp r11w, word [r14 + 58] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0x5e3b4566; BYTE $0x38 // cmp r11w, word [r14 + 56] +LBB5_154: + QUAD $0x000000a8248c2b48 // sub rcx, qword [rsp + 168] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + +LBB5_155: + LONG $0x1f773a44 // cmp r14b, byte [rdi + 31] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x1e773a44 // cmp r14b, byte [rdi + 30] LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0x5e3b4566; BYTE $0x36 // cmp r11w, word [r14 + 54] + LONG $0x1d773a44 // cmp r14b, byte [rdi + 29] LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0x5e3b4566; BYTE $0x34 // cmp r11w, word [r14 + 52] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0x5e3b4566; BYTE $0x32 // cmp r11w, word [r14 + 50] + LONG $0x1c773a44 // cmp r14b, byte [rdi + 28] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x1b773a44 // cmp r14b, byte [rdi + 27] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x1a773a44 // cmp r14b, byte [rdi + 26] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0x5e3b4566; BYTE $0x2e // cmp r11w, word [r14 + 46] + LONG $0x19773a44 // cmp r14b, byte [rdi + 25] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x17773a44 // cmp r14b, byte [rdi + 23] + LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] + LONG $0x16773a44 // cmp r14b, byte [rdi + 22] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x15773a44 // cmp r14b, byte [rdi + 21] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x14773a44 // cmp r14b, byte [rdi + 20] LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0x5e3b4566; BYTE $0x2c // cmp r11w, word [r14 + 44] + LONG $0x13773a44 // cmp r14b, byte [rdi + 19] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x12773a44 // cmp r14b, byte [rdi + 18] LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0x5e3b4566; BYTE $0x2a // cmp r11w, word [r14 + 42] - LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0x5e3b4566; BYTE $0x28 // cmp r11w, word [r14 + 40] + LONG $0x11773a44 // cmp r14b, byte [rdi + 17] LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x5e3b4566; BYTE $0x26 // cmp r11w, word [r14 + 38] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x5e3b4566; BYTE $0x24 // cmp r11w, word [r14 + 36] + LONG $0x0f773a44 // cmp r14b, byte [rdi + 15] + LONG $0xd2950f41 // setne r10b + LONG $0x0e773a44 // cmp r14b, byte [rdi + 14] QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x5e3b4566; BYTE $0x22 // cmp r11w, word [r14 + 34] + LONG $0x0d773a44 // cmp r14b, byte [rdi + 13] LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x5e3b4566; BYTE $0x1e // cmp r11w, word [r14 + 30] - LONG $0xd1950f41 // setne r9b - LONG $0x5e3b4566; BYTE $0x1c // cmp r11w, word [r14 + 28] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x5e3b4566; BYTE $0x1a // cmp r11w, word [r14 + 26] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - LONG $0x5e3b4566; BYTE $0x18 // cmp r11w, word [r14 + 24] - LONG $0xd5950f41 // setne r13b - LONG $0x5e3b4566; BYTE $0x16 // cmp r11w, word [r14 + 22] + LONG $0x0c773a44 // cmp r14b, byte [rdi + 12] + LONG $0xd4950f41 // setne r12b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x0b // cmp al, byte [rdi + 11] LONG $0xd7950f41 // setne r15b - LONG $0x5e3b4566; BYTE $0x14 // cmp r11w, word [r14 + 20] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x0a // cmp al, byte [rdi + 10] + LONG $0xd6950f41 // setne r14b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x09 // cmp al, byte [rdi + 9] LONG $0xd3950f41 // setne r11b - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x12 // cmp ax, word [r14 + 18] - LONG $0xd2950f41 // setne r10b - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x0e // cmp ax, word [r14 + 14] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x07 // cmp al, byte [rdi + 7] WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x0c // cmp ax, word [r14 + 12] - QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x0a // cmp ax, word [r14 + 10] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x06 // cmp al, byte [rdi + 6] + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x05 // cmp al, byte [rdi + 5] + LONG $0xd1950f41 // setne r9b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x04 // cmp al, byte [rdi + 4] LONG $0xd0950f41 // setne r8b - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x08 // cmp ax, word [r14 + 8] - LONG $0xd7950f40 // setne dil - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x06 // cmp ax, word [r14 + 6] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x03 // cmp al, byte [rdi + 3] LONG $0xd6950f40 // setne sil - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x04 // cmp ax, word [r14 + 4] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x02 // cmp al, byte [rdi + 2] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x063b4166 // cmp ax, word [r14] - QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x1024448b // mov eax, dword [rsp + 16] - LONG $0x463b4166; BYTE $0x02 // cmp ax, word [r14 + 2] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x073a // cmp al, byte [rdi] + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x01 // cmp al, byte [rdi + 1] WORD $0x950f; BYTE $0xd0 // setne al - WORD $0x894c; BYTE $0xe3 // mov rbx, r12 - LONG $0x24648b44; BYTE $0x10 // mov r12d, dword [rsp + 16] - LONG $0x663b4566; BYTE $0x10 // cmp r12w, word [r14 + 16] - WORD $0x8949; BYTE $0xdc // mov r12, rbx + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x6cb60f44; WORD $0x0c24 // movzx r13d, byte [rsp + 12] + LONG $0x086f3a44 // cmp r13b, byte [rdi + 8] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x000000902494950f // setne byte [rsp + 144] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x5f3a; BYTE $0x10 // cmp bl, byte [rdi + 16] QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x10245c8b // mov ebx, dword [rsp + 16] - LONG $0x5e3b4166; BYTE $0x20 // cmp bx, word [r14 + 32] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x10245c8b // mov ebx, dword [rsp + 16] - LONG $0x5e3b4166; BYTE $0x30 // cmp bx, word [r14 + 48] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x5f3a; BYTE $0x18 // cmp bl, byte [rdi + 24] WORD $0x950f; BYTE $0xd3 // setne bl WORD $0xc000 // add al, al - LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al LONG $0x03e6c040 // shl sil, 3 WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x04e7c040 // shl dil, 4 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x05e0c041 // shl r8b, 5 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x04e0c041 // shl r8b, 4 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + LONG $0x05e1c041 // shl r9b, 5 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x06 // shl al, 6 WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0xc208 // or dl, al - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x24148841 // mov byte [r12], dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000b024940244 // add r10b, byte [rsp + 176] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b + WORD $0x0844; BYTE $0xca // or dl, r9b + LONG $0x00558841 // mov byte [r13], dl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x00000090249c0244 // add r11b, byte [rsp + 144] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xde // or r14b, r11b LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x245c8b44; BYTE $0x10 // mov r11d, dword [rsp + 16] - LONG $0x04e5c041 // shl r13b, 4 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xe8 // or al, r13b - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x74b60f44; WORD $0x0c24 // movzx r14d, byte [rsp + 12] + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc9 // or r9b, cl - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x244c8845; BYTE $0x01 // mov byte [r12 + 1], r9b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x01558845 // mov byte [r13 + 1], r10b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x98248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 152] + LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl - LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x02458841 // mov byte [r13 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al WORD $0xd808 // or al, bl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + LONG $0x2454b60f; BYTE $0x18 // movzx edx, byte [rsp + 24] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl - LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al - LONG $0x40c68349 // add r14, 64 - LONG $0x04c48349 // add r12, 4 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_137 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - JMP LBB5_139 + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x20c78348 // add rdi, 32 + LONG $0x04c58349 // add r13, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB5_155 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + JMP LBB5_158 -LBB5_159: - WORD $0x8b4c; BYTE $0x1e // mov r11, qword [rsi] - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_163 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] +LBB5_157: + WORD $0x894c; BYTE $0xef // mov rdi, r13 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + +LBB5_158: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB5_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JE LBB5_174 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + +LBB5_180: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0f343a46 // cmp r14b, byte [rdi + r9] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xce // mov rsi, r9 + LONG $0x03eec148 // shr rsi, 3 + WORD $0xc189 // mov ecx, eax + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x35548841; BYTE $0x00 // mov byte [r13 + rsi], dl + LONG $0x07743a44; BYTE $0x01 // cmp r14b, byte [rdi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB5_180 + JMP LBB5_183 LBB5_161: - WORD $0x3b4d; BYTE $0x1e // cmp r11, qword [r14] - LONG $0x08768d4d // lea r14, [r14 + 8] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x1cb60f41; BYTE $0x30 // movzx ebx, byte [r8 + rsi] - WORD $0xda30 // xor dl, bl - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3040; BYTE $0xdf // xor dil, bl - LONG $0x303c8841 // mov byte [r8 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_161 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB5_200 + +LBB5_162: + LONG $0x01c48349 // add r12, 1 LBB5_163: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_167 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - QUAD $0x000000a82494894c // mov qword [rsp + 168], r10 + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB5_171 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x24748844; BYTE $0x0c // mov byte [rsp + 12], r14b + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + JB LBB5_167 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB5_217 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB5_217 -LBB5_165: - LONG $0xf89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 248] - LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] - LONG $0xf09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 240] - LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] - LONG $0xe89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 232] - LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] - LONG $0xe09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 224] +LBB5_167: + WORD $0xc031 // xor eax, eax + QUAD $0x000000a824848948 // mov qword [rsp + 168], rax + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + +LBB5_168: + QUAD $0x000000a8248c2b48 // sub rcx, qword [rsp + 168] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + +LBB5_169: + LONG $0x1f773a44 // cmp r14b, byte [rdi + 31] + QUAD $0x000000882494950f // setne byte [rsp + 136] + LONG $0x1e773a44 // cmp r14b, byte [rdi + 30] LONG $0x2454950f; BYTE $0x18 // setne byte [rsp + 24] - LONG $0xd89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 216] + LONG $0x1d773a44 // cmp r14b, byte [rdi + 29] LONG $0x2454950f; BYTE $0x28 // setne byte [rsp + 40] - LONG $0xd09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 208] - LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] - LONG $0xc89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 200] + LONG $0x1c773a44 // cmp r14b, byte [rdi + 28] + LONG $0x2454950f; BYTE $0x10 // setne byte [rsp + 16] + LONG $0x1b773a44 // cmp r14b, byte [rdi + 27] + LONG $0x2454950f; BYTE $0x20 // setne byte [rsp + 32] + LONG $0x1a773a44 // cmp r14b, byte [rdi + 26] LONG $0x2454950f; BYTE $0x30 // setne byte [rsp + 48] - LONG $0xb89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 184] - LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] - LONG $0xb09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 176] + LONG $0x19773a44 // cmp r14b, byte [rdi + 25] + LONG $0x2454950f; BYTE $0x38 // setne byte [rsp + 56] + LONG $0x17773a44 // cmp r14b, byte [rdi + 23] LONG $0x2454950f; BYTE $0x48 // setne byte [rsp + 72] - LONG $0xa89e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 168] + LONG $0x16773a44 // cmp r14b, byte [rdi + 22] + LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] + LONG $0x15773a44 // cmp r14b, byte [rdi + 21] + LONG $0x2454950f; BYTE $0x40 // setne byte [rsp + 64] + LONG $0x14773a44 // cmp r14b, byte [rdi + 20] + LONG $0x2454950f; BYTE $0x50 // setne byte [rsp + 80] + LONG $0x13773a44 // cmp r14b, byte [rdi + 19] + LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] + LONG $0x12773a44 // cmp r14b, byte [rdi + 18] LONG $0x2454950f; BYTE $0x68 // setne byte [rsp + 104] - LONG $0xa09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 160] + LONG $0x11773a44 // cmp r14b, byte [rdi + 17] LONG $0x2454950f; BYTE $0x60 // setne byte [rsp + 96] - LONG $0x989e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 152] - LONG $0x2454950f; BYTE $0x58 // setne byte [rsp + 88] - LONG $0x909e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 144] + LONG $0x0f773a44 // cmp r14b, byte [rdi + 15] + LONG $0xd2950f41 // setne r10b + LONG $0x0e773a44 // cmp r14b, byte [rdi + 14] QUAD $0x000000802494950f // setne byte [rsp + 128] - LONG $0x889e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 136] + LONG $0x0d773a44 // cmp r14b, byte [rdi + 13] LONG $0x2454950f; BYTE $0x78 // setne byte [rsp + 120] - LONG $0x785e3b4d // cmp r11, qword [r14 + 120] - LONG $0xd0950f41 // setne r8b - LONG $0x705e3b4d // cmp r11, qword [r14 + 112] - QUAD $0x000000882494950f // setne byte [rsp + 136] - LONG $0x685e3b4d // cmp r11, qword [r14 + 104] - QUAD $0x000000982494950f // setne byte [rsp + 152] - LONG $0x605e3b4d // cmp r11, qword [r14 + 96] - LONG $0xd7950f40 // setne dil - LONG $0x585e3b4d // cmp r11, qword [r14 + 88] - LONG $0xd2950f41 // setne r10b - LONG $0x505e3b4d // cmp r11, qword [r14 + 80] + LONG $0x0c773a44 // cmp r14b, byte [rdi + 12] + LONG $0xd4950f41 // setne r12b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x0b // cmp al, byte [rdi + 11] + LONG $0xd7950f41 // setne r15b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x0a // cmp al, byte [rdi + 10] + LONG $0xd6950f41 // setne r14b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x09 // cmp al, byte [rdi + 9] + LONG $0xd3950f41 // setne r11b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x07 // cmp al, byte [rdi + 7] + WORD $0x950f; BYTE $0xd2 // setne dl + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x06 // cmp al, byte [rdi + 6] + QUAD $0x000000c02494950f // setne byte [rsp + 192] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x05 // cmp al, byte [rdi + 5] LONG $0xd1950f41 // setne r9b - LONG $0x485e3b4d // cmp r11, qword [r14 + 72] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x04 // cmp al, byte [rdi + 4] + LONG $0xd0950f41 // setne r8b + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x03 // cmp al, byte [rdi + 3] LONG $0xd6950f40 // setne sil - LONG $0x385e3b4d // cmp r11, qword [r14 + 56] - WORD $0x950f; BYTE $0xd0 // setne al - LONG $0x305e3b4d // cmp r11, qword [r14 + 48] - WORD $0x950f; BYTE $0xd3 // setne bl - LONG $0x285e3b4d // cmp r11, qword [r14 + 40] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x02 // cmp al, byte [rdi + 2] WORD $0x950f; BYTE $0xd1 // setne cl - LONG $0x205e3b4d // cmp r11, qword [r14 + 32] - WORD $0x950f; BYTE $0xd2 // setne dl - LONG $0x185e3b4d // cmp r11, qword [r14 + 24] - LONG $0xd7950f41 // setne r15b - LONG $0x105e3b4d // cmp r11, qword [r14 + 16] - LONG $0xd4950f41 // setne r12b - WORD $0x3b4d; BYTE $0x1e // cmp r11, qword [r14] - QUAD $0x000000c02494950f // setne byte [rsp + 192] - LONG $0x085e3b4d // cmp r11, qword [r14 + 8] - LONG $0xd5950f41 // setne r13b - LONG $0x405e3b4d // cmp r11, qword [r14 + 64] - QUAD $0x000000b02494950f // setne byte [rsp + 176] - LONG $0x809e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 128] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x073a // cmp al, byte [rdi] + QUAD $0x000000a02494950f // setne byte [rsp + 160] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] + WORD $0x473a; BYTE $0x01 // cmp al, byte [rdi + 1] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x6cb60f44; WORD $0x0c24 // movzx r13d, byte [rsp + 12] + LONG $0x086f3a44 // cmp r13b, byte [rdi + 8] + WORD $0x8949; BYTE $0xdd // mov r13, rbx QUAD $0x000000902494950f // setne byte [rsp + 144] - LONG $0xc09e3b4d; WORD $0x0000; BYTE $0x00 // cmp r11, qword [r14 + 192] - LONG $0x2454950f; BYTE $0x70 // setne byte [rsp + 112] - WORD $0x0045; BYTE $0xed // add r13b, r13b - QUAD $0x000000c024ac0244 // add r13b, byte [rsp + 192] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xec // or r12b, r13b - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x5f3a; BYTE $0x10 // cmp bl, byte [rdi + 16] + QUAD $0x000000b02494950f // setne byte [rsp + 176] + LONG $0x245cb60f; BYTE $0x0c // movzx ebx, byte [rsp + 12] + WORD $0x5f3a; BYTE $0x18 // cmp bl, byte [rdi + 24] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xc000 // add al, al + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + LONG $0x03e6c040 // shl sil, 3 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x04e0c041 // shl r8b, 4 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + LONG $0x05e1c041 // shl r9b, 5 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xc208 // or dl, al + WORD $0x0844; BYTE $0xca // or dl, r9b + LONG $0x00558841 // mov byte [r13], dl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x00000090249c0244 // add r11b, byte [rsp + 144] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xde // or r14b, r11b LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xe7 // or r15b, r12b - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xfa // or dl, r15b - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x00458841 // mov byte [r13], al - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000b024b40240 // add sil, byte [rsp + 176] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e7c040 // shl dil, 4 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - QUAD $0x000000982484b60f // movzx eax, byte [rsp + 152] + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x74b60f44; WORD $0x0c24 // movzx r14d, byte [rsp + 12] + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01458845 // mov byte [r13 + 1], r8b - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x01558845 // mov byte [r13 + 1], r10b + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] WORD $0xc189 // mov ecx, eax - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd008 // or al, dl WORD $0xc808 // or al, cl LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x70244402 // add al, byte [rsp + 112] - WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl + WORD $0xc000 // add al, al + WORD $0xd808 // or al, bl WORD $0xc189 // mov ecx, eax - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl - WORD $0xc808 // or al, cl - LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x00c68149; WORD $0x0001; BYTE $0x00 // add r14, 256 - LONG $0x04c58349 // add r13, 4 - LONG $0x246c894c; BYTE $0x08 // mov qword [rsp + 8], r13 - QUAD $0x000000a824848348; BYTE $0xff // add qword [rsp + 168], -1 - JNE LBB5_165 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - -LBB5_167: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JNE LBB5_169 - -LBB5_40: - WORD $0xff31 // xor edi, edi - JMP LBB5_41 - -LBB5_171: - LONG $0x1f578d4d // lea r10, [r15 + 31] - WORD $0x854d; BYTE $0xff // test r15, r15 - LONG $0xd7490f4d // cmovns r10, r15 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff3 // movss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB5_175 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - -LBB5_173: - LONG $0x062e0f41 // ucomiss xmm0, dword [r14] - LONG $0x04768d4d // lea r14, [r14 + 4] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xca08 // or dl, cl - WORD $0xdaf6 // neg dl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x1cb60f41; BYTE $0x30 // movzx ebx, byte [r8 + rsi] - WORD $0xda30 // xor dl, bl - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3040; BYTE $0xdf // xor dil, bl - LONG $0x303c8841 // mov byte [r8 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB5_173 - LONG $0x24448348; WORD $0x0108 // add qword [rsp + 8], 1 - -LBB5_175: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20ff8349 // cmp r15, 32 - JL LBB5_176 - LONG $0x04fa8349 // cmp r10, 4 - JB LBB5_178 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - LONG $0x24443948; BYTE $0x08 // cmp qword [rsp + 8], rax - JAE LBB5_181 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - WORD $0x394c; BYTE $0xf0 // cmp rax, r14 - JBE LBB5_181 - -LBB5_178: - WORD $0x3145; BYTE $0xc0 // xor r8d, r8d - WORD $0x894c; BYTE $0xf3 // mov rbx, r14 - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - -LBB5_184: - LONG $0x2464894c; BYTE $0x10 // mov qword [rsp + 16], r12 - QUAD $0x000000a024bc894c // mov qword [rsp + 160], r15 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - WORD $0x294d; BYTE $0xc2 // sub r10, r8 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - -LBB5_185: - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xcd // mov r13d, ecx - LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - LONG $0x08432e0f // ucomiss xmm0, dword [rbx + 8] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x18244c88 // mov byte [rsp + 24], cl - LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x20244c88 // mov byte [rsp + 32], cl - LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x40244c88 // mov byte [rsp + 64], cl - LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x38244c88 // mov byte [rsp + 56], cl - LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x30244c88 // mov byte [rsp + 48], cl - LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x08244c88 // mov byte [rsp + 8], cl - LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x28244c88 // mov byte [rsp + 40], cl - LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x50244c88 // mov byte [rsp + 80], cl - LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x48244c88 // mov byte [rsp + 72], cl - LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x68244c88 // mov byte [rsp + 104], cl - LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x60244c88 // mov byte [rsp + 96], cl - LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x80248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 128], cl - LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x70244c88 // mov byte [rsp + 112], cl - LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x78244c88 // mov byte [rsp + 120], cl - LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x58244c88 // mov byte [rsp + 88], cl - LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd4950f41 // setne r12b - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x48432e0f // ucomiss xmm0, dword [rbx + 72] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x88248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 136], cl - LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x98248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 152], cl - LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0x90248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 144], cl - LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xc0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 192], cl - LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f41 // setne r14b - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x5c432e0f // ucomiss xmm0, dword [rbx + 92] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd0950f41 // setne r8b - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x60432e0f // ucomiss xmm0, dword [rbx + 96] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xb0248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 176], cl - LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd3950f41 // setne r11b - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x68432e0f // ucomiss xmm0, dword [rbx + 104] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd2950f41 // setne r10b - WORD $0x0841; BYTE $0xc2 // or r10b, al - LONG $0x6c432e0f // ucomiss xmm0, dword [rbx + 108] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd1950f41 // setne r9b - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x70432e0f // ucomiss xmm0, dword [rbx + 112] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f41 // setne r15b - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd1 // setne cl - WORD $0xc108 // or cl, al - LONG $0xa8248c88; WORD $0x0000; BYTE $0x00 // mov byte [rsp + 168], cl - LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd7950f40 // setne dil - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x7c432e0f // ucomiss xmm0, dword [rbx + 124] - WORD $0x9a0f; BYTE $0xd0 // setp al - LONG $0xd6950f40 // setne sil - WORD $0x0840; BYTE $0xc6 // or sil, al - WORD $0xd200 // add dl, dl - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd5 // mov r13d, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] - WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd008 // or al, dl - LONG $0x08244488 // mov byte [rsp + 8], al - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc5 // mov r13d, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xca08 // or dl, cl - QUAD $0x00008024acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 128] - LONG $0x05e5c041 // shl r13b, 5 - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x6cb60f44; WORD $0x7824 // movzx r13d, byte [rsp + 120] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xcd // or r13b, cl - WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x58 // add r12b, byte [rsp + 88] - WORD $0x8944; BYTE $0xe1 // mov ecx, r12d - QUAD $0x00008824a4b60f44; BYTE $0x00 // movzx r12d, byte [rsp + 136] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0841; BYTE $0xcc // or r12b, cl - QUAD $0x00000098248cb60f // movzx ecx, byte [rsp + 152] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - WORD $0x8941; BYTE $0xcc // mov r12d, ecx - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe1 // or cl, r12b - LONG $0x64b60f44; WORD $0x0824 // movzx r12d, byte [rsp + 8] - WORD $0x0841; BYTE $0xc4 // or r12b, al - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - LONG $0x06e6c041 // shl r14b, 6 - WORD $0x0841; BYTE $0xc6 // or r14b, al - WORD $0x0841; BYTE $0xd5 // or r13b, dl - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0845; BYTE $0xf0 // or r8b, r14b - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000b0249c0244 // add r11b, byte [rsp + 176] - LONG $0x02e2c041 // shl r10b, 2 - WORD $0x0845; BYTE $0xda // or r10b, r11b - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xd1 // or r9b, r10b - LONG $0x04e7c041 // shl r15b, 4 - WORD $0x0845; BYTE $0xcf // or r15b, r9b - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - WORD $0x8844; BYTE $0x20 // mov byte [rax], r12b - QUAD $0x000000a8248cb60f // movzx ecx, byte [rsp + 168] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - LONG $0x06e7c040 // shl dil, 6 - WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x01688844 // mov byte [rax + 1], r13b - LONG $0x07e6c040 // shl sil, 7 - WORD $0x0840; BYTE $0xfe // or sil, dil - WORD $0x0844; BYTE $0xfe // or sil, r15b - LONG $0x02408844 // mov byte [rax + 2], r8b - LONG $0x03708840 // mov byte [rax + 3], sil - LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 - LONG $0x04c08348 // add rax, 4 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB5_185 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - JMP LBB5_187 - -LBB5_9: - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - -LBB5_92: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JNE LBB5_95 - WORD $0xf631 // xor esi, esi - JMP LBB5_98 - -LBB5_62: - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - -LBB5_73: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JNE LBB5_76 - WORD $0xf631 // xor esi, esi - JMP LBB5_79 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2454b60f; BYTE $0x18 // movzx edx, byte [rsp + 24] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd008 // or al, dl + WORD $0xc808 // or al, cl + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x20c78348 // add rdi, 32 + LONG $0x04c58349 // add r13, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB5_169 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + JMP LBB5_172 -LBB5_105: - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] +LBB5_171: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB5_116: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 +LBB5_172: + LONG $0x05e1c148 // shl rcx, 5 WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JE LBB5_118 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xf631 // xor esi, esi - -LBB5_122: - LONG $0x1e3b4566 // cmp r11w, word [r14] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3c // movzx r10d, byte [r12 + rdi] - WORD $0xf189 // mov ecx, esi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x02c68348 // add rsi, 2 - LONG $0x5e3b4566; BYTE $0x02 // cmp r11w, word [r14 + 2] - LONG $0x04768d4d // lea r14, [r14 + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - WORD $0xda30 // xor dl, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0xd830 // xor al, bl - LONG $0x3c048841 // mov byte [r12 + rdi], al - WORD $0x3949; BYTE $0xf1 // cmp r9, rsi - JNE LBB5_122 - JMP LBB5_119 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB5_200 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB5_181 -LBB5_128: - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - -LBB5_139: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JNE LBB5_141 +LBB5_174: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB5_184 -LBB5_118: - WORD $0xf631 // xor esi, esi - JMP LBB5_119 +LBB5_175: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 + WORD $0xff31 // xor edi, edi LBB5_176: - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - WORD $0x894c; BYTE $0xf3 // mov rbx, r14 - -LBB5_187: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xfa // cmp r10, r15 - JGE LBB5_198 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xfa // add r10, r15 - JNE LBB5_192 - WORD $0xf631 // xor esi, esi - JMP LBB5_190 - -LBB5_155: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xff31 // xor edi, edi - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] - -LBB5_156: - WORD $0x3b45; BYTE $0x1e // cmp r11d, dword [r14] + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0x3044; BYTE $0xd0 // xor al, r10b - WORD $0xc220 // and dl, al - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - LONG $0x37148841 // mov byte [r15 + rsi], dl - LONG $0x02c78348 // add rdi, 2 - LONG $0x045e3b45 // cmp r11d, dword [r14 + 4] - LONG $0x08768d4d // lea r14, [r14 + 8] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0xd030 // xor al, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0xd330 // xor bl, dl - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB5_156 - -LBB5_24: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_198 - WORD $0x3b45; BYTE $0x1e // cmp r11d, dword [r14] - JMP LBB5_26 - -LBB5_95: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - -LBB5_96: - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x2474b60f; BYTE $0x10 // movzx esi, byte [rsp + 16] - LONG $0x06343a41 // cmp sil, byte [r14 + rax] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x06743a41; BYTE $0x01 // cmp sil, byte [r14 + rax + 1] - LONG $0x02708d48 // lea rsi, [rax + 2] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB5_96 - WORD $0x0149; BYTE $0xf6 // add r14, rsi - -LBB5_98: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_198 - LONG $0x1024448a // mov al, byte [rsp + 16] - WORD $0x3a41; BYTE $0x06 // cmp al, byte [r14] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - JMP LBB5_81 - -LBB5_76: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - -LBB5_77: - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] - LONG $0x06343a41 // cmp sil, byte [r14 + rax] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - LONG $0x03efc148 // shr rdi, 3 - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xda20 // and dl, bl - WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x06743a41; BYTE $0x01 // cmp sil, byte [r14 + rax + 1] - LONG $0x02708d48 // lea rsi, [rax + 2] - WORD $0x950f; BYTE $0xd3 // setne bl - WORD $0xdbf6 // neg bl - WORD $0xd330 // xor bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x341c8841 // mov byte [r12 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0x08528d48 // lea rdx, [rdx + 8] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0xd820 // and al, bl - WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB5_77 - WORD $0x0149; BYTE $0xf6 // add r14, rsi - -LBB5_79: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_198 - LONG $0x4024448a // mov al, byte [rsp + 64] - WORD $0x3a41; BYTE $0x06 // cmp al, byte [r14] - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_176 -LBB5_81: - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB5_198 +LBB5_177: + LONG $0x01c1f641 // test r9b, 1 + JE LBB5_200 + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + JMP LBB5_194 -LBB5_194: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xff31 // xor edi, edi - LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] +LBB5_181: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d -LBB5_195: - LONG $0x2e0f4166; BYTE $0x06 // ucomisd xmm0, qword [r14] - WORD $0x9a0f; BYTE $0xd1 // setp cl - WORD $0x950f; BYTE $0xd0 // setne al - WORD $0xc808 // or al, cl - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi +LBB5_182: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0f343a46 // cmp r14b, byte [rdi + r9] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xce // mov rsi, r9 LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f41; BYTE $0x33 // movzx edx, byte [r11 + rsi] - WORD $0xf989 // mov ecx, edi + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0xd030 // xor al, dl - WORD $0xc320 // and bl, al + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x35548841; BYTE $0x00 // mov byte [r13 + rsi], dl + LONG $0x07743a44; BYTE $0x01 // cmp r14b, byte [rdi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x950f; BYTE $0xd3 // setne bl + WORD $0xdbf6 // neg bl WORD $0xd330 // xor bl, dl - LONG $0x331c8841 // mov byte [r11 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x2e0f4166; WORD $0x0846 // ucomisd xmm0, qword [r14 + 8] - LONG $0x10768d4d // lea r14, [r14 + 16] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - WORD $0xdaf6 // neg dl - WORD $0xda30 // xor dl, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0xd830 // xor al, bl - LONG $0x33048841 // mov byte [r11 + rsi], al - WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB5_195 + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB5_182 -LBB5_196: +LBB5_183: + WORD $0x014c; BYTE $0xcf // add rdi, r9 + +LBB5_184: LONG $0x01c0f641 // test r8b, 1 - JE LBB5_198 - LONG $0x2e0f4166; BYTE $0x06 // ucomisd xmm0, qword [r14] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x03e8c148 // shr rax, 3 - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - LONG $0x00348a41 // mov sil, byte [r8 + rax] - LONG $0x07e78040 // and dil, 7 + JE LBB5_200 + WORD $0x3a44; BYTE $0x37 // cmp r14b, byte [rdi] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf989 // mov ecx, edi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf2 // xor dl, sil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x001c8841 // mov byte [r8 + rax], bl - JMP LBB5_198 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + JMP LBB5_199 -LBB5_169: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xff31 // xor edi, edi - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] +LBB5_186: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xff31 // xor edi, edi -LBB5_170: - WORD $0x3b4d; BYTE $0x1e // cmp r11, qword [r14] +LBB5_187: + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xc808 // or al, cl WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl + WORD $0xb341; BYTE $0x01 // mov r11b, 1 + WORD $0xd241; BYTE $0xe3 // shl r11b, cl WORD $0x3044; BYTE $0xd0 // xor al, r10b - WORD $0xc220 // and dl, al - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - LONG $0x37148841 // mov byte [r15 + rsi], dl + WORD $0x2041; BYTE $0xc3 // and r11b, al + WORD $0x3045; BYTE $0xd3 // xor r11b, r10b + LONG $0x341c8845 // mov byte [r12 + rsi], r11b LONG $0x02c78348 // add rdi, 2 - LONG $0x085e3b4d // cmp r11, qword [r14 + 8] - LONG $0x10768d4d // lea r14, [r14 + 16] + LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd29a0f41 // setp r10b WORD $0x950f; BYTE $0xd0 // setne al + WORD $0x0844; BYTE $0xd0 // or al, r10b WORD $0xd8f6 // neg al - WORD $0xd030 // xor al, dl + WORD $0x3044; BYTE $0xd8 // xor al, r11b WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al - WORD $0xd330 // xor bl, dl - LONG $0x371c8841 // mov byte [r15 + rsi], bl + WORD $0x3044; BYTE $0xdb // xor bl, r11b + LONG $0x341c8841 // mov byte [r12 + rsi], bl WORD $0x3949; BYTE $0xf9 // cmp r9, rdi - JNE LBB5_170 + JNE LBB5_187 -LBB5_41: +LBB5_188: LONG $0x01c0f641 // test r8b, 1 - JE LBB5_198 - WORD $0x3b4d; BYTE $0x1e // cmp r11, qword [r14] + JE LBB5_200 + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + LONG $0x03e8c148 // shr rax, 3 + LONG $0x04348a41 // mov sil, byte [r12 + rax] + LONG $0x07e78040 // and dil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf989 // mov ecx, edi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf2 // xor dl, sil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xf3 // xor bl, sil + LONG $0x041c8841 // mov byte [r12 + rax], bl + JMP LBB5_200 -LBB5_26: +LBB5_190: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 + WORD $0xff31 // xor edi, edi + +LBB5_191: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - LONG $0x10348a41 // mov sil, byte [r8 + rdx] - LONG $0x07e78040 // and dil, 7 - WORD $0x01b3 // mov bl, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB5_198 - -LBB5_141: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xf631 // xor esi, esi - -LBB5_142: - LONG $0x1e3b4566 // cmp r11w, word [r14] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3c // movzx r10d, byte [r12 + rdi] - WORD $0xf189 // mov ecx, esi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd0 // xor al, r10b + WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x02c68348 // add rsi, 2 - LONG $0x5e3b4566; BYTE $0x02 // cmp r11w, word [r14 + 2] - LONG $0x04768d4d // lea r14, [r14 + 4] - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xdaf6 // neg dl - WORD $0xda30 // xor dl, bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl - LONG $0x3c048841 // mov byte [r12 + rdi], al - WORD $0x3949; BYTE $0xf1 // cmp r9, rsi - JNE LBB5_142 + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB5_191 -LBB5_119: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_198 - LONG $0x1e3b4566 // cmp r11w, word [r14] +LBB5_192: + LONG $0x01c1f641 // test r9b, 1 + JE LBB5_200 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + +LBB5_194: WORD $0x950f; BYTE $0xd0 // setne al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x8948; BYTE $0xfa // mov rdx, rdi LONG $0x03eac148 // shr rdx, 3 - LONG $0x143c8a41 // mov dil, byte [r12 + rdx] - LONG $0x07e68040 // and sil, 7 + LONG $0x14348a41 // mov sil, byte [r12 + rdx] + LONG $0x07e78040 // and dil, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi + WORD $0xf989 // mov ecx, edi WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil + WORD $0x3040; BYTE $0xf3 // xor bl, sil LONG $0x141c8841 // mov byte [r12 + rdx], bl - JMP LBB5_198 + JMP LBB5_200 -LBB5_192: +LBB5_195: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xf631 // xor esi, esi + +LBB5_196: + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + LONG $0x323b4466 // cmp r14w, word [rdx] + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x03efc148 // shr rdi, 3 + LONG $0x54b60f45; WORD $0x003d // movzx r10d, byte [r13 + rdi] + WORD $0xf189 // mov ecx, esi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl + LONG $0x02c68348 // add rsi, 2 + LONG $0x703b4466; BYTE $0x02 // cmp r14w, word [rax + 2] + LONG $0x04508d48 // lea rdx, [rax + 4] + LONG $0xd2950f41 // setne r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB5_196 + +LBB5_197: + LONG $0x01c0f641 // test r8b, 1 + JE LBB5_200 + LONG $0x323b4466 // cmp r14w, word [rdx] + WORD $0x950f; BYTE $0xd0 // setne al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + LONG $0x03eac148 // shr rdx, 3 + LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi + +LBB5_199: + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x155c8841; BYTE $0x00 // mov byte [r13 + rdx], bl + +LBB5_200: + MOVQ 272(SP), SP + RET + +LBB5_201: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0xf631 // xor esi, esi - WORD $0x894d; BYTE $0xe6 // mov r14, r12 + WORD $0x894d; BYTE $0xee // mov r14, r13 -LBB5_193: +LBB5_202: WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] WORD $0x9a0f; BYTE $0xd1 // setp cl WORD $0x950f; BYTE $0xd2 // setne dl @@ -28025,1134 +28923,1699 @@ LBB5_193: WORD $0x3044; BYTE $0xd8 // xor al, r11b LONG $0x3e048841 // mov byte [r14 + rdi], al WORD $0x3949; BYTE $0xf1 // cmp r9, rsi - JNE LBB5_193 + JNE LBB5_202 -LBB5_190: - LONG $0x01c0f641 // test r8b, 1 - JE LBB5_198 - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x9a0f; BYTE $0xd0 // setp al - WORD $0x950f; BYTE $0xd2 // setne dl - WORD $0xc208 // or dl, al - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x03e8c148 // shr rax, 3 - LONG $0x043c8a41 // mov dil, byte [r12 + rax] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xfa // xor dl, dil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x041c8841 // mov byte [r12 + rax], bl +LBB5_203: + LONG $0x01c0f641 // test r8b, 1 + JE LBB5_200 + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x9a0f; BYTE $0xd0 // setp al + WORD $0x950f; BYTE $0xd2 // setne dl + WORD $0xc208 // or dl, al + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x03e8c148 // shr rax, 3 + LONG $0x057c8a41; BYTE $0x00 // mov dil, byte [r13 + rax] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xfa // xor dl, dil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x055c8841; BYTE $0x00 // mov byte [r13 + rax], bl + JMP LBB5_200 -LBB5_198: - MOVQ 288(SP), SP - RET +LBB5_205: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 + LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0xef0f4566; BYTE $0xff // pxor xmm15, xmm15 + +LBB5_206: + LONG $0x2474894c; BYTE $0x28 // mov qword [rsp + 40], r14 + LONG $0x06e6c149 // shl r14, 6 + WORD $0x894d; BYTE $0xf1 // mov r9, r14 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + LONG $0x04b70f42; BYTE $0x32 // movzx eax, word [rdx + r14] + LONG $0xe86e0f66 // movd xmm5, eax + LONG $0x44b70f42; WORD $0x0232 // movzx eax, word [rdx + r14 + 2] + LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x44b70f42; WORD $0x0432 // movzx eax, word [rdx + r14 + 4] + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x44b70f42; WORD $0x0632 // movzx eax, word [rdx + r14 + 6] + LONG $0xf86e0f66 // movd xmm7, eax + LONG $0x44b70f42; WORD $0x0832 // movzx eax, word [rdx + r14 + 8] + LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax + LONG $0x44b70f42; WORD $0x0a32 // movzx eax, word [rdx + r14 + 10] + LONG $0xe06e0f66 // movd xmm4, eax + LONG $0x44b70f42; WORD $0x0c32 // movzx eax, word [rdx + r14 + 12] + LONG $0x54b70f46; WORD $0x0e32 // movzx r10d, word [rdx + r14 + 14] + LONG $0x5cb70f42; WORD $0x1032 // movzx ebx, word [rdx + r14 + 16] + LONG $0x7cb70f42; WORD $0x1232 // movzx edi, word [rdx + r14 + 18] + LONG $0x4cb70f42; WORD $0x1432 // movzx ecx, word [rdx + r14 + 20] + LONG $0x18244c89 // mov dword [rsp + 24], ecx + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + LONG $0x40c98348 // or rcx, 64 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + LONG $0xc0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 192 + LONG $0x00cc8149; WORD $0x0001; BYTE $0x00 // or r12, 256 + LONG $0x40cd8149; WORD $0x0001; BYTE $0x00 // or r13, 320 + LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 + LONG $0x2cc40f66; WORD $0x010a // pinsrw xmm5, word [rdx + rcx], 1 + LONG $0xc40f4266; WORD $0x0a2c; BYTE $0x02 // pinsrw xmm5, word [rdx + r9], 2 + LONG $0xc40f4266; WORD $0x3a2c; BYTE $0x03 // pinsrw xmm5, word [rdx + r15], 3 + LONG $0xc40f4266; WORD $0x222c; BYTE $0x04 // pinsrw xmm5, word [rdx + r12], 4 + LONG $0xc40f4266; WORD $0x2a2c; BYTE $0x05 // pinsrw xmm5, word [rdx + r13], 5 + LONG $0x2cc40f66; WORD $0x0632 // pinsrw xmm5, word [rdx + rsi], 6 + LONG $0x44c40f66; WORD $0x020a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 2], 1 + QUAD $0x02020a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 2], 2 + QUAD $0x03023a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 2], 3 + QUAD $0x04022244c40f4266 // pinsrw xmm0, word [rdx + r12 + 2], 4 + QUAD $0x05022a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 2], 5 + LONG $0x44c40f66; WORD $0x0232; BYTE $0x06 // pinsrw xmm0, word [rdx + rsi + 2], 6 + LONG $0xc0c88149; WORD $0x0001; BYTE $0x00 // or r8, 448 + QUAD $0x07020244c40f4266 // pinsrw xmm0, word [rdx + r8 + 2], 7 + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x44b70f42; WORD $0x1632 // movzx eax, word [rdx + r14 + 22] + LONG $0x10244489 // mov dword [rsp + 16], eax + LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 + LONG $0x4cc40f66; WORD $0x040a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 4], 1 + QUAD $0x02040a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 4], 2 + QUAD $0x03043a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 4], 3 + QUAD $0x0404224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 4], 4 + QUAD $0x05042a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 4], 5 + LONG $0x4cc40f66; WORD $0x0432; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 4], 6 + QUAD $0x0704024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 4], 7 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + QUAD $0x0000808d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 128[rbp] /* [rip + .LCPI5_8] */ + LONG $0x6f0f4166; BYTE $0xd9 // movdqa xmm3, xmm9 + LONG $0x380f4166; WORD $0xdf10 // pblendvb xmm3, xmm15, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + QUAD $0x00000090856f0f66 // movdqa xmm0, oword 144[rbp] /* [rip + .LCPI5_9] */ + LONG $0xf06f0f66 // movdqa xmm6, xmm0 + LONG $0x6f0f4466; BYTE $0xf0 // movdqa xmm14, xmm0 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xca // movd xmm1, r10d + LONG $0x5cb70f46; WORD $0x1832 // movzx r11d, word [rdx + r14 + 24] + LONG $0xc40f4266; WORD $0x022c; BYTE $0x07 // pinsrw xmm5, word [rdx + r8], 7 + LONG $0x750f4166; BYTE $0xeb // pcmpeqw xmm5, xmm11 + LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 + LONG $0xe8ef0f66 // pxor xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0x7cc40f66; WORD $0x060a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 6], 1 + QUAD $0x02060a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 6], 2 + QUAD $0x03063a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 6], 3 + QUAD $0x0406227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 6], 4 + QUAD $0x05062a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 6], 5 + LONG $0x7cc40f66; WORD $0x0632; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 6], 6 + QUAD $0x0706027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 6], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x01080a44c40f4466 // pinsrw xmm8, word [rdx + rcx + 8], 1 + QUAD $0x02080a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 8], 2 + QUAD $0x03083a44c40f4666 // pinsrw xmm8, word [rdx + r15 + 8], 3 + QUAD $0x04082244c40f4666 // pinsrw xmm8, word [rdx + r12 + 8], 4 + QUAD $0x05082a44c40f4666 // pinsrw xmm8, word [rdx + r13 + 8], 5 + QUAD $0x06083244c40f4466 // pinsrw xmm8, word [rdx + rsi + 8], 6 + QUAD $0x07080244c40f4666 // pinsrw xmm8, word [rdx + r8 + 8], 7 + LONG $0xddf80f66 // psubb xmm3, xmm5 + QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI5_10] */ + LONG $0xc76f0f66 // movdqa xmm0, xmm7 + LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 + LONG $0xfb6e0f66 // movd xmm7, ebx + LONG $0x44b70f42; WORD $0x1a32 // movzx eax, word [rdx + r14 + 26] + LONG $0x750f4566; BYTE $0xc3 // pcmpeqw xmm8, xmm11 + LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 + LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 + QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI5_11] */ + LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0xf76e0f66 // movd xmm6, edi + LONG $0x54b70f46; WORD $0x1c32 // movzx r10d, word [rdx + r14 + 28] + LONG $0x64c40f66; WORD $0x0a0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 10], 1 + QUAD $0x020a0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 10], 2 + QUAD $0x030a3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 10], 3 + QUAD $0x040a2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 10], 4 + QUAD $0x050a2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 10], 5 + LONG $0x64c40f66; WORD $0x0a32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 10], 6 + QUAD $0x070a0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 10], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0x54c40f66; WORD $0x0c0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 12], 1 + QUAD $0x020c0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 12], 2 + QUAD $0x030c3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 12], 3 + QUAD $0x040c2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 12], 4 + QUAD $0x050c2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 12], 5 + LONG $0x54c40f66; WORD $0x0c32; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 12], 6 + LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI5_12] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x646e0f66; WORD $0x1824 // movd xmm4, dword [rsp + 24] + LONG $0x5cb70f42; WORD $0x1e32 // movzx ebx, word [rdx + r14 + 30] + QUAD $0x070c0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 12], 7 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 + QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI5_13] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0x5c6e0f66; WORD $0x1024 // movd xmm3, dword [rsp + 16] + LONG $0x7cb70f42; WORD $0x2032 // movzx edi, word [rdx + r14 + 32] + LONG $0x10247c89 // mov dword [rsp + 16], edi + LONG $0x4cc40f66; WORD $0x0e0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 14], 1 + QUAD $0x020e0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 14], 2 + QUAD $0x030e3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 14], 3 + QUAD $0x040e224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 14], 4 + QUAD $0x050e2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 14], 5 + LONG $0x4cc40f66; WORD $0x0e32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 14], 6 + LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x7cb70f42; WORD $0x2232 // movzx edi, word [rdx + r14 + 34] + LONG $0x18247c89 // mov dword [rsp + 24], edi + QUAD $0x070e024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 14], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0x74c40f66; WORD $0x120a; BYTE $0x01 // pinsrw xmm6, word [rdx + rcx + 18], 1 + QUAD $0x02120a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 18], 2 + QUAD $0x03123a74c40f4266 // pinsrw xmm6, word [rdx + r15 + 18], 3 + QUAD $0x04122274c40f4266 // pinsrw xmm6, word [rdx + r12 + 18], 4 + QUAD $0x05122a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 18], 5 + LONG $0x74c40f66; WORD $0x1232; BYTE $0x06 // pinsrw xmm6, word [rdx + rsi + 18], 6 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + QUAD $0x07120274c40f4266 // pinsrw xmm6, word [rdx + r8 + 18], 7 + LONG $0x750f4166; BYTE $0xf3 // pcmpeqw xmm6, xmm11 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 + QUAD $0x0000e0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 224[rbp] /* [rip + .LCPI5_14] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 + LONG $0x6f0f4566; BYTE $0xc1 // movdqa xmm8, xmm9 + LONG $0xc66f0f66 // movdqa xmm0, xmm6 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x5cb70f46; WORD $0x2432 // movzx r11d, word [rdx + r14 + 36] + LONG $0x7cc40f66; WORD $0x100a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 16], 1 + QUAD $0x02100a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 16], 2 + QUAD $0x03103a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 16], 3 + QUAD $0x0410227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 16], 4 + QUAD $0x05102a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 16], 5 + LONG $0x7cc40f66; WORD $0x1032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 16], 6 + LONG $0x64c40f66; WORD $0x140a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 20], 1 + QUAD $0x02140a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 20], 2 + QUAD $0x03143a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 20], 3 + QUAD $0x04142264c40f4266 // pinsrw xmm4, word [rdx + r12 + 20], 4 + QUAD $0x05142a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 20], 5 + LONG $0x64c40f66; WORD $0x1432; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 20], 6 + QUAD $0x07140264c40f4266 // pinsrw xmm4, word [rdx + r8 + 20], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x6f0f4166; BYTE $0xee // movdqa xmm5, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xe2 // movd xmm4, r10d + LONG $0x7cb70f42; WORD $0x2632 // movzx edi, word [rdx + r14 + 38] + QUAD $0x0710027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 16], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x5cc40f66; WORD $0x160a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 22], 1 + QUAD $0x02160a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 22], 2 + QUAD $0x03163a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 22], 3 + QUAD $0x0416225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 22], 4 + QUAD $0x05162a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 22], 5 + LONG $0x5cc40f66; WORD $0x1632; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 22], 6 + QUAD $0x0716025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 22], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0x54c40f66; WORD $0x180a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 24], 1 + QUAD $0x02180a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 24], 2 + QUAD $0x03183a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 24], 3 + QUAD $0x04182254c40f4266 // pinsrw xmm2, word [rdx + r12 + 24], 4 + QUAD $0x05182a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 24], 5 + LONG $0x54c40f66; WORD $0x1832; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 24], 6 + QUAD $0x07180254c40f4266 // pinsrw xmm2, word [rdx + r8 + 24], 7 + LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 + QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI5_10] */ + LONG $0x6f0f4566; BYTE $0xf2 // movdqa xmm14, xmm10 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 + LONG $0xdb6e0f66 // movd xmm3, ebx + LONG $0x44b70f42; WORD $0x2832 // movzx eax, word [rdx + r14 + 40] + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4466; BYTE $0xf5 // por xmm14, xmm5 + QUAD $0x0000b08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 176[rbp] /* [rip + .LCPI5_11] */ + LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0x7c6e0f66; WORD $0x1024 // movd xmm7, dword [rsp + 16] + LONG $0x54b70f46; WORD $0x2a32 // movzx r10d, word [rdx + r14 + 42] + LONG $0x4cc40f66; WORD $0x1a0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 26], 1 + QUAD $0x021a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 26], 2 + QUAD $0x031a3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 26], 3 + QUAD $0x041a224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 26], 4 + QUAD $0x051a2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 26], 5 + LONG $0x4cc40f66; WORD $0x1a32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 26], 6 + QUAD $0x071a024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 26], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x64c40f66; WORD $0x1c0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 28], 1 + QUAD $0x021c0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 28], 2 + QUAD $0x031c3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 28], 3 + QUAD $0x041c2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 28], 4 + QUAD $0x051c2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 28], 5 + LONG $0x64c40f66; WORD $0x1c32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 28], 6 + LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI5_12] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x546e0f66; WORD $0x1824 // movd xmm2, dword [rsp + 24] + LONG $0x5cb70f42; WORD $0x2c32 // movzx ebx, word [rdx + r14 + 44] + LONG $0x10245c89 // mov dword [rsp + 16], ebx + QUAD $0x071c0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 28], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 + QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI5_13] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x5cb70f42; WORD $0x2e32 // movzx ebx, word [rdx + r14 + 46] + LONG $0x18245c89 // mov dword [rsp + 24], ebx + LONG $0x5cc40f66; WORD $0x1e0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 30], 1 + QUAD $0x021e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 30], 2 + QUAD $0x031e3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 30], 3 + QUAD $0x041e225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 30], 4 + QUAD $0x051e2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 30], 5 + LONG $0x5cc40f66; WORD $0x1e32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 30], 6 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0xcf6e0f66 // movd xmm1, edi + LONG $0x7cb70f42; WORD $0x3032 // movzx edi, word [rdx + r14 + 48] + QUAD $0x071e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 30], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0x54c40f66; WORD $0x220a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 34], 1 + QUAD $0x02220a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 34], 2 + QUAD $0x03223a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 34], 3 + QUAD $0x04222254c40f4266 // pinsrw xmm2, word [rdx + r12 + 34], 4 + QUAD $0x05222a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 34], 5 + LONG $0x54c40f66; WORD $0x2232; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 34], 6 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + QUAD $0x07220254c40f4266 // pinsrw xmm2, word [rdx + r8 + 34], 7 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 + QUAD $0x0000e0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 224[rbp] /* [rip + .LCPI5_14] */ + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + QUAD $0x000080856f0f4466; BYTE $0x00 // movdqa xmm8, oword 128[rbp] /* [rip + .LCPI5_8] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x5cb70f46; WORD $0x3232 // movzx r11d, word [rdx + r14 + 50] + LONG $0x7cc40f66; WORD $0x200a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 32], 1 + QUAD $0x02200a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 32], 2 + QUAD $0x03203a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 32], 3 + QUAD $0x0420227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 32], 4 + QUAD $0x05202a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 32], 5 + LONG $0x7cc40f66; WORD $0x2032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 32], 6 + LONG $0x64c40f66; WORD $0x240a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 36], 1 + QUAD $0x02240a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 36], 2 + QUAD $0x03243a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 36], 3 + QUAD $0x04242264c40f4266 // pinsrw xmm4, word [rdx + r12 + 36], 4 + QUAD $0x05242a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 36], 5 + LONG $0x64c40f66; WORD $0x2432; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 36], 6 + QUAD $0x07240264c40f4266 // pinsrw xmm4, word [rdx + r8 + 36], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 + QUAD $0x00000090b56f0f66 // movdqa xmm6, oword 144[rbp] /* [rip + .LCPI5_9] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x54b70f46; WORD $0x3432 // movzx r10d, word [rdx + r14 + 52] + QUAD $0x0720027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 32], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x4cc40f66; WORD $0x260a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 38], 1 + QUAD $0x02260a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 38], 2 + QUAD $0x03263a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 38], 3 + QUAD $0x0426224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 38], 4 + QUAD $0x05262a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 38], 5 + LONG $0x4cc40f66; WORD $0x2632; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 38], 6 + QUAD $0x0726024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 38], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x54c40f66; WORD $0x280a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 40], 1 + QUAD $0x02280a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 40], 2 + QUAD $0x03283a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 40], 3 + QUAD $0x04282254c40f4266 // pinsrw xmm2, word [rdx + r12 + 40], 4 + QUAD $0x05282a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 40], 5 + LONG $0x54c40f66; WORD $0x2832; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 40], 6 + QUAD $0x07280254c40f4266 // pinsrw xmm2, word [rdx + r8 + 40], 7 + LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 + LONG $0x6f0f4166; BYTE $0xea // movdqa xmm5, xmm10 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x4c6e0f66; WORD $0x1024 // movd xmm1, dword [rsp + 16] + LONG $0x44b70f42; WORD $0x3632 // movzx eax, word [rdx + r14 + 54] + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x6f0f4166; BYTE $0xf1 // movdqa xmm6, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x646e0f66; WORD $0x1824 // movd xmm4, dword [rsp + 24] + LONG $0x5cb70f42; WORD $0x3832 // movzx ebx, word [rdx + r14 + 56] + LONG $0x5cc40f66; WORD $0x2a0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 42], 1 + QUAD $0x022a0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 42], 2 + QUAD $0x032a3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 42], 3 + QUAD $0x042a225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 42], 4 + QUAD $0x052a2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 42], 5 + LONG $0x5cc40f66; WORD $0x2a32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 42], 6 + QUAD $0x072a025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 42], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0x4cc40f66; WORD $0x2c0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 44], 1 + QUAD $0x022c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 44], 2 + QUAD $0x032c3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 44], 3 + QUAD $0x042c224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 44], 4 + QUAD $0x052c2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 44], 5 + LONG $0x4cc40f66; WORD $0x2c32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 44], 6 + LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 + QUAD $0x0000c08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 192[rbp] /* [rip + .LCPI5_12] */ + LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4166; WORD $0xd710 // pblendvb xmm2, xmm15, xmm0 + LONG $0xff6e0f66 // movd xmm7, edi + LONG $0x7cb70f42; WORD $0x3a32 // movzx edi, word [rdx + r14 + 58] + QUAD $0x072c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 44], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0x0000d0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 208[rbp] /* [rip + .LCPI5_13] */ + LONG $0x6f0f4166; BYTE $0xf2 // movdqa xmm6, xmm10 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + LONG $0x5cb70f46; WORD $0x3c32 // movzx r11d, word [rdx + r14 + 60] + LONG $0xf2eb0f66 // por xmm6, xmm2 + LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d + LONG $0x64c40f66; WORD $0x2e0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 46], 1 + QUAD $0x022e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 46], 2 + QUAD $0x032e3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 46], 3 + QUAD $0x042e2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 46], 4 + QUAD $0x052e2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 46], 5 + LONG $0x64c40f66; WORD $0x2e32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 46], 6 + QUAD $0x072e0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 46], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0x6f0f4566; BYTE $0xc6 // movdqa xmm8, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xd86e0f66 // movd xmm3, eax + LONG $0x4cc40f66; WORD $0x320a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 50], 1 + QUAD $0x02320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 2 + QUAD $0x03323a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 50], 3 + QUAD $0x0432224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 50], 4 + QUAD $0x05322a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 50], 5 + LONG $0x4cc40f66; WORD $0x3232; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 50], 6 + QUAD $0x0732024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 50], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 + QUAD $0x00000080a56f0f66 // movdqa xmm4, oword 128[rbp] /* [rip + .LCPI5_8] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 + LONG $0xcb6e0f66 // movd xmm1, ebx + LONG $0x7cc40f66; WORD $0x300a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 48], 1 + QUAD $0x02300a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 48], 2 + QUAD $0x03303a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 48], 3 + QUAD $0x0430227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 48], 4 + QUAD $0x05302a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 48], 5 + LONG $0x7cc40f66; WORD $0x3032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 48], 6 + QUAD $0x0730027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 48], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0x54c40f66; WORD $0x340a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 52], 1 + QUAD $0x02340a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 52], 2 + QUAD $0x03343a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 52], 3 + QUAD $0x04342254c40f4266 // pinsrw xmm2, word [rdx + r12 + 52], 4 + QUAD $0x05342a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 52], 5 + LONG $0x54c40f66; WORD $0x3432; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 52], 6 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x07340254c40f4266 // pinsrw xmm2, word [rdx + r8 + 52], 7 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0x5cc40f66; WORD $0x360a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 54], 1 + QUAD $0x02360a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 54], 2 + QUAD $0x03363a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 54], 3 + QUAD $0x0436225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 54], 4 + QUAD $0x05362a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 54], 5 + LONG $0x5cc40f66; WORD $0x3632; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 54], 6 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x0736025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 54], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0x4cc40f66; WORD $0x380a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 56], 1 + QUAD $0x02380a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 56], 2 + QUAD $0x03383a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 56], 3 + QUAD $0x0438224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 56], 4 + QUAD $0x05382a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 56], 5 + LONG $0x4cc40f66; WORD $0x3832; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 56], 6 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + QUAD $0x0738024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 56], 7 + LONG $0xe7f80f66 // psubb xmm4, xmm7 + QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI5_9] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + QUAD $0x000000a0b56f0f66 // movdqa xmm6, oword 160[rbp] /* [rip + .LCPI5_10] */ + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0xd76e0f66 // movd xmm2, edi + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0x54c40f66; WORD $0x3a0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 58], 1 + QUAD $0x023a0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 58], 2 + QUAD $0x033a3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 58], 3 + QUAD $0x043a2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 58], 4 + QUAD $0x053a2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 58], 5 + LONG $0x54c40f66; WORD $0x3a32; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 58], 6 + QUAD $0x073a0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 58], 7 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d + LONG $0x5cc40f66; WORD $0x3c0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 60], 1 + QUAD $0x023c0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 60], 2 + QUAD $0x033c3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 60], 3 + QUAD $0x043c225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 60], 4 + QUAD $0x053c2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 60], 5 + LONG $0x5cc40f66; WORD $0x3c32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 60], 6 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x073c025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 60], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf4eb0f66 // por xmm6, xmm4 + QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI5_11] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 + LONG $0x6f0f4166; BYTE $0xc9 // movdqa xmm1, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xcf10 // pblendvb xmm1, xmm15, xmm0 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xd710 // pblendvb xmm10, xmm15, xmm0 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0x44b70f42; WORD $0x3e32 // movzx eax, word [rdx + r14 + 62] + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x44c40f66; WORD $0x3e0a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 62], 1 + QUAD $0x023e0a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 62], 2 + QUAD $0x033e3a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 62], 3 + QUAD $0x043e2244c40f4266 // pinsrw xmm0, word [rdx + r12 + 62], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x053e2a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 62], 5 + LONG $0x44c40f66; WORD $0x3e32; BYTE $0x06 // pinsrw xmm0, word [rdx + rsi + 62], 6 + QUAD $0x073e0244c40f4266 // pinsrw xmm0, word [rdx + r8 + 62], 7 + LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xeb0f4466; BYTE $0xd6 // por xmm10, xmm6 + LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 + LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 + LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 + LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 + LONG $0x6c0f4166; BYTE $0xd6 // punpcklqdq xmm2, xmm14 + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI5_15] */ + LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 + LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 + LONG $0xc2610f66 // punpcklwd xmm0, xmm2 + LONG $0x600f4566; BYTE $0xc6 // punpcklbw xmm8, xmm14 + LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 + LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + LONG $0x7f0f44f3; WORD $0x8824 // movdqu oword [rax + 4*rcx], xmm12 + LONG $0x447f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm0 + LONG $0x08c18348 // add rcx, 8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] + JNE LBB5_206 + QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] + LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x24748b44; BYTE $0x0c // mov r14d, dword [rsp + 12] + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + JNE LBB5_70 + JMP LBB5_134 -LBB5_86: - LONG $0xf0e28349 // and r10, -16 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000e82494894c // mov qword [rsp + 232], r10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 - WORD $0xc031 // xor eax, eax +LBB5_208: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 + LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0xef0f4566; BYTE $0xff // pxor xmm15, xmm15 -LBB5_87: - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax - LONG $0x05e0c148 // shl rax, 5 - WORD $0x8948; BYTE $0xc2 // mov rdx, rax - WORD $0x8949; BYTE $0xc4 // mov r12, rax - WORD $0x8949; BYTE $0xc0 // mov r8, rax - WORD $0x8949; BYTE $0xc2 // mov r10, rax - WORD $0x8949; BYTE $0xc7 // mov r15, rax - WORD $0x8949; BYTE $0xc1 // mov r9, rax - WORD $0x8949; BYTE $0xc3 // mov r11, rax - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax - WORD $0x8949; BYTE $0xc5 // mov r13, rax - LONG $0x0cb60f41; BYTE $0x06 // movzx ecx, byte [r14 + rax] - LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x4cb60f41; WORD $0x0106 // movzx ecx, byte [r14 + rax + 1] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x4cb60f41; WORD $0x0206 // movzx ecx, byte [r14 + rax + 2] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x4cb60f41; WORD $0x0306 // movzx ecx, byte [r14 + rax + 3] - LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x4cb60f41; WORD $0x0406 // movzx ecx, byte [r14 + rax + 4] - LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x4cb60f41; WORD $0x0506 // movzx ecx, byte [r14 + rax + 5] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x4cb60f41; WORD $0x0606 // movzx ecx, byte [r14 + rax + 6] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x4cb60f41; WORD $0x0706 // movzx ecx, byte [r14 + rax + 7] - LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x4cb60f41; WORD $0x0806 // movzx ecx, byte [r14 + rax + 8] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x4cb60f41; WORD $0x0906 // movzx ecx, byte [r14 + rax + 9] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x4cb60f41; WORD $0x0a06 // movzx ecx, byte [r14 + rax + 10] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x4cb60f41; WORD $0x0b06 // movzx ecx, byte [r14 + rax + 11] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x4cb60f41; WORD $0x0c06 // movzx ecx, byte [r14 + rax + 12] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 - LONG $0x4cb60f41; WORD $0x0d06 // movzx ecx, byte [r14 + rax + 13] - LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x4cb60f41; WORD $0x0e06 // movzx ecx, byte [r14 + rax + 14] - LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x4cb60f41; WORD $0x0f06 // movzx ecx, byte [r14 + rax + 15] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - LONG $0x20cf8348 // or rdi, 32 - LONG $0x40ca8348 // or rdx, 64 - LONG $0x24548948; BYTE $0x28 // mov qword [rsp + 40], rdx - LONG $0x60cc8349 // or r12, 96 - LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 - LONG $0xa0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 160 +LBB5_209: + LONG $0x2474894c; BYTE $0x28 // mov qword [rsp + 40], r14 + LONG $0x06e6c149 // shl r14, 6 + WORD $0x894d; BYTE $0xf1 // mov r9, r14 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + LONG $0x04b70f42; BYTE $0x32 // movzx eax, word [rdx + r14] + LONG $0xe86e0f66 // movd xmm5, eax + LONG $0x44b70f42; WORD $0x0232 // movzx eax, word [rdx + r14 + 2] + LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x44b70f42; WORD $0x0432 // movzx eax, word [rdx + r14 + 4] + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x44b70f42; WORD $0x0632 // movzx eax, word [rdx + r14 + 6] + LONG $0xf86e0f66 // movd xmm7, eax + LONG $0x44b70f42; WORD $0x0832 // movzx eax, word [rdx + r14 + 8] + LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax + LONG $0x44b70f42; WORD $0x0a32 // movzx eax, word [rdx + r14 + 10] + LONG $0xe06e0f66 // movd xmm4, eax + LONG $0x44b70f42; WORD $0x0c32 // movzx eax, word [rdx + r14 + 12] + LONG $0x54b70f46; WORD $0x0e32 // movzx r10d, word [rdx + r14 + 14] + LONG $0x5cb70f42; WORD $0x1032 // movzx ebx, word [rdx + r14 + 16] + LONG $0x7cb70f42; WORD $0x1232 // movzx edi, word [rdx + r14 + 18] + LONG $0x4cb70f42; WORD $0x1432 // movzx ecx, word [rdx + r14 + 20] + LONG $0x18244c89 // mov dword [rsp + 24], ecx + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + LONG $0x40c98348 // or rcx, 64 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 LONG $0xc0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 192 - LONG $0xe0c98149; WORD $0x0000; BYTE $0x00 // or r9, 224 - LONG $0x00cb8149; WORD $0x0001; BYTE $0x00 // or r11, 256 - LONG $0x20cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 288 - LONG $0x40ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 320 - LONG $0x24748948; BYTE $0x68 // mov qword [rsp + 104], rsi - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - LONG $0x60ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 352 - LONG $0x24748948; BYTE $0x48 // mov qword [rsp + 72], rsi - LONG $0x80cd8149; WORD $0x0001; BYTE $0x00 // or r13, 384 - LONG $0x246c894c; BYTE $0x70 // mov qword [rsp + 112], r13 - LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax - WORD $0x8949; BYTE $0xcd // mov r13, rcx - LONG $0xc0cd8149; WORD $0x0001; BYTE $0x00 // or r13, 448 - LONG $0x246c894c; BYTE $0x38 // mov qword [rsp + 56], r13 - LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 - LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - QUAD $0x013e24203a0f4166 // pinsrb xmm4, byte [r14 + rdi], 1 - QUAD $0x021624203a0f4166 // pinsrb xmm4, byte [r14 + rdx], 2 - LONG $0x2464894c; BYTE $0x78 // mov qword [rsp + 120], r12 - QUAD $0x032624203a0f4366 // pinsrb xmm4, byte [r14 + r12], 3 - QUAD $0x040624203a0f4366 // pinsrb xmm4, byte [r14 + r8], 4 - LONG $0x2454894c; BYTE $0x60 // mov qword [rsp + 96], r10 - QUAD $0x051624203a0f4366 // pinsrb xmm4, byte [r14 + r10], 5 - QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 - QUAD $0x063e24203a0f4366 // pinsrb xmm4, byte [r14 + r15], 6 - QUAD $0x070e24203a0f4366 // pinsrb xmm4, byte [r14 + r9], 7 - QUAD $0x081e24203a0f4366 // pinsrb xmm4, byte [r14 + r11], 8 - LONG $0x245c8948; BYTE $0x58 // mov qword [rsp + 88], rbx - QUAD $0x091e24203a0f4166 // pinsrb xmm4, byte [r14 + rbx], 9 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x0a1e24203a0f4166 // pinsrb xmm4, byte [r14 + rbx], 10 - QUAD $0x0b3624203a0f4166 // pinsrb xmm4, byte [r14 + rsi], 11 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0c3e24203a0f4166 // pinsrb xmm4, byte [r14 + rdi], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0d0624203a0f4166 // pinsrb xmm4, byte [r14 + rax], 13 - QUAD $0x0e2e24203a0f4366 // pinsrb xmm4, byte [r14 + r13], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0f0624203a0f4166 // pinsrb xmm4, byte [r14 + rax], 15 - QUAD $0x010e5c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rcx + 1], 1 - QUAD $0x01165c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rdx + 1], 2 - QUAD $0x01265c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r14 + r12 + 1], 3 - QUAD $0x01065c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r14 + r8 + 1], 4 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - QUAD $0x01165c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r10 + 1], 5 - QUAD $0x013e5c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r14 + r15 + 1], 6 - QUAD $0x010e5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r9 + 1], 7 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - QUAD $0x011e5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r11 + 1], 8 - WORD $0x894d; BYTE $0xda // mov r10, r11 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x01265c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r12 + 1], 9 - QUAD $0x011e5c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r14 + rbx + 1], 10 - QUAD $0x01365c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rsi + 1], 11 - QUAD $0x013e5c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r14 + rdi + 1], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x01065c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rax + 1], 13 - QUAD $0x012e5c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r14 + r13 + 1], 14 - QUAD $0x0000b0248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 176] - LONG $0xe1740f66 // pcmpeqb xmm4, xmm1 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x012e5c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r14 + r13 + 1], 15 - LONG $0xd9740f66 // pcmpeqb xmm3, xmm1 - QUAD $0x00000100856f0f66 // movdqa xmm0, oword 256[rbp] /* [rip + .LCPI5_16] */ - LONG $0xd8df0f66 // pandn xmm3, xmm0 - LONG $0xdcfc0f66 // paddb xmm3, xmm4 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - LONG $0x74b60f41; WORD $0x1006 // movzx esi, byte [r14 + rax + 16] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - QUAD $0x020e6c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rcx + 2], 1 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x244c8948; BYTE $0x18 // mov qword [rsp + 24], rcx - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x020e6c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rcx + 2], 2 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x023e6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r15 + 2], 3 - WORD $0x8948; BYTE $0xd3 // mov rbx, rdx - QUAD $0x02166c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rdx + 2], 4 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x020e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r9 + 2], 5 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x021e6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r11 + 2], 6 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - LONG $0x2444894c; BYTE $0x30 // mov qword [rsp + 48], r8 - QUAD $0x02066c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r8 + 2], 7 - QUAD $0x02166c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r10 + 2], 8 - QUAD $0x02266c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r12 + 2], 9 - LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] - QUAD $0x02066c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r8 + 2], 10 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x020e6c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r14 + rcx + 2], 11 - QUAD $0x023e6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rdi + 2], 12 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x02366c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rsi + 2], 13 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x02366c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rsi + 2], 14 - QUAD $0x022e6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r13 + 2], 15 - QUAD $0x03067c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rax + 3], 1 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x03067c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rax + 3], 2 - QUAD $0x033e7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r14 + r15 + 3], 3 - QUAD $0x031e7c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r14 + rbx + 3], 4 - QUAD $0x030e7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r9 + 3], 5 - QUAD $0x031e7c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r14 + r11 + 3], 6 - QUAD $0x03167c203a0f4166; BYTE $0x07 // pinsrb xmm7, byte [r14 + rdx + 3], 7 - QUAD $0x03167c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r10 + 3], 8 - QUAD $0x03267c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r12 + 3], 9 - QUAD $0x03067c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r14 + r8 + 3], 10 - QUAD $0x030e7c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r14 + rcx + 3], 11 - QUAD $0x033e7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r14 + rdi + 3], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x03067c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rax + 3], 13 - QUAD $0x03367c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r14 + rsi + 3], 14 - QUAD $0x032e7c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r14 + r13 + 3], 15 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x04064c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rax + 4], 1 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x04064c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rax + 4], 2 - QUAD $0x043e4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r14 + r15 + 4], 3 - QUAD $0x041e4c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r14 + rbx + 4], 4 - QUAD $0x040e4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r9 + 4], 5 - QUAD $0x041e4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r14 + r11 + 4], 6 - QUAD $0x04164c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r14 + rdx + 4], 7 - QUAD $0x04164c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r10 + 4], 8 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x04264c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r14 + r12 + 4], 9 - QUAD $0x04064c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r14 + r8 + 4], 10 - QUAD $0x040e4c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rcx + 4], 11 - QUAD $0x043e4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r14 + rdi + 4], 12 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x04164c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r14 + rdx + 4], 13 - QUAD $0x04364c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rsi + 4], 14 - QUAD $0x042e4c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r14 + r13 + 4], 15 - LONG $0xe9740f66 // pcmpeqb xmm5, xmm1 - QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI5_17] */ - LONG $0xe8df0f66 // pandn xmm5, xmm0 - LONG $0xf9740f66 // pcmpeqb xmm7, xmm1 - QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI5_18] */ - LONG $0xf8df0f66 // pandn xmm7, xmm0 - LONG $0xfdeb0f66 // por xmm7, xmm5 - QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] - LONG $0x74b60f43; WORD $0x110e // movzx esi, byte [r14 + r9 + 17] - LONG $0xe66e0f66 // movd xmm4, esi - LONG $0x740f4466; BYTE $0xc9 // pcmpeqb xmm9, xmm1 - QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI5_19] */ - LONG $0xdf0f4466; BYTE $0xc8 // pandn xmm9, xmm0 - LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 - LONG $0x74b60f43; WORD $0x120e // movzx esi, byte [r14 + r9 + 18] - LONG $0xfe6e0f66 // movd xmm7, esi + LONG $0x00cc8149; WORD $0x0001; BYTE $0x00 // or r12, 256 + LONG $0x40cd8149; WORD $0x0001; BYTE $0x00 // or r13, 320 + LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 + LONG $0x2cc40f66; WORD $0x010a // pinsrw xmm5, word [rdx + rcx], 1 + LONG $0xc40f4266; WORD $0x0a2c; BYTE $0x02 // pinsrw xmm5, word [rdx + r9], 2 + LONG $0xc40f4266; WORD $0x3a2c; BYTE $0x03 // pinsrw xmm5, word [rdx + r15], 3 + LONG $0xc40f4266; WORD $0x222c; BYTE $0x04 // pinsrw xmm5, word [rdx + r12], 4 + LONG $0xc40f4266; WORD $0x2a2c; BYTE $0x05 // pinsrw xmm5, word [rdx + r13], 5 + LONG $0x2cc40f66; WORD $0x0632 // pinsrw xmm5, word [rdx + rsi], 6 + LONG $0x44c40f66; WORD $0x020a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 2], 1 + QUAD $0x02020a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 2], 2 + QUAD $0x03023a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 2], 3 + QUAD $0x04022244c40f4266 // pinsrw xmm0, word [rdx + r12 + 2], 4 + QUAD $0x05022a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 2], 5 + LONG $0x44c40f66; WORD $0x0232; BYTE $0x06 // pinsrw xmm0, word [rdx + rsi + 2], 6 + LONG $0xc0c88149; WORD $0x0001; BYTE $0x00 // or r8, 448 + QUAD $0x07020244c40f4266 // pinsrw xmm0, word [rdx + r8 + 2], 7 + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x44b70f42; WORD $0x1632 // movzx eax, word [rdx + r14 + 22] + LONG $0x10244489 // mov dword [rsp + 16], eax + LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 + LONG $0x4cc40f66; WORD $0x040a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 4], 1 + QUAD $0x02040a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 4], 2 + QUAD $0x03043a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 4], 3 + QUAD $0x0404224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 4], 4 + QUAD $0x05042a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 4], 5 + LONG $0x4cc40f66; WORD $0x0432; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 4], 6 + QUAD $0x0704024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 4], 7 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + QUAD $0x0000808d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 128[rbp] /* [rip + .LCPI5_8] */ + LONG $0x6f0f4166; BYTE $0xd9 // movdqa xmm3, xmm9 + LONG $0x380f4166; WORD $0xdf10 // pblendvb xmm3, xmm15, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + QUAD $0x00000090856f0f66 // movdqa xmm0, oword 144[rbp] /* [rip + .LCPI5_9] */ + LONG $0xf06f0f66 // movdqa xmm6, xmm0 + LONG $0x6f0f4466; BYTE $0xf0 // movdqa xmm14, xmm0 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xca // movd xmm1, r10d + LONG $0x5cb70f46; WORD $0x1832 // movzx r11d, word [rdx + r14 + 24] + LONG $0xc40f4266; WORD $0x022c; BYTE $0x07 // pinsrw xmm5, word [rdx + r8], 7 + LONG $0x750f4166; BYTE $0xeb // pcmpeqw xmm5, xmm11 LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 - LONG $0xd8f80f66 // psubb xmm3, xmm0 - LONG $0xeb0f4466; BYTE $0xcb // por xmm9, xmm3 - LONG $0x74b60f43; WORD $0x130e // movzx esi, byte [r14 + r9 + 19] - LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x050e54203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r14 + r9 + 5], 1 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x050654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rax + 5], 2 - QUAD $0x053e54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r15 + 5], 3 - QUAD $0x051e54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rbx + 5], 4 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x00000098249c8948 // mov qword [rsp + 152], rbx - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x052e54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r13 + 5], 5 - QUAD $0x051e54203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r14 + r11 + 5], 6 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x053654203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rsi + 5], 7 - QUAD $0x051654203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r10 + 5], 8 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x053e54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r15 + 5], 9 - QUAD $0x050654203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r8 + 5], 10 - QUAD $0x050e54203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rcx + 5], 11 - QUAD $0x053e54203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r14 + rdi + 5], 12 - QUAD $0x051654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rdx + 5], 13 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - QUAD $0x051e54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r11 + 5], 14 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x051654203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r10 + 5], 15 - QUAD $0x060e44203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r14 + r9 + 6], 1 - QUAD $0x060644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rax + 6], 2 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x061e44203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rbx + 6], 3 - QUAD $0x062644203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r14 + r12 + 6], 4 - QUAD $0x062e44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r13 + 6], 5 - QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] - QUAD $0x062644203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r14 + r12 + 6], 6 - QUAD $0x063644203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r14 + rsi + 6], 7 - QUAD $0x0000009024a48b4c // mov r12, qword [rsp + 144] - QUAD $0x062644203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r12 + 6], 8 - QUAD $0x063e44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r15 + 6], 9 - QUAD $0x060644203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r14 + r8 + 6], 10 - QUAD $0x060e44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rcx + 6], 11 - QUAD $0x063e44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rdi + 6], 12 - QUAD $0x061644203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rdx + 6], 13 - QUAD $0x061e44203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r14 + r11 + 6], 14 - QUAD $0x061644203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r10 + 6], 15 - QUAD $0x070e74203a0f4766; BYTE $0x01 // pinsrb xmm14, byte [r14 + r9 + 7], 1 - QUAD $0x070674203a0f4566; BYTE $0x02 // pinsrb xmm14, byte [r14 + rax + 7], 2 - WORD $0x8949; BYTE $0xc7 // mov r15, rax - QUAD $0x071e74203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r14 + rbx + 7], 3 - QUAD $0x00000098249c8b4c // mov r11, qword [rsp + 152] - QUAD $0x071e74203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r14 + r11 + 7], 4 - QUAD $0x072e74203a0f4766; BYTE $0x05 // pinsrb xmm14, byte [r14 + r13 + 7], 5 - QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] - QUAD $0x070674203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r14 + rax + 7], 6 - QUAD $0x073674203a0f4566; BYTE $0x07 // pinsrb xmm14, byte [r14 + rsi + 7], 7 - WORD $0x894d; BYTE $0xe1 // mov r9, r12 - QUAD $0x072674203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r14 + r12 + 7], 8 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x072674203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r14 + r12 + 7], 9 - QUAD $0x070674203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r14 + r8 + 7], 10 - QUAD $0x070e74203a0f4566; BYTE $0x0b // pinsrb xmm14, byte [r14 + rcx + 7], 11 - QUAD $0x073e74203a0f4566; BYTE $0x0c // pinsrb xmm14, byte [r14 + rdi + 7], 12 - QUAD $0x071674203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r14 + rdx + 7], 13 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x073e74203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r14 + rdi + 7], 14 - LONG $0x6f0f4166; BYTE $0xce // movdqa xmm1, xmm14 - QUAD $0x00b024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 - QUAD $0x00000140856f0f66 // movdqa xmm0, oword 320[rbp] /* [rip + .LCPI5_20] */ - LONG $0xd0df0f66 // pandn xmm2, xmm0 - LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 - QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI5_21] */ - LONG $0xdf0f4466; BYTE $0xc0 // pandn xmm8, xmm0 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - LONG $0x74b60f43; WORD $0x1416 // movzx esi, byte [r14 + r10 + 20] - LONG $0xde6e0f66 // movd xmm3, esi - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x07064c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rax + 7], 15 - LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 - LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI5_6] */ - LONG $0xc8df0f66 // pandn xmm1, xmm0 - LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - LONG $0x74b60f43; WORD $0x1516 // movzx esi, byte [r14 + r10 + 21] - LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0000f024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 240] - QUAD $0x081644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rdx + 8], 1 - QUAD $0x083e44203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r14 + r15 + 8], 2 - QUAD $0x081e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rbx + 8], 3 - WORD $0x8949; BYTE $0xdf // mov r15, rbx - WORD $0x894c; BYTE $0xdb // mov rbx, r11 - QUAD $0x081e44203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r11 + 8], 4 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - QUAD $0x082e44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r13 + 8], 5 - QUAD $0x0000008824ac8b4c // mov r13, qword [rsp + 136] - QUAD $0x082e44203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r14 + r13 + 8], 6 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x080e44203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r14 + rcx + 8], 7 - QUAD $0x080e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r9 + 8], 8 - QUAD $0x082644203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r12 + 8], 9 - QUAD $0x080644203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r8 + 8], 10 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x080644203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r8 + 8], 11 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x080e44203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r9 + 8], 12 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x083644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rsi + 8], 13 - QUAD $0x083e44203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rdi + 8], 14 - QUAD $0x080644203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rax + 8], 15 - LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 - QUAD $0x0000f0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm1 - LONG $0x74b60f43; WORD $0x1616 // movzx esi, byte [r14 + r10 + 22] - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 - QUAD $0x09165c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rdx + 9], 1 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x09065c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rax + 9], 2 - QUAD $0x093e5c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r14 + r15 + 9], 3 - QUAD $0x091e5c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rbx + 9], 4 - WORD $0x894c; BYTE $0xda // mov rdx, r11 - QUAD $0x091e5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r11 + 9], 5 - QUAD $0x092e5c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r13 + 9], 6 - QUAD $0x090e5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rcx + 9], 7 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x09165c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r10 + 9], 8 - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - QUAD $0x09265c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r12 + 9], 9 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x09365c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r14 + rsi + 9], 10 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - QUAD $0x09065c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r14 + r8 + 9], 11 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - QUAD $0x090e5c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r9 + 9], 12 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x091e5c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r14 + r11 + 9], 13 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x09265c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r12 + 9], 14 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x09065c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r8 + 9], 15 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x0a0e64203a0f4766; BYTE $0x01 // pinsrb xmm12, byte [r14 + r9 + 10], 1 - QUAD $0x0a0664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rax + 10], 2 - QUAD $0x0a3e64203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r14 + r15 + 10], 3 - QUAD $0x0a1e64203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r14 + rbx + 10], 4 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x0a1e64203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r14 + rbx + 10], 5 - QUAD $0x0a2e64203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r14 + r13 + 10], 6 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x0a3e64203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r14 + r15 + 10], 7 - QUAD $0x0a1664203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r10 + 10], 8 - QUAD $0x0a0e64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r14 + rcx + 10], 9 - QUAD $0x0a3664203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r14 + rsi + 10], 10 - QUAD $0x0a1664203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r14 + rdx + 10], 11 - QUAD $0x0a3e64203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r14 + rdi + 10], 12 - QUAD $0x0a1e64203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r14 + r11 + 10], 13 - QUAD $0x0a2664203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r14 + r12 + 10], 14 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - QUAD $0x0a0664203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r14 + r8 + 10], 15 - WORD $0x894d; BYTE $0xc4 // mov r12, r8 - QUAD $0x0b0e6c203a0f4766; BYTE $0x01 // pinsrb xmm13, byte [r14 + r9 + 11], 1 - QUAD $0x0b066c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rax + 11], 2 - WORD $0x8949; BYTE $0xc0 // mov r8, rax - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x0b3e6c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r14 + r15 + 11], 3 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x0b0e6c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r14 + r9 + 11], 4 - QUAD $0x0b1e6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r14 + rbx + 11], 5 - QUAD $0x0b2e6c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r14 + r13 + 11], 6 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b066c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r14 + rax + 11], 7 - QUAD $0x0b166c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r10 + 11], 8 - QUAD $0x0b0e6c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r14 + rcx + 11], 9 - QUAD $0x0b366c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r14 + rsi + 11], 10 - QUAD $0x0b166c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r14 + rdx + 11], 11 - QUAD $0x0b3e6c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r14 + rdi + 11], 12 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0b066c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rax + 11], 13 - QUAD $0x0b1e6c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r14 + r11 + 11], 14 - QUAD $0x0b266c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r14 + r12 + 11], 15 - LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 - QUAD $0x0001009ddf0f4466; BYTE $0x00 // pandn xmm11, oword 256[rbp] /* [rip + .LCPI5_16] */ - LONG $0xfc0f4466; BYTE $0xd8 // paddb xmm11, xmm0 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - LONG $0x74b60f41; WORD $0x1706 // movzx esi, byte [r14 + rax + 23] - LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi - LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 - QUAD $0x000110a5df0f4466; BYTE $0x00 // pandn xmm12, oword 272[rbp] /* [rip + .LCPI5_17] */ - LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 - QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI5_18] */ - LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - LONG $0x74b60f41; WORD $0x1806 // movzx esi, byte [r14 + rax + 24] - LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - QUAD $0x00d0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 208] - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0c064c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rax + 12], 1 - WORD $0x894d; BYTE $0xc4 // mov r12, r8 - QUAD $0x0c064c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r14 + r8 + 12], 2 - QUAD $0x0c3e4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r14 + r15 + 12], 3 - WORD $0x894c; BYTE $0xcb // mov rbx, r9 - QUAD $0x0c0e4c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r14 + r9 + 12], 4 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x0c0e4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r9 + 12], 5 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - QUAD $0x0c2e4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r14 + r13 + 12], 6 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x0c064c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r8 + 12], 7 - WORD $0x894c; BYTE $0xd6 // mov rsi, r10 - QUAD $0x0c164c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r10 + 12], 8 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0c0e4c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r14 + rcx + 12], 9 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x0c164c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r14 + r10 + 12], 10 - QUAD $0x0c164c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rdx + 12], 11 - QUAD $0x0c3e4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r14 + rdi + 12], 12 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x0c2e4c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r14 + r13 + 12], 13 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0c064c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rax + 12], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c064c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r14 + rax + 12], 15 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0d0674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rax + 13], 1 - QUAD $0x0d2674203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r14 + r12 + 13], 2 - QUAD $0x0d3e74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r15 + 13], 3 - QUAD $0x0d1e74203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rbx + 13], 4 - QUAD $0x0d0e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r9 + 13], 5 - QUAD $0x0d1e74203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r11 + 13], 6 - QUAD $0x0d0674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r8 + 13], 7 - QUAD $0x0d3674203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r14 + rsi + 13], 8 - QUAD $0x0d0e74203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r14 + rcx + 13], 9 - QUAD $0x0d1674203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r10 + 13], 10 - QUAD $0x0d1674203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r14 + rdx + 13], 11 - QUAD $0x0d3e74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rdi + 13], 12 - QUAD $0x0d2e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r13 + 13], 13 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0d0674203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rax + 13], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d0674203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rax + 13], 15 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e067c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rax + 14], 1 - QUAD $0x0e267c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r14 + r12 + 14], 2 - QUAD $0x0e3e7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r14 + r15 + 14], 3 - QUAD $0x0e1e7c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r14 + rbx + 14], 4 - QUAD $0x0e0e7c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r14 + r9 + 14], 5 - QUAD $0x0e1e7c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r14 + r11 + 14], 6 - QUAD $0x0e067c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r14 + r8 + 14], 7 - QUAD $0x0e367c203a0f4566; BYTE $0x08 // pinsrb xmm15, byte [r14 + rsi + 14], 8 - QUAD $0x0e0e7c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r14 + rcx + 14], 9 - QUAD $0x0e167c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r14 + r10 + 14], 10 - QUAD $0x0e167c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r14 + rdx + 14], 11 - QUAD $0x0e3e7c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r14 + rdi + 14], 12 - QUAD $0x0e2e7c203a0f4766; BYTE $0x0d // pinsrb xmm15, byte [r14 + r13 + 14], 13 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x0e267c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r14 + r12 + 14], 14 - LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 - QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI5_19] */ - LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - LONG $0x74b60f43; WORD $0x193e // movzx esi, byte [r14 + r15 + 25] - LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi - QUAD $0x0001609df80f4466; BYTE $0x00 // psubb xmm11, oword 352[rbp] /* [rip + .LCPI5_22] */ - LONG $0xeb0f4566; BYTE $0xcb // por xmm9, xmm11 - LONG $0x74b60f43; WORD $0x1a3e // movzx esi, byte [r14 + r15 + 26] - LONG $0xc66e0f66 // movd xmm0, esi - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x0e1e7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r14 + rbx + 14], 15 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - QUAD $0x00000140b5df0f66 // pandn xmm6, oword 320[rbp] /* [rip + .LCPI5_20] */ - LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 - QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI5_21] */ - LONG $0xeb0f4466; BYTE $0xfe // por xmm15, xmm6 - LONG $0x74b60f43; WORD $0x1b3e // movzx esi, byte [r14 + r15 + 27] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - QUAD $0x0000c024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 192] - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0f0674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rax + 15], 1 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0f3e74203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rdi + 15], 2 - LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] - QUAD $0x0f1674203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rdx + 15], 3 - QUAD $0x00000098248c8b48 // mov rcx, qword [rsp + 152] - QUAD $0x0f0e74203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rcx + 15], 4 - QUAD $0x0f0e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r9 + 15], 5 - QUAD $0x0f1e74203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r11 + 15], 6 - QUAD $0x0f0674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r8 + 15], 7 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x0f0674203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r8 + 15], 8 - LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] - QUAD $0x0f0e74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r9 + 15], 9 - QUAD $0x0f1674203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r10 + 15], 10 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x0f1674203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r10 + 15], 11 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x0f3674203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rsi + 15], 12 - QUAD $0x0f2e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r13 + 15], 13 - QUAD $0x0f2674203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r14 + r12 + 15], 14 - QUAD $0x0f1e74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rbx + 15], 15 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI5_6] */ - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x74b60f43; WORD $0x1c3e // movzx esi, byte [r14 + r15 + 28] - LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 - QUAD $0x0000c024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm6 - LONG $0x74b60f43; WORD $0x1d3e // movzx esi, byte [r14 + r15 + 29] - LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - QUAD $0x100654203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rax + 16], 1 - QUAD $0x103e54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rdi + 16], 2 - QUAD $0x101654203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rdx + 16], 3 - QUAD $0x100e54203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r14 + rcx + 16], 4 - LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x103654203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r14 + rsi + 16], 5 - QUAD $0x101e54203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r11 + 16], 6 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x103654203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rsi + 16], 7 - QUAD $0x100654203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r14 + r8 + 16], 8 - QUAD $0x100e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r9 + 16], 9 - LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] - QUAD $0x103654203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r14 + rsi + 16], 10 - QUAD $0x101654203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r10 + 16], 11 - LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] - QUAD $0x103654203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r14 + rsi + 16], 12 - QUAD $0x102e54203a0f4766; BYTE $0x0d // pinsrb xmm10, byte [r14 + r13 + 16], 13 - QUAD $0x102654203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r14 + r12 + 16], 14 - QUAD $0x101e54203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rbx + 16], 15 - QUAD $0x110664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rax + 17], 1 - QUAD $0x113e64203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rdi + 17], 2 - QUAD $0x111664203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdx + 17], 3 - QUAD $0x110e64203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rcx + 17], 4 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x110e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r9 + 17], 5 - QUAD $0x111e64203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r14 + r11 + 17], 6 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x110664203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r8 + 17], 7 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x113e64203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r14 + rdi + 17], 8 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x110e64203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r14 + rcx + 17], 9 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x111664203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r10 + 17], 10 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x111664203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r14 + rdx + 17], 11 - QUAD $0x113664203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r14 + rsi + 17], 12 - QUAD $0x112e64203a0f4366; BYTE $0x0d // pinsrb xmm4, byte [r14 + r13 + 17], 13 - QUAD $0x112664203a0f4366; BYTE $0x0e // pinsrb xmm4, byte [r14 + r12 + 17], 14 - QUAD $0x111e64203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r14 + rbx + 17], 15 - LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 - LONG $0x740f4166; BYTE $0xe6 // pcmpeqb xmm4, xmm14 - QUAD $0x00000100b56f0f66 // movdqa xmm6, oword 256[rbp] /* [rip + .LCPI5_16] */ - LONG $0xe6df0f66 // pandn xmm4, xmm6 - LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 - LONG $0x74b60f43; WORD $0x1e3e // movzx esi, byte [r14 + r15 + 30] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - QUAD $0x12067c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rax + 18], 1 - QUAD $0x13066c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rax + 19], 1 - QUAD $0x14065c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rax + 20], 1 - QUAD $0x150654203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rax + 21], 1 - QUAD $0x16064c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rax + 22], 1 - QUAD $0x170644203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rax + 23], 1 - QUAD $0x180664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rax + 24], 1 - QUAD $0x19066c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rax + 25], 1 - QUAD $0x1a0644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rax + 26], 1 - QUAD $0x1b065c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rax + 27], 1 - QUAD $0x1c067c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rax + 28], 1 - QUAD $0x1d064c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rax + 29], 1 - QUAD $0x1e0654203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rax + 30], 1 - LONG $0x44b60f43; WORD $0x1f3e // movzx eax, byte [r14 + r15 + 31] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x1f3674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rsi + 31], 1 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x12067c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rax + 18], 2 - QUAD $0x13066c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rax + 19], 2 - QUAD $0x14065c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rax + 20], 2 - QUAD $0x150654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rax + 21], 2 - QUAD $0x16064c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rax + 22], 2 - QUAD $0x170644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rax + 23], 2 - QUAD $0x180664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rax + 24], 2 - QUAD $0x19066c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rax + 25], 2 - QUAD $0x1a0644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rax + 26], 2 - QUAD $0x1b065c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rax + 27], 2 - QUAD $0x1c067c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r14 + rax + 28], 2 - QUAD $0x1d064c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rax + 29], 2 - QUAD $0x1e0654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rax + 30], 2 - QUAD $0x1f0674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rax + 31], 2 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x123e7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r14 + r15 + 18], 3 - QUAD $0x0000009824848b48 // mov rax, qword [rsp + 152] - QUAD $0x12067c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r14 + rax + 18], 4 - QUAD $0x120e7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r9 + 18], 5 - QUAD $0x121e7c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r14 + r11 + 18], 6 - QUAD $0x12067c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r14 + r8 + 18], 7 - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - QUAD $0x123e7c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r14 + rdi + 18], 8 - QUAD $0x120e7c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r14 + rcx + 18], 9 - QUAD $0x12167c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r14 + r10 + 18], 10 - QUAD $0x12167c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r14 + rdx + 18], 11 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x123e7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r14 + rdi + 18], 12 - QUAD $0x122e7c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r14 + r13 + 18], 13 - QUAD $0x12267c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r14 + r12 + 18], 14 - QUAD $0x121e7c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r14 + rbx + 18], 15 - QUAD $0x133e6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r15 + 19], 3 - QUAD $0x13066c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rax + 19], 4 - QUAD $0x130e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r9 + 19], 5 - QUAD $0x131e6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r11 + 19], 6 - QUAD $0x13066c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r8 + 19], 7 - QUAD $0x13366c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r14 + rsi + 19], 8 - QUAD $0x130e6c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r14 + rcx + 19], 9 - QUAD $0x13166c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r10 + 19], 10 - QUAD $0x13166c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r14 + rdx + 19], 11 - QUAD $0x133e6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rdi + 19], 12 - QUAD $0x132e6c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r14 + r13 + 19], 13 - QUAD $0x13266c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r14 + r12 + 19], 14 - QUAD $0x131e6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r14 + rbx + 19], 15 - QUAD $0x143e5c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r14 + r15 + 20], 3 - QUAD $0x14065c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r14 + rax + 20], 4 - QUAD $0x140e5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r9 + 20], 5 - QUAD $0x141e5c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r14 + r11 + 20], 6 - QUAD $0x14065c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r8 + 20], 7 - QUAD $0x14365c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r14 + rsi + 20], 8 - QUAD $0x140e5c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r14 + rcx + 20], 9 - QUAD $0x14165c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r14 + r10 + 20], 10 - QUAD $0x14165c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rdx + 20], 11 - QUAD $0x143e5c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r14 + rdi + 20], 12 - QUAD $0x142e5c203a0f4366; BYTE $0x0d // pinsrb xmm3, byte [r14 + r13 + 20], 13 - QUAD $0x14265c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r14 + r12 + 20], 14 - LONG $0x740f4166; BYTE $0xfe // pcmpeqb xmm7, xmm14 - QUAD $0x000110b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 272[rbp] /* [rip + .LCPI5_17] */ - LONG $0xdf0f4166; BYTE $0xfe // pandn xmm7, xmm14 - QUAD $0x0000b024ac740f66; BYTE $0x00 // pcmpeqb xmm5, oword [rsp + 176] - QUAD $0x000120b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 288[rbp] /* [rip + .LCPI5_18] */ - LONG $0xdf0f4166; BYTE $0xee // pandn xmm5, xmm14 - LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0x141e5c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r14 + rbx + 20], 15 - QUAD $0x00b024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xde // pcmpeqb xmm3, xmm14 - QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI5_19] */ - LONG $0xdfdf0f66 // pandn xmm3, xmm7 - LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xed760f66 // pcmpeqd xmm5, xmm5 - LONG $0xe5f80f66 // psubb xmm4, xmm5 - LONG $0xdceb0f66 // por xmm3, xmm4 - QUAD $0x153e54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r15 + 21], 3 - QUAD $0x150654203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rax + 21], 4 - QUAD $0x150e54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r9 + 21], 5 - QUAD $0x151e54203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r14 + r11 + 21], 6 - QUAD $0x150654203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r8 + 21], 7 - QUAD $0x153654203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r14 + rsi + 21], 8 - QUAD $0x150e54203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r14 + rcx + 21], 9 - QUAD $0x151654203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r10 + 21], 10 - QUAD $0x151654203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rdx + 21], 11 - QUAD $0x153e54203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r14 + rdi + 21], 12 - QUAD $0x152e54203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r14 + r13 + 21], 13 - QUAD $0x152654203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r12 + 21], 14 - QUAD $0x151e54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rbx + 21], 15 - QUAD $0x163e4c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r14 + r15 + 22], 3 - QUAD $0x16064c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r14 + rax + 22], 4 - QUAD $0x160e4c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r14 + r9 + 22], 5 - QUAD $0x161e4c203a0f4366; BYTE $0x06 // pinsrb xmm1, byte [r14 + r11 + 22], 6 - QUAD $0x16064c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r14 + r8 + 22], 7 - QUAD $0x16364c203a0f4166; BYTE $0x08 // pinsrb xmm1, byte [r14 + rsi + 22], 8 - QUAD $0x160e4c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r14 + rcx + 22], 9 - QUAD $0x16164c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r14 + r10 + 22], 10 - QUAD $0x16164c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r14 + rdx + 22], 11 - QUAD $0x163e4c203a0f4166; BYTE $0x0c // pinsrb xmm1, byte [r14 + rdi + 22], 12 - QUAD $0x162e4c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r14 + r13 + 22], 13 - QUAD $0x16264c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r14 + r12 + 22], 14 - QUAD $0x161e4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rbx + 22], 15 - QUAD $0x173e44203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r14 + r15 + 23], 3 - QUAD $0x170644203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r14 + rax + 23], 4 - QUAD $0x170e44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r9 + 23], 5 - QUAD $0x171e44203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r14 + r11 + 23], 6 - QUAD $0x170644203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r8 + 23], 7 - QUAD $0x173644203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r14 + rsi + 23], 8 - QUAD $0x170e44203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r14 + rcx + 23], 9 - QUAD $0x171644203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r14 + r10 + 23], 10 - QUAD $0x171644203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rdx + 23], 11 - QUAD $0x173e44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rdi + 23], 12 - QUAD $0x172e44203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r14 + r13 + 23], 13 - QUAD $0x172644203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r14 + r12 + 23], 14 - LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 - QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI5_20] */ - LONG $0xd5df0f66 // pandn xmm2, xmm5 - LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 - QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI5_21] */ - LONG $0xcfdf0f66 // pandn xmm1, xmm7 - LONG $0xcaeb0f66 // por xmm1, xmm2 - QUAD $0x171e44203a0f4566; BYTE $0x0f // pinsrb xmm8, byte [r14 + rbx + 23], 15 - LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 - LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI5_6] */ - LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - QUAD $0x183e64203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r14 + r15 + 24], 3 - QUAD $0x180664203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r14 + rax + 24], 4 - QUAD $0x180e64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r14 + r9 + 24], 5 - QUAD $0x181e64203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r14 + r11 + 24], 6 - QUAD $0x180664203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r14 + r8 + 24], 7 - QUAD $0x183664203a0f4566; BYTE $0x08 // pinsrb xmm12, byte [r14 + rsi + 24], 8 - QUAD $0x180e64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r14 + rcx + 24], 9 - QUAD $0x181664203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r14 + r10 + 24], 10 - QUAD $0x181664203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r14 + rdx + 24], 11 - QUAD $0x183e64203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r14 + rdi + 24], 12 - QUAD $0x182e64203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r14 + r13 + 24], 13 - QUAD $0x182664203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r14 + r12 + 24], 14 - QUAD $0x181e64203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r14 + rbx + 24], 15 - LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 - QUAD $0x193e6c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r14 + r15 + 25], 3 - QUAD $0x19066c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r14 + rax + 25], 4 - QUAD $0x190e6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r14 + r9 + 25], 5 - QUAD $0x191e6c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r14 + r11 + 25], 6 - QUAD $0x19066c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r14 + r8 + 25], 7 - QUAD $0x19366c203a0f4566; BYTE $0x08 // pinsrb xmm13, byte [r14 + rsi + 25], 8 - QUAD $0x190e6c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r14 + rcx + 25], 9 - QUAD $0x19166c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r14 + r10 + 25], 10 - QUAD $0x19166c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r14 + rdx + 25], 11 - QUAD $0x193e6c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r14 + rdi + 25], 12 - QUAD $0x192e6c203a0f4766; BYTE $0x0d // pinsrb xmm13, byte [r14 + r13 + 25], 13 - QUAD $0x19266c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r14 + r12 + 25], 14 - QUAD $0x191e6c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r14 + rbx + 25], 15 - QUAD $0x1a3e44203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r14 + r15 + 26], 3 - QUAD $0x1a0644203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rax + 26], 4 - QUAD $0x1a0e44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r9 + 26], 5 - QUAD $0x1a1e44203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r14 + r11 + 26], 6 - QUAD $0x1a0644203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r8 + 26], 7 - QUAD $0x1a3644203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r14 + rsi + 26], 8 - QUAD $0x1a0e44203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r14 + rcx + 26], 9 - QUAD $0x1a1644203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r10 + 26], 10 - QUAD $0x1a1644203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r14 + rdx + 26], 11 - QUAD $0x1a3e44203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r14 + rdi + 26], 12 - QUAD $0x1a2e44203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r14 + r13 + 26], 13 - QUAD $0x1a2644203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r14 + r12 + 26], 14 - QUAD $0x1a1e44203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rbx + 26], 15 - QUAD $0x1b3e5c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r14 + r15 + 27], 3 - QUAD $0x1b065c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rax + 27], 4 - QUAD $0x1b0e5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r9 + 27], 5 - QUAD $0x1b1e5c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r11 + 27], 6 - QUAD $0x1b065c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r14 + r8 + 27], 7 - QUAD $0x1b365c203a0f4566; BYTE $0x08 // pinsrb xmm11, byte [r14 + rsi + 27], 8 - QUAD $0x1b0e5c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r14 + rcx + 27], 9 - QUAD $0x1b165c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r14 + r10 + 27], 10 - QUAD $0x1b165c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r14 + rdx + 27], 11 - QUAD $0x1b3e5c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r14 + rdi + 27], 12 - QUAD $0x1b2e5c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r14 + r13 + 27], 13 - QUAD $0x1b265c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r12 + 27], 14 - LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 - QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI5_16] */ - LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 - QUAD $0x1b1e5c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r14 + rbx + 27], 15 - LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 - QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI5_17] */ - LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 - QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI5_18] */ - LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 - QUAD $0x1c3e7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r14 + r15 + 28], 3 - QUAD $0x1d3e4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r14 + r15 + 29], 3 - QUAD $0x1e3e54203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r14 + r15 + 30], 3 - QUAD $0x1f3e74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r15 + 31], 3 - QUAD $0x1c067c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r14 + rax + 28], 4 - QUAD $0x1d064c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r14 + rax + 29], 4 - QUAD $0x1e0654203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r14 + rax + 30], 4 - QUAD $0x1f0674203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rax + 31], 4 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x1c0e7c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r14 + r9 + 28], 5 - QUAD $0x1d0e4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r9 + 29], 5 - QUAD $0x1e0e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r9 + 30], 5 - QUAD $0x1f0e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r9 + 31], 5 - QUAD $0x1c1e7c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r14 + r11 + 28], 6 - QUAD $0x1d1e4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r14 + r11 + 29], 6 - QUAD $0x1e1e54203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r11 + 30], 6 - QUAD $0x1f1e74203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r11 + 31], 6 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x1c067c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r14 + r8 + 28], 7 - QUAD $0x1d064c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r8 + 29], 7 - QUAD $0x1e0654203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r14 + r8 + 30], 7 - QUAD $0x1f0674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r8 + 31], 7 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - QUAD $0x1c367c203a0f4566; BYTE $0x08 // pinsrb xmm15, byte [r14 + rsi + 28], 8 - QUAD $0x1d364c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r14 + rsi + 29], 8 - QUAD $0x1e3654203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rsi + 30], 8 - QUAD $0x1f3674203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r14 + rsi + 31], 8 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x1c0e7c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r14 + rcx + 28], 9 - QUAD $0x1d0e4c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r14 + rcx + 29], 9 - QUAD $0x1e0e54203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r14 + rcx + 30], 9 - QUAD $0x1f0e74203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r14 + rcx + 31], 9 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x1c167c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r14 + r10 + 28], 10 - QUAD $0x1d164c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r14 + r10 + 29], 10 - QUAD $0x1e1654203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r10 + 30], 10 - QUAD $0x1f1674203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r10 + 31], 10 - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - QUAD $0x1c167c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r14 + rdx + 28], 11 - QUAD $0x1d164c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rdx + 29], 11 - QUAD $0x1e1654203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r14 + rdx + 30], 11 - QUAD $0x1f1674203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r14 + rdx + 31], 11 - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - QUAD $0x1c3e7c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r14 + rdi + 28], 12 - QUAD $0x1d3e4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r14 + rdi + 29], 12 - QUAD $0x1e3e54203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r14 + rdi + 30], 12 - QUAD $0x1f3e74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rdi + 31], 12 - QUAD $0x1c2e7c203a0f4766; BYTE $0x0d // pinsrb xmm15, byte [r14 + r13 + 28], 13 - QUAD $0x1d2e4c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r14 + r13 + 29], 13 - QUAD $0x1e2e54203a0f4766; BYTE $0x0d // pinsrb xmm10, byte [r14 + r13 + 30], 13 - QUAD $0x1f2e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r13 + 31], 13 - QUAD $0x1c267c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r14 + r12 + 28], 14 - QUAD $0x1d264c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r14 + r12 + 29], 14 - QUAD $0x1e2654203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r14 + r12 + 30], 14 - QUAD $0x1f2674203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r14 + r12 + 31], 14 - QUAD $0x1c1e7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r14 + rbx + 28], 15 - QUAD $0x1d1e4c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r14 + rbx + 29], 15 - QUAD $0x1e1e54203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rbx + 30], 15 - LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 - QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI5_19] */ - LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 - QUAD $0x1f1e74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rbx + 31], 15 - QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI5_22] */ - LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 - LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 - LONG $0xdf0f4466; BYTE $0xcd // pandn xmm9, xmm5 - LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 - LONG $0xdf0f4466; BYTE $0xd7 // pandn xmm10, xmm7 - LONG $0xeb0f4566; BYTE $0xd1 // por xmm10, xmm9 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - LONG $0xf4df0f66 // pandn xmm6, xmm4 - LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0xe8ef0f66 // pxor xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0x7cc40f66; WORD $0x060a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 6], 1 + QUAD $0x02060a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 6], 2 + QUAD $0x03063a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 6], 3 + QUAD $0x0406227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 6], 4 + QUAD $0x05062a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 6], 5 + LONG $0x7cc40f66; WORD $0x0632; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 6], 6 + QUAD $0x0706027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 6], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x01080a44c40f4466 // pinsrw xmm8, word [rdx + rcx + 8], 1 + QUAD $0x02080a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 8], 2 + QUAD $0x03083a44c40f4666 // pinsrw xmm8, word [rdx + r15 + 8], 3 + QUAD $0x04082244c40f4666 // pinsrw xmm8, word [rdx + r12 + 8], 4 + QUAD $0x05082a44c40f4666 // pinsrw xmm8, word [rdx + r13 + 8], 5 + QUAD $0x06083244c40f4466 // pinsrw xmm8, word [rdx + rsi + 8], 6 + QUAD $0x07080244c40f4666 // pinsrw xmm8, word [rdx + r8 + 8], 7 + LONG $0xddf80f66 // psubb xmm3, xmm5 + QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI5_10] */ + LONG $0xc76f0f66 // movdqa xmm0, xmm7 + LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 + LONG $0xfb6e0f66 // movd xmm7, ebx + LONG $0x44b70f42; WORD $0x1a32 // movzx eax, word [rdx + r14 + 26] + LONG $0x750f4566; BYTE $0xc3 // pcmpeqw xmm8, xmm11 + LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 + LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 + QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI5_11] */ LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0xc6600f66 // punpcklbw xmm0, xmm6 - QUAD $0x0000f0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 240] - LONG $0xcb6f0f66 // movdqa xmm1, xmm3 - QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] - LONG $0xcc600f66 // punpcklbw xmm1, xmm4 - LONG $0xd16f0f66 // movdqa xmm2, xmm1 - LONG $0xd0610f66 // punpcklwd xmm2, xmm0 - LONG $0xc8690f66 // punpckhwd xmm1, xmm0 - LONG $0x680f4466; BYTE $0xc6 // punpckhbw xmm8, xmm6 - LONG $0xdc680f66 // punpckhbw xmm3, xmm4 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0xf76e0f66 // movd xmm6, edi + LONG $0x54b70f46; WORD $0x1c32 // movzx r10d, word [rdx + r14 + 28] + LONG $0x64c40f66; WORD $0x0a0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 10], 1 + QUAD $0x020a0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 10], 2 + QUAD $0x030a3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 10], 3 + QUAD $0x040a2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 10], 4 + QUAD $0x050a2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 10], 5 + LONG $0x64c40f66; WORD $0x0a32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 10], 6 + QUAD $0x070a0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 10], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0x54c40f66; WORD $0x0c0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 12], 1 + QUAD $0x020c0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 12], 2 + QUAD $0x030c3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 12], 3 + QUAD $0x040c2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 12], 4 + QUAD $0x050c2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 12], 5 + LONG $0x54c40f66; WORD $0x0c32; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 12], 6 + LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI5_12] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x646e0f66; WORD $0x1824 // movd xmm4, dword [rsp + 24] + LONG $0x5cb70f42; WORD $0x1e32 // movzx ebx, word [rdx + r14 + 30] + QUAD $0x070c0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 12], 7 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 + QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI5_13] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0x5c6e0f66; WORD $0x1024 // movd xmm3, dword [rsp + 16] + LONG $0x7cb70f42; WORD $0x2032 // movzx edi, word [rdx + r14 + 32] + LONG $0x10247c89 // mov dword [rsp + 16], edi + LONG $0x4cc40f66; WORD $0x0e0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 14], 1 + QUAD $0x020e0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 14], 2 + QUAD $0x030e3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 14], 3 + QUAD $0x040e224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 14], 4 + QUAD $0x050e2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 14], 5 + LONG $0x4cc40f66; WORD $0x0e32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 14], 6 + LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x7cb70f42; WORD $0x2232 // movzx edi, word [rdx + r14 + 34] + LONG $0x18247c89 // mov dword [rsp + 24], edi + QUAD $0x070e024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 14], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0x74c40f66; WORD $0x120a; BYTE $0x01 // pinsrw xmm6, word [rdx + rcx + 18], 1 + QUAD $0x02120a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 18], 2 + QUAD $0x03123a74c40f4266 // pinsrw xmm6, word [rdx + r15 + 18], 3 + QUAD $0x04122274c40f4266 // pinsrw xmm6, word [rdx + r12 + 18], 4 + QUAD $0x05122a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 18], 5 + LONG $0x74c40f66; WORD $0x1232; BYTE $0x06 // pinsrw xmm6, word [rdx + rsi + 18], 6 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + QUAD $0x07120274c40f4266 // pinsrw xmm6, word [rdx + r8 + 18], 7 + LONG $0x750f4166; BYTE $0xf3 // pcmpeqw xmm6, xmm11 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 + QUAD $0x0000e0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 224[rbp] /* [rip + .LCPI5_14] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 + LONG $0x6f0f4566; BYTE $0xc1 // movdqa xmm8, xmm9 + LONG $0xc66f0f66 // movdqa xmm0, xmm6 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x5cb70f46; WORD $0x2432 // movzx r11d, word [rdx + r14 + 36] + LONG $0x7cc40f66; WORD $0x100a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 16], 1 + QUAD $0x02100a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 16], 2 + QUAD $0x03103a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 16], 3 + QUAD $0x0410227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 16], 4 + QUAD $0x05102a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 16], 5 + LONG $0x7cc40f66; WORD $0x1032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 16], 6 + LONG $0x64c40f66; WORD $0x140a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 20], 1 + QUAD $0x02140a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 20], 2 + QUAD $0x03143a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 20], 3 + QUAD $0x04142264c40f4266 // pinsrw xmm4, word [rdx + r12 + 20], 4 + QUAD $0x05142a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 20], 5 + LONG $0x64c40f66; WORD $0x1432; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 20], 6 + QUAD $0x07140264c40f4266 // pinsrw xmm4, word [rdx + r8 + 20], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x6f0f4166; BYTE $0xee // movdqa xmm5, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xe2 // movd xmm4, r10d + LONG $0x7cb70f42; WORD $0x2632 // movzx edi, word [rdx + r14 + 38] + QUAD $0x0710027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 16], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x5cc40f66; WORD $0x160a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 22], 1 + QUAD $0x02160a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 22], 2 + QUAD $0x03163a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 22], 3 + QUAD $0x0416225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 22], 4 + QUAD $0x05162a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 22], 5 + LONG $0x5cc40f66; WORD $0x1632; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 22], 6 + QUAD $0x0716025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 22], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0x54c40f66; WORD $0x180a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 24], 1 + QUAD $0x02180a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 24], 2 + QUAD $0x03183a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 24], 3 + QUAD $0x04182254c40f4266 // pinsrw xmm2, word [rdx + r12 + 24], 4 + QUAD $0x05182a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 24], 5 + LONG $0x54c40f66; WORD $0x1832; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 24], 6 + QUAD $0x07180254c40f4266 // pinsrw xmm2, word [rdx + r8 + 24], 7 + LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 + QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI5_10] */ + LONG $0x6f0f4566; BYTE $0xf2 // movdqa xmm14, xmm10 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 + LONG $0xdb6e0f66 // movd xmm3, ebx + LONG $0x44b70f42; WORD $0x2832 // movzx eax, word [rdx + r14 + 40] + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4466; BYTE $0xf5 // por xmm14, xmm5 + QUAD $0x0000b08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 176[rbp] /* [rip + .LCPI5_11] */ + LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0x7c6e0f66; WORD $0x1024 // movd xmm7, dword [rsp + 16] + LONG $0x54b70f46; WORD $0x2a32 // movzx r10d, word [rdx + r14 + 42] + LONG $0x4cc40f66; WORD $0x1a0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 26], 1 + QUAD $0x021a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 26], 2 + QUAD $0x031a3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 26], 3 + QUAD $0x041a224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 26], 4 + QUAD $0x051a2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 26], 5 + LONG $0x4cc40f66; WORD $0x1a32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 26], 6 + QUAD $0x071a024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 26], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x64c40f66; WORD $0x1c0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 28], 1 + QUAD $0x021c0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 28], 2 + QUAD $0x031c3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 28], 3 + QUAD $0x041c2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 28], 4 + QUAD $0x051c2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 28], 5 + LONG $0x64c40f66; WORD $0x1c32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 28], 6 + LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI5_12] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x546e0f66; WORD $0x1824 // movd xmm2, dword [rsp + 24] + LONG $0x5cb70f42; WORD $0x2c32 // movzx ebx, word [rdx + r14 + 44] + LONG $0x10245c89 // mov dword [rsp + 16], ebx + QUAD $0x071c0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 28], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 + QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI5_13] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x5cb70f42; WORD $0x2e32 // movzx ebx, word [rdx + r14 + 46] + LONG $0x18245c89 // mov dword [rsp + 24], ebx + LONG $0x5cc40f66; WORD $0x1e0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 30], 1 + QUAD $0x021e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 30], 2 + QUAD $0x031e3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 30], 3 + QUAD $0x041e225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 30], 4 + QUAD $0x051e2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 30], 5 + LONG $0x5cc40f66; WORD $0x1e32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 30], 6 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0xcf6e0f66 // movd xmm1, edi + LONG $0x7cb70f42; WORD $0x3032 // movzx edi, word [rdx + r14 + 48] + QUAD $0x071e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 30], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0x54c40f66; WORD $0x220a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 34], 1 + QUAD $0x02220a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 34], 2 + QUAD $0x03223a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 34], 3 + QUAD $0x04222254c40f4266 // pinsrw xmm2, word [rdx + r12 + 34], 4 + QUAD $0x05222a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 34], 5 + LONG $0x54c40f66; WORD $0x2232; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 34], 6 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + QUAD $0x07220254c40f4266 // pinsrw xmm2, word [rdx + r8 + 34], 7 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 + QUAD $0x0000e0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 224[rbp] /* [rip + .LCPI5_14] */ + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + QUAD $0x000080856f0f4466; BYTE $0x00 // movdqa xmm8, oword 128[rbp] /* [rip + .LCPI5_8] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x5cb70f46; WORD $0x3232 // movzx r11d, word [rdx + r14 + 50] + LONG $0x7cc40f66; WORD $0x200a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 32], 1 + QUAD $0x02200a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 32], 2 + QUAD $0x03203a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 32], 3 + QUAD $0x0420227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 32], 4 + QUAD $0x05202a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 32], 5 + LONG $0x7cc40f66; WORD $0x2032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 32], 6 + LONG $0x64c40f66; WORD $0x240a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 36], 1 + QUAD $0x02240a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 36], 2 + QUAD $0x03243a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 36], 3 + QUAD $0x04242264c40f4266 // pinsrw xmm4, word [rdx + r12 + 36], 4 + QUAD $0x05242a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 36], 5 + LONG $0x64c40f66; WORD $0x2432; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 36], 6 + QUAD $0x07240264c40f4266 // pinsrw xmm4, word [rdx + r8 + 36], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 + QUAD $0x00000090b56f0f66 // movdqa xmm6, oword 144[rbp] /* [rip + .LCPI5_9] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x54b70f46; WORD $0x3432 // movzx r10d, word [rdx + r14 + 52] + QUAD $0x0720027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 32], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x4cc40f66; WORD $0x260a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 38], 1 + QUAD $0x02260a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 38], 2 + QUAD $0x03263a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 38], 3 + QUAD $0x0426224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 38], 4 + QUAD $0x05262a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 38], 5 + LONG $0x4cc40f66; WORD $0x2632; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 38], 6 + QUAD $0x0726024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 38], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x54c40f66; WORD $0x280a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 40], 1 + QUAD $0x02280a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 40], 2 + QUAD $0x03283a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 40], 3 + QUAD $0x04282254c40f4266 // pinsrw xmm2, word [rdx + r12 + 40], 4 + QUAD $0x05282a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 40], 5 + LONG $0x54c40f66; WORD $0x2832; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 40], 6 + QUAD $0x07280254c40f4266 // pinsrw xmm2, word [rdx + r8 + 40], 7 + LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 + LONG $0x6f0f4166; BYTE $0xea // movdqa xmm5, xmm10 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x4c6e0f66; WORD $0x1024 // movd xmm1, dword [rsp + 16] + LONG $0x44b70f42; WORD $0x3632 // movzx eax, word [rdx + r14 + 54] + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x6f0f4166; BYTE $0xf1 // movdqa xmm6, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x646e0f66; WORD $0x1824 // movd xmm4, dword [rsp + 24] + LONG $0x5cb70f42; WORD $0x3832 // movzx ebx, word [rdx + r14 + 56] + LONG $0x5cc40f66; WORD $0x2a0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 42], 1 + QUAD $0x022a0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 42], 2 + QUAD $0x032a3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 42], 3 + QUAD $0x042a225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 42], 4 + QUAD $0x052a2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 42], 5 + LONG $0x5cc40f66; WORD $0x2a32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 42], 6 + QUAD $0x072a025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 42], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0x4cc40f66; WORD $0x2c0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 44], 1 + QUAD $0x022c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 44], 2 + QUAD $0x032c3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 44], 3 + QUAD $0x042c224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 44], 4 + QUAD $0x052c2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 44], 5 + LONG $0x4cc40f66; WORD $0x2c32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 44], 6 + LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 + QUAD $0x0000c08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 192[rbp] /* [rip + .LCPI5_12] */ + LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4166; WORD $0xd710 // pblendvb xmm2, xmm15, xmm0 + LONG $0xff6e0f66 // movd xmm7, edi + LONG $0x7cb70f42; WORD $0x3a32 // movzx edi, word [rdx + r14 + 58] + QUAD $0x072c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 44], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0x0000d0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 208[rbp] /* [rip + .LCPI5_13] */ + LONG $0x6f0f4166; BYTE $0xf2 // movdqa xmm6, xmm10 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + LONG $0x5cb70f46; WORD $0x3c32 // movzx r11d, word [rdx + r14 + 60] + LONG $0xf2eb0f66 // por xmm6, xmm2 + LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d + LONG $0x64c40f66; WORD $0x2e0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 46], 1 + QUAD $0x022e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 46], 2 + QUAD $0x032e3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 46], 3 + QUAD $0x042e2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 46], 4 + QUAD $0x052e2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 46], 5 + LONG $0x64c40f66; WORD $0x2e32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 46], 6 + QUAD $0x072e0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 46], 7 + LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0x6f0f4566; BYTE $0xc6 // movdqa xmm8, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xd86e0f66 // movd xmm3, eax + LONG $0x4cc40f66; WORD $0x320a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 50], 1 + QUAD $0x02320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 2 + QUAD $0x03323a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 50], 3 + QUAD $0x0432224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 50], 4 + QUAD $0x05322a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 50], 5 + LONG $0x4cc40f66; WORD $0x3232; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 50], 6 + QUAD $0x0732024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 50], 7 + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 + QUAD $0x00000080a56f0f66 // movdqa xmm4, oword 128[rbp] /* [rip + .LCPI5_8] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 + LONG $0xcb6e0f66 // movd xmm1, ebx + LONG $0x7cc40f66; WORD $0x300a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 48], 1 + QUAD $0x02300a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 48], 2 + QUAD $0x03303a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 48], 3 + QUAD $0x0430227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 48], 4 + QUAD $0x05302a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 48], 5 + LONG $0x7cc40f66; WORD $0x3032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 48], 6 + QUAD $0x0730027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 48], 7 + LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0x54c40f66; WORD $0x340a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 52], 1 + QUAD $0x02340a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 52], 2 + QUAD $0x03343a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 52], 3 + QUAD $0x04342254c40f4266 // pinsrw xmm2, word [rdx + r12 + 52], 4 + QUAD $0x05342a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 52], 5 + LONG $0x54c40f66; WORD $0x3432; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 52], 6 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x07340254c40f4266 // pinsrw xmm2, word [rdx + r8 + 52], 7 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0x5cc40f66; WORD $0x360a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 54], 1 + QUAD $0x02360a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 54], 2 + QUAD $0x03363a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 54], 3 + QUAD $0x0436225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 54], 4 + QUAD $0x05362a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 54], 5 + LONG $0x5cc40f66; WORD $0x3632; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 54], 6 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x0736025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 54], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0x4cc40f66; WORD $0x380a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 56], 1 + QUAD $0x02380a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 56], 2 + QUAD $0x03383a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 56], 3 + QUAD $0x0438224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 56], 4 + QUAD $0x05382a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 56], 5 + LONG $0x4cc40f66; WORD $0x3832; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 56], 6 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + QUAD $0x0738024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 56], 7 + LONG $0xe7f80f66 // psubb xmm4, xmm7 + QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI5_9] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + QUAD $0x000000a0b56f0f66 // movdqa xmm6, oword 160[rbp] /* [rip + .LCPI5_10] */ LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xd8 // punpckhwd xmm3, xmm8 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0xd76e0f66 // movd xmm2, edi + LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 + LONG $0x54c40f66; WORD $0x3a0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 58], 1 + QUAD $0x023a0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 58], 2 + QUAD $0x033a3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 58], 3 + QUAD $0x043a2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 58], 4 + QUAD $0x053a2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 58], 5 + LONG $0x54c40f66; WORD $0x3a32; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 58], 6 + QUAD $0x073a0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 58], 7 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d + LONG $0x5cc40f66; WORD $0x3c0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 60], 1 + QUAD $0x023c0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 60], 2 + QUAD $0x033c3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 60], 3 + QUAD $0x043c225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 60], 4 + QUAD $0x053c2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 60], 5 + LONG $0x5cc40f66; WORD $0x3c32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 60], 6 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x073c025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 60], 7 + LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf4eb0f66 // por xmm6, xmm4 + QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI5_11] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 + LONG $0x6f0f4166; BYTE $0xc9 // movdqa xmm1, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xcf10 // pblendvb xmm1, xmm15, xmm0 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xd710 // pblendvb xmm10, xmm15, xmm0 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0x44b70f42; WORD $0x3e32 // movzx eax, word [rdx + r14 + 62] + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x44c40f66; WORD $0x3e0a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 62], 1 + QUAD $0x023e0a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 62], 2 + QUAD $0x033e3a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 62], 3 + QUAD $0x043e2244c40f4266 // pinsrw xmm0, word [rdx + r12 + 62], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x053e2a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 62], 5 + LONG $0x44c40f66; WORD $0x3e32; BYTE $0x06 // pinsrw xmm0, word [rdx + rsi + 62], 6 + QUAD $0x073e0244c40f4266 // pinsrw xmm0, word [rdx + r8 + 62], 7 + LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xeb0f4466; BYTE $0xd6 // por xmm10, xmm6 + LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 + LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 + LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 + LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 + LONG $0x6c0f4166; BYTE $0xd6 // punpcklqdq xmm2, xmm14 + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI5_15] */ + LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 + LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 + LONG $0xc2610f66 // punpcklwd xmm0, xmm2 + LONG $0x600f4566; BYTE $0xc6 // punpcklbw xmm8, xmm14 + LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 + LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + LONG $0x7f0f44f3; WORD $0x8824 // movdqu oword [rax + 4*rcx], xmm12 + LONG $0x447f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm0 + LONG $0x08c18348 // add rcx, 8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] + JNE LBB5_209 QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x5c7f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm3 - LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 - LONG $0x4c7f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm1 - LONG $0x147f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm2 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB5_87 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x000000e824943b4c // cmp r10, qword [rsp + 232] - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - JNE LBB5_89 - JMP LBB5_92 + LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x24748b44; BYTE $0x0c // mov r14d, dword [rsp + 12] + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + JNE LBB5_84 + JMP LBB5_139 + +LBB5_211: + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0xfce18349 // and r9, -4 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + LONG $0x07e3c148 // shl rbx, 7 + WORD $0x0148; BYTE $0xd3 // add rbx, rdx + LONG $0x8c2c8d4f // lea r13, [r12 + 4*r9] + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0x00c8c60f // shufps xmm1, xmm0, 0 + LONG $0xfcc28148; WORD $0x0001; BYTE $0x00 // add rdx, 508 + WORD $0xf631 // xor esi, esi + LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI5_0] */ + LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI5_1] */ + LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI5_2] */ + LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI5_3] */ + LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI5_4] */ + LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI5_5] */ + LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI5_6] */ + LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI5_7] */ + +LBB5_212: + QUAD $0xfffffe04b2100ff3 // movss xmm6, dword [rdx - 508] + QUAD $0xfffffe08ba100ff3 // movss xmm7, dword [rdx - 504] + QUAD $0xfffffe0caa100ff3 // movss xmm5, dword [rdx - 500] + QUAD $0xfffffe10a2100ff3 // movss xmm4, dword [rdx - 496] + QUAD $0xfffe84b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 380], 16 + QUAD $0xffff04b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 252], 32 + LONG $0x213a0f66; WORD $0x8472; BYTE $0x30 // insertps xmm6, dword [rdx - 124], 48 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + QUAD $0xfffe88ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 376], 16 + QUAD $0xffff08ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 248], 32 + LONG $0x213a0f66; WORD $0x887a; BYTE $0x30 // insertps xmm7, dword [rdx - 120], 48 + QUAD $0xfffe8caa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 372], 16 + QUAD $0xffff0caa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 244], 32 + LONG $0x213a0f66; WORD $0x8c6a; BYTE $0x30 // insertps xmm5, dword [rdx - 116], 48 + QUAD $0xfffe90a2213a0f66; WORD $0x10ff // insertps xmm4, dword [rdx - 368], 16 + QUAD $0xffff10a2213a0f66; WORD $0x20ff // insertps xmm4, dword [rdx - 240], 32 + LONG $0x213a0f66; WORD $0x9062; BYTE $0x30 // insertps xmm4, dword [rdx - 112], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xd76f0f66 // movdqa xmm2, xmm7 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xd7f80f66 // psubb xmm2, xmm7 + QUAD $0xfffffe14ba100ff3 // movss xmm7, dword [rdx - 492] + QUAD $0xfffe94ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 364], 16 + QUAD $0xffff14ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 236], 32 + LONG $0x213a0f66; WORD $0x947a; BYTE $0x30 // insertps xmm7, dword [rdx - 108], 48 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe18b2100ff3 // movss xmm6, dword [rdx - 488] + QUAD $0xfffe98b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 360], 16 + QUAD $0xffff18b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 232], 32 + LONG $0x213a0f66; WORD $0x9872; BYTE $0x30 // insertps xmm6, dword [rdx - 104], 48 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 + LONG $0xeaeb0f66 // por xmm5, xmm2 + QUAD $0xfffffe1c9a100ff3 // movss xmm3, dword [rdx - 484] + QUAD $0xfffe9c9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 356], 16 + QUAD $0xffff1c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 228], 32 + LONG $0x213a0f66; WORD $0x9c5a; BYTE $0x30 // insertps xmm3, dword [rdx - 100], 48 + LONG $0x04e1c20f // cmpneqps xmm4, xmm1 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + LONG $0xf4710f66; BYTE $0x03 // psllw xmm4, 3 + LONG $0xdb0f4166; BYTE $0xe2 // pand xmm4, xmm10 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x04 // psllw xmm7, 4 + LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 + LONG $0xfceb0f66 // por xmm7, xmm4 + QUAD $0xfffffe20a2100ff3 // movss xmm4, dword [rdx - 480] + QUAD $0xfffea0a2213a0f66; WORD $0x10ff // insertps xmm4, dword [rdx - 352], 16 + QUAD $0xffff20a2213a0f66; WORD $0x20ff // insertps xmm4, dword [rdx - 224], 32 + LONG $0x213a0f66; WORD $0xa062; BYTE $0x30 // insertps xmm4, dword [rdx - 96], 48 + LONG $0xfdeb0f66 // por xmm7, xmm5 + QUAD $0xfffffe24aa100ff3 // movss xmm5, dword [rdx - 476] + QUAD $0xfffea4aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 348], 16 + QUAD $0xffff24aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 220], 32 + LONG $0x213a0f66; WORD $0xa46a; BYTE $0x30 // insertps xmm5, dword [rdx - 92], 48 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 + LONG $0xdb0f4166; BYTE $0xdd // pand xmm3, xmm13 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe2892100ff3 // movss xmm2, dword [rdx - 472] + QUAD $0xfffea892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 344], 16 + QUAD $0xffff2892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 216], 32 + LONG $0x213a0f66; WORD $0xa852; BYTE $0x30 // insertps xmm2, dword [rdx - 88], 48 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0x04e1c20f // cmpneqps xmm4, xmm1 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 + LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 + LONG $0xe3eb0f66 // por xmm4, xmm3 + QUAD $0xfffffe2c9a100ff3 // movss xmm3, dword [rdx - 468] + QUAD $0xfffeac9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 340], 16 + QUAD $0xffff2c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 212], 32 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0x213a0f66; WORD $0xac5a; BYTE $0x30 // insertps xmm3, dword [rdx - 84], 48 + LONG $0xe7eb0f66 // por xmm4, xmm7 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf26f0f66 // movdqa xmm6, xmm2 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf2f80f66 // psubb xmm6, xmm2 + QUAD $0xfffffe30ba100ff3 // movss xmm7, dword [rdx - 464] + QUAD $0xfffeb0ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 336], 16 + QUAD $0xffff30ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 208], 32 + LONG $0x213a0f66; WORD $0xb07a; BYTE $0x30 // insertps xmm7, dword [rdx - 80], 48 + LONG $0xf5eb0f66 // por xmm6, xmm5 + QUAD $0xfffffe34aa100ff3 // movss xmm5, dword [rdx - 460] + QUAD $0xfffeb4aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 332], 16 + QUAD $0xffff34aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 204], 32 + LONG $0x213a0f66; WORD $0xb46a; BYTE $0x30 // insertps xmm5, dword [rdx - 76], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe38b2100ff3 // movss xmm6, dword [rdx - 456] + QUAD $0xfffeb8b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 328], 16 + QUAD $0xffff38b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 200], 32 + LONG $0x213a0f66; WORD $0xb872; BYTE $0x30 // insertps xmm6, dword [rdx - 72], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x03 // psllw xmm7, 3 + LONG $0xdb0f4166; BYTE $0xfa // pand xmm7, xmm10 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 + LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 + LONG $0xefeb0f66 // por xmm5, xmm7 + QUAD $0xfffffe3c92100ff3 // movss xmm2, dword [rdx - 452] + QUAD $0xfffebc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 324], 16 + QUAD $0xffff3c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 196], 32 + LONG $0x213a0f66; WORD $0xbc52; BYTE $0x30 // insertps xmm2, dword [rdx - 68], 48 + LONG $0xebeb0f66 // por xmm5, xmm3 + QUAD $0xfffffe40ba100ff3 // movss xmm7, dword [rdx - 448] + QUAD $0xfffec0ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 320], 16 + QUAD $0xffff40ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 192], 32 + LONG $0x213a0f66; WORD $0xc07a; BYTE $0x30 // insertps xmm7, dword [rdx - 64], 48 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe44b2100ff3 // movss xmm6, dword [rdx - 444] + QUAD $0xfffec4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 316], 16 + QUAD $0xffff44b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 188], 32 + LONG $0x213a0f66; WORD $0xc472; BYTE $0x30 // insertps xmm6, dword [rdx - 60], 48 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xf7710f66; BYTE $0x07 // psllw xmm7, 7 + LONG $0xdb0f4166; BYTE $0xfe // pand xmm7, xmm14 + LONG $0xfaeb0f66 // por xmm7, xmm2 + QUAD $0xfffffe4892100ff3 // movss xmm2, dword [rdx - 440] + QUAD $0xfffec892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 312], 16 + QUAD $0xffff4892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 184], 32 + LONG $0x213a0f66; WORD $0xc852; BYTE $0x30 // insertps xmm2, dword [rdx - 56], 48 + LONG $0xfdeb0f66 // por xmm7, xmm5 + QUAD $0xfffffe4c9a100ff3 // movss xmm3, dword [rdx - 436] + QUAD $0xfffecc9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 308], 16 + QUAD $0xffff4c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 180], 32 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0x213a0f66; WORD $0xcc5a; BYTE $0x30 // insertps xmm3, dword [rdx - 52], 48 + LONG $0xe7620f66 // punpckldq xmm4, xmm7 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xfa6f0f66 // movdqa xmm7, xmm2 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xfaf80f66 // psubb xmm7, xmm2 + QUAD $0xfffffe50aa100ff3 // movss xmm5, dword [rdx - 432] + QUAD $0xfffed0aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 304], 16 + QUAD $0xffff50aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 176], 32 + LONG $0x213a0f66; WORD $0xd06a; BYTE $0x30 // insertps xmm5, dword [rdx - 48], 48 + LONG $0xfeeb0f66 // por xmm7, xmm6 + QUAD $0xfffffe54b2100ff3 // movss xmm6, dword [rdx - 428] + QUAD $0xfffed4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 300], 16 + QUAD $0xffff54b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 172], 32 + LONG $0x213a0f66; WORD $0xd472; BYTE $0x30 // insertps xmm6, dword [rdx - 44], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdfeb0f66 // por xmm3, xmm7 + QUAD $0xfffffe58ba100ff3 // movss xmm7, dword [rdx - 424] + QUAD $0xfffed8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 296], 16 + QUAD $0xffff58ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 168], 32 + LONG $0x213a0f66; WORD $0xd87a; BYTE $0x30 // insertps xmm7, dword [rdx - 40], 48 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 + LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf5eb0f66 // por xmm6, xmm5 + QUAD $0xfffffe5c92100ff3 // movss xmm2, dword [rdx - 420] + QUAD $0xfffedc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 292], 16 + QUAD $0xffff5c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 164], 32 + LONG $0x213a0f66; WORD $0xdc52; BYTE $0x30 // insertps xmm2, dword [rdx - 36], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe60aa100ff3 // movss xmm5, dword [rdx - 416] + QUAD $0xfffee0aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 288], 16 + QUAD $0xffff60aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 160], 32 + LONG $0x213a0f66; WORD $0xe06a; BYTE $0x30 // insertps xmm5, dword [rdx - 32], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe64ba100ff3 // movss xmm7, dword [rdx - 412] + QUAD $0xfffee4ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 284], 16 + QUAD $0xffff64ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 156], 32 + LONG $0x213a0f66; WORD $0xe47a; BYTE $0x30 // insertps xmm7, dword [rdx - 28], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x04e9c20f // cmpneqps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xf5710f66; BYTE $0x07 // psllw xmm5, 7 + LONG $0xdb0f4166; BYTE $0xee // pand xmm5, xmm14 + LONG $0xeaeb0f66 // por xmm5, xmm2 + QUAD $0xfffffe6892100ff3 // movss xmm2, dword [rdx - 408] + QUAD $0xfffee892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 280], 16 + QUAD $0xffff6892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 152], 32 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0x213a0f66; WORD $0xe852; BYTE $0x30 // insertps xmm2, dword [rdx - 24], 48 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf26f0f66 // movdqa xmm6, xmm2 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf2f80f66 // psubb xmm6, xmm2 + QUAD $0xfffffe6c9a100ff3 // movss xmm3, dword [rdx - 404] + QUAD $0xfffeec9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 276], 16 + QUAD $0xffff6c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 148], 32 + LONG $0x213a0f66; WORD $0xec5a; BYTE $0x30 // insertps xmm3, dword [rdx - 20], 48 + LONG $0xf7eb0f66 // por xmm6, xmm7 + QUAD $0xfffffe7092100ff3 // movss xmm2, dword [rdx - 400] + QUAD $0xfffef092213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 272], 16 + QUAD $0xffff7092213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 144], 32 + LONG $0x213a0f66; WORD $0xf052; BYTE $0x30 // insertps xmm2, dword [rdx - 16], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe74b2100ff3 // movss xmm6, dword [rdx - 396] + QUAD $0xfffef4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 268], 16 + QUAD $0xffff74b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 140], 32 + LONG $0x213a0f66; WORD $0xf472; BYTE $0x30 // insertps xmm6, dword [rdx - 12], 48 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0x04f1c20f // cmpneqps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf2eb0f66 // por xmm6, xmm2 + QUAD $0xfffffe78ba100ff3 // movss xmm7, dword [rdx - 392] + QUAD $0xfffef8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 264], 16 + QUAD $0xffff78ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 136], 32 + LONG $0x213a0f66; WORD $0xf87a; BYTE $0x30 // insertps xmm7, dword [rdx - 8], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe7c92100ff3 // movss xmm2, dword [rdx - 388] + QUAD $0xfffefc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 260], 16 + QUAD $0xffff7c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 132], 32 + LONG $0x213a0f66; WORD $0xfc52; BYTE $0x30 // insertps xmm2, dword [rdx - 4], 48 + LONG $0x04f9c20f // cmpneqps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x04d1c20f // cmpneqps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe809a100ff3 // movss xmm3, dword [rdx - 384] + QUAD $0xffff009a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 256], 16 + LONG $0x213a0f66; WORD $0x805a; BYTE $0x20 // insertps xmm3, dword [rdx - 128], 32 + LONG $0x213a0f66; WORD $0x301a // insertps xmm3, dword [rdx], 48 + LONG $0x04d9c20f // cmpneqps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0xdeeb0f66 // por xmm3, xmm6 + LONG $0xeb620f66 // punpckldq xmm5, xmm3 + LONG $0xe5600f66 // punpcklbw xmm4, xmm5 + LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 + LONG $0x7f0f41f3; WORD $0xb424 // movdqu oword [r12 + 4*rsi], xmm4 + LONG $0x04c68348 // add rsi, 4 + LONG $0x00c28148; WORD $0x0002; BYTE $0x00 // add rdx, 512 + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB5_212 + WORD $0x394c; BYTE $0xc9 // cmp rcx, r9 + JNE LBB5_111 + JMP LBB5_143 -LBB5_67: - LONG $0xf0e28349 // and r10, -16 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 +LBB5_214: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - QUAD $0x0000011024848948 // mov qword [rsp + 272], rax - QUAD $0x000000e82494894c // mov qword [rsp + 232], r10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0x014c; BYTE $0xe8 // add rax, r13 + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + QUAD $0x000000a8248c8948 // mov qword [rsp + 168], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + LONG $0xc6b60f41 // movzx eax, r14b LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 WORD $0xc031 // xor eax, eax + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 -LBB5_68: - QUAD $0x000000a824848948 // mov qword [rsp + 168], rax +LBB5_215: + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax LONG $0x05e0c148 // shl rax, 5 - WORD $0x8949; BYTE $0xc5 // mov r13, rax - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - WORD $0x8949; BYTE $0xc7 // mov r15, rax WORD $0x8948; BYTE $0xc3 // mov rbx, rax - WORD $0x8949; BYTE $0xc2 // mov r10, rax - WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + WORD $0x8949; BYTE $0xc3 // mov r11, rax WORD $0x8949; BYTE $0xc0 // mov r8, rax + WORD $0x8948; BYTE $0xc7 // mov rdi, rax WORD $0x8949; BYTE $0xc4 // mov r12, rax + WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + WORD $0x8949; BYTE $0xc6 // mov r14, rax WORD $0x8948; BYTE $0xc2 // mov rdx, rax - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax - LONG $0x0cb60f41; BYTE $0x06 // movzx ecx, byte [r14 + rax] + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + LONG $0x4cb60f41; WORD $0x0005 // movzx ecx, byte [r13 + rax] LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x4cb60f41; WORD $0x0106 // movzx ecx, byte [r14 + rax + 1] + LONG $0x4cb60f41; WORD $0x0105 // movzx ecx, byte [r13 + rax + 1] LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x4cb60f41; WORD $0x0206 // movzx ecx, byte [r14 + rax + 2] + LONG $0x4cb60f41; WORD $0x0205 // movzx ecx, byte [r13 + rax + 2] LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x4cb60f41; WORD $0x0306 // movzx ecx, byte [r14 + rax + 3] + LONG $0x4cb60f41; WORD $0x0305 // movzx ecx, byte [r13 + rax + 3] LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x4cb60f41; WORD $0x0406 // movzx ecx, byte [r14 + rax + 4] + LONG $0x4cb60f41; WORD $0x0405 // movzx ecx, byte [r13 + rax + 4] LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x4cb60f41; WORD $0x0506 // movzx ecx, byte [r14 + rax + 5] + LONG $0x4cb60f41; WORD $0x0505 // movzx ecx, byte [r13 + rax + 5] LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x4cb60f41; WORD $0x0606 // movzx ecx, byte [r14 + rax + 6] + LONG $0x4cb60f41; WORD $0x0605 // movzx ecx, byte [r13 + rax + 6] LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x4cb60f41; WORD $0x0706 // movzx ecx, byte [r14 + rax + 7] + LONG $0x4cb60f41; WORD $0x0705 // movzx ecx, byte [r13 + rax + 7] LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x4cb60f41; WORD $0x0806 // movzx ecx, byte [r14 + rax + 8] + LONG $0x4cb60f41; WORD $0x0805 // movzx ecx, byte [r13 + rax + 8] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 - LONG $0x4cb60f41; WORD $0x0906 // movzx ecx, byte [r14 + rax + 9] + QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 + LONG $0x4cb60f41; WORD $0x0905 // movzx ecx, byte [r13 + rax + 9] LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x4cb60f41; WORD $0x0a06 // movzx ecx, byte [r14 + rax + 10] + LONG $0x4cb60f41; WORD $0x0a05 // movzx ecx, byte [r13 + rax + 10] LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x4cb60f41; WORD $0x0b06 // movzx ecx, byte [r14 + rax + 11] + LONG $0x4cb60f41; WORD $0x0b05 // movzx ecx, byte [r13 + rax + 11] LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x4cb60f41; WORD $0x0c06 // movzx ecx, byte [r14 + rax + 12] + LONG $0x4cb60f41; WORD $0x0c05 // movzx ecx, byte [r13 + rax + 12] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 - LONG $0x4cb60f41; WORD $0x0d06 // movzx ecx, byte [r14 + rax + 13] + QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 + LONG $0x4cb60f41; WORD $0x0d05 // movzx ecx, byte [r13 + rax + 13] LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x4cb60f41; WORD $0x0e06 // movzx ecx, byte [r14 + rax + 14] + LONG $0x4cb60f41; WORD $0x0e05 // movzx ecx, byte [r13 + rax + 14] LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x4cb60f41; WORD $0x0f06 // movzx ecx, byte [r14 + rax + 15] + LONG $0x4cb60f41; WORD $0x0f05 // movzx ecx, byte [r13 + rax + 15] LONG $0xc16e0f66 // movd xmm0, ecx QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - WORD $0x8949; BYTE $0xc3 // mov r11, rax - LONG $0x20cb8349 // or r11, 32 - LONG $0x245c894c; BYTE $0x10 // mov qword [rsp + 16], r11 - LONG $0x40cd8349 // or r13, 64 - LONG $0x60cf8348 // or rdi, 96 - LONG $0x80cf8149; WORD $0x0000; BYTE $0x00 // or r15, 128 - LONG $0xa0cb8148; WORD $0x0000; BYTE $0x00 // or rbx, 160 - LONG $0xc0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 192 + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + WORD $0x8949; BYTE $0xc7 // mov r15, rax + LONG $0x20cf8349 // or r15, 32 + LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 + LONG $0x40cb8348 // or rbx, 64 + LONG $0x60ce8348 // or rsi, 96 + LONG $0x24748948; BYTE $0x70 // mov qword [rsp + 112], rsi + LONG $0x80cb8149; WORD $0x0000; BYTE $0x00 // or r11, 128 + LONG $0xa0c88149; WORD $0x0000; BYTE $0x00 // or r8, 160 + LONG $0x2444894c; BYTE $0x38 // mov qword [rsp + 56], r8 + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0xc0c98148; WORD $0x0000; BYTE $0x00 // or rcx, 192 + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx + WORD $0x8949; BYTE $0xc1 // mov r9, rax LONG $0xe0c98149; WORD $0x0000; BYTE $0x00 // or r9, 224 - LONG $0x00c88149; WORD $0x0001; BYTE $0x00 // or r8, 256 - LONG $0x20cc8149; WORD $0x0001; BYTE $0x00 // or r12, 288 - LONG $0x40ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 320 - LONG $0x24548948; BYTE $0x70 // mov qword [rsp + 112], rdx - LONG $0x60ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 352 - QUAD $0x0000009824b48948 // mov qword [rsp + 152], rsi - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - LONG $0x80c98148; WORD $0x0001; BYTE $0x00 // or rcx, 384 - LONG $0x244c8948; BYTE $0x60 // mov qword [rsp + 96], rcx - WORD $0x8948; BYTE $0xc2 // mov rdx, rax - LONG $0xa0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 416 - LONG $0x24548948; BYTE $0x18 // mov qword [rsp + 24], rdx - WORD $0x8948; BYTE $0xc2 // mov rdx, rax - LONG $0xc0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 448 - LONG $0x24548948; BYTE $0x20 // mov qword [rsp + 32], rdx - WORD $0x8948; BYTE $0xc2 // mov rdx, rax - LONG $0xe0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 480 - LONG $0x24548948; BYTE $0x50 // mov qword [rsp + 80], rdx - QUAD $0x011e24203a0f4366 // pinsrb xmm4, byte [r14 + r11], 1 - LONG $0x246c894c; BYTE $0x30 // mov qword [rsp + 48], r13 - QUAD $0x022e24203a0f4366 // pinsrb xmm4, byte [r14 + r13], 2 - LONG $0x247c8948; BYTE $0x28 // mov qword [rsp + 40], rdi - QUAD $0x033e24203a0f4166 // pinsrb xmm4, byte [r14 + rdi], 3 - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - QUAD $0x043e24203a0f4366 // pinsrb xmm4, byte [r14 + r15], 4 - QUAD $0x00000080249c8948 // mov qword [rsp + 128], rbx - QUAD $0x051e24203a0f4166 // pinsrb xmm4, byte [r14 + rbx], 5 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x061624203a0f4366 // pinsrb xmm4, byte [r14 + r10], 6 - LONG $0x244c894c; BYTE $0x58 // mov qword [rsp + 88], r9 - QUAD $0x070e24203a0f4366 // pinsrb xmm4, byte [r14 + r9], 7 - LONG $0x2444894c; BYTE $0x48 // mov qword [rsp + 72], r8 - QUAD $0x080624203a0f4366 // pinsrb xmm4, byte [r14 + r8], 8 - WORD $0x894d; BYTE $0xe0 // mov r8, r12 - QUAD $0x092624203a0f4366 // pinsrb xmm4, byte [r14 + r12], 9 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x0a2624203a0f4366 // pinsrb xmm4, byte [r14 + r12], 10 - QUAD $0x0b3624203a0f4166 // pinsrb xmm4, byte [r14 + rsi], 11 - QUAD $0x0c0e24203a0f4166 // pinsrb xmm4, byte [r14 + rcx], 12 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0d0624203a0f4166 // pinsrb xmm4, byte [r14 + rax], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e0624203a0f4166 // pinsrb xmm4, byte [r14 + rax], 14 - QUAD $0x0f1624203a0f4166 // pinsrb xmm4, byte [r14 + rdx], 15 - QUAD $0x011e5c203a0f4366; BYTE $0x01 // pinsrb xmm3, byte [r14 + r11 + 1], 1 - QUAD $0x012e5c203a0f4366; BYTE $0x02 // pinsrb xmm3, byte [r14 + r13 + 1], 2 - QUAD $0x013e5c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r14 + rdi + 1], 3 - QUAD $0x013e5c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r14 + r15 + 1], 4 - QUAD $0x011e5c203a0f4166; BYTE $0x05 // pinsrb xmm3, byte [r14 + rbx + 1], 5 - QUAD $0x01165c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r14 + r10 + 1], 6 - QUAD $0x010e5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r9 + 1], 7 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x012e5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r13 + 1], 8 - QUAD $0x01065c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r8 + 1], 9 - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - QUAD $0x01265c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r14 + r12 + 1], 10 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - QUAD $0x01365c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rsi + 1], 11 - QUAD $0x010e5c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r14 + rcx + 1], 12 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - QUAD $0x011e5c203a0f4366; BYTE $0x0d // pinsrb xmm3, byte [r14 + r11 + 1], 13 + LONG $0x00ca8149; WORD $0x0001; BYTE $0x00 // or r10, 256 + LONG $0x2454894c; BYTE $0x10 // mov qword [rsp + 16], r10 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + LONG $0x20cc8149; WORD $0x0001; BYTE $0x00 // or r12, 288 + LONG $0x40cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 320 + LONG $0x60ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 352 + QUAD $0x0000008024948948 // mov qword [rsp + 128], rdx + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + LONG $0x80ca8149; WORD $0x0001; BYTE $0x00 // or r10, 384 + LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 + LONG $0xa0ce8149; WORD $0x0001; BYTE $0x00 // or r14, 416 + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0xc0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 448 + LONG $0x24548948; BYTE $0x60 // mov qword [rsp + 96], rdx + LONG $0x01e00d48; WORD $0x0000 // or rax, 480 + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + QUAD $0x003d64203a0f4366; BYTE $0x01 // pinsrb xmm4, byte [r13 + r15], 1 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + LONG $0x245c8948; BYTE $0x68 // mov qword [rsp + 104], rbx + QUAD $0x001d64203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r13 + rbx], 2 + QUAD $0x003564203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r13 + rsi], 3 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0x245c894c; BYTE $0x40 // mov qword [rsp + 64], r11 + QUAD $0x001d64203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r13 + r11], 4 + QUAD $0x000564203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r13 + r8], 5 + QUAD $0x000d64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r13 + rcx], 6 + QUAD $0x000d64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r13 + r9], 7 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x003d64203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r13 + r15], 8 + QUAD $0x002564203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r13 + r12], 9 + QUAD $0x0000009024bc8948 // mov qword [rsp + 144], rdi + QUAD $0x003d64203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r13 + rdi], 10 + QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] + QUAD $0x001d64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r13 + r11], 11 + QUAD $0x001564203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r13 + r10], 12 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + QUAD $0x003564203a0f4366; BYTE $0x0d // pinsrb xmm4, byte [r13 + r14], 13 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x000d64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r13 + rcx], 14 + LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] + QUAD $0x003564203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r13 + r14], 15 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x01355c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r13 + rsi + 1], 1 + QUAD $0x01055c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r13 + rax + 1], 2 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x01055c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r13 + rax + 1], 3 + QUAD $0x01155c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r13 + rdx + 1], 4 + QUAD $0x01055c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r13 + r8 + 1], 5 LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x01065c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r14 + rax + 1], 14 + QUAD $0x01055c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r13 + rax + 1], 6 + QUAD $0x010d5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r13 + r9 + 1], 7 + WORD $0x894d; BYTE $0xc8 // mov r8, r9 + QUAD $0x013d5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r13 + r15 + 1], 8 + QUAD $0x01255c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r13 + r12 + 1], 9 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + LONG $0x2464894c; BYTE $0x58 // mov qword [rsp + 88], r12 + QUAD $0x013d5c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r13 + rdi + 1], 10 + QUAD $0x011d5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r13 + r11 + 1], 11 + QUAD $0x01155c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r13 + r10 + 1], 12 + QUAD $0x011d5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r13 + rbx + 1], 13 + QUAD $0x010d5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r13 + rcx + 1], 14 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx QUAD $0x0000b0248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 176] LONG $0xe1740f66 // pcmpeqb xmm4, xmm1 - QUAD $0x01165c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r14 + rdx + 1], 15 + QUAD $0x01355c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r13 + r14 + 1], 15 LONG $0xd9740f66 // pcmpeqb xmm3, xmm1 QUAD $0x00000100856f0f66 // movdqa xmm0, oword 256[rbp] /* [rip + .LCPI5_16] */ LONG $0xd8df0f66 // pandn xmm3, xmm0 LONG $0xdcfc0f66 // paddb xmm3, xmm4 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x74b60f41; WORD $0x1006 // movzx esi, byte [r14 + rax + 16] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + LONG $0x74b60f41; WORD $0x1005 // movzx esi, byte [r13 + rax + 16] LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x02066c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rax + 2], 1 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x02266c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r14 + r12 + 2], 2 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x02066c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r14 + rax + 2], 3 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x021e6c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rbx + 2], 4 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - QUAD $0x02166c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r10 + 2], 5 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x020e6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r9 + 2], 6 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x02066c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r8 + 2], 7 - QUAD $0x022e6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r13 + 2], 8 - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - QUAD $0x023e6c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r14 + rdi + 2], 9 - QUAD $0x023e6c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r15 + 2], 10 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x02166c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r14 + rdx + 2], 11 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x023e6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rdi + 2], 12 - QUAD $0x021e6c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r14 + r11 + 2], 13 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x02366c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rsi + 2], 14 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x021e6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r11 + 2], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x03067c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rax + 3], 1 - QUAD $0x03267c203a0f4366; BYTE $0x02 // pinsrb xmm7, byte [r14 + r12 + 3], 2 + QUAD $0x02056c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r13 + rax + 2], 1 + LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] + QUAD $0x023d6c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r13 + rdi + 2], 2 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x021d6c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r13 + rbx + 2], 3 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x02356c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r13 + r14 + 2], 4 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x02256c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r13 + r12 + 2], 5 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x02156c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r13 + r10 + 2], 6 + LONG $0x2444894c; BYTE $0x50 // mov qword [rsp + 80], r8 + QUAD $0x02056c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r13 + r8 + 2], 7 + QUAD $0x023d6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r13 + r15 + 2], 8 + QUAD $0x02156c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r13 + rdx + 2], 9 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x02356c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r13 + rsi + 2], 10 + QUAD $0x021d6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r13 + r11 + 2], 11 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x020d6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r13 + rcx + 2], 12 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x021d6c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r13 + r11 + 2], 13 + QUAD $0x020d6c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r13 + r9 + 2], 14 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x02156c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r13 + rdx + 2], 15 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x03067c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r14 + rax + 3], 3 - QUAD $0x031e7c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r14 + rbx + 3], 4 - QUAD $0x03167c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r10 + 3], 5 - QUAD $0x030e7c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r14 + r9 + 3], 6 - QUAD $0x03067c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r14 + r8 + 3], 7 - QUAD $0x032e7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r13 + 3], 8 - QUAD $0x030e7c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r14 + rcx + 3], 9 - QUAD $0x033e7c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r14 + r15 + 3], 10 - QUAD $0x03167c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r14 + rdx + 3], 11 - QUAD $0x033e7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r14 + rdi + 3], 12 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x03067c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rax + 3], 13 - QUAD $0x03367c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r14 + rsi + 3], 14 - QUAD $0x031e7c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r14 + r11 + 3], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x04064c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rax + 4], 1 - QUAD $0x04264c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r14 + r12 + 4], 2 + QUAD $0x03057c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r13 + rax + 3], 1 + QUAD $0x033d7c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r13 + rdi + 3], 2 + QUAD $0x031d7c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r13 + rbx + 3], 3 + QUAD $0x03357c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r13 + r14 + 3], 4 + QUAD $0x03257c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r13 + r12 + 3], 5 + QUAD $0x03157c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r13 + r10 + 3], 6 + QUAD $0x03057c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r13 + r8 + 3], 7 + QUAD $0x033d7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r13 + r15 + 3], 8 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x03057c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r13 + rax + 3], 9 + QUAD $0x03357c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r13 + rsi + 3], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x03057c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r13 + rax + 3], 11 + QUAD $0x030d7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r13 + rcx + 3], 12 + QUAD $0x031d7c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r13 + r11 + 3], 13 + QUAD $0x030d7c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r13 + r9 + 3], 14 + QUAD $0x03157c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r13 + rdx + 3], 15 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x04064c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r14 + rax + 4], 3 - QUAD $0x041e4c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r14 + rbx + 4], 4 - QUAD $0x04164c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r10 + 4], 5 - QUAD $0x040e4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r14 + r9 + 4], 6 - QUAD $0x04064c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r8 + 4], 7 - QUAD $0x042e4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r13 + 4], 8 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x040e4c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r14 + rcx + 4], 9 - QUAD $0x043e4c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r14 + r15 + 4], 10 - QUAD $0x04164c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rdx + 4], 11 - QUAD $0x043e4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r14 + rdi + 4], 12 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x042e4c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r14 + r13 + 4], 13 - QUAD $0x04364c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rsi + 4], 14 - QUAD $0x041e4c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r14 + r11 + 4], 15 + QUAD $0x04054c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r13 + rax + 4], 1 + QUAD $0x043d4c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r13 + rdi + 4], 2 + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + QUAD $0x041d4c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r13 + rbx + 4], 3 + WORD $0x8948; BYTE $0xdf // mov rdi, rbx + QUAD $0x04354c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r14 + 4], 4 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + QUAD $0x04254c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r13 + r12 + 4], 5 + QUAD $0x04154c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r13 + r10 + 4], 6 + QUAD $0x04054c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r13 + r8 + 4], 7 + QUAD $0x043d4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r13 + r15 + 4], 8 + LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] + QUAD $0x04254c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r13 + r12 + 4], 9 + QUAD $0x04354c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r13 + rsi + 4], 10 + WORD $0x8949; BYTE $0xf0 // mov r8, rsi + QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] + QUAD $0x04154c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r13 + r10 + 4], 11 + QUAD $0x040d4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r13 + rcx + 4], 12 + QUAD $0x041d4c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r13 + r11 + 4], 13 + QUAD $0x040d4c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r13 + r9 + 4], 14 + QUAD $0x04154c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r13 + rdx + 4], 15 LONG $0xe9740f66 // pcmpeqb xmm5, xmm1 QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI5_17] */ LONG $0xe8df0f66 // pandn xmm5, xmm0 @@ -29160,80 +30623,85 @@ LBB5_68: QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI5_18] */ LONG $0xf8df0f66 // pandn xmm7, xmm0 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] - LONG $0x74b60f43; WORD $0x111e // movzx esi, byte [r14 + r11 + 17] + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + LONG $0x74b60f41; WORD $0x1115 // movzx esi, byte [r13 + rdx + 17] LONG $0xe66e0f66 // movd xmm4, esi LONG $0x740f4466; BYTE $0xc9 // pcmpeqb xmm9, xmm1 QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI5_19] */ LONG $0xdf0f4466; BYTE $0xc8 // pandn xmm9, xmm0 LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 - LONG $0x74b60f43; WORD $0x121e // movzx esi, byte [r14 + r11 + 18] + LONG $0x74b60f41; WORD $0x1215 // movzx esi, byte [r13 + rdx + 18] LONG $0xfe6e0f66 // movd xmm7, esi LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 LONG $0xd8f80f66 // psubb xmm3, xmm0 LONG $0xeb0f4466; BYTE $0xcb // por xmm9, xmm3 - LONG $0x74b60f43; WORD $0x131e // movzx esi, byte [r14 + r11 + 19] + LONG $0x74b60f41; WORD $0x1315 // movzx esi, byte [r13 + rdx + 19] LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x053654203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rsi + 5], 1 - QUAD $0x052654203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r12 + 5], 2 LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x053e54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r15 + 5], 3 - QUAD $0x051e54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rbx + 5], 4 - QUAD $0x051654203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r10 + 5], 5 - QUAD $0x050e54203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r14 + r9 + 5], 6 - QUAD $0x050654203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r14 + r8 + 5], 7 - QUAD $0x050654203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r14 + rax + 5], 8 - QUAD $0x00000088248c8948 // mov qword [rsp + 136], rcx - QUAD $0x050e54203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r14 + rcx + 5], 9 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x050654203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r14 + rax + 5], 10 - QUAD $0x051654203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rdx + 5], 11 - QUAD $0x053e54203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r14 + rdi + 5], 12 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - QUAD $0x052e54203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r14 + r13 + 5], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x050654203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rax + 5], 14 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x052e54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r13 + 5], 15 - QUAD $0x063644203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rsi + 6], 1 - QUAD $0x062644203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r14 + r12 + 6], 2 - QUAD $0x063e44203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r14 + r15 + 6], 3 - QUAD $0x061e44203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r14 + rbx + 6], 4 - QUAD $0x061644203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r10 + 6], 5 - QUAD $0x060e44203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r14 + r9 + 6], 6 - QUAD $0x060644203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r8 + 6], 7 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x060644203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r14 + rax + 6], 8 - QUAD $0x060e44203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r14 + rcx + 6], 9 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x060644203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rax + 6], 10 - QUAD $0x061644203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rdx + 6], 11 - QUAD $0x063e44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rdi + 6], 12 - QUAD $0x061e44203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r14 + r11 + 6], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x060644203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rax + 6], 14 - QUAD $0x062e44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r13 + 6], 15 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x073674203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r14 + rsi + 7], 1 - QUAD $0x072674203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r14 + r12 + 7], 2 - QUAD $0x073e74203a0f4766; BYTE $0x03 // pinsrb xmm14, byte [r14 + r15 + 7], 3 - QUAD $0x071e74203a0f4566; BYTE $0x04 // pinsrb xmm14, byte [r14 + rbx + 7], 4 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x071674203a0f4766; BYTE $0x05 // pinsrb xmm14, byte [r14 + r10 + 7], 5 - QUAD $0x070e74203a0f4766; BYTE $0x06 // pinsrb xmm14, byte [r14 + r9 + 7], 6 - QUAD $0x070674203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r14 + r8 + 7], 7 + QUAD $0x053d54203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r13 + r15 + 5], 1 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x050554203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r13 + rax + 5], 2 + QUAD $0x053d54203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r13 + rdi + 5], 3 + WORD $0x8949; BYTE $0xfe // mov r14, rdi + QUAD $0x051d54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r13 + rbx + 5], 4 + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x051d54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r13 + r11 + 5], 5 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x053d54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r13 + rdi + 5], 6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x050554203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r13 + rax + 5], 7 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x051554203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r13 + rdx + 5], 8 + QUAD $0x052554203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r13 + r12 + 5], 9 WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x072e74203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r14 + r13 + 7], 8 - QUAD $0x070e74203a0f4566; BYTE $0x09 // pinsrb xmm14, byte [r14 + rcx + 7], 9 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x073e74203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r14 + r15 + 7], 10 - QUAD $0x071674203a0f4566; BYTE $0x0b // pinsrb xmm14, byte [r14 + rdx + 7], 11 - QUAD $0x073e74203a0f4566; BYTE $0x0c // pinsrb xmm14, byte [r14 + rdi + 7], 12 - QUAD $0x071e74203a0f4766; BYTE $0x0d // pinsrb xmm14, byte [r14 + r11 + 7], 13 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x070e74203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r14 + rcx + 7], 14 + QUAD $0x050554203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r13 + r8 + 5], 10 + QUAD $0x051554203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r13 + r10 + 5], 11 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + QUAD $0x050d54203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r13 + rcx + 5], 12 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x051d54203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r13 + rbx + 5], 13 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x050554203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r13 + r8 + 5], 14 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x050d54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r13 + rcx + 5], 15 + QUAD $0x063d44203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r13 + r15 + 6], 1 + QUAD $0x063544203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r13 + rsi + 6], 2 + QUAD $0x063544203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r13 + r14 + 6], 3 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x063544203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r13 + r14 + 6], 4 + QUAD $0x061d44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r13 + r11 + 6], 5 + QUAD $0x063d44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r13 + rdi + 6], 6 + QUAD $0x060544203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r13 + rax + 6], 7 + LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] + QUAD $0x063544203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r13 + r14 + 6], 8 + QUAD $0x062544203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r13 + r12 + 6], 9 + QUAD $0x060d44203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r13 + r9 + 6], 10 + QUAD $0x061544203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r13 + r10 + 6], 11 + WORD $0x894d; BYTE $0xd1 // mov r9, r10 + QUAD $0x061544203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r13 + rdx + 6], 12 + QUAD $0x061d44203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r13 + rbx + 6], 13 + QUAD $0x060544203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r13 + r8 + 6], 14 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] + QUAD $0x061544203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r13 + r10 + 6], 15 + QUAD $0x073d74203a0f4766; BYTE $0x01 // pinsrb xmm14, byte [r13 + r15 + 7], 1 + QUAD $0x073574203a0f4566; BYTE $0x02 // pinsrb xmm14, byte [r13 + rsi + 7], 2 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x071d74203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r13 + rbx + 7], 3 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x073574203a0f4566; BYTE $0x04 // pinsrb xmm14, byte [r13 + rsi + 7], 4 + QUAD $0x071d74203a0f4766; BYTE $0x05 // pinsrb xmm14, byte [r13 + r11 + 7], 5 + QUAD $0x073d74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r13 + rdi + 7], 6 + QUAD $0x070574203a0f4566; BYTE $0x07 // pinsrb xmm14, byte [r13 + rax + 7], 7 + QUAD $0x073574203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r13 + r14 + 7], 8 + QUAD $0x072574203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r13 + r12 + 7], 9 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x070574203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r13 + r8 + 7], 10 + QUAD $0x070d74203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r13 + r9 + 7], 11 + QUAD $0x071574203a0f4566; BYTE $0x0c // pinsrb xmm14, byte [r13 + rdx + 7], 12 + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x073d74203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r13 + rdi + 7], 13 + QUAD $0x070d74203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r13 + rcx + 7], 14 LONG $0x6f0f4166; BYTE $0xce // movdqa xmm1, xmm14 QUAD $0x00b024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 176] LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 @@ -29243,2051 +30711,1507 @@ LBB5_68: QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI5_21] */ LONG $0xdf0f4466; BYTE $0xc0 // pandn xmm8, xmm0 LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - LONG $0x74b60f43; WORD $0x1406 // movzx esi, byte [r14 + r8 + 20] + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + LONG $0x74b60f41; WORD $0x140d // movzx esi, byte [r13 + rcx + 20] LONG $0xde6e0f66 // movd xmm3, esi - QUAD $0x07064c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rax + 7], 15 + QUAD $0x07154c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r13 + r10 + 7], 15 + WORD $0x894d; BYTE $0xd6 // mov r14, r10 LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI5_6] */ LONG $0xc8df0f66 // pandn xmm1, xmm0 LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - LONG $0x74b60f43; WORD $0x1506 // movzx esi, byte [r14 + r8 + 21] + LONG $0x74b60f41; WORD $0x150d // movzx esi, byte [r13 + rcx + 21] LONG $0xd66e0f66 // movd xmm2, esi - QUAD $0x0000f024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 240] - LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] - QUAD $0x081e44203a0f4366; BYTE $0x01 // pinsrb xmm0, byte [r14 + r11 + 8], 1 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x081e44203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rbx + 8], 2 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x083e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdi + 8], 3 - QUAD $0x082644203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r12 + 8], 4 - WORD $0x894c; BYTE $0xe2 // mov rdx, r12 - QUAD $0x081644203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r10 + 8], 5 - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x083644203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rsi + 8], 6 - QUAD $0x080e44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r9 + 8], 7 - QUAD $0x082e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r13 + 8], 8 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x083644203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r14 + rsi + 8], 9 - QUAD $0x083e44203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r15 + 8], 10 - QUAD $0x00000098248c8b4c // mov r9, qword [rsp + 152] - QUAD $0x080e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r9 + 8], 11 - LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] - QUAD $0x082644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r12 + 8], 12 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x083644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rsi + 8], 13 - QUAD $0x080e44203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rcx + 8], 14 - QUAD $0x080644203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rax + 8], 15 + QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x083d44203a0f4366; BYTE $0x01 // pinsrb xmm0, byte [r13 + r15 + 8], 1 + LONG $0x24748b48; BYTE $0x68 // mov rsi, qword [rsp + 104] + QUAD $0x083544203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r13 + rsi + 8], 2 + QUAD $0x081d44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r13 + rbx + 8], 3 + LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + QUAD $0x083d44203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r13 + r15 + 8], 4 + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x081544203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r13 + r10 + 8], 5 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x083544203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r13 + rsi + 8], 6 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x081d44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r13 + r11 + 8], 7 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x083544203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r13 + rsi + 8], 8 + QUAD $0x082544203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r13 + r12 + 8], 9 + QUAD $0x080544203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r13 + r8 + 8], 10 + QUAD $0x080d44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r13 + r9 + 8], 11 + QUAD $0x081544203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r13 + rdx + 8], 12 + QUAD $0x083d44203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r13 + rdi + 8], 13 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x083544203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r13 + rsi + 8], 14 + QUAD $0x083544203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r13 + r14 + 8], 15 LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 - QUAD $0x0000f0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm1 - LONG $0x74b60f43; WORD $0x1606 // movzx esi, byte [r14 + r8 + 22] + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 + LONG $0x74b60f41; WORD $0x160d // movzx esi, byte [r13 + rcx + 22] LONG $0xce6e0f66 // movd xmm1, esi LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 - QUAD $0x091e5c203a0f4766; BYTE $0x01 // pinsrb xmm11, byte [r14 + r11 + 9], 1 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x091e5c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rbx + 9], 2 - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - QUAD $0x093e5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r14 + rdi + 9], 3 - QUAD $0x09165c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rdx + 9], 4 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x090e5c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r14 + rcx + 9], 5 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x091e5c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r11 + 9], 6 - LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] - QUAD $0x09365c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rsi + 9], 7 - QUAD $0x092e5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r13 + 9], 8 - QUAD $0x00000088248c8b48 // mov rcx, qword [rsp + 136] - QUAD $0x090e5c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r14 + rcx + 9], 9 - QUAD $0x093e5c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r14 + r15 + 9], 10 - WORD $0x894c; BYTE $0xca // mov rdx, r9 - QUAD $0x090e5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r14 + r9 + 9], 11 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x09265c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r12 + 9], 12 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x091e5c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rbx + 9], 13 - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x09065c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r8 + 9], 14 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x090e5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r9 + 9], 15 - QUAD $0x0a1664203a0f4766; BYTE $0x01 // pinsrb xmm12, byte [r14 + r10 + 10], 1 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x0a1664203a0f4766; BYTE $0x02 // pinsrb xmm12, byte [r14 + r10 + 10], 2 - QUAD $0x0a0664203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rax + 10], 3 - LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] - QUAD $0x0a2664203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r14 + r12 + 10], 4 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0a1e64203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r14 + rbx + 10], 5 - QUAD $0x0a1e64203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r14 + r11 + 10], 6 - QUAD $0x0a3664203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r14 + rsi + 10], 7 - QUAD $0x0a2e64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r13 + 10], 8 - QUAD $0x0a0e64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r14 + rcx + 10], 9 - QUAD $0x0a3e64203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r14 + r15 + 10], 10 - QUAD $0x0a1664203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r14 + rdx + 10], 11 - QUAD $0x0a3e64203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r14 + rdi + 10], 12 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x0a1e64203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rbx + 10], 13 - QUAD $0x0a0664203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r14 + r8 + 10], 14 - QUAD $0x0a0e64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r14 + r9 + 10], 15 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0b1e6c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rbx + 11], 1 - QUAD $0x0b166c203a0f4766; BYTE $0x02 // pinsrb xmm13, byte [r14 + r10 + 11], 2 - WORD $0x894d; BYTE $0xd4 // mov r12, r10 - QUAD $0x0b066c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r14 + rax + 11], 3 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0b166c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r14 + r10 + 11], 4 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0b066c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r14 + rax + 11], 5 - QUAD $0x0b1e6c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r14 + r11 + 11], 6 - QUAD $0x0b366c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r14 + rsi + 11], 7 - QUAD $0x0b2e6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r13 + 11], 8 - QUAD $0x0b0e6c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r14 + rcx + 11], 9 - QUAD $0x0b3e6c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r14 + r15 + 11], 10 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 - QUAD $0x0b166c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r14 + rdx + 11], 11 - QUAD $0x0b3e6c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r14 + rdi + 11], 12 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x0b2e6c203a0f4766; BYTE $0x0d // pinsrb xmm13, byte [r14 + r13 + 11], 13 - QUAD $0x0b066c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r14 + r8 + 11], 14 - QUAD $0x0b0e6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r14 + r9 + 11], 15 + QUAD $0x09055c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r13 + rax + 9], 1 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x090d5c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r13 + rcx + 9], 2 + QUAD $0x091d5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r13 + rbx + 9], 3 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x093d5c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r13 + r15 + 9], 4 + QUAD $0x09155c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r13 + r10 + 9], 5 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x09155c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r13 + r10 + 9], 6 + QUAD $0x091d5c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r13 + r11 + 9], 7 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x093d5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r13 + r15 + 9], 8 + QUAD $0x09255c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r13 + r12 + 9], 9 + QUAD $0x09055c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r13 + r8 + 9], 10 + WORD $0x894c; BYTE $0xce // mov rsi, r9 + QUAD $0x090d5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r13 + r9 + 9], 11 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x09155c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r13 + rdx + 9], 12 + QUAD $0x093d5c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r13 + rdi + 9], 13 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + QUAD $0x090d5c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r13 + r9 + 9], 14 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x09155c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r13 + rdx + 9], 15 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0a1564203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r13 + rdx + 10], 1 + QUAD $0x0a0d64203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r13 + rcx + 10], 2 + QUAD $0x0a1d64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r13 + rbx + 10], 3 + QUAD $0x0a3564203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r13 + r14 + 10], 4 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0a1564203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r13 + rdx + 10], 5 + QUAD $0x0a1564203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r13 + r10 + 10], 6 + QUAD $0x0a1d64203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r13 + r11 + 10], 7 + QUAD $0x0a3d64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r13 + r15 + 10], 8 + QUAD $0x0a2564203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r13 + r12 + 10], 9 + QUAD $0x0a0564203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r13 + r8 + 10], 10 + QUAD $0x0a3564203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r13 + rsi + 10], 11 + QUAD $0x0a0564203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r13 + rax + 10], 12 + QUAD $0x0a3d64203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r13 + rdi + 10], 13 + QUAD $0x0a0d64203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r13 + r9 + 10], 14 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + QUAD $0x0a0d64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r13 + r9 + 10], 15 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0b056c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r13 + rax + 11], 1 + QUAD $0x0b0d6c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r13 + rcx + 11], 2 + QUAD $0x0b1d6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r13 + rbx + 11], 3 + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + QUAD $0x0b356c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r13 + r14 + 11], 4 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + QUAD $0x0b156c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r13 + rdx + 11], 5 + QUAD $0x0b156c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r13 + r10 + 11], 6 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0b156c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r13 + rdx + 11], 7 + QUAD $0x0b3d6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r13 + r15 + 11], 8 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x0b256c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r13 + r12 + 11], 9 + QUAD $0x0b056c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r13 + r8 + 11], 10 + QUAD $0x0b356c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r13 + rsi + 11], 11 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x0b356c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r13 + rsi + 11], 12 + QUAD $0x0b3d6c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r13 + rdi + 11], 13 + QUAD $0x0b1d6c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r13 + r11 + 11], 14 + QUAD $0x0b0d6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r13 + r9 + 11], 15 LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 QUAD $0x0001009ddf0f4466; BYTE $0x00 // pandn xmm11, oword 256[rbp] /* [rip + .LCPI5_16] */ LONG $0xfc0f4466; BYTE $0xd8 // paddb xmm11, xmm0 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x74b60f41; WORD $0x1706 // movzx esi, byte [r14 + rax + 23] + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + LONG $0x74b60f41; WORD $0x1705 // movzx esi, byte [r13 + rax + 23] LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 QUAD $0x000110a5df0f4466; BYTE $0x00 // pandn xmm12, oword 272[rbp] /* [rip + .LCPI5_17] */ LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI5_18] */ LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - LONG $0x74b60f41; WORD $0x1806 // movzx esi, byte [r14 + rax + 24] + LONG $0x74b60f41; WORD $0x1805 // movzx esi, byte [r13 + rax + 24] LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - QUAD $0x00d0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 208] - QUAD $0x0c1e4c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rbx + 12], 1 - QUAD $0x0c264c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r14 + r12 + 12], 2 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0c3e4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r14 + r15 + 12], 3 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - QUAD $0x0c164c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r14 + r10 + 12], 4 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - QUAD $0x0c164c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r10 + 12], 5 - WORD $0x894d; BYTE $0xd9 // mov r9, r11 - QUAD $0x0c1e4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r14 + r11 + 12], 6 - LONG $0x245c8b4c; BYTE $0x58 // mov r11, qword [rsp + 88] - QUAD $0x0c1e4c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r11 + 12], 7 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x0c064c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r8 + 12], 8 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x0c364c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r14 + rsi + 12], 9 - QUAD $0x0c0e4c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r14 + rcx + 12], 10 - QUAD $0x0c164c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rdx + 12], 11 - QUAD $0x0c3e4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r14 + rdi + 12], 12 - QUAD $0x0c2e4c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r14 + r13 + 12], 13 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0c064c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rax + 12], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0c064c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r14 + rax + 12], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d0674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rax + 13], 1 - QUAD $0x0d2674203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r14 + r12 + 13], 2 - QUAD $0x0d3e74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r15 + 13], 3 - QUAD $0x0d1e74203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rbx + 13], 4 - QUAD $0x0d1674203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r10 + 13], 5 - QUAD $0x0d0e74203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r9 + 13], 6 - QUAD $0x0d1e74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r11 + 13], 7 - QUAD $0x0d0674203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r8 + 13], 8 - QUAD $0x0d3674203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r14 + rsi + 13], 9 - QUAD $0x0d0e74203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r14 + rcx + 13], 10 - QUAD $0x0d1674203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r14 + rdx + 13], 11 - QUAD $0x0d3e74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rdi + 13], 12 - QUAD $0x0d2e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r13 + 13], 13 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0d2e74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r14 + r13 + 13], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0d0674203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rax + 13], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e067c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rax + 14], 1 - QUAD $0x0e267c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r14 + r12 + 14], 2 - QUAD $0x0e3e7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r14 + r15 + 14], 3 - QUAD $0x0e1e7c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r14 + rbx + 14], 4 - QUAD $0x0e167c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r14 + r10 + 14], 5 - WORD $0x894d; BYTE $0xd4 // mov r12, r10 - QUAD $0x0e0e7c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r14 + r9 + 14], 6 - WORD $0x894d; BYTE $0xca // mov r10, r9 - QUAD $0x0e1e7c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r14 + r11 + 14], 7 - WORD $0x894d; BYTE $0xd9 // mov r9, r11 - QUAD $0x0e067c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r8 + 14], 8 - QUAD $0x0e367c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r14 + rsi + 14], 9 - QUAD $0x0e0e7c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r14 + rcx + 14], 10 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - QUAD $0x0e167c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r14 + rdx + 14], 11 - QUAD $0x0e3e7c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r14 + rdi + 14], 12 - WORD $0x8948; BYTE $0xfa // mov rdx, rdi + QUAD $0x00e0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 224] + LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] + QUAD $0x0c354c203a0f4766; BYTE $0x01 // pinsrb xmm9, byte [r13 + r14 + 12], 1 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0c054c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r13 + rax + 12], 2 + QUAD $0x0c0d4c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r13 + rcx + 12], 3 + QUAD $0x0c1d4c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r13 + rbx + 12], 4 + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x0c0d4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r13 + r9 + 12], 5 + QUAD $0x0c154c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r13 + r10 + 12], 6 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0c354c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r13 + rsi + 12], 7 + QUAD $0x0c154c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r13 + rdx + 12], 8 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0c0d4c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r13 + rcx + 12], 9 + QUAD $0x0c054c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r13 + r8 + 12], 10 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + QUAD $0x0c254c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r13 + r12 + 12], 11 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0c154c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r13 + rdx + 12], 12 + WORD $0x8949; BYTE $0xfa // mov r10, rdi + QUAD $0x0c3d4c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r13 + rdi + 12], 13 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x0c1d4c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r13 + r11 + 12], 14 LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x0e1e7c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r14 + rbx + 14], 13 - QUAD $0x0e2e7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r14 + r13 + 14], 14 - LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 - QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI5_19] */ - LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - LONG $0x74b60f41; WORD $0x190e // movzx esi, byte [r14 + rcx + 25] - LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi - QUAD $0x0001609df80f4466; BYTE $0x00 // psubb xmm11, oword 352[rbp] /* [rip + .LCPI5_22] */ - LONG $0xeb0f4566; BYTE $0xcb // por xmm9, xmm11 - LONG $0x74b60f41; WORD $0x1a0e // movzx esi, byte [r14 + rcx + 26] - LONG $0xc66e0f66 // movd xmm0, esi - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e067c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r14 + rax + 14], 15 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - QUAD $0x00000140b5df0f66 // pandn xmm6, oword 320[rbp] /* [rip + .LCPI5_20] */ - LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 - QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI5_21] */ - LONG $0xeb0f4466; BYTE $0xfe // por xmm15, xmm6 - LONG $0x74b60f41; WORD $0x1b0e // movzx esi, byte [r14 + rcx + 27] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - QUAD $0x0000c024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 192] + QUAD $0x0c1d4c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r13 + rbx + 12], 15 + QUAD $0x0d3574203a0f4366; BYTE $0x01 // pinsrb xmm6, byte [r13 + r14 + 13], 1 + QUAD $0x0d0574203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r13 + rax + 13], 2 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0d2574203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r13 + r12 + 13], 3 + QUAD $0x0d3d74203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r15 + 13], 4 + QUAD $0x0d0d74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r13 + r9 + 13], 5 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x0d3d74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r13 + rdi + 13], 6 + QUAD $0x0d3574203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r13 + rsi + 13], 7 LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x0f3e74203a0f4366; BYTE $0x01 // pinsrb xmm6, byte [r14 + r15 + 15], 1 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0f0e74203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rcx + 15], 2 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0f3e74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rdi + 15], 3 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - QUAD $0x0f0674203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r14 + r8 + 15], 4 - QUAD $0x0f2674203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r12 + 15], 5 - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x0f1674203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r10 + 15], 6 - QUAD $0x0f0e74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r9 + 15], 7 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0f3674203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r14 + rsi + 15], 8 - QUAD $0x00000088248c8b4c // mov r9, qword [rsp + 136] - QUAD $0x0f0e74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r9 + 15], 9 - QUAD $0x0f1e74203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r11 + 15], 10 - QUAD $0x0000009824948b4c // mov r10, qword [rsp + 152] - QUAD $0x0f1674203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r10 + 15], 11 - QUAD $0x0f1674203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rdx + 15], 12 - QUAD $0x0f1e74203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r14 + rbx + 15], 13 - QUAD $0x0f2e74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r14 + r13 + 15], 14 - QUAD $0x0f0674203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rax + 15], 15 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI5_6] */ - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x74b60f41; WORD $0x1c06 // movzx esi, byte [r14 + rax + 28] - LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 - QUAD $0x0000c024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm6 - LONG $0x74b60f41; WORD $0x1d06 // movzx esi, byte [r14 + rax + 29] - LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - WORD $0x894c; BYTE $0xfe // mov rsi, r15 - QUAD $0x103e54203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r15 + 16], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x100654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rax + 16], 2 - QUAD $0x103e54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rdi + 16], 3 - WORD $0x8949; BYTE $0xfb // mov r11, rdi - QUAD $0x100654203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r8 + 16], 4 - QUAD $0x102654203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r12 + 16], 5 - QUAD $0x100e54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r14 + rcx + 16], 6 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x101654203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rdx + 16], 7 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x100e54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rcx + 16], 8 - QUAD $0x100e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r9 + 16], 9 - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x103e54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r15 + 16], 10 - QUAD $0x101654203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r10 + 16], 11 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x103e54203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r14 + rdi + 16], 12 - QUAD $0x101e54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rbx + 16], 13 - QUAD $0x102e54203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r14 + r13 + 16], 14 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x100654203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rax + 16], 15 - QUAD $0x113664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rsi + 17], 1 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x113664203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rsi + 17], 2 - QUAD $0x111e64203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r14 + r11 + 17], 3 - QUAD $0x110664203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r8 + 17], 4 - QUAD $0x112664203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r12 + 17], 5 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - QUAD $0x111664203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r14 + r10 + 17], 6 - QUAD $0x111664203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r14 + rdx + 17], 7 - QUAD $0x110e64203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r14 + rcx + 17], 8 - QUAD $0x110e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r9 + 17], 9 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - QUAD $0x113e64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r15 + 17], 10 - QUAD $0x0000009824948b48 // mov rdx, qword [rsp + 152] - QUAD $0x111664203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r14 + rdx + 17], 11 - QUAD $0x113e64203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r14 + rdi + 17], 12 - WORD $0x8949; BYTE $0xfb // mov r11, rdi - QUAD $0x111e64203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rbx + 17], 13 - QUAD $0x112e64203a0f4366; BYTE $0x0e // pinsrb xmm4, byte [r14 + r13 + 17], 14 - QUAD $0x110664203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r14 + rax + 17], 15 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 - LONG $0x740f4166; BYTE $0xe6 // pcmpeqb xmm4, xmm14 - QUAD $0x00000100b56f0f66 // movdqa xmm6, oword 256[rbp] /* [rip + .LCPI5_16] */ - LONG $0xe6df0f66 // pandn xmm4, xmm6 - LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x74b60f41; WORD $0x1e06 // movzx esi, byte [r14 + rax + 30] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x12367c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rsi + 18], 1 - QUAD $0x13366c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rsi + 19], 1 - QUAD $0x14365c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rsi + 20], 1 - QUAD $0x153654203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rsi + 21], 1 - QUAD $0x16364c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rsi + 22], 1 - QUAD $0x173644203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rsi + 23], 1 - QUAD $0x183664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rsi + 24], 1 - QUAD $0x19366c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rsi + 25], 1 - QUAD $0x1a3644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rsi + 26], 1 - QUAD $0x1b365c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rsi + 27], 1 - QUAD $0x1c367c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rsi + 28], 1 - QUAD $0x1d364c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rsi + 29], 1 - QUAD $0x1e3654203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rsi + 30], 1 - LONG $0x44b60f41; WORD $0x1f06 // movzx eax, byte [r14 + rax + 31] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x1f3674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rsi + 31], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x12067c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rax + 18], 2 - QUAD $0x13066c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rax + 19], 2 - QUAD $0x14065c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rax + 20], 2 - QUAD $0x150654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rax + 21], 2 - QUAD $0x16064c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rax + 22], 2 - QUAD $0x170644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rax + 23], 2 - QUAD $0x180664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rax + 24], 2 - QUAD $0x19066c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rax + 25], 2 - QUAD $0x1a0644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rax + 26], 2 - QUAD $0x1b065c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rax + 27], 2 - QUAD $0x1c067c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r14 + rax + 28], 2 - QUAD $0x1d064c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rax + 29], 2 - QUAD $0x1e0654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rax + 30], 2 - QUAD $0x1f0674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rax + 31], 2 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x123e7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r14 + r15 + 18], 3 - LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] - QUAD $0x12067c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r14 + rax + 18], 4 - QUAD $0x12267c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r12 + 18], 5 - QUAD $0x12167c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r14 + r10 + 18], 6 + QUAD $0x0d3d74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r13 + r15 + 13], 8 LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x123e7c203a0f4166; BYTE $0x07 // pinsrb xmm7, byte [r14 + rdi + 18], 7 - LONG $0x244c8b4c; BYTE $0x48 // mov r9, qword [rsp + 72] - QUAD $0x120e7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r9 + 18], 8 - QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] - QUAD $0x12367c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r14 + rsi + 18], 9 - QUAD $0x12067c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r14 + r8 + 18], 10 - QUAD $0x12167c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r14 + rdx + 18], 11 - QUAD $0x121e7c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r14 + r11 + 18], 12 - QUAD $0x121e7c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rbx + 18], 13 - QUAD $0x122e7c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r14 + r13 + 18], 14 - QUAD $0x120e7c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r14 + rcx + 18], 15 - QUAD $0x133e6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r15 + 19], 3 - QUAD $0x13066c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rax + 19], 4 - QUAD $0x13266c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r12 + 19], 5 - QUAD $0x13166c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r10 + 19], 6 - QUAD $0x133e6c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r14 + rdi + 19], 7 - QUAD $0x130e6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r9 + 19], 8 - QUAD $0x13366c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r14 + rsi + 19], 9 - QUAD $0x13066c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r8 + 19], 10 - QUAD $0x13166c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r14 + rdx + 19], 11 - QUAD $0x131e6c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r14 + r11 + 19], 12 - QUAD $0x131e6c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rbx + 19], 13 - QUAD $0x132e6c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r14 + r13 + 19], 14 - QUAD $0x130e6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r14 + rcx + 19], 15 - QUAD $0x143e5c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r14 + r15 + 20], 3 - QUAD $0x14065c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r14 + rax + 20], 4 - QUAD $0x14265c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r12 + 20], 5 - QUAD $0x14165c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r14 + r10 + 20], 6 - QUAD $0x143e5c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r14 + rdi + 20], 7 - QUAD $0x140e5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r9 + 20], 8 - QUAD $0x14365c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r14 + rsi + 20], 9 - QUAD $0x14065c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r14 + r8 + 20], 10 - QUAD $0x14165c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rdx + 20], 11 - QUAD $0x141e5c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r11 + 20], 12 - QUAD $0x141e5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rbx + 20], 13 - QUAD $0x142e5c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r14 + r13 + 20], 14 - LONG $0x740f4166; BYTE $0xfe // pcmpeqb xmm7, xmm14 - QUAD $0x000110b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 272[rbp] /* [rip + .LCPI5_17] */ - LONG $0xdf0f4166; BYTE $0xfe // pandn xmm7, xmm14 - QUAD $0x0000b024ac740f66; BYTE $0x00 // pcmpeqb xmm5, oword [rsp + 176] - QUAD $0x000120b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 288[rbp] /* [rip + .LCPI5_18] */ - LONG $0xdf0f4166; BYTE $0xee // pandn xmm5, xmm14 - LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0x140e5c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r14 + rcx + 20], 15 - QUAD $0x00b024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 176] - LONG $0x740f4166; BYTE $0xde // pcmpeqb xmm3, xmm14 - QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI5_19] */ - LONG $0xdfdf0f66 // pandn xmm3, xmm7 - LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xed760f66 // pcmpeqd xmm5, xmm5 - LONG $0xe5f80f66 // psubb xmm4, xmm5 - LONG $0xdceb0f66 // por xmm3, xmm4 - QUAD $0x153e54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r15 + 21], 3 - QUAD $0x150654203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rax + 21], 4 - QUAD $0x152654203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r12 + 21], 5 - QUAD $0x151654203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r14 + r10 + 21], 6 - QUAD $0x153e54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rdi + 21], 7 - QUAD $0x150e54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r9 + 21], 8 - QUAD $0x153654203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r14 + rsi + 21], 9 - QUAD $0x150654203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r8 + 21], 10 - QUAD $0x151654203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rdx + 21], 11 - QUAD $0x151e54203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r11 + 21], 12 - QUAD $0x151e54203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rbx + 21], 13 - QUAD $0x152e54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r13 + 21], 14 - QUAD $0x150e54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rcx + 21], 15 - QUAD $0x163e4c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r14 + r15 + 22], 3 - QUAD $0x16064c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r14 + rax + 22], 4 - QUAD $0x16264c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r14 + r12 + 22], 5 - QUAD $0x16164c203a0f4366; BYTE $0x06 // pinsrb xmm1, byte [r14 + r10 + 22], 6 - QUAD $0x163e4c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r14 + rdi + 22], 7 - QUAD $0x160e4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r9 + 22], 8 - QUAD $0x16364c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r14 + rsi + 22], 9 - QUAD $0x16064c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r14 + r8 + 22], 10 - QUAD $0x16164c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r14 + rdx + 22], 11 - QUAD $0x161e4c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r11 + 22], 12 - QUAD $0x161e4c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r14 + rbx + 22], 13 - QUAD $0x162e4c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r14 + r13 + 22], 14 - QUAD $0x160e4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rcx + 22], 15 - QUAD $0x173e44203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r14 + r15 + 23], 3 - QUAD $0x170644203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r14 + rax + 23], 4 - QUAD $0x172644203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r12 + 23], 5 - QUAD $0x171644203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r14 + r10 + 23], 6 - QUAD $0x173e44203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r14 + rdi + 23], 7 - QUAD $0x170e44203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r9 + 23], 8 - QUAD $0x173644203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r14 + rsi + 23], 9 - QUAD $0x170644203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r14 + r8 + 23], 10 - QUAD $0x171644203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rdx + 23], 11 - QUAD $0x171e44203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r14 + r11 + 23], 12 - QUAD $0x171e44203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rbx + 23], 13 - QUAD $0x172e44203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r14 + r13 + 23], 14 - LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 - QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI5_20] */ - LONG $0xd5df0f66 // pandn xmm2, xmm5 - LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 - QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI5_21] */ - LONG $0xcfdf0f66 // pandn xmm1, xmm7 - LONG $0xcaeb0f66 // por xmm1, xmm2 - QUAD $0x170e44203a0f4566; BYTE $0x0f // pinsrb xmm8, byte [r14 + rcx + 23], 15 - LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 - LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI5_6] */ - LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - QUAD $0x183e64203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r14 + r15 + 24], 3 - QUAD $0x180664203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r14 + rax + 24], 4 - QUAD $0x182664203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r14 + r12 + 24], 5 - QUAD $0x181664203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r14 + r10 + 24], 6 - QUAD $0x183e64203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r14 + rdi + 24], 7 - QUAD $0x180e64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r9 + 24], 8 - QUAD $0x183664203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r14 + rsi + 24], 9 - QUAD $0x180664203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r14 + r8 + 24], 10 - QUAD $0x181664203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r14 + rdx + 24], 11 - QUAD $0x181e64203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r11 + 24], 12 - QUAD $0x181e64203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rbx + 24], 13 - QUAD $0x182e64203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r14 + r13 + 24], 14 - QUAD $0x180e64203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r14 + rcx + 24], 15 - LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 - QUAD $0x193e6c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r14 + r15 + 25], 3 - QUAD $0x19066c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r14 + rax + 25], 4 - QUAD $0x19266c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r14 + r12 + 25], 5 - QUAD $0x19166c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r14 + r10 + 25], 6 - QUAD $0x193e6c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r14 + rdi + 25], 7 - QUAD $0x190e6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r9 + 25], 8 - QUAD $0x19366c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r14 + rsi + 25], 9 - QUAD $0x19066c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r14 + r8 + 25], 10 - QUAD $0x19166c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r14 + rdx + 25], 11 - QUAD $0x191e6c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r11 + 25], 12 - QUAD $0x191e6c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rbx + 25], 13 - QUAD $0x192e6c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r14 + r13 + 25], 14 - QUAD $0x190e6c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r14 + rcx + 25], 15 - QUAD $0x1a3e44203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r14 + r15 + 26], 3 - QUAD $0x1a0644203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rax + 26], 4 - QUAD $0x1a2644203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r12 + 26], 5 - QUAD $0x1a1644203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r14 + r10 + 26], 6 - QUAD $0x1a3e44203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r14 + rdi + 26], 7 - QUAD $0x1a0e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r9 + 26], 8 - QUAD $0x1a3644203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r14 + rsi + 26], 9 - QUAD $0x1a0644203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r8 + 26], 10 - QUAD $0x1a1644203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r14 + rdx + 26], 11 - QUAD $0x1a1e44203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r11 + 26], 12 - QUAD $0x1a1e44203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rbx + 26], 13 - QUAD $0x1a2e44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r14 + r13 + 26], 14 - QUAD $0x1a0e44203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rcx + 26], 15 - QUAD $0x1b3e5c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r14 + r15 + 27], 3 - QUAD $0x1b065c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rax + 27], 4 - QUAD $0x1b265c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r12 + 27], 5 - QUAD $0x1b165c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r10 + 27], 6 - QUAD $0x1b3e5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rdi + 27], 7 - QUAD $0x1b0e5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r9 + 27], 8 - QUAD $0x1b365c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r14 + rsi + 27], 9 - QUAD $0x1b065c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r14 + r8 + 27], 10 - QUAD $0x1b165c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r14 + rdx + 27], 11 - QUAD $0x1b1e5c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r11 + 27], 12 - QUAD $0x1b1e5c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rbx + 27], 13 - QUAD $0x1b2e5c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r13 + 27], 14 - LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 - QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI5_16] */ - LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 - QUAD $0x1b0e5c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r14 + rcx + 27], 15 - LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 - QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI5_17] */ - LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 - QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI5_18] */ - LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 - QUAD $0x1c3e7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r14 + r15 + 28], 3 - QUAD $0x1d3e4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r14 + r15 + 29], 3 - QUAD $0x1e3e54203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r14 + r15 + 30], 3 - QUAD $0x1f3e74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r15 + 31], 3 - QUAD $0x1c067c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r14 + rax + 28], 4 - QUAD $0x1d064c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r14 + rax + 29], 4 - QUAD $0x1e0654203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r14 + rax + 30], 4 - QUAD $0x1f0674203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rax + 31], 4 - QUAD $0x1c267c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r14 + r12 + 28], 5 - QUAD $0x1d264c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r12 + 29], 5 - QUAD $0x1e2654203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r12 + 30], 5 - QUAD $0x1f2674203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r12 + 31], 5 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x1c167c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r14 + r10 + 28], 6 - QUAD $0x1d164c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r14 + r10 + 29], 6 - QUAD $0x1e1654203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r10 + 30], 6 - QUAD $0x1f1674203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r14 + r10 + 31], 6 - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - QUAD $0x1c3e7c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r14 + rdi + 28], 7 - QUAD $0x1d3e4c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r14 + rdi + 29], 7 - QUAD $0x1e3e54203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rdi + 30], 7 - QUAD $0x1f3e74203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r14 + rdi + 31], 7 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x1c0e7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r9 + 28], 8 - QUAD $0x1d0e4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r9 + 29], 8 - QUAD $0x1e0e54203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r14 + r9 + 30], 8 - QUAD $0x1f0e74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r9 + 31], 8 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - QUAD $0x1c367c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r14 + rsi + 28], 9 - QUAD $0x1d364c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r14 + rsi + 29], 9 - QUAD $0x1e3654203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r14 + rsi + 30], 9 - QUAD $0x1f3674203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r14 + rsi + 31], 9 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x1c067c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r14 + r8 + 28], 10 - QUAD $0x1d064c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r14 + r8 + 29], 10 - QUAD $0x1e0654203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r8 + 30], 10 - QUAD $0x1f0674203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r8 + 31], 10 - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - QUAD $0x1c167c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r14 + rdx + 28], 11 - QUAD $0x1d164c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rdx + 29], 11 - QUAD $0x1e1654203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r14 + rdx + 30], 11 - QUAD $0x1f1674203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r14 + rdx + 31], 11 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - QUAD $0x1c1e7c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r14 + r11 + 28], 12 - QUAD $0x1d1e4c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r14 + r11 + 29], 12 - QUAD $0x1e1e54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r11 + 30], 12 - QUAD $0x1f1e74203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r11 + 31], 12 - QUAD $0x1c1e7c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r14 + rbx + 28], 13 - QUAD $0x1d1e4c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r14 + rbx + 29], 13 - QUAD $0x1e1e54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rbx + 30], 13 - QUAD $0x1f1e74203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r14 + rbx + 31], 13 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x1c2e7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r14 + r13 + 28], 14 - QUAD $0x1d2e4c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r14 + r13 + 29], 14 - QUAD $0x1e2e54203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r14 + r13 + 30], 14 - QUAD $0x1f2e74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r14 + r13 + 31], 14 - QUAD $0x1c0e7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r14 + rcx + 28], 15 - QUAD $0x1d0e4c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r14 + rcx + 29], 15 - QUAD $0x1e0e54203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rcx + 30], 15 - LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 - QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI5_19] */ - LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 - QUAD $0x1f0e74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rcx + 31], 15 - QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI5_22] */ - LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 - LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 - LONG $0xdf0f4466; BYTE $0xcd // pandn xmm9, xmm5 - LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 - LONG $0xdf0f4466; BYTE $0xd7 // pandn xmm10, xmm7 - LONG $0xeb0f4566; BYTE $0xd1 // por xmm10, xmm9 - LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 - LONG $0xf4df0f66 // pandn xmm6, xmm4 - LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 - LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0xc6600f66 // punpcklbw xmm0, xmm6 - QUAD $0x0000f0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 240] - LONG $0xcb6f0f66 // movdqa xmm1, xmm3 - QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] - LONG $0xcc600f66 // punpcklbw xmm1, xmm4 - LONG $0xd16f0f66 // movdqa xmm2, xmm1 - LONG $0xd0610f66 // punpcklwd xmm2, xmm0 - LONG $0xc8690f66 // punpckhwd xmm1, xmm0 - LONG $0x680f4466; BYTE $0xc6 // punpckhbw xmm8, xmm6 - LONG $0xdc680f66 // punpckhbw xmm3, xmm4 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xd8 // punpckhwd xmm3, xmm8 - QUAD $0x000000a8248c8b48 // mov rcx, qword [rsp + 168] - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x5c7f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm3 - LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 - LONG $0x4c7f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm1 - LONG $0x147f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm2 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB5_68 - QUAD $0x0000010824948b4c // mov r10, qword [rsp + 264] - QUAD $0x000000e824943b4c // cmp r10, qword [rsp + 232] - QUAD $0x0000011024b48b4c // mov r14, qword [rsp + 272] - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - JNE LBB5_70 - JMP LBB5_73 - -LBB5_110: - LONG $0xf8e28349 // and r10, -8 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - LONG $0x2454894c; BYTE $0x28 // mov qword [rsp + 40], r10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x6e0f4166; BYTE $0xc3 // movd xmm0, r11d - LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 - LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 - WORD $0xff31 // xor edi, edi - LONG $0xef0f4566; BYTE $0xc9 // pxor xmm9, xmm9 - -LBB5_111: - LONG $0x247c8948; BYTE $0x40 // mov qword [rsp + 64], rdi - LONG $0x06e7c148 // shl rdi, 6 - WORD $0x8949; BYTE $0xff // mov r15, rdi - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - WORD $0x8949; BYTE $0xfc // mov r12, rdi - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - WORD $0x8948; BYTE $0xfb // mov rbx, rdi + QUAD $0x0d3d74203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r13 + rdi + 13], 9 + QUAD $0x0d0574203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r13 + r8 + 13], 10 + QUAD $0x0d0d74203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r13 + rcx + 13], 11 + QUAD $0x0d1574203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r13 + rdx + 13], 12 + QUAD $0x0d1574203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r13 + r10 + 13], 13 + QUAD $0x0d1d74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r13 + r11 + 13], 14 + QUAD $0x0d1d74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r13 + rbx + 13], 15 + QUAD $0x0e357c203a0f4766; BYTE $0x01 // pinsrb xmm15, byte [r13 + r14 + 14], 1 + QUAD $0x0e057c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r13 + rax + 14], 2 + QUAD $0x0e257c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r13 + r12 + 14], 3 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0e057c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r13 + rax + 14], 4 + QUAD $0x0e0d7c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r13 + r9 + 14], 5 + WORD $0x894d; BYTE $0xce // mov r14, r9 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0e1d7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r13 + rbx + 14], 6 + QUAD $0x0e357c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r13 + rsi + 14], 7 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x0e3d7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r13 + r15 + 14], 8 WORD $0x8949; BYTE $0xf9 // mov r9, rdi - LONG $0x04b70f41; BYTE $0x3e // movzx eax, word [r14 + rdi] - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f41; WORD $0x023e // movzx eax, word [r14 + rdi + 2] - LONG $0xc06e0f66 // movd xmm0, eax - LONG $0x44b70f41; WORD $0x043e // movzx eax, word [r14 + rdi + 4] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x44b70f41; WORD $0x063e // movzx eax, word [r14 + rdi + 6] - LONG $0xf86e0f66 // movd xmm7, eax - LONG $0x44b70f41; WORD $0x083e // movzx eax, word [r14 + rdi + 8] - LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax - LONG $0x44b70f41; WORD $0x0a3e // movzx eax, word [r14 + rdi + 10] - LONG $0xe06e0f66 // movd xmm4, eax - LONG $0x44b70f41; WORD $0x0c3e // movzx eax, word [r14 + rdi + 12] - LONG $0x44b70f45; WORD $0x0e3e // movzx r8d, word [r14 + rdi + 14] - LONG $0x54b70f45; WORD $0x103e // movzx r10d, word [r14 + rdi + 16] - LONG $0x6cb70f45; WORD $0x123e // movzx r13d, word [r14 + rdi + 18] - LONG $0x4cb70f41; WORD $0x143e // movzx ecx, word [r14 + rdi + 20] - LONG $0x20244c89 // mov dword [rsp + 32], ecx - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - LONG $0x40c98348 // or rcx, 64 - LONG $0x80cf8149; WORD $0x0000; BYTE $0x00 // or r15, 128 - LONG $0xc0ce8148; WORD $0x0000; BYTE $0x00 // or rsi, 192 - LONG $0x00cc8149; WORD $0x0001; BYTE $0x00 // or r12, 256 - LONG $0x40ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 320 - LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 - LONG $0xc40f4166; WORD $0x0e2c; BYTE $0x01 // pinsrw xmm5, word [r14 + rcx], 1 - LONG $0xc40f4366; WORD $0x3e2c; BYTE $0x02 // pinsrw xmm5, word [r14 + r15], 2 - LONG $0xc40f4166; WORD $0x362c; BYTE $0x03 // pinsrw xmm5, word [r14 + rsi], 3 - LONG $0xc40f4366; WORD $0x262c; BYTE $0x04 // pinsrw xmm5, word [r14 + r12], 4 - LONG $0xc40f4166; WORD $0x162c; BYTE $0x05 // pinsrw xmm5, word [r14 + rdx], 5 - LONG $0xc40f4166; WORD $0x1e2c; BYTE $0x06 // pinsrw xmm5, word [r14 + rbx], 6 - QUAD $0x01020e44c40f4166 // pinsrw xmm0, word [r14 + rcx + 2], 1 - QUAD $0x02023e44c40f4366 // pinsrw xmm0, word [r14 + r15 + 2], 2 - QUAD $0x03023644c40f4166 // pinsrw xmm0, word [r14 + rsi + 2], 3 - QUAD $0x04022644c40f4366 // pinsrw xmm0, word [r14 + r12 + 2], 4 - QUAD $0x05021644c40f4166 // pinsrw xmm0, word [r14 + rdx + 2], 5 - QUAD $0x06021e44c40f4166 // pinsrw xmm0, word [r14 + rbx + 2], 6 - LONG $0xc0c98149; WORD $0x0001; BYTE $0x00 // or r9, 448 - QUAD $0x07020e44c40f4366 // pinsrw xmm0, word [r14 + r9 + 2], 7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f41; WORD $0x163e // movzx eax, word [r14 + rdi + 22] - LONG $0x18244489 // mov dword [rsp + 24], eax - LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 - QUAD $0x01040e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 4], 1 - QUAD $0x02043e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 4], 2 - QUAD $0x0304364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 4], 3 - QUAD $0x0404264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 4], 4 - QUAD $0x0504164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 4], 5 - QUAD $0x06041e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 4], 6 - QUAD $0x07040e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 4], 7 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - QUAD $0x000080b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 128[rbp] /* [rip + .LCPI5_8] */ - LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 - LONG $0x380f4166; WORD $0xd910 // pblendvb xmm3, xmm9, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x000090bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 144[rbp] /* [rip + .LCPI5_9] */ - LONG $0x6f0f4166; BYTE $0xf7 // movdqa xmm6, xmm15 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xc8 // movd xmm1, r8d - LONG $0x5cb70f45; WORD $0x183e // movzx r11d, word [r14 + rdi + 24] - LONG $0xc40f4366; WORD $0x0e2c; BYTE $0x07 // pinsrw xmm5, word [r14 + r9], 7 - LONG $0x750f4166; BYTE $0xeb // pcmpeqw xmm5, xmm11 - LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 - LONG $0xe8ef0f66 // pxor xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - QUAD $0x01060e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 6], 1 - QUAD $0x02063e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 6], 2 - QUAD $0x0306367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 6], 3 - QUAD $0x0406267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 6], 4 - QUAD $0x0506167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 6], 5 - QUAD $0x06061e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 6], 6 - QUAD $0x07060e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 6], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x01080e44c40f4566 // pinsrw xmm8, word [r14 + rcx + 8], 1 - QUAD $0x02083e44c40f4766 // pinsrw xmm8, word [r14 + r15 + 8], 2 - QUAD $0x03083644c40f4566 // pinsrw xmm8, word [r14 + rsi + 8], 3 - QUAD $0x04082644c40f4766 // pinsrw xmm8, word [r14 + r12 + 8], 4 - QUAD $0x05081644c40f4566 // pinsrw xmm8, word [r14 + rdx + 8], 5 - QUAD $0x06081e44c40f4566 // pinsrw xmm8, word [r14 + rbx + 8], 6 - QUAD $0x07080e44c40f4766 // pinsrw xmm8, word [r14 + r9 + 8], 7 - LONG $0xddf80f66 // psubb xmm3, xmm5 - QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc76f0f66 // movdqa xmm0, xmm7 - LONG $0x380f4566; WORD $0xe110 // pblendvb xmm12, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d - LONG $0x44b70f45; WORD $0x1a3e // movzx r8d, word [r14 + rdi + 26] - LONG $0x750f4566; BYTE $0xc3 // pcmpeqw xmm8, xmm11 - LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 - LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 - QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xf5 // movd xmm6, r13d - LONG $0x6cb70f45; WORD $0x1c3e // movzx r13d, word [r14 + rdi + 28] - QUAD $0x010a0e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 10], 1 - QUAD $0x020a3e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 10], 2 - QUAD $0x030a3664c40f4166 // pinsrw xmm4, word [r14 + rsi + 10], 3 - QUAD $0x040a2664c40f4366 // pinsrw xmm4, word [r14 + r12 + 10], 4 - QUAD $0x050a1664c40f4166 // pinsrw xmm4, word [r14 + rdx + 10], 5 - QUAD $0x060a1e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 10], 6 - QUAD $0x070a0e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 10], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - QUAD $0x010c0e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 12], 1 - QUAD $0x020c3e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 12], 2 - QUAD $0x030c3654c40f4166 // pinsrw xmm2, word [r14 + rsi + 12], 3 - QUAD $0x040c2654c40f4366 // pinsrw xmm2, word [r14 + r12 + 12], 4 - QUAD $0x050c1654c40f4166 // pinsrw xmm2, word [r14 + rdx + 12], 5 - QUAD $0x060c1e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 12], 6 - LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI5_12] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - LONG $0x646e0f66; WORD $0x2024 // movd xmm4, dword [rsp + 32] - LONG $0x54b70f45; WORD $0x1e3e // movzx r10d, word [r14 + rdi + 30] - QUAD $0x070c0e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 12], 7 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 - QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI5_13] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - LONG $0x5c6e0f66; WORD $0x1824 // movd xmm3, dword [rsp + 24] - LONG $0x44b70f41; WORD $0x203e // movzx eax, word [r14 + rdi + 32] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x010e0e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 14], 1 - QUAD $0x020e3e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 14], 2 - QUAD $0x030e364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 14], 3 - QUAD $0x040e264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 14], 4 - QUAD $0x050e164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 14], 5 - QUAD $0x060e1e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 14], 6 - LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 - LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d - LONG $0x44b70f41; WORD $0x223e // movzx eax, word [r14 + rdi + 34] - LONG $0x20244489 // mov dword [rsp + 32], eax - QUAD $0x070e0e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 14], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - QUAD $0x01120e74c40f4166 // pinsrw xmm6, word [r14 + rcx + 18], 1 - QUAD $0x02123e74c40f4366 // pinsrw xmm6, word [r14 + r15 + 18], 2 - QUAD $0x03123674c40f4166 // pinsrw xmm6, word [r14 + rsi + 18], 3 - QUAD $0x04122674c40f4366 // pinsrw xmm6, word [r14 + r12 + 18], 4 - QUAD $0x05121674c40f4166 // pinsrw xmm6, word [r14 + rdx + 18], 5 - QUAD $0x06121e74c40f4166 // pinsrw xmm6, word [r14 + rbx + 18], 6 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x07120e74c40f4366 // pinsrw xmm6, word [r14 + r9 + 18], 7 - LONG $0x750f4166; BYTE $0xf3 // pcmpeqw xmm6, xmm11 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - QUAD $0x0000e0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 224[rbp] /* [rip + .LCPI5_14] */ - LONG $0x6f0f4566; BYTE $0xe2 // movdqa xmm12, xmm10 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4566; WORD $0xe110 // pblendvb xmm12, xmm9, xmm0 - LONG $0x6f0f4566; BYTE $0xc6 // movdqa xmm8, xmm14 - LONG $0xc66f0f66 // movdqa xmm0, xmm6 - LONG $0x380f4566; WORD $0xc110 // pblendvb xmm8, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xc8 // movd xmm1, r8d - LONG $0x5cb70f45; WORD $0x243e // movzx r11d, word [r14 + rdi + 36] - QUAD $0x01100e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 16], 1 - QUAD $0x02103e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 16], 2 - QUAD $0x0310367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 16], 3 - QUAD $0x0410267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 16], 4 - QUAD $0x0510167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 16], 5 - QUAD $0x06101e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 16], 6 - QUAD $0x01140e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 20], 1 - QUAD $0x02143e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 20], 2 - QUAD $0x03143664c40f4166 // pinsrw xmm4, word [r14 + rsi + 20], 3 - QUAD $0x04142664c40f4366 // pinsrw xmm4, word [r14 + r12 + 20], 4 - QUAD $0x05141664c40f4166 // pinsrw xmm4, word [r14 + rdx + 20], 5 - QUAD $0x06141e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 20], 6 - QUAD $0x07140e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 20], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4566; WORD $0xf910 // pblendvb xmm15, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xe5 // movd xmm4, r13d - LONG $0x6cb70f45; WORD $0x263e // movzx r13d, word [r14 + rdi + 38] - QUAD $0x07100e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 16], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x01160e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 22], 1 - QUAD $0x02163e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 22], 2 - QUAD $0x0316365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 22], 3 - QUAD $0x0416265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 22], 4 - QUAD $0x0516165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 22], 5 - QUAD $0x06161e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 22], 6 - QUAD $0x07160e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 22], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x01180e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 24], 1 - QUAD $0x02183e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 24], 2 - QUAD $0x03183654c40f4166 // pinsrw xmm2, word [r14 + rsi + 24], 3 - QUAD $0x04182654c40f4366 // pinsrw xmm2, word [r14 + r12 + 24], 4 - QUAD $0x05181654c40f4166 // pinsrw xmm2, word [r14 + rdx + 24], 5 - QUAD $0x06181e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 24], 6 - QUAD $0x07180e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 24], 7 - LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 - QUAD $0x0000a0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4566; WORD $0xf110 // pblendvb xmm14, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d - LONG $0x44b70f45; WORD $0x283e // movzx r8d, word [r14 + rdi + 40] - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4566; BYTE $0xf7 // por xmm14, xmm15 - QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - LONG $0x7c6e0f66; WORD $0x1824 // movd xmm7, dword [rsp + 24] - LONG $0x54b70f45; WORD $0x2a3e // movzx r10d, word [r14 + rdi + 42] - QUAD $0x011a0e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 26], 1 - QUAD $0x021a3e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 26], 2 - QUAD $0x031a364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 26], 3 - QUAD $0x041a264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 26], 4 - QUAD $0x051a164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 26], 5 - QUAD $0x061a1e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 26], 6 - QUAD $0x071a0e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 26], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x011c0e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 28], 1 - QUAD $0x021c3e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 28], 2 - QUAD $0x031c3664c40f4166 // pinsrw xmm4, word [r14 + rsi + 28], 3 - QUAD $0x041c2664c40f4366 // pinsrw xmm4, word [r14 + r12 + 28], 4 - QUAD $0x051c1664c40f4166 // pinsrw xmm4, word [r14 + rdx + 28], 5 - QUAD $0x061c1e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 28], 6 - LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 - QUAD $0x0000c0bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 192[rbp] /* [rip + .LCPI5_12] */ - LONG $0x6f0f4166; BYTE $0xef // movdqa xmm5, xmm15 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - LONG $0x546e0f66; WORD $0x2024 // movd xmm2, dword [rsp + 32] - LONG $0x44b70f41; WORD $0x2c3e // movzx eax, word [r14 + rdi + 44] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x071c0e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 28], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 - QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI5_13] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x5cb70f45; WORD $0x2e3e // movzx r11d, word [r14 + rdi + 46] - QUAD $0x011e0e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 30], 1 - QUAD $0x021e3e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 30], 2 - QUAD $0x031e365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 30], 3 - QUAD $0x041e265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 30], 4 - QUAD $0x051e165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 30], 5 - QUAD $0x061e1e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 30], 6 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0x6e0f4166; BYTE $0xcd // movd xmm1, r13d - LONG $0x44b70f41; WORD $0x303e // movzx eax, word [r14 + rdi + 48] - LONG $0x20244489 // mov dword [rsp + 32], eax - QUAD $0x071e0e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 30], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - QUAD $0x01220e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 34], 1 - QUAD $0x02223e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 34], 2 - QUAD $0x03223654c40f4166 // pinsrw xmm2, word [r14 + rsi + 34], 3 - QUAD $0x04222654c40f4366 // pinsrw xmm2, word [r14 + r12 + 34], 4 - QUAD $0x05221654c40f4166 // pinsrw xmm2, word [r14 + rdx + 34], 5 - QUAD $0x06221e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 34], 6 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07220e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 34], 7 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 - LONG $0x6f0f4566; BYTE $0xea // movdqa xmm13, xmm10 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - QUAD $0x000080856f0f4466; BYTE $0x00 // movdqa xmm8, oword 128[rbp] /* [rip + .LCPI5_8] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xc110 // pblendvb xmm8, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xd0 // movd xmm2, r8d - LONG $0x6cb70f45; WORD $0x323e // movzx r13d, word [r14 + rdi + 50] - QUAD $0x01200e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 32], 1 - QUAD $0x02203e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 32], 2 - QUAD $0x0320367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 32], 3 - QUAD $0x0420267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 32], 4 - QUAD $0x0520167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 32], 5 - QUAD $0x06201e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 32], 6 - QUAD $0x01240e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 36], 1 - QUAD $0x02243e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 36], 2 - QUAD $0x03243664c40f4166 // pinsrw xmm4, word [r14 + rsi + 36], 3 - QUAD $0x04242664c40f4366 // pinsrw xmm4, word [r14 + r12 + 36], 4 - QUAD $0x05241664c40f4166 // pinsrw xmm4, word [r14 + rdx + 36], 5 - QUAD $0x06241e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 36], 6 - QUAD $0x07240e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 36], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 - QUAD $0x00000090b56f0f66 // movdqa xmm6, oword 144[rbp] /* [rip + .LCPI5_9] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d - LONG $0x54b70f45; WORD $0x343e // movzx r10d, word [r14 + rdi + 52] - QUAD $0x07200e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 32], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - LONG $0x760f4566; BYTE $0xf6 // pcmpeqd xmm14, xmm14 - LONG $0xef0f4166; BYTE $0xfe // pxor xmm7, xmm14 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x01260e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 38], 1 - QUAD $0x02263e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 38], 2 - QUAD $0x0326364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 38], 3 - QUAD $0x0426264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 38], 4 - QUAD $0x0526164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 38], 5 - QUAD $0x06261e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 38], 6 - QUAD $0x07260e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 38], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x01280e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 40], 1 - QUAD $0x02283e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 40], 2 - QUAD $0x03283654c40f4166 // pinsrw xmm2, word [r14 + rsi + 40], 3 - QUAD $0x04282654c40f4366 // pinsrw xmm2, word [r14 + r12 + 40], 4 - QUAD $0x05281654c40f4166 // pinsrw xmm2, word [r14 + rdx + 40], 5 - QUAD $0x06281e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 40], 6 - QUAD $0x07280e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 40], 7 - LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 - QUAD $0x000000a0ad6f0f66 // movdqa xmm5, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] - LONG $0x44b70f45; WORD $0x363e // movzx r8d, word [r14 + rdi + 54] - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeeeb0f66 // por xmm5, xmm6 - QUAD $0x000000b0b56f0f66 // movdqa xmm6, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x44b70f41; WORD $0x383e // movzx eax, word [r14 + rdi + 56] - QUAD $0x012a0e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 42], 1 - QUAD $0x022a3e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 42], 2 - QUAD $0x032a365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 42], 3 - QUAD $0x042a265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 42], 4 - QUAD $0x052a165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 42], 5 - QUAD $0x062a1e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 42], 6 - QUAD $0x072a0e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 42], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x012c0e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 44], 1 - QUAD $0x022c3e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 44], 2 - QUAD $0x032c364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 44], 3 - QUAD $0x042c264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 44], 4 - QUAD $0x052c164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 44], 5 - QUAD $0x062c1e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 44], 6 - LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 - LONG $0x6f0f4166; BYTE $0xd7 // movdqa xmm2, xmm15 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xd110 // pblendvb xmm2, xmm9, xmm0 - LONG $0x7c6e0f66; WORD $0x2024 // movd xmm7, dword [rsp + 32] - LONG $0x5cb70f45; WORD $0x3a3e // movzx r11d, word [r14 + rdi + 58] - QUAD $0x072c0e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 44], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0x0000d0bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 208[rbp] /* [rip + .LCPI5_13] */ - LONG $0x6f0f4166; BYTE $0xf7 // movdqa xmm6, xmm15 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xcd // movd xmm1, r13d - LONG $0x6cb70f45; WORD $0x3c3e // movzx r13d, word [r14 + rdi + 60] - LONG $0xf2eb0f66 // por xmm6, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - QUAD $0x012e0e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 46], 1 - QUAD $0x022e3e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 46], 2 - QUAD $0x032e3664c40f4166 // pinsrw xmm4, word [r14 + rsi + 46], 3 - QUAD $0x042e2664c40f4366 // pinsrw xmm4, word [r14 + r12 + 46], 4 - QUAD $0x052e1664c40f4166 // pinsrw xmm4, word [r14 + rdx + 46], 5 - QUAD $0x062e1e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 46], 6 - QUAD $0x072e0e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 46], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0x6f0f4566; BYTE $0xc2 // movdqa xmm8, xmm10 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4566; WORD $0xc110 // pblendvb xmm8, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xd8 // movd xmm3, r8d - QUAD $0x01320e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 50], 1 - QUAD $0x02323e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 50], 2 - QUAD $0x0332364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 50], 3 - QUAD $0x0432264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 50], 4 - QUAD $0x0532164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 50], 5 - QUAD $0x06321e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 50], 6 - QUAD $0x07320e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 50], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - QUAD $0x00000080a56f0f66 // movdqa xmm4, oword 128[rbp] /* [rip + .LCPI5_8] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe110 // pblendvb xmm4, xmm9, xmm0 - LONG $0xc86e0f66 // movd xmm1, eax - QUAD $0x01300e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 48], 1 - QUAD $0x02303e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 48], 2 - QUAD $0x0330367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 48], 3 - QUAD $0x0430267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 48], 4 - QUAD $0x0530167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 48], 5 - QUAD $0x06301e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 48], 6 - QUAD $0x07300e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 48], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - LONG $0xef0f4166; BYTE $0xfe // pxor xmm7, xmm14 - QUAD $0x01340e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 52], 1 - QUAD $0x02343e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 52], 2 - QUAD $0x03343654c40f4166 // pinsrw xmm2, word [r14 + rsi + 52], 3 - QUAD $0x04342654c40f4366 // pinsrw xmm2, word [r14 + r12 + 52], 4 - QUAD $0x05341654c40f4166 // pinsrw xmm2, word [r14 + rdx + 52], 5 - QUAD $0x06341e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 52], 6 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x07340e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 52], 7 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - QUAD $0x01360e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 54], 1 - QUAD $0x02363e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 54], 2 - QUAD $0x0336365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 54], 3 - QUAD $0x0436265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 54], 4 - QUAD $0x0536165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 54], 5 - QUAD $0x06361e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 54], 6 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x07360e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 54], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - QUAD $0x01380e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 56], 1 - QUAD $0x02383e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 56], 2 - QUAD $0x0338364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 56], 3 - QUAD $0x0438264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 56], 4 - QUAD $0x0538164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 56], 5 - QUAD $0x06381e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 56], 6 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07380e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 56], 7 - LONG $0xe7f80f66 // psubb xmm4, xmm7 - QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI5_9] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - QUAD $0x000000a0b56f0f66 // movdqa xmm6, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - QUAD $0x013a0e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 58], 1 - QUAD $0x023a3e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 58], 2 - QUAD $0x033a3654c40f4166 // pinsrw xmm2, word [r14 + rsi + 58], 3 - QUAD $0x043a2654c40f4366 // pinsrw xmm2, word [r14 + r12 + 58], 4 - QUAD $0x053a1654c40f4166 // pinsrw xmm2, word [r14 + rdx + 58], 5 - QUAD $0x063a1e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 58], 6 - QUAD $0x073a0e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 58], 7 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0x6e0f4166; BYTE $0xdd // movd xmm3, r13d - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - QUAD $0x013c0e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 60], 1 - QUAD $0x023c3e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 60], 2 - QUAD $0x033c365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 60], 3 - QUAD $0x043c265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 60], 4 - QUAD $0x053c165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 60], 5 - QUAD $0x063c1e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 60], 6 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x073c0e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 60], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf4eb0f66 // por xmm6, xmm4 - QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe110 // pblendvb xmm4, xmm9, xmm0 - QUAD $0x000000c08d6f0f66 // movdqa xmm1, oword 192[rbp] /* [rip + .LCPI5_12] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xc910 // pblendvb xmm1, xmm9, xmm0 - LONG $0x6f0f4166; BYTE $0xd7 // movdqa xmm2, xmm15 + QUAD $0x0e3d7c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r13 + rdi + 14], 9 + QUAD $0x0e057c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r13 + r8 + 14], 10 + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + QUAD $0x0e0d7c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r13 + rcx + 14], 11 + QUAD $0x0e157c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r13 + rdx + 14], 12 + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x0e3d7c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r13 + rdi + 14], 13 + WORD $0x894d; BYTE $0xda // mov r10, r11 + QUAD $0x0e1d7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r13 + r11 + 14], 14 + LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 + QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI5_19] */ + LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + LONG $0x74b60f43; WORD $0x1925 // movzx esi, byte [r13 + r12 + 25] + LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi + QUAD $0x0001609df80f4466; BYTE $0x00 // psubb xmm11, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xeb0f4566; BYTE $0xcb // por xmm9, xmm11 + LONG $0x74b60f43; WORD $0x1a25 // movzx esi, byte [r13 + r12 + 26] + LONG $0xc66e0f66 // movd xmm0, esi + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0e0d7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r13 + rcx + 14], 15 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + QUAD $0x00000140b5df0f66 // pandn xmm6, oword 320[rbp] /* [rip + .LCPI5_20] */ + LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 + QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI5_21] */ + LONG $0xeb0f4466; BYTE $0xfe // por xmm15, xmm6 + LONG $0x74b60f43; WORD $0x1b25 // movzx esi, byte [r13 + r12 + 27] + LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi + QUAD $0x0000c024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 192] + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0f1574203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r13 + rdx + 15], 1 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0f1574203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r13 + rdx + 15], 2 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x0f1d74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r13 + r11 + 15], 3 + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + QUAD $0x0f0574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r8 + 15], 4 + QUAD $0x0f3574203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r13 + r14 + 15], 5 + QUAD $0x0f1d74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r13 + rbx + 15], 6 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0f3574203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r13 + rsi + 15], 7 + QUAD $0x0f3d74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r13 + r15 + 15], 8 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + WORD $0x894d; BYTE $0xcf // mov r15, r9 + QUAD $0x0f0d74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r13 + r9 + 15], 9 + QUAD $0x0f0574203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r13 + rax + 15], 10 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0f0574203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r13 + rax + 15], 11 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + QUAD $0x0f1d74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r13 + rbx + 15], 12 + QUAD $0x0f3d74203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r13 + rdi + 15], 13 + QUAD $0x0f1574203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r13 + r10 + 15], 14 + QUAD $0x0f0d74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r13 + rcx + 15], 15 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI5_6] */ + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x74b60f43; WORD $0x1c25 // movzx esi, byte [r13 + r12 + 28] + LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi + LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 + QUAD $0x0000c024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm6 + LONG $0x74b60f43; WORD $0x1d25 // movzx esi, byte [r13 + r12 + 29] + LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x103554203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r13 + rsi + 16], 1 + QUAD $0x101554203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r13 + rdx + 16], 2 + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + WORD $0x894c; BYTE $0xd9 // mov rcx, r11 + QUAD $0x101d54203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r13 + r11 + 16], 3 + QUAD $0x100554203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r13 + r8 + 16], 4 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x100d54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r13 + r9 + 16], 5 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x103d54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r13 + rdi + 16], 6 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + QUAD $0x100554203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r13 + r8 + 16], 7 + QUAD $0x103554203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r13 + r14 + 16], 8 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x103d54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r13 + r15 + 16], 9 + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + QUAD $0x103554203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r13 + r14 + 16], 10 + QUAD $0x100554203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r13 + rax + 16], 11 + QUAD $0x101d54203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r13 + rbx + 16], 12 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x100554203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r13 + rax + 16], 13 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x101d54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r13 + rbx + 16], 14 + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + QUAD $0x103d54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r13 + r15 + 16], 15 + QUAD $0x113564203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r13 + rsi + 17], 1 + QUAD $0x111564203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r13 + r10 + 17], 2 + QUAD $0x110d64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r13 + rcx + 17], 3 + QUAD $0x111d64203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r13 + r11 + 17], 4 + QUAD $0x110d64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r13 + r9 + 17], 5 + QUAD $0x113d64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r13 + rdi + 17], 6 + QUAD $0x110564203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r13 + r8 + 17], 7 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x110d64203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r13 + rcx + 17], 8 + QUAD $0x111564203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r13 + rdx + 17], 9 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + QUAD $0x113564203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r13 + r14 + 17], 10 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x110d64203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r13 + rcx + 17], 11 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x111564203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r13 + rdx + 17], 12 + QUAD $0x110564203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r13 + rax + 17], 13 + QUAD $0x111d64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r13 + rbx + 17], 14 + WORD $0x894d; BYTE $0xfa // mov r10, r15 + QUAD $0x113d64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r13 + r15 + 17], 15 + LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 + LONG $0x740f4166; BYTE $0xe6 // pcmpeqb xmm4, xmm14 + QUAD $0x00000100b56f0f66 // movdqa xmm6, oword 256[rbp] /* [rip + .LCPI5_16] */ + LONG $0xe6df0f66 // pandn xmm4, xmm6 + LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 + LONG $0x74b60f43; WORD $0x1e25 // movzx esi, byte [r13 + r12 + 30] + LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x12357c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r13 + rsi + 18], 1 + QUAD $0x13356c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r13 + rsi + 19], 1 + QUAD $0x14355c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r13 + rsi + 20], 1 + QUAD $0x153554203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r13 + rsi + 21], 1 + QUAD $0x16354c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r13 + rsi + 22], 1 + QUAD $0x173544203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r13 + rsi + 23], 1 + QUAD $0x183564203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r13 + rsi + 24], 1 + QUAD $0x19356c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r13 + rsi + 25], 1 + QUAD $0x1a3544203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r13 + rsi + 26], 1 + QUAD $0x1b355c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r13 + rsi + 27], 1 + QUAD $0x1c357c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r13 + rsi + 28], 1 + QUAD $0x1d354c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r13 + rsi + 29], 1 + QUAD $0x1e3554203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r13 + rsi + 30], 1 + LONG $0x44b60f43; WORD $0x1f25 // movzx eax, byte [r13 + r12 + 31] + LONG $0xf06e0f66 // movd xmm6, eax + QUAD $0x1f3574203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r13 + rsi + 31], 1 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x12057c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r13 + rax + 18], 2 + QUAD $0x13056c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r13 + rax + 19], 2 + QUAD $0x14055c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r13 + rax + 20], 2 + QUAD $0x150554203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r13 + rax + 21], 2 + QUAD $0x16054c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r13 + rax + 22], 2 + QUAD $0x170544203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r13 + rax + 23], 2 + QUAD $0x180564203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r13 + rax + 24], 2 + QUAD $0x19056c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r13 + rax + 25], 2 + QUAD $0x1a0544203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r13 + rax + 26], 2 + QUAD $0x1b055c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r13 + rax + 27], 2 + QUAD $0x1c057c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r13 + rax + 28], 2 + QUAD $0x1d054c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r13 + rax + 29], 2 + QUAD $0x1e0554203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r13 + rax + 30], 2 + QUAD $0x1f0574203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r13 + rax + 31], 2 + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] + QUAD $0x121d7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r13 + r11 + 18], 3 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x12357c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r13 + r14 + 18], 4 + WORD $0x894d; BYTE $0xcc // mov r12, r9 + QUAD $0x120d7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r13 + r9 + 18], 5 + QUAD $0x123d7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r13 + rdi + 18], 6 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x120d7c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r13 + r9 + 18], 7 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x12057c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r13 + rax + 18], 8 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x12357c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r13 + rsi + 18], 9 + QUAD $0x12057c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r13 + r8 + 18], 10 + QUAD $0x120d7c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r13 + rcx + 18], 11 + QUAD $0x12157c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r13 + rdx + 18], 12 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x123d7c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r13 + r15 + 18], 13 + QUAD $0x121d7c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r13 + rbx + 18], 14 + QUAD $0x12157c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r13 + r10 + 18], 15 + QUAD $0x131d6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r13 + r11 + 19], 3 + QUAD $0x13356c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r13 + r14 + 19], 4 + QUAD $0x13256c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r13 + r12 + 19], 5 + QUAD $0x133d6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r13 + rdi + 19], 6 + QUAD $0x130d6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r13 + r9 + 19], 7 + QUAD $0x13056c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r13 + rax + 19], 8 + QUAD $0x13356c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r13 + rsi + 19], 9 + QUAD $0x13056c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r13 + r8 + 19], 10 + QUAD $0x130d6c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r13 + rcx + 19], 11 + QUAD $0x13156c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r13 + rdx + 19], 12 + QUAD $0x133d6c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r13 + r15 + 19], 13 + QUAD $0x131d6c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r13 + rbx + 19], 14 + QUAD $0x13156c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r13 + r10 + 19], 15 + QUAD $0x141d5c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r13 + r11 + 20], 3 + QUAD $0x14355c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r13 + r14 + 20], 4 + QUAD $0x14255c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r13 + r12 + 20], 5 + QUAD $0x143d5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r13 + rdi + 20], 6 + QUAD $0x140d5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r13 + r9 + 20], 7 + QUAD $0x14055c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r13 + rax + 20], 8 + QUAD $0x14355c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r13 + rsi + 20], 9 + WORD $0x8949; BYTE $0xf7 // mov r15, rsi + QUAD $0x14055c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r13 + r8 + 20], 10 + QUAD $0x140d5c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r13 + rcx + 20], 11 + QUAD $0x14155c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r13 + rdx + 20], 12 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x14255c203a0f4366; BYTE $0x0d // pinsrb xmm3, byte [r13 + r12 + 20], 13 + QUAD $0x141d5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r13 + rbx + 20], 14 + LONG $0x740f4166; BYTE $0xfe // pcmpeqb xmm7, xmm14 + QUAD $0x000110b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 272[rbp] /* [rip + .LCPI5_17] */ + LONG $0xdf0f4166; BYTE $0xfe // pandn xmm7, xmm14 + QUAD $0x0000b024ac740f66; BYTE $0x00 // pcmpeqb xmm5, oword [rsp + 176] + QUAD $0x000120b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 288[rbp] /* [rip + .LCPI5_18] */ + LONG $0xdf0f4166; BYTE $0xee // pandn xmm5, xmm14 + LONG $0xefeb0f66 // por xmm5, xmm7 + QUAD $0x14155c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r13 + r10 + 20], 15 + QUAD $0x00b024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xde // pcmpeqb xmm3, xmm14 + QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI5_19] */ + LONG $0xdfdf0f66 // pandn xmm3, xmm7 + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xed760f66 // pcmpeqd xmm5, xmm5 + LONG $0xe5f80f66 // psubb xmm4, xmm5 + LONG $0xdceb0f66 // por xmm3, xmm4 + QUAD $0x151d54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r13 + r11 + 21], 3 + QUAD $0x153554203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r13 + r14 + 21], 4 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x153554203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r13 + rsi + 21], 5 + QUAD $0x153d54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r13 + rdi + 21], 6 + QUAD $0x150d54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r13 + r9 + 21], 7 + QUAD $0x150554203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r13 + rax + 21], 8 + QUAD $0x153d54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r13 + r15 + 21], 9 + QUAD $0x150554203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r13 + r8 + 21], 10 + QUAD $0x150d54203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r13 + rcx + 21], 11 + QUAD $0x151554203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r13 + rdx + 21], 12 + QUAD $0x152554203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r13 + r12 + 21], 13 + QUAD $0x151d54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r13 + rbx + 21], 14 + QUAD $0x151554203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r13 + r10 + 21], 15 + QUAD $0x161d4c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r13 + r11 + 22], 3 + QUAD $0x16354c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r13 + r14 + 22], 4 + QUAD $0x16354c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r13 + rsi + 22], 5 + QUAD $0x163d4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r13 + rdi + 22], 6 + QUAD $0x160d4c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r13 + r9 + 22], 7 + QUAD $0x16054c203a0f4166; BYTE $0x08 // pinsrb xmm1, byte [r13 + rax + 22], 8 + QUAD $0x163d4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r13 + r15 + 22], 9 + QUAD $0x16054c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r13 + r8 + 22], 10 + QUAD $0x160d4c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r13 + rcx + 22], 11 + QUAD $0x16154c203a0f4166; BYTE $0x0c // pinsrb xmm1, byte [r13 + rdx + 22], 12 + QUAD $0x16254c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r13 + r12 + 22], 13 + QUAD $0x161d4c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r13 + rbx + 22], 14 + QUAD $0x16154c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r13 + r10 + 22], 15 + QUAD $0x171d44203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r13 + r11 + 23], 3 + QUAD $0x173544203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r13 + r14 + 23], 4 + QUAD $0x173544203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r13 + rsi + 23], 5 + QUAD $0x173d44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r13 + rdi + 23], 6 + QUAD $0x170d44203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r13 + r9 + 23], 7 + QUAD $0x170544203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r13 + rax + 23], 8 + QUAD $0x173d44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r13 + r15 + 23], 9 + QUAD $0x170544203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r13 + r8 + 23], 10 + QUAD $0x170d44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r13 + rcx + 23], 11 + QUAD $0x171544203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r13 + rdx + 23], 12 + QUAD $0x172544203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r13 + r12 + 23], 13 + QUAD $0x171d44203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r13 + rbx + 23], 14 + LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 + QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI5_20] */ + LONG $0xd5df0f66 // pandn xmm2, xmm5 + LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 + QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI5_21] */ + LONG $0xcfdf0f66 // pandn xmm1, xmm7 + LONG $0xcaeb0f66 // por xmm1, xmm2 + QUAD $0x171544203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r13 + r10 + 23], 15 + LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 + LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI5_6] */ + LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + QUAD $0x181d64203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r13 + r11 + 24], 3 + QUAD $0x183564203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r13 + r14 + 24], 4 + QUAD $0x183564203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r13 + rsi + 24], 5 + QUAD $0x183d64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r13 + rdi + 24], 6 + QUAD $0x180d64203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r13 + r9 + 24], 7 + QUAD $0x180564203a0f4566; BYTE $0x08 // pinsrb xmm12, byte [r13 + rax + 24], 8 + QUAD $0x183d64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r13 + r15 + 24], 9 + QUAD $0x180564203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r13 + r8 + 24], 10 + QUAD $0x180d64203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r13 + rcx + 24], 11 + QUAD $0x181564203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r13 + rdx + 24], 12 + QUAD $0x182564203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r13 + r12 + 24], 13 + QUAD $0x181d64203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r13 + rbx + 24], 14 + QUAD $0x181564203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r13 + r10 + 24], 15 + LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 + LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 + QUAD $0x191d6c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r13 + r11 + 25], 3 + QUAD $0x19356c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r13 + r14 + 25], 4 + QUAD $0x19356c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r13 + rsi + 25], 5 + QUAD $0x193d6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r13 + rdi + 25], 6 + QUAD $0x190d6c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r13 + r9 + 25], 7 + QUAD $0x19056c203a0f4566; BYTE $0x08 // pinsrb xmm13, byte [r13 + rax + 25], 8 + QUAD $0x193d6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r13 + r15 + 25], 9 + QUAD $0x19056c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r13 + r8 + 25], 10 + QUAD $0x190d6c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r13 + rcx + 25], 11 + QUAD $0x19156c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r13 + rdx + 25], 12 + QUAD $0x19256c203a0f4766; BYTE $0x0d // pinsrb xmm13, byte [r13 + r12 + 25], 13 + QUAD $0x191d6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r13 + rbx + 25], 14 + QUAD $0x19156c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r13 + r10 + 25], 15 + QUAD $0x1a1d44203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r13 + r11 + 26], 3 + QUAD $0x1a3544203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r13 + r14 + 26], 4 + QUAD $0x1a3544203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r13 + rsi + 26], 5 + QUAD $0x1a3d44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r13 + rdi + 26], 6 + QUAD $0x1a0d44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r13 + r9 + 26], 7 + QUAD $0x1a0544203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r13 + rax + 26], 8 + QUAD $0x1a3d44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r13 + r15 + 26], 9 + QUAD $0x1a0544203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r13 + r8 + 26], 10 + QUAD $0x1a0d44203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r13 + rcx + 26], 11 + QUAD $0x1a1544203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r13 + rdx + 26], 12 + QUAD $0x1a2544203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r13 + r12 + 26], 13 + QUAD $0x1a1d44203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r13 + rbx + 26], 14 + QUAD $0x1a1544203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r13 + r10 + 26], 15 + QUAD $0x1b1d5c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r13 + r11 + 27], 3 + QUAD $0x1b355c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r13 + r14 + 27], 4 + QUAD $0x1b355c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r13 + rsi + 27], 5 + QUAD $0x1b3d5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r13 + rdi + 27], 6 + QUAD $0x1b0d5c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r13 + r9 + 27], 7 + QUAD $0x1b055c203a0f4566; BYTE $0x08 // pinsrb xmm11, byte [r13 + rax + 27], 8 + QUAD $0x1b3d5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r13 + r15 + 27], 9 + QUAD $0x1b055c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r13 + r8 + 27], 10 + QUAD $0x1b0d5c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r13 + rcx + 27], 11 + QUAD $0x1b155c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r13 + rdx + 27], 12 + QUAD $0x1b255c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r13 + r12 + 27], 13 + QUAD $0x1b1d5c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r13 + rbx + 27], 14 + LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 + QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI5_16] */ + LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 + QUAD $0x1b155c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r13 + r10 + 27], 15 + LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 + QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI5_17] */ + LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 + QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI5_18] */ + LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 + QUAD $0x1c1d7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r13 + r11 + 28], 3 + QUAD $0x1d1d4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r13 + r11 + 29], 3 + QUAD $0x1e1d54203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r13 + r11 + 30], 3 + QUAD $0x1f1d74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r13 + r11 + 31], 3 + QUAD $0x1c357c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r13 + r14 + 28], 4 + QUAD $0x1d354c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r14 + 29], 4 + QUAD $0x1e3554203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r13 + r14 + 30], 4 + QUAD $0x1f3574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r14 + 31], 4 + QUAD $0x1c357c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r13 + rsi + 28], 5 + QUAD $0x1d354c203a0f4566; BYTE $0x05 // pinsrb xmm9, byte [r13 + rsi + 29], 5 + QUAD $0x1e3554203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r13 + rsi + 30], 5 + QUAD $0x1f3574203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r13 + rsi + 31], 5 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x1c3d7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r13 + rdi + 28], 6 + QUAD $0x1d3d4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r13 + rdi + 29], 6 + QUAD $0x1e3d54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r13 + rdi + 30], 6 + QUAD $0x1f3d74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r13 + rdi + 31], 6 + QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] + WORD $0x894c; BYTE $0xce // mov rsi, r9 + QUAD $0x1c0d7c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r13 + r9 + 28], 7 + QUAD $0x1d0d4c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r13 + r9 + 29], 7 + QUAD $0x1e0d54203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r13 + r9 + 30], 7 + QUAD $0x1f0d74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r13 + r9 + 31], 7 + QUAD $0x1c057c203a0f4566; BYTE $0x08 // pinsrb xmm15, byte [r13 + rax + 28], 8 + QUAD $0x1d054c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r13 + rax + 29], 8 + QUAD $0x1e0554203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r13 + rax + 30], 8 + QUAD $0x1f0574203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r13 + rax + 31], 8 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x1c3d7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r13 + r15 + 28], 9 + QUAD $0x1d3d4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r13 + r15 + 29], 9 + QUAD $0x1e3d54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r13 + r15 + 30], 9 + QUAD $0x1f3d74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r13 + r15 + 31], 9 + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + QUAD $0x1c057c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r13 + r8 + 28], 10 + QUAD $0x1d054c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r13 + r8 + 29], 10 + QUAD $0x1e0554203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r13 + r8 + 30], 10 + QUAD $0x1f0574203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r13 + r8 + 31], 10 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x1c0d7c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r13 + rcx + 28], 11 + QUAD $0x1d0d4c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r13 + rcx + 29], 11 + QUAD $0x1e0d54203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r13 + rcx + 30], 11 + QUAD $0x1f0d74203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r13 + rcx + 31], 11 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x1c157c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r13 + rdx + 28], 12 + QUAD $0x1d154c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r13 + rdx + 29], 12 + QUAD $0x1e1554203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r13 + rdx + 30], 12 + QUAD $0x1f1574203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r13 + rdx + 31], 12 + QUAD $0x1c257c203a0f4766; BYTE $0x0d // pinsrb xmm15, byte [r13 + r12 + 28], 13 + QUAD $0x1d254c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r13 + r12 + 29], 13 + QUAD $0x1e2554203a0f4766; BYTE $0x0d // pinsrb xmm10, byte [r13 + r12 + 30], 13 + QUAD $0x1f2574203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r13 + r12 + 31], 13 + QUAD $0x1c1d7c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r13 + rbx + 28], 14 + QUAD $0x1d1d4c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r13 + rbx + 29], 14 + QUAD $0x1e1d54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r13 + rbx + 30], 14 + QUAD $0x1f1d74203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r13 + rbx + 31], 14 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x1c157c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r13 + r10 + 28], 15 + QUAD $0x1d154c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r13 + r10 + 29], 15 + QUAD $0x1e1554203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r13 + r10 + 30], 15 + LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 + QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI5_19] */ + LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 + QUAD $0x1f1574203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r13 + r10 + 31], 15 + QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 + LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 + LONG $0xdf0f4466; BYTE $0xcd // pandn xmm9, xmm5 + LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 + LONG $0xdf0f4466; BYTE $0xd7 // pandn xmm10, xmm7 + LONG $0xeb0f4566; BYTE $0xd1 // por xmm10, xmm9 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + LONG $0xf4df0f66 // pandn xmm6, xmm4 + LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 + LONG $0xc6600f66 // punpcklbw xmm0, xmm6 + QUAD $0x0000d0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 208] + LONG $0xcb6f0f66 // movdqa xmm1, xmm3 + QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] + LONG $0xcc600f66 // punpcklbw xmm1, xmm4 + LONG $0xd16f0f66 // movdqa xmm2, xmm1 + LONG $0xd0610f66 // punpcklwd xmm2, xmm0 + LONG $0xc8690f66 // punpckhwd xmm1, xmm0 + LONG $0x680f4466; BYTE $0xc6 // punpckhbw xmm8, xmm6 + LONG $0xdc680f66 // punpckhbw xmm3, xmm4 LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xd110 // pblendvb xmm2, xmm9, xmm0 - LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x44b70f41; WORD $0x3e3e // movzx eax, word [r14 + rdi + 62] - LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0xc06e0f66 // movd xmm0, eax - QUAD $0x013e0e44c40f4166 // pinsrw xmm0, word [r14 + rcx + 62], 1 - QUAD $0x023e3e44c40f4366 // pinsrw xmm0, word [r14 + r15 + 62], 2 - QUAD $0x033e3644c40f4166 // pinsrw xmm0, word [r14 + rsi + 62], 3 - QUAD $0x043e2644c40f4366 // pinsrw xmm0, word [r14 + r12 + 62], 4 - QUAD $0x053e1644c40f4166 // pinsrw xmm0, word [r14 + rdx + 62], 5 - QUAD $0x063e1e44c40f4166 // pinsrw xmm0, word [r14 + rbx + 62], 6 - QUAD $0x073e0e44c40f4366 // pinsrw xmm0, word [r14 + r9 + 62], 7 - LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xd6eb0f66 // por xmm2, xmm6 - LONG $0x380f4566; WORD $0xd110 // pblendvb xmm10, xmm9, xmm0 - LONG $0xeb0f4466; BYTE $0xd2 // por xmm10, xmm2 - LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 - LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 - LONG $0x6c0f4166; BYTE $0xd2 // punpcklqdq xmm2, xmm10 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI5_15] */ - LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 - LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 - LONG $0xc2610f66 // punpcklwd xmm0, xmm2 - LONG $0x600f4566; BYTE $0xc2 // punpcklbw xmm8, xmm10 - LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 - LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - LONG $0x7f0f45f3; WORD $0x8824 // movdqu oword [r8 + 4*rcx], xmm12 - LONG $0x2444894c; BYTE $0x08 // mov qword [rsp + 8], r8 - LONG $0x7f0f41f3; WORD $0x8844; BYTE $0x10 // movdqu oword [r8 + 4*rcx + 16], xmm0 - LONG $0x08c18348 // add rcx, 8 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] - JNE LBB5_111 - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - LONG $0x24543b4c; BYTE $0x28 // cmp r10, qword [rsp + 40] - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - LONG $0x245c8b44; BYTE $0x10 // mov r11d, dword [rsp + 16] - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - JNE LBB5_113 - JMP LBB5_116 - -LBB5_133: - LONG $0xf8e28349 // and r10, -8 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x014c; BYTE $0xf0 // add rax, r14 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - LONG $0x2454894c; BYTE $0x28 // mov qword [rsp + 40], r10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x6e0f4166; BYTE $0xc3 // movd xmm0, r11d - LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 - LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 - WORD $0xff31 // xor edi, edi - LONG $0xef0f4566; BYTE $0xc9 // pxor xmm9, xmm9 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xd8 // punpckhwd xmm3, xmm8 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + LONG $0x7f0f41f3; WORD $0x8b5c; BYTE $0x30 // movdqu oword [r11 + 4*rcx + 48], xmm3 + LONG $0x7f0f41f3; WORD $0x8b44; BYTE $0x20 // movdqu oword [r11 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x8b4c; BYTE $0x10 // movdqu oword [r11 + 4*rcx + 16], xmm1 + LONG $0x7f0f41f3; WORD $0x8b14 // movdqu oword [r11 + 4*rcx], xmm2 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + JNE LBB5_215 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x24748a44; BYTE $0x0c // mov r14b, byte [rsp + 12] + QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] + QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] + JNE LBB5_154 + JMP LBB5_158 + +LBB5_217: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + QUAD $0x000000a8248c8948 // mov qword [rsp + 168], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + LONG $0xc6b60f41 // movzx eax, r14b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + WORD $0xc031 // xor eax, eax + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 -LBB5_134: - LONG $0x247c8948; BYTE $0x40 // mov qword [rsp + 64], rdi - LONG $0x06e7c148 // shl rdi, 6 - WORD $0x8949; BYTE $0xff // mov r15, rdi - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - WORD $0x8949; BYTE $0xfc // mov r12, rdi - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - WORD $0x8948; BYTE $0xfb // mov rbx, rdi - WORD $0x8949; BYTE $0xf9 // mov r9, rdi - LONG $0x04b70f41; BYTE $0x3e // movzx eax, word [r14 + rdi] - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f41; WORD $0x023e // movzx eax, word [r14 + rdi + 2] - LONG $0xc06e0f66 // movd xmm0, eax - LONG $0x44b70f41; WORD $0x043e // movzx eax, word [r14 + rdi + 4] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x44b70f41; WORD $0x063e // movzx eax, word [r14 + rdi + 6] - LONG $0xf86e0f66 // movd xmm7, eax - LONG $0x44b70f41; WORD $0x083e // movzx eax, word [r14 + rdi + 8] - LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax - LONG $0x44b70f41; WORD $0x0a3e // movzx eax, word [r14 + rdi + 10] - LONG $0xe06e0f66 // movd xmm4, eax - LONG $0x44b70f41; WORD $0x0c3e // movzx eax, word [r14 + rdi + 12] - LONG $0x44b70f45; WORD $0x0e3e // movzx r8d, word [r14 + rdi + 14] - LONG $0x54b70f45; WORD $0x103e // movzx r10d, word [r14 + rdi + 16] - LONG $0x6cb70f45; WORD $0x123e // movzx r13d, word [r14 + rdi + 18] - LONG $0x4cb70f41; WORD $0x143e // movzx ecx, word [r14 + rdi + 20] - LONG $0x20244c89 // mov dword [rsp + 32], ecx - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - LONG $0x40c98348 // or rcx, 64 +LBB5_218: + QUAD $0x000000a024848948 // mov qword [rsp + 160], rax + LONG $0x05e0c148 // shl rax, 5 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + WORD $0x8949; BYTE $0xc6 // mov r14, rax + WORD $0x8949; BYTE $0xc7 // mov r15, rax + WORD $0x8949; BYTE $0xc2 // mov r10, rax + WORD $0x8949; BYTE $0xc3 // mov r11, rax + WORD $0x8949; BYTE $0xc4 // mov r12, rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax + LONG $0x070cb60f // movzx ecx, byte [rdi + rax] + LONG $0xe16e0f66 // movd xmm4, ecx + LONG $0x074cb60f; BYTE $0x01 // movzx ecx, byte [rdi + rax + 1] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x074cb60f; BYTE $0x02 // movzx ecx, byte [rdi + rax + 2] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x074cb60f; BYTE $0x03 // movzx ecx, byte [rdi + rax + 3] + LONG $0xf96e0f66 // movd xmm7, ecx + LONG $0x074cb60f; BYTE $0x04 // movzx ecx, byte [rdi + rax + 4] + LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx + LONG $0x074cb60f; BYTE $0x05 // movzx ecx, byte [rdi + rax + 5] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x074cb60f; BYTE $0x06 // movzx ecx, byte [rdi + rax + 6] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x074cb60f; BYTE $0x07 // movzx ecx, byte [rdi + rax + 7] + LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx + LONG $0x074cb60f; BYTE $0x08 // movzx ecx, byte [rdi + rax + 8] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 + LONG $0x074cb60f; BYTE $0x09 // movzx ecx, byte [rdi + rax + 9] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x074cb60f; BYTE $0x0a // movzx ecx, byte [rdi + rax + 10] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x074cb60f; BYTE $0x0b // movzx ecx, byte [rdi + rax + 11] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x074cb60f; BYTE $0x0c // movzx ecx, byte [rdi + rax + 12] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 + LONG $0x074cb60f; BYTE $0x0d // movzx ecx, byte [rdi + rax + 13] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x074cb60f; BYTE $0x0e // movzx ecx, byte [rdi + rax + 14] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x074cb60f; BYTE $0x0f // movzx ecx, byte [rdi + rax + 15] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 + LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x20cd8349 // or r13, 32 + LONG $0x40c88349 // or r8, 64 + LONG $0x60ce8349 // or r14, 96 LONG $0x80cf8149; WORD $0x0000; BYTE $0x00 // or r15, 128 - LONG $0xc0ce8148; WORD $0x0000; BYTE $0x00 // or rsi, 192 - LONG $0x00cc8149; WORD $0x0001; BYTE $0x00 // or r12, 256 - LONG $0x40ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 320 - LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 - LONG $0xc40f4166; WORD $0x0e2c; BYTE $0x01 // pinsrw xmm5, word [r14 + rcx], 1 - LONG $0xc40f4366; WORD $0x3e2c; BYTE $0x02 // pinsrw xmm5, word [r14 + r15], 2 - LONG $0xc40f4166; WORD $0x362c; BYTE $0x03 // pinsrw xmm5, word [r14 + rsi], 3 - LONG $0xc40f4366; WORD $0x262c; BYTE $0x04 // pinsrw xmm5, word [r14 + r12], 4 - LONG $0xc40f4166; WORD $0x162c; BYTE $0x05 // pinsrw xmm5, word [r14 + rdx], 5 - LONG $0xc40f4166; WORD $0x1e2c; BYTE $0x06 // pinsrw xmm5, word [r14 + rbx], 6 - QUAD $0x01020e44c40f4166 // pinsrw xmm0, word [r14 + rcx + 2], 1 - QUAD $0x02023e44c40f4366 // pinsrw xmm0, word [r14 + r15 + 2], 2 - QUAD $0x03023644c40f4166 // pinsrw xmm0, word [r14 + rsi + 2], 3 - QUAD $0x04022644c40f4366 // pinsrw xmm0, word [r14 + r12 + 2], 4 - QUAD $0x05021644c40f4166 // pinsrw xmm0, word [r14 + rdx + 2], 5 - QUAD $0x06021e44c40f4166 // pinsrw xmm0, word [r14 + rbx + 2], 6 - LONG $0xc0c98149; WORD $0x0001; BYTE $0x00 // or r9, 448 - QUAD $0x07020e44c40f4366 // pinsrw xmm0, word [r14 + r9 + 2], 7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f41; WORD $0x163e // movzx eax, word [r14 + rdi + 22] - LONG $0x18244489 // mov dword [rsp + 24], eax - LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 - QUAD $0x01040e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 4], 1 - QUAD $0x02043e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 4], 2 - QUAD $0x0304364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 4], 3 - QUAD $0x0404264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 4], 4 - QUAD $0x0504164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 4], 5 - QUAD $0x06041e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 4], 6 - QUAD $0x07040e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 4], 7 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - QUAD $0x000080b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 128[rbp] /* [rip + .LCPI5_8] */ - LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 - LONG $0x380f4166; WORD $0xd910 // pblendvb xmm3, xmm9, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x000090bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 144[rbp] /* [rip + .LCPI5_9] */ - LONG $0x6f0f4166; BYTE $0xf7 // movdqa xmm6, xmm15 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xc8 // movd xmm1, r8d - LONG $0x5cb70f45; WORD $0x183e // movzx r11d, word [r14 + rdi + 24] - LONG $0xc40f4366; WORD $0x0e2c; BYTE $0x07 // pinsrw xmm5, word [r14 + r9], 7 - LONG $0x750f4166; BYTE $0xeb // pcmpeqw xmm5, xmm11 + LONG $0xa0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 160 + LONG $0xc0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 192 + LONG $0xe0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 224 + LONG $0x00c98149; WORD $0x0001; BYTE $0x00 // or r9, 256 + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x20ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 288 + LONG $0x24548948; BYTE $0x38 // mov qword [rsp + 56], rdx + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 + LONG $0x60ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 352 + LONG $0x24748948; BYTE $0x40 // mov qword [rsp + 64], rsi + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 + LONG $0x24748948; BYTE $0x58 // mov qword [rsp + 88], rsi + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 + LONG $0x244c8948; BYTE $0x18 // mov qword [rsp + 24], rcx + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0xc0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 448 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx + LONG $0x01e00d48; WORD $0x0000 // or rax, 480 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + QUAD $0x012f24203a0f4266 // pinsrb xmm4, byte [rdi + r13], 1 + LONG $0x2444894c; BYTE $0x68 // mov qword [rsp + 104], r8 + QUAD $0x020724203a0f4266 // pinsrb xmm4, byte [rdi + r8], 2 + LONG $0x2474894c; BYTE $0x20 // mov qword [rsp + 32], r14 + QUAD $0x033724203a0f4266 // pinsrb xmm4, byte [rdi + r14], 3 + QUAD $0x043f24203a0f4266 // pinsrb xmm4, byte [rdi + r15], 4 + LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 + QUAD $0x051724203a0f4266 // pinsrb xmm4, byte [rdi + r10], 5 + QUAD $0x061f24203a0f4266 // pinsrb xmm4, byte [rdi + r11], 6 + QUAD $0x072724203a0f4266 // pinsrb xmm4, byte [rdi + r12], 7 + LONG $0x244c894c; BYTE $0x50 // mov qword [rsp + 80], r9 + QUAD $0x080f24203a0f4266 // pinsrb xmm4, byte [rdi + r9], 8 + LONG $0x203a0f66; WORD $0x1724; BYTE $0x09 // pinsrb xmm4, byte [rdi + rdx], 9 + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + LONG $0x203a0f66; WORD $0x1f24; BYTE $0x0a // pinsrb xmm4, byte [rdi + rbx], 10 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + LONG $0x203a0f66; WORD $0x1f24; BYTE $0x0b // pinsrb xmm4, byte [rdi + rbx], 11 + LONG $0x203a0f66; WORD $0x3724; BYTE $0x0c // pinsrb xmm4, byte [rdi + rsi], 12 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + LONG $0x203a0f66; WORD $0x0724; BYTE $0x0d // pinsrb xmm4, byte [rdi + rax], 13 + LONG $0x203a0f66; WORD $0x0f24; BYTE $0x0e // pinsrb xmm4, byte [rdi + rcx], 14 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + LONG $0x203a0f66; WORD $0x0724; BYTE $0x0f // pinsrb xmm4, byte [rdi + rax], 15 + QUAD $0x012f5c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdi + r13 + 1], 1 + LONG $0x246c894c; BYTE $0x30 // mov qword [rsp + 48], r13 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0201075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 1], 2 + QUAD $0x01375c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r14 + 1], 3 + QUAD $0x013f5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r15 + 1], 4 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x01175c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdi + r10 + 1], 5 + QUAD $0x011f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r11 + 1], 6 + WORD $0x894d; BYTE $0xda // mov r10, r11 + QUAD $0x01275c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r12 + 1], 7 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x010f5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdi + r9 + 1], 8 + QUAD $0x0901175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 1], 9 + QUAD $0x01075c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdi + r8 + 1], 10 + QUAD $0x0b011f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 1], 11 + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x0c01375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 1], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0d01375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 1], 13 + QUAD $0x0e010f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 1], 14 + QUAD $0x0000b0248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 176] + LONG $0xe1740f66 // pcmpeqb xmm4, xmm1 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0f01075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 1], 15 + LONG $0xd9740f66 // pcmpeqb xmm3, xmm1 + QUAD $0x00000100856f0f66 // movdqa xmm0, oword 256[rbp] /* [rip + .LCPI5_16] */ + LONG $0xd8df0f66 // pandn xmm3, xmm0 + LONG $0xdcfc0f66 // paddb xmm3, xmm4 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + LONG $0x0f74b60f; BYTE $0x10 // movzx esi, byte [rdi + rcx + 16] + LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi + QUAD $0x022f6c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdi + r13 + 2], 1 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x02276c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rdi + r12 + 2], 2 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x021f6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r11 + 2], 3 + QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 + QUAD $0x02376c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdi + r14 + 2], 4 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x05021f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 2], 5 + WORD $0x894d; BYTE $0xd1 // mov r9, r10 + QUAD $0x02176c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r10 + 2], 6 + WORD $0x894d; BYTE $0xfa // mov r10, r15 + QUAD $0x023f6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r15 + 2], 7 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x023f6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdi + r15 + 2], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0902076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 2], 9 + QUAD $0x02076c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r8 + 2], 10 + QUAD $0x0b02176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 2], 11 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0c020f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 2], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0d02376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 2], 13 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0e02176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 2], 14 + LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] + QUAD $0x022f6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdi + r13 + 2], 15 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0103077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 3], 1 + QUAD $0x03277c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rdi + r12 + 3], 2 + QUAD $0x031f7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r11 + 3], 3 + QUAD $0x03377c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdi + r14 + 3], 4 + QUAD $0x05031f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 3], 5 + QUAD $0x030f7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r9 + 3], 6 + QUAD $0x03177c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r10 + 3], 7 + QUAD $0x033f7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdi + r15 + 3], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0903077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 3], 9 + QUAD $0x03077c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdi + r8 + 3], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0b03077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 3], 11 + QUAD $0x0c030f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 3], 12 + QUAD $0x0d03377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 3], 13 + QUAD $0x0e03177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 3], 14 + QUAD $0x032f7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdi + r13 + 3], 15 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x04074c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdi + rax + 4], 1 + QUAD $0x04274c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rdi + r12 + 4], 2 + QUAD $0x041f4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdi + r11 + 4], 3 + QUAD $0x04374c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdi + r14 + 4], 4 + QUAD $0x041f4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdi + rbx + 4], 5 + QUAD $0x040f4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r9 + 4], 6 + LONG $0x244c894c; BYTE $0x78 // mov qword [rsp + 120], r9 + QUAD $0x04174c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r10 + 4], 7 + QUAD $0x043f4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdi + r15 + 4], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x04074c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdi + rax + 4], 9 + QUAD $0x04074c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdi + r8 + 4], 10 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + QUAD $0x04074c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdi + r8 + 4], 11 + QUAD $0x040f4c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rdi + rcx + 4], 12 + QUAD $0x04374c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdi + rsi + 4], 13 + QUAD $0x04174c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdi + rdx + 4], 14 + QUAD $0x042f4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdi + r13 + 4], 15 + LONG $0xe9740f66 // pcmpeqb xmm5, xmm1 + QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI5_17] */ + LONG $0xe8df0f66 // pandn xmm5, xmm0 + LONG $0xf9740f66 // pcmpeqb xmm7, xmm1 + QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI5_18] */ + LONG $0xf8df0f66 // pandn xmm7, xmm0 + LONG $0xfdeb0f66 // por xmm7, xmm5 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + LONG $0x1774b60f; BYTE $0x11 // movzx esi, byte [rdi + rdx + 17] + LONG $0xe66e0f66 // movd xmm4, esi + LONG $0x740f4466; BYTE $0xc9 // pcmpeqb xmm9, xmm1 + QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI5_19] */ + LONG $0xdf0f4466; BYTE $0xc8 // pandn xmm9, xmm0 + LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 + LONG $0x1774b60f; BYTE $0x12 // movzx esi, byte [rdi + rdx + 18] + LONG $0xfe6e0f66 // movd xmm7, esi LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 - LONG $0xe8ef0f66 // pxor xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - QUAD $0x01060e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 6], 1 - QUAD $0x02063e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 6], 2 - QUAD $0x0306367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 6], 3 - QUAD $0x0406267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 6], 4 - QUAD $0x0506167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 6], 5 - QUAD $0x06061e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 6], 6 - QUAD $0x07060e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 6], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x01080e44c40f4566 // pinsrw xmm8, word [r14 + rcx + 8], 1 - QUAD $0x02083e44c40f4766 // pinsrw xmm8, word [r14 + r15 + 8], 2 - QUAD $0x03083644c40f4566 // pinsrw xmm8, word [r14 + rsi + 8], 3 - QUAD $0x04082644c40f4766 // pinsrw xmm8, word [r14 + r12 + 8], 4 - QUAD $0x05081644c40f4566 // pinsrw xmm8, word [r14 + rdx + 8], 5 - QUAD $0x06081e44c40f4566 // pinsrw xmm8, word [r14 + rbx + 8], 6 - QUAD $0x07080e44c40f4766 // pinsrw xmm8, word [r14 + r9 + 8], 7 - LONG $0xddf80f66 // psubb xmm3, xmm5 - QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc76f0f66 // movdqa xmm0, xmm7 - LONG $0x380f4566; WORD $0xe110 // pblendvb xmm12, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d - LONG $0x44b70f45; WORD $0x1a3e // movzx r8d, word [r14 + rdi + 26] - LONG $0x750f4566; BYTE $0xc3 // pcmpeqw xmm8, xmm11 - LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 - LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 - QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xf5 // movd xmm6, r13d - LONG $0x6cb70f45; WORD $0x1c3e // movzx r13d, word [r14 + rdi + 28] - QUAD $0x010a0e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 10], 1 - QUAD $0x020a3e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 10], 2 - QUAD $0x030a3664c40f4166 // pinsrw xmm4, word [r14 + rsi + 10], 3 - QUAD $0x040a2664c40f4366 // pinsrw xmm4, word [r14 + r12 + 10], 4 - QUAD $0x050a1664c40f4166 // pinsrw xmm4, word [r14 + rdx + 10], 5 - QUAD $0x060a1e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 10], 6 - QUAD $0x070a0e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 10], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - QUAD $0x010c0e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 12], 1 - QUAD $0x020c3e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 12], 2 - QUAD $0x030c3654c40f4166 // pinsrw xmm2, word [r14 + rsi + 12], 3 - QUAD $0x040c2654c40f4366 // pinsrw xmm2, word [r14 + r12 + 12], 4 - QUAD $0x050c1654c40f4166 // pinsrw xmm2, word [r14 + rdx + 12], 5 - QUAD $0x060c1e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 12], 6 - LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI5_12] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - LONG $0x646e0f66; WORD $0x2024 // movd xmm4, dword [rsp + 32] - LONG $0x54b70f45; WORD $0x1e3e // movzx r10d, word [r14 + rdi + 30] - QUAD $0x070c0e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 12], 7 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 - QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI5_13] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - LONG $0x5c6e0f66; WORD $0x1824 // movd xmm3, dword [rsp + 24] - LONG $0x44b70f41; WORD $0x203e // movzx eax, word [r14 + rdi + 32] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x010e0e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 14], 1 - QUAD $0x020e3e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 14], 2 - QUAD $0x030e364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 14], 3 - QUAD $0x040e264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 14], 4 - QUAD $0x050e164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 14], 5 - QUAD $0x060e1e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 14], 6 - LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 - LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d - LONG $0x44b70f41; WORD $0x223e // movzx eax, word [r14 + rdi + 34] - LONG $0x20244489 // mov dword [rsp + 32], eax - QUAD $0x070e0e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 14], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - QUAD $0x01120e74c40f4166 // pinsrw xmm6, word [r14 + rcx + 18], 1 - QUAD $0x02123e74c40f4366 // pinsrw xmm6, word [r14 + r15 + 18], 2 - QUAD $0x03123674c40f4166 // pinsrw xmm6, word [r14 + rsi + 18], 3 - QUAD $0x04122674c40f4366 // pinsrw xmm6, word [r14 + r12 + 18], 4 - QUAD $0x05121674c40f4166 // pinsrw xmm6, word [r14 + rdx + 18], 5 - QUAD $0x06121e74c40f4166 // pinsrw xmm6, word [r14 + rbx + 18], 6 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x07120e74c40f4366 // pinsrw xmm6, word [r14 + r9 + 18], 7 - LONG $0x750f4166; BYTE $0xf3 // pcmpeqw xmm6, xmm11 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - QUAD $0x0000e0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 224[rbp] /* [rip + .LCPI5_14] */ - LONG $0x6f0f4566; BYTE $0xe2 // movdqa xmm12, xmm10 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4566; WORD $0xe110 // pblendvb xmm12, xmm9, xmm0 - LONG $0x6f0f4566; BYTE $0xc6 // movdqa xmm8, xmm14 - LONG $0xc66f0f66 // movdqa xmm0, xmm6 - LONG $0x380f4566; WORD $0xc110 // pblendvb xmm8, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xc8 // movd xmm1, r8d - LONG $0x5cb70f45; WORD $0x243e // movzx r11d, word [r14 + rdi + 36] - QUAD $0x01100e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 16], 1 - QUAD $0x02103e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 16], 2 - QUAD $0x0310367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 16], 3 - QUAD $0x0410267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 16], 4 - QUAD $0x0510167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 16], 5 - QUAD $0x06101e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 16], 6 - QUAD $0x01140e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 20], 1 - QUAD $0x02143e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 20], 2 - QUAD $0x03143664c40f4166 // pinsrw xmm4, word [r14 + rsi + 20], 3 - QUAD $0x04142664c40f4366 // pinsrw xmm4, word [r14 + r12 + 20], 4 - QUAD $0x05141664c40f4166 // pinsrw xmm4, word [r14 + rdx + 20], 5 - QUAD $0x06141e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 20], 6 - QUAD $0x07140e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 20], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4566; WORD $0xf910 // pblendvb xmm15, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xe5 // movd xmm4, r13d - LONG $0x6cb70f45; WORD $0x263e // movzx r13d, word [r14 + rdi + 38] - QUAD $0x07100e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 16], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI5_22] */ - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x01160e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 22], 1 - QUAD $0x02163e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 22], 2 - QUAD $0x0316365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 22], 3 - QUAD $0x0416265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 22], 4 - QUAD $0x0516165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 22], 5 - QUAD $0x06161e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 22], 6 - QUAD $0x07160e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 22], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x01180e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 24], 1 - QUAD $0x02183e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 24], 2 - QUAD $0x03183654c40f4166 // pinsrw xmm2, word [r14 + rsi + 24], 3 - QUAD $0x04182654c40f4366 // pinsrw xmm2, word [r14 + r12 + 24], 4 - QUAD $0x05181654c40f4166 // pinsrw xmm2, word [r14 + rdx + 24], 5 - QUAD $0x06181e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 24], 6 - QUAD $0x07180e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 24], 7 - LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 - QUAD $0x0000a0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4566; WORD $0xf110 // pblendvb xmm14, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d - LONG $0x44b70f45; WORD $0x283e // movzx r8d, word [r14 + rdi + 40] - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4566; BYTE $0xf7 // por xmm14, xmm15 - QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - LONG $0x7c6e0f66; WORD $0x1824 // movd xmm7, dword [rsp + 24] - LONG $0x54b70f45; WORD $0x2a3e // movzx r10d, word [r14 + rdi + 42] - QUAD $0x011a0e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 26], 1 - QUAD $0x021a3e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 26], 2 - QUAD $0x031a364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 26], 3 - QUAD $0x041a264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 26], 4 - QUAD $0x051a164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 26], 5 - QUAD $0x061a1e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 26], 6 - QUAD $0x071a0e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 26], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x011c0e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 28], 1 - QUAD $0x021c3e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 28], 2 - QUAD $0x031c3664c40f4166 // pinsrw xmm4, word [r14 + rsi + 28], 3 - QUAD $0x041c2664c40f4366 // pinsrw xmm4, word [r14 + r12 + 28], 4 - QUAD $0x051c1664c40f4166 // pinsrw xmm4, word [r14 + rdx + 28], 5 - QUAD $0x061c1e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 28], 6 - LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 - QUAD $0x0000c0bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 192[rbp] /* [rip + .LCPI5_12] */ - LONG $0x6f0f4166; BYTE $0xef // movdqa xmm5, xmm15 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - LONG $0x546e0f66; WORD $0x2024 // movd xmm2, dword [rsp + 32] - LONG $0x44b70f41; WORD $0x2c3e // movzx eax, word [r14 + rdi + 44] - LONG $0x18244489 // mov dword [rsp + 24], eax - QUAD $0x071c0e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 28], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 - QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI5_13] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x5cb70f45; WORD $0x2e3e // movzx r11d, word [r14 + rdi + 46] - QUAD $0x011e0e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 30], 1 - QUAD $0x021e3e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 30], 2 - QUAD $0x031e365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 30], 3 - QUAD $0x041e265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 30], 4 - QUAD $0x051e165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 30], 5 - QUAD $0x061e1e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 30], 6 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0x6e0f4166; BYTE $0xcd // movd xmm1, r13d - LONG $0x44b70f41; WORD $0x303e // movzx eax, word [r14 + rdi + 48] - LONG $0x20244489 // mov dword [rsp + 32], eax - QUAD $0x071e0e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 30], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - QUAD $0x01220e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 34], 1 - QUAD $0x02223e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 34], 2 - QUAD $0x03223654c40f4166 // pinsrw xmm2, word [r14 + rsi + 34], 3 - QUAD $0x04222654c40f4366 // pinsrw xmm2, word [r14 + r12 + 34], 4 - QUAD $0x05221654c40f4166 // pinsrw xmm2, word [r14 + rdx + 34], 5 - QUAD $0x06221e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 34], 6 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07220e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 34], 7 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 - LONG $0x6f0f4566; BYTE $0xea // movdqa xmm13, xmm10 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4566; WORD $0xe910 // pblendvb xmm13, xmm9, xmm0 - QUAD $0x000080856f0f4466; BYTE $0x00 // movdqa xmm8, oword 128[rbp] /* [rip + .LCPI5_8] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xc110 // pblendvb xmm8, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xd0 // movd xmm2, r8d - LONG $0x6cb70f45; WORD $0x323e // movzx r13d, word [r14 + rdi + 50] - QUAD $0x01200e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 32], 1 - QUAD $0x02203e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 32], 2 - QUAD $0x0320367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 32], 3 - QUAD $0x0420267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 32], 4 - QUAD $0x0520167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 32], 5 - QUAD $0x06201e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 32], 6 - QUAD $0x01240e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 36], 1 - QUAD $0x02243e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 36], 2 - QUAD $0x03243664c40f4166 // pinsrw xmm4, word [r14 + rsi + 36], 3 - QUAD $0x04242664c40f4366 // pinsrw xmm4, word [r14 + r12 + 36], 4 - QUAD $0x05241664c40f4166 // pinsrw xmm4, word [r14 + rdx + 36], 5 - QUAD $0x06241e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 36], 6 - QUAD $0x07240e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 36], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 - QUAD $0x00000090b56f0f66 // movdqa xmm6, oword 144[rbp] /* [rip + .LCPI5_9] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d - LONG $0x54b70f45; WORD $0x343e // movzx r10d, word [r14 + rdi + 52] - QUAD $0x07200e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 32], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - LONG $0x760f4566; BYTE $0xf6 // pcmpeqd xmm14, xmm14 - LONG $0xef0f4166; BYTE $0xfe // pxor xmm7, xmm14 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x01260e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 38], 1 - QUAD $0x02263e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 38], 2 - QUAD $0x0326364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 38], 3 - QUAD $0x0426264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 38], 4 - QUAD $0x0526164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 38], 5 - QUAD $0x06261e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 38], 6 - QUAD $0x07260e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 38], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x01280e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 40], 1 - QUAD $0x02283e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 40], 2 - QUAD $0x03283654c40f4166 // pinsrw xmm2, word [r14 + rsi + 40], 3 - QUAD $0x04282654c40f4366 // pinsrw xmm2, word [r14 + r12 + 40], 4 - QUAD $0x05281654c40f4166 // pinsrw xmm2, word [r14 + rdx + 40], 5 - QUAD $0x06281e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 40], 6 - QUAD $0x07280e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 40], 7 - LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 - QUAD $0x000000a0ad6f0f66 // movdqa xmm5, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] - LONG $0x44b70f45; WORD $0x363e // movzx r8d, word [r14 + rdi + 54] - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeeeb0f66 // por xmm5, xmm6 - QUAD $0x000000b0b56f0f66 // movdqa xmm6, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x44b70f41; WORD $0x383e // movzx eax, word [r14 + rdi + 56] - QUAD $0x012a0e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 42], 1 - QUAD $0x022a3e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 42], 2 - QUAD $0x032a365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 42], 3 - QUAD $0x042a265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 42], 4 - QUAD $0x052a165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 42], 5 - QUAD $0x062a1e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 42], 6 - QUAD $0x072a0e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 42], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x012c0e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 44], 1 - QUAD $0x022c3e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 44], 2 - QUAD $0x032c364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 44], 3 - QUAD $0x042c264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 44], 4 - QUAD $0x052c164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 44], 5 - QUAD $0x062c1e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 44], 6 - LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 - LONG $0x6f0f4166; BYTE $0xd7 // movdqa xmm2, xmm15 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xd110 // pblendvb xmm2, xmm9, xmm0 - LONG $0x7c6e0f66; WORD $0x2024 // movd xmm7, dword [rsp + 32] - LONG $0x5cb70f45; WORD $0x3a3e // movzx r11d, word [r14 + rdi + 58] - QUAD $0x072c0e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 44], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0x0000d0bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 208[rbp] /* [rip + .LCPI5_13] */ - LONG $0x6f0f4166; BYTE $0xf7 // movdqa xmm6, xmm15 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xcd // movd xmm1, r13d - LONG $0x6cb70f45; WORD $0x3c3e // movzx r13d, word [r14 + rdi + 60] - LONG $0xf2eb0f66 // por xmm6, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - QUAD $0x012e0e64c40f4166 // pinsrw xmm4, word [r14 + rcx + 46], 1 - QUAD $0x022e3e64c40f4366 // pinsrw xmm4, word [r14 + r15 + 46], 2 - QUAD $0x032e3664c40f4166 // pinsrw xmm4, word [r14 + rsi + 46], 3 - QUAD $0x042e2664c40f4366 // pinsrw xmm4, word [r14 + r12 + 46], 4 - QUAD $0x052e1664c40f4166 // pinsrw xmm4, word [r14 + rdx + 46], 5 - QUAD $0x062e1e64c40f4166 // pinsrw xmm4, word [r14 + rbx + 46], 6 - QUAD $0x072e0e64c40f4366 // pinsrw xmm4, word [r14 + r9 + 46], 7 - LONG $0x750f4166; BYTE $0xe3 // pcmpeqw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0x6f0f4566; BYTE $0xc2 // movdqa xmm8, xmm10 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4566; WORD $0xc110 // pblendvb xmm8, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xd8 // movd xmm3, r8d - QUAD $0x01320e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 50], 1 - QUAD $0x02323e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 50], 2 - QUAD $0x0332364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 50], 3 - QUAD $0x0432264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 50], 4 - QUAD $0x0532164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 50], 5 - QUAD $0x06321e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 50], 6 - QUAD $0x07320e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 50], 7 - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - QUAD $0x00000080a56f0f66 // movdqa xmm4, oword 128[rbp] /* [rip + .LCPI5_8] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe110 // pblendvb xmm4, xmm9, xmm0 - LONG $0xc86e0f66 // movd xmm1, eax - QUAD $0x01300e7cc40f4166 // pinsrw xmm7, word [r14 + rcx + 48], 1 - QUAD $0x02303e7cc40f4366 // pinsrw xmm7, word [r14 + r15 + 48], 2 - QUAD $0x0330367cc40f4166 // pinsrw xmm7, word [r14 + rsi + 48], 3 - QUAD $0x0430267cc40f4366 // pinsrw xmm7, word [r14 + r12 + 48], 4 - QUAD $0x0530167cc40f4166 // pinsrw xmm7, word [r14 + rdx + 48], 5 - QUAD $0x06301e7cc40f4166 // pinsrw xmm7, word [r14 + rbx + 48], 6 - QUAD $0x07300e7cc40f4366 // pinsrw xmm7, word [r14 + r9 + 48], 7 - LONG $0x750f4166; BYTE $0xfb // pcmpeqw xmm7, xmm11 - LONG $0xef0f4166; BYTE $0xfe // pxor xmm7, xmm14 - QUAD $0x01340e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 52], 1 - QUAD $0x02343e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 52], 2 - QUAD $0x03343654c40f4166 // pinsrw xmm2, word [r14 + rsi + 52], 3 - QUAD $0x04342654c40f4366 // pinsrw xmm2, word [r14 + r12 + 52], 4 - QUAD $0x05341654c40f4166 // pinsrw xmm2, word [r14 + rdx + 52], 5 - QUAD $0x06341e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 52], 6 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x07340e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 52], 7 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - QUAD $0x01360e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 54], 1 - QUAD $0x02363e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 54], 2 - QUAD $0x0336365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 54], 3 - QUAD $0x0436265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 54], 4 - QUAD $0x0536165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 54], 5 - QUAD $0x06361e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 54], 6 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x07360e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 54], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - QUAD $0x01380e4cc40f4166 // pinsrw xmm1, word [r14 + rcx + 56], 1 - QUAD $0x02383e4cc40f4366 // pinsrw xmm1, word [r14 + r15 + 56], 2 - QUAD $0x0338364cc40f4166 // pinsrw xmm1, word [r14 + rsi + 56], 3 - QUAD $0x0438264cc40f4366 // pinsrw xmm1, word [r14 + r12 + 56], 4 - QUAD $0x0538164cc40f4166 // pinsrw xmm1, word [r14 + rdx + 56], 5 - QUAD $0x06381e4cc40f4166 // pinsrw xmm1, word [r14 + rbx + 56], 6 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07380e4cc40f4366 // pinsrw xmm1, word [r14 + r9 + 56], 7 - LONG $0xe7f80f66 // psubb xmm4, xmm7 - QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI5_9] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xe910 // pblendvb xmm5, xmm9, xmm0 - QUAD $0x000000a0b56f0f66 // movdqa xmm6, oword 160[rbp] /* [rip + .LCPI5_10] */ - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xf110 // pblendvb xmm6, xmm9, xmm0 - LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d - LONG $0x750f4166; BYTE $0xcb // pcmpeqw xmm1, xmm11 - QUAD $0x013a0e54c40f4166 // pinsrw xmm2, word [r14 + rcx + 58], 1 - QUAD $0x023a3e54c40f4366 // pinsrw xmm2, word [r14 + r15 + 58], 2 - QUAD $0x033a3654c40f4166 // pinsrw xmm2, word [r14 + rsi + 58], 3 - QUAD $0x043a2654c40f4366 // pinsrw xmm2, word [r14 + r12 + 58], 4 - QUAD $0x053a1654c40f4166 // pinsrw xmm2, word [r14 + rdx + 58], 5 - QUAD $0x063a1e54c40f4166 // pinsrw xmm2, word [r14 + rbx + 58], 6 - QUAD $0x073a0e54c40f4366 // pinsrw xmm2, word [r14 + r9 + 58], 7 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0x750f4166; BYTE $0xd3 // pcmpeqw xmm2, xmm11 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0x6e0f4166; BYTE $0xdd // movd xmm3, r13d - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - QUAD $0x013c0e5cc40f4166 // pinsrw xmm3, word [r14 + rcx + 60], 1 - QUAD $0x023c3e5cc40f4366 // pinsrw xmm3, word [r14 + r15 + 60], 2 - QUAD $0x033c365cc40f4166 // pinsrw xmm3, word [r14 + rsi + 60], 3 - QUAD $0x043c265cc40f4366 // pinsrw xmm3, word [r14 + r12 + 60], 4 - QUAD $0x053c165cc40f4166 // pinsrw xmm3, word [r14 + rdx + 60], 5 - QUAD $0x063c1e5cc40f4166 // pinsrw xmm3, word [r14 + rbx + 60], 6 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x073c0e5cc40f4366 // pinsrw xmm3, word [r14 + r9 + 60], 7 - LONG $0x750f4166; BYTE $0xdb // pcmpeqw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf4eb0f66 // por xmm6, xmm4 - QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI5_11] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe110 // pblendvb xmm4, xmm9, xmm0 - QUAD $0x000000c08d6f0f66 // movdqa xmm1, oword 192[rbp] /* [rip + .LCPI5_12] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xc910 // pblendvb xmm1, xmm9, xmm0 - LONG $0x6f0f4166; BYTE $0xd7 // movdqa xmm2, xmm15 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xd110 // pblendvb xmm2, xmm9, xmm0 - LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x44b70f41; WORD $0x3e3e // movzx eax, word [r14 + rdi + 62] - LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0xc06e0f66 // movd xmm0, eax - QUAD $0x013e0e44c40f4166 // pinsrw xmm0, word [r14 + rcx + 62], 1 - QUAD $0x023e3e44c40f4366 // pinsrw xmm0, word [r14 + r15 + 62], 2 - QUAD $0x033e3644c40f4166 // pinsrw xmm0, word [r14 + rsi + 62], 3 - QUAD $0x043e2644c40f4366 // pinsrw xmm0, word [r14 + r12 + 62], 4 - QUAD $0x053e1644c40f4166 // pinsrw xmm0, word [r14 + rdx + 62], 5 - QUAD $0x063e1e44c40f4166 // pinsrw xmm0, word [r14 + rbx + 62], 6 - QUAD $0x073e0e44c40f4366 // pinsrw xmm0, word [r14 + r9 + 62], 7 - LONG $0x750f4166; BYTE $0xc3 // pcmpeqw xmm0, xmm11 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xd6eb0f66 // por xmm2, xmm6 - LONG $0x380f4566; WORD $0xd110 // pblendvb xmm10, xmm9, xmm0 - LONG $0xeb0f4466; BYTE $0xd2 // por xmm10, xmm2 - LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 - LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 - LONG $0x6c0f4166; BYTE $0xd2 // punpcklqdq xmm2, xmm10 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI5_15] */ - LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 - LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 - LONG $0xc2610f66 // punpcklwd xmm0, xmm2 - LONG $0x600f4566; BYTE $0xc2 // punpcklbw xmm8, xmm10 - LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 - LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 + LONG $0xd8f80f66 // psubb xmm3, xmm0 + LONG $0xeb0f4466; BYTE $0xcb // por xmm9, xmm3 + LONG $0x1774b60f; BYTE $0x13 // movzx esi, byte [rdi + rdx + 19] + LONG $0xee6e0f66 // movd xmm5, esi + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x01051754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 5], 1 + QUAD $0x052754203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdi + r12 + 5], 2 + QUAD $0x051f54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdi + r11 + 5], 3 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x053754203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdi + r14 + 5], 4 + QUAD $0x05051f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 5], 5 + QUAD $0x050f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r9 + 5], 6 + WORD $0x894d; BYTE $0xd3 // mov r11, r10 + QUAD $0x051754203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r10 + 5], 7 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + QUAD $0x051754203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdi + r10 + 5], 8 + QUAD $0x09050754203a0f66 // pinsrb xmm2, byte [rdi + rax + 5], 9 + WORD $0x894c; BYTE $0xfe // mov rsi, r15 + LONG $0x247c894c; BYTE $0x60 // mov qword [rsp + 96], r15 + QUAD $0x053f54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r15 + 5], 10 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + QUAD $0x050754203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdi + r8 + 5], 11 + QUAD $0x0c050f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 5], 12 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x050754203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdi + r8 + 5], 13 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0e051f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 5], 14 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x050f54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r9 + 5], 15 + QUAD $0x061744203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdi + rdx + 6], 1 + QUAD $0x062744203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rdi + r12 + 6], 2 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x063f44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdi + r15 + 6], 3 + QUAD $0x063744203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdi + r14 + 6], 4 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x061f44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdi + rbx + 6], 5 + LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] + QUAD $0x061f44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rdi + rbx + 6], 6 + QUAD $0x061f44203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r11 + 6], 7 + QUAD $0x061744203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdi + r10 + 6], 8 + QUAD $0x060744203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdi + rax + 6], 9 + QUAD $0x063744203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdi + rsi + 6], 10 + QUAD $0x062f44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdi + r13 + 6], 11 + QUAD $0x060f44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rdi + rcx + 6], 12 + QUAD $0x060744203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rdi + r8 + 6], 13 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x061f44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdi + rbx + 6], 14 + QUAD $0x060f44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdi + r9 + 6], 15 + QUAD $0x071774203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdi + rdx + 7], 1 + QUAD $0x072774203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdi + r12 + 7], 2 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x073f74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdi + r15 + 7], 3 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x071774203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rdi + rdx + 7], 4 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x071774203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdi + rdx + 7], 5 + LONG $0x244c8b4c; BYTE $0x78 // mov r9, qword [rsp + 120] + QUAD $0x070f74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdi + r9 + 7], 6 + QUAD $0x071f74203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdi + r11 + 7], 7 + QUAD $0x071774203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdi + r10 + 7], 8 + QUAD $0x070774203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdi + rax + 7], 9 + WORD $0x8949; BYTE $0xc6 // mov r14, rax + QUAD $0x073774203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdi + rsi + 7], 10 + QUAD $0x072f74203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdi + r13 + 7], 11 + QUAD $0x070f74203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rdi + rcx + 7], 12 + QUAD $0x070774203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rdi + r8 + 7], 13 + QUAD $0x071f74203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rdi + rbx + 7], 14 + LONG $0x6f0f4166; BYTE $0xce // movdqa xmm1, xmm14 + QUAD $0x00b024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 + QUAD $0x00000140856f0f66 // movdqa xmm0, oword 320[rbp] /* [rip + .LCPI5_20] */ + LONG $0xd0df0f66 // pandn xmm2, xmm0 + LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 + QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI5_21] */ + LONG $0xdf0f4466; BYTE $0xc0 // pandn xmm8, xmm0 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] + LONG $0x1f74b60f; BYTE $0x14 // movzx esi, byte [rdi + rbx + 20] + LONG $0xde6e0f66 // movd xmm3, esi + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0f07074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 7], 15 + LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 + LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI5_6] */ + LONG $0xc8df0f66 // pandn xmm1, xmm0 + LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 + LONG $0x1f74b60f; BYTE $0x15 // movzx esi, byte [rdi + rbx + 21] + LONG $0xd66e0f66 // movd xmm2, esi + QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x081744203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdi + r10 + 8], 1 + QUAD $0x082744203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdi + r12 + 8], 2 + QUAD $0x083f44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdi + r15 + 8], 3 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x04081744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 8], 4 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x05080f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 8], 5 + QUAD $0x080f44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r9 + 8], 6 + QUAD $0x081f44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r11 + 8], 7 + LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] + QUAD $0x083f44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdi + r15 + 8], 8 + QUAD $0x083744203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdi + r14 + 8], 9 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x082f44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdi + r13 + 8], 10 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0b083744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 8], 11 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0c083744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 8], 12 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x080744203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdi + r8 + 8], 13 + LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] + QUAD $0x083744203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdi + r14 + 8], 14 + QUAD $0x0f080744203a0f66 // pinsrb xmm0, byte [rdi + rax + 8], 15 + LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 + LONG $0x1f74b60f; BYTE $0x16 // movzx esi, byte [rdi + rbx + 22] + LONG $0xce6e0f66 // movd xmm1, esi + LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 + QUAD $0x09175c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdi + r10 + 9], 1 + QUAD $0x09275c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rdi + r12 + 9], 2 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x09075c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rdi + rax + 9], 3 + QUAD $0x09175c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdi + rdx + 9], 4 + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + QUAD $0x090f5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdi + rcx + 9], 5 + QUAD $0x090f5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdi + r9 + 9], 6 + QUAD $0x00000090249c894c // mov qword [rsp + 144], r11 + QUAD $0x091f5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdi + r11 + 9], 7 + QUAD $0x093f5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdi + r15 + 9], 8 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x09375c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdi + rsi + 9], 9 + WORD $0x894c; BYTE $0xe8 // mov rax, r13 + QUAD $0x092f5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdi + r13 + 9], 10 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x092f5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdi + r13 + 9], 11 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x09175c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rdi + rdx + 9], 12 + QUAD $0x09075c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdi + r8 + 9], 13 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + QUAD $0x09375c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdi + r14 + 9], 14 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x09075c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdi + r8 + 9], 15 + QUAD $0x0a1764203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdi + r10 + 10], 1 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0a0f64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdi + rcx + 10], 2 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0a0f64203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdi + rcx + 10], 3 + QUAD $0x0a1f64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdi + rbx + 10], 4 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x0a1f64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdi + rbx + 10], 5 + QUAD $0x0a0f64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdi + r9 + 10], 6 + QUAD $0x0a1f64203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdi + r11 + 10], 7 + QUAD $0x0a3f64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdi + r15 + 10], 8 + QUAD $0x0a3764203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rdi + rsi + 10], 9 + QUAD $0x0a0764203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdi + rax + 10], 10 + QUAD $0x0a2f64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdi + r13 + 10], 11 + QUAD $0x0a1764203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdi + rdx + 10], 12 + QUAD $0x0a2764203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdi + r12 + 10], 13 + QUAD $0x0a3764203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdi + r14 + 10], 14 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + QUAD $0x0a0764203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdi + r8 + 10], 15 + QUAD $0x0b176c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rdi + r10 + 11], 1 + LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] + QUAD $0x0b376c203a0f4666; BYTE $0x02 // pinsrb xmm13, byte [rdi + r14 + 11], 2 + QUAD $0x0b0f6c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rdi + rcx + 11], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x0b0f6c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdi + rcx + 11], 4 + QUAD $0x0b1f6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdi + rbx + 11], 5 + QUAD $0x0b0f6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdi + r9 + 11], 6 + QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] + QUAD $0x0b0f6c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdi + r9 + 11], 7 + QUAD $0x0b3f6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdi + r15 + 11], 8 + QUAD $0x0b376c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rdi + rsi + 11], 9 + QUAD $0x0b076c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdi + rax + 11], 10 + QUAD $0x0b2f6c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdi + r13 + 11], 11 + QUAD $0x0b176c203a0f4466; BYTE $0x0c // pinsrb xmm13, byte [rdi + rdx + 11], 12 + QUAD $0x0b276c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdi + r12 + 11], 13 + QUAD $0x0b1f6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdi + r11 + 11], 14 + QUAD $0x0b076c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdi + r8 + 11], 15 + LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 + QUAD $0x0001009ddf0f4466; BYTE $0x00 // pandn xmm11, oword 256[rbp] /* [rip + .LCPI5_16] */ + LONG $0xfc0f4466; BYTE $0xd8 // paddb xmm11, xmm0 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + LONG $0x74b60f42; WORD $0x1707 // movzx esi, byte [rdi + r8 + 23] + LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi + LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 + QUAD $0x000110a5df0f4466; BYTE $0x00 // pandn xmm12, oword 272[rbp] /* [rip + .LCPI5_17] */ + LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 + QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI5_18] */ + LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 + LONG $0x74b60f42; WORD $0x1807 // movzx esi, byte [rdi + r8 + 24] + LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi + QUAD $0x00e0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 224] + QUAD $0x0c174c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rdi + r10 + 12], 1 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + QUAD $0x0c374c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rdi + r14 + 12], 2 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x0c1f4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdi + r11 + 12], 3 + WORD $0x8949; BYTE $0xce // mov r14, rcx + QUAD $0x0c0f4c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdi + rcx + 12], 4 + QUAD $0x0c1f4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdi + rbx + 12], 5 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x0c074c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r8 + 12], 6 + WORD $0x894d; BYTE $0xca // mov r10, r9 + QUAD $0x0c0f4c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r9 + 12], 7 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x0c3f4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdi + r15 + 12], 8 + LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + QUAD $0x0c3f4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdi + r15 + 12], 9 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x0c074c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rdi + rax + 12], 10 LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - LONG $0x7f0f45f3; WORD $0x8824 // movdqu oword [r8 + 4*rcx], xmm12 - LONG $0x2444894c; BYTE $0x08 // mov qword [rsp + 8], r8 - LONG $0x7f0f41f3; WORD $0x8844; BYTE $0x10 // movdqu oword [r8 + 4*rcx + 16], xmm0 - LONG $0x08c18348 // add rcx, 8 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] - JNE LBB5_134 - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - LONG $0x24543b4c; BYTE $0x28 // cmp r10, qword [rsp + 40] - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - LONG $0x245c8b44; BYTE $0x10 // mov r11d, dword [rsp + 16] - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - JNE LBB5_136 - JMP LBB5_139 - -LBB5_181: + QUAD $0x0c0f4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdi + rcx + 12], 11 + QUAD $0x0c174c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rdi + rdx + 12], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0c374c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdi + rsi + 12], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0c074c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdi + rax + 12], 14 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0c074c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rdi + rax + 12], 15 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x010d0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 13], 1 + QUAD $0x0d2774203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdi + r12 + 13], 2 + QUAD $0x0d1f74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r11 + 13], 3 + QUAD $0x0d3774203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r14 + 13], 4 + QUAD $0x050d1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 13], 5 + QUAD $0x0d0774203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r8 + 13], 6 + QUAD $0x0d1774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r10 + 13], 7 + QUAD $0x0d0f74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdi + r9 + 13], 8 + QUAD $0x0d3f74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r15 + 13], 9 + QUAD $0x0d2f74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdi + r13 + 13], 10 + QUAD $0x0b0d0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 13], 11 + QUAD $0x0c0d1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 13], 12 + QUAD $0x0d0d3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 13], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0e0d0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 13], 14 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0f0d0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 13], 15 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0e077c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdi + rax + 14], 1 + QUAD $0x0e277c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rdi + r12 + 14], 2 + QUAD $0x0e1f7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdi + r11 + 14], 3 + QUAD $0x0e377c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdi + r14 + 14], 4 + QUAD $0x0e1f7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdi + rbx + 14], 5 + QUAD $0x0e077c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r8 + 14], 6 + QUAD $0x0e177c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r10 + 14], 7 + QUAD $0x0e0f7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdi + r9 + 14], 8 + QUAD $0x0e3f7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r15 + 14], 9 + QUAD $0x0e2f7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdi + r13 + 14], 10 + QUAD $0x0e0f7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rdi + rcx + 14], 11 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + QUAD $0x0e177c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rdi + rdx + 14], 12 + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + QUAD $0x0e377c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdi + rsi + 14], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0e077c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdi + rax + 14], 14 + LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 + QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI5_19] */ + LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + LONG $0x0774b60f; BYTE $0x19 // movzx esi, byte [rdi + rax + 25] + LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi + QUAD $0x0001609df80f4466; BYTE $0x00 // psubb xmm11, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xeb0f4566; BYTE $0xcb // por xmm9, xmm11 + LONG $0x0774b60f; BYTE $0x1a // movzx esi, byte [rdi + rax + 26] + LONG $0xc66e0f66 // movd xmm0, esi + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0e0f7c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rdi + rcx + 14], 15 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + QUAD $0x00000140b5df0f66 // pandn xmm6, oword 320[rbp] /* [rip + .LCPI5_20] */ + LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 + QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI5_21] */ + LONG $0xeb0f4466; BYTE $0xfe // por xmm15, xmm6 + LONG $0x0774b60f; BYTE $0x1b // movzx esi, byte [rdi + rax + 27] + LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi + QUAD $0x0000c024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 192] + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0f1f74203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdi + r11 + 15], 1 + QUAD $0x0f2774203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdi + r12 + 15], 2 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x030f1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 15], 3 + QUAD $0x0f3774203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r14 + 15], 4 + QUAD $0x050f1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 15], 5 + QUAD $0x0f0774203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r8 + 15], 6 WORD $0x894d; BYTE $0xd0 // mov r8, r10 - LONG $0xfce08349 // and r8, -4 + QUAD $0x0f1774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r10 + 15], 7 + QUAD $0x0f0f74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdi + r9 + 15], 8 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x0f0f74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r9 + 15], 9 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x0f1774203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdi + r10 + 15], 10 + QUAD $0x0f3f74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r15 + 15], 11 + QUAD $0x0f2f74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r13 + 15], 12 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0d0f3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 15], 13 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0e0f3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 15], 14 + QUAD $0x0f0f0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 15], 15 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI5_6] */ + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x0774b60f; BYTE $0x1c // movzx esi, byte [rdi + rax + 28] + LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi + LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 + QUAD $0x0000c024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm6 + LONG $0x0774b60f; BYTE $0x1d // movzx esi, byte [rdi + rax + 29] + LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x101f54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdi + r11 + 16], 1 + QUAD $0x102754203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdi + r12 + 16], 2 + QUAD $0x101754203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdi + rdx + 16], 3 + QUAD $0x103754203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdi + r14 + 16], 4 + QUAD $0x101f54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdi + rbx + 16], 5 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + QUAD $0x101754203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rdi + rdx + 16], 6 + QUAD $0x100754203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r8 + 16], 7 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + QUAD $0x100754203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdi + r8 + 16], 8 + QUAD $0x100f54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdi + r9 + 16], 9 + QUAD $0x101754203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdi + r10 + 16], 10 + QUAD $0x103f54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r15 + 16], 11 + QUAD $0x102f54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdi + r13 + 16], 12 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x100f54203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdi + rcx + 16], 13 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x100f54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rdi + rcx + 16], 14 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x103754203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdi + rsi + 16], 15 + QUAD $0x01110764203a0f66 // pinsrb xmm4, byte [rdi + rax + 17], 1 + QUAD $0x112764203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdi + r12 + 17], 2 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x112764203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdi + r12 + 17], 3 + QUAD $0x113764203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdi + r14 + 17], 4 + QUAD $0x05111f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 17], 5 + QUAD $0x06111764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 17], 6 + QUAD $0x111f64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r11 + 17], 7 + QUAD $0x110764203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdi + r8 + 17], 8 + QUAD $0x110f64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdi + r9 + 17], 9 + QUAD $0x111764203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdi + r10 + 17], 10 + QUAD $0x113f64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r15 + 17], 11 + QUAD $0x112f64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdi + r13 + 17], 12 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0d111764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 17], 13 + QUAD $0x0e110f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 17], 14 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + QUAD $0x0f113764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 17], 15 + LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 + LONG $0x740f4166; BYTE $0xe6 // pcmpeqb xmm4, xmm14 + QUAD $0x00000100b56f0f66 // movdqa xmm6, oword 256[rbp] /* [rip + .LCPI5_16] */ + LONG $0xe6df0f66 // pandn xmm4, xmm6 + LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + LONG $0x0774b60f; BYTE $0x1e // movzx esi, byte [rdi + rax + 30] + LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0112377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 18], 1 + QUAD $0x0113376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 19], 1 + QUAD $0x0114375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 20], 1 + QUAD $0x01153754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 21], 1 + QUAD $0x0116374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 22], 1 + QUAD $0x173744203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdi + rsi + 23], 1 + QUAD $0x183764203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdi + rsi + 24], 1 + QUAD $0x19376c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdi + rsi + 25], 1 + QUAD $0x011a3744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 26], 1 + QUAD $0x1b375c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdi + rsi + 27], 1 + QUAD $0x1c377c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdi + rsi + 28], 1 + QUAD $0x1d374c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdi + rsi + 29], 1 + QUAD $0x1e3754203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdi + rsi + 30], 1 + LONG $0x0744b60f; BYTE $0x1f // movzx eax, byte [rdi + rax + 31] + LONG $0xf06e0f66 // movd xmm6, eax + QUAD $0x011f3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 31], 1 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x0212077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 18], 2 + QUAD $0x0213076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 19], 2 + QUAD $0x0214075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 20], 2 + QUAD $0x02150754203a0f66 // pinsrb xmm2, byte [rdi + rax + 21], 2 + QUAD $0x0216074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 22], 2 + QUAD $0x170744203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdi + rax + 23], 2 + QUAD $0x180764203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdi + rax + 24], 2 + QUAD $0x19076c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdi + rax + 25], 2 + QUAD $0x021a0744203a0f66 // pinsrb xmm0, byte [rdi + rax + 26], 2 + QUAD $0x1b075c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdi + rax + 27], 2 + QUAD $0x1c077c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rax + 28], 2 + QUAD $0x1d074c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdi + rax + 29], 2 + QUAD $0x1e0754203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdi + rax + 30], 2 + QUAD $0x021f0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 31], 2 + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + QUAD $0x12277c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r12 + 18], 3 + QUAD $0x12377c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdi + r14 + 18], 4 + QUAD $0x05121f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 18], 5 + LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] + QUAD $0x12077c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r8 + 18], 6 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x12177c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r10 + 18], 7 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x08120f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 18], 8 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0912077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 18], 9 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0a12377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 18], 10 + QUAD $0x123f7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdi + r15 + 18], 11 + QUAD $0x122f7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdi + r13 + 18], 12 + QUAD $0x0d12177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 18], 13 + QUAD $0x120f7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdi + r9 + 18], 14 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x12277c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdi + r12 + 18], 15 + QUAD $0x131f6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r11 + 19], 3 + QUAD $0x13376c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdi + r14 + 19], 4 + QUAD $0x05131f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 19], 5 + QUAD $0x13076c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r8 + 19], 6 + QUAD $0x13176c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r10 + 19], 7 + QUAD $0x08130f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 19], 8 + QUAD $0x0913076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 19], 9 + QUAD $0x0a13376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 19], 10 + QUAD $0x133f6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdi + r15 + 19], 11 + QUAD $0x132f6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdi + r13 + 19], 12 + QUAD $0x0d13176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 19], 13 + QUAD $0x130f6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdi + r9 + 19], 14 + QUAD $0x13276c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdi + r12 + 19], 15 + QUAD $0x141f5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r11 + 20], 3 + QUAD $0x14375c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r14 + 20], 4 + QUAD $0x05141f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 20], 5 + QUAD $0x14075c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r8 + 20], 6 + QUAD $0x14175c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r10 + 20], 7 + QUAD $0x08140f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 20], 8 + QUAD $0x0914075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 20], 9 + QUAD $0x0a14375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 20], 10 + QUAD $0x143f5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r15 + 20], 11 + QUAD $0x142f5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r13 + 20], 12 + QUAD $0x0d14175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 20], 13 + QUAD $0x140f5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdi + r9 + 20], 14 + LONG $0x740f4166; BYTE $0xfe // pcmpeqb xmm7, xmm14 + QUAD $0x000110b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 272[rbp] /* [rip + .LCPI5_17] */ + LONG $0xdf0f4166; BYTE $0xfe // pandn xmm7, xmm14 + QUAD $0x0000b024ac740f66; BYTE $0x00 // pcmpeqb xmm5, oword [rsp + 176] + QUAD $0x000120b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 288[rbp] /* [rip + .LCPI5_18] */ + LONG $0xdf0f4166; BYTE $0xee // pandn xmm5, xmm14 + LONG $0xefeb0f66 // por xmm5, xmm7 + QUAD $0x14275c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdi + r12 + 20], 15 + QUAD $0x00b024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 176] + LONG $0x740f4166; BYTE $0xde // pcmpeqb xmm3, xmm14 + QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI5_19] */ + LONG $0xdfdf0f66 // pandn xmm3, xmm7 + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xed760f66 // pcmpeqd xmm5, xmm5 + LONG $0xe5f80f66 // psubb xmm4, xmm5 + LONG $0xdceb0f66 // por xmm3, xmm4 + QUAD $0x151f54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdi + r11 + 21], 3 + QUAD $0x153754203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdi + r14 + 21], 4 + QUAD $0x05151f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 21], 5 + QUAD $0x150754203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r8 + 21], 6 + QUAD $0x151754203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r10 + 21], 7 + QUAD $0x08150f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 21], 8 + QUAD $0x09150754203a0f66 // pinsrb xmm2, byte [rdi + rax + 21], 9 + QUAD $0x0a153754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 21], 10 + QUAD $0x153f54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdi + r15 + 21], 11 + QUAD $0x152f54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdi + r13 + 21], 12 + QUAD $0x0d151754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 21], 13 + QUAD $0x150f54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdi + r9 + 21], 14 + QUAD $0x152754203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r12 + 21], 15 + QUAD $0x161f4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdi + r11 + 22], 3 + QUAD $0x16374c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdi + r14 + 22], 4 + QUAD $0x05161f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 22], 5 + QUAD $0x16074c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdi + r8 + 22], 6 + QUAD $0x16174c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdi + r10 + 22], 7 + QUAD $0x08160f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 22], 8 + QUAD $0x0916074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 22], 9 + QUAD $0x0a16374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 22], 10 + QUAD $0x163f4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdi + r15 + 22], 11 + QUAD $0x162f4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdi + r13 + 22], 12 + QUAD $0x0d16174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 22], 13 + QUAD $0x160f4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdi + r9 + 22], 14 + QUAD $0x16274c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdi + r12 + 22], 15 + QUAD $0x171f44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdi + r11 + 23], 3 + QUAD $0x173744203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdi + r14 + 23], 4 + QUAD $0x171f44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdi + rbx + 23], 5 + QUAD $0x170744203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r8 + 23], 6 + QUAD $0x171744203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r10 + 23], 7 + QUAD $0x170f44203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rdi + rcx + 23], 8 + QUAD $0x170744203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdi + rax + 23], 9 + QUAD $0x173744203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdi + rsi + 23], 10 + QUAD $0x173f44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdi + r15 + 23], 11 + QUAD $0x172f44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdi + r13 + 23], 12 + QUAD $0x171744203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdi + rdx + 23], 13 + QUAD $0x170f44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdi + r9 + 23], 14 + LONG $0x740f4166; BYTE $0xd6 // pcmpeqb xmm2, xmm14 + QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI5_20] */ + LONG $0xd5df0f66 // pandn xmm2, xmm5 + LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 + QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI5_21] */ + LONG $0xcfdf0f66 // pandn xmm1, xmm7 + LONG $0xcaeb0f66 // por xmm1, xmm2 + QUAD $0x172744203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdi + r12 + 23], 15 + LONG $0x740f4566; BYTE $0xc6 // pcmpeqb xmm8, xmm14 + LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI5_6] */ + LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + QUAD $0x181f64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdi + r11 + 24], 3 + QUAD $0x183764203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdi + r14 + 24], 4 + QUAD $0x181f64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdi + rbx + 24], 5 + QUAD $0x180764203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdi + r8 + 24], 6 + QUAD $0x181764203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdi + r10 + 24], 7 + QUAD $0x180f64203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rdi + rcx + 24], 8 + QUAD $0x180764203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rdi + rax + 24], 9 + QUAD $0x183764203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdi + rsi + 24], 10 + QUAD $0x183f64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdi + r15 + 24], 11 + QUAD $0x182f64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdi + r13 + 24], 12 + QUAD $0x181764203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdi + rdx + 24], 13 + QUAD $0x180f64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdi + r9 + 24], 14 + QUAD $0x182764203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdi + r12 + 24], 15 + LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 + LONG $0x740f4566; BYTE $0xe6 // pcmpeqb xmm12, xmm14 + QUAD $0x191f6c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdi + r11 + 25], 3 + QUAD $0x19376c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdi + r14 + 25], 4 + QUAD $0x191f6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdi + rbx + 25], 5 + QUAD $0x19076c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdi + r8 + 25], 6 + QUAD $0x19176c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdi + r10 + 25], 7 + QUAD $0x190f6c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rdi + rcx + 25], 8 + QUAD $0x19076c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rdi + rax + 25], 9 + QUAD $0x19376c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdi + rsi + 25], 10 + QUAD $0x193f6c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdi + r15 + 25], 11 + QUAD $0x192f6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdi + r13 + 25], 12 + QUAD $0x19176c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rdi + rdx + 25], 13 + QUAD $0x190f6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdi + r9 + 25], 14 + QUAD $0x19276c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdi + r12 + 25], 15 + QUAD $0x1a1f44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdi + r11 + 26], 3 + QUAD $0x1a3744203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdi + r14 + 26], 4 + QUAD $0x051a1f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 26], 5 + QUAD $0x1a0744203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r8 + 26], 6 + QUAD $0x1a1744203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r10 + 26], 7 + QUAD $0x081a0f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 26], 8 + QUAD $0x091a0744203a0f66 // pinsrb xmm0, byte [rdi + rax + 26], 9 + QUAD $0x0a1a3744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 26], 10 + QUAD $0x1a3f44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdi + r15 + 26], 11 + QUAD $0x1a2f44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdi + r13 + 26], 12 + QUAD $0x0d1a1744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 26], 13 + QUAD $0x1a0f44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdi + r9 + 26], 14 + QUAD $0x1a2744203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdi + r12 + 26], 15 + QUAD $0x1b1f5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdi + r11 + 27], 3 + QUAD $0x1b375c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdi + r14 + 27], 4 + QUAD $0x1b1f5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdi + rbx + 27], 5 + QUAD $0x1b075c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdi + r8 + 27], 6 + QUAD $0x1b175c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdi + r10 + 27], 7 + QUAD $0x1b0f5c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rdi + rcx + 27], 8 + QUAD $0x1b075c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdi + rax + 27], 9 + QUAD $0x1b375c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdi + rsi + 27], 10 + QUAD $0x1b3f5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdi + r15 + 27], 11 + QUAD $0x1b2f5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdi + r13 + 27], 12 + QUAD $0x1b175c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdi + rdx + 27], 13 + QUAD $0x1b0f5c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdi + r9 + 27], 14 + LONG $0x740f4566; BYTE $0xee // pcmpeqb xmm13, xmm14 + QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI5_16] */ + LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 + QUAD $0x1b275c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdi + r12 + 27], 15 + LONG $0x740f4166; BYTE $0xc6 // pcmpeqb xmm0, xmm14 + QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI5_17] */ + LONG $0x740f4566; BYTE $0xde // pcmpeqb xmm11, xmm14 + QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI5_18] */ + LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 + QUAD $0x1c1f7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdi + r11 + 28], 3 + QUAD $0x1d1f4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdi + r11 + 29], 3 + QUAD $0x1e1f54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdi + r11 + 30], 3 + QUAD $0x1f1f74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r11 + 31], 3 + QUAD $0x1c377c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdi + r14 + 28], 4 + QUAD $0x1d374c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdi + r14 + 29], 4 + QUAD $0x1e3754203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdi + r14 + 30], 4 + QUAD $0x1f3774203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r14 + 31], 4 + QUAD $0x1c1f7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdi + rbx + 28], 5 + QUAD $0x1d1f4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdi + rbx + 29], 5 + QUAD $0x1e1f54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdi + rbx + 30], 5 + QUAD $0x051f1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 31], 5 WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - LONG $0x07e3c148 // shl rbx, 7 - WORD $0x014c; BYTE $0xf3 // add rbx, r14 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - LONG $0x80248d4e // lea r12, [rax + 4*r8] - WORD $0x280f; BYTE $0xc8 // movaps xmm1, xmm0 - LONG $0x00c8c60f // shufps xmm1, xmm0, 0 - LONG $0xfcc68149; WORD $0x0001; BYTE $0x00 // add r14, 508 - WORD $0xc931 // xor ecx, ecx - LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI5_0] */ - LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI5_1] */ - LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI5_2] */ - LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI5_3] */ - LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI5_4] */ - LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI5_5] */ - LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI5_6] */ - LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI5_7] */ - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - -LBB5_182: - QUAD $0xfffe04b6100f41f3; BYTE $0xff // movss xmm6, dword [r14 - 508] - QUAD $0xfffe08be100f41f3; BYTE $0xff // movss xmm7, dword [r14 - 504] - QUAD $0xfffe0cae100f41f3; BYTE $0xff // movss xmm5, dword [r14 - 500] - QUAD $0xfffe10a6100f41f3; BYTE $0xff // movss xmm4, dword [r14 - 496] - QUAD $0xfe84b6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm6, dword [r14 - 380], 16 - QUAD $0xff04b6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm6, dword [r14 - 252], 32 - QUAD $0x308476213a0f4166 // insertps xmm6, dword [r14 - 124], 48 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - QUAD $0xfe88be213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm7, dword [r14 - 376], 16 - QUAD $0xff08be213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm7, dword [r14 - 248], 32 - QUAD $0x30887e213a0f4166 // insertps xmm7, dword [r14 - 120], 48 - QUAD $0xfe8cae213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm5, dword [r14 - 372], 16 - QUAD $0xff0cae213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm5, dword [r14 - 244], 32 - QUAD $0x308c6e213a0f4166 // insertps xmm5, dword [r14 - 116], 48 - QUAD $0xfe90a6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm4, dword [r14 - 368], 16 - QUAD $0xff10a6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm4, dword [r14 - 240], 32 - QUAD $0x309066213a0f4166 // insertps xmm4, dword [r14 - 112], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xd76f0f66 // movdqa xmm2, xmm7 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xd7f80f66 // psubb xmm2, xmm7 - QUAD $0xfffe14be100f41f3; BYTE $0xff // movss xmm7, dword [r14 - 492] - QUAD $0xfe94be213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm7, dword [r14 - 364], 16 - QUAD $0xff14be213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm7, dword [r14 - 236], 32 - QUAD $0x30947e213a0f4166 // insertps xmm7, dword [r14 - 108], 48 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffe18b6100f41f3; BYTE $0xff // movss xmm6, dword [r14 - 488] - QUAD $0xfe98b6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm6, dword [r14 - 360], 16 - QUAD $0xff18b6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm6, dword [r14 - 232], 32 - QUAD $0x309876213a0f4166 // insertps xmm6, dword [r14 - 104], 48 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 - LONG $0xeaeb0f66 // por xmm5, xmm2 - QUAD $0xfffe1c9e100f41f3; BYTE $0xff // movss xmm3, dword [r14 - 484] - QUAD $0xfe9c9e213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm3, dword [r14 - 356], 16 - QUAD $0xff1c9e213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm3, dword [r14 - 228], 32 - QUAD $0x309c5e213a0f4166 // insertps xmm3, dword [r14 - 100], 48 - LONG $0x04e1c20f // cmpneqps xmm4, xmm1 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xf4710f66; BYTE $0x03 // psllw xmm4, 3 - LONG $0xdb0f4166; BYTE $0xe2 // pand xmm4, xmm10 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x04 // psllw xmm7, 4 - LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 - LONG $0xfceb0f66 // por xmm7, xmm4 - QUAD $0xfffe20a6100f41f3; BYTE $0xff // movss xmm4, dword [r14 - 480] - QUAD $0xfea0a6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm4, dword [r14 - 352], 16 - QUAD $0xff20a6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm4, dword [r14 - 224], 32 - QUAD $0x30a066213a0f4166 // insertps xmm4, dword [r14 - 96], 48 - LONG $0xfdeb0f66 // por xmm7, xmm5 - QUAD $0xfffe24ae100f41f3; BYTE $0xff // movss xmm5, dword [r14 - 476] - QUAD $0xfea4ae213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm5, dword [r14 - 348], 16 - QUAD $0xff24ae213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm5, dword [r14 - 220], 32 - QUAD $0x30a46e213a0f4166 // insertps xmm5, dword [r14 - 92], 48 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 - LONG $0xdb0f4166; BYTE $0xdd // pand xmm3, xmm13 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffe2896100f41f3; BYTE $0xff // movss xmm2, dword [r14 - 472] - QUAD $0xfea896213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm2, dword [r14 - 344], 16 - QUAD $0xff2896213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm2, dword [r14 - 216], 32 - QUAD $0x30a856213a0f4166 // insertps xmm2, dword [r14 - 88], 48 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0x04e1c20f // cmpneqps xmm4, xmm1 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 - LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 - LONG $0xe3eb0f66 // por xmm4, xmm3 - QUAD $0xfffe2c9e100f41f3; BYTE $0xff // movss xmm3, dword [r14 - 468] - QUAD $0xfeac9e213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm3, dword [r14 - 340], 16 - QUAD $0xff2c9e213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm3, dword [r14 - 212], 32 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - QUAD $0x30ac5e213a0f4166 // insertps xmm3, dword [r14 - 84], 48 - LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf26f0f66 // movdqa xmm6, xmm2 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf2f80f66 // psubb xmm6, xmm2 - QUAD $0xfffe30be100f41f3; BYTE $0xff // movss xmm7, dword [r14 - 464] - QUAD $0xfeb0be213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm7, dword [r14 - 336], 16 - QUAD $0xff30be213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm7, dword [r14 - 208], 32 - QUAD $0x30b07e213a0f4166 // insertps xmm7, dword [r14 - 80], 48 - LONG $0xf5eb0f66 // por xmm6, xmm5 - QUAD $0xfffe34ae100f41f3; BYTE $0xff // movss xmm5, dword [r14 - 460] - QUAD $0xfeb4ae213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm5, dword [r14 - 332], 16 - QUAD $0xff34ae213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm5, dword [r14 - 204], 32 - QUAD $0x30b46e213a0f4166 // insertps xmm5, dword [r14 - 76], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffe38b6100f41f3; BYTE $0xff // movss xmm6, dword [r14 - 456] - QUAD $0xfeb8b6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm6, dword [r14 - 328], 16 - QUAD $0xff38b6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm6, dword [r14 - 200], 32 - QUAD $0x30b876213a0f4166 // insertps xmm6, dword [r14 - 72], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x03 // psllw xmm7, 3 - LONG $0xdb0f4166; BYTE $0xfa // pand xmm7, xmm10 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 - LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 - LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0xfffe3c96100f41f3; BYTE $0xff // movss xmm2, dword [r14 - 452] - QUAD $0xfebc96213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm2, dword [r14 - 324], 16 - QUAD $0xff3c96213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm2, dword [r14 - 196], 32 - QUAD $0x30bc56213a0f4166 // insertps xmm2, dword [r14 - 68], 48 - LONG $0xebeb0f66 // por xmm5, xmm3 - QUAD $0xfffe40be100f41f3; BYTE $0xff // movss xmm7, dword [r14 - 448] - QUAD $0xfec0be213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm7, dword [r14 - 320], 16 - QUAD $0xff40be213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm7, dword [r14 - 192], 32 - QUAD $0x30c07e213a0f4166 // insertps xmm7, dword [r14 - 64], 48 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffe44b6100f41f3; BYTE $0xff // movss xmm6, dword [r14 - 444] - QUAD $0xfec4b6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm6, dword [r14 - 316], 16 - QUAD $0xff44b6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm6, dword [r14 - 188], 32 - QUAD $0x30c476213a0f4166 // insertps xmm6, dword [r14 - 60], 48 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xf7710f66; BYTE $0x07 // psllw xmm7, 7 - LONG $0xdb0f4166; BYTE $0xfe // pand xmm7, xmm14 - LONG $0xfaeb0f66 // por xmm7, xmm2 - QUAD $0xfffe4896100f41f3; BYTE $0xff // movss xmm2, dword [r14 - 440] - QUAD $0xfec896213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm2, dword [r14 - 312], 16 - QUAD $0xff4896213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm2, dword [r14 - 184], 32 - QUAD $0x30c856213a0f4166 // insertps xmm2, dword [r14 - 56], 48 - LONG $0xfdeb0f66 // por xmm7, xmm5 - QUAD $0xfffe4c9e100f41f3; BYTE $0xff // movss xmm3, dword [r14 - 436] - QUAD $0xfecc9e213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm3, dword [r14 - 308], 16 - QUAD $0xff4c9e213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm3, dword [r14 - 180], 32 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - QUAD $0x30cc5e213a0f4166 // insertps xmm3, dword [r14 - 52], 48 - LONG $0xe7620f66 // punpckldq xmm4, xmm7 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xfa6f0f66 // movdqa xmm7, xmm2 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xfaf80f66 // psubb xmm7, xmm2 - QUAD $0xfffe50ae100f41f3; BYTE $0xff // movss xmm5, dword [r14 - 432] - QUAD $0xfed0ae213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm5, dword [r14 - 304], 16 - QUAD $0xff50ae213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm5, dword [r14 - 176], 32 - QUAD $0x30d06e213a0f4166 // insertps xmm5, dword [r14 - 48], 48 - LONG $0xfeeb0f66 // por xmm7, xmm6 - QUAD $0xfffe54b6100f41f3; BYTE $0xff // movss xmm6, dword [r14 - 428] - QUAD $0xfed4b6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm6, dword [r14 - 300], 16 - QUAD $0xff54b6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm6, dword [r14 - 172], 32 - QUAD $0x30d476213a0f4166 // insertps xmm6, dword [r14 - 44], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdfeb0f66 // por xmm3, xmm7 - QUAD $0xfffe58be100f41f3; BYTE $0xff // movss xmm7, dword [r14 - 424] - QUAD $0xfed8be213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm7, dword [r14 - 296], 16 - QUAD $0xff58be213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm7, dword [r14 - 168], 32 - QUAD $0x30d87e213a0f4166 // insertps xmm7, dword [r14 - 40], 48 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 - LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf5eb0f66 // por xmm6, xmm5 - QUAD $0xfffe5c96100f41f3; BYTE $0xff // movss xmm2, dword [r14 - 420] - QUAD $0xfedc96213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm2, dword [r14 - 292], 16 - QUAD $0xff5c96213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm2, dword [r14 - 164], 32 - QUAD $0x30dc56213a0f4166 // insertps xmm2, dword [r14 - 36], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffe60ae100f41f3; BYTE $0xff // movss xmm5, dword [r14 - 416] - QUAD $0xfee0ae213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm5, dword [r14 - 288], 16 - QUAD $0xff60ae213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm5, dword [r14 - 160], 32 - QUAD $0x30e06e213a0f4166 // insertps xmm5, dword [r14 - 32], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffe64be100f41f3; BYTE $0xff // movss xmm7, dword [r14 - 412] - QUAD $0xfee4be213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm7, dword [r14 - 284], 16 - QUAD $0xff64be213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm7, dword [r14 - 156], 32 - QUAD $0x30e47e213a0f4166 // insertps xmm7, dword [r14 - 28], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0x04e9c20f // cmpneqps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xf5710f66; BYTE $0x07 // psllw xmm5, 7 - LONG $0xdb0f4166; BYTE $0xee // pand xmm5, xmm14 - LONG $0xeaeb0f66 // por xmm5, xmm2 - QUAD $0xfffe6896100f41f3; BYTE $0xff // movss xmm2, dword [r14 - 408] - QUAD $0xfee896213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm2, dword [r14 - 280], 16 - QUAD $0xff6896213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm2, dword [r14 - 152], 32 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - QUAD $0x30e856213a0f4166 // insertps xmm2, dword [r14 - 24], 48 - LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf26f0f66 // movdqa xmm6, xmm2 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf2f80f66 // psubb xmm6, xmm2 - QUAD $0xfffe6c9e100f41f3; BYTE $0xff // movss xmm3, dword [r14 - 404] - QUAD $0xfeec9e213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm3, dword [r14 - 276], 16 - QUAD $0xff6c9e213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm3, dword [r14 - 148], 32 - QUAD $0x30ec5e213a0f4166 // insertps xmm3, dword [r14 - 20], 48 - LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0xfffe7096100f41f3; BYTE $0xff // movss xmm2, dword [r14 - 400] - QUAD $0xfef096213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm2, dword [r14 - 272], 16 - QUAD $0xff7096213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm2, dword [r14 - 144], 32 - QUAD $0x30f056213a0f4166 // insertps xmm2, dword [r14 - 16], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffe74b6100f41f3; BYTE $0xff // movss xmm6, dword [r14 - 396] - QUAD $0xfef4b6213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm6, dword [r14 - 268], 16 - QUAD $0xff74b6213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm6, dword [r14 - 140], 32 - QUAD $0x30f476213a0f4166 // insertps xmm6, dword [r14 - 12], 48 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0x04f1c20f // cmpneqps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf2eb0f66 // por xmm6, xmm2 - QUAD $0xfffe78be100f41f3; BYTE $0xff // movss xmm7, dword [r14 - 392] - QUAD $0xfef8be213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm7, dword [r14 - 264], 16 - QUAD $0xff78be213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm7, dword [r14 - 136], 32 - QUAD $0x30f87e213a0f4166 // insertps xmm7, dword [r14 - 8], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffe7c96100f41f3; BYTE $0xff // movss xmm2, dword [r14 - 388] - QUAD $0xfefc96213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm2, dword [r14 - 260], 16 - QUAD $0xff7c96213a0f4166; WORD $0xffff; BYTE $0x20 // insertps xmm2, dword [r14 - 132], 32 - QUAD $0x30fc56213a0f4166 // insertps xmm2, dword [r14 - 4], 48 - LONG $0x04f9c20f // cmpneqps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x04d1c20f // cmpneqps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffe809e100f41f3; BYTE $0xff // movss xmm3, dword [r14 - 384] - QUAD $0xff009e213a0f4166; WORD $0xffff; BYTE $0x10 // insertps xmm3, dword [r14 - 256], 16 - QUAD $0x20805e213a0f4166 // insertps xmm3, dword [r14 - 128], 32 - LONG $0x3a0f4166; WORD $0x1e21; BYTE $0x30 // insertps xmm3, dword [r14], 48 - LONG $0x04d9c20f // cmpneqps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0xdeeb0f66 // por xmm3, xmm6 - LONG $0xeb620f66 // punpckldq xmm5, xmm3 - LONG $0xe5600f66 // punpcklbw xmm4, xmm5 - LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 - LONG $0x247f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm4 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c68149; WORD $0x0002; BYTE $0x00 // add r14, 512 - WORD $0x3949; BYTE $0xc8 // cmp r8, rcx - JNE LBB5_182 - WORD $0x394d; BYTE $0xc2 // cmp r10, r8 - JNE LBB5_184 - JMP LBB5_187 + QUAD $0x1c077c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r8 + 28], 6 + QUAD $0x1d074c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r8 + 29], 6 + QUAD $0x1e0754203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r8 + 30], 6 + QUAD $0x1f0774203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r8 + 31], 6 + WORD $0x894c; BYTE $0xd3 // mov rbx, r10 + QUAD $0x1c177c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r10 + 28], 7 + QUAD $0x1d174c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r10 + 29], 7 + QUAD $0x1e1754203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r10 + 30], 7 + QUAD $0x1f1774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r10 + 31], 7 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + WORD $0x8948; BYTE $0xcb // mov rbx, rcx + QUAD $0x1c0f7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdi + rcx + 28], 8 + QUAD $0x1d0f4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rdi + rcx + 29], 8 + QUAD $0x1e0f54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rdi + rcx + 30], 8 + QUAD $0x081f0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 31], 8 + QUAD $0x1c077c203a0f4466; BYTE $0x09 // pinsrb xmm15, byte [rdi + rax + 28], 9 + QUAD $0x1d074c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdi + rax + 29], 9 + QUAD $0x1e0754203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdi + rax + 30], 9 + QUAD $0x091f0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 31], 9 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x1c377c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdi + rsi + 28], 10 + QUAD $0x1d374c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rdi + rsi + 29], 10 + QUAD $0x1e3754203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdi + rsi + 30], 10 + QUAD $0x0a1f3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 31], 10 + QUAD $0x1c3f7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdi + r15 + 28], 11 + QUAD $0x1d3f4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdi + r15 + 29], 11 + QUAD $0x1e3f54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r15 + 30], 11 + QUAD $0x1f3f74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r15 + 31], 11 + QUAD $0x1c2f7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdi + r13 + 28], 12 + QUAD $0x1d2f4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdi + r13 + 29], 12 + QUAD $0x1e2f54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdi + r13 + 30], 12 + QUAD $0x1f2f74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r13 + 31], 12 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x1c177c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdi + rdx + 28], 13 + QUAD $0x1d174c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdi + rdx + 29], 13 + QUAD $0x1e1754203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdi + rdx + 30], 13 + QUAD $0x0d1f1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 31], 13 + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + QUAD $0x1c0f7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdi + r9 + 28], 14 + QUAD $0x1d0f4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdi + r9 + 29], 14 + QUAD $0x1e0f54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdi + r9 + 30], 14 + QUAD $0x1f0f74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdi + r9 + 31], 14 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x1c277c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r12 + 28], 15 + QUAD $0x1d274c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdi + r12 + 29], 15 + QUAD $0x1e2754203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdi + r12 + 30], 15 + LONG $0x740f4566; BYTE $0xfe // pcmpeqb xmm15, xmm14 + QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI5_19] */ + LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 + QUAD $0x1f2774203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdi + r12 + 31], 15 + QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI5_22] */ + LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 + LONG $0x740f4566; BYTE $0xce // pcmpeqb xmm9, xmm14 + LONG $0xdf0f4466; BYTE $0xcd // pandn xmm9, xmm5 + LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 + LONG $0xdf0f4466; BYTE $0xd7 // pandn xmm10, xmm7 + LONG $0xeb0f4566; BYTE $0xd1 // por xmm10, xmm9 + LONG $0x740f4166; BYTE $0xf6 // pcmpeqb xmm6, xmm14 + LONG $0xf4df0f66 // pandn xmm6, xmm4 + LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 + LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 + LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 + LONG $0xc6600f66 // punpcklbw xmm0, xmm6 + QUAD $0x0000d0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 208] + LONG $0xcb6f0f66 // movdqa xmm1, xmm3 + QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] + LONG $0xcc600f66 // punpcklbw xmm1, xmm4 + LONG $0xd16f0f66 // movdqa xmm2, xmm1 + LONG $0xd0610f66 // punpcklwd xmm2, xmm0 + LONG $0xc8690f66 // punpckhwd xmm1, xmm0 + LONG $0x680f4466; BYTE $0xc6 // punpckhbw xmm8, xmm6 + LONG $0xdc680f66 // punpckhbw xmm3, xmm4 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xd8 // punpckhwd xmm3, xmm8 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + LONG $0x7f0f41f3; WORD $0x885c; BYTE $0x30 // movdqu oword [r8 + 4*rcx + 48], xmm3 + LONG $0x7f0f41f3; WORD $0x8844; BYTE $0x20 // movdqu oword [r8 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x884c; BYTE $0x10 // movdqu oword [r8 + 4*rcx + 16], xmm1 + LONG $0x7f0f41f3; WORD $0x8814 // movdqu oword [r8 + 4*rcx], xmm2 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + JNE LBB5_218 + QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] + QUAD $0x000000a8248c3b48 // cmp rcx, qword [rsp + 168] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x24748a44; BYTE $0x0c // mov r14b, byte [rsp + 12] + QUAD $0x0000010024ac8b4c // mov r13, qword [rsp + 256] + QUAD $0x000000f824bc8b48 // mov rdi, qword [rsp + 248] + JNE LBB5_168 + JMP LBB5_172 TEXT ·_comparison_greater_arr_arr_sse4(SB), $80-48 @@ -31299,68 +32223,82 @@ TEXT ·_comparison_greater_arr_arr_sse4(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB6_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB6_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB6_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB6_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB6_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_22 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_20: - WORD $0x0a8b // mov ecx, dword [rdx] - LONG $0x04c28348 // add rdx, 4 - WORD $0x0e3b // cmp ecx, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_20 - LONG $0x01c68349 // add r14, 1 - -LBB6_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_26 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB6_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB6_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB6_24: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x82 // mov ebx, dword [rdx + 4*rax] + WORD $0x1c3b; BYTE $0x86 // cmp ebx, dword [rsi + 4*rax] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_26: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_28: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_32 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_30: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] LONG $0xd5970f41 // seta r13b @@ -31381,7 +32319,7 @@ LBB6_24: WORD $0x468b; BYTE $0x1c // mov eax, dword [rsi + 28] WORD $0x423b; BYTE $0x1c // cmp eax, dword [rdx + 28] WORD $0x468b; BYTE $0x20 // mov eax, dword [rsi + 32] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b WORD $0x423b; BYTE $0x20 // cmp eax, dword [rdx + 32] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] @@ -31395,7 +32333,7 @@ LBB6_24: WORD $0x468b; BYTE $0x30 // mov eax, dword [rsi + 48] LONG $0xd1970f41 // seta r9b WORD $0x423b; BYTE $0x30 // cmp eax, dword [rdx + 48] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b WORD $0x468b; BYTE $0x34 // mov eax, dword [rsi + 52] WORD $0x423b; BYTE $0x34 // cmp eax, dword [rdx + 52] WORD $0x468b; BYTE $0x38 // mov eax, dword [rsi + 56] @@ -31411,7 +32349,7 @@ LBB6_24: LONG $0x405a3b44 // cmp r11d, dword [rdx + 64] LONG $0x2454970f; BYTE $0x0a // seta byte [rsp + 10] WORD $0x4a3b; BYTE $0x44 // cmp ecx, dword [rdx + 68] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b WORD $0x423b; BYTE $0x48 // cmp eax, dword [rdx + 72] WORD $0x468b; BYTE $0x4c // mov eax, dword [rsi + 76] LONG $0x2454970f; BYTE $0x06 // seta byte [rsp + 6] @@ -31455,11 +32393,11 @@ LBB6_24: WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] WORD $0x970f; BYTE $0xd0 // seta al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] + LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0844; BYTE $0xe9 // or cl, r13b @@ -31479,23 +32417,23 @@ LBB6_24: LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xcc // or r12b, r9b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0845; BYTE $0xc2 // or r10b, r8b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0a // add r14b, byte [rsp + 10] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0a // add r12b, byte [rsp + 10] LONG $0x244cb60f; BYTE $0x06 // movzx ecx, byte [rsp + 6] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe1 // or cl, r12b LONG $0x03e3c041 // shl r11b, 3 WORD $0x0841; BYTE $0xcb // or r11b, cl LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] @@ -31505,12 +32443,12 @@ LBB6_24: LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd908 // or cl, bl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x44b60f44; WORD $0x0d24 // movzx r8d, byte [rsp + 13] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0844; BYTE $0xc7 // or dil, r8b - LONG $0x01568845 // mov byte [r14 + 1], r10b + LONG $0x01578845 // mov byte [r15 + 1], r10b WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xc900 // add cl, cl @@ -31534,98 +32472,111 @@ LBB6_24: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x027e8841 // mov byte [r14 + 2], dil - LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x027f8841 // mov byte [r15 + 2], dil + LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_24 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_30 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] -LBB6_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_28: +LBB6_34: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8a // mov edi, dword [rdx + 4*rcx] WORD $0x3c3b; BYTE $0x8e // cmp edi, dword [rsi + 4*rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_28 - JMP LBB6_123 - -LBB6_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB6_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB6_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB6_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_50 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_48: - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - LONG $0xd2970f41 // seta r10b - LONG $0x08c28348 // add rdx, 8 - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_48 - LONG $0x01c68349 // add r14, 1 - -LBB6_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_54 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB6_52: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_34 + JMP LBB6_153 + +LBB6_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB6_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB6_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB6_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_58: + LONG $0x04100ff2; BYTE $0xc6 // movsd xmm0, qword [rsi + 8*rax] + LONG $0x042e0f66; BYTE $0xc2 // ucomisd xmm0, qword [rdx + 8*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xd3970f41 // seta r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_58 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_60: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_62: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_66 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB6_64: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06100ff2 // movsd xmm0, qword [rsi] LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] LONG $0x2454970f; BYTE $0x04 // seta byte [rsp + 4] @@ -31649,7 +32600,7 @@ LBB6_52: WORD $0x970f; BYTE $0xd0 // seta al LONG $0x46100ff2; BYTE $0x38 // movsd xmm0, qword [rsi + 56] LONG $0x422e0f66; BYTE $0x38 // ucomisd xmm0, qword [rdx + 56] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x46100ff2; BYTE $0x40 // movsd xmm0, qword [rsi + 64] LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] @@ -31664,7 +32615,7 @@ LBB6_52: LONG $0xd3970f41 // seta r11b LONG $0x46100ff2; BYTE $0x60 // movsd xmm0, qword [rsi + 96] LONG $0x422e0f66; BYTE $0x60 // ucomisd xmm0, qword [rdx + 96] - LONG $0xd6970f41 // seta r14b + LONG $0xd7970f41 // seta r15b LONG $0x46100ff2; BYTE $0x68 // movsd xmm0, qword [rsi + 104] LONG $0x422e0f66; BYTE $0x68 // ucomisd xmm0, qword [rdx + 104] LONG $0x2454970f; BYTE $0x05 // seta byte [rsp + 5] @@ -31726,8 +32677,8 @@ LBB6_52: WORD $0xc900 // add cl, cl LONG $0x04244c02 // add cl, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl @@ -31748,26 +32699,26 @@ LBB6_52: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -31775,12 +32726,12 @@ LBB6_52: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -31806,23 +32757,22 @@ LBB6_52: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB6_52 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB6_64 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB6_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_56: +LBB6_68: LONG $0x04100ff2; BYTE $0xce // movsd xmm0, qword [rsi + 8*rcx] LONG $0x042e0f66; BYTE $0xca // ucomisd xmm0, qword [rdx + 8*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -31830,75 +32780,95 @@ LBB6_56: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_56 - JMP LBB6_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_68 + JMP LBB6_153 LBB6_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB6_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + JE LBB6_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB6_9 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB6_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd49f0f41 // setg r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_6 - LONG $0x01c68349 // add r14, 1 - -LBB6_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_12 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB6_10: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + LONG $0x38048841 // mov byte [r8 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB6_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB6_9: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_11: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_15 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_13: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x0246b60f // movzx eax, byte [rsi + 2] @@ -31918,7 +32888,7 @@ LBB6_10: LONG $0x24549f0f; BYTE $0x04 // setg byte [rsp + 4] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd79f0f41 // setg r15b + LONG $0xd69f0f41 // setg r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x24549f0f; BYTE $0x07 // setg byte [rsp + 7] @@ -31933,7 +32903,7 @@ LBB6_10: LONG $0xd39f0f41 // setg r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd69f0f41 // setg r14b + LONG $0xd79f0f41 // setg r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] LONG $0x24549f0f; BYTE $0x05 // setg byte [rsp + 5] @@ -31993,12 +32963,12 @@ LBB6_10: WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] LONG $0xd09f0f41 // setg r8b WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x30244c02 // add cl, byte [rsp + 48] WORD $0xc889 // mov eax, ecx LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al @@ -32020,26 +32990,26 @@ LBB6_10: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x06 // movzx edi, byte [rsp + 6] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0d // add r12b, byte [rsp + 13] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -32047,12 +33017,12 @@ LBB6_10: LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al @@ -32078,23 +33048,22 @@ LBB6_10: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_10 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB6_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_13 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB6_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_14: +LBB6_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -32102,74 +33071,88 @@ LBB6_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_14 - JMP LBB6_123 - -LBB6_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB6_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB6_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_36 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_34: - WORD $0x8b48; BYTE $0x0a // mov rcx, qword [rdx] - LONG $0x08c28348 // add rdx, 8 - WORD $0x3b48; BYTE $0x0e // cmp rcx, qword [rsi] - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_34 - LONG $0x01c68349 // add r14, 1 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_17 + JMP LBB6_153 LBB6_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_40 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB6_38: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB6_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB6_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_41: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc21c8b48 // mov rbx, qword [rdx + 8*rax] + LONG $0xc61c3b48 // cmp rbx, qword [rsi + 8*rax] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_43: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_45: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_49 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_47: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0xd5970f41 // seta r13b @@ -32190,7 +33173,7 @@ LBB6_38: LONG $0x38468b48 // mov rax, qword [rsi + 56] LONG $0x38423b48 // cmp rax, qword [rdx + 56] LONG $0x40468b48 // mov rax, qword [rsi + 64] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x40423b48 // cmp rax, qword [rdx + 64] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] @@ -32204,7 +33187,7 @@ LBB6_38: LONG $0x60468b48 // mov rax, qword [rsi + 96] LONG $0xd1970f41 // seta r9b LONG $0x60423b48 // cmp rax, qword [rdx + 96] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b LONG $0x68468b48 // mov rax, qword [rsi + 104] LONG $0x68423b48 // cmp rax, qword [rdx + 104] LONG $0x70468b48 // mov rax, qword [rsi + 112] @@ -32220,7 +33203,7 @@ LBB6_38: LONG $0x809a3b4c; WORD $0x0000; BYTE $0x00 // cmp r11, qword [rdx + 128] LONG $0x2454970f; BYTE $0x0a // seta byte [rsp + 10] LONG $0x888a3b48; WORD $0x0000; BYTE $0x00 // cmp rcx, qword [rdx + 136] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b LONG $0x90823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 144] LONG $0x98868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 152] LONG $0x2454970f; BYTE $0x06 // seta byte [rsp + 6] @@ -32264,11 +33247,11 @@ LBB6_38: LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] WORD $0x970f; BYTE $0xd0 // seta al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] + LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0844; BYTE $0xe9 // or cl, r13b @@ -32288,23 +33271,23 @@ LBB6_38: LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xcc // or r12b, r9b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0845; BYTE $0xc2 // or r10b, r8b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0a // add r14b, byte [rsp + 10] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0a // add r12b, byte [rsp + 10] LONG $0x244cb60f; BYTE $0x06 // movzx ecx, byte [rsp + 6] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe1 // or cl, r12b LONG $0x03e3c041 // shl r11b, 3 WORD $0x0841; BYTE $0xcb // or r11b, cl LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] @@ -32314,12 +33297,12 @@ LBB6_38: LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd908 // or cl, bl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x44b60f44; WORD $0x0d24 // movzx r8d, byte [rsp + 13] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0844; BYTE $0xc7 // or dil, r8b - LONG $0x01568845 // mov byte [r14 + 1], r10b + LONG $0x01578845 // mov byte [r15 + 1], r10b WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xc900 // add cl, cl @@ -32343,93 +33326,106 @@ LBB6_38: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x027e8841 // mov byte [r14 + 2], dil - LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x027f8841 // mov byte [r15 + 2], dil + LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_38 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_47 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] -LBB6_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_42: +LBB6_51: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xca3c8b48 // mov rdi, qword [rdx + 8*rcx] LONG $0xce3c3b48 // cmp rdi, qword [rsi + 8*rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_42 - JMP LBB6_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_51 + JMP LBB6_153 -LBB6_68: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_72 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_70: - WORD $0xb70f; BYTE $0x0a // movzx ecx, word [rdx] - LONG $0x02c28348 // add rdx, 2 - WORD $0x3b66; BYTE $0x0e // cmp cx, word [rsi] - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_70 - LONG $0x01c68349 // add r14, 1 +LBB6_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_86: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x421cb70f // movzx ebx, word [rdx + 2*rax] + LONG $0x461c3b66 // cmp bx, word [rsi + 2*rax] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB6_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_76 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 +LBB6_88: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 -LBB6_74: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_90: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_94 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_92: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0xd5970f41 // seta r13b @@ -32450,7 +33446,7 @@ LBB6_74: LONG $0x0e46b70f // movzx eax, word [rsi + 14] LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0x1046b70f // movzx eax, word [rsi + 16] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x10423b66 // cmp ax, word [rdx + 16] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] @@ -32464,7 +33460,7 @@ LBB6_74: LONG $0x1846b70f // movzx eax, word [rsi + 24] LONG $0xd1970f41 // seta r9b LONG $0x18423b66 // cmp ax, word [rdx + 24] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b LONG $0x1a46b70f // movzx eax, word [rsi + 26] LONG $0x1a423b66 // cmp ax, word [rdx + 26] LONG $0x1c46b70f // movzx eax, word [rsi + 28] @@ -32480,7 +33476,7 @@ LBB6_74: LONG $0x5a3b4466; BYTE $0x20 // cmp r11w, word [rdx + 32] LONG $0x2454970f; BYTE $0x0a // seta byte [rsp + 10] LONG $0x224a3b66 // cmp cx, word [rdx + 34] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b LONG $0x24423b66 // cmp ax, word [rdx + 36] LONG $0x2646b70f // movzx eax, word [rsi + 38] LONG $0x2454970f; BYTE $0x06 // seta byte [rsp + 6] @@ -32524,11 +33520,11 @@ LBB6_74: LONG $0x3e423b66 // cmp ax, word [rdx + 62] WORD $0x970f; BYTE $0xd0 // seta al WORD $0x0045; BYTE $0xed // add r13b, r13b - LONG $0x246c0244; BYTE $0x28 // add r13b, byte [rsp + 40] + LONG $0x246c0244; BYTE $0x30 // add r13b, byte [rsp + 48] LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0844; BYTE $0xe9 // or cl, r13b @@ -32548,23 +33544,23 @@ LBB6_74: LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xcc // or r12b, r9b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xcf // or r15b, r9b LONG $0x245cb60f; BYTE $0x05 // movzx ebx, byte [rsp + 5] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b + WORD $0x0844; BYTE $0xfb // or bl, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e2c041 // shl r10b, 7 WORD $0x0845; BYTE $0xc2 // or r10b, r8b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0x0841; BYTE $0xda // or r10b, bl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0a // add r14b, byte [rsp + 10] + WORD $0x0045; BYTE $0xe4 // add r12b, r12b + LONG $0x24640244; BYTE $0x0a // add r12b, byte [rsp + 10] LONG $0x244cb60f; BYTE $0x06 // movzx ecx, byte [rsp + 6] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0844; BYTE $0xf1 // or cl, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe1 // or cl, r12b LONG $0x03e3c041 // shl r11b, 3 WORD $0x0841; BYTE $0xcb // or r11b, cl LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] @@ -32574,12 +33570,12 @@ LBB6_74: LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd908 // or cl, bl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x44b60f44; WORD $0x0d24 // movzx r8d, byte [rsp + 13] LONG $0x06e0c041 // shl r8b, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0844; BYTE $0xc7 // or dil, r8b - LONG $0x01568845 // mov byte [r14 + 1], r10b + LONG $0x01578845 // mov byte [r15 + 1], r10b WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xc900 // add cl, cl @@ -32603,96 +33599,109 @@ LBB6_74: WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x027e8841 // mov byte [r14 + 2], dil - LONG $0x03468841 // mov byte [r14 + 3], al + LONG $0x027f8841 // mov byte [r15 + 2], dil + LONG $0x03478841 // mov byte [r15 + 3], al LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_74 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_92 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] -LBB6_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_78: +LBB6_96: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4a3cb70f // movzx edi, word [rdx + 2*rcx] LONG $0x4e3c3b66 // cmp di, word [rsi + 2*rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_78 - JMP LBB6_123 - -LBB6_79: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_83 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_81 - LONG $0x01c68349 // add r14, 1 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_96 + JMP LBB6_153 + +LBB6_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB6_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_87 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB6_85: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd39f0f41 // setg r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_102: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_104: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_108 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB6_106: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] LONG $0x24549f0f; BYTE $0x14 // setg byte [rsp + 20] @@ -32716,7 +33725,7 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x09 // setg byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd09f0f41 // setg r8b + LONG $0xd79f0f40 // setg dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd39f0f41 // setg r11b @@ -32756,7 +33765,7 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x0b // setg byte [rsp + 11] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] + LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd19f0f41 // setg r9b @@ -32765,10 +33774,10 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x13 // setg byte [rsp + 19] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] + LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] + LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] LONG $0x24549f0f; BYTE $0x0f // setg byte [rsp + 15] @@ -32783,10 +33792,10 @@ LBB6_85: LONG $0x24549f0f; BYTE $0x11 // setg byte [rsp + 17] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] - LONG $0xd79f0f40 // setg dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09f0f41 // setg r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -32795,34 +33804,34 @@ LBB6_85: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -32835,22 +33844,23 @@ LBB6_85: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -32867,26 +33877,25 @@ LBB6_85: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB6_85 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - -LBB6_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + JNE LBB6_106 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB6_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_89: +LBB6_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -32894,73 +33903,87 @@ LBB6_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_89 - JMP LBB6_123 - -LBB6_101: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_105 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_103 - LONG $0x01c68349 // add r14, 1 - -LBB6_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_109 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB6_107: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_110 + JMP LBB6_153 + +LBB6_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd39f0f41 // setg r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_130: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_132: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_136 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB6_134: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] LONG $0x24549f0f; BYTE $0x14 // setg byte [rsp + 20] @@ -32984,7 +34007,7 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x09 // setg byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd09f0f41 // setg r8b + LONG $0xd79f0f40 // setg dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd39f0f41 // setg r11b @@ -33024,7 +34047,7 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x0b // setg byte [rsp + 11] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] + LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd19f0f41 // setg r9b @@ -33033,10 +34056,10 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x13 // setg byte [rsp + 19] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] + LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] + LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] LONG $0x24549f0f; BYTE $0x0f // setg byte [rsp + 15] @@ -33051,10 +34074,10 @@ LBB6_107: LONG $0x24549f0f; BYTE $0x11 // setg byte [rsp + 17] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] - LONG $0xd79f0f40 // setg dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09f0f41 // setg r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -33063,34 +34086,34 @@ LBB6_107: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -33103,22 +34126,23 @@ LBB6_107: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -33135,26 +34159,25 @@ LBB6_107: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB6_107 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB6_134 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB6_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_111: +LBB6_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -33162,67 +34185,81 @@ LBB6_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_111 - JMP LBB6_123 - -LBB6_112: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_116 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_114: - LONG $0x06100ff3 // movss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] - LONG $0xd2970f41 // seta r10b - LONG $0x04c28348 // add rdx, 4 - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_114 - LONG $0x01c68349 // add r14, 1 - -LBB6_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_120 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_138 + JMP LBB6_153 + +LBB6_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB6_142: + LONG $0x04100ff3; BYTE $0x86 // movss xmm0, dword [rsi + 4*rax] + LONG $0x82042e0f // ucomiss xmm0, dword [rdx + 4*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xd3970f41 // seta r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_142 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB6_144: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_146: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_150 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax -LBB6_118: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_148: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06100ff3 // movss xmm0, dword [rsi] WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] LONG $0x2454970f; BYTE $0x04 // seta byte [rsp + 4] @@ -33246,7 +34283,7 @@ LBB6_118: WORD $0x970f; BYTE $0xd0 // seta al LONG $0x46100ff3; BYTE $0x1c // movss xmm0, dword [rsi + 28] LONG $0x1c422e0f // ucomiss xmm0, dword [rdx + 28] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x46100ff3; BYTE $0x20 // movss xmm0, dword [rsi + 32] LONG $0x20422e0f // ucomiss xmm0, dword [rdx + 32] LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] @@ -33261,7 +34298,7 @@ LBB6_118: LONG $0xd3970f41 // seta r11b LONG $0x46100ff3; BYTE $0x30 // movss xmm0, dword [rsi + 48] LONG $0x30422e0f // ucomiss xmm0, dword [rdx + 48] - LONG $0xd6970f41 // seta r14b + LONG $0xd7970f41 // seta r15b LONG $0x46100ff3; BYTE $0x34 // movss xmm0, dword [rsi + 52] LONG $0x34422e0f // ucomiss xmm0, dword [rdx + 52] LONG $0x2454970f; BYTE $0x05 // seta byte [rsp + 5] @@ -33323,8 +34360,8 @@ LBB6_118: WORD $0xc900 // add cl, cl LONG $0x04244c02 // add cl, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xc6 // or r14b, al LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl @@ -33345,26 +34382,26 @@ LBB6_118: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0e // add r12b, byte [rsp + 14] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -33372,12 +34409,12 @@ LBB6_118: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -33403,23 +34440,22 @@ LBB6_118: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB6_118 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB6_148 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB6_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_122: +LBB6_152: LONG $0x04100ff3; BYTE $0x8e // movss xmm0, dword [rsi + 4*rcx] LONG $0x8a042e0f // ucomiss xmm0, dword [rdx + 4*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -33427,66 +34463,85 @@ LBB6_122: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_122 - JMP LBB6_123 - -LBB6_57: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_61 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB6_59: - WORD $0xb60f; BYTE $0x0a // movzx ecx, byte [rdx] - LONG $0x01c28348 // add rdx, 1 - WORD $0x0e3a // cmp cl, byte [rsi] - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d - LONG $0x07588d48 // lea rbx, [rax + 7] + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_152 + JMP LBB6_153 + +LBB6_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_59 - LONG $0x01c68349 // add r14, 1 - -LBB6_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_65 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB6_63: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + JLE LBB6_74 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x3145; BYTE $0xe4 // xor r12d, r12d + +LBB6_72: + LONG $0x0cb60f42; BYTE $0x22 // movzx ecx, byte [rdx + r12] + LONG $0x260c3a42 // cmp cl, byte [rsi + r12] + WORD $0x1945; BYTE $0xd2 // sbb r10d, r10d + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf2 // xor r10b, r14b + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + LONG $0x38048841 // mov byte [r8 + rdi], al + LONG $0x01c48349 // add r12, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc38349 // add r11, -1 + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB6_72 + WORD $0x294c; BYTE $0xde // sub rsi, r11 + WORD $0x294c; BYTE $0xda // sub rdx, r11 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB6_74: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 + +LBB6_76: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_80 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB6_78: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] @@ -33508,9 +34563,9 @@ LBB6_63: LONG $0x0646b60f // movzx eax, byte [rsi + 6] WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] LONG $0x0746b60f // movzx eax, byte [rsi + 7] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7970f41 // seta r15b + LONG $0xd6970f41 // seta r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x0946b60f // movzx eax, byte [rsi + 9] @@ -33540,11 +34595,11 @@ LBB6_63: LONG $0x1146b60f // movzx eax, byte [rsi + 17] LONG $0x2454970f; BYTE $0x0c // seta byte [rsp + 12] WORD $0x423a; BYTE $0x11 // cmp al, byte [rdx + 17] - LONG $0xd4970f41 // seta r12b + LONG $0xd7970f41 // seta r15b LONG $0x1246b60f // movzx eax, byte [rsi + 18] WORD $0x423a; BYTE $0x12 // cmp al, byte [rdx + 18] LONG $0x1346b60f // movzx eax, byte [rsi + 19] - LONG $0xd6970f41 // seta r14b + LONG $0xd4970f41 // seta r12b WORD $0x423a; BYTE $0x13 // cmp al, byte [rdx + 19] LONG $0x2454970f; BYTE $0x09 // seta byte [rsp + 9] LONG $0x1446b60f // movzx eax, byte [rsi + 20] @@ -33587,10 +34642,10 @@ LBB6_63: WORD $0x0045; BYTE $0xed // add r13b, r13b LONG $0x246c0244; BYTE $0x04 // add r13b, byte [rsp + 4] WORD $0x8944; BYTE $0xe8 // mov eax, r13d - LONG $0x6cb60f44; WORD $0x2824 // movzx r13d, byte [rsp + 40] + LONG $0x6cb60f44; WORD $0x3024 // movzx r13d, byte [rsp + 48] LONG $0x06e5c041 // shl r13b, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0845; BYTE $0xef // or r15b, r13b + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0845; BYTE $0xee // or r14b, r13b LONG $0x6cb60f44; WORD $0x1424 // movzx r13d, byte [rsp + 20] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0841; BYTE $0xc5 // or r13b, al @@ -33620,28 +34675,28 @@ LBB6_63: LONG $0x06e1c041 // shl r9b, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al - WORD $0x0045; BYTE $0xe4 // add r12b, r12b - LONG $0x24640244; BYTE $0x0c // add r12b, byte [rsp + 12] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xe6 // or r14b, r12b + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x0c // add r15b, byte [rsp + 12] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0844; BYTE $0xe0 // or al, r12b LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0a // movzx ecx, byte [rsp + 10] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc0 // or r8b, al LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] WORD $0xc000 // add al, al @@ -33664,96 +34719,109 @@ LBB6_63: LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xc7 // or dil, al WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x02468845 // mov byte [r14 + 2], r8b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x02478845 // mov byte [r15 + 2], r8b + LONG $0x037f8841 // mov byte [r15 + 3], dil LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB6_63 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB6_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB6_78 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB6_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_67: +LBB6_82: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0a1cb60f // movzx ebx, byte [rdx + rcx] WORD $0x1c3a; BYTE $0x0e // cmp bl, byte [rsi + rcx] WORD $0xff19 // sbb edi, edi WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_67 - JMP LBB6_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_82 + JMP LBB6_153 -LBB6_90: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB6_94 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB6_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB6_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB6_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB6_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd29f0f41 // setg r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB6_92 - LONG $0x01c68349 // add r14, 1 +LBB6_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd39f0f41 // setg r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB6_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB6_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB6_98 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 +LBB6_116: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB6_153 + LONG $0x01c78349 // add r15, 1 -LBB6_96: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB6_118: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB6_122 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB6_120: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] LONG $0x24549f0f; BYTE $0x14 // setg byte [rsp + 20] @@ -33777,7 +34845,7 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x09 // setg byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd09f0f41 // setg r8b + LONG $0xd79f0f40 // setg dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd39f0f41 // setg r11b @@ -33817,7 +34885,7 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x0b // setg byte [rsp + 11] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] + LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd19f0f41 // setg r9b @@ -33826,10 +34894,10 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x13 // setg byte [rsp + 19] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] + LONG $0x24549f0f; BYTE $0x0c // setg byte [rsp + 12] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x24549f0f; BYTE $0x0e // setg byte [rsp + 14] + LONG $0x24549f0f; BYTE $0x0d // setg byte [rsp + 13] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] LONG $0x24549f0f; BYTE $0x0f // setg byte [rsp + 15] @@ -33844,10 +34912,10 @@ LBB6_96: LONG $0x24549f0f; BYTE $0x11 // setg byte [rsp + 17] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] - LONG $0xd79f0f40 // setg dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09f0f41 // setg r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -33856,34 +34924,34 @@ LBB6_96: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -33896,22 +34964,23 @@ LBB6_96: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -33928,26 +34997,25 @@ LBB6_96: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB6_96 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB6_120 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB6_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB6_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB6_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB6_153 WORD $0xc931 // xor ecx, ecx -LBB6_100: +LBB6_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -33955,19 +35023,19 @@ LBB6_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB6_100 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB6_124 -LBB6_123: +LBB6_153: SUBQ $8, SP RET @@ -34007,7 +35075,7 @@ DATA LCDATA5<>+0x100(SB)/8, $0xffffffffffffffff DATA LCDATA5<>+0x108(SB)/8, $0xffffffffffffffff GLOBL LCDATA5<>(SB), 8, $272 -TEXT ·_comparison_greater_arr_scalar_sse4(SB), $360-48 +TEXT ·_comparison_greater_arr_scalar_sse4(SB), $376-48 MOVQ typ+0(FP), DI MOVQ left+8(FP), SI @@ -34018,108 +35086,121 @@ TEXT ·_comparison_greater_arr_scalar_sse4(SB), $360-48 MOVQ SP, BP ADDQ $16, SP ANDQ $-16, SP - MOVQ BP, 336(SP) + MOVQ BP, 352(SP) LEAQ LCDATA5<>(SB), BP - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - LONG $0x240c8948 // mov qword [rsp], rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB7_26 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB7_24 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB7_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB7_98 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB7_114 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB7_202 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_17 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB7_112 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB7_130 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB7_226 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_15 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_13 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_12: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc08348 // add rax, -1 + JNE LBB7_12 + +LBB7_13: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 LBB7_15: - WORD $0x3b44; BYTE $0x2e // cmp r13d, dword [rsi] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0xd219 // sbb edx, edx - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x19 // movzx r8d, byte [r9 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x193c8841 // mov byte [r9 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_15 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_19 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax LBB7_17: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_21 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - -LBB7_19: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d QUAD $0x000000d02494970f // seta byte [rsp + 208] LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd2970f41 // seta r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd7970f40 // seta dil + LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0xd6970f41 // seta r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d QUAD $0x000000b02494970f // seta byte [rsp + 176] LONG $0x106e3944 // cmp dword [rsi + 16], r13d - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x970f; BYTE $0xd0 // seta al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - LONG $0xd6970f41 // seta r14b + WORD $0x970f; BYTE $0xd3 // seta bl LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x000000802494970f // seta byte [rsp + 128] + QUAD $0x000000c02494970f // seta byte [rsp + 192] LONG $0x246e3944 // cmp dword [rsi + 36], r13d - WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x286e3944 // cmp dword [rsi + 40], r13d LONG $0xd1970f41 // seta r9b LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd3970f41 // seta r11b + LONG $0xd2970f41 // seta r10b LONG $0x306e3944 // cmp dword [rsi + 48], r13d - WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0xd3970f41 // seta r11b LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4970f41 // seta r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d - QUAD $0x000000a02494970f // seta byte [rsp + 160] + QUAD $0x000000902494970f // seta byte [rsp + 144] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x970f; BYTE $0xd1 // seta cl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - QUAD $0x000000902494970f // seta byte [rsp + 144] + QUAD $0x000000a02494970f // seta byte [rsp + 160] LONG $0x486e3944 // cmp dword [rsi + 72], r13d - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x546e3944 // cmp dword [rsi + 84], r13d LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x586e3944 // cmp dword [rsi + 88], r13d @@ -34127,7 +35208,7 @@ LBB7_19: LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7970f41 // seta r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0x646e3944 // cmp dword [rsi + 100], r13d LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x686e3944 // cmp dword [rsi + 104], r13d @@ -34135,76 +35216,76 @@ LBB7_19: LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0x706e3944 // cmp dword [rsi + 112], r13d - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x746e3944 // cmp dword [rsi + 116], r13d LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x786e3944 // cmp dword [rsi + 120], r13d LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d LONG $0xd0970f41 // seta r8b - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x000000d024bc0240 // add dil, byte [rsp + 208] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - WORD $0xd200 // add dl, dl - LONG $0x80249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0xc900 // add cl, cl + LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x24148b4c // mov r10, qword [rsp] + WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0841; BYTE $0xdc // or r12b, bl - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0x0841; BYTE $0xd6 // or r14b, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xd200 // add dl, dl - LONG $0x48245402 // add dl, byte [rsp + 72] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x8845; BYTE $0x32 // mov byte [r10], r14b + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x241c8841 // mov byte [r12], bl LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014a8841 // mov byte [r10 + 1], cl - WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] + LONG $0x18244c02 // add cl, byte [rsp + 24] WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 @@ -34214,7 +35295,7 @@ LBB7_19: WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx @@ -34226,90 +35307,102 @@ LBB7_19: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8845 // mov byte [r10 + 2], r15b - LONG $0x03428845 // mov byte [r10 + 3], r8b + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c28349 // add r10, 4 - LONG $0x2414894c // mov qword [rsp], r10 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB7_19 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - -LBB7_21: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB7_137 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB7_17 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + +LBB7_19: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_226 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_155 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_24 + JMP LBB7_22 -LBB7_26: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB7_27 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB7_157 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB7_172 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB7_202 - LONG $0x1f738d4d // lea r14, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xf3490f4d // cmovns r14, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x02100ff2 // movsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_49 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24148b4c // mov r10, qword [rsp] - -LBB7_47: +LBB7_24: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB7_25 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB7_177 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB7_194 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB7_226 + WORD $0x8b4c; BYTE $0x32 // mov r14, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_49 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB7_48: LONG $0x0e100ff2 // movsd xmm1, qword [rsi] LONG $0x08c68348 // add rsi, 8 LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3a // movzx r9d, byte [r10 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3a1c8841 // mov byte [r10 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_47 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB7_48 LBB7_49: - LONG $0x05fec149 // sar r14, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_53 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000c024b4894c // mov qword [rsp + 192], r14 - QUAD $0x000000d024b4894c // mov qword [rsp + 208], r14 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 LBB7_51: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_55 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x000000e024b4894c // mov qword [rsp + 224], r14 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + +LBB7_53: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 LONG $0x0e100ff2 // movsd xmm1, qword [rsi] LONG $0x56100ff2; BYTE $0x08 // movsd xmm2, qword [rsi + 8] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0xd02e0f66 // ucomisd xmm2, xmm0 - WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x4e100ff2; BYTE $0x10 // movsd xmm1, qword [rsi + 16] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0x4e100ff2; BYTE $0x18 // movsd xmm1, qword [rsi + 24] @@ -34319,13 +35412,13 @@ LBB7_51: LONG $0x4e100ff2; BYTE $0x20 // movsd xmm1, qword [rsi + 32] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0x4e100ff2; BYTE $0x28 // movsd xmm1, qword [rsi + 40] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x4e100ff2; BYTE $0x30 // movsd xmm1, qword [rsi + 48] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0x4e100ff2; BYTE $0x38 // movsd xmm1, qword [rsi + 56] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x4e100ff2; BYTE $0x40 // movsd xmm1, qword [rsi + 64] @@ -34337,9 +35430,9 @@ LBB7_51: LONG $0x4e100ff2; BYTE $0x50 // movsd xmm1, qword [rsi + 80] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0x4e100ff2; BYTE $0x58 // movsd xmm1, qword [rsi + 88] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0x4e100ff2; BYTE $0x60 // movsd xmm1, qword [rsi + 96] LONG $0x5e100ff2; BYTE $0x68 // movsd xmm3, qword [rsi + 104] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 @@ -34351,13 +35444,13 @@ LBB7_51: LONG $0xd82e0f66 // ucomisd xmm3, xmm0 QUAD $0x00009096100f44f2; BYTE $0x00 // movsd xmm10, qword [rsi + 144] QUAD $0x0000989e100f44f2; BYTE $0x00 // movsd xmm11, qword [rsi + 152] - QUAD $0x000000902494970f // seta byte [rsp + 144] + QUAD $0x000000a02494970f // seta byte [rsp + 160] QUAD $0x0000a0a6100f44f2; BYTE $0x00 // movsd xmm12, qword [rsi + 160] QUAD $0x0000a8ae100f44f2; BYTE $0x00 // movsd xmm13, qword [rsi + 168] LONG $0xe82e0f66 // ucomisd xmm5, xmm0 QUAD $0x0000b0b6100f44f2; BYTE $0x00 // movsd xmm14, qword [rsi + 176] QUAD $0x000000b896100ff2 // movsd xmm2, qword [rsi + 184] - QUAD $0x000000802494970f // seta byte [rsp + 128] + QUAD $0x000000c02494970f // seta byte [rsp + 192] QUAD $0x000000c09e100ff2 // movsd xmm3, qword [rsi + 192] QUAD $0x000000c8a6100ff2 // movsd xmm4, qword [rsi + 200] LONG $0xf02e0f66 // ucomisd xmm6, xmm0 @@ -34379,482 +35472,282 @@ LBB7_51: LONG $0x2e0f4466; BYTE $0xe8 // ucomisd xmm13, xmm0 LONG $0xd6970f41 // seta r14b LONG $0x2e0f4466; BYTE $0xf0 // ucomisd xmm14, xmm0 - QUAD $0x000000a02494970f // seta byte [rsp + 160] + QUAD $0x000000902494970f // seta byte [rsp + 144] LONG $0xd02e0f66 // ucomisd xmm2, xmm0 LONG $0xd1970f41 // seta r9b LONG $0xd82e0f66 // ucomisd xmm3, xmm0 - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0xe02e0f66 // ucomisd xmm4, xmm0 LONG $0xd7970f41 // seta r15b LONG $0xf02e0f66 // ucomisd xmm6, xmm0 - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0xf82e0f66 // ucomisd xmm7, xmm0 - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0xe82e0f66 // ucomisd xmm5, xmm0 - QUAD $0x000000f08e100ff2 // movsd xmm1, qword [rsi + 240] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] - LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - QUAD $0x000000f88e100ff2 // movsd xmm1, qword [rsi + 248] - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdb00 // add bl, bl - LONG $0x18245c02 // add bl, byte [rsp + 24] - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xec // or r12b, r13b - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - WORD $0x8941; BYTE $0xdc // mov r12d, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - LONG $0x64b60f44; WORD $0x5824 // movzx r12d, byte [rsp + 88] - LONG $0x06e4c041 // shl r12b, 6 - LONG $0x6cb60f44; WORD $0x4024 // movzx r13d, byte [rsp + 64] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xc000 // add al, al - LONG $0x10244402 // add al, byte [rsp + 16] - LONG $0x64b60f44; WORD $0x3824 // movzx r12d, byte [rsp + 56] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0x8944; BYTE $0xe0 // mov eax, r12d - LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x0841; BYTE $0xdd // or r13b, bl - QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0xc308 // or bl, al - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0xc900 // add cl, cl - LONG $0xb0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 176] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x03e0c041 // shl r8b, 3 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xc2 // or r10b, r8b - LONG $0x05e6c041 // shl r14b, 5 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0841; BYTE $0xdb // or r11b, bl - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x24048b48 // mov rax, qword [rsp] - WORD $0x8844; BYTE $0x28 // mov byte [rax], r13b - WORD $0x0845; BYTE $0xf1 // or r9b, r14b - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x68 // add r15b, byte [rsp + 104] - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc389 // mov ebx, eax - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd908 // or cl, bl - WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd908 // or cl, bl - LONG $0x01588844 // mov byte [rax + 1], r11b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - LONG $0x02488844 // mov byte [rax + 2], r9b - WORD $0xca08 // or dl, cl - WORD $0x5088; BYTE $0x03 // mov byte [rax + 3], dl - LONG $0x04c08348 // add rax, 4 - LONG $0x24048948 // mov qword [rsp], rax - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB7_51 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000c024b48b4c // mov r14, qword [rsp + 192] - -LBB7_53: - LONG $0x05e6c149 // shl r14, 5 - WORD $0x394d; BYTE $0xde // cmp r14, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xf0 // sub r8, r14 - WORD $0xf749; BYTE $0xd6 // not r14 - WORD $0x014d; BYTE $0xde // add r14, r11 - JNE LBB7_196 - WORD $0x3145; BYTE $0xd2 // xor r10d, r10d - JMP LBB7_198 - -LBB7_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB7_56 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB7_202 - WORD $0x8a44; BYTE $0x22 // mov r12b, byte [rdx] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24348b4c // mov r14, qword [rsp] - -LBB7_6: - WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_6 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB7_8: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_9 - LONG $0x10fa8349 // cmp r10, 16 - LONG $0x24648844; BYTE $0x08 // mov byte [rsp + 8], r12b - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000001202494894c // mov qword [rsp + 288], r10 - JB LBB7_81 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB7_84 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB7_84 - -LBB7_81: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax - -LBB7_87: - QUAD $0x000000e824942b4c // sub r10, qword [rsp + 232] - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - -LBB7_88: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b - QUAD $0x000000c024949f0f // setg byte [rsp + 192] - LONG $0x01663844 // cmp byte [rsi + 1], r12b - LONG $0xd69f0f40 // setg sil - LONG $0x02613844 // cmp byte [rcx + 2], r12b - LONG $0xd79f0f41 // setg r15b - LONG $0x03613844 // cmp byte [rcx + 3], r12b - LONG $0xd49f0f41 // setg r12b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al - QUAD $0x000000b024949f0f // setg byte [rsp + 176] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al - QUAD $0x000000d024949f0f // setg byte [rsp + 208] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al - LONG $0xd19f0f41 // setg r9b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al - QUAD $0x0000008024949f0f // setg byte [rsp + 128] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al - WORD $0x9f0f; BYTE $0xd2 // setg dl - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al - LONG $0xd79f0f40 // setg dil - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al - LONG $0xd29f0f41 // setg r10b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al - LONG $0xd69f0f41 // setg r14b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al - LONG $0xd59f0f41 // setg r13b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al - QUAD $0x000000a024949f0f // setg byte [rsp + 160] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al - LONG $0xd09f0f41 // setg r8b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl - QUAD $0x0000009024949f0f // setg byte [rsp + 144] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl - LONG $0xd39f0f41 // setg r11b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - LONG $0x24149f0f // setg byte [rsp] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x000000c024b40240 // add sil, byte [rsp + 192] - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0xf82e0f66 // ucomisd xmm7, xmm0 + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0xc82e0f66 // ucomisd xmm1, xmm0 + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0xe82e0f66 // ucomisd xmm5, xmm0 + QUAD $0x000000f08e100ff2 // movsd xmm1, qword [rsi + 240] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0xc82e0f66 // ucomisd xmm1, xmm0 + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + QUAD $0x000000f88e100ff2 // movsd xmm1, qword [rsi + 248] + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0xc82e0f66 // ucomisd xmm1, xmm0 + WORD $0x970f; BYTE $0xd3 // seta bl WORD $0xd200 // add dl, dl - LONG $0x80249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 128] + LONG $0x20245402 // add dl, byte [rsp + 32] + LONG $0x02e5c041 // shl r13b, 2 + WORD $0x0841; BYTE $0xd5 // or r13b, dl LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0x0845; BYTE $0xec // or r12b, r13b + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xe2 // or dl, r12b + WORD $0x8941; BYTE $0xd4 // mov r12d, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x64b60f44; WORD $0x5024 // movzx r12d, byte [rsp + 80] + LONG $0x06e4c041 // shl r12b, 6 + LONG $0x6cb60f44; WORD $0x4024 // movzx r13d, byte [rsp + 64] + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + WORD $0xc000 // add al, al + LONG $0x10244402 // add al, byte [rsp + 16] + LONG $0x64b60f44; WORD $0x2824 // movzx r12d, byte [rsp + 40] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0841; BYTE $0xc4 // or r12b, al + WORD $0x8944; BYTE $0xe0 // mov eax, r12d + LONG $0x64b60f44; WORD $0x1824 // movzx r12d, byte [rsp + 24] + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x64b60f44; WORD $0x0824 // movzx r12d, byte [rsp + 8] - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + WORD $0x0841; BYTE $0xd5 // or r13b, dl + QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] WORD $0xe2c0; BYTE $0x05 // shl dl, 5 WORD $0xc208 // or dl, al - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - WORD $0x0841; BYTE $0xd1 // or r9b, dl - WORD $0x0845; BYTE $0xe8 // or r8b, r13b - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xd200 // add dl, dl - LONG $0x90249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 144] - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - WORD $0x8844; BYTE $0x0a // mov byte [rdx], r9b - LONG $0x247cb60f; BYTE $0x50 // movzx edi, byte [rsp + 80] - LONG $0x06e7c040 // shl dil, 6 + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xfb // or r11b, dil - LONG $0x01428844 // mov byte [rdx + 1], r8b - WORD $0x0841; BYTE $0xf3 // or r11b, sil - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x38244402 // add al, byte [rsp + 56] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0xc900 // add cl, cl + LONG $0xb0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 176] + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x05e6c041 // shl r14b, 5 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + WORD $0x0841; BYTE $0xd3 // or r11b, dl + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xc1 // or r9b, al + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + WORD $0x8844; BYTE $0x28 // mov byte [rax], r13b + WORD $0x0845; BYTE $0xf1 // or r9b, r14b + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x70 // add r15b, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0x0844; BYTE $0xf8 // or al, r15b + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - LONG $0x2434b60f // movzx esi, byte [rsp] - LONG $0x06e6c040 // shl sil, 6 + WORD $0xc808 // or al, cl + LONG $0x245c8845; BYTE $0x01 // mov byte [r12 + 1], r11b + LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xcb08 // or bl, cl + LONG $0x244c8845; BYTE $0x02 // mov byte [r12 + 2], r9b WORD $0xc308 // or bl, al - LONG $0x025a8844 // mov byte [rdx + 2], r11b - WORD $0x5a88; BYTE $0x03 // mov byte [rdx + 3], bl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c28348 // add rdx, 4 - LONG $0x24548948; BYTE $0x60 // mov qword [rsp + 96], rdx - QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 + JNE LBB7_53 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + +LBB7_55: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_226 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_220 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + JMP LBB7_222 + +LBB7_2: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB7_58 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB7_226 + WORD $0x8a44; BYTE $0x2a // mov r13b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_5 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_86 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + +LBB7_92: + LONG $0x01768d4c // lea r14, [rsi + 1] + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x343c8841 // mov byte [r12 + rsi], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + LONG $0xffc08348 // add rax, -1 + JNE LBB7_92 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 JNE LBB7_88 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - JMP LBB7_90 - -LBB7_27: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB7_139 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB7_202 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JMP LBB7_226 + +LBB7_25: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB7_157 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB7_226 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax JE LBB7_33 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_31 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_30: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc08348 // add rax, -1 + JNE LBB7_30 LBB7_31: - WORD $0x3b4c; BYTE $0x2e // cmp r13, qword [rsi] - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0xd219 // sbb edx, edx - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x19 // movzx r8d, byte [r9 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x193c8841 // mov byte [r9 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_31 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 LBB7_33: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 JL LBB7_37 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax LBB7_35: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 QUAD $0x000000d02494970f // seta byte [rsp + 208] LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0xd2970f41 // seta r10b - LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd7970f40 // seta dil + LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0xd6970f41 // seta r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 QUAD $0x000000b02494970f // seta byte [rsp + 176] LONG $0x206e394c // cmp qword [rsi + 32], r13 - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x970f; BYTE $0xd0 // seta al LONG $0x386e394c // cmp qword [rsi + 56], r13 - LONG $0xd6970f41 // seta r14b + WORD $0x970f; BYTE $0xd3 // seta bl LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x000000802494970f // seta byte [rsp + 128] + QUAD $0x000000c02494970f // seta byte [rsp + 192] LONG $0x486e394c // cmp qword [rsi + 72], r13 - WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x506e394c // cmp qword [rsi + 80], r13 LONG $0xd1970f41 // seta r9b LONG $0x586e394c // cmp qword [rsi + 88], r13 - LONG $0xd3970f41 // seta r11b + LONG $0xd2970f41 // seta r10b LONG $0x606e394c // cmp qword [rsi + 96], r13 - WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0xd3970f41 // seta r11b LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4970f41 // seta r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 - QUAD $0x000000a02494970f // seta byte [rsp + 160] + QUAD $0x000000902494970f // seta byte [rsp + 144] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x970f; BYTE $0xd1 // seta cl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - QUAD $0x000000902494970f // seta byte [rsp + 144] + QUAD $0x000000a02494970f // seta byte [rsp + 160] LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 @@ -34862,7 +35755,7 @@ LBB7_35: LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7970f41 // seta r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 @@ -34870,76 +35763,76 @@ LBB7_35: LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 LONG $0xd0970f41 // seta r8b - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x000000d024bc0240 // add dil, byte [rsp + 208] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - WORD $0xd200 // add dl, dl - LONG $0x80249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0xc900 // add cl, cl + LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x24148b4c // mov r10, qword [rsp] + WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0841; BYTE $0xdc // or r12b, bl - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0x0841; BYTE $0xd6 // or r14b, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xd200 // add dl, dl - LONG $0x48245402 // add dl, byte [rsp + 72] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x8845; BYTE $0x32 // mov byte [r10], r14b + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x241c8841 // mov byte [r12], bl LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014a8841 // mov byte [r10 + 1], cl - WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] + LONG $0x18244c02 // add cl, byte [rsp + 24] WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 @@ -34949,7 +35842,7 @@ LBB7_35: WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx @@ -34961,578 +35854,125 @@ LBB7_35: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8845 // mov byte [r10 + 2], r15b - LONG $0x03428845 // mov byte [r10 + 3], r8b + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c28349 // add r10, 4 - LONG $0x2414894c // mov qword [rsp], r10 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 JNE LBB7_35 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] LBB7_37: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB7_155 + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_226 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_175 WORD $0x3145; BYTE $0xdb // xor r11d, r11d JMP LBB7_40 -LBB7_56: - WORD $0x8a44; BYTE $0x12 // mov r10b, byte [rdx] - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_60 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24348b4c // mov r14, qword [rsp] - -LBB7_58: - WORD $0x3a44; BYTE $0x16 // cmp r10b, byte [rsi] - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0xd219 // sbb edx, edx - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax +LBB7_112: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_116 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_115: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + WORD $0x2044; BYTE $0xdb // and bl, r11b WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_58 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB7_60: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_61 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x24548844; BYTE $0x08 // mov byte [rsp + 8], r10b - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x0000010824bc894c // mov qword [rsp + 264], r15 - JB LBB7_63 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB7_66 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB7_66 - -LBB7_63: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax - -LBB7_69: - QUAD $0x000000e824bc2b4c // sub r15, qword [rsp + 232] - QUAD $0x000000c024bc894c // mov qword [rsp + 192], r15 - -LBB7_70: - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - LONG $0x24143845 // cmp byte [r12], r10b - QUAD $0x000000d02494970f // seta byte [rsp + 208] - LONG $0x24543845; BYTE $0x01 // cmp byte [r12 + 1], r10b - LONG $0xd6970f41 // seta r14b - LONG $0x24543845; BYTE $0x02 // cmp byte [r12 + 2], r10b - LONG $0xd3970f41 // seta r11b - LONG $0x24543845; BYTE $0x03 // cmp byte [r12 + 3], r10b - LONG $0xd7970f41 // seta r15b - LONG $0x24543845; BYTE $0x04 // cmp byte [r12 + 4], r10b - QUAD $0x000000b02494970f // seta byte [rsp + 176] - LONG $0x24543845; BYTE $0x05 // cmp byte [r12 + 5], r10b - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x24543845; BYTE $0x06 // cmp byte [r12 + 6], r10b - WORD $0x970f; BYTE $0xd0 // seta al - LONG $0x24543845; BYTE $0x07 // cmp byte [r12 + 7], r10b - LONG $0xd0970f41 // seta r8b - LONG $0x24543845; BYTE $0x08 // cmp byte [r12 + 8], r10b - QUAD $0x000000802494970f // seta byte [rsp + 128] - LONG $0x24543845; BYTE $0x09 // cmp byte [r12 + 9], r10b - LONG $0xd6970f40 // seta sil - LONG $0x24543845; BYTE $0x0a // cmp byte [r12 + 10], r10b - LONG $0xd7970f40 // seta dil - LONG $0x24543845; BYTE $0x0b // cmp byte [r12 + 11], r10b - LONG $0xd1970f41 // seta r9b - LONG $0x24543845; BYTE $0x0c // cmp byte [r12 + 12], r10b - LONG $0xd2970f41 // seta r10b - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - LONG $0x24543841; BYTE $0x0d // cmp byte [r12 + 13], dl - LONG $0xd4970f41 // seta r12b - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x0e // cmp byte [rcx + 14], dl - QUAD $0x000000a02494970f // seta byte [rsp + 160] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x0f // cmp byte [rcx + 15], dl - WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x10 // cmp byte [rcx + 16], dl - QUAD $0x000000902494970f // seta byte [rsp + 144] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x11 // cmp byte [rcx + 17], dl - LONG $0xd5970f41 // seta r13b - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x12 // cmp byte [rcx + 18], dl - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x13 // cmp byte [rcx + 19], dl - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x14 // cmp byte [rcx + 20], dl - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x15 // cmp byte [rcx + 21], dl - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x16 // cmp byte [rcx + 22], dl - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x17 // cmp byte [rcx + 23], dl - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x18 // cmp byte [rcx + 24], dl - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x19 // cmp byte [rcx + 25], dl - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x1a // cmp byte [rcx + 26], dl - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x1b // cmp byte [rcx + 27], dl - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x1c // cmp byte [rcx + 28], dl - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x1d // cmp byte [rcx + 29], dl - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x1e // cmp byte [rcx + 30], dl - LONG $0x2414970f // seta byte [rsp] - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0x5138; BYTE $0x1f // cmp byte [rcx + 31], dl - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - QUAD $0x000000d024b40244 // add r14b, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xf3 // or r11b, r14b - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xf7 // or dil, sil - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0xc689 // mov esi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x54b60f44; WORD $0x0824 // movzx r10d, byte [rsp + 8] - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0x0841; BYTE $0xc0 // or r8b, al - WORD $0x0844; BYTE $0xe3 // or bl, r12b - WORD $0x0045; BYTE $0xed // add r13b, r13b - QUAD $0x0000009024ac0244 // add r13b, byte [rsp + 144] - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8941; BYTE $0xc1 // mov r9d, eax - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - WORD $0x8844; BYTE $0x06 // mov byte [rsi], r8b - LONG $0x247cb60f; BYTE $0x50 // movzx edi, byte [rsp + 80] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x5e88; BYTE $0x01 // mov byte [rsi + 1], bl - WORD $0x0844; BYTE $0xc8 // or al, r9b - LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] - WORD $0xdb00 // add bl, bl - LONG $0x40245c02 // add bl, byte [rsp + 64] - WORD $0xdf89 // mov edi, ebx - LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0xdf89 // mov edi, ebx - LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0xdf89 // mov edi, ebx - LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0xdf89 // mov edi, ebx - LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x243cb60f // movzx edi, byte [rsp] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xda08 // or dl, bl - WORD $0x4688; BYTE $0x02 // mov byte [rsi + 2], al - WORD $0x5688; BYTE $0x03 // mov byte [rsi + 3], dl - LONG $0x20618d4c // lea r12, [rcx + 32] - LONG $0x04c68348 // add rsi, 4 - LONG $0x24748948; BYTE $0x78 // mov qword [rsp + 120], rsi - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB7_70 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - JMP LBB7_72 - -LBB7_139: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_143 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] - -LBB7_141: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x19 // movzx r8d, byte [r9 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x193c8841 // mov byte [r9 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_141 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 - -LBB7_143: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_147 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - -LBB7_145: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000d024949f0f // setg byte [rsp + 208] - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd29f0f41 // setg r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d - LONG $0xd79f0f40 // setg dil - LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000000b024949f0f // setg byte [rsp + 176] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x146e3944 // cmp dword [rsi + 20], r13d - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x186e3944 // cmp dword [rsi + 24], r13d - WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - LONG $0xd69f0f41 // setg r14b - LONG $0x206e3944 // cmp dword [rsi + 32], r13d - QUAD $0x0000008024949f0f // setg byte [rsp + 128] - LONG $0x246e3944 // cmp dword [rsi + 36], r13d - WORD $0x9f0f; BYTE $0xd2 // setg dl - LONG $0x286e3944 // cmp dword [rsi + 40], r13d - LONG $0xd19f0f41 // setg r9b - LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd39f0f41 // setg r11b - LONG $0x306e3944 // cmp dword [rsi + 48], r13d - WORD $0x9f0f; BYTE $0xd3 // setg bl - LONG $0x346e3944 // cmp dword [rsi + 52], r13d - LONG $0xd49f0f41 // setg r12b - LONG $0x386e3944 // cmp dword [rsi + 56], r13d - QUAD $0x000000a024949f0f // setg byte [rsp + 160] - LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x9f0f; BYTE $0xd1 // setg cl - LONG $0x406e3944 // cmp dword [rsi + 64], r13d - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d - QUAD $0x0000009024949f0f // setg byte [rsp + 144] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0x506e3944 // cmp dword [rsi + 80], r13d - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d - LONG $0xd79f0f41 // setg r15b - LONG $0x606e3944 // cmp dword [rsi + 96], r13d - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0x646e3944 // cmp dword [rsi + 100], r13d - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0x706e3944 // cmp dword [rsi + 112], r13d - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x786e3944 // cmp dword [rsi + 120], r13d - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - LONG $0xd09f0f41 // setg r8b - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - WORD $0xd200 // add dl, dl - LONG $0x80249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x24148b4c // mov r10, qword [rsp] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0841; BYTE $0xdc // or r12b, bl - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0x0841; BYTE $0xd6 // or r14b, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xd200 // add dl, dl - LONG $0x48245402 // add dl, byte [rsp + 72] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x8845; BYTE $0x32 // mov byte [r10], r14b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014a8841 // mov byte [r10 + 1], cl - WORD $0x0841; BYTE $0xd7 // or r15b, dl - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xd0 // or r8b, dl - WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8845 // mov byte [r10 + 2], r15b - LONG $0x03428845 // mov byte [r10 + 3], r8b - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c28349 // add r10, 4 - LONG $0x2414894c // mov qword [rsp], r10 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB7_145 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] - -LBB7_147: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB7_153 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_150 - -LBB7_98: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_102 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24148b48 // mov rdx, qword [rsp] + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc08348 // add rax, -1 + JNE LBB7_115 -LBB7_100: - LONG $0x2e3b4466 // cmp r13w, word [rsi] - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x1945; BYTE $0xc9 // sbb r9d, r9d - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f44; BYTE $0x1a // movzx r8d, byte [rdx + rbx] - WORD $0x3045; BYTE $0xc1 // xor r9b, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xcf // and dil, r9b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1a3c8840 // mov byte [rdx + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_100 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 +LBB7_116: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 -LBB7_102: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_106 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 +LBB7_118: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_122 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax -LBB7_104: +LBB7_120: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0xd2970f41 // seta r10b - LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w LONG $0xd7970f40 // seta dil + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w + LONG $0xd6970f41 // seta r14b LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w QUAD $0x000000d02494970f // seta byte [rsp + 208] LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - QUAD $0x000000802494970f // seta byte [rsp + 128] + QUAD $0x000000b02494970f // seta byte [rsp + 176] LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w QUAD $0x000000902494970f // seta byte [rsp + 144] LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w WORD $0x970f; BYTE $0xd0 // seta al LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w - LONG $0xd6970f41 // seta r14b + WORD $0x970f; BYTE $0xd3 // seta bl LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w - WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd1970f41 // seta r9b LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w - LONG $0xd3970f41 // seta r11b + LONG $0xd2970f41 // seta r10b LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w - WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0xd3970f41 // seta r11b LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w LONG $0xd4970f41 // seta r12b LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - QUAD $0x000000b02494970f // seta byte [rsp + 176] + QUAD $0x000000c02494970f // seta byte [rsp + 192] LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x970f; BYTE $0xd1 // seta cl + WORD $0x970f; BYTE $0xd2 // seta dl LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w QUAD $0x000000a02494970f // seta byte [rsp + 160] LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w @@ -35544,96 +35984,96 @@ LBB7_104: LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w + LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w LONG $0xd0970f41 // seta r8b - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - LONG $0x24540244; BYTE $0x38 // add r10b, byte [rsp + 56] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x58 // add dil, byte [rsp + 88] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - WORD $0xd200 // add dl, dl - LONG $0x18245402 // add dl, byte [rsp + 24] + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0xc900 // add cl, cl + LONG $0x40244c02 // add cl, byte [rsp + 64] QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x24148b4c // mov r10, qword [rsp] + WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b + WORD $0x0841; BYTE $0xc9 // or r9b, cl + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0841; BYTE $0xdc // or r12b, bl - QUAD $0x000000b024bcb60f // movzx edi, byte [rsp + 176] + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x000000c024bcb60f // movzx edi, byte [rsp + 192] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0x0841; BYTE $0xd6 // or r14b, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xd200 // add dl, dl - LONG $0x10245402 // add dl, byte [rsp + 16] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x8845; BYTE $0x32 // mov byte [r10], r14b + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0x10244c02 // add cl, byte [rsp + 16] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x241c8841 // mov byte [r12], bl LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014a8841 // mov byte [r10 + 1], cl - WORD $0x0841; BYTE $0xd7 // or r15b, dl - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xc900 // add cl, cl LONG $0x08244c02 // add cl, byte [rsp + 8] WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd108 // or cl, dl LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] @@ -35641,98 +36081,103 @@ LBB7_104: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8845 // mov byte [r10 + 2], r15b - LONG $0x03428845 // mov byte [r10 + 3], r8b + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b LONG $0x40c68348 // add rsi, 64 - LONG $0x04c28349 // add r10, 4 - LONG $0x2414894c // mov qword [rsp], r10 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB7_104 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB7_120 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] -LBB7_106: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB7_112 +LBB7_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_226 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_128 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_109 + JMP LBB7_125 -LBB7_114: - WORD $0xb70f; BYTE $0x02 // movzx eax, word [rdx] - LONG $0xf0248489; WORD $0x0000; BYTE $0x00 // mov dword [rsp + 240], eax - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_118 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - QUAD $0x000000f024948b44 // mov r10d, dword [rsp + 240] - LONG $0x24348b4c // mov r14, qword [rsp] +LBB7_130: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_136 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_134 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB7_116: - LONG $0x16394466 // cmp word [rsi], r10w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl +LBB7_133: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_116 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB7_133 -LBB7_118: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_119 - LONG $0x08ff8349 // cmp r15, 8 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x0000011024bc894c // mov qword [rsp + 272], r15 - JB LBB7_121 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB7_134: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 + +LBB7_136: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_137 + LONG $0x08f98348 // cmp rcx, 8 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + JB LBB7_139 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB7_124 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB7_142 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB7_124 + JBE LBB7_142 -LBB7_121: +LBB7_139: WORD $0xc031 // xor eax, eax LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax - LONG $0x24348b4c // mov r14, qword [rsp] + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB7_127: - LONG $0x2474894c; BYTE $0x08 // mov qword [rsp + 8], r14 - LONG $0x247c2b4c; BYTE $0x28 // sub r15, qword [rsp + 40] - QUAD $0x000000c024bc894c // mov qword [rsp + 192], r15 - QUAD $0x000000f024ac8b44 // mov r13d, dword [rsp + 240] +LBB7_145: + LONG $0x244c2b48; BYTE $0x28 // sub rcx, qword [rsp + 40] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx -LBB7_128: +LBB7_146: WORD $0x8949; BYTE $0xf3 // mov r11, rsi LONG $0x2e394466 // cmp word [rsi], r13w QUAD $0x000000d024949f0f // setg byte [rsp + 208] @@ -35743,15 +36188,15 @@ LBB7_128: LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w QUAD $0x000000b024949f0f // setg byte [rsp + 176] LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w WORD $0x9f0f; BYTE $0xd0 // setg al LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w WORD $0x9f0f; BYTE $0xd3 // setg bl LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - QUAD $0x0000008024949f0f // setg byte [rsp + 128] + QUAD $0x000000c024949f0f // setg byte [rsp + 192] LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w WORD $0x9f0f; BYTE $0xd1 // setg cl LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w @@ -35763,19 +36208,19 @@ LBB7_128: LONG $0x6b394566; BYTE $0x1a // cmp word [r11 + 26], r13w LONG $0xd49f0f41 // setg r12b LONG $0x6b394566; BYTE $0x1c // cmp word [r11 + 28], r13w - QUAD $0x000000a024949f0f // setg byte [rsp + 160] + QUAD $0x0000009024949f0f // setg byte [rsp + 144] LONG $0x6b394566; BYTE $0x1e // cmp word [r11 + 30], r13w LONG $0xd79f0f40 // setg dil LONG $0x6b394566; BYTE $0x20 // cmp word [r11 + 32], r13w - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] LONG $0x6b394566; BYTE $0x22 // cmp word [r11 + 34], r13w - QUAD $0x0000009024949f0f // setg byte [rsp + 144] + QUAD $0x000000a024949f0f // setg byte [rsp + 160] LONG $0x6b394566; BYTE $0x24 // cmp word [r11 + 36], r13w - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] LONG $0x6b394566; BYTE $0x26 // cmp word [r11 + 38], r13w LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] LONG $0x6b394566; BYTE $0x28 // cmp word [r11 + 40], r13w - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] LONG $0x6b394566; BYTE $0x2a // cmp word [r11 + 42], r13w LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] LONG $0x6b394566; BYTE $0x2c // cmp word [r11 + 44], r13w @@ -35783,7 +36228,7 @@ LBB7_128: LONG $0x6b394566; BYTE $0x2e // cmp word [r11 + 46], r13w LONG $0xd79f0f41 // setg r15b LONG $0x6b394566; BYTE $0x30 // cmp word [r11 + 48], r13w - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] LONG $0x6b394566; BYTE $0x32 // cmp word [r11 + 50], r13w LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] LONG $0x6b394566; BYTE $0x34 // cmp word [r11 + 52], r13w @@ -35791,11 +36236,11 @@ LBB7_128: LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] LONG $0x6b394566; BYTE $0x38 // cmp word [r11 + 56], r13w - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] LONG $0x6b394566; BYTE $0x3a // cmp word [r11 + 58], r13w LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] LONG $0x6b394566; BYTE $0x3c // cmp word [r11 + 60], r13w - LONG $0x24149f0f // setg byte [rsp] + QUAD $0x0000008024949f0f // setg byte [rsp + 128] LONG $0x6b394566; BYTE $0x3e // cmp word [r11 + 62], r13w WORD $0x9f0f; BYTE $0xd2 // setg dl WORD $0x0045; BYTE $0xc0 // add r8b, r8b @@ -35806,36 +36251,36 @@ LBB7_128: LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xc6 // or r14b, r8b WORD $0xc900 // add cl, cl - LONG $0x80248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 128] + LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e6c040 // shl sil, 2 WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al WORD $0x8941; BYTE $0xc8 // mov r8d, ecx LONG $0x03e1c041 // shl r9b, 3 WORD $0x0841; BYTE $0xf1 // or r9b, sil - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xc1 // or cl, r8b LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xf7 // or dil, sil WORD $0xcb08 // or bl, cl WORD $0x0844; BYTE $0xe7 // or dil, r12b - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] WORD $0xc900 // add cl, cl - LONG $0x48244c02 // add cl, byte [rsp + 72] + LONG $0x58244c02 // add cl, byte [rsp + 88] WORD $0xce89 // mov esi, ecx - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx @@ -35843,7 +36288,7 @@ LBB7_128: WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0xce89 // mov esi, ecx @@ -35861,214 +36306,767 @@ LBB7_128: WORD $0x0841; BYTE $0xf7 // or r15b, sil LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x18244402 // add al, byte [rsp + 24] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd808 // or al, bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02798844 // mov byte [rcx + 2], r15b + WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl + LONG $0x40738d49 // lea rsi, [r11 + 64] + LONG $0x04c18348 // add rcx, 4 + LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB7_146 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + JMP LBB7_148 + +LBB7_177: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_183 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_181 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_180: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB7_180 + +LBB7_181: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 + +LBB7_183: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_187 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + +LBB7_185: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + QUAD $0x000000d024949f0f // setg byte [rsp + 208] + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0xd79f0f40 // setg dil + LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0xd69f0f41 // setg r14b + LONG $0x186e394c // cmp qword [rsi + 24], r13 + QUAD $0x000000b024949f0f // setg byte [rsp + 176] + LONG $0x206e394c // cmp qword [rsi + 32], r13 + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x286e394c // cmp qword [rsi + 40], r13 + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x306e394c // cmp qword [rsi + 48], r13 + WORD $0x9f0f; BYTE $0xd0 // setg al + LONG $0x386e394c // cmp qword [rsi + 56], r13 + WORD $0x9f0f; BYTE $0xd3 // setg bl + LONG $0x406e394c // cmp qword [rsi + 64], r13 + QUAD $0x000000c024949f0f // setg byte [rsp + 192] + LONG $0x486e394c // cmp qword [rsi + 72], r13 + WORD $0x9f0f; BYTE $0xd1 // setg cl + LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0xd19f0f41 // setg r9b + LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0xd29f0f41 // setg r10b + LONG $0x606e394c // cmp qword [rsi + 96], r13 + LONG $0xd39f0f41 // setg r11b + LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0xd49f0f41 // setg r12b + LONG $0x706e394c // cmp qword [rsi + 112], r13 + QUAD $0x0000009024949f0f // setg byte [rsp + 144] + LONG $0x786e394c // cmp qword [rsi + 120], r13 + WORD $0x9f0f; BYTE $0xd2 // setg dl + LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 + QUAD $0x000000a024949f0f // setg byte [rsp + 160] + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 + LONG $0xd79f0f41 // setg r15b + LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 + LONG $0xd09f0f41 // setg r8b + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x000000d024bc0240 // add dil, byte [rsp + 208] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0xc900 // add cl, cl + LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] + LONG $0x06e7c040 // shl dil, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x241c8841 // mov byte [r12], bl + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xdf // or r15b, bl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xc900 // add cl, cl + LONG $0x18244c02 // add cl, byte [rsp + 24] + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd108 // or cl, dl + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + WORD $0x0841; BYTE $0xc8 // or r8b, cl + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB7_185 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] + +LBB7_187: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_226 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_192 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB7_190 + +LBB7_194: + WORD $0x8b44; BYTE $0x32 // mov r14d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_200 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_198 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB7_197: + LONG $0x0e100ff3 // movss xmm1, dword [rsi] + LONG $0x04c68348 // add rsi, 4 + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 + WORD $0x970f; BYTE $0xd3 // seta bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB7_197 + +LBB7_198: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 + +LBB7_200: + LONG $0x1f7f8d49 // lea rdi, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xff490f49 // cmovns rdi, r15 + LONG $0x05ffc148 // sar rdi, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_201 + LONG $0x6e0f4566; BYTE $0xde // movd xmm11, r14d + LONG $0x04ff8348 // cmp rdi, 4 + JB LBB7_203 + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB7_206 + LONG $0xbc048d49 // lea rax, [r12 + 4*rdi] + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JBE LBB7_206 + +LBB7_203: + WORD $0xc031 // xor eax, eax + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x894d; BYTE $0xe2 // mov r10, r12 + +LBB7_209: + QUAD $0x000000802494894c // mov qword [rsp + 128], r10 + QUAD $0x0000010024b48944 // mov dword [rsp + 256], r14d + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x0000014024bc8948 // mov qword [rsp + 320], rdi + WORD $0x2948; BYTE $0xc7 // sub rdi, rax + QUAD $0x000000e024bc8948 // mov qword [rsp + 224], rdi + +LBB7_210: + LONG $0x01100ff3 // movss xmm0, dword [rcx] + LONG $0x49100ff3; BYTE $0x04 // movss xmm1, dword [rcx + 4] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0xd5970f41 // seta r13b + LONG $0x41100ff3; BYTE $0x08 // movss xmm0, dword [rcx + 8] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x0c // movss xmm0, dword [rcx + 12] + LONG $0xd4970f41 // seta r12b + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x41100ff3; BYTE $0x10 // movss xmm0, dword [rcx + 16] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x14 // movss xmm0, dword [rcx + 20] + WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x41100ff3; BYTE $0x18 // movss xmm0, dword [rcx + 24] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x1c // movss xmm0, dword [rcx + 28] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x41100ff3; BYTE $0x20 // movss xmm0, dword [rcx + 32] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x24 // movss xmm0, dword [rcx + 36] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x41100ff3; BYTE $0x28 // movss xmm0, dword [rcx + 40] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x2c // movss xmm0, dword [rcx + 44] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000000d02494970f // seta byte [rsp + 208] + LONG $0x41100ff3; BYTE $0x30 // movss xmm0, dword [rcx + 48] + LONG $0x59100ff3; BYTE $0x34 // movss xmm3, dword [rcx + 52] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x38 // movss xmm0, dword [rcx + 56] + LONG $0x69100ff3; BYTE $0x3c // movss xmm5, dword [rcx + 60] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x100f44f3; WORD $0x4041 // movss xmm8, dword [rcx + 64] + LONG $0x100f44f3; WORD $0x4449 // movss xmm9, dword [rcx + 68] + LONG $0xdb2e0f41 // ucomiss xmm3, xmm11 + LONG $0x100f44f3; WORD $0x4851 // movss xmm10, dword [rcx + 72] + LONG $0x100f44f3; WORD $0x4c61 // movss xmm12, dword [rcx + 76] + QUAD $0x000000a02494970f // seta byte [rsp + 160] + LONG $0x100f44f3; WORD $0x5069 // movss xmm13, dword [rcx + 80] + LONG $0x100f44f3; WORD $0x5471 // movss xmm14, dword [rcx + 84] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x58 // movss xmm0, dword [rcx + 88] + LONG $0x49100ff3; BYTE $0x5c // movss xmm1, dword [rcx + 92] + QUAD $0x000000c02494970f // seta byte [rsp + 192] + LONG $0x51100ff3; BYTE $0x60 // movss xmm2, dword [rcx + 96] + LONG $0x59100ff3; BYTE $0x64 // movss xmm3, dword [rcx + 100] + LONG $0xeb2e0f41 // ucomiss xmm5, xmm11 + LONG $0x69100ff3; BYTE $0x68 // movss xmm5, dword [rcx + 104] + LONG $0x61100ff3; BYTE $0x6c // movss xmm4, dword [rcx + 108] + LONG $0xd2970f41 // seta r10b + LONG $0x71100ff3; BYTE $0x70 // movss xmm6, dword [rcx + 112] + LONG $0x79100ff3; BYTE $0x74 // movss xmm7, dword [rcx + 116] + LONG $0xc32e0f45 // ucomiss xmm8, xmm11 + QUAD $0x000000b02494970f // seta byte [rsp + 176] + LONG $0xcb2e0f45 // ucomiss xmm9, xmm11 + WORD $0x970f; BYTE $0xd0 // seta al + LONG $0xd32e0f45 // ucomiss xmm10, xmm11 + LONG $0xd6970f40 // seta sil + LONG $0xe32e0f45 // ucomiss xmm12, xmm11 + LONG $0xd0970f41 // seta r8b + LONG $0xeb2e0f45 // ucomiss xmm13, xmm11 + LONG $0xd1970f41 // seta r9b + LONG $0xf32e0f45 // ucomiss xmm14, xmm11 + LONG $0xd3970f41 // seta r11b + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0xd7970f41 // seta r15b + LONG $0xd32e0f41 // ucomiss xmm2, xmm11 + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0xdb2e0f41 // ucomiss xmm3, xmm11 + LONG $0xd6970f41 // seta r14b + LONG $0xeb2e0f41 // ucomiss xmm5, xmm11 + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0xe32e0f41 // ucomiss xmm4, xmm11 + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0xf32e0f41 // ucomiss xmm6, xmm11 + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0xfb2e0f41 // ucomiss xmm7, xmm11 + LONG $0x41100ff3; BYTE $0x78 // movss xmm0, dword [rcx + 120] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0x41100ff3; BYTE $0x7c // movss xmm0, dword [rcx + 124] + LONG $0x80e98348 // sub rcx, -128 + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0xd7970f40 // seta dil + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x18 // add r13b, byte [rsp + 24] + LONG $0x02e4c041 // shl r12b, 2 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0x8945; BYTE $0xe5 // mov r13d, r12d + LONG $0x64b60f44; WORD $0x2824 // movzx r12d, byte [rsp + 40] + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xec // or r12b, r13b + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xe3 // or bl, r12b + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xda08 // or dl, bl + LONG $0x08245488 // mov byte [rsp + 8], dl + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x64b60f44; WORD $0x5024 // movzx r12d, byte [rsp + 80] + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x6cb60f44; WORD $0x3824 // movzx r13d, byte [rsp + 56] + WORD $0x0045; BYTE $0xed // add r13b, r13b + LONG $0x246c0244; BYTE $0x20 // add r13b, byte [rsp + 32] + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0x0844; BYTE $0xeb // or bl, r13b + WORD $0x8941; BYTE $0xdd // mov r13d, ebx + QUAD $0x000000d0249cb60f // movzx ebx, byte [rsp + 208] + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0x0844; BYTE $0xeb // or bl, r13b + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xda08 // or dl, bl + LONG $0x24640a44; BYTE $0x08 // or r12b, byte [rsp + 8] + QUAD $0x0000a024acb60f44; BYTE $0x00 // movzx r13d, byte [rsp + 160] + LONG $0x05e5c041 // shl r13b, 5 + WORD $0x0841; BYTE $0xd5 // or r13b, dl + QUAD $0x000000c02494b60f // movzx edx, byte [rsp + 192] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xd2 // or r10b, dl + WORD $0xc000 // add al, al + LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xc6 // or sil, al + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + LONG $0x04e1c041 // shl r9b, 4 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + LONG $0x05e3c041 // shl r11b, 5 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0x0845; BYTE $0xea // or r10b, r13b + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xc7 // or r15b, al + QUAD $0x0000008024b48b48 // mov rsi, qword [rsp + 128] + WORD $0x8844; BYTE $0x26 // mov byte [rsi], r12b + WORD $0x0845; BYTE $0xdf // or r15b, r11b + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + LONG $0x24740244; BYTE $0x70 // add r14b, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl + WORD $0xd008 // or al, dl WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax + LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x01568844 // mov byte [rsi + 1], r10b LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - LONG $0x241cb60f // movzx ebx, byte [rsp] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02798844 // mov byte [rcx + 2], r15b - WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl - LONG $0x40738d49 // lea rsi, [r11 + 64] - LONG $0x04c18348 // add rcx, 4 - LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB7_128 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] - JMP LBB7_130 + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x027e8844 // mov byte [rsi + 2], r15b + WORD $0x0840; BYTE $0xdf // or dil, bl + LONG $0x037e8840 // mov byte [rsi + 3], dil + LONG $0x04c68348 // add rsi, 4 + QUAD $0x0000008024b48948 // mov qword [rsp + 128], rsi + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB7_210 + QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0000010024b48b44 // mov r14d, dword [rsp + 256] + QUAD $0x0000014024bc8b48 // mov rdi, qword [rsp + 320] + JMP LBB7_212 + +LBB7_58: + WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + QUAD $0x00000118249c8844 // mov byte [rsp + 280], r11b + JE LBB7_59 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_61 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + +LBB7_68: + LONG $0x01768d4c // lea r14, [rsi + 1] + WORD $0x3a44; BYTE $0x1e // cmp r11b, byte [rsi] + WORD $0xf619 // sbb esi, esi + LONG $0x075a8d48 // lea rbx, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xda490f48 // cmovns rbx, rdx + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xce // xor sil, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xf7 // and dil, sil + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x1c3c8841 // mov byte [r12 + rbx], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + LONG $0xffc08348 // add rax, -1 + JNE LBB7_68 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB7_63 + JMP LBB7_226 LBB7_157: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_161 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x240c8b4c // mov r9, qword [rsp] - -LBB7_159: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x19 // movzx r8d, byte [r9 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x193c8841 // mov byte [r9 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_159 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB7_163 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB7_161 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_160: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077a8d48 // lea rdi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xfa490f48 // cmovns rdi, rdx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB7_160 LBB7_161: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_165 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000f02494894c // mov qword [rsp + 240], r10 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + LONG $0x01c48349 // add r12, 1 LBB7_163: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_167 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + +LBB7_165: + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d QUAD $0x000000d024949f0f // setg byte [rsp + 208] - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0xd29f0f41 // setg r10b - LONG $0x106e394c // cmp qword [rsi + 16], r13 + LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0xd79f0f40 // setg dil - LONG $0x186e394c // cmp qword [rsi + 24], r13 + LONG $0x086e3944 // cmp dword [rsi + 8], r13d + LONG $0xd69f0f41 // setg r14b + LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d QUAD $0x000000b024949f0f // setg byte [rsp + 176] - LONG $0x206e394c // cmp qword [rsi + 32], r13 - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x286e394c // cmp qword [rsi + 40], r13 - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x306e394c // cmp qword [rsi + 48], r13 + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x146e3944 // cmp dword [rsi + 20], r13d + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x386e394c // cmp qword [rsi + 56], r13 - LONG $0xd69f0f41 // setg r14b - LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x0000008024949f0f // setg byte [rsp + 128] - LONG $0x486e394c // cmp qword [rsi + 72], r13 - WORD $0x9f0f; BYTE $0xd2 // setg dl - LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + WORD $0x9f0f; BYTE $0xd3 // setg bl + LONG $0x206e3944 // cmp dword [rsi + 32], r13d + QUAD $0x000000c024949f0f // setg byte [rsp + 192] + LONG $0x246e3944 // cmp dword [rsi + 36], r13d + WORD $0x9f0f; BYTE $0xd1 // setg cl + LONG $0x286e3944 // cmp dword [rsi + 40], r13d LONG $0xd19f0f41 // setg r9b - LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0xd29f0f41 // setg r10b + LONG $0x306e3944 // cmp dword [rsi + 48], r13d LONG $0xd39f0f41 // setg r11b - LONG $0x606e394c // cmp qword [rsi + 96], r13 - WORD $0x9f0f; BYTE $0xd3 // setg bl - LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd49f0f41 // setg r12b - LONG $0x706e394c // cmp qword [rsi + 112], r13 - QUAD $0x000000a024949f0f // setg byte [rsp + 160] - LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x9f0f; BYTE $0xd1 // setg cl - LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 + LONG $0x386e3944 // cmp dword [rsi + 56], r13d QUAD $0x0000009024949f0f // setg byte [rsp + 144] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d + WORD $0x9f0f; BYTE $0xd2 // setg dl + LONG $0x406e3944 // cmp dword [rsi + 64], r13d + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x446e3944 // cmp dword [rsi + 68], r13d + QUAD $0x000000a024949f0f // setg byte [rsp + 160] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 + LONG $0x506e3944 // cmp dword [rsi + 80], r13d + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x546e3944 // cmp dword [rsi + 84], r13d LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + LONG $0x586e3944 // cmp dword [rsi + 88], r13d LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 + LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd79f0f41 // setg r15b - LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x606e3944 // cmp dword [rsi + 96], r13d + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x646e3944 // cmp dword [rsi + 100], r13d LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + LONG $0x706e3944 // cmp dword [rsi + 112], r13d + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x746e3944 // cmp dword [rsi + 116], r13d LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x786e3944 // cmp dword [rsi + 120], r13d LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 + LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d LONG $0xd09f0f41 // setg r8b - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000d024940244 // add r10b, byte [rsp + 208] + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x000000d024bc0240 // add dil, byte [rsp + 208] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xc6 // or r14b, al - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0844; BYTE $0xd7 // or dil, r10b - WORD $0xd200 // add dl, dl - LONG $0x80249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0xc900 // add cl, cl + LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x24148b4c // mov r10, qword [rsp] + WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xd1 // or r9b, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0xc208 // or dl, al - WORD $0xd789 // mov edi, edx - LONG $0x03e3c041 // shl r11b, 3 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xdb // or bl, r11b + WORD $0x0841; BYTE $0xc9 // or r9b, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0841; BYTE $0xdc // or r12b, bl - QUAD $0x000000a024bcb60f // movzx edi, byte [rsp + 160] + WORD $0x0845; BYTE $0xdc // or r12b, r11b + QUAD $0x0000009024bcb60f // movzx edi, byte [rsp + 144] LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0x0841; BYTE $0xd6 // or r14b, dl - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xd200 // add dl, dl - LONG $0x48245402 // add dl, byte [rsp + 72] - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0xd789 // mov edi, edx - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 WORD $0x0840; BYTE $0xfa // or dl, dil - WORD $0x8845; BYTE $0x32 // mov byte [r10], r14b + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xe2 // or dl, r12b + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf9 // or cl, dil + WORD $0xcf89 // mov edi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x241c8841 // mov byte [r12], bl LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014a8841 // mov byte [r10 + 1], cl - WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xcf // or r15b, cl LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] WORD $0xc900 // add cl, cl - LONG $0x20244c02 // add cl, byte [rsp + 32] + LONG $0x18244c02 // add cl, byte [rsp + 24] WORD $0xca89 // mov edx, ecx LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 @@ -36078,7 +37076,7 @@ LBB7_163: WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx @@ -36090,358 +37088,532 @@ LBB7_163: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x027a8845 // mov byte [r10 + 2], r15b - LONG $0x03428845 // mov byte [r10 + 3], r8b - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c28349 // add r10, 4 - LONG $0x2414894c // mov qword [rsp], r10 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB7_163 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000f024948b4c // mov r10, qword [rsp + 240] + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x24448845; BYTE $0x03 // mov byte [r12 + 3], r8b + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB7_165 + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x0000010024848b48 // mov rax, qword [rsp + 256] -LBB7_165: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB7_170 +LBB7_167: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB7_226 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB7_173 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_168 + JMP LBB7_170 -LBB7_172: - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x100f44f3; BYTE $0x1a // movss xmm11, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB7_176 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - LONG $0x24348b4c // mov r14, qword [rsp] +LBB7_5: + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + JMP LBB7_89 -LBB7_174: - LONG $0x06100ff3 // movss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB7_174 - LONG $0x24048348; BYTE $0x01 // add qword [rsp], 1 +LBB7_137: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB7_176: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB7_177 - LONG $0x04fa8349 // cmp r10, 4 - JB LBB7_179 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24043948 // cmp qword [rsp], rax - JAE LBB7_182 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB7_182 +LBB7_148: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB7_226 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB7_153 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB7_151 + +LBB7_201: + WORD $0x894d; BYTE $0xe2 // mov r10, r12 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_212: + LONG $0x05e7c148 // shl rdi, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xf8 // sub r8, rdi + JLE LBB7_226 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x01cf8348 // or rdi, 1 + WORD $0x3949; BYTE $0xff // cmp r15, rdi + JNE LBB7_217 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB7_215 + +LBB7_59: + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + JMP LBB7_64 + +LBB7_86: + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + +LBB7_88: + LONG $0x01c48349 // add r12, 1 + +LBB7_89: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_90 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x246c8844; BYTE $0x08 // mov byte [rsp + 8], r13b + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x00000118248c8948 // mov qword [rsp + 280], rcx + JB LBB7_94 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB7_97 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB7_97 + +LBB7_94: + WORD $0xc031 // xor eax, eax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + QUAD $0x0000012024a4894c // mov qword [rsp + 288], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + +LBB7_100: + QUAD $0x000000f8248c2b48 // sub rcx, qword [rsp + 248] + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + QUAD $0x0000012024bc8b48 // mov rdi, qword [rsp + 288] + +LBB7_101: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + QUAD $0x000000e024949f0f // setg byte [rsp + 224] + LONG $0x016e3844 // cmp byte [rsi + 1], r13b + LONG $0xd69f0f40 // setg sil + LONG $0x02693844 // cmp byte [rcx + 2], r13b + LONG $0xd79f0f41 // setg r15b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al + QUAD $0x000000b024949f0f // setg byte [rsp + 176] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al + LONG $0xd59f0f41 // setg r13b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al + LONG $0xd19f0f41 // setg r9b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + QUAD $0x000000c024949f0f // setg byte [rsp + 192] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al + WORD $0x9f0f; BYTE $0xd2 // setg dl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0xd09f0f41 // setg r8b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0xd29f0f41 // setg r10b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd69f0f41 // setg r14b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + QUAD $0x000000d024949f0f // setg byte [rsp + 208] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x0000009024949f0f // setg byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + LONG $0xd49f0f41 // setg r12b + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl + QUAD $0x000000a024949f0f // setg byte [rsp + 160] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd39f0f41 // setg r11b + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + QUAD $0x0000008024949f0f // setg byte [rsp + 128] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x000000e024b40240 // add sil, byte [rsp + 224] + LONG $0x06e5c041 // shl r13b, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0845; BYTE $0xe9 // or r9b, r13b + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + WORD $0xd200 // add dl, dl + LONG $0xc0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 192] + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf8 // or al, r15b + LONG $0x6cb60f44; WORD $0x0824 // movzx r13d, byte [rsp + 8] + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xd6 // or r14b, r10b + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xf4 // or r12b, sil + WORD $0x0841; BYTE $0xd1 // or r9b, dl + WORD $0x0841; BYTE $0xc4 // or r12b, al + LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + WORD $0xd200 // add dl, dl + LONG $0xa0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 160] + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0x8844; BYTE $0x0f // mov byte [rdi], r9b + LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xf3 // or r11b, sil + LONG $0x01678844 // mov byte [rdi + 1], r12b + WORD $0x0841; BYTE $0xd3 // or r11b, dl + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xc000 // add al, al + LONG $0x38244402 // add al, byte [rsp + 56] + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x025f8844 // mov byte [rdi + 2], r11b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000010024848348; BYTE $0xff // add qword [rsp + 256], -1 + JNE LBB7_101 + QUAD $0x0000012024bc8948 // mov qword [rsp + 288], rdi + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + QUAD $0x00000118248c8b48 // mov rcx, qword [rsp + 280] + JMP LBB7_103 + +LBB7_90: + QUAD $0x0000012024a4894c // mov qword [rsp + 288], r12 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + +LBB7_103: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB7_226 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB7_106 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB7_109 + +LBB7_61: + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB7_226 + +LBB7_63: + LONG $0x01c48349 // add r12, 1 + +LBB7_64: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB7_77 + LONG $0x10f98348 // cmp rcx, 16 + QUAD $0x0000008824bc894c // mov qword [rsp + 136], r15 + QUAD $0x00000138248c8948 // mov qword [rsp + 312], rcx + JB LBB7_66 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xf0 // add rax, r14 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB7_71 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB7_71 -LBB7_179: +LBB7_66: WORD $0xc031 // xor eax, eax - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x243c8b4c // mov r15, qword [rsp] + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax -LBB7_185: - LONG $0x243c894c // mov qword [rsp], r15 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - WORD $0x2949; BYTE $0xc2 // sub r10, rax - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - -LBB7_186: - LONG $0x02100ff3 // movss xmm0, dword [rdx] - LONG $0x4a100ff3; BYTE $0x04 // movss xmm1, dword [rdx + 4] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x42100ff3; BYTE $0x08 // movss xmm0, dword [rdx + 8] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x0c // movss xmm0, dword [rdx + 12] - LONG $0xd5970f41 // seta r13b - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd4970f41 // seta r12b - LONG $0x42100ff3; BYTE $0x10 // movss xmm0, dword [rdx + 16] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x14 // movss xmm0, dword [rdx + 20] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x42100ff3; BYTE $0x18 // movss xmm0, dword [rdx + 24] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x1c // movss xmm0, dword [rdx + 28] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0x42100ff3; BYTE $0x20 // movss xmm0, dword [rdx + 32] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x24 // movss xmm0, dword [rdx + 36] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - WORD $0x970f; BYTE $0xd0 // seta al - LONG $0x42100ff3; BYTE $0x28 // movss xmm0, dword [rdx + 40] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x2c // movss xmm0, dword [rdx + 44] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] - LONG $0x42100ff3; BYTE $0x30 // movss xmm0, dword [rdx + 48] - LONG $0x52100ff3; BYTE $0x34 // movss xmm2, dword [rdx + 52] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x62100ff3; BYTE $0x38 // movss xmm4, dword [rdx + 56] - LONG $0x6a100ff3; BYTE $0x3c // movss xmm5, dword [rdx + 60] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] - LONG $0x100f44f3; WORD $0x4042 // movss xmm8, dword [rdx + 64] - LONG $0x100f44f3; WORD $0x444a // movss xmm9, dword [rdx + 68] - LONG $0xd32e0f41 // ucomiss xmm2, xmm11 - LONG $0x100f44f3; WORD $0x4852 // movss xmm10, dword [rdx + 72] - LONG $0x100f44f3; WORD $0x4c62 // movss xmm12, dword [rdx + 76] - QUAD $0x000000902494970f // seta byte [rsp + 144] - LONG $0x100f44f3; WORD $0x506a // movss xmm13, dword [rdx + 80] - LONG $0x100f44f3; WORD $0x5472 // movss xmm14, dword [rdx + 84] - LONG $0xe32e0f41 // ucomiss xmm4, xmm11 - LONG $0x62100ff3; BYTE $0x58 // movss xmm4, dword [rdx + 88] - LONG $0x42100ff3; BYTE $0x5c // movss xmm0, dword [rdx + 92] - QUAD $0x000000802494970f // seta byte [rsp + 128] - LONG $0x4a100ff3; BYTE $0x60 // movss xmm1, dword [rdx + 96] - LONG $0x52100ff3; BYTE $0x64 // movss xmm2, dword [rdx + 100] - LONG $0xeb2e0f41 // ucomiss xmm5, xmm11 - LONG $0x6a100ff3; BYTE $0x68 // movss xmm5, dword [rdx + 104] - LONG $0x5a100ff3; BYTE $0x6c // movss xmm3, dword [rdx + 108] - LONG $0xd3970f41 // seta r11b - LONG $0x72100ff3; BYTE $0x70 // movss xmm6, dword [rdx + 112] - LONG $0x7a100ff3; BYTE $0x74 // movss xmm7, dword [rdx + 116] - LONG $0xc32e0f45 // ucomiss xmm8, xmm11 - QUAD $0x000000b02494970f // seta byte [rsp + 176] - LONG $0xcb2e0f45 // ucomiss xmm9, xmm11 - WORD $0x970f; BYTE $0xd1 // seta cl - LONG $0xd32e0f45 // ucomiss xmm10, xmm11 +LBB7_74: + LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 + QUAD $0x000000f8248c2b48 // sub rcx, qword [rsp + 248] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + QUAD $0x0000011824a48a44 // mov r12b, byte [rsp + 280] + +LBB7_75: + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + WORD $0x3845; BYTE $0x26 // cmp byte [r14], r12b + QUAD $0x000000d02494970f // seta byte [rsp + 208] + LONG $0x01663845 // cmp byte [r14 + 1], r12b LONG $0xd6970f40 // seta sil - LONG $0xe32e0f45 // ucomiss xmm12, xmm11 - LONG $0xd0970f41 // seta r8b - LONG $0xeb2e0f45 // ucomiss xmm13, xmm11 - LONG $0xd2970f41 // seta r10b - LONG $0xf32e0f45 // ucomiss xmm14, xmm11 + LONG $0x02663845 // cmp byte [r14 + 2], r12b + LONG $0xd3970f41 // seta r11b + LONG $0x03663845 // cmp byte [r14 + 3], r12b LONG $0xd6970f41 // seta r14b - LONG $0xe32e0f41 // ucomiss xmm4, xmm11 + LONG $0x04613844 // cmp byte [rcx + 4], r12b QUAD $0x000000a02494970f // seta byte [rsp + 160] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd1970f41 // seta r9b - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x05613844 // cmp byte [rcx + 5], r12b LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] - LONG $0xd32e0f41 // ucomiss xmm2, xmm11 - LONG $0xd7970f41 // seta r15b - LONG $0xeb2e0f41 // ucomiss xmm5, xmm11 + LONG $0x06613844 // cmp byte [rcx + 6], r12b + WORD $0x970f; BYTE $0xd0 // seta al + LONG $0x07613844 // cmp byte [rcx + 7], r12b + LONG $0xd0970f41 // seta r8b + LONG $0x08613844 // cmp byte [rcx + 8], r12b + QUAD $0x000000c02494970f // seta byte [rsp + 192] + LONG $0x09613844 // cmp byte [rcx + 9], r12b + WORD $0x970f; BYTE $0xd2 // seta dl + LONG $0x0a613844 // cmp byte [rcx + 10], r12b + LONG $0xd7970f40 // seta dil + LONG $0x0b613844 // cmp byte [rcx + 11], r12b + LONG $0xd1970f41 // seta r9b + LONG $0x0c613844 // cmp byte [rcx + 12], r12b + LONG $0xd2970f41 // seta r10b + LONG $0x0d613844 // cmp byte [rcx + 13], r12b + LONG $0xd5970f41 // seta r13b + LONG $0x0e613844 // cmp byte [rcx + 14], r12b + QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0x0f613844 // cmp byte [rcx + 15], r12b + WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0x10613844 // cmp byte [rcx + 16], r12b + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x11613844 // cmp byte [rcx + 17], r12b + QUAD $0x000000b02494970f // seta byte [rsp + 176] + LONG $0x12613844 // cmp byte [rcx + 18], r12b LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0xdb2e0f41 // ucomiss xmm3, xmm11 + LONG $0x13613844 // cmp byte [rcx + 19], r12b + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x14613844 // cmp byte [rcx + 20], r12b LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0xf32e0f41 // ucomiss xmm6, xmm11 + LONG $0x15613844 // cmp byte [rcx + 21], r12b + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x16613844 // cmp byte [rcx + 22], r12b + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x17613844 // cmp byte [rcx + 23], r12b LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0xfb2e0f41 // ucomiss xmm7, xmm11 - LONG $0x42100ff3; BYTE $0x78 // movss xmm0, dword [rdx + 120] + LONG $0x18613844 // cmp byte [rcx + 24], r12b LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x19613844 // cmp byte [rcx + 25], r12b + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x1a613844 // cmp byte [rcx + 26], r12b + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x1b613844 // cmp byte [rcx + 27], r12b + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x1c613844 // cmp byte [rcx + 28], r12b + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0x1d613844 // cmp byte [rcx + 29], r12b + QUAD $0x000000802494970f // seta byte [rsp + 128] + LONG $0x1e613844 // cmp byte [rcx + 30], r12b LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0x42100ff3; BYTE $0x7c // movss xmm0, dword [rdx + 124] - LONG $0x80ea8348 // sub rdx, -128 - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd7970f40 // seta dil - WORD $0xdb00 // add bl, bl - LONG $0x18245c02 // add bl, byte [rsp + 24] - LONG $0x02e5c041 // shl r13b, 2 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xec // or r12b, r13b - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - WORD $0x8941; BYTE $0xdc // mov r12d, ebx - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0844; BYTE $0xe3 // or bl, r12b - LONG $0x64b60f44; WORD $0x5824 // movzx r12d, byte [rsp + 88] - LONG $0x06e4c041 // shl r12b, 6 - LONG $0x6cb60f44; WORD $0x4024 // movzx r13d, byte [rsp + 64] - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xc000 // add al, al - LONG $0x10244402 // add al, byte [rsp + 16] - LONG $0x64b60f44; WORD $0x2824 // movzx r12d, byte [rsp + 40] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0841; BYTE $0xc4 // or r12b, al - WORD $0x8944; BYTE $0xe0 // mov eax, r12d - LONG $0x64b60f44; WORD $0x2024 // movzx r12d, byte [rsp + 32] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0841; BYTE $0xc4 // or r12b, al - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x0841; BYTE $0xdd // or r13b, bl - QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0xc308 // or bl, al - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x1f613844 // cmp byte [rcx + 31], r12b + LONG $0xd7970f41 // seta r15b + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x000000d024b40240 // add sil, byte [rsp + 208] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0xc900 // add cl, cl - LONG $0xb0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 176] - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x03e0c041 // shl r8b, 3 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xc2 // or r10b, r8b - LONG $0x05e6c041 // shl r14b, 5 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0841; BYTE $0xdb // or r11b, bl + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0841; BYTE $0xf3 // or r11b, sil + WORD $0xd200 // add dl, dl + LONG $0xc0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 192] + LONG $0x03e6c041 // shl r14b, 3 + WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xd7 // or dil, dl QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x24348b48 // mov rsi, qword [rsp] - WORD $0x8844; BYTE $0x2e // mov byte [rsi], r13b - WORD $0x0845; BYTE $0xf1 // or r9b, r14b - WORD $0x0045; BYTE $0xff // add r15b, r15b - LONG $0x247c0244; BYTE $0x68 // add r15b, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0xc289 // mov edx, eax + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0841; BYTE $0xf9 // or r9b, dil + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x05e5c041 // shl r13b, 5 + WORD $0x0845; BYTE $0xd5 // or r13b, r10b + QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0x0841; BYTE $0xc0 // or r8b, al + WORD $0x0844; BYTE $0xeb // or bl, r13b + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xc000 // add al, al + LONG $0x78244402 // add al, byte [rsp + 120] + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - LONG $0x245cb60f; BYTE $0x30 // movzx ebx, byte [rsp + 48] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd008 // or al, dl + WORD $0xc689 // mov esi, eax + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + WORD $0x8844; BYTE $0x00 // mov byte [rax], r8b + LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0x0840; BYTE $0xfa // or dl, dil + WORD $0x5888; BYTE $0x01 // mov byte [rax + 1], bl + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xdb00 // add bl, bl + LONG $0x30245c02 // add bl, byte [rsp + 48] + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x18 // movzx ebx, byte [rsp + 24] + WORD $0xe3c0; BYTE $0x02 // shl bl, 2 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x20 // movzx ebx, byte [rsp + 32] + WORD $0xe3c0; BYTE $0x03 // shl bl, 3 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0xde89 // mov esi, ebx + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0xc308 // or bl, al - LONG $0x015e8844 // mov byte [rsi + 1], r11b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8844 // mov byte [rsi + 2], r9b - WORD $0x0840; BYTE $0xdf // or dil, bl - LONG $0x037e8840 // mov byte [rsi + 3], dil - LONG $0x04c68348 // add rsi, 4 - LONG $0x24348948 // mov qword [rsp], rsi - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB7_186 - LONG $0x243c8b4c // mov r15, qword [rsp] - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - JMP LBB7_188 - -LBB7_9: - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax - -LBB7_90: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB7_93 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB7_96 - -LBB7_61: - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - -LBB7_72: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xdf // add r15, r11 + WORD $0x0840; BYTE $0xf3 // or bl, sil + LONG $0x2474b60f; BYTE $0x08 // movzx esi, byte [rsp + 8] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + WORD $0x0841; BYTE $0xdf // or r15b, bl + WORD $0x5088; BYTE $0x02 // mov byte [rax + 2], dl + LONG $0x03788844 // mov byte [rax + 3], r15b + LONG $0x20718d4c // lea r14, [rcx + 32] + LONG $0x04c08348 // add rax, 4 + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 JNE LBB7_75 - WORD $0xc031 // xor eax, eax - JMP LBB7_78 - -LBB7_119: - LONG $0x24348b4c // mov r14, qword [rsp] - -LBB7_130: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xdf // add r15, r11 - JNE LBB7_135 - WORD $0x3145; BYTE $0xff // xor r15d, r15d - JMP LBB7_133 - -LBB7_177: - LONG $0x243c8b4c // mov r15, qword [rsp] - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x00000138248c8b48 // mov rcx, qword [rsp + 312] -LBB7_188: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB7_202 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB7_193 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB7_191 +LBB7_77: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB7_226 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB7_80 + WORD $0xc031 // xor eax, eax + JMP LBB7_83 -LBB7_155: +LBB7_175: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - LONG $0x24348b4c // mov r14, qword [rsp] -LBB7_156: +LBB7_176: WORD $0x3b4c; BYTE $0x2e // cmp r13, qword [rsi] WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] + LONG $0x14b60f45; BYTE $0x14 // movzx r10d, byte [r12 + rdx] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 @@ -36449,7 +37621,7 @@ LBB7_156: WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x16048841 // mov byte [r14 + rdx], al + LONG $0x14048841 // mov byte [r12 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x086e3b4c // cmp r13, qword [rsi + 8] LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -36460,29 +37632,28 @@ LBB7_156: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x161c8841 // mov byte [r14 + rdx], bl + LONG $0x141c8841 // mov byte [r12 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB7_156 + JNE LBB7_176 LBB7_40: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 + JE LBB7_226 WORD $0x3b4c; BYTE $0x2e // cmp r13, qword [rsi] - JMP LBB7_111 + JMP LBB7_127 -LBB7_153: +LBB7_173: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - LONG $0x24348b4c // mov r14, qword [rsp] -LBB7_154: +LBB7_174: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -36490,7 +37661,7 @@ LBB7_154: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -36502,25 +37673,25 @@ LBB7_154: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB7_154 + JNE LBB7_174 -LBB7_150: +LBB7_170: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 + JE LBB7_226 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - JMP LBB7_152 + JMP LBB7_172 -LBB7_93: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] +LBB7_106: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] -LBB7_94: +LBB7_107: WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e243846 // cmp byte [rsi + r9], r12b + LONG $0x0e2c3846 // cmp byte [rsi + r9], r13b WORD $0x9f0f; BYTE $0xd3 // setg bl WORD $0xdbf6 // neg bl WORD $0x894c; BYTE $0xcf // mov rdi, r9 @@ -36529,12 +37700,12 @@ LBB7_94: WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x06643844; BYTE $0x01 // cmp byte [rsi + rax + 1], r12b + LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x066c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r13b LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x9f0f; BYTE $0xd3 // setg bl WORD $0xdbf6 // neg bl @@ -36544,39 +37715,34 @@ LBB7_94: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al + LONG $0x3e048841 // mov byte [r14 + rdi], al WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB7_94 + JNE LBB7_107 WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB7_96: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 - WORD $0x3844; BYTE $0x26 // cmp byte [rsi], r12b - WORD $0x9f0f; BYTE $0xd0 // setg al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xca // mov rdx, r9 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e18041 // and r9b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xc9 // mov ecx, r9d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB7_202 +LBB7_109: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_226 + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + WORD $0x9f0f; BYTE $0xd0 // setg al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + QUAD $0x0000012024848b4c // mov r8, qword [rsp + 288] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + JMP LBB7_111 -LBB7_75: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0xc031 // xor eax, eax - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] +LBB7_80: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0xc031 // xor eax, eax + QUAD $0x0000011824948a44 // mov r10b, byte [rsp + 280] -LBB7_76: - LONG $0x04143a45 // cmp r10b, byte [r12 + rax] +LBB7_81: + LONG $0x06143a45 // cmp r10b, byte [r14 + rax] WORD $0xf619 // sbb esi, esi WORD $0x8948; BYTE $0xc7 // mov rdi, rax LONG $0x03efc148 // shr rdi, 3 @@ -36584,12 +37750,12 @@ LBB7_76: WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x1cb60f41; BYTE $0x3b // movzx ebx, byte [r11 + rdi] + LONG $0x1cb60f41; BYTE $0x3c // movzx ebx, byte [r12 + rdi] WORD $0x3040; BYTE $0xde // xor sil, bl WORD $0x2040; BYTE $0xf2 // and dl, sil WORD $0xda30 // xor dl, bl - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x04543a45; BYTE $0x01 // cmp r10b, byte [r12 + rax + 1] + LONG $0x3c148841 // mov byte [r12 + rdi], dl + LONG $0x06543a45; BYTE $0x01 // cmp r10b, byte [r14 + rax + 1] LONG $0x02408d48 // lea rax, [rax + 2] WORD $0xf619 // sbb esi, esi WORD $0x3040; BYTE $0xd6 // xor sil, dl @@ -36598,42 +37764,41 @@ LBB7_76: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xf3 // and bl, sil WORD $0xd330 // xor bl, dl - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl WORD $0x3949; BYTE $0xc1 // cmp r9, rax - JNE LBB7_76 - WORD $0x0149; BYTE $0xc4 // add r12, rax + JNE LBB7_81 + WORD $0x0149; BYTE $0xc6 // add r14, rax -LBB7_78: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 - LONG $0x24143a45 // cmp r10b, byte [r12] - WORD $0xd219 // sbb edx, edx - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - LONG $0x03eec148 // shr rsi, 3 - LONG $0x24448b4c; BYTE $0x78 // mov r8, qword [rsp + 120] - LONG $0x303c8a41 // mov dil, byte [r8 + rsi] - WORD $0x0724 // and al, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xc189 // mov ecx, eax - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xfa // xor dl, dil - WORD $0xd320 // and bl, dl - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x301c8841 // mov byte [r8 + rsi], bl - JMP LBB7_202 +LBB7_83: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_226 + LONG $0x18248c8a; WORD $0x0001; BYTE $0x00 // mov cl, byte [rsp + 280] + WORD $0x3a41; BYTE $0x0e // cmp cl, byte [r14] + WORD $0xd219 // sbb edx, edx + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + LONG $0x03eec148 // shr rsi, 3 + LONG $0x343c8a41 // mov dil, byte [r12 + rsi] + WORD $0x0724 // and al, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xc189 // mov ecx, eax + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xfa // xor dl, dil + WORD $0xd320 // and bl, dl + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x341c8841 // mov byte [r12 + rsi], bl + JMP LBB7_226 -LBB7_137: +LBB7_155: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - LONG $0x24348b4c // mov r14, qword [rsp] -LBB7_138: +LBB7_156: WORD $0x3b44; BYTE $0x2e // cmp r13d, dword [rsi] WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] + LONG $0x14b60f45; BYTE $0x14 // movzx r10d, byte [r12 + rdx] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 @@ -36641,7 +37806,7 @@ LBB7_138: WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x16048841 // mov byte [r14 + rdx], al + LONG $0x14048841 // mov byte [r12 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x046e3b44 // cmp r13d, dword [rsi + 4] LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -36652,23 +37817,22 @@ LBB7_138: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x161c8841 // mov byte [r14 + rdx], bl + LONG $0x141c8841 // mov byte [r12 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB7_138 + JNE LBB7_156 -LBB7_24: +LBB7_22: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 + JE LBB7_226 WORD $0x3b44; BYTE $0x2e // cmp r13d, dword [rsi] - JMP LBB7_111 + JMP LBB7_127 -LBB7_196: +LBB7_220: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xd2 // xor r10d, r10d - LONG $0x241c8b4c // mov r11, qword [rsp] -LBB7_197: +LBB7_221: LONG $0x0e100ff2 // movsd xmm1, qword [rsi] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 WORD $0x970f; BYTE $0xd0 // seta al @@ -36679,11 +37843,11 @@ LBB7_197: WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - LONG $0x14b60f41; BYTE $0x3b // movzx edx, byte [r11 + rdi] + LONG $0x14b60f41; BYTE $0x3c // movzx edx, byte [r12 + rdi] WORD $0xd030 // xor al, dl WORD $0xc320 // and bl, al WORD $0xd330 // xor bl, dl - LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c28349 // add r10, 2 LONG $0x4e100ff2; BYTE $0x08 // movsd xmm1, qword [rsi + 8] LONG $0x10c68348 // add rsi, 16 @@ -36696,38 +37860,36 @@ LBB7_197: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xd1 // cmp r9, r10 - JNE LBB7_197 + JNE LBB7_221 -LBB7_198: +LBB7_222: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 + JE LBB7_226 LONG $0x0e100ff2 // movsd xmm1, qword [rsi] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 WORD $0x970f; BYTE $0xd0 // seta al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xd2 // mov rdx, r10 LONG $0x03eac148 // shr rdx, 3 - LONG $0x243c8b48 // mov rdi, qword [rsp] - LONG $0x17348a40 // mov sil, byte [rdi + rdx] + LONG $0x14348a41 // mov sil, byte [r12 + rdx] LONG $0x07e28041 // and r10b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xd1 // mov ecx, r10d - JMP LBB7_200 + JMP LBB7_224 -LBB7_112: +LBB7_128: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - LONG $0x24348b4c // mov r14, qword [rsp] -LBB7_113: +LBB7_129: LONG $0x2e3b4466 // cmp r13w, word [rsi] WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] + LONG $0x14b60f45; BYTE $0x14 // movzx r10d, byte [r12 + rdx] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 @@ -36735,7 +37897,7 @@ LBB7_113: WORD $0x3044; BYTE $0xd7 // xor dil, r10b WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x16048841 // mov byte [r14 + rdx], al + LONG $0x14048841 // mov byte [r12 + rdx], al LONG $0x02c38349 // add r11, 2 LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] LONG $0x04768d48 // lea rsi, [rsi + 4] @@ -36746,42 +37908,40 @@ LBB7_113: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x161c8841 // mov byte [r14 + rdx], bl + LONG $0x141c8841 // mov byte [r12 + rdx], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB7_113 + JNE LBB7_129 -LBB7_109: +LBB7_125: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 + JE LBB7_226 LONG $0x2e3b4466 // cmp r13w, word [rsi] -LBB7_111: +LBB7_127: WORD $0xc019 // sbb eax, eax WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x243c8b48 // mov rdi, qword [rsp] - LONG $0x17348a40 // mov sil, byte [rdi + rdx] + LONG $0x14348a41 // mov sil, byte [r12 + rdx] LONG $0x07e38041 // and r11b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - JMP LBB7_201 + JMP LBB7_225 -LBB7_170: +LBB7_192: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - LONG $0x24348b4c // mov r14, qword [rsp] -LBB7_171: +LBB7_193: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -36789,7 +37949,7 @@ LBB7_171: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -36801,63 +37961,59 @@ LBB7_171: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB7_171 + JNE LBB7_193 -LBB7_168: +LBB7_190: LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 + JE LBB7_226 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 -LBB7_152: +LBB7_172: WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x243c8b48 // mov rdi, qword [rsp] - LONG $0x17348a40 // mov sil, byte [rdi + rdx] + LONG $0x14348a41 // mov sil, byte [r12 + rdx] LONG $0x07e38041 // and r11b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xd9 // mov ecx, r11d -LBB7_200: +LBB7_224: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al -LBB7_201: +LBB7_225: WORD $0x3040; BYTE $0xf3 // xor bl, sil - WORD $0x1c88; BYTE $0x17 // mov byte [rdi + rdx], bl - -LBB7_202: - MOVQ 336(SP), SP - RET + LONG $0x141c8841 // mov byte [r12 + rdx], bl + JMP LBB7_226 -LBB7_135: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xff // xor r15d, r15d - QUAD $0x000000f0249c8b44 // mov r11d, dword [rsp + 240] +LBB7_153: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] -LBB7_136: +LBB7_154: WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x1e394466 // cmp word [rsi], r11w + LONG $0x2e394466 // cmp word [rsi], r13w WORD $0x9f0f; BYTE $0xd2 // setg dl WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xff // mov rdi, r15 + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3e // movzx r10d, byte [r14 + rdi] - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d + LONG $0x14b60f45; BYTE $0x3b // movzx r10d, byte [r11 + rdi] + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl WORD $0x3044; BYTE $0xd2 // xor dl, r10b WORD $0xd320 // and bl, dl WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x02c78349 // add r15, 2 - LONG $0x5e394466; BYTE $0x02 // cmp word [rsi + 2], r11w + LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + LONG $0x02c68349 // add r14, 2 + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] WORD $0x9f0f; BYTE $0xd2 // setg dl WORD $0xdaf6 // neg dl @@ -36867,57 +38023,59 @@ LBB7_136: WORD $0xe0d2 // shl al, cl WORD $0xd020 // and al, dl WORD $0xd830 // xor al, bl - LONG $0x3e048841 // mov byte [r14 + rdi], al - WORD $0x394d; BYTE $0xf9 // cmp r9, r15 - JNE LBB7_136 + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB7_154 -LBB7_133: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 - LONG $0xf024848b; WORD $0x0000; BYTE $0x00 // mov eax, dword [rsp + 240] - WORD $0x3966; BYTE $0x06 // cmp word [rsi], ax - WORD $0x9f0f; BYTE $0xd0 // setg al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xfa // mov rdx, r15 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x163c8a41 // mov dil, byte [r14 + rdx] - LONG $0x07e78041 // and r15b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xf9 // mov ecx, r15d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x161c8841 // mov byte [r14 + rdx], bl - JMP LBB7_202 +LBB7_151: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_226 + LONG $0x2e394466 // cmp word [rsi], r13w + WORD $0x9f0f; BYTE $0xd0 // setg al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e68041 // and r14b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d -LBB7_193: +LBB7_111: + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + JMP LBB7_226 + +LBB7_217: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - WORD $0x894d; BYTE $0xfa // mov r10, r15 - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + WORD $0x894d; BYTE $0xd3 // mov r11, r10 + WORD $0x8948; BYTE $0xce // mov rsi, rcx -LBB7_194: - LONG $0x06100ff3 // movss xmm0, dword [rsi] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 +LBB7_218: + LONG $0x0e100ff3 // movss xmm1, dword [rsi] + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 WORD $0x970f; BYTE $0xd3 // seta bl WORD $0xdbf6 // neg bl - WORD $0x894c; BYTE $0xdf // mov rdi, r11 + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 LONG $0x03efc148 // shr rdi, 3 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x04b60f41; BYTE $0x3a // movzx eax, byte [r10 + rdi] + LONG $0x04b60f41; BYTE $0x3b // movzx eax, byte [r11 + rdi] WORD $0xc330 // xor bl, al WORD $0xda20 // and dl, bl WORD $0xc230 // xor dl, al - LONG $0x3a148841 // mov byte [r10 + rdi], dl - LONG $0x02c38349 // add r11, 2 - LONG $0x46100ff3; BYTE $0x04 // movss xmm0, dword [rsi + 4] + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x02c68349 // add r14, 2 + LONG $0x4e100ff3; BYTE $0x04 // movss xmm1, dword [rsi + 4] LONG $0x08c68348 // add rsi, 8 - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 WORD $0x970f; BYTE $0xd0 // seta al WORD $0xd8f6 // neg al WORD $0xd030 // xor al, dl @@ -36926,265 +38084,1204 @@ LBB7_194: WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0xd330 // xor bl, dl - LONG $0x3a1c8841 // mov byte [r10 + rdi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB7_194 - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB7_218 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB7_215: + LONG $0x01c0f641 // test r8b, 1 + JE LBB7_226 + LONG $0x09100ff3 // movss xmm1, dword [rcx] + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x123c8a41 // mov dil, byte [r10 + rdx] + LONG $0x07e68041 // and r14b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x121c8841 // mov byte [r10 + rdx], bl + +LBB7_226: + MOVQ 352(SP), SP + RET + +LBB7_142: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x244c8948; BYTE $0x28 // mov qword [rsp + 40], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + LONG $0x246c8944; BYTE $0x38 // mov dword [rsp + 56], r13d + LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d + LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 + LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 + WORD $0x3145; BYTE $0xff // xor r15d, r15d + QUAD $0x000080bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 128[rbp] /* [rip + .LCPI7_8] */ + LONG $0x6f0f4466; WORD $0x104d // movdqa xmm9, oword 16[rbp] /* [rip + .LCPI7_1] */ + LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI7_2] */ + LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI7_3] */ + LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI7_4] */ + LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI7_5] */ + LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI7_6] */ + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + +LBB7_143: + LONG $0x247c894c; BYTE $0x10 // mov qword [rsp + 16], r15 + LONG $0x06e7c149 // shl r15, 6 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x894d; BYTE $0xfc // mov r12, r15 + WORD $0x894d; BYTE $0xfd // mov r13, r15 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0x894c; BYTE $0xff // mov rdi, r15 + LONG $0x34b70f46; BYTE $0x3e // movzx r14d, word [rsi + r15] + LONG $0x44b70f42; WORD $0x023e // movzx eax, word [rsi + r15 + 2] + LONG $0x5cb70f46; WORD $0x043e // movzx r11d, word [rsi + r15 + 4] + LONG $0x54b70f42; WORD $0x063e // movzx edx, word [rsi + r15 + 6] + LONG $0x54b70f46; WORD $0x083e // movzx r10d, word [rsi + r15 + 8] + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + LONG $0x40c98349 // or r9, 64 + LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 + LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 + LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 + LONG $0x40c98148; WORD $0x0001; BYTE $0x00 // or rcx, 320 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 + LONG $0xc0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 448 + LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d + LONG $0xc40f4266; WORD $0x0e24; BYTE $0x01 // pinsrw xmm4, word [rsi + r9], 1 + LONG $0xc40f4266; WORD $0x0624; BYTE $0x02 // pinsrw xmm4, word [rsi + r8], 2 + LONG $0xc40f4266; WORD $0x2624; BYTE $0x03 // pinsrw xmm4, word [rsi + r12], 3 + LONG $0xc40f4266; WORD $0x2e24; BYTE $0x04 // pinsrw xmm4, word [rsi + r13], 4 + LONG $0x24c40f66; WORD $0x050e // pinsrw xmm4, word [rsi + rcx], 5 + LONG $0x24c40f66; WORD $0x061e // pinsrw xmm4, word [rsi + rbx], 6 + LONG $0x24c40f66; WORD $0x073e // pinsrw xmm4, word [rsi + rdi], 7 + LONG $0x74b70f46; WORD $0x0a3e // movzx r14d, word [rsi + r15 + 10] + LONG $0xf06e0f66 // movd xmm6, eax + QUAD $0x01020e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 2], 1 + QUAD $0x02020674c40f4266 // pinsrw xmm6, word [rsi + r8 + 2], 2 + QUAD $0x03022674c40f4266 // pinsrw xmm6, word [rsi + r12 + 2], 3 + LONG $0x44b70f42; WORD $0x0c3e // movzx eax, word [rsi + r15 + 12] + LONG $0x18244489 // mov dword [rsp + 24], eax + QUAD $0x04022e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 2], 4 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x5cb70f46; WORD $0x0e3e // movzx r11d, word [rsi + r15 + 14] + LONG $0x74c40f66; WORD $0x020e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 2], 5 + LONG $0xea6e0f66 // movd xmm5, edx + LONG $0x54b70f42; WORD $0x103e // movzx edx, word [rsi + r15 + 16] + LONG $0x74c40f66; WORD $0x021e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 2], 6 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x44b70f42; WORD $0x123e // movzx eax, word [rsi + r15 + 18] + LONG $0x20244489 // mov dword [rsp + 32], eax + LONG $0x74c40f66; WORD $0x023e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 2], 7 + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xce6f0f66 // movdqa xmm1, xmm6 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xcef80f66 // psubb xmm1, xmm6 + LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d + LONG $0x54b70f46; WORD $0x143e // movzx r10d, word [rsi + r15 + 20] + LONG $0xe0650f66 // pcmpgtw xmm4, xmm0 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + QUAD $0x01040e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 4], 1 + QUAD $0x02040654c40f4266 // pinsrw xmm2, word [rsi + r8 + 4], 2 + QUAD $0x03042654c40f4266 // pinsrw xmm2, word [rsi + r12 + 4], 3 + QUAD $0x04042e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 4], 4 + LONG $0x54c40f66; WORD $0x040e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 4], 5 + LONG $0x54c40f66; WORD $0x041e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 4], 6 + LONG $0x54c40f66; WORD $0x043e; BYTE $0x07 // pinsrw xmm2, word [rsi + rdi + 4], 7 + QUAD $0x01060e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 6], 1 + QUAD $0x0206066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 6], 2 + QUAD $0x0306266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 6], 3 + QUAD $0x04062e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 6], 4 + LONG $0x6cc40f66; WORD $0x060e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 6], 5 + LONG $0x6cc40f66; WORD $0x061e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 6], 6 + LONG $0x6cc40f66; WORD $0x063e; BYTE $0x07 // pinsrw xmm5, word [rsi + rdi + 6], 7 + QUAD $0x01080e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 8], 1 + QUAD $0x0208065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 8], 2 + QUAD $0x0308265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 8], 3 + QUAD $0x04082e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 8], 4 + LONG $0x5cc40f66; WORD $0x080e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 8], 5 + LONG $0x5cc40f66; WORD $0x081e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 8], 6 + LONG $0x5cc40f66; WORD $0x083e; BYTE $0x07 // pinsrw xmm3, word [rsi + rdi + 8], 7 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0x7c6e0f66; WORD $0x1824 // movd xmm7, dword [rsp + 24] + LONG $0x44b70f42; WORD $0x163e // movzx eax, word [rsi + r15 + 22] + LONG $0xd0650f66 // pcmpgtw xmm2, xmm0 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x02 // psllw xmm2, 2 + LONG $0xdb0f4166; BYTE $0xd1 // pand xmm2, xmm9 + LONG $0xd1eb0f66 // por xmm2, xmm1 + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x5cb70f46; WORD $0x183e // movzx r11d, word [rsi + r15 + 24] + LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 + LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 + LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 + LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x54b70f42; WORD $0x1a3e // movzx edx, word [rsi + r15 + 26] + QUAD $0x010a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 10], 1 + QUAD $0x020a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 10], 2 + QUAD $0x030a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 10], 3 + QUAD $0x040a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 10], 4 + LONG $0x74c40f66; WORD $0x0a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 10], 5 + LONG $0x74c40f66; WORD $0x0a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 10], 6 + LONG $0x74c40f66; WORD $0x0a3e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 10], 7 + QUAD $0x010c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 12], 1 + QUAD $0x020c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 12], 2 + QUAD $0x030c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 12], 3 + QUAD $0x040c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 12], 4 + LONG $0x7cc40f66; WORD $0x0c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 12], 5 + LONG $0x7cc40f66; WORD $0x0c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 12], 6 + LONG $0x7cc40f66; WORD $0x0c3e; BYTE $0x07 // pinsrw xmm7, word [rsi + rdi + 12], 7 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0x6e0f4466; WORD $0x2444; BYTE $0x20 // movd xmm8, dword [rsp + 32] + LONG $0x74b70f46; WORD $0x1c3e // movzx r14d, word [rsi + r15 + 28] + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0xf8650f66 // pcmpgtw xmm7, xmm0 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 + LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 + LONG $0xfeeb0f66 // por xmm7, xmm6 + LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d + LONG $0x54b70f46; WORD $0x1e3e // movzx r10d, word [rsi + r15 + 30] + QUAD $0x010e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 14], 1 + QUAD $0x020e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 14], 2 + QUAD $0x030e2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 14], 3 + QUAD $0x040e2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 14], 4 + LONG $0x64c40f66; WORD $0x0e0e; BYTE $0x05 // pinsrw xmm4, word [rsi + rcx + 14], 5 + LONG $0x64c40f66; WORD $0x0e1e; BYTE $0x06 // pinsrw xmm4, word [rsi + rbx + 14], 6 + LONG $0x64c40f66; WORD $0x0e3e; BYTE $0x07 // pinsrw xmm4, word [rsi + rdi + 14], 7 + QUAD $0x01120e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 18], 1 + QUAD $0x02120644c40f4666 // pinsrw xmm8, word [rsi + r8 + 18], 2 + QUAD $0x03122644c40f4666 // pinsrw xmm8, word [rsi + r12 + 18], 3 + QUAD $0x04122e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 18], 4 + QUAD $0x05120e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 18], 5 + QUAD $0x06121e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 18], 6 + QUAD $0x07123e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 18], 7 + LONG $0xe0650f66 // pcmpgtw xmm4, xmm0 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 + LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 + LONG $0xe7eb0f66 // por xmm4, xmm7 + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x44b70f42; WORD $0x203e // movzx eax, word [rsi + r15 + 32] + LONG $0xe3eb0f66 // por xmm4, xmm3 + LONG $0x650f4466; BYTE $0xc0 // pcmpgtw xmm8, xmm0 + LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 + LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf80f4166; BYTE $0xf8 // psubb xmm7, xmm8 + LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d + LONG $0x5cb70f46; WORD $0x223e // movzx r11d, word [rsi + r15 + 34] + QUAD $0x01100e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 16], 1 + QUAD $0x0210064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 16], 2 + QUAD $0x0310264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 16], 3 + QUAD $0x04102e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 16], 4 + LONG $0x4cc40f66; WORD $0x100e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 16], 5 + LONG $0x4cc40f66; WORD $0x101e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 16], 6 + LONG $0x4cc40f66; WORD $0x103e; BYTE $0x07 // pinsrw xmm1, word [rsi + rdi + 16], 7 + LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf9eb0f66 // por xmm7, xmm1 + LONG $0xf26e0f66 // movd xmm6, edx + LONG $0x54b70f42; WORD $0x243e // movzx edx, word [rsi + r15 + 36] + LONG $0x30245489 // mov dword [rsp + 48], edx + QUAD $0x01140e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 20], 1 + QUAD $0x0214066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 20], 2 + QUAD $0x0314266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 20], 3 + QUAD $0x04142e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 20], 4 + LONG $0x6cc40f66; WORD $0x140e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 20], 5 + LONG $0x6cc40f66; WORD $0x141e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 20], 6 + LONG $0x6cc40f66; WORD $0x143e; BYTE $0x07 // pinsrw xmm5, word [rsi + rdi + 20], 7 + LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 + LONG $0xefeb0f66 // por xmm5, xmm7 + LONG $0x6e0f4166; BYTE $0xfe // movd xmm7, r14d + LONG $0x54b70f42; WORD $0x263e // movzx edx, word [rsi + r15 + 38] + LONG $0x20245489 // mov dword [rsp + 32], edx + QUAD $0x01160e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 22], 1 + QUAD $0x02160654c40f4266 // pinsrw xmm2, word [rsi + r8 + 22], 2 + QUAD $0x03162654c40f4266 // pinsrw xmm2, word [rsi + r12 + 22], 3 + QUAD $0x04162e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 22], 4 + LONG $0x54c40f66; WORD $0x160e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 22], 5 + LONG $0x54c40f66; WORD $0x161e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 22], 6 + LONG $0x54c40f66; WORD $0x163e; BYTE $0x07 // pinsrw xmm2, word [rsi + rdi + 22], 7 + QUAD $0x01180e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 24], 1 + QUAD $0x0218065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 24], 2 + QUAD $0x0318265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 24], 3 + QUAD $0x04182e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 24], 4 + LONG $0x5cc40f66; WORD $0x180e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 24], 5 + LONG $0x5cc40f66; WORD $0x181e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 24], 6 + LONG $0x5cc40f66; WORD $0x183e; BYTE $0x07 // pinsrw xmm3, word [rsi + rdi + 24], 7 + LONG $0xd0650f66 // pcmpgtw xmm2, xmm0 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 + LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d + LONG $0x74b70f46; WORD $0x283e // movzx r14d, word [rsi + r15 + 40] + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xe86e0f66 // movd xmm5, eax + LONG $0x44b70f42; WORD $0x2a3e // movzx eax, word [rsi + r15 + 42] + LONG $0x18244489 // mov dword [rsp + 24], eax + QUAD $0x011a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 26], 1 + QUAD $0x021a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 26], 2 + QUAD $0x031a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 26], 3 + QUAD $0x041a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 26], 4 + LONG $0x74c40f66; WORD $0x1a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 26], 5 + LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 26], 6 + LONG $0x74c40f66; WORD $0x1a3e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 26], 7 + QUAD $0x011c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 28], 1 + QUAD $0x021c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 28], 2 + QUAD $0x031c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 28], 3 + QUAD $0x041c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 28], 4 + LONG $0x7cc40f66; WORD $0x1c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 28], 5 + LONG $0x7cc40f66; WORD $0x1c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 28], 6 + LONG $0x7cc40f66; WORD $0x1c3e; BYTE $0x07 // pinsrw xmm7, word [rsi + rdi + 28], 7 + QUAD $0x011e0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 30], 1 + QUAD $0x021e0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 30], 2 + QUAD $0x031e2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 30], 3 + QUAD $0x041e2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 30], 4 + LONG $0x54c40f66; WORD $0x1e0e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 30], 5 + LONG $0x54c40f66; WORD $0x1e1e; BYTE $0x06 // pinsrw xmm2, word [rsi + rbx + 30], 6 + LONG $0x54c40f66; WORD $0x1e3e; BYTE $0x07 // pinsrw xmm2, word [rsi + rdi + 30], 7 + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0xf8650f66 // pcmpgtw xmm7, xmm0 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 + LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 + LONG $0xfeeb0f66 // por xmm7, xmm6 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + LONG $0x54b70f46; WORD $0x2c3e // movzx r10d, word [rsi + r15 + 44] + LONG $0xd0650f66 // pcmpgtw xmm2, xmm0 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 + LONG $0xdb0f4166; BYTE $0xd6 // pand xmm2, xmm14 + LONG $0xd7eb0f66 // por xmm2, xmm7 + LONG $0x746e0f66; WORD $0x3024 // movd xmm6, dword [rsp + 48] + LONG $0x54b70f42; WORD $0x2e3e // movzx edx, word [rsi + r15 + 46] + QUAD $0x01200e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 32], 1 + QUAD $0x0220066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 32], 2 + QUAD $0x0320266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 32], 3 + QUAD $0x04202e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 32], 4 + LONG $0x6cc40f66; WORD $0x200e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 32], 5 + LONG $0x6cc40f66; WORD $0x201e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 32], 6 + QUAD $0x01220e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 34], 1 + QUAD $0x0222064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 34], 2 + QUAD $0x0322264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 34], 3 + QUAD $0x04222e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 34], 4 + LONG $0x4cc40f66; WORD $0x220e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 34], 5 + LONG $0x4cc40f66; WORD $0x221e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 34], 6 + LONG $0x4cc40f66; WORD $0x223e; BYTE $0x07 // pinsrw xmm1, word [rsi + rdi + 34], 7 + LONG $0xd3eb0f66 // por xmm2, xmm3 + LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xf96f0f66 // movdqa xmm7, xmm1 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf9f80f66 // psubb xmm7, xmm1 + LONG $0x5c6e0f66; WORD $0x2024 // movd xmm3, dword [rsp + 32] + LONG $0x5cb70f46; WORD $0x303e // movzx r11d, word [rsi + r15 + 48] + LONG $0x6cc40f66; WORD $0x203e; BYTE $0x07 // pinsrw xmm5, word [rsi + rdi + 32], 7 + LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + QUAD $0x01240e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 36], 1 + QUAD $0x02240674c40f4266 // pinsrw xmm6, word [rsi + r8 + 36], 2 + QUAD $0x03242674c40f4266 // pinsrw xmm6, word [rsi + r12 + 36], 3 + QUAD $0x04242e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 36], 4 + LONG $0x74c40f66; WORD $0x240e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 36], 5 + LONG $0x74c40f66; WORD $0x241e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 36], 6 + LONG $0x74c40f66; WORD $0x243e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 36], 7 + QUAD $0x01260e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 38], 1 + QUAD $0x0226065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 38], 2 + QUAD $0x0326265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 38], 3 + QUAD $0x04262e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 38], 4 + LONG $0x5cc40f66; WORD $0x260e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 38], 5 + LONG $0x5cc40f66; WORD $0x261e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 38], 6 + LONG $0x5cc40f66; WORD $0x263e; BYTE $0x07 // pinsrw xmm3, word [rsi + rdi + 38], 7 + LONG $0xfdeb0f66 // por xmm7, xmm5 + LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d + QUAD $0x01280e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 40], 1 + QUAD $0x0228066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 40], 2 + QUAD $0x0328266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 40], 3 + QUAD $0x04282e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 40], 4 + LONG $0x6cc40f66; WORD $0x280e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 40], 5 + LONG $0x6cc40f66; WORD $0x281e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 40], 6 + LONG $0x44b70f42; WORD $0x323e // movzx eax, word [rsi + r15 + 50] + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 + LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 + LONG $0xf7eb0f66 // por xmm6, xmm7 + LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] + LONG $0x74b70f46; WORD $0x343e // movzx r14d, word [rsi + r15 + 52] + LONG $0x6cc40f66; WORD $0x283e; BYTE $0x07 // pinsrw xmm5, word [rsi + rdi + 40], 7 + LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x03 // psllw xmm3, 3 + LONG $0xdb0f4166; BYTE $0xda // pand xmm3, xmm10 + LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 + LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 + LONG $0xebeb0f66 // por xmm5, xmm3 + LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d + LONG $0x54b70f46; WORD $0x363e // movzx r10d, word [rsi + r15 + 54] + QUAD $0x012a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 42], 1 + QUAD $0x022a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 42], 2 + QUAD $0x032a264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 42], 3 + QUAD $0x042a2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 42], 4 + LONG $0x4cc40f66; WORD $0x2a0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 42], 5 + LONG $0x4cc40f66; WORD $0x2a1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 42], 6 + LONG $0x4cc40f66; WORD $0x2a3e; BYTE $0x07 // pinsrw xmm1, word [rsi + rdi + 42], 7 + QUAD $0x012c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 44], 1 + QUAD $0x022c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 44], 2 + QUAD $0x032c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 44], 3 + QUAD $0x042c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 44], 4 + LONG $0x7cc40f66; WORD $0x2c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 44], 5 + LONG $0x7cc40f66; WORD $0x2c1e; BYTE $0x06 // pinsrw xmm7, word [rsi + rbx + 44], 6 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0xda6e0f66 // movd xmm3, edx + LONG $0x54b70f42; WORD $0x383e // movzx edx, word [rsi + r15 + 56] + LONG $0x7cc40f66; WORD $0x2c3e; BYTE $0x07 // pinsrw xmm7, word [rsi + rdi + 44], 7 + LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x05 // psllw xmm1, 5 + LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 + LONG $0xf8650f66 // pcmpgtw xmm7, xmm0 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 + LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 + LONG $0xf9eb0f66 // por xmm7, xmm1 + LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d + LONG $0x5cb70f46; WORD $0x3a3e // movzx r11d, word [rsi + r15 + 58] + QUAD $0x012e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 46], 1 + QUAD $0x022e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 46], 2 + QUAD $0x032e265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 46], 3 + QUAD $0x042e2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 46], 4 + LONG $0x5cc40f66; WORD $0x2e0e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 46], 5 + LONG $0x5cc40f66; WORD $0x2e1e; BYTE $0x06 // pinsrw xmm3, word [rsi + rbx + 46], 6 + LONG $0x5cc40f66; WORD $0x2e3e; BYTE $0x07 // pinsrw xmm3, word [rsi + rdi + 46], 7 + LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 + LONG $0xdfeb0f66 // por xmm3, xmm7 + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x44b70f42; WORD $0x3c3e // movzx eax, word [rsi + r15 + 60] + LONG $0x7cb70f46; WORD $0x3e3e // movzx r15d, word [rsi + r15 + 62] + QUAD $0x01320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 1 + QUAD $0x0232064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 2 + QUAD $0x0332264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 50], 3 + QUAD $0x04322e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 50], 4 + LONG $0x4cc40f66; WORD $0x320e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 50], 5 + LONG $0x4cc40f66; WORD $0x321e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 50], 6 + LONG $0x4cc40f66; WORD $0x323e; BYTE $0x07 // pinsrw xmm1, word [rsi + rdi + 50], 7 + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xe96f0f66 // movdqa xmm5, xmm1 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xe9f80f66 // psubb xmm5, xmm1 + LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d + QUAD $0x01300e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 48], 1 + QUAD $0x02300674c40f4266 // pinsrw xmm6, word [rsi + r8 + 48], 2 + QUAD $0x03302674c40f4266 // pinsrw xmm6, word [rsi + r12 + 48], 3 + QUAD $0x04302e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 48], 4 + LONG $0x74c40f66; WORD $0x300e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 48], 5 + LONG $0x74c40f66; WORD $0x301e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 48], 6 + LONG $0x74c40f66; WORD $0x303e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 48], 7 + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + QUAD $0x01340e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 52], 1 + QUAD $0x0234064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 52], 2 + QUAD $0x0334264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 52], 3 + QUAD $0x04342e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 52], 4 + LONG $0x4cc40f66; WORD $0x340e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 52], 5 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0x4cc40f66; WORD $0x341e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 52], 6 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d + LONG $0x4cc40f66; WORD $0x343e; BYTE $0x07 // pinsrw xmm1, word [rsi + rdi + 52], 7 + LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x02 // psllw xmm1, 2 + LONG $0xdb0f4166; BYTE $0xc9 // pand xmm1, xmm9 + LONG $0xcdeb0f66 // por xmm1, xmm5 + LONG $0xea6e0f66 // movd xmm5, edx + QUAD $0x01360e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 54], 1 + QUAD $0x02360674c40f4266 // pinsrw xmm6, word [rsi + r8 + 54], 2 + QUAD $0x03362674c40f4266 // pinsrw xmm6, word [rsi + r12 + 54], 3 + QUAD $0x04362e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 54], 4 + LONG $0x74c40f66; WORD $0x360e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 54], 5 + LONG $0x74c40f66; WORD $0x361e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 54], 6 + LONG $0x74c40f66; WORD $0x363e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 54], 7 + QUAD $0x01380e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 56], 1 + QUAD $0x0238066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 56], 2 + QUAD $0x0338266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 56], 3 + QUAD $0x04382e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 56], 4 + LONG $0x6cc40f66; WORD $0x380e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 56], 5 + LONG $0x6cc40f66; WORD $0x381e; BYTE $0x06 // pinsrw xmm5, word [rsi + rbx + 56], 6 + LONG $0x6cc40f66; WORD $0x383e; BYTE $0x07 // pinsrw xmm5, word [rsi + rdi + 56], 7 + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x03 // psllw xmm6, 3 + LONG $0xdb0f4166; BYTE $0xf2 // pand xmm6, xmm10 + LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 + LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d + QUAD $0x013a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 58], 1 + QUAD $0x023a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 58], 2 + QUAD $0x033a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 58], 3 + QUAD $0x043a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 58], 4 + LONG $0x74c40f66; WORD $0x3a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 58], 5 + LONG $0x74c40f66; WORD $0x3a1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 58], 6 + LONG $0x74c40f66; WORD $0x3a3e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 58], 7 + LONG $0xe9eb0f66 // por xmm5, xmm1 + LONG $0xc86e0f66 // movd xmm1, eax + QUAD $0x013c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 60], 1 + QUAD $0x023c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 60], 2 + QUAD $0x033c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 60], 3 + QUAD $0x043c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 60], 4 + LONG $0x4cc40f66; WORD $0x3c0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 60], 5 + LONG $0x4cc40f66; WORD $0x3c1e; BYTE $0x06 // pinsrw xmm1, word [rsi + rbx + 60], 6 + LONG $0x4cc40f66; WORD $0x3c3e; BYTE $0x07 // pinsrw xmm1, word [rsi + rdi + 60], 7 + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x06 // psllw xmm1, 6 + LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 + LONG $0xceeb0f66 // por xmm1, xmm6 + LONG $0x6e0f4166; BYTE $0xf7 // movd xmm6, r15d + QUAD $0x013e0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 62], 1 + QUAD $0x023e0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 62], 2 + QUAD $0x033e2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 62], 3 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x043e2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 62], 4 + LONG $0x74c40f66; WORD $0x3e0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 62], 5 + LONG $0x74c40f66; WORD $0x3e1e; BYTE $0x06 // pinsrw xmm6, word [rsi + rbx + 62], 6 + LONG $0x74c40f66; WORD $0x3e3e; BYTE $0x07 // pinsrw xmm6, word [rsi + rdi + 62], 7 + LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 + LONG $0xdb0f4166; BYTE $0xf6 // pand xmm6, xmm14 + LONG $0xf1eb0f66 // por xmm6, xmm1 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0xcc6f0f66 // movdqa xmm1, xmm4 + LONG $0xca6c0f66 // punpcklqdq xmm1, xmm2 + LONG $0xeb6f0f66 // movdqa xmm5, xmm3 + LONG $0xee6c0f66 // punpcklqdq xmm5, xmm6 + QUAD $0x00000090bd6f0f66 // movdqa xmm7, oword 144[rbp] /* [rip + .LCPI7_9] */ + LONG $0x00380f66; BYTE $0xef // pshufb xmm5, xmm7 + LONG $0x00380f66; BYTE $0xcf // pshufb xmm1, xmm7 + LONG $0xcd610f66 // punpcklwd xmm1, xmm5 + LONG $0xde600f66 // punpcklbw xmm3, xmm6 + LONG $0xe2600f66 // punpcklbw xmm4, xmm2 + LONG $0xe3610f66 // punpcklwd xmm4, xmm3 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + LONG $0x7f0f41f3; WORD $0x8c24 // movdqu oword [r12 + 4*rcx], xmm4 + LONG $0x7f0f41f3; WORD $0x8c4c; BYTE $0x10 // movdqu oword [r12 + 4*rcx + 16], xmm1 + LONG $0x08c18348 // add rcx, 8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] + JNE LBB7_143 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x246c8b44; BYTE $0x38 // mov r13d, dword [rsp + 56] + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + JNE LBB7_145 + JMP LBB7_148 -LBB7_191: - LONG $0x01c0f641 // test r8b, 1 - JE LBB7_202 - LONG $0x02100ff3 // movss xmm0, dword [rdx] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xda // mov rdx, r11 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x173c8a41 // mov dil, byte [r15 + rdx] - LONG $0x07e38041 // and r11b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x171c8841 // mov byte [r15 + rdx], bl - JMP LBB7_202 +LBB7_206: + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + LONG $0xfce08348 // and rax, -4 + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0x07e1c148 // shl rcx, 7 + WORD $0x0148; BYTE $0xf1 // add rcx, rsi + LONG $0x84148d4d // lea r10, [r12 + 4*rax] + LONG $0x6f0f4566; BYTE $0xf3 // movdqa xmm14, xmm11 + LONG $0xf3c60f45; BYTE $0x00 // shufps xmm14, xmm11, 0 + LONG $0xfcc68148; WORD $0x0001; BYTE $0x00 // add rsi, 508 + WORD $0xd231 // xor edx, edx + LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI7_0] */ -LBB7_84: - LONG $0xf0e28349 // and r10, -16 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 +LBB7_207: + QUAD $0xfffffe049e100ff3 // movss xmm3, dword [rsi - 508] + QUAD $0xfffe0896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 504] + QUAD $0xfffe0c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 500] + QUAD $0xfffffe108e100ff3 // movss xmm1, dword [rsi - 496] + QUAD $0xfffe849e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 380], 16 + QUAD $0xffff049e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 252], 32 + LONG $0x213a0f66; WORD $0x845e; BYTE $0x30 // insertps xmm3, dword [rsi - 124], 48 + QUAD $0xfe8896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 376], 16 + QUAD $0xff0896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 248], 32 + QUAD $0x308856213a0f4466 // insertps xmm10, dword [rsi - 120], 48 + QUAD $0xfe8c8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 372], 16 + QUAD $0xff0c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 244], 32 + QUAD $0x308c4e213a0f4466 // insertps xmm9, dword [rsi - 116], 48 + QUAD $0xfffe908e213a0f66; WORD $0x10ff // insertps xmm1, dword [rsi - 368], 16 + QUAD $0xffff108e213a0f66; WORD $0x20ff // insertps xmm1, dword [rsi - 240], 32 + LONG $0x213a0f66; WORD $0x904e; BYTE $0x30 // insertps xmm1, dword [rsi - 112], 48 + QUAD $0xfffe1486100f44f3; BYTE $0xff // movss xmm8, dword [rsi - 492] + QUAD $0xfe9486213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm8, dword [rsi - 364], 16 + QUAD $0xff1486213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm8, dword [rsi - 236], 32 + LONG $0xe6280f45 // movaps xmm12, xmm14 + QUAD $0x309446213a0f4466 // insertps xmm8, dword [rsi - 108], 48 + QUAD $0xfffffe1896100ff3 // movss xmm2, dword [rsi - 488] + QUAD $0xfffe9896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 360], 16 + QUAD $0xffff1896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 232], 32 + LONG $0xe3c20f44; BYTE $0x01 // cmpltps xmm12, xmm3 + LONG $0x213a0f66; WORD $0x9856; BYTE $0x30 // insertps xmm2, dword [rsi - 104], 48 + QUAD $0xfffffe1c9e100ff3 // movss xmm3, dword [rsi - 484] + QUAD $0xfffe9c9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 356], 16 + QUAD $0xffff1c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 228], 32 + LONG $0x6b0f4566; BYTE $0xe4 // packssdw xmm12, xmm12 + LONG $0x213a0f66; WORD $0x9c5e; BYTE $0x30 // insertps xmm3, dword [rsi - 100], 48 + QUAD $0xfffffe24a6100ff3 // movss xmm4, dword [rsi - 476] + QUAD $0xfffea4a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 348], 16 + QUAD $0xffff24a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 220], 32 + LONG $0x630f4566; BYTE $0xe4 // packsswb xmm12, xmm12 + LONG $0x213a0f66; WORD $0xa466; BYTE $0x30 // insertps xmm4, dword [rsi - 92], 48 + LONG $0xfe280f41 // movaps xmm7, xmm14 + QUAD $0xfffffe44ae100ff3 // movss xmm5, dword [rsi - 444] + QUAD $0xfffec4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 316], 16 + QUAD $0xffff44ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 188], 32 + LONG $0x01fcc20f // cmpltps xmm7, xmm4 + LONG $0x213a0f66; WORD $0xc46e; BYTE $0x30 // insertps xmm5, dword [rsi - 60], 48 + LONG $0xf6280f41 // movaps xmm6, xmm14 + QUAD $0xfffe64ae100f44f3; BYTE $0xff // movss xmm13, dword [rsi - 412] + QUAD $0xfee4ae213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm13, dword [rsi - 284], 16 + QUAD $0xff64ae213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm13, dword [rsi - 156], 32 + LONG $0x01f5c20f // cmpltps xmm6, xmm5 + QUAD $0x30e46e213a0f4466 // insertps xmm13, dword [rsi - 28], 48 + LONG $0xe6280f41 // movaps xmm4, xmm14 + LONG $0xe5c20f41; BYTE $0x01 // cmpltps xmm4, xmm13 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xeac20f41; BYTE $0x01 // cmpltps xmm5, xmm10 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xc56f0f66 // movdqa xmm0, xmm5 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xc5f80f66 // psubb xmm0, xmm5 + QUAD $0xfffe2096100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 480] + QUAD $0xfea096213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 352], 16 + LONG $0xdb0f4566; BYTE $0xe7 // pand xmm12, xmm15 + QUAD $0xff2096213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 224], 32 + LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xe9c20f41; BYTE $0x01 // cmpltps xmm5, xmm9 + QUAD $0x30a056213a0f4466 // insertps xmm10, dword [rsi - 96], 48 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0x6f0f4466; WORD $0x106d // movdqa xmm13, oword 16[rbp] /* [rip + .LCPI7_1] */ + LONG $0xdb0f4166; BYTE $0xed // pand xmm5, xmm13 + LONG $0xe8eb0f66 // por xmm5, xmm0 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c1c20f // cmpltps xmm0, xmm1 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0xc8c20f41; BYTE $0x01 // cmpltps xmm1, xmm8 + QUAD $0xfffe288e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 472] + QUAD $0xfea88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 344], 16 + QUAD $0xff288e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 216], 32 + QUAD $0x30a84e213a0f4466 // insertps xmm9, dword [rsi - 88], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0x6f0f4466; WORD $0x206d // movdqa xmm13, oword 32[rbp] /* [rip + .LCPI7_2] */ + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0x6f0f4466; WORD $0x306d // movdqa xmm13, oword 48[rbp] /* [rip + .LCPI7_3] */ + LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffe2ca6100f44f3; BYTE $0xff // movss xmm12, dword [rsi - 468] + QUAD $0xfeaca6213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm12, dword [rsi - 340], 16 + QUAD $0xff2ca6213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm12, dword [rsi - 212], 32 + QUAD $0x30ac66213a0f4466 // insertps xmm12, dword [rsi - 84], 48 + LONG $0xcdeb0f66 // por xmm1, xmm5 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c2c20f // cmpltps xmm0, xmm2 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0x01ebc20f // cmpltps xmm5, xmm3 + QUAD $0xfffffe3096100ff3 // movss xmm2, dword [rsi - 464] + QUAD $0xfffeb096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 336], 16 + QUAD $0xffff3096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 208], 32 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0x213a0f66; WORD $0xb056; BYTE $0x30 // insertps xmm2, dword [rsi - 80], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 + LONG $0x6f0f4466; WORD $0x406d // movdqa xmm13, oword 64[rbp] /* [rip + .LCPI7_4] */ + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 + LONG $0x5d6f0f66; BYTE $0x50 // movdqa xmm3, oword 80[rbp] /* [rip + .LCPI7_5] */ + LONG $0xebdb0f66 // pand xmm5, xmm3 + LONG $0xe8eb0f66 // por xmm5, xmm0 + LONG $0xc6280f45 // movaps xmm8, xmm14 + LONG $0xc2c20f45; BYTE $0x01 // cmpltps xmm8, xmm10 + QUAD $0xfffffe349e100ff3 // movss xmm3, dword [rsi - 460] + QUAD $0xfffeb49e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 332], 16 + QUAD $0xffff349e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 204], 32 + LONG $0x213a0f66; WORD $0xb45e; BYTE $0x30 // insertps xmm3, dword [rsi - 76], 48 + LONG $0x6b0f4566; BYTE $0xc0 // packssdw xmm8, xmm8 + LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 + LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 + LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI7_6] */ + LONG $0xdb0f4466; BYTE $0xc0 // pand xmm8, xmm0 + LONG $0xeb0f4466; BYTE $0xc5 // por xmm8, xmm5 + QUAD $0xfffe3896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 456] + QUAD $0xfeb896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 328], 16 + QUAD $0xff3896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 200], 32 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x30b856213a0f4466 // insertps xmm10, dword [rsi - 72], 48 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0xc1c20f41; BYTE $0x01 // cmpltps xmm0, xmm9 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xc8f80f66 // psubb xmm1, xmm0 + QUAD $0xfffe3c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 452] + QUAD $0xfebc8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 324], 16 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + QUAD $0xff3c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 196], 32 + LONG $0xcfeb0f66 // por xmm1, xmm7 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xecc20f41; BYTE $0x01 // cmpltps xmm5, xmm12 + QUAD $0x30bc4e213a0f4466 // insertps xmm9, dword [rsi - 68], 48 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0x6ddb0f66; BYTE $0x10 // pand xmm5, oword 16[rbp] /* [rip + .LCPI7_1] */ + LONG $0xe9eb0f66 // por xmm5, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c2c20f // cmpltps xmm0, xmm2 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0x01cbc20f // cmpltps xmm1, xmm3 + QUAD $0xfffffe409e100ff3 // movss xmm3, dword [rsi - 448] + QUAD $0xfffec09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 320], 16 + QUAD $0xffff409e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 192], 32 + LONG $0x213a0f66; WORD $0xc05e; BYTE $0x30 // insertps xmm3, dword [rsi - 64], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0x6f0f4466; WORD $0x2065 // movdqa xmm12, oword 32[rbp] /* [rip + .LCPI7_2] */ + LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0x4ddb0f66; BYTE $0x30 // pand xmm1, oword 48[rbp] /* [rip + .LCPI7_3] */ + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffffe4896100ff3 // movss xmm2, dword [rsi - 440] + QUAD $0xfffec896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 312], 16 + QUAD $0xffff4896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 184], 32 + LONG $0x213a0f66; WORD $0xc856; BYTE $0x30 // insertps xmm2, dword [rsi - 56], 48 + LONG $0xcdeb0f66 // por xmm1, xmm5 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0xc2c20f41; BYTE $0x01 // cmpltps xmm0, xmm10 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xe9c20f41; BYTE $0x01 // cmpltps xmm5, xmm9 + QUAD $0xfffffe4cbe100ff3 // movss xmm7, dword [rsi - 436] + QUAD $0xfffeccbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 308], 16 + QUAD $0xffff4cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 180], 32 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0x213a0f66; WORD $0xcc7e; BYTE $0x30 // insertps xmm7, dword [rsi - 52], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 + LONG $0x6ddb0f66; BYTE $0x50 // pand xmm5, oword 80[rbp] /* [rip + .LCPI7_5] */ + LONG $0xe8eb0f66 // por xmm5, xmm0 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c3c20f // cmpltps xmm0, xmm3 + QUAD $0xfffffe509e100ff3 // movss xmm3, dword [rsi - 432] + QUAD $0xfffed09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 304], 16 + QUAD $0xffff509e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 176], 32 + LONG $0x213a0f66; WORD $0xd05e; BYTE $0x30 // insertps xmm3, dword [rsi - 48], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0x6f0f4466; WORD $0x6055 // movdqa xmm10, oword 96[rbp] /* [rip + .LCPI7_6] */ + LONG $0xdb0f4166; BYTE $0xc2 // pand xmm0, xmm10 + LONG $0xc5eb0f66 // por xmm0, xmm5 + QUAD $0xfffffe54ae100ff3 // movss xmm5, dword [rsi - 428] + QUAD $0xfffed4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 300], 16 + QUAD $0xffff54ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 172], 32 + LONG $0x213a0f66; WORD $0xd46e; BYTE $0x30 // insertps xmm5, dword [rsi - 44], 48 + LONG $0xc1eb0f66 // por xmm0, xmm1 + QUAD $0xfffe588e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 424] + QUAD $0xfed88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 296], 16 + QUAD $0xff588e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 168], 32 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + QUAD $0x30d84e213a0f4466 // insertps xmm9, dword [rsi - 40], 48 + LONG $0x620f4466; BYTE $0xc0 // punpckldq xmm8, xmm0 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c2c20f // cmpltps xmm0, xmm2 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xc8f80f66 // psubb xmm1, xmm0 + QUAD $0xfffffe5c96100ff3 // movss xmm2, dword [rsi - 420] + QUAD $0xfffedc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 292], 16 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + QUAD $0xffff5c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 164], 32 + LONG $0xceeb0f66 // por xmm1, xmm6 + LONG $0xf6280f41 // movaps xmm6, xmm14 + LONG $0x01f7c20f // cmpltps xmm6, xmm7 + LONG $0x213a0f66; WORD $0xdc56; BYTE $0x30 // insertps xmm2, dword [rsi - 36], 48 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 + LONG $0x456f0f66; BYTE $0x10 // movdqa xmm0, oword 16[rbp] /* [rip + .LCPI7_1] */ + LONG $0xf0db0f66 // pand xmm6, xmm0 + LONG $0xf1eb0f66 // por xmm6, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c3c20f // cmpltps xmm0, xmm3 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0x01cdc20f // cmpltps xmm1, xmm5 + QUAD $0xfffffe609e100ff3 // movss xmm3, dword [rsi - 416] + QUAD $0xfffee09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 288], 16 + QUAD $0xffff609e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 160], 32 + LONG $0x213a0f66; WORD $0xe05e; BYTE $0x30 // insertps xmm3, dword [rsi - 32], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0x6f0f4466; WORD $0x3065 // movdqa xmm12, oword 48[rbp] /* [rip + .LCPI7_3] */ + LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffffe68ae100ff3 // movss xmm5, dword [rsi - 408] + QUAD $0xfffee8ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 280], 16 + QUAD $0xffff68ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 152], 32 + LONG $0x213a0f66; WORD $0xe86e; BYTE $0x30 // insertps xmm5, dword [rsi - 24], 48 + LONG $0xceeb0f66 // por xmm1, xmm6 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0xc1c20f41; BYTE $0x01 // cmpltps xmm0, xmm9 + LONG $0xf6280f41 // movaps xmm6, xmm14 + LONG $0x01f2c20f // cmpltps xmm6, xmm2 + QUAD $0xfffffe6cbe100ff3 // movss xmm7, dword [rsi - 404] + QUAD $0xfffeecbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 276], 16 + QUAD $0xffff6cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 148], 32 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0x213a0f66; WORD $0xec7e; BYTE $0x30 // insertps xmm7, dword [rsi - 20], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x06 // psllw xmm6, 6 + LONG $0x6f0f4466; WORD $0x504d // movdqa xmm9, oword 80[rbp] /* [rip + .LCPI7_5] */ + LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 + LONG $0xf0eb0f66 // por xmm6, xmm0 + LONG $0xd6280f41 // movaps xmm2, xmm14 + LONG $0x01d3c20f // cmpltps xmm2, xmm3 + QUAD $0xfffffe709e100ff3 // movss xmm3, dword [rsi - 400] + QUAD $0xfffef09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 272], 16 + QUAD $0xffff709e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 144], 32 + LONG $0x213a0f66; WORD $0xf05e; BYTE $0x30 // insertps xmm3, dword [rsi - 16], 48 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] + QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 + QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 + LONG $0xd1eb0f66 // por xmm2, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c5c20f // cmpltps xmm0, xmm5 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xc8f80f66 // psubb xmm1, xmm0 + QUAD $0xfffffe78ae100ff3 // movss xmm5, dword [rsi - 392] + QUAD $0xfffef8ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 264], 16 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + QUAD $0xffff78ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 136], 32 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0xe6280f41 // movaps xmm4, xmm14 + LONG $0x01e7c20f // cmpltps xmm4, xmm7 + LONG $0x213a0f66; WORD $0xf86e; BYTE $0x30 // insertps xmm5, dword [rsi - 8], 48 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + LONG $0xf4710f66; BYTE $0x02 // psllw xmm4, 2 + LONG $0x65db0f66; BYTE $0x10 // pand xmm4, oword 16[rbp] /* [rip + .LCPI7_1] */ + LONG $0xe1eb0f66 // por xmm4, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x01c3c20f // cmpltps xmm0, xmm3 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0x01cec20f // cmpltps xmm1, xmm6 + QUAD $0xfffffe7c9e100ff3 // movss xmm3, dword [rsi - 388] + QUAD $0xfffefc9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 260], 16 + QUAD $0xffff7c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 132], 32 + LONG $0x213a0f66; WORD $0xfc5e; BYTE $0x30 // insertps xmm3, dword [rsi - 4], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0x45db0f66; BYTE $0x20 // pand xmm0, oword 32[rbp] /* [rip + .LCPI7_2] */ + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffffe8086100ff3 // movss xmm0, dword [rsi - 384] + QUAD $0xffff0086213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 256], 16 + LONG $0x213a0f66; WORD $0x8046; BYTE $0x20 // insertps xmm0, dword [rsi - 128], 32 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0xe6280f41 // movaps xmm4, xmm14 + LONG $0x01e5c20f // cmpltps xmm4, xmm5 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0x01ebc20f // cmpltps xmm5, xmm3 + LONG $0x213a0f66; WORD $0x3006 // insertps xmm0, dword [rsi], 48 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + LONG $0xf4710f66; BYTE $0x05 // psllw xmm4, 5 + LONG $0xdb0f4166; BYTE $0xe5 // pand xmm4, xmm13 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 + LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 + LONG $0xeceb0f66 // por xmm5, xmm4 + LONG $0xde280f41 // movaps xmm3, xmm14 + LONG $0x01d8c20f // cmpltps xmm3, xmm0 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xda // pand xmm3, xmm10 + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xd9eb0f66 // por xmm3, xmm1 + LONG $0xd3620f66 // punpckldq xmm2, xmm3 + LONG $0x600f4466; BYTE $0xc2 // punpcklbw xmm8, xmm2 + LONG $0x380f4466; WORD $0x4500; BYTE $0x70 // pshufb xmm8, oword 112[rbp] /* [rip + .LCPI7_7] */ + LONG $0x7f0f45f3; WORD $0x9404 // movdqu oword [r12 + 4*rdx], xmm8 + LONG $0x04c28348 // add rdx, 4 + LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JNE LBB7_207 + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JNE LBB7_209 + JMP LBB7_212 + +LBB7_97: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000e82494894c // mov qword [rsp + 232], r10 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x90048d4a // lea rax, [rax + 4*r10] - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax - LONG $0xc4b60f41 // movzx eax, r12b + WORD $0x014c; BYTE $0xf0 // add rax, r14 + QUAD $0x0000013824848948 // mov qword [rsp + 312], rax + QUAD $0x000000f8248c8948 // mov qword [rsp + 248], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + LONG $0xc5b60f41 // movzx eax, r13b LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000090248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm1 + QUAD $0x0000a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm1 WORD $0xc031 // xor eax, eax + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 -LBB7_85: - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - LONG $0x05e7c148 // shl rdi, 5 - WORD $0x8949; BYTE $0xfc // mov r12, rdi - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - WORD $0x8949; BYTE $0xfb // mov r11, rdi - WORD $0x8949; BYTE $0xf9 // mov r9, rdi - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - WORD $0x8949; BYTE $0xf8 // mov r8, rdi - WORD $0x8949; BYTE $0xfe // mov r14, rdi - WORD $0x8949; BYTE $0xfa // mov r10, rdi - WORD $0x8949; BYTE $0xff // mov r15, rdi - WORD $0x8948; BYTE $0xfb // mov rbx, rdi - LONG $0x247c8948; BYTE $0x38 // mov qword [rsp + 56], rdi - LONG $0x3e0cb60f // movzx ecx, byte [rsi + rdi] +LBB7_98: + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + LONG $0x05e6c148 // shl rsi, 5 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x8949; BYTE $0xf2 // mov r10, rsi + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + WORD $0x8949; BYTE $0xf7 // mov r15, rsi + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x8949; BYTE $0xf0 // mov r8, rsi + WORD $0x8949; BYTE $0xf1 // mov r9, rsi + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + LONG $0x24748948; BYTE $0x28 // mov qword [rsp + 40], rsi + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + LONG $0x0cb60f41; BYTE $0x36 // movzx ecx, byte [r14 + rsi] LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x3e4cb60f; BYTE $0x01 // movzx ecx, byte [rsi + rdi + 1] + LONG $0x4cb60f41; WORD $0x0136 // movzx ecx, byte [r14 + rsi + 1] LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x3e4cb60f; BYTE $0x02 // movzx ecx, byte [rsi + rdi + 2] + LONG $0x4cb60f41; WORD $0x0236 // movzx ecx, byte [r14 + rsi + 2] LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x3e4cb60f; BYTE $0x03 // movzx ecx, byte [rsi + rdi + 3] + LONG $0x4cb60f41; WORD $0x0336 // movzx ecx, byte [r14 + rsi + 3] LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x3e4cb60f; BYTE $0x04 // movzx ecx, byte [rsi + rdi + 4] + LONG $0x4cb60f41; WORD $0x0436 // movzx ecx, byte [r14 + rsi + 4] LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x3e4cb60f; BYTE $0x05 // movzx ecx, byte [rsi + rdi + 5] + LONG $0x4cb60f41; WORD $0x0536 // movzx ecx, byte [r14 + rsi + 5] LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x3e4cb60f; BYTE $0x06 // movzx ecx, byte [rsi + rdi + 6] + LONG $0x4cb60f41; WORD $0x0636 // movzx ecx, byte [r14 + rsi + 6] LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x3e4cb60f; BYTE $0x07 // movzx ecx, byte [rsi + rdi + 7] + LONG $0x4cb60f41; WORD $0x0736 // movzx ecx, byte [r14 + rsi + 7] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 - LONG $0x3e4cb60f; BYTE $0x08 // movzx ecx, byte [rsi + rdi + 8] + QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 + LONG $0x4cb60f41; WORD $0x0836 // movzx ecx, byte [r14 + rsi + 8] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00013024847f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm0 - LONG $0x3e4cb60f; BYTE $0x09 // movzx ecx, byte [rsi + rdi + 9] + QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 + LONG $0x4cb60f41; WORD $0x0936 // movzx ecx, byte [r14 + rsi + 9] LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x3e4cb60f; BYTE $0x0a // movzx ecx, byte [rsi + rdi + 10] + LONG $0x4cb60f41; WORD $0x0a36 // movzx ecx, byte [r14 + rsi + 10] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 - LONG $0x3e4cb60f; BYTE $0x0b // movzx ecx, byte [rsi + rdi + 11] + QUAD $0x00009024847f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm0 + LONG $0x4cb60f41; WORD $0x0b36 // movzx ecx, byte [r14 + rsi + 11] LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x3e4cb60f; BYTE $0x0c // movzx ecx, byte [rsi + rdi + 12] + LONG $0x4cb60f41; WORD $0x0c36 // movzx ecx, byte [r14 + rsi + 12] LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x3e4cb60f; BYTE $0x0d // movzx ecx, byte [rsi + rdi + 13] + LONG $0x4cb60f41; WORD $0x0d36 // movzx ecx, byte [r14 + rsi + 13] LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x3e4cb60f; BYTE $0x0e // movzx ecx, byte [rsi + rdi + 14] + LONG $0x4cb60f41; WORD $0x0e36 // movzx ecx, byte [r14 + rsi + 14] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 - LONG $0x247c8948; BYTE $0x28 // mov qword [rsp + 40], rdi - WORD $0x8949; BYTE $0xfd // mov r13, rdi + QUAD $0x00010024847f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm0 + WORD $0x8949; BYTE $0xf5 // mov r13, rsi LONG $0x20cd8349 // or r13, 32 LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 - LONG $0x40cc8349 // or r12, 64 + LONG $0x40c88348 // or rax, 64 + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax LONG $0x60ca8348 // or rdx, 96 - LONG $0x24548948; BYTE $0x68 // mov qword [rsp + 104], rdx - LONG $0x80cb8149; WORD $0x0000; BYTE $0x00 // or r11, 128 - LONG $0x245c894c; BYTE $0x40 // mov qword [rsp + 64], r11 - WORD $0x8949; BYTE $0xfb // mov r11, rdi - LONG $0xa0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 160 - LONG $0x00c00d48; WORD $0x0000 // or rax, 192 - LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - LONG $0xe0c98149; WORD $0x0000; BYTE $0x00 // or r9, 224 - LONG $0x00ce8149; WORD $0x0001; BYTE $0x00 // or r14, 256 - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 - LONG $0x2454894c; BYTE $0x78 // mov qword [rsp + 120], r10 - LONG $0x40c88149; WORD $0x0001; BYTE $0x00 // or r8, 320 - LONG $0x2444894c; BYTE $0x48 // mov qword [rsp + 72], r8 - LONG $0x60cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 352 - LONG $0x245c8948; BYTE $0x58 // mov qword [rsp + 88], rbx - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - LONG $0x80c98148; WORD $0x0001; BYTE $0x00 // or rcx, 384 - LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01c00d48; WORD $0x0000 // or rax, 448 - LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax - WORD $0x8948; BYTE $0xf8 // mov rax, rdi - LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - QUAD $0x012e3c203a0f4666 // pinsrb xmm15, byte [rsi + r13], 1 - QUAD $0x02263c203a0f4666 // pinsrb xmm15, byte [rsi + r12], 2 - QUAD $0x03163c203a0f4466 // pinsrb xmm15, byte [rsi + rdx], 3 - LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] - QUAD $0x042e3c203a0f4666 // pinsrb xmm15, byte [rsi + r13], 4 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - QUAD $0x051e3c203a0f4666 // pinsrb xmm15, byte [rsi + r11], 5 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x063e3c203a0f4666 // pinsrb xmm15, byte [rsi + r15], 6 - QUAD $0x070e3c203a0f4666 // pinsrb xmm15, byte [rsi + r9], 7 - QUAD $0x08363c203a0f4666 // pinsrb xmm15, byte [rsi + r14], 8 - QUAD $0x09163c203a0f4666 // pinsrb xmm15, byte [rsi + r10], 9 - QUAD $0x0a063c203a0f4666 // pinsrb xmm15, byte [rsi + r8], 10 - QUAD $0x0b1e3c203a0f4466 // pinsrb xmm15, byte [rsi + rbx], 11 - QUAD $0x0c0e3c203a0f4466 // pinsrb xmm15, byte [rsi + rcx], 12 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0d163c203a0f4466 // pinsrb xmm15, byte [rsi + rdx], 13 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0e163c203a0f4466 // pinsrb xmm15, byte [rsi + rdx], 14 - QUAD $0x0f063c203a0f4466 // pinsrb xmm15, byte [rsi + rax], 15 - LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] - QUAD $0x011e6c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rsi + r11 + 1], 1 - QUAD $0x01266c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rsi + r12 + 1], 2 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x011e6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r11 + 1], 3 - QUAD $0x012e6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r13 + 1], 4 - QUAD $0x05013e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 1], 5 - QUAD $0x013e6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r15 + 1], 6 - QUAD $0x010e6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r9 + 1], 7 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - QUAD $0x01366c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r14 + 1], 8 - QUAD $0x01166c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r10 + 1], 9 - QUAD $0x01066c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r8 + 1], 10 - QUAD $0x0b011e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 1], 11 - QUAD $0x0c010e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 1], 12 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0d010e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 1], 13 - QUAD $0x0e01166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 1], 14 - QUAD $0x0f01066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 1], 15 - QUAD $0x0090248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 144] + LONG $0x24548948; BYTE $0x58 // mov qword [rsp + 88], rdx + LONG $0x80ca8149; WORD $0x0000; BYTE $0x00 // or r10, 128 + LONG $0xa0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 160 + LONG $0xc0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 192 + LONG $0x247c894c; BYTE $0x50 // mov qword [rsp + 80], r15 + LONG $0xe0cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 224 + LONG $0x247c8948; BYTE $0x38 // mov qword [rsp + 56], rdi + LONG $0x00c88149; WORD $0x0001; BYTE $0x00 // or r8, 256 + LONG $0x20c98149; WORD $0x0001; BYTE $0x00 // or r9, 288 + LONG $0x40cb8149; WORD $0x0001; BYTE $0x00 // or r11, 320 + LONG $0x245c894c; BYTE $0x78 // mov qword [rsp + 120], r11 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + LONG $0x60cf8149; WORD $0x0001; BYTE $0x00 // or r15, 352 + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 + LONG $0x247c8948; BYTE $0x48 // mov qword [rsp + 72], rdi + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0x24748948; BYTE $0x40 // mov qword [rsp + 64], rsi + LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 + LONG $0x245c8948; BYTE $0x18 // mov qword [rsp + 24], rbx + LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 + LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx + QUAD $0x012e3c203a0f4766 // pinsrb xmm15, byte [r14 + r13], 1 + QUAD $0x02063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 2 + QUAD $0x03163c203a0f4566 // pinsrb xmm15, byte [r14 + rdx], 3 + WORD $0x894c; BYTE $0xd6 // mov rsi, r10 + QUAD $0x04163c203a0f4766 // pinsrb xmm15, byte [r14 + r10], 4 + QUAD $0x05263c203a0f4766 // pinsrb xmm15, byte [r14 + r12], 5 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x06063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 6 + LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] + QUAD $0x072e3c203a0f4766 // pinsrb xmm15, byte [r14 + r13], 7 + QUAD $0x08063c203a0f4766 // pinsrb xmm15, byte [r14 + r8], 8 + QUAD $0x090e3c203a0f4766 // pinsrb xmm15, byte [r14 + r9], 9 + QUAD $0x0a1e3c203a0f4766 // pinsrb xmm15, byte [r14 + r11], 10 + QUAD $0x0b3e3c203a0f4766 // pinsrb xmm15, byte [r14 + r15], 11 + QUAD $0x0c3e3c203a0f4566 // pinsrb xmm15, byte [r14 + rdi], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d063c203a0f4566 // pinsrb xmm15, byte [r14 + rax], 13 + QUAD $0x0e1e3c203a0f4566 // pinsrb xmm15, byte [r14 + rbx], 14 + QUAD $0x0f0e3c203a0f4566 // pinsrb xmm15, byte [r14 + rcx], 15 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x01166c203a0f4366; BYTE $0x01 // pinsrb xmm5, byte [r14 + r10 + 1], 1 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x01166c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r14 + r10 + 1], 2 + QUAD $0x01166c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r14 + rdx + 1], 3 + QUAD $0x01366c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rsi + 1], 4 + QUAD $0x01266c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r12 + 1], 5 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x01066c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r14 + rax + 1], 6 + QUAD $0x012e6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r13 + 1], 7 + WORD $0x894d; BYTE $0xec // mov r12, r13 + QUAD $0x01066c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r8 + 1], 8 + QUAD $0x010e6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r9 + 1], 9 + QUAD $0x011e6c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r11 + 1], 10 + QUAD $0x013e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r15 + 1], 11 + WORD $0x894d; BYTE $0xfb // mov r11, r15 + LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 + QUAD $0x013e6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rdi + 1], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x01066c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rax + 1], 13 + QUAD $0x011e6c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rbx + 1], 14 + QUAD $0x010e6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r14 + rcx + 1], 15 + QUAD $0x00a0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 160] LONG $0x640f4166; BYTE $0xe9 // pcmpgtb xmm5, xmm9 LONG $0xfd6f0f66 // movdqa xmm7, xmm5 QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI7_10] */ LONG $0xfcdb0f66 // pand xmm7, xmm4 LONG $0xfdf80f66 // psubb xmm7, xmm5 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - LONG $0x065cb60f; BYTE $0x0f // movzx ebx, byte [rsi + rax + 15] - LONG $0x6e0f4466; BYTE $0xf3 // movd xmm14, ebx + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x7cb60f41; WORD $0x0f06 // movzx edi, byte [r14 + rax + 15] + LONG $0x6e0f4466; BYTE $0xf7 // movd xmm14, edi LONG $0x640f4566; BYTE $0xf9 // pcmpgtb xmm15, xmm9 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x023674203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r14 + 2], 1 - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - QUAD $0x022674203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rsi + r12 + 2], 2 - WORD $0x894c; BYTE $0xda // mov rdx, r11 - QUAD $0x021e74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r11 + 2], 3 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x020674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r8 + 2], 4 - QUAD $0x05023e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 2], 5 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x022674203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r12 + 2], 6 - QUAD $0x000000c0248c894c // mov qword [rsp + 192], r9 - QUAD $0x020e74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r9 + 2], 7 - QUAD $0x0000008024948b4c // mov r10, qword [rsp + 128] - QUAD $0x021674203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r10 + 2], 8 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x021e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r11 + 2], 9 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x023e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r15 + 2], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 11 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0c021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0d021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 13 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x0e021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 14 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0f021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 15 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x020e74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rcx + 2], 1 + WORD $0x894d; BYTE $0xd5 // mov r13, r10 + QUAD $0x021674203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r14 + r10 + 2], 2 + LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] + QUAD $0x021674203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r10 + 2], 3 + WORD $0x8948; BYTE $0xf3 // mov rbx, rsi + QUAD $0x023674203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rsi + 2], 4 + QUAD $0x021674203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r14 + rdx + 2], 5 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x023674203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rsi + 2], 6 + QUAD $0x022674203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r12 + 2], 7 + QUAD $0x020674203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r8 + 2], 8 + LONG $0x244c894c; BYTE $0x70 // mov qword [rsp + 112], r9 + QUAD $0x020e74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r9 + 2], 9 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x023e74203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r14 + r15 + 2], 10 + QUAD $0x021e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r11 + 2], 11 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x022674203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r12 + 2], 12 + LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] + QUAD $0x021e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r11 + 2], 13 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x023e74203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rdi + 2], 14 + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x023e74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r14 + rdi + 2], 15 LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 LONG $0x640f4166; BYTE $0xf1 // pcmpgtb xmm6, xmm9 QUAD $0x000000b0856f0f66 // movdqa xmm0, oword 176[rbp] /* [rip + .LCPI7_11] */ LONG $0xf0db0f66 // pand xmm6, xmm0 LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x065cb60f; BYTE $0x10 // movzx ebx, byte [rsi + rax + 16] - LONG $0x6e0f4466; BYTE $0xfb // movd xmm15, ebx - QUAD $0x033654203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r14 + 3], 1 - QUAD $0x02030e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 3], 2 + LONG $0x7cb60f41; WORD $0x1006 // movzx edi, byte [r14 + rax + 16] + LONG $0x6e0f4466; BYTE $0xff // movd xmm15, edi + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x030e54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rcx + 3], 1 + QUAD $0x032e54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r13 + 3], 2 + QUAD $0x031654203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r10 + 3], 3 + QUAD $0x031e54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rbx + 3], 4 + QUAD $0x031654203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r14 + rdx + 3], 5 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + QUAD $0x033654203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rsi + 3], 6 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x033654203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rsi + 3], 7 + QUAD $0x030654203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r8 + 3], 8 + QUAD $0x030e54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r9 + 3], 9 + QUAD $0x033e54203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r14 + r15 + 3], 10 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x033e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 3], 11 + QUAD $0x032654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 3], 12 + QUAD $0x031e54203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r14 + r11 + 3], 13 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x033e54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rdi + 3], 14 + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + QUAD $0x033e54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rdi + 3], 15 + QUAD $0x04064c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rax + 4], 1 + QUAD $0x042e4c203a0f4366; BYTE $0x02 // pinsrb xmm1, byte [r14 + r13 + 4], 2 + QUAD $0x04164c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r14 + r10 + 4], 3 + QUAD $0x041e4c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r14 + rbx + 4], 4 + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x000000b0249c8948 // mov qword [rsp + 176], rbx + QUAD $0x04164c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r14 + rdx + 4], 5 WORD $0x8948; BYTE $0xd3 // mov rbx, rdx - QUAD $0x03031654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 3], 3 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - QUAD $0x030654203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r8 + 3], 4 - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - LONG $0x247c8948; BYTE $0x70 // mov qword [rsp + 112], rdi - QUAD $0x05033e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 3], 5 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x032654203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r12 + 3], 6 - QUAD $0x032e54203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rsi + r13 + 3], 7 - QUAD $0x031654203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r10 + 3], 8 - QUAD $0x031e54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r11 + 3], 9 - QUAD $0x033e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r15 + 3], 10 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x032654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r12 + 3], 11 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x032e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r13 + 3], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d030654203a0f66 // pinsrb xmm2, byte [rsi + rax + 3], 13 - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x030654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r8 + 3], 14 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x030654203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r8 + 3], 15 - QUAD $0x04364c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rsi + r14 + 4], 1 - QUAD $0x02040e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 4], 2 - QUAD $0x03041e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 4], 3 - QUAD $0x040e4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rsi + r9 + 4], 4 - QUAD $0x0504164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 4], 5 - QUAD $0x06043e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 4], 6 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - QUAD $0x0704064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 4], 7 - QUAD $0x04164c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r10 + 4], 8 - QUAD $0x041e4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r11 + 4], 9 - QUAD $0x043e4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r15 + 4], 10 - QUAD $0x04264c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r12 + 4], 11 - QUAD $0x042e4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r13 + 4], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d04064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 4], 13 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - QUAD $0x04364c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r14 + 4], 14 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - QUAD $0x04064c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r8 + 4], 15 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 + QUAD $0x040e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 4], 6 + QUAD $0x04364c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r14 + rsi + 4], 7 + QUAD $0x04064c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r8 + 4], 8 + QUAD $0x040e4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r9 + 4], 9 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + QUAD $0x040e4c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r14 + rcx + 4], 10 + QUAD $0x043e4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r14 + r15 + 4], 11 + QUAD $0x04264c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r12 + 4], 12 + QUAD $0x041e4c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r14 + r11 + 4], 13 + WORD $0x894d; BYTE $0xd9 // mov r9, r11 + LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] + QUAD $0x041e4c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r14 + r11 + 4], 14 + QUAD $0x043e4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rdi + 4], 15 LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - LONG $0x165cb60f; BYTE $0x11 // movzx ebx, byte [rsi + rdx + 17] - LONG $0xc36e0f66 // movd xmm0, ebx + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x7cb60f41; WORD $0x1106 // movzx edi, byte [r14 + rax + 17] + LONG $0xc76e0f66 // movd xmm0, edi LONG $0x640f4166; BYTE $0xd1 // pcmpgtb xmm2, xmm9 QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI7_12] */ LONG $0xd5db0f66 // pand xmm2, xmm5 @@ -37192,92 +39289,90 @@ LBB7_85: QUAD $0x000000d0ad6f0f66 // movdqa xmm5, oword 208[rbp] /* [rip + .LCPI7_13] */ LONG $0xcddb0f66 // pand xmm1, xmm5 LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0x165cb60f; BYTE $0x12 // movzx ebx, byte [rsi + rdx + 18] - LONG $0xeb6e0f66 // movd xmm5, ebx - LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] - QUAD $0x050644203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rsi + r8 + 5], 1 - QUAD $0x050e44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rcx + 5], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x053e44203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rdi + 5], 3 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x050e44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r9 + 5], 4 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x051644203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rsi + rdx + 5], 5 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x051644203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rsi + r10 + 5], 6 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x051e44203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rsi + r11 + 5], 7 - QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] - QUAD $0x052644203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r12 + 5], 8 - LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] - QUAD $0x052e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r13 + 5], 9 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x051e44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rsi + rbx + 5], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x051e44203a0f4466; BYTE $0x0b // pinsrb xmm8, byte [rsi + rbx + 5], 11 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x051e44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rsi + rbx + 5], 12 - QUAD $0x050644203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rax + 5], 13 - QUAD $0x053644203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r14 + 5], 14 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - QUAD $0x053e44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r15 + 5], 15 + LONG $0x7cb60f41; WORD $0x1206 // movzx edi, byte [r14 + rax + 18] + LONG $0xef6e0f66 // movd xmm5, edi + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x053e44203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r14 + r15 + 5], 1 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x051644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rdx + 5], 2 + QUAD $0x051644203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r14 + r10 + 5], 3 + QUAD $0x052e44203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r14 + r13 + 5], 4 + QUAD $0x051e44203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r14 + rbx + 5], 5 + LONG $0x245c8948; BYTE $0x68 // mov qword [rsp + 104], rbx + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x052644203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r14 + r12 + 5], 6 + QUAD $0x053644203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r14 + rsi + 5], 7 + QUAD $0x050644203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r8 + 5], 8 + LONG $0x24748b48; BYTE $0x70 // mov rsi, qword [rsp + 112] + QUAD $0x053644203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r14 + rsi + 5], 9 + QUAD $0x050e44203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rcx + 5], 10 + WORD $0x8948; BYTE $0xce // mov rsi, rcx + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x050e44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rcx + 5], 11 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x050e44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rcx + 5], 12 + QUAD $0x050e44203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r14 + r9 + 5], 13 + QUAD $0x051e44203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r14 + r11 + 5], 14 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x050e44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r9 + 5], 15 LONG $0x640f4566; BYTE $0xc1 // pcmpgtb xmm8, xmm9 QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI7_14] */ LONG $0xdb0f4466; BYTE $0xc2 // pand xmm8, xmm2 LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - LONG $0x065cb60f; BYTE $0x13 // movzx ebx, byte [rsi + rax + 19] - LONG $0xfb6e0f66 // movd xmm7, ebx + LONG $0x7cb60f41; WORD $0x1306 // movzx edi, byte [r14 + rax + 19] + LONG $0xff6e0f66 // movd xmm7, edi LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - LONG $0x065cb60f; BYTE $0x14 // movzx ebx, byte [rsi + rax + 20] - LONG $0xf36e0f66 // movd xmm6, ebx - QUAD $0x06065c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r8 + 6], 1 - QUAD $0x02060e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 6], 2 - WORD $0x8949; BYTE $0xfe // mov r14, rdi - QUAD $0x03063e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 6], 3 - WORD $0x894d; BYTE $0xcf // mov r15, r9 - QUAD $0x060e5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r9 + 6], 4 - QUAD $0x0506165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 6], 5 - WORD $0x894c; BYTE $0xd7 // mov rdi, r10 - QUAD $0x06165c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r10 + 6], 6 - WORD $0x894d; BYTE $0xd9 // mov r9, r11 - QUAD $0x061e5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r11 + 6], 7 - WORD $0x894d; BYTE $0xe2 // mov r10, r12 - QUAD $0x06265c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r12 + 6], 8 - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - QUAD $0x062e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r13 + 6], 9 - LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] - QUAD $0x0a06165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 6], 10 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x06265c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r12 + 6], 11 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x062e5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r13 + 6], 12 - LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] - QUAD $0x061e5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r11 + 6], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e06065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 6], 14 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f06065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 6], 15 - QUAD $0x0000a024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 160] - QUAD $0x070654203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r8 + 7], 1 - QUAD $0x02070e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 7], 2 - QUAD $0x073654203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r14 + 7], 3 - QUAD $0x073e54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r15 + 7], 4 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x05070654203a0f66 // pinsrb xmm2, byte [rsi + rax + 7], 5 - QUAD $0x06073e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 7], 6 - QUAD $0x070e54203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rsi + r9 + 7], 7 - QUAD $0x071654203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r10 + 7], 8 - QUAD $0x09071e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 7], 9 - QUAD $0x0a071654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 7], 10 - QUAD $0x072654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r12 + 7], 11 - QUAD $0x072e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r13 + 7], 12 - QUAD $0x071e54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r11 + 7], 13 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x0e073e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 7], 14 + LONG $0x7cb60f41; WORD $0x1406 // movzx edi, byte [r14 + rax + 20] + LONG $0xf76e0f66 // movd xmm6, edi + QUAD $0x063e5c203a0f4366; BYTE $0x01 // pinsrb xmm3, byte [r14 + r15 + 6], 1 + WORD $0x894d; BYTE $0xfd // mov r13, r15 + QUAD $0x06165c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rdx + 6], 2 + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + QUAD $0x06165c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r14 + r10 + 6], 3 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x06165c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r14 + rdx + 6], 4 + QUAD $0x061e5c203a0f4166; BYTE $0x05 // pinsrb xmm3, byte [r14 + rbx + 6], 5 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + QUAD $0x06265c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r14 + r12 + 6], 6 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x06065c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r14 + rax + 6], 7 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + QUAD $0x06065c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r8 + 6], 8 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x06065c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r8 + 6], 9 + QUAD $0x06365c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r14 + rsi + 6], 10 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x063e5c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rdi + 6], 11 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x06065c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r14 + rax + 6], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x061e5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rbx + 6], 13 + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + QUAD $0x063e5c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r14 + r15 + 6], 14 + QUAD $0x060e5c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r14 + r9 + 6], 15 + QUAD $0x0000c024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 192] + QUAD $0x072e54203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r14 + r13 + 7], 1 + QUAD $0x071e54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r11 + 7], 2 + QUAD $0x071654203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r10 + 7], 3 + WORD $0x894c; BYTE $0xd3 // mov rbx, r10 + QUAD $0x071654203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rdx + 7], 4 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x071654203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r14 + rdx + 7], 5 + QUAD $0x070e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 7], 6 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x070e54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rcx + 7], 7 + QUAD $0x072654203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r12 + 7], 8 + QUAD $0x0000014024a4894c // mov qword [rsp + 320], r12 + QUAD $0x070654203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r8 + 7], 9 + QUAD $0x073654203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r14 + rsi + 7], 10 + QUAD $0x073e54203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r14 + rdi + 7], 11 + QUAD $0x070654203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r14 + rax + 7], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x073654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rsi + 7], 13 + QUAD $0x073e54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r15 + 7], 14 LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0f071654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 7], 15 + QUAD $0x071654203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r14 + rdx + 7], 15 LONG $0x640f4166; BYTE $0xd9 // pcmpgtb xmm3, xmm9 QUAD $0x000000f08d6f0f66 // movdqa xmm1, oword 240[rbp] /* [rip + .LCPI7_15] */ LONG $0xd9db0f66 // pand xmm3, xmm1 @@ -37287,415 +39382,420 @@ LBB7_85: LONG $0xd1db0f66 // pand xmm2, xmm1 LONG $0xd3eb0f66 // por xmm2, xmm3 LONG $0xca6f0f66 // movdqa xmm1, xmm2 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - LONG $0x5cb60f42; WORD $0x1506 // movzx ebx, byte [rsi + r8 + 21] - LONG $0xd36e0f66 // movd xmm2, ebx - LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] - QUAD $0x090e54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r9 + 9], 1 - QUAD $0x090e54203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rcx + 9], 2 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x093e54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r15 + 9], 3 - QUAD $0x093654203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r14 + 9], 4 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x091e54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rsi + rbx + 9], 5 - LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] - QUAD $0x091e54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rbx + 9], 6 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x091654203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r10 + 9], 7 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x091e54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r11 + 9], 8 - LONG $0x245c8b48; BYTE $0x78 // mov rbx, qword [rsp + 120] - QUAD $0x091e54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rbx + 9], 9 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x091e54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rbx + 9], 10 - QUAD $0x092654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r12 + 9], 11 - QUAD $0x092e54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r13 + 9], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x091e54203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rsi + rbx + 9], 13 - QUAD $0x093e54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rdi + 9], 14 - QUAD $0x091654203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rsi + rdx + 9], 15 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x7cb60f41; WORD $0x1506 // movzx edi, byte [r14 + rax + 21] + LONG $0xd76e0f66 // movd xmm2, edi + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x090e54203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rcx + 9], 1 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x091654203a0f4766; BYTE $0x02 // pinsrb xmm10, byte [r14 + r10 + 9], 2 + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + QUAD $0x091e54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r14 + rbx + 9], 3 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x092e54203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r13 + 9], 4 + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] + QUAD $0x091e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r11 + 9], 5 + QUAD $0x090e54203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r9 + 9], 6 + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x091e54203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rbx + 9], 7 + QUAD $0x092654203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r14 + r12 + 9], 8 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x093e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r15 + 9], 9 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x092654203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r12 + 9], 10 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x093e54203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r14 + rdi + 9], 11 + LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] + QUAD $0x093e54203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r14 + rdi + 9], 12 + QUAD $0x093654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rsi + 9], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x093654203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rsi + 9], 14 + QUAD $0x091654203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r14 + rdx + 9], 15 LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - QUAD $0x0000a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm1 + QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 LONG $0x640f4566; BYTE $0xd1 // pcmpgtb xmm10, xmm9 LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 LONG $0xccdb0f66 // pand xmm1, xmm4 LONG $0xf80f4166; BYTE $0xca // psubb xmm1, xmm10 - LONG $0x5cb60f42; WORD $0x1606 // movzx ebx, byte [rsi + r8 + 22] - LONG $0xdb6e0f66 // movd xmm3, ebx - QUAD $0x00013024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 304] - WORD $0x894c; BYTE $0xcb // mov rbx, r9 - QUAD $0x080e64203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r9 + 8], 1 - QUAD $0x02080e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 8], 2 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - QUAD $0x083e64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r15 + 8], 3 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - QUAD $0x083664203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r14 + 8], 4 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x05081664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 8], 5 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x06083e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 8], 6 - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - QUAD $0x081664203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r10 + 8], 7 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x081e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r11 + 8], 8 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - QUAD $0x09080e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 8], 9 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0a080664203a0f66 // pinsrb xmm4, byte [rsi + rax + 8], 10 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x083664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r14 + 8], 11 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0c080664203a0f66 // pinsrb xmm4, byte [rsi + rax + 8], 12 - LONG $0x245c8b4c; BYTE $0x10 // mov r11, qword [rsp + 16] - QUAD $0x081e64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r11 + 8], 13 - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x080664203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r8 + 8], 14 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f080664203a0f66 // pinsrb xmm4, byte [rsi + rax + 8], 15 + LONG $0x7cb60f41; WORD $0x1606 // movzx edi, byte [r14 + rax + 22] + LONG $0xdf6e0f66 // movd xmm3, edi + QUAD $0x0000e024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 224] + QUAD $0x080e64203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rcx + 8], 1 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + QUAD $0x081664203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r14 + r10 + 8], 2 + QUAD $0x080664203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r14 + r8 + 8], 3 + QUAD $0x082e64203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r13 + 8], 4 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + QUAD $0x081e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r11 + 8], 5 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x081e64203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r14 + r11 + 8], 6 + QUAD $0x081e64203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r14 + rbx + 8], 7 + QUAD $0x0000014024848b48 // mov rax, qword [rsp + 320] + QUAD $0x080664203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r14 + rax + 8], 8 + WORD $0x894c; BYTE $0xff // mov rdi, r15 + QUAD $0x083e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r15 + 8], 9 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x082664203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r12 + 8], 10 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x080e64203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r14 + rcx + 8], 11 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x082664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r12 + 8], 12 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x080e64203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rcx + 8], 13 + QUAD $0x083664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rsi + 8], 14 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x080664203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r8 + 8], 15 LONG $0x640f4166; BYTE $0xe1 // pcmpgtb xmm4, xmm9 LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 - QUAD $0x00b024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 176] - QUAD $0x0a1e54203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rbx + 10], 1 - QUAD $0x0a2654203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r12 + 10], 2 - QUAD $0x0a3e54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r15 + 10], 3 - QUAD $0x0a2e54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rsi + r13 + 10], 4 - QUAD $0x0a1654203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rsi + rdx + 10], 5 - QUAD $0x0a3e54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rdi + 10], 6 - QUAD $0x0a0e54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r9 + 10], 7 - QUAD $0x0a1654203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r10 + 10], 8 - QUAD $0x0a0e54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rsi + rcx + 10], 9 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0a3e54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r15 + 10], 10 - QUAD $0x0a3654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r14 + 10], 11 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x0a2e54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r13 + 10], 12 - QUAD $0x0a1e54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r11 + 10], 13 - QUAD $0x0a0654203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r8 + 10], 14 - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - QUAD $0x0a0654203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rsi + rax + 10], 15 + QUAD $0x009024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 144] + QUAD $0x0a0e54203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r14 + r9 + 10], 1 + QUAD $0x0a1654203a0f4766; BYTE $0x02 // pinsrb xmm10, byte [r14 + r10 + 10], 2 + WORD $0x894c; BYTE $0xd3 // mov rbx, r10 + LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] + QUAD $0x0a1654203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r14 + r10 + 10], 3 + QUAD $0x0a2e54203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r14 + r13 + 10], 4 + QUAD $0x0a1654203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r14 + rdx + 10], 5 + WORD $0x894d; BYTE $0xd9 // mov r9, r11 + QUAD $0x0a1e54203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r14 + r11 + 10], 6 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0a1654203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rdx + 10], 7 + QUAD $0x0a0654203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r14 + rax + 10], 8 + WORD $0x8949; BYTE $0xc3 // mov r11, rax + QUAD $0x0a3e54203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r14 + rdi + 10], 9 + QUAD $0x0a3e54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r14 + r15 + 10], 10 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0a0654203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r14 + rax + 10], 11 + QUAD $0x0a2654203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r12 + 10], 12 + QUAD $0x0a0e54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rcx + 10], 13 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x0a2e54203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r14 + r13 + 10], 14 + QUAD $0x0a0654203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r8 + 10], 15 LONG $0x640f4566; BYTE $0xd1 // pcmpgtb xmm10, xmm9 QUAD $0x0000b095db0f4466; BYTE $0x00 // pand xmm10, oword 176[rbp] /* [rip + .LCPI7_11] */ LONG $0xeb0f4466; BYTE $0xd4 // por xmm10, xmm4 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - LONG $0x065cb60f; BYTE $0x17 // movzx ebx, byte [rsi + rax + 23] - LONG $0x6e0f4466; BYTE $0xc3 // movd xmm8, ebx + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + LONG $0x7cb60f41; WORD $0x170e // movzx edi, byte [r14 + rcx + 23] + LONG $0x6e0f4466; BYTE $0xc7 // movd xmm8, edi LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - QUAD $0x00b024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 176], xmm10 - LONG $0x065cb60f; BYTE $0x18 // movzx ebx, byte [rsi + rax + 24] - LONG $0x6e0f4466; BYTE $0xd3 // movd xmm10, ebx - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x0b365c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rsi + r14 + 11], 1 - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - QUAD $0x000000d024a4894c // mov qword [rsp + 208], r12 - QUAD $0x0b265c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rsi + r12 + 11], 2 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x0b065c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rsi + rax + 11], 3 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0b1e5c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rsi + rbx + 11], 4 - QUAD $0x0b165c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rsi + rdx + 11], 5 - QUAD $0x0b3e5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rsi + rdi + 11], 6 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - QUAD $0x0b0e5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r9 + 11], 7 - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - QUAD $0x0b165c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r10 + 11], 8 - LONG $0x24548b4c; BYTE $0x78 // mov r10, qword [rsp + 120] - QUAD $0x0b165c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r10 + 11], 9 - QUAD $0x0b3e5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rsi + r15 + 11], 10 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0b265c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r12 + 11], 11 - QUAD $0x0b2e5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r13 + 11], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0b1e5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rbx + 11], 13 - QUAD $0x0b1e5c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rsi + r11 + 11], 14 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0b1e5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rsi + r11 + 11], 15 - QUAD $0x0c366c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rsi + r14 + 12], 1 - QUAD $0x0c0e6c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rcx + 12], 2 - QUAD $0x0c066c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rsi + rax + 12], 3 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0c366c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r14 + 12], 4 - QUAD $0x0c166c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rsi + rdx + 12], 5 - QUAD $0x0c3e6c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rsi + rdi + 12], 6 - QUAD $0x0c066c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rsi + r8 + 12], 7 - QUAD $0x0c0e6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r9 + 12], 8 - QUAD $0x0c166c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r10 + 12], 9 - QUAD $0x0c3e6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rsi + r15 + 12], 10 - QUAD $0x0c266c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r12 + 12], 11 - QUAD $0x0c2e6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r13 + 12], 12 - QUAD $0x0c1e6c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rbx + 12], 13 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x0c1e6c203a0f4466; BYTE $0x0e // pinsrb xmm13, byte [rsi + rbx + 12], 14 - QUAD $0x0c1e6c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rsi + r11 + 12], 15 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0d0664203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rax + 13], 1 - QUAD $0x0d0e64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rcx + 13], 2 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0d0e64203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rsi + rcx + 13], 3 - QUAD $0x0d3664203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rsi + r14 + 13], 4 - QUAD $0x0d1664203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rsi + rdx + 13], 5 - QUAD $0x0d3e64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rdi + 13], 6 - QUAD $0x0d0664203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rsi + r8 + 13], 7 - QUAD $0x0d0e64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r9 + 13], 8 - QUAD $0x0d1664203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r10 + 13], 9 - QUAD $0x0d3e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r15 + 13], 10 - QUAD $0x0d2664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r12 + 13], 11 - QUAD $0x0d2e64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r13 + 13], 12 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0d3e64203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rsi + rdi + 13], 13 - QUAD $0x0d1e64203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rsi + rbx + 13], 14 - QUAD $0x0d1e64203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rsi + r11 + 13], 15 + QUAD $0x009024947f0f4466; WORD $0x0000 // movdqa oword [rsp + 144], xmm10 + LONG $0x7cb60f41; WORD $0x180e // movzx edi, byte [r14 + rcx + 24] + LONG $0x6e0f4466; BYTE $0xd7 // movd xmm10, edi + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0b365c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rsi + 11], 1 + QUAD $0x0b1e5c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rbx + 11], 2 + QUAD $0x0b165c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r14 + r10 + 11], 3 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x0b1e5c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rbx + 11], 4 + LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] + QUAD $0x0b165c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r10 + 11], 5 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + QUAD $0x0b0e5c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r14 + r9 + 11], 6 + QUAD $0x0b165c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rdx + 11], 7 + WORD $0x894d; BYTE $0xd8 // mov r8, r11 + QUAD $0x0b1e5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r11 + 11], 8 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x0b0e5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r9 + 11], 9 + WORD $0x894d; BYTE $0xfb // mov r11, r15 + QUAD $0x0b3e5c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r14 + r15 + 11], 10 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + QUAD $0x0b065c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r14 + rax + 11], 11 + QUAD $0x0b265c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r12 + 11], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0b065c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rax + 11], 13 + WORD $0x894c; BYTE $0xef // mov rdi, r13 + QUAD $0x0b2e5c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r13 + 11], 14 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0b165c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r14 + rdx + 11], 15 + QUAD $0x0c366c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rsi + 12], 1 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0c166c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rdx + 12], 2 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0c2e6c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r14 + r13 + 12], 3 + QUAD $0x0c1e6c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r14 + rbx + 12], 4 + QUAD $0x0c166c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r14 + r10 + 12], 5 + QUAD $0x0c0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 12], 6 + LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] + QUAD $0x0c2e6c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r14 + r13 + 12], 7 + QUAD $0x0c066c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r8 + 12], 8 + QUAD $0x0c0e6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r9 + 12], 9 + QUAD $0x0c1e6c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r14 + r11 + 12], 10 + QUAD $0x0c3e6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r14 + r15 + 12], 11 + QUAD $0x0c266c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r12 + 12], 12 + QUAD $0x0c066c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rax + 12], 13 + QUAD $0x0c3e6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r14 + rdi + 12], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0c066c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r14 + rax + 12], 15 + QUAD $0x0d3664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rsi + 13], 1 + QUAD $0x0d1664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rdx + 13], 2 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0d1664203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rdx + 13], 3 + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + QUAD $0x0d1e64203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r14 + rbx + 13], 4 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0d1664203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r14 + rdx + 13], 5 + QUAD $0x0d0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 13], 6 + QUAD $0x0d2e64203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r14 + r13 + 13], 7 + QUAD $0x0d0664203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r8 + 13], 8 + QUAD $0x0d0e64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r9 + 13], 9 + QUAD $0x0d1e64203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r14 + r11 + 13], 10 + QUAD $0x0d3e64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r14 + r15 + 13], 11 + QUAD $0x0d2664203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r12 + 13], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0d3664203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rsi + 13], 13 + QUAD $0x0d3e64203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r14 + rdi + 13], 14 + QUAD $0x0d0664203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r14 + rax + 13], 15 LONG $0x640f4566; BYTE $0xd9 // pcmpgtb xmm11, xmm9 QUAD $0x0000c09ddb0f4466; BYTE $0x00 // pand xmm11, oword 192[rbp] /* [rip + .LCPI7_12] */ LONG $0x640f4566; BYTE $0xe9 // pcmpgtb xmm13, xmm9 QUAD $0x0000d0addb0f4466; BYTE $0x00 // pand xmm13, oword 208[rbp] /* [rip + .LCPI7_13] */ LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - LONG $0x3e5cb60f; BYTE $0x19 // movzx ebx, byte [rsi + rdi + 25] - LONG $0xcb6e0f66 // movd xmm1, ebx + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + LONG $0x7cb60f41; WORD $0x1906 // movzx edi, byte [r14 + rax + 25] + LONG $0xcf6e0f66 // movd xmm1, edi LONG $0x640f4566; BYTE $0xe1 // pcmpgtb xmm12, xmm9 QUAD $0x0000e0a5db0f4466; BYTE $0x00 // pand xmm12, oword 224[rbp] /* [rip + .LCPI7_14] */ LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0x3e5cb60f; BYTE $0x1a // movzx ebx, byte [rsi + rdi + 26] - LONG $0x6e0f4466; BYTE $0xdb // movd xmm11, ebx - QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] - QUAD $0x010e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 14], 1 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x020e1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 14], 2 - WORD $0x8949; BYTE $0xcb // mov r11, rcx - QUAD $0x030e0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 14], 3 + LONG $0x7cb60f41; WORD $0x1a06 // movzx edi, byte [r14 + rax + 26] + LONG $0x6e0f4466; BYTE $0xdf // movd xmm11, edi + QUAD $0x00010024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 256] + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0e0664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rax + 14], 1 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0e2e64203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r14 + r13 + 14], 2 + QUAD $0x0e1664203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r14 + r10 + 14], 3 + QUAD $0x0e1e64203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rbx + 14], 4 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x0e1664203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r14 + rdx + 14], 5 + QUAD $0x0e0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 14], 6 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0e1664203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r14 + rdx + 14], 7 + QUAD $0x0e0664203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r8 + 14], 8 + QUAD $0x0e0e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r9 + 14], 9 + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + QUAD $0x0e1e64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r11 + 14], 10 + QUAD $0x0e3e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r15 + 14], 11 + QUAD $0x0e2664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r12 + 14], 12 + QUAD $0x0e3664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rsi + 14], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0e3664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rsi + 14], 14 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0e1e64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r11 + 14], 15 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0f3674203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r14 + rsi + 15], 1 + QUAD $0x0f2e74203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r14 + r13 + 15], 2 + QUAD $0x0f1674203a0f4766; BYTE $0x03 // pinsrb xmm14, byte [r14 + r10 + 15], 3 + QUAD $0x0f1e74203a0f4566; BYTE $0x04 // pinsrb xmm14, byte [r14 + rbx + 15], 4 + QUAD $0x0f0674203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r14 + rax + 15], 5 + QUAD $0x0f0e74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r14 + rcx + 15], 6 + QUAD $0x0f1674203a0f4566; BYTE $0x07 // pinsrb xmm14, byte [r14 + rdx + 15], 7 + QUAD $0x0f0674203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r14 + r8 + 15], 8 + QUAD $0x0f0e74203a0f4766; BYTE $0x09 // pinsrb xmm14, byte [r14 + r9 + 15], 9 + QUAD $0x0f3e74203a0f4566; BYTE $0x0a // pinsrb xmm14, byte [r14 + rdi + 15], 10 + QUAD $0x0f3e74203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r14 + r15 + 15], 11 + QUAD $0x0f2674203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r14 + r12 + 15], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0f3674203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r14 + rsi + 15], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x0f3674203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r14 + rsi + 15], 14 + QUAD $0x0f1e74203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r14 + r11 + 15], 15 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x10367c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rsi + 16], 1 + QUAD $0x102e7c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r14 + r13 + 16], 2 + QUAD $0x10167c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r14 + r10 + 16], 3 + QUAD $0x101e7c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r14 + rbx + 16], 4 + QUAD $0x10067c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r14 + rax + 16], 5 + QUAD $0x100e7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r14 + rcx + 16], 6 + QUAD $0x10167c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r14 + rdx + 16], 7 + QUAD $0x10067c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r8 + 16], 8 + QUAD $0x100e7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r14 + r9 + 16], 9 + QUAD $0x103e7c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r14 + rdi + 16], 10 + QUAD $0x103e7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r14 + r15 + 16], 11 + QUAD $0x10267c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r14 + r12 + 16], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x10367c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r14 + rsi + 16], 13 + LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] + QUAD $0x101e7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r14 + r11 + 16], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x113644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rsi + 17], 1 + QUAD $0x112e44203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r14 + r13 + 17], 2 + QUAD $0x111644203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r14 + r10 + 17], 3 + QUAD $0x111e44203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rbx + 17], 4 + QUAD $0x110644203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rax + 17], 5 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x110e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 17], 6 + QUAD $0x111644203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r14 + rdx + 17], 7 + QUAD $0x110644203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r8 + 17], 8 + QUAD $0x110e44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r9 + 17], 9 + QUAD $0x113e44203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rdi + 17], 10 + QUAD $0x113e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r15 + 17], 11 + QUAD $0x112644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r12 + 17], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x110644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rax + 17], 13 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x113644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rsi + 17], 14 + QUAD $0x009024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 144] LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x040e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 14], 4 - WORD $0x8948; BYTE $0xd1 // mov rcx, rdx - QUAD $0x050e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 14], 5 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x060e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 14], 6 - QUAD $0x0e0664203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r8 + 14], 7 - QUAD $0x0e0e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r9 + 14], 8 - QUAD $0x0e1664203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r10 + 14], 9 - QUAD $0x0e3e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r15 + 14], 10 - QUAD $0x0e2664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r12 + 14], 11 - QUAD $0x0e2e64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r13 + 14], 12 - LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] - QUAD $0x0e3664203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r14 + 14], 13 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x0e0e3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 14], 14 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0f0e3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 14], 15 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0f3e74203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rsi + rdi + 15], 1 - QUAD $0x0f1e74203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rsi + rbx + 15], 2 - QUAD $0x0f1e74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rsi + r11 + 15], 3 - QUAD $0x0f0674203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rsi + rax + 15], 4 - QUAD $0x0f0e74203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rsi + rcx + 15], 5 - QUAD $0x0f1674203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rsi + rdx + 15], 6 - QUAD $0x0f0674203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rsi + r8 + 15], 7 - QUAD $0x0f0e74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r9 + 15], 8 - QUAD $0x0f1674203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r10 + 15], 9 - QUAD $0x0f3e74203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rsi + r15 + 15], 10 - QUAD $0x0f2674203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rsi + r12 + 15], 11 - QUAD $0x0f2e74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rsi + r13 + 15], 12 - QUAD $0x0f3674203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rsi + r14 + 15], 13 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x0f3e74203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rsi + rdi + 15], 14 - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x0f3674203a0f4666; BYTE $0x0f // pinsrb xmm14, byte [rsi + r14 + 15], 15 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x103e7c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rdi + 16], 1 - QUAD $0x101e7c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rsi + rbx + 16], 2 - QUAD $0x101e7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rsi + r11 + 16], 3 - QUAD $0x10067c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rsi + rax + 16], 4 - QUAD $0x100e7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rcx + 16], 5 - QUAD $0x10167c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rdx + 16], 6 - QUAD $0x10067c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rsi + r8 + 16], 7 - QUAD $0x100e7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r9 + 16], 8 - QUAD $0x10167c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r10 + 16], 9 - QUAD $0x103e7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r15 + 16], 10 - QUAD $0x10267c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r12 + 16], 11 - QUAD $0x102e7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r13 + 16], 12 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x103e7c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rsi + rdi + 16], 13 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - QUAD $0x10367c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r14 + 16], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x01113e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 17], 1 - QUAD $0x02111e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 17], 2 - QUAD $0x111e44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r11 + 17], 3 - QUAD $0x04110644203a0f66 // pinsrb xmm0, byte [rsi + rax + 17], 4 - QUAD $0x05110e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 17], 5 - QUAD $0x06111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 6 - QUAD $0x110644203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r8 + 17], 7 - QUAD $0x110e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r9 + 17], 8 - QUAD $0x111644203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r10 + 17], 9 - QUAD $0x113e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r15 + 17], 10 - QUAD $0x112644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r12 + 17], 11 - QUAD $0x112e44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r13 + 17], 12 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0d113e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 17], 13 - QUAD $0x113644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r14 + 17], 14 - QUAD $0x00b024a4eb0f4466; WORD $0x0000 // por xmm12, oword [rsp + 176] - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - LONG $0x3e5cb60f; BYTE $0x1b // movzx ebx, byte [rsi + rdi + 27] - LONG $0x6e0f4466; BYTE $0xcb // movd xmm9, ebx - QUAD $0x009024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 144] + LONG $0x7cb60f41; WORD $0x1b06 // movzx edi, byte [r14 + rax + 27] + LONG $0x6e0f4466; BYTE $0xcf // movd xmm9, edi + QUAD $0x00a024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 160] LONG $0x640f4166; BYTE $0xe5 // pcmpgtb xmm4, xmm13 QUAD $0x000000f0a5db0f66 // pand xmm4, oword 240[rbp] /* [rip + .LCPI7_15] */ LONG $0x640f4566; BYTE $0xf5 // pcmpgtb xmm14, xmm13 LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI7_6] */ LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 - LONG $0x3e5cb60f; BYTE $0x1c // movzx ebx, byte [rsi + rdi + 28] - LONG $0xe36e0f66 // movd xmm4, ebx - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] - QUAD $0x113644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r14 + 17], 15 + LONG $0x7cb60f41; WORD $0x1c06 // movzx edi, byte [r14 + rax + 28] + LONG $0xe76e0f66 // movd xmm4, edi + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x111e44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r11 + 17], 15 LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 LONG $0x640f4166; BYTE $0xc5 // pcmpgtb xmm0, xmm13 LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI7_10] */ LONG $0xdb0f4566; BYTE $0xec // pand xmm13, xmm12 LONG $0xf80f4466; BYTE $0xe8 // psubb xmm13, xmm0 - QUAD $0x00b024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 176], xmm13 - LONG $0x3e5cb60f; BYTE $0x1d // movzx ebx, byte [rsi + rdi + 29] - LONG $0x6e0f4466; BYTE $0xeb // movd xmm13, ebx - QUAD $0x10367c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r14 + 16], 15 - QUAD $0x00009024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 144] + QUAD $0x009024ac7f0f4466; WORD $0x0000 // movdqa oword [rsp + 144], xmm13 + LONG $0x7cb60f41; WORD $0x1d06 // movzx edi, byte [r14 + rax + 29] + LONG $0x6e0f4466; BYTE $0xef // movd xmm13, edi + QUAD $0x101e7c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r14 + r11 + 16], 15 + QUAD $0x0000a024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 160] LONG $0x640f4466; BYTE $0xf8 // pcmpgtb xmm15, xmm0 LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x01123e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 18], 1 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x02121e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 18], 2 - QUAD $0x121e6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r11 + 18], 3 - QUAD $0x0412066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 18], 4 - QUAD $0x05120e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 18], 5 - QUAD $0x0612166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 18], 6 - QUAD $0x12066c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r8 + 18], 7 - QUAD $0x120e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r9 + 18], 8 - QUAD $0x12166c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r10 + 18], 9 - QUAD $0x123e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r15 + 18], 10 - QUAD $0x12266c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r12 + 18], 11 - QUAD $0x122e6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r13 + 18], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0d121e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 18], 13 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x0e121e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 18], 14 + QUAD $0x123e6c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rdi + 18], 1 + LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] + QUAD $0x123e6c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rdi + 18], 2 + QUAD $0x12166c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r10 + 18], 3 + QUAD $0x121e6c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rbx + 18], 4 + QUAD $0x122e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r13 + 18], 5 + QUAD $0x120e6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r14 + rcx + 18], 6 + QUAD $0x12166c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r14 + rdx + 18], 7 + QUAD $0x12066c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r8 + 18], 8 + QUAD $0x120e6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r9 + 18], 9 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x12066c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r14 + rax + 18], 10 + QUAD $0x123e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r15 + 18], 11 + QUAD $0x12266c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r14 + r12 + 18], 12 + LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] + QUAD $0x123e6c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rdi + 18], 13 + QUAD $0x12366c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rsi + 18], 14 LONG $0xdb0f4566; BYTE $0xfc // pand xmm15, xmm12 - QUAD $0x12366c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r14 + 18], 15 + QUAD $0x121e6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r11 + 18], 15 LONG $0xe8640f66 // pcmpgtb xmm5, xmm0 QUAD $0x000000b0addb0f66 // pand xmm5, oword 176[rbp] /* [rip + .LCPI7_11] */ LONG $0xeb0f4166; BYTE $0xef // por xmm5, xmm15 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - LONG $0x065cb60f; BYTE $0x1e // movzx ebx, byte [rsi + rax + 30] - LONG $0x6e0f4466; BYTE $0xe3 // movd xmm12, ebx - WORD $0x8948; BYTE $0xfb // mov rbx, rdi - QUAD $0x01133e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 19], 1 - QUAD $0x01143e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 20], 1 - QUAD $0x01153e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 21], 1 - QUAD $0x01163e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 22], 1 - QUAD $0x173e44203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rdi + 23], 1 - QUAD $0x183e54203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rdi + 24], 1 - QUAD $0x01193e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 25], 1 - QUAD $0x1a3e5c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rdi + 26], 1 - QUAD $0x1b3e4c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rdi + 27], 1 - QUAD $0x011c3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 28], 1 - QUAD $0x1d3e6c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rsi + rdi + 29], 1 - QUAD $0x1e3e64203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rdi + 30], 1 - LONG $0x067cb60f; BYTE $0x1f // movzx edi, byte [rsi + rax + 31] - LONG $0xc76e0f66 // movd xmm0, edi - QUAD $0x011f1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 31], 1 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x02133e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 19], 2 - QUAD $0x02143e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 20], 2 - QUAD $0x02153e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 21], 2 - QUAD $0x02163e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 22], 2 - QUAD $0x173e44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rdi + 23], 2 - QUAD $0x183e54203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rdi + 24], 2 - QUAD $0x02193e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 25], 2 - QUAD $0x1a3e5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rdi + 26], 2 - QUAD $0x1b3e4c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rdi + 27], 2 - QUAD $0x021c3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 28], 2 - QUAD $0x1d3e6c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rdi + 29], 2 - QUAD $0x1e3e64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rdi + 30], 2 - QUAD $0x021f3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 31], 2 - QUAD $0x131e7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rsi + r11 + 19], 3 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0413067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 19], 4 - QUAD $0x05130e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 19], 5 - QUAD $0x0613167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 19], 6 - QUAD $0x13067c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rsi + r8 + 19], 7 - QUAD $0x130e7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r9 + 19], 8 - QUAD $0x13167c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r10 + 19], 9 - QUAD $0x133e7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r15 + 19], 10 - QUAD $0x13267c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r12 + 19], 11 - QUAD $0x132e7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r13 + 19], 12 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0d133e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 19], 13 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x0e131e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 19], 14 - QUAD $0x13367c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r14 + 19], 15 - QUAD $0x141e74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r11 + 20], 3 - QUAD $0x04140674203a0f66 // pinsrb xmm6, byte [rsi + rax + 20], 4 - QUAD $0x05140e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 20], 5 - QUAD $0x06141674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 20], 6 - QUAD $0x140674203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r8 + 20], 7 - QUAD $0x140e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r9 + 20], 8 - QUAD $0x141674203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r10 + 20], 9 - QUAD $0x143e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r15 + 20], 10 - QUAD $0x142674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r12 + 20], 11 - QUAD $0x142e74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r13 + 20], 12 - QUAD $0x0d143e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 20], 13 - QUAD $0x0e141e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 20], 14 - QUAD $0x0000b024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 176] - QUAD $0x143674203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r14 + 20], 15 - QUAD $0x009024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 144] + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + LONG $0x7cb60f41; WORD $0x1e36 // movzx edi, byte [r14 + rsi + 30] + LONG $0x6e0f4466; BYTE $0xe7 // movd xmm12, edi + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x133e7c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rdi + 19], 1 + QUAD $0x143e74203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rdi + 20], 1 + QUAD $0x153e54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rdi + 21], 1 + QUAD $0x163e5c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rdi + 22], 1 + QUAD $0x173e44203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rdi + 23], 1 + QUAD $0x183e54203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r14 + rdi + 24], 1 + QUAD $0x193e4c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rdi + 25], 1 + QUAD $0x1a3e5c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rdi + 26], 1 + QUAD $0x1b3e4c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rdi + 27], 1 + QUAD $0x1c3e64203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rdi + 28], 1 + QUAD $0x1d3e6c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r14 + rdi + 29], 1 + QUAD $0x1e3e64203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rdi + 30], 1 + LONG $0x74b60f41; WORD $0x1f36 // movzx esi, byte [r14 + rsi + 31] + LONG $0xc66e0f66 // movd xmm0, esi + QUAD $0x1f3e44203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rdi + 31], 1 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x13367c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rsi + 19], 2 + QUAD $0x143674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rsi + 20], 2 + QUAD $0x153654203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r14 + rsi + 21], 2 + QUAD $0x16365c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rsi + 22], 2 + QUAD $0x173644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rsi + 23], 2 + QUAD $0x183654203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r14 + rsi + 24], 2 + QUAD $0x19364c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rsi + 25], 2 + QUAD $0x1a365c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rsi + 26], 2 + QUAD $0x1b364c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rsi + 27], 2 + QUAD $0x1c3664203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rsi + 28], 2 + QUAD $0x1d366c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r14 + rsi + 29], 2 + QUAD $0x1e3664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rsi + 30], 2 + QUAD $0x1f3644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rsi + 31], 2 + QUAD $0x13167c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r14 + r10 + 19], 3 + QUAD $0x131e7c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r14 + rbx + 19], 4 + QUAD $0x132e7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r14 + r13 + 19], 5 + QUAD $0x130e7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r14 + rcx + 19], 6 + QUAD $0x13167c203a0f4166; BYTE $0x07 // pinsrb xmm7, byte [r14 + rdx + 19], 7 + QUAD $0x13067c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r8 + 19], 8 + QUAD $0x130e7c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r9 + 19], 9 + QUAD $0x13067c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r14 + rax + 19], 10 + QUAD $0x133e7c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r14 + r15 + 19], 11 + QUAD $0x13267c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r14 + r12 + 19], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x13367c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rsi + 19], 13 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x133e7c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r14 + rdi + 19], 14 + QUAD $0x131e7c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r14 + r11 + 19], 15 + QUAD $0x141674203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r10 + 20], 3 + QUAD $0x141e74203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rbx + 20], 4 + QUAD $0x142e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r13 + 20], 5 + QUAD $0x140e74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rcx + 20], 6 + QUAD $0x141674203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r14 + rdx + 20], 7 + QUAD $0x140674203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r8 + 20], 8 + QUAD $0x140e74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r9 + 20], 9 + QUAD $0x140674203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r14 + rax + 20], 10 + QUAD $0x143e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r15 + 20], 11 + QUAD $0x142674203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r12 + 20], 12 + QUAD $0x143674203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r14 + rsi + 20], 13 + QUAD $0x143e74203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rdi + 20], 14 + QUAD $0x00009024aceb0f66; BYTE $0x00 // por xmm5, oword [rsp + 144] + QUAD $0x141e74203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r14 + r11 + 20], 15 + QUAD $0x00a024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 160] LONG $0x640f4166; BYTE $0xff // pcmpgtb xmm7, xmm15 QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI7_12] */ LONG $0x640f4166; BYTE $0xf7 // pcmpgtb xmm6, xmm15 QUAD $0x000000d0b5db0f66 // pand xmm6, oword 208[rbp] /* [rip + .LCPI7_13] */ LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0x151e54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r11 + 21], 3 - QUAD $0x04150654203a0f66 // pinsrb xmm2, byte [rsi + rax + 21], 4 - QUAD $0x05150e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 21], 5 - QUAD $0x06151654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 21], 6 - QUAD $0x150654203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rsi + r8 + 21], 7 - QUAD $0x150e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r9 + 21], 8 - QUAD $0x151654203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r10 + 21], 9 - QUAD $0x153e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r15 + 21], 10 - QUAD $0x152654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r12 + 21], 11 - QUAD $0x152e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r13 + 21], 12 - QUAD $0x0d153e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 21], 13 - QUAD $0x0e151e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 21], 14 - QUAD $0x153654203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r14 + 21], 15 + QUAD $0x151654203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r14 + r10 + 21], 3 + QUAD $0x151e54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rbx + 21], 4 + QUAD $0x152e54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r14 + r13 + 21], 5 + QUAD $0x150e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 21], 6 + QUAD $0x151654203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rdx + 21], 7 + QUAD $0x150654203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r8 + 21], 8 + QUAD $0x150e54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r9 + 21], 9 + QUAD $0x150654203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r14 + rax + 21], 10 + QUAD $0x153e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 21], 11 + QUAD $0x152654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r12 + 21], 12 + QUAD $0x153654203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r14 + rsi + 21], 13 + QUAD $0x153e54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r14 + rdi + 21], 14 + QUAD $0x151e54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r11 + 21], 15 LONG $0x640f4166; BYTE $0xd7 // pcmpgtb xmm2, xmm15 QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI7_14] */ LONG $0xd7db0f66 // pand xmm2, xmm7 LONG $0xd6eb0f66 // por xmm2, xmm6 LONG $0xd5eb0f66 // por xmm2, xmm5 - QUAD $0x161e5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r11 + 22], 3 - QUAD $0x0416065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 22], 4 - QUAD $0x05160e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 22], 5 - QUAD $0x0616165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 22], 6 - QUAD $0x16065c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r8 + 22], 7 - QUAD $0x160e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r9 + 22], 8 - QUAD $0x16165c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r10 + 22], 9 - QUAD $0x163e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r15 + 22], 10 - QUAD $0x16265c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r12 + 22], 11 - QUAD $0x162e5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r13 + 22], 12 - QUAD $0x0d163e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 22], 13 - QUAD $0x0e161e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 22], 14 - QUAD $0x16365c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r14 + 22], 15 - QUAD $0x171e44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rsi + r11 + 23], 3 - QUAD $0x170644203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rax + 23], 4 - QUAD $0x170e44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rsi + rcx + 23], 5 - QUAD $0x171644203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rdx + 23], 6 - QUAD $0x170644203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rsi + r8 + 23], 7 - QUAD $0x170e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r9 + 23], 8 - QUAD $0x171644203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r10 + 23], 9 - QUAD $0x173e44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r15 + 23], 10 - QUAD $0x172644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r12 + 23], 11 - QUAD $0x172e44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r13 + 23], 12 - QUAD $0x173e44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rdi + 23], 13 - QUAD $0x171e44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rbx + 23], 14 - QUAD $0x173644203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r14 + 23], 15 + QUAD $0x16165c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r14 + r10 + 22], 3 + QUAD $0x161e5c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r14 + rbx + 22], 4 + QUAD $0x162e5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r13 + 22], 5 + QUAD $0x160e5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r14 + rcx + 22], 6 + QUAD $0x16165c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r14 + rdx + 22], 7 + QUAD $0x16065c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r8 + 22], 8 + QUAD $0x160e5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r9 + 22], 9 + QUAD $0x16065c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r14 + rax + 22], 10 + QUAD $0x163e5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r14 + r15 + 22], 11 + QUAD $0x16265c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r14 + r12 + 22], 12 + QUAD $0x16365c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r14 + rsi + 22], 13 + QUAD $0x163e5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r14 + rdi + 22], 14 + QUAD $0x161e5c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r14 + r11 + 22], 15 + QUAD $0x171644203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r14 + r10 + 23], 3 + QUAD $0x171e44203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r14 + rbx + 23], 4 + QUAD $0x172e44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r14 + r13 + 23], 5 + QUAD $0x170e44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r14 + rcx + 23], 6 + QUAD $0x171644203a0f4566; BYTE $0x07 // pinsrb xmm8, byte [r14 + rdx + 23], 7 + QUAD $0x170644203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r8 + 23], 8 + QUAD $0x170e44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r9 + 23], 9 + QUAD $0x170644203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rax + 23], 10 + QUAD $0x173e44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r14 + r15 + 23], 11 + QUAD $0x172644203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r14 + r12 + 23], 12 + QUAD $0x173644203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rsi + 23], 13 + QUAD $0x173e44203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rdi + 23], 14 + QUAD $0x171e44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r11 + 23], 15 LONG $0x640f4166; BYTE $0xdf // pcmpgtb xmm3, xmm15 QUAD $0x000000f0ad6f0f66 // movdqa xmm5, oword 240[rbp] /* [rip + .LCPI7_15] */ LONG $0xdddb0f66 // pand xmm3, xmm5 @@ -37704,131 +39804,132 @@ LBB7_85: LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI7_6] */ LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 - QUAD $0x191e4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rsi + r11 + 25], 3 - QUAD $0x0419064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 25], 4 - QUAD $0x05190e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 25], 5 - QUAD $0x0619164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 25], 6 - QUAD $0x19064c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rsi + r8 + 25], 7 - QUAD $0x190e4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r9 + 25], 8 - QUAD $0x19164c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r10 + 25], 9 - QUAD $0x193e4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r15 + 25], 10 - QUAD $0x19264c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r12 + 25], 11 - QUAD $0x192e4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r13 + 25], 12 - QUAD $0x0d193e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 25], 13 - QUAD $0x0e191e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 25], 14 - QUAD $0x19364c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r14 + 25], 15 + QUAD $0x19164c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r14 + r10 + 25], 3 + QUAD $0x191e4c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r14 + rbx + 25], 4 + QUAD $0x192e4c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r14 + r13 + 25], 5 + QUAD $0x190e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rcx + 25], 6 + QUAD $0x19164c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r14 + rdx + 25], 7 + QUAD $0x19064c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r8 + 25], 8 + QUAD $0x190e4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r9 + 25], 9 + QUAD $0x19064c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r14 + rax + 25], 10 + QUAD $0x193e4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r14 + r15 + 25], 11 + QUAD $0x19264c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r12 + 25], 12 + QUAD $0x19364c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r14 + rsi + 25], 13 + QUAD $0x193e4c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r14 + rdi + 25], 14 + QUAD $0x191e4c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r14 + r11 + 25], 15 LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 LONG $0x640f4166; BYTE $0xcf // pcmpgtb xmm1, xmm15 LONG $0xd16f0f66 // movdqa xmm2, xmm1 QUAD $0x000000a09d6f0f66 // movdqa xmm3, oword 160[rbp] /* [rip + .LCPI7_10] */ LONG $0xd3db0f66 // pand xmm2, xmm3 LONG $0xd1f80f66 // psubb xmm2, xmm1 - QUAD $0x181e54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r11 + 24], 3 - QUAD $0x180654203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rax + 24], 4 - QUAD $0x180e54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rsi + rcx + 24], 5 - QUAD $0x181654203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rdx + 24], 6 - QUAD $0x180654203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rsi + r8 + 24], 7 - QUAD $0x180e54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r9 + 24], 8 - QUAD $0x181654203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r10 + 24], 9 - QUAD $0x183e54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r15 + 24], 10 - QUAD $0x182654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r12 + 24], 11 - QUAD $0x182e54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r13 + 24], 12 - QUAD $0x183e54203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rsi + rdi + 24], 13 - QUAD $0x181e54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rbx + 24], 14 - QUAD $0x183654203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r14 + 24], 15 + QUAD $0x181654203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r14 + r10 + 24], 3 + QUAD $0x181e54203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r14 + rbx + 24], 4 + QUAD $0x182e54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r14 + r13 + 24], 5 + QUAD $0x180e54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r14 + rcx + 24], 6 + QUAD $0x181654203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r14 + rdx + 24], 7 + QUAD $0x180654203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r14 + r8 + 24], 8 + QUAD $0x180e54203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r14 + r9 + 24], 9 + QUAD $0x180654203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r14 + rax + 24], 10 + QUAD $0x183e54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r14 + r15 + 24], 11 + QUAD $0x182654203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r14 + r12 + 24], 12 + QUAD $0x183654203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r14 + rsi + 24], 13 + QUAD $0x183e54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r14 + rdi + 24], 14 + QUAD $0x181e54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r14 + r11 + 24], 15 LONG $0x640f4566; BYTE $0xd7 // pcmpgtb xmm10, xmm15 LONG $0xdb0f4466; BYTE $0xd3 // pand xmm10, xmm3 - QUAD $0x1a1e5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r11 + 26], 3 - QUAD $0x1a065c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rsi + rax + 26], 4 - QUAD $0x1a0e5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rsi + rcx + 26], 5 - QUAD $0x1a165c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rsi + rdx + 26], 6 - QUAD $0x1a065c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r8 + 26], 7 - QUAD $0x1a0e5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r9 + 26], 8 - QUAD $0x1a165c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r10 + 26], 9 - QUAD $0x1a3e5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rsi + r15 + 26], 10 - QUAD $0x1a265c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r12 + 26], 11 - QUAD $0x1a2e5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r13 + 26], 12 - QUAD $0x1a3e5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rdi + 26], 13 - QUAD $0x1a1e5c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rsi + rbx + 26], 14 - QUAD $0x1a365c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rsi + r14 + 26], 15 + QUAD $0x1a165c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r14 + r10 + 26], 3 + QUAD $0x1a1e5c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r14 + rbx + 26], 4 + QUAD $0x1a2e5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r14 + r13 + 26], 5 + QUAD $0x1a0e5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r14 + rcx + 26], 6 + QUAD $0x1a165c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rdx + 26], 7 + QUAD $0x1a065c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r8 + 26], 8 + QUAD $0x1a0e5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r9 + 26], 9 + QUAD $0x1a065c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r14 + rax + 26], 10 + QUAD $0x1a3e5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r14 + r15 + 26], 11 + QUAD $0x1a265c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r12 + 26], 12 + QUAD $0x1a365c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r14 + rsi + 26], 13 + QUAD $0x1a3e5c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r14 + rdi + 26], 14 + QUAD $0x1a1e5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r11 + 26], 15 LONG $0x640f4566; BYTE $0xdf // pcmpgtb xmm11, xmm15 QUAD $0x0000b09ddb0f4466; BYTE $0x00 // pand xmm11, oword 176[rbp] /* [rip + .LCPI7_11] */ LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 LONG $0xeb0f4466; BYTE $0xda // por xmm11, xmm2 - QUAD $0x1b1e4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r11 + 27], 3 - QUAD $0x1b064c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rsi + rax + 27], 4 - QUAD $0x1b0e4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rsi + rcx + 27], 5 - QUAD $0x1b164c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rdx + 27], 6 - QUAD $0x1b064c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rsi + r8 + 27], 7 - QUAD $0x1b0e4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r9 + 27], 8 - QUAD $0x1b164c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r10 + 27], 9 - QUAD $0x1b3e4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r15 + 27], 10 - QUAD $0x1b264c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r12 + 27], 11 - QUAD $0x1b2e4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r13 + 27], 12 - QUAD $0x1b3e4c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rsi + rdi + 27], 13 - QUAD $0x1b1e4c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rsi + rbx + 27], 14 - QUAD $0x1b364c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r14 + 27], 15 - QUAD $0x1c1e64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r11 + 28], 3 - QUAD $0x041c0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 28], 4 - QUAD $0x051c0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 28], 5 - QUAD $0x061c1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 28], 6 - QUAD $0x1c0664203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r8 + 28], 7 - QUAD $0x1c0e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r9 + 28], 8 - QUAD $0x1c1664203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r10 + 28], 9 - QUAD $0x1c3e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r15 + 28], 10 - QUAD $0x1c2664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r12 + 28], 11 - QUAD $0x1c2e64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r13 + 28], 12 - QUAD $0x0d1c3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 28], 13 - QUAD $0x0e1c1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 28], 14 - QUAD $0x1c3664203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r14 + 28], 15 - QUAD $0x1d1e6c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rsi + r11 + 29], 3 - QUAD $0x1d066c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rsi + rax + 29], 4 - QUAD $0x1d0e6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rsi + rcx + 29], 5 - QUAD $0x1d166c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rsi + rdx + 29], 6 - QUAD $0x1d066c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rsi + r8 + 29], 7 - QUAD $0x1d0e6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r9 + 29], 8 - QUAD $0x1d166c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r10 + 29], 9 - QUAD $0x1d3e6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rsi + r15 + 29], 10 - QUAD $0x1d266c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r12 + 29], 11 - QUAD $0x1d2e6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r13 + 29], 12 - QUAD $0x1d3e6c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rdi + 29], 13 - QUAD $0x1d1e6c203a0f4466; BYTE $0x0e // pinsrb xmm13, byte [rsi + rbx + 29], 14 + QUAD $0x1b164c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r14 + r10 + 27], 3 + QUAD $0x1b1e4c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r14 + rbx + 27], 4 + QUAD $0x1b2e4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r14 + r13 + 27], 5 + QUAD $0x1b0e4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r14 + rcx + 27], 6 + QUAD $0x1b164c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r14 + rdx + 27], 7 + QUAD $0x1b064c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r8 + 27], 8 + QUAD $0x1b0e4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r14 + r9 + 27], 9 + QUAD $0x1b064c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r14 + rax + 27], 10 + QUAD $0x1b3e4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r14 + r15 + 27], 11 + QUAD $0x1b264c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r14 + r12 + 27], 12 + QUAD $0x1b364c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r14 + rsi + 27], 13 + QUAD $0x1b3e4c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rdi + 27], 14 + QUAD $0x1b1e4c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r14 + r11 + 27], 15 + QUAD $0x1c1664203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r14 + r10 + 28], 3 + QUAD $0x1c1e64203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rbx + 28], 4 + QUAD $0x1c2e64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r14 + r13 + 28], 5 + QUAD $0x1c0e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rcx + 28], 6 + QUAD $0x1c1664203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r14 + rdx + 28], 7 + QUAD $0x1c0664203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r8 + 28], 8 + QUAD $0x1c0e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r9 + 28], 9 + QUAD $0x1c0664203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r14 + rax + 28], 10 + QUAD $0x1c3e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r15 + 28], 11 + QUAD $0x1c2664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r12 + 28], 12 + QUAD $0x1c3664203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r14 + rsi + 28], 13 + QUAD $0x1c3e64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rdi + 28], 14 + QUAD $0x1c1e64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r11 + 28], 15 + QUAD $0x1d166c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r14 + r10 + 29], 3 + QUAD $0x1d1e6c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r14 + rbx + 29], 4 + QUAD $0x1d2e6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r14 + r13 + 29], 5 + QUAD $0x1d0e6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rcx + 29], 6 + QUAD $0x1d166c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r14 + rdx + 29], 7 + QUAD $0x1d066c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r8 + 29], 8 + QUAD $0x1d0e6c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r14 + r9 + 29], 9 + QUAD $0x1d066c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r14 + rax + 29], 10 + QUAD $0x1d3e6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r14 + r15 + 29], 11 + QUAD $0x1d266c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r12 + 29], 12 + QUAD $0x1d366c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rsi + 29], 13 + QUAD $0x1d3e6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r14 + rdi + 29], 14 LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 LONG $0x640f4566; BYTE $0xcf // pcmpgtb xmm9, xmm15 QUAD $0x0000c08ddb0f4466; BYTE $0x00 // pand xmm9, oword 192[rbp] /* [rip + .LCPI7_12] */ LONG $0x640f4166; BYTE $0xe7 // pcmpgtb xmm4, xmm15 QUAD $0x000000d0a5db0f66 // pand xmm4, oword 208[rbp] /* [rip + .LCPI7_13] */ LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 - QUAD $0x1d366c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rsi + r14 + 29], 15 + QUAD $0x1d1e6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r14 + r11 + 29], 15 LONG $0x640f4566; BYTE $0xef // pcmpgtb xmm13, xmm15 LONG $0xdb0f4466; BYTE $0xef // pand xmm13, xmm7 LONG $0xeb0f4466; BYTE $0xec // por xmm13, xmm4 - QUAD $0x1e1e64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rsi + r11 + 30], 3 - QUAD $0x1f1e44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r11 + 31], 3 - QUAD $0x1e0664203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rsi + rax + 30], 4 - QUAD $0x041f0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 31], 4 - QUAD $0x1e0e64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rsi + rcx + 30], 5 - QUAD $0x051f0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 31], 5 - QUAD $0x1e1664203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rsi + rdx + 30], 6 - QUAD $0x061f1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 31], 6 - QUAD $0x1e0664203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rsi + r8 + 30], 7 - QUAD $0x1f0644203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r8 + 31], 7 - QUAD $0x1e0e64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r9 + 30], 8 - QUAD $0x1f0e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r9 + 31], 8 - QUAD $0x1e1664203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r10 + 30], 9 - QUAD $0x1f1644203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r10 + 31], 9 - QUAD $0x1e3e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r15 + 30], 10 - QUAD $0x1f3e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r15 + 31], 10 - QUAD $0x1e2664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r12 + 30], 11 - QUAD $0x1f2644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r12 + 31], 11 - QUAD $0x1e2e64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r13 + 30], 12 - QUAD $0x1f2e44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r13 + 31], 12 - QUAD $0x1e3e64203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rsi + rdi + 30], 13 - QUAD $0x0d1f3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 31], 13 - QUAD $0x1e1e64203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rsi + rbx + 30], 14 - QUAD $0x0e1f1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 31], 14 - QUAD $0x1e3664203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rsi + r14 + 30], 15 - QUAD $0x1f3644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r14 + 31], 15 + QUAD $0x1e1664203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r14 + r10 + 30], 3 + QUAD $0x1f1644203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r14 + r10 + 31], 3 + QUAD $0x1e1e64203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r14 + rbx + 30], 4 + QUAD $0x1f1e44203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rbx + 31], 4 + QUAD $0x1e2e64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r14 + r13 + 30], 5 + QUAD $0x1f2e44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r13 + 31], 5 + QUAD $0x1e0e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rcx + 30], 6 + QUAD $0x1f0e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rcx + 31], 6 + QUAD $0x1e1664203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r14 + rdx + 30], 7 + QUAD $0x1f1644203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r14 + rdx + 31], 7 + QUAD $0x1e0664203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r14 + r8 + 30], 8 + QUAD $0x1f0644203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r8 + 31], 8 + QUAD $0x1e0e64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r9 + 30], 9 + QUAD $0x1f0e44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r9 + 31], 9 + QUAD $0x1e0664203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r14 + rax + 30], 10 + QUAD $0x1f0644203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rax + 31], 10 + QUAD $0x1e3e64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r14 + r15 + 30], 11 + QUAD $0x1f3e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r15 + 31], 11 + QUAD $0x1e2664203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r14 + r12 + 30], 12 + QUAD $0x1f2644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r12 + 31], 12 + QUAD $0x1e3664203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r14 + rsi + 30], 13 + QUAD $0x1f3644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rsi + 31], 13 + QUAD $0x1e3e64203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r14 + rdi + 30], 14 + QUAD $0x1f3e44203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rdi + 31], 14 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x1e1e64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r14 + r11 + 30], 15 + QUAD $0x1f1e44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r11 + 31], 15 LONG $0xeb0f4566; BYTE $0xeb // por xmm13, xmm11 LONG $0x640f4566; BYTE $0xe7 // pcmpgtb xmm12, xmm15 LONG $0xdb0f4466; BYTE $0xe5 // pand xmm12, xmm5 @@ -37839,7 +39940,7 @@ LBB7_85: LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 LONG $0xc8600f66 // punpcklbw xmm1, xmm0 - QUAD $0x0000a024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 160] + QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] LONG $0xd46f0f66 // movdqa xmm2, xmm4 LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 LONG $0xda6f0f66 // movdqa xmm3, xmm2 @@ -37850,1971 +39951,1035 @@ LBB7_85: LONG $0xc46f0f66 // movdqa xmm0, xmm4 LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0x647f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm4 - LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 - LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 - LONG $0x1c7f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm3 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x7f0f41f3; WORD $0x8c64; BYTE $0x30 // movdqu oword [r12 + 4*rcx + 48], xmm4 + LONG $0x7f0f41f3; WORD $0x8c44; BYTE $0x20 // movdqu oword [r12 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x8c54; BYTE $0x10 // movdqu oword [r12 + 4*rcx + 16], xmm2 + LONG $0x7f0f41f3; WORD $0x8c1c // movdqu oword [r12 + 4*rcx], xmm3 LONG $0x10c18348 // add rcx, 16 WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB7_85 - QUAD $0x0000012024948b4c // mov r10, qword [rsp + 288] - QUAD $0x000000e824943b4c // cmp r10, qword [rsp + 232] - LONG $0x24648a44; BYTE $0x08 // mov r12b, byte [rsp + 8] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - JNE LBB7_87 - JMP LBB7_90 + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + JNE LBB7_98 + QUAD $0x00000118248c8b48 // mov rcx, qword [rsp + 280] + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x246c8a44; BYTE $0x08 // mov r13b, byte [rsp + 8] + QUAD $0x0000013824b48b48 // mov rsi, qword [rsp + 312] + JNE LBB7_100 + JMP LBB7_103 -LBB7_66: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB7_71: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000014024848948 // mov qword [rsp + 320], rax - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax - LONG $0xc2b60f41 // movzx eax, r10b + WORD $0x014c; BYTE $0xf0 // add rax, r14 + QUAD $0x0000015024848948 // mov qword [rsp + 336], rax + QUAD $0x000000f8248c8948 // mov qword [rsp + 248], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x000001182484b60f // movzx eax, byte [rsp + 280] LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 QUAD $0x000120248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm1 WORD $0xc031 // xor eax, eax + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 -LBB7_67: - QUAD $0x000000b024848948 // mov qword [rsp + 176], rax - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] +LBB7_72: + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] LONG $0x05e0c148 // shl rax, 5 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - WORD $0x8949; BYTE $0xc6 // mov r14, rax - WORD $0x8948; BYTE $0xc2 // mov rdx, rax + WORD $0x8949; BYTE $0xc0 // mov r8, rax WORD $0x8948; BYTE $0xc7 // mov rdi, rax - WORD $0x8949; BYTE $0xc5 // mov r13, rax WORD $0x8949; BYTE $0xc1 // mov r9, rax - WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + WORD $0x8949; BYTE $0xc4 // mov r12, rax WORD $0x8949; BYTE $0xc3 // mov r11, rax WORD $0x8949; BYTE $0xc7 // mov r15, rax - WORD $0x8949; BYTE $0xc0 // mov r8, rax - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x060cb60f // movzx ecx, byte [rsi + rax] + WORD $0x8949; BYTE $0xc2 // mov r10, rax + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax + LONG $0x0cb60f41; BYTE $0x06 // movzx ecx, byte [r14 + rax] LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x064cb60f; BYTE $0x01 // movzx ecx, byte [rsi + rax + 1] + LONG $0x4cb60f41; WORD $0x0106 // movzx ecx, byte [r14 + rax + 1] LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x064cb60f; BYTE $0x02 // movzx ecx, byte [rsi + rax + 2] + LONG $0x4cb60f41; WORD $0x0206 // movzx ecx, byte [r14 + rax + 2] LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x064cb60f; BYTE $0x03 // movzx ecx, byte [rsi + rax + 3] + LONG $0x4cb60f41; WORD $0x0306 // movzx ecx, byte [r14 + rax + 3] LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x064cb60f; BYTE $0x04 // movzx ecx, byte [rsi + rax + 4] + LONG $0x4cb60f41; WORD $0x0406 // movzx ecx, byte [r14 + rax + 4] LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x064cb60f; BYTE $0x05 // movzx ecx, byte [rsi + rax + 5] + LONG $0x4cb60f41; WORD $0x0506 // movzx ecx, byte [r14 + rax + 5] LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x064cb60f; BYTE $0x06 // movzx ecx, byte [rsi + rax + 6] + LONG $0x4cb60f41; WORD $0x0606 // movzx ecx, byte [r14 + rax + 6] LONG $0xc16e0f66 // movd xmm0, ecx - LONG $0x064cb60f; BYTE $0x07 // movzx ecx, byte [rsi + rax + 7] + LONG $0x4cb60f41; WORD $0x0706 // movzx ecx, byte [r14 + rax + 7] LONG $0xc96e0f66 // movd xmm1, ecx - QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 - LONG $0x064cb60f; BYTE $0x08 // movzx ecx, byte [rsi + rax + 8] + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 + LONG $0x4cb60f41; WORD $0x0806 // movzx ecx, byte [r14 + rax + 8] LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x064cb60f; BYTE $0x09 // movzx ecx, byte [rsi + rax + 9] + LONG $0x4cb60f41; WORD $0x0906 // movzx ecx, byte [r14 + rax + 9] LONG $0xc96e0f66 // movd xmm1, ecx - QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 - LONG $0x064cb60f; BYTE $0x0a // movzx ecx, byte [rsi + rax + 10] + QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + LONG $0x4cb60f41; WORD $0x0a06 // movzx ecx, byte [r14 + rax + 10] LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x064cb60f; BYTE $0x0b // movzx ecx, byte [rsi + rax + 11] + LONG $0x4cb60f41; WORD $0x0b06 // movzx ecx, byte [r14 + rax + 11] LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x064cb60f; BYTE $0x0c // movzx ecx, byte [rsi + rax + 12] + LONG $0x4cb60f41; WORD $0x0c06 // movzx ecx, byte [r14 + rax + 12] LONG $0xc96e0f66 // movd xmm1, ecx - QUAD $0x000130248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm1 - LONG $0x064cb60f; BYTE $0x10 // movzx ecx, byte [rsi + rax + 16] + QUAD $0x000140248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 320], xmm1 + LONG $0x4cb60f41; WORD $0x1006 // movzx ecx, byte [r14 + rax + 16] LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - QUAD $0x000000a024848948 // mov qword [rsp + 160], rax - LONG $0x064cb60f; BYTE $0x18 // movzx ecx, byte [rsi + rax + 24] + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + LONG $0x4cb60f41; WORD $0x1806 // movzx ecx, byte [r14 + rax + 24] LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - WORD $0x8949; BYTE $0xc4 // mov r12, rax - LONG $0x20cc8349 // or r12, 32 - LONG $0x2464894c; BYTE $0x60 // mov qword [rsp + 96], r12 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - LONG $0x40c98348 // or rcx, 64 - LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx - LONG $0x60ce8349 // or r14, 96 - LONG $0x80ca8148; WORD $0x0000; BYTE $0x00 // or rdx, 128 - LONG $0xa0cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 160 - LONG $0xc0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 192 - LONG $0x246c894c; BYTE $0x68 // mov qword [rsp + 104], r13 - LONG $0xe0c98149; WORD $0x0000; BYTE $0x00 // or r9, 224 - LONG $0x00ca8149; WORD $0x0001; BYTE $0x00 // or r10, 256 - LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 - LONG $0x20cb8149; WORD $0x0001; BYTE $0x00 // or r11, 288 - LONG $0x40cf8149; WORD $0x0001; BYTE $0x00 // or r15, 320 - LONG $0x60c88149; WORD $0x0001; BYTE $0x00 // or r8, 352 - LONG $0x2444894c; BYTE $0x28 // mov qword [rsp + 40], r8 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - LONG $0x80c88149; WORD $0x0001; BYTE $0x00 // or r8, 384 - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - LONG $0xa0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 416 - LONG $0x245c8948; BYTE $0x10 // mov qword [rsp + 16], rbx - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 - LONG $0x245c8948; BYTE $0x18 // mov qword [rsp + 24], rbx - LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax - QUAD $0x012614203a0f4666 // pinsrb xmm10, byte [rsi + r12], 1 - QUAD $0x020e14203a0f4466 // pinsrb xmm10, byte [rsi + rcx], 2 - QUAD $0x033614203a0f4666 // pinsrb xmm10, byte [rsi + r14], 3 - LONG $0x2474894c; BYTE $0x40 // mov qword [rsp + 64], r14 - QUAD $0x041614203a0f4466 // pinsrb xmm10, byte [rsi + rdx], 4 - QUAD $0x053e14203a0f4466 // pinsrb xmm10, byte [rsi + rdi], 5 - QUAD $0x062e14203a0f4666 // pinsrb xmm10, byte [rsi + r13], 6 - QUAD $0x070e14203a0f4666 // pinsrb xmm10, byte [rsi + r9], 7 - QUAD $0x081614203a0f4666 // pinsrb xmm10, byte [rsi + r10], 8 - QUAD $0x091e14203a0f4666 // pinsrb xmm10, byte [rsi + r11], 9 - QUAD $0x0a3e14203a0f4666 // pinsrb xmm10, byte [rsi + r15], 10 - LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] - QUAD $0x0b2614203a0f4666 // pinsrb xmm10, byte [rsi + r12], 11 - QUAD $0x0c0614203a0f4666 // pinsrb xmm10, byte [rsi + r8], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0d1e14203a0f4466 // pinsrb xmm10, byte [rsi + rbx], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e0614203a0f4466 // pinsrb xmm10, byte [rsi + rax], 14 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x0f1614203a0f4666 // pinsrb xmm10, byte [rsi + r10], 15 - LONG $0x6f0f4566; BYTE $0xc2 // movdqa xmm8, xmm10 - QUAD $0x012024a46f0f4466; WORD $0x0000 // movdqa xmm12, oword [rsp + 288] - LONG $0xda0f4566; BYTE $0xc4 // pminub xmm8, xmm12 - LONG $0x740f4566; BYTE $0xc2 // pcmpeqb xmm8, xmm10 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x01010664203a0f66 // pinsrb xmm4, byte [rsi + rax + 1], 1 - QUAD $0x02010e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 1], 2 - QUAD $0x013664203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r14 + 1], 3 - QUAD $0x04011664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 1], 4 - QUAD $0x05013e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 1], 5 - QUAD $0x012e64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r13 + 1], 6 - WORD $0x894d; BYTE $0xce // mov r14, r9 - QUAD $0x010e64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r9 + 1], 7 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x08011e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 1], 8 - QUAD $0x011e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r11 + 1], 9 - QUAD $0x013e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r15 + 1], 10 - QUAD $0x012664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r12 + 1], 11 - QUAD $0x010664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r8 + 1], 12 - LONG $0x244c8b4c; BYTE $0x10 // mov r9, qword [rsp + 16] - QUAD $0x010e64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r9 + 1], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e010664203a0f66 // pinsrb xmm4, byte [rsi + rax + 1], 14 - QUAD $0x011664203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r10 + 1], 15 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x020e74203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r9 + 2], 1 - QUAD $0x02020e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 2], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x03020674203a0f66 // pinsrb xmm6, byte [rsi + rax + 2], 3 - QUAD $0x04021674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 2], 4 - QUAD $0x05023e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 2], 5 - QUAD $0x022e74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r13 + 2], 6 - QUAD $0x023674203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r14 + 2], 7 - QUAD $0x08021e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 2], 8 - QUAD $0x021e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r11 + 2], 9 - QUAD $0x023e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r15 + 2], 10 - QUAD $0x022674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r12 + 2], 11 - QUAD $0x020674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r8 + 2], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d020674203a0f66 // pinsrb xmm6, byte [rsi + rax + 2], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e020674203a0f66 // pinsrb xmm6, byte [rsi + rax + 2], 14 - QUAD $0x021674203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r10 + 2], 15 - QUAD $0x080e74203a0f4666; BYTE $0x01 // pinsrb xmm14, byte [rsi + r9 + 8], 1 - QUAD $0x080e74203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rsi + rcx + 8], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x080674203a0f4466; BYTE $0x03 // pinsrb xmm14, byte [rsi + rax + 8], 3 - QUAD $0x081674203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rsi + rdx + 8], 4 - QUAD $0x083e74203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rsi + rdi + 8], 5 - QUAD $0x082e74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rsi + r13 + 8], 6 - QUAD $0x083674203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rsi + r14 + 8], 7 - QUAD $0x081e74203a0f4466; BYTE $0x08 // pinsrb xmm14, byte [rsi + rbx + 8], 8 - QUAD $0x081e74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r11 + 8], 9 - QUAD $0x083e74203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rsi + r15 + 8], 10 - QUAD $0x082674203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rsi + r12 + 8], 11 - QUAD $0x080674203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rsi + r8 + 8], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x080674203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rsi + rax + 8], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x080674203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rsi + rax + 8], 14 - QUAD $0x081674203a0f4666; BYTE $0x0f // pinsrb xmm14, byte [rsi + r10 + 8], 15 - LONG $0x6f0f4566; BYTE $0xd6 // movdqa xmm10, xmm14 - LONG $0xda0f4566; BYTE $0xd4 // pminub xmm10, xmm12 - LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 - QUAD $0x100e6c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rsi + r9 + 16], 1 - QUAD $0x100e6c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rcx + 16], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x10066c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rsi + rax + 16], 3 - QUAD $0x10166c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rsi + rdx + 16], 4 - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - LONG $0x24548948; BYTE $0x58 // mov qword [rsp + 88], rdx - QUAD $0x103e6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rsi + rdi + 16], 5 - LONG $0x247c8948; BYTE $0x50 // mov qword [rsp + 80], rdi - QUAD $0x102e6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rsi + r13 + 16], 6 - QUAD $0x10366c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rsi + r14 + 16], 7 - QUAD $0x101e6c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rsi + rbx + 16], 8 - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x101e6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r11 + 16], 9 - QUAD $0x00000080249c894c // mov qword [rsp + 128], r11 - QUAD $0x103e6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rsi + r15 + 16], 10 - LONG $0x247c894c; BYTE $0x30 // mov qword [rsp + 48], r15 - QUAD $0x10266c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r12 + 16], 11 - QUAD $0x10066c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r8 + 16], 12 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - LONG $0x2444894c; BYTE $0x38 // mov qword [rsp + 56], r8 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x10166c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rdx + 16], 13 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x10166c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r10 + 16], 14 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x10066c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rsi + r8 + 16], 15 - LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 - LONG $0xda0f4166; BYTE $0xdc // pminub xmm3, xmm12 - LONG $0x740f4166; BYTE $0xdd // pcmpeqb xmm3, xmm13 - QUAD $0x000110249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm3 - QUAD $0x180e7c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rsi + r9 + 24], 1 - QUAD $0x180e7c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rsi + rcx + 24], 2 - LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] - QUAD $0x180e7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rsi + r9 + 24], 3 - QUAD $0x18067c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rsi + rax + 24], 4 - QUAD $0x183e7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rdi + 24], 5 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x18067c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rax + 24], 6 - QUAD $0x18367c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rsi + r14 + 24], 7 - QUAD $0x182e7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r13 + 24], 8 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x181e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r11 + 24], 9 - QUAD $0x183e7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r15 + 24], 10 - QUAD $0x18267c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r12 + 24], 11 - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - QUAD $0x181e7c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rsi + rbx + 24], 12 - QUAD $0x18167c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rsi + rdx + 24], 13 - QUAD $0x18167c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r10 + 24], 14 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x18067c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r8 + 24], 15 - LONG $0x6f0f4166; BYTE $0xdf // movdqa xmm3, xmm15 - LONG $0xda0f4166; BYTE $0xdc // pminub xmm3, xmm12 - LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 - QUAD $0x0000f0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm3 - LONG $0x6f0f4466; BYTE $0xf4 // movdqa xmm14, xmm4 - LONG $0xda0f4566; BYTE $0xf4 // pminub xmm14, xmm12 - LONG $0x740f4466; BYTE $0xf4 // pcmpeqb xmm14, xmm4 - LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 - QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI7_10] */ - LONG $0xdf0f4466; BYTE $0xec // pandn xmm13, xmm4 - LONG $0xfc0f4566; BYTE $0xee // paddb xmm13, xmm14 - LONG $0x6f0f4466; BYTE $0xf6 // movdqa xmm14, xmm6 - LONG $0xda0f4566; BYTE $0xf4 // pminub xmm14, xmm12 - LONG $0x740f4466; BYTE $0xf6 // pcmpeqb xmm14, xmm6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - LONG $0x1654b60f; BYTE $0x0d // movzx edx, byte [rsi + rdx + 13] - LONG $0xf26e0f66 // movd xmm6, edx - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x01033e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 3], 1 - LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] - QUAD $0x031e6c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rsi + r11 + 3], 2 - QUAD $0x030e6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r9 + 3], 3 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x04031e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 3], 4 - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x0503166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 3], 5 - LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] - QUAD $0x0603166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 3], 6 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - QUAD $0x03366c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r14 + 3], 7 - QUAD $0x0803066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 3], 8 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x033e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r15 + 3], 9 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x03266c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r12 + 3], 10 - QUAD $0x0b030e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 3], 11 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x0c03066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 3], 12 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x03166c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r10 + 3], 13 - WORD $0x894d; BYTE $0xee // mov r14, r13 - QUAD $0x032e6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rsi + r13 + 3], 14 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x032e6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r13 + 3], 15 - QUAD $0x043e4c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rdi + 4], 1 - QUAD $0x041e4c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rsi + r11 + 4], 2 - QUAD $0x040e4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r9 + 4], 3 - QUAD $0x041e4c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rsi + rbx + 4], 4 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x04064c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rsi + r8 + 4], 5 - QUAD $0x04164c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rdx + 4], 6 - QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] - QUAD $0x040e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rcx + 4], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x040e4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rsi + rcx + 4], 8 - QUAD $0x043e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r15 + 4], 9 - QUAD $0x04264c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r12 + 4], 10 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x040e4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rsi + rcx + 4], 11 - WORD $0x8949; BYTE $0xc0 // mov r8, rax - QUAD $0x04064c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rsi + rax + 4], 12 - QUAD $0x04164c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r10 + 4], 13 - QUAD $0x04364c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r14 + 4], 14 - QUAD $0x042e4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r13 + 4], 15 - QUAD $0x01053e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 5], 1 - QUAD $0x051e7c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rsi + r11 + 5], 2 - QUAD $0x050e7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rsi + r9 + 5], 3 - QUAD $0x04051e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 5], 4 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0505067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 5], 5 - QUAD $0x0605167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 5], 6 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x0705067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 5], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x08050e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 5], 8 - QUAD $0x053e7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r15 + 5], 9 - QUAD $0x05267c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r12 + 5], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0b05067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 5], 11 - QUAD $0x05067c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r8 + 5], 12 - QUAD $0x05167c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r10 + 5], 13 - QUAD $0x05367c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rsi + r14 + 5], 14 - QUAD $0x052e7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r13 + 5], 15 - QUAD $0x01063e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 6], 1 - QUAD $0x061e44203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r11 + 6], 2 - QUAD $0x060e44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r9 + 6], 3 - QUAD $0x04061e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 6], 4 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x05063e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 6], 5 - QUAD $0x06061644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 6], 6 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x060e44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r9 + 6], 7 - QUAD $0x08060e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 6], 8 - QUAD $0x063e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r15 + 6], 9 - QUAD $0x062644203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r12 + 6], 10 - QUAD $0x0b060644203a0f66 // pinsrb xmm0, byte [rsi + rax + 6], 11 - QUAD $0x060644203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r8 + 6], 12 - QUAD $0x061644203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r10 + 6], 13 - LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 - QUAD $0x063644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r14 + 6], 14 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI7_11] */ - LONG $0xdf0f4466; BYTE $0xf4 // pandn xmm14, xmm4 - LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 - LONG $0x6f0f4466; BYTE $0xfd // movdqa xmm15, xmm5 - LONG $0xda0f4566; BYTE $0xfc // pminub xmm15, xmm12 - LONG $0x740f4466; BYTE $0xfd // pcmpeqb xmm15, xmm5 - QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] - LONG $0x1e54b60f; BYTE $0x0e // movzx edx, byte [rsi + rbx + 14] - LONG $0xea6e0f66 // movd xmm5, edx - QUAD $0x000000c0a56f0f66 // movdqa xmm4, oword 192[rbp] /* [rip + .LCPI7_12] */ - LONG $0xdf0f4466; BYTE $0xfc // pandn xmm15, xmm4 - LONG $0xeb0f4566; BYTE $0xfe // por xmm15, xmm14 - LONG $0x1e54b60f; BYTE $0x0f // movzx edx, byte [rsi + rbx + 15] - LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - LONG $0xdb760f66 // pcmpeqd xmm3, xmm3 - LONG $0xf80f4466; BYTE $0xeb // psubb xmm13, xmm3 - LONG $0x760f4566; BYTE $0xf6 // pcmpeqd xmm14, xmm14 - LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 - LONG $0x6f0f4166; BYTE $0xe1 // movdqa xmm4, xmm9 - LONG $0xda0f4166; BYTE $0xe4 // pminub xmm4, xmm12 - LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 - LONG $0x6f0f4466; BYTE $0xcf // movdqa xmm9, xmm7 - LONG $0xda0f4566; BYTE $0xcc // pminub xmm9, xmm12 - LONG $0x740f4466; BYTE $0xcf // pcmpeqb xmm9, xmm7 - LONG $0x1e54b60f; BYTE $0x11 // movzx edx, byte [rsi + rbx + 17] - LONG $0xfa6e0f66 // movd xmm7, edx - QUAD $0x062e44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r13 + 6], 15 - QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI7_13] */ - LONG $0xe1df0f66 // pandn xmm4, xmm1 - QUAD $0x000000e08d6f0f66 // movdqa xmm1, oword 224[rbp] /* [rip + .LCPI7_14] */ - LONG $0xdf0f4466; BYTE $0xc9 // pandn xmm9, xmm1 - LONG $0xeb0f4466; BYTE $0xcc // por xmm9, xmm4 - LONG $0xe06f0f66 // movdqa xmm4, xmm0 - LONG $0xda0f4166; BYTE $0xe4 // pminub xmm4, xmm12 - LONG $0xe0740f66 // pcmpeqb xmm4, xmm0 - LONG $0x1e54b60f; BYTE $0x12 // movzx edx, byte [rsi + rbx + 18] - LONG $0xca6e0f66 // movd xmm1, edx - QUAD $0x0000c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 192] - LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] - QUAD $0x071644203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rsi + r10 + 7], 1 - LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] - QUAD $0x071e44203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r11 + 7], 2 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x073644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r14 + 7], 3 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x04070e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 7], 4 - QUAD $0x05073e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 7], 5 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x073e44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rsi + r15 + 7], 6 - QUAD $0x070e44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r9 + 7], 7 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x08070e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 7], 8 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x09070e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 7], 9 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x0a070e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 7], 10 - LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] - QUAD $0x070644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r8 + 7], 11 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x0c070e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 7], 12 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0d071644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 7], 13 - QUAD $0x072644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r12 + 7], 14 - QUAD $0x072e44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r13 + 7], 15 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI7_15] */ - LONG $0xe3df0f66 // pandn xmm4, xmm3 - LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 - LONG $0x6f0f4466; BYTE $0xc8 // movdqa xmm9, xmm0 - LONG $0xda0f4566; BYTE $0xcc // pminub xmm9, xmm12 - LONG $0x740f4466; BYTE $0xc8 // pcmpeqb xmm9, xmm0 - LONG $0x1e54b60f; BYTE $0x13 // movzx edx, byte [rsi + rbx + 19] - LONG $0xda6e0f66 // movd xmm3, edx - LONG $0xef0f4566; BYTE $0xce // pxor xmm9, xmm14 - LONG $0x710f4166; WORD $0x07f1 // psllw xmm9, 7 - LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI7_6] */ - LONG $0xdb0f4466; BYTE $0xc8 // pand xmm9, xmm0 - LONG $0xeb0f4466; BYTE $0xcc // por xmm9, xmm4 - LONG $0x6f0f4166; BYTE $0xe1 // movdqa xmm4, xmm9 - LONG $0x1e54b60f; BYTE $0x14 // movzx edx, byte [rsi + rbx + 20] - LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx - QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] - WORD $0x894d; BYTE $0xd4 // mov r12, r10 - QUAD $0x091644203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rsi + r10 + 9], 1 - QUAD $0x091e44203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r11 + 9], 2 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - QUAD $0x093644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r14 + 9], 3 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x04090644203a0f66 // pinsrb xmm0, byte [rsi + rax + 9], 4 - QUAD $0x05093e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 9], 5 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - QUAD $0x093e44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rsi + r15 + 9], 6 - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - QUAD $0x07091644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 9], 7 - LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] - QUAD $0x093644203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r14 + 9], 8 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x091e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r11 + 9], 9 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x093e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r15 + 9], 10 - QUAD $0x090644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r8 + 9], 11 - QUAD $0x0c090e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 9], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0d091e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 9], 13 - LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] - QUAD $0x091644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r10 + 9], 14 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0f090644203a0f66 // pinsrb xmm0, byte [rsi + rax + 9], 15 - QUAD $0x0a2654203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r12 + 10], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x020a0654203a0f66 // pinsrb xmm2, byte [rsi + rax + 10], 2 - QUAD $0x0a2e54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r13 + 10], 3 - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x0a2654203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r12 + 10], 4 - QUAD $0x050a3e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 10], 5 - QUAD $0x0a0e54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r9 + 10], 6 - QUAD $0x070a1654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 10], 7 - WORD $0x8948; BYTE $0xd7 // mov rdi, rdx - QUAD $0x0a3654203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r14 + 10], 8 - QUAD $0x0a1e54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r11 + 10], 9 - QUAD $0x0a3e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r15 + 10], 10 - QUAD $0x0a0654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r8 + 10], 11 - QUAD $0x0c0a0e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 10], 12 - QUAD $0x0d0a1e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 10], 13 - QUAD $0x0a1654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r10 + 10], 14 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0a2e54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r13 + 10], 15 - LONG $0xeb0f4166; BYTE $0xe7 // por xmm4, xmm15 - QUAD $0x0000d024a47f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm4 - LONG $0xe06f0f66 // movdqa xmm4, xmm0 - LONG $0xda0f4166; BYTE $0xe4 // pminub xmm4, xmm12 - LONG $0xe0740f66 // pcmpeqb xmm4, xmm0 - LONG $0x6f0f4466; BYTE $0xec // movdqa xmm13, xmm4 - QUAD $0x0000a0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 160[rbp] /* [rip + .LCPI7_10] */ - LONG $0xdf0f4566; BYTE $0xee // pandn xmm13, xmm14 - LONG $0xfc0f4466; BYTE $0xec // paddb xmm13, xmm4 - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0xda0f4166; BYTE $0xc4 // pminub xmm0, xmm12 - LONG $0xc2740f66 // pcmpeqb xmm0, xmm2 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - LONG $0x0654b60f; BYTE $0x15 // movzx edx, byte [rsi + rax + 21] - LONG $0xe26e0f66 // movd xmm4, edx - LONG $0xdf0f4566; BYTE $0xd6 // pandn xmm10, xmm14 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x0b1e5c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rsi + r11 + 11], 1 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0b165c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rsi + r10 + 11], 2 - LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] - QUAD $0x0b365c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r14 + 11], 3 - WORD $0x894d; BYTE $0xe0 // mov r8, r12 - QUAD $0x0b265c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rsi + r12 + 11], 4 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x0b0e5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rsi + r9 + 11], 5 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0b0e5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rsi + rcx + 11], 6 - QUAD $0x0b3e5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rsi + rdi + 11], 7 - WORD $0x8949; BYTE $0xfc // mov r12, rdi - LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] - QUAD $0x0b3e5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r15 + 11], 8 - QUAD $0x00000080249c8b48 // mov rbx, qword [rsp + 128] - QUAD $0x0b1e5c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rsi + rbx + 11], 9 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0b165c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rsi + rdx + 11], 10 - LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] - QUAD $0x0b165c203a0f4466; BYTE $0x0b // pinsrb xmm11, byte [rsi + rdx + 11], 11 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0b3e5c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rsi + rdi + 11], 12 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0b165c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rdx + 11], 13 - LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] - QUAD $0x0b165c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rsi + rdx + 11], 14 - QUAD $0x0b2e5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rsi + r13 + 11], 15 - QUAD $0x000000b085df0f66 // pandn xmm0, oword 176[rbp] /* [rip + .LCPI7_11] */ - LONG $0xeb0f4166; BYTE $0xc2 // por xmm0, xmm10 - LONG $0x6f0f4566; BYTE $0xd3 // movdqa xmm10, xmm11 - LONG $0xda0f4566; BYTE $0xd4 // pminub xmm10, xmm12 - LONG $0x740f4566; BYTE $0xd3 // pcmpeqb xmm10, xmm11 - LONG $0x0654b60f; BYTE $0x16 // movzx edx, byte [rsi + rax + 22] - LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - QUAD $0x0000c095df0f4466; BYTE $0x00 // pandn xmm10, oword 192[rbp] /* [rip + .LCPI7_12] */ - LONG $0xeb0f4466; BYTE $0xd0 // por xmm10, xmm0 - LONG $0x0654b60f; BYTE $0x17 // movzx edx, byte [rsi + rax + 23] - LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - QUAD $0x00013024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 304] - QUAD $0x0c1e44203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rsi + r11 + 12], 1 - QUAD $0x0c1644203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r10 + 12], 2 - WORD $0x894d; BYTE $0xd3 // mov r11, r10 - WORD $0x894c; BYTE $0xf2 // mov rdx, r14 - QUAD $0x0c3644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r14 + 12], 3 - QUAD $0x0c0644203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rsi + r8 + 12], 4 - QUAD $0x0c0e44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r9 + 12], 5 - QUAD $0x060c0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 12], 6 - QUAD $0x0c2644203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r12 + 12], 7 - QUAD $0x0c3e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r15 + 12], 8 - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x090c1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 12], 9 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0a0c1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 12], 10 - LONG $0x24748b4c; BYTE $0x28 // mov r14, qword [rsp + 40] - QUAD $0x0c3644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r14 + 12], 11 - QUAD $0x0c0c3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 12], 12 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x0d0c1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 12], 13 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x0c0e44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r9 + 12], 14 - WORD $0x894d; BYTE $0xea // mov r10, r13 - QUAD $0x0c2e44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r13 + 12], 15 - QUAD $0x010d0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 13], 1 - QUAD $0x0d1e74203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rsi + r11 + 13], 2 - QUAD $0x030d1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 13], 3 - QUAD $0x0d0674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r8 + 13], 4 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x050d0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 13], 5 - QUAD $0x060d0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 13], 6 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x0d1e74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r11 + 13], 7 - QUAD $0x0d3e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r15 + 13], 8 - QUAD $0x0d2674203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r12 + 13], 9 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0a0d1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 13], 10 - QUAD $0x0d3674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r14 + 13], 11 - QUAD $0x0c0d3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 13], 12 - QUAD $0x0d0d1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 13], 13 - QUAD $0x0d0e74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r9 + 13], 14 - QUAD $0x0d2e74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r13 + 13], 15 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - QUAD $0x000100adf80f4466; BYTE $0x00 // psubb xmm13, oword 256[rbp] /* [rip + .LCPI7_16] */ - LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 - LONG $0xd06f0f66 // movdqa xmm2, xmm0 - LONG $0x6f0f4566; BYTE $0xec // movdqa xmm13, xmm12 - LONG $0xda0f4166; BYTE $0xd4 // pminub xmm2, xmm12 - LONG $0xd0740f66 // pcmpeqb xmm2, xmm0 - LONG $0xc66f0f66 // movdqa xmm0, xmm6 - LONG $0xda0f4166; BYTE $0xc4 // pminub xmm0, xmm12 - LONG $0xc6740f66 // pcmpeqb xmm0, xmm6 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - LONG $0x1654b60f; BYTE $0x19 // movzx edx, byte [rsi + rdx + 25] - LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x010e1e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 14], 1 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0e2e6c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rsi + r13 + 14], 2 - LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] - QUAD $0x030e166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 14], 3 - QUAD $0x0e066c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r8 + 14], 4 - WORD $0x8949; BYTE $0xc0 // mov r8, rax - QUAD $0x050e066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 14], 5 - QUAD $0x060e0e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 14], 6 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x0e1e6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r11 + 14], 7 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x0e3e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r15 + 14], 8 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x0e266c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r12 + 14], 9 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x0e1e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r11 + 14], 10 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0e3e6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r15 + 14], 11 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - QUAD $0x0e266c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r12 + 14], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d0e066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 14], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e0e066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 14], 14 - QUAD $0x0e0e6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r9 + 14], 15 - QUAD $0x0f1e44203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rbx + 15], 1 - QUAD $0x0f2e44203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rsi + r13 + 15], 2 - QUAD $0x0f1644203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rdx + 15], 3 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x0f2e44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rsi + r13 + 15], 4 - QUAD $0x0f0644203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r8 + 15], 5 - QUAD $0x0f0e44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rcx + 15], 6 - QUAD $0x0f1644203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rsi + r10 + 15], 7 - QUAD $0x0f3644203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r14 + 15], 8 - QUAD $0x0f3e44203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rsi + rdi + 15], 9 - QUAD $0x0f1e44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r11 + 15], 10 - QUAD $0x0f3e44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r15 + 15], 11 - QUAD $0x0f2644203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r12 + 15], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f0644203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rax + 15], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0f0644203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rax + 15], 14 - QUAD $0x0f0e44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r9 + 15], 15 - QUAD $0x01111e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 17], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0211067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 17], 2 - QUAD $0x0311167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 17], 3 - QUAD $0x112e7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r13 + 17], 4 - QUAD $0x11067c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r8 + 17], 5 - QUAD $0x06110e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 17], 6 - QUAD $0x11167c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rsi + r10 + 17], 7 - QUAD $0x11367c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r14 + 17], 8 - QUAD $0x09113e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 17], 9 - QUAD $0x111e7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r11 + 17], 10 - QUAD $0x113e7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r15 + 17], 11 - QUAD $0x11267c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r12 + 17], 12 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x112e7c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r13 + 17], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e11067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 17], 14 - QUAD $0x110e7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r9 + 17], 15 - QUAD $0x01121e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 18], 1 - LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] - QUAD $0x02121e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 18], 2 - QUAD $0x0312164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 18], 3 - LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] - QUAD $0x0412064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 18], 4 - QUAD $0x12064c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r8 + 18], 5 - QUAD $0x06120e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 18], 6 - QUAD $0x12164c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rsi + r10 + 18], 7 - QUAD $0x12364c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r14 + 18], 8 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - QUAD $0x09123e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 18], 9 - QUAD $0x121e4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r11 + 18], 10 - QUAD $0x123e4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r15 + 18], 11 - QUAD $0x12264c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r12 + 18], 12 - QUAD $0x122e4c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r13 + 18], 13 - QUAD $0x000000d095df0f66 // pandn xmm2, oword 208[rbp] /* [rip + .LCPI7_13] */ - QUAD $0x000000e085df0f66 // pandn xmm0, oword 224[rbp] /* [rip + .LCPI7_14] */ - LONG $0xc2eb0f66 // por xmm0, xmm2 - LONG $0xd56f0f66 // movdqa xmm2, xmm5 - LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 - LONG $0xd5740f66 // pcmpeqb xmm2, xmm5 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - LONG $0x0654b60f; BYTE $0x1a // movzx edx, byte [rsi + rax + 26] - LONG $0xea6e0f66 // movd xmm5, edx - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x120e4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rsi + r9 + 18], 14 - QUAD $0x000000f095df0f66 // pandn xmm2, oword 240[rbp] /* [rip + .LCPI7_15] */ - LONG $0xd0eb0f66 // por xmm2, xmm0 - LONG $0x6f0f4166; BYTE $0xf0 // movdqa xmm6, xmm8 - LONG $0xda0f4166; BYTE $0xf5 // pminub xmm6, xmm13 - LONG $0x740f4166; BYTE $0xf0 // pcmpeqb xmm6, xmm8 - LONG $0x0654b60f; BYTE $0x1b // movzx edx, byte [rsi + rax + 27] - LONG $0xc26e0f66 // movd xmm0, edx - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x12064c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r8 + 18], 15 - QUAD $0x00000100b5ef0f66 // pxor xmm6, oword 256[rbp] /* [rip + .LCPI7_16] */ - LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 - LONG $0x75db0f66; BYTE $0x60 // pand xmm6, oword 96[rbp] /* [rip + .LCPI7_6] */ - LONG $0xf2eb0f66 // por xmm6, xmm2 - LONG $0x0654b60f; BYTE $0x1c // movzx edx, byte [rsi + rax + 28] - LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 - QUAD $0x0000c024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm6 - LONG $0xd76f0f66 // movdqa xmm2, xmm7 - LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 - LONG $0xd7740f66 // pcmpeqb xmm2, xmm7 - LONG $0x6f0f4466; BYTE $0xf2 // movdqa xmm14, xmm2 - QUAD $0x0000a0b5df0f4466; BYTE $0x00 // pandn xmm14, oword 160[rbp] /* [rip + .LCPI7_10] */ - LONG $0xfc0f4466; BYTE $0xf2 // paddb xmm14, xmm2 - LONG $0x6f0f4466; BYTE $0xd1 // movdqa xmm10, xmm1 - LONG $0xda0f4566; BYTE $0xd5 // pminub xmm10, xmm13 - LONG $0x740f4466; BYTE $0xd1 // pcmpeqb xmm10, xmm1 - LONG $0x0654b60f; BYTE $0x1d // movzx edx, byte [rsi + rax + 29] - LONG $0xf26e0f66 // movd xmm6, edx - LONG $0x0654b60f; BYTE $0x1e // movzx edx, byte [rsi + rax + 30] - LONG $0x064cb60f; BYTE $0x1f // movzx ecx, byte [rsi + rax + 31] - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0113065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 19], 1 - QUAD $0x14064c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rax + 20], 1 - QUAD $0x01150664203a0f66 // pinsrb xmm4, byte [rsi + rax + 21], 1 - QUAD $0x16067c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rax + 22], 1 - QUAD $0x17065c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rax + 23], 1 - QUAD $0x190664203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rax + 25], 1 - QUAD $0x011a066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 26], 1 - QUAD $0x011b0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 27], 1 - QUAD $0x1c0644203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rax + 28], 1 - QUAD $0x011d0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 29], 1 - LONG $0xca6e0f66 // movd xmm1, edx - QUAD $0x011e064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 30], 1 - LONG $0xf96e0f66 // movd xmm7, ecx - QUAD $0x011f067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 31], 1 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x02131e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 19], 2 - QUAD $0x141e4c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rbx + 20], 2 - QUAD $0x02151e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 21], 2 - QUAD $0x161e7c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rsi + rbx + 22], 2 - QUAD $0x171e5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rbx + 23], 2 - QUAD $0x191e64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rbx + 25], 2 - QUAD $0x021a1e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 26], 2 - QUAD $0x021b1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 27], 2 - QUAD $0x1c1e44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rbx + 28], 2 - QUAD $0x021d1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 29], 2 - QUAD $0x021e1e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 30], 2 - QUAD $0x021f1e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 31], 2 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0313065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 19], 3 - LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] - QUAD $0x0413165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 19], 4 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x05130e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 19], 5 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x06133e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 19], 6 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x13365c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rsi + r14 + 19], 7 - WORD $0x894d; BYTE $0xd4 // mov r12, r10 - QUAD $0x13165c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r10 + 19], 8 - QUAD $0x00000080249c8b4c // mov r11, qword [rsp + 128] - QUAD $0x131e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r11 + 19], 9 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x133e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r15 + 19], 10 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x13165c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r10 + 19], 11 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0c131e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 19], 12 - QUAD $0x132e5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r13 + 19], 13 - QUAD $0x130e5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rsi + r9 + 19], 14 - QUAD $0x13065c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r8 + 19], 15 - QUAD $0x14064c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rsi + rax + 20], 3 - QUAD $0x14164c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rsi + rdx + 20], 4 - QUAD $0x140e4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rsi + rcx + 20], 5 - QUAD $0x143e4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rdi + 20], 6 - QUAD $0x14364c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rsi + r14 + 20], 7 - QUAD $0x14264c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r12 + 20], 8 - QUAD $0x141e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r11 + 20], 9 - QUAD $0x143e4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r15 + 20], 10 - QUAD $0x14164c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r10 + 20], 11 - QUAD $0x141e4c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rsi + rbx + 20], 12 - QUAD $0x142e4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r13 + 20], 13 - QUAD $0x140e4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r9 + 20], 14 - QUAD $0x14064c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r8 + 20], 15 - QUAD $0x03150664203a0f66 // pinsrb xmm4, byte [rsi + rax + 21], 3 - QUAD $0x04151664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 21], 4 - QUAD $0x05150e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 21], 5 - QUAD $0x06153e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 21], 6 - QUAD $0x153664203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rsi + r14 + 21], 7 - QUAD $0x152664203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r12 + 21], 8 - QUAD $0x151e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r11 + 21], 9 - QUAD $0x153e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r15 + 21], 10 - QUAD $0x151664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r10 + 21], 11 - QUAD $0x0c151e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 21], 12 - WORD $0x8949; BYTE $0xd8 // mov r8, rbx - QUAD $0x152e64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r13 + 21], 13 - QUAD $0x150e64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r9 + 21], 14 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x0f151e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 21], 15 - QUAD $0x16067c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rsi + rax + 22], 3 - QUAD $0x16167c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rsi + rdx + 22], 4 - QUAD $0x160e7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rcx + 22], 5 - QUAD $0x163e7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rdi + 22], 6 - QUAD $0x16367c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rsi + r14 + 22], 7 - QUAD $0x16267c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r12 + 22], 8 - QUAD $0x161e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r11 + 22], 9 - QUAD $0x163e7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r15 + 22], 10 - QUAD $0x00011024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 272] - QUAD $0x000000a095df0f66 // pandn xmm2, oword 160[rbp] /* [rip + .LCPI7_10] */ - QUAD $0x16167c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r10 + 22], 11 - QUAD $0x0000b095df0f4466; BYTE $0x00 // pandn xmm10, oword 176[rbp] /* [rip + .LCPI7_11] */ - LONG $0xeb0f4466; BYTE $0xd2 // por xmm10, xmm2 - QUAD $0x16067c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r8 + 22], 12 - LONG $0xd36f0f66 // movdqa xmm2, xmm3 - LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 - LONG $0xd3740f66 // pcmpeqb xmm2, xmm3 - QUAD $0x162e7c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rsi + r13 + 22], 13 - QUAD $0x000000c095df0f66 // pandn xmm2, oword 192[rbp] /* [rip + .LCPI7_12] */ - LONG $0xeb0f4166; BYTE $0xd2 // por xmm2, xmm10 - QUAD $0x160e7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r9 + 22], 14 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - QUAD $0x000100b5f80f4466; BYTE $0x00 // psubb xmm14, oword 256[rbp] /* [rip + .LCPI7_16] */ - LONG $0xeb0f4166; BYTE $0xd6 // por xmm2, xmm14 - LONG $0x6f0f4566; BYTE $0xd1 // movdqa xmm10, xmm9 - LONG $0xda0f4566; BYTE $0xd5 // pminub xmm10, xmm13 - LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 - LONG $0xdc6f0f66 // movdqa xmm3, xmm4 - LONG $0x6f0f4566; BYTE $0xcd // movdqa xmm9, xmm13 - LONG $0xda0f4166; BYTE $0xdd // pminub xmm3, xmm13 - LONG $0xdc740f66 // pcmpeqb xmm3, xmm4 - QUAD $0x161e7c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rsi + rbx + 22], 15 - QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI7_13] */ - LONG $0xdf0f4566; BYTE $0xd5 // pandn xmm10, xmm13 - QUAD $0x000000e0a56f0f66 // movdqa xmm4, oword 224[rbp] /* [rip + .LCPI7_14] */ - LONG $0xdcdf0f66 // pandn xmm3, xmm4 - LONG $0xeb0f4166; BYTE $0xda // por xmm3, xmm10 - LONG $0x6f0f4166; BYTE $0xe7 // movdqa xmm4, xmm15 - LONG $0xda0f4166; BYTE $0xe1 // pminub xmm4, xmm9 - LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 - LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 - QUAD $0x17065c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rsi + rax + 23], 3 - QUAD $0x17165c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rsi + rdx + 23], 4 - QUAD $0x170e5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rsi + rcx + 23], 5 - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x170e5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rsi + r9 + 23], 6 - QUAD $0x17365c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r14 + 23], 7 - QUAD $0x17265c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r12 + 23], 8 - QUAD $0x171e5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r11 + 23], 9 - QUAD $0x173e5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rsi + r15 + 23], 10 - QUAD $0x17165c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r10 + 23], 11 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x170e5c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rsi + rcx + 23], 12 - QUAD $0x172e5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rsi + r13 + 23], 13 - QUAD $0x173e5c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rsi + rdi + 23], 14 - QUAD $0x171e5c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rsi + rbx + 23], 15 - QUAD $0x0000f0bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 240[rbp] /* [rip + .LCPI7_15] */ - LONG $0xdf0f4166; BYTE $0xe7 // pandn xmm4, xmm15 - LONG $0xe3eb0f66 // por xmm4, xmm3 - LONG $0x6f0f4166; BYTE $0xdb // movdqa xmm3, xmm11 - LONG $0xda0f4166; BYTE $0xd9 // pminub xmm3, xmm9 - LONG $0x740f4166; BYTE $0xdb // pcmpeqb xmm3, xmm11 - QUAD $0x000001009def0f66 // pxor xmm3, oword 256[rbp] /* [rip + .LCPI7_16] */ - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0x6f0f4466; WORD $0x605d // movdqa xmm11, oword 96[rbp] /* [rip + .LCPI7_6] */ - LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 - LONG $0xdceb0f66 // por xmm3, xmm4 - QUAD $0x190664203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rsi + rax + 25], 3 - QUAD $0x191664203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rsi + rdx + 25], 4 - QUAD $0x190664203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r8 + 25], 5 - QUAD $0x190e64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rsi + r9 + 25], 6 - QUAD $0x193664203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rsi + r14 + 25], 7 - QUAD $0x192664203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r12 + 25], 8 - QUAD $0x191e64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r11 + 25], 9 - QUAD $0x193e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r15 + 25], 10 - QUAD $0x191664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r10 + 25], 11 - QUAD $0x190e64203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rsi + rcx + 25], 12 - QUAD $0x192e64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rsi + r13 + 25], 13 - QUAD $0x193e64203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rsi + rdi + 25], 14 - QUAD $0x191e64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rsi + rbx + 25], 15 - QUAD $0x031a066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 26], 3 - QUAD $0x041a166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 26], 4 - QUAD $0x1a066c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r8 + 26], 5 - QUAD $0x1a0e6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r9 + 26], 6 - QUAD $0x1a366c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rsi + r14 + 26], 7 - QUAD $0x1a266c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r12 + 26], 8 - QUAD $0x1a1e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r11 + 26], 9 - QUAD $0x1a3e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r15 + 26], 10 - QUAD $0x1a166c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r10 + 26], 11 - QUAD $0x0c1a0e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 26], 12 - QUAD $0x1a2e6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r13 + 26], 13 - QUAD $0x0e1a3e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 26], 14 - QUAD $0x0f1a1e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 26], 15 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6f0f4166; BYTE $0xd4 // movdqa xmm2, xmm12 - LONG $0xda0f4166; BYTE $0xd1 // pminub xmm2, xmm9 - LONG $0x740f4166; BYTE $0xd4 // pcmpeqb xmm2, xmm12 - LONG $0x6f0f4466; BYTE $0xca // movdqa xmm9, xmm2 - QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI7_10] */ - LONG $0xdf0f4566; BYTE $0xca // pandn xmm9, xmm10 - LONG $0xfc0f4466; BYTE $0xca // paddb xmm9, xmm2 - LONG $0xe56f0f66 // movdqa xmm4, xmm5 - LONG $0xda0f4166; BYTE $0xe5 // pminub xmm4, xmm13 - LONG $0xe5740f66 // pcmpeqb xmm4, xmm5 - QUAD $0x0000f024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 240] - LONG $0xdf0f4166; BYTE $0xd2 // pandn xmm2, xmm10 - QUAD $0x031b0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 27], 3 - QUAD $0x041b1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 27], 4 - QUAD $0x1b0644203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r8 + 27], 5 - QUAD $0x1b0e44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rsi + r9 + 27], 6 - QUAD $0x1b3644203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rsi + r14 + 27], 7 - QUAD $0x1b2644203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r12 + 27], 8 - QUAD $0x1b1e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r11 + 27], 9 - QUAD $0x1b3e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r15 + 27], 10 - QUAD $0x1b1644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r10 + 27], 11 - QUAD $0x0c1b0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 27], 12 - QUAD $0x1b2e44203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r13 + 27], 13 - QUAD $0x0e1b3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 27], 14 - QUAD $0x0f1b1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 27], 15 - QUAD $0x000000b0a5df0f66 // pandn xmm4, oword 176[rbp] /* [rip + .LCPI7_11] */ - LONG $0xe2eb0f66 // por xmm4, xmm2 - LONG $0xd06f0f66 // movdqa xmm2, xmm0 - LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 - LONG $0xd0740f66 // pcmpeqb xmm2, xmm0 - QUAD $0x000000c095df0f66 // pandn xmm2, oword 192[rbp] /* [rip + .LCPI7_12] */ - LONG $0xd4eb0f66 // por xmm2, xmm4 - QUAD $0x1c0644203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rax + 28], 3 - QUAD $0x1c1644203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rdx + 28], 4 - QUAD $0x1c0644203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r8 + 28], 5 - QUAD $0x1c0e44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rsi + r9 + 28], 6 - QUAD $0x1c3644203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rsi + r14 + 28], 7 - QUAD $0x1c2644203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r12 + 28], 8 - QUAD $0x1c1e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r11 + 28], 9 - QUAD $0x1c3e44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r15 + 28], 10 - QUAD $0x1c1644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r10 + 28], 11 - QUAD $0x1c0e44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rsi + rcx + 28], 12 - QUAD $0x1c2e44203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r13 + 28], 13 - QUAD $0x1c3e44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rdi + 28], 14 - QUAD $0x1c1e44203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rsi + rbx + 28], 15 - QUAD $0x031d0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 29], 3 - QUAD $0x041d1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 29], 4 - QUAD $0x1d0674203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r8 + 29], 5 - QUAD $0x1d0e74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r9 + 29], 6 - QUAD $0x1d3674203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rsi + r14 + 29], 7 - QUAD $0x1d2674203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r12 + 29], 8 - QUAD $0x1d1e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r11 + 29], 9 - QUAD $0x1d3e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r15 + 29], 10 - QUAD $0x1d1674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r10 + 29], 11 - QUAD $0x0c1d0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 29], 12 - QUAD $0x1d2e74203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r13 + 29], 13 - QUAD $0x0e1d3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 29], 14 - QUAD $0x0f1d1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 29], 15 - LONG $0x760f4566; BYTE $0xd2 // pcmpeqd xmm10, xmm10 - LONG $0xf80f4566; BYTE $0xca // psubb xmm9, xmm10 - LONG $0xeb0f4166; BYTE $0xd1 // por xmm2, xmm9 - LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0xda0f4166; BYTE $0xc5 // pminub xmm0, xmm13 - LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 - LONG $0xe66f0f66 // movdqa xmm4, xmm6 - LONG $0xda0f4166; BYTE $0xe5 // pminub xmm4, xmm13 - LONG $0xe6740f66 // pcmpeqb xmm4, xmm6 - QUAD $0x031e064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 30], 3 - QUAD $0x031f067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 31], 3 - QUAD $0x041e164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 30], 4 - QUAD $0x041f167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 31], 4 - QUAD $0x1e064c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r8 + 30], 5 - QUAD $0x1f067c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r8 + 31], 5 - QUAD $0x1e0e4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rsi + r9 + 30], 6 - QUAD $0x1f0e7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rsi + r9 + 31], 6 - QUAD $0x1e364c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rsi + r14 + 30], 7 - QUAD $0x1f367c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rsi + r14 + 31], 7 - QUAD $0x1e264c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r12 + 30], 8 - QUAD $0x1f267c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r12 + 31], 8 - QUAD $0x1e1e4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r11 + 30], 9 - QUAD $0x1f1e7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r11 + 31], 9 - QUAD $0x1e3e4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r15 + 30], 10 - QUAD $0x1f3e7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r15 + 31], 10 - LONG $0x24048b48 // mov rax, qword [rsp] - QUAD $0x1e164c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r10 + 30], 11 - QUAD $0x1f167c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r10 + 31], 11 - QUAD $0x0c1e0e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 30], 12 - QUAD $0x0c1f0e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 31], 12 - QUAD $0x1e2e4c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r13 + 30], 13 - QUAD $0x1f2e7c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r13 + 31], 13 - QUAD $0x0e1e3e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 30], 14 - QUAD $0x0e1f3e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 31], 14 - QUAD $0x0f1e1e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 30], 15 - QUAD $0x0f1f1e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 31], 15 - QUAD $0x000000d085df0f66 // pandn xmm0, oword 208[rbp] /* [rip + .LCPI7_13] */ - QUAD $0x000000e0a5df0f66 // pandn xmm4, oword 224[rbp] /* [rip + .LCPI7_14] */ - LONG $0xe0eb0f66 // por xmm4, xmm0 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0xda0f4166; BYTE $0xc5 // pminub xmm0, xmm13 - LONG $0xc1740f66 // pcmpeqb xmm0, xmm1 - LONG $0xdf0f4166; BYTE $0xc7 // pandn xmm0, xmm15 - LONG $0xc4eb0f66 // por xmm0, xmm4 - LONG $0xcf6f0f66 // movdqa xmm1, xmm7 - LONG $0xda0f4166; BYTE $0xcd // pminub xmm1, xmm13 - LONG $0xcf740f66 // pcmpeqb xmm1, xmm7 - LONG $0xef0f4166; BYTE $0xca // pxor xmm1, xmm10 - LONG $0xf1710f66; BYTE $0x07 // psllw xmm1, 7 - LONG $0xdb0f4166; BYTE $0xcb // pand xmm1, xmm11 - LONG $0xc8eb0f66 // por xmm1, xmm0 - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0xc1600f66 // punpcklbw xmm0, xmm1 - QUAD $0x0000d024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 208] - LONG $0xd56f0f66 // movdqa xmm2, xmm5 - QUAD $0x0000c024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 192] - LONG $0xd6600f66 // punpcklbw xmm2, xmm6 - LONG $0xe26f0f66 // movdqa xmm4, xmm2 - LONG $0xe0610f66 // punpcklwd xmm4, xmm0 - LONG $0xd0690f66 // punpckhwd xmm2, xmm0 - LONG $0xd9680f66 // punpckhbw xmm3, xmm1 - LONG $0xee680f66 // punpckhbw xmm5, xmm6 - LONG $0xc56f0f66 // movdqa xmm0, xmm5 - LONG $0xc3610f66 // punpcklwd xmm0, xmm3 - LONG $0xeb690f66 // punpckhwd xmm5, xmm3 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - LONG $0x6c7f0ff3; WORD $0x3088 // movdqu oword [rax + 4*rcx + 48], xmm5 - LONG $0x447f0ff3; WORD $0x2088 // movdqu oword [rax + 4*rcx + 32], xmm0 - LONG $0x547f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm2 - LONG $0x24048948 // mov qword [rsp], rax - LONG $0x247f0ff3; BYTE $0x88 // movdqu oword [rax + 4*rcx], xmm4 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB7_67 - QUAD $0x0000010824bc8b4c // mov r15, qword [rsp + 264] - QUAD $0x000000e824bc3b4c // cmp r15, qword [rsp + 232] - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - LONG $0x24548a44; BYTE $0x08 // mov r10b, byte [rsp + 8] - QUAD $0x0000014024a48b4c // mov r12, qword [rsp + 320] - JNE LBB7_69 - JMP LBB7_72 - -LBB7_124: - LONG $0xf8e78349 // and r15, -8 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - LONG $0x24048b48 // mov rax, qword [rsp] - LONG $0xb8048d4a // lea rax, [rax + 4*r15] - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - QUAD $0x0000f024846e0f66; BYTE $0x00 // movd xmm0, dword [rsp + 240] - LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 - LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 - WORD $0x3145; BYTE $0xff // xor r15d, r15d - QUAD $0x000080bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 128[rbp] /* [rip + .LCPI7_8] */ - LONG $0x6f0f4466; WORD $0x104d // movdqa xmm9, oword 16[rbp] /* [rip + .LCPI7_1] */ - LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI7_2] */ - LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI7_3] */ - LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI7_4] */ - LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI7_5] */ - LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI7_6] */ - -LBB7_125: - LONG $0x247c894c; BYTE $0x10 // mov qword [rsp + 16], r15 - LONG $0x06e7c149 // shl r15, 6 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x894d; BYTE $0xfd // mov r13, r15 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 - WORD $0x894c; BYTE $0xff // mov rdi, r15 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - LONG $0x34b70f46; BYTE $0x3e // movzx r14d, word [rsi + r15] - LONG $0x44b70f42; WORD $0x023e // movzx eax, word [rsi + r15 + 2] - LONG $0x5cb70f46; WORD $0x043e // movzx r11d, word [rsi + r15 + 4] - LONG $0x54b70f42; WORD $0x063e // movzx edx, word [rsi + r15 + 6] - LONG $0x54b70f46; WORD $0x083e // movzx r10d, word [rsi + r15 + 8] - WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + LONG $0x20ce8348 // or rsi, 32 LONG $0x40c88349 // or r8, 64 + LONG $0x2444894c; BYTE $0x48 // mov qword [rsp + 72], r8 + LONG $0x60cf8348 // or rdi, 96 + LONG $0x247c8948; BYTE $0x28 // mov qword [rsp + 40], rdi LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 - LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 - LONG $0x40c98148; WORD $0x0001; BYTE $0x00 // or rcx, 320 - LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 - LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 - LONG $0x6e0f4166; BYTE $0xe6 // movd xmm4, r14d - LONG $0xc40f4266; WORD $0x0624; BYTE $0x01 // pinsrw xmm4, word [rsi + r8], 1 - LONG $0xc40f4266; WORD $0x0e24; BYTE $0x02 // pinsrw xmm4, word [rsi + r9], 2 - LONG $0xc40f4266; WORD $0x2624; BYTE $0x03 // pinsrw xmm4, word [rsi + r12], 3 - LONG $0xc40f4266; WORD $0x2e24; BYTE $0x04 // pinsrw xmm4, word [rsi + r13], 4 - LONG $0x24c40f66; WORD $0x050e // pinsrw xmm4, word [rsi + rcx], 5 - LONG $0x24c40f66; WORD $0x063e // pinsrw xmm4, word [rsi + rdi], 6 - LONG $0x24c40f66; WORD $0x071e // pinsrw xmm4, word [rsi + rbx], 7 - LONG $0x74b70f46; WORD $0x0a3e // movzx r14d, word [rsi + r15 + 10] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x01020674c40f4266 // pinsrw xmm6, word [rsi + r8 + 2], 1 - QUAD $0x02020e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 2], 2 - QUAD $0x03022674c40f4266 // pinsrw xmm6, word [rsi + r12 + 2], 3 - LONG $0x44b70f42; WORD $0x0c3e // movzx eax, word [rsi + r15 + 12] - LONG $0x20244489 // mov dword [rsp + 32], eax - QUAD $0x04022e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 2], 4 - LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d - LONG $0x5cb70f46; WORD $0x0e3e // movzx r11d, word [rsi + r15 + 14] - LONG $0x74c40f66; WORD $0x020e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 2], 5 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + LONG $0xa0c98148; WORD $0x0000; BYTE $0x00 // or rcx, 160 + LONG $0x244c8948; BYTE $0x50 // mov qword [rsp + 80], rcx + WORD $0x8948; BYTE $0xc7 // mov rdi, rax + LONG $0xc0cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 192 + LONG $0x247c8948; BYTE $0x38 // mov qword [rsp + 56], rdi + LONG $0xe0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 224 + LONG $0x00cf8149; WORD $0x0001; BYTE $0x00 // or r15, 256 + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 + LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 + LONG $0x60cd8149; WORD $0x0001; BYTE $0x00 // or r13, 352 + QUAD $0x00018010244c8148; BYTE $0x00 // or qword [rsp + 16], 384 + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0xa0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 416 + LONG $0x24548948; BYTE $0x18 // mov qword [rsp + 24], rdx + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0xc0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 448 + LONG $0x24548948; BYTE $0x08 // mov qword [rsp + 8], rdx + LONG $0xe0cc8149; WORD $0x0001; BYTE $0x00 // or r12, 480 + QUAD $0x013614203a0f4566 // pinsrb xmm10, byte [r14 + rsi], 1 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x24748948; BYTE $0x30 // mov qword [rsp + 48], rsi + QUAD $0x020614203a0f4766 // pinsrb xmm10, byte [r14 + r8], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031614203a0f4566 // pinsrb xmm10, byte [r14 + rdx], 3 + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + QUAD $0x040e14203a0f4766 // pinsrb xmm10, byte [r14 + r9], 4 + WORD $0x894c; BYTE $0xca // mov rdx, r9 + QUAD $0x00000090248c894c // mov qword [rsp + 144], r9 + QUAD $0x050e14203a0f4566 // pinsrb xmm10, byte [r14 + rcx], 5 + QUAD $0x063e14203a0f4566 // pinsrb xmm10, byte [r14 + rdi], 6 + QUAD $0x071e14203a0f4766 // pinsrb xmm10, byte [r14 + r11], 7 + QUAD $0x083e14203a0f4766 // pinsrb xmm10, byte [r14 + r15], 8 + QUAD $0x091614203a0f4766 // pinsrb xmm10, byte [r14 + r10], 9 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + QUAD $0x0a1e14203a0f4566 // pinsrb xmm10, byte [r14 + rbx], 10 + WORD $0x8948; BYTE $0xdf // mov rdi, rbx + QUAD $0x000000a0249c8948 // mov qword [rsp + 160], rbx + QUAD $0x0b2e14203a0f4766 // pinsrb xmm10, byte [r14 + r13], 11 + LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] + QUAD $0x0c1614203a0f4766 // pinsrb xmm10, byte [r14 + r10], 12 + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + QUAD $0x0d0e14203a0f4766 // pinsrb xmm10, byte [r14 + r9], 13 + LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] + QUAD $0x0e1e14203a0f4566 // pinsrb xmm10, byte [r14 + rbx], 14 + QUAD $0x0f2614203a0f4766 // pinsrb xmm10, byte [r14 + r12], 15 + LONG $0x6f0f4566; BYTE $0xc2 // movdqa xmm8, xmm10 + QUAD $0x012024a46f0f4466; WORD $0x0000 // movdqa xmm12, oword [rsp + 288] + LONG $0xda0f4566; BYTE $0xc4 // pminub xmm8, xmm12 + LONG $0x740f4566; BYTE $0xc2 // pcmpeqb xmm8, xmm10 + QUAD $0x010664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rax + 1], 1 + QUAD $0x010664203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r14 + r8 + 1], 2 + QUAD $0x013664203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rsi + 1], 3 + QUAD $0x011664203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r14 + rdx + 1], 4 + QUAD $0x010e64203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r14 + rcx + 1], 5 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x010664203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rax + 1], 6 + QUAD $0x011e64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r11 + 1], 7 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x011664203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r14 + rdx + 1], 8 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + LONG $0x247c894c; BYTE $0x68 // mov qword [rsp + 104], r15 + QUAD $0x013e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r15 + 1], 9 + QUAD $0x013e64203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r14 + rdi + 1], 10 + QUAD $0x012e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r13 + 1], 11 + QUAD $0x011664203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r14 + r10 + 1], 12 + QUAD $0x010e64203a0f4366; BYTE $0x0d // pinsrb xmm4, byte [r14 + r9 + 1], 13 + QUAD $0x011e64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rbx + 1], 14 + QUAD $0x012664203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r14 + r12 + 1], 15 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x023674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rsi + 2], 1 + QUAD $0x020674203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r14 + r8 + 2], 2 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x023e74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r14 + r15 + 2], 3 + QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] + QUAD $0x023e74203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rdi + 2], 4 + QUAD $0x020e74203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r14 + rcx + 2], 5 + QUAD $0x020674203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rax + 2], 6 + QUAD $0x021e74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r11 + 2], 7 + WORD $0x894d; BYTE $0xdf // mov r15, r11 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x021e74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r14 + r11 + 2], 8 + QUAD $0x021674203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r14 + rdx + 2], 9 + QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] + QUAD $0x023e74203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r14 + rdi + 2], 10 + QUAD $0x022e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r13 + 2], 11 + QUAD $0x021674203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r14 + r10 + 2], 12 + QUAD $0x020e74203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r9 + 2], 13 + QUAD $0x021e74203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rbx + 2], 14 + QUAD $0x022674203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r14 + r12 + 2], 15 + QUAD $0x083674203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r14 + rsi + 8], 1 + QUAD $0x080674203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r14 + r8 + 8], 2 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x083674203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r14 + rsi + 8], 3 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x081674203a0f4566; BYTE $0x04 // pinsrb xmm14, byte [r14 + rdx + 8], 4 + QUAD $0x080e74203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r14 + rcx + 8], 5 + QUAD $0x080674203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r14 + rax + 8], 6 + QUAD $0x083e74203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r14 + r15 + 8], 7 + QUAD $0x081e74203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r14 + r11 + 8], 8 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x080674203a0f4566; BYTE $0x09 // pinsrb xmm14, byte [r14 + rax + 8], 9 + QUAD $0x083e74203a0f4566; BYTE $0x0a // pinsrb xmm14, byte [r14 + rdi + 8], 10 + QUAD $0x082e74203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r14 + r13 + 8], 11 + QUAD $0x081674203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r14 + r10 + 8], 12 + QUAD $0x080e74203a0f4766; BYTE $0x0d // pinsrb xmm14, byte [r14 + r9 + 8], 13 + QUAD $0x081e74203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r14 + rbx + 8], 14 + QUAD $0x082674203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r14 + r12 + 8], 15 + LONG $0x6f0f4566; BYTE $0xd6 // movdqa xmm10, xmm14 + LONG $0xda0f4566; BYTE $0xd4 // pminub xmm10, xmm12 + LONG $0x740f4566; BYTE $0xd6 // pcmpeqb xmm10, xmm14 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x100e6c203a0f4766; BYTE $0x01 // pinsrb xmm13, byte [r14 + r9 + 16], 1 + QUAD $0x10066c203a0f4766; BYTE $0x02 // pinsrb xmm13, byte [r14 + r8 + 16], 2 + QUAD $0x10366c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r14 + rsi + 16], 3 + QUAD $0x10166c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r14 + rdx + 16], 4 + QUAD $0x100e6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r14 + rcx + 16], 5 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x10366c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r14 + rsi + 16], 6 + WORD $0x894d; BYTE $0xfb // mov r11, r15 + LONG $0x247c894c; BYTE $0x70 // mov qword [rsp + 112], r15 + QUAD $0x103e6c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r14 + r15 + 16], 7 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x103e6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r14 + r15 + 16], 8 + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + QUAD $0x10066c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r14 + rax + 16], 9 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + QUAD $0x103e6c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r14 + rdi + 16], 10 + QUAD $0x102e6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r14 + r13 + 16], 11 + QUAD $0x10166c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r14 + r10 + 16], 12 + WORD $0x894c; BYTE $0xd7 // mov rdi, r10 + LONG $0x2454894c; BYTE $0x10 // mov qword [rsp + 16], r10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x10066c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r14 + rax + 16], 13 + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] + QUAD $0x100e6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r14 + rcx + 16], 14 + LONG $0x2464894c; BYTE $0x40 // mov qword [rsp + 64], r12 + QUAD $0x10266c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r14 + r12 + 16], 15 + LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 + LONG $0xda0f4166; BYTE $0xdc // pminub xmm3, xmm12 + LONG $0x740f4166; BYTE $0xdd // pcmpeqb xmm3, xmm13 + QUAD $0x000100249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm3 + QUAD $0x180e7c203a0f4766; BYTE $0x01 // pinsrb xmm15, byte [r14 + r9 + 24], 1 + QUAD $0x18067c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r14 + r8 + 24], 2 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x180e7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r14 + r9 + 24], 3 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x18167c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r14 + r10 + 24], 4 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + QUAD $0x18067c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r14 + r8 + 24], 5 + QUAD $0x18367c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r14 + rsi + 24], 6 + QUAD $0x181e7c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r14 + r11 + 24], 7 + QUAD $0x183e7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r15 + 24], 8 + QUAD $0x181e7c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r14 + rbx + 24], 9 + QUAD $0x18167c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r14 + rdx + 24], 10 + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + QUAD $0x182e7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r14 + r13 + 24], 11 + QUAD $0x183e7c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r14 + rdi + 24], 12 + QUAD $0x18067c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r14 + rax + 24], 13 + QUAD $0x180e7c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r14 + rcx + 24], 14 + QUAD $0x18267c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r14 + r12 + 24], 15 + LONG $0x6f0f4166; BYTE $0xdf // movdqa xmm3, xmm15 + LONG $0xda0f4166; BYTE $0xdc // pminub xmm3, xmm12 + LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 + QUAD $0x0000e0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm3 + LONG $0x6f0f4466; BYTE $0xf4 // movdqa xmm14, xmm4 + LONG $0xda0f4566; BYTE $0xf4 // pminub xmm14, xmm12 + LONG $0x740f4466; BYTE $0xf4 // pcmpeqb xmm14, xmm4 + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + QUAD $0x000000a0a56f0f66 // movdqa xmm4, oword 160[rbp] /* [rip + .LCPI7_10] */ + LONG $0xdf0f4466; BYTE $0xec // pandn xmm13, xmm4 + LONG $0xfc0f4566; BYTE $0xee // paddb xmm13, xmm14 + LONG $0x6f0f4466; BYTE $0xf6 // movdqa xmm14, xmm6 + LONG $0xda0f4566; BYTE $0xf4 // pminub xmm14, xmm12 + LONG $0x740f4466; BYTE $0xf6 // pcmpeqb xmm14, xmm6 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + LONG $0x54b60f41; WORD $0x0d06 // movzx edx, byte [r14 + rax + 13] + LONG $0xf26e0f66 // movd xmm6, edx + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x03066c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rax + 3], 1 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x030e6c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rcx + 3], 2 + WORD $0x894c; BYTE $0xce // mov rsi, r9 + QUAD $0x030e6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r9 + 3], 3 + WORD $0x894c; BYTE $0xd7 // mov rdi, r10 + QUAD $0x03166c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r14 + r10 + 3], 4 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x03066c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r8 + 3], 5 + LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] + QUAD $0x030e6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r9 + 3], 6 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x033e6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r15 + 3], 7 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x03166c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r10 + 3], 8 + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] + QUAD $0x03066c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r8 + 3], 9 + QUAD $0x031e6c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r14 + r11 + 3], 10 + LONG $0x246c894c; BYTE $0x58 // mov qword [rsp + 88], r13 + QUAD $0x032e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r13 + 3], 11 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x031e6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rbx + 3], 12 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x03266c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r14 + r12 + 3], 13 + LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + QUAD $0x032e6c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r14 + r13 + 3], 14 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x031e6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r11 + 3], 15 + QUAD $0x04064c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rax + 4], 1 + QUAD $0x040e4c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rcx + 4], 2 + QUAD $0x04364c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r14 + rsi + 4], 3 + QUAD $0x043e4c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r14 + rdi + 4], 4 + QUAD $0x04164c203a0f4566; BYTE $0x05 // pinsrb xmm9, byte [r14 + rdx + 4], 5 + QUAD $0x040e4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r14 + r9 + 4], 6 + QUAD $0x043e4c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r15 + 4], 7 + QUAD $0x04164c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r10 + 4], 8 + QUAD $0x04064c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r14 + r8 + 4], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x041e4c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r14 + rbx + 4], 10 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x041e4c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r14 + rbx + 4], 11 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x041e4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r14 + rbx + 4], 12 + QUAD $0x04264c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r14 + r12 + 4], 13 + QUAD $0x042e4c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r14 + r13 + 4], 14 + QUAD $0x041e4c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r14 + r11 + 4], 15 + QUAD $0x05067c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rax + 5], 1 + QUAD $0x050e7c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rcx + 5], 2 + QUAD $0x05367c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r14 + rsi + 5], 3 + QUAD $0x053e7c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r14 + rdi + 5], 4 + QUAD $0x05167c203a0f4166; BYTE $0x05 // pinsrb xmm7, byte [r14 + rdx + 5], 5 + QUAD $0x050e7c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r14 + r9 + 5], 6 + QUAD $0x053e7c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r14 + r15 + 5], 7 + QUAD $0x05167c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r10 + 5], 8 + QUAD $0x05067c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r8 + 5], 9 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x051e7c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r14 + rbx + 5], 10 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x051e7c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r14 + rbx + 5], 11 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x051e7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r14 + rbx + 5], 12 + QUAD $0x05267c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r14 + r12 + 5], 13 + QUAD $0x052e7c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r14 + r13 + 5], 14 + QUAD $0x051e7c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r14 + r11 + 5], 15 + QUAD $0x060644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rax + 6], 1 + QUAD $0x060e44203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rcx + 6], 2 + QUAD $0x063644203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rsi + 6], 3 + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + QUAD $0x063e44203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rdi + 6], 4 + QUAD $0x061644203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rdx + 6], 5 + QUAD $0x060e44203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r14 + r9 + 6], 6 + QUAD $0x063e44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r15 + 6], 7 + QUAD $0x061644203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r10 + 6], 8 + QUAD $0x060644203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r8 + 6], 9 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x060e44203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r9 + 6], 10 + LONG $0x24448b48; BYTE $0x58 // mov rax, qword [rsp + 88] + QUAD $0x060644203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r14 + rax + 6], 11 + QUAD $0x061e44203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r14 + rbx + 6], 12 + QUAD $0x062644203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r14 + r12 + 6], 13 + LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 + QUAD $0x062e44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r14 + r13 + 6], 14 + QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI7_11] */ + LONG $0xdf0f4466; BYTE $0xf4 // pandn xmm14, xmm4 + LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 + LONG $0x6f0f4466; BYTE $0xfd // movdqa xmm15, xmm5 + LONG $0xda0f4566; BYTE $0xfc // pminub xmm15, xmm12 + LONG $0x740f4466; BYTE $0xfd // pcmpeqb xmm15, xmm5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + LONG $0x54b60f41; WORD $0x0e06 // movzx edx, byte [r14 + rax + 14] LONG $0xea6e0f66 // movd xmm5, edx - LONG $0x54b70f42; WORD $0x103e // movzx edx, word [rsi + r15 + 16] - LONG $0x74c40f66; WORD $0x023e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 2], 6 - LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d - LONG $0x44b70f42; WORD $0x123e // movzx eax, word [rsi + r15 + 18] - LONG $0x18244489 // mov dword [rsp + 24], eax - LONG $0x74c40f66; WORD $0x021e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 2], 7 - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xce6f0f66 // movdqa xmm1, xmm6 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xcef80f66 // psubb xmm1, xmm6 - LONG $0x6e0f4166; BYTE $0xf6 // movd xmm6, r14d - LONG $0x54b70f46; WORD $0x143e // movzx r10d, word [rsi + r15 + 20] - LONG $0xe0650f66 // pcmpgtw xmm4, xmm0 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - QUAD $0x01040654c40f4266 // pinsrw xmm2, word [rsi + r8 + 4], 1 - QUAD $0x02040e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 4], 2 - QUAD $0x03042654c40f4266 // pinsrw xmm2, word [rsi + r12 + 4], 3 - QUAD $0x04042e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 4], 4 - LONG $0x54c40f66; WORD $0x040e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 4], 5 - LONG $0x54c40f66; WORD $0x043e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 4], 6 - LONG $0x54c40f66; WORD $0x041e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 4], 7 - QUAD $0x0106066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 6], 1 - QUAD $0x02060e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 6], 2 - QUAD $0x0306266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 6], 3 - QUAD $0x04062e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 6], 4 - LONG $0x6cc40f66; WORD $0x060e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 6], 5 - LONG $0x6cc40f66; WORD $0x063e; BYTE $0x06 // pinsrw xmm5, word [rsi + rdi + 6], 6 - LONG $0x6cc40f66; WORD $0x061e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 6], 7 - QUAD $0x0108065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 8], 1 - QUAD $0x02080e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 8], 2 - QUAD $0x0308265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 8], 3 - QUAD $0x04082e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 8], 4 - LONG $0x5cc40f66; WORD $0x080e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 8], 5 - LONG $0x5cc40f66; WORD $0x083e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 8], 6 - LONG $0x5cc40f66; WORD $0x081e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 8], 7 - LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x7c6e0f66; WORD $0x2024 // movd xmm7, dword [rsp + 32] - LONG $0x44b70f42; WORD $0x163e // movzx eax, word [rsi + r15 + 22] - LONG $0xd0650f66 // pcmpgtw xmm2, xmm0 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x02 // psllw xmm2, 2 - LONG $0xdb0f4166; BYTE $0xd1 // pand xmm2, xmm9 - LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x5cb70f46; WORD $0x183e // movzx r11d, word [rsi + r15 + 24] - LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 - LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 - LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 - LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 - LONG $0xddeb0f66 // por xmm3, xmm5 + QUAD $0x000000c0a56f0f66 // movdqa xmm4, oword 192[rbp] /* [rip + .LCPI7_12] */ + LONG $0xdf0f4466; BYTE $0xfc // pandn xmm15, xmm4 + LONG $0xeb0f4566; BYTE $0xfe // por xmm15, xmm14 + LONG $0x54b60f41; WORD $0x0f06 // movzx edx, byte [r14 + rax + 15] + LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx + LONG $0xdb760f66 // pcmpeqd xmm3, xmm3 + LONG $0xf80f4466; BYTE $0xeb // psubb xmm13, xmm3 + LONG $0x760f4566; BYTE $0xf6 // pcmpeqd xmm14, xmm14 + LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 + LONG $0x6f0f4166; BYTE $0xe1 // movdqa xmm4, xmm9 + LONG $0xda0f4166; BYTE $0xe4 // pminub xmm4, xmm12 + LONG $0x740f4166; BYTE $0xe1 // pcmpeqb xmm4, xmm9 + LONG $0x6f0f4466; BYTE $0xcf // movdqa xmm9, xmm7 + LONG $0xda0f4566; BYTE $0xcc // pminub xmm9, xmm12 + LONG $0x740f4466; BYTE $0xcf // pcmpeqb xmm9, xmm7 + LONG $0x54b60f41; WORD $0x1106 // movzx edx, byte [r14 + rax + 17] + LONG $0xfa6e0f66 // movd xmm7, edx + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x060e44203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rcx + 6], 15 + QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI7_13] */ + LONG $0xe1df0f66 // pandn xmm4, xmm1 + QUAD $0x000000e08d6f0f66 // movdqa xmm1, oword 224[rbp] /* [rip + .LCPI7_14] */ + LONG $0xdf0f4466; BYTE $0xc9 // pandn xmm9, xmm1 + LONG $0xeb0f4466; BYTE $0xcc // por xmm9, xmm4 + LONG $0xe06f0f66 // movdqa xmm4, xmm0 + LONG $0xda0f4166; BYTE $0xe4 // pminub xmm4, xmm12 + LONG $0xe0740f66 // pcmpeqb xmm4, xmm0 + LONG $0x54b60f41; WORD $0x1206 // movzx edx, byte [r14 + rax + 18] + WORD $0x8949; BYTE $0xc2 // mov r10, rax LONG $0xca6e0f66 // movd xmm1, edx - LONG $0x54b70f42; WORD $0x1a3e // movzx edx, word [rsi + r15 + 26] - QUAD $0x010a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 10], 1 - QUAD $0x020a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 10], 2 - QUAD $0x030a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 10], 3 - QUAD $0x040a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 10], 4 - LONG $0x74c40f66; WORD $0x0a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 10], 5 - LONG $0x74c40f66; WORD $0x0a3e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 10], 6 - LONG $0x74c40f66; WORD $0x0a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 10], 7 - QUAD $0x010c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 12], 1 - QUAD $0x020c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 12], 2 - QUAD $0x030c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 12], 3 - QUAD $0x040c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 12], 4 - LONG $0x7cc40f66; WORD $0x0c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 12], 5 - LONG $0x7cc40f66; WORD $0x0c3e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 12], 6 - LONG $0x7cc40f66; WORD $0x0c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 12], 7 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4466; WORD $0x2444; BYTE $0x18 // movd xmm8, dword [rsp + 24] - LONG $0x74b70f46; WORD $0x1c3e // movzx r14d, word [rsi + r15 + 28] - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0xf8650f66 // pcmpgtw xmm7, xmm0 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 - LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 - LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xea // movd xmm5, r10d - LONG $0x54b70f46; WORD $0x1e3e // movzx r10d, word [rsi + r15 + 30] - QUAD $0x010e0664c40f4266 // pinsrw xmm4, word [rsi + r8 + 14], 1 - QUAD $0x020e0e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 14], 2 - QUAD $0x030e2664c40f4266 // pinsrw xmm4, word [rsi + r12 + 14], 3 - QUAD $0x040e2e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 14], 4 - LONG $0x64c40f66; WORD $0x0e0e; BYTE $0x05 // pinsrw xmm4, word [rsi + rcx + 14], 5 - LONG $0x64c40f66; WORD $0x0e3e; BYTE $0x06 // pinsrw xmm4, word [rsi + rdi + 14], 6 - LONG $0x64c40f66; WORD $0x0e1e; BYTE $0x07 // pinsrw xmm4, word [rsi + rbx + 14], 7 - QUAD $0x01120644c40f4666 // pinsrw xmm8, word [rsi + r8 + 18], 1 - QUAD $0x02120e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 18], 2 - QUAD $0x03122644c40f4666 // pinsrw xmm8, word [rsi + r12 + 18], 3 - QUAD $0x04122e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 18], 4 - QUAD $0x05120e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 18], 5 - QUAD $0x06123e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 18], 6 - QUAD $0x07121e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 18], 7 - LONG $0xe0650f66 // pcmpgtw xmm4, xmm0 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 - LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 - LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f42; WORD $0x203e // movzx eax, word [rsi + r15 + 32] - LONG $0xe3eb0f66 // por xmm4, xmm3 - LONG $0x650f4466; BYTE $0xc0 // pcmpgtw xmm8, xmm0 - LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 - LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf80f4166; BYTE $0xf8 // psubb xmm7, xmm8 - LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d - LONG $0x5cb70f46; WORD $0x223e // movzx r11d, word [rsi + r15 + 34] - QUAD $0x0110064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 16], 1 - QUAD $0x02100e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 16], 2 - QUAD $0x0310264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 16], 3 - QUAD $0x04102e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 16], 4 - LONG $0x4cc40f66; WORD $0x100e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 16], 5 - LONG $0x4cc40f66; WORD $0x103e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 16], 6 - LONG $0x4cc40f66; WORD $0x101e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 16], 7 - LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0xf26e0f66 // movd xmm6, edx - LONG $0x54b70f42; WORD $0x243e // movzx edx, word [rsi + r15 + 36] - LONG $0x30245489 // mov dword [rsp + 48], edx - QUAD $0x0114066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 20], 1 - QUAD $0x02140e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 20], 2 - QUAD $0x0314266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 20], 3 - QUAD $0x04142e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 20], 4 - LONG $0x6cc40f66; WORD $0x140e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 20], 5 - LONG $0x6cc40f66; WORD $0x143e; BYTE $0x06 // pinsrw xmm5, word [rsi + rdi + 20], 6 - LONG $0x6cc40f66; WORD $0x141e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 20], 7 - LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 - LONG $0xefeb0f66 // por xmm5, xmm7 - LONG $0x6e0f4166; BYTE $0xfe // movd xmm7, r14d - LONG $0x54b70f42; WORD $0x263e // movzx edx, word [rsi + r15 + 38] - LONG $0x18245489 // mov dword [rsp + 24], edx - QUAD $0x01160654c40f4266 // pinsrw xmm2, word [rsi + r8 + 22], 1 - QUAD $0x02160e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 22], 2 - QUAD $0x03162654c40f4266 // pinsrw xmm2, word [rsi + r12 + 22], 3 - QUAD $0x04162e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 22], 4 - LONG $0x54c40f66; WORD $0x160e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 22], 5 - LONG $0x54c40f66; WORD $0x163e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 22], 6 - LONG $0x54c40f66; WORD $0x161e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 22], 7 - QUAD $0x0118065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 24], 1 - QUAD $0x02180e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 24], 2 - QUAD $0x0318265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 24], 3 - QUAD $0x04182e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 24], 4 - LONG $0x5cc40f66; WORD $0x180e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 24], 5 - LONG $0x5cc40f66; WORD $0x183e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 24], 6 - LONG $0x5cc40f66; WORD $0x181e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 24], 7 - LONG $0xd0650f66 // pcmpgtw xmm2, xmm0 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x04 // psllw xmm3, 4 - LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x74b70f46; WORD $0x283e // movzx r14d, word [rsi + r15 + 40] - LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f42; WORD $0x2a3e // movzx eax, word [rsi + r15 + 42] - LONG $0x20244489 // mov dword [rsp + 32], eax - QUAD $0x011a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 26], 1 - QUAD $0x021a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 26], 2 - QUAD $0x031a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 26], 3 - QUAD $0x041a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 26], 4 - LONG $0x74c40f66; WORD $0x1a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 26], 5 - LONG $0x74c40f66; WORD $0x1a3e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 26], 6 - LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 26], 7 - QUAD $0x011c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 28], 1 - QUAD $0x021c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 28], 2 - QUAD $0x031c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 28], 3 - QUAD $0x041c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 28], 4 - LONG $0x7cc40f66; WORD $0x1c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 28], 5 - LONG $0x7cc40f66; WORD $0x1c3e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 28], 6 - LONG $0x7cc40f66; WORD $0x1c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 28], 7 - QUAD $0x011e0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 30], 1 - QUAD $0x021e0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 30], 2 - QUAD $0x031e2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 30], 3 - QUAD $0x041e2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 30], 4 - LONG $0x54c40f66; WORD $0x1e0e; BYTE $0x05 // pinsrw xmm2, word [rsi + rcx + 30], 5 - LONG $0x54c40f66; WORD $0x1e3e; BYTE $0x06 // pinsrw xmm2, word [rsi + rdi + 30], 6 - LONG $0x54c40f66; WORD $0x1e1e; BYTE $0x07 // pinsrw xmm2, word [rsi + rbx + 30], 7 - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0xf8650f66 // pcmpgtw xmm7, xmm0 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 - LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 - LONG $0xfeeb0f66 // por xmm7, xmm6 - LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d - LONG $0x54b70f46; WORD $0x2c3e // movzx r10d, word [rsi + r15 + 44] - LONG $0xd0650f66 // pcmpgtw xmm2, xmm0 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 - LONG $0xdb0f4166; BYTE $0xd6 // pand xmm2, xmm14 - LONG $0xd7eb0f66 // por xmm2, xmm7 - LONG $0x746e0f66; WORD $0x3024 // movd xmm6, dword [rsp + 48] - LONG $0x54b70f42; WORD $0x2e3e // movzx edx, word [rsi + r15 + 46] - QUAD $0x0120066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 32], 1 - QUAD $0x02200e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 32], 2 - QUAD $0x0320266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 32], 3 - QUAD $0x04202e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 32], 4 - LONG $0x6cc40f66; WORD $0x200e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 32], 5 - LONG $0x6cc40f66; WORD $0x203e; BYTE $0x06 // pinsrw xmm5, word [rsi + rdi + 32], 6 - QUAD $0x0122064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 34], 1 - QUAD $0x02220e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 34], 2 - QUAD $0x0322264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 34], 3 - QUAD $0x04222e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 34], 4 - LONG $0x4cc40f66; WORD $0x220e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 34], 5 - LONG $0x4cc40f66; WORD $0x223e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 34], 6 - LONG $0x4cc40f66; WORD $0x221e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 34], 7 - LONG $0xd3eb0f66 // por xmm2, xmm3 - LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xf96f0f66 // movdqa xmm7, xmm1 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf9f80f66 // psubb xmm7, xmm1 - LONG $0x5c6e0f66; WORD $0x1824 // movd xmm3, dword [rsp + 24] - LONG $0x5cb70f46; WORD $0x303e // movzx r11d, word [rsi + r15 + 48] - LONG $0x6cc40f66; WORD $0x201e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 32], 7 - LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - QUAD $0x01240674c40f4266 // pinsrw xmm6, word [rsi + r8 + 36], 1 - QUAD $0x02240e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 36], 2 - QUAD $0x03242674c40f4266 // pinsrw xmm6, word [rsi + r12 + 36], 3 - QUAD $0x04242e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 36], 4 - LONG $0x74c40f66; WORD $0x240e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 36], 5 - LONG $0x74c40f66; WORD $0x243e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 36], 6 - LONG $0x74c40f66; WORD $0x241e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 36], 7 - QUAD $0x0126065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 38], 1 - QUAD $0x02260e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 38], 2 - QUAD $0x0326265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 38], 3 - QUAD $0x04262e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 38], 4 - LONG $0x5cc40f66; WORD $0x260e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 38], 5 - LONG $0x5cc40f66; WORD $0x263e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 38], 6 - LONG $0x5cc40f66; WORD $0x261e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 38], 7 - LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d - QUAD $0x0128066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 40], 1 - QUAD $0x02280e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 40], 2 - QUAD $0x0328266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 40], 3 - QUAD $0x04282e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 40], 4 - LONG $0x6cc40f66; WORD $0x280e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 40], 5 - LONG $0x6cc40f66; WORD $0x283e; BYTE $0x06 // pinsrw xmm5, word [rsi + rdi + 40], 6 - LONG $0x44b70f42; WORD $0x323e // movzx eax, word [rsi + r15 + 50] - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 - LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 - LONG $0xf7eb0f66 // por xmm6, xmm7 - LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] - LONG $0x74b70f46; WORD $0x343e // movzx r14d, word [rsi + r15 + 52] - LONG $0x6cc40f66; WORD $0x281e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 40], 7 - LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x03 // psllw xmm3, 3 - LONG $0xdb0f4166; BYTE $0xda // pand xmm3, xmm10 - LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 - LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 - LONG $0xebeb0f66 // por xmm5, xmm3 - LONG $0x6e0f4166; BYTE $0xfa // movd xmm7, r10d - LONG $0x54b70f46; WORD $0x363e // movzx r10d, word [rsi + r15 + 54] - QUAD $0x012a064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 42], 1 - QUAD $0x022a0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 42], 2 - QUAD $0x032a264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 42], 3 - QUAD $0x042a2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 42], 4 - LONG $0x4cc40f66; WORD $0x2a0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 42], 5 - LONG $0x4cc40f66; WORD $0x2a3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 42], 6 - LONG $0x4cc40f66; WORD $0x2a1e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 42], 7 - QUAD $0x012c067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 44], 1 - QUAD $0x022c0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 44], 2 - QUAD $0x032c267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 44], 3 - QUAD $0x042c2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 44], 4 - LONG $0x7cc40f66; WORD $0x2c0e; BYTE $0x05 // pinsrw xmm7, word [rsi + rcx + 44], 5 - LONG $0x7cc40f66; WORD $0x2c3e; BYTE $0x06 // pinsrw xmm7, word [rsi + rdi + 44], 6 - LONG $0xeeeb0f66 // por xmm5, xmm6 + QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x073644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rsi + 7], 1 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x070644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rax + 7], 2 + QUAD $0x071e44203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r14 + r11 + 7], 3 + QUAD $0x073e44203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rdi + 7], 4 + WORD $0x8949; BYTE $0xfc // mov r12, rdi + LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] + QUAD $0x073e44203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rdi + 7], 5 + LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] + QUAD $0x070644203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r14 + r8 + 7], 6 + WORD $0x894d; BYTE $0xfb // mov r11, r15 + QUAD $0x073e44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r15 + 7], 7 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x073e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r15 + 7], 8 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x071644203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r14 + rdx + 7], 9 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + QUAD $0x070e44203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r14 + r9 + 7], 10 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x072e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r13 + 7], 11 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x071644203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r14 + rdx + 7], 12 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x071644203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r14 + rdx + 7], 13 + LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] + QUAD $0x070e44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r14 + r9 + 7], 14 + QUAD $0x070e44203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r14 + rcx + 7], 15 + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI7_15] */ + LONG $0xe3df0f66 // pandn xmm4, xmm3 + LONG $0xeb0f4166; BYTE $0xe1 // por xmm4, xmm9 + LONG $0x6f0f4466; BYTE $0xc8 // movdqa xmm9, xmm0 + LONG $0xda0f4566; BYTE $0xcc // pminub xmm9, xmm12 + LONG $0x740f4466; BYTE $0xc8 // pcmpeqb xmm9, xmm0 + LONG $0x54b60f43; WORD $0x1316 // movzx edx, byte [r14 + r10 + 19] LONG $0xda6e0f66 // movd xmm3, edx - LONG $0x54b70f42; WORD $0x383e // movzx edx, word [rsi + r15 + 56] - LONG $0x7cc40f66; WORD $0x2c1e; BYTE $0x07 // pinsrw xmm7, word [rsi + rbx + 44], 7 - LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x05 // psllw xmm1, 5 - LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 - LONG $0xf8650f66 // pcmpgtw xmm7, xmm0 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x06 // psllw xmm7, 6 - LONG $0xdb0f4166; BYTE $0xfd // pand xmm7, xmm13 - LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - LONG $0x5cb70f46; WORD $0x3a3e // movzx r11d, word [rsi + r15 + 58] - QUAD $0x012e065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 46], 1 - QUAD $0x022e0e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 46], 2 - QUAD $0x032e265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 46], 3 - QUAD $0x042e2e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 46], 4 - LONG $0x5cc40f66; WORD $0x2e0e; BYTE $0x05 // pinsrw xmm3, word [rsi + rcx + 46], 5 - LONG $0x5cc40f66; WORD $0x2e3e; BYTE $0x06 // pinsrw xmm3, word [rsi + rdi + 46], 6 - LONG $0x5cc40f66; WORD $0x2e1e; BYTE $0x07 // pinsrw xmm3, word [rsi + rbx + 46], 7 - LONG $0xd8650f66 // pcmpgtw xmm3, xmm0 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0xdfeb0f66 // por xmm3, xmm7 - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x44b70f42; WORD $0x3c3e // movzx eax, word [rsi + r15 + 60] - LONG $0x7cb70f46; WORD $0x3e3e // movzx r15d, word [rsi + r15 + 62] - QUAD $0x0132064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 50], 1 - QUAD $0x02320e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 50], 2 - QUAD $0x0332264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 50], 3 - QUAD $0x04322e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 50], 4 - LONG $0x4cc40f66; WORD $0x320e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 50], 5 - LONG $0x4cc40f66; WORD $0x323e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 50], 6 - LONG $0x4cc40f66; WORD $0x321e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 50], 7 - LONG $0xddeb0f66 // por xmm3, xmm5 - LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xe96f0f66 // movdqa xmm5, xmm1 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xe9f80f66 // psubb xmm5, xmm1 - LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d - LONG $0x24348b4c // mov r14, qword [rsp] - QUAD $0x01300674c40f4266 // pinsrw xmm6, word [rsi + r8 + 48], 1 - QUAD $0x02300e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 48], 2 - QUAD $0x03302674c40f4266 // pinsrw xmm6, word [rsi + r12 + 48], 3 - QUAD $0x04302e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 48], 4 - LONG $0x74c40f66; WORD $0x300e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 48], 5 - LONG $0x74c40f66; WORD $0x303e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 48], 6 - LONG $0x74c40f66; WORD $0x301e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 48], 7 - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - QUAD $0x0134064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 52], 1 - QUAD $0x02340e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 52], 2 - QUAD $0x0334264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 52], 3 - QUAD $0x04342e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 52], 4 - LONG $0x4cc40f66; WORD $0x340e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 52], 5 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0x4cc40f66; WORD $0x343e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 52], 6 - LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d - LONG $0x4cc40f66; WORD $0x341e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 52], 7 - LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x02 // psllw xmm1, 2 - LONG $0xdb0f4166; BYTE $0xc9 // pand xmm1, xmm9 - LONG $0xcdeb0f66 // por xmm1, xmm5 + LONG $0xef0f4566; BYTE $0xce // pxor xmm9, xmm14 + LONG $0x710f4166; WORD $0x07f1 // psllw xmm9, 7 + LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI7_6] */ + LONG $0xdb0f4466; BYTE $0xc8 // pand xmm9, xmm0 + LONG $0xeb0f4466; BYTE $0xcc // por xmm9, xmm4 + LONG $0x6f0f4166; BYTE $0xe1 // movdqa xmm4, xmm9 + LONG $0x54b60f43; WORD $0x1416 // movzx edx, byte [r14 + r10 + 20] + LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + QUAD $0x093644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rsi + 9], 1 + QUAD $0x090644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rax + 9], 2 + WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x091644203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdx + 9], 3 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x092644203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r12 + 9], 4 + QUAD $0x093e44203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rdi + 9], 5 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + QUAD $0x090644203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r14 + r8 + 9], 6 + QUAD $0x091e44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r11 + 9], 7 + WORD $0x894d; BYTE $0xfc // mov r12, r15 + QUAD $0x093e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r15 + 9], 8 + LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] + QUAD $0x093e44203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r14 + rdi + 9], 9 + QUAD $0x091e44203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rbx + 9], 10 + QUAD $0x092e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r13 + 9], 11 + WORD $0x894d; BYTE $0xef // mov r15, r13 + LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] + QUAD $0x090644203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r14 + r8 + 9], 12 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x092e44203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r14 + r13 + 9], 13 + QUAD $0x090e44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r14 + r9 + 9], 14 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x091e44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r11 + 9], 15 + QUAD $0x0a3654203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r14 + rsi + 10], 1 + QUAD $0x0a1654203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r14 + r10 + 10], 2 + QUAD $0x0a1654203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r14 + rdx + 10], 3 + QUAD $0x0a0654203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r14 + rax + 10], 4 + WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0a3654203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r14 + rsi + 10], 5 + QUAD $0x0a0e54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r14 + rcx + 10], 6 + LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] + QUAD $0x0a3e54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r14 + rdi + 10], 7 + QUAD $0x0a2654203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r14 + r12 + 10], 8 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0a2654203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r14 + r12 + 10], 9 + QUAD $0x0a1e54203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r14 + rbx + 10], 10 + QUAD $0x0a3e54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r14 + r15 + 10], 11 + QUAD $0x0a0654203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r14 + r8 + 10], 12 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + QUAD $0x0a2e54203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r14 + r13 + 10], 13 + QUAD $0x0a0e54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r14 + r9 + 10], 14 + QUAD $0x0a1e54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r14 + r11 + 10], 15 + LONG $0xeb0f4166; BYTE $0xe7 // por xmm4, xmm15 + QUAD $0x0000b024a47f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm4 + LONG $0xe06f0f66 // movdqa xmm4, xmm0 + LONG $0xda0f4166; BYTE $0xe4 // pminub xmm4, xmm12 + LONG $0xe0740f66 // pcmpeqb xmm4, xmm0 + LONG $0x6f0f4466; BYTE $0xec // movdqa xmm13, xmm4 + QUAD $0x0000a0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 160[rbp] /* [rip + .LCPI7_10] */ + LONG $0xdf0f4566; BYTE $0xee // pandn xmm13, xmm14 + LONG $0xfc0f4466; BYTE $0xec // paddb xmm13, xmm4 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0xda0f4166; BYTE $0xc4 // pminub xmm0, xmm12 + LONG $0xc2740f66 // pcmpeqb xmm0, xmm2 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + LONG $0x54b60f41; WORD $0x1506 // movzx edx, byte [r14 + rax + 21] + LONG $0xe26e0f66 // movd xmm4, edx + LONG $0xdf0f4566; BYTE $0xd6 // pandn xmm10, xmm14 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0b0e5c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rcx + 11], 1 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0b165c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rdx + 11], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x0b165c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r14 + rdx + 11], 3 + QUAD $0x0b165c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r14 + r10 + 11], 4 + QUAD $0x0b365c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r14 + rsi + 11], 5 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x0b165c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r14 + rdx + 11], 6 + QUAD $0x0b3e5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r14 + rdi + 11], 7 + LONG $0x244c8b4c; BYTE $0x20 // mov r9, qword [rsp + 32] + QUAD $0x0b0e5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r14 + r9 + 11], 8 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + QUAD $0x0b265c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r12 + 11], 9 + QUAD $0x0b1e5c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r14 + rbx + 11], 10 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x0b165c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r14 + rdx + 11], 11 + QUAD $0x0b3e5c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r14 + r15 + 11], 12 + WORD $0x894d; BYTE $0xec // mov r12, r13 + QUAD $0x0b2e5c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r14 + r13 + 11], 13 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0b165c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r14 + rdx + 11], 14 + QUAD $0x0b1e5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r11 + 11], 15 + QUAD $0x000000b085df0f66 // pandn xmm0, oword 176[rbp] /* [rip + .LCPI7_11] */ + LONG $0xeb0f4166; BYTE $0xc2 // por xmm0, xmm10 + LONG $0x6f0f4566; BYTE $0xd3 // movdqa xmm10, xmm11 + LONG $0xda0f4566; BYTE $0xd4 // pminub xmm10, xmm12 + LONG $0x740f4566; BYTE $0xd3 // pcmpeqb xmm10, xmm11 + LONG $0x54b60f41; WORD $0x1606 // movzx edx, byte [r14 + rax + 22] + LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx + QUAD $0x0000c095df0f4466; BYTE $0x00 // pandn xmm10, oword 192[rbp] /* [rip + .LCPI7_12] */ + LONG $0xeb0f4466; BYTE $0xd0 // por xmm10, xmm0 + LONG $0x54b60f41; WORD $0x1706 // movzx edx, byte [r14 + rax + 23] + LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx + QUAD $0x00014024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 320] + QUAD $0x0c0e44203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rcx + 12], 1 + WORD $0x8949; BYTE $0xca // mov r10, rcx + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0c3e44203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r14 + r15 + 12], 2 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0c0e44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rcx + 12], 3 + QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] + QUAD $0x0c3644203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r14 + rsi + 12], 4 + LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] + QUAD $0x0c1e44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r14 + r11 + 12], 5 + LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] + QUAD $0x0c3e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rdi + 12], 6 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0c0644203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r14 + rax + 12], 7 + QUAD $0x0c0e44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r14 + r9 + 12], 8 + QUAD $0x0c0644203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r8 + 12], 9 + QUAD $0x0c1e44203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rbx + 12], 10 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x0c2e44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r13 + 12], 11 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0c1644203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r14 + rdx + 12], 12 + QUAD $0x0c2644203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r14 + r12 + 12], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0c0644203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r14 + rax + 12], 14 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x0c0e44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r9 + 12], 15 + QUAD $0x0d1674203a0f4366; BYTE $0x01 // pinsrb xmm6, byte [r14 + r10 + 13], 1 + QUAD $0x0d3e74203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r14 + r15 + 13], 2 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x0d0e74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rcx + 13], 3 + WORD $0x8949; BYTE $0xca // mov r10, rcx + QUAD $0x0d3674203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r14 + rsi + 13], 4 + QUAD $0x0d1e74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r14 + r11 + 13], 5 + WORD $0x894d; BYTE $0xdf // mov r15, r11 + QUAD $0x0d3e74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rdi + 13], 6 + WORD $0x8949; BYTE $0xfb // mov r11, rdi + LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] + QUAD $0x0d3e74203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r14 + rdi + 13], 7 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x0d0e74203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r14 + rcx + 13], 8 + QUAD $0x0d0674203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r8 + 13], 9 + QUAD $0x0d1e74203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r14 + rbx + 13], 10 + QUAD $0x0d2e74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r13 + 13], 11 + QUAD $0x0d1674203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rdx + 13], 12 + QUAD $0x0d2674203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r12 + 13], 13 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0d1674203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r14 + rdx + 13], 14 + QUAD $0x0d0e74203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r14 + r9 + 13], 15 + QUAD $0x000100adf80f4466; BYTE $0x00 // psubb xmm13, oword 256[rbp] /* [rip + .LCPI7_16] */ + LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 + LONG $0xd06f0f66 // movdqa xmm2, xmm0 + LONG $0x6f0f4566; BYTE $0xec // movdqa xmm13, xmm12 + LONG $0xda0f4166; BYTE $0xd4 // pminub xmm2, xmm12 + LONG $0xd0740f66 // pcmpeqb xmm2, xmm0 + LONG $0xc66f0f66 // movdqa xmm0, xmm6 + LONG $0xda0f4166; BYTE $0xc4 // pminub xmm0, xmm12 + LONG $0xc6740f66 // pcmpeqb xmm0, xmm6 + LONG $0x24548b48; BYTE $0x78 // mov rdx, qword [rsp + 120] + LONG $0x54b60f41; WORD $0x1916 // movzx edx, byte [r14 + rdx + 25] + LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0e0e6c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rcx + 14], 1 + QUAD $0x0e066c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rax + 14], 2 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + QUAD $0x0e166c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r14 + r10 + 14], 3 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + QUAD $0x0e366c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r14 + rsi + 14], 4 + WORD $0x894c; BYTE $0xf9 // mov rcx, r15 + QUAD $0x0e3e6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r14 + r15 + 14], 5 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + QUAD $0x0e1e6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r14 + r11 + 14], 6 + WORD $0x8949; BYTE $0xfb // mov r11, rdi + QUAD $0x0e3e6c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r14 + rdi + 14], 7 + LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + QUAD $0x0e3e6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r14 + r15 + 14], 8 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + QUAD $0x0e066c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r8 + 14], 9 + WORD $0x8948; BYTE $0xdf // mov rdi, rbx + QUAD $0x0e1e6c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r14 + rbx + 14], 10 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x0e2e6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r13 + 14], 11 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x0e2e6c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r14 + r13 + 14], 12 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0e066c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r14 + rax + 14], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e066c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r14 + rax + 14], 14 + QUAD $0x0e0e6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r9 + 14], 15 + LONG $0x244c8b4c; BYTE $0x30 // mov r9, qword [rsp + 48] + QUAD $0x0f0e44203a0f4766; BYTE $0x01 // pinsrb xmm8, byte [r14 + r9 + 15], 1 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + QUAD $0x0f0644203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r14 + r8 + 15], 2 + QUAD $0x0f1644203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rdx + 15], 3 + QUAD $0x0f2644203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r14 + r12 + 15], 4 + QUAD $0x0f0e44203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r14 + rcx + 15], 5 + QUAD $0x0f3644203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r14 + rsi + 15], 6 + QUAD $0x0f1e44203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r11 + 15], 7 + QUAD $0x0f3e44203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r14 + r15 + 15], 8 + QUAD $0x0f1644203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r10 + 15], 9 + QUAD $0x0f3e44203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rdi + 15], 10 + QUAD $0x0f1e44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r14 + rbx + 15], 11 + QUAD $0x0f2e44203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r14 + r13 + 15], 12 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x0f0644203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r14 + rax + 15], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0f0644203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r14 + rax + 15], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x0f0644203a0f4566; BYTE $0x0f // pinsrb xmm8, byte [r14 + rax + 15], 15 + QUAD $0x110e7c203a0f4366; BYTE $0x01 // pinsrb xmm7, byte [r14 + r9 + 17], 1 + QUAD $0x11067c203a0f4366; BYTE $0x02 // pinsrb xmm7, byte [r14 + r8 + 17], 2 + QUAD $0x11167c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r14 + rdx + 17], 3 + QUAD $0x11267c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r14 + r12 + 17], 4 + QUAD $0x110e7c203a0f4166; BYTE $0x05 // pinsrb xmm7, byte [r14 + rcx + 17], 5 + QUAD $0x11367c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r14 + rsi + 17], 6 + QUAD $0x111e7c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r14 + r11 + 17], 7 + QUAD $0x113e7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r14 + r15 + 17], 8 + QUAD $0x11167c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r10 + 17], 9 + QUAD $0x113e7c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r14 + rdi + 17], 10 + QUAD $0x111e7c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r14 + rbx + 17], 11 + QUAD $0x112e7c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r14 + r13 + 17], 12 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x11067c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r14 + rax + 17], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x11067c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r14 + rax + 17], 14 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x11067c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r14 + rax + 17], 15 + QUAD $0x120e4c203a0f4366; BYTE $0x01 // pinsrb xmm1, byte [r14 + r9 + 18], 1 + QUAD $0x12064c203a0f4366; BYTE $0x02 // pinsrb xmm1, byte [r14 + r8 + 18], 2 + QUAD $0x12164c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r14 + rdx + 18], 3 + QUAD $0x12264c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r14 + r12 + 18], 4 + QUAD $0x120e4c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r14 + rcx + 18], 5 + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + QUAD $0x12364c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rsi + 18], 6 + QUAD $0x121e4c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r14 + r11 + 18], 7 + QUAD $0x123e4c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r14 + r15 + 18], 8 + QUAD $0x12164c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r10 + 18], 9 + WORD $0x894d; BYTE $0xd3 // mov r11, r10 + QUAD $0x123e4c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r14 + rdi + 18], 10 + WORD $0x8949; BYTE $0xfa // mov r10, rdi + QUAD $0x121e4c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r14 + rbx + 18], 11 + WORD $0x8948; BYTE $0xd9 // mov rcx, rbx + QUAD $0x122e4c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r14 + r13 + 18], 12 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x12064c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r14 + r8 + 18], 13 + QUAD $0x000000d095df0f66 // pandn xmm2, oword 208[rbp] /* [rip + .LCPI7_13] */ + QUAD $0x000000e085df0f66 // pandn xmm0, oword 224[rbp] /* [rip + .LCPI7_14] */ + LONG $0xc2eb0f66 // por xmm0, xmm2 + LONG $0xd56f0f66 // movdqa xmm2, xmm5 + LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 + LONG $0xd5740f66 // pcmpeqb xmm2, xmm5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + LONG $0x54b60f41; WORD $0x1a06 // movzx edx, byte [r14 + rax + 26] LONG $0xea6e0f66 // movd xmm5, edx - QUAD $0x01360674c40f4266 // pinsrw xmm6, word [rsi + r8 + 54], 1 - QUAD $0x02360e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 54], 2 - QUAD $0x03362674c40f4266 // pinsrw xmm6, word [rsi + r12 + 54], 3 - QUAD $0x04362e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 54], 4 - LONG $0x74c40f66; WORD $0x360e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 54], 5 - LONG $0x74c40f66; WORD $0x363e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 54], 6 - LONG $0x74c40f66; WORD $0x361e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 54], 7 - QUAD $0x0138066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 56], 1 - QUAD $0x02380e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 56], 2 - QUAD $0x0338266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 56], 3 - QUAD $0x04382e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 56], 4 - LONG $0x6cc40f66; WORD $0x380e; BYTE $0x05 // pinsrw xmm5, word [rsi + rcx + 56], 5 - LONG $0x6cc40f66; WORD $0x383e; BYTE $0x06 // pinsrw xmm5, word [rsi + rdi + 56], 6 - LONG $0x6cc40f66; WORD $0x381e; BYTE $0x07 // pinsrw xmm5, word [rsi + rbx + 56], 7 - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x03 // psllw xmm6, 3 - LONG $0xdb0f4166; BYTE $0xf2 // pand xmm6, xmm10 - LONG $0xe8650f66 // pcmpgtw xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 - LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 - LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6e0f4166; BYTE $0xf3 // movd xmm6, r11d - QUAD $0x013a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 58], 1 - QUAD $0x023a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 58], 2 - QUAD $0x033a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 58], 3 - QUAD $0x043a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 58], 4 - LONG $0x74c40f66; WORD $0x3a0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 58], 5 - LONG $0x74c40f66; WORD $0x3a3e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 58], 6 - LONG $0x74c40f66; WORD $0x3a1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 58], 7 - LONG $0xe9eb0f66 // por xmm5, xmm1 - LONG $0xc86e0f66 // movd xmm1, eax - QUAD $0x013c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 60], 1 - QUAD $0x023c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 60], 2 - QUAD $0x033c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 60], 3 - QUAD $0x043c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 60], 4 - LONG $0x4cc40f66; WORD $0x3c0e; BYTE $0x05 // pinsrw xmm1, word [rsi + rcx + 60], 5 - LONG $0x4cc40f66; WORD $0x3c3e; BYTE $0x06 // pinsrw xmm1, word [rsi + rdi + 60], 6 - LONG $0x4cc40f66; WORD $0x3c1e; BYTE $0x07 // pinsrw xmm1, word [rsi + rbx + 60], 7 - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x06 // psllw xmm1, 6 - LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 - LONG $0xceeb0f66 // por xmm1, xmm6 - LONG $0x6e0f4166; BYTE $0xf7 // movd xmm6, r15d - QUAD $0x013e0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 62], 1 - QUAD $0x023e0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 62], 2 - QUAD $0x033e2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 62], 3 - QUAD $0x043e2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 62], 4 - LONG $0x74c40f66; WORD $0x3e0e; BYTE $0x05 // pinsrw xmm6, word [rsi + rcx + 62], 5 - LONG $0x74c40f66; WORD $0x3e3e; BYTE $0x06 // pinsrw xmm6, word [rsi + rdi + 62], 6 - LONG $0x74c40f66; WORD $0x3e1e; BYTE $0x07 // pinsrw xmm6, word [rsi + rbx + 62], 7 - LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 - LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x12164c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r14 + rdx + 18], 14 + QUAD $0x000000f095df0f66 // pandn xmm2, oword 240[rbp] /* [rip + .LCPI7_15] */ + LONG $0xd0eb0f66 // por xmm2, xmm0 + LONG $0x6f0f4166; BYTE $0xf0 // movdqa xmm6, xmm8 + LONG $0xda0f4166; BYTE $0xf5 // pminub xmm6, xmm13 + LONG $0x740f4166; BYTE $0xf0 // pcmpeqb xmm6, xmm8 + LONG $0x54b60f41; WORD $0x1b06 // movzx edx, byte [r14 + rax + 27] + LONG $0xc26e0f66 // movd xmm0, edx + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x121e4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r14 + rbx + 18], 15 + QUAD $0x00000100b5ef0f66 // pxor xmm6, oword 256[rbp] /* [rip + .LCPI7_16] */ LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 - LONG $0xdb0f4166; BYTE $0xf6 // pand xmm6, xmm14 - LONG $0xf1eb0f66 // por xmm6, xmm1 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0xcc6f0f66 // movdqa xmm1, xmm4 - LONG $0xca6c0f66 // punpcklqdq xmm1, xmm2 - LONG $0xeb6f0f66 // movdqa xmm5, xmm3 - LONG $0xee6c0f66 // punpcklqdq xmm5, xmm6 - QUAD $0x00000090bd6f0f66 // movdqa xmm7, oword 144[rbp] /* [rip + .LCPI7_9] */ - LONG $0x00380f66; BYTE $0xef // pshufb xmm5, xmm7 - LONG $0x00380f66; BYTE $0xcf // pshufb xmm1, xmm7 - LONG $0xcd610f66 // punpcklwd xmm1, xmm5 - LONG $0xde600f66 // punpcklbw xmm3, xmm6 - LONG $0xe2600f66 // punpcklbw xmm4, xmm2 - LONG $0xe3610f66 // punpcklwd xmm4, xmm3 + LONG $0x75db0f66; BYTE $0x60 // pand xmm6, oword 96[rbp] /* [rip + .LCPI7_6] */ + LONG $0xf2eb0f66 // por xmm6, xmm2 + LONG $0x54b60f41; WORD $0x1c06 // movzx edx, byte [r14 + rax + 28] + LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx + LONG $0xeb0f4166; BYTE $0xf2 // por xmm6, xmm10 + QUAD $0x0000d024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm6 + LONG $0xd76f0f66 // movdqa xmm2, xmm7 + LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 + LONG $0xd7740f66 // pcmpeqb xmm2, xmm7 + LONG $0x6f0f4466; BYTE $0xf2 // movdqa xmm14, xmm2 + QUAD $0x0000a0b5df0f4466; BYTE $0x00 // pandn xmm14, oword 160[rbp] /* [rip + .LCPI7_10] */ + LONG $0xfc0f4466; BYTE $0xf2 // paddb xmm14, xmm2 + LONG $0x6f0f4466; BYTE $0xd1 // movdqa xmm10, xmm1 + LONG $0xda0f4566; BYTE $0xd5 // pminub xmm10, xmm13 + LONG $0x740f4466; BYTE $0xd1 // pcmpeqb xmm10, xmm1 + LONG $0x54b60f41; WORD $0x1d06 // movzx edx, byte [r14 + rax + 29] + LONG $0xf26e0f66 // movd xmm6, edx + LONG $0x54b60f41; WORD $0x1e06 // movzx edx, byte [r14 + rax + 30] + LONG $0x74b60f41; WORD $0x1f06 // movzx esi, byte [r14 + rax + 31] + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x13065c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r14 + rax + 19], 1 + QUAD $0x14064c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r14 + rax + 20], 1 + QUAD $0x150664203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r14 + rax + 21], 1 + QUAD $0x16067c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r14 + rax + 22], 1 + QUAD $0x17065c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r14 + rax + 23], 1 + QUAD $0x190664203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r14 + rax + 25], 1 + QUAD $0x1a066c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r14 + rax + 26], 1 + QUAD $0x1b0644203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r14 + rax + 27], 1 + QUAD $0x1c0644203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r14 + rax + 28], 1 + QUAD $0x1d0674203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r14 + rax + 29], 1 + LONG $0xca6e0f66 // movd xmm1, edx + QUAD $0x1e064c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r14 + rax + 30], 1 + LONG $0xfe6e0f66 // movd xmm7, esi + QUAD $0x1f067c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r14 + rax + 31], 1 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x13165c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r14 + rdx + 19], 2 + QUAD $0x14164c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r14 + rdx + 20], 2 + QUAD $0x151664203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r14 + rdx + 21], 2 + QUAD $0x16167c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r14 + rdx + 22], 2 + QUAD $0x17165c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r14 + rdx + 23], 2 + QUAD $0x191664203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r14 + rdx + 25], 2 + QUAD $0x1a166c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r14 + rdx + 26], 2 + QUAD $0x1b1644203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r14 + rdx + 27], 2 + QUAD $0x1c1644203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r14 + rdx + 28], 2 + QUAD $0x1d1674203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r14 + rdx + 29], 2 + QUAD $0x1e164c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r14 + rdx + 30], 2 + QUAD $0x1f167c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r14 + rdx + 31], 2 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x13165c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r14 + rdx + 19], 3 + QUAD $0x13265c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r14 + r12 + 19], 4 + WORD $0x894c; BYTE $0xce // mov rsi, r9 + QUAD $0x130e5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r14 + r9 + 19], 5 + LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] + QUAD $0x133e5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r14 + rdi + 19], 6 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x130e5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r14 + r9 + 19], 7 + QUAD $0x133e5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r14 + r15 + 19], 8 + QUAD $0x131e5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r14 + r11 + 19], 9 + QUAD $0x13165c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r14 + r10 + 19], 10 + WORD $0x8949; BYTE $0xcd // mov r13, rcx + QUAD $0x130e5c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r14 + rcx + 19], 11 LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - LONG $0x7f0f41f3; WORD $0x8e24 // movdqu oword [r14 + 4*rcx], xmm4 - LONG $0x2434894c // mov qword [rsp], r14 - LONG $0x7f0f41f3; WORD $0x8e4c; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm1 - LONG $0x08c18348 // add rcx, 8 - WORD $0x8949; BYTE $0xcf // mov r15, rcx - LONG $0x244c3b48; BYTE $0x28 // cmp rcx, qword [rsp + 40] - JNE LBB7_125 - QUAD $0x0000011024bc8b4c // mov r15, qword [rsp + 272] - LONG $0x247c3b4c; BYTE $0x28 // cmp r15, qword [rsp + 40] - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - JNE LBB7_127 - JMP LBB7_130 - -LBB7_182: - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0xfce08348 // and rax, -4 - WORD $0x8948; BYTE $0xc2 // mov rdx, rax - LONG $0x07e2c148 // shl rdx, 7 - WORD $0x0148; BYTE $0xf2 // add rdx, rsi - LONG $0x240c8b48 // mov rcx, qword [rsp] - LONG $0x813c8d4c // lea r15, [rcx + 4*rax] - LONG $0xeb280f45 // movaps xmm13, xmm11 - LONG $0xebc60f45; BYTE $0x00 // shufps xmm13, xmm11, 0 - LONG $0xfcc68148; WORD $0x0001; BYTE $0x00 // add rsi, 508 - WORD $0xc931 // xor ecx, ecx - LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI7_0] */ - LONG $0x243c8b48 // mov rdi, qword [rsp] - -LBB7_183: - QUAD $0xfffffe049e100ff3 // movss xmm3, dword [rsi - 508] - QUAD $0xfffe0896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 504] - QUAD $0xfffe0c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 500] - QUAD $0xfffffe108e100ff3 // movss xmm1, dword [rsi - 496] - QUAD $0xfffe849e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 380], 16 - QUAD $0xffff049e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 252], 32 - LONG $0x213a0f66; WORD $0x845e; BYTE $0x30 // insertps xmm3, dword [rsi - 124], 48 - QUAD $0xfe8896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 376], 16 - QUAD $0xff0896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 248], 32 - QUAD $0x308856213a0f4466 // insertps xmm10, dword [rsi - 120], 48 - QUAD $0xfe8c8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 372], 16 - QUAD $0xff0c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 244], 32 - QUAD $0x308c4e213a0f4466 // insertps xmm9, dword [rsi - 116], 48 - QUAD $0xfffe908e213a0f66; WORD $0x10ff // insertps xmm1, dword [rsi - 368], 16 - QUAD $0xffff108e213a0f66; WORD $0x20ff // insertps xmm1, dword [rsi - 240], 32 - LONG $0x213a0f66; WORD $0x904e; BYTE $0x30 // insertps xmm1, dword [rsi - 112], 48 - QUAD $0xfffe1486100f44f3; BYTE $0xff // movss xmm8, dword [rsi - 492] - QUAD $0xfe9486213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm8, dword [rsi - 364], 16 - QUAD $0xff1486213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm8, dword [rsi - 236], 32 - LONG $0xe5280f45 // movaps xmm12, xmm13 - QUAD $0x309446213a0f4466 // insertps xmm8, dword [rsi - 108], 48 - QUAD $0xfffffe1896100ff3 // movss xmm2, dword [rsi - 488] - QUAD $0xfffe9896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 360], 16 - QUAD $0xffff1896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 232], 32 - LONG $0xe3c20f44; BYTE $0x01 // cmpltps xmm12, xmm3 - LONG $0x213a0f66; WORD $0x9856; BYTE $0x30 // insertps xmm2, dword [rsi - 104], 48 - QUAD $0xfffffe1c9e100ff3 // movss xmm3, dword [rsi - 484] - QUAD $0xfffe9c9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 356], 16 - QUAD $0xffff1c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 228], 32 - LONG $0x6b0f4566; BYTE $0xe4 // packssdw xmm12, xmm12 - LONG $0x213a0f66; WORD $0x9c5e; BYTE $0x30 // insertps xmm3, dword [rsi - 100], 48 - QUAD $0xfffffe24a6100ff3 // movss xmm4, dword [rsi - 476] - QUAD $0xfffea4a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 348], 16 - QUAD $0xffff24a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 220], 32 - LONG $0x630f4566; BYTE $0xe4 // packsswb xmm12, xmm12 - LONG $0x213a0f66; WORD $0xa466; BYTE $0x30 // insertps xmm4, dword [rsi - 92], 48 - LONG $0xfd280f41 // movaps xmm7, xmm13 - QUAD $0xfffffe44ae100ff3 // movss xmm5, dword [rsi - 444] - QUAD $0xfffec4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 316], 16 - QUAD $0xffff44ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 188], 32 - LONG $0x01fcc20f // cmpltps xmm7, xmm4 - LONG $0x213a0f66; WORD $0xc46e; BYTE $0x30 // insertps xmm5, dword [rsi - 60], 48 - LONG $0xf5280f41 // movaps xmm6, xmm13 - QUAD $0xfffffe6486100ff3 // movss xmm0, dword [rsi - 412] - QUAD $0xfffee486213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 284], 16 - QUAD $0xffff6486213a0f66; WORD $0x20ff // insertps xmm0, dword [rsi - 156], 32 - LONG $0x01f5c20f // cmpltps xmm6, xmm5 - LONG $0x213a0f66; WORD $0xe446; BYTE $0x30 // insertps xmm0, dword [rsi - 28], 48 - LONG $0xe5280f41 // movaps xmm4, xmm13 - LONG $0x01e0c20f // cmpltps xmm4, xmm0 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc2c20f41; BYTE $0x01 // cmpltps xmm0, xmm10 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x6f0f4466; BYTE $0xf0 // movdqa xmm14, xmm0 - LONG $0xdb0f4566; BYTE $0xf7 // pand xmm14, xmm15 - LONG $0xf80f4466; BYTE $0xf0 // psubb xmm14, xmm0 - QUAD $0xfffe2096100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 480] - QUAD $0xfea096213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 352], 16 - LONG $0xdb0f4566; BYTE $0xe7 // pand xmm12, xmm15 - QUAD $0xff2096213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 224], 32 - LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0xe9c20f41; BYTE $0x01 // cmpltps xmm5, xmm9 - QUAD $0x30a056213a0f4466 // insertps xmm10, dword [rsi - 96], 48 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0x456f0f66; BYTE $0x10 // movdqa xmm0, oword 16[rbp] /* [rip + .LCPI7_1] */ - LONG $0xe8db0f66 // pand xmm5, xmm0 - LONG $0xeb0f4166; BYTE $0xee // por xmm5, xmm14 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x01c1c20f // cmpltps xmm0, xmm1 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0xc8c20f41; BYTE $0x01 // cmpltps xmm1, xmm8 - QUAD $0xfffe288e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 472] - QUAD $0xfea88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 344], 16 - QUAD $0xff288e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 216], 32 - QUAD $0x30a84e213a0f4466 // insertps xmm9, dword [rsi - 88], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 - LONG $0x6f0f4466; WORD $0x2075 // movdqa xmm14, oword 32[rbp] /* [rip + .LCPI7_2] */ - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0x6f0f4466; WORD $0x3075 // movdqa xmm14, oword 48[rbp] /* [rip + .LCPI7_3] */ - LONG $0xdb0f4166; BYTE $0xce // pand xmm1, xmm14 - LONG $0xc8eb0f66 // por xmm1, xmm0 - QUAD $0xfffe2ca6100f44f3; BYTE $0xff // movss xmm12, dword [rsi - 468] - QUAD $0xfeaca6213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm12, dword [rsi - 340], 16 - QUAD $0xff2ca6213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm12, dword [rsi - 212], 32 - QUAD $0x30ac66213a0f4466 // insertps xmm12, dword [rsi - 84], 48 - LONG $0xcdeb0f66 // por xmm1, xmm5 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x01c2c20f // cmpltps xmm0, xmm2 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0x01ebc20f // cmpltps xmm5, xmm3 - QUAD $0xfffffe3096100ff3 // movss xmm2, dword [rsi - 464] - QUAD $0xfffeb096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 336], 16 - QUAD $0xffff3096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 208], 32 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0x213a0f66; WORD $0xb056; BYTE $0x30 // insertps xmm2, dword [rsi - 80], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 - LONG $0x6f0f4466; WORD $0x4075 // movdqa xmm14, oword 64[rbp] /* [rip + .LCPI7_4] */ - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 - LONG $0x5d6f0f66; BYTE $0x50 // movdqa xmm3, oword 80[rbp] /* [rip + .LCPI7_5] */ - LONG $0xebdb0f66 // pand xmm5, xmm3 - LONG $0xe8eb0f66 // por xmm5, xmm0 - LONG $0xc5280f45 // movaps xmm8, xmm13 - LONG $0xc2c20f45; BYTE $0x01 // cmpltps xmm8, xmm10 - QUAD $0xfffffe349e100ff3 // movss xmm3, dword [rsi - 460] - QUAD $0xfffeb49e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 332], 16 - QUAD $0xffff349e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 204], 32 - LONG $0x213a0f66; WORD $0xb45e; BYTE $0x30 // insertps xmm3, dword [rsi - 76], 48 - LONG $0x6b0f4566; BYTE $0xc0 // packssdw xmm8, xmm8 - LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 - LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 - LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI7_6] */ - LONG $0xdb0f4466; BYTE $0xc0 // pand xmm8, xmm0 - LONG $0xeb0f4466; BYTE $0xc5 // por xmm8, xmm5 - QUAD $0xfffe3896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 456] - QUAD $0xfeb896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 328], 16 - QUAD $0xff3896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 200], 32 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x30b856213a0f4466 // insertps xmm10, dword [rsi - 72], 48 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc1c20f41; BYTE $0x01 // cmpltps xmm0, xmm9 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xc8f80f66 // psubb xmm1, xmm0 - QUAD $0xfffe3c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 452] - QUAD $0xfebc8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 324], 16 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - QUAD $0xff3c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 196], 32 - LONG $0xcfeb0f66 // por xmm1, xmm7 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0xecc20f41; BYTE $0x01 // cmpltps xmm5, xmm12 - QUAD $0x30bc4e213a0f4466 // insertps xmm9, dword [rsi - 68], 48 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0x6ddb0f66; BYTE $0x10 // pand xmm5, oword 16[rbp] /* [rip + .LCPI7_1] */ - LONG $0xe9eb0f66 // por xmm5, xmm1 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x01c2c20f // cmpltps xmm0, xmm2 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x01cbc20f // cmpltps xmm1, xmm3 - QUAD $0xfffffe409e100ff3 // movss xmm3, dword [rsi - 448] - QUAD $0xfffec09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 320], 16 - QUAD $0xffff409e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 192], 32 - LONG $0x213a0f66; WORD $0xc05e; BYTE $0x30 // insertps xmm3, dword [rsi - 64], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 - LONG $0x6f0f4466; WORD $0x2065 // movdqa xmm12, oword 32[rbp] /* [rip + .LCPI7_2] */ - LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0x4ddb0f66; BYTE $0x30 // pand xmm1, oword 48[rbp] /* [rip + .LCPI7_3] */ - LONG $0xc8eb0f66 // por xmm1, xmm0 - QUAD $0xfffffe4896100ff3 // movss xmm2, dword [rsi - 440] - QUAD $0xfffec896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 312], 16 - QUAD $0xffff4896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 184], 32 - LONG $0x213a0f66; WORD $0xc856; BYTE $0x30 // insertps xmm2, dword [rsi - 56], 48 - LONG $0xcdeb0f66 // por xmm1, xmm5 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc2c20f41; BYTE $0x01 // cmpltps xmm0, xmm10 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0xe9c20f41; BYTE $0x01 // cmpltps xmm5, xmm9 - QUAD $0xfffffe4cbe100ff3 // movss xmm7, dword [rsi - 436] - QUAD $0xfffeccbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 308], 16 - QUAD $0xffff4cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 180], 32 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0x213a0f66; WORD $0xcc7e; BYTE $0x30 // insertps xmm7, dword [rsi - 52], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 - LONG $0x6ddb0f66; BYTE $0x50 // pand xmm5, oword 80[rbp] /* [rip + .LCPI7_5] */ - LONG $0xe8eb0f66 // por xmm5, xmm0 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x01c3c20f // cmpltps xmm0, xmm3 - QUAD $0xfffffe509e100ff3 // movss xmm3, dword [rsi - 432] - QUAD $0xfffed09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 304], 16 - QUAD $0xffff509e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 176], 32 - LONG $0x213a0f66; WORD $0xd05e; BYTE $0x30 // insertps xmm3, dword [rsi - 48], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0x6f0f4466; WORD $0x6055 // movdqa xmm10, oword 96[rbp] /* [rip + .LCPI7_6] */ - LONG $0xdb0f4166; BYTE $0xc2 // pand xmm0, xmm10 - LONG $0xc5eb0f66 // por xmm0, xmm5 - QUAD $0xfffffe54ae100ff3 // movss xmm5, dword [rsi - 428] - QUAD $0xfffed4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 300], 16 - QUAD $0xffff54ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 172], 32 - LONG $0x213a0f66; WORD $0xd46e; BYTE $0x30 // insertps xmm5, dword [rsi - 44], 48 - LONG $0xc1eb0f66 // por xmm0, xmm1 - QUAD $0xfffe588e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 424] - QUAD $0xfed88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 296], 16 - QUAD $0xff588e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 168], 32 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - QUAD $0x30d84e213a0f4466 // insertps xmm9, dword [rsi - 40], 48 - LONG $0x620f4466; BYTE $0xc0 // punpckldq xmm8, xmm0 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x01c2c20f // cmpltps xmm0, xmm2 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xc8f80f66 // psubb xmm1, xmm0 - QUAD $0xfffffe5c96100ff3 // movss xmm2, dword [rsi - 420] - QUAD $0xfffedc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 292], 16 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - QUAD $0xffff5c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 164], 32 - LONG $0xceeb0f66 // por xmm1, xmm6 - LONG $0xf5280f41 // movaps xmm6, xmm13 - LONG $0x01f7c20f // cmpltps xmm6, xmm7 - LONG $0x213a0f66; WORD $0xdc56; BYTE $0x30 // insertps xmm2, dword [rsi - 36], 48 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 - LONG $0x456f0f66; BYTE $0x10 // movdqa xmm0, oword 16[rbp] /* [rip + .LCPI7_1] */ - LONG $0xf0db0f66 // pand xmm6, xmm0 - LONG $0xf1eb0f66 // por xmm6, xmm1 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x01c3c20f // cmpltps xmm0, xmm3 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x01cdc20f // cmpltps xmm1, xmm5 - QUAD $0xfffffe609e100ff3 // movss xmm3, dword [rsi - 416] - QUAD $0xfffee09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 288], 16 - QUAD $0xffff609e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 160], 32 - LONG $0x213a0f66; WORD $0xe05e; BYTE $0x30 // insertps xmm3, dword [rsi - 32], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 - LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0x6f0f4466; WORD $0x3065 // movdqa xmm12, oword 48[rbp] /* [rip + .LCPI7_3] */ - LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 - LONG $0xc8eb0f66 // por xmm1, xmm0 - QUAD $0xfffffe68ae100ff3 // movss xmm5, dword [rsi - 408] - QUAD $0xfffee8ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 280], 16 - QUAD $0xffff68ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 152], 32 - LONG $0x213a0f66; WORD $0xe86e; BYTE $0x30 // insertps xmm5, dword [rsi - 24], 48 - LONG $0xceeb0f66 // por xmm1, xmm6 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc1c20f41; BYTE $0x01 // cmpltps xmm0, xmm9 - LONG $0xf5280f41 // movaps xmm6, xmm13 - LONG $0x01f2c20f // cmpltps xmm6, xmm2 - QUAD $0xfffffe6cbe100ff3 // movss xmm7, dword [rsi - 404] - QUAD $0xfffeecbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 276], 16 - QUAD $0xffff6cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 148], 32 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0x213a0f66; WORD $0xec7e; BYTE $0x30 // insertps xmm7, dword [rsi - 20], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x06 // psllw xmm6, 6 - LONG $0x6f0f4466; WORD $0x504d // movdqa xmm9, oword 80[rbp] /* [rip + .LCPI7_5] */ - LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 - LONG $0xf0eb0f66 // por xmm6, xmm0 - LONG $0xd5280f41 // movaps xmm2, xmm13 - LONG $0x01d3c20f // cmpltps xmm2, xmm3 - QUAD $0xfffffe7086100ff3 // movss xmm0, dword [rsi - 400] - QUAD $0xfffef086213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 272], 16 - QUAD $0xffff7086213a0f66; WORD $0x20ff // insertps xmm0, dword [rsi - 144], 32 - LONG $0x213a0f66; WORD $0xf046; BYTE $0x30 // insertps xmm0, dword [rsi - 16], 48 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] - QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 - QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 - LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x01cdc20f // cmpltps xmm1, xmm5 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xe96f0f66 // movdqa xmm5, xmm1 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xe9f80f66 // psubb xmm5, xmm1 - QUAD $0xfffffe789e100ff3 // movss xmm3, dword [rsi - 392] - QUAD $0xfffef89e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 264], 16 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - QUAD $0xffff789e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 136], 32 - LONG $0xeceb0f66 // por xmm5, xmm4 - LONG $0xe5280f41 // movaps xmm4, xmm13 - LONG $0x01e7c20f // cmpltps xmm4, xmm7 - LONG $0x213a0f66; WORD $0xf85e; BYTE $0x30 // insertps xmm3, dword [rsi - 8], 48 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xf4710f66; BYTE $0x02 // psllw xmm4, 2 - LONG $0x65db0f66; BYTE $0x10 // pand xmm4, oword 16[rbp] /* [rip + .LCPI7_1] */ - LONG $0xe5eb0f66 // por xmm4, xmm5 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0x01e8c20f // cmpltps xmm5, xmm0 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x01cec20f // cmpltps xmm1, xmm6 - QUAD $0xfffffe7c86100ff3 // movss xmm0, dword [rsi - 388] - QUAD $0xfffefc86213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 260], 16 - QUAD $0xffff7c86213a0f66; WORD $0x20ff // insertps xmm0, dword [rsi - 132], 32 - LONG $0x213a0f66; WORD $0xfc46; BYTE $0x30 // insertps xmm0, dword [rsi - 4], 48 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 - LONG $0x6ddb0f66; BYTE $0x20 // pand xmm5, oword 32[rbp] /* [rip + .LCPI7_2] */ - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 - LONG $0xcdeb0f66 // por xmm1, xmm5 - QUAD $0xfffffe80ae100ff3 // movss xmm5, dword [rsi - 384] - QUAD $0xffff00ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 256], 16 - LONG $0x213a0f66; WORD $0x806e; BYTE $0x20 // insertps xmm5, dword [rsi - 128], 32 - LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0xe5280f41 // movaps xmm4, xmm13 - LONG $0x01e3c20f // cmpltps xmm4, xmm3 - LONG $0xdd280f41 // movaps xmm3, xmm13 - LONG $0x01d8c20f // cmpltps xmm3, xmm0 - LONG $0x213a0f66; WORD $0x302e // insertps xmm5, dword [rsi], 48 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xf4710f66; BYTE $0x05 // psllw xmm4, 5 - LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 - LONG $0xdb0f4166; BYTE $0xd9 // pand xmm3, xmm9 - LONG $0xdceb0f66 // por xmm3, xmm4 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x01c5c20f // cmpltps xmm0, xmm5 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0xdb0f4166; BYTE $0xc2 // pand xmm0, xmm10 - LONG $0xc3eb0f66 // por xmm0, xmm3 - LONG $0xc1eb0f66 // por xmm0, xmm1 - LONG $0xd0620f66 // punpckldq xmm2, xmm0 - LONG $0x600f4466; BYTE $0xc2 // punpcklbw xmm8, xmm2 - LONG $0x380f4466; WORD $0x4500; BYTE $0x70 // pshufb xmm8, oword 112[rbp] /* [rip + .LCPI7_7] */ - LONG $0x7f0f44f3; WORD $0x8f04 // movdqu oword [rdi + 4*rcx], xmm8 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 - WORD $0x3948; BYTE $0xc8 // cmp rax, rcx - JNE LBB7_183 - WORD $0x3949; BYTE $0xc2 // cmp r10, rax - JNE LBB7_185 - JMP LBB7_188 + QUAD $0x130e5c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r14 + rcx + 19], 12 + QUAD $0x13065c203a0f4366; BYTE $0x0d // pinsrb xmm3, byte [r14 + r8 + 19], 13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x13065c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r14 + rax + 19], 14 + QUAD $0x131e5c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r14 + rbx + 19], 15 + QUAD $0x14164c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r14 + rdx + 20], 3 + QUAD $0x14264c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r14 + r12 + 20], 4 + QUAD $0x14364c203a0f4566; BYTE $0x05 // pinsrb xmm9, byte [r14 + rsi + 20], 5 + QUAD $0x143e4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r14 + rdi + 20], 6 + QUAD $0x140e4c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r14 + r9 + 20], 7 + QUAD $0x143e4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r14 + r15 + 20], 8 + QUAD $0x141e4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r14 + r11 + 20], 9 + QUAD $0x14164c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r14 + r10 + 20], 10 + QUAD $0x142e4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r14 + r13 + 20], 11 + QUAD $0x140e4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r14 + rcx + 20], 12 + QUAD $0x14064c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r14 + r8 + 20], 13 + QUAD $0x14064c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r14 + rax + 20], 14 + QUAD $0x141e4c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r14 + rbx + 20], 15 + QUAD $0x151664203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r14 + rdx + 21], 3 + QUAD $0x152664203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r14 + r12 + 21], 4 + QUAD $0x153664203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r14 + rsi + 21], 5 + QUAD $0x153e64203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r14 + rdi + 21], 6 + QUAD $0x150e64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r14 + r9 + 21], 7 + QUAD $0x153e64203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r14 + r15 + 21], 8 + QUAD $0x151e64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r14 + r11 + 21], 9 + QUAD $0x151664203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r14 + r10 + 21], 10 + QUAD $0x152e64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r14 + r13 + 21], 11 + QUAD $0x150e64203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r14 + rcx + 21], 12 + QUAD $0x150664203a0f4366; BYTE $0x0d // pinsrb xmm4, byte [r14 + r8 + 21], 13 + QUAD $0x150664203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r14 + rax + 21], 14 + QUAD $0x151e64203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r14 + rbx + 21], 15 + QUAD $0x16167c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r14 + rdx + 22], 3 + QUAD $0x16267c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r14 + r12 + 22], 4 + QUAD $0x16367c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r14 + rsi + 22], 5 + QUAD $0x163e7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r14 + rdi + 22], 6 + QUAD $0x160e7c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r14 + r9 + 22], 7 + QUAD $0x163e7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r14 + r15 + 22], 8 + QUAD $0x161e7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r14 + r11 + 22], 9 + QUAD $0x16167c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r14 + r10 + 22], 10 + QUAD $0x00010024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 256] + QUAD $0x000000a095df0f66 // pandn xmm2, oword 160[rbp] /* [rip + .LCPI7_10] */ + QUAD $0x162e7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r14 + r13 + 22], 11 + WORD $0x894d; BYTE $0xea // mov r10, r13 + QUAD $0x0000b095df0f4466; BYTE $0x00 // pandn xmm10, oword 176[rbp] /* [rip + .LCPI7_11] */ + LONG $0xeb0f4466; BYTE $0xd2 // por xmm10, xmm2 + QUAD $0x160e7c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r14 + rcx + 22], 12 + LONG $0xd36f0f66 // movdqa xmm2, xmm3 + LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 + LONG $0xd3740f66 // pcmpeqb xmm2, xmm3 + QUAD $0x16067c203a0f4766; BYTE $0x0d // pinsrb xmm15, byte [r14 + r8 + 22], 13 + QUAD $0x000000c095df0f66 // pandn xmm2, oword 192[rbp] /* [rip + .LCPI7_12] */ + LONG $0xeb0f4166; BYTE $0xd2 // por xmm2, xmm10 + QUAD $0x16067c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r14 + rax + 22], 14 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + QUAD $0x000100b5f80f4466; BYTE $0x00 // psubb xmm14, oword 256[rbp] /* [rip + .LCPI7_16] */ + LONG $0xeb0f4166; BYTE $0xd6 // por xmm2, xmm14 + LONG $0x6f0f4566; BYTE $0xd1 // movdqa xmm10, xmm9 + LONG $0xda0f4566; BYTE $0xd5 // pminub xmm10, xmm13 + LONG $0x740f4566; BYTE $0xd1 // pcmpeqb xmm10, xmm9 + LONG $0xdc6f0f66 // movdqa xmm3, xmm4 + LONG $0x6f0f4566; BYTE $0xcd // movdqa xmm9, xmm13 + LONG $0xda0f4166; BYTE $0xdd // pminub xmm3, xmm13 + LONG $0xdc740f66 // pcmpeqb xmm3, xmm4 + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x161e7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r14 + rbx + 22], 15 + QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI7_13] */ + LONG $0xdf0f4566; BYTE $0xd5 // pandn xmm10, xmm13 + QUAD $0x000000e0a56f0f66 // movdqa xmm4, oword 224[rbp] /* [rip + .LCPI7_14] */ + LONG $0xdcdf0f66 // pandn xmm3, xmm4 + LONG $0xeb0f4166; BYTE $0xda // por xmm3, xmm10 + LONG $0x6f0f4166; BYTE $0xe7 // movdqa xmm4, xmm15 + LONG $0xda0f4166; BYTE $0xe1 // pminub xmm4, xmm9 + LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 + LONG $0x740f4166; BYTE $0xe7 // pcmpeqb xmm4, xmm15 + QUAD $0x17165c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r14 + rdx + 23], 3 + QUAD $0x17265c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r14 + r12 + 23], 4 + QUAD $0x17365c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r14 + rsi + 23], 5 + QUAD $0x173e5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r14 + rdi + 23], 6 + QUAD $0x170e5c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r14 + r9 + 23], 7 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x171e5c203a0f4566; BYTE $0x08 // pinsrb xmm11, byte [r14 + rbx + 23], 8 + QUAD $0x171e5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r14 + r11 + 23], 9 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x17065c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r14 + rax + 23], 10 + QUAD $0x17165c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r14 + r10 + 23], 11 + QUAD $0x170e5c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r14 + rcx + 23], 12 + QUAD $0x17065c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r14 + r8 + 23], 13 + QUAD $0x173e5c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r14 + r15 + 23], 14 + QUAD $0x172e5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r14 + r13 + 23], 15 + QUAD $0x0000f0bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 240[rbp] /* [rip + .LCPI7_15] */ + LONG $0xdf0f4166; BYTE $0xe7 // pandn xmm4, xmm15 + LONG $0xe3eb0f66 // por xmm4, xmm3 + LONG $0x6f0f4166; BYTE $0xdb // movdqa xmm3, xmm11 + LONG $0xda0f4166; BYTE $0xd9 // pminub xmm3, xmm9 + LONG $0x740f4166; BYTE $0xdb // pcmpeqb xmm3, xmm11 + QUAD $0x000001009def0f66 // pxor xmm3, oword 256[rbp] /* [rip + .LCPI7_16] */ + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0x6f0f4466; WORD $0x605d // movdqa xmm11, oword 96[rbp] /* [rip + .LCPI7_6] */ + LONG $0xdb0f4166; BYTE $0xdb // pand xmm3, xmm11 + LONG $0xdceb0f66 // por xmm3, xmm4 + QUAD $0x191664203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r14 + rdx + 25], 3 + QUAD $0x192664203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r14 + r12 + 25], 4 + QUAD $0x193664203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r14 + rsi + 25], 5 + QUAD $0x193e64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r14 + rdi + 25], 6 + QUAD $0x190e64203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r14 + r9 + 25], 7 + QUAD $0x191e64203a0f4566; BYTE $0x08 // pinsrb xmm12, byte [r14 + rbx + 25], 8 + QUAD $0x191e64203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r14 + r11 + 25], 9 + QUAD $0x190664203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r14 + rax + 25], 10 + QUAD $0x191664203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r14 + r10 + 25], 11 + QUAD $0x190e64203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r14 + rcx + 25], 12 + QUAD $0x190664203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r14 + r8 + 25], 13 + QUAD $0x193e64203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r14 + r15 + 25], 14 + QUAD $0x192e64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r14 + r13 + 25], 15 + QUAD $0x1a166c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r14 + rdx + 26], 3 + QUAD $0x1a266c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r14 + r12 + 26], 4 + QUAD $0x1a366c203a0f4166; BYTE $0x05 // pinsrb xmm5, byte [r14 + rsi + 26], 5 + QUAD $0x1a3e6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r14 + rdi + 26], 6 + QUAD $0x1a0e6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r14 + r9 + 26], 7 + QUAD $0x1a1e6c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r14 + rbx + 26], 8 + QUAD $0x1a1e6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r14 + r11 + 26], 9 + QUAD $0x1a066c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r14 + rax + 26], 10 + QUAD $0x1a166c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r14 + r10 + 26], 11 + QUAD $0x1a0e6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r14 + rcx + 26], 12 + QUAD $0x1a066c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r14 + r8 + 26], 13 + QUAD $0x1a3e6c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r14 + r15 + 26], 14 + QUAD $0x1a2e6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r14 + r13 + 26], 15 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0x6f0f4166; BYTE $0xd4 // movdqa xmm2, xmm12 + LONG $0xda0f4166; BYTE $0xd1 // pminub xmm2, xmm9 + LONG $0x740f4166; BYTE $0xd4 // pcmpeqb xmm2, xmm12 + LONG $0x6f0f4466; BYTE $0xca // movdqa xmm9, xmm2 + QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI7_10] */ + LONG $0xdf0f4566; BYTE $0xca // pandn xmm9, xmm10 + LONG $0xfc0f4466; BYTE $0xca // paddb xmm9, xmm2 + LONG $0xe56f0f66 // movdqa xmm4, xmm5 + LONG $0xda0f4166; BYTE $0xe5 // pminub xmm4, xmm13 + LONG $0xe5740f66 // pcmpeqb xmm4, xmm5 + QUAD $0x0000e024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 224] + LONG $0xdf0f4166; BYTE $0xd2 // pandn xmm2, xmm10 + QUAD $0x1b1644203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r14 + rdx + 27], 3 + QUAD $0x1b2644203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r14 + r12 + 27], 4 + QUAD $0x1b3644203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r14 + rsi + 27], 5 + QUAD $0x1b3e44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r14 + rdi + 27], 6 + QUAD $0x1b0e44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r14 + r9 + 27], 7 + QUAD $0x1b1e44203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r14 + rbx + 27], 8 + QUAD $0x1b1e44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r14 + r11 + 27], 9 + QUAD $0x1b0644203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r14 + rax + 27], 10 + QUAD $0x1b1644203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r14 + r10 + 27], 11 + QUAD $0x1b0e44203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r14 + rcx + 27], 12 + QUAD $0x1b0644203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r14 + r8 + 27], 13 + QUAD $0x1b3e44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r14 + r15 + 27], 14 + QUAD $0x1b2e44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r14 + r13 + 27], 15 + QUAD $0x000000b0a5df0f66 // pandn xmm4, oword 176[rbp] /* [rip + .LCPI7_11] */ + LONG $0xe2eb0f66 // por xmm4, xmm2 + LONG $0xd06f0f66 // movdqa xmm2, xmm0 + LONG $0xda0f4166; BYTE $0xd5 // pminub xmm2, xmm13 + LONG $0xd0740f66 // pcmpeqb xmm2, xmm0 + QUAD $0x000000c095df0f66 // pandn xmm2, oword 192[rbp] /* [rip + .LCPI7_12] */ + LONG $0xd4eb0f66 // por xmm2, xmm4 + QUAD $0x1c1644203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r14 + rdx + 28], 3 + QUAD $0x1c2644203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r14 + r12 + 28], 4 + QUAD $0x1c3644203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r14 + rsi + 28], 5 + QUAD $0x1c3e44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r14 + rdi + 28], 6 + QUAD $0x1c0e44203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r14 + r9 + 28], 7 + QUAD $0x1c1e44203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r14 + rbx + 28], 8 + QUAD $0x1c1e44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r14 + r11 + 28], 9 + QUAD $0x1c0644203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r14 + rax + 28], 10 + QUAD $0x1c1644203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r14 + r10 + 28], 11 + QUAD $0x1c0e44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r14 + rcx + 28], 12 + QUAD $0x1c0644203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r14 + r8 + 28], 13 + QUAD $0x1c3e44203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r14 + r15 + 28], 14 + QUAD $0x1c2e44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r14 + r13 + 28], 15 + QUAD $0x1d1674203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r14 + rdx + 29], 3 + QUAD $0x1d2674203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r14 + r12 + 29], 4 + QUAD $0x1d3674203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r14 + rsi + 29], 5 + QUAD $0x1d3e74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r14 + rdi + 29], 6 + QUAD $0x1d0e74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r14 + r9 + 29], 7 + QUAD $0x1d1e74203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r14 + rbx + 29], 8 + QUAD $0x1d1e74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r14 + r11 + 29], 9 + QUAD $0x1d0674203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r14 + rax + 29], 10 + QUAD $0x1d1674203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r14 + r10 + 29], 11 + QUAD $0x1d0e74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r14 + rcx + 29], 12 + QUAD $0x1d0674203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r14 + r8 + 29], 13 + QUAD $0x1d3e74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r14 + r15 + 29], 14 + QUAD $0x1d2e74203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r14 + r13 + 29], 15 + LONG $0x760f4566; BYTE $0xd2 // pcmpeqd xmm10, xmm10 + LONG $0xf80f4566; BYTE $0xca // psubb xmm9, xmm10 + LONG $0xeb0f4166; BYTE $0xd1 // por xmm2, xmm9 + LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 + LONG $0xda0f4166; BYTE $0xc5 // pminub xmm0, xmm13 + LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 + LONG $0xe66f0f66 // movdqa xmm4, xmm6 + LONG $0xda0f4166; BYTE $0xe5 // pminub xmm4, xmm13 + LONG $0xe6740f66 // pcmpeqb xmm4, xmm6 + QUAD $0x1e164c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r14 + rdx + 30], 3 + QUAD $0x1f167c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r14 + rdx + 31], 3 + QUAD $0x1e264c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r14 + r12 + 30], 4 + QUAD $0x1f267c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r14 + r12 + 31], 4 + QUAD $0x1e364c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r14 + rsi + 30], 5 + QUAD $0x1f367c203a0f4166; BYTE $0x05 // pinsrb xmm7, byte [r14 + rsi + 31], 5 + QUAD $0x1e3e4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r14 + rdi + 30], 6 + QUAD $0x1f3e7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r14 + rdi + 31], 6 + QUAD $0x1e0e4c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r14 + r9 + 30], 7 + QUAD $0x1f0e7c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r14 + r9 + 31], 7 + QUAD $0x1e1e4c203a0f4166; BYTE $0x08 // pinsrb xmm1, byte [r14 + rbx + 30], 8 + QUAD $0x1f1e7c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r14 + rbx + 31], 8 + QUAD $0x1e1e4c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r14 + r11 + 30], 9 + QUAD $0x1f1e7c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r14 + r11 + 31], 9 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x1e064c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r14 + rax + 30], 10 + QUAD $0x1f067c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r14 + rax + 31], 10 + QUAD $0x1e164c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r14 + r10 + 30], 11 + QUAD $0x1f167c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r14 + r10 + 31], 11 + QUAD $0x1e0e4c203a0f4166; BYTE $0x0c // pinsrb xmm1, byte [r14 + rcx + 30], 12 + QUAD $0x1f0e7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r14 + rcx + 31], 12 + QUAD $0x1e064c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r14 + r8 + 30], 13 + QUAD $0x1f067c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r14 + r8 + 31], 13 + QUAD $0x1e3e4c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r14 + r15 + 30], 14 + QUAD $0x1f3e7c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r14 + r15 + 31], 14 + QUAD $0x1e2e4c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r14 + r13 + 30], 15 + QUAD $0x1f2e7c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r14 + r13 + 31], 15 + QUAD $0x000000d085df0f66 // pandn xmm0, oword 208[rbp] /* [rip + .LCPI7_13] */ + QUAD $0x000000e0a5df0f66 // pandn xmm4, oword 224[rbp] /* [rip + .LCPI7_14] */ + LONG $0xe0eb0f66 // por xmm4, xmm0 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0xda0f4166; BYTE $0xc5 // pminub xmm0, xmm13 + LONG $0xc1740f66 // pcmpeqb xmm0, xmm1 + LONG $0xdf0f4166; BYTE $0xc7 // pandn xmm0, xmm15 + LONG $0xc4eb0f66 // por xmm0, xmm4 + LONG $0xcf6f0f66 // movdqa xmm1, xmm7 + LONG $0xda0f4166; BYTE $0xcd // pminub xmm1, xmm13 + LONG $0xcf740f66 // pcmpeqb xmm1, xmm7 + LONG $0xef0f4166; BYTE $0xca // pxor xmm1, xmm10 + LONG $0xf1710f66; BYTE $0x07 // psllw xmm1, 7 + LONG $0xdb0f4166; BYTE $0xcb // pand xmm1, xmm11 + LONG $0xc8eb0f66 // por xmm1, xmm0 + LONG $0xcaeb0f66 // por xmm1, xmm2 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0xc1600f66 // punpcklbw xmm0, xmm1 + QUAD $0x0000b024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 176] + LONG $0xd56f0f66 // movdqa xmm2, xmm5 + QUAD $0x0000d024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 208] + LONG $0xd6600f66 // punpcklbw xmm2, xmm6 + LONG $0xe26f0f66 // movdqa xmm4, xmm2 + LONG $0xe0610f66 // punpcklwd xmm4, xmm0 + LONG $0xd0690f66 // punpckhwd xmm2, xmm0 + LONG $0xd9680f66 // punpckhbw xmm3, xmm1 + LONG $0xee680f66 // punpckhbw xmm5, xmm6 + LONG $0xc56f0f66 // movdqa xmm0, xmm5 + LONG $0xc3610f66 // punpcklwd xmm0, xmm3 + LONG $0xeb690f66 // punpckhwd xmm5, xmm3 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + LONG $0x7f0f41f3; WORD $0x8c6c; BYTE $0x30 // movdqu oword [r12 + 4*rcx + 48], xmm5 + LONG $0x7f0f41f3; WORD $0x8c44; BYTE $0x20 // movdqu oword [r12 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x8c54; BYTE $0x10 // movdqu oword [r12 + 4*rcx + 16], xmm2 + LONG $0x7f0f41f3; WORD $0x8c24 // movdqu oword [r12 + 4*rcx], xmm4 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + JNE LBB7_72 + QUAD $0x00000138248c8b48 // mov rcx, qword [rsp + 312] + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + QUAD $0x0000008824bc8b4c // mov r15, qword [rsp + 136] + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0000015024b48b4c // mov r14, qword [rsp + 336] + JNE LBB7_74 + JMP LBB7_77 DATA LCDATA6<>+0x000(SB)/8, $0x0000000001010101 DATA LCDATA6<>+0x008(SB)/8, $0x0000000000000000 @@ -39866,62 +41031,75 @@ TEXT ·_comparison_greater_scalar_arr_sse4(SB), $360-48 MOVQ BP, 336(SP) LEAQ LCDATA6<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB8_16 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB8_31 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB8_81 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB8_92 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB8_182 - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_9 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_7: - WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0xf619 // sbb esi, esi - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_7 - LONG $0x01c68349 // add r14, 1 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB8_18 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB8_35 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB8_57 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB8_70 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB8_215 + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_11 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_9 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_8: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc08348 // add rax, -1 + JNE LBB8_8 LBB8_9: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_13 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 LBB8_11: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_15 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + +LBB8_13: QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] QUAD $0x000000c02494970f // seta byte [rsp + 192] @@ -39932,7 +41110,7 @@ LBB8_11: LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] @@ -39942,9 +41120,9 @@ LBB8_11: LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] - LONG $0xd0970f41 // seta r8b + LONG $0xd6970f40 // seta sil LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] LONG $0xd1970f41 // seta r9b LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] @@ -39952,37 +41130,37 @@ LBB8_11: LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] LONG $0xd4970f41 // seta r12b LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + QUAD $0x000000b02494970f // seta byte [rsp + 176] LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd0970f41 // seta r8b LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] - QUAD $0x000000b02494970f // seta byte [rsp + 176] + QUAD $0x000000902494970f // seta byte [rsp + 144] LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] QUAD $0x000000a02494970f // seta byte [rsp + 160] + LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] LONG $0xd7970f41 // seta r15b LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] LONG $0x2414970f // seta byte [rsp] LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] @@ -39994,65 +41172,64 @@ LBB8_11: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x70 // add sil, byte [rsp + 112] + WORD $0xc900 // add cl, cl + LONG $0x70244c02 // add cl, byte [rsp + 112] LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x58244402 // add al, byte [rsp + 88] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xce89 // mov esi, ecx + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b - LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x01468845 // mov byte [r14 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al LONG $0x18244402 // add al, byte [rsp + 24] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -40060,11 +41237,11 @@ LBB8_11: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl LONG $0x240cb60f // movzx ecx, byte [rsp] @@ -40076,77 +41253,92 @@ LBB8_11: LONG $0x035e8841 // mov byte [r14 + 3], bl LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 LONG $0x04c68349 // add r14, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_11 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB8_13 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB8_13: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB8_162 +LBB8_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB8_185 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB8_164 - -LBB8_16: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB8_45 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB8_104 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB8_115 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB8_182 - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_24 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_22: - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + JMP LBB8_187 + +LBB8_18: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB8_42 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB8_84 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB8_97 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB8_215 + WORD $0x8b4c; BYTE $0x3e // mov r15, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_26 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_25: + LONG $0x012e0f66 // ucomisd xmm0, qword [rcx] WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x08c28348 // add rdx, 8 + LONG $0x08518d48 // lea rdx, [rcx + 8] WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_22 - LONG $0x01c68349 // add r14, 1 - -LBB8_24: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_28 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 - QUAD $0x000000c0249c894c // mov qword [rsp + 192], r11 + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_25 LBB8_26: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 + +LBB8_28: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_32 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000e024bc894c // mov qword [rsp + 224], r15 + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000c024848948 // mov qword [rsp + 192], rax + +LBB8_30: QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] @@ -40157,7 +41349,7 @@ LBB8_26: LONG $0x422e0f66; BYTE $0x18 // ucomisd xmm0, qword [rdx + 24] LONG $0xd5970f41 // seta r13b LONG $0x422e0f66; BYTE $0x20 // ucomisd xmm0, qword [rdx + 32] - QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x422e0f66; BYTE $0x28 // ucomisd xmm0, qword [rdx + 40] LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x422e0f66; BYTE $0x30 // ucomisd xmm0, qword [rdx + 48] @@ -40165,11 +41357,11 @@ LBB8_26: LONG $0x422e0f66; BYTE $0x38 // ucomisd xmm0, qword [rdx + 56] LONG $0xd3970f41 // seta r11b LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + QUAD $0x000000b02494970f // seta byte [rsp + 176] LONG $0x422e0f66; BYTE $0x48 // ucomisd xmm0, qword [rdx + 72] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x422e0f66; BYTE $0x50 // ucomisd xmm0, qword [rdx + 80] - LONG $0xd7970f40 // seta dil + LONG $0xd6970f40 // seta sil LONG $0x422e0f66; BYTE $0x58 // ucomisd xmm0, qword [rdx + 88] LONG $0xd1970f41 // seta r9b LONG $0x422e0f66; BYTE $0x60 // ucomisd xmm0, qword [rdx + 96] @@ -40177,37 +41369,37 @@ LBB8_26: LONG $0x422e0f66; BYTE $0x68 // ucomisd xmm0, qword [rdx + 104] LONG $0xd4970f41 // seta r12b LONG $0x422e0f66; BYTE $0x70 // ucomisd xmm0, qword [rdx + 112] - QUAD $0x000000b02494970f // seta byte [rsp + 176] + QUAD $0x000000902494970f // seta byte [rsp + 144] LONG $0x422e0f66; BYTE $0x78 // ucomisd xmm0, qword [rdx + 120] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd7970f40 // seta dil QUAD $0x00000080822e0f66 // ucomisd xmm0, qword [rdx + 128] LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] QUAD $0x00000088822e0f66 // ucomisd xmm0, qword [rdx + 136] LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] QUAD $0x00000090822e0f66 // ucomisd xmm0, qword [rdx + 144] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - QUAD $0x00000098822e0f66 // ucomisd xmm0, qword [rdx + 152] QUAD $0x000000a02494970f // seta byte [rsp + 160] + QUAD $0x00000098822e0f66 // ucomisd xmm0, qword [rdx + 152] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] QUAD $0x000000a0822e0f66 // ucomisd xmm0, qword [rdx + 160] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] QUAD $0x000000a8822e0f66 // ucomisd xmm0, qword [rdx + 168] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - QUAD $0x000000b0822e0f66 // ucomisd xmm0, qword [rdx + 176] LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + QUAD $0x000000b0822e0f66 // ucomisd xmm0, qword [rdx + 176] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] QUAD $0x000000b8822e0f66 // ucomisd xmm0, qword [rdx + 184] LONG $0xd7970f41 // seta r15b QUAD $0x000000c0822e0f66 // ucomisd xmm0, qword [rdx + 192] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] QUAD $0x000000c8822e0f66 // ucomisd xmm0, qword [rdx + 200] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] QUAD $0x000000e0822e0f66 // ucomisd xmm0, qword [rdx + 224] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] QUAD $0x000000f0822e0f66 // ucomisd xmm0, qword [rdx + 240] LONG $0x2414970f // seta byte [rsp] QUAD $0x000000f8822e0f66 // ucomisd xmm0, qword [rdx + 248] @@ -40219,412 +41411,213 @@ LBB8_26: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xc6 // or r14b, r8b - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x68 // add sil, byte [rsp + 104] + WORD $0xc900 // add cl, cl + LONG $0xb0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 176] LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xf7 // or dil, sil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe8 // or al, r13b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xf7 // or dil, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0844; BYTE $0xe7 // or dil, r12b LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al LONG $0x58244402 // add al, byte [rsp + 88] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b - LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x240cb60f // movzx ecx, byte [rsp] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xcb08 // or bl, cl - WORD $0xc308 // or bl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x035e8841 // mov byte [r14 + 3], bl - LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB8_26 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - -LBB8_28: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB8_166 - WORD $0xff31 // xor edi, edi - JMP LBB8_168 - -LBB8_31: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB8_58 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB8_182 - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_37 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_35: - WORD $0x3a44; BYTE $0x1a // cmp r11b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_35 - LONG $0x01c68349 // add r14, 1 - -LBB8_37: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_127 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x241c8844 // mov byte [rsp], r11b - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x0000010024bc894c // mov qword [rsp + 256], r15 - JB LBB8_41 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB8_191 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB8_191 - -LBB8_41: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - LONG $0x2474894c; BYTE $0x58 // mov qword [rsp + 88], r14 - -LBB8_42: - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x000000e824b42b4c // sub r14, qword [rsp + 232] - QUAD $0x000000d024b4894c // mov qword [rsp + 208], r14 - -LBB8_43: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3a44; BYTE $0x1e // cmp r11b, byte [rsi] - QUAD $0x000000c024949f0f // setg byte [rsp + 192] - LONG $0x015e3a44 // cmp r11b, byte [rsi + 1] - LONG $0xd79f0f40 // setg dil - LONG $0x025e3a44 // cmp r11b, byte [rsi + 2] - LONG $0xd39f0f41 // setg r11b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x03 // cmp al, byte [rsi + 3] - LONG $0xd79f0f41 // setg r15b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] - WORD $0x9f0f; BYTE $0xd3 // setg bl - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] - LONG $0xd59f0f41 // setg r13b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] - LONG $0xd69f0f40 // setg sil - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] - LONG $0xd09f0f41 // setg r8b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] - LONG $0xd19f0f41 // setg r9b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] - LONG $0xd69f0f41 // setg r14b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] - LONG $0xd49f0f41 // setg r12b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] - WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] - QUAD $0x000000b024949f0f // setg byte [rsp + 176] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] - QUAD $0x0000009024949f0f // setg byte [rsp + 144] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] - QUAD $0x000000a024949f0f // setg byte [rsp + 160] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] - LONG $0xd29f0f41 // setg r10b - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - QUAD $0x0000008024949f0f // setg byte [rsp + 128] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xfb // or r11b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x70 // add sil, byte [rsp + 112] - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x1cb60f44; BYTE $0x24 // movzx r11d, byte [rsp] - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xfb // or bl, r15b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xce // or r14b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xdb00 // add bl, bl - LONG $0xb0249c02; WORD $0x0000; BYTE $0x00 // add bl, byte [rsp + 176] - WORD $0xde89 // mov esi, ebx - QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b - LONG $0x2474b60f; BYTE $0x48 // movzx esi, byte [rsp + 72] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xf2 // or r10b, sil - WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al - WORD $0x0841; BYTE $0xda // or r10b, bl + LONG $0x017e8841 // mov byte [r14 + 1], dil + WORD $0x0841; BYTE $0xcf // or r15b, cl LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x18244402 // add al, byte [rsp + 24] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02578844 // mov byte [rdi + 2], r10b - WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c78348 // add rdi, 4 - LONG $0x247c8948; BYTE $0x58 // mov qword [rsp + 88], rdi - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_43 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - JMP LBB8_128 + WORD $0xc808 // or al, cl + LONG $0x240cb60f // movzx ecx, byte [rsp] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x035e8841 // mov byte [r14 + 3], bl + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 + JNE LBB8_30 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB8_45: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB8_70 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB8_182 - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_51 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_49: - WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0xf619 // sbb esi, esi - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_49 - LONG $0x01c68349 // add r14, 1 +LBB8_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_215 + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB8_189 + WORD $0xff31 // xor edi, edi + JMP LBB8_191 + +LBB8_35: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB8_111 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB8_215 + WORD $0x8a44; BYTE $0x3e // mov r15b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_129 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_139 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB8_40: + LONG $0x017a8d48 // lea rdi, [rdx + 1] + WORD $0x3a44; BYTE $0x3a // cmp r15b, byte [rdx] + WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB8_40 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JNE LBB8_140 + JMP LBB8_215 -LBB8_51: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_55 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 +LBB8_42: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB8_116 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB8_215 + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_50 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_48 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_47: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc08348 // add rax, -1 + JNE LBB8_47 + +LBB8_48: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 + +LBB8_50: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_54 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax -LBB8_53: +LBB8_52: QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] QUAD $0x000000c02494970f // seta byte [rsp + 192] @@ -40635,7 +41628,7 @@ LBB8_53: LONG $0x186a3b4c // cmp r13, qword [rdx + 24] LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] LONG $0x286a3b4c // cmp r13, qword [rdx + 40] LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] LONG $0x306a3b4c // cmp r13, qword [rdx + 48] @@ -40645,9 +41638,9 @@ LBB8_53: LONG $0x406a3b4c // cmp r13, qword [rdx + 64] LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] LONG $0x486a3b4c // cmp r13, qword [rdx + 72] - LONG $0xd6970f40 // seta sil + WORD $0x970f; BYTE $0xd1 // seta cl LONG $0x506a3b4c // cmp r13, qword [rdx + 80] - LONG $0xd0970f41 // seta r8b + LONG $0xd6970f40 // seta sil LONG $0x586a3b4c // cmp r13, qword [rdx + 88] LONG $0xd1970f41 // seta r9b LONG $0x606a3b4c // cmp r13, qword [rdx + 96] @@ -40655,37 +41648,37 @@ LBB8_53: LONG $0x686a3b4c // cmp r13, qword [rdx + 104] LONG $0xd4970f41 // seta r12b LONG $0x706a3b4c // cmp r13, qword [rdx + 112] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + QUAD $0x000000b02494970f // seta byte [rsp + 176] LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0xd0970f41 // seta r8b LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] - QUAD $0x000000b02494970f // seta byte [rsp + 176] + QUAD $0x000000902494970f // seta byte [rsp + 144] LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] QUAD $0x000000a02494970f // seta byte [rsp + 160] + LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] LONG $0xd7970f41 // seta r15b LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] LONG $0xf0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 240] LONG $0x2414970f // seta byte [rsp] LONG $0xf8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 248] @@ -40697,65 +41690,64 @@ LBB8_53: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x70 // add sil, byte [rsp + 112] + WORD $0xc900 // add cl, cl + LONG $0x70244c02 // add cl, byte [rsp + 112] LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x58244402 // add al, byte [rsp + 88] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xce89 // mov esi, ecx + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b - LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x01468845 // mov byte [r14 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al LONG $0x18244402 // add al, byte [rsp + 24] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -40763,11 +41755,11 @@ LBB8_53: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl LONG $0x240cb60f // movzx ecx, byte [rsp] @@ -40779,455 +41771,211 @@ LBB8_53: LONG $0x035e8841 // mov byte [r14 + 3], bl LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 LONG $0x04c68349 // add r14, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_53 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB8_52 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB8_55: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB8_143 +LBB8_54: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB8_167 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB8_145 - -LBB8_58: - WORD $0x8a44; BYTE $0x1e // mov r11b, byte [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_62 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JMP LBB8_169 + +LBB8_57: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_63 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_61 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx LBB8_60: - WORD $0x3844; BYTE $0x1a // cmp byte [rdx], r11b - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0xf619 // sbb esi, esi - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + WORD $0x1945; BYTE $0xdb // sbb r11d, r11d + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi LONG $0x03ffc148 // sar rdi, 3 LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + WORD $0x3045; BYTE $0xcb // xor r11b, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil + WORD $0x2044; BYTE $0xdb // and bl, r11b WORD $0x3044; BYTE $0xcb // xor bl, r9b LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc08348 // add rax, -1 JNE LBB8_60 - LONG $0x01c68349 // add r14, 1 - -LBB8_62: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_131 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x241c8844 // mov byte [rsp], r11b - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x0000010024bc894c // mov qword [rsp + 256], r15 - JB LBB8_66 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB8_194 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB8_194 - -LBB8_66: - WORD $0xc031 // xor eax, eax - QUAD $0x000000e824848948 // mov qword [rsp + 232], rax - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 -LBB8_67: - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x000000e824b42b4c // sub r14, qword [rsp + 232] - QUAD $0x000000d024b4894c // mov qword [rsp + 208], r14 +LBB8_61: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 + +LBB8_63: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_67 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax -LBB8_68: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3a44; BYTE $0x1e // cmp r11b, byte [rsi] - QUAD $0x000000c02494970f // seta byte [rsp + 192] - LONG $0x015e3a44 // cmp r11b, byte [rsi + 1] +LBB8_65: + QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 + LONG $0x2a3b4466 // cmp r13w, word [rdx] + WORD $0x970f; BYTE $0xd0 // seta al + LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] LONG $0xd7970f40 // seta dil - LONG $0x025e3a44 // cmp r11b, byte [rsi + 2] - LONG $0xd3970f41 // seta r11b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x03 // cmp al, byte [rsi + 3] - LONG $0xd7970f41 // seta r15b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] + LONG $0x6a3b4466; BYTE $0x04 // cmp r13w, word [rdx + 4] + LONG $0xd6970f41 // seta r14b + LONG $0x6a3b4466; BYTE $0x06 // cmp r13w, word [rdx + 6] LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] - WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] - LONG $0xd5970f41 // seta r13b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] + LONG $0x6a3b4466; BYTE $0x08 // cmp r13w, word [rdx + 8] LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] + LONG $0x6a3b4466; BYTE $0x0a // cmp r13w, word [rdx + 10] + QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0x6a3b4466; BYTE $0x0c // cmp r13w, word [rdx + 12] + QUAD $0x000000c02494970f // seta byte [rsp + 192] + LONG $0x6a3b4466; BYTE $0x0e // cmp r13w, word [rdx + 14] + LONG $0xd3970f41 // seta r11b + LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] + QUAD $0x000000a02494970f // seta byte [rsp + 160] + LONG $0x6a3b4466; BYTE $0x12 // cmp r13w, word [rdx + 18] + WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0x6a3b4466; BYTE $0x14 // cmp r13w, word [rdx + 20] LONG $0xd6970f40 // seta sil - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] - LONG $0xd0970f41 // seta r8b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] + LONG $0x6a3b4466; BYTE $0x16 // cmp r13w, word [rdx + 22] LONG $0xd1970f41 // seta r9b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] - LONG $0xd6970f41 // seta r14b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] + LONG $0x6a3b4466; BYTE $0x18 // cmp r13w, word [rdx + 24] + LONG $0xd2970f41 // seta r10b + LONG $0x6a3b4466; BYTE $0x1a // cmp r13w, word [rdx + 26] LONG $0xd4970f41 // seta r12b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] - WORD $0x970f; BYTE $0xd0 // seta al - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + LONG $0x6a3b4466; BYTE $0x1c // cmp r13w, word [rdx + 28] QUAD $0x000000b02494970f // seta byte [rsp + 176] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] - QUAD $0x000000902494970f // seta byte [rsp + 144] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] - QUAD $0x000000a02494970f // seta byte [rsp + 160] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] + LONG $0x6a3b4466; BYTE $0x1e // cmp r13w, word [rdx + 30] + LONG $0xd0970f41 // seta r8b + LONG $0x6a3b4466; BYTE $0x20 // cmp r13w, word [rdx + 32] LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x6a3b4466; BYTE $0x22 // cmp r13w, word [rdx + 34] LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] - LONG $0xd2970f41 // seta r10b - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] + LONG $0x6a3b4466; BYTE $0x24 // cmp r13w, word [rdx + 36] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x6a3b4466; BYTE $0x26 // cmp r13w, word [rdx + 38] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x6a3b4466; BYTE $0x2a // cmp r13w, word [rdx + 42] LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] + LONG $0x6a3b4466; BYTE $0x2c // cmp r13w, word [rdx + 44] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x6a3b4466; BYTE $0x2e // cmp r13w, word [rdx + 46] + LONG $0xd7970f41 // seta r15b + LONG $0x6a3b4466; BYTE $0x30 // cmp r13w, word [rdx + 48] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x6a3b4466; BYTE $0x32 // cmp r13w, word [rdx + 50] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] + LONG $0x6a3b4466; BYTE $0x36 // cmp r13w, word [rdx + 54] LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] + LONG $0x6a3b4466; BYTE $0x38 // cmp r13w, word [rdx + 56] LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] - QUAD $0x000000802494970f // seta byte [rsp + 128] - LONG $0x2414b60f // movzx edx, byte [rsp] - WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xdd // or r13b, bl - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0841; BYTE $0xfb // or r11b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x70 // add sil, byte [rsp + 112] - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - LONG $0x1cb60f44; BYTE $0x24 // movzx r11d, byte [rsp] - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x245cb60f; BYTE $0x78 // movzx ebx, byte [rsp + 120] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0844; BYTE $0xfb // or bl, r15b - WORD $0xde89 // mov esi, ebx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xce // or r14b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x0841; BYTE $0xdd // or r13b, bl - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x245cb60f; BYTE $0x60 // movzx ebx, byte [rsp + 96] - WORD $0xdb00 // add bl, bl - LONG $0xb0249c02; WORD $0x0000; BYTE $0x00 // add bl, byte [rsp + 176] - WORD $0xde89 // mov esi, ebx - QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] - WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] - WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] - WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b - LONG $0x2474b60f; BYTE $0x50 // movzx esi, byte [rsp + 80] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xf2 // or r10b, sil - WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al - WORD $0x0841; BYTE $0xda // or r10b, bl - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xc000 // add al, al - LONG $0x40244402 // add al, byte [rsp + 64] - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02578844 // mov byte [rdi + 2], r10b - WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c78348 // add rdi, 4 - LONG $0x247c8948; BYTE $0x30 // mov qword [rsp + 48], rdi - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_68 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - JMP LBB8_132 - -LBB8_70: - WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_74 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_72: - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_72 - LONG $0x01c68349 // add r14, 1 - -LBB8_74: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_78 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 - -LBB8_76: - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - QUAD $0x000000c024949f0f // setg byte [rsp + 192] - LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] - LONG $0xd79f0f40 // setg dil - LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] - LONG $0xd69f0f41 // setg r14b - LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] - LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] - QUAD $0x0000009024949f0f // setg byte [rsp + 144] - LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] - LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] - WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] - LONG $0xd39f0f41 // setg r11b - LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] - LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] - LONG $0xd69f0f40 // setg sil - LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] - LONG $0xd09f0f41 // setg r8b - LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] - LONG $0xd19f0f41 // setg r9b - LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] - LONG $0xd29f0f41 // setg r10b - LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] - LONG $0xd49f0f41 // setg r12b - LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] - WORD $0x9f0f; BYTE $0xd1 // setg cl - LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] - QUAD $0x000000b024949f0f // setg byte [rsp + 176] - LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] - QUAD $0x000000a024949f0f // setg byte [rsp + 160] - LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] - LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] - LONG $0xd79f0f41 // setg r15b - LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] - LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] - LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] - LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] - LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] - LONG $0x24149f0f // setg byte [rsp] - LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] - WORD $0x9f0f; BYTE $0xd3 // setg bl + LONG $0x6a3b4466; BYTE $0x3a // cmp r13w, word [rdx + 58] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x6a3b4466; BYTE $0x3c // cmp r13w, word [rdx + 60] + LONG $0x2414970f // seta byte [rsp] + LONG $0x6a3b4466; BYTE $0x3e // cmp r13w, word [rdx + 62] + WORD $0x970f; BYTE $0xd3 // seta bl WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] + WORD $0x0840; BYTE $0xc7 // or dil, al + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x06 // shl al, 6 LONG $0x07e3c041 // shl r11b, 7 WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x70 // add sil, byte [rsp + 112] + WORD $0xc900 // add cl, cl + LONG $0xa0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 160] LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x58244402 // add al, byte [rsp + 88] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xc900 // add cl, cl + LONG $0x48244c02 // add cl, byte [rsp + 72] + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b - LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x01468845 // mov byte [r14 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al LONG $0x18244402 // add al, byte [rsp + 24] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -41235,11 +41983,11 @@ LBB8_76: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl LONG $0x240cb60f // movzx ecx, byte [rsp] @@ -41249,308 +41997,102 @@ LBB8_76: WORD $0xc308 // or bl, al LONG $0x027e8845 // mov byte [r14 + 2], r15b LONG $0x035e8841 // mov byte [r14 + 3], bl - LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 + LONG $0x40c28348 // add rdx, 64 LONG $0x04c68349 // add r14, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_76 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - -LBB8_78: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB8_147 - WORD $0xff31 // xor edi, edi - JMP LBB8_149 - -LBB8_81: - LONG $0x2eb70f44 // movzx r13d, word [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_85 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_83: - LONG $0x2a394466 // cmp word [rdx], r13w - LONG $0x02528d48 // lea rdx, [rdx + 2] - WORD $0xf619 // sbb esi, esi - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_83 - LONG $0x01c68349 // add r14, 1 - -LBB8_85: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_89 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB8_65 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB8_87: - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - LONG $0x2a3b4466 // cmp r13w, word [rdx] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x6a3b4466; BYTE $0x02 // cmp r13w, word [rdx + 2] - LONG $0xd7970f40 // seta dil - LONG $0x6a3b4466; BYTE $0x04 // cmp r13w, word [rdx + 4] - LONG $0xd6970f41 // seta r14b - LONG $0x6a3b4466; BYTE $0x06 // cmp r13w, word [rdx + 6] - QUAD $0x000000c02494970f // seta byte [rsp + 192] - LONG $0x6a3b4466; BYTE $0x08 // cmp r13w, word [rdx + 8] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] - LONG $0x6a3b4466; BYTE $0x0a // cmp r13w, word [rdx + 10] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] - LONG $0x6a3b4466; BYTE $0x0c // cmp r13w, word [rdx + 12] - WORD $0x970f; BYTE $0xd0 // seta al - LONG $0x6a3b4466; BYTE $0x0e // cmp r13w, word [rdx + 14] - LONG $0xd3970f41 // seta r11b - LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0x6a3b4466; BYTE $0x12 // cmp r13w, word [rdx + 18] - LONG $0xd6970f40 // seta sil - LONG $0x6a3b4466; BYTE $0x14 // cmp r13w, word [rdx + 20] - LONG $0xd0970f41 // seta r8b - LONG $0x6a3b4466; BYTE $0x16 // cmp r13w, word [rdx + 22] - LONG $0xd1970f41 // seta r9b - LONG $0x6a3b4466; BYTE $0x18 // cmp r13w, word [rdx + 24] - LONG $0xd2970f41 // seta r10b - LONG $0x6a3b4466; BYTE $0x1a // cmp r13w, word [rdx + 26] - LONG $0xd4970f41 // seta r12b - LONG $0x6a3b4466; BYTE $0x1c // cmp r13w, word [rdx + 28] - LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0x6a3b4466; BYTE $0x1e // cmp r13w, word [rdx + 30] - WORD $0x970f; BYTE $0xd1 // seta cl - LONG $0x6a3b4466; BYTE $0x20 // cmp r13w, word [rdx + 32] - LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x6a3b4466; BYTE $0x22 // cmp r13w, word [rdx + 34] - QUAD $0x000000b02494970f // seta byte [rsp + 176] - LONG $0x6a3b4466; BYTE $0x24 // cmp r13w, word [rdx + 36] - QUAD $0x000000902494970f // seta byte [rsp + 144] - LONG $0x6a3b4466; BYTE $0x26 // cmp r13w, word [rdx + 38] - QUAD $0x000000a02494970f // seta byte [rsp + 160] - LONG $0x6a3b4466; BYTE $0x28 // cmp r13w, word [rdx + 40] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0x6a3b4466; BYTE $0x2a // cmp r13w, word [rdx + 42] - LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0x6a3b4466; BYTE $0x2c // cmp r13w, word [rdx + 44] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0x6a3b4466; BYTE $0x2e // cmp r13w, word [rdx + 46] - LONG $0xd7970f41 // seta r15b - LONG $0x6a3b4466; BYTE $0x30 // cmp r13w, word [rdx + 48] - LONG $0x2414970f // seta byte [rsp] - LONG $0x6a3b4466; BYTE $0x32 // cmp r13w, word [rdx + 50] - LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0x6a3b4466; BYTE $0x34 // cmp r13w, word [rdx + 52] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] - LONG $0x6a3b4466; BYTE $0x36 // cmp r13w, word [rdx + 54] - LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] - LONG $0x6a3b4466; BYTE $0x38 // cmp r13w, word [rdx + 56] - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] - LONG $0x6a3b4466; BYTE $0x3a // cmp r13w, word [rdx + 58] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0x6a3b4466; BYTE $0x3c // cmp r13w, word [rdx + 60] - LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x6a3b4466; BYTE $0x3e // cmp r13w, word [rdx + 62] - WORD $0x970f; BYTE $0xd3 // seta bl - WORD $0x0040; BYTE $0xff // add dil, dil - LONG $0x247c0240; BYTE $0x60 // add dil, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x38 // add sil, byte [rsp + 56] - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] - WORD $0xc689 // mov esi, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b - LONG $0x2474b60f; BYTE $0x48 // movzx esi, byte [rsp + 72] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xc000 // add al, al - WORD $0x0402; BYTE $0x24 // add al, byte [rsp] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xcb08 // or bl, cl - WORD $0xc308 // or bl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x035e8841 // mov byte [r14 + 3], bl - LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_87 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] - -LBB8_89: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB8_170 +LBB8_67: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB8_193 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB8_172 - -LBB8_92: - LONG $0x2eb70f44 // movzx r13d, word [rsi] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_96 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + JMP LBB8_195 -LBB8_94: - LONG $0x2a3b4466 // cmp r13w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] +LBB8_70: + LONG $0x2eb70f44 // movzx r13d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_76 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_74 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_73: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x293b4466 // cmp r13w, word [rcx] WORD $0x9f0f; BYTE $0xd3 // setg bl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_94 - LONG $0x01c68349 // add r14, 1 - -LBB8_96: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_135 - LONG $0x08ff8349 // cmp r15, 8 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000f024bc894c // mov qword [rsp + 240], r15 - JB LBB8_100 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB8_197 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xd0 // cmp rax, rdx - JBE LBB8_197 + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_73 -LBB8_100: +LBB8_74: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 + +LBB8_76: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_130 + LONG $0x08f98348 // cmp rcx, 8 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx + JB LBB8_80 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB8_216 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB8_216 + +LBB8_80: WORD $0xc031 // xor eax, eax LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x2434894c // mov qword [rsp], r14 -LBB8_101: - LONG $0x2424894c // mov qword [rsp], r12 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - LONG $0x24742b4c; BYTE $0x20 // sub r14, qword [rsp + 32] - QUAD $0x000000d024b4894c // mov qword [rsp + 208], r14 +LBB8_81: + LONG $0x244c2b48; BYTE $0x20 // sub rcx, qword [rsp + 32] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx -LBB8_102: +LBB8_82: WORD $0x8949; BYTE $0xf3 // mov r11, rsi LONG $0x2e3b4466 // cmp r13w, word [rsi] QUAD $0x000000c024949f0f // setg byte [rsp + 192] @@ -41561,7 +42103,7 @@ LBB8_102: LONG $0x6e3b4466; BYTE $0x06 // cmp r13w, word [rsi + 6] LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] LONG $0x6e3b4466; BYTE $0x08 // cmp r13w, word [rsi + 8] - QUAD $0x0000009024949f0f // setg byte [rsp + 144] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] LONG $0x6e3b4466; BYTE $0x0a // cmp r13w, word [rsi + 10] LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] LONG $0x6e3b4466; BYTE $0x0c // cmp r13w, word [rsi + 12] @@ -41581,37 +42123,37 @@ LBB8_102: LONG $0x6b3b4566; BYTE $0x1a // cmp r13w, word [r11 + 26] LONG $0xd49f0f41 // setg r12b LONG $0x6b3b4566; BYTE $0x1c // cmp r13w, word [r11 + 28] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + QUAD $0x000000b024949f0f // setg byte [rsp + 176] LONG $0x6b3b4566; BYTE $0x1e // cmp r13w, word [r11 + 30] LONG $0xd09f0f41 // setg r8b LONG $0x6b3b4566; BYTE $0x20 // cmp r13w, word [r11 + 32] LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] LONG $0x6b3b4566; BYTE $0x22 // cmp r13w, word [r11 + 34] - QUAD $0x000000b024949f0f // setg byte [rsp + 176] + QUAD $0x0000009024949f0f // setg byte [rsp + 144] LONG $0x6b3b4566; BYTE $0x24 // cmp r13w, word [r11 + 36] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x6b3b4566; BYTE $0x26 // cmp r13w, word [r11 + 38] QUAD $0x000000a024949f0f // setg byte [rsp + 160] + LONG $0x6b3b4566; BYTE $0x26 // cmp r13w, word [r11 + 38] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] LONG $0x6b3b4566; BYTE $0x28 // cmp r13w, word [r11 + 40] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] LONG $0x6b3b4566; BYTE $0x2a // cmp r13w, word [r11 + 42] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0x6b3b4566; BYTE $0x2c // cmp r13w, word [r11 + 44] LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x6b3b4566; BYTE $0x2c // cmp r13w, word [r11 + 44] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] LONG $0x6b3b4566; BYTE $0x2e // cmp r13w, word [r11 + 46] LONG $0xd79f0f41 // setg r15b LONG $0x6b3b4566; BYTE $0x30 // cmp r13w, word [r11 + 48] LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] LONG $0x6b3b4566; BYTE $0x32 // cmp r13w, word [r11 + 50] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0x6b3b4566; BYTE $0x34 // cmp r13w, word [r11 + 52] LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x6b3b4566; BYTE $0x34 // cmp r13w, word [r11 + 52] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] LONG $0x6b3b4566; BYTE $0x36 // cmp r13w, word [r11 + 54] LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] LONG $0x6b3b4566; BYTE $0x38 // cmp r13w, word [r11 + 56] - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0x6b3b4566; BYTE $0x3a // cmp r13w, word [r11 + 58] LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0x6b3b4566; BYTE $0x3a // cmp r13w, word [r11 + 58] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] LONG $0x6b3b4566; BYTE $0x3c // cmp r13w, word [r11 + 60] QUAD $0x0000008024949f0f // setg byte [rsp + 128] LONG $0x6b3b4566; BYTE $0x3e // cmp r13w, word [r11 + 62] @@ -41630,7 +42172,7 @@ LBB8_102: WORD $0x0844; BYTE $0xf0 // or al, r14b WORD $0xe2c0; BYTE $0x02 // shl dl, 2 WORD $0xca08 // or dl, cl - QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al WORD $0xcf89 // mov edi, ecx @@ -41643,45 +42185,45 @@ LBB8_102: WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xcc // or r12b, r9b - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] + QUAD $0x000000b02494b60f // movzx edx, byte [rsp + 176] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xd0 // or r8b, dl WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0845; BYTE $0xe0 // or r8b, r12b - QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] WORD $0xc900 // add cl, cl LONG $0x58244c02 // add cl, byte [rsp + 88] WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd108 // or cl, dl WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd108 // or cl, dl WORD $0xce89 // mov esi, ecx LONG $0x240c8b48 // mov rcx, qword [rsp] WORD $0x8844; BYTE $0x11 // mov byte [rcx], r10b - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] + LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xd7 // or r15b, dl LONG $0x01418844 // mov byte [rcx + 1], r8b WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al LONG $0x18244402 // add al, byte [rsp + 24] WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax @@ -41689,11 +42231,11 @@ LBB8_102: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xd008 // or al, dl WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xd008 // or al, dl QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] @@ -41706,123 +42248,646 @@ LBB8_102: LONG $0x40738d49 // lea rsi, [r11 + 64] LONG $0x04c18348 // add rcx, 4 LONG $0x240c8948 // mov qword [rsp], rcx - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_102 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - LONG $0x24248b4c // mov r12, qword [rsp] - JMP LBB8_136 - -LBB8_104: - WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_108 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_106: + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB8_82 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + JMP LBB8_131 + +LBB8_84: + WORD $0x8b4c; BYTE $0x2e // mov r13, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_88 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_87: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x29 // cmp r13, qword [rcx] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_87 + +LBB8_88: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 + +LBB8_90: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_94 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + +LBB8_92: + QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] + QUAD $0x000000c024949f0f // setg byte [rsp + 192] + LONG $0x086a3b4c // cmp r13, qword [rdx + 8] + LONG $0xd79f0f40 // setg dil + LONG $0x106a3b4c // cmp r13, qword [rdx + 16] + LONG $0xd69f0f41 // setg r14b + LONG $0x186a3b4c // cmp r13, qword [rdx + 24] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x206a3b4c // cmp r13, qword [rdx + 32] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x286a3b4c // cmp r13, qword [rdx + 40] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x306a3b4c // cmp r13, qword [rdx + 48] + WORD $0x9f0f; BYTE $0xd0 // setg al + LONG $0x386a3b4c // cmp r13, qword [rdx + 56] + LONG $0xd39f0f41 // setg r11b + LONG $0x406a3b4c // cmp r13, qword [rdx + 64] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x486a3b4c // cmp r13, qword [rdx + 72] + WORD $0x9f0f; BYTE $0xd1 // setg cl + LONG $0x506a3b4c // cmp r13, qword [rdx + 80] + LONG $0xd69f0f40 // setg sil + LONG $0x586a3b4c // cmp r13, qword [rdx + 88] + LONG $0xd19f0f41 // setg r9b + LONG $0x606a3b4c // cmp r13, qword [rdx + 96] + LONG $0xd29f0f41 // setg r10b + LONG $0x686a3b4c // cmp r13, qword [rdx + 104] + LONG $0xd49f0f41 // setg r12b + LONG $0x706a3b4c // cmp r13, qword [rdx + 112] + QUAD $0x000000b024949f0f // setg byte [rsp + 176] + LONG $0x786a3b4c // cmp r13, qword [rdx + 120] + LONG $0xd09f0f41 // setg r8b + LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] + QUAD $0x0000009024949f0f // setg byte [rsp + 144] + LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] + QUAD $0x000000a024949f0f // setg byte [rsp + 160] + LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] + LONG $0xd79f0f41 // setg r15b + LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0xf0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 240] + LONG $0x24149f0f // setg byte [rsp] + LONG $0xf8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 248] WORD $0x9f0f; BYTE $0xd3 // setg bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x36 // movzx r8d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_106 - LONG $0x01c68349 // add r14, 1 + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0xc900 // add cl, cl + LONG $0x70244c02 // add cl, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xce89 // mov esi, ecx + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + LONG $0x01468845 // mov byte [r14 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x18244402 // add al, byte [rsp + 24] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x240cb60f // movzx ecx, byte [rsp] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x027e8845 // mov byte [r14 + 2], r15b + LONG $0x035e8841 // mov byte [r14 + 3], bl + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c68349 // add r14, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB8_92 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + +LBB8_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB8_198 + WORD $0xff31 // xor edi, edi + JMP LBB8_200 + +LBB8_97: + WORD $0x8b44; BYTE $0x3e // mov r15d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_103 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_101 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB8_100: + WORD $0x2e0f; BYTE $0x01 // ucomiss xmm0, dword [rcx] + WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0xdbf6 // neg bl + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x06 // movzx r9d, byte [r14 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x063c8841 // mov byte [r14 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_100 + +LBB8_101: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 + +LBB8_103: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_134 + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + LONG $0x04f98348 // cmp rcx, 4 + JB LBB8_107 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB8_219 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB8_219 + +LBB8_107: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + +LBB8_108: + LONG $0x241c894c // mov qword [rsp], r11 + QUAD $0x000000e024bc8944 // mov dword [rsp + 224], r15d + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx + WORD $0x294c; BYTE $0xc9 // sub rcx, r9 + QUAD $0x000000c0248c8948 // mov qword [rsp + 192], rcx + +LBB8_109: + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] + LONG $0xd0970f41 // seta r8b + LONG $0x08432e0f // ucomiss xmm0, dword [rbx + 8] + LONG $0xd6970f41 // seta r14b + LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] + LONG $0xd5970f41 // seta r13b + LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] + LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] + LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] + WORD $0x970f; BYTE $0xd0 // seta al + LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] + LONG $0xd3970f41 // seta r11b + LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] + QUAD $0x000000b02494970f // seta byte [rsp + 176] + LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] + WORD $0x970f; BYTE $0xd1 // seta cl + LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] + LONG $0xd6970f40 // seta sil + LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] + LONG $0xd7970f40 // seta dil + LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] + LONG $0xd2970f41 // seta r10b + LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] + LONG $0xd4970f41 // seta r12b + LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] + QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] + LONG $0xd1970f41 // seta r9b + LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] + LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] + LONG $0x48432e0f // ucomiss xmm0, dword [rbx + 72] + QUAD $0x000000a02494970f // seta byte [rsp + 160] + LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] + LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] + LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x5c432e0f // ucomiss xmm0, dword [rbx + 92] + LONG $0xd7970f41 // seta r15b + LONG $0x60432e0f // ucomiss xmm0, dword [rbx + 96] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] + LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] + LONG $0x68432e0f // ucomiss xmm0, dword [rbx + 104] + LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] + LONG $0x6c432e0f // ucomiss xmm0, dword [rbx + 108] + LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] + LONG $0x70432e0f // ucomiss xmm0, dword [rbx + 112] + LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] + LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] + QUAD $0x000000802494970f // seta byte [rsp + 128] + LONG $0x7c432e0f // ucomiss xmm0, dword [rbx + 124] + WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + LONG $0x24440244; BYTE $0x78 // add r8b, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xc900 // add cl, cl + LONG $0xb0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 176] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0841; BYTE $0xfa // or r10b, dil + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x0000009024b4b60f // movzx esi, byte [rsp + 144] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x58244402 // add al, byte [rsp + 88] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x24348b48 // mov rsi, qword [rsp] + WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b + LONG $0x247cb60f; BYTE $0x38 // movzx edi, byte [rsp + 56] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xff // or r15b, dil + LONG $0x014e8844 // mov byte [rsi + 1], r9b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xc000 // add al, al + LONG $0x18244402 // add al, byte [rsp + 24] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + QUAD $0x00000080248cb60f // movzx ecx, byte [rsp + 128] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0xc208 // or dl, al + LONG $0x027e8844 // mov byte [rsi + 2], r15b + WORD $0x5688; BYTE $0x03 // mov byte [rsi + 3], dl + LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 + LONG $0x04c68348 // add rsi, 4 + LONG $0x24348948 // mov qword [rsp], rsi + QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 + JNE LBB8_109 + LONG $0x241c8b4c // mov r11, qword [rsp] + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000e024bc8b44 // mov r15d, dword [rsp + 224] + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + JMP LBB8_135 + +LBB8_111: + WORD $0x8a44; BYTE $0x3e // mov r15b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_138 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_153 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + +LBB8_114: + LONG $0x015a8d4c // lea r11, [rdx + 1] + WORD $0x3844; BYTE $0x3a // cmp byte [rdx], r15b + WORD $0xd219 // sbb edx, edx + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xd7 // and dil, dl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x1e3c8841 // mov byte [r14 + rbx], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0xffc08348 // add rax, -1 + JNE LBB8_114 + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JNE LBB8_154 + JMP LBB8_215 + +LBB8_116: + WORD $0x8b44; BYTE $0x2e // mov r13d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB8_122 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe0 // cmp r8, r12 + LONG $0xc44f0f4d // cmovg r8, r12 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB8_120 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB8_108: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_112 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 - -LBB8_110: +LBB8_119: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x29 // cmp r13d, dword [rcx] + WORD $0x9f0f; BYTE $0xd3 // setg bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB8_119 + +LBB8_120: + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + LONG $0x01c68349 // add r14, 1 + +LBB8_122: + LONG $0x24448d49; BYTE $0x1f // lea rax, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_126 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x000000d024848948 // mov qword [rsp + 208], rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + +LBB8_124: QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] + WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] QUAD $0x000000c024949f0f // setg byte [rsp + 192] - LONG $0x086a3b4c // cmp r13, qword [rdx + 8] + LONG $0x046a3b44 // cmp r13d, dword [rdx + 4] LONG $0xd79f0f40 // setg dil - LONG $0x106a3b4c // cmp r13, qword [rdx + 16] + LONG $0x086a3b44 // cmp r13d, dword [rdx + 8] LONG $0xd69f0f41 // setg r14b - LONG $0x186a3b4c // cmp r13, qword [rdx + 24] + LONG $0x0c6a3b44 // cmp r13d, dword [rdx + 12] LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] - LONG $0x206a3b4c // cmp r13, qword [rdx + 32] - QUAD $0x0000009024949f0f // setg byte [rsp + 144] - LONG $0x286a3b4c // cmp r13, qword [rdx + 40] + LONG $0x106a3b44 // cmp r13d, dword [rdx + 16] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x146a3b44 // cmp r13d, dword [rdx + 20] LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] - LONG $0x306a3b4c // cmp r13, qword [rdx + 48] + LONG $0x186a3b44 // cmp r13d, dword [rdx + 24] WORD $0x9f0f; BYTE $0xd0 // setg al - LONG $0x386a3b4c // cmp r13, qword [rdx + 56] + LONG $0x1c6a3b44 // cmp r13d, dword [rdx + 28] LONG $0xd39f0f41 // setg r11b - LONG $0x406a3b4c // cmp r13, qword [rdx + 64] + LONG $0x206a3b44 // cmp r13d, dword [rdx + 32] LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] - LONG $0x486a3b4c // cmp r13, qword [rdx + 72] + LONG $0x246a3b44 // cmp r13d, dword [rdx + 36] + WORD $0x9f0f; BYTE $0xd1 // setg cl + LONG $0x286a3b44 // cmp r13d, dword [rdx + 40] LONG $0xd69f0f40 // setg sil - LONG $0x506a3b4c // cmp r13, qword [rdx + 80] - LONG $0xd09f0f41 // setg r8b - LONG $0x586a3b4c // cmp r13, qword [rdx + 88] + LONG $0x2c6a3b44 // cmp r13d, dword [rdx + 44] LONG $0xd19f0f41 // setg r9b - LONG $0x606a3b4c // cmp r13, qword [rdx + 96] + LONG $0x306a3b44 // cmp r13d, dword [rdx + 48] LONG $0xd29f0f41 // setg r10b - LONG $0x686a3b4c // cmp r13, qword [rdx + 104] + LONG $0x346a3b44 // cmp r13d, dword [rdx + 52] LONG $0xd49f0f41 // setg r12b - LONG $0x706a3b4c // cmp r13, qword [rdx + 112] - LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] - LONG $0x786a3b4c // cmp r13, qword [rdx + 120] - WORD $0x9f0f; BYTE $0xd1 // setg cl - LONG $0x80aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 128] - LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] - LONG $0x88aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 136] + LONG $0x386a3b44 // cmp r13d, dword [rdx + 56] QUAD $0x000000b024949f0f // setg byte [rsp + 176] - LONG $0x90aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 144] - LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] - LONG $0x98aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 152] + LONG $0x3c6a3b44 // cmp r13d, dword [rdx + 60] + LONG $0xd09f0f41 // setg r8b + LONG $0x406a3b44 // cmp r13d, dword [rdx + 64] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x446a3b44 // cmp r13d, dword [rdx + 68] + QUAD $0x0000009024949f0f // setg byte [rsp + 144] + LONG $0x486a3b44 // cmp r13d, dword [rdx + 72] QUAD $0x000000a024949f0f // setg byte [rsp + 160] - LONG $0xa0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 160] - LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] - LONG $0xa8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 168] - LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] - LONG $0xb0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 176] + LONG $0x4c6a3b44 // cmp r13d, dword [rdx + 76] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x506a3b44 // cmp r13d, dword [rdx + 80] + LONG $0x24549f0f; BYTE $0x68 // setg byte [rsp + 104] + LONG $0x546a3b44 // cmp r13d, dword [rdx + 84] LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] - LONG $0xb8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 184] + LONG $0x586a3b44 // cmp r13d, dword [rdx + 88] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x5c6a3b44 // cmp r13d, dword [rdx + 92] LONG $0xd79f0f41 // setg r15b - LONG $0xc0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 192] + LONG $0x606a3b44 // cmp r13d, dword [rdx + 96] LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] - LONG $0xc8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 200] - LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] - LONG $0xd0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 208] + LONG $0x646a3b44 // cmp r13d, dword [rdx + 100] LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] - LONG $0xd8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 216] + LONG $0x686a3b44 // cmp r13d, dword [rdx + 104] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x6c6a3b44 // cmp r13d, dword [rdx + 108] LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] - LONG $0xe0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 224] - LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] - LONG $0xe8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 232] + LONG $0x706a3b44 // cmp r13d, dword [rdx + 112] LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] - LONG $0xf0aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 240] + LONG $0x746a3b44 // cmp r13d, dword [rdx + 116] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x786a3b44 // cmp r13d, dword [rdx + 120] LONG $0x24149f0f // setg byte [rsp] - LONG $0xf8aa3b4c; WORD $0x0000; BYTE $0x00 // cmp r13, qword [rdx + 248] + LONG $0x7c6a3b44 // cmp r13d, dword [rdx + 124] WORD $0x9f0f; BYTE $0xd3 // setg bl WORD $0x0040; BYTE $0xff // add dil, dil QUAD $0x000000c024bc0240 // add dil, byte [rsp + 192] @@ -41831,65 +42896,64 @@ LBB8_110: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0841; BYTE $0xfe // or r14b, dil - WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x70 // add sil, byte [rsp + 112] + WORD $0xc900 // add cl, cl + LONG $0x70244c02 // add cl, byte [rsp + 112] LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0xc789 // mov edi, eax - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + WORD $0xcf89 // mov edi, ecx LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - LONG $0x2474b60f; BYTE $0x68 // movzx esi, byte [rsp + 104] + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] LONG $0x06e6c040 // shl sil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0x0841; BYTE $0xc3 // or r11b, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe0 // or r8b, r12b QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xc000 // add al, al - LONG $0x58244402 // add al, byte [rsp + 88] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xc900 // add cl, cl + LONG $0x58244c02 // add cl, byte [rsp + 88] + WORD $0xce89 // mov esi, ecx + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b - LONG $0x2474b60f; BYTE $0x40 // movzx esi, byte [rsp + 64] + LONG $0x2474b60f; BYTE $0x38 // movzx esi, byte [rsp + 56] LONG $0x06e6c040 // shl sil, 6 LONG $0x07e7c041 // shl r15b, 7 WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x01468845 // mov byte [r14 + 1], r8b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xc000 // add al, al LONG $0x18244402 // add al, byte [rsp + 24] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -41897,11 +42961,11 @@ LBB8_110: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl LONG $0x240cb60f // movzx ecx, byte [rsp] @@ -41911,318 +42975,555 @@ LBB8_110: WORD $0xc308 // or bl, al LONG $0x027e8845 // mov byte [r14 + 2], r15b LONG $0x035e8841 // mov byte [r14 + 3], bl - LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 LONG $0x04c68349 // add r14, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB8_110 - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB8_124 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] -LBB8_112: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB8_175 +LBB8_126: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB8_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JNE LBB8_171 WORD $0xff31 // xor edi, edi - JMP LBB8_177 - -LBB8_115: - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff3 // movss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB8_119 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB8_117: - WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] - WORD $0x970f; BYTE $0xd3 // seta bl - LONG $0x04c28348 // add rdx, 4 - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x363c8841 // mov byte [r14 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB8_117 - LONG $0x01c68349 // add r14, 1 + JMP LBB8_173 -LBB8_119: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB8_139 - LONG $0x04fb8349 // cmp r11, 4 - JB LBB8_123 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB8_200 - LONG $0x9e048d4b // lea rax, [r14 + 4*r11] - WORD $0x3948; BYTE $0xd0 // cmp rax, rdx - JBE LBB8_200 +LBB8_129: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + JMP LBB8_141 + +LBB8_130: + LONG $0x2434894c // mov qword [rsp], r14 + WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + +LBB8_131: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB8_215 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JNE LBB8_205 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB8_207 -LBB8_123: - WORD $0x3145; BYTE $0xc0 // xor r8d, r8d +LBB8_134: + WORD $0x894d; BYTE $0xf3 // mov r11, r14 WORD $0x8948; BYTE $0xd3 // mov rbx, rdx - WORD $0x894d; BYTE $0xf7 // mov r15, r14 -LBB8_124: - LONG $0x243c894c // mov qword [rsp], r15 - QUAD $0x000000882494894c // mov qword [rsp + 136], r10 - QUAD $0x000000d0249c894c // mov qword [rsp + 208], r11 - WORD $0x294d; BYTE $0xc3 // sub r11, r8 - QUAD $0x000000c0249c894c // mov qword [rsp + 192], r11 +LBB8_135: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB8_215 + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JNE LBB8_211 + WORD $0xf631 // xor esi, esi + JMP LBB8_213 -LBB8_125: - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] - LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] - LONG $0xd0970f41 // seta r8b - LONG $0x08432e0f // ucomiss xmm0, dword [rbx + 8] - LONG $0xd6970f41 // seta r14b - LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] - LONG $0xd5970f41 // seta r13b - LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] - QUAD $0x000000902494970f // seta byte [rsp + 144] - LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] - LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] - LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] - WORD $0x970f; BYTE $0xd0 // seta al - LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] - LONG $0xd3970f41 // seta r11b - LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] - LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] - LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] - WORD $0x970f; BYTE $0xd2 // seta dl - LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] - LONG $0xd6970f40 // seta sil - LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] +LBB8_138: + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + JMP LBB8_155 + +LBB8_139: + WORD $0x8948; BYTE $0xd7 // mov rdi, rdx + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + +LBB8_140: + LONG $0x01c68349 // add r14, 1 + +LBB8_141: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_149 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x243c8844 // mov byte [rsp], r15b + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + JB LBB8_145 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB8_222 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB8_222 + +LBB8_145: + WORD $0xc031 // xor eax, eax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + LONG $0x2474894c; BYTE $0x68 // mov qword [rsp + 104], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + +LBB8_146: + QUAD $0x000000f8248c2b48 // sub rcx, qword [rsp + 248] + QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx + +LBB8_147: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3a44; BYTE $0x3e // cmp r15b, byte [rsi] + QUAD $0x000000e024949f0f // setg byte [rsp + 224] + LONG $0x017e3a44 // cmp r15b, byte [rsi + 1] + LONG $0xd79f0f40 // setg dil + LONG $0x027e3a44 // cmp r15b, byte [rsi + 2] + LONG $0xd39f0f41 // setg r11b + LONG $0x037e3a44 // cmp r15b, byte [rsi + 3] + LONG $0xd79f0f41 // setg r15b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] + QUAD $0x000000c024949f0f // setg byte [rsp + 192] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] + QUAD $0x000000a024949f0f // setg byte [rsp + 160] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] + WORD $0x9f0f; BYTE $0xd3 // setg bl + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] + LONG $0xd49f0f41 // setg r12b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] + LONG $0x24549f0f; BYTE $0x78 // setg byte [rsp + 120] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] + LONG $0xd69f0f40 // setg sil + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] + LONG $0xd09f0f41 // setg r8b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] + LONG $0xd19f0f41 // setg r9b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] + LONG $0xd69f0f41 // setg r14b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] + LONG $0x24549f0f; BYTE $0x48 // setg byte [rsp + 72] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] + LONG $0x24549f0f; BYTE $0x70 // setg byte [rsp + 112] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + LONG $0xd59f0f41 // setg r13b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + QUAD $0x000000b024949f0f // setg byte [rsp + 176] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + QUAD $0x0000009024949f0f // setg byte [rsp + 144] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] + LONG $0x24549f0f; BYTE $0x50 // setg byte [rsp + 80] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] + LONG $0x24549f0f; BYTE $0x60 // setg byte [rsp + 96] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] + LONG $0x24549f0f; BYTE $0x58 // setg byte [rsp + 88] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] + LONG $0x24549f0f; BYTE $0x38 // setg byte [rsp + 56] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x24549f0f; BYTE $0x40 // setg byte [rsp + 64] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] + LONG $0xd29f0f41 // setg r10b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] + LONG $0x24549f0f; BYTE $0x30 // setg byte [rsp + 48] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] + LONG $0x24549f0f; BYTE $0x28 // setg byte [rsp + 40] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] + LONG $0x24549f0f; BYTE $0x20 // setg byte [rsp + 32] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] + LONG $0x24549f0f; BYTE $0x18 // setg byte [rsp + 24] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] + LONG $0x24549f0f; BYTE $0x10 // setg byte [rsp + 16] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] + LONG $0x24549f0f; BYTE $0x08 // setg byte [rsp + 8] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] + QUAD $0x0000008024949f0f // setg byte [rsp + 128] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] + WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x000000e024bc0240 // add dil, byte [rsp + 224] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0841; BYTE $0xfb // or r11b, dil + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + QUAD $0x000000c0249cb60f // movzx ebx, byte [rsp + 192] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xfb // or bl, r15b + WORD $0xd889 // mov eax, ebx + LONG $0x3cb60f44; BYTE $0x24 // movzx r15d, byte [rsp] + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xce // or r14b, r9b + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xf5 // or r13b, sil + WORD $0x0841; BYTE $0xdc // or r12b, bl + WORD $0x0841; BYTE $0xc5 // or r13b, al + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xc000 // add al, al + LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x245cb60f; BYTE $0x38 // movzx ebx, byte [rsp + 56] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] + WORD $0x8844; BYTE $0x27 // mov byte [rdi], r12b + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x016f8844 // mov byte [rdi + 1], r13b + WORD $0x0841; BYTE $0xda // or r10b, bl + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xd808 // or al, bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02578844 // mov byte [rdi + 2], r10b + WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + LONG $0x247c8948; BYTE $0x68 // mov qword [rsp + 104], rdi + QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 + JNE LBB8_147 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + JMP LBB8_150 + +LBB8_149: + LONG $0x2474894c; BYTE $0x68 // mov qword [rsp + 104], r14 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + +LBB8_150: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB8_215 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JNE LBB8_175 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB8_178 + +LBB8_153: + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + WORD $0x294d; BYTE $0xc4 // sub r12, r8 + JE LBB8_215 + +LBB8_154: + LONG $0x01c68349 // add r14, 1 + +LBB8_155: + LONG $0x244c8d49; BYTE $0x1f // lea rcx, [r12 + 31] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xcc490f49 // cmovns rcx, r12 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fc8349 // cmp r12, 32 + JL LBB8_163 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x243c8844 // mov byte [rsp], r15b + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + JB LBB8_159 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xd8 // add rax, r11 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JAE LBB8_225 + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + WORD $0x3949; BYTE $0xc3 // cmp r11, rax + JAE LBB8_225 + +LBB8_159: + WORD $0xc031 // xor eax, eax + QUAD $0x000000f824848948 // mov qword [rsp + 248], rax + LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x894c; BYTE $0xde // mov rsi, r11 + +LBB8_160: + QUAD $0x000000f8248c2b48 // sub rcx, qword [rsp + 248] + QUAD $0x000000d0248c8948 // mov qword [rsp + 208], rcx + +LBB8_161: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3a44; BYTE $0x3e // cmp r15b, byte [rsi] + QUAD $0x000000e02494970f // seta byte [rsp + 224] + LONG $0x017e3a44 // cmp r15b, byte [rsi + 1] LONG $0xd7970f40 // seta dil - LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] - LONG $0xd2970f41 // seta r10b - LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] + LONG $0x027e3a44 // cmp r15b, byte [rsi + 2] + LONG $0xd3970f41 // seta r11b + LONG $0x037e3a44 // cmp r15b, byte [rsi + 3] + LONG $0xd7970f41 // seta r15b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x04 // cmp al, byte [rsi + 4] + QUAD $0x000000c02494970f // seta byte [rsp + 192] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x05 // cmp al, byte [rsi + 5] + QUAD $0x000000a02494970f // seta byte [rsp + 160] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x06 // cmp al, byte [rsi + 6] + WORD $0x970f; BYTE $0xd3 // seta bl + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x07 // cmp al, byte [rsi + 7] LONG $0xd4970f41 // seta r12b - LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] - QUAD $0x000000b02494970f // seta byte [rsp + 176] - LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x08 // cmp al, byte [rsi + 8] + LONG $0x2454970f; BYTE $0x78 // seta byte [rsp + 120] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x463a; BYTE $0x09 // cmp al, byte [rsi + 9] + LONG $0xd6970f40 // seta sil + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0a // cmp al, byte [rcx + 10] + LONG $0xd0970f41 // seta r8b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0b // cmp al, byte [rcx + 11] LONG $0xd1970f41 // seta r9b - LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] - LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] - LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0c // cmp al, byte [rcx + 12] + LONG $0xd6970f41 // seta r14b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0d // cmp al, byte [rcx + 13] + LONG $0x2454970f; BYTE $0x68 // seta byte [rsp + 104] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0e // cmp al, byte [rcx + 14] LONG $0x2454970f; BYTE $0x70 // seta byte [rsp + 112] - LONG $0x48432e0f // ucomiss xmm0, dword [rbx + 72] - LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] - LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] - QUAD $0x000000a02494970f // seta byte [rsp + 160] - LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x413a; BYTE $0x0f // cmp al, byte [rcx + 15] + LONG $0xd5970f41 // seta r13b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x10 // cmp dl, byte [rcx + 16] + QUAD $0x000000b02494970f // seta byte [rsp + 176] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x11 // cmp dl, byte [rcx + 17] + QUAD $0x000000902494970f // seta byte [rsp + 144] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x12 // cmp dl, byte [rcx + 18] LONG $0x2454970f; BYTE $0x50 // seta byte [rsp + 80] - LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] - LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] - LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x13 // cmp dl, byte [rcx + 19] + LONG $0x2454970f; BYTE $0x60 // seta byte [rsp + 96] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x14 // cmp dl, byte [rcx + 20] + LONG $0x2454970f; BYTE $0x58 // seta byte [rsp + 88] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x15 // cmp dl, byte [rcx + 21] LONG $0x2454970f; BYTE $0x40 // seta byte [rsp + 64] - LONG $0x5c432e0f // ucomiss xmm0, dword [rbx + 92] - LONG $0xd7970f41 // seta r15b - LONG $0x60432e0f // ucomiss xmm0, dword [rbx + 96] - LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] - LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x16 // cmp dl, byte [rcx + 22] + LONG $0x2454970f; BYTE $0x48 // seta byte [rsp + 72] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x17 // cmp dl, byte [rcx + 23] + LONG $0xd2970f41 // seta r10b + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x18 // cmp dl, byte [rcx + 24] + LONG $0x2454970f; BYTE $0x38 // seta byte [rsp + 56] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x19 // cmp dl, byte [rcx + 25] LONG $0x2454970f; BYTE $0x28 // seta byte [rsp + 40] - LONG $0x68432e0f // ucomiss xmm0, dword [rbx + 104] - LONG $0x2454970f; BYTE $0x30 // seta byte [rsp + 48] - LONG $0x6c432e0f // ucomiss xmm0, dword [rbx + 108] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1a // cmp dl, byte [rcx + 26] LONG $0x2454970f; BYTE $0x20 // seta byte [rsp + 32] - LONG $0x70432e0f // ucomiss xmm0, dword [rbx + 112] - LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] - LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1b // cmp dl, byte [rcx + 27] + LONG $0x2454970f; BYTE $0x18 // seta byte [rsp + 24] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1c // cmp dl, byte [rcx + 28] LONG $0x2454970f; BYTE $0x10 // seta byte [rsp + 16] - LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1d // cmp dl, byte [rcx + 29] + LONG $0x2454970f; BYTE $0x08 // seta byte [rsp + 8] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1e // cmp dl, byte [rcx + 30] QUAD $0x000000802494970f // seta byte [rsp + 128] - LONG $0x7c432e0f // ucomiss xmm0, dword [rbx + 124] - WORD $0x970f; BYTE $0xd1 // seta cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x78 // add r8b, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xc3 // or r11b, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xc6 // or r14b, r8b - WORD $0xd200 // add dl, dl - LONG $0x68245402 // add dl, byte [rsp + 104] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b - LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + LONG $0x2414b60f // movzx edx, byte [rsp] + WORD $0x513a; BYTE $0x1f // cmp dl, byte [rcx + 31] + WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0x0040; BYTE $0xff // add dil, dil + QUAD $0x000000e024bc0240 // add dil, byte [rsp + 224] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0841; BYTE $0xfb // or r11b, dil + WORD $0x0040; BYTE $0xf6 // add sil, sil + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + QUAD $0x000000c0249cb60f // movzx ebx, byte [rsp + 192] + WORD $0xe3c0; BYTE $0x04 // shl bl, 4 + WORD $0x0844; BYTE $0xfb // or bl, r15b + WORD $0xd889 // mov eax, ebx + LONG $0x3cb60f44; BYTE $0x24 // movzx r15d, byte [rsp] + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xce // or r14b, r9b + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xf0 // or al, r14b + LONG $0x2474b60f; BYTE $0x70 // movzx esi, byte [rsp + 112] LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0845; BYTE $0xe1 // or r9b, r12b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xf5 // or r13b, sil + WORD $0x0841; BYTE $0xdc // or r12b, bl + WORD $0x0841; BYTE $0xc5 // or r13b, al + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xc000 // add al, al - LONG $0x58244402 // add al, byte [rsp + 88] - LONG $0x2454b60f; BYTE $0x60 // movzx edx, byte [rsp + 96] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x38 // movzx edx, byte [rsp + 56] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - LONG $0x24348b48 // mov rsi, qword [rsp] - WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b - LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xff // or r15b, dil - LONG $0x014e8844 // mov byte [rsi + 1], r9b - WORD $0x0841; BYTE $0xd7 // or r15b, dl + LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + WORD $0xe3c0; BYTE $0x05 // shl bl, 5 + WORD $0xc308 // or bl, al + LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] + WORD $0x8844; BYTE $0x27 // mov byte [rdi], r12b + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x016f8844 // mov byte [rdi + 1], r13b + WORD $0x0841; BYTE $0xda // or r10b, bl LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax + LONG $0x38244402 // add al, byte [rsp + 56] + WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd008 // or al, dl - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd108 // or cl, dl - WORD $0xc108 // or cl, al - LONG $0x027e8844 // mov byte [rsi + 2], r15b - WORD $0x4e88; BYTE $0x03 // mov byte [rsi + 3], cl - LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 - LONG $0x04c68348 // add rsi, 4 - LONG $0x24348948 // mov qword [rsp], rsi - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB8_125 - LONG $0x243c8b4c // mov r15, qword [rsp] - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - QUAD $0x000000d0249c8b4c // mov r11, qword [rsp + 208] - JMP LBB8_140 - -LBB8_127: - LONG $0x2474894c; BYTE $0x58 // mov qword [rsp + 88], r14 - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - -LBB8_128: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB8_151 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB8_154 + WORD $0xd808 // or al, bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02578844 // mov byte [rdi + 2], r10b + WORD $0x5788; BYTE $0x03 // mov byte [rdi + 3], dl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + LONG $0x247c8948; BYTE $0x30 // mov qword [rsp + 48], rdi + QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 + JNE LBB8_161 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + JMP LBB8_164 -LBB8_131: +LBB8_163: LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx + WORD $0x894c; BYTE $0xde // mov rsi, r11 -LBB8_132: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB8_156 +LBB8_164: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB8_215 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcc // cmp r12, rcx + JNE LBB8_180 WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB8_159 - -LBB8_135: - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - WORD $0x8948; BYTE $0xd6 // mov rsi, rdx - -LBB8_136: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB8_183 - WORD $0x3145; BYTE $0xf6 // xor r14d, r14d - JMP LBB8_185 - -LBB8_139: - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + JMP LBB8_183 -LBB8_140: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB8_182 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB8_187 - WORD $0xf631 // xor esi, esi - JMP LBB8_189 - -LBB8_143: +LBB8_167: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB8_144: +LBB8_168: WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xde // mov rsi, r11 @@ -42248,20 +43549,20 @@ LBB8_144: WORD $0xc330 // xor bl, al LONG $0x361c8841 // mov byte [r14 + rsi], bl WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB8_144 + JNE LBB8_168 -LBB8_145: +LBB8_169: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 + JE LBB8_215 WORD $0x394c; BYTE $0x2a // cmp qword [rdx], r13 - JMP LBB8_174 + JMP LBB8_197 -LBB8_147: +LBB8_171: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0xff31 // xor edi, edi -LBB8_148: +LBB8_172: WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al @@ -42289,23 +43590,23 @@ LBB8_148: WORD $0xd830 // xor al, bl LONG $0x36048841 // mov byte [r14 + rsi], al WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_148 + JNE LBB8_172 -LBB8_149: +LBB8_173: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 + JE LBB8_215 WORD $0x3b44; BYTE $0x2a // cmp r13d, dword [rdx] - JMP LBB8_179 + JMP LBB8_202 -LBB8_151: +LBB8_175: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] -LBB8_152: +LBB8_176: WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3a46 // cmp r11b, byte [rsi + r9] + LONG $0x0e3c3a46 // cmp r15b, byte [rsi + r9] WORD $0x9f0f; BYTE $0xd3 // setg bl WORD $0xdbf6 // neg bl WORD $0x894c; BYTE $0xcf // mov rdi, r9 @@ -42314,12 +43615,12 @@ LBB8_152: WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x065c3a44; BYTE $0x01 // cmp r11b, byte [rsi + rax + 1] + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x067c3a44; BYTE $0x01 // cmp r15b, byte [rsi + rax + 1] LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x9f0f; BYTE $0xd3 // setg bl WORD $0xdbf6 // neg bl @@ -42329,38 +43630,35 @@ LBB8_152: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3b048841 // mov byte [r11 + rdi], al WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB8_152 + JNE LBB8_176 WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB8_154: +LBB8_178: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - WORD $0x3a44; BYTE $0x1e // cmp r11b, byte [rsi] + JE LBB8_215 + WORD $0x3a44; BYTE $0x3e // cmp r15b, byte [rsi] WORD $0x9f0f; BYTE $0xd0 // setg al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + LONG $0x24448b4c; BYTE $0x68 // mov r8, qword [rsp + 104] LONG $0x103c8a41 // mov dil, byte [r8 + rdx] LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xc9 // mov ecx, r9d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - JMP LBB8_161 + JMP LBB8_209 -LBB8_156: +LBB8_180: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] -LBB8_157: +LBB8_181: WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b + LONG $0x0e3c3846 // cmp byte [rsi + r9], r15b WORD $0xff19 // sbb edi, edi WORD $0x894c; BYTE $0xcb // mov rbx, r9 LONG $0x03ebc148 // shr rbx, 3 @@ -42368,12 +43666,12 @@ LBB8_157: WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1b // movzx r9d, byte [r11 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0x2040; BYTE $0xfa // and dl, dil WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x1e148841 // mov byte [r14 + rbx], dl - LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b + LONG $0x1b148841 // mov byte [r11 + rbx], dl + LONG $0x067c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r15b LONG $0x02488d4c // lea r9, [rax + 2] WORD $0xff19 // sbb edi, edi WORD $0x3040; BYTE $0xd7 // xor dil, dl @@ -42382,15 +43680,15 @@ LBB8_157: WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0xd030 // xor al, dl - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1b048841 // mov byte [r11 + rbx], al WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB8_157 + JNE LBB8_181 WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB8_159: +LBB8_183: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b + JE LBB8_215 + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b WORD $0xc019 // sbb eax, eax WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 @@ -42402,2320 +43700,415 @@ LBB8_159: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al + JMP LBB8_210 -LBB8_161: - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB8_182 - -LBB8_162: +LBB8_185: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB8_163: +LBB8_186: WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d - WORD $0xff19 // sbb edi, edi - WORD $0x894c; BYTE $0xde // mov rsi, r11 - LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x36 // movzx r10d, byte [r14 + rsi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x36048841 // mov byte [r14 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x046a3944 // cmp dword [rdx + 4], r13d - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0xff19 // sbb edi, edi - WORD $0x3040; BYTE $0xc7 // xor dil, al - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x361c8841 // mov byte [r14 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB8_163 - -LBB8_164: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d - JMP LBB8_174 - -LBB8_166: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi - -LBB8_167: - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] - LONG $0xd1970f41 // seta r9b - LONG $0x10c28348 // add rdx, 16 - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x36048841 // mov byte [r14 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_167 - -LBB8_168: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - WORD $0x970f; BYTE $0xd0 // seta al - JMP LBB8_180 - -LBB8_170: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - -LBB8_171: - LONG $0x2a394466 // cmp word [rdx], r13w - WORD $0xff19 // sbb edi, edi - WORD $0x894c; BYTE $0xde // mov rsi, r11 - LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x36 // movzx r10d, byte [r14 + rsi] - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x36048841 // mov byte [r14 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x6a394466; BYTE $0x02 // cmp word [rdx + 2], r13w - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0xff19 // sbb edi, edi - WORD $0x3040; BYTE $0xc7 // xor dil, al - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x361c8841 // mov byte [r14 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB8_171 - -LBB8_172: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - LONG $0x2a394466 // cmp word [rdx], r13w - -LBB8_174: - WORD $0xc019 // sbb eax, eax - WORD $0x894c; BYTE $0xda // mov rdx, r11 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x16348a41 // mov sil, byte [r14 + rdx] - LONG $0x07e38041 // and r11b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - JMP LBB8_181 - -LBB8_175: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xff31 // xor edi, edi - -LBB8_176: - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - WORD $0x9f0f; BYTE $0xd0 // setg al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfe // mov rsi, rdi - LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] - WORD $0xf989 // mov ecx, edi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x361c8841 // mov byte [r14 + rsi], bl - LONG $0x02c78348 // add rdi, 2 - LONG $0x086a3b4c // cmp r13, qword [rdx + 8] - LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd19f0f41 // setg r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x36048841 // mov byte [r14 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB8_176 - -LBB8_177: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] - -LBB8_179: - WORD $0x9f0f; BYTE $0xd0 // setg al - -LBB8_180: - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xfa // mov rdx, rdi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x16348a41 // mov sil, byte [r14 + rdx] - LONG $0x07e78040 // and dil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf989 // mov ecx, edi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - -LBB8_181: - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x161c8841 // mov byte [r14 + rdx], bl - -LBB8_182: - MOVQ 336(SP), SP - RET - -LBB8_183: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xf6 // xor r14d, r14d - -LBB8_184: - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x2e3b4466 // cmp r13w, word [rsi] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3c // movzx r10d, byte [r12 + rdi] - WORD $0x8944; BYTE $0xf1 // mov ecx, r14d - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x02c68349 // add r14, 2 - LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x9f0f; BYTE $0xd2 // setg dl - WORD $0xdaf6 // neg dl - WORD $0xda30 // xor dl, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0xff19 // sbb edi, edi + WORD $0x894c; BYTE $0xde // mov rsi, r11 + LONG $0x03eec148 // shr rsi, 3 + LONG $0x14b60f45; BYTE $0x36 // movzx r10d, byte [r14 + rsi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0xd020 // and al, dl - WORD $0xd830 // xor al, bl - LONG $0x3c048841 // mov byte [r12 + rdi], al - WORD $0x394d; BYTE $0xf1 // cmp r9, r14 - JNE LBB8_184 + WORD $0x3044; BYTE $0xd7 // xor dil, r10b + WORD $0x2040; BYTE $0xf8 // and al, dil + WORD $0x3044; BYTE $0xd0 // xor al, r10b + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x02c38349 // add r11, 2 + LONG $0x046a3944 // cmp dword [rdx + 4], r13d + LONG $0x08528d48 // lea rdx, [rdx + 8] + WORD $0xff19 // sbb edi, edi + WORD $0x3040; BYTE $0xc7 // xor dil, al + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x2040; BYTE $0xfb // and bl, dil + WORD $0xc330 // xor bl, al + LONG $0x361c8841 // mov byte [r14 + rsi], bl + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB8_186 -LBB8_185: +LBB8_187: LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - LONG $0x2e3b4466 // cmp r13w, word [rsi] - WORD $0x9f0f; BYTE $0xd0 // setg al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xf2 // mov rdx, r14 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x143c8a41 // mov dil, byte [r12 + rdx] - LONG $0x07e68041 // and r14b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xf1 // mov ecx, r14d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x141c8841 // mov byte [r12 + rdx], bl - JMP LBB8_182 + JE LBB8_215 + WORD $0x3944; BYTE $0x2a // cmp dword [rdx], r13d + JMP LBB8_197 -LBB8_187: +LBB8_189: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - WORD $0x894d; BYTE $0xfb // mov r11, r15 + WORD $0xff31 // xor edi, edi -LBB8_188: - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x970f; BYTE $0xd2 // seta dl - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] - WORD $0xf189 // mov ecx, esi +LBB8_190: + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x3044; BYTE $0xca // xor dl, r9b - WORD $0xd020 // and al, dl + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3b048841 // mov byte [r11 + rdi], al - LONG $0x02c68348 // add rsi, 2 - LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x361c8841 // mov byte [r14 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] LONG $0xd1970f41 // seta r9b - LONG $0x08c38348 // add rbx, 8 + LONG $0x10c28348 // add rdx, 16 WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xc1 // xor r9b, al - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0x2044; BYTE $0xca // and dl, r9b - WORD $0xc230 // xor dl, al - LONG $0x3b148841 // mov byte [r11 + rdi], dl - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB8_188 - -LBB8_189: - LONG $0x01c0f641 // test r8b, 1 - JE LBB8_182 - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0x970f; BYTE $0xd0 // seta al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - LONG $0x173c8a41 // mov dil, byte [r15 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x171c8841 // mov byte [r15 + rdx], bl - JMP LBB8_182 - -LBB8_191: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - LONG $0x24448948; BYTE $0x58 // mov qword [rsp + 88], rax - LONG $0xc3b60f41 // movzx eax, r11b - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000120248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm1 - WORD $0xc031 // xor eax, eax - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 - -LBB8_192: - WORD $0x8949; BYTE $0xc1 // mov r9, rax - LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax - LONG $0x05e0c148 // shl rax, 5 - LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax - WORD $0x8949; BYTE $0xc3 // mov r11, rax - WORD $0x8949; BYTE $0xc1 // mov r9, rax - WORD $0x8949; BYTE $0xc4 // mov r12, rax - WORD $0x8949; BYTE $0xc6 // mov r14, rax - WORD $0x8949; BYTE $0xc5 // mov r13, rax - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - WORD $0x8949; BYTE $0xc2 // mov r10, rax - WORD $0x8949; BYTE $0xc7 // mov r15, rax - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax - LONG $0x020cb60f // movzx ecx, byte [rdx + rax] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x024cb60f; BYTE $0x01 // movzx ecx, byte [rdx + rax + 1] - LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x024cb60f; BYTE $0x02 // movzx ecx, byte [rdx + rax + 2] - LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x024cb60f; BYTE $0x03 // movzx ecx, byte [rdx + rax + 3] - LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x024cb60f; BYTE $0x04 // movzx ecx, byte [rdx + rax + 4] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x024cb60f; BYTE $0x05 // movzx ecx, byte [rdx + rax + 5] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x024cb60f; BYTE $0x06 // movzx ecx, byte [rdx + rax + 6] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 - LONG $0x024cb60f; BYTE $0x07 // movzx ecx, byte [rdx + rax + 7] - LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x024cb60f; BYTE $0x08 // movzx ecx, byte [rdx + rax + 8] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x024cb60f; BYTE $0x09 // movzx ecx, byte [rdx + rax + 9] - LONG $0xc16e0f66 // movd xmm0, ecx - LONG $0x024cb60f; BYTE $0x0a // movzx ecx, byte [rdx + rax + 10] - LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x024cb60f; BYTE $0x0b // movzx ecx, byte [rdx + rax + 11] - LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x024cb60f; BYTE $0x0c // movzx ecx, byte [rdx + rax + 12] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x024cb60f; BYTE $0x10 // movzx ecx, byte [rdx + rax + 16] - LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x024cb60f; BYTE $0x18 // movzx ecx, byte [rdx + rax + 24] - LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x20c98348 // or rcx, 32 - LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - LONG $0x40c88349 // or r8, 64 - LONG $0x2444894c; BYTE $0x40 // mov qword [rsp + 64], r8 - LONG $0x60cb8349 // or r11, 96 - LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 - LONG $0xa0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 160 - QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 - LONG $0xc0ce8149; WORD $0x0000; BYTE $0x00 // or r14, 192 - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - LONG $0xe0cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 224 - LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 - LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 - LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 - LONG $0x40cf8149; WORD $0x0001; BYTE $0x00 // or r15, 320 - LONG $0x60cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 352 - QUAD $0x00018048244c8148; BYTE $0x00 // or qword [rsp + 72], 384 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 - LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx - LONG $0xc0ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 448 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 - LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x010204203a0f4466 // pinsrb xmm8, byte [rdx + rax], 1 - QUAD $0x020204203a0f4666 // pinsrb xmm8, byte [rdx + r8], 2 - QUAD $0x031a04203a0f4666 // pinsrb xmm8, byte [rdx + r11], 3 - QUAD $0x040a04203a0f4666 // pinsrb xmm8, byte [rdx + r9], 4 - QUAD $0x052204203a0f4666 // pinsrb xmm8, byte [rdx + r12], 5 - QUAD $0x063204203a0f4666 // pinsrb xmm8, byte [rdx + r14], 6 - QUAD $0x073a04203a0f4466 // pinsrb xmm8, byte [rdx + rdi], 7 - QUAD $0x082a04203a0f4666 // pinsrb xmm8, byte [rdx + r13], 8 - QUAD $0x091204203a0f4666 // pinsrb xmm8, byte [rdx + r10], 9 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - LONG $0x247c894c; BYTE $0x60 // mov qword [rsp + 96], r15 - QUAD $0x0a3a04203a0f4666 // pinsrb xmm8, byte [rdx + r15], 10 - QUAD $0x0b1a04203a0f4466 // pinsrb xmm8, byte [rdx + rbx], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0c3a04203a0f4666 // pinsrb xmm8, byte [rdx + r15], 12 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0d0204203a0f4466 // pinsrb xmm8, byte [rdx + rax], 13 - QUAD $0x0e3204203a0f4466 // pinsrb xmm8, byte [rdx + rsi], 14 - QUAD $0x0f0a04203a0f4466 // pinsrb xmm8, byte [rdx + rcx], 15 - QUAD $0x012024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 288] - LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0101027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 1], 1 - QUAD $0x01027c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rdx + r8 + 1], 2 - QUAD $0x011a7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r11 + 1], 3 - QUAD $0x010a7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdx + r9 + 1], 4 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x012a7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdx + r13 + 1], 5 - QUAD $0x01327c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdx + r14 + 1], 6 - QUAD $0x07013a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 1], 7 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0801027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 1], 8 - QUAD $0x01127c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdx + r10 + 1], 9 - QUAD $0x01227c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdx + r12 + 1], 10 - QUAD $0x0b011a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 1], 11 - QUAD $0x013a7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r15 + 1], 12 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0d01027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 1], 13 - QUAD $0x0e01327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 1], 14 - QUAD $0x0f010a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 1], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x01020274203a0f66 // pinsrb xmm6, byte [rdx + rax + 2], 1 - QUAD $0x020274203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdx + r8 + 2], 2 - QUAD $0x021a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r11 + 2], 3 - QUAD $0x020a74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdx + r9 + 2], 4 - QUAD $0x022a74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdx + r13 + 2], 5 - QUAD $0x023274203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r14 + 2], 6 - QUAD $0x07023a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 2], 7 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x08020274203a0f66 // pinsrb xmm6, byte [rdx + rax + 2], 8 - QUAD $0x021274203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r10 + 2], 9 - QUAD $0x022274203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r12 + 2], 10 - QUAD $0x0b021a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 2], 11 - QUAD $0x023a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r15 + 2], 12 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0d020274203a0f66 // pinsrb xmm6, byte [rdx + rax + 2], 13 - QUAD $0x0e023274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 2], 14 - QUAD $0x0f020a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 2], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x080264203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdx + rax + 8], 1 - QUAD $0x080264203a0f4666; BYTE $0x02 // pinsrb xmm12, byte [rdx + r8 + 8], 2 - QUAD $0x081a64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r11 + 8], 3 - QUAD $0x080a64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdx + r9 + 8], 4 - QUAD $0x082a64203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdx + r13 + 8], 5 - QUAD $0x083264203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdx + r14 + 8], 6 - QUAD $0x083a64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rdx + rdi + 8], 7 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x080264203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rdx + rax + 8], 8 - QUAD $0x081264203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdx + r10 + 8], 9 - QUAD $0x082264203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdx + r12 + 8], 10 - QUAD $0x081a64203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rdx + rbx + 8], 11 - QUAD $0x083a64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdx + r15 + 8], 12 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x080264203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdx + rax + 8], 13 - QUAD $0x083264203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rdx + rsi + 8], 14 - QUAD $0x080a64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdx + rcx + 8], 15 - LONG $0x640f4166; BYTE $0xd8 // pcmpgtb xmm3, xmm8 - QUAD $0x000110249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm3 - LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 - LONG $0x640f4166; BYTE $0xdc // pcmpgtb xmm3, xmm12 - QUAD $0x000130249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm3 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x100a74203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdx + rcx + 16], 1 - QUAD $0x100274203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdx + r8 + 16], 2 - QUAD $0x101a74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdx + r11 + 16], 3 - QUAD $0x100a74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rdx + r9 + 16], 4 - QUAD $0x102a74203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rdx + r13 + 16], 5 - QUAD $0x103274203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdx + r14 + 16], 6 - QUAD $0x103a74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rdx + rdi + 16], 7 - WORD $0x8949; BYTE $0xfe // mov r14, rdi - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x100a74203a0f4466; BYTE $0x08 // pinsrb xmm14, byte [rdx + rcx + 16], 8 - QUAD $0x101274203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rdx + r10 + 16], 9 - QUAD $0x102274203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rdx + r12 + 16], 10 - QUAD $0x101a74203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rdx + rbx + 16], 11 - QUAD $0x103a74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdx + r15 + 16], 12 - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - QUAD $0x100274203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdx + rax + 16], 13 - LONG $0x24748948; BYTE $0x18 // mov qword [rsp + 24], rsi - QUAD $0x103274203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rdx + rsi + 16], 14 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x103a74203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdx + rdi + 16], 15 - LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x01180264203a0f66 // pinsrb xmm4, byte [rdx + rax + 24], 1 - QUAD $0x180264203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdx + r8 + 24], 2 - QUAD $0x181a64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r11 + 24], 3 - QUAD $0x180a64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r9 + 24], 4 - QUAD $0x182a64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdx + r13 + 24], 5 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x180264203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdx + r8 + 24], 6 - QUAD $0x183264203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r14 + 24], 7 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x08180264203a0f66 // pinsrb xmm4, byte [rdx + rax + 24], 8 - QUAD $0x181264203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r10 + 24], 9 - QUAD $0x000000b02494894c // mov qword [rsp + 176], r10 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0a180264203a0f66 // pinsrb xmm4, byte [rdx + rax + 24], 10 - QUAD $0x0b181a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 24], 11 - QUAD $0x183a64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r15 + 24], 12 - QUAD $0x0d180a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 24], 13 - QUAD $0x0e183264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 24], 14 - LONG $0x640f4166; BYTE $0xde // pcmpgtb xmm3, xmm14 - QUAD $0x0000f0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm3 - QUAD $0x0f183a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 24], 15 - LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 - LONG $0xdc640f66 // pcmpgtb xmm3, xmm4 - QUAD $0x0000d0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm3 - LONG $0x6f0f4166; BYTE $0xe5 // movdqa xmm4, xmm13 - LONG $0xe7640f66 // pcmpgtb xmm4, xmm7 - LONG $0x6f0f4466; BYTE $0xe4 // movdqa xmm12, xmm4 - QUAD $0x0000a0856f0f4466; BYTE $0x00 // movdqa xmm8, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xdb0f4566; BYTE $0xe0 // pand xmm12, xmm8 - LONG $0xf80f4466; BYTE $0xe4 // psubb xmm12, xmm4 - LONG $0x6f0f4166; BYTE $0xe5 // movdqa xmm4, xmm13 - LONG $0x6f0f4566; BYTE $0xf5 // movdqa xmm14, xmm13 - LONG $0xe6640f66 // pcmpgtb xmm4, xmm6 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x0274b60f; BYTE $0x0d // movzx esi, byte [rdx + rax + 13] - LONG $0xfe6e0f66 // movd xmm7, esi - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x03327c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rsi + 3], 1 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x03027c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdx + rax + 3], 2 - LONG $0x245c894c; BYTE $0x28 // mov qword [rsp + 40], r11 - QUAD $0x031a7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r11 + 3], 3 - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - LONG $0x244c894c; BYTE $0x70 // mov qword [rsp + 112], r9 - QUAD $0x030a7c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdx + r9 + 3], 4 - QUAD $0x032a7c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rdx + r13 + 3], 5 - QUAD $0x03027c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdx + r8 + 3], 6 - LONG $0x2474894c; BYTE $0x50 // mov qword [rsp + 80], r14 - QUAD $0x03327c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r14 + 3], 7 - LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] - QUAD $0x03227c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdx + r12 + 3], 8 - QUAD $0x03127c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdx + r10 + 3], 9 - LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] - QUAD $0x030a7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdx + r9 + 3], 10 - LONG $0x245c8948; BYTE $0x68 // mov qword [rsp + 104], rbx - QUAD $0x031a7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rdx + rbx + 3], 11 - QUAD $0x033a7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdx + r15 + 3], 12 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x033a7c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdx + rdi + 3], 13 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x033a7c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdx + rdi + 3], 14 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x03127c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdx + r10 + 3], 15 - QUAD $0x0104326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 4], 1 - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - QUAD $0x0204026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 4], 2 - QUAD $0x041a6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r11 + 4], 3 - QUAD $0x04040a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 4], 4 - QUAD $0x042a6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rdx + r13 + 4], 5 - QUAD $0x04026c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r8 + 4], 6 - QUAD $0x04326c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r14 + 4], 7 - QUAD $0x04226c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r12 + 4], 8 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x09040a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 4], 9 - QUAD $0x040a6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r9 + 4], 10 - WORD $0x894d; BYTE $0xcb // mov r11, r9 - QUAD $0x0b041a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 4], 11 - QUAD $0x043a6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r15 + 4], 12 - LONG $0x244c8b4c; BYTE $0x08 // mov r9, qword [rsp + 8] - QUAD $0x040a6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdx + r9 + 4], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e04026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 4], 14 - QUAD $0x000110249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 272] - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - QUAD $0x000000b0b56f0f66 // movdqa xmm6, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xe6db0f66 // pand xmm4, xmm6 - LONG $0xe3eb0f66 // por xmm4, xmm3 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - LONG $0x3a74b60f; BYTE $0x0e // movzx esi, byte [rdx + rdi + 14] - LONG $0xf66e0f66 // movd xmm6, esi - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x0f041a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 4], 15 - LONG $0xeb0f4166; BYTE $0xe4 // por xmm4, xmm12 - LONG $0x6f0f4566; BYTE $0xe5 // movdqa xmm12, xmm13 - LONG $0x640f4566; BYTE $0xe7 // pcmpgtb xmm12, xmm15 - LONG $0x640f4466; BYTE $0xed // pcmpgtb xmm13, xmm5 - LONG $0x3a74b60f; BYTE $0x0f // movzx esi, byte [rdx + rdi + 15] - LONG $0xee6e0f66 // movd xmm5, esi - QUAD $0x051254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r10 + 5], 1 - LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] - QUAD $0x050254203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r8 + 5], 2 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x03053a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 5], 3 - LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] - QUAD $0x052a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r13 + 5], 4 - QUAD $0x000000a024b48b48 // mov rsi, qword [rsp + 160] - QUAD $0x05053254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 5], 5 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x053254203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r14 + 5], 6 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x051254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r10 + 5], 7 - QUAD $0x052254203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r12 + 5], 8 - QUAD $0x09050a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 5], 9 - QUAD $0x051a54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r11 + 5], 10 - LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] - QUAD $0x0b050a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 5], 11 - QUAD $0x053a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r15 + 5], 12 - QUAD $0x050a54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r9 + 5], 13 - WORD $0x894d; BYTE $0xcb // mov r11, r9 - QUAD $0x0e050254203a0f66 // pinsrb xmm2, byte [rdx + rax + 5], 14 - QUAD $0x0f051a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 5], 15 - QUAD $0x000000c09d6f0f66 // movdqa xmm3, oword 192[rbp] /* [rip + .LCPI8_12] */ - LONG $0xdb0f4466; BYTE $0xe3 // pand xmm12, xmm3 - QUAD $0x000000d09d6f0f66 // movdqa xmm3, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xdb0f4466; BYTE $0xeb // pand xmm13, xmm3 - LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - LONG $0x6f0f4566; BYTE $0xe6 // movdqa xmm12, xmm14 - LONG $0x640f4466; BYTE $0xe2 // pcmpgtb xmm12, xmm2 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x0274b60f; BYTE $0x11 // movzx esi, byte [rdx + rax + 17] - LONG $0xd66e0f66 // movd xmm2, esi - QUAD $0x000000e09d6f0f66 // movdqa xmm3, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xdb0f4466; BYTE $0xe3 // pand xmm12, xmm3 - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0x0274b60f; BYTE $0x12 // movzx esi, byte [rdx + rax + 18] - LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - QUAD $0x0000c0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 192] - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0106025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 6], 1 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - QUAD $0x06025c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdx + r8 + 6], 2 - QUAD $0x03063a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 6], 3 - WORD $0x894c; BYTE $0xe9 // mov rcx, r13 - QUAD $0x062a5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdx + r13 + 6], 4 - QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] - QUAD $0x062a5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdx + r13 + 6], 5 - QUAD $0x06325c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdx + r14 + 6], 6 - QUAD $0x06125c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdx + r10 + 6], 7 - QUAD $0x06225c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdx + r12 + 6], 8 - QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] - QUAD $0x0906325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 6], 9 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x06025c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r8 + 6], 10 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x0b061a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 6], 11 - LONG $0x247c894c; BYTE $0x48 // mov qword [rsp + 72], r15 - QUAD $0x063a5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r15 + 6], 12 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - QUAD $0x061a5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdx + r11 + 6], 13 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - QUAD $0x061a5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdx + r11 + 6], 14 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x06125c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r10 + 6], 15 - QUAD $0x0107024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 7], 1 - QUAD $0x070a4c203a0f4266; BYTE $0x02 // pinsrb xmm1, byte [rdx + r9 + 7], 2 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0307024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 7], 3 - QUAD $0x04070a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 7], 4 - QUAD $0x072a4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdx + r13 + 7], 5 - QUAD $0x07324c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r14 + 7], 6 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x07324c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r14 + 7], 7 - QUAD $0x07224c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r12 + 7], 8 - QUAD $0x0907324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 7], 9 - QUAD $0x07024c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdx + r8 + 7], 10 - QUAD $0x0b071a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 7], 11 - QUAD $0x073a4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r15 + 7], 12 - QUAD $0x0d073a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 7], 13 - QUAD $0x071a4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r11 + 7], 14 - QUAD $0x07124c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r10 + 7], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x01090244203a0f66 // pinsrb xmm0, byte [rdx + rax + 9], 1 - QUAD $0x090a44203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdx + r9 + 9], 2 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x03090244203a0f66 // pinsrb xmm0, byte [rdx + rax + 9], 3 - QUAD $0x04090a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 9], 4 - QUAD $0x092a44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdx + r13 + 9], 5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - QUAD $0x06090244203a0f66 // pinsrb xmm0, byte [rdx + rax + 9], 6 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x07090244203a0f66 // pinsrb xmm0, byte [rdx + rax + 9], 7 - QUAD $0x092244203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r12 + 9], 8 - QUAD $0x09093244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 9], 9 - QUAD $0x090244203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdx + r8 + 9], 10 - QUAD $0x0b091a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 9], 11 - QUAD $0x093a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r15 + 9], 12 - QUAD $0x0d093a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 9], 13 - QUAD $0x091a44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdx + r11 + 9], 14 - WORD $0x894d; BYTE $0xde // mov r14, r11 - QUAD $0x091244203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r10 + 9], 15 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a024c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rax + 10], 1 - QUAD $0x0a0a4c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rdx + r9 + 10], 2 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0a024c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rdx + rax + 10], 3 - QUAD $0x0a0a4c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdx + rcx + 10], 4 - QUAD $0x0a2a4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdx + r13 + 10], 5 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x0a1a4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdx + r11 + 10], 6 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x0a0a4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rdx + rcx + 10], 7 - QUAD $0x0a224c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r12 + 10], 8 - QUAD $0x0a324c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdx + rsi + 10], 9 - QUAD $0x0a024c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdx + r8 + 10], 10 - QUAD $0x0a1a4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdx + rbx + 10], 11 - QUAD $0x0a3a4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdx + r15 + 10], 12 - QUAD $0x0a3a4c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdx + rdi + 10], 13 - LONG $0xeb0f4466; BYTE $0xe4 // por xmm12, xmm4 - LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 - LONG $0x6f0f4166; BYTE $0xe6 // movdqa xmm4, xmm14 - LONG $0xe3640f66 // pcmpgtb xmm4, xmm3 - LONG $0x640f4466; BYTE $0xf1 // pcmpgtb xmm14, xmm1 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - LONG $0x3a74b60f; BYTE $0x13 // movzx esi, byte [rdx + rdi + 19] - LONG $0xce6e0f66 // movd xmm1, esi - QUAD $0x0a324c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r14 + 10], 14 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI8_15] */ - LONG $0xe3db0f66 // pand xmm4, xmm3 - LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 - LONG $0x5d6f0f66; BYTE $0x60 // movdqa xmm3, oword 96[rbp] /* [rip + .LCPI8_6] */ - LONG $0xdb0f4466; BYTE $0xf3 // pand xmm14, xmm3 - LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 - LONG $0x3a74b60f; BYTE $0x14 // movzx esi, byte [rdx + rdi + 20] - LONG $0xe66e0f66 // movd xmm4, esi - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x0a124c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdx + r10 + 10], 15 - LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 - QUAD $0x00c024b47f0f4466; WORD $0x0000 // movdqa oword [rsp + 192], xmm14 - LONG $0x6f0f4566; BYTE $0xf5 // movdqa xmm14, xmm13 - LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 - LONG $0xd8640f66 // pcmpgtb xmm3, xmm0 - LONG $0x6f0f4466; BYTE $0xe3 // movdqa xmm12, xmm3 - LONG $0xdb0f4566; BYTE $0xe0 // pand xmm12, xmm8 - LONG $0xf80f4466; BYTE $0xe3 // psubb xmm12, xmm3 - LONG $0x640f4566; BYTE $0xe9 // pcmpgtb xmm13, xmm9 - LONG $0x3a74b60f; BYTE $0x15 // movzx esi, byte [rdx + rdi + 21] - LONG $0xc66e0f66 // movd xmm0, esi - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x0b1254203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdx + r10 + 11], 1 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x0b0a54203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdx + r9 + 11], 2 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b3a54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdx + rdi + 11], 3 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x0b0254203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r8 + 11], 4 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x0b0a54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdx + r9 + 11], 5 - QUAD $0x0b1a54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r11 + 11], 6 - WORD $0x8948; BYTE $0xcb // mov rbx, rcx - QUAD $0x0b0a54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rdx + rcx + 11], 7 - QUAD $0x0b2254203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r12 + 11], 8 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0b0a54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rcx + 11], 9 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x0b3254203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdx + r14 + 11], 10 - LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] - QUAD $0x0b3a54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdx + r15 + 11], 11 - LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] - QUAD $0x0b3254203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdx + rsi + 11], 12 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0b3254203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdx + rsi + 11], 13 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x0b3254203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rdx + rsi + 11], 14 - QUAD $0x0b2a54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdx + r13 + 11], 15 - QUAD $0x0c125c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdx + r10 + 12], 1 - QUAD $0x0c025c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rax + 12], 2 - QUAD $0x0c3a5c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rdx + rdi + 12], 3 - QUAD $0x0c025c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdx + r8 + 12], 4 - QUAD $0x0c0a5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdx + r9 + 12], 5 - QUAD $0x0c1a5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r11 + 12], 6 - QUAD $0x0c1a5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rdx + rbx + 12], 7 - QUAD $0x0c225c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r12 + 12], 8 - QUAD $0x0c0a5c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdx + rcx + 12], 9 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - QUAD $0x0c325c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdx + r14 + 12], 10 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - QUAD $0x0c3a5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r15 + 12], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x0c3a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r15 + 12], 12 - LONG $0x247c8b48; BYTE $0x08 // mov rdi, qword [rsp + 8] - QUAD $0x0c3a5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdx + rdi + 12], 13 - QUAD $0x0c325c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rdx + rsi + 12], 14 - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - QUAD $0x000130249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 304] - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - QUAD $0x0000b0addb0f4466; BYTE $0x00 // pand xmm13, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xeb0f4466; BYTE $0xeb // por xmm13, xmm3 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x0274b60f; BYTE $0x16 // movzx esi, byte [rdx + rax + 22] - LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi - QUAD $0x0c2a5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdx + r13 + 12], 15 - LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - LONG $0x6f0f4566; BYTE $0xe6 // movdqa xmm12, xmm14 - LONG $0x640f4566; BYTE $0xe2 // pcmpgtb xmm12, xmm10 - LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 - LONG $0x640f4166; BYTE $0xdb // pcmpgtb xmm3, xmm11 - LONG $0x0274b60f; BYTE $0x17 // movzx esi, byte [rdx + rax + 23] - LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x010d027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 13], 1 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x020d0a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 13], 2 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x0d1a7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r11 + 13], 3 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x040d0a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 13], 4 - QUAD $0x0d0a7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdx + r9 + 13], 5 - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] - QUAD $0x0d327c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdx + r14 + 13], 6 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x070d327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 13], 7 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x080d327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 13], 8 - QUAD $0x0d227c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdx + r12 + 13], 9 - QUAD $0x0d027c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdx + r8 + 13], 10 - QUAD $0x0b0d1a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 13], 11 - QUAD $0x0d3a7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r15 + 13], 12 - QUAD $0x0d0d3a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 13], 13 - QUAD $0x0d127c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdx + r10 + 13], 14 - QUAD $0x0d2a7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdx + r13 + 13], 15 - QUAD $0x0000c0a5db0f4466; BYTE $0x00 // pand xmm12, oword 192[rbp] /* [rip + .LCPI8_12] */ - QUAD $0x000000d09ddb0f66 // pand xmm3, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xeb0f4166; BYTE $0xdc // por xmm3, xmm12 - LONG $0x6f0f4566; BYTE $0xd6 // movdqa xmm10, xmm14 - LONG $0x640f4466; BYTE $0xd7 // pcmpgtb xmm10, xmm7 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - LONG $0x74b60f42; WORD $0x1922 // movzx esi, byte [rdx + r12 + 25] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - QUAD $0x0000e095db0f4466; BYTE $0x00 // pand xmm10, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xeb0f4466; BYTE $0xd3 // por xmm10, xmm3 - LONG $0x74b60f42; WORD $0x1a22 // movzx esi, byte [rdx + r12 + 26] - LONG $0xfe6e0f66 // movd xmm7, esi - QUAD $0x010e0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 14], 1 - LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] - QUAD $0x020e3274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 14], 2 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x0e1a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r11 + 14], 3 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - QUAD $0x040e0a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 14], 4 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - QUAD $0x0e0a74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdx + r9 + 14], 5 - WORD $0x894d; BYTE $0xf3 // mov r11, r14 - QUAD $0x0e3274203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r14 + 14], 6 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x0e3274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r14 + 14], 7 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x080e0a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 14], 8 - QUAD $0x000000b0248c8b4c // mov r9, qword [rsp + 176] - QUAD $0x0e0a74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r9 + 14], 9 - QUAD $0x0e0274203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r8 + 14], 10 - QUAD $0x0b0e1a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 14], 11 - QUAD $0x0e3a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r15 + 14], 12 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0d0e0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 14], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e0e0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 14], 14 - QUAD $0x0e2a74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdx + r13 + 14], 15 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x0f2a6c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdx + r13 + 15], 1 - QUAD $0x020f326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 15], 2 - QUAD $0x0f126c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r10 + 15], 3 - QUAD $0x0f226c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdx + r12 + 15], 4 - QUAD $0x050f3a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 15], 5 - QUAD $0x0f1a6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r11 + 15], 6 - QUAD $0x0f326c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r14 + 15], 7 - QUAD $0x080f0a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 15], 8 - QUAD $0x0f0a6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r9 + 15], 9 - QUAD $0x0f026c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r8 + 15], 10 - QUAD $0x0b0f1a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 15], 11 - QUAD $0x0f3a6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r15 + 15], 12 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0d0f026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 15], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e0f026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 15], 14 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f0f026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 15], 15 - QUAD $0x112a54203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r13 + 17], 1 - QUAD $0x02113254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 17], 2 - QUAD $0x111254203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r10 + 17], 3 - QUAD $0x112254203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r12 + 17], 4 - QUAD $0x05113a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 17], 5 - QUAD $0x111a54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r11 + 17], 6 - QUAD $0x113254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r14 + 17], 7 - QUAD $0x08110a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 17], 8 - QUAD $0x110a54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r9 + 17], 9 - QUAD $0x110254203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r8 + 17], 10 - QUAD $0x0b111a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 17], 11 - QUAD $0x113a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r15 + 17], 12 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0d110254203a0f66 // pinsrb xmm2, byte [rdx + rax + 17], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e110254203a0f66 // pinsrb xmm2, byte [rdx + rax + 17], 14 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0f110254203a0f66 // pinsrb xmm2, byte [rdx + rax + 17], 15 - QUAD $0x122a7c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rdx + r13 + 18], 1 - QUAD $0x12327c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdx + rsi + 18], 2 - QUAD $0x12127c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r10 + 18], 3 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x12227c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdx + r12 + 18], 4 - QUAD $0x123a7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdx + rdi + 18], 5 - QUAD $0x121a7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdx + r11 + 18], 6 - QUAD $0x12327c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r14 + 18], 7 - QUAD $0x120a7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdx + rcx + 18], 8 - QUAD $0x120a7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdx + r9 + 18], 9 - QUAD $0x12027c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdx + r8 + 18], 10 - QUAD $0x121a7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rdx + rbx + 18], 11 - WORD $0x8948; BYTE $0xdf // mov rdi, rbx - QUAD $0x123a7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdx + r15 + 18], 12 - LONG $0x24548b4c; BYTE $0x08 // mov r10, qword [rsp + 8] - QUAD $0x12127c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdx + r10 + 18], 13 - LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 - LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 - LONG $0x640f4466; BYTE $0xee // pcmpgtb xmm13, xmm6 - LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 - LONG $0xdd640f66 // pcmpgtb xmm3, xmm5 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x0274b60f; BYTE $0x1b // movzx esi, byte [rdx + rax + 27] - LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x120a7c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdx + rcx + 18], 14 - QUAD $0x0000f0addb0f4466; BYTE $0x00 // pand xmm13, oword 240[rbp] /* [rip + .LCPI8_15] */ - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0x5ddb0f66; BYTE $0x60 // pand xmm3, oword 96[rbp] /* [rip + .LCPI8_6] */ - LONG $0xeb0f4166; BYTE $0xdd // por xmm3, xmm13 - LONG $0x0274b60f; BYTE $0x1c // movzx esi, byte [rdx + rax + 28] - LONG $0xf66e0f66 // movd xmm6, esi - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x120a7c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rdx + rcx + 18], 15 - LONG $0xeb0f4166; BYTE $0xda // por xmm3, xmm10 - QUAD $0x000110249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm3 - LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 - LONG $0xda640f66 // pcmpgtb xmm3, xmm2 - LONG $0x6f0f4466; BYTE $0xeb // movdqa xmm13, xmm3 - QUAD $0x000000a0956f0f66 // movdqa xmm2, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xdb0f4466; BYTE $0xea // pand xmm13, xmm2 - LONG $0xf80f4466; BYTE $0xeb // psubb xmm13, xmm3 - LONG $0x6f0f4566; BYTE $0xd6 // movdqa xmm10, xmm14 - LONG $0x640f4566; BYTE $0xd7 // pcmpgtb xmm10, xmm15 - LONG $0x0274b60f; BYTE $0x1d // movzx esi, byte [rdx + rax + 29] - LONG $0xde6e0f66 // movd xmm3, esi - QUAD $0x00f024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 240] - LONG $0xdb0f4466; BYTE $0xfa // pand xmm15, xmm2 - QUAD $0x000000b0956f0f66 // movdqa xmm2, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xdb0f4466; BYTE $0xd2 // pand xmm10, xmm2 - LONG $0xeb0f4566; BYTE $0xd7 // por xmm10, xmm15 - LONG $0x0274b60f; BYTE $0x1e // movzx esi, byte [rdx + rax + 30] - LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x0244b60f; BYTE $0x1f // movzx eax, byte [rdx + rax + 31] - LONG $0x38244489 // mov dword [rsp + 56], eax - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0113024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 19], 1 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x02130a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 19], 2 - QUAD $0x132a4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r13 + 19], 3 - QUAD $0x13224c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdx + r12 + 19], 4 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x13024c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdx + r8 + 19], 5 - QUAD $0x131a4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r11 + 19], 6 - WORD $0x894c; BYTE $0xdb // mov rbx, r11 - QUAD $0x13324c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r14 + 19], 7 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] - QUAD $0x0813324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 19], 8 - QUAD $0x130a4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdx + r9 + 19], 9 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x131a4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdx + r11 + 19], 10 - QUAD $0x0b133a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 19], 11 - LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] - QUAD $0x0c133a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 19], 12 - QUAD $0x13124c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdx + r10 + 19], 13 - WORD $0x894d; BYTE $0xd6 // mov r14, r10 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x0e133a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 19], 14 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x13124c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r10 + 19], 15 - QUAD $0x01140264203a0f66 // pinsrb xmm4, byte [rdx + rax + 20], 1 - QUAD $0x02140a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 20], 2 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x142a64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r13 + 20], 3 - QUAD $0x142264203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r12 + 20], 4 - QUAD $0x140264203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdx + r8 + 20], 5 - QUAD $0x06141a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 20], 6 - QUAD $0x143a64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r15 + 20], 7 - QUAD $0x08143264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 20], 8 - QUAD $0x140a64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r9 + 20], 9 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - QUAD $0x141a64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdx + r11 + 20], 10 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x0b141a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 20], 11 - LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] - QUAD $0x143a64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r15 + 20], 12 - QUAD $0x143264203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdx + r14 + 20], 13 - QUAD $0x0e143a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 20], 14 - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - QUAD $0x141264203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdx + r10 + 20], 15 - LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 - LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 - LONG $0x640f4466; BYTE $0xe9 // pcmpgtb xmm13, xmm1 - LONG $0x6f0f4566; BYTE $0xfe // movdqa xmm15, xmm14 - LONG $0x640f4466; BYTE $0xfc // pcmpgtb xmm15, xmm4 - LONG $0x4c6e0f66; WORD $0x3824 // movd xmm1, dword [rsp + 56] - QUAD $0x01150244203a0f66 // pinsrb xmm0, byte [rdx + rax + 21], 1 - QUAD $0x160244203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdx + rax + 22], 1 - QUAD $0x17024c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rax + 23], 1 - QUAD $0x19025c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdx + rax + 25], 1 - QUAD $0x011a027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 26], 1 - QUAD $0x011b026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 27], 1 - QUAD $0x011c0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 28], 1 - QUAD $0x011d025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 29], 1 - QUAD $0x011e0254203a0f66 // pinsrb xmm2, byte [rdx + rax + 30], 1 - QUAD $0x011f024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 31], 1 - QUAD $0x02150a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 21], 2 - QUAD $0x160a44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdx + rcx + 22], 2 - QUAD $0x170a4c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rcx + 23], 2 - QUAD $0x190a5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rcx + 25], 2 - QUAD $0x021a0a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 26], 2 - QUAD $0x021b0a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 27], 2 - QUAD $0x021c0a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 28], 2 - QUAD $0x021d0a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 29], 2 - QUAD $0x021e0a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 30], 2 - QUAD $0x021f0a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 31], 2 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x152a44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r13 + 21], 3 - QUAD $0x152244203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdx + r12 + 21], 4 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x05153a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 21], 5 - QUAD $0x00000090249c8b4c // mov r11, qword [rsp + 144] - QUAD $0x151a44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdx + r11 + 21], 6 - LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] - QUAD $0x153244203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r14 + 21], 7 - QUAD $0x08153244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 21], 8 - QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] - QUAD $0x151244203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdx + r10 + 21], 9 - QUAD $0x150244203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdx + r8 + 21], 10 - QUAD $0x0b151a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 21], 11 - QUAD $0x153a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r15 + 21], 12 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0d150a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 21], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e150244203a0f66 // pinsrb xmm0, byte [rdx + rax + 21], 14 - QUAD $0x150a44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r9 + 21], 15 - QUAD $0x000000c0a56f0f66 // movdqa xmm4, oword 192[rbp] /* [rip + .LCPI8_12] */ - LONG $0xdb0f4466; BYTE $0xec // pand xmm13, xmm4 - QUAD $0x000000d0a56f0f66 // movdqa xmm4, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 - LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 - LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 - LONG $0x640f4466; BYTE $0xe8 // pcmpgtb xmm13, xmm0 - QUAD $0x000000e0856f0f66 // movdqa xmm0, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xdb0f4466; BYTE $0xe8 // pand xmm13, xmm0 - LONG $0xeb0f4566; BYTE $0xef // por xmm13, xmm15 - QUAD $0x162a44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r13 + 22], 3 - QUAD $0x162244203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdx + r12 + 22], 4 - QUAD $0x163a44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdx + rdi + 22], 5 - QUAD $0x161a44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdx + r11 + 22], 6 - QUAD $0x163244203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdx + r14 + 22], 7 - QUAD $0x163244203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rdx + rsi + 22], 8 - QUAD $0x161244203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdx + r10 + 22], 9 - QUAD $0x160244203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdx + r8 + 22], 10 - QUAD $0x161a44203a0f4466; BYTE $0x0b // pinsrb xmm8, byte [rdx + rbx + 22], 11 - QUAD $0x163a44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdx + r15 + 22], 12 - QUAD $0x160a44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdx + rcx + 22], 13 - QUAD $0x160244203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdx + rax + 22], 14 - QUAD $0x160a44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdx + r9 + 22], 15 - QUAD $0x172a4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdx + r13 + 23], 3 - QUAD $0x17224c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdx + r12 + 23], 4 - QUAD $0x173a4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdx + rdi + 23], 5 - QUAD $0x171a4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdx + r11 + 23], 6 - QUAD $0x17324c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdx + r14 + 23], 7 - QUAD $0x17324c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rdx + rsi + 23], 8 - QUAD $0x17124c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdx + r10 + 23], 9 - QUAD $0x17024c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdx + r8 + 23], 10 - QUAD $0x171a4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdx + rbx + 23], 11 - QUAD $0x173a4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdx + r15 + 23], 12 - QUAD $0x170a4c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdx + rcx + 23], 13 - QUAD $0x17024c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdx + rax + 23], 14 - QUAD $0x170a4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdx + r9 + 23], 15 - QUAD $0x192a5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r13 + 25], 3 - QUAD $0x19225c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdx + r12 + 25], 4 - QUAD $0x193a5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdx + rdi + 25], 5 - QUAD $0x191a5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r11 + 25], 6 - QUAD $0x19325c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdx + r14 + 25], 7 - QUAD $0x19325c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rdx + rsi + 25], 8 - QUAD $0x19125c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdx + r10 + 25], 9 - QUAD $0x19025c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdx + r8 + 25], 10 - QUAD $0x191a5c203a0f4466; BYTE $0x0b // pinsrb xmm11, byte [rdx + rbx + 25], 11 - QUAD $0x193a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r15 + 25], 12 - QUAD $0x190a5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdx + rcx + 25], 13 - QUAD $0x19025c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rdx + rax + 25], 14 - QUAD $0x190a5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdx + r9 + 25], 15 - QUAD $0x1a2a7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r13 + 26], 3 - QUAD $0x1a227c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdx + r12 + 26], 4 - QUAD $0x051a3a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 26], 5 - QUAD $0x1a1a7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdx + r11 + 26], 6 - QUAD $0x1a327c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdx + r14 + 26], 7 - QUAD $0x081a327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 26], 8 - QUAD $0x1a127c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdx + r10 + 26], 9 - QUAD $0x1a027c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdx + r8 + 26], 10 - QUAD $0x0b1a1a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 26], 11 - QUAD $0x1a3a7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r15 + 26], 12 - QUAD $0x0d1a0a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 26], 13 - QUAD $0x0e1a027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 26], 14 - LONG $0xeb0f4566; BYTE $0xea // por xmm13, xmm10 - LONG $0x6f0f4566; BYTE $0xe6 // movdqa xmm12, xmm14 - LONG $0x6f0f4166; BYTE $0xe6 // movdqa xmm4, xmm14 - LONG $0x640f4166; BYTE $0xe0 // pcmpgtb xmm4, xmm8 - LONG $0x6f0f4166; BYTE $0xc6 // movdqa xmm0, xmm14 - LONG $0x640f4166; BYTE $0xc1 // pcmpgtb xmm0, xmm9 - QUAD $0x0000f0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 240[rbp] /* [rip + .LCPI8_15] */ - LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0x6f0f4466; WORD $0x607d // movdqa xmm15, oword 96[rbp] /* [rip + .LCPI8_6] */ - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xc4eb0f66 // por xmm0, xmm4 - QUAD $0x1a0a7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdx + r9 + 26], 15 - LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xe4 // movdqa xmm4, xmm12 - LONG $0x640f4166; BYTE $0xe3 // pcmpgtb xmm4, xmm11 - LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 - QUAD $0x0000a09d6f0f4466; BYTE $0x00 // movdqa xmm11, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xdb0f4566; BYTE $0xc3 // pand xmm8, xmm11 - LONG $0xf80f4466; BYTE $0xc4 // psubb xmm8, xmm4 - LONG $0x6f0f4166; BYTE $0xe4 // movdqa xmm4, xmm12 - LONG $0xe7640f66 // pcmpgtb xmm4, xmm7 - QUAD $0x1b2a6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r13 + 27], 3 - QUAD $0x1b226c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdx + r12 + 27], 4 - QUAD $0x051b3a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 27], 5 - QUAD $0x1b1a6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r11 + 27], 6 - QUAD $0x1b326c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r14 + 27], 7 - QUAD $0x081b326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 27], 8 - QUAD $0x1b126c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r10 + 27], 9 - QUAD $0x1b026c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r8 + 27], 10 - QUAD $0x0b1b1a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 27], 11 - QUAD $0x1b3a6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r15 + 27], 12 - QUAD $0x0d1b0a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 27], 13 - QUAD $0x0e1b026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 27], 14 - QUAD $0x1b0a6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdx + r9 + 27], 15 - QUAD $0x1c2a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r13 + 28], 3 - QUAD $0x1c2274203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdx + r12 + 28], 4 - QUAD $0x051c3a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 28], 5 - QUAD $0x1c1a74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r11 + 28], 6 - QUAD $0x1c3274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r14 + 28], 7 - QUAD $0x081c3274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 28], 8 - QUAD $0x1c1274203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r10 + 28], 9 - QUAD $0x1c0274203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r8 + 28], 10 - QUAD $0x0b1c1a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 28], 11 - QUAD $0x1c3a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r15 + 28], 12 - QUAD $0x0d1c0a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 28], 13 - QUAD $0x0000d024bc6f0f66; BYTE $0x00 // movdqa xmm7, oword [rsp + 208] - LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 - QUAD $0x0e1c0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 28], 14 - QUAD $0x000000b0a5db0f66 // pand xmm4, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xe7eb0f66 // por xmm4, xmm7 - QUAD $0x1c0a74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdx + r9 + 28], 15 - LONG $0xeb0f4166; BYTE $0xe0 // por xmm4, xmm8 - LONG $0x6f0f4166; BYTE $0xfc // movdqa xmm7, xmm12 - LONG $0xfd640f66 // pcmpgtb xmm7, xmm5 - LONG $0x6f0f4166; BYTE $0xec // movdqa xmm5, xmm12 - LONG $0xee640f66 // pcmpgtb xmm5, xmm6 - QUAD $0x1d2a5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r13 + 29], 3 - QUAD $0x1d225c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdx + r12 + 29], 4 - QUAD $0x051d3a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 29], 5 - QUAD $0x1d1a5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdx + r11 + 29], 6 - QUAD $0x1d325c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdx + r14 + 29], 7 - QUAD $0x081d325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 29], 8 - QUAD $0x1d125c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdx + r10 + 29], 9 - QUAD $0x1d025c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r8 + 29], 10 - QUAD $0x0b1d1a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 29], 11 - QUAD $0x1d3a5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r15 + 29], 12 - QUAD $0x0d1d0a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 29], 13 - QUAD $0x0e1d025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 29], 14 - QUAD $0x1d0a5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r9 + 29], 15 - QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI8_12] */ - QUAD $0x000000d0addb0f66 // pand xmm5, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xefeb0f66 // por xmm5, xmm7 - LONG $0x6f0f4166; BYTE $0xf4 // movdqa xmm6, xmm12 - LONG $0xf3640f66 // pcmpgtb xmm6, xmm3 - QUAD $0x000000e0b5db0f66 // pand xmm6, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xf5eb0f66 // por xmm6, xmm5 - QUAD $0x1e2a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r13 + 30], 3 - QUAD $0x1f2a4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r13 + 31], 3 - QUAD $0x1e2254203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r12 + 30], 4 - QUAD $0x1f224c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdx + r12 + 31], 4 - QUAD $0x051e3a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 30], 5 - QUAD $0x051f3a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 31], 5 - QUAD $0x1e1a54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r11 + 30], 6 - QUAD $0x1f1a4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r11 + 31], 6 - QUAD $0x1e3254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r14 + 30], 7 - QUAD $0x1f324c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r14 + 31], 7 - QUAD $0x081e3254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 30], 8 - QUAD $0x081f324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 31], 8 - QUAD $0x1e1254203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r10 + 30], 9 - QUAD $0x1f124c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdx + r10 + 31], 9 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x1e0254203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r8 + 30], 10 - QUAD $0x1f024c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdx + r8 + 31], 10 - QUAD $0x0b1e1a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 30], 11 - QUAD $0x0b1f1a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 31], 11 - QUAD $0x1e3a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r15 + 30], 12 - QUAD $0x1f3a4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r15 + 31], 12 - QUAD $0x0d1e0a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 30], 13 - QUAD $0x0d1f0a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 31], 13 - QUAD $0x0e1e0254203a0f66 // pinsrb xmm2, byte [rdx + rax + 30], 14 - QUAD $0x0e1f024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 31], 14 - QUAD $0x1e0a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r9 + 30], 15 - QUAD $0x1f0a4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r9 + 31], 15 - LONG $0xf4eb0f66 // por xmm6, xmm4 - LONG $0x6f0f4166; BYTE $0xdc // movdqa xmm3, xmm12 - LONG $0xda640f66 // pcmpgtb xmm3, xmm2 - LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0x640f4466; BYTE $0xe1 // pcmpgtb xmm12, xmm1 - LONG $0x710f4166; WORD $0x07f4 // psllw xmm12, 7 - LONG $0xdb0f4566; BYTE $0xe7 // pand xmm12, xmm15 - LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 - LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0x600f4166; BYTE $0xcc // punpcklbw xmm1, xmm12 - QUAD $0x0000c024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 192] - LONG $0xdd6f0f66 // movdqa xmm3, xmm5 - QUAD $0x00011024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 272] - LONG $0xde600f66 // punpcklbw xmm3, xmm6 - LONG $0xe36f0f66 // movdqa xmm4, xmm3 - LONG $0xe1610f66 // punpcklwd xmm4, xmm1 - LONG $0xd9690f66 // punpckhwd xmm3, xmm1 - LONG $0x680f4166; BYTE $0xc4 // punpckhbw xmm0, xmm12 - LONG $0xee680f66 // punpckhbw xmm5, xmm6 - LONG $0xcd6f0f66 // movdqa xmm1, xmm5 - LONG $0xc8610f66 // punpcklwd xmm1, xmm0 - LONG $0xe8690f66 // punpckhwd xmm5, xmm0 - LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] - LONG $0x7f0f41f3; WORD $0x8e6c; BYTE $0x30 // movdqu oword [r14 + 4*rcx + 48], xmm5 - LONG $0x7f0f41f3; WORD $0x8e4c; BYTE $0x20 // movdqu oword [r14 + 4*rcx + 32], xmm1 - LONG $0x7f0f41f3; WORD $0x8e5c; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm3 - LONG $0x7f0f41f3; WORD $0x8e24 // movdqu oword [r14 + 4*rcx], xmm4 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB8_192 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x000000e824bc3b4c // cmp r15, qword [rsp + 232] - LONG $0x241c8a44 // mov r11b, byte [rsp] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - JNE LBB8_42 - JMP LBB8_128 + WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0xd830 // xor al, bl + LONG $0x36048841 // mov byte [r14 + rsi], al + WORD $0x3949; BYTE $0xfa // cmp r10, rdi + JNE LBB8_190 + +LBB8_191: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_215 + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0x970f; BYTE $0xd0 // seta al + JMP LBB8_203 + +LBB8_193: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d LBB8_194: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000010824848948 // mov qword [rsp + 264], rax - QUAD $0x000000e824bc894c // mov qword [rsp + 232], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - LONG $0xc3b60f41 // movzx eax, r11b - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0xc0ef0f66 // pxor xmm0, xmm0 - LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000120248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm1 - WORD $0xc031 // xor eax, eax - QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 + LONG $0x2a394466 // cmp word [rdx], r13w + WORD $0xff19 // sbb edi, edi + WORD $0x894c; BYTE $0xde // mov rsi, r11 + LONG $0x03eec148 // shr rsi, 3 + LONG $0x14b60f45; BYTE $0x36 // movzx r10d, byte [r14 + rsi] + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x3044; BYTE $0xd7 // xor dil, r10b + WORD $0x2040; BYTE $0xf8 // and al, dil + WORD $0x3044; BYTE $0xd0 // xor al, r10b + LONG $0x36048841 // mov byte [r14 + rsi], al + LONG $0x02c38349 // add r11, 2 + LONG $0x6a394466; BYTE $0x02 // cmp word [rdx + 2], r13w + LONG $0x04528d48 // lea rdx, [rdx + 4] + WORD $0xff19 // sbb edi, edi + WORD $0x3040; BYTE $0xc7 // xor dil, al + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x2040; BYTE $0xfb // and bl, dil + WORD $0xc330 // xor bl, al + LONG $0x361c8841 // mov byte [r14 + rsi], bl + WORD $0x394d; BYTE $0xd9 // cmp r9, r11 + JNE LBB8_194 LBB8_195: - WORD $0x8949; BYTE $0xc1 // mov r9, rax - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - LONG $0x05e1c148 // shl rcx, 5 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0x8948; BYTE $0xcb // mov rbx, rcx - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - WORD $0x8949; BYTE $0xcb // mov r11, rcx - WORD $0x8949; BYTE $0xca // mov r10, rcx - WORD $0x8949; BYTE $0xc8 // mov r8, rcx - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - LONG $0x244c8948; BYTE $0x40 // mov qword [rsp + 64], rcx - WORD $0x8949; BYTE $0xcc // mov r12, rcx - WORD $0x8949; BYTE $0xcf // mov r15, rcx - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - WORD $0x8948; BYTE $0xce // mov rsi, rcx - LONG $0x0a0cb60f // movzx ecx, byte [rdx + rcx] - LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x324cb60f; BYTE $0x01 // movzx ecx, byte [rdx + rsi + 1] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x324cb60f; BYTE $0x02 // movzx ecx, byte [rdx + rsi + 2] - LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x324cb60f; BYTE $0x03 // movzx ecx, byte [rdx + rsi + 3] - LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x324cb60f; BYTE $0x04 // movzx ecx, byte [rdx + rsi + 4] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x324cb60f; BYTE $0x05 // movzx ecx, byte [rdx + rsi + 5] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x324cb60f; BYTE $0x06 // movzx ecx, byte [rdx + rsi + 6] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x324cb60f; BYTE $0x07 // movzx ecx, byte [rdx + rsi + 7] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 - LONG $0x324cb60f; BYTE $0x08 // movzx ecx, byte [rdx + rsi + 8] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 - LONG $0x324cb60f; BYTE $0x09 // movzx ecx, byte [rdx + rsi + 9] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x324cb60f; BYTE $0x0a // movzx ecx, byte [rdx + rsi + 10] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x324cb60f; BYTE $0x0b // movzx ecx, byte [rdx + rsi + 11] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00009024847f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm0 - LONG $0x324cb60f; BYTE $0x0c // movzx ecx, byte [rdx + rsi + 12] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00013024847f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm0 - LONG $0x324cb60f; BYTE $0x0d // movzx ecx, byte [rdx + rsi + 13] - LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x324cb60f; BYTE $0x0e // movzx ecx, byte [rdx + rsi + 14] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x24748948; BYTE $0x38 // mov qword [rsp + 56], rsi - WORD $0x8949; BYTE $0xf5 // mov r13, rsi - LONG $0x20cd8349 // or r13, 32 - LONG $0x246c894c; BYTE $0x08 // mov qword [rsp + 8], r13 - LONG $0x40ce8349 // or r14, 64 - LONG $0x2474894c; BYTE $0x20 // mov qword [rsp + 32], r14 - LONG $0x60cb8348 // or rbx, 96 - LONG $0x245c8948; BYTE $0x58 // mov qword [rsp + 88], rbx - LONG $0x00800d48; WORD $0x0000 // or rax, 128 - WORD $0x894c; BYTE $0xdb // mov rbx, r11 - LONG $0xa0cb8148; WORD $0x0000; BYTE $0x00 // or rbx, 160 - WORD $0x894d; BYTE $0xd3 // mov r11, r10 - LONG $0xc0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 192 - LONG $0x245c894c; BYTE $0x60 // mov qword [rsp + 96], r11 - LONG $0xe0c88149; WORD $0x0000; BYTE $0x00 // or r8, 224 - LONG $0x00c98149; WORD $0x0001; BYTE $0x00 // or r9, 256 - LONG $0x244c894c; BYTE $0x50 // mov qword [rsp + 80], r9 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - LONG $0x20c98148; WORD $0x0001; BYTE $0x00 // or rcx, 288 - LONG $0x40cc8149; WORD $0x0001; BYTE $0x00 // or r12, 320 - LONG $0x60cf8149; WORD $0x0001; BYTE $0x00 // or r15, 352 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - WORD $0x8949; BYTE $0xfa // mov r10, rdi - LONG $0x80ca8149; WORD $0x0001; BYTE $0x00 // or r10, 384 - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0xa0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 416 - LONG $0x247c8948; BYTE $0x68 // mov qword [rsp + 104], rdi - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0xc0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 448 - LONG $0x247c8948; BYTE $0x10 // mov qword [rsp + 16], rdi - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0xe0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 480 - LONG $0x247c8948; BYTE $0x18 // mov qword [rsp + 24], rdi - QUAD $0x012a6c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdx + r13 + 1], 1 - QUAD $0x01326c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rdx + r14 + 1], 2 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x012a6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r13 + 1], 3 - QUAD $0x0401026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 1], 4 - WORD $0x8949; BYTE $0xc6 // mov r14, rax - QUAD $0x05011a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 1], 5 - QUAD $0x011a6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r11 + 1], 6 - QUAD $0x01026c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r8 + 1], 7 - QUAD $0x010a6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r9 + 1], 8 - QUAD $0x09010a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 1], 9 - QUAD $0x01226c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r12 + 1], 10 - QUAD $0x013a6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdx + r15 + 1], 11 - QUAD $0x01126c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r10 + 1], 12 - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x011a6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdx + r11 + 1], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e01026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 1], 14 - QUAD $0x0f013a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 1], 15 - QUAD $0x012024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 288] - LONG $0xda0f4166; BYTE $0xea // pminub xmm5, xmm10 - LONG $0x740f4166; BYTE $0xea // pcmpeqb xmm5, xmm10 - LONG $0xf56f0f66 // movdqa xmm6, xmm5 - QUAD $0x000000a08d6f0f66 // movdqa xmm1, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xf1df0f66 // pandn xmm6, xmm1 - LONG $0xf5fc0f66 // paddb xmm6, xmm5 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - LONG $0x3274b60f; BYTE $0x0f // movzx esi, byte [rdx + rsi + 15] - LONG $0xc66e0f66 // movd xmm0, esi - QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x01020c203a0f4466 // pinsrb xmm9, byte [rdx + rax], 1 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x02120c203a0f4666 // pinsrb xmm9, byte [rdx + r10], 2 - QUAD $0x032a0c203a0f4666 // pinsrb xmm9, byte [rdx + r13], 3 - WORD $0x894c; BYTE $0xf6 // mov rsi, r14 - QUAD $0x04320c203a0f4666 // pinsrb xmm9, byte [rdx + r14], 4 - WORD $0x8949; BYTE $0xde // mov r14, rbx - QUAD $0x051a0c203a0f4466 // pinsrb xmm9, byte [rdx + rbx], 5 - LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] - QUAD $0x061a0c203a0f4466 // pinsrb xmm9, byte [rdx + rbx], 6 - QUAD $0x07020c203a0f4666 // pinsrb xmm9, byte [rdx + r8], 7 - LONG $0x247c8b4c; BYTE $0x50 // mov r15, qword [rsp + 80] - QUAD $0x083a0c203a0f4666 // pinsrb xmm9, byte [rdx + r15], 8 - LONG $0x244c8948; BYTE $0x40 // mov qword [rsp + 64], rcx - QUAD $0x090a0c203a0f4466 // pinsrb xmm9, byte [rdx + rcx], 9 - LONG $0x2464894c; BYTE $0x48 // mov qword [rsp + 72], r12 - QUAD $0x0a220c203a0f4666 // pinsrb xmm9, byte [rdx + r12], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b3a0c203a0f4466 // pinsrb xmm9, byte [rdx + rdi], 11 - QUAD $0x0c0a0c203a0f4666 // pinsrb xmm9, byte [rdx + r9], 12 - QUAD $0x0d1a0c203a0f4666 // pinsrb xmm9, byte [rdx + r11], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e020c203a0f4466 // pinsrb xmm9, byte [rdx + rax], 14 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x0f2a0c203a0f4666 // pinsrb xmm9, byte [rdx + r13], 15 - LONG $0xda0f4566; BYTE $0xca // pminub xmm9, xmm10 - LONG $0x740f4566; BYTE $0xca // pcmpeqb xmm9, xmm10 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0102027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 2], 1 - QUAD $0x02127c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rdx + r10 + 2], 2 - LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] - QUAD $0x022a7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r13 + 2], 3 - QUAD $0x0402327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 2], 4 - QUAD $0x02327c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdx + r14 + 2], 5 - QUAD $0x06021a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 2], 6 - QUAD $0x02027c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdx + r8 + 2], 7 - QUAD $0x023a7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdx + r15 + 2], 8 - QUAD $0x09020a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 2], 9 - QUAD $0x02227c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdx + r12 + 2], 10 - QUAD $0x0b023a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 2], 11 - QUAD $0x020a7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r9 + 2], 12 - QUAD $0x021a7c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rdx + r11 + 2], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e02027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 2], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0f02027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 2], 15 - LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x01030244203a0f66 // pinsrb xmm0, byte [rdx + rax + 3], 1 - QUAD $0x031244203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdx + r10 + 3], 2 - QUAD $0x032a44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r13 + 3], 3 - QUAD $0x04033244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 3], 4 - QUAD $0x033244203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdx + r14 + 3], 5 - QUAD $0x06031a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 3], 6 - QUAD $0x030244203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r8 + 3], 7 - QUAD $0x033a44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r15 + 3], 8 - QUAD $0x09030a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 3], 9 - QUAD $0x032244203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdx + r12 + 3], 10 - QUAD $0x0b033a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 3], 11 - QUAD $0x030a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r9 + 3], 12 - QUAD $0x031a44203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdx + r11 + 3], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e030244203a0f66 // pinsrb xmm0, byte [rdx + rax + 3], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0f030244203a0f66 // pinsrb xmm0, byte [rdx + rax + 3], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0104025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 4], 1 - QUAD $0x04125c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdx + r10 + 4], 2 - QUAD $0x042a5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r13 + 4], 3 - QUAD $0x0404325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 4], 4 - QUAD $0x04325c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdx + r14 + 4], 5 - QUAD $0x06041a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 4], 6 - QUAD $0x04025c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdx + r8 + 4], 7 - QUAD $0x043a5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdx + r15 + 4], 8 - QUAD $0x09040a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 4], 9 - QUAD $0x04225c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r12 + 4], 10 - QUAD $0x0b043a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 4], 11 - QUAD $0x040a5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r9 + 4], 12 - QUAD $0x041a5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdx + r11 + 4], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e04025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 4], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0f04025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 4], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x01050254203a0f66 // pinsrb xmm2, byte [rdx + rax + 5], 1 - QUAD $0x051254203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r10 + 5], 2 - QUAD $0x052a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r13 + 5], 3 - QUAD $0x04053254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 5], 4 - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - QUAD $0x000000c024b48948 // mov qword [rsp + 192], rsi - QUAD $0x053254203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdx + r14 + 5], 5 - QUAD $0x06051a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 5], 6 - QUAD $0x050254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r8 + 5], 7 - QUAD $0x053a54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r15 + 5], 8 - QUAD $0x09050a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 5], 9 - QUAD $0x052254203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r12 + 5], 10 - QUAD $0x0b053a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 5], 11 - QUAD $0x050a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r9 + 5], 12 - QUAD $0x051a54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r11 + 5], 13 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - LONG $0xdf0f4466; BYTE $0xc9 // pandn xmm9, xmm1 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e050254203a0f66 // pinsrb xmm2, byte [rdx + rax + 5], 14 - LONG $0xda0f4166; BYTE $0xfa // pminub xmm7, xmm10 - LONG $0x740f4166; BYTE $0xfa // pcmpeqb xmm7, xmm10 - QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xf9df0f66 // pandn xmm7, xmm1 - LONG $0xeb0f4166; BYTE $0xf9 // por xmm7, xmm9 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - LONG $0x74b60f42; WORD $0x1022 // movzx esi, byte [rdx + r12 + 16] - LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x0f050a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 5], 15 - LONG $0xda0f4166; BYTE $0xc2 // pminub xmm0, xmm10 - LONG $0x740f4166; BYTE $0xc2 // pcmpeqb xmm0, xmm10 - QUAD $0x000000c08d6f0f66 // movdqa xmm1, oword 192[rbp] /* [rip + .LCPI8_12] */ - LONG $0xc1df0f66 // pandn xmm0, xmm1 - LONG $0xc7eb0f66 // por xmm0, xmm7 - LONG $0x74b60f42; WORD $0x1122 // movzx esi, byte [rdx + r12 + 17] - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0xff760f66 // pcmpeqd xmm7, xmm7 - LONG $0xf7f80f66 // psubb xmm6, xmm7 - LONG $0x760f4566; BYTE $0xc9 // pcmpeqd xmm9, xmm9 - LONG $0xc6eb0f66 // por xmm0, xmm6 - LONG $0x74b60f42; WORD $0x1222 // movzx esi, byte [rdx + r12 + 18] - LONG $0xfe6e0f66 // movd xmm7, esi - LONG $0xda0f4166; BYTE $0xda // pminub xmm3, xmm10 - LONG $0x740f4166; BYTE $0xda // pcmpeqb xmm3, xmm10 - QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xdedf0f66 // pandn xmm3, xmm6 - LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 - LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 - QUAD $0x000000e0b56f0f66 // movdqa xmm6, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xd6df0f66 // pandn xmm2, xmm6 - LONG $0xd3eb0f66 // por xmm2, xmm3 - LONG $0x74b60f42; WORD $0x1322 // movzx esi, byte [rdx + r12 + 19] - LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x060a44203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdx + rcx + 6], 1 - LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] - QUAD $0x061a44203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rdx + r11 + 6], 2 - QUAD $0x062a44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r13 + 6], 3 - QUAD $0x061244203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdx + r10 + 6], 4 - LONG $0x2474894c; BYTE $0x78 // mov qword [rsp + 120], r14 - QUAD $0x063244203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rdx + r14 + 6], 5 - QUAD $0x061a44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rdx + rbx + 6], 6 - QUAD $0x000000d02484894c // mov qword [rsp + 208], r8 - QUAD $0x060244203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdx + r8 + 6], 7 - QUAD $0x063a44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdx + r15 + 6], 8 - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - QUAD $0x063a44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdx + r15 + 6], 9 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x060244203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdx + rax + 6], 10 - LONG $0x24548b4c; BYTE $0x28 // mov r10, qword [rsp + 40] - QUAD $0x061244203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r10 + 6], 11 - QUAD $0x060a44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdx + r9 + 6], 12 - QUAD $0x063a44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdx + rdi + 6], 13 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - QUAD $0x061a44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdx + rbx + 6], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x060244203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rdx + rax + 6], 15 - LONG $0xda0f4566; BYTE $0xc2 // pminub xmm8, xmm10 - LONG $0x740f4566; BYTE $0xc2 // pcmpeqb xmm8, xmm10 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI8_15] */ - LONG $0xdf0f4466; BYTE $0xc3 // pandn xmm8, xmm3 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x74b60f42; WORD $0x1422 // movzx esi, byte [rdx + r12 + 20] - LONG $0xe66e0f66 // movd xmm4, esi - QUAD $0x0000a024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 160] - QUAD $0x01070a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 7], 1 - QUAD $0x071a74203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdx + r11 + 7], 2 - QUAD $0x072a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r13 + 7], 3 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x04070a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 7], 4 - QUAD $0x073274203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdx + r14 + 7], 5 - LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] - QUAD $0x073274203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r14 + 7], 6 - QUAD $0x070274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r8 + 7], 7 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - QUAD $0x072274203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r12 + 7], 8 - QUAD $0x073a74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r15 + 7], 9 - LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] - QUAD $0x070274203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r8 + 7], 10 - QUAD $0x071274203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r10 + 7], 11 - QUAD $0x070a74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r9 + 7], 12 - QUAD $0x0d073a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 7], 13 - WORD $0x8949; BYTE $0xff // mov r15, rdi - QUAD $0x0e071a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 7], 14 - QUAD $0x0f070274203a0f66 // pinsrb xmm6, byte [rdx + rax + 7], 15 - LONG $0xda0f4166; BYTE $0xf2 // pminub xmm6, xmm10 - LONG $0x740f4166; BYTE $0xf2 // pcmpeqb xmm6, xmm10 - LONG $0xef0f4166; BYTE $0xf1 // pxor xmm6, xmm9 - LONG $0xdb760f66 // pcmpeqd xmm3, xmm3 - LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 - LONG $0x556f0f66; BYTE $0x60 // movdqa xmm2, oword 96[rbp] /* [rip + .LCPI8_6] */ - LONG $0xf2db0f66 // pand xmm6, xmm2 - LONG $0xeb0f4166; BYTE $0xf0 // por xmm6, xmm8 - LONG $0x6f0f4466; BYTE $0xc6 // movdqa xmm8, xmm6 - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - LONG $0x0274b60f; BYTE $0x15 // movzx esi, byte [rdx + rax + 21] - LONG $0xf66e0f66 // movd xmm6, esi - QUAD $0x00011024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 272] - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x01080a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 8], 1 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - QUAD $0x081a54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r11 + 8], 2 - WORD $0x894c; BYTE $0xef // mov rdi, r13 - QUAD $0x082a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r13 + 8], 3 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x081254203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r10 + 8], 4 - LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] - QUAD $0x081a54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdx + r11 + 8], 5 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - QUAD $0x083254203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r14 + 8], 6 - QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] - QUAD $0x07083254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 8], 7 - WORD $0x894d; BYTE $0xe6 // mov r14, r12 - QUAD $0x082254203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r12 + 8], 8 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x09081a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 8], 9 - WORD $0x894d; BYTE $0xc4 // mov r12, r8 - QUAD $0x080254203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r8 + 8], 10 - LONG $0x245c8b48; BYTE $0x28 // mov rbx, qword [rsp + 40] - QUAD $0x0b081a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 8], 11 - LONG $0x244c894c; BYTE $0x70 // mov qword [rsp + 112], r9 - QUAD $0x080a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r9 + 8], 12 - WORD $0x894d; BYTE $0xf8 // mov r8, r15 - QUAD $0x083a54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r15 + 8], 13 - LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] - QUAD $0x083a54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r15 + 8], 14 - QUAD $0x090a5c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdx + rcx + 9], 1 - QUAD $0x09025c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rax + 9], 2 - QUAD $0x093a5c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rdx + rdi + 9], 3 - QUAD $0x09125c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdx + r10 + 9], 4 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - QUAD $0x091a5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdx + r11 + 9], 5 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - QUAD $0x092a5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r13 + 9], 6 - WORD $0x894d; BYTE $0xea // mov r10, r13 - QUAD $0x09325c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rdx + rsi + 9], 7 - QUAD $0x09325c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r14 + 9], 8 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x09025c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdx + rax + 9], 9 - QUAD $0x09225c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdx + r12 + 9], 10 - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x091a5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r11 + 9], 11 - QUAD $0x090a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r9 + 9], 12 - QUAD $0x09025c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdx + r8 + 9], 13 - WORD $0x894d; BYTE $0xc5 // mov r13, r8 - LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] - QUAD $0x09025c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r8 + 9], 14 - LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] - QUAD $0x093a5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdx + r15 + 9], 15 - LONG $0xeb0f4466; BYTE $0xc0 // por xmm8, xmm0 - QUAD $0x00a024847f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm8 - LONG $0xda0f4566; BYTE $0xda // pminub xmm11, xmm10 - LONG $0x740f4566; BYTE $0xda // pcmpeqb xmm11, xmm10 - LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 - QUAD $0x0000a0856f0f4466; BYTE $0x00 // movdqa xmm8, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xdf0f4166; BYTE $0xc0 // pandn xmm0, xmm8 - LONG $0xfc0f4166; BYTE $0xc3 // paddb xmm0, xmm11 - LONG $0x244c8b4c; BYTE $0x38 // mov r9, qword [rsp + 56] - LONG $0x74b60f42; WORD $0x160a // movzx esi, byte [rdx + r9 + 22] - LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - QUAD $0x083a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r15 + 8], 15 - LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 - LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 - LONG $0xdf0f4166; BYTE $0xd0 // pandn xmm2, xmm8 - QUAD $0x0a0a64203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdx + rcx + 10], 1 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x0a0a64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rcx + 10], 2 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0a0a64203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdx + rcx + 10], 3 - QUAD $0x0a1a64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdx + rbx + 10], 4 - QUAD $0x0a3a64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdx + rdi + 10], 5 - QUAD $0x0a1264203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdx + r10 + 10], 6 - QUAD $0x000000d0249c8b48 // mov rbx, qword [rsp + 208] - QUAD $0x0a1a64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rdx + rbx + 10], 7 - QUAD $0x0a3264203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r14 + 10], 8 - QUAD $0x0a0264203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rdx + rax + 10], 9 - WORD $0x8949; BYTE $0xc6 // mov r14, rax - QUAD $0x0a2264203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdx + r12 + 10], 10 - QUAD $0x0a1a64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdx + r11 + 10], 11 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0a0264203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdx + rax + 10], 12 - QUAD $0x0a2a64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdx + r13 + 10], 13 - QUAD $0x0a0264203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r8 + 10], 14 - QUAD $0x0a3a64203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdx + r15 + 10], 15 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - LONG $0xda0f4566; BYTE $0xe2 // pminub xmm12, xmm10 - LONG $0x740f4566; BYTE $0xe2 // pcmpeqb xmm12, xmm10 - QUAD $0x0000b0a5df0f4466; BYTE $0x00 // pandn xmm12, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xeb0f4466; BYTE $0xe2 // por xmm12, xmm2 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x74b60f42; WORD $0x170a // movzx esi, byte [rdx + r9 + 23] - LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi - QUAD $0x00009024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 144] - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - QUAD $0x0b0254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r8 + 11], 1 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0b3a54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r15 + 11], 2 - QUAD $0x030b0a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 11], 3 - QUAD $0x000000c0249c8b4c // mov r11, qword [rsp + 192] - QUAD $0x0b1a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r11 + 11], 4 - QUAD $0x050b3a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 11], 5 - QUAD $0x0b1254203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r10 + 11], 6 - QUAD $0x070b1a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 11], 7 - LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] - QUAD $0x080b3254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 11], 8 - QUAD $0x0b3254203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r14 + 11], 9 - LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] - QUAD $0x0b3254203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r14 + 11], 10 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x0b0b3a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 11], 11 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x0b0a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r9 + 11], 12 - QUAD $0x0b2a54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r13 + 11], 13 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0e0b3254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 11], 14 - QUAD $0x0b2254203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r12 + 11], 15 - WORD $0x894d; BYTE $0xe5 // mov r13, r12 - LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 - LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 - QUAD $0x000000c095df0f66 // pandn xmm2, oword 192[rbp] /* [rip + .LCPI8_12] */ - LONG $0xeb0f4166; BYTE $0xd4 // por xmm2, xmm12 - LONG $0x0274b60f; BYTE $0x18 // movzx esi, byte [rdx + rax + 24] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - LONG $0xc3f80f66 // psubb xmm0, xmm3 - LONG $0xd0eb0f66 // por xmm2, xmm0 - QUAD $0x00009024947f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm2 - LONG $0x0274b60f; BYTE $0x19 // movzx esi, byte [rdx + rax + 25] - LONG $0xde6e0f66 // movd xmm3, esi - QUAD $0x00013024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 304] - QUAD $0x0c0254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r8 + 12], 1 - QUAD $0x0c3a54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r15 + 12], 2 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0c0254203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r8 + 12], 3 - WORD $0x894d; BYTE $0xda // mov r10, r11 - QUAD $0x0c1a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r11 + 12], 4 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x050c3254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 12], 5 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x0c3a54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r15 + 12], 6 - QUAD $0x070c1a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 12], 7 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0c1a54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r11 + 12], 8 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x090c0a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 12], 9 - QUAD $0x0c3254203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r14 + 12], 10 - QUAD $0x0b0c3a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 12], 11 - QUAD $0x0c0a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r9 + 12], 12 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x0c2254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r12 + 12], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e0c0254203a0f66 // pinsrb xmm2, byte [rdx + rax + 12], 14 - QUAD $0x0c2a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r13 + 12], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0d0274203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdx + rax + 13], 1 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0d2a74203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdx + r13 + 13], 2 - QUAD $0x0d0274203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdx + r8 + 13], 3 - QUAD $0x0d1274203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rdx + r10 + 13], 4 - QUAD $0x0d3274203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdx + rsi + 13], 5 - QUAD $0x0d3a74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdx + r15 + 13], 6 - QUAD $0x0d1a74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rdx + rbx + 13], 7 - QUAD $0x0d1a74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdx + r11 + 13], 8 - QUAD $0x0d0a74203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdx + rcx + 13], 9 - QUAD $0x0d3274203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rdx + r14 + 13], 10 - QUAD $0x0d3a74203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rdx + rdi + 13], 11 - QUAD $0x0d0a74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdx + r9 + 13], 12 - QUAD $0x0d2274203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rdx + r12 + 13], 13 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x0d2a74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdx + r13 + 13], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0d0274203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdx + rax + 13], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e026c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdx + rax + 14], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0e026c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rax + 14], 2 - QUAD $0x0e026c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdx + r8 + 14], 3 - QUAD $0x0e126c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdx + r10 + 14], 4 - QUAD $0x0e326c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdx + rsi + 14], 5 - QUAD $0x0e3a6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdx + r15 + 14], 6 - QUAD $0x0e1a6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rdx + rbx + 14], 7 - QUAD $0x0e1a6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r11 + 14], 8 - QUAD $0x0e0a6c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rdx + rcx + 14], 9 - QUAD $0x0e326c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rdx + r14 + 14], 10 - QUAD $0x0e3a6c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rdx + rdi + 14], 11 - QUAD $0x0e0a6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r9 + 14], 12 - QUAD $0x0e226c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdx + r12 + 14], 13 - QUAD $0x0e2a6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r13 + 14], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e026c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdx + rax + 14], 15 - QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x010f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 15], 1 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0f2a44203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdx + r13 + 15], 2 - QUAD $0x0f0244203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r8 + 15], 3 - QUAD $0x0f1244203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdx + r10 + 15], 4 - QUAD $0x050f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 15], 5 - QUAD $0x0f3a44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdx + r15 + 15], 6 - QUAD $0x070f1a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 15], 7 - QUAD $0x0f1a44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r11 + 15], 8 - QUAD $0x090f0a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 15], 9 - QUAD $0x0f3244203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdx + r14 + 15], 10 - QUAD $0x0b0f3a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 15], 11 - QUAD $0x0f0a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r9 + 15], 12 - QUAD $0x0f2244203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdx + r12 + 15], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e0f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 15], 14 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0f0f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 15], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0111024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 17], 1 - QUAD $0x112a4c203a0f4266; BYTE $0x02 // pinsrb xmm1, byte [rdx + r13 + 17], 2 - QUAD $0x11024c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r8 + 17], 3 - QUAD $0x11124c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdx + r10 + 17], 4 - QUAD $0x0511324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 17], 5 - QUAD $0x113a4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r15 + 17], 6 - QUAD $0x07111a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 17], 7 - QUAD $0x111a4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r11 + 17], 8 - QUAD $0x09110a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 17], 9 - QUAD $0x11324c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdx + r14 + 17], 10 - QUAD $0x0b113a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 17], 11 - WORD $0x8949; BYTE $0xfe // mov r14, rdi - QUAD $0x110a4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r9 + 17], 12 - QUAD $0x11224c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdx + r12 + 17], 13 - LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 - LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 - QUAD $0x000000d095df0f66 // pandn xmm2, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xda0f4566; BYTE $0xf2 // pminub xmm14, xmm10 - LONG $0x740f4566; BYTE $0xf2 // pcmpeqb xmm14, xmm10 - QUAD $0x0000e0b5df0f4466; BYTE $0x00 // pandn xmm14, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xeb0f4466; BYTE $0xf2 // por xmm14, xmm2 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - LONG $0x3a74b60f; BYTE $0x1a // movzx esi, byte [rdx + rdi + 26] - LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x244c8b4c; BYTE $0x10 // mov r9, qword [rsp + 16] - QUAD $0x110a4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r9 + 17], 14 - LONG $0xda0f4566; BYTE $0xea // pminub xmm13, xmm10 - LONG $0x740f4566; BYTE $0xea // pcmpeqb xmm13, xmm10 - QUAD $0x0000f0addf0f4466; BYTE $0x00 // pandn xmm13, oword 240[rbp] /* [rip + .LCPI8_15] */ - LONG $0xeb0f4566; BYTE $0xee // por xmm13, xmm14 - LONG $0x3a74b60f; BYTE $0x1b // movzx esi, byte [rdx + rdi + 27] - LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - LONG $0xda0f4166; BYTE $0xc2 // pminub xmm0, xmm10 - LONG $0x740f4166; BYTE $0xc2 // pcmpeqb xmm0, xmm10 - QUAD $0x0000010085ef0f66 // pxor xmm0, oword 256[rbp] /* [rip + .LCPI8_16] */ - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0x45db0f66; BYTE $0x60 // pand xmm0, oword 96[rbp] /* [rip + .LCPI8_6] */ - LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 - LONG $0x3a74b60f; BYTE $0x1c // movzx esi, byte [rdx + rdi + 28] - LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x112a4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r13 + 17], 15 - QUAD $0x0000902484eb0f66; BYTE $0x00 // por xmm0, oword [rsp + 144] - QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 - LONG $0xda0f4166; BYTE $0xca // pminub xmm1, xmm10 - LONG $0x740f4166; BYTE $0xca // pcmpeqb xmm1, xmm10 - LONG $0x6f0f4166; BYTE $0xc2 // movdqa xmm0, xmm10 - LONG $0x6f0f4466; BYTE $0xf1 // movdqa xmm14, xmm1 - QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xdf0f4566; BYTE $0xf2 // pandn xmm14, xmm10 - LONG $0xfc0f4466; BYTE $0xf1 // paddb xmm14, xmm1 - QUAD $0x009024b47f0f4466; WORD $0x0000 // movdqa oword [rsp + 144], xmm14 - LONG $0x3a74b60f; BYTE $0x1d // movzx esi, byte [rdx + rdi + 29] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0110026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 16], 1 - QUAD $0x0112027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 18], 1 - QUAD $0x13027c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rax + 19], 1 - QUAD $0x01140264203a0f66 // pinsrb xmm4, byte [rdx + rax + 20], 1 - QUAD $0x01150274203a0f66 // pinsrb xmm6, byte [rdx + rax + 21], 1 - QUAD $0x16024c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rax + 22], 1 - QUAD $0x170244203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdx + rax + 23], 1 - QUAD $0x18025c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdx + rax + 24], 1 - QUAD $0x0119025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 25], 1 - QUAD $0x011a0254203a0f66 // pinsrb xmm2, byte [rdx + rax + 26], 1 - QUAD $0x1b0264203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdx + rax + 27], 1 - QUAD $0x1c026c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdx + rax + 28], 1 - QUAD $0x1d0254203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdx + rax + 29], 1 - LONG $0x3a74b60f; BYTE $0x1e // movzx esi, byte [rdx + rdi + 30] - LONG $0x6e0f4466; BYTE $0xf6 // movd xmm14, esi - QUAD $0x1e0274203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdx + rax + 30], 1 - LONG $0x3a74b60f; BYTE $0x1f // movzx esi, byte [rdx + rdi + 31] - LONG $0xce6e0f66 // movd xmm1, esi - QUAD $0x011f024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 31], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0210026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 16], 2 - QUAD $0x0212027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 18], 2 - QUAD $0x13027c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdx + rax + 19], 2 - QUAD $0x02140264203a0f66 // pinsrb xmm4, byte [rdx + rax + 20], 2 - QUAD $0x02150274203a0f66 // pinsrb xmm6, byte [rdx + rax + 21], 2 - QUAD $0x16024c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rax + 22], 2 - QUAD $0x170244203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdx + rax + 23], 2 - QUAD $0x18025c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rax + 24], 2 - QUAD $0x0219025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 25], 2 - QUAD $0x021a0254203a0f66 // pinsrb xmm2, byte [rdx + rax + 26], 2 - QUAD $0x1b0264203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rax + 27], 2 - QUAD $0x1c026c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rax + 28], 2 - QUAD $0x1d0254203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdx + rax + 29], 2 - QUAD $0x1e0274203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rdx + rax + 30], 2 - QUAD $0x021f024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 31], 2 - QUAD $0x10026c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r8 + 16], 3 - QUAD $0x10126c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdx + r10 + 16], 4 - LONG $0x24748b48; BYTE $0x78 // mov rsi, qword [rsp + 120] - QUAD $0x0510326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 16], 5 - QUAD $0x103a6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r15 + 16], 6 - QUAD $0x07101a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 16], 7 - QUAD $0x101a6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r11 + 16], 8 - QUAD $0x09100a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 16], 9 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x0a10026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 16], 10 - QUAD $0x10326c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdx + r14 + 16], 11 - LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] - QUAD $0x10226c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r12 + 16], 12 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x0d103a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 16], 13 - QUAD $0x100a6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdx + r9 + 16], 14 - QUAD $0x102a6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdx + r13 + 16], 15 - LONG $0xe8da0f66 // pminub xmm5, xmm0 - LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 - QUAD $0x12027c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r8 + 18], 3 - QUAD $0x12127c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdx + r10 + 18], 4 - QUAD $0x0512327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 18], 5 - QUAD $0x123a7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdx + r15 + 18], 6 - QUAD $0x07121a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 18], 7 - QUAD $0x121a7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdx + r11 + 18], 8 - QUAD $0x09120a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 18], 9 - QUAD $0x0a12027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 18], 10 - QUAD $0x12327c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdx + r14 + 18], 11 - QUAD $0x12227c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r12 + 18], 12 - QUAD $0x0d123a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 18], 13 - QUAD $0x120a7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdx + r9 + 18], 14 - QUAD $0x122a7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdx + r13 + 18], 15 - QUAD $0x13027c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r8 + 19], 3 - QUAD $0x13127c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdx + r10 + 19], 4 - QUAD $0x13327c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdx + rsi + 19], 5 - QUAD $0x133a7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdx + r15 + 19], 6 - QUAD $0x131a7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rdx + rbx + 19], 7 - QUAD $0x131a7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdx + r11 + 19], 8 - QUAD $0x130a7c203a0f4466; BYTE $0x09 // pinsrb xmm15, byte [rdx + rcx + 19], 9 - QUAD $0x13027c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdx + rax + 19], 10 - QUAD $0x13327c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdx + r14 + 19], 11 - QUAD $0x13227c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdx + r12 + 19], 12 - QUAD $0x133a7c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdx + rdi + 19], 13 - QUAD $0x130a7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdx + r9 + 19], 14 - QUAD $0x132a7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdx + r13 + 19], 15 - QUAD $0x140264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r8 + 20], 3 - QUAD $0x141264203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r10 + 20], 4 - QUAD $0x05143264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 20], 5 - QUAD $0x143a64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdx + r15 + 20], 6 - QUAD $0x07141a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 20], 7 - QUAD $0x141a64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r11 + 20], 8 - QUAD $0x09140a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 20], 9 - QUAD $0x0a140264203a0f66 // pinsrb xmm4, byte [rdx + rax + 20], 10 - QUAD $0x143264203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r14 + 20], 11 - QUAD $0x142264203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r12 + 20], 12 - QUAD $0x0d143a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 20], 13 - QUAD $0x140a64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdx + r9 + 20], 14 - QUAD $0x142a64203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdx + r13 + 20], 15 - QUAD $0x150274203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r8 + 21], 3 - QUAD $0x151274203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdx + r10 + 21], 4 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x05153274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 21], 5 - QUAD $0x153a74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r15 + 21], 6 - QUAD $0x07151a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 21], 7 - QUAD $0x151a74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r11 + 21], 8 - QUAD $0x09150a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 21], 9 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x151274203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r10 + 21], 10 - QUAD $0x153274203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r14 + 21], 11 - QUAD $0x152274203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r12 + 21], 12 - QUAD $0x0d153a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 21], 13 - QUAD $0x150a74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdx + r9 + 21], 14 - QUAD $0x000000a0addf0f66 // pandn xmm5, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xf8da0f66 // pminub xmm7, xmm0 - LONG $0xf8740f66 // pcmpeqb xmm7, xmm0 - QUAD $0x000000b0bddf0f66 // pandn xmm7, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0xda0f4466; BYTE $0xf8 // pminub xmm15, xmm0 - LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI8_12] */ - LONG $0xdf0f4466; BYTE $0xfd // pandn xmm15, xmm5 - LONG $0xeb0f4466; BYTE $0xff // por xmm15, xmm7 - QUAD $0x152a74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdx + r13 + 21], 15 - LONG $0xed760f66 // pcmpeqd xmm5, xmm5 - QUAD $0x00009024bc6f0f66; BYTE $0x00 // movdqa xmm7, oword [rsp + 144] - LONG $0xfdf80f66 // psubb xmm7, xmm5 - LONG $0xeb0f4466; BYTE $0xff // por xmm15, xmm7 - LONG $0xe0da0f66 // pminub xmm4, xmm0 - LONG $0xe0740f66 // pcmpeqb xmm4, xmm0 - QUAD $0x000000d0bd6f0f66 // movdqa xmm7, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xe7df0f66 // pandn xmm4, xmm7 - LONG $0xf0da0f66 // pminub xmm6, xmm0 - LONG $0xf0740f66 // pcmpeqb xmm6, xmm0 - QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xf7df0f66 // pandn xmm6, xmm7 - LONG $0xf4eb0f66 // por xmm6, xmm4 - QUAD $0x16024c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdx + r8 + 22], 3 - QUAD $0x16024c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdx + rax + 22], 4 - QUAD $0x16324c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdx + rsi + 22], 5 - QUAD $0x163a4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdx + r15 + 22], 6 - QUAD $0x161a4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rdx + rbx + 22], 7 - QUAD $0x161a4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r11 + 22], 8 - QUAD $0x160a4c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdx + rcx + 22], 9 - QUAD $0x16124c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdx + r10 + 22], 10 - QUAD $0x16324c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdx + r14 + 22], 11 - QUAD $0x16224c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdx + r12 + 22], 12 - QUAD $0x163a4c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdx + rdi + 22], 13 - QUAD $0x160a4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r9 + 22], 14 - QUAD $0x162a4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdx + r13 + 22], 15 - LONG $0xda0f4466; BYTE $0xc8 // pminub xmm9, xmm0 - LONG $0x740f4466; BYTE $0xc8 // pcmpeqb xmm9, xmm0 - QUAD $0x000000f0bd6f0f66 // movdqa xmm7, oword 240[rbp] /* [rip + .LCPI8_15] */ - LONG $0xdf0f4466; BYTE $0xcf // pandn xmm9, xmm7 - LONG $0xeb0f4466; BYTE $0xce // por xmm9, xmm6 - QUAD $0x170244203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r8 + 23], 3 - QUAD $0x170244203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rdx + rax + 23], 4 - QUAD $0x173244203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdx + rsi + 23], 5 - QUAD $0x173a44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdx + r15 + 23], 6 - QUAD $0x171a44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rdx + rbx + 23], 7 - QUAD $0x171a44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdx + r11 + 23], 8 - QUAD $0x170a44203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdx + rcx + 23], 9 - QUAD $0x171244203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdx + r10 + 23], 10 - QUAD $0x173244203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r14 + 23], 11 - QUAD $0x172244203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdx + r12 + 23], 12 - QUAD $0x173a44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdx + rdi + 23], 13 - QUAD $0x170a44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdx + r9 + 23], 14 - QUAD $0x172a44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdx + r13 + 23], 15 - LONG $0xda0f4466; BYTE $0xc0 // pminub xmm8, xmm0 - LONG $0x740f4466; BYTE $0xc0 // pcmpeqb xmm8, xmm0 - LONG $0xef0f4466; BYTE $0xc5 // pxor xmm8, xmm5 - LONG $0xed760f66 // pcmpeqd xmm5, xmm5 - LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 - LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI8_6] */ - LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 - LONG $0xeb0f4566; BYTE $0xc1 // por xmm8, xmm9 - QUAD $0x18025c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r8 + 24], 3 - QUAD $0x18025c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdx + rax + 24], 4 - QUAD $0x18325c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdx + rsi + 24], 5 - QUAD $0x183a5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r15 + 24], 6 - QUAD $0x181a5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rdx + rbx + 24], 7 - QUAD $0x181a5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r11 + 24], 8 - QUAD $0x180a5c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdx + rcx + 24], 9 - QUAD $0x18125c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdx + r10 + 24], 10 - QUAD $0x18325c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r14 + 24], 11 - QUAD $0x18225c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r12 + 24], 12 - QUAD $0x183a5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdx + rdi + 24], 13 - QUAD $0x180a5c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r9 + 24], 14 - QUAD $0x19025c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r8 + 25], 3 - QUAD $0x0419025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 25], 4 - QUAD $0x0519325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 25], 5 - QUAD $0x193a5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdx + r15 + 25], 6 - QUAD $0x07191a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 25], 7 - QUAD $0x191a5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdx + r11 + 25], 8 - QUAD $0x09190a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 25], 9 - QUAD $0x19125c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r10 + 25], 10 - QUAD $0x19325c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r14 + 25], 11 - QUAD $0x19225c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r12 + 25], 12 - QUAD $0x0d193a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 25], 13 - QUAD $0x190a5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdx + r9 + 25], 14 - QUAD $0x192a5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r13 + 25], 15 - LONG $0xeb0f4566; BYTE $0xc7 // por xmm8, xmm15 - LONG $0xe06f0f66 // movdqa xmm4, xmm0 - LONG $0xd8da0f66 // pminub xmm3, xmm0 - LONG $0xd8740f66 // pcmpeqb xmm3, xmm0 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - QUAD $0x0000a08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 160[rbp] /* [rip + .LCPI8_10] */ - LONG $0xdf0f4166; BYTE $0xc1 // pandn xmm0, xmm9 - LONG $0xc3fc0f66 // paddb xmm0, xmm3 - QUAD $0x182a5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdx + r13 + 24], 15 - LONG $0xda0f4466; BYTE $0xdc // pminub xmm11, xmm4 - LONG $0x740f4466; BYTE $0xdc // pcmpeqb xmm11, xmm4 - LONG $0xdf0f4566; BYTE $0xd9 // pandn xmm11, xmm9 - QUAD $0x1a0254203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r8 + 26], 3 - QUAD $0x041a0254203a0f66 // pinsrb xmm2, byte [rdx + rax + 26], 4 - QUAD $0x051a3254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 26], 5 - QUAD $0x1a3a54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r15 + 26], 6 - QUAD $0x071a1a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 26], 7 - QUAD $0x1a1a54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r11 + 26], 8 - QUAD $0x091a0a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 26], 9 - QUAD $0x1a1254203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r10 + 26], 10 - QUAD $0x1a3254203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r14 + 26], 11 - QUAD $0x1a2254203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r12 + 26], 12 - QUAD $0x0d1a3a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 26], 13 - QUAD $0x1a0a54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r9 + 26], 14 - QUAD $0x1a2a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r13 + 26], 15 - LONG $0xd4da0f66 // pminub xmm2, xmm4 - LONG $0xd4740f66 // pcmpeqb xmm2, xmm4 - QUAD $0x000000b095df0f66 // pandn xmm2, oword 176[rbp] /* [rip + .LCPI8_11] */ - LONG $0xeb0f4166; BYTE $0xd3 // por xmm2, xmm11 - QUAD $0x1b0264203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r8 + 27], 3 - QUAD $0x1b0264203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdx + rax + 27], 4 - QUAD $0x1b3264203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdx + rsi + 27], 5 - QUAD $0x1b3a64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdx + r15 + 27], 6 - QUAD $0x1b1a64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rdx + rbx + 27], 7 - QUAD $0x1b1a64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r11 + 27], 8 - QUAD $0x1b0a64203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rdx + rcx + 27], 9 - QUAD $0x1b1264203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdx + r10 + 27], 10 - QUAD $0x1b3264203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdx + r14 + 27], 11 - QUAD $0x1b2264203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdx + r12 + 27], 12 - QUAD $0x1b3a64203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdx + rdi + 27], 13 - QUAD $0x1b0a64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r9 + 27], 14 - QUAD $0x1b2a64203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdx + r13 + 27], 15 - LONG $0xda0f4466; BYTE $0xe4 // pminub xmm12, xmm4 - LONG $0x740f4466; BYTE $0xe4 // pcmpeqb xmm12, xmm4 - LONG $0xdc6f0f66 // movdqa xmm3, xmm4 - QUAD $0x0000c0a5df0f4466; BYTE $0x00 // pandn xmm12, oword 192[rbp] /* [rip + .LCPI8_12] */ - LONG $0xeb0f4466; BYTE $0xe2 // por xmm12, xmm2 - LONG $0xc5f80f66 // psubb xmm0, xmm5 - LONG $0xeb0f4466; BYTE $0xe0 // por xmm12, xmm0 - QUAD $0x1c026c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdx + r8 + 28], 3 - QUAD $0x1d0254203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r8 + 29], 3 - QUAD $0x1e0274203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdx + r8 + 30], 3 - QUAD $0x1f024c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r8 + 31], 3 - QUAD $0x1c026c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdx + rax + 28], 4 - QUAD $0x1d0254203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdx + rax + 29], 4 - QUAD $0x1e0274203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rdx + rax + 30], 4 - QUAD $0x041f024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 31], 4 - QUAD $0x1c326c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdx + rsi + 28], 5 - QUAD $0x1d3254203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdx + rsi + 29], 5 - QUAD $0x1e3274203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdx + rsi + 30], 5 - QUAD $0x051f324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 31], 5 - QUAD $0x1c3a6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdx + r15 + 28], 6 - QUAD $0x1d3a54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r15 + 29], 6 - QUAD $0x1e3a74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdx + r15 + 30], 6 - QUAD $0x1f3a4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r15 + 31], 6 - QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] - QUAD $0x1c1a6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rdx + rbx + 28], 7 - QUAD $0x1d1a54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rdx + rbx + 29], 7 - QUAD $0x1e1a74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rdx + rbx + 30], 7 - QUAD $0x071f1a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 31], 7 - QUAD $0x1c1a6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r11 + 28], 8 - QUAD $0x1d1a54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r11 + 29], 8 - QUAD $0x1e1a74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdx + r11 + 30], 8 - QUAD $0x1f1a4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r11 + 31], 8 - QUAD $0x1c0a6c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rdx + rcx + 28], 9 - QUAD $0x1d0a54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rcx + 29], 9 - QUAD $0x1e0a74203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdx + rcx + 30], 9 - QUAD $0x091f0a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 31], 9 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - QUAD $0x1c126c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rdx + r10 + 28], 10 - QUAD $0x1d1254203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdx + r10 + 29], 10 - QUAD $0x1e1274203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rdx + r10 + 30], 10 - QUAD $0x1f124c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdx + r10 + 31], 10 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x1c026c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rdx + rax + 28], 11 - QUAD $0x1d0254203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rdx + rax + 29], 11 - QUAD $0x1e0274203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rdx + rax + 30], 11 - QUAD $0x0b1f024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 31], 11 - WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x1c226c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r12 + 28], 12 - QUAD $0x1d2254203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdx + r12 + 29], 12 - QUAD $0x1e2274203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdx + r12 + 30], 12 - QUAD $0x1f224c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r12 + 31], 12 - QUAD $0x1c3a6c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rdx + rdi + 28], 13 - QUAD $0x1d3a54203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdx + rdi + 29], 13 - QUAD $0x1e3a74203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdx + rdi + 30], 13 - QUAD $0x0d1f3a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 31], 13 - QUAD $0x1c0a6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r9 + 28], 14 - QUAD $0x1d0a54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r9 + 29], 14 - QUAD $0x1e0a74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdx + r9 + 30], 14 - QUAD $0x1f0a4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r9 + 31], 14 - WORD $0x894c; BYTE $0xe8 // mov rax, r13 - QUAD $0x1c2a6c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdx + r13 + 28], 15 - QUAD $0x1d2a54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdx + r13 + 29], 15 - QUAD $0x1e2a74203a0f4666; BYTE $0x0f // pinsrb xmm14, byte [rdx + r13 + 30], 15 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0xda0f4466; BYTE $0xec // pminub xmm13, xmm4 - LONG $0x740f4466; BYTE $0xec // pcmpeqb xmm13, xmm4 - QUAD $0x0000d0addf0f4466; BYTE $0x00 // pandn xmm13, oword 208[rbp] /* [rip + .LCPI8_13] */ - LONG $0xda0f4466; BYTE $0xd4 // pminub xmm10, xmm4 - LONG $0x740f4466; BYTE $0xd4 // pcmpeqb xmm10, xmm4 - QUAD $0x0000e095df0f4466; BYTE $0x00 // pandn xmm10, oword 224[rbp] /* [rip + .LCPI8_14] */ - LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 - QUAD $0x1f2a4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r13 + 31], 15 - LONG $0xda0f4466; BYTE $0xf4 // pminub xmm14, xmm4 - LONG $0x740f4466; BYTE $0xf4 // pcmpeqb xmm14, xmm4 - LONG $0xdf0f4466; BYTE $0xf7 // pandn xmm14, xmm7 - LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 - LONG $0xccda0f66 // pminub xmm1, xmm4 - LONG $0xcc740f66 // pcmpeqb xmm1, xmm4 - LONG $0xcdef0f66 // pxor xmm1, xmm5 - LONG $0xf1710f66; BYTE $0x07 // psllw xmm1, 7 - LONG $0xcedb0f66 // pand xmm1, xmm6 - LONG $0xeb0f4166; BYTE $0xce // por xmm1, xmm14 - LONG $0xeb0f4166; BYTE $0xcc // por xmm1, xmm12 - LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0xc1600f66 // punpcklbw xmm0, xmm1 - QUAD $0x0000a024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 160] - LONG $0xd46f0f66 // movdqa xmm2, xmm4 - QUAD $0x0000b024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 176] - LONG $0xd5600f66 // punpcklbw xmm2, xmm5 - LONG $0xda6f0f66 // movdqa xmm3, xmm2 - LONG $0xd8610f66 // punpcklwd xmm3, xmm0 - LONG $0xd0690f66 // punpckhwd xmm2, xmm0 - LONG $0x680f4466; BYTE $0xc1 // punpckhbw xmm8, xmm1 - LONG $0xe5680f66 // punpckhbw xmm4, xmm5 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 - LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 - QUAD $0x000000f0248c8b48 // mov rcx, qword [rsp + 240] - LONG $0x7f0f41f3; WORD $0x8e64; BYTE $0x30 // movdqu oword [r14 + 4*rcx + 48], xmm4 - LONG $0x7f0f41f3; WORD $0x8e44; BYTE $0x20 // movdqu oword [r14 + 4*rcx + 32], xmm0 - LONG $0x7f0f41f3; WORD $0x8e54; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm2 - LONG $0x7f0f41f3; WORD $0x8e1c // movdqu oword [r14 + 4*rcx], xmm3 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000e8248c3b48 // cmp rcx, qword [rsp + 232] - JNE LBB8_195 - QUAD $0x0000010024bc8b4c // mov r15, qword [rsp + 256] - QUAD $0x000000e824bc3b4c // cmp r15, qword [rsp + 232] - LONG $0x241c8a44 // mov r11b, byte [rsp] - QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - JNE LBB8_67 - JMP LBB8_132 + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_215 + LONG $0x2a394466 // cmp word [rdx], r13w + +LBB8_197: + WORD $0xc019 // sbb eax, eax + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x16348a41 // mov sil, byte [r14 + rdx] + LONG $0x07e38041 // and r11b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0xc320 // and bl, al + JMP LBB8_204 + +LBB8_198: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0xff31 // xor edi, edi + +LBB8_199: + WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] + WORD $0x9f0f; BYTE $0xd0 // setg al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0x03eec148 // shr rsi, 3 + LONG $0x0cb60f45; BYTE $0x36 // movzx r9d, byte [r14 + rsi] + WORD $0xf989 // mov ecx, edi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x361c8841 // mov byte [r14 + rsi], bl + LONG $0x02c78348 // add rdi, 2 + LONG $0x086a3b4c // cmp r13, qword [rdx + 8] + LONG $0x10528d48 // lea rdx, [rdx + 16] + LONG $0xd19f0f41 // setg r9b + WORD $0xf641; BYTE $0xd9 // neg r9b + WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0xd830 // xor al, bl + LONG $0x36048841 // mov byte [r14 + rsi], al + WORD $0x3949; BYTE $0xfa // cmp r10, rdi + JNE LBB8_199 + +LBB8_200: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_215 + WORD $0x3b4c; BYTE $0x2a // cmp r13, qword [rdx] + +LBB8_202: + WORD $0x9f0f; BYTE $0xd0 // setg al + +LBB8_203: + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0x03eac148 // shr rdx, 3 + LONG $0x16348a41 // mov sil, byte [r14 + rdx] + LONG $0x07e78040 // and dil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf989 // mov ecx, edi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0xc320 // and bl, al -LBB8_197: - LONG $0xf8e78349 // and r15, -8 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB8_204: + WORD $0x3040; BYTE $0xf3 // xor bl, sil + LONG $0x161c8841 // mov byte [r14 + rdx], bl + JMP LBB8_215 + +LBB8_205: + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + LONG $0xfee18349 // and r9, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + LONG $0x241c8b4c // mov r11, qword [rsp] + +LBB8_206: + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + LONG $0x2e3b4466 // cmp r13w, word [rsi] + WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0xdaf6 // neg dl + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x14b60f45; BYTE $0x3b // movzx r10d, byte [r11 + rdi] + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3b1c8841 // mov byte [r11 + rdi], bl + LONG $0x02c68349 // add r14, 2 + LONG $0x6e3b4466; BYTE $0x02 // cmp r13w, word [rsi + 2] + LONG $0x04768d48 // lea rsi, [rsi + 4] + WORD $0x9f0f; BYTE $0xd2 // setg dl + WORD $0xdaf6 // neg dl + WORD $0xda30 // xor dl, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd020 // and al, dl + WORD $0xd830 // xor al, bl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x394d; BYTE $0xf1 // cmp r9, r14 + JNE LBB8_206 + +LBB8_207: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_215 + LONG $0x2e3b4466 // cmp r13w, word [rsi] + WORD $0x9f0f; BYTE $0xd0 // setg al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x24048b4c // mov r8, qword [rsp] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e68041 // and r14b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + +LBB8_209: + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + +LBB8_210: + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + JMP LBB8_215 + +LBB8_211: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0xf631 // xor esi, esi + WORD $0x894d; BYTE $0xde // mov r14, r11 + +LBB8_212: + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x970f; BYTE $0xd2 // seta dl + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x03efc148 // shr rdi, 3 + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + WORD $0xf189 // mov ecx, esi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x3044; BYTE $0xca // xor dl, r9b + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x02c68348 // add rsi, 2 + LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] + LONG $0xd1970f41 // seta r9b + LONG $0x08c38348 // add rbx, 8 + WORD $0xf641; BYTE $0xd9 // neg r9b + WORD $0x3041; BYTE $0xc1 // xor r9b, al + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0x2044; BYTE $0xca // and dl, r9b + WORD $0xc230 // xor dl, al + LONG $0x3e148841 // mov byte [r14 + rdi], dl + WORD $0x3949; BYTE $0xf2 // cmp r10, rsi + JNE LBB8_212 + +LBB8_213: + LONG $0x01c0f641 // test r8b, 1 + JE LBB8_215 + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0x970f; BYTE $0xd0 // seta al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + LONG $0x03eac148 // shr rdx, 3 + LONG $0x133c8a41 // mov dil, byte [r11 + rdx] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x131c8841 // mov byte [r11 + rdx], bl + +LBB8_215: + MOVQ 336(SP), SP + RET + +LBB8_216: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x06e0c148 // shl rax, 6 WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] LONG $0x24048948 // mov qword [rsp], rax - LONG $0x246c8944; BYTE $0x30 // mov dword [rsp + 48], r13d + LONG $0x246c8944; BYTE $0x28 // mov dword [rsp + 40], r13d LONG $0x6e0f4166; BYTE $0xc5 // movd xmm0, r13d LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 LONG $0x700f4466; WORD $0x00f8 // pshufd xmm15, xmm0, 0 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + WORD $0x3145; BYTE $0xc0 // xor r8d, r8d QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 QUAD $0x000080856f0f4466; BYTE $0x00 // movdqa xmm8, oword 128[rbp] /* [rip + .LCPI8_8] */ -LBB8_198: - LONG $0x244c894c; BYTE $0x10 // mov qword [rsp + 16], r9 - LONG $0x06e1c149 // shl r9, 6 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - WORD $0x894d; BYTE $0xcc // mov r12, r9 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - WORD $0x894c; BYTE $0xcb // mov rbx, r9 - LONG $0x04b70f42; BYTE $0x0a // movzx eax, word [rdx + r9] +LBB8_217: + LONG $0x2444894c; BYTE $0x08 // mov qword [rsp + 8], r8 + LONG $0x06e0c149 // shl r8, 6 + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 + WORD $0x894c; BYTE $0xc7 // mov rdi, r8 + LONG $0x04b70f42; BYTE $0x02 // movzx eax, word [rdx + r8] LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f42; WORD $0x020a // movzx eax, word [rdx + r9 + 2] + LONG $0x44b70f42; WORD $0x0202 // movzx eax, word [rdx + r8 + 2] LONG $0xd86e0f66 // movd xmm3, eax - LONG $0x44b70f42; WORD $0x040a // movzx eax, word [rdx + r9 + 4] + LONG $0x44b70f42; WORD $0x0402 // movzx eax, word [rdx + r8 + 4] LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f42; WORD $0x060a // movzx eax, word [rdx + r9 + 6] + LONG $0x44b70f42; WORD $0x0602 // movzx eax, word [rdx + r8 + 6] LONG $0xe06e0f66 // movd xmm4, eax - LONG $0x54b70f46; WORD $0x080a // movzx r10d, word [rdx + r9 + 8] - LONG $0x74b70f42; WORD $0x0a0a // movzx esi, word [rdx + r9 + 10] - LONG $0x5cb70f46; WORD $0x0c0a // movzx r11d, word [rdx + r9 + 12] - LONG $0x44b70f42; WORD $0x0e0a // movzx eax, word [rdx + r9 + 14] - LONG $0x08244489 // mov dword [rsp + 8], eax - LONG $0x44b70f42; WORD $0x100a // movzx eax, word [rdx + r9 + 16] + LONG $0x54b70f46; WORD $0x0802 // movzx r10d, word [rdx + r8 + 8] + LONG $0x74b70f42; WORD $0x0a02 // movzx esi, word [rdx + r8 + 10] + LONG $0x5cb70f46; WORD $0x0c02 // movzx r11d, word [rdx + r8 + 12] + LONG $0x44b70f42; WORD $0x0e02 // movzx eax, word [rdx + r8 + 14] + LONG $0x10244489 // mov dword [rsp + 16], eax + LONG $0x44b70f42; WORD $0x1002 // movzx eax, word [rdx + r8 + 16] LONG $0xf06e0f66 // movd xmm6, eax - LONG $0x44b70f42; WORD $0x200a // movzx eax, word [rdx + r9 + 32] + LONG $0x44b70f42; WORD $0x2002 // movzx eax, word [rdx + r8 + 32] LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x44b70f42; WORD $0x300a // movzx eax, word [rdx + r9 + 48] - WORD $0x894d; BYTE $0xcf // mov r15, r9 + LONG $0x44b70f42; WORD $0x3002 // movzx eax, word [rdx + r8 + 48] + WORD $0x894d; BYTE $0xc7 // mov r15, r8 LONG $0x40cf8349 // or r15, 64 - LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 LONG $0x40c98148; WORD $0x0001; BYTE $0x00 // or rcx, 320 - LONG $0x80cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 384 + LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 LONG $0xc40f4266; WORD $0x3a2c; BYTE $0x01 // pinsrw xmm5, word [rdx + r15], 1 - LONG $0xc40f4266; WORD $0x022c; BYTE $0x02 // pinsrw xmm5, word [rdx + r8], 2 + LONG $0xc40f4266; WORD $0x0a2c; BYTE $0x02 // pinsrw xmm5, word [rdx + r9], 2 LONG $0xc40f4266; WORD $0x222c; BYTE $0x03 // pinsrw xmm5, word [rdx + r12], 3 LONG $0xc40f4266; WORD $0x2a2c; BYTE $0x04 // pinsrw xmm5, word [rdx + r13], 4 LONG $0x2cc40f66; WORD $0x050a // pinsrw xmm5, word [rdx + rcx], 5 - LONG $0x2cc40f66; WORD $0x063a // pinsrw xmm5, word [rdx + rdi], 6 - LONG $0xc0cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 448 - LONG $0x2cc40f66; WORD $0x071a // pinsrw xmm5, word [rdx + rbx], 7 + LONG $0x2cc40f66; WORD $0x061a // pinsrw xmm5, word [rdx + rbx], 6 + LONG $0xc0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 448 + LONG $0x2cc40f66; WORD $0x073a // pinsrw xmm5, word [rdx + rdi], 7 LONG $0x6e0f4466; BYTE $0xc8 // movd xmm9, eax - LONG $0x44b70f42; WORD $0x120a // movzx eax, word [rdx + r9 + 18] + LONG $0x44b70f42; WORD $0x1202 // movzx eax, word [rdx + r8 + 18] LONG $0x18244489 // mov dword [rsp + 24], eax LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 LONG $0xc5650f66 // pcmpgtw xmm0, xmm5 QUAD $0x01023a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 2], 1 - QUAD $0x0202025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 2], 2 + QUAD $0x02020a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 2], 2 QUAD $0x0302225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 2], 3 QUAD $0x04022a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 2], 4 LONG $0x5cc40f66; WORD $0x020a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 2], 5 - LONG $0x5cc40f66; WORD $0x023a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 2], 6 - LONG $0x5cc40f66; WORD $0x021a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 2], 7 + LONG $0x5cc40f66; WORD $0x021a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 2], 6 + LONG $0x5cc40f66; WORD $0x023a; BYTE $0x07 // pinsrw xmm3, word [rdx + rdi + 2], 7 QUAD $0x01103a74c40f4266 // pinsrw xmm6, word [rdx + r15 + 16], 1 - QUAD $0x02100274c40f4266 // pinsrw xmm6, word [rdx + r8 + 16], 2 + QUAD $0x02100a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 16], 2 QUAD $0x03102274c40f4266 // pinsrw xmm6, word [rdx + r12 + 16], 3 QUAD $0x04102a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 16], 4 LONG $0x74c40f66; WORD $0x100a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 16], 5 - LONG $0x74c40f66; WORD $0x103a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 16], 6 - LONG $0x74c40f66; WORD $0x101a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 16], 7 + LONG $0x74c40f66; WORD $0x101a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 16], 6 + LONG $0x74c40f66; WORD $0x103a; BYTE $0x07 // pinsrw xmm6, word [rdx + rdi + 16], 7 LONG $0x6f0f4566; BYTE $0xd7 // movdqa xmm10, xmm15 QUAD $0x01203a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 32], 1 - QUAD $0x0220024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 32], 2 + QUAD $0x02200a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 32], 2 QUAD $0x0320224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 32], 3 QUAD $0x04202a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 32], 4 LONG $0x4cc40f66; WORD $0x200a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 32], 5 - LONG $0x4cc40f66; WORD $0x203a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 32], 6 - LONG $0x4cc40f66; WORD $0x201a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 32], 7 + LONG $0x4cc40f66; WORD $0x201a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 32], 6 + LONG $0x4cc40f66; WORD $0x203a; BYTE $0x07 // pinsrw xmm1, word [rdx + rdi + 32], 7 LONG $0x650f4466; BYTE $0xd6 // pcmpgtw xmm10, xmm6 LONG $0x6f0f4166; BYTE $0xf7 // movdqa xmm6, xmm15 LONG $0xf1650f66 // pcmpgtw xmm6, xmm1 QUAD $0x01303a4cc40f4666 // pinsrw xmm9, word [rdx + r15 + 48], 1 - QUAD $0x0230024cc40f4666 // pinsrw xmm9, word [rdx + r8 + 48], 2 + QUAD $0x02300a4cc40f4666 // pinsrw xmm9, word [rdx + r9 + 48], 2 QUAD $0x0330224cc40f4666 // pinsrw xmm9, word [rdx + r12 + 48], 3 QUAD $0x04302a4cc40f4666 // pinsrw xmm9, word [rdx + r13 + 48], 4 QUAD $0x05300a4cc40f4466 // pinsrw xmm9, word [rdx + rcx + 48], 5 - QUAD $0x06303a4cc40f4466 // pinsrw xmm9, word [rdx + rdi + 48], 6 - QUAD $0x07301a4cc40f4466 // pinsrw xmm9, word [rdx + rbx + 48], 7 + QUAD $0x06301a4cc40f4466 // pinsrw xmm9, word [rdx + rbx + 48], 6 + QUAD $0x07303a4cc40f4466 // pinsrw xmm9, word [rdx + rdi + 48], 7 LONG $0x6f0f4166; BYTE $0xef // movdqa xmm5, xmm15 LONG $0x650f4166; BYTE $0xe9 // pcmpgtw xmm5, xmm9 LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 @@ -44725,35 +44118,35 @@ LBB8_198: LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 LONG $0xd9f80f66 // psubb xmm3, xmm1 LONG $0x6e0f4166; BYTE $0xca // movd xmm1, r10d - LONG $0x74b70f46; WORD $0x140a // movzx r14d, word [rdx + r9 + 20] + LONG $0x74b70f46; WORD $0x1402 // movzx r14d, word [rdx + r8 + 20] LONG $0xc0630f66 // packsswb xmm0, xmm0 QUAD $0x01043a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 4], 1 - QUAD $0x02040254c40f4266 // pinsrw xmm2, word [rdx + r8 + 4], 2 + QUAD $0x02040a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 4], 2 QUAD $0x03042254c40f4266 // pinsrw xmm2, word [rdx + r12 + 4], 3 QUAD $0x04042a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 4], 4 LONG $0x54c40f66; WORD $0x040a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 4], 5 - LONG $0x54c40f66; WORD $0x043a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 4], 6 - LONG $0x54c40f66; WORD $0x041a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 4], 7 + LONG $0x54c40f66; WORD $0x041a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 4], 6 + LONG $0x54c40f66; WORD $0x043a; BYTE $0x07 // pinsrw xmm2, word [rdx + rdi + 4], 7 QUAD $0x01063a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 6], 1 - QUAD $0x02060264c40f4266 // pinsrw xmm4, word [rdx + r8 + 6], 2 + QUAD $0x02060a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 6], 2 QUAD $0x03062264c40f4266 // pinsrw xmm4, word [rdx + r12 + 6], 3 QUAD $0x04062a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 6], 4 LONG $0x64c40f66; WORD $0x060a; BYTE $0x05 // pinsrw xmm4, word [rdx + rcx + 6], 5 - LONG $0x64c40f66; WORD $0x063a; BYTE $0x06 // pinsrw xmm4, word [rdx + rdi + 6], 6 - LONG $0x64c40f66; WORD $0x061a; BYTE $0x07 // pinsrw xmm4, word [rdx + rbx + 6], 7 + LONG $0x64c40f66; WORD $0x061a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 6], 6 + LONG $0x64c40f66; WORD $0x063a; BYTE $0x07 // pinsrw xmm4, word [rdx + rdi + 6], 7 QUAD $0x01083a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 8], 1 - QUAD $0x0208024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 8], 2 + QUAD $0x02080a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 8], 2 QUAD $0x0308224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 8], 3 QUAD $0x04082a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 8], 4 LONG $0x4cc40f66; WORD $0x080a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 8], 5 - LONG $0x4cc40f66; WORD $0x083a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 8], 6 + LONG $0x4cc40f66; WORD $0x081a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 8], 6 LONG $0xdb0f4166; BYTE $0xc0 // pand xmm0, xmm8 LONG $0xd8eb0f66 // por xmm3, xmm0 LONG $0x6f0f4166; BYTE $0xff // movdqa xmm7, xmm15 LONG $0xfa650f66 // pcmpgtw xmm7, xmm2 LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x74b70f42; WORD $0x160a // movzx esi, word [rdx + r9 + 22] - LONG $0x4cc40f66; WORD $0x081a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 8], 7 + LONG $0x74b70f42; WORD $0x1602 // movzx esi, word [rdx + r8 + 22] + LONG $0x4cc40f66; WORD $0x083a; BYTE $0x07 // pinsrw xmm1, word [rdx + rdi + 8], 7 LONG $0xff630f66 // packsswb xmm7, xmm7 LONG $0xdb0f4166; BYTE $0xf8 // pand xmm7, xmm8 LONG $0xf7710f66; BYTE $0x02 // psllw xmm7, 2 @@ -44765,20 +44158,20 @@ LBB8_198: LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 LONG $0xc1650f66 // pcmpgtw xmm0, xmm1 LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d - LONG $0x5cb70f46; WORD $0x180a // movzx r11d, word [rdx + r9 + 24] + LONG $0x5cb70f46; WORD $0x1802 // movzx r11d, word [rdx + r8 + 24] QUAD $0x010a3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 10], 1 - QUAD $0x020a0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 10], 2 + QUAD $0x020a0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 10], 2 QUAD $0x030a2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 10], 3 QUAD $0x040a2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 10], 4 LONG $0x54c40f66; WORD $0x0a0a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 10], 5 - LONG $0x54c40f66; WORD $0x0a3a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 10], 6 - LONG $0x54c40f66; WORD $0x0a1a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 10], 7 + LONG $0x54c40f66; WORD $0x0a1a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 10], 6 + LONG $0x54c40f66; WORD $0x0a3a; BYTE $0x07 // pinsrw xmm2, word [rdx + rdi + 10], 7 QUAD $0x010c3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 12], 1 - QUAD $0x020c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 12], 2 + QUAD $0x020c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 12], 2 QUAD $0x030c224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 12], 3 QUAD $0x040c2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 12], 4 LONG $0x4cc40f66; WORD $0x0c0a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 12], 5 - LONG $0x4cc40f66; WORD $0x0c3a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 12], 6 + LONG $0x4cc40f66; WORD $0x0c1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 12], 6 LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 LONG $0xf3710f66; BYTE $0x03 // psllw xmm3, 3 @@ -44790,23 +44183,23 @@ LBB8_198: LONG $0x6f0f4466; WORD $0x306d // movdqa xmm13, oword 48[rbp] /* [rip + .LCPI8_3] */ LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 LONG $0xc3eb0f66 // por xmm0, xmm3 - LONG $0x5c6e0f66; WORD $0x0824 // movd xmm3, dword [rsp + 8] - LONG $0x44b70f42; WORD $0x1a0a // movzx eax, word [rdx + r9 + 26] - LONG $0x4cc40f66; WORD $0x0c1a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 12], 7 + LONG $0x5c6e0f66; WORD $0x1024 // movd xmm3, dword [rsp + 16] + LONG $0x44b70f42; WORD $0x1a02 // movzx eax, word [rdx + r8 + 26] + LONG $0x4cc40f66; WORD $0x0c3a; BYTE $0x07 // pinsrw xmm1, word [rdx + rdi + 12], 7 LONG $0xc7eb0f66 // por xmm0, xmm7 LONG $0x6f0f4166; BYTE $0xe7 // movdqa xmm4, xmm15 LONG $0xe2650f66 // pcmpgtw xmm4, xmm2 LONG $0x6f0f4166; BYTE $0xff // movdqa xmm7, xmm15 LONG $0xf9650f66 // pcmpgtw xmm7, xmm1 LONG $0x4c6e0f66; WORD $0x1824 // movd xmm1, dword [rsp + 24] - LONG $0x54b70f46; WORD $0x1c0a // movzx r10d, word [rdx + r9 + 28] + LONG $0x54b70f46; WORD $0x1c02 // movzx r10d, word [rdx + r8 + 28] QUAD $0x010e3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 14], 1 - QUAD $0x020e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 14], 2 + QUAD $0x020e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 14], 2 QUAD $0x030e225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 14], 3 QUAD $0x040e2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 14], 4 LONG $0x5cc40f66; WORD $0x0e0a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 14], 5 - LONG $0x5cc40f66; WORD $0x0e3a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 14], 6 - LONG $0x5cc40f66; WORD $0x0e1a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 14], 7 + LONG $0x5cc40f66; WORD $0x0e1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 14], 6 + LONG $0x5cc40f66; WORD $0x0e3a; BYTE $0x07 // pinsrw xmm3, word [rdx + rdi + 14], 7 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 LONG $0xf4710f66; BYTE $0x05 // psllw xmm4, 5 @@ -44821,22 +44214,22 @@ LBB8_198: LONG $0x6f0f4566; BYTE $0xcf // movdqa xmm9, xmm15 LONG $0x650f4466; BYTE $0xcb // pcmpgtw xmm9, xmm3 LONG $0x6e0f4166; BYTE $0xde // movd xmm3, r14d - LONG $0x74b70f46; WORD $0x1e0a // movzx r14d, word [rdx + r9 + 30] + LONG $0x74b70f46; WORD $0x1e02 // movzx r14d, word [rdx + r8 + 30] LONG $0x630f4566; BYTE $0xc9 // packsswb xmm9, xmm9 LONG $0x710f4166; WORD $0x07f1 // psllw xmm9, 7 LONG $0x556f0f66; BYTE $0x60 // movdqa xmm2, oword 96[rbp] /* [rip + .LCPI8_6] */ LONG $0xdb0f4466; BYTE $0xca // pand xmm9, xmm2 LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 LONG $0xe66e0f66 // movd xmm4, esi - LONG $0x74b70f42; WORD $0x220a // movzx esi, word [rdx + r9 + 34] + LONG $0x74b70f42; WORD $0x2202 // movzx esi, word [rdx + r8 + 34] LONG $0x18247489 // mov dword [rsp + 24], esi QUAD $0x01123a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 18], 1 - QUAD $0x0212024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 18], 2 + QUAD $0x02120a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 18], 2 QUAD $0x0312224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 18], 3 QUAD $0x04122a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 18], 4 LONG $0x4cc40f66; WORD $0x120a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 18], 5 - LONG $0x4cc40f66; WORD $0x123a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 18], 6 - LONG $0x4cc40f66; WORD $0x121a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 18], 7 + LONG $0x4cc40f66; WORD $0x121a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 18], 6 + LONG $0x4cc40f66; WORD $0x123a; BYTE $0x07 // pinsrw xmm1, word [rdx + rdi + 18], 7 LONG $0xeb0f4466; BYTE $0xc8 // por xmm9, xmm0 LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 LONG $0xc1650f66 // pcmpgtw xmm0, xmm1 @@ -44845,36 +44238,36 @@ LBB8_198: LONG $0xdb0f4166; BYTE $0xc8 // pand xmm1, xmm8 LONG $0xc8f80f66 // psubb xmm1, xmm0 LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d - LONG $0x74b70f42; WORD $0x240a // movzx esi, word [rdx + r9 + 36] - LONG $0x08247489 // mov dword [rsp + 8], esi + LONG $0x74b70f42; WORD $0x2402 // movzx esi, word [rdx + r8 + 36] + LONG $0x10247489 // mov dword [rsp + 16], esi LONG $0x630f4566; BYTE $0xd2 // packsswb xmm10, xmm10 QUAD $0x01143a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 20], 1 - QUAD $0x0214025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 20], 2 + QUAD $0x02140a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 20], 2 QUAD $0x0314225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 20], 3 QUAD $0x04142a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 20], 4 LONG $0x5cc40f66; WORD $0x140a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 20], 5 - LONG $0x5cc40f66; WORD $0x143a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 20], 6 - LONG $0x5cc40f66; WORD $0x141a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 20], 7 + LONG $0x5cc40f66; WORD $0x141a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 20], 6 + LONG $0x5cc40f66; WORD $0x143a; BYTE $0x07 // pinsrw xmm3, word [rdx + rdi + 20], 7 QUAD $0x01163a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 22], 1 - QUAD $0x02160264c40f4266 // pinsrw xmm4, word [rdx + r8 + 22], 2 + QUAD $0x02160a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 22], 2 QUAD $0x03162264c40f4266 // pinsrw xmm4, word [rdx + r12 + 22], 3 QUAD $0x04162a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 22], 4 LONG $0x64c40f66; WORD $0x160a; BYTE $0x05 // pinsrw xmm4, word [rdx + rcx + 22], 5 - LONG $0x64c40f66; WORD $0x163a; BYTE $0x06 // pinsrw xmm4, word [rdx + rdi + 22], 6 - LONG $0x64c40f66; WORD $0x161a; BYTE $0x07 // pinsrw xmm4, word [rdx + rbx + 22], 7 + LONG $0x64c40f66; WORD $0x161a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 22], 6 + LONG $0x64c40f66; WORD $0x163a; BYTE $0x07 // pinsrw xmm4, word [rdx + rdi + 22], 7 QUAD $0x01183a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 24], 1 - QUAD $0x0218027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 24], 2 + QUAD $0x02180a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 24], 2 QUAD $0x0318227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 24], 3 QUAD $0x04182a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 24], 4 LONG $0x7cc40f66; WORD $0x180a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 24], 5 - LONG $0x7cc40f66; WORD $0x183a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 24], 6 - LONG $0x7cc40f66; WORD $0x181a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 24], 7 + LONG $0x7cc40f66; WORD $0x181a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 24], 6 + LONG $0x7cc40f66; WORD $0x183a; BYTE $0x07 // pinsrw xmm7, word [rdx + rdi + 24], 7 LONG $0xdb0f4566; BYTE $0xd0 // pand xmm10, xmm8 LONG $0xeb0f4166; BYTE $0xca // por xmm1, xmm10 LONG $0x6f0f4166; BYTE $0xd7 // movdqa xmm2, xmm15 LONG $0xd3650f66 // pcmpgtw xmm2, xmm3 LONG $0xd86e0f66 // movd xmm3, eax - LONG $0x5cb70f46; WORD $0x260a // movzx r11d, word [rdx + r9 + 38] + LONG $0x5cb70f46; WORD $0x2602 // movzx r11d, word [rdx + r8 + 38] LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd0 // pand xmm2, xmm8 LONG $0xf2710f66; BYTE $0x02 // psllw xmm2, 2 @@ -44886,21 +44279,21 @@ LBB8_198: LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 LONG $0xc7650f66 // pcmpgtw xmm0, xmm7 LONG $0x6e0f4166; BYTE $0xe2 // movd xmm4, r10d - LONG $0x54b70f46; WORD $0x280a // movzx r10d, word [rdx + r9 + 40] + LONG $0x54b70f46; WORD $0x2802 // movzx r10d, word [rdx + r8 + 40] QUAD $0x011a3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 26], 1 - QUAD $0x021a025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 26], 2 + QUAD $0x021a0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 26], 2 QUAD $0x031a225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 26], 3 QUAD $0x041a2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 26], 4 LONG $0x5cc40f66; WORD $0x1a0a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 26], 5 - LONG $0x5cc40f66; WORD $0x1a3a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 26], 6 - LONG $0x5cc40f66; WORD $0x1a1a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 26], 7 + LONG $0x5cc40f66; WORD $0x1a1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 26], 6 + LONG $0x5cc40f66; WORD $0x1a3a; BYTE $0x07 // pinsrw xmm3, word [rdx + rdi + 26], 7 QUAD $0x011c3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 28], 1 - QUAD $0x021c0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 28], 2 + QUAD $0x021c0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 28], 2 QUAD $0x031c2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 28], 3 QUAD $0x041c2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 28], 4 LONG $0x64c40f66; WORD $0x1c0a; BYTE $0x05 // pinsrw xmm4, word [rdx + rcx + 28], 5 - LONG $0x64c40f66; WORD $0x1c3a; BYTE $0x06 // pinsrw xmm4, word [rdx + rdi + 28], 6 - LONG $0x64c40f66; WORD $0x1c1a; BYTE $0x07 // pinsrw xmm4, word [rdx + rbx + 28], 7 + LONG $0x64c40f66; WORD $0x1c1a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 28], 6 + LONG $0x64c40f66; WORD $0x1c3a; BYTE $0x07 // pinsrw xmm4, word [rdx + rdi + 28], 7 LONG $0xc9630f66 // packsswb xmm1, xmm1 LONG $0xdb0f4166; BYTE $0xc8 // pand xmm1, xmm8 LONG $0xf1710f66; BYTE $0x03 // psllw xmm1, 3 @@ -44913,21 +44306,21 @@ LBB8_198: LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 LONG $0xc1eb0f66 // por xmm0, xmm1 LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d - LONG $0x44b70f42; WORD $0x2a0a // movzx eax, word [rdx + r9 + 42] + LONG $0x44b70f42; WORD $0x2a02 // movzx eax, word [rdx + r8 + 42] LONG $0xc2eb0f66 // por xmm0, xmm2 LONG $0x6f0f4166; BYTE $0xd7 // movdqa xmm2, xmm15 LONG $0xd3650f66 // pcmpgtw xmm2, xmm3 LONG $0x6f0f4166; BYTE $0xff // movdqa xmm7, xmm15 LONG $0xfc650f66 // pcmpgtw xmm7, xmm4 LONG $0x646e0f66; WORD $0x1824 // movd xmm4, dword [rsp + 24] - LONG $0x74b70f46; WORD $0x2c0a // movzx r14d, word [rdx + r9 + 44] + LONG $0x74b70f46; WORD $0x2c02 // movzx r14d, word [rdx + r8 + 44] QUAD $0x011e3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 30], 1 - QUAD $0x021e024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 30], 2 + QUAD $0x021e0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 30], 2 QUAD $0x031e224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 30], 3 QUAD $0x041e2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 30], 4 LONG $0x4cc40f66; WORD $0x1e0a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 30], 5 - LONG $0x4cc40f66; WORD $0x1e3a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 30], 6 - LONG $0x4cc40f66; WORD $0x1e1a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 30], 7 + LONG $0x4cc40f66; WORD $0x1e1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 30], 6 + LONG $0x4cc40f66; WORD $0x1e3a; BYTE $0x07 // pinsrw xmm1, word [rdx + rdi + 30], 7 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd0 // pand xmm2, xmm8 LONG $0xf2710f66; BYTE $0x05 // psllw xmm2, 5 @@ -44940,8 +44333,8 @@ LBB8_198: LONG $0xfaeb0f66 // por xmm7, xmm2 LONG $0x6f0f4566; BYTE $0xd7 // movdqa xmm10, xmm15 LONG $0x650f4466; BYTE $0xd1 // pcmpgtw xmm10, xmm1 - LONG $0x4c6e0f66; WORD $0x0824 // movd xmm1, dword [rsp + 8] - LONG $0x74b70f42; WORD $0x2e0a // movzx esi, word [rdx + r9 + 46] + LONG $0x4c6e0f66; WORD $0x1024 // movd xmm1, dword [rsp + 16] + LONG $0x74b70f42; WORD $0x2e02 // movzx esi, word [rdx + r8 + 46] LONG $0x18247489 // mov dword [rsp + 24], esi LONG $0x630f4566; BYTE $0xd2 // packsswb xmm10, xmm10 LONG $0x710f4166; WORD $0x07f2 // psllw xmm10, 7 @@ -44949,14 +44342,14 @@ LBB8_198: LONG $0xdb0f4566; BYTE $0xd6 // pand xmm10, xmm14 LONG $0xeb0f4466; BYTE $0xd7 // por xmm10, xmm7 LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d - LONG $0x5cb70f46; WORD $0x320a // movzx r11d, word [rdx + r9 + 50] + LONG $0x5cb70f46; WORD $0x3202 // movzx r11d, word [rdx + r8 + 50] QUAD $0x01223a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 34], 1 - QUAD $0x02220264c40f4266 // pinsrw xmm4, word [rdx + r8 + 34], 2 + QUAD $0x02220a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 34], 2 QUAD $0x03222264c40f4266 // pinsrw xmm4, word [rdx + r12 + 34], 3 QUAD $0x04222a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 34], 4 LONG $0x64c40f66; WORD $0x220a; BYTE $0x05 // pinsrw xmm4, word [rdx + rcx + 34], 5 - LONG $0x64c40f66; WORD $0x223a; BYTE $0x06 // pinsrw xmm4, word [rdx + rdi + 34], 6 - LONG $0x64c40f66; WORD $0x221a; BYTE $0x07 // pinsrw xmm4, word [rdx + rbx + 34], 7 + LONG $0x64c40f66; WORD $0x221a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 34], 6 + LONG $0x64c40f66; WORD $0x223a; BYTE $0x07 // pinsrw xmm4, word [rdx + rdi + 34], 7 LONG $0xeb0f4466; BYTE $0xd0 // por xmm10, xmm0 LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 LONG $0xc4650f66 // pcmpgtw xmm0, xmm4 @@ -44965,36 +44358,36 @@ LBB8_198: LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 LONG $0xe0f80f66 // psubb xmm4, xmm0 LONG $0x6e0f4166; BYTE $0xc2 // movd xmm0, r10d - LONG $0x74b70f42; WORD $0x340a // movzx esi, word [rdx + r9 + 52] - LONG $0x08247489 // mov dword [rsp + 8], esi + LONG $0x74b70f42; WORD $0x3402 // movzx esi, word [rdx + r8 + 52] + LONG $0x10247489 // mov dword [rsp + 16], esi LONG $0xf6630f66 // packsswb xmm6, xmm6 QUAD $0x01243a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 36], 1 - QUAD $0x0224024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 36], 2 + QUAD $0x02240a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 36], 2 QUAD $0x0324224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 36], 3 QUAD $0x04242a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 36], 4 LONG $0x4cc40f66; WORD $0x240a; BYTE $0x05 // pinsrw xmm1, word [rdx + rcx + 36], 5 - LONG $0x4cc40f66; WORD $0x243a; BYTE $0x06 // pinsrw xmm1, word [rdx + rdi + 36], 6 - LONG $0x4cc40f66; WORD $0x241a; BYTE $0x07 // pinsrw xmm1, word [rdx + rbx + 36], 7 + LONG $0x4cc40f66; WORD $0x241a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 36], 6 + LONG $0x4cc40f66; WORD $0x243a; BYTE $0x07 // pinsrw xmm1, word [rdx + rdi + 36], 7 QUAD $0x01263a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 38], 1 - QUAD $0x02260254c40f4266 // pinsrw xmm2, word [rdx + r8 + 38], 2 + QUAD $0x02260a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 38], 2 QUAD $0x03262254c40f4266 // pinsrw xmm2, word [rdx + r12 + 38], 3 QUAD $0x04262a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 38], 4 LONG $0x54c40f66; WORD $0x260a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 38], 5 - LONG $0x54c40f66; WORD $0x263a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 38], 6 - LONG $0x54c40f66; WORD $0x261a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 38], 7 + LONG $0x54c40f66; WORD $0x261a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 38], 6 + LONG $0x54c40f66; WORD $0x263a; BYTE $0x07 // pinsrw xmm2, word [rdx + rdi + 38], 7 QUAD $0x01283a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 40], 1 - QUAD $0x02280244c40f4266 // pinsrw xmm0, word [rdx + r8 + 40], 2 + QUAD $0x02280a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 40], 2 QUAD $0x03282244c40f4266 // pinsrw xmm0, word [rdx + r12 + 40], 3 QUAD $0x04282a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 40], 4 LONG $0x44c40f66; WORD $0x280a; BYTE $0x05 // pinsrw xmm0, word [rdx + rcx + 40], 5 - LONG $0x44c40f66; WORD $0x283a; BYTE $0x06 // pinsrw xmm0, word [rdx + rdi + 40], 6 + LONG $0x44c40f66; WORD $0x281a; BYTE $0x06 // pinsrw xmm0, word [rdx + rbx + 40], 6 LONG $0xdb0f4166; BYTE $0xf0 // pand xmm6, xmm8 LONG $0xe6eb0f66 // por xmm4, xmm6 LONG $0x6f0f4166; BYTE $0xf7 // movdqa xmm6, xmm15 LONG $0xf1650f66 // pcmpgtw xmm6, xmm1 LONG $0xf86e0f66 // movd xmm7, eax - LONG $0x54b70f46; WORD $0x360a // movzx r10d, word [rdx + r9 + 54] - LONG $0x44c40f66; WORD $0x281a; BYTE $0x07 // pinsrw xmm0, word [rdx + rbx + 40], 7 + LONG $0x54b70f46; WORD $0x3602 // movzx r10d, word [rdx + r8 + 54] + LONG $0x44c40f66; WORD $0x283a; BYTE $0x07 // pinsrw xmm0, word [rdx + rdi + 40], 7 LONG $0xf6630f66 // packsswb xmm6, xmm6 LONG $0xdb0f4166; BYTE $0xf0 // pand xmm6, xmm8 LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 @@ -45005,20 +44398,20 @@ LBB8_198: LONG $0x6f0f4166; BYTE $0xcf // movdqa xmm1, xmm15 LONG $0xc8650f66 // pcmpgtw xmm1, xmm0 LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d - LONG $0x44b70f42; WORD $0x380a // movzx eax, word [rdx + r9 + 56] + LONG $0x44b70f42; WORD $0x3802 // movzx eax, word [rdx + r8 + 56] QUAD $0x012a3a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 42], 1 - QUAD $0x022a027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 42], 2 + QUAD $0x022a0a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 42], 2 QUAD $0x032a227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 42], 3 QUAD $0x042a2a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 42], 4 LONG $0x7cc40f66; WORD $0x2a0a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 42], 5 - LONG $0x7cc40f66; WORD $0x2a3a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 42], 6 - LONG $0x7cc40f66; WORD $0x2a1a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 42], 7 + LONG $0x7cc40f66; WORD $0x2a1a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 42], 6 + LONG $0x7cc40f66; WORD $0x2a3a; BYTE $0x07 // pinsrw xmm7, word [rdx + rdi + 42], 7 QUAD $0x012c3a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 44], 1 - QUAD $0x022c0244c40f4266 // pinsrw xmm0, word [rdx + r8 + 44], 2 + QUAD $0x022c0a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 44], 2 QUAD $0x032c2244c40f4266 // pinsrw xmm0, word [rdx + r12 + 44], 3 QUAD $0x042c2a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 44], 4 LONG $0x44c40f66; WORD $0x2c0a; BYTE $0x05 // pinsrw xmm0, word [rdx + rcx + 44], 5 - LONG $0x44c40f66; WORD $0x2c3a; BYTE $0x06 // pinsrw xmm0, word [rdx + rdi + 44], 6 + LONG $0x44c40f66; WORD $0x2c1a; BYTE $0x06 // pinsrw xmm0, word [rdx + rbx + 44], 6 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 LONG $0xf4710f66; BYTE $0x03 // psllw xmm4, 3 @@ -45030,23 +44423,23 @@ LBB8_198: LONG $0x6f0f4566; BYTE $0xec // movdqa xmm13, xmm12 LONG $0xcceb0f66 // por xmm1, xmm4 LONG $0x546e0f66; WORD $0x1824 // movd xmm2, dword [rsp + 24] - LONG $0x74b70f42; WORD $0x3a0a // movzx esi, word [rdx + r9 + 58] - LONG $0x44c40f66; WORD $0x2c1a; BYTE $0x07 // pinsrw xmm0, word [rdx + rbx + 44], 7 + LONG $0x74b70f42; WORD $0x3a02 // movzx esi, word [rdx + r8 + 58] + LONG $0x44c40f66; WORD $0x2c3a; BYTE $0x07 // pinsrw xmm0, word [rdx + rdi + 44], 7 LONG $0xceeb0f66 // por xmm1, xmm6 LONG $0x6f0f4166; BYTE $0xe7 // movdqa xmm4, xmm15 LONG $0xe7650f66 // pcmpgtw xmm4, xmm7 LONG $0x6f0f4166; BYTE $0xf7 // movdqa xmm6, xmm15 LONG $0xf0650f66 // pcmpgtw xmm6, xmm0 LONG $0x6e0f4166; BYTE $0xfb // movd xmm7, r11d - LONG $0x5cb70f46; WORD $0x3c0a // movzx r11d, word [rdx + r9 + 60] + LONG $0x5cb70f46; WORD $0x3c02 // movzx r11d, word [rdx + r8 + 60] QUAD $0x012e3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 46], 1 - QUAD $0x022e0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 46], 2 + QUAD $0x022e0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 46], 2 QUAD $0x032e2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 46], 3 QUAD $0x042e2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 46], 4 LONG $0x54c40f66; WORD $0x2e0a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 46], 5 - LONG $0x54c40f66; WORD $0x2e3a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 46], 6 - LONG $0x4cb70f46; WORD $0x3e0a // movzx r9d, word [rdx + r9 + 62] - LONG $0x54c40f66; WORD $0x2e1a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 46], 7 + LONG $0x54c40f66; WORD $0x2e1a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 46], 6 + LONG $0x44b70f46; WORD $0x3e02 // movzx r8d, word [rdx + r8 + 62] + LONG $0x54c40f66; WORD $0x2e3a; BYTE $0x07 // pinsrw xmm2, word [rdx + rdi + 46], 7 LONG $0xe4630f66 // packsswb xmm4, xmm4 LONG $0xdb0f4166; BYTE $0xe0 // pand xmm4, xmm8 LONG $0xf4710f66; BYTE $0x05 // psllw xmm4, 5 @@ -45059,14 +44452,14 @@ LBB8_198: LONG $0xf4eb0f66 // por xmm6, xmm4 LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 LONG $0xc2650f66 // pcmpgtw xmm0, xmm2 - LONG $0x546e0f66; WORD $0x0824 // movd xmm2, dword [rsp + 8] + LONG $0x546e0f66; WORD $0x1024 // movd xmm2, dword [rsp + 16] QUAD $0x01323a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 50], 1 - QUAD $0x0232027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 50], 2 + QUAD $0x02320a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 50], 2 QUAD $0x0332227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 50], 3 QUAD $0x04322a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 50], 4 LONG $0x7cc40f66; WORD $0x320a; BYTE $0x05 // pinsrw xmm7, word [rdx + rcx + 50], 5 - LONG $0x7cc40f66; WORD $0x323a; BYTE $0x06 // pinsrw xmm7, word [rdx + rdi + 50], 6 - LONG $0x7cc40f66; WORD $0x321a; BYTE $0x07 // pinsrw xmm7, word [rdx + rbx + 50], 7 + LONG $0x7cc40f66; WORD $0x321a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 50], 6 + LONG $0x7cc40f66; WORD $0x323a; BYTE $0x07 // pinsrw xmm7, word [rdx + rdi + 50], 7 LONG $0xc0630f66 // packsswb xmm0, xmm0 LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 @@ -45082,38 +44475,38 @@ LBB8_198: LONG $0xd86e0f66 // movd xmm3, eax LONG $0xed630f66 // packsswb xmm5, xmm5 QUAD $0x01343a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 52], 1 - QUAD $0x02340254c40f4266 // pinsrw xmm2, word [rdx + r8 + 52], 2 + QUAD $0x02340a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 52], 2 QUAD $0x03342254c40f4266 // pinsrw xmm2, word [rdx + r12 + 52], 3 QUAD $0x04342a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 52], 4 LONG $0x54c40f66; WORD $0x340a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 52], 5 - LONG $0x54c40f66; WORD $0x343a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 52], 6 + LONG $0x54c40f66; WORD $0x341a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 52], 6 LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 - LONG $0x54c40f66; WORD $0x341a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 52], 7 + LONG $0x54c40f66; WORD $0x343a; BYTE $0x07 // pinsrw xmm2, word [rdx + rdi + 52], 7 LONG $0xfdeb0f66 // por xmm7, xmm5 LONG $0x6f0f4166; BYTE $0xef // movdqa xmm5, xmm15 LONG $0xea650f66 // pcmpgtw xmm5, xmm2 LONG $0xe66e0f66 // movd xmm4, esi QUAD $0x01363a74c40f4266 // pinsrw xmm6, word [rdx + r15 + 54], 1 - QUAD $0x02360274c40f4266 // pinsrw xmm6, word [rdx + r8 + 54], 2 + QUAD $0x02360a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 54], 2 QUAD $0x03362274c40f4266 // pinsrw xmm6, word [rdx + r12 + 54], 3 QUAD $0x04362a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 54], 4 LONG $0x74c40f66; WORD $0x360a; BYTE $0x05 // pinsrw xmm6, word [rdx + rcx + 54], 5 - LONG $0x74c40f66; WORD $0x363a; BYTE $0x06 // pinsrw xmm6, word [rdx + rdi + 54], 6 - LONG $0x74c40f66; WORD $0x361a; BYTE $0x07 // pinsrw xmm6, word [rdx + rbx + 54], 7 + LONG $0x74c40f66; WORD $0x361a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 54], 6 + LONG $0x74c40f66; WORD $0x363a; BYTE $0x07 // pinsrw xmm6, word [rdx + rdi + 54], 7 QUAD $0x01383a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 56], 1 - QUAD $0x0238025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 56], 2 + QUAD $0x02380a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 56], 2 QUAD $0x0338225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 56], 3 QUAD $0x04382a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 56], 4 LONG $0x5cc40f66; WORD $0x380a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 56], 5 - LONG $0x5cc40f66; WORD $0x383a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 56], 6 - LONG $0x5cc40f66; WORD $0x381a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 56], 7 + LONG $0x5cc40f66; WORD $0x381a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 56], 6 + LONG $0x5cc40f66; WORD $0x383a; BYTE $0x07 // pinsrw xmm3, word [rdx + rdi + 56], 7 QUAD $0x013a3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 58], 1 - QUAD $0x023a0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 58], 2 + QUAD $0x023a0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 58], 2 QUAD $0x033a2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 58], 3 QUAD $0x043a2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 58], 4 LONG $0x64c40f66; WORD $0x3a0a; BYTE $0x05 // pinsrw xmm4, word [rdx + rcx + 58], 5 - LONG $0x64c40f66; WORD $0x3a3a; BYTE $0x06 // pinsrw xmm4, word [rdx + rdi + 58], 6 - LONG $0x64c40f66; WORD $0x3a1a; BYTE $0x07 // pinsrw xmm4, word [rdx + rbx + 58], 7 + LONG $0x64c40f66; WORD $0x3a1a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 58], 6 + LONG $0x64c40f66; WORD $0x3a3a; BYTE $0x07 // pinsrw xmm4, word [rdx + rdi + 58], 7 LONG $0xed630f66 // packsswb xmm5, xmm5 LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 @@ -45125,12 +44518,12 @@ LBB8_198: LONG $0xcb650f66 // pcmpgtw xmm1, xmm3 LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d QUAD $0x013c3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 60], 1 - QUAD $0x023c025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 60], 2 + QUAD $0x023c0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 60], 2 QUAD $0x033c225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 60], 3 QUAD $0x043c2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 60], 4 LONG $0x5cc40f66; WORD $0x3c0a; BYTE $0x05 // pinsrw xmm3, word [rdx + rcx + 60], 5 - LONG $0x5cc40f66; WORD $0x3c3a; BYTE $0x06 // pinsrw xmm3, word [rdx + rdi + 60], 6 - LONG $0x5cc40f66; WORD $0x3c1a; BYTE $0x07 // pinsrw xmm3, word [rdx + rbx + 60], 7 + LONG $0x5cc40f66; WORD $0x3c1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 60], 6 + LONG $0x5cc40f66; WORD $0x3c3a; BYTE $0x07 // pinsrw xmm3, word [rdx + rdi + 60], 7 LONG $0xd2630f66 // packsswb xmm2, xmm2 LONG $0xdb0f4166; BYTE $0xd0 // pand xmm2, xmm8 LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 @@ -45140,15 +44533,15 @@ LBB8_198: LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0x6e0f4166; BYTE $0xd1 // movd xmm2, r9d + LONG $0x6e0f4166; BYTE $0xd0 // movd xmm2, r8d QUAD $0x013e3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 62], 1 - QUAD $0x023e0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 62], 2 + QUAD $0x023e0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 62], 2 QUAD $0x033e2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 62], 3 QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] QUAD $0x043e2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 62], 4 LONG $0x54c40f66; WORD $0x3e0a; BYTE $0x05 // pinsrw xmm2, word [rdx + rcx + 62], 5 - LONG $0x54c40f66; WORD $0x3e3a; BYTE $0x06 // pinsrw xmm2, word [rdx + rdi + 62], 6 - LONG $0x54c40f66; WORD $0x3e1a; BYTE $0x07 // pinsrw xmm2, word [rdx + rbx + 62], 7 + LONG $0x54c40f66; WORD $0x3e1a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 62], 6 + LONG $0x54c40f66; WORD $0x3e3a; BYTE $0x07 // pinsrw xmm2, word [rdx + rdi + 62], 7 LONG $0xcdeb0f66 // por xmm1, xmm5 LONG $0x6f0f4166; BYTE $0xef // movdqa xmm5, xmm15 LONG $0xec650f66 // pcmpgtw xmm5, xmm4 @@ -45181,33 +44574,32 @@ LBB8_198: LONG $0xc3600f66 // punpcklbw xmm0, xmm3 LONG $0x600f4566; BYTE $0xca // punpcklbw xmm9, xmm10 LONG $0x610f4466; BYTE $0xc8 // punpcklwd xmm9, xmm0 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] LONG $0x7f0f45f3; WORD $0x8e0c // movdqu oword [r14 + 4*rcx], xmm9 LONG $0x7f0f41f3; WORD $0x8e4c; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm1 LONG $0x08c18348 // add rcx, 8 - WORD $0x8949; BYTE $0xc9 // mov r9, rcx + WORD $0x8949; BYTE $0xc8 // mov r8, rcx LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB8_198 - QUAD $0x000000f024bc8b4c // mov r15, qword [rsp + 240] - LONG $0x247c3b4c; BYTE $0x20 // cmp r15, qword [rsp + 32] - QUAD $0x0000008824948b4c // mov r10, qword [rsp + 136] - LONG $0x246c8b44; BYTE $0x30 // mov r13d, dword [rsp + 48] - LONG $0x24248b4c // mov r12, qword [rsp] - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - JNE LBB8_101 - JMP LBB8_136 + JNE LBB8_217 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + LONG $0x246c8b44; BYTE $0x28 // mov r13d, dword [rsp + 40] + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + JNE LBB8_81 + JMP LBB8_131 -LBB8_200: - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - LONG $0xfce08349 // and r8, -4 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 +LBB8_219: + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0xfce18349 // and r9, -4 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 LONG $0x07e3c148 // shl rbx, 7 WORD $0x0148; BYTE $0xd3 // add rbx, rdx - LONG $0x863c8d4f // lea r15, [r14 + 4*r8] - WORD $0x280f; BYTE $0xc8 // movaps xmm1, xmm0 + LONG $0x8e1c8d4f // lea r11, [r14 + 4*r9] + LONG $0xc86f0f66 // movdqa xmm1, xmm0 LONG $0x00c8c60f // shufps xmm1, xmm0, 0 LONG $0xfcc28148; WORD $0x0001; BYTE $0x00 // add rdx, 508 - WORD $0xc931 // xor ecx, ecx + WORD $0xf631 // xor esi, esi LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI8_0] */ LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI8_1] */ LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI8_2] */ @@ -45217,7 +44609,7 @@ LBB8_200: LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI8_6] */ LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI8_7] */ -LBB8_201: +LBB8_220: QUAD $0xfffffe04b2100ff3 // movss xmm6, dword [rdx - 508] QUAD $0xfffffe08ba100ff3 // movss xmm7, dword [rdx - 504] QUAD $0xfffffe0caa100ff3 // movss xmm5, dword [rdx - 500] @@ -45553,19 +44945,1933 @@ LBB8_201: LONG $0xdb630f66 // packsswb xmm3, xmm3 LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0xdeeb0f66 // por xmm3, xmm6 - LONG $0xeb620f66 // punpckldq xmm5, xmm3 - LONG $0xe5600f66 // punpcklbw xmm4, xmm5 - LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0xdeeb0f66 // por xmm3, xmm6 + LONG $0xeb620f66 // punpckldq xmm5, xmm3 + LONG $0xe5600f66 // punpcklbw xmm4, xmm5 + LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 + LONG $0x7f0f41f3; WORD $0xb624 // movdqu oword [r14 + 4*rsi], xmm4 + LONG $0x04c68348 // add rsi, 4 + LONG $0x00c28148; WORD $0x0002; BYTE $0x00 // add rdx, 512 + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB8_220 + WORD $0x394c; BYTE $0xc9 // cmp rcx, r9 + JNE LBB8_108 + JMP LBB8_135 + +LBB8_222: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + QUAD $0x0000010824848948 // mov qword [rsp + 264], rax + QUAD $0x000000f8248c8948 // mov qword [rsp + 248], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + LONG $0xc7b60f41 // movzx eax, r15b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x000120248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm1 + WORD $0xc031 // xor eax, eax + QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 + +LBB8_223: + WORD $0x8949; BYTE $0xc1 // mov r9, rax + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + LONG $0x05e0c148 // shl rax, 5 + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc3 // mov r11, rax + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + WORD $0x8949; BYTE $0xc5 // mov r13, rax + WORD $0x8949; BYTE $0xc6 // mov r14, rax + WORD $0x8949; BYTE $0xc0 // mov r8, rax + WORD $0x8949; BYTE $0xc4 // mov r12, rax + WORD $0x8949; BYTE $0xc2 // mov r10, rax + WORD $0x8949; BYTE $0xc7 // mov r15, rax + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x070cb60f // movzx ecx, byte [rdi + rax] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x074cb60f; BYTE $0x01 // movzx ecx, byte [rdi + rax + 1] + LONG $0xf96e0f66 // movd xmm7, ecx + LONG $0x074cb60f; BYTE $0x02 // movzx ecx, byte [rdi + rax + 2] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x074cb60f; BYTE $0x03 // movzx ecx, byte [rdi + rax + 3] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x074cb60f; BYTE $0x04 // movzx ecx, byte [rdi + rax + 4] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x074cb60f; BYTE $0x05 // movzx ecx, byte [rdi + rax + 5] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x074cb60f; BYTE $0x06 // movzx ecx, byte [rdi + rax + 6] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 + LONG $0x074cb60f; BYTE $0x07 // movzx ecx, byte [rdi + rax + 7] + LONG $0xc96e0f66 // movd xmm1, ecx + LONG $0x074cb60f; BYTE $0x08 // movzx ecx, byte [rdi + rax + 8] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x074cb60f; BYTE $0x09 // movzx ecx, byte [rdi + rax + 9] + LONG $0xc16e0f66 // movd xmm0, ecx + LONG $0x074cb60f; BYTE $0x0a // movzx ecx, byte [rdi + rax + 10] + LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx + LONG $0x074cb60f; BYTE $0x0b // movzx ecx, byte [rdi + rax + 11] + LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx + LONG $0x074cb60f; BYTE $0x0c // movzx ecx, byte [rdi + rax + 12] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x074cb60f; BYTE $0x10 // movzx ecx, byte [rdi + rax + 16] + LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx + LONG $0x074cb60f; BYTE $0x18 // movzx ecx, byte [rdi + rax + 24] + LONG $0xe16e0f66 // movd xmm4, ecx + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0x20c98348 // or rcx, 32 + LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + LONG $0x40c98349 // or r9, 64 + LONG $0x244c894c; BYTE $0x18 // mov qword [rsp + 24], r9 + LONG $0x60cb8349 // or r11, 96 + QUAD $0x00000090249c894c // mov qword [rsp + 144], r11 + LONG $0x80cb8148; WORD $0x0000; BYTE $0x00 // or rbx, 128 + LONG $0xa0cd8149; WORD $0x0000; BYTE $0x00 // or r13, 160 + QUAD $0x000000a024ac894c // mov qword [rsp + 160], r13 + LONG $0xc0ce8149; WORD $0x0000; BYTE $0x00 // or r14, 192 + LONG $0xe0c88149; WORD $0x0000; BYTE $0x00 // or r8, 224 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x00cd8149; WORD $0x0001; BYTE $0x00 // or r13, 256 + LONG $0x246c894c; BYTE $0x28 // mov qword [rsp + 40], r13 + LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 + LONG $0x40cf8149; WORD $0x0001; BYTE $0x00 // or r15, 320 + LONG $0x60ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 352 + LONG $0x80cc8149; WORD $0x0001; BYTE $0x00 // or r12, 384 + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx + LONG $0xc0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 448 + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0xe0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 480 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x010704203a0f4466 // pinsrb xmm8, byte [rdi + rax], 1 + QUAD $0x020f04203a0f4666 // pinsrb xmm8, byte [rdi + r9], 2 + QUAD $0x031f04203a0f4666 // pinsrb xmm8, byte [rdi + r11], 3 + QUAD $0x041f04203a0f4466 // pinsrb xmm8, byte [rdi + rbx], 4 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x050704203a0f4466 // pinsrb xmm8, byte [rdi + rax], 5 + QUAD $0x063704203a0f4666 // pinsrb xmm8, byte [rdi + r14], 6 + QUAD $0x070704203a0f4666 // pinsrb xmm8, byte [rdi + r8], 7 + QUAD $0x082f04203a0f4666 // pinsrb xmm8, byte [rdi + r13], 8 + QUAD $0x091704203a0f4666 // pinsrb xmm8, byte [rdi + r10], 9 + LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 + QUAD $0x0a3f04203a0f4666 // pinsrb xmm8, byte [rdi + r15], 10 + QUAD $0x0b3704203a0f4466 // pinsrb xmm8, byte [rdi + rsi], 11 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x0c2704203a0f4666 // pinsrb xmm8, byte [rdi + r12], 12 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x0d2704203a0f4666 // pinsrb xmm8, byte [rdi + r12], 13 + QUAD $0x0e1704203a0f4466 // pinsrb xmm8, byte [rdi + rdx], 14 + QUAD $0x0f0f04203a0f4466 // pinsrb xmm8, byte [rdi + rcx], 15 + QUAD $0x012024ac6f0f4466; WORD $0x0000 // movdqa xmm13, oword [rsp + 288] + LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0101077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 1], 1 + QUAD $0x010f7c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rdi + r9 + 1], 2 + QUAD $0x011f7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r11 + 1], 3 + QUAD $0x04011f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 1], 4 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x012f7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdi + r13 + 1], 5 + QUAD $0x01377c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r14 + 1], 6 + QUAD $0x01077c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r8 + 1], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0801077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 1], 8 + QUAD $0x01177c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdi + r10 + 1], 9 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0a01077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 1], 10 + QUAD $0x0b01377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 1], 11 + QUAD $0x013f7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdi + r15 + 1], 12 + QUAD $0x01277c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rdi + r12 + 1], 13 + QUAD $0x0e01177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 1], 14 + QUAD $0x0f010f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 1], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x01020774203a0f66 // pinsrb xmm6, byte [rdi + rax + 2], 1 + QUAD $0x020f74203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdi + r9 + 2], 2 + QUAD $0x021f74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r11 + 2], 3 + QUAD $0x04021f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 2], 4 + QUAD $0x022f74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdi + r13 + 2], 5 + QUAD $0x023774203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r14 + 2], 6 + QUAD $0x020774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r8 + 2], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x08020774203a0f66 // pinsrb xmm6, byte [rdi + rax + 2], 8 + QUAD $0x021774203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r10 + 2], 9 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0a020774203a0f66 // pinsrb xmm6, byte [rdi + rax + 2], 10 + QUAD $0x0b023774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 2], 11 + QUAD $0x023f74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r15 + 2], 12 + QUAD $0x022774203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdi + r12 + 2], 13 + QUAD $0x0e021774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 2], 14 + QUAD $0x0f020f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 2], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x080764203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdi + rax + 8], 1 + QUAD $0x080f64203a0f4666; BYTE $0x02 // pinsrb xmm12, byte [rdi + r9 + 8], 2 + QUAD $0x081f64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdi + r11 + 8], 3 + QUAD $0x081f64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdi + rbx + 8], 4 + QUAD $0x082f64203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdi + r13 + 8], 5 + QUAD $0x083764203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdi + r14 + 8], 6 + QUAD $0x080764203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdi + r8 + 8], 7 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x080764203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rdi + rax + 8], 8 + QUAD $0x081764203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdi + r10 + 8], 9 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x080764203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdi + rax + 8], 10 + QUAD $0x083764203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rdi + rsi + 8], 11 + QUAD $0x083f64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdi + r15 + 8], 12 + QUAD $0x082764203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdi + r12 + 8], 13 + QUAD $0x081764203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rdi + rdx + 8], 14 + QUAD $0x080f64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdi + rcx + 8], 15 + LONG $0x640f4166; BYTE $0xd8 // pcmpgtb xmm3, xmm8 + QUAD $0x000110249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm3 + LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 + LONG $0x640f4166; BYTE $0xdc // pcmpgtb xmm3, xmm12 + QUAD $0x000130249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm3 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x102774203a0f4666; BYTE $0x01 // pinsrb xmm14, byte [rdi + r12 + 16], 1 + QUAD $0x100f74203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdi + r9 + 16], 2 + QUAD $0x101f74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdi + r11 + 16], 3 + QUAD $0x101f74203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rdi + rbx + 16], 4 + LONG $0x245c8948; BYTE $0x40 // mov qword [rsp + 64], rbx + QUAD $0x102f74203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rdi + r13 + 16], 5 + QUAD $0x103774203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdi + r14 + 16], 6 + QUAD $0x100774203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdi + r8 + 16], 7 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x102774203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdi + r12 + 16], 8 + QUAD $0x101774203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rdi + r10 + 16], 9 + WORD $0x894d; BYTE $0xd3 // mov r11, r10 + LONG $0x2454894c; BYTE $0x58 // mov qword [rsp + 88], r10 + QUAD $0x100774203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdi + rax + 16], 10 + QUAD $0x103774203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rdi + rsi + 16], 11 + WORD $0x8949; BYTE $0xf2 // mov r10, rsi + QUAD $0x103f74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdi + r15 + 16], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x103774203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdi + rsi + 16], 13 + QUAD $0x101774203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rdi + rdx + 16], 14 + LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx + QUAD $0x100f74203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdi + rcx + 16], 15 + LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x01180764203a0f66 // pinsrb xmm4, byte [rdi + rax + 24], 1 + QUAD $0x180f64203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdi + r9 + 24], 2 + QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] + QUAD $0x180f64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdi + r9 + 24], 3 + QUAD $0x04181f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 24], 4 + QUAD $0x182f64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdi + r13 + 24], 5 + QUAD $0x183764203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r14 + 24], 6 + QUAD $0x180764203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r8 + 24], 7 + LONG $0x2444894c; BYTE $0x38 // mov qword [rsp + 56], r8 + QUAD $0x182764203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdi + r12 + 24], 8 + QUAD $0x181f64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdi + r11 + 24], 9 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0a180764203a0f66 // pinsrb xmm4, byte [rdi + rax + 24], 10 + QUAD $0x181764203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r10 + 24], 11 + WORD $0x894c; BYTE $0xd3 // mov rbx, r10 + QUAD $0x183f64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdi + r15 + 24], 12 + QUAD $0x0d183764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 24], 13 + QUAD $0x0e181764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 24], 14 + WORD $0x8949; BYTE $0xd2 // mov r10, rdx + LONG $0x24548948; BYTE $0x48 // mov qword [rsp + 72], rdx + LONG $0x640f4166; BYTE $0xde // pcmpgtb xmm3, xmm14 + QUAD $0x0000d0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm3 + QUAD $0x0f180f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 24], 15 + LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 + LONG $0xdc640f66 // pcmpgtb xmm3, xmm4 + QUAD $0x0000e0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm3 + LONG $0x6f0f4166; BYTE $0xe5 // movdqa xmm4, xmm13 + LONG $0xe7640f66 // pcmpgtb xmm4, xmm7 + LONG $0x6f0f4466; BYTE $0xe4 // movdqa xmm12, xmm4 + QUAD $0x0000a0856f0f4466; BYTE $0x00 // movdqa xmm8, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xdb0f4566; BYTE $0xe0 // pand xmm12, xmm8 + LONG $0xf80f4466; BYTE $0xe4 // psubb xmm12, xmm4 + LONG $0x6f0f4166; BYTE $0xe5 // movdqa xmm4, xmm13 + LONG $0x6f0f4566; BYTE $0xf5 // movdqa xmm14, xmm13 + LONG $0xe6640f66 // pcmpgtb xmm4, xmm6 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + LONG $0x0774b60f; BYTE $0x0d // movzx esi, byte [rdi + rax + 13] + LONG $0xfe6e0f66 // movd xmm7, esi + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x03377c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdi + rsi + 3], 1 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x03077c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rax + 3], 2 + WORD $0x894d; BYTE $0xcb // mov r11, r9 + QUAD $0x030f7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdi + r9 + 3], 3 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x030f7c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdi + rcx + 3], 4 + WORD $0x894c; BYTE $0xea // mov rdx, r13 + QUAD $0x032f7c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rdi + r13 + 3], 5 + LONG $0x2474894c; BYTE $0x60 // mov qword [rsp + 96], r14 + QUAD $0x03377c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r14 + 3], 6 + QUAD $0x03077c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r8 + 3], 7 + QUAD $0x03277c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdi + r12 + 3], 8 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x030f7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r9 + 3], 9 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x03077c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdi + r8 + 3], 10 + QUAD $0x000000b0249c8948 // mov qword [rsp + 176], rbx + QUAD $0x031f7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rdi + rbx + 3], 11 + QUAD $0x033f7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdi + r15 + 3], 12 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x032f7c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdi + r13 + 3], 13 + QUAD $0x03177c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdi + r10 + 3], 14 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x03177c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r10 + 3], 15 + QUAD $0x0104376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 4], 1 + QUAD $0x0204076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 4], 2 + QUAD $0x041f6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r11 + 4], 3 + QUAD $0x04040f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 4], 4 + QUAD $0x0504176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 4], 5 + QUAD $0x04376c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r14 + 4], 6 + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x07040f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 4], 7 + QUAD $0x04276c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdi + r12 + 4], 8 + QUAD $0x040f6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r9 + 4], 9 + QUAD $0x04076c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r8 + 4], 10 + QUAD $0x0b041f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 4], 11 + QUAD $0x043f6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdi + r15 + 4], 12 + QUAD $0x042f6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdi + r13 + 4], 13 + WORD $0x894c; BYTE $0xea // mov rdx, r13 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0e04076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 4], 14 + QUAD $0x000110249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 272] + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + QUAD $0x000000b0b56f0f66 // movdqa xmm6, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xe6db0f66 // pand xmm4, xmm6 + LONG $0xe3eb0f66 // por xmm4, xmm3 + LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] + LONG $0x74b60f42; WORD $0x0e17 // movzx esi, byte [rdi + r10 + 14] + LONG $0xf66e0f66 // movd xmm6, esi + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x041f6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdi + r11 + 4], 15 + LONG $0xeb0f4166; BYTE $0xe4 // por xmm4, xmm12 + LONG $0x6f0f4566; BYTE $0xe5 // movdqa xmm12, xmm13 + LONG $0x640f4566; BYTE $0xe7 // pcmpgtb xmm12, xmm15 + LONG $0x640f4466; BYTE $0xed // pcmpgtb xmm13, xmm5 + LONG $0x74b60f42; WORD $0x0f17 // movzx esi, byte [rdi + r10 + 15] + LONG $0xee6e0f66 // movd xmm5, esi + LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] + QUAD $0x053754203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdi + r14 + 5], 1 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x02053754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 5], 2 + QUAD $0x0000009024ac8b4c // mov r13, qword [rsp + 144] + QUAD $0x052f54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdi + r13 + 5], 3 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x04053754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 5], 4 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x05051f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 5], 5 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x06053754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 5], 6 + QUAD $0x07050f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 5], 7 + QUAD $0x052754203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdi + r12 + 5], 8 + QUAD $0x050f54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r9 + 5], 9 + QUAD $0x050754203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r8 + 5], 10 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x0b050f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 5], 11 + QUAD $0x053f54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdi + r15 + 5], 12 + QUAD $0x0d051754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 5], 13 + QUAD $0x0e050754203a0f66 // pinsrb xmm2, byte [rdi + rax + 5], 14 + QUAD $0x051f54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r11 + 5], 15 + QUAD $0x000000c09d6f0f66 // movdqa xmm3, oword 192[rbp] /* [rip + .LCPI8_12] */ + LONG $0xdb0f4466; BYTE $0xe3 // pand xmm12, xmm3 + QUAD $0x000000d09d6f0f66 // movdqa xmm3, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xdb0f4466; BYTE $0xeb // pand xmm13, xmm3 + LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 + LONG $0x6f0f4566; BYTE $0xe6 // movdqa xmm12, xmm14 + LONG $0x640f4466; BYTE $0xe2 // pcmpgtb xmm12, xmm2 + LONG $0x74b60f42; WORD $0x1117 // movzx esi, byte [rdi + r10 + 17] + LONG $0xd66e0f66 // movd xmm2, esi + QUAD $0x000000e09d6f0f66 // movdqa xmm3, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xdb0f4466; BYTE $0xe3 // pand xmm12, xmm3 + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x74b60f42; WORD $0x1217 // movzx esi, byte [rdi + r10 + 18] + LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi + QUAD $0x0000c0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 192] + QUAD $0x06375c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdi + r14 + 6], 1 + WORD $0x894c; BYTE $0xf0 // mov rax, r14 + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + QUAD $0x060f5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdi + r9 + 6], 2 + QUAD $0x062f5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r13 + 6], 3 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x04060f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 6], 4 + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x05061f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 6], 5 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0606375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 6], 6 + WORD $0x8949; BYTE $0xf6 // mov r14, rsi + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0706375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 6], 7 + QUAD $0x06275c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdi + r12 + 6], 8 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0906375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 6], 9 + QUAD $0x06075c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdi + r8 + 6], 10 + QUAD $0x000000b0249c8b48 // mov rbx, qword [rsp + 176] + QUAD $0x0b061f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 6], 11 + LONG $0x247c894c; BYTE $0x70 // mov qword [rsp + 112], r15 + QUAD $0x063f5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r15 + 6], 12 + QUAD $0x0d06175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 6], 13 + LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x06175c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdi + r10 + 6], 14 + QUAD $0x061f5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdi + r11 + 6], 15 + QUAD $0x0107074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 7], 1 + QUAD $0x070f4c203a0f4266; BYTE $0x02 // pinsrb xmm1, byte [rdi + r9 + 7], 2 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x0307074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 7], 3 + QUAD $0x04070f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 7], 4 + QUAD $0x072f4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdi + r13 + 7], 5 + QUAD $0x07374c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdi + r14 + 7], 6 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x07374c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdi + r14 + 7], 7 + QUAD $0x07274c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdi + r12 + 7], 8 + QUAD $0x0907374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 7], 9 + QUAD $0x07074c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdi + r8 + 7], 10 + QUAD $0x0b071f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 7], 11 + QUAD $0x073f4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdi + r15 + 7], 12 + QUAD $0x0d07174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 7], 13 + QUAD $0x07174c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdi + r10 + 7], 14 + QUAD $0x071f4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdi + r11 + 7], 15 + LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] + QUAD $0x093744203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdi + r14 + 9], 1 + QUAD $0x090f44203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdi + r9 + 9], 2 + QUAD $0x03090744203a0f66 // pinsrb xmm0, byte [rdi + rax + 9], 3 + QUAD $0x04090f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 9], 4 + QUAD $0x092f44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdi + r13 + 9], 5 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x06090744203a0f66 // pinsrb xmm0, byte [rdi + rax + 9], 6 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x07090744203a0f66 // pinsrb xmm0, byte [rdi + rax + 9], 7 + QUAD $0x092744203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdi + r12 + 9], 8 + QUAD $0x09093744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 9], 9 + QUAD $0x090744203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdi + r8 + 9], 10 + QUAD $0x0b091f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 9], 11 + QUAD $0x093f44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdi + r15 + 9], 12 + QUAD $0x0d091744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 9], 13 + QUAD $0x091744203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdi + r10 + 9], 14 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x091f44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdi + r11 + 9], 15 + QUAD $0x0a374c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rdi + r14 + 10], 1 + QUAD $0x0a0f4c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rdi + r9 + 10], 2 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x0a174c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdi + r10 + 10], 3 + QUAD $0x0a0f4c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdi + rcx + 10], 4 + QUAD $0x0a2f4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdi + r13 + 10], 5 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x0a1f4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r11 + 10], 6 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0a374c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r14 + 10], 7 + QUAD $0x0a274c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdi + r12 + 10], 8 + QUAD $0x0a374c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdi + rsi + 10], 9 + QUAD $0x0a074c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdi + r8 + 10], 10 + QUAD $0x0a1f4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdi + rbx + 10], 11 + QUAD $0x0a3f4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdi + r15 + 10], 12 + QUAD $0x0a174c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdi + rdx + 10], 13 + LONG $0xeb0f4466; BYTE $0xe4 // por xmm12, xmm4 + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + LONG $0x6f0f4166; BYTE $0xe6 // movdqa xmm4, xmm14 + LONG $0xe3640f66 // pcmpgtb xmm4, xmm3 + LONG $0x640f4466; BYTE $0xf1 // pcmpgtb xmm14, xmm1 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + LONG $0x1f74b60f; BYTE $0x13 // movzx esi, byte [rdi + rbx + 19] + LONG $0xce6e0f66 // movd xmm1, esi + QUAD $0x0a074c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdi + rax + 10], 14 + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI8_15] */ + LONG $0xe3db0f66 // pand xmm4, xmm3 + LONG $0x710f4166; WORD $0x07f6 // psllw xmm14, 7 + LONG $0x5d6f0f66; BYTE $0x60 // movdqa xmm3, oword 96[rbp] /* [rip + .LCPI8_6] */ + LONG $0xdb0f4466; BYTE $0xf3 // pand xmm14, xmm3 + LONG $0xeb0f4466; BYTE $0xf4 // por xmm14, xmm4 + LONG $0x1f74b60f; BYTE $0x14 // movzx esi, byte [rdi + rbx + 20] + LONG $0xe66e0f66 // movd xmm4, esi + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x0a2f4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdi + r13 + 10], 15 + LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 + QUAD $0x00c024b47f0f4466; WORD $0x0000 // movdqa oword [rsp + 192], xmm14 + LONG $0x6f0f4566; BYTE $0xf5 // movdqa xmm14, xmm13 + LONG $0x6f0f4166; BYTE $0xdd // movdqa xmm3, xmm13 + LONG $0xd8640f66 // pcmpgtb xmm3, xmm0 + LONG $0x6f0f4466; BYTE $0xe3 // movdqa xmm12, xmm3 + LONG $0xdb0f4566; BYTE $0xe0 // pand xmm12, xmm8 + LONG $0xf80f4466; BYTE $0xe3 // psubb xmm12, xmm3 + LONG $0x640f4566; BYTE $0xe9 // pcmpgtb xmm13, xmm9 + LONG $0x1f74b60f; BYTE $0x15 // movzx esi, byte [rdi + rbx + 21] + LONG $0xc66e0f66 // movd xmm0, esi + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x0b3754203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdi + rsi + 11], 1 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x0b0754203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rdi + r8 + 11], 2 + QUAD $0x0b1754203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdi + r10 + 11], 3 + QUAD $0x0b0f54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdi + rcx + 11], 4 + QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] + QUAD $0x0b0f54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdi + r9 + 11], 5 + QUAD $0x0b1f54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r11 + 11], 6 + WORD $0x894c; BYTE $0xf3 // mov rbx, r14 + QUAD $0x0b3754203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r14 + 11], 7 + QUAD $0x0b2754203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdi + r12 + 11], 8 + LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] + QUAD $0x0b3754203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdi + r14 + 11], 9 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0b0754203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdi + rax + 11], 10 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x0b3f54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r15 + 11], 11 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x0b2754203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdi + r12 + 11], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0b0754203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdi + rax + 11], 13 + QUAD $0x0b1754203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rdi + rdx + 11], 14 + QUAD $0x0b2f54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdi + r13 + 11], 15 + QUAD $0x0c375c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdi + rsi + 12], 1 + QUAD $0x0c075c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rdi + r8 + 12], 2 + QUAD $0x0c175c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdi + r10 + 12], 3 + QUAD $0x0c0f5c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdi + rcx + 12], 4 + QUAD $0x0c0f5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdi + r9 + 12], 5 + QUAD $0x0c1f5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdi + r11 + 12], 6 + QUAD $0x0c1f5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rdi + rbx + 12], 7 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0c0f5c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rdi + rcx + 12], 8 + QUAD $0x0c375c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdi + r14 + 12], 9 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0c075c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdi + r8 + 12], 10 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x0c3f5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdi + r15 + 12], 11 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x0c275c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdi + r12 + 12], 12 + QUAD $0x0c075c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdi + rax + 12], 13 + QUAD $0x0c175c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rdi + rdx + 12], 14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + QUAD $0x000130249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 304] + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + QUAD $0x0000b0addb0f4466; BYTE $0x00 // pand xmm13, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xeb0f4466; BYTE $0xeb // por xmm13, xmm3 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + LONG $0x1774b60f; BYTE $0x16 // movzx esi, byte [rdi + rdx + 22] + LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi + QUAD $0x0c2f5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdi + r13 + 12], 15 + LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 + LONG $0x6f0f4566; BYTE $0xe6 // movdqa xmm12, xmm14 + LONG $0x640f4566; BYTE $0xe2 // pcmpgtb xmm12, xmm10 + LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 + LONG $0x640f4166; BYTE $0xdb // pcmpgtb xmm3, xmm11 + LONG $0x1774b60f; BYTE $0x17 // movzx esi, byte [rdi + rdx + 23] + LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x010d077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 13], 1 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x020d377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 13], 2 + QUAD $0x0d177c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r10 + 13], 3 + LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] + QUAD $0x0d1f7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdi + r11 + 13], 4 + QUAD $0x0d0f7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdi + r9 + 13], 5 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0d377c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r14 + 13], 6 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x070d377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 13], 7 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x0d277c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdi + r12 + 13], 8 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x090d377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 13], 9 + QUAD $0x0d077c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdi + r8 + 13], 10 + QUAD $0x0b0d1f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 13], 11 + QUAD $0x0d3f7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdi + r15 + 13], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0d0d377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 13], 13 + QUAD $0x0e0d0f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 13], 14 + QUAD $0x0d2f7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdi + r13 + 13], 15 + QUAD $0x0000c0a5db0f4466; BYTE $0x00 // pand xmm12, oword 192[rbp] /* [rip + .LCPI8_12] */ + QUAD $0x000000d09ddb0f66 // pand xmm3, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xeb0f4166; BYTE $0xdc // por xmm3, xmm12 + LONG $0x6f0f4566; BYTE $0xd6 // movdqa xmm10, xmm14 + LONG $0x640f4466; BYTE $0xd7 // pcmpgtb xmm10, xmm7 + LONG $0x1774b60f; BYTE $0x19 // movzx esi, byte [rdi + rdx + 25] + LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi + QUAD $0x0000e095db0f4466; BYTE $0x00 // pand xmm10, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xeb0f4466; BYTE $0xd3 // por xmm10, xmm3 + LONG $0x1774b60f; BYTE $0x1a // movzx esi, byte [rdi + rdx + 26] + LONG $0xfe6e0f66 // movd xmm7, esi + QUAD $0x010e0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 14], 1 + LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] + QUAD $0x020e3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 14], 2 + QUAD $0x0e1774203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r10 + 14], 3 + WORD $0x894d; BYTE $0xdd // mov r13, r11 + QUAD $0x0e1f74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r11 + 14], 4 + WORD $0x894c; BYTE $0xca // mov rdx, r9 + QUAD $0x0e0f74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdi + r9 + 14], 5 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + QUAD $0x0e3774203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r14 + 14], 6 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x0e3774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r14 + 14], 7 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + QUAD $0x0e2774203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdi + r12 + 14], 8 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x0e0f74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r9 + 14], 9 + QUAD $0x0e0774203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdi + r8 + 14], 10 + QUAD $0x0b0e1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 14], 11 + QUAD $0x0e3f74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r15 + 14], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d0e0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 14], 13 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0e0e0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 14], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f0e0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 14], 15 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x0f276c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdi + r12 + 15], 1 + QUAD $0x020f376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 15], 2 + QUAD $0x0f176c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r10 + 15], 3 + QUAD $0x0f2f6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdi + r13 + 15], 4 + QUAD $0x050f176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 15], 5 + QUAD $0x0f1f6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r11 + 15], 6 + QUAD $0x0f376c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r14 + 15], 7 + QUAD $0x080f0f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 15], 8 + QUAD $0x0f0f6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r9 + 15], 9 + QUAD $0x0f076c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r8 + 15], 10 + QUAD $0x0b0f1f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 15], 11 + QUAD $0x0f3f6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdi + r15 + 15], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d0f076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 15], 13 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x0f276c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdi + r12 + 15], 14 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0f0f076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 15], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x01110754203a0f66 // pinsrb xmm2, byte [rdi + rax + 17], 1 + QUAD $0x02113754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 17], 2 + QUAD $0x111754203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdi + r10 + 17], 3 + QUAD $0x112f54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdi + r13 + 17], 4 + QUAD $0x05111754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 17], 5 + QUAD $0x111f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r11 + 17], 6 + QUAD $0x113754203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r14 + 17], 7 + QUAD $0x08110f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 17], 8 + QUAD $0x110f54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r9 + 17], 9 + QUAD $0x110754203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r8 + 17], 10 + QUAD $0x0b111f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 17], 11 + QUAD $0x113f54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdi + r15 + 17], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d110754203a0f66 // pinsrb xmm2, byte [rdi + rax + 17], 13 + QUAD $0x112754203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdi + r12 + 17], 14 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x112754203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r12 + 17], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x12077c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdi + rax + 18], 1 + QUAD $0x12377c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rsi + 18], 2 + QUAD $0x12177c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdi + r10 + 18], 3 + QUAD $0x122f7c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdi + r13 + 18], 4 + QUAD $0x12177c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdi + rdx + 18], 5 + QUAD $0x121f7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r11 + 18], 6 + QUAD $0x12377c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r14 + 18], 7 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + QUAD $0x120f7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdi + rcx + 18], 8 + QUAD $0x120f7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r9 + 18], 9 + QUAD $0x12077c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdi + r8 + 18], 10 + QUAD $0x121f7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rdi + rbx + 18], 11 + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + QUAD $0x123f7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdi + r15 + 18], 12 + LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] + QUAD $0x12077c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdi + r8 + 18], 13 + LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + LONG $0x640f4466; BYTE $0xee // pcmpgtb xmm13, xmm6 + LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 + LONG $0xdd640f66 // pcmpgtb xmm3, xmm5 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + LONG $0x0774b60f; BYTE $0x1b // movzx esi, byte [rdi + rax + 27] + LONG $0xee6e0f66 // movd xmm5, esi + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x120f7c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdi + rcx + 18], 14 + QUAD $0x0000f0addb0f4466; BYTE $0x00 // pand xmm13, oword 240[rbp] /* [rip + .LCPI8_15] */ + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0x5ddb0f66; BYTE $0x60 // pand xmm3, oword 96[rbp] /* [rip + .LCPI8_6] */ + LONG $0xeb0f4166; BYTE $0xdd // por xmm3, xmm13 + LONG $0x0774b60f; BYTE $0x1c // movzx esi, byte [rdi + rax + 28] + LONG $0xf66e0f66 // movd xmm6, esi + QUAD $0x12277c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r12 + 18], 15 + LONG $0xeb0f4166; BYTE $0xda // por xmm3, xmm10 + QUAD $0x000110249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm3 + LONG $0x6f0f4166; BYTE $0xde // movdqa xmm3, xmm14 + LONG $0xda640f66 // pcmpgtb xmm3, xmm2 + LONG $0x6f0f4466; BYTE $0xeb // movdqa xmm13, xmm3 + QUAD $0x000000a0956f0f66 // movdqa xmm2, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xdb0f4466; BYTE $0xea // pand xmm13, xmm2 + LONG $0xf80f4466; BYTE $0xeb // psubb xmm13, xmm3 + LONG $0x6f0f4566; BYTE $0xd6 // movdqa xmm10, xmm14 + LONG $0x640f4566; BYTE $0xd7 // pcmpgtb xmm10, xmm15 + LONG $0x0774b60f; BYTE $0x1d // movzx esi, byte [rdi + rax + 29] + LONG $0xde6e0f66 // movd xmm3, esi + QUAD $0x00d024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 208] + LONG $0xdb0f4466; BYTE $0xfa // pand xmm15, xmm2 + QUAD $0x000000b0956f0f66 // movdqa xmm2, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xdb0f4466; BYTE $0xd2 // pand xmm10, xmm2 + LONG $0xeb0f4566; BYTE $0xd7 // por xmm10, xmm15 + LONG $0x0774b60f; BYTE $0x1e // movzx esi, byte [rdi + rax + 30] + LONG $0xd66e0f66 // movd xmm2, esi + LONG $0x0744b60f; BYTE $0x1f // movzx eax, byte [rdi + rax + 31] + LONG $0x50244489 // mov dword [rsp + 80], eax + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0113074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 19], 1 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x02130f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 19], 2 + QUAD $0x13174c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdi + r10 + 19], 3 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x0413374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 19], 4 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x13174c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdi + r10 + 19], 5 + QUAD $0x131f4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdi + r11 + 19], 6 + WORD $0x894d; BYTE $0xde // mov r14, r11 + QUAD $0x132f4c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdi + r13 + 19], 7 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0813374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 19], 8 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x09131f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 19], 9 + LONG $0x245c8b4c; BYTE $0x20 // mov r11, qword [rsp + 32] + QUAD $0x131f4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdi + r11 + 19], 10 + WORD $0x894d; BYTE $0xcf // mov r15, r9 + QUAD $0x130f4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdi + r9 + 19], 11 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x132f4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdi + r13 + 19], 12 + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + QUAD $0x13074c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdi + r8 + 19], 13 + LONG $0x24448b4c; BYTE $0x48 // mov r8, qword [rsp + 72] + QUAD $0x13074c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdi + r8 + 19], 14 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x13274c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdi + r12 + 19], 15 + QUAD $0x01140764203a0f66 // pinsrb xmm4, byte [rdi + rax + 20], 1 + QUAD $0x02140f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 20], 2 + QUAD $0x03141764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 20], 3 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x04141764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 20], 4 + QUAD $0x141764203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdi + r10 + 20], 5 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + QUAD $0x143764203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r14 + 20], 6 + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x143764203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r14 + 20], 7 + QUAD $0x08143764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 20], 8 + WORD $0x8948; BYTE $0xde // mov rsi, rbx + QUAD $0x09141f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 20], 9 + QUAD $0x141f64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdi + r11 + 20], 10 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x143f64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r15 + 20], 11 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x142f64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdi + r13 + 20], 12 + QUAD $0x140f64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdi + r9 + 20], 13 + QUAD $0x140764203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdi + r8 + 20], 14 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x142764203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdi + r12 + 20], 15 + LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + LONG $0x640f4466; BYTE $0xe9 // pcmpgtb xmm13, xmm1 + LONG $0x6f0f4566; BYTE $0xfe // movdqa xmm15, xmm14 + LONG $0x640f4466; BYTE $0xfc // pcmpgtb xmm15, xmm4 + LONG $0x4c6e0f66; WORD $0x5024 // movd xmm1, dword [rsp + 80] + QUAD $0x01150744203a0f66 // pinsrb xmm0, byte [rdi + rax + 21], 1 + QUAD $0x160744203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdi + rax + 22], 1 + QUAD $0x17074c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdi + rax + 23], 1 + QUAD $0x19075c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdi + rax + 25], 1 + QUAD $0x011a077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 26], 1 + QUAD $0x011b076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 27], 1 + QUAD $0x011c0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 28], 1 + QUAD $0x011d075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 29], 1 + QUAD $0x011e0754203a0f66 // pinsrb xmm2, byte [rdi + rax + 30], 1 + QUAD $0x011f074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 31], 1 + QUAD $0x02150f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 21], 2 + QUAD $0x160f44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdi + rcx + 22], 2 + QUAD $0x170f4c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdi + rcx + 23], 2 + QUAD $0x190f5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdi + rcx + 25], 2 + QUAD $0x021a0f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 26], 2 + QUAD $0x021b0f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 27], 2 + QUAD $0x021c0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 28], 2 + QUAD $0x021d0f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 29], 2 + QUAD $0x021e0f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 30], 2 + QUAD $0x021f0f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 31], 2 + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + QUAD $0x151744203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdi + r10 + 21], 3 + LONG $0x246c8b4c; BYTE $0x40 // mov r13, qword [rsp + 64] + QUAD $0x152f44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdi + r13 + 21], 4 + QUAD $0x05151744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 21], 5 + LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] + QUAD $0x151f44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r11 + 21], 6 + QUAD $0x153744203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r14 + 21], 7 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x150f44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdi + r9 + 21], 8 + QUAD $0x09153744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 21], 9 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x150744203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdi + r8 + 21], 10 + QUAD $0x0b151f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 21], 11 + QUAD $0x153f44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdi + r15 + 21], 12 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x0d150f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 21], 13 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0e150744203a0f66 // pinsrb xmm0, byte [rdi + rax + 21], 14 + QUAD $0x152744203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdi + r12 + 21], 15 + QUAD $0x000000c0a56f0f66 // movdqa xmm4, oword 192[rbp] /* [rip + .LCPI8_12] */ + LONG $0xdb0f4466; BYTE $0xec // pand xmm13, xmm4 + QUAD $0x000000d0a56f0f66 // movdqa xmm4, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xdb0f4466; BYTE $0xfc // pand xmm15, xmm4 + LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + LONG $0x640f4466; BYTE $0xe8 // pcmpgtb xmm13, xmm0 + QUAD $0x000000e0856f0f66 // movdqa xmm0, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xdb0f4466; BYTE $0xe8 // pand xmm13, xmm0 + LONG $0xeb0f4566; BYTE $0xef // por xmm13, xmm15 + QUAD $0x161744203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdi + r10 + 22], 3 + QUAD $0x162f44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdi + r13 + 22], 4 + QUAD $0x161744203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdi + rdx + 22], 5 + QUAD $0x161f44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r11 + 22], 6 + QUAD $0x163744203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r14 + 22], 7 + QUAD $0x160f44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdi + r9 + 22], 8 + QUAD $0x163744203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdi + rsi + 22], 9 + QUAD $0x160744203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdi + r8 + 22], 10 + QUAD $0x161f44203a0f4466; BYTE $0x0b // pinsrb xmm8, byte [rdi + rbx + 22], 11 + QUAD $0x163f44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdi + r15 + 22], 12 + QUAD $0x160f44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdi + rcx + 22], 13 + QUAD $0x160744203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdi + rax + 22], 14 + QUAD $0x162744203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdi + r12 + 22], 15 + QUAD $0x17174c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdi + r10 + 23], 3 + QUAD $0x172f4c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdi + r13 + 23], 4 + QUAD $0x17174c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdi + rdx + 23], 5 + QUAD $0x171f4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r11 + 23], 6 + QUAD $0x17374c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r14 + 23], 7 + QUAD $0x170f4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdi + r9 + 23], 8 + QUAD $0x17374c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdi + rsi + 23], 9 + QUAD $0x17074c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdi + r8 + 23], 10 + QUAD $0x171f4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdi + rbx + 23], 11 + QUAD $0x173f4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdi + r15 + 23], 12 + QUAD $0x170f4c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdi + rcx + 23], 13 + QUAD $0x17074c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdi + rax + 23], 14 + QUAD $0x17274c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdi + r12 + 23], 15 + QUAD $0x19175c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdi + r10 + 25], 3 + QUAD $0x192f5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdi + r13 + 25], 4 + QUAD $0x19175c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdi + rdx + 25], 5 + QUAD $0x191f5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdi + r11 + 25], 6 + QUAD $0x19375c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdi + r14 + 25], 7 + QUAD $0x190f5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdi + r9 + 25], 8 + QUAD $0x19375c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdi + rsi + 25], 9 + QUAD $0x19075c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdi + r8 + 25], 10 + QUAD $0x191f5c203a0f4466; BYTE $0x0b // pinsrb xmm11, byte [rdi + rbx + 25], 11 + QUAD $0x193f5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdi + r15 + 25], 12 + QUAD $0x190f5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdi + rcx + 25], 13 + QUAD $0x19075c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rdi + rax + 25], 14 + QUAD $0x19275c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdi + r12 + 25], 15 + QUAD $0x1a177c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r10 + 26], 3 + QUAD $0x1a2f7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdi + r13 + 26], 4 + QUAD $0x051a177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 26], 5 + QUAD $0x1a1f7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r11 + 26], 6 + QUAD $0x1a377c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r14 + 26], 7 + QUAD $0x1a0f7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdi + r9 + 26], 8 + QUAD $0x091a377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 26], 9 + WORD $0x8949; BYTE $0xf1 // mov r9, rsi + QUAD $0x1a077c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdi + r8 + 26], 10 + QUAD $0x0b1a1f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 26], 11 + QUAD $0x1a3f7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdi + r15 + 26], 12 + QUAD $0x0d1a0f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 26], 13 + QUAD $0x0e1a077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 26], 14 + LONG $0xeb0f4566; BYTE $0xea // por xmm13, xmm10 + LONG $0x6f0f4566; BYTE $0xe6 // movdqa xmm12, xmm14 + LONG $0x6f0f4166; BYTE $0xe6 // movdqa xmm4, xmm14 + LONG $0x640f4166; BYTE $0xe0 // pcmpgtb xmm4, xmm8 + LONG $0x6f0f4166; BYTE $0xc6 // movdqa xmm0, xmm14 + LONG $0x640f4166; BYTE $0xc1 // pcmpgtb xmm0, xmm9 + QUAD $0x0000f0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 240[rbp] /* [rip + .LCPI8_15] */ + LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0x6f0f4466; WORD $0x607d // movdqa xmm15, oword 96[rbp] /* [rip + .LCPI8_6] */ + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xc4eb0f66 // por xmm0, xmm4 + QUAD $0x1a277c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdi + r12 + 26], 15 + LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xe4 // movdqa xmm4, xmm12 + LONG $0x640f4166; BYTE $0xe3 // pcmpgtb xmm4, xmm11 + LONG $0x6f0f4466; BYTE $0xc4 // movdqa xmm8, xmm4 + QUAD $0x0000a09d6f0f4466; BYTE $0x00 // movdqa xmm11, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xdb0f4566; BYTE $0xc3 // pand xmm8, xmm11 + LONG $0xf80f4466; BYTE $0xc4 // psubb xmm8, xmm4 + LONG $0x6f0f4166; BYTE $0xe4 // movdqa xmm4, xmm12 + LONG $0xe7640f66 // pcmpgtb xmm4, xmm7 + QUAD $0x1b176c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r10 + 27], 3 + QUAD $0x1b2f6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdi + r13 + 27], 4 + QUAD $0x051b176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 27], 5 + QUAD $0x1b1f6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r11 + 27], 6 + QUAD $0x1b376c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r14 + 27], 7 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x081b376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 27], 8 + QUAD $0x1b0f6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r9 + 27], 9 + QUAD $0x1b076c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r8 + 27], 10 + QUAD $0x0b1b1f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 27], 11 + QUAD $0x1b3f6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdi + r15 + 27], 12 + QUAD $0x0d1b0f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 27], 13 + QUAD $0x0e1b076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 27], 14 + QUAD $0x1b276c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdi + r12 + 27], 15 + QUAD $0x1c1774203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r10 + 28], 3 + QUAD $0x1c2f74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r13 + 28], 4 + QUAD $0x051c1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 28], 5 + QUAD $0x1c1f74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r11 + 28], 6 + QUAD $0x1c3774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r14 + 28], 7 + QUAD $0x081c3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 28], 8 + QUAD $0x1c0f74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r9 + 28], 9 + QUAD $0x1c0774203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdi + r8 + 28], 10 + QUAD $0x0b1c1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 28], 11 + QUAD $0x1c3f74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r15 + 28], 12 + QUAD $0x0d1c0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 28], 13 + QUAD $0x0000e024bc6f0f66; BYTE $0x00 // movdqa xmm7, oword [rsp + 224] + LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 + QUAD $0x0e1c0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 28], 14 + QUAD $0x000000b0a5db0f66 // pand xmm4, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xe7eb0f66 // por xmm4, xmm7 + QUAD $0x1c2774203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdi + r12 + 28], 15 + LONG $0xeb0f4166; BYTE $0xe0 // por xmm4, xmm8 + LONG $0x6f0f4166; BYTE $0xfc // movdqa xmm7, xmm12 + LONG $0xfd640f66 // pcmpgtb xmm7, xmm5 + LONG $0x6f0f4166; BYTE $0xec // movdqa xmm5, xmm12 + LONG $0xee640f66 // pcmpgtb xmm5, xmm6 + QUAD $0x1d175c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r10 + 29], 3 + QUAD $0x1d2f5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r13 + 29], 4 + QUAD $0x051d175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 29], 5 + QUAD $0x1d1f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r11 + 29], 6 + QUAD $0x1d375c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r14 + 29], 7 + QUAD $0x081d375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 29], 8 + QUAD $0x1d0f5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdi + r9 + 29], 9 + QUAD $0x1d075c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdi + r8 + 29], 10 + QUAD $0x0b1d1f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 29], 11 + QUAD $0x1d3f5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r15 + 29], 12 + QUAD $0x0d1d0f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 29], 13 + QUAD $0x0e1d075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 29], 14 + QUAD $0x1d275c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdi + r12 + 29], 15 + QUAD $0x000000c0bddb0f66 // pand xmm7, oword 192[rbp] /* [rip + .LCPI8_12] */ + QUAD $0x000000d0addb0f66 // pand xmm5, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xefeb0f66 // por xmm5, xmm7 + LONG $0x6f0f4166; BYTE $0xf4 // movdqa xmm6, xmm12 + LONG $0xf3640f66 // pcmpgtb xmm6, xmm3 + QUAD $0x000000e0b5db0f66 // pand xmm6, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xf5eb0f66 // por xmm6, xmm5 + QUAD $0x1e1754203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdi + r10 + 30], 3 + QUAD $0x1f174c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdi + r10 + 31], 3 + QUAD $0x1e2f54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdi + r13 + 30], 4 + QUAD $0x1f2f4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdi + r13 + 31], 4 + QUAD $0x051e1754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 30], 5 + QUAD $0x051f174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 31], 5 + QUAD $0x1e1f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r11 + 30], 6 + QUAD $0x1f1f4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdi + r11 + 31], 6 + QUAD $0x1e3754203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r14 + 30], 7 + QUAD $0x1f374c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdi + r14 + 31], 7 + QUAD $0x081e3754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 30], 8 + QUAD $0x081f374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 31], 8 + QUAD $0x1e0f54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r9 + 30], 9 + QUAD $0x1f0f4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdi + r9 + 31], 9 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x1e0754203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r8 + 30], 10 + QUAD $0x1f074c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rdi + r8 + 31], 10 + QUAD $0x0b1e1f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 30], 11 + QUAD $0x0b1f1f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 31], 11 + QUAD $0x1e3f54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdi + r15 + 30], 12 + QUAD $0x1f3f4c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdi + r15 + 31], 12 + QUAD $0x0d1e0f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 30], 13 + QUAD $0x0d1f0f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 31], 13 + QUAD $0x0e1e0754203a0f66 // pinsrb xmm2, byte [rdi + rax + 30], 14 + QUAD $0x0e1f074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 31], 14 + QUAD $0x1e2754203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r12 + 30], 15 + QUAD $0x1f274c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdi + r12 + 31], 15 + LONG $0xf4eb0f66 // por xmm6, xmm4 + LONG $0x6f0f4166; BYTE $0xdc // movdqa xmm3, xmm12 + LONG $0xda640f66 // pcmpgtb xmm3, xmm2 + LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 + LONG $0x640f4466; BYTE $0xe1 // pcmpgtb xmm12, xmm1 + LONG $0x710f4166; WORD $0x07f4 // psllw xmm12, 7 + LONG $0xdb0f4566; BYTE $0xe7 // pand xmm12, xmm15 + LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 + LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0x600f4166; BYTE $0xcc // punpcklbw xmm1, xmm12 + QUAD $0x0000c024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 192] + LONG $0xdd6f0f66 // movdqa xmm3, xmm5 + QUAD $0x00011024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 272] + LONG $0xde600f66 // punpcklbw xmm3, xmm6 + LONG $0xe36f0f66 // movdqa xmm4, xmm3 + LONG $0xe1610f66 // punpcklwd xmm4, xmm1 + LONG $0xd9690f66 // punpckhwd xmm3, xmm1 + LONG $0x680f4166; BYTE $0xc4 // punpckhbw xmm0, xmm12 + LONG $0xee680f66 // punpckhbw xmm5, xmm6 + LONG $0xcd6f0f66 // movdqa xmm1, xmm5 + LONG $0xc8610f66 // punpcklwd xmm1, xmm0 + LONG $0xe8690f66 // punpckhwd xmm5, xmm0 + LONG $0x244c8b48; BYTE $0x78 // mov rcx, qword [rsp + 120] + LONG $0x7f0f41f3; WORD $0x8e6c; BYTE $0x30 // movdqu oword [r14 + 4*rcx + 48], xmm5 + LONG $0x7f0f41f3; WORD $0x8e4c; BYTE $0x20 // movdqu oword [r14 + 4*rcx + 32], xmm1 + LONG $0x7f0f41f3; WORD $0x8e5c; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm3 LONG $0x7f0f41f3; WORD $0x8e24 // movdqu oword [r14 + 4*rcx], xmm4 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c28148; WORD $0x0002; BYTE $0x00 // add rdx, 512 - WORD $0x3949; BYTE $0xc8 // cmp r8, rcx - JNE LBB8_201 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB8_124 - JMP LBB8_140 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + JNE LBB8_223 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + LONG $0x243c8a44 // mov r15b, byte [rsp] + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + JNE LBB8_146 + JMP LBB8_150 + +LBB8_225: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xd8 // add rax, r11 + QUAD $0x0000010824848948 // mov qword [rsp + 264], rax + QUAD $0x000000f8248c8948 // mov qword [rsp + 248], rcx + LONG $0x8e048d49 // lea rax, [r14 + 4*rcx] + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0xc7b60f41 // movzx eax, r15b + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0xc0ef0f66 // pxor xmm0, xmm0 + LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 + QUAD $0x000120248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm1 + WORD $0xc031 // xor eax, eax + QUAD $0x0000008024b4894c // mov qword [rsp + 128], r14 + +LBB8_226: + WORD $0x8949; BYTE $0xc1 // mov r9, rax + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0x8948; BYTE $0xcb // mov rbx, rcx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + WORD $0x8949; BYTE $0xca // mov r10, rcx + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx + WORD $0x8948; BYTE $0xce // mov rsi, rcx + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0x8948; BYTE $0xca // mov rdx, rcx + WORD $0x8948; BYTE $0xcf // mov rdi, rcx + LONG $0x0cb60f41; BYTE $0x0b // movzx ecx, byte [r11 + rcx] + LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx + LONG $0x4cb60f41; WORD $0x013b // movzx ecx, byte [r11 + rdi + 1] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x4cb60f41; WORD $0x023b // movzx ecx, byte [r11 + rdi + 2] + LONG $0xf96e0f66 // movd xmm7, ecx + LONG $0x4cb60f41; WORD $0x033b // movzx ecx, byte [r11 + rdi + 3] + LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx + LONG $0x4cb60f41; WORD $0x043b // movzx ecx, byte [r11 + rdi + 4] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x4cb60f41; WORD $0x053b // movzx ecx, byte [r11 + rdi + 5] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x4cb60f41; WORD $0x063b // movzx ecx, byte [r11 + rdi + 6] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x4cb60f41; WORD $0x073b // movzx ecx, byte [r11 + rdi + 7] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 + LONG $0x4cb60f41; WORD $0x083b // movzx ecx, byte [r11 + rdi + 8] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 + LONG $0x4cb60f41; WORD $0x093b // movzx ecx, byte [r11 + rdi + 9] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x4cb60f41; WORD $0x0a3b // movzx ecx, byte [r11 + rdi + 10] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x4cb60f41; WORD $0x0b3b // movzx ecx, byte [r11 + rdi + 11] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x00009024847f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm0 + LONG $0x4cb60f41; WORD $0x0c3b // movzx ecx, byte [r11 + rdi + 12] + LONG $0xc16e0f66 // movd xmm0, ecx + QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 + LONG $0x4cb60f41; WORD $0x0d3b // movzx ecx, byte [r11 + rdi + 13] + LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx + LONG $0x4cb60f41; WORD $0x0e3b // movzx ecx, byte [r11 + rdi + 14] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x247c8948; BYTE $0x48 // mov qword [rsp + 72], rdi + WORD $0x8949; BYTE $0xfd // mov r13, rdi + LONG $0x20cd8349 // or r13, 32 + LONG $0x246c894c; BYTE $0x08 // mov qword [rsp + 8], r13 + LONG $0x40ce8349 // or r14, 64 + LONG $0x2474894c; BYTE $0x20 // mov qword [rsp + 32], r14 + LONG $0x60cb8348 // or rbx, 96 + LONG $0x245c8948; BYTE $0x78 // mov qword [rsp + 120], rbx + LONG $0x00800d48; WORD $0x0000 // or rax, 128 + LONG $0xa0c98149; WORD $0x0000; BYTE $0x00 // or r9, 160 + LONG $0xc0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 192 + LONG $0x2454894c; BYTE $0x60 // mov qword [rsp + 96], r10 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 + LONG $0xe0cb8148; WORD $0x0000; BYTE $0x00 // or rbx, 224 + LONG $0x245c8948; BYTE $0x50 // mov qword [rsp + 80], rbx + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + LONG $0x00c98148; WORD $0x0001; BYTE $0x00 // or rcx, 256 + LONG $0x20ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 288 + LONG $0x24748948; BYTE $0x58 // mov qword [rsp + 88], rsi + LONG $0x40cc8149; WORD $0x0001; BYTE $0x00 // or r12, 320 + LONG $0x60cf8149; WORD $0x0001; BYTE $0x00 // or r15, 352 + LONG $0x247c894c; BYTE $0x68 // mov qword [rsp + 104], r15 + WORD $0x8949; BYTE $0xd0 // mov r8, rdx + LONG $0x80c88149; WORD $0x0001; BYTE $0x00 // or r8, 384 + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xa0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 416 + LONG $0x24548948; BYTE $0x28 // mov qword [rsp + 40], rdx + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xc0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 448 + LONG $0x24548948; BYTE $0x10 // mov qword [rsp + 16], rdx + WORD $0x8948; BYTE $0xfa // mov rdx, rdi + LONG $0xe0ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 480 + LONG $0x24548948; BYTE $0x18 // mov qword [rsp + 24], rdx + QUAD $0x012b6c203a0f4366; BYTE $0x01 // pinsrb xmm5, byte [r11 + r13 + 1], 1 + QUAD $0x01336c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r11 + r14 + 1], 2 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x012b6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r11 + r13 + 1], 3 + QUAD $0x01036c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r11 + rax + 1], 4 + WORD $0x8949; BYTE $0xc6 // mov r14, rax + QUAD $0x010b6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r11 + r9 + 1], 5 + QUAD $0x01136c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r11 + r10 + 1], 6 + QUAD $0x011b6c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r11 + rbx + 1], 7 + QUAD $0x010b6c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r11 + rcx + 1], 8 + QUAD $0x01336c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r11 + rsi + 1], 9 + QUAD $0x01236c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r11 + r12 + 1], 10 + QUAD $0x013b6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r11 + r15 + 1], 11 + QUAD $0x01036c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r11 + r8 + 1], 12 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x01336c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r11 + rsi + 1], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x01036c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r11 + rax + 1], 14 + QUAD $0x01136c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r11 + rdx + 1], 15 + QUAD $0x012024946f0f4466; WORD $0x0000 // movdqa xmm10, oword [rsp + 288] + LONG $0xda0f4166; BYTE $0xea // pminub xmm5, xmm10 + LONG $0x740f4166; BYTE $0xea // pcmpeqb xmm5, xmm10 + LONG $0xf56f0f66 // movdqa xmm6, xmm5 + QUAD $0x000000a08d6f0f66 // movdqa xmm1, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xf1df0f66 // pandn xmm6, xmm1 + LONG $0xf5fc0f66 // paddb xmm6, xmm5 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + LONG $0x7cb60f41; WORD $0x0f13 // movzx edi, byte [r11 + rdx + 15] + LONG $0xc76e0f66 // movd xmm0, edi + QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x01030c203a0f4566 // pinsrb xmm9, byte [r11 + rax], 1 + LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] + QUAD $0x02130c203a0f4766 // pinsrb xmm9, byte [r11 + r10], 2 + QUAD $0x032b0c203a0f4766 // pinsrb xmm9, byte [r11 + r13], 3 + WORD $0x894c; BYTE $0xf7 // mov rdi, r14 + QUAD $0x04330c203a0f4766 // pinsrb xmm9, byte [r11 + r14], 4 + QUAD $0x050b0c203a0f4766 // pinsrb xmm9, byte [r11 + r9], 5 + LONG $0x245c8b48; BYTE $0x60 // mov rbx, qword [rsp + 96] + QUAD $0x061b0c203a0f4566 // pinsrb xmm9, byte [r11 + rbx], 6 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x07330c203a0f4766 // pinsrb xmm9, byte [r11 + r14], 7 + QUAD $0x080b0c203a0f4566 // pinsrb xmm9, byte [r11 + rcx], 8 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x093b0c203a0f4766 // pinsrb xmm9, byte [r11 + r15], 9 + QUAD $0x0a230c203a0f4766 // pinsrb xmm9, byte [r11 + r12], 10 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0b130c203a0f4566 // pinsrb xmm9, byte [r11 + rdx], 11 + LONG $0x2444894c; BYTE $0x70 // mov qword [rsp + 112], r8 + QUAD $0x0c030c203a0f4766 // pinsrb xmm9, byte [r11 + r8], 12 + QUAD $0x0d330c203a0f4566 // pinsrb xmm9, byte [r11 + rsi], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0e030c203a0f4566 // pinsrb xmm9, byte [r11 + rax], 14 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x0f2b0c203a0f4766 // pinsrb xmm9, byte [r11 + r13], 15 + LONG $0xda0f4566; BYTE $0xca // pminub xmm9, xmm10 + LONG $0x740f4566; BYTE $0xca // pcmpeqb xmm9, xmm10 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x02037c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r11 + rax + 2], 1 + QUAD $0x02137c203a0f4366; BYTE $0x02 // pinsrb xmm7, byte [r11 + r10 + 2], 2 + LONG $0x246c8b4c; BYTE $0x78 // mov r13, qword [rsp + 120] + QUAD $0x022b7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r11 + r13 + 2], 3 + QUAD $0x023b7c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r11 + rdi + 2], 4 + QUAD $0x020b7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r11 + r9 + 2], 5 + QUAD $0x021b7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r11 + rbx + 2], 6 + QUAD $0x02337c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r11 + r14 + 2], 7 + QUAD $0x020b7c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r11 + rcx + 2], 8 + QUAD $0x023b7c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r11 + r15 + 2], 9 + QUAD $0x02237c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r11 + r12 + 2], 10 + QUAD $0x02137c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r11 + rdx + 2], 11 + QUAD $0x02037c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r11 + r8 + 2], 12 + QUAD $0x02337c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r11 + rsi + 2], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x02037c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r11 + rax + 2], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x02037c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r11 + rax + 2], 15 + LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x030344203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r11 + rax + 3], 1 + QUAD $0x031344203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r11 + r10 + 3], 2 + QUAD $0x032b44203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r11 + r13 + 3], 3 + QUAD $0x033b44203a0f4166; BYTE $0x04 // pinsrb xmm0, byte [r11 + rdi + 3], 4 + QUAD $0x030b44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r11 + r9 + 3], 5 + QUAD $0x031b44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r11 + rbx + 3], 6 + QUAD $0x033344203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r11 + r14 + 3], 7 + QUAD $0x030b44203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r11 + rcx + 3], 8 + QUAD $0x033b44203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r11 + r15 + 3], 9 + QUAD $0x032344203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r11 + r12 + 3], 10 + QUAD $0x031344203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r11 + rdx + 3], 11 + QUAD $0x030344203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r11 + r8 + 3], 12 + QUAD $0x033344203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r11 + rsi + 3], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x030344203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r11 + rax + 3], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x030344203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r11 + rax + 3], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x04035c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r11 + rax + 4], 1 + QUAD $0x04135c203a0f4366; BYTE $0x02 // pinsrb xmm3, byte [r11 + r10 + 4], 2 + QUAD $0x042b5c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r11 + r13 + 4], 3 + QUAD $0x043b5c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r11 + rdi + 4], 4 + QUAD $0x040b5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r11 + r9 + 4], 5 + QUAD $0x041b5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r11 + rbx + 4], 6 + QUAD $0x04335c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r11 + r14 + 4], 7 + QUAD $0x040b5c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r11 + rcx + 4], 8 + QUAD $0x043b5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r11 + r15 + 4], 9 + QUAD $0x04235c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r11 + r12 + 4], 10 + QUAD $0x04135c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r11 + rdx + 4], 11 + QUAD $0x04035c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r11 + r8 + 4], 12 + QUAD $0x04335c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r11 + rsi + 4], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x04035c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r11 + rax + 4], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x04035c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r11 + rax + 4], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x050354203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rax + 5], 1 + QUAD $0x051354203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r11 + r10 + 5], 2 + QUAD $0x052b54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r13 + 5], 3 + QUAD $0x053b54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r11 + rdi + 5], 4 + WORD $0x8949; BYTE $0xfa // mov r10, rdi + QUAD $0x050b54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r11 + r9 + 5], 5 + QUAD $0x051b54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r11 + rbx + 5], 6 + QUAD $0x053354203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r11 + r14 + 5], 7 + QUAD $0x050b54203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r11 + rcx + 5], 8 + LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx + QUAD $0x053b54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r15 + 5], 9 + QUAD $0x052354203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r11 + r12 + 5], 10 + LONG $0x2464894c; BYTE $0x40 // mov qword [rsp + 64], r12 + QUAD $0x051354203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r11 + rdx + 5], 11 + QUAD $0x050354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r8 + 5], 12 + QUAD $0x053354203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rsi + 5], 13 + LONG $0xdf0f4466; BYTE $0xc9 // pandn xmm9, xmm1 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x050354203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r11 + rax + 5], 14 + LONG $0xda0f4166; BYTE $0xfa // pminub xmm7, xmm10 + LONG $0x740f4166; BYTE $0xfa // pcmpeqb xmm7, xmm10 + QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xf9df0f66 // pandn xmm7, xmm1 + LONG $0xeb0f4166; BYTE $0xf9 // por xmm7, xmm9 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + LONG $0x7cb60f41; WORD $0x1003 // movzx edi, byte [r11 + rax + 16] + LONG $0xef6e0f66 // movd xmm5, edi + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x051354203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r11 + rdx + 5], 15 + LONG $0xda0f4166; BYTE $0xc2 // pminub xmm0, xmm10 + LONG $0x740f4166; BYTE $0xc2 // pcmpeqb xmm0, xmm10 + QUAD $0x000000c08d6f0f66 // movdqa xmm1, oword 192[rbp] /* [rip + .LCPI8_12] */ + LONG $0xc1df0f66 // pandn xmm0, xmm1 + LONG $0xc7eb0f66 // por xmm0, xmm7 + LONG $0x7cb60f41; WORD $0x1103 // movzx edi, byte [r11 + rax + 17] + LONG $0xcf6e0f66 // movd xmm1, edi + LONG $0xff760f66 // pcmpeqd xmm7, xmm7 + LONG $0xf7f80f66 // psubb xmm6, xmm7 + LONG $0x760f4566; BYTE $0xc9 // pcmpeqd xmm9, xmm9 + LONG $0xc6eb0f66 // por xmm0, xmm6 + LONG $0x7cb60f41; WORD $0x1203 // movzx edi, byte [r11 + rax + 18] + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0xff6e0f66 // movd xmm7, edi + LONG $0xda0f4166; BYTE $0xda // pminub xmm3, xmm10 + LONG $0x740f4166; BYTE $0xda // pcmpeqb xmm3, xmm10 + QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xdedf0f66 // pandn xmm3, xmm6 + LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 + LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 + QUAD $0x000000e0b56f0f66 // movdqa xmm6, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xd6df0f66 // pandn xmm2, xmm6 + LONG $0xd3eb0f66 // por xmm2, xmm3 + LONG $0x7cb60f41; WORD $0x1303 // movzx edi, byte [r11 + rax + 19] + LONG $0x6e0f4466; BYTE $0xff // movd xmm15, edi + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + QUAD $0x063344203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r11 + rsi + 6], 1 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x060344203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r11 + r8 + 6], 2 + QUAD $0x062b44203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r11 + r13 + 6], 3 + QUAD $0x061344203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r11 + r10 + 6], 4 + QUAD $0x060b44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r11 + r9 + 6], 5 + QUAD $0x061b44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r11 + rbx + 6], 6 + QUAD $0x063344203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r11 + r14 + 6], 7 + QUAD $0x060b44203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r11 + rcx + 6], 8 + QUAD $0x063b44203a0f4766; BYTE $0x09 // pinsrb xmm8, byte [r11 + r15 + 6], 9 + QUAD $0x062344203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r11 + r12 + 6], 10 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x063b44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r11 + r15 + 6], 11 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + QUAD $0x063344203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r11 + r14 + 6], 12 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x062344203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r11 + r12 + 6], 13 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x060b44203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r11 + rcx + 6], 14 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x060344203a0f4566; BYTE $0x0f // pinsrb xmm8, byte [r11 + rax + 6], 15 + LONG $0xda0f4566; BYTE $0xc2 // pminub xmm8, xmm10 + LONG $0x740f4566; BYTE $0xc2 // pcmpeqb xmm8, xmm10 + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI8_15] */ + LONG $0xdf0f4466; BYTE $0xc3 // pandn xmm8, xmm3 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + LONG $0x7cb60f41; WORD $0x1413 // movzx edi, byte [r11 + rdx + 20] + LONG $0xe76e0f66 // movd xmm4, edi + QUAD $0x0000a024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 160] + QUAD $0x073374203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r11 + rsi + 7], 1 + QUAD $0x070374203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r11 + r8 + 7], 2 + QUAD $0x072b74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r11 + r13 + 7], 3 + QUAD $0x071374203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r11 + r10 + 7], 4 + QUAD $0x070b74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r11 + r9 + 7], 5 + QUAD $0x071b74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r11 + rbx + 7], 6 + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + QUAD $0x071b74203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r11 + rbx + 7], 7 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x071374203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r11 + rdx + 7], 8 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x071374203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r11 + rdx + 7], 9 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x071374203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r11 + rdx + 7], 10 + WORD $0x894c; BYTE $0xfe // mov rsi, r15 + QUAD $0x073b74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r11 + r15 + 7], 11 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + QUAD $0x073374203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r11 + r14 + 7], 12 + QUAD $0x072374203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r11 + r12 + 7], 13 + QUAD $0x070b74203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r11 + rcx + 7], 14 + QUAD $0x070374203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r11 + rax + 7], 15 + LONG $0xda0f4166; BYTE $0xf2 // pminub xmm6, xmm10 + LONG $0x740f4166; BYTE $0xf2 // pcmpeqb xmm6, xmm10 + LONG $0xef0f4166; BYTE $0xf1 // pxor xmm6, xmm9 + LONG $0xdb760f66 // pcmpeqd xmm3, xmm3 + LONG $0xf6710f66; BYTE $0x07 // psllw xmm6, 7 + LONG $0x556f0f66; BYTE $0x60 // movdqa xmm2, oword 96[rbp] /* [rip + .LCPI8_6] */ + LONG $0xf2db0f66 // pand xmm6, xmm2 + LONG $0xeb0f4166; BYTE $0xf0 // por xmm6, xmm8 + LONG $0x6f0f4466; BYTE $0xc6 // movdqa xmm8, xmm6 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + LONG $0x7cb60f41; WORD $0x1503 // movzx edi, byte [r11 + rax + 21] + LONG $0xf76e0f66 // movd xmm6, edi + QUAD $0x0000d024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 208] + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x080354203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rax + 8], 1 + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + QUAD $0x080354203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r11 + r8 + 8], 2 + WORD $0x894c; BYTE $0xe9 // mov rcx, r13 + QUAD $0x082b54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r13 + 8], 3 + QUAD $0x000001302494894c // mov qword [rsp + 304], r10 + QUAD $0x081354203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r11 + r10 + 8], 4 + QUAD $0x080b54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r11 + r9 + 8], 5 + LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] + QUAD $0x083b54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r11 + rdi + 8], 6 + QUAD $0x081b54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r11 + rbx + 8], 7 + LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] + QUAD $0x082b54203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r11 + r13 + 8], 8 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x081354203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r11 + rdx + 8], 9 + LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] + QUAD $0x082354203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r11 + r12 + 8], 10 + QUAD $0x083354203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r11 + rsi + 8], 11 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + QUAD $0x083b54203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r15 + 8], 12 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x083354203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rsi + 8], 13 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x083b54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r11 + r15 + 8], 14 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x09035c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r11 + rax + 9], 1 + QUAD $0x09335c203a0f4766; BYTE $0x02 // pinsrb xmm11, byte [r11 + r14 + 9], 2 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + QUAD $0x090b5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r11 + rcx + 9], 3 + QUAD $0x09135c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r11 + r10 + 9], 4 + QUAD $0x090b5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r11 + r9 + 9], 5 + QUAD $0x093b5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r11 + rdi + 9], 6 + QUAD $0x091b5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r11 + rbx + 9], 7 + QUAD $0x092b5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r11 + r13 + 9], 8 + WORD $0x894c; BYTE $0xe9 // mov rcx, r13 + QUAD $0x09135c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r11 + rdx + 9], 9 + QUAD $0x09235c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r11 + r12 + 9], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x09035c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r11 + rax + 9], 11 + QUAD $0x09035c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r11 + r8 + 9], 12 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 + QUAD $0x09335c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r11 + rsi + 9], 13 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x09335c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r11 + rsi + 9], 14 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x092b5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r11 + r13 + 9], 15 + LONG $0xeb0f4466; BYTE $0xc0 // por xmm8, xmm0 + QUAD $0x00a024847f0f4466; WORD $0x0000 // movdqa oword [rsp + 160], xmm8 + LONG $0xda0f4566; BYTE $0xda // pminub xmm11, xmm10 + LONG $0x740f4566; BYTE $0xda // pcmpeqb xmm11, xmm10 + LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 + QUAD $0x0000a0856f0f4466; BYTE $0x00 // movdqa xmm8, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xdf0f4166; BYTE $0xc0 // pandn xmm0, xmm8 + LONG $0xfc0f4166; BYTE $0xc3 // paddb xmm0, xmm11 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + LONG $0x7cb60f41; WORD $0x1603 // movzx edi, byte [r11 + rax + 22] + LONG $0x6e0f4466; BYTE $0xcf // movd xmm9, edi + QUAD $0x082b54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r11 + r13 + 8], 15 + LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 + LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 + LONG $0xdf0f4166; BYTE $0xd0 // pandn xmm2, xmm8 + LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] + QUAD $0x0a3364203a0f4766; BYTE $0x01 // pinsrb xmm12, byte [r11 + r14 + 10], 1 + QUAD $0x0a3b64203a0f4766; BYTE $0x02 // pinsrb xmm12, byte [r11 + r15 + 10], 2 + LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] + QUAD $0x0a3b64203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r11 + r15 + 10], 3 + QUAD $0x0a1364203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r11 + r10 + 10], 4 + QUAD $0x000000c0248c894c // mov qword [rsp + 192], r9 + QUAD $0x0a0b64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r11 + r9 + 10], 5 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x0a0364203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r11 + r8 + 10], 6 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0a1364203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r11 + rdx + 10], 7 + QUAD $0x0a0b64203a0f4566; BYTE $0x08 // pinsrb xmm12, byte [r11 + rcx + 10], 8 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x0a0b64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r11 + rcx + 10], 9 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0a0b64203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r11 + rcx + 10], 10 + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + QUAD $0x0a1364203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r11 + rdx + 10], 11 + QUAD $0x0a1b64203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r11 + rbx + 10], 12 + WORD $0x8949; BYTE $0xda // mov r10, rbx + QUAD $0x0a2364203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r11 + r12 + 10], 13 + QUAD $0x0a3364203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r11 + rsi + 10], 14 + QUAD $0x0a2b64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r11 + r13 + 10], 15 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0xda0f4566; BYTE $0xe2 // pminub xmm12, xmm10 + LONG $0x740f4566; BYTE $0xe2 // pcmpeqb xmm12, xmm10 + QUAD $0x0000b0a5df0f4466; BYTE $0x00 // pandn xmm12, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xeb0f4466; BYTE $0xe2 // por xmm12, xmm2 + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + LONG $0x7cb60f41; WORD $0x1703 // movzx edi, byte [r11 + rax + 23] + LONG $0x6e0f4466; BYTE $0xc7 // movd xmm8, edi + QUAD $0x00009024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 144] + WORD $0x894c; BYTE $0xf0 // mov rax, r14 + QUAD $0x0b3354203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r11 + r14 + 11], 1 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x0b3b54203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r11 + rdi + 11], 2 + WORD $0x8949; BYTE $0xfd // mov r13, rdi + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x0b3b54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r15 + 11], 3 + QUAD $0x0000013024bc8b4c // mov r15, qword [rsp + 304] + QUAD $0x0b3b54203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r11 + r15 + 11], 4 + QUAD $0x0b0b54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r11 + r9 + 11], 5 + QUAD $0x0b0354203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r11 + r8 + 11], 6 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + QUAD $0x0b0b54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r11 + r9 + 11], 7 + LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] + QUAD $0x0b3b54203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r11 + rdi + 11], 8 + LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] + QUAD $0x0b0354203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r8 + 11], 9 + QUAD $0x0b0b54203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r11 + rcx + 11], 10 + QUAD $0x0b1354203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r11 + rdx + 11], 11 + QUAD $0x0b1354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r10 + 11], 12 + QUAD $0x0b2354203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r11 + r12 + 11], 13 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x0b0b54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r11 + rcx + 11], 14 + QUAD $0x0b1b54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r11 + rbx + 11], 15 + LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 + LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 + QUAD $0x000000c095df0f66 // pandn xmm2, oword 192[rbp] /* [rip + .LCPI8_12] */ + LONG $0xeb0f4166; BYTE $0xd4 // por xmm2, xmm12 + LONG $0x7cb60f41; WORD $0x1833 // movzx edi, byte [r11 + rsi + 24] + LONG $0x6e0f4466; BYTE $0xdf // movd xmm11, edi + LONG $0xc3f80f66 // psubb xmm0, xmm3 + LONG $0xd0eb0f66 // por xmm2, xmm0 + QUAD $0x00009024947f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm2 + LONG $0x7cb60f41; WORD $0x1933 // movzx edi, byte [r11 + rsi + 25] + LONG $0xdf6e0f66 // movd xmm3, edi + QUAD $0x00011024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 272] + QUAD $0x0c0354203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rax + 12], 1 + QUAD $0x0c2b54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r11 + r13 + 12], 2 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + QUAD $0x0c3354203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r14 + 12], 3 + WORD $0x894d; BYTE $0xfa // mov r10, r15 + QUAD $0x0c3b54203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r11 + r15 + 12], 4 + QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] + QUAD $0x0c3b54203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r11 + rdi + 12], 5 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x0c3b54203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r11 + r15 + 12], 6 + QUAD $0x0c0b54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r11 + r9 + 12], 7 + LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + QUAD $0x0c2354203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r11 + r12 + 12], 8 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 + QUAD $0x0c0354203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r8 + 12], 9 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x0c3354203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r11 + r14 + 12], 10 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x0c1354203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r11 + rdx + 12], 11 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + QUAD $0x0c0354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r8 + 12], 12 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + QUAD $0x0c0b54203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rcx + 12], 13 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x0c0b54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r11 + rcx + 12], 14 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0c1354203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r11 + rdx + 12], 15 + LONG $0x24548b48; BYTE $0x08 // mov rdx, qword [rsp + 8] + QUAD $0x0d1374203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r11 + rdx + 13], 1 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0d2b74203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r11 + r13 + 13], 2 + QUAD $0x0d3374203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r11 + rsi + 13], 3 + QUAD $0x0d1374203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r11 + r10 + 13], 4 + QUAD $0x0d3b74203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r11 + rdi + 13], 5 + QUAD $0x0d3b74203a0f4766; BYTE $0x06 // pinsrb xmm14, byte [r11 + r15 + 13], 6 + QUAD $0x0d0b74203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r11 + r9 + 13], 7 + QUAD $0x0d2374203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r11 + r12 + 13], 8 + QUAD $0x0d1b74203a0f4566; BYTE $0x09 // pinsrb xmm14, byte [r11 + rbx + 13], 9 + QUAD $0x0d3374203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r11 + r14 + 13], 10 + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + QUAD $0x0d0374203a0f4566; BYTE $0x0b // pinsrb xmm14, byte [r11 + rax + 13], 11 + QUAD $0x0d0374203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r11 + r8 + 13], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0d0374203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r11 + rax + 13], 13 + QUAD $0x0d0b74203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r11 + rcx + 13], 14 + LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] + QUAD $0x0d2b74203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r11 + r13 + 13], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x0e036c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r11 + rax + 14], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0e036c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r11 + rax + 14], 2 + QUAD $0x0e336c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r11 + rsi + 14], 3 + QUAD $0x0e136c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r11 + r10 + 14], 4 + QUAD $0x0e3b6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r11 + rdi + 14], 5 + QUAD $0x0e3b6c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r11 + r15 + 14], 6 + QUAD $0x0e0b6c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r11 + r9 + 14], 7 + QUAD $0x0e236c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r11 + r12 + 14], 8 + QUAD $0x0e1b6c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r11 + rbx + 14], 9 + QUAD $0x0e336c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r11 + r14 + 14], 10 + QUAD $0x0e136c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r11 + rdx + 14], 11 + QUAD $0x0e036c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r11 + r8 + 14], 12 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x0e036c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r11 + rax + 14], 13 + QUAD $0x0e0b6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r11 + rcx + 14], 14 + QUAD $0x0e2b6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r11 + r13 + 14], 15 + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] + QUAD $0x0f0b44203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r11 + rcx + 15], 1 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x0f2b44203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r11 + r13 + 15], 2 + QUAD $0x0f3344203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r11 + rsi + 15], 3 + QUAD $0x0f1344203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r11 + r10 + 15], 4 + QUAD $0x0f3b44203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r11 + rdi + 15], 5 + QUAD $0x0f3b44203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r11 + r15 + 15], 6 + QUAD $0x0f0b44203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r11 + r9 + 15], 7 + QUAD $0x0f2344203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r11 + r12 + 15], 8 + QUAD $0x0f1b44203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r11 + rbx + 15], 9 + QUAD $0x0f3344203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r11 + r14 + 15], 10 + QUAD $0x0f1344203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r11 + rdx + 15], 11 + QUAD $0x0f0344203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r11 + r8 + 15], 12 + QUAD $0x0f0344203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r11 + rax + 15], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0f0344203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r11 + rax + 15], 14 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0f0b44203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r11 + rcx + 15], 15 + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x11034c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r11 + rax + 17], 1 + QUAD $0x112b4c203a0f4366; BYTE $0x02 // pinsrb xmm1, byte [r11 + r13 + 17], 2 + QUAD $0x11334c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r11 + rsi + 17], 3 + QUAD $0x11134c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r11 + r10 + 17], 4 + QUAD $0x113b4c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r11 + rdi + 17], 5 + QUAD $0x113b4c203a0f4366; BYTE $0x06 // pinsrb xmm1, byte [r11 + r15 + 17], 6 + QUAD $0x110b4c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r11 + r9 + 17], 7 + QUAD $0x11234c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r11 + r12 + 17], 8 + QUAD $0x111b4c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r11 + rbx + 17], 9 + QUAD $0x11334c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r11 + r14 + 17], 10 + WORD $0x8949; BYTE $0xd6 // mov r14, rdx + QUAD $0x11134c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r11 + rdx + 17], 11 + QUAD $0x11034c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r11 + r8 + 17], 12 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x11034c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r11 + r8 + 17], 13 + LONG $0xda0f4166; BYTE $0xd2 // pminub xmm2, xmm10 + LONG $0x740f4166; BYTE $0xd2 // pcmpeqb xmm2, xmm10 + QUAD $0x000000d095df0f66 // pandn xmm2, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xda0f4566; BYTE $0xf2 // pminub xmm14, xmm10 + LONG $0x740f4566; BYTE $0xf2 // pcmpeqb xmm14, xmm10 + QUAD $0x0000e0b5df0f4466; BYTE $0x00 // pandn xmm14, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xeb0f4466; BYTE $0xf2 // por xmm14, xmm2 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + LONG $0x7cb60f41; WORD $0x1a13 // movzx edi, byte [r11 + rdx + 26] + LONG $0xd76e0f66 // movd xmm2, edi + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x11034c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r11 + rax + 17], 14 + LONG $0xda0f4566; BYTE $0xea // pminub xmm13, xmm10 + LONG $0x740f4566; BYTE $0xea // pcmpeqb xmm13, xmm10 + QUAD $0x0000f0addf0f4466; BYTE $0x00 // pandn xmm13, oword 240[rbp] /* [rip + .LCPI8_15] */ + LONG $0xeb0f4566; BYTE $0xee // por xmm13, xmm14 + LONG $0x7cb60f41; WORD $0x1b13 // movzx edi, byte [r11 + rdx + 27] + LONG $0x6e0f4466; BYTE $0xe7 // movd xmm12, edi + LONG $0xda0f4166; BYTE $0xc2 // pminub xmm0, xmm10 + LONG $0x740f4166; BYTE $0xc2 // pcmpeqb xmm0, xmm10 + QUAD $0x0000010085ef0f66 // pxor xmm0, oword 256[rbp] /* [rip + .LCPI8_16] */ + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0x45db0f66; BYTE $0x60 // pand xmm0, oword 96[rbp] /* [rip + .LCPI8_6] */ + LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 + LONG $0x7cb60f41; WORD $0x1c13 // movzx edi, byte [r11 + rdx + 28] + LONG $0x6e0f4466; BYTE $0xef // movd xmm13, edi + QUAD $0x110b4c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r11 + rcx + 17], 15 + WORD $0x8949; BYTE $0xcd // mov r13, rcx + QUAD $0x0000902484eb0f66; BYTE $0x00 // por xmm0, oword [rsp + 144] + QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 + LONG $0xda0f4166; BYTE $0xca // pminub xmm1, xmm10 + LONG $0x740f4166; BYTE $0xca // pcmpeqb xmm1, xmm10 + LONG $0x6f0f4166; BYTE $0xc2 // movdqa xmm0, xmm10 + LONG $0x6f0f4466; BYTE $0xf1 // movdqa xmm14, xmm1 + QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xdf0f4566; BYTE $0xf2 // pandn xmm14, xmm10 + LONG $0xfc0f4466; BYTE $0xf1 // paddb xmm14, xmm1 + QUAD $0x009024b47f0f4466; WORD $0x0000 // movdqa oword [rsp + 144], xmm14 + LONG $0x7cb60f41; WORD $0x1d13 // movzx edi, byte [r11 + rdx + 29] + LONG $0x6e0f4466; BYTE $0xd7 // movd xmm10, edi + LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] + QUAD $0x10036c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r11 + rax + 16], 1 + QUAD $0x12037c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r11 + rax + 18], 1 + QUAD $0x13037c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r11 + rax + 19], 1 + QUAD $0x140364203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r11 + rax + 20], 1 + QUAD $0x150374203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r11 + rax + 21], 1 + QUAD $0x16034c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r11 + rax + 22], 1 + QUAD $0x170344203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r11 + rax + 23], 1 + QUAD $0x18035c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r11 + rax + 24], 1 + QUAD $0x19035c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r11 + rax + 25], 1 + QUAD $0x1a0354203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rax + 26], 1 + QUAD $0x1b0364203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r11 + rax + 27], 1 + QUAD $0x1c036c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r11 + rax + 28], 1 + QUAD $0x1d0354203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r11 + rax + 29], 1 + LONG $0x7cb60f41; WORD $0x1e13 // movzx edi, byte [r11 + rdx + 30] + LONG $0x6e0f4466; BYTE $0xf7 // movd xmm14, edi + QUAD $0x1e0374203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r11 + rax + 30], 1 + LONG $0x7cb60f41; WORD $0x1f13 // movzx edi, byte [r11 + rdx + 31] + LONG $0xcf6e0f66 // movd xmm1, edi + QUAD $0x1f034c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r11 + rax + 31], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x10036c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r11 + rax + 16], 2 + QUAD $0x12037c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r11 + rax + 18], 2 + QUAD $0x13037c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r11 + rax + 19], 2 + QUAD $0x140364203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r11 + rax + 20], 2 + QUAD $0x150374203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r11 + rax + 21], 2 + QUAD $0x16034c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r11 + rax + 22], 2 + QUAD $0x170344203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r11 + rax + 23], 2 + QUAD $0x18035c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r11 + rax + 24], 2 + QUAD $0x19035c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r11 + rax + 25], 2 + QUAD $0x1a0354203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r11 + rax + 26], 2 + QUAD $0x1b0364203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r11 + rax + 27], 2 + QUAD $0x1c036c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r11 + rax + 28], 2 + QUAD $0x1d0354203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r11 + rax + 29], 2 + QUAD $0x1e0374203a0f4566; BYTE $0x02 // pinsrb xmm14, byte [r11 + rax + 30], 2 + QUAD $0x1f034c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r11 + rax + 31], 2 + QUAD $0x10336c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r11 + rsi + 16], 3 + QUAD $0x10136c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r11 + r10 + 16], 4 + QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] + QUAD $0x103b6c203a0f4166; BYTE $0x05 // pinsrb xmm5, byte [r11 + rdi + 16], 5 + QUAD $0x103b6c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r11 + r15 + 16], 6 + QUAD $0x100b6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r11 + r9 + 16], 7 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + QUAD $0x10236c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r11 + r12 + 16], 8 + QUAD $0x101b6c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r11 + rbx + 16], 9 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x10036c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r11 + rax + 16], 10 + QUAD $0x10336c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r11 + r14 + 16], 11 + LONG $0x24648b4c; BYTE $0x70 // mov r12, qword [rsp + 112] + QUAD $0x10236c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r11 + r12 + 16], 12 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 + QUAD $0x10036c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r11 + r8 + 16], 13 + LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] + QUAD $0x10036c203a0f4366; BYTE $0x0e // pinsrb xmm5, byte [r11 + r8 + 16], 14 + QUAD $0x102b6c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r11 + r13 + 16], 15 + LONG $0xe8da0f66 // pminub xmm5, xmm0 + LONG $0xe8740f66 // pcmpeqb xmm5, xmm0 + QUAD $0x12337c203a0f4166; BYTE $0x03 // pinsrb xmm7, byte [r11 + rsi + 18], 3 + QUAD $0x12137c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r11 + r10 + 18], 4 + QUAD $0x123b7c203a0f4166; BYTE $0x05 // pinsrb xmm7, byte [r11 + rdi + 18], 5 + QUAD $0x123b7c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r11 + r15 + 18], 6 + QUAD $0x120b7c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r11 + r9 + 18], 7 + QUAD $0x120b7c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r11 + rcx + 18], 8 + QUAD $0x121b7c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r11 + rbx + 18], 9 + QUAD $0x12037c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r11 + rax + 18], 10 + QUAD $0x12337c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r11 + r14 + 18], 11 + QUAD $0x12237c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r11 + r12 + 18], 12 + QUAD $0x12137c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r11 + rdx + 18], 13 + QUAD $0x12037c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r11 + r8 + 18], 14 + QUAD $0x122b7c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r11 + r13 + 18], 15 + QUAD $0x13337c203a0f4566; BYTE $0x03 // pinsrb xmm15, byte [r11 + rsi + 19], 3 + QUAD $0x13137c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r11 + r10 + 19], 4 + QUAD $0x133b7c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r11 + rdi + 19], 5 + QUAD $0x133b7c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r11 + r15 + 19], 6 + QUAD $0x130b7c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r11 + r9 + 19], 7 + QUAD $0x130b7c203a0f4566; BYTE $0x08 // pinsrb xmm15, byte [r11 + rcx + 19], 8 + QUAD $0x131b7c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r11 + rbx + 19], 9 + QUAD $0x13037c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r11 + rax + 19], 10 + QUAD $0x13337c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r11 + r14 + 19], 11 + QUAD $0x13237c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r11 + r12 + 19], 12 + QUAD $0x13137c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r11 + rdx + 19], 13 + QUAD $0x13037c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r11 + r8 + 19], 14 + QUAD $0x132b7c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r11 + r13 + 19], 15 + QUAD $0x143364203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r11 + rsi + 20], 3 + QUAD $0x141364203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r11 + r10 + 20], 4 + QUAD $0x143b64203a0f4166; BYTE $0x05 // pinsrb xmm4, byte [r11 + rdi + 20], 5 + QUAD $0x143b64203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r11 + r15 + 20], 6 + QUAD $0x140b64203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r11 + r9 + 20], 7 + QUAD $0x140b64203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r11 + rcx + 20], 8 + QUAD $0x141b64203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r11 + rbx + 20], 9 + QUAD $0x140364203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r11 + rax + 20], 10 + QUAD $0x143364203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r11 + r14 + 20], 11 + QUAD $0x142364203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r11 + r12 + 20], 12 + QUAD $0x141364203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r11 + rdx + 20], 13 + QUAD $0x140364203a0f4366; BYTE $0x0e // pinsrb xmm4, byte [r11 + r8 + 20], 14 + QUAD $0x142b64203a0f4366; BYTE $0x0f // pinsrb xmm4, byte [r11 + r13 + 20], 15 + QUAD $0x153374203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r11 + rsi + 21], 3 + QUAD $0x151374203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r11 + r10 + 21], 4 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x153b74203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r11 + rdi + 21], 5 + QUAD $0x153b74203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r11 + r15 + 21], 6 + QUAD $0x150b74203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r11 + r9 + 21], 7 + QUAD $0x150b74203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r11 + rcx + 21], 8 + QUAD $0x151b74203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r11 + rbx + 21], 9 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x151374203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r11 + r10 + 21], 10 + QUAD $0x153374203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r11 + r14 + 21], 11 + QUAD $0x152374203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r11 + r12 + 21], 12 + QUAD $0x151374203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r11 + rdx + 21], 13 + QUAD $0x150374203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r11 + r8 + 21], 14 + QUAD $0x000000a0addf0f66 // pandn xmm5, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xf8da0f66 // pminub xmm7, xmm0 + LONG $0xf8740f66 // pcmpeqb xmm7, xmm0 + QUAD $0x000000b0bddf0f66 // pandn xmm7, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xfdeb0f66 // por xmm7, xmm5 + LONG $0xda0f4466; BYTE $0xf8 // pminub xmm15, xmm0 + LONG $0x740f4466; BYTE $0xf8 // pcmpeqb xmm15, xmm0 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI8_12] */ + LONG $0xdf0f4466; BYTE $0xfd // pandn xmm15, xmm5 + LONG $0xeb0f4466; BYTE $0xff // por xmm15, xmm7 + QUAD $0x152b74203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r11 + r13 + 21], 15 + LONG $0xed760f66 // pcmpeqd xmm5, xmm5 + QUAD $0x00009024bc6f0f66; BYTE $0x00 // movdqa xmm7, oword [rsp + 144] + LONG $0xfdf80f66 // psubb xmm7, xmm5 + LONG $0xeb0f4466; BYTE $0xff // por xmm15, xmm7 + LONG $0xe0da0f66 // pminub xmm4, xmm0 + LONG $0xe0740f66 // pcmpeqb xmm4, xmm0 + QUAD $0x000000d0bd6f0f66 // movdqa xmm7, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xe7df0f66 // pandn xmm4, xmm7 + LONG $0xf0da0f66 // pminub xmm6, xmm0 + LONG $0xf0740f66 // pcmpeqb xmm6, xmm0 + QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xf7df0f66 // pandn xmm6, xmm7 + LONG $0xf4eb0f66 // por xmm6, xmm4 + QUAD $0x16334c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r11 + rsi + 22], 3 + QUAD $0x16034c203a0f4566; BYTE $0x04 // pinsrb xmm9, byte [r11 + rax + 22], 4 + QUAD $0x163b4c203a0f4566; BYTE $0x05 // pinsrb xmm9, byte [r11 + rdi + 22], 5 + QUAD $0x163b4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r11 + r15 + 22], 6 + QUAD $0x160b4c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r11 + r9 + 22], 7 + QUAD $0x160b4c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r11 + rcx + 22], 8 + QUAD $0x161b4c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r11 + rbx + 22], 9 + QUAD $0x16134c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r11 + r10 + 22], 10 + QUAD $0x16334c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r11 + r14 + 22], 11 + QUAD $0x16234c203a0f4766; BYTE $0x0c // pinsrb xmm9, byte [r11 + r12 + 22], 12 + QUAD $0x16134c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r11 + rdx + 22], 13 + QUAD $0x16034c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r11 + r8 + 22], 14 + QUAD $0x162b4c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r11 + r13 + 22], 15 + LONG $0xda0f4466; BYTE $0xc8 // pminub xmm9, xmm0 + LONG $0x740f4466; BYTE $0xc8 // pcmpeqb xmm9, xmm0 + QUAD $0x000000f0bd6f0f66 // movdqa xmm7, oword 240[rbp] /* [rip + .LCPI8_15] */ + LONG $0xdf0f4466; BYTE $0xcf // pandn xmm9, xmm7 + LONG $0xeb0f4466; BYTE $0xce // por xmm9, xmm6 + QUAD $0x173344203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r11 + rsi + 23], 3 + QUAD $0x170344203a0f4566; BYTE $0x04 // pinsrb xmm8, byte [r11 + rax + 23], 4 + QUAD $0x173b44203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r11 + rdi + 23], 5 + QUAD $0x173b44203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r11 + r15 + 23], 6 + QUAD $0x170b44203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r11 + r9 + 23], 7 + QUAD $0x170b44203a0f4566; BYTE $0x08 // pinsrb xmm8, byte [r11 + rcx + 23], 8 + QUAD $0x171b44203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r11 + rbx + 23], 9 + QUAD $0x171344203a0f4766; BYTE $0x0a // pinsrb xmm8, byte [r11 + r10 + 23], 10 + QUAD $0x173344203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r11 + r14 + 23], 11 + QUAD $0x172344203a0f4766; BYTE $0x0c // pinsrb xmm8, byte [r11 + r12 + 23], 12 + QUAD $0x171344203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r11 + rdx + 23], 13 + QUAD $0x170344203a0f4766; BYTE $0x0e // pinsrb xmm8, byte [r11 + r8 + 23], 14 + QUAD $0x172b44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r11 + r13 + 23], 15 + LONG $0xda0f4466; BYTE $0xc0 // pminub xmm8, xmm0 + LONG $0x740f4466; BYTE $0xc0 // pcmpeqb xmm8, xmm0 + LONG $0xef0f4466; BYTE $0xc5 // pxor xmm8, xmm5 + LONG $0xed760f66 // pcmpeqd xmm5, xmm5 + LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 + LONG $0x756f0f66; BYTE $0x60 // movdqa xmm6, oword 96[rbp] /* [rip + .LCPI8_6] */ + LONG $0xdb0f4466; BYTE $0xc6 // pand xmm8, xmm6 + LONG $0xeb0f4566; BYTE $0xc1 // por xmm8, xmm9 + QUAD $0x18335c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r11 + rsi + 24], 3 + QUAD $0x18035c203a0f4566; BYTE $0x04 // pinsrb xmm11, byte [r11 + rax + 24], 4 + QUAD $0x183b5c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r11 + rdi + 24], 5 + QUAD $0x183b5c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r11 + r15 + 24], 6 + QUAD $0x180b5c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r11 + r9 + 24], 7 + QUAD $0x180b5c203a0f4566; BYTE $0x08 // pinsrb xmm11, byte [r11 + rcx + 24], 8 + QUAD $0x181b5c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r11 + rbx + 24], 9 + QUAD $0x18135c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r11 + r10 + 24], 10 + QUAD $0x18335c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r11 + r14 + 24], 11 + QUAD $0x18235c203a0f4766; BYTE $0x0c // pinsrb xmm11, byte [r11 + r12 + 24], 12 + QUAD $0x18135c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r11 + rdx + 24], 13 + QUAD $0x18035c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r11 + r8 + 24], 14 + QUAD $0x19335c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r11 + rsi + 25], 3 + QUAD $0x19035c203a0f4166; BYTE $0x04 // pinsrb xmm3, byte [r11 + rax + 25], 4 + QUAD $0x193b5c203a0f4166; BYTE $0x05 // pinsrb xmm3, byte [r11 + rdi + 25], 5 + QUAD $0x193b5c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r11 + r15 + 25], 6 + QUAD $0x190b5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r11 + r9 + 25], 7 + QUAD $0x190b5c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r11 + rcx + 25], 8 + QUAD $0x191b5c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r11 + rbx + 25], 9 + QUAD $0x19135c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r11 + r10 + 25], 10 + QUAD $0x19335c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r11 + r14 + 25], 11 + QUAD $0x19235c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r11 + r12 + 25], 12 + QUAD $0x19135c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r11 + rdx + 25], 13 + QUAD $0x19035c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r11 + r8 + 25], 14 + QUAD $0x192b5c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r11 + r13 + 25], 15 + LONG $0xeb0f4566; BYTE $0xc7 // por xmm8, xmm15 + LONG $0xe06f0f66 // movdqa xmm4, xmm0 + LONG $0xd8da0f66 // pminub xmm3, xmm0 + LONG $0xd8740f66 // pcmpeqb xmm3, xmm0 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + QUAD $0x0000a08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 160[rbp] /* [rip + .LCPI8_10] */ + LONG $0xdf0f4166; BYTE $0xc1 // pandn xmm0, xmm9 + LONG $0xc3fc0f66 // paddb xmm0, xmm3 + QUAD $0x182b5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r11 + r13 + 24], 15 + LONG $0xda0f4466; BYTE $0xdc // pminub xmm11, xmm4 + LONG $0x740f4466; BYTE $0xdc // pcmpeqb xmm11, xmm4 + LONG $0xdf0f4566; BYTE $0xd9 // pandn xmm11, xmm9 + QUAD $0x1a3354203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r11 + rsi + 26], 3 + QUAD $0x1a0354203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r11 + rax + 26], 4 + QUAD $0x1a3b54203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r11 + rdi + 26], 5 + QUAD $0x1a3b54203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r11 + r15 + 26], 6 + QUAD $0x1a0b54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r11 + r9 + 26], 7 + QUAD $0x1a0b54203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r11 + rcx + 26], 8 + QUAD $0x1a1b54203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r11 + rbx + 26], 9 + QUAD $0x1a1354203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r11 + r10 + 26], 10 + QUAD $0x1a3354203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r11 + r14 + 26], 11 + QUAD $0x1a2354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r12 + 26], 12 + QUAD $0x1a1354203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rdx + 26], 13 + QUAD $0x1a0354203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r11 + r8 + 26], 14 + QUAD $0x1a2b54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r11 + r13 + 26], 15 + LONG $0xd4da0f66 // pminub xmm2, xmm4 + LONG $0xd4740f66 // pcmpeqb xmm2, xmm4 + QUAD $0x000000b095df0f66 // pandn xmm2, oword 176[rbp] /* [rip + .LCPI8_11] */ + LONG $0xeb0f4166; BYTE $0xd3 // por xmm2, xmm11 + QUAD $0x1b3364203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r11 + rsi + 27], 3 + QUAD $0x1b0364203a0f4566; BYTE $0x04 // pinsrb xmm12, byte [r11 + rax + 27], 4 + QUAD $0x1b3b64203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r11 + rdi + 27], 5 + QUAD $0x1b3b64203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r11 + r15 + 27], 6 + QUAD $0x1b0b64203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r11 + r9 + 27], 7 + QUAD $0x1b0b64203a0f4566; BYTE $0x08 // pinsrb xmm12, byte [r11 + rcx + 27], 8 + QUAD $0x1b1b64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r11 + rbx + 27], 9 + QUAD $0x1b1364203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r11 + r10 + 27], 10 + QUAD $0x1b3364203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r11 + r14 + 27], 11 + QUAD $0x1b2364203a0f4766; BYTE $0x0c // pinsrb xmm12, byte [r11 + r12 + 27], 12 + QUAD $0x1b1364203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r11 + rdx + 27], 13 + QUAD $0x1b0364203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r11 + r8 + 27], 14 + QUAD $0x1b2b64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r11 + r13 + 27], 15 + LONG $0xda0f4466; BYTE $0xe4 // pminub xmm12, xmm4 + LONG $0x740f4466; BYTE $0xe4 // pcmpeqb xmm12, xmm4 + LONG $0xdc6f0f66 // movdqa xmm3, xmm4 + QUAD $0x0000c0a5df0f4466; BYTE $0x00 // pandn xmm12, oword 192[rbp] /* [rip + .LCPI8_12] */ + LONG $0xeb0f4466; BYTE $0xe2 // por xmm12, xmm2 + LONG $0xc5f80f66 // psubb xmm0, xmm5 + LONG $0xeb0f4466; BYTE $0xe0 // por xmm12, xmm0 + QUAD $0x1c336c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r11 + rsi + 28], 3 + QUAD $0x1d3354203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r11 + rsi + 29], 3 + QUAD $0x1e3374203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r11 + rsi + 30], 3 + QUAD $0x1f334c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r11 + rsi + 31], 3 + QUAD $0x1c036c203a0f4566; BYTE $0x04 // pinsrb xmm13, byte [r11 + rax + 28], 4 + QUAD $0x1d0354203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r11 + rax + 29], 4 + QUAD $0x1e0374203a0f4566; BYTE $0x04 // pinsrb xmm14, byte [r11 + rax + 30], 4 + QUAD $0x1f034c203a0f4166; BYTE $0x04 // pinsrb xmm1, byte [r11 + rax + 31], 4 + QUAD $0x1c3b6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r11 + rdi + 28], 5 + QUAD $0x1d3b54203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r11 + rdi + 29], 5 + QUAD $0x1e3b74203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r11 + rdi + 30], 5 + QUAD $0x1f3b4c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r11 + rdi + 31], 5 + QUAD $0x1c3b6c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r11 + r15 + 28], 6 + QUAD $0x1d3b54203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r11 + r15 + 29], 6 + QUAD $0x1e3b74203a0f4766; BYTE $0x06 // pinsrb xmm14, byte [r11 + r15 + 30], 6 + QUAD $0x1f3b4c203a0f4366; BYTE $0x06 // pinsrb xmm1, byte [r11 + r15 + 31], 6 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x1c0b6c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r11 + r9 + 28], 7 + QUAD $0x1d0b54203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r11 + r9 + 29], 7 + QUAD $0x1e0b74203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r11 + r9 + 30], 7 + QUAD $0x1f0b4c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r11 + r9 + 31], 7 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x1c0b6c203a0f4566; BYTE $0x08 // pinsrb xmm13, byte [r11 + rcx + 28], 8 + QUAD $0x1d0b54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r11 + rcx + 29], 8 + QUAD $0x1e0b74203a0f4566; BYTE $0x08 // pinsrb xmm14, byte [r11 + rcx + 30], 8 + QUAD $0x1f0b4c203a0f4166; BYTE $0x08 // pinsrb xmm1, byte [r11 + rcx + 31], 8 + QUAD $0x1c1b6c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r11 + rbx + 28], 9 + QUAD $0x1d1b54203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r11 + rbx + 29], 9 + QUAD $0x1e1b74203a0f4566; BYTE $0x09 // pinsrb xmm14, byte [r11 + rbx + 30], 9 + QUAD $0x1f1b4c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r11 + rbx + 31], 9 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x1c136c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r11 + r10 + 28], 10 + QUAD $0x1d1354203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r11 + r10 + 29], 10 + QUAD $0x1e1374203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r11 + r10 + 30], 10 + QUAD $0x1f134c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r11 + r10 + 31], 10 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x1c036c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r11 + rax + 28], 11 + QUAD $0x1d0354203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r11 + rax + 29], 11 + QUAD $0x1e0374203a0f4566; BYTE $0x0b // pinsrb xmm14, byte [r11 + rax + 30], 11 + QUAD $0x1f034c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r11 + rax + 31], 11 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x1c236c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r11 + r12 + 28], 12 + QUAD $0x1d2354203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r11 + r12 + 29], 12 + QUAD $0x1e2374203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r11 + r12 + 30], 12 + QUAD $0x1f234c203a0f4366; BYTE $0x0c // pinsrb xmm1, byte [r11 + r12 + 31], 12 + QUAD $0x1c136c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r11 + rdx + 28], 13 + QUAD $0x1d1354203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r11 + rdx + 29], 13 + QUAD $0x1e1374203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r11 + rdx + 30], 13 + QUAD $0x1f134c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r11 + rdx + 31], 13 + QUAD $0x1c036c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r11 + r8 + 28], 14 + QUAD $0x1d0354203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r11 + r8 + 29], 14 + QUAD $0x1e0374203a0f4766; BYTE $0x0e // pinsrb xmm14, byte [r11 + r8 + 30], 14 + QUAD $0x1f034c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r11 + r8 + 31], 14 + WORD $0x894c; BYTE $0xe8 // mov rax, r13 + QUAD $0x1c2b6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r11 + r13 + 28], 15 + QUAD $0x1d2b54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r11 + r13 + 29], 15 + QUAD $0x1e2b74203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r11 + r13 + 30], 15 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0xda0f4466; BYTE $0xec // pminub xmm13, xmm4 + LONG $0x740f4466; BYTE $0xec // pcmpeqb xmm13, xmm4 + QUAD $0x0000d0addf0f4466; BYTE $0x00 // pandn xmm13, oword 208[rbp] /* [rip + .LCPI8_13] */ + LONG $0xda0f4466; BYTE $0xd4 // pminub xmm10, xmm4 + LONG $0x740f4466; BYTE $0xd4 // pcmpeqb xmm10, xmm4 + QUAD $0x0000e095df0f4466; BYTE $0x00 // pandn xmm10, oword 224[rbp] /* [rip + .LCPI8_14] */ + LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 + QUAD $0x1f2b4c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r11 + r13 + 31], 15 + LONG $0xda0f4466; BYTE $0xf4 // pminub xmm14, xmm4 + LONG $0x740f4466; BYTE $0xf4 // pcmpeqb xmm14, xmm4 + LONG $0xdf0f4466; BYTE $0xf7 // pandn xmm14, xmm7 + LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 + LONG $0xccda0f66 // pminub xmm1, xmm4 + LONG $0xcc740f66 // pcmpeqb xmm1, xmm4 + LONG $0xcdef0f66 // pxor xmm1, xmm5 + LONG $0xf1710f66; BYTE $0x07 // psllw xmm1, 7 + LONG $0xcedb0f66 // pand xmm1, xmm6 + LONG $0xeb0f4166; BYTE $0xce // por xmm1, xmm14 + LONG $0xeb0f4166; BYTE $0xcc // por xmm1, xmm12 + LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 + LONG $0xc1600f66 // punpcklbw xmm0, xmm1 + QUAD $0x0000a024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 160] + LONG $0xd46f0f66 // movdqa xmm2, xmm4 + QUAD $0x0000b024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 176] + LONG $0xd5600f66 // punpcklbw xmm2, xmm5 + LONG $0xda6f0f66 // movdqa xmm3, xmm2 + LONG $0xd8610f66 // punpcklwd xmm3, xmm0 + LONG $0xd0690f66 // punpckhwd xmm2, xmm0 + LONG $0x680f4466; BYTE $0xc1 // punpckhbw xmm8, xmm1 + LONG $0xe5680f66 // punpckhbw xmm4, xmm5 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 + LONG $0x690f4166; BYTE $0xe0 // punpckhwd xmm4, xmm8 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x7f0f41f3; WORD $0x8e64; BYTE $0x30 // movdqu oword [r14 + 4*rcx + 48], xmm4 + LONG $0x7f0f41f3; WORD $0x8e44; BYTE $0x20 // movdqu oword [r14 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x8e54; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm2 + LONG $0x7f0f41f3; WORD $0x8e1c // movdqu oword [r14 + 4*rcx], xmm3 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + JNE LBB8_226 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x000000f8248c3b48 // cmp rcx, qword [rsp + 248] + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + LONG $0x243c8a44 // mov r15b, byte [rsp] + QUAD $0x0000010824b48b48 // mov rsi, qword [rsp + 264] + JNE LBB8_160 + JMP LBB8_164 TEXT ·_comparison_greater_equal_arr_arr_sse4(SB), $80-48 @@ -45577,71 +46883,85 @@ TEXT ·_comparison_greater_equal_arr_arr_sse4(SB), $80-48 MOVQ offset+40(FP), R9 ADDQ $8, SP - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB9_29 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB9_35 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB9_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB9_68 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB9_79 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_22 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_20: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_20 - LONG $0x01c68349 // add r14, 1 - -LBB9_22: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_26 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB9_83 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB9_97 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_26 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax LBB9_24: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x0c8b; BYTE $0x86 // mov ecx, dword [rsi + 4*rax] + WORD $0x0c3b; BYTE $0x82 // cmp ecx, dword [rdx + 4*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_24 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_26: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_28: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_32 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_30: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] LONG $0x2454930f; BYTE $0x14 // setae byte [rsp + 20] @@ -45665,7 +46985,7 @@ LBB9_24: LONG $0x2454930f; BYTE $0x09 // setae byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd3930f41 // setae r11b @@ -45705,7 +47025,7 @@ LBB9_24: LONG $0x2454930f; BYTE $0x0b // setae byte [rsp + 11] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] + LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd1930f41 // setae r9b @@ -45714,10 +47034,10 @@ LBB9_24: LONG $0x2454930f; BYTE $0x13 // setae byte [rsp + 19] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] + LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] + LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] LONG $0x2454930f; BYTE $0x0f // setae byte [rsp + 15] @@ -45732,10 +47052,10 @@ LBB9_24: LONG $0x2454930f; BYTE $0x11 // setae byte [rsp + 17] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] - LONG $0xd7930f40 // setae dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd0930f41 // setae r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -45744,34 +47064,34 @@ LBB9_24: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -45784,22 +47104,23 @@ LBB9_24: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -45816,26 +47137,25 @@ LBB9_24: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_24 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_30 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_26: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_28: +LBB9_34: WORD $0x048b; BYTE $0x8e // mov eax, dword [rsi + 4*rcx] WORD $0x043b; BYTE $0x8a // cmp eax, dword [rdx + 4*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -45843,75 +47163,89 @@ LBB9_28: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_28 - JMP LBB9_123 - -LBB9_29: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB9_30 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB9_101 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB9_112 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_50 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_48: - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_48 - LONG $0x01c68349 // add r14, 1 - -LBB9_50: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_54 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 - -LBB9_52: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_34 + JMP LBB9_153 + +LBB9_35: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB9_36 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB9_125 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB9_139 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_62 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_60 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_58: + LONG $0x04100ff2; BYTE $0xc6 // movsd xmm0, qword [rsi + 8*rax] + LONG $0x042e0f66; BYTE $0xc2 // ucomisd xmm0, qword [rdx + 8*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_58 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_60: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_62: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_66 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + +LBB9_64: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06100ff2 // movsd xmm0, qword [rsi] LONG $0x4e100ff2; BYTE $0x08 // movsd xmm1, qword [rsi + 8] LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] @@ -45935,7 +47269,7 @@ LBB9_52: LONG $0x46100ff2; BYTE $0x38 // movsd xmm0, qword [rsi + 56] LONG $0xd5930f41 // setae r13b LONG $0x422e0f66; BYTE $0x38 // ucomisd xmm0, qword [rdx + 56] - LONG $0xd7930f41 // setae r15b + LONG $0xd6930f41 // setae r14b LONG $0x46100ff2; BYTE $0x40 // movsd xmm0, qword [rsi + 64] LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] LONG $0x46100ff2; BYTE $0x48 // movsd xmm0, qword [rsi + 72] @@ -45966,7 +47300,7 @@ LBB9_52: LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] QUAD $0x00000088822e0f66 // ucomisd xmm0, qword [rdx + 136] QUAD $0x0000009086100ff2 // movsd xmm0, qword [rsi + 144] - LONG $0xd6930f41 // setae r14b + LONG $0xd7930f41 // setae r15b QUAD $0x00000090822e0f66 // ucomisd xmm0, qword [rdx + 144] QUAD $0x0000009886100ff2 // movsd xmm0, qword [rsi + 152] LONG $0xd4930f41 // setae r12b @@ -46012,8 +47346,8 @@ LBB9_52: WORD $0xc000 // add al, al LONG $0x04244402 // add al, byte [rsp + 4] LONG $0x06e5c041 // shl r13b, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0845; BYTE $0xef // or r15b, r13b + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0845; BYTE $0xee // or r14b, r13b LONG $0x6cb60f44; WORD $0x0524 // movzx r13d, byte [rsp + 5] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0841; BYTE $0xc5 // or r13b, al @@ -46043,17 +47377,17 @@ LBB9_52: LONG $0x06e1c041 // shl r9b, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0e // add r14b, byte [rsp + 14] + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x0e // add r15b, byte [rsp + 14] LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0845; BYTE $0xfc // or r12b, r15b LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -46061,12 +47395,12 @@ LBB9_52: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc0 // or r8b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -46091,23 +47425,22 @@ LBB9_52: LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xc7 // or dil, al WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x02468845 // mov byte [r14 + 2], r8b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x02478845 // mov byte [r15 + 2], r8b + LONG $0x037f8841 // mov byte [r15 + 3], dil LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB9_52 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB9_64 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB9_54: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_66: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_56: +LBB9_68: LONG $0x04100ff2; BYTE $0xce // movsd xmm0, qword [rsi + 8*rcx] LONG $0x042e0f66; BYTE $0xca // ucomisd xmm0, qword [rdx + 8*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -46115,75 +47448,95 @@ LBB9_56: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_56 - JMP LBB9_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_68 + JMP LBB9_153 LBB9_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB9_57 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_6: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + JE LBB9_69 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_11 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax + JLE LBB9_9 + WORD $0x6349; BYTE $0xd9 // movsxd rbx, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB9_7: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0xd49d0f41 // setge r12b + WORD $0xf641; BYTE $0xdc // neg r12b + LONG $0x077b8d48 // lea rdi, [rbx + 7] + WORD $0x8548; BYTE $0xdb // test rbx, rbx + LONG $0xfb490f48 // cmovns rdi, rbx LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_6 - LONG $0x01c68349 // add r14, 1 - -LBB9_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_12 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB9_10: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + LONG $0x34b60f45; BYTE $0x3f // movzx r14d, byte [r15 + rdi] + QUAD $0x00000000fd3c8d44 // lea r15d, [8*rdi] + WORD $0xd989 // mov ecx, ebx + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x3045; BYTE $0xf4 // xor r12b, r14b + WORD $0x2044; BYTE $0xe0 // and al, r12b + WORD $0x3044; BYTE $0xf0 // xor al, r14b + LONG $0x38048841 // mov byte [r8 + rdi], al + LONG $0x01c38349 // add r11, 1 + LONG $0x01c38348 // add rbx, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB9_7 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB9_9: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_11: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_15 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB9_13: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x9d0f; BYTE $0xd1 // setge cl LONG $0x0246b60f // movzx eax, byte [rsi + 2] @@ -46203,7 +47556,7 @@ LBB9_10: LONG $0x24549d0f; BYTE $0x04 // setge byte [rsp + 4] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd79d0f41 // setge r15b + LONG $0xd69d0f41 // setge r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x24549d0f; BYTE $0x07 // setge byte [rsp + 7] @@ -46218,7 +47571,7 @@ LBB9_10: LONG $0xd39d0f41 // setge r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd69d0f41 // setge r14b + LONG $0xd79d0f41 // setge r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] LONG $0x24549d0f; BYTE $0x05 // setge byte [rsp + 5] @@ -46278,12 +47631,12 @@ LBB9_10: WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] LONG $0xd09d0f41 // setge r8b WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x30244c02 // add cl, byte [rsp + 48] WORD $0xc889 // mov eax, ecx LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al @@ -46305,26 +47658,26 @@ LBB9_10: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x06 // movzx edi, byte [rsp + 6] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0d // add r12b, byte [rsp + 13] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -46332,12 +47685,12 @@ LBB9_10: LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al @@ -46363,23 +47716,22 @@ LBB9_10: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB9_10 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB9_12: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB9_13 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB9_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_14: +LBB9_17: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x0e1cb60f // movzx ebx, byte [rsi + rcx] WORD $0x1c3a; BYTE $0x0a // cmp bl, byte [rdx + rcx] @@ -46387,77 +47739,91 @@ LBB9_14: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_14 - JMP LBB9_123 - -LBB9_30: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB9_90 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB9_123 - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_36 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_34: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_34 - LONG $0x01c68349 // add r14, 1 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_17 + JMP LBB9_153 LBB9_36: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_40 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB9_38: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB9_111 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB9_153 + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_45 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_43 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_41: + LONG $0xc60c8b48 // mov rcx, qword [rsi + 8*rax] + LONG $0xc20c3b48 // cmp rcx, qword [rdx + 8*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_41 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_43: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_45: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_49 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_47: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] LONG $0x2454930f; BYTE $0x14 // setae byte [rsp + 20] @@ -46481,7 +47847,7 @@ LBB9_38: LONG $0x2454930f; BYTE $0x09 // setae byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd3930f41 // setae r11b @@ -46521,7 +47887,7 @@ LBB9_38: LONG $0x2454930f; BYTE $0x0b // setae byte [rsp + 11] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] + LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd1930f41 // setae r9b @@ -46530,10 +47896,10 @@ LBB9_38: LONG $0x2454930f; BYTE $0x13 // setae byte [rsp + 19] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] + LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] + LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] LONG $0x2454930f; BYTE $0x0f // setae byte [rsp + 15] @@ -46548,10 +47914,10 @@ LBB9_38: LONG $0x2454930f; BYTE $0x11 // setae byte [rsp + 17] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] - LONG $0xd7930f40 // setae dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd0930f41 // setae r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -46560,34 +47926,34 @@ LBB9_38: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -46600,22 +47966,23 @@ LBB9_38: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -46632,26 +47999,25 @@ LBB9_38: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_38 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_47 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_40: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_49: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_42: +LBB9_51: LONG $0xce048b48 // mov rax, qword [rsi + 8*rcx] LONG $0xca043b48 // cmp rax, qword [rdx + 8*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -46659,73 +48025,87 @@ LBB9_42: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_42 - JMP LBB9_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_51 + JMP LBB9_153 -LBB9_68: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_72 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_70: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_70 - LONG $0x01c68349 // add r14, 1 +LBB9_83: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_90 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_88 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_86: + LONG $0x460cb70f // movzx ecx, word [rsi + 2*rax] + LONG $0x420c3b66 // cmp cx, word [rdx + 2*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_86 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB9_72: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_76 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 +LBB9_88: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 -LBB9_74: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_90: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_94 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_92: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] LONG $0x2454930f; BYTE $0x14 // setae byte [rsp + 20] @@ -46749,7 +48129,7 @@ LBB9_74: LONG $0x2454930f; BYTE $0x09 // setae byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd3930f41 // setae r11b @@ -46789,7 +48169,7 @@ LBB9_74: LONG $0x2454930f; BYTE $0x0b // setae byte [rsp + 11] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] + LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd1930f41 // setae r9b @@ -46798,10 +48178,10 @@ LBB9_74: LONG $0x2454930f; BYTE $0x13 // setae byte [rsp + 19] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] + LONG $0x2454930f; BYTE $0x0c // setae byte [rsp + 12] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] + LONG $0x2454930f; BYTE $0x0d // setae byte [rsp + 13] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] LONG $0x2454930f; BYTE $0x0f // setae byte [rsp + 15] @@ -46816,10 +48196,10 @@ LBB9_74: LONG $0x2454930f; BYTE $0x11 // setae byte [rsp + 17] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] - LONG $0xd7930f40 // setae dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd0930f41 // setae r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -46828,34 +48208,34 @@ LBB9_74: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -46868,22 +48248,23 @@ LBB9_74: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -46900,26 +48281,25 @@ LBB9_74: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_74 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_92 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_76: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_78: +LBB9_96: LONG $0x4e04b70f // movzx eax, word [rsi + 2*rcx] LONG $0x4a043b66 // cmp ax, word [rdx + 2*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -46927,73 +48307,87 @@ LBB9_78: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_78 - JMP LBB9_123 - -LBB9_79: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_83 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_81: - WORD $0xb70f; BYTE $0x0e // movzx ecx, word [rsi] - LONG $0x02c68348 // add rsi, 2 - WORD $0x3b66; BYTE $0x0a // cmp cx, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_81 - LONG $0x01c68349 // add r14, 1 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_96 + JMP LBB9_153 + +LBB9_97: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_104 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_102 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB9_83: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_87 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB9_85: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_100: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x461cb70f // movzx ebx, word [rsi + 2*rax] + LONG $0x421c3b66 // cmp bx, word [rdx + 2*rax] + LONG $0xd39d0f41 // setge r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfec28349 // add r10, -2 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_100 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_102: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_104: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_108 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_106: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb70f; BYTE $0x06 // movzx eax, word [rsi] LONG $0x024eb70f // movzx ecx, word [rsi + 2] WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] LONG $0x024a3b66 // cmp cx, word [rdx + 2] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] LONG $0x0446b70f // movzx eax, word [rsi + 4] LONG $0x04423b66 // cmp ax, word [rdx + 4] LONG $0x24549d0f; BYTE $0x14 // setge byte [rsp + 20] @@ -47017,7 +48411,7 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x09 // setge byte [rsp + 9] LONG $0x1246b70f // movzx eax, word [rsi + 18] LONG $0x12423b66 // cmp ax, word [rdx + 18] - LONG $0xd09d0f41 // setge r8b + LONG $0xd79d0f40 // setge dil LONG $0x1446b70f // movzx eax, word [rsi + 20] LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd39d0f41 // setge r11b @@ -47057,7 +48451,7 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x0b // setge byte [rsp + 11] LONG $0x2c423b66 // cmp ax, word [rdx + 44] LONG $0x2e46b70f // movzx eax, word [rsi + 46] - LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] + LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] LONG $0x2e423b66 // cmp ax, word [rdx + 46] LONG $0x3046b70f // movzx eax, word [rsi + 48] LONG $0xd19d0f41 // setge r9b @@ -47066,10 +48460,10 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x13 // setge byte [rsp + 19] LONG $0x32423b66 // cmp ax, word [rdx + 50] LONG $0x3446b70f // movzx eax, word [rsi + 52] - LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] + LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] LONG $0x34423b66 // cmp ax, word [rdx + 52] LONG $0x3646b70f // movzx eax, word [rsi + 54] - LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] + LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] LONG $0x36423b66 // cmp ax, word [rdx + 54] LONG $0x3846b70f // movzx eax, word [rsi + 56] LONG $0x24549d0f; BYTE $0x0f // setge byte [rsp + 15] @@ -47084,10 +48478,10 @@ LBB9_85: LONG $0x24549d0f; BYTE $0x11 // setge byte [rsp + 17] LONG $0x40c68348 // add rsi, 64 LONG $0x3e423b66 // cmp ax, word [rdx + 62] - LONG $0xd79d0f40 // setge dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09d0f41 // setge r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -47096,34 +48490,34 @@ LBB9_85: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -47136,22 +48530,23 @@ LBB9_85: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -47168,26 +48563,25 @@ LBB9_85: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x40c28348 // add rdx, 64 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_85 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] - -LBB9_87: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + JNE LBB9_106 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + +LBB9_108: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_89: +LBB9_110: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0x4e3cb70f // movzx edi, word [rsi + 2*rcx] LONG $0x4a3c3b66 // cmp di, word [rdx + 2*rcx] @@ -47195,73 +48589,87 @@ LBB9_89: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_89 - JMP LBB9_123 - -LBB9_101: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_105 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_103: - WORD $0x8b48; BYTE $0x0e // mov rcx, qword [rsi] - LONG $0x08c68348 // add rsi, 8 - WORD $0x3b48; BYTE $0x0a // cmp rcx, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_103 - LONG $0x01c68349 // add r14, 1 - -LBB9_105: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_109 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - -LBB9_107: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_110 + JMP LBB9_153 + +LBB9_125: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_132 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_130 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_128: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0xc61c8b48 // mov rbx, qword [rsi + 8*rax] + LONG $0xc21c3b48 // cmp rbx, qword [rdx + 8*rax] + LONG $0xd39d0f41 // setge r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xf8c28349 // add r10, -8 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_128 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_130: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_132: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_136 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_134: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x8b48; BYTE $0x06 // mov rax, qword [rsi] LONG $0x084e8b48 // mov rcx, qword [rsi + 8] WORD $0x3b48; BYTE $0x02 // cmp rax, qword [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] LONG $0x084a3b48 // cmp rcx, qword [rdx + 8] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] LONG $0x10468b48 // mov rax, qword [rsi + 16] LONG $0x10423b48 // cmp rax, qword [rdx + 16] LONG $0x24549d0f; BYTE $0x14 // setge byte [rsp + 20] @@ -47285,7 +48693,7 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x09 // setge byte [rsp + 9] LONG $0x48468b48 // mov rax, qword [rsi + 72] LONG $0x48423b48 // cmp rax, qword [rdx + 72] - LONG $0xd09d0f41 // setge r8b + LONG $0xd79d0f40 // setge dil LONG $0x50468b48 // mov rax, qword [rsi + 80] LONG $0x50423b48 // cmp rax, qword [rdx + 80] LONG $0xd39d0f41 // setge r11b @@ -47325,7 +48733,7 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x0b // setge byte [rsp + 11] LONG $0xb0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 176] LONG $0xb8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 184] - LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] + LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] LONG $0xb8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 184] LONG $0xc0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 192] LONG $0xd19d0f41 // setge r9b @@ -47334,10 +48742,10 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x13 // setge byte [rsp + 19] LONG $0xc8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 200] LONG $0xd0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 208] - LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] + LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] LONG $0xd0823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 208] LONG $0xd8868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 216] - LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] + LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] LONG $0xd8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 216] LONG $0xe0868b48; WORD $0x0000; BYTE $0x00 // mov rax, qword [rsi + 224] LONG $0x24549d0f; BYTE $0x0f // setge byte [rsp + 15] @@ -47352,10 +48760,10 @@ LBB9_107: LONG $0x24549d0f; BYTE $0x11 // setge byte [rsp + 17] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xf8823b48; WORD $0x0000; BYTE $0x00 // cmp rax, qword [rdx + 248] - LONG $0xd79d0f40 // setge dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09d0f41 // setge r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -47364,34 +48772,34 @@ LBB9_107: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -47404,22 +48812,23 @@ LBB9_107: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -47436,26 +48845,25 @@ LBB9_107: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_107 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_134 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_109: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_136: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_111: +LBB9_138: LONG $0x01418d4c // lea r8, [rcx + 1] LONG $0xce3c8b48 // mov rdi, qword [rsi + 8*rcx] LONG $0xca3c3b48 // cmp rdi, qword [rdx + 8*rcx] @@ -47463,67 +48871,81 @@ LBB9_111: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_111 - JMP LBB9_123 - -LBB9_112: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_116 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_114: - LONG $0x06100ff3 // movss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_114 - LONG $0x01c68349 // add r14, 1 - -LBB9_116: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_120 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - LONG $0x247c894c; BYTE $0x28 // mov qword [rsp + 40], r15 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_138 + JMP LBB9_153 + +LBB9_139: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_146 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_144 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax + +LBB9_142: + LONG $0x04100ff3; BYTE $0x86 // movss xmm0, dword [rsi + 4*rax] + LONG $0x82042e0f // ucomiss xmm0, dword [rdx + 4*rax] + LONG $0x010c8d49 // lea rcx, [r9 + rax] + LONG $0x0000bb41; WORD $0x0000 // mov r11d, 0 + LONG $0xffd38041 // adc r11b, -1 + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_142 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + +LBB9_144: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_146: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_150 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax -LBB9_118: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_148: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 LONG $0x06100ff3 // movss xmm0, dword [rsi] LONG $0x4e100ff3; BYTE $0x04 // movss xmm1, dword [rsi + 4] WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] @@ -47547,7 +48969,7 @@ LBB9_118: LONG $0x46100ff3; BYTE $0x1c // movss xmm0, dword [rsi + 28] LONG $0xd5930f41 // setae r13b LONG $0x1c422e0f // ucomiss xmm0, dword [rdx + 28] - LONG $0xd7930f41 // setae r15b + LONG $0xd6930f41 // setae r14b LONG $0x46100ff3; BYTE $0x20 // movss xmm0, dword [rsi + 32] LONG $0x20422e0f // ucomiss xmm0, dword [rdx + 32] LONG $0x46100ff3; BYTE $0x24 // movss xmm0, dword [rsi + 36] @@ -47578,7 +49000,7 @@ LBB9_118: LONG $0x2454930f; BYTE $0x0e // setae byte [rsp + 14] LONG $0x44422e0f // ucomiss xmm0, dword [rdx + 68] LONG $0x46100ff3; BYTE $0x48 // movss xmm0, dword [rsi + 72] - LONG $0xd6930f41 // setae r14b + LONG $0xd7930f41 // setae r15b LONG $0x48422e0f // ucomiss xmm0, dword [rdx + 72] LONG $0x46100ff3; BYTE $0x4c // movss xmm0, dword [rsi + 76] LONG $0xd4930f41 // setae r12b @@ -47624,8 +49046,8 @@ LBB9_118: WORD $0xc000 // add al, al LONG $0x04244402 // add al, byte [rsp + 4] LONG $0x06e5c041 // shl r13b, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0845; BYTE $0xef // or r15b, r13b + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0845; BYTE $0xee // or r14b, r13b LONG $0x6cb60f44; WORD $0x0524 // movzx r13d, byte [rsp + 5] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0841; BYTE $0xc5 // or r13b, al @@ -47655,17 +49077,17 @@ LBB9_118: LONG $0x06e1c041 // shl r9b, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0844; BYTE $0xcb // or bl, r9b - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al - WORD $0x0045; BYTE $0xf6 // add r14b, r14b - LONG $0x24740244; BYTE $0x0e // add r14b, byte [rsp + 14] + WORD $0x0045; BYTE $0xff // add r15b, r15b + LONG $0x247c0244; BYTE $0x0e // add r15b, byte [rsp + 14] LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + WORD $0x0845; BYTE $0xfc // or r12b, r15b LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -47673,12 +49095,12 @@ LBB9_118: LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc0 // or r8b, al LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xc000 // add al, al @@ -47703,23 +49125,22 @@ LBB9_118: LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xc7 // or dil, al WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x02468845 // mov byte [r14 + 2], r8b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x02478845 // mov byte [r15 + 2], r8b + LONG $0x037f8841 // mov byte [r15 + 3], dil LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 - JNE LBB9_118 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff30 // add qword [rsp + 48], -1 + JNE LBB9_148 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] -LBB9_120: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_150: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_122: +LBB9_152: LONG $0x04100ff3; BYTE $0x8e // movss xmm0, dword [rsi + 4*rcx] LONG $0x8a042e0f // ucomiss xmm0, dword [rdx + 4*rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -47727,71 +49148,90 @@ LBB9_122: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_122 - JMP LBB9_123 - -LBB9_57: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_61 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB9_59: - WORD $0xb60f; BYTE $0x0e // movzx ecx, byte [rsi] - LONG $0x01c68348 // add rsi, 1 - WORD $0x0a3a // cmp cl, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0x0000ba41; WORD $0x0000 // mov r10d, 0 - LONG $0xffd28041 // adc r10b, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000dd0c8d44 // lea r9d, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2044; BYTE $0xd7 // and dil, r10b - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_59 - LONG $0x01c68349 // add r14, 1 - -LBB9_61: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_65 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 - LONG $0x247c894c; BYTE $0x20 // mov qword [rsp + 32], r15 - -LBB9_63: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_152 + JMP LBB9_153 + +LBB9_69: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_76 + LONG $0x000008b8; BYTE $0x00 // mov eax, 8 + WORD $0x2944; BYTE $0xc8 // sub eax, r9d + WORD $0x394c; BYTE $0xe8 // cmp rax, r13 + LONG $0xc54f0f49 // cmovg rax, r13 + WORD $0x8548; BYTE $0xc0 // test rax, rax + JLE LBB9_74 + WORD $0x634d; BYTE $0xe1 // movsxd r12, r9d + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0xf749; BYTE $0xd9 // neg r9 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + +LBB9_72: + LONG $0x0cb60f42; BYTE $0x1e // movzx ecx, byte [rsi + r11] + LONG $0x1a0c3a42 // cmp cl, byte [rdx + r11] + LONG $0x000000bf; BYTE $0x00 // mov edi, 0 + LONG $0xffd78040 // adc dil, -1 + LONG $0x24448d49; BYTE $0x07 // lea rax, [r12 + 7] + WORD $0x854d; BYTE $0xe4 // test r12, r12 + LONG $0xc4490f49 // cmovns rax, r12 + LONG $0x03f8c148 // sar rax, 3 + LONG $0x34b60f45; BYTE $0x07 // movzx r14d, byte [r15 + rax] + QUAD $0x00000000c53c8d44 // lea r15d, [8*rax] + WORD $0x8944; BYTE $0xe1 // mov ecx, r12d + WORD $0x2944; BYTE $0xf9 // sub ecx, r15d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + WORD $0x3044; BYTE $0xf7 // xor dil, r14b + WORD $0x2040; BYTE $0xfb // and bl, dil + WORD $0x3044; BYTE $0xf3 // xor bl, r14b + LONG $0x001c8841 // mov byte [r8 + rax], bl + LONG $0x01c38349 // add r11, 1 + LONG $0x01c48349 // add r12, 1 + LONG $0xffc28349 // add r10, -1 + WORD $0x394d; BYTE $0xd1 // cmp r9, r10 + JNE LBB9_72 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + +LBB9_74: + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 + +LBB9_76: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_80 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + +LBB9_78: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0xb60f; BYTE $0x06 // movzx eax, byte [rsi] LONG $0x014eb60f // movzx ecx, byte [rsi + 1] WORD $0x023a // cmp al, byte [rdx] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] WORD $0x4a3a; BYTE $0x01 // cmp cl, byte [rdx + 1] WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x0246b60f // movzx eax, byte [rsi + 2] @@ -47811,7 +49251,7 @@ LBB9_63: LONG $0x2454930f; BYTE $0x04 // setae byte [rsp + 4] LONG $0x0746b60f // movzx eax, byte [rsi + 7] WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd7930f41 // setae r15b + LONG $0xd6930f41 // setae r14b LONG $0x0846b60f // movzx eax, byte [rsi + 8] WORD $0x423a; BYTE $0x08 // cmp al, byte [rdx + 8] LONG $0x2454930f; BYTE $0x07 // setae byte [rsp + 7] @@ -47826,7 +49266,7 @@ LBB9_63: LONG $0xd3930f41 // setae r11b LONG $0x0c46b60f // movzx eax, byte [rsi + 12] WORD $0x423a; BYTE $0x0c // cmp al, byte [rdx + 12] - LONG $0xd6930f41 // setae r14b + LONG $0xd7930f41 // setae r15b LONG $0x0d46b60f // movzx eax, byte [rsi + 13] WORD $0x423a; BYTE $0x0d // cmp al, byte [rdx + 13] LONG $0x2454930f; BYTE $0x05 // setae byte [rsp + 5] @@ -47886,12 +49326,12 @@ LBB9_63: WORD $0x423a; BYTE $0x1f // cmp al, byte [rdx + 31] LONG $0xd0930f41 // setae r8b WORD $0xc900 // add cl, cl - LONG $0x28244c02 // add cl, byte [rsp + 40] + LONG $0x30244c02 // add cl, byte [rsp + 48] WORD $0xc889 // mov eax, ecx LONG $0x244cb60f; BYTE $0x04 // movzx ecx, byte [rsp + 4] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x07e6c041 // shl r14b, 7 + WORD $0x0841; BYTE $0xce // or r14b, cl LONG $0x244cb60f; BYTE $0x14 // movzx ecx, byte [rsp + 20] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xc108 // or cl, al @@ -47913,26 +49353,26 @@ LBB9_63: LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0840; BYTE $0xf9 // or cl, dil - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xf0 // or al, r14b + WORD $0x0844; BYTE $0xf8 // or al, r15b LONG $0x247cb60f; BYTE $0x06 // movzx edi, byte [rsp + 6] LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 WORD $0x0840; BYTE $0xfb // or bl, dil - WORD $0x0841; BYTE $0xcf // or r15b, cl + WORD $0x0841; BYTE $0xce // or r14b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xe4 // add r12b, r12b LONG $0x24640244; BYTE $0x0d // add r12b, byte [rsp + 13] LONG $0x02e5c041 // shl r13b, 2 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xe8 // or al, r13b WORD $0xc189 // mov ecx, eax + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] LONG $0x2444b60f; BYTE $0x09 // movzx eax, byte [rsp + 9] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl @@ -47940,12 +49380,12 @@ LBB9_63: LONG $0x2444b60f; BYTE $0x0a // movzx eax, byte [rsp + 10] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x3e // mov byte [r14], r15b + WORD $0x8845; BYTE $0x37 // mov byte [r15], r14b LONG $0x244cb60f; BYTE $0x0b // movzx ecx, byte [rsp + 11] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al @@ -47971,23 +49411,22 @@ LBB9_63: LONG $0x07e0c041 // shl r8b, 7 WORD $0x0841; BYTE $0xc8 // or r8b, cl WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x03468845 // mov byte [r14 + 3], r8b + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x20c28348 // add rdx, 32 - LONG $0x04c68349 // add r14, 4 - LONG $0x24448348; WORD $0xff20 // add qword [rsp + 32], -1 - JNE LBB9_63 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - -LBB9_65: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 + LONG $0x04c78349 // add r15, 4 + LONG $0x24448348; WORD $0xff28 // add qword [rsp + 40], -1 + JNE LBB9_78 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + +LBB9_80: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_67: +LBB9_82: LONG $0x0e04b60f // movzx eax, byte [rsi + rcx] WORD $0x043a; BYTE $0x0a // cmp al, byte [rdx + rcx] LONG $0x01418d4c // lea r8, [rcx + 1] @@ -47995,73 +49434,87 @@ LBB9_67: LONG $0xffd78040 // adc dil, -1 WORD $0x8948; BYTE $0xcb // mov rbx, rcx LONG $0x03ebc148 // shr rbx, 3 - LONG $0x0cb60f45; BYTE $0x1e // movzx r9d, byte [r14 + rbx] + LONG $0x0cb60f45; BYTE $0x1f // movzx r9d, byte [r15 + rbx] WORD $0x3044; BYTE $0xcf // xor dil, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x1e048841 // mov byte [r14 + rbx], al + LONG $0x1f048841 // mov byte [r15 + rbx], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_67 - JMP LBB9_123 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_82 + JMP LBB9_153 -LBB9_90: - LONG $0x1f7b8d4d // lea r15, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xfb490f4d // cmovns r15, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB9_94 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB9_111: + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB9_118 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xe8 // cmp r8, r13 + LONG $0xc54f0f4d // cmovg r8, r13 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB9_116 + WORD $0x634d; BYTE $0xc9 // movsxd r9, r9d + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + WORD $0xc031 // xor eax, eax -LBB9_92: - WORD $0x0e8b // mov ecx, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - WORD $0x0a3b // cmp ecx, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x04b60f45; BYTE $0x3e // movzx r8d, byte [r14 + rdi] - WORD $0x3045; BYTE $0xc2 // xor r10b, r8b - QUAD $0x00000000fd0c8d44 // lea r9d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc9 // sub ecx, r9d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2044; BYTE $0xd3 // and bl, r10b - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB9_92 - LONG $0x01c68349 // add r14, 1 +LBB9_114: + LONG $0x010c8d49 // lea rcx, [r9 + rax] + WORD $0x1c8b; BYTE $0x86 // mov ebx, dword [rsi + 4*rax] + WORD $0x1c3b; BYTE $0x82 // cmp ebx, dword [rdx + 4*rax] + LONG $0xd39d0f41 // setge r11b + WORD $0xf641; BYTE $0xdb // neg r11b + LONG $0x013c8d49 // lea rdi, [r9 + rax] + LONG $0x07c78348 // add rdi, 7 + WORD $0x8548; BYTE $0xc9 // test rcx, rcx + LONG $0xf9490f48 // cmovns rdi, rcx + LONG $0x03ffc148 // sar rdi, 3 + LONG $0x00fd1c8d; WORD $0x0000; BYTE $0x00 // lea ebx, [8*rdi] + WORD $0xd929 // sub ecx, ebx + LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 + WORD $0xe3d3 // shl ebx, cl + LONG $0x0cb60f41; BYTE $0x3f // movzx ecx, byte [r15 + rdi] + WORD $0x3041; BYTE $0xcb // xor r11b, cl + WORD $0x2044; BYTE $0xdb // and bl, r11b + WORD $0xcb30 // xor bl, cl + LONG $0x3f1c8841 // mov byte [r15 + rdi], bl + LONG $0x01c08348 // add rax, 1 + LONG $0xfcc28349 // add r10, -4 + WORD $0x3949; BYTE $0xc0 // cmp r8, rax + JNE LBB9_114 + WORD $0x294c; BYTE $0xd6 // sub rsi, r10 + WORD $0x294c; BYTE $0xd2 // sub rdx, r10 -LBB9_94: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB9_98 - LONG $0x245c894c; BYTE $0x18 // mov qword [rsp + 24], r11 - LONG $0x247c894c; BYTE $0x40 // mov qword [rsp + 64], r15 - LONG $0x247c894c; BYTE $0x38 // mov qword [rsp + 56], r15 +LBB9_116: + WORD $0x294d; BYTE $0xc5 // sub r13, r8 + JE LBB9_153 + LONG $0x01c78349 // add r15, 1 -LBB9_96: - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 +LBB9_118: + LONG $0x1f458d49 // lea rax, [r13 + 31] + WORD $0x854d; BYTE $0xed // test r13, r13 + LONG $0xc5490f49 // cmovns rax, r13 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fd8349 // cmp r13, 32 + JL LBB9_122 + LONG $0x246c894c; BYTE $0x20 // mov qword [rsp + 32], r13 + LONG $0x24448948; BYTE $0x40 // mov qword [rsp + 64], rax + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + +LBB9_120: + LONG $0x247c894c; BYTE $0x18 // mov qword [rsp + 24], r15 WORD $0x068b // mov eax, dword [rsi] WORD $0x4e8b; BYTE $0x04 // mov ecx, dword [rsi + 4] WORD $0x023b // cmp eax, dword [rdx] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] WORD $0x4a3b; BYTE $0x04 // cmp ecx, dword [rdx + 4] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] WORD $0x468b; BYTE $0x08 // mov eax, dword [rsi + 8] WORD $0x423b; BYTE $0x08 // cmp eax, dword [rdx + 8] LONG $0x24549d0f; BYTE $0x14 // setge byte [rsp + 20] @@ -48085,7 +49538,7 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x09 // setge byte [rsp + 9] WORD $0x468b; BYTE $0x24 // mov eax, dword [rsi + 36] WORD $0x423b; BYTE $0x24 // cmp eax, dword [rdx + 36] - LONG $0xd09d0f41 // setge r8b + LONG $0xd79d0f40 // setge dil WORD $0x468b; BYTE $0x28 // mov eax, dword [rsi + 40] WORD $0x423b; BYTE $0x28 // cmp eax, dword [rdx + 40] LONG $0xd39d0f41 // setge r11b @@ -48125,7 +49578,7 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x0b // setge byte [rsp + 11] WORD $0x423b; BYTE $0x58 // cmp eax, dword [rdx + 88] WORD $0x468b; BYTE $0x5c // mov eax, dword [rsi + 92] - LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] + LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] WORD $0x423b; BYTE $0x5c // cmp eax, dword [rdx + 92] WORD $0x468b; BYTE $0x60 // mov eax, dword [rsi + 96] LONG $0xd19d0f41 // setge r9b @@ -48134,10 +49587,10 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x13 // setge byte [rsp + 19] WORD $0x423b; BYTE $0x64 // cmp eax, dword [rdx + 100] WORD $0x468b; BYTE $0x68 // mov eax, dword [rsi + 104] - LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] + LONG $0x24549d0f; BYTE $0x0c // setge byte [rsp + 12] WORD $0x423b; BYTE $0x68 // cmp eax, dword [rdx + 104] WORD $0x468b; BYTE $0x6c // mov eax, dword [rsi + 108] - LONG $0x24549d0f; BYTE $0x0e // setge byte [rsp + 14] + LONG $0x24549d0f; BYTE $0x0d // setge byte [rsp + 13] WORD $0x423b; BYTE $0x6c // cmp eax, dword [rdx + 108] WORD $0x468b; BYTE $0x70 // mov eax, dword [rsi + 112] LONG $0x24549d0f; BYTE $0x0f // setge byte [rsp + 15] @@ -48152,10 +49605,10 @@ LBB9_96: LONG $0x24549d0f; BYTE $0x11 // setge byte [rsp + 17] LONG $0x80ee8348 // sub rsi, -128 WORD $0x423b; BYTE $0x7c // cmp eax, dword [rdx + 124] - LONG $0xd79d0f40 // setge dil - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0xd09d0f41 // setge r8b + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xc000 // add al, al - LONG $0x28244402 // add al, byte [rsp + 40] + LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x04 // movzx eax, byte [rsp + 4] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -48164,34 +49617,34 @@ LBB9_96: LONG $0x2444b60f; BYTE $0x14 // movzx eax, byte [rsp + 20] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - LONG $0x24440244; BYTE $0x09 // add r8b, byte [rsp + 9] + WORD $0x0040; BYTE $0xff // add dil, dil + LONG $0x247c0240; BYTE $0x09 // add dil, byte [rsp + 9] LONG $0x244cb60f; BYTE $0x15 // movzx ecx, byte [rsp + 21] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xc108 // or cl, al WORD $0xc889 // mov eax, ecx LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xc3 // or r11b, r8b + WORD $0x0841; BYTE $0xfb // or r11b, dil LONG $0x244cb60f; BYTE $0x16 // movzx ecx, byte [rsp + 22] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + WORD $0xcf89 // mov edi, ecx LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xdf // or r15b, r11b LONG $0x244cb60f; BYTE $0x17 // movzx ecx, byte [rsp + 23] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + WORD $0x0840; BYTE $0xf9 // or cl, dil LONG $0x2444b60f; BYTE $0x05 // movzx eax, byte [rsp + 5] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax + WORD $0xc789 // mov edi, eax LONG $0x2444b60f; BYTE $0x06 // movzx eax, byte [rsp + 6] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - LONG $0x44b60f44; WORD $0x0724 // movzx r8d, byte [rsp + 7] - LONG $0x06e0c041 // shl r8b, 6 + WORD $0x0840; BYTE $0xf8 // or al, dil + LONG $0x247cb60f; BYTE $0x07 // movzx edi, byte [rsp + 7] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0844; BYTE $0xc3 // or bl, r8b + WORD $0x0840; BYTE $0xfb // or bl, dil WORD $0x0841; BYTE $0xcd // or r13b, cl WORD $0xc308 // or bl, al WORD $0x0045; BYTE $0xd2 // add r10b, r10b @@ -48204,22 +49657,23 @@ LBB9_96: WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0x0844; BYTE $0xe0 // or al, r12b WORD $0xc189 // mov ecx, eax - LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] LONG $0x2444b60f; BYTE $0x0b // movzx eax, byte [rsp + 11] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - WORD $0x8845; BYTE $0x2e // mov byte [r14], r13b - LONG $0x244cb60f; BYTE $0x0c // movzx ecx, byte [rsp + 12] + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + WORD $0x8844; BYTE $0x2f // mov byte [rdi], r13b + LONG $0x247c8b4c; BYTE $0x18 // mov r15, qword [rsp + 24] + LONG $0x244cb60f; BYTE $0x0e // movzx ecx, byte [rsp + 14] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e1c041 // shl r9b, 7 WORD $0x0841; BYTE $0xc9 // or r9b, cl - LONG $0x015e8841 // mov byte [r14 + 1], bl + LONG $0x015f8841 // mov byte [r15 + 1], bl WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] + LONG $0x2444b60f; BYTE $0x0c // movzx eax, byte [rsp + 12] WORD $0xc000 // add al, al LONG $0x13244402 // add al, byte [rsp + 19] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x0e // movzx eax, byte [rsp + 14] + LONG $0x2444b60f; BYTE $0x0d // movzx eax, byte [rsp + 13] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -48236,26 +49690,25 @@ LBB9_96: WORD $0xc808 // or al, cl LONG $0x244cb60f; BYTE $0x11 // movzx ecx, byte [rsp + 17] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xcf // or dil, cl - WORD $0x0840; BYTE $0xc7 // or dil, al - LONG $0x024e8845 // mov byte [r14 + 2], r9b - LONG $0x037e8841 // mov byte [r14 + 3], dil + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0841; BYTE $0xc8 // or r8b, cl + WORD $0x0841; BYTE $0xc0 // or r8b, al + LONG $0x024f8845 // mov byte [r15 + 2], r9b + LONG $0x03478845 // mov byte [r15 + 3], r8b LONG $0x80c28148; WORD $0x0000; BYTE $0x00 // add rdx, 128 - LONG $0x04c68349 // add r14, 4 + LONG $0x04c78349 // add r15, 4 LONG $0x24448348; WORD $0xff38 // add qword [rsp + 56], -1 - JNE LBB9_96 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + JNE LBB9_120 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] -LBB9_98: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xdf // cmp r15, r11 - JGE LBB9_123 - WORD $0x294d; BYTE $0xfb // sub r11, r15 +LBB9_122: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x2949; BYTE $0xc5 // sub r13, rax + JLE LBB9_153 WORD $0xc931 // xor ecx, ecx -LBB9_100: +LBB9_124: LONG $0x01418d4c // lea r8, [rcx + 1] WORD $0x3c8b; BYTE $0x8e // mov edi, dword [rsi + 4*rcx] WORD $0x3c3b; BYTE $0x8a // cmp edi, dword [rdx + 4*rcx] @@ -48263,19 +49716,19 @@ LBB9_100: WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xcf // mov rdi, rcx LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xe180; BYTE $0x07 // and cl, 7 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0x3044; BYTE $0xc8 // xor al, r9b - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3f048841 // mov byte [r15 + rdi], al WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - WORD $0x394d; BYTE $0xc3 // cmp r11, r8 - JNE LBB9_100 + WORD $0x394d; BYTE $0xc5 // cmp r13, r8 + JNE LBB9_124 -LBB9_123: +LBB9_153: SUBQ $8, SP RET @@ -48327,7 +49780,7 @@ DATA LCDATA7<>+0x160(SB)/8, $0xffffffffffffffff DATA LCDATA7<>+0x168(SB)/8, $0xffffffffffffffff GLOBL LCDATA7<>(SB), 8, $368 -TEXT ·_comparison_greater_equal_arr_scalar_sse4(SB), $520-48 +TEXT ·_comparison_greater_equal_arr_scalar_sse4(SB), $504-48 MOVQ typ+0(FP), DI MOVQ left+8(FP), SI @@ -48338,119 +49791,132 @@ TEXT ·_comparison_greater_equal_arr_scalar_sse4(SB), $520-48 MOVQ SP, BP ADDQ $16, SP ANDQ $-16, SP - MOVQ BP, 496(SP) + MOVQ BP, 480(SP) LEAQ LCDATA7<>(SB), BP - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB10_26 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB10_24 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 JLE LBB10_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB10_99 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 JE LBB10_114 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB10_201 - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_17 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB10_131 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB10_227 + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB10_15 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_13 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_12: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_12 + +LBB10_13: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 LBB10_15: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_15 - LONG $0x01c68349 // add r14, 1 + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_19 + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x0000016024848948 // mov qword [rsp + 352], rax + QUAD $0x0000013024848948 // mov qword [rsp + 304], rax LBB10_17: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_21 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x00000170249c894c // mov qword [rsp + 368], r11 - QUAD $0x00000140249c894c // mov qword [rsp + 320], r11 - -LBB10_19: - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000f02494930f // setae byte [rsp + 240] + QUAD $0x000001402494930f // setae byte [rsp + 320] LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd2930f41 // setae r10b + LONG $0xd1930f41 // setae r9b LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd6930f41 // setae r14b LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x000001102494930f // setae byte [rsp + 272] + QUAD $0x000000f02494930f // setae byte [rsp + 240] LONG $0x106e3944 // cmp dword [rsi + 16], r13d - QUAD $0x000000d02494930f // setae byte [rsp + 208] + QUAD $0x000000e02494930f // setae byte [rsp + 224] LONG $0x146e3944 // cmp dword [rsi + 20], r13d - QUAD $0x000000c02494930f // setae byte [rsp + 192] + QUAD $0x000000b02494930f // setae byte [rsp + 176] LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x930f; BYTE $0xd0 // setae al LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - WORD $0x930f; BYTE $0xd3 // setae bl + LONG $0xd3930f41 // setae r11b LONG $0x206e3944 // cmp dword [rsi + 32], r13d QUAD $0x000001502494930f // setae byte [rsp + 336] LONG $0x246e3944 // cmp dword [rsi + 36], r13d - LONG $0xd7930f40 // setae dil + WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x286e3944 // cmp dword [rsi + 40], r13d - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd1930f41 // setae r9b + LONG $0xd0930f41 // setae r8b LONG $0x306e3944 // cmp dword [rsi + 48], r13d - LONG $0xd3930f41 // setae r11b + LONG $0xd2930f41 // setae r10b LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd4930f41 // setae r12b LONG $0x386e3944 // cmp dword [rsi + 56], r13d QUAD $0x000001202494930f // setae byte [rsp + 288] LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x930f; BYTE $0xd1 // setae cl + WORD $0x930f; BYTE $0xd2 // setae dl LONG $0x406e3944 // cmp dword [rsi + 64], r13d QUAD $0x000000a02494930f // setae byte [rsp + 160] LONG $0x446e3944 // cmp dword [rsi + 68], r13d - QUAD $0x000001302494930f // setae byte [rsp + 304] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d QUAD $0x000001002494930f // setae byte [rsp + 256] + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + QUAD $0x000001102494930f // setae byte [rsp + 272] LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - QUAD $0x000000e02494930f // setae byte [rsp + 224] + QUAD $0x000000d02494930f // setae byte [rsp + 208] LONG $0x506e3944 // cmp dword [rsi + 80], r13d - QUAD $0x000000b02494930f // setae byte [rsp + 176] + QUAD $0x000000c02494930f // setae byte [rsp + 192] LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x586e3944 // cmp dword [rsi + 88], r13d + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd7930f41 // setae r15b LONG $0x606e3944 // cmp dword [rsi + 96], r13d LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0x646e3944 // cmp dword [rsi + 100], r13d - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d @@ -48460,71 +49926,69 @@ LBB10_19: LONG $0x746e3944 // cmp dword [rsi + 116], r13d LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] LONG $0x786e3944 // cmp dword [rsi + 120], r13d - LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] + LONG $0x2414930f // setae byte [rsp] LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x930f; BYTE $0xd2 // setae dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000f024940244 // add r10b, byte [rsp + 240] + WORD $0x930f; BYTE $0xd3 // setae bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000140248c0244 // add r9b, byte [rsp + 320] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000015024bc0240 // add dil, byte [rsp + 336] - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0x50248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 336] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - LONG $0x02e0c041 // shl r8b, 2 + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000012024bcb60f // movzx edi, byte [rsp + 288] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000001302484b60f // movzx eax, byte [rsp + 304] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] WORD $0xc000 // add al, al LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] - WORD $0xc789 // mov edi, eax - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xc189 // mov ecx, eax + QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000e02484b60f // movzx eax, byte [rsp + 224] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax @@ -48543,94 +50007,107 @@ LBB10_19: LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + LONG $0x240cb60f // movzx ecx, byte [rsp] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c68349 // add r14, 4 - QUAD $0x0000014024848348; BYTE $0xff // add qword [rsp + 320], -1 - JNE LBB10_19 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x00000170249c8b4c // mov r11, qword [rsp + 368] - -LBB10_21: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB10_137 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000013024848348; BYTE $0xff // add qword [rsp + 304], -1 + JNE LBB10_17 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0000016024848b48 // mov rax, qword [rsp + 352] + +LBB10_19: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_227 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB10_156 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_24 - -LBB10_26: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB10_27 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB10_157 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB10_172 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB10_201 - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x02100ff2 // movsd xmm0, qword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_49 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_47: + JMP LBB10_22 + +LBB10_24: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB10_25 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB10_178 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB10_195 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB10_227 + WORD $0x8b4c; BYTE $0x3a // mov r15, qword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_51 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_49 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB10_48: LONG $0x0e100ff2 // movsd xmm1, qword [rsi] LONG $0x08c68348 // add rsi, 8 LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_47 - LONG $0x01c68349 // add r14, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB10_48 LBB10_49: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_53 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x00000140249c894c // mov qword [rsp + 320], r11 - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 LBB10_51: - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_55 + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x0000013024bc894c // mov qword [rsp + 304], r15 + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + QUAD $0x0000016024848948 // mov qword [rsp + 352], rax + QUAD $0x0000014024848948 // mov qword [rsp + 320], rax + +LBB10_53: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 LONG $0x0e100ff2 // movsd xmm1, qword [rsi] LONG $0x56100ff2; BYTE $0x08 // movsd xmm2, qword [rsi + 8] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 QUAD $0x000001202494930f // setae byte [rsp + 288] LONG $0xd02e0f66 // ucomisd xmm2, xmm0 - WORD $0x930f; BYTE $0xd2 // setae dl + WORD $0x930f; BYTE $0xd0 // setae al LONG $0x4e100ff2; BYTE $0x10 // movsd xmm1, qword [rsi + 16] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0xd7930f40 // setae dil @@ -48642,16 +50119,16 @@ LBB10_51: LONG $0xd1930f41 // setae r9b LONG $0x4e100ff2; BYTE $0x28 // movsd xmm1, qword [rsi + 40] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - QUAD $0x000001102494930f // setae byte [rsp + 272] + QUAD $0x000000f02494930f // setae byte [rsp + 240] LONG $0x4e100ff2; BYTE $0x30 // movsd xmm1, qword [rsi + 48] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - QUAD $0x000001302494930f // setae byte [rsp + 304] + QUAD $0x000001002494930f // setae byte [rsp + 256] LONG $0x4e100ff2; BYTE $0x38 // movsd xmm1, qword [rsi + 56] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 QUAD $0x000001502494930f // setae byte [rsp + 336] LONG $0x4e100ff2; BYTE $0x40 // movsd xmm1, qword [rsi + 64] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - QUAD $0x000000c02494930f // setae byte [rsp + 192] + QUAD $0x000000b02494930f // setae byte [rsp + 176] LONG $0x4e100ff2; BYTE $0x48 // movsd xmm1, qword [rsi + 72] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0xd2930f41 // setae r10b @@ -48663,21 +50140,21 @@ LBB10_51: LONG $0xd7930f41 // setae r15b LONG $0x4e100ff2; BYTE $0x60 // movsd xmm1, qword [rsi + 96] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - WORD $0x930f; BYTE $0xd0 // setae al + WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x4e100ff2; BYTE $0x68 // movsd xmm1, qword [rsi + 104] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - QUAD $0x000000d02494930f // setae byte [rsp + 208] + QUAD $0x000000e02494930f // setae byte [rsp + 224] LONG $0x4e100ff2; BYTE $0x70 // movsd xmm1, qword [rsi + 112] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - QUAD $0x000000b02494930f // setae byte [rsp + 176] + QUAD $0x000000a02494930f // setae byte [rsp + 160] LONG $0x4e100ff2; BYTE $0x78 // movsd xmm1, qword [rsi + 120] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - QUAD $0x000000e02494930f // setae byte [rsp + 224] + QUAD $0x000000d02494930f // setae byte [rsp + 208] QUAD $0x000000808e100ff2 // movsd xmm1, qword [rsi + 128] QUAD $0x0000008896100ff2 // movsd xmm2, qword [rsi + 136] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 QUAD $0x000000908e100ff2 // movsd xmm1, qword [rsi + 144] - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0xd02e0f66 // ucomisd xmm2, xmm0 QUAD $0x0000009896100ff2 // movsd xmm2, qword [rsi + 152] LONG $0xd3930f41 // setae r11b @@ -48689,13 +50166,13 @@ LBB10_51: LONG $0xd4930f41 // setae r12b LONG $0xc82e0f66 // ucomisd xmm1, xmm0 QUAD $0x000000b08e100ff2 // movsd xmm1, qword [rsi + 176] - QUAD $0x000001002494930f // setae byte [rsp + 256] + QUAD $0x000001102494930f // setae byte [rsp + 272] LONG $0xd02e0f66 // ucomisd xmm2, xmm0 QUAD $0x000000b896100ff2 // movsd xmm2, qword [rsi + 184] - QUAD $0x000000a02494930f // setae byte [rsp + 160] + QUAD $0x000000c02494930f // setae byte [rsp + 192] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 QUAD $0x000000c08e100ff2 // movsd xmm1, qword [rsi + 192] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + QUAD $0x000000802494930f // setae byte [rsp + 128] LONG $0xd02e0f66 // ucomisd xmm2, xmm0 QUAD $0x000000c896100ff2 // movsd xmm2, qword [rsi + 200] LONG $0xd5930f41 // setae r13b @@ -48704,7 +50181,7 @@ LBB10_51: LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] LONG $0xd02e0f66 // ucomisd xmm2, xmm0 QUAD $0x000000d896100ff2 // movsd xmm2, qword [rsi + 216] - QUAD $0x000000802494930f // setae byte [rsp + 128] + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 QUAD $0x000000e08e100ff2 // movsd xmm1, qword [rsi + 224] LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] @@ -48718,473 +50195,276 @@ LBB10_51: QUAD $0x000000f896100ff2 // movsd xmm2, qword [rsi + 248] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] + LONG $0x2414930f // setae byte [rsp] LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 LONG $0xd02e0f66 // ucomisd xmm2, xmm0 - WORD $0x930f; BYTE $0xd1 // setae cl - WORD $0xd200 // add dl, dl - LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] + WORD $0x930f; BYTE $0xd2 // setae dl + WORD $0xc000 // add al, al + LONG $0x20248402; WORD $0x0001; BYTE $0x00 // add al, byte [rsp + 288] LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl + WORD $0x0840; BYTE $0xc7 // or dil, al LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil LONG $0x04e1c041 // shl r9b, 4 WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000001102494b60f // movzx edx, byte [rsp + 272] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xca // or dl, r9b - WORD $0xd789 // mov edi, edx - QUAD $0x0001302484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 304] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xc8 // or al, r9b + WORD $0xc789 // mov edi, eax + QUAD $0x0001002484b60f44; BYTE $0x00 // movzx r8d, byte [rsp + 256] LONG $0x06e0c041 // shl r8b, 6 - QUAD $0x000001502494b60f // movzx edx, byte [rsp + 336] - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0x0844; BYTE $0xc2 // or dl, r8b + QUAD $0x000001502484b60f // movzx eax, byte [rsp + 336] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0844; BYTE $0xc0 // or al, r8b WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000c024940244 // add r10b, byte [rsp + 192] + QUAD $0x000000b024940244 // add r10b, byte [rsp + 176] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 WORD $0x0844; BYTE $0xd3 // or bl, r10b LONG $0x03e7c041 // shl r15b, 3 WORD $0x0841; BYTE $0xdf // or r15b, bl - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x0840; BYTE $0xfa // or dl, dil - QUAD $0x000000d0249cb60f // movzx ebx, byte [rsp + 208] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xf9 // or cl, r15b + WORD $0x0840; BYTE $0xf8 // or al, dil + QUAD $0x000000e0249cb60f // movzx ebx, byte [rsp + 224] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0xc308 // or bl, al + WORD $0xcb08 // or bl, cl WORD $0xdf89 // mov edi, ebx - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - QUAD $0x000000e0249cb60f // movzx ebx, byte [rsp + 224] + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + QUAD $0x000000d0249cb60f // movzx ebx, byte [rsp + 208] WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + WORD $0xcb08 // or bl, cl WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x00000090249c0244 // add r11b, byte [rsp + 144] + LONG $0x245c0244; BYTE $0x70 // add r11b, byte [rsp + 112] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xde // or r14b, r11b LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xf4 // or r12b, r14b - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b + QUAD $0x00000110248cb60f // movzx ecx, byte [rsp + 272] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe1 // or cl, r12b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b WORD $0x0840; BYTE $0xfb // or bl, dil - LONG $0x247cb60f; BYTE $0x70 // movzx edi, byte [rsp + 112] + QUAD $0x0000008024bcb60f // movzx edi, byte [rsp + 128] LONG $0x06e7c040 // shl dil, 6 LONG $0x07e5c041 // shl r13b, 7 WORD $0x0841; BYTE $0xfd // or r13b, dil - WORD $0x8841; BYTE $0x16 // mov byte [r14], dl - WORD $0x0841; BYTE $0xc5 // or r13b, al - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + LONG $0x24048841 // mov byte [r12], al + WORD $0x0841; BYTE $0xcd // or r13b, cl + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xc000 // add al, al LONG $0x10244402 // add al, byte [rsp + 16] - WORD $0xc289 // mov edx, eax + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x20 // movzx edx, byte [rsp + 32] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x015e8841 // mov byte [r14 + 1], bl - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x245c8841; BYTE $0x01 // mov byte [r12 + 1], bl + LONG $0x241cb60f // movzx ebx, byte [rsp] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - LONG $0x026e8845 // mov byte [r14 + 2], r13b - WORD $0xd108 // or cl, dl - LONG $0x034e8841 // mov byte [r14 + 3], cl - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB10_51 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - -LBB10_53: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB10_195 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_197 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + LONG $0x246c8845; BYTE $0x02 // mov byte [r12 + 2], r13b + WORD $0xc208 // or dl, al + LONG $0x24548841; BYTE $0x03 // mov byte [r12 + 3], dl + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000014024848348; BYTE $0xff // add qword [rsp + 320], -1 + JNE LBB10_53 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0000013024bc8b4c // mov r15, qword [rsp + 304] + QUAD $0x0000016024848b48 // mov rax, qword [rsp + 352] -LBB10_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB10_56 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB10_201 - WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_6: - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - LONG $0x01768d48 // lea rsi, [rsi + 1] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_6 - LONG $0x01c68349 // add r14, 1 - -LBB10_8: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_9 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x245c8844; BYTE $0x08 // mov byte [rsp + 8], r11b - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x000001b024bc894c // mov qword [rsp + 432], r15 - JB LBB10_82 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB10_55: LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_227 + LONG $0x6e0f4966; BYTE $0xc7 // movq xmm0, r15 + LONG $0x01c88348 // or rax, 1 WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB10_85 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB10_85 - -LBB10_82: - WORD $0xc031 // xor eax, eax - QUAD $0x000000f024848948 // mov qword [rsp + 240], rax - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 + JNE LBB10_221 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_223 -LBB10_88: - QUAD $0x000000f024bc2b4c // sub r15, qword [rsp + 240] - QUAD $0x0000017024bc894c // mov qword [rsp + 368], r15 - -LBB10_89: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - QUAD $0x0000014024949d0f // setge byte [rsp + 320] - LONG $0x015e3844 // cmp byte [rsi + 1], r11b - LONG $0xd69d0f40 // setge sil - LONG $0x02593844 // cmp byte [rcx + 2], r11b - LONG $0xd79d0f41 // setge r15b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al - LONG $0xd49d0f41 // setge r12b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al - QUAD $0x0000011024949d0f // setge byte [rsp + 272] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al - QUAD $0x000000f024949d0f // setge byte [rsp + 240] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al - LONG $0xd19d0f41 // setge r9b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al - QUAD $0x0000015024949d0f // setge byte [rsp + 336] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al - WORD $0x9d0f; BYTE $0xd2 // setge dl - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al - LONG $0xd79d0f40 // setge dil - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al - LONG $0xd29d0f41 // setge r10b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al - LONG $0xd69d0f41 // setge r14b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al - LONG $0xd59d0f41 // setge r13b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al - QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al - LONG $0xd09d0f41 // setge r8b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl - QUAD $0x0000013024949d0f // setge byte [rsp + 304] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl - QUAD $0x0000010024949d0f // setge byte [rsp + 256] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl - QUAD $0x000000d024949d0f // setge byte [rsp + 208] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl - QUAD $0x000000e024949d0f // setge byte [rsp + 224] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl - QUAD $0x000000c024949d0f // setge byte [rsp + 192] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl - QUAD $0x000000b024949d0f // setge byte [rsp + 176] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl - LONG $0xd39d0f41 // setge r11b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl - LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - QUAD $0x0000016024949d0f // setge byte [rsp + 352] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000014024b40240 // add sil, byte [rsp + 320] - QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - WORD $0xd200 // add dl, dl - LONG $0x50249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 336] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x7cb60f44; WORD $0x0824 // movzx r15d, byte [rsp + 8] - LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0841; BYTE $0xfa // or r10b, dil - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - QUAD $0x0000012024b4b60f // movzx esi, byte [rsp + 288] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - WORD $0x0841; BYTE $0xd1 // or r9b, dl - WORD $0x0845; BYTE $0xe8 // or r8b, r13b - QUAD $0x000001002494b60f // movzx edx, byte [rsp + 256] - WORD $0xd200 // add dl, dl - LONG $0x30249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 304] - WORD $0xd689 // mov esi, edx - QUAD $0x000000d02494b60f // movzx edx, byte [rsp + 208] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000e02494b60f // movzx edx, byte [rsp + 224] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000c02494b60f // movzx edx, byte [rsp + 192] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] - WORD $0x8844; BYTE $0x0a // mov byte [rdx], r9b - QUAD $0x000000b024bcb60f // movzx edi, byte [rsp + 176] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xfb // or r11b, dil - LONG $0x01428844 // mov byte [rdx + 1], r8b - WORD $0x0841; BYTE $0xf3 // or r11b, sil - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xc000 // add al, al - LONG $0x80248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 128] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x0000016024b4b60f // movzx esi, byte [rsp + 352] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xc308 // or bl, al - LONG $0x025a8844 // mov byte [rdx + 2], r11b - WORD $0x8945; BYTE $0xfb // mov r11d, r15d - WORD $0x5a88; BYTE $0x03 // mov byte [rdx + 3], bl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c28348 // add rdx, 4 - QUAD $0x0000009024948948 // mov qword [rsp + 144], rdx - QUAD $0x0000017024848348; BYTE $0xff // add qword [rsp + 368], -1 +LBB10_2: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB10_58 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB10_227 + WORD $0x8a44; BYTE $0x3a // mov r15b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_5 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_87 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB10_93: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x07728d48 // lea rsi, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xf2490f48 // cmovns rsi, rdx + LONG $0x03fec148 // sar rsi, 3 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000f5148d44 // lea r10d, [8*rsi] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_93 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 JNE LBB10_89 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x000001b024bc8b4c // mov r15, qword [rsp + 432] - JMP LBB10_91 - -LBB10_27: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB10_139 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB10_201 - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JMP LBB10_227 + +LBB10_25: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB10_158 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB10_227 + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx JE LBB10_33 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_31 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_30: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_30 LBB10_31: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_31 - LONG $0x01c68349 // add r14, 1 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 LBB10_33: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 JL LBB10_37 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x00000170249c894c // mov qword [rsp + 368], r11 - QUAD $0x00000140249c894c // mov qword [rsp + 320], r11 + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x0000016024848948 // mov qword [rsp + 352], rax + QUAD $0x0000013024848948 // mov qword [rsp + 304], rax LBB10_35: - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000f02494930f // setae byte [rsp + 240] + QUAD $0x000001402494930f // setae byte [rsp + 320] LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0xd2930f41 // setae r10b + LONG $0xd1930f41 // setae r9b LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd6930f41 // setae r14b LONG $0x186e394c // cmp qword [rsi + 24], r13 - QUAD $0x000001102494930f // setae byte [rsp + 272] + QUAD $0x000000f02494930f // setae byte [rsp + 240] LONG $0x206e394c // cmp qword [rsi + 32], r13 - QUAD $0x000000d02494930f // setae byte [rsp + 208] + QUAD $0x000000e02494930f // setae byte [rsp + 224] LONG $0x286e394c // cmp qword [rsi + 40], r13 - QUAD $0x000000c02494930f // setae byte [rsp + 192] + QUAD $0x000000b02494930f // setae byte [rsp + 176] LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x930f; BYTE $0xd0 // setae al LONG $0x386e394c // cmp qword [rsi + 56], r13 - WORD $0x930f; BYTE $0xd3 // setae bl + LONG $0xd3930f41 // setae r11b LONG $0x406e394c // cmp qword [rsi + 64], r13 QUAD $0x000001502494930f // setae byte [rsp + 336] LONG $0x486e394c // cmp qword [rsi + 72], r13 - LONG $0xd7930f40 // setae dil + WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x506e394c // cmp qword [rsi + 80], r13 - LONG $0xd0930f41 // setae r8b + LONG $0xd7930f40 // setae dil LONG $0x586e394c // cmp qword [rsi + 88], r13 - LONG $0xd1930f41 // setae r9b + LONG $0xd0930f41 // setae r8b LONG $0x606e394c // cmp qword [rsi + 96], r13 - LONG $0xd3930f41 // setae r11b + LONG $0xd2930f41 // setae r10b LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd4930f41 // setae r12b LONG $0x706e394c // cmp qword [rsi + 112], r13 QUAD $0x000001202494930f // setae byte [rsp + 288] LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x930f; BYTE $0xd1 // setae cl + WORD $0x930f; BYTE $0xd2 // setae dl LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 QUAD $0x000000a02494930f // setae byte [rsp + 160] LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - QUAD $0x000001302494930f // setae byte [rsp + 304] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 QUAD $0x000001002494930f // setae byte [rsp + 256] + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + QUAD $0x000001102494930f // setae byte [rsp + 272] LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 - QUAD $0x000000e02494930f // setae byte [rsp + 224] + QUAD $0x000000d02494930f // setae byte [rsp + 208] LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 - QUAD $0x000000b02494930f // setae byte [rsp + 176] + QUAD $0x000000c02494930f // setae byte [rsp + 192] LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + QUAD $0x000000902494930f // setae byte [rsp + 144] LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd7930f41 // setae r15b LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 - QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 @@ -49194,71 +50474,69 @@ LBB10_35: LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 - LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] + LONG $0x2414930f // setae byte [rsp] LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x930f; BYTE $0xd2 // setae dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000f024940244 // add r10b, byte [rsp + 240] + WORD $0x930f; BYTE $0xd3 // setae bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000140248c0244 // add r9b, byte [rsp + 320] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000015024bc0240 // add dil, byte [rsp + 336] - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0x50248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 336] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - LONG $0x02e0c041 // shl r8b, 2 + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000012024bcb60f // movzx edi, byte [rsp + 288] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000001302484b60f // movzx eax, byte [rsp + 304] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] WORD $0xc000 // add al, al LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] - WORD $0xc789 // mov edi, eax - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xc189 // mov ecx, eax + QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000e02484b60f // movzx eax, byte [rsp + 224] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax @@ -49277,461 +50555,699 @@ LBB10_35: LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + LONG $0x240cb60f // movzx ecx, byte [rsp] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c68349 // add r14, 4 - QUAD $0x0000014024848348; BYTE $0xff // add qword [rsp + 320], -1 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000013024848348; BYTE $0xff // add qword [rsp + 304], -1 JNE LBB10_35 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x00000170249c8b4c // mov r11, qword [rsp + 368] + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0000016024848b48 // mov rax, qword [rsp + 352] LBB10_37: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB10_155 + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_227 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB10_176 WORD $0x3145; BYTE $0xdb // xor r11d, r11d JMP LBB10_40 -LBB10_56: - WORD $0x8a44; BYTE $0x1a // mov r11b, byte [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_60 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_58: - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - LONG $0x01768d48 // lea rsi, [rsi + 1] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl +LBB10_114: + LONG $0x2ab70f44 // movzx r13d, word [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB10_120 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_118 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_117: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x29394466 // cmp word [rcx], r13w + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_58 - LONG $0x01c68349 // add r14, 1 - -LBB10_60: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_61 - LONG $0x10ff8349 // cmp r15, 16 - LONG $0x245c8844; BYTE $0x08 // mov byte [rsp + 8], r11b - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x000001d024bc894c // mov qword [rsp + 464], r15 - JB LBB10_63 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB10_66 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xc6 // cmp rsi, rax - JAE LBB10_66 - -LBB10_63: - WORD $0xc031 // xor eax, eax - QUAD $0x000001a024848948 // mov qword [rsp + 416], rax - QUAD $0x000000e024b4894c // mov qword [rsp + 224], r14 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_117 -LBB10_69: - QUAD $0x000001a024bc2b4c // sub r15, qword [rsp + 416] - QUAD $0x0000017024bc894c // mov qword [rsp + 368], r15 +LBB10_118: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 + +LBB10_120: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_124 + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x0000016024848948 // mov qword [rsp + 352], rax + QUAD $0x0000013024848948 // mov qword [rsp + 304], rax -LBB10_70: - WORD $0x8948; BYTE $0xf1 // mov rcx, rsi - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b +LBB10_122: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 + LONG $0x2e394466 // cmp word [rsi], r13w QUAD $0x000001402494930f // setae byte [rsp + 320] - LONG $0x015e3844 // cmp byte [rsi + 1], r11b - LONG $0xd6930f40 // setae sil - LONG $0x02593844 // cmp byte [rcx + 2], r11b - LONG $0xd7930f41 // setae r15b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x03 // cmp byte [rcx + 3], al - LONG $0xd4930f41 // setae r12b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al - QUAD $0x000001102494930f // setae byte [rsp + 272] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al - QUAD $0x000000f02494930f // setae byte [rsp + 240] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al + LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0xd1930f41 // setae r9b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w + LONG $0xd6930f41 // setae r14b + LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w + QUAD $0x000000f02494930f // setae byte [rsp + 240] + LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w + QUAD $0x000000e02494930f // setae byte [rsp + 224] + LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w + QUAD $0x000000b02494930f // setae byte [rsp + 176] + LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w + LONG $0xd3930f41 // setae r11b + LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w QUAD $0x000001502494930f // setae byte [rsp + 336] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al - WORD $0x930f; BYTE $0xd2 // setae dl - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w + WORD $0x930f; BYTE $0xd1 // setae cl + LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w LONG $0xd7930f40 // setae dil - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al + LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w + LONG $0xd0930f41 // setae r8b + LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w LONG $0xd2930f41 // setae r10b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al - LONG $0xd6930f41 // setae r14b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al - LONG $0xd5930f41 // setae r13b - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w + LONG $0xd4930f41 // setae r12b + LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al - LONG $0xd0930f41 // setae r8b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl - QUAD $0x000001302494930f // setae byte [rsp + 304] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w + WORD $0x930f; BYTE $0xd2 // setae dl + LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w + QUAD $0x000000a02494930f // setae byte [rsp + 160] + LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w QUAD $0x000001002494930f // setae byte [rsp + 256] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w + QUAD $0x000001102494930f // setae byte [rsp + 272] + LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w QUAD $0x000000d02494930f // setae byte [rsp + 208] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl - QUAD $0x000000b02494930f // setae byte [rsp + 176] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w QUAD $0x000000c02494930f // setae byte [rsp + 192] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl - LONG $0xd3930f41 // setae r11b - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl + LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w + LONG $0xd7930f41 // setae r15b + LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl + LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl + LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl - QUAD $0x000001602494930f // setae byte [rsp + 352] - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w + LONG $0x2414930f // setae byte [rsp] + LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w WORD $0x930f; BYTE $0xd3 // setae bl - WORD $0x0040; BYTE $0xf6 // add sil, sil - QUAD $0x0000014024b40240 // add sil, byte [rsp + 320] - QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000140248c0244 // add r9b, byte [rsp + 320] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e1c041 // shl r9b, 7 - WORD $0x0841; BYTE $0xc1 // or r9b, al - LONG $0x02e7c041 // shl r15b, 2 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - WORD $0xd200 // add dl, dl - LONG $0x50249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 336] - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x7cb60f44; WORD $0x0824 // movzx r15d, byte [rsp + 8] + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0x50248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 336] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0x0844; BYTE $0xf0 // or al, r14b LONG $0x02e7c040 // shl dil, 2 - WORD $0x0840; BYTE $0xd7 // or dil, dl + WORD $0x0840; BYTE $0xcf // or dil, cl + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xc000 // add al, al + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] + WORD $0xc189 // mov ecx, eax QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0841; BYTE $0xfa // or r10b, dil - QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0xc208 // or dl, al - LONG $0x04e6c041 // shl r14b, 4 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x05e5c041 // shl r13b, 5 - WORD $0x0845; BYTE $0xf5 // or r13b, r14b - QUAD $0x0000012024b4b60f // movzx esi, byte [rsp + 288] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xf0 // or r8b, sil - WORD $0x0841; BYTE $0xd1 // or r9b, dl - WORD $0x0845; BYTE $0xe8 // or r8b, r13b - QUAD $0x000001002494b60f // movzx edx, byte [rsp + 256] - WORD $0xd200 // add dl, dl - LONG $0x30249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 304] - WORD $0xd689 // mov esi, edx - QUAD $0x000000d02494b60f // movzx edx, byte [rsp + 208] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000b02494b60f // movzx edx, byte [rsp + 176] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] - WORD $0x8844; BYTE $0x0a // mov byte [rdx], r9b - QUAD $0x000000c024bcb60f // movzx edi, byte [rsp + 192] - LONG $0x06e7c040 // shl dil, 6 - LONG $0x07e3c041 // shl r11b, 7 - WORD $0x0841; BYTE $0xfb // or r11b, dil - LONG $0x01428844 // mov byte [rdx + 1], r8b - WORD $0x0841; BYTE $0xf3 // or r11b, sil + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x30244402 // add al, byte [rsp + 48] + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x240cb60f // movzx ecx, byte [rsp] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl + LONG $0x40c68348 // add rsi, 64 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000013024848348; BYTE $0xff // add qword [rsp + 304], -1 + JNE LBB10_122 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0000016024848b48 // mov rax, qword [rsp + 352] + +LBB10_124: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_227 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB10_129 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_127 + +LBB10_131: + LONG $0x3ab70f44 // movzx r15d, word [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_137 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_135 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_134: + LONG $0x02718d48 // lea rsi, [rcx + 2] + LONG $0x39394466 // cmp word [rcx], r15w + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_134 + +LBB10_135: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 + +LBB10_137: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_138 + LONG $0x08f98348 // cmp rcx, 8 + LONG $0x243c8944 // mov dword [rsp], r15d + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x000001b8248c8948 // mov qword [rsp + 440], rcx + JB LBB10_140 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB10_143 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JBE LBB10_143 + +LBB10_140: + WORD $0xc031 // xor eax, eax + QUAD $0x0000017824848948 // mov qword [rsp + 376], rax + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 + +LBB10_146: + QUAD $0x00000178248c2b48 // sub rcx, qword [rsp + 376] + QUAD $0x00000160248c8948 // mov qword [rsp + 352], rcx + +LBB10_147: + LONG $0x3b394566 // cmp word [r11], r15w + QUAD $0x0000013024949d0f // setge byte [rsp + 304] + LONG $0x7b394566; BYTE $0x02 // cmp word [r11 + 2], r15w + LONG $0xd09d0f41 // setge r8b + LONG $0x7b394566; BYTE $0x04 // cmp word [r11 + 4], r15w + LONG $0xd69d0f41 // setge r14b + LONG $0x7b394566; BYTE $0x06 // cmp word [r11 + 6], r15w + LONG $0xd59d0f41 // setge r13b + LONG $0x7b394566; BYTE $0x08 // cmp word [r11 + 8], r15w + QUAD $0x0000011024949d0f // setge byte [rsp + 272] + LONG $0x7b394566; BYTE $0x0a // cmp word [r11 + 10], r15w + QUAD $0x000000c024949d0f // setge byte [rsp + 192] + LONG $0x7b394566; BYTE $0x0c // cmp word [r11 + 12], r15w + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x7b394566; BYTE $0x0e // cmp word [r11 + 14], r15w + WORD $0x9d0f; BYTE $0xd3 // setge bl + LONG $0x7b394566; BYTE $0x10 // cmp word [r11 + 16], r15w + QUAD $0x0000015024949d0f // setge byte [rsp + 336] + LONG $0x7b394566; BYTE $0x12 // cmp word [r11 + 18], r15w + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x7b394566; BYTE $0x14 // cmp word [r11 + 20], r15w + LONG $0xd69d0f40 // setge sil + LONG $0x7b394566; BYTE $0x16 // cmp word [r11 + 22], r15w + LONG $0xd19d0f41 // setge r9b + LONG $0x7b394566; BYTE $0x18 // cmp word [r11 + 24], r15w + LONG $0xd29d0f41 // setge r10b + LONG $0x7b394566; BYTE $0x1a // cmp word [r11 + 26], r15w + LONG $0xd79d0f41 // setge r15b + WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] + LONG $0x43394166; BYTE $0x1c // cmp word [r11 + 28], ax + QUAD $0x0000012024949d0f // setge byte [rsp + 288] + WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] + LONG $0x43394166; BYTE $0x1e // cmp word [r11 + 30], ax + LONG $0xd79d0f40 // setge dil + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x20 // cmp word [r11 + 32], dx + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x22 // cmp word [r11 + 34], dx + QUAD $0x000000f024949d0f // setge byte [rsp + 240] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x24 // cmp word [r11 + 36], dx + QUAD $0x0000010024949d0f // setge byte [rsp + 256] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x26 // cmp word [r11 + 38], dx + QUAD $0x000000e024949d0f // setge byte [rsp + 224] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x28 // cmp word [r11 + 40], dx + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x2a // cmp word [r11 + 42], dx + QUAD $0x000000b024949d0f // setge byte [rsp + 176] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x2c // cmp word [r11 + 44], dx + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x2e // cmp word [r11 + 46], dx + LONG $0xd49d0f41 // setge r12b + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x30 // cmp word [r11 + 48], dx + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x32 // cmp word [r11 + 50], dx + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x34 // cmp word [r11 + 52], dx + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x36 // cmp word [r11 + 54], dx + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x38 // cmp word [r11 + 56], dx + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x3a // cmp word [r11 + 58], dx + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x3c // cmp word [r11 + 60], dx + LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] + WORD $0x148b; BYTE $0x24 // mov edx, dword [rsp] + LONG $0x53394166; BYTE $0x3e // cmp word [r11 + 62], dx + WORD $0x9d0f; BYTE $0xd2 // setge dl + WORD $0x0045; BYTE $0xc0 // add r8b, r8b + QUAD $0x0000013024840244 // add r8b, byte [rsp + 304] + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xc308 // or bl, al + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0xc900 // add cl, cl + LONG $0x50248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 336] + LONG $0x03e5c041 // shl r13b, 3 + WORD $0x0845; BYTE $0xf5 // or r13b, r14b + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xce // or sil, cl + QUAD $0x00000110248cb60f // movzx ecx, byte [rsp + 272] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + LONG $0x03e1c041 // shl r9b, 3 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x05e7c041 // shl r15b, 5 + WORD $0x0845; BYTE $0xd7 // or r15b, r10b + QUAD $0x0000012024b4b60f // movzx esi, byte [rsp + 288] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xf7 // or dil, sil + WORD $0xcb08 // or bl, cl + WORD $0x0844; BYTE $0xff // or dil, r15b + LONG $0x243c8b44 // mov r15d, dword [rsp] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] + QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xce89 // mov esi, ecx + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] + WORD $0x1988 // mov byte [rcx], bl + QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xdc // or r12b, bl + LONG $0x01798840 // mov byte [rcx + 1], dil + WORD $0x0841; BYTE $0xf4 // or r12b, sil + QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0xc000 // add al, al + LONG $0x50244402 // add al, byte [rsp + 80] + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0xc689 // mov esi, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xd808 // or al, bl + WORD $0xc389 // mov ebx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf0 // or al, sil - QUAD $0x0000016024b4b60f // movzx esi, byte [rsp + 352] - LONG $0x06e6c040 // shl sil, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xc308 // or bl, al - LONG $0x025a8844 // mov byte [rdx + 2], r11b - WORD $0x8945; BYTE $0xfb // mov r11d, r15d - WORD $0x5a88; BYTE $0x03 // mov byte [rdx + 3], bl - LONG $0x20718d48 // lea rsi, [rcx + 32] - LONG $0x04c28348 // add rdx, 4 - QUAD $0x000000e024948948 // mov qword [rsp + 224], rdx - QUAD $0x0000017024848348; BYTE $0xff // add qword [rsp + 368], -1 - JNE LBB10_70 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x000001d024bc8b4c // mov r15, qword [rsp + 464] - JMP LBB10_72 - -LBB10_139: - WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_143 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_141: - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x04768d48 // lea rsi, [rsi + 4] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_141 - LONG $0x01c68349 // add r14, 1 + WORD $0xd808 // or al, bl + LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xda08 // or dl, bl + WORD $0xc208 // or dl, al + LONG $0x02618844 // mov byte [rcx + 2], r12b + WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl + LONG $0x40c38349 // add r11, 64 + LONG $0x04c18348 // add rcx, 4 + LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx + QUAD $0x0000016024848348; BYTE $0xff // add qword [rsp + 352], -1 + JNE LBB10_147 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x000001b8248c8b48 // mov rcx, qword [rsp + 440] + JMP LBB10_149 + +LBB10_178: + WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB10_184 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_182 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_181: + LONG $0x08718d48 // lea rsi, [rcx + 8] + WORD $0x394c; BYTE $0x29 // cmp qword [rcx], r13 + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_181 -LBB10_143: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_147 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x00000170249c894c // mov qword [rsp + 368], r11 - QUAD $0x00000140249c894c // mov qword [rsp + 320], r11 - -LBB10_145: - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 - WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - QUAD $0x000000f024949d0f // setge byte [rsp + 240] - LONG $0x046e3944 // cmp dword [rsi + 4], r13d - LONG $0xd29d0f41 // setge r10b - LONG $0x086e3944 // cmp dword [rsi + 8], r13d +LBB10_182: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 + +LBB10_184: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_188 + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x0000016024848948 // mov qword [rsp + 352], rax + QUAD $0x0000013024848948 // mov qword [rsp + 304], rax + +LBB10_186: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 + WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x086e394c // cmp qword [rsi + 8], r13 + LONG $0xd19d0f41 // setge r9b + LONG $0x106e394c // cmp qword [rsi + 16], r13 LONG $0xd69d0f41 // setge r14b - LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d - QUAD $0x0000011024949d0f // setge byte [rsp + 272] - LONG $0x106e3944 // cmp dword [rsi + 16], r13d - QUAD $0x000000d024949d0f // setge byte [rsp + 208] - LONG $0x146e3944 // cmp dword [rsi + 20], r13d - QUAD $0x000000c024949d0f // setge byte [rsp + 192] - LONG $0x186e3944 // cmp dword [rsi + 24], r13d + LONG $0x186e394c // cmp qword [rsi + 24], r13 + QUAD $0x000000f024949d0f // setge byte [rsp + 240] + LONG $0x206e394c // cmp qword [rsi + 32], r13 + QUAD $0x000000e024949d0f // setge byte [rsp + 224] + LONG $0x286e394c // cmp qword [rsi + 40], r13 + QUAD $0x000000b024949d0f // setge byte [rsp + 176] + LONG $0x306e394c // cmp qword [rsi + 48], r13 WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x206e3944 // cmp dword [rsi + 32], r13d + LONG $0x386e394c // cmp qword [rsi + 56], r13 + LONG $0xd39d0f41 // setge r11b + LONG $0x406e394c // cmp qword [rsi + 64], r13 QUAD $0x0000015024949d0f // setge byte [rsp + 336] - LONG $0x246e3944 // cmp dword [rsi + 36], r13d + LONG $0x486e394c // cmp qword [rsi + 72], r13 + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x506e394c // cmp qword [rsi + 80], r13 LONG $0xd79d0f40 // setge dil - LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0x586e394c // cmp qword [rsi + 88], r13 LONG $0xd09d0f41 // setge r8b - LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d - LONG $0xd19d0f41 // setge r9b - LONG $0x306e3944 // cmp dword [rsi + 48], r13d - LONG $0xd39d0f41 // setge r11b - LONG $0x346e3944 // cmp dword [rsi + 52], r13d + LONG $0x606e394c // cmp qword [rsi + 96], r13 + LONG $0xd29d0f41 // setge r10b + LONG $0x686e394c // cmp qword [rsi + 104], r13 LONG $0xd49d0f41 // setge r12b - LONG $0x386e3944 // cmp dword [rsi + 56], r13d + LONG $0x706e394c // cmp qword [rsi + 112], r13 QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x406e3944 // cmp dword [rsi + 64], r13d + LONG $0x786e394c // cmp qword [rsi + 120], r13 + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x446e3944 // cmp dword [rsi + 68], r13d - QUAD $0x0000013024949d0f // setge byte [rsp + 304] - LONG $0x486e3944 // cmp dword [rsi + 72], r13d + LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 QUAD $0x0000010024949d0f // setge byte [rsp + 256] - LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d - QUAD $0x000000e024949d0f // setge byte [rsp + 224] - LONG $0x506e3944 // cmp dword [rsi + 80], r13d - QUAD $0x000000b024949d0f // setge byte [rsp + 176] - LONG $0x546e3944 // cmp dword [rsi + 84], r13d - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x586e3944 // cmp dword [rsi + 88], r13d + LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + QUAD $0x0000011024949d0f // setge byte [rsp + 272] + LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 + QUAD $0x000000c024949d0f // setge byte [rsp + 192] + LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d + LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 LONG $0xd79d0f41 // setge r15b - LONG $0x606e3944 // cmp dword [rsi + 96], r13d + LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x646e3944 // cmp dword [rsi + 100], r13d - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x686e3944 // cmp dword [rsi + 104], r13d + LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d + LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x706e3944 // cmp dword [rsi + 112], r13d + LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x746e3944 // cmp dword [rsi + 116], r13d + LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0x786e3944 // cmp dword [rsi + 120], r13d - LONG $0x24549d0f; BYTE $0x08 // setge byte [rsp + 8] - LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000f024940244 // add r10b, byte [rsp + 240] + LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x24149d0f // setge byte [rsp] + LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000140248c0244 // add r9b, byte [rsp + 320] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000015024bc0240 // add dil, byte [rsp + 336] - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] + WORD $0x0845; BYTE $0xce // or r14b, r9b + WORD $0xc900 // add cl, cl + LONG $0x50248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 336] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - LONG $0x02e0c041 // shl r8b, 2 + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xc108 // or cl, al + LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0xc808 // or al, cl + LONG $0x04e2c041 // shl r10b, 4 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000012024bcb60f // movzx edi, byte [rsp + 288] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000001302484b60f // movzx eax, byte [rsp + 304] + WORD $0x0845; BYTE $0xd4 // or r12b, r10b + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] WORD $0xc000 // add al, al LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] - WORD $0xc789 // mov edi, eax - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xc189 // mov ecx, eax + QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000e02484b60f // movzx eax, byte [rsp + 224] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl WORD $0x0841; BYTE $0xc7 // or r15b, al - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al LONG $0x30244402 // add al, byte [rsp + 48] WORD $0xc189 // mov ecx, eax @@ -49750,1065 +51266,1151 @@ LBB10_145: LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + LONG $0x240cb60f // movzx ecx, byte [rsp] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl - LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 - LONG $0x04c68349 // add r14, 4 - QUAD $0x0000014024848348; BYTE $0xff // add qword [rsp + 320], -1 - JNE LBB10_145 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x00000170249c8b4c // mov r11, qword [rsp + 368] + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl + LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000013024848348; BYTE $0xff // add qword [rsp + 304], -1 + JNE LBB10_186 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0000016024848b48 // mov rax, qword [rsp + 352] -LBB10_147: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB10_153 +LBB10_188: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_227 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB10_193 WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_150 + JMP LBB10_191 -LBB10_99: - LONG $0x2ab70f44 // movzx r13d, word [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_103 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB10_195: + WORD $0x8b44; BYTE $0x3a // mov r15d, dword [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_201 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_199 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + +LBB10_198: + LONG $0x0e100ff3 // movss xmm1, dword [rsi] + LONG $0x04c68348 // add rsi, 4 + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07428d48 // lea rax, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xc2490f48 // cmovns rax, rdx + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c28348 // add rdx, 1 + LONG $0xffc38349 // add r11, -1 + JNE LBB10_198 -LBB10_101: - LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x02768d48 // lea rsi, [rsi + 2] - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_101 - LONG $0x01c68349 // add r14, 1 +LBB10_199: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 -LBB10_103: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_107 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x00000170249c894c // mov qword [rsp + 368], r11 - QUAD $0x00000140249c894c // mov qword [rsp + 320], r11 +LBB10_201: + LONG $0x1f7e8d49 // lea rdi, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xfe490f49 // cmovns rdi, r14 + LONG $0x05ffc148 // sar rdi, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_202 + LONG $0x6e0f4566; BYTE $0xdf // movd xmm11, r15d + LONG $0x04ff8348 // cmp rdi, 4 + JB LBB10_204 + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xf0 // add rax, rsi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB10_207 + LONG $0xbc048d49 // lea rax, [r12 + 4*rdi] + WORD $0x3948; BYTE $0xf0 // cmp rax, rsi + JBE LBB10_207 -LBB10_105: - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 - LONG $0x2e394466 // cmp word [rsi], r13w - QUAD $0x000000f02494930f // setae byte [rsp + 240] - LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w - LONG $0xd2930f41 // setae r10b - LONG $0x6e394466; BYTE $0x04 // cmp word [rsi + 4], r13w - LONG $0xd6930f41 // setae r14b - LONG $0x6e394466; BYTE $0x06 // cmp word [rsi + 6], r13w - QUAD $0x000001102494930f // setae byte [rsp + 272] - LONG $0x6e394466; BYTE $0x08 // cmp word [rsi + 8], r13w - QUAD $0x000000d02494930f // setae byte [rsp + 208] - LONG $0x6e394466; BYTE $0x0a // cmp word [rsi + 10], r13w - QUAD $0x000000c02494930f // setae byte [rsp + 192] - LONG $0x6e394466; BYTE $0x0c // cmp word [rsi + 12], r13w - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x6e394466; BYTE $0x0e // cmp word [rsi + 14], r13w - WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x6e394466; BYTE $0x10 // cmp word [rsi + 16], r13w - QUAD $0x000001502494930f // setae byte [rsp + 336] - LONG $0x6e394466; BYTE $0x12 // cmp word [rsi + 18], r13w +LBB10_204: + WORD $0xc031 // xor eax, eax + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + +LBB10_210: + LONG $0x241c894c // mov qword [rsp], r11 + QUAD $0x0000013024bc8944 // mov dword [rsp + 304], r15d + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x0000016024bc8948 // mov qword [rsp + 352], rdi + WORD $0x2948; BYTE $0xc7 // sub rdi, rax + QUAD $0x0000014024bc8948 // mov qword [rsp + 320], rdi + +LBB10_211: + LONG $0x01100ff3 // movss xmm0, dword [rcx] + LONG $0x49100ff3; BYTE $0x04 // movss xmm1, dword [rcx + 4] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000001202494930f // setae byte [rsp + 288] + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + WORD $0x930f; BYTE $0xd2 // setae dl + LONG $0x41100ff3; BYTE $0x08 // movss xmm0, dword [rcx + 8] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0xd6930f40 // setae sil + LONG $0x41100ff3; BYTE $0x0c // movss xmm0, dword [rcx + 12] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 LONG $0xd7930f40 // setae dil - LONG $0x6e394466; BYTE $0x14 // cmp word [rsi + 20], r13w + LONG $0x41100ff3; BYTE $0x10 // movss xmm0, dword [rcx + 16] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 LONG $0xd0930f41 // setae r8b - LONG $0x6e394466; BYTE $0x16 // cmp word [rsi + 22], r13w + LONG $0x41100ff3; BYTE $0x14 // movss xmm0, dword [rcx + 20] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000000f02494930f // setae byte [rsp + 240] + LONG $0x41100ff3; BYTE $0x18 // movss xmm0, dword [rcx + 24] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000001002494930f // setae byte [rsp + 256] + LONG $0x41100ff3; BYTE $0x1c // movss xmm0, dword [rcx + 28] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000001502494930f // setae byte [rsp + 336] + LONG $0x41100ff3; BYTE $0x20 // movss xmm0, dword [rcx + 32] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000000b02494930f // setae byte [rsp + 176] + LONG $0x41100ff3; BYTE $0x24 // movss xmm0, dword [rcx + 36] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 LONG $0xd1930f41 // setae r9b - LONG $0x6e394466; BYTE $0x18 // cmp word [rsi + 24], r13w + LONG $0x41100ff3; BYTE $0x28 // movss xmm0, dword [rcx + 40] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 LONG $0xd3930f41 // setae r11b - LONG $0x6e394466; BYTE $0x1a // cmp word [rsi + 26], r13w - LONG $0xd4930f41 // setae r12b - LONG $0x6e394466; BYTE $0x1c // cmp word [rsi + 28], r13w - QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0x6e394466; BYTE $0x1e // cmp word [rsi + 30], r13w - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x6e394466; BYTE $0x20 // cmp word [rsi + 32], r13w - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x6e394466; BYTE $0x22 // cmp word [rsi + 34], r13w - QUAD $0x000001302494930f // setae byte [rsp + 304] - LONG $0x6e394466; BYTE $0x24 // cmp word [rsi + 36], r13w - QUAD $0x000001002494930f // setae byte [rsp + 256] - LONG $0x6e394466; BYTE $0x26 // cmp word [rsi + 38], r13w + LONG $0x41100ff3; BYTE $0x2c // movss xmm0, dword [rcx + 44] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0xd7930f41 // setae r15b + LONG $0x41100ff3; BYTE $0x30 // movss xmm0, dword [rcx + 48] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x41100ff3; BYTE $0x34 // movss xmm0, dword [rcx + 52] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 QUAD $0x000000e02494930f // setae byte [rsp + 224] - LONG $0x6e394466; BYTE $0x28 // cmp word [rsi + 40], r13w - QUAD $0x000000b02494930f // setae byte [rsp + 176] - LONG $0x6e394466; BYTE $0x2a // cmp word [rsi + 42], r13w + LONG $0x41100ff3; BYTE $0x38 // movss xmm0, dword [rcx + 56] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000000c02494930f // setae byte [rsp + 192] + LONG $0x41100ff3; BYTE $0x3c // movss xmm0, dword [rcx + 60] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + QUAD $0x000000d02494930f // setae byte [rsp + 208] + LONG $0x41100ff3; BYTE $0x40 // movss xmm0, dword [rcx + 64] + LONG $0x49100ff3; BYTE $0x44 // movss xmm1, dword [rcx + 68] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x48 // movss xmm0, dword [rcx + 72] LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x6e394466; BYTE $0x2c // cmp word [rsi + 44], r13w + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x49100ff3; BYTE $0x4c // movss xmm1, dword [rcx + 76] + LONG $0xd2930f41 // setae r10b + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x50 // movss xmm0, dword [rcx + 80] + LONG $0xd6930f41 // setae r14b + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x49100ff3; BYTE $0x54 // movss xmm1, dword [rcx + 84] + LONG $0xd4930f41 // setae r12b + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x58 // movss xmm0, dword [rcx + 88] + QUAD $0x000001102494930f // setae byte [rsp + 272] + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x49100ff3; BYTE $0x5c // movss xmm1, dword [rcx + 92] + QUAD $0x000000a02494930f // setae byte [rsp + 160] + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x60 // movss xmm0, dword [rcx + 96] QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x6e394466; BYTE $0x2e // cmp word [rsi + 46], r13w - LONG $0xd7930f41 // setae r15b - LONG $0x6e394466; BYTE $0x30 // cmp word [rsi + 48], r13w - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x6e394466; BYTE $0x32 // cmp word [rsi + 50], r13w + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x49100ff3; BYTE $0x64 // movss xmm1, dword [rcx + 100] + LONG $0xd5930f41 // setae r13b + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x68 // movss xmm0, dword [rcx + 104] + LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x49100ff3; BYTE $0x6c // movss xmm1, dword [rcx + 108] QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x6e394466; BYTE $0x34 // cmp word [rsi + 52], r13w + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x70 // movss xmm0, dword [rcx + 112] LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x6e394466; BYTE $0x36 // cmp word [rsi + 54], r13w + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x49100ff3; BYTE $0x74 // movss xmm1, dword [rcx + 116] LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x6e394466; BYTE $0x38 // cmp word [rsi + 56], r13w + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x41100ff3; BYTE $0x78 // movss xmm0, dword [rcx + 120] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x49100ff3; BYTE $0x7c // movss xmm1, dword [rcx + 124] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x6e394466; BYTE $0x3a // cmp word [rsi + 58], r13w - LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] - LONG $0x6e394466; BYTE $0x3c // cmp word [rsi + 60], r13w + LONG $0xc32e0f41 // ucomiss xmm0, xmm11 LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] - LONG $0x6e394466; BYTE $0x3e // cmp word [rsi + 62], r13w - WORD $0x930f; BYTE $0xd2 // setae dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000f024940244 // add r10b, byte [rsp + 240] + LONG $0x80e98348 // sub rcx, -128 + LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + WORD $0x930f; BYTE $0xd3 // setae bl + WORD $0xd200 // add dl, dl + LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] + LONG $0x02e6c040 // shl sil, 2 + WORD $0x0840; BYTE $0xd6 // or sil, dl + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x04e0c041 // shl r8b, 4 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + QUAD $0x000000f02494b60f // movzx edx, byte [rsp + 240] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0844; BYTE $0xc2 // or dl, r8b + QUAD $0x0000010024bcb60f // movzx edi, byte [rsp + 256] + LONG $0x06e7c040 // shl dil, 6 + QUAD $0x0000015024b4b60f // movzx esi, byte [rsp + 336] + LONG $0x07e6c040 // shl sil, 7 + WORD $0x0840; BYTE $0xfe // or sil, dil + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x000000b0248c0244 // add r9b, byte [rsp + 176] + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0845; BYTE $0xcb // or r11b, r9b + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0844; BYTE $0xf8 // or al, r15b + WORD $0x0840; BYTE $0xd6 // or sil, dl + QUAD $0x000000e02494b60f // movzx edx, byte [rsp + 224] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0xc208 // or dl, al + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + QUAD $0x000000d024bcb60f // movzx edi, byte [rsp + 208] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xc7 // or dil, al + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + LONG $0x24540244; BYTE $0x70 // add r10b, byte [rsp + 112] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000015024bc0240 // add dil, byte [rsp + 336] + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xf4 // or r12b, r14b QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000012024bcb60f // movzx edi, byte [rsp + 288] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000001302484b60f // movzx eax, byte [rsp + 304] - WORD $0xc000 // add al, al - LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] - WORD $0xc789 // mov edi, eax - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000e02484b60f // movzx eax, byte [rsp + 224] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0x0844; BYTE $0xe0 // or al, r12b + WORD $0x8941; BYTE $0xc0 // mov r8d, eax + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al + WORD $0x0844; BYTE $0xc0 // or al, r8b + WORD $0x0840; BYTE $0xd7 // or dil, dl + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + LONG $0x07e5c041 // shl r13b, 7 + WORD $0x0841; BYTE $0xd5 // or r13b, dl + LONG $0x24048b4c // mov r8, qword [rsp] + WORD $0x8841; BYTE $0x30 // mov byte [r8], sil + WORD $0x0841; BYTE $0xc5 // or r13b, al QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] WORD $0xc000 // add al, al - LONG $0x30244402 // add al, byte [rsp + 48] - WORD $0xc189 // mov ecx, eax + LONG $0x10244402 // add al, byte [rsp + 16] + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl - LONG $0x40c68348 // add rsi, 64 - LONG $0x04c68349 // add r14, 4 + WORD $0xd008 // or al, dl + LONG $0x01788841 // mov byte [r8 + 1], dil + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + LONG $0x02688845 // mov byte [r8 + 2], r13b + WORD $0xc308 // or bl, al + LONG $0x03588841 // mov byte [r8 + 3], bl + LONG $0x04c08349 // add r8, 4 + LONG $0x2404894c // mov qword [rsp], r8 QUAD $0x0000014024848348; BYTE $0xff // add qword [rsp + 320], -1 - JNE LBB10_105 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x00000170249c8b4c // mov r11, qword [rsp + 368] - -LBB10_107: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB10_112 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_110 - -LBB10_114: - LONG $0x1ab70f44 // movzx r11d, word [rdx] - LONG $0x1f7a8d4d // lea r15, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xfa490f4d // cmovns r15, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_118 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_116: - LONG $0x1e394466 // cmp word [rsi], r11w - LONG $0x02768d48 // lea rsi, [rsi + 2] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_116 - LONG $0x01c68349 // add r14, 1 + JNE LBB10_211 + LONG $0x241c8b4c // mov r11, qword [rsp] + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0000013024bc8b44 // mov r15d, dword [rsp + 304] + QUAD $0x0000016024bc8b48 // mov rdi, qword [rsp + 352] + JMP LBB10_213 -LBB10_118: - LONG $0x05ffc149 // sar r15, 5 - LONG $0x20fa8349 // cmp r10, 32 - QUAD $0x00000188249c8944 // mov dword [rsp + 392], r11d - JL LBB10_119 - LONG $0x08ff8349 // cmp r15, 8 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x000001c824bc894c // mov qword [rsp + 456], r15 - JB LBB10_121 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB10_124 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB10_124 +LBB10_58: + WORD $0x8a44; BYTE $0x2a // mov r13b, byte [rdx] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB10_59 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_61 + WORD $0x6349; BYTE $0xd1 // movsxd rdx, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 -LBB10_121: - WORD $0xc031 // xor eax, eax - QUAD $0x0000019024848948 // mov qword [rsp + 400], rax - WORD $0x8949; BYTE $0xf3 // mov r11, rsi - WORD $0x894d; BYTE $0xf4 // mov r12, r14 +LBB10_67: + LONG $0x017e8d48 // lea rdi, [rsi + 1] + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b + LONG $0x000000be; BYTE $0x00 // mov esi, 0 + LONG $0xffd68040 // adc sil, -1 + LONG $0x075a8d48 // lea rbx, [rdx + 7] + WORD $0x8548; BYTE $0xd2 // test rdx, rdx + LONG $0xda490f48 // cmovns rbx, rdx + LONG $0x03fbc148 // sar rbx, 3 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xce // xor sil, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xd189 // mov ecx, edx + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0x2040; BYTE $0xf0 // and al, sil + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1c048841 // mov byte [r12 + rbx], al + LONG $0x01c28348 // add rdx, 1 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_67 + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JNE LBB10_63 + JMP LBB10_227 + +LBB10_158: + WORD $0x8b44; BYTE $0x2a // mov r13d, dword [rdx] + LONG $0x07498d41 // lea ecx, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc9490f41 // cmovns ecx, r9d + WORD $0xe183; BYTE $0xf8 // and ecx, -8 + WORD $0x2941; BYTE $0xc9 // sub r9d, ecx + JE LBB10_164 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf0 // cmp r8, r14 + LONG $0xc64f0f4d // cmovg r8, r14 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB10_162 + WORD $0x6349; BYTE $0xf9 // movsxd rdi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi -LBB10_127: - LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 - QUAD $0x0000019024bc2b4c // sub r15, qword [rsp + 400] - QUAD $0x0000014024bc894c // mov qword [rsp + 320], r15 - QUAD $0x0000018824ac8b44 // mov r13d, dword [rsp + 392] +LBB10_161: + LONG $0x04718d48 // lea rsi, [rcx + 4] + WORD $0x3944; BYTE $0x29 // cmp dword [rcx], r13d + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x07478d48 // lea rax, [rdi + 7] + WORD $0x8548; BYTE $0xff // test rdi, rdi + LONG $0xc7490f48 // cmovns rax, rdi + LONG $0x03f8c148 // sar rax, 3 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf989 // mov ecx, edi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001ba; BYTE $0x00 // mov edx, 1 + WORD $0xe2d3 // shl edx, cl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x04148841 // mov byte [r12 + rax], dl + LONG $0x01c78348 // add rdi, 1 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + LONG $0xffc38349 // add r11, -1 + JNE LBB10_161 + +LBB10_162: + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + LONG $0x01c48349 // add r12, 1 + +LBB10_164: + LONG $0x1f468d49 // lea rax, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xc6490f49 // cmovns rax, r14 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_168 + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x0000016024848948 // mov qword [rsp + 352], rax + QUAD $0x0000013024848948 // mov qword [rsp + 304], rax -LBB10_128: - LONG $0x2b394566 // cmp word [r11], r13w - QUAD $0x000000f024949d0f // setge byte [rsp + 240] - LONG $0x6b394566; BYTE $0x02 // cmp word [r11 + 2], r13w - LONG $0xd09d0f41 // setge r8b - LONG $0x6b394566; BYTE $0x04 // cmp word [r11 + 4], r13w +LBB10_166: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 + WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x046e3944 // cmp dword [rsi + 4], r13d + LONG $0xd19d0f41 // setge r9b + LONG $0x086e3944 // cmp dword [rsi + 8], r13d LONG $0xd69d0f41 // setge r14b - LONG $0x6b394566; BYTE $0x06 // cmp word [r11 + 6], r13w - QUAD $0x0000011024949d0f // setge byte [rsp + 272] - LONG $0x6b394566; BYTE $0x08 // cmp word [r11 + 8], r13w - QUAD $0x000000d024949d0f // setge byte [rsp + 208] - LONG $0x6b394566; BYTE $0x0a // cmp word [r11 + 10], r13w - QUAD $0x000000c024949d0f // setge byte [rsp + 192] - LONG $0x6b394566; BYTE $0x0c // cmp word [r11 + 12], r13w + LONG $0x0c6e3944 // cmp dword [rsi + 12], r13d + QUAD $0x000000f024949d0f // setge byte [rsp + 240] + LONG $0x106e3944 // cmp dword [rsi + 16], r13d + QUAD $0x000000e024949d0f // setge byte [rsp + 224] + LONG $0x146e3944 // cmp dword [rsi + 20], r13d + QUAD $0x000000b024949d0f // setge byte [rsp + 176] + LONG $0x186e3944 // cmp dword [rsi + 24], r13d WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x6b394566; BYTE $0x0e // cmp word [r11 + 14], r13w - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x6b394566; BYTE $0x10 // cmp word [r11 + 16], r13w + LONG $0x1c6e3944 // cmp dword [rsi + 28], r13d + LONG $0xd39d0f41 // setge r11b + LONG $0x206e3944 // cmp dword [rsi + 32], r13d QUAD $0x0000015024949d0f // setge byte [rsp + 336] - LONG $0x6b394566; BYTE $0x12 // cmp word [r11 + 18], r13w + LONG $0x246e3944 // cmp dword [rsi + 36], r13d WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x6b394566; BYTE $0x14 // cmp word [r11 + 20], r13w - LONG $0xd69d0f40 // setge sil - LONG $0x6b394566; BYTE $0x16 // cmp word [r11 + 22], r13w - LONG $0xd19d0f41 // setge r9b - LONG $0x6b394566; BYTE $0x18 // cmp word [r11 + 24], r13w + LONG $0x286e3944 // cmp dword [rsi + 40], r13d + LONG $0xd79d0f40 // setge dil + LONG $0x2c6e3944 // cmp dword [rsi + 44], r13d + LONG $0xd09d0f41 // setge r8b + LONG $0x306e3944 // cmp dword [rsi + 48], r13d LONG $0xd29d0f41 // setge r10b - LONG $0x6b394566; BYTE $0x1a // cmp word [r11 + 26], r13w + LONG $0x346e3944 // cmp dword [rsi + 52], r13d LONG $0xd49d0f41 // setge r12b - LONG $0x6b394566; BYTE $0x1c // cmp word [r11 + 28], r13w + LONG $0x386e3944 // cmp dword [rsi + 56], r13d QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x6b394566; BYTE $0x1e // cmp word [r11 + 30], r13w - LONG $0xd79d0f40 // setge dil - LONG $0x6b394566; BYTE $0x20 // cmp word [r11 + 32], r13w + LONG $0x3c6e3944 // cmp dword [rsi + 60], r13d + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x406e3944 // cmp dword [rsi + 64], r13d QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x6b394566; BYTE $0x22 // cmp word [r11 + 34], r13w - QUAD $0x0000013024949d0f // setge byte [rsp + 304] - LONG $0x6b394566; BYTE $0x24 // cmp word [r11 + 36], r13w + LONG $0x446e3944 // cmp dword [rsi + 68], r13d QUAD $0x0000010024949d0f // setge byte [rsp + 256] - LONG $0x6b394566; BYTE $0x26 // cmp word [r11 + 38], r13w - QUAD $0x000000e024949d0f // setge byte [rsp + 224] - LONG $0x6b394566; BYTE $0x28 // cmp word [r11 + 40], r13w - QUAD $0x000000b024949d0f // setge byte [rsp + 176] - LONG $0x6b394566; BYTE $0x2a // cmp word [r11 + 42], r13w - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x6b394566; BYTE $0x2c // cmp word [r11 + 44], r13w + LONG $0x486e3944 // cmp dword [rsi + 72], r13d + QUAD $0x0000011024949d0f // setge byte [rsp + 272] + LONG $0x4c6e3944 // cmp dword [rsi + 76], r13d + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + LONG $0x506e3944 // cmp dword [rsi + 80], r13d + QUAD $0x000000c024949d0f // setge byte [rsp + 192] + LONG $0x546e3944 // cmp dword [rsi + 84], r13d QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x6b394566; BYTE $0x2e // cmp word [r11 + 46], r13w + LONG $0x586e3944 // cmp dword [rsi + 88], r13d + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x5c6e3944 // cmp dword [rsi + 92], r13d LONG $0xd79d0f41 // setge r15b - LONG $0x6b394566; BYTE $0x30 // cmp word [r11 + 48], r13w + LONG $0x606e3944 // cmp dword [rsi + 96], r13d LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x6b394566; BYTE $0x32 // cmp word [r11 + 50], r13w - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x6b394566; BYTE $0x34 // cmp word [r11 + 52], r13w + LONG $0x646e3944 // cmp dword [rsi + 100], r13d + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x686e3944 // cmp dword [rsi + 104], r13d LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x6b394566; BYTE $0x36 // cmp word [r11 + 54], r13w + LONG $0x6c6e3944 // cmp dword [rsi + 108], r13d LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x6b394566; BYTE $0x38 // cmp word [r11 + 56], r13w + LONG $0x706e3944 // cmp dword [rsi + 112], r13d LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x6b394566; BYTE $0x3a // cmp word [r11 + 58], r13w + LONG $0x746e3944 // cmp dword [rsi + 116], r13d LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0x6b394566; BYTE $0x3c // cmp word [r11 + 60], r13w - QUAD $0x0000016024949d0f // setge byte [rsp + 352] - LONG $0x6b394566; BYTE $0x3e // cmp word [r11 + 62], r13w - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0x0045; BYTE $0xc0 // add r8b, r8b - QUAD $0x000000f024840244 // add r8b, byte [rsp + 240] + LONG $0x786e3944 // cmp dword [rsi + 120], r13d + LONG $0x24149d0f // setge byte [rsp] + LONG $0x7c6e3944 // cmp dword [rsi + 124], r13d + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0x0045; BYTE $0xc9 // add r9b, r9b + QUAD $0x00000140248c0244 // add r9b, byte [rsp + 320] WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xc6 // or r14b, r8b + WORD $0x0845; BYTE $0xce // or r14b, r9b WORD $0xc900 // add cl, cl LONG $0x50248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 336] - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf0 // or al, r14b - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xce // or sil, cl - QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xcf // or dil, cl + QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xc108 // or cl, al - WORD $0x8941; BYTE $0xc8 // mov r8d, ecx - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b + LONG $0x03e0c041 // shl r8b, 3 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xca // or r10b, r9b + WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x0000012024b4b60f // movzx esi, byte [rsp + 288] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xf7 // or dil, sil - WORD $0xcb08 // or bl, cl - WORD $0x0844; BYTE $0xe7 // or dil, r12b - QUAD $0x00000130248cb60f // movzx ecx, byte [rsp + 304] - WORD $0xc900 // add cl, cl - LONG $0xa0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 160] - WORD $0xce89 // mov esi, ecx - QUAD $0x00000100248cb60f // movzx ecx, byte [rsp + 256] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0xce89 // mov esi, ecx - QUAD $0x000000e0248cb60f // movzx ecx, byte [rsp + 224] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0xce89 // mov esi, ecx - QUAD $0x000000b0248cb60f // movzx ecx, byte [rsp + 176] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0xce89 // mov esi, ecx - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0840; BYTE $0xf1 // or cl, sil - WORD $0xce89 // mov esi, ecx - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - WORD $0x1988 // mov byte [rcx], bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + QUAD $0x00000120248cb60f // movzx ecx, byte [rsp + 288] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl + WORD $0x0841; BYTE $0xc3 // or r11b, al + WORD $0x0844; BYTE $0xe2 // or dl, r12b + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] + WORD $0xc000 // add al, al + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] + WORD $0xc189 // mov ecx, eax + QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + LONG $0x241c8845 // mov byte [r12], r11b + QUAD $0x00000090248cb60f // movzx ecx, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x01798840 // mov byte [rcx + 1], dil - WORD $0x0841; BYTE $0xf7 // or r15b, sil - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x24548841; BYTE $0x01 // mov byte [r12 + 1], dl + WORD $0x0841; BYTE $0xc7 // or r15b, al + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al LONG $0x30244402 // add al, byte [rsp + 48] - WORD $0xc389 // mov ebx, eax + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd808 // or al, bl - WORD $0xc389 // mov ebx, eax + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd808 // or al, bl - QUAD $0x00000160249cb60f // movzx ebx, byte [rsp + 352] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xda08 // or dl, bl - WORD $0xc208 // or dl, al - LONG $0x02798844 // mov byte [rcx + 2], r15b - WORD $0x5188; BYTE $0x03 // mov byte [rcx + 3], dl - LONG $0x40c38349 // add r11, 64 - LONG $0x04c18348 // add rcx, 4 - LONG $0x244c8948; BYTE $0x08 // mov qword [rsp + 8], rcx - QUAD $0x0000014024848348; BYTE $0xff // add qword [rsp + 320], -1 - JNE LBB10_128 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x000001c824bc8b4c // mov r15, qword [rsp + 456] - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - JMP LBB10_130 + WORD $0xc808 // or al, cl + LONG $0x240cb60f // movzx ecx, byte [rsp] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xcb08 // or bl, cl + WORD $0xc308 // or bl, al + LONG $0x247c8845; BYTE $0x02 // mov byte [r12 + 2], r15b + LONG $0x245c8841; BYTE $0x03 // mov byte [r12 + 3], bl + LONG $0x80c68148; WORD $0x0000; BYTE $0x00 // add rsi, 128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x0000013024848348; BYTE $0xff // add qword [rsp + 304], -1 + JNE LBB10_166 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x0000016024848b48 // mov rax, qword [rsp + 352] -LBB10_157: - WORD $0x8b4c; BYTE $0x2a // mov r13, qword [rdx] - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_161 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB10_159: - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x08768d48 // lea rsi, [rsi + 8] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1e // movzx r8d, byte [r14 + rbx] - WORD $0x3044; BYTE $0xc2 // xor dl, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xd7 // and dil, dl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1e3c8841 // mov byte [r14 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_159 - LONG $0x01c68349 // add r14, 1 +LBB10_168: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB10_227 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc6 // cmp r14, rax + JNE LBB10_174 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB10_171 -LBB10_161: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_165 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x00000170249c894c // mov qword [rsp + 368], r11 - QUAD $0x00000140249c894c // mov qword [rsp + 320], r11 - -LBB10_163: - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 - WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - QUAD $0x000000f024949d0f // setge byte [rsp + 240] - LONG $0x086e394c // cmp qword [rsi + 8], r13 - LONG $0xd29d0f41 // setge r10b - LONG $0x106e394c // cmp qword [rsi + 16], r13 - LONG $0xd69d0f41 // setge r14b - LONG $0x186e394c // cmp qword [rsi + 24], r13 +LBB10_5: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB10_90 + +LBB10_138: + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 + WORD $0x8949; BYTE $0xf3 // mov r11, rsi + +LBB10_149: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB10_227 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB10_154 + WORD $0xf631 // xor esi, esi + JMP LBB10_152 + +LBB10_202: + WORD $0x894d; BYTE $0xe3 // mov r11, r12 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_213: + LONG $0x05e7c148 // shl rdi, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xf8 // sub r8, rdi + JLE LBB10_227 + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + LONG $0x01cf8348 // or rdi, 1 + WORD $0x3949; BYTE $0xfe // cmp r14, rdi + JNE LBB10_218 + WORD $0x3145; BYTE $0xff // xor r15d, r15d + JMP LBB10_216 + +LBB10_59: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + JMP LBB10_64 + +LBB10_87: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + +LBB10_89: + LONG $0x01c48349 // add r12, 1 + +LBB10_90: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_91 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x243c8844 // mov byte [rsp], r15b + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x00000190248c8948 // mov qword [rsp + 400], rcx + JB LBB10_95 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB10_98 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB10_98 + +LBB10_95: + WORD $0xc031 // xor eax, eax + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + LONG $0x2464894c; BYTE $0x70 // mov qword [rsp + 112], r12 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + +LBB10_101: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x00000130248c8948 // mov qword [rsp + 304], rcx + +LBB10_102: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b + QUAD $0x0000014024949d0f // setge byte [rsp + 320] + LONG $0x017e3844 // cmp byte [rsi + 1], r15b + LONG $0xd69d0f40 // setge sil + LONG $0x02793844 // cmp byte [rcx + 2], r15b + LONG $0xd39d0f41 // setge r11b + LONG $0x03793844 // cmp byte [rcx + 3], r15b + LONG $0xd79d0f41 // setge r15b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al QUAD $0x0000011024949d0f // setge byte [rsp + 272] - LONG $0x206e394c // cmp qword [rsi + 32], r13 - QUAD $0x000000d024949d0f // setge byte [rsp + 208] - LONG $0x286e394c // cmp qword [rsi + 40], r13 - QUAD $0x000000c024949d0f // setge byte [rsp + 192] - LONG $0x306e394c // cmp qword [rsi + 48], r13 - WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x386e394c // cmp qword [rsi + 56], r13 - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x406e394c // cmp qword [rsi + 64], r13 - QUAD $0x0000015024949d0f // setge byte [rsp + 336] - LONG $0x486e394c // cmp qword [rsi + 72], r13 - LONG $0xd79d0f40 // setge dil - LONG $0x506e394c // cmp qword [rsi + 80], r13 + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al + LONG $0xd59d0f41 // setge r13b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al LONG $0xd09d0f41 // setge r8b - LONG $0x586e394c // cmp qword [rsi + 88], r13 + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + QUAD $0x000000f024949d0f // setge byte [rsp + 240] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0xd79d0f40 // setge dil + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al LONG $0xd19d0f41 // setge r9b - LONG $0x606e394c // cmp qword [rsi + 96], r13 - LONG $0xd39d0f41 // setge r11b - LONG $0x686e394c // cmp qword [rsi + 104], r13 + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al + LONG $0xd69d0f41 // setge r14b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al LONG $0xd49d0f41 // setge r12b - LONG $0x706e394c // cmp qword [rsi + 112], r13 + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x0000015024949d0f // setge byte [rsp + 336] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al + WORD $0x9d0f; BYTE $0xd0 // setge al + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl QUAD $0x0000012024949d0f // setge byte [rsp + 288] - LONG $0x786e394c // cmp qword [rsi + 120], r13 - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x80ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 128], r13 - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x88ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 136], r13 - QUAD $0x0000013024949d0f // setge byte [rsp + 304] - LONG $0x90ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 144], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl QUAD $0x0000010024949d0f // setge byte [rsp + 256] - LONG $0x98ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 152], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl QUAD $0x000000e024949d0f // setge byte [rsp + 224] - LONG $0xa0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 160], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl QUAD $0x000000b024949d0f // setge byte [rsp + 176] - LONG $0xa8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 168], r13 - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0xb0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 176], r13 - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0xb8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 184], r13 - LONG $0xd79d0f41 // setge r15b - LONG $0xc0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 192], r13 - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0xc8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 200], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + QUAD $0x000000c024949d0f // setge byte [rsp + 192] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd29d0f41 // setge r10b + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0xd0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 208], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0xd8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 216], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0xe0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 224], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0xe8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 232], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0xf0ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 240], r13 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl LONG $0x24549d0f; BYTE $0x08 // setge byte [rsp + 8] - LONG $0xf8ae394c; WORD $0x0000; BYTE $0x00 // cmp qword [rsi + 248], r13 - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x000000f024940244 // add r10b, byte [rsp + 240] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xc308 // or bl, al - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xd6 // or r14b, r10b - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000015024bc0240 // add dil, byte [rsp + 336] - QUAD $0x000001102484b60f // movzx eax, byte [rsp + 272] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0844; BYTE $0xf0 // or al, r14b - WORD $0x8941; BYTE $0xc2 // mov r10d, eax - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - LONG $0x02e0c041 // shl r8b, 2 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xd0 // or al, r10b - WORD $0xc789 // mov edi, eax + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000014024b40240 // add sil, byte [rsp + 320] + LONG $0x06e5c041 // shl r13b, 6 + LONG $0x07e0c041 // shl r8b, 7 + WORD $0x0845; BYTE $0xe8 // or r8b, r13b + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0841; BYTE $0xf3 // or r11b, sil + WORD $0xd200 // add dl, dl + LONG $0xf0249402; WORD $0x0000; BYTE $0x00 // add dl, byte [rsp + 240] + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xdf // or r15b, r11b + LONG $0x02e7c040 // shl dil, 2 + WORD $0x0840; BYTE $0xd7 // or dil, dl + QUAD $0x000001102494b60f // movzx edx, byte [rsp + 272] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0844; BYTE $0xfa // or dl, r15b + WORD $0xd689 // mov esi, edx + LONG $0x3cb60f44; BYTE $0x24 // movzx r15d, byte [rsp] LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xcb // or r11b, r9b + WORD $0x0841; BYTE $0xf9 // or r9b, dil + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x04e6c041 // shl r14b, 4 + WORD $0x0845; BYTE $0xce // or r14b, r9b LONG $0x05e4c041 // shl r12b, 5 - WORD $0x0845; BYTE $0xdc // or r12b, r11b - QUAD $0x0000012024bcb60f // movzx edi, byte [rsp + 288] - LONG $0x06e7c040 // shl dil, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf9 // or cl, dil - WORD $0xc308 // or bl, al - WORD $0x0844; BYTE $0xe1 // or cl, r12b - QUAD $0x000001302484b60f // movzx eax, byte [rsp + 304] - WORD $0xc000 // add al, al - LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] - WORD $0xc789 // mov edi, eax - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000e02484b60f // movzx eax, byte [rsp + 224] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0xc789 // mov edi, eax - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0840; BYTE $0xf8 // or al, dil - WORD $0x8841; BYTE $0x1e // mov byte [r14], bl - QUAD $0x00000080249cb60f // movzx ebx, byte [rsp + 128] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xdf // or r15b, bl - LONG $0x014e8841 // mov byte [r14 + 1], cl - WORD $0x0841; BYTE $0xc7 // or r15b, al - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xc000 // add al, al - LONG $0x30244402 // add al, byte [rsp + 48] - WORD $0xc189 // mov ecx, eax + WORD $0x0845; BYTE $0xf4 // or r12b, r14b + QUAD $0x0000015024b4b60f // movzx esi, byte [rsp + 336] + LONG $0x06e6c040 // shl sil, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0x0840; BYTE $0xf0 // or al, sil + WORD $0x0841; BYTE $0xd0 // or r8b, dl + WORD $0x0844; BYTE $0xe0 // or al, r12b + QUAD $0x000001002494b60f // movzx edx, byte [rsp + 256] + WORD $0xd200 // add dl, dl + LONG $0x20249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 288] + WORD $0xd689 // mov esi, edx + QUAD $0x000000e02494b60f // movzx edx, byte [rsp + 224] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000d02494b60f // movzx edx, byte [rsp + 208] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000b02494b60f // movzx edx, byte [rsp + 176] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] + WORD $0x8844; BYTE $0x07 // mov byte [rdi], r8b + QUAD $0x000000c024b4b60f // movzx esi, byte [rsp + 192] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xf2 // or r10b, sil + WORD $0x4788; BYTE $0x01 // mov byte [rdi + 1], al + WORD $0x0841; BYTE $0xd2 // or r10b, dl LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xc000 // add al, al + LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - WORD $0xe2c0; BYTE $0x07 // shl dl, 7 - WORD $0xca08 // or dl, cl - WORD $0xc208 // or dl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x03568841 // mov byte [r14 + 3], dl - LONG $0x00c68148; WORD $0x0001; BYTE $0x00 // add rsi, 256 - LONG $0x04c68349 // add r14, 4 - QUAD $0x0000014024848348; BYTE $0xff // add qword [rsp + 320], -1 - JNE LBB10_163 - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x00000170249c8b4c // mov r11, qword [rsp + 368] - -LBB10_165: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB10_170 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB10_168 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0xe3c0; BYTE $0x07 // shl bl, 7 + WORD $0xd308 // or bl, dl + WORD $0xc308 // or bl, al + LONG $0x02578844 // mov byte [rdi + 2], r10b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + LONG $0x247c8948; BYTE $0x70 // mov qword [rsp + 112], rdi + QUAD $0x0000013024848348; BYTE $0xff // add qword [rsp + 304], -1 + JNE LBB10_102 + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x00000190248c8b48 // mov rcx, qword [rsp + 400] + JMP LBB10_104 -LBB10_172: - LONG $0x1f5a8d4d // lea r11, [r10 + 31] - WORD $0x854d; BYTE $0xd2 // test r10, r10 - LONG $0xda490f4d // cmovns r11, r10 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x100f44f3; BYTE $0x1a // movss xmm11, dword [rdx] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB10_176 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB10_91: + LONG $0x2464894c; BYTE $0x70 // mov qword [rsp + 112], r12 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB10_174: - LONG $0x06100ff3 // movss xmm0, dword [rsi] - LONG $0x04c68348 // add rsi, 4 - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x000000ba; BYTE $0x00 // mov edx, 0 - WORD $0xd280; BYTE $0xff // adc dl, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] - WORD $0x3044; BYTE $0xca // xor dl, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB10_174 - LONG $0x01c68349 // add r14, 1 +LBB10_104: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB10_227 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB10_107 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB10_110 -LBB10_176: - LONG $0x05fbc149 // sar r11, 5 - LONG $0x20fa8349 // cmp r10, 32 - JL LBB10_177 - LONG $0x04fb8349 // cmp r11, 4 - JB LBB10_179 - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - WORD $0x3949; BYTE $0xc6 // cmp r14, rax - JAE LBB10_182 - LONG $0x9e048d4b // lea rax, [r14 + 4*r11] - WORD $0x3948; BYTE $0xf0 // cmp rax, rsi - JBE LBB10_182 +LBB10_61: + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x294d; BYTE $0xc6 // sub r14, r8 + JE LBB10_227 + +LBB10_63: + LONG $0x01c48349 // add r12, 1 + +LBB10_64: + LONG $0x1f4e8d49 // lea rcx, [r14 + 31] + WORD $0x854d; BYTE $0xf6 // test r14, r14 + LONG $0xce490f49 // cmovns rcx, r14 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20fe8349 // cmp r14, 32 + JL LBB10_65 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x242c8844 // mov byte [rsp], r13b + LONG $0x2474894c; BYTE $0x48 // mov qword [rsp + 72], r14 + QUAD $0x00000178248c8948 // mov qword [rsp + 376], rcx + JB LBB10_69 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x0148; BYTE $0xf8 // add rax, rdi + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB10_72 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JAE LBB10_72 -LBB10_179: +LBB10_69: WORD $0xc031 // xor eax, eax - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - WORD $0x894d; BYTE $0xf7 // mov r15, r14 + QUAD $0x0000018024848948 // mov qword [rsp + 384], rax + QUAD $0x0000019024a4894c // mov qword [rsp + 400], r12 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB10_185: - LONG $0x247c894c; BYTE $0x08 // mov qword [rsp + 8], r15 - LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 - QUAD $0x00000140249c894c // mov qword [rsp + 320], r11 - WORD $0x2949; BYTE $0xc3 // sub r11, rax - QUAD $0x000000f0249c894c // mov qword [rsp + 240], r11 +LBB10_75: + QUAD $0x00000180248c2b48 // sub rcx, qword [rsp + 384] + QUAD $0x00000160248c8948 // mov qword [rsp + 352], rcx + QUAD $0x0000019024bc8b48 // mov rdi, qword [rsp + 400] -LBB10_186: - LONG $0x02100ff3 // movss xmm0, dword [rdx] - LONG $0x4a100ff3; BYTE $0x04 // movss xmm1, dword [rdx + 4] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - QUAD $0x000001202494930f // setae byte [rsp + 288] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x42100ff3; BYTE $0x08 // movss xmm0, dword [rdx + 8] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd6930f40 // setae sil - LONG $0x42100ff3; BYTE $0x0c // movss xmm0, dword [rdx + 12] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd7930f40 // setae dil - LONG $0x42100ff3; BYTE $0x10 // movss xmm0, dword [rdx + 16] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd0930f41 // setae r8b - LONG $0x42100ff3; BYTE $0x14 // movss xmm0, dword [rdx + 20] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - QUAD $0x000001102494930f // setae byte [rsp + 272] - LONG $0x42100ff3; BYTE $0x18 // movss xmm0, dword [rdx + 24] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 +LBB10_76: + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b QUAD $0x000001302494930f // setae byte [rsp + 304] - LONG $0x42100ff3; BYTE $0x1c // movss xmm0, dword [rdx + 28] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - QUAD $0x000001502494930f // setae byte [rsp + 336] - LONG $0x42100ff3; BYTE $0x20 // movss xmm0, dword [rdx + 32] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - QUAD $0x000000c02494930f // setae byte [rsp + 192] - LONG $0x42100ff3; BYTE $0x24 // movss xmm0, dword [rdx + 36] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd1930f41 // setae r9b - LONG $0x42100ff3; BYTE $0x28 // movss xmm0, dword [rdx + 40] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0xd3930f41 // setae r11b - LONG $0x42100ff3; BYTE $0x2c // movss xmm0, dword [rdx + 44] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x016e3844 // cmp byte [rsi + 1], r13b + LONG $0xd6930f40 // setae sil + LONG $0x02693844 // cmp byte [rcx + 2], r13b LONG $0xd7930f41 // setae r15b - LONG $0x42100ff3; BYTE $0x30 // movss xmm0, dword [rdx + 48] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x42100ff3; BYTE $0x34 // movss xmm0, dword [rdx + 52] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - QUAD $0x000000d02494930f // setae byte [rsp + 208] - LONG $0x42100ff3; BYTE $0x38 // movss xmm0, dword [rdx + 56] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - QUAD $0x000000b02494930f // setae byte [rsp + 176] - LONG $0x42100ff3; BYTE $0x3c // movss xmm0, dword [rdx + 60] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x03693844 // cmp byte [rcx + 3], r13b + QUAD $0x000000f02494930f // setae byte [rsp + 240] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x04 // cmp byte [rcx + 4], al QUAD $0x000000e02494930f // setae byte [rsp + 224] - LONG $0x42100ff3; BYTE $0x40 // movss xmm0, dword [rdx + 64] - LONG $0x4a100ff3; BYTE $0x44 // movss xmm1, dword [rdx + 68] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x48 // movss xmm0, dword [rdx + 72] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x05 // cmp byte [rcx + 5], al QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - LONG $0x4a100ff3; BYTE $0x4c // movss xmm1, dword [rdx + 76] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x06 // cmp byte [rcx + 6], al + LONG $0xd5930f41 // setae r13b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x07 // cmp byte [rcx + 7], al + LONG $0xd1930f41 // setae r9b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x08 // cmp byte [rcx + 8], al + QUAD $0x000001502494930f // setae byte [rsp + 336] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x09 // cmp byte [rcx + 9], al + WORD $0x930f; BYTE $0xd2 // setae dl + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0a // cmp byte [rcx + 10], al + LONG $0xd0930f41 // setae r8b + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0b // cmp byte [rcx + 11], al LONG $0xd2930f41 // setae r10b - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x50 // movss xmm0, dword [rdx + 80] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0c // cmp byte [rcx + 12], al LONG $0xd6930f41 // setae r14b - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - LONG $0x4a100ff3; BYTE $0x54 // movss xmm1, dword [rdx + 84] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0d // cmp byte [rcx + 13], al + QUAD $0x000001402494930f // setae byte [rsp + 320] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0e // cmp byte [rcx + 14], al + QUAD $0x000001202494930f // setae byte [rsp + 288] + LONG $0x2404b60f // movzx eax, byte [rsp] + WORD $0x4138; BYTE $0x0f // cmp byte [rcx + 15], al LONG $0xd4930f41 // setae r12b - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x58 // movss xmm0, dword [rdx + 88] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x10 // cmp byte [rcx + 16], bl QUAD $0x000001002494930f // setae byte [rsp + 256] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - LONG $0x4a100ff3; BYTE $0x5c // movss xmm1, dword [rdx + 92] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x11 // cmp byte [rcx + 17], bl + QUAD $0x000001102494930f // setae byte [rsp + 272] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x12 // cmp byte [rcx + 18], bl + QUAD $0x000000d02494930f // setae byte [rsp + 208] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x13 // cmp byte [rcx + 19], bl QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x60 // movss xmm0, dword [rdx + 96] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - LONG $0x4a100ff3; BYTE $0x64 // movss xmm1, dword [rdx + 100] - LONG $0xd5930f41 // setae r13b - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x68 // movss xmm0, dword [rdx + 104] - LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - LONG $0x4a100ff3; BYTE $0x6c // movss xmm1, dword [rdx + 108] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x14 // cmp byte [rcx + 20], bl + QUAD $0x000000c02494930f // setae byte [rsp + 192] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x15 // cmp byte [rcx + 21], bl QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x70 // movss xmm0, dword [rdx + 112] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x16 // cmp byte [rcx + 22], bl + QUAD $0x000000b02494930f // setae byte [rsp + 176] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x17 // cmp byte [rcx + 23], bl + LONG $0xd3930f41 // setae r11b + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x18 // cmp byte [rcx + 24], bl + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x19 // cmp byte [rcx + 25], bl LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - LONG $0x4a100ff3; BYTE $0x74 // movss xmm1, dword [rdx + 116] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1a // cmp byte [rcx + 26], bl LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - LONG $0x42100ff3; BYTE $0x78 // movss xmm0, dword [rdx + 120] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1b // cmp byte [rcx + 27], bl LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 - LONG $0x4a100ff3; BYTE $0x7c // movss xmm1, dword [rdx + 124] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1c // cmp byte [rcx + 28], bl LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - QUAD $0x000001602494930f // setae byte [rsp + 352] - LONG $0x80ea8348 // sub rdx, -128 - LONG $0xcb2e0f41 // ucomiss xmm1, xmm11 + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1d // cmp byte [rcx + 29], bl + LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1e // cmp byte [rcx + 30], bl + LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] + LONG $0x241cb60f // movzx ebx, byte [rsp] + WORD $0x5938; BYTE $0x1f // cmp byte [rcx + 31], bl WORD $0x930f; BYTE $0xd3 // setae bl - WORD $0xc900 // add cl, cl - LONG $0x20248c02; WORD $0x0001; BYTE $0x00 // add cl, byte [rsp + 288] - LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xce // or sil, cl - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xf7 // or dil, sil - LONG $0x04e0c041 // shl r8b, 4 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - QUAD $0x00000110248cb60f // movzx ecx, byte [rsp + 272] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0x0844; BYTE $0xc1 // or cl, r8b - QUAD $0x0000013024bcb60f // movzx edi, byte [rsp + 304] - LONG $0x06e7c040 // shl dil, 6 - QUAD $0x0000015024b4b60f // movzx esi, byte [rsp + 336] - LONG $0x07e6c040 // shl sil, 7 - WORD $0x0840; BYTE $0xfe // or sil, dil - WORD $0x0045; BYTE $0xc9 // add r9b, r9b - QUAD $0x000000c0248c0244 // add r9b, byte [rsp + 192] - LONG $0x02e3c041 // shl r11b, 2 - WORD $0x0845; BYTE $0xcb // or r11b, r9b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xdf // or r15b, r11b - WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000013024b40240 // add sil, byte [rsp + 304] + LONG $0x06e5c041 // shl r13b, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0845; BYTE $0xe9 // or r9b, r13b + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0841; BYTE $0xf7 // or r15b, sil + WORD $0xd200 // add dl, dl + LONG $0x50249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 336] + QUAD $0x000000f02484b60f // movzx eax, byte [rsp + 240] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0x0844; BYTE $0xf8 // or al, r15b - WORD $0x0840; BYTE $0xce // or sil, cl - QUAD $0x000000d0248cb60f // movzx ecx, byte [rsp + 208] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xc108 // or cl, al - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - QUAD $0x000000e024bcb60f // movzx edi, byte [rsp + 224] - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xc7 // or dil, al - WORD $0x0045; BYTE $0xd2 // add r10b, r10b - QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] - LONG $0x02e6c041 // shl r14b, 2 + LONG $0x02e0c041 // shl r8b, 2 + WORD $0x0841; BYTE $0xd0 // or r8b, dl + QUAD $0x000000e02494b60f // movzx edx, byte [rsp + 224] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0xc208 // or dl, al + WORD $0xd689 // mov esi, edx + LONG $0x2cb60f44; BYTE $0x24 // movzx r13d, byte [rsp] + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xc2 // or r10b, r8b + QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + LONG $0x04e6c041 // shl r14b, 4 WORD $0x0845; BYTE $0xd6 // or r14b, r10b - LONG $0x03e4c041 // shl r12b, 3 - WORD $0x0845; BYTE $0xf4 // or r12b, r14b - QUAD $0x000001002484b60f // movzx eax, byte [rsp + 256] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0x0844; BYTE $0xe0 // or al, r12b - WORD $0x8941; BYTE $0xc0 // mov r8d, eax - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + QUAD $0x000001402484b60f // movzx eax, byte [rsp + 320] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xc0 // or al, r8b - WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e5c041 // shl r13b, 7 - WORD $0x0841; BYTE $0xcd // or r13b, cl - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - WORD $0x8841; BYTE $0x30 // mov byte [r8], sil - WORD $0x0841; BYTE $0xc5 // or r13b, al - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xc000 // add al, al - LONG $0x10244402 // add al, byte [rsp + 16] - WORD $0xc189 // mov ecx, eax + WORD $0x0844; BYTE $0xf0 // or al, r14b + QUAD $0x0000012024b4b60f // movzx esi, byte [rsp + 288] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e4c041 // shl r12b, 7 + WORD $0x0841; BYTE $0xf4 // or r12b, sil + WORD $0x0841; BYTE $0xd1 // or r9b, dl + WORD $0x0841; BYTE $0xc4 // or r12b, al + QUAD $0x000001102494b60f // movzx edx, byte [rsp + 272] + WORD $0xd200 // add dl, dl + LONG $0x00249402; WORD $0x0001; BYTE $0x00 // add dl, byte [rsp + 256] + WORD $0xd689 // mov esi, edx + QUAD $0x000000d02494b60f // movzx edx, byte [rsp + 208] + WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000a02494b60f // movzx edx, byte [rsp + 160] + WORD $0xe2c0; BYTE $0x03 // shl dl, 3 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000c02494b60f // movzx edx, byte [rsp + 192] + WORD $0xe2c0; BYTE $0x04 // shl dl, 4 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0xd689 // mov esi, edx + QUAD $0x000000802494b60f // movzx edx, byte [rsp + 128] + WORD $0xe2c0; BYTE $0x05 // shl dl, 5 + WORD $0x0840; BYTE $0xf2 // or dl, sil + WORD $0x8844; BYTE $0x0f // mov byte [rdi], r9b + QUAD $0x000000b024b4b60f // movzx esi, byte [rsp + 176] + LONG $0x06e6c040 // shl sil, 6 + LONG $0x07e3c041 // shl r11b, 7 + WORD $0x0841; BYTE $0xf3 // or r11b, sil + LONG $0x01678844 // mov byte [rdi + 1], r12b + WORD $0x0841; BYTE $0xd3 // or r11b, dl LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xc000 // add al, al + LONG $0x70244402 // add al, byte [rsp + 112] + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xd008 // or al, dl + WORD $0xc289 // mov edx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - LONG $0x01788841 // mov byte [r8 + 1], dil - QUAD $0x00000160248cb60f // movzx ecx, byte [rsp + 352] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xd008 // or al, dl + LONG $0x2454b60f; BYTE $0x08 // movzx edx, byte [rsp + 8] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 WORD $0xe3c0; BYTE $0x07 // shl bl, 7 - WORD $0xcb08 // or bl, cl - LONG $0x02688845 // mov byte [r8 + 2], r13b + WORD $0xd308 // or bl, dl WORD $0xc308 // or bl, al - LONG $0x03588841 // mov byte [r8 + 3], bl - LONG $0x04c08349 // add r8, 4 - LONG $0x2444894c; BYTE $0x08 // mov qword [rsp + 8], r8 - QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 - JNE LBB10_186 - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - QUAD $0x00000140249c8b4c // mov r11, qword [rsp + 320] - JMP LBB10_188 - -LBB10_9: - QUAD $0x0000009024b4894c // mov qword [rsp + 144], r14 - -LBB10_91: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_94 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB10_97 - -LBB10_61: - QUAD $0x000000e024b4894c // mov qword [rsp + 224], r14 - -LBB10_72: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_75 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + LONG $0x025f8844 // mov byte [rdi + 2], r11b + WORD $0x5f88; BYTE $0x03 // mov byte [rdi + 3], bl + LONG $0x20718d48 // lea rsi, [rcx + 32] + LONG $0x04c78348 // add rdi, 4 + QUAD $0x0000016024848348; BYTE $0xff // add qword [rsp + 352], -1 + JNE LBB10_76 + QUAD $0x0000019024bc8948 // mov qword [rsp + 400], rdi + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] JMP LBB10_78 -LBB10_119: - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - WORD $0x8949; BYTE $0xf3 // mov r11, rsi - -LBB10_130: - LONG $0x05e7c149 // shl r15, 5 - WORD $0x394d; BYTE $0xd7 // cmp r15, r10 - JGE LBB10_201 - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xf8 // sub r8, r15 - WORD $0xf749; BYTE $0xd7 // not r15 - WORD $0x014d; BYTE $0xd7 // add r15, r10 - JNE LBB10_135 - WORD $0xf631 // xor esi, esi - JMP LBB10_133 - -LBB10_177: - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi +LBB10_65: + QUAD $0x0000019024a4894c // mov qword [rsp + 400], r12 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi -LBB10_188: - LONG $0x05e3c149 // shl r11, 5 - WORD $0x394d; BYTE $0xd3 // cmp r11, r10 - JGE LBB10_201 - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - WORD $0x294d; BYTE $0xd8 // sub r8, r11 - WORD $0xf749; BYTE $0xd3 // not r11 - WORD $0x014d; BYTE $0xd3 // add r11, r10 - JNE LBB10_193 - WORD $0xf631 // xor esi, esi - JMP LBB10_191 +LBB10_78: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB10_227 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xce // cmp r14, rcx + JNE LBB10_81 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + JMP LBB10_84 -LBB10_155: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 +LBB10_176: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB10_156: +LBB10_177: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - LONG $0x000000bf; BYTE $0x00 // mov edi, 0 - LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xda // mov rdx, r11 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b + LONG $0x000000b8; BYTE $0x00 // mov eax, 0 + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x16048841 // mov byte [r14 + rdx], al + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] - LONG $0x000000bf; BYTE $0x00 // mov edi, 0 - LONG $0xffd78040 // adc dil, -1 - WORD $0x3040; BYTE $0xc7 // xor dil, al + LONG $0x000000b8; BYTE $0x00 // mov eax, 0 + WORD $0xff14 // adc al, -1 + WORD $0xd830 // xor al, bl WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x161c8841 // mov byte [r14 + rdx], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB10_156 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3c148841 // mov byte [r12 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB10_177 LBB10_40: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 + JE LBB10_227 WORD $0xc031 // xor eax, eax WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 - JMP LBB10_199 + JMP LBB10_225 -LBB10_153: +LBB10_174: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB10_154: +LBB10_175: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -50816,7 +52418,7 @@ LBB10_154: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] @@ -50828,25 +52430,25 @@ LBB10_154: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_154 + JNE LBB10_175 -LBB10_150: +LBB10_171: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 + JE LBB10_227 WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - JMP LBB10_152 + JMP LBB10_173 -LBB10_94: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] +LBB10_107: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] -LBB10_95: +LBB10_108: WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b + LONG $0x0e3c3846 // cmp byte [rsi + r9], r15b WORD $0x9d0f; BYTE $0xd3 // setge bl WORD $0xdbf6 // neg bl WORD $0x894c; BYTE $0xcf // mov rdi, r9 @@ -50855,12 +52457,12 @@ LBB10_95: WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x067c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r15b LONG $0x02488d4c // lea r9, [rax + 2] WORD $0x9d0f; BYTE $0xd3 // setge bl WORD $0xdbf6 // neg bl @@ -50870,43 +52472,40 @@ LBB10_95: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3b048841 // mov byte [r11 + rdi], al WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB10_95 + JNE LBB10_108 WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB10_97: - LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b - WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0xd8f6 // neg al - WORD $0x894c; BYTE $0xca // mov rdx, r9 - LONG $0x03eac148 // shr rdx, 3 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - LONG $0x103c8a41 // mov dil, byte [r8 + rdx] - LONG $0x07e18041 // and r9b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xc9 // mov ecx, r9d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - JMP LBB10_80 +LBB10_110: + LONG $0x01c0f641 // test r8b, 1 + JE LBB10_227 + WORD $0x3844; BYTE $0x3e // cmp byte [rsi], r15b + WORD $0x9d0f; BYTE $0xd0 // setge al + WORD $0xd8f6 // neg al + WORD $0x894c; BYTE $0xca // mov rdx, r9 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e18041 // and r9b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + JMP LBB10_112 -LBB10_75: +LBB10_81: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - QUAD $0x000000e024b48b4c // mov r14, qword [rsp + 224] + QUAD $0x00000190249c8b4c // mov r11, qword [rsp + 400] -LBB10_76: +LBB10_82: WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0e1c3846 // cmp byte [rsi + r9], r11b + LONG $0x0e2c3846 // cmp byte [rsi + r9], r13b LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 WORD $0xd380; BYTE $0xff // adc bl, -1 WORD $0x894c; BYTE $0xcf // mov rdi, r9 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 @@ -50914,8 +52513,8 @@ LBB10_76: WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3e148841 // mov byte [r14 + rdi], dl - LONG $0x065c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r11b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x066c3844; BYTE $0x01 // cmp byte [rsi + rax + 1], r13b LONG $0x02488d4c // lea r9, [rax + 2] LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 WORD $0xd380; BYTE $0xff // adc bl, -1 @@ -50925,20 +52524,20 @@ LBB10_76: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3e048841 // mov byte [r14 + rdi], al + LONG $0x3b048841 // mov byte [r11 + rdi], al WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB10_76 + JNE LBB10_82 WORD $0x014c; BYTE $0xce // add rsi, r9 -LBB10_78: +LBB10_84: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 + JE LBB10_227 WORD $0xc031 // xor eax, eax - WORD $0x3844; BYTE $0x1e // cmp byte [rsi], r11b + WORD $0x3844; BYTE $0x2e // cmp byte [rsi], r13b WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 - QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] + QUAD $0x0000019024848b4c // mov r8, qword [rsp + 400] LONG $0x103c8a41 // mov dil, byte [r8 + rdx] LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 @@ -50946,67 +52545,63 @@ LBB10_78: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al + JMP LBB10_113 -LBB10_80: - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x101c8841 // mov byte [r8 + rdx], bl - JMP LBB10_201 - -LBB10_137: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 +LBB10_156: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB10_138: +LBB10_157: WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - LONG $0x000000bf; BYTE $0x00 // mov edi, 0 - LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xda // mov rdx, r11 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b + LONG $0x000000b8; BYTE $0x00 // mov eax, 0 + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x16048841 // mov byte [r14 + rdx], al + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x046e3944 // cmp dword [rsi + 4], r13d LONG $0x08768d48 // lea rsi, [rsi + 8] - LONG $0x000000bf; BYTE $0x00 // mov edi, 0 - LONG $0xffd78040 // adc dil, -1 - WORD $0x3040; BYTE $0xc7 // xor dil, al + LONG $0x000000b8; BYTE $0x00 // mov eax, 0 + WORD $0xff14 // adc al, -1 + WORD $0xd830 // xor al, bl WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x161c8841 // mov byte [r14 + rdx], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB10_138 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3c148841 // mov byte [r12 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB10_157 -LBB10_24: +LBB10_22: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 + JE LBB10_227 WORD $0xc031 // xor eax, eax WORD $0x3944; BYTE $0x2e // cmp dword [rsi], r13d - JMP LBB10_199 + JMP LBB10_225 -LBB10_195: +LBB10_221: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB10_196: +LBB10_222: LONG $0x0e100ff2 // movsd xmm1, qword [rsi] LONG $0xc82e0f66 // ucomisd xmm1, xmm0 LONG $0x000000b8; BYTE $0x00 // mov eax, 0 WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 @@ -51014,7 +52609,7 @@ LBB10_196: WORD $0xe3d2 // shl bl, cl WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x4e100ff2; BYTE $0x08 // movsd xmm1, qword [rsi + 8] LONG $0x10c68348 // add rsi, 16 @@ -51027,84 +52622,84 @@ LBB10_196: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_196 + JNE LBB10_222 -LBB10_197: +LBB10_223: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 + JE LBB10_227 LONG $0x0e100ff2 // movsd xmm1, qword [rsi] WORD $0xc031 // xor eax, eax LONG $0xc82e0f66 // ucomisd xmm1, xmm0 - JMP LBB10_199 + JMP LBB10_225 -LBB10_112: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 +LBB10_129: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB10_113: +LBB10_130: LONG $0x2e394466 // cmp word [rsi], r13w - LONG $0x000000bf; BYTE $0x00 // mov edi, 0 - LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xda // mov rdx, r11 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x14b60f45; BYTE $0x16 // movzx r10d, byte [r14 + rdx] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b + LONG $0x000000b8; BYTE $0x00 // mov eax, 0 + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xdf // mov rdi, r11 + LONG $0x03efc148 // shr rdi, 3 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x16048841 // mov byte [r14 + rdx], al + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0xc320 // and bl, al + WORD $0x3044; BYTE $0xcb // xor bl, r9b + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x6e394466; BYTE $0x02 // cmp word [rsi + 2], r13w LONG $0x04768d48 // lea rsi, [rsi + 4] - LONG $0x000000bf; BYTE $0x00 // mov edi, 0 - LONG $0xffd78040 // adc dil, -1 - WORD $0x3040; BYTE $0xc7 // xor dil, al + LONG $0x000000b8; BYTE $0x00 // mov eax, 0 + WORD $0xff14 // adc al, -1 + WORD $0xd830 // xor al, bl WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x2040; BYTE $0xfb // and bl, dil - WORD $0xc330 // xor bl, al - LONG $0x161c8841 // mov byte [r14 + rdx], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB10_113 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0xc220 // and dl, al + WORD $0xda30 // xor dl, bl + LONG $0x3c148841 // mov byte [r12 + rdi], dl + WORD $0x394d; BYTE $0xda // cmp r10, r11 + JNE LBB10_130 -LBB10_110: +LBB10_127: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 + JE LBB10_227 WORD $0xc031 // xor eax, eax LONG $0x2e394466 // cmp word [rsi], r13w -LBB10_199: +LBB10_225: WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x16348a41 // mov sil, byte [r14 + rdx] + LONG $0x14348a41 // mov sil, byte [r12 + rdx] LONG $0x07e38041 // and r11b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - JMP LBB10_200 + JMP LBB10_226 -LBB10_170: +LBB10_193: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB10_171: +LBB10_194: WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xdf // mov rdi, r11 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -51112,7 +52707,7 @@ LBB10_171: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3e1c8841 // mov byte [r14 + rdi], bl + LONG $0x3c1c8841 // mov byte [r12 + rdi], bl LONG $0x02c38349 // add r11, 2 LONG $0x086e394c // cmp qword [rsi + 8], r13 LONG $0x10768d48 // lea rsi, [rsi + 16] @@ -51124,21 +52719,21 @@ LBB10_171: WORD $0xe2d2 // shl dl, cl WORD $0xc220 // and dl, al WORD $0xda30 // xor dl, bl - LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x3c148841 // mov byte [r12 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB10_171 + JNE LBB10_194 -LBB10_168: +LBB10_191: LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 + JE LBB10_227 WORD $0x394c; BYTE $0x2e // cmp qword [rsi], r13 -LBB10_152: +LBB10_173: WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x894c; BYTE $0xda // mov rdx, r11 LONG $0x03eac148 // shr rdx, 3 - LONG $0x16348a41 // mov sil, byte [r14 + rdx] + LONG $0x14348a41 // mov sil, byte [r12 + rdx] LONG $0x07e38041 // and r11b, 7 WORD $0x01b3 // mov bl, 1 WORD $0x8944; BYTE $0xd9 // mov ecx, r11d @@ -51146,27 +52741,24 @@ LBB10_152: WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al -LBB10_200: +LBB10_226: WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x161c8841 // mov byte [r14 + rdx], bl - -LBB10_201: - MOVQ 496(SP), SP - RET + LONG $0x141c8841 // mov byte [r12 + rdx], bl + JMP LBB10_227 -LBB10_135: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - QUAD $0x0000018824b48b44 // mov r14d, dword [rsp + 392] +LBB10_154: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0xf631 // xor esi, esi + LONG $0x24748b4c; BYTE $0x08 // mov r14, qword [rsp + 8] -LBB10_136: - LONG $0x33394566 // cmp word [r11], r14w +LBB10_155: + LONG $0x3b394566 // cmp word [r11], r15w WORD $0x9d0f; BYTE $0xd3 // setge bl WORD $0xdbf6 // neg bl WORD $0x8948; BYTE $0xf7 // mov rdi, rsi LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0xf189 // mov ecx, esi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 @@ -51174,9 +52766,9 @@ LBB10_136: WORD $0x3044; BYTE $0xcb // xor bl, r9b WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3c148841 // mov byte [r12 + rdi], dl + LONG $0x3e148841 // mov byte [r14 + rdi], dl LONG $0x02c68348 // add rsi, 2 - LONG $0x73394566; BYTE $0x02 // cmp word [r11 + 2], r14w + LONG $0x7b394566; BYTE $0x02 // cmp word [r11 + 2], r15w LONG $0x045b8d4d // lea r11, [r11 + 4] WORD $0x9d0f; BYTE $0xd3 // setge bl WORD $0xdbf6 // neg bl @@ -51186,388 +52778,1406 @@ LBB10_136: WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x3e048841 // mov byte [r14 + rdi], al WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB10_136 + JNE LBB10_155 -LBB10_133: - LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 - LONG $0x8824848b; WORD $0x0001; BYTE $0x00 // mov eax, dword [rsp + 392] - LONG $0x03394166 // cmp word [r11], ax - WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x143c8a41 // mov dil, byte [r12 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x141c8841 // mov byte [r12 + rdx], bl - JMP LBB10_201 +LBB10_152: + LONG $0x01c0f641 // test r8b, 1 + JE LBB10_227 + LONG $0x3b394566 // cmp word [r11], r15w + WORD $0x9d0f; BYTE $0xd0 // setge al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + LONG $0x03eac148 // shr rdx, 3 + LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] + LONG $0x103c8a41 // mov dil, byte [r8 + rdx] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi -LBB10_193: +LBB10_112: + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + +LBB10_113: + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x101c8841 // mov byte [r8 + rdx], bl + JMP LBB10_227 + +LBB10_218: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi - WORD $0x894d; BYTE $0xfb // mov r11, r15 + WORD $0x3145; BYTE $0xff // xor r15d, r15d + WORD $0x894d; BYTE $0xde // mov r14, r11 + WORD $0x8948; BYTE $0xce // mov rsi, rcx -LBB10_194: - LONG $0x00100ff3 // movss xmm0, dword [rax] - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 +LBB10_219: + LONG $0x0e100ff3 // movss xmm1, dword [rsi] + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 WORD $0xd380; BYTE $0xff // adc bl, -1 - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + WORD $0x894c; BYTE $0xff // mov rdi, r15 LONG $0x03efc148 // shr rdi, 3 - LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + LONG $0x0cb60f45; BYTE $0x3e // movzx r9d, byte [r14 + rdi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - WORD $0xf189 // mov ecx, esi + WORD $0x8944; BYTE $0xf9 // mov ecx, r15d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b2 // mov dl, 1 WORD $0xe2d2 // shl dl, cl WORD $0xda20 // and dl, bl WORD $0x3044; BYTE $0xca // xor dl, r9b - LONG $0x3b148841 // mov byte [r11 + rdi], dl - LONG $0x02c68348 // add rsi, 2 - LONG $0x40100ff3; BYTE $0x04 // movss xmm0, dword [rax + 4] - LONG $0x08c08348 // add rax, 8 - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 + LONG $0x3e148841 // mov byte [r14 + rdi], dl + LONG $0x02c78349 // add r15, 2 + LONG $0x4e100ff3; BYTE $0x04 // movss xmm1, dword [rsi + 4] + LONG $0x08c68348 // add rsi, 8 + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 WORD $0xd380; BYTE $0xff // adc bl, -1 WORD $0xd330 // xor bl, dl WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x8949; BYTE $0xc1 // mov r9, rax WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0xd820 // and al, bl WORD $0xd030 // xor al, dl - LONG $0x3b048841 // mov byte [r11 + rdi], al - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB10_194 + LONG $0x3e048841 // mov byte [r14 + rdi], al + WORD $0x394d; BYTE $0xfa // cmp r10, r15 + JNE LBB10_219 + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + +LBB10_216: + LONG $0x01c0f641 // test r8b, 1 + JE LBB10_227 + LONG $0x09100ff3 // movss xmm1, dword [rcx] + WORD $0xc031 // xor eax, eax + WORD $0x2e0f; BYTE $0xc8 // ucomiss xmm1, xmm0 + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x133c8a41 // mov dil, byte [r11 + rdx] + LONG $0x07e78041 // and r15b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xf9 // mov ecx, r15d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf8 // xor al, dil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xfb // xor bl, dil + LONG $0x131c8841 // mov byte [r11 + rdx], bl + +LBB10_227: + MOVQ 480(SP), SP + RET + +LBB10_143: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8949; BYTE $0xcb // mov r11, rcx + LONG $0x06e3c149 // shl r11, 6 + WORD $0x0149; BYTE $0xf3 // add r11, rsi + QUAD $0x00000178248c8948 // mov qword [rsp + 376], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax + LONG $0x6e0f4166; BYTE $0xc7 // movd xmm0, r15d + LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 + LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 + QUAD $0x0001c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 448], xmm0 + WORD $0x3145; BYTE $0xd2 // xor r10d, r10d + +LBB10_144: + WORD $0x894d; BYTE $0xd0 // mov r8, r10 + LONG $0x06e0c149 // shl r8, 6 + WORD $0x894d; BYTE $0xc1 // mov r9, r8 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 + WORD $0x894c; BYTE $0xc7 // mov rdi, r8 + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + WORD $0x894d; BYTE $0xc4 // mov r12, r8 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 + LONG $0x0cb70f42; BYTE $0x06 // movzx ecx, word [rsi + r8] + LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx + LONG $0x4cb70f42; WORD $0x0206 // movzx ecx, word [rsi + r8 + 2] + LONG $0xc16e0f66 // movd xmm0, ecx + LONG $0x447f0f66; WORD $0x2024 // movdqa oword [rsp + 32], xmm0 + LONG $0x4cb70f42; WORD $0x0406 // movzx ecx, word [rsi + r8 + 4] + LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx + LONG $0x4cb70f42; WORD $0x0606 // movzx ecx, word [rsi + r8 + 6] + LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx + LONG $0x4cb70f42; WORD $0x0806 // movzx ecx, word [rsi + r8 + 8] + LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx + LONG $0x4cb70f42; WORD $0x0a06 // movzx ecx, word [rsi + r8 + 10] + LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx + LONG $0x4cb70f42; WORD $0x0c06 // movzx ecx, word [rsi + r8 + 12] + LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx + LONG $0x4cb70f42; WORD $0x0e06 // movzx ecx, word [rsi + r8 + 14] + LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx + LONG $0x4cb70f42; WORD $0x1006 // movzx ecx, word [rsi + r8 + 16] + LONG $0xc96e0f66 // movd xmm1, ecx + LONG $0x4cb70f42; WORD $0x1206 // movzx ecx, word [rsi + r8 + 18] + LONG $0xd16e0f66 // movd xmm2, ecx + LONG $0x4cb70f42; WORD $0x1406 // movzx ecx, word [rsi + r8 + 20] + LONG $0xd96e0f66 // movd xmm3, ecx + LONG $0x4cb70f42; WORD $0x1606 // movzx ecx, word [rsi + r8 + 22] + LONG $0xe16e0f66 // movd xmm4, ecx + LONG $0x4cb70f42; WORD $0x1806 // movzx ecx, word [rsi + r8 + 24] + LONG $0xe96e0f66 // movd xmm5, ecx + LONG $0x4cb70f42; WORD $0x1a06 // movzx ecx, word [rsi + r8 + 26] + LONG $0xf16e0f66 // movd xmm6, ecx + LONG $0x54b70f42; WORD $0x1c06 // movzx edx, word [rsi + r8 + 28] + LONG $0x74b70f46; WORD $0x1e06 // movzx r14d, word [rsi + r8 + 30] + WORD $0x894c; BYTE $0xc1 // mov rcx, r8 + LONG $0x40c98348 // or rcx, 64 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + LONG $0xc0cb8148; WORD $0x0000; BYTE $0x00 // or rbx, 192 + LONG $0x00cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 256 + LONG $0x01400d48; WORD $0x0000 // or rax, 320 + LONG $0x80cc8149; WORD $0x0001; BYTE $0x00 // or r12, 384 + LONG $0xc0cd8149; WORD $0x0001; BYTE $0x00 // or r13, 448 + LONG $0xc40f4466; WORD $0x0e1c; BYTE $0x01 // pinsrw xmm11, word [rsi + rcx], 1 + LONG $0xc40f4666; WORD $0x0e1c; BYTE $0x02 // pinsrw xmm11, word [rsi + r9], 2 + LONG $0xc40f4466; WORD $0x1e1c; BYTE $0x03 // pinsrw xmm11, word [rsi + rbx], 3 + LONG $0xc40f4466; WORD $0x3e1c; BYTE $0x04 // pinsrw xmm11, word [rsi + rdi], 4 + LONG $0xc40f4466; WORD $0x061c; BYTE $0x05 // pinsrw xmm11, word [rsi + rax], 5 + LONG $0xc40f4666; WORD $0x261c; BYTE $0x06 // pinsrw xmm11, word [rsi + r12], 6 + LONG $0xc40f4666; WORD $0x2e1c; BYTE $0x07 // pinsrw xmm11, word [rsi + r13], 7 + LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx + QUAD $0x0001c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 448] + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 + LONG $0x7c7f0f66; WORD $0x1024 // movdqa oword [rsp + 16], xmm7 + LONG $0x7c6f0f66; WORD $0x2024 // movdqa xmm7, oword [rsp + 32] + LONG $0x7cc40f66; WORD $0x020e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 2], 1 + QUAD $0x02020e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 2], 2 + LONG $0x7cc40f66; WORD $0x021e; BYTE $0x03 // pinsrw xmm7, word [rsi + rbx + 2], 3 + LONG $0x7cc40f66; WORD $0x023e; BYTE $0x04 // pinsrw xmm7, word [rsi + rdi + 2], 4 + LONG $0x7cc40f66; WORD $0x0206; BYTE $0x05 // pinsrw xmm7, word [rsi + rax + 2], 5 + QUAD $0x0602267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 2], 6 + QUAD $0x07022e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 2], 7 + LONG $0x6f0f4466; BYTE $0xd8 // movdqa xmm11, xmm0 + QUAD $0x01040e4cc40f4466 // pinsrw xmm9, word [rsi + rcx + 4], 1 + QUAD $0x02040e4cc40f4666 // pinsrw xmm9, word [rsi + r9 + 4], 2 + QUAD $0x03041e4cc40f4466 // pinsrw xmm9, word [rsi + rbx + 4], 3 + QUAD $0x04043e4cc40f4466 // pinsrw xmm9, word [rsi + rdi + 4], 4 + QUAD $0x0504064cc40f4466 // pinsrw xmm9, word [rsi + rax + 4], 5 + QUAD $0x0604264cc40f4666 // pinsrw xmm9, word [rsi + r12 + 4], 6 + LONG $0x650f4466; BYTE $0xdf // pcmpgtw xmm11, xmm7 + QUAD $0x07042e4cc40f4666 // pinsrw xmm9, word [rsi + r13 + 4], 7 + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + LONG $0x650f4166; BYTE $0xf9 // pcmpgtw xmm7, xmm9 + LONG $0x7c7f0f66; WORD $0x6024 // movdqa oword [rsp + 96], xmm7 + QUAD $0x01060e54c40f4466 // pinsrw xmm10, word [rsi + rcx + 6], 1 + QUAD $0x02060e54c40f4666 // pinsrw xmm10, word [rsi + r9 + 6], 2 + QUAD $0x03061e54c40f4466 // pinsrw xmm10, word [rsi + rbx + 6], 3 + QUAD $0x04063e54c40f4466 // pinsrw xmm10, word [rsi + rdi + 6], 4 + QUAD $0x05060654c40f4466 // pinsrw xmm10, word [rsi + rax + 6], 5 + QUAD $0x06062654c40f4666 // pinsrw xmm10, word [rsi + r12 + 6], 6 + QUAD $0x07062e54c40f4666 // pinsrw xmm10, word [rsi + r13 + 6], 7 + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + QUAD $0x01080e64c40f4466 // pinsrw xmm12, word [rsi + rcx + 8], 1 + QUAD $0x02080e64c40f4666 // pinsrw xmm12, word [rsi + r9 + 8], 2 + QUAD $0x03081e64c40f4466 // pinsrw xmm12, word [rsi + rbx + 8], 3 + QUAD $0x04083e64c40f4466 // pinsrw xmm12, word [rsi + rdi + 8], 4 + QUAD $0x05080664c40f4466 // pinsrw xmm12, word [rsi + rax + 8], 5 + QUAD $0x06082664c40f4666 // pinsrw xmm12, word [rsi + r12 + 8], 6 + QUAD $0x07082e64c40f4666 // pinsrw xmm12, word [rsi + r13 + 8], 7 + LONG $0x650f4166; BYTE $0xfa // pcmpgtw xmm7, xmm10 + QUAD $0x00009024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm7 + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + LONG $0x650f4166; BYTE $0xfc // pcmpgtw xmm7, xmm12 + LONG $0x7c7f0f66; WORD $0x3024 // movdqa oword [rsp + 48], xmm7 + QUAD $0x010a0e6cc40f4466 // pinsrw xmm13, word [rsi + rcx + 10], 1 + QUAD $0x020a0e6cc40f4666 // pinsrw xmm13, word [rsi + r9 + 10], 2 + QUAD $0x030a1e6cc40f4466 // pinsrw xmm13, word [rsi + rbx + 10], 3 + QUAD $0x040a3e6cc40f4466 // pinsrw xmm13, word [rsi + rdi + 10], 4 + QUAD $0x050a066cc40f4466 // pinsrw xmm13, word [rsi + rax + 10], 5 + QUAD $0x060a266cc40f4666 // pinsrw xmm13, word [rsi + r12 + 10], 6 + QUAD $0x070a2e6cc40f4666 // pinsrw xmm13, word [rsi + r13 + 10], 7 + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + QUAD $0x010c0e74c40f4466 // pinsrw xmm14, word [rsi + rcx + 12], 1 + QUAD $0x020c0e74c40f4666 // pinsrw xmm14, word [rsi + r9 + 12], 2 + QUAD $0x030c1e74c40f4466 // pinsrw xmm14, word [rsi + rbx + 12], 3 + QUAD $0x040c3e74c40f4466 // pinsrw xmm14, word [rsi + rdi + 12], 4 + QUAD $0x050c0674c40f4466 // pinsrw xmm14, word [rsi + rax + 12], 5 + QUAD $0x060c2674c40f4666 // pinsrw xmm14, word [rsi + r12 + 12], 6 + LONG $0x650f4166; BYTE $0xfd // pcmpgtw xmm7, xmm13 + QUAD $0x00008024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 128], xmm7 + QUAD $0x070c2e74c40f4666 // pinsrw xmm14, word [rsi + r13 + 12], 7 + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + LONG $0x650f4166; BYTE $0xfe // pcmpgtw xmm7, xmm14 + LONG $0x6f0f4466; BYTE $0xf7 // movdqa xmm14, xmm7 + QUAD $0x010e0e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 14], 1 + QUAD $0x020e0e44c40f4666 // pinsrw xmm8, word [rsi + r9 + 14], 2 + QUAD $0x030e1e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 14], 3 + QUAD $0x040e3e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 14], 4 + QUAD $0x050e0644c40f4466 // pinsrw xmm8, word [rsi + rax + 14], 5 + QUAD $0x060e2644c40f4666 // pinsrw xmm8, word [rsi + r12 + 14], 6 + QUAD $0x070e2e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 14], 7 + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + LONG $0x4cc40f66; WORD $0x100e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 16], 1 + QUAD $0x02100e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 16], 2 + LONG $0x4cc40f66; WORD $0x101e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 16], 3 + LONG $0x4cc40f66; WORD $0x103e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 16], 4 + LONG $0x4cc40f66; WORD $0x1006; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 16], 5 + QUAD $0x0610264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 16], 6 + QUAD $0x07102e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 16], 7 + LONG $0x650f4166; BYTE $0xf8 // pcmpgtw xmm7, xmm8 + LONG $0x7c7f0f66; WORD $0x7024 // movdqa oword [rsp + 112], xmm7 + LONG $0xf86f0f66 // movdqa xmm7, xmm0 + LONG $0xf9650f66 // pcmpgtw xmm7, xmm1 + QUAD $0x0001a024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 416], xmm7 + LONG $0x54c40f66; WORD $0x120e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 18], 1 + QUAD $0x02120e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 18], 2 + LONG $0x54c40f66; WORD $0x121e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 18], 3 + LONG $0x54c40f66; WORD $0x123e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 18], 4 + LONG $0x54c40f66; WORD $0x1206; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 18], 5 + QUAD $0x06122654c40f4266 // pinsrw xmm2, word [rsi + r12 + 18], 6 + QUAD $0x07122e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 18], 7 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0x5cc40f66; WORD $0x140e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 20], 1 + QUAD $0x02140e5cc40f4266 // pinsrw xmm3, word [rsi + r9 + 20], 2 + LONG $0x5cc40f66; WORD $0x141e; BYTE $0x03 // pinsrw xmm3, word [rsi + rbx + 20], 3 + LONG $0x5cc40f66; WORD $0x143e; BYTE $0x04 // pinsrw xmm3, word [rsi + rdi + 20], 4 + LONG $0x5cc40f66; WORD $0x1406; BYTE $0x05 // pinsrw xmm3, word [rsi + rax + 20], 5 + QUAD $0x0614265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 20], 6 + LONG $0xca650f66 // pcmpgtw xmm1, xmm2 + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 + QUAD $0x07142e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 20], 7 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xcb650f66 // pcmpgtw xmm1, xmm3 + LONG $0x4c7f0f66; WORD $0x5024 // movdqa oword [rsp + 80], xmm1 + LONG $0x64c40f66; WORD $0x160e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 22], 1 + QUAD $0x02160e64c40f4266 // pinsrw xmm4, word [rsi + r9 + 22], 2 + LONG $0x64c40f66; WORD $0x161e; BYTE $0x03 // pinsrw xmm4, word [rsi + rbx + 22], 3 + LONG $0x64c40f66; WORD $0x163e; BYTE $0x04 // pinsrw xmm4, word [rsi + rdi + 22], 4 + LONG $0x64c40f66; WORD $0x1606; BYTE $0x05 // pinsrw xmm4, word [rsi + rax + 22], 5 + QUAD $0x06162664c40f4266 // pinsrw xmm4, word [rsi + r12 + 22], 6 + QUAD $0x07162e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 22], 7 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0x6cc40f66; WORD $0x180e; BYTE $0x01 // pinsrw xmm5, word [rsi + rcx + 24], 1 + QUAD $0x02180e6cc40f4266 // pinsrw xmm5, word [rsi + r9 + 24], 2 + LONG $0x6cc40f66; WORD $0x181e; BYTE $0x03 // pinsrw xmm5, word [rsi + rbx + 24], 3 + LONG $0x6cc40f66; WORD $0x183e; BYTE $0x04 // pinsrw xmm5, word [rsi + rdi + 24], 4 + LONG $0x6cc40f66; WORD $0x1806; BYTE $0x05 // pinsrw xmm5, word [rsi + rax + 24], 5 + QUAD $0x0618266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 24], 6 + QUAD $0x07182e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 24], 7 + LONG $0xcc650f66 // pcmpgtw xmm1, xmm4 + QUAD $0x0000a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm1 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xcd650f66 // pcmpgtw xmm1, xmm5 + LONG $0x4c7f0f66; WORD $0x2024 // movdqa oword [rsp + 32], xmm1 + LONG $0x74c40f66; WORD $0x1a0e; BYTE $0x01 // pinsrw xmm6, word [rsi + rcx + 26], 1 + QUAD $0x021a0e74c40f4266 // pinsrw xmm6, word [rsi + r9 + 26], 2 + LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x03 // pinsrw xmm6, word [rsi + rbx + 26], 3 + LONG $0x74c40f66; WORD $0x1a3e; BYTE $0x04 // pinsrw xmm6, word [rsi + rdi + 26], 4 + LONG $0x74c40f66; WORD $0x1a06; BYTE $0x05 // pinsrw xmm6, word [rsi + rax + 26], 5 + QUAD $0x061a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 26], 6 + QUAD $0x071a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 26], 7 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + QUAD $0x011c0e7cc40f4466 // pinsrw xmm15, word [rsi + rcx + 28], 1 + QUAD $0x021c0e7cc40f4666 // pinsrw xmm15, word [rsi + r9 + 28], 2 + QUAD $0x031c1e7cc40f4466 // pinsrw xmm15, word [rsi + rbx + 28], 3 + QUAD $0x041c3e7cc40f4466 // pinsrw xmm15, word [rsi + rdi + 28], 4 + QUAD $0x051c067cc40f4466 // pinsrw xmm15, word [rsi + rax + 28], 5 + QUAD $0x061c267cc40f4666 // pinsrw xmm15, word [rsi + r12 + 28], 6 + LONG $0xce650f66 // pcmpgtw xmm1, xmm6 + QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 + QUAD $0x071c2e7cc40f4666 // pinsrw xmm15, word [rsi + r13 + 28], 7 + LONG $0x6e0f4166; BYTE $0xce // movd xmm1, r14d + LONG $0x4cc40f66; WORD $0x1e0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 30], 1 + QUAD $0x021e0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 30], 2 + LONG $0x4cc40f66; WORD $0x1e1e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 30], 3 + LONG $0x4cc40f66; WORD $0x1e3e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 30], 4 + LONG $0x4cc40f66; WORD $0x1e06; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 30], 5 + QUAD $0x061e264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 30], 6 + LONG $0xd06f0f66 // movdqa xmm2, xmm0 + LONG $0x650f4166; BYTE $0xd7 // pcmpgtw xmm2, xmm15 + QUAD $0x0000e024947f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm2 + QUAD $0x071e2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 30], 7 + LONG $0xd06f0f66 // movdqa xmm2, xmm0 + LONG $0xd1650f66 // pcmpgtw xmm2, xmm1 + QUAD $0x0000b024947f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm2 + LONG $0x54b70f42; WORD $0x2006 // movzx edx, word [rsi + r8 + 32] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x4cc40f66; WORD $0x200e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 32], 1 + QUAD $0x02200e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 32], 2 + LONG $0x4cc40f66; WORD $0x201e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 32], 3 + LONG $0x4cc40f66; WORD $0x203e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 32], 4 + LONG $0x4cc40f66; WORD $0x2006; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 32], 5 + QUAD $0x0620264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 32], 6 + QUAD $0x07202e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 32], 7 + LONG $0x54b70f42; WORD $0x2206 // movzx edx, word [rsi + r8 + 34] + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x220e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 34], 1 + QUAD $0x02220e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 34], 2 + LONG $0x54c40f66; WORD $0x221e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 34], 3 + LONG $0x54c40f66; WORD $0x223e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 34], 4 + LONG $0x54c40f66; WORD $0x2206; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 34], 5 + QUAD $0x06222654c40f4266 // pinsrw xmm2, word [rsi + r12 + 34], 6 + QUAD $0x07222e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 34], 7 + LONG $0xd86f0f66 // movdqa xmm3, xmm0 + LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 + QUAD $0x000110249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm3 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xca650f66 // pcmpgtw xmm1, xmm2 + QUAD $0x000100248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm1 + LONG $0x54b70f42; WORD $0x2406 // movzx edx, word [rsi + r8 + 36] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x4cc40f66; WORD $0x240e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 36], 1 + QUAD $0x02240e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 36], 2 + LONG $0x4cc40f66; WORD $0x241e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 36], 3 + LONG $0x4cc40f66; WORD $0x243e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 36], 4 + LONG $0x4cc40f66; WORD $0x2406; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 36], 5 + QUAD $0x0624264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 36], 6 + LONG $0x54b70f42; WORD $0x2606 // movzx edx, word [rsi + r8 + 38] + QUAD $0x07242e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 36], 7 + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x260e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 38], 1 + QUAD $0x02260e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 38], 2 + LONG $0x54c40f66; WORD $0x261e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 38], 3 + LONG $0x54c40f66; WORD $0x263e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 38], 4 + LONG $0x54c40f66; WORD $0x2606; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 38], 5 + QUAD $0x06262654c40f4266 // pinsrw xmm2, word [rsi + r12 + 38], 6 + LONG $0xd86f0f66 // movdqa xmm3, xmm0 + LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 + QUAD $0x000150249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 336], xmm3 + QUAD $0x07262e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 38], 7 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xca650f66 // pcmpgtw xmm1, xmm2 + QUAD $0x000120248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm1 + LONG $0x54b70f42; WORD $0x2806 // movzx edx, word [rsi + r8 + 40] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x4cc40f66; WORD $0x280e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 40], 1 + QUAD $0x02280e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 40], 2 + LONG $0x4cc40f66; WORD $0x281e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 40], 3 + LONG $0x4cc40f66; WORD $0x283e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 40], 4 + LONG $0x4cc40f66; WORD $0x2806; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 40], 5 + QUAD $0x0628264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 40], 6 + QUAD $0x07282e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 40], 7 + LONG $0x54b70f42; WORD $0x2a06 // movzx edx, word [rsi + r8 + 42] + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x2a0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 42], 1 + QUAD $0x022a0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 42], 2 + LONG $0x54c40f66; WORD $0x2a1e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 42], 3 + LONG $0x54c40f66; WORD $0x2a3e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 42], 4 + LONG $0x54c40f66; WORD $0x2a06; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 42], 5 + QUAD $0x062a2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 42], 6 + QUAD $0x072a2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 42], 7 + LONG $0xd86f0f66 // movdqa xmm3, xmm0 + LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 + QUAD $0x0000f0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm3 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xca650f66 // pcmpgtw xmm1, xmm2 + QUAD $0x000140248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 320], xmm1 + LONG $0x54b70f42; WORD $0x2c06 // movzx edx, word [rsi + r8 + 44] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x4cc40f66; WORD $0x2c0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 44], 1 + QUAD $0x022c0e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 44], 2 + LONG $0x4cc40f66; WORD $0x2c1e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 44], 3 + LONG $0x4cc40f66; WORD $0x2c3e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 44], 4 + LONG $0x4cc40f66; WORD $0x2c06; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 44], 5 + QUAD $0x062c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 44], 6 + LONG $0x54b70f42; WORD $0x2e06 // movzx edx, word [rsi + r8 + 46] + QUAD $0x072c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 44], 7 + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x2e0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 46], 1 + QUAD $0x022e0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 46], 2 + LONG $0x54c40f66; WORD $0x2e1e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 46], 3 + LONG $0x54c40f66; WORD $0x2e3e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 46], 4 + LONG $0x54c40f66; WORD $0x2e06; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 46], 5 + QUAD $0x062e2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 46], 6 + LONG $0xd86f0f66 // movdqa xmm3, xmm0 + LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 + QUAD $0x000160249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 352], xmm3 + QUAD $0x072e2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 46], 7 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xca650f66 // pcmpgtw xmm1, xmm2 + QUAD $0x000130248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm1 + LONG $0x54b70f42; WORD $0x3006 // movzx edx, word [rsi + r8 + 48] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x4cc40f66; WORD $0x300e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 48], 1 + QUAD $0x02300e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 48], 2 + LONG $0x4cc40f66; WORD $0x301e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 48], 3 + LONG $0x4cc40f66; WORD $0x303e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 48], 4 + LONG $0x4cc40f66; WORD $0x3006; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 48], 5 + QUAD $0x0630264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 48], 6 + QUAD $0x07302e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 48], 7 + LONG $0x54b70f42; WORD $0x3206 // movzx edx, word [rsi + r8 + 50] + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x320e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 50], 1 + QUAD $0x02320e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 50], 2 + LONG $0x54c40f66; WORD $0x321e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 50], 3 + LONG $0x54c40f66; WORD $0x323e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 50], 4 + LONG $0x54c40f66; WORD $0x3206; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 50], 5 + QUAD $0x06322654c40f4266 // pinsrw xmm2, word [rsi + r12 + 50], 6 + QUAD $0x07322e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 50], 7 + LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 + LONG $0x650f4466; BYTE $0xe9 // pcmpgtw xmm13, xmm1 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xca650f66 // pcmpgtw xmm1, xmm2 + QUAD $0x000180248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 384], xmm1 + LONG $0x54b70f42; WORD $0x3406 // movzx edx, word [rsi + r8 + 52] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x4cc40f66; WORD $0x340e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 52], 1 + QUAD $0x02340e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 52], 2 + LONG $0x4cc40f66; WORD $0x341e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 52], 3 + LONG $0x4cc40f66; WORD $0x343e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 52], 4 + LONG $0x4cc40f66; WORD $0x3406; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 52], 5 + QUAD $0x0634264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 52], 6 + LONG $0x54b70f42; WORD $0x3606 // movzx edx, word [rsi + r8 + 54] + QUAD $0x07342e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 52], 7 + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x360e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 54], 1 + QUAD $0x02360e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 54], 2 + LONG $0x54c40f66; WORD $0x361e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 54], 3 + LONG $0x54c40f66; WORD $0x363e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 54], 4 + LONG $0x54c40f66; WORD $0x3606; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 54], 5 + QUAD $0x06362654c40f4266 // pinsrw xmm2, word [rsi + r12 + 54], 6 + LONG $0xd86f0f66 // movdqa xmm3, xmm0 + LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 + QUAD $0x000190249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 400], xmm3 + QUAD $0x07362e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 54], 7 + LONG $0x6f0f4466; BYTE $0xf8 // movdqa xmm15, xmm0 + LONG $0x650f4466; BYTE $0xfa // pcmpgtw xmm15, xmm2 + LONG $0x54b70f42; WORD $0x3806 // movzx edx, word [rsi + r8 + 56] + LONG $0xca6e0f66 // movd xmm1, edx + LONG $0x4cc40f66; WORD $0x380e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 56], 1 + QUAD $0x02380e4cc40f4266 // pinsrw xmm1, word [rsi + r9 + 56], 2 + LONG $0x4cc40f66; WORD $0x381e; BYTE $0x03 // pinsrw xmm1, word [rsi + rbx + 56], 3 + LONG $0x4cc40f66; WORD $0x383e; BYTE $0x04 // pinsrw xmm1, word [rsi + rdi + 56], 4 + LONG $0x4cc40f66; WORD $0x3806; BYTE $0x05 // pinsrw xmm1, word [rsi + rax + 56], 5 + QUAD $0x0638264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 56], 6 + QUAD $0x07382e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 56], 7 + LONG $0x54b70f42; WORD $0x3a06 // movzx edx, word [rsi + r8 + 58] + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x3a0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 58], 1 + QUAD $0x023a0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 58], 2 + LONG $0x54c40f66; WORD $0x3a1e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 58], 3 + LONG $0x54c40f66; WORD $0x3a3e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 58], 4 + LONG $0x54c40f66; WORD $0x3a06; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 58], 5 + QUAD $0x063a2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 58], 6 + QUAD $0x073a2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 58], 7 + LONG $0x6f0f4466; BYTE $0xc8 // movdqa xmm9, xmm0 + LONG $0x650f4466; BYTE $0xc9 // pcmpgtw xmm9, xmm1 + LONG $0x6f0f4466; BYTE $0xe0 // movdqa xmm12, xmm0 + LONG $0x650f4466; BYTE $0xe2 // pcmpgtw xmm12, xmm2 + LONG $0x54b70f42; WORD $0x3c06 // movzx edx, word [rsi + r8 + 60] + LONG $0xd26e0f66 // movd xmm2, edx + LONG $0x54c40f66; WORD $0x3c0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 60], 1 + QUAD $0x023c0e54c40f4266 // pinsrw xmm2, word [rsi + r9 + 60], 2 + LONG $0x54c40f66; WORD $0x3c1e; BYTE $0x03 // pinsrw xmm2, word [rsi + rbx + 60], 3 + LONG $0x54c40f66; WORD $0x3c3e; BYTE $0x04 // pinsrw xmm2, word [rsi + rdi + 60], 4 + LONG $0x54c40f66; WORD $0x3c06; BYTE $0x05 // pinsrw xmm2, word [rsi + rax + 60], 5 + QUAD $0x063c2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 60], 6 + LONG $0x54b70f42; WORD $0x3e06 // movzx edx, word [rsi + r8 + 62] + QUAD $0x073c2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 60], 7 + LONG $0xfa6e0f66 // movd xmm7, edx + LONG $0x7cc40f66; WORD $0x3e0e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 62], 1 + QUAD $0x023e0e7cc40f4266 // pinsrw xmm7, word [rsi + r9 + 62], 2 + LONG $0x7cc40f66; WORD $0x3e1e; BYTE $0x03 // pinsrw xmm7, word [rsi + rbx + 62], 3 + LONG $0x7cc40f66; WORD $0x3e3e; BYTE $0x04 // pinsrw xmm7, word [rsi + rdi + 62], 4 + LONG $0x7cc40f66; WORD $0x3e06; BYTE $0x05 // pinsrw xmm7, word [rsi + rax + 62], 5 + QUAD $0x063e267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 62], 6 + WORD $0x894d; BYTE $0xfc // mov r12, r15 + LONG $0xe86f0f66 // movdqa xmm5, xmm0 + LONG $0xea650f66 // pcmpgtw xmm5, xmm2 + QUAD $0x073e2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 62], 7 + LONG $0xf06f0f66 // movdqa xmm6, xmm0 + LONG $0xf7650f66 // pcmpgtw xmm6, xmm7 + LONG $0x630f4566; BYTE $0xdb // packsswb xmm11, xmm11 + QUAD $0x000000808d6f0f66 // movdqa xmm1, oword 128[rbp] /* [rip + .LCPI10_8] */ + LONG $0xf96f0f66 // movdqa xmm7, xmm1 + LONG $0xd96f0f66 // movdqa xmm3, xmm1 + LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 + LONG $0xe4ef0f66 // pxor xmm4, xmm4 + LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 + LONG $0x546f0f66; WORD $0x6024 // movdqa xmm2, oword [rsp + 96] + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x000000908d6f0f66 // movdqa xmm1, oword 144[rbp] /* [rip + .LCPI10_9] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + LONG $0xd2760f66 // pcmpeqd xmm2, xmm2 + LONG $0x446f0f66; WORD $0x1024 // movdqa xmm0, oword [rsp + 16] + LONG $0xc2ef0f66 // pxor xmm0, xmm2 + LONG $0x760f4566; BYTE $0xc0 // pcmpeqd xmm8, xmm8 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xf8f80f66 // psubb xmm7, xmm0 + QUAD $0x00009024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 144] + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x0000a09d6f0f4466; BYTE $0x00 // movdqa xmm11, oword 160[rbp] /* [rip + .LCPI10_10] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4466; WORD $0xdc10 // pblendvb xmm11, xmm4, xmm0 + LONG $0xeb0f4466; BYTE $0xd9 // por xmm11, xmm1 + LONG $0x546f0f66; WORD $0x3024 // movdqa xmm2, oword [rsp + 48] + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + LONG $0xeb0f4466; BYTE $0xdf // por xmm11, xmm7 + QUAD $0x00008024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 128] + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x0000c0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 192[rbp] /* [rip + .LCPI10_12] */ + LONG $0x6f0f4166; BYTE $0xfa // movdqa xmm7, xmm10 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 + LONG $0xf9eb0f66 // por xmm7, xmm1 + LONG $0x630f4566; BYTE $0xf6 // packsswb xmm14, xmm14 + QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ + LONG $0x6f0f4166; BYTE $0xc6 // movdqa xmm0, xmm14 + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + LONG $0xcfeb0f66 // por xmm1, xmm7 + LONG $0x546f0f66; WORD $0x7024 // movdqa xmm2, oword [rsp + 112] + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x0000e0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 224[rbp] /* [rip + .LCPI10_14] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4466; WORD $0xf410 // pblendvb xmm14, xmm4, xmm0 + LONG $0xeb0f4166; BYTE $0xcb // por xmm1, xmm11 + QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x6f0f4466; BYTE $0xdb // movdqa xmm11, xmm3 + LONG $0xfb6f0f66 // movdqa xmm7, xmm3 + LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 + LONG $0xeb0f4466; BYTE $0xf1 // por xmm14, xmm1 + QUAD $0x0001a024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 416] + LONG $0xef0f4166; BYTE $0xc0 // pxor xmm0, xmm8 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xf8f80f66 // psubb xmm7, xmm0 + LONG $0x446f0f66; WORD $0x5024 // movdqa xmm0, oword [rsp + 80] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + QUAD $0x000000909d6f0f66 // movdqa xmm3, oword 144[rbp] /* [rip + .LCPI10_9] */ + LONG $0xcb6f0f66 // movdqa xmm1, xmm3 + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + QUAD $0x0000a024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 160] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + QUAD $0x0000a0856f0f4466; BYTE $0x00 // movdqa xmm8, oword 160[rbp] /* [rip + .LCPI10_10] */ + LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 + LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 + LONG $0xd1eb0f66 // por xmm2, xmm1 + LONG $0xd7eb0f66 // por xmm2, xmm7 + LONG $0x446f0f66; WORD $0x2024 // movdqa xmm0, oword [rsp + 32] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + QUAD $0x0000c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 192] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x380f4466; WORD $0xd410 // pblendvb xmm10, xmm4, xmm0 + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + QUAD $0x0000e024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 224] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + LONG $0xeb0f4166; BYTE $0xca // por xmm1, xmm10 + LONG $0xcaeb0f66 // por xmm1, xmm2 + QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + QUAD $0x0000e0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 224[rbp] /* [rip + .LCPI10_14] */ + LONG $0x380f4466; WORD $0xd410 // pblendvb xmm10, xmm4, xmm0 + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + QUAD $0x00010024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 256] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x6f0f4166; BYTE $0xcb // movdqa xmm1, xmm11 + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + QUAD $0x00015024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 336] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xd36f0f66 // movdqa xmm2, xmm3 + LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 + QUAD $0x00011024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 272] + QUAD $0x0000016085ef0f66 // pxor xmm0, oword 352[rbp] /* [rip + .LCPI10_22] */ + LONG $0xdb760f66 // pcmpeqd xmm3, xmm3 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xc8f80f66 // psubb xmm1, xmm0 + QUAD $0x00012024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 288] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 + LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 + LONG $0xfaeb0f66 // por xmm7, xmm2 + QUAD $0x0000f024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 240] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + QUAD $0x0140249c6f0f4466; WORD $0x0000 // movdqa xmm11, oword [rsp + 320] + LONG $0x630f4566; BYTE $0xdb // packsswb xmm11, xmm11 + LONG $0xf9eb0f66 // por xmm7, xmm1 + QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + QUAD $0x000000c0956f0f66 // movdqa xmm2, oword 192[rbp] /* [rip + .LCPI10_12] */ + LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 + LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 + QUAD $0x00016024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 352] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xd1eb0f66 // por xmm2, xmm1 + QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + LONG $0xcaeb0f66 // por xmm1, xmm2 + QUAD $0x00013024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 304] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + QUAD $0x0180249c6f0f4466; WORD $0x0000 // movdqa xmm11, oword [rsp + 384] + LONG $0x630f4566; BYTE $0xdb // packsswb xmm11, xmm11 + LONG $0xcfeb0f66 // por xmm1, xmm7 + QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI10_14] */ + LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 + QUAD $0x00000080956f0f66 // movdqa xmm2, oword 128[rbp] /* [rip + .LCPI10_8] */ + LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 + LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 + LONG $0xf9eb0f66 // por xmm7, xmm1 + LONG $0xef0f4466; BYTE $0xeb // pxor xmm13, xmm3 + LONG $0x630f4566; BYTE $0xed // packsswb xmm13, xmm13 + QUAD $0x00019024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 400] + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x630f4566; BYTE $0xff // packsswb xmm15, xmm15 + LONG $0xf80f4166; BYTE $0xd5 // psubb xmm2, xmm13 + QUAD $0x000000908d6f0f66 // movdqa xmm1, oword 144[rbp] /* [rip + .LCPI10_9] */ + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 + LONG $0x380f4466; WORD $0xc410 // pblendvb xmm8, xmm4, xmm0 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + LONG $0x630f4566; BYTE $0xc9 // packsswb xmm9, xmm9 + LONG $0x630f4566; BYTE $0xe4 // packsswb xmm12, xmm12 + LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 + QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ + LONG $0x6f0f4166; BYTE $0xc1 // movdqa xmm0, xmm9 + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + QUAD $0x000000c0956f0f66 // movdqa xmm2, oword 192[rbp] /* [rip + .LCPI10_12] */ + LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 + LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xd1eb0f66 // por xmm2, xmm1 + QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ + LONG $0xc56f0f66 // movdqa xmm0, xmm5 + LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 + LONG $0xcaeb0f66 // por xmm1, xmm2 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 + QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI10_14] */ + LONG $0xc66f0f66 // movdqa xmm0, xmm6 + LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 + LONG $0xd1eb0f66 // por xmm2, xmm1 + LONG $0x6f0f4166; BYTE $0xc6 // movdqa xmm0, xmm14 + LONG $0x6c0f4166; BYTE $0xc2 // punpcklqdq xmm0, xmm10 + LONG $0xcf6f0f66 // movdqa xmm1, xmm7 + LONG $0xca6c0f66 // punpcklqdq xmm1, xmm2 + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI10_15] */ + LONG $0x00380f66; BYTE $0xcb // pshufb xmm1, xmm3 + LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 + LONG $0xc1610f66 // punpcklwd xmm0, xmm1 + LONG $0xfa600f66 // punpcklbw xmm7, xmm2 + LONG $0x600f4566; BYTE $0xf2 // punpcklbw xmm14, xmm10 + LONG $0x610f4466; BYTE $0xf7 // punpcklwd xmm14, xmm7 + LONG $0x7f0f47f3; WORD $0x9734 // movdqu oword [r15 + 4*r10], xmm14 + LONG $0x7f0f43f3; WORD $0x9744; BYTE $0x10 // movdqu oword [r15 + 4*r10 + 16], xmm0 + LONG $0x08c28349 // add r10, 8 + QUAD $0x0000017824943b4c // cmp r10, qword [rsp + 376] + JNE LBB10_144 + QUAD $0x000001b8248c8b48 // mov rcx, qword [rsp + 440] + QUAD $0x00000178248c3b48 // cmp rcx, qword [rsp + 376] + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + LONG $0x243c8b44 // mov r15d, dword [rsp] + JNE LBB10_146 + JMP LBB10_149 -LBB10_191: - LONG $0x01c0f641 // test r8b, 1 - JE LBB10_201 - LONG $0x00100ff3 // movss xmm0, dword [rax] - WORD $0xc031 // xor eax, eax - LONG $0xc32e0f41 // ucomiss xmm0, xmm11 - WORD $0xff14 // adc al, -1 - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x173c8a41 // mov dil, byte [r15 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x171c8841 // mov byte [r15 + rdx], bl - JMP LBB10_201 +LBB10_207: + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + LONG $0xfce08348 // and rax, -4 + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0x07e1c148 // shl rcx, 7 + WORD $0x0148; BYTE $0xf1 // add rcx, rsi + LONG $0x841c8d4d // lea r11, [r12 + 4*rax] + LONG $0x6f0f4566; BYTE $0xf3 // movdqa xmm14, xmm11 + LONG $0xf3c60f45; BYTE $0x00 // shufps xmm14, xmm11, 0 + LONG $0xfcc68148; WORD $0x0001; BYTE $0x00 // add rsi, 508 + WORD $0xd231 // xor edx, edx + LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI10_0] */ -LBB10_85: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB10_208: + QUAD $0xfffffe049e100ff3 // movss xmm3, dword [rsi - 508] + QUAD $0xfffe0896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 504] + QUAD $0xfffe0c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 500] + QUAD $0xfffffe108e100ff3 // movss xmm1, dword [rsi - 496] + QUAD $0xfffe849e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 380], 16 + QUAD $0xffff049e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 252], 32 + LONG $0x213a0f66; WORD $0x845e; BYTE $0x30 // insertps xmm3, dword [rsi - 124], 48 + QUAD $0xfe8896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 376], 16 + QUAD $0xff0896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 248], 32 + QUAD $0x308856213a0f4466 // insertps xmm10, dword [rsi - 120], 48 + QUAD $0xfe8c8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 372], 16 + QUAD $0xff0c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 244], 32 + QUAD $0x308c4e213a0f4466 // insertps xmm9, dword [rsi - 116], 48 + QUAD $0xfffe908e213a0f66; WORD $0x10ff // insertps xmm1, dword [rsi - 368], 16 + QUAD $0xffff108e213a0f66; WORD $0x20ff // insertps xmm1, dword [rsi - 240], 32 + LONG $0x213a0f66; WORD $0x904e; BYTE $0x30 // insertps xmm1, dword [rsi - 112], 48 + QUAD $0xfffe1486100f44f3; BYTE $0xff // movss xmm8, dword [rsi - 492] + QUAD $0xfe9486213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm8, dword [rsi - 364], 16 + QUAD $0xff1486213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm8, dword [rsi - 236], 32 + LONG $0xe6280f45 // movaps xmm12, xmm14 + QUAD $0x309446213a0f4466 // insertps xmm8, dword [rsi - 108], 48 + QUAD $0xfffffe1896100ff3 // movss xmm2, dword [rsi - 488] + QUAD $0xfffe9896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 360], 16 + QUAD $0xffff1896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 232], 32 + LONG $0xe3c20f44; BYTE $0x02 // cmpleps xmm12, xmm3 + LONG $0x213a0f66; WORD $0x9856; BYTE $0x30 // insertps xmm2, dword [rsi - 104], 48 + QUAD $0xfffffe1c9e100ff3 // movss xmm3, dword [rsi - 484] + QUAD $0xfffe9c9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 356], 16 + QUAD $0xffff1c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 228], 32 + LONG $0x6b0f4566; BYTE $0xe4 // packssdw xmm12, xmm12 + LONG $0x213a0f66; WORD $0x9c5e; BYTE $0x30 // insertps xmm3, dword [rsi - 100], 48 + QUAD $0xfffffe24a6100ff3 // movss xmm4, dword [rsi - 476] + QUAD $0xfffea4a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 348], 16 + QUAD $0xffff24a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 220], 32 + LONG $0x630f4566; BYTE $0xe4 // packsswb xmm12, xmm12 + LONG $0x213a0f66; WORD $0xa466; BYTE $0x30 // insertps xmm4, dword [rsi - 92], 48 + LONG $0xfe280f41 // movaps xmm7, xmm14 + QUAD $0xfffffe44ae100ff3 // movss xmm5, dword [rsi - 444] + QUAD $0xfffec4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 316], 16 + QUAD $0xffff44ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 188], 32 + LONG $0x02fcc20f // cmpleps xmm7, xmm4 + LONG $0x213a0f66; WORD $0xc46e; BYTE $0x30 // insertps xmm5, dword [rsi - 60], 48 + LONG $0xf6280f41 // movaps xmm6, xmm14 + QUAD $0xfffe64ae100f44f3; BYTE $0xff // movss xmm13, dword [rsi - 412] + QUAD $0xfee4ae213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm13, dword [rsi - 284], 16 + QUAD $0xff64ae213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm13, dword [rsi - 156], 32 + LONG $0x02f5c20f // cmpleps xmm6, xmm5 + QUAD $0x30e46e213a0f4466 // insertps xmm13, dword [rsi - 28], 48 + LONG $0xe6280f41 // movaps xmm4, xmm14 + LONG $0xe5c20f41; BYTE $0x02 // cmpleps xmm4, xmm13 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xeac20f41; BYTE $0x02 // cmpleps xmm5, xmm10 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xc56f0f66 // movdqa xmm0, xmm5 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xc5f80f66 // psubb xmm0, xmm5 + QUAD $0xfffe2096100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 480] + QUAD $0xfea096213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 352], 16 + LONG $0xdb0f4566; BYTE $0xe7 // pand xmm12, xmm15 + QUAD $0xff2096213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 224], 32 + LONG $0xeb0f4166; BYTE $0xc4 // por xmm0, xmm12 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xe9c20f41; BYTE $0x02 // cmpleps xmm5, xmm9 + QUAD $0x30a056213a0f4466 // insertps xmm10, dword [rsi - 96], 48 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0x6f0f4466; WORD $0x106d // movdqa xmm13, oword 16[rbp] /* [rip + .LCPI10_1] */ + LONG $0xdb0f4166; BYTE $0xed // pand xmm5, xmm13 + LONG $0xe8eb0f66 // por xmm5, xmm0 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c1c20f // cmpleps xmm0, xmm1 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0xc8c20f41; BYTE $0x02 // cmpleps xmm1, xmm8 + QUAD $0xfffe288e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 472] + QUAD $0xfea88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 344], 16 + QUAD $0xff288e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 216], 32 + QUAD $0x30a84e213a0f4466 // insertps xmm9, dword [rsi - 88], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0x6f0f4466; WORD $0x206d // movdqa xmm13, oword 32[rbp] /* [rip + .LCPI10_2] */ + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0x6f0f4466; WORD $0x306d // movdqa xmm13, oword 48[rbp] /* [rip + .LCPI10_3] */ + LONG $0xdb0f4166; BYTE $0xcd // pand xmm1, xmm13 + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffe2ca6100f44f3; BYTE $0xff // movss xmm12, dword [rsi - 468] + QUAD $0xfeaca6213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm12, dword [rsi - 340], 16 + QUAD $0xff2ca6213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm12, dword [rsi - 212], 32 + QUAD $0x30ac66213a0f4466 // insertps xmm12, dword [rsi - 84], 48 + LONG $0xcdeb0f66 // por xmm1, xmm5 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c2c20f // cmpleps xmm0, xmm2 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0x02ebc20f // cmpleps xmm5, xmm3 + QUAD $0xfffffe3096100ff3 // movss xmm2, dword [rsi - 464] + QUAD $0xfffeb096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 336], 16 + QUAD $0xffff3096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 208], 32 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0x213a0f66; WORD $0xb056; BYTE $0x30 // insertps xmm2, dword [rsi - 80], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 + LONG $0x6f0f4466; WORD $0x406d // movdqa xmm13, oword 64[rbp] /* [rip + .LCPI10_4] */ + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 + LONG $0x5d6f0f66; BYTE $0x50 // movdqa xmm3, oword 80[rbp] /* [rip + .LCPI10_5] */ + LONG $0xebdb0f66 // pand xmm5, xmm3 + LONG $0xe8eb0f66 // por xmm5, xmm0 + LONG $0xc6280f45 // movaps xmm8, xmm14 + LONG $0xc2c20f45; BYTE $0x02 // cmpleps xmm8, xmm10 + QUAD $0xfffffe349e100ff3 // movss xmm3, dword [rsi - 460] + QUAD $0xfffeb49e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 332], 16 + QUAD $0xffff349e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 204], 32 + LONG $0x213a0f66; WORD $0xb45e; BYTE $0x30 // insertps xmm3, dword [rsi - 76], 48 + LONG $0x6b0f4566; BYTE $0xc0 // packssdw xmm8, xmm8 + LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 + LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 + LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI10_6] */ + LONG $0xdb0f4466; BYTE $0xc0 // pand xmm8, xmm0 + LONG $0xeb0f4466; BYTE $0xc5 // por xmm8, xmm5 + QUAD $0xfffe3896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 456] + QUAD $0xfeb896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 328], 16 + QUAD $0xff3896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 200], 32 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x30b856213a0f4466 // insertps xmm10, dword [rsi - 72], 48 + LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0xc1c20f41; BYTE $0x02 // cmpleps xmm0, xmm9 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xc8f80f66 // psubb xmm1, xmm0 + QUAD $0xfffe3c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 452] + QUAD $0xfebc8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 324], 16 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + QUAD $0xff3c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 196], 32 + LONG $0xcfeb0f66 // por xmm1, xmm7 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xecc20f41; BYTE $0x02 // cmpleps xmm5, xmm12 + QUAD $0x30bc4e213a0f4466 // insertps xmm9, dword [rsi - 68], 48 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0x6ddb0f66; BYTE $0x10 // pand xmm5, oword 16[rbp] /* [rip + .LCPI10_1] */ + LONG $0xe9eb0f66 // por xmm5, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c2c20f // cmpleps xmm0, xmm2 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0x02cbc20f // cmpleps xmm1, xmm3 + QUAD $0xfffffe409e100ff3 // movss xmm3, dword [rsi - 448] + QUAD $0xfffec09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 320], 16 + QUAD $0xffff409e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 192], 32 + LONG $0x213a0f66; WORD $0xc05e; BYTE $0x30 // insertps xmm3, dword [rsi - 64], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0x6f0f4466; WORD $0x2065 // movdqa xmm12, oword 32[rbp] /* [rip + .LCPI10_2] */ + LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0x4ddb0f66; BYTE $0x30 // pand xmm1, oword 48[rbp] /* [rip + .LCPI10_3] */ + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffffe4896100ff3 // movss xmm2, dword [rsi - 440] + QUAD $0xfffec896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 312], 16 + QUAD $0xffff4896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 184], 32 + LONG $0x213a0f66; WORD $0xc856; BYTE $0x30 // insertps xmm2, dword [rsi - 56], 48 + LONG $0xcdeb0f66 // por xmm1, xmm5 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0xc2c20f41; BYTE $0x02 // cmpleps xmm0, xmm10 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0xe9c20f41; BYTE $0x02 // cmpleps xmm5, xmm9 + QUAD $0xfffffe4cbe100ff3 // movss xmm7, dword [rsi - 436] + QUAD $0xfffeccbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 308], 16 + QUAD $0xffff4cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 180], 32 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0x213a0f66; WORD $0xcc7e; BYTE $0x30 // insertps xmm7, dword [rsi - 52], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 + LONG $0x6ddb0f66; BYTE $0x50 // pand xmm5, oword 80[rbp] /* [rip + .LCPI10_5] */ + LONG $0xe8eb0f66 // por xmm5, xmm0 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c3c20f // cmpleps xmm0, xmm3 + QUAD $0xfffffe509e100ff3 // movss xmm3, dword [rsi - 432] + QUAD $0xfffed09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 304], 16 + QUAD $0xffff509e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 176], 32 + LONG $0x213a0f66; WORD $0xd05e; BYTE $0x30 // insertps xmm3, dword [rsi - 48], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 + LONG $0x6f0f4466; WORD $0x6055 // movdqa xmm10, oword 96[rbp] /* [rip + .LCPI10_6] */ + LONG $0xdb0f4166; BYTE $0xc2 // pand xmm0, xmm10 + LONG $0xc5eb0f66 // por xmm0, xmm5 + QUAD $0xfffffe54ae100ff3 // movss xmm5, dword [rsi - 428] + QUAD $0xfffed4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 300], 16 + QUAD $0xffff54ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 172], 32 + LONG $0x213a0f66; WORD $0xd46e; BYTE $0x30 // insertps xmm5, dword [rsi - 44], 48 + LONG $0xc1eb0f66 // por xmm0, xmm1 + QUAD $0xfffe588e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 424] + QUAD $0xfed88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 296], 16 + QUAD $0xff588e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 168], 32 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + QUAD $0x30d84e213a0f4466 // insertps xmm9, dword [rsi - 40], 48 + LONG $0x620f4466; BYTE $0xc0 // punpckldq xmm8, xmm0 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c2c20f // cmpleps xmm0, xmm2 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xc8f80f66 // psubb xmm1, xmm0 + QUAD $0xfffffe5c96100ff3 // movss xmm2, dword [rsi - 420] + QUAD $0xfffedc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 292], 16 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + QUAD $0xffff5c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 164], 32 + LONG $0xceeb0f66 // por xmm1, xmm6 + LONG $0xf6280f41 // movaps xmm6, xmm14 + LONG $0x02f7c20f // cmpleps xmm6, xmm7 + LONG $0x213a0f66; WORD $0xdc56; BYTE $0x30 // insertps xmm2, dword [rsi - 36], 48 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 + LONG $0x456f0f66; BYTE $0x10 // movdqa xmm0, oword 16[rbp] /* [rip + .LCPI10_1] */ + LONG $0xf0db0f66 // pand xmm6, xmm0 + LONG $0xf1eb0f66 // por xmm6, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c3c20f // cmpleps xmm0, xmm3 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0x02cdc20f // cmpleps xmm1, xmm5 + QUAD $0xfffffe609e100ff3 // movss xmm3, dword [rsi - 416] + QUAD $0xfffee09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 288], 16 + QUAD $0xffff609e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 160], 32 + LONG $0x213a0f66; WORD $0xe05e; BYTE $0x30 // insertps xmm3, dword [rsi - 32], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0x6f0f4466; WORD $0x3065 // movdqa xmm12, oword 48[rbp] /* [rip + .LCPI10_3] */ + LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffffe68ae100ff3 // movss xmm5, dword [rsi - 408] + QUAD $0xfffee8ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 280], 16 + QUAD $0xffff68ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 152], 32 + LONG $0x213a0f66; WORD $0xe86e; BYTE $0x30 // insertps xmm5, dword [rsi - 24], 48 + LONG $0xceeb0f66 // por xmm1, xmm6 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0xc1c20f41; BYTE $0x02 // cmpleps xmm0, xmm9 + LONG $0xf6280f41 // movaps xmm6, xmm14 + LONG $0x02f2c20f // cmpleps xmm6, xmm2 + QUAD $0xfffffe6cbe100ff3 // movss xmm7, dword [rsi - 404] + QUAD $0xfffeecbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 276], 16 + QUAD $0xffff6cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 148], 32 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0x213a0f66; WORD $0xec7e; BYTE $0x30 // insertps xmm7, dword [rsi - 20], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 + LONG $0xdb0f4166; BYTE $0xc5 // pand xmm0, xmm13 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x06 // psllw xmm6, 6 + LONG $0x6f0f4466; WORD $0x504d // movdqa xmm9, oword 80[rbp] /* [rip + .LCPI10_5] */ + LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 + LONG $0xf0eb0f66 // por xmm6, xmm0 + LONG $0xd6280f41 // movaps xmm2, xmm14 + LONG $0x02d3c20f // cmpleps xmm2, xmm3 + QUAD $0xfffffe709e100ff3 // movss xmm3, dword [rsi - 400] + QUAD $0xfffef09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 272], 16 + QUAD $0xffff709e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 144], 32 + LONG $0x213a0f66; WORD $0xf05e; BYTE $0x30 // insertps xmm3, dword [rsi - 16], 48 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] + QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 + QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 + LONG $0xd1eb0f66 // por xmm2, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c5c20f // cmpleps xmm0, xmm5 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xc8f80f66 // psubb xmm1, xmm0 + QUAD $0xfffffe78ae100ff3 // movss xmm5, dword [rsi - 392] + QUAD $0xfffef8ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 264], 16 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + QUAD $0xffff78ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 136], 32 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0xe6280f41 // movaps xmm4, xmm14 + LONG $0x02e7c20f // cmpleps xmm4, xmm7 + LONG $0x213a0f66; WORD $0xf86e; BYTE $0x30 // insertps xmm5, dword [rsi - 8], 48 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + LONG $0xf4710f66; BYTE $0x02 // psllw xmm4, 2 + LONG $0x65db0f66; BYTE $0x10 // pand xmm4, oword 16[rbp] /* [rip + .LCPI10_1] */ + LONG $0xe1eb0f66 // por xmm4, xmm1 + LONG $0xc6280f41 // movaps xmm0, xmm14 + LONG $0x02c3c20f // cmpleps xmm0, xmm3 + LONG $0xce280f41 // movaps xmm1, xmm14 + LONG $0x02cec20f // cmpleps xmm1, xmm6 + QUAD $0xfffffe7c9e100ff3 // movss xmm3, dword [rsi - 388] + QUAD $0xfffefc9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 260], 16 + QUAD $0xffff7c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 132], 32 + LONG $0x213a0f66; WORD $0xfc5e; BYTE $0x30 // insertps xmm3, dword [rsi - 4], 48 + LONG $0xc06b0f66 // packssdw xmm0, xmm0 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 + LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 + LONG $0x45db0f66; BYTE $0x20 // pand xmm0, oword 32[rbp] /* [rip + .LCPI10_2] */ + LONG $0xc96b0f66 // packssdw xmm1, xmm1 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 + LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 + LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 + LONG $0xc8eb0f66 // por xmm1, xmm0 + QUAD $0xfffffe8086100ff3 // movss xmm0, dword [rsi - 384] + QUAD $0xffff0086213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 256], 16 + LONG $0x213a0f66; WORD $0x8046; BYTE $0x20 // insertps xmm0, dword [rsi - 128], 32 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0xe6280f41 // movaps xmm4, xmm14 + LONG $0x02e5c20f // cmpleps xmm4, xmm5 + LONG $0xee280f41 // movaps xmm5, xmm14 + LONG $0x02ebc20f // cmpleps xmm5, xmm3 + LONG $0x213a0f66; WORD $0x3006 // insertps xmm0, dword [rsi], 48 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + LONG $0xf4710f66; BYTE $0x05 // psllw xmm4, 5 + LONG $0xdb0f4166; BYTE $0xe5 // pand xmm4, xmm13 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 + LONG $0xdb0f4166; BYTE $0xe9 // pand xmm5, xmm9 + LONG $0xeceb0f66 // por xmm5, xmm4 + LONG $0xde280f41 // movaps xmm3, xmm14 + LONG $0x02d8c20f // cmpleps xmm3, xmm0 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xda // pand xmm3, xmm10 + LONG $0xddeb0f66 // por xmm3, xmm5 + LONG $0xd9eb0f66 // por xmm3, xmm1 + LONG $0xd3620f66 // punpckldq xmm2, xmm3 + LONG $0x600f4466; BYTE $0xc2 // punpcklbw xmm8, xmm2 + LONG $0x380f4466; WORD $0x4500; BYTE $0x70 // pshufb xmm8, oword 112[rbp] /* [rip + .LCPI10_7] */ + LONG $0x7f0f45f3; WORD $0x9404 // movdqu oword [r12 + 4*rdx], xmm8 + LONG $0x04c28348 // add rdx, 4 + LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JNE LBB10_208 + WORD $0x3948; BYTE $0xc7 // cmp rdi, rax + JNE LBB10_210 + JMP LBB10_213 + +LBB10_98: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000017024848948 // mov qword [rsp + 368], rax - QUAD $0x000000f024bc894c // mov qword [rsp + 240], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - QUAD $0x0000009024848948 // mov qword [rsp + 144], rax - LONG $0xc3b60f41 // movzx eax, r11b + WORD $0x0148; BYTE $0xf8 // add rax, rdi + QUAD $0x0000017824848948 // mov qword [rsp + 376], rax + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + LONG $0xc7b60f41 // movzx eax, r15b LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000140248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 320], xmm1 + QUAD $0x0001a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 416], xmm1 WORD $0x3145; BYTE $0xc0 // xor r8d, r8d - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB10_86: - QUAD $0x000001002484894c // mov qword [rsp + 256], r8 +LBB10_99: + QUAD $0x000000e02484894c // mov qword [rsp + 224], r8 LONG $0x05e0c149 // shl r8, 5 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 + QUAD $0x000000c02484894c // mov qword [rsp + 192], r8 + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 QUAD $0x000000802484894c // mov qword [rsp + 128], r8 WORD $0x894d; BYTE $0xc4 // mov r12, r8 WORD $0x894d; BYTE $0xc7 // mov r15, r8 - LONG $0x2444894c; BYTE $0x10 // mov qword [rsp + 16], r8 + WORD $0x894d; BYTE $0xc6 // mov r14, r8 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x894c; BYTE $0xc2 // mov rdx, r8 WORD $0x894d; BYTE $0xc2 // mov r10, r8 + QUAD $0x000000902484894c // mov qword [rsp + 144], r8 + LONG $0x04b60f42; BYTE $0x07 // movzx eax, byte [rdi + r8] + LONG $0x6e0f4466; BYTE $0xc8 // movd xmm9, eax + LONG $0x44b60f42; WORD $0x0107 // movzx eax, byte [rdi + r8 + 1] + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x44b60f42; WORD $0x0207 // movzx eax, byte [rdi + r8 + 2] + LONG $0xd86e0f66 // movd xmm3, eax + LONG $0x44b60f42; WORD $0x0307 // movzx eax, byte [rdi + r8 + 3] + LONG $0xe06e0f66 // movd xmm4, eax + LONG $0x44b60f42; WORD $0x0407 // movzx eax, byte [rdi + r8 + 4] + LONG $0xf06e0f66 // movd xmm6, eax + LONG $0x44b60f42; WORD $0x0507 // movzx eax, byte [rdi + r8 + 5] + LONG $0xc06e0f66 // movd xmm0, eax + QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 + LONG $0x44b60f42; WORD $0x0607 // movzx eax, byte [rdi + r8 + 6] + LONG $0xf86e0f66 // movd xmm7, eax + LONG $0x44b60f42; WORD $0x0707 // movzx eax, byte [rdi + r8 + 7] + LONG $0xc06e0f66 // movd xmm0, eax + QUAD $0x00011024847f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm0 + LONG $0x44b60f42; WORD $0x0807 // movzx eax, byte [rdi + r8 + 8] + LONG $0x6e0f4466; BYTE $0xe8 // movd xmm13, eax + LONG $0x44b60f42; WORD $0x0907 // movzx eax, byte [rdi + r8 + 9] + LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax + LONG $0x44b60f42; WORD $0x0a07 // movzx eax, byte [rdi + r8 + 10] + LONG $0x6e0f4466; BYTE $0xd0 // movd xmm10, eax + LONG $0x44b60f42; WORD $0x0b07 // movzx eax, byte [rdi + r8 + 11] + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x44b60f42; WORD $0x0c07 // movzx eax, byte [rdi + r8 + 12] + LONG $0x6e0f4466; BYTE $0xe0 // movd xmm12, eax + LONG $0x44b60f42; WORD $0x1007 // movzx eax, byte [rdi + r8 + 16] + LONG $0x6e0f4466; BYTE $0xf0 // movd xmm14, eax + QUAD $0x000000d02484894c // mov qword [rsp + 208], r8 + LONG $0x44b60f42; WORD $0x1807 // movzx eax, byte [rdi + r8 + 24] + LONG $0xe86e0f66 // movd xmm5, eax WORD $0x894c; BYTE $0xc0 // mov rax, r8 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - LONG $0x0cb60f42; BYTE $0x06 // movzx ecx, byte [rsi + r8] - LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x4cb60f42; WORD $0x0106 // movzx ecx, byte [rsi + r8 + 1] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x4cb60f42; WORD $0x0206 // movzx ecx, byte [rsi + r8 + 2] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x4cb60f42; WORD $0x0306 // movzx ecx, byte [rsi + r8 + 3] - LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x4cb60f42; WORD $0x0406 // movzx ecx, byte [rsi + r8 + 4] - LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x4cb60f42; WORD $0x0506 // movzx ecx, byte [rsi + r8 + 5] - LONG $0xc16e0f66 // movd xmm0, ecx - LONG $0x447f0f66; WORD $0x7024 // movdqa oword [rsp + 112], xmm0 - LONG $0x4cb60f42; WORD $0x0606 // movzx ecx, byte [rsi + r8 + 6] - LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x4cb60f42; WORD $0x0706 // movzx ecx, byte [rsi + r8 + 7] - LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x00013024847f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm0 - LONG $0x4cb60f42; WORD $0x0806 // movzx ecx, byte [rsi + r8 + 8] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x4cb60f42; WORD $0x0906 // movzx ecx, byte [rsi + r8 + 9] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x4cb60f42; WORD $0x0a06 // movzx ecx, byte [rsi + r8 + 10] - LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x4cb60f42; WORD $0x0b06 // movzx ecx, byte [rsi + r8 + 11] - LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x4cb60f42; WORD $0x0c06 // movzx ecx, byte [rsi + r8 + 12] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x4cb60f42; WORD $0x1006 // movzx ecx, byte [rsi + r8 + 16] - LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - QUAD $0x000000c02484894c // mov qword [rsp + 192], r8 - LONG $0x4cb60f42; WORD $0x1806 // movzx ecx, byte [rsi + r8 + 24] - LONG $0xe96e0f66 // movd xmm5, ecx - WORD $0x894c; BYTE $0xc1 // mov rcx, r8 - LONG $0x20c98348 // or rcx, 32 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - LONG $0x244c8948; BYTE $0x50 // mov qword [rsp + 80], rcx + LONG $0x20c88348 // or rax, 32 + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] LONG $0x40c98349 // or r9, 64 - LONG $0x244c894c; BYTE $0x20 // mov qword [rsp + 32], r9 - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0x60c98349 // or r9, 96 - QUAD $0x00000080248c8148; LONG $0x00000080 // or qword [rsp + 128], 128 + QUAD $0x000000c0248c894c // mov qword [rsp + 192], r9 + LONG $0x60ce8348 // or rsi, 96 + QUAD $0x000000b024b48948 // mov qword [rsp + 176], rsi + WORD $0x8948; BYTE $0xf1 // mov rcx, rsi + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + LONG $0x00800d48; WORD $0x0000 // or rax, 128 + QUAD $0x0000008024848948 // mov qword [rsp + 128], rax LONG $0xa0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 160 + QUAD $0x0000016024a4894c // mov qword [rsp + 352], r12 LONG $0xc0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 192 - LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] - LONG $0xe0cb8148; WORD $0x0000; BYTE $0x00 // or rbx, 224 - LONG $0x00cb8149; WORD $0x0001; BYTE $0x00 // or r11, 256 - LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 - LONG $0x01400d48; WORD $0x0000 // or rax, 320 - LONG $0x60ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 352 - LONG $0x24548948; BYTE $0x30 // mov qword [rsp + 48], rdx - LONG $0x80ce8149; WORD $0x0001; BYTE $0x00 // or r14, 384 - QUAD $0x000000b024b4894c // mov qword [rsp + 176], r14 - LONG $0xa0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 416 - LONG $0x247c8948; BYTE $0x60 // mov qword [rsp + 96], rdi - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - LONG $0xc0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 448 - LONG $0x247c8948; BYTE $0x10 // mov qword [rsp + 16], rdi - WORD $0x894c; BYTE $0xc7 // mov rdi, r8 - LONG $0xe0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 480 - QUAD $0x012e0c203a0f4666 // pinsrb xmm9, byte [rsi + r13], 1 - QUAD $0x020e0c203a0f4466 // pinsrb xmm9, byte [rsi + rcx], 2 - QUAD $0x030e0c203a0f4666 // pinsrb xmm9, byte [rsi + r9], 3 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x04060c203a0f4666 // pinsrb xmm9, byte [rsi + r8], 4 - QUAD $0x05260c203a0f4666 // pinsrb xmm9, byte [rsi + r12], 5 - QUAD $0x063e0c203a0f4666 // pinsrb xmm9, byte [rsi + r15], 6 - QUAD $0x071e0c203a0f4466 // pinsrb xmm9, byte [rsi + rbx], 7 - QUAD $0x081e0c203a0f4666 // pinsrb xmm9, byte [rsi + r11], 8 - QUAD $0x09160c203a0f4666 // pinsrb xmm9, byte [rsi + r10], 9 - QUAD $0x0a060c203a0f4466 // pinsrb xmm9, byte [rsi + rax], 10 - QUAD $0x0b160c203a0f4466 // pinsrb xmm9, byte [rsi + rdx], 11 - QUAD $0x0c360c203a0f4666 // pinsrb xmm9, byte [rsi + r14], 12 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x0d2e0c203a0f4666 // pinsrb xmm9, byte [rsi + r13], 13 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e0e0c203a0f4466 // pinsrb xmm9, byte [rsi + rcx], 14 - QUAD $0x000000d024bc8948 // mov qword [rsp + 208], rdi - QUAD $0x0f3e0c203a0f4466 // pinsrb xmm9, byte [rsi + rdi], 15 - QUAD $0x014024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 320] - LONG $0x6f0f4566; BYTE $0xdf // movdqa xmm11, xmm15 + LONG $0xe0ce8149; WORD $0x0000; BYTE $0x00 // or r14, 224 + LONG $0x00cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 256 + LONG $0x20cb8149; WORD $0x0001; BYTE $0x00 // or r11, 288 + LONG $0x40ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 320 + LONG $0x60ca8149; WORD $0x0001; BYTE $0x00 // or r10, 352 + QUAD $0x00000090248c8148; LONG $0x00000180 // or qword [rsp + 144], 384 + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 + LONG $0xa0ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 416 + LONG $0x24748948; BYTE $0x10 // mov qword [rsp + 16], rsi + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 + LONG $0xc0ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 448 + LONG $0x24748948; BYTE $0x50 // mov qword [rsp + 80], rsi + WORD $0x894c; BYTE $0xc6 // mov rsi, r8 + LONG $0xe0ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 480 + QUAD $0x012f0c203a0f4666 // pinsrb xmm9, byte [rdi + r13], 1 + QUAD $0x020f0c203a0f4666 // pinsrb xmm9, byte [rdi + r9], 2 + QUAD $0x030f0c203a0f4466 // pinsrb xmm9, byte [rdi + rcx], 3 + QUAD $0x04070c203a0f4466 // pinsrb xmm9, byte [rdi + rax], 4 + QUAD $0x05270c203a0f4666 // pinsrb xmm9, byte [rdi + r12], 5 + QUAD $0x063f0c203a0f4666 // pinsrb xmm9, byte [rdi + r15], 6 + QUAD $0x07370c203a0f4666 // pinsrb xmm9, byte [rdi + r14], 7 + QUAD $0x081f0c203a0f4466 // pinsrb xmm9, byte [rdi + rbx], 8 + QUAD $0x091f0c203a0f4666 // pinsrb xmm9, byte [rdi + r11], 9 + QUAD $0x0a170c203a0f4466 // pinsrb xmm9, byte [rdi + rdx], 10 + QUAD $0x0b170c203a0f4666 // pinsrb xmm9, byte [rdi + r10], 11 + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + QUAD $0x0c070c203a0f4666 // pinsrb xmm9, byte [rdi + r8], 12 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x0d2f0c203a0f4666 // pinsrb xmm9, byte [rdi + r13], 13 LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x01010e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 1], 1 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x02010e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 1], 2 - QUAD $0x010e54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r9 + 1], 3 - QUAD $0x010654203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rsi + r8 + 1], 4 - QUAD $0x012654203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r12 + 1], 5 - QUAD $0x013e54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r15 + 1], 6 - QUAD $0x07011e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 1], 7 - QUAD $0x011e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r11 + 1], 8 - QUAD $0x011654203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r10 + 1], 9 - QUAD $0x0a010654203a0f66 // pinsrb xmm2, byte [rsi + rax + 1], 10 - QUAD $0x0b011654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 1], 11 - QUAD $0x013654203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r14 + 1], 12 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x012e54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r13 + 1], 13 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e010e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 1], 14 - QUAD $0x0f013e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 1], 15 + QUAD $0x0e0f0c203a0f4466 // pinsrb xmm9, byte [rdi + rcx], 14 + LONG $0x24748948; BYTE $0x20 // mov qword [rsp + 32], rsi + QUAD $0x0f370c203a0f4466 // pinsrb xmm9, byte [rdi + rsi], 15 + QUAD $0x01a024bc6f0f4466; WORD $0x0000 // movdqa xmm15, oword [rsp + 416] + LONG $0x6f0f4566; BYTE $0xdf // movdqa xmm11, xmm15 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + QUAD $0x01010f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 1], 1 + QUAD $0x010f54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdi + r9 + 1], 2 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x03010f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 1], 3 + QUAD $0x04010754203a0f66 // pinsrb xmm2, byte [rdi + rax + 1], 4 + QUAD $0x012754203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdi + r12 + 1], 5 + QUAD $0x013f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r15 + 1], 6 + QUAD $0x013754203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r14 + 1], 7 + QUAD $0x08011f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 1], 8 + QUAD $0x011f54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r11 + 1], 9 + QUAD $0x0a011754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 1], 10 + QUAD $0x011754203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdi + r10 + 1], 11 + QUAD $0x010754203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdi + r8 + 1], 12 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x012f54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdi + r13 + 1], 13 LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x01020e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 2], 1 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x022e5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rsi + r13 + 2], 2 - QUAD $0x020e5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r9 + 2], 3 - QUAD $0x02065c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r8 + 2], 4 - QUAD $0x02265c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r12 + 2], 5 - QUAD $0x023e5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r15 + 2], 6 - QUAD $0x07021e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 2], 7 - QUAD $0x021e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r11 + 2], 8 - QUAD $0x02165c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r10 + 2], 9 - QUAD $0x0a02065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 2], 10 - QUAD $0x0b02165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 2], 11 - QUAD $0x02365c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r14 + 2], 12 + QUAD $0x0e010f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 1], 14 + QUAD $0x0f013754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 1], 15 LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0d020e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 2], 13 + QUAD $0x01020f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 2], 1 + QUAD $0x020f5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdi + r9 + 2], 2 + QUAD $0x000000b024ac8b4c // mov r13, qword [rsp + 176] + QUAD $0x022f5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r13 + 2], 3 + QUAD $0x0402075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 2], 4 + QUAD $0x02275c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdi + r12 + 2], 5 + QUAD $0x023f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r15 + 2], 6 + QUAD $0x02375c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r14 + 2], 7 + QUAD $0x08021f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 2], 8 + QUAD $0x021f5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdi + r11 + 2], 9 + QUAD $0x0a02175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 2], 10 + QUAD $0x02175c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r10 + 2], 11 + QUAD $0x02075c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r8 + 2], 12 LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e020e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 2], 14 - QUAD $0x0f023e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 2], 15 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 + QUAD $0x0d020f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 2], 13 LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x01030e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 3], 1 - QUAD $0x032e64203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r13 + 3], 2 - QUAD $0x030e64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r9 + 3], 3 - QUAD $0x030664203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rsi + r8 + 3], 4 - QUAD $0x032664203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r12 + 3], 5 - QUAD $0x033e64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r15 + 3], 6 - QUAD $0x07031e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 3], 7 - QUAD $0x031e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r11 + 3], 8 - QUAD $0x031664203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r10 + 3], 9 - QUAD $0x0a030664203a0f66 // pinsrb xmm4, byte [rsi + rax + 3], 10 - QUAD $0x0b031664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 3], 11 - QUAD $0x033664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r14 + 3], 12 + QUAD $0x0e020f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 2], 14 + QUAD $0x0f02375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 2], 15 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0d030e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 3], 13 + QUAD $0x01030f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 3], 1 + QUAD $0x030f64203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdi + r9 + 3], 2 + QUAD $0x032f64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdi + r13 + 3], 3 + QUAD $0x04030764203a0f66 // pinsrb xmm4, byte [rdi + rax + 3], 4 + QUAD $0x032764203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdi + r12 + 3], 5 + QUAD $0x033f64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r15 + 3], 6 + QUAD $0x033764203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r14 + 3], 7 + QUAD $0x08031f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 3], 8 + QUAD $0x031f64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdi + r11 + 3], 9 + QUAD $0x0a031764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 3], 10 + QUAD $0x031764203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r10 + 3], 11 + QUAD $0x030764203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdi + r8 + 3], 12 LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e030e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 3], 14 - QUAD $0x0f033e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 3], 15 + QUAD $0x0d030f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 3], 13 LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x01040e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 4], 1 - QUAD $0x042e74203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rsi + r13 + 4], 2 - QUAD $0x040e74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r9 + 4], 3 - QUAD $0x040674203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rsi + r8 + 4], 4 - QUAD $0x042674203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r12 + 4], 5 - QUAD $0x043e74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r15 + 4], 6 - QUAD $0x07041e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 4], 7 - QUAD $0x041e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r11 + 4], 8 - QUAD $0x041674203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r10 + 4], 9 - QUAD $0x0a040674203a0f66 // pinsrb xmm6, byte [rsi + rax + 4], 10 - QUAD $0x0b041674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 4], 11 - QUAD $0x043674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r14 + 4], 12 + QUAD $0x0e030f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 3], 14 + QUAD $0x0f033764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 3], 15 LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0d040e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 4], 13 + QUAD $0x01040f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 4], 1 + QUAD $0x040f74203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdi + r9 + 4], 2 + QUAD $0x042f74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r13 + 4], 3 + QUAD $0x04040774203a0f66 // pinsrb xmm6, byte [rdi + rax + 4], 4 + QUAD $0x042774203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdi + r12 + 4], 5 + QUAD $0x043f74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r15 + 4], 6 + QUAD $0x043774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r14 + 4], 7 + QUAD $0x08041f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 4], 8 + QUAD $0x041f74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r11 + 4], 9 + QUAD $0x0a041774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 4], 10 + QUAD $0x041774203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r10 + 4], 11 + QUAD $0x040774203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r8 + 4], 12 LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e040e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 4], 14 - QUAD $0x0f043e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 4], 15 - LONG $0x5c6f0f66; WORD $0x7024 // movdqa xmm3, oword [rsp + 112] + QUAD $0x0d040f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 4], 13 LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - QUAD $0x01050e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 5], 1 - QUAD $0x052e5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rsi + r13 + 5], 2 - QUAD $0x050e5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r9 + 5], 3 - QUAD $0x05065c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r8 + 5], 4 - QUAD $0x05265c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r12 + 5], 5 - QUAD $0x053e5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r15 + 5], 6 - QUAD $0x07051e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 5], 7 - QUAD $0x051e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r11 + 5], 8 - QUAD $0x05165c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r10 + 5], 9 - QUAD $0x0a05065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 5], 10 - QUAD $0x0b05165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 5], 11 - QUAD $0x05365c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r14 + 5], 12 + QUAD $0x0e040f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 4], 14 + QUAD $0x0f043774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 4], 15 + QUAD $0x0000a0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 160] LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0d050e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 5], 13 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e050e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 5], 14 - QUAD $0x0f053e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 5], 15 - LONG $0x5c7f0f66; WORD $0x7024 // movdqa oword [rsp + 112], xmm3 - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x01063e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 6], 1 - WORD $0x894c; BYTE $0xe9 // mov rcx, r13 - QUAD $0x062e7c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rsi + r13 + 6], 2 - QUAD $0x060e7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rsi + r9 + 6], 3 - QUAD $0x06067c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rsi + r8 + 6], 4 - QUAD $0x06267c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r12 + 6], 5 - QUAD $0x063e7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rsi + r15 + 6], 6 - QUAD $0x07061e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 6], 7 - QUAD $0x061e7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r11 + 6], 8 - QUAD $0x06167c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r10 + 6], 9 - QUAD $0x0a06067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 6], 10 - QUAD $0x0b06167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 6], 11 - QUAD $0x06367c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r14 + 6], 12 - QUAD $0x083e6c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rsi + rdi + 8], 1 - WORD $0x8949; BYTE $0xfd // mov r13, rdi - QUAD $0x080e6c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rcx + 8], 2 - QUAD $0x080e6c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rsi + r9 + 8], 3 - QUAD $0x08066c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rsi + r8 + 8], 4 - QUAD $0x08266c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rsi + r12 + 8], 5 - QUAD $0x083e6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rsi + r15 + 8], 6 - QUAD $0x081e6c203a0f4466; BYTE $0x07 // pinsrb xmm13, byte [rsi + rbx + 8], 7 - QUAD $0x081e6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r11 + 8], 8 - QUAD $0x08166c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rsi + r10 + 8], 9 - QUAD $0x08066c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rsi + rax + 8], 10 - QUAD $0x08166c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rsi + rdx + 8], 11 - QUAD $0x08366c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rsi + r14 + 8], 12 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x08066c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rsi + r8 + 8], 13 + QUAD $0x01050f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 5], 1 + QUAD $0x050f5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdi + r9 + 5], 2 + QUAD $0x052f5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r13 + 5], 3 + QUAD $0x0405075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 5], 4 + QUAD $0x05275c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdi + r12 + 5], 5 + QUAD $0x053f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r15 + 5], 6 + QUAD $0x05375c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r14 + 5], 7 + QUAD $0x08051f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 5], 8 + QUAD $0x051f5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdi + r11 + 5], 9 + QUAD $0x0a05175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 5], 10 + QUAD $0x05175c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r10 + 5], 11 + QUAD $0x05075c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r8 + 5], 12 LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x080e6c203a0f4466; BYTE $0x0e // pinsrb xmm13, byte [rsi + rcx + 8], 14 + QUAD $0x0d050f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 5], 13 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x052f5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdi + r13 + 5], 14 + QUAD $0x0f05375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 5], 15 + QUAD $0x0000a0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm3 + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + QUAD $0x0106377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 6], 1 + QUAD $0x060f7c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rdi + r9 + 6], 2 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x03060f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 6], 3 + QUAD $0x0406077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 6], 4 + QUAD $0x06277c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdi + r12 + 6], 5 + QUAD $0x063f7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r15 + 6], 6 + QUAD $0x06377c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r14 + 6], 7 + QUAD $0x08061f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 6], 8 + QUAD $0x061f7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdi + r11 + 6], 9 + QUAD $0x0a06177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 6], 10 + QUAD $0x06177c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdi + r10 + 6], 11 + QUAD $0x06077c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdi + r8 + 6], 12 + QUAD $0x08376c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdi + rsi + 8], 1 + QUAD $0x080f6c203a0f4666; BYTE $0x02 // pinsrb xmm13, byte [rdi + r9 + 8], 2 + QUAD $0x080f6c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rdi + rcx + 8], 3 + QUAD $0x08076c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdi + rax + 8], 4 + QUAD $0x08276c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rdi + r12 + 8], 5 + QUAD $0x083f6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdi + r15 + 8], 6 + QUAD $0x08376c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdi + r14 + 8], 7 + QUAD $0x081f6c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rdi + rbx + 8], 8 + QUAD $0x081f6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdi + r11 + 8], 9 + QUAD $0x08176c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdi + rdx + 8], 10 + QUAD $0x08176c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdi + r10 + 8], 11 + QUAD $0x08076c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdi + r8 + 8], 12 + LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] + QUAD $0x08076c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdi + r8 + 8], 13 + QUAD $0x082f6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdi + r13 + 8], 14 LONG $0x640f4566; BYTE $0xd9 // pcmpgtb xmm11, xmm9 - QUAD $0x000000d024bc8b48 // mov rdi, qword [rsp + 208] - QUAD $0x083e6c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rsi + rdi + 8], 15 + LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] + QUAD $0x082f6c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdi + r13 + 8], 15 LONG $0x6f0f4566; BYTE $0xcf // movdqa xmm9, xmm15 LONG $0x640f4566; BYTE $0xcd // pcmpgtb xmm9, xmm13 - QUAD $0x102e74203a0f4666; BYTE $0x01 // pinsrb xmm14, byte [rsi + r13 + 16], 1 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x100e74203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rsi + rcx + 16], 2 - QUAD $0x100e74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rsi + r9 + 16], 3 - WORD $0x894d; BYTE $0xce // mov r14, r9 - QUAD $0x000000a0248c894c // mov qword [rsp + 160], r9 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x100e74203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rsi + rcx + 16], 4 - QUAD $0x102674203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rsi + r12 + 16], 5 - QUAD $0x000000e024a4894c // mov qword [rsp + 224], r12 - QUAD $0x103e74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rsi + r15 + 16], 6 - QUAD $0x101e74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rsi + rbx + 16], 7 - QUAD $0x101e74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r11 + 16], 8 - QUAD $0x101674203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r10 + 16], 9 - QUAD $0x100674203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rsi + rax + 16], 10 - WORD $0x8949; BYTE $0xc1 // mov r9, rax - QUAD $0x101674203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rsi + rdx + 16], 11 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x101674203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rsi + rdx + 16], 12 - QUAD $0x100674203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rsi + r8 + 16], 13 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x102e74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rsi + r13 + 16], 14 - QUAD $0x103e74203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rsi + rdi + 16], 15 + QUAD $0x103774203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdi + rsi + 16], 1 + QUAD $0x100f74203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdi + r9 + 16], 2 + QUAD $0x100f74203a0f4466; BYTE $0x03 // pinsrb xmm14, byte [rdi + rcx + 16], 3 + QUAD $0x100774203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rdi + rax + 16], 4 + QUAD $0x102774203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rdi + r12 + 16], 5 + QUAD $0x103f74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdi + r15 + 16], 6 + QUAD $0x000000f024bc894c // mov qword [rsp + 240], r15 + QUAD $0x103774203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdi + r14 + 16], 7 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + QUAD $0x0000015024b4894c // mov qword [rsp + 336], r14 + QUAD $0x101f74203a0f4466; BYTE $0x08 // pinsrb xmm14, byte [rdi + rbx + 16], 8 + QUAD $0x00000140249c8948 // mov qword [rsp + 320], rbx + QUAD $0x101f74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rdi + r11 + 16], 9 + QUAD $0x101774203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdi + rdx + 16], 10 + LONG $0x24548948; BYTE $0x30 // mov qword [rsp + 48], rdx + QUAD $0x101774203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdi + r10 + 16], 11 + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + QUAD $0x100774203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rdi + rax + 16], 12 + QUAD $0x100774203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rdi + r8 + 16], 13 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x102f74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdi + r13 + 16], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x103774203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdi + rsi + 16], 15 LONG $0x6f0f4166; BYTE $0xdf // movdqa xmm3, xmm15 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0118066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 24], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0218066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 24], 2 - QUAD $0x18366c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r14 + 24], 3 - QUAD $0x04180e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 24], 4 - QUAD $0x18266c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r12 + 24], 5 - QUAD $0x183e6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r15 + 24], 6 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x07181e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 24], 7 - QUAD $0x181e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r11 + 24], 8 - QUAD $0x18166c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r10 + 24], 9 - QUAD $0x180e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r9 + 24], 10 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x0b18066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 24], 11 - QUAD $0x0c18166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 24], 12 - QUAD $0x18066c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r8 + 24], 13 - QUAD $0x182e6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rsi + r13 + 24], 14 - QUAD $0x0f183e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 24], 15 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x18376c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdi + r14 + 24], 1 + QUAD $0x180f6c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rdi + r9 + 24], 2 + QUAD $0x03180f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 24], 3 + QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] + QUAD $0x04180f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 24], 4 + QUAD $0x00000160248c8b4c // mov r9, qword [rsp + 352] + QUAD $0x180f6c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rdi + r9 + 24], 5 + QUAD $0x183f6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r15 + 24], 6 + QUAD $0x18276c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r12 + 24], 7 + QUAD $0x08181f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 24], 8 + QUAD $0x181f6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r11 + 24], 9 + WORD $0x894d; BYTE $0xdc // mov r12, r11 + QUAD $0x0a18176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 24], 10 + QUAD $0x18176c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdi + r10 + 24], 11 + WORD $0x894d; BYTE $0xd7 // mov r15, r10 + QUAD $0x0c18076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 24], 12 + QUAD $0x18076c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdi + r8 + 24], 13 + QUAD $0x182f6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdi + r13 + 24], 14 + WORD $0x894c; BYTE $0xe8 // mov rax, r13 + QUAD $0x0f18376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 24], 15 LONG $0x640f4166; BYTE $0xde // pcmpgtb xmm3, xmm14 - QUAD $0x000150249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 336], xmm3 + QUAD $0x000120249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm3 LONG $0x6f0f4166; BYTE $0xdf // movdqa xmm3, xmm15 LONG $0xdd640f66 // pcmpgtb xmm3, xmm5 - QUAD $0x000120249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm3 + QUAD $0x000100249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm3 LONG $0x6f0f4166; BYTE $0xef // movdqa xmm5, xmm15 LONG $0xea640f66 // pcmpgtb xmm5, xmm2 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - LONG $0x0e54b60f; BYTE $0x0d // movzx edx, byte [rsi + rcx + 13] + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + LONG $0x0f54b60f; BYTE $0x0d // movzx edx, byte [rdi + rcx + 13] LONG $0xd26e0f66 // movd xmm2, edx - QUAD $0x06067c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r8 + 6], 13 + QUAD $0x06077c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rdi + r8 + 6], 13 + WORD $0x894d; BYTE $0xc5 // mov r13, r8 QUAD $0x000001009d6f0f66 // movdqa xmm3, oword 256[rbp] /* [rip + .LCPI10_16] */ LONG $0xebdf0f66 // pandn xmm5, xmm3 LONG $0xfc0f4166; BYTE $0xeb // paddb xmm5, xmm11 @@ -51575,9 +54185,9 @@ LBB10_86: LONG $0x640f4466; BYTE $0xe8 // pcmpgtb xmm13, xmm0 LONG $0x6f0f4166; BYTE $0xdf // movdqa xmm3, xmm15 LONG $0xdc640f66 // pcmpgtb xmm3, xmm4 - LONG $0x0e54b60f; BYTE $0x0e // movzx edx, byte [rsi + rcx + 14] + LONG $0x0f54b60f; BYTE $0x0e // movzx edx, byte [rdi + rcx + 14] LONG $0xe26e0f66 // movd xmm4, edx - QUAD $0x062e7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rsi + r13 + 6], 14 + QUAD $0x0e06077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 6], 14 QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI10_17] */ LONG $0xdf0f4466; BYTE $0xe8 // pandn xmm13, xmm0 QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI10_18] */ @@ -51585,478 +54195,483 @@ LBB10_86: LONG $0xeb0f4166; BYTE $0xdd // por xmm3, xmm13 LONG $0x6f0f4566; BYTE $0xf7 // movdqa xmm14, xmm15 LONG $0x640f4466; BYTE $0xf6 // pcmpgtb xmm14, xmm6 - LONG $0x0e54b60f; BYTE $0x0f // movzx edx, byte [rsi + rcx + 15] + LONG $0x0f54b60f; BYTE $0x0f // movzx edx, byte [rdi + rcx + 15] LONG $0xf26e0f66 // movd xmm6, edx QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI10_19] */ LONG $0xdf0f4466; BYTE $0xf0 // pandn xmm14, xmm0 LONG $0xeb0f4466; BYTE $0xf3 // por xmm14, xmm3 - LONG $0x0e54b60f; BYTE $0x11 // movzx edx, byte [rsi + rcx + 17] + LONG $0x0f54b60f; BYTE $0x11 // movzx edx, byte [rdi + rcx + 17] LONG $0xda6e0f66 // movd xmm3, edx - QUAD $0x0f063e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 6], 15 + QUAD $0x0f06377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 6], 15 LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 LONG $0xe8f80f66 // psubb xmm5, xmm0 LONG $0xeb0f4466; BYTE $0xf5 // por xmm14, xmm5 LONG $0x6f0f4166; BYTE $0xef // movdqa xmm5, xmm15 - LONG $0x6c640f66; WORD $0x7024 // pcmpgtb xmm5, oword [rsp + 112] + QUAD $0x0000a024ac640f66; BYTE $0x00 // pcmpgtb xmm5, oword [rsp + 160] LONG $0x6f0f4566; BYTE $0xef // movdqa xmm13, xmm15 LONG $0x6f0f4566; BYTE $0xdf // movdqa xmm11, xmm15 LONG $0x640f4466; BYTE $0xef // pcmpgtb xmm13, xmm7 - LONG $0x0e54b60f; BYTE $0x12 // movzx edx, byte [rsi + rcx + 18] + LONG $0x0f54b60f; BYTE $0x12 // movzx edx, byte [rdi + rcx + 18] LONG $0xfa6e0f66 // movd xmm7, edx QUAD $0x00000140856f0f66 // movdqa xmm0, oword 320[rbp] /* [rip + .LCPI10_20] */ LONG $0xe8df0f66 // pandn xmm5, xmm0 QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI10_21] */ LONG $0xdf0f4466; BYTE $0xe8 // pandn xmm13, xmm0 LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 - LONG $0x0e54b60f; BYTE $0x13 // movzx edx, byte [rsi + rcx + 19] + LONG $0x0f54b60f; BYTE $0x13 // movzx edx, byte [rdi + rcx + 19] LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - QUAD $0x00013024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 304] - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x01073e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 7], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x02070644203a0f66 // pinsrb xmm0, byte [rsi + rax + 7], 2 - QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] - QUAD $0x03070e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 7], 3 + QUAD $0x00011024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 272] + QUAD $0x073744203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdi + r14 + 7], 1 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x02070f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 7], 2 + QUAD $0x000000b024b48b48 // mov rsi, qword [rsp + 176] + QUAD $0x03073744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 7], 3 QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x04070644203a0f66 // pinsrb xmm0, byte [rsi + rax + 7], 4 - QUAD $0x000000e024bc8b4c // mov r15, qword [rsp + 224] - QUAD $0x073e44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rsi + r15 + 7], 5 - QUAD $0x073644203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rsi + r14 + 7], 6 - QUAD $0x07071e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 7], 7 - QUAD $0x071e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r11 + 7], 8 - QUAD $0x071644203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r10 + 7], 9 - QUAD $0x070e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r9 + 7], 10 - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0b071644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 7], 11 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0c071644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 7], 12 - QUAD $0x070644203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r8 + 7], 13 - QUAD $0x072e44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r13 + 7], 14 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x072644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r12 + 7], 15 - QUAD $0x093e44203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rdi + 9], 1 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x092e44203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rsi + r13 + 9], 2 - QUAD $0x090e44203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rcx + 9], 3 - QUAD $0x090644203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rax + 9], 4 - QUAD $0x093e44203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r15 + 9], 5 - QUAD $0x093644203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rsi + r14 + 9], 6 - QUAD $0x091e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rbx + 9], 7 - QUAD $0x091e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r11 + 9], 8 - QUAD $0x091644203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r10 + 9], 9 - QUAD $0x090e44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r9 + 9], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x093e44203a0f4466; BYTE $0x0b // pinsrb xmm8, byte [rsi + rdi + 9], 11 - QUAD $0x091644203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rsi + rdx + 9], 12 - QUAD $0x090644203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r8 + 9], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x093e44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rdi + 9], 14 - QUAD $0x092644203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r12 + 9], 15 + QUAD $0x04070744203a0f66 // pinsrb xmm0, byte [rdi + rax + 7], 4 + WORD $0x894d; BYTE $0xce // mov r14, r9 + QUAD $0x070f44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdi + r9 + 7], 5 + QUAD $0x000000f0249c8b4c // mov r11, qword [rsp + 240] + QUAD $0x071f44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r11 + 7], 6 + QUAD $0x0000015024948b4c // mov r10, qword [rsp + 336] + QUAD $0x071744203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r10 + 7], 7 + QUAD $0x00000140248c8b4c // mov r9, qword [rsp + 320] + QUAD $0x070f44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdi + r9 + 7], 8 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + QUAD $0x072744203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdi + r12 + 7], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a071f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 7], 10 + QUAD $0x0000013024bc894c // mov qword [rsp + 304], r15 + QUAD $0x073f44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdi + r15 + 7], 11 + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + QUAD $0x0c071744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 7], 12 + QUAD $0x072f44203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdi + r13 + 7], 13 LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x0a2e54203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rsi + r13 + 10], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0a3e54203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rdi + 10], 2 - QUAD $0x0a0e54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rcx + 10], 3 - QUAD $0x0a0654203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rax + 10], 4 - QUAD $0x0a3e54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r15 + 10], 5 - QUAD $0x0a3654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r14 + 10], 6 - QUAD $0x0a1e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rbx + 10], 7 - QUAD $0x0a1e54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r11 + 10], 8 - QUAD $0x0a1654203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r10 + 10], 9 - QUAD $0x0a0e54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r9 + 10], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0a3e54203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rsi + rdi + 10], 11 - QUAD $0x0a1654203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rsi + rdx + 10], 12 - QUAD $0x0a0654203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r8 + 10], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0a3e54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rdi + 10], 14 - QUAD $0x0a2654203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r12 + 10], 15 - QUAD $0x0b2e4c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rsi + r13 + 11], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x020b3e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 11], 2 - QUAD $0x030b0e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 11], 3 - QUAD $0x040b064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 11], 4 - QUAD $0x0b3e4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rsi + r15 + 11], 5 - QUAD $0x0b364c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rsi + r14 + 11], 6 - QUAD $0x070b1e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 11], 7 - QUAD $0x0b1e4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r11 + 11], 8 - QUAD $0x0b164c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r10 + 11], 9 - QUAD $0x0b0e4c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r9 + 11], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b0b3e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 11], 11 - QUAD $0x0c0b164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 11], 12 - QUAD $0x0b064c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r8 + 11], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e0b3e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 11], 14 - QUAD $0x0b264c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r12 + 11], 15 - QUAD $0x0c2e64203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rsi + r13 + 12], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x0c3e64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rdi + 12], 2 - QUAD $0x0c0e64203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rsi + rcx + 12], 3 - QUAD $0x0c0664203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rsi + rax + 12], 4 - QUAD $0x0c3e64203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rsi + r15 + 12], 5 - QUAD $0x0c3664203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rsi + r14 + 12], 6 - QUAD $0x0c1e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rbx + 12], 7 - QUAD $0x0c1e64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r11 + 12], 8 - QUAD $0x0c1664203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r10 + 12], 9 - QUAD $0x0c0e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r9 + 12], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0c3e64203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rsi + rdi + 12], 11 - QUAD $0x0c1664203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rsi + rdx + 12], 12 - QUAD $0x0c0664203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rsi + r8 + 12], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0c3e64203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rsi + rdi + 12], 14 - QUAD $0x0c2664203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rsi + r12 + 12], 15 - QUAD $0x0d2e54203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r13 + 13], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x020d3e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 13], 2 - QUAD $0x030d0e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 13], 3 - QUAD $0x040d0654203a0f66 // pinsrb xmm2, byte [rsi + rax + 13], 4 - QUAD $0x0d3e54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r15 + 13], 5 - QUAD $0x0d3654203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r14 + 13], 6 - QUAD $0x070d1e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 13], 7 - QUAD $0x0d1e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r11 + 13], 8 - QUAD $0x0d1654203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r10 + 13], 9 - QUAD $0x0d0e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r9 + 13], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b0d3e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 13], 11 - QUAD $0x0c0d1654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 13], 12 - QUAD $0x0d0654203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r8 + 13], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e0d3e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 13], 14 - QUAD $0x0d2654203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r12 + 13], 15 - QUAD $0x0e2e64203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r13 + 14], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x020e3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 14], 2 - QUAD $0x030e0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 14], 3 - QUAD $0x040e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 14], 4 - QUAD $0x0e3e64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r15 + 14], 5 - QUAD $0x0e3664203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r14 + 14], 6 - QUAD $0x070e1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 14], 7 - QUAD $0x0e1e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r11 + 14], 8 - QUAD $0x0e1664203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r10 + 14], 9 - QUAD $0x0e0e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r9 + 14], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b0e3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 14], 11 - QUAD $0x0c0e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 14], 12 - QUAD $0x0e0664203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r8 + 14], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e0e3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 14], 14 - QUAD $0x0e2664203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r12 + 14], 15 - QUAD $0x0f2e74203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r13 + 15], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x020f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 15], 2 - QUAD $0x030f0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 15], 3 - QUAD $0x040f0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 15], 4 - QUAD $0x0f3e74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rsi + r15 + 15], 5 - QUAD $0x0f3674203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r14 + 15], 6 - QUAD $0x070f1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 15], 7 - QUAD $0x0f1e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r11 + 15], 8 - QUAD $0x0f1674203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r10 + 15], 9 - QUAD $0x0f0e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r9 + 15], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b0f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 15], 11 - QUAD $0x0c0f1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 15], 12 - QUAD $0x0f0674203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r8 + 15], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e0f3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 15], 14 - QUAD $0x0f2674203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r12 + 15], 15 - QUAD $0x112e5c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r13 + 17], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x02113e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 17], 2 - QUAD $0x03110e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 17], 3 - QUAD $0x0411065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 17], 4 - QUAD $0x113e5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r15 + 17], 5 - QUAD $0x11365c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r14 + 17], 6 - QUAD $0x07111e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 17], 7 - QUAD $0x111e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r11 + 17], 8 - QUAD $0x11165c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r10 + 17], 9 - QUAD $0x110e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r9 + 17], 10 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b113e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 17], 11 - QUAD $0x0c11165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 17], 12 - QUAD $0x11065c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r8 + 17], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e113e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 17], 14 - QUAD $0x11265c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r12 + 17], 15 - QUAD $0x122e7c203a0f4266; BYTE $0x01 // pinsrb xmm7, byte [rsi + r13 + 18], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x02123e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 18], 2 - QUAD $0x03120e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 18], 3 - QUAD $0x0412067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 18], 4 - QUAD $0x123e7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rsi + r15 + 18], 5 - QUAD $0x12367c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rsi + r14 + 18], 6 - QUAD $0x07121e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 18], 7 - QUAD $0x121e7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r11 + 18], 8 - QUAD $0x12167c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r10 + 18], 9 - QUAD $0x120e7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r9 + 18], 10 - QUAD $0x00000110248c894c // mov qword [rsp + 272], r9 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x0b123e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 18], 11 - QUAD $0x0c12167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 18], 12 - WORD $0x8949; BYTE $0xd7 // mov r15, rdx - QUAD $0x12067c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r8 + 18], 13 - LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] - QUAD $0x12067c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rsi + r8 + 18], 14 - QUAD $0x12267c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r12 + 18], 15 - QUAD $0x132e7c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rsi + r13 + 19], 1 + QUAD $0x072f44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdi + r13 + 7], 14 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x072744203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdi + r12 + 7], 15 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x092744203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rdi + r12 + 9], 1 + QUAD $0x090f44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdi + rcx + 9], 2 + QUAD $0x093744203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rdi + rsi + 9], 3 + QUAD $0x090744203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rdi + rax + 9], 4 + QUAD $0x093744203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rdi + r14 + 9], 5 + QUAD $0x091f44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r11 + 9], 6 + QUAD $0x091744203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r10 + 9], 7 + QUAD $0x090f44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdi + r9 + 9], 8 + QUAD $0x090744203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdi + r8 + 9], 9 + QUAD $0x091f44203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdi + rbx + 9], 10 + QUAD $0x093f44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdi + r15 + 9], 11 + QUAD $0x091744203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rdi + rdx + 9], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x091f44203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rdi + rbx + 9], 13 + QUAD $0x092f44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdi + r13 + 9], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x091f44203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rdi + rbx + 9], 15 + QUAD $0x0a2754203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdi + r12 + 10], 1 + QUAD $0x0a0f54203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdi + rcx + 10], 2 + QUAD $0x0a3754203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdi + rsi + 10], 3 + QUAD $0x0a0754203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdi + rax + 10], 4 + QUAD $0x0a3754203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdi + r14 + 10], 5 + QUAD $0x0a1f54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r11 + 10], 6 + QUAD $0x0a1754203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r10 + 10], 7 + QUAD $0x0a0f54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdi + r9 + 10], 8 + QUAD $0x0a0754203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdi + r8 + 10], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a1f54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdi + rbx + 10], 10 + QUAD $0x0a3f54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r15 + 10], 11 + QUAD $0x0a1754203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdi + rdx + 10], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0a1f54203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdi + rbx + 10], 13 + QUAD $0x0a2f54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdi + r13 + 10], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0a1f54203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdi + rbx + 10], 15 + QUAD $0x0b274c203a0f4266; BYTE $0x01 // pinsrb xmm1, byte [rdi + r12 + 11], 1 + QUAD $0x020b0f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 11], 2 + QUAD $0x030b374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 11], 3 + QUAD $0x040b074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 11], 4 + QUAD $0x0b374c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdi + r14 + 11], 5 + QUAD $0x0b1f4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdi + r11 + 11], 6 + QUAD $0x0b174c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdi + r10 + 11], 7 + QUAD $0x0b0f4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdi + r9 + 11], 8 + QUAD $0x0b074c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdi + r8 + 11], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a0b1f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 11], 10 + QUAD $0x0b3f4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdi + r15 + 11], 11 + QUAD $0x0c0b174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 11], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0d0b1f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 11], 13 + QUAD $0x0b2f4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdi + r13 + 11], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f0b1f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 11], 15 + QUAD $0x0c2764203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdi + r12 + 12], 1 + QUAD $0x0c0f64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdi + rcx + 12], 2 + QUAD $0x0c3764203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdi + rsi + 12], 3 + QUAD $0x0c0764203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdi + rax + 12], 4 + QUAD $0x0c3764203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdi + r14 + 12], 5 + QUAD $0x0c1f64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdi + r11 + 12], 6 + QUAD $0x0c1764203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdi + r10 + 12], 7 + QUAD $0x0c0f64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdi + r9 + 12], 8 + QUAD $0x0c0764203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdi + r8 + 12], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0c1f64203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdi + rbx + 12], 10 + QUAD $0x0c3f64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdi + r15 + 12], 11 + QUAD $0x0c1764203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdi + rdx + 12], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0c1f64203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdi + rbx + 12], 13 + QUAD $0x0c2f64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdi + r13 + 12], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0c1f64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdi + rbx + 12], 15 + QUAD $0x0d2754203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdi + r12 + 13], 1 + QUAD $0x020d0f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 13], 2 + QUAD $0x030d3754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 13], 3 + QUAD $0x040d0754203a0f66 // pinsrb xmm2, byte [rdi + rax + 13], 4 + QUAD $0x0d3754203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdi + r14 + 13], 5 + QUAD $0x0d1f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r11 + 13], 6 + QUAD $0x0d1754203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r10 + 13], 7 + QUAD $0x0d0f54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdi + r9 + 13], 8 + QUAD $0x0d0754203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r8 + 13], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a0d1f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 13], 10 + QUAD $0x0d3f54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdi + r15 + 13], 11 + QUAD $0x0c0d1754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 13], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0d0d1f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 13], 13 + QUAD $0x0d2f54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdi + r13 + 13], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f0d1f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 13], 15 + QUAD $0x0e2764203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdi + r12 + 14], 1 + QUAD $0x020e0f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 14], 2 + QUAD $0x030e3764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 14], 3 + QUAD $0x040e0764203a0f66 // pinsrb xmm4, byte [rdi + rax + 14], 4 + QUAD $0x0e3764203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdi + r14 + 14], 5 + QUAD $0x0e1f64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r11 + 14], 6 + QUAD $0x0e1764203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r10 + 14], 7 + QUAD $0x0e0f64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdi + r9 + 14], 8 + QUAD $0x0e0764203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdi + r8 + 14], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a0e1f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 14], 10 + QUAD $0x0e3f64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r15 + 14], 11 + QUAD $0x0c0e1764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 14], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0d0e1f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 14], 13 + QUAD $0x0e2f64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdi + r13 + 14], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f0e1f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 14], 15 + QUAD $0x0f2774203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdi + r12 + 15], 1 + QUAD $0x020f0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 15], 2 + QUAD $0x030f3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 15], 3 + QUAD $0x040f0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 15], 4 + QUAD $0x0f3774203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdi + r14 + 15], 5 + QUAD $0x0f1f74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r11 + 15], 6 + QUAD $0x0f1774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r10 + 15], 7 + QUAD $0x0f0f74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdi + r9 + 15], 8 + QUAD $0x0f0774203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r8 + 15], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a0f1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 15], 10 + QUAD $0x0f3f74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r15 + 15], 11 + QUAD $0x0c0f1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 15], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0d0f1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 15], 13 + QUAD $0x0f2f74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdi + r13 + 15], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f0f1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 15], 15 + QUAD $0x11275c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdi + r12 + 17], 1 + QUAD $0x02110f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 17], 2 + QUAD $0x0311375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 17], 3 + QUAD $0x0411075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 17], 4 + QUAD $0x11375c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdi + r14 + 17], 5 + QUAD $0x111f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r11 + 17], 6 + QUAD $0x11175c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r10 + 17], 7 + QUAD $0x110f5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdi + r9 + 17], 8 + QUAD $0x11075c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdi + r8 + 17], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a111f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 17], 10 + QUAD $0x113f5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r15 + 17], 11 + QUAD $0x0c11175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 17], 12 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x0d111f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 17], 13 + QUAD $0x112f5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdi + r13 + 17], 14 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f111f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 17], 15 + QUAD $0x12277c203a0f4266; BYTE $0x01 // pinsrb xmm7, byte [rdi + r12 + 18], 1 + QUAD $0x02120f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 18], 2 + QUAD $0x0312377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 18], 3 + QUAD $0x0412077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 18], 4 + QUAD $0x12377c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdi + r14 + 18], 5 + QUAD $0x121f7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r11 + 18], 6 + QUAD $0x12177c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r10 + 18], 7 + QUAD $0x120f7c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdi + r9 + 18], 8 + QUAD $0x12077c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdi + r8 + 18], 9 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0a121f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 18], 10 + QUAD $0x123f7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdi + r15 + 18], 11 + QUAD $0x0c12177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 18], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0d12377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 18], 13 + QUAD $0x122f7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdi + r13 + 18], 14 LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x132e7c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rsi + r13 + 19], 2 - QUAD $0x130e7c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rsi + rcx + 19], 3 - QUAD $0x13067c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rsi + rax + 19], 4 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - QUAD $0x130e7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rcx + 19], 5 - QUAD $0x13367c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rsi + r14 + 19], 6 - QUAD $0x131e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rbx + 19], 7 - QUAD $0x131e7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r11 + 19], 8 - QUAD $0x13167c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r10 + 19], 9 - QUAD $0x130e7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r9 + 19], 10 - QUAD $0x133e7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rsi + rdi + 19], 11 + QUAD $0x122f7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdi + r13 + 18], 15 + QUAD $0x13277c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rdi + r12 + 19], 1 + QUAD $0x130f7c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rcx + 19], 2 + QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] + QUAD $0x130f7c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rdi + rcx + 19], 3 + QUAD $0x13077c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdi + rax + 19], 4 + QUAD $0x13377c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rdi + r14 + 19], 5 + QUAD $0x131f7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r11 + 19], 6 + QUAD $0x13177c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r10 + 19], 7 + QUAD $0x130f7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdi + r9 + 19], 8 + QUAD $0x13077c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r8 + 19], 9 + QUAD $0x131f7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdi + rbx + 19], 10 + QUAD $0x133f7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdi + r15 + 19], 11 LONG $0x6f0f4166; BYTE $0xeb // movdqa xmm5, xmm11 LONG $0xe8640f66 // pcmpgtb xmm5, xmm0 LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI10_6] */ LONG $0xe8df0f66 // pandn xmm5, xmm0 LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 - QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] - LONG $0x0654b60f; BYTE $0x14 // movzx edx, byte [rsi + rax + 20] + QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] + LONG $0x0754b60f; BYTE $0x14 // movzx edx, byte [rdi + rax + 20] LONG $0xc26e0f66 // movd xmm0, edx LONG $0xeb0f4166; BYTE $0xee // por xmm5, xmm14 - LONG $0x6c7f0f66; WORD $0x7024 // movdqa oword [rsp + 112], xmm5 + QUAD $0x0000a024ac7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm5 LONG $0x6f0f4566; BYTE $0xeb // movdqa xmm13, xmm11 LONG $0x640f4566; BYTE $0xe8 // pcmpgtb xmm13, xmm8 - LONG $0x0654b60f; BYTE $0x15 // movzx edx, byte [rsi + rax + 21] + LONG $0x0754b60f; BYTE $0x15 // movzx edx, byte [rdi + rax + 21] LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - QUAD $0x133e7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r15 + 19], 12 + QUAD $0x00000090249c8b48 // mov rbx, qword [rsp + 144] + QUAD $0x131f7c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rdi + rbx + 19], 12 QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI10_16] */ LONG $0xfc0f4566; BYTE $0xe9 // paddb xmm13, xmm9 LONG $0x6f0f4166; BYTE $0xeb // movdqa xmm5, xmm11 LONG $0x640f4166; BYTE $0xea // pcmpgtb xmm5, xmm10 LONG $0x6f0f4566; BYTE $0xcb // movdqa xmm9, xmm11 LONG $0x640f4466; BYTE $0xc9 // pcmpgtb xmm9, xmm1 - LONG $0x0654b60f; BYTE $0x16 // movzx edx, byte [rsi + rax + 22] + LONG $0x0754b60f; BYTE $0x16 // movzx edx, byte [rdi + rax + 22] LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x13167c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rsi + rdx + 19], 13 + QUAD $0x13377c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdi + rsi + 19], 13 + WORD $0x8949; BYTE $0xf7 // mov r15, rsi QUAD $0x00000110addf0f66 // pandn xmm5, oword 272[rbp] /* [rip + .LCPI10_17] */ QUAD $0x0001208ddf0f4466; BYTE $0x00 // pandn xmm9, oword 288[rbp] /* [rip + .LCPI10_18] */ LONG $0xeb0f4466; BYTE $0xcd // por xmm9, xmm5 LONG $0x6f0f4166; BYTE $0xcb // movdqa xmm1, xmm11 LONG $0x640f4166; BYTE $0xcc // pcmpgtb xmm1, xmm12 - LONG $0x0654b60f; BYTE $0x17 // movzx edx, byte [rsi + rax + 23] + LONG $0x0754b60f; BYTE $0x17 // movzx edx, byte [rdi + rax + 23] LONG $0xea6e0f66 // movd xmm5, edx QUAD $0x000001308ddf0f66 // pandn xmm1, oword 304[rbp] /* [rip + .LCPI10_19] */ LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 - LONG $0x0654b60f; BYTE $0x19 // movzx edx, byte [rsi + rax + 25] + LONG $0x0754b60f; BYTE $0x19 // movzx edx, byte [rdi + rax + 25] LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx - QUAD $0x13067c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r8 + 19], 14 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x13377c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdi + rsi + 19], 14 QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI10_22] */ LONG $0xeb0f4166; BYTE $0xcd // por xmm1, xmm13 LONG $0x6f0f4566; BYTE $0xf3 // movdqa xmm14, xmm11 LONG $0x640f4466; BYTE $0xf2 // pcmpgtb xmm14, xmm2 LONG $0x6f0f4566; BYTE $0xeb // movdqa xmm13, xmm11 LONG $0x640f4466; BYTE $0xec // pcmpgtb xmm13, xmm4 - LONG $0x0654b60f; BYTE $0x1a // movzx edx, byte [rsi + rax + 26] + LONG $0x0754b60f; BYTE $0x1a // movzx edx, byte [rdi + rax + 26] LONG $0x6e0f4466; BYTE $0xe2 // movd xmm12, edx - QUAD $0x13267c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r12 + 19], 15 + QUAD $0x132f7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r13 + 19], 15 QUAD $0x000140b5df0f4466; BYTE $0x00 // pandn xmm14, oword 320[rbp] /* [rip + .LCPI10_20] */ QUAD $0x000150addf0f4466; BYTE $0x00 // pandn xmm13, oword 336[rbp] /* [rip + .LCPI10_21] */ LONG $0xeb0f4566; BYTE $0xee // por xmm13, xmm14 LONG $0x6f0f4166; BYTE $0xe3 // movdqa xmm4, xmm11 LONG $0x6f0f4566; BYTE $0xf3 // movdqa xmm14, xmm11 LONG $0x640f4466; BYTE $0xf6 // pcmpgtb xmm14, xmm6 - LONG $0x0654b60f; BYTE $0x1b // movzx edx, byte [rsi + rax + 27] + LONG $0x0754b60f; BYTE $0x1b // movzx edx, byte [rdi + rax + 27] LONG $0xd26e0f66 // movd xmm2, edx LONG $0xdf0f4466; WORD $0x6075 // pandn xmm14, oword 96[rbp] /* [rip + .LCPI10_6] */ LONG $0xeb0f4566; BYTE $0xf5 // por xmm14, xmm13 - LONG $0x0654b60f; BYTE $0x1c // movzx edx, byte [rsi + rax + 28] + LONG $0x0754b60f; BYTE $0x1c // movzx edx, byte [rdi + rax + 28] LONG $0xf26e0f66 // movd xmm6, edx LONG $0xeb0f4466; BYTE $0xf1 // por xmm14, xmm1 LONG $0x640f4466; BYTE $0xdb // pcmpgtb xmm11, xmm3 - LONG $0x0654b60f; BYTE $0x1d // movzx edx, byte [rsi + rax + 29] + LONG $0x0754b60f; BYTE $0x1d // movzx edx, byte [rdi + rax + 29] LONG $0xda6e0f66 // movd xmm3, edx QUAD $0x0001009ddf0f4466; BYTE $0x00 // pandn xmm11, oword 256[rbp] /* [rip + .LCPI10_16] */ - QUAD $0x0150249cfc0f4466; WORD $0x0000 // paddb xmm11, oword [rsp + 336] + QUAD $0x0120249cfc0f4466; WORD $0x0000 // paddb xmm11, oword [rsp + 288] LONG $0xcc6f0f66 // movdqa xmm1, xmm4 LONG $0xcf640f66 // pcmpgtb xmm1, xmm7 LONG $0x6f0f4466; BYTE $0xec // movdqa xmm13, xmm4 LONG $0xfc6f0f66 // movdqa xmm7, xmm4 LONG $0x640f4566; BYTE $0xef // pcmpgtb xmm13, xmm15 - LONG $0x0654b60f; BYTE $0x1e // movzx edx, byte [rsi + rax + 30] + LONG $0x0754b60f; BYTE $0x1e // movzx edx, byte [rdi + rax + 30] LONG $0xe26e0f66 // movd xmm4, edx - LONG $0x0654b60f; BYTE $0x1f // movzx edx, byte [rsi + rax + 31] + LONG $0x0754b60f; BYTE $0x1f // movzx edx, byte [rdi + rax + 31] QUAD $0x000001108ddf0f66 // pandn xmm1, oword 272[rbp] /* [rip + .LCPI10_17] */ QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI10_18] */ LONG $0xeb0f4466; BYTE $0xe9 // por xmm13, xmm1 LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x01140644203a0f66 // pinsrb xmm0, byte [rsi + rax + 20], 1 - QUAD $0x150644203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rax + 21], 1 - QUAD $0x160654203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rax + 22], 1 - QUAD $0x0117066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 23], 1 - QUAD $0x19064c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rax + 25], 1 - QUAD $0x1a0664203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rsi + rax + 26], 1 - QUAD $0x011b0654203a0f66 // pinsrb xmm2, byte [rsi + rax + 27], 1 - QUAD $0x011c0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 28], 1 - QUAD $0x011d065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 29], 1 - QUAD $0x011e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 30], 1 - QUAD $0x1f067c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rax + 31], 1 - QUAD $0x142e44203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rsi + r13 + 20], 2 - QUAD $0x152e44203a0f4666; BYTE $0x02 // pinsrb xmm8, byte [rsi + r13 + 21], 2 - QUAD $0x162e54203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r13 + 22], 2 - QUAD $0x172e6c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rsi + r13 + 23], 2 - QUAD $0x192e4c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rsi + r13 + 25], 2 - QUAD $0x1a2e64203a0f4666; BYTE $0x02 // pinsrb xmm12, byte [rsi + r13 + 26], 2 - QUAD $0x1b2e54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rsi + r13 + 27], 2 - QUAD $0x1c2e74203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rsi + r13 + 28], 2 - QUAD $0x1d2e5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rsi + r13 + 29], 2 - QUAD $0x1e2e64203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rsi + r13 + 30], 2 - QUAD $0x1f2e7c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rsi + r13 + 31], 2 - QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] - QUAD $0x03141644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 20], 3 - QUAD $0x151644203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rsi + rdx + 21], 3 - QUAD $0x161654203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rsi + rdx + 22], 3 - QUAD $0x0317166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 23], 3 - QUAD $0x19164c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rsi + rdx + 25], 3 - QUAD $0x1a1664203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rsi + rdx + 26], 3 - QUAD $0x031b1654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 27], 3 - QUAD $0x031c1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 28], 3 - QUAD $0x031d165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 29], 3 - QUAD $0x031e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 30], 3 - QUAD $0x1f167c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rsi + rdx + 31], 3 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x142744203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdi + r12 + 20], 1 + QUAD $0x152744203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rdi + r12 + 21], 1 + QUAD $0x162754203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdi + r12 + 22], 1 + QUAD $0x17276c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdi + r12 + 23], 1 + QUAD $0x19274c203a0f4666; BYTE $0x01 // pinsrb xmm9, byte [rdi + r12 + 25], 1 + QUAD $0x1a2764203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdi + r12 + 26], 1 + QUAD $0x1b2754203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdi + r12 + 27], 1 + QUAD $0x1c2774203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdi + r12 + 28], 1 + QUAD $0x1d275c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdi + r12 + 29], 1 + QUAD $0x1e2764203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdi + r12 + 30], 1 + QUAD $0x1f277c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rdi + r12 + 31], 1 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x02140744203a0f66 // pinsrb xmm0, byte [rdi + rax + 20], 2 + QUAD $0x150744203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdi + rax + 21], 2 + QUAD $0x160754203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdi + rax + 22], 2 + QUAD $0x0217076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 23], 2 + QUAD $0x19074c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdi + rax + 25], 2 + QUAD $0x1a0764203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdi + rax + 26], 2 + QUAD $0x021b0754203a0f66 // pinsrb xmm2, byte [rdi + rax + 27], 2 + QUAD $0x021c0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 28], 2 + QUAD $0x021d075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 29], 2 + QUAD $0x021e0764203a0f66 // pinsrb xmm4, byte [rdi + rax + 30], 2 + QUAD $0x1f077c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rax + 31], 2 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + QUAD $0x03140f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 20], 3 + QUAD $0x150f44203a0f4466; BYTE $0x03 // pinsrb xmm8, byte [rdi + rcx + 21], 3 + QUAD $0x160f54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdi + rcx + 22], 3 + QUAD $0x03170f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 23], 3 + QUAD $0x190f4c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rdi + rcx + 25], 3 + QUAD $0x1a0f64203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdi + rcx + 26], 3 + QUAD $0x031b0f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 27], 3 + QUAD $0x031c0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 28], 3 + QUAD $0x031d0f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 29], 3 + QUAD $0x031e0f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 30], 3 + QUAD $0x1f0f7c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rdi + rcx + 31], 3 QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] - QUAD $0x04141644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 20], 4 - QUAD $0x151644203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rdx + 21], 4 - QUAD $0x161654203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rdx + 22], 4 - QUAD $0x0417166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 23], 4 - QUAD $0x19164c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rsi + rdx + 25], 4 - QUAD $0x1a1664203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rsi + rdx + 26], 4 - QUAD $0x041b1654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 27], 4 - QUAD $0x041c1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 28], 4 - QUAD $0x041d165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 29], 4 - QUAD $0x041e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 30], 4 - QUAD $0x1f167c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rsi + rdx + 31], 4 - QUAD $0x05140e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 20], 5 - QUAD $0x150e44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rsi + rcx + 21], 5 - QUAD $0x160e54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rsi + rcx + 22], 5 - QUAD $0x05170e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 23], 5 - QUAD $0x190e4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rsi + rcx + 25], 5 - QUAD $0x1a0e64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rsi + rcx + 26], 5 - QUAD $0x051b0e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 27], 5 - QUAD $0x051c0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 28], 5 - QUAD $0x051d0e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 29], 5 - QUAD $0x051e0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 30], 5 - QUAD $0x1f0e7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rcx + 31], 5 - QUAD $0x143644203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rsi + r14 + 20], 6 - QUAD $0x153644203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rsi + r14 + 21], 6 - QUAD $0x163654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r14 + 22], 6 - QUAD $0x17366c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r14 + 23], 6 - QUAD $0x19364c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rsi + r14 + 25], 6 - QUAD $0x1a3664203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rsi + r14 + 26], 6 - QUAD $0x1b3654203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r14 + 27], 6 - QUAD $0x1c3674203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r14 + 28], 6 - QUAD $0x1d365c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r14 + 29], 6 - QUAD $0x1e3664203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r14 + 30], 6 - QUAD $0x1f367c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rsi + r14 + 31], 6 - QUAD $0x07141e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 20], 7 - QUAD $0x151e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rbx + 21], 7 - QUAD $0x161e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rbx + 22], 7 - QUAD $0x07171e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 23], 7 - QUAD $0x191e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rbx + 25], 7 - QUAD $0x1a1e64203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rsi + rbx + 26], 7 - QUAD $0x071b1e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 27], 7 - QUAD $0x071c1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 28], 7 - QUAD $0x071d1e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 29], 7 - QUAD $0x071e1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 30], 7 - QUAD $0x1f1e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rbx + 31], 7 - QUAD $0x141e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r11 + 20], 8 - QUAD $0x151e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r11 + 21], 8 - QUAD $0x161e54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r11 + 22], 8 - QUAD $0x171e6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r11 + 23], 8 - QUAD $0x191e4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r11 + 25], 8 - QUAD $0x1a1e64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r11 + 26], 8 - QUAD $0x1b1e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r11 + 27], 8 - QUAD $0x1c1e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r11 + 28], 8 - QUAD $0x1d1e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r11 + 29], 8 - QUAD $0x1e1e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r11 + 30], 8 - QUAD $0x1f1e7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r11 + 31], 8 - QUAD $0x141644203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r10 + 20], 9 - QUAD $0x151644203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r10 + 21], 9 - QUAD $0x161654203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r10 + 22], 9 - QUAD $0x17166c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r10 + 23], 9 - QUAD $0x19164c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r10 + 25], 9 - QUAD $0x1a1664203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r10 + 26], 9 - QUAD $0x1b1654203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r10 + 27], 9 - QUAD $0x1c1674203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r10 + 28], 9 - QUAD $0x1d165c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r10 + 29], 9 - QUAD $0x1e1664203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r10 + 30], 9 - QUAD $0x1f167c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r10 + 31], 9 - QUAD $0x0000011024948b4c // mov r10, qword [rsp + 272] - QUAD $0x141644203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r10 + 20], 10 - QUAD $0x151644203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r10 + 21], 10 - QUAD $0x161654203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r10 + 22], 10 - QUAD $0x17166c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r10 + 23], 10 - QUAD $0x19164c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r10 + 25], 10 - QUAD $0x1a1664203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r10 + 26], 10 - QUAD $0x1b1654203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r10 + 27], 10 - QUAD $0x1c1674203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r10 + 28], 10 - QUAD $0x1d165c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r10 + 29], 10 - QUAD $0x1e1664203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r10 + 30], 10 - QUAD $0x1f167c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r10 + 31], 10 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x141644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r10 + 20], 11 - QUAD $0x151644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r10 + 21], 11 - QUAD $0x161654203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r10 + 22], 11 - QUAD $0x17166c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r10 + 23], 11 - QUAD $0x19164c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r10 + 25], 11 - QUAD $0x1a1664203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r10 + 26], 11 - QUAD $0x1b1654203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r10 + 27], 11 - QUAD $0x1c1674203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r10 + 28], 11 - QUAD $0x1d165c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r10 + 29], 11 - QUAD $0x1e1664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r10 + 30], 11 - QUAD $0x1f167c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r10 + 31], 11 - QUAD $0x143e44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r15 + 20], 12 - QUAD $0x153e44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r15 + 21], 12 - QUAD $0x163e54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r15 + 22], 12 - QUAD $0x173e6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r15 + 23], 12 - QUAD $0x193e4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r15 + 25], 12 - QUAD $0x1a3e64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rsi + r15 + 26], 12 - QUAD $0x1b3e54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r15 + 27], 12 - QUAD $0x1c3e74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r15 + 28], 12 - QUAD $0x1d3e5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r15 + 29], 12 - QUAD $0x1e3e64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r15 + 30], 12 - QUAD $0x1f3e7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r15 + 31], 12 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x0d140644203a0f66 // pinsrb xmm0, byte [rsi + rax + 20], 13 - QUAD $0x150644203a0f4466; BYTE $0x0d // pinsrb xmm8, byte [rsi + rax + 21], 13 - QUAD $0x160654203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rsi + rax + 22], 13 - QUAD $0x0d17066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 23], 13 - QUAD $0x19064c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rsi + rax + 25], 13 - QUAD $0x1a0664203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rsi + rax + 26], 13 - QUAD $0x0d1b0654203a0f66 // pinsrb xmm2, byte [rsi + rax + 27], 13 - QUAD $0x0d1c0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 28], 13 - QUAD $0x0d1d065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 29], 13 - QUAD $0x0d1e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 30], 13 - QUAD $0x1f067c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rsi + rax + 31], 13 - QUAD $0x140644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r8 + 20], 14 - QUAD $0x150644203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rsi + r8 + 21], 14 - QUAD $0x160654203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rsi + r8 + 22], 14 - QUAD $0x17066c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rsi + r8 + 23], 14 - QUAD $0x19064c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rsi + r8 + 25], 14 - QUAD $0x1a0664203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r8 + 26], 14 - QUAD $0x1b0654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r8 + 27], 14 - QUAD $0x1c0674203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r8 + 28], 14 - QUAD $0x1d065c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rsi + r8 + 29], 14 - QUAD $0x1e0664203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r8 + 30], 14 - QUAD $0x1f067c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r8 + 31], 14 - QUAD $0x142644203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r12 + 20], 15 - QUAD $0x152644203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r12 + 21], 15 - QUAD $0x162654203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r12 + 22], 15 - QUAD $0x17266c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r12 + 23], 15 - QUAD $0x19264c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r12 + 25], 15 - QUAD $0x1a2664203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rsi + r12 + 26], 15 + QUAD $0x04141744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 20], 4 + QUAD $0x151744203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rdi + rdx + 21], 4 + QUAD $0x161754203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdi + rdx + 22], 4 + QUAD $0x0417176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 23], 4 + QUAD $0x19174c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdi + rdx + 25], 4 + QUAD $0x1a1764203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdi + rdx + 26], 4 + QUAD $0x041b1754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 27], 4 + QUAD $0x041c1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 28], 4 + QUAD $0x041d175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 29], 4 + QUAD $0x041e1764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 30], 4 + QUAD $0x1f177c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdi + rdx + 31], 4 + QUAD $0x143744203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdi + r14 + 20], 5 + QUAD $0x153744203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rdi + r14 + 21], 5 + QUAD $0x163754203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdi + r14 + 22], 5 + QUAD $0x17376c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rdi + r14 + 23], 5 + QUAD $0x19374c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdi + r14 + 25], 5 + QUAD $0x1a3764203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdi + r14 + 26], 5 + QUAD $0x1b3754203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdi + r14 + 27], 5 + QUAD $0x1c3774203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdi + r14 + 28], 5 + QUAD $0x1d375c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdi + r14 + 29], 5 + QUAD $0x1e3764203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdi + r14 + 30], 5 + QUAD $0x1f377c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rdi + r14 + 31], 5 + QUAD $0x141f44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r11 + 20], 6 + QUAD $0x151f44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r11 + 21], 6 + QUAD $0x161f54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r11 + 22], 6 + QUAD $0x171f6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r11 + 23], 6 + QUAD $0x191f4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r11 + 25], 6 + QUAD $0x1a1f64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdi + r11 + 26], 6 + QUAD $0x1b1f54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r11 + 27], 6 + QUAD $0x1c1f74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r11 + 28], 6 + QUAD $0x1d1f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r11 + 29], 6 + QUAD $0x1e1f64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r11 + 30], 6 + QUAD $0x1f1f7c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r11 + 31], 6 + LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] + QUAD $0x141744203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r10 + 20], 7 + QUAD $0x151744203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r10 + 21], 7 + QUAD $0x161754203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r10 + 22], 7 + QUAD $0x17176c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r10 + 23], 7 + QUAD $0x19174c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r10 + 25], 7 + QUAD $0x1a1764203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdi + r10 + 26], 7 + QUAD $0x1b1754203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r10 + 27], 7 + QUAD $0x1c1774203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r10 + 28], 7 + QUAD $0x1d175c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r10 + 29], 7 + QUAD $0x1e1764203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r10 + 30], 7 + QUAD $0x1f177c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r10 + 31], 7 + QUAD $0x140f44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdi + r9 + 20], 8 + QUAD $0x150f44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdi + r9 + 21], 8 + QUAD $0x160f54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdi + r9 + 22], 8 + QUAD $0x170f6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdi + r9 + 23], 8 + QUAD $0x190f4c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdi + r9 + 25], 8 + QUAD $0x1a0f64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdi + r9 + 26], 8 + QUAD $0x1b0f54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdi + r9 + 27], 8 + QUAD $0x1c0f74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdi + r9 + 28], 8 + QUAD $0x1d0f5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdi + r9 + 29], 8 + QUAD $0x1e0f64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdi + r9 + 30], 8 + QUAD $0x1f0f7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdi + r9 + 31], 8 + QUAD $0x140744203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdi + r8 + 20], 9 + QUAD $0x150744203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdi + r8 + 21], 9 + QUAD $0x160754203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdi + r8 + 22], 9 + QUAD $0x17076c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r8 + 23], 9 + QUAD $0x19074c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdi + r8 + 25], 9 + QUAD $0x1a0764203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdi + r8 + 26], 9 + QUAD $0x1b0754203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r8 + 27], 9 + QUAD $0x1c0774203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r8 + 28], 9 + QUAD $0x1d075c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdi + r8 + 29], 9 + QUAD $0x1e0764203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdi + r8 + 30], 9 + QUAD $0x1f077c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r8 + 31], 9 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x143744203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdi + r14 + 20], 10 + QUAD $0x153744203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdi + r14 + 21], 10 + QUAD $0x163754203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdi + r14 + 22], 10 + QUAD $0x17376c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r14 + 23], 10 + QUAD $0x19374c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdi + r14 + 25], 10 + QUAD $0x1a3764203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdi + r14 + 26], 10 + QUAD $0x1b3754203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r14 + 27], 10 + QUAD $0x1c3774203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdi + r14 + 28], 10 + QUAD $0x1d375c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdi + r14 + 29], 10 + QUAD $0x1e3764203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdi + r14 + 30], 10 + QUAD $0x1f377c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdi + r14 + 31], 10 + QUAD $0x0000013024b48b4c // mov r14, qword [rsp + 304] + QUAD $0x143744203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdi + r14 + 20], 11 + QUAD $0x153744203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdi + r14 + 21], 11 + QUAD $0x163754203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r14 + 22], 11 + QUAD $0x17376c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdi + r14 + 23], 11 + QUAD $0x19374c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdi + r14 + 25], 11 + QUAD $0x1a3764203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdi + r14 + 26], 11 + QUAD $0x1b3754203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdi + r14 + 27], 11 + QUAD $0x1c3774203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r14 + 28], 11 + QUAD $0x1d375c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r14 + 29], 11 + QUAD $0x1e3764203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r14 + 30], 11 + QUAD $0x1f377c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdi + r14 + 31], 11 + QUAD $0x0c141f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 20], 12 + QUAD $0x151f44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rdi + rbx + 21], 12 + QUAD $0x161f54203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdi + rbx + 22], 12 + QUAD $0x0c171f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 23], 12 + QUAD $0x191f4c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rdi + rbx + 25], 12 + QUAD $0x1a1f64203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdi + rbx + 26], 12 + QUAD $0x0c1b1f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 27], 12 + QUAD $0x0c1c1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 28], 12 + QUAD $0x0c1d1f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 29], 12 + QUAD $0x0c1e1f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 30], 12 + QUAD $0x1f1f7c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rdi + rbx + 31], 12 + QUAD $0x143f44203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdi + r15 + 20], 13 + QUAD $0x153f44203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rdi + r15 + 21], 13 + QUAD $0x163f54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdi + r15 + 22], 13 + QUAD $0x173f6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdi + r15 + 23], 13 + QUAD $0x193f4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rdi + r15 + 25], 13 + QUAD $0x1a3f64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdi + r15 + 26], 13 + QUAD $0x1b3f54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdi + r15 + 27], 13 + QUAD $0x1c3f74203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdi + r15 + 28], 13 + QUAD $0x1d3f5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdi + r15 + 29], 13 + QUAD $0x1e3f64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdi + r15 + 30], 13 + QUAD $0x1f3f7c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdi + r15 + 31], 13 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x0e143744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 20], 14 + QUAD $0x153744203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdi + rsi + 21], 14 + QUAD $0x163754203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rdi + rsi + 22], 14 + QUAD $0x0e17376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 23], 14 + QUAD $0x19374c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdi + rsi + 25], 14 + QUAD $0x1a3764203a0f4466; BYTE $0x0e // pinsrb xmm12, byte [rdi + rsi + 26], 14 + QUAD $0x0e1b3754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 27], 14 + QUAD $0x0e1c3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 28], 14 + QUAD $0x0e1d375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 29], 14 + QUAD $0x0e1e3764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 30], 14 + QUAD $0x1f377c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdi + rsi + 31], 14 + QUAD $0x142f44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdi + r13 + 20], 15 + QUAD $0x152f44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdi + r13 + 21], 15 + QUAD $0x162f54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdi + r13 + 22], 15 + QUAD $0x172f6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdi + r13 + 23], 15 + QUAD $0x192f4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdi + r13 + 25], 15 + QUAD $0x1a2f64203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdi + r13 + 26], 15 LONG $0xcf6f0f66 // movdqa xmm1, xmm7 LONG $0xc8640f66 // pcmpgtb xmm1, xmm0 - QUAD $0x1b2654203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r12 + 27], 15 + QUAD $0x1b2f54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r13 + 27], 15 QUAD $0x000001308ddf0f66 // pandn xmm1, oword 304[rbp] /* [rip + .LCPI10_19] */ LONG $0xeb0f4166; BYTE $0xcd // por xmm1, xmm13 LONG $0x760f4566; BYTE $0xed // pcmpeqd xmm13, xmm13 @@ -52073,16 +54688,16 @@ LBB10_86: LONG $0xf8eb0f66 // por xmm7, xmm0 LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 LONG $0xc5640f66 // pcmpgtb xmm0, xmm5 - QUAD $0x1c2674203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r12 + 28], 15 + QUAD $0x1c2f74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdi + r13 + 28], 15 LONG $0x6d6f0f66; BYTE $0x60 // movdqa xmm5, oword 96[rbp] /* [rip + .LCPI10_6] */ LONG $0xc5df0f66 // pandn xmm0, xmm5 LONG $0xc7eb0f66 // por xmm0, xmm7 - QUAD $0x1d265c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r12 + 29], 15 + QUAD $0x1d2f5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdi + r13 + 29], 15 LONG $0xc1eb0f66 // por xmm0, xmm1 LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 LONG $0x640f4166; BYTE $0xc9 // pcmpgtb xmm1, xmm9 QUAD $0x000001008ddf0f66 // pandn xmm1, oword 256[rbp] /* [rip + .LCPI10_16] */ - QUAD $0x000120248cfc0f66; BYTE $0x00 // paddb xmm1, oword [rsp + 288] + QUAD $0x000100248cfc0f66; BYTE $0x00 // paddb xmm1, oword [rsp + 256] LONG $0x6f0f4166; BYTE $0xe8 // movdqa xmm5, xmm8 LONG $0x640f4166; BYTE $0xec // pcmpgtb xmm5, xmm12 LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 @@ -52092,7 +54707,7 @@ LBB10_86: LONG $0xfdeb0f66 // por xmm7, xmm5 LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 LONG $0xd6640f66 // pcmpgtb xmm2, xmm6 - QUAD $0x1e2664203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r12 + 30], 15 + QUAD $0x1e2f64203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdi + r13 + 30], 15 QUAD $0x0000013095df0f66 // pandn xmm2, oword 304[rbp] /* [rip + .LCPI10_19] */ LONG $0xd7eb0f66 // por xmm2, xmm7 LONG $0xf80f4166; BYTE $0xcd // psubb xmm1, xmm13 @@ -52101,8 +54716,7 @@ LBB10_86: LONG $0xcb640f66 // pcmpgtb xmm1, xmm3 LONG $0x6f0f4166; BYTE $0xd8 // movdqa xmm3, xmm8 LONG $0xdc640f66 // pcmpgtb xmm3, xmm4 - QUAD $0x1f267c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r12 + 31], 15 - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] + QUAD $0x1f2f7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r13 + 31], 15 LONG $0xdf0f4166; BYTE $0xca // pandn xmm1, xmm10 LONG $0xdf0f4166; BYTE $0xdb // pandn xmm3, xmm11 LONG $0xd9eb0f66 // por xmm3, xmm1 @@ -52113,7 +54727,7 @@ LBB10_86: LONG $0xcaeb0f66 // por xmm1, xmm2 LONG $0xd06f0f66 // movdqa xmm2, xmm0 LONG $0xd1600f66 // punpcklbw xmm2, xmm1 - LONG $0x6c6f0f66; WORD $0x7024 // movdqa xmm5, oword [rsp + 112] + QUAD $0x0000a024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 160] LONG $0xdd6f0f66 // movdqa xmm3, xmm5 LONG $0x600f4166; BYTE $0xde // punpcklbw xmm3, xmm14 LONG $0xe36f0f66 // movdqa xmm4, xmm3 @@ -52124,290 +54738,290 @@ LBB10_86: LONG $0xcd6f0f66 // movdqa xmm1, xmm5 LONG $0xc8610f66 // punpcklwd xmm1, xmm0 LONG $0xe8690f66 // punpckhwd xmm5, xmm0 - QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] - LONG $0x7f0f41f3; WORD $0x8e6c; BYTE $0x30 // movdqu oword [r14 + 4*rcx + 48], xmm5 - LONG $0x7f0f41f3; WORD $0x8e4c; BYTE $0x20 // movdqu oword [r14 + 4*rcx + 32], xmm1 - LONG $0x7f0f41f3; WORD $0x8e5c; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm3 - LONG $0x7f0f41f3; WORD $0x8e24 // movdqu oword [r14 + 4*rcx], xmm4 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + LONG $0x7f0f41f3; WORD $0x8c6c; BYTE $0x30 // movdqu oword [r12 + 4*rcx + 48], xmm5 + LONG $0x7f0f41f3; WORD $0x8c4c; BYTE $0x20 // movdqu oword [r12 + 4*rcx + 32], xmm1 + LONG $0x7f0f41f3; WORD $0x8c5c; BYTE $0x10 // movdqu oword [r12 + 4*rcx + 16], xmm3 + LONG $0x7f0f41f3; WORD $0x8c24 // movdqu oword [r12 + 4*rcx], xmm4 LONG $0x10c18348 // add rcx, 16 WORD $0x8949; BYTE $0xc8 // mov r8, rcx - QUAD $0x000000f0248c3b48 // cmp rcx, qword [rsp + 240] - JNE LBB10_86 - QUAD $0x000001b024bc8b4c // mov r15, qword [rsp + 432] - QUAD $0x000000f024bc3b4c // cmp r15, qword [rsp + 240] - LONG $0x245c8a44; BYTE $0x08 // mov r11b, byte [rsp + 8] - QUAD $0x0000017024b48b48 // mov rsi, qword [rsp + 368] - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - JNE LBB10_88 - JMP LBB10_91 + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + JNE LBB10_99 + QUAD $0x00000190248c8b48 // mov rcx, qword [rsp + 400] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + LONG $0x243c8a44 // mov r15b, byte [rsp] + QUAD $0x0000017824b48b48 // mov rsi, qword [rsp + 376] + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + JNE LBB10_101 + JMP LBB10_104 -LBB10_66: - LONG $0xf0e78349 // and r15, -16 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 +LBB10_72: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xf0 // add rax, rsi - QUAD $0x0000018824848948 // mov qword [rsp + 392], rax - QUAD $0x000001a024bc894c // mov qword [rsp + 416], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax - LONG $0xc3b60f41 // movzx eax, r11b + WORD $0x0148; BYTE $0xf8 // add rax, rdi + QUAD $0x000001c024848948 // mov qword [rsp + 448], rax + QUAD $0x00000180248c8948 // mov qword [rsp + 384], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x0000019024848948 // mov qword [rsp + 400], rax + LONG $0xc5b60f41 // movzx eax, r13b LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000190248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 400], xmm1 + QUAD $0x0001a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 416], xmm1 WORD $0xc031 // xor eax, eax - QUAD $0x0000016024b4894c // mov qword [rsp + 352], r14 + LONG $0x2464894c; BYTE $0x08 // mov qword [rsp + 8], r12 -LBB10_67: - WORD $0x8949; BYTE $0xc1 // mov r9, rax +LBB10_73: + WORD $0x8948; BYTE $0xc1 // mov rcx, rax QUAD $0x0000015024848948 // mov qword [rsp + 336], rax - LONG $0x05e1c149 // shl r9, 5 - WORD $0x894c; BYTE $0xcb // mov rbx, r9 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - WORD $0x894c; BYTE $0xca // mov rdx, r9 - LONG $0x244c894c; BYTE $0x30 // mov qword [rsp + 48], r9 - WORD $0x894d; BYTE $0xce // mov r14, r9 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - WORD $0x894d; BYTE $0xca // mov r10, r9 - WORD $0x894d; BYTE $0xcc // mov r12, r9 - WORD $0x894d; BYTE $0xcb // mov r11, r9 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - QUAD $0x000000d0248c894c // mov qword [rsp + 208], r9 - LONG $0x0cb60f42; BYTE $0x0e // movzx ecx, byte [rsi + r9] - LONG $0xc16e0f66 // movd xmm0, ecx - LONG $0x4cb60f42; WORD $0x010e // movzx ecx, byte [rsi + r9 + 1] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x4cb60f42; WORD $0x020e // movzx ecx, byte [rsi + r9 + 2] - LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x4cb60f42; WORD $0x030e // movzx ecx, byte [rsi + r9 + 3] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x4cb60f42; WORD $0x040e // movzx ecx, byte [rsi + r9 + 4] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x4cb60f42; WORD $0x050e // movzx ecx, byte [rsi + r9 + 5] - LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x4cb60f42; WORD $0x060e // movzx ecx, byte [rsi + r9 + 6] - LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x4cb60f42; WORD $0x070e // movzx ecx, byte [rsi + r9 + 7] - LONG $0xd16e0f66 // movd xmm2, ecx - QUAD $0x00014024947f0f66; BYTE $0x00 // movdqa oword [rsp + 320], xmm2 - LONG $0x4cb60f42; WORD $0x080e // movzx ecx, byte [rsi + r9 + 8] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x4cb60f42; WORD $0x090e // movzx ecx, byte [rsi + r9 + 9] - LONG $0xd16e0f66 // movd xmm2, ecx - QUAD $0x00011024947f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm2 - LONG $0x4cb60f42; WORD $0x0a0e // movzx ecx, byte [rsi + r9 + 10] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x4cb60f42; WORD $0x0b0e // movzx ecx, byte [rsi + r9 + 11] - LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x4cb60f42; WORD $0x0c0e // movzx ecx, byte [rsi + r9 + 12] - LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x4cb60f42; WORD $0x100e // movzx ecx, byte [rsi + r9 + 16] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x4cb60f42; WORD $0x180e // movzx ecx, byte [rsi + r9 + 24] - LONG $0xd16e0f66 // movd xmm2, ecx - QUAD $0x00000090248c894c // mov qword [rsp + 144], r9 - WORD $0x894d; BYTE $0xcf // mov r15, r9 - LONG $0x20cf8349 // or r15, 32 - LONG $0x247c894c; BYTE $0x50 // mov qword [rsp + 80], r15 - LONG $0x40cb8348 // or rbx, 64 - QUAD $0x00000080249c8948 // mov qword [rsp + 128], rbx - LONG $0x60cf8348 // or rdi, 96 - QUAD $0x000000c024bc8948 // mov qword [rsp + 192], rdi - LONG $0x80ca8148; WORD $0x0000; BYTE $0x00 // or rdx, 128 - LONG $0x24548948; BYTE $0x70 // mov qword [rsp + 112], rdx - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - LONG $0xa0c98148; WORD $0x0000; BYTE $0x00 // or rcx, 160 - LONG $0xc0ce8149; WORD $0x0000; BYTE $0x00 // or r14, 192 - LONG $0xe0c88149; WORD $0x0000; BYTE $0x00 // or r8, 224 - LONG $0x00ca8149; WORD $0x0001; BYTE $0x00 // or r10, 256 - LONG $0x20cc8149; WORD $0x0001; BYTE $0x00 // or r12, 288 - LONG $0x40cb8149; WORD $0x0001; BYTE $0x00 // or r11, 320 - LONG $0x60cd8149; WORD $0x0001; BYTE $0x00 // or r13, 352 - QUAD $0x000000a024ac894c // mov qword [rsp + 160], r13 - QUAD $0x000000d024ac8b4c // mov r13, qword [rsp + 208] + LONG $0x05e1c148 // shl rcx, 5 + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + WORD $0x8948; BYTE $0xce // mov rsi, rcx + WORD $0x8949; BYTE $0xcb // mov r11, rcx + WORD $0x8949; BYTE $0xce // mov r14, rcx + WORD $0x8949; BYTE $0xca // mov r10, rcx + WORD $0x8949; BYTE $0xcf // mov r15, rcx + WORD $0x8948; BYTE $0xcb // mov rbx, rcx + WORD $0x8949; BYTE $0xcd // mov r13, rcx + LONG $0x0f04b60f // movzx eax, byte [rdi + rcx] + LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x0f44b60f; BYTE $0x01 // movzx eax, byte [rdi + rcx + 1] + LONG $0x6e0f4466; BYTE $0xd8 // movd xmm11, eax + LONG $0x0f44b60f; BYTE $0x02 // movzx eax, byte [rdi + rcx + 2] + LONG $0x6e0f4466; BYTE $0xf0 // movd xmm14, eax + LONG $0x0f44b60f; BYTE $0x03 // movzx eax, byte [rdi + rcx + 3] + LONG $0xe86e0f66 // movd xmm5, eax + LONG $0x0f44b60f; BYTE $0x04 // movzx eax, byte [rdi + rcx + 4] + LONG $0xd86e0f66 // movd xmm3, eax + LONG $0x0f44b60f; BYTE $0x05 // movzx eax, byte [rdi + rcx + 5] + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x0f44b60f; BYTE $0x06 // movzx eax, byte [rdi + rcx + 6] + LONG $0xe06e0f66 // movd xmm4, eax + LONG $0x0f44b60f; BYTE $0x07 // movzx eax, byte [rdi + rcx + 7] + LONG $0xd06e0f66 // movd xmm2, eax + QUAD $0x00013024947f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm2 + LONG $0x0f44b60f; BYTE $0x08 // movzx eax, byte [rdi + rcx + 8] + LONG $0x6e0f4466; BYTE $0xe8 // movd xmm13, eax + LONG $0x0f44b60f; BYTE $0x09 // movzx eax, byte [rdi + rcx + 9] + LONG $0xd06e0f66 // movd xmm2, eax + QUAD $0x0000f024947f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm2 + LONG $0x0f44b60f; BYTE $0x0a // movzx eax, byte [rdi + rcx + 10] + LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax + LONG $0x0f44b60f; BYTE $0x0b // movzx eax, byte [rdi + rcx + 11] + LONG $0x6e0f4466; BYTE $0xd0 // movd xmm10, eax + LONG $0x0f44b60f; BYTE $0x0c // movzx eax, byte [rdi + rcx + 12] + LONG $0xf06e0f66 // movd xmm6, eax + LONG $0x0f44b60f; BYTE $0x10 // movzx eax, byte [rdi + rcx + 16] + LONG $0x6e0f4466; BYTE $0xe0 // movd xmm12, eax + LONG $0x0f44b60f; BYTE $0x18 // movzx eax, byte [rdi + rcx + 24] + LONG $0xd06e0f66 // movd xmm2, eax + QUAD $0x00000090248c8948 // mov qword [rsp + 144], rcx + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x20c88348 // or rax, 32 + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + LONG $0x40ca8348 // or rdx, 64 + LONG $0x60cc8349 // or r12, 96 + QUAD $0x000000a024a4894c // mov qword [rsp + 160], r12 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + QUAD $0x00000110248c894c // mov qword [rsp + 272], r9 + LONG $0xa0c88149; WORD $0x0000; BYTE $0x00 // or r8, 160 + QUAD $0x000000d02484894c // mov qword [rsp + 208], r8 + LONG $0xc0ce8148; WORD $0x0000; BYTE $0x00 // or rsi, 192 + QUAD $0x000000e024b48948 // mov qword [rsp + 224], rsi + LONG $0xe0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 224 + QUAD $0x00000100249c894c // mov qword [rsp + 256], r11 + LONG $0x00ce8149; WORD $0x0001; BYTE $0x00 // or r14, 256 + LONG $0x2474894c; BYTE $0x70 // mov qword [rsp + 112], r14 + LONG $0x20ca8149; WORD $0x0001; BYTE $0x00 // or r10, 288 + LONG $0x40cf8149; WORD $0x0001; BYTE $0x00 // or r15, 320 + QUAD $0x0000012024bc894c // mov qword [rsp + 288], r15 + LONG $0x60cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 352 + QUAD $0x000000b0249c8948 // mov qword [rsp + 176], rbx LONG $0x80cd8149; WORD $0x0001; BYTE $0x00 // or r13, 384 - QUAD $0x000000d024ac894c // mov qword [rsp + 208], r13 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x01a00d48; WORD $0x0000 // or rax, 416 - LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x01c00d48; WORD $0x0000 // or rax, 448 LONG $0x24448948; BYTE $0x10 // mov qword [rsp + 16], rax - WORD $0x894c; BYTE $0xc8 // mov rax, r9 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x01c00d48; WORD $0x0000 // or rax, 448 + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x01e00d48; WORD $0x0000 // or rax, 480 - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - QUAD $0x013e04203a0f4266 // pinsrb xmm0, byte [rsi + r15], 1 - LONG $0x203a0f66; WORD $0x1e04; BYTE $0x02 // pinsrb xmm0, byte [rsi + rbx], 2 - LONG $0x203a0f66; WORD $0x3e04; BYTE $0x03 // pinsrb xmm0, byte [rsi + rdi], 3 - LONG $0x203a0f66; WORD $0x1604; BYTE $0x04 // pinsrb xmm0, byte [rsi + rdx], 4 - LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx - LONG $0x203a0f66; WORD $0x0e04; BYTE $0x05 // pinsrb xmm0, byte [rsi + rcx], 5 - QUAD $0x063604203a0f4266 // pinsrb xmm0, byte [rsi + r14], 6 - QUAD $0x070604203a0f4266 // pinsrb xmm0, byte [rsi + r8], 7 - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - QUAD $0x081604203a0f4266 // pinsrb xmm0, byte [rsi + r10], 8 - QUAD $0x092604203a0f4266 // pinsrb xmm0, byte [rsi + r12], 9 - QUAD $0x0a1e04203a0f4266 // pinsrb xmm0, byte [rsi + r11], 10 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x0b3e04203a0f4266 // pinsrb xmm0, byte [rsi + r15], 11 - QUAD $0x0c2e04203a0f4266 // pinsrb xmm0, byte [rsi + r13], 12 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - LONG $0x203a0f66; WORD $0x3e04; BYTE $0x0d // pinsrb xmm0, byte [rsi + rdi], 13 + LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] + LONG $0x203a0f66; WORD $0x0f04; BYTE $0x01 // pinsrb xmm0, byte [rdi + rcx], 1 + LONG $0x203a0f66; WORD $0x1704; BYTE $0x02 // pinsrb xmm0, byte [rdi + rdx], 2 + QUAD $0x032704203a0f4266 // pinsrb xmm0, byte [rdi + r12], 3 + QUAD $0x040f04203a0f4266 // pinsrb xmm0, byte [rdi + r9], 4 + QUAD $0x050704203a0f4266 // pinsrb xmm0, byte [rdi + r8], 5 + LONG $0x203a0f66; WORD $0x3704; BYTE $0x06 // pinsrb xmm0, byte [rdi + rsi], 6 + QUAD $0x071f04203a0f4266 // pinsrb xmm0, byte [rdi + r11], 7 + QUAD $0x083704203a0f4266 // pinsrb xmm0, byte [rdi + r14], 8 + QUAD $0x091704203a0f4266 // pinsrb xmm0, byte [rdi + r10], 9 + QUAD $0x0a3f04203a0f4266 // pinsrb xmm0, byte [rdi + r15], 10 + LONG $0x203a0f66; WORD $0x1f04; BYTE $0x0b // pinsrb xmm0, byte [rdi + rbx], 11 + QUAD $0x0000008024ac894c // mov qword [rsp + 128], r13 + QUAD $0x0c2f04203a0f4266 // pinsrb xmm0, byte [rdi + r13], 12 LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - LONG $0x203a0f66; WORD $0x0e04; BYTE $0x0e // pinsrb xmm0, byte [rsi + rcx], 14 - LONG $0x203a0f66; WORD $0x0604; BYTE $0x0f // pinsrb xmm0, byte [rsi + rax], 15 + LONG $0x203a0f66; WORD $0x0f04; BYTE $0x0d // pinsrb xmm0, byte [rdi + rcx], 13 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0e0704203a0f4266 // pinsrb xmm0, byte [rdi + r8], 14 + WORD $0x8949; BYTE $0xc6 // mov r14, rax + LONG $0x203a0f66; WORD $0x0704; BYTE $0x0f // pinsrb xmm0, byte [rdi + rax], 15 LONG $0x6f0f4466; BYTE $0xc8 // movdqa xmm9, xmm0 - QUAD $0x00019024bc6f0f66; BYTE $0x00 // movdqa xmm7, oword [rsp + 400] + QUAD $0x0001a024bc6f0f66; BYTE $0x00 // movdqa xmm7, oword [rsp + 416] LONG $0xde0f4466; BYTE $0xcf // pmaxub xmm9, xmm7 LONG $0x6f0f4466; BYTE $0xff // movdqa xmm15, xmm7 LONG $0x740f4466; BYTE $0xc8 // pcmpeqb xmm9, xmm0 LONG $0x6f0f4166; BYTE $0xc1 // movdqa xmm0, xmm9 - LONG $0x24548b4c; BYTE $0x50 // mov r10, qword [rsp + 80] - QUAD $0x01165c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rsi + r10 + 1], 1 - QUAD $0x011e5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rbx + 1], 2 - QUAD $0x000000c024ac8b4c // mov r13, qword [rsp + 192] - QUAD $0x012e5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r13 + 1], 3 - QUAD $0x01165c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rsi + rdx + 1], 4 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x010e5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rsi + rcx + 1], 5 - QUAD $0x01365c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rsi + r14 + 1], 6 - QUAD $0x01065c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rsi + r8 + 1], 7 - QUAD $0x010e5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r9 + 1], 8 - WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x0000013024a4894c // mov qword [rsp + 304], r12 - QUAD $0x01265c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r12 + 1], 9 - QUAD $0x011e5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rsi + r11 + 1], 10 - QUAD $0x013e5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r15 + 1], 11 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x01265c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r12 + 1], 12 - QUAD $0x013e5c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rsi + rdi + 1], 13 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x01265c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rsi + r12 + 1], 14 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x013e5c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rsi + rdi + 1], 15 - QUAD $0x08166c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rsi + r10 + 8], 1 - QUAD $0x081e6c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rsi + rbx + 8], 2 - QUAD $0x082e6c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rsi + r13 + 8], 3 - QUAD $0x08166c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rsi + rdx + 8], 4 - QUAD $0x080e6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rsi + rcx + 8], 5 - QUAD $0x08366c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rsi + r14 + 8], 6 - QUAD $0x08066c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rsi + r8 + 8], 7 - QUAD $0x080e6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rsi + r9 + 8], 8 - QUAD $0x08066c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rsi + rax + 8], 9 - QUAD $0x081e6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rsi + r11 + 8], 10 - QUAD $0x083e6c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rsi + r15 + 8], 11 - QUAD $0x000000d024848b48 // mov rax, qword [rsp + 208] - QUAD $0x08066c203a0f4466; BYTE $0x0c // pinsrb xmm13, byte [rsi + rax + 8], 12 - WORD $0x8948; BYTE $0xc7 // mov rdi, rax LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x08066c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rsi + rax + 8], 13 - QUAD $0x08266c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rsi + r12 + 8], 14 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x08066c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rsi + rax + 8], 15 + QUAD $0x01075c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdi + rax + 1], 1 + QUAD $0x01175c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdi + rdx + 1], 2 + QUAD $0x01275c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdi + r12 + 1], 3 + QUAD $0x010f5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdi + r9 + 1], 4 + QUAD $0x000000d0248c8b48 // mov rcx, qword [rsp + 208] + QUAD $0x010f5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdi + rcx + 1], 5 + QUAD $0x01375c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rdi + rsi + 1], 6 + QUAD $0x011f5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdi + r11 + 1], 7 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x01075c203a0f4466; BYTE $0x08 // pinsrb xmm11, byte [rdi + rax + 1], 8 + QUAD $0x01175c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdi + r10 + 1], 9 + QUAD $0x013f5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdi + r15 + 1], 10 + QUAD $0x011f5c203a0f4466; BYTE $0x0b // pinsrb xmm11, byte [rdi + rbx + 1], 11 + QUAD $0x012f5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdi + r13 + 1], 12 + LONG $0x247c8b4c; BYTE $0x10 // mov r15, qword [rsp + 16] + QUAD $0x013f5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdi + r15 + 1], 13 + QUAD $0x01075c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdi + r8 + 1], 14 + QUAD $0x01375c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdi + r14 + 1], 15 + LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] + QUAD $0x08076c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rdi + r8 + 8], 1 + QUAD $0x08176c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdi + rdx + 8], 2 + QUAD $0x08276c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdi + r12 + 8], 3 + QUAD $0x080f6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdi + r9 + 8], 4 + QUAD $0x080f6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdi + rcx + 8], 5 + QUAD $0x08376c203a0f4466; BYTE $0x06 // pinsrb xmm13, byte [rdi + rsi + 8], 6 + QUAD $0x081f6c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdi + r11 + 8], 7 + QUAD $0x08076c203a0f4466; BYTE $0x08 // pinsrb xmm13, byte [rdi + rax + 8], 8 + QUAD $0x08176c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdi + r10 + 8], 9 + QUAD $0x00000120249c8b4c // mov r11, qword [rsp + 288] + QUAD $0x081f6c203a0f4666; BYTE $0x0a // pinsrb xmm13, byte [rdi + r11 + 8], 10 + QUAD $0x081f6c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rdi + rbx + 8], 11 + QUAD $0x082f6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdi + r13 + 8], 12 + QUAD $0x083f6c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdi + r15 + 8], 13 + LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] + QUAD $0x08276c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdi + r12 + 8], 14 + QUAD $0x08376c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdi + r14 + 8], 15 LONG $0x6f0f4566; BYTE $0xcd // movdqa xmm9, xmm13 LONG $0xde0f4466; BYTE $0xcf // pmaxub xmm9, xmm7 LONG $0x740f4566; BYTE $0xcd // pcmpeqb xmm9, xmm13 - QUAD $0x101664203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rsi + r10 + 16], 1 - QUAD $0x101e64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rsi + rbx + 16], 2 - QUAD $0x102e64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rsi + r13 + 16], 3 - QUAD $0x101664203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rsi + rdx + 16], 4 - QUAD $0x100e64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rsi + rcx + 16], 5 - QUAD $0x103664203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rsi + r14 + 16], 6 - QUAD $0x100664203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rsi + r8 + 16], 7 - WORD $0x894c; BYTE $0xc2 // mov rdx, r8 - QUAD $0x000001b02484894c // mov qword [rsp + 432], r8 - QUAD $0x100e64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rsi + r9 + 16], 8 - QUAD $0x0000013024a48b4c // mov r12, qword [rsp + 304] - QUAD $0x102664203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rsi + r12 + 16], 9 - QUAD $0x101e64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rsi + r11 + 16], 10 - QUAD $0x000000b0249c894c // mov qword [rsp + 176], r11 - QUAD $0x103e64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rsi + r15 + 16], 11 - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - QUAD $0x103e64203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rsi + rdi + 16], 12 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x103e64203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rsi + rdi + 16], 13 - LONG $0x24448b4c; BYTE $0x10 // mov r8, qword [rsp + 16] - QUAD $0x100664203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rsi + r8 + 16], 14 - QUAD $0x100664203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rsi + rax + 16], 15 + QUAD $0x100764203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdi + r8 + 16], 1 + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + QUAD $0x101764203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdi + rdx + 16], 2 + QUAD $0x000000a0249c8b48 // mov rbx, qword [rsp + 160] + QUAD $0x101f64203a0f4466; BYTE $0x03 // pinsrb xmm12, byte [rdi + rbx + 16], 3 + QUAD $0x100f64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdi + r9 + 16], 4 + QUAD $0x100f64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdi + rcx + 16], 5 + QUAD $0x103764203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rdi + rsi + 16], 6 + QUAD $0x0000010024b48b48 // mov rsi, qword [rsp + 256] + QUAD $0x103764203a0f4466; BYTE $0x07 // pinsrb xmm12, byte [rdi + rsi + 16], 7 + QUAD $0x100764203a0f4466; BYTE $0x08 // pinsrb xmm12, byte [rdi + rax + 16], 8 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + QUAD $0x101764203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdi + r10 + 16], 9 + QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 + QUAD $0x101f64203a0f4666; BYTE $0x0a // pinsrb xmm12, byte [rdi + r11 + 16], 10 + QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] + QUAD $0x100764203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rdi + rax + 16], 11 + QUAD $0x102f64203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdi + r13 + 16], 12 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x102f64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdi + r13 + 16], 13 + QUAD $0x102764203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdi + r12 + 16], 14 + QUAD $0x103764203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdi + r14 + 16], 15 + LONG $0x2474894c; BYTE $0x50 // mov qword [rsp + 80], r14 LONG $0x6f0f4166; BYTE $0xfc // movdqa xmm7, xmm12 LONG $0xde0f4166; BYTE $0xff // pmaxub xmm7, xmm15 LONG $0x740f4166; BYTE $0xfc // pcmpeqb xmm7, xmm12 - QUAD $0x00017024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 368], xmm7 - QUAD $0x181654203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rsi + r10 + 24], 1 - QUAD $0x02181e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 24], 2 - QUAD $0x182e54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r13 + 24], 3 - LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] - QUAD $0x04181e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 24], 4 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x181654203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rsi + r10 + 24], 5 - QUAD $0x183654203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rsi + r14 + 24], 6 - QUAD $0x07181654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 24], 7 - QUAD $0x180e54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r9 + 24], 8 - QUAD $0x182654203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r12 + 24], 9 - QUAD $0x181e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r11 + 24], 10 - QUAD $0x183e54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r15 + 24], 11 - WORD $0x894d; BYTE $0xfc // mov r12, r15 - QUAD $0x0c180e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 24], 12 - QUAD $0x0d183e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 24], 13 - QUAD $0x180654203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rsi + r8 + 24], 14 - WORD $0x894d; BYTE $0xc5 // mov r13, r8 - QUAD $0x0f180654203a0f66 // pinsrb xmm2, byte [rsi + rax + 24], 15 + QUAD $0x00016024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 352], xmm7 + QUAD $0x183f54203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdi + r15 + 24], 1 + QUAD $0x02181754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 24], 2 + WORD $0x8949; BYTE $0xd7 // mov r15, rdx + LONG $0x24548948; BYTE $0x20 // mov qword [rsp + 32], rdx + QUAD $0x03181f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 24], 3 + QUAD $0x0000011024948b48 // mov rdx, qword [rsp + 272] + QUAD $0x04181754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 24], 4 + QUAD $0x05180f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 24], 5 + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + QUAD $0x06180f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 24], 6 + QUAD $0x07183754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 24], 7 + QUAD $0x180754203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdi + r8 + 24], 8 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 + QUAD $0x181754203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r10 + 24], 9 + QUAD $0x181f54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r11 + 24], 10 + WORD $0x894d; BYTE $0xda // mov r10, r11 + QUAD $0x0b180754203a0f66 // pinsrb xmm2, byte [rdi + rax + 24], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x0c180754203a0f66 // pinsrb xmm2, byte [rdi + rax + 24], 12 + QUAD $0x182f54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdi + r13 + 24], 13 + QUAD $0x182754203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdi + r12 + 24], 14 + QUAD $0x183754203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdi + r14 + 24], 15 LONG $0xfa6f0f66 // movdqa xmm7, xmm2 LONG $0xde0f4166; BYTE $0xff // pmaxub xmm7, xmm15 LONG $0xfa740f66 // pcmpeqb xmm7, xmm2 - QUAD $0x0000f024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm7 + QUAD $0x00014024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 320], xmm7 LONG $0x6f0f4566; BYTE $0xe3 // movdqa xmm12, xmm11 LONG $0x6f0f4566; BYTE $0xef // movdqa xmm13, xmm15 LONG $0xde0f4566; BYTE $0xe7 // pmaxub xmm12, xmm15 LONG $0x740f4566; BYTE $0xe3 // pcmpeqb xmm12, xmm11 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - LONG $0x0654b60f; BYTE $0x0d // movzx edx, byte [rsi + rax + 13] + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + LONG $0x1754b60f; BYTE $0x0d // movzx edx, byte [rdi + rdx + 13] LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x020674203a0f4666; BYTE $0x01 // pinsrb xmm14, byte [rsi + r8 + 2], 1 - QUAD $0x0000008024bc8b4c // mov r15, qword [rsp + 128] - QUAD $0x023e74203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rsi + r15 + 2], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x023e74203a0f4466; BYTE $0x03 // pinsrb xmm14, byte [rsi + rdi + 2], 3 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - QUAD $0x021e74203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rsi + rbx + 2], 4 - QUAD $0x021674203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rsi + r10 + 2], 5 - QUAD $0x023674203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rsi + r14 + 2], 6 - QUAD $0x000001b0249c8b48 // mov rbx, qword [rsp + 432] - QUAD $0x021e74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rsi + rbx + 2], 7 - WORD $0x894c; BYTE $0xca // mov rdx, r9 - QUAD $0x00000100248c894c // mov qword [rsp + 256], r9 - QUAD $0x020e74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rsi + r9 + 2], 8 - QUAD $0x00000130248c8b4c // mov r9, qword [rsp + 304] - QUAD $0x020e74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r9 + 2], 9 - QUAD $0x000000b024848b48 // mov rax, qword [rsp + 176] - QUAD $0x020674203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rsi + rax + 2], 10 - QUAD $0x022674203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rsi + r12 + 2], 11 - WORD $0x8949; BYTE $0xcc // mov r12, rcx - QUAD $0x020e74203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rsi + rcx + 2], 12 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x020e74203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rsi + rcx + 2], 13 - QUAD $0x022e74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rsi + r13 + 2], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x022e74203a0f4666; BYTE $0x0f // pinsrb xmm14, byte [rsi + r13 + 2], 15 - QUAD $0x03066c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rsi + r8 + 3], 1 - QUAD $0x033e6c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rsi + r15 + 3], 2 - QUAD $0x03033e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 3], 3 - WORD $0x8949; BYTE $0xf8 // mov r8, rdi - QUAD $0x031e6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rsi + r11 + 3], 4 - QUAD $0x03166c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rsi + r10 + 3], 5 - QUAD $0x03366c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rsi + r14 + 3], 6 - QUAD $0x07031e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 3], 7 - QUAD $0x0803166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 3], 8 - QUAD $0x030e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r9 + 3], 9 - QUAD $0x0a03066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 3], 10 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x021774203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdi + rdx + 2], 1 + QUAD $0x023f74203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdi + r15 + 2], 2 QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x033e6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r15 + 3], 11 - QUAD $0x03266c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r12 + 3], 12 - QUAD $0x0d030e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 3], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e03066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 3], 14 - QUAD $0x032e6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r13 + 3], 15 + QUAD $0x023f74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdi + r15 + 2], 3 + QUAD $0x00000110248c8b4c // mov r9, qword [rsp + 272] + QUAD $0x020f74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rdi + r9 + 2], 4 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x023774203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdi + rsi + 2], 5 + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + QUAD $0x020f74203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rdi + rcx + 2], 6 + QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] + QUAD $0x021f74203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdi + r11 + 2], 7 + QUAD $0x021f74203a0f4466; BYTE $0x08 // pinsrb xmm14, byte [rdi + rbx + 2], 8 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x020f74203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdi + rcx + 2], 9 + WORD $0x894c; BYTE $0xd3 // mov rbx, r10 + QUAD $0x021774203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rdi + r10 + 2], 10 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x021774203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdi + r10 + 2], 11 + QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] + QUAD $0x020774203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rdi + rax + 2], 12 + QUAD $0x022f74203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rdi + r13 + 2], 13 + LONG $0x24748b4c; BYTE $0x30 // mov r14, qword [rsp + 48] + QUAD $0x023774203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdi + r14 + 2], 14 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x022774203a0f4666; BYTE $0x0f // pinsrb xmm14, byte [rdi + r12 + 2], 15 + QUAD $0x0103176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 3], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0203176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 3], 2 + QUAD $0x033f6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r15 + 3], 3 + QUAD $0x030f6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdi + r9 + 3], 4 + QUAD $0x0503376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 3], 5 + QUAD $0x03076c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r8 + 3], 6 + QUAD $0x031f6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r11 + 3], 7 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0803176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 3], 8 + QUAD $0x09030f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 3], 9 + QUAD $0x0a031f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 3], 10 + QUAD $0x03176c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdi + r10 + 3], 11 + QUAD $0x0c03076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 3], 12 + QUAD $0x032f6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdi + r13 + 3], 13 + WORD $0x894c; BYTE $0xe8 // mov rax, r13 + QUAD $0x03376c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdi + r14 + 3], 14 + QUAD $0x03276c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdi + r12 + 3], 15 QUAD $0x00000100956f0f66 // movdqa xmm2, oword 256[rbp] /* [rip + .LCPI10_16] */ LONG $0xdb0f4466; BYTE $0xe2 // pand xmm12, xmm2 LONG $0xf80f4466; BYTE $0xe0 // psubb xmm12, xmm0 @@ -52417,60 +55031,56 @@ LBB10_67: LONG $0xd56f0f66 // movdqa xmm2, xmm5 LONG $0xde0f4166; BYTE $0xd5 // pmaxub xmm2, xmm13 LONG $0xd5740f66 // pcmpeqb xmm2, xmm5 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - LONG $0x0654b60f; BYTE $0x0e // movzx edx, byte [rsi + rax + 14] + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + LONG $0x1754b60f; BYTE $0x0e // movzx edx, byte [rdi + rdx + 14] LONG $0x6e0f4466; BYTE $0xf2 // movd xmm14, edx - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x01043e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 4], 1 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0204065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 4], 2 - QUAD $0x04065c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r8 + 4], 3 - QUAD $0x041e5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rsi + r11 + 4], 4 - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x04165c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r10 + 4], 5 - QUAD $0x04365c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r14 + 4], 6 - QUAD $0x07041e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 4], 7 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - QUAD $0x04165c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r10 + 4], 8 - QUAD $0x040e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r9 + 4], 9 - QUAD $0x000000b024848b4c // mov r8, qword [rsp + 176] - QUAD $0x04065c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r8 + 4], 10 - QUAD $0x043e5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r15 + 4], 11 - QUAD $0x04265c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r12 + 4], 12 - LONG $0x245c8b4c; BYTE $0x60 // mov r11, qword [rsp + 96] - QUAD $0x041e5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r11 + 4], 13 - LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0e04165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 4], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x042e5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r13 + 4], 15 - QUAD $0x01053e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 5], 1 - QUAD $0x0205064c203a0f66 // pinsrb xmm1, byte [rsi + rax + 5], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x03053e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 5], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x04053e4c203a0f66 // pinsrb xmm1, byte [rsi + rdi + 5], 4 - QUAD $0x05050e4c203a0f66 // pinsrb xmm1, byte [rsi + rcx + 5], 5 - QUAD $0x05364c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rsi + r14 + 5], 6 - QUAD $0x07051e4c203a0f66 // pinsrb xmm1, byte [rsi + rbx + 5], 7 - QUAD $0x05164c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rsi + r10 + 5], 8 - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x050e4c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rsi + r9 + 5], 9 - QUAD $0x05064c203a0f4266; BYTE $0x0a // pinsrb xmm1, byte [rsi + r8 + 5], 10 - QUAD $0x053e4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rsi + r15 + 5], 11 - WORD $0x894d; BYTE $0xfa // mov r10, r15 - QUAD $0x05264c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rsi + r12 + 5], 12 - QUAD $0x051e4c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rsi + r11 + 5], 13 - QUAD $0x0e05164c203a0f66 // pinsrb xmm1, byte [rsi + rdx + 5], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x0104175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 4], 1 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x04275c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdi + r12 + 4], 2 + QUAD $0x043f5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r15 + 4], 3 + QUAD $0x040f5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r9 + 4], 4 + QUAD $0x0504375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 4], 5 + QUAD $0x04075c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r8 + 4], 6 + QUAD $0x041f5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r11 + 4], 7 + LONG $0x246c8b4c; BYTE $0x70 // mov r13, qword [rsp + 112] + QUAD $0x042f5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdi + r13 + 4], 8 + QUAD $0x09040f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 4], 9 + QUAD $0x0a041f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 4], 10 + QUAD $0x04175c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r10 + 4], 11 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x04375c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r14 + 4], 12 + QUAD $0x0d04075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 4], 13 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0e04075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 4], 14 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0f04075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 4], 15 + QUAD $0x0105174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 5], 1 + QUAD $0x05274c203a0f4266; BYTE $0x02 // pinsrb xmm1, byte [rdi + r12 + 5], 2 + QUAD $0x053f4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdi + r15 + 5], 3 + QUAD $0x050f4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdi + r9 + 5], 4 + QUAD $0x0505374c203a0f66 // pinsrb xmm1, byte [rdi + rsi + 5], 5 + QUAD $0x05074c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdi + r8 + 5], 6 + QUAD $0x051f4c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdi + r11 + 5], 7 + QUAD $0x052f4c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdi + r13 + 5], 8 + QUAD $0x09050f4c203a0f66 // pinsrb xmm1, byte [rdi + rcx + 5], 9 + QUAD $0x0a051f4c203a0f66 // pinsrb xmm1, byte [rdi + rbx + 5], 10 + QUAD $0x05174c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdi + r10 + 5], 11 + QUAD $0x05374c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdi + r14 + 5], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d05074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 5], 13 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0e05074c203a0f66 // pinsrb xmm1, byte [rdi + rax + 5], 14 QUAD $0x00000110ad6f0f66 // movdqa xmm5, oword 272[rbp] /* [rip + .LCPI10_17] */ LONG $0xdb0f4466; BYTE $0xdd // pand xmm11, xmm5 QUAD $0x00000120ad6f0f66 // movdqa xmm5, oword 288[rbp] /* [rip + .LCPI10_18] */ LONG $0xd5db0f66 // pand xmm2, xmm5 LONG $0xeb0f4166; BYTE $0xd3 // por xmm2, xmm11 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - LONG $0x3e54b60f; BYTE $0x0f // movzx edx, byte [rsi + rdi + 15] + QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] + LONG $0x0754b60f; BYTE $0x0f // movzx edx, byte [rdi + rax + 15] LONG $0x6e0f4466; BYTE $0xda // movd xmm11, edx - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x052e4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rsi + r13 + 5], 15 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0f05174c203a0f66 // pinsrb xmm1, byte [rdi + rdx + 5], 15 LONG $0xeb0f4166; BYTE $0xd4 // por xmm2, xmm12 LONG $0x6f0f4466; BYTE $0xe3 // movdqa xmm12, xmm3 LONG $0xde0f4566; BYTE $0xe5 // pmaxub xmm12, xmm13 @@ -52478,50 +55088,49 @@ LBB10_67: LONG $0xe96f0f66 // movdqa xmm5, xmm1 LONG $0xde0f4166; BYTE $0xed // pmaxub xmm5, xmm13 LONG $0xe9740f66 // pcmpeqb xmm5, xmm1 - LONG $0x3e54b60f; BYTE $0x11 // movzx edx, byte [rsi + rdi + 17] + LONG $0x0754b60f; BYTE $0x11 // movzx edx, byte [rdi + rax + 17] LONG $0xc26e0f66 // movd xmm0, edx - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x060664203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rsi + r8 + 6], 1 - QUAD $0x02060664203a0f66 // pinsrb xmm4, byte [rsi + rax + 6], 2 - QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] - QUAD $0x03063e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 6], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x04060664203a0f66 // pinsrb xmm4, byte [rsi + rax + 6], 4 - LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] - QUAD $0x061e64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rsi + r11 + 6], 5 - QUAD $0x063664203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r14 + 6], 6 - QUAD $0x07061e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 6], 7 - QUAD $0x08060e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 6], 8 - QUAD $0x060e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r9 + 6], 9 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x063e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r15 + 6], 10 - QUAD $0x061664203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r10 + 6], 11 - QUAD $0x062664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r12 + 6], 12 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0d061664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 6], 13 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e060e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 6], 14 - QUAD $0x062e64203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r13 + 6], 15 - QUAD $0x000140249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 320] - QUAD $0x07065c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rsi + r8 + 7], 1 - QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] - QUAD $0x07065c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rsi + r8 + 7], 2 - QUAD $0x03073e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 7], 3 - QUAD $0x0407065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 7], 4 - WORD $0x894c; BYTE $0xdf // mov rdi, r11 - QUAD $0x071e5c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r11 + 7], 5 - QUAD $0x07365c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r14 + 7], 6 - QUAD $0x0000012024b4894c // mov qword [rsp + 288], r14 - QUAD $0x07071e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 7], 7 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - QUAD $0x071e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r11 + 7], 8 - QUAD $0x070e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r9 + 7], 9 - QUAD $0x073e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r15 + 7], 10 - QUAD $0x07165c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r10 + 7], 11 - QUAD $0x07265c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r12 + 7], 12 - QUAD $0x0d07165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 7], 13 - QUAD $0x0e070e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 7], 14 - QUAD $0x072e5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r13 + 7], 15 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x062f64203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdi + r13 + 6], 1 + QUAD $0x062764203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdi + r12 + 6], 2 + QUAD $0x063f64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdi + r15 + 6], 3 + QUAD $0x060f64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdi + r9 + 6], 4 + QUAD $0x05063764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 6], 5 + QUAD $0x060764203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r8 + 6], 6 + QUAD $0x061f64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r11 + 6], 7 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x08061764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 6], 8 + QUAD $0x09060f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 6], 9 + QUAD $0x0a061f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 6], 10 + QUAD $0x061764203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r10 + 6], 11 + QUAD $0x0000008024b48b4c // mov r14, qword [rsp + 128] + QUAD $0x063764203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdi + r14 + 6], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d060764203a0f66 // pinsrb xmm4, byte [rdi + rax + 6], 13 + LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] + QUAD $0x0e060764203a0f66 // pinsrb xmm4, byte [rdi + rax + 6], 14 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0f060764203a0f66 // pinsrb xmm4, byte [rdi + rax + 6], 15 + QUAD $0x000130249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 304] + QUAD $0x072f5c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdi + r13 + 7], 1 + QUAD $0x07275c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdi + r12 + 7], 2 + QUAD $0x073f5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r15 + 7], 3 + QUAD $0x070f5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r9 + 7], 4 + QUAD $0x0507375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 7], 5 + QUAD $0x07075c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r8 + 7], 6 + QUAD $0x071f5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r11 + 7], 7 + QUAD $0x0807175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 7], 8 + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + QUAD $0x09070f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 7], 9 + QUAD $0x0a071f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 7], 10 + QUAD $0x07175c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdi + r10 + 7], 11 + QUAD $0x07375c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r14 + 7], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d07075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 7], 13 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0e07375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 7], 14 + LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] + QUAD $0x0f070f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 7], 15 QUAD $0x000001308d6f0f66 // movdqa xmm1, oword 304[rbp] /* [rip + .LCPI10_19] */ LONG $0xdb0f4466; BYTE $0xe1 // pand xmm12, xmm1 QUAD $0x000001408d6f0f66 // movdqa xmm1, oword 320[rbp] /* [rip + .LCPI10_20] */ @@ -52530,97 +55139,100 @@ LBB10_67: LONG $0xcc6f0f66 // movdqa xmm1, xmm4 LONG $0xde0f4166; BYTE $0xcd // pmaxub xmm1, xmm13 LONG $0xcc740f66 // pcmpeqb xmm1, xmm4 - QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] - LONG $0x54b60f42; WORD $0x1216 // movzx edx, byte [rsi + r10 + 18] + QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] + LONG $0x54b60f42; WORD $0x1207 // movzx edx, byte [rdi + r8 + 18] LONG $0xe26e0f66 // movd xmm4, edx QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI10_21] */ LONG $0xcfdb0f66 // pand xmm1, xmm7 LONG $0xcdeb0f66 // por xmm1, xmm5 - LONG $0x54b60f42; WORD $0x1316 // movzx edx, byte [rsi + r10 + 19] + LONG $0x54b60f42; WORD $0x1307 // movzx edx, byte [rdi + r8 + 19] LONG $0xea6e0f66 // movd xmm5, edx LONG $0xcaeb0f66 // por xmm1, xmm2 LONG $0xd36f0f66 // movdqa xmm2, xmm3 LONG $0xde0f4166; BYTE $0xd5 // pmaxub xmm2, xmm13 LONG $0xd3740f66 // pcmpeqb xmm2, xmm3 LONG $0x6f0f4466; BYTE $0xe2 // movdqa xmm12, xmm2 - LONG $0x54b60f42; WORD $0x1416 // movzx edx, byte [rsi + r10 + 20] + LONG $0x54b60f42; WORD $0x1407 // movzx edx, byte [rdi + r8 + 20] LONG $0xd26e0f66 // movd xmm2, edx - QUAD $0x000110249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 272] - LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] - QUAD $0x01093e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 9], 1 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x09065c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rsi + r8 + 9], 2 - QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] - QUAD $0x03090e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 9], 3 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x04090e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 9], 4 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x09065c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rsi + r8 + 9], 5 - QUAD $0x09365c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rsi + r14 + 9], 6 - QUAD $0x07091e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 9], 7 - QUAD $0x091e5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r11 + 9], 8 - QUAD $0x090e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r9 + 9], 9 - QUAD $0x093e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r15 + 9], 10 - QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] - QUAD $0x09265c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r12 + 9], 11 - QUAD $0x000000d024948b48 // mov rdx, qword [rsp + 208] - QUAD $0x0c09165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 9], 12 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x092e5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r13 + 9], 13 + QUAD $0x0000f0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 240] + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0109075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 9], 1 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x02091f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 9], 2 + QUAD $0x093f5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r15 + 9], 3 + QUAD $0x090f5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdi + r9 + 9], 4 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x09175c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdi + r10 + 9], 5 + QUAD $0x000000e0249c8b4c // mov r11, qword [rsp + 224] + QUAD $0x091f5c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r11 + 9], 6 + QUAD $0x0000010024b48b4c // mov r14, qword [rsp + 256] + QUAD $0x09375c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r14 + 9], 7 + WORD $0x894d; BYTE $0xec // mov r12, r13 + QUAD $0x092f5c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdi + r13 + 9], 8 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0909175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 9], 9 + QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] + QUAD $0x092f5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdi + r13 + 9], 10 + QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] + QUAD $0x0b09175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 9], 11 + QUAD $0x0000008024948b48 // mov rdx, qword [rsp + 128] + QUAD $0x0c09175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 9], 12 LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] - QUAD $0x0e09165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 9], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f09165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 9], 15 + QUAD $0x0d09175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 9], 13 + QUAD $0x0e09375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 9], 14 + QUAD $0x0f090f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 9], 15 LONG $0x7d6f0f66; BYTE $0x60 // movdqa xmm7, oword 96[rbp] /* [rip + .LCPI10_6] */ LONG $0xdb0f4466; BYTE $0xe7 // pand xmm12, xmm7 LONG $0xeb0f4466; BYTE $0xe1 // por xmm12, xmm1 - QUAD $0x011024a47f0f4466; WORD $0x0000 // movdqa oword [rsp + 272], xmm12 + QUAD $0x00f024a47f0f4466; WORD $0x0000 // movdqa oword [rsp + 240], xmm12 LONG $0xfb6f0f66 // movdqa xmm7, xmm3 LONG $0xde0f4166; BYTE $0xfd // pmaxub xmm7, xmm13 LONG $0xfb740f66 // pcmpeqb xmm7, xmm3 - LONG $0x54b60f42; WORD $0x1516 // movzx edx, byte [rsi + r10 + 21] + LONG $0x54b60f42; WORD $0x1507 // movzx edx, byte [rdi + r8 + 21] LONG $0xda6e0f66 // movd xmm3, edx - QUAD $0x0a3e44203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rdi + 10], 1 - QUAD $0x0a0644203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rax + 10], 2 - WORD $0x8949; BYTE $0xc6 // mov r14, rax - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x0a1644203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rsi + r10 + 10], 3 - QUAD $0x0a0e44203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rcx + 10], 4 - QUAD $0x0a0644203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rsi + r8 + 10], 5 - QUAD $0x0000012024848b48 // mov rax, qword [rsp + 288] - QUAD $0x0a0644203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rax + 10], 6 - QUAD $0x0a1e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rbx + 10], 7 - QUAD $0x0a1e44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r11 + 10], 8 - QUAD $0x0a0e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r9 + 10], 9 - WORD $0x894c; BYTE $0xf8 // mov rax, r15 - QUAD $0x0a3e44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r15 + 10], 10 - WORD $0x894c; BYTE $0xe2 // mov rdx, r12 - QUAD $0x0a2644203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r12 + 10], 11 - QUAD $0x000000d024a48b4c // mov r12, qword [rsp + 208] - QUAD $0x0a2644203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r12 + 10], 12 - WORD $0x894d; BYTE $0xef // mov r15, r13 - QUAD $0x0a2e44203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r13 + 10], 13 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0a0e44203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rcx + 10], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0a2e44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r13 + 10], 15 - QUAD $0x0b3e54203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rdi + 11], 1 - QUAD $0x0b3654203a0f4666; BYTE $0x02 // pinsrb xmm10, byte [rsi + r14 + 11], 2 - QUAD $0x0b1654203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r10 + 11], 3 - LONG $0x247c8b48; BYTE $0x70 // mov rdi, qword [rsp + 112] - QUAD $0x0b3e54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rdi + 11], 4 - QUAD $0x0b0654203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rsi + r8 + 11], 5 - QUAD $0x0000012024b48b4c // mov r14, qword [rsp + 288] - QUAD $0x0b3654203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rsi + r14 + 11], 6 - QUAD $0x0b1e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rbx + 11], 7 - QUAD $0x0b1e54203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r11 + 11], 8 - QUAD $0x0b0e54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r9 + 11], 9 - QUAD $0x0b0654203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rsi + rax + 11], 10 - QUAD $0x0b1654203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rsi + rdx + 11], 11 - QUAD $0x0b2654203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r12 + 11], 12 - QUAD $0x0b3e54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r15 + 11], 13 - QUAD $0x0b0e54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rcx + 11], 14 - QUAD $0x0b2e54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r13 + 11], 15 + QUAD $0x0a0744203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdi + rax + 10], 1 + QUAD $0x0a1f44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdi + rbx + 10], 2 + QUAD $0x0a3f44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdi + r15 + 10], 3 + QUAD $0x0a0f44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdi + r9 + 10], 4 + WORD $0x894c; BYTE $0xd6 // mov rsi, r10 + QUAD $0x0a1744203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rdi + r10 + 10], 5 + WORD $0x894d; BYTE $0xd8 // mov r8, r11 + QUAD $0x0a1f44203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r11 + 10], 6 + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + QUAD $0x0a3744203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r14 + 10], 7 + QUAD $0x0a2744203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdi + r12 + 10], 8 + QUAD $0x000000c0248c8b48 // mov rcx, qword [rsp + 192] + QUAD $0x0a0f44203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdi + rcx + 10], 9 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x0a2f44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdi + r13 + 10], 10 + QUAD $0x000000b024948b4c // mov r10, qword [rsp + 176] + QUAD $0x0a1744203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdi + r10 + 10], 11 + QUAD $0x0000008024a48b4c // mov r12, qword [rsp + 128] + QUAD $0x0a2744203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdi + r12 + 10], 12 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x0a2f44203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rdi + r13 + 10], 13 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x0a1744203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdi + rdx + 10], 14 + LONG $0x24748b4c; BYTE $0x50 // mov r14, qword [rsp + 80] + QUAD $0x0a3744203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdi + r14 + 10], 15 + QUAD $0x0b0754203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdi + rax + 11], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0b0754203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdi + rax + 11], 2 + QUAD $0x0b3f54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdi + r15 + 11], 3 + QUAD $0x0b0f54203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdi + r9 + 11], 4 + QUAD $0x0b3754203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdi + rsi + 11], 5 + QUAD $0x0b0754203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r8 + 11], 6 + QUAD $0x0b1f54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r11 + 11], 7 + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + QUAD $0x0b0754203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rdi + rax + 11], 8 + QUAD $0x0b0f54203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdi + rcx + 11], 9 + QUAD $0x0b1f54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdi + rbx + 11], 10 + QUAD $0x0b1754203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdi + r10 + 11], 11 + QUAD $0x0b2754203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdi + r12 + 11], 12 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x0b2f54203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdi + r13 + 11], 13 + QUAD $0x0b1754203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rdi + rdx + 11], 14 + QUAD $0x0b3754203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdi + r14 + 11], 15 QUAD $0x00000100bddb0f66 // pand xmm7, oword 256[rbp] /* [rip + .LCPI10_16] */ LONG $0xf80f4166; BYTE $0xf9 // psubb xmm7, xmm9 LONG $0x6f0f4166; BYTE $0xc8 // movdqa xmm1, xmm8 @@ -52629,60 +55241,56 @@ LBB10_67: LONG $0x6f0f4566; BYTE $0xca // movdqa xmm9, xmm10 LONG $0xde0f4566; BYTE $0xcd // pmaxub xmm9, xmm13 LONG $0x740f4566; BYTE $0xca // pcmpeqb xmm9, xmm10 - QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - LONG $0x0654b60f; BYTE $0x16 // movzx edx, byte [rsi + rax + 22] + QUAD $0x0000009024948b48 // mov rdx, qword [rsp + 144] + LONG $0x1754b60f; BYTE $0x16 // movzx edx, byte [rdi + rdx + 22] LONG $0x6e0f4466; BYTE $0xd2 // movd xmm10, edx - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x0c0674203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rsi + r8 + 12], 1 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x020c0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 12], 2 - QUAD $0x0c1674203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r10 + 12], 3 - WORD $0x894d; BYTE $0xd7 // mov r15, r10 - WORD $0x8948; BYTE $0xf9 // mov rcx, rdi - QUAD $0x040c3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 12], 4 - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x050c3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 12], 5 - QUAD $0x0c3674203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rsi + r14 + 12], 6 - QUAD $0x070c1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 12], 7 - QUAD $0x0c1e74203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r11 + 12], 8 - QUAD $0x0c0e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r9 + 12], 9 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0a0c1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 12], 10 - QUAD $0x000000a0249c8b4c // mov r11, qword [rsp + 160] - QUAD $0x0c1e74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r11 + 12], 11 - QUAD $0x0c2674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r12 + 12], 12 - LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] - QUAD $0x0d0c1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 12], 13 - LONG $0x24548b4c; BYTE $0x10 // mov r10, qword [rsp + 16] - QUAD $0x0c1674203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rsi + r10 + 12], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0c2e74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r13 + 12], 15 - QUAD $0x0d067c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rsi + r8 + 13], 1 - QUAD $0x0d067c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rsi + rax + 13], 2 - QUAD $0x0d3e7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rsi + r15 + 13], 3 - QUAD $0x0d0e7c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rsi + rcx + 13], 4 - QUAD $0x0d3e7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rdi + 13], 5 - WORD $0x8949; BYTE $0xf8 // mov r8, rdi - QUAD $0x0d367c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rsi + r14 + 13], 6 - QUAD $0x0d1e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rbx + 13], 7 - QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] - QUAD $0x0d3e7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rsi + rdi + 13], 8 - QUAD $0x0d0e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r9 + 13], 9 - QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] - QUAD $0x0d3e7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r15 + 13], 10 - QUAD $0x0d1e7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r11 + 13], 11 - QUAD $0x0d267c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r12 + 13], 12 - QUAD $0x0d167c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rsi + rdx + 13], 13 - WORD $0x8949; BYTE $0xd3 // mov r11, rdx - QUAD $0x0d167c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rsi + r10 + 13], 14 + LONG $0x24648b4c; BYTE $0x60 // mov r12, qword [rsp + 96] + QUAD $0x0c2774203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdi + r12 + 12], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x020c1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 12], 2 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x0c3774203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r14 + 12], 3 + QUAD $0x0c0f74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdi + r9 + 12], 4 + QUAD $0x050c3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 12], 5 + QUAD $0x0c0774203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r8 + 12], 6 + QUAD $0x0c1f74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r11 + 12], 7 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x080c1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 12], 8 + QUAD $0x090c0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 12], 9 + QUAD $0x0a0c1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 12], 10 + QUAD $0x0c1774203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdi + r10 + 12], 11 + QUAD $0x0c0c0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 12], 12 + QUAD $0x0c2f74203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdi + r13 + 12], 13 + LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] + QUAD $0x0c3f74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdi + r15 + 12], 14 + LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] + QUAD $0x0c2f74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rdi + r13 + 12], 15 + QUAD $0x0d277c203a0f4666; BYTE $0x01 // pinsrb xmm15, byte [rdi + r12 + 13], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x0d177c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rdx + 13], 2 + QUAD $0x0d377c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdi + r14 + 13], 3 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + QUAD $0x0d0f7c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdi + r9 + 13], 4 + QUAD $0x0d377c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdi + rsi + 13], 5 + QUAD $0x0d077c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r8 + 13], 6 + QUAD $0x0d1f7c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r11 + 13], 7 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x0d177c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdi + rdx + 13], 8 + QUAD $0x0d0f7c203a0f4466; BYTE $0x09 // pinsrb xmm15, byte [rdi + rcx + 13], 9 + QUAD $0x0d1f7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdi + rbx + 13], 10 + QUAD $0x0d177c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdi + r10 + 13], 11 + QUAD $0x0d077c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rdi + rax + 13], 12 + LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] + QUAD $0x0d2f7c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdi + r13 + 13], 13 + QUAD $0x0d3f7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdi + r15 + 13], 14 QUAD $0x000001108ddb0f66 // pand xmm1, oword 272[rbp] /* [rip + .LCPI10_17] */ QUAD $0x0001208ddb0f4466; BYTE $0x00 // pand xmm9, oword 288[rbp] /* [rip + .LCPI10_18] */ LONG $0xeb0f4466; BYTE $0xc9 // por xmm9, xmm1 QUAD $0x0000009024848b48 // mov rax, qword [rsp + 144] - LONG $0x0654b60f; BYTE $0x17 // movzx edx, byte [rsi + rax + 23] + LONG $0x0754b60f; BYTE $0x17 // movzx edx, byte [rdi + rax + 23] LONG $0x6e0f4466; BYTE $0xc2 // movd xmm8, edx - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x0d2e7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r13 + 13], 15 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + QUAD $0x0d077c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdi + r8 + 13], 15 LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 LONG $0xce6f0f66 // movdqa xmm1, xmm6 LONG $0xde0f4166; BYTE $0xcd // pmaxub xmm1, xmm13 @@ -52690,213 +55298,212 @@ LBB10_67: LONG $0x6f0f4166; BYTE $0xff // movdqa xmm7, xmm15 LONG $0xde0f4166; BYTE $0xfd // pmaxub xmm7, xmm13 LONG $0x740f4166; BYTE $0xff // pcmpeqb xmm7, xmm15 - LONG $0x0654b60f; BYTE $0x19 // movzx edx, byte [rsi + rax + 25] + LONG $0x0754b60f; BYTE $0x19 // movzx edx, byte [rdi + rax + 25] LONG $0x6e0f4466; BYTE $0xfa // movd xmm15, edx - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0e0674203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rsi + rax + 14], 1 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x0e3774203a0f4666; BYTE $0x01 // pinsrb xmm14, byte [rdi + r14 + 14], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0e0774203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rdi + rax + 14], 2 + QUAD $0x0e2774203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdi + r12 + 14], 3 + QUAD $0x0e0f74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rdi + r9 + 14], 4 + QUAD $0x0e3774203a0f4466; BYTE $0x05 // pinsrb xmm14, byte [rdi + rsi + 14], 5 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + QUAD $0x000000e024948b48 // mov rdx, qword [rsp + 224] + QUAD $0x0e1774203a0f4466; BYTE $0x06 // pinsrb xmm14, byte [rdi + rdx + 14], 6 + QUAD $0x0e1f74203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdi + r11 + 14], 7 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x0e3f74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdi + r15 + 14], 8 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + QUAD $0x0e0f74203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdi + rcx + 14], 9 + QUAD $0x0e1f74203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdi + rbx + 14], 10 + WORD $0x894c; BYTE $0xd6 // mov rsi, r10 + QUAD $0x0e1774203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdi + r10 + 14], 11 QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - QUAD $0x0e0e74203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rsi + rcx + 14], 2 - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - QUAD $0x0e1674203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rsi + r10 + 14], 3 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x0e1674203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rsi + rdx + 14], 4 - QUAD $0x0e0674203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rsi + r8 + 14], 5 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - QUAD $0x0e3674203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rsi + r14 + 14], 6 - QUAD $0x0e1e74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rsi + rbx + 14], 7 - QUAD $0x0e3e74203a0f4466; BYTE $0x08 // pinsrb xmm14, byte [rsi + rdi + 14], 8 - WORD $0x8949; BYTE $0xfe // mov r14, rdi - QUAD $0x0e0e74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rsi + r9 + 14], 9 - QUAD $0x0e3e74203a0f4666; BYTE $0x0a // pinsrb xmm14, byte [rsi + r15 + 14], 10 - QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] - QUAD $0x0e3e74203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rsi + rdi + 14], 11 - QUAD $0x0e2674203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rsi + r12 + 14], 12 - QUAD $0x0e1e74203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rsi + r11 + 14], 13 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x0e3e74203a0f4466; BYTE $0x0e // pinsrb xmm14, byte [rsi + rdi + 14], 14 - QUAD $0x0e2e74203a0f4666; BYTE $0x0f // pinsrb xmm14, byte [rsi + r13 + 14], 15 - QUAD $0x0f065c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rsi + rax + 15], 1 - QUAD $0x0f0e5c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rsi + rcx + 15], 2 - QUAD $0x0f165c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rsi + r10 + 15], 3 - QUAD $0x0f165c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rsi + rdx + 15], 4 - WORD $0x8948; BYTE $0xd1 // mov rcx, rdx - LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x0f165c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rsi + rdx + 15], 5 - QUAD $0x0f065c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rsi + r8 + 15], 6 - QUAD $0x0f1e5c203a0f4466; BYTE $0x07 // pinsrb xmm11, byte [rsi + rbx + 15], 7 - QUAD $0x0f365c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rsi + r14 + 15], 8 - QUAD $0x0f0e5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rsi + r9 + 15], 9 - QUAD $0x0f3e5c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rsi + r15 + 15], 10 - QUAD $0x000000a024848b4c // mov r8, qword [rsp + 160] - QUAD $0x0f065c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rsi + r8 + 15], 11 - QUAD $0x0f265c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rsi + r12 + 15], 12 - QUAD $0x0f1e5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rsi + r11 + 15], 13 - QUAD $0x0f3e5c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rsi + rdi + 15], 14 - QUAD $0x0f2e5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rsi + r13 + 15], 15 + QUAD $0x0e0f74203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rdi + rcx + 14], 12 + QUAD $0x0e2f74203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rdi + r13 + 14], 13 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x0e1774203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdi + r10 + 14], 14 + QUAD $0x0e0774203a0f4666; BYTE $0x0f // pinsrb xmm14, byte [rdi + r8 + 14], 15 + QUAD $0x0f375c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdi + r14 + 15], 1 + QUAD $0x0f075c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdi + rax + 15], 2 + QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] + QUAD $0x0f075c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rdi + rax + 15], 3 + QUAD $0x0f0f5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdi + r9 + 15], 4 + QUAD $0x0f275c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdi + r12 + 15], 5 + QUAD $0x000000e024848b4c // mov r8, qword [rsp + 224] + QUAD $0x0f075c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdi + r8 + 15], 6 + QUAD $0x0f1f5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdi + r11 + 15], 7 + QUAD $0x0f3f5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdi + r15 + 15], 8 + QUAD $0x0f175c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdi + rdx + 15], 9 + QUAD $0x0f1f5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdi + rbx + 15], 10 + QUAD $0x0f375c203a0f4466; BYTE $0x0b // pinsrb xmm11, byte [rdi + rsi + 15], 11 + QUAD $0x0f0f5c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rdi + rcx + 15], 12 + QUAD $0x0f2f5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdi + r13 + 15], 13 + QUAD $0x0f175c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdi + r10 + 15], 14 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + QUAD $0x0f075c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdi + rax + 15], 15 QUAD $0x000001308ddb0f66 // pand xmm1, oword 304[rbp] /* [rip + .LCPI10_19] */ QUAD $0x00000140bddb0f66 // pand xmm7, oword 320[rbp] /* [rip + .LCPI10_20] */ LONG $0xf9eb0f66 // por xmm7, xmm1 LONG $0x6f0f4166; BYTE $0xce // movdqa xmm1, xmm14 LONG $0xde0f4166; BYTE $0xcd // pmaxub xmm1, xmm13 LONG $0x740f4166; BYTE $0xce // pcmpeqb xmm1, xmm14 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - LONG $0x3e54b60f; BYTE $0x1a // movzx edx, byte [rsi + rdi + 26] + QUAD $0x0000009024948b4c // mov r10, qword [rsp + 144] + LONG $0x54b60f42; WORD $0x1a17 // movzx edx, byte [rdi + r10 + 26] LONG $0xf26e0f66 // movd xmm6, edx QUAD $0x000001508ddb0f66 // pand xmm1, oword 336[rbp] /* [rip + .LCPI10_21] */ LONG $0xcfeb0f66 // por xmm1, xmm7 - LONG $0x3e54b60f; BYTE $0x1b // movzx edx, byte [rsi + rdi + 27] + LONG $0x54b60f42; WORD $0x1b17 // movzx edx, byte [rdi + r10 + 27] LONG $0xfa6e0f66 // movd xmm7, edx LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 LONG $0x6f0f4566; BYTE $0xf3 // movdqa xmm14, xmm11 LONG $0xde0f4566; BYTE $0xf5 // pmaxub xmm14, xmm13 LONG $0x740f4566; BYTE $0xf3 // pcmpeqb xmm14, xmm11 - LONG $0x3e54b60f; BYTE $0x1c // movzx edx, byte [rsi + rdi + 28] + LONG $0x54b60f42; WORD $0x1c17 // movzx edx, byte [rdi + r10 + 28] LONG $0x6e0f4466; BYTE $0xca // movd xmm9, edx - QUAD $0x01110644203a0f66 // pinsrb xmm0, byte [rsi + rax + 17], 1 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x02110644203a0f66 // pinsrb xmm0, byte [rsi + rax + 17], 2 - QUAD $0x111644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r10 + 17], 3 - QUAD $0x04110e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 17], 4 + QUAD $0x113744203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdi + r14 + 17], 1 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x02110f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 17], 2 + QUAD $0x000000a024a48b4c // mov r12, qword [rsp + 160] + QUAD $0x112744203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdi + r12 + 17], 3 + QUAD $0x110f44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdi + r9 + 17], 4 + QUAD $0x000000d024b48b48 // mov rsi, qword [rsp + 208] + QUAD $0x05113744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 17], 5 + QUAD $0x110744203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r8 + 17], 6 + QUAD $0x111f44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r11 + 17], 7 + LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] + QUAD $0x08111744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 17], 8 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x09111744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 17], 9 + QUAD $0x0a111f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 17], 10 + QUAD $0x000000b024bc8b4c // mov r15, qword [rsp + 176] + QUAD $0x113f44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdi + r15 + 17], 11 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x112f44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdi + r13 + 17], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0d111744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 17], 13 LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] - QUAD $0x05111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 5 - QUAD $0x00000120248c8b4c // mov r9, qword [rsp + 288] - QUAD $0x110e44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rsi + r9 + 17], 6 - QUAD $0x07111e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 17], 7 - QUAD $0x00000100249c8b4c // mov r11, qword [rsp + 256] - QUAD $0x111e44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r11 + 17], 8 - QUAD $0x0000013024bc8b4c // mov r15, qword [rsp + 304] - QUAD $0x113e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r15 + 17], 9 - QUAD $0x000000b024948b48 // mov rdx, qword [rsp + 176] - QUAD $0x0a111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 10 - QUAD $0x110644203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r8 + 17], 11 - QUAD $0x112644203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r12 + 17], 12 - LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] - QUAD $0x112e44203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r13 + 17], 13 - LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] - QUAD $0x113644203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rsi + r14 + 17], 14 - LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] - QUAD $0x0f111644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 17], 15 + QUAD $0x0e111744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 17], 14 + QUAD $0x0f110744203a0f66 // pinsrb xmm0, byte [rdi + rax + 17], 15 LONG $0xdb0f4466; WORD $0x6075 // pand xmm14, oword 96[rbp] /* [rip + .LCPI10_6] */ LONG $0xeb0f4466; BYTE $0xf1 // por xmm14, xmm1 LONG $0xc86f0f66 // movdqa xmm1, xmm0 LONG $0x6f0f4566; BYTE $0xe5 // movdqa xmm12, xmm13 LONG $0xde0f4166; BYTE $0xcd // pmaxub xmm1, xmm13 LONG $0xc8740f66 // pcmpeqb xmm1, xmm0 - LONG $0x3e54b60f; BYTE $0x1d // movzx edx, byte [rsi + rdi + 29] + LONG $0x54b60f42; WORD $0x1d17 // movzx edx, byte [rdi + r10 + 29] LONG $0xc26e0f66 // movd xmm0, edx - LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] - QUAD $0x01121664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 18], 1 - QUAD $0x02120664203a0f66 // pinsrb xmm4, byte [rsi + rax + 18], 2 - QUAD $0x121664203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r10 + 18], 3 - QUAD $0x04120e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 18], 4 - LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] - QUAD $0x05120e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 18], 5 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - QUAD $0x120e64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rsi + r9 + 18], 6 - QUAD $0x07121e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 18], 7 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - QUAD $0x121e64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r11 + 18], 8 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - QUAD $0x123e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r15 + 18], 9 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x121e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r11 + 18], 10 - QUAD $0x000000a024bc8b4c // mov r15, qword [rsp + 160] - QUAD $0x123e64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r15 + 18], 11 - QUAD $0x122664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r12 + 18], 12 - WORD $0x894c; BYTE $0xea // mov rdx, r13 - QUAD $0x122e64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r13 + 18], 13 - QUAD $0x123664203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rsi + r14 + 18], 14 - LONG $0x246c8b4c; BYTE $0x20 // mov r13, qword [rsp + 32] - QUAD $0x122e64203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r13 + 18], 15 + QUAD $0x123764203a0f4266; BYTE $0x01 // pinsrb xmm4, byte [rdi + r14 + 18], 1 + QUAD $0x02120f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 18], 2 + QUAD $0x122764203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdi + r12 + 18], 3 + QUAD $0x120f64203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdi + r9 + 18], 4 + QUAD $0x05123764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 18], 5 + QUAD $0x120764203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r8 + 18], 6 + QUAD $0x121f64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r11 + 18], 7 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x08120f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 18], 8 + QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + QUAD $0x121764203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdi + r10 + 18], 9 + WORD $0x8949; BYTE $0xd9 // mov r9, rbx + QUAD $0x0a121f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 18], 10 + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + QUAD $0x123f64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdi + r15 + 18], 11 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x122f64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdi + r13 + 18], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0d121764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 18], 13 + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + QUAD $0x122f64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdi + r13 + 18], 14 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0113066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 1 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x0213066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 2 - QUAD $0x13166c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r10 + 19], 3 - LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] - QUAD $0x0413066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 4 - QUAD $0x05130e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 19], 5 - QUAD $0x06133e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 19], 6 - QUAD $0x07131e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 19], 7 - QUAD $0x13066c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r8 + 19], 8 - WORD $0x894d; BYTE $0xc6 // mov r14, r8 - QUAD $0x130e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r9 + 19], 9 - QUAD $0x131e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r11 + 19], 10 - QUAD $0x133e6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r15 + 19], 11 - QUAD $0x13266c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r12 + 19], 12 - QUAD $0x0d13166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 19], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e13066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 19], 14 - QUAD $0x132e6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r13 + 19], 15 + QUAD $0x0f120764203a0f66 // pinsrb xmm4, byte [rdi + rax + 18], 15 + LONG $0x24748b4c; BYTE $0x60 // mov r14, qword [rsp + 96] + QUAD $0x13376c203a0f4266; BYTE $0x01 // pinsrb xmm5, byte [rdi + r14 + 19], 1 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x0213076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 19], 2 + QUAD $0x13276c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r12 + 19], 3 + QUAD $0x0000011024848b48 // mov rax, qword [rsp + 272] + QUAD $0x0413076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 19], 4 + QUAD $0x0513376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 19], 5 + QUAD $0x13076c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r8 + 19], 6 + QUAD $0x131f6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r11 + 19], 7 + QUAD $0x08130f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 19], 8 + QUAD $0x13176c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r10 + 19], 9 + QUAD $0x130f6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r9 + 19], 10 + QUAD $0x0b131f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 19], 11 + QUAD $0x133f6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdi + r15 + 19], 12 + QUAD $0x0d13176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 19], 13 + QUAD $0x132f6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdi + r13 + 19], 14 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0f13176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 19], 15 QUAD $0x000001008ddb0f66 // pand xmm1, oword 256[rbp] /* [rip + .LCPI10_16] */ - QUAD $0x000170248cf80f66; BYTE $0x00 // psubb xmm1, oword [rsp + 368] + QUAD $0x000160248cf80f66; BYTE $0x00 // psubb xmm1, oword [rsp + 352] LONG $0x6f0f4466; BYTE $0xec // movdqa xmm13, xmm4 LONG $0xde0f4566; BYTE $0xec // pmaxub xmm13, xmm12 LONG $0x740f4466; BYTE $0xec // pcmpeqb xmm13, xmm4 LONG $0x6f0f4466; BYTE $0xdd // movdqa xmm11, xmm5 LONG $0xde0f4566; BYTE $0xdc // pmaxub xmm11, xmm12 LONG $0x740f4466; BYTE $0xdd // pcmpeqb xmm11, xmm5 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - LONG $0x54b60f42; WORD $0x1e06 // movzx edx, byte [rsi + r8 + 30] + QUAD $0x0000009024b48b4c // mov r14, qword [rsp + 144] + LONG $0x54b60f42; WORD $0x1e37 // movzx edx, byte [rdi + r14 + 30] LONG $0xe26e0f66 // movd xmm4, edx - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x01140654203a0f66 // pinsrb xmm2, byte [rsi + rax + 20], 1 - QUAD $0x0115065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 21], 1 - QUAD $0x160654203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rsi + rax + 22], 1 - QUAD $0x170644203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rsi + rax + 23], 1 - QUAD $0x19067c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rsi + rax + 25], 1 - QUAD $0x011a0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 26], 1 - QUAD $0x011b067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 27], 1 - QUAD $0x1c064c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rsi + rax + 28], 1 - QUAD $0x011d0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 29], 1 - LONG $0x54b60f42; WORD $0x1f06 // movzx edx, byte [rsi + r8 + 31] - QUAD $0x011e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 30], 1 - LONG $0xea6e0f66 // movd xmm5, edx - QUAD $0x011f066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 31], 1 - QUAD $0x0000008024848b48 // mov rax, qword [rsp + 128] - QUAD $0x02140654203a0f66 // pinsrb xmm2, byte [rsi + rax + 20], 2 - QUAD $0x0215065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 21], 2 - QUAD $0x160654203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rsi + rax + 22], 2 - QUAD $0x170644203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rsi + rax + 23], 2 - QUAD $0x19067c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rsi + rax + 25], 2 - QUAD $0x021a0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 26], 2 - QUAD $0x021b067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 27], 2 - QUAD $0x1c064c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rsi + rax + 28], 2 - QUAD $0x021d0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 29], 2 - QUAD $0x021e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 30], 2 - QUAD $0x021f066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 31], 2 - QUAD $0x141654203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rsi + r10 + 20], 3 - LONG $0x24548b48; BYTE $0x70 // mov rdx, qword [rsp + 112] - QUAD $0x04141654203a0f66 // pinsrb xmm2, byte [rsi + rdx + 20], 4 - QUAD $0x05140e54203a0f66 // pinsrb xmm2, byte [rsi + rcx + 20], 5 - QUAD $0x06143e54203a0f66 // pinsrb xmm2, byte [rsi + rdi + 20], 6 - QUAD $0x07141e54203a0f66 // pinsrb xmm2, byte [rsi + rbx + 20], 7 - QUAD $0x143654203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rsi + r14 + 20], 8 - QUAD $0x140e54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rsi + r9 + 20], 9 - QUAD $0x141e54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rsi + r11 + 20], 10 - QUAD $0x143e54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rsi + r15 + 20], 11 - QUAD $0x142654203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rsi + r12 + 20], 12 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x140654203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rsi + r8 + 20], 13 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0e140654203a0f66 // pinsrb xmm2, byte [rsi + rax + 20], 14 - QUAD $0x142e54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rsi + r13 + 20], 15 - QUAD $0x15165c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rsi + r10 + 21], 3 - QUAD $0x0415165c203a0f66 // pinsrb xmm3, byte [rsi + rdx + 21], 4 - QUAD $0x05150e5c203a0f66 // pinsrb xmm3, byte [rsi + rcx + 21], 5 - QUAD $0x06153e5c203a0f66 // pinsrb xmm3, byte [rsi + rdi + 21], 6 - QUAD $0x07151e5c203a0f66 // pinsrb xmm3, byte [rsi + rbx + 21], 7 - QUAD $0x15365c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rsi + r14 + 21], 8 - QUAD $0x150e5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rsi + r9 + 21], 9 - QUAD $0x151e5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rsi + r11 + 21], 10 - QUAD $0x153e5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rsi + r15 + 21], 11 - QUAD $0x15265c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rsi + r12 + 21], 12 - QUAD $0x15065c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rsi + r8 + 21], 13 - QUAD $0x0e15065c203a0f66 // pinsrb xmm3, byte [rsi + rax + 21], 14 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x01141754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 20], 1 + QUAD $0x0115175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 21], 1 + QUAD $0x161754203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdi + rdx + 22], 1 + QUAD $0x171744203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdi + rdx + 23], 1 + QUAD $0x19177c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdi + rdx + 25], 1 + QUAD $0x011a1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 26], 1 + QUAD $0x011b177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 27], 1 + QUAD $0x1c174c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdi + rdx + 28], 1 + QUAD $0x011d1744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 29], 1 + LONG $0x74b60f46; WORD $0x1f37 // movzx r14d, byte [rdi + r14 + 31] + QUAD $0x011e1764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 30], 1 + LONG $0x6e0f4166; BYTE $0xee // movd xmm5, r14d + QUAD $0x011f176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 31], 1 + LONG $0x24548b48; BYTE $0x20 // mov rdx, qword [rsp + 32] + QUAD $0x02141754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 20], 2 + QUAD $0x0215175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 21], 2 + QUAD $0x161754203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdi + rdx + 22], 2 + QUAD $0x171744203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdi + rdx + 23], 2 + QUAD $0x19177c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdi + rdx + 25], 2 + QUAD $0x021a1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 26], 2 + QUAD $0x021b177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 27], 2 + QUAD $0x1c174c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdi + rdx + 28], 2 + QUAD $0x021d1744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 29], 2 + QUAD $0x021e1764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 30], 2 + QUAD $0x021f176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 31], 2 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + QUAD $0x142754203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdi + r12 + 20], 3 + QUAD $0x04140754203a0f66 // pinsrb xmm2, byte [rdi + rax + 20], 4 + QUAD $0x05143754203a0f66 // pinsrb xmm2, byte [rdi + rsi + 20], 5 + QUAD $0x140754203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdi + r8 + 20], 6 + QUAD $0x141f54203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdi + r11 + 20], 7 + QUAD $0x08140f54203a0f66 // pinsrb xmm2, byte [rdi + rcx + 20], 8 + QUAD $0x141754203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdi + r10 + 20], 9 + QUAD $0x140f54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdi + r9 + 20], 10 + QUAD $0x0b141f54203a0f66 // pinsrb xmm2, byte [rdi + rbx + 20], 11 + QUAD $0x143f54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdi + r15 + 20], 12 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x142754203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdi + r12 + 20], 13 + QUAD $0x142f54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdi + r13 + 20], 14 + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + QUAD $0x0f141754203a0f66 // pinsrb xmm2, byte [rdi + rdx + 20], 15 + QUAD $0x15375c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdi + r14 + 21], 3 + QUAD $0x0415075c203a0f66 // pinsrb xmm3, byte [rdi + rax + 21], 4 + QUAD $0x0515375c203a0f66 // pinsrb xmm3, byte [rdi + rsi + 21], 5 + QUAD $0x15075c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdi + r8 + 21], 6 + QUAD $0x151f5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdi + r11 + 21], 7 + QUAD $0x08150f5c203a0f66 // pinsrb xmm3, byte [rdi + rcx + 21], 8 + QUAD $0x15175c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdi + r10 + 21], 9 + QUAD $0x150f5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdi + r9 + 21], 10 + QUAD $0x0b151f5c203a0f66 // pinsrb xmm3, byte [rdi + rbx + 21], 11 + QUAD $0x153f5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdi + r15 + 21], 12 + QUAD $0x15275c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdi + r12 + 21], 13 + QUAD $0x152f5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdi + r13 + 21], 14 QUAD $0x000110addb0f4466; BYTE $0x00 // pand xmm13, oword 272[rbp] /* [rip + .LCPI10_17] */ QUAD $0x0001209ddb0f4466; BYTE $0x00 // pand xmm11, oword 288[rbp] /* [rip + .LCPI10_18] */ LONG $0xeb0f4566; BYTE $0xdd // por xmm11, xmm13 - QUAD $0x152e5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rsi + r13 + 21], 15 + QUAD $0x0f15175c203a0f66 // pinsrb xmm3, byte [rdi + rdx + 21], 15 LONG $0xeb0f4466; BYTE $0xd9 // por xmm11, xmm1 LONG $0xca6f0f66 // movdqa xmm1, xmm2 LONG $0xde0f4166; BYTE $0xcc // pmaxub xmm1, xmm12 @@ -52904,1209 +55511,204 @@ LBB10_67: LONG $0xd36f0f66 // movdqa xmm2, xmm3 LONG $0xde0f4166; BYTE $0xd4 // pmaxub xmm2, xmm12 LONG $0xd3740f66 // pcmpeqb xmm2, xmm3 - QUAD $0x161654203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rsi + r10 + 22], 3 - QUAD $0x161654203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rsi + rdx + 22], 4 - QUAD $0x160e54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rsi + rcx + 22], 5 - QUAD $0x163e54203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rsi + rdi + 22], 6 - QUAD $0x161e54203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rsi + rbx + 22], 7 - QUAD $0x163654203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rsi + r14 + 22], 8 - QUAD $0x160e54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rsi + r9 + 22], 9 - QUAD $0x161e54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rsi + r11 + 22], 10 - QUAD $0x163e54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rsi + r15 + 22], 11 - QUAD $0x162654203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rsi + r12 + 22], 12 - QUAD $0x160654203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rsi + r8 + 22], 13 - QUAD $0x160654203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rsi + rax + 22], 14 - QUAD $0x162e54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rsi + r13 + 22], 15 - QUAD $0x171644203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rsi + r10 + 23], 3 - QUAD $0x171644203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rsi + rdx + 23], 4 - QUAD $0x170e44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rsi + rcx + 23], 5 - QUAD $0x173e44203a0f4466; BYTE $0x06 // pinsrb xmm8, byte [rsi + rdi + 23], 6 - QUAD $0x171e44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rsi + rbx + 23], 7 - QUAD $0x173644203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rsi + r14 + 23], 8 - QUAD $0x170e44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rsi + r9 + 23], 9 - QUAD $0x171e44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rsi + r11 + 23], 10 - QUAD $0x173e44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rsi + r15 + 23], 11 - QUAD $0x172644203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rsi + r12 + 23], 12 - QUAD $0x170644203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rsi + r8 + 23], 13 + QUAD $0x163754203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdi + r14 + 22], 3 + QUAD $0x160754203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdi + rax + 22], 4 + QUAD $0x163754203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdi + rsi + 22], 5 + QUAD $0x160754203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdi + r8 + 22], 6 + QUAD $0x161f54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdi + r11 + 22], 7 + QUAD $0x160f54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rdi + rcx + 22], 8 + QUAD $0x161754203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdi + r10 + 22], 9 + QUAD $0x160f54203a0f4666; BYTE $0x0a // pinsrb xmm10, byte [rdi + r9 + 22], 10 + QUAD $0x161f54203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rdi + rbx + 22], 11 + QUAD $0x163f54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdi + r15 + 22], 12 + QUAD $0x162754203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdi + r12 + 22], 13 + QUAD $0x162f54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdi + r13 + 22], 14 + QUAD $0x161754203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdi + rdx + 22], 15 + QUAD $0x173744203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdi + r14 + 23], 3 + QUAD $0x170744203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rdi + rax + 23], 4 + QUAD $0x173744203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdi + rsi + 23], 5 + QUAD $0x170744203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdi + r8 + 23], 6 + QUAD $0x171f44203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdi + r11 + 23], 7 + QUAD $0x170f44203a0f4466; BYTE $0x08 // pinsrb xmm8, byte [rdi + rcx + 23], 8 + QUAD $0x171744203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdi + r10 + 23], 9 + QUAD $0x170f44203a0f4666; BYTE $0x0a // pinsrb xmm8, byte [rdi + r9 + 23], 10 + QUAD $0x171f44203a0f4466; BYTE $0x0b // pinsrb xmm8, byte [rdi + rbx + 23], 11 + QUAD $0x173f44203a0f4666; BYTE $0x0c // pinsrb xmm8, byte [rdi + r15 + 23], 12 + QUAD $0x172744203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rdi + r12 + 23], 13 QUAD $0x000001308ddb0f66 // pand xmm1, oword 304[rbp] /* [rip + .LCPI10_19] */ QUAD $0x0000014095db0f66 // pand xmm2, oword 320[rbp] /* [rip + .LCPI10_20] */ LONG $0xd1eb0f66 // por xmm2, xmm1 LONG $0x6f0f4166; BYTE $0xca // movdqa xmm1, xmm10 LONG $0xde0f4166; BYTE $0xcc // pmaxub xmm1, xmm12 LONG $0x740f4166; BYTE $0xca // pcmpeqb xmm1, xmm10 - QUAD $0x170644203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rsi + rax + 23], 14 + QUAD $0x172f44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdi + r13 + 23], 14 QUAD $0x000001508ddb0f66 // pand xmm1, oword 336[rbp] /* [rip + .LCPI10_21] */ LONG $0xcaeb0f66 // por xmm1, xmm2 - QUAD $0x172e44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rsi + r13 + 23], 15 + QUAD $0x171744203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rdi + rdx + 23], 15 LONG $0xeb0f4166; BYTE $0xcb // por xmm1, xmm11 LONG $0x6f0f4566; BYTE $0xd0 // movdqa xmm10, xmm8 LONG $0xde0f4566; BYTE $0xd4 // pmaxub xmm10, xmm12 LONG $0x740f4566; BYTE $0xd0 // pcmpeqb xmm10, xmm8 - QUAD $0x19167c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rsi + r10 + 25], 3 - QUAD $0x19167c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rsi + rdx + 25], 4 - QUAD $0x190e7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rsi + rcx + 25], 5 - QUAD $0x193e7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rsi + rdi + 25], 6 - QUAD $0x191e7c203a0f4466; BYTE $0x07 // pinsrb xmm15, byte [rsi + rbx + 25], 7 - QUAD $0x19367c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rsi + r14 + 25], 8 - QUAD $0x190e7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rsi + r9 + 25], 9 - QUAD $0x191e7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rsi + r11 + 25], 10 - QUAD $0x193e7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rsi + r15 + 25], 11 - QUAD $0x19267c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rsi + r12 + 25], 12 - QUAD $0x19067c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rsi + r8 + 25], 13 - QUAD $0x19067c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rsi + rax + 25], 14 - QUAD $0x192e7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rsi + r13 + 25], 15 + QUAD $0x19377c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdi + r14 + 25], 3 + QUAD $0x19077c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdi + rax + 25], 4 + QUAD $0x19377c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdi + rsi + 25], 5 + QUAD $0x19077c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdi + r8 + 25], 6 + QUAD $0x191f7c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdi + r11 + 25], 7 + QUAD $0x190f7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdi + rcx + 25], 8 + QUAD $0x19177c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdi + r10 + 25], 9 + QUAD $0x190f7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdi + r9 + 25], 10 + QUAD $0x191f7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rdi + rbx + 25], 11 + QUAD $0x193f7c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdi + r15 + 25], 12 + QUAD $0x19277c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdi + r12 + 25], 13 + QUAD $0x192f7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdi + r13 + 25], 14 + QUAD $0x19177c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rdi + rdx + 25], 15 LONG $0x6f0f4466; WORD $0x605d // movdqa xmm11, oword 96[rbp] /* [rip + .LCPI10_6] */ LONG $0xdb0f4566; BYTE $0xd3 // pand xmm10, xmm11 LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 LONG $0x6f0f4166; BYTE $0xdf // movdqa xmm3, xmm15 LONG $0xde0f4166; BYTE $0xdc // pmaxub xmm3, xmm12 LONG $0x740f4166; BYTE $0xdf // pcmpeqb xmm3, xmm15 - QUAD $0x1a1674203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rsi + r10 + 26], 3 - QUAD $0x041a1674203a0f66 // pinsrb xmm6, byte [rsi + rdx + 26], 4 - QUAD $0x051a0e74203a0f66 // pinsrb xmm6, byte [rsi + rcx + 26], 5 - QUAD $0x061a3e74203a0f66 // pinsrb xmm6, byte [rsi + rdi + 26], 6 - QUAD $0x071a1e74203a0f66 // pinsrb xmm6, byte [rsi + rbx + 26], 7 - QUAD $0x1a3674203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rsi + r14 + 26], 8 - QUAD $0x1a0e74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rsi + r9 + 26], 9 - QUAD $0x1a1e74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rsi + r11 + 26], 10 - QUAD $0x1a3e74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rsi + r15 + 26], 11 - QUAD $0x1a2674203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rsi + r12 + 26], 12 - QUAD $0x1a0674203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rsi + r8 + 26], 13 - QUAD $0x0e1a0674203a0f66 // pinsrb xmm6, byte [rsi + rax + 26], 14 - QUAD $0x1a2e74203a0f4266; BYTE $0x0f // pinsrb xmm6, byte [rsi + r13 + 26], 15 - QUAD $0x1b167c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rsi + r10 + 27], 3 - QUAD $0x041b167c203a0f66 // pinsrb xmm7, byte [rsi + rdx + 27], 4 - QUAD $0x051b0e7c203a0f66 // pinsrb xmm7, byte [rsi + rcx + 27], 5 - QUAD $0x061b3e7c203a0f66 // pinsrb xmm7, byte [rsi + rdi + 27], 6 - QUAD $0x071b1e7c203a0f66 // pinsrb xmm7, byte [rsi + rbx + 27], 7 - QUAD $0x1b367c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rsi + r14 + 27], 8 - QUAD $0x1b0e7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rsi + r9 + 27], 9 - QUAD $0x1b1e7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rsi + r11 + 27], 10 - QUAD $0x1b3e7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rsi + r15 + 27], 11 - QUAD $0x1b267c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rsi + r12 + 27], 12 - QUAD $0x1b067c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rsi + r8 + 27], 13 - QUAD $0x0e1b067c203a0f66 // pinsrb xmm7, byte [rsi + rax + 27], 14 - QUAD $0x1b2e7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rsi + r13 + 27], 15 + QUAD $0x1a3774203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdi + r14 + 26], 3 + QUAD $0x041a0774203a0f66 // pinsrb xmm6, byte [rdi + rax + 26], 4 + QUAD $0x051a3774203a0f66 // pinsrb xmm6, byte [rdi + rsi + 26], 5 + QUAD $0x1a0774203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdi + r8 + 26], 6 + QUAD $0x1a1f74203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdi + r11 + 26], 7 + QUAD $0x081a0f74203a0f66 // pinsrb xmm6, byte [rdi + rcx + 26], 8 + QUAD $0x1a1774203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdi + r10 + 26], 9 + QUAD $0x1a0f74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdi + r9 + 26], 10 + QUAD $0x0b1a1f74203a0f66 // pinsrb xmm6, byte [rdi + rbx + 26], 11 + QUAD $0x1a3f74203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdi + r15 + 26], 12 + QUAD $0x1a2774203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdi + r12 + 26], 13 + QUAD $0x1a2f74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdi + r13 + 26], 14 + QUAD $0x0f1a1774203a0f66 // pinsrb xmm6, byte [rdi + rdx + 26], 15 + QUAD $0x1b377c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdi + r14 + 27], 3 + QUAD $0x041b077c203a0f66 // pinsrb xmm7, byte [rdi + rax + 27], 4 + QUAD $0x051b377c203a0f66 // pinsrb xmm7, byte [rdi + rsi + 27], 5 + QUAD $0x1b077c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdi + r8 + 27], 6 + QUAD $0x1b1f7c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdi + r11 + 27], 7 + QUAD $0x081b0f7c203a0f66 // pinsrb xmm7, byte [rdi + rcx + 27], 8 + QUAD $0x1b177c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdi + r10 + 27], 9 + QUAD $0x1b0f7c203a0f4266; BYTE $0x0a // pinsrb xmm7, byte [rdi + r9 + 27], 10 + QUAD $0x0b1b1f7c203a0f66 // pinsrb xmm7, byte [rdi + rbx + 27], 11 + QUAD $0x1b3f7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdi + r15 + 27], 12 + QUAD $0x1b277c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rdi + r12 + 27], 13 + QUAD $0x1b2f7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdi + r13 + 27], 14 + QUAD $0x0f1b177c203a0f66 // pinsrb xmm7, byte [rdi + rdx + 27], 15 QUAD $0x000001009ddb0f66 // pand xmm3, oword 256[rbp] /* [rip + .LCPI10_16] */ - QUAD $0x0000f0249cf80f66; BYTE $0x00 // psubb xmm3, oword [rsp + 240] - LONG $0xd66f0f66 // movdqa xmm2, xmm6 - LONG $0xde0f4166; BYTE $0xd4 // pmaxub xmm2, xmm12 - LONG $0xd6740f66 // pcmpeqb xmm2, xmm6 - LONG $0xcf6f0f66 // movdqa xmm1, xmm7 - LONG $0xde0f4166; BYTE $0xcc // pmaxub xmm1, xmm12 - LONG $0xcf740f66 // pcmpeqb xmm1, xmm7 - QUAD $0x1c164c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rsi + r10 + 28], 3 - QUAD $0x1c164c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rsi + rdx + 28], 4 - QUAD $0x1c0e4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rsi + rcx + 28], 5 - QUAD $0x1c3e4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rsi + rdi + 28], 6 - QUAD $0x1c1e4c203a0f4466; BYTE $0x07 // pinsrb xmm9, byte [rsi + rbx + 28], 7 - QUAD $0x1c364c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rsi + r14 + 28], 8 - QUAD $0x1c0e4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rsi + r9 + 28], 9 - QUAD $0x1c1e4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rsi + r11 + 28], 10 - QUAD $0x1c3e4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rsi + r15 + 28], 11 - QUAD $0x1c264c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rsi + r12 + 28], 12 - QUAD $0x1c064c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rsi + r8 + 28], 13 - QUAD $0x1c064c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rsi + rax + 28], 14 - QUAD $0x1c2e4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rsi + r13 + 28], 15 - QUAD $0x1d1644203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rsi + r10 + 29], 3 - QUAD $0x041d1644203a0f66 // pinsrb xmm0, byte [rsi + rdx + 29], 4 - QUAD $0x051d0e44203a0f66 // pinsrb xmm0, byte [rsi + rcx + 29], 5 - QUAD $0x061d3e44203a0f66 // pinsrb xmm0, byte [rsi + rdi + 29], 6 - QUAD $0x071d1e44203a0f66 // pinsrb xmm0, byte [rsi + rbx + 29], 7 - QUAD $0x1d3644203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rsi + r14 + 29], 8 - QUAD $0x1d0e44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rsi + r9 + 29], 9 - QUAD $0x1d1e44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rsi + r11 + 29], 10 - QUAD $0x1d3e44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rsi + r15 + 29], 11 - QUAD $0x1d2644203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rsi + r12 + 29], 12 - QUAD $0x1d0644203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rsi + r8 + 29], 13 - QUAD $0x0e1d0644203a0f66 // pinsrb xmm0, byte [rsi + rax + 29], 14 - QUAD $0x1d2e44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rsi + r13 + 29], 15 - QUAD $0x0000011095db0f66 // pand xmm2, oword 272[rbp] /* [rip + .LCPI10_17] */ - QUAD $0x000001208ddb0f66 // pand xmm1, oword 288[rbp] /* [rip + .LCPI10_18] */ - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0xcbeb0f66 // por xmm1, xmm3 - LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 - LONG $0xde0f4166; BYTE $0xd4 // pmaxub xmm2, xmm12 - LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 - LONG $0xd86f0f66 // movdqa xmm3, xmm0 - LONG $0xde0f4166; BYTE $0xdc // pmaxub xmm3, xmm12 - LONG $0xd8740f66 // pcmpeqb xmm3, xmm0 - QUAD $0x1e1664203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rsi + r10 + 30], 3 - QUAD $0x1f166c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rsi + r10 + 31], 3 - QUAD $0x041e1664203a0f66 // pinsrb xmm4, byte [rsi + rdx + 30], 4 - QUAD $0x041f166c203a0f66 // pinsrb xmm5, byte [rsi + rdx + 31], 4 - QUAD $0x051e0e64203a0f66 // pinsrb xmm4, byte [rsi + rcx + 30], 5 - QUAD $0x051f0e6c203a0f66 // pinsrb xmm5, byte [rsi + rcx + 31], 5 - QUAD $0x061e3e64203a0f66 // pinsrb xmm4, byte [rsi + rdi + 30], 6 - QUAD $0x061f3e6c203a0f66 // pinsrb xmm5, byte [rsi + rdi + 31], 6 - QUAD $0x071e1e64203a0f66 // pinsrb xmm4, byte [rsi + rbx + 30], 7 - QUAD $0x071f1e6c203a0f66 // pinsrb xmm5, byte [rsi + rbx + 31], 7 - QUAD $0x1e3664203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rsi + r14 + 30], 8 - QUAD $0x1f366c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rsi + r14 + 31], 8 - QUAD $0x1e0e64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rsi + r9 + 30], 9 - QUAD $0x1f0e6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rsi + r9 + 31], 9 - QUAD $0x1e1e64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rsi + r11 + 30], 10 - QUAD $0x1f1e6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rsi + r11 + 31], 10 - QUAD $0x0000016024b48b4c // mov r14, qword [rsp + 352] - QUAD $0x1e3e64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rsi + r15 + 30], 11 - QUAD $0x1f3e6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rsi + r15 + 31], 11 - QUAD $0x1e2664203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rsi + r12 + 30], 12 - QUAD $0x1f266c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rsi + r12 + 31], 12 - QUAD $0x1e0664203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rsi + r8 + 30], 13 - QUAD $0x1f066c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rsi + r8 + 31], 13 - QUAD $0x0e1e0664203a0f66 // pinsrb xmm4, byte [rsi + rax + 30], 14 - QUAD $0x0e1f066c203a0f66 // pinsrb xmm5, byte [rsi + rax + 31], 14 - QUAD $0x1e2e64203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rsi + r13 + 30], 15 - QUAD $0x0000013095db0f66 // pand xmm2, oword 304[rbp] /* [rip + .LCPI10_19] */ - QUAD $0x000001409ddb0f66 // pand xmm3, oword 320[rbp] /* [rip + .LCPI10_20] */ - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0xde0f4166; BYTE $0xc4 // pmaxub xmm0, xmm12 - LONG $0xc4740f66 // pcmpeqb xmm0, xmm4 - QUAD $0x1f2e6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rsi + r13 + 31], 15 - QUAD $0x0000015085db0f66 // pand xmm0, oword 336[rbp] /* [rip + .LCPI10_21] */ - LONG $0xc3eb0f66 // por xmm0, xmm3 - LONG $0xc1eb0f66 // por xmm0, xmm1 - LONG $0xcd6f0f66 // movdqa xmm1, xmm5 - LONG $0xde0f4166; BYTE $0xcc // pmaxub xmm1, xmm12 - LONG $0xcd740f66 // pcmpeqb xmm1, xmm5 - LONG $0xdb0f4166; BYTE $0xcb // pand xmm1, xmm11 - LONG $0xc8eb0f66 // por xmm1, xmm0 - LONG $0x6f0f4166; BYTE $0xc2 // movdqa xmm0, xmm10 - LONG $0xc1600f66 // punpcklbw xmm0, xmm1 - QUAD $0x00011024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 272] - LONG $0xd46f0f66 // movdqa xmm2, xmm4 - LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 - LONG $0xda6f0f66 // movdqa xmm3, xmm2 - LONG $0xd8610f66 // punpcklwd xmm3, xmm0 - LONG $0xd0690f66 // punpckhwd xmm2, xmm0 - LONG $0x680f4466; BYTE $0xd1 // punpckhbw xmm10, xmm1 - LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x610f4166; BYTE $0xc2 // punpcklwd xmm0, xmm10 - LONG $0x690f4166; BYTE $0xe2 // punpckhwd xmm4, xmm10 - QUAD $0x00000150248c8b48 // mov rcx, qword [rsp + 336] - LONG $0x7f0f41f3; WORD $0x8e64; BYTE $0x30 // movdqu oword [r14 + 4*rcx + 48], xmm4 - LONG $0x7f0f41f3; WORD $0x8e44; BYTE $0x20 // movdqu oword [r14 + 4*rcx + 32], xmm0 - LONG $0x7f0f41f3; WORD $0x8e54; BYTE $0x10 // movdqu oword [r14 + 4*rcx + 16], xmm2 - LONG $0x7f0f41f3; WORD $0x8e1c // movdqu oword [r14 + 4*rcx], xmm3 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000001a0248c3b48 // cmp rcx, qword [rsp + 416] - JNE LBB10_67 - QUAD $0x000001d024bc8b4c // mov r15, qword [rsp + 464] - QUAD $0x000001a024bc3b4c // cmp r15, qword [rsp + 416] - LONG $0x245c8a44; BYTE $0x08 // mov r11b, byte [rsp + 8] - QUAD $0x0000018824b48b48 // mov rsi, qword [rsp + 392] - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] - JNE LBB10_69 - JMP LBB10_72 - -LBB10_124: - LONG $0xf8e78349 // and r15, -8 - WORD $0x894d; BYTE $0xfb // mov r11, r15 - LONG $0x06e3c149 // shl r11, 6 - WORD $0x0149; BYTE $0xf3 // add r11, rsi - QUAD $0x0000019024bc894c // mov qword [rsp + 400], r15 - LONG $0xbe048d4b // lea rax, [r14 + 4*r15] - LONG $0x24448948; BYTE $0x08 // mov qword [rsp + 8], rax - QUAD $0x00018824846e0f66; BYTE $0x00 // movd xmm0, dword [rsp + 392] - LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 - LONG $0xc0700f66; BYTE $0x00 // pshufd xmm0, xmm0, 0 - QUAD $0x0001d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 464], xmm0 - WORD $0x3145; BYTE $0xd2 // xor r10d, r10d - -LBB10_125: - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - LONG $0x06e1c149 // shl r9, 6 - WORD $0x894d; BYTE $0xc8 // mov r8, r9 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - WORD $0x894c; BYTE $0xcb // mov rbx, r9 - WORD $0x894d; BYTE $0xcf // mov r15, r9 - WORD $0x894d; BYTE $0xcc // mov r12, r9 - WORD $0x894d; BYTE $0xcd // mov r13, r9 - LONG $0x0cb70f42; BYTE $0x0e // movzx ecx, word [rsi + r9] - LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x4cb70f42; WORD $0x020e // movzx ecx, word [rsi + r9 + 2] - LONG $0xc16e0f66 // movd xmm0, ecx - LONG $0x447f0f66; WORD $0x1024 // movdqa oword [rsp + 16], xmm0 - LONG $0x4cb70f42; WORD $0x040e // movzx ecx, word [rsi + r9 + 4] - LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x4cb70f42; WORD $0x060e // movzx ecx, word [rsi + r9 + 6] - LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x4cb70f42; WORD $0x080e // movzx ecx, word [rsi + r9 + 8] - LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x4cb70f42; WORD $0x0a0e // movzx ecx, word [rsi + r9 + 10] - LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x4cb70f42; WORD $0x0c0e // movzx ecx, word [rsi + r9 + 12] - LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x4cb70f42; WORD $0x0e0e // movzx ecx, word [rsi + r9 + 14] - LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x4cb70f42; WORD $0x100e // movzx ecx, word [rsi + r9 + 16] - LONG $0xc96e0f66 // movd xmm1, ecx - LONG $0x4cb70f42; WORD $0x120e // movzx ecx, word [rsi + r9 + 18] - LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x4cb70f42; WORD $0x140e // movzx ecx, word [rsi + r9 + 20] - LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x4cb70f42; WORD $0x160e // movzx ecx, word [rsi + r9 + 22] - LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x4cb70f42; WORD $0x180e // movzx ecx, word [rsi + r9 + 24] - LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x4cb70f42; WORD $0x1a0e // movzx ecx, word [rsi + r9 + 26] - LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x44b70f42; WORD $0x1c0e // movzx eax, word [rsi + r9 + 28] - LONG $0x54b70f42; WORD $0x1e0e // movzx edx, word [rsi + r9 + 30] - WORD $0x894c; BYTE $0xc9 // mov rcx, r9 - LONG $0x40c98348 // or rcx, 64 - LONG $0x80c88149; WORD $0x0000; BYTE $0x00 // or r8, 128 - LONG $0xc0cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 192 - LONG $0x00cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 256 - LONG $0x40cf8149; WORD $0x0001; BYTE $0x00 // or r15, 320 - LONG $0x80cc8149; WORD $0x0001; BYTE $0x00 // or r12, 384 - LONG $0xc0cd8149; WORD $0x0001; BYTE $0x00 // or r13, 448 - LONG $0xc40f4466; WORD $0x0e1c; BYTE $0x01 // pinsrw xmm11, word [rsi + rcx], 1 - LONG $0xc40f4666; WORD $0x061c; BYTE $0x02 // pinsrw xmm11, word [rsi + r8], 2 - LONG $0xc40f4466; WORD $0x3e1c; BYTE $0x03 // pinsrw xmm11, word [rsi + rdi], 3 - LONG $0xc40f4466; WORD $0x1e1c; BYTE $0x04 // pinsrw xmm11, word [rsi + rbx], 4 - LONG $0xc40f4666; WORD $0x3e1c; BYTE $0x05 // pinsrw xmm11, word [rsi + r15], 5 - LONG $0xc40f4666; WORD $0x261c; BYTE $0x06 // pinsrw xmm11, word [rsi + r12], 6 - LONG $0xc40f4666; WORD $0x2e1c; BYTE $0x07 // pinsrw xmm11, word [rsi + r13], 7 - LONG $0x6e0f4466; BYTE $0xf8 // movd xmm15, eax - QUAD $0x0001d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 464] - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 - QUAD $0x00016024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 352], xmm7 - LONG $0x7c6f0f66; WORD $0x1024 // movdqa xmm7, oword [rsp + 16] - LONG $0x7cc40f66; WORD $0x020e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 2], 1 - QUAD $0x0202067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 2], 2 - LONG $0x7cc40f66; WORD $0x023e; BYTE $0x03 // pinsrw xmm7, word [rsi + rdi + 2], 3 - LONG $0x7cc40f66; WORD $0x021e; BYTE $0x04 // pinsrw xmm7, word [rsi + rbx + 2], 4 - QUAD $0x05023e7cc40f4266 // pinsrw xmm7, word [rsi + r15 + 2], 5 - QUAD $0x0602267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 2], 6 - QUAD $0x07022e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 2], 7 - LONG $0x6f0f4466; BYTE $0xd8 // movdqa xmm11, xmm0 - QUAD $0x01040e4cc40f4466 // pinsrw xmm9, word [rsi + rcx + 4], 1 - QUAD $0x0204064cc40f4666 // pinsrw xmm9, word [rsi + r8 + 4], 2 - QUAD $0x03043e4cc40f4466 // pinsrw xmm9, word [rsi + rdi + 4], 3 - QUAD $0x04041e4cc40f4466 // pinsrw xmm9, word [rsi + rbx + 4], 4 - QUAD $0x05043e4cc40f4666 // pinsrw xmm9, word [rsi + r15 + 4], 5 - QUAD $0x0604264cc40f4666 // pinsrw xmm9, word [rsi + r12 + 4], 6 - LONG $0x650f4466; BYTE $0xdf // pcmpgtw xmm11, xmm7 - QUAD $0x07042e4cc40f4666 // pinsrw xmm9, word [rsi + r13 + 4], 7 - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - LONG $0x650f4166; BYTE $0xf9 // pcmpgtw xmm7, xmm9 - LONG $0x7c7f0f66; WORD $0x5024 // movdqa oword [rsp + 80], xmm7 - QUAD $0x01060e54c40f4466 // pinsrw xmm10, word [rsi + rcx + 6], 1 - QUAD $0x02060654c40f4666 // pinsrw xmm10, word [rsi + r8 + 6], 2 - QUAD $0x03063e54c40f4466 // pinsrw xmm10, word [rsi + rdi + 6], 3 - QUAD $0x04061e54c40f4466 // pinsrw xmm10, word [rsi + rbx + 6], 4 - QUAD $0x05063e54c40f4666 // pinsrw xmm10, word [rsi + r15 + 6], 5 - QUAD $0x06062654c40f4666 // pinsrw xmm10, word [rsi + r12 + 6], 6 - QUAD $0x07062e54c40f4666 // pinsrw xmm10, word [rsi + r13 + 6], 7 - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - QUAD $0x01080e64c40f4466 // pinsrw xmm12, word [rsi + rcx + 8], 1 - QUAD $0x02080664c40f4666 // pinsrw xmm12, word [rsi + r8 + 8], 2 - QUAD $0x03083e64c40f4466 // pinsrw xmm12, word [rsi + rdi + 8], 3 - QUAD $0x04081e64c40f4466 // pinsrw xmm12, word [rsi + rbx + 8], 4 - QUAD $0x05083e64c40f4666 // pinsrw xmm12, word [rsi + r15 + 8], 5 - QUAD $0x06082664c40f4666 // pinsrw xmm12, word [rsi + r12 + 8], 6 - QUAD $0x07082e64c40f4666 // pinsrw xmm12, word [rsi + r13 + 8], 7 - LONG $0x650f4166; BYTE $0xfa // pcmpgtw xmm7, xmm10 - QUAD $0x00009024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm7 - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - LONG $0x650f4166; BYTE $0xfc // pcmpgtw xmm7, xmm12 - LONG $0x7c7f0f66; WORD $0x2024 // movdqa oword [rsp + 32], xmm7 - QUAD $0x010a0e6cc40f4466 // pinsrw xmm13, word [rsi + rcx + 10], 1 - QUAD $0x020a066cc40f4666 // pinsrw xmm13, word [rsi + r8 + 10], 2 - QUAD $0x030a3e6cc40f4466 // pinsrw xmm13, word [rsi + rdi + 10], 3 - QUAD $0x040a1e6cc40f4466 // pinsrw xmm13, word [rsi + rbx + 10], 4 - QUAD $0x050a3e6cc40f4666 // pinsrw xmm13, word [rsi + r15 + 10], 5 - QUAD $0x060a266cc40f4666 // pinsrw xmm13, word [rsi + r12 + 10], 6 - QUAD $0x070a2e6cc40f4666 // pinsrw xmm13, word [rsi + r13 + 10], 7 - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - QUAD $0x010c0e74c40f4466 // pinsrw xmm14, word [rsi + rcx + 12], 1 - QUAD $0x020c0674c40f4666 // pinsrw xmm14, word [rsi + r8 + 12], 2 - QUAD $0x030c3e74c40f4466 // pinsrw xmm14, word [rsi + rdi + 12], 3 - QUAD $0x040c1e74c40f4466 // pinsrw xmm14, word [rsi + rbx + 12], 4 - QUAD $0x050c3e74c40f4666 // pinsrw xmm14, word [rsi + r15 + 12], 5 - QUAD $0x060c2674c40f4666 // pinsrw xmm14, word [rsi + r12 + 12], 6 - LONG $0x650f4166; BYTE $0xfd // pcmpgtw xmm7, xmm13 - QUAD $0x00008024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 128], xmm7 - QUAD $0x070c2e74c40f4666 // pinsrw xmm14, word [rsi + r13 + 12], 7 - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - LONG $0x650f4166; BYTE $0xfe // pcmpgtw xmm7, xmm14 - LONG $0x6f0f4466; BYTE $0xf7 // movdqa xmm14, xmm7 - QUAD $0x010e0e44c40f4466 // pinsrw xmm8, word [rsi + rcx + 14], 1 - QUAD $0x020e0644c40f4666 // pinsrw xmm8, word [rsi + r8 + 14], 2 - QUAD $0x030e3e44c40f4466 // pinsrw xmm8, word [rsi + rdi + 14], 3 - QUAD $0x040e1e44c40f4466 // pinsrw xmm8, word [rsi + rbx + 14], 4 - QUAD $0x050e3e44c40f4666 // pinsrw xmm8, word [rsi + r15 + 14], 5 - QUAD $0x060e2644c40f4666 // pinsrw xmm8, word [rsi + r12 + 14], 6 - QUAD $0x070e2e44c40f4666 // pinsrw xmm8, word [rsi + r13 + 14], 7 - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - LONG $0x4cc40f66; WORD $0x100e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 16], 1 - QUAD $0x0210064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 16], 2 - LONG $0x4cc40f66; WORD $0x103e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 16], 3 - LONG $0x4cc40f66; WORD $0x101e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 16], 4 - QUAD $0x05103e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 16], 5 - QUAD $0x0610264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 16], 6 - QUAD $0x07102e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 16], 7 - LONG $0x650f4166; BYTE $0xf8 // pcmpgtw xmm7, xmm8 - LONG $0x7c7f0f66; WORD $0x6024 // movdqa oword [rsp + 96], xmm7 - LONG $0xf86f0f66 // movdqa xmm7, xmm0 - LONG $0xf9650f66 // pcmpgtw xmm7, xmm1 - QUAD $0x0001b024bc7f0f66; BYTE $0x00 // movdqa oword [rsp + 432], xmm7 - LONG $0x54c40f66; WORD $0x120e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 18], 1 - QUAD $0x02120654c40f4266 // pinsrw xmm2, word [rsi + r8 + 18], 2 - LONG $0x54c40f66; WORD $0x123e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 18], 3 - LONG $0x54c40f66; WORD $0x121e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 18], 4 - QUAD $0x05123e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 18], 5 - QUAD $0x06122654c40f4266 // pinsrw xmm2, word [rsi + r12 + 18], 6 - QUAD $0x07122e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 18], 7 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0x5cc40f66; WORD $0x140e; BYTE $0x01 // pinsrw xmm3, word [rsi + rcx + 20], 1 - QUAD $0x0214065cc40f4266 // pinsrw xmm3, word [rsi + r8 + 20], 2 - LONG $0x5cc40f66; WORD $0x143e; BYTE $0x03 // pinsrw xmm3, word [rsi + rdi + 20], 3 - LONG $0x5cc40f66; WORD $0x141e; BYTE $0x04 // pinsrw xmm3, word [rsi + rbx + 20], 4 - QUAD $0x05143e5cc40f4266 // pinsrw xmm3, word [rsi + r15 + 20], 5 - QUAD $0x0614265cc40f4266 // pinsrw xmm3, word [rsi + r12 + 20], 6 - LONG $0xca650f66 // pcmpgtw xmm1, xmm2 - QUAD $0x0000a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm1 - QUAD $0x07142e5cc40f4266 // pinsrw xmm3, word [rsi + r13 + 20], 7 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xcb650f66 // pcmpgtw xmm1, xmm3 - LONG $0x4c7f0f66; WORD $0x3024 // movdqa oword [rsp + 48], xmm1 - LONG $0x64c40f66; WORD $0x160e; BYTE $0x01 // pinsrw xmm4, word [rsi + rcx + 22], 1 - QUAD $0x02160664c40f4266 // pinsrw xmm4, word [rsi + r8 + 22], 2 - LONG $0x64c40f66; WORD $0x163e; BYTE $0x03 // pinsrw xmm4, word [rsi + rdi + 22], 3 - LONG $0x64c40f66; WORD $0x161e; BYTE $0x04 // pinsrw xmm4, word [rsi + rbx + 22], 4 - QUAD $0x05163e64c40f4266 // pinsrw xmm4, word [rsi + r15 + 22], 5 - QUAD $0x06162664c40f4266 // pinsrw xmm4, word [rsi + r12 + 22], 6 - QUAD $0x07162e64c40f4266 // pinsrw xmm4, word [rsi + r13 + 22], 7 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0x6cc40f66; WORD $0x180e; BYTE $0x01 // pinsrw xmm5, word [rsi + rcx + 24], 1 - QUAD $0x0218066cc40f4266 // pinsrw xmm5, word [rsi + r8 + 24], 2 - LONG $0x6cc40f66; WORD $0x183e; BYTE $0x03 // pinsrw xmm5, word [rsi + rdi + 24], 3 - LONG $0x6cc40f66; WORD $0x181e; BYTE $0x04 // pinsrw xmm5, word [rsi + rbx + 24], 4 - QUAD $0x05183e6cc40f4266 // pinsrw xmm5, word [rsi + r15 + 24], 5 - QUAD $0x0618266cc40f4266 // pinsrw xmm5, word [rsi + r12 + 24], 6 - QUAD $0x07182e6cc40f4266 // pinsrw xmm5, word [rsi + r13 + 24], 7 - LONG $0xcc650f66 // pcmpgtw xmm1, xmm4 - QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xcd650f66 // pcmpgtw xmm1, xmm5 - LONG $0x4c7f0f66; WORD $0x1024 // movdqa oword [rsp + 16], xmm1 - LONG $0x74c40f66; WORD $0x1a0e; BYTE $0x01 // pinsrw xmm6, word [rsi + rcx + 26], 1 - QUAD $0x021a0674c40f4266 // pinsrw xmm6, word [rsi + r8 + 26], 2 - LONG $0x74c40f66; WORD $0x1a3e; BYTE $0x03 // pinsrw xmm6, word [rsi + rdi + 26], 3 - LONG $0x74c40f66; WORD $0x1a1e; BYTE $0x04 // pinsrw xmm6, word [rsi + rbx + 26], 4 - QUAD $0x051a3e74c40f4266 // pinsrw xmm6, word [rsi + r15 + 26], 5 - QUAD $0x061a2674c40f4266 // pinsrw xmm6, word [rsi + r12 + 26], 6 - QUAD $0x071a2e74c40f4266 // pinsrw xmm6, word [rsi + r13 + 26], 7 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - QUAD $0x011c0e7cc40f4466 // pinsrw xmm15, word [rsi + rcx + 28], 1 - QUAD $0x021c067cc40f4666 // pinsrw xmm15, word [rsi + r8 + 28], 2 - QUAD $0x031c3e7cc40f4466 // pinsrw xmm15, word [rsi + rdi + 28], 3 - QUAD $0x041c1e7cc40f4466 // pinsrw xmm15, word [rsi + rbx + 28], 4 - QUAD $0x051c3e7cc40f4666 // pinsrw xmm15, word [rsi + r15 + 28], 5 - QUAD $0x061c267cc40f4666 // pinsrw xmm15, word [rsi + r12 + 28], 6 - LONG $0xce650f66 // pcmpgtw xmm1, xmm6 - QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 - QUAD $0x071c2e7cc40f4666 // pinsrw xmm15, word [rsi + r13 + 28], 7 - LONG $0xca6e0f66 // movd xmm1, edx - LONG $0x4cc40f66; WORD $0x1e0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 30], 1 - QUAD $0x021e064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 30], 2 - LONG $0x4cc40f66; WORD $0x1e3e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 30], 3 - LONG $0x4cc40f66; WORD $0x1e1e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 30], 4 - QUAD $0x051e3e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 30], 5 - QUAD $0x061e264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 30], 6 - LONG $0xd06f0f66 // movdqa xmm2, xmm0 - LONG $0x650f4166; BYTE $0xd7 // pcmpgtw xmm2, xmm15 - QUAD $0x0000e024947f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm2 - QUAD $0x071e2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 30], 7 - LONG $0xd06f0f66 // movdqa xmm2, xmm0 - LONG $0xd1650f66 // pcmpgtw xmm2, xmm1 - LONG $0x547f0f66; WORD $0x7024 // movdqa oword [rsp + 112], xmm2 - LONG $0x44b70f42; WORD $0x200e // movzx eax, word [rsi + r9 + 32] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x4cc40f66; WORD $0x200e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 32], 1 - QUAD $0x0220064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 32], 2 - LONG $0x4cc40f66; WORD $0x203e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 32], 3 - LONG $0x4cc40f66; WORD $0x201e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 32], 4 - QUAD $0x05203e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 32], 5 - QUAD $0x0620264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 32], 6 - QUAD $0x07202e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 32], 7 - LONG $0x44b70f42; WORD $0x220e // movzx eax, word [rsi + r9 + 34] - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x220e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 34], 1 - QUAD $0x02220654c40f4266 // pinsrw xmm2, word [rsi + r8 + 34], 2 - LONG $0x54c40f66; WORD $0x223e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 34], 3 - LONG $0x54c40f66; WORD $0x221e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 34], 4 - QUAD $0x05223e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 34], 5 - QUAD $0x06222654c40f4266 // pinsrw xmm2, word [rsi + r12 + 34], 6 - QUAD $0x07222e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 34], 7 - LONG $0xd86f0f66 // movdqa xmm3, xmm0 - LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 - QUAD $0x0000d0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm3 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xca650f66 // pcmpgtw xmm1, xmm2 - QUAD $0x000100248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm1 - LONG $0x44b70f42; WORD $0x240e // movzx eax, word [rsi + r9 + 36] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x4cc40f66; WORD $0x240e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 36], 1 - QUAD $0x0224064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 36], 2 - LONG $0x4cc40f66; WORD $0x243e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 36], 3 - LONG $0x4cc40f66; WORD $0x241e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 36], 4 - QUAD $0x05243e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 36], 5 - QUAD $0x0624264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 36], 6 - LONG $0x44b70f42; WORD $0x260e // movzx eax, word [rsi + r9 + 38] - QUAD $0x07242e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 36], 7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x260e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 38], 1 - QUAD $0x02260654c40f4266 // pinsrw xmm2, word [rsi + r8 + 38], 2 - LONG $0x54c40f66; WORD $0x263e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 38], 3 - LONG $0x54c40f66; WORD $0x261e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 38], 4 - QUAD $0x05263e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 38], 5 - QUAD $0x06262654c40f4266 // pinsrw xmm2, word [rsi + r12 + 38], 6 - LONG $0xd86f0f66 // movdqa xmm3, xmm0 - LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 - QUAD $0x000120249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 288], xmm3 - QUAD $0x07262e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 38], 7 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xca650f66 // pcmpgtw xmm1, xmm2 - QUAD $0x000130248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 304], xmm1 - LONG $0x44b70f42; WORD $0x280e // movzx eax, word [rsi + r9 + 40] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x4cc40f66; WORD $0x280e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 40], 1 - QUAD $0x0228064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 40], 2 - LONG $0x4cc40f66; WORD $0x283e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 40], 3 - LONG $0x4cc40f66; WORD $0x281e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 40], 4 - QUAD $0x05283e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 40], 5 - QUAD $0x0628264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 40], 6 - QUAD $0x07282e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 40], 7 - LONG $0x44b70f42; WORD $0x2a0e // movzx eax, word [rsi + r9 + 42] - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x2a0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 42], 1 - QUAD $0x022a0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 42], 2 - LONG $0x54c40f66; WORD $0x2a3e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 42], 3 - LONG $0x54c40f66; WORD $0x2a1e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 42], 4 - QUAD $0x052a3e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 42], 5 - QUAD $0x062a2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 42], 6 - QUAD $0x072a2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 42], 7 - LONG $0xd86f0f66 // movdqa xmm3, xmm0 - LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 - QUAD $0x000150249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 336], xmm3 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xca650f66 // pcmpgtw xmm1, xmm2 - QUAD $0x000110248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm1 - LONG $0x44b70f42; WORD $0x2c0e // movzx eax, word [rsi + r9 + 44] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x4cc40f66; WORD $0x2c0e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 44], 1 - QUAD $0x022c064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 44], 2 - LONG $0x4cc40f66; WORD $0x2c3e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 44], 3 - LONG $0x4cc40f66; WORD $0x2c1e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 44], 4 - QUAD $0x052c3e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 44], 5 - QUAD $0x062c264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 44], 6 - LONG $0x44b70f42; WORD $0x2e0e // movzx eax, word [rsi + r9 + 46] - QUAD $0x072c2e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 44], 7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x2e0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 46], 1 - QUAD $0x022e0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 46], 2 - LONG $0x54c40f66; WORD $0x2e3e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 46], 3 - LONG $0x54c40f66; WORD $0x2e1e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 46], 4 - QUAD $0x052e3e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 46], 5 - QUAD $0x062e2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 46], 6 - LONG $0xd86f0f66 // movdqa xmm3, xmm0 - LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 - QUAD $0x000140249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 320], xmm3 - QUAD $0x072e2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 46], 7 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xca650f66 // pcmpgtw xmm1, xmm2 - QUAD $0x0000f0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm1 - LONG $0x44b70f42; WORD $0x300e // movzx eax, word [rsi + r9 + 48] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x4cc40f66; WORD $0x300e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 48], 1 - QUAD $0x0230064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 48], 2 - LONG $0x4cc40f66; WORD $0x303e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 48], 3 - LONG $0x4cc40f66; WORD $0x301e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 48], 4 - QUAD $0x05303e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 48], 5 - QUAD $0x0630264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 48], 6 - QUAD $0x07302e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 48], 7 - LONG $0x44b70f42; WORD $0x320e // movzx eax, word [rsi + r9 + 50] - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x320e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 50], 1 - QUAD $0x02320654c40f4266 // pinsrw xmm2, word [rsi + r8 + 50], 2 - LONG $0x54c40f66; WORD $0x323e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 50], 3 - LONG $0x54c40f66; WORD $0x321e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 50], 4 - QUAD $0x05323e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 50], 5 - QUAD $0x06322654c40f4266 // pinsrw xmm2, word [rsi + r12 + 50], 6 - QUAD $0x07322e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 50], 7 - LONG $0x6f0f4466; BYTE $0xe8 // movdqa xmm13, xmm0 - LONG $0x650f4466; BYTE $0xe9 // pcmpgtw xmm13, xmm1 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xca650f66 // pcmpgtw xmm1, xmm2 - QUAD $0x000170248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 368], xmm1 - LONG $0x44b70f42; WORD $0x340e // movzx eax, word [rsi + r9 + 52] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x4cc40f66; WORD $0x340e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 52], 1 - QUAD $0x0234064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 52], 2 - LONG $0x4cc40f66; WORD $0x343e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 52], 3 - LONG $0x4cc40f66; WORD $0x341e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 52], 4 - QUAD $0x05343e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 52], 5 - QUAD $0x0634264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 52], 6 - LONG $0x44b70f42; WORD $0x360e // movzx eax, word [rsi + r9 + 54] - QUAD $0x07342e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 52], 7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x360e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 54], 1 - QUAD $0x02360654c40f4266 // pinsrw xmm2, word [rsi + r8 + 54], 2 - LONG $0x54c40f66; WORD $0x363e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 54], 3 - LONG $0x54c40f66; WORD $0x361e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 54], 4 - QUAD $0x05363e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 54], 5 - QUAD $0x06362654c40f4266 // pinsrw xmm2, word [rsi + r12 + 54], 6 - LONG $0xd86f0f66 // movdqa xmm3, xmm0 - LONG $0xd9650f66 // pcmpgtw xmm3, xmm1 - QUAD $0x0001a0249c7f0f66; BYTE $0x00 // movdqa oword [rsp + 416], xmm3 - QUAD $0x07362e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 54], 7 - LONG $0x6f0f4466; BYTE $0xf8 // movdqa xmm15, xmm0 - LONG $0x650f4466; BYTE $0xfa // pcmpgtw xmm15, xmm2 - LONG $0x44b70f42; WORD $0x380e // movzx eax, word [rsi + r9 + 56] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x4cc40f66; WORD $0x380e; BYTE $0x01 // pinsrw xmm1, word [rsi + rcx + 56], 1 - QUAD $0x0238064cc40f4266 // pinsrw xmm1, word [rsi + r8 + 56], 2 - LONG $0x4cc40f66; WORD $0x383e; BYTE $0x03 // pinsrw xmm1, word [rsi + rdi + 56], 3 - LONG $0x4cc40f66; WORD $0x381e; BYTE $0x04 // pinsrw xmm1, word [rsi + rbx + 56], 4 - QUAD $0x05383e4cc40f4266 // pinsrw xmm1, word [rsi + r15 + 56], 5 - QUAD $0x0638264cc40f4266 // pinsrw xmm1, word [rsi + r12 + 56], 6 - QUAD $0x07382e4cc40f4266 // pinsrw xmm1, word [rsi + r13 + 56], 7 - LONG $0x44b70f42; WORD $0x3a0e // movzx eax, word [rsi + r9 + 58] - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x3a0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 58], 1 - QUAD $0x023a0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 58], 2 - LONG $0x54c40f66; WORD $0x3a3e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 58], 3 - LONG $0x54c40f66; WORD $0x3a1e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 58], 4 - QUAD $0x053a3e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 58], 5 - QUAD $0x063a2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 58], 6 - QUAD $0x073a2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 58], 7 - LONG $0x6f0f4466; BYTE $0xc8 // movdqa xmm9, xmm0 - LONG $0x650f4466; BYTE $0xc9 // pcmpgtw xmm9, xmm1 - LONG $0x6f0f4466; BYTE $0xe0 // movdqa xmm12, xmm0 - LONG $0x650f4466; BYTE $0xe2 // pcmpgtw xmm12, xmm2 - LONG $0x44b70f42; WORD $0x3c0e // movzx eax, word [rsi + r9 + 60] - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x54c40f66; WORD $0x3c0e; BYTE $0x01 // pinsrw xmm2, word [rsi + rcx + 60], 1 - QUAD $0x023c0654c40f4266 // pinsrw xmm2, word [rsi + r8 + 60], 2 - LONG $0x54c40f66; WORD $0x3c3e; BYTE $0x03 // pinsrw xmm2, word [rsi + rdi + 60], 3 - LONG $0x54c40f66; WORD $0x3c1e; BYTE $0x04 // pinsrw xmm2, word [rsi + rbx + 60], 4 - QUAD $0x053c3e54c40f4266 // pinsrw xmm2, word [rsi + r15 + 60], 5 - QUAD $0x063c2654c40f4266 // pinsrw xmm2, word [rsi + r12 + 60], 6 - LONG $0x44b70f42; WORD $0x3e0e // movzx eax, word [rsi + r9 + 62] - QUAD $0x073c2e54c40f4266 // pinsrw xmm2, word [rsi + r13 + 60], 7 - LONG $0xf86e0f66 // movd xmm7, eax - LONG $0x7cc40f66; WORD $0x3e0e; BYTE $0x01 // pinsrw xmm7, word [rsi + rcx + 62], 1 - QUAD $0x023e067cc40f4266 // pinsrw xmm7, word [rsi + r8 + 62], 2 - LONG $0x7cc40f66; WORD $0x3e3e; BYTE $0x03 // pinsrw xmm7, word [rsi + rdi + 62], 3 - LONG $0x7cc40f66; WORD $0x3e1e; BYTE $0x04 // pinsrw xmm7, word [rsi + rbx + 62], 4 - QUAD $0x053e3e7cc40f4266 // pinsrw xmm7, word [rsi + r15 + 62], 5 - QUAD $0x063e267cc40f4266 // pinsrw xmm7, word [rsi + r12 + 62], 6 - LONG $0xe86f0f66 // movdqa xmm5, xmm0 - LONG $0xea650f66 // pcmpgtw xmm5, xmm2 - QUAD $0x073e2e7cc40f4266 // pinsrw xmm7, word [rsi + r13 + 62], 7 - LONG $0xf06f0f66 // movdqa xmm6, xmm0 - LONG $0xf7650f66 // pcmpgtw xmm6, xmm7 - LONG $0x630f4566; BYTE $0xdb // packsswb xmm11, xmm11 - QUAD $0x000000808d6f0f66 // movdqa xmm1, oword 128[rbp] /* [rip + .LCPI10_8] */ - LONG $0xf96f0f66 // movdqa xmm7, xmm1 - LONG $0xd96f0f66 // movdqa xmm3, xmm1 - LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 - LONG $0xe4ef0f66 // pxor xmm4, xmm4 - LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 - LONG $0x546f0f66; WORD $0x5024 // movdqa xmm2, oword [rsp + 80] - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x000000908d6f0f66 // movdqa xmm1, oword 144[rbp] /* [rip + .LCPI10_9] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - LONG $0xd2760f66 // pcmpeqd xmm2, xmm2 - QUAD $0x00016024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 352] - LONG $0xc2ef0f66 // pxor xmm0, xmm2 - LONG $0x760f4566; BYTE $0xc0 // pcmpeqd xmm8, xmm8 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xf8f80f66 // psubb xmm7, xmm0 - QUAD $0x00009024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 144] - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x0000a09d6f0f4466; BYTE $0x00 // movdqa xmm11, oword 160[rbp] /* [rip + .LCPI10_10] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4466; WORD $0xdc10 // pblendvb xmm11, xmm4, xmm0 - LONG $0xeb0f4466; BYTE $0xd9 // por xmm11, xmm1 - LONG $0x546f0f66; WORD $0x2024 // movdqa xmm2, oword [rsp + 32] - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - LONG $0xeb0f4466; BYTE $0xdf // por xmm11, xmm7 - QUAD $0x00008024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 128] - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x0000c0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 192[rbp] /* [rip + .LCPI10_12] */ - LONG $0x6f0f4166; BYTE $0xfa // movdqa xmm7, xmm10 - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 - LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0x630f4566; BYTE $0xf6 // packsswb xmm14, xmm14 - QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ - LONG $0x6f0f4166; BYTE $0xc6 // movdqa xmm0, xmm14 - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - LONG $0xcfeb0f66 // por xmm1, xmm7 - LONG $0x546f0f66; WORD $0x6024 // movdqa xmm2, oword [rsp + 96] - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x0000e0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 224[rbp] /* [rip + .LCPI10_14] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4466; WORD $0xf410 // pblendvb xmm14, xmm4, xmm0 - LONG $0xeb0f4166; BYTE $0xcb // por xmm1, xmm11 - QUAD $0x0000a024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 160] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x6f0f4466; BYTE $0xdb // movdqa xmm11, xmm3 - LONG $0xfb6f0f66 // movdqa xmm7, xmm3 - LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 - LONG $0xeb0f4466; BYTE $0xf1 // por xmm14, xmm1 - QUAD $0x0001b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 432] - LONG $0xef0f4166; BYTE $0xc0 // pxor xmm0, xmm8 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xf8f80f66 // psubb xmm7, xmm0 - LONG $0x446f0f66; WORD $0x3024 // movdqa xmm0, oword [rsp + 48] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - QUAD $0x000000909d6f0f66 // movdqa xmm3, oword 144[rbp] /* [rip + .LCPI10_9] */ - LONG $0xcb6f0f66 // movdqa xmm1, xmm3 - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - QUAD $0x0000a0856f0f4466; BYTE $0x00 // movdqa xmm8, oword 160[rbp] /* [rip + .LCPI10_10] */ - LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 - LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 - LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0xd7eb0f66 // por xmm2, xmm7 - LONG $0x446f0f66; WORD $0x1024 // movdqa xmm0, oword [rsp + 16] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - QUAD $0x0000c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 192] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x380f4466; WORD $0xd410 // pblendvb xmm10, xmm4, xmm0 - LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - QUAD $0x0000e024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 224] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - LONG $0xeb0f4166; BYTE $0xca // por xmm1, xmm10 - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0x446f0f66; WORD $0x7024 // movdqa xmm0, oword [rsp + 112] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - QUAD $0x0000e0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 224[rbp] /* [rip + .LCPI10_14] */ - LONG $0x380f4466; WORD $0xd410 // pblendvb xmm10, xmm4, xmm0 - LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - QUAD $0x00010024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 256] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x6f0f4166; BYTE $0xcb // movdqa xmm1, xmm11 - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - QUAD $0x00012024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 288] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xd36f0f66 // movdqa xmm2, xmm3 - LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 - QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] - QUAD $0x0000016085ef0f66 // pxor xmm0, oword 352[rbp] /* [rip + .LCPI10_22] */ - LONG $0xdb760f66 // pcmpeqd xmm3, xmm3 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xc8f80f66 // psubb xmm1, xmm0 - QUAD $0x00013024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 304] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x6f0f4166; BYTE $0xf8 // movdqa xmm7, xmm8 - LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 - LONG $0xfaeb0f66 // por xmm7, xmm2 - QUAD $0x00015024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 336] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - QUAD $0x0110249c6f0f4466; WORD $0x0000 // movdqa xmm11, oword [rsp + 272] - LONG $0x630f4566; BYTE $0xdb // packsswb xmm11, xmm11 - LONG $0xf9eb0f66 // por xmm7, xmm1 - QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - QUAD $0x000000c0956f0f66 // movdqa xmm2, oword 192[rbp] /* [rip + .LCPI10_12] */ - LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 - LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 - QUAD $0x00014024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 320] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xd1eb0f66 // por xmm2, xmm1 - QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - LONG $0xcaeb0f66 // por xmm1, xmm2 - QUAD $0x0000f024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 240] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - QUAD $0x0170249c6f0f4466; WORD $0x0000 // movdqa xmm11, oword [rsp + 368] - LONG $0x630f4566; BYTE $0xdb // packsswb xmm11, xmm11 - LONG $0xcfeb0f66 // por xmm1, xmm7 - QUAD $0x000000e0bd6f0f66 // movdqa xmm7, oword 224[rbp] /* [rip + .LCPI10_14] */ - LONG $0x10380f66; BYTE $0xfc // pblendvb xmm7, xmm4, xmm0 - QUAD $0x00000080956f0f66 // movdqa xmm2, oword 128[rbp] /* [rip + .LCPI10_8] */ - LONG $0x6f0f4166; BYTE $0xc3 // movdqa xmm0, xmm11 - LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 - LONG $0xf9eb0f66 // por xmm7, xmm1 - LONG $0xef0f4466; BYTE $0xeb // pxor xmm13, xmm3 - LONG $0x630f4566; BYTE $0xed // packsswb xmm13, xmm13 - QUAD $0x0001a024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 416] - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x630f4566; BYTE $0xff // packsswb xmm15, xmm15 - LONG $0xf80f4166; BYTE $0xd5 // psubb xmm2, xmm13 - QUAD $0x000000908d6f0f66 // movdqa xmm1, oword 144[rbp] /* [rip + .LCPI10_9] */ - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - LONG $0x6f0f4166; BYTE $0xc7 // movdqa xmm0, xmm15 - LONG $0x380f4466; WORD $0xc410 // pblendvb xmm8, xmm4, xmm0 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0x630f4566; BYTE $0xc9 // packsswb xmm9, xmm9 - LONG $0x630f4566; BYTE $0xe4 // packsswb xmm12, xmm12 - LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - QUAD $0x000000b08d6f0f66 // movdqa xmm1, oword 176[rbp] /* [rip + .LCPI10_11] */ - LONG $0x6f0f4166; BYTE $0xc1 // movdqa xmm0, xmm9 - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - QUAD $0x000000c0956f0f66 // movdqa xmm2, oword 192[rbp] /* [rip + .LCPI10_12] */ - LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 - LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xd1eb0f66 // por xmm2, xmm1 - QUAD $0x000000d08d6f0f66 // movdqa xmm1, oword 208[rbp] /* [rip + .LCPI10_13] */ - LONG $0xc56f0f66 // movdqa xmm0, xmm5 - LONG $0x10380f66; BYTE $0xcc // pblendvb xmm1, xmm4, xmm0 - LONG $0xcaeb0f66 // por xmm1, xmm2 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - QUAD $0x000000e0956f0f66 // movdqa xmm2, oword 224[rbp] /* [rip + .LCPI10_14] */ - LONG $0xc66f0f66 // movdqa xmm0, xmm6 - LONG $0x10380f66; BYTE $0xd4 // pblendvb xmm2, xmm4, xmm0 - LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0x6f0f4166; BYTE $0xc6 // movdqa xmm0, xmm14 - LONG $0x6c0f4166; BYTE $0xc2 // punpcklqdq xmm0, xmm10 - LONG $0xcf6f0f66 // movdqa xmm1, xmm7 - LONG $0xca6c0f66 // punpcklqdq xmm1, xmm2 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI10_15] */ - LONG $0x00380f66; BYTE $0xcb // pshufb xmm1, xmm3 - LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 - LONG $0xc1610f66 // punpcklwd xmm0, xmm1 - LONG $0xfa600f66 // punpcklbw xmm7, xmm2 - LONG $0x600f4566; BYTE $0xf2 // punpcklbw xmm14, xmm10 - LONG $0x610f4466; BYTE $0xf7 // punpcklwd xmm14, xmm7 - LONG $0x7f0f47f3; WORD $0x9634 // movdqu oword [r14 + 4*r10], xmm14 - LONG $0x7f0f43f3; WORD $0x9644; BYTE $0x10 // movdqu oword [r14 + 4*r10 + 16], xmm0 - LONG $0x08c28349 // add r10, 8 - QUAD $0x0000019024943b4c // cmp r10, qword [rsp + 400] - JNE LBB10_125 - QUAD $0x000001c824bc8b4c // mov r15, qword [rsp + 456] - QUAD $0x0000019024bc3b4c // cmp r15, qword [rsp + 400] - LONG $0x24548b4c; BYTE $0x48 // mov r10, qword [rsp + 72] + QUAD $0x000140249cf80f66; BYTE $0x00 // psubb xmm3, oword [rsp + 320] + LONG $0xd66f0f66 // movdqa xmm2, xmm6 + LONG $0xde0f4166; BYTE $0xd4 // pmaxub xmm2, xmm12 + LONG $0xd6740f66 // pcmpeqb xmm2, xmm6 + LONG $0xcf6f0f66 // movdqa xmm1, xmm7 + LONG $0xde0f4166; BYTE $0xcc // pmaxub xmm1, xmm12 + LONG $0xcf740f66 // pcmpeqb xmm1, xmm7 + QUAD $0x1c374c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdi + r14 + 28], 3 + QUAD $0x1c074c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdi + rax + 28], 4 + QUAD $0x1c374c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdi + rsi + 28], 5 + QUAD $0x1c074c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdi + r8 + 28], 6 + QUAD $0x1c1f4c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdi + r11 + 28], 7 + QUAD $0x1c0f4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rdi + rcx + 28], 8 + QUAD $0x1c174c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdi + r10 + 28], 9 + QUAD $0x1c0f4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdi + r9 + 28], 10 + QUAD $0x1c1f4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdi + rbx + 28], 11 + QUAD $0x1c3f4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdi + r15 + 28], 12 + QUAD $0x1c274c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rdi + r12 + 28], 13 + QUAD $0x1c2f4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdi + r13 + 28], 14 + QUAD $0x1c174c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rdi + rdx + 28], 15 + QUAD $0x1d3744203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdi + r14 + 29], 3 + QUAD $0x041d0744203a0f66 // pinsrb xmm0, byte [rdi + rax + 29], 4 + QUAD $0x051d3744203a0f66 // pinsrb xmm0, byte [rdi + rsi + 29], 5 + QUAD $0x1d0744203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdi + r8 + 29], 6 + QUAD $0x1d1f44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdi + r11 + 29], 7 + QUAD $0x081d0f44203a0f66 // pinsrb xmm0, byte [rdi + rcx + 29], 8 + QUAD $0x1d1744203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdi + r10 + 29], 9 + QUAD $0x1d0f44203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdi + r9 + 29], 10 + QUAD $0x0b1d1f44203a0f66 // pinsrb xmm0, byte [rdi + rbx + 29], 11 + QUAD $0x1d3f44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdi + r15 + 29], 12 + QUAD $0x1d2744203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdi + r12 + 29], 13 + QUAD $0x1d2f44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdi + r13 + 29], 14 + QUAD $0x0f1d1744203a0f66 // pinsrb xmm0, byte [rdi + rdx + 29], 15 + QUAD $0x0000011095db0f66 // pand xmm2, oword 272[rbp] /* [rip + .LCPI10_17] */ + QUAD $0x000001208ddb0f66 // pand xmm1, oword 288[rbp] /* [rip + .LCPI10_18] */ + LONG $0xcaeb0f66 // por xmm1, xmm2 + LONG $0xcbeb0f66 // por xmm1, xmm3 + LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 + LONG $0xde0f4166; BYTE $0xd4 // pmaxub xmm2, xmm12 + LONG $0x740f4166; BYTE $0xd1 // pcmpeqb xmm2, xmm9 + LONG $0xd86f0f66 // movdqa xmm3, xmm0 + LONG $0xde0f4166; BYTE $0xdc // pmaxub xmm3, xmm12 + LONG $0xd8740f66 // pcmpeqb xmm3, xmm0 + QUAD $0x1e3764203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdi + r14 + 30], 3 + QUAD $0x1f376c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdi + r14 + 31], 3 + QUAD $0x041e0764203a0f66 // pinsrb xmm4, byte [rdi + rax + 30], 4 + QUAD $0x041f076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 31], 4 + QUAD $0x051e3764203a0f66 // pinsrb xmm4, byte [rdi + rsi + 30], 5 + QUAD $0x051f376c203a0f66 // pinsrb xmm5, byte [rdi + rsi + 31], 5 + QUAD $0x1e0764203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdi + r8 + 30], 6 + QUAD $0x1f076c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdi + r8 + 31], 6 + QUAD $0x1e1f64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdi + r11 + 30], 7 + QUAD $0x1f1f6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdi + r11 + 31], 7 + QUAD $0x081e0f64203a0f66 // pinsrb xmm4, byte [rdi + rcx + 30], 8 + QUAD $0x081f0f6c203a0f66 // pinsrb xmm5, byte [rdi + rcx + 31], 8 + QUAD $0x1e1764203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdi + r10 + 30], 9 + QUAD $0x1f176c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdi + r10 + 31], 9 LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - JNE LBB10_127 - JMP LBB10_130 - -LBB10_182: - WORD $0x894c; BYTE $0xd8 // mov rax, r11 - LONG $0xfce08348 // and rax, -4 - WORD $0x8948; BYTE $0xc2 // mov rdx, rax - LONG $0x07e2c148 // shl rdx, 7 - WORD $0x0148; BYTE $0xf2 // add rdx, rsi - LONG $0x863c8d4d // lea r15, [r14 + 4*rax] - LONG $0xeb280f45 // movaps xmm13, xmm11 - LONG $0xebc60f45; BYTE $0x00 // shufps xmm13, xmm11, 0 - LONG $0xfcc68148; WORD $0x0001; BYTE $0x00 // add rsi, 508 - WORD $0xc931 // xor ecx, ecx - LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI10_0] */ - -LBB10_183: - QUAD $0xfffffe049e100ff3 // movss xmm3, dword [rsi - 508] - QUAD $0xfffe0896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 504] - QUAD $0xfffe0c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 500] - QUAD $0xfffffe108e100ff3 // movss xmm1, dword [rsi - 496] - QUAD $0xfffe849e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 380], 16 - QUAD $0xffff049e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 252], 32 - LONG $0x213a0f66; WORD $0x845e; BYTE $0x30 // insertps xmm3, dword [rsi - 124], 48 - QUAD $0xfe8896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 376], 16 - QUAD $0xff0896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 248], 32 - QUAD $0x308856213a0f4466 // insertps xmm10, dword [rsi - 120], 48 - QUAD $0xfe8c8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 372], 16 - QUAD $0xff0c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 244], 32 - QUAD $0x308c4e213a0f4466 // insertps xmm9, dword [rsi - 116], 48 - QUAD $0xfffe908e213a0f66; WORD $0x10ff // insertps xmm1, dword [rsi - 368], 16 - QUAD $0xffff108e213a0f66; WORD $0x20ff // insertps xmm1, dword [rsi - 240], 32 - LONG $0x213a0f66; WORD $0x904e; BYTE $0x30 // insertps xmm1, dword [rsi - 112], 48 - QUAD $0xfffe1486100f44f3; BYTE $0xff // movss xmm8, dword [rsi - 492] - QUAD $0xfe9486213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm8, dword [rsi - 364], 16 - QUAD $0xff1486213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm8, dword [rsi - 236], 32 - LONG $0xe5280f45 // movaps xmm12, xmm13 - QUAD $0x309446213a0f4466 // insertps xmm8, dword [rsi - 108], 48 - QUAD $0xfffffe1896100ff3 // movss xmm2, dword [rsi - 488] - QUAD $0xfffe9896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 360], 16 - QUAD $0xffff1896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 232], 32 - LONG $0xe3c20f44; BYTE $0x02 // cmpleps xmm12, xmm3 - LONG $0x213a0f66; WORD $0x9856; BYTE $0x30 // insertps xmm2, dword [rsi - 104], 48 - QUAD $0xfffffe1c9e100ff3 // movss xmm3, dword [rsi - 484] - QUAD $0xfffe9c9e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 356], 16 - QUAD $0xffff1c9e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 228], 32 - LONG $0x6b0f4566; BYTE $0xe4 // packssdw xmm12, xmm12 - LONG $0x213a0f66; WORD $0x9c5e; BYTE $0x30 // insertps xmm3, dword [rsi - 100], 48 - QUAD $0xfffffe24a6100ff3 // movss xmm4, dword [rsi - 476] - QUAD $0xfffea4a6213a0f66; WORD $0x10ff // insertps xmm4, dword [rsi - 348], 16 - QUAD $0xffff24a6213a0f66; WORD $0x20ff // insertps xmm4, dword [rsi - 220], 32 - LONG $0x630f4566; BYTE $0xe4 // packsswb xmm12, xmm12 - LONG $0x213a0f66; WORD $0xa466; BYTE $0x30 // insertps xmm4, dword [rsi - 92], 48 - LONG $0xfd280f41 // movaps xmm7, xmm13 - QUAD $0xfffffe44ae100ff3 // movss xmm5, dword [rsi - 444] - QUAD $0xfffec4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 316], 16 - QUAD $0xffff44ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 188], 32 - LONG $0x02fcc20f // cmpleps xmm7, xmm4 - LONG $0x213a0f66; WORD $0xc46e; BYTE $0x30 // insertps xmm5, dword [rsi - 60], 48 - LONG $0xf5280f41 // movaps xmm6, xmm13 - QUAD $0xfffffe6486100ff3 // movss xmm0, dword [rsi - 412] - QUAD $0xfffee486213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 284], 16 - QUAD $0xffff6486213a0f66; WORD $0x20ff // insertps xmm0, dword [rsi - 156], 32 - LONG $0x02f5c20f // cmpleps xmm6, xmm5 - LONG $0x213a0f66; WORD $0xe446; BYTE $0x30 // insertps xmm0, dword [rsi - 28], 48 - LONG $0xe5280f41 // movaps xmm4, xmm13 - LONG $0x02e0c20f // cmpleps xmm4, xmm0 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc2c20f41; BYTE $0x02 // cmpleps xmm0, xmm10 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x6f0f4466; BYTE $0xf0 // movdqa xmm14, xmm0 - LONG $0xdb0f4566; BYTE $0xf7 // pand xmm14, xmm15 - LONG $0xf80f4466; BYTE $0xf0 // psubb xmm14, xmm0 - QUAD $0xfffe2096100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 480] - QUAD $0xfea096213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 352], 16 - LONG $0xdb0f4566; BYTE $0xe7 // pand xmm12, xmm15 - QUAD $0xff2096213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 224], 32 - LONG $0xeb0f4566; BYTE $0xf4 // por xmm14, xmm12 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0xe9c20f41; BYTE $0x02 // cmpleps xmm5, xmm9 - QUAD $0x30a056213a0f4466 // insertps xmm10, dword [rsi - 96], 48 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0x456f0f66; BYTE $0x10 // movdqa xmm0, oword 16[rbp] /* [rip + .LCPI10_1] */ - LONG $0xe8db0f66 // pand xmm5, xmm0 - LONG $0xeb0f4166; BYTE $0xee // por xmm5, xmm14 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x02c1c20f // cmpleps xmm0, xmm1 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0xc8c20f41; BYTE $0x02 // cmpleps xmm1, xmm8 - QUAD $0xfffe288e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 472] - QUAD $0xfea88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 344], 16 - QUAD $0xff288e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 216], 32 - QUAD $0x30a84e213a0f4466 // insertps xmm9, dword [rsi - 88], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 - LONG $0x6f0f4466; WORD $0x2075 // movdqa xmm14, oword 32[rbp] /* [rip + .LCPI10_2] */ - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0x6f0f4466; WORD $0x3075 // movdqa xmm14, oword 48[rbp] /* [rip + .LCPI10_3] */ - LONG $0xdb0f4166; BYTE $0xce // pand xmm1, xmm14 - LONG $0xc8eb0f66 // por xmm1, xmm0 - QUAD $0xfffe2ca6100f44f3; BYTE $0xff // movss xmm12, dword [rsi - 468] - QUAD $0xfeaca6213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm12, dword [rsi - 340], 16 - QUAD $0xff2ca6213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm12, dword [rsi - 212], 32 - QUAD $0x30ac66213a0f4466 // insertps xmm12, dword [rsi - 84], 48 - LONG $0xcdeb0f66 // por xmm1, xmm5 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x02c2c20f // cmpleps xmm0, xmm2 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0x02ebc20f // cmpleps xmm5, xmm3 - QUAD $0xfffffe3096100ff3 // movss xmm2, dword [rsi - 464] - QUAD $0xfffeb096213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 336], 16 - QUAD $0xffff3096213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 208], 32 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0x213a0f66; WORD $0xb056; BYTE $0x30 // insertps xmm2, dword [rsi - 80], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 - LONG $0x6f0f4466; WORD $0x4075 // movdqa xmm14, oword 64[rbp] /* [rip + .LCPI10_4] */ - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 - LONG $0x5d6f0f66; BYTE $0x50 // movdqa xmm3, oword 80[rbp] /* [rip + .LCPI10_5] */ - LONG $0xebdb0f66 // pand xmm5, xmm3 - LONG $0xe8eb0f66 // por xmm5, xmm0 - LONG $0xc5280f45 // movaps xmm8, xmm13 - LONG $0xc2c20f45; BYTE $0x02 // cmpleps xmm8, xmm10 - QUAD $0xfffffe349e100ff3 // movss xmm3, dword [rsi - 460] - QUAD $0xfffeb49e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 332], 16 - QUAD $0xffff349e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 204], 32 - LONG $0x213a0f66; WORD $0xb45e; BYTE $0x30 // insertps xmm3, dword [rsi - 76], 48 - LONG $0x6b0f4566; BYTE $0xc0 // packssdw xmm8, xmm8 - LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 - LONG $0x710f4166; WORD $0x07f0 // psllw xmm8, 7 - LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI10_6] */ - LONG $0xdb0f4466; BYTE $0xc0 // pand xmm8, xmm0 - LONG $0xeb0f4466; BYTE $0xc5 // por xmm8, xmm5 - QUAD $0xfffe3896100f44f3; BYTE $0xff // movss xmm10, dword [rsi - 456] - QUAD $0xfeb896213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm10, dword [rsi - 328], 16 - QUAD $0xff3896213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm10, dword [rsi - 200], 32 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x30b856213a0f4466 // insertps xmm10, dword [rsi - 72], 48 - LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc1c20f41; BYTE $0x02 // cmpleps xmm0, xmm9 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xc8f80f66 // psubb xmm1, xmm0 - QUAD $0xfffe3c8e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 452] - QUAD $0xfebc8e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 324], 16 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - QUAD $0xff3c8e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 196], 32 - LONG $0xcfeb0f66 // por xmm1, xmm7 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0xecc20f41; BYTE $0x02 // cmpleps xmm5, xmm12 - QUAD $0x30bc4e213a0f4466 // insertps xmm9, dword [rsi - 68], 48 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0x6ddb0f66; BYTE $0x10 // pand xmm5, oword 16[rbp] /* [rip + .LCPI10_1] */ - LONG $0xe9eb0f66 // por xmm5, xmm1 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x02c2c20f // cmpleps xmm0, xmm2 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x02cbc20f // cmpleps xmm1, xmm3 - QUAD $0xfffffe409e100ff3 // movss xmm3, dword [rsi - 448] - QUAD $0xfffec09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 320], 16 - QUAD $0xffff409e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 192], 32 - LONG $0x213a0f66; WORD $0xc05e; BYTE $0x30 // insertps xmm3, dword [rsi - 64], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 - LONG $0x6f0f4466; WORD $0x2065 // movdqa xmm12, oword 32[rbp] /* [rip + .LCPI10_2] */ - LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0x4ddb0f66; BYTE $0x30 // pand xmm1, oword 48[rbp] /* [rip + .LCPI10_3] */ - LONG $0xc8eb0f66 // por xmm1, xmm0 - QUAD $0xfffffe4896100ff3 // movss xmm2, dword [rsi - 440] - QUAD $0xfffec896213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 312], 16 - QUAD $0xffff4896213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 184], 32 - LONG $0x213a0f66; WORD $0xc856; BYTE $0x30 // insertps xmm2, dword [rsi - 56], 48 - LONG $0xcdeb0f66 // por xmm1, xmm5 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc2c20f41; BYTE $0x02 // cmpleps xmm0, xmm10 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0xe9c20f41; BYTE $0x02 // cmpleps xmm5, xmm9 - QUAD $0xfffffe4cbe100ff3 // movss xmm7, dword [rsi - 436] - QUAD $0xfffeccbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 308], 16 - QUAD $0xffff4cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 180], 32 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0x213a0f66; WORD $0xcc7e; BYTE $0x30 // insertps xmm7, dword [rsi - 52], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x06 // psllw xmm5, 6 - LONG $0x6ddb0f66; BYTE $0x50 // pand xmm5, oword 80[rbp] /* [rip + .LCPI10_5] */ - LONG $0xe8eb0f66 // por xmm5, xmm0 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x02c3c20f // cmpleps xmm0, xmm3 - QUAD $0xfffffe509e100ff3 // movss xmm3, dword [rsi - 432] - QUAD $0xfffed09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 304], 16 - QUAD $0xffff509e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 176], 32 - LONG $0x213a0f66; WORD $0xd05e; BYTE $0x30 // insertps xmm3, dword [rsi - 48], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0x6f0f4466; WORD $0x6055 // movdqa xmm10, oword 96[rbp] /* [rip + .LCPI10_6] */ - LONG $0xdb0f4166; BYTE $0xc2 // pand xmm0, xmm10 - LONG $0xc5eb0f66 // por xmm0, xmm5 - QUAD $0xfffffe54ae100ff3 // movss xmm5, dword [rsi - 428] - QUAD $0xfffed4ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 300], 16 - QUAD $0xffff54ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 172], 32 - LONG $0x213a0f66; WORD $0xd46e; BYTE $0x30 // insertps xmm5, dword [rsi - 44], 48 - LONG $0xc1eb0f66 // por xmm0, xmm1 - QUAD $0xfffe588e100f44f3; BYTE $0xff // movss xmm9, dword [rsi - 424] - QUAD $0xfed88e213a0f4466; WORD $0xffff; BYTE $0x10 // insertps xmm9, dword [rsi - 296], 16 - QUAD $0xff588e213a0f4466; WORD $0xffff; BYTE $0x20 // insertps xmm9, dword [rsi - 168], 32 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - QUAD $0x30d84e213a0f4466 // insertps xmm9, dword [rsi - 40], 48 - LONG $0x620f4466; BYTE $0xc0 // punpckldq xmm8, xmm0 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x02c2c20f // cmpleps xmm0, xmm2 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xc86f0f66 // movdqa xmm1, xmm0 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xc8f80f66 // psubb xmm1, xmm0 - QUAD $0xfffffe5c96100ff3 // movss xmm2, dword [rsi - 420] - QUAD $0xfffedc96213a0f66; WORD $0x10ff // insertps xmm2, dword [rsi - 292], 16 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - QUAD $0xffff5c96213a0f66; WORD $0x20ff // insertps xmm2, dword [rsi - 164], 32 - LONG $0xceeb0f66 // por xmm1, xmm6 - LONG $0xf5280f41 // movaps xmm6, xmm13 - LONG $0x02f7c20f // cmpleps xmm6, xmm7 - LONG $0x213a0f66; WORD $0xdc56; BYTE $0x30 // insertps xmm2, dword [rsi - 36], 48 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x02 // psllw xmm6, 2 - LONG $0x456f0f66; BYTE $0x10 // movdqa xmm0, oword 16[rbp] /* [rip + .LCPI10_1] */ - LONG $0xf0db0f66 // pand xmm6, xmm0 - LONG $0xf1eb0f66 // por xmm6, xmm1 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x02c3c20f // cmpleps xmm0, xmm3 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x02cdc20f // cmpleps xmm1, xmm5 - QUAD $0xfffffe609e100ff3 // movss xmm3, dword [rsi - 416] - QUAD $0xfffee09e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 288], 16 - QUAD $0xffff609e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 160], 32 - LONG $0x213a0f66; WORD $0xe05e; BYTE $0x30 // insertps xmm3, dword [rsi - 32], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x03 // psllw xmm0, 3 - LONG $0xdb0f4166; BYTE $0xc4 // pand xmm0, xmm12 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0x6f0f4466; WORD $0x3065 // movdqa xmm12, oword 48[rbp] /* [rip + .LCPI10_3] */ - LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 - LONG $0xc8eb0f66 // por xmm1, xmm0 - QUAD $0xfffffe68ae100ff3 // movss xmm5, dword [rsi - 408] - QUAD $0xfffee8ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 280], 16 - QUAD $0xffff68ae213a0f66; WORD $0x20ff // insertps xmm5, dword [rsi - 152], 32 - LONG $0x213a0f66; WORD $0xe86e; BYTE $0x30 // insertps xmm5, dword [rsi - 24], 48 - LONG $0xceeb0f66 // por xmm1, xmm6 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0xc1c20f41; BYTE $0x02 // cmpleps xmm0, xmm9 - LONG $0xf5280f41 // movaps xmm6, xmm13 - LONG $0x02f2c20f // cmpleps xmm6, xmm2 - QUAD $0xfffffe6cbe100ff3 // movss xmm7, dword [rsi - 404] - QUAD $0xfffeecbe213a0f66; WORD $0x10ff // insertps xmm7, dword [rsi - 276], 16 - QUAD $0xffff6cbe213a0f66; WORD $0x20ff // insertps xmm7, dword [rsi - 148], 32 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0x213a0f66; WORD $0xec7e; BYTE $0x30 // insertps xmm7, dword [rsi - 20], 48 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xdb0f4166; BYTE $0xc7 // pand xmm0, xmm15 - LONG $0xf0710f66; BYTE $0x05 // psllw xmm0, 5 - LONG $0xdb0f4166; BYTE $0xc6 // pand xmm0, xmm14 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x06 // psllw xmm6, 6 - LONG $0x6f0f4466; WORD $0x504d // movdqa xmm9, oword 80[rbp] /* [rip + .LCPI10_5] */ - LONG $0xdb0f4166; BYTE $0xf1 // pand xmm6, xmm9 - LONG $0xf0eb0f66 // por xmm6, xmm0 - LONG $0xd5280f41 // movaps xmm2, xmm13 - LONG $0x02d3c20f // cmpleps xmm2, xmm3 - QUAD $0xfffffe7086100ff3 // movss xmm0, dword [rsi - 400] - QUAD $0xfffef086213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 272], 16 - QUAD $0xffff7086213a0f66; WORD $0x20ff // insertps xmm0, dword [rsi - 144], 32 - LONG $0x213a0f66; WORD $0xf046; BYTE $0x30 // insertps xmm0, dword [rsi - 16], 48 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf2710f66; BYTE $0x07 // psllw xmm2, 7 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffffe74b6100ff3 // movss xmm6, dword [rsi - 396] - QUAD $0xfffef4b6213a0f66; WORD $0x10ff // insertps xmm6, dword [rsi - 268], 16 - QUAD $0xffff74b6213a0f66; WORD $0x20ff // insertps xmm6, dword [rsi - 140], 32 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0x213a0f66; WORD $0xf476; BYTE $0x30 // insertps xmm6, dword [rsi - 12], 48 - LONG $0xd1eb0f66 // por xmm2, xmm1 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x02cdc20f // cmpleps xmm1, xmm5 - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xe96f0f66 // movdqa xmm5, xmm1 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xe9f80f66 // psubb xmm5, xmm1 - QUAD $0xfffffe789e100ff3 // movss xmm3, dword [rsi - 392] - QUAD $0xfffef89e213a0f66; WORD $0x10ff // insertps xmm3, dword [rsi - 264], 16 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - QUAD $0xffff789e213a0f66; WORD $0x20ff // insertps xmm3, dword [rsi - 136], 32 - LONG $0xeceb0f66 // por xmm5, xmm4 - LONG $0xe5280f41 // movaps xmm4, xmm13 - LONG $0x02e7c20f // cmpleps xmm4, xmm7 - LONG $0x213a0f66; WORD $0xf85e; BYTE $0x30 // insertps xmm3, dword [rsi - 8], 48 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xf4710f66; BYTE $0x02 // psllw xmm4, 2 - LONG $0x65db0f66; BYTE $0x10 // pand xmm4, oword 16[rbp] /* [rip + .LCPI10_1] */ - LONG $0xe5eb0f66 // por xmm4, xmm5 - LONG $0xed280f41 // movaps xmm5, xmm13 - LONG $0x02e8c20f // cmpleps xmm5, xmm0 - LONG $0xcd280f41 // movaps xmm1, xmm13 - LONG $0x02cec20f // cmpleps xmm1, xmm6 - QUAD $0xfffffe7c86100ff3 // movss xmm0, dword [rsi - 388] - QUAD $0xfffefc86213a0f66; WORD $0x10ff // insertps xmm0, dword [rsi - 260], 16 - QUAD $0xffff7c86213a0f66; WORD $0x20ff // insertps xmm0, dword [rsi - 132], 32 - LONG $0x213a0f66; WORD $0xfc46; BYTE $0x30 // insertps xmm0, dword [rsi - 4], 48 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 - LONG $0x6ddb0f66; BYTE $0x20 // pand xmm5, oword 32[rbp] /* [rip + .LCPI10_2] */ - LONG $0xc96b0f66 // packssdw xmm1, xmm1 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xdb0f4166; BYTE $0xcf // pand xmm1, xmm15 - LONG $0xf1710f66; BYTE $0x04 // psllw xmm1, 4 - LONG $0xdb0f4166; BYTE $0xcc // pand xmm1, xmm12 - LONG $0xcdeb0f66 // por xmm1, xmm5 - QUAD $0xfffffe80ae100ff3 // movss xmm5, dword [rsi - 384] - QUAD $0xffff00ae213a0f66; WORD $0x10ff // insertps xmm5, dword [rsi - 256], 16 - LONG $0x213a0f66; WORD $0x806e; BYTE $0x20 // insertps xmm5, dword [rsi - 128], 32 - LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0xe5280f41 // movaps xmm4, xmm13 - LONG $0x02e3c20f // cmpleps xmm4, xmm3 - LONG $0xdd280f41 // movaps xmm3, xmm13 - LONG $0x02d8c20f // cmpleps xmm3, xmm0 - LONG $0x213a0f66; WORD $0x302e // insertps xmm5, dword [rsi], 48 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xf4710f66; BYTE $0x05 // psllw xmm4, 5 - LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 - LONG $0xdb0f4166; BYTE $0xd9 // pand xmm3, xmm9 - LONG $0xdceb0f66 // por xmm3, xmm4 - LONG $0xc5280f41 // movaps xmm0, xmm13 - LONG $0x02c5c20f // cmpleps xmm0, xmm5 - LONG $0xc06b0f66 // packssdw xmm0, xmm0 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xf0710f66; BYTE $0x07 // psllw xmm0, 7 - LONG $0xdb0f4166; BYTE $0xc2 // pand xmm0, xmm10 - LONG $0xc3eb0f66 // por xmm0, xmm3 - LONG $0xc1eb0f66 // por xmm0, xmm1 - LONG $0xd0620f66 // punpckldq xmm2, xmm0 - LONG $0x600f4466; BYTE $0xc2 // punpcklbw xmm8, xmm2 - LONG $0x380f4466; WORD $0x4500; BYTE $0x70 // pshufb xmm8, oword 112[rbp] /* [rip + .LCPI10_7] */ - LONG $0x7f0f45f3; WORD $0x8e04 // movdqu oword [r14 + 4*rcx], xmm8 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c68148; WORD $0x0002; BYTE $0x00 // add rsi, 512 - WORD $0x3948; BYTE $0xc8 // cmp rax, rcx - JNE LBB10_183 - WORD $0x3949; BYTE $0xc3 // cmp r11, rax - JNE LBB10_185 - JMP LBB10_188 + QUAD $0x1e0f64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdi + r9 + 30], 10 + QUAD $0x1f0f6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdi + r9 + 31], 10 + QUAD $0x0b1e1f64203a0f66 // pinsrb xmm4, byte [rdi + rbx + 30], 11 + QUAD $0x0b1f1f6c203a0f66 // pinsrb xmm5, byte [rdi + rbx + 31], 11 + QUAD $0x1e3f64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdi + r15 + 30], 12 + QUAD $0x1f3f6c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdi + r15 + 31], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d1e0764203a0f66 // pinsrb xmm4, byte [rdi + rax + 30], 13 + QUAD $0x0d1f076c203a0f66 // pinsrb xmm5, byte [rdi + rax + 31], 13 + QUAD $0x1e2f64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdi + r13 + 30], 14 + QUAD $0x1f2f6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdi + r13 + 31], 14 + QUAD $0x0f1e1764203a0f66 // pinsrb xmm4, byte [rdi + rdx + 30], 15 + QUAD $0x0000013095db0f66 // pand xmm2, oword 304[rbp] /* [rip + .LCPI10_19] */ + QUAD $0x000001409ddb0f66 // pand xmm3, oword 320[rbp] /* [rip + .LCPI10_20] */ + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0xde0f4166; BYTE $0xc4 // pmaxub xmm0, xmm12 + LONG $0xc4740f66 // pcmpeqb xmm0, xmm4 + QUAD $0x0f1f176c203a0f66 // pinsrb xmm5, byte [rdi + rdx + 31], 15 + QUAD $0x0000015085db0f66 // pand xmm0, oword 336[rbp] /* [rip + .LCPI10_21] */ + LONG $0xc3eb0f66 // por xmm0, xmm3 + LONG $0xc1eb0f66 // por xmm0, xmm1 + LONG $0xcd6f0f66 // movdqa xmm1, xmm5 + LONG $0xde0f4166; BYTE $0xcc // pmaxub xmm1, xmm12 + LONG $0xcd740f66 // pcmpeqb xmm1, xmm5 + LONG $0xdb0f4166; BYTE $0xcb // pand xmm1, xmm11 + LONG $0xc8eb0f66 // por xmm1, xmm0 + LONG $0x6f0f4166; BYTE $0xc2 // movdqa xmm0, xmm10 + LONG $0xc1600f66 // punpcklbw xmm0, xmm1 + QUAD $0x0000f024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 240] + LONG $0xd46f0f66 // movdqa xmm2, xmm4 + LONG $0x600f4166; BYTE $0xd6 // punpcklbw xmm2, xmm14 + LONG $0xda6f0f66 // movdqa xmm3, xmm2 + LONG $0xd8610f66 // punpcklwd xmm3, xmm0 + LONG $0xd0690f66 // punpckhwd xmm2, xmm0 + LONG $0x680f4466; BYTE $0xd1 // punpckhbw xmm10, xmm1 + LONG $0x680f4166; BYTE $0xe6 // punpckhbw xmm4, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x610f4166; BYTE $0xc2 // punpcklwd xmm0, xmm10 + LONG $0x690f4166; BYTE $0xe2 // punpckhwd xmm4, xmm10 + QUAD $0x00000150248c8b48 // mov rcx, qword [rsp + 336] + LONG $0x7f0f41f3; WORD $0x8c64; BYTE $0x30 // movdqu oword [r12 + 4*rcx + 48], xmm4 + LONG $0x7f0f41f3; WORD $0x8c44; BYTE $0x20 // movdqu oword [r12 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x8c54; BYTE $0x10 // movdqu oword [r12 + 4*rcx + 16], xmm2 + LONG $0x7f0f41f3; WORD $0x8c1c // movdqu oword [r12 + 4*rcx], xmm3 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + JNE LBB10_73 + QUAD $0x00000178248c8b48 // mov rcx, qword [rsp + 376] + QUAD $0x00000180248c3b48 // cmp rcx, qword [rsp + 384] + LONG $0x242c8a44 // mov r13b, byte [rsp] + QUAD $0x000001c024b48b48 // mov rsi, qword [rsp + 448] + LONG $0x24748b4c; BYTE $0x48 // mov r14, qword [rsp + 72] + JNE LBB10_75 + JMP LBB10_78 DATA LCDATA8<>+0x000(SB)/8, $0x0000000001010101 DATA LCDATA8<>+0x008(SB)/8, $0x0000000000000000 @@ -54170,164 +55772,178 @@ TEXT ·_comparison_greater_equal_scalar_arr_sse4(SB), $328-48 MOVQ BP, 304(SP) LEAQ LCDATA8<>(SB), BP - WORD $0x894d; BYTE $0xc3 // mov r11, r8 - WORD $0x8949; BYTE $0xcf // mov r15, rcx - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JG LBB11_26 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JLE LBB11_2 - WORD $0xff83; BYTE $0x04 // cmp edi, 4 - JE LBB11_99 - WORD $0xff83; BYTE $0x05 // cmp edi, 5 - JE LBB11_114 - WORD $0xff83; BYTE $0x06 // cmp edi, 6 - JNE LBB11_201 - WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_17 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0x894d; BYTE $0xc7 // mov r15, r8 + WORD $0x8949; BYTE $0xcc // mov r12, rcx + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JG LBB11_18 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JLE LBB11_35 + WORD $0xff83; BYTE $0x04 // cmp edi, 4 + JE LBB11_57 + WORD $0xff83; BYTE $0x05 // cmp edi, 5 + JE LBB11_70 + WORD $0xff83; BYTE $0x06 // cmp edi, 6 + JNE LBB11_215 + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_11 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_9 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB11_15: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1f // movzx r8d, byte [r15 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1f3c8841 // mov byte [r15 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_15 - LONG $0x01c78349 // add r15, 1 - -LBB11_17: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_21 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - -LBB11_19: - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - LONG $0x7c723b44 // cmp r14d, dword [rdx + 124] - LONG $0x2414930f // setae byte [rsp] - LONG $0x78723b44 // cmp r14d, dword [rdx + 120] - LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] - LONG $0x74723b44 // cmp r14d, dword [rdx + 116] +LBB11_8: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_8 + +LBB11_9: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 + +LBB11_11: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_15 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + +LBB11_13: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] - LONG $0x70723b44 // cmp r14d, dword [rdx + 112] - LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] - LONG $0x6c723b44 // cmp r14d, dword [rdx + 108] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x68723b44 // cmp r14d, dword [rdx + 104] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x64723b44 // cmp r14d, dword [rdx + 100] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x5c723b44 // cmp r14d, dword [rdx + 92] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] + LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x58723b44 // cmp r14d, dword [rdx + 88] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x54723b44 // cmp r14d, dword [rdx + 84] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x50723b44 // cmp r14d, dword [rdx + 80] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x4c723b44 // cmp r14d, dword [rdx + 76] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x48723b44 // cmp r14d, dword [rdx + 72] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x44723b44 // cmp r14d, dword [rdx + 68] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x3c723b44 // cmp r14d, dword [rdx + 60] - LONG $0xd0930f41 // setae r8b - LONG $0x38723b44 // cmp r14d, dword [rdx + 56] - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x34723b44 // cmp r14d, dword [rdx + 52] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x30723b44 // cmp r14d, dword [rdx + 48] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] + LONG $0xd7930f40 // setae dil + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + QUAD $0x000000c02494930f // setae byte [rsp + 192] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] LONG $0xd3930f41 // setae r11b - LONG $0x2c723b44 // cmp r14d, dword [rdx + 44] + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] LONG $0xd2930f41 // setae r10b - LONG $0x28723b44 // cmp r14d, dword [rdx + 40] + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] LONG $0xd1930f41 // setae r9b - LONG $0x24723b44 // cmp r14d, dword [rdx + 36] - LONG $0xd7930f40 // setae dil - LONG $0x1c723b44 // cmp r14d, dword [rdx + 28] + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] + LONG $0xd6930f40 // setae sil + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x18723b44 // cmp r14d, dword [rdx + 24] + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x14723b44 // cmp r14d, dword [rdx + 20] - LONG $0xd6930f40 // setae sil - LONG $0x10723b44 // cmp r14d, dword [rdx + 16] + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x0c723b44 // cmp r14d, dword [rdx + 12] + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] LONG $0xd5930f41 // setae r13b - LONG $0x08723b44 // cmp r14d, dword [rdx + 8] + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] LONG $0xd4930f41 // setae r12b - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - QUAD $0x000000e02494930f // setae byte [rsp + 224] - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] LONG $0xd7930f41 // setae r15b - LONG $0x20723b44 // cmp r14d, dword [rdx + 32] - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x40723b44 // cmp r14d, dword [rdx + 64] - QUAD $0x000000b02494930f // setae byte [rsp + 176] - LONG $0x60723b44 // cmp r14d, dword [rdx + 96] + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] QUAD $0x000000902494930f // setae byte [rsp + 144] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000e024bc0244 // add r15b, byte [rsp + 224] - LONG $0x02e4c041 // shl r12b, 2 + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd6930f41 // setae r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + QUAD $0x000000d02494930f // setae byte [rsp + 208] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + QUAD $0x000000a02494930f // setae byte [rsp + 160] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x0000009024b40244 // add r14b, byte [rsp + 144] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - LONG $0x03e5c041 // shl r13b, 3 + LONG $0x04e5c041 // shl r13b, 4 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] + WORD $0xc808 // or al, cl + LONG $0x24048841 // mov byte [r12], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al - LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x02 // shl al, 2 @@ -54337,122 +55953,138 @@ LBB11_19: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2404b60f // movzx eax, byte [rsp] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al LONG $0x80ea8348 // sub rdx, -128 - LONG $0x04c78349 // add r15, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB11_19 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB11_13 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB11_21: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_137 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_24 +LBB11_15: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB11_185 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB11_187 + +LBB11_18: + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JLE LBB11_42 + WORD $0xff83; BYTE $0x09 // cmp edi, 9 + JE LBB11_84 + WORD $0xff83; BYTE $0x0b // cmp edi, 11 + JE LBB11_97 + WORD $0xff83; BYTE $0x0c // cmp edi, 12 + JNE LBB11_215 + WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_28 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_26 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_25: + LONG $0x08518d48 // lea rdx, [rcx + 8] + LONG $0x012e0f66 // ucomisd xmm0, qword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_25 LBB11_26: - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JLE LBB11_27 - WORD $0xff83; BYTE $0x09 // cmp edi, 9 - JE LBB11_157 - WORD $0xff83; BYTE $0x0b // cmp edi, 11 - JE LBB11_172 - WORD $0xff83; BYTE $0x0c // cmp edi, 12 - JNE LBB11_201 - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff2 // movsd xmm0, qword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_49 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 -LBB11_47: - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_47 - LONG $0x01c78349 // add r15, 1 - -LBB11_49: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_53 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - QUAD $0x000000e02494894c // mov qword [rsp + 224], r10 - -LBB11_51: - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 +LBB11_28: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_32 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000f024b4894c // mov qword [rsp + 240], r14 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax + +LBB11_30: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] QUAD $0x000000802494930f // setae byte [rsp + 128] LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] @@ -54462,15 +56094,15 @@ LBB11_51: LONG $0x422e0f66; BYTE $0x18 // ucomisd xmm0, qword [rdx + 24] LONG $0xd5930f41 // setae r13b LONG $0x422e0f66; BYTE $0x20 // ucomisd xmm0, qword [rdx + 32] - QUAD $0x000000b02494930f // setae byte [rsp + 176] + QUAD $0x000000d02494930f // setae byte [rsp + 208] LONG $0x422e0f66; BYTE $0x28 // ucomisd xmm0, qword [rdx + 40] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x422e0f66; BYTE $0x30 // ucomisd xmm0, qword [rdx + 48] WORD $0x930f; BYTE $0xd3 // setae bl LONG $0x422e0f66; BYTE $0x38 // ucomisd xmm0, qword [rdx + 56] LONG $0xd4930f41 // setae r12b LONG $0x422e0f66; BYTE $0x40 // ucomisd xmm0, qword [rdx + 64] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] LONG $0x422e0f66; BYTE $0x48 // ucomisd xmm0, qword [rdx + 72] LONG $0xd6930f40 // setae sil LONG $0x422e0f66; BYTE $0x50 // ucomisd xmm0, qword [rdx + 80] @@ -54482,39 +56114,39 @@ LBB11_51: LONG $0x422e0f66; BYTE $0x68 // ucomisd xmm0, qword [rdx + 104] LONG $0xd7930f41 // setae r15b LONG $0x422e0f66; BYTE $0x70 // ucomisd xmm0, qword [rdx + 112] - QUAD $0x000000a02494930f // setae byte [rsp + 160] + QUAD $0x000000c02494930f // setae byte [rsp + 192] LONG $0x422e0f66; BYTE $0x78 // ucomisd xmm0, qword [rdx + 120] WORD $0x930f; BYTE $0xd1 // setae cl QUAD $0x00000080822e0f66 // ucomisd xmm0, qword [rdx + 128] LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] QUAD $0x00000088822e0f66 // ucomisd xmm0, qword [rdx + 136] - QUAD $0x000000902494930f // setae byte [rsp + 144] + QUAD $0x000000a02494930f // setae byte [rsp + 160] QUAD $0x00000090822e0f66 // ucomisd xmm0, qword [rdx + 144] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] QUAD $0x00000098822e0f66 // ucomisd xmm0, qword [rdx + 152] LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] QUAD $0x000000a0822e0f66 // ucomisd xmm0, qword [rdx + 160] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] QUAD $0x000000a8822e0f66 // ucomisd xmm0, qword [rdx + 168] LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] QUAD $0x000000b0822e0f66 // ucomisd xmm0, qword [rdx + 176] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] QUAD $0x000000b8822e0f66 // ucomisd xmm0, qword [rdx + 184] LONG $0xd6930f41 // setae r14b QUAD $0x000000c0822e0f66 // ucomisd xmm0, qword [rdx + 192] - LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] + LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] QUAD $0x000000c8822e0f66 // ucomisd xmm0, qword [rdx + 200] LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] QUAD $0x000000d0822e0f66 // ucomisd xmm0, qword [rdx + 208] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] QUAD $0x000000d8822e0f66 // ucomisd xmm0, qword [rdx + 216] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] QUAD $0x000000e0822e0f66 // ucomisd xmm0, qword [rdx + 224] - LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] - QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + QUAD $0x000000e8822e0f66 // ucomisd xmm0, qword [rdx + 232] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] QUAD $0x000000f0822e0f66 // ucomisd xmm0, qword [rdx + 240] - LONG $0x2414930f // setae byte [rsp] + LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] QUAD $0x000000f8822e0f66 // ucomisd xmm0, qword [rdx + 248] WORD $0x930f; BYTE $0xd0 // setae al WORD $0x0045; BYTE $0xc9 // add r9b, r9b @@ -54525,750 +56157,318 @@ LBB11_51: LONG $0x02e3c041 // shl r11b, 2 WORD $0x0845; BYTE $0xcb // or r11b, r9b WORD $0x0040; BYTE $0xf6 // add sil, sil - LONG $0x24740240; BYTE $0x70 // add sil, byte [rsp + 112] + LONG $0x24740240; BYTE $0x78 // add sil, byte [rsp + 120] LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xdd // or r13b, r11b LONG $0x02e7c040 // shl dil, 2 WORD $0x0840; BYTE $0xf7 // or dil, sil - QUAD $0x000000b0249cb60f // movzx ebx, byte [rsp + 176] + QUAD $0x000000d0249cb60f // movzx ebx, byte [rsp + 208] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 WORD $0x0844; BYTE $0xeb // or bl, r13b - WORD $0xde89 // mov esi, ebx + WORD $0x8941; BYTE $0xd9 // mov r9d, ebx + QUAD $0x0000008824b48b48 // mov rsi, qword [rsp + 136] LONG $0x03e0c041 // shl r8b, 3 WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil + WORD $0x0844; BYTE $0xcb // or bl, r9b LONG $0x04e2c041 // shl r10b, 4 WORD $0x0845; BYTE $0xc2 // or r10b, r8b LONG $0x05e7c041 // shl r15b, 5 WORD $0x0845; BYTE $0xd7 // or r15b, r10b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] - LONG $0x06e6c040 // shl sil, 6 + QUAD $0x000000c024bcb60f // movzx edi, byte [rsp + 192] + LONG $0x06e7c040 // shl dil, 6 WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0x0840; BYTE $0xf9 // or cl, dil WORD $0x0841; BYTE $0xdc // or r12b, bl WORD $0x0844; BYTE $0xf9 // or cl, r15b - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x00000090249cb60f // movzx ebx, byte [rsp + 144] + QUAD $0x000000a0249cb60f // movzx ebx, byte [rsp + 160] WORD $0xdb00 // add bl, bl LONG $0x60245c02 // add bl, byte [rsp + 96] - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] + WORD $0xdf89 // mov edi, ebx + LONG $0x245cb60f; BYTE $0x70 // movzx ebx, byte [rsp + 112] WORD $0xe3c0; BYTE $0x02 // shl bl, 2 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx LONG $0x245cb60f; BYTE $0x58 // movzx ebx, byte [rsp + 88] WORD $0xe3c0; BYTE $0x03 // shl bl, 3 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx - LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx + LONG $0x245cb60f; BYTE $0x68 // movzx ebx, byte [rsp + 104] WORD $0xe3c0; BYTE $0x04 // shl bl, 4 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0xde89 // mov esi, ebx + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0xdf89 // mov edi, ebx LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x05 // shl bl, 5 - WORD $0x0840; BYTE $0xf3 // or bl, sil - WORD $0x8845; BYTE $0x27 // mov byte [r15], r12b - LONG $0x2474b60f; BYTE $0x30 // movzx esi, byte [rsp + 48] - LONG $0x06e6c040 // shl sil, 6 + WORD $0x0840; BYTE $0xfb // or bl, dil + WORD $0x8844; BYTE $0x26 // mov byte [rsi], r12b + LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] + LONG $0x06e7c040 // shl dil, 6 LONG $0x07e6c041 // shl r14b, 7 - WORD $0x0841; BYTE $0xf6 // or r14b, sil - LONG $0x014f8841 // mov byte [r15 + 1], cl + WORD $0x0841; BYTE $0xfe // or r14b, dil + WORD $0x4e88; BYTE $0x01 // mov byte [rsi + 1], cl WORD $0x0841; BYTE $0xde // or r14b, bl LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] WORD $0xc900 // add cl, cl - LONG $0x18244c02 // add cl, byte [rsp + 24] + LONG $0x20244c02 // add cl, byte [rsp + 32] WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] WORD $0xe1c0; BYTE $0x02 // shl cl, 2 WORD $0xd908 // or cl, bl WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] WORD $0xe1c0; BYTE $0x03 // shl cl, 3 WORD $0xd908 // or cl, bl WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x08 // movzx ecx, byte [rsp + 8] + LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] WORD $0xe1c0; BYTE $0x04 // shl cl, 4 WORD $0xd908 // or cl, bl WORD $0xcb89 // mov ebx, ecx - LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0xd908 // or cl, bl - LONG $0x241cb60f // movzx ebx, byte [rsp] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02778845 // mov byte [r15 + 2], r14b - LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x02768844 // mov byte [rsi + 2], r14b + WORD $0x4688; BYTE $0x03 // mov byte [rsi + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c78349 // add r15, 4 - QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 - JNE LBB11_51 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + LONG $0x04c68348 // add rsi, 4 + WORD $0x8949; BYTE $0xf4 // mov r12, rsi + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB11_30 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000f024b48b4c // mov r14, qword [rsp + 240] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB11_53: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_195 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_197 +LBB11_32: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc0 // sub r8, rax + JLE LBB11_215 + LONG $0x6e0f4966; BYTE $0xc6 // movq xmm0, r14 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB11_189 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB11_191 -LBB11_2: - WORD $0xff83; BYTE $0x02 // cmp edi, 2 - JE LBB11_56 - WORD $0xff83; BYTE $0x03 // cmp edi, 3 - JNE LBB11_201 - WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_8 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_6: - WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_6 - LONG $0x01c78349 // add r15, 1 +LBB11_35: + WORD $0xff83; BYTE $0x02 // cmp edi, 2 + JE LBB11_111 + WORD $0xff83; BYTE $0x03 // cmp edi, 3 + JNE LBB11_215 + WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_129 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_139 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 -LBB11_8: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_9 - LONG $0x10fa8349 // cmp r10, 16 - LONG $0x24348844 // mov byte [rsp], r14b - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - JB LBB11_82 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc7 // cmp r15, rax - JAE LBB11_85 - LONG $0x97048d4b // lea rax, [r15 + 4*r10] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB11_85 +LBB11_40: + LONG $0x016a8d4c // lea r13, [rdx + 1] + WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + WORD $0x9d0f; BYTE $0xd2 // setge dl + WORD $0xdaf6 // neg dl + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894c; BYTE $0xe7 // mov rdi, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd020 // and al, dl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x1c048841 // mov byte [r12 + rbx], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x894c; BYTE $0xea // mov rdx, r13 + LONG $0xffc38349 // add r11, -1 + JNE LBB11_40 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB11_140 + JMP LBB11_215 + +LBB11_42: + WORD $0xff83; BYTE $0x07 // cmp edi, 7 + JE LBB11_116 + WORD $0xff83; BYTE $0x08 // cmp edi, 8 + JNE LBB11_215 + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_50 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_48 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB11_82: - WORD $0xc031 // xor eax, eax - QUAD $0x0000010024848948 // mov qword [rsp + 256], rax - WORD $0x894d; BYTE $0xfd // mov r13, r15 +LBB11_47: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_47 -LBB11_88: - QUAD $0x0000010024942b4c // sub r10, qword [rsp + 256] - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 +LBB11_48: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 -LBB11_89: - LONG $0x1f723a44 // cmp r14b, byte [rdx + 31] - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x1e723a44 // cmp r14b, byte [rdx + 30] - LONG $0x24549d0f; BYTE $0x08 // setge byte [rsp + 8] - LONG $0x1d723a44 // cmp r14b, byte [rdx + 29] - LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0x1c723a44 // cmp r14b, byte [rdx + 28] - LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] - LONG $0x1b723a44 // cmp r14b, byte [rdx + 27] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x1a723a44 // cmp r14b, byte [rdx + 26] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x19723a44 // cmp r14b, byte [rdx + 25] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x17723a44 // cmp r14b, byte [rdx + 23] - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x16723a44 // cmp r14b, byte [rdx + 22] - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x15723a44 // cmp r14b, byte [rdx + 21] - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x14723a44 // cmp r14b, byte [rdx + 20] - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x13723a44 // cmp r14b, byte [rdx + 19] - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x12723a44 // cmp r14b, byte [rdx + 18] - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x11723a44 // cmp r14b, byte [rdx + 17] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x0f723a44 // cmp r14b, byte [rdx + 15] - LONG $0xd29d0f41 // setge r10b - LONG $0x0e723a44 // cmp r14b, byte [rdx + 14] - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x0d723a44 // cmp r14b, byte [rdx + 13] - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x0c723a44 // cmp r14b, byte [rdx + 12] - LONG $0xd49d0f41 // setge r12b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x0b // cmp al, byte [rdx + 11] - LONG $0xd79d0f41 // setge r15b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x0a // cmp al, byte [rdx + 10] - LONG $0xd69d0f41 // setge r14b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] - LONG $0xd39d0f41 // setge r11b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd69d0f40 // setge sil - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0xd19d0f41 // setge r9b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0xd09d0f41 // setge r8b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0xd79d0f40 // setge dil - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x023a // cmp al, byte [rdx] - QUAD $0x000000d024949d0f // setge byte [rsp + 208] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x01 // cmp al, byte [rdx + 1] - WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - LONG $0x2cb60f44; BYTE $0x24 // movzx r13d, byte [rsp] - LONG $0x086a3a44 // cmp r13b, byte [rdx + 8] - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x000000e024949d0f // setge byte [rsp + 224] - LONG $0x241cb60f // movzx ebx, byte [rsp] - WORD $0x5a3a; BYTE $0x10 // cmp bl, byte [rdx + 16] - QUAD $0x000000b024949d0f // setge byte [rsp + 176] - LONG $0x241cb60f // movzx ebx, byte [rsp] - WORD $0x5a3a; BYTE $0x18 // cmp bl, byte [rdx + 24] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - WORD $0xc000 // add al, al - LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al - LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x04e0c041 // shl r8b, 4 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x05e1c041 // shl r9b, 5 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c040 // shl sil, 7 - WORD $0x0840; BYTE $0xc6 // or sil, al - WORD $0x0844; BYTE $0xce // or sil, r9b - LONG $0x00758841 // mov byte [r13], sil - WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000e0249c0244 // add r11b, byte [rsp + 224] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xf7 // or r15b, r14b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x34b60f44; BYTE $0x24 // movzx r14d, byte [rsp] - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xca // or r10b, cl - WORD $0x0841; BYTE $0xc2 // or r10b, al - LONG $0x01558845 // mov byte [r13 + 1], r10b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xc000 // add al, al - LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02458841 // mov byte [r13 + 2], al - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xc000 // add al, al - LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x20c28348 // add rdx, 32 - LONG $0x04c58349 // add r13, 4 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB11_89 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - JMP LBB11_91 - -LBB11_27: - WORD $0xff83; BYTE $0x07 // cmp edi, 7 - JE LBB11_139 - WORD $0xff83; BYTE $0x08 // cmp edi, 8 - JNE LBB11_201 - WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_33 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_31: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1f // movzx r8d, byte [r15 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1f3c8841 // mov byte [r15 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_31 - LONG $0x01c78349 // add r15, 1 - -LBB11_33: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_37 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 +LBB11_50: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_54 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax -LBB11_35: - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - LONG $0xf8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 248] - LONG $0x2414930f // setae byte [rsp] - LONG $0xf0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 240] - LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] - LONG $0xe8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 232] +LBB11_52: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] - LONG $0xe0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 224] - LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] - LONG $0xd8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 216] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0xd0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 208] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] + LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0xc8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 200] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0xb8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 184] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] + LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0xb0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 176] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0xa8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 168] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0xa0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 160] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x98b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 152] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x90b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 144] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x88b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 136] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x78723b4c // cmp r14, qword [rdx + 120] - LONG $0xd0930f41 // setae r8b - LONG $0x70723b4c // cmp r14, qword [rdx + 112] - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x68723b4c // cmp r14, qword [rdx + 104] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x60723b4c // cmp r14, qword [rdx + 96] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] + LONG $0xd7930f40 // setae dil + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + QUAD $0x000000c02494930f // setae byte [rsp + 192] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] LONG $0xd3930f41 // setae r11b - LONG $0x58723b4c // cmp r14, qword [rdx + 88] + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd2930f41 // setae r10b - LONG $0x50723b4c // cmp r14, qword [rdx + 80] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd1930f41 // setae r9b - LONG $0x48723b4c // cmp r14, qword [rdx + 72] - LONG $0xd7930f40 // setae dil - LONG $0x38723b4c // cmp r14, qword [rdx + 56] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] + LONG $0xd6930f40 // setae sil + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x30723b4c // cmp r14, qword [rdx + 48] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x28723b4c // cmp r14, qword [rdx + 40] - LONG $0xd6930f40 // setae sil - LONG $0x20723b4c // cmp r14, qword [rdx + 32] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x18723b4c // cmp r14, qword [rdx + 24] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] LONG $0xd5930f41 // setae r13b - LONG $0x10723b4c // cmp r14, qword [rdx + 16] + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd4930f41 // setae r12b - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - QUAD $0x000000e02494930f // setae byte [rsp + 224] - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] LONG $0xd7930f41 // setae r15b - LONG $0x40723b4c // cmp r14, qword [rdx + 64] - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x80b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 128] - QUAD $0x000000b02494930f // setae byte [rsp + 176] - LONG $0xc0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 192] + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] QUAD $0x000000902494930f // setae byte [rsp + 144] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000e024bc0244 // add r15b, byte [rsp + 224] - LONG $0x02e4c041 // shl r12b, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0xd6930f41 // setae r14b + LONG $0x40423b4c // cmp r8, qword [rdx + 64] + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + QUAD $0x000000d02494930f // setae byte [rsp + 208] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + QUAD $0x000000a02494930f // setae byte [rsp + 160] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x0000009024b40244 // add r14b, byte [rsp + 144] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - LONG $0x03e5c041 // shl r13b, 3 + LONG $0x04e5c041 // shl r13b, 4 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] + WORD $0xc808 // or al, cl + LONG $0x24048841 // mov byte [r12], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xc000 // add al, al - LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c78349 // add r15, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB11_35 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - -LBB11_37: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_155 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_40 - -LBB11_56: - WORD $0x8a44; BYTE $0x36 // mov r14b, byte [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_60 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_58: - WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] - LONG $0x01528d48 // lea rdx, [rdx + 1] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_58 - LONG $0x01c78349 // add r15, 1 - -LBB11_60: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_61 - LONG $0x10fa8349 // cmp r10, 16 - LONG $0x24348844 // mov byte [rsp], r14b - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000f82494894c // mov qword [rsp + 248], r10 - JB LBB11_63 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc7 // cmp r15, rax - JAE LBB11_66 - LONG $0x97048d4b // lea rax, [r15 + 4*r10] - WORD $0x3948; BYTE $0xc2 // cmp rdx, rax - JAE LBB11_66 - -LBB11_63: - WORD $0xc031 // xor eax, eax - QUAD $0x000000c024848948 // mov qword [rsp + 192], rax - WORD $0x894d; BYTE $0xfd // mov r13, r15 - -LBB11_69: - QUAD $0x000000c024942b4c // sub r10, qword [rsp + 192] - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - -LBB11_70: - LONG $0x1f723a44 // cmp r14b, byte [rdx + 31] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] - LONG $0x1e723a44 // cmp r14b, byte [rdx + 30] - LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] - LONG $0x1d723a44 // cmp r14b, byte [rdx + 29] - LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] - LONG $0x1c723a44 // cmp r14b, byte [rdx + 28] - LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] - LONG $0x1b723a44 // cmp r14b, byte [rdx + 27] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x1a723a44 // cmp r14b, byte [rdx + 26] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - LONG $0x19723a44 // cmp r14b, byte [rdx + 25] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x17723a44 // cmp r14b, byte [rdx + 23] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x16723a44 // cmp r14b, byte [rdx + 22] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x15723a44 // cmp r14b, byte [rdx + 21] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x14723a44 // cmp r14b, byte [rdx + 20] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x13723a44 // cmp r14b, byte [rdx + 19] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x12723a44 // cmp r14b, byte [rdx + 18] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x11723a44 // cmp r14b, byte [rdx + 17] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x0f723a44 // cmp r14b, byte [rdx + 15] - LONG $0xd2930f41 // setae r10b - LONG $0x0e723a44 // cmp r14b, byte [rdx + 14] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x0d723a44 // cmp r14b, byte [rdx + 13] - QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x0c723a44 // cmp r14b, byte [rdx + 12] - LONG $0xd4930f41 // setae r12b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x0b // cmp al, byte [rdx + 11] - LONG $0xd7930f41 // setae r15b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x0a // cmp al, byte [rdx + 10] - LONG $0xd6930f41 // setae r14b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x09 // cmp al, byte [rdx + 9] - LONG $0xd3930f41 // setae r11b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x07 // cmp al, byte [rdx + 7] - LONG $0xd6930f40 // setae sil - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x06 // cmp al, byte [rdx + 6] - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x05 // cmp al, byte [rdx + 5] - LONG $0xd1930f41 // setae r9b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x04 // cmp al, byte [rdx + 4] - LONG $0xd0930f41 // setae r8b - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x03 // cmp al, byte [rdx + 3] - LONG $0xd7930f40 // setae dil - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x02 // cmp al, byte [rdx + 2] - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x023a // cmp al, byte [rdx] - QUAD $0x000000d02494930f // setae byte [rsp + 208] - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0x423a; BYTE $0x01 // cmp al, byte [rdx + 1] - WORD $0x930f; BYTE $0xd0 // setae al - WORD $0x894c; BYTE $0xeb // mov rbx, r13 - LONG $0x2cb60f44; BYTE $0x24 // movzx r13d, byte [rsp] - LONG $0x086a3a44 // cmp r13b, byte [rdx + 8] - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x000000e02494930f // setae byte [rsp + 224] - LONG $0x241cb60f // movzx ebx, byte [rsp] - WORD $0x5a3a; BYTE $0x10 // cmp bl, byte [rdx + 16] - QUAD $0x000000b02494930f // setae byte [rsp + 176] - LONG $0x241cb60f // movzx ebx, byte [rsp] - WORD $0x5a3a; BYTE $0x18 // cmp bl, byte [rdx + 24] - QUAD $0x000000a02494930f // setae byte [rsp + 160] - WORD $0xc000 // add al, al - LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xc108 // or cl, al - LONG $0x03e7c040 // shl dil, 3 + LONG $0x07e7c040 // shl dil, 7 WORD $0x0840; BYTE $0xcf // or dil, cl - LONG $0x04e0c041 // shl r8b, 4 - WORD $0x0841; BYTE $0xf8 // or r8b, dil - LONG $0x05e1c041 // shl r9b, 5 - WORD $0x0845; BYTE $0xc1 // or r9b, r8b - QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] - WORD $0xe0c0; BYTE $0x06 // shl al, 6 - LONG $0x07e6c040 // shl sil, 7 - WORD $0x0840; BYTE $0xc6 // or sil, al - WORD $0x0844; BYTE $0xce // or sil, r9b - LONG $0x00758841 // mov byte [r13], sil - WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000e0249c0244 // add r11b, byte [rsp + 224] - LONG $0x02e6c041 // shl r14b, 2 - WORD $0x0845; BYTE $0xde // or r14b, r11b - LONG $0x03e7c041 // shl r15b, 3 - WORD $0x0845; BYTE $0xf7 // or r15b, r14b - LONG $0x04e4c041 // shl r12b, 4 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xe0 // or al, r12b - LONG $0x34b60f44; BYTE $0x24 // movzx r14d, byte [rsp] - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xca // or r10b, cl - WORD $0x0841; BYTE $0xc2 // or r10b, al - LONG $0x01558845 // mov byte [r13 + 1], r10b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al - LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x02 // shl al, 2 @@ -55278,34 +56478,34 @@ LBB11_70: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02458841 // mov byte [r13 + 2], al + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax @@ -55313,608 +56513,426 @@ LBB11_70: WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03458841 // mov byte [r13 + 3], al - LONG $0x20c28348 // add rdx, 32 - LONG $0x04c58349 // add r13, 4 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB11_70 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - JMP LBB11_72 + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al + LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB11_52 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB11_139: - WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_143 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB11_54: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB11_167 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB11_169 + +LBB11_57: + LONG $0x06b70f44 // movzx r8d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_63 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_61 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx -LBB11_141: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x37 // movzx r8d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_141 - LONG $0x01c78349 // add r15, 1 - -LBB11_143: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_147 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 +LBB11_60: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x013b4466 // cmp r8w, word [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_60 -LBB11_145: - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - LONG $0x7c723b44 // cmp r14d, dword [rdx + 124] - LONG $0x24149d0f // setge byte [rsp] - LONG $0x78723b44 // cmp r14d, dword [rdx + 120] - LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0x74723b44 // cmp r14d, dword [rdx + 116] - LONG $0x24549d0f; BYTE $0x08 // setge byte [rsp + 8] - LONG $0x70723b44 // cmp r14d, dword [rdx + 112] - LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] - LONG $0x6c723b44 // cmp r14d, dword [rdx + 108] - LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x68723b44 // cmp r14d, dword [rdx + 104] - LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x64723b44 // cmp r14d, dword [rdx + 100] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x5c723b44 // cmp r14d, dword [rdx + 92] - LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x58723b44 // cmp r14d, dword [rdx + 88] - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x54723b44 // cmp r14d, dword [rdx + 84] - LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x50723b44 // cmp r14d, dword [rdx + 80] - LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x4c723b44 // cmp r14d, dword [rdx + 76] - LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x48723b44 // cmp r14d, dword [rdx + 72] - LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x44723b44 // cmp r14d, dword [rdx + 68] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x3c723b44 // cmp r14d, dword [rdx + 60] - LONG $0xd09d0f41 // setge r8b - LONG $0x38723b44 // cmp r14d, dword [rdx + 56] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x34723b44 // cmp r14d, dword [rdx + 52] - LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x30723b44 // cmp r14d, dword [rdx + 48] - LONG $0xd39d0f41 // setge r11b - LONG $0x2c723b44 // cmp r14d, dword [rdx + 44] - LONG $0xd29d0f41 // setge r10b - LONG $0x28723b44 // cmp r14d, dword [rdx + 40] - LONG $0xd19d0f41 // setge r9b - LONG $0x24723b44 // cmp r14d, dword [rdx + 36] - LONG $0xd79d0f40 // setge dil - LONG $0x1c723b44 // cmp r14d, dword [rdx + 28] - WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x18723b44 // cmp r14d, dword [rdx + 24] - WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x14723b44 // cmp r14d, dword [rdx + 20] - LONG $0xd69d0f40 // setge sil - LONG $0x10723b44 // cmp r14d, dword [rdx + 16] - WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x0c723b44 // cmp r14d, dword [rdx + 12] - LONG $0xd59d0f41 // setge r13b - LONG $0x08723b44 // cmp r14d, dword [rdx + 8] - LONG $0xd49d0f41 // setge r12b - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - QUAD $0x000000e024949d0f // setge byte [rsp + 224] - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] - LONG $0xd79d0f41 // setge r15b - LONG $0x20723b44 // cmp r14d, dword [rdx + 32] - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x40723b44 // cmp r14d, dword [rdx + 64] - QUAD $0x000000b024949d0f // setge byte [rsp + 176] - LONG $0x60723b44 // cmp r14d, dword [rdx + 96] - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000e024bc0244 // add r15b, byte [rsp + 224] - LONG $0x02e4c041 // shl r12b, 2 +LBB11_61: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 + +LBB11_63: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_67 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + +LBB11_65: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0x423b4466; BYTE $0x3e // cmp r8w, word [rdx + 62] + LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] + LONG $0x423b4466; BYTE $0x3c // cmp r8w, word [rdx + 60] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x423b4466; BYTE $0x3a // cmp r8w, word [rdx + 58] + LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + LONG $0x423b4466; BYTE $0x38 // cmp r8w, word [rdx + 56] + LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x423b4466; BYTE $0x36 // cmp r8w, word [rdx + 54] + LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] + LONG $0x423b4466; BYTE $0x34 // cmp r8w, word [rdx + 52] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x423b4466; BYTE $0x32 // cmp r8w, word [rdx + 50] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x423b4466; BYTE $0x2e // cmp r8w, word [rdx + 46] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x423b4466; BYTE $0x2c // cmp r8w, word [rdx + 44] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x423b4466; BYTE $0x2a // cmp r8w, word [rdx + 42] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x423b4466; BYTE $0x28 // cmp r8w, word [rdx + 40] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x423b4466; BYTE $0x26 // cmp r8w, word [rdx + 38] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x423b4466; BYTE $0x24 // cmp r8w, word [rdx + 36] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x423b4466; BYTE $0x22 // cmp r8w, word [rdx + 34] + QUAD $0x000000c02494930f // setae byte [rsp + 192] + LONG $0x423b4466; BYTE $0x1e // cmp r8w, word [rdx + 30] + LONG $0xd7930f40 // setae dil + LONG $0x423b4466; BYTE $0x1c // cmp r8w, word [rdx + 28] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x423b4466; BYTE $0x1a // cmp r8w, word [rdx + 26] + QUAD $0x000000d02494930f // setae byte [rsp + 208] + LONG $0x423b4466; BYTE $0x18 // cmp r8w, word [rdx + 24] + LONG $0xd3930f41 // setae r11b + LONG $0x423b4466; BYTE $0x16 // cmp r8w, word [rdx + 22] + LONG $0xd2930f41 // setae r10b + LONG $0x423b4466; BYTE $0x14 // cmp r8w, word [rdx + 20] + LONG $0xd1930f41 // setae r9b + LONG $0x423b4466; BYTE $0x12 // cmp r8w, word [rdx + 18] + LONG $0xd6930f40 // setae sil + LONG $0x423b4466; BYTE $0x0e // cmp r8w, word [rdx + 14] + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x423b4466; BYTE $0x0c // cmp r8w, word [rdx + 12] + WORD $0x930f; BYTE $0xd3 // setae bl + LONG $0x423b4466; BYTE $0x0a // cmp r8w, word [rdx + 10] + WORD $0x930f; BYTE $0xd1 // setae cl + LONG $0x423b4466; BYTE $0x08 // cmp r8w, word [rdx + 8] + LONG $0xd5930f41 // setae r13b + LONG $0x423b4466; BYTE $0x06 // cmp r8w, word [rdx + 6] + LONG $0xd4930f41 // setae r12b + LONG $0x423b4466; BYTE $0x04 // cmp r8w, word [rdx + 4] + LONG $0xd7930f41 // setae r15b + LONG $0x023b4466 // cmp r8w, word [rdx] + QUAD $0x000000902494930f // setae byte [rsp + 144] + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] + LONG $0xd6930f41 // setae r14b + LONG $0x423b4466; BYTE $0x10 // cmp r8w, word [rdx + 16] + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x423b4466; BYTE $0x20 // cmp r8w, word [rdx + 32] + QUAD $0x000000a02494930f // setae byte [rsp + 160] + LONG $0x423b4466; BYTE $0x30 // cmp r8w, word [rdx + 48] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x0000009024b40244 // add r14b, byte [rsp + 144] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - LONG $0x03e5c041 // shl r13b, 3 + LONG $0x04e5c041 // shl r13b, 4 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] + WORD $0xc808 // or al, cl + LONG $0x24048841 // mov byte [r12], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + QUAD $0x000000c02484b60f // movzx eax, byte [rsp + 192] WORD $0xc000 // add al, al - LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0x40244402 // add al, byte [rsp + 64] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2404b60f // movzx eax, byte [rsp] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x80ea8348 // sub rdx, -128 - LONG $0x04c78349 // add r15, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB11_145 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - -LBB11_147: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_153 - WORD $0xff31 // xor edi, edi - JMP LBB11_150 - -LBB11_99: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_103 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_101: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07588d48 // lea rbx, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xd8490f48 // cmovns rbx, rax - LONG $0x03fbc148 // sar rbx, 3 - LONG $0x04b60f45; BYTE $0x1f // movzx r8d, byte [r15 + rbx] - WORD $0x3044; BYTE $0xc6 // xor sil, r8b - LONG $0x00dd3c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rbx] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xf7 // and dil, sil - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x1f3c8841 // mov byte [r15 + rbx], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_101 - LONG $0x01c78349 // add r15, 1 - -LBB11_103: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_107 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - -LBB11_105: - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] - LONG $0x2414930f // setae byte [rsp] - LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] - LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] - LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] - LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] - LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] - LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] - LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] - LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] - LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] - LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] - LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] - LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] - LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] - LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] - LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] - LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] - LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] - LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] - QUAD $0x000000902494930f // setae byte [rsp + 144] - LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] - QUAD $0x000000a02494930f // setae byte [rsp + 160] - LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] - LONG $0xd0930f41 // setae r8b - LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] - LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] - QUAD $0x000000b02494930f // setae byte [rsp + 176] - LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] - LONG $0xd3930f41 // setae r11b - LONG $0x723b4466; BYTE $0x16 // cmp r14w, word [rdx + 22] - LONG $0xd2930f41 // setae r10b - LONG $0x723b4466; BYTE $0x14 // cmp r14w, word [rdx + 20] - LONG $0xd1930f41 // setae r9b - LONG $0x723b4466; BYTE $0x12 // cmp r14w, word [rdx + 18] - LONG $0xd7930f40 // setae dil - LONG $0x723b4466; BYTE $0x0e // cmp r14w, word [rdx + 14] - WORD $0x930f; BYTE $0xd0 // setae al - LONG $0x723b4466; BYTE $0x0c // cmp r14w, word [rdx + 12] - WORD $0x930f; BYTE $0xd3 // setae bl - LONG $0x723b4466; BYTE $0x0a // cmp r14w, word [rdx + 10] - LONG $0xd6930f40 // setae sil - LONG $0x723b4466; BYTE $0x08 // cmp r14w, word [rdx + 8] - WORD $0x930f; BYTE $0xd1 // setae cl - LONG $0x723b4466; BYTE $0x06 // cmp r14w, word [rdx + 6] - LONG $0xd5930f41 // setae r13b - LONG $0x723b4466; BYTE $0x04 // cmp r14w, word [rdx + 4] - LONG $0xd4930f41 // setae r12b - LONG $0x323b4466 // cmp r14w, word [rdx] - QUAD $0x000000e02494930f // setae byte [rsp + 224] - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] - LONG $0xd7930f41 // setae r15b - LONG $0x723b4466; BYTE $0x10 // cmp r14w, word [rdx + 16] - QUAD $0x000000802494930f // setae byte [rsp + 128] - LONG $0x723b4466; BYTE $0x20 // cmp r14w, word [rdx + 32] - LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] - LONG $0x723b4466; BYTE $0x30 // cmp r14w, word [rdx + 48] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000e024bc0244 // add r15b, byte [rsp + 224] - LONG $0x02e4c041 // shl r12b, 2 - WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - LONG $0x03e5c041 // shl r13b, 3 - WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] - LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil - LONG $0x03e2c041 // shl r10b, 3 - WORD $0x0845; BYTE $0xca // or r10b, r9b - LONG $0x04e3c041 // shl r11b, 4 - WORD $0x0845; BYTE $0xd3 // or r11b, r10b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xd8 // or al, r11b - LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] - WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] - WORD $0xc000 // add al, al - LONG $0x60244402 // add al, byte [rsp + 96] - WORD $0xc189 // mov ecx, eax - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] - WORD $0xc000 // add al, al - LONG $0x20244402 // add al, byte [rsp + 32] - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] - WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] - WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] - WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] - WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xc808 // or al, cl - WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] - WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2404b60f // movzx eax, byte [rsp] - WORD $0xe0c0; BYTE $0x07 // shl al, 7 - WORD $0xd808 // or al, bl - WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al - LONG $0x40c28348 // add rdx, 64 - LONG $0x04c78349 // add r15, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB11_105 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] - -LBB11_107: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_112 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_110 + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB11_65 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB11_114: - LONG $0x36b70f44 // movzx r14d, word [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_118 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d +LBB11_67: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB11_193 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + JMP LBB11_195 -LBB11_116: - LONG $0x323b4466 // cmp r14w, word [rdx] - LONG $0x02528d48 // lea rdx, [rdx + 2] +LBB11_70: + LONG $0x36b70f44 // movzx r14d, word [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_76 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_74 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_73: + LONG $0x02518d48 // lea rdx, [rcx + 2] + LONG $0x313b4466 // cmp r14w, word [rcx] WORD $0x9d0f; BYTE $0xd3 // setge bl WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - QUAD $0x00000000f5048d44 // lea r8d, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d LONG $0x000001bf; BYTE $0x00 // mov edi, 1 WORD $0xe7d3 // shl edi, cl WORD $0x2040; BYTE $0xdf // and dil, bl WORD $0x3044; BYTE $0xcf // xor dil, r9b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_116 - LONG $0x01c78349 // add r15, 1 - -LBB11_118: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_119 - LONG $0x08fa8349 // cmp r10, 8 - LONG $0x24348944 // mov dword [rsp], r14d - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000001002494894c // mov qword [rsp + 256], r10 - JB LBB11_121 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc7 // cmp r15, rax - JAE LBB11_124 - LONG $0x97048d4b // lea rax, [r15 + 4*r10] - WORD $0x3948; BYTE $0xd0 // cmp rax, rdx - JBE LBB11_124 + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_73 + +LBB11_74: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 + +LBB11_76: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_130 + LONG $0x08f98348 // cmp rcx, 8 + LONG $0x24748944; BYTE $0x08 // mov dword [rsp + 8], r14d + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000b8248c8948 // mov qword [rsp + 184], rcx + JB LBB11_80 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB11_216 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB11_216 -LBB11_121: +LBB11_80: WORD $0xc031 // xor eax, eax - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax - WORD $0x8948; BYTE $0xd0 // mov rax, rdx - WORD $0x894d; BYTE $0xfc // mov r12, r15 + LONG $0x24448948; BYTE $0x18 // mov qword [rsp + 24], rax + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB11_127: - LONG $0x24542b4c; BYTE $0x20 // sub r10, qword [rsp + 32] - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 +LBB11_81: + LONG $0x244c2b48; BYTE $0x18 // sub rcx, qword [rsp + 24] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx -LBB11_128: - LONG $0x703b4466; BYTE $0x3e // cmp r14w, word [rax + 62] - LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] - LONG $0x703b4466; BYTE $0x3c // cmp r14w, word [rax + 60] - LONG $0x24549d0f; BYTE $0x08 // setge byte [rsp + 8] - LONG $0x703b4466; BYTE $0x3a // cmp r14w, word [rax + 58] +LBB11_82: + LONG $0x723b4466; BYTE $0x3e // cmp r14w, word [rdx + 62] + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x723b4466; BYTE $0x3c // cmp r14w, word [rdx + 60] LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0x703b4466; BYTE $0x38 // cmp r14w, word [rax + 56] - LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] - LONG $0x703b4466; BYTE $0x36 // cmp r14w, word [rax + 54] + LONG $0x723b4466; BYTE $0x3a // cmp r14w, word [rdx + 58] LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0x703b4466; BYTE $0x34 // cmp r14w, word [rax + 52] + LONG $0x723b4466; BYTE $0x38 // cmp r14w, word [rdx + 56] LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0x703b4466; BYTE $0x32 // cmp r14w, word [rax + 50] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0x703b4466; BYTE $0x2e // cmp r14w, word [rax + 46] + LONG $0x723b4466; BYTE $0x36 // cmp r14w, word [rdx + 54] + LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] + LONG $0x723b4466; BYTE $0x34 // cmp r14w, word [rdx + 52] LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0x703b4466; BYTE $0x2c // cmp r14w, word [rax + 44] + LONG $0x723b4466; BYTE $0x32 // cmp r14w, word [rdx + 50] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x723b4466; BYTE $0x2e // cmp r14w, word [rdx + 46] LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0x703b4466; BYTE $0x2a // cmp r14w, word [rax + 42] - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0x703b4466; BYTE $0x28 // cmp r14w, word [rax + 40] + LONG $0x723b4466; BYTE $0x2c // cmp r14w, word [rdx + 44] LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x703b4466; BYTE $0x26 // cmp r14w, word [rax + 38] + LONG $0x723b4466; BYTE $0x2a // cmp r14w, word [rdx + 42] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x723b4466; BYTE $0x28 // cmp r14w, word [rdx + 40] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x723b4466; BYTE $0x26 // cmp r14w, word [rdx + 38] LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x703b4466; BYTE $0x24 // cmp r14w, word [rax + 36] + LONG $0x723b4466; BYTE $0x24 // cmp r14w, word [rdx + 36] LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x703b4466; BYTE $0x22 // cmp r14w, word [rax + 34] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x703b4466; BYTE $0x1e // cmp r14w, word [rax + 30] - LONG $0xd29d0f41 // setge r10b - LONG $0x703b4466; BYTE $0x1c // cmp r14w, word [rax + 28] + LONG $0x723b4466; BYTE $0x22 // cmp r14w, word [rdx + 34] LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x703b4466; BYTE $0x1a // cmp r14w, word [rax + 26] - WORD $0x8948; BYTE $0xc1 // mov rcx, rax - QUAD $0x0000009024949d0f // setge byte [rsp + 144] - LONG $0x703b4466; BYTE $0x18 // cmp r14w, word [rax + 24] - LONG $0xd59d0f41 // setge r13b - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x16413b66 // cmp ax, word [rcx + 22] + LONG $0x723b4466; BYTE $0x1e // cmp r14w, word [rdx + 30] + LONG $0xd29d0f41 // setge r10b + LONG $0x723b4466; BYTE $0x1c // cmp r14w, word [rdx + 28] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x723b4466; BYTE $0x1a // cmp r14w, word [rdx + 26] + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + LONG $0x723b4466; BYTE $0x18 // cmp r14w, word [rdx + 24] + LONG $0xd49d0f41 // setge r12b + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x16423b66 // cmp ax, word [rdx + 22] LONG $0xd79d0f41 // setge r15b - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x14413b66 // cmp ax, word [rcx + 20] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x14423b66 // cmp ax, word [rdx + 20] LONG $0xd69d0f41 // setge r14b - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x12413b66 // cmp ax, word [rcx + 18] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x12423b66 // cmp ax, word [rdx + 18] LONG $0xd39d0f41 // setge r11b - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x0e413b66 // cmp ax, word [rcx + 14] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x0e423b66 // cmp ax, word [rdx + 14] LONG $0xd69d0f40 // setge sil - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x0c413b66 // cmp ax, word [rcx + 12] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x0c423b66 // cmp ax, word [rdx + 12] QUAD $0x0000008024949d0f // setge byte [rsp + 128] - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x0a413b66 // cmp ax, word [rcx + 10] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x0a423b66 // cmp ax, word [rdx + 10] LONG $0xd19d0f41 // setge r9b - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x08413b66 // cmp ax, word [rcx + 8] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x08423b66 // cmp ax, word [rdx + 8] LONG $0xd09d0f41 // setge r8b - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x06413b66 // cmp ax, word [rcx + 6] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x06423b66 // cmp ax, word [rdx + 6] LONG $0xd79d0f40 // setge dil - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x04413b66 // cmp ax, word [rcx + 4] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - WORD $0x3b66; BYTE $0x01 // cmp ax, word [rcx] - QUAD $0x000000d024949d0f // setge byte [rsp + 208] - WORD $0x048b; BYTE $0x24 // mov eax, dword [rsp] - LONG $0x02413b66 // cmp ax, word [rcx + 2] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x04423b66 // cmp ax, word [rdx + 4] + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x0824448b // mov eax, dword [rsp + 8] + WORD $0x3b66; BYTE $0x02 // cmp ax, word [rdx] + QUAD $0x000000f024949d0f // setge byte [rsp + 240] + LONG $0x0824448b // mov eax, dword [rsp + 8] + LONG $0x02423b66 // cmp ax, word [rdx + 2] WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0x894c; BYTE $0xe3 // mov rbx, r12 - LONG $0x24248b44 // mov r12d, dword [rsp] - LONG $0x613b4466; BYTE $0x10 // cmp r12w, word [rcx + 16] - WORD $0x8949; BYTE $0xdc // mov r12, rbx - QUAD $0x000000e024949d0f // setge byte [rsp + 224] - WORD $0x1c8b; BYTE $0x24 // mov ebx, dword [rsp] - LONG $0x20593b66 // cmp bx, word [rcx + 32] - QUAD $0x000000b024949d0f // setge byte [rsp + 176] - WORD $0x1c8b; BYTE $0x24 // mov ebx, dword [rsp] - LONG $0x30593b66 // cmp bx, word [rcx + 48] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x246c8b44; BYTE $0x08 // mov r13d, dword [rsp + 8] + LONG $0x6a3b4466; BYTE $0x10 // cmp r13w, word [rdx + 16] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x08245c8b // mov ebx, dword [rsp + 8] + LONG $0x205a3b66 // cmp bx, word [rdx + 32] + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + LONG $0x08245c8b // mov ebx, dword [rsp + 8] + LONG $0x305a3b66 // cmp bx, word [rdx + 48] + QUAD $0x000000c024949d0f // setge byte [rsp + 192] WORD $0xc000 // add al, al - LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 - WORD $0xc208 // or dl, al + LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al LONG $0x03e7c040 // shl dil, 3 - WORD $0x0840; BYTE $0xd7 // or dil, dl + WORD $0x0840; BYTE $0xcf // or dil, cl LONG $0x04e0c041 // shl r8b, 4 WORD $0x0841; BYTE $0xf8 // or r8b, dil LONG $0x05e1c041 // shl r9b, 5 @@ -55924,235 +56942,248 @@ LBB11_128: LONG $0x07e6c040 // shl sil, 7 WORD $0x0840; BYTE $0xc6 // or sil, al WORD $0x0844; BYTE $0xce // or sil, r9b - LONG $0x24348841 // mov byte [r12], sil + LONG $0x00758841 // mov byte [r13], sil WORD $0x0045; BYTE $0xdb // add r11b, r11b - QUAD $0x000000e0249c0244 // add r11b, byte [rsp + 224] + QUAD $0x00000090249c0244 // add r11b, byte [rsp + 144] LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xde // or r14b, r11b LONG $0x03e7c041 // shl r15b, 3 WORD $0x0845; BYTE $0xf7 // or r15b, r14b - LONG $0x04e5c041 // shl r13b, 4 - WORD $0x0845; BYTE $0xfd // or r13b, r15b - QUAD $0x000000902484b60f // movzx eax, byte [rsp + 144] + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0x0844; BYTE $0xe8 // or al, r13b - LONG $0x24348b44 // mov r14d, dword [rsp] - LONG $0x2454b60f; BYTE $0x70 // movzx edx, byte [rsp + 112] - WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x24748b44; BYTE $0x08 // mov r14d, dword [rsp + 8] + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 LONG $0x07e2c041 // shl r10b, 7 - WORD $0x0841; BYTE $0xd2 // or r10b, dl + WORD $0x0841; BYTE $0xca // or r10b, cl WORD $0x0841; BYTE $0xc2 // or r10b, al - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - LONG $0x24548845; BYTE $0x01 // mov byte [r12 + 1], r10b - LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] - WORD $0xc900 // add cl, cl - LONG $0xb0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 176] - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x245cb60f; BYTE $0x40 // movzx ebx, byte [rsp + 64] + LONG $0x01558845 // mov byte [r13 + 1], r10b + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x50 // movzx ebx, byte [rsp + 80] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xd108 // or cl, dl - LONG $0x244c8841; BYTE $0x02 // mov byte [r12 + 2], cl - LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] - WORD $0xc900 // add cl, cl - LONG $0xa0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 160] - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] - WORD $0xe1c0; BYTE $0x02 // shl cl, 2 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] - WORD $0xe1c0; BYTE $0x03 // shl cl, 3 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x244cb60f; BYTE $0x10 // movzx ecx, byte [rsp + 16] - WORD $0xe1c0; BYTE $0x05 // shl cl, 5 - WORD $0xd108 // or cl, dl - WORD $0xca89 // mov edx, ecx - LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x02458841 // mov byte [r13 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0xc0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 192] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd908 // or cl, bl - WORD $0xd108 // or cl, dl - LONG $0x244c8841; BYTE $0x03 // mov byte [r12 + 3], cl - LONG $0x40c08348 // add rax, 64 - LONG $0x04c48349 // add r12, 4 - QUAD $0x000000c024848348; BYTE $0xff // add qword [rsp + 192], -1 - JNE LBB11_128 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - JMP LBB11_130 - -LBB11_157: - WORD $0x8b4c; BYTE $0x36 // mov r14, qword [rsi] - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_161 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_159: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - LONG $0x08528d48 // lea rdx, [rdx + 8] - WORD $0x9d0f; BYTE $0xd3 // setge bl - WORD $0xdbf6 // neg bl - LONG $0x07708d48 // lea rsi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf0490f48 // cmovns rsi, rax - LONG $0x03fec148 // sar rsi, 3 - LONG $0x04b60f45; BYTE $0x37 // movzx r8d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xc3 // xor bl, r8b - LONG $0x00f53c8d; WORD $0x0000; BYTE $0x00 // lea edi, [8*rsi] - WORD $0xc189 // mov ecx, eax - WORD $0xf929 // sub ecx, edi - LONG $0x000001bf; BYTE $0x00 // mov edi, 1 - WORD $0xe7d3 // shl edi, cl - WORD $0x2040; BYTE $0xdf // and dil, bl - WORD $0x3044; BYTE $0xc7 // xor dil, r8b - LONG $0x373c8841 // mov byte [r15 + rsi], dil - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_159 - LONG $0x01c78349 // add r15, 1 + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x40c28348 // add rdx, 64 + LONG $0x04c58349 // add r13, 4 + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB11_82 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + JMP LBB11_131 + +LBB11_84: + WORD $0x8b4c; BYTE $0x06 // mov r8, qword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_90 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_88 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_87: + LONG $0x08518d48 // lea rdx, [rcx + 8] + WORD $0x3b4c; BYTE $0x01 // cmp r8, qword [rcx] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_87 -LBB11_161: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_165 - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 +LBB11_88: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 + +LBB11_90: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_94 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax -LBB11_163: - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - LONG $0xf8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 248] - LONG $0x24149d0f // setge byte [rsp] - LONG $0xf0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 240] - LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] - LONG $0xe8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 232] +LBB11_92: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0xf8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 248] LONG $0x24549d0f; BYTE $0x08 // setge byte [rsp + 8] - LONG $0xe0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 224] - LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] - LONG $0xd8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 216] + LONG $0xf0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 240] LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] - LONG $0xd0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 208] + LONG $0xe8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 232] + LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] + LONG $0xe0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 224] LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] - LONG $0xc8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 200] - LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] - LONG $0xb8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 184] + LONG $0xd8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 216] + LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] + LONG $0xd0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 208] LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] - LONG $0xb0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 176] - LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] - LONG $0xa8b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 168] + LONG $0xc8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 200] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0xb8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 184] LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] - LONG $0xa0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 160] + LONG $0xb0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 176] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0xa8823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 168] LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] - LONG $0x98b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 152] + LONG $0xa0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 160] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x98823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 152] LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] - LONG $0x90b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 144] + LONG $0x90823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 144] LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] - LONG $0x88b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 136] - LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] - LONG $0x78723b4c // cmp r14, qword [rdx + 120] - LONG $0xd09d0f41 // setge r8b - LONG $0x70723b4c // cmp r14, qword [rdx + 112] - QUAD $0x000000a024949d0f // setge byte [rsp + 160] - LONG $0x68723b4c // cmp r14, qword [rdx + 104] + LONG $0x88823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 136] LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] - LONG $0x60723b4c // cmp r14, qword [rdx + 96] + LONG $0x78423b4c // cmp r8, qword [rdx + 120] + LONG $0xd79d0f40 // setge dil + LONG $0x70423b4c // cmp r8, qword [rdx + 112] + QUAD $0x000000c024949d0f // setge byte [rsp + 192] + LONG $0x68423b4c // cmp r8, qword [rdx + 104] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x60423b4c // cmp r8, qword [rdx + 96] LONG $0xd39d0f41 // setge r11b - LONG $0x58723b4c // cmp r14, qword [rdx + 88] + LONG $0x58423b4c // cmp r8, qword [rdx + 88] LONG $0xd29d0f41 // setge r10b - LONG $0x50723b4c // cmp r14, qword [rdx + 80] + LONG $0x50423b4c // cmp r8, qword [rdx + 80] LONG $0xd19d0f41 // setge r9b - LONG $0x48723b4c // cmp r14, qword [rdx + 72] - LONG $0xd79d0f40 // setge dil - LONG $0x38723b4c // cmp r14, qword [rdx + 56] + LONG $0x48423b4c // cmp r8, qword [rdx + 72] + LONG $0xd69d0f40 // setge sil + LONG $0x38423b4c // cmp r8, qword [rdx + 56] WORD $0x9d0f; BYTE $0xd0 // setge al - LONG $0x30723b4c // cmp r14, qword [rdx + 48] + LONG $0x30423b4c // cmp r8, qword [rdx + 48] WORD $0x9d0f; BYTE $0xd3 // setge bl - LONG $0x28723b4c // cmp r14, qword [rdx + 40] - LONG $0xd69d0f40 // setge sil - LONG $0x20723b4c // cmp r14, qword [rdx + 32] + LONG $0x28423b4c // cmp r8, qword [rdx + 40] WORD $0x9d0f; BYTE $0xd1 // setge cl - LONG $0x18723b4c // cmp r14, qword [rdx + 24] + LONG $0x20423b4c // cmp r8, qword [rdx + 32] LONG $0xd59d0f41 // setge r13b - LONG $0x10723b4c // cmp r14, qword [rdx + 16] + LONG $0x18423b4c // cmp r8, qword [rdx + 24] LONG $0xd49d0f41 // setge r12b - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - QUAD $0x000000e024949d0f // setge byte [rsp + 224] - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x10423b4c // cmp r8, qword [rdx + 16] LONG $0xd79d0f41 // setge r15b - LONG $0x40723b4c // cmp r14, qword [rdx + 64] - QUAD $0x0000008024949d0f // setge byte [rsp + 128] - LONG $0x80b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 128] - QUAD $0x000000b024949d0f // setge byte [rsp + 176] - LONG $0xc0b23b4c; WORD $0x0000; BYTE $0x00 // cmp r14, qword [rdx + 192] + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] QUAD $0x0000009024949d0f // setge byte [rsp + 144] - WORD $0x0045; BYTE $0xff // add r15b, r15b - QUAD $0x000000e024bc0244 // add r15b, byte [rsp + 224] - LONG $0x02e4c041 // shl r12b, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] + LONG $0xd69d0f41 // setge r14b + LONG $0x40423b4c // cmp r8, qword [rdx + 64] + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x80823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 128] + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + LONG $0xc0823b4c; WORD $0x0000; BYTE $0x00 // cmp r8, qword [rdx + 192] + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x0000009024b40244 // add r14b, byte [rsp + 144] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 WORD $0x0845; BYTE $0xfc // or r12b, r15b - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - LONG $0x03e5c041 // shl r13b, 3 + LONG $0x04e5c041 // shl r13b, 4 WORD $0x0845; BYTE $0xe5 // or r13b, r12b - WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 WORD $0x0844; BYTE $0xe9 // or cl, r13b - LONG $0x05e6c040 // shl sil, 5 - WORD $0x0840; BYTE $0xce // or sil, cl WORD $0xe3c0; BYTE $0x06 // shl bl, 6 WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl - WORD $0x0840; BYTE $0xf0 // or al, sil - WORD $0x8841; BYTE $0x07 // mov byte [r15], al - WORD $0x0040; BYTE $0xff // add dil, dil - QUAD $0x0000008024bc0240 // add dil, byte [rsp + 128] + WORD $0xc808 // or al, cl + LONG $0x24048841 // mov byte [r12], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] LONG $0x02e1c041 // shl r9b, 2 - WORD $0x0841; BYTE $0xf9 // or r9b, dil + WORD $0x0841; BYTE $0xf1 // or r9b, sil LONG $0x03e2c041 // shl r10b, 3 WORD $0x0845; BYTE $0xca // or r10b, r9b LONG $0x04e3c041 // shl r11b, 4 WORD $0x0845; BYTE $0xd3 // or r11b, r10b - LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0x0844; BYTE $0xd8 // or al, r11b - QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] WORD $0xe1c0; BYTE $0x06 // shl cl, 6 - LONG $0x07e0c041 // shl r8b, 7 - WORD $0x0841; BYTE $0xc8 // or r8b, cl - WORD $0x0841; BYTE $0xc0 // or r8b, al - LONG $0x01478845 // mov byte [r15 + 1], r8b - LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] WORD $0xc000 // add al, al - LONG $0xb0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 176] + LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] WORD $0xc189 // mov ecx, eax LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] WORD $0xe0c0; BYTE $0x02 // shl al, 2 @@ -56162,132 +57193,148 @@ LBB11_163: WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x02478841 // mov byte [r15 + 2], al + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x03 // shl al, 3 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] WORD $0xe0c0; BYTE $0x05 // shl al, 5 WORD $0xc808 // or al, cl WORD $0xc189 // mov ecx, eax - LONG $0x245cb60f; BYTE $0x10 // movzx ebx, byte [rsp + 16] + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] WORD $0xe3c0; BYTE $0x06 // shl bl, 6 - LONG $0x2404b60f // movzx eax, byte [rsp] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] WORD $0xe0c0; BYTE $0x07 // shl al, 7 WORD $0xd808 // or al, bl WORD $0xc808 // or al, cl - LONG $0x03478841 // mov byte [r15 + 3], al + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al LONG $0x00c28148; WORD $0x0001; BYTE $0x00 // add rdx, 256 - LONG $0x04c78349 // add r15, 4 - QUAD $0x000000d024848348; BYTE $0xff // add qword [rsp + 208], -1 - JNE LBB11_163 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000c024948b4c // mov r10, qword [rsp + 192] + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB11_92 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] -LBB11_165: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_170 +LBB11_94: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB11_199 WORD $0xff31 // xor edi, edi - JMP LBB11_168 + JMP LBB11_201 -LBB11_172: - LONG $0x1f538d4d // lea r10, [r11 + 31] - WORD $0x854d; BYTE $0xdb // test r11, r11 - LONG $0xd3490f4d // cmovns r10, r11 - LONG $0x07418d41 // lea eax, [r9 + 7] - WORD $0x8545; BYTE $0xc9 // test r9d, r9d - LONG $0xc1490f41 // cmovns eax, r9d - WORD $0xe083; BYTE $0xf8 // and eax, -8 - LONG $0x06100ff3 // movss xmm0, dword [rsi] - WORD $0x2941; BYTE $0xc1 // sub r9d, eax - JE LBB11_176 - WORD $0x6349; BYTE $0xc1 // movsxd rax, r9d - -LBB11_174: - WORD $0x2e0f; BYTE $0x02 // ucomiss xmm0, dword [rdx] - LONG $0x04528d48 // lea rdx, [rdx + 4] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - LONG $0x07788d48 // lea rdi, [rax + 7] - WORD $0x8548; BYTE $0xc0 // test rax, rax - LONG $0xf8490f48 // cmovns rdi, rax - LONG $0x03ffc148 // sar rdi, 3 - LONG $0x0cb60f45; BYTE $0x3f // movzx r9d, byte [r15 + rdi] - WORD $0x3044; BYTE $0xce // xor sil, r9b - QUAD $0x00000000fd048d44 // lea r8d, [8*rdi] - WORD $0xc189 // mov ecx, eax - WORD $0x2944; BYTE $0xc1 // sub ecx, r8d - LONG $0x000001bb; BYTE $0x00 // mov ebx, 1 - WORD $0xe3d3 // shl ebx, cl - WORD $0x2040; BYTE $0xf3 // and bl, sil +LBB11_97: + WORD $0x8b44; BYTE $0x36 // mov r14d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_103 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_101 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_100: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x2e0f; BYTE $0x01 // ucomiss xmm0, dword [rcx] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + LONG $0x07468d48 // lea rax, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xc6490f48 // cmovns rax, rsi + LONG $0x03f8c148 // sar rax, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x04 // movzx r9d, byte [r12 + rax] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3f1c8841 // mov byte [r15 + rdi], bl - LONG $0x01c08348 // add rax, 1 - LONG $0x08f88348 // cmp rax, 8 - JNE LBB11_174 - LONG $0x01c78349 // add r15, 1 + QUAD $0x00000000c5148d44 // lea r10d, [8*rax] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xdf // and dil, bl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x043c8841 // mov byte [r12 + rax], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_100 -LBB11_176: - LONG $0x05fac149 // sar r10, 5 - LONG $0x20fb8349 // cmp r11, 32 - JL LBB11_177 - LONG $0x04fa8349 // cmp r10, 4 - JB LBB11_179 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x07e0c148 // shl rax, 7 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - WORD $0x3949; BYTE $0xc7 // cmp r15, rax - JAE LBB11_182 - LONG $0x97048d4b // lea rax, [r15 + 4*r10] - WORD $0x3948; BYTE $0xd0 // cmp rax, rdx - JBE LBB11_182 +LBB11_101: + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 + +LBB11_103: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_134 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x04f98348 // cmp rcx, 4 + JB LBB11_107 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x07e0c148 // shl rax, 7 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB11_219 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3948; BYTE $0xd0 // cmp rax, rdx + JBE LBB11_219 -LBB11_179: - WORD $0x3145; BYTE $0xc0 // xor r8d, r8d +LBB11_107: + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d WORD $0x8948; BYTE $0xd3 // mov rbx, rdx - WORD $0x894d; BYTE $0xfe // mov r14, r15 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB11_185: - QUAD $0x00000088249c894c // mov qword [rsp + 136], r11 - QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 - WORD $0x294d; BYTE $0xc2 // sub r10, r8 - QUAD $0x000000e02494894c // mov qword [rsp + 224], r10 +LBB11_108: + LONG $0x246c894c; BYTE $0x08 // mov qword [rsp + 8], r13 + QUAD $0x000000f024b48944 // mov dword [rsp + 240], r14d + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + WORD $0x294c; BYTE $0xc9 // sub rcx, r9 + QUAD $0x00000090248c8948 // mov qword [rsp + 144], rcx -LBB11_186: - LONG $0x2434894c // mov qword [rsp], r14 +LBB11_109: WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] QUAD $0x000000802494930f // setae byte [rsp + 128] LONG $0x04432e0f // ucomiss xmm0, dword [rbx + 4] @@ -56297,61 +57344,61 @@ LBB11_186: LONG $0x0c432e0f // ucomiss xmm0, dword [rbx + 12] LONG $0xd5930f41 // setae r13b LONG $0x10432e0f // ucomiss xmm0, dword [rbx + 16] - LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] LONG $0x14432e0f // ucomiss xmm0, dword [rbx + 20] - LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] LONG $0x18432e0f // ucomiss xmm0, dword [rbx + 24] WORD $0x930f; BYTE $0xd0 // setae al LONG $0x1c432e0f // ucomiss xmm0, dword [rbx + 28] LONG $0xd3930f41 // setae r11b LONG $0x20432e0f // ucomiss xmm0, dword [rbx + 32] - LONG $0x2454930f; BYTE $0x70 // setae byte [rsp + 112] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] LONG $0x24432e0f // ucomiss xmm0, dword [rbx + 36] - WORD $0x930f; BYTE $0xd2 // setae dl + WORD $0x930f; BYTE $0xd1 // setae cl LONG $0x28432e0f // ucomiss xmm0, dword [rbx + 40] LONG $0xd6930f40 // setae sil LONG $0x2c432e0f // ucomiss xmm0, dword [rbx + 44] - LONG $0xd1930f41 // setae r9b + LONG $0xd7930f40 // setae dil LONG $0x30432e0f // ucomiss xmm0, dword [rbx + 48] LONG $0xd2930f41 // setae r10b LONG $0x34432e0f // ucomiss xmm0, dword [rbx + 52] LONG $0xd4930f41 // setae r12b LONG $0x38432e0f // ucomiss xmm0, dword [rbx + 56] - QUAD $0x000000a02494930f // setae byte [rsp + 160] + QUAD $0x000000c02494930f // setae byte [rsp + 192] LONG $0x3c432e0f // ucomiss xmm0, dword [rbx + 60] - LONG $0xd7930f40 // setae dil + LONG $0xd1930f41 // setae r9b LONG $0x40432e0f // ucomiss xmm0, dword [rbx + 64] LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] LONG $0x44432e0f // ucomiss xmm0, dword [rbx + 68] - QUAD $0x000000b02494930f // setae byte [rsp + 176] + QUAD $0x000000d02494930f // setae byte [rsp + 208] LONG $0x48432e0f // ucomiss xmm0, dword [rbx + 72] - QUAD $0x000000902494930f // setae byte [rsp + 144] + QUAD $0x000000a02494930f // setae byte [rsp + 160] LONG $0x4c432e0f // ucomiss xmm0, dword [rbx + 76] LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] LONG $0x50432e0f // ucomiss xmm0, dword [rbx + 80] - LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] LONG $0x54432e0f // ucomiss xmm0, dword [rbx + 84] LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] LONG $0x58432e0f // ucomiss xmm0, dword [rbx + 88] - LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] LONG $0x5c432e0f // ucomiss xmm0, dword [rbx + 92] LONG $0xd7930f41 // setae r15b LONG $0x60432e0f // ucomiss xmm0, dword [rbx + 96] - LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] + LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] LONG $0x64432e0f // ucomiss xmm0, dword [rbx + 100] LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] LONG $0x68432e0f // ucomiss xmm0, dword [rbx + 104] - LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] LONG $0x6c432e0f // ucomiss xmm0, dword [rbx + 108] - LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] LONG $0x70432e0f // ucomiss xmm0, dword [rbx + 112] - LONG $0x2454930f; BYTE $0x08 // setae byte [rsp + 8] - LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + LONG $0x74432e0f // ucomiss xmm0, dword [rbx + 116] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] LONG $0x78432e0f // ucomiss xmm0, dword [rbx + 120] - LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + QUAD $0x000000882494930f // setae byte [rsp + 136] LONG $0x7c432e0f // ucomiss xmm0, dword [rbx + 124] - WORD $0x930f; BYTE $0xd1 // setae cl + WORD $0x930f; BYTE $0xd2 // setae dl WORD $0x0045; BYTE $0xc0 // add r8b, r8b QUAD $0x0000008024840244 // add r8b, byte [rsp + 128] WORD $0xe0c0; BYTE $0x06 // shl al, 6 @@ -56359,175 +57406,888 @@ LBB11_186: WORD $0x0841; BYTE $0xc3 // or r11b, al LONG $0x02e6c041 // shl r14b, 2 WORD $0x0845; BYTE $0xc6 // or r14b, r8b - WORD $0xd200 // add dl, dl - LONG $0x70245402 // add dl, byte [rsp + 112] + WORD $0xc900 // add cl, cl + LONG $0x78244c02 // add cl, byte [rsp + 120] LONG $0x03e5c041 // shl r13b, 3 WORD $0x0845; BYTE $0xf5 // or r13b, r14b LONG $0x02e6c040 // shl sil, 2 - WORD $0x0840; BYTE $0xd6 // or sil, dl - LONG $0x2454b60f; BYTE $0x68 // movzx edx, byte [rsp + 104] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0844; BYTE $0xea // or dl, r13b - WORD $0x8941; BYTE $0xd0 // mov r8d, edx - LONG $0x24348b4c // mov r14, qword [rsp] - LONG $0x03e1c041 // shl r9b, 3 - WORD $0x0841; BYTE $0xf1 // or r9b, sil - LONG $0x2454b60f; BYTE $0x40 // movzx edx, byte [rsp + 64] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0844; BYTE $0xc2 // or dl, r8b + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x244cb60f; BYTE $0x70 // movzx ecx, byte [rsp + 112] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0x8941; BYTE $0xc8 // mov r8d, ecx + LONG $0x03e7c040 // shl dil, 3 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x244cb60f; BYTE $0x50 // movzx ecx, byte [rsp + 80] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xc1 // or cl, r8b LONG $0x04e2c041 // shl r10b, 4 - WORD $0x0845; BYTE $0xca // or r10b, r9b + WORD $0x0841; BYTE $0xfa // or r10b, dil LONG $0x05e4c041 // shl r12b, 5 WORD $0x0845; BYTE $0xd4 // or r12b, r10b - QUAD $0x000000a024b4b60f // movzx esi, byte [rsp + 160] + QUAD $0x000000c024b4b60f // movzx esi, byte [rsp + 192] LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e7c040 // shl dil, 7 - WORD $0x0840; BYTE $0xf7 // or dil, sil - WORD $0x0841; BYTE $0xd3 // or r11b, dl - WORD $0x0844; BYTE $0xe7 // or dil, r12b - QUAD $0x000000b02484b60f // movzx eax, byte [rsp + 176] + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + WORD $0x0841; BYTE $0xcb // or r11b, cl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] WORD $0xc000 // add al, al LONG $0x60244402 // add al, byte [rsp + 96] - QUAD $0x000000902494b60f // movzx edx, byte [rsp + 144] - WORD $0xe2c0; BYTE $0x02 // shl dl, 2 + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0xce89 // mov esi, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0840; BYTE $0xf1 // or cl, sil + LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] + WORD $0x8844; BYTE $0x1e // mov byte [rsi], r11b + LONG $0x247cb60f; BYTE $0x40 // movzx edi, byte [rsp + 64] + LONG $0x06e7c040 // shl dil, 6 + LONG $0x07e7c041 // shl r15b, 7 + WORD $0x0841; BYTE $0xff // or r15b, dil + LONG $0x014e8844 // mov byte [rsi + 1], r9b + WORD $0x0841; BYTE $0xcf // or r15b, cl + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0x20244402 // add al, byte [rsp + 32] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xca08 // or dl, cl WORD $0xc208 // or dl, al - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x58 // movzx edx, byte [rsp + 88] - WORD $0xe2c0; BYTE $0x03 // shl dl, 3 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx + LONG $0x027e8844 // mov byte [rsi + 2], r15b + WORD $0x5688; BYTE $0x03 // mov byte [rsi + 3], dl + LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 + LONG $0x04c68348 // add rsi, 4 + LONG $0x24748948; BYTE $0x08 // mov qword [rsp + 8], rsi + QUAD $0x0000009024848348; BYTE $0xff // add qword [rsp + 144], -1 + JNE LBB11_109 + LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000f024b48b44 // mov r14d, dword [rsp + 240] + QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] + JMP LBB11_135 + +LBB11_111: + WORD $0x8a44; BYTE $0x2e // mov r13b, byte [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_138 + LONG $0x0008b841; WORD $0x0000 // mov r8d, 8 + WORD $0x2945; BYTE $0xc8 // sub r8d, r9d + WORD $0x394d; BYTE $0xf8 // cmp r8, r15 + LONG $0xc74f0f4d // cmovg r8, r15 + WORD $0x854d; BYTE $0xc0 // test r8, r8 + JLE LBB11_153 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + +LBB11_114: + LONG $0x015a8d4c // lea r11, [rdx + 1] + WORD $0x3a44; BYTE $0x2a // cmp r13b, byte [rdx] + LONG $0x000000ba; BYTE $0x00 // mov edx, 0 + WORD $0xd280; BYTE $0xff // adc dl, -1 + LONG $0x075e8d48 // lea rbx, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xde490f48 // cmovns rbx, rsi + LONG $0x03fbc148 // sar rbx, 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x1c // movzx r9d, byte [r12 + rbx] + WORD $0x3044; BYTE $0xca // xor dl, r9b + QUAD $0x00000000dd148d44 // lea r10d, [8*rbx] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001bf; BYTE $0x00 // mov edi, 1 + WORD $0xe7d3 // shl edi, cl + WORD $0x2040; BYTE $0xd7 // and dil, dl + WORD $0x3044; BYTE $0xcf // xor dil, r9b + LONG $0x1c3c8841 // mov byte [r12 + rbx], dil + LONG $0x01c68348 // add rsi, 1 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0xffc08348 // add rax, -1 + JNE LBB11_114 + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JNE LBB11_154 + JMP LBB11_215 + +LBB11_116: + WORD $0x8b44; BYTE $0x06 // mov r8d, dword [rsi] + LONG $0x07418d41 // lea eax, [r9 + 7] + WORD $0x8545; BYTE $0xc9 // test r9d, r9d + LONG $0xc1490f41 // cmovns eax, r9d + WORD $0xe083; BYTE $0xf8 // and eax, -8 + WORD $0x2941; BYTE $0xc1 // sub r9d, eax + JE LBB11_122 + LONG $0x0008be41; WORD $0x0000 // mov r14d, 8 + WORD $0x2945; BYTE $0xce // sub r14d, r9d + WORD $0x394d; BYTE $0xfe // cmp r14, r15 + LONG $0xf74f0f4d // cmovg r14, r15 + WORD $0x854d; BYTE $0xf6 // test r14, r14 + JLE LBB11_120 + WORD $0x6349; BYTE $0xf1 // movsxd rsi, r9d + WORD $0x894d; BYTE $0xf3 // mov r11, r14 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + +LBB11_119: + LONG $0x04518d48 // lea rdx, [rcx + 4] + WORD $0x3b44; BYTE $0x01 // cmp r8d, dword [rcx] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + LONG $0x077e8d48 // lea rdi, [rsi + 7] + WORD $0x8548; BYTE $0xf6 // test rsi, rsi + LONG $0xfe490f48 // cmovns rdi, rsi + LONG $0x03ffc148 // sar rdi, 3 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + LONG $0x0cb60f45; BYTE $0x3c // movzx r9d, byte [r12 + rdi] + WORD $0x3044; BYTE $0xcb // xor bl, r9b + QUAD $0x00000000fd148d44 // lea r10d, [8*rdi] + WORD $0xf189 // mov ecx, esi + WORD $0x2944; BYTE $0xd1 // sub ecx, r10d + LONG $0x000001b8; BYTE $0x00 // mov eax, 1 + WORD $0xe0d3 // shl eax, cl + WORD $0xd820 // and al, bl + WORD $0x3044; BYTE $0xc8 // xor al, r9b + LONG $0x3c048841 // mov byte [r12 + rdi], al + LONG $0x01c68348 // add rsi, 1 + WORD $0x8948; BYTE $0xd1 // mov rcx, rdx + LONG $0xffc38349 // add r11, -1 + JNE LBB11_119 + +LBB11_120: + WORD $0x294d; BYTE $0xf7 // sub r15, r14 + JE LBB11_215 + LONG $0x01c48349 // add r12, 1 + +LBB11_122: + LONG $0x1f478d49 // lea rax, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xc7490f49 // cmovns rax, r15 + LONG $0x05f8c148 // sar rax, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_126 + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x000000e024848948 // mov qword [rsp + 224], rax + QUAD $0x000000f024848948 // mov qword [rsp + 240], rax + +LBB11_124: + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0x7c423b44 // cmp r8d, dword [rdx + 124] + LONG $0x24549d0f; BYTE $0x08 // setge byte [rsp + 8] + LONG $0x78423b44 // cmp r8d, dword [rdx + 120] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x74423b44 // cmp r8d, dword [rdx + 116] + LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] + LONG $0x70423b44 // cmp r8d, dword [rdx + 112] + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x6c423b44 // cmp r8d, dword [rdx + 108] + LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] + LONG $0x68423b44 // cmp r8d, dword [rdx + 104] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x64423b44 // cmp r8d, dword [rdx + 100] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x5c423b44 // cmp r8d, dword [rdx + 92] + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x58423b44 // cmp r8d, dword [rdx + 88] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x54423b44 // cmp r8d, dword [rdx + 84] + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x50423b44 // cmp r8d, dword [rdx + 80] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x4c423b44 // cmp r8d, dword [rdx + 76] + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x48423b44 // cmp r8d, dword [rdx + 72] + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x44423b44 // cmp r8d, dword [rdx + 68] + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x3c423b44 // cmp r8d, dword [rdx + 60] + LONG $0xd79d0f40 // setge dil + LONG $0x38423b44 // cmp r8d, dword [rdx + 56] + QUAD $0x000000c024949d0f // setge byte [rsp + 192] + LONG $0x34423b44 // cmp r8d, dword [rdx + 52] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x30423b44 // cmp r8d, dword [rdx + 48] + LONG $0xd39d0f41 // setge r11b + LONG $0x2c423b44 // cmp r8d, dword [rdx + 44] + LONG $0xd29d0f41 // setge r10b + LONG $0x28423b44 // cmp r8d, dword [rdx + 40] + LONG $0xd19d0f41 // setge r9b + LONG $0x24423b44 // cmp r8d, dword [rdx + 36] + LONG $0xd69d0f40 // setge sil + LONG $0x1c423b44 // cmp r8d, dword [rdx + 28] + WORD $0x9d0f; BYTE $0xd0 // setge al + LONG $0x18423b44 // cmp r8d, dword [rdx + 24] + WORD $0x9d0f; BYTE $0xd3 // setge bl + LONG $0x14423b44 // cmp r8d, dword [rdx + 20] + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x10423b44 // cmp r8d, dword [rdx + 16] + LONG $0xd59d0f41 // setge r13b + LONG $0x0c423b44 // cmp r8d, dword [rdx + 12] + LONG $0xd49d0f41 // setge r12b + LONG $0x08423b44 // cmp r8d, dword [rdx + 8] + LONG $0xd79d0f41 // setge r15b + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] + LONG $0xd69d0f41 // setge r14b + LONG $0x20423b44 // cmp r8d, dword [rdx + 32] + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x40423b44 // cmp r8d, dword [rdx + 64] + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + LONG $0x60423b44 // cmp r8d, dword [rdx + 96] + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + WORD $0x0045; BYTE $0xf6 // add r14b, r14b + QUAD $0x0000009024b40244 // add r14b, byte [rsp + 144] + LONG $0x02e7c041 // shl r15b, 2 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x03e4c041 // shl r12b, 3 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x04e5c041 // shl r13b, 4 + WORD $0x0845; BYTE $0xe5 // or r13b, r12b + QUAD $0x0000008824a48b4c // mov r12, qword [rsp + 136] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0x0844; BYTE $0xe9 // or cl, r13b + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x24048841 // mov byte [r12], al + WORD $0x0040; BYTE $0xf6 // add sil, sil + QUAD $0x0000008024b40240 // add sil, byte [rsp + 128] + LONG $0x02e1c041 // shl r9b, 2 + WORD $0x0841; BYTE $0xf1 // or r9b, sil + LONG $0x03e2c041 // shl r10b, 3 + WORD $0x0845; BYTE $0xca // or r10b, r9b + LONG $0x04e3c041 // shl r11b, 4 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x2444b60f; BYTE $0x78 // movzx eax, byte [rsp + 120] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xd8 // or al, r11b + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e7c040 // shl dil, 7 + WORD $0x0840; BYTE $0xcf // or dil, cl + WORD $0x0840; BYTE $0xc7 // or dil, al + LONG $0x247c8841; BYTE $0x01 // mov byte [r12 + 1], dil + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0xd0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 208] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x50 // movzx eax, byte [rsp + 80] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x48 // movzx ebx, byte [rsp + 72] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x24448841; BYTE $0x02 // mov byte [r12 + 2], al + LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] + WORD $0xc000 // add al, al + LONG $0xa0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 160] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x245cb60f; BYTE $0x28 // movzx ebx, byte [rsp + 40] + WORD $0xe3c0; BYTE $0x06 // shl bl, 6 + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd808 // or al, bl + WORD $0xc808 // or al, cl + LONG $0x24448841; BYTE $0x03 // mov byte [r12 + 3], al + LONG $0x80ea8348 // sub rdx, -128 + LONG $0x04c48349 // add r12, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB11_124 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x000000e024848b48 // mov rax, qword [rsp + 224] + +LBB11_126: + LONG $0x05e0c148 // shl rax, 5 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + WORD $0x2949; BYTE $0xc1 // sub r9, rax + JLE LBB11_215 + LONG $0x01c88348 // or rax, 1 + WORD $0x3949; BYTE $0xc7 // cmp r15, rax + JNE LBB11_171 + WORD $0xff31 // xor edi, edi + JMP LBB11_173 + +LBB11_129: + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + JMP LBB11_141 + +LBB11_130: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + +LBB11_131: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB11_215 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB11_205 + WORD $0xf631 // xor esi, esi + JMP LBB11_207 + +LBB11_134: + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + WORD $0x8948; BYTE $0xd3 // mov rbx, rdx + +LBB11_135: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB11_215 + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB11_210 + WORD $0x3145; BYTE $0xdb // xor r11d, r11d + JMP LBB11_212 + +LBB11_138: + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + JMP LBB11_155 + +LBB11_139: + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB11_215 + +LBB11_140: + LONG $0x01c48349 // add r12, 1 + +LBB11_141: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_149 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x24748844; BYTE $0x08 // mov byte [rsp + 8], r14b + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x00000110248c8948 // mov qword [rsp + 272], rcx + JB LBB11_145 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xe8 // add rax, r13 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB11_222 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc5 // cmp r13, rax + JAE LBB11_222 + +LBB11_145: + WORD $0xc031 // xor eax, eax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + WORD $0x894c; BYTE $0xef // mov rdi, r13 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 + +LBB11_146: + QUAD $0x000000b8248c2b48 // sub rcx, qword [rsp + 184] + QUAD $0x000000f0248c8948 // mov qword [rsp + 240], rcx + +LBB11_147: + LONG $0x1f773a44 // cmp r14b, byte [rdi + 31] + QUAD $0x0000008824949d0f // setge byte [rsp + 136] + LONG $0x1e773a44 // cmp r14b, byte [rdi + 30] + LONG $0x24549d0f; BYTE $0x10 // setge byte [rsp + 16] + LONG $0x1d773a44 // cmp r14b, byte [rdi + 29] + LONG $0x24549d0f; BYTE $0x28 // setge byte [rsp + 40] + LONG $0x1c773a44 // cmp r14b, byte [rdi + 28] + LONG $0x24549d0f; BYTE $0x20 // setge byte [rsp + 32] + LONG $0x1b773a44 // cmp r14b, byte [rdi + 27] + LONG $0x24549d0f; BYTE $0x18 // setge byte [rsp + 24] + LONG $0x1a773a44 // cmp r14b, byte [rdi + 26] + LONG $0x24549d0f; BYTE $0x30 // setge byte [rsp + 48] + LONG $0x19773a44 // cmp r14b, byte [rdi + 25] + LONG $0x24549d0f; BYTE $0x38 // setge byte [rsp + 56] + LONG $0x17773a44 // cmp r14b, byte [rdi + 23] + LONG $0x24549d0f; BYTE $0x40 // setge byte [rsp + 64] + LONG $0x16773a44 // cmp r14b, byte [rdi + 22] + LONG $0x24549d0f; BYTE $0x50 // setge byte [rsp + 80] + LONG $0x15773a44 // cmp r14b, byte [rdi + 21] + LONG $0x24549d0f; BYTE $0x48 // setge byte [rsp + 72] + LONG $0x14773a44 // cmp r14b, byte [rdi + 20] + LONG $0x24549d0f; BYTE $0x68 // setge byte [rsp + 104] + LONG $0x13773a44 // cmp r14b, byte [rdi + 19] + LONG $0x24549d0f; BYTE $0x60 // setge byte [rsp + 96] + LONG $0x12773a44 // cmp r14b, byte [rdi + 18] + LONG $0x24549d0f; BYTE $0x58 // setge byte [rsp + 88] + LONG $0x11773a44 // cmp r14b, byte [rdi + 17] + LONG $0x24549d0f; BYTE $0x70 // setge byte [rsp + 112] + LONG $0x0f773a44 // cmp r14b, byte [rdi + 15] + LONG $0xd29d0f41 // setge r10b + LONG $0x0e773a44 // cmp r14b, byte [rdi + 14] + QUAD $0x000000c024949d0f // setge byte [rsp + 192] + LONG $0x0d773a44 // cmp r14b, byte [rdi + 13] + QUAD $0x000000a024949d0f // setge byte [rsp + 160] + LONG $0x0c773a44 // cmp r14b, byte [rdi + 12] + LONG $0xd49d0f41 // setge r12b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x0b // cmp al, byte [rdi + 11] + LONG $0xd79d0f41 // setge r15b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x0a // cmp al, byte [rdi + 10] + LONG $0xd69d0f41 // setge r14b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x09 // cmp al, byte [rdi + 9] + LONG $0xd39d0f41 // setge r11b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x07 // cmp al, byte [rdi + 7] + WORD $0x9d0f; BYTE $0xd2 // setge dl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x06 // cmp al, byte [rdi + 6] + QUAD $0x000000d024949d0f // setge byte [rsp + 208] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x05 // cmp al, byte [rdi + 5] + LONG $0xd19d0f41 // setge r9b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x04 // cmp al, byte [rdi + 4] + LONG $0xd09d0f41 // setge r8b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x03 // cmp al, byte [rdi + 3] + LONG $0xd69d0f40 // setge sil + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x02 // cmp al, byte [rdi + 2] + WORD $0x9d0f; BYTE $0xd1 // setge cl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x073a // cmp al, byte [rdi] + QUAD $0x0000009024949d0f // setge byte [rsp + 144] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x473a; BYTE $0x01 // cmp al, byte [rdi + 1] + WORD $0x9d0f; BYTE $0xd0 // setge al + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + LONG $0x6cb60f44; WORD $0x0824 // movzx r13d, byte [rsp + 8] + LONG $0x086f3a44 // cmp r13b, byte [rdi + 8] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + QUAD $0x0000008024949d0f // setge byte [rsp + 128] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5f3a; BYTE $0x10 // cmp bl, byte [rdi + 16] + LONG $0x24549d0f; BYTE $0x78 // setge byte [rsp + 120] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + WORD $0x5f3a; BYTE $0x18 // cmp bl, byte [rdi + 24] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xc000 // add al, al + LONG $0x90248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 144] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + LONG $0x03e6c040 // shl sil, 3 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x04e0c041 // shl r8b, 4 + WORD $0x0841; BYTE $0xf0 // or r8b, sil + LONG $0x05e1c041 // shl r9b, 5 + WORD $0x0845; BYTE $0xc1 // or r9b, r8b + QUAD $0x000000d02484b60f // movzx eax, byte [rsp + 208] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xc208 // or dl, al + WORD $0x0844; BYTE $0xca // or dl, r9b + LONG $0x00558841 // mov byte [r13], dl + WORD $0x0045; BYTE $0xdb // add r11b, r11b + QUAD $0x00000080249c0244 // add r11b, byte [rsp + 128] + LONG $0x02e6c041 // shl r14b, 2 + WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x03e7c041 // shl r15b, 3 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x04e4c041 // shl r12b, 4 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + QUAD $0x000000a02484b60f // movzx eax, byte [rsp + 160] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0x0844; BYTE $0xe0 // or al, r12b + LONG $0x74b60f44; WORD $0x0824 // movzx r14d, byte [rsp + 8] + QUAD $0x000000c0248cb60f // movzx ecx, byte [rsp + 192] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e2c041 // shl r10b, 7 + WORD $0x0841; BYTE $0xca // or r10b, cl + WORD $0x0841; BYTE $0xc2 // or r10b, al + LONG $0x01558845 // mov byte [r13 + 1], r10b + LONG $0x2444b60f; BYTE $0x70 // movzx eax, byte [rsp + 112] + WORD $0xc000 // add al, al + LONG $0x78244402 // add al, byte [rsp + 120] + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x58 // movzx eax, byte [rsp + 88] + WORD $0xe0c0; BYTE $0x02 // shl al, 2 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x60 // movzx eax, byte [rsp + 96] + WORD $0xe0c0; BYTE $0x03 // shl al, 3 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x68 // movzx eax, byte [rsp + 104] + WORD $0xe0c0; BYTE $0x04 // shl al, 4 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x48 // movzx eax, byte [rsp + 72] + WORD $0xe0c0; BYTE $0x05 // shl al, 5 + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] - WORD $0xe2c0; BYTE $0x04 // shl dl, 4 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0xd689 // mov esi, edx - LONG $0x2454b60f; BYTE $0x48 // movzx edx, byte [rsp + 72] - WORD $0xe2c0; BYTE $0x05 // shl dl, 5 - WORD $0x0840; BYTE $0xf2 // or dl, sil - WORD $0x8845; BYTE $0x1e // mov byte [r14], r11b - LONG $0x2474b60f; BYTE $0x30 // movzx esi, byte [rsp + 48] - LONG $0x06e6c040 // shl sil, 6 - LONG $0x07e7c041 // shl r15b, 7 - WORD $0x0841; BYTE $0xf7 // or r15b, sil - LONG $0x017e8841 // mov byte [r14 + 1], dil - WORD $0x0841; BYTE $0xd7 // or r15b, dl + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + LONG $0x2444b60f; BYTE $0x40 // movzx eax, byte [rsp + 64] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd008 // or al, dl + WORD $0xc808 // or al, cl + LONG $0x02458841 // mov byte [r13 + 2], al LONG $0x2444b60f; BYTE $0x38 // movzx eax, byte [rsp + 56] WORD $0xc000 // add al, al - LONG $0x18244402 // add al, byte [rsp + 24] - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] + WORD $0xd808 // or al, bl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x30 // movzx eax, byte [rsp + 48] WORD $0xe0c0; BYTE $0x02 // shl al, 2 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x18 // movzx eax, byte [rsp + 24] WORD $0xe0c0; BYTE $0x03 // shl al, 3 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x20 // movzx eax, byte [rsp + 32] WORD $0xe0c0; BYTE $0x04 // shl al, 4 - WORD $0xd008 // or al, dl - WORD $0xc289 // mov edx, eax - LONG $0x2444b60f; BYTE $0x10 // movzx eax, byte [rsp + 16] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2444b60f; BYTE $0x28 // movzx eax, byte [rsp + 40] WORD $0xe0c0; BYTE $0x05 // shl al, 5 - WORD $0xd008 // or al, dl - LONG $0x2454b60f; BYTE $0x78 // movzx edx, byte [rsp + 120] + WORD $0xc808 // or al, cl + WORD $0xc189 // mov ecx, eax + LONG $0x2454b60f; BYTE $0x10 // movzx edx, byte [rsp + 16] WORD $0xe2c0; BYTE $0x06 // shl dl, 6 - WORD $0xe1c0; BYTE $0x07 // shl cl, 7 - WORD $0xd108 // or cl, dl - WORD $0xc108 // or cl, al - LONG $0x027e8845 // mov byte [r14 + 2], r15b - LONG $0x034e8841 // mov byte [r14 + 3], cl - LONG $0x80c38148; WORD $0x0000; BYTE $0x00 // add rbx, 128 - LONG $0x04c68349 // add r14, 4 - QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 - JNE LBB11_186 - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] - JMP LBB11_188 + QUAD $0x000000882484b60f // movzx eax, byte [rsp + 136] + WORD $0xe0c0; BYTE $0x07 // shl al, 7 + WORD $0xd008 // or al, dl + WORD $0xc808 // or al, cl + LONG $0x03458841 // mov byte [r13 + 3], al + LONG $0x20c78348 // add rdi, 32 + LONG $0x04c58349 // add r13, 4 + QUAD $0x000000f024848348; BYTE $0xff // add qword [rsp + 240], -1 + JNE LBB11_147 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x00000110248c8b48 // mov rcx, qword [rsp + 272] + JMP LBB11_150 -LBB11_9: - WORD $0x894d; BYTE $0xfd // mov r13, r15 - -LBB11_91: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_94 - WORD $0xf631 // xor esi, esi - JMP LBB11_97 +LBB11_149: + WORD $0x894c; BYTE $0xef // mov rdi, r13 + WORD $0x894d; BYTE $0xe5 // mov r13, r12 -LBB11_61: - WORD $0x894d; BYTE $0xfd // mov r13, r15 - -LBB11_72: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_75 +LBB11_150: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB11_215 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB11_175 WORD $0x3145; BYTE $0xc9 // xor r9d, r9d - JMP LBB11_78 + JMP LBB11_178 -LBB11_119: - WORD $0x894d; BYTE $0xfc // mov r12, r15 - WORD $0x8948; BYTE $0xd0 // mov rax, rdx +LBB11_153: + WORD $0x8949; BYTE $0xd3 // mov r11, rdx + WORD $0x294d; BYTE $0xc7 // sub r15, r8 + JE LBB11_215 -LBB11_130: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_135 - WORD $0xf631 // xor esi, esi - JMP LBB11_133 +LBB11_154: + LONG $0x01c48349 // add r12, 1 -LBB11_177: - WORD $0x894d; BYTE $0xfe // mov r14, r15 - WORD $0x8948; BYTE $0xd3 // mov rbx, rdx +LBB11_155: + LONG $0x1f4f8d49 // lea rcx, [r15 + 31] + WORD $0x854d; BYTE $0xff // test r15, r15 + LONG $0xcf490f49 // cmovns rcx, r15 + LONG $0x05f9c148 // sar rcx, 5 + LONG $0x20ff8349 // cmp r15, 32 + JL LBB11_163 + LONG $0x10f98348 // cmp rcx, 16 + LONG $0x246c8844; BYTE $0x08 // mov byte [rsp + 8], r13b + QUAD $0x0000009824bc894c // mov qword [rsp + 152], r15 + QUAD $0x00000100248c8948 // mov qword [rsp + 256], rcx + JB LBB11_159 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x05e0c148 // shl rax, 5 + WORD $0x014c; BYTE $0xd8 // add rax, r11 + WORD $0x3949; BYTE $0xc4 // cmp r12, rax + JAE LBB11_225 + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + WORD $0x3949; BYTE $0xc3 // cmp r11, rax + JAE LBB11_225 -LBB11_188: - LONG $0x05e2c149 // shl r10, 5 - WORD $0x394d; BYTE $0xda // cmp r10, r11 - JGE LBB11_201 - WORD $0x894d; BYTE $0xd8 // mov r8, r11 - WORD $0x294d; BYTE $0xd0 // sub r8, r10 - WORD $0xf749; BYTE $0xd2 // not r10 - WORD $0x014d; BYTE $0xda // add r10, r11 - JNE LBB11_193 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d - JMP LBB11_191 +LBB11_159: + WORD $0xc031 // xor eax, eax + QUAD $0x000000b824848948 // mov qword [rsp + 184], rax + WORD $0x894c; BYTE $0xdb // mov rbx, r11 + LONG $0x2464894c; BYTE $0x70 // mov qword [rsp + 112], r12 -LBB11_155: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d +LBB11_160: + QUAD $0x000000b8248c2b48 // sub rcx, qword [rsp + 184] + QUAD $0x000000e0248c8948 // mov qword [rsp + 224], rcx + +LBB11_161: + LONG $0x1f6b3a44 // cmp r13b, byte [rbx + 31] + QUAD $0x000000882494930f // setae byte [rsp + 136] + LONG $0x1e6b3a44 // cmp r13b, byte [rbx + 30] + LONG $0x2454930f; BYTE $0x10 // setae byte [rsp + 16] + LONG $0x1d6b3a44 // cmp r13b, byte [rbx + 29] + LONG $0x2454930f; BYTE $0x28 // setae byte [rsp + 40] + LONG $0x1c6b3a44 // cmp r13b, byte [rbx + 28] + LONG $0x2454930f; BYTE $0x20 // setae byte [rsp + 32] + LONG $0x1b6b3a44 // cmp r13b, byte [rbx + 27] + LONG $0x2454930f; BYTE $0x18 // setae byte [rsp + 24] + LONG $0x1a6b3a44 // cmp r13b, byte [rbx + 26] + LONG $0x2454930f; BYTE $0x30 // setae byte [rsp + 48] + LONG $0x196b3a44 // cmp r13b, byte [rbx + 25] + LONG $0x2454930f; BYTE $0x38 // setae byte [rsp + 56] + LONG $0x176b3a44 // cmp r13b, byte [rbx + 23] + LONG $0x2454930f; BYTE $0x40 // setae byte [rsp + 64] + LONG $0x166b3a44 // cmp r13b, byte [rbx + 22] + LONG $0x2454930f; BYTE $0x50 // setae byte [rsp + 80] + LONG $0x156b3a44 // cmp r13b, byte [rbx + 21] + LONG $0x2454930f; BYTE $0x48 // setae byte [rsp + 72] + LONG $0x146b3a44 // cmp r13b, byte [rbx + 20] + LONG $0x2454930f; BYTE $0x68 // setae byte [rsp + 104] + LONG $0x136b3a44 // cmp r13b, byte [rbx + 19] + LONG $0x2454930f; BYTE $0x60 // setae byte [rsp + 96] + LONG $0x126b3a44 // cmp r13b, byte [rbx + 18] + LONG $0x2454930f; BYTE $0x58 // setae byte [rsp + 88] + LONG $0x116b3a44 // cmp r13b, byte [rbx + 17] + QUAD $0x000000a02494930f // setae byte [rsp + 160] + LONG $0x0f6b3a44 // cmp r13b, byte [rbx + 15] + LONG $0xd1930f41 // setae r9b + LONG $0x0e6b3a44 // cmp r13b, byte [rbx + 14] + LONG $0x2454930f; BYTE $0x78 // setae byte [rsp + 120] + LONG $0x0d6b3a44 // cmp r13b, byte [rbx + 13] + LONG $0xd4930f41 // setae r12b + LONG $0x0c6b3a44 // cmp r13b, byte [rbx + 12] + LONG $0xd7930f41 // setae r15b + LONG $0x0b6b3a44 // cmp r13b, byte [rbx + 11] + LONG $0xd6930f41 // setae r14b + LONG $0x0a6b3a44 // cmp r13b, byte [rbx + 10] + LONG $0xd3930f41 // setae r11b + LONG $0x096b3a44 // cmp r13b, byte [rbx + 9] + LONG $0xd2930f41 // setae r10b + LONG $0x076b3a44 // cmp r13b, byte [rbx + 7] + WORD $0x930f; BYTE $0xd2 // setae dl + LONG $0x066b3a44 // cmp r13b, byte [rbx + 6] + QUAD $0x000000802494930f // setae byte [rsp + 128] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x433a; BYTE $0x05 // cmp al, byte [rbx + 5] + LONG $0xd0930f41 // setae r8b + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x433a; BYTE $0x04 // cmp al, byte [rbx + 4] + LONG $0xd7930f40 // setae dil + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x433a; BYTE $0x03 // cmp al, byte [rbx + 3] + LONG $0xd6930f40 // setae sil + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x433a; BYTE $0x02 // cmp al, byte [rbx + 2] + WORD $0x930f; BYTE $0xd1 // setae cl + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x033a // cmp al, byte [rbx] + QUAD $0x000000f02494930f // setae byte [rsp + 240] + LONG $0x2444b60f; BYTE $0x08 // movzx eax, byte [rsp + 8] + WORD $0x433a; BYTE $0x01 // cmp al, byte [rbx + 1] + WORD $0x930f; BYTE $0xd0 // setae al + LONG $0x6cb60f44; WORD $0x0824 // movzx r13d, byte [rsp + 8] + LONG $0x086b3a44 // cmp r13b, byte [rbx + 8] + QUAD $0x000000902494930f // setae byte [rsp + 144] + WORD $0x8949; BYTE $0xdd // mov r13, rbx + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x105d3a41 // cmp bl, byte [r13 + 16] + QUAD $0x000000d02494930f // setae byte [rsp + 208] + LONG $0x245cb60f; BYTE $0x08 // movzx ebx, byte [rsp + 8] + LONG $0x185d3a41 // cmp bl, byte [r13 + 24] + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x000000c02494930f // setae byte [rsp + 192] + WORD $0xc000 // add al, al + LONG $0xf0248402; WORD $0x0000; BYTE $0x00 // add al, byte [rsp + 240] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xc108 // or cl, al + LONG $0x03e6c040 // shl sil, 3 + WORD $0x0840; BYTE $0xce // or sil, cl + LONG $0x04e7c040 // shl dil, 4 + WORD $0x0840; BYTE $0xf7 // or dil, sil + LONG $0x05e0c041 // shl r8b, 5 + WORD $0x0841; BYTE $0xf8 // or r8b, dil + QUAD $0x000000802484b60f // movzx eax, byte [rsp + 128] + WORD $0xe0c0; BYTE $0x06 // shl al, 6 + WORD $0xe2c0; BYTE $0x07 // shl dl, 7 + WORD $0xc208 // or dl, al + LONG $0x6cb60f44; WORD $0x0824 // movzx r13d, byte [rsp + 8] + WORD $0x0844; BYTE $0xc2 // or dl, r8b + LONG $0x24448b48; BYTE $0x70 // mov rax, qword [rsp + 112] + WORD $0x1088 // mov byte [rax], dl + WORD $0x0045; BYTE $0xd2 // add r10b, r10b + QUAD $0x0000009024940244 // add r10b, byte [rsp + 144] + LONG $0x02e3c041 // shl r11b, 2 + WORD $0x0845; BYTE $0xd3 // or r11b, r10b + LONG $0x03e6c041 // shl r14b, 3 + WORD $0x0845; BYTE $0xde // or r14b, r11b + LONG $0x04e7c041 // shl r15b, 4 + WORD $0x0845; BYTE $0xf7 // or r15b, r14b + LONG $0x05e4c041 // shl r12b, 5 + WORD $0x0845; BYTE $0xfc // or r12b, r15b + LONG $0x244cb60f; BYTE $0x78 // movzx ecx, byte [rsp + 120] + WORD $0xe1c0; BYTE $0x06 // shl cl, 6 + LONG $0x07e1c041 // shl r9b, 7 + WORD $0x0841; BYTE $0xc9 // or r9b, cl + WORD $0x0845; BYTE $0xe1 // or r9b, r12b + LONG $0x01488844 // mov byte [rax + 1], r9b + QUAD $0x000000a0248cb60f // movzx ecx, byte [rsp + 160] + WORD $0xc900 // add cl, cl + LONG $0xd0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 208] + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x58 // movzx ecx, byte [rsp + 88] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x60 // movzx ecx, byte [rsp + 96] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x68 // movzx ecx, byte [rsp + 104] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x48 // movzx ecx, byte [rsp + 72] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd108 // or cl, dl + WORD $0xce89 // mov esi, ecx + LONG $0x2454b60f; BYTE $0x50 // movzx edx, byte [rsp + 80] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + LONG $0x244cb60f; BYTE $0x40 // movzx ecx, byte [rsp + 64] + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0x4888; BYTE $0x02 // mov byte [rax + 2], cl + LONG $0x244cb60f; BYTE $0x38 // movzx ecx, byte [rsp + 56] + WORD $0xc900 // add cl, cl + LONG $0xc0248c02; WORD $0x0000; BYTE $0x00 // add cl, byte [rsp + 192] + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x30 // movzx ecx, byte [rsp + 48] + WORD $0xe1c0; BYTE $0x02 // shl cl, 2 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x18 // movzx ecx, byte [rsp + 24] + WORD $0xe1c0; BYTE $0x03 // shl cl, 3 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x20 // movzx ecx, byte [rsp + 32] + WORD $0xe1c0; BYTE $0x04 // shl cl, 4 + WORD $0xd108 // or cl, dl + WORD $0xca89 // mov edx, ecx + LONG $0x244cb60f; BYTE $0x28 // movzx ecx, byte [rsp + 40] + WORD $0xe1c0; BYTE $0x05 // shl cl, 5 + WORD $0xd108 // or cl, dl + WORD $0xce89 // mov esi, ecx + LONG $0x2454b60f; BYTE $0x10 // movzx edx, byte [rsp + 16] + WORD $0xe2c0; BYTE $0x06 // shl dl, 6 + QUAD $0x00000088248cb60f // movzx ecx, byte [rsp + 136] + WORD $0xe1c0; BYTE $0x07 // shl cl, 7 + WORD $0xd108 // or cl, dl + WORD $0x0840; BYTE $0xf1 // or cl, sil + WORD $0x4888; BYTE $0x03 // mov byte [rax + 3], cl + LONG $0x20c38348 // add rbx, 32 + LONG $0x04c08348 // add rax, 4 + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + QUAD $0x000000e024848348; BYTE $0xff // add qword [rsp + 224], -1 + JNE LBB11_161 + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + JMP LBB11_164 -LBB11_156: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] +LBB11_163: + LONG $0x2464894c; BYTE $0x70 // mov qword [rsp + 112], r12 + WORD $0x894c; BYTE $0xdb // mov rbx, r11 + +LBB11_164: + LONG $0x05e1c148 // shl rcx, 5 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + WORD $0x2949; BYTE $0xc8 // sub r8, rcx + JLE LBB11_215 + LONG $0x01c98348 // or rcx, 1 + WORD $0x3949; BYTE $0xcf // cmp r15, rcx + JNE LBB11_180 + WORD $0xf631 // xor esi, esi + JMP LBB11_183 + +LBB11_167: + WORD $0x894d; BYTE $0xca // mov r10, r9 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + +LBB11_168: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xde // mov rsi, r11 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x1cb60f45; BYTE $0x34 // movzx r11d, byte [r12 + rsi] + WORD $0x3044; BYTE $0xdf // xor dil, r11b + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + WORD $0x3044; BYTE $0xd8 // xor al, r11b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x02c68349 // add r14, 2 + LONG $0x08423b4c // cmp r8, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 @@ -56537,189 +58297,190 @@ LBB11_156: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB11_156 + LONG $0x341c8841 // mov byte [r12 + rsi], bl + WORD $0x394d; BYTE $0xf2 // cmp r10, r14 + JNE LBB11_168 -LBB11_40: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 +LBB11_169: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_215 WORD $0xc031 // xor eax, eax - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] - JMP LBB11_199 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] + JMP LBB11_197 -LBB11_153: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB11_171: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB11_154: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] +LBB11_172: + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x371c8841 // mov byte [r15 + rsi], bl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] LONG $0x08528d48 // lea rdx, [rdx + 8] - LONG $0xd19d0f41 // setge r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd29d0f41 // setge r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl - LONG $0x37048841 // mov byte [r15 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB11_154 + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB11_172 -LBB11_150: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - JMP LBB11_152 +LBB11_173: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_215 + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + JMP LBB11_203 -LBB11_94: +LBB11_175: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 - WORD $0xf631 // xor esi, esi + WORD $0x3145; BYTE $0xc9 // xor r9d, r9d -LBB11_95: - LONG $0x32343a44 // cmp r14b, byte [rdx + rsi] - WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - WORD $0xf189 // mov ecx, esi +LBB11_176: + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + LONG $0x0f343a46 // cmp r14b, byte [rdi + r9] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + WORD $0x894c; BYTE $0xce // mov rsi, r9 + LONG $0x03eec148 // shr rsi, 3 + WORD $0xc189 // mov ecx, eax WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] - WORD $0x3044; BYTE $0xc8 // xor al, r9b - WORD $0xc320 // and bl, al + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + LONG $0x4cb60f45; WORD $0x0035 // movzx r9d, byte [r13 + rsi] WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl - LONG $0x32743a44; BYTE $0x01 // cmp r14b, byte [rdx + rsi + 1] - LONG $0x02768d48 // lea rsi, [rsi + 2] - LONG $0xd19d0f41 // setge r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x35548841; BYTE $0x00 // mov byte [r13 + rsi], dl + LONG $0x07743a44; BYTE $0x01 // cmp r14b, byte [rdi + rax + 1] + LONG $0x02488d4c // lea r9, [rax + 2] + WORD $0x9d0f; BYTE $0xd3 // setge bl + WORD $0xdbf6 // neg bl + WORD $0xd330 // xor bl, dl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b - WORD $0xd830 // xor al, bl - LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al - WORD $0x3949; BYTE $0xf2 // cmp r10, rsi - JNE LBB11_95 - WORD $0x0148; BYTE $0xf2 // add rdx, rsi + WORD $0xd820 // and al, bl + WORD $0xd030 // xor al, dl + LONG $0x35448841; BYTE $0x00 // mov byte [r13 + rsi], al + WORD $0x394d; BYTE $0xca // cmp r10, r9 + JNE LBB11_176 + WORD $0x014c; BYTE $0xcf // add rdi, r9 -LBB11_97: +LBB11_178: LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 - WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + JE LBB11_215 + WORD $0x3a44; BYTE $0x37 // cmp r14b, byte [rdi] WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + WORD $0x894c; BYTE $0xca // mov rdx, r9 LONG $0x03eac148 // shr rdx, 3 LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] - LONG $0x07e68040 // and sil, 7 + LONG $0x07e18041 // and r9b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf8 // xor al, dil - WORD $0xc320 // and bl, al - JMP LBB11_80 + WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + JMP LBB11_209 -LBB11_75: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 - WORD $0x3145; BYTE $0xc9 // xor r9d, r9d +LBB11_180: + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + LONG $0xfee28349 // and r10, -2 + WORD $0xf631 // xor esi, esi + LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] -LBB11_76: - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - LONG $0x0a343a46 // cmp r14b, byte [rdx + r9] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - LONG $0x03efc148 // shr rdi, 3 - LONG $0x4cb60f45; WORD $0x003d // movzx r9d, byte [r13 + rdi] - WORD $0xc189 // mov ecx, eax - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xce // xor sil, r9b - WORD $0x2040; BYTE $0xf3 // and bl, sil - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl - LONG $0x02743a44; BYTE $0x01 // cmp r14b, byte [rdx + rax + 1] - LONG $0x02488d4c // lea r9, [rax + 2] - LONG $0x000000be; BYTE $0x00 // mov esi, 0 - LONG $0xffd68040 // adc sil, -1 - WORD $0x3040; BYTE $0xde // xor sil, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b0 // mov al, 1 - WORD $0xe0d2 // shl al, cl - WORD $0x2040; BYTE $0xf0 // and al, sil - WORD $0xd830 // xor al, bl - LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al - WORD $0x394d; BYTE $0xca // cmp r10, r9 - JNE LBB11_76 - WORD $0x014c; BYTE $0xca // add rdx, r9 +LBB11_181: + LONG $0x332c3a44 // cmp r13b, byte [rbx + rsi] + WORD $0x8949; BYTE $0xdf // mov r15, rbx + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x03efc148 // shr rdi, 3 + LONG $0x0cb60f45; BYTE $0x3b // movzx r9d, byte [r11 + rdi] + WORD $0xf189 // mov ecx, esi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b2 // mov dl, 1 + WORD $0xe2d2 // shl dl, cl + WORD $0x3044; BYTE $0xcb // xor bl, r9b + WORD $0xda20 // and dl, bl + WORD $0x3044; BYTE $0xca // xor dl, r9b + LONG $0x3b148841 // mov byte [r11 + rdi], dl + LONG $0x376c3a45; BYTE $0x01 // cmp r13b, byte [r15 + rsi + 1] + LONG $0x02768d48 // lea rsi, [rsi + 2] + LONG $0x000000bb; BYTE $0x00 // mov ebx, 0 + WORD $0xd380; BYTE $0xff // adc bl, -1 + WORD $0xd330 // xor bl, dl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0xd820 // and al, bl + WORD $0x894c; BYTE $0xfb // mov rbx, r15 + WORD $0xd030 // xor al, dl + LONG $0x3b048841 // mov byte [r11 + rdi], al + WORD $0x3949; BYTE $0xf2 // cmp r10, rsi + JNE LBB11_181 + WORD $0x0148; BYTE $0xf3 // add rbx, rsi -LBB11_78: +LBB11_183: LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 + JE LBB11_215 WORD $0xc031 // xor eax, eax - WORD $0x3a44; BYTE $0x32 // cmp r14b, byte [rdx] + WORD $0x3a44; BYTE $0x2b // cmp r13b, byte [rbx] WORD $0xff14 // adc al, -1 - WORD $0x894c; BYTE $0xca // mov rdx, r9 + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi LONG $0x03eac148 // shr rdx, 3 - LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] - LONG $0x07e18041 // and r9b, 7 + LONG $0x24748b4c; BYTE $0x70 // mov r14, qword [rsp + 112] + LONG $0x163c8a41 // mov dil, byte [r14 + rdx] + LONG $0x07e68040 // and sil, 7 WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xc9 // mov ecx, r9d + WORD $0xf189 // mov ecx, esi WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al - -LBB11_80: WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x155c8841; BYTE $0x00 // mov byte [r13 + rdx], bl - JMP LBB11_201 + LONG $0x161c8841 // mov byte [r14 + rdx], bl + JMP LBB11_215 -LBB11_137: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d +LBB11_185: + WORD $0x894d; BYTE $0xca // mov r10, r9 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB11_138: - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] +LBB11_186: + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xde // mov rsi, r11 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x1cb60f45; BYTE $0x34 // movzx r11d, byte [r12 + rsi] + WORD $0x3044; BYTE $0xdf // xor dil, r11b + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x04723b44 // cmp r14d, dword [rdx + 4] + WORD $0x3044; BYTE $0xd8 // xor al, r11b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x02c68349 // add r14, 2 + LONG $0x04423b44 // cmp r8d, dword [rdx + 4] LONG $0x08528d48 // lea rdx, [rdx + 8] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 @@ -56729,29 +58490,30 @@ LBB11_138: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB11_138 + LONG $0x341c8841 // mov byte [r12 + rsi], bl + WORD $0x394d; BYTE $0xf2 // cmp r10, r14 + JNE LBB11_186 -LBB11_24: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 +LBB11_187: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_215 WORD $0xc031 // xor eax, eax - WORD $0x3b44; BYTE $0x32 // cmp r14d, dword [rdx] - JMP LBB11_199 + WORD $0x3b44; BYTE $0x02 // cmp r8d, dword [rdx] + JMP LBB11_197 -LBB11_195: +LBB11_189: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d -LBB11_196: +LBB11_190: LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] LONG $0x000000b8; BYTE $0x00 // mov eax, 0 WORD $0xff14 // adc al, -1 WORD $0x894c; BYTE $0xde // mov rsi, r11 LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x0cb60f45; BYTE $0x34 // movzx r9d, byte [r12 + rsi] WORD $0x8944; BYTE $0xd9 // mov ecx, r11d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 @@ -56759,7 +58521,7 @@ LBB11_196: WORD $0x3044; BYTE $0xc8 // xor al, r9b WORD $0xc320 // and bl, al WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x371c8841 // mov byte [r15 + rsi], bl + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c38349 // add r11, 2 LONG $0x422e0f66; BYTE $0x08 // ucomisd xmm0, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] @@ -56771,39 +58533,47 @@ LBB11_196: WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil WORD $0xd830 // xor al, bl - LONG $0x37048841 // mov byte [r15 + rsi], al + LONG $0x34048841 // mov byte [r12 + rsi], al WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB11_196 + JNE LBB11_190 -LBB11_197: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 - WORD $0xc031 // xor eax, eax - LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] - JMP LBB11_199 +LBB11_191: + LONG $0x01c0f641 // test r8b, 1 + JE LBB11_215 + WORD $0xc031 // xor eax, eax + LONG $0x022e0f66 // ucomisd xmm0, qword [rdx] + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x14348a41 // mov sil, byte [r12 + rdx] + LONG $0x07e38041 // and r11b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + JMP LBB11_198 -LBB11_112: - WORD $0x894d; BYTE $0xc1 // mov r9, r8 - LONG $0xfee18349 // and r9, -2 - WORD $0x3145; BYTE $0xdb // xor r11d, r11d +LBB11_193: + WORD $0x894d; BYTE $0xca // mov r10, r9 + LONG $0xfee28349 // and r10, -2 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d -LBB11_113: - LONG $0x323b4466 // cmp r14w, word [rdx] +LBB11_194: + LONG $0x023b4466 // cmp r8w, word [rdx] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 - WORD $0x894c; BYTE $0xde // mov rsi, r11 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 LONG $0x03eec148 // shr rsi, 3 - LONG $0x14b60f45; BYTE $0x37 // movzx r10d, byte [r15 + rsi] - WORD $0x3044; BYTE $0xd7 // xor dil, r10b - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + LONG $0x1cb60f45; BYTE $0x34 // movzx r11d, byte [r12 + rsi] + WORD $0x3044; BYTE $0xdf // xor dil, r11b + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl WORD $0x2040; BYTE $0xf8 // and al, dil - WORD $0x3044; BYTE $0xd0 // xor al, r10b - LONG $0x37048841 // mov byte [r15 + rsi], al - LONG $0x02c38349 // add r11, 2 - LONG $0x723b4466; BYTE $0x02 // cmp r14w, word [rdx + 2] + WORD $0x3044; BYTE $0xd8 // xor al, r11b + LONG $0x34048841 // mov byte [r12 + rsi], al + LONG $0x02c68349 // add r14, 2 + LONG $0x423b4466; BYTE $0x02 // cmp r8w, word [rdx + 2] LONG $0x04528d48 // lea rdx, [rdx + 4] LONG $0x000000bf; BYTE $0x00 // mov edi, 0 LONG $0xffd78040 // adc dil, -1 @@ -56813,75 +58583,78 @@ LBB11_113: WORD $0xe3d2 // shl bl, cl WORD $0x2040; BYTE $0xfb // and bl, dil WORD $0xc330 // xor bl, al - LONG $0x371c8841 // mov byte [r15 + rsi], bl - WORD $0x394d; BYTE $0xd9 // cmp r9, r11 - JNE LBB11_113 + LONG $0x341c8841 // mov byte [r12 + rsi], bl + WORD $0x394d; BYTE $0xf2 // cmp r10, r14 + JNE LBB11_194 -LBB11_110: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 +LBB11_195: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_215 WORD $0xc031 // xor eax, eax - LONG $0x323b4466 // cmp r14w, word [rdx] + LONG $0x023b4466 // cmp r8w, word [rdx] -LBB11_199: +LBB11_197: WORD $0xff14 // adc al, -1 - WORD $0x894c; BYTE $0xda // mov rdx, r11 + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 LONG $0x03eac148 // shr rdx, 3 - LONG $0x17348a41 // mov sil, byte [r15 + rdx] - LONG $0x07e38041 // and r11b, 7 + LONG $0x14348a41 // mov sil, byte [r12 + rdx] + LONG $0x07e68041 // and r14b, 7 WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0x8944; BYTE $0xf1 // mov ecx, r14d + +LBB11_198: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al - JMP LBB11_200 + JMP LBB11_204 -LBB11_170: - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0xfee28349 // and r10, -2 +LBB11_199: + WORD $0x894d; BYTE $0xcb // mov r11, r9 + LONG $0xfee38349 // and r11, -2 WORD $0xff31 // xor edi, edi -LBB11_171: - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] +LBB11_200: + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfe // mov rsi, rdi LONG $0x03eec148 // shr rsi, 3 - LONG $0x0cb60f45; BYTE $0x37 // movzx r9d, byte [r15 + rsi] + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + LONG $0x14b60f45; BYTE $0x34 // movzx r10d, byte [r12 + rsi] WORD $0xf989 // mov ecx, edi WORD $0xe180; BYTE $0x06 // and cl, 6 WORD $0x01b3 // mov bl, 1 WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xc8 // xor al, r9b + WORD $0x3044; BYTE $0xd0 // xor al, r10b WORD $0xc320 // and bl, al - WORD $0x3044; BYTE $0xcb // xor bl, r9b - LONG $0x371c8841 // mov byte [r15 + rsi], bl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x341c8841 // mov byte [r12 + rsi], bl LONG $0x02c78348 // add rdi, 2 - LONG $0x08723b4c // cmp r14, qword [rdx + 8] + LONG $0x08423b4c // cmp r8, qword [rdx + 8] LONG $0x10528d48 // lea rdx, [rdx + 16] - LONG $0xd19d0f41 // setge r9b - WORD $0xf641; BYTE $0xd9 // neg r9b - WORD $0x3041; BYTE $0xd9 // xor r9b, bl + LONG $0xd29d0f41 // setge r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl WORD $0xc980; BYTE $0x01 // or cl, 1 WORD $0x01b0 // mov al, 1 WORD $0xe0d2 // shl al, cl - WORD $0x2044; BYTE $0xc8 // and al, r9b + WORD $0x2044; BYTE $0xd0 // and al, r10b WORD $0xd830 // xor al, bl - LONG $0x37048841 // mov byte [r15 + rsi], al - WORD $0x3949; BYTE $0xfa // cmp r10, rdi - JNE LBB11_171 + LONG $0x34048841 // mov byte [r12 + rsi], al + WORD $0x3949; BYTE $0xfb // cmp r11, rdi + JNE LBB11_200 -LBB11_168: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 - WORD $0x3b4c; BYTE $0x32 // cmp r14, qword [rdx] +LBB11_201: + LONG $0x01c1f641 // test r9b, 1 + JE LBB11_215 + WORD $0x3b4c; BYTE $0x02 // cmp r8, qword [rdx] -LBB11_152: +LBB11_203: WORD $0x9d0f; BYTE $0xd0 // setge al WORD $0xd8f6 // neg al WORD $0x8948; BYTE $0xfa // mov rdx, rdi LONG $0x03eac148 // shr rdx, 3 - LONG $0x17348a41 // mov sil, byte [r15 + rdx] + LONG $0x14348a41 // mov sil, byte [r12 + rdx] LONG $0x07e78040 // and dil, 7 WORD $0x01b3 // mov bl, 1 WORD $0xf989 // mov ecx, edi @@ -56889,74 +58662,74 @@ LBB11_152: WORD $0x3040; BYTE $0xf0 // xor al, sil WORD $0xc320 // and bl, al -LBB11_200: +LBB11_204: WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x171c8841 // mov byte [r15 + rdx], bl - -LBB11_201: - MOVQ 304(SP), SP - RET + LONG $0x141c8841 // mov byte [r12 + rdx], bl + JMP LBB11_215 -LBB11_135: +LBB11_205: WORD $0x894d; BYTE $0xc1 // mov r9, r8 LONG $0xfee18349 // and r9, -2 WORD $0xf631 // xor esi, esi -LBB11_136: - LONG $0x303b4466 // cmp r14w, word [rax] - WORD $0x9d0f; BYTE $0xd2 // setge dl - WORD $0xdaf6 // neg dl - WORD $0x8948; BYTE $0xf7 // mov rdi, rsi - LONG $0x03efc148 // shr rdi, 3 - LONG $0x14b60f45; BYTE $0x3c // movzx r10d, byte [r12 + rdi] - WORD $0xf189 // mov ecx, esi - WORD $0xe180; BYTE $0x06 // and cl, 6 - WORD $0x01b3 // mov bl, 1 - WORD $0xe3d2 // shl bl, cl - WORD $0x3044; BYTE $0xd2 // xor dl, r10b - WORD $0xd320 // and bl, dl - WORD $0x3044; BYTE $0xd3 // xor bl, r10b - LONG $0x3c1c8841 // mov byte [r12 + rdi], bl - LONG $0x02c68348 // add rsi, 2 - LONG $0x703b4466; BYTE $0x02 // cmp r14w, word [rax + 2] - LONG $0x04408d48 // lea rax, [rax + 4] - LONG $0xd29d0f41 // setge r10b - WORD $0xf641; BYTE $0xda // neg r10b - WORD $0x3041; BYTE $0xda // xor r10b, bl - WORD $0xc980; BYTE $0x01 // or cl, 1 - WORD $0x01b2 // mov dl, 1 - WORD $0xe2d2 // shl dl, cl - WORD $0x2044; BYTE $0xd2 // and dl, r10b - WORD $0xda30 // xor dl, bl - LONG $0x3c148841 // mov byte [r12 + rdi], dl - WORD $0x3949; BYTE $0xf1 // cmp r9, rsi - JNE LBB11_136 +LBB11_206: + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + LONG $0x323b4466 // cmp r14w, word [rdx] + WORD $0x9d0f; BYTE $0xd2 // setge dl + WORD $0xdaf6 // neg dl + WORD $0x8948; BYTE $0xf7 // mov rdi, rsi + LONG $0x03efc148 // shr rdi, 3 + LONG $0x54b60f45; WORD $0x003d // movzx r10d, byte [r13 + rdi] + WORD $0xf189 // mov ecx, esi + WORD $0xe180; BYTE $0x06 // and cl, 6 + WORD $0x01b3 // mov bl, 1 + WORD $0xe3d2 // shl bl, cl + WORD $0x3044; BYTE $0xd2 // xor dl, r10b + WORD $0xd320 // and bl, dl + WORD $0x3044; BYTE $0xd3 // xor bl, r10b + LONG $0x3d5c8841; BYTE $0x00 // mov byte [r13 + rdi], bl + LONG $0x02c68348 // add rsi, 2 + LONG $0x703b4466; BYTE $0x02 // cmp r14w, word [rax + 2] + LONG $0x04508d48 // lea rdx, [rax + 4] + LONG $0xd29d0f41 // setge r10b + WORD $0xf641; BYTE $0xda // neg r10b + WORD $0x3041; BYTE $0xda // xor r10b, bl + WORD $0xc980; BYTE $0x01 // or cl, 1 + WORD $0x01b0 // mov al, 1 + WORD $0xe0d2 // shl al, cl + WORD $0x2044; BYTE $0xd0 // and al, r10b + WORD $0xd830 // xor al, bl + LONG $0x3d448841; BYTE $0x00 // mov byte [r13 + rdi], al + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB11_206 + +LBB11_207: + LONG $0x01c0f641 // test r8b, 1 + JE LBB11_215 + LONG $0x323b4466 // cmp r14w, word [rdx] + WORD $0x9d0f; BYTE $0xd0 // setge al + WORD $0xd8f6 // neg al + WORD $0x8948; BYTE $0xf2 // mov rdx, rsi + LONG $0x03eac148 // shr rdx, 3 + LONG $0x157c8a41; BYTE $0x00 // mov dil, byte [r13 + rdx] + LONG $0x07e68040 // and sil, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0xf189 // mov ecx, esi -LBB11_133: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 - LONG $0x303b4466 // cmp r14w, word [rax] - WORD $0x9d0f; BYTE $0xd0 // setge al - WORD $0xd8f6 // neg al - WORD $0x8948; BYTE $0xf2 // mov rdx, rsi - LONG $0x03eac148 // shr rdx, 3 - LONG $0x143c8a41 // mov dil, byte [r12 + rdx] - LONG $0x07e68040 // and sil, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0xf189 // mov ecx, esi +LBB11_209: WORD $0xe3d2 // shl bl, cl WORD $0x3040; BYTE $0xf8 // xor al, dil WORD $0xc320 // and bl, al WORD $0x3040; BYTE $0xfb // xor bl, dil - LONG $0x141c8841 // mov byte [r12 + rdx], bl - JMP LBB11_201 + JMP LBB11_214 -LBB11_193: +LBB11_210: WORD $0x894d; BYTE $0xc2 // mov r10, r8 LONG $0xfee28349 // and r10, -2 WORD $0x3145; BYTE $0xdb // xor r11d, r11d + WORD $0x894d; BYTE $0xee // mov r14, r13 -LBB11_194: +LBB11_211: WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] LONG $0x000000ba; BYTE $0x00 // mov edx, 0 WORD $0xd280; BYTE $0xff // adc dl, -1 @@ -56984,238 +58757,1155 @@ LBB11_194: WORD $0xc230 // xor dl, al LONG $0x3e148841 // mov byte [r14 + rdi], dl WORD $0x394d; BYTE $0xda // cmp r10, r11 - JNE LBB11_194 + JNE LBB11_211 -LBB11_191: - LONG $0x01c0f641 // test r8b, 1 - JE LBB11_201 - WORD $0xc031 // xor eax, eax - WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] - WORD $0xff14 // adc al, -1 - WORD $0x894c; BYTE $0xda // mov rdx, r11 - LONG $0x03eac148 // shr rdx, 3 - LONG $0x16348a41 // mov sil, byte [r14 + rdx] - LONG $0x07e38041 // and r11b, 7 - WORD $0x01b3 // mov bl, 1 - WORD $0x8944; BYTE $0xd9 // mov ecx, r11d - WORD $0xe3d2 // shl bl, cl - WORD $0x3040; BYTE $0xf0 // xor al, sil - WORD $0xc320 // and bl, al - WORD $0x3040; BYTE $0xf3 // xor bl, sil - LONG $0x161c8841 // mov byte [r14 + rdx], bl - JMP LBB11_201 +LBB11_212: + LONG $0x01c0f641 // test r8b, 1 + JE LBB11_215 + WORD $0xc031 // xor eax, eax + WORD $0x2e0f; BYTE $0x03 // ucomiss xmm0, dword [rbx] + WORD $0xff14 // adc al, -1 + WORD $0x894c; BYTE $0xda // mov rdx, r11 + LONG $0x03eac148 // shr rdx, 3 + LONG $0x15748a41; BYTE $0x00 // mov sil, byte [r13 + rdx] + LONG $0x07e38041 // and r11b, 7 + WORD $0x01b3 // mov bl, 1 + WORD $0x8944; BYTE $0xd9 // mov ecx, r11d + WORD $0xe3d2 // shl bl, cl + WORD $0x3040; BYTE $0xf0 // xor al, sil + WORD $0xc320 // and bl, al + WORD $0x3040; BYTE $0xf3 // xor bl, sil + +LBB11_214: + LONG $0x155c8841; BYTE $0x00 // mov byte [r13 + rdx], bl + +LBB11_215: + MOVQ 304(SP), SP + RET + +LBB11_216: + LONG $0xf8e18348 // and rcx, -8 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + LONG $0x06e0c148 // shl rax, 6 + WORD $0x0148; BYTE $0xd0 // add rax, rdx + LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + LONG $0x244c8948; BYTE $0x18 // mov qword [rsp + 24], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax + LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d + LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 + LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 + WORD $0x3145; BYTE $0xf6 // xor r14d, r14d + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + LONG $0xef0f4566; BYTE $0xff // pxor xmm15, xmm15 + +LBB11_217: + LONG $0x2474894c; BYTE $0x28 // mov qword [rsp + 40], r14 + LONG $0x06e6c149 // shl r14, 6 + WORD $0x894d; BYTE $0xf1 // mov r9, r14 + WORD $0x894d; BYTE $0xf7 // mov r15, r14 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + WORD $0x894d; BYTE $0xf5 // mov r13, r14 + WORD $0x894c; BYTE $0xf6 // mov rsi, r14 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + LONG $0x04b70f42; BYTE $0x32 // movzx eax, word [rdx + r14] + LONG $0xe86e0f66 // movd xmm5, eax + LONG $0x44b70f42; WORD $0x0232 // movzx eax, word [rdx + r14 + 2] + LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x44b70f42; WORD $0x0432 // movzx eax, word [rdx + r14 + 4] + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x44b70f42; WORD $0x0632 // movzx eax, word [rdx + r14 + 6] + LONG $0xf86e0f66 // movd xmm7, eax + LONG $0x44b70f42; WORD $0x0832 // movzx eax, word [rdx + r14 + 8] + LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax + LONG $0x44b70f42; WORD $0x0a32 // movzx eax, word [rdx + r14 + 10] + LONG $0xe06e0f66 // movd xmm4, eax + LONG $0x44b70f42; WORD $0x0c32 // movzx eax, word [rdx + r14 + 12] + LONG $0x54b70f46; WORD $0x0e32 // movzx r10d, word [rdx + r14 + 14] + LONG $0x5cb70f42; WORD $0x1032 // movzx ebx, word [rdx + r14 + 16] + LONG $0x7cb70f42; WORD $0x1232 // movzx edi, word [rdx + r14 + 18] + LONG $0x4cb70f42; WORD $0x1432 // movzx ecx, word [rdx + r14 + 20] + LONG $0x10244c89 // mov dword [rsp + 16], ecx + WORD $0x894c; BYTE $0xf1 // mov rcx, r14 + LONG $0x40c98348 // or rcx, 64 + LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + LONG $0xc0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 192 + LONG $0x00cc8149; WORD $0x0001; BYTE $0x00 // or r12, 256 + LONG $0x40cd8149; WORD $0x0001; BYTE $0x00 // or r13, 320 + LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 + LONG $0x2cc40f66; WORD $0x010a // pinsrw xmm5, word [rdx + rcx], 1 + LONG $0xc40f4266; WORD $0x0a2c; BYTE $0x02 // pinsrw xmm5, word [rdx + r9], 2 + LONG $0xc40f4266; WORD $0x3a2c; BYTE $0x03 // pinsrw xmm5, word [rdx + r15], 3 + LONG $0xc40f4266; WORD $0x222c; BYTE $0x04 // pinsrw xmm5, word [rdx + r12], 4 + LONG $0xc40f4266; WORD $0x2a2c; BYTE $0x05 // pinsrw xmm5, word [rdx + r13], 5 + LONG $0x2cc40f66; WORD $0x0632 // pinsrw xmm5, word [rdx + rsi], 6 + LONG $0x44c40f66; WORD $0x020a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 2], 1 + QUAD $0x02020a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 2], 2 + QUAD $0x03023a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 2], 3 + QUAD $0x04022244c40f4266 // pinsrw xmm0, word [rdx + r12 + 2], 4 + QUAD $0x05022a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 2], 5 + LONG $0x44c40f66; WORD $0x0232; BYTE $0x06 // pinsrw xmm0, word [rdx + rsi + 2], 6 + LONG $0xc0c88149; WORD $0x0001; BYTE $0x00 // or r8, 448 + QUAD $0x07020244c40f4266 // pinsrw xmm0, word [rdx + r8 + 2], 7 + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x44b70f42; WORD $0x1632 // movzx eax, word [rdx + r14 + 22] + LONG $0x20244489 // mov dword [rsp + 32], eax + LONG $0x650f4166; BYTE $0xc3 // pcmpgtw xmm0, xmm11 + LONG $0x4cc40f66; WORD $0x040a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 4], 1 + QUAD $0x02040a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 4], 2 + QUAD $0x03043a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 4], 3 + QUAD $0x0404224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 4], 4 + QUAD $0x05042a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 4], 5 + LONG $0x4cc40f66; WORD $0x0432; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 4], 6 + QUAD $0x0704024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 4], 7 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 + QUAD $0x0000808d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 128[rbp] /* [rip + .LCPI11_8] */ + LONG $0x6f0f4166; BYTE $0xd9 // movdqa xmm3, xmm9 + LONG $0x380f4166; WORD $0xdf10 // pblendvb xmm3, xmm15, xmm0 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + QUAD $0x00000090856f0f66 // movdqa xmm0, oword 144[rbp] /* [rip + .LCPI11_9] */ + LONG $0xf06f0f66 // movdqa xmm6, xmm0 + LONG $0x6f0f4466; BYTE $0xf0 // movdqa xmm14, xmm0 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xca // movd xmm1, r10d + LONG $0x5cb70f46; WORD $0x1832 // movzx r11d, word [rdx + r14 + 24] + LONG $0xc40f4266; WORD $0x022c; BYTE $0x07 // pinsrw xmm5, word [rdx + r8], 7 + LONG $0x650f4166; BYTE $0xeb // pcmpgtw xmm5, xmm11 + LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 + LONG $0xe8ef0f66 // pxor xmm5, xmm0 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0x7cc40f66; WORD $0x060a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 6], 1 + QUAD $0x02060a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 6], 2 + QUAD $0x03063a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 6], 3 + QUAD $0x0406227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 6], 4 + QUAD $0x05062a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 6], 5 + LONG $0x7cc40f66; WORD $0x0632; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 6], 6 + QUAD $0x0706027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 6], 7 + LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x01080a44c40f4466 // pinsrw xmm8, word [rdx + rcx + 8], 1 + QUAD $0x02080a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 8], 2 + QUAD $0x03083a44c40f4666 // pinsrw xmm8, word [rdx + r15 + 8], 3 + QUAD $0x04082244c40f4666 // pinsrw xmm8, word [rdx + r12 + 8], 4 + QUAD $0x05082a44c40f4666 // pinsrw xmm8, word [rdx + r13 + 8], 5 + QUAD $0x06083244c40f4466 // pinsrw xmm8, word [rdx + rsi + 8], 6 + QUAD $0x07080244c40f4666 // pinsrw xmm8, word [rdx + r8 + 8], 7 + LONG $0xddf80f66 // psubb xmm3, xmm5 + QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI11_10] */ + LONG $0xc76f0f66 // movdqa xmm0, xmm7 + LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 + LONG $0xfb6e0f66 // movd xmm7, ebx + LONG $0x44b70f42; WORD $0x1a32 // movzx eax, word [rdx + r14 + 26] + LONG $0x650f4566; BYTE $0xc3 // pcmpgtw xmm8, xmm11 + LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 + LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 + QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI11_11] */ + LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0xf76e0f66 // movd xmm6, edi + LONG $0x54b70f46; WORD $0x1c32 // movzx r10d, word [rdx + r14 + 28] + LONG $0x64c40f66; WORD $0x0a0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 10], 1 + QUAD $0x020a0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 10], 2 + QUAD $0x030a3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 10], 3 + QUAD $0x040a2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 10], 4 + QUAD $0x050a2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 10], 5 + LONG $0x64c40f66; WORD $0x0a32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 10], 6 + QUAD $0x070a0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 10], 7 + LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0x54c40f66; WORD $0x0c0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 12], 1 + QUAD $0x020c0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 12], 2 + QUAD $0x030c3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 12], 3 + QUAD $0x040c2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 12], 4 + QUAD $0x050c2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 12], 5 + LONG $0x54c40f66; WORD $0x0c32; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 12], 6 + LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI11_12] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x646e0f66; WORD $0x1024 // movd xmm4, dword [rsp + 16] + LONG $0x5cb70f42; WORD $0x1e32 // movzx ebx, word [rdx + r14 + 30] + QUAD $0x070c0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 12], 7 + LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 + QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI11_13] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0x5c6e0f66; WORD $0x2024 // movd xmm3, dword [rsp + 32] + LONG $0x7cb70f42; WORD $0x2032 // movzx edi, word [rdx + r14 + 32] + LONG $0x20247c89 // mov dword [rsp + 32], edi + LONG $0x4cc40f66; WORD $0x0e0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 14], 1 + QUAD $0x020e0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 14], 2 + QUAD $0x030e3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 14], 3 + QUAD $0x040e224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 14], 4 + QUAD $0x050e2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 14], 5 + LONG $0x4cc40f66; WORD $0x0e32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 14], 6 + LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 + LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d + LONG $0x7cb70f42; WORD $0x2232 // movzx edi, word [rdx + r14 + 34] + LONG $0x10247c89 // mov dword [rsp + 16], edi + QUAD $0x070e024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 14], 7 + LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 + LONG $0x74c40f66; WORD $0x120a; BYTE $0x01 // pinsrw xmm6, word [rdx + rcx + 18], 1 + QUAD $0x02120a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 18], 2 + QUAD $0x03123a74c40f4266 // pinsrw xmm6, word [rdx + r15 + 18], 3 + QUAD $0x04122274c40f4266 // pinsrw xmm6, word [rdx + r12 + 18], 4 + QUAD $0x05122a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 18], 5 + LONG $0x74c40f66; WORD $0x1232; BYTE $0x06 // pinsrw xmm6, word [rdx + rsi + 18], 6 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + QUAD $0x07120274c40f4266 // pinsrw xmm6, word [rdx + r8 + 18], 7 + LONG $0x650f4166; BYTE $0xf3 // pcmpgtw xmm6, xmm11 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 + QUAD $0x0000e0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 224[rbp] /* [rip + .LCPI11_14] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 + LONG $0x6f0f4566; BYTE $0xc1 // movdqa xmm8, xmm9 + LONG $0xc66f0f66 // movdqa xmm0, xmm6 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xc86e0f66 // movd xmm1, eax + LONG $0x5cb70f46; WORD $0x2432 // movzx r11d, word [rdx + r14 + 36] + LONG $0x7cc40f66; WORD $0x100a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 16], 1 + QUAD $0x02100a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 16], 2 + QUAD $0x03103a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 16], 3 + QUAD $0x0410227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 16], 4 + QUAD $0x05102a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 16], 5 + LONG $0x7cc40f66; WORD $0x1032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 16], 6 + LONG $0x64c40f66; WORD $0x140a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 20], 1 + QUAD $0x02140a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 20], 2 + QUAD $0x03143a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 20], 3 + QUAD $0x04142264c40f4266 // pinsrw xmm4, word [rdx + r12 + 20], 4 + QUAD $0x05142a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 20], 5 + LONG $0x64c40f66; WORD $0x1432; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 20], 6 + QUAD $0x07140264c40f4266 // pinsrw xmm4, word [rdx + r8 + 20], 7 + LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 + LONG $0x6f0f4166; BYTE $0xee // movdqa xmm5, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xe2 // movd xmm4, r10d + LONG $0x7cb70f42; WORD $0x2632 // movzx edi, word [rdx + r14 + 38] + QUAD $0x0710027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 16], 7 + LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI11_22] */ + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x5cc40f66; WORD $0x160a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 22], 1 + QUAD $0x02160a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 22], 2 + QUAD $0x03163a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 22], 3 + QUAD $0x0416225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 22], 4 + QUAD $0x05162a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 22], 5 + LONG $0x5cc40f66; WORD $0x1632; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 22], 6 + QUAD $0x0716025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 22], 7 + LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0x54c40f66; WORD $0x180a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 24], 1 + QUAD $0x02180a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 24], 2 + QUAD $0x03183a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 24], 3 + QUAD $0x04182254c40f4266 // pinsrw xmm2, word [rdx + r12 + 24], 4 + QUAD $0x05182a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 24], 5 + LONG $0x54c40f66; WORD $0x1832; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 24], 6 + QUAD $0x07180254c40f4266 // pinsrw xmm2, word [rdx + r8 + 24], 7 + LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 + QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI11_10] */ + LONG $0x6f0f4566; BYTE $0xf2 // movdqa xmm14, xmm10 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 + LONG $0xdb6e0f66 // movd xmm3, ebx + LONG $0x44b70f42; WORD $0x2832 // movzx eax, word [rdx + r14 + 40] + LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4466; BYTE $0xf5 // por xmm14, xmm5 + QUAD $0x0000b08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 176[rbp] /* [rip + .LCPI11_11] */ + LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + LONG $0x7c6e0f66; WORD $0x2024 // movd xmm7, dword [rsp + 32] + LONG $0x54b70f46; WORD $0x2a32 // movzx r10d, word [rdx + r14 + 42] + LONG $0x4cc40f66; WORD $0x1a0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 26], 1 + QUAD $0x021a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 26], 2 + QUAD $0x031a3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 26], 3 + QUAD $0x041a224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 26], 4 + QUAD $0x051a2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 26], 5 + LONG $0x4cc40f66; WORD $0x1a32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 26], 6 + QUAD $0x071a024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 26], 7 + LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x64c40f66; WORD $0x1c0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 28], 1 + QUAD $0x021c0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 28], 2 + QUAD $0x031c3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 28], 3 + QUAD $0x041c2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 28], 4 + QUAD $0x051c2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 28], 5 + LONG $0x64c40f66; WORD $0x1c32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 28], 6 + LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 + QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI11_12] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x546e0f66; WORD $0x1024 // movd xmm2, dword [rsp + 16] + LONG $0x5cb70f42; WORD $0x2c32 // movzx ebx, word [rdx + r14 + 44] + LONG $0x20245c89 // mov dword [rsp + 32], ebx + QUAD $0x071c0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 28], 7 + LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 + QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI11_13] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d + LONG $0x5cb70f42; WORD $0x2e32 // movzx ebx, word [rdx + r14 + 46] + LONG $0x10245c89 // mov dword [rsp + 16], ebx + LONG $0x5cc40f66; WORD $0x1e0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 30], 1 + QUAD $0x021e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 30], 2 + QUAD $0x031e3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 30], 3 + QUAD $0x041e225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 30], 4 + QUAD $0x051e2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 30], 5 + LONG $0x5cc40f66; WORD $0x1e32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 30], 6 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0xcf6e0f66 // movd xmm1, edi + LONG $0x7cb70f42; WORD $0x3032 // movzx edi, word [rdx + r14 + 48] + QUAD $0x071e025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 30], 7 + LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 + LONG $0x54c40f66; WORD $0x220a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 34], 1 + QUAD $0x02220a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 34], 2 + QUAD $0x03223a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 34], 3 + QUAD $0x04222254c40f4266 // pinsrw xmm2, word [rdx + r12 + 34], 4 + QUAD $0x05222a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 34], 5 + LONG $0x54c40f66; WORD $0x2232; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 34], 6 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + QUAD $0x07220254c40f4266 // pinsrw xmm2, word [rdx + r8 + 34], 7 + LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 + QUAD $0x0000e0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 224[rbp] /* [rip + .LCPI11_14] */ + LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 + QUAD $0x000080856f0f4466; BYTE $0x00 // movdqa xmm8, oword 128[rbp] /* [rip + .LCPI11_8] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xd06e0f66 // movd xmm2, eax + LONG $0x5cb70f46; WORD $0x3232 // movzx r11d, word [rdx + r14 + 50] + LONG $0x7cc40f66; WORD $0x200a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 32], 1 + QUAD $0x02200a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 32], 2 + QUAD $0x03203a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 32], 3 + QUAD $0x0420227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 32], 4 + QUAD $0x05202a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 32], 5 + LONG $0x7cc40f66; WORD $0x2032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 32], 6 + LONG $0x64c40f66; WORD $0x240a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 36], 1 + QUAD $0x02240a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 36], 2 + QUAD $0x03243a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 36], 3 + QUAD $0x04242264c40f4266 // pinsrw xmm4, word [rdx + r12 + 36], 4 + QUAD $0x05242a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 36], 5 + LONG $0x64c40f66; WORD $0x2432; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 36], 6 + QUAD $0x07240264c40f4266 // pinsrw xmm4, word [rdx + r8 + 36], 7 + LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 + QUAD $0x00000090b56f0f66 // movdqa xmm6, oword 144[rbp] /* [rip + .LCPI11_9] */ + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d + LONG $0x54b70f46; WORD $0x3432 // movzx r10d, word [rdx + r14 + 52] + QUAD $0x0720027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 32], 7 + LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI11_22] */ + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x4cc40f66; WORD $0x260a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 38], 1 + QUAD $0x02260a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 38], 2 + QUAD $0x03263a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 38], 3 + QUAD $0x0426224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 38], 4 + QUAD $0x05262a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 38], 5 + LONG $0x4cc40f66; WORD $0x2632; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 38], 6 + QUAD $0x0726024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 38], 7 + LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x54c40f66; WORD $0x280a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 40], 1 + QUAD $0x02280a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 40], 2 + QUAD $0x03283a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 40], 3 + QUAD $0x04282254c40f4266 // pinsrw xmm2, word [rdx + r12 + 40], 4 + QUAD $0x05282a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 40], 5 + LONG $0x54c40f66; WORD $0x2832; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 40], 6 + QUAD $0x07280254c40f4266 // pinsrw xmm2, word [rdx + r8 + 40], 7 + LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 + LONG $0x6f0f4166; BYTE $0xea // movdqa xmm5, xmm10 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + LONG $0x4c6e0f66; WORD $0x2024 // movd xmm1, dword [rsp + 32] + LONG $0x44b70f42; WORD $0x3632 // movzx eax, word [rdx + r14 + 54] + LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x6f0f4166; BYTE $0xf1 // movdqa xmm6, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x646e0f66; WORD $0x1024 // movd xmm4, dword [rsp + 16] + LONG $0x5cb70f42; WORD $0x3832 // movzx ebx, word [rdx + r14 + 56] + LONG $0x5cc40f66; WORD $0x2a0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 42], 1 + QUAD $0x022a0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 42], 2 + QUAD $0x032a3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 42], 3 + QUAD $0x042a225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 42], 4 + QUAD $0x052a2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 42], 5 + LONG $0x5cc40f66; WORD $0x2a32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 42], 6 + QUAD $0x072a025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 42], 7 + LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0x4cc40f66; WORD $0x2c0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 44], 1 + QUAD $0x022c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 44], 2 + QUAD $0x032c3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 44], 3 + QUAD $0x042c224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 44], 4 + QUAD $0x052c2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 44], 5 + LONG $0x4cc40f66; WORD $0x2c32; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 44], 6 + LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 + QUAD $0x0000c08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 192[rbp] /* [rip + .LCPI11_12] */ + LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4166; WORD $0xd710 // pblendvb xmm2, xmm15, xmm0 + LONG $0xff6e0f66 // movd xmm7, edi + LONG $0x7cb70f42; WORD $0x3a32 // movzx edi, word [rdx + r14 + 58] + QUAD $0x072c024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 44], 7 + LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0x0000d0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 208[rbp] /* [rip + .LCPI11_13] */ + LONG $0x6f0f4166; BYTE $0xf2 // movdqa xmm6, xmm10 + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0x6e0f4166; BYTE $0xcb // movd xmm1, r11d + LONG $0x5cb70f46; WORD $0x3c32 // movzx r11d, word [rdx + r14 + 60] + LONG $0xf2eb0f66 // por xmm6, xmm2 + LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d + LONG $0x64c40f66; WORD $0x2e0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 46], 1 + QUAD $0x022e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 46], 2 + QUAD $0x032e3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 46], 3 + QUAD $0x042e2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 46], 4 + QUAD $0x052e2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 46], 5 + LONG $0x64c40f66; WORD $0x2e32; BYTE $0x06 // pinsrw xmm4, word [rdx + rsi + 46], 6 + QUAD $0x072e0264c40f4266 // pinsrw xmm4, word [rdx + r8 + 46], 7 + LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0x6f0f4566; BYTE $0xc6 // movdqa xmm8, xmm14 + LONG $0xc46f0f66 // movdqa xmm0, xmm4 + LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 + LONG $0xd86e0f66 // movd xmm3, eax + LONG $0x4cc40f66; WORD $0x320a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 50], 1 + QUAD $0x02320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 2 + QUAD $0x03323a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 50], 3 + QUAD $0x0432224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 50], 4 + QUAD $0x05322a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 50], 5 + LONG $0x4cc40f66; WORD $0x3232; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 50], 6 + QUAD $0x0732024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 50], 7 + LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 + QUAD $0x00000080a56f0f66 // movdqa xmm4, oword 128[rbp] /* [rip + .LCPI11_8] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 + LONG $0xcb6e0f66 // movd xmm1, ebx + LONG $0x7cc40f66; WORD $0x300a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 48], 1 + QUAD $0x02300a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 48], 2 + QUAD $0x03303a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 48], 3 + QUAD $0x0430227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 48], 4 + QUAD $0x05302a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 48], 5 + LONG $0x7cc40f66; WORD $0x3032; BYTE $0x06 // pinsrw xmm7, word [rdx + rsi + 48], 6 + QUAD $0x0730027cc40f4266 // pinsrw xmm7, word [rdx + r8 + 48], 7 + LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 + QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI11_22] */ + LONG $0x54c40f66; WORD $0x340a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 52], 1 + QUAD $0x02340a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 52], 2 + QUAD $0x03343a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 52], 3 + QUAD $0x04342254c40f4266 // pinsrw xmm2, word [rdx + r12 + 52], 4 + QUAD $0x05342a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 52], 5 + LONG $0x54c40f66; WORD $0x3432; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 52], 6 + LONG $0xff630f66 // packsswb xmm7, xmm7 + QUAD $0x07340254c40f4266 // pinsrw xmm2, word [rdx + r8 + 52], 7 + LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 + LONG $0x5cc40f66; WORD $0x360a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 54], 1 + QUAD $0x02360a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 54], 2 + QUAD $0x03363a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 54], 3 + QUAD $0x0436225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 54], 4 + QUAD $0x05362a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 54], 5 + LONG $0x5cc40f66; WORD $0x3632; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 54], 6 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x0736025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 54], 7 + LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 + LONG $0x4cc40f66; WORD $0x380a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 56], 1 + QUAD $0x02380a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 56], 2 + QUAD $0x03383a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 56], 3 + QUAD $0x0438224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 56], 4 + QUAD $0x05382a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 56], 5 + LONG $0x4cc40f66; WORD $0x3832; BYTE $0x06 // pinsrw xmm1, word [rdx + rsi + 56], 6 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + QUAD $0x0738024cc40f4266 // pinsrw xmm1, word [rdx + r8 + 56], 7 + LONG $0xe7f80f66 // psubb xmm4, xmm7 + QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI11_9] */ + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 + QUAD $0x000000a0b56f0f66 // movdqa xmm6, oword 160[rbp] /* [rip + .LCPI11_10] */ + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 + LONG $0xd76e0f66 // movd xmm2, edi + LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 + LONG $0x54c40f66; WORD $0x3a0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 58], 1 + QUAD $0x023a0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 58], 2 + QUAD $0x033a3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 58], 3 + QUAD $0x043a2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 58], 4 + QUAD $0x053a2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 58], 5 + LONG $0x54c40f66; WORD $0x3a32; BYTE $0x06 // pinsrw xmm2, word [rdx + rsi + 58], 6 + QUAD $0x073a0254c40f4266 // pinsrw xmm2, word [rdx + r8 + 58], 7 + LONG $0xc9630f66 // packsswb xmm1, xmm1 + LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 + LONG $0xf5eb0f66 // por xmm6, xmm5 + LONG $0x6e0f4166; BYTE $0xdb // movd xmm3, r11d + LONG $0x5cc40f66; WORD $0x3c0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 60], 1 + QUAD $0x023c0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 60], 2 + QUAD $0x033c3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 60], 3 + QUAD $0x043c225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 60], 4 + QUAD $0x053c2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 60], 5 + LONG $0x5cc40f66; WORD $0x3c32; BYTE $0x06 // pinsrw xmm3, word [rdx + rsi + 60], 6 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + QUAD $0x073c025cc40f4266 // pinsrw xmm3, word [rdx + r8 + 60], 7 + LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf4eb0f66 // por xmm6, xmm4 + QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI11_11] */ + LONG $0xc16f0f66 // movdqa xmm0, xmm1 + LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 + LONG $0x6f0f4166; BYTE $0xc9 // movdqa xmm1, xmm9 + LONG $0xc26f0f66 // movdqa xmm0, xmm2 + LONG $0x380f4166; WORD $0xcf10 // pblendvb xmm1, xmm15, xmm0 + LONG $0xc36f0f66 // movdqa xmm0, xmm3 + LONG $0x380f4566; WORD $0xd710 // pblendvb xmm10, xmm15, xmm0 + LONG $0xcceb0f66 // por xmm1, xmm4 + LONG $0x44b70f42; WORD $0x3e32 // movzx eax, word [rdx + r14 + 62] + LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 + LONG $0xc06e0f66 // movd xmm0, eax + LONG $0x44c40f66; WORD $0x3e0a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 62], 1 + QUAD $0x023e0a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 62], 2 + QUAD $0x033e3a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 62], 3 + QUAD $0x043e2244c40f4266 // pinsrw xmm0, word [rdx + r12 + 62], 4 + QUAD $0x0000008824848b48 // mov rax, qword [rsp + 136] + QUAD $0x053e2a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 62], 5 + LONG $0x44c40f66; WORD $0x3e32; BYTE $0x06 // pinsrw xmm0, word [rdx + rsi + 62], 6 + QUAD $0x073e0244c40f4266 // pinsrw xmm0, word [rdx + r8 + 62], 7 + LONG $0x650f4166; BYTE $0xc3 // pcmpgtw xmm0, xmm11 + LONG $0xc0630f66 // packsswb xmm0, xmm0 + LONG $0xeb0f4466; BYTE $0xd6 // por xmm10, xmm6 + LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 + LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 + LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 + LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 + LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 + LONG $0x6c0f4166; BYTE $0xd6 // punpcklqdq xmm2, xmm14 + QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI11_15] */ + LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 + LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 + LONG $0xc2610f66 // punpcklwd xmm0, xmm2 + LONG $0x600f4566; BYTE $0xc6 // punpcklbw xmm8, xmm14 + LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 + LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 + LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] + LONG $0x7f0f44f3; WORD $0x8824 // movdqu oword [rax + 4*rcx], xmm12 + LONG $0x447f0ff3; WORD $0x1088 // movdqu oword [rax + 4*rcx + 16], xmm0 + LONG $0x08c18348 // add rcx, 8 + WORD $0x8949; BYTE $0xce // mov r14, rcx + LONG $0x244c3b48; BYTE $0x18 // cmp rcx, qword [rsp + 24] + JNE LBB11_217 + QUAD $0x000000b8248c8b48 // mov rcx, qword [rsp + 184] + LONG $0x244c3b48; BYTE $0x18 // cmp rcx, qword [rsp + 24] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x24748b44; BYTE $0x08 // mov r14d, dword [rsp + 8] + LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + JNE LBB11_81 + JMP LBB11_131 + +LBB11_219: + WORD $0x8949; BYTE $0xc9 // mov r9, rcx + LONG $0xfce18349 // and r9, -4 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + LONG $0x07e3c148 // shl rbx, 7 + WORD $0x0148; BYTE $0xd3 // add rbx, rdx + LONG $0x8c2c8d4f // lea r13, [r12 + 4*r9] + LONG $0xc86f0f66 // movdqa xmm1, xmm0 + LONG $0x00c8c60f // shufps xmm1, xmm0, 0 + LONG $0xfcc28148; WORD $0x0001; BYTE $0x00 // add rdx, 508 + WORD $0xf631 // xor esi, esi + LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI11_0] */ + LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI11_1] */ + LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI11_2] */ + LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI11_3] */ + LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI11_4] */ + LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI11_5] */ + LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI11_6] */ + LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI11_7] */ -LBB11_85: - LONG $0xf0e28349 // and r10, -16 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 +LBB11_220: + QUAD $0xfffffe04b2100ff3 // movss xmm6, dword [rdx - 508] + QUAD $0xfffffe08ba100ff3 // movss xmm7, dword [rdx - 504] + QUAD $0xfffffe0caa100ff3 // movss xmm5, dword [rdx - 500] + QUAD $0xfffffe10a2100ff3 // movss xmm4, dword [rdx - 496] + QUAD $0xfffe84b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 380], 16 + QUAD $0xffff04b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 252], 32 + LONG $0x213a0f66; WORD $0x8472; BYTE $0x30 // insertps xmm6, dword [rdx - 124], 48 + LONG $0x02f1c20f // cmpleps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + QUAD $0xfffe88ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 376], 16 + QUAD $0xffff08ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 248], 32 + LONG $0x213a0f66; WORD $0x887a; BYTE $0x30 // insertps xmm7, dword [rdx - 120], 48 + QUAD $0xfffe8caa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 372], 16 + QUAD $0xffff0caa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 244], 32 + LONG $0x213a0f66; WORD $0x8c6a; BYTE $0x30 // insertps xmm5, dword [rdx - 116], 48 + QUAD $0xfffe90a2213a0f66; WORD $0x10ff // insertps xmm4, dword [rdx - 368], 16 + QUAD $0xffff10a2213a0f66; WORD $0x20ff // insertps xmm4, dword [rdx - 240], 32 + LONG $0x213a0f66; WORD $0x9062; BYTE $0x30 // insertps xmm4, dword [rdx - 112], 48 + LONG $0x02f9c20f // cmpleps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xd76f0f66 // movdqa xmm2, xmm7 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xd7f80f66 // psubb xmm2, xmm7 + QUAD $0xfffffe14ba100ff3 // movss xmm7, dword [rdx - 492] + QUAD $0xfffe94ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 364], 16 + QUAD $0xffff14ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 236], 32 + LONG $0x213a0f66; WORD $0x947a; BYTE $0x30 // insertps xmm7, dword [rdx - 108], 48 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe18b2100ff3 // movss xmm6, dword [rdx - 488] + QUAD $0xfffe98b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 360], 16 + QUAD $0xffff18b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 232], 32 + LONG $0x213a0f66; WORD $0x9872; BYTE $0x30 // insertps xmm6, dword [rdx - 104], 48 + LONG $0x02e9c20f // cmpleps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 + LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 + LONG $0xeaeb0f66 // por xmm5, xmm2 + QUAD $0xfffffe1c9a100ff3 // movss xmm3, dword [rdx - 484] + QUAD $0xfffe9c9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 356], 16 + QUAD $0xffff1c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 228], 32 + LONG $0x213a0f66; WORD $0x9c5a; BYTE $0x30 // insertps xmm3, dword [rdx - 100], 48 + LONG $0x02e1c20f // cmpleps xmm4, xmm1 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 + LONG $0xf4710f66; BYTE $0x03 // psllw xmm4, 3 + LONG $0xdb0f4166; BYTE $0xe2 // pand xmm4, xmm10 + LONG $0x02f9c20f // cmpleps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x04 // psllw xmm7, 4 + LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 + LONG $0xfceb0f66 // por xmm7, xmm4 + QUAD $0xfffffe20a2100ff3 // movss xmm4, dword [rdx - 480] + QUAD $0xfffea0a2213a0f66; WORD $0x10ff // insertps xmm4, dword [rdx - 352], 16 + QUAD $0xffff20a2213a0f66; WORD $0x20ff // insertps xmm4, dword [rdx - 224], 32 + LONG $0x213a0f66; WORD $0xa062; BYTE $0x30 // insertps xmm4, dword [rdx - 96], 48 + LONG $0xfdeb0f66 // por xmm7, xmm5 + QUAD $0xfffffe24aa100ff3 // movss xmm5, dword [rdx - 476] + QUAD $0xfffea4aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 348], 16 + QUAD $0xffff24aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 220], 32 + LONG $0x213a0f66; WORD $0xa46a; BYTE $0x30 // insertps xmm5, dword [rdx - 92], 48 + LONG $0x02e9c20f // cmpleps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0x02f1c20f // cmpleps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0x02d9c20f // cmpleps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 + LONG $0xdb0f4166; BYTE $0xdd // pand xmm3, xmm13 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe2892100ff3 // movss xmm2, dword [rdx - 472] + QUAD $0xfffea892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 344], 16 + QUAD $0xffff2892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 216], 32 + LONG $0x213a0f66; WORD $0xa852; BYTE $0x30 // insertps xmm2, dword [rdx - 88], 48 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0x02e1c20f // cmpleps xmm4, xmm1 + LONG $0xe46b0f66 // packssdw xmm4, xmm4 + LONG $0xe4630f66 // packsswb xmm4, xmm4 + LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 + LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 + LONG $0xe3eb0f66 // por xmm4, xmm3 + QUAD $0xfffffe2c9a100ff3 // movss xmm3, dword [rdx - 468] + QUAD $0xfffeac9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 340], 16 + QUAD $0xffff2c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 212], 32 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0x213a0f66; WORD $0xac5a; BYTE $0x30 // insertps xmm3, dword [rdx - 84], 48 + LONG $0xe7eb0f66 // por xmm4, xmm7 + LONG $0x02d1c20f // cmpleps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf26f0f66 // movdqa xmm6, xmm2 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf2f80f66 // psubb xmm6, xmm2 + QUAD $0xfffffe30ba100ff3 // movss xmm7, dword [rdx - 464] + QUAD $0xfffeb0ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 336], 16 + QUAD $0xffff30ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 208], 32 + LONG $0x213a0f66; WORD $0xb07a; BYTE $0x30 // insertps xmm7, dword [rdx - 80], 48 + LONG $0xf5eb0f66 // por xmm6, xmm5 + QUAD $0xfffffe34aa100ff3 // movss xmm5, dword [rdx - 460] + QUAD $0xfffeb4aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 332], 16 + QUAD $0xffff34aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 204], 32 + LONG $0x213a0f66; WORD $0xb46a; BYTE $0x30 // insertps xmm5, dword [rdx - 76], 48 + LONG $0x02d9c20f // cmpleps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe38b2100ff3 // movss xmm6, dword [rdx - 456] + QUAD $0xfffeb8b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 328], 16 + QUAD $0xffff38b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 200], 32 + LONG $0x213a0f66; WORD $0xb872; BYTE $0x30 // insertps xmm6, dword [rdx - 72], 48 + LONG $0x02f9c20f // cmpleps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x03 // psllw xmm7, 3 + LONG $0xdb0f4166; BYTE $0xfa // pand xmm7, xmm10 + LONG $0x02e9c20f // cmpleps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 + LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 + LONG $0xefeb0f66 // por xmm5, xmm7 + QUAD $0xfffffe3c92100ff3 // movss xmm2, dword [rdx - 452] + QUAD $0xfffebc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 324], 16 + QUAD $0xffff3c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 196], 32 + LONG $0x213a0f66; WORD $0xbc52; BYTE $0x30 // insertps xmm2, dword [rdx - 68], 48 + LONG $0xebeb0f66 // por xmm5, xmm3 + QUAD $0xfffffe40ba100ff3 // movss xmm7, dword [rdx - 448] + QUAD $0xfffec0ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 320], 16 + QUAD $0xffff40ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 192], 32 + LONG $0x213a0f66; WORD $0xc07a; BYTE $0x30 // insertps xmm7, dword [rdx - 64], 48 + LONG $0x02f1c20f // cmpleps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 + LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 + LONG $0x02d1c20f // cmpleps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd6eb0f66 // por xmm2, xmm6 + QUAD $0xfffffe44b2100ff3 // movss xmm6, dword [rdx - 444] + QUAD $0xfffec4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 316], 16 + QUAD $0xffff44b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 188], 32 + LONG $0x213a0f66; WORD $0xc472; BYTE $0x30 // insertps xmm6, dword [rdx - 60], 48 + LONG $0x02f1c20f // cmpleps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0x02f9c20f // cmpleps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xf7710f66; BYTE $0x07 // psllw xmm7, 7 + LONG $0xdb0f4166; BYTE $0xfe // pand xmm7, xmm14 + LONG $0xfaeb0f66 // por xmm7, xmm2 + QUAD $0xfffffe4892100ff3 // movss xmm2, dword [rdx - 440] + QUAD $0xfffec892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 312], 16 + QUAD $0xffff4892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 184], 32 + LONG $0x213a0f66; WORD $0xc852; BYTE $0x30 // insertps xmm2, dword [rdx - 56], 48 + LONG $0xfdeb0f66 // por xmm7, xmm5 + QUAD $0xfffffe4c9a100ff3 // movss xmm3, dword [rdx - 436] + QUAD $0xfffecc9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 308], 16 + QUAD $0xffff4c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 180], 32 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0x213a0f66; WORD $0xcc5a; BYTE $0x30 // insertps xmm3, dword [rdx - 52], 48 + LONG $0xe7620f66 // punpckldq xmm4, xmm7 + LONG $0x02d1c20f // cmpleps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xfa6f0f66 // movdqa xmm7, xmm2 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xfaf80f66 // psubb xmm7, xmm2 + QUAD $0xfffffe50aa100ff3 // movss xmm5, dword [rdx - 432] + QUAD $0xfffed0aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 304], 16 + QUAD $0xffff50aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 176], 32 + LONG $0x213a0f66; WORD $0xd06a; BYTE $0x30 // insertps xmm5, dword [rdx - 48], 48 + LONG $0xfeeb0f66 // por xmm7, xmm6 + QUAD $0xfffffe54b2100ff3 // movss xmm6, dword [rdx - 428] + QUAD $0xfffed4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 300], 16 + QUAD $0xffff54b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 172], 32 + LONG $0x213a0f66; WORD $0xd472; BYTE $0x30 // insertps xmm6, dword [rdx - 44], 48 + LONG $0x02d9c20f // cmpleps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdfeb0f66 // por xmm3, xmm7 + QUAD $0xfffffe58ba100ff3 // movss xmm7, dword [rdx - 424] + QUAD $0xfffed8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 296], 16 + QUAD $0xffff58ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 168], 32 + LONG $0x213a0f66; WORD $0xd87a; BYTE $0x30 // insertps xmm7, dword [rdx - 40], 48 + LONG $0x02e9c20f // cmpleps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 + LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 + LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 + LONG $0x02f1c20f // cmpleps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf5eb0f66 // por xmm6, xmm5 + QUAD $0xfffffe5c92100ff3 // movss xmm2, dword [rdx - 420] + QUAD $0xfffedc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 292], 16 + QUAD $0xffff5c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 164], 32 + LONG $0x213a0f66; WORD $0xdc52; BYTE $0x30 // insertps xmm2, dword [rdx - 36], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe60aa100ff3 // movss xmm5, dword [rdx - 416] + QUAD $0xfffee0aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 288], 16 + QUAD $0xffff60aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 160], 32 + LONG $0x213a0f66; WORD $0xe06a; BYTE $0x30 // insertps xmm5, dword [rdx - 32], 48 + LONG $0x02f9c20f // cmpleps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x02d1c20f // cmpleps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe64ba100ff3 // movss xmm7, dword [rdx - 412] + QUAD $0xfffee4ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 284], 16 + QUAD $0xffff64ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 156], 32 + LONG $0x213a0f66; WORD $0xe47a; BYTE $0x30 // insertps xmm7, dword [rdx - 28], 48 + LONG $0x02f9c20f // cmpleps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0x02e9c20f // cmpleps xmm5, xmm1 + LONG $0xed6b0f66 // packssdw xmm5, xmm5 + LONG $0xed630f66 // packsswb xmm5, xmm5 + LONG $0xf5710f66; BYTE $0x07 // psllw xmm5, 7 + LONG $0xdb0f4166; BYTE $0xee // pand xmm5, xmm14 + LONG $0xeaeb0f66 // por xmm5, xmm2 + QUAD $0xfffffe6892100ff3 // movss xmm2, dword [rdx - 408] + QUAD $0xfffee892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 280], 16 + QUAD $0xffff6892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 152], 32 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0x213a0f66; WORD $0xe852; BYTE $0x30 // insertps xmm2, dword [rdx - 24], 48 + LONG $0xeeeb0f66 // por xmm5, xmm6 + LONG $0x02d1c20f // cmpleps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xf26f0f66 // movdqa xmm6, xmm2 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf2f80f66 // psubb xmm6, xmm2 + QUAD $0xfffffe6c9a100ff3 // movss xmm3, dword [rdx - 404] + QUAD $0xfffeec9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 276], 16 + QUAD $0xffff6c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 148], 32 + LONG $0x213a0f66; WORD $0xec5a; BYTE $0x30 // insertps xmm3, dword [rdx - 20], 48 + LONG $0xf7eb0f66 // por xmm6, xmm7 + QUAD $0xfffffe7092100ff3 // movss xmm2, dword [rdx - 400] + QUAD $0xfffef092213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 272], 16 + QUAD $0xffff7092213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 144], 32 + LONG $0x213a0f66; WORD $0xf052; BYTE $0x30 // insertps xmm2, dword [rdx - 16], 48 + LONG $0x02d9c20f // cmpleps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 + LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 + LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 + LONG $0xdeeb0f66 // por xmm3, xmm6 + QUAD $0xfffffe74b2100ff3 // movss xmm6, dword [rdx - 396] + QUAD $0xfffef4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 268], 16 + QUAD $0xffff74b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 140], 32 + LONG $0x213a0f66; WORD $0xf472; BYTE $0x30 // insertps xmm6, dword [rdx - 12], 48 + LONG $0x02d1c20f // cmpleps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 + LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 + LONG $0x02f1c20f // cmpleps xmm6, xmm1 + LONG $0xf66b0f66 // packssdw xmm6, xmm6 + LONG $0xf6630f66 // packsswb xmm6, xmm6 + LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 + LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 + LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 + LONG $0xf2eb0f66 // por xmm6, xmm2 + QUAD $0xfffffe78ba100ff3 // movss xmm7, dword [rdx - 392] + QUAD $0xfffef8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 264], 16 + QUAD $0xffff78ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 136], 32 + LONG $0x213a0f66; WORD $0xf87a; BYTE $0x30 // insertps xmm7, dword [rdx - 8], 48 + LONG $0xf3eb0f66 // por xmm6, xmm3 + QUAD $0xfffffe7c92100ff3 // movss xmm2, dword [rdx - 388] + QUAD $0xfffefc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 260], 16 + QUAD $0xffff7c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 132], 32 + LONG $0x213a0f66; WORD $0xfc52; BYTE $0x30 // insertps xmm2, dword [rdx - 4], 48 + LONG $0x02f9c20f // cmpleps xmm7, xmm1 + LONG $0xff6b0f66 // packssdw xmm7, xmm7 + LONG $0xff630f66 // packsswb xmm7, xmm7 + LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 + LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 + LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 + LONG $0x02d1c20f // cmpleps xmm2, xmm1 + LONG $0xd26b0f66 // packssdw xmm2, xmm2 + LONG $0xd2630f66 // packsswb xmm2, xmm2 + LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 + LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 + LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xd7eb0f66 // por xmm2, xmm7 + QUAD $0xfffffe809a100ff3 // movss xmm3, dword [rdx - 384] + QUAD $0xffff009a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 256], 16 + LONG $0x213a0f66; WORD $0x805a; BYTE $0x20 // insertps xmm3, dword [rdx - 128], 32 + LONG $0x213a0f66; WORD $0x301a // insertps xmm3, dword [rdx], 48 + LONG $0x02d9c20f // cmpleps xmm3, xmm1 + LONG $0xdb6b0f66 // packssdw xmm3, xmm3 + LONG $0xdb630f66 // packsswb xmm3, xmm3 + LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 + LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 + LONG $0xdaeb0f66 // por xmm3, xmm2 + LONG $0xdeeb0f66 // por xmm3, xmm6 + LONG $0xeb620f66 // punpckldq xmm5, xmm3 + LONG $0xe5600f66 // punpcklbw xmm4, xmm5 + LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 + LONG $0x7f0f41f3; WORD $0xb424 // movdqu oword [r12 + 4*rsi], xmm4 + LONG $0x04c68348 // add rsi, 4 + LONG $0x00c28148; WORD $0x0002; BYTE $0x00 // add rdx, 512 + WORD $0x3949; BYTE $0xf1 // cmp r9, rsi + JNE LBB11_220 + WORD $0x394c; BYTE $0xc9 // cmp rcx, r9 + JNE LBB11_108 + JMP LBB11_135 + +LBB11_222: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000011824848948 // mov qword [rsp + 280], rax - QUAD $0x000001002494894c // mov qword [rsp + 256], r10 - LONG $0x97048d4b // lea rax, [r15 + 4*r10] - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax + WORD $0x014c; BYTE $0xe8 // add rax, r13 + QUAD $0x0000010024848948 // mov qword [rsp + 256], rax + QUAD $0x000000b8248c8948 // mov qword [rsp + 184], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + QUAD $0x0000010824848948 // mov qword [rsp + 264], rax LONG $0xc6b60f41 // movzx eax, r14b LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000090248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 144], xmm1 + QUAD $0x0000a0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm1 WORD $0xc031 // xor eax, eax - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 -LBB11_86: - QUAD $0x000000e024848948 // mov qword [rsp + 224], rax +LBB11_223: + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax LONG $0x05e0c148 // shl rax, 5 - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - WORD $0x8949; BYTE $0xc1 // mov r9, rax - WORD $0x8949; BYTE $0xc2 // mov r10, rax - WORD $0x8949; BYTE $0xc4 // mov r12, rax + WORD $0x8949; BYTE $0xc0 // mov r8, rax WORD $0x8949; BYTE $0xc6 // mov r14, rax WORD $0x8949; BYTE $0xc7 // mov r15, rax - WORD $0x8949; BYTE $0xc5 // mov r13, rax - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax + WORD $0x8949; BYTE $0xc2 // mov r10, rax WORD $0x8949; BYTE $0xc3 // mov r11, rax - WORD $0x8949; BYTE $0xc0 // mov r8, rax - LONG $0x020cb60f // movzx ecx, byte [rdx + rax] + WORD $0x8949; BYTE $0xc4 // mov r12, rax + WORD $0x8949; BYTE $0xc1 // mov r9, rax + WORD $0x8948; BYTE $0xc3 // mov rbx, rax + LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax + WORD $0x8948; BYTE $0xc6 // mov rsi, rax + LONG $0x24448948; BYTE $0x60 // mov qword [rsp + 96], rax + LONG $0x4cb60f41; WORD $0x0005 // movzx ecx, byte [r13 + rax] LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x024cb60f; BYTE $0x01 // movzx ecx, byte [rdx + rax + 1] + LONG $0x4cb60f41; WORD $0x0105 // movzx ecx, byte [r13 + rax + 1] LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x024cb60f; BYTE $0x02 // movzx ecx, byte [rdx + rax + 2] + LONG $0x4cb60f41; WORD $0x0205 // movzx ecx, byte [r13 + rax + 2] LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x024cb60f; BYTE $0x03 // movzx ecx, byte [rdx + rax + 3] + LONG $0x4cb60f41; WORD $0x0305 // movzx ecx, byte [r13 + rax + 3] LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x024cb60f; BYTE $0x04 // movzx ecx, byte [rdx + rax + 4] + LONG $0x4cb60f41; WORD $0x0405 // movzx ecx, byte [r13 + rax + 4] LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x024cb60f; BYTE $0x05 // movzx ecx, byte [rdx + rax + 5] + LONG $0x4cb60f41; WORD $0x0505 // movzx ecx, byte [r13 + rax + 5] LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x024cb60f; BYTE $0x06 // movzx ecx, byte [rdx + rax + 6] + LONG $0x4cb60f41; WORD $0x0605 // movzx ecx, byte [r13 + rax + 6] LONG $0x6e0f4466; BYTE $0xc1 // movd xmm8, ecx - LONG $0x024cb60f; BYTE $0x07 // movzx ecx, byte [rdx + rax + 7] + LONG $0x4cb60f41; WORD $0x0705 // movzx ecx, byte [r13 + rax + 7] LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x024cb60f; BYTE $0x08 // movzx ecx, byte [rdx + rax + 8] + LONG $0x4cb60f41; WORD $0x0805 // movzx ecx, byte [r13 + rax + 8] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 - LONG $0x024cb60f; BYTE $0x09 // movzx ecx, byte [rdx + rax + 9] + QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 + LONG $0x4cb60f41; WORD $0x0905 // movzx ecx, byte [r13 + rax + 9] LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x024cb60f; BYTE $0x0a // movzx ecx, byte [rdx + rax + 10] + LONG $0x4cb60f41; WORD $0x0a05 // movzx ecx, byte [r13 + rax + 10] LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x024cb60f; BYTE $0x0b // movzx ecx, byte [rdx + rax + 11] + LONG $0x4cb60f41; WORD $0x0b05 // movzx ecx, byte [r13 + rax + 11] LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x024cb60f; BYTE $0x0c // movzx ecx, byte [rdx + rax + 12] + LONG $0x4cb60f41; WORD $0x0c05 // movzx ecx, byte [r13 + rax + 12] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 - LONG $0x024cb60f; BYTE $0x0d // movzx ecx, byte [rdx + rax + 13] + QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 + LONG $0x4cb60f41; WORD $0x0d05 // movzx ecx, byte [r13 + rax + 13] LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x024cb60f; BYTE $0x0e // movzx ecx, byte [rdx + rax + 14] + LONG $0x4cb60f41; WORD $0x0e05 // movzx ecx, byte [r13 + rax + 14] LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x024cb60f; BYTE $0x0f // movzx ecx, byte [rdx + rax + 15] + LONG $0x4cb60f41; WORD $0x0f05 // movzx ecx, byte [r13 + rax + 15] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000a024847f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm0 - LONG $0x24448948; BYTE $0x48 // mov qword [rsp + 72], rax - WORD $0x8948; BYTE $0xc3 // mov rbx, rax - LONG $0x20cb8348 // or rbx, 32 - LONG $0x245c8948; BYTE $0x08 // mov qword [rsp + 8], rbx - LONG $0x40cf8348 // or rdi, 64 - LONG $0x247c8948; BYTE $0x20 // mov qword [rsp + 32], rdi - LONG $0x60ce8348 // or rsi, 96 - LONG $0x24748948; BYTE $0x18 // mov qword [rsp + 24], rsi - LONG $0x80c98149; WORD $0x0000; BYTE $0x00 // or r9, 128 + QUAD $0x0000c024847f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm0 + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax + WORD $0x8948; BYTE $0xc7 // mov rdi, rax + LONG $0x20cf8348 // or rdi, 32 + LONG $0x40c88349 // or r8, 64 + LONG $0x60ce8349 // or r14, 96 + LONG $0x80cf8149; WORD $0x0000; BYTE $0x00 // or r15, 128 LONG $0xa0ca8149; WORD $0x0000; BYTE $0x00 // or r10, 160 - LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 - LONG $0x2464894c; BYTE $0x40 // mov qword [rsp + 64], r12 - LONG $0xe0ce8149; WORD $0x0000; BYTE $0x00 // or r14, 224 - LONG $0x00cf8149; WORD $0x0001; BYTE $0x00 // or r15, 256 - LONG $0x247c894c; BYTE $0x58 // mov qword [rsp + 88], r15 - LONG $0x20cd8149; WORD $0x0001; BYTE $0x00 // or r13, 288 - LONG $0x246c894c; BYTE $0x50 // mov qword [rsp + 80], r13 - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] - LONG $0x40cc8149; WORD $0x0001; BYTE $0x00 // or r12, 320 - LONG $0x60cb8149; WORD $0x0001; BYTE $0x00 // or r11, 352 - LONG $0x80c88149; WORD $0x0001; BYTE $0x00 // or r8, 384 - LONG $0x2444894c; BYTE $0x60 // mov qword [rsp + 96], r8 + LONG $0xc0cb8149; WORD $0x0000; BYTE $0x00 // or r11, 192 + LONG $0xe0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 224 + LONG $0x00c98149; WORD $0x0001; BYTE $0x00 // or r9, 256 + WORD $0x8948; BYTE $0xc2 // mov rdx, rax + LONG $0x20ca8148; WORD $0x0001; BYTE $0x00 // or rdx, 288 + LONG $0x24548948; BYTE $0x48 // mov qword [rsp + 72], rdx + LONG $0x245c8b48; BYTE $0x50 // mov rbx, qword [rsp + 80] + LONG $0x40cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 320 + LONG $0x60ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 352 + LONG $0x24748948; BYTE $0x40 // mov qword [rsp + 64], rsi + LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] + LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 + LONG $0x24748948; BYTE $0x60 // mov qword [rsp + 96], rsi WORD $0x8948; BYTE $0xc1 // mov rcx, rax LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 - LONG $0x244c8948; BYTE $0x30 // mov qword [rsp + 48], rcx + LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx WORD $0x8948; BYTE $0xc1 // mov rcx, rax LONG $0xc0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 448 - LONG $0x244c8948; BYTE $0x28 // mov qword [rsp + 40], rcx - WORD $0x8948; BYTE $0xc6 // mov rsi, rax - LONG $0xe0ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 480 - LONG $0x24748948; BYTE $0x10 // mov qword [rsp + 16], rsi - LONG $0x203a0f66; WORD $0x1a24; BYTE $0x01 // pinsrb xmm4, byte [rdx + rbx], 1 - LONG $0x203a0f66; WORD $0x3a24; BYTE $0x02 // pinsrb xmm4, byte [rdx + rdi], 2 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - LONG $0x203a0f66; WORD $0x1a24; BYTE $0x03 // pinsrb xmm4, byte [rdx + rbx], 3 - QUAD $0x040a24203a0f4266 // pinsrb xmm4, byte [rdx + r9], 4 - QUAD $0x051224203a0f4266 // pinsrb xmm4, byte [rdx + r10], 5 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - LONG $0x203a0f66; WORD $0x0224; BYTE $0x06 // pinsrb xmm4, byte [rdx + rax], 6 - QUAD $0x073224203a0f4266 // pinsrb xmm4, byte [rdx + r14], 7 - QUAD $0x083a24203a0f4266 // pinsrb xmm4, byte [rdx + r15], 8 - QUAD $0x092a24203a0f4266 // pinsrb xmm4, byte [rdx + r13], 9 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - LONG $0x2464894c; BYTE $0x38 // mov qword [rsp + 56], r12 - QUAD $0x0a2224203a0f4266 // pinsrb xmm4, byte [rdx + r12], 10 - QUAD $0x0b1a24203a0f4266 // pinsrb xmm4, byte [rdx + r11], 11 - QUAD $0x0c0224203a0f4266 // pinsrb xmm4, byte [rdx + r8], 12 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - LONG $0x203a0f66; WORD $0x0224; BYTE $0x0d // pinsrb xmm4, byte [rdx + rax], 13 - LONG $0x203a0f66; WORD $0x0a24; BYTE $0x0e // pinsrb xmm4, byte [rdx + rcx], 14 - LONG $0x203a0f66; WORD $0x3224; BYTE $0x0f // pinsrb xmm4, byte [rdx + rsi], 15 - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - QUAD $0x01225c203a0f4266; BYTE $0x01 // pinsrb xmm3, byte [rdx + r12 + 1], 1 - QUAD $0x02013a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 1], 2 - QUAD $0x03011a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 1], 3 - QUAD $0x010a5c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdx + r9 + 1], 4 - QUAD $0x01125c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdx + r10 + 1], 5 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx + LONG $0x01e00d48; WORD $0x0000 // or rax, 480 + LONG $0x24448948; BYTE $0x28 // mov qword [rsp + 40], rax + QUAD $0x003d64203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r13 + rdi], 1 + LONG $0x2444894c; BYTE $0x18 // mov qword [rsp + 24], r8 + QUAD $0x000564203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r13 + r8], 2 + LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 + QUAD $0x003564203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r13 + r14], 3 + QUAD $0x003d64203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r13 + r15], 4 + LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 + QUAD $0x001564203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r13 + r10], 5 + QUAD $0x001d64203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r13 + r11], 6 + QUAD $0x002564203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r13 + r12], 7 + LONG $0x244c894c; BYTE $0x58 // mov qword [rsp + 88], r9 + QUAD $0x000d64203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r13 + r9], 8 + QUAD $0x001564203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r13 + rdx], 9 + WORD $0x8949; BYTE $0xd8 // mov r8, rbx + QUAD $0x001d64203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r13 + rbx], 10 LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x06011a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 1], 6 - QUAD $0x01325c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdx + r14 + 1], 7 - LONG $0x247c8b48; BYTE $0x58 // mov rdi, qword [rsp + 88] - QUAD $0x08013a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 1], 8 - QUAD $0x012a5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdx + r13 + 1], 9 - QUAD $0x013a5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r15 + 1], 10 - QUAD $0x011a5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r11 + 1], 11 - WORD $0x894d; BYTE $0xdf // mov r15, r11 - QUAD $0x01025c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r8 + 1], 12 - LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] - QUAD $0x012a5c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdx + r13 + 1], 13 - QUAD $0x0e010a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 1], 14 - QUAD $0x000090248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 144] + QUAD $0x001d64203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r13 + rbx], 11 + QUAD $0x003564203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r13 + rsi], 12 + LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] + QUAD $0x000564203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r13 + rax], 13 + QUAD $0x000d64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r13 + rcx], 14 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x000564203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r13 + rax], 15 + QUAD $0x013d5c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r13 + rdi + 1], 1 + LONG $0x247c8948; BYTE $0x38 // mov qword [rsp + 56], rdi + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x01055c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r13 + rax + 1], 2 + QUAD $0x01355c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r13 + r14 + 1], 3 + QUAD $0x013d5c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r13 + r15 + 1], 4 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x01155c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r13 + r10 + 1], 5 + QUAD $0x011d5c203a0f4366; BYTE $0x06 // pinsrb xmm3, byte [r13 + r11 + 1], 6 + WORD $0x894d; BYTE $0xda // mov r10, r11 + QUAD $0x01255c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r13 + r12 + 1], 7 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x010d5c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r13 + r9 + 1], 8 + QUAD $0x01155c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r13 + rdx + 1], 9 + QUAD $0x01055c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r13 + r8 + 1], 10 + QUAD $0x011d5c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r13 + rbx + 1], 11 + WORD $0x8948; BYTE $0xda // mov rdx, rbx + QUAD $0x01355c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r13 + rsi + 1], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x01355c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r13 + rsi + 1], 13 + QUAD $0x010d5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r13 + rcx + 1], 14 + QUAD $0x0000a0248c6f0f66; BYTE $0x00 // movdqa xmm1, oword [rsp + 160] LONG $0xe1640f66 // pcmpgtb xmm4, xmm1 - QUAD $0x0f01325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 1], 15 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x01055c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r13 + rax + 1], 15 LONG $0xd9640f66 // pcmpgtb xmm3, xmm1 QUAD $0x00000100856f0f66 // movdqa xmm0, oword 256[rbp] /* [rip + .LCPI11_16] */ LONG $0xd8df0f66 // pandn xmm3, xmm0 LONG $0xdcfc0f66 // paddb xmm3, xmm4 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - LONG $0x0274b60f; BYTE $0x10 // movzx esi, byte [rdx + rax + 16] + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + LONG $0x74b60f41; WORD $0x100d // movzx esi, byte [r13 + rcx + 16] LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0102026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 2], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0202026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 2], 2 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - QUAD $0x021a6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r11 + 2], 3 - QUAD $0x020a6c203a0f4266; BYTE $0x04 // pinsrb xmm5, byte [rdx + r9 + 2], 4 - QUAD $0x02126c203a0f4266; BYTE $0x05 // pinsrb xmm5, byte [rdx + r10 + 2], 5 - QUAD $0x06021a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 2], 6 - LONG $0x2474894c; BYTE $0x68 // mov qword [rsp + 104], r14 - QUAD $0x02326c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r14 + 2], 7 - WORD $0x8949; BYTE $0xfc // mov r12, rdi - QUAD $0x08023a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 2], 8 - LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] - QUAD $0x02026c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r8 + 2], 9 - LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] - QUAD $0x0a023a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 2], 10 - QUAD $0x000000b024bc894c // mov qword [rsp + 176], r15 - QUAD $0x023a6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdx + r15 + 2], 11 + QUAD $0x023d6c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r13 + rdi + 2], 1 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x02256c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r13 + r12 + 2], 2 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x021d6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r13 + r11 + 2], 3 + LONG $0x2474894c; BYTE $0x78 // mov qword [rsp + 120], r14 + QUAD $0x02356c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r13 + r14 + 2], 4 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x021d6c203a0f4166; BYTE $0x05 // pinsrb xmm5, byte [r13 + rbx + 2], 5 + WORD $0x894d; BYTE $0xd1 // mov r9, r10 + QUAD $0x02156c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r13 + r10 + 2], 6 + WORD $0x894d; BYTE $0xfa // mov r10, r15 + QUAD $0x023d6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r13 + r15 + 2], 7 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x023d6c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r13 + r15 + 2], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x02056c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r13 + rax + 2], 9 + LONG $0x2444894c; BYTE $0x50 // mov qword [rsp + 80], r8 + QUAD $0x02056c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r13 + r8 + 2], 10 + QUAD $0x02156c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r13 + rdx + 2], 11 LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0c020a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 2], 12 - WORD $0x894c; BYTE $0xee // mov rsi, r13 - QUAD $0x022a6c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdx + r13 + 2], 13 - LONG $0x246c8b4c; BYTE $0x28 // mov r13, qword [rsp + 40] - QUAD $0x022a6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdx + r13 + 2], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f02026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 2], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0103027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 3], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0203027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 3], 2 - QUAD $0x031a7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r11 + 3], 3 - QUAD $0x030a7c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdx + r9 + 3], 4 - QUAD $0x03127c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdx + r10 + 3], 5 - QUAD $0x06031a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 3], 6 - QUAD $0x03327c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdx + r14 + 3], 7 - QUAD $0x03227c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdx + r12 + 3], 8 - QUAD $0x03027c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdx + r8 + 3], 9 - QUAD $0x0a033a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 3], 10 - QUAD $0x033a7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdx + r15 + 3], 11 - QUAD $0x0c030a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 3], 12 - QUAD $0x0d03327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 3], 13 - QUAD $0x032a7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdx + r13 + 3], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f03027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 3], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x04024c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rax + 4], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x04024c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rax + 4], 2 - QUAD $0x041a4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdx + r11 + 4], 3 - QUAD $0x040a4c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdx + r9 + 4], 4 - QUAD $0x00000080248c894c // mov qword [rsp + 128], r9 - QUAD $0x04124c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdx + r10 + 4], 5 - QUAD $0x041a4c203a0f4466; BYTE $0x06 // pinsrb xmm9, byte [rdx + rbx + 4], 6 - QUAD $0x04324c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdx + r14 + 4], 7 - QUAD $0x04224c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r12 + 4], 8 - QUAD $0x04024c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdx + r8 + 4], 9 - QUAD $0x043a4c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rdx + rdi + 4], 10 - QUAD $0x043a4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdx + r15 + 4], 11 - QUAD $0x040a4c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rdx + rcx + 4], 12 - QUAD $0x04324c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdx + rsi + 4], 13 - QUAD $0x042a4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r13 + 4], 14 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x04024c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rdx + rax + 4], 15 - WORD $0x8949; BYTE $0xc5 // mov r13, rax + QUAD $0x020d6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r13 + rcx + 2], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x02356c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r13 + rsi + 2], 13 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x02156c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r13 + rdx + 2], 14 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x023d6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r13 + rdi + 2], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x03057c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r13 + rax + 3], 1 + QUAD $0x03257c203a0f4366; BYTE $0x02 // pinsrb xmm7, byte [r13 + r12 + 3], 2 + QUAD $0x031d7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r13 + r11 + 3], 3 + QUAD $0x03357c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r13 + r14 + 3], 4 + QUAD $0x031d7c203a0f4166; BYTE $0x05 // pinsrb xmm7, byte [r13 + rbx + 3], 5 + QUAD $0x030d7c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r13 + r9 + 3], 6 + QUAD $0x03157c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r13 + r10 + 3], 7 + QUAD $0x033d7c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r13 + r15 + 3], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x03057c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r13 + rax + 3], 9 + QUAD $0x03057c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r13 + r8 + 3], 10 + LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] + QUAD $0x03057c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r13 + rax + 3], 11 + QUAD $0x030d7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r13 + rcx + 3], 12 + QUAD $0x03357c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r13 + rsi + 3], 13 + QUAD $0x03157c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r13 + rdx + 3], 14 + QUAD $0x033d7c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r13 + rdi + 3], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x04054c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r13 + rax + 4], 1 + QUAD $0x04254c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r13 + r12 + 4], 2 + QUAD $0x041d4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r13 + r11 + 4], 3 + QUAD $0x04354c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r14 + 4], 4 + QUAD $0x041d4c203a0f4566; BYTE $0x05 // pinsrb xmm9, byte [r13 + rbx + 4], 5 + QUAD $0x040d4c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r13 + r9 + 4], 6 + QUAD $0x04154c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r13 + r10 + 4], 7 + QUAD $0x043d4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r13 + r15 + 4], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x04054c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r13 + rax + 4], 9 + QUAD $0x04054c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r13 + r8 + 4], 10 + LONG $0x24448b4c; BYTE $0x40 // mov r8, qword [rsp + 64] + QUAD $0x04054c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r13 + r8 + 4], 11 + QUAD $0x040d4c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r13 + rcx + 4], 12 + QUAD $0x04354c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r13 + rsi + 4], 13 + QUAD $0x04154c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r13 + rdx + 4], 14 + QUAD $0x043d4c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r13 + rdi + 4], 15 LONG $0xe9640f66 // pcmpgtb xmm5, xmm1 QUAD $0x00000110856f0f66 // movdqa xmm0, oword 272[rbp] /* [rip + .LCPI11_17] */ LONG $0xe8df0f66 // pandn xmm5, xmm0 @@ -57223,89 +59913,89 @@ LBB11_86: QUAD $0x00000120856f0f66 // movdqa xmm0, oword 288[rbp] /* [rip + .LCPI11_18] */ LONG $0xf8df0f66 // pandn xmm7, xmm0 LONG $0xfdeb0f66 // por xmm7, xmm5 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - LONG $0x0274b60f; BYTE $0x11 // movzx esi, byte [rdx + rax + 17] + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + LONG $0x74b60f41; WORD $0x1115 // movzx esi, byte [r13 + rdx + 17] LONG $0xe66e0f66 // movd xmm4, esi LONG $0x640f4466; BYTE $0xc9 // pcmpgtb xmm9, xmm1 QUAD $0x00000130856f0f66 // movdqa xmm0, oword 304[rbp] /* [rip + .LCPI11_19] */ LONG $0xdf0f4466; BYTE $0xc8 // pandn xmm9, xmm0 LONG $0xeb0f4466; BYTE $0xcf // por xmm9, xmm7 - LONG $0x0274b60f; BYTE $0x12 // movzx esi, byte [rdx + rax + 18] + LONG $0x74b60f41; WORD $0x1215 // movzx esi, byte [r13 + rdx + 18] LONG $0xfe6e0f66 // movd xmm7, esi LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 LONG $0xd8f80f66 // psubb xmm3, xmm0 LONG $0xeb0f4466; BYTE $0xcb // por xmm9, xmm3 - LONG $0x0274b60f; BYTE $0x13 // movzx esi, byte [rdx + rax + 19] + LONG $0x74b60f41; WORD $0x1315 // movzx esi, byte [r13 + rdx + 19] LONG $0xee6e0f66 // movd xmm5, esi - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - QUAD $0x050254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r8 + 5], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x02053a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 5], 2 - QUAD $0x051a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r11 + 5], 3 - QUAD $0x050a54203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r9 + 5], 4 - QUAD $0x051254203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdx + r10 + 5], 5 - WORD $0x894d; BYTE $0xd4 // mov r12, r10 - WORD $0x8949; BYTE $0xde // mov r14, rbx - QUAD $0x06051a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 5], 6 - LONG $0x245c8b48; BYTE $0x68 // mov rbx, qword [rsp + 104] - QUAD $0x07051a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 5], 7 - LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] - QUAD $0x053a54203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r15 + 5], 8 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - QUAD $0x050a54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r9 + 5], 9 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0a053254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 5], 10 - QUAD $0x000000b0249c8b4c // mov r11, qword [rsp + 176] - QUAD $0x051a54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r11 + 5], 11 - QUAD $0x0c050a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 5], 12 - LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] - QUAD $0x051254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r10 + 5], 13 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e050254203a0f66 // pinsrb xmm2, byte [rdx + rax + 5], 14 - QUAD $0x052a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r13 + 5], 15 - QUAD $0x060244203a0f4666; BYTE $0x01 // pinsrb xmm8, byte [rdx + r8 + 6], 1 - QUAD $0x063a44203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdx + rdi + 6], 2 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x062a44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r13 + 6], 3 - QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] - QUAD $0x062a44203a0f4666; BYTE $0x04 // pinsrb xmm8, byte [rdx + r13 + 6], 4 - QUAD $0x062244203a0f4666; BYTE $0x05 // pinsrb xmm8, byte [rdx + r12 + 6], 5 - QUAD $0x063244203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdx + r14 + 6], 6 - QUAD $0x061a44203a0f4466; BYTE $0x07 // pinsrb xmm8, byte [rdx + rbx + 6], 7 - QUAD $0x063a44203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdx + r15 + 6], 8 - QUAD $0x060a44203a0f4666; BYTE $0x09 // pinsrb xmm8, byte [rdx + r9 + 6], 9 - QUAD $0x063244203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdx + rsi + 6], 10 - QUAD $0x061a44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r11 + 6], 11 - WORD $0x894d; BYTE $0xdf // mov r15, r11 - QUAD $0x060a44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rdx + rcx + 6], 12 - QUAD $0x061244203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rdx + r10 + 6], 13 - QUAD $0x060244203a0f4466; BYTE $0x0e // pinsrb xmm8, byte [rdx + rax + 6], 14 - WORD $0x8949; BYTE $0xc2 // mov r10, rax - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x060244203a0f4466; BYTE $0x0f // pinsrb xmm8, byte [rdx + rax + 6], 15 - QUAD $0x070274203a0f4666; BYTE $0x01 // pinsrb xmm14, byte [rdx + r8 + 7], 1 - QUAD $0x073a74203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rdx + rdi + 7], 2 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x070274203a0f4466; BYTE $0x03 // pinsrb xmm14, byte [rdx + rax + 7], 3 - WORD $0x894d; BYTE $0xe9 // mov r9, r13 - QUAD $0x072a74203a0f4666; BYTE $0x04 // pinsrb xmm14, byte [rdx + r13 + 7], 4 - WORD $0x894c; BYTE $0xe7 // mov rdi, r12 - QUAD $0x072274203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rdx + r12 + 7], 5 - QUAD $0x073274203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdx + r14 + 7], 6 - QUAD $0x071a74203a0f4466; BYTE $0x07 // pinsrb xmm14, byte [rdx + rbx + 7], 7 - WORD $0x8949; BYTE $0xdb // mov r11, rbx - LONG $0x24648b4c; BYTE $0x58 // mov r12, qword [rsp + 88] - QUAD $0x072274203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdx + r12 + 7], 8 - LONG $0x246c8b4c; BYTE $0x50 // mov r13, qword [rsp + 80] - QUAD $0x072a74203a0f4666; BYTE $0x09 // pinsrb xmm14, byte [rdx + r13 + 7], 9 - QUAD $0x073274203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdx + rsi + 7], 10 - QUAD $0x073a74203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdx + r15 + 7], 11 - QUAD $0x070a74203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rdx + rcx + 7], 12 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x051554203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r13 + rdx + 5], 1 + QUAD $0x052554203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r13 + r12 + 5], 2 + QUAD $0x051d54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r13 + r11 + 5], 3 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x053554203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r13 + r14 + 5], 4 + QUAD $0x051d54203a0f4166; BYTE $0x05 // pinsrb xmm2, byte [r13 + rbx + 5], 5 + QUAD $0x050d54203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r13 + r9 + 5], 6 + WORD $0x894d; BYTE $0xcf // mov r15, r9 + WORD $0x894d; BYTE $0xd3 // mov r11, r10 + QUAD $0x000000d02494894c // mov qword [rsp + 208], r10 + QUAD $0x051554203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r13 + r10 + 5], 7 + LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] + QUAD $0x051554203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r13 + r10 + 5], 8 + QUAD $0x050554203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r13 + rax + 5], 9 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x053554203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r13 + rsi + 5], 10 + WORD $0x894c; BYTE $0xc7 // mov rdi, r8 + QUAD $0x050554203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r13 + r8 + 5], 11 + QUAD $0x050d54203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r13 + rcx + 5], 12 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x050554203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r13 + r8 + 5], 13 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x051d54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r13 + rbx + 5], 14 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x050d54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r13 + r9 + 5], 15 + QUAD $0x061544203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r13 + rdx + 6], 1 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x062544203a0f4766; BYTE $0x02 // pinsrb xmm8, byte [r13 + r12 + 6], 2 LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x071a74203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdx + rbx + 7], 13 - QUAD $0x071274203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdx + r10 + 7], 14 + QUAD $0x061d44203a0f4566; BYTE $0x03 // pinsrb xmm8, byte [r13 + rbx + 6], 3 + QUAD $0x063544203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r13 + r14 + 6], 4 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x245c8b48; BYTE $0x70 // mov rbx, qword [rsp + 112] + QUAD $0x061d44203a0f4566; BYTE $0x05 // pinsrb xmm8, byte [r13 + rbx + 6], 5 + QUAD $0x063d44203a0f4766; BYTE $0x06 // pinsrb xmm8, byte [r13 + r15 + 6], 6 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + QUAD $0x061d44203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r13 + r11 + 6], 7 + QUAD $0x061544203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r13 + r10 + 6], 8 + QUAD $0x060544203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r13 + rax + 6], 9 + QUAD $0x063544203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r13 + rsi + 6], 10 + QUAD $0x063d44203a0f4566; BYTE $0x0b // pinsrb xmm8, byte [r13 + rdi + 6], 11 + QUAD $0x060d44203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r13 + rcx + 6], 12 + QUAD $0x060544203a0f4766; BYTE $0x0d // pinsrb xmm8, byte [r13 + r8 + 6], 13 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x061d44203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r13 + rbx + 6], 14 + QUAD $0x060d44203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r13 + r9 + 6], 15 + QUAD $0x071574203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r13 + rdx + 7], 1 + LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] + QUAD $0x071d74203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r13 + r11 + 7], 2 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x071574203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r13 + rdx + 7], 3 + WORD $0x894c; BYTE $0xe2 // mov rdx, r12 + QUAD $0x072574203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r13 + r12 + 7], 4 + LONG $0x247c8b4c; BYTE $0x70 // mov r15, qword [rsp + 112] + QUAD $0x073d74203a0f4766; BYTE $0x05 // pinsrb xmm14, byte [r13 + r15 + 7], 5 + QUAD $0x073574203a0f4766; BYTE $0x06 // pinsrb xmm14, byte [r13 + r14 + 7], 6 + QUAD $0x000000d024948b4c // mov r10, qword [rsp + 208] + QUAD $0x071574203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r13 + r10 + 7], 7 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x071574203a0f4566; BYTE $0x08 // pinsrb xmm14, byte [r13 + rdx + 7], 8 + QUAD $0x070574203a0f4566; BYTE $0x09 // pinsrb xmm14, byte [r13 + rax + 7], 9 + QUAD $0x073574203a0f4566; BYTE $0x0a // pinsrb xmm14, byte [r13 + rsi + 7], 10 + QUAD $0x073d74203a0f4566; BYTE $0x0b // pinsrb xmm14, byte [r13 + rdi + 7], 11 + QUAD $0x070d74203a0f4566; BYTE $0x0c // pinsrb xmm14, byte [r13 + rcx + 7], 12 + QUAD $0x070574203a0f4766; BYTE $0x0d // pinsrb xmm14, byte [r13 + r8 + 7], 13 + QUAD $0x071d74203a0f4566; BYTE $0x0e // pinsrb xmm14, byte [r13 + rbx + 7], 14 LONG $0x6f0f4166; BYTE $0xce // movdqa xmm1, xmm14 - QUAD $0x009024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 144] + QUAD $0x00a024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 160] LONG $0x640f4166; BYTE $0xd6 // pcmpgtb xmm2, xmm14 QUAD $0x00000140856f0f66 // movdqa xmm0, oword 320[rbp] /* [rip + .LCPI11_20] */ LONG $0xd0df0f66 // pandn xmm2, xmm0 @@ -57313,377 +60003,378 @@ LBB11_86: QUAD $0x00000150856f0f66 // movdqa xmm0, oword 336[rbp] /* [rip + .LCPI11_21] */ LONG $0xdf0f4466; BYTE $0xc0 // pandn xmm8, xmm0 LONG $0xeb0f4466; BYTE $0xc2 // por xmm8, xmm2 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - LONG $0x0274b60f; BYTE $0x14 // movzx esi, byte [rdx + rax + 20] + LONG $0x24548b48; BYTE $0x68 // mov rdx, qword [rsp + 104] + LONG $0x74b60f41; WORD $0x1415 // movzx esi, byte [r13 + rdx + 20] LONG $0xde6e0f66 // movd xmm3, esi - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0f070a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 7], 15 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x07054c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r13 + rax + 7], 15 LONG $0x640f4166; BYTE $0xce // pcmpgtb xmm1, xmm14 LONG $0x456f0f66; BYTE $0x60 // movdqa xmm0, oword 96[rbp] /* [rip + .LCPI11_6] */ LONG $0xc8df0f66 // pandn xmm1, xmm0 LONG $0xeb0f4166; BYTE $0xc8 // por xmm1, xmm8 - LONG $0x0274b60f; BYTE $0x15 // movzx esi, byte [rdx + rax + 21] + LONG $0x74b60f41; WORD $0x1515 // movzx esi, byte [r13 + rdx + 21] LONG $0xd66e0f66 // movd xmm2, esi - QUAD $0x0000c024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 192] - QUAD $0x080244203a0f4266; BYTE $0x01 // pinsrb xmm0, byte [rdx + r8 + 8], 1 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x083244203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdx + r14 + 8], 2 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x03083244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 8], 3 - QUAD $0x080a44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdx + r9 + 8], 4 - QUAD $0x05083a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 8], 5 - WORD $0x8949; BYTE $0xfa // mov r10, rdi - LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] - QUAD $0x06083a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 8], 6 - QUAD $0x081a44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r11 + 8], 7 - QUAD $0x082244203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r12 + 8], 8 - QUAD $0x082a44203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdx + r13 + 8], 9 - LONG $0x24448b4c; BYTE $0x38 // mov r8, qword [rsp + 56] - QUAD $0x080244203a0f4266; BYTE $0x0a // pinsrb xmm0, byte [rdx + r8 + 8], 10 - QUAD $0x083a44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r15 + 8], 11 + QUAD $0x0000e024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 224] + LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] + QUAD $0x081d44203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r13 + rbx + 8], 1 + QUAD $0x081d44203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r13 + r11 + 8], 2 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x080d44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r13 + rcx + 8], 3 + QUAD $0x082544203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r13 + r12 + 8], 4 + QUAD $0x083d44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r13 + r15 + 8], 5 + QUAD $0x083544203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r13 + r14 + 8], 6 + WORD $0x894d; BYTE $0xf1 // mov r9, r14 + QUAD $0x081544203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r13 + r10 + 8], 7 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x083544203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r13 + rsi + 8], 8 + LONG $0x247c8b48; BYTE $0x48 // mov rdi, qword [rsp + 72] + QUAD $0x083d44203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r13 + rdi + 8], 9 + LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] + QUAD $0x082544203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r13 + r12 + 8], 10 + LONG $0x24748b48; BYTE $0x40 // mov rsi, qword [rsp + 64] + QUAD $0x083544203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r13 + rsi + 8], 11 LONG $0x24748b48; BYTE $0x60 // mov rsi, qword [rsp + 96] - QUAD $0x0c083244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 8], 12 - QUAD $0x0d081a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 8], 13 - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0e083244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 8], 14 - QUAD $0x0f080a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 8], 15 + QUAD $0x083544203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r13 + rsi + 8], 12 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x080544203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r13 + r8 + 8], 13 + LONG $0x24748b4c; BYTE $0x10 // mov r14, qword [rsp + 16] + QUAD $0x083544203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r13 + r14 + 8], 14 + QUAD $0x080544203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r13 + rax + 8], 15 LONG $0xeb0f4166; BYTE $0xc9 // por xmm1, xmm9 - QUAD $0x0000c0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm1 - LONG $0x0274b60f; BYTE $0x16 // movzx esi, byte [rdx + rax + 22] - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x640f4166; BYTE $0xc6 // pcmpgtb xmm0, xmm14 - LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] - QUAD $0x091a5c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdx + r11 + 9], 1 - WORD $0x894c; BYTE $0xdb // mov rbx, r11 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - QUAD $0x09325c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rdx + r14 + 9], 2 - LONG $0x245c8b4c; BYTE $0x18 // mov r11, qword [rsp + 24] - QUAD $0x091a5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r11 + 9], 3 - QUAD $0x090a5c203a0f4666; BYTE $0x04 // pinsrb xmm11, byte [rdx + r9 + 9], 4 - LONG $0x2454894c; BYTE $0x70 // mov qword [rsp + 112], r10 - QUAD $0x09125c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdx + r10 + 9], 5 - QUAD $0x093a5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rdx + rdi + 9], 6 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - QUAD $0x09325c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdx + r14 + 9], 7 - QUAD $0x09225c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r12 + 9], 8 - QUAD $0x092a5c203a0f4666; BYTE $0x09 // pinsrb xmm11, byte [rdx + r13 + 9], 9 - WORD $0x894c; BYTE $0xc6 // mov rsi, r8 - QUAD $0x09025c203a0f4666; BYTE $0x0a // pinsrb xmm11, byte [rdx + r8 + 9], 10 - WORD $0x894c; BYTE $0xf9 // mov rcx, r15 - QUAD $0x093a5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r15 + 9], 11 - LONG $0x24448b4c; BYTE $0x60 // mov r8, qword [rsp + 96] - QUAD $0x09025c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r8 + 9], 12 - LONG $0x247c8b4c; BYTE $0x30 // mov r15, qword [rsp + 48] - QUAD $0x093a5c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdx + r15 + 9], 13 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x093a5c203a0f4466; BYTE $0x0e // pinsrb xmm11, byte [rdx + rdi + 9], 14 - LONG $0x247c8b48; BYTE $0x10 // mov rdi, qword [rsp + 16] - QUAD $0x093a5c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdx + rdi + 9], 15 - QUAD $0x0a1a64203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdx + rbx + 10], 1 - QUAD $0x0a0264203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rax + 10], 2 - QUAD $0x0a1a64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r11 + 10], 3 - QUAD $0x0a0a64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdx + r9 + 10], 4 - QUAD $0x0a1264203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdx + r10 + 10], 5 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0a1a64203a0f4466; BYTE $0x06 // pinsrb xmm12, byte [rdx + rbx + 10], 6 - QUAD $0x0a3264203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdx + r14 + 10], 7 - QUAD $0x0a2264203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r12 + 10], 8 - QUAD $0x0a2a64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdx + r13 + 10], 9 - QUAD $0x0a3264203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdx + rsi + 10], 10 - QUAD $0x0a0a64203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rdx + rcx + 10], 11 - QUAD $0x0a0264203a0f4666; BYTE $0x0c // pinsrb xmm12, byte [rdx + r8 + 10], 12 - QUAD $0x0a3a64203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdx + r15 + 10], 13 - WORD $0x894d; BYTE $0xfb // mov r11, r15 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0a3a64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r15 + 10], 14 - QUAD $0x0a3a64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdx + rdi + 10], 15 - LONG $0x245c8b48; BYTE $0x08 // mov rbx, qword [rsp + 8] - QUAD $0x0b1a6c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdx + rbx + 11], 1 - QUAD $0x0b026c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rax + 11], 2 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0b026c203a0f4466; BYTE $0x03 // pinsrb xmm13, byte [rdx + rax + 11], 3 - QUAD $0x0b0a6c203a0f4666; BYTE $0x04 // pinsrb xmm13, byte [rdx + r9 + 11], 4 - QUAD $0x0b126c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rdx + r10 + 11], 5 - LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] - QUAD $0x0b126c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdx + r10 + 11], 6 - QUAD $0x0b326c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdx + r14 + 11], 7 - QUAD $0x0b226c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r12 + 11], 8 - QUAD $0x0b2a6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdx + r13 + 11], 9 - QUAD $0x0b326c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdx + rsi + 11], 10 - QUAD $0x0b0a6c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rdx + rcx + 11], 11 - QUAD $0x0b026c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r8 + 11], 12 - QUAD $0x0b1a6c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdx + r11 + 11], 13 - QUAD $0x0b3a6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r15 + 11], 14 - QUAD $0x0b3a6c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdx + rdi + 11], 15 + QUAD $0x0000e0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm1 + LONG $0x74b60f41; WORD $0x1615 // movzx esi, byte [r13 + rdx + 22] + LONG $0xce6e0f66 // movd xmm1, esi + LONG $0x640f4166; BYTE $0xc6 // pcmpgtb xmm0, xmm14 + QUAD $0x091d5c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r13 + rbx + 9], 1 + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x091d5c203a0f4766; BYTE $0x02 // pinsrb xmm11, byte [r13 + r11 + 9], 2 + QUAD $0x090d5c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r13 + rcx + 9], 3 + LONG $0x245c8b4c; BYTE $0x78 // mov r11, qword [rsp + 120] + QUAD $0x091d5c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r13 + r11 + 9], 4 + QUAD $0x093d5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r13 + r15 + 9], 5 + QUAD $0x00000080248c894c // mov qword [rsp + 128], r9 + QUAD $0x090d5c203a0f4766; BYTE $0x06 // pinsrb xmm11, byte [r13 + r9 + 9], 6 + QUAD $0x09155c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r13 + r10 + 9], 7 + LONG $0x247c8b4c; BYTE $0x58 // mov r15, qword [rsp + 88] + QUAD $0x093d5c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r13 + r15 + 9], 8 + WORD $0x8948; BYTE $0xfe // mov rsi, rdi + QUAD $0x093d5c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r13 + rdi + 9], 9 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x09255c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r13 + r12 + 9], 10 + LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] + QUAD $0x093d5c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r13 + rdi + 9], 11 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x09155c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r13 + rdx + 9], 12 + QUAD $0x09055c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r13 + r8 + 9], 13 + QUAD $0x09355c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r13 + r14 + 9], 14 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x09055c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r13 + r8 + 9], 15 + QUAD $0x0a1d64203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r13 + rbx + 10], 1 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x0a2564203a0f4766; BYTE $0x02 // pinsrb xmm12, byte [r13 + r12 + 10], 2 + QUAD $0x0a0d64203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r13 + rcx + 10], 3 + QUAD $0x0a1d64203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r13 + r11 + 10], 4 + LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] + QUAD $0x0a0d64203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r13 + rcx + 10], 5 + QUAD $0x0a0d64203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r13 + r9 + 10], 6 + QUAD $0x0a1564203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r13 + r10 + 10], 7 + QUAD $0x0a3d64203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r13 + r15 + 10], 8 + QUAD $0x0a3564203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r13 + rsi + 10], 9 + QUAD $0x0a0564203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r13 + rax + 10], 10 + QUAD $0x0a3d64203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r13 + rdi + 10], 11 + QUAD $0x0a1564203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r13 + rdx + 10], 12 + LONG $0x24648b4c; BYTE $0x20 // mov r12, qword [rsp + 32] + QUAD $0x0a2564203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r13 + r12 + 10], 13 + QUAD $0x0a3564203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r13 + r14 + 10], 14 + WORD $0x894d; BYTE $0xf2 // mov r10, r14 + QUAD $0x0a0564203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r13 + r8 + 10], 15 + QUAD $0x0b1d6c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r13 + rbx + 11], 1 + WORD $0x8949; BYTE $0xdb // mov r11, rbx + LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] + QUAD $0x0b1d6c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r13 + rbx + 11], 2 + LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] + QUAD $0x0b1d6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r13 + rbx + 11], 3 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x0b356c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r13 + r14 + 11], 4 + QUAD $0x0b0d6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r13 + rcx + 11], 5 + QUAD $0x0b0d6c203a0f4766; BYTE $0x06 // pinsrb xmm13, byte [r13 + r9 + 11], 6 + QUAD $0x000000d0248c8b4c // mov r9, qword [rsp + 208] + QUAD $0x0b0d6c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r13 + r9 + 11], 7 + QUAD $0x0b3d6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r13 + r15 + 11], 8 + QUAD $0x0b356c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r13 + rsi + 11], 9 + QUAD $0x0b056c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r13 + rax + 11], 10 + QUAD $0x0b3d6c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r13 + rdi + 11], 11 + QUAD $0x0b156c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r13 + rdx + 11], 12 + QUAD $0x0b256c203a0f4766; BYTE $0x0d // pinsrb xmm13, byte [r13 + r12 + 11], 13 + QUAD $0x0b156c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r13 + r10 + 11], 14 + QUAD $0x0b056c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r13 + r8 + 11], 15 LONG $0x640f4566; BYTE $0xde // pcmpgtb xmm11, xmm14 QUAD $0x0001009ddf0f4466; BYTE $0x00 // pandn xmm11, oword 256[rbp] /* [rip + .LCPI11_16] */ LONG $0xfc0f4466; BYTE $0xd8 // paddb xmm11, xmm0 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - LONG $0x0a74b60f; BYTE $0x17 // movzx esi, byte [rdx + rcx + 23] + LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] + LONG $0x74b60f41; WORD $0x173d // movzx esi, byte [r13 + rdi + 23] LONG $0x6e0f4466; BYTE $0xc6 // movd xmm8, esi LONG $0x640f4566; BYTE $0xe6 // pcmpgtb xmm12, xmm14 QUAD $0x000110a5df0f4466; BYTE $0x00 // pandn xmm12, oword 272[rbp] /* [rip + .LCPI11_17] */ LONG $0x640f4566; BYTE $0xee // pcmpgtb xmm13, xmm14 QUAD $0x000120addf0f4466; BYTE $0x00 // pandn xmm13, oword 288[rbp] /* [rip + .LCPI11_18] */ LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - LONG $0x0a74b60f; BYTE $0x18 // movzx esi, byte [rdx + rcx + 24] + LONG $0x74b60f41; WORD $0x183d // movzx esi, byte [r13 + rdi + 24] LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - QUAD $0x00d0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 208] - QUAD $0x0c1a4c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rbx + 12], 1 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0c3a4c203a0f4666; BYTE $0x02 // pinsrb xmm9, byte [rdx + r15 + 12], 2 - WORD $0x8949; BYTE $0xc3 // mov r11, rax - QUAD $0x0c024c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rdx + rax + 12], 3 - WORD $0x894c; BYTE $0xcf // mov rdi, r9 - QUAD $0x0c0a4c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdx + r9 + 12], 4 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x0c0a4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdx + r9 + 12], 5 - WORD $0x894c; BYTE $0xd3 // mov rbx, r10 - QUAD $0x0c124c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdx + r10 + 12], 6 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - QUAD $0x0c324c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdx + r14 + 12], 7 - WORD $0x894d; BYTE $0xe6 // mov r14, r12 - QUAD $0x0c224c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r12 + 12], 8 - WORD $0x894d; BYTE $0xec // mov r12, r13 - QUAD $0x0c2a4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdx + r13 + 12], 9 - LONG $0x246c8b4c; BYTE $0x38 // mov r13, qword [rsp + 56] - QUAD $0x0c2a4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdx + r13 + 12], 10 - QUAD $0x000000b0248c8b48 // mov rcx, qword [rsp + 176] - QUAD $0x0c0a4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdx + rcx + 12], 11 - QUAD $0x0c024c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdx + r8 + 12], 12 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0c324c203a0f4466; BYTE $0x0d // pinsrb xmm9, byte [rdx + rsi + 12], 13 + QUAD $0x00f0248c6f0f4466; WORD $0x0000 // movdqa xmm9, oword [rsp + 240] + QUAD $0x0c1d4c203a0f4766; BYTE $0x01 // pinsrb xmm9, byte [r13 + r11 + 12], 1 + LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] + QUAD $0x0c254c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r13 + r12 + 12], 2 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x0c1d4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r13 + r11 + 12], 3 + QUAD $0x0c354c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r14 + 12], 4 + WORD $0x8948; BYTE $0xcb // mov rbx, rcx + QUAD $0x0c0d4c203a0f4566; BYTE $0x05 // pinsrb xmm9, byte [r13 + rcx + 12], 5 + QUAD $0x0000008024848b4c // mov r8, qword [rsp + 128] + QUAD $0x0c054c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r13 + r8 + 12], 6 + WORD $0x894d; BYTE $0xca // mov r10, r9 + QUAD $0x0c0d4c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r13 + r9 + 12], 7 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x0c3d4c203a0f4766; BYTE $0x08 // pinsrb xmm9, byte [r13 + r15 + 12], 8 + LONG $0x247c8b4c; BYTE $0x48 // mov r15, qword [rsp + 72] + QUAD $0x0c3d4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r13 + r15 + 12], 9 + WORD $0x8948; BYTE $0xc7 // mov rdi, rax + QUAD $0x0c054c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r13 + rax + 12], 10 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x0c0d4c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r13 + rcx + 12], 11 + QUAD $0x0c154c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r13 + rdx + 12], 12 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0c354c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r13 + rsi + 12], 13 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0c054c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r13 + rax + 12], 14 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0c024c203a0f4466; BYTE $0x0e // pinsrb xmm9, byte [rdx + rax + 12], 14 + QUAD $0x0c054c203a0f4566; BYTE $0x0f // pinsrb xmm9, byte [r13 + rax + 12], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0d0574203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r13 + rax + 13], 1 + QUAD $0x0d2574203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r13 + r12 + 13], 2 + QUAD $0x0d1d74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r13 + r11 + 13], 3 + QUAD $0x0d3574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r14 + 13], 4 + QUAD $0x0d1d74203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r13 + rbx + 13], 5 + QUAD $0x0d0574203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r13 + r8 + 13], 6 + QUAD $0x0d1574203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r13 + r10 + 13], 7 + QUAD $0x0d0d74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r13 + r9 + 13], 8 + QUAD $0x0d3d74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r13 + r15 + 13], 9 + QUAD $0x0d3d74203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r13 + rdi + 13], 10 + QUAD $0x0d0d74203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r13 + rcx + 13], 11 + QUAD $0x0d1574203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r13 + rdx + 13], 12 + QUAD $0x0d3574203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r13 + rsi + 13], 13 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0c024c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rdx + rax + 12], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x010d0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 13], 1 - QUAD $0x0d3a74203a0f4266; BYTE $0x02 // pinsrb xmm6, byte [rdx + r15 + 13], 2 - QUAD $0x0d1a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r11 + 13], 3 - QUAD $0x040d3a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 13], 4 - QUAD $0x0d0a74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdx + r9 + 13], 5 - QUAD $0x060d1a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 13], 6 - QUAD $0x0d1274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r10 + 13], 7 - QUAD $0x0d3274203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r14 + 13], 8 - QUAD $0x0d2274203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r12 + 13], 9 - QUAD $0x0d2a74203a0f4266; BYTE $0x0a // pinsrb xmm6, byte [rdx + r13 + 13], 10 - QUAD $0x0b0d0a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 13], 11 - QUAD $0x0d0274203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r8 + 13], 12 - QUAD $0x0d0d3274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 13], 13 + QUAD $0x0d0574203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r13 + rax + 13], 14 LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x0e0d0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 13], 14 + QUAD $0x0d0574203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r13 + rax + 13], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0e057c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r13 + rax + 14], 1 + QUAD $0x0e257c203a0f4766; BYTE $0x02 // pinsrb xmm15, byte [r13 + r12 + 14], 2 + QUAD $0x0e1d7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r13 + r11 + 14], 3 + QUAD $0x0e357c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r13 + r14 + 14], 4 + QUAD $0x0e1d7c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r13 + rbx + 14], 5 + QUAD $0x0e057c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r13 + r8 + 14], 6 + QUAD $0x0e157c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r13 + r10 + 14], 7 + QUAD $0x0e0d7c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r13 + r9 + 14], 8 + QUAD $0x0e3d7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r13 + r15 + 14], 9 + QUAD $0x0e3d7c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r13 + rdi + 14], 10 + QUAD $0x0e0d7c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r13 + rcx + 14], 11 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + QUAD $0x0e157c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r13 + rdx + 14], 12 + QUAD $0x0e357c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r13 + rsi + 14], 13 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0f0d0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 13], 15 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0e027c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rax + 14], 1 - QUAD $0x0e3a7c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rdx + r15 + 14], 2 - QUAD $0x0e1a7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r11 + 14], 3 - QUAD $0x0e3a7c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdx + rdi + 14], 4 - WORD $0x8949; BYTE $0xfb // mov r11, rdi - QUAD $0x0e0a7c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rdx + r9 + 14], 5 - QUAD $0x0e1a7c203a0f4466; BYTE $0x06 // pinsrb xmm15, byte [rdx + rbx + 14], 6 - QUAD $0x0e127c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r10 + 14], 7 - QUAD $0x0e327c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdx + r14 + 14], 8 - QUAD $0x0e227c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdx + r12 + 14], 9 - QUAD $0x0e2a7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdx + r13 + 14], 10 - QUAD $0x0e0a7c203a0f4466; BYTE $0x0b // pinsrb xmm15, byte [rdx + rcx + 14], 11 - WORD $0x8949; BYTE $0xcd // mov r13, rcx - QUAD $0x0e027c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdx + r8 + 14], 12 - WORD $0x894d; BYTE $0xc4 // mov r12, r8 - QUAD $0x0e327c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdx + rsi + 14], 13 - LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] - QUAD $0x0e3a7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdx + r15 + 14], 14 + QUAD $0x0e057c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r13 + rax + 14], 14 LONG $0x640f4566; BYTE $0xce // pcmpgtb xmm9, xmm14 QUAD $0x0001308ddf0f4466; BYTE $0x00 // pandn xmm9, oword 304[rbp] /* [rip + .LCPI11_19] */ LONG $0xeb0f4566; BYTE $0xcd // por xmm9, xmm13 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - LONG $0x0274b60f; BYTE $0x19 // movzx esi, byte [rdx + rax + 25] + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + LONG $0x74b60f41; WORD $0x1905 // movzx esi, byte [r13 + rax + 25] LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi QUAD $0x0001609df80f4466; BYTE $0x00 // psubb xmm11, oword 352[rbp] /* [rip + .LCPI11_22] */ LONG $0xeb0f4566; BYTE $0xcb // por xmm9, xmm11 - LONG $0x0274b60f; BYTE $0x1a // movzx esi, byte [rdx + rax + 26] + LONG $0x74b60f41; WORD $0x1a05 // movzx esi, byte [r13 + rax + 26] LONG $0xc66e0f66 // movd xmm0, esi - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e0a7c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rdx + rcx + 14], 15 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x0e3d7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r13 + rdi + 14], 15 LONG $0x640f4166; BYTE $0xf6 // pcmpgtb xmm6, xmm14 QUAD $0x00000140b5df0f66 // pandn xmm6, oword 320[rbp] /* [rip + .LCPI11_20] */ LONG $0x640f4566; BYTE $0xfe // pcmpgtb xmm15, xmm14 QUAD $0x000150bddf0f4466; BYTE $0x00 // pandn xmm15, oword 336[rbp] /* [rip + .LCPI11_21] */ LONG $0xeb0f4466; BYTE $0xfe // por xmm15, xmm6 - LONG $0x0274b60f; BYTE $0x1b // movzx esi, byte [rdx + rax + 27] + LONG $0x74b60f41; WORD $0x1b05 // movzx esi, byte [r13 + rax + 27] LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - QUAD $0x0000a024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 160] - LONG $0x24448b4c; BYTE $0x08 // mov r8, qword [rsp + 8] - QUAD $0x0f0274203a0f4266; BYTE $0x01 // pinsrb xmm6, byte [rdx + r8 + 15], 1 - LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] - QUAD $0x020f3a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 15], 2 - LONG $0x24748b48; BYTE $0x18 // mov rsi, qword [rsp + 24] - QUAD $0x030f3274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 15], 3 - QUAD $0x0f1a74203a0f4266; BYTE $0x04 // pinsrb xmm6, byte [rdx + r11 + 15], 4 - QUAD $0x0f0a74203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdx + r9 + 15], 5 - WORD $0x8949; BYTE $0xd9 // mov r9, rbx - QUAD $0x060f1a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 15], 6 - QUAD $0x0f1274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r10 + 15], 7 - QUAD $0x0f3274203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r14 + 15], 8 - WORD $0x894d; BYTE $0xf2 // mov r10, r14 - LONG $0x245c8b4c; BYTE $0x50 // mov r11, qword [rsp + 80] - QUAD $0x0f1a74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r11 + 15], 9 - LONG $0x245c8b48; BYTE $0x38 // mov rbx, qword [rsp + 56] - QUAD $0x0a0f1a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 15], 10 - QUAD $0x0f2a74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r13 + 15], 11 - QUAD $0x0f2274203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r12 + 15], 12 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x0f2274203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdx + r12 + 15], 13 - QUAD $0x0f3a74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdx + r15 + 15], 14 - QUAD $0x0f0f0a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 15], 15 + QUAD $0x0000c024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 192] + LONG $0x245c8b4c; BYTE $0x38 // mov r11, qword [rsp + 56] + QUAD $0x0f1d74203a0f4366; BYTE $0x01 // pinsrb xmm6, byte [r13 + r11 + 15], 1 + QUAD $0x0f2574203a0f4366; BYTE $0x02 // pinsrb xmm6, byte [r13 + r12 + 15], 2 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0f0d74203a0f4166; BYTE $0x03 // pinsrb xmm6, byte [r13 + rcx + 15], 3 + QUAD $0x0f3574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r14 + 15], 4 + QUAD $0x0f1d74203a0f4166; BYTE $0x05 // pinsrb xmm6, byte [r13 + rbx + 15], 5 + QUAD $0x0f0574203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r13 + r8 + 15], 6 + QUAD $0x0f1574203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r13 + r10 + 15], 7 + QUAD $0x0f0d74203a0f4366; BYTE $0x08 // pinsrb xmm6, byte [r13 + r9 + 15], 8 + LONG $0x24548b48; BYTE $0x48 // mov rdx, qword [rsp + 72] + QUAD $0x0f1574203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r13 + rdx + 15], 9 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x0f3574203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r13 + rsi + 15], 10 + QUAD $0x0f3d74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r13 + r15 + 15], 11 + LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] + QUAD $0x0f3d74203a0f4366; BYTE $0x0c // pinsrb xmm6, byte [r13 + r15 + 15], 12 + LONG $0x245c8b48; BYTE $0x20 // mov rbx, qword [rsp + 32] + QUAD $0x0f1d74203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r13 + rbx + 15], 13 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0f3574203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r13 + rsi + 15], 14 + QUAD $0x0f3d74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r13 + rdi + 15], 15 LONG $0x640f4166; BYTE $0xf6 // pcmpgtb xmm6, xmm14 LONG $0x75df0f66; BYTE $0x60 // pandn xmm6, oword 96[rbp] /* [rip + .LCPI11_6] */ LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 - LONG $0x0274b60f; BYTE $0x1c // movzx esi, byte [rdx + rax + 28] + LONG $0x74b60f41; WORD $0x1c05 // movzx esi, byte [r13 + rax + 28] LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi LONG $0xeb0f4166; BYTE $0xf1 // por xmm6, xmm9 - QUAD $0x0000a024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 160], xmm6 - LONG $0x0274b60f; BYTE $0x1d // movzx esi, byte [rdx + rax + 29] + QUAD $0x0000c024b47f0f66; BYTE $0x00 // movdqa oword [rsp + 192], xmm6 + LONG $0x74b60f41; WORD $0x1d05 // movzx esi, byte [r13 + rax + 29] LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x100254203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdx + r8 + 16], 1 - WORD $0x8949; BYTE $0xfe // mov r14, rdi - QUAD $0x103a54203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdx + rdi + 16], 2 - LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] - QUAD $0x100a54203a0f4466; BYTE $0x03 // pinsrb xmm10, byte [rdx + rcx + 16], 3 - QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] - QUAD $0x103a54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdx + rdi + 16], 4 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x100254203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdx + r8 + 16], 5 - QUAD $0x100a54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r9 + 16], 6 - LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] - QUAD $0x100a54203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdx + r9 + 16], 7 - QUAD $0x101254203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r10 + 16], 8 - QUAD $0x101a54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdx + r11 + 16], 9 - QUAD $0x101a54203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdx + rbx + 16], 10 - QUAD $0x102a54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdx + r13 + 16], 11 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x103a54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdx + r15 + 16], 12 - QUAD $0x102254203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdx + r12 + 16], 13 - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x100a54203a0f4466; BYTE $0x0e // pinsrb xmm10, byte [rdx + rcx + 16], 14 - LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x103254203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdx + rsi + 16], 15 - QUAD $0x01110264203a0f66 // pinsrb xmm4, byte [rdx + rax + 17], 1 - QUAD $0x113264203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdx + r14 + 17], 2 - LONG $0x24748b4c; BYTE $0x18 // mov r14, qword [rsp + 24] - QUAD $0x113264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r14 + 17], 3 - QUAD $0x04113a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 17], 4 - QUAD $0x110264203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdx + r8 + 17], 5 - LONG $0x24648b4c; BYTE $0x40 // mov r12, qword [rsp + 64] - QUAD $0x112264203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdx + r12 + 17], 6 - QUAD $0x110a64203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r9 + 17], 7 - QUAD $0x111264203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r10 + 17], 8 - QUAD $0x111a64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r11 + 17], 9 - QUAD $0x0a111a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 17], 10 - QUAD $0x112a64203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r13 + 17], 11 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - QUAD $0x113a64203a0f4266; BYTE $0x0c // pinsrb xmm4, byte [rdx + r15 + 17], 12 - LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] - QUAD $0x110264203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdx + r8 + 17], 13 - QUAD $0x0e110a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 17], 14 - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - QUAD $0x0f113264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 17], 15 - WORD $0x8949; BYTE $0xf7 // mov r15, rsi + WORD $0x894c; BYTE $0xd8 // mov rax, r11 + QUAD $0x101d54203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r13 + r11 + 16], 1 + QUAD $0x102554203a0f4766; BYTE $0x02 // pinsrb xmm10, byte [r13 + r12 + 16], 2 + QUAD $0x100d54203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r13 + rcx + 16], 3 + QUAD $0x103554203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r13 + r14 + 16], 4 + WORD $0x894d; BYTE $0xf4 // mov r12, r14 + LONG $0x24548b4c; BYTE $0x70 // mov r10, qword [rsp + 112] + QUAD $0x101554203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r13 + r10 + 16], 5 + QUAD $0x100554203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r13 + r8 + 16], 6 + WORD $0x894d; BYTE $0xc3 // mov r11, r8 + QUAD $0x000000d024848b4c // mov r8, qword [rsp + 208] + QUAD $0x100554203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r13 + r8 + 16], 7 + WORD $0x894d; BYTE $0xce // mov r14, r9 + QUAD $0x100d54203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r13 + r9 + 16], 8 + QUAD $0x101554203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r13 + rdx + 16], 9 + LONG $0x247c8b48; BYTE $0x50 // mov rdi, qword [rsp + 80] + QUAD $0x103d54203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r13 + rdi + 16], 10 + LONG $0x244c8b4c; BYTE $0x40 // mov r9, qword [rsp + 64] + QUAD $0x100d54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r13 + r9 + 16], 11 + QUAD $0x103d54203a0f4766; BYTE $0x0c // pinsrb xmm10, byte [r13 + r15 + 16], 12 + QUAD $0x101d54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r13 + rbx + 16], 13 + LONG $0x245c8b48; BYTE $0x10 // mov rbx, qword [rsp + 16] + QUAD $0x101d54203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r13 + rbx + 16], 14 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x103554203a0f4566; BYTE $0x0f // pinsrb xmm10, byte [r13 + rsi + 16], 15 + QUAD $0x110564203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r13 + rax + 17], 1 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x110564203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r13 + rax + 17], 2 + QUAD $0x110d64203a0f4166; BYTE $0x03 // pinsrb xmm4, byte [r13 + rcx + 17], 3 + QUAD $0x112564203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r13 + r12 + 17], 4 + QUAD $0x111564203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r13 + r10 + 17], 5 + QUAD $0x111d64203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r13 + r11 + 17], 6 + QUAD $0x110564203a0f4366; BYTE $0x07 // pinsrb xmm4, byte [r13 + r8 + 17], 7 + WORD $0x894d; BYTE $0xc2 // mov r10, r8 + WORD $0x894d; BYTE $0xf0 // mov r8, r14 + QUAD $0x113564203a0f4366; BYTE $0x08 // pinsrb xmm4, byte [r13 + r14 + 17], 8 + QUAD $0x111564203a0f4166; BYTE $0x09 // pinsrb xmm4, byte [r13 + rdx + 17], 9 + QUAD $0x113d64203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r13 + rdi + 17], 10 + QUAD $0x110d64203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r13 + r9 + 17], 11 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x113d64203a0f4366; BYTE $0x0c // pinsrb xmm4, byte [r13 + r15 + 17], 12 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x110d64203a0f4166; BYTE $0x0d // pinsrb xmm4, byte [r13 + rcx + 17], 13 + QUAD $0x111d64203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r13 + rbx + 17], 14 + QUAD $0x113564203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r13 + rsi + 17], 15 LONG $0x640f4566; BYTE $0xd6 // pcmpgtb xmm10, xmm14 LONG $0x640f4166; BYTE $0xe6 // pcmpgtb xmm4, xmm14 QUAD $0x00000100b56f0f66 // movdqa xmm6, oword 256[rbp] /* [rip + .LCPI11_16] */ LONG $0xe6df0f66 // pandn xmm4, xmm6 LONG $0xfc0f4166; BYTE $0xe2 // paddb xmm4, xmm10 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - LONG $0x0274b60f; BYTE $0x1e // movzx esi, byte [rdx + rax + 30] + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + LONG $0x74b60f41; WORD $0x1e05 // movzx esi, byte [r13 + rax + 30] LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0112327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 18], 1 - QUAD $0x0113326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 19], 1 - QUAD $0x0114325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 20], 1 - QUAD $0x01153254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 21], 1 - QUAD $0x0116324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 22], 1 - QUAD $0x173244203a0f4466; BYTE $0x01 // pinsrb xmm8, byte [rdx + rsi + 23], 1 - QUAD $0x183264203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdx + rsi + 24], 1 - QUAD $0x19326c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdx + rsi + 25], 1 - QUAD $0x011a3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 26], 1 - QUAD $0x1b325c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdx + rsi + 27], 1 - QUAD $0x1c327c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rsi + 28], 1 - QUAD $0x1d324c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rsi + 29], 1 - QUAD $0x1e3254203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdx + rsi + 30], 1 - LONG $0x0244b60f; BYTE $0x1f // movzx eax, byte [rdx + rax + 31] - LONG $0xf06e0f66 // movd xmm6, eax - QUAD $0x011f3274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 31], 1 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0212027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 18], 2 - QUAD $0x0213026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 19], 2 - QUAD $0x0214025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 20], 2 - QUAD $0x02150254203a0f66 // pinsrb xmm2, byte [rdx + rax + 21], 2 - QUAD $0x0216024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 22], 2 - QUAD $0x170244203a0f4466; BYTE $0x02 // pinsrb xmm8, byte [rdx + rax + 23], 2 - QUAD $0x180264203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rax + 24], 2 - QUAD $0x19026c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rax + 25], 2 - QUAD $0x021a0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 26], 2 - QUAD $0x1b025c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rax + 27], 2 - QUAD $0x1c027c203a0f4466; BYTE $0x02 // pinsrb xmm15, byte [rdx + rax + 28], 2 - QUAD $0x1d024c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rax + 29], 2 - QUAD $0x1e0254203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdx + rax + 30], 2 - QUAD $0x021f0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 31], 2 - WORD $0x894d; BYTE $0xf3 // mov r11, r14 - QUAD $0x12327c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r14 + 18], 3 - QUAD $0x04123a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 18], 4 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x05120a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 18], 5 - QUAD $0x12227c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdx + r12 + 18], 6 - LONG $0x24548b4c; BYTE $0x68 // mov r10, qword [rsp + 104] - QUAD $0x12127c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdx + r10 + 18], 7 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x12327c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdx + r14 + 18], 8 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - QUAD $0x0912027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 18], 9 LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0a12327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 18], 10 - QUAD $0x122a7c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdx + r13 + 18], 11 - QUAD $0x0c121a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 18], 12 - QUAD $0x12027c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rdx + r8 + 18], 13 - QUAD $0x120a7c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdx + r9 + 18], 14 - QUAD $0x123a7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdx + r15 + 18], 15 - QUAD $0x131a6c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r11 + 19], 3 - QUAD $0x04133a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 19], 4 - QUAD $0x05130a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 19], 5 - QUAD $0x13226c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r12 + 19], 6 - QUAD $0x13126c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r10 + 19], 7 - QUAD $0x13326c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r14 + 19], 8 - QUAD $0x0913026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 19], 9 - QUAD $0x0a13326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 19], 10 - QUAD $0x132a6c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdx + r13 + 19], 11 - QUAD $0x0c131a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 19], 12 - QUAD $0x13026c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdx + r8 + 19], 13 - QUAD $0x130a6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdx + r9 + 19], 14 - QUAD $0x133a6c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdx + r15 + 19], 15 - QUAD $0x141a5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r11 + 20], 3 - QUAD $0x04143a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 20], 4 - QUAD $0x05140a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 20], 5 - QUAD $0x14225c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdx + r12 + 20], 6 - QUAD $0x14125c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdx + r10 + 20], 7 - QUAD $0x14325c203a0f4266; BYTE $0x08 // pinsrb xmm3, byte [rdx + r14 + 20], 8 - QUAD $0x0914025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 20], 9 - QUAD $0x0a14325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 20], 10 - QUAD $0x142a5c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r13 + 20], 11 - QUAD $0x0c141a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 20], 12 - QUAD $0x14025c203a0f4266; BYTE $0x0d // pinsrb xmm3, byte [rdx + r8 + 20], 13 - QUAD $0x140a5c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdx + r9 + 20], 14 + QUAD $0x12357c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r13 + rsi + 18], 1 + QUAD $0x13356c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r13 + rsi + 19], 1 + QUAD $0x14355c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r13 + rsi + 20], 1 + QUAD $0x153554203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r13 + rsi + 21], 1 + QUAD $0x16354c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r13 + rsi + 22], 1 + QUAD $0x173544203a0f4566; BYTE $0x01 // pinsrb xmm8, byte [r13 + rsi + 23], 1 + QUAD $0x183564203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r13 + rsi + 24], 1 + QUAD $0x19356c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r13 + rsi + 25], 1 + QUAD $0x1a3544203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r13 + rsi + 26], 1 + QUAD $0x1b355c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r13 + rsi + 27], 1 + QUAD $0x1c357c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r13 + rsi + 28], 1 + QUAD $0x1d354c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r13 + rsi + 29], 1 + QUAD $0x1e3554203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r13 + rsi + 30], 1 + LONG $0x44b60f41; WORD $0x1f05 // movzx eax, byte [r13 + rax + 31] + LONG $0xf06e0f66 // movd xmm6, eax + QUAD $0x1f3574203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r13 + rsi + 31], 1 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x12057c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r13 + rax + 18], 2 + QUAD $0x13056c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r13 + rax + 19], 2 + QUAD $0x14055c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r13 + rax + 20], 2 + QUAD $0x150554203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r13 + rax + 21], 2 + QUAD $0x16054c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r13 + rax + 22], 2 + QUAD $0x170544203a0f4566; BYTE $0x02 // pinsrb xmm8, byte [r13 + rax + 23], 2 + QUAD $0x180564203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r13 + rax + 24], 2 + QUAD $0x19056c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r13 + rax + 25], 2 + QUAD $0x1a0544203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r13 + rax + 26], 2 + QUAD $0x1b055c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r13 + rax + 27], 2 + QUAD $0x1c057c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r13 + rax + 28], 2 + QUAD $0x1d054c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r13 + rax + 29], 2 + QUAD $0x1e0554203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r13 + rax + 30], 2 + QUAD $0x1f0574203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r13 + rax + 31], 2 + LONG $0x245c8b4c; BYTE $0x30 // mov r11, qword [rsp + 48] + QUAD $0x121d7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r13 + r11 + 18], 3 + WORD $0x894d; BYTE $0xe6 // mov r14, r12 + QUAD $0x12257c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r13 + r12 + 18], 4 + LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] + QUAD $0x120d7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r13 + r9 + 18], 5 + QUAD $0x0000008024bc8b48 // mov rdi, qword [rsp + 128] + QUAD $0x123d7c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r13 + rdi + 18], 6 + QUAD $0x12157c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r13 + r10 + 18], 7 + QUAD $0x12057c203a0f4366; BYTE $0x08 // pinsrb xmm7, byte [r13 + r8 + 18], 8 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x12057c203a0f4166; BYTE $0x09 // pinsrb xmm7, byte [r13 + rax + 18], 9 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + QUAD $0x12357c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r13 + rsi + 18], 10 + LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + QUAD $0x123d7c203a0f4366; BYTE $0x0b // pinsrb xmm7, byte [r13 + r15 + 18], 11 + QUAD $0x12157c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r13 + rdx + 18], 12 + QUAD $0x120d7c203a0f4166; BYTE $0x0d // pinsrb xmm7, byte [r13 + rcx + 18], 13 + QUAD $0x121d7c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r13 + rbx + 18], 14 + LONG $0x24648b4c; BYTE $0x28 // mov r12, qword [rsp + 40] + QUAD $0x12257c203a0f4366; BYTE $0x0f // pinsrb xmm7, byte [r13 + r12 + 18], 15 + QUAD $0x131d6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r13 + r11 + 19], 3 + QUAD $0x13356c203a0f4366; BYTE $0x04 // pinsrb xmm5, byte [r13 + r14 + 19], 4 + QUAD $0x130d6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r13 + r9 + 19], 5 + QUAD $0x133d6c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r13 + rdi + 19], 6 + QUAD $0x13156c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r13 + r10 + 19], 7 + QUAD $0x13056c203a0f4366; BYTE $0x08 // pinsrb xmm5, byte [r13 + r8 + 19], 8 + QUAD $0x13056c203a0f4166; BYTE $0x09 // pinsrb xmm5, byte [r13 + rax + 19], 9 + QUAD $0x13356c203a0f4166; BYTE $0x0a // pinsrb xmm5, byte [r13 + rsi + 19], 10 + QUAD $0x133d6c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r13 + r15 + 19], 11 + QUAD $0x13156c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r13 + rdx + 19], 12 + QUAD $0x130d6c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r13 + rcx + 19], 13 + QUAD $0x131d6c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r13 + rbx + 19], 14 + QUAD $0x13256c203a0f4366; BYTE $0x0f // pinsrb xmm5, byte [r13 + r12 + 19], 15 + QUAD $0x141d5c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r13 + r11 + 20], 3 + QUAD $0x14355c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r13 + r14 + 20], 4 + QUAD $0x140d5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r13 + r9 + 20], 5 + QUAD $0x143d5c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r13 + rdi + 20], 6 + QUAD $0x14155c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r13 + r10 + 20], 7 + QUAD $0x14055c203a0f4366; BYTE $0x08 // pinsrb xmm3, byte [r13 + r8 + 20], 8 + QUAD $0x14055c203a0f4166; BYTE $0x09 // pinsrb xmm3, byte [r13 + rax + 20], 9 + QUAD $0x14355c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r13 + rsi + 20], 10 + QUAD $0x143d5c203a0f4366; BYTE $0x0b // pinsrb xmm3, byte [r13 + r15 + 20], 11 + QUAD $0x14155c203a0f4166; BYTE $0x0c // pinsrb xmm3, byte [r13 + rdx + 20], 12 + QUAD $0x140d5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r13 + rcx + 20], 13 + QUAD $0x141d5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r13 + rbx + 20], 14 LONG $0x640f4166; BYTE $0xfe // pcmpgtb xmm7, xmm14 QUAD $0x000110b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 272[rbp] /* [rip + .LCPI11_17] */ LONG $0xdf0f4166; BYTE $0xfe // pandn xmm7, xmm14 - QUAD $0x00009024ac640f66; BYTE $0x00 // pcmpgtb xmm5, oword [rsp + 144] + QUAD $0x0000a024ac640f66; BYTE $0x00 // pcmpgtb xmm5, oword [rsp + 160] QUAD $0x000120b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 288[rbp] /* [rip + .LCPI11_18] */ LONG $0xdf0f4166; BYTE $0xee // pandn xmm5, xmm14 LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0x143a5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r15 + 20], 15 - QUAD $0x009024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 144] + QUAD $0x14255c203a0f4366; BYTE $0x0f // pinsrb xmm3, byte [r13 + r12 + 20], 15 + QUAD $0x00a024b46f0f4466; WORD $0x0000 // movdqa xmm14, oword [rsp + 160] LONG $0x640f4166; BYTE $0xde // pcmpgtb xmm3, xmm14 QUAD $0x00000130bd6f0f66 // movdqa xmm7, oword 304[rbp] /* [rip + .LCPI11_19] */ LONG $0xdfdf0f66 // pandn xmm3, xmm7 @@ -57691,44 +60382,44 @@ LBB11_86: LONG $0xed760f66 // pcmpeqd xmm5, xmm5 LONG $0xe5f80f66 // psubb xmm4, xmm5 LONG $0xdceb0f66 // por xmm3, xmm4 - QUAD $0x151a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r11 + 21], 3 - QUAD $0x04153a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 21], 4 - QUAD $0x05150a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 21], 5 - QUAD $0x152254203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r12 + 21], 6 - QUAD $0x151254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r10 + 21], 7 - QUAD $0x153254203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r14 + 21], 8 - QUAD $0x09150254203a0f66 // pinsrb xmm2, byte [rdx + rax + 21], 9 - QUAD $0x0a153254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 21], 10 - QUAD $0x152a54203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r13 + 21], 11 - QUAD $0x0c151a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 21], 12 - QUAD $0x150254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r8 + 21], 13 - QUAD $0x150a54203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r9 + 21], 14 - QUAD $0x153a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r15 + 21], 15 - QUAD $0x161a4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r11 + 22], 3 - QUAD $0x04163a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 22], 4 - QUAD $0x05160a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 22], 5 - QUAD $0x16224c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r12 + 22], 6 - QUAD $0x16124c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r10 + 22], 7 - QUAD $0x16324c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r14 + 22], 8 - QUAD $0x0916024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 22], 9 - QUAD $0x0a16324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 22], 10 - QUAD $0x162a4c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdx + r13 + 22], 11 - QUAD $0x0c161a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 22], 12 - QUAD $0x16024c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdx + r8 + 22], 13 - QUAD $0x160a4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r9 + 22], 14 - QUAD $0x163a4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r15 + 22], 15 - QUAD $0x171a44203a0f4666; BYTE $0x03 // pinsrb xmm8, byte [rdx + r11 + 23], 3 - QUAD $0x173a44203a0f4466; BYTE $0x04 // pinsrb xmm8, byte [rdx + rdi + 23], 4 - QUAD $0x170a44203a0f4466; BYTE $0x05 // pinsrb xmm8, byte [rdx + rcx + 23], 5 - QUAD $0x172244203a0f4666; BYTE $0x06 // pinsrb xmm8, byte [rdx + r12 + 23], 6 - QUAD $0x171244203a0f4666; BYTE $0x07 // pinsrb xmm8, byte [rdx + r10 + 23], 7 - QUAD $0x173244203a0f4666; BYTE $0x08 // pinsrb xmm8, byte [rdx + r14 + 23], 8 - QUAD $0x170244203a0f4466; BYTE $0x09 // pinsrb xmm8, byte [rdx + rax + 23], 9 - QUAD $0x173244203a0f4466; BYTE $0x0a // pinsrb xmm8, byte [rdx + rsi + 23], 10 - QUAD $0x172a44203a0f4666; BYTE $0x0b // pinsrb xmm8, byte [rdx + r13 + 23], 11 - QUAD $0x171a44203a0f4466; BYTE $0x0c // pinsrb xmm8, byte [rdx + rbx + 23], 12 - QUAD $0x170244203a0f4666; BYTE $0x0d // pinsrb xmm8, byte [rdx + r8 + 23], 13 - QUAD $0x170a44203a0f4666; BYTE $0x0e // pinsrb xmm8, byte [rdx + r9 + 23], 14 + QUAD $0x151d54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r13 + r11 + 21], 3 + QUAD $0x153554203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r13 + r14 + 21], 4 + QUAD $0x150d54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r13 + r9 + 21], 5 + QUAD $0x153d54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r13 + rdi + 21], 6 + QUAD $0x151554203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r13 + r10 + 21], 7 + QUAD $0x150554203a0f4366; BYTE $0x08 // pinsrb xmm2, byte [r13 + r8 + 21], 8 + QUAD $0x150554203a0f4166; BYTE $0x09 // pinsrb xmm2, byte [r13 + rax + 21], 9 + QUAD $0x153554203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r13 + rsi + 21], 10 + QUAD $0x153d54203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r13 + r15 + 21], 11 + QUAD $0x151554203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r13 + rdx + 21], 12 + QUAD $0x150d54203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r13 + rcx + 21], 13 + QUAD $0x151d54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r13 + rbx + 21], 14 + QUAD $0x152554203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r13 + r12 + 21], 15 + QUAD $0x161d4c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r13 + r11 + 22], 3 + QUAD $0x16354c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r13 + r14 + 22], 4 + QUAD $0x160d4c203a0f4366; BYTE $0x05 // pinsrb xmm1, byte [r13 + r9 + 22], 5 + QUAD $0x163d4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r13 + rdi + 22], 6 + QUAD $0x16154c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r13 + r10 + 22], 7 + QUAD $0x16054c203a0f4366; BYTE $0x08 // pinsrb xmm1, byte [r13 + r8 + 22], 8 + QUAD $0x16054c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r13 + rax + 22], 9 + QUAD $0x16354c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r13 + rsi + 22], 10 + QUAD $0x163d4c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r13 + r15 + 22], 11 + QUAD $0x16154c203a0f4166; BYTE $0x0c // pinsrb xmm1, byte [r13 + rdx + 22], 12 + QUAD $0x160d4c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r13 + rcx + 22], 13 + QUAD $0x161d4c203a0f4166; BYTE $0x0e // pinsrb xmm1, byte [r13 + rbx + 22], 14 + QUAD $0x16254c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r13 + r12 + 22], 15 + QUAD $0x171d44203a0f4766; BYTE $0x03 // pinsrb xmm8, byte [r13 + r11 + 23], 3 + QUAD $0x173544203a0f4766; BYTE $0x04 // pinsrb xmm8, byte [r13 + r14 + 23], 4 + QUAD $0x170d44203a0f4766; BYTE $0x05 // pinsrb xmm8, byte [r13 + r9 + 23], 5 + QUAD $0x173d44203a0f4566; BYTE $0x06 // pinsrb xmm8, byte [r13 + rdi + 23], 6 + QUAD $0x171544203a0f4766; BYTE $0x07 // pinsrb xmm8, byte [r13 + r10 + 23], 7 + QUAD $0x170544203a0f4766; BYTE $0x08 // pinsrb xmm8, byte [r13 + r8 + 23], 8 + QUAD $0x170544203a0f4566; BYTE $0x09 // pinsrb xmm8, byte [r13 + rax + 23], 9 + QUAD $0x173544203a0f4566; BYTE $0x0a // pinsrb xmm8, byte [r13 + rsi + 23], 10 + QUAD $0x173d44203a0f4766; BYTE $0x0b // pinsrb xmm8, byte [r13 + r15 + 23], 11 + QUAD $0x171544203a0f4566; BYTE $0x0c // pinsrb xmm8, byte [r13 + rdx + 23], 12 + QUAD $0x170d44203a0f4566; BYTE $0x0d // pinsrb xmm8, byte [r13 + rcx + 23], 13 + QUAD $0x171d44203a0f4566; BYTE $0x0e // pinsrb xmm8, byte [r13 + rbx + 23], 14 LONG $0x640f4166; BYTE $0xd6 // pcmpgtb xmm2, xmm14 QUAD $0x00000140ad6f0f66 // movdqa xmm5, oword 320[rbp] /* [rip + .LCPI11_20] */ LONG $0xd5df0f66 // pandn xmm2, xmm5 @@ -57736,136 +60427,138 @@ LBB11_86: QUAD $0x00000150bd6f0f66 // movdqa xmm7, oword 336[rbp] /* [rip + .LCPI11_21] */ LONG $0xcfdf0f66 // pandn xmm1, xmm7 LONG $0xcaeb0f66 // por xmm1, xmm2 - QUAD $0x173a44203a0f4666; BYTE $0x0f // pinsrb xmm8, byte [rdx + r15 + 23], 15 + QUAD $0x172544203a0f4766; BYTE $0x0f // pinsrb xmm8, byte [r13 + r12 + 23], 15 LONG $0x640f4566; BYTE $0xc6 // pcmpgtb xmm8, xmm14 LONG $0x656f0f66; BYTE $0x60 // movdqa xmm4, oword 96[rbp] /* [rip + .LCPI11_6] */ LONG $0xdf0f4466; BYTE $0xc4 // pandn xmm8, xmm4 LONG $0xeb0f4466; BYTE $0xc1 // por xmm8, xmm1 - QUAD $0x181a64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r11 + 24], 3 - QUAD $0x183a64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdx + rdi + 24], 4 - QUAD $0x180a64203a0f4466; BYTE $0x05 // pinsrb xmm12, byte [rdx + rcx + 24], 5 - QUAD $0x182264203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdx + r12 + 24], 6 - QUAD $0x181264203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdx + r10 + 24], 7 - QUAD $0x183264203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r14 + 24], 8 - QUAD $0x180264203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rdx + rax + 24], 9 - QUAD $0x183264203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdx + rsi + 24], 10 - QUAD $0x182a64203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdx + r13 + 24], 11 - QUAD $0x181a64203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdx + rbx + 24], 12 - QUAD $0x180264203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdx + r8 + 24], 13 - QUAD $0x180a64203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r9 + 24], 14 - QUAD $0x183a64203a0f4666; BYTE $0x0f // pinsrb xmm12, byte [rdx + r15 + 24], 15 + QUAD $0x181d64203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r13 + r11 + 24], 3 + QUAD $0x183564203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r13 + r14 + 24], 4 + QUAD $0x180d64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r13 + r9 + 24], 5 + QUAD $0x183d64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r13 + rdi + 24], 6 + QUAD $0x181564203a0f4766; BYTE $0x07 // pinsrb xmm12, byte [r13 + r10 + 24], 7 + QUAD $0x180564203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r13 + r8 + 24], 8 + QUAD $0x180564203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r13 + rax + 24], 9 + QUAD $0x183564203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r13 + rsi + 24], 10 + QUAD $0x183d64203a0f4766; BYTE $0x0b // pinsrb xmm12, byte [r13 + r15 + 24], 11 + QUAD $0x181564203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r13 + rdx + 24], 12 + QUAD $0x180d64203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r13 + rcx + 24], 13 + QUAD $0x181d64203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r13 + rbx + 24], 14 + QUAD $0x182564203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r13 + r12 + 24], 15 LONG $0xeb0f4466; BYTE $0xc3 // por xmm8, xmm3 LONG $0x640f4566; BYTE $0xe6 // pcmpgtb xmm12, xmm14 - QUAD $0x191a6c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdx + r11 + 25], 3 - QUAD $0x193a6c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdx + rdi + 25], 4 - QUAD $0x190a6c203a0f4466; BYTE $0x05 // pinsrb xmm13, byte [rdx + rcx + 25], 5 - QUAD $0x19226c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdx + r12 + 25], 6 - QUAD $0x19126c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdx + r10 + 25], 7 - QUAD $0x19326c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r14 + 25], 8 - QUAD $0x19026c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rdx + rax + 25], 9 - QUAD $0x19326c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdx + rsi + 25], 10 - QUAD $0x192a6c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdx + r13 + 25], 11 - QUAD $0x191a6c203a0f4466; BYTE $0x0c // pinsrb xmm13, byte [rdx + rbx + 25], 12 - QUAD $0x19026c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdx + r8 + 25], 13 - QUAD $0x190a6c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r9 + 25], 14 - QUAD $0x193a6c203a0f4666; BYTE $0x0f // pinsrb xmm13, byte [rdx + r15 + 25], 15 - QUAD $0x1a1a44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r11 + 26], 3 - QUAD $0x041a3a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 26], 4 - QUAD $0x051a0a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 26], 5 - QUAD $0x1a2244203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdx + r12 + 26], 6 - QUAD $0x1a1244203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r10 + 26], 7 - QUAD $0x1a3244203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r14 + 26], 8 - QUAD $0x091a0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 26], 9 - QUAD $0x0a1a3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 26], 10 - QUAD $0x1a2a44203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r13 + 26], 11 - QUAD $0x0c1a1a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 26], 12 - QUAD $0x1a0244203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdx + r8 + 26], 13 - QUAD $0x1a0a44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdx + r9 + 26], 14 - QUAD $0x1a3a44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r15 + 26], 15 - QUAD $0x1b1a5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r11 + 27], 3 - QUAD $0x1b3a5c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdx + rdi + 27], 4 - QUAD $0x1b0a5c203a0f4466; BYTE $0x05 // pinsrb xmm11, byte [rdx + rcx + 27], 5 - QUAD $0x1b225c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r12 + 27], 6 - QUAD $0x1b125c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdx + r10 + 27], 7 - QUAD $0x1b325c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r14 + 27], 8 - QUAD $0x1b025c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdx + rax + 27], 9 - QUAD $0x1b325c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdx + rsi + 27], 10 - QUAD $0x1b2a5c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r13 + 27], 11 - QUAD $0x1b1a5c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rdx + rbx + 27], 12 - QUAD $0x1b025c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdx + r8 + 27], 13 - QUAD $0x1b0a5c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r9 + 27], 14 + QUAD $0x191d6c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r13 + r11 + 25], 3 + QUAD $0x19356c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r13 + r14 + 25], 4 + QUAD $0x190d6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r13 + r9 + 25], 5 + QUAD $0x193d6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r13 + rdi + 25], 6 + QUAD $0x19156c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r13 + r10 + 25], 7 + QUAD $0x19056c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r13 + r8 + 25], 8 + QUAD $0x19056c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r13 + rax + 25], 9 + QUAD $0x19356c203a0f4566; BYTE $0x0a // pinsrb xmm13, byte [r13 + rsi + 25], 10 + QUAD $0x193d6c203a0f4766; BYTE $0x0b // pinsrb xmm13, byte [r13 + r15 + 25], 11 + QUAD $0x19156c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r13 + rdx + 25], 12 + QUAD $0x190d6c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r13 + rcx + 25], 13 + QUAD $0x191d6c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r13 + rbx + 25], 14 + QUAD $0x19256c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r13 + r12 + 25], 15 + QUAD $0x1a1d44203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r13 + r11 + 26], 3 + QUAD $0x1a3544203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r13 + r14 + 26], 4 + QUAD $0x1a0d44203a0f4366; BYTE $0x05 // pinsrb xmm0, byte [r13 + r9 + 26], 5 + QUAD $0x1a3d44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r13 + rdi + 26], 6 + QUAD $0x1a1544203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r13 + r10 + 26], 7 + QUAD $0x1a0544203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r13 + r8 + 26], 8 + QUAD $0x1a0544203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r13 + rax + 26], 9 + QUAD $0x1a3544203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r13 + rsi + 26], 10 + QUAD $0x1a3d44203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r13 + r15 + 26], 11 + QUAD $0x1a1544203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r13 + rdx + 26], 12 + QUAD $0x1a0d44203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r13 + rcx + 26], 13 + QUAD $0x1a1d44203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r13 + rbx + 26], 14 + QUAD $0x1a2544203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r13 + r12 + 26], 15 + QUAD $0x1b1d5c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r13 + r11 + 27], 3 + QUAD $0x1b355c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r13 + r14 + 27], 4 + QUAD $0x1b0d5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r13 + r9 + 27], 5 + QUAD $0x1b3d5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r13 + rdi + 27], 6 + QUAD $0x1b155c203a0f4766; BYTE $0x07 // pinsrb xmm11, byte [r13 + r10 + 27], 7 + QUAD $0x1b055c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r13 + r8 + 27], 8 + QUAD $0x1b055c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r13 + rax + 27], 9 + QUAD $0x1b355c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r13 + rsi + 27], 10 + QUAD $0x1b3d5c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r13 + r15 + 27], 11 + QUAD $0x1b155c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r13 + rdx + 27], 12 + QUAD $0x1b0d5c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r13 + rcx + 27], 13 + QUAD $0x1b1d5c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r13 + rbx + 27], 14 LONG $0x640f4566; BYTE $0xee // pcmpgtb xmm13, xmm14 QUAD $0x000100addf0f4466; BYTE $0x00 // pandn xmm13, oword 256[rbp] /* [rip + .LCPI11_16] */ LONG $0xfc0f4566; BYTE $0xec // paddb xmm13, xmm12 - QUAD $0x1b3a5c203a0f4666; BYTE $0x0f // pinsrb xmm11, byte [rdx + r15 + 27], 15 + QUAD $0x1b255c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r13 + r12 + 27], 15 LONG $0x640f4166; BYTE $0xc6 // pcmpgtb xmm0, xmm14 QUAD $0x0000011085df0f66 // pandn xmm0, oword 272[rbp] /* [rip + .LCPI11_17] */ LONG $0x640f4566; BYTE $0xde // pcmpgtb xmm11, xmm14 QUAD $0x0001209ddf0f4466; BYTE $0x00 // pandn xmm11, oword 288[rbp] /* [rip + .LCPI11_18] */ LONG $0xeb0f4466; BYTE $0xd8 // por xmm11, xmm0 - QUAD $0x1c1a7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r11 + 28], 3 - QUAD $0x1d1a4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdx + r11 + 29], 3 - QUAD $0x1e1a54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r11 + 30], 3 - QUAD $0x1f1a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r11 + 31], 3 - QUAD $0x1c3a7c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdx + rdi + 28], 4 - QUAD $0x1d3a4c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdx + rdi + 29], 4 - QUAD $0x1e3a54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdx + rdi + 30], 4 - QUAD $0x041f3a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 31], 4 - WORD $0x8948; BYTE $0xcf // mov rdi, rcx - QUAD $0x1c0a7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdx + rcx + 28], 5 - QUAD $0x1d0a4c203a0f4466; BYTE $0x05 // pinsrb xmm9, byte [rdx + rcx + 29], 5 - QUAD $0x1e0a54203a0f4466; BYTE $0x05 // pinsrb xmm10, byte [rdx + rcx + 30], 5 - QUAD $0x051f0a74203a0f66 // pinsrb xmm6, byte [rdx + rcx + 31], 5 - QUAD $0x1c227c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdx + r12 + 28], 6 - QUAD $0x1d224c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdx + r12 + 29], 6 - QUAD $0x1e2254203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r12 + 30], 6 - QUAD $0x1f2274203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r12 + 31], 6 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - WORD $0x894c; BYTE $0xd7 // mov rdi, r10 - QUAD $0x1c127c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r10 + 28], 7 - QUAD $0x1d124c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdx + r10 + 29], 7 - QUAD $0x1e1254203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdx + r10 + 30], 7 - QUAD $0x1f1274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r10 + 31], 7 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - QUAD $0x1c327c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdx + r14 + 28], 8 - QUAD $0x1d324c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r14 + 29], 8 - QUAD $0x1e3254203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r14 + 30], 8 - QUAD $0x1f3274203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r14 + 31], 8 - QUAD $0x1c027c203a0f4466; BYTE $0x09 // pinsrb xmm15, byte [rdx + rax + 28], 9 - QUAD $0x1d024c203a0f4466; BYTE $0x09 // pinsrb xmm9, byte [rdx + rax + 29], 9 - QUAD $0x1e0254203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rax + 30], 9 - QUAD $0x091f0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 31], 9 + QUAD $0x1c1d7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r13 + r11 + 28], 3 + QUAD $0x1d1d4c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r13 + r11 + 29], 3 + QUAD $0x1e1d54203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r13 + r11 + 30], 3 + QUAD $0x1f1d74203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r13 + r11 + 31], 3 + QUAD $0x1c357c203a0f4766; BYTE $0x04 // pinsrb xmm15, byte [r13 + r14 + 28], 4 + QUAD $0x1d354c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r13 + r14 + 29], 4 + QUAD $0x1e3554203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r13 + r14 + 30], 4 + QUAD $0x1f3574203a0f4366; BYTE $0x04 // pinsrb xmm6, byte [r13 + r14 + 31], 4 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + QUAD $0x1c0d7c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r13 + r9 + 28], 5 + QUAD $0x1d0d4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r13 + r9 + 29], 5 + QUAD $0x1e0d54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r13 + r9 + 30], 5 + QUAD $0x1f0d74203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r13 + r9 + 31], 5 + QUAD $0x1c3d7c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r13 + rdi + 28], 6 + QUAD $0x1d3d4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r13 + rdi + 29], 6 + QUAD $0x1e3d54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r13 + rdi + 30], 6 + QUAD $0x1f3d74203a0f4166; BYTE $0x06 // pinsrb xmm6, byte [r13 + rdi + 31], 6 + WORD $0x894c; BYTE $0xd3 // mov rbx, r10 + QUAD $0x1c157c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r13 + r10 + 28], 7 + QUAD $0x1d154c203a0f4766; BYTE $0x07 // pinsrb xmm9, byte [r13 + r10 + 29], 7 + QUAD $0x1e1554203a0f4766; BYTE $0x07 // pinsrb xmm10, byte [r13 + r10 + 30], 7 + QUAD $0x1f1574203a0f4366; BYTE $0x07 // pinsrb xmm6, byte [r13 + r10 + 31], 7 + QUAD $0x0000008824848b4c // mov r8, qword [rsp + 136] + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x1c1d7c203a0f4566; BYTE $0x08 // pinsrb xmm15, byte [r13 + rbx + 28], 8 + QUAD $0x1d1d4c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r13 + rbx + 29], 8 + QUAD $0x1e1d54203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r13 + rbx + 30], 8 + QUAD $0x1f1d74203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r13 + rbx + 31], 8 + QUAD $0x1c057c203a0f4566; BYTE $0x09 // pinsrb xmm15, byte [r13 + rax + 28], 9 + QUAD $0x1d054c203a0f4566; BYTE $0x09 // pinsrb xmm9, byte [r13 + rax + 29], 9 + QUAD $0x1e0554203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r13 + rax + 30], 9 + QUAD $0x1f0574203a0f4166; BYTE $0x09 // pinsrb xmm6, byte [r13 + rax + 31], 9 WORD $0x8948; BYTE $0xf0 // mov rax, rsi - QUAD $0x1c327c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdx + rsi + 28], 10 - QUAD $0x1d324c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rdx + rsi + 29], 10 - QUAD $0x1e3254203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdx + rsi + 30], 10 - QUAD $0x0a1f3274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 31], 10 - QUAD $0x1c2a7c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdx + r13 + 28], 11 - QUAD $0x1d2a4c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdx + r13 + 29], 11 - QUAD $0x1e2a54203a0f4666; BYTE $0x0b // pinsrb xmm10, byte [rdx + r13 + 30], 11 - QUAD $0x1f2a74203a0f4266; BYTE $0x0b // pinsrb xmm6, byte [rdx + r13 + 31], 11 - QUAD $0x1c1a7c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rdx + rbx + 28], 12 - QUAD $0x1d1a4c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rdx + rbx + 29], 12 - QUAD $0x1e1a54203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdx + rbx + 30], 12 - QUAD $0x0c1f1a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 31], 12 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x1c027c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdx + r8 + 28], 13 - QUAD $0x1d024c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rdx + r8 + 29], 13 - QUAD $0x1e0254203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdx + r8 + 30], 13 - QUAD $0x1f0274203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdx + r8 + 31], 13 - WORD $0x894c; BYTE $0xc8 // mov rax, r9 - QUAD $0x1c0a7c203a0f4666; BYTE $0x0e // pinsrb xmm15, byte [rdx + r9 + 28], 14 - QUAD $0x1d0a4c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r9 + 29], 14 - QUAD $0x1e0a54203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r9 + 30], 14 - QUAD $0x1f0a74203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdx + r9 + 31], 14 + QUAD $0x1c357c203a0f4566; BYTE $0x0a // pinsrb xmm15, byte [r13 + rsi + 28], 10 + QUAD $0x1d354c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r13 + rsi + 29], 10 + QUAD $0x1e3554203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r13 + rsi + 30], 10 + QUAD $0x1f3574203a0f4166; BYTE $0x0a // pinsrb xmm6, byte [r13 + rsi + 31], 10 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x1c3d7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r13 + r15 + 28], 11 + QUAD $0x1d3d4c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r13 + r15 + 29], 11 + QUAD $0x1e3d54203a0f4766; BYTE $0x0b // pinsrb xmm10, byte [r13 + r15 + 30], 11 + QUAD $0x1f3d74203a0f4366; BYTE $0x0b // pinsrb xmm6, byte [r13 + r15 + 31], 11 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x1c157c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r13 + rdx + 28], 12 + QUAD $0x1d154c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r13 + rdx + 29], 12 + QUAD $0x1e1554203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r13 + rdx + 30], 12 + QUAD $0x1f1574203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r13 + rdx + 31], 12 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x1c0d7c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r13 + rcx + 28], 13 + QUAD $0x1d0d4c203a0f4566; BYTE $0x0d // pinsrb xmm9, byte [r13 + rcx + 29], 13 + QUAD $0x1e0d54203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r13 + rcx + 30], 13 + QUAD $0x1f0d74203a0f4166; BYTE $0x0d // pinsrb xmm6, byte [r13 + rcx + 31], 13 LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x1c027c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rdx + rax + 28], 15 - QUAD $0x1d024c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rdx + rax + 29], 15 - QUAD $0x1e0254203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdx + rax + 30], 15 + QUAD $0x1c057c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r13 + rax + 28], 14 + QUAD $0x1d054c203a0f4566; BYTE $0x0e // pinsrb xmm9, byte [r13 + rax + 29], 14 + QUAD $0x1e0554203a0f4566; BYTE $0x0e // pinsrb xmm10, byte [r13 + rax + 30], 14 + QUAD $0x1f0574203a0f4166; BYTE $0x0e // pinsrb xmm6, byte [r13 + rax + 31], 14 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x1c257c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r13 + r12 + 28], 15 + QUAD $0x1d254c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r13 + r12 + 29], 15 + QUAD $0x1e2554203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r13 + r12 + 30], 15 LONG $0x640f4566; BYTE $0xfe // pcmpgtb xmm15, xmm14 QUAD $0x000130bddf0f4466; BYTE $0x00 // pandn xmm15, oword 304[rbp] /* [rip + .LCPI11_19] */ LONG $0xeb0f4566; BYTE $0xfb // por xmm15, xmm11 - QUAD $0x0f1f0274203a0f66 // pinsrb xmm6, byte [rdx + rax + 31], 15 + QUAD $0x1f2574203a0f4366; BYTE $0x0f // pinsrb xmm6, byte [r13 + r12 + 31], 15 QUAD $0x000160adf80f4466; BYTE $0x00 // psubb xmm13, oword 352[rbp] /* [rip + .LCPI11_22] */ LONG $0xeb0f4566; BYTE $0xfd // por xmm15, xmm13 LONG $0x640f4566; BYTE $0xce // pcmpgtb xmm9, xmm14 @@ -57879,9 +60572,9 @@ LBB11_86: LONG $0xeb0f4166; BYTE $0xf7 // por xmm6, xmm15 LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 LONG $0xc6600f66 // punpcklbw xmm0, xmm6 - QUAD $0x0000c0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 192] + QUAD $0x0000e0249c6f0f66; BYTE $0x00 // movdqa xmm3, oword [rsp + 224] LONG $0xcb6f0f66 // movdqa xmm1, xmm3 - QUAD $0x0000a024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 160] + QUAD $0x0000c024a46f0f66; BYTE $0x00 // movdqa xmm4, oword [rsp + 192] LONG $0xcc600f66 // punpcklbw xmm1, xmm4 LONG $0xd16f0f66 // movdqa xmm2, xmm1 LONG $0xd0610f66 // punpcklwd xmm2, xmm0 @@ -57891,222 +60584,218 @@ LBB11_86: LONG $0xc36f0f66 // movdqa xmm0, xmm3 LONG $0x610f4166; BYTE $0xc0 // punpcklwd xmm0, xmm8 LONG $0x690f4166; BYTE $0xd8 // punpckhwd xmm3, xmm8 - QUAD $0x000000e0248c8b48 // mov rcx, qword [rsp + 224] - LONG $0x7f0f41f3; WORD $0x8f5c; BYTE $0x30 // movdqu oword [r15 + 4*rcx + 48], xmm3 - LONG $0x7f0f41f3; WORD $0x8f44; BYTE $0x20 // movdqu oword [r15 + 4*rcx + 32], xmm0 - LONG $0x7f0f41f3; WORD $0x8f4c; BYTE $0x10 // movdqu oword [r15 + 4*rcx + 16], xmm1 - LONG $0x7f0f41f3; WORD $0x8f14 // movdqu oword [r15 + 4*rcx], xmm2 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + LONG $0x7f0f41f3; WORD $0x885c; BYTE $0x30 // movdqu oword [r8 + 4*rcx + 48], xmm3 + LONG $0x7f0f41f3; WORD $0x8844; BYTE $0x20 // movdqu oword [r8 + 4*rcx + 32], xmm0 + LONG $0x7f0f41f3; WORD $0x884c; BYTE $0x10 // movdqu oword [r8 + 4*rcx + 16], xmm1 + LONG $0x7f0f41f3; WORD $0x8814 // movdqu oword [r8 + 4*rcx], xmm2 LONG $0x10c18348 // add rcx, 16 WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x00000100248c3b48 // cmp rcx, qword [rsp + 256] - JNE LBB11_86 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x0000010024943b4c // cmp r10, qword [rsp + 256] - LONG $0x24348a44 // mov r14b, byte [rsp] - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0000011824948b48 // mov rdx, qword [rsp + 280] - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - JNE LBB11_88 - JMP LBB11_91 + QUAD $0x000000b8248c3b48 // cmp rcx, qword [rsp + 184] + JNE LBB11_223 + QUAD $0x00000110248c8b48 // mov rcx, qword [rsp + 272] + QUAD $0x000000b8248c3b48 // cmp rcx, qword [rsp + 184] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x24748a44; BYTE $0x08 // mov r14b, byte [rsp + 8] + QUAD $0x0000010824ac8b4c // mov r13, qword [rsp + 264] + QUAD $0x0000010024bc8b48 // mov rdi, qword [rsp + 256] + JNE LBB11_146 + JMP LBB11_150 -LBB11_66: - LONG $0xf0e28349 // and r10, -16 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 +LBB11_225: + LONG $0xf0e18348 // and rcx, -16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx LONG $0x05e0c148 // shl rax, 5 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - QUAD $0x0000011824848948 // mov qword [rsp + 280], rax - QUAD $0x000000c02494894c // mov qword [rsp + 192], r10 - LONG $0x97048d4b // lea rax, [r15 + 4*r10] - QUAD $0x0000012024848948 // mov qword [rsp + 288], rax - LONG $0xc6b60f41 // movzx eax, r14b + WORD $0x014c; BYTE $0xd8 // add rax, r11 + QUAD $0x0000010824848948 // mov qword [rsp + 264], rax + QUAD $0x000000b8248c8948 // mov qword [rsp + 184], rcx + LONG $0x8c048d49 // lea rax, [r12 + 4*rcx] + LONG $0x24448948; BYTE $0x70 // mov qword [rsp + 112], rax + LONG $0xc5b60f41 // movzx eax, r13b LONG $0xc86e0f66 // movd xmm1, eax LONG $0xc0ef0f66 // pxor xmm0, xmm0 LONG $0x00380f66; BYTE $0xc8 // pshufb xmm1, xmm0 - QUAD $0x000100248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 256], xmm1 + QUAD $0x000110248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 272], xmm1 WORD $0xc031 // xor eax, eax - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - QUAD $0x010024846f0f4466; WORD $0x0000 // movdqa xmm8, oword [rsp + 256] + QUAD $0x0000008824a4894c // mov qword [rsp + 136], r12 + QUAD $0x011024846f0f4466; WORD $0x0000 // movdqa xmm8, oword [rsp + 272] -LBB11_67: - QUAD $0x0000008024848948 // mov qword [rsp + 128], rax +LBB11_226: + QUAD $0x0000009024848948 // mov qword [rsp + 144], rax LONG $0x05e0c148 // shl rax, 5 - WORD $0x8949; BYTE $0xc6 // mov r14, rax WORD $0x8948; BYTE $0xc3 // mov rbx, rax WORD $0x8949; BYTE $0xc7 // mov r15, rax - LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + WORD $0x8949; BYTE $0xc6 // mov r14, rax WORD $0x8949; BYTE $0xc4 // mov r12, rax + WORD $0x8948; BYTE $0xc2 // mov rdx, rax WORD $0x8949; BYTE $0xc0 // mov r8, rax - WORD $0x8949; BYTE $0xc3 // mov r11, rax + WORD $0x8949; BYTE $0xc5 // mov r13, rax + LONG $0x24448948; BYTE $0x68 // mov qword [rsp + 104], rax WORD $0x8949; BYTE $0xc1 // mov r9, rax - WORD $0x8949; BYTE $0xc2 // mov r10, rax WORD $0x8948; BYTE $0xc6 // mov rsi, rax WORD $0x8948; BYTE $0xc7 // mov rdi, rax - LONG $0x020cb60f // movzx ecx, byte [rdx + rax] + LONG $0x0cb60f41; BYTE $0x03 // movzx ecx, byte [r11 + rax] LONG $0xf16e0f66 // movd xmm6, ecx - LONG $0x024cb60f; BYTE $0x01 // movzx ecx, byte [rdx + rax + 1] + LONG $0x4cb60f41; WORD $0x0103 // movzx ecx, byte [r11 + rax + 1] LONG $0x6e0f4466; BYTE $0xf9 // movd xmm15, ecx - LONG $0x024cb60f; BYTE $0x02 // movzx ecx, byte [rdx + rax + 2] + LONG $0x4cb60f41; WORD $0x0203 // movzx ecx, byte [r11 + rax + 2] LONG $0xe96e0f66 // movd xmm5, ecx - LONG $0x024cb60f; BYTE $0x03 // movzx ecx, byte [rdx + rax + 3] + LONG $0x4cb60f41; WORD $0x0303 // movzx ecx, byte [r11 + rax + 3] LONG $0xe16e0f66 // movd xmm4, ecx - LONG $0x024cb60f; BYTE $0x04 // movzx ecx, byte [rdx + rax + 4] + LONG $0x4cb60f41; WORD $0x0403 // movzx ecx, byte [r11 + rax + 4] LONG $0xd96e0f66 // movd xmm3, ecx - LONG $0x024cb60f; BYTE $0x05 // movzx ecx, byte [rdx + rax + 5] + LONG $0x4cb60f41; WORD $0x0503 // movzx ecx, byte [r11 + rax + 5] LONG $0xf96e0f66 // movd xmm7, ecx - LONG $0x024cb60f; BYTE $0x06 // movzx ecx, byte [rdx + rax + 6] + LONG $0x4cb60f41; WORD $0x0603 // movzx ecx, byte [r11 + rax + 6] LONG $0xd16e0f66 // movd xmm2, ecx - LONG $0x024cb60f; BYTE $0x07 // movzx ecx, byte [rdx + rax + 7] + LONG $0x4cb60f41; WORD $0x0703 // movzx ecx, byte [r11 + rax + 7] LONG $0x6e0f4466; BYTE $0xc9 // movd xmm9, ecx - LONG $0x024cb60f; BYTE $0x08 // movzx ecx, byte [rdx + rax + 8] + LONG $0x4cb60f41; WORD $0x0803 // movzx ecx, byte [r11 + rax + 8] LONG $0xc16e0f66 // movd xmm0, ecx - QUAD $0x0000e024847f0f66; BYTE $0x00 // movdqa oword [rsp + 224], xmm0 - LONG $0x024cb60f; BYTE $0x09 // movzx ecx, byte [rdx + rax + 9] + QUAD $0x0000f024847f0f66; BYTE $0x00 // movdqa oword [rsp + 240], xmm0 + LONG $0x4cb60f41; WORD $0x0903 // movzx ecx, byte [r11 + rax + 9] LONG $0x6e0f4466; BYTE $0xd1 // movd xmm10, ecx - LONG $0x024cb60f; BYTE $0x0a // movzx ecx, byte [rdx + rax + 10] + LONG $0x4cb60f41; WORD $0x0a03 // movzx ecx, byte [r11 + rax + 10] LONG $0x6e0f4466; BYTE $0xe1 // movd xmm12, ecx - LONG $0x024cb60f; BYTE $0x0b // movzx ecx, byte [rdx + rax + 11] + LONG $0x4cb60f41; WORD $0x0b03 // movzx ecx, byte [r11 + rax + 11] LONG $0x6e0f4466; BYTE $0xd9 // movd xmm11, ecx - LONG $0x024cb60f; BYTE $0x0c // movzx ecx, byte [rdx + rax + 12] + LONG $0x4cb60f41; WORD $0x0c03 // movzx ecx, byte [r11 + rax + 12] LONG $0x6e0f4466; BYTE $0xe9 // movd xmm13, ecx - LONG $0x024cb60f; BYTE $0x0d // movzx ecx, byte [rdx + rax + 13] + LONG $0x4cb60f41; WORD $0x0d03 // movzx ecx, byte [r11 + rax + 13] LONG $0xc16e0f66 // movd xmm0, ecx - LONG $0x024cb60f; BYTE $0x0e // movzx ecx, byte [rdx + rax + 14] + LONG $0x4cb60f41; WORD $0x0e03 // movzx ecx, byte [r11 + rax + 14] LONG $0x6e0f4466; BYTE $0xf1 // movd xmm14, ecx - LONG $0x024cb60f; BYTE $0x0f // movzx ecx, byte [rdx + rax + 15] + LONG $0x4cb60f41; WORD $0x0f03 // movzx ecx, byte [r11 + rax + 15] LONG $0xc96e0f66 // movd xmm1, ecx - QUAD $0x0000b0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm1 + QUAD $0x0000d0248c7f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm1 LONG $0x24448948; BYTE $0x50 // mov qword [rsp + 80], rax - WORD $0x8949; BYTE $0xc5 // mov r13, rax - LONG $0x20cd8349 // or r13, 32 - LONG $0x246c894c; BYTE $0x28 // mov qword [rsp + 40], r13 - LONG $0x40ce8349 // or r14, 64 - LONG $0x60cb8348 // or rbx, 96 - LONG $0x80cf8149; WORD $0x0000; BYTE $0x00 // or r15, 128 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - LONG $0xa0c98148; WORD $0x0000; BYTE $0x00 // or rcx, 160 - LONG $0x244c8948; BYTE $0x20 // mov qword [rsp + 32], rcx - LONG $0xc0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 192 + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0x20c98348 // or rcx, 32 + LONG $0x244c8948; BYTE $0x38 // mov qword [rsp + 56], rcx + LONG $0x40cb8348 // or rbx, 64 + LONG $0x245c8948; BYTE $0x40 // mov qword [rsp + 64], rbx + LONG $0x60cf8349 // or r15, 96 + LONG $0x80ce8149; WORD $0x0000; BYTE $0x00 // or r14, 128 + QUAD $0x000000a024b4894c // mov qword [rsp + 160], r14 + LONG $0xa0cc8149; WORD $0x0000; BYTE $0x00 // or r12, 160 + LONG $0xc0ca8148; WORD $0x0000; BYTE $0x00 // or rdx, 192 LONG $0xe0c88149; WORD $0x0000; BYTE $0x00 // or r8, 224 - LONG $0x00cb8149; WORD $0x0001; BYTE $0x00 // or r11, 256 - LONG $0x20c98149; WORD $0x0001; BYTE $0x00 // or r9, 288 - LONG $0x40ca8149; WORD $0x0001; BYTE $0x00 // or r10, 320 + WORD $0x8949; BYTE $0xc2 // mov r10, rax + LONG $0x00ca8149; WORD $0x0001; BYTE $0x00 // or r10, 256 + LONG $0x246c8b4c; BYTE $0x68 // mov r13, qword [rsp + 104] + LONG $0x20cd8149; WORD $0x0001; BYTE $0x00 // or r13, 288 + LONG $0x40c98149; WORD $0x0001; BYTE $0x00 // or r9, 320 LONG $0x60ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 352 - LONG $0x24748948; BYTE $0x58 // mov qword [rsp + 88], rsi + LONG $0x24748948; BYTE $0x18 // mov qword [rsp + 24], rsi WORD $0x8948; BYTE $0xc6 // mov rsi, rax LONG $0x80ce8148; WORD $0x0001; BYTE $0x00 // or rsi, 384 - LONG $0x24748948; BYTE $0x70 // mov qword [rsp + 112], rsi - LONG $0xa0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 416 - LONG $0x247c8948; BYTE $0x10 // mov qword [rsp + 16], rdi - WORD $0x8948; BYTE $0xc7 // mov rdi, rax + LONG $0x24748948; BYTE $0x30 // mov qword [rsp + 48], rsi + WORD $0x8948; BYTE $0xc1 // mov rcx, rax + LONG $0xa0c98148; WORD $0x0001; BYTE $0x00 // or rcx, 416 + LONG $0x244c8948; BYTE $0x10 // mov qword [rsp + 16], rcx LONG $0xc0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 448 - LONG $0x247c8948; BYTE $0x18 // mov qword [rsp + 24], rdi - WORD $0x8948; BYTE $0xc7 // mov rdi, rax - LONG $0xe0cf8148; WORD $0x0001; BYTE $0x00 // or rdi, 480 - LONG $0x247c8948; BYTE $0x08 // mov qword [rsp + 8], rdi - QUAD $0x012a34203a0f4266 // pinsrb xmm6, byte [rdx + r13], 1 - QUAD $0x023234203a0f4266 // pinsrb xmm6, byte [rdx + r14], 2 - LONG $0x245c8948; BYTE $0x68 // mov qword [rsp + 104], rbx - LONG $0x203a0f66; WORD $0x1a34; BYTE $0x03 // pinsrb xmm6, byte [rdx + rbx], 3 - QUAD $0x043a34203a0f4266 // pinsrb xmm6, byte [rdx + r15], 4 - LONG $0x203a0f66; WORD $0x0a34; BYTE $0x05 // pinsrb xmm6, byte [rdx + rcx], 5 - QUAD $0x062234203a0f4266 // pinsrb xmm6, byte [rdx + r12], 6 - LONG $0x2444894c; BYTE $0x38 // mov qword [rsp + 56], r8 - QUAD $0x070234203a0f4266 // pinsrb xmm6, byte [rdx + r8], 7 - LONG $0x245c894c; BYTE $0x48 // mov qword [rsp + 72], r11 - QUAD $0x081a34203a0f4266 // pinsrb xmm6, byte [rdx + r11], 8 - WORD $0x894d; BYTE $0xcb // mov r11, r9 - LONG $0x244c894c; BYTE $0x60 // mov qword [rsp + 96], r9 - QUAD $0x090a34203a0f4266 // pinsrb xmm6, byte [rdx + r9], 9 - WORD $0x894d; BYTE $0xd1 // mov r9, r10 - QUAD $0x0a1234203a0f4266 // pinsrb xmm6, byte [rdx + r10], 10 - LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] - QUAD $0x0b1234203a0f4266 // pinsrb xmm6, byte [rdx + r10], 11 - LONG $0x203a0f66; WORD $0x3234; BYTE $0x0c // pinsrb xmm6, byte [rdx + rsi], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - LONG $0x203a0f66; WORD $0x0234; BYTE $0x0d // pinsrb xmm6, byte [rdx + rax], 13 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x0e2a34203a0f4266 // pinsrb xmm6, byte [rdx + r13], 14 - LONG $0x203a0f66; WORD $0x3a34; BYTE $0x0f // pinsrb xmm6, byte [rdx + rdi], 15 + LONG $0x01e00d48; WORD $0x0000 // or rax, 480 + LONG $0x24448948; BYTE $0x20 // mov qword [rsp + 32], rax + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x010b34203a0f4166 // pinsrb xmm6, byte [r11 + rcx], 1 + QUAD $0x021b34203a0f4166 // pinsrb xmm6, byte [r11 + rbx], 2 + QUAD $0x000000c024bc894c // mov qword [rsp + 192], r15 + QUAD $0x033b34203a0f4366 // pinsrb xmm6, byte [r11 + r15], 3 + QUAD $0x043334203a0f4366 // pinsrb xmm6, byte [r11 + r14], 4 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x0000008024a4894c // mov qword [rsp + 128], r12 + QUAD $0x052334203a0f4366 // pinsrb xmm6, byte [r11 + r12], 5 + QUAD $0x061334203a0f4166 // pinsrb xmm6, byte [r11 + rdx], 6 + WORD $0x894c; BYTE $0xc3 // mov rbx, r8 + QUAD $0x070334203a0f4366 // pinsrb xmm6, byte [r11 + r8], 7 + LONG $0x2454894c; BYTE $0x48 // mov qword [rsp + 72], r10 + QUAD $0x081334203a0f4366 // pinsrb xmm6, byte [r11 + r10], 8 + QUAD $0x092b34203a0f4366 // pinsrb xmm6, byte [r11 + r13], 9 + WORD $0x894d; BYTE $0xc8 // mov r8, r9 + QUAD $0x0a0b34203a0f4366 // pinsrb xmm6, byte [r11 + r9], 10 + LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] + QUAD $0x0b0b34203a0f4366 // pinsrb xmm6, byte [r11 + r9], 11 + QUAD $0x0c3334203a0f4166 // pinsrb xmm6, byte [r11 + rsi], 12 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x0d2334203a0f4366 // pinsrb xmm6, byte [r11 + r12], 13 + QUAD $0x0e3b34203a0f4166 // pinsrb xmm6, byte [r11 + rdi], 14 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x0f3334203a0f4366 // pinsrb xmm6, byte [r11 + r14], 15 LONG $0xde0f4166; BYTE $0xf0 // pmaxub xmm6, xmm8 LONG $0x740f4166; BYTE $0xf0 // pcmpeqb xmm6, xmm8 - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x013a7c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rdi + 1], 1 - QUAD $0x01327c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rdx + r14 + 1], 2 - QUAD $0x011a7c203a0f4466; BYTE $0x03 // pinsrb xmm15, byte [rdx + rbx + 1], 3 - QUAD $0x013a7c203a0f4666; BYTE $0x04 // pinsrb xmm15, byte [rdx + r15 + 1], 4 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - QUAD $0x010a7c203a0f4466; BYTE $0x05 // pinsrb xmm15, byte [rdx + rcx + 1], 5 - QUAD $0x01227c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdx + r12 + 1], 6 - WORD $0x894d; BYTE $0xe7 // mov r15, r12 - QUAD $0x01027c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r8 + 1], 7 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x012a7c203a0f4666; BYTE $0x08 // pinsrb xmm15, byte [rdx + r13 + 1], 8 - QUAD $0x011a7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdx + r11 + 1], 9 - QUAD $0x010a7c203a0f4666; BYTE $0x0a // pinsrb xmm15, byte [rdx + r9 + 1], 10 - LONG $0x244c894c; BYTE $0x40 // mov qword [rsp + 64], r9 - QUAD $0x01127c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdx + r10 + 1], 11 - WORD $0x894c; BYTE $0xd1 // mov rcx, r10 - QUAD $0x01327c203a0f4466; BYTE $0x0c // pinsrb xmm15, byte [rdx + rsi + 1], 12 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x01227c203a0f4666; BYTE $0x0d // pinsrb xmm15, byte [rdx + r12 + 1], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x01027c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdx + rax + 1], 14 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x01027c203a0f4466; BYTE $0x0f // pinsrb xmm15, byte [rdx + rax + 1], 15 + QUAD $0x010b7c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r11 + rcx + 1], 1 + LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] + QUAD $0x010b7c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r11 + rcx + 1], 2 + QUAD $0x013b7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r11 + r15 + 1], 3 + QUAD $0x000000a0248c8b48 // mov rcx, qword [rsp + 160] + QUAD $0x010b7c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r11 + rcx + 1], 4 + QUAD $0x01037c203a0f4566; BYTE $0x05 // pinsrb xmm15, byte [r11 + rax + 1], 5 + QUAD $0x01137c203a0f4566; BYTE $0x06 // pinsrb xmm15, byte [r11 + rdx + 1], 6 + WORD $0x8948; BYTE $0xd0 // mov rax, rdx + QUAD $0x011b7c203a0f4566; BYTE $0x07 // pinsrb xmm15, byte [r11 + rbx + 1], 7 + QUAD $0x01137c203a0f4766; BYTE $0x08 // pinsrb xmm15, byte [r11 + r10 + 1], 8 + QUAD $0x012b7c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r11 + r13 + 1], 9 + WORD $0x894d; BYTE $0xef // mov r15, r13 + QUAD $0x01037c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r11 + r8 + 1], 10 + LONG $0x2444894c; BYTE $0x28 // mov qword [rsp + 40], r8 + QUAD $0x010b7c203a0f4766; BYTE $0x0b // pinsrb xmm15, byte [r11 + r9 + 1], 11 + QUAD $0x01337c203a0f4566; BYTE $0x0c // pinsrb xmm15, byte [r11 + rsi + 1], 12 + QUAD $0x01237c203a0f4766; BYTE $0x0d // pinsrb xmm15, byte [r11 + r12 + 1], 13 + QUAD $0x013b7c203a0f4566; BYTE $0x0e // pinsrb xmm15, byte [r11 + rdi + 1], 14 + LONG $0x247c8948; BYTE $0x60 // mov qword [rsp + 96], rdi + QUAD $0x01337c203a0f4766; BYTE $0x0f // pinsrb xmm15, byte [r11 + r14 + 1], 15 LONG $0xde0f4566; BYTE $0xf8 // pmaxub xmm15, xmm8 LONG $0x740f4566; BYTE $0xf8 // pcmpeqb xmm15, xmm8 QUAD $0x000001008d6f0f66 // movdqa xmm1, oword 256[rbp] /* [rip + .LCPI11_16] */ LONG $0xdb0f4466; BYTE $0xf9 // pand xmm15, xmm1 LONG $0xf80f4466; BYTE $0xfe // psubb xmm15, xmm6 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - LONG $0x0274b60f; BYTE $0x10 // movzx esi, byte [rdx + rax + 16] + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + LONG $0x74b60f41; WORD $0x1013 // movzx esi, byte [r11 + rdx + 16] LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x01023a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 2], 1 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - LONG $0x2474894c; BYTE $0x30 // mov qword [rsp + 48], r14 - QUAD $0x02326c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rdx + r14 + 2], 2 - LONG $0x24748b4c; BYTE $0x68 // mov r14, qword [rsp + 104] - QUAD $0x02326c203a0f4266; BYTE $0x03 // pinsrb xmm5, byte [rdx + r14 + 2], 3 - WORD $0x8949; BYTE $0xda // mov r10, rbx - QUAD $0x04021a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 2], 4 - LONG $0x24448b48; BYTE $0x20 // mov rax, qword [rsp + 32] - QUAD $0x0502026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 2], 5 - WORD $0x894c; BYTE $0xfb // mov rbx, r15 - QUAD $0x023a6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r15 + 2], 6 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x0702326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 2], 7 - WORD $0x894d; BYTE $0xeb // mov r11, r13 - QUAD $0x022a6c203a0f4266; BYTE $0x08 // pinsrb xmm5, byte [rdx + r13 + 2], 8 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x023a6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r15 + 2], 9 - QUAD $0x020a6c203a0f4266; BYTE $0x0a // pinsrb xmm5, byte [rdx + r9 + 2], 10 - QUAD $0x0b020a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 2], 11 - LONG $0x244c8b48; BYTE $0x70 // mov rcx, qword [rsp + 112] - QUAD $0x0c020a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 2], 12 - WORD $0x894d; BYTE $0xe5 // mov r13, r12 - QUAD $0x02226c203a0f4266; BYTE $0x0d // pinsrb xmm5, byte [rdx + r12 + 2], 13 - LONG $0x244c8b4c; BYTE $0x18 // mov r9, qword [rsp + 24] - QUAD $0x020a6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdx + r9 + 2], 14 - LONG $0x24648b4c; BYTE $0x08 // mov r12, qword [rsp + 8] - QUAD $0x02226c203a0f4266; BYTE $0x0f // pinsrb xmm5, byte [rdx + r12 + 2], 15 - QUAD $0x01033a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 3], 1 - QUAD $0x030264203a0f4266; BYTE $0x02 // pinsrb xmm4, byte [rdx + r8 + 3], 2 - QUAD $0x033264203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r14 + 3], 3 - QUAD $0x031264203a0f4266; BYTE $0x04 // pinsrb xmm4, byte [rdx + r10 + 3], 4 - QUAD $0x05030264203a0f66 // pinsrb xmm4, byte [rdx + rax + 3], 5 - QUAD $0x06031a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 3], 6 - QUAD $0x07033264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 3], 7 - QUAD $0x031a64203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r11 + 3], 8 - QUAD $0x033a64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r15 + 3], 9 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x031a64203a0f4266; BYTE $0x0a // pinsrb xmm4, byte [rdx + r11 + 3], 10 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x030264203a0f4266; BYTE $0x0b // pinsrb xmm4, byte [rdx + r8 + 3], 11 - QUAD $0x0c030a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 3], 12 - QUAD $0x032a64203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdx + r13 + 3], 13 - QUAD $0x030a64203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdx + r9 + 3], 14 - QUAD $0x032264203a0f4266; BYTE $0x0f // pinsrb xmm4, byte [rdx + r12 + 3], 15 + LONG $0x24548b48; BYTE $0x38 // mov rdx, qword [rsp + 56] + QUAD $0x02136c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r11 + rdx + 2], 1 + LONG $0x24748b4c; BYTE $0x40 // mov r14, qword [rsp + 64] + QUAD $0x02336c203a0f4366; BYTE $0x02 // pinsrb xmm5, byte [r11 + r14 + 2], 2 + QUAD $0x000000c0248c8b4c // mov r9, qword [rsp + 192] + QUAD $0x020b6c203a0f4366; BYTE $0x03 // pinsrb xmm5, byte [r11 + r9 + 2], 3 + WORD $0x8949; BYTE $0xca // mov r10, rcx + QUAD $0x020b6c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r11 + rcx + 2], 4 + QUAD $0x0000008024ac8b4c // mov r13, qword [rsp + 128] + QUAD $0x022b6c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r11 + r13 + 2], 5 + QUAD $0x02036c203a0f4166; BYTE $0x06 // pinsrb xmm5, byte [r11 + rax + 2], 6 + QUAD $0x021b6c203a0f4166; BYTE $0x07 // pinsrb xmm5, byte [r11 + rbx + 2], 7 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x02336c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r11 + rsi + 2], 8 + QUAD $0x023b6c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r11 + r15 + 2], 9 + QUAD $0x02036c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r11 + r8 + 2], 10 + LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] + QUAD $0x02036c203a0f4366; BYTE $0x0b // pinsrb xmm5, byte [r11 + r8 + 2], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x020b6c203a0f4166; BYTE $0x0c // pinsrb xmm5, byte [r11 + rcx + 2], 12 + QUAD $0x02236c203a0f4366; BYTE $0x0d // pinsrb xmm5, byte [r11 + r12 + 2], 13 + QUAD $0x023b6c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r11 + rdi + 2], 14 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x023b6c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r11 + rdi + 2], 15 + QUAD $0x031364203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r11 + rdx + 3], 1 + QUAD $0x033364203a0f4366; BYTE $0x02 // pinsrb xmm4, byte [r11 + r14 + 3], 2 + QUAD $0x030b64203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r11 + r9 + 3], 3 + QUAD $0x031364203a0f4366; BYTE $0x04 // pinsrb xmm4, byte [r11 + r10 + 3], 4 + QUAD $0x032b64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r11 + r13 + 3], 5 + QUAD $0x030364203a0f4166; BYTE $0x06 // pinsrb xmm4, byte [r11 + rax + 3], 6 + QUAD $0x031b64203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r11 + rbx + 3], 7 + LONG $0x245c8948; BYTE $0x58 // mov qword [rsp + 88], rbx + QUAD $0x033364203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r11 + rsi + 3], 8 + QUAD $0x033b64203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r11 + r15 + 3], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x031364203a0f4166; BYTE $0x0a // pinsrb xmm4, byte [r11 + rdx + 3], 10 + QUAD $0x030364203a0f4366; BYTE $0x0b // pinsrb xmm4, byte [r11 + r8 + 3], 11 + QUAD $0x030b64203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r11 + rcx + 3], 12 + WORD $0x8949; BYTE $0xc8 // mov r8, rcx + QUAD $0x032364203a0f4366; BYTE $0x0d // pinsrb xmm4, byte [r11 + r12 + 3], 13 + WORD $0x894c; BYTE $0xe1 // mov rcx, r12 + LONG $0x24548b48; BYTE $0x60 // mov rdx, qword [rsp + 96] + QUAD $0x031364203a0f4166; BYTE $0x0e // pinsrb xmm4, byte [r11 + rdx + 3], 14 + QUAD $0x033b64203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r11 + rdi + 3], 15 LONG $0xde0f4166; BYTE $0xe8 // pmaxub xmm5, xmm8 LONG $0x740f4166; BYTE $0xe8 // pcmpeqb xmm5, xmm8 QUAD $0x00000110b56f0f66 // movdqa xmm6, oword 272[rbp] /* [rip + .LCPI11_17] */ @@ -58116,80 +60805,75 @@ LBB11_67: QUAD $0x00000120b56f0f66 // movdqa xmm6, oword 288[rbp] /* [rip + .LCPI11_18] */ LONG $0xe6db0f66 // pand xmm4, xmm6 LONG $0xe5eb0f66 // por xmm4, xmm5 - LONG $0x244c8b48; BYTE $0x50 // mov rcx, qword [rsp + 80] - LONG $0x0a74b60f; BYTE $0x11 // movzx esi, byte [rdx + rcx + 17] + LONG $0x24548b48; BYTE $0x50 // mov rdx, qword [rsp + 80] + LONG $0x74b60f41; WORD $0x1113 // movzx esi, byte [r11 + rdx + 17] LONG $0xee6e0f66 // movd xmm5, esi LONG $0xeb0f4166; BYTE $0xe7 // por xmm4, xmm15 - LONG $0x0a74b60f; BYTE $0x12 // movzx esi, byte [rdx + rcx + 18] + LONG $0x74b60f41; WORD $0x1213 // movzx esi, byte [r11 + rdx + 18] LONG $0x6e0f4466; BYTE $0xfe // movd xmm15, esi - WORD $0x8949; BYTE $0xfe // mov r14, rdi - QUAD $0x01043a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 4], 1 - LONG $0x246c8b4c; BYTE $0x30 // mov r13, qword [rsp + 48] - QUAD $0x042a5c203a0f4266; BYTE $0x02 // pinsrb xmm3, byte [rdx + r13 + 4], 2 - LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] - QUAD $0x04225c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r12 + 4], 3 - QUAD $0x000000902494894c // mov qword [rsp + 144], r10 - QUAD $0x04125c203a0f4266; BYTE $0x04 // pinsrb xmm3, byte [rdx + r10 + 4], 4 - QUAD $0x0504025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 4], 5 - QUAD $0x06041a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 4], 6 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x07040a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 4], 7 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x08040a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 4], 8 - QUAD $0x043a5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdx + r15 + 4], 9 - WORD $0x894c; BYTE $0xde // mov rsi, r11 - QUAD $0x041a5c203a0f4266; BYTE $0x0a // pinsrb xmm3, byte [rdx + r11 + 4], 10 - QUAD $0x04025c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r8 + 4], 11 - LONG $0x244c8b4c; BYTE $0x70 // mov r9, qword [rsp + 112] - QUAD $0x040a5c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r9 + 4], 12 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0d040a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 4], 13 - LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] - QUAD $0x0e043a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 4], 14 - LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] - QUAD $0x041a5c203a0f4266; BYTE $0x0f // pinsrb xmm3, byte [rdx + r11 + 4], 15 - QUAD $0x05327c203a0f4266; BYTE $0x01 // pinsrb xmm7, byte [rdx + r14 + 5], 1 - QUAD $0x052a7c203a0f4266; BYTE $0x02 // pinsrb xmm7, byte [rdx + r13 + 5], 2 - QUAD $0x05227c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r12 + 5], 3 - QUAD $0x05127c203a0f4266; BYTE $0x04 // pinsrb xmm7, byte [rdx + r10 + 5], 4 - QUAD $0x0505027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 5], 5 - QUAD $0x06051a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 5], 6 - LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] - QUAD $0x07050a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 5], 7 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x08050a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 5], 8 - QUAD $0x053a7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdx + r15 + 5], 9 - QUAD $0x0a05327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 5], 10 - QUAD $0x05027c203a0f4266; BYTE $0x0b // pinsrb xmm7, byte [rdx + r8 + 5], 11 - QUAD $0x050a7c203a0f4266; BYTE $0x0c // pinsrb xmm7, byte [rdx + r9 + 5], 12 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0d050a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 5], 13 - QUAD $0x0e053a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 5], 14 - QUAD $0x051a7c203a0f4266; BYTE $0x0f // pinsrb xmm7, byte [rdx + r11 + 5], 15 - QUAD $0x063254203a0f4266; BYTE $0x01 // pinsrb xmm2, byte [rdx + r14 + 6], 1 - QUAD $0x062a54203a0f4266; BYTE $0x02 // pinsrb xmm2, byte [rdx + r13 + 6], 2 - QUAD $0x062254203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r12 + 6], 3 - QUAD $0x061254203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r10 + 6], 4 - QUAD $0x05060254203a0f66 // pinsrb xmm2, byte [rdx + rax + 6], 5 - WORD $0x8949; BYTE $0xc2 // mov r10, rax - QUAD $0x06061a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 6], 6 - WORD $0x8949; BYTE $0xdd // mov r13, rbx - QUAD $0x000000a0249c8948 // mov qword [rsp + 160], rbx - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x07060254203a0f66 // pinsrb xmm2, byte [rdx + rax + 6], 7 - WORD $0x8949; BYTE $0xc6 // mov r14, rax + LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] + QUAD $0x04335c203a0f4366; BYTE $0x01 // pinsrb xmm3, byte [r11 + r14 + 4], 1 + LONG $0x24548b48; BYTE $0x40 // mov rdx, qword [rsp + 64] + QUAD $0x04135c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r11 + rdx + 4], 2 + QUAD $0x040b5c203a0f4366; BYTE $0x03 // pinsrb xmm3, byte [r11 + r9 + 4], 3 + QUAD $0x04135c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r11 + r10 + 4], 4 + WORD $0x894d; BYTE $0xec // mov r12, r13 + QUAD $0x042b5c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r11 + r13 + 4], 5 + LONG $0x24448948; BYTE $0x78 // mov qword [rsp + 120], rax + QUAD $0x04035c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r11 + rax + 4], 6 + QUAD $0x041b5c203a0f4166; BYTE $0x07 // pinsrb xmm3, byte [r11 + rbx + 4], 7 LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x08061a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 6], 8 - QUAD $0x063a54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r15 + 6], 9 - WORD $0x894d; BYTE $0xfb // mov r11, r15 - QUAD $0x0a063254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 6], 10 - QUAD $0x060254203a0f4266; BYTE $0x0b // pinsrb xmm2, byte [rdx + r8 + 6], 11 - WORD $0x894d; BYTE $0xc4 // mov r12, r8 - QUAD $0x060a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r9 + 6], 12 - QUAD $0x0d060a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 6], 13 - QUAD $0x0e063a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 6], 14 - LONG $0x247c8b4c; BYTE $0x08 // mov r15, qword [rsp + 8] - QUAD $0x063a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r15 + 6], 15 + QUAD $0x041b5c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r11 + rbx + 4], 8 + LONG $0x247c894c; BYTE $0x68 // mov qword [rsp + 104], r15 + QUAD $0x043b5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r11 + r15 + 4], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x04335c203a0f4166; BYTE $0x0a // pinsrb xmm3, byte [r11 + rsi + 4], 10 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x04135c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r11 + rdx + 4], 11 + QUAD $0x04035c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r11 + r8 + 4], 12 + QUAD $0x040b5c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r11 + rcx + 4], 13 + LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] + QUAD $0x043b5c203a0f4166; BYTE $0x0e // pinsrb xmm3, byte [r11 + rdi + 4], 14 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x040b5c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r11 + rcx + 4], 15 + QUAD $0x05337c203a0f4366; BYTE $0x01 // pinsrb xmm7, byte [r11 + r14 + 5], 1 + LONG $0x24548b4c; BYTE $0x40 // mov r10, qword [rsp + 64] + QUAD $0x05137c203a0f4366; BYTE $0x02 // pinsrb xmm7, byte [r11 + r10 + 5], 2 + QUAD $0x050b7c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r11 + r9 + 5], 3 + QUAD $0x000000a024ac8b4c // mov r13, qword [rsp + 160] + QUAD $0x052b7c203a0f4366; BYTE $0x04 // pinsrb xmm7, byte [r11 + r13 + 5], 4 + QUAD $0x05237c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r11 + r12 + 5], 5 + QUAD $0x05037c203a0f4166; BYTE $0x06 // pinsrb xmm7, byte [r11 + rax + 5], 6 + LONG $0x246c8b4c; BYTE $0x58 // mov r13, qword [rsp + 88] + QUAD $0x052b7c203a0f4366; BYTE $0x07 // pinsrb xmm7, byte [r11 + r13 + 5], 7 + QUAD $0x051b7c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r11 + rbx + 5], 8 + QUAD $0x053b7c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r11 + r15 + 5], 9 + QUAD $0x05337c203a0f4166; BYTE $0x0a // pinsrb xmm7, byte [r11 + rsi + 5], 10 + QUAD $0x05137c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r11 + rdx + 5], 11 + QUAD $0x05037c203a0f4366; BYTE $0x0c // pinsrb xmm7, byte [r11 + r8 + 5], 12 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x05237c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r11 + r12 + 5], 13 + QUAD $0x053b7c203a0f4166; BYTE $0x0e // pinsrb xmm7, byte [r11 + rdi + 5], 14 + QUAD $0x050b7c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r11 + rcx + 5], 15 + QUAD $0x063354203a0f4366; BYTE $0x01 // pinsrb xmm2, byte [r11 + r14 + 6], 1 + QUAD $0x061354203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r11 + r10 + 6], 2 + QUAD $0x060b54203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r9 + 6], 3 + QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] + QUAD $0x061354203a0f4366; BYTE $0x04 // pinsrb xmm2, byte [r11 + r10 + 6], 4 + QUAD $0x00000080248c8b4c // mov r9, qword [rsp + 128] + QUAD $0x060b54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r11 + r9 + 6], 5 + QUAD $0x060354203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r11 + rax + 6], 6 + QUAD $0x062b54203a0f4366; BYTE $0x07 // pinsrb xmm2, byte [r11 + r13 + 6], 7 + QUAD $0x061b54203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r11 + rbx + 6], 8 + QUAD $0x063b54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r15 + 6], 9 + QUAD $0x063354203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r11 + rsi + 6], 10 + QUAD $0x061354203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r11 + rdx + 6], 11 + QUAD $0x060354203a0f4366; BYTE $0x0c // pinsrb xmm2, byte [r11 + r8 + 6], 12 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + QUAD $0x062354203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r11 + r12 + 6], 13 + QUAD $0x063b54203a0f4166; BYTE $0x0e // pinsrb xmm2, byte [r11 + rdi + 6], 14 + WORD $0x8949; BYTE $0xfe // mov r14, rdi + QUAD $0x060b54203a0f4166; BYTE $0x0f // pinsrb xmm2, byte [r11 + rcx + 6], 15 LONG $0xde0f4166; BYTE $0xd8 // pmaxub xmm3, xmm8 LONG $0x740f4166; BYTE $0xd8 // pcmpeqb xmm3, xmm8 QUAD $0x00000130b56f0f66 // movdqa xmm6, oword 304[rbp] /* [rip + .LCPI11_19] */ @@ -58200,1573 +60884,676 @@ LBB11_67: LONG $0xfedb0f66 // pand xmm7, xmm6 LONG $0xfbeb0f66 // por xmm7, xmm3 LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - LONG $0x0274b60f; BYTE $0x13 // movzx esi, byte [rdx + rax + 19] + LONG $0x74b60f41; WORD $0x1303 // movzx esi, byte [r11 + rax + 19] LONG $0xde6e0f66 // movd xmm3, esi LONG $0xde0f4166; BYTE $0xd0 // pmaxub xmm2, xmm8 LONG $0x740f4166; BYTE $0xd0 // pcmpeqb xmm2, xmm8 QUAD $0x00000150b56f0f66 // movdqa xmm6, oword 336[rbp] /* [rip + .LCPI11_21] */ LONG $0xd6db0f66 // pand xmm2, xmm6 LONG $0xd7eb0f66 // por xmm2, xmm7 - LONG $0x0274b60f; BYTE $0x14 // movzx esi, byte [rdx + rax + 20] + LONG $0x74b60f41; WORD $0x1403 // movzx esi, byte [r11 + rax + 20] LONG $0xf66e0f66 // movd xmm6, esi LONG $0xd4eb0f66 // por xmm2, xmm4 - LONG $0x0274b60f; BYTE $0x15 // movzx esi, byte [rdx + rax + 21] + LONG $0x74b60f41; WORD $0x1503 // movzx esi, byte [r11 + rax + 21] LONG $0xe66e0f66 // movd xmm4, esi - LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] - QUAD $0x073a4c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rdi + 7], 1 - LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - QUAD $0x07024c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rax + 7], 2 - LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] - QUAD $0x07024c203a0f4466; BYTE $0x03 // pinsrb xmm9, byte [rdx + rax + 7], 3 - QUAD $0x0000009024848b4c // mov r8, qword [rsp + 144] - QUAD $0x07024c203a0f4666; BYTE $0x04 // pinsrb xmm9, byte [rdx + r8 + 7], 4 - QUAD $0x07124c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdx + r10 + 7], 5 - QUAD $0x072a4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdx + r13 + 7], 6 - QUAD $0x07324c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdx + r14 + 7], 7 - QUAD $0x071a4c203a0f4466; BYTE $0x08 // pinsrb xmm9, byte [rdx + rbx + 7], 8 - QUAD $0x071a4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdx + r11 + 7], 9 - WORD $0x894c; BYTE $0xd9 // mov rcx, r11 - LONG $0x245c8b4c; BYTE $0x40 // mov r11, qword [rsp + 64] - QUAD $0x071a4c203a0f4666; BYTE $0x0a // pinsrb xmm9, byte [rdx + r11 + 7], 10 - QUAD $0x07224c203a0f4666; BYTE $0x0b // pinsrb xmm9, byte [rdx + r12 + 7], 11 - QUAD $0x070a4c203a0f4666; BYTE $0x0c // pinsrb xmm9, byte [rdx + r9 + 7], 12 - LONG $0x246c8b4c; BYTE $0x10 // mov r13, qword [rsp + 16] - QUAD $0x072a4c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rdx + r13 + 7], 13 - LONG $0x24648b4c; BYTE $0x18 // mov r12, qword [rsp + 24] - QUAD $0x07224c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r12 + 7], 14 - QUAD $0x073a4c203a0f4666; BYTE $0x0f // pinsrb xmm9, byte [rdx + r15 + 7], 15 + LONG $0x247c8b48; BYTE $0x38 // mov rdi, qword [rsp + 56] + QUAD $0x073b4c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r11 + rdi + 7], 1 + LONG $0x247c8b4c; BYTE $0x40 // mov r15, qword [rsp + 64] + QUAD $0x073b4c203a0f4766; BYTE $0x02 // pinsrb xmm9, byte [r11 + r15 + 7], 2 + QUAD $0x000000c024848b48 // mov rax, qword [rsp + 192] + QUAD $0x07034c203a0f4566; BYTE $0x03 // pinsrb xmm9, byte [r11 + rax + 7], 3 + QUAD $0x07134c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r11 + r10 + 7], 4 + QUAD $0x070b4c203a0f4766; BYTE $0x05 // pinsrb xmm9, byte [r11 + r9 + 7], 5 + WORD $0x894d; BYTE $0xcd // mov r13, r9 + LONG $0x24648b4c; BYTE $0x78 // mov r12, qword [rsp + 120] + QUAD $0x07234c203a0f4766; BYTE $0x06 // pinsrb xmm9, byte [r11 + r12 + 7], 6 + LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] + QUAD $0x071b4c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r11 + rbx + 7], 7 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x070b4c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r11 + rcx + 7], 8 + LONG $0x244c8b4c; BYTE $0x68 // mov r9, qword [rsp + 104] + QUAD $0x070b4c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r11 + r9 + 7], 9 + LONG $0x24548b48; BYTE $0x28 // mov rdx, qword [rsp + 40] + QUAD $0x07134c203a0f4566; BYTE $0x0a // pinsrb xmm9, byte [r11 + rdx + 7], 10 + LONG $0x24548b4c; BYTE $0x18 // mov r10, qword [rsp + 24] + QUAD $0x07134c203a0f4766; BYTE $0x0b // pinsrb xmm9, byte [r11 + r10 + 7], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x07334c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r11 + rsi + 7], 12 + QUAD $0x07034c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r11 + r8 + 7], 13 + QUAD $0x07334c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r11 + r14 + 7], 14 + LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] + QUAD $0x07334c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r11 + r14 + 7], 15 LONG $0xde0f4566; BYTE $0xc8 // pmaxub xmm9, xmm8 LONG $0x740f4566; BYTE $0xc8 // pcmpeqb xmm9, xmm8 LONG $0x7d6f0f66; BYTE $0x60 // movdqa xmm7, oword 96[rbp] /* [rip + .LCPI11_6] */ LONG $0xdb0f4466; BYTE $0xcf // pand xmm9, xmm7 LONG $0xeb0f4466; BYTE $0xca // por xmm9, xmm2 - QUAD $0x00d0248c7f0f4466; WORD $0x0000 // movdqa oword [rsp + 208], xmm9 - LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] - LONG $0x74b60f42; WORD $0x160a // movzx esi, byte [rdx + r9 + 22] + QUAD $0x00e0248c7f0f4466; WORD $0x0000 // movdqa oword [rsp + 224], xmm9 + LONG $0x24748b48; BYTE $0x50 // mov rsi, qword [rsp + 80] + LONG $0x74b60f41; WORD $0x1633 // movzx esi, byte [r11 + rsi + 22] LONG $0xfe6e0f66 // movd xmm7, esi - QUAD $0x0000e024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 224] - QUAD $0x01083a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 8], 1 - WORD $0x8949; BYTE $0xfe // mov r14, rdi - LONG $0x247c8b48; BYTE $0x30 // mov rdi, qword [rsp + 48] - QUAD $0x02083a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 8], 2 - QUAD $0x03080254203a0f66 // pinsrb xmm2, byte [rdx + rax + 8], 3 - WORD $0x8949; BYTE $0xc7 // mov r15, rax - QUAD $0x080254203a0f4266; BYTE $0x04 // pinsrb xmm2, byte [rdx + r8 + 8], 4 - QUAD $0x081254203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdx + r10 + 8], 5 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x06080254203a0f66 // pinsrb xmm2, byte [rdx + rax + 8], 6 - LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] - QUAD $0x07083254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 8], 7 - LONG $0x245c8b48; BYTE $0x48 // mov rbx, qword [rsp + 72] - QUAD $0x08081a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 8], 8 - QUAD $0x09080a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 8], 9 - QUAD $0x081a54203a0f4266; BYTE $0x0a // pinsrb xmm2, byte [rdx + r11 + 8], 10 - LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] - QUAD $0x0b080a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 8], 11 - LONG $0x245c8b4c; BYTE $0x70 // mov r11, qword [rsp + 112] - QUAD $0x081a54203a0f4266; BYTE $0x0c // pinsrb xmm2, byte [rdx + r11 + 8], 12 - WORD $0x894c; BYTE $0xee // mov rsi, r13 - QUAD $0x082a54203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r13 + 8], 13 - QUAD $0x082254203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r12 + 8], 14 - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] - QUAD $0x082a54203a0f4266; BYTE $0x0f // pinsrb xmm2, byte [rdx + r13 + 8], 15 - LONG $0xde0f4166; BYTE $0xd0 // pmaxub xmm2, xmm8 - LONG $0x740f4166; BYTE $0xd0 // pcmpeqb xmm2, xmm8 - QUAD $0x093254203a0f4666; BYTE $0x01 // pinsrb xmm10, byte [rdx + r14 + 9], 1 - QUAD $0x093a54203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdx + rdi + 9], 2 - QUAD $0x093a54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r15 + 9], 3 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x090254203a0f4666; BYTE $0x04 // pinsrb xmm10, byte [rdx + r8 + 9], 4 - WORD $0x894d; BYTE $0xc7 // mov r15, r8 - QUAD $0x091254203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdx + r10 + 9], 5 - QUAD $0x090254203a0f4466; BYTE $0x06 // pinsrb xmm10, byte [rdx + rax + 9], 6 - WORD $0x8949; BYTE $0xc0 // mov r8, rax - LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] - QUAD $0x090254203a0f4466; BYTE $0x07 // pinsrb xmm10, byte [rdx + rax + 9], 7 - QUAD $0x091a54203a0f4466; BYTE $0x08 // pinsrb xmm10, byte [rdx + rbx + 9], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x090254203a0f4466; BYTE $0x09 // pinsrb xmm10, byte [rdx + rax + 9], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x090254203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdx + rax + 9], 10 - QUAD $0x090a54203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rdx + rcx + 9], 11 - WORD $0x894c; BYTE $0xd9 // mov rcx, r11 - QUAD $0x091a54203a0f4666; BYTE $0x0c // pinsrb xmm10, byte [rdx + r11 + 9], 12 - QUAD $0x093254203a0f4466; BYTE $0x0d // pinsrb xmm10, byte [rdx + rsi + 9], 13 - QUAD $0x092254203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r12 + 9], 14 - QUAD $0x092a54203a0f4666; BYTE $0x0f // pinsrb xmm10, byte [rdx + r13 + 9], 15 - LONG $0xde0f4566; BYTE $0xd0 // pmaxub xmm10, xmm8 - LONG $0x740f4566; BYTE $0xd0 // pcmpeqb xmm10, xmm8 - QUAD $0x00010095db0f4466; BYTE $0x00 // pand xmm10, oword 256[rbp] /* [rip + .LCPI11_16] */ - LONG $0xf80f4466; BYTE $0xd2 // psubb xmm10, xmm2 - LONG $0x74b60f42; WORD $0x170a // movzx esi, byte [rdx + r9 + 23] - LONG $0xd66e0f66 // movd xmm2, esi - LONG $0x245c8b4c; BYTE $0x28 // mov r11, qword [rsp + 40] - QUAD $0x0a1a64203a0f4666; BYTE $0x01 // pinsrb xmm12, byte [rdx + r11 + 10], 1 - QUAD $0x0a3a64203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rdi + 10], 2 - WORD $0x8949; BYTE $0xfa // mov r10, rdi - WORD $0x894c; BYTE $0xf6 // mov rsi, r14 - QUAD $0x0a3264203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r14 + 10], 3 - QUAD $0x0a3a64203a0f4666; BYTE $0x04 // pinsrb xmm12, byte [rdx + r15 + 10], 4 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x0a3264203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdx + r14 + 10], 5 - QUAD $0x0a0264203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdx + r8 + 10], 6 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - LONG $0x247c8b4c; BYTE $0x38 // mov r15, qword [rsp + 56] - QUAD $0x0a3a64203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdx + r15 + 10], 7 - LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] - QUAD $0x0a2a64203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r13 + 10], 8 - LONG $0x247c8b48; BYTE $0x60 // mov rdi, qword [rsp + 96] - QUAD $0x0a3a64203a0f4466; BYTE $0x09 // pinsrb xmm12, byte [rdx + rdi + 10], 9 - QUAD $0x0a0264203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdx + rax + 10], 10 - LONG $0x24448b4c; BYTE $0x58 // mov r8, qword [rsp + 88] - QUAD $0x0a0264203a0f4666; BYTE $0x0b // pinsrb xmm12, byte [rdx + r8 + 10], 11 - WORD $0x8949; BYTE $0xc9 // mov r9, rcx - QUAD $0x0a0a64203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdx + rcx + 10], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0a0264203a0f4466; BYTE $0x0d // pinsrb xmm12, byte [rdx + rax + 10], 13 - QUAD $0x0a2264203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r12 + 10], 14 - LONG $0x244c8b48; BYTE $0x08 // mov rcx, qword [rsp + 8] - QUAD $0x0a0a64203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdx + rcx + 10], 15 - QUAD $0x0b1a5c203a0f4666; BYTE $0x01 // pinsrb xmm11, byte [rdx + r11 + 11], 1 - QUAD $0x0b125c203a0f4666; BYTE $0x02 // pinsrb xmm11, byte [rdx + r10 + 11], 2 - QUAD $0x0b325c203a0f4466; BYTE $0x03 // pinsrb xmm11, byte [rdx + rsi + 11], 3 - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - QUAD $0x0000009024b48b48 // mov rsi, qword [rsp + 144] - QUAD $0x0b325c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdx + rsi + 11], 4 - QUAD $0x0b325c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdx + r14 + 11], 5 - QUAD $0x0b1a5c203a0f4466; BYTE $0x06 // pinsrb xmm11, byte [rdx + rbx + 11], 6 - QUAD $0x0b3a5c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdx + r15 + 11], 7 - WORD $0x894d; BYTE $0xfe // mov r14, r15 - QUAD $0x0b2a5c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r13 + 11], 8 - QUAD $0x0b3a5c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdx + rdi + 11], 9 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0b1a5c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdx + rbx + 11], 10 - QUAD $0x0b025c203a0f4666; BYTE $0x0b // pinsrb xmm11, byte [rdx + r8 + 11], 11 - QUAD $0x0b0a5c203a0f4666; BYTE $0x0c // pinsrb xmm11, byte [rdx + r9 + 11], 12 - QUAD $0x0b025c203a0f4466; BYTE $0x0d // pinsrb xmm11, byte [rdx + rax + 11], 13 - QUAD $0x0b225c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r12 + 11], 14 - QUAD $0x0b0a5c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdx + rcx + 11], 15 - LONG $0xde0f4566; BYTE $0xe0 // pmaxub xmm12, xmm8 - LONG $0x740f4566; BYTE $0xe0 // pcmpeqb xmm12, xmm8 - QUAD $0x000110a5db0f4466; BYTE $0x00 // pand xmm12, oword 272[rbp] /* [rip + .LCPI11_17] */ - LONG $0xde0f4566; BYTE $0xd8 // pmaxub xmm11, xmm8 - LONG $0x740f4566; BYTE $0xd8 // pcmpeqb xmm11, xmm8 - QUAD $0x0001209ddb0f4466; BYTE $0x00 // pand xmm11, oword 288[rbp] /* [rip + .LCPI11_18] */ - LONG $0xeb0f4566; BYTE $0xdc // por xmm11, xmm12 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - LONG $0x0274b60f; BYTE $0x18 // movzx esi, byte [rdx + rax + 24] - LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi - LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 - LONG $0x0274b60f; BYTE $0x19 // movzx esi, byte [rdx + rax + 25] - LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi - QUAD $0x0c1a6c203a0f4666; BYTE $0x01 // pinsrb xmm13, byte [rdx + r11 + 12], 1 - LONG $0x24648b4c; BYTE $0x30 // mov r12, qword [rsp + 48] - QUAD $0x0c226c203a0f4666; BYTE $0x02 // pinsrb xmm13, byte [rdx + r12 + 12], 2 - WORD $0x894d; BYTE $0xd3 // mov r11, r10 - QUAD $0x0c126c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdx + r10 + 12], 3 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x0c3a6c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdx + rdi + 12], 4 - LONG $0x247c8b4c; BYTE $0x20 // mov r15, qword [rsp + 32] - QUAD $0x0c3a6c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rdx + r15 + 12], 5 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x0c126c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdx + r10 + 12], 6 - QUAD $0x0c326c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdx + r14 + 12], 7 - QUAD $0x0c2a6c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r13 + 12], 8 - LONG $0x244c8b48; BYTE $0x60 // mov rcx, qword [rsp + 96] - QUAD $0x0c0a6c203a0f4466; BYTE $0x09 // pinsrb xmm13, byte [rdx + rcx + 12], 9 - QUAD $0x0c1a6c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdx + rbx + 12], 10 - QUAD $0x0c026c203a0f4666; BYTE $0x0b // pinsrb xmm13, byte [rdx + r8 + 12], 11 - QUAD $0x0c0a6c203a0f4666; BYTE $0x0c // pinsrb xmm13, byte [rdx + r9 + 12], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0c026c203a0f4466; BYTE $0x0d // pinsrb xmm13, byte [rdx + rax + 12], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0c026c203a0f4466; BYTE $0x0e // pinsrb xmm13, byte [rdx + rax + 12], 14 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0c326c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdx + rsi + 12], 15 - LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] - QUAD $0x010d0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 13], 1 - QUAD $0x0d2244203a0f4266; BYTE $0x02 // pinsrb xmm0, byte [rdx + r12 + 13], 2 - QUAD $0x0d1a44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r11 + 13], 3 - QUAD $0x040d3a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 13], 4 - QUAD $0x0d3a44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdx + r15 + 13], 5 - QUAD $0x0d1244203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdx + r10 + 13], 6 - QUAD $0x0d3244203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r14 + 13], 7 - QUAD $0x0d2a44203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r13 + 13], 8 - QUAD $0x090d0a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 13], 9 - QUAD $0x0a0d1a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 13], 10 - QUAD $0x0d0244203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r8 + 13], 11 - QUAD $0x0d0a44203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r9 + 13], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d0d0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 13], 13 - LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] - QUAD $0x0e0d0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 13], 14 - QUAD $0x0f0d3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 13], 15 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x0e3274203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdx + rsi + 14], 1 - QUAD $0x0e2274203a0f4666; BYTE $0x02 // pinsrb xmm14, byte [rdx + r12 + 14], 2 - QUAD $0x0e1a74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdx + r11 + 14], 3 - QUAD $0x0e3a74203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rdx + rdi + 14], 4 - QUAD $0x0e3a74203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rdx + r15 + 14], 5 - QUAD $0x0e1274203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdx + r10 + 14], 6 - QUAD $0x0e3274203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdx + r14 + 14], 7 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - QUAD $0x0e2a74203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdx + r13 + 14], 8 - QUAD $0x0e0a74203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdx + rcx + 14], 9 - WORD $0x8949; BYTE $0xce // mov r14, rcx - QUAD $0x0e1a74203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdx + rbx + 14], 10 - QUAD $0x0e0274203a0f4666; BYTE $0x0b // pinsrb xmm14, byte [rdx + r8 + 14], 11 - QUAD $0x0e0a74203a0f4666; BYTE $0x0c // pinsrb xmm14, byte [rdx + r9 + 14], 12 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - QUAD $0x0e0a74203a0f4466; BYTE $0x0d // pinsrb xmm14, byte [rdx + rcx + 14], 13 - LONG $0x246c8b4c; BYTE $0x18 // mov r13, qword [rsp + 24] - QUAD $0x0e2a74203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdx + r13 + 14], 14 - QUAD $0x0e0274203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdx + rax + 14], 15 - LONG $0xde0f4566; BYTE $0xe8 // pmaxub xmm13, xmm8 - LONG $0x740f4566; BYTE $0xe8 // pcmpeqb xmm13, xmm8 - QUAD $0x000130addb0f4466; BYTE $0x00 // pand xmm13, oword 304[rbp] /* [rip + .LCPI11_19] */ - LONG $0xde0f4166; BYTE $0xc0 // pmaxub xmm0, xmm8 - LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 - QUAD $0x0000014085db0f66 // pand xmm0, oword 320[rbp] /* [rip + .LCPI11_20] */ - LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 - LONG $0x24648b4c; BYTE $0x50 // mov r12, qword [rsp + 80] - LONG $0x74b60f42; WORD $0x1a22 // movzx esi, byte [rdx + r12 + 26] - LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi - LONG $0xde0f4566; BYTE $0xf0 // pmaxub xmm14, xmm8 - LONG $0x740f4566; BYTE $0xf0 // pcmpeqb xmm14, xmm8 - QUAD $0x000150b5db0f4466; BYTE $0x00 // pand xmm14, oword 336[rbp] /* [rip + .LCPI11_21] */ - LONG $0xeb0f4466; BYTE $0xf0 // por xmm14, xmm0 - LONG $0x74b60f42; WORD $0x1b22 // movzx esi, byte [rdx + r12 + 27] - LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi - LONG $0xeb0f4566; BYTE $0xf3 // por xmm14, xmm11 - LONG $0x74b60f42; WORD $0x1c22 // movzx esi, byte [rdx + r12 + 28] - LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi - QUAD $0x0000b024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 176] - LONG $0x244c8b48; BYTE $0x28 // mov rcx, qword [rsp + 40] - QUAD $0x010f0a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 15], 1 + QUAD $0x0000f024946f0f66; BYTE $0x00 // movdqa xmm2, oword [rsp + 240] + QUAD $0x083b54203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rdi + 8], 1 + WORD $0x8949; BYTE $0xf8 // mov r8, rdi + QUAD $0x083b54203a0f4366; BYTE $0x02 // pinsrb xmm2, byte [r11 + r15 + 8], 2 + QUAD $0x080354203a0f4166; BYTE $0x03 // pinsrb xmm2, byte [r11 + rax + 8], 3 + QUAD $0x000000a024bc8b48 // mov rdi, qword [rsp + 160] + QUAD $0x083b54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r11 + rdi + 8], 4 + QUAD $0x082b54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r11 + r13 + 8], 5 + QUAD $0x082354203a0f4366; BYTE $0x06 // pinsrb xmm2, byte [r11 + r12 + 8], 6 + QUAD $0x081b54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r11 + rbx + 8], 7 + QUAD $0x080b54203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r11 + rcx + 8], 8 + WORD $0x894c; BYTE $0xc9 // mov rcx, r9 + QUAD $0x080b54203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r9 + 8], 9 + QUAD $0x081354203a0f4166; BYTE $0x0a // pinsrb xmm2, byte [r11 + rdx + 8], 10 + WORD $0x894c; BYTE $0xd2 // mov rdx, r10 + QUAD $0x081354203a0f4366; BYTE $0x0b // pinsrb xmm2, byte [r11 + r10 + 8], 11 LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x020f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 15], 2 - LONG $0x247c8b48; BYTE $0x68 // mov rdi, qword [rsp + 104] - QUAD $0x030f3a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 15], 3 - QUAD $0x00000090248c8b4c // mov r9, qword [rsp + 144] - QUAD $0x0f0a44203a0f4266; BYTE $0x04 // pinsrb xmm0, byte [rdx + r9 + 15], 4 - LONG $0x24548b4c; BYTE $0x20 // mov r10, qword [rsp + 32] - QUAD $0x0f1244203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdx + r10 + 15], 5 - QUAD $0x000000a024848b48 // mov rax, qword [rsp + 160] - QUAD $0x060f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 15], 6 - QUAD $0x0f3a44203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r15 + 15], 7 - LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] - QUAD $0x080f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 15], 8 - QUAD $0x0f3244203a0f4266; BYTE $0x09 // pinsrb xmm0, byte [rdx + r14 + 15], 9 - LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] - QUAD $0x0a0f1a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 15], 10 - QUAD $0x0f0244203a0f4266; BYTE $0x0b // pinsrb xmm0, byte [rdx + r8 + 15], 11 - LONG $0x24448b4c; BYTE $0x70 // mov r8, qword [rsp + 112] - QUAD $0x0f0244203a0f4266; BYTE $0x0c // pinsrb xmm0, byte [rdx + r8 + 15], 12 + QUAD $0x083354203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r11 + rsi + 8], 12 LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] - QUAD $0x0d0f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 15], 13 - QUAD $0x0f2a44203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdx + r13 + 15], 14 - LONG $0x245c8b4c; BYTE $0x08 // mov r11, qword [rsp + 8] - QUAD $0x0f1a44203a0f4266; BYTE $0x0f // pinsrb xmm0, byte [rdx + r11 + 15], 15 - LONG $0xde0f4166; BYTE $0xc0 // pmaxub xmm0, xmm8 - LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 - LONG $0x45db0f66; BYTE $0x60 // pand xmm0, oword 96[rbp] /* [rip + .LCPI11_6] */ - LONG $0xeb0f4166; BYTE $0xc6 // por xmm0, xmm14 - QUAD $0x0000b024847f0f66; BYTE $0x00 // movdqa oword [rsp + 176], xmm0 - LONG $0x74b60f42; WORD $0x1d22 // movzx esi, byte [rdx + r12 + 29] - LONG $0x6e0f4466; BYTE $0xf6 // movd xmm14, esi - QUAD $0x01100a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 16], 1 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x0210324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 16], 2 - WORD $0x8949; BYTE $0xf4 // mov r12, rsi - QUAD $0x03103a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 16], 3 - QUAD $0x100a4c203a0f4266; BYTE $0x04 // pinsrb xmm1, byte [rdx + r9 + 16], 4 - QUAD $0x10124c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdx + r10 + 16], 5 - QUAD $0x000000a0248c8b4c // mov r9, qword [rsp + 160] - QUAD $0x100a4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r9 + 16], 6 - QUAD $0x103a4c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r15 + 16], 7 - QUAD $0x0810024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 16], 8 - QUAD $0x10324c203a0f4266; BYTE $0x09 // pinsrb xmm1, byte [rdx + r14 + 16], 9 - QUAD $0x0a101a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 16], 10 - LONG $0x24748b4c; BYTE $0x58 // mov r14, qword [rsp + 88] - QUAD $0x10324c203a0f4266; BYTE $0x0b // pinsrb xmm1, byte [rdx + r14 + 16], 11 - QUAD $0x10024c203a0f4266; BYTE $0x0c // pinsrb xmm1, byte [rdx + r8 + 16], 12 - WORD $0x894d; BYTE $0xc2 // mov r10, r8 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x0d10024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 16], 13 - QUAD $0x102a4c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r13 + 16], 14 - WORD $0x894c; BYTE $0xde // mov rsi, r11 - QUAD $0x101a4c203a0f4266; BYTE $0x0f // pinsrb xmm1, byte [rdx + r11 + 16], 15 - LONG $0xde0f4166; BYTE $0xc8 // pmaxub xmm1, xmm8 - LONG $0x740f4166; BYTE $0xc8 // pcmpeqb xmm1, xmm8 - QUAD $0x01110a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 17], 1 - QUAD $0x11226c203a0f4266; BYTE $0x02 // pinsrb xmm5, byte [rdx + r12 + 17], 2 - WORD $0x894d; BYTE $0xe3 // mov r11, r12 - QUAD $0x03113a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 17], 3 - QUAD $0x0000009024bc8b48 // mov rdi, qword [rsp + 144] - QUAD $0x04113a6c203a0f66 // pinsrb xmm5, byte [rdx + rdi + 17], 4 - LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] - QUAD $0x05110a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 17], 5 - QUAD $0x110a6c203a0f4266; BYTE $0x06 // pinsrb xmm5, byte [rdx + r9 + 17], 6 - QUAD $0x113a6c203a0f4266; BYTE $0x07 // pinsrb xmm5, byte [rdx + r15 + 17], 7 - WORD $0x894d; BYTE $0xf9 // mov r9, r15 - LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] - QUAD $0x08110a6c203a0f66 // pinsrb xmm5, byte [rdx + rcx + 17], 8 - LONG $0x247c8b4c; BYTE $0x60 // mov r15, qword [rsp + 96] - QUAD $0x113a6c203a0f4266; BYTE $0x09 // pinsrb xmm5, byte [rdx + r15 + 17], 9 - QUAD $0x0a111a6c203a0f66 // pinsrb xmm5, byte [rdx + rbx + 17], 10 - WORD $0x894d; BYTE $0xf0 // mov r8, r14 - QUAD $0x11326c203a0f4266; BYTE $0x0b // pinsrb xmm5, byte [rdx + r14 + 17], 11 - QUAD $0x11126c203a0f4266; BYTE $0x0c // pinsrb xmm5, byte [rdx + r10 + 17], 12 - WORD $0x894d; BYTE $0xd4 // mov r12, r10 - QUAD $0x0d11026c203a0f66 // pinsrb xmm5, byte [rdx + rax + 17], 13 - QUAD $0x112a6c203a0f4266; BYTE $0x0e // pinsrb xmm5, byte [rdx + r13 + 17], 14 - QUAD $0x0f11326c203a0f66 // pinsrb xmm5, byte [rdx + rsi + 17], 15 - LONG $0xde0f4166; BYTE $0xe8 // pmaxub xmm5, xmm8 - LONG $0x740f4166; BYTE $0xe8 // pcmpeqb xmm5, xmm8 - QUAD $0x00000100addb0f66 // pand xmm5, oword 256[rbp] /* [rip + .LCPI11_16] */ - LONG $0xe9f80f66 // psubb xmm5, xmm1 - LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] - LONG $0x0274b60f; BYTE $0x1e // movzx esi, byte [rdx + rax + 30] - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] - QUAD $0x12327c203a0f4466; BYTE $0x01 // pinsrb xmm15, byte [rdx + rsi + 18], 1 - QUAD $0x0113325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 19], 1 - QUAD $0x01143274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 20], 1 - QUAD $0x01153264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 21], 1 - QUAD $0x0116327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 22], 1 - QUAD $0x01173254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 23], 1 - QUAD $0x18324c203a0f4466; BYTE $0x01 // pinsrb xmm9, byte [rdx + rsi + 24], 1 - QUAD $0x193264203a0f4466; BYTE $0x01 // pinsrb xmm12, byte [rdx + rsi + 25], 1 - QUAD $0x1a326c203a0f4466; BYTE $0x01 // pinsrb xmm13, byte [rdx + rsi + 26], 1 - QUAD $0x1b3254203a0f4466; BYTE $0x01 // pinsrb xmm10, byte [rdx + rsi + 27], 1 - QUAD $0x1c325c203a0f4466; BYTE $0x01 // pinsrb xmm11, byte [rdx + rsi + 28], 1 - QUAD $0x1d3274203a0f4466; BYTE $0x01 // pinsrb xmm14, byte [rdx + rsi + 29], 1 - QUAD $0x011e324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 30], 1 - LONG $0x0244b60f; BYTE $0x1f // movzx eax, byte [rdx + rax + 31] - LONG $0xc06e0f66 // movd xmm0, eax - QUAD $0x011f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 31], 1 - QUAD $0x121a7c203a0f4666; BYTE $0x02 // pinsrb xmm15, byte [rdx + r11 + 18], 2 - LONG $0x245c8b4c; BYTE $0x68 // mov r11, qword [rsp + 104] - QUAD $0x121a7c203a0f4666; BYTE $0x03 // pinsrb xmm15, byte [rdx + r11 + 18], 3 - QUAD $0x123a7c203a0f4466; BYTE $0x04 // pinsrb xmm15, byte [rdx + rdi + 18], 4 - LONG $0x24748b4c; BYTE $0x20 // mov r14, qword [rsp + 32] - QUAD $0x12327c203a0f4666; BYTE $0x05 // pinsrb xmm15, byte [rdx + r14 + 18], 5 - QUAD $0x000000a024948b4c // mov r10, qword [rsp + 160] - QUAD $0x12127c203a0f4666; BYTE $0x06 // pinsrb xmm15, byte [rdx + r10 + 18], 6 - QUAD $0x120a7c203a0f4666; BYTE $0x07 // pinsrb xmm15, byte [rdx + r9 + 18], 7 - WORD $0x8948; BYTE $0xce // mov rsi, rcx - QUAD $0x120a7c203a0f4466; BYTE $0x08 // pinsrb xmm15, byte [rdx + rcx + 18], 8 - QUAD $0x123a7c203a0f4666; BYTE $0x09 // pinsrb xmm15, byte [rdx + r15 + 18], 9 - LONG $0x244c8b48; BYTE $0x40 // mov rcx, qword [rsp + 64] - QUAD $0x120a7c203a0f4466; BYTE $0x0a // pinsrb xmm15, byte [rdx + rcx + 18], 10 - QUAD $0x12027c203a0f4666; BYTE $0x0b // pinsrb xmm15, byte [rdx + r8 + 18], 11 - QUAD $0x12227c203a0f4666; BYTE $0x0c // pinsrb xmm15, byte [rdx + r12 + 18], 12 - LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] - QUAD $0x12027c203a0f4466; BYTE $0x0d // pinsrb xmm15, byte [rdx + rax + 18], 13 - LONG $0x245c8b48; BYTE $0x18 // mov rbx, qword [rsp + 24] - QUAD $0x121a7c203a0f4466; BYTE $0x0e // pinsrb xmm15, byte [rdx + rbx + 18], 14 - LONG $0x246c8b4c; BYTE $0x08 // mov r13, qword [rsp + 8] - QUAD $0x122a7c203a0f4666; BYTE $0x0f // pinsrb xmm15, byte [rdx + r13 + 18], 15 - LONG $0x245c8b48; BYTE $0x30 // mov rbx, qword [rsp + 48] - QUAD $0x02131a5c203a0f66 // pinsrb xmm3, byte [rdx + rbx + 19], 2 - QUAD $0x131a5c203a0f4266; BYTE $0x03 // pinsrb xmm3, byte [rdx + r11 + 19], 3 - QUAD $0x04133a5c203a0f66 // pinsrb xmm3, byte [rdx + rdi + 19], 4 - QUAD $0x13325c203a0f4266; BYTE $0x05 // pinsrb xmm3, byte [rdx + r14 + 19], 5 - QUAD $0x13125c203a0f4266; BYTE $0x06 // pinsrb xmm3, byte [rdx + r10 + 19], 6 - WORD $0x894d; BYTE $0xd5 // mov r13, r10 - QUAD $0x130a5c203a0f4266; BYTE $0x07 // pinsrb xmm3, byte [rdx + r9 + 19], 7 - QUAD $0x0813325c203a0f66 // pinsrb xmm3, byte [rdx + rsi + 19], 8 - WORD $0x8949; BYTE $0xf2 // mov r10, rsi - QUAD $0x133a5c203a0f4266; BYTE $0x09 // pinsrb xmm3, byte [rdx + r15 + 19], 9 - QUAD $0x0a130a5c203a0f66 // pinsrb xmm3, byte [rdx + rcx + 19], 10 - QUAD $0x13025c203a0f4266; BYTE $0x0b // pinsrb xmm3, byte [rdx + r8 + 19], 11 - WORD $0x894c; BYTE $0xe1 // mov rcx, r12 - QUAD $0x13225c203a0f4266; BYTE $0x0c // pinsrb xmm3, byte [rdx + r12 + 19], 12 - QUAD $0x0d13025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 19], 13 - LONG $0x24448b4c; BYTE $0x18 // mov r8, qword [rsp + 24] - QUAD $0x13025c203a0f4266; BYTE $0x0e // pinsrb xmm3, byte [rdx + r8 + 19], 14 - LONG $0x24448b48; BYTE $0x08 // mov rax, qword [rsp + 8] - QUAD $0x0f13025c203a0f66 // pinsrb xmm3, byte [rdx + rax + 19], 15 - LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] - QUAD $0x02143274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 20], 2 - QUAD $0x02153264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 21], 2 - QUAD $0x0216327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 22], 2 - QUAD $0x02173254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 23], 2 - QUAD $0x18324c203a0f4466; BYTE $0x02 // pinsrb xmm9, byte [rdx + rsi + 24], 2 - QUAD $0x193264203a0f4466; BYTE $0x02 // pinsrb xmm12, byte [rdx + rsi + 25], 2 - QUAD $0x1a326c203a0f4466; BYTE $0x02 // pinsrb xmm13, byte [rdx + rsi + 26], 2 - QUAD $0x1b3254203a0f4466; BYTE $0x02 // pinsrb xmm10, byte [rdx + rsi + 27], 2 - QUAD $0x1c325c203a0f4466; BYTE $0x02 // pinsrb xmm11, byte [rdx + rsi + 28], 2 - QUAD $0x1d3274203a0f4466; BYTE $0x02 // pinsrb xmm14, byte [rdx + rsi + 29], 2 - QUAD $0x021e324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 30], 2 - LONG $0xde0f4566; BYTE $0xf8 // pmaxub xmm15, xmm8 - LONG $0x740f4566; BYTE $0xf8 // pcmpeqb xmm15, xmm8 - QUAD $0x000110bddb0f4466; BYTE $0x00 // pand xmm15, oword 272[rbp] /* [rip + .LCPI11_17] */ - LONG $0xde0f4166; BYTE $0xd8 // pmaxub xmm3, xmm8 - LONG $0x740f4166; BYTE $0xd8 // pcmpeqb xmm3, xmm8 - QUAD $0x000001209ddb0f66 // pand xmm3, oword 288[rbp] /* [rip + .LCPI11_18] */ - LONG $0xeb0f4166; BYTE $0xdf // por xmm3, xmm15 - QUAD $0x021f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 31], 2 - LONG $0xddeb0f66 // por xmm3, xmm5 - QUAD $0x141a74203a0f4266; BYTE $0x03 // pinsrb xmm6, byte [rdx + r11 + 20], 3 - QUAD $0x04143a74203a0f66 // pinsrb xmm6, byte [rdx + rdi + 20], 4 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - QUAD $0x143274203a0f4266; BYTE $0x05 // pinsrb xmm6, byte [rdx + r14 + 20], 5 - QUAD $0x142a74203a0f4266; BYTE $0x06 // pinsrb xmm6, byte [rdx + r13 + 20], 6 - LONG $0x24748b4c; BYTE $0x38 // mov r14, qword [rsp + 56] - QUAD $0x143274203a0f4266; BYTE $0x07 // pinsrb xmm6, byte [rdx + r14 + 20], 7 - QUAD $0x141274203a0f4266; BYTE $0x08 // pinsrb xmm6, byte [rdx + r10 + 20], 8 - QUAD $0x143a74203a0f4266; BYTE $0x09 // pinsrb xmm6, byte [rdx + r15 + 20], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x0a140274203a0f66 // pinsrb xmm6, byte [rdx + rax + 20], 10 - LONG $0x245c8b48; BYTE $0x58 // mov rbx, qword [rsp + 88] - QUAD $0x0b141a74203a0f66 // pinsrb xmm6, byte [rdx + rbx + 20], 11 - QUAD $0x142274203a0f4266; BYTE $0x0c // pinsrb xmm6, byte [rdx + r12 + 20], 12 - LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] - QUAD $0x142274203a0f4266; BYTE $0x0d // pinsrb xmm6, byte [rdx + r12 + 20], 13 - QUAD $0x140274203a0f4266; BYTE $0x0e // pinsrb xmm6, byte [rdx + r8 + 20], 14 - LONG $0x24748b48; BYTE $0x08 // mov rsi, qword [rsp + 8] - QUAD $0x0f143274203a0f66 // pinsrb xmm6, byte [rdx + rsi + 20], 15 - QUAD $0x151a64203a0f4266; BYTE $0x03 // pinsrb xmm4, byte [rdx + r11 + 21], 3 - QUAD $0x04153a64203a0f66 // pinsrb xmm4, byte [rdx + rdi + 21], 4 - QUAD $0x150a64203a0f4266; BYTE $0x05 // pinsrb xmm4, byte [rdx + r9 + 21], 5 - QUAD $0x152a64203a0f4266; BYTE $0x06 // pinsrb xmm4, byte [rdx + r13 + 21], 6 - QUAD $0x153264203a0f4266; BYTE $0x07 // pinsrb xmm4, byte [rdx + r14 + 21], 7 - QUAD $0x151264203a0f4266; BYTE $0x08 // pinsrb xmm4, byte [rdx + r10 + 21], 8 - QUAD $0x153a64203a0f4266; BYTE $0x09 // pinsrb xmm4, byte [rdx + r15 + 21], 9 - QUAD $0x0a150264203a0f66 // pinsrb xmm4, byte [rdx + rax + 21], 10 - QUAD $0x0b151a64203a0f66 // pinsrb xmm4, byte [rdx + rbx + 21], 11 - QUAD $0x0c150a64203a0f66 // pinsrb xmm4, byte [rdx + rcx + 21], 12 - QUAD $0x152264203a0f4266; BYTE $0x0d // pinsrb xmm4, byte [rdx + r12 + 21], 13 - QUAD $0x150264203a0f4266; BYTE $0x0e // pinsrb xmm4, byte [rdx + r8 + 21], 14 - QUAD $0x0f153264203a0f66 // pinsrb xmm4, byte [rdx + rsi + 21], 15 - QUAD $0x161a7c203a0f4266; BYTE $0x03 // pinsrb xmm7, byte [rdx + r11 + 22], 3 - QUAD $0x04163a7c203a0f66 // pinsrb xmm7, byte [rdx + rdi + 22], 4 - QUAD $0x160a7c203a0f4266; BYTE $0x05 // pinsrb xmm7, byte [rdx + r9 + 22], 5 - QUAD $0x162a7c203a0f4266; BYTE $0x06 // pinsrb xmm7, byte [rdx + r13 + 22], 6 - QUAD $0x16327c203a0f4266; BYTE $0x07 // pinsrb xmm7, byte [rdx + r14 + 22], 7 - QUAD $0x16127c203a0f4266; BYTE $0x08 // pinsrb xmm7, byte [rdx + r10 + 22], 8 - QUAD $0x163a7c203a0f4266; BYTE $0x09 // pinsrb xmm7, byte [rdx + r15 + 22], 9 - QUAD $0x0a16027c203a0f66 // pinsrb xmm7, byte [rdx + rax + 22], 10 - QUAD $0x0b161a7c203a0f66 // pinsrb xmm7, byte [rdx + rbx + 22], 11 - QUAD $0x0c160a7c203a0f66 // pinsrb xmm7, byte [rdx + rcx + 22], 12 - QUAD $0x16227c203a0f4266; BYTE $0x0d // pinsrb xmm7, byte [rdx + r12 + 22], 13 - QUAD $0x16027c203a0f4266; BYTE $0x0e // pinsrb xmm7, byte [rdx + r8 + 22], 14 - QUAD $0x0f16327c203a0f66 // pinsrb xmm7, byte [rdx + rsi + 22], 15 - LONG $0xde0f4166; BYTE $0xf0 // pmaxub xmm6, xmm8 - LONG $0x740f4166; BYTE $0xf0 // pcmpeqb xmm6, xmm8 - QUAD $0x00000130ad6f0f66 // movdqa xmm5, oword 304[rbp] /* [rip + .LCPI11_19] */ - LONG $0xf5db0f66 // pand xmm6, xmm5 - LONG $0xde0f4166; BYTE $0xe0 // pmaxub xmm4, xmm8 - LONG $0x740f4166; BYTE $0xe0 // pcmpeqb xmm4, xmm8 - QUAD $0x000140bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 320[rbp] /* [rip + .LCPI11_20] */ - LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xe6eb0f66 // por xmm4, xmm6 - LONG $0xde0f4166; BYTE $0xf8 // pmaxub xmm7, xmm8 - LONG $0x740f4166; BYTE $0xf8 // pcmpeqb xmm7, xmm8 - QUAD $0x00000150b56f0f66 // movdqa xmm6, oword 336[rbp] /* [rip + .LCPI11_21] */ - LONG $0xfedb0f66 // pand xmm7, xmm6 - LONG $0xfceb0f66 // por xmm7, xmm4 - LONG $0xfbeb0f66 // por xmm7, xmm3 - QUAD $0x171a54203a0f4266; BYTE $0x03 // pinsrb xmm2, byte [rdx + r11 + 23], 3 - QUAD $0x04173a54203a0f66 // pinsrb xmm2, byte [rdx + rdi + 23], 4 - QUAD $0x170a54203a0f4266; BYTE $0x05 // pinsrb xmm2, byte [rdx + r9 + 23], 5 - QUAD $0x172a54203a0f4266; BYTE $0x06 // pinsrb xmm2, byte [rdx + r13 + 23], 6 - QUAD $0x173254203a0f4266; BYTE $0x07 // pinsrb xmm2, byte [rdx + r14 + 23], 7 - QUAD $0x171254203a0f4266; BYTE $0x08 // pinsrb xmm2, byte [rdx + r10 + 23], 8 - QUAD $0x173a54203a0f4266; BYTE $0x09 // pinsrb xmm2, byte [rdx + r15 + 23], 9 - QUAD $0x0a170254203a0f66 // pinsrb xmm2, byte [rdx + rax + 23], 10 - QUAD $0x0b171a54203a0f66 // pinsrb xmm2, byte [rdx + rbx + 23], 11 - QUAD $0x0c170a54203a0f66 // pinsrb xmm2, byte [rdx + rcx + 23], 12 - QUAD $0x172254203a0f4266; BYTE $0x0d // pinsrb xmm2, byte [rdx + r12 + 23], 13 - QUAD $0x170254203a0f4266; BYTE $0x0e // pinsrb xmm2, byte [rdx + r8 + 23], 14 - QUAD $0x0f173254203a0f66 // pinsrb xmm2, byte [rdx + rsi + 23], 15 + QUAD $0x083354203a0f4166; BYTE $0x0d // pinsrb xmm2, byte [r11 + rsi + 8], 13 + LONG $0x24548b4c; BYTE $0x60 // mov r10, qword [rsp + 96] + QUAD $0x081354203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r11 + r10 + 8], 14 + QUAD $0x083354203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r11 + r14 + 8], 15 LONG $0xde0f4166; BYTE $0xd0 // pmaxub xmm2, xmm8 - LONG $0x740f4166; BYTE $0xd0 // pcmpeqb xmm2, xmm8 - LONG $0x5d6f0f66; BYTE $0x60 // movdqa xmm3, oword 96[rbp] /* [rip + .LCPI11_6] */ - LONG $0xd3db0f66 // pand xmm2, xmm3 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0x181a4c203a0f4666; BYTE $0x03 // pinsrb xmm9, byte [rdx + r11 + 24], 3 - QUAD $0x183a4c203a0f4466; BYTE $0x04 // pinsrb xmm9, byte [rdx + rdi + 24], 4 - QUAD $0x180a4c203a0f4666; BYTE $0x05 // pinsrb xmm9, byte [rdx + r9 + 24], 5 - QUAD $0x182a4c203a0f4666; BYTE $0x06 // pinsrb xmm9, byte [rdx + r13 + 24], 6 - QUAD $0x18324c203a0f4666; BYTE $0x07 // pinsrb xmm9, byte [rdx + r14 + 24], 7 - QUAD $0x18124c203a0f4666; BYTE $0x08 // pinsrb xmm9, byte [rdx + r10 + 24], 8 - QUAD $0x183a4c203a0f4666; BYTE $0x09 // pinsrb xmm9, byte [rdx + r15 + 24], 9 - QUAD $0x18024c203a0f4466; BYTE $0x0a // pinsrb xmm9, byte [rdx + rax + 24], 10 - QUAD $0x181a4c203a0f4466; BYTE $0x0b // pinsrb xmm9, byte [rdx + rbx + 24], 11 - QUAD $0x180a4c203a0f4466; BYTE $0x0c // pinsrb xmm9, byte [rdx + rcx + 24], 12 - QUAD $0x18224c203a0f4666; BYTE $0x0d // pinsrb xmm9, byte [rdx + r12 + 24], 13 - QUAD $0x18024c203a0f4666; BYTE $0x0e // pinsrb xmm9, byte [rdx + r8 + 24], 14 - QUAD $0x18324c203a0f4466; BYTE $0x0f // pinsrb xmm9, byte [rdx + rsi + 24], 15 - LONG $0xde0f4566; BYTE $0xc8 // pmaxub xmm9, xmm8 - LONG $0x740f4566; BYTE $0xc8 // pcmpeqb xmm9, xmm8 - QUAD $0x191a64203a0f4666; BYTE $0x03 // pinsrb xmm12, byte [rdx + r11 + 25], 3 - QUAD $0x193a64203a0f4466; BYTE $0x04 // pinsrb xmm12, byte [rdx + rdi + 25], 4 - QUAD $0x190a64203a0f4666; BYTE $0x05 // pinsrb xmm12, byte [rdx + r9 + 25], 5 - QUAD $0x192a64203a0f4666; BYTE $0x06 // pinsrb xmm12, byte [rdx + r13 + 25], 6 - QUAD $0x193264203a0f4666; BYTE $0x07 // pinsrb xmm12, byte [rdx + r14 + 25], 7 - QUAD $0x191264203a0f4666; BYTE $0x08 // pinsrb xmm12, byte [rdx + r10 + 25], 8 - QUAD $0x193a64203a0f4666; BYTE $0x09 // pinsrb xmm12, byte [rdx + r15 + 25], 9 - QUAD $0x190264203a0f4466; BYTE $0x0a // pinsrb xmm12, byte [rdx + rax + 25], 10 - QUAD $0x191a64203a0f4466; BYTE $0x0b // pinsrb xmm12, byte [rdx + rbx + 25], 11 - QUAD $0x190a64203a0f4466; BYTE $0x0c // pinsrb xmm12, byte [rdx + rcx + 25], 12 - QUAD $0x192264203a0f4666; BYTE $0x0d // pinsrb xmm12, byte [rdx + r12 + 25], 13 - QUAD $0x190264203a0f4666; BYTE $0x0e // pinsrb xmm12, byte [rdx + r8 + 25], 14 - QUAD $0x193264203a0f4466; BYTE $0x0f // pinsrb xmm12, byte [rdx + rsi + 25], 15 - LONG $0xde0f4566; BYTE $0xe0 // pmaxub xmm12, xmm8 - LONG $0x740f4566; BYTE $0xe0 // pcmpeqb xmm12, xmm8 - QUAD $0x000100a5db0f4466; BYTE $0x00 // pand xmm12, oword 256[rbp] /* [rip + .LCPI11_16] */ - LONG $0xf80f4566; BYTE $0xe1 // psubb xmm12, xmm9 - QUAD $0x1a1a6c203a0f4666; BYTE $0x03 // pinsrb xmm13, byte [rdx + r11 + 26], 3 - QUAD $0x1a3a6c203a0f4466; BYTE $0x04 // pinsrb xmm13, byte [rdx + rdi + 26], 4 - QUAD $0x1a0a6c203a0f4666; BYTE $0x05 // pinsrb xmm13, byte [rdx + r9 + 26], 5 - QUAD $0x1a2a6c203a0f4666; BYTE $0x06 // pinsrb xmm13, byte [rdx + r13 + 26], 6 - QUAD $0x1a326c203a0f4666; BYTE $0x07 // pinsrb xmm13, byte [rdx + r14 + 26], 7 - QUAD $0x1a126c203a0f4666; BYTE $0x08 // pinsrb xmm13, byte [rdx + r10 + 26], 8 - QUAD $0x1a3a6c203a0f4666; BYTE $0x09 // pinsrb xmm13, byte [rdx + r15 + 26], 9 - QUAD $0x1a026c203a0f4466; BYTE $0x0a // pinsrb xmm13, byte [rdx + rax + 26], 10 - QUAD $0x1a1a6c203a0f4466; BYTE $0x0b // pinsrb xmm13, byte [rdx + rbx + 26], 11 - QUAD $0x1a0a6c203a0f4466; BYTE $0x0c // pinsrb xmm13, byte [rdx + rcx + 26], 12 - QUAD $0x1a226c203a0f4666; BYTE $0x0d // pinsrb xmm13, byte [rdx + r12 + 26], 13 - QUAD $0x1a026c203a0f4666; BYTE $0x0e // pinsrb xmm13, byte [rdx + r8 + 26], 14 - QUAD $0x1a326c203a0f4466; BYTE $0x0f // pinsrb xmm13, byte [rdx + rsi + 26], 15 - QUAD $0x1b1a54203a0f4666; BYTE $0x03 // pinsrb xmm10, byte [rdx + r11 + 27], 3 - QUAD $0x1b3a54203a0f4466; BYTE $0x04 // pinsrb xmm10, byte [rdx + rdi + 27], 4 - QUAD $0x1b0a54203a0f4666; BYTE $0x05 // pinsrb xmm10, byte [rdx + r9 + 27], 5 - QUAD $0x1b2a54203a0f4666; BYTE $0x06 // pinsrb xmm10, byte [rdx + r13 + 27], 6 - QUAD $0x1b3254203a0f4666; BYTE $0x07 // pinsrb xmm10, byte [rdx + r14 + 27], 7 - QUAD $0x1b1254203a0f4666; BYTE $0x08 // pinsrb xmm10, byte [rdx + r10 + 27], 8 - QUAD $0x1b3a54203a0f4666; BYTE $0x09 // pinsrb xmm10, byte [rdx + r15 + 27], 9 - QUAD $0x1b0254203a0f4466; BYTE $0x0a // pinsrb xmm10, byte [rdx + rax + 27], 10 - QUAD $0x1b1a54203a0f4466; BYTE $0x0b // pinsrb xmm10, byte [rdx + rbx + 27], 11 - QUAD $0x1b0a54203a0f4466; BYTE $0x0c // pinsrb xmm10, byte [rdx + rcx + 27], 12 - QUAD $0x1b2254203a0f4666; BYTE $0x0d // pinsrb xmm10, byte [rdx + r12 + 27], 13 - QUAD $0x1b0254203a0f4666; BYTE $0x0e // pinsrb xmm10, byte [rdx + r8 + 27], 14 - QUAD $0x1b3254203a0f4466; BYTE $0x0f // pinsrb xmm10, byte [rdx + rsi + 27], 15 - LONG $0xde0f4566; BYTE $0xe8 // pmaxub xmm13, xmm8 - LONG $0x740f4566; BYTE $0xe8 // pcmpeqb xmm13, xmm8 - QUAD $0x000110addb0f4466; BYTE $0x00 // pand xmm13, oword 272[rbp] /* [rip + .LCPI11_17] */ + LONG $0x740f4166; BYTE $0xd0 // pcmpeqb xmm2, xmm8 + QUAD $0x090354203a0f4766; BYTE $0x01 // pinsrb xmm10, byte [r11 + r8 + 9], 1 + QUAD $0x093b54203a0f4766; BYTE $0x02 // pinsrb xmm10, byte [r11 + r15 + 9], 2 + WORD $0x894d; BYTE $0xf9 // mov r9, r15 + QUAD $0x090354203a0f4566; BYTE $0x03 // pinsrb xmm10, byte [r11 + rax + 9], 3 + QUAD $0x093b54203a0f4566; BYTE $0x04 // pinsrb xmm10, byte [r11 + rdi + 9], 4 + QUAD $0x092b54203a0f4766; BYTE $0x05 // pinsrb xmm10, byte [r11 + r13 + 9], 5 + QUAD $0x092354203a0f4766; BYTE $0x06 // pinsrb xmm10, byte [r11 + r12 + 9], 6 + WORD $0x894d; BYTE $0xe7 // mov r15, r12 + QUAD $0x091b54203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r11 + rbx + 9], 7 + LONG $0x24648b4c; BYTE $0x48 // mov r12, qword [rsp + 72] + QUAD $0x092354203a0f4766; BYTE $0x08 // pinsrb xmm10, byte [r11 + r12 + 9], 8 + QUAD $0x090b54203a0f4566; BYTE $0x09 // pinsrb xmm10, byte [r11 + rcx + 9], 9 + LONG $0x247c8b48; BYTE $0x28 // mov rdi, qword [rsp + 40] + QUAD $0x093b54203a0f4566; BYTE $0x0a // pinsrb xmm10, byte [r11 + rdi + 9], 10 + QUAD $0x091354203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r11 + rdx + 9], 11 + LONG $0x24548b48; BYTE $0x30 // mov rdx, qword [rsp + 48] + QUAD $0x091354203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r11 + rdx + 9], 12 + QUAD $0x093354203a0f4566; BYTE $0x0d // pinsrb xmm10, byte [r11 + rsi + 9], 13 + QUAD $0x091354203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r11 + r10 + 9], 14 + WORD $0x894c; BYTE $0xd3 // mov rbx, r10 + QUAD $0x093354203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r11 + r14 + 9], 15 LONG $0xde0f4566; BYTE $0xd0 // pmaxub xmm10, xmm8 LONG $0x740f4566; BYTE $0xd0 // pcmpeqb xmm10, xmm8 - QUAD $0x00012095db0f4466; BYTE $0x00 // pand xmm10, oword 288[rbp] /* [rip + .LCPI11_18] */ - LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 - LONG $0xeb0f4566; BYTE $0xd4 // por xmm10, xmm12 - QUAD $0x1c1a5c203a0f4666; BYTE $0x03 // pinsrb xmm11, byte [rdx + r11 + 28], 3 - QUAD $0x1d1a74203a0f4666; BYTE $0x03 // pinsrb xmm14, byte [rdx + r11 + 29], 3 - QUAD $0x1e1a4c203a0f4266; BYTE $0x03 // pinsrb xmm1, byte [rdx + r11 + 30], 3 - QUAD $0x1f1a44203a0f4266; BYTE $0x03 // pinsrb xmm0, byte [rdx + r11 + 31], 3 - QUAD $0x1c3a5c203a0f4466; BYTE $0x04 // pinsrb xmm11, byte [rdx + rdi + 28], 4 - QUAD $0x1d3a74203a0f4466; BYTE $0x04 // pinsrb xmm14, byte [rdx + rdi + 29], 4 - QUAD $0x041e3a4c203a0f66 // pinsrb xmm1, byte [rdx + rdi + 30], 4 - QUAD $0x041f3a44203a0f66 // pinsrb xmm0, byte [rdx + rdi + 31], 4 - QUAD $0x1c0a5c203a0f4666; BYTE $0x05 // pinsrb xmm11, byte [rdx + r9 + 28], 5 - QUAD $0x1d0a74203a0f4666; BYTE $0x05 // pinsrb xmm14, byte [rdx + r9 + 29], 5 - QUAD $0x1e0a4c203a0f4266; BYTE $0x05 // pinsrb xmm1, byte [rdx + r9 + 30], 5 - QUAD $0x1f0a44203a0f4266; BYTE $0x05 // pinsrb xmm0, byte [rdx + r9 + 31], 5 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x1c2a5c203a0f4666; BYTE $0x06 // pinsrb xmm11, byte [rdx + r13 + 28], 6 - QUAD $0x1d2a74203a0f4666; BYTE $0x06 // pinsrb xmm14, byte [rdx + r13 + 29], 6 - QUAD $0x1e2a4c203a0f4266; BYTE $0x06 // pinsrb xmm1, byte [rdx + r13 + 30], 6 - QUAD $0x1f2a44203a0f4266; BYTE $0x06 // pinsrb xmm0, byte [rdx + r13 + 31], 6 - WORD $0x894c; BYTE $0xf0 // mov rax, r14 - QUAD $0x1c325c203a0f4666; BYTE $0x07 // pinsrb xmm11, byte [rdx + r14 + 28], 7 - QUAD $0x1d3274203a0f4666; BYTE $0x07 // pinsrb xmm14, byte [rdx + r14 + 29], 7 - QUAD $0x1e324c203a0f4266; BYTE $0x07 // pinsrb xmm1, byte [rdx + r14 + 30], 7 - QUAD $0x1f3244203a0f4266; BYTE $0x07 // pinsrb xmm0, byte [rdx + r14 + 31], 7 - QUAD $0x1c125c203a0f4666; BYTE $0x08 // pinsrb xmm11, byte [rdx + r10 + 28], 8 - QUAD $0x1d1274203a0f4666; BYTE $0x08 // pinsrb xmm14, byte [rdx + r10 + 29], 8 - QUAD $0x1e124c203a0f4266; BYTE $0x08 // pinsrb xmm1, byte [rdx + r10 + 30], 8 - QUAD $0x1f1244203a0f4266; BYTE $0x08 // pinsrb xmm0, byte [rdx + r10 + 31], 8 - LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] - QUAD $0x1c025c203a0f4466; BYTE $0x09 // pinsrb xmm11, byte [rdx + rax + 28], 9 - QUAD $0x1d0274203a0f4466; BYTE $0x09 // pinsrb xmm14, byte [rdx + rax + 29], 9 - QUAD $0x091e024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 30], 9 - QUAD $0x091f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 31], 9 - LONG $0x24448b48; BYTE $0x40 // mov rax, qword [rsp + 64] - QUAD $0x1c025c203a0f4466; BYTE $0x0a // pinsrb xmm11, byte [rdx + rax + 28], 10 - QUAD $0x1d0274203a0f4466; BYTE $0x0a // pinsrb xmm14, byte [rdx + rax + 29], 10 - QUAD $0x0a1e024c203a0f66 // pinsrb xmm1, byte [rdx + rax + 30], 10 - QUAD $0x0a1f0244203a0f66 // pinsrb xmm0, byte [rdx + rax + 31], 10 - WORD $0x8948; BYTE $0xd8 // mov rax, rbx - QUAD $0x1c1a5c203a0f4466; BYTE $0x0b // pinsrb xmm11, byte [rdx + rbx + 28], 11 - QUAD $0x1d1a74203a0f4466; BYTE $0x0b // pinsrb xmm14, byte [rdx + rbx + 29], 11 - QUAD $0x0b1e1a4c203a0f66 // pinsrb xmm1, byte [rdx + rbx + 30], 11 - QUAD $0x0b1f1a44203a0f66 // pinsrb xmm0, byte [rdx + rbx + 31], 11 - QUAD $0x1c0a5c203a0f4466; BYTE $0x0c // pinsrb xmm11, byte [rdx + rcx + 28], 12 - QUAD $0x1d0a74203a0f4466; BYTE $0x0c // pinsrb xmm14, byte [rdx + rcx + 29], 12 - QUAD $0x0c1e0a4c203a0f66 // pinsrb xmm1, byte [rdx + rcx + 30], 12 - QUAD $0x0c1f0a44203a0f66 // pinsrb xmm0, byte [rdx + rcx + 31], 12 - WORD $0x894c; BYTE $0xe0 // mov rax, r12 - QUAD $0x1c225c203a0f4666; BYTE $0x0d // pinsrb xmm11, byte [rdx + r12 + 28], 13 - QUAD $0x1d2274203a0f4666; BYTE $0x0d // pinsrb xmm14, byte [rdx + r12 + 29], 13 - QUAD $0x1e224c203a0f4266; BYTE $0x0d // pinsrb xmm1, byte [rdx + r12 + 30], 13 - QUAD $0x1f2244203a0f4266; BYTE $0x0d // pinsrb xmm0, byte [rdx + r12 + 31], 13 - WORD $0x894c; BYTE $0xc0 // mov rax, r8 - QUAD $0x1c025c203a0f4666; BYTE $0x0e // pinsrb xmm11, byte [rdx + r8 + 28], 14 - QUAD $0x1d0274203a0f4666; BYTE $0x0e // pinsrb xmm14, byte [rdx + r8 + 29], 14 - QUAD $0x1e024c203a0f4266; BYTE $0x0e // pinsrb xmm1, byte [rdx + r8 + 30], 14 - QUAD $0x1f0244203a0f4266; BYTE $0x0e // pinsrb xmm0, byte [rdx + r8 + 31], 14 - WORD $0x8948; BYTE $0xf0 // mov rax, rsi - QUAD $0x1c325c203a0f4466; BYTE $0x0f // pinsrb xmm11, byte [rdx + rsi + 28], 15 - QUAD $0x1d3274203a0f4466; BYTE $0x0f // pinsrb xmm14, byte [rdx + rsi + 29], 15 - QUAD $0x0f1e324c203a0f66 // pinsrb xmm1, byte [rdx + rsi + 30], 15 - QUAD $0x0f1f3244203a0f66 // pinsrb xmm0, byte [rdx + rsi + 31], 15 + QUAD $0x00010095db0f4466; BYTE $0x00 // pand xmm10, oword 256[rbp] /* [rip + .LCPI11_16] */ + LONG $0xf80f4466; BYTE $0xd2 // psubb xmm10, xmm2 + LONG $0x24448b4c; BYTE $0x50 // mov r8, qword [rsp + 80] + LONG $0x74b60f43; WORD $0x1703 // movzx esi, byte [r11 + r8 + 23] + LONG $0xd66e0f66 // movd xmm2, esi + LONG $0x24548b4c; BYTE $0x38 // mov r10, qword [rsp + 56] + QUAD $0x0a1364203a0f4766; BYTE $0x01 // pinsrb xmm12, byte [r11 + r10 + 10], 1 + QUAD $0x0a0b64203a0f4766; BYTE $0x02 // pinsrb xmm12, byte [r11 + r9 + 10], 2 + QUAD $0x0a0364203a0f4566; BYTE $0x03 // pinsrb xmm12, byte [r11 + rax + 10], 3 + QUAD $0x000000a024b48b4c // mov r14, qword [rsp + 160] + QUAD $0x0a3364203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r11 + r14 + 10], 4 + QUAD $0x0a2b64203a0f4766; BYTE $0x05 // pinsrb xmm12, byte [r11 + r13 + 10], 5 + QUAD $0x0a3b64203a0f4766; BYTE $0x06 // pinsrb xmm12, byte [r11 + r15 + 10], 6 + LONG $0x24748b48; BYTE $0x58 // mov rsi, qword [rsp + 88] + QUAD $0x0a3364203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r11 + rsi + 10], 7 + QUAD $0x0a2364203a0f4766; BYTE $0x08 // pinsrb xmm12, byte [r11 + r12 + 10], 8 + QUAD $0x0a0b64203a0f4566; BYTE $0x09 // pinsrb xmm12, byte [r11 + rcx + 10], 9 + WORD $0x8949; BYTE $0xcf // mov r15, rcx + QUAD $0x0a3b64203a0f4566; BYTE $0x0a // pinsrb xmm12, byte [r11 + rdi + 10], 10 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x0a0b64203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r11 + rcx + 10], 11 + QUAD $0x0a1364203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r11 + rdx + 10], 12 + LONG $0x24548b48; BYTE $0x10 // mov rdx, qword [rsp + 16] + QUAD $0x0a1364203a0f4566; BYTE $0x0d // pinsrb xmm12, byte [r11 + rdx + 10], 13 + QUAD $0x0a1b64203a0f4566; BYTE $0x0e // pinsrb xmm12, byte [r11 + rbx + 10], 14 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x0a3b64203a0f4566; BYTE $0x0f // pinsrb xmm12, byte [r11 + rdi + 10], 15 + QUAD $0x0b135c203a0f4766; BYTE $0x01 // pinsrb xmm11, byte [r11 + r10 + 11], 1 + QUAD $0x0b0b5c203a0f4766; BYTE $0x02 // pinsrb xmm11, byte [r11 + r9 + 11], 2 + QUAD $0x0b035c203a0f4566; BYTE $0x03 // pinsrb xmm11, byte [r11 + rax + 11], 3 + QUAD $0x0b335c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r11 + r14 + 11], 4 + QUAD $0x0b2b5c203a0f4766; BYTE $0x05 // pinsrb xmm11, byte [r11 + r13 + 11], 5 + LONG $0x24448b48; BYTE $0x78 // mov rax, qword [rsp + 120] + QUAD $0x0b035c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r11 + rax + 11], 6 + QUAD $0x0b335c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r11 + rsi + 11], 7 + QUAD $0x0b235c203a0f4766; BYTE $0x08 // pinsrb xmm11, byte [r11 + r12 + 11], 8 + QUAD $0x0b3b5c203a0f4766; BYTE $0x09 // pinsrb xmm11, byte [r11 + r15 + 11], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0b335c203a0f4566; BYTE $0x0a // pinsrb xmm11, byte [r11 + rsi + 11], 10 + QUAD $0x0b0b5c203a0f4566; BYTE $0x0b // pinsrb xmm11, byte [r11 + rcx + 11], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x0b0b5c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r11 + rcx + 11], 12 + QUAD $0x0b135c203a0f4566; BYTE $0x0d // pinsrb xmm11, byte [r11 + rdx + 11], 13 + QUAD $0x0b1b5c203a0f4566; BYTE $0x0e // pinsrb xmm11, byte [r11 + rbx + 11], 14 + QUAD $0x0b3b5c203a0f4566; BYTE $0x0f // pinsrb xmm11, byte [r11 + rdi + 11], 15 + LONG $0xde0f4566; BYTE $0xe0 // pmaxub xmm12, xmm8 + LONG $0x740f4566; BYTE $0xe0 // pcmpeqb xmm12, xmm8 + QUAD $0x000110a5db0f4466; BYTE $0x00 // pand xmm12, oword 272[rbp] /* [rip + .LCPI11_17] */ LONG $0xde0f4566; BYTE $0xd8 // pmaxub xmm11, xmm8 LONG $0x740f4566; BYTE $0xd8 // pcmpeqb xmm11, xmm8 - LONG $0xdb0f4466; BYTE $0xdd // pand xmm11, xmm5 + QUAD $0x0001209ddb0f4466; BYTE $0x00 // pand xmm11, oword 288[rbp] /* [rip + .LCPI11_18] */ + LONG $0xeb0f4566; BYTE $0xdc // por xmm11, xmm12 + LONG $0x74b60f43; WORD $0x1803 // movzx esi, byte [r11 + r8 + 24] + LONG $0x6e0f4466; BYTE $0xce // movd xmm9, esi + LONG $0xeb0f4566; BYTE $0xda // por xmm11, xmm10 + LONG $0x74b60f43; WORD $0x1903 // movzx esi, byte [r11 + r8 + 25] + LONG $0x6e0f4466; BYTE $0xe6 // movd xmm12, esi + QUAD $0x0c136c203a0f4766; BYTE $0x01 // pinsrb xmm13, byte [r11 + r10 + 12], 1 + WORD $0x894d; BYTE $0xcc // mov r12, r9 + QUAD $0x0c0b6c203a0f4766; BYTE $0x02 // pinsrb xmm13, byte [r11 + r9 + 12], 2 + QUAD $0x000000c024bc8b48 // mov rdi, qword [rsp + 192] + QUAD $0x0c3b6c203a0f4566; BYTE $0x03 // pinsrb xmm13, byte [r11 + rdi + 12], 3 + QUAD $0x0c336c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r11 + r14 + 12], 4 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x0c2b6c203a0f4766; BYTE $0x05 // pinsrb xmm13, byte [r11 + r13 + 12], 5 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + QUAD $0x0c036c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r11 + rax + 12], 6 + LONG $0x24548b4c; BYTE $0x58 // mov r10, qword [rsp + 88] + QUAD $0x0c136c203a0f4766; BYTE $0x07 // pinsrb xmm13, byte [r11 + r10 + 12], 7 + LONG $0x246c8b4c; BYTE $0x48 // mov r13, qword [rsp + 72] + QUAD $0x0c2b6c203a0f4766; BYTE $0x08 // pinsrb xmm13, byte [r11 + r13 + 12], 8 + LONG $0x244c8b48; BYTE $0x68 // mov rcx, qword [rsp + 104] + QUAD $0x0c0b6c203a0f4566; BYTE $0x09 // pinsrb xmm13, byte [r11 + rcx + 12], 9 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x0c0b6c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r11 + r9 + 12], 10 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x0c136c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r11 + rdx + 12], 11 + LONG $0x24448b4c; BYTE $0x30 // mov r8, qword [rsp + 48] + QUAD $0x0c036c203a0f4766; BYTE $0x0c // pinsrb xmm13, byte [r11 + r8 + 12], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0c036c203a0f4566; BYTE $0x0d // pinsrb xmm13, byte [r11 + rax + 12], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0c036c203a0f4566; BYTE $0x0e // pinsrb xmm13, byte [r11 + rax + 12], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x0c336c203a0f4566; BYTE $0x0f // pinsrb xmm13, byte [r11 + rsi + 12], 15 + LONG $0x24448b48; BYTE $0x38 // mov rax, qword [rsp + 56] + QUAD $0x0d0344203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r11 + rax + 13], 1 + QUAD $0x0d2344203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r11 + r12 + 13], 2 + QUAD $0x0d3b44203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r11 + rdi + 13], 3 + QUAD $0x0d3344203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r11 + r14 + 13], 4 + QUAD $0x0d1b44203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r11 + rbx + 13], 5 + QUAD $0x0d3b44203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r11 + r15 + 13], 6 + QUAD $0x0d1344203a0f4366; BYTE $0x07 // pinsrb xmm0, byte [r11 + r10 + 13], 7 + QUAD $0x0d2b44203a0f4366; BYTE $0x08 // pinsrb xmm0, byte [r11 + r13 + 13], 8 + QUAD $0x0d0b44203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r11 + rcx + 13], 9 + QUAD $0x0d0b44203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r11 + r9 + 13], 10 + QUAD $0x0d1344203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r11 + rdx + 13], 11 + QUAD $0x0d0344203a0f4366; BYTE $0x0c // pinsrb xmm0, byte [r11 + r8 + 13], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x0d0344203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r11 + rax + 13], 13 + LONG $0x24448b48; BYTE $0x60 // mov rax, qword [rsp + 96] + QUAD $0x0d0344203a0f4166; BYTE $0x0e // pinsrb xmm0, byte [r11 + rax + 13], 14 + QUAD $0x0d3344203a0f4166; BYTE $0x0f // pinsrb xmm0, byte [r11 + rsi + 13], 15 + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x0e3374203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r11 + rsi + 14], 1 + QUAD $0x0e2374203a0f4766; BYTE $0x02 // pinsrb xmm14, byte [r11 + r12 + 14], 2 + QUAD $0x0e3b74203a0f4566; BYTE $0x03 // pinsrb xmm14, byte [r11 + rdi + 14], 3 + QUAD $0x0e3374203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r11 + r14 + 14], 4 + QUAD $0x0e1b74203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r11 + rbx + 14], 5 + QUAD $0x0e3b74203a0f4766; BYTE $0x06 // pinsrb xmm14, byte [r11 + r15 + 14], 6 + QUAD $0x0e1374203a0f4766; BYTE $0x07 // pinsrb xmm14, byte [r11 + r10 + 14], 7 + WORD $0x894c; BYTE $0xd0 // mov rax, r10 + QUAD $0x0e2b74203a0f4766; BYTE $0x08 // pinsrb xmm14, byte [r11 + r13 + 14], 8 + QUAD $0x0e0b74203a0f4566; BYTE $0x09 // pinsrb xmm14, byte [r11 + rcx + 14], 9 + QUAD $0x0e0b74203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r11 + r9 + 14], 10 + QUAD $0x0e1374203a0f4566; BYTE $0x0b // pinsrb xmm14, byte [r11 + rdx + 14], 11 + QUAD $0x0e0374203a0f4766; BYTE $0x0c // pinsrb xmm14, byte [r11 + r8 + 14], 12 + LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] + QUAD $0x0e0b74203a0f4566; BYTE $0x0d // pinsrb xmm14, byte [r11 + rcx + 14], 13 + LONG $0x246c8b4c; BYTE $0x60 // mov r13, qword [rsp + 96] + QUAD $0x0e2b74203a0f4766; BYTE $0x0e // pinsrb xmm14, byte [r11 + r13 + 14], 14 + LONG $0x24448b4c; BYTE $0x20 // mov r8, qword [rsp + 32] + QUAD $0x0e0374203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r11 + r8 + 14], 15 + LONG $0xde0f4566; BYTE $0xe8 // pmaxub xmm13, xmm8 + LONG $0x740f4566; BYTE $0xe8 // pcmpeqb xmm13, xmm8 + QUAD $0x000130addb0f4466; BYTE $0x00 // pand xmm13, oword 304[rbp] /* [rip + .LCPI11_19] */ + LONG $0xde0f4166; BYTE $0xc0 // pmaxub xmm0, xmm8 + LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 + QUAD $0x0000014085db0f66 // pand xmm0, oword 320[rbp] /* [rip + .LCPI11_20] */ + LONG $0xeb0f4166; BYTE $0xc5 // por xmm0, xmm13 + LONG $0x244c8b4c; BYTE $0x50 // mov r9, qword [rsp + 80] + LONG $0x74b60f43; WORD $0x1a0b // movzx esi, byte [r11 + r9 + 26] + LONG $0x6e0f4466; BYTE $0xee // movd xmm13, esi LONG $0xde0f4566; BYTE $0xf0 // pmaxub xmm14, xmm8 LONG $0x740f4566; BYTE $0xf0 // pcmpeqb xmm14, xmm8 - LONG $0xdb0f4566; BYTE $0xf7 // pand xmm14, xmm15 + QUAD $0x000150b5db0f4466; BYTE $0x00 // pand xmm14, oword 336[rbp] /* [rip + .LCPI11_21] */ + LONG $0xeb0f4466; BYTE $0xf0 // por xmm14, xmm0 + LONG $0x74b60f43; WORD $0x1b0b // movzx esi, byte [r11 + r9 + 27] + LONG $0x6e0f4466; BYTE $0xd6 // movd xmm10, esi LONG $0xeb0f4566; BYTE $0xf3 // por xmm14, xmm11 - LONG $0xde0f4166; BYTE $0xc8 // pmaxub xmm1, xmm8 - LONG $0x740f4166; BYTE $0xc8 // pcmpeqb xmm1, xmm8 - LONG $0xcedb0f66 // pand xmm1, xmm6 - LONG $0xeb0f4166; BYTE $0xce // por xmm1, xmm14 - LONG $0xeb0f4166; BYTE $0xca // por xmm1, xmm10 - LONG $0xde0f4166; BYTE $0xc0 // pmaxub xmm0, xmm8 - LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 - LONG $0xc3db0f66 // pand xmm0, xmm3 - LONG $0xc1eb0f66 // por xmm0, xmm1 - LONG $0xca6f0f66 // movdqa xmm1, xmm2 - LONG $0xc8600f66 // punpcklbw xmm1, xmm0 - QUAD $0x0000d024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 208] - LONG $0xdd6f0f66 // movdqa xmm3, xmm5 - QUAD $0x0000b024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 176] - LONG $0xde600f66 // punpcklbw xmm3, xmm6 - LONG $0xe36f0f66 // movdqa xmm4, xmm3 - LONG $0xe1610f66 // punpcklwd xmm4, xmm1 - LONG $0xd9690f66 // punpckhwd xmm3, xmm1 - LONG $0xd0680f66 // punpckhbw xmm2, xmm0 - LONG $0xee680f66 // punpckhbw xmm5, xmm6 - LONG $0xc56f0f66 // movdqa xmm0, xmm5 - LONG $0xc2610f66 // punpcklwd xmm0, xmm2 - LONG $0xea690f66 // punpckhwd xmm5, xmm2 - QUAD $0x00000080248c8b48 // mov rcx, qword [rsp + 128] - LONG $0x7f0f41f3; WORD $0x8f6c; BYTE $0x30 // movdqu oword [r15 + 4*rcx + 48], xmm5 - LONG $0x7f0f41f3; WORD $0x8f44; BYTE $0x20 // movdqu oword [r15 + 4*rcx + 32], xmm0 - LONG $0x7f0f41f3; WORD $0x8f5c; BYTE $0x10 // movdqu oword [r15 + 4*rcx + 16], xmm3 - LONG $0x7f0f41f3; WORD $0x8f24 // movdqu oword [r15 + 4*rcx], xmm4 - LONG $0x10c18348 // add rcx, 16 - WORD $0x8948; BYTE $0xc8 // mov rax, rcx - QUAD $0x000000c0248c3b48 // cmp rcx, qword [rsp + 192] - JNE LBB11_67 - QUAD $0x000000f824948b4c // mov r10, qword [rsp + 248] - QUAD $0x000000c024943b4c // cmp r10, qword [rsp + 192] - LONG $0x24348a44 // mov r14b, byte [rsp] - QUAD $0x0000012024ac8b4c // mov r13, qword [rsp + 288] - QUAD $0x0000011824948b48 // mov rdx, qword [rsp + 280] - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - JNE LBB11_69 - JMP LBB11_72 - -LBB11_124: - LONG $0xf8e28349 // and r10, -8 - WORD $0x894c; BYTE $0xd0 // mov rax, r10 - LONG $0x06e0c148 // shl rax, 6 - WORD $0x0148; BYTE $0xd0 // add rax, rdx - LONG $0x24448948; BYTE $0x30 // mov qword [rsp + 48], rax - LONG $0x2454894c; BYTE $0x20 // mov qword [rsp + 32], r10 - LONG $0x97048d4b // lea rax, [r15 + 4*r10] - LONG $0x24448948; BYTE $0x38 // mov qword [rsp + 56], rax - LONG $0x6e0f4166; BYTE $0xc6 // movd xmm0, r14d - LONG $0xc0700ff2; BYTE $0xe0 // pshuflw xmm0, xmm0, 224 - LONG $0x700f4466; WORD $0x00d8 // pshufd xmm11, xmm0, 0 - WORD $0x3145; BYTE $0xf6 // xor r14d, r14d - LONG $0x247c894c; BYTE $0x78 // mov qword [rsp + 120], r15 - LONG $0xef0f4566; BYTE $0xff // pxor xmm15, xmm15 - -LBB11_125: - LONG $0x2474894c; BYTE $0x10 // mov qword [rsp + 16], r14 - LONG $0x06e6c149 // shl r14, 6 - WORD $0x894c; BYTE $0xf7 // mov rdi, r14 - WORD $0x894d; BYTE $0xf7 // mov r15, r14 - WORD $0x894d; BYTE $0xf4 // mov r12, r14 - WORD $0x894d; BYTE $0xf5 // mov r13, r14 - WORD $0x894c; BYTE $0xf3 // mov rbx, r14 - WORD $0x894d; BYTE $0xf1 // mov r9, r14 - LONG $0x04b70f42; BYTE $0x32 // movzx eax, word [rdx + r14] - LONG $0xe86e0f66 // movd xmm5, eax - LONG $0x44b70f42; WORD $0x0232 // movzx eax, word [rdx + r14 + 2] - LONG $0xc06e0f66 // movd xmm0, eax - LONG $0x44b70f42; WORD $0x0432 // movzx eax, word [rdx + r14 + 4] - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x44b70f42; WORD $0x0632 // movzx eax, word [rdx + r14 + 6] - LONG $0xf86e0f66 // movd xmm7, eax - LONG $0x44b70f42; WORD $0x0832 // movzx eax, word [rdx + r14 + 8] - LONG $0x6e0f4466; BYTE $0xc0 // movd xmm8, eax - LONG $0x44b70f42; WORD $0x0a32 // movzx eax, word [rdx + r14 + 10] - LONG $0xe06e0f66 // movd xmm4, eax - LONG $0x44b70f42; WORD $0x0c32 // movzx eax, word [rdx + r14 + 12] - LONG $0x74b70f42; WORD $0x0e32 // movzx esi, word [rdx + r14 + 14] - LONG $0x4cb70f42; WORD $0x1032 // movzx ecx, word [rdx + r14 + 16] - LONG $0x18244c89 // mov dword [rsp + 24], ecx - LONG $0x54b70f46; WORD $0x1232 // movzx r10d, word [rdx + r14 + 18] - LONG $0x5cb70f46; WORD $0x1432 // movzx r11d, word [rdx + r14 + 20] - WORD $0x894c; BYTE $0xf1 // mov rcx, r14 - LONG $0x40c98348 // or rcx, 64 - LONG $0x80cf8148; WORD $0x0000; BYTE $0x00 // or rdi, 128 - LONG $0xc0cf8149; WORD $0x0000; BYTE $0x00 // or r15, 192 - LONG $0x00cc8149; WORD $0x0001; BYTE $0x00 // or r12, 256 - LONG $0x40cd8149; WORD $0x0001; BYTE $0x00 // or r13, 320 - LONG $0x80cb8148; WORD $0x0001; BYTE $0x00 // or rbx, 384 - LONG $0x2cc40f66; WORD $0x010a // pinsrw xmm5, word [rdx + rcx], 1 - LONG $0x2cc40f66; WORD $0x023a // pinsrw xmm5, word [rdx + rdi], 2 - LONG $0xc40f4266; WORD $0x3a2c; BYTE $0x03 // pinsrw xmm5, word [rdx + r15], 3 - LONG $0xc40f4266; WORD $0x222c; BYTE $0x04 // pinsrw xmm5, word [rdx + r12], 4 - LONG $0xc40f4266; WORD $0x2a2c; BYTE $0x05 // pinsrw xmm5, word [rdx + r13], 5 - LONG $0x2cc40f66; WORD $0x061a // pinsrw xmm5, word [rdx + rbx], 6 - LONG $0x44c40f66; WORD $0x020a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 2], 1 - LONG $0x44c40f66; WORD $0x023a; BYTE $0x02 // pinsrw xmm0, word [rdx + rdi + 2], 2 - QUAD $0x03023a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 2], 3 - QUAD $0x04022244c40f4266 // pinsrw xmm0, word [rdx + r12 + 2], 4 - QUAD $0x05022a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 2], 5 - LONG $0x44c40f66; WORD $0x021a; BYTE $0x06 // pinsrw xmm0, word [rdx + rbx + 2], 6 - LONG $0xc0c98149; WORD $0x0001; BYTE $0x00 // or r9, 448 - QUAD $0x07020a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 2], 7 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x44b70f42; WORD $0x1632 // movzx eax, word [rdx + r14 + 22] - LONG $0x08244489 // mov dword [rsp + 8], eax - LONG $0x650f4166; BYTE $0xc3 // pcmpgtw xmm0, xmm11 - LONG $0x4cc40f66; WORD $0x040a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 4], 1 - LONG $0x4cc40f66; WORD $0x043a; BYTE $0x02 // pinsrw xmm1, word [rdx + rdi + 4], 2 - QUAD $0x03043a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 4], 3 - QUAD $0x0404224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 4], 4 - QUAD $0x05042a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 4], 5 - LONG $0x4cc40f66; WORD $0x041a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 4], 6 - QUAD $0x07040a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 4], 7 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 - QUAD $0x0000808d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 128[rbp] /* [rip + .LCPI11_8] */ - LONG $0x6f0f4166; BYTE $0xd9 // movdqa xmm3, xmm9 - LONG $0x380f4166; WORD $0xdf10 // pblendvb xmm3, xmm15, xmm0 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x00000090856f0f66 // movdqa xmm0, oword 144[rbp] /* [rip + .LCPI11_9] */ - LONG $0xf06f0f66 // movdqa xmm6, xmm0 - LONG $0x6f0f4466; BYTE $0xf0 // movdqa xmm14, xmm0 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x44b70f46; WORD $0x1832 // movzx r8d, word [rdx + r14 + 24] - LONG $0xc40f4266; WORD $0x0a2c; BYTE $0x07 // pinsrw xmm5, word [rdx + r9], 7 - LONG $0x650f4166; BYTE $0xeb // pcmpgtw xmm5, xmm11 - LONG $0xc0760f66 // pcmpeqd xmm0, xmm0 - LONG $0xe8ef0f66 // pxor xmm5, xmm0 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0x7cc40f66; WORD $0x060a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 6], 1 - LONG $0x7cc40f66; WORD $0x063a; BYTE $0x02 // pinsrw xmm7, word [rdx + rdi + 6], 2 - QUAD $0x03063a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 6], 3 - QUAD $0x0406227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 6], 4 - QUAD $0x05062a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 6], 5 - LONG $0x7cc40f66; WORD $0x061a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 6], 6 - QUAD $0x07060a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 6], 7 - LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x01080a44c40f4466 // pinsrw xmm8, word [rdx + rcx + 8], 1 - QUAD $0x02083a44c40f4466 // pinsrw xmm8, word [rdx + rdi + 8], 2 - QUAD $0x03083a44c40f4666 // pinsrw xmm8, word [rdx + r15 + 8], 3 - QUAD $0x04082244c40f4666 // pinsrw xmm8, word [rdx + r12 + 8], 4 - QUAD $0x05082a44c40f4666 // pinsrw xmm8, word [rdx + r13 + 8], 5 - QUAD $0x06081a44c40f4466 // pinsrw xmm8, word [rdx + rbx + 8], 6 - QUAD $0x07080a44c40f4666 // pinsrw xmm8, word [rdx + r9 + 8], 7 - LONG $0xddf80f66 // psubb xmm3, xmm5 - QUAD $0x0000a0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 160[rbp] /* [rip + .LCPI11_10] */ - LONG $0xc76f0f66 // movdqa xmm0, xmm7 - LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 - LONG $0x7c6e0f66; WORD $0x1824 // movd xmm7, dword [rsp + 24] - LONG $0x44b70f42; WORD $0x1a32 // movzx eax, word [rdx + r14 + 26] - LONG $0x650f4566; BYTE $0xc3 // pcmpgtw xmm8, xmm11 - LONG $0x630f4566; BYTE $0xc0 // packsswb xmm8, xmm8 - LONG $0xeb0f4466; BYTE $0xe6 // por xmm12, xmm6 - QUAD $0x0000b0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 176[rbp] /* [rip + .LCPI11_11] */ - LONG $0x6f0f4166; BYTE $0xc0 // movdqa xmm0, xmm8 - LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xf2 // movd xmm6, r10d - LONG $0x54b70f46; WORD $0x1c32 // movzx r10d, word [rdx + r14 + 28] - LONG $0x64c40f66; WORD $0x0a0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 10], 1 - LONG $0x64c40f66; WORD $0x0a3a; BYTE $0x02 // pinsrw xmm4, word [rdx + rdi + 10], 2 - QUAD $0x030a3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 10], 3 - QUAD $0x040a2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 10], 4 - QUAD $0x050a2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 10], 5 - LONG $0x64c40f66; WORD $0x0a1a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 10], 6 - QUAD $0x070a0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 10], 7 - LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0x54c40f66; WORD $0x0c0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 12], 1 - LONG $0x54c40f66; WORD $0x0c3a; BYTE $0x02 // pinsrw xmm2, word [rdx + rdi + 12], 2 - QUAD $0x030c3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 12], 3 - QUAD $0x040c2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 12], 4 - QUAD $0x050c2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 12], 5 - LONG $0x54c40f66; WORD $0x0c1a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 12], 6 - LONG $0xeb0f4466; BYTE $0xe3 // por xmm12, xmm3 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI11_12] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x74b70f42; WORD $0x1e32 // movzx esi, word [rdx + r14 + 30] - LONG $0x28247489 // mov dword [rsp + 40], esi - QUAD $0x070c0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 12], 7 - LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 - QUAD $0x0000d0ad6f0f4466; BYTE $0x00 // movdqa xmm13, oword 208[rbp] /* [rip + .LCPI11_13] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 - LONG $0x5c6e0f66; WORD $0x0824 // movd xmm3, dword [rsp + 8] - LONG $0x74b70f42; WORD $0x2032 // movzx esi, word [rdx + r14 + 32] - LONG $0x18247489 // mov dword [rsp + 24], esi - LONG $0x4cc40f66; WORD $0x0e0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 14], 1 - LONG $0x4cc40f66; WORD $0x0e3a; BYTE $0x02 // pinsrw xmm1, word [rdx + rdi + 14], 2 - QUAD $0x030e3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 14], 3 - QUAD $0x040e224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 14], 4 - QUAD $0x050e2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 14], 5 - LONG $0x4cc40f66; WORD $0x0e1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 14], 6 - LONG $0xeb0f4466; BYTE $0xed // por xmm13, xmm5 - LONG $0x6e0f4166; BYTE $0xd0 // movd xmm2, r8d - LONG $0x74b70f42; WORD $0x2232 // movzx esi, word [rdx + r14 + 34] - LONG $0x08247489 // mov dword [rsp + 8], esi - QUAD $0x070e0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 14], 7 - LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 - LONG $0x74c40f66; WORD $0x120a; BYTE $0x01 // pinsrw xmm6, word [rdx + rcx + 18], 1 - LONG $0x74c40f66; WORD $0x123a; BYTE $0x02 // pinsrw xmm6, word [rdx + rdi + 18], 2 - QUAD $0x03123a74c40f4266 // pinsrw xmm6, word [rdx + r15 + 18], 3 - QUAD $0x04122274c40f4266 // pinsrw xmm6, word [rdx + r12 + 18], 4 - QUAD $0x05122a74c40f4266 // pinsrw xmm6, word [rdx + r13 + 18], 5 - LONG $0x74c40f66; WORD $0x121a; BYTE $0x06 // pinsrw xmm6, word [rdx + rbx + 18], 6 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - QUAD $0x07120a74c40f4266 // pinsrw xmm6, word [rdx + r9 + 18], 7 - LONG $0x650f4166; BYTE $0xf3 // pcmpgtw xmm6, xmm11 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xeb0f4566; BYTE $0xec // por xmm13, xmm12 - QUAD $0x0000e0a56f0f4466; BYTE $0x00 // movdqa xmm12, oword 224[rbp] /* [rip + .LCPI11_14] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4566; WORD $0xe710 // pblendvb xmm12, xmm15, xmm0 - LONG $0x6f0f4566; BYTE $0xc1 // movdqa xmm8, xmm9 - LONG $0xc66f0f66 // movdqa xmm0, xmm6 - LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x5cb70f46; WORD $0x2432 // movzx r11d, word [rdx + r14 + 36] - LONG $0x7cc40f66; WORD $0x100a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 16], 1 - LONG $0x7cc40f66; WORD $0x103a; BYTE $0x02 // pinsrw xmm7, word [rdx + rdi + 16], 2 - QUAD $0x03103a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 16], 3 - QUAD $0x0410227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 16], 4 - QUAD $0x05102a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 16], 5 - LONG $0x7cc40f66; WORD $0x101a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 16], 6 - LONG $0x64c40f66; WORD $0x140a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 20], 1 - LONG $0x64c40f66; WORD $0x143a; BYTE $0x02 // pinsrw xmm4, word [rdx + rdi + 20], 2 - QUAD $0x03143a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 20], 3 - QUAD $0x04142264c40f4266 // pinsrw xmm4, word [rdx + r12 + 20], 4 - QUAD $0x05142a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 20], 5 - LONG $0x64c40f66; WORD $0x141a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 20], 6 - QUAD $0x07140a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 20], 7 - LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4566; BYTE $0xe5 // por xmm12, xmm13 - LONG $0x6f0f4166; BYTE $0xee // movdqa xmm5, xmm14 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xe2 // movd xmm4, r10d - LONG $0x74b70f42; WORD $0x2632 // movzx esi, word [rdx + r14 + 38] - QUAD $0x07100a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 16], 7 - LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 - QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI11_22] */ - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0x5cc40f66; WORD $0x160a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 22], 1 - LONG $0x5cc40f66; WORD $0x163a; BYTE $0x02 // pinsrw xmm3, word [rdx + rdi + 22], 2 - QUAD $0x03163a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 22], 3 - QUAD $0x0416225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 22], 4 - QUAD $0x05162a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 22], 5 - LONG $0x5cc40f66; WORD $0x161a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 22], 6 - QUAD $0x07160a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 22], 7 - LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0x54c40f66; WORD $0x180a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 24], 1 - LONG $0x54c40f66; WORD $0x183a; BYTE $0x02 // pinsrw xmm2, word [rdx + rdi + 24], 2 - QUAD $0x03183a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 24], 3 - QUAD $0x04182254c40f4266 // pinsrw xmm2, word [rdx + r12 + 24], 4 - QUAD $0x05182a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 24], 5 - LONG $0x54c40f66; WORD $0x181a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 24], 6 - QUAD $0x07180a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 24], 7 - LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 - QUAD $0x0000a0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 160[rbp] /* [rip + .LCPI11_10] */ - LONG $0x6f0f4566; BYTE $0xf2 // movdqa xmm14, xmm10 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 - LONG $0x5c6e0f66; WORD $0x2824 // movd xmm3, dword [rsp + 40] - LONG $0x44b70f42; WORD $0x2832 // movzx eax, word [rdx + r14 + 40] - LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4466; BYTE $0xf5 // por xmm14, xmm5 - QUAD $0x0000b08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 176[rbp] /* [rip + .LCPI11_11] */ - LONG $0x6f0f4566; BYTE $0xe9 // movdqa xmm13, xmm9 - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 - LONG $0x7c6e0f66; WORD $0x1824 // movd xmm7, dword [rsp + 24] - LONG $0x54b70f46; WORD $0x2a32 // movzx r10d, word [rdx + r14 + 42] - LONG $0x4cc40f66; WORD $0x1a0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 26], 1 - LONG $0x4cc40f66; WORD $0x1a3a; BYTE $0x02 // pinsrw xmm1, word [rdx + rdi + 26], 2 - QUAD $0x031a3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 26], 3 - QUAD $0x041a224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 26], 4 - QUAD $0x051a2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 26], 5 - LONG $0x4cc40f66; WORD $0x1a1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 26], 6 - QUAD $0x071a0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 26], 7 - LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0x64c40f66; WORD $0x1c0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 28], 1 - LONG $0x64c40f66; WORD $0x1c3a; BYTE $0x02 // pinsrw xmm4, word [rdx + rdi + 28], 2 - QUAD $0x031c3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 28], 3 - QUAD $0x041c2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 28], 4 - QUAD $0x051c2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 28], 5 - LONG $0x64c40f66; WORD $0x1c1a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 28], 6 - LONG $0xeb0f4566; BYTE $0xf0 // por xmm14, xmm8 - QUAD $0x000000c0ad6f0f66 // movdqa xmm5, oword 192[rbp] /* [rip + .LCPI11_12] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 - LONG $0x546e0f66; WORD $0x0824 // movd xmm2, dword [rsp + 8] - LONG $0x44b70f46; WORD $0x2c32 // movzx r8d, word [rdx + r14 + 44] - QUAD $0x071c0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 28], 7 - LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4166; BYTE $0xed // por xmm5, xmm13 - QUAD $0x000000d0b56f0f66 // movdqa xmm6, oword 208[rbp] /* [rip + .LCPI11_13] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x5cb70f46; WORD $0x2e32 // movzx r11d, word [rdx + r14 + 46] - LONG $0x5cc40f66; WORD $0x1e0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 30], 1 - LONG $0x5cc40f66; WORD $0x1e3a; BYTE $0x02 // pinsrw xmm3, word [rdx + rdi + 30], 2 - QUAD $0x031e3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 30], 3 - QUAD $0x041e225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 30], 4 - QUAD $0x051e2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 30], 5 - LONG $0x5cc40f66; WORD $0x1e1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 30], 6 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x74b70f42; WORD $0x3032 // movzx esi, word [rdx + r14 + 48] - LONG $0x08247489 // mov dword [rsp + 8], esi - QUAD $0x071e0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 30], 7 - LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 - LONG $0x54c40f66; WORD $0x220a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 34], 1 - LONG $0x54c40f66; WORD $0x223a; BYTE $0x02 // pinsrw xmm2, word [rdx + rdi + 34], 2 - QUAD $0x03223a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 34], 3 - QUAD $0x04222254c40f4266 // pinsrw xmm2, word [rdx + r12 + 34], 4 - QUAD $0x05222a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 34], 5 - LONG $0x54c40f66; WORD $0x221a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 34], 6 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07220a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 34], 7 - LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeb0f4166; BYTE $0xf6 // por xmm6, xmm14 - QUAD $0x0000e0b56f0f4466; BYTE $0x00 // movdqa xmm14, oword 224[rbp] /* [rip + .LCPI11_14] */ - LONG $0x6f0f4566; BYTE $0xee // movdqa xmm13, xmm14 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4566; WORD $0xef10 // pblendvb xmm13, xmm15, xmm0 - QUAD $0x000080856f0f4466; BYTE $0x00 // movdqa xmm8, oword 128[rbp] /* [rip + .LCPI11_8] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 - LONG $0xd06e0f66 // movd xmm2, eax - LONG $0x74b70f42; WORD $0x3232 // movzx esi, word [rdx + r14 + 50] - LONG $0x7cc40f66; WORD $0x200a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 32], 1 - LONG $0x7cc40f66; WORD $0x203a; BYTE $0x02 // pinsrw xmm7, word [rdx + rdi + 32], 2 - QUAD $0x03203a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 32], 3 - QUAD $0x0420227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 32], 4 - QUAD $0x05202a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 32], 5 - LONG $0x7cc40f66; WORD $0x201a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 32], 6 - LONG $0x64c40f66; WORD $0x240a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 36], 1 - LONG $0x64c40f66; WORD $0x243a; BYTE $0x02 // pinsrw xmm4, word [rdx + rdi + 36], 2 - QUAD $0x03243a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 36], 3 - QUAD $0x04242264c40f4266 // pinsrw xmm4, word [rdx + r12 + 36], 4 - QUAD $0x05242a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 36], 5 - LONG $0x64c40f66; WORD $0x241a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 36], 6 - QUAD $0x07240a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 36], 7 - LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xeb0f4466; BYTE $0xee // por xmm13, xmm6 - QUAD $0x00000090b56f0f66 // movdqa xmm6, oword 144[rbp] /* [rip + .LCPI11_9] */ - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xda // movd xmm3, r10d - LONG $0x54b70f46; WORD $0x3432 // movzx r10d, word [rdx + r14 + 52] - QUAD $0x07200a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 32], 7 - LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 - QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI11_22] */ - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0x4cc40f66; WORD $0x260a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 38], 1 - LONG $0x4cc40f66; WORD $0x263a; BYTE $0x02 // pinsrw xmm1, word [rdx + rdi + 38], 2 - QUAD $0x03263a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 38], 3 - QUAD $0x0426224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 38], 4 - QUAD $0x05262a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 38], 5 - LONG $0x4cc40f66; WORD $0x261a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 38], 6 - QUAD $0x07260a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 38], 7 - LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0x54c40f66; WORD $0x280a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 40], 1 - LONG $0x54c40f66; WORD $0x283a; BYTE $0x02 // pinsrw xmm2, word [rdx + rdi + 40], 2 - QUAD $0x03283a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 40], 3 - QUAD $0x04282254c40f4266 // pinsrw xmm2, word [rdx + r12 + 40], 4 - QUAD $0x05282a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 40], 5 - LONG $0x54c40f66; WORD $0x281a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 40], 6 - QUAD $0x07280a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 40], 7 - LONG $0xf80f4466; BYTE $0xc7 // psubb xmm8, xmm7 - LONG $0x6f0f4166; BYTE $0xea // movdqa xmm5, xmm10 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xc8 // movd xmm1, r8d - LONG $0x44b70f46; WORD $0x3632 // movzx r8d, word [rdx + r14 + 54] - LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x6f0f4166; BYTE $0xf1 // movdqa xmm6, xmm9 - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xe3 // movd xmm4, r11d - LONG $0x44b70f42; WORD $0x3832 // movzx eax, word [rdx + r14 + 56] - LONG $0x5cc40f66; WORD $0x2a0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 42], 1 - LONG $0x5cc40f66; WORD $0x2a3a; BYTE $0x02 // pinsrw xmm3, word [rdx + rdi + 42], 2 - QUAD $0x032a3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 42], 3 - QUAD $0x042a225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 42], 4 - QUAD $0x052a2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 42], 5 - LONG $0x5cc40f66; WORD $0x2a1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 42], 6 - QUAD $0x072a0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 42], 7 - LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0x4cc40f66; WORD $0x2c0a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 44], 1 - LONG $0x4cc40f66; WORD $0x2c3a; BYTE $0x02 // pinsrw xmm1, word [rdx + rdi + 44], 2 - QUAD $0x032c3a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 44], 3 - QUAD $0x042c224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 44], 4 - QUAD $0x052c2a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 44], 5 - LONG $0x4cc40f66; WORD $0x2c1a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 44], 6 - LONG $0xeb0f4166; BYTE $0xe8 // por xmm5, xmm8 - QUAD $0x0000c08d6f0f4466; BYTE $0x00 // movdqa xmm9, oword 192[rbp] /* [rip + .LCPI11_12] */ - LONG $0x6f0f4166; BYTE $0xd1 // movdqa xmm2, xmm9 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xd710 // pblendvb xmm2, xmm15, xmm0 - LONG $0x7c6e0f66; WORD $0x0824 // movd xmm7, dword [rsp + 8] - LONG $0x5cb70f46; WORD $0x3a32 // movzx r11d, word [rdx + r14 + 58] - QUAD $0x072c0a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 44], 7 - LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0x0000d0956f0f4466; BYTE $0x00 // movdqa xmm10, oword 208[rbp] /* [rip + .LCPI11_13] */ - LONG $0x6f0f4166; BYTE $0xf2 // movdqa xmm6, xmm10 - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 - LONG $0xce6e0f66 // movd xmm1, esi - LONG $0x74b70f42; WORD $0x3c32 // movzx esi, word [rdx + r14 + 60] - LONG $0xf2eb0f66 // por xmm6, xmm2 - LONG $0x6e0f4166; BYTE $0xd2 // movd xmm2, r10d - LONG $0x64c40f66; WORD $0x2e0a; BYTE $0x01 // pinsrw xmm4, word [rdx + rcx + 46], 1 - LONG $0x64c40f66; WORD $0x2e3a; BYTE $0x02 // pinsrw xmm4, word [rdx + rdi + 46], 2 - QUAD $0x032e3a64c40f4266 // pinsrw xmm4, word [rdx + r15 + 46], 3 - QUAD $0x042e2264c40f4266 // pinsrw xmm4, word [rdx + r12 + 46], 4 - QUAD $0x052e2a64c40f4266 // pinsrw xmm4, word [rdx + r13 + 46], 5 - LONG $0x64c40f66; WORD $0x2e1a; BYTE $0x06 // pinsrw xmm4, word [rdx + rbx + 46], 6 - QUAD $0x072e0a64c40f4266 // pinsrw xmm4, word [rdx + r9 + 46], 7 - LONG $0x650f4166; BYTE $0xe3 // pcmpgtw xmm4, xmm11 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0x6f0f4566; BYTE $0xc6 // movdqa xmm8, xmm14 - LONG $0xc46f0f66 // movdqa xmm0, xmm4 - LONG $0x380f4566; WORD $0xc710 // pblendvb xmm8, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xd8 // movd xmm3, r8d - LONG $0x4cc40f66; WORD $0x320a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 50], 1 - LONG $0x4cc40f66; WORD $0x323a; BYTE $0x02 // pinsrw xmm1, word [rdx + rdi + 50], 2 - QUAD $0x03323a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 50], 3 - QUAD $0x0432224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 50], 4 - QUAD $0x05322a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 50], 5 - LONG $0x4cc40f66; WORD $0x321a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 50], 6 - QUAD $0x07320a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 50], 7 - LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0xeb0f4466; BYTE $0xc6 // por xmm8, xmm6 - QUAD $0x00000080a56f0f66 // movdqa xmm4, oword 128[rbp] /* [rip + .LCPI11_8] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 - LONG $0xc86e0f66 // movd xmm1, eax - LONG $0x7cc40f66; WORD $0x300a; BYTE $0x01 // pinsrw xmm7, word [rdx + rcx + 48], 1 - LONG $0x7cc40f66; WORD $0x303a; BYTE $0x02 // pinsrw xmm7, word [rdx + rdi + 48], 2 - QUAD $0x03303a7cc40f4266 // pinsrw xmm7, word [rdx + r15 + 48], 3 - QUAD $0x0430227cc40f4266 // pinsrw xmm7, word [rdx + r12 + 48], 4 - QUAD $0x05302a7cc40f4266 // pinsrw xmm7, word [rdx + r13 + 48], 5 - LONG $0x7cc40f66; WORD $0x301a; BYTE $0x06 // pinsrw xmm7, word [rdx + rbx + 48], 6 - QUAD $0x07300a7cc40f4266 // pinsrw xmm7, word [rdx + r9 + 48], 7 - LONG $0x650f4166; BYTE $0xfb // pcmpgtw xmm7, xmm11 - QUAD $0x00000160bdef0f66 // pxor xmm7, oword 352[rbp] /* [rip + .LCPI11_22] */ - LONG $0x54c40f66; WORD $0x340a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 52], 1 - LONG $0x54c40f66; WORD $0x343a; BYTE $0x02 // pinsrw xmm2, word [rdx + rdi + 52], 2 - QUAD $0x03343a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 52], 3 - QUAD $0x04342254c40f4266 // pinsrw xmm2, word [rdx + r12 + 52], 4 - QUAD $0x05342a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 52], 5 - LONG $0x54c40f66; WORD $0x341a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 52], 6 - LONG $0xff630f66 // packsswb xmm7, xmm7 - QUAD $0x07340a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 52], 7 - LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 - LONG $0x5cc40f66; WORD $0x360a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 54], 1 - LONG $0x5cc40f66; WORD $0x363a; BYTE $0x02 // pinsrw xmm3, word [rdx + rdi + 54], 2 - QUAD $0x03363a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 54], 3 - QUAD $0x0436225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 54], 4 - QUAD $0x05362a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 54], 5 - LONG $0x5cc40f66; WORD $0x361a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 54], 6 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x07360a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 54], 7 - LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 - LONG $0x4cc40f66; WORD $0x380a; BYTE $0x01 // pinsrw xmm1, word [rdx + rcx + 56], 1 - LONG $0x4cc40f66; WORD $0x383a; BYTE $0x02 // pinsrw xmm1, word [rdx + rdi + 56], 2 - QUAD $0x03383a4cc40f4266 // pinsrw xmm1, word [rdx + r15 + 56], 3 - QUAD $0x0438224cc40f4266 // pinsrw xmm1, word [rdx + r12 + 56], 4 - QUAD $0x05382a4cc40f4266 // pinsrw xmm1, word [rdx + r13 + 56], 5 - LONG $0x4cc40f66; WORD $0x381a; BYTE $0x06 // pinsrw xmm1, word [rdx + rbx + 56], 6 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - QUAD $0x07380a4cc40f4266 // pinsrw xmm1, word [rdx + r9 + 56], 7 - LONG $0xe7f80f66 // psubb xmm4, xmm7 - QUAD $0x00000090ad6f0f66 // movdqa xmm5, oword 144[rbp] /* [rip + .LCPI11_9] */ - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xef10 // pblendvb xmm5, xmm15, xmm0 - QUAD $0x000000a0b56f0f66 // movdqa xmm6, oword 160[rbp] /* [rip + .LCPI11_10] */ - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4166; WORD $0xf710 // pblendvb xmm6, xmm15, xmm0 - LONG $0x6e0f4166; BYTE $0xd3 // movd xmm2, r11d - LONG $0x650f4166; BYTE $0xcb // pcmpgtw xmm1, xmm11 - LONG $0x54c40f66; WORD $0x3a0a; BYTE $0x01 // pinsrw xmm2, word [rdx + rcx + 58], 1 - LONG $0x54c40f66; WORD $0x3a3a; BYTE $0x02 // pinsrw xmm2, word [rdx + rdi + 58], 2 - QUAD $0x033a3a54c40f4266 // pinsrw xmm2, word [rdx + r15 + 58], 3 - QUAD $0x043a2254c40f4266 // pinsrw xmm2, word [rdx + r12 + 58], 4 - QUAD $0x053a2a54c40f4266 // pinsrw xmm2, word [rdx + r13 + 58], 5 - LONG $0x54c40f66; WORD $0x3a1a; BYTE $0x06 // pinsrw xmm2, word [rdx + rbx + 58], 6 - QUAD $0x073a0a54c40f4266 // pinsrw xmm2, word [rdx + r9 + 58], 7 - LONG $0xc9630f66 // packsswb xmm1, xmm1 - LONG $0x650f4166; BYTE $0xd3 // pcmpgtw xmm2, xmm11 - LONG $0xf5eb0f66 // por xmm6, xmm5 - LONG $0xde6e0f66 // movd xmm3, esi - LONG $0x5cc40f66; WORD $0x3c0a; BYTE $0x01 // pinsrw xmm3, word [rdx + rcx + 60], 1 - LONG $0x5cc40f66; WORD $0x3c3a; BYTE $0x02 // pinsrw xmm3, word [rdx + rdi + 60], 2 - QUAD $0x033c3a5cc40f4266 // pinsrw xmm3, word [rdx + r15 + 60], 3 - QUAD $0x043c225cc40f4266 // pinsrw xmm3, word [rdx + r12 + 60], 4 - QUAD $0x053c2a5cc40f4266 // pinsrw xmm3, word [rdx + r13 + 60], 5 - LONG $0x5cc40f66; WORD $0x3c1a; BYTE $0x06 // pinsrw xmm3, word [rdx + rbx + 60], 6 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - QUAD $0x073c0a5cc40f4266 // pinsrw xmm3, word [rdx + r9 + 60], 7 - LONG $0x650f4166; BYTE $0xdb // pcmpgtw xmm3, xmm11 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf4eb0f66 // por xmm6, xmm4 - QUAD $0x000000b0a56f0f66 // movdqa xmm4, oword 176[rbp] /* [rip + .LCPI11_11] */ - LONG $0xc16f0f66 // movdqa xmm0, xmm1 - LONG $0x380f4166; WORD $0xe710 // pblendvb xmm4, xmm15, xmm0 - LONG $0x6f0f4166; BYTE $0xc9 // movdqa xmm1, xmm9 - LONG $0xc26f0f66 // movdqa xmm0, xmm2 - LONG $0x380f4166; WORD $0xcf10 // pblendvb xmm1, xmm15, xmm0 - LONG $0xc36f0f66 // movdqa xmm0, xmm3 - LONG $0x380f4566; WORD $0xd710 // pblendvb xmm10, xmm15, xmm0 - LONG $0xcceb0f66 // por xmm1, xmm4 - LONG $0x44b70f42; WORD $0x3e32 // movzx eax, word [rdx + r14 + 62] - LONG $0xeb0f4466; BYTE $0xd1 // por xmm10, xmm1 - LONG $0xc06e0f66 // movd xmm0, eax - LONG $0x44c40f66; WORD $0x3e0a; BYTE $0x01 // pinsrw xmm0, word [rdx + rcx + 62], 1 - LONG $0x44c40f66; WORD $0x3e3a; BYTE $0x02 // pinsrw xmm0, word [rdx + rdi + 62], 2 - QUAD $0x033e3a44c40f4266 // pinsrw xmm0, word [rdx + r15 + 62], 3 - LONG $0x247c8b4c; BYTE $0x78 // mov r15, qword [rsp + 120] - QUAD $0x043e2244c40f4266 // pinsrw xmm0, word [rdx + r12 + 62], 4 - QUAD $0x053e2a44c40f4266 // pinsrw xmm0, word [rdx + r13 + 62], 5 - LONG $0x44c40f66; WORD $0x3e1a; BYTE $0x06 // pinsrw xmm0, word [rdx + rbx + 62], 6 - QUAD $0x073e0a44c40f4266 // pinsrw xmm0, word [rdx + r9 + 62], 7 - LONG $0x650f4166; BYTE $0xc3 // pcmpgtw xmm0, xmm11 - LONG $0xc0630f66 // packsswb xmm0, xmm0 - LONG $0xeb0f4466; BYTE $0xd6 // por xmm10, xmm6 - LONG $0x380f4566; WORD $0xf710 // pblendvb xmm14, xmm15, xmm0 - LONG $0xeb0f4566; BYTE $0xf2 // por xmm14, xmm10 - LONG $0x6f0f4166; BYTE $0xc4 // movdqa xmm0, xmm12 - LONG $0x6c0f4166; BYTE $0xc5 // punpcklqdq xmm0, xmm13 - LONG $0x6f0f4166; BYTE $0xd0 // movdqa xmm2, xmm8 - LONG $0x6c0f4166; BYTE $0xd6 // punpcklqdq xmm2, xmm14 - QUAD $0x000000f09d6f0f66 // movdqa xmm3, oword 240[rbp] /* [rip + .LCPI11_15] */ - LONG $0x00380f66; BYTE $0xd3 // pshufb xmm2, xmm3 - LONG $0x00380f66; BYTE $0xc3 // pshufb xmm0, xmm3 - LONG $0xc2610f66 // punpcklwd xmm0, xmm2 - LONG $0x600f4566; BYTE $0xc6 // punpcklbw xmm8, xmm14 - LONG $0x600f4566; BYTE $0xe5 // punpcklbw xmm12, xmm13 - LONG $0x610f4566; BYTE $0xe0 // punpcklwd xmm12, xmm8 - LONG $0x244c8b48; BYTE $0x10 // mov rcx, qword [rsp + 16] - LONG $0x7f0f45f3; WORD $0x8f24 // movdqu oword [r15 + 4*rcx], xmm12 - LONG $0x7f0f41f3; WORD $0x8f44; BYTE $0x10 // movdqu oword [r15 + 4*rcx + 16], xmm0 - LONG $0x08c18348 // add rcx, 8 - WORD $0x8949; BYTE $0xce // mov r14, rcx - LONG $0x244c3b48; BYTE $0x20 // cmp rcx, qword [rsp + 32] - JNE LBB11_125 - QUAD $0x0000010024948b4c // mov r10, qword [rsp + 256] - LONG $0x24543b4c; BYTE $0x20 // cmp r10, qword [rsp + 32] - QUAD $0x00000088249c8b4c // mov r11, qword [rsp + 136] - LONG $0x24348b44 // mov r14d, dword [rsp] - LONG $0x24648b4c; BYTE $0x38 // mov r12, qword [rsp + 56] + LONG $0x74b60f43; WORD $0x1c0b // movzx esi, byte [r11 + r9 + 28] + LONG $0x6e0f4466; BYTE $0xde // movd xmm11, esi + QUAD $0x0000d024846f0f66; BYTE $0x00 // movdqa xmm0, oword [rsp + 208] + LONG $0x244c8b48; BYTE $0x38 // mov rcx, qword [rsp + 56] + QUAD $0x0f0b44203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r11 + rcx + 15], 1 + QUAD $0x0f2344203a0f4366; BYTE $0x02 // pinsrb xmm0, byte [r11 + r12 + 15], 2 + WORD $0x894d; BYTE $0xe2 // mov r10, r12 + QUAD $0x000000c024948b48 // mov rdx, qword [rsp + 192] + QUAD $0x0f1344203a0f4166; BYTE $0x03 // pinsrb xmm0, byte [r11 + rdx + 15], 3 + QUAD $0x0f3344203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r11 + r14 + 15], 4 + QUAD $0x0f1b44203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r11 + rbx + 15], 5 + QUAD $0x0f3b44203a0f4366; BYTE $0x06 // pinsrb xmm0, byte [r11 + r15 + 15], 6 + QUAD $0x0f0344203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r11 + rax + 15], 7 + LONG $0x24448b48; BYTE $0x48 // mov rax, qword [rsp + 72] + QUAD $0x0f0344203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r11 + rax + 15], 8 + LONG $0x24648b4c; BYTE $0x68 // mov r12, qword [rsp + 104] + QUAD $0x0f2344203a0f4366; BYTE $0x09 // pinsrb xmm0, byte [r11 + r12 + 15], 9 + LONG $0x24748b48; BYTE $0x28 // mov rsi, qword [rsp + 40] + QUAD $0x0f3344203a0f4166; BYTE $0x0a // pinsrb xmm0, byte [r11 + rsi + 15], 10 + LONG $0x247c8b48; BYTE $0x18 // mov rdi, qword [rsp + 24] + QUAD $0x0f3b44203a0f4166; BYTE $0x0b // pinsrb xmm0, byte [r11 + rdi + 15], 11 + LONG $0x24748b48; BYTE $0x30 // mov rsi, qword [rsp + 48] + QUAD $0x0f3344203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r11 + rsi + 15], 12 + LONG $0x24748b48; BYTE $0x10 // mov rsi, qword [rsp + 16] + QUAD $0x0f3344203a0f4166; BYTE $0x0d // pinsrb xmm0, byte [r11 + rsi + 15], 13 + QUAD $0x0f2b44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r11 + r13 + 15], 14 + QUAD $0x0f0344203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r11 + r8 + 15], 15 + LONG $0xde0f4166; BYTE $0xc0 // pmaxub xmm0, xmm8 + LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 + LONG $0x45db0f66; BYTE $0x60 // pand xmm0, oword 96[rbp] /* [rip + .LCPI11_6] */ + LONG $0xeb0f4166; BYTE $0xc6 // por xmm0, xmm14 + QUAD $0x0000d024847f0f66; BYTE $0x00 // movdqa oword [rsp + 208], xmm0 + LONG $0x74b60f43; WORD $0x1d0b // movzx esi, byte [r11 + r9 + 29] + LONG $0x6e0f4466; BYTE $0xf6 // movd xmm14, esi + QUAD $0x100b4c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r11 + rcx + 16], 1 + QUAD $0x10134c203a0f4366; BYTE $0x02 // pinsrb xmm1, byte [r11 + r10 + 16], 2 + QUAD $0x10134c203a0f4166; BYTE $0x03 // pinsrb xmm1, byte [r11 + rdx + 16], 3 + QUAD $0x10334c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r11 + r14 + 16], 4 + QUAD $0x101b4c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r11 + rbx + 16], 5 + WORD $0x8949; BYTE $0xda // mov r10, rbx + QUAD $0x103b4c203a0f4366; BYTE $0x06 // pinsrb xmm1, byte [r11 + r15 + 16], 6 + WORD $0x894d; BYTE $0xfe // mov r14, r15 + LONG $0x244c8b4c; BYTE $0x58 // mov r9, qword [rsp + 88] + QUAD $0x100b4c203a0f4366; BYTE $0x07 // pinsrb xmm1, byte [r11 + r9 + 16], 7 + QUAD $0x10034c203a0f4166; BYTE $0x08 // pinsrb xmm1, byte [r11 + rax + 16], 8 + WORD $0x894d; BYTE $0xe0 // mov r8, r12 + QUAD $0x10234c203a0f4366; BYTE $0x09 // pinsrb xmm1, byte [r11 + r12 + 16], 9 + LONG $0x24448b48; BYTE $0x28 // mov rax, qword [rsp + 40] + QUAD $0x10034c203a0f4166; BYTE $0x0a // pinsrb xmm1, byte [r11 + rax + 16], 10 + WORD $0x8949; BYTE $0xc7 // mov r15, rax + QUAD $0x103b4c203a0f4166; BYTE $0x0b // pinsrb xmm1, byte [r11 + rdi + 16], 11 LONG $0x24448b48; BYTE $0x30 // mov rax, qword [rsp + 48] - JNE LBB11_127 - JMP LBB11_130 - -LBB11_182: - WORD $0x894d; BYTE $0xd0 // mov r8, r10 - LONG $0xfce08349 // and r8, -4 - WORD $0x894c; BYTE $0xc3 // mov rbx, r8 - LONG $0x07e3c148 // shl rbx, 7 - WORD $0x0148; BYTE $0xd3 // add rbx, rdx - LONG $0x87348d4f // lea r14, [r15 + 4*r8] - WORD $0x280f; BYTE $0xc8 // movaps xmm1, xmm0 - LONG $0x00c8c60f // shufps xmm1, xmm0, 0 - LONG $0xfcc28148; WORD $0x0001; BYTE $0x00 // add rdx, 508 - WORD $0xc931 // xor ecx, ecx - LONG $0x6f0f4466; WORD $0x007d // movdqa xmm15, oword 0[rbp] /* [rip + .LCPI11_0] */ - LONG $0x6f0f4466; WORD $0x1045 // movdqa xmm8, oword 16[rbp] /* [rip + .LCPI11_1] */ - LONG $0x6f0f4466; WORD $0x2055 // movdqa xmm10, oword 32[rbp] /* [rip + .LCPI11_2] */ - LONG $0x6f0f4466; WORD $0x305d // movdqa xmm11, oword 48[rbp] /* [rip + .LCPI11_3] */ - LONG $0x6f0f4466; WORD $0x4065 // movdqa xmm12, oword 64[rbp] /* [rip + .LCPI11_4] */ - LONG $0x6f0f4466; WORD $0x506d // movdqa xmm13, oword 80[rbp] /* [rip + .LCPI11_5] */ - LONG $0x6f0f4466; WORD $0x6075 // movdqa xmm14, oword 96[rbp] /* [rip + .LCPI11_6] */ - LONG $0x6f0f4466; WORD $0x704d // movdqa xmm9, oword 112[rbp] /* [rip + .LCPI11_7] */ - -LBB11_183: - QUAD $0xfffffe04b2100ff3 // movss xmm6, dword [rdx - 508] - QUAD $0xfffffe08ba100ff3 // movss xmm7, dword [rdx - 504] - QUAD $0xfffffe0caa100ff3 // movss xmm5, dword [rdx - 500] - QUAD $0xfffffe10a2100ff3 // movss xmm4, dword [rdx - 496] - QUAD $0xfffe84b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 380], 16 - QUAD $0xffff04b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 252], 32 - LONG $0x213a0f66; WORD $0x8472; BYTE $0x30 // insertps xmm6, dword [rdx - 124], 48 - LONG $0x02f1c20f // cmpleps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - QUAD $0xfffe88ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 376], 16 - QUAD $0xffff08ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 248], 32 - LONG $0x213a0f66; WORD $0x887a; BYTE $0x30 // insertps xmm7, dword [rdx - 120], 48 - QUAD $0xfffe8caa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 372], 16 - QUAD $0xffff0caa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 244], 32 - LONG $0x213a0f66; WORD $0x8c6a; BYTE $0x30 // insertps xmm5, dword [rdx - 116], 48 - QUAD $0xfffe90a2213a0f66; WORD $0x10ff // insertps xmm4, dword [rdx - 368], 16 - QUAD $0xffff10a2213a0f66; WORD $0x20ff // insertps xmm4, dword [rdx - 240], 32 - LONG $0x213a0f66; WORD $0x9062; BYTE $0x30 // insertps xmm4, dword [rdx - 112], 48 - LONG $0x02f9c20f // cmpleps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xd76f0f66 // movdqa xmm2, xmm7 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xd7f80f66 // psubb xmm2, xmm7 - QUAD $0xfffffe14ba100ff3 // movss xmm7, dword [rdx - 492] - QUAD $0xfffe94ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 364], 16 - QUAD $0xffff14ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 236], 32 - LONG $0x213a0f66; WORD $0x947a; BYTE $0x30 // insertps xmm7, dword [rdx - 108], 48 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffffe18b2100ff3 // movss xmm6, dword [rdx - 488] - QUAD $0xfffe98b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 360], 16 - QUAD $0xffff18b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 232], 32 - LONG $0x213a0f66; WORD $0x9872; BYTE $0x30 // insertps xmm6, dword [rdx - 104], 48 - LONG $0x02e9c20f // cmpleps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x02 // psllw xmm5, 2 - LONG $0xdb0f4166; BYTE $0xe8 // pand xmm5, xmm8 - LONG $0xeaeb0f66 // por xmm5, xmm2 - QUAD $0xfffffe1c9a100ff3 // movss xmm3, dword [rdx - 484] - QUAD $0xfffe9c9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 356], 16 - QUAD $0xffff1c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 228], 32 - LONG $0x213a0f66; WORD $0x9c5a; BYTE $0x30 // insertps xmm3, dword [rdx - 100], 48 - LONG $0x02e1c20f // cmpleps xmm4, xmm1 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 + QUAD $0x10034c203a0f4166; BYTE $0x0c // pinsrb xmm1, byte [r11 + rax + 16], 12 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x10034c203a0f4166; BYTE $0x0d // pinsrb xmm1, byte [r11 + rax + 16], 13 + WORD $0x894c; BYTE $0xef // mov rdi, r13 + QUAD $0x102b4c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r11 + r13 + 16], 14 + LONG $0x24748b48; BYTE $0x20 // mov rsi, qword [rsp + 32] + QUAD $0x10334c203a0f4166; BYTE $0x0f // pinsrb xmm1, byte [r11 + rsi + 16], 15 + LONG $0xde0f4166; BYTE $0xc8 // pmaxub xmm1, xmm8 + LONG $0x740f4166; BYTE $0xc8 // pcmpeqb xmm1, xmm8 + QUAD $0x110b6c203a0f4166; BYTE $0x01 // pinsrb xmm5, byte [r11 + rcx + 17], 1 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x111b6c203a0f4166; BYTE $0x02 // pinsrb xmm5, byte [r11 + rbx + 17], 2 + QUAD $0x11136c203a0f4166; BYTE $0x03 // pinsrb xmm5, byte [r11 + rdx + 17], 3 + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + QUAD $0x000000a024948b48 // mov rdx, qword [rsp + 160] + QUAD $0x11136c203a0f4166; BYTE $0x04 // pinsrb xmm5, byte [r11 + rdx + 17], 4 + QUAD $0x11136c203a0f4366; BYTE $0x05 // pinsrb xmm5, byte [r11 + r10 + 17], 5 + WORD $0x894d; BYTE $0xd4 // mov r12, r10 + QUAD $0x11336c203a0f4366; BYTE $0x06 // pinsrb xmm5, byte [r11 + r14 + 17], 6 + QUAD $0x110b6c203a0f4366; BYTE $0x07 // pinsrb xmm5, byte [r11 + r9 + 17], 7 + LONG $0x244c8b48; BYTE $0x48 // mov rcx, qword [rsp + 72] + QUAD $0x110b6c203a0f4166; BYTE $0x08 // pinsrb xmm5, byte [r11 + rcx + 17], 8 + QUAD $0x11036c203a0f4366; BYTE $0x09 // pinsrb xmm5, byte [r11 + r8 + 17], 9 + QUAD $0x113b6c203a0f4366; BYTE $0x0a // pinsrb xmm5, byte [r11 + r15 + 17], 10 + LONG $0x244c8b48; BYTE $0x18 // mov rcx, qword [rsp + 24] + QUAD $0x110b6c203a0f4166; BYTE $0x0b // pinsrb xmm5, byte [r11 + rcx + 17], 11 + LONG $0x24548b4c; BYTE $0x30 // mov r10, qword [rsp + 48] + QUAD $0x11136c203a0f4366; BYTE $0x0c // pinsrb xmm5, byte [r11 + r10 + 17], 12 + QUAD $0x11036c203a0f4166; BYTE $0x0d // pinsrb xmm5, byte [r11 + rax + 17], 13 + QUAD $0x113b6c203a0f4166; BYTE $0x0e // pinsrb xmm5, byte [r11 + rdi + 17], 14 + QUAD $0x11336c203a0f4166; BYTE $0x0f // pinsrb xmm5, byte [r11 + rsi + 17], 15 + LONG $0xde0f4166; BYTE $0xe8 // pmaxub xmm5, xmm8 + LONG $0x740f4166; BYTE $0xe8 // pcmpeqb xmm5, xmm8 + QUAD $0x00000100addb0f66 // pand xmm5, oword 256[rbp] /* [rip + .LCPI11_16] */ + LONG $0xe9f80f66 // psubb xmm5, xmm1 + LONG $0x24448b48; BYTE $0x50 // mov rax, qword [rsp + 80] + LONG $0x74b60f41; WORD $0x1e03 // movzx esi, byte [r11 + rax + 30] + LONG $0xce6e0f66 // movd xmm1, esi + LONG $0x24748b48; BYTE $0x38 // mov rsi, qword [rsp + 56] + QUAD $0x12337c203a0f4566; BYTE $0x01 // pinsrb xmm15, byte [r11 + rsi + 18], 1 + QUAD $0x13335c203a0f4166; BYTE $0x01 // pinsrb xmm3, byte [r11 + rsi + 19], 1 + QUAD $0x143374203a0f4166; BYTE $0x01 // pinsrb xmm6, byte [r11 + rsi + 20], 1 + QUAD $0x153364203a0f4166; BYTE $0x01 // pinsrb xmm4, byte [r11 + rsi + 21], 1 + QUAD $0x16337c203a0f4166; BYTE $0x01 // pinsrb xmm7, byte [r11 + rsi + 22], 1 + QUAD $0x173354203a0f4166; BYTE $0x01 // pinsrb xmm2, byte [r11 + rsi + 23], 1 + QUAD $0x18334c203a0f4566; BYTE $0x01 // pinsrb xmm9, byte [r11 + rsi + 24], 1 + QUAD $0x193364203a0f4566; BYTE $0x01 // pinsrb xmm12, byte [r11 + rsi + 25], 1 + QUAD $0x1a336c203a0f4566; BYTE $0x01 // pinsrb xmm13, byte [r11 + rsi + 26], 1 + QUAD $0x1b3354203a0f4566; BYTE $0x01 // pinsrb xmm10, byte [r11 + rsi + 27], 1 + QUAD $0x1c335c203a0f4566; BYTE $0x01 // pinsrb xmm11, byte [r11 + rsi + 28], 1 + QUAD $0x1d3374203a0f4566; BYTE $0x01 // pinsrb xmm14, byte [r11 + rsi + 29], 1 + QUAD $0x1e334c203a0f4166; BYTE $0x01 // pinsrb xmm1, byte [r11 + rsi + 30], 1 + LONG $0x44b60f41; WORD $0x1f03 // movzx eax, byte [r11 + rax + 31] + LONG $0xc06e0f66 // movd xmm0, eax + QUAD $0x1f3344203a0f4166; BYTE $0x01 // pinsrb xmm0, byte [r11 + rsi + 31], 1 + QUAD $0x121b7c203a0f4566; BYTE $0x02 // pinsrb xmm15, byte [r11 + rbx + 18], 2 + WORD $0x894c; BYTE $0xef // mov rdi, r13 + QUAD $0x122b7c203a0f4766; BYTE $0x03 // pinsrb xmm15, byte [r11 + r13 + 18], 3 + QUAD $0x12137c203a0f4566; BYTE $0x04 // pinsrb xmm15, byte [r11 + rdx + 18], 4 + WORD $0x8949; BYTE $0xd5 // mov r13, rdx + QUAD $0x12237c203a0f4766; BYTE $0x05 // pinsrb xmm15, byte [r11 + r12 + 18], 5 + WORD $0x894c; BYTE $0xf2 // mov rdx, r14 + QUAD $0x12337c203a0f4766; BYTE $0x06 // pinsrb xmm15, byte [r11 + r14 + 18], 6 + QUAD $0x120b7c203a0f4766; BYTE $0x07 // pinsrb xmm15, byte [r11 + r9 + 18], 7 + WORD $0x894d; BYTE $0xcf // mov r15, r9 + LONG $0x24748b48; BYTE $0x48 // mov rsi, qword [rsp + 72] + QUAD $0x12337c203a0f4566; BYTE $0x08 // pinsrb xmm15, byte [r11 + rsi + 18], 8 + QUAD $0x12037c203a0f4766; BYTE $0x09 // pinsrb xmm15, byte [r11 + r8 + 18], 9 + LONG $0x24448b4c; BYTE $0x28 // mov r8, qword [rsp + 40] + QUAD $0x12037c203a0f4766; BYTE $0x0a // pinsrb xmm15, byte [r11 + r8 + 18], 10 + QUAD $0x120b7c203a0f4566; BYTE $0x0b // pinsrb xmm15, byte [r11 + rcx + 18], 11 + QUAD $0x12137c203a0f4766; BYTE $0x0c // pinsrb xmm15, byte [r11 + r10 + 18], 12 + WORD $0x894d; BYTE $0xd6 // mov r14, r10 + LONG $0x24448b48; BYTE $0x10 // mov rax, qword [rsp + 16] + QUAD $0x12037c203a0f4566; BYTE $0x0d // pinsrb xmm15, byte [r11 + rax + 18], 13 + LONG $0x244c8b4c; BYTE $0x60 // mov r9, qword [rsp + 96] + QUAD $0x120b7c203a0f4766; BYTE $0x0e // pinsrb xmm15, byte [r11 + r9 + 18], 14 + LONG $0x244c8b48; BYTE $0x20 // mov rcx, qword [rsp + 32] + QUAD $0x120b7c203a0f4566; BYTE $0x0f // pinsrb xmm15, byte [r11 + rcx + 18], 15 + LONG $0x245c8b48; BYTE $0x40 // mov rbx, qword [rsp + 64] + QUAD $0x131b5c203a0f4166; BYTE $0x02 // pinsrb xmm3, byte [r11 + rbx + 19], 2 + QUAD $0x133b5c203a0f4166; BYTE $0x03 // pinsrb xmm3, byte [r11 + rdi + 19], 3 + WORD $0x8949; BYTE $0xfa // mov r10, rdi + QUAD $0x132b5c203a0f4366; BYTE $0x04 // pinsrb xmm3, byte [r11 + r13 + 19], 4 + WORD $0x894c; BYTE $0xeb // mov rbx, r13 + QUAD $0x13235c203a0f4366; BYTE $0x05 // pinsrb xmm3, byte [r11 + r12 + 19], 5 + QUAD $0x13135c203a0f4166; BYTE $0x06 // pinsrb xmm3, byte [r11 + rdx + 19], 6 + QUAD $0x133b5c203a0f4366; BYTE $0x07 // pinsrb xmm3, byte [r11 + r15 + 19], 7 + QUAD $0x13335c203a0f4166; BYTE $0x08 // pinsrb xmm3, byte [r11 + rsi + 19], 8 + LONG $0x247c8b4c; BYTE $0x68 // mov r15, qword [rsp + 104] + QUAD $0x133b5c203a0f4366; BYTE $0x09 // pinsrb xmm3, byte [r11 + r15 + 19], 9 + QUAD $0x13035c203a0f4366; BYTE $0x0a // pinsrb xmm3, byte [r11 + r8 + 19], 10 + LONG $0x24548b48; BYTE $0x18 // mov rdx, qword [rsp + 24] + QUAD $0x13135c203a0f4166; BYTE $0x0b // pinsrb xmm3, byte [r11 + rdx + 19], 11 + QUAD $0x13335c203a0f4366; BYTE $0x0c // pinsrb xmm3, byte [r11 + r14 + 19], 12 + QUAD $0x13035c203a0f4166; BYTE $0x0d // pinsrb xmm3, byte [r11 + rax + 19], 13 + QUAD $0x130b5c203a0f4366; BYTE $0x0e // pinsrb xmm3, byte [r11 + r9 + 19], 14 + WORD $0x894d; BYTE $0xcd // mov r13, r9 + QUAD $0x130b5c203a0f4166; BYTE $0x0f // pinsrb xmm3, byte [r11 + rcx + 19], 15 + LONG $0x247c8b48; BYTE $0x40 // mov rdi, qword [rsp + 64] + QUAD $0x143b74203a0f4166; BYTE $0x02 // pinsrb xmm6, byte [r11 + rdi + 20], 2 + QUAD $0x153b64203a0f4166; BYTE $0x02 // pinsrb xmm4, byte [r11 + rdi + 21], 2 + QUAD $0x163b7c203a0f4166; BYTE $0x02 // pinsrb xmm7, byte [r11 + rdi + 22], 2 + QUAD $0x173b54203a0f4166; BYTE $0x02 // pinsrb xmm2, byte [r11 + rdi + 23], 2 + QUAD $0x183b4c203a0f4566; BYTE $0x02 // pinsrb xmm9, byte [r11 + rdi + 24], 2 + QUAD $0x193b64203a0f4566; BYTE $0x02 // pinsrb xmm12, byte [r11 + rdi + 25], 2 + QUAD $0x1a3b6c203a0f4566; BYTE $0x02 // pinsrb xmm13, byte [r11 + rdi + 26], 2 + QUAD $0x1b3b54203a0f4566; BYTE $0x02 // pinsrb xmm10, byte [r11 + rdi + 27], 2 + QUAD $0x1c3b5c203a0f4566; BYTE $0x02 // pinsrb xmm11, byte [r11 + rdi + 28], 2 + QUAD $0x1d3b74203a0f4566; BYTE $0x02 // pinsrb xmm14, byte [r11 + rdi + 29], 2 + QUAD $0x1e3b4c203a0f4166; BYTE $0x02 // pinsrb xmm1, byte [r11 + rdi + 30], 2 + LONG $0xde0f4566; BYTE $0xf8 // pmaxub xmm15, xmm8 + LONG $0x740f4566; BYTE $0xf8 // pcmpeqb xmm15, xmm8 + QUAD $0x000110bddb0f4466; BYTE $0x00 // pand xmm15, oword 272[rbp] /* [rip + .LCPI11_17] */ + LONG $0xde0f4166; BYTE $0xd8 // pmaxub xmm3, xmm8 + LONG $0x740f4166; BYTE $0xd8 // pcmpeqb xmm3, xmm8 + QUAD $0x000001209ddb0f66 // pand xmm3, oword 288[rbp] /* [rip + .LCPI11_18] */ + LONG $0xeb0f4166; BYTE $0xdf // por xmm3, xmm15 + QUAD $0x1f3b44203a0f4166; BYTE $0x02 // pinsrb xmm0, byte [r11 + rdi + 31], 2 + LONG $0xddeb0f66 // por xmm3, xmm5 + QUAD $0x141374203a0f4366; BYTE $0x03 // pinsrb xmm6, byte [r11 + r10 + 20], 3 + QUAD $0x141b74203a0f4166; BYTE $0x04 // pinsrb xmm6, byte [r11 + rbx + 20], 4 + QUAD $0x142374203a0f4366; BYTE $0x05 // pinsrb xmm6, byte [r11 + r12 + 20], 5 + WORD $0x894d; BYTE $0xe1 // mov r9, r12 + LONG $0x24748b4c; BYTE $0x78 // mov r14, qword [rsp + 120] + QUAD $0x143374203a0f4366; BYTE $0x06 // pinsrb xmm6, byte [r11 + r14 + 20], 6 + LONG $0x24548b48; BYTE $0x58 // mov rdx, qword [rsp + 88] + QUAD $0x141374203a0f4166; BYTE $0x07 // pinsrb xmm6, byte [r11 + rdx + 20], 7 + QUAD $0x143374203a0f4166; BYTE $0x08 // pinsrb xmm6, byte [r11 + rsi + 20], 8 + WORD $0x894d; BYTE $0xf8 // mov r8, r15 + QUAD $0x143b74203a0f4366; BYTE $0x09 // pinsrb xmm6, byte [r11 + r15 + 20], 9 + LONG $0x247c8b4c; BYTE $0x28 // mov r15, qword [rsp + 40] + QUAD $0x143b74203a0f4366; BYTE $0x0a // pinsrb xmm6, byte [r11 + r15 + 20], 10 + LONG $0x24448b48; BYTE $0x18 // mov rax, qword [rsp + 24] + QUAD $0x140374203a0f4166; BYTE $0x0b // pinsrb xmm6, byte [r11 + rax + 20], 11 + LONG $0x244c8b48; BYTE $0x30 // mov rcx, qword [rsp + 48] + QUAD $0x140b74203a0f4166; BYTE $0x0c // pinsrb xmm6, byte [r11 + rcx + 20], 12 + LONG $0x24648b4c; BYTE $0x10 // mov r12, qword [rsp + 16] + QUAD $0x142374203a0f4366; BYTE $0x0d // pinsrb xmm6, byte [r11 + r12 + 20], 13 + QUAD $0x142b74203a0f4366; BYTE $0x0e // pinsrb xmm6, byte [r11 + r13 + 20], 14 + LONG $0x247c8b48; BYTE $0x20 // mov rdi, qword [rsp + 32] + QUAD $0x143b74203a0f4166; BYTE $0x0f // pinsrb xmm6, byte [r11 + rdi + 20], 15 + QUAD $0x151364203a0f4366; BYTE $0x03 // pinsrb xmm4, byte [r11 + r10 + 21], 3 + QUAD $0x151b64203a0f4166; BYTE $0x04 // pinsrb xmm4, byte [r11 + rbx + 21], 4 + QUAD $0x150b64203a0f4366; BYTE $0x05 // pinsrb xmm4, byte [r11 + r9 + 21], 5 + QUAD $0x153364203a0f4366; BYTE $0x06 // pinsrb xmm4, byte [r11 + r14 + 21], 6 + QUAD $0x151364203a0f4166; BYTE $0x07 // pinsrb xmm4, byte [r11 + rdx + 21], 7 + QUAD $0x153364203a0f4166; BYTE $0x08 // pinsrb xmm4, byte [r11 + rsi + 21], 8 + QUAD $0x150364203a0f4366; BYTE $0x09 // pinsrb xmm4, byte [r11 + r8 + 21], 9 + QUAD $0x153b64203a0f4366; BYTE $0x0a // pinsrb xmm4, byte [r11 + r15 + 21], 10 + QUAD $0x150364203a0f4166; BYTE $0x0b // pinsrb xmm4, byte [r11 + rax + 21], 11 + QUAD $0x150b64203a0f4166; BYTE $0x0c // pinsrb xmm4, byte [r11 + rcx + 21], 12 + QUAD $0x152364203a0f4366; BYTE $0x0d // pinsrb xmm4, byte [r11 + r12 + 21], 13 + QUAD $0x152b64203a0f4366; BYTE $0x0e // pinsrb xmm4, byte [r11 + r13 + 21], 14 + QUAD $0x153b64203a0f4166; BYTE $0x0f // pinsrb xmm4, byte [r11 + rdi + 21], 15 + QUAD $0x16137c203a0f4366; BYTE $0x03 // pinsrb xmm7, byte [r11 + r10 + 22], 3 + QUAD $0x161b7c203a0f4166; BYTE $0x04 // pinsrb xmm7, byte [r11 + rbx + 22], 4 + QUAD $0x160b7c203a0f4366; BYTE $0x05 // pinsrb xmm7, byte [r11 + r9 + 22], 5 + QUAD $0x16337c203a0f4366; BYTE $0x06 // pinsrb xmm7, byte [r11 + r14 + 22], 6 + QUAD $0x16137c203a0f4166; BYTE $0x07 // pinsrb xmm7, byte [r11 + rdx + 22], 7 + QUAD $0x16337c203a0f4166; BYTE $0x08 // pinsrb xmm7, byte [r11 + rsi + 22], 8 + QUAD $0x16037c203a0f4366; BYTE $0x09 // pinsrb xmm7, byte [r11 + r8 + 22], 9 + WORD $0x894c; BYTE $0xfa // mov rdx, r15 + QUAD $0x163b7c203a0f4366; BYTE $0x0a // pinsrb xmm7, byte [r11 + r15 + 22], 10 + QUAD $0x16037c203a0f4166; BYTE $0x0b // pinsrb xmm7, byte [r11 + rax + 22], 11 + QUAD $0x160b7c203a0f4166; BYTE $0x0c // pinsrb xmm7, byte [r11 + rcx + 22], 12 + WORD $0x8948; BYTE $0xca // mov rdx, rcx + QUAD $0x16237c203a0f4366; BYTE $0x0d // pinsrb xmm7, byte [r11 + r12 + 22], 13 + QUAD $0x162b7c203a0f4366; BYTE $0x0e // pinsrb xmm7, byte [r11 + r13 + 22], 14 + QUAD $0x163b7c203a0f4166; BYTE $0x0f // pinsrb xmm7, byte [r11 + rdi + 22], 15 + WORD $0x8949; BYTE $0xff // mov r15, rdi + LONG $0xde0f4166; BYTE $0xf0 // pmaxub xmm6, xmm8 + LONG $0x740f4166; BYTE $0xf0 // pcmpeqb xmm6, xmm8 + QUAD $0x00000130ad6f0f66 // movdqa xmm5, oword 304[rbp] /* [rip + .LCPI11_19] */ + LONG $0xf5db0f66 // pand xmm6, xmm5 + LONG $0xde0f4166; BYTE $0xe0 // pmaxub xmm4, xmm8 + LONG $0x740f4166; BYTE $0xe0 // pcmpeqb xmm4, xmm8 + QUAD $0x000140bd6f0f4466; BYTE $0x00 // movdqa xmm15, oword 320[rbp] /* [rip + .LCPI11_20] */ LONG $0xdb0f4166; BYTE $0xe7 // pand xmm4, xmm15 - LONG $0xf4710f66; BYTE $0x03 // psllw xmm4, 3 - LONG $0xdb0f4166; BYTE $0xe2 // pand xmm4, xmm10 - LONG $0x02f9c20f // cmpleps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x04 // psllw xmm7, 4 - LONG $0xdb0f4166; BYTE $0xfb // pand xmm7, xmm11 + LONG $0xe6eb0f66 // por xmm4, xmm6 + LONG $0xde0f4166; BYTE $0xf8 // pmaxub xmm7, xmm8 + LONG $0x740f4166; BYTE $0xf8 // pcmpeqb xmm7, xmm8 + QUAD $0x00000150b56f0f66 // movdqa xmm6, oword 336[rbp] /* [rip + .LCPI11_21] */ + LONG $0xfedb0f66 // pand xmm7, xmm6 LONG $0xfceb0f66 // por xmm7, xmm4 - QUAD $0xfffffe20a2100ff3 // movss xmm4, dword [rdx - 480] - QUAD $0xfffea0a2213a0f66; WORD $0x10ff // insertps xmm4, dword [rdx - 352], 16 - QUAD $0xffff20a2213a0f66; WORD $0x20ff // insertps xmm4, dword [rdx - 224], 32 - LONG $0x213a0f66; WORD $0xa062; BYTE $0x30 // insertps xmm4, dword [rdx - 96], 48 - LONG $0xfdeb0f66 // por xmm7, xmm5 - QUAD $0xfffffe24aa100ff3 // movss xmm5, dword [rdx - 476] - QUAD $0xfffea4aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 348], 16 - QUAD $0xffff24aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 220], 32 - LONG $0x213a0f66; WORD $0xa46a; BYTE $0x30 // insertps xmm5, dword [rdx - 92], 48 - LONG $0x02e9c20f // cmpleps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0x02f1c20f // cmpleps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0x02d9c20f // cmpleps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x06 // psllw xmm3, 6 - LONG $0xdb0f4166; BYTE $0xdd // pand xmm3, xmm13 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe2892100ff3 // movss xmm2, dword [rdx - 472] - QUAD $0xfffea892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 344], 16 - QUAD $0xffff2892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 216], 32 - LONG $0x213a0f66; WORD $0xa852; BYTE $0x30 // insertps xmm2, dword [rdx - 88], 48 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0x02e1c20f // cmpleps xmm4, xmm1 - LONG $0xe46b0f66 // packssdw xmm4, xmm4 - LONG $0xe4630f66 // packsswb xmm4, xmm4 - LONG $0xf4710f66; BYTE $0x07 // psllw xmm4, 7 - LONG $0xdb0f4166; BYTE $0xe6 // pand xmm4, xmm14 - LONG $0xe3eb0f66 // por xmm4, xmm3 - QUAD $0xfffffe2c9a100ff3 // movss xmm3, dword [rdx - 468] - QUAD $0xfffeac9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 340], 16 - QUAD $0xffff2c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 212], 32 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0x213a0f66; WORD $0xac5a; BYTE $0x30 // insertps xmm3, dword [rdx - 84], 48 - LONG $0xe7eb0f66 // por xmm4, xmm7 - LONG $0x02d1c20f // cmpleps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf26f0f66 // movdqa xmm6, xmm2 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf2f80f66 // psubb xmm6, xmm2 - QUAD $0xfffffe30ba100ff3 // movss xmm7, dword [rdx - 464] - QUAD $0xfffeb0ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 336], 16 - QUAD $0xffff30ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 208], 32 - LONG $0x213a0f66; WORD $0xb07a; BYTE $0x30 // insertps xmm7, dword [rdx - 80], 48 - LONG $0xf5eb0f66 // por xmm6, xmm5 - QUAD $0xfffffe34aa100ff3 // movss xmm5, dword [rdx - 460] - QUAD $0xfffeb4aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 332], 16 - QUAD $0xffff34aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 204], 32 - LONG $0x213a0f66; WORD $0xb46a; BYTE $0x30 // insertps xmm5, dword [rdx - 76], 48 - LONG $0x02d9c20f // cmpleps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe38b2100ff3 // movss xmm6, dword [rdx - 456] - QUAD $0xfffeb8b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 328], 16 - QUAD $0xffff38b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 200], 32 - LONG $0x213a0f66; WORD $0xb872; BYTE $0x30 // insertps xmm6, dword [rdx - 72], 48 - LONG $0x02f9c20f // cmpleps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x03 // psllw xmm7, 3 - LONG $0xdb0f4166; BYTE $0xfa // pand xmm7, xmm10 - LONG $0x02e9c20f // cmpleps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x04 // psllw xmm5, 4 - LONG $0xdb0f4166; BYTE $0xeb // pand xmm5, xmm11 - LONG $0xefeb0f66 // por xmm5, xmm7 - QUAD $0xfffffe3c92100ff3 // movss xmm2, dword [rdx - 452] - QUAD $0xfffebc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 324], 16 - QUAD $0xffff3c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 196], 32 - LONG $0x213a0f66; WORD $0xbc52; BYTE $0x30 // insertps xmm2, dword [rdx - 68], 48 - LONG $0xebeb0f66 // por xmm5, xmm3 - QUAD $0xfffffe40ba100ff3 // movss xmm7, dword [rdx - 448] - QUAD $0xfffec0ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 320], 16 - QUAD $0xffff40ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 192], 32 - LONG $0x213a0f66; WORD $0xc07a; BYTE $0x30 // insertps xmm7, dword [rdx - 64], 48 - LONG $0x02f1c20f // cmpleps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x05 // psllw xmm6, 5 - LONG $0xdb0f4166; BYTE $0xf4 // pand xmm6, xmm12 - LONG $0x02d1c20f // cmpleps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd6eb0f66 // por xmm2, xmm6 - QUAD $0xfffffe44b2100ff3 // movss xmm6, dword [rdx - 444] - QUAD $0xfffec4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 316], 16 - QUAD $0xffff44b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 188], 32 - LONG $0x213a0f66; WORD $0xc472; BYTE $0x30 // insertps xmm6, dword [rdx - 60], 48 - LONG $0x02f1c20f // cmpleps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0x02f9c20f // cmpleps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xf7710f66; BYTE $0x07 // psllw xmm7, 7 - LONG $0xdb0f4166; BYTE $0xfe // pand xmm7, xmm14 - LONG $0xfaeb0f66 // por xmm7, xmm2 - QUAD $0xfffffe4892100ff3 // movss xmm2, dword [rdx - 440] - QUAD $0xfffec892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 312], 16 - QUAD $0xffff4892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 184], 32 - LONG $0x213a0f66; WORD $0xc852; BYTE $0x30 // insertps xmm2, dword [rdx - 56], 48 - LONG $0xfdeb0f66 // por xmm7, xmm5 - QUAD $0xfffffe4c9a100ff3 // movss xmm3, dword [rdx - 436] - QUAD $0xfffecc9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 308], 16 - QUAD $0xffff4c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 180], 32 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0x213a0f66; WORD $0xcc5a; BYTE $0x30 // insertps xmm3, dword [rdx - 52], 48 - LONG $0xe7620f66 // punpckldq xmm4, xmm7 - LONG $0x02d1c20f // cmpleps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xfa6f0f66 // movdqa xmm7, xmm2 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xfaf80f66 // psubb xmm7, xmm2 - QUAD $0xfffffe50aa100ff3 // movss xmm5, dword [rdx - 432] - QUAD $0xfffed0aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 304], 16 - QUAD $0xffff50aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 176], 32 - LONG $0x213a0f66; WORD $0xd06a; BYTE $0x30 // insertps xmm5, dword [rdx - 48], 48 - LONG $0xfeeb0f66 // por xmm7, xmm6 - QUAD $0xfffffe54b2100ff3 // movss xmm6, dword [rdx - 428] - QUAD $0xfffed4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 300], 16 - QUAD $0xffff54b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 172], 32 - LONG $0x213a0f66; WORD $0xd472; BYTE $0x30 // insertps xmm6, dword [rdx - 44], 48 - LONG $0x02d9c20f // cmpleps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdfeb0f66 // por xmm3, xmm7 - QUAD $0xfffffe58ba100ff3 // movss xmm7, dword [rdx - 424] - QUAD $0xfffed8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 296], 16 - QUAD $0xffff58ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 168], 32 - LONG $0x213a0f66; WORD $0xd87a; BYTE $0x30 // insertps xmm7, dword [rdx - 40], 48 - LONG $0x02e9c20f // cmpleps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xdb0f4166; BYTE $0xef // pand xmm5, xmm15 - LONG $0xf5710f66; BYTE $0x03 // psllw xmm5, 3 - LONG $0xdb0f4166; BYTE $0xea // pand xmm5, xmm10 - LONG $0x02f1c20f // cmpleps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf5eb0f66 // por xmm6, xmm5 - QUAD $0xfffffe5c92100ff3 // movss xmm2, dword [rdx - 420] - QUAD $0xfffedc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 292], 16 - QUAD $0xffff5c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 164], 32 - LONG $0x213a0f66; WORD $0xdc52; BYTE $0x30 // insertps xmm2, dword [rdx - 36], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffffe60aa100ff3 // movss xmm5, dword [rdx - 416] - QUAD $0xfffee0aa213a0f66; WORD $0x10ff // insertps xmm5, dword [rdx - 288], 16 - QUAD $0xffff60aa213a0f66; WORD $0x20ff // insertps xmm5, dword [rdx - 160], 32 - LONG $0x213a0f66; WORD $0xe06a; BYTE $0x30 // insertps xmm5, dword [rdx - 32], 48 - LONG $0x02f9c20f // cmpleps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x02d1c20f // cmpleps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 - LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffffe64ba100ff3 // movss xmm7, dword [rdx - 412] - QUAD $0xfffee4ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 284], 16 - QUAD $0xffff64ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 156], 32 - LONG $0x213a0f66; WORD $0xe47a; BYTE $0x30 // insertps xmm7, dword [rdx - 28], 48 - LONG $0x02f9c20f // cmpleps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0x02e9c20f // cmpleps xmm5, xmm1 - LONG $0xed6b0f66 // packssdw xmm5, xmm5 - LONG $0xed630f66 // packsswb xmm5, xmm5 - LONG $0xf5710f66; BYTE $0x07 // psllw xmm5, 7 - LONG $0xdb0f4166; BYTE $0xee // pand xmm5, xmm14 - LONG $0xeaeb0f66 // por xmm5, xmm2 - QUAD $0xfffffe6892100ff3 // movss xmm2, dword [rdx - 408] - QUAD $0xfffee892213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 280], 16 - QUAD $0xffff6892213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 152], 32 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0x213a0f66; WORD $0xe852; BYTE $0x30 // insertps xmm2, dword [rdx - 24], 48 - LONG $0xeeeb0f66 // por xmm5, xmm6 - LONG $0x02d1c20f // cmpleps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xf26f0f66 // movdqa xmm6, xmm2 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf2f80f66 // psubb xmm6, xmm2 - QUAD $0xfffffe6c9a100ff3 // movss xmm3, dword [rdx - 404] - QUAD $0xfffeec9a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 276], 16 - QUAD $0xffff6c9a213a0f66; WORD $0x20ff // insertps xmm3, dword [rdx - 148], 32 - LONG $0x213a0f66; WORD $0xec5a; BYTE $0x30 // insertps xmm3, dword [rdx - 20], 48 - LONG $0xf7eb0f66 // por xmm6, xmm7 - QUAD $0xfffffe7092100ff3 // movss xmm2, dword [rdx - 400] - QUAD $0xfffef092213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 272], 16 - QUAD $0xffff7092213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 144], 32 - LONG $0x213a0f66; WORD $0xf052; BYTE $0x30 // insertps xmm2, dword [rdx - 16], 48 - LONG $0x02d9c20f // cmpleps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xdb0f4166; BYTE $0xdf // pand xmm3, xmm15 - LONG $0xf3710f66; BYTE $0x02 // psllw xmm3, 2 - LONG $0xdb0f4166; BYTE $0xd8 // pand xmm3, xmm8 - LONG $0xdeeb0f66 // por xmm3, xmm6 - QUAD $0xfffffe74b2100ff3 // movss xmm6, dword [rdx - 396] - QUAD $0xfffef4b2213a0f66; WORD $0x10ff // insertps xmm6, dword [rdx - 268], 16 - QUAD $0xffff74b2213a0f66; WORD $0x20ff // insertps xmm6, dword [rdx - 140], 32 - LONG $0x213a0f66; WORD $0xf472; BYTE $0x30 // insertps xmm6, dword [rdx - 12], 48 - LONG $0x02d1c20f // cmpleps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x03 // psllw xmm2, 3 - LONG $0xdb0f4166; BYTE $0xd2 // pand xmm2, xmm10 - LONG $0x02f1c20f // cmpleps xmm6, xmm1 - LONG $0xf66b0f66 // packssdw xmm6, xmm6 - LONG $0xf6630f66 // packsswb xmm6, xmm6 - LONG $0xdb0f4166; BYTE $0xf7 // pand xmm6, xmm15 - LONG $0xf6710f66; BYTE $0x04 // psllw xmm6, 4 - LONG $0xdb0f4166; BYTE $0xf3 // pand xmm6, xmm11 - LONG $0xf2eb0f66 // por xmm6, xmm2 - QUAD $0xfffffe78ba100ff3 // movss xmm7, dword [rdx - 392] - QUAD $0xfffef8ba213a0f66; WORD $0x10ff // insertps xmm7, dword [rdx - 264], 16 - QUAD $0xffff78ba213a0f66; WORD $0x20ff // insertps xmm7, dword [rdx - 136], 32 - LONG $0x213a0f66; WORD $0xf87a; BYTE $0x30 // insertps xmm7, dword [rdx - 8], 48 - LONG $0xf3eb0f66 // por xmm6, xmm3 - QUAD $0xfffffe7c92100ff3 // movss xmm2, dword [rdx - 388] - QUAD $0xfffefc92213a0f66; WORD $0x10ff // insertps xmm2, dword [rdx - 260], 16 - QUAD $0xffff7c92213a0f66; WORD $0x20ff // insertps xmm2, dword [rdx - 132], 32 - LONG $0x213a0f66; WORD $0xfc52; BYTE $0x30 // insertps xmm2, dword [rdx - 4], 48 - LONG $0x02f9c20f // cmpleps xmm7, xmm1 - LONG $0xff6b0f66 // packssdw xmm7, xmm7 - LONG $0xff630f66 // packsswb xmm7, xmm7 - LONG $0xdb0f4166; BYTE $0xff // pand xmm7, xmm15 - LONG $0xf7710f66; BYTE $0x05 // psllw xmm7, 5 - LONG $0xdb0f4166; BYTE $0xfc // pand xmm7, xmm12 - LONG $0x02d1c20f // cmpleps xmm2, xmm1 - LONG $0xd26b0f66 // packssdw xmm2, xmm2 - LONG $0xd2630f66 // packsswb xmm2, xmm2 - LONG $0xdb0f4166; BYTE $0xd7 // pand xmm2, xmm15 - LONG $0xf2710f66; BYTE $0x06 // psllw xmm2, 6 - LONG $0xdb0f4166; BYTE $0xd5 // pand xmm2, xmm13 + LONG $0xfbeb0f66 // por xmm7, xmm3 + QUAD $0x171354203a0f4366; BYTE $0x03 // pinsrb xmm2, byte [r11 + r10 + 23], 3 + WORD $0x8949; BYTE $0xde // mov r14, rbx + QUAD $0x171b54203a0f4166; BYTE $0x04 // pinsrb xmm2, byte [r11 + rbx + 23], 4 + WORD $0x894c; BYTE $0xcb // mov rbx, r9 + QUAD $0x170b54203a0f4366; BYTE $0x05 // pinsrb xmm2, byte [r11 + r9 + 23], 5 + LONG $0x247c8b48; BYTE $0x78 // mov rdi, qword [rsp + 120] + QUAD $0x173b54203a0f4166; BYTE $0x06 // pinsrb xmm2, byte [r11 + rdi + 23], 6 + LONG $0x244c8b48; BYTE $0x58 // mov rcx, qword [rsp + 88] + QUAD $0x170b54203a0f4166; BYTE $0x07 // pinsrb xmm2, byte [r11 + rcx + 23], 7 + QUAD $0x173354203a0f4166; BYTE $0x08 // pinsrb xmm2, byte [r11 + rsi + 23], 8 + QUAD $0x170354203a0f4366; BYTE $0x09 // pinsrb xmm2, byte [r11 + r8 + 23], 9 + LONG $0x244c8b4c; BYTE $0x28 // mov r9, qword [rsp + 40] + QUAD $0x170b54203a0f4366; BYTE $0x0a // pinsrb xmm2, byte [r11 + r9 + 23], 10 + QUAD $0x170354203a0f4166; BYTE $0x0b // pinsrb xmm2, byte [r11 + rax + 23], 11 + QUAD $0x171354203a0f4166; BYTE $0x0c // pinsrb xmm2, byte [r11 + rdx + 23], 12 + QUAD $0x172354203a0f4366; BYTE $0x0d // pinsrb xmm2, byte [r11 + r12 + 23], 13 + QUAD $0x172b54203a0f4366; BYTE $0x0e // pinsrb xmm2, byte [r11 + r13 + 23], 14 + QUAD $0x173b54203a0f4366; BYTE $0x0f // pinsrb xmm2, byte [r11 + r15 + 23], 15 + LONG $0xde0f4166; BYTE $0xd0 // pmaxub xmm2, xmm8 + LONG $0x740f4166; BYTE $0xd0 // pcmpeqb xmm2, xmm8 + LONG $0x5d6f0f66; BYTE $0x60 // movdqa xmm3, oword 96[rbp] /* [rip + .LCPI11_6] */ + LONG $0xd3db0f66 // pand xmm2, xmm3 LONG $0xd7eb0f66 // por xmm2, xmm7 - QUAD $0xfffffe809a100ff3 // movss xmm3, dword [rdx - 384] - QUAD $0xffff009a213a0f66; WORD $0x10ff // insertps xmm3, dword [rdx - 256], 16 - LONG $0x213a0f66; WORD $0x805a; BYTE $0x20 // insertps xmm3, dword [rdx - 128], 32 - LONG $0x213a0f66; WORD $0x301a // insertps xmm3, dword [rdx], 48 - LONG $0x02d9c20f // cmpleps xmm3, xmm1 - LONG $0xdb6b0f66 // packssdw xmm3, xmm3 - LONG $0xdb630f66 // packsswb xmm3, xmm3 - LONG $0xf3710f66; BYTE $0x07 // psllw xmm3, 7 - LONG $0xdb0f4166; BYTE $0xde // pand xmm3, xmm14 - LONG $0xdaeb0f66 // por xmm3, xmm2 - LONG $0xdeeb0f66 // por xmm3, xmm6 - LONG $0xeb620f66 // punpckldq xmm5, xmm3 - LONG $0xe5600f66 // punpcklbw xmm4, xmm5 - LONG $0x380f4166; WORD $0xe100 // pshufb xmm4, xmm9 - LONG $0x7f0f41f3; WORD $0x8f24 // movdqu oword [r15 + 4*rcx], xmm4 - LONG $0x04c18348 // add rcx, 4 - LONG $0x00c28148; WORD $0x0002; BYTE $0x00 // add rdx, 512 - WORD $0x3949; BYTE $0xc8 // cmp r8, rcx - JNE LBB11_183 - WORD $0x394d; BYTE $0xc2 // cmp r10, r8 - JNE LBB11_185 - JMP LBB11_188 + QUAD $0x18134c203a0f4766; BYTE $0x03 // pinsrb xmm9, byte [r11 + r10 + 24], 3 + QUAD $0x18334c203a0f4766; BYTE $0x04 // pinsrb xmm9, byte [r11 + r14 + 24], 4 + QUAD $0x181b4c203a0f4566; BYTE $0x05 // pinsrb xmm9, byte [r11 + rbx + 24], 5 + QUAD $0x183b4c203a0f4566; BYTE $0x06 // pinsrb xmm9, byte [r11 + rdi + 24], 6 + QUAD $0x180b4c203a0f4566; BYTE $0x07 // pinsrb xmm9, byte [r11 + rcx + 24], 7 + QUAD $0x18334c203a0f4566; BYTE $0x08 // pinsrb xmm9, byte [r11 + rsi + 24], 8 + QUAD $0x18034c203a0f4766; BYTE $0x09 // pinsrb xmm9, byte [r11 + r8 + 24], 9 + QUAD $0x180b4c203a0f4766; BYTE $0x0a // pinsrb xmm9, byte [r11 + r9 + 24], 10 + QUAD $0x18034c203a0f4566; BYTE $0x0b // pinsrb xmm9, byte [r11 + rax + 24], 11 + QUAD $0x18134c203a0f4566; BYTE $0x0c // pinsrb xmm9, byte [r11 + rdx + 24], 12 + QUAD $0x18234c203a0f4766; BYTE $0x0d // pinsrb xmm9, byte [r11 + r12 + 24], 13 + QUAD $0x182b4c203a0f4766; BYTE $0x0e // pinsrb xmm9, byte [r11 + r13 + 24], 14 + QUAD $0x183b4c203a0f4766; BYTE $0x0f // pinsrb xmm9, byte [r11 + r15 + 24], 15 + LONG $0xde0f4566; BYTE $0xc8 // pmaxub xmm9, xmm8 + LONG $0x740f4566; BYTE $0xc8 // pcmpeqb xmm9, xmm8 + QUAD $0x191364203a0f4766; BYTE $0x03 // pinsrb xmm12, byte [r11 + r10 + 25], 3 + QUAD $0x193364203a0f4766; BYTE $0x04 // pinsrb xmm12, byte [r11 + r14 + 25], 4 + QUAD $0x191b64203a0f4566; BYTE $0x05 // pinsrb xmm12, byte [r11 + rbx + 25], 5 + QUAD $0x193b64203a0f4566; BYTE $0x06 // pinsrb xmm12, byte [r11 + rdi + 25], 6 + QUAD $0x190b64203a0f4566; BYTE $0x07 // pinsrb xmm12, byte [r11 + rcx + 25], 7 + QUAD $0x193364203a0f4566; BYTE $0x08 // pinsrb xmm12, byte [r11 + rsi + 25], 8 + QUAD $0x190364203a0f4766; BYTE $0x09 // pinsrb xmm12, byte [r11 + r8 + 25], 9 + QUAD $0x190b64203a0f4766; BYTE $0x0a // pinsrb xmm12, byte [r11 + r9 + 25], 10 + QUAD $0x190364203a0f4566; BYTE $0x0b // pinsrb xmm12, byte [r11 + rax + 25], 11 + QUAD $0x191364203a0f4566; BYTE $0x0c // pinsrb xmm12, byte [r11 + rdx + 25], 12 + QUAD $0x192364203a0f4766; BYTE $0x0d // pinsrb xmm12, byte [r11 + r12 + 25], 13 + QUAD $0x192b64203a0f4766; BYTE $0x0e // pinsrb xmm12, byte [r11 + r13 + 25], 14 + QUAD $0x193b64203a0f4766; BYTE $0x0f // pinsrb xmm12, byte [r11 + r15 + 25], 15 + LONG $0xde0f4566; BYTE $0xe0 // pmaxub xmm12, xmm8 + LONG $0x740f4566; BYTE $0xe0 // pcmpeqb xmm12, xmm8 + QUAD $0x000100a5db0f4466; BYTE $0x00 // pand xmm12, oword 256[rbp] /* [rip + .LCPI11_16] */ + LONG $0xf80f4566; BYTE $0xe1 // psubb xmm12, xmm9 + QUAD $0x1a136c203a0f4766; BYTE $0x03 // pinsrb xmm13, byte [r11 + r10 + 26], 3 + QUAD $0x1a336c203a0f4766; BYTE $0x04 // pinsrb xmm13, byte [r11 + r14 + 26], 4 + QUAD $0x1a1b6c203a0f4566; BYTE $0x05 // pinsrb xmm13, byte [r11 + rbx + 26], 5 + QUAD $0x1a3b6c203a0f4566; BYTE $0x06 // pinsrb xmm13, byte [r11 + rdi + 26], 6 + QUAD $0x1a0b6c203a0f4566; BYTE $0x07 // pinsrb xmm13, byte [r11 + rcx + 26], 7 + QUAD $0x1a336c203a0f4566; BYTE $0x08 // pinsrb xmm13, byte [r11 + rsi + 26], 8 + QUAD $0x1a036c203a0f4766; BYTE $0x09 // pinsrb xmm13, byte [r11 + r8 + 26], 9 + QUAD $0x1a0b6c203a0f4766; BYTE $0x0a // pinsrb xmm13, byte [r11 + r9 + 26], 10 + QUAD $0x1a036c203a0f4566; BYTE $0x0b // pinsrb xmm13, byte [r11 + rax + 26], 11 + QUAD $0x1a136c203a0f4566; BYTE $0x0c // pinsrb xmm13, byte [r11 + rdx + 26], 12 + QUAD $0x1a236c203a0f4766; BYTE $0x0d // pinsrb xmm13, byte [r11 + r12 + 26], 13 + QUAD $0x1a2b6c203a0f4766; BYTE $0x0e // pinsrb xmm13, byte [r11 + r13 + 26], 14 + QUAD $0x1a3b6c203a0f4766; BYTE $0x0f // pinsrb xmm13, byte [r11 + r15 + 26], 15 + QUAD $0x1b1354203a0f4766; BYTE $0x03 // pinsrb xmm10, byte [r11 + r10 + 27], 3 + QUAD $0x1b3354203a0f4766; BYTE $0x04 // pinsrb xmm10, byte [r11 + r14 + 27], 4 + QUAD $0x1b1b54203a0f4566; BYTE $0x05 // pinsrb xmm10, byte [r11 + rbx + 27], 5 + QUAD $0x1b3b54203a0f4566; BYTE $0x06 // pinsrb xmm10, byte [r11 + rdi + 27], 6 + QUAD $0x1b0b54203a0f4566; BYTE $0x07 // pinsrb xmm10, byte [r11 + rcx + 27], 7 + QUAD $0x1b3354203a0f4566; BYTE $0x08 // pinsrb xmm10, byte [r11 + rsi + 27], 8 + QUAD $0x1b0354203a0f4766; BYTE $0x09 // pinsrb xmm10, byte [r11 + r8 + 27], 9 + QUAD $0x1b0b54203a0f4766; BYTE $0x0a // pinsrb xmm10, byte [r11 + r9 + 27], 10 + QUAD $0x1b0354203a0f4566; BYTE $0x0b // pinsrb xmm10, byte [r11 + rax + 27], 11 + WORD $0x8949; BYTE $0xc0 // mov r8, rax + QUAD $0x1b1354203a0f4566; BYTE $0x0c // pinsrb xmm10, byte [r11 + rdx + 27], 12 + QUAD $0x1b2354203a0f4766; BYTE $0x0d // pinsrb xmm10, byte [r11 + r12 + 27], 13 + QUAD $0x1b2b54203a0f4766; BYTE $0x0e // pinsrb xmm10, byte [r11 + r13 + 27], 14 + QUAD $0x1b3b54203a0f4766; BYTE $0x0f // pinsrb xmm10, byte [r11 + r15 + 27], 15 + LONG $0xde0f4566; BYTE $0xe8 // pmaxub xmm13, xmm8 + LONG $0x740f4566; BYTE $0xe8 // pcmpeqb xmm13, xmm8 + QUAD $0x000110addb0f4466; BYTE $0x00 // pand xmm13, oword 272[rbp] /* [rip + .LCPI11_17] */ + LONG $0xde0f4566; BYTE $0xd0 // pmaxub xmm10, xmm8 + LONG $0x740f4566; BYTE $0xd0 // pcmpeqb xmm10, xmm8 + QUAD $0x00012095db0f4466; BYTE $0x00 // pand xmm10, oword 288[rbp] /* [rip + .LCPI11_18] */ + LONG $0xeb0f4566; BYTE $0xd5 // por xmm10, xmm13 + LONG $0xeb0f4566; BYTE $0xd4 // por xmm10, xmm12 + QUAD $0x1c135c203a0f4766; BYTE $0x03 // pinsrb xmm11, byte [r11 + r10 + 28], 3 + QUAD $0x1d1374203a0f4766; BYTE $0x03 // pinsrb xmm14, byte [r11 + r10 + 29], 3 + QUAD $0x1e134c203a0f4366; BYTE $0x03 // pinsrb xmm1, byte [r11 + r10 + 30], 3 + QUAD $0x1f1344203a0f4366; BYTE $0x03 // pinsrb xmm0, byte [r11 + r10 + 31], 3 + QUAD $0x1c335c203a0f4766; BYTE $0x04 // pinsrb xmm11, byte [r11 + r14 + 28], 4 + QUAD $0x1d3374203a0f4766; BYTE $0x04 // pinsrb xmm14, byte [r11 + r14 + 29], 4 + QUAD $0x1e334c203a0f4366; BYTE $0x04 // pinsrb xmm1, byte [r11 + r14 + 30], 4 + QUAD $0x1f3344203a0f4366; BYTE $0x04 // pinsrb xmm0, byte [r11 + r14 + 31], 4 + WORD $0x8948; BYTE $0xd8 // mov rax, rbx + QUAD $0x1c1b5c203a0f4566; BYTE $0x05 // pinsrb xmm11, byte [r11 + rbx + 28], 5 + QUAD $0x1d1b74203a0f4566; BYTE $0x05 // pinsrb xmm14, byte [r11 + rbx + 29], 5 + QUAD $0x1e1b4c203a0f4166; BYTE $0x05 // pinsrb xmm1, byte [r11 + rbx + 30], 5 + QUAD $0x1f1b44203a0f4166; BYTE $0x05 // pinsrb xmm0, byte [r11 + rbx + 31], 5 + WORD $0x8948; BYTE $0xf8 // mov rax, rdi + QUAD $0x1c3b5c203a0f4566; BYTE $0x06 // pinsrb xmm11, byte [r11 + rdi + 28], 6 + QUAD $0x1d3b74203a0f4566; BYTE $0x06 // pinsrb xmm14, byte [r11 + rdi + 29], 6 + QUAD $0x1e3b4c203a0f4166; BYTE $0x06 // pinsrb xmm1, byte [r11 + rdi + 30], 6 + QUAD $0x1f3b44203a0f4166; BYTE $0x06 // pinsrb xmm0, byte [r11 + rdi + 31], 6 + QUAD $0x00000088249c8b48 // mov rbx, qword [rsp + 136] + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x1c0b5c203a0f4566; BYTE $0x07 // pinsrb xmm11, byte [r11 + rcx + 28], 7 + QUAD $0x1d0b74203a0f4566; BYTE $0x07 // pinsrb xmm14, byte [r11 + rcx + 29], 7 + QUAD $0x1e0b4c203a0f4166; BYTE $0x07 // pinsrb xmm1, byte [r11 + rcx + 30], 7 + QUAD $0x1f0b44203a0f4166; BYTE $0x07 // pinsrb xmm0, byte [r11 + rcx + 31], 7 + WORD $0x8948; BYTE $0xf0 // mov rax, rsi + QUAD $0x1c335c203a0f4566; BYTE $0x08 // pinsrb xmm11, byte [r11 + rsi + 28], 8 + QUAD $0x1d3374203a0f4566; BYTE $0x08 // pinsrb xmm14, byte [r11 + rsi + 29], 8 + QUAD $0x1e334c203a0f4166; BYTE $0x08 // pinsrb xmm1, byte [r11 + rsi + 30], 8 + QUAD $0x1f3344203a0f4166; BYTE $0x08 // pinsrb xmm0, byte [r11 + rsi + 31], 8 + LONG $0x24448b48; BYTE $0x68 // mov rax, qword [rsp + 104] + QUAD $0x1c035c203a0f4566; BYTE $0x09 // pinsrb xmm11, byte [r11 + rax + 28], 9 + QUAD $0x1d0374203a0f4566; BYTE $0x09 // pinsrb xmm14, byte [r11 + rax + 29], 9 + QUAD $0x1e034c203a0f4166; BYTE $0x09 // pinsrb xmm1, byte [r11 + rax + 30], 9 + QUAD $0x1f0344203a0f4166; BYTE $0x09 // pinsrb xmm0, byte [r11 + rax + 31], 9 + WORD $0x894c; BYTE $0xc8 // mov rax, r9 + QUAD $0x1c0b5c203a0f4766; BYTE $0x0a // pinsrb xmm11, byte [r11 + r9 + 28], 10 + QUAD $0x1d0b74203a0f4766; BYTE $0x0a // pinsrb xmm14, byte [r11 + r9 + 29], 10 + QUAD $0x1e0b4c203a0f4366; BYTE $0x0a // pinsrb xmm1, byte [r11 + r9 + 30], 10 + QUAD $0x1f0b44203a0f4366; BYTE $0x0a // pinsrb xmm0, byte [r11 + r9 + 31], 10 + WORD $0x894c; BYTE $0xc0 // mov rax, r8 + QUAD $0x1c035c203a0f4766; BYTE $0x0b // pinsrb xmm11, byte [r11 + r8 + 28], 11 + QUAD $0x1d0374203a0f4766; BYTE $0x0b // pinsrb xmm14, byte [r11 + r8 + 29], 11 + QUAD $0x1e034c203a0f4366; BYTE $0x0b // pinsrb xmm1, byte [r11 + r8 + 30], 11 + QUAD $0x1f0344203a0f4366; BYTE $0x0b // pinsrb xmm0, byte [r11 + r8 + 31], 11 + QUAD $0x1c135c203a0f4566; BYTE $0x0c // pinsrb xmm11, byte [r11 + rdx + 28], 12 + QUAD $0x1d1374203a0f4566; BYTE $0x0c // pinsrb xmm14, byte [r11 + rdx + 29], 12 + QUAD $0x1e134c203a0f4166; BYTE $0x0c // pinsrb xmm1, byte [r11 + rdx + 30], 12 + QUAD $0x1f1344203a0f4166; BYTE $0x0c // pinsrb xmm0, byte [r11 + rdx + 31], 12 + WORD $0x894c; BYTE $0xe0 // mov rax, r12 + QUAD $0x1c235c203a0f4766; BYTE $0x0d // pinsrb xmm11, byte [r11 + r12 + 28], 13 + QUAD $0x1d2374203a0f4766; BYTE $0x0d // pinsrb xmm14, byte [r11 + r12 + 29], 13 + QUAD $0x1e234c203a0f4366; BYTE $0x0d // pinsrb xmm1, byte [r11 + r12 + 30], 13 + QUAD $0x1f2344203a0f4366; BYTE $0x0d // pinsrb xmm0, byte [r11 + r12 + 31], 13 + WORD $0x894c; BYTE $0xe8 // mov rax, r13 + QUAD $0x1c2b5c203a0f4766; BYTE $0x0e // pinsrb xmm11, byte [r11 + r13 + 28], 14 + QUAD $0x1d2b74203a0f4766; BYTE $0x0e // pinsrb xmm14, byte [r11 + r13 + 29], 14 + QUAD $0x1e2b4c203a0f4366; BYTE $0x0e // pinsrb xmm1, byte [r11 + r13 + 30], 14 + QUAD $0x1f2b44203a0f4366; BYTE $0x0e // pinsrb xmm0, byte [r11 + r13 + 31], 14 + WORD $0x894c; BYTE $0xf8 // mov rax, r15 + QUAD $0x1c3b5c203a0f4766; BYTE $0x0f // pinsrb xmm11, byte [r11 + r15 + 28], 15 + QUAD $0x1d3b74203a0f4766; BYTE $0x0f // pinsrb xmm14, byte [r11 + r15 + 29], 15 + QUAD $0x1e3b4c203a0f4366; BYTE $0x0f // pinsrb xmm1, byte [r11 + r15 + 30], 15 + QUAD $0x1f3b44203a0f4366; BYTE $0x0f // pinsrb xmm0, byte [r11 + r15 + 31], 15 + LONG $0xde0f4566; BYTE $0xd8 // pmaxub xmm11, xmm8 + LONG $0x740f4566; BYTE $0xd8 // pcmpeqb xmm11, xmm8 + LONG $0xdb0f4466; BYTE $0xdd // pand xmm11, xmm5 + LONG $0xde0f4566; BYTE $0xf0 // pmaxub xmm14, xmm8 + LONG $0x740f4566; BYTE $0xf0 // pcmpeqb xmm14, xmm8 + LONG $0xdb0f4566; BYTE $0xf7 // pand xmm14, xmm15 + LONG $0xeb0f4566; BYTE $0xf3 // por xmm14, xmm11 + LONG $0xde0f4166; BYTE $0xc8 // pmaxub xmm1, xmm8 + LONG $0x740f4166; BYTE $0xc8 // pcmpeqb xmm1, xmm8 + LONG $0xcedb0f66 // pand xmm1, xmm6 + LONG $0xeb0f4166; BYTE $0xce // por xmm1, xmm14 + LONG $0xeb0f4166; BYTE $0xca // por xmm1, xmm10 + LONG $0xde0f4166; BYTE $0xc0 // pmaxub xmm0, xmm8 + LONG $0x740f4166; BYTE $0xc0 // pcmpeqb xmm0, xmm8 + LONG $0xc3db0f66 // pand xmm0, xmm3 + LONG $0xc1eb0f66 // por xmm0, xmm1 + LONG $0xca6f0f66 // movdqa xmm1, xmm2 + LONG $0xc8600f66 // punpcklbw xmm1, xmm0 + QUAD $0x0000e024ac6f0f66; BYTE $0x00 // movdqa xmm5, oword [rsp + 224] + LONG $0xdd6f0f66 // movdqa xmm3, xmm5 + QUAD $0x0000d024b46f0f66; BYTE $0x00 // movdqa xmm6, oword [rsp + 208] + LONG $0xde600f66 // punpcklbw xmm3, xmm6 + LONG $0xe36f0f66 // movdqa xmm4, xmm3 + LONG $0xe1610f66 // punpcklwd xmm4, xmm1 + LONG $0xd9690f66 // punpckhwd xmm3, xmm1 + LONG $0xd0680f66 // punpckhbw xmm2, xmm0 + LONG $0xee680f66 // punpckhbw xmm5, xmm6 + LONG $0xc56f0f66 // movdqa xmm0, xmm5 + LONG $0xc2610f66 // punpcklwd xmm0, xmm2 + LONG $0xea690f66 // punpckhwd xmm5, xmm2 + QUAD $0x00000090248c8b48 // mov rcx, qword [rsp + 144] + LONG $0x6c7f0ff3; WORD $0x308b // movdqu oword [rbx + 4*rcx + 48], xmm5 + LONG $0x447f0ff3; WORD $0x208b // movdqu oword [rbx + 4*rcx + 32], xmm0 + LONG $0x5c7f0ff3; WORD $0x108b // movdqu oword [rbx + 4*rcx + 16], xmm3 + LONG $0x247f0ff3; BYTE $0x8b // movdqu oword [rbx + 4*rcx], xmm4 + LONG $0x10c18348 // add rcx, 16 + WORD $0x8948; BYTE $0xc8 // mov rax, rcx + QUAD $0x000000b8248c3b48 // cmp rcx, qword [rsp + 184] + JNE LBB11_226 + QUAD $0x00000100248c8b48 // mov rcx, qword [rsp + 256] + QUAD $0x000000b8248c3b48 // cmp rcx, qword [rsp + 184] + QUAD $0x0000009824bc8b4c // mov r15, qword [rsp + 152] + LONG $0x246c8a44; BYTE $0x08 // mov r13b, byte [rsp + 8] + QUAD $0x00000108249c8b48 // mov rbx, qword [rsp + 264] + JNE LBB11_160 + JMP LBB11_164 diff --git a/arrow/compute/internal/kernels/scalar_comparisons.go b/arrow/compute/internal/kernels/scalar_comparisons.go index aed44da69..4dfe00cc5 100644 --- a/arrow/compute/internal/kernels/scalar_comparisons.go +++ b/arrow/compute/internal/kernels/scalar_comparisons.go @@ -55,24 +55,28 @@ func comparePrimitiveArrayArray[T arrow.FixedWidthType](op cmpFn[T, T]) binaryKe left = arrow.GetData[T](leftBytes) right = arrow.GetData[T](rightBytes) nvals = len(left) - nbatches = nvals / batchSize tmpOutput [batchSize]uint32 ) tmpOutSlice := tmpOutput[:] if prefix := offset % 8; prefix != 0 { - vals := 8 - prefix + vals := min(nvals, 8-prefix) op(left[:vals], right[:vals], tmpOutSlice[:vals]) left, right = left[vals:], right[vals:] + nvals -= vals for i, v := range tmpOutSlice[:vals] { bitutil.SetBitTo(out, prefix+i, v != 0) } + if nvals == 0 { + return + } out = out[1:] } + nbatches := nvals / batchSize for j := 0; j < nbatches; j++ { - op(left, right, tmpOutSlice) + op(left[:batchSize], right[:batchSize], tmpOutSlice) left, right = left[batchSize:], right[batchSize:] packBits(tmpOutput, out) out = out[batchSize/8:] @@ -93,22 +97,26 @@ func comparePrimitiveArrayScalar[T arrow.FixedWidthType](op cmpScalarRight[T, T] left = arrow.GetData[T](leftBytes) rightVal = *(*T)(unsafe.Pointer(&rightBytes[0])) nvals = len(left) - nbatches = nvals / batchSize tmpOutput [batchSize]uint32 ) tmpOutSlice := tmpOutput[:] if prefix := offset % 8; prefix != 0 { - vals := 8 - prefix + vals := min(nvals, 8-prefix) op(left[:vals], rightVal, tmpOutSlice[:vals]) left = left[vals:] + nvals -= vals for i, v := range tmpOutSlice[:vals] { bitutil.SetBitTo(out, prefix+i, v != 0) } + if nvals == 0 { + return + } out = out[1:] } + nbatches := nvals / batchSize for j := 0; j < nbatches; j++ { op(left[:batchSize], rightVal, tmpOutSlice) left = left[batchSize:] @@ -132,22 +140,26 @@ func comparePrimitiveScalarArray[T arrow.FixedWidthType](op cmpScalarLeft[T, T]) right = arrow.GetData[T](rightBytes) nvals = len(right) - nbatches = nvals / batchSize tmpOutput [batchSize]uint32 ) tmpOutSlice := tmpOutput[:] if prefix := offset % 8; prefix != 0 { - vals := 8 - prefix + vals := min(nvals, 8-prefix) op(leftVal, right[:vals], tmpOutSlice[:vals]) right = right[vals:] + nvals -= vals for i, v := range tmpOutSlice[:vals] { bitutil.SetBitTo(out, prefix+i, v != 0) } + if nvals == 0 { + return + } out = out[1:] } + nbatches := nvals / batchSize for j := 0; j < nbatches; j++ { op(leftVal, right[:batchSize], tmpOutSlice) right = right[batchSize:] diff --git a/arrow/compute/internal/kernels/scalar_comparisons_test.go b/arrow/compute/internal/kernels/scalar_comparisons_test.go new file mode 100644 index 000000000..b1fc992f6 --- /dev/null +++ b/arrow/compute/internal/kernels/scalar_comparisons_test.go @@ -0,0 +1,119 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +//go:build go1.18 + +package kernels + +import ( + "bytes" + "fmt" + "testing" + + "github.com/apache/arrow-go/v18/arrow" + "github.com/apache/arrow-go/v18/arrow/bitutil" +) + +func TestPrimitiveComparisonsWithOutputOffset(t *testing.T) { + const maxLength = 65 + + left := make([]int32, maxLength) + right := make([]int32, maxLength) + for i := range left { + left[i] = int32((i*7 + 1) % 11) + right[i] = int32((i*5 + 3) % 11) + } + + type operation struct { + op CompareOperator + eval func(int32, int32) bool + } + operations := []operation{ + {CmpEQ, func(l, r int32) bool { return l == r }}, + {CmpNE, func(l, r int32) bool { return l != r }}, + {CmpGT, func(l, r int32) bool { return l > r }}, + {CmpGE, func(l, r int32) bool { return l >= r }}, + } + // The assembly wrappers require non-empty slices to obtain data pointers. + implementations := []struct { + name string + minLength int + makeKernel func(CompareOperator) *CompareData + }{ + {"pure_go", 0, func(op CompareOperator) *CompareData { + return genGoCompareKernel(getCmpOp[int32](op)) + }}, + {"dispatch", 1, func(op CompareOperator) *CompareData { + return genCompareKernel[int32](op) + }}, + } + + leftBytes := arrow.Int32Traits.CastToBytes(left) + rightBytes := arrow.Int32Traits.CastToBytes(right) + leftScalar := int32(6) + rightScalar := int32(4) + leftScalarBytes := arrow.Int32Traits.CastToBytes([]int32{leftScalar}) + rightScalarBytes := arrow.Int32Traits.CastToBytes([]int32{rightScalar}) + + for _, implementation := range implementations { + t.Run(implementation.name, func(t *testing.T) { + for _, operation := range operations { + t.Run(operation.op.String(), func(t *testing.T) { + cmp := implementation.makeKernel(operation.op) + for _, shape := range []string{"array_array", "array_scalar", "scalar_array"} { + t.Run(shape, func(t *testing.T) { + for offset := 0; offset < 8; offset++ { + t.Run(fmt.Sprintf("offset_%d", offset), func(t *testing.T) { + for length := implementation.minLength; length <= maxLength; length++ { + out := bytes.Repeat([]byte{0xa5}, int(bitutil.BytesForBits(int64(offset+length)))) + expected := append([]byte(nil), out...) + + for i := 0; i < length; i++ { + var result bool + switch shape { + case "array_array": + result = operation.eval(left[i], right[i]) + case "array_scalar": + result = operation.eval(left[i], rightScalar) + case "scalar_array": + result = operation.eval(leftScalar, right[i]) + } + bitutil.SetBitTo(expected, offset+i, result) + } + + switch shape { + case "array_array": + cmp.funcAA(leftBytes[:length*4], rightBytes[:length*4], out, offset) + case "array_scalar": + cmp.funcAS(leftBytes[:length*4], rightScalarBytes, out, offset) + case "scalar_array": + cmp.funcSA(leftScalarBytes, rightBytes[:length*4], out, offset) + } + + if !bytes.Equal(expected, out) { + t.Fatalf("length %d: expected %08b, got %08b", length, expected, out) + } + } + }) + } + }) + } + }) + } + }) + } +}